73 lines
1.6 KiB
YAML
73 lines
1.6 KiB
YAML
# This file is used by the training script in train.ipynb. You can read more about
|
|
# the format and see more examples at https://github.com/OpenAccess-AI-Collective/axolotl.
|
|
# One of the parameters you might want to play around with is `num_epochs`: if you have a
|
|
# smaller dataset size, making that large can have good results.
|
|
|
|
base_model: meta-llama/Llama-2-7b-hf
|
|
base_model_config: meta-llama/Llama-2-7b-hf
|
|
model_type: LlamaForCausalLM
|
|
tokenizer_type: LlamaTokenizer
|
|
is_llama_derived_model: true
|
|
|
|
load_in_8bit: true
|
|
load_in_4bit: false
|
|
strict: false
|
|
|
|
datasets:
|
|
- path: ./data/train.jsonl
|
|
type: alpaca_instruct.load_no_prompt
|
|
dataset_prepared_path: ./data/last_run_prepared
|
|
val_set_size: 0.05
|
|
output_dir: ./models/run1
|
|
|
|
sequence_len: 4096
|
|
sample_packing: true
|
|
|
|
adapter: lora
|
|
lora_model_dir:
|
|
lora_r: 32
|
|
lora_alpha: 16
|
|
lora_dropout: 0.05
|
|
lora_target_linear: true
|
|
lora_fan_in_fan_out:
|
|
|
|
# This will report stats from your training run to https://wandb.ai/. If you don't want to create a wandb account you can comment this section out.
|
|
wandb_project: classify-recipes
|
|
wandb_entity:
|
|
wandb_watch:
|
|
wandb_run_id: run1
|
|
wandb_log_model:
|
|
|
|
gradient_accumulation_steps: 4
|
|
micro_batch_size: 2
|
|
num_epochs: 5
|
|
optimizer: adamw_bnb_8bit
|
|
lr_scheduler: cosine
|
|
learning_rate: 0.0002
|
|
|
|
train_on_inputs: false
|
|
group_by_length: false
|
|
bf16: true
|
|
fp16: false
|
|
tf32: false
|
|
|
|
gradient_checkpointing: true
|
|
early_stopping_patience:
|
|
resume_from_checkpoint:
|
|
local_rank:
|
|
logging_steps: 1
|
|
xformers_attention:
|
|
flash_attention: true
|
|
|
|
warmup_steps: 10
|
|
eval_steps: 20
|
|
save_steps: 60
|
|
debug:
|
|
deepspeed:
|
|
weight_decay: 0.0
|
|
fsdp:
|
|
fsdp_config:
|
|
special_tokens:
|
|
bos_token: "<s>"
|
|
eos_token: "</s>"
|
|
unk_token: "<unk>" |