| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 3.0, |
| "eval_steps": 500, |
| "global_step": 6729, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.22291573785109228, |
| "grad_norm": 1.3647773265838623, |
| "learning_rate": 5e-05, |
| "loss": 0.7791, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.44583147570218457, |
| "grad_norm": 0.9170280694961548, |
| "learning_rate": 4.598651468935624e-05, |
| "loss": 0.1977, |
| "step": 1000 |
| }, |
| { |
| "epoch": 0.6687472135532768, |
| "grad_norm": 0.8765759468078613, |
| "learning_rate": 4.1973029378712475e-05, |
| "loss": 0.1697, |
| "step": 1500 |
| }, |
| { |
| "epoch": 0.8916629514043691, |
| "grad_norm": 0.6906009912490845, |
| "learning_rate": 3.7959544068068715e-05, |
| "loss": 0.1548, |
| "step": 2000 |
| }, |
| { |
| "epoch": 1.1145786892554614, |
| "grad_norm": 0.9499293565750122, |
| "learning_rate": 3.394605875742495e-05, |
| "loss": 0.1323, |
| "step": 2500 |
| }, |
| { |
| "epoch": 1.3374944271065536, |
| "grad_norm": 0.822642982006073, |
| "learning_rate": 2.9932573446781187e-05, |
| "loss": 0.1174, |
| "step": 3000 |
| }, |
| { |
| "epoch": 1.560410164957646, |
| "grad_norm": 0.757134735584259, |
| "learning_rate": 2.591908813613742e-05, |
| "loss": 0.1101, |
| "step": 3500 |
| }, |
| { |
| "epoch": 1.7833259028087383, |
| "grad_norm": 0.6683522462844849, |
| "learning_rate": 2.190560282549366e-05, |
| "loss": 0.1051, |
| "step": 4000 |
| }, |
| { |
| "epoch": 2.0062416406598307, |
| "grad_norm": 0.7783832550048828, |
| "learning_rate": 1.7892117514849896e-05, |
| "loss": 0.1017, |
| "step": 4500 |
| }, |
| { |
| "epoch": 2.229157378510923, |
| "grad_norm": 0.6604039669036865, |
| "learning_rate": 1.3878632204206132e-05, |
| "loss": 0.0858, |
| "step": 5000 |
| }, |
| { |
| "epoch": 2.452073116362015, |
| "grad_norm": 0.7059195637702942, |
| "learning_rate": 9.86514689356237e-06, |
| "loss": 0.0835, |
| "step": 5500 |
| }, |
| { |
| "epoch": 2.6749888542131073, |
| "grad_norm": 0.6601874232292175, |
| "learning_rate": 5.851661582918607e-06, |
| "loss": 0.0824, |
| "step": 6000 |
| }, |
| { |
| "epoch": 2.8979045920642, |
| "grad_norm": 0.6698402762413025, |
| "learning_rate": 1.8381762722748435e-06, |
| "loss": 0.0816, |
| "step": 6500 |
| } |
| ], |
| "logging_steps": 500, |
| "max_steps": 6729, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 3, |
| "save_steps": 10000, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 7031368581120000.0, |
| "train_batch_size": 4, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
