| { | |
| "best_metric": 0.6948868632316589, | |
| "best_model_checkpoint": "/output/zgt-roberta-base-finetuned-Gu21schedule-BS256-10ep/checkpoint-31926", | |
| "epoch": 9.999029597282872, | |
| "global_step": 32200, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.1, | |
| "eval_accuracy": 0.15792088093844922, | |
| "eval_loss": 6.227477550506592, | |
| "eval_runtime": 1564.1073, | |
| "eval_samples_per_second": 65.972, | |
| "eval_steps_per_second": 4.124, | |
| "step": 313 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 9.316770186335403e-05, | |
| "loss": 7.1011, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "eval_accuracy": 0.17130737364600243, | |
| "eval_loss": 6.035614967346191, | |
| "eval_runtime": 1566.1128, | |
| "eval_samples_per_second": 65.887, | |
| "eval_steps_per_second": 4.118, | |
| "step": 626 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "eval_accuracy": 0.15421966595333422, | |
| "eval_loss": 5.970716953277588, | |
| "eval_runtime": 1567.0923, | |
| "eval_samples_per_second": 65.846, | |
| "eval_steps_per_second": 4.116, | |
| "step": 939 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 0.00018633540372670805, | |
| "loss": 6.0182, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "eval_accuracy": 0.17392094665213684, | |
| "eval_loss": 5.876271724700928, | |
| "eval_runtime": 1568.897, | |
| "eval_samples_per_second": 65.77, | |
| "eval_steps_per_second": 4.111, | |
| "step": 1252 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 0.0002795031055900621, | |
| "loss": 5.8908, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "eval_accuracy": 0.17560553688955177, | |
| "eval_loss": 5.8265557289123535, | |
| "eval_runtime": 1564.0767, | |
| "eval_samples_per_second": 65.973, | |
| "eval_steps_per_second": 4.124, | |
| "step": 1565 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "eval_accuracy": 0.1755758633601614, | |
| "eval_loss": 5.785298824310303, | |
| "eval_runtime": 1563.8448, | |
| "eval_samples_per_second": 65.983, | |
| "eval_steps_per_second": 4.124, | |
| "step": 1878 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 0.0003726708074534161, | |
| "loss": 5.8105, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "eval_accuracy": 0.1851031730080446, | |
| "eval_loss": 5.230679988861084, | |
| "eval_runtime": 1563.8141, | |
| "eval_samples_per_second": 65.984, | |
| "eval_steps_per_second": 4.125, | |
| "step": 2191 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 0.0004658385093167702, | |
| "loss": 4.8469, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "eval_accuracy": 0.49302250475931464, | |
| "eval_loss": 2.994337320327759, | |
| "eval_runtime": 1564.1944, | |
| "eval_samples_per_second": 65.968, | |
| "eval_steps_per_second": 4.124, | |
| "step": 2504 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "eval_accuracy": 0.6404133912717029, | |
| "eval_loss": 1.8836123943328857, | |
| "eval_runtime": 1565.3247, | |
| "eval_samples_per_second": 65.921, | |
| "eval_steps_per_second": 4.121, | |
| "step": 2817 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 0.0005590062111801242, | |
| "loss": 2.2431, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "eval_accuracy": 0.6801897739457411, | |
| "eval_loss": 1.6012158393859863, | |
| "eval_runtime": 1567.0654, | |
| "eval_samples_per_second": 65.847, | |
| "eval_steps_per_second": 4.116, | |
| "step": 3130 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "eval_accuracy": 0.7009936840521221, | |
| "eval_loss": 1.4589687585830688, | |
| "eval_runtime": 1567.9702, | |
| "eval_samples_per_second": 65.809, | |
| "eval_steps_per_second": 4.114, | |
| "step": 3443 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "learning_rate": 0.0005942028985507245, | |
| "loss": 1.618, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "eval_accuracy": 0.7143850078266079, | |
| "eval_loss": 1.3708570003509521, | |
| "eval_runtime": 1567.3868, | |
| "eval_samples_per_second": 65.834, | |
| "eval_steps_per_second": 4.115, | |
| "step": 3756 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "learning_rate": 0.0005838509316770186, | |
| "loss": 1.436, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "eval_accuracy": 0.725278557944805, | |
| "eval_loss": 1.2998367547988892, | |
| "eval_runtime": 1564.9997, | |
| "eval_samples_per_second": 65.934, | |
| "eval_steps_per_second": 4.121, | |
| "step": 4069 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "eval_accuracy": 0.7341513279268731, | |
| "eval_loss": 1.2506020069122314, | |
| "eval_runtime": 1565.2355, | |
| "eval_samples_per_second": 65.924, | |
| "eval_steps_per_second": 4.121, | |
| "step": 4382 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "learning_rate": 0.0005734989648033125, | |
| "loss": 1.3344, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 1.46, | |
| "eval_accuracy": 0.7414229730121367, | |
| "eval_loss": 1.2084842920303345, | |
| "eval_runtime": 1564.6672, | |
| "eval_samples_per_second": 65.948, | |
| "eval_steps_per_second": 4.122, | |
| "step": 4695 | |
| }, | |
| { | |
| "epoch": 1.55, | |
| "learning_rate": 0.0005631469979296066, | |
| "loss": 1.2678, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "eval_accuracy": 0.7460624134488423, | |
| "eval_loss": 1.1799527406692505, | |
| "eval_runtime": 1565.6909, | |
| "eval_samples_per_second": 65.905, | |
| "eval_steps_per_second": 4.12, | |
| "step": 5008 | |
| }, | |
| { | |
| "epoch": 1.65, | |
| "eval_accuracy": 0.7513162543657942, | |
| "eval_loss": 1.1497138738632202, | |
| "eval_runtime": 1565.9769, | |
| "eval_samples_per_second": 65.893, | |
| "eval_steps_per_second": 4.119, | |
| "step": 5321 | |
| }, | |
| { | |
| "epoch": 1.71, | |
| "learning_rate": 0.0005527950310559006, | |
| "loss": 1.2183, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "eval_accuracy": 0.7555471802775164, | |
| "eval_loss": 1.1244266033172607, | |
| "eval_runtime": 1565.313, | |
| "eval_samples_per_second": 65.921, | |
| "eval_steps_per_second": 4.121, | |
| "step": 5634 | |
| }, | |
| { | |
| "epoch": 1.85, | |
| "eval_accuracy": 0.7586796535932161, | |
| "eval_loss": 1.1065826416015625, | |
| "eval_runtime": 1565.5955, | |
| "eval_samples_per_second": 65.909, | |
| "eval_steps_per_second": 4.12, | |
| "step": 5947 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "learning_rate": 0.0005424430641821946, | |
| "loss": 1.1764, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 1.94, | |
| "eval_accuracy": 0.7621753158952852, | |
| "eval_loss": 1.0877457857131958, | |
| "eval_runtime": 1565.477, | |
| "eval_samples_per_second": 65.914, | |
| "eval_steps_per_second": 4.12, | |
| "step": 6260 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "learning_rate": 0.0005320910973084886, | |
| "loss": 1.1481, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 2.04, | |
| "eval_accuracy": 0.7653308256390273, | |
| "eval_loss": 1.069921851158142, | |
| "eval_runtime": 1565.5751, | |
| "eval_samples_per_second": 65.91, | |
| "eval_steps_per_second": 4.12, | |
| "step": 6573 | |
| }, | |
| { | |
| "epoch": 2.14, | |
| "eval_accuracy": 0.7669783269978627, | |
| "eval_loss": 1.059142827987671, | |
| "eval_runtime": 1564.7195, | |
| "eval_samples_per_second": 65.946, | |
| "eval_steps_per_second": 4.122, | |
| "step": 6886 | |
| }, | |
| { | |
| "epoch": 2.17, | |
| "learning_rate": 0.0005217391304347826, | |
| "loss": 1.1169, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 2.24, | |
| "eval_accuracy": 0.7701243077960133, | |
| "eval_loss": 1.0415377616882324, | |
| "eval_runtime": 1565.3407, | |
| "eval_samples_per_second": 65.92, | |
| "eval_steps_per_second": 4.121, | |
| "step": 7199 | |
| }, | |
| { | |
| "epoch": 2.33, | |
| "learning_rate": 0.0005113871635610765, | |
| "loss": 1.0953, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 2.33, | |
| "eval_accuracy": 0.7718881473585557, | |
| "eval_loss": 1.0299146175384521, | |
| "eval_runtime": 1565.1494, | |
| "eval_samples_per_second": 65.928, | |
| "eval_steps_per_second": 4.121, | |
| "step": 7512 | |
| }, | |
| { | |
| "epoch": 2.43, | |
| "eval_accuracy": 0.7742740416938212, | |
| "eval_loss": 1.0169405937194824, | |
| "eval_runtime": 1565.1719, | |
| "eval_samples_per_second": 65.927, | |
| "eval_steps_per_second": 4.121, | |
| "step": 7825 | |
| }, | |
| { | |
| "epoch": 2.48, | |
| "learning_rate": 0.0005010351966873705, | |
| "loss": 1.0743, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 2.53, | |
| "eval_accuracy": 0.7762836729268914, | |
| "eval_loss": 1.006744146347046, | |
| "eval_runtime": 1565.0712, | |
| "eval_samples_per_second": 65.931, | |
| "eval_steps_per_second": 4.121, | |
| "step": 8138 | |
| }, | |
| { | |
| "epoch": 2.62, | |
| "eval_accuracy": 0.7780289191145969, | |
| "eval_loss": 0.9963796734809875, | |
| "eval_runtime": 1564.7218, | |
| "eval_samples_per_second": 65.946, | |
| "eval_steps_per_second": 4.122, | |
| "step": 8451 | |
| }, | |
| { | |
| "epoch": 2.64, | |
| "learning_rate": 0.0004906832298136645, | |
| "loss": 1.0582, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 2.72, | |
| "eval_accuracy": 0.7799966088129119, | |
| "eval_loss": 0.9861342310905457, | |
| "eval_runtime": 1564.6716, | |
| "eval_samples_per_second": 65.948, | |
| "eval_steps_per_second": 4.122, | |
| "step": 8764 | |
| }, | |
| { | |
| "epoch": 2.79, | |
| "learning_rate": 0.00048033126293995856, | |
| "loss": 1.0401, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 2.82, | |
| "eval_accuracy": 0.7818533899689635, | |
| "eval_loss": 0.9751449227333069, | |
| "eval_runtime": 1564.9804, | |
| "eval_samples_per_second": 65.935, | |
| "eval_steps_per_second": 4.121, | |
| "step": 9077 | |
| }, | |
| { | |
| "epoch": 2.92, | |
| "eval_accuracy": 0.7830731640909905, | |
| "eval_loss": 0.9680520296096802, | |
| "eval_runtime": 1565.4431, | |
| "eval_samples_per_second": 65.916, | |
| "eval_steps_per_second": 4.12, | |
| "step": 9390 | |
| }, | |
| { | |
| "epoch": 2.95, | |
| "learning_rate": 0.00046997929606625255, | |
| "loss": 1.0262, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 3.01, | |
| "eval_accuracy": 0.7843024373004699, | |
| "eval_loss": 0.9606424570083618, | |
| "eval_runtime": 1565.1725, | |
| "eval_samples_per_second": 65.927, | |
| "eval_steps_per_second": 4.121, | |
| "step": 9703 | |
| }, | |
| { | |
| "epoch": 3.11, | |
| "learning_rate": 0.0004596273291925466, | |
| "loss": 1.0093, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 3.11, | |
| "eval_accuracy": 0.7858115501363246, | |
| "eval_loss": 0.9535852670669556, | |
| "eval_runtime": 1564.8587, | |
| "eval_samples_per_second": 65.94, | |
| "eval_steps_per_second": 4.122, | |
| "step": 10016 | |
| }, | |
| { | |
| "epoch": 3.21, | |
| "eval_accuracy": 0.7874158219284931, | |
| "eval_loss": 0.9444663524627686, | |
| "eval_runtime": 1564.7558, | |
| "eval_samples_per_second": 65.944, | |
| "eval_steps_per_second": 4.122, | |
| "step": 10329 | |
| }, | |
| { | |
| "epoch": 3.26, | |
| "learning_rate": 0.0004492753623188405, | |
| "loss": 0.995, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 3.3, | |
| "eval_accuracy": 0.7884454282264995, | |
| "eval_loss": 0.9367947578430176, | |
| "eval_runtime": 1565.5731, | |
| "eval_samples_per_second": 65.91, | |
| "eval_steps_per_second": 4.12, | |
| "step": 10642 | |
| }, | |
| { | |
| "epoch": 3.4, | |
| "eval_accuracy": 0.7902011668190658, | |
| "eval_loss": 0.9284105896949768, | |
| "eval_runtime": 1564.8586, | |
| "eval_samples_per_second": 65.94, | |
| "eval_steps_per_second": 4.122, | |
| "step": 10955 | |
| }, | |
| { | |
| "epoch": 3.42, | |
| "learning_rate": 0.0004389233954451345, | |
| "loss": 0.983, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 3.5, | |
| "eval_accuracy": 0.7912236011775762, | |
| "eval_loss": 0.9227182269096375, | |
| "eval_runtime": 1564.9848, | |
| "eval_samples_per_second": 65.935, | |
| "eval_steps_per_second": 4.121, | |
| "step": 11268 | |
| }, | |
| { | |
| "epoch": 3.57, | |
| "learning_rate": 0.00042857142857142855, | |
| "loss": 0.9728, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 3.6, | |
| "eval_accuracy": 0.7926902278847275, | |
| "eval_loss": 0.9144140481948853, | |
| "eval_runtime": 1564.605, | |
| "eval_samples_per_second": 65.951, | |
| "eval_steps_per_second": 4.122, | |
| "step": 11581 | |
| }, | |
| { | |
| "epoch": 3.69, | |
| "eval_accuracy": 0.7936642140619866, | |
| "eval_loss": 0.9096552133560181, | |
| "eval_runtime": 1565.1262, | |
| "eval_samples_per_second": 65.929, | |
| "eval_steps_per_second": 4.121, | |
| "step": 11894 | |
| }, | |
| { | |
| "epoch": 3.73, | |
| "learning_rate": 0.00041821946169772254, | |
| "loss": 0.9632, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 3.79, | |
| "eval_accuracy": 0.7947595817774112, | |
| "eval_loss": 0.9028408527374268, | |
| "eval_runtime": 1564.7786, | |
| "eval_samples_per_second": 65.944, | |
| "eval_steps_per_second": 4.122, | |
| "step": 12207 | |
| }, | |
| { | |
| "epoch": 3.88, | |
| "learning_rate": 0.0004078674948240166, | |
| "loss": 0.953, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 3.89, | |
| "eval_accuracy": 0.7958614481801236, | |
| "eval_loss": 0.896992564201355, | |
| "eval_runtime": 1564.1136, | |
| "eval_samples_per_second": 65.972, | |
| "eval_steps_per_second": 4.124, | |
| "step": 12520 | |
| }, | |
| { | |
| "epoch": 3.99, | |
| "eval_accuracy": 0.796848649990296, | |
| "eval_loss": 0.8908724188804626, | |
| "eval_runtime": 1564.2284, | |
| "eval_samples_per_second": 65.967, | |
| "eval_steps_per_second": 4.123, | |
| "step": 12833 | |
| }, | |
| { | |
| "epoch": 4.04, | |
| "learning_rate": 0.0003975155279503105, | |
| "loss": 0.9414, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 4.08, | |
| "eval_accuracy": 0.797744672086327, | |
| "eval_loss": 0.8873794674873352, | |
| "eval_runtime": 1565.739, | |
| "eval_samples_per_second": 65.903, | |
| "eval_steps_per_second": 4.119, | |
| "step": 13146 | |
| }, | |
| { | |
| "epoch": 4.18, | |
| "eval_accuracy": 0.7986036425092956, | |
| "eval_loss": 0.881266713142395, | |
| "eval_runtime": 1565.4321, | |
| "eval_samples_per_second": 65.916, | |
| "eval_steps_per_second": 4.12, | |
| "step": 13459 | |
| }, | |
| { | |
| "epoch": 4.19, | |
| "learning_rate": 0.0003871635610766045, | |
| "loss": 0.9287, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 4.28, | |
| "eval_accuracy": 0.7999304297565917, | |
| "eval_loss": 0.8743026852607727, | |
| "eval_runtime": 1564.903, | |
| "eval_samples_per_second": 65.938, | |
| "eval_steps_per_second": 4.122, | |
| "step": 13772 | |
| }, | |
| { | |
| "epoch": 4.35, | |
| "learning_rate": 0.00037681159420289854, | |
| "loss": 0.9219, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 4.37, | |
| "eval_accuracy": 0.80051802299604, | |
| "eval_loss": 0.8717477917671204, | |
| "eval_runtime": 1565.3161, | |
| "eval_samples_per_second": 65.921, | |
| "eval_steps_per_second": 4.121, | |
| "step": 14085 | |
| }, | |
| { | |
| "epoch": 4.47, | |
| "eval_accuracy": 0.801263244223999, | |
| "eval_loss": 0.8662565350532532, | |
| "eval_runtime": 1564.6984, | |
| "eval_samples_per_second": 65.947, | |
| "eval_steps_per_second": 4.122, | |
| "step": 14398 | |
| }, | |
| { | |
| "epoch": 4.5, | |
| "learning_rate": 0.0003664596273291925, | |
| "loss": 0.9137, | |
| "step": 14500 | |
| }, | |
| { | |
| "epoch": 4.57, | |
| "eval_accuracy": 0.8024215648096065, | |
| "eval_loss": 0.8607039451599121, | |
| "eval_runtime": 1565.2999, | |
| "eval_samples_per_second": 65.922, | |
| "eval_steps_per_second": 4.121, | |
| "step": 14711 | |
| }, | |
| { | |
| "epoch": 4.66, | |
| "learning_rate": 0.0003561076604554865, | |
| "loss": 0.9062, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 4.67, | |
| "eval_accuracy": 0.80312043845701, | |
| "eval_loss": 0.8565826416015625, | |
| "eval_runtime": 1566.6554, | |
| "eval_samples_per_second": 65.865, | |
| "eval_steps_per_second": 4.117, | |
| "step": 15024 | |
| }, | |
| { | |
| "epoch": 4.76, | |
| "eval_accuracy": 0.8044941042086672, | |
| "eval_loss": 0.8497495055198669, | |
| "eval_runtime": 1566.3382, | |
| "eval_samples_per_second": 65.878, | |
| "eval_steps_per_second": 4.118, | |
| "step": 15337 | |
| }, | |
| { | |
| "epoch": 4.81, | |
| "learning_rate": 0.0003457556935817805, | |
| "loss": 0.8978, | |
| "step": 15500 | |
| }, | |
| { | |
| "epoch": 4.86, | |
| "eval_accuracy": 0.8053608800858211, | |
| "eval_loss": 0.8438310623168945, | |
| "eval_runtime": 1565.4433, | |
| "eval_samples_per_second": 65.916, | |
| "eval_steps_per_second": 4.12, | |
| "step": 15650 | |
| }, | |
| { | |
| "epoch": 4.96, | |
| "eval_accuracy": 0.8064097453094475, | |
| "eval_loss": 0.8402115702629089, | |
| "eval_runtime": 1565.8792, | |
| "eval_samples_per_second": 65.897, | |
| "eval_steps_per_second": 4.119, | |
| "step": 15963 | |
| }, | |
| { | |
| "epoch": 4.97, | |
| "learning_rate": 0.0003354037267080745, | |
| "loss": 0.8907, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 5.05, | |
| "eval_accuracy": 0.8072085264677659, | |
| "eval_loss": 0.8345613479614258, | |
| "eval_runtime": 1565.4826, | |
| "eval_samples_per_second": 65.914, | |
| "eval_steps_per_second": 4.12, | |
| "step": 16276 | |
| }, | |
| { | |
| "epoch": 5.12, | |
| "learning_rate": 0.0003250517598343685, | |
| "loss": 0.8791, | |
| "step": 16500 | |
| }, | |
| { | |
| "epoch": 5.15, | |
| "eval_accuracy": 0.8079710854147522, | |
| "eval_loss": 0.8311530947685242, | |
| "eval_runtime": 1565.3772, | |
| "eval_samples_per_second": 65.918, | |
| "eval_steps_per_second": 4.12, | |
| "step": 16589 | |
| }, | |
| { | |
| "epoch": 5.25, | |
| "eval_accuracy": 0.808113472692542, | |
| "eval_loss": 0.8312503695487976, | |
| "eval_runtime": 1564.9419, | |
| "eval_samples_per_second": 65.937, | |
| "eval_steps_per_second": 4.122, | |
| "step": 16902 | |
| }, | |
| { | |
| "epoch": 5.28, | |
| "learning_rate": 0.00031469979296066245, | |
| "loss": 0.8713, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 5.35, | |
| "eval_accuracy": 0.8089870028151737, | |
| "eval_loss": 0.8246920108795166, | |
| "eval_runtime": 1566.1653, | |
| "eval_samples_per_second": 65.885, | |
| "eval_steps_per_second": 4.118, | |
| "step": 17215 | |
| }, | |
| { | |
| "epoch": 5.43, | |
| "learning_rate": 0.0003043478260869565, | |
| "loss": 0.866, | |
| "step": 17500 | |
| }, | |
| { | |
| "epoch": 5.44, | |
| "eval_accuracy": 0.8100817167380647, | |
| "eval_loss": 0.8203573822975159, | |
| "eval_runtime": 1563.7507, | |
| "eval_samples_per_second": 65.987, | |
| "eval_steps_per_second": 4.125, | |
| "step": 17528 | |
| }, | |
| { | |
| "epoch": 5.54, | |
| "eval_accuracy": 0.8106388454645975, | |
| "eval_loss": 0.8163631558418274, | |
| "eval_runtime": 1563.2024, | |
| "eval_samples_per_second": 66.01, | |
| "eval_steps_per_second": 4.126, | |
| "step": 17841 | |
| }, | |
| { | |
| "epoch": 5.59, | |
| "learning_rate": 0.0002939958592132505, | |
| "loss": 0.8607, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 5.64, | |
| "eval_accuracy": 0.8114071774300123, | |
| "eval_loss": 0.8129469752311707, | |
| "eval_runtime": 1563.1261, | |
| "eval_samples_per_second": 66.013, | |
| "eval_steps_per_second": 4.126, | |
| "step": 18154 | |
| }, | |
| { | |
| "epoch": 5.73, | |
| "eval_accuracy": 0.8122062364179543, | |
| "eval_loss": 0.808627724647522, | |
| "eval_runtime": 1564.3551, | |
| "eval_samples_per_second": 65.961, | |
| "eval_steps_per_second": 4.123, | |
| "step": 18467 | |
| }, | |
| { | |
| "epoch": 5.74, | |
| "learning_rate": 0.00028364389233954447, | |
| "loss": 0.8534, | |
| "step": 18500 | |
| }, | |
| { | |
| "epoch": 5.83, | |
| "eval_accuracy": 0.8128903362394657, | |
| "eval_loss": 0.8055641651153564, | |
| "eval_runtime": 1563.7512, | |
| "eval_samples_per_second": 65.987, | |
| "eval_steps_per_second": 4.125, | |
| "step": 18780 | |
| }, | |
| { | |
| "epoch": 5.9, | |
| "learning_rate": 0.0002732919254658385, | |
| "loss": 0.8448, | |
| "step": 19000 | |
| }, | |
| { | |
| "epoch": 5.93, | |
| "eval_accuracy": 0.8134494722363886, | |
| "eval_loss": 0.8019941449165344, | |
| "eval_runtime": 1563.2984, | |
| "eval_samples_per_second": 66.006, | |
| "eval_steps_per_second": 4.126, | |
| "step": 19093 | |
| }, | |
| { | |
| "epoch": 6.03, | |
| "eval_accuracy": 0.8143192139194421, | |
| "eval_loss": 0.7982867956161499, | |
| "eval_runtime": 1563.6693, | |
| "eval_samples_per_second": 65.99, | |
| "eval_steps_per_second": 4.125, | |
| "step": 19406 | |
| }, | |
| { | |
| "epoch": 6.06, | |
| "learning_rate": 0.0002629399585921325, | |
| "loss": 0.8391, | |
| "step": 19500 | |
| }, | |
| { | |
| "epoch": 6.12, | |
| "eval_accuracy": 0.8147886522353383, | |
| "eval_loss": 0.7949500679969788, | |
| "eval_runtime": 1563.7961, | |
| "eval_samples_per_second": 65.985, | |
| "eval_steps_per_second": 4.125, | |
| "step": 19719 | |
| }, | |
| { | |
| "epoch": 6.21, | |
| "learning_rate": 0.0002525879917184265, | |
| "loss": 0.8304, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 6.22, | |
| "eval_accuracy": 0.8155781682195781, | |
| "eval_loss": 0.7908634543418884, | |
| "eval_runtime": 1563.2059, | |
| "eval_samples_per_second": 66.01, | |
| "eval_steps_per_second": 4.126, | |
| "step": 20032 | |
| }, | |
| { | |
| "epoch": 6.32, | |
| "eval_accuracy": 0.816149684044946, | |
| "eval_loss": 0.7888238430023193, | |
| "eval_runtime": 1565.7848, | |
| "eval_samples_per_second": 65.901, | |
| "eval_steps_per_second": 4.119, | |
| "step": 20345 | |
| }, | |
| { | |
| "epoch": 6.37, | |
| "learning_rate": 0.00024223602484472047, | |
| "loss": 0.825, | |
| "step": 20500 | |
| }, | |
| { | |
| "epoch": 6.41, | |
| "eval_accuracy": 0.8167946967773272, | |
| "eval_loss": 0.7858228087425232, | |
| "eval_runtime": 1565.9773, | |
| "eval_samples_per_second": 65.893, | |
| "eval_steps_per_second": 4.119, | |
| "step": 20658 | |
| }, | |
| { | |
| "epoch": 6.51, | |
| "eval_accuracy": 0.8174543786608812, | |
| "eval_loss": 0.7798792123794556, | |
| "eval_runtime": 1566.9273, | |
| "eval_samples_per_second": 65.853, | |
| "eval_steps_per_second": 4.116, | |
| "step": 20971 | |
| }, | |
| { | |
| "epoch": 6.52, | |
| "learning_rate": 0.00023188405797101448, | |
| "loss": 0.8198, | |
| "step": 21000 | |
| }, | |
| { | |
| "epoch": 6.61, | |
| "eval_accuracy": 0.818135156601779, | |
| "eval_loss": 0.7765618562698364, | |
| "eval_runtime": 1568.3727, | |
| "eval_samples_per_second": 65.792, | |
| "eval_steps_per_second": 4.113, | |
| "step": 21284 | |
| }, | |
| { | |
| "epoch": 6.68, | |
| "learning_rate": 0.00022153209109730847, | |
| "loss": 0.8139, | |
| "step": 21500 | |
| }, | |
| { | |
| "epoch": 6.71, | |
| "eval_accuracy": 0.8189553029778005, | |
| "eval_loss": 0.7735697627067566, | |
| "eval_runtime": 1567.9384, | |
| "eval_samples_per_second": 65.811, | |
| "eval_steps_per_second": 4.114, | |
| "step": 21597 | |
| }, | |
| { | |
| "epoch": 6.8, | |
| "eval_accuracy": 0.8195096365262311, | |
| "eval_loss": 0.7705960273742676, | |
| "eval_runtime": 1568.1878, | |
| "eval_samples_per_second": 65.8, | |
| "eval_steps_per_second": 4.113, | |
| "step": 21910 | |
| }, | |
| { | |
| "epoch": 6.83, | |
| "learning_rate": 0.00021118012422360248, | |
| "loss": 0.8094, | |
| "step": 22000 | |
| }, | |
| { | |
| "epoch": 6.9, | |
| "eval_accuracy": 0.8200746154831311, | |
| "eval_loss": 0.7673328518867493, | |
| "eval_runtime": 1567.3958, | |
| "eval_samples_per_second": 65.833, | |
| "eval_steps_per_second": 4.115, | |
| "step": 22223 | |
| }, | |
| { | |
| "epoch": 6.99, | |
| "learning_rate": 0.00020082815734989647, | |
| "loss": 0.8032, | |
| "step": 22500 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_accuracy": 0.8205203976743998, | |
| "eval_loss": 0.764415979385376, | |
| "eval_runtime": 1567.2437, | |
| "eval_samples_per_second": 65.84, | |
| "eval_steps_per_second": 4.116, | |
| "step": 22536 | |
| }, | |
| { | |
| "epoch": 7.1, | |
| "eval_accuracy": 0.8215158231256271, | |
| "eval_loss": 0.7607036232948303, | |
| "eval_runtime": 1568.907, | |
| "eval_samples_per_second": 65.77, | |
| "eval_steps_per_second": 4.111, | |
| "step": 22849 | |
| }, | |
| { | |
| "epoch": 7.14, | |
| "learning_rate": 0.00019047619047619045, | |
| "loss": 0.794, | |
| "step": 23000 | |
| }, | |
| { | |
| "epoch": 7.19, | |
| "eval_accuracy": 0.8218634447758527, | |
| "eval_loss": 0.7578034996986389, | |
| "eval_runtime": 1562.4876, | |
| "eval_samples_per_second": 66.04, | |
| "eval_steps_per_second": 4.128, | |
| "step": 23162 | |
| }, | |
| { | |
| "epoch": 7.29, | |
| "eval_accuracy": 0.8225726120979496, | |
| "eval_loss": 0.7539456486701965, | |
| "eval_runtime": 1563.2377, | |
| "eval_samples_per_second": 66.009, | |
| "eval_steps_per_second": 4.126, | |
| "step": 23475 | |
| }, | |
| { | |
| "epoch": 7.3, | |
| "learning_rate": 0.00018012422360248444, | |
| "loss": 0.7891, | |
| "step": 23500 | |
| }, | |
| { | |
| "epoch": 7.39, | |
| "eval_accuracy": 0.8229123629611099, | |
| "eval_loss": 0.751589298248291, | |
| "eval_runtime": 1562.2621, | |
| "eval_samples_per_second": 66.05, | |
| "eval_steps_per_second": 4.129, | |
| "step": 23788 | |
| }, | |
| { | |
| "epoch": 7.45, | |
| "learning_rate": 0.00016977225672877845, | |
| "loss": 0.7854, | |
| "step": 24000 | |
| }, | |
| { | |
| "epoch": 7.48, | |
| "eval_accuracy": 0.8234190549813617, | |
| "eval_loss": 0.7492088079452515, | |
| "eval_runtime": 1562.6896, | |
| "eval_samples_per_second": 66.032, | |
| "eval_steps_per_second": 4.127, | |
| "step": 24101 | |
| }, | |
| { | |
| "epoch": 7.58, | |
| "eval_accuracy": 0.823868769101777, | |
| "eval_loss": 0.7464490532875061, | |
| "eval_runtime": 1563.2351, | |
| "eval_samples_per_second": 66.009, | |
| "eval_steps_per_second": 4.126, | |
| "step": 24414 | |
| }, | |
| { | |
| "epoch": 7.61, | |
| "learning_rate": 0.00015942028985507247, | |
| "loss": 0.7813, | |
| "step": 24500 | |
| }, | |
| { | |
| "epoch": 7.68, | |
| "eval_accuracy": 0.8245509114698386, | |
| "eval_loss": 0.7424126863479614, | |
| "eval_runtime": 1563.6491, | |
| "eval_samples_per_second": 65.991, | |
| "eval_steps_per_second": 4.125, | |
| "step": 24727 | |
| }, | |
| { | |
| "epoch": 7.76, | |
| "learning_rate": 0.00014906832298136645, | |
| "loss": 0.7757, | |
| "step": 25000 | |
| }, | |
| { | |
| "epoch": 7.78, | |
| "eval_accuracy": 0.8252597131033751, | |
| "eval_loss": 0.7401213049888611, | |
| "eval_runtime": 1563.1841, | |
| "eval_samples_per_second": 66.011, | |
| "eval_steps_per_second": 4.126, | |
| "step": 25040 | |
| }, | |
| { | |
| "epoch": 7.87, | |
| "eval_accuracy": 0.8254715067571893, | |
| "eval_loss": 0.7378228306770325, | |
| "eval_runtime": 1563.1126, | |
| "eval_samples_per_second": 66.014, | |
| "eval_steps_per_second": 4.126, | |
| "step": 25353 | |
| }, | |
| { | |
| "epoch": 7.92, | |
| "learning_rate": 0.00013871635610766044, | |
| "loss": 0.7722, | |
| "step": 25500 | |
| }, | |
| { | |
| "epoch": 7.97, | |
| "eval_accuracy": 0.8263812114502447, | |
| "eval_loss": 0.734555184841156, | |
| "eval_runtime": 1563.3264, | |
| "eval_samples_per_second": 66.005, | |
| "eval_steps_per_second": 4.126, | |
| "step": 25666 | |
| }, | |
| { | |
| "epoch": 8.07, | |
| "eval_accuracy": 0.8266910048907001, | |
| "eval_loss": 0.7316432595252991, | |
| "eval_runtime": 1565.1422, | |
| "eval_samples_per_second": 65.928, | |
| "eval_steps_per_second": 4.121, | |
| "step": 25979 | |
| }, | |
| { | |
| "epoch": 8.07, | |
| "learning_rate": 0.00012836438923395443, | |
| "loss": 0.765, | |
| "step": 26000 | |
| }, | |
| { | |
| "epoch": 8.16, | |
| "eval_accuracy": 0.8270383479169559, | |
| "eval_loss": 0.7292919754981995, | |
| "eval_runtime": 1563.9337, | |
| "eval_samples_per_second": 65.979, | |
| "eval_steps_per_second": 4.124, | |
| "step": 26292 | |
| }, | |
| { | |
| "epoch": 8.23, | |
| "learning_rate": 0.00011801242236024844, | |
| "loss": 0.7584, | |
| "step": 26500 | |
| }, | |
| { | |
| "epoch": 8.26, | |
| "eval_accuracy": 0.8277969783059648, | |
| "eval_loss": 0.7266284227371216, | |
| "eval_runtime": 1566.4843, | |
| "eval_samples_per_second": 65.872, | |
| "eval_steps_per_second": 4.118, | |
| "step": 26605 | |
| }, | |
| { | |
| "epoch": 8.36, | |
| "eval_accuracy": 0.8280860122956746, | |
| "eval_loss": 0.7245298624038696, | |
| "eval_runtime": 1564.0929, | |
| "eval_samples_per_second": 65.972, | |
| "eval_steps_per_second": 4.124, | |
| "step": 26918 | |
| }, | |
| { | |
| "epoch": 8.38, | |
| "learning_rate": 0.00010766045548654244, | |
| "loss": 0.7565, | |
| "step": 27000 | |
| }, | |
| { | |
| "epoch": 8.46, | |
| "eval_accuracy": 0.8286899161017834, | |
| "eval_loss": 0.7209280729293823, | |
| "eval_runtime": 1567.5209, | |
| "eval_samples_per_second": 65.828, | |
| "eval_steps_per_second": 4.115, | |
| "step": 27231 | |
| }, | |
| { | |
| "epoch": 8.54, | |
| "learning_rate": 9.730848861283643e-05, | |
| "loss": 0.7506, | |
| "step": 27500 | |
| }, | |
| { | |
| "epoch": 8.55, | |
| "eval_accuracy": 0.829094583836786, | |
| "eval_loss": 0.7193953990936279, | |
| "eval_runtime": 1567.7556, | |
| "eval_samples_per_second": 65.818, | |
| "eval_steps_per_second": 4.114, | |
| "step": 27544 | |
| }, | |
| { | |
| "epoch": 8.65, | |
| "eval_accuracy": 0.8296025421755568, | |
| "eval_loss": 0.7171857357025146, | |
| "eval_runtime": 1567.618, | |
| "eval_samples_per_second": 65.824, | |
| "eval_steps_per_second": 4.115, | |
| "step": 27857 | |
| }, | |
| { | |
| "epoch": 8.69, | |
| "learning_rate": 8.695652173913043e-05, | |
| "loss": 0.7469, | |
| "step": 28000 | |
| }, | |
| { | |
| "epoch": 8.75, | |
| "eval_accuracy": 0.8297588118895532, | |
| "eval_loss": 0.715788722038269, | |
| "eval_runtime": 1568.2621, | |
| "eval_samples_per_second": 65.797, | |
| "eval_steps_per_second": 4.113, | |
| "step": 28170 | |
| }, | |
| { | |
| "epoch": 8.84, | |
| "eval_accuracy": 0.8303201783553539, | |
| "eval_loss": 0.7129087448120117, | |
| "eval_runtime": 1566.51, | |
| "eval_samples_per_second": 65.871, | |
| "eval_steps_per_second": 4.117, | |
| "step": 28483 | |
| }, | |
| { | |
| "epoch": 8.85, | |
| "learning_rate": 7.660455486542441e-05, | |
| "loss": 0.7434, | |
| "step": 28500 | |
| }, | |
| { | |
| "epoch": 8.94, | |
| "eval_accuracy": 0.8310723013027939, | |
| "eval_loss": 0.7107537984848022, | |
| "eval_runtime": 1565.7298, | |
| "eval_samples_per_second": 65.903, | |
| "eval_steps_per_second": 4.119, | |
| "step": 28796 | |
| }, | |
| { | |
| "epoch": 9.01, | |
| "learning_rate": 6.625258799171841e-05, | |
| "loss": 0.7395, | |
| "step": 29000 | |
| }, | |
| { | |
| "epoch": 9.04, | |
| "eval_accuracy": 0.8311976533176414, | |
| "eval_loss": 0.7103267908096313, | |
| "eval_runtime": 1566.6592, | |
| "eval_samples_per_second": 65.864, | |
| "eval_steps_per_second": 4.117, | |
| "step": 29109 | |
| }, | |
| { | |
| "epoch": 9.14, | |
| "eval_accuracy": 0.831599738008909, | |
| "eval_loss": 0.7076959609985352, | |
| "eval_runtime": 1563.475, | |
| "eval_samples_per_second": 65.998, | |
| "eval_steps_per_second": 4.125, | |
| "step": 29422 | |
| }, | |
| { | |
| "epoch": 9.16, | |
| "learning_rate": 5.5900621118012414e-05, | |
| "loss": 0.7327, | |
| "step": 29500 | |
| }, | |
| { | |
| "epoch": 9.23, | |
| "eval_accuracy": 0.8318789165507281, | |
| "eval_loss": 0.7060185074806213, | |
| "eval_runtime": 1563.2277, | |
| "eval_samples_per_second": 66.009, | |
| "eval_steps_per_second": 4.126, | |
| "step": 29735 | |
| }, | |
| { | |
| "epoch": 9.32, | |
| "learning_rate": 4.554865424430642e-05, | |
| "loss": 0.7294, | |
| "step": 30000 | |
| }, | |
| { | |
| "epoch": 9.33, | |
| "eval_accuracy": 0.8324941188917658, | |
| "eval_loss": 0.7029792070388794, | |
| "eval_runtime": 1563.5398, | |
| "eval_samples_per_second": 65.996, | |
| "eval_steps_per_second": 4.125, | |
| "step": 30048 | |
| }, | |
| { | |
| "epoch": 9.43, | |
| "eval_accuracy": 0.832804502850609, | |
| "eval_loss": 0.7012088298797607, | |
| "eval_runtime": 1563.5997, | |
| "eval_samples_per_second": 65.993, | |
| "eval_steps_per_second": 4.125, | |
| "step": 30361 | |
| }, | |
| { | |
| "epoch": 9.47, | |
| "learning_rate": 3.5196687370600414e-05, | |
| "loss": 0.7277, | |
| "step": 30500 | |
| }, | |
| { | |
| "epoch": 9.53, | |
| "eval_accuracy": 0.8329869074323458, | |
| "eval_loss": 0.7000030875205994, | |
| "eval_runtime": 1563.8346, | |
| "eval_samples_per_second": 65.983, | |
| "eval_steps_per_second": 4.124, | |
| "step": 30674 | |
| }, | |
| { | |
| "epoch": 9.62, | |
| "eval_accuracy": 0.8334238360274034, | |
| "eval_loss": 0.6988800764083862, | |
| "eval_runtime": 1563.4183, | |
| "eval_samples_per_second": 66.001, | |
| "eval_steps_per_second": 4.126, | |
| "step": 30987 | |
| }, | |
| { | |
| "epoch": 9.63, | |
| "learning_rate": 2.4844720496894407e-05, | |
| "loss": 0.7237, | |
| "step": 31000 | |
| }, | |
| { | |
| "epoch": 9.72, | |
| "eval_accuracy": 0.8335258711989345, | |
| "eval_loss": 0.6981679201126099, | |
| "eval_runtime": 1564.2656, | |
| "eval_samples_per_second": 65.965, | |
| "eval_steps_per_second": 4.123, | |
| "step": 31300 | |
| }, | |
| { | |
| "epoch": 9.78, | |
| "learning_rate": 1.4492753623188405e-05, | |
| "loss": 0.7233, | |
| "step": 31500 | |
| }, | |
| { | |
| "epoch": 9.82, | |
| "eval_accuracy": 0.8338284368943191, | |
| "eval_loss": 0.6956919431686401, | |
| "eval_runtime": 1565.7206, | |
| "eval_samples_per_second": 65.904, | |
| "eval_steps_per_second": 4.12, | |
| "step": 31613 | |
| }, | |
| { | |
| "epoch": 9.91, | |
| "eval_accuracy": 0.8342045312252818, | |
| "eval_loss": 0.6948868632316589, | |
| "eval_runtime": 1564.1555, | |
| "eval_samples_per_second": 65.97, | |
| "eval_steps_per_second": 4.124, | |
| "step": 31926 | |
| }, | |
| { | |
| "epoch": 9.94, | |
| "learning_rate": 4.140786749482401e-06, | |
| "loss": 0.7196, | |
| "step": 32000 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "step": 32200, | |
| "total_flos": 2.1701190649823816e+18, | |
| "train_loss": 1.3247782011802152, | |
| "train_runtime": 514233.1245, | |
| "train_samples_per_second": 16.031, | |
| "train_steps_per_second": 0.063 | |
| } | |
| ], | |
| "max_steps": 32200, | |
| "num_train_epochs": 10, | |
| "total_flos": 2.1701190649823816e+18, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |