| { | |
| "best_metric": 0.9280074314909428, | |
| "best_model_checkpoint": "/content/dissertation/scripts/ner/output/checkpoint-4480", | |
| "epoch": 10.0, | |
| "eval_steps": 500, | |
| "global_step": 4480, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.9985976613735942, | |
| "eval_f1": 0.9184549356223176, | |
| "eval_loss": 0.005405870731920004, | |
| "eval_precision": 0.9404296875, | |
| "eval_recall": 0.8974836905871388, | |
| "eval_runtime": 15.084, | |
| "eval_samples_per_second": 460.487, | |
| "eval_steps_per_second": 57.611, | |
| "step": 448 | |
| }, | |
| { | |
| "epoch": 1.1160714285714286, | |
| "grad_norm": 0.0893813744187355, | |
| "learning_rate": 4.4419642857142854e-05, | |
| "loss": 0.016, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.9985627773281612, | |
| "eval_f1": 0.9166278528178854, | |
| "eval_loss": 0.004539168905466795, | |
| "eval_precision": 0.9162011173184358, | |
| "eval_recall": 0.9170549860205033, | |
| "eval_runtime": 15.2132, | |
| "eval_samples_per_second": 456.577, | |
| "eval_steps_per_second": 57.121, | |
| "step": 896 | |
| }, | |
| { | |
| "epoch": 2.232142857142857, | |
| "grad_norm": 0.01820996217429638, | |
| "learning_rate": 3.883928571428572e-05, | |
| "loss": 0.0039, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.998548823709988, | |
| "eval_f1": 0.9221611721611722, | |
| "eval_loss": 0.005798548460006714, | |
| "eval_precision": 0.9063906390639064, | |
| "eval_recall": 0.9384902143522833, | |
| "eval_runtime": 15.0713, | |
| "eval_samples_per_second": 460.875, | |
| "eval_steps_per_second": 57.659, | |
| "step": 1344 | |
| }, | |
| { | |
| "epoch": 3.3482142857142856, | |
| "grad_norm": 0.09450385719537735, | |
| "learning_rate": 3.325892857142857e-05, | |
| "loss": 0.0022, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.998513939664555, | |
| "eval_f1": 0.9151459854014599, | |
| "eval_loss": 0.005682563409209251, | |
| "eval_precision": 0.8963360142984808, | |
| "eval_recall": 0.934762348555452, | |
| "eval_runtime": 15.3704, | |
| "eval_samples_per_second": 451.907, | |
| "eval_steps_per_second": 56.537, | |
| "step": 1792 | |
| }, | |
| { | |
| "epoch": 4.464285714285714, | |
| "grad_norm": 0.08753237873315811, | |
| "learning_rate": 2.767857142857143e-05, | |
| "loss": 0.0017, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.9987023135098931, | |
| "eval_f1": 0.9271217712177122, | |
| "eval_loss": 0.005979395937174559, | |
| "eval_precision": 0.9178082191780822, | |
| "eval_recall": 0.9366262814538676, | |
| "eval_runtime": 15.1424, | |
| "eval_samples_per_second": 458.713, | |
| "eval_steps_per_second": 57.389, | |
| "step": 2240 | |
| }, | |
| { | |
| "epoch": 5.580357142857143, | |
| "grad_norm": 0.010990791022777557, | |
| "learning_rate": 2.2098214285714286e-05, | |
| "loss": 0.0012, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.9987092903189797, | |
| "eval_f1": 0.9254426840633737, | |
| "eval_loss": 0.006339639890938997, | |
| "eval_precision": 0.9254426840633737, | |
| "eval_recall": 0.9254426840633737, | |
| "eval_runtime": 15.1172, | |
| "eval_samples_per_second": 459.478, | |
| "eval_steps_per_second": 57.484, | |
| "step": 2688 | |
| }, | |
| { | |
| "epoch": 6.696428571428571, | |
| "grad_norm": 0.0010647091548889875, | |
| "learning_rate": 1.6517857142857144e-05, | |
| "loss": 0.0008, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_accuracy": 0.9986116149917673, | |
| "eval_f1": 0.9260450160771704, | |
| "eval_loss": 0.0069307987578213215, | |
| "eval_precision": 0.9130434782608695, | |
| "eval_recall": 0.9394221808014911, | |
| "eval_runtime": 15.1162, | |
| "eval_samples_per_second": 459.508, | |
| "eval_steps_per_second": 57.488, | |
| "step": 3136 | |
| }, | |
| { | |
| "epoch": 7.8125, | |
| "grad_norm": 0.0007633898057974875, | |
| "learning_rate": 1.09375e-05, | |
| "loss": 0.0005, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.9986395222281137, | |
| "eval_f1": 0.9252900232018563, | |
| "eval_loss": 0.006891186349093914, | |
| "eval_precision": 0.9214417744916821, | |
| "eval_recall": 0.9291705498602051, | |
| "eval_runtime": 15.1611, | |
| "eval_samples_per_second": 458.146, | |
| "eval_steps_per_second": 57.318, | |
| "step": 3584 | |
| }, | |
| { | |
| "epoch": 8.928571428571429, | |
| "grad_norm": 0.0015532037941738963, | |
| "learning_rate": 5.357142857142857e-06, | |
| "loss": 0.0004, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_accuracy": 0.9986534758462869, | |
| "eval_f1": 0.9270106927010694, | |
| "eval_loss": 0.0076610674150288105, | |
| "eval_precision": 0.924860853432282, | |
| "eval_recall": 0.9291705498602051, | |
| "eval_runtime": 15.344, | |
| "eval_samples_per_second": 452.684, | |
| "eval_steps_per_second": 56.634, | |
| "step": 4032 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_accuracy": 0.9986883598917199, | |
| "eval_f1": 0.9280074314909428, | |
| "eval_loss": 0.007708101533353329, | |
| "eval_precision": 0.925, | |
| "eval_recall": 0.9310344827586207, | |
| "eval_runtime": 15.1825, | |
| "eval_samples_per_second": 457.501, | |
| "eval_steps_per_second": 57.237, | |
| "step": 4480 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "step": 4480, | |
| "total_flos": 1.178126279062056e+16, | |
| "train_loss": 0.0030171065125614406, | |
| "train_runtime": 1889.6824, | |
| "train_samples_per_second": 151.708, | |
| "train_steps_per_second": 2.371 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 4480, | |
| "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": 1.178126279062056e+16, | |
| "train_batch_size": 32, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |