| { |
| "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": 62.793856616348066, |
| "learning_rate": 9.59731543624161e-06, |
| "loss": -0.7422, |
| "step": 7 |
| }, |
| { |
| "epoch": 14.0, |
| "grad_norm": 56.9408295734485, |
| "learning_rate": 9.12751677852349e-06, |
| "loss": -0.8301, |
| "step": 14 |
| }, |
| { |
| "epoch": 21.0, |
| "grad_norm": 45.157650718729144, |
| "learning_rate": 8.65771812080537e-06, |
| "loss": -2.4042, |
| "step": 21 |
| }, |
| { |
| "epoch": 28.0, |
| "grad_norm": 47.35942717812566, |
| "learning_rate": 8.18791946308725e-06, |
| "loss": -1.8824, |
| "step": 28 |
| }, |
| { |
| "epoch": 35.0, |
| "grad_norm": 48.05921398337566, |
| "learning_rate": 7.718120805369127e-06, |
| "loss": -2.7664, |
| "step": 35 |
| }, |
| { |
| "epoch": 42.0, |
| "grad_norm": 45.36934348020007, |
| "learning_rate": 7.248322147651007e-06, |
| "loss": -4.0572, |
| "step": 42 |
| }, |
| { |
| "epoch": 49.0, |
| "grad_norm": 46.17873814269687, |
| "learning_rate": 6.778523489932887e-06, |
| "loss": -5.1926, |
| "step": 49 |
| }, |
| { |
| "epoch": 56.0, |
| "grad_norm": 45.55979398789716, |
| "learning_rate": 6.308724832214766e-06, |
| "loss": -5.433, |
| "step": 56 |
| }, |
| { |
| "epoch": 63.0, |
| "grad_norm": 48.44378585370266, |
| "learning_rate": 5.8389261744966455e-06, |
| "loss": -6.8876, |
| "step": 63 |
| }, |
| { |
| "epoch": 70.0, |
| "grad_norm": 45.51230868679239, |
| "learning_rate": 5.369127516778524e-06, |
| "loss": -6.8249, |
| "step": 70 |
| }, |
| { |
| "epoch": 77.0, |
| "grad_norm": 43.72025392664926, |
| "learning_rate": 4.899328859060403e-06, |
| "loss": -7.6626, |
| "step": 77 |
| }, |
| { |
| "epoch": 84.0, |
| "grad_norm": 41.92085497059608, |
| "learning_rate": 4.429530201342283e-06, |
| "loss": -7.7817, |
| "step": 84 |
| }, |
| { |
| "epoch": 91.0, |
| "grad_norm": 47.03121171415375, |
| "learning_rate": 3.959731543624161e-06, |
| "loss": -8.1769, |
| "step": 91 |
| }, |
| { |
| "epoch": 98.0, |
| "grad_norm": 41.54635533700402, |
| "learning_rate": 3.4899328859060407e-06, |
| "loss": -8.865, |
| "step": 98 |
| }, |
| { |
| "epoch": 105.0, |
| "grad_norm": 41.72605528729653, |
| "learning_rate": 3.02013422818792e-06, |
| "loss": -9.7963, |
| "step": 105 |
| }, |
| { |
| "epoch": 112.0, |
| "grad_norm": 40.892345986997725, |
| "learning_rate": 2.5503355704697992e-06, |
| "loss": -9.7775, |
| "step": 112 |
| }, |
| { |
| "epoch": 119.0, |
| "grad_norm": 41.37552841719097, |
| "learning_rate": 2.080536912751678e-06, |
| "loss": -9.8272, |
| "step": 119 |
| }, |
| { |
| "epoch": 126.0, |
| "grad_norm": 49.612967721348554, |
| "learning_rate": 1.6107382550335572e-06, |
| "loss": -9.9642, |
| "step": 126 |
| }, |
| { |
| "epoch": 133.0, |
| "grad_norm": 58.685446208928745, |
| "learning_rate": 1.1409395973154363e-06, |
| "loss": -10.339, |
| "step": 133 |
| }, |
| { |
| "epoch": 140.0, |
| "grad_norm": 49.5575241662933, |
| "learning_rate": 6.711409395973155e-07, |
| "loss": -10.3831, |
| "step": 140 |
| }, |
| { |
| "epoch": 147.0, |
| "grad_norm": 46.87818731610494, |
| "learning_rate": 2.0134228187919465e-07, |
| "loss": -11.0643, |
| "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 |
| } |
|
|
