| { |
| "best_global_step": 42, |
| "best_metric": 0.20909090909090908, |
| "best_model_checkpoint": "font-identifier/checkpoint-42", |
| "epoch": 3.0, |
| "eval_steps": 500, |
| "global_step": 42, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.7272727272727273, |
| "grad_norm": 9.430075645446777, |
| "learning_rate": 6.428571428571429e-06, |
| "loss": 3.3213, |
| "step": 10 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_accuracy": 0.06818181818181818, |
| "eval_loss": 3.2453081607818604, |
| "eval_runtime": 2.4333, |
| "eval_samples_per_second": 90.411, |
| "eval_steps_per_second": 5.753, |
| "step": 14 |
| }, |
| { |
| "epoch": 1.4363636363636363, |
| "grad_norm": 9.360711097717285, |
| "learning_rate": 1.357142857142857e-05, |
| "loss": 3.1711, |
| "step": 20 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_accuracy": 0.12727272727272726, |
| "eval_loss": 3.0051403045654297, |
| "eval_runtime": 2.0612, |
| "eval_samples_per_second": 106.735, |
| "eval_steps_per_second": 6.792, |
| "step": 28 |
| }, |
| { |
| "epoch": 2.1454545454545455, |
| "grad_norm": 8.500679016113281, |
| "learning_rate": 2.0714285714285718e-05, |
| "loss": 2.983, |
| "step": 30 |
| }, |
| { |
| "epoch": 2.8727272727272726, |
| "grad_norm": 9.82868766784668, |
| "learning_rate": 2.785714285714286e-05, |
| "loss": 2.8729, |
| "step": 40 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_accuracy": 0.20909090909090908, |
| "eval_loss": 2.6284613609313965, |
| "eval_runtime": 2.0503, |
| "eval_samples_per_second": 107.302, |
| "eval_steps_per_second": 6.828, |
| "step": 42 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 700, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 50, |
| "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": 2.667577742032896e+16, |
| "train_batch_size": 16, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
