| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 3.0, | |
| "global_step": 12918, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 4.8064715900294164e-05, | |
| "loss": 0.1967, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 4.612943180058833e-05, | |
| "loss": 0.0684, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 4.4194147700882494e-05, | |
| "loss": 0.0782, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 4.2258863601176655e-05, | |
| "loss": 0.0436, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 4.032357950147082e-05, | |
| "loss": 0.0573, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 3.838829540176498e-05, | |
| "loss": 0.0549, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 3.645301130205914e-05, | |
| "loss": 0.0573, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 3.451772720235331e-05, | |
| "loss": 0.0545, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "learning_rate": 3.258244310264747e-05, | |
| "loss": 0.0422, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "learning_rate": 3.064715900294163e-05, | |
| "loss": 0.0339, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "learning_rate": 2.8711874903235797e-05, | |
| "loss": 0.0285, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "learning_rate": 2.677659080352996e-05, | |
| "loss": 0.0311, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 1.51, | |
| "learning_rate": 2.4841306703824123e-05, | |
| "loss": 0.0276, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 1.63, | |
| "learning_rate": 2.2906022604118285e-05, | |
| "loss": 0.0317, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 1.74, | |
| "learning_rate": 2.097073850441245e-05, | |
| "loss": 0.0248, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "learning_rate": 1.903545440470661e-05, | |
| "loss": 0.0291, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 1.97, | |
| "learning_rate": 1.7100170305000776e-05, | |
| "loss": 0.0303, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 2.09, | |
| "learning_rate": 1.5164886205294938e-05, | |
| "loss": 0.0298, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 2.21, | |
| "learning_rate": 1.3229602105589101e-05, | |
| "loss": 0.0149, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 2.32, | |
| "learning_rate": 1.1294318005883264e-05, | |
| "loss": 0.0203, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 2.44, | |
| "learning_rate": 9.359033906177428e-06, | |
| "loss": 0.0143, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 2.55, | |
| "learning_rate": 7.42374980647159e-06, | |
| "loss": 0.0155, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 2.67, | |
| "learning_rate": 5.488465706765753e-06, | |
| "loss": 0.0178, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 2.79, | |
| "learning_rate": 3.5531816070599166e-06, | |
| "loss": 0.0146, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 2.9, | |
| "learning_rate": 1.6178975073540798e-06, | |
| "loss": 0.0229, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "step": 12918, | |
| "total_flos": 999930331972800.0, | |
| "train_loss": 0.04092990191179563, | |
| "train_runtime": 1783.3593, | |
| "train_samples_per_second": 21.728, | |
| "train_steps_per_second": 7.244 | |
| } | |
| ], | |
| "max_steps": 12918, | |
| "num_train_epochs": 3, | |
| "total_flos": 999930331972800.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |