| { |
| "best_metric": 0.7492123503465657, |
| "best_model_checkpoint": "/nfs/production/literature/amina-mardiyyah/new_data/Ner_Pipeline/src/ner_pipeline/model_outputs/NER/CeLLaTe_2_Class_1.0/BiomedNLP_BiomedBERT_base_uncased_abstract/BaseStrategy/StandardNerHead/BaseTrainer/no_data_aug/checkpoint-1052", |
| "epoch": 7.0, |
| "eval_steps": 100, |
| "global_step": 1841, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 1.0, |
| "grad_norm": 0.8261250257492065, |
| "learning_rate": 1.9204916458613406e-05, |
| "loss": 0.2418, |
| "step": 263 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_accuracy": 0.9794236594074149, |
| "eval_f1": 0.6608890131395024, |
| "eval_loss": 0.06121203675866127, |
| "eval_precision": 0.6099071207430341, |
| "eval_recall": 0.7211714460036608, |
| "step": 263 |
| }, |
| { |
| "epoch": 2.0, |
| "grad_norm": 0.3401033580303192, |
| "learning_rate": 1.819473785289034e-05, |
| "loss": 0.0403, |
| "step": 526 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_accuracy": 0.983417093930318, |
| "eval_f1": 0.7395377888819488, |
| "eval_loss": 0.05201728269457817, |
| "eval_precision": 0.7575175943698017, |
| "eval_recall": 0.7223917022574741, |
| "step": 526 |
| }, |
| { |
| "epoch": 3.0, |
| "grad_norm": 0.4749569892883301, |
| "learning_rate": 1.7184559247167276e-05, |
| "loss": 0.0258, |
| "step": 789 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_accuracy": 0.9829263752813172, |
| "eval_f1": 0.740989615149664, |
| "eval_loss": 0.06125689297914505, |
| "eval_precision": 0.7418960244648318, |
| "eval_recall": 0.7400854179377669, |
| "step": 789 |
| }, |
| { |
| "epoch": 4.0, |
| "grad_norm": 0.8778874278068542, |
| "learning_rate": 1.617438064144421e-05, |
| "loss": 0.0196, |
| "step": 1052 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_accuracy": 0.9838570485811462, |
| "eval_f1": 0.7492123503465657, |
| "eval_loss": 0.06435362249612808, |
| "eval_precision": 0.7745928338762215, |
| "eval_recall": 0.7254423428920074, |
| "step": 1052 |
| }, |
| { |
| "epoch": 5.0, |
| "grad_norm": 0.05232912302017212, |
| "learning_rate": 1.5164202035721145e-05, |
| "loss": 0.0145, |
| "step": 1315 |
| }, |
| { |
| "epoch": 5.0, |
| "eval_accuracy": 0.9831463526067313, |
| "eval_f1": 0.7380191693290735, |
| "eval_loss": 0.06831890344619751, |
| "eval_precision": 0.7746478873239436, |
| "eval_recall": 0.7046979865771812, |
| "step": 1315 |
| }, |
| { |
| "epoch": 6.0, |
| "grad_norm": 0.022152185440063477, |
| "learning_rate": 1.415402342999808e-05, |
| "loss": 0.011, |
| "step": 1578 |
| }, |
| { |
| "epoch": 6.0, |
| "eval_accuracy": 0.9830955886085588, |
| "eval_f1": 0.7345776652957926, |
| "eval_loss": 0.07682684063911438, |
| "eval_precision": 0.7628120893561103, |
| "eval_recall": 0.7083587553386211, |
| "step": 1578 |
| }, |
| { |
| "epoch": 7.0, |
| "grad_norm": 0.0060246409848332405, |
| "learning_rate": 1.3143844824275017e-05, |
| "loss": 0.0086, |
| "step": 1841 |
| }, |
| { |
| "epoch": 7.0, |
| "eval_accuracy": 0.9837893632502496, |
| "eval_f1": 0.7458766035430666, |
| "eval_loss": 0.07318853586912155, |
| "eval_precision": 0.7467889908256881, |
| "eval_recall": 0.7449664429530202, |
| "step": 1841 |
| }, |
| { |
| "epoch": 7.0, |
| "step": 1841, |
| "total_flos": 1490490904958250.0, |
| "train_loss": 0.05166175364152949, |
| "train_runtime": 318.4852, |
| "train_samples_per_second": 528.062, |
| "train_steps_per_second": 16.516 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 5260, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 20, |
| "save_steps": 100, |
| "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": 1490490904958250.0, |
| "train_batch_size": 16, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
