| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.0, | |
| "eval_steps": 25, | |
| "global_step": 294, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.17006802721088435, | |
| "grad_norm": 1.6777013540267944, | |
| "learning_rate": 2.0833333333333336e-05, | |
| "loss": 0.6393, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.17006802721088435, | |
| "eval_accuracy": 0.8759578544061303, | |
| "eval_auc": 0.9551645887113986, | |
| "eval_f1": 0.7757575757575758, | |
| "eval_loss": 0.4472915232181549, | |
| "eval_precision": 0.9032258064516129, | |
| "eval_recall": 0.6798179059180577, | |
| "eval_runtime": 3.1514, | |
| "eval_samples_per_second": 662.564, | |
| "eval_steps_per_second": 2.856, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.3401360544217687, | |
| "grad_norm": 1.745863676071167, | |
| "learning_rate": 2.464764460404427e-05, | |
| "loss": 0.2377, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.3401360544217687, | |
| "eval_accuracy": 0.9439655172413793, | |
| "eval_auc": 0.9875004114850522, | |
| "eval_f1": 0.9164882226980728, | |
| "eval_loss": 0.15234950184822083, | |
| "eval_precision": 0.8652291105121294, | |
| "eval_recall": 0.9742033383915023, | |
| "eval_runtime": 3.1506, | |
| "eval_samples_per_second": 662.733, | |
| "eval_steps_per_second": 2.857, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.5102040816326531, | |
| "grad_norm": 2.064204454421997, | |
| "learning_rate": 2.3250178002596257e-05, | |
| "loss": 0.1276, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.5102040816326531, | |
| "eval_accuracy": 0.9640804597701149, | |
| "eval_auc": 0.9937093227115326, | |
| "eval_f1": 0.9433106575963719, | |
| "eval_loss": 0.09969615936279297, | |
| "eval_precision": 0.9397590361445783, | |
| "eval_recall": 0.9468892261001517, | |
| "eval_runtime": 3.1599, | |
| "eval_samples_per_second": 660.782, | |
| "eval_steps_per_second": 2.848, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.6802721088435374, | |
| "grad_norm": 1.5831186771392822, | |
| "learning_rate": 2.090825467126566e-05, | |
| "loss": 0.1035, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.6802721088435374, | |
| "eval_accuracy": 0.9664750957854407, | |
| "eval_auc": 0.9949464326104294, | |
| "eval_f1": 0.9470499243570348, | |
| "eval_loss": 0.08703920990228653, | |
| "eval_precision": 0.9441930618401206, | |
| "eval_recall": 0.9499241274658573, | |
| "eval_runtime": 3.1587, | |
| "eval_samples_per_second": 661.03, | |
| "eval_steps_per_second": 2.849, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.8503401360544217, | |
| "grad_norm": 1.721102237701416, | |
| "learning_rate": 1.7827624249789604e-05, | |
| "loss": 0.0727, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.8503401360544217, | |
| "eval_accuracy": 0.9669540229885057, | |
| "eval_auc": 0.9950313843631433, | |
| "eval_f1": 0.9473684210526315, | |
| "eval_loss": 0.08850479125976562, | |
| "eval_precision": 0.9524539877300614, | |
| "eval_recall": 0.9423368740515933, | |
| "eval_runtime": 3.1669, | |
| "eval_samples_per_second": 659.316, | |
| "eval_steps_per_second": 2.842, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 1.0204081632653061, | |
| "grad_norm": 1.1454665660858154, | |
| "learning_rate": 1.4278935478416066e-05, | |
| "loss": 0.0885, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 1.0204081632653061, | |
| "eval_accuracy": 0.9712643678160919, | |
| "eval_auc": 0.9956770176837693, | |
| "eval_f1": 0.9541984732824428, | |
| "eval_loss": 0.08041754364967346, | |
| "eval_precision": 0.9600614439324117, | |
| "eval_recall": 0.9484066767830045, | |
| "eval_runtime": 3.1728, | |
| "eval_samples_per_second": 658.102, | |
| "eval_steps_per_second": 2.837, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 1.1904761904761905, | |
| "grad_norm": 0.6928611397743225, | |
| "learning_rate": 1.0573958356820683e-05, | |
| "loss": 0.0614, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 1.1904761904761905, | |
| "eval_accuracy": 0.9746168582375478, | |
| "eval_auc": 0.9961580569835119, | |
| "eval_f1": 0.9594491201224178, | |
| "eval_loss": 0.07542683929204941, | |
| "eval_precision": 0.9675925925925926, | |
| "eval_recall": 0.9514415781487102, | |
| "eval_runtime": 3.1686, | |
| "eval_samples_per_second": 658.971, | |
| "eval_steps_per_second": 2.84, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 1.3605442176870748, | |
| "grad_norm": 0.8894994854927063, | |
| "learning_rate": 7.038193595383008e-06, | |
| "loss": 0.0448, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.3605442176870748, | |
| "eval_accuracy": 0.9712643678160919, | |
| "eval_auc": 0.9961644283649654, | |
| "eval_f1": 0.9541984732824428, | |
| "eval_loss": 0.07568268477916718, | |
| "eval_precision": 0.9600614439324117, | |
| "eval_recall": 0.9484066767830045, | |
| "eval_runtime": 3.162, | |
| "eval_samples_per_second": 660.342, | |
| "eval_steps_per_second": 2.846, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.5306122448979593, | |
| "grad_norm": 0.8013057708740234, | |
| "learning_rate": 3.98227575507636e-06, | |
| "loss": 0.0547, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 1.5306122448979593, | |
| "eval_accuracy": 0.9717432950191571, | |
| "eval_auc": 0.9963555698085719, | |
| "eval_f1": 0.954858454475899, | |
| "eval_loss": 0.07406975328922272, | |
| "eval_precision": 0.9629629629629629, | |
| "eval_recall": 0.9468892261001517, | |
| "eval_runtime": 3.1666, | |
| "eval_samples_per_second": 659.381, | |
| "eval_steps_per_second": 2.842, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 1.7006802721088436, | |
| "grad_norm": 1.3701196908950806, | |
| "learning_rate": 1.6746824526945163e-06, | |
| "loss": 0.048, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 1.7006802721088436, | |
| "eval_accuracy": 0.9746168582375478, | |
| "eval_auc": 0.9967229861390597, | |
| "eval_f1": 0.9601203912716328, | |
| "eval_loss": 0.07189524918794632, | |
| "eval_precision": 0.9522388059701492, | |
| "eval_recall": 0.9681335356600911, | |
| "eval_runtime": 3.1579, | |
| "eval_samples_per_second": 661.202, | |
| "eval_steps_per_second": 2.85, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 1.870748299319728, | |
| "grad_norm": 1.6245123147964478, | |
| "learning_rate": 3.181472637875868e-07, | |
| "loss": 0.0473, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 1.870748299319728, | |
| "eval_accuracy": 0.975095785440613, | |
| "eval_auc": 0.9967537811494185, | |
| "eval_f1": 0.9606060606060606, | |
| "eval_loss": 0.07112736254930496, | |
| "eval_precision": 0.9591527987897126, | |
| "eval_recall": 0.9620637329286799, | |
| "eval_runtime": 3.1642, | |
| "eval_samples_per_second": 659.887, | |
| "eval_steps_per_second": 2.844, | |
| "step": 275 | |
| } | |
| ], | |
| "logging_steps": 25, | |
| "max_steps": 294, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 3, | |
| "early_stopping_threshold": 0.01 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 4985013284110336.0, | |
| "train_batch_size": 32, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |