| { |
| "best_metric": 0.8438751000800641, |
| "best_model_checkpoint": "/nfs/production/literature/amina-mardiyyah/new_data/OT-Entity-Extraction-Pipeline/model_outputs/hf_cellfinder_conll-V1/bioformers/checkpoint-1221", |
| "epoch": 11.0, |
| "eval_steps": 500, |
| "global_step": 1221, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 1.0, |
| "grad_norm": 0.795136570930481, |
| "learning_rate": 1.901801801801802e-05, |
| "loss": 0.2939, |
| "step": 111 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_accuracy": 0.974508886810103, |
| "eval_f1": 0.578688524590164, |
| "eval_loss": 0.09425864368677139, |
| "eval_precision": 0.5952782462057336, |
| "eval_recall": 0.5629984051036683, |
| "eval_runtime": 9.1819, |
| "eval_samples_per_second": 48.356, |
| "eval_steps_per_second": 3.049, |
| "step": 111 |
| }, |
| { |
| "epoch": 2.0, |
| "grad_norm": 1.5788325071334839, |
| "learning_rate": 1.801801801801802e-05, |
| "loss": 0.0922, |
| "step": 222 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_accuracy": 0.9832787652011226, |
| "eval_f1": 0.7074601844090529, |
| "eval_loss": 0.060064926743507385, |
| "eval_precision": 0.7455830388692579, |
| "eval_recall": 0.6730462519936204, |
| "eval_runtime": 9.1954, |
| "eval_samples_per_second": 48.285, |
| "eval_steps_per_second": 3.045, |
| "step": 222 |
| }, |
| { |
| "epoch": 3.0, |
| "grad_norm": 1.0079556703567505, |
| "learning_rate": 1.701801801801802e-05, |
| "loss": 0.066, |
| "step": 333 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_accuracy": 0.9841557530402245, |
| "eval_f1": 0.7742435996896818, |
| "eval_loss": 0.054448943585157394, |
| "eval_precision": 0.7537764350453172, |
| "eval_recall": 0.79585326953748, |
| "eval_runtime": 9.1805, |
| "eval_samples_per_second": 48.363, |
| "eval_steps_per_second": 3.05, |
| "step": 333 |
| }, |
| { |
| "epoch": 4.0, |
| "grad_norm": 1.0463738441467285, |
| "learning_rate": 1.601801801801802e-05, |
| "loss": 0.05, |
| "step": 444 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_accuracy": 0.9860851262862488, |
| "eval_f1": 0.801261829652997, |
| "eval_loss": 0.05010896548628807, |
| "eval_precision": 0.7925117004680188, |
| "eval_recall": 0.810207336523126, |
| "eval_runtime": 9.1685, |
| "eval_samples_per_second": 48.427, |
| "eval_steps_per_second": 3.054, |
| "step": 444 |
| }, |
| { |
| "epoch": 5.0, |
| "grad_norm": 1.8808237314224243, |
| "learning_rate": 1.5018018018018019e-05, |
| "loss": 0.0384, |
| "step": 555 |
| }, |
| { |
| "epoch": 5.0, |
| "eval_accuracy": 0.9872544434050514, |
| "eval_f1": 0.8314960629921261, |
| "eval_loss": 0.047017596662044525, |
| "eval_precision": 0.8211508553654744, |
| "eval_recall": 0.8421052631578947, |
| "eval_runtime": 9.141, |
| "eval_samples_per_second": 48.573, |
| "eval_steps_per_second": 3.063, |
| "step": 555 |
| }, |
| { |
| "epoch": 6.0, |
| "grad_norm": 0.8775511980056763, |
| "learning_rate": 1.4018018018018018e-05, |
| "loss": 0.0316, |
| "step": 666 |
| }, |
| { |
| "epoch": 6.0, |
| "eval_accuracy": 0.9878975678203928, |
| "eval_f1": 0.819935691318328, |
| "eval_loss": 0.0532170832157135, |
| "eval_precision": 0.826580226904376, |
| "eval_recall": 0.8133971291866029, |
| "eval_runtime": 9.3828, |
| "eval_samples_per_second": 47.321, |
| "eval_steps_per_second": 2.984, |
| "step": 666 |
| }, |
| { |
| "epoch": 7.0, |
| "grad_norm": 2.152559757232666, |
| "learning_rate": 1.301801801801802e-05, |
| "loss": 0.0261, |
| "step": 777 |
| }, |
| { |
| "epoch": 7.0, |
| "eval_accuracy": 0.987488306828812, |
| "eval_f1": 0.812807881773399, |
| "eval_loss": 0.050550468266010284, |
| "eval_precision": 0.8375634517766497, |
| "eval_recall": 0.7894736842105263, |
| "eval_runtime": 9.3573, |
| "eval_samples_per_second": 47.449, |
| "eval_steps_per_second": 2.992, |
| "step": 777 |
| }, |
| { |
| "epoch": 8.0, |
| "grad_norm": 0.400267630815506, |
| "learning_rate": 1.2018018018018019e-05, |
| "loss": 0.0228, |
| "step": 888 |
| }, |
| { |
| "epoch": 8.0, |
| "eval_accuracy": 0.9872544434050514, |
| "eval_f1": 0.825296442687747, |
| "eval_loss": 0.05137129873037338, |
| "eval_precision": 0.8181818181818182, |
| "eval_recall": 0.8325358851674641, |
| "eval_runtime": 9.3986, |
| "eval_samples_per_second": 47.241, |
| "eval_steps_per_second": 2.979, |
| "step": 888 |
| }, |
| { |
| "epoch": 9.0, |
| "grad_norm": 0.5100765228271484, |
| "learning_rate": 1.101801801801802e-05, |
| "loss": 0.0189, |
| "step": 999 |
| }, |
| { |
| "epoch": 9.0, |
| "eval_accuracy": 0.9877221702525725, |
| "eval_f1": 0.8288726682887267, |
| "eval_loss": 0.05429461598396301, |
| "eval_precision": 0.8432343234323433, |
| "eval_recall": 0.8149920255183413, |
| "eval_runtime": 9.1439, |
| "eval_samples_per_second": 48.557, |
| "eval_steps_per_second": 3.062, |
| "step": 999 |
| }, |
| { |
| "epoch": 10.0, |
| "grad_norm": 2.543349266052246, |
| "learning_rate": 1.001801801801802e-05, |
| "loss": 0.0162, |
| "step": 1110 |
| }, |
| { |
| "epoch": 10.0, |
| "eval_accuracy": 0.9881314312441534, |
| "eval_f1": 0.8352180936995154, |
| "eval_loss": 0.05771711841225624, |
| "eval_precision": 0.8461538461538461, |
| "eval_recall": 0.8245614035087719, |
| "eval_runtime": 9.1278, |
| "eval_samples_per_second": 48.642, |
| "eval_steps_per_second": 3.068, |
| "step": 1110 |
| }, |
| { |
| "epoch": 11.0, |
| "grad_norm": 0.7831849455833435, |
| "learning_rate": 9.018018018018019e-06, |
| "loss": 0.0142, |
| "step": 1221 |
| }, |
| { |
| "epoch": 11.0, |
| "eval_accuracy": 0.9886576239476146, |
| "eval_f1": 0.8438751000800641, |
| "eval_loss": 0.05389339104294777, |
| "eval_precision": 0.8472668810289389, |
| "eval_recall": 0.8405103668261563, |
| "eval_runtime": 9.1654, |
| "eval_samples_per_second": 48.443, |
| "eval_steps_per_second": 3.055, |
| "step": 1221 |
| } |
| ], |
| "logging_steps": 500, |
| "max_steps": 2220, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 20, |
| "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": 1622782443811692.0, |
| "train_batch_size": 16, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
