| { |
| "best_global_step": 500, |
| "best_metric": 0.8412698412698413, |
| "best_model_checkpoint": "doctomodernbert-ft-incertain/checkpoint-500", |
| "epoch": 2.0, |
| "eval_steps": 500, |
| "global_step": 500, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 1.0, |
| "grad_norm": 6.427690029144287, |
| "learning_rate": 2.004e-05, |
| "loss": 0.4546, |
| "step": 250 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_accuracy": 0.702, |
| "eval_f1_incertain": 0.718336483931947, |
| "eval_loss": 0.61598801612854, |
| "eval_runtime": 2.3103, |
| "eval_samples_per_second": 216.418, |
| "eval_steps_per_second": 27.269, |
| "step": 250 |
| }, |
| { |
| "epoch": 2.0, |
| "grad_norm": 1.7718960046768188, |
| "learning_rate": 1.004e-05, |
| "loss": 0.3273, |
| "step": 500 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_accuracy": 0.88, |
| "eval_f1_incertain": 0.8412698412698413, |
| "eval_loss": 0.30243343114852905, |
| "eval_runtime": 2.3289, |
| "eval_samples_per_second": 214.691, |
| "eval_steps_per_second": 27.051, |
| "step": 500 |
| } |
| ], |
| "logging_steps": 500, |
| "max_steps": 750, |
| "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": 1367450587379520.0, |
| "train_batch_size": 16, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
