{"epoch": 1.0, "global_step": 87, "max_steps": 1740, "logging_steps": 50, "eval_steps": 50, "save_steps": 50, "train_batch_size": 2, "num_train_epochs": 20, "num_input_tokens_seen": 0, "total_flos": 9222053953536000.0, "log_history": [{"loss": 4.3402, "grad_norm": 0.8734406232833862, "learning_rate": 2.9442508710801396e-05, "epoch": 0.5747126436781609, "step": 50}, {"eval_loss": 3.7241973876953125, "eval_runtime": 1.118, "eval_samples_per_second": 8.05, "eval_steps_per_second": 2.683, "epoch": 0.5747126436781609, "step": 50}], "best_metric": 3.7241973876953125, "best_model_checkpoint": "./pf-data-use-unsloth-phi-3.5-simpleschema-thinking-prwp-manual-914-train-20epochs-1738770532/checkpoint-50", "is_local_process_zero": true, "is_world_process_zero": true, "is_hyper_param_search": false, "trial_name": null, "trial_params": null, "stateful_callbacks": {"TrainerControl": {"args": {"should_training_stop": false, "should_epoch_stop": false, "should_save": true, "should_evaluate": false, "should_log": false}, "attributes": {}}}} (Trained with Unsloth)
0022915
verified
| { | |
| "alpha_pattern": {}, | |
| "auto_mapping": null, | |
| "base_model_name_or_path": "unsloth/phi-3.5-mini-instruct-bnb-4bit", | |
| "bias": "none", | |
| "eva_config": null, | |
| "exclude_modules": null, | |
| "fan_in_fan_out": false, | |
| "inference_mode": true, | |
| "init_lora_weights": true, | |
| "layer_replication": null, | |
| "layers_pattern": null, | |
| "layers_to_transform": null, | |
| "loftq_config": {}, | |
| "lora_alpha": 16, | |
| "lora_bias": false, | |
| "lora_dropout": 0, | |
| "megatron_config": null, | |
| "megatron_core": "megatron.core", | |
| "modules_to_save": null, | |
| "peft_type": "LORA", | |
| "r": 16, | |
| "rank_pattern": {}, | |
| "revision": null, | |
| "target_modules": [ | |
| "gate_proj", | |
| "v_proj", | |
| "up_proj", | |
| "o_proj", | |
| "k_proj", | |
| "down_proj", | |
| "q_proj" | |
| ], | |
| "task_type": "CAUSAL_LM", | |
| "use_dora": false, | |
| "use_rslora": false | |
| } |