| { |
| "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": 49.4614286089246, |
| "learning_rate": 9.59731543624161e-06, |
| "loss": -2.1193, |
| "step": 7 |
| }, |
| { |
| "epoch": 14.0, |
| "grad_norm": 55.59276691001918, |
| "learning_rate": 9.12751677852349e-06, |
| "loss": -1.9205, |
| "step": 14 |
| }, |
| { |
| "epoch": 21.0, |
| "grad_norm": 50.4479201890886, |
| "learning_rate": 8.65771812080537e-06, |
| "loss": -3.7194, |
| "step": 21 |
| }, |
| { |
| "epoch": 28.0, |
| "grad_norm": 43.410955254524396, |
| "learning_rate": 8.18791946308725e-06, |
| "loss": -3.5004, |
| "step": 28 |
| }, |
| { |
| "epoch": 35.0, |
| "grad_norm": 40.74330532944559, |
| "learning_rate": 7.718120805369127e-06, |
| "loss": -4.4373, |
| "step": 35 |
| }, |
| { |
| "epoch": 42.0, |
| "grad_norm": 35.47518411666178, |
| "learning_rate": 7.248322147651007e-06, |
| "loss": -5.8654, |
| "step": 42 |
| }, |
| { |
| "epoch": 49.0, |
| "grad_norm": 38.36179150082702, |
| "learning_rate": 6.778523489932887e-06, |
| "loss": -7.0026, |
| "step": 49 |
| }, |
| { |
| "epoch": 56.0, |
| "grad_norm": 42.89189964871521, |
| "learning_rate": 6.308724832214766e-06, |
| "loss": -7.0654, |
| "step": 56 |
| }, |
| { |
| "epoch": 63.0, |
| "grad_norm": 49.59026451902394, |
| "learning_rate": 5.8389261744966455e-06, |
| "loss": -8.7445, |
| "step": 63 |
| }, |
| { |
| "epoch": 70.0, |
| "grad_norm": 49.32539631151106, |
| "learning_rate": 5.369127516778524e-06, |
| "loss": -8.7375, |
| "step": 70 |
| }, |
| { |
| "epoch": 77.0, |
| "grad_norm": 50.75839910680419, |
| "learning_rate": 4.899328859060403e-06, |
| "loss": -9.351, |
| "step": 77 |
| }, |
| { |
| "epoch": 84.0, |
| "grad_norm": 51.06753474326904, |
| "learning_rate": 4.429530201342283e-06, |
| "loss": -10.7511, |
| "step": 84 |
| }, |
| { |
| "epoch": 91.0, |
| "grad_norm": 56.33626345309772, |
| "learning_rate": 3.959731543624161e-06, |
| "loss": -10.7132, |
| "step": 91 |
| }, |
| { |
| "epoch": 98.0, |
| "grad_norm": 49.98648100418674, |
| "learning_rate": 3.4899328859060407e-06, |
| "loss": -11.5812, |
| "step": 98 |
| }, |
| { |
| "epoch": 105.0, |
| "grad_norm": 50.999402353756416, |
| "learning_rate": 3.02013422818792e-06, |
| "loss": -12.7886, |
| "step": 105 |
| }, |
| { |
| "epoch": 112.0, |
| "grad_norm": 49.28466702769597, |
| "learning_rate": 2.5503355704697992e-06, |
| "loss": -13.087, |
| "step": 112 |
| }, |
| { |
| "epoch": 119.0, |
| "grad_norm": 50.682183745220584, |
| "learning_rate": 2.080536912751678e-06, |
| "loss": -13.3733, |
| "step": 119 |
| }, |
| { |
| "epoch": 126.0, |
| "grad_norm": 55.75834274698238, |
| "learning_rate": 1.6107382550335572e-06, |
| "loss": -13.3372, |
| "step": 126 |
| }, |
| { |
| "epoch": 133.0, |
| "grad_norm": 64.85630797436718, |
| "learning_rate": 1.1409395973154363e-06, |
| "loss": -13.9536, |
| "step": 133 |
| }, |
| { |
| "epoch": 140.0, |
| "grad_norm": 57.208515349818654, |
| "learning_rate": 6.711409395973155e-07, |
| "loss": -14.0713, |
| "step": 140 |
| }, |
| { |
| "epoch": 147.0, |
| "grad_norm": 55.22414857046122, |
| "learning_rate": 2.0134228187919465e-07, |
| "loss": -14.3914, |
| "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 |
| } |
|
|
