| { | |
| "best_metric": 0.4740733206272125, | |
| "best_model_checkpoint": "autotrain-r1yj0-cf7iv\\checkpoint-1069", | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 1069, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.023386342376052385, | |
| "grad_norm": 5.740257263183594, | |
| "learning_rate": 3.7383177570093455e-06, | |
| "loss": 0.6342, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.04677268475210477, | |
| "grad_norm": 14.392058372497559, | |
| "learning_rate": 7.632398753894081e-06, | |
| "loss": 0.6224, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.07015902712815715, | |
| "grad_norm": 3.3625519275665283, | |
| "learning_rate": 1.1370716510903428e-05, | |
| "loss": 0.6528, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.09354536950420954, | |
| "grad_norm": 4.029227256774902, | |
| "learning_rate": 1.5264797507788163e-05, | |
| "loss": 0.656, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.11693171188026193, | |
| "grad_norm": 8.60779857635498, | |
| "learning_rate": 1.9158878504672896e-05, | |
| "loss": 0.5875, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.1403180542563143, | |
| "grad_norm": 6.021254539489746, | |
| "learning_rate": 2.3052959501557633e-05, | |
| "loss": 0.5991, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.1637043966323667, | |
| "grad_norm": 5.536247253417969, | |
| "learning_rate": 2.6947040498442366e-05, | |
| "loss": 0.5335, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.18709073900841908, | |
| "grad_norm": 15.138010025024414, | |
| "learning_rate": 3.08411214953271e-05, | |
| "loss": 0.5251, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.21047708138447146, | |
| "grad_norm": 7.112364292144775, | |
| "learning_rate": 3.473520249221184e-05, | |
| "loss": 0.6142, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 0.23386342376052385, | |
| "grad_norm": 4.341497898101807, | |
| "learning_rate": 3.8629283489096576e-05, | |
| "loss": 0.5335, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.25724976613657624, | |
| "grad_norm": 8.008849143981934, | |
| "learning_rate": 4.2523364485981306e-05, | |
| "loss": 0.5334, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 0.2806361085126286, | |
| "grad_norm": 10.854963302612305, | |
| "learning_rate": 4.641744548286604e-05, | |
| "loss": 0.5426, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.304022450888681, | |
| "grad_norm": 7.643686294555664, | |
| "learning_rate": 4.996534996534997e-05, | |
| "loss": 0.5182, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 0.3274087932647334, | |
| "grad_norm": 9.238261222839355, | |
| "learning_rate": 4.953222453222454e-05, | |
| "loss": 0.5533, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.3507951356407858, | |
| "grad_norm": 11.438433647155762, | |
| "learning_rate": 4.911642411642412e-05, | |
| "loss": 0.4975, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 0.37418147801683815, | |
| "grad_norm": 12.855971336364746, | |
| "learning_rate": 4.868329868329868e-05, | |
| "loss": 0.5749, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.39756782039289057, | |
| "grad_norm": 5.299699306488037, | |
| "learning_rate": 4.8250173250173255e-05, | |
| "loss": 0.4549, | |
| "step": 425 | |
| }, | |
| { | |
| "epoch": 0.42095416276894293, | |
| "grad_norm": 10.646358489990234, | |
| "learning_rate": 4.781704781704782e-05, | |
| "loss": 0.5222, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.44434050514499535, | |
| "grad_norm": 2.6679370403289795, | |
| "learning_rate": 4.7383922383922385e-05, | |
| "loss": 0.4018, | |
| "step": 475 | |
| }, | |
| { | |
| "epoch": 0.4677268475210477, | |
| "grad_norm": 19.63835334777832, | |
| "learning_rate": 4.695079695079696e-05, | |
| "loss": 0.6872, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.49111318989710007, | |
| "grad_norm": 6.7021164894104, | |
| "learning_rate": 4.6517671517671515e-05, | |
| "loss": 0.5816, | |
| "step": 525 | |
| }, | |
| { | |
| "epoch": 0.5144995322731525, | |
| "grad_norm": 3.0843610763549805, | |
| "learning_rate": 4.608454608454609e-05, | |
| "loss": 0.5361, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.5378858746492049, | |
| "grad_norm": 4.530772686004639, | |
| "learning_rate": 4.565142065142065e-05, | |
| "loss": 0.497, | |
| "step": 575 | |
| }, | |
| { | |
| "epoch": 0.5612722170252572, | |
| "grad_norm": 5.629061222076416, | |
| "learning_rate": 4.521829521829522e-05, | |
| "loss": 0.512, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.5846585594013096, | |
| "grad_norm": 25.673725128173828, | |
| "learning_rate": 4.478516978516979e-05, | |
| "loss": 0.5513, | |
| "step": 625 | |
| }, | |
| { | |
| "epoch": 0.608044901777362, | |
| "grad_norm": 14.942848205566406, | |
| "learning_rate": 4.4352044352044354e-05, | |
| "loss": 0.5827, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.6314312441534145, | |
| "grad_norm": 14.735203742980957, | |
| "learning_rate": 4.391891891891892e-05, | |
| "loss": 0.5152, | |
| "step": 675 | |
| }, | |
| { | |
| "epoch": 0.6548175865294668, | |
| "grad_norm": 5.862784385681152, | |
| "learning_rate": 4.3485793485793484e-05, | |
| "loss": 0.552, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.6782039289055192, | |
| "grad_norm": 20.512489318847656, | |
| "learning_rate": 4.3052668052668056e-05, | |
| "loss": 0.4681, | |
| "step": 725 | |
| }, | |
| { | |
| "epoch": 0.7015902712815716, | |
| "grad_norm": 8.461663246154785, | |
| "learning_rate": 4.261954261954262e-05, | |
| "loss": 0.4881, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.724976613657624, | |
| "grad_norm": 9.755269050598145, | |
| "learning_rate": 4.2186417186417186e-05, | |
| "loss": 0.5161, | |
| "step": 775 | |
| }, | |
| { | |
| "epoch": 0.7483629560336763, | |
| "grad_norm": 8.718260765075684, | |
| "learning_rate": 4.175329175329176e-05, | |
| "loss": 0.5136, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.7717492984097287, | |
| "grad_norm": 6.111654281616211, | |
| "learning_rate": 4.132016632016632e-05, | |
| "loss": 0.5476, | |
| "step": 825 | |
| }, | |
| { | |
| "epoch": 0.7951356407857811, | |
| "grad_norm": 18.179821014404297, | |
| "learning_rate": 4.088704088704089e-05, | |
| "loss": 0.4995, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 0.8185219831618334, | |
| "grad_norm": 4.754278182983398, | |
| "learning_rate": 4.045391545391546e-05, | |
| "loss": 0.5333, | |
| "step": 875 | |
| }, | |
| { | |
| "epoch": 0.8419083255378859, | |
| "grad_norm": 7.877356052398682, | |
| "learning_rate": 4.0020790020790025e-05, | |
| "loss": 0.493, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.8652946679139383, | |
| "grad_norm": 7.563741683959961, | |
| "learning_rate": 3.958766458766459e-05, | |
| "loss": 0.4307, | |
| "step": 925 | |
| }, | |
| { | |
| "epoch": 0.8886810102899907, | |
| "grad_norm": 7.025684833526611, | |
| "learning_rate": 3.9154539154539155e-05, | |
| "loss": 0.5825, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 0.912067352666043, | |
| "grad_norm": 7.9024577140808105, | |
| "learning_rate": 3.8721413721413727e-05, | |
| "loss": 0.5078, | |
| "step": 975 | |
| }, | |
| { | |
| "epoch": 0.9354536950420954, | |
| "grad_norm": 12.190203666687012, | |
| "learning_rate": 3.8288288288288285e-05, | |
| "loss": 0.474, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.9588400374181478, | |
| "grad_norm": 11.860328674316406, | |
| "learning_rate": 3.785516285516286e-05, | |
| "loss": 0.495, | |
| "step": 1025 | |
| }, | |
| { | |
| "epoch": 0.9822263797942001, | |
| "grad_norm": 14.630024909973145, | |
| "learning_rate": 3.742203742203743e-05, | |
| "loss": 0.5006, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.7823585810162992, | |
| "eval_auc": 0.8029694782091815, | |
| "eval_f1": 0.8560558021559924, | |
| "eval_loss": 0.4740733206272125, | |
| "eval_precision": 0.7885514018691588, | |
| "eval_recall": 0.9361997226074896, | |
| "eval_runtime": 4.1379, | |
| "eval_samples_per_second": 252.058, | |
| "eval_steps_per_second": 15.95, | |
| "step": 1069 | |
| } | |
| ], | |
| "logging_steps": 25, | |
| "max_steps": 3207, | |
| "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": 562465658595840.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |