| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 4.8997772828507795, | |
| "global_step": 11000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 1.910913140311804e-05, | |
| "loss": 0.0349, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 1.8218262806236084e-05, | |
| "loss": 0.004, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 1.7327394209354123e-05, | |
| "loss": 0.0001, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 1.643652561247216e-05, | |
| "loss": 0.0037, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "learning_rate": 1.5545657015590202e-05, | |
| "loss": 0.0, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "learning_rate": 1.4654788418708241e-05, | |
| "loss": 0.0006, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "learning_rate": 1.3763919821826281e-05, | |
| "loss": 0.0016, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 1.78, | |
| "learning_rate": 1.2873051224944322e-05, | |
| "loss": 0.001, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 1.1982182628062361e-05, | |
| "loss": 0.0, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 2.23, | |
| "learning_rate": 1.1091314031180403e-05, | |
| "loss": 0.0012, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 2.45, | |
| "learning_rate": 1.0200445434298442e-05, | |
| "loss": 0.0, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 2.67, | |
| "learning_rate": 9.309576837416481e-06, | |
| "loss": 0.0, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 2.9, | |
| "learning_rate": 8.418708240534522e-06, | |
| "loss": 0.0, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 3.12, | |
| "learning_rate": 7.527839643652561e-06, | |
| "loss": 0.0, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 3.34, | |
| "learning_rate": 6.636971046770601e-06, | |
| "loss": 0.0, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 3.56, | |
| "learning_rate": 5.7461024498886416e-06, | |
| "loss": 0.0, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 3.79, | |
| "learning_rate": 4.855233853006682e-06, | |
| "loss": 0.0013, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 4.01, | |
| "learning_rate": 3.964365256124722e-06, | |
| "loss": 0.0, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 4.23, | |
| "learning_rate": 3.073496659242762e-06, | |
| "loss": 0.0, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 4.45, | |
| "learning_rate": 2.182628062360802e-06, | |
| "loss": 0.0012, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 4.68, | |
| "learning_rate": 1.291759465478842e-06, | |
| "loss": 0.0, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 4.9, | |
| "learning_rate": 4.00890868596882e-07, | |
| "loss": 0.0, | |
| "step": 11000 | |
| } | |
| ], | |
| "max_steps": 11225, | |
| "num_train_epochs": 5, | |
| "total_flos": 2.3312738788371456e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |