| { |
| "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": 22.53773096654945, |
| "learning_rate": 9.59731543624161e-06, |
| "loss": 0.3209, |
| "step": 7 |
| }, |
| { |
| "epoch": 14.0, |
| "grad_norm": 26.583446594810738, |
| "learning_rate": 9.12751677852349e-06, |
| "loss": 0.588, |
| "step": 14 |
| }, |
| { |
| "epoch": 21.0, |
| "grad_norm": 28.68725502381928, |
| "learning_rate": 8.65771812080537e-06, |
| "loss": -0.1057, |
| "step": 21 |
| }, |
| { |
| "epoch": 28.0, |
| "grad_norm": 29.867392254771623, |
| "learning_rate": 8.18791946308725e-06, |
| "loss": -0.0705, |
| "step": 28 |
| }, |
| { |
| "epoch": 35.0, |
| "grad_norm": 27.06663729446553, |
| "learning_rate": 7.718120805369127e-06, |
| "loss": -0.141, |
| "step": 35 |
| }, |
| { |
| "epoch": 42.0, |
| "grad_norm": 26.823991222331102, |
| "learning_rate": 7.248322147651007e-06, |
| "loss": -2.1082, |
| "step": 42 |
| }, |
| { |
| "epoch": 49.0, |
| "grad_norm": 24.80830010493394, |
| "learning_rate": 6.778523489932887e-06, |
| "loss": -1.8793, |
| "step": 49 |
| }, |
| { |
| "epoch": 56.0, |
| "grad_norm": 31.090920124525447, |
| "learning_rate": 6.308724832214766e-06, |
| "loss": -1.7685, |
| "step": 56 |
| }, |
| { |
| "epoch": 63.0, |
| "grad_norm": 38.12470011869168, |
| "learning_rate": 5.8389261744966455e-06, |
| "loss": -3.4825, |
| "step": 63 |
| }, |
| { |
| "epoch": 70.0, |
| "grad_norm": 29.860770041143137, |
| "learning_rate": 5.369127516778524e-06, |
| "loss": -3.3901, |
| "step": 70 |
| }, |
| { |
| "epoch": 77.0, |
| "grad_norm": 33.12124310459433, |
| "learning_rate": 4.899328859060403e-06, |
| "loss": -4.4806, |
| "step": 77 |
| }, |
| { |
| "epoch": 84.0, |
| "grad_norm": 33.59918714377934, |
| "learning_rate": 4.429530201342283e-06, |
| "loss": -3.5523, |
| "step": 84 |
| }, |
| { |
| "epoch": 91.0, |
| "grad_norm": 32.85272684016845, |
| "learning_rate": 3.959731543624161e-06, |
| "loss": -3.9153, |
| "step": 91 |
| }, |
| { |
| "epoch": 98.0, |
| "grad_norm": 34.32594328402985, |
| "learning_rate": 3.4899328859060407e-06, |
| "loss": -4.6285, |
| "step": 98 |
| }, |
| { |
| "epoch": 105.0, |
| "grad_norm": 34.0159030432969, |
| "learning_rate": 3.02013422818792e-06, |
| "loss": -6.1686, |
| "step": 105 |
| }, |
| { |
| "epoch": 112.0, |
| "grad_norm": 34.513130708330365, |
| "learning_rate": 2.5503355704697992e-06, |
| "loss": -5.45, |
| "step": 112 |
| }, |
| { |
| "epoch": 119.0, |
| "grad_norm": 34.48082510584053, |
| "learning_rate": 2.080536912751678e-06, |
| "loss": -5.3978, |
| "step": 119 |
| }, |
| { |
| "epoch": 126.0, |
| "grad_norm": 45.03506925512733, |
| "learning_rate": 1.6107382550335572e-06, |
| "loss": -5.7079, |
| "step": 126 |
| }, |
| { |
| "epoch": 133.0, |
| "grad_norm": 60.173985241016176, |
| "learning_rate": 1.1409395973154363e-06, |
| "loss": -6.1938, |
| "step": 133 |
| }, |
| { |
| "epoch": 140.0, |
| "grad_norm": 45.52508642117794, |
| "learning_rate": 6.711409395973155e-07, |
| "loss": -6.3943, |
| "step": 140 |
| }, |
| { |
| "epoch": 147.0, |
| "grad_norm": 41.11841550181555, |
| "learning_rate": 2.0134228187919465e-07, |
| "loss": -6.7556, |
| "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 |
| } |
|
|
