|
|
|
base_model: NousResearch/Meta-Llama-3-8B |
|
model_type: AutoModelForCausalLM |
|
tokenizer_type: AutoTokenizer |
|
|
|
load_in_8bit: false |
|
load_in_4bit: true |
|
strict: false |
|
|
|
datasets: |
|
- path: 64bits/lima_vicuna_format |
|
|
|
type: sharegpt |
|
conversation: chatml |
|
chat_template: chatml |
|
dataset_prepared_path: lima/data |
|
val_set_size: 0.05 |
|
output_dir: ./llama3-lima-out |
|
|
|
adapter: qlora |
|
lora_model_dir: |
|
|
|
sequence_len: 4096 |
|
sample_packing: true |
|
pad_to_sequence_len: true |
|
eval_sample_packing: false |
|
|
|
lora_r: 32 |
|
lora_alpha: 16 |
|
lora_dropout: 0.05 |
|
lora_target_modules: |
|
lora_target_linear: true |
|
lora_fan_in_fan_out: |
|
lora_modules_to_save: |
|
- embed_tokens |
|
- lm_head |
|
|
|
wandb_project: llama3-lima |
|
wandb_entity: |
|
wandb_watch: |
|
wandb_name: |
|
wandb_log_model: |
|
|
|
gradient_accumulation_steps: 2 |
|
micro_batch_size: 1 |
|
num_epochs: 3 |
|
optimizer: paged_adamw_32bit |
|
lr_scheduler: cosine |
|
learning_rate: 0.0002 |
|
|
|
train_on_inputs: false |
|
group_by_length: false |
|
bf16: auto |
|
fp16: |
|
tf32: false |
|
|
|
gradient_checkpointing: true |
|
gradient_checkpointing_kwargs: |
|
use_reentrant: false |
|
early_stopping_patience: |
|
resume_from_checkpoint: |
|
local_rank: |
|
logging_steps: 2 |
|
xformers_attention: |
|
flash_attention: true |
|
|
|
|
|
warmup_steps: 10 |
|
evals_per_epoch: 4 |
|
eval_table_size: |
|
eval_table_max_new_tokens: |
|
saves_per_epoch: 1 |
|
debug: true |
|
deepspeed: |
|
weight_decay: 0.05 |
|
fsdp: |
|
fsdp_config: |
|
special_tokens: |
|
eos_token: "<|im_end|>" |
|
pad_token: "<|end_of_text|>" |
|
tokens: |
|
- "<|im_start|>" |
|
- "<|im_end|>" |
