| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.0, | |
| "global_step": 12720, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 2.8820754716981133e-05, | |
| "loss": 4.3332, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 2.7641509433962264e-05, | |
| "loss": 3.1388, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 2.6462264150943396e-05, | |
| "loss": 2.557, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 2.528301886792453e-05, | |
| "loss": 2.2015, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 2.410377358490566e-05, | |
| "loss": 1.9948, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 2.2924528301886795e-05, | |
| "loss": 1.9278, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 2.1745283018867927e-05, | |
| "loss": 1.8199, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 2.0566037735849055e-05, | |
| "loss": 1.7275, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 1.938679245283019e-05, | |
| "loss": 1.6389, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 1.8207547169811322e-05, | |
| "loss": 1.636, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 1.7028301886792454e-05, | |
| "loss": 1.6225, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 1.5849056603773586e-05, | |
| "loss": 1.5949, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "learning_rate": 1.4669811320754717e-05, | |
| "loss": 1.4982, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "learning_rate": 1.349056603773585e-05, | |
| "loss": 1.475, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "learning_rate": 1.2311320754716983e-05, | |
| "loss": 1.4551, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "learning_rate": 1.1132075471698113e-05, | |
| "loss": 1.4413, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "learning_rate": 9.952830188679245e-06, | |
| "loss": 1.4178, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 1.42, | |
| "learning_rate": 8.773584905660376e-06, | |
| "loss": 1.3974, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 1.49, | |
| "learning_rate": 7.59433962264151e-06, | |
| "loss": 1.4176, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 1.57, | |
| "learning_rate": 6.415094339622642e-06, | |
| "loss": 1.4098, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 1.65, | |
| "learning_rate": 5.2358490566037735e-06, | |
| "loss": 1.3751, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 1.73, | |
| "learning_rate": 4.056603773584905e-06, | |
| "loss": 1.3756, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 1.81, | |
| "learning_rate": 2.877358490566038e-06, | |
| "loss": 1.3999, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 1.89, | |
| "learning_rate": 1.69811320754717e-06, | |
| "loss": 1.3809, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 1.97, | |
| "learning_rate": 5.188679245283019e-07, | |
| "loss": 1.3565, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "step": 12720, | |
| "total_flos": 1666807897807872.0, | |
| "train_loss": 1.7758963099065816, | |
| "train_runtime": 1367.5464, | |
| "train_samples_per_second": 111.614, | |
| "train_steps_per_second": 9.301 | |
| } | |
| ], | |
| "max_steps": 12720, | |
| "num_train_epochs": 2, | |
| "total_flos": 1666807897807872.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |