| { | |
| "best_metric": 0.3905062973499298, | |
| "best_model_checkpoint": "olid-stylebkd-p10-bert-uncased/checkpoint-596", | |
| "epoch": 2.0, | |
| "eval_steps": 500, | |
| "global_step": 596, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.04697986577181208, | |
| "grad_norm": 2.8473196029663086, | |
| "learning_rate": 3.1111111111111116e-06, | |
| "loss": 0.7023, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.09395973154362416, | |
| "grad_norm": 2.5279300212860107, | |
| "learning_rate": 6.222222222222223e-06, | |
| "loss": 0.6861, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.14093959731543623, | |
| "grad_norm": 2.878610134124756, | |
| "learning_rate": 9.333333333333334e-06, | |
| "loss": 0.6529, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.18791946308724833, | |
| "grad_norm": 2.704759359359741, | |
| "learning_rate": 1.2444444444444446e-05, | |
| "loss": 0.6374, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.2348993288590604, | |
| "grad_norm": 2.618530750274658, | |
| "learning_rate": 1.5333333333333334e-05, | |
| "loss": 0.5798, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.28187919463087246, | |
| "grad_norm": 3.5130767822265625, | |
| "learning_rate": 1.8444444444444448e-05, | |
| "loss": 0.5442, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.3288590604026846, | |
| "grad_norm": 6.02633810043335, | |
| "learning_rate": 1.982587064676617e-05, | |
| "loss": 0.5442, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.37583892617449666, | |
| "grad_norm": 6.7346673011779785, | |
| "learning_rate": 1.947761194029851e-05, | |
| "loss": 0.538, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 0.4228187919463087, | |
| "grad_norm": 4.506645202636719, | |
| "learning_rate": 1.9129353233830846e-05, | |
| "loss": 0.4524, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 0.4697986577181208, | |
| "grad_norm": 16.355239868164062, | |
| "learning_rate": 1.8781094527363186e-05, | |
| "loss": 0.4682, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.5167785234899329, | |
| "grad_norm": 4.144381046295166, | |
| "learning_rate": 1.8432835820895526e-05, | |
| "loss": 0.491, | |
| "step": 154 | |
| }, | |
| { | |
| "epoch": 0.5637583892617449, | |
| "grad_norm": 4.07854700088501, | |
| "learning_rate": 1.8084577114427863e-05, | |
| "loss": 0.474, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 0.610738255033557, | |
| "grad_norm": 8.74126148223877, | |
| "learning_rate": 1.77363184079602e-05, | |
| "loss": 0.4303, | |
| "step": 182 | |
| }, | |
| { | |
| "epoch": 0.6577181208053692, | |
| "grad_norm": 4.1934285163879395, | |
| "learning_rate": 1.7412935323383088e-05, | |
| "loss": 0.4545, | |
| "step": 196 | |
| }, | |
| { | |
| "epoch": 0.7046979865771812, | |
| "grad_norm": 4.430333137512207, | |
| "learning_rate": 1.7064676616915424e-05, | |
| "loss": 0.4735, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.7516778523489933, | |
| "grad_norm": 3.5821316242218018, | |
| "learning_rate": 1.671641791044776e-05, | |
| "loss": 0.4115, | |
| "step": 224 | |
| }, | |
| { | |
| "epoch": 0.7986577181208053, | |
| "grad_norm": 2.470816135406494, | |
| "learning_rate": 1.63681592039801e-05, | |
| "loss": 0.4395, | |
| "step": 238 | |
| }, | |
| { | |
| "epoch": 0.8456375838926175, | |
| "grad_norm": 3.9837400913238525, | |
| "learning_rate": 1.601990049751244e-05, | |
| "loss": 0.4232, | |
| "step": 252 | |
| }, | |
| { | |
| "epoch": 0.8926174496644296, | |
| "grad_norm": 5.207034111022949, | |
| "learning_rate": 1.5671641791044777e-05, | |
| "loss": 0.394, | |
| "step": 266 | |
| }, | |
| { | |
| "epoch": 0.9395973154362416, | |
| "grad_norm": 3.6829946041107178, | |
| "learning_rate": 1.5323383084577114e-05, | |
| "loss": 0.4827, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.9865771812080537, | |
| "grad_norm": 3.973491668701172, | |
| "learning_rate": 1.4975124378109454e-05, | |
| "loss": 0.4326, | |
| "step": 294 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.8217281879194631, | |
| "eval_auc": 0.8938196432503853, | |
| "eval_f1": 0.7706422018348624, | |
| "eval_loss": 0.3977891504764557, | |
| "eval_precision": 0.7906976744186046, | |
| "eval_recall": 0.751578947368421, | |
| "eval_runtime": 2.28, | |
| "eval_samples_per_second": 1045.597, | |
| "eval_steps_per_second": 16.666, | |
| "step": 298 | |
| }, | |
| { | |
| "epoch": 1.0335570469798658, | |
| "grad_norm": 5.082137107849121, | |
| "learning_rate": 1.4626865671641792e-05, | |
| "loss": 0.3941, | |
| "step": 308 | |
| }, | |
| { | |
| "epoch": 1.0805369127516777, | |
| "grad_norm": 8.384503364562988, | |
| "learning_rate": 1.427860696517413e-05, | |
| "loss": 0.3692, | |
| "step": 322 | |
| }, | |
| { | |
| "epoch": 1.1275167785234899, | |
| "grad_norm": 4.126455783843994, | |
| "learning_rate": 1.393034825870647e-05, | |
| "loss": 0.3797, | |
| "step": 336 | |
| }, | |
| { | |
| "epoch": 1.174496644295302, | |
| "grad_norm": 2.891618013381958, | |
| "learning_rate": 1.3582089552238807e-05, | |
| "loss": 0.4014, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 1.221476510067114, | |
| "grad_norm": 6.136148929595947, | |
| "learning_rate": 1.3233830845771145e-05, | |
| "loss": 0.393, | |
| "step": 364 | |
| }, | |
| { | |
| "epoch": 1.2684563758389262, | |
| "grad_norm": 3.083270788192749, | |
| "learning_rate": 1.2885572139303483e-05, | |
| "loss": 0.3564, | |
| "step": 378 | |
| }, | |
| { | |
| "epoch": 1.3154362416107381, | |
| "grad_norm": 2.6372623443603516, | |
| "learning_rate": 1.2537313432835823e-05, | |
| "loss": 0.3492, | |
| "step": 392 | |
| }, | |
| { | |
| "epoch": 1.3624161073825503, | |
| "grad_norm": 4.032045841217041, | |
| "learning_rate": 1.218905472636816e-05, | |
| "loss": 0.3858, | |
| "step": 406 | |
| }, | |
| { | |
| "epoch": 1.4093959731543624, | |
| "grad_norm": 5.014185428619385, | |
| "learning_rate": 1.1840796019900498e-05, | |
| "loss": 0.3123, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 1.4563758389261745, | |
| "grad_norm": 5.151511192321777, | |
| "learning_rate": 1.1492537313432836e-05, | |
| "loss": 0.3717, | |
| "step": 434 | |
| }, | |
| { | |
| "epoch": 1.5033557046979866, | |
| "grad_norm": 4.571159839630127, | |
| "learning_rate": 1.1144278606965176e-05, | |
| "loss": 0.3542, | |
| "step": 448 | |
| }, | |
| { | |
| "epoch": 1.5503355704697985, | |
| "grad_norm": 4.309226036071777, | |
| "learning_rate": 1.0796019900497514e-05, | |
| "loss": 0.348, | |
| "step": 462 | |
| }, | |
| { | |
| "epoch": 1.5973154362416109, | |
| "grad_norm": 3.4935061931610107, | |
| "learning_rate": 1.0447761194029851e-05, | |
| "loss": 0.3742, | |
| "step": 476 | |
| }, | |
| { | |
| "epoch": 1.6442953020134228, | |
| "grad_norm": 3.565952777862549, | |
| "learning_rate": 1.009950248756219e-05, | |
| "loss": 0.3557, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 1.691275167785235, | |
| "grad_norm": 6.2538065910339355, | |
| "learning_rate": 9.751243781094527e-06, | |
| "loss": 0.3404, | |
| "step": 504 | |
| }, | |
| { | |
| "epoch": 1.738255033557047, | |
| "grad_norm": 3.3098158836364746, | |
| "learning_rate": 9.402985074626867e-06, | |
| "loss": 0.401, | |
| "step": 518 | |
| }, | |
| { | |
| "epoch": 1.785234899328859, | |
| "grad_norm": 5.43450927734375, | |
| "learning_rate": 9.054726368159204e-06, | |
| "loss": 0.3626, | |
| "step": 532 | |
| }, | |
| { | |
| "epoch": 1.8322147651006713, | |
| "grad_norm": 5.279735088348389, | |
| "learning_rate": 8.706467661691544e-06, | |
| "loss": 0.2923, | |
| "step": 546 | |
| }, | |
| { | |
| "epoch": 1.8791946308724832, | |
| "grad_norm": 6.0305328369140625, | |
| "learning_rate": 8.35820895522388e-06, | |
| "loss": 0.3978, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 1.9261744966442953, | |
| "grad_norm": 1.9193602800369263, | |
| "learning_rate": 8.00995024875622e-06, | |
| "loss": 0.3308, | |
| "step": 574 | |
| }, | |
| { | |
| "epoch": 1.9731543624161074, | |
| "grad_norm": 4.429193019866943, | |
| "learning_rate": 7.661691542288557e-06, | |
| "loss": 0.3681, | |
| "step": 588 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.8309563758389261, | |
| "eval_auc": 0.8991059238053292, | |
| "eval_f1": 0.7820443482963764, | |
| "eval_loss": 0.3905062973499298, | |
| "eval_precision": 0.8042269187986651, | |
| "eval_recall": 0.7610526315789473, | |
| "eval_runtime": 2.2806, | |
| "eval_samples_per_second": 1045.317, | |
| "eval_steps_per_second": 16.662, | |
| "step": 596 | |
| } | |
| ], | |
| "logging_steps": 14, | |
| "max_steps": 894, | |
| "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": 1 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1253987289845760.0, | |
| "train_batch_size": 32, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |