| { | |
| "best_metric": 0.90210919178688, | |
| "best_model_checkpoint": "videomae-surf-analytics-runpod4/checkpoint-2697", | |
| "epoch": 29.02282608695652, | |
| "eval_steps": 500, | |
| "global_step": 2760, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0036231884057971015, | |
| "grad_norm": 9.726770401000977, | |
| "learning_rate": 1.8115942028985508e-06, | |
| "loss": 1.3861, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.007246376811594203, | |
| "grad_norm": 8.901580810546875, | |
| "learning_rate": 3.6231884057971017e-06, | |
| "loss": 1.3917, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.010869565217391304, | |
| "grad_norm": 5.0848612785339355, | |
| "learning_rate": 5.4347826086956525e-06, | |
| "loss": 1.3179, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.014492753623188406, | |
| "grad_norm": 8.99917221069336, | |
| "learning_rate": 7.246376811594203e-06, | |
| "loss": 1.2512, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.018115942028985508, | |
| "grad_norm": 11.607219696044922, | |
| "learning_rate": 9.057971014492753e-06, | |
| "loss": 1.2267, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.021739130434782608, | |
| "grad_norm": 6.150553226470947, | |
| "learning_rate": 1.0869565217391305e-05, | |
| "loss": 1.2952, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.025362318840579712, | |
| "grad_norm": 7.3294358253479, | |
| "learning_rate": 1.2681159420289857e-05, | |
| "loss": 1.0431, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.028985507246376812, | |
| "grad_norm": 4.637725830078125, | |
| "learning_rate": 1.4492753623188407e-05, | |
| "loss": 1.2039, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.03260869565217391, | |
| "grad_norm": 7.160071849822998, | |
| "learning_rate": 1.630434782608696e-05, | |
| "loss": 1.2463, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.03369565217391304, | |
| "eval_accuracy": 0.4344262295081967, | |
| "eval_f1": 0.29487747520534413, | |
| "eval_loss": 1.2388594150543213, | |
| "eval_runtime": 42.3507, | |
| "eval_samples_per_second": 2.881, | |
| "eval_steps_per_second": 0.378, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 1.002536231884058, | |
| "grad_norm": 4.499807834625244, | |
| "learning_rate": 1.8115942028985507e-05, | |
| "loss": 1.1553, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.0061594202898552, | |
| "grad_norm": 5.520775318145752, | |
| "learning_rate": 1.992753623188406e-05, | |
| "loss": 1.1873, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 1.0097826086956523, | |
| "grad_norm": 7.460188388824463, | |
| "learning_rate": 2.173913043478261e-05, | |
| "loss": 1.0111, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 1.0134057971014492, | |
| "grad_norm": 7.1730875968933105, | |
| "learning_rate": 2.355072463768116e-05, | |
| "loss": 1.0118, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 1.0170289855072463, | |
| "grad_norm": 6.370150566101074, | |
| "learning_rate": 2.5362318840579714e-05, | |
| "loss": 0.9757, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 1.0206521739130434, | |
| "grad_norm": 12.998475074768066, | |
| "learning_rate": 2.7173913043478262e-05, | |
| "loss": 0.9456, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 1.0242753623188405, | |
| "grad_norm": 19.65399169921875, | |
| "learning_rate": 2.8985507246376814e-05, | |
| "loss": 1.0014, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 1.0278985507246376, | |
| "grad_norm": 11.76526927947998, | |
| "learning_rate": 3.079710144927536e-05, | |
| "loss": 1.0805, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 1.0315217391304348, | |
| "grad_norm": 8.409660339355469, | |
| "learning_rate": 3.260869565217392e-05, | |
| "loss": 1.024, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 1.0336956521739131, | |
| "eval_accuracy": 0.5491803278688525, | |
| "eval_f1": 0.5254458656098001, | |
| "eval_loss": 1.0342785120010376, | |
| "eval_runtime": 42.2598, | |
| "eval_samples_per_second": 2.887, | |
| "eval_steps_per_second": 0.379, | |
| "step": 186 | |
| }, | |
| { | |
| "epoch": 2.0014492753623188, | |
| "grad_norm": 8.813424110412598, | |
| "learning_rate": 3.4420289855072465e-05, | |
| "loss": 0.9424, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 2.005072463768116, | |
| "grad_norm": 18.248958587646484, | |
| "learning_rate": 3.6231884057971014e-05, | |
| "loss": 0.8009, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 2.008695652173913, | |
| "grad_norm": 9.742342948913574, | |
| "learning_rate": 3.804347826086957e-05, | |
| "loss": 0.6643, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 2.0123188405797103, | |
| "grad_norm": 10.787181854248047, | |
| "learning_rate": 3.985507246376812e-05, | |
| "loss": 1.0492, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 2.0159420289855072, | |
| "grad_norm": 10.376043319702148, | |
| "learning_rate": 4.166666666666667e-05, | |
| "loss": 0.6274, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 2.0195652173913046, | |
| "grad_norm": 8.305957794189453, | |
| "learning_rate": 4.347826086956522e-05, | |
| "loss": 0.7027, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 2.0231884057971015, | |
| "grad_norm": 13.777029991149902, | |
| "learning_rate": 4.528985507246377e-05, | |
| "loss": 0.6191, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 2.0268115942028984, | |
| "grad_norm": 10.486043930053711, | |
| "learning_rate": 4.710144927536232e-05, | |
| "loss": 0.8711, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 2.0304347826086957, | |
| "grad_norm": 5.285229682922363, | |
| "learning_rate": 4.891304347826087e-05, | |
| "loss": 0.6932, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 2.033695652173913, | |
| "eval_accuracy": 0.6639344262295082, | |
| "eval_f1": 0.6359864440646367, | |
| "eval_loss": 0.8279891610145569, | |
| "eval_runtime": 36.4539, | |
| "eval_samples_per_second": 3.347, | |
| "eval_steps_per_second": 0.439, | |
| "step": 279 | |
| }, | |
| { | |
| "epoch": 3.0003623188405797, | |
| "grad_norm": 7.227272033691406, | |
| "learning_rate": 4.99194847020934e-05, | |
| "loss": 0.8223, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 3.003985507246377, | |
| "grad_norm": 6.091291427612305, | |
| "learning_rate": 4.9718196457326895e-05, | |
| "loss": 0.7407, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 3.007608695652174, | |
| "grad_norm": 12.283949851989746, | |
| "learning_rate": 4.9516908212560386e-05, | |
| "loss": 0.5408, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 3.011231884057971, | |
| "grad_norm": 12.24530029296875, | |
| "learning_rate": 4.9315619967793884e-05, | |
| "loss": 0.5201, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 3.014855072463768, | |
| "grad_norm": 13.709362983703613, | |
| "learning_rate": 4.911433172302738e-05, | |
| "loss": 0.5266, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 3.018478260869565, | |
| "grad_norm": 8.324898719787598, | |
| "learning_rate": 4.891304347826087e-05, | |
| "loss": 0.5397, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 3.0221014492753624, | |
| "grad_norm": 13.807954788208008, | |
| "learning_rate": 4.871175523349436e-05, | |
| "loss": 0.5297, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 3.0257246376811593, | |
| "grad_norm": 12.566025733947754, | |
| "learning_rate": 4.851046698872786e-05, | |
| "loss": 0.4034, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 3.0293478260869566, | |
| "grad_norm": 15.83183479309082, | |
| "learning_rate": 4.830917874396135e-05, | |
| "loss": 0.4654, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 3.0329710144927535, | |
| "grad_norm": 1.7397154569625854, | |
| "learning_rate": 4.810789049919485e-05, | |
| "loss": 0.4467, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 3.033695652173913, | |
| "eval_accuracy": 0.7459016393442623, | |
| "eval_f1": 0.7338377280393545, | |
| "eval_loss": 0.7664637565612793, | |
| "eval_runtime": 36.3739, | |
| "eval_samples_per_second": 3.354, | |
| "eval_steps_per_second": 0.44, | |
| "step": 372 | |
| }, | |
| { | |
| "epoch": 4.0028985507246375, | |
| "grad_norm": 2.2322423458099365, | |
| "learning_rate": 4.790660225442835e-05, | |
| "loss": 0.3515, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 4.006521739130434, | |
| "grad_norm": 17.386234283447266, | |
| "learning_rate": 4.770531400966184e-05, | |
| "loss": 0.2997, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 4.010144927536232, | |
| "grad_norm": 11.770244598388672, | |
| "learning_rate": 4.7504025764895335e-05, | |
| "loss": 0.2963, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 4.013768115942029, | |
| "grad_norm": 17.996971130371094, | |
| "learning_rate": 4.7302737520128826e-05, | |
| "loss": 0.2062, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 4.017391304347826, | |
| "grad_norm": 0.812595009803772, | |
| "learning_rate": 4.710144927536232e-05, | |
| "loss": 0.1948, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 4.021014492753623, | |
| "grad_norm": 9.69245433807373, | |
| "learning_rate": 4.6900161030595815e-05, | |
| "loss": 0.5129, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 4.024637681159421, | |
| "grad_norm": 9.770214080810547, | |
| "learning_rate": 4.669887278582931e-05, | |
| "loss": 0.3938, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 4.028260869565218, | |
| "grad_norm": 16.608795166015625, | |
| "learning_rate": 4.64975845410628e-05, | |
| "loss": 0.3251, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 4.0318840579710145, | |
| "grad_norm": 14.123062133789062, | |
| "learning_rate": 4.62962962962963e-05, | |
| "loss": 0.4449, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 4.033695652173913, | |
| "eval_accuracy": 0.7131147540983607, | |
| "eval_f1": 0.6741469908968126, | |
| "eval_loss": 0.871498703956604, | |
| "eval_runtime": 36.9705, | |
| "eval_samples_per_second": 3.3, | |
| "eval_steps_per_second": 0.433, | |
| "step": 465 | |
| }, | |
| { | |
| "epoch": 5.0018115942028984, | |
| "grad_norm": 6.473958969116211, | |
| "learning_rate": 4.609500805152979e-05, | |
| "loss": 0.1426, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 5.005434782608695, | |
| "grad_norm": 0.1059931218624115, | |
| "learning_rate": 4.589371980676328e-05, | |
| "loss": 0.1327, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 5.009057971014493, | |
| "grad_norm": 0.7832779884338379, | |
| "learning_rate": 4.569243156199678e-05, | |
| "loss": 0.1692, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 5.01268115942029, | |
| "grad_norm": 12.166410446166992, | |
| "learning_rate": 4.549114331723028e-05, | |
| "loss": 0.2135, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 5.016304347826087, | |
| "grad_norm": 4.051369667053223, | |
| "learning_rate": 4.528985507246377e-05, | |
| "loss": 0.2939, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 5.019927536231884, | |
| "grad_norm": 1.8354891538619995, | |
| "learning_rate": 4.5088566827697266e-05, | |
| "loss": 0.2449, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 5.023550724637682, | |
| "grad_norm": 0.3607825040817261, | |
| "learning_rate": 4.488727858293076e-05, | |
| "loss": 0.0841, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 5.0271739130434785, | |
| "grad_norm": 7.8428239822387695, | |
| "learning_rate": 4.4685990338164255e-05, | |
| "loss": 0.4005, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 5.030797101449275, | |
| "grad_norm": 0.2001497596502304, | |
| "learning_rate": 4.4484702093397746e-05, | |
| "loss": 0.1371, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 5.033695652173913, | |
| "eval_accuracy": 0.7295081967213115, | |
| "eval_f1": 0.7157775700184823, | |
| "eval_loss": 1.0560429096221924, | |
| "eval_runtime": 42.0495, | |
| "eval_samples_per_second": 2.901, | |
| "eval_steps_per_second": 0.381, | |
| "step": 558 | |
| }, | |
| { | |
| "epoch": 6.000724637681159, | |
| "grad_norm": 0.06493417173624039, | |
| "learning_rate": 4.428341384863124e-05, | |
| "loss": 0.2275, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 6.004347826086956, | |
| "grad_norm": 11.751331329345703, | |
| "learning_rate": 4.408212560386474e-05, | |
| "loss": 0.2252, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 6.007971014492754, | |
| "grad_norm": 19.441425323486328, | |
| "learning_rate": 4.388083735909823e-05, | |
| "loss": 0.2761, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 6.011594202898551, | |
| "grad_norm": 0.09549690037965775, | |
| "learning_rate": 4.367954911433172e-05, | |
| "loss": 0.2724, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 6.015217391304348, | |
| "grad_norm": 12.359782218933105, | |
| "learning_rate": 4.347826086956522e-05, | |
| "loss": 0.1888, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 6.018840579710145, | |
| "grad_norm": 20.348411560058594, | |
| "learning_rate": 4.327697262479871e-05, | |
| "loss": 0.4012, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 6.022463768115942, | |
| "grad_norm": 0.05766362324357033, | |
| "learning_rate": 4.307568438003221e-05, | |
| "loss": 0.1362, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 6.026086956521739, | |
| "grad_norm": 18.2602481842041, | |
| "learning_rate": 4.2874396135265707e-05, | |
| "loss": 0.1788, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 6.029710144927536, | |
| "grad_norm": 0.44831833243370056, | |
| "learning_rate": 4.26731078904992e-05, | |
| "loss": 0.1337, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 6.033333333333333, | |
| "grad_norm": 13.512539863586426, | |
| "learning_rate": 4.247181964573269e-05, | |
| "loss": 0.1789, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 6.033695652173913, | |
| "eval_accuracy": 0.7868852459016393, | |
| "eval_f1": 0.7876811278368901, | |
| "eval_loss": 0.8218082189559937, | |
| "eval_runtime": 41.3621, | |
| "eval_samples_per_second": 2.95, | |
| "eval_steps_per_second": 0.387, | |
| "step": 651 | |
| }, | |
| { | |
| "epoch": 7.003260869565217, | |
| "grad_norm": 0.31983035802841187, | |
| "learning_rate": 4.2270531400966186e-05, | |
| "loss": 0.1123, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 7.006884057971014, | |
| "grad_norm": 3.5525496006011963, | |
| "learning_rate": 4.206924315619968e-05, | |
| "loss": 0.1231, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 7.010507246376812, | |
| "grad_norm": 17.89982795715332, | |
| "learning_rate": 4.1867954911433174e-05, | |
| "loss": 0.1998, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 7.014130434782609, | |
| "grad_norm": 14.844808578491211, | |
| "learning_rate": 4.166666666666667e-05, | |
| "loss": 0.0988, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 7.017753623188406, | |
| "grad_norm": 1.0570082664489746, | |
| "learning_rate": 4.146537842190016e-05, | |
| "loss": 0.1069, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 7.021376811594203, | |
| "grad_norm": 58.255123138427734, | |
| "learning_rate": 4.126409017713366e-05, | |
| "loss": 0.2484, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 7.025, | |
| "grad_norm": 0.30179139971733093, | |
| "learning_rate": 4.106280193236715e-05, | |
| "loss": 0.0665, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 7.028623188405797, | |
| "grad_norm": 36.053836822509766, | |
| "learning_rate": 4.086151368760064e-05, | |
| "loss": 0.2122, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 7.032246376811594, | |
| "grad_norm": 0.23371699452400208, | |
| "learning_rate": 4.066022544283414e-05, | |
| "loss": 0.2125, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 7.033695652173913, | |
| "eval_accuracy": 0.7868852459016393, | |
| "eval_f1": 0.7812358925016187, | |
| "eval_loss": 0.7612058520317078, | |
| "eval_runtime": 38.7607, | |
| "eval_samples_per_second": 3.148, | |
| "eval_steps_per_second": 0.413, | |
| "step": 744 | |
| }, | |
| { | |
| "epoch": 8.002173913043478, | |
| "grad_norm": 0.2972787022590637, | |
| "learning_rate": 4.045893719806764e-05, | |
| "loss": 0.0607, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 8.005797101449275, | |
| "grad_norm": 0.18866966664791107, | |
| "learning_rate": 4.025764895330113e-05, | |
| "loss": 0.1634, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 8.009420289855072, | |
| "grad_norm": 0.39748045802116394, | |
| "learning_rate": 4.0056360708534626e-05, | |
| "loss": 0.0266, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 8.013043478260869, | |
| "grad_norm": 8.73737907409668, | |
| "learning_rate": 3.985507246376812e-05, | |
| "loss": 0.0885, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 8.016666666666667, | |
| "grad_norm": 0.15234462916851044, | |
| "learning_rate": 3.965378421900161e-05, | |
| "loss": 0.0031, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 8.020289855072464, | |
| "grad_norm": 12.640290260314941, | |
| "learning_rate": 3.9452495974235105e-05, | |
| "loss": 0.2264, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 8.023913043478261, | |
| "grad_norm": 0.857113778591156, | |
| "learning_rate": 3.92512077294686e-05, | |
| "loss": 0.2147, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 8.027536231884058, | |
| "grad_norm": 22.054996490478516, | |
| "learning_rate": 3.9049919484702094e-05, | |
| "loss": 0.1488, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 8.031159420289855, | |
| "grad_norm": 0.0397706963121891, | |
| "learning_rate": 3.884863123993559e-05, | |
| "loss": 0.1561, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 8.033695652173913, | |
| "eval_accuracy": 0.8524590163934426, | |
| "eval_f1": 0.8498439299955695, | |
| "eval_loss": 0.6051312685012817, | |
| "eval_runtime": 37.4453, | |
| "eval_samples_per_second": 3.258, | |
| "eval_steps_per_second": 0.427, | |
| "step": 837 | |
| }, | |
| { | |
| "epoch": 9.001086956521739, | |
| "grad_norm": 21.391626358032227, | |
| "learning_rate": 3.864734299516908e-05, | |
| "loss": 0.0403, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 9.004710144927536, | |
| "grad_norm": 29.436418533325195, | |
| "learning_rate": 3.844605475040258e-05, | |
| "loss": 0.0919, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 9.008333333333333, | |
| "grad_norm": 0.7489465475082397, | |
| "learning_rate": 3.824476650563607e-05, | |
| "loss": 0.1226, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 9.01195652173913, | |
| "grad_norm": 0.17123177647590637, | |
| "learning_rate": 3.804347826086957e-05, | |
| "loss": 0.1048, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 9.015579710144927, | |
| "grad_norm": 0.16690145432949066, | |
| "learning_rate": 3.784219001610306e-05, | |
| "loss": 0.019, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 9.019202898550725, | |
| "grad_norm": 0.029665417969226837, | |
| "learning_rate": 3.764090177133656e-05, | |
| "loss": 0.0916, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 9.022826086956522, | |
| "grad_norm": 0.02787993662059307, | |
| "learning_rate": 3.743961352657005e-05, | |
| "loss": 0.1313, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 9.02644927536232, | |
| "grad_norm": 0.020100735127925873, | |
| "learning_rate": 3.7238325281803546e-05, | |
| "loss": 0.0665, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 9.030072463768116, | |
| "grad_norm": 0.46395331621170044, | |
| "learning_rate": 3.7037037037037037e-05, | |
| "loss": 0.1576, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 9.033695652173913, | |
| "grad_norm": 15.341463088989258, | |
| "learning_rate": 3.6835748792270534e-05, | |
| "loss": 0.2297, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 9.033695652173913, | |
| "eval_accuracy": 0.8770491803278688, | |
| "eval_f1": 0.8766394106755289, | |
| "eval_loss": 0.6320860385894775, | |
| "eval_runtime": 36.4362, | |
| "eval_samples_per_second": 3.348, | |
| "eval_steps_per_second": 0.439, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 10.003623188405797, | |
| "grad_norm": 0.1273241639137268, | |
| "learning_rate": 3.663446054750403e-05, | |
| "loss": 0.023, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 10.007246376811594, | |
| "grad_norm": 7.185577869415283, | |
| "learning_rate": 3.643317230273752e-05, | |
| "loss": 0.0476, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 10.01086956521739, | |
| "grad_norm": 0.06820656359195709, | |
| "learning_rate": 3.6231884057971014e-05, | |
| "loss": 0.098, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 10.014492753623188, | |
| "grad_norm": 3.738891124725342, | |
| "learning_rate": 3.603059581320451e-05, | |
| "loss": 0.0214, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 10.018115942028986, | |
| "grad_norm": 0.026407288387417793, | |
| "learning_rate": 3.5829307568438e-05, | |
| "loss": 0.0211, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 10.021739130434783, | |
| "grad_norm": 0.013281815685331821, | |
| "learning_rate": 3.56280193236715e-05, | |
| "loss": 0.0539, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 10.02536231884058, | |
| "grad_norm": 0.016630737110972404, | |
| "learning_rate": 3.5426731078905e-05, | |
| "loss": 0.0013, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 10.028985507246377, | |
| "grad_norm": 0.013293278403580189, | |
| "learning_rate": 3.522544283413849e-05, | |
| "loss": 0.0542, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 10.032608695652174, | |
| "grad_norm": 0.021008765324950218, | |
| "learning_rate": 3.502415458937198e-05, | |
| "loss": 0.0692, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 10.033695652173913, | |
| "eval_accuracy": 0.8442622950819673, | |
| "eval_f1": 0.8454522438128995, | |
| "eval_loss": 0.7127842903137207, | |
| "eval_runtime": 37.7495, | |
| "eval_samples_per_second": 3.232, | |
| "eval_steps_per_second": 0.424, | |
| "step": 1023 | |
| }, | |
| { | |
| "epoch": 11.002536231884058, | |
| "grad_norm": 1.3483757972717285, | |
| "learning_rate": 3.482286634460548e-05, | |
| "loss": 0.0038, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 11.006159420289855, | |
| "grad_norm": 3.5823521614074707, | |
| "learning_rate": 3.462157809983897e-05, | |
| "loss": 0.0591, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 11.009782608695652, | |
| "grad_norm": 0.010481027886271477, | |
| "learning_rate": 3.4420289855072465e-05, | |
| "loss": 0.1033, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 11.013405797101449, | |
| "grad_norm": 0.022550148889422417, | |
| "learning_rate": 3.421900161030596e-05, | |
| "loss": 0.073, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 11.017028985507247, | |
| "grad_norm": 0.22509634494781494, | |
| "learning_rate": 3.4017713365539454e-05, | |
| "loss": 0.0726, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 11.020652173913044, | |
| "grad_norm": 0.409952849149704, | |
| "learning_rate": 3.381642512077295e-05, | |
| "loss": 0.02, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 11.024275362318841, | |
| "grad_norm": 0.022929221391677856, | |
| "learning_rate": 3.361513687600644e-05, | |
| "loss": 0.0079, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 11.027898550724638, | |
| "grad_norm": 0.009896630421280861, | |
| "learning_rate": 3.341384863123993e-05, | |
| "loss": 0.0277, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 11.031521739130435, | |
| "grad_norm": 0.04593189060688019, | |
| "learning_rate": 3.321256038647343e-05, | |
| "loss": 0.0495, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 11.033695652173913, | |
| "eval_accuracy": 0.8360655737704918, | |
| "eval_f1": 0.8352522796879587, | |
| "eval_loss": 0.7737651467323303, | |
| "eval_runtime": 37.723, | |
| "eval_samples_per_second": 3.234, | |
| "eval_steps_per_second": 0.424, | |
| "step": 1116 | |
| }, | |
| { | |
| "epoch": 12.001449275362319, | |
| "grad_norm": 0.4977063536643982, | |
| "learning_rate": 3.301127214170693e-05, | |
| "loss": 0.068, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 12.005072463768116, | |
| "grad_norm": 9.698254585266113, | |
| "learning_rate": 3.280998389694042e-05, | |
| "loss": 0.0108, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 12.008695652173913, | |
| "grad_norm": 37.918338775634766, | |
| "learning_rate": 3.260869565217392e-05, | |
| "loss": 0.0108, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 12.01231884057971, | |
| "grad_norm": 0.012104889377951622, | |
| "learning_rate": 3.240740740740741e-05, | |
| "loss": 0.0524, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 12.015942028985508, | |
| "grad_norm": 40.3338623046875, | |
| "learning_rate": 3.22061191626409e-05, | |
| "loss": 0.0867, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 12.019565217391305, | |
| "grad_norm": 37.17512130737305, | |
| "learning_rate": 3.2004830917874396e-05, | |
| "loss": 0.058, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 12.023188405797102, | |
| "grad_norm": 0.11629298329353333, | |
| "learning_rate": 3.1803542673107894e-05, | |
| "loss": 0.0826, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 12.026811594202899, | |
| "grad_norm": 0.01565568707883358, | |
| "learning_rate": 3.1602254428341385e-05, | |
| "loss": 0.1293, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 12.030434782608696, | |
| "grad_norm": 0.0614808052778244, | |
| "learning_rate": 3.140096618357488e-05, | |
| "loss": 0.1059, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 12.033695652173913, | |
| "eval_accuracy": 0.8524590163934426, | |
| "eval_f1": 0.8524029704357573, | |
| "eval_loss": 0.6213375329971313, | |
| "eval_runtime": 37.3424, | |
| "eval_samples_per_second": 3.267, | |
| "eval_steps_per_second": 0.428, | |
| "step": 1209 | |
| }, | |
| { | |
| "epoch": 13.00036231884058, | |
| "grad_norm": 0.01347822230309248, | |
| "learning_rate": 3.119967793880837e-05, | |
| "loss": 0.002, | |
| "step": 1210 | |
| }, | |
| { | |
| "epoch": 13.003985507246377, | |
| "grad_norm": 0.02086636610329151, | |
| "learning_rate": 3.099838969404187e-05, | |
| "loss": 0.0658, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 13.007608695652173, | |
| "grad_norm": 0.18250229954719543, | |
| "learning_rate": 3.079710144927536e-05, | |
| "loss": 0.018, | |
| "step": 1230 | |
| }, | |
| { | |
| "epoch": 13.01123188405797, | |
| "grad_norm": 0.01864694245159626, | |
| "learning_rate": 3.059581320450886e-05, | |
| "loss": 0.0016, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 13.014855072463767, | |
| "grad_norm": 0.03139445558190346, | |
| "learning_rate": 3.0394524959742354e-05, | |
| "loss": 0.0011, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 13.018478260869566, | |
| "grad_norm": 0.013789031654596329, | |
| "learning_rate": 3.0193236714975848e-05, | |
| "loss": 0.0016, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 13.022101449275363, | |
| "grad_norm": 0.03744020313024521, | |
| "learning_rate": 2.9991948470209342e-05, | |
| "loss": 0.001, | |
| "step": 1270 | |
| }, | |
| { | |
| "epoch": 13.02572463768116, | |
| "grad_norm": 0.007898851297795773, | |
| "learning_rate": 2.9790660225442833e-05, | |
| "loss": 0.0106, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 13.029347826086957, | |
| "grad_norm": 3.897127866744995, | |
| "learning_rate": 2.9589371980676327e-05, | |
| "loss": 0.0454, | |
| "step": 1290 | |
| }, | |
| { | |
| "epoch": 13.032971014492754, | |
| "grad_norm": 0.009393475018441677, | |
| "learning_rate": 2.938808373590982e-05, | |
| "loss": 0.1672, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 13.033695652173913, | |
| "eval_accuracy": 0.8442622950819673, | |
| "eval_f1": 0.8408580352564015, | |
| "eval_loss": 0.7887758612632751, | |
| "eval_runtime": 37.7507, | |
| "eval_samples_per_second": 3.232, | |
| "eval_steps_per_second": 0.424, | |
| "step": 1302 | |
| }, | |
| { | |
| "epoch": 14.002898550724638, | |
| "grad_norm": 0.034189604222774506, | |
| "learning_rate": 2.918679549114332e-05, | |
| "loss": 0.044, | |
| "step": 1310 | |
| }, | |
| { | |
| "epoch": 14.006521739130434, | |
| "grad_norm": 0.02449285238981247, | |
| "learning_rate": 2.8985507246376814e-05, | |
| "loss": 0.0904, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 14.010144927536231, | |
| "grad_norm": 0.027986012399196625, | |
| "learning_rate": 2.8784219001610308e-05, | |
| "loss": 0.0059, | |
| "step": 1330 | |
| }, | |
| { | |
| "epoch": 14.013768115942028, | |
| "grad_norm": 0.017405090853571892, | |
| "learning_rate": 2.8582930756843802e-05, | |
| "loss": 0.0016, | |
| "step": 1340 | |
| }, | |
| { | |
| "epoch": 14.017391304347827, | |
| "grad_norm": 0.009259097278118134, | |
| "learning_rate": 2.8381642512077293e-05, | |
| "loss": 0.1116, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 14.021014492753624, | |
| "grad_norm": 0.27058884501457214, | |
| "learning_rate": 2.8180354267310787e-05, | |
| "loss": 0.0011, | |
| "step": 1360 | |
| }, | |
| { | |
| "epoch": 14.02463768115942, | |
| "grad_norm": 0.04683419317007065, | |
| "learning_rate": 2.7979066022544288e-05, | |
| "loss": 0.0022, | |
| "step": 1370 | |
| }, | |
| { | |
| "epoch": 14.028260869565218, | |
| "grad_norm": 0.011938877403736115, | |
| "learning_rate": 2.777777777777778e-05, | |
| "loss": 0.092, | |
| "step": 1380 | |
| }, | |
| { | |
| "epoch": 14.031884057971014, | |
| "grad_norm": 0.020922021940350533, | |
| "learning_rate": 2.7576489533011273e-05, | |
| "loss": 0.0178, | |
| "step": 1390 | |
| }, | |
| { | |
| "epoch": 14.033695652173913, | |
| "eval_accuracy": 0.8688524590163934, | |
| "eval_f1": 0.8657779177289288, | |
| "eval_loss": 0.6488391757011414, | |
| "eval_runtime": 37.3683, | |
| "eval_samples_per_second": 3.265, | |
| "eval_steps_per_second": 0.428, | |
| "step": 1395 | |
| }, | |
| { | |
| "epoch": 15.001811594202898, | |
| "grad_norm": 0.014293194748461246, | |
| "learning_rate": 2.7375201288244768e-05, | |
| "loss": 0.0616, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 15.005434782608695, | |
| "grad_norm": 0.012990676797926426, | |
| "learning_rate": 2.7173913043478262e-05, | |
| "loss": 0.0038, | |
| "step": 1410 | |
| }, | |
| { | |
| "epoch": 15.009057971014492, | |
| "grad_norm": 0.021259872242808342, | |
| "learning_rate": 2.6972624798711753e-05, | |
| "loss": 0.0008, | |
| "step": 1420 | |
| }, | |
| { | |
| "epoch": 15.01268115942029, | |
| "grad_norm": 0.02497517503798008, | |
| "learning_rate": 2.6771336553945254e-05, | |
| "loss": 0.0016, | |
| "step": 1430 | |
| }, | |
| { | |
| "epoch": 15.016304347826088, | |
| "grad_norm": 7.305609703063965, | |
| "learning_rate": 2.6570048309178748e-05, | |
| "loss": 0.1195, | |
| "step": 1440 | |
| }, | |
| { | |
| "epoch": 15.019927536231885, | |
| "grad_norm": 65.574462890625, | |
| "learning_rate": 2.636876006441224e-05, | |
| "loss": 0.0579, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 15.023550724637682, | |
| "grad_norm": 0.010529917664825916, | |
| "learning_rate": 2.6167471819645733e-05, | |
| "loss": 0.0296, | |
| "step": 1460 | |
| }, | |
| { | |
| "epoch": 15.027173913043478, | |
| "grad_norm": 0.010935317724943161, | |
| "learning_rate": 2.5966183574879227e-05, | |
| "loss": 0.0616, | |
| "step": 1470 | |
| }, | |
| { | |
| "epoch": 15.030797101449275, | |
| "grad_norm": 0.03048408031463623, | |
| "learning_rate": 2.576489533011272e-05, | |
| "loss": 0.0165, | |
| "step": 1480 | |
| }, | |
| { | |
| "epoch": 15.033695652173913, | |
| "eval_accuracy": 0.8770491803278688, | |
| "eval_f1": 0.8772784869363629, | |
| "eval_loss": 0.68454909324646, | |
| "eval_runtime": 38.539, | |
| "eval_samples_per_second": 3.166, | |
| "eval_steps_per_second": 0.415, | |
| "step": 1488 | |
| }, | |
| { | |
| "epoch": 16.00072463768116, | |
| "grad_norm": 0.026206759735941887, | |
| "learning_rate": 2.556360708534622e-05, | |
| "loss": 0.0027, | |
| "step": 1490 | |
| }, | |
| { | |
| "epoch": 16.004347826086956, | |
| "grad_norm": 0.17636388540267944, | |
| "learning_rate": 2.5362318840579714e-05, | |
| "loss": 0.0013, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 16.007971014492753, | |
| "grad_norm": 0.009907973930239677, | |
| "learning_rate": 2.5161030595813208e-05, | |
| "loss": 0.0008, | |
| "step": 1510 | |
| }, | |
| { | |
| "epoch": 16.01159420289855, | |
| "grad_norm": 0.007697808090597391, | |
| "learning_rate": 2.49597423510467e-05, | |
| "loss": 0.0012, | |
| "step": 1520 | |
| }, | |
| { | |
| "epoch": 16.015217391304347, | |
| "grad_norm": 0.012929815798997879, | |
| "learning_rate": 2.4758454106280193e-05, | |
| "loss": 0.0008, | |
| "step": 1530 | |
| }, | |
| { | |
| "epoch": 16.018840579710144, | |
| "grad_norm": 0.03589075058698654, | |
| "learning_rate": 2.455716586151369e-05, | |
| "loss": 0.0006, | |
| "step": 1540 | |
| }, | |
| { | |
| "epoch": 16.02246376811594, | |
| "grad_norm": 0.012779805809259415, | |
| "learning_rate": 2.435587761674718e-05, | |
| "loss": 0.1136, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 16.026086956521738, | |
| "grad_norm": 51.02324676513672, | |
| "learning_rate": 2.4154589371980676e-05, | |
| "loss": 0.1051, | |
| "step": 1560 | |
| }, | |
| { | |
| "epoch": 16.029710144927535, | |
| "grad_norm": 0.01224570907652378, | |
| "learning_rate": 2.3953301127214173e-05, | |
| "loss": 0.0355, | |
| "step": 1570 | |
| }, | |
| { | |
| "epoch": 16.033333333333335, | |
| "grad_norm": 0.1042768731713295, | |
| "learning_rate": 2.3752012882447668e-05, | |
| "loss": 0.0166, | |
| "step": 1580 | |
| }, | |
| { | |
| "epoch": 16.033695652173915, | |
| "eval_accuracy": 0.8524590163934426, | |
| "eval_f1": 0.8445057204972595, | |
| "eval_loss": 0.8649476766586304, | |
| "eval_runtime": 42.3787, | |
| "eval_samples_per_second": 2.879, | |
| "eval_steps_per_second": 0.378, | |
| "step": 1581 | |
| }, | |
| { | |
| "epoch": 17.003260869565217, | |
| "grad_norm": 0.007085030898451805, | |
| "learning_rate": 2.355072463768116e-05, | |
| "loss": 0.0251, | |
| "step": 1590 | |
| }, | |
| { | |
| "epoch": 17.006884057971014, | |
| "grad_norm": 0.015758316963911057, | |
| "learning_rate": 2.3349436392914656e-05, | |
| "loss": 0.0598, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 17.01050724637681, | |
| "grad_norm": 0.0069606369361281395, | |
| "learning_rate": 2.314814814814815e-05, | |
| "loss": 0.004, | |
| "step": 1610 | |
| }, | |
| { | |
| "epoch": 17.014130434782608, | |
| "grad_norm": 0.008627723902463913, | |
| "learning_rate": 2.294685990338164e-05, | |
| "loss": 0.0065, | |
| "step": 1620 | |
| }, | |
| { | |
| "epoch": 17.017753623188405, | |
| "grad_norm": 0.009509687311947346, | |
| "learning_rate": 2.274557165861514e-05, | |
| "loss": 0.0005, | |
| "step": 1630 | |
| }, | |
| { | |
| "epoch": 17.0213768115942, | |
| "grad_norm": 0.014063004404306412, | |
| "learning_rate": 2.2544283413848633e-05, | |
| "loss": 0.0011, | |
| "step": 1640 | |
| }, | |
| { | |
| "epoch": 17.025, | |
| "grad_norm": 14.068120956420898, | |
| "learning_rate": 2.2342995169082127e-05, | |
| "loss": 0.0636, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 17.028623188405795, | |
| "grad_norm": 0.08216149359941483, | |
| "learning_rate": 2.214170692431562e-05, | |
| "loss": 0.1043, | |
| "step": 1660 | |
| }, | |
| { | |
| "epoch": 17.032246376811596, | |
| "grad_norm": 0.14345373213291168, | |
| "learning_rate": 2.1940418679549116e-05, | |
| "loss": 0.0014, | |
| "step": 1670 | |
| }, | |
| { | |
| "epoch": 17.033695652173915, | |
| "eval_accuracy": 0.8524590163934426, | |
| "eval_f1": 0.8516181034534225, | |
| "eval_loss": 0.7865917086601257, | |
| "eval_runtime": 40.0693, | |
| "eval_samples_per_second": 3.045, | |
| "eval_steps_per_second": 0.399, | |
| "step": 1674 | |
| }, | |
| { | |
| "epoch": 18.002173913043478, | |
| "grad_norm": 0.006833807565271854, | |
| "learning_rate": 2.173913043478261e-05, | |
| "loss": 0.0039, | |
| "step": 1680 | |
| }, | |
| { | |
| "epoch": 18.005797101449275, | |
| "grad_norm": 0.014425553381443024, | |
| "learning_rate": 2.1537842190016104e-05, | |
| "loss": 0.022, | |
| "step": 1690 | |
| }, | |
| { | |
| "epoch": 18.009420289855072, | |
| "grad_norm": 0.05315766856074333, | |
| "learning_rate": 2.13365539452496e-05, | |
| "loss": 0.0055, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 18.01304347826087, | |
| "grad_norm": 0.006013238336890936, | |
| "learning_rate": 2.1135265700483093e-05, | |
| "loss": 0.0725, | |
| "step": 1710 | |
| }, | |
| { | |
| "epoch": 18.016666666666666, | |
| "grad_norm": 0.009230862371623516, | |
| "learning_rate": 2.0933977455716587e-05, | |
| "loss": 0.0005, | |
| "step": 1720 | |
| }, | |
| { | |
| "epoch": 18.020289855072463, | |
| "grad_norm": 0.007369612343609333, | |
| "learning_rate": 2.073268921095008e-05, | |
| "loss": 0.0005, | |
| "step": 1730 | |
| }, | |
| { | |
| "epoch": 18.02391304347826, | |
| "grad_norm": 0.005340999457985163, | |
| "learning_rate": 2.0531400966183576e-05, | |
| "loss": 0.0043, | |
| "step": 1740 | |
| }, | |
| { | |
| "epoch": 18.027536231884056, | |
| "grad_norm": 5.2305498123168945, | |
| "learning_rate": 2.033011272141707e-05, | |
| "loss": 0.0677, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 18.031159420289853, | |
| "grad_norm": 0.008544102311134338, | |
| "learning_rate": 2.0128824476650564e-05, | |
| "loss": 0.0473, | |
| "step": 1760 | |
| }, | |
| { | |
| "epoch": 18.033695652173915, | |
| "eval_accuracy": 0.8770491803278688, | |
| "eval_f1": 0.8776382319776725, | |
| "eval_loss": 0.6390149593353271, | |
| "eval_runtime": 38.4182, | |
| "eval_samples_per_second": 3.176, | |
| "eval_steps_per_second": 0.416, | |
| "step": 1767 | |
| }, | |
| { | |
| "epoch": 19.00108695652174, | |
| "grad_norm": 0.007366463541984558, | |
| "learning_rate": 1.992753623188406e-05, | |
| "loss": 0.0005, | |
| "step": 1770 | |
| }, | |
| { | |
| "epoch": 19.004710144927536, | |
| "grad_norm": 2.3047983646392822, | |
| "learning_rate": 1.9726247987117553e-05, | |
| "loss": 0.0185, | |
| "step": 1780 | |
| }, | |
| { | |
| "epoch": 19.008333333333333, | |
| "grad_norm": 0.005975569132715464, | |
| "learning_rate": 1.9524959742351047e-05, | |
| "loss": 0.0007, | |
| "step": 1790 | |
| }, | |
| { | |
| "epoch": 19.01195652173913, | |
| "grad_norm": 0.007045724429190159, | |
| "learning_rate": 1.932367149758454e-05, | |
| "loss": 0.0008, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 19.015579710144927, | |
| "grad_norm": 0.005632986314594746, | |
| "learning_rate": 1.9122383252818036e-05, | |
| "loss": 0.001, | |
| "step": 1810 | |
| }, | |
| { | |
| "epoch": 19.019202898550724, | |
| "grad_norm": 0.0067955972626805305, | |
| "learning_rate": 1.892109500805153e-05, | |
| "loss": 0.0006, | |
| "step": 1820 | |
| }, | |
| { | |
| "epoch": 19.02282608695652, | |
| "grad_norm": 0.0061930399388074875, | |
| "learning_rate": 1.8719806763285024e-05, | |
| "loss": 0.0154, | |
| "step": 1830 | |
| }, | |
| { | |
| "epoch": 19.026449275362317, | |
| "grad_norm": 0.005985133349895477, | |
| "learning_rate": 1.8518518518518518e-05, | |
| "loss": 0.0029, | |
| "step": 1840 | |
| }, | |
| { | |
| "epoch": 19.030072463768114, | |
| "grad_norm": 0.005963871255517006, | |
| "learning_rate": 1.8317230273752016e-05, | |
| "loss": 0.0407, | |
| "step": 1850 | |
| }, | |
| { | |
| "epoch": 19.033695652173915, | |
| "grad_norm": 0.004762581083923578, | |
| "learning_rate": 1.8115942028985507e-05, | |
| "loss": 0.0441, | |
| "step": 1860 | |
| }, | |
| { | |
| "epoch": 19.033695652173915, | |
| "eval_accuracy": 0.8360655737704918, | |
| "eval_f1": 0.834206674473068, | |
| "eval_loss": 0.8234833478927612, | |
| "eval_runtime": 37.3263, | |
| "eval_samples_per_second": 3.268, | |
| "eval_steps_per_second": 0.429, | |
| "step": 1860 | |
| }, | |
| { | |
| "epoch": 20.003623188405797, | |
| "grad_norm": 0.12766918540000916, | |
| "learning_rate": 1.7914653784219e-05, | |
| "loss": 0.0067, | |
| "step": 1870 | |
| }, | |
| { | |
| "epoch": 20.007246376811594, | |
| "grad_norm": 0.031153714284300804, | |
| "learning_rate": 1.77133655394525e-05, | |
| "loss": 0.0007, | |
| "step": 1880 | |
| }, | |
| { | |
| "epoch": 20.01086956521739, | |
| "grad_norm": 0.0049373493529856205, | |
| "learning_rate": 1.751207729468599e-05, | |
| "loss": 0.0148, | |
| "step": 1890 | |
| }, | |
| { | |
| "epoch": 20.014492753623188, | |
| "grad_norm": 0.04706621542572975, | |
| "learning_rate": 1.7310789049919484e-05, | |
| "loss": 0.0516, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 20.018115942028984, | |
| "grad_norm": 0.011202222667634487, | |
| "learning_rate": 1.710950080515298e-05, | |
| "loss": 0.0073, | |
| "step": 1910 | |
| }, | |
| { | |
| "epoch": 20.02173913043478, | |
| "grad_norm": 0.004066763911396265, | |
| "learning_rate": 1.6908212560386476e-05, | |
| "loss": 0.0065, | |
| "step": 1920 | |
| }, | |
| { | |
| "epoch": 20.02536231884058, | |
| "grad_norm": 0.5498021245002747, | |
| "learning_rate": 1.6706924315619967e-05, | |
| "loss": 0.0549, | |
| "step": 1930 | |
| }, | |
| { | |
| "epoch": 20.028985507246375, | |
| "grad_norm": 0.011782179586589336, | |
| "learning_rate": 1.6505636070853464e-05, | |
| "loss": 0.0009, | |
| "step": 1940 | |
| }, | |
| { | |
| "epoch": 20.032608695652176, | |
| "grad_norm": 0.0048751975409686565, | |
| "learning_rate": 1.630434782608696e-05, | |
| "loss": 0.0006, | |
| "step": 1950 | |
| }, | |
| { | |
| "epoch": 20.033695652173915, | |
| "eval_accuracy": 0.8852459016393442, | |
| "eval_f1": 0.88558791751199, | |
| "eval_loss": 0.6014039516448975, | |
| "eval_runtime": 37.9636, | |
| "eval_samples_per_second": 3.214, | |
| "eval_steps_per_second": 0.421, | |
| "step": 1953 | |
| }, | |
| { | |
| "epoch": 21.002536231884058, | |
| "grad_norm": 0.009569565765559673, | |
| "learning_rate": 1.610305958132045e-05, | |
| "loss": 0.0004, | |
| "step": 1960 | |
| }, | |
| { | |
| "epoch": 21.006159420289855, | |
| "grad_norm": 0.0038696015253663063, | |
| "learning_rate": 1.5901771336553947e-05, | |
| "loss": 0.0005, | |
| "step": 1970 | |
| }, | |
| { | |
| "epoch": 21.00978260869565, | |
| "grad_norm": 0.012325268238782883, | |
| "learning_rate": 1.570048309178744e-05, | |
| "loss": 0.0248, | |
| "step": 1980 | |
| }, | |
| { | |
| "epoch": 21.01340579710145, | |
| "grad_norm": 0.927451491355896, | |
| "learning_rate": 1.5499194847020936e-05, | |
| "loss": 0.0384, | |
| "step": 1990 | |
| }, | |
| { | |
| "epoch": 21.017028985507245, | |
| "grad_norm": 0.005916436202824116, | |
| "learning_rate": 1.529790660225443e-05, | |
| "loss": 0.0004, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 21.020652173913042, | |
| "grad_norm": 0.00484825111925602, | |
| "learning_rate": 1.5096618357487924e-05, | |
| "loss": 0.0028, | |
| "step": 2010 | |
| }, | |
| { | |
| "epoch": 21.02427536231884, | |
| "grad_norm": 0.05984441190958023, | |
| "learning_rate": 1.4895330112721417e-05, | |
| "loss": 0.0635, | |
| "step": 2020 | |
| }, | |
| { | |
| "epoch": 21.027898550724636, | |
| "grad_norm": 0.006016437895596027, | |
| "learning_rate": 1.469404186795491e-05, | |
| "loss": 0.0005, | |
| "step": 2030 | |
| }, | |
| { | |
| "epoch": 21.031521739130437, | |
| "grad_norm": 0.006119464058429003, | |
| "learning_rate": 1.4492753623188407e-05, | |
| "loss": 0.0005, | |
| "step": 2040 | |
| }, | |
| { | |
| "epoch": 21.033695652173915, | |
| "eval_accuracy": 0.8688524590163934, | |
| "eval_f1": 0.8672487891684085, | |
| "eval_loss": 0.758141815662384, | |
| "eval_runtime": 38.1916, | |
| "eval_samples_per_second": 3.194, | |
| "eval_steps_per_second": 0.419, | |
| "step": 2046 | |
| }, | |
| { | |
| "epoch": 22.00144927536232, | |
| "grad_norm": 0.008889817632734776, | |
| "learning_rate": 1.4291465378421901e-05, | |
| "loss": 0.0009, | |
| "step": 2050 | |
| }, | |
| { | |
| "epoch": 22.005072463768116, | |
| "grad_norm": 0.004777275491505861, | |
| "learning_rate": 1.4090177133655394e-05, | |
| "loss": 0.0159, | |
| "step": 2060 | |
| }, | |
| { | |
| "epoch": 22.008695652173913, | |
| "grad_norm": 0.005355835892260075, | |
| "learning_rate": 1.388888888888889e-05, | |
| "loss": 0.0066, | |
| "step": 2070 | |
| }, | |
| { | |
| "epoch": 22.01231884057971, | |
| "grad_norm": 0.006906128488481045, | |
| "learning_rate": 1.3687600644122384e-05, | |
| "loss": 0.0005, | |
| "step": 2080 | |
| }, | |
| { | |
| "epoch": 22.015942028985506, | |
| "grad_norm": 0.0049617839977145195, | |
| "learning_rate": 1.3486312399355876e-05, | |
| "loss": 0.0007, | |
| "step": 2090 | |
| }, | |
| { | |
| "epoch": 22.019565217391303, | |
| "grad_norm": 0.004387282766401768, | |
| "learning_rate": 1.3285024154589374e-05, | |
| "loss": 0.0004, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 22.0231884057971, | |
| "grad_norm": 0.004814252723008394, | |
| "learning_rate": 1.3083735909822867e-05, | |
| "loss": 0.0041, | |
| "step": 2110 | |
| }, | |
| { | |
| "epoch": 22.026811594202897, | |
| "grad_norm": 0.007489080540835857, | |
| "learning_rate": 1.288244766505636e-05, | |
| "loss": 0.0442, | |
| "step": 2120 | |
| }, | |
| { | |
| "epoch": 22.030434782608694, | |
| "grad_norm": 0.00951230525970459, | |
| "learning_rate": 1.2681159420289857e-05, | |
| "loss": 0.0032, | |
| "step": 2130 | |
| }, | |
| { | |
| "epoch": 22.033695652173915, | |
| "eval_accuracy": 0.8770491803278688, | |
| "eval_f1": 0.8771730619791396, | |
| "eval_loss": 0.6454241871833801, | |
| "eval_runtime": 37.8713, | |
| "eval_samples_per_second": 3.221, | |
| "eval_steps_per_second": 0.422, | |
| "step": 2139 | |
| }, | |
| { | |
| "epoch": 23.00036231884058, | |
| "grad_norm": 0.005327664315700531, | |
| "learning_rate": 1.247987117552335e-05, | |
| "loss": 0.027, | |
| "step": 2140 | |
| }, | |
| { | |
| "epoch": 23.003985507246377, | |
| "grad_norm": 0.006378709804266691, | |
| "learning_rate": 1.2278582930756845e-05, | |
| "loss": 0.0005, | |
| "step": 2150 | |
| }, | |
| { | |
| "epoch": 23.007608695652173, | |
| "grad_norm": 0.004449001979082823, | |
| "learning_rate": 1.2077294685990338e-05, | |
| "loss": 0.0166, | |
| "step": 2160 | |
| }, | |
| { | |
| "epoch": 23.01123188405797, | |
| "grad_norm": 0.011220560409128666, | |
| "learning_rate": 1.1876006441223834e-05, | |
| "loss": 0.013, | |
| "step": 2170 | |
| }, | |
| { | |
| "epoch": 23.014855072463767, | |
| "grad_norm": 0.007521830964833498, | |
| "learning_rate": 1.1674718196457328e-05, | |
| "loss": 0.0004, | |
| "step": 2180 | |
| }, | |
| { | |
| "epoch": 23.018478260869564, | |
| "grad_norm": 0.06200418993830681, | |
| "learning_rate": 1.147342995169082e-05, | |
| "loss": 0.0204, | |
| "step": 2190 | |
| }, | |
| { | |
| "epoch": 23.02210144927536, | |
| "grad_norm": 0.005162249319255352, | |
| "learning_rate": 1.1272141706924317e-05, | |
| "loss": 0.0005, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 23.025724637681158, | |
| "grad_norm": 0.004768849816173315, | |
| "learning_rate": 1.107085346215781e-05, | |
| "loss": 0.0963, | |
| "step": 2210 | |
| }, | |
| { | |
| "epoch": 23.029347826086955, | |
| "grad_norm": 0.006896668113768101, | |
| "learning_rate": 1.0869565217391305e-05, | |
| "loss": 0.0209, | |
| "step": 2220 | |
| }, | |
| { | |
| "epoch": 23.032971014492755, | |
| "grad_norm": 0.5598499178886414, | |
| "learning_rate": 1.06682769726248e-05, | |
| "loss": 0.0565, | |
| "step": 2230 | |
| }, | |
| { | |
| "epoch": 23.033695652173915, | |
| "eval_accuracy": 0.8524590163934426, | |
| "eval_f1": 0.8542214345493033, | |
| "eval_loss": 0.8096156120300293, | |
| "eval_runtime": 39.1323, | |
| "eval_samples_per_second": 3.118, | |
| "eval_steps_per_second": 0.409, | |
| "step": 2232 | |
| }, | |
| { | |
| "epoch": 24.002898550724638, | |
| "grad_norm": 0.017325986176729202, | |
| "learning_rate": 1.0466988727858294e-05, | |
| "loss": 0.0005, | |
| "step": 2240 | |
| }, | |
| { | |
| "epoch": 24.006521739130434, | |
| "grad_norm": 0.2567996382713318, | |
| "learning_rate": 1.0265700483091788e-05, | |
| "loss": 0.011, | |
| "step": 2250 | |
| }, | |
| { | |
| "epoch": 24.01014492753623, | |
| "grad_norm": 0.008284560404717922, | |
| "learning_rate": 1.0064412238325282e-05, | |
| "loss": 0.0105, | |
| "step": 2260 | |
| }, | |
| { | |
| "epoch": 24.013768115942028, | |
| "grad_norm": 0.021722067147493362, | |
| "learning_rate": 9.863123993558776e-06, | |
| "loss": 0.0129, | |
| "step": 2270 | |
| }, | |
| { | |
| "epoch": 24.017391304347825, | |
| "grad_norm": 0.01306977029889822, | |
| "learning_rate": 9.66183574879227e-06, | |
| "loss": 0.093, | |
| "step": 2280 | |
| }, | |
| { | |
| "epoch": 24.021014492753622, | |
| "grad_norm": 0.006157809402793646, | |
| "learning_rate": 9.460547504025765e-06, | |
| "loss": 0.0005, | |
| "step": 2290 | |
| }, | |
| { | |
| "epoch": 24.02463768115942, | |
| "grad_norm": 0.006750662811100483, | |
| "learning_rate": 9.259259259259259e-06, | |
| "loss": 0.0004, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 24.028260869565216, | |
| "grad_norm": 0.004828326869755983, | |
| "learning_rate": 9.057971014492753e-06, | |
| "loss": 0.0095, | |
| "step": 2310 | |
| }, | |
| { | |
| "epoch": 24.031884057971016, | |
| "grad_norm": 1.7074612379074097, | |
| "learning_rate": 8.85668276972625e-06, | |
| "loss": 0.011, | |
| "step": 2320 | |
| }, | |
| { | |
| "epoch": 24.033695652173915, | |
| "eval_accuracy": 0.8852459016393442, | |
| "eval_f1": 0.8858382568953512, | |
| "eval_loss": 0.6807242631912231, | |
| "eval_runtime": 41.3656, | |
| "eval_samples_per_second": 2.949, | |
| "eval_steps_per_second": 0.387, | |
| "step": 2325 | |
| }, | |
| { | |
| "epoch": 25.0018115942029, | |
| "grad_norm": 0.0043255784548819065, | |
| "learning_rate": 8.655394524959742e-06, | |
| "loss": 0.0022, | |
| "step": 2330 | |
| }, | |
| { | |
| "epoch": 25.005434782608695, | |
| "grad_norm": 0.007067692466080189, | |
| "learning_rate": 8.454106280193238e-06, | |
| "loss": 0.0073, | |
| "step": 2340 | |
| }, | |
| { | |
| "epoch": 25.009057971014492, | |
| "grad_norm": 1.005963683128357, | |
| "learning_rate": 8.252818035426732e-06, | |
| "loss": 0.0011, | |
| "step": 2350 | |
| }, | |
| { | |
| "epoch": 25.01268115942029, | |
| "grad_norm": 0.004243878182023764, | |
| "learning_rate": 8.051529790660225e-06, | |
| "loss": 0.0004, | |
| "step": 2360 | |
| }, | |
| { | |
| "epoch": 25.016304347826086, | |
| "grad_norm": 0.0035646618343889713, | |
| "learning_rate": 7.85024154589372e-06, | |
| "loss": 0.0004, | |
| "step": 2370 | |
| }, | |
| { | |
| "epoch": 25.019927536231883, | |
| "grad_norm": 0.004057039972394705, | |
| "learning_rate": 7.648953301127215e-06, | |
| "loss": 0.0004, | |
| "step": 2380 | |
| }, | |
| { | |
| "epoch": 25.02355072463768, | |
| "grad_norm": 0.010123531334102154, | |
| "learning_rate": 7.447665056360708e-06, | |
| "loss": 0.0025, | |
| "step": 2390 | |
| }, | |
| { | |
| "epoch": 25.027173913043477, | |
| "grad_norm": 1.058449387550354, | |
| "learning_rate": 7.246376811594203e-06, | |
| "loss": 0.0228, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 25.030797101449274, | |
| "grad_norm": 2.1814162731170654, | |
| "learning_rate": 7.045088566827697e-06, | |
| "loss": 0.0146, | |
| "step": 2410 | |
| }, | |
| { | |
| "epoch": 25.033695652173915, | |
| "eval_accuracy": 0.8688524590163934, | |
| "eval_f1": 0.8695984040246334, | |
| "eval_loss": 0.7754350900650024, | |
| "eval_runtime": 41.8119, | |
| "eval_samples_per_second": 2.918, | |
| "eval_steps_per_second": 0.383, | |
| "step": 2418 | |
| }, | |
| { | |
| "epoch": 26.00072463768116, | |
| "grad_norm": 0.00446619326248765, | |
| "learning_rate": 6.843800322061192e-06, | |
| "loss": 0.0469, | |
| "step": 2420 | |
| }, | |
| { | |
| "epoch": 26.004347826086956, | |
| "grad_norm": 0.005227618385106325, | |
| "learning_rate": 6.642512077294687e-06, | |
| "loss": 0.0105, | |
| "step": 2430 | |
| }, | |
| { | |
| "epoch": 26.007971014492753, | |
| "grad_norm": 2.0163729190826416, | |
| "learning_rate": 6.44122383252818e-06, | |
| "loss": 0.0116, | |
| "step": 2440 | |
| }, | |
| { | |
| "epoch": 26.01159420289855, | |
| "grad_norm": 0.0069722458720207214, | |
| "learning_rate": 6.239935587761675e-06, | |
| "loss": 0.0079, | |
| "step": 2450 | |
| }, | |
| { | |
| "epoch": 26.015217391304347, | |
| "grad_norm": 0.006805983372032642, | |
| "learning_rate": 6.038647342995169e-06, | |
| "loss": 0.0004, | |
| "step": 2460 | |
| }, | |
| { | |
| "epoch": 26.018840579710144, | |
| "grad_norm": 0.005044913850724697, | |
| "learning_rate": 5.837359098228664e-06, | |
| "loss": 0.0036, | |
| "step": 2470 | |
| }, | |
| { | |
| "epoch": 26.02246376811594, | |
| "grad_norm": 0.005564519669860601, | |
| "learning_rate": 5.636070853462158e-06, | |
| "loss": 0.0003, | |
| "step": 2480 | |
| }, | |
| { | |
| "epoch": 26.026086956521738, | |
| "grad_norm": 0.003706958144903183, | |
| "learning_rate": 5.4347826086956525e-06, | |
| "loss": 0.0004, | |
| "step": 2490 | |
| }, | |
| { | |
| "epoch": 26.029710144927535, | |
| "grad_norm": 0.02714346908032894, | |
| "learning_rate": 5.233494363929147e-06, | |
| "loss": 0.0191, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 26.033333333333335, | |
| "grad_norm": 0.008597085252404213, | |
| "learning_rate": 5.032206119162641e-06, | |
| "loss": 0.0004, | |
| "step": 2510 | |
| }, | |
| { | |
| "epoch": 26.033695652173915, | |
| "eval_accuracy": 0.8852459016393442, | |
| "eval_f1": 0.885748980830948, | |
| "eval_loss": 0.7246056199073792, | |
| "eval_runtime": 39.2721, | |
| "eval_samples_per_second": 3.107, | |
| "eval_steps_per_second": 0.407, | |
| "step": 2511 | |
| }, | |
| { | |
| "epoch": 27.003260869565217, | |
| "grad_norm": 0.004729451611638069, | |
| "learning_rate": 4.830917874396135e-06, | |
| "loss": 0.0004, | |
| "step": 2520 | |
| }, | |
| { | |
| "epoch": 27.006884057971014, | |
| "grad_norm": 0.0047379061579704285, | |
| "learning_rate": 4.6296296296296296e-06, | |
| "loss": 0.0169, | |
| "step": 2530 | |
| }, | |
| { | |
| "epoch": 27.01050724637681, | |
| "grad_norm": 0.0059508224949240685, | |
| "learning_rate": 4.428341384863125e-06, | |
| "loss": 0.0003, | |
| "step": 2540 | |
| }, | |
| { | |
| "epoch": 27.014130434782608, | |
| "grad_norm": 0.004985982086509466, | |
| "learning_rate": 4.227053140096619e-06, | |
| "loss": 0.0004, | |
| "step": 2550 | |
| }, | |
| { | |
| "epoch": 27.017753623188405, | |
| "grad_norm": 0.004285223316401243, | |
| "learning_rate": 4.025764895330112e-06, | |
| "loss": 0.0064, | |
| "step": 2560 | |
| }, | |
| { | |
| "epoch": 27.0213768115942, | |
| "grad_norm": 0.00481518916785717, | |
| "learning_rate": 3.8244766505636074e-06, | |
| "loss": 0.0036, | |
| "step": 2570 | |
| }, | |
| { | |
| "epoch": 27.025, | |
| "grad_norm": 0.005598173942416906, | |
| "learning_rate": 3.6231884057971017e-06, | |
| "loss": 0.0265, | |
| "step": 2580 | |
| }, | |
| { | |
| "epoch": 27.028623188405795, | |
| "grad_norm": 0.005482200998812914, | |
| "learning_rate": 3.421900161030596e-06, | |
| "loss": 0.0003, | |
| "step": 2590 | |
| }, | |
| { | |
| "epoch": 27.032246376811596, | |
| "grad_norm": 0.0035128567833453417, | |
| "learning_rate": 3.22061191626409e-06, | |
| "loss": 0.0004, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 27.033695652173915, | |
| "eval_accuracy": 0.8934426229508197, | |
| "eval_f1": 0.8942102524069736, | |
| "eval_loss": 0.7165006995201111, | |
| "eval_runtime": 37.9801, | |
| "eval_samples_per_second": 3.212, | |
| "eval_steps_per_second": 0.421, | |
| "step": 2604 | |
| }, | |
| { | |
| "epoch": 28.002173913043478, | |
| "grad_norm": 0.004918423481285572, | |
| "learning_rate": 3.0193236714975845e-06, | |
| "loss": 0.0003, | |
| "step": 2610 | |
| }, | |
| { | |
| "epoch": 28.005797101449275, | |
| "grad_norm": 0.00445589842274785, | |
| "learning_rate": 2.818035426731079e-06, | |
| "loss": 0.0096, | |
| "step": 2620 | |
| }, | |
| { | |
| "epoch": 28.009420289855072, | |
| "grad_norm": 0.0045196604914963245, | |
| "learning_rate": 2.6167471819645734e-06, | |
| "loss": 0.0159, | |
| "step": 2630 | |
| }, | |
| { | |
| "epoch": 28.01304347826087, | |
| "grad_norm": 0.005592667497694492, | |
| "learning_rate": 2.4154589371980677e-06, | |
| "loss": 0.0135, | |
| "step": 2640 | |
| }, | |
| { | |
| "epoch": 28.016666666666666, | |
| "grad_norm": 0.004337575286626816, | |
| "learning_rate": 2.2141706924315623e-06, | |
| "loss": 0.0003, | |
| "step": 2650 | |
| }, | |
| { | |
| "epoch": 28.020289855072463, | |
| "grad_norm": 0.014842136763036251, | |
| "learning_rate": 2.012882447665056e-06, | |
| "loss": 0.0004, | |
| "step": 2660 | |
| }, | |
| { | |
| "epoch": 28.02391304347826, | |
| "grad_norm": 2.614138603210449, | |
| "learning_rate": 1.8115942028985508e-06, | |
| "loss": 0.0216, | |
| "step": 2670 | |
| }, | |
| { | |
| "epoch": 28.027536231884056, | |
| "grad_norm": 0.004238471854478121, | |
| "learning_rate": 1.610305958132045e-06, | |
| "loss": 0.0048, | |
| "step": 2680 | |
| }, | |
| { | |
| "epoch": 28.031159420289853, | |
| "grad_norm": 0.006333829369395971, | |
| "learning_rate": 1.4090177133655396e-06, | |
| "loss": 0.0003, | |
| "step": 2690 | |
| }, | |
| { | |
| "epoch": 28.033695652173915, | |
| "eval_accuracy": 0.9016393442622951, | |
| "eval_f1": 0.90210919178688, | |
| "eval_loss": 0.723217248916626, | |
| "eval_runtime": 42.3468, | |
| "eval_samples_per_second": 2.881, | |
| "eval_steps_per_second": 0.378, | |
| "step": 2697 | |
| }, | |
| { | |
| "epoch": 29.00108695652174, | |
| "grad_norm": 0.00406339205801487, | |
| "learning_rate": 1.2077294685990338e-06, | |
| "loss": 0.0003, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 29.004710144927536, | |
| "grad_norm": 0.00470451544970274, | |
| "learning_rate": 1.006441223832528e-06, | |
| "loss": 0.0052, | |
| "step": 2710 | |
| }, | |
| { | |
| "epoch": 29.008333333333333, | |
| "grad_norm": 0.0051088836044073105, | |
| "learning_rate": 8.051529790660226e-07, | |
| "loss": 0.0003, | |
| "step": 2720 | |
| }, | |
| { | |
| "epoch": 29.01195652173913, | |
| "grad_norm": 0.00631117494776845, | |
| "learning_rate": 6.038647342995169e-07, | |
| "loss": 0.0054, | |
| "step": 2730 | |
| }, | |
| { | |
| "epoch": 29.015579710144927, | |
| "grad_norm": 0.006218273192644119, | |
| "learning_rate": 4.025764895330113e-07, | |
| "loss": 0.0003, | |
| "step": 2740 | |
| }, | |
| { | |
| "epoch": 29.019202898550724, | |
| "grad_norm": 0.004932409152388573, | |
| "learning_rate": 2.0128824476650564e-07, | |
| "loss": 0.0043, | |
| "step": 2750 | |
| }, | |
| { | |
| "epoch": 29.02282608695652, | |
| "grad_norm": 0.00396711053326726, | |
| "learning_rate": 0.0, | |
| "loss": 0.0177, | |
| "step": 2760 | |
| }, | |
| { | |
| "epoch": 29.02282608695652, | |
| "eval_accuracy": 0.9016393442622951, | |
| "eval_f1": 0.90210919178688, | |
| "eval_loss": 0.7259094715118408, | |
| "eval_runtime": 42.2094, | |
| "eval_samples_per_second": 2.89, | |
| "eval_steps_per_second": 0.379, | |
| "step": 2760 | |
| }, | |
| { | |
| "epoch": 29.02282608695652, | |
| "step": 2760, | |
| "total_flos": 2.7405187314155127e+19, | |
| "train_loss": 0.1748103732693657, | |
| "train_runtime": 10578.7771, | |
| "train_samples_per_second": 2.087, | |
| "train_steps_per_second": 0.261 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 2760, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 9223372036854775807, | |
| "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": 2.7405187314155127e+19, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |