| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 4.992, | |
| "eval_steps": 500, | |
| "global_step": 780, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.64, | |
| "grad_norm": 0.13891594111919403, | |
| "learning_rate": 0.0001798941798941799, | |
| "loss": 1.323, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "grad_norm": 0.23397774994373322, | |
| "learning_rate": 0.00015343915343915345, | |
| "loss": 0.5897, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "grad_norm": 0.23413389921188354, | |
| "learning_rate": 0.00012698412698412698, | |
| "loss": 0.5623, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 2.56, | |
| "grad_norm": 0.2651359736919403, | |
| "learning_rate": 0.00010052910052910055, | |
| "loss": 0.5462, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 3.2, | |
| "grad_norm": 0.28590303659439087, | |
| "learning_rate": 7.407407407407407e-05, | |
| "loss": 0.5365, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 3.84, | |
| "grad_norm": 0.2999708950519562, | |
| "learning_rate": 4.761904761904762e-05, | |
| "loss": 0.5271, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 4.48, | |
| "grad_norm": 0.31423741579055786, | |
| "learning_rate": 2.1164021164021164e-05, | |
| "loss": 0.5206, | |
| "step": 700 | |
| } | |
| ], | |
| "logging_steps": 100, | |
| "max_steps": 780, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 5, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 8.548980461202309e+17, | |
| "train_batch_size": 16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |