| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 9247, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 4.7296420460689956e-05, | |
| "loss": 1.3402, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 4.459284092137991e-05, | |
| "loss": 0.9119, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 4.188926138206986e-05, | |
| "loss": 0.8126, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 3.9185681842759816e-05, | |
| "loss": 0.7416, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 3.648210230344977e-05, | |
| "loss": 0.6728, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 3.3778522764139723e-05, | |
| "loss": 0.6253, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 3.107494322482968e-05, | |
| "loss": 0.569, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 2.837136368551963e-05, | |
| "loss": 0.5355, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 2.5667784146209584e-05, | |
| "loss": 0.4955, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 2.2964204606899537e-05, | |
| "loss": 0.4613, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 2.026062506758949e-05, | |
| "loss": 0.4306, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 1.755704552827944e-05, | |
| "loss": 0.4053, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 1.4853465988969395e-05, | |
| "loss": 0.3821, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 1.214988644965935e-05, | |
| "loss": 0.3572, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 9.446306910349303e-06, | |
| "loss": 0.3274, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 6.742727371039257e-06, | |
| "loss": 0.3131, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 4.03914783172921e-06, | |
| "loss": 0.2879, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 1.335568292419163e-06, | |
| "loss": 0.2808, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "step": 9247, | |
| "total_flos": 7.900925099184e+16, | |
| "train_loss": 0.5455552286053394, | |
| "train_runtime": 25986.0373, | |
| "train_samples_per_second": 22.772, | |
| "train_steps_per_second": 0.356 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 9247, | |
| "num_train_epochs": 1, | |
| "save_steps": 500, | |
| "total_flos": 7.900925099184e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |