| { | |
| "best_metric": 0.8691893001382458, | |
| "best_model_checkpoint": "CurbRamp/dinov2/checkpoint-2875", | |
| "epoch": 24.786177105831534, | |
| "eval_steps": 500, | |
| "global_step": 2875, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.08639308855291576, | |
| "grad_norm": 381.287109375, | |
| "learning_rate": 3.472222222222223e-07, | |
| "loss": 3.0906, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.17278617710583152, | |
| "grad_norm": 161.04339599609375, | |
| "learning_rate": 6.944444444444446e-07, | |
| "loss": 2.6994, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.2591792656587473, | |
| "grad_norm": 111.33332824707031, | |
| "learning_rate": 1.0416666666666667e-06, | |
| "loss": 2.6304, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.34557235421166305, | |
| "grad_norm": 74.54171752929688, | |
| "learning_rate": 1.3888888888888892e-06, | |
| "loss": 2.4279, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.4319654427645788, | |
| "grad_norm": 62.23763656616211, | |
| "learning_rate": 1.7361111111111112e-06, | |
| "loss": 2.0601, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.5183585313174947, | |
| "grad_norm": 109.49163055419922, | |
| "learning_rate": 2.0833333333333334e-06, | |
| "loss": 2.2144, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.6047516198704104, | |
| "grad_norm": 140.09844970703125, | |
| "learning_rate": 2.4305555555555557e-06, | |
| "loss": 1.9144, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.6911447084233261, | |
| "grad_norm": 86.56855010986328, | |
| "learning_rate": 2.7777777777777783e-06, | |
| "loss": 1.9794, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.7775377969762419, | |
| "grad_norm": 87.58937072753906, | |
| "learning_rate": 3.125e-06, | |
| "loss": 1.99, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.8639308855291576, | |
| "grad_norm": 95.44474029541016, | |
| "learning_rate": 3.4722222222222224e-06, | |
| "loss": 1.8081, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.9503239740820735, | |
| "grad_norm": 135.51611328125, | |
| "learning_rate": 3.819444444444444e-06, | |
| "loss": 1.723, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 0.5266662836074829, | |
| "eval_macro_f1": 0.7558472709624431, | |
| "eval_runtime": 52.7672, | |
| "eval_samples_per_second": 17.549, | |
| "eval_steps_per_second": 2.198, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 1.0345572354211663, | |
| "grad_norm": 67.76123809814453, | |
| "learning_rate": 4.166666666666667e-06, | |
| "loss": 1.7629, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 1.1209503239740821, | |
| "grad_norm": 164.42552185058594, | |
| "learning_rate": 4.5138888888888895e-06, | |
| "loss": 1.7207, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 1.2073434125269977, | |
| "grad_norm": 63.25754165649414, | |
| "learning_rate": 4.861111111111111e-06, | |
| "loss": 1.8562, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 1.2937365010799136, | |
| "grad_norm": 101.76183319091797, | |
| "learning_rate": 5.208333333333334e-06, | |
| "loss": 1.5125, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 1.3801295896328294, | |
| "grad_norm": 104.06229400634766, | |
| "learning_rate": 5.555555555555557e-06, | |
| "loss": 1.7283, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 1.4665226781857452, | |
| "grad_norm": 100.93425750732422, | |
| "learning_rate": 5.9027777777777785e-06, | |
| "loss": 1.8195, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 1.552915766738661, | |
| "grad_norm": 73.55767822265625, | |
| "learning_rate": 6.25e-06, | |
| "loss": 1.6554, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 1.6393088552915767, | |
| "grad_norm": 80.74930572509766, | |
| "learning_rate": 6.597222222222223e-06, | |
| "loss": 1.4719, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 1.7257019438444925, | |
| "grad_norm": 70.96980285644531, | |
| "learning_rate": 6.944444444444445e-06, | |
| "loss": 1.8123, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.812095032397408, | |
| "grad_norm": 59.61140823364258, | |
| "learning_rate": 7.291666666666667e-06, | |
| "loss": 1.4448, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 1.898488120950324, | |
| "grad_norm": 278.9685974121094, | |
| "learning_rate": 7.638888888888888e-06, | |
| "loss": 1.7311, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 1.9848812095032398, | |
| "grad_norm": 149.49319458007812, | |
| "learning_rate": 7.986111111111112e-06, | |
| "loss": 1.79, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 0.5045331716537476, | |
| "eval_macro_f1": 0.7580948382431834, | |
| "eval_runtime": 16.9579, | |
| "eval_samples_per_second": 54.606, | |
| "eval_steps_per_second": 6.84, | |
| "step": 232 | |
| }, | |
| { | |
| "epoch": 2.0691144708423326, | |
| "grad_norm": 39.244441986083984, | |
| "learning_rate": 8.333333333333334e-06, | |
| "loss": 1.4816, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 2.1555075593952484, | |
| "grad_norm": 62.760921478271484, | |
| "learning_rate": 8.680555555555557e-06, | |
| "loss": 1.5412, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 2.2419006479481642, | |
| "grad_norm": 58.07555389404297, | |
| "learning_rate": 9.027777777777779e-06, | |
| "loss": 1.5415, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 2.32829373650108, | |
| "grad_norm": 83.29940032958984, | |
| "learning_rate": 9.375000000000001e-06, | |
| "loss": 1.3842, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 2.4146868250539955, | |
| "grad_norm": 91.45130157470703, | |
| "learning_rate": 9.722222222222223e-06, | |
| "loss": 1.3325, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 2.5010799136069113, | |
| "grad_norm": 63.806114196777344, | |
| "learning_rate": 9.99226903749517e-06, | |
| "loss": 1.4369, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 2.587473002159827, | |
| "grad_norm": 70.26383972167969, | |
| "learning_rate": 9.95361422497101e-06, | |
| "loss": 1.8433, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 2.673866090712743, | |
| "grad_norm": 136.43692016601562, | |
| "learning_rate": 9.914959412446851e-06, | |
| "loss": 1.9714, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 2.760259179265659, | |
| "grad_norm": 66.07856750488281, | |
| "learning_rate": 9.87630459992269e-06, | |
| "loss": 1.5597, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 2.8466522678185746, | |
| "grad_norm": 43.0218620300293, | |
| "learning_rate": 9.837649787398532e-06, | |
| "loss": 1.7732, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 2.9330453563714904, | |
| "grad_norm": 85.20895385742188, | |
| "learning_rate": 9.798994974874372e-06, | |
| "loss": 1.8472, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 0.5161793231964111, | |
| "eval_macro_f1": 0.7796335673223247, | |
| "eval_runtime": 17.216, | |
| "eval_samples_per_second": 53.787, | |
| "eval_steps_per_second": 6.738, | |
| "step": 348 | |
| }, | |
| { | |
| "epoch": 3.0172786177105833, | |
| "grad_norm": 42.26615905761719, | |
| "learning_rate": 9.760340162350214e-06, | |
| "loss": 1.261, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 3.103671706263499, | |
| "grad_norm": 152.00830078125, | |
| "learning_rate": 9.721685349826055e-06, | |
| "loss": 1.1856, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 3.190064794816415, | |
| "grad_norm": 70.4239273071289, | |
| "learning_rate": 9.683030537301895e-06, | |
| "loss": 1.2873, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 3.2764578833693303, | |
| "grad_norm": 48.222984313964844, | |
| "learning_rate": 9.644375724777736e-06, | |
| "loss": 1.0901, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 3.362850971922246, | |
| "grad_norm": 56.9564323425293, | |
| "learning_rate": 9.605720912253576e-06, | |
| "loss": 1.1631, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 3.449244060475162, | |
| "grad_norm": 48.229427337646484, | |
| "learning_rate": 9.567066099729418e-06, | |
| "loss": 1.3436, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 3.535637149028078, | |
| "grad_norm": 69.0005111694336, | |
| "learning_rate": 9.528411287205257e-06, | |
| "loss": 1.0393, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 3.6220302375809936, | |
| "grad_norm": 69.22911071777344, | |
| "learning_rate": 9.489756474681099e-06, | |
| "loss": 1.3696, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 3.708423326133909, | |
| "grad_norm": 89.3969497680664, | |
| "learning_rate": 9.45110166215694e-06, | |
| "loss": 1.2418, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 3.7948164146868253, | |
| "grad_norm": 76.02294921875, | |
| "learning_rate": 9.41244684963278e-06, | |
| "loss": 1.3444, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 3.8812095032397407, | |
| "grad_norm": 79.65322875976562, | |
| "learning_rate": 9.373792037108622e-06, | |
| "loss": 1.5226, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 3.9676025917926565, | |
| "grad_norm": 118.36911010742188, | |
| "learning_rate": 9.335137224584461e-06, | |
| "loss": 1.4474, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_loss": 0.39091792702674866, | |
| "eval_macro_f1": 0.8356080726022923, | |
| "eval_runtime": 17.0101, | |
| "eval_samples_per_second": 54.438, | |
| "eval_steps_per_second": 6.819, | |
| "step": 464 | |
| }, | |
| { | |
| "epoch": 4.05183585313175, | |
| "grad_norm": 34.40155029296875, | |
| "learning_rate": 9.296482412060303e-06, | |
| "loss": 0.9722, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 4.138228941684665, | |
| "grad_norm": 52.04656219482422, | |
| "learning_rate": 9.257827599536143e-06, | |
| "loss": 0.9749, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 4.224622030237581, | |
| "grad_norm": 65.06253814697266, | |
| "learning_rate": 9.219172787011984e-06, | |
| "loss": 1.1242, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 4.311015118790497, | |
| "grad_norm": 66.4505844116211, | |
| "learning_rate": 9.180517974487826e-06, | |
| "loss": 1.1458, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 4.397408207343412, | |
| "grad_norm": 158.91885375976562, | |
| "learning_rate": 9.141863161963665e-06, | |
| "loss": 1.3353, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 4.4838012958963285, | |
| "grad_norm": 60.72650909423828, | |
| "learning_rate": 9.103208349439507e-06, | |
| "loss": 1.1444, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 4.570194384449244, | |
| "grad_norm": 46.68295669555664, | |
| "learning_rate": 9.064553536915347e-06, | |
| "loss": 1.1094, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 4.65658747300216, | |
| "grad_norm": 121.51728820800781, | |
| "learning_rate": 9.025898724391188e-06, | |
| "loss": 1.398, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 4.7429805615550755, | |
| "grad_norm": 46.293556213378906, | |
| "learning_rate": 8.987243911867028e-06, | |
| "loss": 1.1777, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 4.829373650107991, | |
| "grad_norm": 67.82626342773438, | |
| "learning_rate": 8.94858909934287e-06, | |
| "loss": 1.0463, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 4.915766738660907, | |
| "grad_norm": 54.6425895690918, | |
| "learning_rate": 8.90993428681871e-06, | |
| "loss": 1.0591, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "grad_norm": 46.120140075683594, | |
| "learning_rate": 8.87127947429455e-06, | |
| "loss": 1.0474, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_loss": 0.5121903419494629, | |
| "eval_macro_f1": 0.7977332272718247, | |
| "eval_runtime": 17.2455, | |
| "eval_samples_per_second": 53.695, | |
| "eval_steps_per_second": 6.726, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 5.086393088552915, | |
| "grad_norm": 59.340538024902344, | |
| "learning_rate": 8.832624661770392e-06, | |
| "loss": 0.9155, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 5.172786177105832, | |
| "grad_norm": 47.96815872192383, | |
| "learning_rate": 8.793969849246232e-06, | |
| "loss": 0.8381, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 5.259179265658747, | |
| "grad_norm": 50.32111358642578, | |
| "learning_rate": 8.755315036722073e-06, | |
| "loss": 0.9608, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 5.345572354211663, | |
| "grad_norm": 76.34898376464844, | |
| "learning_rate": 8.716660224197913e-06, | |
| "loss": 0.9766, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 5.431965442764579, | |
| "grad_norm": 40.53537368774414, | |
| "learning_rate": 8.678005411673755e-06, | |
| "loss": 1.1101, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 5.518358531317495, | |
| "grad_norm": 62.64771270751953, | |
| "learning_rate": 8.639350599149594e-06, | |
| "loss": 1.0492, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 5.60475161987041, | |
| "grad_norm": 34.409095764160156, | |
| "learning_rate": 8.600695786625436e-06, | |
| "loss": 1.0763, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 5.691144708423326, | |
| "grad_norm": 77.56722259521484, | |
| "learning_rate": 8.562040974101277e-06, | |
| "loss": 0.9917, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 5.777537796976242, | |
| "grad_norm": 37.74449920654297, | |
| "learning_rate": 8.523386161577117e-06, | |
| "loss": 1.1072, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 5.863930885529157, | |
| "grad_norm": 55.60712814331055, | |
| "learning_rate": 8.484731349052959e-06, | |
| "loss": 0.9095, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 5.950323974082074, | |
| "grad_norm": 45.91484451293945, | |
| "learning_rate": 8.446076536528798e-06, | |
| "loss": 0.931, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_loss": 0.41715672612190247, | |
| "eval_macro_f1": 0.8296228150873965, | |
| "eval_runtime": 16.9093, | |
| "eval_samples_per_second": 54.763, | |
| "eval_steps_per_second": 6.86, | |
| "step": 696 | |
| }, | |
| { | |
| "epoch": 6.0345572354211665, | |
| "grad_norm": 38.476654052734375, | |
| "learning_rate": 8.40742172400464e-06, | |
| "loss": 0.7875, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 6.120950323974082, | |
| "grad_norm": 23.64281463623047, | |
| "learning_rate": 8.36876691148048e-06, | |
| "loss": 0.7492, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 6.207343412526998, | |
| "grad_norm": 102.30036926269531, | |
| "learning_rate": 8.330112098956321e-06, | |
| "loss": 0.6453, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 6.293736501079914, | |
| "grad_norm": 27.228309631347656, | |
| "learning_rate": 8.291457286432163e-06, | |
| "loss": 0.9595, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 6.38012958963283, | |
| "grad_norm": 54.58305358886719, | |
| "learning_rate": 8.252802473908002e-06, | |
| "loss": 0.5922, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 6.466522678185745, | |
| "grad_norm": 99.91376495361328, | |
| "learning_rate": 8.214147661383844e-06, | |
| "loss": 0.7878, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 6.552915766738661, | |
| "grad_norm": 91.14471435546875, | |
| "learning_rate": 8.175492848859684e-06, | |
| "loss": 0.7622, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 6.639308855291577, | |
| "grad_norm": 79.27790069580078, | |
| "learning_rate": 8.136838036335525e-06, | |
| "loss": 0.9503, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 6.725701943844492, | |
| "grad_norm": 70.4741439819336, | |
| "learning_rate": 8.098183223811365e-06, | |
| "loss": 0.8432, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 6.8120950323974085, | |
| "grad_norm": 62.995697021484375, | |
| "learning_rate": 8.059528411287206e-06, | |
| "loss": 0.8593, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 6.898488120950324, | |
| "grad_norm": 34.43967056274414, | |
| "learning_rate": 8.020873598763048e-06, | |
| "loss": 0.577, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 6.984881209503239, | |
| "grad_norm": 101.01258087158203, | |
| "learning_rate": 7.982218786238888e-06, | |
| "loss": 0.9042, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_loss": 0.4327438175678253, | |
| "eval_macro_f1": 0.8414019539605782, | |
| "eval_runtime": 16.9563, | |
| "eval_samples_per_second": 54.611, | |
| "eval_steps_per_second": 6.841, | |
| "step": 812 | |
| }, | |
| { | |
| "epoch": 7.069114470842333, | |
| "grad_norm": 60.159706115722656, | |
| "learning_rate": 7.943563973714729e-06, | |
| "loss": 0.7565, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 7.155507559395248, | |
| "grad_norm": 94.81135559082031, | |
| "learning_rate": 7.904909161190569e-06, | |
| "loss": 0.5015, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 7.241900647948164, | |
| "grad_norm": 148.54061889648438, | |
| "learning_rate": 7.86625434866641e-06, | |
| "loss": 0.9681, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 7.32829373650108, | |
| "grad_norm": 89.39724731445312, | |
| "learning_rate": 7.82759953614225e-06, | |
| "loss": 1.3573, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 7.4146868250539955, | |
| "grad_norm": 32.64114761352539, | |
| "learning_rate": 7.788944723618092e-06, | |
| "loss": 0.5587, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 7.501079913606912, | |
| "grad_norm": 49.56209182739258, | |
| "learning_rate": 7.750289911093933e-06, | |
| "loss": 0.7781, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 7.587473002159827, | |
| "grad_norm": 65.53961181640625, | |
| "learning_rate": 7.711635098569773e-06, | |
| "loss": 0.6911, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 7.6738660907127425, | |
| "grad_norm": 52.27827835083008, | |
| "learning_rate": 7.672980286045614e-06, | |
| "loss": 0.8156, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 7.760259179265659, | |
| "grad_norm": 58.8625602722168, | |
| "learning_rate": 7.634325473521454e-06, | |
| "loss": 0.6504, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 7.846652267818574, | |
| "grad_norm": 58.183353424072266, | |
| "learning_rate": 7.595670660997296e-06, | |
| "loss": 0.8262, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 7.93304535637149, | |
| "grad_norm": 66.90734100341797, | |
| "learning_rate": 7.557015848473136e-06, | |
| "loss": 0.7893, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_loss": 0.4484424591064453, | |
| "eval_macro_f1": 0.832676482797353, | |
| "eval_runtime": 17.3598, | |
| "eval_samples_per_second": 53.342, | |
| "eval_steps_per_second": 6.682, | |
| "step": 928 | |
| }, | |
| { | |
| "epoch": 8.017278617710582, | |
| "grad_norm": 56.62957000732422, | |
| "learning_rate": 7.518361035948977e-06, | |
| "loss": 0.6286, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 8.1036717062635, | |
| "grad_norm": 83.84600067138672, | |
| "learning_rate": 7.4797062234248175e-06, | |
| "loss": 0.809, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 8.190064794816415, | |
| "grad_norm": 63.44249725341797, | |
| "learning_rate": 7.441051410900658e-06, | |
| "loss": 0.7384, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 8.27645788336933, | |
| "grad_norm": 30.475244522094727, | |
| "learning_rate": 7.402396598376499e-06, | |
| "loss": 0.561, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 8.362850971922246, | |
| "grad_norm": 67.37047576904297, | |
| "learning_rate": 7.363741785852339e-06, | |
| "loss": 0.7086, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 8.449244060475163, | |
| "grad_norm": 61.570945739746094, | |
| "learning_rate": 7.325086973328181e-06, | |
| "loss": 0.5365, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 8.535637149028078, | |
| "grad_norm": 52.1601676940918, | |
| "learning_rate": 7.2864321608040215e-06, | |
| "loss": 0.4852, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 8.622030237580994, | |
| "grad_norm": 34.1832275390625, | |
| "learning_rate": 7.247777348279862e-06, | |
| "loss": 0.6972, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 8.708423326133909, | |
| "grad_norm": 63.52924346923828, | |
| "learning_rate": 7.209122535755703e-06, | |
| "loss": 0.7469, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 8.794816414686824, | |
| "grad_norm": 62.66010284423828, | |
| "learning_rate": 7.170467723231543e-06, | |
| "loss": 0.9771, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 8.881209503239742, | |
| "grad_norm": 76.71471405029297, | |
| "learning_rate": 7.131812910707384e-06, | |
| "loss": 0.7411, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 8.967602591792657, | |
| "grad_norm": 27.406539916992188, | |
| "learning_rate": 7.093158098183225e-06, | |
| "loss": 0.7943, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_loss": 0.46906793117523193, | |
| "eval_macro_f1": 0.8359894804603093, | |
| "eval_runtime": 17.671, | |
| "eval_samples_per_second": 52.402, | |
| "eval_steps_per_second": 6.564, | |
| "step": 1044 | |
| }, | |
| { | |
| "epoch": 9.051835853131749, | |
| "grad_norm": 16.15360450744629, | |
| "learning_rate": 7.054503285659065e-06, | |
| "loss": 0.4819, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 9.138228941684666, | |
| "grad_norm": 86.55136108398438, | |
| "learning_rate": 7.015848473134907e-06, | |
| "loss": 0.8165, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 9.224622030237581, | |
| "grad_norm": 58.48967361450195, | |
| "learning_rate": 6.977193660610747e-06, | |
| "loss": 0.6899, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 9.311015118790497, | |
| "grad_norm": 74.65888214111328, | |
| "learning_rate": 6.938538848086588e-06, | |
| "loss": 0.4518, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 9.397408207343412, | |
| "grad_norm": 32.85594940185547, | |
