| base_model: meta-llama/Meta-Llama-3-8B-Instruct | |
| model_type: AutoModelForCausalLM | |
| tokenizer_type: AutoTokenizer | |
| load_in_8bit: false | |
| load_in_4bit: false | |
| strict: false | |
| datasets: | |
| - path: /workspace/axolotl/mathvi/input_output_meta_llama_3_8b_instruct-00000-of-00001.parquet | |
| type: input_output | |
| dataset_prepared_path: | |
| val_set_size: 0.05 | |
| eval_sample_packing: false | |
| output_dir: mathvi/output_model2 | |
| sequence_len: 4096 | |
| sample_packing: false | |
| pad_to_sequence_len: false | |
| adapter: lora | |
| lora_model_dir: | |
| lora_r: 64 | |
| lora_alpha: 32 | |
| lora_dropout: 0.05 | |
| lora_target_linear: true | |
| lora_fan_in_fan_out: | |
| wandb_project: | |
| wandb_entity: | |
| wandb_watch: | |
| wandb_name: | |
| wandb_log_model: | |
| gradient_accumulation_steps: 32 | |
| micro_batch_size: 4 | |
| num_epochs: 3 | |
| optimizer: paged_adamw_32bit | |
| lr_scheduler: cosine | |
| learning_rate: 2e-4 | |
| train_on_inputs: false | |
| group_by_length: false | |
| bf16: auto | |
| fp16: | |
| tf32: false | |
| gradient_checkpointing: false | |
| early_stopping_patience: | |
| resume_from_checkpoint: | |
| local_rank: | |
| logging_steps: 1 | |
| xformers_attention: | |
| flash_attention: true | |
| s2_attention: | |
| loss_watchdog_threshold: 5.0 | |
| loss_watchdog_patience: 3 | |
| warmup_steps: 10 | |
| evals_per_epoch: 10 | |
| eval_table_size: | |
| eval_max_new_tokens: 512 | |
| saves_per_epoch: 2 | |
| save_total_limit: 20 | |
| debug: | |
| deepspeed: | |
| weight_decay: 0.0 | |
| fsdp: | |
| fsdp_config: | |
| special_tokens: | |
| pad_token: <|end_of_text|> | |