| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.988361119849009, | |
| "global_step": 9500, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 2.8427178357974207e-05, | |
| "loss": 1.375, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 2.6854356715948413e-05, | |
| "loss": 0.8081, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 2.5281535073922616e-05, | |
| "loss": 0.6701, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 2.3708713431896822e-05, | |
| "loss": 0.6539, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 2.213589178987103e-05, | |
| "loss": 0.6176, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 2.0563070147845238e-05, | |
| "loss": 0.5754, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "learning_rate": 1.899024850581944e-05, | |
| "loss": 0.4299, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "learning_rate": 1.7417426863793647e-05, | |
| "loss": 0.3507, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 1.42, | |
| "learning_rate": 1.5844605221767853e-05, | |
| "loss": 0.3356, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 1.57, | |
| "learning_rate": 1.4271783579742058e-05, | |
| "loss": 0.3311, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 1.73, | |
| "learning_rate": 1.2698961937716264e-05, | |
| "loss": 0.3037, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 1.89, | |
| "learning_rate": 1.1126140295690468e-05, | |
| "loss": 0.2988, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 2.04, | |
| "learning_rate": 9.553318653664675e-06, | |
| "loss": 0.247, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 2.2, | |
| "learning_rate": 7.980497011638881e-06, | |
| "loss": 0.1414, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 2.36, | |
| "learning_rate": 6.407675369613086e-06, | |
| "loss": 0.1402, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 2.52, | |
| "learning_rate": 4.834853727587292e-06, | |
| "loss": 0.1443, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 2.67, | |
| "learning_rate": 3.2620320855614974e-06, | |
| "loss": 0.1387, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 2.83, | |
| "learning_rate": 1.6892104435357032e-06, | |
| "loss": 0.1413, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 2.99, | |
| "learning_rate": 1.1638880150990878e-07, | |
| "loss": 0.1322, | |
| "step": 9500 | |
| } | |
| ], | |
| "max_steps": 9537, | |
| "num_train_epochs": 3, | |
| "total_flos": 2.233891297525248e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |