| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 4977, | |
| "is_hyper_param_search": true, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.10046212577858148, | |
| "grad_norm": 3.10841703414917, | |
| "learning_rate": 1.883778579223417e-05, | |
| "loss": 0.3172, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.20092425155716295, | |
| "grad_norm": 4.298633575439453, | |
| "learning_rate": 1.78414992578448e-05, | |
| "loss": 0.1925, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.3013863773357444, | |
| "grad_norm": 3.002183198928833, | |
| "learning_rate": 1.6845212723455437e-05, | |
| "loss": 0.1792, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.4018485031143259, | |
| "grad_norm": 5.602917671203613, | |
| "learning_rate": 1.5848926189066066e-05, | |
| "loss": 0.174, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.5023106288929073, | |
| "grad_norm": 4.334236145019531, | |
| "learning_rate": 1.4852639654676699e-05, | |
| "loss": 0.157, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.6027727546714888, | |
| "grad_norm": 6.822575092315674, | |
| "learning_rate": 1.385635312028733e-05, | |
| "loss": 0.1529, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.7032348804500703, | |
| "grad_norm": 3.9460644721984863, | |
| "learning_rate": 1.2860066585897963e-05, | |
| "loss": 0.1408, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.8036970062286518, | |
| "grad_norm": 15.131864547729492, | |
| "learning_rate": 1.1863780051508595e-05, | |
| "loss": 0.1321, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.9041591320072333, | |
| "grad_norm": 11.002291679382324, | |
| "learning_rate": 1.0867493517119226e-05, | |
| "loss": 0.1378, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.9573226552157906, | |
| "eval_f1": 0.8167489442693154, | |
| "eval_loss": 0.12773554027080536, | |
| "eval_precision": 0.7712873511570434, | |
| "eval_recall": 0.8679054481102263, | |
| "eval_runtime": 22.6145, | |
| "eval_samples_per_second": 188.64, | |
| "eval_steps_per_second": 23.613, | |
| "step": 4977 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 9954, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 532506033294048.0, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": { | |
| "learning_rate": 1.983407232662354e-05, | |
| "num_train_epochs": 2, | |
| "per_device_train_batch_size": 4, | |
| "seed": 40 | |
| } | |
| } | |