| { | |
| "best_metric": 0.6090161800384521, | |
| "best_model_checkpoint": "autotrain-k2nef-2mp1e/checkpoint-300", | |
| "epoch": 3.0, | |
| "eval_steps": 500, | |
| "global_step": 300, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.05, | |
| "grad_norm": 2.0926642417907715, | |
| "learning_rate": 8.333333333333334e-06, | |
| "loss": 0.7016, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "grad_norm": 4.052657127380371, | |
| "learning_rate": 1.6666666666666667e-05, | |
| "loss": 0.7067, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "grad_norm": 5.750674724578857, | |
| "learning_rate": 2.5e-05, | |
| "loss": 0.6934, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "grad_norm": 3.0751872062683105, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 0.7022, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "grad_norm": 7.624610900878906, | |
| "learning_rate": 4.166666666666667e-05, | |
| "loss": 0.6635, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "grad_norm": 6.501454830169678, | |
| "learning_rate": 5e-05, | |
| "loss": 0.7008, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "grad_norm": 1.1909492015838623, | |
| "learning_rate": 4.9074074074074075e-05, | |
| "loss": 0.7069, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "grad_norm": 4.995346546173096, | |
| "learning_rate": 4.814814814814815e-05, | |
| "loss": 0.6667, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "grad_norm": 4.344069004058838, | |
| "learning_rate": 4.722222222222222e-05, | |
| "loss": 0.6798, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "grad_norm": 2.269436836242676, | |
| "learning_rate": 4.62962962962963e-05, | |
| "loss": 0.7114, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "grad_norm": 3.151176929473877, | |
| "learning_rate": 4.5370370370370374e-05, | |
| "loss": 0.6304, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "grad_norm": 2.426318407058716, | |
| "learning_rate": 4.4444444444444447e-05, | |
| "loss": 0.7266, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "grad_norm": 2.212985038757324, | |
| "learning_rate": 4.351851851851852e-05, | |
| "loss": 0.7392, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "grad_norm": 1.5283116102218628, | |
| "learning_rate": 4.259259259259259e-05, | |
| "loss": 0.7266, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "grad_norm": 2.971235752105713, | |
| "learning_rate": 4.166666666666667e-05, | |
| "loss": 0.6728, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "grad_norm": 3.4530913829803467, | |
| "learning_rate": 4.074074074074074e-05, | |
| "loss": 0.7161, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "grad_norm": 4.985769271850586, | |
| "learning_rate": 3.981481481481482e-05, | |
| "loss": 0.6379, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "grad_norm": 1.9118386507034302, | |
| "learning_rate": 3.888888888888889e-05, | |
| "loss": 0.6737, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "grad_norm": 3.0985093116760254, | |
| "learning_rate": 3.7962962962962964e-05, | |
| "loss": 0.6806, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 8.572888374328613, | |
| "learning_rate": 3.7037037037037037e-05, | |
| "loss": 0.8093, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.525, | |
| "eval_auc": 0.6939348370927318, | |
| "eval_f1": 0.6885245901639344, | |
| "eval_loss": 0.6925095319747925, | |
| "eval_precision": 0.525, | |
| "eval_recall": 1.0, | |
| "eval_runtime": 35.807, | |
| "eval_samples_per_second": 5.585, | |
| "eval_steps_per_second": 0.363, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "grad_norm": 1.2586256265640259, | |
| "learning_rate": 3.611111111111111e-05, | |
| "loss": 0.716, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "grad_norm": 1.7259572744369507, | |
| "learning_rate": 3.518518518518519e-05, | |
| "loss": 0.6773, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "grad_norm": 1.5281599760055542, | |
| "learning_rate": 3.425925925925926e-05, | |
| "loss": 0.7073, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "grad_norm": 2.143573760986328, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 0.6748, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "grad_norm": 2.464813709259033, | |
| "learning_rate": 3.240740740740741e-05, | |
| "loss": 0.7014, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "grad_norm": 3.4055287837982178, | |
| "learning_rate": 3.148148148148148e-05, | |
| "loss": 0.6871, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "grad_norm": 2.0612735748291016, | |
| "learning_rate": 3.055555555555556e-05, | |
| "loss": 0.6959, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "grad_norm": 4.995764255523682, | |
| "learning_rate": 2.962962962962963e-05, | |
| "loss": 0.6947, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "grad_norm": 5.578982830047607, | |
| "learning_rate": 2.8703703703703706e-05, | |
| "loss": 0.6397, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "grad_norm": 13.800985336303711, | |
| "learning_rate": 2.777777777777778e-05, | |
| "loss": 0.7913, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 1.55, | |
| "grad_norm": 6.1693806648254395, | |
| "learning_rate": 2.6851851851851855e-05, | |
| "loss": 0.7603, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "grad_norm": 2.4309499263763428, | |
| "learning_rate": 2.5925925925925925e-05, | |
| "loss": 0.6809, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 1.65, | |
| "grad_norm": 3.3699936866760254, | |
| "learning_rate": 2.5e-05, | |
| "loss": 0.702, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "grad_norm": 7.083240032196045, | |
| "learning_rate": 2.4074074074074074e-05, | |
| "loss": 0.7349, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "grad_norm": 3.991142988204956, | |
| "learning_rate": 2.314814814814815e-05, | |
| "loss": 0.6858, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "grad_norm": 2.0945520401000977, | |
| "learning_rate": 2.2222222222222223e-05, | |
| "loss": 0.7108, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 1.85, | |
| "grad_norm": 4.659959316253662, | |
| "learning_rate": 2.1296296296296296e-05, | |
| "loss": 0.6984, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 1.9, | |
| "grad_norm": 5.092476844787598, | |
| "learning_rate": 2.037037037037037e-05, | |
| "loss": 0.7022, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 1.95, | |
| "grad_norm": 3.881072521209717, | |
| "learning_rate": 1.9444444444444445e-05, | |
| "loss": 0.6897, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 2.4203667640686035, | |
| "learning_rate": 1.8518518518518518e-05, | |
| "loss": 0.7064, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.53, | |
| "eval_auc": 0.7506766917293233, | |
| "eval_f1": 0.6907894736842105, | |
| "eval_loss": 0.6854195594787598, | |
| "eval_precision": 0.5276381909547738, | |
| "eval_recall": 1.0, | |
| "eval_runtime": 35.8907, | |
| "eval_samples_per_second": 5.572, | |
| "eval_steps_per_second": 0.362, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 2.05, | |
| "grad_norm": 4.770285606384277, | |
| "learning_rate": 1.7592592592592595e-05, | |
| "loss": 0.688, | |
| "step": 205 | |
| }, | |
| { | |
| "epoch": 2.1, | |
| "grad_norm": 2.5155324935913086, | |
| "learning_rate": 1.6666666666666667e-05, | |
| "loss": 0.6474, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 2.15, | |
| "grad_norm": 2.7012557983398438, | |
| "learning_rate": 1.574074074074074e-05, | |
| "loss": 0.7223, | |
| "step": 215 | |
| }, | |
| { | |
| "epoch": 2.2, | |
| "grad_norm": 4.726611614227295, | |
| "learning_rate": 1.4814814814814815e-05, | |
| "loss": 0.6941, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 2.25, | |
| "grad_norm": 1.7803250551223755, | |
| "learning_rate": 1.388888888888889e-05, | |
| "loss": 0.6845, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 2.3, | |
| "grad_norm": 11.724671363830566, | |
| "learning_rate": 1.2962962962962962e-05, | |
| "loss": 0.6677, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 2.35, | |
| "grad_norm": 5.12057638168335, | |
| "learning_rate": 1.2037037037037037e-05, | |
| "loss": 0.6699, | |
| "step": 235 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "grad_norm": 4.75656270980835, | |
| "learning_rate": 1.1111111111111112e-05, | |
| "loss": 0.7428, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 2.45, | |
| "grad_norm": 7.563472747802734, | |
| "learning_rate": 1.0185185185185185e-05, | |
| "loss": 0.6592, | |
| "step": 245 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "grad_norm": 1.8900893926620483, | |
| "learning_rate": 9.259259259259259e-06, | |
| "loss": 0.6835, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 2.55, | |
| "grad_norm": 6.5432024002075195, | |
| "learning_rate": 8.333333333333334e-06, | |
| "loss": 0.6682, | |
| "step": 255 | |
| }, | |
| { | |
| "epoch": 2.6, | |
| "grad_norm": 3.4254777431488037, | |
| "learning_rate": 7.4074074074074075e-06, | |
| "loss": 0.7187, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 2.65, | |
| "grad_norm": 5.301848411560059, | |
| "learning_rate": 6.481481481481481e-06, | |
| "loss": 0.6392, | |
| "step": 265 | |
| }, | |
| { | |
| "epoch": 2.7, | |
| "grad_norm": 2.3317384719848633, | |
| "learning_rate": 5.555555555555556e-06, | |
| "loss": 0.6316, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 2.75, | |
| "grad_norm": 4.123948574066162, | |
| "learning_rate": 4.6296296296296296e-06, | |
| "loss": 0.6764, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 2.8, | |
| "grad_norm": 6.580291748046875, | |
| "learning_rate": 3.7037037037037037e-06, | |
| "loss": 0.6914, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 2.85, | |
| "grad_norm": 6.623916149139404, | |
| "learning_rate": 2.777777777777778e-06, | |
| "loss": 0.5946, | |
| "step": 285 | |
| }, | |
| { | |
| "epoch": 2.9, | |
| "grad_norm": 13.349700927734375, | |
| "learning_rate": 1.8518518518518519e-06, | |
| "loss": 0.6564, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 2.95, | |
| "grad_norm": 29.791109085083008, | |
| "learning_rate": 9.259259259259259e-07, | |
| "loss": 0.613, | |
| "step": 295 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "grad_norm": 3.5324182510375977, | |
| "learning_rate": 0.0, | |
| "loss": 0.5895, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.74, | |
| "eval_auc": 0.8025062656641604, | |
| "eval_f1": 0.7886178861788617, | |
| "eval_loss": 0.6090161800384521, | |
| "eval_precision": 0.6879432624113475, | |
| "eval_recall": 0.9238095238095239, | |
| "eval_runtime": 40.0605, | |
| "eval_samples_per_second": 4.992, | |
| "eval_steps_per_second": 0.325, | |
| "step": 300 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 300, | |
| "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": 157866633216000.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |