| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 8.856682769726248, | |
| "global_step": 11000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 4.7987117552334945e-05, | |
| "loss": 0.6228, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 4.597423510466989e-05, | |
| "loss": 0.4692, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "learning_rate": 4.396135265700484e-05, | |
| "loss": 0.4092, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 1.61, | |
| "learning_rate": 4.194847020933977e-05, | |
| "loss": 0.3743, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 2.01, | |
| "learning_rate": 3.993558776167472e-05, | |
| "loss": 0.3588, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 2.42, | |
| "learning_rate": 3.7922705314009665e-05, | |
| "loss": 0.3095, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 2.82, | |
| "learning_rate": 3.590982286634461e-05, | |
| "loss": 0.3107, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 3.22, | |
| "learning_rate": 3.389694041867955e-05, | |
| "loss": 0.2899, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 3.62, | |
| "learning_rate": 3.188405797101449e-05, | |
| "loss": 0.2695, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 4.03, | |
| "learning_rate": 2.9871175523349438e-05, | |
| "loss": 0.2674, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 4.43, | |
| "learning_rate": 2.7858293075684384e-05, | |
| "loss": 0.2422, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 4.83, | |
| "learning_rate": 2.5845410628019323e-05, | |
| "loss": 0.2407, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 5.23, | |
| "learning_rate": 2.383252818035427e-05, | |
| "loss": 0.2228, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 5.64, | |
| "learning_rate": 2.1819645732689212e-05, | |
| "loss": 0.2172, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 6.04, | |
| "learning_rate": 1.9806763285024154e-05, | |
| "loss": 0.2167, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 6.44, | |
| "learning_rate": 1.77938808373591e-05, | |
| "loss": 0.1963, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 6.84, | |
| "learning_rate": 1.5780998389694043e-05, | |
| "loss": 0.2008, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 7.25, | |
| "learning_rate": 1.3768115942028985e-05, | |
| "loss": 0.1892, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 7.65, | |
| "learning_rate": 1.175523349436393e-05, | |
| "loss": 0.1842, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 8.05, | |
| "learning_rate": 9.742351046698874e-06, | |
| "loss": 0.1843, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 8.45, | |
| "learning_rate": 7.729468599033817e-06, | |
| "loss": 0.1742, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 8.86, | |
| "learning_rate": 5.71658615136876e-06, | |
| "loss": 0.1733, | |
| "step": 11000 | |
| } | |
| ], | |
| "max_steps": 12420, | |
| "num_train_epochs": 10, | |
| "total_flos": 1.2707766784548864e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |