| { | |
| "best_metric": 0.2697308361530304, | |
| "best_model_checkpoint": "autotrain-9d8m7-5e3go/checkpoint-250", | |
| "epoch": 2.0, | |
| "eval_steps": 500, | |
| "global_step": 250, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.048, | |
| "grad_norm": 10.31029987335205, | |
| "learning_rate": 7.894736842105263e-06, | |
| "loss": 0.9688, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.096, | |
| "grad_norm": 6.658392906188965, | |
| "learning_rate": 1.5789473684210526e-05, | |
| "loss": 0.6108, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.144, | |
| "grad_norm": 12.619353294372559, | |
| "learning_rate": 2.368421052631579e-05, | |
| "loss": 0.5394, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.192, | |
| "grad_norm": 1.8838263750076294, | |
| "learning_rate": 3.157894736842105e-05, | |
| "loss": 0.4617, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "grad_norm": 8.438435554504395, | |
| "learning_rate": 3.9473684210526316e-05, | |
| "loss": 0.443, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.288, | |
| "grad_norm": 5.801192760467529, | |
| "learning_rate": 4.736842105263158e-05, | |
| "loss": 0.433, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.336, | |
| "grad_norm": 4.70213508605957, | |
| "learning_rate": 4.9406528189910986e-05, | |
| "loss": 0.4381, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.384, | |
| "grad_norm": 5.330947399139404, | |
| "learning_rate": 4.851632047477745e-05, | |
| "loss": 0.4312, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.432, | |
| "grad_norm": 3.07973313331604, | |
| "learning_rate": 4.762611275964392e-05, | |
| "loss": 0.3787, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "grad_norm": 6.628166675567627, | |
| "learning_rate": 4.673590504451038e-05, | |
| "loss": 0.2378, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.528, | |
| "grad_norm": 1.0855748653411865, | |
| "learning_rate": 4.584569732937686e-05, | |
| "loss": 0.2797, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.576, | |
| "grad_norm": 1.5934823751449585, | |
| "learning_rate": 4.4955489614243326e-05, | |
| "loss": 0.2863, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.624, | |
| "grad_norm": 2.8034512996673584, | |
| "learning_rate": 4.4065281899109794e-05, | |
| "loss": 0.5325, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.672, | |
| "grad_norm": 12.93682861328125, | |
| "learning_rate": 4.317507418397626e-05, | |
| "loss": 0.3248, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "grad_norm": 9.533049583435059, | |
| "learning_rate": 4.228486646884273e-05, | |
| "loss": 0.2357, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.768, | |
| "grad_norm": 12.49010181427002, | |
| "learning_rate": 4.1394658753709205e-05, | |
| "loss": 0.557, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.816, | |
| "grad_norm": 1.8601925373077393, | |
| "learning_rate": 4.050445103857567e-05, | |
| "loss": 0.2432, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 0.864, | |
| "grad_norm": 4.38627815246582, | |
| "learning_rate": 3.961424332344214e-05, | |
| "loss": 0.1943, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 0.912, | |
| "grad_norm": 5.118112087249756, | |
| "learning_rate": 3.87240356083086e-05, | |
| "loss": 0.5135, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "grad_norm": 12.806257247924805, | |
| "learning_rate": 3.783382789317508e-05, | |
| "loss": 0.4216, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.8634538152610441, | |
| "eval_auc": 0.917822966507177, | |
| "eval_f1": 0.41379310344827586, | |
| "eval_loss": 0.27404287457466125, | |
| "eval_precision": 0.6666666666666666, | |
| "eval_recall": 0.3, | |
| "eval_runtime": 38.5461, | |
| "eval_samples_per_second": 6.46, | |
| "eval_steps_per_second": 0.415, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 1.008, | |
| "grad_norm": 3.2676734924316406, | |
| "learning_rate": 3.6943620178041546e-05, | |
| "loss": 0.273, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 1.056, | |
| "grad_norm": 4.2453203201293945, | |
| "learning_rate": 3.6053412462908014e-05, | |
| "loss": 0.1784, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 1.104, | |
| "grad_norm": 4.445944309234619, | |
| "learning_rate": 3.516320474777448e-05, | |
| "loss": 0.307, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 1.152, | |
| "grad_norm": 3.5331907272338867, | |
| "learning_rate": 3.427299703264095e-05, | |
| "loss": 0.2794, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "grad_norm": 1.581238865852356, | |
| "learning_rate": 3.338278931750742e-05, | |
| "loss": 0.3854, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 1.248, | |
| "grad_norm": 10.242961883544922, | |
| "learning_rate": 3.249258160237389e-05, | |
| "loss": 0.1236, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 1.296, | |
| "grad_norm": 11.508437156677246, | |
| "learning_rate": 3.1602373887240355e-05, | |
| "loss": 0.3079, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 1.3439999999999999, | |
| "grad_norm": 4.03028678894043, | |
| "learning_rate": 3.071216617210683e-05, | |
| "loss": 0.3989, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 1.392, | |
| "grad_norm": 3.1952617168426514, | |
| "learning_rate": 2.9821958456973298e-05, | |
| "loss": 0.3071, | |
| "step": 174 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "grad_norm": 0.6087659597396851, | |
| "learning_rate": 2.8931750741839762e-05, | |
| "loss": 0.2171, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 1.488, | |
| "grad_norm": 1.4459624290466309, | |
| "learning_rate": 2.8041543026706234e-05, | |
| "loss": 0.1617, | |
| "step": 186 | |
| }, | |
| { | |
| "epoch": 1.536, | |
| "grad_norm": 2.4748902320861816, | |
| "learning_rate": 2.7151335311572702e-05, | |
| "loss": 0.2654, | |
| "step": 192 | |
| }, | |
| { | |
| "epoch": 1.584, | |
| "grad_norm": 2.966203212738037, | |
| "learning_rate": 2.6261127596439174e-05, | |
| "loss": 0.2538, | |
| "step": 198 | |
| }, | |
| { | |
| "epoch": 1.6320000000000001, | |
| "grad_norm": 3.4787888526916504, | |
| "learning_rate": 2.537091988130564e-05, | |
| "loss": 0.3404, | |
| "step": 204 | |
| }, | |
| { | |
| "epoch": 1.6800000000000002, | |
| "grad_norm": 7.650554656982422, | |
| "learning_rate": 2.4480712166172106e-05, | |
| "loss": 0.3208, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 1.728, | |
| "grad_norm": 2.050452470779419, | |
| "learning_rate": 2.3590504451038578e-05, | |
| "loss": 0.1486, | |
| "step": 216 | |
| }, | |
| { | |
| "epoch": 1.776, | |
| "grad_norm": 29.640296936035156, | |
| "learning_rate": 2.2700296735905046e-05, | |
| "loss": 0.3721, | |
| "step": 222 | |
| }, | |
| { | |
| "epoch": 1.8239999999999998, | |
| "grad_norm": 4.195475101470947, | |
| "learning_rate": 2.1810089020771514e-05, | |
| "loss": 0.1306, | |
| "step": 228 | |
| }, | |
| { | |
| "epoch": 1.8719999999999999, | |
| "grad_norm": 20.677532196044922, | |
| "learning_rate": 2.0919881305637982e-05, | |
| "loss": 0.1396, | |
| "step": 234 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "grad_norm": 5.205203056335449, | |
| "learning_rate": 2.0029673590504454e-05, | |
| "loss": 0.413, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 1.968, | |
| "grad_norm": 0.5597999691963196, | |
| "learning_rate": 1.9139465875370922e-05, | |
| "loss": 0.5066, | |
| "step": 246 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.8955823293172691, | |
| "eval_auc": 0.942822966507177, | |
| "eval_f1": 0.6904761904761905, | |
| "eval_loss": 0.2697308361530304, | |
| "eval_precision": 0.6590909090909091, | |
| "eval_recall": 0.725, | |
| "eval_runtime": 38.8974, | |
| "eval_samples_per_second": 6.401, | |
| "eval_steps_per_second": 0.411, | |
| "step": 250 | |
| } | |
| ], | |
| "logging_steps": 6, | |
| "max_steps": 375, | |
| "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": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 130766194513920.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |