| { | |
| "best_metric": 1.0135893821716309, | |
| "best_model_checkpoint": "bygpt5_quatags/base/de/checkpoint-126928", | |
| "epoch": 8.0, | |
| "global_step": 126928, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 3.948822752188864e-05, | |
| "loss": 1.1989, | |
| "step": 15866 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 1.0848549604415894, | |
| "eval_runtime": 372.1518, | |
| "eval_samples_per_second": 75.789, | |
| "eval_steps_per_second": 9.475, | |
| "step": 15866 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 3.7044371705883534e-05, | |
| "loss": 1.0865, | |
| "step": 31732 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 1.0513544082641602, | |
| "eval_runtime": 372.83, | |
| "eval_samples_per_second": 75.651, | |
| "eval_steps_per_second": 9.457, | |
| "step": 31732 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 3.2828209599601426e-05, | |
| "loss": 1.0519, | |
| "step": 47598 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 1.0346773862838745, | |
| "eval_runtime": 372.798, | |
| "eval_samples_per_second": 75.658, | |
| "eval_steps_per_second": 9.458, | |
| "step": 47598 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "learning_rate": 2.7278145783201285e-05, | |
| "loss": 1.0273, | |
| "step": 63464 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_loss": 1.0246155261993408, | |
| "eval_runtime": 372.4011, | |
| "eval_samples_per_second": 75.738, | |
| "eval_steps_per_second": 9.468, | |
| "step": 63464 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "learning_rate": 2.0971286481716286e-05, | |
| "loss": 1.0084, | |
| "step": 79330 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_loss": 1.01944899559021, | |
| "eval_runtime": 371.0717, | |
| "eval_samples_per_second": 76.01, | |
| "eval_steps_per_second": 9.502, | |
| "step": 79330 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "learning_rate": 1.4563430958668448e-05, | |
| "loss": 0.9938, | |
| "step": 95196 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_loss": 1.0151903629302979, | |
| "eval_runtime": 370.7077, | |
| "eval_samples_per_second": 76.084, | |
| "eval_steps_per_second": 9.512, | |
| "step": 95196 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "learning_rate": 8.720880257396538e-06, | |
| "loss": 0.9828, | |
| "step": 111062 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_loss": 1.0147309303283691, | |
| "eval_runtime": 369.733, | |
| "eval_samples_per_second": 76.285, | |
| "eval_steps_per_second": 9.537, | |
| "step": 111062 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "learning_rate": 4.05115394728147e-06, | |
| "loss": 0.9748, | |
| "step": 126928 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_loss": 1.0135893821716309, | |
| "eval_runtime": 369.751, | |
| "eval_samples_per_second": 76.281, | |
| "eval_steps_per_second": 9.536, | |
| "step": 126928 | |
| } | |
| ], | |
| "max_steps": 158660, | |
| "num_train_epochs": 10, | |
| "total_flos": 3.584795444379648e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |