Merge pull request #95 from Noir97/master

add demo, rearrange code
This commit is contained in:
Noir97
2023-10-15 23:03:55 +08:00
committed by GitHub
9 changed files with 731 additions and 3636 deletions

View File

@@ -1,346 +0,0 @@
{
"cells": [
{
"cell_type": "code",
"execution_count": 1,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"[2023-09-11 10:40:44,355] [INFO] [real_accelerator.py:158:get_accelerator] Setting ds_accelerator to cuda (auto detect)\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"/opt/conda/lib/python3.9/site-packages/apex/pyprof/__init__.py:5: FutureWarning: pyprof will be removed by the end of June, 2022\n",
" warnings.warn(\"pyprof will be removed by the end of June, 2022\", FutureWarning)\n"
]
}
],
"source": []
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Load Model (Pick one according the model from the following blocks)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"#### 1. **FInGPT v3.1** based on ChatGLM2, runable on 1 * RTX 3090"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [
{
"data": {
"application/json": {
"ascii": false,
"bar_format": null,
"colour": null,
"elapsed": 0.006453275680541992,
"initial": 0,
"n": 0,
"ncols": null,
"nrows": null,
"postfix": null,
"prefix": "Loading checkpoint shards",
"rate": null,
"total": 7,
"unit": "it",
"unit_divisor": 1000,
"unit_scale": false
},
"application/vnd.jupyter.widget-view+json": {
"model_id": "ec84227239134d398cb009c6c54a9330",
"version_major": 2,
"version_minor": 0
},
"text/plain": [
"Loading checkpoint shards: 0%| | 0/7 [00:00<?, ?it/s]"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"# v3.1\n"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"#### 2. **FinGPT v3.2** based on Llama2, runable on 1 * A 100 and also runable on 1 * RTX 3090 as long as `load_in_8bit = True` is set in Line 8, but the speed is slower"
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {},
"outputs": [
{
"data": {
"application/json": {
"ascii": false,
"bar_format": null,
"colour": null,
"elapsed": 0.004700183868408203,
"initial": 0,
"n": 0,
"ncols": null,
"nrows": null,
"postfix": null,
"prefix": "Loading checkpoint shards",
"rate": null,
"total": 2,
"unit": "it",
"unit_divisor": 1000,
"unit_scale": false
},
"application/vnd.jupyter.widget-view+json": {
"model_id": "e093e3e5f32f46bf85aa35f8b2009f6f",
"version_major": 2,
"version_minor": 0
},
"text/plain": [
"Loading checkpoint shards: 0%| | 0/2 [00:00<?, ?it/s]"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": []
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Test"
]
},
{
"cell_type": "code",
"execution_count": 8,
"metadata": {},
"outputs": [],
"source": [
"import os\n",
"\n",
"os.environ['PATH'] = '/root/.conda/envs/torch2/bin:'\n",
"\n",
"batch_size = 4\n",
"tokenizer.return_token_type_ids=False\n"
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"\n",
"Prompt example:\n",
"Instruction: What is the sentiment of this news? Please choose an answer from {negative/neutral/positive}.\n",
"Input: L&T has also made a commitment to redeem the remaining shares by the end of 2011 .\n",
"Answer: \n",
"\n",
"\n",
"Total len: 1212. Batchsize: 8. Total steps: 152\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
" 0%| | 0/152 [00:00<?, ?it/s]\n"
]
},
{
"ename": "ValueError",
"evalue": "The following `model_kwargs` are not used by the model: ['token_type_ids'] (note: typos in the generate arguments will also show up in this list)",
"output_type": "error",
"traceback": [
"\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
"\u001b[0;31mValueError\u001b[0m Traceback (most recent call last)",
"Cell \u001b[0;32mIn[4], line 2\u001b[0m\n\u001b[1;32m 1\u001b[0m \u001b[38;5;66;03m# FPB\u001b[39;00m\n\u001b[0;32m----> 2\u001b[0m res \u001b[38;5;241m=\u001b[39m \u001b[43mtest_fpb\u001b[49m\u001b[43m(\u001b[49m\u001b[43mmodel\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mtokenizer\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mbatch_size\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43m \u001b[49m\u001b[43mbatch_size\u001b[49m\u001b[43m)\u001b[49m\n",
"File \u001b[0;32m/workspace/linqing.wn/FinGPT/fingpt/FinGPT_Omni/benchmarks/fpb.py:64\u001b[0m, in \u001b[0;36mtest_fpb\u001b[0;34m(model, tokenizer, batch_size, prompt_fun)\u001b[0m\n\u001b[1;32m 62\u001b[0m \u001b[38;5;28;01mfor\u001b[39;00m k \u001b[38;5;129;01min\u001b[39;00m tokens\u001b[38;5;241m.\u001b[39mkeys():\n\u001b[1;32m 63\u001b[0m tokens[k] \u001b[38;5;241m=\u001b[39m tokens[k]\u001b[38;5;241m.\u001b[39mcuda()\n\u001b[0;32m---> 64\u001b[0m res \u001b[38;5;241m=\u001b[39m \u001b[43mmodel\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mgenerate\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mtokens\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mmax_length\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;241;43m512\u001b[39;49m\u001b[43m)\u001b[49m\n\u001b[1;32m 65\u001b[0m res_sentences \u001b[38;5;241m=\u001b[39m [tokenizer\u001b[38;5;241m.\u001b[39mdecode(i) \u001b[38;5;28;01mfor\u001b[39;00m i \u001b[38;5;129;01min\u001b[39;00m res]\n\u001b[1;32m 66\u001b[0m out_text \u001b[38;5;241m=\u001b[39m [o\u001b[38;5;241m.\u001b[39msplit(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mAnswer: \u001b[39m\u001b[38;5;124m\"\u001b[39m)[\u001b[38;5;241m1\u001b[39m] \u001b[38;5;28;01mfor\u001b[39;00m o \u001b[38;5;129;01min\u001b[39;00m res_sentences]\n",
"File \u001b[0;32m/opt/conda/lib/python3.9/site-packages/peft/peft_model.py:975\u001b[0m, in \u001b[0;36mPeftModelForCausalLM.generate\u001b[0;34m(self, **kwargs)\u001b[0m\n\u001b[1;32m 973\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mbase_model\u001b[38;5;241m.\u001b[39mgeneration_config \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mgeneration_config\n\u001b[1;32m 974\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[0;32m--> 975\u001b[0m outputs \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mbase_model\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mgenerate\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 976\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m:\n\u001b[1;32m 977\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mbase_model\u001b[38;5;241m.\u001b[39mprepare_inputs_for_generation \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mbase_model_prepare_inputs_for_generation\n",
"File \u001b[0;32m/opt/conda/lib/python3.9/site-packages/torch/autograd/grad_mode.py:27\u001b[0m, in \u001b[0;36m_DecoratorContextManager.__call__.<locals>.decorate_context\u001b[0;34m(*args, **kwargs)\u001b[0m\n\u001b[1;32m 24\u001b[0m \u001b[38;5;129m@functools\u001b[39m\u001b[38;5;241m.\u001b[39mwraps(func)\n\u001b[1;32m 25\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21mdecorate_context\u001b[39m(\u001b[38;5;241m*\u001b[39margs, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs):\n\u001b[1;32m 26\u001b[0m \u001b[38;5;28;01mwith\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mclone():\n\u001b[0;32m---> 27\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mfunc\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n",
"File \u001b[0;32m/opt/conda/lib/python3.9/site-packages/transformers/generation/utils.py:1423\u001b[0m, in \u001b[0;36mGenerationMixin.generate\u001b[0;34m(self, inputs, generation_config, logits_processor, stopping_criteria, prefix_allowed_tokens_fn, synced_gpus, assistant_model, streamer, negative_prompt_ids, negative_prompt_attention_mask, **kwargs)\u001b[0m\n\u001b[1;32m 1421\u001b[0m model_kwargs \u001b[38;5;241m=\u001b[39m generation_config\u001b[38;5;241m.\u001b[39mupdate(\u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs) \u001b[38;5;66;03m# All unused kwargs must be model kwargs\u001b[39;00m\n\u001b[1;32m 1422\u001b[0m generation_config\u001b[38;5;241m.\u001b[39mvalidate()\n\u001b[0;32m-> 1423\u001b[0m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_validate_model_kwargs\u001b[49m\u001b[43m(\u001b[49m\u001b[43mmodel_kwargs\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mcopy\u001b[49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 1425\u001b[0m \u001b[38;5;66;03m# 2. Set generation parameters if not already defined\u001b[39;00m\n\u001b[1;32m 1426\u001b[0m logits_processor \u001b[38;5;241m=\u001b[39m logits_processor \u001b[38;5;28;01mif\u001b[39;00m logits_processor \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m \u001b[38;5;28;01melse\u001b[39;00m LogitsProcessorList()\n",
"File \u001b[0;32m/opt/conda/lib/python3.9/site-packages/transformers/generation/utils.py:1243\u001b[0m, in \u001b[0;36mGenerationMixin._validate_model_kwargs\u001b[0;34m(self, model_kwargs)\u001b[0m\n\u001b[1;32m 1240\u001b[0m unused_model_args\u001b[38;5;241m.\u001b[39mappend(key)\n\u001b[1;32m 1242\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m unused_model_args:\n\u001b[0;32m-> 1243\u001b[0m \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mValueError\u001b[39;00m(\n\u001b[1;32m 1244\u001b[0m \u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mThe following `model_kwargs` are not used by the model: \u001b[39m\u001b[38;5;132;01m{\u001b[39;00munused_model_args\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m (note: typos in the\u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m 1245\u001b[0m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m generate arguments will also show up in this list)\u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m 1246\u001b[0m )\n",
"\u001b[0;31mValueError\u001b[0m: The following `model_kwargs` are not used by the model: ['token_type_ids'] (note: typos in the generate arguments will also show up in this list)"
]
}
],
"source": [
"# FPB\n",
"res = test_fpb(model, tokenizer, batch_size = batch_size)"
]
},
{
"cell_type": "code",
"execution_count": 9,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"\n",
"Prompt example:\n",
"Instruction: What is the sentiment of this tweet? Please choose an answer from {negative/neutral/positive}.\n",
"Input: This $BBBY stock options trade would have more than doubled your money https://t.co/Oa0loiRIJL via @TheStreet\n",
"Answer: \n",
"\n",
"\n",
"Total len: 275. Batchsize: 4. Total steps: 69\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
" 0%| | 0/69 [00:00<?, ?it/s]\n"
]
},
{
"ename": "ValueError",
"evalue": "The following `model_kwargs` are not used by the model: ['token_type_ids'] (note: typos in the generate arguments will also show up in this list)",
"output_type": "error",
"traceback": [
"\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
"\u001b[0;31mValueError\u001b[0m Traceback (most recent call last)",
"Cell \u001b[0;32mIn[9], line 2\u001b[0m\n\u001b[1;32m 1\u001b[0m \u001b[38;5;66;03m# FiQA\u001b[39;00m\n\u001b[0;32m----> 2\u001b[0m res \u001b[38;5;241m=\u001b[39m \u001b[43mtest_fiqa\u001b[49m\u001b[43m(\u001b[49m\u001b[43mmodel\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mtokenizer\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mprompt_fun\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43m \u001b[49m\u001b[43madd_instructions\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mbatch_size\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43m \u001b[49m\u001b[43mbatch_size\u001b[49m\u001b[43m)\u001b[49m\n",
"File \u001b[0;32m/workspace/linqing.wn/FinGPT/fingpt/FinGPT_Omni/benchmarks/fiqa.py:69\u001b[0m, in \u001b[0;36mtest_fiqa\u001b[0;34m(model, tokenizer, batch_size, prompt_fun)\u001b[0m\n\u001b[1;32m 66\u001b[0m \u001b[38;5;28;01mfor\u001b[39;00m k \u001b[38;5;129;01min\u001b[39;00m tokens\u001b[38;5;241m.\u001b[39mkeys():\n\u001b[1;32m 67\u001b[0m tokens[k] \u001b[38;5;241m=\u001b[39m tokens[k]\u001b[38;5;241m.\u001b[39mcuda()\n\u001b[0;32m---> 69\u001b[0m res \u001b[38;5;241m=\u001b[39m \u001b[43mmodel\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mgenerate\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mtokens\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mmax_length\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;241;43m512\u001b[39;49m\u001b[43m)\u001b[49m\n\u001b[1;32m 70\u001b[0m res_sentences \u001b[38;5;241m=\u001b[39m [tokenizer\u001b[38;5;241m.\u001b[39mdecode(i) \u001b[38;5;28;01mfor\u001b[39;00m i \u001b[38;5;129;01min\u001b[39;00m res]\n\u001b[1;32m 71\u001b[0m \u001b[38;5;28mprint\u001b[39m(\u001b[38;5;124mf\u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;132;01m{\u001b[39;00mi\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m: \u001b[39m\u001b[38;5;132;01m{\u001b[39;00mres_sentences\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m'\u001b[39m)\n",
"File \u001b[0;32m/opt/conda/lib/python3.9/site-packages/peft/peft_model.py:975\u001b[0m, in \u001b[0;36mPeftModelForCausalLM.generate\u001b[0;34m(self, **kwargs)\u001b[0m\n\u001b[1;32m 973\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mbase_model\u001b[38;5;241m.\u001b[39mgeneration_config \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mgeneration_config\n\u001b[1;32m 974\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[0;32m--> 975\u001b[0m outputs \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mbase_model\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mgenerate\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 976\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m:\n\u001b[1;32m 977\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mbase_model\u001b[38;5;241m.\u001b[39mprepare_inputs_for_generation \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mbase_model_prepare_inputs_for_generation\n",
"File \u001b[0;32m/opt/conda/lib/python3.9/site-packages/torch/autograd/grad_mode.py:27\u001b[0m, in \u001b[0;36m_DecoratorContextManager.__call__.<locals>.decorate_context\u001b[0;34m(*args, **kwargs)\u001b[0m\n\u001b[1;32m 24\u001b[0m \u001b[38;5;129m@functools\u001b[39m\u001b[38;5;241m.\u001b[39mwraps(func)\n\u001b[1;32m 25\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21mdecorate_context\u001b[39m(\u001b[38;5;241m*\u001b[39margs, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs):\n\u001b[1;32m 26\u001b[0m \u001b[38;5;28;01mwith\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mclone():\n\u001b[0;32m---> 27\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mfunc\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n",
"File \u001b[0;32m/opt/conda/lib/python3.9/site-packages/transformers/generation/utils.py:1423\u001b[0m, in \u001b[0;36mGenerationMixin.generate\u001b[0;34m(self, inputs, generation_config, logits_processor, stopping_criteria, prefix_allowed_tokens_fn, synced_gpus, assistant_model, streamer, negative_prompt_ids, negative_prompt_attention_mask, **kwargs)\u001b[0m\n\u001b[1;32m 1421\u001b[0m model_kwargs \u001b[38;5;241m=\u001b[39m generation_config\u001b[38;5;241m.\u001b[39mupdate(\u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs) \u001b[38;5;66;03m# All unused kwargs must be model kwargs\u001b[39;00m\n\u001b[1;32m 1422\u001b[0m generation_config\u001b[38;5;241m.\u001b[39mvalidate()\n\u001b[0;32m-> 1423\u001b[0m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_validate_model_kwargs\u001b[49m\u001b[43m(\u001b[49m\u001b[43mmodel_kwargs\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mcopy\u001b[49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 1425\u001b[0m \u001b[38;5;66;03m# 2. Set generation parameters if not already defined\u001b[39;00m\n\u001b[1;32m 1426\u001b[0m logits_processor \u001b[38;5;241m=\u001b[39m logits_processor \u001b[38;5;28;01mif\u001b[39;00m logits_processor \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m \u001b[38;5;28;01melse\u001b[39;00m LogitsProcessorList()\n",
"File \u001b[0;32m/opt/conda/lib/python3.9/site-packages/transformers/generation/utils.py:1243\u001b[0m, in \u001b[0;36mGenerationMixin._validate_model_kwargs\u001b[0;34m(self, model_kwargs)\u001b[0m\n\u001b[1;32m 1240\u001b[0m unused_model_args\u001b[38;5;241m.\u001b[39mappend(key)\n\u001b[1;32m 1242\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m unused_model_args:\n\u001b[0;32m-> 1243\u001b[0m \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mValueError\u001b[39;00m(\n\u001b[1;32m 1244\u001b[0m \u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mThe following `model_kwargs` are not used by the model: \u001b[39m\u001b[38;5;132;01m{\u001b[39;00munused_model_args\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m (note: typos in the\u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m 1245\u001b[0m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m generate arguments will also show up in this list)\u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m 1246\u001b[0m )\n",
"\u001b[0;31mValueError\u001b[0m: The following `model_kwargs` are not used by the model: ['token_type_ids'] (note: typos in the generate arguments will also show up in this list)"
]
}
],
"source": [
"# FiQA\n",
"res = test_fiqa(model, tokenizer, prompt_fun = add_instructions, batch_size = batch_size)"
]
},
{
"cell_type": "code",
"execution_count": 7,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"\n",
"Prompt example:\n",
"Instruction: What is the sentiment of this tweet? Please choose an answer from {negative/neutral/positive}.\n",
"Input: $ALLY - Ally Financial pulls outlook https://t.co/G9Zdi1boy5\n",
"Answer: \n",
"\n",
"\n",
"Total len: 2388. Batchsize: 8. Total steps: 299\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
" 27%|██▋ | 80/299 [00:48<02:13, 1.64it/s]\n"
]
},
{
"ename": "KeyboardInterrupt",
"evalue": "",
"output_type": "error",
"traceback": [
"\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
"\u001b[0;31mKeyboardInterrupt\u001b[0m Traceback (most recent call last)",
"Cell \u001b[0;32mIn[7], line 2\u001b[0m\n\u001b[1;32m 1\u001b[0m \u001b[38;5;66;03m# TFNS\u001b[39;00m\n\u001b[0;32m----> 2\u001b[0m res \u001b[38;5;241m=\u001b[39m \u001b[43mtest_tfns\u001b[49m\u001b[43m(\u001b[49m\u001b[43mmodel\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mtokenizer\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mbatch_size\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43m \u001b[49m\u001b[43mbatch_size\u001b[49m\u001b[43m)\u001b[49m\n",
"File \u001b[0;32m/workspace/linqing.wn/FinGPT/fingpt/FinGPT_Omni/benchmarks/tfns.py:63\u001b[0m, in \u001b[0;36mtest_tfns\u001b[0;34m(model, tokenizer, batch_size, prompt_fun)\u001b[0m\n\u001b[1;32m 61\u001b[0m \u001b[38;5;28;01mfor\u001b[39;00m k \u001b[38;5;129;01min\u001b[39;00m tokens\u001b[38;5;241m.\u001b[39mkeys():\n\u001b[1;32m 62\u001b[0m tokens[k] \u001b[38;5;241m=\u001b[39m tokens[k]\u001b[38;5;241m.\u001b[39mcuda()\n\u001b[0;32m---> 63\u001b[0m res \u001b[38;5;241m=\u001b[39m \u001b[43mmodel\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mgenerate\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mtokens\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mmax_length\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;241;43m512\u001b[39;49m\u001b[43m)\u001b[49m\n\u001b[1;32m 64\u001b[0m res_sentences \u001b[38;5;241m=\u001b[39m [tokenizer\u001b[38;5;241m.\u001b[39mdecode(i) \u001b[38;5;28;01mfor\u001b[39;00m i \u001b[38;5;129;01min\u001b[39;00m res]\n\u001b[1;32m 65\u001b[0m out_text \u001b[38;5;241m=\u001b[39m [o\u001b[38;5;241m.\u001b[39msplit(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mAnswer: \u001b[39m\u001b[38;5;124m\"\u001b[39m)[\u001b[38;5;241m1\u001b[39m] \u001b[38;5;28;01mfor\u001b[39;00m o \u001b[38;5;129;01min\u001b[39;00m res_sentences]\n",
"File \u001b[0;32m/opt/conda/lib/python3.9/site-packages/peft/peft_model.py:975\u001b[0m, in \u001b[0;36mPeftModelForCausalLM.generate\u001b[0;34m(self, **kwargs)\u001b[0m\n\u001b[1;32m 973\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mbase_model\u001b[38;5;241m.\u001b[39mgeneration_config \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mgeneration_config\n\u001b[1;32m 974\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[0;32m--> 975\u001b[0m outputs \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mbase_model\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mgenerate\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 976\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m:\n\u001b[1;32m 977\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mbase_model\u001b[38;5;241m.\u001b[39mprepare_inputs_for_generation \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mbase_model_prepare_inputs_for_generation\n",
"File \u001b[0;32m/opt/conda/lib/python3.9/site-packages/torch/autograd/grad_mode.py:27\u001b[0m, in \u001b[0;36m_DecoratorContextManager.__call__.<locals>.decorate_context\u001b[0;34m(*args, **kwargs)\u001b[0m\n\u001b[1;32m 24\u001b[0m \u001b[38;5;129m@functools\u001b[39m\u001b[38;5;241m.\u001b[39mwraps(func)\n\u001b[1;32m 25\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21mdecorate_context\u001b[39m(\u001b[38;5;241m*\u001b[39margs, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs):\n\u001b[1;32m 26\u001b[0m \u001b[38;5;28;01mwith\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mclone():\n\u001b[0;32m---> 27\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mfunc\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n",
"File \u001b[0;32m/opt/conda/lib/python3.9/site-packages/transformers/generation/utils.py:1596\u001b[0m, in \u001b[0;36mGenerationMixin.generate\u001b[0;34m(self, inputs, generation_config, logits_processor, stopping_criteria, prefix_allowed_tokens_fn, synced_gpus, assistant_model, streamer, negative_prompt_ids, negative_prompt_attention_mask, **kwargs)\u001b[0m\n\u001b[1;32m 1579\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39massisted_decoding(\n\u001b[1;32m 1580\u001b[0m input_ids,\n\u001b[1;32m 1581\u001b[0m assistant_model\u001b[38;5;241m=\u001b[39massistant_model,\n\u001b[0;32m (...)\u001b[0m\n\u001b[1;32m 1592\u001b[0m \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mmodel_kwargs,\n\u001b[1;32m 1593\u001b[0m )\n\u001b[1;32m 1594\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m generation_mode \u001b[38;5;241m==\u001b[39m GenerationMode\u001b[38;5;241m.\u001b[39mGREEDY_SEARCH:\n\u001b[1;32m 1595\u001b[0m \u001b[38;5;66;03m# 11. run greedy search\u001b[39;00m\n\u001b[0;32m-> 1596\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mgreedy_search\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m 1597\u001b[0m \u001b[43m \u001b[49m\u001b[43minput_ids\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1598\u001b[0m \u001b[43m \u001b[49m\u001b[43mlogits_processor\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mlogits_processor\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1599\u001b[0m \u001b[43m \u001b[49m\u001b[43mstopping_criteria\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mstopping_criteria\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1600\u001b[0m \u001b[43m \u001b[49m\u001b[43mpad_token_id\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mgeneration_config\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mpad_token_id\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1601\u001b[0m \u001b[43m \u001b[49m\u001b[43meos_token_id\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mgeneration_config\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43meos_token_id\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1602\u001b[0m \u001b[43m \u001b[49m\u001b[43moutput_scores\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mgeneration_config\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43moutput_scores\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1603\u001b[0m \u001b[43m \u001b[49m\u001b[43mreturn_dict_in_generate\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mgeneration_config\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mreturn_dict_in_generate\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1604\u001b[0m \u001b[43m \u001b[49m\u001b[43msynced_gpus\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43msynced_gpus\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1605\u001b[0m \u001b[43m \u001b[49m\u001b[43mstreamer\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mstreamer\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1606\u001b[0m \u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mmodel_kwargs\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1607\u001b[0m \u001b[43m \u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 1609\u001b[0m \u001b[38;5;28;01melif\u001b[39;00m generation_mode \u001b[38;5;241m==\u001b[39m GenerationMode\u001b[38;5;241m.\u001b[39mCONTRASTIVE_SEARCH:\n\u001b[1;32m 1610\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m model_kwargs[\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124muse_cache\u001b[39m\u001b[38;5;124m\"\u001b[39m]:\n",
"File \u001b[0;32m/opt/conda/lib/python3.9/site-packages/transformers/generation/utils.py:2444\u001b[0m, in \u001b[0;36mGenerationMixin.greedy_search\u001b[0;34m(self, input_ids, logits_processor, stopping_criteria, max_length, pad_token_id, eos_token_id, output_attentions, output_hidden_states, output_scores, return_dict_in_generate, synced_gpus, streamer, **model_kwargs)\u001b[0m\n\u001b[1;32m 2441\u001b[0m model_inputs \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mprepare_inputs_for_generation(input_ids, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mmodel_kwargs)\n\u001b[1;32m 2443\u001b[0m \u001b[38;5;66;03m# forward pass to get next token\u001b[39;00m\n\u001b[0;32m-> 2444\u001b[0m outputs \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[43m(\u001b[49m\n\u001b[1;32m 2445\u001b[0m \u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mmodel_inputs\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 2446\u001b[0m \u001b[43m \u001b[49m\u001b[43mreturn_dict\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;28;43;01mTrue\u001b[39;49;00m\u001b[43m,\u001b[49m\n\u001b[1;32m 2447\u001b[0m \u001b[43m \u001b[49m\u001b[43moutput_attentions\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43moutput_attentions\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 2448\u001b[0m \u001b[43m \u001b[49m\u001b[43moutput_hidden_states\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43moutput_hidden_states\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 2449\u001b[0m \u001b[43m\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 2451\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m synced_gpus \u001b[38;5;129;01mand\u001b[39;00m this_peer_finished:\n\u001b[1;32m 2452\u001b[0m \u001b[38;5;28;01mcontinue\u001b[39;00m \u001b[38;5;66;03m# don't waste resources running the code we don't need\u001b[39;00m\n",
"File \u001b[0;32m/opt/conda/lib/python3.9/site-packages/torch/nn/modules/module.py:1110\u001b[0m, in \u001b[0;36mModule._call_impl\u001b[0;34m(self, *input, **kwargs)\u001b[0m\n\u001b[1;32m 1106\u001b[0m \u001b[38;5;66;03m# If we don't have any hooks, we want to skip the rest of the logic in\u001b[39;00m\n\u001b[1;32m 1107\u001b[0m \u001b[38;5;66;03m# this function, and just call forward.\u001b[39;00m\n\u001b[1;32m 1108\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m (\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_backward_hooks \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_forward_hooks \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_forward_pre_hooks \u001b[38;5;129;01mor\u001b[39;00m _global_backward_hooks\n\u001b[1;32m 1109\u001b[0m \u001b[38;5;129;01mor\u001b[39;00m _global_forward_hooks \u001b[38;5;129;01mor\u001b[39;00m _global_forward_pre_hooks):\n\u001b[0;32m-> 1110\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mforward_call\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;28;43minput\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 1111\u001b[0m \u001b[38;5;66;03m# Do not call functions when jit is used\u001b[39;00m\n\u001b[1;32m 1112\u001b[0m full_backward_hooks, non_full_backward_hooks \u001b[38;5;241m=\u001b[39m [], []\n",
"File \u001b[0;32m/opt/conda/lib/python3.9/site-packages/accelerate/hooks.py:166\u001b[0m, in \u001b[0;36madd_hook_to_module.<locals>.new_forward\u001b[0;34m(*args, **kwargs)\u001b[0m\n\u001b[1;32m 164\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[1;32m 165\u001b[0m output \u001b[38;5;241m=\u001b[39m old_forward(\u001b[38;5;241m*\u001b[39margs, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs)\n\u001b[0;32m--> 166\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mmodule\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_hf_hook\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mpost_forward\u001b[49m\u001b[43m(\u001b[49m\u001b[43mmodule\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43moutput\u001b[49m\u001b[43m)\u001b[49m\n",
"File \u001b[0;32m/opt/conda/lib/python3.9/site-packages/accelerate/hooks.py:305\u001b[0m, in \u001b[0;36mAlignDevicesHook.post_forward\u001b[0;34m(self, module, output)\u001b[0m\n\u001b[1;32m 302\u001b[0m module\u001b[38;5;241m.\u001b[39mstate\u001b[38;5;241m.\u001b[39mCxB \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m\n\u001b[1;32m 304\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mio_same_device \u001b[38;5;129;01mand\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39minput_device \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m:\n\u001b[0;32m--> 305\u001b[0m output \u001b[38;5;241m=\u001b[39m \u001b[43msend_to_device\u001b[49m\u001b[43m(\u001b[49m\u001b[43moutput\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43minput_device\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mskip_keys\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mskip_keys\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 307\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m output\n",
"File \u001b[0;32m/opt/conda/lib/python3.9/site-packages/accelerate/utils/operations.py:160\u001b[0m, in \u001b[0;36msend_to_device\u001b[0;34m(tensor, device, non_blocking, skip_keys)\u001b[0m\n\u001b[1;32m 157\u001b[0m \u001b[38;5;28;01melif\u001b[39;00m skip_keys \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m:\n\u001b[1;32m 158\u001b[0m skip_keys \u001b[38;5;241m=\u001b[39m []\n\u001b[1;32m 159\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mtype\u001b[39m(tensor)(\n\u001b[0;32m--> 160\u001b[0m {\n\u001b[1;32m 161\u001b[0m k: t \u001b[38;5;28;01mif\u001b[39;00m k \u001b[38;5;129;01min\u001b[39;00m skip_keys \u001b[38;5;28;01melse\u001b[39;00m send_to_device(t, device, non_blocking\u001b[38;5;241m=\u001b[39mnon_blocking, skip_keys\u001b[38;5;241m=\u001b[39mskip_keys)\n\u001b[1;32m 162\u001b[0m \u001b[38;5;28;01mfor\u001b[39;00m k, t \u001b[38;5;129;01min\u001b[39;00m tensor\u001b[38;5;241m.\u001b[39mitems()\n\u001b[1;32m 163\u001b[0m }\n\u001b[1;32m 164\u001b[0m )\n\u001b[1;32m 165\u001b[0m \u001b[38;5;28;01melif\u001b[39;00m \u001b[38;5;28mhasattr\u001b[39m(tensor, \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mto\u001b[39m\u001b[38;5;124m\"\u001b[39m):\n\u001b[1;32m 166\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n",
"File \u001b[0;32m/opt/conda/lib/python3.9/site-packages/accelerate/utils/operations.py:161\u001b[0m, in \u001b[0;36m<dictcomp>\u001b[0;34m(.0)\u001b[0m\n\u001b[1;32m 157\u001b[0m \u001b[38;5;28;01melif\u001b[39;00m skip_keys \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m:\n\u001b[1;32m 158\u001b[0m skip_keys \u001b[38;5;241m=\u001b[39m []\n\u001b[1;32m 159\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mtype\u001b[39m(tensor)(\n\u001b[1;32m 160\u001b[0m {\n\u001b[0;32m--> 161\u001b[0m k: t \u001b[38;5;28;01mif\u001b[39;00m k \u001b[38;5;129;01min\u001b[39;00m skip_keys \u001b[38;5;28;01melse\u001b[39;00m \u001b[43msend_to_device\u001b[49m\u001b[43m(\u001b[49m\u001b[43mt\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mdevice\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mnon_blocking\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mnon_blocking\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mskip_keys\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mskip_keys\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 162\u001b[0m \u001b[38;5;28;01mfor\u001b[39;00m k, t \u001b[38;5;129;01min\u001b[39;00m tensor\u001b[38;5;241m.\u001b[39mitems()\n\u001b[1;32m 163\u001b[0m }\n\u001b[1;32m 164\u001b[0m )\n\u001b[1;32m 165\u001b[0m \u001b[38;5;28;01melif\u001b[39;00m \u001b[38;5;28mhasattr\u001b[39m(tensor, \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mto\u001b[39m\u001b[38;5;124m\"\u001b[39m):\n\u001b[1;32m 166\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n",
"File \u001b[0;32m/opt/conda/lib/python3.9/site-packages/accelerate/utils/operations.py:151\u001b[0m, in \u001b[0;36msend_to_device\u001b[0;34m(tensor, device, non_blocking, skip_keys)\u001b[0m\n\u001b[1;32m 138\u001b[0m \u001b[38;5;250m\u001b[39m\u001b[38;5;124;03m\"\"\"\u001b[39;00m\n\u001b[1;32m 139\u001b[0m \u001b[38;5;124;03mRecursively sends the elements in a nested list/tuple/dictionary of tensors to a given device.\u001b[39;00m\n\u001b[1;32m 140\u001b[0m \n\u001b[0;32m (...)\u001b[0m\n\u001b[1;32m 148\u001b[0m \u001b[38;5;124;03m The same data structure as `tensor` with all tensors sent to the proper device.\u001b[39;00m\n\u001b[1;32m 149\u001b[0m \u001b[38;5;124;03m\"\"\"\u001b[39;00m\n\u001b[1;32m 150\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28misinstance\u001b[39m(tensor, (\u001b[38;5;28mtuple\u001b[39m, \u001b[38;5;28mlist\u001b[39m)):\n\u001b[0;32m--> 151\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mhonor_type\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m 152\u001b[0m \u001b[43m \u001b[49m\u001b[43mtensor\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43m(\u001b[49m\u001b[43msend_to_device\u001b[49m\u001b[43m(\u001b[49m\u001b[43mt\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mdevice\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mnon_blocking\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mnon_blocking\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mskip_keys\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mskip_keys\u001b[49m\u001b[43m)\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;28;43;01mfor\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[43mt\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;129;43;01min\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[43mtensor\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 153\u001b[0m \u001b[43m \u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 154\u001b[0m \u001b[38;5;28;01melif\u001b[39;00m \u001b[38;5;28misinstance\u001b[39m(tensor, Mapping):\n\u001b[1;32m 155\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28misinstance\u001b[39m(skip_keys, \u001b[38;5;28mstr\u001b[39m):\n",
"File \u001b[0;32m/opt/conda/lib/python3.9/site-packages/accelerate/utils/operations.py:83\u001b[0m, in \u001b[0;36mhonor_type\u001b[0;34m(obj, generator)\u001b[0m\n\u001b[1;32m 81\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mtype\u001b[39m(obj)(\u001b[38;5;241m*\u001b[39m\u001b[38;5;28mlist\u001b[39m(generator))\n\u001b[1;32m 82\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[0;32m---> 83\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mtype\u001b[39;49m\u001b[43m(\u001b[49m\u001b[43mobj\u001b[49m\u001b[43m)\u001b[49m\u001b[43m(\u001b[49m\u001b[43mgenerator\u001b[49m\u001b[43m)\u001b[49m\n",
"File \u001b[0;32m/opt/conda/lib/python3.9/site-packages/accelerate/utils/operations.py:152\u001b[0m, in \u001b[0;36m<genexpr>\u001b[0;34m(.0)\u001b[0m\n\u001b[1;32m 138\u001b[0m \u001b[38;5;250m\u001b[39m\u001b[38;5;124;03m\"\"\"\u001b[39;00m\n\u001b[1;32m 139\u001b[0m \u001b[38;5;124;03mRecursively sends the elements in a nested list/tuple/dictionary of tensors to a given device.\u001b[39;00m\n\u001b[1;32m 140\u001b[0m \n\u001b[0;32m (...)\u001b[0m\n\u001b[1;32m 148\u001b[0m \u001b[38;5;124;03m The same data structure as `tensor` with all tensors sent to the proper device.\u001b[39;00m\n\u001b[1;32m 149\u001b[0m \u001b[38;5;124;03m\"\"\"\u001b[39;00m\n\u001b[1;32m 150\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28misinstance\u001b[39m(tensor, (\u001b[38;5;28mtuple\u001b[39m, \u001b[38;5;28mlist\u001b[39m)):\n\u001b[1;32m 151\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m honor_type(\n\u001b[0;32m--> 152\u001b[0m tensor, (\u001b[43msend_to_device\u001b[49m\u001b[43m(\u001b[49m\u001b[43mt\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mdevice\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mnon_blocking\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mnon_blocking\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mskip_keys\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mskip_keys\u001b[49m\u001b[43m)\u001b[49m \u001b[38;5;28;01mfor\u001b[39;00m t \u001b[38;5;129;01min\u001b[39;00m tensor)\n\u001b[1;32m 153\u001b[0m )\n\u001b[1;32m 154\u001b[0m \u001b[38;5;28;01melif\u001b[39;00m \u001b[38;5;28misinstance\u001b[39m(tensor, Mapping):\n\u001b[1;32m 155\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28misinstance\u001b[39m(skip_keys, \u001b[38;5;28mstr\u001b[39m):\n",
"File \u001b[0;32m/opt/conda/lib/python3.9/site-packages/accelerate/utils/operations.py:151\u001b[0m, in \u001b[0;36msend_to_device\u001b[0;34m(tensor, device, non_blocking, skip_keys)\u001b[0m\n\u001b[1;32m 138\u001b[0m \u001b[38;5;250m\u001b[39m\u001b[38;5;124;03m\"\"\"\u001b[39;00m\n\u001b[1;32m 139\u001b[0m \u001b[38;5;124;03mRecursively sends the elements in a nested list/tuple/dictionary of tensors to a given device.\u001b[39;00m\n\u001b[1;32m 140\u001b[0m \n\u001b[0;32m (...)\u001b[0m\n\u001b[1;32m 148\u001b[0m \u001b[38;5;124;03m The same data structure as `tensor` with all tensors sent to the proper device.\u001b[39;00m\n\u001b[1;32m 149\u001b[0m \u001b[38;5;124;03m\"\"\"\u001b[39;00m\n\u001b[1;32m 150\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28misinstance\u001b[39m(tensor, (\u001b[38;5;28mtuple\u001b[39m, \u001b[38;5;28mlist\u001b[39m)):\n\u001b[0;32m--> 151\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mhonor_type\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m 152\u001b[0m \u001b[43m \u001b[49m\u001b[43mtensor\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43m(\u001b[49m\u001b[43msend_to_device\u001b[49m\u001b[43m(\u001b[49m\u001b[43mt\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mdevice\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mnon_blocking\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mnon_blocking\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mskip_keys\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mskip_keys\u001b[49m\u001b[43m)\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;28;43;01mfor\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[43mt\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;129;43;01min\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[43mtensor\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 153\u001b[0m \u001b[43m \u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 154\u001b[0m \u001b[38;5;28;01melif\u001b[39;00m \u001b[38;5;28misinstance\u001b[39m(tensor, Mapping):\n\u001b[1;32m 155\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28misinstance\u001b[39m(skip_keys, \u001b[38;5;28mstr\u001b[39m):\n",
"File \u001b[0;32m/opt/conda/lib/python3.9/site-packages/accelerate/utils/operations.py:83\u001b[0m, in \u001b[0;36mhonor_type\u001b[0;34m(obj, generator)\u001b[0m\n\u001b[1;32m 81\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mtype\u001b[39m(obj)(\u001b[38;5;241m*\u001b[39m\u001b[38;5;28mlist\u001b[39m(generator))\n\u001b[1;32m 82\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[0;32m---> 83\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mtype\u001b[39;49m\u001b[43m(\u001b[49m\u001b[43mobj\u001b[49m\u001b[43m)\u001b[49m\u001b[43m(\u001b[49m\u001b[43mgenerator\u001b[49m\u001b[43m)\u001b[49m\n",
"File \u001b[0;32m/opt/conda/lib/python3.9/site-packages/accelerate/utils/operations.py:152\u001b[0m, in \u001b[0;36m<genexpr>\u001b[0;34m(.0)\u001b[0m\n\u001b[1;32m 138\u001b[0m \u001b[38;5;250m\u001b[39m\u001b[38;5;124;03m\"\"\"\u001b[39;00m\n\u001b[1;32m 139\u001b[0m \u001b[38;5;124;03mRecursively sends the elements in a nested list/tuple/dictionary of tensors to a given device.\u001b[39;00m\n\u001b[1;32m 140\u001b[0m \n\u001b[0;32m (...)\u001b[0m\n\u001b[1;32m 148\u001b[0m \u001b[38;5;124;03m The same data structure as `tensor` with all tensors sent to the proper device.\u001b[39;00m\n\u001b[1;32m 149\u001b[0m \u001b[38;5;124;03m\"\"\"\u001b[39;00m\n\u001b[1;32m 150\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28misinstance\u001b[39m(tensor, (\u001b[38;5;28mtuple\u001b[39m, \u001b[38;5;28mlist\u001b[39m)):\n\u001b[1;32m 151\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m honor_type(\n\u001b[0;32m--> 152\u001b[0m tensor, (\u001b[43msend_to_device\u001b[49m\u001b[43m(\u001b[49m\u001b[43mt\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mdevice\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mnon_blocking\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mnon_blocking\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mskip_keys\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mskip_keys\u001b[49m\u001b[43m)\u001b[49m \u001b[38;5;28;01mfor\u001b[39;00m t \u001b[38;5;129;01min\u001b[39;00m tensor)\n\u001b[1;32m 153\u001b[0m )\n\u001b[1;32m 154\u001b[0m \u001b[38;5;28;01melif\u001b[39;00m \u001b[38;5;28misinstance\u001b[39m(tensor, Mapping):\n\u001b[1;32m 155\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28misinstance\u001b[39m(skip_keys, \u001b[38;5;28mstr\u001b[39m):\n",
"File \u001b[0;32m/opt/conda/lib/python3.9/site-packages/accelerate/utils/operations.py:167\u001b[0m, in \u001b[0;36msend_to_device\u001b[0;34m(tensor, device, non_blocking, skip_keys)\u001b[0m\n\u001b[1;32m 165\u001b[0m \u001b[38;5;28;01melif\u001b[39;00m \u001b[38;5;28mhasattr\u001b[39m(tensor, \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mto\u001b[39m\u001b[38;5;124m\"\u001b[39m):\n\u001b[1;32m 166\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[0;32m--> 167\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mtensor\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mto\u001b[49m\u001b[43m(\u001b[49m\u001b[43mdevice\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mnon_blocking\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mnon_blocking\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 168\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m \u001b[38;5;167;01mTypeError\u001b[39;00m: \u001b[38;5;66;03m# .to() doesn't accept non_blocking as kwarg\u001b[39;00m\n\u001b[1;32m 169\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m tensor\u001b[38;5;241m.\u001b[39mto(device)\n",
"\u001b[0;31mKeyboardInterrupt\u001b[0m: "
]
}
],
"source": [
"# TFNS\n",
"res = test_tfns(model, tokenizer, batch_size = batch_size)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"# NWGI\n",
"res = test_nwgi(model, tokenizer, batch_size = batch_size)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.9.12"
}
},
"nbformat": 4,
"nbformat_minor": 4
}

View File

@@ -16,7 +16,6 @@ dic = {
2:'positive',
}
with open('sentiment_templates.txt') as f:
templates = [l.strip() for l in f.readlines()]

File diff suppressed because it is too large Load Diff

View File

@@ -1,826 +0,0 @@
,input,output,text_type,instruction,context,target,out_text_0,out_text_1,out_text_2,out_text_3,out_text_4,new_target,new_out
0,This $BBBY stock options trade would have more than doubled your money https://t.co/Oa0loiRIJL via @TheStreet,positive,tweet,"Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.
Input: This $BBBY stock options trade would have more than doubled your money https://t.co/Oa0loiRIJL via @TheStreet
Answer: ",positive,positive,positive,positive,negative,negative,positive,positive
1,$COST short finally making gains. I will take half my gains at 147,negative,tweet,"Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.
Input: $COST short finally making gains. I will take half my gains at 147
Answer: ",negative,positive,positive,positive,positive,positive,negative,positive
2,"$KO had missed earnings expectations for the last two quarters, so today’s strong results came as a major surprise http://stks.co/d0RHF",positive,tweet,"Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.
Input: $KO had missed earnings expectations for the last two quarters, so today’s strong results came as a major surprise http://stks.co/d0RHF
Answer: ",positive,positive,positive,negative,negative,negative,positive,negative
3,#Fintech provider $CAFN Cachet Financial Solutions Surging Forward today post earnings Up +13.26% https://t.co/9BJ3csk2i9 $JKHY $FISV #Momo,positive,tweet,"Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.
Input: #Fintech provider $CAFN Cachet Financial Solutions Surging Forward today post earnings Up +13.26% https://t.co/9BJ3csk2i9 $JKHY $FISV #Momo
Answer: ",positive,negative,negative,negative,negative,positive,positive,negative
4,"Daily Mail owner considering Yahoo bid $yhoo ,up 2,05% https://t.co/extZr1riyP",positive,tweet,"Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.
Input: Daily Mail owner considering Yahoo bid $yhoo ,up 2,05% https://t.co/extZr1riyP
Answer: ",positive,positive,negative,negative,negative,negative,positive,negative
5,SAB's Chairman Digs In With Board Divided on InBev Offer,neutral,news,"Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive.
Input: SAB's Chairman Digs In With Board Divided on InBev Offer
Answer: ",neutral,negative,negative,negative,negative,negative,neutral,negative
6,Insurers: Admiral blows hot and cold but Aviva soars pre-Friends Life merger,neutral,news,"Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive.
Input: Insurers: Admiral blows hot and cold but Aviva soars pre-Friends Life merger
Answer: ",neutral,positive,positive,negative,negative,positive,neutral,positive
7,BRIEF-Legal & General's retirement business books 4 billion stg H1 sales,positive,news,"Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive.
Input: BRIEF-Legal & General's retirement business books 4 billion stg H1 sales
Answer: ",positive,negative,negative,negative,negative,negative,positive,negative
8,Ocwen Reaches Settlement With California Regulator,positive,news,"Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive.
Input: Ocwen Reaches Settlement With California Regulator
Answer: ",positive,negative,negative,negative,negative,negative,positive,negative
9,"UPDATE 3-BP settles oil spill-related claims with Halliburton, Transocean",negative,news,"Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive.
Input: UPDATE 3-BP settles oil spill-related claims with Halliburton, Transocean
Answer: ",negative,negative,negative,negative,negative,negative,negative,negative
10,$CRUS Upgraded to a buy by Alpha Street Research,positive,tweet,"Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.
Input: $CRUS Upgraded to a buy by Alpha Street Research
Answer: ",positive,positive,positive,positive,negative,positive,positive,positive
11,"$DNN picked some up, like this going into 2014",positive,tweet,"Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.
Input: $DNN picked some up, like this going into 2014
Answer: ",positive,positive,positive,negative,negative,positive,positive,positive
12,Berkshire Hathaway names Kara Raiguel to lead General Re unit,neutral,news,"Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive.
Input: Berkshire Hathaway names Kara Raiguel to lead General Re unit
Answer: ",neutral,positive,positive,negative,negative,positive,neutral,positive
13,Tesco leads leap in FTSE 100; Marks & Spencer drops,positive,news,"Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive.
Input: Tesco leads leap in FTSE 100; Marks & Spencer drops
Answer: ",positive,negative,negative,negative,negative,negative,positive,negative
14,RT @tomhend777 $MU needs to hold here -Broken for now. Needs big flush. Still not technically oversold so now big bounce yet,neutral,tweet,"Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.
Input: RT @tomhend777 $MU needs to hold here -Broken for now. Needs big flush. Still not technically oversold so now big bounce yet
Answer: ",neutral,negative,negative,negative,negative,negative,neutral,negative
15,$GOOGL is setting up above its 50-day moving average. https://t.co/tTm9RnFoXJ,positive,tweet,"Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.
Input: $GOOGL is setting up above its 50-day moving average. https://t.co/tTm9RnFoXJ
Answer: ",positive,negative,negative,negative,negative,negative,positive,negative
16,Irish housebuilder Cairn Homes plans London listing,positive,news,"Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive.
Input: Irish housebuilder Cairn Homes plans London listing
Answer: ",positive,negative,negative,negative,negative,negative,positive,negative
17,"78 users on Vetr are bearish on Tesla Motors, Inc., indicating a SELL Rating (2 stars) for $TSLA https://t.co/vVpzqCXsNJ",negative,tweet,"Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.
Input: 78 users on Vetr are bearish on Tesla Motors, Inc., indicating a SELL Rating (2 stars) for $TSLA https://t.co/vVpzqCXsNJ
Answer: ",negative,positive,positive,positive,positive,positive,negative,positive
18,$OSUR up 33% since 6/25 buy signal. resistance 5.33 - expect 1. pullback 2nd half of day or 2. break abov 5.33 & continue rally for 4-5 days,positive,tweet,"Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.
Input: $OSUR up 33% since 6/25 buy signal. resistance 5.33 - expect 1. pullback 2nd half of day or 2. break abov 5.33 & continue rally for 4-5 days
Answer: ",positive,negative,negative,negative,negative,negative,positive,negative
19,Long $GPRO for a brealout trade,positive,tweet,"Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.
Input: Long $GPRO for a brealout trade
Answer: ",positive,positive,positive,positive,positive,positive,positive,positive
20,"$NFLX small pos, short 180 wkly puts.",negative,tweet,"Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.
Input: $NFLX small pos, short 180 wkly puts.
Answer: ",negative,positive,positive,positive,negative,positive,negative,positive
21,"$SLV -4.44% at 18 now AWFUL, down from 42.50",negative,tweet,"Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.
Input: $SLV -4.44% at 18 now AWFUL, down from 42.50
Answer: ",negative,positive,positive,negative,negative,negative,negative,negative
22,Investors Remain Skeptical About Shell-BG Deal,negative,news,"Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive.
Input: Investors Remain Skeptical About Shell-BG Deal
Answer: ",negative,positive,negative,negative,negative,negative,negative,negative
23,easyJet leads Britain's FTSE lower as global bond rout resumes,negative,news,"Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive.
Input: easyJet leads Britain's FTSE lower as global bond rout resumes
Answer: ",negative,negative,negative,negative,negative,negative,negative,negative
24,UPDATE 1-BP shareholders back more disclosure on climate change risks,neutral,news,"Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive.
Input: UPDATE 1-BP shareholders back more disclosure on climate change risks
Answer: ",neutral,negative,negative,negative,negative,negative,neutral,negative
25,5-star analyst @brianwieser from Pivotal Research upgraded rating on $GOOGL to BUY. Brian has a 79% success rate https://t.co/t0dn02EOH5,positive,tweet,"Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.
Input: 5-star analyst @brianwieser from Pivotal Research upgraded rating on $GOOGL to BUY. Brian has a 79% success rate https://t.co/t0dn02EOH5
Answer: ",positive,positive,negative,negative,negative,positive,positive,negative
26,Glencore sees Tripoli-based NOC as sole legal seller of Libyan oil,neutral,news,"Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive.
Input: Glencore sees Tripoli-based NOC as sole legal seller of Libyan oil
Answer: ",neutral,negative,positive,negative,negative,negative,neutral,negative
27,"Fastenal misses by $0.01, misses on revenue $FAST #NYSE https://t.co/63JHQ7pwMN",negative,tweet,"Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.
Input: Fastenal misses by $0.01, misses on revenue $FAST #NYSE https://t.co/63JHQ7pwMN
Answer: ",negative,negative,negative,negative,negative,negative,negative,negative
28,$NIHD insiders got this one wrong. Looking for bottom. Rsi under 30,negative,tweet,"Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.
Input: $NIHD insiders got this one wrong. Looking for bottom. Rsi under 30
Answer: ",negative,positive,positive,negative,negative,negative,negative,negative
29,AstraZeneca's Lung Cancer Drug Tagrisso Gets FDA Approval,positive,news,"Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive.
Input: AstraZeneca's Lung Cancer Drug Tagrisso Gets FDA Approval
Answer: ",positive,positive,positive,positive,positive,positive,positive,positive
30,looks like a big feb 18-22 $put spread on $cree. Last quarter 0% YoY rev growth trading @ 24x earnings. I may try a short.,negative,tweet,"Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.
Input: looks like a big feb 18-22 $put spread on $cree. Last quarter 0% YoY rev growth trading @ 24x earnings. I may try a short.
Answer: ",negative,negative,negative,negative,negative,negative,negative,negative
31,Miners Meltdown as BHP to Rio Tinto Sink in Commodities Rout,negative,news,"Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive.
Input: Miners Meltdown as BHP to Rio Tinto Sink in Commodities Rout
Answer: ",negative,negative,negative,negative,negative,negative,negative,negative
32,Starbucks' Digital Strategy To Drive Significant Growth With Customer Loyalty $SBUX https://t.co/Xk6lZ3UI3K,positive,tweet,"Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.
Input: Starbucks' Digital Strategy To Drive Significant Growth With Customer Loyalty $SBUX https://t.co/Xk6lZ3UI3K
Answer: ",positive,negative,negative,negative,negative,negative,positive,negative
33,"UPDATE: EasyJet Passenger Numbers, Aer Lingus Traffic Up In February",positive,news,"Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive.
Input: UPDATE: EasyJet Passenger Numbers, Aer Lingus Traffic Up In February
Answer: ",positive,positive,positive,negative,negative,positive,positive,positive
34,"Should you buy Associated British Foods plc, Great Portland Estates plc and Dunelm Group plc following today's news?",positive,news,"Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive.
Input: Should you buy Associated British Foods plc, Great Portland Estates plc and Dunelm Group plc following today's news?
Answer: ",positive,negative,negative,negative,negative,negative,positive,negative
35,Deutsche Bank cuts $SBUX,negative,tweet,"Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.
Input: Deutsche Bank cuts $SBUX
Answer: ",negative,positive,positive,negative,negative,positive,negative,positive
36,"Saudi Aramco, Shell plan to break up Motiva, divide up assets",negative,news,"Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive.
Input: Saudi Aramco, Shell plan to break up Motiva, divide up assets
Answer: ",negative,negative,negative,negative,negative,negative,negative,negative
37,Rolls-Royce to Ensure Compliance After Petrobras Bribery Report,neutral,news,"Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive.
Input: Rolls-Royce to Ensure Compliance After Petrobras Bribery Report
Answer: ",neutral,negative,negative,negative,negative,negative,neutral,negative
38,AstraZeneca And Daiichi Sankyo To Jointly Commercialise MOVANTIK In The US,positive,news,"Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive.
Input: AstraZeneca And Daiichi Sankyo To Jointly Commercialise MOVANTIK In The US
Answer: ",positive,positive,positive,negative,positive,positive,positive,positive
39,Why $MCD looks set to fall further. http://stks.co/f2fgj,negative,tweet,"Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.
Input: Why $MCD looks set to fall further. http://stks.co/f2fgj
Answer: ",negative,negative,negative,negative,negative,negative,negative,negative
40,"Britain's FTSE outperforms Europe, Royal Mail and Tesco rise",positive,news,"Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive.
Input: Britain's FTSE outperforms Europe, Royal Mail and Tesco rise
Answer: ",positive,negative,negative,negative,negative,negative,positive,negative
41,$NFLX +1% $104.80 LONG streaming services rapidly outpacing traditional cable,positive,tweet,"Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.
Input: $NFLX +1% $104.80 LONG streaming services rapidly outpacing traditional cable
Answer: ",positive,positive,positive,negative,positive,positive,positive,positive
42,$PLUG Closed short position. Small gain. Not interested in options expiring worthless,positive,tweet,"Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.
Input: $PLUG Closed short position. Small gain. Not interested in options expiring worthless
Answer: ",positive,negative,positive,negative,negative,negative,positive,negative
43,"RT @Cash_Cow $TLT still has a rising RSI & MACD, all this bond buying is signaling some bad moves for the market. $SPY $UUP",negative,tweet,"Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.
Input: RT @Cash_Cow $TLT still has a rising RSI & MACD, all this bond buying is signaling some bad moves for the market. $SPY $UUP
Answer: ",negative,negative,negative,negative,negative,negative,negative,negative
44,$NFLX VISION : short term consolidation then movement higher http://stks.co/j05uu,positive,tweet,"Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.
Input: $NFLX VISION : short term consolidation then movement higher http://stks.co/j05uu
Answer: ",positive,positive,positive,negative,negative,negative,positive,negative
45,$INVE : SEE YA ABOVE $8,positive,tweet,"Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.
Input: $INVE : SEE YA ABOVE $8
Answer: ",positive,positive,positive,positive,negative,positive,positive,positive
46,AB InBev offers SABMiller $3 billion breakup fee,positive,news,"Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive.
Input: AB InBev offers SABMiller $3 billion breakup fee
Answer: ",positive,negative,negative,negative,negative,negative,positive,negative
47,Citrix Systems Inc $CTXS Position Increased by Mizuho… https://t.co/v7Lkq08Flp @ShareStockNews,positive,tweet,"Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.
Input: Citrix Systems Inc $CTXS Position Increased by Mizuho… https://t.co/v7Lkq08Flp @ShareStockNews
Answer: ",positive,negative,negative,negative,negative,negative,positive,negative
48,$NUGT longer term bullish,positive,tweet,"Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.
Input: $NUGT longer term bullish
Answer: ",positive,positive,positive,positive,positive,positive,positive,positive
49,"Loaded up on $bsx yesterday,looking good now. Still think way more upside than downside.",positive,tweet,"Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.
Input: Loaded up on $bsx yesterday,looking good now. Still think way more upside than downside.
Answer: ",positive,negative,positive,negative,negative,negative,positive,negative
50,FDA approves Shire's Vyvanse for binge-eating disorder,positive,news,"Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive.
Input: FDA approves Shire's Vyvanse for binge-eating disorder
Answer: ",positive,negative,positive,negative,negative,negative,positive,negative
51,"$HAL If bulls lucky enuff to get an upside gap fill, better take it. Wouldn't chase it here. http://stks.co/r12Us",neutral,tweet,"Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.
Input: $HAL If bulls lucky enuff to get an upside gap fill, better take it. Wouldn't chase it here. http://stks.co/r12Us
Answer: ",neutral,negative,negative,negative,negative,negative,neutral,negative
52,Short interest increases yet again http://stks.co/e19h via @ryandetrick $SPY,negative,tweet,"Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.
Input: Short interest increases yet again http://stks.co/e19h via @ryandetrick $SPY
Answer: ",negative,positive,positive,negative,negative,negative,negative,negative
53,$BBRY lets see 14+ today,positive,tweet,"Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.
Input: $BBRY lets see 14+ today
Answer: ",positive,positive,positive,negative,negative,positive,positive,positive
54,"Reuters: Green Mountain revenue misses, shares plunge http://stks.co/13mW > $GMCR prints 43.80, market in a foul mood, bad day to disappoint",negative,tweet,"Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.
Input: Reuters: Green Mountain revenue misses, shares plunge http://stks.co/13mW > $GMCR prints 43.80, market in a foul mood, bad day to disappoint
Answer: ",negative,negative,negative,negative,negative,negative,negative,negative
55,#Apple up almost 20% from its February lows with very little fanfare. $AAPL,positive,tweet,"Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.
Input: #Apple up almost 20% from its February lows with very little fanfare. $AAPL
Answer: ",positive,positive,positive,negative,negative,negative,positive,negative
56,Shell and BG Shareholders to Vote on Deal at End of January,neutral,news,"Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive.
Input: Shell and BG Shareholders to Vote on Deal at End of January
Answer: ",neutral,negative,negative,negative,negative,negative,neutral,negative
57,RBI surprises Street; Sensex pares gains after hitting mount 30k,negative,news,"Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive.
Input: RBI surprises Street; Sensex pares gains after hitting mount 30k
Answer: ",negative,negative,negative,negative,negative,negative,negative,negative
58,X marks the recall: Tesla recalls #ModelX for faulty 3rd row seat. https://t.co/HSqdoVry07 $TSLA https://t.co/4Cs3CNZEBB,negative,tweet,"Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.
Input: X marks the recall: Tesla recalls #ModelX for faulty 3rd row seat. https://t.co/HSqdoVry07 $TSLA https://t.co/4Cs3CNZEBB
Answer: ",negative,negative,negative,negative,negative,negative,negative,negative
59,"$QCOR a little pullback is fine but if this erases all of todays gains, I cannot believe the manipulation its capable of",negative,tweet,"Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.
Input: $QCOR a little pullback is fine but if this erases all of todays gains, I cannot believe the manipulation its capable of
Answer: ",negative,negative,negative,negative,negative,negative,negative,negative
60,Glencore slumps 30 percent as debt fears grow,negative,news,"Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive.
Input: Glencore slumps 30 percent as debt fears grow
Answer: ",negative,positive,negative,negative,negative,positive,negative,negative
61,$TSLA <STUDY the CHARTS> Pullback_Time https://t.co/ZMDG0fb3I7,negative,tweet,"Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.
Input: $TSLA <STUDY the CHARTS> Pullback_Time https://t.co/ZMDG0fb3I7
Answer: ",negative,positive,positive,negative,negative,negative,negative,negative
62,LONDON MORNING BRIEFING: HSBC And Standard Chartered Shares Rise,positive,news,"Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive.
Input: LONDON MORNING BRIEFING: HSBC And Standard Chartered Shares Rise
Answer: ",positive,positive,negative,negative,negative,negative,positive,negative
63,AstraZeneca's patent on asthma drug invalidated by US court,negative,news,"Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive.
Input: AstraZeneca's patent on asthma drug invalidated by US court
Answer: ",negative,negative,negative,negative,negative,negative,negative,negative
64,Is It Worth Investing In Tesco PLC And Prudential plc Now?,positive,news,"Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive.
Input: Is It Worth Investing In Tesco PLC And Prudential plc Now?
Answer: ",positive,negative,negative,negative,negative,negative,positive,negative
65,NYSE owner ICE considers offer for LSE,positive,news,"Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive.
Input: NYSE owner ICE considers offer for LSE
Answer: ",positive,negative,negative,negative,negative,negative,positive,negative
66,"$ESI on lows, down $1.50 to $2.50 BK a real possibility",negative,tweet,"Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.
Input: $ESI on lows, down $1.50 to $2.50 BK a real possibility
Answer: ",negative,negative,negative,negative,negative,negative,negative,negative
67,"$QIHU totally missed this one, was about to jump in on that 60 break test but didn't, congrats shorts",negative,tweet,"Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.
Input: $QIHU totally missed this one, was about to jump in on that 60 break test but didn't, congrats shorts
Answer: ",negative,negative,negative,negative,negative,negative,negative,negative
68,Morrisons and Debenhams surprise City with Christmas bounce back,positive,news,"Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive.
Input: Morrisons and Debenhams surprise City with Christmas bounce back
Answer: ",positive,positive,positive,negative,negative,positive,positive,positive
69,$AAPL wants lower. up waves getting smaller on the 2 min,negative,tweet,"Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.
Input: $AAPL wants lower. up waves getting smaller on the 2 min
Answer: ",negative,positive,positive,negative,negative,negative,negative,negative
70,"$AAPL at pivot area on intraday chart- break here could send this to 50-day SMA, 457.80 http://stks.co/jPbN",positive,tweet,"Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.
Input: $AAPL at pivot area on intraday chart- break here could send this to 50-day SMA, 457.80 http://stks.co/jPbN
Answer: ",positive,negative,negative,negative,negative,negative,positive,negative
71,Short on $ATVI from 24.55.,negative,tweet,"Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.
Input: Short on $ATVI from 24.55.
Answer: ",negative,positive,positive,negative,negative,positive,negative,positive
72,"METALS-Zinc surges 12 pct after Glencore cuts output, fuelling metals rally",positive,news,"Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive.
Input: METALS-Zinc surges 12 pct after Glencore cuts output, fuelling metals rally
Answer: ",positive,negative,negative,negative,negative,negative,positive,negative
73,Academics claim Google Android two-factor authentication is breakable. #security #authentication #hacking $goog https://t.co/nJx4mnrGLo,negative,tweet,"Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.
Input: Academics claim Google Android two-factor authentication is breakable. #security #authentication #hacking $goog https://t.co/nJx4mnrGLo
Answer: ",negative,negative,negative,negative,negative,negative,negative,negative
74,G4S sees profits rise but UK contract problems remain,positive,news,"Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive.
Input: G4S sees profits rise but UK contract problems remain
Answer: ",positive,negative,negative,negative,negative,negative,positive,negative
75,Tesla issues its first Model X recall https://t.co/t1kMqVwhQQ $TSLA,negative,tweet,"Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.
Input: Tesla issues its first Model X recall https://t.co/t1kMqVwhQQ $TSLA
Answer: ",negative,positive,positive,negative,positive,positive,negative,positive
76,Double bottom with handle buy point of 56.49 $WMT http://chart.ly/ml857v3,positive,tweet,"Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.
Input: Double bottom with handle buy point of 56.49 $WMT http://chart.ly/ml857v3
Answer: ",positive,negative,negative,negative,negative,negative,positive,negative
77,Facebook $FB received a Buy rating from Wells Fargo 5-star Analyst Peter Stabler (Wells Fargo) https://t.co/jnB4c9vdCu,positive,tweet,"Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.
Input: Facebook $FB received a Buy rating from Wells Fargo 5-star Analyst Peter Stabler (Wells Fargo) https://t.co/jnB4c9vdCu
Answer: ",positive,negative,negative,negative,negative,negative,positive,negative
78,$AMCN pushing highs,positive,tweet,"Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.
Input: $AMCN pushing highs
Answer: ",positive,positive,positive,negative,positive,positive,positive,positive
79,"Tesco, Asda sales fall as march of the discounters continues-Kantar",negative,news,"Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive.
Input: Tesco, Asda sales fall as march of the discounters continues-Kantar
Answer: ",negative,negative,negative,negative,negative,negative,negative,negative
80,longed $AMZN 300 @ 189.82,positive,tweet,"Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.
Input: longed $AMZN 300 @ 189.82
Answer: ",positive,positive,positive,negative,negative,negative,positive,negative
81,@Renatta @Fr0van @kjepeneter @RPTL Strong close 4 $PLNR coming,positive,tweet,"Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.
Input: @Renatta @Fr0van @kjepeneter @RPTL Strong close 4 $PLNR coming
Answer: ",positive,negative,negative,negative,negative,negative,positive,negative
82,Retail giant Kingfisher reports 'solid' start to the year,positive,news,"Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive.
Input: Retail giant Kingfisher reports 'solid' start to the year
Answer: ",positive,negative,negative,negative,negative,negative,positive,negative
83,$PG Ackman making the big added efficiency argument. betting on operational imporvement in a huge conglomerate can go either way imo.,positive,tweet,"Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.
Input: $PG Ackman making the big added efficiency argument. betting on operational imporvement in a huge conglomerate can go either way imo.
Answer: ",positive,negative,negative,negative,negative,negative,positive,negative
84,"Ackman, in email, says supports Valeant CEO Pearson",positive,news,"Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive.
Input: Ackman, in email, says supports Valeant CEO Pearson
Answer: ",positive,negative,negative,negative,negative,negative,positive,negative
85,UPDATE 1-EU regulator backs approval for GSK injectable asthma drug,positive,news,"Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive.
Input: UPDATE 1-EU regulator backs approval for GSK injectable asthma drug
Answer: ",positive,positive,positive,negative,negative,negative,positive,negative
86,Commented on It's Time To Embrace Dividend Growth https://t.co/wc2qfP79TN $ABBV $CSCO $WYN,positive,tweet,"Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.
Input: Commented on It's Time To Embrace Dividend Growth https://t.co/wc2qfP79TN $ABBV $CSCO $WYN
Answer: ",positive,negative,negative,negative,negative,negative,positive,negative
87,Entering long Lockheed Martin $LMT at Thursday's open. http://stks.co/eXtA,positive,tweet,"Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.
Input: Entering long Lockheed Martin $LMT at Thursday's open. http://stks.co/eXtA
Answer: ",positive,negative,negative,negative,negative,negative,positive,negative
88,AstraZeneca share price: Acerta deal pays off with orphan drug status,positive,news,"Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive.
Input: AstraZeneca share price: Acerta deal pays off with orphan drug status
Answer: ",positive,positive,positive,positive,positive,positive,positive,positive
89,Teva: FDA Approves Generic Version of AstraZeneca Heartburn Drug,positive,news,"Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive.
Input: Teva: FDA Approves Generic Version of AstraZeneca Heartburn Drug
Answer: ",positive,negative,negative,negative,negative,negative,positive,negative
90,$ACOM http://stks.co/1G6x Downside breakout looks to be coming soon.,negative,tweet,"Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.
Input: $ACOM http://stks.co/1G6x Downside breakout looks to be coming soon.
Answer: ",negative,negative,negative,negative,negative,negative,negative,negative
91,$HZNP havent seen vol like this since the runup. lets see one more dip to 2.0x,negative,tweet,"Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.
Input: $HZNP havent seen vol like this since the runup. lets see one more dip to 2.0x
Answer: ",negative,negative,negative,negative,negative,negative,negative,negative
92,$BAC $ADSK $NFLX long this morning,positive,tweet,"Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.
Input: $BAC $ADSK $NFLX long this morning
Answer: ",positive,positive,positive,negative,negative,positive,positive,positive
93,$GALE Breakout Coming Soon!,positive,tweet,"Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.
Input: $GALE Breakout Coming Soon!
Answer: ",positive,positive,positive,negative,negative,negative,positive,negative
94,"Baird likes $TSLA - upgrades to outperform, lifts price target to $300. Research firm also sees no capital raise necessary in next few qtrs",positive,tweet,"Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.
Input: Baird likes $TSLA - upgrades to outperform, lifts price target to $300. Research firm also sees no capital raise necessary in next few qtrs
Answer: ",positive,negative,negative,negative,negative,negative,positive,negative
95,GlaxoSmithKline set to complete $20 billion Novartis asset swap next week,positive,news,"Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive.
Input: GlaxoSmithKline set to complete $20 billion Novartis asset swap next week
Answer: ",positive,negative,negative,negative,negative,negative,positive,negative
96,$TSLA not dipping - testing the 200 day ma https://t.co/jEPLmZQKGW,positive,tweet,"Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.
Input: $TSLA not dipping - testing the 200 day ma https://t.co/jEPLmZQKGW
Answer: ",positive,negative,negative,negative,negative,negative,positive,negative
97,Hargreaves Lansdown share price falls as costs mount - although pensions ...,negative,news,"Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive.
Input: Hargreaves Lansdown share price falls as costs mount - although pensions ...
Answer: ",negative,negative,negative,negative,negative,negative,negative,negative
98,"HSBC shakes up board with two new business chiefs, three departures",neutral,news,"Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive.
Input: HSBC shakes up board with two new business chiefs, three departures
Answer: ",neutral,negative,negative,negative,negative,negative,neutral,negative
99,$YELP wayyy overvalued right now IMO. Should be trading single digits. May take a short pos. into earnings. Near term target 18 ......,negative,tweet,"Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.
Input: $YELP wayyy overvalued right now IMO. Should be trading single digits. May take a short pos. into earnings. Near term target 18 ......
Answer: ",negative,negative,negative,negative,negative,negative,negative,negative
100,Long $TSLA short $MBLY https://t.co/jSpUSzo6na,positive,tweet,"Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.
Input: Long $TSLA short $MBLY https://t.co/jSpUSzo6na
Answer: ",positive,negative,negative,negative,negative,negative,positive,negative
101,AstraZeneca wins FDA approval for key new lung cancer pill,positive,news,"Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive.
Input: AstraZeneca wins FDA approval for key new lung cancer pill
Answer: ",positive,positive,positive,negative,negative,positive,positive,positive
102,"Sold out $TZA 45 $PUT (down $1), which were hedging my 45 $CALL. Letting the calls ride solo now.",positive,tweet,"Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.
Input: Sold out $TZA 45 $PUT (down $1), which were hedging my 45 $CALL. Letting the calls ride solo now.
Answer: ",positive,negative,negative,negative,negative,negative,positive,negative
103,$ATHN Seems like a good short setup. Stop above the 50 day. No position.,negative,tweet,"Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.
Input: $ATHN Seems like a good short setup. Stop above the 50 day. No position.
Answer: ",negative,negative,negative,negative,negative,negative,negative,negative
104,Morning Agenda: Shire's Deal for NPS,positive,news,"Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive.
Input: Morning Agenda: Shire's Deal for NPS
Answer: ",positive,positive,positive,negative,positive,positive,positive,positive
105,$GOOGL gets an upgrade price target $970,positive,tweet,"Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.
Input: $GOOGL gets an upgrade price target $970
Answer: ",positive,positive,positive,negative,negative,positive,positive,positive
106,$DARA breaking out,positive,tweet,"Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.
Input: $DARA breaking out
Answer: ",positive,positive,positive,positive,positive,positive,positive,positive
107,"@CGrantWSJ I think this $TSLA bubble might go on for some time. So long as ppl love the cars, they might keep getting funding.",positive,tweet,"Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.
Input: @CGrantWSJ I think this $TSLA bubble might go on for some time. So long as ppl love the cars, they might keep getting funding.
Answer: ",positive,negative,negative,negative,negative,negative,positive,negative
108,$SPY bull move ended waiting for next setup,negative,tweet,"Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.
Input: $SPY bull move ended waiting for next setup
Answer: ",negative,positive,positive,negative,negative,negative,negative,negative
109,Supermarket Stocks Rally as Tesco Plans to Axe Non-core UK Assets $TSCO https://t.co/BmvhcrwREA,positive,tweet,"Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.
Input: Supermarket Stocks Rally as Tesco Plans to Axe Non-core UK Assets $TSCO https://t.co/BmvhcrwREA
Answer: ",positive,negative,negative,negative,negative,negative,positive,negative
110,Novartis buys remaining rights to GSK treatment in deal up to $1 billion,positive,news,"Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive.
Input: Novartis buys remaining rights to GSK treatment in deal up to $1 billion
Answer: ",positive,negative,negative,negative,negative,negative,positive,negative
111,$FB popping up to HOD,positive,tweet,"Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.
Input: $FB popping up to HOD
Answer: ",positive,positive,positive,negative,positive,positive,positive,positive
112,$HYG Potential continuation Uptrend on a 60'-15'-4' charts http://stks.co/t1Qp6,positive,tweet,"Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.
Input: $HYG Potential continuation Uptrend on a 60'-15'-4' charts http://stks.co/t1Qp6
Answer: ",positive,positive,positive,positive,negative,negative,positive,positive
113,I am not optimistic about $amzn both fundementals and charts look like poopoo this quarter.,negative,tweet,"Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.
Input: I am not optimistic about $amzn both fundementals and charts look like poopoo this quarter.
Answer: ",negative,negative,negative,negative,negative,negative,negative,negative
114,Borealis Infrastructure putting together new Severn Trent bid,positive,news,"Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive.
Input: Borealis Infrastructure putting together new Severn Trent bid
Answer: ",positive,negative,negative,negative,negative,negative,positive,negative
115,Thank you $GOOG (Google Alphabet) and $FB (Facebook) stocks! What a nice reversal.,positive,tweet,"Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.
Input: Thank you $GOOG (Google Alphabet) and $FB (Facebook) stocks! What a nice reversal.
Answer: ",positive,positive,positive,positive,positive,positive,positive,positive
116,Costco: A Premier Retail Dividend Play https://t.co/J3UhTs022M $COST,positive,tweet,"Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.
Input: Costco: A Premier Retail Dividend Play https://t.co/J3UhTs022M $COST
Answer: ",positive,positive,positive,positive,negative,negative,positive,positive
117,"DJI overbought: $AAPL, $AXP, $BA, $CVX, $IBM, $INTC, $VZ https://t.co/wMy1PnomJF",negative,tweet,"Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.
Input: DJI overbought: $AAPL, $AXP, $BA, $CVX, $IBM, $INTC, $VZ https://t.co/wMy1PnomJF
Answer: ",negative,negative,negative,negative,negative,negative,negative,negative
118,"$YOKU high volume blast off Friday, goes higher http://stks.co/qSaL",positive,tweet,"Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.
Input: $YOKU high volume blast off Friday, goes higher http://stks.co/qSaL
Answer: ",positive,positive,positive,positive,positive,positive,positive,positive
119,"Tesla to recall 2,700 Model X SUVs over seat issue https://t.co/OdPraN59Xq $TSLA https://t.co/xvn4blIwpy https://t.co/ThfvWTnRPs",negative,tweet,"Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.
Input: Tesla to recall 2,700 Model X SUVs over seat issue https://t.co/OdPraN59Xq $TSLA https://t.co/xvn4blIwpy https://t.co/ThfvWTnRPs
Answer: ",negative,negative,negative,negative,negative,negative,negative,negative
120,"I'm liking the price action in $SWKS, currently @21.80 ; my target: 24.00+ before year end.",positive,tweet,"Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.
Input: I'm liking the price action in $SWKS, currently @21.80 ; my target: 24.00+ before year end.
Answer: ",positive,positive,positive,positive,positive,positive,positive,positive
121,"So as of today's close (8/15/14), I'm long $TSLA $AMTD $TWTR $FB $AAPL $CELG - all on a longer-term, technical swing long basis.",positive,tweet,"Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.
Input: So as of today's close (8/15/14), I'm long $TSLA $AMTD $TWTR $FB $AAPL $CELG - all on a longer-term, technical swing long basis.
Answer: ",positive,negative,negative,negative,negative,positive,positive,negative
122,Aberdeen Asset Management Gains Foothold In China,positive,news,"Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive.
Input: Aberdeen Asset Management Gains Foothold In China
Answer: ",positive,positive,positive,positive,positive,positive,positive,positive
123,$KIOR My god. Market getting crushed today. Gotta hold if anything g should recover some tomorrow I imagine.,negative,tweet,"Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.
Input: $KIOR My god. Market getting crushed today. Gotta hold if anything g should recover some tomorrow I imagine.
Answer: ",negative,negative,positive,negative,negative,negative,negative,negative
124,$UUP at major resistance right now. Can go much higher if it can break above. May take several attempts - few days to a week,positive,tweet,"Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.
Input: $UUP at major resistance right now. Can go much higher if it can break above. May take several attempts - few days to a week
Answer: ",positive,positive,positive,positive,negative,positive,positive,positive
125,Royal Mail share price rallies amid positive broker comments,positive,news,"Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive.
Input: Royal Mail share price rallies amid positive broker comments
Answer: ",positive,positive,positive,positive,positive,positive,positive,positive
126,"$SLV POS, been saying it for 2 years. Going lower. Forget about it or go short.",negative,tweet,"Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.
Input: $SLV POS, been saying it for 2 years. Going lower. Forget about it or go short.
Answer: ",negative,positive,positive,positive,positive,positive,negative,positive
127,Severn Trent share price jumps as Canadian investor renews pursuit of utility,positive,news,"Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive.
Input: Severn Trent share price jumps as Canadian investor renews pursuit of utility
Answer: ",positive,positive,positive,positive,negative,positive,positive,positive
128,$FB still a dog going much lower this week,negative,tweet,"Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.
Input: $FB still a dog going much lower this week
Answer: ",negative,positive,positive,negative,negative,negative,negative,negative
129,"$TXRH reports Q1 EPS of $0.37 versus the estimated $0.35, beating by $0.02. EPS were Up 19% from the same quarter last year.",positive,tweet,"Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.
Input: $TXRH reports Q1 EPS of $0.37 versus the estimated $0.35, beating by $0.02. EPS were Up 19% from the same quarter last year.
Answer: ",positive,positive,negative,negative,negative,negative,positive,negative
130,$SPY $MITK fast 56pc dive http://stks.co/3ffN $$,negative,tweet,"Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.
Input: $SPY $MITK fast 56pc dive http://stks.co/3ffN $$
Answer: ",negative,positive,positive,negative,negative,negative,negative,negative
131,"Long Position on $IP,....Scaling UP http://stks.co/sIln",positive,tweet,"Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.
Input: Long Position on $IP,....Scaling UP http://stks.co/sIln
Answer: ",positive,negative,positive,negative,negative,negative,positive,negative
132,"RT @stockdemons think shorting here into close might be play, $SPY - high beta reversing..looks worth a shot",negative,tweet,"Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.
Input: RT @stockdemons think shorting here into close might be play, $SPY - high beta reversing..looks worth a shot
Answer: ",negative,negative,positive,negative,negative,negative,negative,negative
133,$GPS Gap September Comparable Store Sales -4%,negative,tweet,"Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.
Input: $GPS Gap September Comparable Store Sales -4%
Answer: ",negative,positive,positive,negative,negative,positive,negative,positive
134,$SIGA Bid for Reargument Denied by Judge,negative,tweet,"Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.
Input: $SIGA Bid for Reargument Denied by Judge
Answer: ",negative,positive,positive,negative,negative,negative,negative,negative
135,Kinder Morgan and BP Form Joint Venture Limited Liability Company to Purchase ...,positive,news,"Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive.
Input: Kinder Morgan and BP Form Joint Venture Limited Liability Company to Purchase ...
Answer: ",positive,positive,negative,negative,negative,negative,positive,negative
136,"$TSLA steaming up again, this stock is relentless at the moment",positive,tweet,"Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.
Input: $TSLA steaming up again, this stock is relentless at the moment
Answer: ",positive,positive,positive,negative,positive,positive,positive,positive
137,"$RUSS Don't catch falling knives, but I think an entry is coming soon on this",positive,tweet,"Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.
Input: $RUSS Don't catch falling knives, but I think an entry is coming soon on this
Answer: ",positive,negative,negative,negative,negative,negative,positive,negative
138,$UBNT still having some trouble at the resistance line. Should resolve soon.@cheri1 @strattonite http://stks.co/c0sU4,neutral,tweet,"Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.
Input: $UBNT still having some trouble at the resistance line. Should resolve soon.@cheri1 @strattonite http://stks.co/c0sU4
Answer: ",neutral,negative,negative,negative,negative,negative,neutral,negative
139,Adobe Receives New Rating from Top Analyst $ADBE https://t.co/LJNXPEvHZN,positive,tweet,"Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.
Input: Adobe Receives New Rating from Top Analyst $ADBE https://t.co/LJNXPEvHZN
Answer: ",positive,positive,positive,negative,negative,negative,positive,negative
140,AstraZeneca Explores Potential Deal With Acerta for Cancer Drug,positive,news,"Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive.
Input: AstraZeneca Explores Potential Deal With Acerta for Cancer Drug
Answer: ",positive,positive,positive,negative,positive,positive,positive,positive
141,"$QCOR Just added 3,000 shares @28.",positive,tweet,"Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.
Input: $QCOR Just added 3,000 shares @28.
Answer: ",positive,positive,positive,negative,negative,negative,positive,negative
142,@Megaas2000 $AAPL McDonalds had a big GROWING success for years with the same BigMac and Apple update and improbe Iphone and Ipad,positive,tweet,"Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.
Input: @Megaas2000 $AAPL McDonalds had a big GROWING success for years with the same BigMac and Apple update and improbe Iphone and Ipad
Answer: ",positive,negative,negative,negative,negative,negative,positive,negative
143,Current holdings via options - Long: $AAPL $V $GS $AET & Short: $VXX,positive,tweet,"Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.
Input: Current holdings via options - Long: $AAPL $V $GS $AET & Short: $VXX
Answer: ",positive,negative,negative,negative,negative,negative,positive,negative
144,Credit Suisse poaches Prudential's Thiam for Asian push,positive,news,"Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive.
Input: Credit Suisse poaches Prudential's Thiam for Asian push
Answer: ",positive,positive,positive,negative,negative,positive,positive,positive
145,"$SDS +1.46% 15.32, picking up some speed. May 16 calls now +35% .19: http://stks.co/3eiK, Next week $16 calls .11c: http://stks.co/3eiL",positive,tweet,"Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.
Input: $SDS +1.46% 15.32, picking up some speed. May 16 calls now +35% .19: http://stks.co/3eiK, Next week $16 calls .11c: http://stks.co/3eiL
Answer: ",positive,negative,negative,negative,negative,negative,positive,negative
146,$AEGN MACD and ADX are crossing over the signal lines! Long Setup http://stks.co/qzzx,positive,tweet,"Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.
Input: $AEGN MACD and ADX are crossing over the signal lines! Long Setup http://stks.co/qzzx
Answer: ",positive,positive,positive,positive,positive,positive,positive,positive
147,ARM Royalties Accelerate as Smartphone Market Regains Strength,positive,news,"Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive.
Input: ARM Royalties Accelerate as Smartphone Market Regains Strength
Answer: ",positive,positive,positive,positive,positive,positive,positive,positive
148,$AAPL nibbling on a small long via 525.. buying off 13min charts..,positive,tweet,"Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.
Input: $AAPL nibbling on a small long via 525.. buying off 13min charts..
Answer: ",positive,positive,positive,positive,positive,positive,positive,positive
149,NaturalGas Settles At 3-year Low $DBO $BNO http://stks.co/d27qX,negative,tweet,"Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.
Input: NaturalGas Settles At 3-year Low $DBO $BNO http://stks.co/d27qX
Answer: ",negative,positive,positive,positive,positive,positive,negative,positive
150,Amazon declares 'best ever' Black Friday and Cyber Monday for Kindle family http://stks.co/cEtw via Engadget $AMZN,positive,tweet,"Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.
Input: Amazon declares 'best ever' Black Friday and Cyber Monday for Kindle family http://stks.co/cEtw via Engadget $AMZN
Answer: ",positive,positive,positive,positive,positive,positive,positive,positive
151,Kingfisher takeover of Mr Bricolage could hit a brick wall,negative,news,"Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive.
Input: Kingfisher takeover of Mr Bricolage could hit a brick wall
Answer: ",negative,negative,negative,negative,negative,negative,negative,negative
152,$NUGT Gold above 1400...wow,positive,tweet,"Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.
Input: $NUGT Gold above 1400...wow
Answer: ",positive,positive,positive,positive,positive,positive,positive,positive
153,GlaxoSmithKline starts hunt for successor to CEO Witty,neutral,news,"Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive.
Input: GlaxoSmithKline starts hunt for successor to CEO Witty
Answer: ",neutral,negative,negative,negative,negative,negative,neutral,negative
154,$CERN - consolidating above 50 & 200 MA - nice long entry here w stop below 10 MA - targeting $70 area,positive,tweet,"Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.
Input: $CERN - consolidating above 50 & 200 MA - nice long entry here w stop below 10 MA - targeting $70 area
Answer: ",positive,negative,negative,negative,negative,negative,positive,negative
155,$UTSI http://stks.co/15uR Long setup. Reported very good earnings.,positive,tweet,"Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.
Input: $UTSI http://stks.co/15uR Long setup. Reported very good earnings.
Answer: ",positive,positive,positive,negative,negative,negative,positive,negative
156,New recommendation from Carl Kirst of BMO Capital Markets for $WMB is BUY.Price target is $62:http://stks.co/t0S0r,positive,tweet,"Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.
Input: New recommendation from Carl Kirst of BMO Capital Markets for $WMB is BUY.Price target is $62:http://stks.co/t0S0r
Answer: ",positive,negative,negative,negative,negative,negative,positive,negative
157,GSK joins China trade push as UK trumpets healthcare deals,positive,news,"Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive.
Input: GSK joins China trade push as UK trumpets healthcare deals
Answer: ",positive,negative,negative,negative,negative,negative,positive,negative
158,"Sainsbury's, Asda, Tesco and Morrisons will all cut petrol prices as oil falls ...",negative,news,"Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive.
Input: Sainsbury's, Asda, Tesco and Morrisons will all cut petrol prices as oil falls ...
Answer: ",negative,negative,negative,negative,negative,negative,negative,negative
159,$LSCC Accumulation chart continues to make new highs showing accumulation continuing to take place http://stks.co/aDpO,positive,tweet,"Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.
Input: $LSCC Accumulation chart continues to make new highs showing accumulation continuing to take place http://stks.co/aDpO
Answer: ",positive,negative,negative,negative,negative,negative,positive,negative
160,"RT @StockTwits RT @fallondpicks Breadth Consolidates: After weeks of steady gains,advances in mkt breadth slowe... http://stks.co/2TrG $QQQ",negative,tweet,"Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.
Input: RT @StockTwits RT @fallondpicks Breadth Consolidates: After weeks of steady gains,advances in mkt breadth slowe... http://stks.co/2TrG $QQQ
Answer: ",negative,negative,negative,negative,negative,negative,negative,negative
161,"Google, Inc. completes acquisition of ICOA, Inc. http://stks.co/nFEI $ICOA $GOOG",positive,tweet,"Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.
Input: Google, Inc. completes acquisition of ICOA, Inc. http://stks.co/nFEI $ICOA $GOOG
Answer: ",positive,positive,positive,negative,negative,negative,positive,negative
162,"Irish Said Chasing Standard Chartered, RBS as Brexit Vote Nears",positive,news,"Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive.
Input: Irish Said Chasing Standard Chartered, RBS as Brexit Vote Nears
Answer: ",positive,negative,negative,negative,negative,negative,positive,negative
163,Glencore chief blames rivals' overproduction for share price fall,negative,news,"Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive.
Input: Glencore chief blames rivals' overproduction for share price fall
Answer: ",negative,negative,negative,negative,negative,negative,negative,negative
164,"FTSE 100 falls as China devaluation hits Burberry, mining stocks",negative,news,"Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive.
Input: FTSE 100 falls as China devaluation hits Burberry, mining stocks
Answer: ",negative,positive,negative,negative,negative,positive,negative,negative
165,Standard Chartered Shifts Emerging-Markets Strategy After Losses,negative,news,"Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive.
Input: Standard Chartered Shifts Emerging-Markets Strategy After Losses
Answer: ",negative,positive,positive,negative,negative,negative,negative,negative
166,Tesco criticised for 'disgraceful' advert showing domestic worker being slapped,negative,news,"Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive.
Input: Tesco criticised for 'disgraceful' advert showing domestic worker being slapped
Answer: ",negative,negative,negative,negative,negative,negative,negative,negative
167,$NUAN held up well after the big gains! Maybe we're finally on the move on this!!its still very undervalued and has major upside,positive,tweet,"Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.
Input: $NUAN held up well after the big gains! Maybe we're finally on the move on this!!its still very undervalued and has major upside
Answer: ",positive,positive,positive,positive,positive,negative,positive,positive
168,$PCLN Trying to break daily trend line! Big move could happen https://t.co/gY0aDb2jsQ https://t.co/KPBBCgQ2xy,positive,tweet,"Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.
Input: $PCLN Trying to break daily trend line! Big move could happen https://t.co/gY0aDb2jsQ https://t.co/KPBBCgQ2xy
Answer: ",positive,negative,negative,negative,negative,negative,positive,negative
169,$GS sells flat..I am out..,negative,tweet,"Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.
Input: $GS sells flat..I am out..
Answer: ",negative,positive,positive,negative,negative,negative,negative,negative
170,$VRTX early technical BUY signal... for confirmation > 86 it needs some fundam. incentive https://t.co/QuYSrqFo2x,positive,tweet,"Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.
Input: $VRTX early technical BUY signal... for confirmation > 86 it needs some fundam. incentive https://t.co/QuYSrqFo2x
Answer: ",positive,negative,negative,negative,negative,negative,positive,negative
171,ConAgra Names Former Hillshire Farms CEO Connolly to Top Post,positive,news,"Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive.
Input: ConAgra Names Former Hillshire Farms CEO Connolly to Top Post
Answer: ",positive,positive,negative,negative,negative,negative,positive,negative
172,$EXPE working on the second leg of its reversal run as it breaks another down trend and continues higher. https://t.co/76DSJysyR0,positive,tweet,"Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.
Input: $EXPE working on the second leg of its reversal run as it breaks another down trend and continues higher. https://t.co/76DSJysyR0
Answer: ",positive,negative,negative,negative,negative,negative,positive,negative
173,$CTRP breaking out https://t.co/Z2je3rTKch,positive,tweet,"Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.
Input: $CTRP breaking out https://t.co/Z2je3rTKch
Answer: ",positive,positive,positive,positive,positive,positive,positive,positive
174,"BHP Billiton slashes dividend, posts $5.67 billion net loss",negative,news,"Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive.
Input: BHP Billiton slashes dividend, posts $5.67 billion net loss
Answer: ",negative,negative,negative,negative,negative,negative,negative,negative
175,$AMZN new HOD with conviction keeping $570 on watch for Resistance.,positive,tweet,"Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.
Input: $AMZN new HOD with conviction keeping $570 on watch for Resistance.
Answer: ",positive,positive,positive,negative,negative,negative,positive,negative
176,"Hammerson, JV Partner secure ownership of Ireland's Dundrum - Quick Facts",positive,news,"Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive.
Input: Hammerson, JV Partner secure ownership of Ireland's Dundrum - Quick Facts
Answer: ",positive,negative,positive,negative,negative,negative,positive,negative
177,Why Alphabet Inc was just upgraded to buy https://t.co/dEVnLKhqtZ $GOOGL,positive,tweet,"Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.
Input: Why Alphabet Inc was just upgraded to buy https://t.co/dEVnLKhqtZ $GOOGL
Answer: ",positive,positive,positive,negative,negative,negative,positive,negative
178,$BAC $ADSK $NFLX long this morning,positive,tweet,"Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.
Input: $BAC $ADSK $NFLX long this morning
Answer: ",positive,positive,positive,negative,negative,positive,positive,positive
179,Legal & General share price: Finance chief to step down,negative,news,"Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive.
Input: Legal & General share price: Finance chief to step down
Answer: ",negative,negative,negative,negative,negative,negative,negative,negative
180,Surprising to see $JWN and $SKS sales numbers still holding up so well. I guess the high end might not be a concern after all.,positive,tweet,"Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.
Input: Surprising to see $JWN and $SKS sales numbers still holding up so well. I guess the high end might not be a concern after all.
Answer: ",positive,negative,negative,negative,negative,negative,positive,negative
181,$AAPL Good time to buy. Will the run come before earnings or after?,positive,tweet,"Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.
Input: $AAPL Good time to buy. Will the run come before earnings or after?
Answer: ",positive,negative,positive,negative,negative,negative,positive,negative
182,$TRX http://stks.co/1KkK Long setup. MACD cross.,positive,tweet,"Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.
Input: $TRX http://stks.co/1KkK Long setup. MACD cross.
Answer: ",positive,negative,positive,negative,negative,negative,positive,negative
183,"$CHKP ABC Bullish Pattern, Targets https://t.co/uVMmRSR5Zy",positive,tweet,"Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.
Input: $CHKP ABC Bullish Pattern, Targets https://t.co/uVMmRSR5Zy
Answer: ",positive,positive,negative,negative,negative,negative,positive,negative
184,"Goldman Sachs, Barclays, HSBC downplay Brexit threat",neutral,news,"Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive.
Input: Goldman Sachs, Barclays, HSBC downplay Brexit threat
Answer: ",neutral,negative,negative,negative,negative,negative,neutral,negative
185,"Isolationism? Another Sell Rating, Sell Ratings On SPY, QQQ, IWM And Several Companies https://t.co/j35FNnx744 $AAPL #APPLE $AXP $BAC",negative,tweet,"Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.
Input: Isolationism? Another Sell Rating, Sell Ratings On SPY, QQQ, IWM And Several Companies https://t.co/j35FNnx744 $AAPL #APPLE $AXP $BAC
Answer: ",negative,negative,negative,negative,negative,negative,negative,negative
186,BBCN Bancorp to buy Wilshire Bancorp in $1 bln deal,positive,news,"Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive.
Input: BBCN Bancorp to buy Wilshire Bancorp in $1 bln deal
Answer: ",positive,negative,negative,negative,negative,negative,positive,negative
187,How Kraft-Heinz Merger Came Together in Speedy 10 Weeks,positive,news,"Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive.
Input: How Kraft-Heinz Merger Came Together in Speedy 10 Weeks
Answer: ",positive,positive,positive,negative,positive,positive,positive,positive
188,$ISRG PT raised to $700 from $640 at Leerink - keeps Outperform rated,positive,tweet,"Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.
Input: $ISRG PT raised to $700 from $640 at Leerink - keeps Outperform rated
Answer: ",positive,negative,negative,negative,negative,negative,positive,negative
189,HSBC Hit by Fresh Details of Tax Evasion Claims,negative,news,"Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive.
Input: HSBC Hit by Fresh Details of Tax Evasion Claims
Answer: ",negative,negative,negative,negative,negative,negative,negative,negative
190,$KCG bot at 2.24,positive,tweet,"Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.
Input: $KCG bot at 2.24
Answer: ",positive,positive,positive,negative,negative,negative,positive,negative
191,$ZNGA http://stks.co/3rdu Looking for a test at 9.25 resistance point. cc @ cfrazierjr @FletchTrade #traders,positive,tweet,"Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.
Input: $ZNGA http://stks.co/3rdu Looking for a test at 9.25 resistance point. cc @ cfrazierjr @FletchTrade #traders
Answer: ",positive,negative,negative,negative,negative,negative,positive,negative
192,RBS Pays $1.7 Billion to Scrap U.K. Treasury's Dividend Rights,neutral,news,"Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive.
Input: RBS Pays $1.7 Billion to Scrap U.K. Treasury's Dividend Rights
Answer: ",neutral,negative,negative,negative,negative,negative,neutral,negative
193,"London open: Taylor Wimpey and Ashtead drive markets higher, Barclays falls",positive,news,"Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive.
Input: London open: Taylor Wimpey and Ashtead drive markets higher, Barclays falls
Answer: ",positive,negative,negative,negative,negative,negative,positive,negative
194,End Of Day Scan: Bullish MA Crossovers $BBVA $PDS $NTLS $NGL $SBRCY $FGL $MTNOY $TTT www.dailystockplays.com,positive,tweet,"Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.
Input: End Of Day Scan: Bullish MA Crossovers $BBVA $PDS $NTLS $NGL $SBRCY $FGL $MTNOY $TTT www.dailystockplays.com
Answer: ",positive,negative,negative,negative,negative,positive,positive,negative
195,@asdfLLC. Nice pop today. Told ya we would be green haha. Funny you bring that up. I'm actually working on a story about $NOK at the moment,positive,tweet,"Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.
Input: @asdfLLC. Nice pop today. Told ya we would be green haha. Funny you bring that up. I'm actually working on a story about $NOK at the moment
Answer: ",positive,positive,positive,negative,negative,negative,positive,negative
196,$GRPN might be selling off ahead of $P earnings...,negative,tweet,"Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.
Input: $GRPN might be selling off ahead of $P earnings...
Answer: ",negative,positive,positive,positive,negative,positive,negative,positive
197,UPDATE 5-Barclays Chairman McFarlane axes CEO to speed up strategic change,negative,news,"Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive.
Input: UPDATE 5-Barclays Chairman McFarlane axes CEO to speed up strategic change
Answer: ",negative,negative,negative,negative,negative,negative,negative,negative
198,Shares in BAE Systems hit 10-month high on rating upgrade,positive,news,"Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive.
Input: Shares in BAE Systems hit 10-month high on rating upgrade
Answer: ",positive,positive,positive,positive,positive,positive,positive,positive
199,"FDA approves NPS drug, in move validating Shire takeover deal",positive,news,"Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive.
Input: FDA approves NPS drug, in move validating Shire takeover deal
Answer: ",positive,positive,positive,negative,negative,positive,positive,positive
200,$renn topping tail 5 min. chart at 7.31 short from here.,negative,tweet,"Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.
Input: $renn topping tail 5 min. chart at 7.31 short from here.
Answer: ",negative,positive,positive,negative,negative,negative,negative,negative
201,Shell share price: Standard Life announce position against BG acquisition,negative,news,"Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive.
Input: Shell share price: Standard Life announce position against BG acquisition
Answer: ",negative,positive,positive,negative,negative,negative,negative,negative
202,CompaniesHome Retail trims gains but is considered 'in play',positive,news,"Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive.
Input: CompaniesHome Retail trims gains but is considered 'in play'
Answer: ",positive,negative,negative,negative,negative,negative,positive,negative
203,stole my tweet. really wouldn't be surprised if we took out 423 and pinned around it RT @totalguru We could possibly even see425 today $AAPL,positive,tweet,"Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.
Input: stole my tweet. really wouldn't be surprised if we took out 423 and pinned around it RT @totalguru We could possibly even see425 today $AAPL
Answer: ",positive,negative,negative,negative,negative,negative,positive,negative
204,$ELN longs...congrats...another HOD,positive,tweet,"Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.
Input: $ELN longs...congrats...another HOD
Answer: ",positive,positive,positive,positive,positive,positive,positive,positive
205,"Intuitive Surgical $ISRG is in a great financial position, take a look https://t.co/VahhJAcBFG https://t.co/24hQTQX4ou",positive,tweet,"Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.
Input: Intuitive Surgical $ISRG is in a great financial position, take a look https://t.co/VahhJAcBFG https://t.co/24hQTQX4ou
Answer: ",positive,negative,negative,negative,negative,negative,positive,negative
206,"$AAPL AAPL: Gundlach Slams iPad mini, Sees Downside to $425. http://stks.co/bDqV",negative,tweet,"Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.
Input: $AAPL AAPL: Gundlach Slams iPad mini, Sees Downside to $425. http://stks.co/bDqV
Answer: ",negative,negative,negative,negative,negative,negative,negative,negative
207,Tesco share price tumbles after negative broker note,negative,news,"Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive.
Input: Tesco share price tumbles after negative broker note
Answer: ",negative,negative,negative,negative,negative,positive,negative,negative
208,$ENB.CA {Head&Shoulders} bullish reversal setup and breakout. Oil and Gas Pipleline stock. $USO,positive,tweet,"Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.
Input: $ENB.CA {Head&Shoulders} bullish reversal setup and breakout. Oil and Gas Pipleline stock. $USO
Answer: ",positive,positive,positive,positive,positive,positive,positive,positive
209,"Philip Morris, BAT Sue Over Law Taking Branding Off Packs",negative,news,"Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive.
Input: Philip Morris, BAT Sue Over Law Taking Branding Off Packs
Answer: ",negative,positive,negative,negative,negative,negative,negative,negative
210,$SAP Q1 disappoints as #software licenses down. Real problem? #Cloud growth trails $MSFT $ORCL $GOOG $CRM $ADBE https://t.co/jNDphllzq5,negative,tweet,"Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.
Input: $SAP Q1 disappoints as #software licenses down. Real problem? #Cloud growth trails $MSFT $ORCL $GOOG $CRM $ADBE https://t.co/jNDphllzq5
Answer: ",negative,negative,negative,negative,negative,negative,negative,negative
211,Juniper tumbles on Q1 warning; Cisco also lower https://t.co/N8X8BpLJ1E $JNPR $CSCO,negative,tweet,"Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.
Input: Juniper tumbles on Q1 warning; Cisco also lower https://t.co/N8X8BpLJ1E $JNPR $CSCO
Answer: ",negative,positive,negative,negative,negative,negative,negative,negative
212,MT @TheAcsMan Amazing seeing everyone suddenly touting $MSFT. Long been favorite covered call & double dip dividend play.,positive,tweet,"Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.
Input: MT @TheAcsMan Amazing seeing everyone suddenly touting $MSFT. Long been favorite covered call & double dip dividend play.
Answer: ",positive,positive,positive,positive,negative,negative,positive,positive
213,Out of shorts $ALTR at 38.85 with loss,positive,tweet,"Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.
Input: Out of shorts $ALTR at 38.85 with loss
Answer: ",positive,positive,positive,positive,positive,positive,positive,positive
214,$AAPL price momentum weakening going into the close.,negative,tweet,"Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.
Input: $AAPL price momentum weakening going into the close.
Answer: ",negative,positive,positive,positive,negative,positive,negative,positive
215,$FB watching for bounce tomorrow,positive,tweet,"Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.
Input: $FB watching for bounce tomorrow
Answer: ",positive,positive,positive,positive,positive,positive,positive,positive
216,Valeant Said to Name New CEO With Pearson Still Hospitalized,neutral,news,"Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive.
Input: Valeant Said to Name New CEO With Pearson Still Hospitalized
Answer: ",neutral,positive,positive,negative,negative,negative,neutral,negative
217,$aapl. Test the high today and probably go beyond after hours...,positive,tweet,"Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.
Input: $aapl. Test the high today and probably go beyond after hours...
Answer: ",positive,negative,negative,negative,negative,negative,positive,negative
218,Builder Persimmon hails 6% rise in house sales,positive,news,"Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive.
Input: Builder Persimmon hails 6% rise in house sales
Answer: ",positive,negative,positive,negative,negative,negative,positive,negative
219,"$FB trend, hits mid 110's and drops",negative,tweet,"Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.
Input: $FB trend, hits mid 110's and drops
Answer: ",negative,positive,positive,negative,negative,negative,negative,negative
220,Crown Castle buys Tower Development Corp for $461 million,positive,news,"Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive.
Input: Crown Castle buys Tower Development Corp for $461 million
Answer: ",positive,negative,positive,negative,negative,negative,positive,negative
221,@Joerazorback This time I think $AAPL will miss again. Generally speaking market is near top when everyone thinks that market goes only up,negative,tweet,"Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.
Input: @Joerazorback This time I think $AAPL will miss again. Generally speaking market is near top when everyone thinks that market goes only up
Answer: ",negative,negative,negative,negative,negative,negative,negative,negative
222,Whitbread share price climbs on Q4 sales growth,positive,news,"Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive.
Input: Whitbread share price climbs on Q4 sales growth
Answer: ",positive,positive,positive,negative,positive,positive,positive,positive
223,@saltwaternurse $INO can test 10 again in next few days. time to take some profits here. or hedge with puts.,negative,tweet,"Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.
Input: @saltwaternurse $INO can test 10 again in next few days. time to take some profits here. or hedge with puts.
Answer: ",negative,negative,negative,negative,negative,negative,negative,negative
224,Barclays Bonds Rise as Lender Cuts Dividends to Shore Up Capital,positive,news,"Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive.
Input: Barclays Bonds Rise as Lender Cuts Dividends to Shore Up Capital
Answer: ",positive,positive,positive,positive,negative,positive,positive,positive
225,5 Best Analyst Rated Stocks in Last 72hrs: $ORCL $AAPL $CBS $INO $CPXX View all ratings here: https://t.co/IRID6zd5gc,positive,tweet,"Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.
Input: 5 Best Analyst Rated Stocks in Last 72hrs: $ORCL $AAPL $CBS $INO $CPXX View all ratings here: https://t.co/IRID6zd5gc
Answer: ",positive,negative,negative,negative,negative,negative,positive,negative
226,GKN to buy Fokker Technologies for 706 mln euros,positive,news,"Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive.
Input: GKN to buy Fokker Technologies for 706 mln euros
Answer: ",positive,positive,negative,negative,negative,negative,positive,negative
227,UPDATE 3-Ex-Barclays director accused by US of illegal tips to plumber,negative,news,"Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive.
Input: UPDATE 3-Ex-Barclays director accused by US of illegal tips to plumber
Answer: ",negative,negative,negative,negative,negative,negative,negative,negative
228,SAB's Chairman Digs In With Board Divided on InBev Offer,neutral,news,"Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive.
Input: SAB's Chairman Digs In With Board Divided on InBev Offer
Answer: ",neutral,negative,negative,negative,negative,negative,neutral,negative
229,@scottrade Why is $tsla not available for shorting at this time? Same for $w?,negative,tweet,"Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.
Input: @scottrade Why is $tsla not available for shorting at this time? Same for $w?
Answer: ",negative,negative,negative,negative,negative,negative,negative,negative
230,@BULLYA @pollux654321 My 50 $KORS 80 Calls are going to b a Blessing for my Daughters tuition!,positive,tweet,"Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.
Input: @BULLYA @pollux654321 My 50 $KORS 80 Calls are going to b a Blessing for my Daughters tuition!
Answer: ",positive,positive,positive,negative,negative,negative,positive,negative
231,"Still short $LNG from $11.70 area...next stop could be down through $9.00. Someone slammed it hard with 230,000 shs this am! More to follow",negative,tweet,"Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.
Input: Still short $LNG from $11.70 area...next stop could be down through $9.00. Someone slammed it hard with 230,000 shs this am! More to follow
Answer: ",negative,negative,negative,negative,negative,negative,negative,negative
232,UPDATE 1-Lloyds to cut 945 jobs as part of 3-year restructuring plan,negative,news,"Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive.
Input: UPDATE 1-Lloyds to cut 945 jobs as part of 3-year restructuring plan
Answer: ",negative,negative,negative,negative,negative,negative,negative,negative
233,$FTI Breakout today after reporting earnings last night,positive,tweet,"Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.
Input: $FTI Breakout today after reporting earnings last night
Answer: ",positive,positive,positive,negative,negative,positive,positive,positive
234,$TRIP maintains Neutral rating at JP Morgan- PT cut $61 from $66,neutral,tweet,"Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.
Input: $TRIP maintains Neutral rating at JP Morgan- PT cut $61 from $66
Answer: ",neutral,negative,positive,negative,negative,negative,neutral,negative
235,GSK and Novartis complete deals to reshape both drugmakers,positive,news,"Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive.
Input: GSK and Novartis complete deals to reshape both drugmakers
Answer: ",positive,positive,negative,negative,negative,negative,positive,negative
236,"potential defect with third-row seat belts. Tesla Motors recalls 2,700 Model X SUVs $TSLA https://t.co/YVYDncdNdi",negative,tweet,"Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.
Input: potential defect with third-row seat belts. Tesla Motors recalls 2,700 Model X SUVs $TSLA https://t.co/YVYDncdNdi
Answer: ",negative,negative,negative,negative,negative,negative,negative,negative
237,$PRGN A bottom right here?,neutral,tweet,"Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.
Input: $PRGN A bottom right here?
Answer: ",neutral,negative,positive,negative,negative,positive,neutral,negative
238,Primark racks up a happy Christmas after strong sales,positive,news,"Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive.
Input: Primark racks up a happy Christmas after strong sales
Answer: ",positive,positive,positive,negative,positive,positive,positive,positive
239,AB InBev attacks SABMiller bid rebuffal,negative,news,"Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive.
Input: AB InBev attacks SABMiller bid rebuffal
Answer: ",negative,negative,negative,negative,negative,negative,negative,negative
240,@technik I still have a smaller $GILD pos. Being very tender with cash due to volatility. So reluctant to keep many big positions.,positive,tweet,"Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.
Input: @technik I still have a smaller $GILD pos. Being very tender with cash due to volatility. So reluctant to keep many big positions.
Answer: ",positive,positive,negative,negative,negative,negative,positive,negative
241,EasyJet attracts more passengers in June but still lags Ryanair,positive,news,"Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive.
Input: EasyJet attracts more passengers in June but still lags Ryanair
Answer: ",positive,positive,negative,negative,negative,positive,positive,negative
242,"Oil majors like Royal Dutch Shell, Chevron, BP fail to find reserves to counter ...",negative,news,"Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive.
Input: Oil majors like Royal Dutch Shell, Chevron, BP fail to find reserves to counter ...
Answer: ",negative,negative,negative,negative,negative,negative,negative,negative
243,CompaniesLSE adds ex-SEC head Schapiro to board,neutral,news,"Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive.
Input: CompaniesLSE adds ex-SEC head Schapiro to board
Answer: ",neutral,negative,negative,negative,negative,negative,neutral,negative
244,"UK housing market steadies after Brexit dip, Persimmon says",positive,news,"Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive.
Input: UK housing market steadies after Brexit dip, Persimmon says
Answer: ",positive,negative,positive,negative,negative,positive,positive,negative
245,Royal Mail share price edges lower as group raises stamp price,negative,news,"Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive.
Input: Royal Mail share price edges lower as group raises stamp price
Answer: ",negative,positive,negative,negative,negative,positive,negative,negative
246,"Are Aviva plc, Direct Line Insurance Group PLC And Admiral Group plc Set To Soar?",positive,news,"Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive.
Input: Are Aviva plc, Direct Line Insurance Group PLC And Admiral Group plc Set To Soar?
Answer: ",positive,negative,negative,negative,negative,negative,positive,negative
247,"$ATVI ooks pretty bullish for now. from a short-term perspective, it's got a good chance of maybe sliding back to 33.70 #stocks #investing",positive,tweet,"Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.
Input: $ATVI ooks pretty bullish for now. from a short-term perspective, it's got a good chance of maybe sliding back to 33.70 #stocks #investing
Answer: ",positive,negative,negative,negative,negative,negative,positive,negative
248,MarketsBP promotes upstream boss to deputy CEO,neutral,news,"Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive.
Input: MarketsBP promotes upstream boss to deputy CEO
Answer: ",neutral,negative,negative,negative,negative,negative,neutral,negative
249,$RDC Rowan Expands Share Repurchase Program to $150 million,positive,tweet,"Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.
Input: $RDC Rowan Expands Share Repurchase Program to $150 million
Answer: ",positive,positive,positive,negative,negative,negative,positive,negative
250,"$STX long play, another consistent profit zone.. check it out https://t.co/DQfuzOzYlh https://t.co/ggne4ayzqn",positive,tweet,"Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.
Input: $STX long play, another consistent profit zone.. check it out https://t.co/DQfuzOzYlh https://t.co/ggne4ayzqn
Answer: ",positive,negative,negative,negative,negative,negative,positive,negative
251,$AAPL at resistance right here...sold my shares...will buy back if it dips or if it goes in the 128 gap zone,negative,tweet,"Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.
Input: $AAPL at resistance right here...sold my shares...will buy back if it dips or if it goes in the 128 gap zone
Answer: ",negative,negative,negative,negative,negative,negative,negative,negative
252,Locked in some $FB puts for nice gain,negative,tweet,"Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.
Input: Locked in some $FB puts for nice gain
Answer: ",negative,positive,positive,positive,positive,positive,negative,positive
253,Industry NewsWolseley confident in reslilience amid mixed markets,positive,news,"Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive.
Input: Industry NewsWolseley confident in reslilience amid mixed markets
Answer: ",positive,positive,positive,negative,negative,positive,positive,positive
254,AstraZeneca sells Caprelsa rights to Sanofi unit,positive,news,"Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive.
Input: AstraZeneca sells Caprelsa rights to Sanofi unit
Answer: ",positive,positive,positive,negative,positive,positive,positive,positive
255,$GNRC finding support at its 10-day line so far.,positive,tweet,"Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.
Input: $GNRC finding support at its 10-day line so far.
Answer: ",positive,positive,positive,negative,positive,positive,positive,positive
256,"$CNP Sell Short Position on CNP,...Closed for Profit $ 59,367.00 (7.75%) http://stks.co/ghjc",positive,tweet,"Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.
Input: $CNP Sell Short Position on CNP,...Closed for Profit $ 59,367.00 (7.75%) http://stks.co/ghjc
Answer: ",positive,negative,negative,negative,negative,negative,positive,negative
257,"Lots of metal stocks look like a 5-10% run awaits. Long $SSRI,$PAAS and $NEM but most high quality names should go if metal prices cooperate",positive,tweet,"Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.
Input: Lots of metal stocks look like a 5-10% run awaits. Long $SSRI,$PAAS and $NEM but most high quality names should go if metal prices cooperate
Answer: ",positive,negative,negative,negative,negative,negative,positive,negative
258,Morrisons finance chief to fill gap as CEO leaves early,negative,news,"Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive.
Input: Morrisons finance chief to fill gap as CEO leaves early
Answer: ",negative,negative,negative,negative,negative,negative,negative,negative
259,Horizonte acquires neighbouring Glencore nickel property in Brazil,positive,news,"Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive.
Input: Horizonte acquires neighbouring Glencore nickel property in Brazil
Answer: ",positive,positive,positive,negative,positive,positive,positive,positive
260,Exact (EXAS) Flagged As Strong On High Volume $EXAS http://stks.co/r26Ra,positive,tweet,"Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.
Input: Exact (EXAS) Flagged As Strong On High Volume $EXAS http://stks.co/r26Ra
Answer: ",positive,positive,negative,negative,negative,negative,positive,negative
261,My $DWA play up 6% today. I'm still skeptical. Will take profits. Not a time cheer,neutral,tweet,"Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.
Input: My $DWA play up 6% today. I'm still skeptical. Will take profits. Not a time cheer
Answer: ",neutral,negative,negative,negative,negative,negative,neutral,negative
262,Breakingviews: IAG can pay more for Aer Lingus,positive,news,"Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive.
Input: Breakingviews: IAG can pay more for Aer Lingus
Answer: ",positive,positive,positive,negative,negative,positive,positive,positive
263,$PLUG bear raid,negative,tweet,"Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.
Input: $PLUG bear raid
Answer: ",negative,positive,positive,negative,negative,positive,negative,positive
264,$GOOGL is a short below 740 into the upper BB and is overbought,negative,tweet,"Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.
Input: $GOOGL is a short below 740 into the upper BB and is overbought
Answer: ",negative,negative,negative,negative,negative,negative,negative,negative
265,$FB they are hitting everything in sight.short it. but twtr,negative,tweet,"Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.
Input: $FB they are hitting everything in sight.short it. but twtr
Answer: ",negative,negative,negative,negative,negative,negative,negative,negative
266,$EDU bouncing nicely after add-on (posted),positive,tweet,"Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.
Input: $EDU bouncing nicely after add-on (posted)
Answer: ",positive,positive,positive,negative,positive,positive,positive,positive
267,Long $PCLN,positive,tweet,"Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.
Input: Long $PCLN
Answer: ",positive,positive,positive,positive,positive,positive,positive,positive
268,Exact (EXAS) Flagged As Strong On High Volume $EXAS http://stks.co/r26Ra,positive,tweet,"Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.
Input: Exact (EXAS) Flagged As Strong On High Volume $EXAS http://stks.co/r26Ra
Answer: ",positive,negative,negative,negative,negative,negative,positive,negative
269,Shire proposes $30 bln all-share tie-up with Baxalta,positive,news,"Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive.
Input: Shire proposes $30 bln all-share tie-up with Baxalta
Answer: ",positive,negative,positive,negative,negative,negative,positive,negative
270,$aapl key is to breakout above 460 on solid volume or else it's a no trade for now,positive,tweet,"Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.
Input: $aapl key is to breakout above 460 on solid volume or else it's a no trade for now
Answer: ",positive,negative,negative,negative,negative,negative,positive,negative
271,"Rio Tinto swings to loss, drops dividend policy",negative,news,"Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive.
Input: Rio Tinto swings to loss, drops dividend policy
Answer: ",negative,negative,negative,negative,negative,negative,negative,negative
272,CompaniesUnilever sales lifted by ice cream in soft economy,positive,news,"Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive.
Input: CompaniesUnilever sales lifted by ice cream in soft economy
Answer: ",positive,positive,positive,negative,positive,positive,positive,positive
273,"Last month we added to our $GILD position and started a new one in $BWLD We see slow, steady, unspectacular growth going forward near term",positive,tweet,"Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive.
Input: Last month we added to our $GILD position and started a new one in $BWLD We see slow, steady, unspectacular growth going forward near term
Answer: ",positive,negative,negative,negative,negative,negative,positive,negative
274,Investors Remain Skeptical About Shell-BG Deal,negative,news,"Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive.","Instruction: Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive.
Input: Investors Remain Skeptical About Shell-BG Deal
Answer: ",negative,positive,negative,negative,negative,negative,negative,negative
1 input output text_type instruction context target out_text_0 out_text_1 out_text_2 out_text_3 out_text_4 new_target new_out
2 0 This $BBBY stock options trade would have more than doubled your money https://t.co/Oa0loiRIJL via @TheStreet positive tweet Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Input: This $BBBY stock options trade would have more than doubled your money https://t.co/Oa0loiRIJL via @TheStreet Answer: positive positive positive positive negative negative positive positive
3 1 $COST short finally making gains. I will take half my gains at 147 negative tweet Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Input: $COST short finally making gains. I will take half my gains at 147 Answer: negative positive positive positive positive positive negative positive
4 2 $KO had missed earnings expectations for the last two quarters, so today’s strong results came as a major surprise http://stks.co/d0RHF positive tweet Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Input: $KO had missed earnings expectations for the last two quarters, so today’s strong results came as a major surprise http://stks.co/d0RHF Answer: positive positive positive negative negative negative positive negative
5 3 #Fintech provider $CAFN Cachet Financial Solutions Surging Forward today post earnings Up +13.26% https://t.co/9BJ3csk2i9 $JKHY $FISV #Momo positive tweet Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Input: #Fintech provider $CAFN Cachet Financial Solutions Surging Forward today post earnings Up +13.26% https://t.co/9BJ3csk2i9 $JKHY $FISV #Momo Answer: positive negative negative negative negative positive positive negative
6 4 Daily Mail owner considering Yahoo bid $yhoo ,up 2,05% https://t.co/extZr1riyP positive tweet Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Input: Daily Mail owner considering Yahoo bid $yhoo ,up 2,05% https://t.co/extZr1riyP Answer: positive positive negative negative negative negative positive negative
7 5 SAB's Chairman Digs In With Board Divided on InBev Offer neutral news Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive. Input: SAB's Chairman Digs In With Board Divided on InBev Offer Answer: neutral negative negative negative negative negative neutral negative
8 6 Insurers: Admiral blows hot and cold but Aviva soars pre-Friends Life merger neutral news Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive. Input: Insurers: Admiral blows hot and cold but Aviva soars pre-Friends Life merger Answer: neutral positive positive negative negative positive neutral positive
9 7 BRIEF-Legal & General's retirement business books 4 billion stg H1 sales positive news Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive. Input: BRIEF-Legal & General's retirement business books 4 billion stg H1 sales Answer: positive negative negative negative negative negative positive negative
10 8 Ocwen Reaches Settlement With California Regulator positive news Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive. Input: Ocwen Reaches Settlement With California Regulator Answer: positive negative negative negative negative negative positive negative
11 9 UPDATE 3-BP settles oil spill-related claims with Halliburton, Transocean negative news Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive. Input: UPDATE 3-BP settles oil spill-related claims with Halliburton, Transocean Answer: negative negative negative negative negative negative negative negative
12 10 $CRUS Upgraded to a buy by Alpha Street Research positive tweet Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Input: $CRUS Upgraded to a buy by Alpha Street Research Answer: positive positive positive positive negative positive positive positive
13 11 $DNN picked some up, like this going into 2014 positive tweet Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Input: $DNN picked some up, like this going into 2014 Answer: positive positive positive negative negative positive positive positive
14 12 Berkshire Hathaway names Kara Raiguel to lead General Re unit neutral news Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive. Input: Berkshire Hathaway names Kara Raiguel to lead General Re unit Answer: neutral positive positive negative negative positive neutral positive
15 13 Tesco leads leap in FTSE 100; Marks & Spencer drops positive news Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive. Input: Tesco leads leap in FTSE 100; Marks & Spencer drops Answer: positive negative negative negative negative negative positive negative
16 14 RT @tomhend777 $MU needs to hold here -Broken for now. Needs big flush. Still not technically oversold so now big bounce yet neutral tweet Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Input: RT @tomhend777 $MU needs to hold here -Broken for now. Needs big flush. Still not technically oversold so now big bounce yet Answer: neutral negative negative negative negative negative neutral negative
17 15 $GOOGL is setting up above its 50-day moving average. https://t.co/tTm9RnFoXJ positive tweet Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Input: $GOOGL is setting up above its 50-day moving average. https://t.co/tTm9RnFoXJ Answer: positive negative negative negative negative negative positive negative
18 16 Irish housebuilder Cairn Homes plans London listing positive news Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive. Input: Irish housebuilder Cairn Homes plans London listing Answer: positive negative negative negative negative negative positive negative
19 17 78 users on Vetr are bearish on Tesla Motors, Inc., indicating a SELL Rating (2 stars) for $TSLA https://t.co/vVpzqCXsNJ negative tweet Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Input: 78 users on Vetr are bearish on Tesla Motors, Inc., indicating a SELL Rating (2 stars) for $TSLA https://t.co/vVpzqCXsNJ Answer: negative positive positive positive positive positive negative positive
20 18 $OSUR up 33% since 6/25 buy signal. resistance 5.33 - expect 1. pullback 2nd half of day or 2. break abov 5.33 & continue rally for 4-5 days positive tweet Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Input: $OSUR up 33% since 6/25 buy signal. resistance 5.33 - expect 1. pullback 2nd half of day or 2. break abov 5.33 & continue rally for 4-5 days Answer: positive negative negative negative negative negative positive negative
21 19 Long $GPRO for a brealout trade positive tweet Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Input: Long $GPRO for a brealout trade Answer: positive positive positive positive positive positive positive positive
22 20 $NFLX small pos, short 180 wkly puts. negative tweet Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Input: $NFLX small pos, short 180 wkly puts. Answer: negative positive positive positive negative positive negative positive
23 21 $SLV -4.44% at 18 now AWFUL, down from 42.50 negative tweet Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Input: $SLV -4.44% at 18 now AWFUL, down from 42.50 Answer: negative positive positive negative negative negative negative negative
24 22 Investors Remain Skeptical About Shell-BG Deal negative news Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive. Input: Investors Remain Skeptical About Shell-BG Deal Answer: negative positive negative negative negative negative negative negative
25 23 easyJet leads Britain's FTSE lower as global bond rout resumes negative news Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive. Input: easyJet leads Britain's FTSE lower as global bond rout resumes Answer: negative negative negative negative negative negative negative negative
26 24 UPDATE 1-BP shareholders back more disclosure on climate change risks neutral news Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive. Input: UPDATE 1-BP shareholders back more disclosure on climate change risks Answer: neutral negative negative negative negative negative neutral negative
27 25 5-star analyst @brianwieser from Pivotal Research upgraded rating on $GOOGL to BUY. Brian has a 79% success rate https://t.co/t0dn02EOH5 positive tweet Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Input: 5-star analyst @brianwieser from Pivotal Research upgraded rating on $GOOGL to BUY. Brian has a 79% success rate https://t.co/t0dn02EOH5 Answer: positive positive negative negative negative positive positive negative
28 26 Glencore sees Tripoli-based NOC as sole legal seller of Libyan oil neutral news Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive. Input: Glencore sees Tripoli-based NOC as sole legal seller of Libyan oil Answer: neutral negative positive negative negative negative neutral negative
29 27 Fastenal misses by $0.01, misses on revenue $FAST #NYSE https://t.co/63JHQ7pwMN negative tweet Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Input: Fastenal misses by $0.01, misses on revenue $FAST #NYSE https://t.co/63JHQ7pwMN Answer: negative negative negative negative negative negative negative negative
30 28 $NIHD insiders got this one wrong. Looking for bottom. Rsi under 30 negative tweet Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Input: $NIHD insiders got this one wrong. Looking for bottom. Rsi under 30 Answer: negative positive positive negative negative negative negative negative
31 29 AstraZeneca's Lung Cancer Drug Tagrisso Gets FDA Approval positive news Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive. Input: AstraZeneca's Lung Cancer Drug Tagrisso Gets FDA Approval Answer: positive positive positive positive positive positive positive positive
32 30 looks like a big feb 18-22 $put spread on $cree. Last quarter 0% YoY rev growth trading @ 24x earnings. I may try a short. negative tweet Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Input: looks like a big feb 18-22 $put spread on $cree. Last quarter 0% YoY rev growth trading @ 24x earnings. I may try a short. Answer: negative negative negative negative negative negative negative negative
33 31 Miners Meltdown as BHP to Rio Tinto Sink in Commodities Rout negative news Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive. Input: Miners Meltdown as BHP to Rio Tinto Sink in Commodities Rout Answer: negative negative negative negative negative negative negative negative
34 32 Starbucks' Digital Strategy To Drive Significant Growth With Customer Loyalty $SBUX https://t.co/Xk6lZ3UI3K positive tweet Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Input: Starbucks' Digital Strategy To Drive Significant Growth With Customer Loyalty $SBUX https://t.co/Xk6lZ3UI3K Answer: positive negative negative negative negative negative positive negative
35 33 UPDATE: EasyJet Passenger Numbers, Aer Lingus Traffic Up In February positive news Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive. Input: UPDATE: EasyJet Passenger Numbers, Aer Lingus Traffic Up In February Answer: positive positive positive negative negative positive positive positive
36 34 Should you buy Associated British Foods plc, Great Portland Estates plc and Dunelm Group plc following today's news? positive news Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive. Input: Should you buy Associated British Foods plc, Great Portland Estates plc and Dunelm Group plc following today's news? Answer: positive negative negative negative negative negative positive negative
37 35 Deutsche Bank cuts $SBUX negative tweet Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Input: Deutsche Bank cuts $SBUX Answer: negative positive positive negative negative positive negative positive
38 36 Saudi Aramco, Shell plan to break up Motiva, divide up assets negative news Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive. Input: Saudi Aramco, Shell plan to break up Motiva, divide up assets Answer: negative negative negative negative negative negative negative negative
39 37 Rolls-Royce to Ensure Compliance After Petrobras Bribery Report neutral news Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive. Input: Rolls-Royce to Ensure Compliance After Petrobras Bribery Report Answer: neutral negative negative negative negative negative neutral negative
40 38 AstraZeneca And Daiichi Sankyo To Jointly Commercialise MOVANTIK In The US positive news Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive. Input: AstraZeneca And Daiichi Sankyo To Jointly Commercialise MOVANTIK In The US Answer: positive positive positive negative positive positive positive positive
41 39 Why $MCD looks set to fall further. http://stks.co/f2fgj negative tweet Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Input: Why $MCD looks set to fall further. http://stks.co/f2fgj Answer: negative negative negative negative negative negative negative negative
42 40 Britain's FTSE outperforms Europe, Royal Mail and Tesco rise positive news Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive. Input: Britain's FTSE outperforms Europe, Royal Mail and Tesco rise Answer: positive negative negative negative negative negative positive negative
43 41 $NFLX +1% $104.80 LONG streaming services rapidly outpacing traditional cable positive tweet Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Input: $NFLX +1% $104.80 LONG streaming services rapidly outpacing traditional cable Answer: positive positive positive negative positive positive positive positive
44 42 $PLUG Closed short position. Small gain. Not interested in options expiring worthless positive tweet Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Input: $PLUG Closed short position. Small gain. Not interested in options expiring worthless Answer: positive negative positive negative negative negative positive negative
45 43 RT @Cash_Cow $TLT still has a rising RSI & MACD, all this bond buying is signaling some bad moves for the market. $SPY $UUP negative tweet Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Input: RT @Cash_Cow $TLT still has a rising RSI & MACD, all this bond buying is signaling some bad moves for the market. $SPY $UUP Answer: negative negative negative negative negative negative negative negative
46 44 $NFLX VISION : short term consolidation then movement higher http://stks.co/j05uu positive tweet Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Input: $NFLX VISION : short term consolidation then movement higher http://stks.co/j05uu Answer: positive positive positive negative negative negative positive negative
47 45 $INVE : SEE YA ABOVE $8 positive tweet Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Input: $INVE : SEE YA ABOVE $8 Answer: positive positive positive positive negative positive positive positive
48 46 AB InBev offers SABMiller $3 billion breakup fee positive news Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive. Input: AB InBev offers SABMiller $3 billion breakup fee Answer: positive negative negative negative negative negative positive negative
49 47 Citrix Systems Inc $CTXS Position Increased by Mizuho… https://t.co/v7Lkq08Flp @ShareStockNews positive tweet Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Input: Citrix Systems Inc $CTXS Position Increased by Mizuho… https://t.co/v7Lkq08Flp @ShareStockNews Answer: positive negative negative negative negative negative positive negative
50 48 $NUGT longer term bullish positive tweet Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Input: $NUGT longer term bullish Answer: positive positive positive positive positive positive positive positive
51 49 Loaded up on $bsx yesterday,looking good now. Still think way more upside than downside. positive tweet Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Input: Loaded up on $bsx yesterday,looking good now. Still think way more upside than downside. Answer: positive negative positive negative negative negative positive negative
52 50 FDA approves Shire's Vyvanse for binge-eating disorder positive news Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive. Input: FDA approves Shire's Vyvanse for binge-eating disorder Answer: positive negative positive negative negative negative positive negative
53 51 $HAL If bulls lucky enuff to get an upside gap fill, better take it. Wouldn't chase it here. http://stks.co/r12Us neutral tweet Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Input: $HAL If bulls lucky enuff to get an upside gap fill, better take it. Wouldn't chase it here. http://stks.co/r12Us Answer: neutral negative negative negative negative negative neutral negative
54 52 Short interest increases yet again http://stks.co/e19h via @ryandetrick $SPY negative tweet Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Input: Short interest increases yet again http://stks.co/e19h via @ryandetrick $SPY Answer: negative positive positive negative negative negative negative negative
55 53 $BBRY lets see 14+ today positive tweet Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Input: $BBRY lets see 14+ today Answer: positive positive positive negative negative positive positive positive
56 54 Reuters: Green Mountain revenue misses, shares plunge http://stks.co/13mW > $GMCR prints 43.80, market in a foul mood, bad day to disappoint negative tweet Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Input: Reuters: Green Mountain revenue misses, shares plunge http://stks.co/13mW > $GMCR prints 43.80, market in a foul mood, bad day to disappoint Answer: negative negative negative negative negative negative negative negative
57 55 #Apple up almost 20% from its February lows with very little fanfare. $AAPL positive tweet Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Input: #Apple up almost 20% from its February lows with very little fanfare. $AAPL Answer: positive positive positive negative negative negative positive negative
58 56 Shell and BG Shareholders to Vote on Deal at End of January neutral news Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive. Input: Shell and BG Shareholders to Vote on Deal at End of January Answer: neutral negative negative negative negative negative neutral negative
59 57 RBI surprises Street; Sensex pares gains after hitting mount 30k negative news Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive. Input: RBI surprises Street; Sensex pares gains after hitting mount 30k Answer: negative negative negative negative negative negative negative negative
60 58 X marks the recall: Tesla recalls #ModelX for faulty 3rd row seat. https://t.co/HSqdoVry07 $TSLA https://t.co/4Cs3CNZEBB negative tweet Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Input: X marks the recall: Tesla recalls #ModelX for faulty 3rd row seat. https://t.co/HSqdoVry07 $TSLA https://t.co/4Cs3CNZEBB Answer: negative negative negative negative negative negative negative negative
61 59 $QCOR a little pullback is fine but if this erases all of todays gains, I cannot believe the manipulation its capable of negative tweet Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Input: $QCOR a little pullback is fine but if this erases all of todays gains, I cannot believe the manipulation its capable of Answer: negative negative negative negative negative negative negative negative
62 60 Glencore slumps 30 percent as debt fears grow negative news Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive. Input: Glencore slumps 30 percent as debt fears grow Answer: negative positive negative negative negative positive negative negative
63 61 $TSLA <STUDY the CHARTS> Pullback_Time https://t.co/ZMDG0fb3I7 negative tweet Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Input: $TSLA <STUDY the CHARTS> Pullback_Time https://t.co/ZMDG0fb3I7 Answer: negative positive positive negative negative negative negative negative
64 62 LONDON MORNING BRIEFING: HSBC And Standard Chartered Shares Rise positive news Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive. Input: LONDON MORNING BRIEFING: HSBC And Standard Chartered Shares Rise Answer: positive positive negative negative negative negative positive negative
65 63 AstraZeneca's patent on asthma drug invalidated by US court negative news Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive. Input: AstraZeneca's patent on asthma drug invalidated by US court Answer: negative negative negative negative negative negative negative negative
66 64 Is It Worth Investing In Tesco PLC And Prudential plc Now? positive news Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive. Input: Is It Worth Investing In Tesco PLC And Prudential plc Now? Answer: positive negative negative negative negative negative positive negative
67 65 NYSE owner ICE considers offer for LSE positive news Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive. Input: NYSE owner ICE considers offer for LSE Answer: positive negative negative negative negative negative positive negative
68 66 $ESI on lows, down $1.50 to $2.50 BK a real possibility negative tweet Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Input: $ESI on lows, down $1.50 to $2.50 BK a real possibility Answer: negative negative negative negative negative negative negative negative
69 67 $QIHU totally missed this one, was about to jump in on that 60 break test but didn't, congrats shorts negative tweet Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Input: $QIHU totally missed this one, was about to jump in on that 60 break test but didn't, congrats shorts Answer: negative negative negative negative negative negative negative negative
70 68 Morrisons and Debenhams surprise City with Christmas bounce back positive news Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive. Input: Morrisons and Debenhams surprise City with Christmas bounce back Answer: positive positive positive negative negative positive positive positive
71 69 $AAPL wants lower. up waves getting smaller on the 2 min negative tweet Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Input: $AAPL wants lower. up waves getting smaller on the 2 min Answer: negative positive positive negative negative negative negative negative
72 70 $AAPL at pivot area on intraday chart- break here could send this to 50-day SMA, 457.80 http://stks.co/jPbN positive tweet Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Input: $AAPL at pivot area on intraday chart- break here could send this to 50-day SMA, 457.80 http://stks.co/jPbN Answer: positive negative negative negative negative negative positive negative
73 71 Short on $ATVI from 24.55. negative tweet Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Input: Short on $ATVI from 24.55. Answer: negative positive positive negative negative positive negative positive
74 72 METALS-Zinc surges 12 pct after Glencore cuts output, fuelling metals rally positive news Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive. Input: METALS-Zinc surges 12 pct after Glencore cuts output, fuelling metals rally Answer: positive negative negative negative negative negative positive negative
75 73 Academics claim Google Android two-factor authentication is breakable. #security #authentication #hacking $goog https://t.co/nJx4mnrGLo negative tweet Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Input: Academics claim Google Android two-factor authentication is breakable. #security #authentication #hacking $goog https://t.co/nJx4mnrGLo Answer: negative negative negative negative negative negative negative negative
76 74 G4S sees profits rise but UK contract problems remain positive news Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive. Input: G4S sees profits rise but UK contract problems remain Answer: positive negative negative negative negative negative positive negative
77 75 Tesla issues its first Model X recall https://t.co/t1kMqVwhQQ $TSLA negative tweet Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Input: Tesla issues its first Model X recall https://t.co/t1kMqVwhQQ $TSLA Answer: negative positive positive negative positive positive negative positive
78 76 Double bottom with handle buy point of 56.49 $WMT http://chart.ly/ml857v3 positive tweet Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Input: Double bottom with handle buy point of 56.49 $WMT http://chart.ly/ml857v3 Answer: positive negative negative negative negative negative positive negative
79 77 Facebook $FB received a Buy rating from Wells Fargo 5-star Analyst Peter Stabler (Wells Fargo) https://t.co/jnB4c9vdCu positive tweet Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Input: Facebook $FB received a Buy rating from Wells Fargo 5-star Analyst Peter Stabler (Wells Fargo) https://t.co/jnB4c9vdCu Answer: positive negative negative negative negative negative positive negative
80 78 $AMCN pushing highs positive tweet Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Input: $AMCN pushing highs Answer: positive positive positive negative positive positive positive positive
81 79 Tesco, Asda sales fall as march of the discounters continues-Kantar negative news Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive. Input: Tesco, Asda sales fall as march of the discounters continues-Kantar Answer: negative negative negative negative negative negative negative negative
82 80 longed $AMZN 300 @ 189.82 positive tweet Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Input: longed $AMZN 300 @ 189.82 Answer: positive positive positive negative negative negative positive negative
83 81 @Renatta @Fr0van @kjepeneter @RPTL Strong close 4 $PLNR coming positive tweet Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Input: @Renatta @Fr0van @kjepeneter @RPTL Strong close 4 $PLNR coming Answer: positive negative negative negative negative negative positive negative
84 82 Retail giant Kingfisher reports 'solid' start to the year positive news Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive. Input: Retail giant Kingfisher reports 'solid' start to the year Answer: positive negative negative negative negative negative positive negative
85 83 $PG Ackman making the big added efficiency argument. betting on operational imporvement in a huge conglomerate can go either way imo. positive tweet Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Input: $PG Ackman making the big added efficiency argument. betting on operational imporvement in a huge conglomerate can go either way imo. Answer: positive negative negative negative negative negative positive negative
86 84 Ackman, in email, says supports Valeant CEO Pearson positive news Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive. Input: Ackman, in email, says supports Valeant CEO Pearson Answer: positive negative negative negative negative negative positive negative
87 85 UPDATE 1-EU regulator backs approval for GSK injectable asthma drug positive news Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive. Input: UPDATE 1-EU regulator backs approval for GSK injectable asthma drug Answer: positive positive positive negative negative negative positive negative
88 86 Commented on It's Time To Embrace Dividend Growth https://t.co/wc2qfP79TN $ABBV $CSCO $WYN positive tweet Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Input: Commented on It's Time To Embrace Dividend Growth https://t.co/wc2qfP79TN $ABBV $CSCO $WYN Answer: positive negative negative negative negative negative positive negative
89 87 Entering long Lockheed Martin $LMT at Thursday's open. http://stks.co/eXtA positive tweet Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Input: Entering long Lockheed Martin $LMT at Thursday's open. http://stks.co/eXtA Answer: positive negative negative negative negative negative positive negative
90 88 AstraZeneca share price: Acerta deal pays off with orphan drug status positive news Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive. Input: AstraZeneca share price: Acerta deal pays off with orphan drug status Answer: positive positive positive positive positive positive positive positive
91 89 Teva: FDA Approves Generic Version of AstraZeneca Heartburn Drug positive news Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive. Input: Teva: FDA Approves Generic Version of AstraZeneca Heartburn Drug Answer: positive negative negative negative negative negative positive negative
92 90 $ACOM http://stks.co/1G6x Downside breakout looks to be coming soon. negative tweet Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Input: $ACOM http://stks.co/1G6x Downside breakout looks to be coming soon. Answer: negative negative negative negative negative negative negative negative
93 91 $HZNP havent seen vol like this since the runup. lets see one more dip to 2.0x negative tweet Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Input: $HZNP havent seen vol like this since the runup. lets see one more dip to 2.0x Answer: negative negative negative negative negative negative negative negative
94 92 $BAC $ADSK $NFLX long this morning positive tweet Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Input: $BAC $ADSK $NFLX long this morning Answer: positive positive positive negative negative positive positive positive
95 93 $GALE Breakout Coming Soon! positive tweet Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Input: $GALE Breakout Coming Soon! Answer: positive positive positive negative negative negative positive negative
96 94 Baird likes $TSLA - upgrades to outperform, lifts price target to $300. Research firm also sees no capital raise necessary in next few qtrs positive tweet Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Input: Baird likes $TSLA - upgrades to outperform, lifts price target to $300. Research firm also sees no capital raise necessary in next few qtrs Answer: positive negative negative negative negative negative positive negative
97 95 GlaxoSmithKline set to complete $20 billion Novartis asset swap next week positive news Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive. Input: GlaxoSmithKline set to complete $20 billion Novartis asset swap next week Answer: positive negative negative negative negative negative positive negative
98 96 $TSLA not dipping - testing the 200 day ma https://t.co/jEPLmZQKGW positive tweet Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Input: $TSLA not dipping - testing the 200 day ma https://t.co/jEPLmZQKGW Answer: positive negative negative negative negative negative positive negative
99 97 Hargreaves Lansdown share price falls as costs mount - although pensions ... negative news Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive. Input: Hargreaves Lansdown share price falls as costs mount - although pensions ... Answer: negative negative negative negative negative negative negative negative
100 98 HSBC shakes up board with two new business chiefs, three departures neutral news Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive. Input: HSBC shakes up board with two new business chiefs, three departures Answer: neutral negative negative negative negative negative neutral negative
101 99 $YELP wayyy overvalued right now IMO. Should be trading single digits. May take a short pos. into earnings. Near term target 18 ...... negative tweet Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Input: $YELP wayyy overvalued right now IMO. Should be trading single digits. May take a short pos. into earnings. Near term target 18 ...... Answer: negative negative negative negative negative negative negative negative
102 100 Long $TSLA short $MBLY https://t.co/jSpUSzo6na positive tweet Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Input: Long $TSLA short $MBLY https://t.co/jSpUSzo6na Answer: positive negative negative negative negative negative positive negative
103 101 AstraZeneca wins FDA approval for key new lung cancer pill positive news Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive. Input: AstraZeneca wins FDA approval for key new lung cancer pill Answer: positive positive positive negative negative positive positive positive
104 102 Sold out $TZA 45 $PUT (down $1), which were hedging my 45 $CALL. Letting the calls ride solo now. positive tweet Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Input: Sold out $TZA 45 $PUT (down $1), which were hedging my 45 $CALL. Letting the calls ride solo now. Answer: positive negative negative negative negative negative positive negative
105 103 $ATHN Seems like a good short setup. Stop above the 50 day. No position. negative tweet Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Input: $ATHN Seems like a good short setup. Stop above the 50 day. No position. Answer: negative negative negative negative negative negative negative negative
106 104 Morning Agenda: Shire's Deal for NPS positive news Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive. Input: Morning Agenda: Shire's Deal for NPS Answer: positive positive positive negative positive positive positive positive
107 105 $GOOGL gets an upgrade price target $970 positive tweet Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Input: $GOOGL gets an upgrade price target $970 Answer: positive positive positive negative negative positive positive positive
108 106 $DARA breaking out positive tweet Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Input: $DARA breaking out Answer: positive positive positive positive positive positive positive positive
109 107 @CGrantWSJ I think this $TSLA bubble might go on for some time. So long as ppl love the cars, they might keep getting funding. positive tweet Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Input: @CGrantWSJ I think this $TSLA bubble might go on for some time. So long as ppl love the cars, they might keep getting funding. Answer: positive negative negative negative negative negative positive negative
110 108 $SPY bull move ended waiting for next setup negative tweet Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Input: $SPY bull move ended waiting for next setup Answer: negative positive positive negative negative negative negative negative
111 109 Supermarket Stocks Rally as Tesco Plans to Axe Non-core UK Assets $TSCO https://t.co/BmvhcrwREA positive tweet Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Input: Supermarket Stocks Rally as Tesco Plans to Axe Non-core UK Assets $TSCO https://t.co/BmvhcrwREA Answer: positive negative negative negative negative negative positive negative
112 110 Novartis buys remaining rights to GSK treatment in deal up to $1 billion positive news Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive. Input: Novartis buys remaining rights to GSK treatment in deal up to $1 billion Answer: positive negative negative negative negative negative positive negative
113 111 $FB popping up to HOD positive tweet Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Input: $FB popping up to HOD Answer: positive positive positive negative positive positive positive positive
114 112 $HYG Potential continuation Uptrend on a 60'-15'-4' charts http://stks.co/t1Qp6 positive tweet Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Input: $HYG Potential continuation Uptrend on a 60'-15'-4' charts http://stks.co/t1Qp6 Answer: positive positive positive positive negative negative positive positive
115 113 I am not optimistic about $amzn both fundementals and charts look like poopoo this quarter. negative tweet Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Input: I am not optimistic about $amzn both fundementals and charts look like poopoo this quarter. Answer: negative negative negative negative negative negative negative negative
116 114 Borealis Infrastructure putting together new Severn Trent bid positive news Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive. Input: Borealis Infrastructure putting together new Severn Trent bid Answer: positive negative negative negative negative negative positive negative
117 115 Thank you $GOOG (Google Alphabet) and $FB (Facebook) stocks! What a nice reversal. positive tweet Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Input: Thank you $GOOG (Google Alphabet) and $FB (Facebook) stocks! What a nice reversal. Answer: positive positive positive positive positive positive positive positive
118 116 Costco: A Premier Retail Dividend Play https://t.co/J3UhTs022M $COST positive tweet Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Input: Costco: A Premier Retail Dividend Play https://t.co/J3UhTs022M $COST Answer: positive positive positive positive negative negative positive positive
119 117 DJI overbought: $AAPL, $AXP, $BA, $CVX, $IBM, $INTC, $VZ https://t.co/wMy1PnomJF negative tweet Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Input: DJI overbought: $AAPL, $AXP, $BA, $CVX, $IBM, $INTC, $VZ https://t.co/wMy1PnomJF Answer: negative negative negative negative negative negative negative negative
120 118 $YOKU high volume blast off Friday, goes higher http://stks.co/qSaL positive tweet Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Input: $YOKU high volume blast off Friday, goes higher http://stks.co/qSaL Answer: positive positive positive positive positive positive positive positive
121 119 Tesla to recall 2,700 Model X SUVs over seat issue https://t.co/OdPraN59Xq $TSLA https://t.co/xvn4blIwpy https://t.co/ThfvWTnRPs negative tweet Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Input: Tesla to recall 2,700 Model X SUVs over seat issue https://t.co/OdPraN59Xq $TSLA https://t.co/xvn4blIwpy https://t.co/ThfvWTnRPs Answer: negative negative negative negative negative negative negative negative
122 120 I'm liking the price action in $SWKS, currently @21.80 ; my target: 24.00+ before year end. positive tweet Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Input: I'm liking the price action in $SWKS, currently @21.80 ; my target: 24.00+ before year end. Answer: positive positive positive positive positive positive positive positive
123 121 So as of today's close (8/15/14), I'm long $TSLA $AMTD $TWTR $FB $AAPL $CELG - all on a longer-term, technical swing long basis. positive tweet Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Input: So as of today's close (8/15/14), I'm long $TSLA $AMTD $TWTR $FB $AAPL $CELG - all on a longer-term, technical swing long basis. Answer: positive negative negative negative negative positive positive negative
124 122 Aberdeen Asset Management Gains Foothold In China positive news Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive. Input: Aberdeen Asset Management Gains Foothold In China Answer: positive positive positive positive positive positive positive positive
125 123 $KIOR My god. Market getting crushed today. Gotta hold if anything g should recover some tomorrow I imagine. negative tweet Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Input: $KIOR My god. Market getting crushed today. Gotta hold if anything g should recover some tomorrow I imagine. Answer: negative negative positive negative negative negative negative negative
126 124 $UUP at major resistance right now. Can go much higher if it can break above. May take several attempts - few days to a week positive tweet Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Input: $UUP at major resistance right now. Can go much higher if it can break above. May take several attempts - few days to a week Answer: positive positive positive positive negative positive positive positive
127 125 Royal Mail share price rallies amid positive broker comments positive news Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive. Input: Royal Mail share price rallies amid positive broker comments Answer: positive positive positive positive positive positive positive positive
128 126 $SLV POS, been saying it for 2 years. Going lower. Forget about it or go short. negative tweet Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Input: $SLV POS, been saying it for 2 years. Going lower. Forget about it or go short. Answer: negative positive positive positive positive positive negative positive
129 127 Severn Trent share price jumps as Canadian investor renews pursuit of utility positive news Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive. Input: Severn Trent share price jumps as Canadian investor renews pursuit of utility Answer: positive positive positive positive negative positive positive positive
130 128 $FB still a dog going much lower this week negative tweet Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Input: $FB still a dog going much lower this week Answer: negative positive positive negative negative negative negative negative
131 129 $TXRH reports Q1 EPS of $0.37 versus the estimated $0.35, beating by $0.02. EPS were Up 19% from the same quarter last year. positive tweet Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Input: $TXRH reports Q1 EPS of $0.37 versus the estimated $0.35, beating by $0.02. EPS were Up 19% from the same quarter last year. Answer: positive positive negative negative negative negative positive negative
132 130 $SPY $MITK fast 56pc dive http://stks.co/3ffN $$ negative tweet Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Input: $SPY $MITK fast 56pc dive http://stks.co/3ffN $$ Answer: negative positive positive negative negative negative negative negative
133 131 Long Position on $IP,....Scaling UP http://stks.co/sIln positive tweet Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Input: Long Position on $IP,....Scaling UP http://stks.co/sIln Answer: positive negative positive negative negative negative positive negative
134 132 RT @stockdemons think shorting here into close might be play, $SPY - high beta reversing..looks worth a shot negative tweet Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Input: RT @stockdemons think shorting here into close might be play, $SPY - high beta reversing..looks worth a shot Answer: negative negative positive negative negative negative negative negative
135 133 $GPS Gap September Comparable Store Sales -4% negative tweet Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Input: $GPS Gap September Comparable Store Sales -4% Answer: negative positive positive negative negative positive negative positive
136 134 $SIGA Bid for Reargument Denied by Judge negative tweet Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Input: $SIGA Bid for Reargument Denied by Judge Answer: negative positive positive negative negative negative negative negative
137 135 Kinder Morgan and BP Form Joint Venture Limited Liability Company to Purchase ... positive news Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive. Input: Kinder Morgan and BP Form Joint Venture Limited Liability Company to Purchase ... Answer: positive positive negative negative negative negative positive negative
138 136 $TSLA steaming up again, this stock is relentless at the moment positive tweet Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Input: $TSLA steaming up again, this stock is relentless at the moment Answer: positive positive positive negative positive positive positive positive
139 137 $RUSS Don't catch falling knives, but I think an entry is coming soon on this positive tweet Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Input: $RUSS Don't catch falling knives, but I think an entry is coming soon on this Answer: positive negative negative negative negative negative positive negative
140 138 $UBNT still having some trouble at the resistance line. Should resolve soon.@cheri1 @strattonite http://stks.co/c0sU4 neutral tweet Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Input: $UBNT still having some trouble at the resistance line. Should resolve soon.@cheri1 @strattonite http://stks.co/c0sU4 Answer: neutral negative negative negative negative negative neutral negative
141 139 Adobe Receives New Rating from Top Analyst $ADBE https://t.co/LJNXPEvHZN positive tweet Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Input: Adobe Receives New Rating from Top Analyst $ADBE https://t.co/LJNXPEvHZN Answer: positive positive positive negative negative negative positive negative
142 140 AstraZeneca Explores Potential Deal With Acerta for Cancer Drug positive news Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive. Input: AstraZeneca Explores Potential Deal With Acerta for Cancer Drug Answer: positive positive positive negative positive positive positive positive
143 141 $QCOR Just added 3,000 shares @28. positive tweet Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Input: $QCOR Just added 3,000 shares @28. Answer: positive positive positive negative negative negative positive negative
144 142 @Megaas2000 $AAPL McDonalds had a big GROWING success for years with the same BigMac and Apple update and improbe Iphone and Ipad positive tweet Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Input: @Megaas2000 $AAPL McDonalds had a big GROWING success for years with the same BigMac and Apple update and improbe Iphone and Ipad Answer: positive negative negative negative negative negative positive negative
145 143 Current holdings via options - Long: $AAPL $V $GS $AET & Short: $VXX positive tweet Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Input: Current holdings via options - Long: $AAPL $V $GS $AET & Short: $VXX Answer: positive negative negative negative negative negative positive negative
146 144 Credit Suisse poaches Prudential's Thiam for Asian push positive news Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive. Input: Credit Suisse poaches Prudential's Thiam for Asian push Answer: positive positive positive negative negative positive positive positive
147 145 $SDS +1.46% 15.32, picking up some speed. May 16 calls now +35% .19: http://stks.co/3eiK, Next week $16 calls .11c: http://stks.co/3eiL positive tweet Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Input: $SDS +1.46% 15.32, picking up some speed. May 16 calls now +35% .19: http://stks.co/3eiK, Next week $16 calls .11c: http://stks.co/3eiL Answer: positive negative negative negative negative negative positive negative
148 146 $AEGN MACD and ADX are crossing over the signal lines! Long Setup http://stks.co/qzzx positive tweet Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Input: $AEGN MACD and ADX are crossing over the signal lines! Long Setup http://stks.co/qzzx Answer: positive positive positive positive positive positive positive positive
149 147 ARM Royalties Accelerate as Smartphone Market Regains Strength positive news Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive. Input: ARM Royalties Accelerate as Smartphone Market Regains Strength Answer: positive positive positive positive positive positive positive positive
150 148 $AAPL nibbling on a small long via 525.. buying off 13min charts.. positive tweet Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Input: $AAPL nibbling on a small long via 525.. buying off 13min charts.. Answer: positive positive positive positive positive positive positive positive
151 149 NaturalGas Settles At 3-year Low $DBO $BNO http://stks.co/d27qX negative tweet Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Input: NaturalGas Settles At 3-year Low $DBO $BNO http://stks.co/d27qX Answer: negative positive positive positive positive positive negative positive
152 150 Amazon declares 'best ever' Black Friday and Cyber Monday for Kindle family http://stks.co/cEtw via Engadget $AMZN positive tweet Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Input: Amazon declares 'best ever' Black Friday and Cyber Monday for Kindle family http://stks.co/cEtw via Engadget $AMZN Answer: positive positive positive positive positive positive positive positive
153 151 Kingfisher takeover of Mr Bricolage could hit a brick wall negative news Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive. Input: Kingfisher takeover of Mr Bricolage could hit a brick wall Answer: negative negative negative negative negative negative negative negative
154 152 $NUGT Gold above 1400...wow positive tweet Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Input: $NUGT Gold above 1400...wow Answer: positive positive positive positive positive positive positive positive
155 153 GlaxoSmithKline starts hunt for successor to CEO Witty neutral news Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive. Input: GlaxoSmithKline starts hunt for successor to CEO Witty Answer: neutral negative negative negative negative negative neutral negative
156 154 $CERN - consolidating above 50 & 200 MA - nice long entry here w stop below 10 MA - targeting $70 area positive tweet Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Input: $CERN - consolidating above 50 & 200 MA - nice long entry here w stop below 10 MA - targeting $70 area Answer: positive negative negative negative negative negative positive negative
157 155 $UTSI http://stks.co/15uR Long setup. Reported very good earnings. positive tweet Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Input: $UTSI http://stks.co/15uR Long setup. Reported very good earnings. Answer: positive positive positive negative negative negative positive negative
158 156 New recommendation from Carl Kirst of BMO Capital Markets for $WMB is BUY.Price target is $62:http://stks.co/t0S0r positive tweet Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Input: New recommendation from Carl Kirst of BMO Capital Markets for $WMB is BUY.Price target is $62:http://stks.co/t0S0r Answer: positive negative negative negative negative negative positive negative
159 157 GSK joins China trade push as UK trumpets healthcare deals positive news Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive. Input: GSK joins China trade push as UK trumpets healthcare deals Answer: positive negative negative negative negative negative positive negative
160 158 Sainsbury's, Asda, Tesco and Morrisons will all cut petrol prices as oil falls ... negative news Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive. Input: Sainsbury's, Asda, Tesco and Morrisons will all cut petrol prices as oil falls ... Answer: negative negative negative negative negative negative negative negative
161 159 $LSCC Accumulation chart continues to make new highs showing accumulation continuing to take place http://stks.co/aDpO positive tweet Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Input: $LSCC Accumulation chart continues to make new highs showing accumulation continuing to take place http://stks.co/aDpO Answer: positive negative negative negative negative negative positive negative
162 160 RT @StockTwits RT @fallondpicks Breadth Consolidates: After weeks of steady gains,advances in mkt breadth slowe... http://stks.co/2TrG $QQQ negative tweet Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Input: RT @StockTwits RT @fallondpicks Breadth Consolidates: After weeks of steady gains,advances in mkt breadth slowe... http://stks.co/2TrG $QQQ Answer: negative negative negative negative negative negative negative negative
163 161 Google, Inc. completes acquisition of ICOA, Inc. http://stks.co/nFEI $ICOA $GOOG positive tweet Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Input: Google, Inc. completes acquisition of ICOA, Inc. http://stks.co/nFEI $ICOA $GOOG Answer: positive positive positive negative negative negative positive negative
164 162 Irish Said Chasing Standard Chartered, RBS as Brexit Vote Nears positive news Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive. Input: Irish Said Chasing Standard Chartered, RBS as Brexit Vote Nears Answer: positive negative negative negative negative negative positive negative
165 163 Glencore chief blames rivals' overproduction for share price fall negative news Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive. Input: Glencore chief blames rivals' overproduction for share price fall Answer: negative negative negative negative negative negative negative negative
166 164 FTSE 100 falls as China devaluation hits Burberry, mining stocks negative news Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive. Input: FTSE 100 falls as China devaluation hits Burberry, mining stocks Answer: negative positive negative negative negative positive negative negative
167 165 Standard Chartered Shifts Emerging-Markets Strategy After Losses negative news Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive. Input: Standard Chartered Shifts Emerging-Markets Strategy After Losses Answer: negative positive positive negative negative negative negative negative
168 166 Tesco criticised for 'disgraceful' advert showing domestic worker being slapped negative news Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive. Input: Tesco criticised for 'disgraceful' advert showing domestic worker being slapped Answer: negative negative negative negative negative negative negative negative
169 167 $NUAN held up well after the big gains! Maybe we're finally on the move on this!!its still very undervalued and has major upside positive tweet Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Input: $NUAN held up well after the big gains! Maybe we're finally on the move on this!!its still very undervalued and has major upside Answer: positive positive positive positive positive negative positive positive
170 168 $PCLN Trying to break daily trend line! Big move could happen https://t.co/gY0aDb2jsQ https://t.co/KPBBCgQ2xy positive tweet Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Input: $PCLN Trying to break daily trend line! Big move could happen https://t.co/gY0aDb2jsQ https://t.co/KPBBCgQ2xy Answer: positive negative negative negative negative negative positive negative
171 169 $GS sells flat..I am out.. negative tweet Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Input: $GS sells flat..I am out.. Answer: negative positive positive negative negative negative negative negative
172 170 $VRTX early technical BUY signal... for confirmation > 86 it needs some fundam. incentive https://t.co/QuYSrqFo2x positive tweet Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Input: $VRTX early technical BUY signal... for confirmation > 86 it needs some fundam. incentive https://t.co/QuYSrqFo2x Answer: positive negative negative negative negative negative positive negative
173 171 ConAgra Names Former Hillshire Farms CEO Connolly to Top Post positive news Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive. Input: ConAgra Names Former Hillshire Farms CEO Connolly to Top Post Answer: positive positive negative negative negative negative positive negative
174 172 $EXPE working on the second leg of its reversal run as it breaks another down trend and continues higher. https://t.co/76DSJysyR0 positive tweet Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Input: $EXPE working on the second leg of its reversal run as it breaks another down trend and continues higher. https://t.co/76DSJysyR0 Answer: positive negative negative negative negative negative positive negative
175 173 $CTRP breaking out https://t.co/Z2je3rTKch positive tweet Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Input: $CTRP breaking out https://t.co/Z2je3rTKch Answer: positive positive positive positive positive positive positive positive
176 174 BHP Billiton slashes dividend, posts $5.67 billion net loss negative news Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive. Input: BHP Billiton slashes dividend, posts $5.67 billion net loss Answer: negative negative negative negative negative negative negative negative
177 175 $AMZN new HOD with conviction keeping $570 on watch for Resistance. positive tweet Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Input: $AMZN new HOD with conviction keeping $570 on watch for Resistance. Answer: positive positive positive negative negative negative positive negative
178 176 Hammerson, JV Partner secure ownership of Ireland's Dundrum - Quick Facts positive news Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive. Input: Hammerson, JV Partner secure ownership of Ireland's Dundrum - Quick Facts Answer: positive negative positive negative negative negative positive negative
179 177 Why Alphabet Inc was just upgraded to buy https://t.co/dEVnLKhqtZ $GOOGL positive tweet Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Input: Why Alphabet Inc was just upgraded to buy https://t.co/dEVnLKhqtZ $GOOGL Answer: positive positive positive negative negative negative positive negative
180 178 $BAC $ADSK $NFLX long this morning positive tweet Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Input: $BAC $ADSK $NFLX long this morning Answer: positive positive positive negative negative positive positive positive
181 179 Legal & General share price: Finance chief to step down negative news Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive. Input: Legal & General share price: Finance chief to step down Answer: negative negative negative negative negative negative negative negative
182 180 Surprising to see $JWN and $SKS sales numbers still holding up so well. I guess the high end might not be a concern after all. positive tweet Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Input: Surprising to see $JWN and $SKS sales numbers still holding up so well. I guess the high end might not be a concern after all. Answer: positive negative negative negative negative negative positive negative
183 181 $AAPL Good time to buy. Will the run come before earnings or after? positive tweet Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Input: $AAPL Good time to buy. Will the run come before earnings or after? Answer: positive negative positive negative negative negative positive negative
184 182 $TRX http://stks.co/1KkK Long setup. MACD cross. positive tweet Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Input: $TRX http://stks.co/1KkK Long setup. MACD cross. Answer: positive negative positive negative negative negative positive negative
185 183 $CHKP ABC Bullish Pattern, Targets https://t.co/uVMmRSR5Zy positive tweet Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Input: $CHKP ABC Bullish Pattern, Targets https://t.co/uVMmRSR5Zy Answer: positive positive negative negative negative negative positive negative
186 184 Goldman Sachs, Barclays, HSBC downplay Brexit threat neutral news Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive. Input: Goldman Sachs, Barclays, HSBC downplay Brexit threat Answer: neutral negative negative negative negative negative neutral negative
187 185 Isolationism? Another Sell Rating, Sell Ratings On SPY, QQQ, IWM And Several Companies https://t.co/j35FNnx744 $AAPL #APPLE $AXP $BAC negative tweet Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Input: Isolationism? Another Sell Rating, Sell Ratings On SPY, QQQ, IWM And Several Companies https://t.co/j35FNnx744 $AAPL #APPLE $AXP $BAC Answer: negative negative negative negative negative negative negative negative
188 186 BBCN Bancorp to buy Wilshire Bancorp in $1 bln deal positive news Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive. Input: BBCN Bancorp to buy Wilshire Bancorp in $1 bln deal Answer: positive negative negative negative negative negative positive negative
189 187 How Kraft-Heinz Merger Came Together in Speedy 10 Weeks positive news Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive. Input: How Kraft-Heinz Merger Came Together in Speedy 10 Weeks Answer: positive positive positive negative positive positive positive positive
190 188 $ISRG PT raised to $700 from $640 at Leerink - keeps Outperform rated positive tweet Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Input: $ISRG PT raised to $700 from $640 at Leerink - keeps Outperform rated Answer: positive negative negative negative negative negative positive negative
191 189 HSBC Hit by Fresh Details of Tax Evasion Claims negative news Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive. Input: HSBC Hit by Fresh Details of Tax Evasion Claims Answer: negative negative negative negative negative negative negative negative
192 190 $KCG bot at 2.24 positive tweet Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Input: $KCG bot at 2.24 Answer: positive positive positive negative negative negative positive negative
193 191 $ZNGA http://stks.co/3rdu Looking for a test at 9.25 resistance point. cc @ cfrazierjr @FletchTrade #traders positive tweet Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Input: $ZNGA http://stks.co/3rdu Looking for a test at 9.25 resistance point. cc @ cfrazierjr @FletchTrade #traders Answer: positive negative negative negative negative negative positive negative
194 192 RBS Pays $1.7 Billion to Scrap U.K. Treasury's Dividend Rights neutral news Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive. Input: RBS Pays $1.7 Billion to Scrap U.K. Treasury's Dividend Rights Answer: neutral negative negative negative negative negative neutral negative
195 193 London open: Taylor Wimpey and Ashtead drive markets higher, Barclays falls positive news Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive. Input: London open: Taylor Wimpey and Ashtead drive markets higher, Barclays falls Answer: positive negative negative negative negative negative positive negative
196 194 End Of Day Scan: Bullish MA Crossovers $BBVA $PDS $NTLS $NGL $SBRCY $FGL $MTNOY $TTT www.dailystockplays.com positive tweet Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Input: End Of Day Scan: Bullish MA Crossovers $BBVA $PDS $NTLS $NGL $SBRCY $FGL $MTNOY $TTT www.dailystockplays.com Answer: positive negative negative negative negative positive positive negative
197 195 @asdfLLC. Nice pop today. Told ya we would be green haha. Funny you bring that up. I'm actually working on a story about $NOK at the moment positive tweet Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Input: @asdfLLC. Nice pop today. Told ya we would be green haha. Funny you bring that up. I'm actually working on a story about $NOK at the moment Answer: positive positive positive negative negative negative positive negative
198 196 $GRPN might be selling off ahead of $P earnings... negative tweet Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Input: $GRPN might be selling off ahead of $P earnings... Answer: negative positive positive positive negative positive negative positive
199 197 UPDATE 5-Barclays Chairman McFarlane axes CEO to speed up strategic change negative news Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive. Input: UPDATE 5-Barclays Chairman McFarlane axes CEO to speed up strategic change Answer: negative negative negative negative negative negative negative negative
200 198 Shares in BAE Systems hit 10-month high on rating upgrade positive news Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive. Input: Shares in BAE Systems hit 10-month high on rating upgrade Answer: positive positive positive positive positive positive positive positive
201 199 FDA approves NPS drug, in move validating Shire takeover deal positive news Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive. Input: FDA approves NPS drug, in move validating Shire takeover deal Answer: positive positive positive negative negative positive positive positive
202 200 $renn topping tail 5 min. chart at 7.31 short from here. negative tweet Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Input: $renn topping tail 5 min. chart at 7.31 short from here. Answer: negative positive positive negative negative negative negative negative
203 201 Shell share price: Standard Life announce position against BG acquisition negative news Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive. Input: Shell share price: Standard Life announce position against BG acquisition Answer: negative positive positive negative negative negative negative negative
204 202 CompaniesHome Retail trims gains but is considered 'in play' positive news Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive. Input: CompaniesHome Retail trims gains but is considered 'in play' Answer: positive negative negative negative negative negative positive negative
205 203 stole my tweet. really wouldn't be surprised if we took out 423 and pinned around it RT @totalguru We could possibly even see425 today $AAPL positive tweet Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Input: stole my tweet. really wouldn't be surprised if we took out 423 and pinned around it RT @totalguru We could possibly even see425 today $AAPL Answer: positive negative negative negative negative negative positive negative
206 204 $ELN longs...congrats...another HOD positive tweet Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Input: $ELN longs...congrats...another HOD Answer: positive positive positive positive positive positive positive positive
207 205 Intuitive Surgical $ISRG is in a great financial position, take a look https://t.co/VahhJAcBFG https://t.co/24hQTQX4ou positive tweet Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Input: Intuitive Surgical $ISRG is in a great financial position, take a look https://t.co/VahhJAcBFG https://t.co/24hQTQX4ou Answer: positive negative negative negative negative negative positive negative
208 206 $AAPL AAPL: Gundlach Slams iPad mini, Sees Downside to $425. http://stks.co/bDqV negative tweet Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Input: $AAPL AAPL: Gundlach Slams iPad mini, Sees Downside to $425. http://stks.co/bDqV Answer: negative negative negative negative negative negative negative negative
209 207 Tesco share price tumbles after negative broker note negative news Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive. Input: Tesco share price tumbles after negative broker note Answer: negative negative negative negative negative positive negative negative
210 208 $ENB.CA {Head&Shoulders} bullish reversal setup and breakout. Oil and Gas Pipleline stock. $USO positive tweet Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Input: $ENB.CA {Head&Shoulders} bullish reversal setup and breakout. Oil and Gas Pipleline stock. $USO Answer: positive positive positive positive positive positive positive positive
211 209 Philip Morris, BAT Sue Over Law Taking Branding Off Packs negative news Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive. Input: Philip Morris, BAT Sue Over Law Taking Branding Off Packs Answer: negative positive negative negative negative negative negative negative
212 210 $SAP Q1 disappoints as #software licenses down. Real problem? #Cloud growth trails $MSFT $ORCL $GOOG $CRM $ADBE https://t.co/jNDphllzq5 negative tweet Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Input: $SAP Q1 disappoints as #software licenses down. Real problem? #Cloud growth trails $MSFT $ORCL $GOOG $CRM $ADBE https://t.co/jNDphllzq5 Answer: negative negative negative negative negative negative negative negative
213 211 Juniper tumbles on Q1 warning; Cisco also lower https://t.co/N8X8BpLJ1E $JNPR $CSCO negative tweet Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Input: Juniper tumbles on Q1 warning; Cisco also lower https://t.co/N8X8BpLJ1E $JNPR $CSCO Answer: negative positive negative negative negative negative negative negative
214 212 MT @TheAcsMan Amazing seeing everyone suddenly touting $MSFT. Long been favorite covered call & double dip dividend play. positive tweet Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Input: MT @TheAcsMan Amazing seeing everyone suddenly touting $MSFT. Long been favorite covered call & double dip dividend play. Answer: positive positive positive positive negative negative positive positive
215 213 Out of shorts $ALTR at 38.85 with loss positive tweet Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Input: Out of shorts $ALTR at 38.85 with loss Answer: positive positive positive positive positive positive positive positive
216 214 $AAPL price momentum weakening going into the close. negative tweet Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Input: $AAPL price momentum weakening going into the close. Answer: negative positive positive positive negative positive negative positive
217 215 $FB watching for bounce tomorrow positive tweet Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Input: $FB watching for bounce tomorrow Answer: positive positive positive positive positive positive positive positive
218 216 Valeant Said to Name New CEO With Pearson Still Hospitalized neutral news Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive. Input: Valeant Said to Name New CEO With Pearson Still Hospitalized Answer: neutral positive positive negative negative negative neutral negative
219 217 $aapl. Test the high today and probably go beyond after hours... positive tweet Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Input: $aapl. Test the high today and probably go beyond after hours... Answer: positive negative negative negative negative negative positive negative
220 218 Builder Persimmon hails 6% rise in house sales positive news Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive. Input: Builder Persimmon hails 6% rise in house sales Answer: positive negative positive negative negative negative positive negative
221 219 $FB trend, hits mid 110's and drops negative tweet Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Input: $FB trend, hits mid 110's and drops Answer: negative positive positive negative negative negative negative negative
222 220 Crown Castle buys Tower Development Corp for $461 million positive news Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive. Input: Crown Castle buys Tower Development Corp for $461 million Answer: positive negative positive negative negative negative positive negative
223 221 @Joerazorback This time I think $AAPL will miss again. Generally speaking market is near top when everyone thinks that market goes only up negative tweet Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Input: @Joerazorback This time I think $AAPL will miss again. Generally speaking market is near top when everyone thinks that market goes only up Answer: negative negative negative negative negative negative negative negative
224 222 Whitbread share price climbs on Q4 sales growth positive news Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive. Input: Whitbread share price climbs on Q4 sales growth Answer: positive positive positive negative positive positive positive positive
225 223 @saltwaternurse $INO can test 10 again in next few days. time to take some profits here. or hedge with puts. negative tweet Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Input: @saltwaternurse $INO can test 10 again in next few days. time to take some profits here. or hedge with puts. Answer: negative negative negative negative negative negative negative negative
226 224 Barclays Bonds Rise as Lender Cuts Dividends to Shore Up Capital positive news Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive. Input: Barclays Bonds Rise as Lender Cuts Dividends to Shore Up Capital Answer: positive positive positive positive negative positive positive positive
227 225 5 Best Analyst Rated Stocks in Last 72hrs: $ORCL $AAPL $CBS $INO $CPXX View all ratings here: https://t.co/IRID6zd5gc positive tweet Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Input: 5 Best Analyst Rated Stocks in Last 72hrs: $ORCL $AAPL $CBS $INO $CPXX View all ratings here: https://t.co/IRID6zd5gc Answer: positive negative negative negative negative negative positive negative
228 226 GKN to buy Fokker Technologies for 706 mln euros positive news Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive. Input: GKN to buy Fokker Technologies for 706 mln euros Answer: positive positive negative negative negative negative positive negative
229 227 UPDATE 3-Ex-Barclays director accused by US of illegal tips to plumber negative news Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive. Input: UPDATE 3-Ex-Barclays director accused by US of illegal tips to plumber Answer: negative negative negative negative negative negative negative negative
230 228 SAB's Chairman Digs In With Board Divided on InBev Offer neutral news Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive. Input: SAB's Chairman Digs In With Board Divided on InBev Offer Answer: neutral negative negative negative negative negative neutral negative
231 229 @scottrade Why is $tsla not available for shorting at this time? Same for $w? negative tweet Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Input: @scottrade Why is $tsla not available for shorting at this time? Same for $w? Answer: negative negative negative negative negative negative negative negative
232 230 @BULLYA @pollux654321 My 50 $KORS 80 Calls are going to b a Blessing for my Daughters tuition! positive tweet Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Input: @BULLYA @pollux654321 My 50 $KORS 80 Calls are going to b a Blessing for my Daughters tuition! Answer: positive positive positive negative negative negative positive negative
233 231 Still short $LNG from $11.70 area...next stop could be down through $9.00. Someone slammed it hard with 230,000 shs this am! More to follow negative tweet Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Input: Still short $LNG from $11.70 area...next stop could be down through $9.00. Someone slammed it hard with 230,000 shs this am! More to follow Answer: negative negative negative negative negative negative negative negative
234 232 UPDATE 1-Lloyds to cut 945 jobs as part of 3-year restructuring plan negative news Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive. Input: UPDATE 1-Lloyds to cut 945 jobs as part of 3-year restructuring plan Answer: negative negative negative negative negative negative negative negative
235 233 $FTI Breakout today after reporting earnings last night positive tweet Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Input: $FTI Breakout today after reporting earnings last night Answer: positive positive positive negative negative positive positive positive
236 234 $TRIP maintains Neutral rating at JP Morgan- PT cut $61 from $66 neutral tweet Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Input: $TRIP maintains Neutral rating at JP Morgan- PT cut $61 from $66 Answer: neutral negative positive negative negative negative neutral negative
237 235 GSK and Novartis complete deals to reshape both drugmakers positive news Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive. Input: GSK and Novartis complete deals to reshape both drugmakers Answer: positive positive negative negative negative negative positive negative
238 236 potential defect with third-row seat belts. Tesla Motors recalls 2,700 Model X SUVs $TSLA https://t.co/YVYDncdNdi negative tweet Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Input: potential defect with third-row seat belts. Tesla Motors recalls 2,700 Model X SUVs $TSLA https://t.co/YVYDncdNdi Answer: negative negative negative negative negative negative negative negative
239 237 $PRGN A bottom right here? neutral tweet Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Input: $PRGN A bottom right here? Answer: neutral negative positive negative negative positive neutral negative
240 238 Primark racks up a happy Christmas after strong sales positive news Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive. Input: Primark racks up a happy Christmas after strong sales Answer: positive positive positive negative positive positive positive positive
241 239 AB InBev attacks SABMiller bid rebuffal negative news Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive. Input: AB InBev attacks SABMiller bid rebuffal Answer: negative negative negative negative negative negative negative negative
242 240 @technik I still have a smaller $GILD pos. Being very tender with cash due to volatility. So reluctant to keep many big positions. positive tweet Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Input: @technik I still have a smaller $GILD pos. Being very tender with cash due to volatility. So reluctant to keep many big positions. Answer: positive positive negative negative negative negative positive negative
243 241 EasyJet attracts more passengers in June but still lags Ryanair positive news Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive. Input: EasyJet attracts more passengers in June but still lags Ryanair Answer: positive positive negative negative negative positive positive negative
244 242 Oil majors like Royal Dutch Shell, Chevron, BP fail to find reserves to counter ... negative news Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive. Input: Oil majors like Royal Dutch Shell, Chevron, BP fail to find reserves to counter ... Answer: negative negative negative negative negative negative negative negative
245 243 CompaniesLSE adds ex-SEC head Schapiro to board neutral news Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive. Input: CompaniesLSE adds ex-SEC head Schapiro to board Answer: neutral negative negative negative negative negative neutral negative
246 244 UK housing market steadies after Brexit dip, Persimmon says positive news Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive. Input: UK housing market steadies after Brexit dip, Persimmon says Answer: positive negative positive negative negative positive positive negative
247 245 Royal Mail share price edges lower as group raises stamp price negative news Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive. Input: Royal Mail share price edges lower as group raises stamp price Answer: negative positive negative negative negative positive negative negative
248 246 Are Aviva plc, Direct Line Insurance Group PLC And Admiral Group plc Set To Soar? positive news Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive. Input: Are Aviva plc, Direct Line Insurance Group PLC And Admiral Group plc Set To Soar? Answer: positive negative negative negative negative negative positive negative
249 247 $ATVI ooks pretty bullish for now. from a short-term perspective, it's got a good chance of maybe sliding back to 33.70 #stocks #investing positive tweet Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Input: $ATVI ooks pretty bullish for now. from a short-term perspective, it's got a good chance of maybe sliding back to 33.70 #stocks #investing Answer: positive negative negative negative negative negative positive negative
250 248 MarketsBP promotes upstream boss to deputy CEO neutral news Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive. Input: MarketsBP promotes upstream boss to deputy CEO Answer: neutral negative negative negative negative negative neutral negative
251 249 $RDC Rowan Expands Share Repurchase Program to $150 million positive tweet Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Input: $RDC Rowan Expands Share Repurchase Program to $150 million Answer: positive positive positive negative negative negative positive negative
252 250 $STX long play, another consistent profit zone.. check it out https://t.co/DQfuzOzYlh https://t.co/ggne4ayzqn positive tweet Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Input: $STX long play, another consistent profit zone.. check it out https://t.co/DQfuzOzYlh https://t.co/ggne4ayzqn Answer: positive negative negative negative negative negative positive negative
253 251 $AAPL at resistance right here...sold my shares...will buy back if it dips or if it goes in the 128 gap zone negative tweet Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Input: $AAPL at resistance right here...sold my shares...will buy back if it dips or if it goes in the 128 gap zone Answer: negative negative negative negative negative negative negative negative
254 252 Locked in some $FB puts for nice gain negative tweet Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Input: Locked in some $FB puts for nice gain Answer: negative positive positive positive positive positive negative positive
255 253 Industry NewsWolseley confident in reslilience amid mixed markets positive news Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive. Input: Industry NewsWolseley confident in reslilience amid mixed markets Answer: positive positive positive negative negative positive positive positive
256 254 AstraZeneca sells Caprelsa rights to Sanofi unit positive news Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive. Input: AstraZeneca sells Caprelsa rights to Sanofi unit Answer: positive positive positive negative positive positive positive positive
257 255 $GNRC finding support at its 10-day line so far. positive tweet Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Input: $GNRC finding support at its 10-day line so far. Answer: positive positive positive negative positive positive positive positive
258 256 $CNP Sell Short Position on CNP,...Closed for Profit $ 59,367.00 (7.75%) http://stks.co/ghjc positive tweet Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Input: $CNP Sell Short Position on CNP,...Closed for Profit $ 59,367.00 (7.75%) http://stks.co/ghjc Answer: positive negative negative negative negative negative positive negative
259 257 Lots of metal stocks look like a 5-10% run awaits. Long $SSRI,$PAAS and $NEM but most high quality names should go if metal prices cooperate positive tweet Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Input: Lots of metal stocks look like a 5-10% run awaits. Long $SSRI,$PAAS and $NEM but most high quality names should go if metal prices cooperate Answer: positive negative negative negative negative negative positive negative
260 258 Morrisons finance chief to fill gap as CEO leaves early negative news Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive. Input: Morrisons finance chief to fill gap as CEO leaves early Answer: negative negative negative negative negative negative negative negative
261 259 Horizonte acquires neighbouring Glencore nickel property in Brazil positive news Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive. Input: Horizonte acquires neighbouring Glencore nickel property in Brazil Answer: positive positive positive negative positive positive positive positive
262 260 Exact (EXAS) Flagged As Strong On High Volume $EXAS http://stks.co/r26Ra positive tweet Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Input: Exact (EXAS) Flagged As Strong On High Volume $EXAS http://stks.co/r26Ra Answer: positive positive negative negative negative negative positive negative
263 261 My $DWA play up 6% today. I'm still skeptical. Will take profits. Not a time cheer neutral tweet Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Input: My $DWA play up 6% today. I'm still skeptical. Will take profits. Not a time cheer Answer: neutral negative negative negative negative negative neutral negative
264 262 Breakingviews: IAG can pay more for Aer Lingus positive news Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive. Input: Breakingviews: IAG can pay more for Aer Lingus Answer: positive positive positive negative negative positive positive positive
265 263 $PLUG bear raid negative tweet Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Input: $PLUG bear raid Answer: negative positive positive negative negative positive negative positive
266 264 $GOOGL is a short below 740 into the upper BB and is overbought negative tweet Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Input: $GOOGL is a short below 740 into the upper BB and is overbought Answer: negative negative negative negative negative negative negative negative
267 265 $FB they are hitting everything in sight.short it. but twtr negative tweet Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Input: $FB they are hitting everything in sight.short it. but twtr Answer: negative negative negative negative negative negative negative negative
268 266 $EDU bouncing nicely after add-on (posted) positive tweet Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Input: $EDU bouncing nicely after add-on (posted) Answer: positive positive positive negative positive positive positive positive
269 267 Long $PCLN positive tweet Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Input: Long $PCLN Answer: positive positive positive positive positive positive positive positive
270 268 Exact (EXAS) Flagged As Strong On High Volume $EXAS http://stks.co/r26Ra positive tweet Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Input: Exact (EXAS) Flagged As Strong On High Volume $EXAS http://stks.co/r26Ra Answer: positive negative negative negative negative negative positive negative
271 269 Shire proposes $30 bln all-share tie-up with Baxalta positive news Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive. Input: Shire proposes $30 bln all-share tie-up with Baxalta Answer: positive negative positive negative negative negative positive negative
272 270 $aapl key is to breakout above 460 on solid volume or else it's a no trade for now positive tweet Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Input: $aapl key is to breakout above 460 on solid volume or else it's a no trade for now Answer: positive negative negative negative negative negative positive negative
273 271 Rio Tinto swings to loss, drops dividend policy negative news Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive. Input: Rio Tinto swings to loss, drops dividend policy Answer: negative negative negative negative negative negative negative negative
274 272 CompaniesUnilever sales lifted by ice cream in soft economy positive news Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive. Input: CompaniesUnilever sales lifted by ice cream in soft economy Answer: positive positive positive negative positive positive positive positive
275 273 Last month we added to our $GILD position and started a new one in $BWLD We see slow, steady, unspectacular growth going forward near term positive tweet Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the tweet and tag it with one of the options: negative, neutral, positive. Input: Last month we added to our $GILD position and started a new one in $BWLD We see slow, steady, unspectacular growth going forward near term Answer: positive negative negative negative negative negative positive negative
276 274 Investors Remain Skeptical About Shell-BG Deal negative news Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive. Instruction: Determine the sentiment expressed in the news and tag it with one of the options: negative, neutral, positive. Input: Investors Remain Skeptical About Shell-BG Deal Answer: negative positive negative negative negative negative negative negative

View File

@@ -0,0 +1,715 @@
{
"cells": [
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Read before you start:\n",
"\n",
"This notebook gives a test demo for all the LLMs we trained during phase2: Multi-Task Instruction Tuning.\n",
"\n",
"- LLMs: Llama2, Falcon, BLOOM, ChatGLM2, Qwen, MPT\n",
"- Tasks: Sentiment Analysis, Headline Classification, Named Entity Extraction, Relation Extraction\n",
"\n",
"All the models & instruction data samples used are also available in our huggingface organization. [https://huggingface.co/FinGPT]\n",
"\n",
"Models trained in phase1&3 are not provided, as MT-models cover most of their capacity. Feel free to train your own models based on the tasks you want.\n",
"\n",
"Due to the limited diversity of the financial tasks and datasets we used, models might not response correctly to out-of-scope instructions. We'll delve into the generalization ability more in our future works."
]
},
{
"cell_type": "code",
"execution_count": 1,
"metadata": {},
"outputs": [],
"source": [
"# First choose to load data/model from huggingface or local space\n",
"\n",
"FROM_REMOTE = False"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"[2023-10-15 20:44:54,084] [INFO] [real_accelerator.py:158:get_accelerator] Setting ds_accelerator to cuda (auto detect)\n"
]
}
],
"source": [
"from transformers import AutoTokenizer, AutoModelForCausalLM\n",
"from peft import PeftModel\n",
"from utils import *"
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {},
"outputs": [],
"source": [
"import logging\n",
"# Suppress Warnings during inference\n",
"logging.getLogger(\"transformers\").setLevel(logging.ERROR)"
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {},
"outputs": [],
"source": [
"demo_tasks = [\n",
" 'Financial Sentiment Analysis',\n",
" 'Financial Relation Extraction',\n",
" 'Financial Headline Classification',\n",
" 'Financial Named Entity Recognition',\n",
"]\n",
"demo_inputs = [\n",
" \"Glaxo's ViiV Healthcare Signs China Manufacturing Deal With Desano\",\n",
" \"Wednesday, July 8, 2015 10:30AM IST (5:00AM GMT) Rimini Street Comment on Oracle Litigation Las Vegas, United States Rimini Street, Inc., the leading independent provider of enterprise software support for SAP AGs (NYSE:SAP) Business Suite and BusinessObjects software and Oracle Corporations (NYSE:ORCL) Siebel , PeopleSoft , JD Edwards , E-Business Suite , Oracle Database , Hyperion and Oracle Retail software, today issued a statement on the Oracle litigation.\",\n",
" 'april gold down 20 cents to settle at $1,116.10/oz',\n",
" 'Subject to the terms and conditions of this Agreement , Bank agrees to lend to Borrower , from time to time prior to the Commitment Termination Date , equipment advances ( each an \" Equipment Advance \" and collectively the \" Equipment Advances \").',\n",
"]\n",
"demo_instructions = [\n",
" 'What is the sentiment of this news? Please choose an answer from {negative/neutral/positive}.',\n",
" 'Given phrases that describe the relationship between two words/phrases as options, extract the word/phrase pair and the corresponding lexical relationship between them from the input text. The output format should be \"relation1: word1, word2; relation2: word3, word4\". Options: product/material produced, manufacturer, distributed by, industry, position held, original broadcaster, owned by, founded by, distribution format, headquarters location, stock exchange, currency, parent organization, chief executive officer, director/manager, owner of, operator, member of, employer, chairperson, platform, subsidiary, legal form, publisher, developer, brand, business division, location of formation, creator.',\n",
" 'Does the news headline talk about price in the past? Please choose an answer from {Yes/No}.',\n",
" 'Please extract entities and their types from the input sentence, entity types should be chosen from {person/organization/location}.',\n",
"]"
]
},
{
"cell_type": "code",
"execution_count": 5,
"metadata": {},
"outputs": [],
"source": [
"def load_model(base_model, peft_model, from_remote=False):\n",
" \n",
" model_name = parse_model_name(base_model, from_remote)\n",
"\n",
" model = AutoModelForCausalLM.from_pretrained(\n",
" model_name, trust_remote_code=True, \n",
" device_map=\"auto\",\n",
" )\n",
" model.model_parallel = True\n",
"\n",
" tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True)\n",
" \n",
" tokenizer.padding_side = \"left\"\n",
" if base_model == 'qwen':\n",
" tokenizer.eos_token_id = tokenizer.convert_tokens_to_ids('<|endoftext|>')\n",
" tokenizer.pad_token_id = tokenizer.convert_tokens_to_ids('<|extra_0|>')\n",
" if not tokenizer.pad_token or tokenizer.pad_token_id == tokenizer.eos_token_id:\n",
" tokenizer.add_special_tokens({'pad_token': '[PAD]'})\n",
" model.resize_token_embeddings(len(tokenizer))\n",
" \n",
" model = PeftModel.from_pretrained(model, peft_model)\n",
" model = model.eval()\n",
" return model, tokenizer\n",
"\n",
"\n",
"def test_demo(model, tokenizer):\n",
"\n",
" for task_name, input, instruction in zip(demo_tasks, demo_inputs, demo_instructions):\n",
" prompt = 'Instruction: {instruction}\\nInput: {input}\\nAnswer: '.format(\n",
" input=input, \n",
" instruction=instruction\n",
" )\n",
" inputs = tokenizer(\n",
" prompt, return_tensors='pt',\n",
" padding=True, max_length=512,\n",
" return_token_type_ids=False\n",
" )\n",
" inputs = {key: value.to(model.device) for key, value in inputs.items()}\n",
" res = model.generate(\n",
" **inputs, max_length=512, do_sample=False,\n",
" eos_token_id=tokenizer.eos_token_id\n",
" )\n",
" output = tokenizer.decode(res[0], skip_special_tokens=True)\n",
" print(f\"\\n==== {task_name} ====\\n\")\n",
" print(output)\n",
" "
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Llama2-7B"
]
},
{
"cell_type": "code",
"execution_count": 6,
"metadata": {},
"outputs": [
{
"data": {
"application/json": {
"ascii": false,
"bar_format": null,
"colour": null,
"elapsed": 0.006228446960449219,
"initial": 0,
"n": 0,
"ncols": null,
"nrows": null,
"postfix": null,
"prefix": "Loading checkpoint shards",
"rate": null,
"total": 2,
"unit": "it",
"unit_divisor": 1000,
"unit_scale": false
},
"application/vnd.jupyter.widget-view+json": {
"model_id": "0d58aff745fb486780792c86384fe702",
"version_major": 2,
"version_minor": 0
},
"text/plain": [
"Loading checkpoint shards: 0%| | 0/2 [00:00<?, ?it/s]"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"Using pad_token, but it is not set yet.\n",
"/root/.conda/envs/torch2/lib/python3.9/site-packages/transformers/tokenization_utils_base.py:2436: UserWarning: `max_length` is ignored when `padding`=`True` and there is no truncation strategy. To pad to max length, use `padding='max_length'`.\n",
" warnings.warn(\n",
"/root/.conda/envs/torch2/lib/python3.9/site-packages/transformers/generation/configuration_utils.py:362: UserWarning: `do_sample` is set to `False`. However, `temperature` is set to `0.6` -- this flag is only used in sample-based generation modes. You should set `do_sample=True` or unset `temperature`.\n",
" warnings.warn(\n",
"/root/.conda/envs/torch2/lib/python3.9/site-packages/transformers/generation/configuration_utils.py:367: UserWarning: `do_sample` is set to `False`. However, `top_p` is set to `0.9` -- this flag is only used in sample-based generation modes. You should set `do_sample=True` or unset `top_p`.\n",
" warnings.warn(\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"==== Financial Sentiment Analysis ====\n",
"\n",
"Instruction: What is the sentiment of this news? Please choose an answer from {negative/neutral/positive}.\n",
"Input: Glaxo's ViiV Healthcare Signs China Manufacturing Deal With Desano\n",
"Answer: positive\n",
"\n",
"==== Financial Relation Extraction ====\n",
"\n",
"Instruction: Given phrases that describe the relationship between two words/phrases as options, extract the word/phrase pair and the corresponding lexical relationship between them from the input text. The output format should be \"relation1: word1, word2; relation2: word3, word4\". Options: product/material produced, manufacturer, distributed by, industry, position held, original broadcaster, owned by, founded by, distribution format, headquarters location, stock exchange, currency, parent organization, chief executive officer, director/manager, owner of, operator, member of, employer, chairperson, platform, subsidiary, legal form, publisher, developer, brand, business division, location of formation, creator.\n",
"Input: Wednesday, July 8, 2015 10:30AM IST (5:00AM GMT) Rimini Street Comment on Oracle Litigation Las Vegas, United States Rimini Street, Inc., the leading independent provider of enterprise software support for SAP AGs (NYSE:SAP) Business Suite and BusinessObjects software and Oracle Corporations (NYSE:ORCL) Siebel , PeopleSoft , JD Edwards , E-Business Suite , Oracle Database , Hyperion and Oracle Retail software, today issued a statement on the Oracle litigation.\n",
"Answer: product_or_material_produced: PeopleSoft, software; parent_organization: Siebel, Oracle Corporation; industry: Oracle Corporation, software; product_or_material_produced: Oracle Corporation, software; product_or_material_produced: Oracle Corporation, software\n",
"\n",
"==== Financial Headline Classification ====\n",
"\n",
"Instruction: Does the news headline talk about price in the past? Please choose an answer from {Yes/No}.\n",
"Input: april gold down 20 cents to settle at $1,116.10/oz\n",
"Answer: Yes\n",
"\n",
"==== Financial Named Entity Recognition ====\n",
"\n",
"Instruction: Please extract entities and their types from the input sentence, entity types should be chosen from {person/organization/location}.\n",
"Input: Subject to the terms and conditions of this Agreement , Bank agrees to lend to Borrower , from time to time prior to the Commitment Termination Date , equipment advances ( each an \" Equipment Advance \" and collectively the \" Equipment Advances \").\n",
"Answer: Bank is an organization, Borrower is a person.\n"
]
}
],
"source": [
"base_model = 'llama2'\n",
"peft_model = 'fingpt-mt_llama2-7b_lora' if FROM_REMOTE else 'finetuned_models/MT-llama2-linear_202309241345'\n",
"\n",
"model, tokenizer = load_model(base_model, peft_model, FROM_REMOTE)\n",
"test_demo(model, tokenizer)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Qwen-7B"
]
},
{
"cell_type": "code",
"execution_count": 7,
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"The model is automatically converting to bf16 for faster inference. If you want to disable the automatic precision, please manually add bf16/fp16/fp32=True to \"AutoModelForCausalLM.from_pretrained\".\n",
"Try importing flash-attention for faster inference...\n",
"Warning: import flash_attn rotary fail, please install FlashAttention rotary to get higher efficiency https://github.com/Dao-AILab/flash-attention/tree/main/csrc/rotary\n",
"Warning: import flash_attn rms_norm fail, please install FlashAttention layer_norm to get higher efficiency https://github.com/Dao-AILab/flash-attention/tree/main/csrc/layer_norm\n",
"Warning: import flash_attn fail, please install FlashAttention to get higher efficiency https://github.com/Dao-AILab/flash-attention\n"
]
},
{
"data": {
"application/json": {
"ascii": false,
"bar_format": null,
"colour": null,
"elapsed": 0.004647493362426758,
"initial": 0,
"n": 0,
"ncols": null,
"nrows": null,
"postfix": null,
"prefix": "Loading checkpoint shards",
"rate": null,
"total": 8,
"unit": "it",
"unit_divisor": 1000,
"unit_scale": false
},
"application/vnd.jupyter.widget-view+json": {
"model_id": "e1978e69ea784778acd1813cc0647c3e",
"version_major": 2,
"version_minor": 0
},
"text/plain": [
"Loading checkpoint shards: 0%| | 0/8 [00:00<?, ?it/s]"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"/root/.conda/envs/torch2/lib/python3.9/site-packages/transformers/generation/configuration_utils.py:367: UserWarning: `do_sample` is set to `False`. However, `top_p` is set to `0.8` -- this flag is only used in sample-based generation modes. You should set `do_sample=True` or unset `top_p`.\n",
" warnings.warn(\n",
"/root/.conda/envs/torch2/lib/python3.9/site-packages/transformers/generation/configuration_utils.py:377: UserWarning: `do_sample` is set to `False`. However, `top_k` is set to `0` -- this flag is only used in sample-based generation modes. You should set `do_sample=True` or unset `top_k`.\n",
" warnings.warn(\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"==== Financial Sentiment Analysis ====\n",
"\n",
"Instruction: What is the sentiment of this news? Please choose an answer from {negative/neutral/positive}.\n",
"Input: Glaxo's ViiV Healthcare Signs China Manufacturing Deal With Desano\n",
"Answer: positive\n",
"\n",
"==== Financial Relation Extraction ====\n",
"\n",
"Instruction: Given phrases that describe the relationship between two words/phrases as options, extract the word/phrase pair and the corresponding lexical relationship between them from the input text. The output format should be \"relation1: word1, word2; relation2: word3, word4\". Options: product/material produced, manufacturer, distributed by, industry, position held, original broadcaster, owned by, founded by, distribution format, headquarters location, stock exchange, currency, parent organization, chief executive officer, director/manager, owner of, operator, member of, employer, chairperson, platform, subsidiary, legal form, publisher, developer, brand, business division, location of formation, creator.\n",
"Input: Wednesday, July 8, 2015 10:30AM IST (5:00AM GMT) Rimini Street Comment on Oracle Litigation Las Vegas, United States Rimini Street, Inc., the leading independent provider of enterprise software support for SAP AGs (NYSE:SAP) Business Suite and BusinessObjects software and Oracle Corporations (NYSE:ORCL) Siebel , PeopleSoft , JD Edwards , E-Business Suite , Oracle Database , Hyperion and Oracle Retail software, today issued a statement on the Oracle litigation.\n",
"Answer: subsidiary: PeopleSoft, JD Edwards\n",
"\n",
"==== Financial Headline Classification ====\n",
"\n",
"Instruction: Does the news headline talk about price in the past? Please choose an answer from {Yes/No}.\n",
"Input: april gold down 20 cents to settle at $1,116.10/oz\n",
"Answer: Yes\n",
"\n",
"==== Financial Named Entity Recognition ====\n",
"\n",
"Instruction: Please extract entities and their types from the input sentence, entity types should be chosen from {person/organization/location}.\n",
"Input: Subject to the terms and conditions of this Agreement , Bank agrees to lend to Borrower , from time to time prior to the Commitment Termination Date , equipment advances ( each an \" Equipment Advance \" and collectively the \" Equipment Advances \").\n",
"Answer: Bank is an organization, Borrower is a person.\n"
]
}
],
"source": [
"base_model = 'qwen'\n",
"peft_model = 'fingpt-mt_qwen-7b_lora' if FROM_REMOTE else 'finetuned_models/MT-qwen-linear_202309221011'\n",
"\n",
"model, tokenizer = load_model(base_model, peft_model, FROM_REMOTE)\n",
"test_demo(model, tokenizer)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Falcon-7B"
]
},
{
"cell_type": "code",
"execution_count": 8,
"metadata": {},
"outputs": [
{
"data": {
"application/json": {
"ascii": false,
"bar_format": null,
"colour": null,
"elapsed": 0.004422426223754883,
"initial": 0,
"n": 0,
"ncols": null,
"nrows": null,
"postfix": null,
"prefix": "Loading checkpoint shards",
"rate": null,
"total": 2,
"unit": "it",
"unit_divisor": 1000,
"unit_scale": false
},
"application/vnd.jupyter.widget-view+json": {
"model_id": "e12fadfbaa6048538bbeef26ed563b28",
"version_major": 2,
"version_minor": 0
},
"text/plain": [
"Loading checkpoint shards: 0%| | 0/2 [00:00<?, ?it/s]"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"Using pad_token, but it is not set yet.\n",
"/root/.conda/envs/torch2/lib/python3.9/site-packages/transformers/generation/utils.py:1411: UserWarning: You have modified the pretrained model configuration to control generation. This is a deprecated strategy to control generation and will be removed soon, in a future version. Please use a generation configuration file (see https://huggingface.co/docs/transformers/main_classes/text_generation )\n",
" warnings.warn(\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"==== Financial Sentiment Analysis ====\n",
"\n",
"Instruction: What is the sentiment of this news? Please choose an answer from {negative/neutral/positive}.\n",
"Input: Glaxo's ViiV Healthcare Signs China Manufacturing Deal With Desano\n",
"Answer: positive\n",
"\n",
"==== Financial Relation Extraction ====\n",
"\n",
"Instruction: Given phrases that describe the relationship between two words/phrases as options, extract the word/phrase pair and the corresponding lexical relationship between them from the input text. The output format should be \"relation1: word1, word2; relation2: word3, word4\". Options: product/material produced, manufacturer, distributed by, industry, position held, original broadcaster, owned by, founded by, distribution format, headquarters location, stock exchange, currency, parent organization, chief executive officer, director/manager, owner of, operator, member of, employer, chairperson, platform, subsidiary, legal form, publisher, developer, brand, business division, location of formation, creator.\n",
"Input: Wednesday, July 8, 2015 10:30AM IST (5:00AM GMT) Rimini Street Comment on Oracle Litigation Las Vegas, United States Rimini Street, Inc., the leading independent provider of enterprise software support for SAP AGs (NYSE:SAP) Business Suite and BusinessObjects software and Oracle Corporations (NYSE:ORCL) Siebel, PeopleSoft, JD Edwards, E-Business Suite, Oracle Database, Hyperion and Oracle Retail software, today issued a statement on the Oracle litigation.\n",
"Answer: product_or_material_produced: PeopleSoft, Oracle Database\n",
"\n",
"==== Financial Headline Classification ====\n",
"\n",
"Instruction: Does the news headline talk about price in the past? Please choose an answer from {Yes/No}.\n",
"Input: april gold down 20 cents to settle at $1,116.10/oz\n",
"Answer: Yes\n",
"\n",
"==== Financial Named Entity Recognition ====\n",
"\n",
"Instruction: Please extract entities and their types from the input sentence, entity types should be chosen from {person/organization/location}.\n",
"Input: Subject to the terms and conditions of this Agreement, Bank agrees to lend to Borrower, from time to time prior to the Commitment Termination Date, equipment advances ( each an \" Equipment Advance \" and collectively the \" Equipment Advances \").\n",
"Answer: Bank is an organization, Borrower is a person.\n"
]
}
],
"source": [
"base_model = 'falcon'\n",
"peft_model = 'fingpt-mt_falcon-7b_lora' if FROM_REMOTE else 'finetuned_models/MT-falcon-linear_202309210126'\n",
"\n",
"model, tokenizer = load_model(base_model, peft_model, FROM_REMOTE)\n",
"test_demo(model, tokenizer)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# ChatGLM2-6B"
]
},
{
"cell_type": "code",
"execution_count": 9,
"metadata": {},
"outputs": [
{
"data": {
"application/json": {
"ascii": false,
"bar_format": null,
"colour": null,
"elapsed": 0.004460573196411133,
"initial": 0,
"n": 0,
"ncols": null,
"nrows": null,
"postfix": null,
"prefix": "Loading checkpoint shards",
"rate": null,
"total": 7,
"unit": "it",
"unit_divisor": 1000,
"unit_scale": false
},
"application/vnd.jupyter.widget-view+json": {
"model_id": "8bddd025a6514946b5f07f55e9c38f58",
"version_major": 2,
"version_minor": 0
},
"text/plain": [
"Loading checkpoint shards: 0%| | 0/7 [00:00<?, ?it/s]"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"==== Financial Sentiment Analysis ====\n",
"\n",
"Instruction: What is the sentiment of this news? Please choose an answer from {negative/neutral/positive}.\n",
"Input: Glaxo's ViiV Healthcare Signs China Manufacturing Deal With Desano\n",
"Answer: positive\n",
"\n",
"==== Financial Relation Extraction ====\n",
"\n",
"Instruction: Given phrases that describe the relationship between two words/phrases as options, extract the word/phrase pair and the corresponding lexical relationship between them from the input text. The output format should be \"relation1: word1, word2; relation2: word3, word4\". Options: product/material produced, manufacturer, distributed by, industry, position held, original broadcaster, owned by, founded by, distribution format, headquarters location, stock exchange, currency, parent organization, chief executive officer, director/manager, owner of, operator, member of, employer, chairperson, platform, subsidiary, legal form, publisher, developer, brand, business division, location of formation, creator.\n",
"Input: Wednesday, July 8, 2015 10:30AM IST (5:00AM GMT) Rimini Street Comment on Oracle Litigation Las Vegas, United States Rimini Street, Inc., the leading independent provider of enterprise software support for SAP AGs (NYSE:SAP) Business Suite and BusinessObjects software and Oracle Corporations (NYSE:ORCL) Siebel , PeopleSoft , JD Edwards , E-Business Suite , Oracle Database , Hyperion and Oracle Retail software, today issued a statement on the Oracle litigation.\n",
"Answer: product_or_material_produced: Oracle, Oracle Database; developer: Oracle, Oracle; product_or_material_produced: Oracle, Oracle Database\n",
"\n",
"==== Financial Headline Classification ====\n",
"\n",
"Instruction: Does the news headline talk about price in the past? Please choose an answer from {Yes/No}.\n",
"Input: april gold down 20 cents to settle at $1,116.10/oz\n",
"Answer: Yes\n",
"\n",
"==== Financial Named Entity Recognition ====\n",
"\n",
"Instruction: Please extract entities and their types from the input sentence, entity types should be chosen from {person/organization/location}.\n",
"Input: Subject to the terms and conditions of this Agreement , Bank agrees to lend to Borrower , from time to time prior to the Commitment Termination Date , equipment advances ( each an \" Equipment Advance \" and collectively the \" Equipment Advances \").\n",
"Answer: Bank is an organization, Borrower is a person.\n"
]
}
],
"source": [
"base_model = 'chatglm2'\n",
"peft_model = 'fingpt-mt_chatglm2-6b_lora' if FROM_REMOTE else 'finetuned_models/MT-chatglm2-linear_202309201120'\n",
"\n",
"model, tokenizer = load_model(base_model, peft_model, FROM_REMOTE)\n",
"test_demo(model, tokenizer)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# BLOOM-7B1"
]
},
{
"cell_type": "code",
"execution_count": 10,
"metadata": {},
"outputs": [
{
"data": {
"application/json": {
"ascii": false,
"bar_format": null,
"colour": null,
"elapsed": 0.004486799240112305,
"initial": 0,
"n": 0,
"ncols": null,
"nrows": null,
"postfix": null,
"prefix": "Loading checkpoint shards",
"rate": null,
"total": 2,
"unit": "it",
"unit_divisor": 1000,
"unit_scale": false
},
"application/vnd.jupyter.widget-view+json": {
"model_id": "32ee0b5e2df049a0b9e458c779e09a68",
"version_major": 2,
"version_minor": 0
},
"text/plain": [
"Loading checkpoint shards: 0%| | 0/2 [00:00<?, ?it/s]"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"==== Financial Sentiment Analysis ====\n",
"\n",
"Instruction: What is the sentiment of this news? Please choose an answer from {negative/neutral/positive}.\n",
"Input: Glaxo's ViiV Healthcare Signs China Manufacturing Deal With Desano\n",
"Answer: positive\n",
"\n",
"==== Financial Relation Extraction ====\n",
"\n",
"Instruction: Given phrases that describe the relationship between two words/phrases as options, extract the word/phrase pair and the corresponding lexical relationship between them from the input text. The output format should be \"relation1: word1, word2; relation2: word3, word4\". Options: product/material produced, manufacturer, distributed by, industry, position held, original broadcaster, owned by, founded by, distribution format, headquarters location, stock exchange, currency, parent organization, chief executive officer, director/manager, owner of, operator, member of, employer, chairperson, platform, subsidiary, legal form, publisher, developer, brand, business division, location of formation, creator.\n",
"Input: Wednesday, July 8, 2015 10:30AM IST (5:00AM GMT) Rimini Street Comment on Oracle Litigation Las Vegas, United States Rimini Street, Inc., the leading independent provider of enterprise software support for SAP AGs (NYSE:SAP) Business Suite and BusinessObjects software and Oracle Corporations (NYSE:ORCL) Siebel , PeopleSoft , JD Edwards , E-Business Suite , Oracle Database , Hyperion and Oracle Retail software, today issued a statement on the Oracle litigation.\n",
"Answer: product_or_material_produced: software provider, Software\n",
"\n",
"==== Financial Headline Classification ====\n",
"\n",
"Instruction: Does the news headline talk about price in the past? Please choose an answer from {Yes/No}.\n",
"Input: april gold down 20 cents to settle at $1,116.10/oz\n",
"Answer: Yes\n",
"\n",
"==== Financial Named Entity Recognition ====\n",
"\n",
"Instruction: Please extract entities and their types from the input sentence, entity types should be chosen from {person/organization/location}.\n",
"Input: Subject to the terms and conditions of this Agreement , Bank agrees to lend to Borrower , from time to time prior to the Commitment Termination Date , equipment advances ( each an \" Equipment Advance \" and collectively the \" Equipment Advances \").\n",
"Answer: Bank is an organization, Borrower is a person.\n"
]
}
],
"source": [
"base_model = 'bloom'\n",
"peft_model = 'fingpt-mt_bloom-7b1_lora' if FROM_REMOTE else 'finetuned_models/MT-bloom-linear_202309211510'\n",
"\n",
"model, tokenizer = load_model(base_model, peft_model, FROM_REMOTE)\n",
"test_demo(model, tokenizer)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# MPT-7B"
]
},
{
"cell_type": "code",
"execution_count": 11,
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"/root/.cache/huggingface/modules/transformers_modules/mpt-7b-peft-compatible/attention.py:148: UserWarning: Using `attn_impl: torch`. If your model does not use `alibi` or `prefix_lm` we recommend using `attn_impl: flash` otherwise we recommend using `attn_impl: triton`.\n",
" warnings.warn('Using `attn_impl: torch`. If your model does not use `alibi` or ' + '`prefix_lm` we recommend using `attn_impl: flash` otherwise ' + 'we recommend using `attn_impl: triton`.')\n",
"The model weights are not tied. Please use the `tie_weights` method before using the `infer_auto_device` function.\n"
]
},
{
"data": {
"application/json": {
"ascii": false,
"bar_format": null,
"colour": null,
"elapsed": 0.004449605941772461,
"initial": 0,
"n": 0,
"ncols": null,
"nrows": null,
"postfix": null,
"prefix": "Loading checkpoint shards",
"rate": null,
"total": 2,
"unit": "it",
"unit_divisor": 1000,
"unit_scale": false
},
"application/vnd.jupyter.widget-view+json": {
"model_id": "0440bc96112344c493c8a1f5dd76f319",
"version_major": 2,
"version_minor": 0
},
"text/plain": [
"Loading checkpoint shards: 0%| | 0/2 [00:00<?, ?it/s]"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"Using pad_token, but it is not set yet.\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"==== Financial Sentiment Analysis ====\n",
"\n",
"Instruction: What is the sentiment of this news? Please choose an answer from {negative/neutral/positive}.\n",
"Input: Glaxo's ViiV Healthcare Signs China Manufacturing Deal With Desano\n",
"Answer: positive\n",
"\n",
"==== Financial Relation Extraction ====\n",
"\n",
"Instruction: Given phrases that describe the relationship between two words/phrases as options, extract the word/phrase pair and the corresponding lexical relationship between them from the input text. The output format should be \"relation1: word1, word2; relation2: word3, word4\". Options: product/material produced, manufacturer, distributed by, industry, position held, original broadcaster, owned by, founded by, distribution format, headquarters location, stock exchange, currency, parent organization, chief executive officer, director/manager, owner of, operator, member of, employer, chairperson, platform, subsidiary, legal form, publisher, developer, brand, business division, location of formation, creator.\n",
"Input: Wednesday, July 8, 2015 10:30AM IST (5:00AM GMT) Rimini Street Comment on Oracle Litigation Las Vegas, United States Rimini Street, Inc., the leading independent provider of enterprise software support for SAP AGs (NYSE:SAP) Business Suite and BusinessObjects software and Oracle Corporations (NYSE:ORCL) Siebel, PeopleSoft, JD Edwards, E-Business Suite, Oracle Database, Hyperion and Oracle Retail software, today issued a statement on the Oracle litigation.\n",
"Answer: product_or_material_produced: Hyperion, software\n",
"\n",
"==== Financial Headline Classification ====\n",
"\n",
"Instruction: Does the news headline talk about price in the past? Please choose an answer from {Yes/No}.\n",
"Input: april gold down 20 cents to settle at $1,116.10/oz\n",
"Answer: Yes\n",
"\n",
"==== Financial Named Entity Recognition ====\n",
"\n",
"Instruction: Please extract entities and their types from the input sentence, entity types should be chosen from {person/organization/location}.\n",
"Input: Subject to the terms and conditions of this Agreement, Bank agrees to lend to Borrower, from time to time prior to the Commitment Termination Date, equipment advances ( each an \" Equipment Advance \" and collectively the \" Equipment Advances \").\n",
"Answer: Bank is an organization, Borrower is a person.\n"
]
}
],
"source": [
"base_model = 'mpt'\n",
"peft_model = 'fingpt-mt_mpt-7b_lora' if FROM_REMOTE else 'finetuned_models/MT-mpt-linear_202309230221'\n",
"\n",
"model, tokenizer = load_model(base_model, peft_model, FROM_REMOTE)\n",
"test_demo(model, tokenizer)"
]
}
],
"metadata": {
"kernelspec": {
"display_name": "torch2",
"language": "python",
"name": "torch2"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.9.12"
}
},
"nbformat": 4,
"nbformat_minor": 4
}

View File

@@ -1,477 +0,0 @@
export CUDA_VISIBLE_DEVICES=0,1,2,3
export NCCL_IGNORE_DISABLED_P2P=1
export TRANSFORMERS_NO_ADVISORY_WARNINGS=1
export TOKENIZERS_PARALLELISM=0
#---- Generalization ----
# deepspeed eval_ckpts.py \
# --run_name GRCLS-sentiment-qwen-linear-1e-4lr \
# --base_model qwen \
# --test_dataset sentiment-cls-instruct \
# --peft_model GRCLS-sentiment-qwen-linear-1e-4lr_202309280036 \
# --max_length 512 \
# --batch_size 4 \
# --learning_rate 1e-4 \
# --num_epochs 1 \
# --log_interval 10 \
# --warmup_ratio 0.03 \
# --scheduler linear \
# --ds_config config_newnew.json
# deepspeed train_lora.py \
# --run_name GRCLS-sentiment-mpt-linear-small \
# --base_model mpt \
# --dataset headline-instruct,finred-cls-instruct*2,ner-cls-instruct*7 \
# --test_dataset sentiment-cls-instruct \
# --max_length 512 \
# --batch_size 4 \
# --learning_rate 1e-4 \
# --num_epochs 1 \
# --log_interval 10 \
# --warmup_ratio 0.03 \
# --scheduler linear \
# --evaluation_strategy steps \
# --ds_config config_newnew.json
deepspeed eval_ckpts.py \
--run_name GRCLS-sentiment-chatglm2-linear-1e-4lr \
--base_model chatglm2 \
--test_dataset sentiment-cls-instruct \
--peft_model GRCLS-sentiment-chatglm2-linear-1e-4lr_202309280440 \
--dataset headline-instruct,finred-cls-instruct*2,ner-cls-instruct*7 \
--max_length 512 \
--batch_size 4 \
--learning_rate 1e-4 \
--num_epochs 1 \
--log_interval 10 \
--warmup_ratio 0.03 \
--scheduler linear \
--evaluation_strategy steps \
--ds_config config_newnew.json
# deepspeed train_lora.py \
# --run_name GRCLS-sentiment-bloom-linear-1e-4lr \
# --base_model bloom \
# --dataset headline-instruct,finred-cls-instruct*2,ner-cls-instruct*7 \
# --max_length 512 \
# --batch_size 4 \
# --learning_rate 1e-4 \
# --num_epochs 1 \
# --log_interval 10 \
# --warmup_ratio 0.03 \
# --scheduler linear \
# --evaluation_strategy steps \
# --ds_config config_newnew.json
# deepspeed train_lora.py \
# --run_name GRCLS-sentiment-llama2-linear-small \
# --base_model llama2 \
# --dataset headline-instruct,finred-cls-instruct*2,ner-cls-instruct*7 \
# --max_length 512 \
# --batch_size 4 \
# --learning_rate 1e-4 \
# --num_epochs 1 \
# --log_interval 10 \
# --warmup_ratio 0 \
# --scheduler linear \
# --evaluation_strategy steps \
# --ds_config config_newnew.json
# deepspeed train_lora.py \
# --run_name GRCLS-sentiment-falcon-linear-small \
# --base_model falcon \
# --dataset headline-instruct,finred-cls-instruct*2,ner-cls-instruct*7 \
# --max_length 512 \
# --batch_size 4 \
# --learning_rate 1e-4 \
# --num_epochs 1 \
# --log_interval 10 \
# --warmup_ratio 0.03 \
# --scheduler linear \
# --evaluation_strategy steps \
# --ds_config config_newnew.json
#---- Multi-Task ----
# deepspeed train_lora.py \
# --run_name MT-chatglm2-linear \
# --base_model chatglm2 \
# --dataset sentiment-train,headline,finred*3,ner*15 \
# --max_length 512 \
# --batch_size 4 \
# --learning_rate 1e-4 \
# --num_epochs 4
# deepspeed train_lora.py \
# --run_name MT-falcon-linear \
# --base_model falcon \
# --dataset sentiment-train,headline,finred*3,ner*15 \
# --max_length 512 \
# --batch_size 4 \
# --learning_rate 1e-4 \
# --num_epochs 4
# deepspeed train_lora.py \
# --run_name MT-qwen-linear \
# --base_model qwen \
# --dataset sentiment-train,headline,finred*3,ner*15 \
# --max_length 512 \
# --batch_size 4 \
# --learning_rate 1e-4 \
# --num_epochs 4
# deepspeed train_lora.py \
# --run_name MT-mpt-linear \
# --base_model mpt \
# --dataset sentiment-train,headline,finred*3,ner*15 \
# --max_length 512 \
# --batch_size 4 \
# --learning_rate 1e-4 \
# --num_epochs 4
# deepspeed train_lora.py \
# --run_name MT-bloom-linear \
# --base_model bloom \
# --dataset sentiment-train,headline,finred*3,ner*15 \
# --max_length 512 \
# --batch_size 4 \
# --learning_rate 1e-4 \
# --num_epochs 4
# deepspeed train_lora.py \
# --run_name MT-llama2-linear \
# --base_model llama2 \
# --dataset sentiment-train,headline,finred*3,ner*15 \
# --max_length 512 \
# --batch_size 4 \
# --learning_rate 1e-4 \
# --num_epochs 4 \
# --log_interval 10
#---- FinEval ----
# deepspeed train_lora.py \
# --run_name fineval-internlm-linear \
# --base_model internlm \
# --dataset data/fingpt-fineval \
# --max_length 512 \
# --batch_size 4 \
# --learning_rate 1e-4 \
# --num_epochs 50 \
# --log_interval 10
# deepspeed train_lora.py \
# --run_name fineval-llama2-linear \
# --base_model llama2 \
# --dataset data/fingpt-fineval \
# --max_length 512 \
# --batch_size 4 \
# --learning_rate 1e-4 \
# --num_epochs 50 \
# --log_interval 10
# deepspeed train_lora.py \
# --run_name fineval-chatglm2-linear \
# --base_model chatglm2 \
# --dataset data/fingpt-fineval \
# --max_length 512 \
# --batch_size 4 \
# --learning_rate 1e-4 \
# --num_epochs 50 \
# --log_interval 10
# deepspeed train_lora.py \
# --run_name fineval-falcon-linear \
# --base_model falcon \
# --dataset data/fingpt-fineval \
# --max_length 512 \
# --batch_size 4 \
# --learning_rate 1e-4 \
# --num_epochs 50 \
# --log_interval 10
# deepspeed train_lora.py \
# --run_name fineval-qwen-linear \
# --base_model qwen \
# --dataset data/fingpt-fineval \
# --max_length 512 \
# --batch_size 4 \
# --learning_rate 1e-4 \
# --num_epochs 50 \
# --log_interval 10
# deepspeed train_lora.py \
# --run_name fineval-mpt-linear \
# --base_model mpt \
# --dataset data/fingpt-fineval \
# --max_length 512 \
# --batch_size 4 \
# --learning_rate 1e-4 \
# --num_epochs 50 \
# --log_interval 10
# deepspeed train_lora.py \
# --run_name fineval-bloom-linear \
# --base_model bloom \
# --dataset data/fingpt-fineval \
# --max_length 512 \
# --batch_size 4 \
# --learning_rate 1e-4 \
# --num_epochs 50 \
# --log_interval 10
#---- ConvFinQA ----
# deepspeed train_lora.py \
# --run_name convfinqa-llama2-linear \
# --base_model llama2 \
# --dataset data/fingpt-convfinqa \
# --max_length 2048 \
# --batch_size 1 \
# --learning_rate 1e-4 \
# --num_epochs 4
# deepspeed train_lora.py \
# --run_name convfinqa-chatglm2-linear \
# --base_model chatglm2 \
# --dataset data/fingpt-convfinqa \
# --max_length 2048 \
# --batch_size 1 \
# --learning_rate 1e-4 \
# --num_epochs 4
# deepspeed train_lora.py \
# --run_name convfinqa-falcon-linear \
# --base_model falcon \
# --dataset data/fingpt-convfinqa \
# --max_length 2048 \
# --batch_size 1 \
# --learning_rate 1e-4 \
# --num_epochs 4
# deepspeed train_lora.py \
# --run_name convfinqa-qwen-linear \
# --base_model qwen \
# --dataset data/fingpt-convfinqa \
# --max_length 2048 \
# --batch_size 1 \
# --learning_rate 1e-4 \
# --num_epochs 4
# deepspeed train_lora.py \
# --run_name convfinqa-mpt-linear \
# --base_model mpt \
# --dataset data/fingpt-convfinqa \
# --max_length 2048 \
# --batch_size 1 \
# --learning_rate 1e-4 \
# --num_epochs 4
# deepspeed train_lora.py \
# --run_name convfinqa-bloom-linear \
# --base_model bloom \
# --dataset data/fingpt-convfinqa \
# --max_length 2048 \
# --batch_size 1 \
# --learning_rate 1e-4 \
# --num_epochs 4
#---- NER ----
# deepspeed train_lora.py \
# --run_name ner-llama2-linear \
# --base_model llama2 \
# --dataset data/fingpt-ner \
# --max_length 512 \
# --batch_size 4 \
# --learning_rate 1e-4 \
# --num_epochs 100 \
# --log_interval 10
# deepspeed train_lora.py \
# --run_name ner-chatglm2-linear \
# --base_model chatglm2 \
# --dataset data/fingpt-ner \
# --max_length 512 \
# --batch_size 4 \
# --learning_rate 1e-4 \
# --num_epochs 100 \
# --log_interval 10
# deepspeed train_lora.py \
# --run_name ner-falcon-linear \
# --base_model falcon \
# --dataset data/fingpt-ner \
# --max_length 512 \
# --batch_size 4 \
# --learning_rate 1e-4 \
# --num_epochs 100 \
# --log_interval 10
# deepspeed train_lora.py \
# --run_name ner-qwen-linear \
# --base_model qwen \
# --dataset data/fingpt-ner \
# --max_length 512 \
# --batch_size 4 \
# --learning_rate 1e-4 \
# --num_epochs 100 \
# --log_interval 10
# deepspeed train_lora.py \
# --run_name ner-mpt-linear \
# --base_model mpt \
# --dataset data/fingpt-ner \
# --max_length 512 \
# --batch_size 4 \
# --learning_rate 1e-4 \
# --num_epochs 100 \
# --log_interval 10
# deepspeed train_lora.py \
# --run_name ner-bloom-linear \
# --base_model bloom \
# --dataset data/fingpt-ner \
# --max_length 512 \
# --batch_size 4 \
# --learning_rate 1e-4 \
# --num_epochs 100 \
# --log_interval 10
#---- Headline (IE) ----
# deepspeed train_lora.py \
# --run_name headline-internlm-linear \
# --base_model internlm \
# --dataset data/fingpt-headline \
# --max_length 512 \
# --batch_size 4 \
# --learning_rate 1e-4 \
# --num_epochs 8
# deepspeed train_lora.py \
# --run_name headline-llama2-linear \
# --base_model llama2 \
# --dataset data/fingpt-headline \
# --max_length 512 \
# --batch_size 4 \
# --learning_rate 1e-4 \
# --num_epochs 8
# deepspeed train_lora.py \
# --run_name headline-chatglm2-linear \
# --base_model chatglm2 \
# --dataset data/fingpt-headline \
# --max_length 512 \
# --batch_size 4 \
# --learning_rate 1e-4 \
# --num_epochs 8
# deepspeed train_lora.py \
# --run_name headline-falcon-linear \
# --base_model falcon \
# --dataset data/fingpt-headline \
# --max_length 512 \
# --batch_size 4 \
# --learning_rate 1e-4 \
# --num_epochs 8
# deepspeed train_lora.py \
# --run_name headline-qwen-linear \
# --base_model qwen \
# --dataset data/fingpt-headline \
# --max_length 512 \
# --batch_size 4 \
# --learning_rate 1e-4 \
# --num_epochs 8
# deepspeed train_lora.py \
# --run_name headline-mpt-linear \
# --base_model mpt \
# --dataset data/fingpt-headline \
# --max_length 512 \
# --batch_size 4 \
# --learning_rate 1e-4 \
# --num_epochs 8
# deepspeed train_lora.py \
# --run_name headline-bloom-linear \
# --base_model bloom \
# --dataset data/fingpt-headline \
# --max_length 512 \
# --batch_size 4 \
# --learning_rate 1e-4 \
# --num_epochs 8
#---- Sentiment Analysis ----
# deepspeed train_lora.py \
# --run_name sentiment-internlm-linear \
# --base_model internlm \
# --dataset data/fingpt-sentiment-train \
# --max_length 512 \
# --batch_size 4 \
# --learning_rate 1e-4 \
# --num_epochs 8
# deepspeed train_lora.py \
# --run_name sentiment-llama2-linear \
# --base_model llama2 \
# --dataset data/fingpt-sentiment-train \
# --max_length 512 \
# --batch_size 4 \
# --learning_rate 1e-4 \
# --num_epochs 8
# deepspeed train_lora.py \
# --run_name sentiment-chatglm2-linear \
# --base_model chatglm2 \
# --dataset data/fingpt-sentiment-train \
# --max_length 512 \
# --batch_size 4 \
# --learning_rate 1e-4 \
# --num_epochs 8
# deepspeed train_lora.py \
# --run_name sentiment-falcon-linear \
# --base_model falcon \
# --dataset data/fingpt-sentiment-train \
# --max_length 512 \
# --batch_size 4 \
# --learning_rate 1e-4 \
# --num_epochs 8
# deepspeed train_lora.py \
# --run_name sentiment-qwen-linear \
# --base_model qwen \
# --dataset data/fingpt-sentiment-train \
# --max_length 512 \
# --batch_size 4 \
# --learning_rate 1e-4 \
# --num_epochs 8
# deepspeed train_lora.py \
# --run_name sentiment-mpt-linear \
# --base_model mpt \
# --dataset data/fingpt-sentiment-train \
# --max_length 512 \
# --batch_size 4 \
# --learning_rate 1e-4 \
# --num_epochs 8
# deepspeed train_lora.py \
# --run_name sentiment-bloom-linear \
# --base_model bloom \
# --dataset data/fingpt-sentiment-train \
# --max_length 512 \
# --batch_size 4 \
# --learning_rate 1e-4 \
# --num_epochs 8

View File

@@ -1,151 +0,0 @@
from transformers.integrations import TensorBoardCallback
from transformers import AutoTokenizer, AutoModel, AutoModelForCausalLM
from transformers import TrainingArguments, Trainer, DataCollatorForSeq2Seq
from transformers.trainer import TRAINING_ARGS_NAME
from torch.utils.tensorboard import SummaryWriter
import datasets
import torch
import os
import sys
import wandb
import argparse
from datetime import datetime
from functools import partial
from utils import *
from glob import glob
# LoRA
from peft import (
TaskType,
LoraConfig,
PeftModel,
get_peft_model,
get_peft_model_state_dict,
prepare_model_for_int8_training,
set_peft_model_state_dict,
)
os.environ['WANDB_API_KEY'] = 'ecf1e5e4f47441d46822d38a3249d62e8fc94db4'
os.environ['WANDB_PROJECT'] = 'fingpt-omni'
def main(args):
model_name = parse_model_name(args.base_model)
# load model
model = AutoModelForCausalLM.from_pretrained(
model_name,
# load_in_8bit=True,
# device_map="auto",
trust_remote_code=True
)
if args.local_rank == 0:
print(model)
tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True)
if args.base_model != 'mpt':
tokenizer.padding_side = "left"
if args.base_model == 'qwen':
tokenizer.eos_token_id = tokenizer.convert_tokens_to_ids('<|endoftext|>')
tokenizer.pad_token_id = tokenizer.convert_tokens_to_ids('<|extra_0|>')
if not tokenizer.pad_token or tokenizer.pad_token_id == tokenizer.eos_token_id:
tokenizer.add_special_tokens({'pad_token': '[PAD]'})
model.resize_token_embeddings(len(tokenizer))
dataset_list = load_dataset(args.test_dataset)
dataset_test = datasets.concatenate_datasets([d['test'] for d in dataset_list])
print(dataset_test[0])
dataset_test = dataset_test.map(partial(tokenize, args, tokenizer))
print('original dataset length: ', len(dataset_test))
dataset_test = dataset_test.filter(lambda x: not x['exceed_max_length'])
print('filtered dataset length: ', len(dataset_test))
dataset_test = dataset_test.remove_columns(['instruction', 'input', 'output', 'exceed_max_length'])
print(dataset_test[0])
# config
# deepspeed_config = './config_newnew.json'
# deepspeed_config = './config_new.json'
# deepspeed_config = './config.json'
current_time = datetime.now()
formatted_time = current_time.strftime('%Y%m%d%H%M')
training_args = TrainingArguments(
output_dir=f'finetuned_models/{args.run_name}_{formatted_time}', # 保存位置
logging_steps=args.log_interval,
num_train_epochs=args.num_epochs,
per_device_train_batch_size=args.batch_size,
per_device_eval_batch_size=args.batch_size,
gradient_accumulation_steps=8,
dataloader_num_workers=args.num_workers,
learning_rate=args.learning_rate,
warmup_ratio=args.warmup_ratio,
lr_scheduler_type=args.scheduler,
save_steps=0.1,
eval_steps=0.1,
fp16=True,
# fp16_full_eval=True,
# deepspeed=args.ds_config,
evaluation_strategy=args.evaluation_strategy,
remove_unused_columns=False,
report_to='wandb',
run_name=args.run_name
)
if not args.base_model == 'mpt':
model.gradient_checkpointing_enable()
model.enable_input_require_grads()
model.is_parallelizable = True
model.model_parallel = True
ckpts = glob(f'finetuned_models/{args.peft_model}/checkpoint-*')
for ckpt in ckpts:
model_ckpt = PeftModel.from_pretrained(model, ckpt)
trainer = Trainer(
model=model_ckpt,
args=training_args,
train_dataset=dataset_test,
eval_dataset=dataset_test,
data_collator=DataCollatorForSeq2Seq(
tokenizer, padding=True,
return_tensors="pt"
),
)
# if torch.__version__ >= "2" and sys.platform != "win32":
# model = torch.compile(model)
torch.cuda.empty_cache()
metrics = trainer.evaluate()
if args.local_rank == 0:
print(ckpt, metrics)
if __name__ == "__main__":
parser = argparse.ArgumentParser()
parser.add_argument("--local_rank", default=0, type=int)
parser.add_argument("--run_name", default='local-test', type=str)
parser.add_argument("--test_dataset", required=True, type=str)
parser.add_argument("--peft_model", required=True, type=str)
parser.add_argument("--dataset", type=str)
parser.add_argument("--base_model", required=True, type=str, choices=['chatglm2', 'llama2', 'falcon', 'internlm', 'qwen', 'mpt', 'bloom'])
parser.add_argument("--max_length", default=512, type=int)
parser.add_argument("--batch_size", default=4, type=int, help="The train batch size per device")
parser.add_argument("--learning_rate", default=1e-4, type=float, help="The learning rate")
parser.add_argument("--num_epochs", default=8, type=float, help="The training epochs")
parser.add_argument("--num_workers", default=8, type=int, help="dataloader workers")
parser.add_argument("--log_interval", default=100, type=int)
parser.add_argument("--warmup_ratio", default=0.05, type=float)
parser.add_argument("--ds_config", default='./config_new.json', type=str)
parser.add_argument("--scheduler", default='linear', type=str)
parser.add_argument("--instruct_template", default='default')
parser.add_argument("--evaluation_strategy", default='steps', type=str)
args = parser.parse_args()
wandb.login()
main(args)

View File

@@ -30,7 +30,7 @@ os.environ['WANDB_PROJECT'] = 'fingpt-benchmark'
def main(args):
model_name = parse_model_name(args.base_model)
model_name = parse_model_name(args.base_model, args.from_remote)
# load model
model = AutoModelForCausalLM.from_pretrained(
@@ -53,12 +53,12 @@ def main(args):
model.resize_token_embeddings(len(tokenizer))
# load data
dataset_list = load_dataset(args.dataset)
dataset_list = load_dataset(args.dataset, args.from_remote)
dataset_train = datasets.concatenate_datasets([d['train'] for d in dataset_list]).shuffle(seed=42)
if args.test_dataset:
dataset_list = load_dataset(args.test_dataset)
dataset_list = load_dataset(args.test_dataset, args.from_remote)
dataset_test = datasets.concatenate_datasets([d['test'] for d in dataset_list])
@@ -166,6 +166,7 @@ if __name__ == "__main__":
parser.add_argument("--instruct_template", default='default')
parser.add_argument("--evaluation_strategy", default='steps', type=str)
parser.add_argument("--eval_steps", default=0.1, type=float)
parser.add_argument("--from_remote", default=False, type=bool)
args = parser.parse_args()
wandb.login()

View File

@@ -70,45 +70,36 @@ def tokenize(args, tokenizer, feature):
}
def parse_model_name(name):
def parse_model_name(name, from_remote=False):
if name == 'chatglm2':
# return 'THUDM/chatglm2-6b'
return 'base_models/chatglm2-6b'
return 'THUDM/chatglm2-6b' if from_remote else 'base_models/chatglm2-6b'
elif name == 'llama2':
# return 'meta-llama/Llama-2-7b-hf'
# return 'NousResearch/Llama-2-7b-hf'
return 'base_models/Llama-2-7b-hf'
# return 'base_models/Llama-2-7b-hf-nous'
return 'meta-llama/Llama-2-7b-hf' if from_remote else 'base_models/Llama-2-7b-hf'
# return 'NousResearch/Llama-2-7b-hf' if from_remote else 'base_models/Llama-2-7b-hf-nous'
elif name == 'falcon':
# return 'tiiuae/falcon-7b'
return 'base_models/falcon-7b'
return 'tiiuae/falcon-7b' if from_remote else 'base_models/falcon-7b'
elif name == 'internlm':
# return 'internlm/internlm-7b'
return 'base_models/internlm-7b'
return 'internlm/internlm-7b' if from_remote else 'base_models/internlm-7b'
elif name == 'qwen':
# return 'Qwen/Qwen-7B'
return 'base_models/Qwen-7B'
return 'Qwen/Qwen-7B' if from_remote else 'base_models/Qwen-7B'
elif name == 'mpt':
# return 'mosaicml/mpt-7b'
# return 'base_models/mpt-7b'
# return 'cekal/mpt-7b-peft-compatible'
return 'base_models/mpt-7b-peft-compatible'
return 'cekal/mpt-7b-peft-compatible' if from_remote else 'base_models/mpt-7b-peft-compatible'
# return 'mosaicml/mpt-7b' if from_remote else 'base_models/mpt-7b'
elif name == 'bloom':
# return 'bigscience/bloom-7b1'
return 'base_models/bloom-7b1'
return 'bigscience/bloom-7b1' if from_remote else 'base_models/bloom-7b1'
else:
raise ValueError(f"Undefined base model {name}")
def load_dataset(names):
def load_dataset(names, from_remote=False):
dataset_names = [d for d in names.split(',')]
dataset_list = []
for name in dataset_names:
rep = 1
if not os.path.exists(name):
rep = int(name.split('*')[1]) if '*' in name else 1
name = 'data/fingpt-' + name.split('*')[0]
name = ('FinGPT/fingpt-' if from_remote else 'data/fingpt-') + name.split('*')[0]
tmp_dataset = datasets.load_from_disk(name)
if 'test' not in tmp_dataset:
tmp_dataset = tmp_dataset.train_test_split(0.2, shuffle=True, seed=42)