| { |
| "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": 1.0580593172334316, |
| "learning_rate": 9.59731543624161e-06, |
| "loss": 0.0037, |
| "step": 7 |
| }, |
| { |
| "epoch": 14.0, |
| "grad_norm": 1.917778225415779, |
| "learning_rate": 9.12751677852349e-06, |
| "loss": -0.0053, |
| "step": 14 |
| }, |
| { |
| "epoch": 21.0, |
| "grad_norm": 2.856271321414714, |
| "learning_rate": 8.65771812080537e-06, |
| "loss": -0.0388, |
| "step": 21 |
| }, |
| { |
| "epoch": 28.0, |
| "grad_norm": 2.8602976277281686, |
| "learning_rate": 8.18791946308725e-06, |
| "loss": -0.0922, |
| "step": 28 |
| }, |
| { |
| "epoch": 35.0, |
| "grad_norm": 2.56359282977704, |
| "learning_rate": 7.718120805369127e-06, |
| "loss": -0.1599, |
| "step": 35 |
| }, |
| { |
| "epoch": 42.0, |
| "grad_norm": 2.1902981070245575, |
| "learning_rate": 7.248322147651007e-06, |
| "loss": -0.2208, |
| "step": 42 |
| }, |
| { |
| "epoch": 49.0, |
| "grad_norm": 2.5179842050101024, |
| "learning_rate": 6.778523489932887e-06, |
| "loss": -0.2805, |
| "step": 49 |
| }, |
| { |
| "epoch": 56.0, |
| "grad_norm": 3.020052307514867, |
| "learning_rate": 6.308724832214766e-06, |
| "loss": -0.3321, |
| "step": 56 |
| }, |
| { |
| "epoch": 63.0, |
| "grad_norm": 4.104147437593582, |
| "learning_rate": 5.8389261744966455e-06, |
| "loss": -0.4024, |
| "step": 63 |
| }, |
| { |
| "epoch": 70.0, |
| "grad_norm": 6.271752210024252, |
| "learning_rate": 5.369127516778524e-06, |
| "loss": -0.4906, |
| "step": 70 |
| }, |
| { |
| "epoch": 77.0, |
| "grad_norm": 8.680130351386671, |
| "learning_rate": 4.899328859060403e-06, |
| "loss": -0.6201, |
| "step": 77 |
| }, |
| { |
| "epoch": 84.0, |
| "grad_norm": 10.374252086894382, |
| "learning_rate": 4.429530201342283e-06, |
| "loss": -0.7926, |
| "step": 84 |
| }, |
| { |
| "epoch": 91.0, |
| "grad_norm": 10.872605027238645, |
| "learning_rate": 3.959731543624161e-06, |
| "loss": -0.9862, |
| "step": 91 |
| }, |
| { |
| "epoch": 98.0, |
| "grad_norm": 10.561731031719896, |
| "learning_rate": 3.4899328859060407e-06, |
| "loss": -1.1732, |
| "step": 98 |
| }, |
| { |
| "epoch": 105.0, |
| "grad_norm": 12.894131660694978, |
| "learning_rate": 3.02013422818792e-06, |
| "loss": -1.37, |
| "step": 105 |
| }, |
| { |
| "epoch": 112.0, |
| "grad_norm": 14.083588240828902, |
| "learning_rate": 2.5503355704697992e-06, |
| "loss": -1.5496, |
| "step": 112 |
| }, |
| { |
| "epoch": 119.0, |
| "grad_norm": 14.83261819867963, |
| "learning_rate": 2.080536912751678e-06, |
| "loss": -1.7171, |
| "step": 119 |
| }, |
| { |
| "epoch": 126.0, |
| "grad_norm": 14.451846913816599, |
| "learning_rate": 1.6107382550335572e-06, |
| "loss": -1.8715, |
| "step": 126 |
| }, |
| { |
| "epoch": 133.0, |
| "grad_norm": 16.064799109043804, |
| "learning_rate": 1.1409395973154363e-06, |
| "loss": -2.0146, |
| "step": 133 |
| }, |
| { |
| "epoch": 140.0, |
| "grad_norm": 16.381551093382335, |
| "learning_rate": 6.711409395973155e-07, |
| "loss": -2.1186, |
| "step": 140 |
| }, |
| { |
| "epoch": 147.0, |
| "grad_norm": 16.412831075564316, |
| "learning_rate": 2.0134228187919465e-07, |
| "loss": -2.1549, |
| "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 |
| } |
|
|
