| base_model: ./mistralai_Mistral-Small-24B-Base-2501/ | |
| # optionally might have model_type or tokenizer_type | |
| model_type: AutoModelForCausalLM | |
| tokenizer_type: AutoTokenizer | |
| # Automatically upload checkpoint and final model to HF | |
| # hub_model_id: username/custom_model_name | |
| trust_remote_code: true | |
| wandb_project: SmallMistral-Reflex2 | |
| wandb_entity: | |
| wandb_watch: | |
| wandb_name: | |
| wandb_log_model: | |
| load_in_8bit: false | |
| load_in_4bit: false | |
| strict: false | |
| model_config: | |
| output_router_logits: true | |
| chat_template: tokenizer_default | |
| datasets: | |
| - path: Undi95/R1-RP-ShareGPT3 | |
| type: chat_template | |
| chat_template: tokenizer_default | |
| field_messages: conversations | |
| message_field_role: from | |
| message_field_content: value | |
| roles: | |
| user: ["human", "user"] | |
| assistant: ["gpt", "assistant"] | |
| system: ["system"] | |
| tool: ["tool"] | |
| dataset_prepared_path: last_run_prepared | |
| shuffle_merged_datasets: true | |
| val_set_size: 0.05 | |
| output_dir: ./out | |
| sequence_len: 4096 | |
| sample_packing: true | |
| pad_to_sequence_len: true | |
| gradient_accumulation_steps: 1 | |
| micro_batch_size: 1 | |
| num_epochs: 2 | |
| optimizer: adamw_bnb_8bit | |
| lr_scheduler: cosine | |
| learning_rate: 0.0000025 | |
| train_on_inputs: false | |
| group_by_length: false | |
| bf16: auto | |
| fp16: | |
| tf32: false | |
| gradient_checkpointing: unsloth | |
| early_stopping_patience: | |
| resume_from_checkpoint: | |
| local_rank: | |
| logging_steps: 1 | |
| xformers_attention: | |
| flash_attention: true | |
| save_total_limit: 6 | |
| saves_per_epoch: 2 | |
| save_steps: | |
| debug: | |
| deepspeed: | |
| weight_decay: 0.0 | |
| fsdp: | |
| fsdp_config: | |
| save_safetensors: true |