| { | |
| "best_metric": 0.36802276968955994, | |
| "best_model_checkpoint": "olid-addsent-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": 1.8412448167800903, | |
| "learning_rate": 3.1111111111111116e-06, | |
| "loss": 0.6471, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.09395973154362416, | |
| "grad_norm": 2.32344388961792, | |
| "learning_rate": 6.222222222222223e-06, | |
| "loss": 0.6828, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.14093959731543623, | |
| "grad_norm": 2.542279005050659, | |
| "learning_rate": 9.333333333333334e-06, | |
| "loss": 0.6446, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.18791946308724833, | |
| "grad_norm": 3.578141212463379, | |
| "learning_rate": 1.2444444444444446e-05, | |
| "loss": 0.6239, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.2348993288590604, | |
| "grad_norm": 5.565161228179932, | |
| "learning_rate": 1.5333333333333334e-05, | |
| "loss": 0.5461, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.28187919463087246, | |
| "grad_norm": 5.0949602127075195, | |
| "learning_rate": 1.8444444444444448e-05, | |
| "loss": 0.5477, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.3288590604026846, | |
| "grad_norm": 3.5840790271759033, | |
| "learning_rate": 1.982587064676617e-05, | |
| "loss": 0.5286, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.37583892617449666, | |
| "grad_norm": 4.95400333404541, | |
| "learning_rate": 1.947761194029851e-05, | |
| "loss": 0.5229, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 0.4228187919463087, | |
| "grad_norm": 7.3577961921691895, | |
| "learning_rate": 1.9129353233830846e-05, | |
| "loss": 0.4241, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 0.4697986577181208, | |
| "grad_norm": 8.08484172821045, | |
| "learning_rate": 1.8781094527363186e-05, | |
| "loss": 0.4589, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.5167785234899329, | |
| "grad_norm": 6.714763641357422, | |
| "learning_rate": 1.8432835820895526e-05, | |
| "loss": 0.4488, | |
| "step": 154 | |
| }, | |
| { | |
| "epoch": 0.5637583892617449, | |
| "grad_norm": 4.4371232986450195, | |
| "learning_rate": 1.8084577114427863e-05, | |
| "loss": 0.4678, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 0.610738255033557, | |
| "grad_norm": 8.616724014282227, | |
| "learning_rate": 1.77363184079602e-05, | |
| "loss": 0.4432, | |
| "step": 182 | |
| }, | |
| { | |
| "epoch": 0.6577181208053692, | |
| "grad_norm": 4.433163166046143, | |
| "learning_rate": 1.7412935323383088e-05, | |
| "loss": 0.444, | |
| "step": 196 | |
| }, | |
| { | |
| "epoch": 0.7046979865771812, | |
| "grad_norm": 5.25762414932251, | |
| "learning_rate": 1.7064676616915424e-05, | |
| "loss": 0.4675, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.7516778523489933, | |
| "grad_norm": 4.365243911743164, | |
| "learning_rate": 1.671641791044776e-05, | |
| "loss": 0.4321, | |
| "step": 224 | |
| }, | |
| { | |
| "epoch": 0.7986577181208053, | |
| "grad_norm": 2.648221254348755, | |
| "learning_rate": 1.63681592039801e-05, | |
| "loss": 0.4324, | |
| "step": 238 | |
| }, | |
| { | |
| "epoch": 0.8456375838926175, | |
| "grad_norm": 5.093845844268799, | |
| "learning_rate": 1.601990049751244e-05, | |
| "loss": 0.4126, | |
| "step": 252 | |
| }, | |
| { | |
| "epoch": 0.8926174496644296, | |
| "grad_norm": 4.171605110168457, | |
| "learning_rate": 1.5671641791044777e-05, | |
| "loss": 0.3719, | |
| "step": 266 | |
| }, | |
| { | |
| "epoch": 0.9395973154362416, | |
| "grad_norm": 3.66264009475708, | |
| "learning_rate": 1.5323383084577114e-05, | |
| "loss": 0.4267, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.9865771812080537, | |
| "grad_norm": 5.941737651824951, | |
| "learning_rate": 1.4975124378109454e-05, | |
| "loss": 0.3997, | |
| "step": 294 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.8380872483221476, | |
| "eval_auc": 0.905364824194377, | |
| "eval_f1": 0.7883771929824561, | |
| "eval_loss": 0.37392669916152954, | |
| "eval_precision": 0.8226544622425629, | |
| "eval_recall": 0.7568421052631579, | |
| "eval_runtime": 2.3094, | |
| "eval_samples_per_second": 1032.289, | |
| "eval_steps_per_second": 16.454, | |
| "step": 298 | |
| }, | |
| { | |
| "epoch": 1.0335570469798658, | |
| "grad_norm": 4.944675445556641, | |
| "learning_rate": 1.4626865671641792e-05, | |
| "loss": 0.3894, | |
| "step": 308 | |
| }, | |
| { | |
| "epoch": 1.0805369127516777, | |
| "grad_norm": 4.378342628479004, | |
| "learning_rate": 1.427860696517413e-05, | |
| "loss": 0.3542, | |
| "step": 322 | |
| }, | |
| { | |
| "epoch": 1.1275167785234899, | |
| "grad_norm": 3.3743112087249756, | |
| "learning_rate": 1.393034825870647e-05, | |
| "loss": 0.3439, | |
| "step": 336 | |
| }, | |
| { | |
| "epoch": 1.174496644295302, | |
| "grad_norm": 2.4719619750976562, | |
| "learning_rate": 1.3582089552238807e-05, | |
| "loss": 0.3792, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 1.221476510067114, | |
| "grad_norm": 9.958576202392578, | |
| "learning_rate": 1.3233830845771145e-05, | |
| "loss": 0.3615, | |
| "step": 364 | |
| }, | |
| { | |
| "epoch": 1.2684563758389262, | |
| "grad_norm": 2.8864505290985107, | |
| "learning_rate": 1.2885572139303483e-05, | |
| "loss": 0.3292, | |
| "step": 378 | |
| }, | |
| { | |
| "epoch": 1.3154362416107381, | |
| "grad_norm": 2.9238033294677734, | |
| "learning_rate": 1.2537313432835823e-05, | |
| "loss": 0.3492, | |
| "step": 392 | |
| }, | |
| { | |
| "epoch": 1.3624161073825503, | |
| "grad_norm": 5.472171306610107, | |
| "learning_rate": 1.218905472636816e-05, | |
| "loss": 0.3781, | |
| "step": 406 | |
| }, | |
| { | |
| "epoch": 1.4093959731543624, | |
| "grad_norm": 5.385850429534912, | |
| "learning_rate": 1.1840796019900498e-05, | |
| "loss": 0.3096, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 1.4563758389261745, | |
| "grad_norm": 6.308224678039551, | |
| "learning_rate": 1.1492537313432836e-05, | |
| "loss": 0.3592, | |
| "step": 434 | |
| }, | |
| { | |
| "epoch": 1.5033557046979866, | |
| "grad_norm": 5.205611705780029, | |
| "learning_rate": 1.1144278606965176e-05, | |
| "loss": 0.3568, | |
| "step": 448 | |
| }, | |
| { | |
| "epoch": 1.5503355704697985, | |
| "grad_norm": 5.692971229553223, | |
| "learning_rate": 1.0796019900497514e-05, | |
| "loss": 0.3646, | |
| "step": 462 | |
| }, | |
| { | |
| "epoch": 1.5973154362416109, | |
| "grad_norm": 3.6310882568359375, | |
| "learning_rate": 1.0447761194029851e-05, | |
| "loss": 0.3665, | |
| "step": 476 | |
| }, | |
| { | |
| "epoch": 1.6442953020134228, | |
| "grad_norm": 3.9791839122772217, | |
| "learning_rate": 1.009950248756219e-05, | |
| "loss": 0.3235, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 1.691275167785235, | |
| "grad_norm": 4.565869331359863, | |
| "learning_rate": 9.751243781094527e-06, | |
| "loss": 0.3274, | |
| "step": 504 | |
| }, | |
| { | |
| "epoch": 1.738255033557047, | |
| "grad_norm": 5.147943496704102, | |
| "learning_rate": 9.402985074626867e-06, | |
| "loss": 0.3703, | |
| "step": 518 | |
| }, | |
| { | |
| "epoch": 1.785234899328859, | |
| "grad_norm": 7.0455641746521, | |
| "learning_rate": 9.054726368159204e-06, | |
| "loss": 0.3431, | |
| "step": 532 | |
| }, | |
| { | |
| "epoch": 1.8322147651006713, | |
| "grad_norm": 4.0590715408325195, | |
| "learning_rate": 8.706467661691544e-06, | |
| "loss": 0.2893, | |
| "step": 546 | |
| }, | |
| { | |
| "epoch": 1.8791946308724832, | |
| "grad_norm": 7.421406269073486, | |
| "learning_rate": 8.35820895522388e-06, | |
| "loss": 0.4008, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 1.9261744966442953, | |
| "grad_norm": 2.0722334384918213, | |
| "learning_rate": 8.00995024875622e-06, | |
| "loss": 0.3209, | |
| "step": 574 | |
| }, | |
| { | |
| "epoch": 1.9731543624161074, | |
| "grad_norm": 3.51348614692688, | |
| "learning_rate": 7.661691542288557e-06, | |
| "loss": 0.3693, | |
| "step": 588 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.8443791946308725, | |
| "eval_auc": 0.9107487337590839, | |
| "eval_f1": 0.7986977753662506, | |
| "eval_loss": 0.36802276968955994, | |
| "eval_precision": 0.8241881298992161, | |
| "eval_recall": 0.7747368421052632, | |
| "eval_runtime": 2.2978, | |
| "eval_samples_per_second": 1037.503, | |
| "eval_steps_per_second": 16.537, | |
| "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 | |
| } | |