| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 6.0, | |
| "eval_steps": 500, | |
| "global_step": 1650, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.9090909090909091, | |
| "grad_norm": 0.6453994512557983, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8517, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 1.8181818181818183, | |
| "grad_norm": 0.8035799860954285, | |
| "learning_rate": 0.0002, | |
| "loss": 0.4305, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 2.7272727272727275, | |
| "grad_norm": 1.0066492557525635, | |
| "learning_rate": 0.0002, | |
| "loss": 0.2833, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 3.6363636363636362, | |
| "grad_norm": 0.6216712594032288, | |
| "learning_rate": 0.0002, | |
| "loss": 0.2105, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 4.545454545454545, | |
| "grad_norm": 0.6158052086830139, | |
| "learning_rate": 0.0002, | |
| "loss": 0.1809, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 5.454545454545454, | |
| "grad_norm": 0.6878110766410828, | |
| "learning_rate": 0.0002, | |
| "loss": 0.1632, | |
| "step": 1500 | |
| } | |
| ], | |
| "logging_steps": 250, | |
| "max_steps": 1650, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 6, | |
| "save_steps": 250, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.324891664420864e+16, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |