| { | |
| "best_metric": 0.8460751725901304, | |
| "best_model_checkpoint": "./ner_models/checkpoint-5500", | |
| "epoch": 6.053935057787562, | |
| "eval_steps": 500, | |
| "global_step": 5500, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.550357732526142, | |
| "grad_norm": 0.050229188054800034, | |
| "learning_rate": 9.816446402349487e-06, | |
| "loss": 0.0026, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.550357732526142, | |
| "eval_accuracy": 0.9978579452614379, | |
| "eval_f1": 0.8398829963118403, | |
| "eval_loss": 0.008182315155863762, | |
| "eval_precision": 0.8228258160976826, | |
| "eval_recall": 0.8576623376623377, | |
| "eval_runtime": 73.1795, | |
| "eval_samples_per_second": 20.907, | |
| "eval_steps_per_second": 2.624, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.100715465052284, | |
| "grad_norm": 0.042086161673069, | |
| "learning_rate": 9.632892804698973e-06, | |
| "loss": 0.0021, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.100715465052284, | |
| "eval_accuracy": 0.9978592218137254, | |
| "eval_f1": 0.8371327254305978, | |
| "eval_loss": 0.008798174560070038, | |
| "eval_precision": 0.8168561542263965, | |
| "eval_recall": 0.8584415584415584, | |
| "eval_runtime": 73.2746, | |
| "eval_samples_per_second": 20.88, | |
| "eval_steps_per_second": 2.62, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.6510731975784259, | |
| "grad_norm": 0.038026291877031326, | |
| "learning_rate": 9.449339207048459e-06, | |
| "loss": 0.0018, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 1.6510731975784259, | |
| "eval_accuracy": 0.9978387969771242, | |
| "eval_f1": 0.8427194317605277, | |
| "eval_loss": 0.009040649980306625, | |
| "eval_precision": 0.8235002478929102, | |
| "eval_recall": 0.8628571428571429, | |
| "eval_runtime": 73.0885, | |
| "eval_samples_per_second": 20.934, | |
| "eval_steps_per_second": 2.627, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 2.201430930104568, | |
| "grad_norm": 0.022481152787804604, | |
| "learning_rate": 9.265785609397945e-06, | |
| "loss": 0.0017, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 2.201430930104568, | |
| "eval_accuracy": 0.9978349673202614, | |
| "eval_f1": 0.839443096180866, | |
| "eval_loss": 0.009410908445715904, | |
| "eval_precision": 0.8258356370947474, | |
| "eval_recall": 0.8535064935064935, | |
| "eval_runtime": 73.3567, | |
| "eval_samples_per_second": 20.857, | |
| "eval_steps_per_second": 2.617, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 2.7517886626307098, | |
| "grad_norm": 0.04910328611731529, | |
| "learning_rate": 9.08223201174743e-06, | |
| "loss": 0.0014, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 2.7517886626307098, | |
| "eval_accuracy": 0.9978770935457516, | |
| "eval_f1": 0.8429856798884806, | |
| "eval_loss": 0.009695506654679775, | |
| "eval_precision": 0.8230635981192774, | |
| "eval_recall": 0.8638961038961039, | |
| "eval_runtime": 72.9707, | |
| "eval_samples_per_second": 20.967, | |
| "eval_steps_per_second": 2.631, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 3.3021463951568517, | |
| "grad_norm": 0.028137343004345894, | |
| "learning_rate": 8.898678414096917e-06, | |
| "loss": 0.0013, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 3.3021463951568517, | |
| "eval_accuracy": 0.997820925245098, | |
| "eval_f1": 0.8397394968714085, | |
| "eval_loss": 0.010312107391655445, | |
| "eval_precision": 0.825923134890731, | |
| "eval_recall": 0.854025974025974, | |
| "eval_runtime": 72.7223, | |
| "eval_samples_per_second": 21.039, | |
| "eval_steps_per_second": 2.64, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 3.852504127682994, | |
| "grad_norm": 0.08884348720312119, | |
| "learning_rate": 8.715124816446402e-06, | |
| "loss": 0.0011, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 3.852504127682994, | |
| "eval_accuracy": 0.997820925245098, | |
| "eval_f1": 0.840376782077393, | |
| "eval_loss": 0.01055143028497696, | |
| "eval_precision": 0.8240139790314528, | |
| "eval_recall": 0.8574025974025974, | |
| "eval_runtime": 73.053, | |
| "eval_samples_per_second": 20.944, | |
| "eval_steps_per_second": 2.628, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 4.402861860209136, | |
| "grad_norm": 0.02799968421459198, | |
| "learning_rate": 8.531571218795888e-06, | |
| "loss": 0.001, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 4.402861860209136, | |
| "eval_accuracy": 0.9978222017973856, | |
| "eval_f1": 0.8401733367320928, | |
| "eval_loss": 0.011290175840258598, | |
| "eval_precision": 0.8248248248248248, | |
| "eval_recall": 0.8561038961038961, | |
| "eval_runtime": 72.7847, | |
| "eval_samples_per_second": 21.021, | |
| "eval_steps_per_second": 2.638, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 4.953219592735278, | |
| "grad_norm": 0.041495781391859055, | |
| "learning_rate": 8.348017621145376e-06, | |
| "loss": 0.0009, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 4.953219592735278, | |
| "eval_accuracy": 0.9977736928104575, | |
| "eval_f1": 0.8377070063694267, | |
| "eval_loss": 0.011407433077692986, | |
| "eval_precision": 0.822, | |
| "eval_recall": 0.854025974025974, | |
| "eval_runtime": 73.0522, | |
| "eval_samples_per_second": 20.944, | |
| "eval_steps_per_second": 2.628, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 5.5035773252614195, | |
| "grad_norm": 0.06250575184822083, | |
| "learning_rate": 8.164464023494862e-06, | |
| "loss": 0.0012, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 5.5035773252614195, | |
| "eval_accuracy": 0.9977622038398692, | |
| "eval_f1": 0.8407464212678937, | |
| "eval_loss": 0.01091926172375679, | |
| "eval_precision": 0.8276295923502768, | |
| "eval_recall": 0.8542857142857143, | |
| "eval_runtime": 75.4389, | |
| "eval_samples_per_second": 20.281, | |
| "eval_steps_per_second": 2.545, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 6.053935057787562, | |
| "grad_norm": 0.05719891935586929, | |
| "learning_rate": 7.980910425844346e-06, | |
| "loss": 0.0014, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 6.053935057787562, | |
| "eval_accuracy": 0.9978017769607843, | |
| "eval_f1": 0.8460751725901304, | |
| "eval_loss": 0.010837742127478123, | |
| "eval_precision": 0.8330815709969789, | |
| "eval_recall": 0.8594805194805195, | |
| "eval_runtime": 76.2331, | |
| "eval_samples_per_second": 20.07, | |
| "eval_steps_per_second": 2.519, | |
| "step": 5500 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 27240, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 30, | |
| "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": 4.597283514855014e+16, | |
| "train_batch_size": 16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |