| { |
| "best_global_step": 95, |
| "best_metric": 0.6507177033492823, |
| "best_model_checkpoint": "./ner-archetype-model/checkpoint-95", |
| "epoch": 1.0, |
| "eval_steps": 500, |
| "global_step": 95, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.10526315789473684, |
| "grad_norm": 0.3689213991165161, |
| "learning_rate": 1.9578947368421055e-05, |
| "loss": 0.4426, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.21052631578947367, |
| "grad_norm": 0.2375708669424057, |
| "learning_rate": 1.9157894736842108e-05, |
| "loss": 0.0929, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.3157894736842105, |
| "grad_norm": 0.6364700198173523, |
| "learning_rate": 1.873684210526316e-05, |
| "loss": 0.0732, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.42105263157894735, |
| "grad_norm": 0.3920805752277374, |
| "learning_rate": 1.831578947368421e-05, |
| "loss": 0.0639, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.5263157894736842, |
| "grad_norm": 0.37786218523979187, |
| "learning_rate": 1.7894736842105264e-05, |
| "loss": 0.0678, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.631578947368421, |
| "grad_norm": 0.41838499903678894, |
| "learning_rate": 1.7473684210526317e-05, |
| "loss": 0.0649, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.7368421052631579, |
| "grad_norm": 0.44255176186561584, |
| "learning_rate": 1.705263157894737e-05, |
| "loss": 0.0469, |
| "step": 70 |
| }, |
| { |
| "epoch": 0.8421052631578947, |
| "grad_norm": 0.44138917326927185, |
| "learning_rate": 1.6631578947368423e-05, |
| "loss": 0.0403, |
| "step": 80 |
| }, |
| { |
| "epoch": 0.9473684210526315, |
| "grad_norm": 0.39505335688591003, |
| "learning_rate": 1.6210526315789473e-05, |
| "loss": 0.0447, |
| "step": 90 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_ARCHETYPE": { |
| "f1": 0.6507177033492823, |
| "number": 338, |
| "precision": 0.7058823529411765, |
| "recall": 0.6035502958579881 |
| }, |
| "eval_loss": 0.034236546605825424, |
| "eval_overall_accuracy": 0.9891579152080903, |
| "eval_overall_f1": 0.6507177033492823, |
| "eval_overall_precision": 0.7058823529411765, |
| "eval_overall_recall": 0.6035502958579881, |
| "eval_runtime": 0.7373, |
| "eval_samples_per_second": 438.086, |
| "eval_steps_per_second": 28.482, |
| "step": 95 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 475, |
| "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": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 98444443122432.0, |
| "train_batch_size": 16, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
