| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.47058823529411764, |
| "eval_steps": 500, |
| "global_step": 1000, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.023529411764705882, |
| "grad_norm": 0.47367432713508606, |
| "learning_rate": 0.0002, |
| "loss": 0.8419, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.047058823529411764, |
| "grad_norm": 0.4179942309856415, |
| "learning_rate": 0.0002, |
| "loss": 0.554, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.07058823529411765, |
| "grad_norm": 0.40505528450012207, |
| "learning_rate": 0.0002, |
| "loss": 0.5132, |
| "step": 150 |
| }, |
| { |
| "epoch": 0.09411764705882353, |
| "grad_norm": 0.3808290958404541, |
| "learning_rate": 0.0002, |
| "loss": 0.5017, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.11764705882352941, |
| "grad_norm": 0.4120051860809326, |
| "learning_rate": 0.0002, |
| "loss": 0.4731, |
| "step": 250 |
| }, |
| { |
| "epoch": 0.1411764705882353, |
| "grad_norm": 0.3958088755607605, |
| "learning_rate": 0.0002, |
| "loss": 0.4676, |
| "step": 300 |
| }, |
| { |
| "epoch": 0.16470588235294117, |
| "grad_norm": 0.3591330349445343, |
| "learning_rate": 0.0002, |
| "loss": 0.4393, |
| "step": 350 |
| }, |
| { |
| "epoch": 0.18823529411764706, |
| "grad_norm": 0.4021323621273041, |
| "learning_rate": 0.0002, |
| "loss": 0.4328, |
| "step": 400 |
| }, |
| { |
| "epoch": 0.21176470588235294, |
| "grad_norm": 0.3221900165081024, |
| "learning_rate": 0.0002, |
| "loss": 0.4532, |
| "step": 450 |
| }, |
| { |
| "epoch": 0.23529411764705882, |
| "grad_norm": 0.3609311282634735, |
| "learning_rate": 0.0002, |
| "loss": 0.4484, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.25882352941176473, |
| "grad_norm": 0.38572075963020325, |
| "learning_rate": 0.0002, |
| "loss": 0.4324, |
| "step": 550 |
| }, |
| { |
| "epoch": 0.2823529411764706, |
| "grad_norm": 0.34739094972610474, |
| "learning_rate": 0.0002, |
| "loss": 0.4229, |
| "step": 600 |
| }, |
| { |
| "epoch": 0.3058823529411765, |
| "grad_norm": 0.37802746891975403, |
| "learning_rate": 0.0002, |
| "loss": 0.4313, |
| "step": 650 |
| }, |
| { |
| "epoch": 0.32941176470588235, |
| "grad_norm": 0.38322341442108154, |
| "learning_rate": 0.0002, |
| "loss": 0.4255, |
| "step": 700 |
| }, |
| { |
| "epoch": 0.35294117647058826, |
| "grad_norm": 0.33342960476875305, |
| "learning_rate": 0.0002, |
| "loss": 0.4146, |
| "step": 750 |
| }, |
| { |
| "epoch": 0.3764705882352941, |
| "grad_norm": 0.39778926968574524, |
| "learning_rate": 0.0002, |
| "loss": 0.4199, |
| "step": 800 |
| }, |
| { |
| "epoch": 0.4, |
| "grad_norm": 0.35360318422317505, |
| "learning_rate": 0.0002, |
| "loss": 0.4078, |
| "step": 850 |
| }, |
| { |
| "epoch": 0.4235294117647059, |
| "grad_norm": 0.3482576906681061, |
| "learning_rate": 0.0002, |
| "loss": 0.4055, |
| "step": 900 |
| }, |
| { |
| "epoch": 0.4470588235294118, |
| "grad_norm": 0.36093461513519287, |
| "learning_rate": 0.0002, |
| "loss": 0.4099, |
| "step": 950 |
| }, |
| { |
| "epoch": 0.47058823529411764, |
| "grad_norm": 0.32471776008605957, |
| "learning_rate": 0.0002, |
| "loss": 0.3933, |
| "step": 1000 |
| } |
| ], |
| "logging_steps": 50, |
| "max_steps": 2125, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 1, |
| "save_steps": 500, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 1.2711615139015066e+17, |
| "train_batch_size": 1, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
