| { | |
| "best_metric": 0.10066879540681839, | |
| "best_model_checkpoint": "autotrain-emecz-j2gix/checkpoint-164", | |
| "epoch": 2.0, | |
| "eval_steps": 500, | |
| "global_step": 164, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.04878048780487805, | |
| "grad_norm": 0.3794308602809906, | |
| "learning_rate": 8.000000000000001e-06, | |
| "loss": 0.6976, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0975609756097561, | |
| "grad_norm": 0.671731173992157, | |
| "learning_rate": 1.6000000000000003e-05, | |
| "loss": 0.6944, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.14634146341463414, | |
| "grad_norm": 2.235081434249878, | |
| "learning_rate": 2.4e-05, | |
| "loss": 0.6922, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.1951219512195122, | |
| "grad_norm": 2.346835136413574, | |
| "learning_rate": 3.2000000000000005e-05, | |
| "loss": 0.6904, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.24390243902439024, | |
| "grad_norm": 4.985357284545898, | |
| "learning_rate": 4e-05, | |
| "loss": 0.5521, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.2926829268292683, | |
| "grad_norm": 4.204496383666992, | |
| "learning_rate": 4.8e-05, | |
| "loss": 0.3967, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.34146341463414637, | |
| "grad_norm": 19.942995071411133, | |
| "learning_rate": 4.997726987107582e-05, | |
| "loss": 0.3278, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.3902439024390244, | |
| "grad_norm": 14.574546813964844, | |
| "learning_rate": 4.9876330414334614e-05, | |
| "loss": 0.3968, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.43902439024390244, | |
| "grad_norm": 12.140644073486328, | |
| "learning_rate": 4.9694981991119004e-05, | |
| "loss": 0.4434, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.4878048780487805, | |
| "grad_norm": 6.911764621734619, | |
| "learning_rate": 4.943381078271214e-05, | |
| "loss": 0.3158, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.5365853658536586, | |
| "grad_norm": 9.625554084777832, | |
| "learning_rate": 4.9093660985448097e-05, | |
| "loss": 0.2399, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.5853658536585366, | |
| "grad_norm": 1.0161175727844238, | |
| "learning_rate": 4.86756320819752e-05, | |
| "loss": 0.4131, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.6341463414634146, | |
| "grad_norm": 12.2647123336792, | |
| "learning_rate": 4.818107528734504e-05, | |
| "loss": 0.1248, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.6829268292682927, | |
| "grad_norm": 1.7963744401931763, | |
| "learning_rate": 4.761158918141474e-05, | |
| "loss": 0.197, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.7317073170731707, | |
| "grad_norm": 5.169480323791504, | |
| "learning_rate": 4.696901454167988e-05, | |
| "loss": 0.2053, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.7804878048780488, | |
| "grad_norm": 7.40244722366333, | |
| "learning_rate": 4.625542839324036e-05, | |
| "loss": 0.3954, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.8292682926829268, | |
| "grad_norm": 4.580534934997559, | |
| "learning_rate": 4.547313729513163e-05, | |
| "loss": 0.2515, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.8780487804878049, | |
| "grad_norm": 5.525244235992432, | |
| "learning_rate": 4.462466988472237e-05, | |
| "loss": 0.2298, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.926829268292683, | |
| "grad_norm": 6.653177261352539, | |
| "learning_rate": 4.371276870427753e-05, | |
| "loss": 0.222, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.975609756097561, | |
| "grad_norm": 8.775516510009766, | |
| "learning_rate": 4.274038133610628e-05, | |
| "loss": 0.1531, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.9493865030674846, | |
| "eval_auc": 0.9892279647889984, | |
| "eval_f1": 0.9470304975922953, | |
| "eval_loss": 0.14209958910942078, | |
| "eval_precision": 0.9305993690851735, | |
| "eval_recall": 0.9640522875816994, | |
| "eval_runtime": 5.3121, | |
| "eval_samples_per_second": 122.739, | |
| "eval_steps_per_second": 2.071, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 1.024390243902439, | |
| "grad_norm": 0.35274970531463623, | |
| "learning_rate": 4.171065087494909e-05, | |
| "loss": 0.0691, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 1.0731707317073171, | |
| "grad_norm": 0.19416379928588867, | |
| "learning_rate": 4.0626905768400516e-05, | |
| "loss": 0.1768, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 1.1219512195121952, | |
| "grad_norm": 2.028865098953247, | |
| "learning_rate": 3.949264905820697e-05, | |
| "loss": 0.1823, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 1.170731707317073, | |
| "grad_norm": 6.421178817749023, | |
| "learning_rate": 3.831154705721541e-05, | |
| "loss": 0.0778, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 1.2195121951219512, | |
| "grad_norm": 6.153197288513184, | |
| "learning_rate": 3.7087417498572944e-05, | |
| "loss": 0.0399, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.2682926829268293, | |
| "grad_norm": 4.175981044769287, | |
| "learning_rate": 3.6143458894413465e-05, | |
| "loss": 0.2834, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 1.3170731707317074, | |
| "grad_norm": 0.08463025838136673, | |
| "learning_rate": 3.485362865576194e-05, | |
| "loss": 0.0894, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 1.3658536585365852, | |
| "grad_norm": 17.901002883911133, | |
| "learning_rate": 3.353194805642477e-05, | |
| "loss": 0.0901, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 1.4146341463414633, | |
| "grad_norm": 18.01471519470215, | |
| "learning_rate": 3.2182689228554517e-05, | |
| "loss": 0.2675, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 1.4634146341463414, | |
| "grad_norm": 2.2452147006988525, | |
| "learning_rate": 3.081021344674632e-05, | |
| "loss": 0.0789, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 1.5121951219512195, | |
| "grad_norm": 9.682868957519531, | |
| "learning_rate": 2.9418957030878874e-05, | |
| "loss": 0.1109, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 1.5609756097560976, | |
| "grad_norm": 0.5994274616241455, | |
| "learning_rate": 2.8013417006383076e-05, | |
| "loss": 0.085, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 1.6097560975609757, | |
| "grad_norm": 7.9580793380737305, | |
| "learning_rate": 2.6598136568289143e-05, | |
| "loss": 0.0938, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 1.6585365853658538, | |
| "grad_norm": 0.2872644066810608, | |
| "learning_rate": 2.517769039603744e-05, | |
| "loss": 0.1155, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 1.7073170731707317, | |
| "grad_norm": 6.185705184936523, | |
| "learning_rate": 2.3756669866520832e-05, | |
| "loss": 0.213, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 1.7560975609756098, | |
| "grad_norm": 2.6776204109191895, | |
| "learning_rate": 2.2339668213154945e-05, | |
| "loss": 0.0741, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 1.8048780487804879, | |
| "grad_norm": 6.972938060760498, | |
| "learning_rate": 2.0931265678947555e-05, | |
| "loss": 0.1297, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 1.8536585365853657, | |
| "grad_norm": 2.5824131965637207, | |
| "learning_rate": 1.9536014711557528e-05, | |
| "loss": 0.0674, | |
| "step": 152 | |
| }, | |
| { | |
| "epoch": 1.9024390243902438, | |
| "grad_norm": 1.7245702743530273, | |
| "learning_rate": 1.815842524819793e-05, | |
| "loss": 0.0738, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 1.951219512195122, | |
| "grad_norm": 0.3297303020954132, | |
| "learning_rate": 1.680295013794778e-05, | |
| "loss": 0.0852, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 5.111387252807617, | |
| "learning_rate": 1.547397074859249e-05, | |
| "loss": 0.057, | |
| "step": 164 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.9708588957055214, | |
| "eval_auc": 0.9946588461974386, | |
| "eval_f1": 0.9691056910569106, | |
| "eval_loss": 0.10066879540681839, | |
| "eval_precision": 0.9644012944983819, | |
| "eval_recall": 0.9738562091503268, | |
| "eval_runtime": 5.3221, | |
| "eval_samples_per_second": 122.509, | |
| "eval_steps_per_second": 2.067, | |
| "step": 164 | |
| } | |
| ], | |
| "logging_steps": 4, | |
| "max_steps": 246, | |
| "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": 798380148400128.0, | |
| "train_batch_size": 32, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |