| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 3.0, | |
| "global_step": 5982, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 6.163875084772396e-05, | |
| "loss": 1.9635, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 5.6040317528221326e-05, | |
| "loss": 1.2706, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 5.0441884208718695e-05, | |
| "loss": 1.1903, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 4.485464775585507e-05, | |
| "loss": 1.1229, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "learning_rate": 3.925621443635244e-05, | |
| "loss": 0.8371, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "learning_rate": 3.365778111684982e-05, | |
| "loss": 0.8272, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "learning_rate": 2.8059347797347183e-05, | |
| "loss": 0.7989, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 2.01, | |
| "learning_rate": 2.2460914477844552e-05, | |
| "loss": 0.7957, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 2.26, | |
| "learning_rate": 1.686248115834192e-05, | |
| "loss": 0.5555, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 2.51, | |
| "learning_rate": 1.1264047838839292e-05, | |
| "loss": 0.5526, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 2.76, | |
| "learning_rate": 5.676811385975667e-06, | |
| "loss": 0.5383, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "step": 5982, | |
| "total_flos": 57468648947712.0, | |
| "train_loss": 0.9183043668358591, | |
| "train_runtime": 896.3057, | |
| "train_samples_per_second": 293.585, | |
| "train_steps_per_second": 6.674 | |
| } | |
| ], | |
| "max_steps": 5982, | |
| "num_train_epochs": 3, | |
| "total_flos": 57468648947712.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |