| { | |
| "best_metric": 0.6601941747572816, | |
| "best_model_checkpoint": "videomae-large-finetuned-right-hand-conflab-v1/checkpoint-708", | |
| "epoch": 14.042022792022792, | |
| "eval_steps": 500, | |
| "global_step": 885, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.007122507122507123, | |
| "grad_norm": 12.899408340454102, | |
| "learning_rate": 3.5460992907801423e-06, | |
| "loss": 2.0965, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.014245014245014245, | |
| "grad_norm": 9.095556259155273, | |
| "learning_rate": 7.092198581560285e-06, | |
| "loss": 2.1002, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.021367521367521368, | |
| "grad_norm": 11.837288856506348, | |
| "learning_rate": 1.0638297872340426e-05, | |
| "loss": 1.9683, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.02849002849002849, | |
| "grad_norm": 8.063945770263672, | |
| "learning_rate": 1.418439716312057e-05, | |
| "loss": 1.9838, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.03561253561253561, | |
| "grad_norm": 7.636847972869873, | |
| "learning_rate": 1.773049645390071e-05, | |
| "loss": 2.0232, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.04202279202279202, | |
| "eval_accuracy": 0.1941747572815534, | |
| "eval_loss": 1.9421881437301636, | |
| "eval_runtime": 24.149, | |
| "eval_samples_per_second": 8.53, | |
| "eval_steps_per_second": 0.538, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 1.0007122507122508, | |
| "grad_norm": 7.21124267578125, | |
| "learning_rate": 2.1276595744680852e-05, | |
| "loss": 1.981, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 1.0078347578347577, | |
| "grad_norm": 8.352581977844238, | |
| "learning_rate": 2.4822695035460995e-05, | |
| "loss": 1.9465, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 1.014957264957265, | |
| "grad_norm": 8.361379623413086, | |
| "learning_rate": 2.836879432624114e-05, | |
| "loss": 1.962, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 1.022079772079772, | |
| "grad_norm": 5.388889312744141, | |
| "learning_rate": 3.191489361702128e-05, | |
| "loss": 1.976, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 1.0292022792022792, | |
| "grad_norm": 5.553725719451904, | |
| "learning_rate": 3.546099290780142e-05, | |
| "loss": 2.0058, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.0363247863247864, | |
| "grad_norm": 6.278877258300781, | |
| "learning_rate": 3.900709219858156e-05, | |
| "loss": 1.8426, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 1.042022792022792, | |
| "eval_accuracy": 0.33980582524271846, | |
| "eval_loss": 1.7418017387390137, | |
| "eval_runtime": 19.8724, | |
| "eval_samples_per_second": 10.366, | |
| "eval_steps_per_second": 0.654, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 2.0014245014245016, | |
| "grad_norm": 5.7616729736328125, | |
| "learning_rate": 4.2553191489361704e-05, | |
| "loss": 1.9192, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 2.0085470085470085, | |
| "grad_norm": 6.886305332183838, | |
| "learning_rate": 4.609929078014185e-05, | |
| "loss": 1.8077, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 2.0156695156695155, | |
| "grad_norm": 12.934743881225586, | |
| "learning_rate": 4.964539007092199e-05, | |
| "loss": 1.6519, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 2.022792022792023, | |
| "grad_norm": 9.393815994262695, | |
| "learning_rate": 4.96437054631829e-05, | |
| "loss": 1.6934, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 2.02991452991453, | |
| "grad_norm": 10.663277626037598, | |
| "learning_rate": 4.924782264449723e-05, | |
| "loss": 1.7591, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 2.037037037037037, | |
| "grad_norm": 6.719297885894775, | |
| "learning_rate": 4.885193982581156e-05, | |
| "loss": 1.7424, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 2.042022792022792, | |
| "eval_accuracy": 0.4174757281553398, | |
| "eval_loss": 1.6896483898162842, | |
| "eval_runtime": 17.8016, | |
| "eval_samples_per_second": 11.572, | |
| "eval_steps_per_second": 0.73, | |
| "step": 177 | |
| }, | |
| { | |
| "epoch": 3.002136752136752, | |
| "grad_norm": 5.332315921783447, | |
| "learning_rate": 4.845605700712589e-05, | |
| "loss": 1.7511, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 3.009259259259259, | |
| "grad_norm": 9.056990623474121, | |
| "learning_rate": 4.806017418844022e-05, | |
| "loss": 1.6771, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 3.0163817663817665, | |
| "grad_norm": 10.588340759277344, | |
| "learning_rate": 4.766429136975455e-05, | |
| "loss": 1.4029, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 3.0235042735042734, | |
| "grad_norm": 17.486988067626953, | |
| "learning_rate": 4.7268408551068886e-05, | |
| "loss": 1.4862, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 3.030626780626781, | |
| "grad_norm": 7.175242900848389, | |
| "learning_rate": 4.687252573238321e-05, | |
| "loss": 1.4282, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 3.0377492877492878, | |
| "grad_norm": 8.013775825500488, | |
| "learning_rate": 4.647664291369755e-05, | |
| "loss": 1.2206, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 3.042022792022792, | |
| "eval_accuracy": 0.44660194174757284, | |
| "eval_loss": 1.628009557723999, | |
| "eval_runtime": 21.5993, | |
| "eval_samples_per_second": 9.537, | |
| "eval_steps_per_second": 0.602, | |
| "step": 236 | |
| }, | |
| { | |
| "epoch": 4.002849002849003, | |
| "grad_norm": 8.972482681274414, | |
| "learning_rate": 4.6080760095011874e-05, | |
| "loss": 1.6023, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 4.00997150997151, | |
| "grad_norm": 7.669183731079102, | |
| "learning_rate": 4.568487727632621e-05, | |
| "loss": 1.1725, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 4.017094017094017, | |
| "grad_norm": 7.465898513793945, | |
| "learning_rate": 4.528899445764054e-05, | |
| "loss": 1.2957, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 4.024216524216524, | |
| "grad_norm": 5.810666561126709, | |
| "learning_rate": 4.4893111638954874e-05, | |
| "loss": 1.3387, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 4.031339031339031, | |
| "grad_norm": 8.172585487365723, | |
| "learning_rate": 4.44972288202692e-05, | |
| "loss": 1.2668, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 4.038461538461538, | |
| "grad_norm": 7.007075309753418, | |
| "learning_rate": 4.4101346001583535e-05, | |
| "loss": 1.0738, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 4.042022792022792, | |
| "eval_accuracy": 0.5825242718446602, | |
| "eval_loss": 1.2310322523117065, | |
| "eval_runtime": 18.9007, | |
| "eval_samples_per_second": 10.899, | |
| "eval_steps_per_second": 0.688, | |
| "step": 295 | |
| }, | |
| { | |
| "epoch": 5.003561253561253, | |
| "grad_norm": 4.775450229644775, | |
| "learning_rate": 4.370546318289787e-05, | |
| "loss": 1.0455, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 5.010683760683761, | |
| "grad_norm": 9.440917015075684, | |
| "learning_rate": 4.3309580364212195e-05, | |
| "loss": 0.99, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 5.017806267806268, | |
| "grad_norm": 5.092905521392822, | |
| "learning_rate": 4.291369754552653e-05, | |
| "loss": 0.9873, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 5.0249287749287745, | |
| "grad_norm": 8.457822799682617, | |
| "learning_rate": 4.2517814726840856e-05, | |
| "loss": 0.8012, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 5.032051282051282, | |
| "grad_norm": 6.717366695404053, | |
| "learning_rate": 4.212193190815519e-05, | |
| "loss": 0.9262, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 5.039173789173789, | |
| "grad_norm": 6.962019920349121, | |
| "learning_rate": 4.172604908946952e-05, | |
| "loss": 1.0054, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 5.042022792022792, | |
| "eval_accuracy": 0.558252427184466, | |
| "eval_loss": 1.3242673873901367, | |
| "eval_runtime": 20.0158, | |
| "eval_samples_per_second": 10.292, | |
| "eval_steps_per_second": 0.649, | |
| "step": 354 | |
| }, | |
| { | |
| "epoch": 6.004273504273504, | |
| "grad_norm": 17.063520431518555, | |
| "learning_rate": 4.133016627078385e-05, | |
| "loss": 0.8909, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 6.011396011396012, | |
| "grad_norm": 8.150900840759277, | |
| "learning_rate": 4.093428345209818e-05, | |
| "loss": 0.89, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 6.018518518518518, | |
| "grad_norm": 8.059175491333008, | |
| "learning_rate": 4.053840063341251e-05, | |
| "loss": 0.7925, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 6.0256410256410255, | |
| "grad_norm": 7.513158798217773, | |
| "learning_rate": 4.0142517814726843e-05, | |
| "loss": 0.853, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 6.032763532763533, | |
| "grad_norm": 6.1937971115112305, | |
| "learning_rate": 3.974663499604117e-05, | |
| "loss": 0.7338, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 6.0398860398860394, | |
| "grad_norm": 5.745666980743408, | |
| "learning_rate": 3.9350752177355504e-05, | |
| "loss": 0.782, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 6.042022792022792, | |
| "eval_accuracy": 0.6359223300970874, | |
| "eval_loss": 1.1890981197357178, | |
| "eval_runtime": 19.1994, | |
| "eval_samples_per_second": 10.73, | |
| "eval_steps_per_second": 0.677, | |
| "step": 413 | |
| }, | |
| { | |
| "epoch": 7.004985754985755, | |
| "grad_norm": 7.788235187530518, | |
| "learning_rate": 3.895486935866984e-05, | |
| "loss": 0.745, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 7.012108262108262, | |
| "grad_norm": 8.95632553100586, | |
| "learning_rate": 3.8558986539984164e-05, | |
| "loss": 0.6315, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 7.019230769230769, | |
| "grad_norm": 9.59426498413086, | |
| "learning_rate": 3.81631037212985e-05, | |
| "loss": 0.6792, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 7.0263532763532766, | |
| "grad_norm": 7.637509822845459, | |
| "learning_rate": 3.7767220902612825e-05, | |
| "loss": 0.5733, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 7.033475783475783, | |
| "grad_norm": 10.775083541870117, | |
| "learning_rate": 3.737133808392716e-05, | |
| "loss": 0.7303, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 7.0405982905982905, | |
| "grad_norm": 6.580932140350342, | |
| "learning_rate": 3.6975455265241485e-05, | |
| "loss": 0.599, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 7.042022792022792, | |
| "eval_accuracy": 0.6504854368932039, | |
| "eval_loss": 1.193009376525879, | |
| "eval_runtime": 20.2931, | |
| "eval_samples_per_second": 10.151, | |
| "eval_steps_per_second": 0.641, | |
| "step": 472 | |
| }, | |
| { | |
| "epoch": 8.005698005698006, | |
| "grad_norm": 8.682097434997559, | |
| "learning_rate": 3.657957244655582e-05, | |
| "loss": 0.4704, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 8.012820512820513, | |
| "grad_norm": 8.527168273925781, | |
| "learning_rate": 3.618368962787015e-05, | |
| "loss": 0.6392, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 8.01994301994302, | |
| "grad_norm": 6.198835849761963, | |
| "learning_rate": 3.578780680918448e-05, | |
| "loss": 0.3972, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 8.027065527065528, | |
| "grad_norm": 6.177005290985107, | |
| "learning_rate": 3.539192399049881e-05, | |
| "loss": 0.4873, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 8.034188034188034, | |
| "grad_norm": 9.330336570739746, | |
| "learning_rate": 3.4996041171813146e-05, | |
| "loss": 0.4534, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 8.04131054131054, | |
| "grad_norm": 5.25494384765625, | |
| "learning_rate": 3.460015835312748e-05, | |
| "loss": 0.6782, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 8.042022792022792, | |
| "eval_accuracy": 0.6359223300970874, | |
| "eval_loss": 1.2866381406784058, | |
| "eval_runtime": 19.101, | |
| "eval_samples_per_second": 10.785, | |
| "eval_steps_per_second": 0.681, | |
| "step": 531 | |
| }, | |
| { | |
| "epoch": 9.006410256410257, | |
| "grad_norm": 5.766805648803711, | |
| "learning_rate": 3.4204275534441806e-05, | |
| "loss": 0.392, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 9.013532763532764, | |
| "grad_norm": 11.340324401855469, | |
| "learning_rate": 3.380839271575614e-05, | |
| "loss": 0.4548, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 9.02065527065527, | |
| "grad_norm": 10.191842079162598, | |
| "learning_rate": 3.3412509897070474e-05, | |
| "loss": 0.3105, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 9.027777777777779, | |
| "grad_norm": 5.949177265167236, | |
| "learning_rate": 3.30166270783848e-05, | |
| "loss": 0.4979, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 9.034900284900285, | |
| "grad_norm": 11.043278694152832, | |
| "learning_rate": 3.2620744259699134e-05, | |
| "loss": 0.3972, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 9.042022792022792, | |
| "grad_norm": 16.354900360107422, | |
| "learning_rate": 3.222486144101346e-05, | |
| "loss": 0.3033, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 9.042022792022792, | |
| "eval_accuracy": 0.5776699029126213, | |
| "eval_loss": 1.423584222793579, | |
| "eval_runtime": 20.9024, | |
| "eval_samples_per_second": 9.855, | |
| "eval_steps_per_second": 0.622, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 10.007122507122507, | |
| "grad_norm": 1.9087872505187988, | |
| "learning_rate": 3.1828978622327794e-05, | |
| "loss": 0.1958, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 10.014245014245015, | |
| "grad_norm": 6.443134307861328, | |
| "learning_rate": 3.143309580364212e-05, | |
| "loss": 0.2865, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 10.021367521367521, | |
| "grad_norm": 5.271445274353027, | |
| "learning_rate": 3.1037212984956455e-05, | |
| "loss": 0.2709, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 10.028490028490028, | |
| "grad_norm": 5.430334568023682, | |
| "learning_rate": 3.064133016627079e-05, | |
| "loss": 0.3552, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 10.035612535612536, | |
| "grad_norm": 8.00438117980957, | |
| "learning_rate": 3.0245447347585115e-05, | |
| "loss": 0.2236, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 10.042022792022792, | |
| "eval_accuracy": 0.6553398058252428, | |
| "eval_loss": 1.3206462860107422, | |
| "eval_runtime": 18.1657, | |
| "eval_samples_per_second": 11.34, | |
| "eval_steps_per_second": 0.716, | |
| "step": 649 | |
| }, | |
| { | |
| "epoch": 11.000712250712251, | |
| "grad_norm": 8.367637634277344, | |
| "learning_rate": 2.984956452889945e-05, | |
| "loss": 0.2997, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 11.007834757834758, | |
| "grad_norm": 4.96151065826416, | |
| "learning_rate": 2.9453681710213776e-05, | |
| "loss": 0.2366, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 11.014957264957266, | |
| "grad_norm": 4.967086315155029, | |
| "learning_rate": 2.905779889152811e-05, | |
| "loss": 0.2191, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 11.022079772079772, | |
| "grad_norm": 5.6478095054626465, | |
| "learning_rate": 2.8661916072842436e-05, | |
| "loss": 0.2042, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 11.029202279202279, | |
| "grad_norm": 15.652437210083008, | |
| "learning_rate": 2.826603325415677e-05, | |
| "loss": 0.2747, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 11.036324786324787, | |
| "grad_norm": 4.030658721923828, | |
| "learning_rate": 2.7870150435471103e-05, | |
| "loss": 0.1756, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 11.042022792022792, | |
| "eval_accuracy": 0.6601941747572816, | |
| "eval_loss": 1.5112863779067993, | |
| "eval_runtime": 18.776, | |
| "eval_samples_per_second": 10.971, | |
| "eval_steps_per_second": 0.692, | |
| "step": 708 | |
| }, | |
| { | |
| "epoch": 12.001424501424502, | |
| "grad_norm": 3.84013295173645, | |
| "learning_rate": 2.7474267616785433e-05, | |
| "loss": 0.1714, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 12.008547008547009, | |
| "grad_norm": 5.428359508514404, | |
| "learning_rate": 2.7078384798099763e-05, | |
| "loss": 0.2056, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 12.015669515669515, | |
| "grad_norm": 5.529027938842773, | |
| "learning_rate": 2.6682501979414094e-05, | |
| "loss": 0.1018, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 12.022792022792023, | |
| "grad_norm": 5.976778984069824, | |
| "learning_rate": 2.6286619160728427e-05, | |
| "loss": 0.0961, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 12.02991452991453, | |
| "grad_norm": 6.043054580688477, | |
| "learning_rate": 2.5890736342042754e-05, | |
| "loss": 0.2393, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 12.037037037037036, | |
| "grad_norm": 4.8577656745910645, | |
| "learning_rate": 2.5494853523357088e-05, | |
| "loss": 0.1341, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 12.042022792022792, | |
| "eval_accuracy": 0.6407766990291263, | |
| "eval_loss": 1.6544133424758911, | |
| "eval_runtime": 18.7553, | |
| "eval_samples_per_second": 10.984, | |
| "eval_steps_per_second": 0.693, | |
| "step": 767 | |
| }, | |
| { | |
| "epoch": 13.002136752136753, | |
| "grad_norm": 3.0963165760040283, | |
| "learning_rate": 2.509897070467142e-05, | |
| "loss": 0.1632, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 13.00925925925926, | |
| "grad_norm": 1.0908960103988647, | |
| "learning_rate": 2.4703087885985748e-05, | |
| "loss": 0.1377, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 13.016381766381766, | |
| "grad_norm": 13.51460075378418, | |
| "learning_rate": 2.4307205067300078e-05, | |
| "loss": 0.1605, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 13.023504273504274, | |
| "grad_norm": 3.4943864345550537, | |
| "learning_rate": 2.3911322248614412e-05, | |
| "loss": 0.1576, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 13.03062678062678, | |
| "grad_norm": 3.6334426403045654, | |
| "learning_rate": 2.3515439429928742e-05, | |
| "loss": 0.1366, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 13.037749287749287, | |
| "grad_norm": 1.571234107017517, | |
| "learning_rate": 2.3119556611243072e-05, | |
| "loss": 0.0823, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 13.042022792022792, | |
| "eval_accuracy": 0.6553398058252428, | |
| "eval_loss": 1.61236572265625, | |
| "eval_runtime": 18.782, | |
| "eval_samples_per_second": 10.968, | |
| "eval_steps_per_second": 0.692, | |
| "step": 826 | |
| }, | |
| { | |
| "epoch": 14.002849002849002, | |
| "grad_norm": 6.992094039916992, | |
| "learning_rate": 2.2723673792557402e-05, | |
| "loss": 0.0825, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 14.00997150997151, | |
| "grad_norm": 0.7775176763534546, | |
| "learning_rate": 2.2327790973871736e-05, | |
| "loss": 0.0993, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 14.017094017094017, | |
| "grad_norm": 5.0337700843811035, | |
| "learning_rate": 2.1931908155186066e-05, | |
| "loss": 0.0713, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 14.024216524216524, | |
| "grad_norm": 0.6653324365615845, | |
| "learning_rate": 2.1536025336500396e-05, | |
| "loss": 0.1065, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 14.031339031339032, | |
| "grad_norm": 11.971256256103516, | |
| "learning_rate": 2.114014251781473e-05, | |
| "loss": 0.144, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 14.038461538461538, | |
| "grad_norm": 10.947636604309082, | |
| "learning_rate": 2.074425969912906e-05, | |
| "loss": 0.0691, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 14.042022792022792, | |
| "eval_accuracy": 0.6456310679611651, | |
| "eval_loss": 1.8230090141296387, | |
| "eval_runtime": 17.8025, | |
| "eval_samples_per_second": 11.571, | |
| "eval_steps_per_second": 0.73, | |
| "step": 885 | |
| }, | |
| { | |
| "epoch": 14.042022792022792, | |
| "step": 885, | |
| "total_flos": 6.204645759270519e+19, | |
| "train_loss": 0.8409665932847281, | |
| "train_runtime": 3290.4789, | |
| "train_samples_per_second": 6.827, | |
| "train_steps_per_second": 0.427 | |
| }, | |
| { | |
| "epoch": 14.042022792022792, | |
| "eval_accuracy": 0.6146341463414634, | |
| "eval_loss": 1.5203598737716675, | |
| "eval_runtime": 24.6199, | |
| "eval_samples_per_second": 8.327, | |
| "eval_steps_per_second": 0.528, | |
| "step": 885 | |
| }, | |
| { | |
| "epoch": 14.042022792022792, | |
| "eval_accuracy": 0.6146341463414634, | |
| "eval_loss": 1.5239903926849365, | |
| "eval_runtime": 17.6083, | |
| "eval_samples_per_second": 11.642, | |
| "eval_steps_per_second": 0.738, | |
| "step": 885 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 1404, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 9223372036854775807, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 3, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 6.204645759270519e+19, | |
| "train_batch_size": 16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |