| base_model: meta-llama/Llama-3.2-3B | |
| # Automatically upload checkpoint and final model to HF | |
| # hub_model_id: username/custom_model_name | |
| load_in_8bit: false | |
| load_in_4bit: false | |
| strict: false | |
| datasets: | |
| - path: ptllama/acemath_test | |
| type: completion | |
| # pretraining_dataset: | |
| # - name: | |
| # path: ptllama/acemath_test | |
| # split: | |
| # text_column: text # column in dataset with the data, usually `text` | |
| # type: pretrain | |
| # trust_remote_code: | |
| # skip: # number of rows of data to skip over from the beginning | |
| dataset_prepared_path: last_run_prepared | |
| val_set_size: 0.01 | |
| output_dir: ./outputs/out | |
| sequence_len: 4096 | |
| sample_packing: true | |
| pad_to_sequence_len: true | |
| eval_sample_packing: false | |
| wandb_project: axolotl-pretraining | |
| wandb_entity: | |
| wandb_watch: | |
| wandb_name: test-2e4 | |
| wandb_log_model: | |
| gradient_accumulation_steps: 16 | |
| micro_batch_size: 4 | |
| num_epochs: 1 | |
| optimizer: paged_adamw_8bit | |
| lr_scheduler: cosine | |
| learning_rate: 2e-4 | |
| 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_ratio: 0.01 | |
| cosine_min_lr_ratio: 0.1 | |
| cosine_constant_lr_ratio: 0.9 | |
| evals_per_epoch: 2 | |
| eval_table_size: | |
| saves_per_epoch: 1 | |
| debug: | |
| deepspeed: | |
| weight_decay: 0.0 | |
| fsdp: | |
| fsdp_config: | |
| special_tokens: | |
| pad_token: <|end_of_text|> | |