| { |
| "best_metric": 0.22371177209886886, |
| "best_model_checkpoint": "/nfs/production/literature/amina-mardiyyah/new_data/OT-Entity-Extraction-Pipeline/model_outputs/Continued_pretraining/TAPT/Mardiyyah/biomedbert_model_extended_untrained/cellate-tapt_base-LR_2e-05/checkpoint-50", |
| "epoch": 8.363636363636363, |
| "eval_steps": 500, |
| "global_step": 50, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 1.0, |
| "grad_norm": 22.1080379486084, |
| "learning_rate": 1.9183673469387756e-05, |
| "loss": 10.133, |
| "step": 6 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_accuracy": 0.0, |
| "eval_loss": 10.35041332244873, |
| "eval_runtime": 0.7052, |
| "eval_samples_per_second": 43.957, |
| "eval_steps_per_second": 2.836, |
| "step": 6 |
| }, |
| { |
| "epoch": 2.0, |
| "grad_norm": 8.525097846984863, |
| "learning_rate": 1.673469387755102e-05, |
| "loss": 8.7383, |
| "step": 12 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_accuracy": 0.011311269375785506, |
| "eval_loss": 8.706360816955566, |
| "eval_runtime": 0.6712, |
| "eval_samples_per_second": 46.188, |
| "eval_steps_per_second": 2.98, |
| "step": 12 |
| }, |
| { |
| "epoch": 3.0, |
| "grad_norm": 4.951538562774658, |
| "learning_rate": 1.4285714285714287e-05, |
| "loss": 7.6303, |
| "step": 18 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_accuracy": 0.057813154587348134, |
| "eval_loss": 8.054218292236328, |
| "eval_runtime": 0.6857, |
| "eval_samples_per_second": 45.211, |
| "eval_steps_per_second": 2.917, |
| "step": 18 |
| }, |
| { |
| "epoch": 4.0, |
| "grad_norm": 4.658953666687012, |
| "learning_rate": 1.1836734693877552e-05, |
| "loss": 7.06, |
| "step": 24 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_accuracy": 0.08211143695014662, |
| "eval_loss": 7.551440238952637, |
| "eval_runtime": 0.6769, |
| "eval_samples_per_second": 45.798, |
| "eval_steps_per_second": 2.955, |
| "step": 24 |
| }, |
| { |
| "epoch": 5.0, |
| "grad_norm": 4.83123779296875, |
| "learning_rate": 9.387755102040818e-06, |
| "loss": 6.6524, |
| "step": 30 |
| }, |
| { |
| "epoch": 5.0, |
| "eval_accuracy": 0.15207373271889402, |
| "eval_loss": 7.070725440979004, |
| "eval_runtime": 0.6777, |
| "eval_samples_per_second": 45.742, |
| "eval_steps_per_second": 2.951, |
| "step": 30 |
| }, |
| { |
| "epoch": 6.0, |
| "grad_norm": 4.068853378295898, |
| "learning_rate": 6.938775510204082e-06, |
| "loss": 6.2891, |
| "step": 36 |
| }, |
| { |
| "epoch": 6.0, |
| "eval_accuracy": 0.1805613741097612, |
| "eval_loss": 6.90059232711792, |
| "eval_runtime": 0.6808, |
| "eval_samples_per_second": 45.536, |
| "eval_steps_per_second": 2.938, |
| "step": 36 |
| }, |
| { |
| "epoch": 7.0, |
| "grad_norm": 6.190578460693359, |
| "learning_rate": 4.489795918367348e-06, |
| "loss": 6.0336, |
| "step": 42 |
| }, |
| { |
| "epoch": 7.0, |
| "eval_accuracy": 0.210305823209049, |
| "eval_loss": 6.646459579467773, |
| "eval_runtime": 0.7705, |
| "eval_samples_per_second": 40.235, |
| "eval_steps_per_second": 2.596, |
| "step": 42 |
| }, |
| { |
| "epoch": 8.0, |
| "grad_norm": 4.320862293243408, |
| "learning_rate": 2.0408163265306125e-06, |
| "loss": 5.9085, |
| "step": 48 |
| }, |
| { |
| "epoch": 8.0, |
| "eval_accuracy": 0.22077922077922077, |
| "eval_loss": 6.615872383117676, |
| "eval_runtime": 0.679, |
| "eval_samples_per_second": 45.655, |
| "eval_steps_per_second": 2.945, |
| "step": 48 |
| }, |
| { |
| "epoch": 8.363636363636363, |
| "grad_norm": 6.226965427398682, |
| "learning_rate": 1.2244897959183673e-06, |
| "loss": 6.375, |
| "step": 50 |
| }, |
| { |
| "epoch": 8.363636363636363, |
| "eval_accuracy": 0.22371177209886886, |
| "eval_loss": 6.628802299499512, |
| "eval_runtime": 0.7625, |
| "eval_samples_per_second": 40.656, |
| "eval_steps_per_second": 2.623, |
| "step": 50 |
| }, |
| { |
| "epoch": 8.363636363636363, |
| "step": 50, |
| "total_flos": 368493460070400.0, |
| "train_loss": 7.268417072296143, |
| "train_runtime": 82.8209, |
| "train_samples_per_second": 20.164, |
| "train_steps_per_second": 0.604 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 50, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 10, |
| "save_steps": 500, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 368493460070400.0, |
| "train_batch_size": 16, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