| "learning_rate": 6.899884035562429e-06, | |
| "loss": 0.5768, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 9.483801295896328, | |
| "grad_norm": 97.70096588134766, | |
| "learning_rate": 6.861229223038269e-06, | |
| "loss": 0.5102, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 9.570194384449245, | |
| "grad_norm": 46.2236213684082, | |
| "learning_rate": 6.82257441051411e-06, | |
| "loss": 0.5204, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 9.65658747300216, | |
| "grad_norm": 67.02069091796875, | |
| "learning_rate": 6.7839195979899505e-06, | |
| "loss": 0.7371, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 9.742980561555076, | |
| "grad_norm": 47.46559143066406, | |
| "learning_rate": 6.745264785465792e-06, | |
| "loss": 0.5447, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 9.829373650107991, | |
| "grad_norm": 31.422773361206055, | |
| "learning_rate": 6.706609972941633e-06, | |
| "loss": 0.6734, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 9.915766738660906, | |
| "grad_norm": 35.7156867980957, | |
| "learning_rate": 6.667955160417473e-06, | |
| "loss": 0.6255, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "grad_norm": 71.64591217041016, | |
| "learning_rate": 6.629300347893314e-06, | |
| "loss": 0.482, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_loss": 0.44722601771354675, | |
| "eval_macro_f1": 0.846851581651592, | |
| "eval_runtime": 16.8938, | |
| "eval_samples_per_second": 54.813, | |
| "eval_steps_per_second": 6.866, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 10.086393088552915, | |
| "grad_norm": 53.67696762084961, | |
| "learning_rate": 6.5906455353691545e-06, | |
| "loss": 0.5785, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 10.17278617710583, | |
| "grad_norm": 26.457019805908203, | |
| "learning_rate": 6.551990722844995e-06, | |
| "loss": 0.528, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 10.259179265658748, | |
| "grad_norm": 87.2643051147461, | |
| "learning_rate": 6.513335910320836e-06, | |
| "loss": 0.5065, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 10.345572354211663, | |
| "grad_norm": 63.67802810668945, | |
| "learning_rate": 6.474681097796676e-06, | |
| "loss": 0.4843, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 10.431965442764579, | |
| "grad_norm": 92.45316314697266, | |
| "learning_rate": 6.436026285272518e-06, | |
| "loss": 0.3929, | |
| "step": 1210 | |
| }, | |
| { | |
| "epoch": 10.518358531317494, | |
| "grad_norm": 110.85811614990234, | |
| "learning_rate": 6.3973714727483585e-06, | |
| "loss": 0.5893, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 10.60475161987041, | |
| "grad_norm": 84.82708740234375, | |
| "learning_rate": 6.358716660224199e-06, | |
| "loss": 0.5031, | |
| "step": 1230 | |
| }, | |
| { | |
| "epoch": 10.691144708423327, | |
| "grad_norm": 75.6590576171875, | |
| "learning_rate": 6.32006184770004e-06, | |
| "loss": 0.5282, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 10.777537796976242, | |
| "grad_norm": 55.62372589111328, | |
| "learning_rate": 6.28140703517588e-06, | |
| "loss": 0.4551, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 10.863930885529157, | |
| "grad_norm": 61.89540100097656, | |
| "learning_rate": 6.24275222265172e-06, | |
| "loss": 0.5981, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 10.950323974082073, | |
| "grad_norm": 51.5389404296875, | |
| "learning_rate": 6.204097410127561e-06, | |
| "loss": 0.5145, | |
| "step": 1270 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_loss": 0.45396292209625244, | |
| "eval_macro_f1": 0.8514981354090372, | |
| "eval_runtime": 16.9232, | |
| "eval_samples_per_second": 54.718, | |
| "eval_steps_per_second": 6.855, | |
| "step": 1276 | |
| }, | |
| { | |
| "epoch": 11.034557235421167, | |
| "grad_norm": 73.23987579345703, | |
| "learning_rate": 6.165442597603401e-06, | |
| "loss": 0.5773, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 11.120950323974082, | |
| "grad_norm": 26.071277618408203, | |
| "learning_rate": 6.126787785079242e-06, | |
| "loss": 0.5628, | |
| "step": 1290 | |
| }, | |
| { | |
| "epoch": 11.207343412526997, | |
| "grad_norm": 49.137691497802734, | |
| "learning_rate": 6.088132972555083e-06, | |
| "loss": 0.4894, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 11.293736501079914, | |
| "grad_norm": 63.3178825378418, | |
| "learning_rate": 6.049478160030924e-06, | |
| "loss": 0.6504, | |
| "step": 1310 | |
| }, | |
| { | |
| "epoch": 11.38012958963283, | |
| "grad_norm": 20.981409072875977, | |
| "learning_rate": 6.010823347506765e-06, | |
| "loss": 0.4835, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 11.466522678185745, | |
| "grad_norm": 35.6384162902832, | |
| "learning_rate": 5.972168534982605e-06, | |
| "loss": 0.568, | |
| "step": 1330 | |
| }, | |
| { | |
| "epoch": 11.55291576673866, | |
| "grad_norm": 20.20071029663086, | |
| "learning_rate": 5.933513722458446e-06, | |
| "loss": 0.2126, | |
| "step": 1340 | |
| }, | |
| { | |
| "epoch": 11.639308855291576, | |
| "grad_norm": 37.92521667480469, | |
| "learning_rate": 5.894858909934287e-06, | |
| "loss": 0.4932, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 11.725701943844493, | |
| "grad_norm": 20.3985538482666, | |
| "learning_rate": 5.856204097410127e-06, | |
| "loss": 0.5133, | |
| "step": 1360 | |
| }, | |
| { | |
| "epoch": 11.812095032397409, | |
| "grad_norm": 70.6824951171875, | |
| "learning_rate": 5.817549284885968e-06, | |
| "loss": 0.7987, | |
| "step": 1370 | |
| }, | |
| { | |
| "epoch": 11.898488120950324, | |
| "grad_norm": 133.84133911132812, | |
| "learning_rate": 5.778894472361809e-06, | |
| "loss": 0.5215, | |
| "step": 1380 | |
| }, | |
| { | |
| "epoch": 11.98488120950324, | |
| "grad_norm": 30.232711791992188, | |
| "learning_rate": 5.74023965983765e-06, | |
| "loss": 0.4581, | |
| "step": 1390 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_loss": 0.4816704988479614, | |
| "eval_macro_f1": 0.8516025641025642, | |
| "eval_runtime": 17.3032, | |
| "eval_samples_per_second": 53.516, | |
| "eval_steps_per_second": 6.704, | |
| "step": 1392 | |
| }, | |
| { | |
| "epoch": 12.069114470842333, | |
| "grad_norm": 65.2093276977539, | |
| "learning_rate": 5.701584847313491e-06, | |
| "loss": 0.285, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 12.155507559395248, | |
| "grad_norm": 73.72334289550781, | |
| "learning_rate": 5.662930034789331e-06, | |
| "loss": 0.5098, | |
| "step": 1410 | |
| }, | |
| { | |
| "epoch": 12.241900647948164, | |
| "grad_norm": 49.37625503540039, | |
| "learning_rate": 5.624275222265172e-06, | |
| "loss": 0.623, | |
| "step": 1420 | |
| }, | |
| { | |
| "epoch": 12.32829373650108, | |
| "grad_norm": 49.2904052734375, | |
| "learning_rate": 5.5856204097410125e-06, | |
| "loss": 0.4641, | |
| "step": 1430 | |
| }, | |
| { | |
| "epoch": 12.414686825053996, | |
| "grad_norm": 29.282928466796875, | |
| "learning_rate": 5.546965597216853e-06, | |
| "loss": 0.4904, | |
| "step": 1440 | |
| }, | |
| { | |
| "epoch": 12.501079913606912, | |
| "grad_norm": 51.97225570678711, | |
| "learning_rate": 5.508310784692694e-06, | |
| "loss": 0.4044, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 12.587473002159827, | |
| "grad_norm": 44.74934768676758, | |
| "learning_rate": 5.469655972168535e-06, | |
| "loss": 0.6768, | |
| "step": 1460 | |
| }, | |
| { | |
| "epoch": 12.673866090712743, | |
| "grad_norm": 40.65571975708008, | |
| "learning_rate": 5.431001159644376e-06, | |
| "loss": 0.3807, | |
| "step": 1470 | |
| }, | |
| { | |
| "epoch": 12.76025917926566, | |
| "grad_norm": 204.83670043945312, | |
| "learning_rate": 5.3923463471202165e-06, | |
| "loss": 0.3421, | |
| "step": 1480 | |
| }, | |
| { | |
| "epoch": 12.846652267818575, | |
| "grad_norm": 45.30833053588867, | |
| "learning_rate": 5.353691534596057e-06, | |
| "loss": 0.4806, | |
| "step": 1490 | |
| }, | |
| { | |
| "epoch": 12.93304535637149, | |
| "grad_norm": 30.75054168701172, | |
| "learning_rate": 5.315036722071898e-06, | |
| "loss": 0.3743, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_loss": 0.4918636083602905, | |
| "eval_macro_f1": 0.8659523584493705, | |
| "eval_runtime": 17.5008, | |
| "eval_samples_per_second": 52.912, | |
| "eval_steps_per_second": 6.628, | |
| "step": 1508 | |
| }, | |
| { | |
| "epoch": 13.017278617710582, | |
| "grad_norm": 76.16972351074219, | |
| "learning_rate": 5.2763819095477384e-06, | |
| "loss": 0.2202, | |
| "step": 1510 | |
| }, | |
| { | |
| "epoch": 13.1036717062635, | |
| "grad_norm": 2.941861152648926, | |
| "learning_rate": 5.237727097023579e-06, | |
| "loss": 0.5201, | |
| "step": 1520 | |
| }, | |
| { | |
| "epoch": 13.190064794816415, | |
| "grad_norm": 102.31110382080078, | |
| "learning_rate": 5.1990722844994205e-06, | |
| "loss": 0.3936, | |
| "step": 1530 | |
| }, | |
| { | |
| "epoch": 13.27645788336933, | |
| "grad_norm": 118.30928802490234, | |
| "learning_rate": 5.160417471975261e-06, | |
| "loss": 0.4541, | |
| "step": 1540 | |
| }, | |
| { | |
| "epoch": 13.362850971922246, | |
| "grad_norm": 27.03119659423828, | |
| "learning_rate": 5.121762659451102e-06, | |
| "loss": 0.5705, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 13.449244060475163, | |
| "grad_norm": 21.778711318969727, | |
| "learning_rate": 5.083107846926942e-06, | |
| "loss": 0.3093, | |
| "step": 1560 | |
| }, | |
| { | |
| "epoch": 13.535637149028078, | |
| "grad_norm": 7.353912830352783, | |
| "learning_rate": 5.044453034402783e-06, | |
| "loss": 0.2553, | |
| "step": 1570 | |
| }, | |
| { | |
| "epoch": 13.622030237580994, | |
| "grad_norm": 41.609153747558594, | |
| "learning_rate": 5.005798221878624e-06, | |
| "loss": 0.4612, | |
| "step": 1580 | |
| }, | |
| { | |
| "epoch": 13.708423326133909, | |
| "grad_norm": 167.5371856689453, | |
| "learning_rate": 4.967143409354465e-06, | |
| "loss": 0.8447, | |
| "step": 1590 | |
| }, | |
| { | |
| "epoch": 13.794816414686824, | |
| "grad_norm": 63.91857147216797, | |
| "learning_rate": 4.928488596830306e-06, | |
| "loss": 0.2376, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 13.881209503239742, | |
| "grad_norm": 5.819667816162109, | |
| "learning_rate": 4.889833784306146e-06, | |
| "loss": 0.2624, | |
| "step": 1610 | |
| }, | |
| { | |
| "epoch": 13.967602591792657, | |
| "grad_norm": 61.421180725097656, | |
| "learning_rate": 4.851178971781987e-06, | |
| "loss": 0.5579, | |
| "step": 1620 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_loss": 0.5265308022499084, | |
| "eval_macro_f1": 0.8497394016895295, | |
| "eval_runtime": 16.9332, | |
| "eval_samples_per_second": 54.685, | |
| "eval_steps_per_second": 6.85, | |
| "step": 1624 | |
| }, | |
| { | |
| "epoch": 14.051835853131749, | |
| "grad_norm": 55.67881774902344, | |
| "learning_rate": 4.8125241592578285e-06, | |
| "loss": 0.3435, | |
| "step": 1630 | |
| }, | |
| { | |
| "epoch": 14.138228941684666, | |
| "grad_norm": 68.73692321777344, | |
| "learning_rate": 4.773869346733669e-06, | |
| "loss": 0.4087, | |
| "step": 1640 | |
| }, | |
| { | |
| "epoch": 14.224622030237581, | |
| "grad_norm": 17.55417823791504, | |
| "learning_rate": 4.73521453420951e-06, | |
| "loss": 0.4633, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 14.311015118790497, | |
| "grad_norm": 71.73014831542969, | |
| "learning_rate": 4.69655972168535e-06, | |
| "loss": 0.3692, | |
| "step": 1660 | |
| }, | |
| { | |
| "epoch": 14.397408207343412, | |
| "grad_norm": 56.00436782836914, | |
| "learning_rate": 4.657904909161191e-06, | |
| "loss": 0.3288, | |
| "step": 1670 | |
| }, | |
| { | |
| "epoch": 14.483801295896328, | |
| "grad_norm": 25.29050636291504, | |
| "learning_rate": 4.619250096637032e-06, | |
| "loss": 0.3702, | |
| "step": 1680 | |
| }, | |
| { | |
| "epoch": 14.570194384449245, | |
| "grad_norm": 56.083961486816406, | |
| "learning_rate": 4.580595284112872e-06, | |
| "loss": 0.3286, | |
| "step": 1690 | |
| }, | |
| { | |
| "epoch": 14.65658747300216, | |
| "grad_norm": 75.87052154541016, | |
| "learning_rate": 4.541940471588713e-06, | |
| "loss": 0.4873, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 14.742980561555076, | |
| "grad_norm": 44.087547302246094, | |
| "learning_rate": 4.503285659064554e-06, | |
| "loss": 0.2683, | |
| "step": 1710 | |
| }, | |
| { | |
| "epoch": 14.829373650107991, | |
| "grad_norm": 22.894262313842773, | |
| "learning_rate": 4.464630846540395e-06, | |
| "loss": 0.3559, | |
| "step": 1720 | |
| }, | |
| { | |
| "epoch": 14.915766738660906, | |
| "grad_norm": 52.25741195678711, | |
| "learning_rate": 4.425976034016236e-06, | |
| "loss": 0.3136, | |
| "step": 1730 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "grad_norm": 29.12067222595215, | |
| "learning_rate": 4.387321221492076e-06, | |
| "loss": 0.5044, | |
| "step": 1740 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "eval_loss": 0.638742983341217, | |
| "eval_macro_f1": 0.8443575406474457, | |
| "eval_runtime": 17.2989, | |
| "eval_samples_per_second": 53.53, | |
| "eval_steps_per_second": 6.706, | |
| "step": 1740 | |
| }, | |
| { | |
| "epoch": 15.086393088552915, | |
| "grad_norm": 47.597984313964844, | |
| "learning_rate": 4.348666408967917e-06, | |
| "loss": 0.4503, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 15.17278617710583, | |
| "grad_norm": 13.964532852172852, | |
| "learning_rate": 4.3100115964437575e-06, | |
| "loss": 0.2143, | |
| "step": 1760 | |
| }, | |
| { | |
| "epoch": 15.259179265658748, | |
| "grad_norm": 82.6571273803711, | |
| "learning_rate": 4.271356783919598e-06, | |
| "loss": 0.5836, | |
| "step": 1770 | |
| }, | |
| { | |
| "epoch": 15.345572354211663, | |
| "grad_norm": 38.710899353027344, | |
| "learning_rate": 4.23270197139544e-06, | |
| "loss": 0.2878, | |
| "step": 1780 | |
| }, | |
| { | |
| "epoch": 15.431965442764579, | |
| "grad_norm": 60.6817626953125, | |
| "learning_rate": 4.19404715887128e-06, | |
| "loss": 0.4409, | |
| "step": 1790 | |
| }, | |
| { | |
| "epoch": 15.518358531317494, | |
| "grad_norm": 43.522804260253906, | |
| "learning_rate": 4.155392346347121e-06, | |
| "loss": 0.7443, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 15.60475161987041, | |
| "grad_norm": 39.97816848754883, | |
| "learning_rate": 4.1167375338229615e-06, | |
| "loss": 0.3902, | |
| "step": 1810 | |
| }, | |
| { | |
| "epoch": 15.691144708423327, | |
| "grad_norm": 4.281501293182373, | |
| "learning_rate": 4.078082721298802e-06, | |
| "loss": 0.2109, | |
| "step": 1820 | |
| }, | |
| { | |
| "epoch": 15.777537796976242, | |
| "grad_norm": 53.80859375, | |
| "learning_rate": 4.039427908774643e-06, | |
| "loss": 0.427, | |
| "step": 1830 | |
| }, | |
| { | |
| "epoch": 15.863930885529157, | |
| "grad_norm": 43.7281494140625, | |
| "learning_rate": 4.0007730962504834e-06, | |
| "loss": 0.4247, | |
| "step": 1840 | |
| }, | |
| { | |
| "epoch": 15.950323974082073, | |
| "grad_norm": 62.55876541137695, | |
| "learning_rate": 3.962118283726324e-06, | |
| "loss": 0.5326, | |
| "step": 1850 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_loss": 0.5283326506614685, | |
| "eval_macro_f1": 0.8416865323027283, | |
| "eval_runtime": 17.0638, | |
| "eval_samples_per_second": 54.267, | |
| "eval_steps_per_second": 6.798, | |
| "step": 1856 | |
| }, | |
| { | |
| "epoch": 16.034557235421165, | |
| "grad_norm": 24.753618240356445, | |
| "learning_rate": 3.9234634712021655e-06, | |
| "loss": 0.2712, | |
| "step": 1860 | |
| }, | |
| { | |
| "epoch": 16.120950323974082, | |
| "grad_norm": 81.78247833251953, | |
| "learning_rate": 3.884808658678006e-06, | |
| "loss": 0.372, | |
| "step": 1870 | |
| }, | |
| { | |
| "epoch": 16.207343412527, | |
| "grad_norm": 43.68366241455078, | |
| "learning_rate": 3.846153846153847e-06, | |
| "loss": 0.3139, | |
| "step": 1880 | |
| }, | |
| { | |
| "epoch": 16.293736501079913, | |
| "grad_norm": 83.01486206054688, | |
| "learning_rate": 3.8074990336296874e-06, | |
| "loss": 0.3837, | |
| "step": 1890 | |
| }, | |
| { | |
| "epoch": 16.38012958963283, | |
| "grad_norm": 14.622414588928223, | |
| "learning_rate": 3.768844221105528e-06, | |
| "loss": 0.2072, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 16.466522678185743, | |
| "grad_norm": 53.248390197753906, | |
| "learning_rate": 3.730189408581369e-06, | |
| "loss": 0.3522, | |
| "step": 1910 | |
| }, | |
| { | |
| "epoch": 16.55291576673866, | |
| "grad_norm": 53.421539306640625, | |
| "learning_rate": 3.6915345960572097e-06, | |
| "loss": 0.2473, | |
| "step": 1920 | |
| }, | |
| { | |
| "epoch": 16.639308855291578, | |
| "grad_norm": 53.37113571166992, | |
| "learning_rate": 3.6528797835330504e-06, | |
| "loss": 0.6206, | |
| "step": 1930 | |
| }, | |
| { | |
| "epoch": 16.72570194384449, | |
| "grad_norm": 152.26011657714844, | |
| "learning_rate": 3.614224971008891e-06, | |
| "loss": 0.4216, | |
| "step": 1940 | |
| }, | |
| { | |
| "epoch": 16.81209503239741, | |
| "grad_norm": 25.104888916015625, | |
| "learning_rate": 3.575570158484732e-06, | |
| "loss": 0.333, | |
| "step": 1950 | |
| }, | |
| { | |
| "epoch": 16.898488120950326, | |
| "grad_norm": 50.0928955078125, | |
| "learning_rate": 3.5369153459605727e-06, | |
| "loss": 0.3633, | |
| "step": 1960 | |
| }, | |
| { | |
| "epoch": 16.98488120950324, | |
| "grad_norm": 4.997694969177246, | |
| "learning_rate": 3.4982605334364133e-06, | |
| "loss": 0.3026, | |
| "step": 1970 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "eval_loss": 0.4961493909358978, | |
| "eval_macro_f1": 0.8517054282094797, | |
| "eval_runtime": 16.6125, | |
| "eval_samples_per_second": 55.741, | |
| "eval_steps_per_second": 6.983, | |
| "step": 1972 | |
| }, | |
| { | |
| "epoch": 17.069114470842333, | |
| "grad_norm": 19.699106216430664, | |
| "learning_rate": 3.459605720912254e-06, | |
| "loss": 0.1953, | |
| "step": 1980 | |
| }, | |
| { | |
| "epoch": 17.155507559395247, | |
| "grad_norm": 39.93479919433594, | |
| "learning_rate": 3.420950908388095e-06, | |
| "loss": 0.3818, | |
| "step": 1990 | |
| }, | |
| { | |
| "epoch": 17.241900647948164, | |
| "grad_norm": 31.303096771240234, | |
| "learning_rate": 3.3822960958639356e-06, | |
| "loss": 0.281, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 17.32829373650108, | |
| "grad_norm": 15.34146785736084, | |
| "learning_rate": 3.3436412833397762e-06, | |
| "loss": 0.4427, | |
| "step": 2010 | |
| }, | |
| { | |
| "epoch": 17.414686825053995, | |
| "grad_norm": 69.86293029785156, | |
| "learning_rate": 3.304986470815617e-06, | |
| "loss": 0.2839, | |
| "step": 2020 | |
| }, | |
| { | |
| "epoch": 17.50107991360691, | |
| "grad_norm": 6.422046661376953, | |
| "learning_rate": 3.266331658291458e-06, | |
| "loss": 0.3117, | |
| "step": 2030 | |
| }, | |
| { | |
| "epoch": 17.58747300215983, | |
| "grad_norm": 88.27076721191406, | |
| "learning_rate": 3.2276768457672986e-06, | |
| "loss": 0.2722, | |
| "step": 2040 | |
| }, | |
| { | |
| "epoch": 17.673866090712743, | |
| "grad_norm": 26.126628875732422, | |
| "learning_rate": 3.189022033243139e-06, | |
| "loss": 0.375, | |
| "step": 2050 | |
| }, | |
| { | |
| "epoch": 17.76025917926566, | |
| "grad_norm": 22.49889373779297, | |
| "learning_rate": 3.1503672207189802e-06, | |
| "loss": 0.4536, | |
| "step": 2060 | |
| }, | |
| { | |
| "epoch": 17.846652267818573, | |
| "grad_norm": 137.3453826904297, | |
| "learning_rate": 3.11171240819482e-06, | |
| "loss": 0.591, | |
| "step": 2070 | |
| }, | |
| { | |
| "epoch": 17.93304535637149, | |
| "grad_norm": 18.906539916992188, | |
| "learning_rate": 3.073057595670661e-06, | |
| "loss": 0.4155, | |
| "step": 2080 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "eval_loss": 0.546431303024292, | |
| "eval_macro_f1": 0.8590125396622391, | |
| "eval_runtime": 17.1502, | |
| "eval_samples_per_second": 53.993, | |
| "eval_steps_per_second": 6.764, | |
| "step": 2088 | |
| }, | |
| { | |
| "epoch": 18.017278617710584, | |
| "grad_norm": 20.98369789123535, | |
| "learning_rate": 3.0344027831465017e-06, | |
| "loss": 0.3026, | |
| "step": 2090 | |
| }, | |
| { | |
| "epoch": 18.103671706263498, | |
| "grad_norm": 27.89241600036621, | |
| "learning_rate": 2.9957479706223423e-06, | |
| "loss": 0.2171, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 18.190064794816415, | |
| "grad_norm": 61.913612365722656, | |
| "learning_rate": 2.9570931580981834e-06, | |
| "loss": 0.4255, | |
| "step": 2110 | |
| }, | |
| { | |
| "epoch": 18.276457883369332, | |
| "grad_norm": 917.5242309570312, | |
| "learning_rate": 2.918438345574024e-06, | |
| "loss": 0.1092, | |
| "step": 2120 | |
| }, | |
| { | |
| "epoch": 18.362850971922246, | |
| "grad_norm": 18.6544189453125, | |
| "learning_rate": 2.8797835330498646e-06, | |
| "loss": 0.3306, | |
| "step": 2130 | |
| }, | |
| { | |
| "epoch": 18.449244060475163, | |
| "grad_norm": 13.983207702636719, | |
| "learning_rate": 2.8411287205257053e-06, | |
| "loss": 0.3184, | |
| "step": 2140 | |
| }, | |
| { | |
| "epoch": 18.535637149028076, | |
| "grad_norm": 19.48896026611328, | |
| "learning_rate": 2.8024739080015463e-06, | |
| "loss": 0.1137, | |
| "step": 2150 | |
| }, | |
| { | |
| "epoch": 18.622030237580994, | |
| "grad_norm": 56.50817108154297, | |
| "learning_rate": 2.763819095477387e-06, | |
| "loss": 0.3258, | |
| "step": 2160 | |
| }, | |
| { | |
| "epoch": 18.70842332613391, | |
| "grad_norm": 54.56320571899414, | |
| "learning_rate": 2.7251642829532276e-06, | |
| "loss": 0.2, | |
| "step": 2170 | |
| }, | |
| { | |
| "epoch": 18.794816414686824, | |
| "grad_norm": 129.62660217285156, | |
| "learning_rate": 2.6865094704290682e-06, | |
| "loss": 0.3135, | |
| "step": 2180 | |
| }, | |
| { | |
| "epoch": 18.88120950323974, | |
| "grad_norm": 107.59940338134766, | |
| "learning_rate": 2.6478546579049093e-06, | |
| "loss": 0.3521, | |
| "step": 2190 | |
| }, | |
| { | |
| "epoch": 18.967602591792655, | |
| "grad_norm": 148.64234924316406, | |
| "learning_rate": 2.60919984538075e-06, | |
| "loss": 0.2763, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "eval_loss": 0.5828408598899841, | |
| "eval_macro_f1": 0.8685469279334771, | |
| "eval_runtime": 17.8662, | |
| "eval_samples_per_second": 51.83, | |
| "eval_steps_per_second": 6.493, | |
| "step": 2204 | |
| }, | |
| { | |
| "epoch": 19.05183585313175, | |
| "grad_norm": 104.04680633544922, | |
| "learning_rate": 2.5705450328565905e-06, | |
| "loss": 0.4048, | |
| "step": 2210 | |
| }, | |
| { | |
| "epoch": 19.138228941684666, | |
| "grad_norm": 123.32837677001953, | |
| "learning_rate": 2.5318902203324316e-06, | |
| "loss": 0.5209, | |
| "step": 2220 | |
| }, | |
| { | |
| "epoch": 19.22462203023758, | |
| "grad_norm": 46.73143005371094, | |
| "learning_rate": 2.493235407808272e-06, | |
| "loss": 0.5217, | |
| "step": 2230 | |
| }, | |
| { | |
| "epoch": 19.311015118790497, | |
| "grad_norm": 8.207721710205078, | |
| "learning_rate": 2.4545805952841133e-06, | |
| "loss": 0.3255, | |
| "step": 2240 | |
| }, | |
| { | |
| "epoch": 19.397408207343414, | |
| "grad_norm": 63.93031311035156, | |
| "learning_rate": 2.415925782759954e-06, | |
| "loss": 0.2312, | |
| "step": 2250 | |
| }, | |
| { | |
| "epoch": 19.483801295896328, | |
| "grad_norm": 43.651065826416016, | |
| "learning_rate": 2.3772709702357945e-06, | |
| "loss": 0.2947, | |
| "step": 2260 | |
| }, | |
| { | |
| "epoch": 19.570194384449245, | |
| "grad_norm": 5.546581745147705, | |
| "learning_rate": 2.338616157711635e-06, | |
| "loss": 0.2463, | |
| "step": 2270 | |
| }, | |
| { | |
| "epoch": 19.65658747300216, | |
| "grad_norm": 63.26512145996094, | |
| "learning_rate": 2.299961345187476e-06, | |
| "loss": 0.4906, | |
| "step": 2280 | |
| }, | |
| { | |
| "epoch": 19.742980561555076, | |
| "grad_norm": 27.615131378173828, | |
| "learning_rate": 2.261306532663317e-06, | |
| "loss": 0.3544, | |
| "step": 2290 | |
| }, | |
| { | |
| "epoch": 19.829373650107993, | |
| "grad_norm": 42.514869689941406, | |
| "learning_rate": 2.2226517201391575e-06, | |
| "loss": 0.2251, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 19.915766738660906, | |
| "grad_norm": 47.34213638305664, | |
| "learning_rate": 2.1839969076149985e-06, | |
| "loss": 0.222, | |
| "step": 2310 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "grad_norm": 103.04148864746094, | |
| "learning_rate": 2.145342095090839e-06, | |
| "loss": 0.1733, | |
| "step": 2320 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_loss": 0.6083136200904846, | |
| "eval_macro_f1": 0.8617720910645434, | |
| "eval_runtime": 16.82, | |
| "eval_samples_per_second": 55.054, | |
| "eval_steps_per_second": 6.897, | |
| "step": 2320 | |
| }, | |
| { | |
| "epoch": 20.086393088552917, | |
| "grad_norm": 11.250152587890625, | |
| "learning_rate": 2.1066872825666798e-06, | |
| "loss": 0.2448, | |
| "step": 2330 | |
| }, | |
| { | |
| "epoch": 20.17278617710583, | |
| "grad_norm": 128.7437744140625, | |
| "learning_rate": 2.0680324700425204e-06, | |
| "loss": 0.2663, | |
| "step": 2340 | |
| }, | |
| { | |
| "epoch": 20.259179265658748, | |
| "grad_norm": 47.49317932128906, | |
| "learning_rate": 2.0293776575183615e-06, | |
| "loss": 0.2796, | |
| "step": 2350 | |
| }, | |
| { | |
| "epoch": 20.34557235421166, | |
| "grad_norm": 49.71406555175781, | |
| "learning_rate": 1.990722844994202e-06, | |
| "loss": 0.3162, | |
| "step": 2360 | |
| }, | |
| { | |
| "epoch": 20.43196544276458, | |
| "grad_norm": 72.845458984375, | |
| "learning_rate": 1.9520680324700427e-06, | |
| "loss": 0.3388, | |
| "step": 2370 | |
| }, | |
| { | |
| "epoch": 20.518358531317496, | |
| "grad_norm": 45.771018981933594, | |
| "learning_rate": 1.9134132199458833e-06, | |
| "loss": 0.3733, | |
| "step": 2380 | |
| }, | |
| { | |
| "epoch": 20.60475161987041, | |
| "grad_norm": 15.408432960510254, | |
| "learning_rate": 1.8747584074217242e-06, | |
| "loss": 0.3589, | |
| "step": 2390 | |
| }, | |
| { | |
| "epoch": 20.691144708423327, | |
| "grad_norm": 53.17451095581055, | |
| "learning_rate": 1.836103594897565e-06, | |
| "loss": 0.2963, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 20.77753779697624, | |
| "grad_norm": 118.89311218261719, | |
| "learning_rate": 1.7974487823734057e-06, | |
| "loss": 0.2782, | |
| "step": 2410 | |
| }, | |
| { | |
| "epoch": 20.863930885529157, | |
| "grad_norm": 42.53224182128906, | |
| "learning_rate": 1.7587939698492465e-06, | |
| "loss": 0.2777, | |
| "step": 2420 | |
| }, | |
| { | |
| "epoch": 20.950323974082075, | |
| "grad_norm": 453.1598205566406, | |
| "learning_rate": 1.7201391573250873e-06, | |
| "loss": 0.4015, | |
| "step": 2430 | |
| }, | |
| { | |
| "epoch": 21.0, | |
| "eval_loss": 0.6018757820129395, | |
| "eval_macro_f1": 0.8631354430151588, | |
| "eval_runtime": 17.8334, | |
| "eval_samples_per_second": 51.925, | |
| "eval_steps_per_second": 6.505, | |
| "step": 2436 | |
| }, | |
| { | |
| "epoch": 21.034557235421165, | |
| "grad_norm": 1.9662721157073975, | |
| "learning_rate": 1.681484344800928e-06, | |
| "loss": 0.1209, | |
| "step": 2440 | |
| }, | |
| { | |
| "epoch": 21.120950323974082, | |
| "grad_norm": 42.46015167236328, | |
| "learning_rate": 1.6428295322767688e-06, | |
| "loss": 0.278, | |
| "step": 2450 | |
| }, | |
| { | |
| "epoch": 21.207343412527, | |
| "grad_norm": 9.549817085266113, | |
| "learning_rate": 1.6041747197526094e-06, | |
| "loss": 0.1866, | |
| "step": 2460 | |
| }, | |
| { | |
| "epoch": 21.293736501079913, | |
| "grad_norm": 3.735248565673828, | |
| "learning_rate": 1.5655199072284503e-06, | |
| "loss": 0.1963, | |
| "step": 2470 | |
| }, | |
| { | |
| "epoch": 21.38012958963283, | |
| "grad_norm": 16.802431106567383, | |
| "learning_rate": 1.5268650947042907e-06, | |
| "loss": 0.2157, | |
| "step": 2480 | |
| }, | |
| { | |
| "epoch": 21.466522678185743, | |
| "grad_norm": 19.582170486450195, | |
| "learning_rate": 1.4882102821801313e-06, | |
| "loss": 0.3382, | |
| "step": 2490 | |
| }, | |
| { | |
| "epoch": 21.55291576673866, | |
| "grad_norm": 0.9627342820167542, | |
| "learning_rate": 1.4495554696559722e-06, | |
| "loss": 0.307, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 21.639308855291578, | |
| "grad_norm": 41.96005630493164, | |
| "learning_rate": 1.410900657131813e-06, | |
| "loss": 0.2993, | |
| "step": 2510 | |
| }, | |
| { | |
| "epoch": 21.72570194384449, | |
| "grad_norm": 81.29263305664062, | |
| "learning_rate": 1.3722458446076536e-06, | |
| "loss": 0.3624, | |
| "step": 2520 | |
| }, | |
| { | |
| "epoch": 21.81209503239741, | |
| "grad_norm": 1.3688504695892334, | |
| "learning_rate": 1.3335910320834945e-06, | |
| "loss": 0.1005, | |
| "step": 2530 | |
| }, | |
| { | |
| "epoch": 21.898488120950326, | |
| "grad_norm": 51.99349594116211, | |
| "learning_rate": 1.2949362195593351e-06, | |
| "loss": 0.3422, | |
| "step": 2540 | |
| }, | |
| { | |
| "epoch": 21.98488120950324, | |
| "grad_norm": 10.257471084594727, | |
| "learning_rate": 1.256281407035176e-06, | |
| "loss": 0.2649, | |
| "step": 2550 | |
| }, | |
| { | |
| "epoch": 22.0, | |
| "eval_loss": 0.6120893955230713, | |
| "eval_macro_f1": 0.8630768559502398, | |
| "eval_runtime": 17.5342, | |
| "eval_samples_per_second": 52.811, | |
| "eval_steps_per_second": 6.616, | |
| "step": 2552 | |
| }, | |
| { | |
| "epoch": 22.069114470842333, | |
| "grad_norm": 31.507051467895508, | |
| "learning_rate": 1.2176265945110168e-06, | |
| "loss": 0.268, | |
| "step": 2560 | |
| }, | |
| { | |
| "epoch": 22.155507559395247, | |
| "grad_norm": 91.0459976196289, | |
| "learning_rate": 1.1789717819868574e-06, | |
| "loss": 0.3532, | |
| "step": 2570 | |
| }, | |
| { | |
| "epoch": 22.241900647948164, | |
| "grad_norm": 47.774391174316406, | |
| "learning_rate": 1.1403169694626983e-06, | |
| "loss": 0.2976, | |
| "step": 2580 | |
| }, | |
| { | |
| "epoch": 22.32829373650108, | |
| "grad_norm": 49.88670349121094, | |
| "learning_rate": 1.1016621569385389e-06, | |
| "loss": 0.065, | |
| "step": 2590 | |
| }, | |
| { | |
| "epoch": 22.414686825053995, | |
| "grad_norm": 187.57847595214844, | |
| "learning_rate": 1.0630073444143797e-06, | |
| "loss": 0.3762, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 22.50107991360691, | |
| "grad_norm": 281.0491638183594, | |
| "learning_rate": 1.0243525318902204e-06, | |
| "loss": 0.2553, | |
| "step": 2610 | |
| }, | |
| { | |
| "epoch": 22.58747300215983, | |
| "grad_norm": 8.582008361816406, | |
| "learning_rate": 9.856977193660612e-07, | |
| "loss": 0.2701, | |
| "step": 2620 | |
| }, | |
| { | |
| "epoch": 22.673866090712743, | |
| "grad_norm": 40.54225540161133, | |
| "learning_rate": 9.470429068419019e-07, | |
| "loss": 0.2672, | |
| "step": 2630 | |
| }, | |
| { | |
| "epoch": 22.76025917926566, | |
| "grad_norm": 45.52231216430664, | |
| "learning_rate": 9.083880943177427e-07, | |
| "loss": 0.3036, | |
| "step": 2640 | |
| }, | |
| { | |
| "epoch": 22.846652267818573, | |
| "grad_norm": 108.5732421875, | |
| "learning_rate": 8.697332817935834e-07, | |
| "loss": 0.3182, | |
| "step": 2650 | |
| }, | |
| { | |
| "epoch": 22.93304535637149, | |
| "grad_norm": 29.52652931213379, | |
| "learning_rate": 8.310784692694241e-07, | |
| "loss": 0.1196, | |
| "step": 2660 | |
| }, | |
| { | |
| "epoch": 23.0, | |
| "eval_loss": 0.6888664960861206, | |
| "eval_macro_f1": 0.8538403632743256, | |
| "eval_runtime": 17.2141, | |
| "eval_samples_per_second": 53.793, | |
| "eval_steps_per_second": 6.739, | |
| "step": 2668 | |
| }, | |
| { | |
| "epoch": 23.017278617710584, | |
| "grad_norm": 68.86863708496094, | |
| "learning_rate": 7.924236567452649e-07, | |
| "loss": 0.2634, | |
| "step": 2670 | |
| }, | |
| { | |
| "epoch": 23.103671706263498, | |
| "grad_norm": 58.899391174316406, | |
| "learning_rate": 7.537688442211055e-07, | |
| "loss": 0.3309, | |
| "step": 2680 | |
| }, | |
| { | |
| "epoch": 23.190064794816415, | |
| "grad_norm": 71.05393981933594, | |
| "learning_rate": 7.151140316969462e-07, | |
| "loss": 0.2153, | |
| "step": 2690 | |
| }, | |
| { | |
| "epoch": 23.276457883369332, | |
| "grad_norm": 2.041644334793091, | |
| "learning_rate": 6.76459219172787e-07, | |
| "loss": 0.3616, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 23.362850971922246, | |
| "grad_norm": 82.25381469726562, | |
| "learning_rate": 6.378044066486277e-07, | |
| "loss": 0.2538, | |
| "step": 2710 | |
| }, | |
| { | |
| "epoch": 23.449244060475163, | |
| "grad_norm": 8.824419021606445, | |
| "learning_rate": 5.991495941244686e-07, | |
| "loss": 0.0927, | |
| "step": 2720 | |
| }, | |
| { | |
| "epoch": 23.535637149028076, | |
| "grad_norm": 17.117977142333984, | |
| "learning_rate": 5.604947816003093e-07, | |
| "loss": 0.1538, | |
| "step": 2730 | |
| }, | |
| { | |
| "epoch": 23.622030237580994, | |
| "grad_norm": 1.6735382080078125, | |
| "learning_rate": 5.2183996907615e-07, | |
| "loss": 0.1548, | |
| "step": 2740 | |
| }, | |
| { | |
| "epoch": 23.70842332613391, | |
| "grad_norm": 6.845789432525635, | |
| "learning_rate": 4.831851565519908e-07, | |
| "loss": 0.1832, | |
| "step": 2750 | |
| }, | |
| { | |
| "epoch": 23.794816414686824, | |
| "grad_norm": 19.85407066345215, | |
| "learning_rate": 4.4453034402783155e-07, | |
| "loss": 0.2808, | |
| "step": 2760 | |
| }, | |
| { | |
| "epoch": 23.88120950323974, | |
| "grad_norm": 5.298573017120361, | |
| "learning_rate": 4.058755315036723e-07, | |
| "loss": 0.2098, | |
| "step": 2770 | |
| }, | |
| { | |
| "epoch": 23.967602591792655, | |
| "grad_norm": 0.8520543575286865, | |
| "learning_rate": 3.6722071897951296e-07, | |
| "loss": 0.0521, | |
| "step": 2780 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "eval_loss": 0.6725981831550598, | |
| "eval_macro_f1": 0.8610719903206292, | |
| "eval_runtime": 16.9666, | |
| "eval_samples_per_second": 54.578, | |
| "eval_steps_per_second": 6.837, | |
| "step": 2784 | |
| }, | |
| { | |
| "epoch": 24.05183585313175, | |
| "grad_norm": 1.0969666242599487, | |
| "learning_rate": 3.285659064553537e-07, | |
| "loss": 0.1449, | |
| "step": 2790 | |
| }, | |
| { | |
| "epoch": 24.138228941684666, | |
| "grad_norm": 4.448155403137207, | |
| "learning_rate": 2.899110939311945e-07, | |
| "loss": 0.1756, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 24.22462203023758, | |
| "grad_norm": 2.900632381439209, | |
| "learning_rate": 2.512562814070352e-07, | |
| "loss": 0.1385, | |
| "step": 2810 | |
| }, | |
| { | |
| "epoch": 24.311015118790497, | |
| "grad_norm": 24.39512062072754, | |
| "learning_rate": 2.1260146888287596e-07, | |
| "loss": 0.2804, | |
| "step": 2820 | |
| }, | |
| { | |
| "epoch": 24.397408207343414, | |
| "grad_norm": 0.170551598072052, | |
| "learning_rate": 1.7394665635871667e-07, | |
| "loss": 0.3555, | |
| "step": 2830 | |
| }, | |
| { | |
| "epoch": 24.483801295896328, | |
| "grad_norm": 0.42594221234321594, | |
| "learning_rate": 1.3529184383455743e-07, | |
| "loss": 0.1433, | |
| "step": 2840 | |
| }, | |
| { | |
| "epoch": 24.570194384449245, | |
| "grad_norm": 26.60655975341797, | |
| "learning_rate": 9.663703131039815e-08, | |
| "loss": 0.3081, | |
| "step": 2850 | |
| }, | |
| { | |
| "epoch": 24.65658747300216, | |
| "grad_norm": 113.71473693847656, | |
| "learning_rate": 5.79822187862389e-08, | |
| "loss": 0.4043, | |
| "step": 2860 | |
| }, | |
| { | |
| "epoch": 24.742980561555076, | |
| "grad_norm": 34.953372955322266, | |
| "learning_rate": 1.9327406262079632e-08, | |
| "loss": 0.1929, | |
| "step": 2870 | |
| }, | |
| { | |
| "epoch": 24.786177105831534, | |
| "eval_loss": 0.6091281175613403, | |
| "eval_macro_f1": 0.8691893001382458, | |
| "eval_runtime": 16.5742, | |
| "eval_samples_per_second": 55.87, | |
| "eval_steps_per_second": 6.999, | |
| "step": 2875 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 2875, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 25, | |
| "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": 3.2955292249139184e+19, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |