| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.3392259274139549, | |
| "global_step": 10000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 2.8995580554439533e-05, | |
| "loss": 1.7911, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 2.799116110887907e-05, | |
| "loss": 1.1202, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 2.69867416633186e-05, | |
| "loss": 1.071, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 2.5982322217758134e-05, | |
| "loss": 1.0396, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 2.497790277219767e-05, | |
| "loss": 0.9828, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 2.3973483326637206e-05, | |
| "loss": 0.9747, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 2.296906388107674e-05, | |
| "loss": 0.9792, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 2.1964644435516274e-05, | |
| "loss": 0.9584, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 2.0960224989955807e-05, | |
| "loss": 0.9178, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 1.995580554439534e-05, | |
| "loss": 0.9288, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 1.8951386098834875e-05, | |
| "loss": 0.9089, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 1.7946966653274408e-05, | |
| "loss": 0.883, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 1.694254720771394e-05, | |
| "loss": 0.8601, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 1.5938127762153476e-05, | |
| "loss": 0.847, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 1.493370831659301e-05, | |
| "loss": 0.831, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 1.3929288871032543e-05, | |
| "loss": 0.6511, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "learning_rate": 1.2924869425472077e-05, | |
| "loss": 0.6223, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "learning_rate": 1.1920449979911611e-05, | |
| "loss": 0.6363, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "learning_rate": 1.0916030534351145e-05, | |
| "loss": 0.6226, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "learning_rate": 9.91161108879068e-06, | |
| "loss": 0.6203, | |
| "step": 10000 | |
| } | |
| ], | |
| "max_steps": 14934, | |
| "num_train_epochs": 2, | |
| "total_flos": 8.357875357981133e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |