| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 150.0, |
| "eval_steps": 0, |
| "global_step": 150, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 7.0, |
| "grad_norm": 42.1325200963559, |
| "learning_rate": 9.59731543624161e-06, |
| "loss": 0.7445, |
| "step": 7 |
| }, |
| { |
| "epoch": 14.0, |
| "grad_norm": 55.653457681069376, |
| "learning_rate": 9.12751677852349e-06, |
| "loss": 0.7998, |
| "step": 14 |
| }, |
| { |
| "epoch": 21.0, |
| "grad_norm": 48.98229976226828, |
| "learning_rate": 8.65771812080537e-06, |
| "loss": -0.7876, |
| "step": 21 |
| }, |
| { |
| "epoch": 28.0, |
| "grad_norm": 44.39063544333735, |
| "learning_rate": 8.18791946308725e-06, |
| "loss": -0.4994, |
| "step": 28 |
| }, |
| { |
| "epoch": 35.0, |
| "grad_norm": 44.39171514520647, |
| "learning_rate": 7.718120805369127e-06, |
| "loss": -1.4729, |
| "step": 35 |
| }, |
| { |
| "epoch": 42.0, |
| "grad_norm": 39.847393464139486, |
| "learning_rate": 7.248322147651007e-06, |
| "loss": -2.7317, |
| "step": 42 |
| }, |
| { |
| "epoch": 49.0, |
| "grad_norm": 41.47715069295314, |
| "learning_rate": 6.778523489932887e-06, |
| "loss": -3.8809, |
| "step": 49 |
| }, |
| { |
| "epoch": 56.0, |
| "grad_norm": 41.39756819220964, |
| "learning_rate": 6.308724832214766e-06, |
| "loss": -3.9631, |
| "step": 56 |
| }, |
| { |
| "epoch": 63.0, |
| "grad_norm": 46.88180194446683, |
| "learning_rate": 5.8389261744966455e-06, |
| "loss": -5.4733, |
| "step": 63 |
| }, |
| { |
| "epoch": 70.0, |
| "grad_norm": 42.02906417790194, |
| "learning_rate": 5.369127516778524e-06, |
| "loss": -5.2957, |
| "step": 70 |
| }, |
| { |
| "epoch": 77.0, |
| "grad_norm": 42.621091297767144, |
| "learning_rate": 4.899328859060403e-06, |
| "loss": -6.3275, |
| "step": 77 |
| }, |
| { |
| "epoch": 84.0, |
| "grad_norm": 46.06752267716322, |
| "learning_rate": 4.429530201342283e-06, |
| "loss": -6.2275, |
| "step": 84 |
| }, |
| { |
| "epoch": 91.0, |
| "grad_norm": 53.68872114062101, |
| "learning_rate": 3.959731543624161e-06, |
| "loss": -6.7181, |
| "step": 91 |
| }, |
| { |
| "epoch": 98.0, |
| "grad_norm": 48.38465381789599, |
| "learning_rate": 3.4899328859060407e-06, |
| "loss": -7.522, |
| "step": 98 |
| }, |
| { |
| "epoch": 105.0, |
| "grad_norm": 51.494136564869486, |
| "learning_rate": 3.02013422818792e-06, |
| "loss": -8.6279, |
| "step": 105 |
| }, |
| { |
| "epoch": 112.0, |
| "grad_norm": 52.52196785284407, |
| "learning_rate": 2.5503355704697992e-06, |
| "loss": -9.0531, |
| "step": 112 |
| }, |
| { |
| "epoch": 119.0, |
| "grad_norm": 53.64307534470575, |
| "learning_rate": 2.080536912751678e-06, |
| "loss": -9.2935, |
| "step": 119 |
| }, |
| { |
| "epoch": 126.0, |
| "grad_norm": 58.10870485556803, |
| "learning_rate": 1.6107382550335572e-06, |
| "loss": -9.2432, |
| "step": 126 |
| }, |
| { |
| "epoch": 133.0, |
| "grad_norm": 69.56079050860436, |
| "learning_rate": 1.1409395973154363e-06, |
| "loss": -9.7614, |
| "step": 133 |
| }, |
| { |
| "epoch": 140.0, |
| "grad_norm": 60.78183847404733, |
| "learning_rate": 6.711409395973155e-07, |
| "loss": -9.976, |
| "step": 140 |
| }, |
| { |
| "epoch": 147.0, |
| "grad_norm": 59.22699782555444, |
| "learning_rate": 2.0134228187919465e-07, |
| "loss": -10.5103, |
| "step": 147 |
| } |
| ], |
| "logging_steps": 7, |
| "max_steps": 150, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 150, |
| "save_steps": 15, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 0.0, |
| "train_batch_size": 1, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
