| { | |
| "best_metric": 1.0013060569763184, | |
| "best_model_checkpoint": "bygpt5_quatags_con/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": 1.2085, | |
| "step": 15866 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 1.0804483890533447, | |
| "eval_runtime": 375.4034, | |
| "eval_samples_per_second": 75.133, | |
| "eval_steps_per_second": 9.393, | |
| "step": 15866 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 3.7044371705883534e-05, | |
| "loss": 1.0806, | |
| "step": 31732 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 1.0416626930236816, | |
| "eval_runtime": 375.8397, | |
| "eval_samples_per_second": 75.045, | |
| "eval_steps_per_second": 9.382, | |
| "step": 31732 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 3.2828209599601426e-05, | |
| "loss": 1.0431, | |
| "step": 47598 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 1.0254769325256348, | |
| "eval_runtime": 375.5399, | |
| "eval_samples_per_second": 75.105, | |
| "eval_steps_per_second": 9.389, | |
| "step": 47598 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "learning_rate": 2.7278145783201285e-05, | |
| "loss": 1.0179, | |
| "step": 63464 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_loss": 1.0140334367752075, | |
| "eval_runtime": 374.8271, | |
| "eval_samples_per_second": 75.248, | |
| "eval_steps_per_second": 9.407, | |
| "step": 63464 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "learning_rate": 2.0971286481716286e-05, | |
| "loss": 0.9988, | |
| "step": 79330 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_loss": 1.0083739757537842, | |
| "eval_runtime": 374.1706, | |
| "eval_samples_per_second": 75.38, | |
| "eval_steps_per_second": 9.424, | |
| "step": 79330 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "learning_rate": 1.4563430958668448e-05, | |
| "loss": 0.984, | |
| "step": 95196 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_loss": 1.0033071041107178, | |
| "eval_runtime": 373.5069, | |
| "eval_samples_per_second": 75.514, | |
| "eval_steps_per_second": 9.44, | |
| "step": 95196 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "learning_rate": 8.720880257396538e-06, | |
| "loss": 0.9729, | |
| "step": 111062 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_loss": 1.0022804737091064, | |
| "eval_runtime": 373.5585, | |
| "eval_samples_per_second": 75.504, | |
| "eval_steps_per_second": 9.439, | |
| "step": 111062 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "learning_rate": 4.05115394728147e-06, | |
| "loss": 0.9651, | |
| "step": 126928 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_loss": 1.0013060569763184, | |
| "eval_runtime": 373.9662, | |
| "eval_samples_per_second": 75.421, | |
| "eval_steps_per_second": 9.429, | |
| "step": 126928 | |
| } | |
| ], | |
| "max_steps": 158660, | |
| "num_train_epochs": 10, | |
| "total_flos": 3.61085560823808e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |