| { | |
| "best_metric": 0.877387523651123, | |
| "best_model_checkpoint": "autotrain-8c1y5-lsgog/checkpoint-588", | |
| "epoch": 3.0, | |
| "eval_steps": 500, | |
| "global_step": 588, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.04591836734693878, | |
| "grad_norm": 13.273290634155273, | |
| "learning_rate": 5.932203389830509e-06, | |
| "loss": 1.3557, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.09183673469387756, | |
| "grad_norm": Infinity, | |
| "learning_rate": 1.2711864406779661e-05, | |
| "loss": 1.4241, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.1377551020408163, | |
| "grad_norm": 16.573213577270508, | |
| "learning_rate": 2.033898305084746e-05, | |
| "loss": 1.3423, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.1836734693877551, | |
| "grad_norm": 11.559469223022461, | |
| "learning_rate": 2.7966101694915255e-05, | |
| "loss": 1.3488, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.22959183673469388, | |
| "grad_norm": 13.121813774108887, | |
| "learning_rate": 3.474576271186441e-05, | |
| "loss": 1.2955, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.2755102040816326, | |
| "grad_norm": 19.90020179748535, | |
| "learning_rate": 4.152542372881356e-05, | |
| "loss": 1.3652, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.32142857142857145, | |
| "grad_norm": 42.38658142089844, | |
| "learning_rate": 4.915254237288136e-05, | |
| "loss": 1.3228, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.3673469387755102, | |
| "grad_norm": 16.879314422607422, | |
| "learning_rate": 4.9243856332703216e-05, | |
| "loss": 1.4373, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.413265306122449, | |
| "grad_norm": 10.268380165100098, | |
| "learning_rate": 4.839319470699433e-05, | |
| "loss": 1.4207, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.45918367346938777, | |
| "grad_norm": 49.17950439453125, | |
| "learning_rate": 4.754253308128545e-05, | |
| "loss": 1.3291, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.5051020408163265, | |
| "grad_norm": 10.70398235321045, | |
| "learning_rate": 4.669187145557656e-05, | |
| "loss": 1.2806, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.5510204081632653, | |
| "grad_norm": 14.200324058532715, | |
| "learning_rate": 4.584120982986768e-05, | |
| "loss": 1.5323, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 0.5969387755102041, | |
| "grad_norm": 13.224357604980469, | |
| "learning_rate": 4.499054820415879e-05, | |
| "loss": 1.3381, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 0.6428571428571429, | |
| "grad_norm": 12.96914291381836, | |
| "learning_rate": 4.413988657844991e-05, | |
| "loss": 1.3752, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 0.6887755102040817, | |
| "grad_norm": 9.912948608398438, | |
| "learning_rate": 4.3289224952741024e-05, | |
| "loss": 1.2576, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.7346938775510204, | |
| "grad_norm": 8.655780792236328, | |
| "learning_rate": 4.243856332703214e-05, | |
| "loss": 1.1475, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 0.7806122448979592, | |
| "grad_norm": 6.818447113037109, | |
| "learning_rate": 4.158790170132325e-05, | |
| "loss": 1.1608, | |
| "step": 153 | |
| }, | |
| { | |
| "epoch": 0.826530612244898, | |
| "grad_norm": 36.97886276245117, | |
| "learning_rate": 4.073724007561437e-05, | |
| "loss": 1.0747, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 0.8724489795918368, | |
| "grad_norm": 18.22942543029785, | |
| "learning_rate": 3.988657844990548e-05, | |
| "loss": 1.0558, | |
| "step": 171 | |
| }, | |
| { | |
| "epoch": 0.9183673469387755, | |
| "grad_norm": 14.418513298034668, | |
| "learning_rate": 3.90359168241966e-05, | |
| "loss": 1.1605, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.9642857142857143, | |
| "grad_norm": 17.860261917114258, | |
| "learning_rate": 3.8185255198487716e-05, | |
| "loss": 1.236, | |
| "step": 189 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.5357142857142857, | |
| "eval_f1_macro": 0.5169015312293899, | |
| "eval_f1_micro": 0.5357142857142857, | |
| "eval_f1_weighted": 0.5169015312293898, | |
| "eval_loss": 1.0397837162017822, | |
| "eval_precision_macro": 0.6040472568054893, | |
| "eval_precision_micro": 0.5357142857142857, | |
| "eval_precision_weighted": 0.6040472568054893, | |
| "eval_recall_macro": 0.5357142857142857, | |
| "eval_recall_micro": 0.5357142857142857, | |
| "eval_recall_weighted": 0.5357142857142857, | |
| "eval_runtime": 0.8403, | |
| "eval_samples_per_second": 466.478, | |
| "eval_steps_per_second": 29.75, | |
| "step": 196 | |
| }, | |
| { | |
| "epoch": 1.010204081632653, | |
| "grad_norm": 10.591184616088867, | |
| "learning_rate": 3.733459357277883e-05, | |
| "loss": 1.0559, | |
| "step": 198 | |
| }, | |
| { | |
| "epoch": 1.0561224489795917, | |
| "grad_norm": 20.194005966186523, | |
| "learning_rate": 3.648393194706995e-05, | |
| "loss": 1.0911, | |
| "step": 207 | |
| }, | |
| { | |
| "epoch": 1.1020408163265305, | |
| "grad_norm": 11.607887268066406, | |
| "learning_rate": 3.563327032136106e-05, | |
| "loss": 0.9098, | |
| "step": 216 | |
| }, | |
| { | |
| "epoch": 1.1479591836734695, | |
| "grad_norm": 29.328445434570312, | |
| "learning_rate": 3.478260869565218e-05, | |
| "loss": 0.9996, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 1.193877551020408, | |
| "grad_norm": 12.970704078674316, | |
| "learning_rate": 3.393194706994329e-05, | |
| "loss": 0.8921, | |
| "step": 234 | |
| }, | |
| { | |
| "epoch": 1.239795918367347, | |
| "grad_norm": 11.346271514892578, | |
| "learning_rate": 3.308128544423441e-05, | |
| "loss": 0.7828, | |
| "step": 243 | |
| }, | |
| { | |
| "epoch": 1.2857142857142856, | |
| "grad_norm": 26.86040687561035, | |
| "learning_rate": 3.2230623818525524e-05, | |
| "loss": 0.9659, | |
| "step": 252 | |
| }, | |
| { | |
| "epoch": 1.3316326530612246, | |
| "grad_norm": 54.28874969482422, | |
| "learning_rate": 3.137996219281664e-05, | |
| "loss": 0.8242, | |
| "step": 261 | |
| }, | |
| { | |
| "epoch": 1.3775510204081631, | |
| "grad_norm": 23.010454177856445, | |
| "learning_rate": 3.052930056710775e-05, | |
| "loss": 0.9375, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 1.4234693877551021, | |
| "grad_norm": 35.56595230102539, | |
| "learning_rate": 2.9678638941398867e-05, | |
| "loss": 0.8834, | |
| "step": 279 | |
| }, | |
| { | |
| "epoch": 1.469387755102041, | |
| "grad_norm": 20.237417221069336, | |
| "learning_rate": 2.882797731568998e-05, | |
| "loss": 1.2205, | |
| "step": 288 | |
| }, | |
| { | |
| "epoch": 1.5153061224489797, | |
| "grad_norm": 17.17922019958496, | |
| "learning_rate": 2.7977315689981097e-05, | |
| "loss": 1.1868, | |
| "step": 297 | |
| }, | |
| { | |
| "epoch": 1.5612244897959182, | |
| "grad_norm": 36.083892822265625, | |
| "learning_rate": 2.7126654064272213e-05, | |
| "loss": 0.7935, | |
| "step": 306 | |
| }, | |
| { | |
| "epoch": 1.6071428571428572, | |
| "grad_norm": 12.143678665161133, | |
| "learning_rate": 2.6275992438563328e-05, | |
| "loss": 0.8405, | |
| "step": 315 | |
| }, | |
| { | |
| "epoch": 1.6530612244897958, | |
| "grad_norm": 17.92725944519043, | |
| "learning_rate": 2.5425330812854444e-05, | |
| "loss": 0.9103, | |
| "step": 324 | |
| }, | |
| { | |
| "epoch": 1.6989795918367347, | |
| "grad_norm": 8.833161354064941, | |
| "learning_rate": 2.457466918714556e-05, | |
| "loss": 0.8916, | |
| "step": 333 | |
| }, | |
| { | |
| "epoch": 1.7448979591836735, | |
| "grad_norm": 16.942583084106445, | |
| "learning_rate": 2.3724007561436674e-05, | |
| "loss": 0.8364, | |
| "step": 342 | |
| }, | |
| { | |
| "epoch": 1.7908163265306123, | |
| "grad_norm": 52.1734733581543, | |
| "learning_rate": 2.287334593572779e-05, | |
| "loss": 1.0671, | |
| "step": 351 | |
| }, | |
| { | |
| "epoch": 1.836734693877551, | |
| "grad_norm": 17.128494262695312, | |
| "learning_rate": 2.2022684310018905e-05, | |
| "loss": 0.7792, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 1.8826530612244898, | |
| "grad_norm": 11.736278533935547, | |
| "learning_rate": 2.117202268431002e-05, | |
| "loss": 0.7889, | |
| "step": 369 | |
| }, | |
| { | |
| "epoch": 1.9285714285714286, | |
| "grad_norm": 22.40500831604004, | |
| "learning_rate": 2.0321361058601136e-05, | |
| "loss": 0.8719, | |
| "step": 378 | |
| }, | |
| { | |
| "epoch": 1.9744897959183674, | |
| "grad_norm": 7.382483959197998, | |
| "learning_rate": 1.947069943289225e-05, | |
| "loss": 0.7411, | |
| "step": 387 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.6454081632653061, | |
| "eval_f1_macro": 0.6383598362124523, | |
| "eval_f1_micro": 0.6454081632653061, | |
| "eval_f1_weighted": 0.6383598362124524, | |
| "eval_loss": 0.9568982720375061, | |
| "eval_precision_macro": 0.6613340870548332, | |
| "eval_precision_micro": 0.6454081632653061, | |
| "eval_precision_weighted": 0.6613340870548333, | |
| "eval_recall_macro": 0.6454081632653061, | |
| "eval_recall_micro": 0.6454081632653061, | |
| "eval_recall_weighted": 0.6454081632653061, | |
| "eval_runtime": 0.8449, | |
| "eval_samples_per_second": 463.965, | |
| "eval_steps_per_second": 29.59, | |
| "step": 392 | |
| }, | |
| { | |
| "epoch": 2.020408163265306, | |
| "grad_norm": 12.731431007385254, | |
| "learning_rate": 1.8714555765595465e-05, | |
| "loss": 0.6781, | |
| "step": 396 | |
| }, | |
| { | |
| "epoch": 2.066326530612245, | |
| "grad_norm": 20.548770904541016, | |
| "learning_rate": 1.786389413988658e-05, | |
| "loss": 0.4761, | |
| "step": 405 | |
| }, | |
| { | |
| "epoch": 2.1122448979591835, | |
| "grad_norm": 22.985334396362305, | |
| "learning_rate": 1.7013232514177692e-05, | |
| "loss": 0.6752, | |
| "step": 414 | |
| }, | |
| { | |
| "epoch": 2.1581632653061225, | |
| "grad_norm": 22.62578010559082, | |
| "learning_rate": 1.6162570888468808e-05, | |
| "loss": 0.5669, | |
| "step": 423 | |
| }, | |
| { | |
| "epoch": 2.204081632653061, | |
| "grad_norm": 11.662425994873047, | |
| "learning_rate": 1.5311909262759923e-05, | |
| "loss": 0.4492, | |
| "step": 432 | |
| }, | |
| { | |
| "epoch": 2.25, | |
| "grad_norm": 22.092039108276367, | |
| "learning_rate": 1.446124763705104e-05, | |
| "loss": 0.6171, | |
| "step": 441 | |
| }, | |
| { | |
| "epoch": 2.295918367346939, | |
| "grad_norm": 18.506088256835938, | |
| "learning_rate": 1.3610586011342156e-05, | |
| "loss": 0.516, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 2.3418367346938775, | |
| "grad_norm": 50.34038543701172, | |
| "learning_rate": 1.2759924385633271e-05, | |
| "loss": 0.8574, | |
| "step": 459 | |
| }, | |
| { | |
| "epoch": 2.387755102040816, | |
| "grad_norm": 17.631423950195312, | |
| "learning_rate": 1.1909262759924386e-05, | |
| "loss": 0.5258, | |
| "step": 468 | |
| }, | |
| { | |
| "epoch": 2.433673469387755, | |
| "grad_norm": 14.761687278747559, | |
| "learning_rate": 1.1058601134215502e-05, | |
| "loss": 0.697, | |
| "step": 477 | |
| }, | |
| { | |
| "epoch": 2.479591836734694, | |
| "grad_norm": 15.371265411376953, | |
| "learning_rate": 1.0207939508506617e-05, | |
| "loss": 0.6966, | |
| "step": 486 | |
| }, | |
| { | |
| "epoch": 2.5255102040816326, | |
| "grad_norm": 11.90428638458252, | |
| "learning_rate": 9.357277882797732e-06, | |
| "loss": 0.4714, | |
| "step": 495 | |
| }, | |
| { | |
| "epoch": 2.571428571428571, | |
| "grad_norm": 20.273618698120117, | |
| "learning_rate": 8.506616257088846e-06, | |
| "loss": 0.4554, | |
| "step": 504 | |
| }, | |
| { | |
| "epoch": 2.61734693877551, | |
| "grad_norm": 16.07473373413086, | |
| "learning_rate": 7.655954631379962e-06, | |
| "loss": 0.5895, | |
| "step": 513 | |
| }, | |
| { | |
| "epoch": 2.663265306122449, | |
| "grad_norm": 13.280965805053711, | |
| "learning_rate": 6.805293005671078e-06, | |
| "loss": 0.5932, | |
| "step": 522 | |
| }, | |
| { | |
| "epoch": 2.7091836734693877, | |
| "grad_norm": 14.767223358154297, | |
| "learning_rate": 5.954631379962193e-06, | |
| "loss": 0.4047, | |
| "step": 531 | |
| }, | |
| { | |
| "epoch": 2.7551020408163263, | |
| "grad_norm": 12.252891540527344, | |
| "learning_rate": 5.1039697542533085e-06, | |
| "loss": 0.544, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 2.8010204081632653, | |
| "grad_norm": 17.47493553161621, | |
| "learning_rate": 4.253308128544423e-06, | |
| "loss": 0.535, | |
| "step": 549 | |
| }, | |
| { | |
| "epoch": 2.8469387755102042, | |
| "grad_norm": 12.823530197143555, | |
| "learning_rate": 3.402646502835539e-06, | |
| "loss": 0.5172, | |
| "step": 558 | |
| }, | |
| { | |
| "epoch": 2.892857142857143, | |
| "grad_norm": 12.597037315368652, | |
| "learning_rate": 2.5519848771266543e-06, | |
| "loss": 0.5575, | |
| "step": 567 | |
| }, | |
| { | |
| "epoch": 2.938775510204082, | |
| "grad_norm": 3.2630369663238525, | |
| "learning_rate": 1.7013232514177694e-06, | |
| "loss": 0.5858, | |
| "step": 576 | |
| }, | |
| { | |
| "epoch": 2.9846938775510203, | |
| "grad_norm": 20.04022789001465, | |
| "learning_rate": 8.506616257088847e-07, | |
| "loss": 0.6399, | |
| "step": 585 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.6938775510204082, | |
| "eval_f1_macro": 0.693991401598852, | |
| "eval_f1_micro": 0.6938775510204082, | |
| "eval_f1_weighted": 0.6939914015988521, | |
| "eval_loss": 0.877387523651123, | |
| "eval_precision_macro": 0.6961606483158189, | |
| "eval_precision_micro": 0.6938775510204082, | |
| "eval_precision_weighted": 0.6961606483158188, | |
| "eval_recall_macro": 0.6938775510204082, | |
| "eval_recall_micro": 0.6938775510204082, | |
| "eval_recall_weighted": 0.6938775510204082, | |
| "eval_runtime": 0.8233, | |
| "eval_samples_per_second": 476.156, | |
| "eval_steps_per_second": 30.367, | |
| "step": 588 | |
| } | |
| ], | |
| "logging_steps": 9, | |
| "max_steps": 588, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 5, | |
| "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": 308634810052608.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |