| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 3.0, |
| "eval_steps": 500, |
| "global_step": 75, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.20202020202020202, |
| "grad_norm": 23.5, |
| "learning_rate": 2.5e-05, |
| "loss": 3.2729, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.40404040404040403, |
| "grad_norm": 4.5625, |
| "learning_rate": 4.9253731343283586e-05, |
| "loss": 1.0994, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.6060606060606061, |
| "grad_norm": 2.3125, |
| "learning_rate": 4.5522388059701495e-05, |
| "loss": 0.2674, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.8080808080808081, |
| "grad_norm": 1.4453125, |
| "learning_rate": 4.1791044776119404e-05, |
| "loss": 0.189, |
| "step": 20 |
| }, |
| { |
| "epoch": 1.0, |
| "grad_norm": 1.6015625, |
| "learning_rate": 3.805970149253731e-05, |
| "loss": 0.175, |
| "step": 25 |
| }, |
| { |
| "epoch": 1.202020202020202, |
| "grad_norm": 1.171875, |
| "learning_rate": 3.432835820895522e-05, |
| "loss": 0.1748, |
| "step": 30 |
| }, |
| { |
| "epoch": 1.404040404040404, |
| "grad_norm": 1.4765625, |
| "learning_rate": 3.059701492537314e-05, |
| "loss": 0.1747, |
| "step": 35 |
| }, |
| { |
| "epoch": 1.606060606060606, |
| "grad_norm": 1.46875, |
| "learning_rate": 2.6865671641791047e-05, |
| "loss": 0.16, |
| "step": 40 |
| }, |
| { |
| "epoch": 1.808080808080808, |
| "grad_norm": 1.421875, |
| "learning_rate": 2.3134328358208956e-05, |
| "loss": 0.1593, |
| "step": 45 |
| }, |
| { |
| "epoch": 2.0, |
| "grad_norm": 1.2109375, |
| "learning_rate": 1.9402985074626868e-05, |
| "loss": 0.1637, |
| "step": 50 |
| }, |
| { |
| "epoch": 2.202020202020202, |
| "grad_norm": 1.1640625, |
| "learning_rate": 1.5671641791044777e-05, |
| "loss": 0.1279, |
| "step": 55 |
| }, |
| { |
| "epoch": 2.404040404040404, |
| "grad_norm": 1.28125, |
| "learning_rate": 1.1940298507462686e-05, |
| "loss": 0.1295, |
| "step": 60 |
| }, |
| { |
| "epoch": 2.606060606060606, |
| "grad_norm": 1.078125, |
| "learning_rate": 8.208955223880597e-06, |
| "loss": 0.14, |
| "step": 65 |
| }, |
| { |
| "epoch": 2.808080808080808, |
| "grad_norm": 1.1015625, |
| "learning_rate": 4.477611940298508e-06, |
| "loss": 0.1461, |
| "step": 70 |
| }, |
| { |
| "epoch": 3.0, |
| "grad_norm": 1.4140625, |
| "learning_rate": 7.462686567164179e-07, |
| "loss": 0.1591, |
| "step": 75 |
| } |
| ], |
| "logging_steps": 5, |
| "max_steps": 75, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 3, |
| "save_steps": 50, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 3025833383688192.0, |
| "train_batch_size": 1, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
