| { | |
| "best_metric": 0.0001521383092040196, | |
| "best_model_checkpoint": "/opt/ml/model/checkpoint-4627", | |
| "epoch": 1.0, | |
| "global_step": 4627, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 2.976e-05, | |
| "loss": 3.0635, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 2.9674896220231594e-05, | |
| "loss": 0.1023, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 2.9347170635787637e-05, | |
| "loss": 0.0253, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 2.9019445051343676e-05, | |
| "loss": 0.012, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 2.8691719466899716e-05, | |
| "loss": 0.007, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 2.8363993882455756e-05, | |
| "loss": 0.0049, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 2.80362682980118e-05, | |
| "loss": 0.0042, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 2.770854271356784e-05, | |
| "loss": 0.0034, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 2.738081712912388e-05, | |
| "loss": 0.0027, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 0.0001521383092040196, | |
| "eval_rouge2_fmeasure": 0.0001, | |
| "eval_rouge2_precision": 0.0001, | |
| "eval_rouge2_recall": 0.0002, | |
| "eval_runtime": 1140.1653, | |
| "eval_samples_per_second": 5.646, | |
| "eval_steps_per_second": 0.706, | |
| "step": 4627 | |
| } | |
| ], | |
| "max_steps": 46270, | |
| "num_train_epochs": 10, | |
| "total_flos": 1.46662238093616e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |