| { |
| "best_global_step": 899, |
| "best_metric": 0.009147428907454014, |
| "best_model_checkpoint": "projects/PetBERT_annonymisation/data/augment/checkpoint-899", |
| "epoch": 4.0, |
| "eval_steps": 500, |
| "global_step": 3596, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0, |
| "eval_f1": 0.012204053693834897, |
| "eval_loss": 2.3885538578033447, |
| "eval_precision": 0.08893940326175621, |
| "eval_recall": 0.08310981045257043, |
| "eval_runtime": 31.2912, |
| "eval_samples_per_second": 139.592, |
| "eval_steps_per_second": 4.378, |
| "step": 0 |
| }, |
| { |
| "epoch": 0.5561735261401557, |
| "grad_norm": 0.35977280139923096, |
| "learning_rate": 4.997224694104561e-05, |
| "loss": 0.0524, |
| "step": 500 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_f1": 0.9528093236906681, |
| "eval_loss": 0.009147428907454014, |
| "eval_precision": 0.9461252678130232, |
| "eval_recall": 0.9597947571160605, |
| "eval_runtime": 32.73, |
| "eval_samples_per_second": 133.456, |
| "eval_steps_per_second": 4.186, |
| "step": 899 |
| }, |
| { |
| "epoch": 1.1123470522803114, |
| "grad_norm": 0.11930424720048904, |
| "learning_rate": 4.99444382647386e-05, |
| "loss": 0.0043, |
| "step": 1000 |
| }, |
| { |
| "epoch": 1.668520578420467, |
| "grad_norm": 0.12083794176578522, |
| "learning_rate": 4.991662958843159e-05, |
| "loss": 0.0026, |
| "step": 1500 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_f1": 0.9591844285588763, |
| "eval_loss": 0.009312924928963184, |
| "eval_precision": 0.9530780078627331, |
| "eval_recall": 0.9657284498000394, |
| "eval_runtime": 32.7085, |
| "eval_samples_per_second": 133.543, |
| "eval_steps_per_second": 4.189, |
| "step": 1798 |
| }, |
| { |
| "epoch": 2.2246941045606228, |
| "grad_norm": 0.012293193489313126, |
| "learning_rate": 4.988882091212459e-05, |
| "loss": 0.0015, |
| "step": 2000 |
| }, |
| { |
| "epoch": 2.7808676307007785, |
| "grad_norm": 0.005511277820914984, |
| "learning_rate": 4.986101223581758e-05, |
| "loss": 0.0014, |
| "step": 2500 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_f1": 0.9473572974918704, |
| "eval_loss": 0.013561395928263664, |
| "eval_precision": 0.9406871215514148, |
| "eval_recall": 0.9544992839810097, |
| "eval_runtime": 32.7338, |
| "eval_samples_per_second": 133.44, |
| "eval_steps_per_second": 4.185, |
| "step": 2697 |
| }, |
| { |
| "epoch": 3.337041156840934, |
| "grad_norm": 0.03908713161945343, |
| "learning_rate": 4.983320355951057e-05, |
| "loss": 0.0014, |
| "step": 3000 |
| }, |
| { |
| "epoch": 3.89321468298109, |
| "grad_norm": 0.009426549077033997, |
| "learning_rate": 4.980539488320356e-05, |
| "loss": 0.0016, |
| "step": 3500 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_f1": 0.953040195996418, |
| "eval_loss": 0.010148942470550537, |
| "eval_precision": 0.9406877737118386, |
| "eval_recall": 0.9674011453268957, |
| "eval_runtime": 32.788, |
| "eval_samples_per_second": 133.219, |
| "eval_steps_per_second": 4.178, |
| "step": 3596 |
| } |
| ], |
| "logging_steps": 500, |
| "max_steps": 899000, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 1000, |
| "save_steps": 500, |
| "stateful_callbacks": { |
| "EarlyStoppingCallback": { |
| "args": { |
| "early_stopping_patience": 3, |
| "early_stopping_threshold": 0.0 |
| }, |
| "attributes": { |
| "early_stopping_patience_counter": 3 |
| } |
| }, |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 3.006829642867507e+16, |
| "train_batch_size": 32, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
