| { | |
| "best_metric": 1.4305617809295654, | |
| "best_model_checkpoint": "./results/checkpoint-2327", | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 2327, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.21486892995272883, | |
| "grad_norm": 1.8023662567138672, | |
| "learning_rate": 4.641885116745452e-05, | |
| "loss": 1.8148, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.42973785990545765, | |
| "grad_norm": 1.5604274272918701, | |
| "learning_rate": 4.283770233490904e-05, | |
| "loss": 1.7135, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.6446067898581865, | |
| "grad_norm": 1.7446964979171753, | |
| "learning_rate": 3.9256553502363556e-05, | |
| "loss": 1.6655, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.8594757198109153, | |
| "grad_norm": 1.6676881313323975, | |
| "learning_rate": 3.567540466981808e-05, | |
| "loss": 1.6373, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 1.4305617809295654, | |
| "eval_runtime": 13.1412, | |
| "eval_samples_per_second": 356.055, | |
| "eval_steps_per_second": 2.816, | |
| "step": 2327 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 6981, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 2, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 5047449588596736.0, | |
| "train_batch_size": 128, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |