| { | |
| "best_metric": 0.8676470588235294, | |
| "best_model_checkpoint": "mobilenet_v2_1.0_224-finetuned-papsmear/checkpoint-1797", | |
| "epoch": 59.6078431372549, | |
| "eval_steps": 500, | |
| "global_step": 2280, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.26143790849673204, | |
| "grad_norm": 9.104169845581055, | |
| "learning_rate": 2.1929824561403507e-06, | |
| "loss": 1.8301, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.5228758169934641, | |
| "grad_norm": 8.698704719543457, | |
| "learning_rate": 4.3859649122807014e-06, | |
| "loss": 1.8234, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.7843137254901961, | |
| "grad_norm": 9.768064498901367, | |
| "learning_rate": 6.578947368421053e-06, | |
| "loss": 1.7932, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.9934640522875817, | |
| "eval_accuracy": 0.25, | |
| "eval_loss": 1.7606836557388306, | |
| "eval_runtime": 20.4249, | |
| "eval_samples_per_second": 6.659, | |
| "eval_steps_per_second": 0.832, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 1.0457516339869282, | |
| "grad_norm": 8.835221290588379, | |
| "learning_rate": 8.771929824561403e-06, | |
| "loss": 1.7895, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.3071895424836601, | |
| "grad_norm": 9.015777587890625, | |
| "learning_rate": 1.0964912280701754e-05, | |
| "loss": 1.7622, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.5686274509803921, | |
| "grad_norm": 8.489930152893066, | |
| "learning_rate": 1.3157894736842106e-05, | |
| "loss": 1.7277, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 1.8300653594771243, | |
| "grad_norm": 8.624068260192871, | |
| "learning_rate": 1.5350877192982457e-05, | |
| "loss": 1.6542, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 1.9869281045751634, | |
| "eval_accuracy": 0.39705882352941174, | |
| "eval_loss": 1.5735763311386108, | |
| "eval_runtime": 19.6256, | |
| "eval_samples_per_second": 6.93, | |
| "eval_steps_per_second": 0.866, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 2.0915032679738563, | |
| "grad_norm": 8.306758880615234, | |
| "learning_rate": 1.7543859649122806e-05, | |
| "loss": 1.6402, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 2.3529411764705883, | |
| "grad_norm": 7.969709873199463, | |
| "learning_rate": 1.9736842105263158e-05, | |
| "loss": 1.6017, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 2.6143790849673203, | |
| "grad_norm": 8.150823593139648, | |
| "learning_rate": 2.1929824561403507e-05, | |
| "loss": 1.5358, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 2.8758169934640523, | |
| "grad_norm": 7.387766361236572, | |
| "learning_rate": 2.412280701754386e-05, | |
| "loss": 1.4692, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 2.980392156862745, | |
| "eval_accuracy": 0.36764705882352944, | |
| "eval_loss": 1.4805188179016113, | |
| "eval_runtime": 20.2426, | |
| "eval_samples_per_second": 6.719, | |
| "eval_steps_per_second": 0.84, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 3.1372549019607843, | |
| "grad_norm": 8.2266845703125, | |
| "learning_rate": 2.6315789473684212e-05, | |
| "loss": 1.439, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 3.3986928104575163, | |
| "grad_norm": 8.400202751159668, | |
| "learning_rate": 2.850877192982456e-05, | |
| "loss": 1.399, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 3.6601307189542482, | |
| "grad_norm": 8.897980690002441, | |
| "learning_rate": 3.0701754385964913e-05, | |
| "loss": 1.3496, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 3.9215686274509802, | |
| "grad_norm": 8.579508781433105, | |
| "learning_rate": 3.289473684210527e-05, | |
| "loss": 1.2759, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.5808823529411765, | |
| "eval_loss": 1.2177482843399048, | |
| "eval_runtime": 19.8987, | |
| "eval_samples_per_second": 6.835, | |
| "eval_steps_per_second": 0.854, | |
| "step": 153 | |
| }, | |
| { | |
| "epoch": 4.183006535947713, | |
| "grad_norm": 7.850776195526123, | |
| "learning_rate": 3.508771929824561e-05, | |
| "loss": 1.2353, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 4.444444444444445, | |
| "grad_norm": 7.207574367523193, | |
| "learning_rate": 3.728070175438597e-05, | |
| "loss": 1.1957, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 4.705882352941177, | |
| "grad_norm": 7.722698211669922, | |
| "learning_rate": 3.9473684210526316e-05, | |
| "loss": 1.1894, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 4.967320261437909, | |
| "grad_norm": 7.626311779022217, | |
| "learning_rate": 4.166666666666667e-05, | |
| "loss": 1.1521, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 4.993464052287582, | |
| "eval_accuracy": 0.6470588235294118, | |
| "eval_loss": 1.0726604461669922, | |
| "eval_runtime": 19.9729, | |
| "eval_samples_per_second": 6.809, | |
| "eval_steps_per_second": 0.851, | |
| "step": 191 | |
| }, | |
| { | |
| "epoch": 5.228758169934641, | |
| "grad_norm": 6.824063301086426, | |
| "learning_rate": 4.3859649122807014e-05, | |
| "loss": 1.1157, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 5.490196078431373, | |
| "grad_norm": 9.015517234802246, | |
| "learning_rate": 4.605263157894737e-05, | |
| "loss": 1.0953, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 5.751633986928105, | |
| "grad_norm": 7.684938430786133, | |
| "learning_rate": 4.824561403508772e-05, | |
| "loss": 1.078, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 5.9869281045751634, | |
| "eval_accuracy": 0.6176470588235294, | |
| "eval_loss": 0.9995782375335693, | |
| "eval_runtime": 19.7917, | |
| "eval_samples_per_second": 6.872, | |
| "eval_steps_per_second": 0.859, | |
| "step": 229 | |
| }, | |
| { | |
| "epoch": 6.0130718954248366, | |
| "grad_norm": 8.750350952148438, | |
| "learning_rate": 4.9951267056530214e-05, | |
| "loss": 1.0635, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 6.2745098039215685, | |
| "grad_norm": 6.832897186279297, | |
| "learning_rate": 4.970760233918128e-05, | |
| "loss": 0.9083, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 6.5359477124183005, | |
| "grad_norm": 6.695949554443359, | |
| "learning_rate": 4.9463937621832366e-05, | |
| "loss": 0.9306, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 6.7973856209150325, | |
| "grad_norm": 7.3760271072387695, | |
| "learning_rate": 4.9220272904483435e-05, | |
| "loss": 1.0235, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 6.980392156862745, | |
| "eval_accuracy": 0.7058823529411765, | |
| "eval_loss": 0.8680174946784973, | |
| "eval_runtime": 19.5178, | |
| "eval_samples_per_second": 6.968, | |
| "eval_steps_per_second": 0.871, | |
| "step": 267 | |
| }, | |
| { | |
| "epoch": 7.0588235294117645, | |
| "grad_norm": 6.625696659088135, | |
| "learning_rate": 4.8976608187134504e-05, | |
| "loss": 0.885, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 7.3202614379084965, | |
| "grad_norm": 6.442111015319824, | |
| "learning_rate": 4.8732943469785574e-05, | |
| "loss": 0.8222, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 7.5816993464052285, | |
| "grad_norm": 8.278558731079102, | |
| "learning_rate": 4.848927875243665e-05, | |
| "loss": 0.8869, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 7.8431372549019605, | |
| "grad_norm": 7.1332106590271, | |
| "learning_rate": 4.824561403508772e-05, | |
| "loss": 0.9554, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.6397058823529411, | |
| "eval_loss": 0.9272549748420715, | |
| "eval_runtime": 19.5476, | |
| "eval_samples_per_second": 6.957, | |
| "eval_steps_per_second": 0.87, | |
| "step": 306 | |
| }, | |
| { | |
| "epoch": 8.104575163398692, | |
| "grad_norm": 8.287984848022461, | |
| "learning_rate": 4.8001949317738795e-05, | |
| "loss": 0.9148, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 8.366013071895425, | |
| "grad_norm": 7.765283107757568, | |
| "learning_rate": 4.7758284600389865e-05, | |
| "loss": 0.7935, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 8.627450980392156, | |
| "grad_norm": 7.960378646850586, | |
| "learning_rate": 4.751461988304094e-05, | |
| "loss": 0.9253, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 8.88888888888889, | |
| "grad_norm": 7.798432350158691, | |
| "learning_rate": 4.727095516569201e-05, | |
| "loss": 0.7437, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 8.993464052287582, | |
| "eval_accuracy": 0.7058823529411765, | |
| "eval_loss": 0.7389305233955383, | |
| "eval_runtime": 20.3392, | |
| "eval_samples_per_second": 6.687, | |
| "eval_steps_per_second": 0.836, | |
| "step": 344 | |
| }, | |
| { | |
| "epoch": 9.15032679738562, | |
| "grad_norm": 7.6827921867370605, | |
| "learning_rate": 4.702729044834308e-05, | |
| "loss": 0.8238, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 9.411764705882353, | |
| "grad_norm": 7.531745433807373, | |
| "learning_rate": 4.678362573099415e-05, | |
| "loss": 0.7379, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 9.673202614379084, | |
| "grad_norm": 7.212475299835205, | |
| "learning_rate": 4.6539961013645225e-05, | |
| "loss": 0.7684, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 9.934640522875817, | |
| "grad_norm": 8.958950996398926, | |
| "learning_rate": 4.62962962962963e-05, | |
| "loss": 0.7876, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 9.986928104575163, | |
| "eval_accuracy": 0.7426470588235294, | |
| "eval_loss": 0.6773847937583923, | |
| "eval_runtime": 22.3142, | |
| "eval_samples_per_second": 6.095, | |
| "eval_steps_per_second": 0.762, | |
| "step": 382 | |
| }, | |
| { | |
| "epoch": 10.196078431372548, | |
| "grad_norm": 8.386847496032715, | |
| "learning_rate": 4.605263157894737e-05, | |
| "loss": 0.7287, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 10.457516339869281, | |
| "grad_norm": 8.313080787658691, | |
| "learning_rate": 4.580896686159844e-05, | |
| "loss": 0.6713, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 10.718954248366012, | |
| "grad_norm": 7.874463081359863, | |
| "learning_rate": 4.5565302144249516e-05, | |
| "loss": 0.7802, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 10.980392156862745, | |
| "grad_norm": 7.682034492492676, | |
| "learning_rate": 4.5321637426900585e-05, | |
| "loss": 0.7698, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 10.980392156862745, | |
| "eval_accuracy": 0.7205882352941176, | |
| "eval_loss": 0.6569061875343323, | |
| "eval_runtime": 20.7833, | |
| "eval_samples_per_second": 6.544, | |
| "eval_steps_per_second": 0.818, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 11.241830065359476, | |
| "grad_norm": 8.04808521270752, | |
| "learning_rate": 4.507797270955166e-05, | |
| "loss": 0.7152, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 11.50326797385621, | |
| "grad_norm": 6.100086212158203, | |
| "learning_rate": 4.483430799220273e-05, | |
| "loss": 0.6517, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 11.764705882352942, | |
| "grad_norm": 10.316337585449219, | |
| "learning_rate": 4.4590643274853806e-05, | |
| "loss": 0.7597, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_accuracy": 0.7573529411764706, | |
| "eval_loss": 0.6757553219795227, | |
| "eval_runtime": 21.1029, | |
| "eval_samples_per_second": 6.445, | |
| "eval_steps_per_second": 0.806, | |
| "step": 459 | |
| }, | |
| { | |
| "epoch": 12.026143790849673, | |
| "grad_norm": 8.15910816192627, | |
| "learning_rate": 4.4346978557504876e-05, | |
| "loss": 0.7, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 12.287581699346406, | |
| "grad_norm": 6.629967212677002, | |
| "learning_rate": 4.4103313840155945e-05, | |
| "loss": 0.6214, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 12.549019607843137, | |
| "grad_norm": 7.6857123374938965, | |
| "learning_rate": 4.3859649122807014e-05, | |
| "loss": 0.6272, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 12.81045751633987, | |
| "grad_norm": 5.317193031311035, | |
| "learning_rate": 4.361598440545809e-05, | |
| "loss": 0.6114, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 12.993464052287582, | |
| "eval_accuracy": 0.7132352941176471, | |
| "eval_loss": 0.8278929591178894, | |
| "eval_runtime": 24.3179, | |
| "eval_samples_per_second": 5.593, | |
| "eval_steps_per_second": 0.699, | |
| "step": 497 | |
| }, | |
| { | |
| "epoch": 13.071895424836601, | |
| "grad_norm": 7.161328315734863, | |
| "learning_rate": 4.3372319688109166e-05, | |
| "loss": 0.66, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 13.333333333333334, | |
| "grad_norm": 7.760936260223389, | |
| "learning_rate": 4.3128654970760236e-05, | |
| "loss": 0.6246, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 13.594771241830065, | |
| "grad_norm": 7.746845245361328, | |
| "learning_rate": 4.2884990253411305e-05, | |
| "loss": 0.6391, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 13.856209150326798, | |
| "grad_norm": 7.603119373321533, | |
| "learning_rate": 4.264132553606238e-05, | |
| "loss": 0.6847, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 13.986928104575163, | |
| "eval_accuracy": 0.7132352941176471, | |
| "eval_loss": 0.7504714131355286, | |
| "eval_runtime": 24.2998, | |
| "eval_samples_per_second": 5.597, | |
| "eval_steps_per_second": 0.7, | |
| "step": 535 | |
| }, | |
| { | |
| "epoch": 14.117647058823529, | |
| "grad_norm": 6.282960414886475, | |
| "learning_rate": 4.239766081871345e-05, | |
| "loss": 0.6034, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 14.379084967320262, | |
| "grad_norm": 9.423322677612305, | |
| "learning_rate": 4.215399610136453e-05, | |
| "loss": 0.6312, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 14.640522875816993, | |
| "grad_norm": 7.931453704833984, | |
| "learning_rate": 4.1910331384015596e-05, | |
| "loss": 0.6247, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 14.901960784313726, | |
| "grad_norm": 8.18138313293457, | |
| "learning_rate": 4.166666666666667e-05, | |
| "loss": 0.5902, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 14.980392156862745, | |
| "eval_accuracy": 0.6691176470588235, | |
| "eval_loss": 0.7918919920921326, | |
| "eval_runtime": 22.015, | |
| "eval_samples_per_second": 6.178, | |
| "eval_steps_per_second": 0.772, | |
| "step": 573 | |
| }, | |
| { | |
| "epoch": 15.163398692810457, | |
| "grad_norm": 9.473512649536133, | |
| "learning_rate": 4.142300194931774e-05, | |
| "loss": 0.6104, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 15.42483660130719, | |
| "grad_norm": 8.635931015014648, | |
| "learning_rate": 4.117933723196881e-05, | |
| "loss": 0.6392, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 15.686274509803921, | |
| "grad_norm": 8.554533004760742, | |
| "learning_rate": 4.093567251461988e-05, | |
| "loss": 0.5461, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 15.947712418300654, | |
| "grad_norm": 6.450700283050537, | |
| "learning_rate": 4.0692007797270956e-05, | |
| "loss": 0.629, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_accuracy": 0.7867647058823529, | |
| "eval_loss": 0.611703097820282, | |
| "eval_runtime": 21.7065, | |
| "eval_samples_per_second": 6.265, | |
| "eval_steps_per_second": 0.783, | |
| "step": 612 | |
| }, | |
| { | |
| "epoch": 16.209150326797385, | |
| "grad_norm": 7.3682026863098145, | |
| "learning_rate": 4.044834307992203e-05, | |
| "loss": 0.5648, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 16.470588235294116, | |
| "grad_norm": 7.454318523406982, | |
| "learning_rate": 4.02046783625731e-05, | |
| "loss": 0.5916, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 16.73202614379085, | |
| "grad_norm": 7.530863285064697, | |
| "learning_rate": 3.996101364522417e-05, | |
| "loss": 0.5476, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 16.99346405228758, | |
| "grad_norm": 6.975796699523926, | |
| "learning_rate": 3.971734892787525e-05, | |
| "loss": 0.5071, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 16.99346405228758, | |
| "eval_accuracy": 0.7352941176470589, | |
| "eval_loss": 0.6048275828361511, | |
| "eval_runtime": 22.49, | |
| "eval_samples_per_second": 6.047, | |
| "eval_steps_per_second": 0.756, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 17.254901960784313, | |
| "grad_norm": 7.351856708526611, | |
| "learning_rate": 3.9473684210526316e-05, | |
| "loss": 0.5372, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 17.516339869281047, | |
| "grad_norm": 8.070556640625, | |
| "learning_rate": 3.923001949317739e-05, | |
| "loss": 0.5503, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 17.77777777777778, | |
| "grad_norm": 8.659597396850586, | |
| "learning_rate": 3.898635477582846e-05, | |
| "loss": 0.5453, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 17.986928104575163, | |
| "eval_accuracy": 0.7279411764705882, | |
| "eval_loss": 0.8086075782775879, | |
| "eval_runtime": 20.3748, | |
| "eval_samples_per_second": 6.675, | |
| "eval_steps_per_second": 0.834, | |
| "step": 688 | |
| }, | |
| { | |
| "epoch": 18.03921568627451, | |
| "grad_norm": 8.510287284851074, | |
| "learning_rate": 3.874269005847954e-05, | |
| "loss": 0.5091, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 18.30065359477124, | |
| "grad_norm": 9.453730583190918, | |
| "learning_rate": 3.849902534113061e-05, | |
| "loss": 0.5115, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 18.562091503267975, | |
| "grad_norm": 6.948453903198242, | |
| "learning_rate": 3.8255360623781676e-05, | |
| "loss": 0.5383, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 18.823529411764707, | |
| "grad_norm": 7.508301734924316, | |
| "learning_rate": 3.8011695906432746e-05, | |
| "loss": 0.5071, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 18.980392156862745, | |
| "eval_accuracy": 0.7058823529411765, | |
| "eval_loss": 0.783478856086731, | |
| "eval_runtime": 21.0622, | |
| "eval_samples_per_second": 6.457, | |
| "eval_steps_per_second": 0.807, | |
| "step": 726 | |
| }, | |
| { | |
| "epoch": 19.084967320261438, | |
| "grad_norm": 8.099154472351074, | |
| "learning_rate": 3.776803118908382e-05, | |
| "loss": 0.4653, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 19.34640522875817, | |
| "grad_norm": 6.376596927642822, | |
| "learning_rate": 3.75243664717349e-05, | |
| "loss": 0.426, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 19.607843137254903, | |
| "grad_norm": 9.521799087524414, | |
| "learning_rate": 3.728070175438597e-05, | |
| "loss": 0.4674, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 19.869281045751634, | |
| "grad_norm": 7.47611141204834, | |
| "learning_rate": 3.7037037037037037e-05, | |
| "loss": 0.5328, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_accuracy": 0.75, | |
| "eval_loss": 0.6138941645622253, | |
| "eval_runtime": 20.7772, | |
| "eval_samples_per_second": 6.546, | |
| "eval_steps_per_second": 0.818, | |
| "step": 765 | |
| }, | |
| { | |
| "epoch": 20.130718954248366, | |
| "grad_norm": 8.478204727172852, | |
| "learning_rate": 3.679337231968811e-05, | |
| "loss": 0.5362, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 20.392156862745097, | |
| "grad_norm": 3.9403858184814453, | |
| "learning_rate": 3.654970760233918e-05, | |
| "loss": 0.4867, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 20.65359477124183, | |
| "grad_norm": 8.257362365722656, | |
| "learning_rate": 3.630604288499025e-05, | |
| "loss": 0.4665, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 20.915032679738562, | |
| "grad_norm": 7.73619270324707, | |
| "learning_rate": 3.606237816764133e-05, | |
| "loss": 0.5053, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 20.99346405228758, | |
| "eval_accuracy": 0.7867647058823529, | |
| "eval_loss": 0.5980984568595886, | |
| "eval_runtime": 20.8979, | |
| "eval_samples_per_second": 6.508, | |
| "eval_steps_per_second": 0.813, | |
| "step": 803 | |
| }, | |
| { | |
| "epoch": 21.176470588235293, | |
| "grad_norm": 9.795605659484863, | |
| "learning_rate": 3.5818713450292403e-05, | |
| "loss": 0.4638, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 21.437908496732025, | |
| "grad_norm": 7.380087375640869, | |
| "learning_rate": 3.557504873294347e-05, | |
| "loss": 0.453, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 21.69934640522876, | |
| "grad_norm": 9.243858337402344, | |
| "learning_rate": 3.533138401559454e-05, | |
| "loss": 0.4768, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 21.96078431372549, | |
| "grad_norm": 9.421792030334473, | |
| "learning_rate": 3.508771929824561e-05, | |
| "loss": 0.4436, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 21.986928104575163, | |
| "eval_accuracy": 0.8014705882352942, | |
| "eval_loss": 0.5218998193740845, | |
| "eval_runtime": 20.8439, | |
| "eval_samples_per_second": 6.525, | |
| "eval_steps_per_second": 0.816, | |
| "step": 841 | |
| }, | |
| { | |
| "epoch": 22.22222222222222, | |
| "grad_norm": 9.261748313903809, | |
| "learning_rate": 3.484405458089669e-05, | |
| "loss": 0.4918, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 22.483660130718953, | |
| "grad_norm": 7.44433069229126, | |
| "learning_rate": 3.4600389863547764e-05, | |
| "loss": 0.4141, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 22.745098039215687, | |
| "grad_norm": 7.531349182128906, | |
| "learning_rate": 3.435672514619883e-05, | |
| "loss": 0.5025, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 22.980392156862745, | |
| "eval_accuracy": 0.8088235294117647, | |
| "eval_loss": 0.4959449768066406, | |
| "eval_runtime": 21.8633, | |
| "eval_samples_per_second": 6.22, | |
| "eval_steps_per_second": 0.778, | |
| "step": 879 | |
| }, | |
| { | |
| "epoch": 23.00653594771242, | |
| "grad_norm": 7.8833794593811035, | |
| "learning_rate": 3.41130604288499e-05, | |
| "loss": 0.4356, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 23.26797385620915, | |
| "grad_norm": 8.349276542663574, | |
| "learning_rate": 3.386939571150098e-05, | |
| "loss": 0.421, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 23.529411764705884, | |
| "grad_norm": 7.9358086585998535, | |
| "learning_rate": 3.362573099415205e-05, | |
| "loss": 0.4414, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 23.790849673202615, | |
| "grad_norm": 7.962532043457031, | |
| "learning_rate": 3.338206627680312e-05, | |
| "loss": 0.4984, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "eval_accuracy": 0.7794117647058824, | |
| "eval_loss": 0.5701327323913574, | |
| "eval_runtime": 20.7703, | |
| "eval_samples_per_second": 6.548, | |
| "eval_steps_per_second": 0.818, | |
| "step": 918 | |
| }, | |
| { | |
| "epoch": 24.052287581699346, | |
| "grad_norm": 7.35078239440918, | |
| "learning_rate": 3.313840155945419e-05, | |
| "loss": 0.4853, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 24.313725490196077, | |
| "grad_norm": 10.068733215332031, | |
| "learning_rate": 3.289473684210527e-05, | |
| "loss": 0.4273, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 24.575163398692812, | |
| "grad_norm": 8.412373542785645, | |
| "learning_rate": 3.265107212475634e-05, | |
| "loss": 0.5412, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 24.836601307189543, | |
| "grad_norm": 6.781473636627197, | |
| "learning_rate": 3.240740740740741e-05, | |
| "loss": 0.4655, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 24.99346405228758, | |
| "eval_accuracy": 0.7205882352941176, | |
| "eval_loss": 0.7179181575775146, | |
| "eval_runtime": 21.5807, | |
| "eval_samples_per_second": 6.302, | |
| "eval_steps_per_second": 0.788, | |
| "step": 956 | |
| }, | |
| { | |
| "epoch": 25.098039215686274, | |
| "grad_norm": 8.029053688049316, | |
| "learning_rate": 3.216374269005848e-05, | |
| "loss": 0.476, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 25.359477124183005, | |
| "grad_norm": 6.743289470672607, | |
| "learning_rate": 3.192007797270955e-05, | |
| "loss": 0.4561, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 25.62091503267974, | |
| "grad_norm": 8.96541690826416, | |
| "learning_rate": 3.167641325536063e-05, | |
| "loss": 0.4343, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 25.88235294117647, | |
| "grad_norm": 6.772902965545654, | |
| "learning_rate": 3.14327485380117e-05, | |
| "loss": 0.3848, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 25.986928104575163, | |
| "eval_accuracy": 0.8088235294117647, | |
| "eval_loss": 0.5074525475502014, | |
| "eval_runtime": 19.6885, | |
| "eval_samples_per_second": 6.908, | |
| "eval_steps_per_second": 0.863, | |
| "step": 994 | |
| }, | |
| { | |
| "epoch": 26.143790849673202, | |
| "grad_norm": 8.97864055633545, | |
| "learning_rate": 3.118908382066277e-05, | |
| "loss": 0.4338, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 26.405228758169933, | |
| "grad_norm": 7.333850383758545, | |
| "learning_rate": 3.0945419103313844e-05, | |
| "loss": 0.4137, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 26.666666666666668, | |
| "grad_norm": 7.425909519195557, | |
| "learning_rate": 3.0701754385964913e-05, | |
| "loss": 0.4776, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 26.9281045751634, | |
| "grad_norm": 6.110713481903076, | |
| "learning_rate": 3.0458089668615986e-05, | |
| "loss": 0.3824, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 26.980392156862745, | |
| "eval_accuracy": 0.7426470588235294, | |
| "eval_loss": 0.6644823551177979, | |
| "eval_runtime": 22.0924, | |
| "eval_samples_per_second": 6.156, | |
| "eval_steps_per_second": 0.769, | |
| "step": 1032 | |
| }, | |
| { | |
| "epoch": 27.18954248366013, | |
| "grad_norm": 7.540946006774902, | |
| "learning_rate": 3.0214424951267055e-05, | |
| "loss": 0.3977, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 27.45098039215686, | |
| "grad_norm": 8.191174507141113, | |
| "learning_rate": 2.997076023391813e-05, | |
| "loss": 0.4704, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 27.712418300653596, | |
| "grad_norm": 10.757161140441895, | |
| "learning_rate": 2.9727095516569204e-05, | |
| "loss": 0.4258, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 27.973856209150327, | |
| "grad_norm": 7.706909656524658, | |
| "learning_rate": 2.9483430799220274e-05, | |
| "loss": 0.4901, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "eval_accuracy": 0.6985294117647058, | |
| "eval_loss": 0.7287850379943848, | |
| "eval_runtime": 23.7514, | |
| "eval_samples_per_second": 5.726, | |
| "eval_steps_per_second": 0.716, | |
| "step": 1071 | |
| }, | |
| { | |
| "epoch": 28.235294117647058, | |
| "grad_norm": 5.9652886390686035, | |
| "learning_rate": 2.9239766081871346e-05, | |
| "loss": 0.4311, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 28.49673202614379, | |
| "grad_norm": 8.528486251831055, | |
| "learning_rate": 2.8996101364522422e-05, | |
| "loss": 0.3898, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 28.758169934640524, | |
| "grad_norm": 8.398402214050293, | |
| "learning_rate": 2.875243664717349e-05, | |
| "loss": 0.397, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 28.99346405228758, | |
| "eval_accuracy": 0.7279411764705882, | |
| "eval_loss": 0.7250666618347168, | |
| "eval_runtime": 21.8786, | |
| "eval_samples_per_second": 6.216, | |
| "eval_steps_per_second": 0.777, | |
| "step": 1109 | |
| }, | |
| { | |
| "epoch": 29.019607843137255, | |
| "grad_norm": 5.904468536376953, | |
| "learning_rate": 2.850877192982456e-05, | |
| "loss": 0.3617, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 29.281045751633986, | |
| "grad_norm": 5.135966777801514, | |
| "learning_rate": 2.8265107212475634e-05, | |
| "loss": 0.4141, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 29.54248366013072, | |
| "grad_norm": 7.617613792419434, | |
| "learning_rate": 2.802144249512671e-05, | |
| "loss": 0.4057, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 29.80392156862745, | |
| "grad_norm": 9.047426223754883, | |
| "learning_rate": 2.777777777777778e-05, | |
| "loss": 0.3818, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 29.986928104575163, | |
| "eval_accuracy": 0.7941176470588235, | |
| "eval_loss": 0.6250298023223877, | |
| "eval_runtime": 21.1786, | |
| "eval_samples_per_second": 6.422, | |
| "eval_steps_per_second": 0.803, | |
| "step": 1147 | |
| }, | |
| { | |
| "epoch": 30.065359477124183, | |
| "grad_norm": 8.303121566772461, | |
| "learning_rate": 2.7534113060428852e-05, | |
| "loss": 0.3813, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 30.326797385620914, | |
| "grad_norm": 6.311716079711914, | |
| "learning_rate": 2.729044834307992e-05, | |
| "loss": 0.3967, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 30.58823529411765, | |
| "grad_norm": 6.965037822723389, | |
| "learning_rate": 2.7046783625730997e-05, | |
| "loss": 0.4462, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 30.84967320261438, | |
| "grad_norm": 9.514204978942871, | |
| "learning_rate": 2.680311890838207e-05, | |
| "loss": 0.3412, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 30.980392156862745, | |
| "eval_accuracy": 0.7279411764705882, | |
| "eval_loss": 0.7065072059631348, | |
| "eval_runtime": 21.6767, | |
| "eval_samples_per_second": 6.274, | |
| "eval_steps_per_second": 0.784, | |
| "step": 1185 | |
| }, | |
| { | |
| "epoch": 31.11111111111111, | |
| "grad_norm": 9.511887550354004, | |
| "learning_rate": 2.655945419103314e-05, | |
| "loss": 0.4346, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 31.372549019607842, | |
| "grad_norm": 8.251455307006836, | |
| "learning_rate": 2.6315789473684212e-05, | |
| "loss": 0.3567, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 31.633986928104576, | |
| "grad_norm": 8.693254470825195, | |
| "learning_rate": 2.6072124756335288e-05, | |
| "loss": 0.4056, | |
| "step": 1210 | |
| }, | |
| { | |
| "epoch": 31.895424836601308, | |
| "grad_norm": 6.94719123840332, | |
| "learning_rate": 2.5828460038986357e-05, | |
| "loss": 0.3627, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 32.0, | |
| "eval_accuracy": 0.7426470588235294, | |
| "eval_loss": 0.6876980662345886, | |
| "eval_runtime": 21.8581, | |
| "eval_samples_per_second": 6.222, | |
| "eval_steps_per_second": 0.778, | |
| "step": 1224 | |
| }, | |
| { | |
| "epoch": 32.15686274509804, | |
| "grad_norm": 6.152271270751953, | |
| "learning_rate": 2.5584795321637427e-05, | |
| "loss": 0.294, | |
| "step": 1230 | |
| }, | |
| { | |
| "epoch": 32.41830065359477, | |
| "grad_norm": 9.349310874938965, | |
| "learning_rate": 2.53411306042885e-05, | |
| "loss": 0.361, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 32.6797385620915, | |
| "grad_norm": 8.874456405639648, | |
| "learning_rate": 2.5097465886939576e-05, | |
| "loss": 0.3795, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 32.94117647058823, | |
| "grad_norm": 6.504201412200928, | |
| "learning_rate": 2.485380116959064e-05, | |
| "loss": 0.3557, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 32.99346405228758, | |
| "eval_accuracy": 0.8529411764705882, | |
| "eval_loss": 0.4244842231273651, | |
| "eval_runtime": 21.3842, | |
| "eval_samples_per_second": 6.36, | |
| "eval_steps_per_second": 0.795, | |
| "step": 1262 | |
| }, | |
| { | |
| "epoch": 33.20261437908497, | |
| "grad_norm": 6.195323467254639, | |
| "learning_rate": 2.4610136452241718e-05, | |
| "loss": 0.3335, | |
| "step": 1270 | |
| }, | |
| { | |
| "epoch": 33.4640522875817, | |
| "grad_norm": 9.20754623413086, | |
| "learning_rate": 2.4366471734892787e-05, | |
| "loss": 0.3705, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 33.72549019607843, | |
| "grad_norm": 7.307880878448486, | |
| "learning_rate": 2.412280701754386e-05, | |
| "loss": 0.3626, | |
| "step": 1290 | |
| }, | |
| { | |
| "epoch": 33.98692810457516, | |
| "grad_norm": 11.704693794250488, | |
| "learning_rate": 2.3879142300194932e-05, | |
| "loss": 0.441, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 33.98692810457516, | |
| "eval_accuracy": 0.75, | |
| "eval_loss": 0.6974249482154846, | |
| "eval_runtime": 21.7309, | |
| "eval_samples_per_second": 6.258, | |
| "eval_steps_per_second": 0.782, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 34.248366013071895, | |
| "grad_norm": 7.3577094078063965, | |
| "learning_rate": 2.3635477582846005e-05, | |
| "loss": 0.4363, | |
| "step": 1310 | |
| }, | |
| { | |
| "epoch": 34.509803921568626, | |
| "grad_norm": 4.33771276473999, | |
| "learning_rate": 2.3391812865497074e-05, | |
| "loss": 0.3408, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 34.77124183006536, | |
| "grad_norm": 7.208470821380615, | |
| "learning_rate": 2.314814814814815e-05, | |
| "loss": 0.3036, | |
| "step": 1330 | |
| }, | |
| { | |
| "epoch": 34.98039215686274, | |
| "eval_accuracy": 0.7426470588235294, | |
| "eval_loss": 0.6457906365394592, | |
| "eval_runtime": 22.2732, | |
| "eval_samples_per_second": 6.106, | |
| "eval_steps_per_second": 0.763, | |
| "step": 1338 | |
| }, | |
| { | |
| "epoch": 35.032679738562095, | |
| "grad_norm": 7.787372589111328, | |
| "learning_rate": 2.290448343079922e-05, | |
| "loss": 0.3159, | |
| "step": 1340 | |
| }, | |
| { | |
| "epoch": 35.294117647058826, | |
| "grad_norm": 6.915111064910889, | |
| "learning_rate": 2.2660818713450292e-05, | |
| "loss": 0.3424, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 35.55555555555556, | |
| "grad_norm": 8.578511238098145, | |
| "learning_rate": 2.2417153996101365e-05, | |
| "loss": 0.3452, | |
| "step": 1360 | |
| }, | |
| { | |
| "epoch": 35.81699346405229, | |
| "grad_norm": 8.574066162109375, | |
| "learning_rate": 2.2173489278752438e-05, | |
| "loss": 0.3213, | |
| "step": 1370 | |
| }, | |
| { | |
| "epoch": 36.0, | |
| "eval_accuracy": 0.7941176470588235, | |
| "eval_loss": 0.5578574538230896, | |
| "eval_runtime": 21.3424, | |
| "eval_samples_per_second": 6.372, | |
| "eval_steps_per_second": 0.797, | |
| "step": 1377 | |
| }, | |
| { | |
| "epoch": 36.07843137254902, | |
| "grad_norm": 7.610787391662598, | |
| "learning_rate": 2.1929824561403507e-05, | |
| "loss": 0.4071, | |
| "step": 1380 | |
| }, | |
| { | |
| "epoch": 36.33986928104575, | |
| "grad_norm": 8.612502098083496, | |
| "learning_rate": 2.1686159844054583e-05, | |
| "loss": 0.2995, | |
| "step": 1390 | |
| }, | |
| { | |
| "epoch": 36.60130718954248, | |
| "grad_norm": 8.465425491333008, | |
| "learning_rate": 2.1442495126705653e-05, | |
| "loss": 0.3456, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 36.86274509803921, | |
| "grad_norm": 7.883861541748047, | |
| "learning_rate": 2.1198830409356725e-05, | |
| "loss": 0.402, | |
| "step": 1410 | |
| }, | |
| { | |
| "epoch": 36.99346405228758, | |
| "eval_accuracy": 0.8382352941176471, | |
| "eval_loss": 0.4578179121017456, | |
| "eval_runtime": 20.8376, | |
| "eval_samples_per_second": 6.527, | |
| "eval_steps_per_second": 0.816, | |
| "step": 1415 | |
| }, | |
| { | |
| "epoch": 37.12418300653595, | |
| "grad_norm": 8.734749794006348, | |
| "learning_rate": 2.0955165692007798e-05, | |
| "loss": 0.3742, | |
| "step": 1420 | |
| }, | |
| { | |
| "epoch": 37.38562091503268, | |
| "grad_norm": 10.651437759399414, | |
| "learning_rate": 2.071150097465887e-05, | |
| "loss": 0.3225, | |
| "step": 1430 | |
| }, | |
| { | |
| "epoch": 37.64705882352941, | |
| "grad_norm": 8.572120666503906, | |
| "learning_rate": 2.046783625730994e-05, | |
| "loss": 0.3638, | |
| "step": 1440 | |
| }, | |
| { | |
| "epoch": 37.908496732026144, | |
| "grad_norm": 7.853600978851318, | |
| "learning_rate": 2.0224171539961016e-05, | |
| "loss": 0.2897, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 37.98692810457516, | |
| "eval_accuracy": 0.7867647058823529, | |
| "eval_loss": 0.5368921756744385, | |
| "eval_runtime": 21.9563, | |
| "eval_samples_per_second": 6.194, | |
| "eval_steps_per_second": 0.774, | |
| "step": 1453 | |
| }, | |
| { | |
| "epoch": 38.169934640522875, | |
| "grad_norm": 7.19242000579834, | |
| "learning_rate": 1.9980506822612085e-05, | |
| "loss": 0.3608, | |
| "step": 1460 | |
| }, | |
| { | |
| "epoch": 38.431372549019606, | |
| "grad_norm": 5.555720329284668, | |
| "learning_rate": 1.9736842105263158e-05, | |
| "loss": 0.3496, | |
| "step": 1470 | |
| }, | |
| { | |
| "epoch": 38.69281045751634, | |
| "grad_norm": 7.676553249359131, | |
| "learning_rate": 1.949317738791423e-05, | |
| "loss": 0.3087, | |
| "step": 1480 | |
| }, | |
| { | |
| "epoch": 38.95424836601307, | |
| "grad_norm": 9.612250328063965, | |
| "learning_rate": 1.9249512670565304e-05, | |
| "loss": 0.348, | |
| "step": 1490 | |
| }, | |
| { | |
| "epoch": 38.98039215686274, | |
| "eval_accuracy": 0.7941176470588235, | |
| "eval_loss": 0.6819477081298828, | |
| "eval_runtime": 20.1264, | |
| "eval_samples_per_second": 6.757, | |
| "eval_steps_per_second": 0.845, | |
| "step": 1491 | |
| }, | |
| { | |
| "epoch": 39.21568627450981, | |
| "grad_norm": 5.8754167556762695, | |
| "learning_rate": 1.9005847953216373e-05, | |
| "loss": 0.2784, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 39.47712418300654, | |
| "grad_norm": 9.667128562927246, | |
| "learning_rate": 1.876218323586745e-05, | |
| "loss": 0.3254, | |
| "step": 1510 | |
| }, | |
| { | |
| "epoch": 39.73856209150327, | |
| "grad_norm": 7.417483329772949, | |
| "learning_rate": 1.8518518518518518e-05, | |
| "loss": 0.3416, | |
| "step": 1520 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "grad_norm": 10.744291305541992, | |
| "learning_rate": 1.827485380116959e-05, | |
| "loss": 0.3929, | |
| "step": 1530 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "eval_accuracy": 0.7867647058823529, | |
| "eval_loss": 0.5809765458106995, | |
| "eval_runtime": 22.4901, | |
| "eval_samples_per_second": 6.047, | |
| "eval_steps_per_second": 0.756, | |
| "step": 1530 | |
| }, | |
| { | |
| "epoch": 40.26143790849673, | |
| "grad_norm": 8.990880012512207, | |
| "learning_rate": 1.8031189083820664e-05, | |
| "loss": 0.3546, | |
| "step": 1540 | |
| }, | |
| { | |
| "epoch": 40.52287581699346, | |
| "grad_norm": 9.770576477050781, | |
| "learning_rate": 1.7787524366471736e-05, | |
| "loss": 0.344, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 40.78431372549019, | |
| "grad_norm": 7.653594017028809, | |
| "learning_rate": 1.7543859649122806e-05, | |
| "loss": 0.3173, | |
| "step": 1560 | |
| }, | |
| { | |
| "epoch": 40.99346405228758, | |
| "eval_accuracy": 0.7426470588235294, | |
| "eval_loss": 0.7875370979309082, | |
| "eval_runtime": 20.0479, | |
| "eval_samples_per_second": 6.784, | |
| "eval_steps_per_second": 0.848, | |
| "step": 1568 | |
| }, | |
| { | |
| "epoch": 41.04575163398693, | |
| "grad_norm": 10.298673629760742, | |
| "learning_rate": 1.7300194931773882e-05, | |
| "loss": 0.3148, | |
| "step": 1570 | |
| }, | |
| { | |
| "epoch": 41.30718954248366, | |
| "grad_norm": 9.334877967834473, | |
| "learning_rate": 1.705653021442495e-05, | |
| "loss": 0.295, | |
| "step": 1580 | |
| }, | |
| { | |
| "epoch": 41.568627450980394, | |
| "grad_norm": 6.963639736175537, | |
| "learning_rate": 1.6812865497076024e-05, | |
| "loss": 0.3274, | |
| "step": 1590 | |
| }, | |
| { | |
| "epoch": 41.830065359477125, | |
| "grad_norm": 9.359763145446777, | |
| "learning_rate": 1.6569200779727097e-05, | |
| "loss": 0.3499, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 41.98692810457516, | |
| "eval_accuracy": 0.8014705882352942, | |
| "eval_loss": 0.5050505995750427, | |
| "eval_runtime": 19.6525, | |
| "eval_samples_per_second": 6.92, | |
| "eval_steps_per_second": 0.865, | |
| "step": 1606 | |
| }, | |
| { | |
| "epoch": 42.091503267973856, | |
| "grad_norm": 8.404752731323242, | |
| "learning_rate": 1.632553606237817e-05, | |
| "loss": 0.3297, | |
| "step": 1610 | |
| }, | |
| { | |
| "epoch": 42.35294117647059, | |
| "grad_norm": 7.797074794769287, | |
| "learning_rate": 1.608187134502924e-05, | |
| "loss": 0.2784, | |
| "step": 1620 | |
| }, | |
| { | |
| "epoch": 42.61437908496732, | |
| "grad_norm": 6.273430347442627, | |
| "learning_rate": 1.5838206627680315e-05, | |
| "loss": 0.3084, | |
| "step": 1630 | |
| }, | |
| { | |
| "epoch": 42.87581699346405, | |
| "grad_norm": 8.596699714660645, | |
| "learning_rate": 1.5594541910331384e-05, | |
| "loss": 0.3053, | |
| "step": 1640 | |
| }, | |
| { | |
| "epoch": 42.98039215686274, | |
| "eval_accuracy": 0.7426470588235294, | |
| "eval_loss": 0.751028299331665, | |
| "eval_runtime": 19.7977, | |
| "eval_samples_per_second": 6.869, | |
| "eval_steps_per_second": 0.859, | |
| "step": 1644 | |
| }, | |
| { | |
| "epoch": 43.13725490196079, | |
| "grad_norm": 10.001852989196777, | |
| "learning_rate": 1.5350877192982457e-05, | |
| "loss": 0.3818, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 43.39869281045752, | |
| "grad_norm": 6.75031042098999, | |
| "learning_rate": 1.5107212475633528e-05, | |
| "loss": 0.2612, | |
| "step": 1660 | |
| }, | |
| { | |
| "epoch": 43.66013071895425, | |
| "grad_norm": 4.408693790435791, | |
| "learning_rate": 1.4863547758284602e-05, | |
| "loss": 0.2901, | |
| "step": 1670 | |
| }, | |
| { | |
| "epoch": 43.92156862745098, | |
| "grad_norm": 9.371530532836914, | |
| "learning_rate": 1.4619883040935673e-05, | |
| "loss": 0.4109, | |
| "step": 1680 | |
| }, | |
| { | |
| "epoch": 44.0, | |
| "eval_accuracy": 0.75, | |
| "eval_loss": 0.6528570055961609, | |
| "eval_runtime": 20.0083, | |
| "eval_samples_per_second": 6.797, | |
| "eval_steps_per_second": 0.85, | |
| "step": 1683 | |
| }, | |
| { | |
| "epoch": 44.18300653594771, | |
| "grad_norm": 7.803284168243408, | |
| "learning_rate": 1.4376218323586746e-05, | |
| "loss": 0.2882, | |
| "step": 1690 | |
| }, | |
| { | |
| "epoch": 44.44444444444444, | |
| "grad_norm": 6.260004043579102, | |
| "learning_rate": 1.4132553606237817e-05, | |
| "loss": 0.333, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 44.705882352941174, | |
| "grad_norm": 11.425740242004395, | |
| "learning_rate": 1.388888888888889e-05, | |
| "loss": 0.3003, | |
| "step": 1710 | |
| }, | |
| { | |
| "epoch": 44.967320261437905, | |
| "grad_norm": 4.394773960113525, | |
| "learning_rate": 1.364522417153996e-05, | |
| "loss": 0.3846, | |
| "step": 1720 | |
| }, | |
| { | |
| "epoch": 44.99346405228758, | |
| "eval_accuracy": 0.7132352941176471, | |
| "eval_loss": 0.961465060710907, | |
| "eval_runtime": 19.8391, | |
| "eval_samples_per_second": 6.855, | |
| "eval_steps_per_second": 0.857, | |
| "step": 1721 | |
| }, | |
| { | |
| "epoch": 45.22875816993464, | |
| "grad_norm": 11.91213321685791, | |
| "learning_rate": 1.3401559454191035e-05, | |
| "loss": 0.3757, | |
| "step": 1730 | |
| }, | |
| { | |
| "epoch": 45.490196078431374, | |
| "grad_norm": 7.775343894958496, | |
| "learning_rate": 1.3157894736842106e-05, | |
| "loss": 0.3259, | |
| "step": 1740 | |
| }, | |
| { | |
| "epoch": 45.751633986928105, | |
| "grad_norm": 4.623126029968262, | |
| "learning_rate": 1.2914230019493179e-05, | |
| "loss": 0.3222, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 45.98692810457516, | |
| "eval_accuracy": 0.6691176470588235, | |
| "eval_loss": 0.8888900279998779, | |
| "eval_runtime": 19.6212, | |
| "eval_samples_per_second": 6.931, | |
| "eval_steps_per_second": 0.866, | |
| "step": 1759 | |
| }, | |
| { | |
| "epoch": 46.01307189542484, | |
| "grad_norm": 7.839041233062744, | |
| "learning_rate": 1.267056530214425e-05, | |
| "loss": 0.2718, | |
| "step": 1760 | |
| }, | |
| { | |
| "epoch": 46.27450980392157, | |
| "grad_norm": 10.323081016540527, | |
| "learning_rate": 1.242690058479532e-05, | |
| "loss": 0.2538, | |
| "step": 1770 | |
| }, | |
| { | |
| "epoch": 46.5359477124183, | |
| "grad_norm": 8.446836471557617, | |
| "learning_rate": 1.2183235867446393e-05, | |
| "loss": 0.2974, | |
| "step": 1780 | |
| }, | |
| { | |
| "epoch": 46.79738562091503, | |
| "grad_norm": 8.584868431091309, | |
| "learning_rate": 1.1939571150097466e-05, | |
| "loss": 0.3293, | |
| "step": 1790 | |
| }, | |
| { | |
| "epoch": 46.98039215686274, | |
| "eval_accuracy": 0.8676470588235294, | |
| "eval_loss": 0.46983805298805237, | |
| "eval_runtime": 20.3581, | |
| "eval_samples_per_second": 6.68, | |
| "eval_steps_per_second": 0.835, | |
| "step": 1797 | |
| }, | |
| { | |
| "epoch": 47.05882352941177, | |
| "grad_norm": 6.30557918548584, | |
| "learning_rate": 1.1695906432748537e-05, | |
| "loss": 0.2915, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 47.3202614379085, | |
| "grad_norm": 6.145007610321045, | |
| "learning_rate": 1.145224171539961e-05, | |
| "loss": 0.2948, | |
| "step": 1810 | |
| }, | |
| { | |
| "epoch": 47.58169934640523, | |
| "grad_norm": 8.976215362548828, | |
| "learning_rate": 1.1208576998050683e-05, | |
| "loss": 0.3189, | |
| "step": 1820 | |
| }, | |
| { | |
| "epoch": 47.84313725490196, | |
| "grad_norm": 5.437533855438232, | |
| "learning_rate": 1.0964912280701754e-05, | |
| "loss": 0.293, | |
| "step": 1830 | |
| }, | |
| { | |
| "epoch": 48.0, | |
| "eval_accuracy": 0.8014705882352942, | |
| "eval_loss": 0.5995640754699707, | |
| "eval_runtime": 22.4921, | |
| "eval_samples_per_second": 6.047, | |
| "eval_steps_per_second": 0.756, | |
| "step": 1836 | |
| }, | |
| { | |
| "epoch": 48.10457516339869, | |
| "grad_norm": 7.454949855804443, | |
| "learning_rate": 1.0721247563352826e-05, | |
| "loss": 0.3486, | |
| "step": 1840 | |
| }, | |
| { | |
| "epoch": 48.36601307189542, | |
| "grad_norm": 5.587437152862549, | |
| "learning_rate": 1.0477582846003899e-05, | |
| "loss": 0.3269, | |
| "step": 1850 | |
| }, | |
| { | |
| "epoch": 48.627450980392155, | |
| "grad_norm": 7.708277702331543, | |
| "learning_rate": 1.023391812865497e-05, | |
| "loss": 0.3436, | |
| "step": 1860 | |
| }, | |
| { | |
| "epoch": 48.888888888888886, | |
| "grad_norm": 9.139860153198242, | |
| "learning_rate": 9.990253411306043e-06, | |
| "loss": 0.2363, | |
| "step": 1870 | |
| }, | |
| { | |
| "epoch": 48.99346405228758, | |
| "eval_accuracy": 0.8308823529411765, | |
| "eval_loss": 0.5006946921348572, | |
| "eval_runtime": 22.6256, | |
| "eval_samples_per_second": 6.011, | |
| "eval_steps_per_second": 0.751, | |
| "step": 1874 | |
| }, | |
| { | |
| "epoch": 49.150326797385624, | |
| "grad_norm": 10.596453666687012, | |
| "learning_rate": 9.746588693957115e-06, | |
| "loss": 0.3911, | |
| "step": 1880 | |
| }, | |
| { | |
| "epoch": 49.411764705882355, | |
| "grad_norm": 7.040250301361084, | |
| "learning_rate": 9.502923976608186e-06, | |
| "loss": 0.3426, | |
| "step": 1890 | |
| }, | |
| { | |
| "epoch": 49.673202614379086, | |
| "grad_norm": 8.111015319824219, | |
| "learning_rate": 9.259259259259259e-06, | |
| "loss": 0.3189, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 49.93464052287582, | |
| "grad_norm": 4.160747528076172, | |
| "learning_rate": 9.015594541910332e-06, | |
| "loss": 0.2811, | |
| "step": 1910 | |
| }, | |
| { | |
| "epoch": 49.98692810457516, | |
| "eval_accuracy": 0.7941176470588235, | |
| "eval_loss": 0.6748296022415161, | |
| "eval_runtime": 21.1042, | |
| "eval_samples_per_second": 6.444, | |
| "eval_steps_per_second": 0.806, | |
| "step": 1912 | |
| }, | |
| { | |
| "epoch": 50.19607843137255, | |
| "grad_norm": 7.058052062988281, | |
| "learning_rate": 8.771929824561403e-06, | |
| "loss": 0.2881, | |
| "step": 1920 | |
| }, | |
| { | |
| "epoch": 50.45751633986928, | |
| "grad_norm": 5.950506210327148, | |
| "learning_rate": 8.528265107212476e-06, | |
| "loss": 0.2872, | |
| "step": 1930 | |
| }, | |
| { | |
| "epoch": 50.71895424836601, | |
| "grad_norm": 7.726902484893799, | |
| "learning_rate": 8.284600389863548e-06, | |
| "loss": 0.3346, | |
| "step": 1940 | |
| }, | |
| { | |
| "epoch": 50.98039215686274, | |
| "grad_norm": 7.297433376312256, | |
| "learning_rate": 8.04093567251462e-06, | |
| "loss": 0.2403, | |
| "step": 1950 | |
| }, | |
| { | |
| "epoch": 50.98039215686274, | |
| "eval_accuracy": 0.7941176470588235, | |
| "eval_loss": 0.6595063209533691, | |
| "eval_runtime": 21.555, | |
| "eval_samples_per_second": 6.309, | |
| "eval_steps_per_second": 0.789, | |
| "step": 1950 | |
| }, | |
| { | |
| "epoch": 51.24183006535948, | |
| "grad_norm": 7.367440700531006, | |
| "learning_rate": 7.797270955165692e-06, | |
| "loss": 0.2824, | |
| "step": 1960 | |
| }, | |
| { | |
| "epoch": 51.50326797385621, | |
| "grad_norm": 10.130813598632812, | |
| "learning_rate": 7.553606237816764e-06, | |
| "loss": 0.3367, | |
| "step": 1970 | |
| }, | |
| { | |
| "epoch": 51.76470588235294, | |
| "grad_norm": 7.926657199859619, | |
| "learning_rate": 7.3099415204678366e-06, | |
| "loss": 0.2553, | |
| "step": 1980 | |
| }, | |
| { | |
| "epoch": 52.0, | |
| "eval_accuracy": 0.7794117647058824, | |
| "eval_loss": 0.5987350344657898, | |
| "eval_runtime": 20.0722, | |
| "eval_samples_per_second": 6.776, | |
| "eval_steps_per_second": 0.847, | |
| "step": 1989 | |
| }, | |
| { | |
| "epoch": 52.02614379084967, | |
| "grad_norm": 8.90279769897461, | |
| "learning_rate": 7.066276803118908e-06, | |
| "loss": 0.3068, | |
| "step": 1990 | |
| }, | |
| { | |
| "epoch": 52.287581699346404, | |
| "grad_norm": 11.345956802368164, | |
| "learning_rate": 6.82261208576998e-06, | |
| "loss": 0.2884, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 52.549019607843135, | |
| "grad_norm": 8.919641494750977, | |
| "learning_rate": 6.578947368421053e-06, | |
| "loss": 0.295, | |
| "step": 2010 | |
| }, | |
| { | |
| "epoch": 52.810457516339866, | |
| "grad_norm": 7.802643775939941, | |
| "learning_rate": 6.335282651072125e-06, | |
| "loss": 0.2959, | |
| "step": 2020 | |
| }, | |
| { | |
| "epoch": 52.99346405228758, | |
| "eval_accuracy": 0.8235294117647058, | |
| "eval_loss": 0.5459432005882263, | |
| "eval_runtime": 20.7402, | |
| "eval_samples_per_second": 6.557, | |
| "eval_steps_per_second": 0.82, | |
| "step": 2027 | |
| }, | |
| { | |
| "epoch": 53.071895424836605, | |
| "grad_norm": 6.629459381103516, | |
| "learning_rate": 6.091617933723197e-06, | |
| "loss": 0.3203, | |
| "step": 2030 | |
| }, | |
| { | |
| "epoch": 53.333333333333336, | |
| "grad_norm": 7.91646671295166, | |
| "learning_rate": 5.8479532163742686e-06, | |
| "loss": 0.3267, | |
| "step": 2040 | |
| }, | |
| { | |
| "epoch": 53.59477124183007, | |
| "grad_norm": 5.941601276397705, | |
| "learning_rate": 5.604288499025341e-06, | |
| "loss": 0.2962, | |
| "step": 2050 | |
| }, | |
| { | |
| "epoch": 53.8562091503268, | |
| "grad_norm": 7.222002029418945, | |
| "learning_rate": 5.360623781676413e-06, | |
| "loss": 0.3066, | |
| "step": 2060 | |
| }, | |
| { | |
| "epoch": 53.98692810457516, | |
| "eval_accuracy": 0.7867647058823529, | |
| "eval_loss": 0.6198421716690063, | |
| "eval_runtime": 20.555, | |
| "eval_samples_per_second": 6.616, | |
| "eval_steps_per_second": 0.827, | |
| "step": 2065 | |
| }, | |
| { | |
| "epoch": 54.11764705882353, | |
| "grad_norm": 6.425452709197998, | |
| "learning_rate": 5.116959064327485e-06, | |
| "loss": 0.2961, | |
| "step": 2070 | |
| }, | |
| { | |
| "epoch": 54.37908496732026, | |
| "grad_norm": 9.548799514770508, | |
| "learning_rate": 4.873294346978558e-06, | |
| "loss": 0.3363, | |
| "step": 2080 | |
| }, | |
| { | |
| "epoch": 54.64052287581699, | |
| "grad_norm": 7.3025970458984375, | |
| "learning_rate": 4.6296296296296296e-06, | |
| "loss": 0.3843, | |
| "step": 2090 | |
| }, | |
| { | |
| "epoch": 54.90196078431372, | |
| "grad_norm": 8.06686019897461, | |
| "learning_rate": 4.3859649122807014e-06, | |
| "loss": 0.2981, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 54.98039215686274, | |
| "eval_accuracy": 0.8308823529411765, | |
| "eval_loss": 0.4885517656803131, | |
| "eval_runtime": 22.3067, | |
| "eval_samples_per_second": 6.097, | |
| "eval_steps_per_second": 0.762, | |
| "step": 2103 | |
| }, | |
| { | |
| "epoch": 55.16339869281046, | |
| "grad_norm": 7.39772891998291, | |
| "learning_rate": 4.142300194931774e-06, | |
| "loss": 0.315, | |
| "step": 2110 | |
| }, | |
| { | |
| "epoch": 55.42483660130719, | |
| "grad_norm": 6.316030502319336, | |
| "learning_rate": 3.898635477582846e-06, | |
| "loss": 0.2416, | |
| "step": 2120 | |
| }, | |
| { | |
| "epoch": 55.68627450980392, | |
| "grad_norm": 9.764727592468262, | |
| "learning_rate": 3.6549707602339183e-06, | |
| "loss": 0.3007, | |
| "step": 2130 | |
| }, | |
| { | |
| "epoch": 55.947712418300654, | |
| "grad_norm": 9.428828239440918, | |
| "learning_rate": 3.41130604288499e-06, | |
| "loss": 0.2658, | |
| "step": 2140 | |
| }, | |
| { | |
| "epoch": 56.0, | |
| "eval_accuracy": 0.7794117647058824, | |
| "eval_loss": 0.6422163844108582, | |
| "eval_runtime": 20.6286, | |
| "eval_samples_per_second": 6.593, | |
| "eval_steps_per_second": 0.824, | |
| "step": 2142 | |
| }, | |
| { | |
| "epoch": 56.209150326797385, | |
| "grad_norm": 11.038329124450684, | |
| "learning_rate": 3.1676413255360624e-06, | |
| "loss": 0.3298, | |
| "step": 2150 | |
| }, | |
| { | |
| "epoch": 56.470588235294116, | |
| "grad_norm": 7.585492134094238, | |
| "learning_rate": 2.9239766081871343e-06, | |
| "loss": 0.3365, | |
| "step": 2160 | |
| }, | |
| { | |
| "epoch": 56.73202614379085, | |
| "grad_norm": 11.289450645446777, | |
| "learning_rate": 2.6803118908382066e-06, | |
| "loss": 0.3559, | |
| "step": 2170 | |
| }, | |
| { | |
| "epoch": 56.99346405228758, | |
| "grad_norm": 8.215266227722168, | |
| "learning_rate": 2.436647173489279e-06, | |
| "loss": 0.2371, | |
| "step": 2180 | |
| }, | |
| { | |
| "epoch": 56.99346405228758, | |
| "eval_accuracy": 0.8382352941176471, | |
| "eval_loss": 0.4999590516090393, | |
| "eval_runtime": 19.8968, | |
| "eval_samples_per_second": 6.835, | |
| "eval_steps_per_second": 0.854, | |
| "step": 2180 | |
| }, | |
| { | |
| "epoch": 57.254901960784316, | |
| "grad_norm": 6.436427116394043, | |
| "learning_rate": 2.1929824561403507e-06, | |
| "loss": 0.2826, | |
| "step": 2190 | |
| }, | |
| { | |
| "epoch": 57.51633986928105, | |
| "grad_norm": 10.186029434204102, | |
| "learning_rate": 1.949317738791423e-06, | |
| "loss": 0.3155, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 57.77777777777778, | |
| "grad_norm": 5.971257209777832, | |
| "learning_rate": 1.705653021442495e-06, | |
| "loss": 0.2331, | |
| "step": 2210 | |
| }, | |
| { | |
| "epoch": 57.98692810457516, | |
| "eval_accuracy": 0.7132352941176471, | |
| "eval_loss": 0.8853857517242432, | |
| "eval_runtime": 21.9358, | |
| "eval_samples_per_second": 6.2, | |
| "eval_steps_per_second": 0.775, | |
| "step": 2218 | |
| }, | |
| { | |
| "epoch": 58.03921568627451, | |
| "grad_norm": 5.772573947906494, | |
| "learning_rate": 1.4619883040935671e-06, | |
| "loss": 0.2802, | |
| "step": 2220 | |
| }, | |
| { | |
| "epoch": 58.30065359477124, | |
| "grad_norm": 8.661057472229004, | |
| "learning_rate": 1.2183235867446394e-06, | |
| "loss": 0.286, | |
| "step": 2230 | |
| }, | |
| { | |
| "epoch": 58.56209150326797, | |
| "grad_norm": 7.350020408630371, | |
| "learning_rate": 9.746588693957115e-07, | |
| "loss": 0.2523, | |
| "step": 2240 | |
| }, | |
| { | |
| "epoch": 58.8235294117647, | |
| "grad_norm": 10.219001770019531, | |
| "learning_rate": 7.309941520467836e-07, | |
| "loss": 0.2777, | |
| "step": 2250 | |
| }, | |
| { | |
| "epoch": 58.98039215686274, | |
| "eval_accuracy": 0.8014705882352942, | |
| "eval_loss": 0.6190231442451477, | |
| "eval_runtime": 19.9884, | |
| "eval_samples_per_second": 6.804, | |
| "eval_steps_per_second": 0.85, | |
| "step": 2256 | |
| }, | |
| { | |
| "epoch": 59.08496732026144, | |
| "grad_norm": 6.8238396644592285, | |
| "learning_rate": 4.873294346978557e-07, | |
| "loss": 0.2722, | |
| "step": 2260 | |
| }, | |
| { | |
| "epoch": 59.34640522875817, | |
| "grad_norm": 9.155200004577637, | |
| "learning_rate": 2.436647173489279e-07, | |
| "loss": 0.2591, | |
| "step": 2270 | |
| }, | |
| { | |
| "epoch": 59.6078431372549, | |
| "grad_norm": 7.341146469116211, | |
| "learning_rate": 0.0, | |
| "loss": 0.3047, | |
| "step": 2280 | |
| }, | |
| { | |
| "epoch": 59.6078431372549, | |
| "eval_accuracy": 0.7647058823529411, | |
| "eval_loss": 0.604828417301178, | |
| "eval_runtime": 20.7055, | |
| "eval_samples_per_second": 6.568, | |
| "eval_steps_per_second": 0.821, | |
| "step": 2280 | |
| }, | |
| { | |
| "epoch": 59.6078431372549, | |
| "step": 2280, | |
| "total_flos": 1.9206376588836864e+17, | |
| "train_loss": 0.5395637326073228, | |
| "train_runtime": 14275.0415, | |
| "train_samples_per_second": 5.145, | |
| "train_steps_per_second": 0.16 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 2280, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 60, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.9206376588836864e+17, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |