| base_model: JackFram/llama-68m | |
| model_type: LlamaForCausalLM | |
| tokenizer_type: AutoTokenizer | |
| load_in_8bit: false | |
| load_in_4bit: false | |
| strict: false | |
| datasets: | |
| - path: /data/data/final_set_cleaned/train/ | |
| type: sharegpt | |
| conversation: chatml | |
| - path: /data/data/map_coig_cqia.jsonl | |
| type: sharegpt | |
| conversation: chatml | |
| - path: /data/data/ruozhiba.jsonl | |
| type: sharegpt | |
| conversation: chatml | |
| dataset_prepared_path: last_run_prepared | |
| val_set_size: 0 | |
| output_dir: ./out | |
| sequence_len: 4096 | |
| sample_packing: true | |
| pad_to_sequence_len: true | |
| wandb_project: | |
| wandb_entity: | |
| wandb_watch: | |
| wandb_name: | |
| wandb_log_model: | |
| gradient_accumulation_steps: 8 | |
| micro_batch_size: 4 | |
| num_epochs: 2 | |
| optimizer: paged_adamw_8bit | |
| lr_scheduler: cosine | |
| learning_rate: 2e-5 | |
| 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: | |
| logging_steps: 1 | |
| xformers_attention: | |
| flash_attention: true | |
| warmup_steps: 100 | |
| evals_per_epoch: 0 | |
| eval_table_size: | |
| saves_per_epoch: 4 | |
| debug: | |
| deepspeed: deepspeed/zero2.json | |
| weight_decay: 0.0 | |
| fsdp: | |
| fsdp_config: | |
| default_system_message: "You are a helpful assistant." | |
| special_tokens: | |
| eos_token: "<|im_end|>" | |
| pad_token: "<|end_of_text|>" | |
| tokens: | |
| - "<|im_start|>" | |
| - "<|im_end|>" | |