| { |
| "best_global_step": 476, |
| "best_metric": 0.010661174543201923, |
| "best_model_checkpoint": "projects/PetBERT_annonymisation/data/augment/checkpoint-476", |
| "epoch": 4.0, |
| "eval_steps": 500, |
| "global_step": 1904, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0, |
| "eval_f1": 0.035302169832600705, |
| "eval_loss": 2.312753200531006, |
| "eval_precision": 0.09090508818188361, |
| "eval_recall": 0.06752732472754598, |
| "eval_runtime": 12.3558, |
| "eval_samples_per_second": 134.107, |
| "eval_steps_per_second": 4.209, |
| "step": 0 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_f1": 0.8995538111348774, |
| "eval_loss": 0.010661174543201923, |
| "eval_precision": 0.8815916042183172, |
| "eval_recall": 0.9190286419243201, |
| "eval_runtime": 12.59, |
| "eval_samples_per_second": 131.612, |
| "eval_steps_per_second": 4.13, |
| "step": 476 |
| }, |
| { |
| "epoch": 1.050420168067227, |
| "grad_norm": 0.16209110617637634, |
| "learning_rate": 4.994758403361345e-05, |
| "loss": 0.0477, |
| "step": 500 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_f1": 0.9230744441736807, |
| "eval_loss": 0.010812721215188503, |
| "eval_precision": 0.8937084772102274, |
| "eval_recall": 0.9571896846985819, |
| "eval_runtime": 12.587, |
| "eval_samples_per_second": 131.644, |
| "eval_steps_per_second": 4.131, |
| "step": 952 |
| }, |
| { |
| "epoch": 2.100840336134454, |
| "grad_norm": 0.012455416843295097, |
| "learning_rate": 4.989506302521009e-05, |
| "loss": 0.0056, |
| "step": 1000 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_f1": 0.9348757835672437, |
| "eval_loss": 0.01099320687353611, |
| "eval_precision": 0.9214871357949422, |
| "eval_recall": 0.9494909444630193, |
| "eval_runtime": 12.579, |
| "eval_samples_per_second": 131.728, |
| "eval_steps_per_second": 4.134, |
| "step": 1428 |
| }, |
| { |
| "epoch": 3.1512605042016806, |
| "grad_norm": 0.015093757770955563, |
| "learning_rate": 4.9842542016806724e-05, |
| "loss": 0.0029, |
| "step": 1500 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_f1": 0.9105180723758415, |
| "eval_loss": 0.012333991006016731, |
| "eval_precision": 0.8738638072175106, |
| "eval_recall": 0.9524189376430204, |
| "eval_runtime": 12.6079, |
| "eval_samples_per_second": 131.426, |
| "eval_steps_per_second": 4.124, |
| "step": 1904 |
| } |
| ], |
| "logging_steps": 500, |
| "max_steps": 476000, |
| "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": 1.5921584203628544e+16, |
| "train_batch_size": 32, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
