| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.9998394949440907, | |
| "eval_steps": 500, | |
| "global_step": 3504, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 8.573059360730594e-06, | |
| "loss": 0.2664, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 7.146118721461188e-06, | |
| "loss": 0.1606, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 5.719178082191781e-06, | |
| "loss": 0.1463, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 4.292237442922374e-06, | |
| "loss": 0.1354, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 2.8652968036529682e-06, | |
| "loss": 0.1274, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 1.4383561643835616e-06, | |
| "loss": 0.1246, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 1.1415525114155251e-08, | |
| "loss": 0.1213, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "step": 3504, | |
| "total_flos": 1.7775025975647528e+16, | |
| "train_loss": 0.15453521883514917, | |
| "train_runtime": 3360.3852, | |
| "train_samples_per_second": 33.373, | |
| "train_steps_per_second": 1.043 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 3504, | |
| "num_train_epochs": 1, | |
| "save_steps": 1000, | |
| "total_flos": 1.7775025975647528e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |