| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 2.6666666666666665, |
| "eval_steps": 500, |
| "global_step": 24, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.5555555555555556, |
| "grad_norm": 3.0, |
| "learning_rate": 1.9274877295384588e-05, |
| "loss": 1.7704, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.8888888888888888, |
| "eval_loss": 1.5440232753753662, |
| "eval_runtime": 4.5371, |
| "eval_samples_per_second": 27.11, |
| "eval_steps_per_second": 27.11, |
| "step": 8 |
| }, |
| { |
| "epoch": 1.1111111111111112, |
| "grad_norm": 2.5625, |
| "learning_rate": 4.3368473914615324e-05, |
| "loss": 1.597, |
| "step": 10 |
| }, |
| { |
| "epoch": 1.6666666666666665, |
| "grad_norm": 2.296875, |
| "learning_rate": 6.746207053384607e-05, |
| "loss": 1.4676, |
| "step": 15 |
| }, |
| { |
| "epoch": 1.7777777777777777, |
| "eval_loss": 1.4144201278686523, |
| "eval_runtime": 4.449, |
| "eval_samples_per_second": 27.646, |
| "eval_steps_per_second": 27.646, |
| "step": 16 |
| }, |
| { |
| "epoch": 2.2222222222222223, |
| "grad_norm": 2.71875, |
| "learning_rate": 9.155566715307679e-05, |
| "loss": 1.3586, |
| "step": 20 |
| }, |
| { |
| "epoch": 2.6666666666666665, |
| "eval_loss": 1.344400405883789, |
| "eval_runtime": 4.4838, |
| "eval_samples_per_second": 27.432, |
| "eval_steps_per_second": 27.432, |
| "step": 24 |
| } |
| ], |
| "logging_steps": 5, |
| "max_steps": 27, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 3, |
| "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": 1.2020876656508928e+16, |
| "train_batch_size": 140, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
