| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 5.0, |
| "eval_steps": 500, |
| "global_step": 1960, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 1.0, |
| "eval_loss": 1.3433195443616972, |
| "las": 72.15189873417721, |
| "step": 392, |
| "uas": 81.66739415102575 |
| }, |
| { |
| "epoch": 1.2755102040816326, |
| "grad_norm": 3.317138433456421, |
| "learning_rate": 0.00014897959183673472, |
| "loss": 0.8116, |
| "step": 500 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_loss": 1.6489886807070837, |
| "las": 73.24312527280664, |
| "step": 784, |
| "uas": 81.92928852029682 |
| }, |
| { |
| "epoch": 2.5510204081632653, |
| "grad_norm": 2.6405985355377197, |
| "learning_rate": 9.79591836734694e-05, |
| "loss": 0.2626, |
| "step": 1000 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_loss": 1.7524571418762207, |
| "las": 73.15582714971627, |
| "step": 1176, |
| "uas": 82.36577913574858 |
| }, |
| { |
| "epoch": 3.826530612244898, |
| "grad_norm": 2.158872365951538, |
| "learning_rate": 4.6938775510204086e-05, |
| "loss": 0.1222, |
| "step": 1500 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_loss": 2.07165447043048, |
| "las": 75.46922741161065, |
| "step": 1568, |
| "uas": 84.37363596682671 |
| } |
| ], |
| "logging_steps": 500, |
| "max_steps": 1960, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 5, |
| "save_steps": 500, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 2.157644595068928e+16, |
| "train_batch_size": 64, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
