| { |
| "best_global_step": 366, |
| "best_metric": 0.41911664605140686, |
| "best_model_checkpoint": "training_output/run_20260713_203733/model/checkpoint-366", |
| "epoch": 2.0, |
| "eval_steps": 500, |
| "global_step": 732, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.0273224043715847, |
| "grad_norm": 4.927176475524902, |
| "learning_rate": 7.377049180327868e-07, |
| "loss": 0.6899909496307373, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.0546448087431694, |
| "grad_norm": 6.0230512619018555, |
| "learning_rate": 1.557377049180328e-06, |
| "loss": 0.7346426486968994, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.08196721311475409, |
| "grad_norm": 6.2535271644592285, |
| "learning_rate": 2.377049180327869e-06, |
| "loss": 0.6693419456481934, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.1092896174863388, |
| "grad_norm": 10.038297653198242, |
| "learning_rate": 3.1967213114754097e-06, |
| "loss": 0.6888828277587891, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.1366120218579235, |
| "grad_norm": 10.041961669921875, |
| "learning_rate": 4.016393442622951e-06, |
| "loss": 0.623580026626587, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.16393442622950818, |
| "grad_norm": 9.107032775878906, |
| "learning_rate": 4.836065573770492e-06, |
| "loss": 0.692430830001831, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.1912568306010929, |
| "grad_norm": 9.090417861938477, |
| "learning_rate": 5.655737704918032e-06, |
| "loss": 0.6110644817352295, |
| "step": 70 |
| }, |
| { |
| "epoch": 0.2185792349726776, |
| "grad_norm": 7.914913177490234, |
| "learning_rate": 6.4754098360655735e-06, |
| "loss": 0.6268288612365722, |
| "step": 80 |
| }, |
| { |
| "epoch": 0.2459016393442623, |
| "grad_norm": 8.18041706085205, |
| "learning_rate": 7.2950819672131145e-06, |
| "loss": 0.6859075546264648, |
| "step": 90 |
| }, |
| { |
| "epoch": 0.273224043715847, |
| "grad_norm": 5.7157392501831055, |
| "learning_rate": 8.114754098360657e-06, |
| "loss": 0.7717578887939454, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.3005464480874317, |
| "grad_norm": 11.109936714172363, |
| "learning_rate": 8.934426229508197e-06, |
| "loss": 0.6476659774780273, |
| "step": 110 |
| }, |
| { |
| "epoch": 0.32786885245901637, |
| "grad_norm": 10.369423866271973, |
| "learning_rate": 9.754098360655738e-06, |
| "loss": 0.6707509994506836, |
| "step": 120 |
| }, |
| { |
| "epoch": 0.3551912568306011, |
| "grad_norm": 10.730874061584473, |
| "learning_rate": 1.0573770491803279e-05, |
| "loss": 0.6787842750549317, |
| "step": 130 |
| }, |
| { |
| "epoch": 0.3825136612021858, |
| "grad_norm": 8.120079040527344, |
| "learning_rate": 1.139344262295082e-05, |
| "loss": 0.6765446186065673, |
| "step": 140 |
| }, |
| { |
| "epoch": 0.4098360655737705, |
| "grad_norm": 14.429889678955078, |
| "learning_rate": 1.221311475409836e-05, |
| "loss": 0.623370361328125, |
| "step": 150 |
| }, |
| { |
| "epoch": 0.4371584699453552, |
| "grad_norm": 9.193517684936523, |
| "learning_rate": 1.3032786885245902e-05, |
| "loss": 0.6362186908721924, |
| "step": 160 |
| }, |
| { |
| "epoch": 0.4644808743169399, |
| "grad_norm": 8.7772855758667, |
| "learning_rate": 1.3852459016393443e-05, |
| "loss": 0.6641538619995118, |
| "step": 170 |
| }, |
| { |
| "epoch": 0.4918032786885246, |
| "grad_norm": 5.2151780128479, |
| "learning_rate": 1.4672131147540984e-05, |
| "loss": 0.6653701782226562, |
| "step": 180 |
| }, |
| { |
| "epoch": 0.5191256830601093, |
| "grad_norm": 17.197834014892578, |
| "learning_rate": 1.5491803278688525e-05, |
| "loss": 0.6582591533660889, |
| "step": 190 |
| }, |
| { |
| "epoch": 0.546448087431694, |
| "grad_norm": 7.26473331451416, |
| "learning_rate": 1.6311475409836068e-05, |
| "loss": 0.765175724029541, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.5737704918032787, |
| "grad_norm": 5.47290563583374, |
| "learning_rate": 1.7131147540983607e-05, |
| "loss": 0.676247501373291, |
| "step": 210 |
| }, |
| { |
| "epoch": 0.6010928961748634, |
| "grad_norm": 4.55684232711792, |
| "learning_rate": 1.7950819672131146e-05, |
| "loss": 0.6748649597167968, |
| "step": 220 |
| }, |
| { |
| "epoch": 0.6284153005464481, |
| "grad_norm": 9.52070140838623, |
| "learning_rate": 1.877049180327869e-05, |
| "loss": 0.7023877143859864, |
| "step": 230 |
| }, |
| { |
| "epoch": 0.6557377049180327, |
| "grad_norm": 10.813623428344727, |
| "learning_rate": 1.959016393442623e-05, |
| "loss": 0.5075790405273437, |
| "step": 240 |
| }, |
| { |
| "epoch": 0.6830601092896175, |
| "grad_norm": 15.77322769165039, |
| "learning_rate": 2.040983606557377e-05, |
| "loss": 0.5947454929351806, |
| "step": 250 |
| }, |
| { |
| "epoch": 0.7103825136612022, |
| "grad_norm": 14.141736030578613, |
| "learning_rate": 2.122950819672131e-05, |
| "loss": 0.7629669666290283, |
| "step": 260 |
| }, |
| { |
| "epoch": 0.7377049180327869, |
| "grad_norm": 0.5761239528656006, |
| "learning_rate": 2.2049180327868853e-05, |
| "loss": 0.717600679397583, |
| "step": 270 |
| }, |
| { |
| "epoch": 0.7650273224043715, |
| "grad_norm": 13.026739120483398, |
| "learning_rate": 2.2868852459016393e-05, |
| "loss": 1.5919431686401366, |
| "step": 280 |
| }, |
| { |
| "epoch": 0.7923497267759563, |
| "grad_norm": 12.15133285522461, |
| "learning_rate": 2.3688524590163936e-05, |
| "loss": 0.6558570861816406, |
| "step": 290 |
| }, |
| { |
| "epoch": 0.819672131147541, |
| "grad_norm": 20.35292625427246, |
| "learning_rate": 2.4508196721311478e-05, |
| "loss": 0.6991987705230713, |
| "step": 300 |
| }, |
| { |
| "epoch": 0.8469945355191257, |
| "grad_norm": 9.59134292602539, |
| "learning_rate": 2.5327868852459018e-05, |
| "loss": 1.1239334106445313, |
| "step": 310 |
| }, |
| { |
| "epoch": 0.8743169398907104, |
| "grad_norm": 4.265232086181641, |
| "learning_rate": 2.6147540983606557e-05, |
| "loss": 0.4866987705230713, |
| "step": 320 |
| }, |
| { |
| "epoch": 0.9016393442622951, |
| "grad_norm": 9.87460708618164, |
| "learning_rate": 2.69672131147541e-05, |
| "loss": 0.7435293674468995, |
| "step": 330 |
| }, |
| { |
| "epoch": 0.9289617486338798, |
| "grad_norm": 12.707701683044434, |
| "learning_rate": 2.7786885245901642e-05, |
| "loss": 0.9141542434692382, |
| "step": 340 |
| }, |
| { |
| "epoch": 0.9562841530054644, |
| "grad_norm": 2.9138967990875244, |
| "learning_rate": 2.860655737704918e-05, |
| "loss": 0.5319347858428956, |
| "step": 350 |
| }, |
| { |
| "epoch": 0.9836065573770492, |
| "grad_norm": 6.917504787445068, |
| "learning_rate": 2.942622950819672e-05, |
| "loss": 0.5438683509826661, |
| "step": 360 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_accuracy": 0.8492, |
| "eval_confusion_matrix": [ |
| [ |
| 282, |
| 0 |
| ], |
| [ |
| 54, |
| 22 |
| ] |
| ], |
| "eval_f1": 0.449, |
| "eval_loss": 0.41911664605140686, |
| "eval_pr_auc": 0.6187, |
| "eval_precision": 1.0, |
| "eval_recall": 0.2895, |
| "eval_roc_auc": 0.7485, |
| "eval_runtime": 138.7598, |
| "eval_samples_per_second": 2.58, |
| "eval_steps_per_second": 0.649, |
| "step": 366 |
| }, |
| { |
| "epoch": 1.010928961748634, |
| "grad_norm": 6.519931316375732, |
| "learning_rate": 2.9972677595628417e-05, |
| "loss": 0.796769380569458, |
| "step": 370 |
| }, |
| { |
| "epoch": 1.0382513661202186, |
| "grad_norm": 4.874457359313965, |
| "learning_rate": 2.98816029143898e-05, |
| "loss": 0.398636531829834, |
| "step": 380 |
| }, |
| { |
| "epoch": 1.0655737704918034, |
| "grad_norm": 15.488590240478516, |
| "learning_rate": 2.9790528233151184e-05, |
| "loss": 0.7061968803405761, |
| "step": 390 |
| }, |
| { |
| "epoch": 1.092896174863388, |
| "grad_norm": 19.74693489074707, |
| "learning_rate": 2.9699453551912568e-05, |
| "loss": 0.5211454391479492, |
| "step": 400 |
| }, |
| { |
| "epoch": 1.1202185792349726, |
| "grad_norm": 2.513188362121582, |
| "learning_rate": 2.9608378870673954e-05, |
| "loss": 0.7898036003112793, |
| "step": 410 |
| }, |
| { |
| "epoch": 1.1475409836065573, |
| "grad_norm": 25.31527328491211, |
| "learning_rate": 2.9517304189435338e-05, |
| "loss": 0.8195189476013184, |
| "step": 420 |
| }, |
| { |
| "epoch": 1.174863387978142, |
| "grad_norm": 26.276199340820312, |
| "learning_rate": 2.942622950819672e-05, |
| "loss": 0.8042145729064941, |
| "step": 430 |
| }, |
| { |
| "epoch": 1.2021857923497268, |
| "grad_norm": 19.838821411132812, |
| "learning_rate": 2.9335154826958105e-05, |
| "loss": 0.5532180786132812, |
| "step": 440 |
| }, |
| { |
| "epoch": 1.2295081967213115, |
| "grad_norm": 1.5704028606414795, |
| "learning_rate": 2.924408014571949e-05, |
| "loss": 0.46767144203186034, |
| "step": 450 |
| }, |
| { |
| "epoch": 1.2568306010928962, |
| "grad_norm": 0.24576333165168762, |
| "learning_rate": 2.9153005464480875e-05, |
| "loss": 0.7125775337219238, |
| "step": 460 |
| }, |
| { |
| "epoch": 1.2841530054644807, |
| "grad_norm": 2.8051435947418213, |
| "learning_rate": 2.9061930783242258e-05, |
| "loss": 1.4706084251403808, |
| "step": 470 |
| }, |
| { |
| "epoch": 1.3114754098360657, |
| "grad_norm": 2.1515614986419678, |
| "learning_rate": 2.897085610200364e-05, |
| "loss": 0.740934181213379, |
| "step": 480 |
| }, |
| { |
| "epoch": 1.3387978142076502, |
| "grad_norm": 5.335806846618652, |
| "learning_rate": 2.8879781420765028e-05, |
| "loss": 0.5567354679107666, |
| "step": 490 |
| }, |
| { |
| "epoch": 1.366120218579235, |
| "grad_norm": 9.499934196472168, |
| "learning_rate": 2.878870673952641e-05, |
| "loss": 0.5102160930633545, |
| "step": 500 |
| }, |
| { |
| "epoch": 1.3934426229508197, |
| "grad_norm": 0.30213791131973267, |
| "learning_rate": 2.8697632058287795e-05, |
| "loss": 0.8127809524536133, |
| "step": 510 |
| }, |
| { |
| "epoch": 1.4207650273224044, |
| "grad_norm": 17.827165603637695, |
| "learning_rate": 2.860655737704918e-05, |
| "loss": 1.3400749206542968, |
| "step": 520 |
| }, |
| { |
| "epoch": 1.4480874316939891, |
| "grad_norm": 2.58740234375, |
| "learning_rate": 2.8515482695810565e-05, |
| "loss": 0.5003597736358643, |
| "step": 530 |
| }, |
| { |
| "epoch": 1.4754098360655736, |
| "grad_norm": 22.007869720458984, |
| "learning_rate": 2.842440801457195e-05, |
| "loss": 1.6859323501586914, |
| "step": 540 |
| }, |
| { |
| "epoch": 1.5027322404371586, |
| "grad_norm": 14.658230781555176, |
| "learning_rate": 2.8333333333333332e-05, |
| "loss": 0.9195033073425293, |
| "step": 550 |
| }, |
| { |
| "epoch": 1.530054644808743, |
| "grad_norm": 1.4521483182907104, |
| "learning_rate": 2.8242258652094715e-05, |
| "loss": 0.4108741283416748, |
| "step": 560 |
| }, |
| { |
| "epoch": 1.5573770491803278, |
| "grad_norm": 10.377533912658691, |
| "learning_rate": 2.8151183970856102e-05, |
| "loss": 0.655418586730957, |
| "step": 570 |
| }, |
| { |
| "epoch": 1.5846994535519126, |
| "grad_norm": 0.5859184265136719, |
| "learning_rate": 2.8060109289617486e-05, |
| "loss": 1.2600435256958007, |
| "step": 580 |
| }, |
| { |
| "epoch": 1.6120218579234973, |
| "grad_norm": 0.8876230120658875, |
| "learning_rate": 2.796903460837887e-05, |
| "loss": 1.0982278823852538, |
| "step": 590 |
| }, |
| { |
| "epoch": 1.639344262295082, |
| "grad_norm": 13.285502433776855, |
| "learning_rate": 2.7877959927140256e-05, |
| "loss": 0.6685476779937745, |
| "step": 600 |
| }, |
| { |
| "epoch": 1.6666666666666665, |
| "grad_norm": 0.6555774211883545, |
| "learning_rate": 2.7786885245901642e-05, |
| "loss": 0.19812407493591308, |
| "step": 610 |
| }, |
| { |
| "epoch": 1.6939890710382515, |
| "grad_norm": 2.7470834255218506, |
| "learning_rate": 2.7695810564663026e-05, |
| "loss": 1.1334525108337403, |
| "step": 620 |
| }, |
| { |
| "epoch": 1.721311475409836, |
| "grad_norm": 14.42418098449707, |
| "learning_rate": 2.760473588342441e-05, |
| "loss": 0.9498401641845703, |
| "step": 630 |
| }, |
| { |
| "epoch": 1.748633879781421, |
| "grad_norm": 57.35378646850586, |
| "learning_rate": 2.7513661202185793e-05, |
| "loss": 1.2678983688354493, |
| "step": 640 |
| }, |
| { |
| "epoch": 1.7759562841530054, |
| "grad_norm": 0.7189310789108276, |
| "learning_rate": 2.742258652094718e-05, |
| "loss": 0.6106186389923096, |
| "step": 650 |
| }, |
| { |
| "epoch": 1.8032786885245902, |
| "grad_norm": 13.546385765075684, |
| "learning_rate": 2.7331511839708563e-05, |
| "loss": 1.4015119552612305, |
| "step": 660 |
| }, |
| { |
| "epoch": 1.830601092896175, |
| "grad_norm": 8.754522323608398, |
| "learning_rate": 2.7240437158469946e-05, |
| "loss": 0.9790468215942383, |
| "step": 670 |
| }, |
| { |
| "epoch": 1.8579234972677594, |
| "grad_norm": 13.214091300964355, |
| "learning_rate": 2.7149362477231333e-05, |
| "loss": 0.6752419948577881, |
| "step": 680 |
| }, |
| { |
| "epoch": 1.8852459016393444, |
| "grad_norm": 2.506131887435913, |
| "learning_rate": 2.7058287795992716e-05, |
| "loss": 0.2787914752960205, |
| "step": 690 |
| }, |
| { |
| "epoch": 1.9125683060109289, |
| "grad_norm": 0.4683574438095093, |
| "learning_rate": 2.69672131147541e-05, |
| "loss": 0.8134347915649414, |
| "step": 700 |
| }, |
| { |
| "epoch": 1.9398907103825138, |
| "grad_norm": 0.8958243131637573, |
| "learning_rate": 2.6876138433515483e-05, |
| "loss": 0.4489922046661377, |
| "step": 710 |
| }, |
| { |
| "epoch": 1.9672131147540983, |
| "grad_norm": 95.41824340820312, |
| "learning_rate": 2.678506375227687e-05, |
| "loss": 0.9731103897094726, |
| "step": 720 |
| }, |
| { |
| "epoch": 1.994535519125683, |
| "grad_norm": 0.7653670907020569, |
| "learning_rate": 2.6693989071038253e-05, |
| "loss": 1.0658687591552733, |
| "step": 730 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_accuracy": 0.8659, |
| "eval_confusion_matrix": [ |
| [ |
| 281, |
| 1 |
| ], |
| [ |
| 47, |
| 29 |
| ] |
| ], |
| "eval_f1": 0.5472, |
| "eval_loss": 0.45224741101264954, |
| "eval_pr_auc": 0.6674, |
| "eval_precision": 0.9667, |
| "eval_recall": 0.3816, |
| "eval_roc_auc": 0.8086, |
| "eval_runtime": 137.9939, |
| "eval_samples_per_second": 2.594, |
| "eval_steps_per_second": 0.652, |
| "step": 732 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 3660, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 10, |
| "save_steps": 500, |
| "stateful_callbacks": { |
| "EarlyStoppingCallback": { |
| "args": { |
| "early_stopping_patience": 3, |
| "early_stopping_threshold": 0.0 |
| }, |
| "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": 770389170094080.0, |
| "train_batch_size": 4, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
