| { | |
| "best_metric": NaN, | |
| "best_model_checkpoint": "mobilebert_sa_pre-training-complete/checkpoint-1787", | |
| "epoch": 167.87912702853944, | |
| "global_step": 300000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 4.9746415471823945e-05, | |
| "loss": 0.0, | |
| "step": 1787 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.6389621318373071, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2.565, | |
| "eval_samples_per_second": 186.748, | |
| "eval_steps_per_second": 1.559, | |
| "step": 1787 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 4.9448482827609205e-05, | |
| "loss": 0.0, | |
| "step": 3574 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.6426345489766697, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2.5231, | |
| "eval_samples_per_second": 189.849, | |
| "eval_steps_per_second": 1.585, | |
| "step": 3574 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 4.9150550183394464e-05, | |
| "loss": 0.0, | |
| "step": 5361 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.6414778901613307, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2.3803, | |
| "eval_samples_per_second": 201.236, | |
| "eval_steps_per_second": 1.68, | |
| "step": 5361 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "learning_rate": 4.885261753917973e-05, | |
| "loss": 0.0, | |
| "step": 7148 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.6339985546722997, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2.2859, | |
| "eval_samples_per_second": 209.542, | |
| "eval_steps_per_second": 1.75, | |
| "step": 7148 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "learning_rate": 4.855468489496499e-05, | |
| "loss": 0.0, | |
| "step": 8935 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.6359570661896243, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2.5196, | |
| "eval_samples_per_second": 190.108, | |
| "eval_steps_per_second": 1.588, | |
| "step": 8935 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "learning_rate": 4.825675225075025e-05, | |
| "loss": 0.0, | |
| "step": 10722 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.6341442999832598, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2.687, | |
| "eval_samples_per_second": 178.265, | |
| "eval_steps_per_second": 1.489, | |
| "step": 10722 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "learning_rate": 4.795881960653552e-05, | |
| "loss": 0.0, | |
| "step": 12509 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_accuracy": 0.6378068416146436, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2.4684, | |
| "eval_samples_per_second": 194.049, | |
| "eval_steps_per_second": 1.62, | |
| "step": 12509 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "learning_rate": 4.766088696232078e-05, | |
| "loss": 0.0, | |
| "step": 14296 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.6334561982096832, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2.4312, | |
| "eval_samples_per_second": 197.02, | |
| "eval_steps_per_second": 1.645, | |
| "step": 14296 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "learning_rate": 4.736295431810604e-05, | |
| "loss": 0.0, | |
| "step": 16083 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_accuracy": 0.6362770101734817, | |
| "eval_loss": NaN, | |
| "eval_runtime": 1.8926, | |
| "eval_samples_per_second": 253.092, | |
| "eval_steps_per_second": 2.114, | |
| "step": 16083 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "learning_rate": 4.70650216738913e-05, | |
| "loss": 0.0, | |
| "step": 17870 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_accuracy": 0.6382731776362349, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2.2948, | |
| "eval_samples_per_second": 208.735, | |
| "eval_steps_per_second": 1.743, | |
| "step": 17870 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "learning_rate": 4.6767089029676556e-05, | |
| "loss": 0.0, | |
| "step": 19657 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_accuracy": 0.6379281255272482, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2.498, | |
| "eval_samples_per_second": 191.754, | |
| "eval_steps_per_second": 1.601, | |
| "step": 19657 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "learning_rate": 4.646915638546182e-05, | |
| "loss": 0.0, | |
| "step": 21444 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_accuracy": 0.6346471430144226, | |
| "eval_loss": NaN, | |
| "eval_runtime": 1.9097, | |
| "eval_samples_per_second": 250.823, | |
| "eval_steps_per_second": 2.095, | |
| "step": 21444 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "learning_rate": 4.617122374124708e-05, | |
| "loss": 0.0006, | |
| "step": 23231 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_accuracy": 0.6408630160258225, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2.4081, | |
| "eval_samples_per_second": 198.912, | |
| "eval_steps_per_second": 1.661, | |
| "step": 23231 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "learning_rate": 4.587329109703234e-05, | |
| "loss": 0.0, | |
| "step": 25018 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_accuracy": 0.6406372714013239, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2.3337, | |
| "eval_samples_per_second": 205.253, | |
| "eval_steps_per_second": 1.714, | |
| "step": 25018 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "learning_rate": 4.557535845281761e-05, | |
| "loss": 0.0, | |
| "step": 26805 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "eval_accuracy": 0.6322750589213919, | |
| "eval_loss": NaN, | |
| "eval_runtime": 1.8775, | |
| "eval_samples_per_second": 255.123, | |
| "eval_steps_per_second": 2.13, | |
| "step": 26805 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "learning_rate": 4.527742580860287e-05, | |
| "loss": 0.0, | |
| "step": 28592 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_accuracy": 0.6402202163038314, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2.3437, | |
| "eval_samples_per_second": 204.38, | |
| "eval_steps_per_second": 1.707, | |
| "step": 28592 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "learning_rate": 4.497949316438813e-05, | |
| "loss": 0.0, | |
| "step": 30379 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "eval_accuracy": 0.6400190007823852, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2.3387, | |
| "eval_samples_per_second": 204.815, | |
| "eval_steps_per_second": 1.71, | |
| "step": 30379 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "learning_rate": 4.4681560520173395e-05, | |
| "loss": 0.0, | |
| "step": 32166 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "eval_accuracy": 0.632776553916511, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2.9244, | |
| "eval_samples_per_second": 163.796, | |
| "eval_steps_per_second": 1.368, | |
| "step": 32166 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "learning_rate": 4.4383627875958655e-05, | |
| "loss": 0.0, | |
| "step": 33953 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "eval_accuracy": 0.6352045133991537, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2.3016, | |
| "eval_samples_per_second": 208.113, | |
| "eval_steps_per_second": 1.738, | |
| "step": 33953 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "learning_rate": 4.4085695231743915e-05, | |
| "loss": 0.0, | |
| "step": 35740 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_accuracy": 0.6380321611988887, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2.3407, | |
| "eval_samples_per_second": 204.636, | |
| "eval_steps_per_second": 1.709, | |
| "step": 35740 | |
| }, | |
| { | |
| "epoch": 21.0, | |
| "learning_rate": 4.378776258752918e-05, | |
| "loss": 0.0, | |
| "step": 37527 | |
| }, | |
| { | |
| "epoch": 21.0, | |
| "eval_accuracy": 0.6462707571066704, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2.3673, | |
| "eval_samples_per_second": 202.344, | |
| "eval_steps_per_second": 1.69, | |
| "step": 37527 | |
| }, | |
| { | |
| "epoch": 22.0, | |
| "learning_rate": 4.348982994331444e-05, | |
| "loss": 0.0, | |
| "step": 39314 | |
| }, | |
| { | |
| "epoch": 22.0, | |
| "eval_accuracy": 0.6313444886822396, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2.3572, | |
| "eval_samples_per_second": 203.209, | |
| "eval_steps_per_second": 1.697, | |
| "step": 39314 | |
| }, | |
| { | |
| "epoch": 23.0, | |
| "learning_rate": 4.31918972990997e-05, | |
| "loss": 0.0, | |
| "step": 41101 | |
| }, | |
| { | |
| "epoch": 23.0, | |
| "eval_accuracy": 0.6385646226283677, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2.3089, | |
| "eval_samples_per_second": 207.457, | |
| "eval_steps_per_second": 1.732, | |
| "step": 41101 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "learning_rate": 4.289396465488497e-05, | |
| "loss": 0.0, | |
| "step": 42888 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "eval_accuracy": 0.6412596473438116, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2.2196, | |
| "eval_samples_per_second": 215.801, | |
| "eval_steps_per_second": 1.802, | |
| "step": 42888 | |
| }, | |
| { | |
| "epoch": 25.0, | |
| "learning_rate": 4.259603201067023e-05, | |
| "loss": 0.0, | |
| "step": 44675 | |
| }, | |
| { | |
| "epoch": 25.0, | |
| "eval_accuracy": 0.6323012458168115, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2.4055, | |
| "eval_samples_per_second": 199.128, | |
| "eval_steps_per_second": 1.663, | |
| "step": 44675 | |
| }, | |
| { | |
| "epoch": 26.0, | |
| "learning_rate": 4.229809936645549e-05, | |
| "loss": 0.0008, | |
| "step": 46462 | |
| }, | |
| { | |
| "epoch": 26.0, | |
| "eval_accuracy": 0.6358967122901087, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2.3859, | |
| "eval_samples_per_second": 200.764, | |
| "eval_steps_per_second": 1.677, | |
| "step": 46462 | |
| }, | |
| { | |
| "epoch": 27.0, | |
| "learning_rate": 4.200016672224075e-05, | |
| "loss": 0.0, | |
| "step": 48249 | |
| }, | |
| { | |
| "epoch": 27.0, | |
| "eval_accuracy": 0.6397165131112686, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2.5031, | |
| "eval_samples_per_second": 191.366, | |
| "eval_steps_per_second": 1.598, | |
| "step": 48249 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "learning_rate": 4.170223407802601e-05, | |
| "loss": 0.0, | |
| "step": 50036 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "eval_accuracy": 0.6377492196507409, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2.4488, | |
| "eval_samples_per_second": 195.602, | |
| "eval_steps_per_second": 1.633, | |
| "step": 50036 | |
| }, | |
| { | |
| "epoch": 29.0, | |
| "learning_rate": 4.1404301433811273e-05, | |
| "loss": 0.0, | |
| "step": 51823 | |
| }, | |
| { | |
| "epoch": 29.0, | |
| "eval_accuracy": 0.6382942861958537, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2.4323, | |
| "eval_samples_per_second": 196.929, | |
| "eval_steps_per_second": 1.645, | |
| "step": 51823 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "learning_rate": 4.110636878959653e-05, | |
| "loss": 0.0, | |
| "step": 53610 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "eval_accuracy": 0.6374012291483757, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2.584, | |
| "eval_samples_per_second": 185.372, | |
| "eval_steps_per_second": 1.548, | |
| "step": 53610 | |
| }, | |
| { | |
| "epoch": 31.0, | |
| "learning_rate": 4.080843614538179e-05, | |
| "loss": 0.0, | |
| "step": 55397 | |
| }, | |
| { | |
| "epoch": 31.0, | |
| "eval_accuracy": 0.6475859910666022, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2.4306, | |
| "eval_samples_per_second": 197.073, | |
| "eval_steps_per_second": 1.646, | |
| "step": 55397 | |
| }, | |
| { | |
| "epoch": 32.0, | |
| "learning_rate": 4.051050350116706e-05, | |
| "loss": 0.0, | |
| "step": 57184 | |
| }, | |
| { | |
| "epoch": 32.0, | |
| "eval_accuracy": 0.6304695249641794, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2.4506, | |
| "eval_samples_per_second": 195.466, | |
| "eval_steps_per_second": 1.632, | |
| "step": 57184 | |
| }, | |
| { | |
| "epoch": 33.0, | |
| "learning_rate": 4.021257085695232e-05, | |
| "loss": 0.0011, | |
| "step": 58971 | |
| }, | |
| { | |
| "epoch": 33.0, | |
| "eval_accuracy": 0.6451093860268172, | |
| "eval_loss": NaN, | |
| "eval_runtime": 3.4567, | |
| "eval_samples_per_second": 138.57, | |
| "eval_steps_per_second": 1.157, | |
| "step": 58971 | |
| }, | |
| { | |
| "epoch": 34.0, | |
| "learning_rate": 3.991463821273758e-05, | |
| "loss": 0.0, | |
| "step": 60758 | |
| }, | |
| { | |
| "epoch": 34.0, | |
| "eval_accuracy": 0.6371792721784336, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2.3878, | |
| "eval_samples_per_second": 200.599, | |
| "eval_steps_per_second": 1.675, | |
| "step": 60758 | |
| }, | |
| { | |
| "epoch": 35.0, | |
| "learning_rate": 3.9616705568522846e-05, | |
| "loss": 0.0, | |
| "step": 62545 | |
| }, | |
| { | |
| "epoch": 35.0, | |
| "eval_accuracy": 0.6368389980602176, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2.369, | |
| "eval_samples_per_second": 202.197, | |
| "eval_steps_per_second": 1.688, | |
| "step": 62545 | |
| }, | |
| { | |
| "epoch": 36.0, | |
| "learning_rate": 3.9318772924308106e-05, | |
| "loss": 0.0006, | |
| "step": 64332 | |
| }, | |
| { | |
| "epoch": 36.0, | |
| "eval_accuracy": 0.6385094217390079, | |
| "eval_loss": NaN, | |
| "eval_runtime": 1.8468, | |
| "eval_samples_per_second": 259.365, | |
| "eval_steps_per_second": 2.166, | |
| "step": 64332 | |
| }, | |
| { | |
| "epoch": 37.0, | |
| "learning_rate": 3.9020840280093365e-05, | |
| "loss": 0.0, | |
| "step": 66119 | |
| }, | |
| { | |
| "epoch": 37.0, | |
| "eval_accuracy": 0.63491709005639, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2.4159, | |
| "eval_samples_per_second": 198.273, | |
| "eval_steps_per_second": 1.656, | |
| "step": 66119 | |
| }, | |
| { | |
| "epoch": 38.0, | |
| "learning_rate": 3.872290763587863e-05, | |
| "loss": 0.0, | |
| "step": 67906 | |
| }, | |
| { | |
| "epoch": 38.0, | |
| "eval_accuracy": 0.6334269272469489, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2.5332, | |
| "eval_samples_per_second": 189.086, | |
| "eval_steps_per_second": 1.579, | |
| "step": 67906 | |
| }, | |
| { | |
| "epoch": 39.0, | |
| "learning_rate": 3.842497499166389e-05, | |
| "loss": 0.0, | |
| "step": 69693 | |
| }, | |
| { | |
| "epoch": 39.0, | |
| "eval_accuracy": 0.639051440673243, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2.9795, | |
| "eval_samples_per_second": 160.763, | |
| "eval_steps_per_second": 1.342, | |
| "step": 69693 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "learning_rate": 3.812704234744915e-05, | |
| "loss": 0.0, | |
| "step": 71480 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "eval_accuracy": 0.6345379279480868, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2.2745, | |
| "eval_samples_per_second": 210.596, | |
| "eval_steps_per_second": 1.759, | |
| "step": 71480 | |
| }, | |
| { | |
| "epoch": 41.0, | |
| "learning_rate": 3.782910970323441e-05, | |
| "loss": 0.0, | |
| "step": 73267 | |
| }, | |
| { | |
| "epoch": 41.0, | |
| "eval_accuracy": 0.6423277130247822, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2.3025, | |
| "eval_samples_per_second": 208.034, | |
| "eval_steps_per_second": 1.737, | |
| "step": 73267 | |
| }, | |
| { | |
| "epoch": 42.0, | |
| "learning_rate": 3.753117705901967e-05, | |
| "loss": 0.0, | |
| "step": 75054 | |
| }, | |
| { | |
| "epoch": 42.0, | |
| "eval_accuracy": 0.6374992997591171, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2.2992, | |
| "eval_samples_per_second": 208.332, | |
| "eval_steps_per_second": 1.74, | |
| "step": 75054 | |
| }, | |
| { | |
| "epoch": 43.0, | |
| "learning_rate": 3.723324441480494e-05, | |
| "loss": 0.0, | |
| "step": 76841 | |
| }, | |
| { | |
| "epoch": 43.0, | |
| "eval_accuracy": 0.6292381720579646, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2.3504, | |
| "eval_samples_per_second": 203.794, | |
| "eval_steps_per_second": 1.702, | |
| "step": 76841 | |
| }, | |
| { | |
| "epoch": 44.0, | |
| "learning_rate": 3.69353117705902e-05, | |
| "loss": 0.0, | |
| "step": 78628 | |
| }, | |
| { | |
| "epoch": 44.0, | |
| "eval_accuracy": 0.6336636427076064, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2.1818, | |
| "eval_samples_per_second": 219.543, | |
| "eval_steps_per_second": 1.833, | |
| "step": 78628 | |
| }, | |
| { | |
| "epoch": 45.0, | |
| "learning_rate": 3.663737912637546e-05, | |
| "loss": 0.0, | |
| "step": 80415 | |
| }, | |
| { | |
| "epoch": 45.0, | |
| "eval_accuracy": 0.6451018731049335, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2.2283, | |
| "eval_samples_per_second": 214.958, | |
| "eval_steps_per_second": 1.795, | |
| "step": 80415 | |
| }, | |
| { | |
| "epoch": 46.0, | |
| "learning_rate": 3.6339446482160724e-05, | |
| "loss": 0.0, | |
| "step": 82202 | |
| }, | |
| { | |
| "epoch": 46.0, | |
| "eval_accuracy": 0.6376266844860229, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2.9896, | |
| "eval_samples_per_second": 160.224, | |
| "eval_steps_per_second": 1.338, | |
| "step": 82202 | |
| }, | |
| { | |
| "epoch": 47.0, | |
| "learning_rate": 3.6041513837945984e-05, | |
| "loss": 0.0, | |
| "step": 83989 | |
| }, | |
| { | |
| "epoch": 47.0, | |
| "eval_accuracy": 0.6354616290150793, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2.3984, | |
| "eval_samples_per_second": 199.716, | |
| "eval_steps_per_second": 1.668, | |
| "step": 83989 | |
| }, | |
| { | |
| "epoch": 48.0, | |
| "learning_rate": 3.5743581193731244e-05, | |
| "loss": 0.0, | |
| "step": 85776 | |
| }, | |
| { | |
| "epoch": 48.0, | |
| "eval_accuracy": 0.64114792031153, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2.2, | |
| "eval_samples_per_second": 217.728, | |
| "eval_steps_per_second": 1.818, | |
| "step": 85776 | |
| }, | |
| { | |
| "epoch": 49.0, | |
| "learning_rate": 3.544564854951651e-05, | |
| "loss": 0.0, | |
| "step": 87563 | |
| }, | |
| { | |
| "epoch": 49.0, | |
| "eval_accuracy": 0.6358090934764191, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2.0902, | |
| "eval_samples_per_second": 229.163, | |
| "eval_steps_per_second": 1.914, | |
| "step": 87563 | |
| }, | |
| { | |
| "epoch": 50.0, | |
| "learning_rate": 3.514771590530177e-05, | |
| "loss": 0.0, | |
| "step": 89350 | |
| }, | |
| { | |
| "epoch": 50.0, | |
| "eval_accuracy": 0.64278059785674, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2.0804, | |
| "eval_samples_per_second": 230.249, | |
| "eval_steps_per_second": 1.923, | |
| "step": 89350 | |
| }, | |
| { | |
| "epoch": 51.0, | |
| "learning_rate": 3.484978326108703e-05, | |
| "loss": 0.0, | |
| "step": 91137 | |
| }, | |
| { | |
| "epoch": 51.0, | |
| "eval_accuracy": 0.6421150697306759, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2.0459, | |
| "eval_samples_per_second": 234.122, | |
| "eval_steps_per_second": 1.955, | |
| "step": 91137 | |
| }, | |
| { | |
| "epoch": 52.0, | |
| "learning_rate": 3.4551850616872296e-05, | |
| "loss": 0.004, | |
| "step": 92924 | |
| }, | |
| { | |
| "epoch": 52.0, | |
| "eval_accuracy": 0.6352199471785989, | |
| "eval_loss": NaN, | |
| "eval_runtime": 1.9574, | |
| "eval_samples_per_second": 244.709, | |
| "eval_steps_per_second": 2.044, | |
| "step": 92924 | |
| }, | |
| { | |
| "epoch": 53.0, | |
| "learning_rate": 3.4253917972657556e-05, | |
| "loss": 0.0, | |
| "step": 94711 | |
| }, | |
| { | |
| "epoch": 53.0, | |
| "eval_accuracy": 0.641116936275197, | |
| "eval_loss": NaN, | |
| "eval_runtime": 1.8623, | |
| "eval_samples_per_second": 257.205, | |
| "eval_steps_per_second": 2.148, | |
| "step": 94711 | |
| }, | |
| { | |
| "epoch": 54.0, | |
| "learning_rate": 3.3955985328442816e-05, | |
| "loss": 0.0, | |
| "step": 96498 | |
| }, | |
| { | |
| "epoch": 54.0, | |
| "eval_accuracy": 0.6376506868516961, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2.0734, | |
| "eval_samples_per_second": 231.022, | |
| "eval_steps_per_second": 1.929, | |
| "step": 96498 | |
| }, | |
| { | |
| "epoch": 55.0, | |
| "learning_rate": 3.3658052684228076e-05, | |
| "loss": 0.0, | |
| "step": 98285 | |
| }, | |
| { | |
| "epoch": 55.0, | |
| "eval_accuracy": 0.6374884528175125, | |
| "eval_loss": NaN, | |
| "eval_runtime": 1.9769, | |
| "eval_samples_per_second": 242.303, | |
| "eval_steps_per_second": 2.023, | |
| "step": 98285 | |
| }, | |
| { | |
| "epoch": 56.0, | |
| "learning_rate": 3.3360120040013336e-05, | |
| "loss": 0.0, | |
| "step": 100072 | |
| }, | |
| { | |
| "epoch": 56.0, | |
| "eval_accuracy": 0.6368413657439933, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2.4635, | |
| "eval_samples_per_second": 194.44, | |
| "eval_steps_per_second": 1.624, | |
| "step": 100072 | |
| }, | |
| { | |
| "epoch": 57.0, | |
| "learning_rate": 3.30621873957986e-05, | |
| "loss": 0.0, | |
| "step": 101859 | |
| }, | |
| { | |
| "epoch": 57.0, | |
| "eval_accuracy": 0.6364829030006979, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2.4227, | |
| "eval_samples_per_second": 197.715, | |
| "eval_steps_per_second": 1.651, | |
| "step": 101859 | |
| }, | |
| { | |
| "epoch": 58.0, | |
| "learning_rate": 3.276425475158386e-05, | |
| "loss": 0.0, | |
| "step": 103646 | |
| }, | |
| { | |
| "epoch": 58.0, | |
| "eval_accuracy": 0.6412562335406511, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2.535, | |
| "eval_samples_per_second": 188.957, | |
| "eval_steps_per_second": 1.578, | |
| "step": 103646 | |
| }, | |
| { | |
| "epoch": 59.0, | |
| "learning_rate": 3.246632210736912e-05, | |
| "loss": 0.0, | |
| "step": 105433 | |
| }, | |
| { | |
| "epoch": 59.0, | |
| "eval_accuracy": 0.6347360495273153, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2.3607, | |
| "eval_samples_per_second": 202.908, | |
| "eval_steps_per_second": 1.694, | |
| "step": 105433 | |
| }, | |
| { | |
| "epoch": 60.0, | |
| "learning_rate": 3.216838946315439e-05, | |
| "loss": 0.0, | |
| "step": 107220 | |
| }, | |
| { | |
| "epoch": 60.0, | |
| "eval_accuracy": 0.6407410498205791, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2.469, | |
| "eval_samples_per_second": 194.009, | |
| "eval_steps_per_second": 1.62, | |
| "step": 107220 | |
| }, | |
| { | |
| "epoch": 61.0, | |
| "learning_rate": 3.187045681893965e-05, | |
| "loss": 0.0, | |
| "step": 109007 | |
| }, | |
| { | |
| "epoch": 61.0, | |
| "eval_accuracy": 0.6394521622227202, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2.4014, | |
| "eval_samples_per_second": 199.465, | |
| "eval_steps_per_second": 1.666, | |
| "step": 109007 | |
| }, | |
| { | |
| "epoch": 62.0, | |
| "learning_rate": 3.157252417472491e-05, | |
| "loss": 0.0, | |
| "step": 110794 | |
| }, | |
| { | |
| "epoch": 62.0, | |
| "eval_accuracy": 0.6373080145210835, | |
| "eval_loss": NaN, | |
| "eval_runtime": 3.0171, | |
| "eval_samples_per_second": 158.763, | |
| "eval_steps_per_second": 1.326, | |
| "step": 110794 | |
| }, | |
| { | |
| "epoch": 63.0, | |
| "learning_rate": 3.1274591530510175e-05, | |
| "loss": 0.0, | |
| "step": 112581 | |
| }, | |
| { | |
| "epoch": 63.0, | |
| "eval_accuracy": 0.6356097148176356, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2.5297, | |
| "eval_samples_per_second": 189.349, | |
| "eval_steps_per_second": 1.581, | |
| "step": 112581 | |
| }, | |
| { | |
| "epoch": 64.0, | |
| "learning_rate": 3.0976658886295434e-05, | |
| "loss": 0.0, | |
| "step": 114368 | |
| }, | |
| { | |
| "epoch": 64.0, | |
| "eval_accuracy": 0.6366671342404264, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2.4813, | |
| "eval_samples_per_second": 193.043, | |
| "eval_steps_per_second": 1.612, | |
| "step": 114368 | |
| }, | |
| { | |
| "epoch": 65.0, | |
| "learning_rate": 3.0678726242080694e-05, | |
| "loss": 0.0, | |
| "step": 116155 | |
| }, | |
| { | |
| "epoch": 65.0, | |
| "eval_accuracy": 0.6440701993138839, | |
| "eval_loss": NaN, | |
| "eval_runtime": 3.2092, | |
| "eval_samples_per_second": 149.257, | |
| "eval_steps_per_second": 1.246, | |
| "step": 116155 | |
| }, | |
| { | |
| "epoch": 66.0, | |
| "learning_rate": 3.0380793597865957e-05, | |
| "loss": 0.0017, | |
| "step": 117942 | |
| }, | |
| { | |
| "epoch": 66.0, | |
| "eval_accuracy": 0.6379713046379714, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2.5164, | |
| "eval_samples_per_second": 190.349, | |
| "eval_steps_per_second": 1.59, | |
| "step": 117942 | |
| }, | |
| { | |
| "epoch": 67.0, | |
| "learning_rate": 3.008286095365122e-05, | |
| "loss": 0.0, | |
| "step": 119729 | |
| }, | |
| { | |
| "epoch": 67.0, | |
| "eval_accuracy": 0.6348476780359295, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2.4358, | |
| "eval_samples_per_second": 196.654, | |
| "eval_steps_per_second": 1.642, | |
| "step": 119729 | |
| }, | |
| { | |
| "epoch": 68.0, | |
| "learning_rate": 2.9784928309436484e-05, | |
| "loss": 0.0, | |
| "step": 121516 | |
| }, | |
| { | |
| "epoch": 68.0, | |
| "eval_accuracy": 0.6356471316782075, | |
| "eval_loss": NaN, | |
| "eval_runtime": 1.8438, | |
| "eval_samples_per_second": 259.796, | |
| "eval_steps_per_second": 2.169, | |
| "step": 121516 | |
| }, | |
| { | |
| "epoch": 69.0, | |
| "learning_rate": 2.948699566522174e-05, | |
| "loss": 0.0, | |
| "step": 123303 | |
| }, | |
| { | |
| "epoch": 69.0, | |
| "eval_accuracy": 0.6391043176626526, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2.4179, | |
| "eval_samples_per_second": 198.106, | |
| "eval_steps_per_second": 1.654, | |
| "step": 123303 | |
| }, | |
| { | |
| "epoch": 70.0, | |
| "learning_rate": 2.9189063021007e-05, | |
| "loss": 0.0006, | |
| "step": 125090 | |
| }, | |
| { | |
| "epoch": 70.0, | |
| "eval_accuracy": 0.636170153182671, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2.5589, | |
| "eval_samples_per_second": 187.19, | |
| "eval_steps_per_second": 1.563, | |
| "step": 125090 | |
| }, | |
| { | |
| "epoch": 71.0, | |
| "learning_rate": 2.8891130376792263e-05, | |
| "loss": 0.0, | |
| "step": 126877 | |
| }, | |
| { | |
| "epoch": 71.0, | |
| "eval_accuracy": 0.6387962677575724, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2.2538, | |
| "eval_samples_per_second": 212.526, | |
| "eval_steps_per_second": 1.775, | |
| "step": 126877 | |
| }, | |
| { | |
| "epoch": 72.0, | |
| "learning_rate": 2.8593197732577526e-05, | |
| "loss": 0.0, | |
| "step": 128664 | |
| }, | |
| { | |
| "epoch": 72.0, | |
| "eval_accuracy": 0.6353993285750558, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2.4543, | |
| "eval_samples_per_second": 195.171, | |
| "eval_steps_per_second": 1.63, | |
| "step": 128664 | |
| }, | |
| { | |
| "epoch": 73.0, | |
| "learning_rate": 2.8295265088362786e-05, | |
| "loss": 0.0, | |
| "step": 130451 | |
| }, | |
| { | |
| "epoch": 73.0, | |
| "eval_accuracy": 0.6361857774753318, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2.4316, | |
| "eval_samples_per_second": 196.992, | |
| "eval_steps_per_second": 1.645, | |
| "step": 130451 | |
| }, | |
| { | |
| "epoch": 74.0, | |
| "learning_rate": 2.799733244414805e-05, | |
| "loss": 0.0013, | |
| "step": 132238 | |
| }, | |
| { | |
| "epoch": 74.0, | |
| "eval_accuracy": 0.6347066167290887, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2.3647, | |
| "eval_samples_per_second": 202.564, | |
| "eval_steps_per_second": 1.692, | |
| "step": 132238 | |
| }, | |
| { | |
| "epoch": 75.0, | |
| "learning_rate": 2.7699399799933313e-05, | |
| "loss": 0.0, | |
| "step": 134025 | |
| }, | |
| { | |
| "epoch": 75.0, | |
| "eval_accuracy": 0.632699704554323, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2.4813, | |
| "eval_samples_per_second": 193.045, | |
| "eval_steps_per_second": 1.612, | |
| "step": 134025 | |
| }, | |
| { | |
| "epoch": 76.0, | |
| "learning_rate": 2.7401467155718576e-05, | |
| "loss": 0.0, | |
| "step": 135812 | |
| }, | |
| { | |
| "epoch": 76.0, | |
| "eval_accuracy": 0.6382416594058293, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2.3498, | |
| "eval_samples_per_second": 203.844, | |
| "eval_steps_per_second": 1.702, | |
| "step": 135812 | |
| }, | |
| { | |
| "epoch": 77.0, | |
| "learning_rate": 2.7103534511503836e-05, | |
| "loss": 0.0, | |
| "step": 137599 | |
| }, | |
| { | |
| "epoch": 77.0, | |
| "eval_accuracy": 0.6411355703960205, | |
| "eval_loss": NaN, | |
| "eval_runtime": 1.8611, | |
| "eval_samples_per_second": 257.378, | |
| "eval_steps_per_second": 2.149, | |
| "step": 137599 | |
| }, | |
| { | |
| "epoch": 78.0, | |
| "learning_rate": 2.68056018672891e-05, | |
| "loss": 0.0, | |
| "step": 139386 | |
| }, | |
| { | |
| "epoch": 78.0, | |
| "eval_accuracy": 0.640435869351532, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2.2547, | |
| "eval_samples_per_second": 212.448, | |
| "eval_steps_per_second": 1.774, | |
| "step": 139386 | |
| }, | |
| { | |
| "epoch": 79.0, | |
| "learning_rate": 2.6507669223074362e-05, | |
| "loss": 0.0, | |
| "step": 141173 | |
| }, | |
| { | |
| "epoch": 79.0, | |
| "eval_accuracy": 0.6391697411777959, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2.1542, | |
| "eval_samples_per_second": 222.352, | |
| "eval_steps_per_second": 1.857, | |
| "step": 141173 | |
| }, | |
| { | |
| "epoch": 80.0, | |
| "learning_rate": 2.6209736578859622e-05, | |
| "loss": 0.0, | |
| "step": 142960 | |
| }, | |
| { | |
| "epoch": 80.0, | |
| "eval_accuracy": 0.6403956068586798, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2.2858, | |
| "eval_samples_per_second": 209.555, | |
| "eval_steps_per_second": 1.75, | |
| "step": 142960 | |
| }, | |
| { | |
| "epoch": 81.0, | |
| "learning_rate": 2.5911803934644885e-05, | |
| "loss": 0.0, | |
| "step": 144747 | |
| }, | |
| { | |
| "epoch": 81.0, | |
| "eval_accuracy": 0.6420577823455521, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2.0194, | |
| "eval_samples_per_second": 237.198, | |
| "eval_steps_per_second": 1.981, | |
| "step": 144747 | |
| }, | |
| { | |
| "epoch": 82.0, | |
| "learning_rate": 2.5613871290430148e-05, | |
| "loss": 0.0, | |
| "step": 146534 | |
| }, | |
| { | |
| "epoch": 82.0, | |
| "eval_accuracy": 0.6363990538472242, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2.2166, | |
| "eval_samples_per_second": 216.094, | |
| "eval_steps_per_second": 1.805, | |
| "step": 146534 | |
| }, | |
| { | |
| "epoch": 83.0, | |
| "learning_rate": 2.5315938646215408e-05, | |
| "loss": 0.0, | |
| "step": 148321 | |
| }, | |
| { | |
| "epoch": 83.0, | |
| "eval_accuracy": 0.6363839910439406, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2.0538, | |
| "eval_samples_per_second": 233.223, | |
| "eval_steps_per_second": 1.948, | |
| "step": 148321 | |
| }, | |
| { | |
| "epoch": 84.0, | |
| "learning_rate": 2.5018006002000664e-05, | |
| "loss": 0.0, | |
| "step": 150108 | |
| }, | |
| { | |
| "epoch": 84.0, | |
| "eval_accuracy": 0.6370422337589449, | |
| "eval_loss": NaN, | |
| "eval_runtime": 1.9129, | |
| "eval_samples_per_second": 250.403, | |
| "eval_steps_per_second": 2.091, | |
| "step": 150108 | |
| }, | |
| { | |
| "epoch": 85.0, | |
| "learning_rate": 2.472007335778593e-05, | |
| "loss": 0.0, | |
| "step": 151895 | |
| }, | |
| { | |
| "epoch": 85.0, | |
| "eval_accuracy": 0.6357136919112145, | |
| "eval_loss": NaN, | |
| "eval_runtime": 1.9511, | |
| "eval_samples_per_second": 245.5, | |
| "eval_steps_per_second": 2.05, | |
| "step": 151895 | |
| }, | |
| { | |
| "epoch": 86.0, | |
| "learning_rate": 2.4422140713571194e-05, | |
| "loss": 0.0, | |
| "step": 153682 | |
| }, | |
| { | |
| "epoch": 86.0, | |
| "eval_accuracy": 0.6353468815697267, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2.3614, | |
| "eval_samples_per_second": 202.845, | |
| "eval_steps_per_second": 1.694, | |
| "step": 153682 | |
| }, | |
| { | |
| "epoch": 87.0, | |
| "learning_rate": 2.412420806935645e-05, | |
| "loss": 0.0, | |
| "step": 155469 | |
| }, | |
| { | |
| "epoch": 87.0, | |
| "eval_accuracy": 0.6392810219998323, | |
| "eval_loss": NaN, | |
| "eval_runtime": 1.9531, | |
| "eval_samples_per_second": 245.249, | |
| "eval_steps_per_second": 2.048, | |
| "step": 155469 | |
| }, | |
| { | |
| "epoch": 88.0, | |
| "learning_rate": 2.3826275425141714e-05, | |
| "loss": 0.0, | |
| "step": 157256 | |
| }, | |
| { | |
| "epoch": 88.0, | |
| "eval_accuracy": 0.639685437438562, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2.3006, | |
| "eval_samples_per_second": 208.209, | |
| "eval_steps_per_second": 1.739, | |
| "step": 157256 | |
| }, | |
| { | |
| "epoch": 89.0, | |
| "learning_rate": 2.3528342780926977e-05, | |
| "loss": 0.0006, | |
| "step": 159043 | |
| }, | |
| { | |
| "epoch": 89.0, | |
| "eval_accuracy": 0.639618138424821, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2.0432, | |
| "eval_samples_per_second": 234.432, | |
| "eval_steps_per_second": 1.958, | |
| "step": 159043 | |
| }, | |
| { | |
| "epoch": 90.0, | |
| "learning_rate": 2.3230410136712237e-05, | |
| "loss": 0.0013, | |
| "step": 160830 | |
| }, | |
| { | |
| "epoch": 90.0, | |
| "eval_accuracy": 0.6378478767047344, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2.1388, | |
| "eval_samples_per_second": 223.962, | |
| "eval_steps_per_second": 1.87, | |
| "step": 160830 | |
| }, | |
| { | |
| "epoch": 91.0, | |
| "learning_rate": 2.29324774924975e-05, | |
| "loss": 0.0, | |
| "step": 162617 | |
| }, | |
| { | |
| "epoch": 91.0, | |
| "eval_accuracy": 0.6385569271433793, | |
| "eval_loss": NaN, | |
| "eval_runtime": 1.9971, | |
| "eval_samples_per_second": 239.843, | |
| "eval_steps_per_second": 2.003, | |
| "step": 162617 | |
| }, | |
| { | |
| "epoch": 92.0, | |
| "learning_rate": 2.2634544848282763e-05, | |
| "loss": 0.0, | |
| "step": 164404 | |
| }, | |
| { | |
| "epoch": 92.0, | |
| "eval_accuracy": 0.6414956218149055, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2.0014, | |
| "eval_samples_per_second": 239.331, | |
| "eval_steps_per_second": 1.999, | |
| "step": 164404 | |
| }, | |
| { | |
| "epoch": 93.0, | |
| "learning_rate": 2.2336612204068026e-05, | |
| "loss": 0.0, | |
| "step": 166191 | |
| }, | |
| { | |
| "epoch": 93.0, | |
| "eval_accuracy": 0.6342390696634239, | |
| "eval_loss": NaN, | |
| "eval_runtime": 1.987, | |
| "eval_samples_per_second": 241.063, | |
| "eval_steps_per_second": 2.013, | |
| "step": 166191 | |
| }, | |
| { | |
| "epoch": 94.0, | |
| "learning_rate": 2.2038679559853283e-05, | |
| "loss": 0.0, | |
| "step": 167978 | |
| }, | |
| { | |
| "epoch": 94.0, | |
| "eval_accuracy": 0.6355638270873869, | |
| "eval_loss": NaN, | |
| "eval_runtime": 1.9543, | |
| "eval_samples_per_second": 245.1, | |
| "eval_steps_per_second": 2.047, | |
| "step": 167978 | |
| }, | |
| { | |
| "epoch": 95.0, | |
| "learning_rate": 2.1740746915638546e-05, | |
| "loss": 0.0, | |
| "step": 169765 | |
| }, | |
| { | |
| "epoch": 95.0, | |
| "eval_accuracy": 0.6410132895072398, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2.1422, | |
| "eval_samples_per_second": 223.599, | |
| "eval_steps_per_second": 1.867, | |
| "step": 169765 | |
| }, | |
| { | |
| "epoch": 96.0, | |
| "learning_rate": 2.144281427142381e-05, | |
| "loss": 0.0, | |
| "step": 171552 | |
| }, | |
| { | |
| "epoch": 96.0, | |
| "eval_accuracy": 0.6365928831605492, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2.1461, | |
| "eval_samples_per_second": 223.199, | |
| "eval_steps_per_second": 1.864, | |
| "step": 171552 | |
| }, | |
| { | |
| "epoch": 97.0, | |
| "learning_rate": 2.114488162720907e-05, | |
| "loss": 0.0, | |
| "step": 173339 | |
| }, | |
| { | |
| "epoch": 97.0, | |
| "eval_accuracy": 0.6328623582197698, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2.0065, | |
| "eval_samples_per_second": 238.72, | |
| "eval_steps_per_second": 1.993, | |
| "step": 173339 | |
| }, | |
| { | |
| "epoch": 98.0, | |
| "learning_rate": 2.0846948982994332e-05, | |
| "loss": 0.0013, | |
| "step": 175126 | |
| }, | |
| { | |
| "epoch": 98.0, | |
| "eval_accuracy": 0.635225093083606, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2.2096, | |
| "eval_samples_per_second": 216.784, | |
| "eval_steps_per_second": 1.81, | |
| "step": 175126 | |
| }, | |
| { | |
| "epoch": 99.0, | |
| "learning_rate": 2.0549016338779595e-05, | |
| "loss": 0.0, | |
| "step": 176913 | |
| }, | |
| { | |
| "epoch": 99.0, | |
| "eval_accuracy": 0.633986562150056, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2.7617, | |
| "eval_samples_per_second": 173.442, | |
| "eval_steps_per_second": 1.448, | |
| "step": 176913 | |
| }, | |
| { | |
| "epoch": 100.0, | |
| "learning_rate": 2.0251083694564855e-05, | |
| "loss": 0.0, | |
| "step": 178700 | |
| }, | |
| { | |
| "epoch": 100.0, | |
| "eval_accuracy": 0.6358424725822532, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2.5626, | |
| "eval_samples_per_second": 186.922, | |
| "eval_steps_per_second": 1.561, | |
| "step": 178700 | |
| }, | |
| { | |
| "epoch": 101.0, | |
| "learning_rate": 1.995315105035012e-05, | |
| "loss": 0.0, | |
| "step": 180487 | |
| }, | |
| { | |
| "epoch": 101.0, | |
| "eval_accuracy": 0.6366913511247729, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2.4375, | |
| "eval_samples_per_second": 196.515, | |
| "eval_steps_per_second": 1.641, | |
| "step": 180487 | |
| }, | |
| { | |
| "epoch": 102.0, | |
| "learning_rate": 1.9655218406135378e-05, | |
| "loss": 0.0006, | |
| "step": 182274 | |
| }, | |
| { | |
| "epoch": 102.0, | |
| "eval_accuracy": 0.6367565747003845, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2.3509, | |
| "eval_samples_per_second": 203.749, | |
| "eval_steps_per_second": 1.701, | |
| "step": 182274 | |
| }, | |
| { | |
| "epoch": 103.0, | |
| "learning_rate": 1.935728576192064e-05, | |
| "loss": 0.0, | |
| "step": 184061 | |
| }, | |
| { | |
| "epoch": 103.0, | |
| "eval_accuracy": 0.6353013702468686, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2.0088, | |
| "eval_samples_per_second": 238.45, | |
| "eval_steps_per_second": 1.991, | |
| "step": 184061 | |
| }, | |
| { | |
| "epoch": 104.0, | |
| "learning_rate": 1.90593531177059e-05, | |
| "loss": 0.0, | |
| "step": 185848 | |
| }, | |
| { | |
| "epoch": 104.0, | |
| "eval_accuracy": 0.6369532258970184, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2.1758, | |
| "eval_samples_per_second": 220.149, | |
| "eval_steps_per_second": 1.838, | |
| "step": 185848 | |
| }, | |
| { | |
| "epoch": 105.0, | |
| "learning_rate": 1.8761420473491164e-05, | |
| "loss": 0.0, | |
| "step": 187635 | |
| }, | |
| { | |
| "epoch": 105.0, | |
| "eval_accuracy": 0.6333213286422694, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2.3075, | |
| "eval_samples_per_second": 207.588, | |
| "eval_steps_per_second": 1.734, | |
| "step": 187635 | |
| }, | |
| { | |
| "epoch": 106.0, | |
| "learning_rate": 1.8463487829276428e-05, | |
| "loss": 0.0, | |
| "step": 189422 | |
| }, | |
| { | |
| "epoch": 106.0, | |
| "eval_accuracy": 0.6316263365222284, | |
| "eval_loss": NaN, | |
| "eval_runtime": 1.8744, | |
| "eval_samples_per_second": 255.55, | |
| "eval_steps_per_second": 2.134, | |
| "step": 189422 | |
| }, | |
| { | |
| "epoch": 107.0, | |
| "learning_rate": 1.8165555185061687e-05, | |
| "loss": 0.0006, | |
| "step": 191209 | |
| }, | |
| { | |
| "epoch": 107.0, | |
| "eval_accuracy": 0.6393596184961253, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2.5091, | |
| "eval_samples_per_second": 190.907, | |
| "eval_steps_per_second": 1.594, | |
| "step": 191209 | |
| }, | |
| { | |
| "epoch": 108.0, | |
| "learning_rate": 1.786762254084695e-05, | |
| "loss": 0.0, | |
| "step": 192996 | |
| }, | |
| { | |
| "epoch": 108.0, | |
| "eval_accuracy": 0.6323443376514835, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2.4565, | |
| "eval_samples_per_second": 194.993, | |
| "eval_steps_per_second": 1.628, | |
| "step": 192996 | |
| }, | |
| { | |
| "epoch": 109.0, | |
| "learning_rate": 1.756968989663221e-05, | |
| "loss": 0.0, | |
| "step": 194783 | |
| }, | |
| { | |
| "epoch": 109.0, | |
| "eval_accuracy": 0.6405684971827432, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2.4473, | |
| "eval_samples_per_second": 195.727, | |
| "eval_steps_per_second": 1.634, | |
| "step": 194783 | |
| }, | |
| { | |
| "epoch": 110.0, | |
| "learning_rate": 1.7271757252417474e-05, | |
| "loss": 0.0012, | |
| "step": 196570 | |
| }, | |
| { | |
| "epoch": 110.0, | |
| "eval_accuracy": 0.6330752990851513, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2.4244, | |
| "eval_samples_per_second": 197.575, | |
| "eval_steps_per_second": 1.65, | |
| "step": 196570 | |
| }, | |
| { | |
| "epoch": 111.0, | |
| "learning_rate": 1.6973824608202733e-05, | |
| "loss": 0.0, | |
| "step": 198357 | |
| }, | |
| { | |
| "epoch": 111.0, | |
| "eval_accuracy": 0.6397748592870544, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2.4021, | |
| "eval_samples_per_second": 199.407, | |
| "eval_steps_per_second": 1.665, | |
| "step": 198357 | |
| }, | |
| { | |
| "epoch": 112.0, | |
| "learning_rate": 1.6675891963987997e-05, | |
| "loss": 0.0, | |
| "step": 200144 | |
| }, | |
| { | |
| "epoch": 112.0, | |
| "eval_accuracy": 0.640183902890303, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2.4547, | |
| "eval_samples_per_second": 195.14, | |
| "eval_steps_per_second": 1.63, | |
| "step": 200144 | |
| }, | |
| { | |
| "epoch": 113.0, | |
| "learning_rate": 1.637795931977326e-05, | |
| "loss": 0.0, | |
| "step": 201931 | |
| }, | |
| { | |
| "epoch": 113.0, | |
| "eval_accuracy": 0.6345416867743492, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2.4355, | |
| "eval_samples_per_second": 196.673, | |
| "eval_steps_per_second": 1.642, | |
| "step": 201931 | |
| }, | |
| { | |
| "epoch": 114.0, | |
| "learning_rate": 1.608002667555852e-05, | |
| "loss": 0.0, | |
| "step": 203718 | |
| }, | |
| { | |
| "epoch": 114.0, | |
| "eval_accuracy": 0.6416126303918804, | |
| "eval_loss": NaN, | |
| "eval_runtime": 1.881, | |
| "eval_samples_per_second": 254.65, | |
| "eval_steps_per_second": 2.127, | |
| "step": 203718 | |
| }, | |
| { | |
| "epoch": 115.0, | |
| "learning_rate": 1.5782094031343783e-05, | |
| "loss": 0.0, | |
| "step": 205505 | |
| }, | |
| { | |
| "epoch": 115.0, | |
| "eval_accuracy": 0.635246810870771, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2.3521, | |
| "eval_samples_per_second": 203.648, | |
| "eval_steps_per_second": 1.701, | |
| "step": 205505 | |
| }, | |
| { | |
| "epoch": 116.0, | |
| "learning_rate": 1.5484161387129043e-05, | |
| "loss": 0.0, | |
| "step": 207292 | |
| }, | |
| { | |
| "epoch": 116.0, | |
| "eval_accuracy": 0.635686274509804, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2.3117, | |
| "eval_samples_per_second": 207.209, | |
| "eval_steps_per_second": 1.73, | |
| "step": 207292 | |
| }, | |
| { | |
| "epoch": 117.0, | |
| "learning_rate": 1.5186228742914304e-05, | |
| "loss": 0.0032, | |
| "step": 209079 | |
| }, | |
| { | |
| "epoch": 117.0, | |
| "eval_accuracy": 0.6358383124351314, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2.4352, | |
| "eval_samples_per_second": 196.698, | |
| "eval_steps_per_second": 1.643, | |
| "step": 209079 | |
| }, | |
| { | |
| "epoch": 118.0, | |
| "learning_rate": 1.4888296098699567e-05, | |
| "loss": 0.0013, | |
| "step": 210866 | |
| }, | |
| { | |
| "epoch": 118.0, | |
| "eval_accuracy": 0.6405930899426493, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2.2861, | |
| "eval_samples_per_second": 209.529, | |
| "eval_steps_per_second": 1.75, | |
| "step": 210866 | |
| }, | |
| { | |
| "epoch": 119.0, | |
| "learning_rate": 1.4590363454484829e-05, | |
| "loss": 0.0, | |
| "step": 212653 | |
| }, | |
| { | |
| "epoch": 119.0, | |
| "eval_accuracy": 0.6353956511992827, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2.3549, | |
| "eval_samples_per_second": 203.406, | |
| "eval_steps_per_second": 1.699, | |
| "step": 212653 | |
| }, | |
| { | |
| "epoch": 120.0, | |
| "learning_rate": 1.429243081027009e-05, | |
| "loss": 0.0, | |
| "step": 214440 | |
| }, | |
| { | |
| "epoch": 120.0, | |
| "eval_accuracy": 0.6345421474450066, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2.4547, | |
| "eval_samples_per_second": 195.139, | |
| "eval_steps_per_second": 1.63, | |
| "step": 214440 | |
| }, | |
| { | |
| "epoch": 121.0, | |
| "learning_rate": 1.3994498166055354e-05, | |
| "loss": 0.0, | |
| "step": 216227 | |
| }, | |
| { | |
| "epoch": 121.0, | |
| "eval_accuracy": 0.6432686391856368, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2.5342, | |
| "eval_samples_per_second": 189.015, | |
| "eval_steps_per_second": 1.578, | |
| "step": 216227 | |
| }, | |
| { | |
| "epoch": 122.0, | |
| "learning_rate": 1.3696565521840615e-05, | |
| "loss": 0.0, | |
| "step": 218014 | |
| }, | |
| { | |
| "epoch": 122.0, | |
| "eval_accuracy": 0.6326222917132008, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2.3651, | |
| "eval_samples_per_second": 202.525, | |
| "eval_steps_per_second": 1.691, | |
| "step": 218014 | |
| }, | |
| { | |
| "epoch": 123.0, | |
| "learning_rate": 1.3398632877625875e-05, | |
| "loss": 0.0, | |
| "step": 219801 | |
| }, | |
| { | |
| "epoch": 123.0, | |
| "eval_accuracy": 0.6357796872798985, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2.4594, | |
| "eval_samples_per_second": 194.763, | |
| "eval_steps_per_second": 1.626, | |
| "step": 219801 | |
| }, | |
| { | |
| "epoch": 124.0, | |
| "learning_rate": 1.3100700233411136e-05, | |
| "loss": 0.0, | |
| "step": 221588 | |
| }, | |
| { | |
| "epoch": 124.0, | |
| "eval_accuracy": 0.6409228526575466, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2.4398, | |
| "eval_samples_per_second": 196.326, | |
| "eval_steps_per_second": 1.639, | |
| "step": 221588 | |
| }, | |
| { | |
| "epoch": 125.0, | |
| "learning_rate": 1.28027675891964e-05, | |
| "loss": 0.0, | |
| "step": 223375 | |
| }, | |
| { | |
| "epoch": 125.0, | |
| "eval_accuracy": 0.6404630806155583, | |
| "eval_loss": NaN, | |
| "eval_runtime": 3.34, | |
| "eval_samples_per_second": 143.413, | |
| "eval_steps_per_second": 1.198, | |
| "step": 223375 | |
| }, | |
| { | |
| "epoch": 126.0, | |
| "learning_rate": 1.2504834944981661e-05, | |
| "loss": 0.0, | |
| "step": 225162 | |
| }, | |
| { | |
| "epoch": 126.0, | |
| "eval_accuracy": 0.637574502616336, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2.7328, | |
| "eval_samples_per_second": 175.276, | |
| "eval_steps_per_second": 1.464, | |
| "step": 225162 | |
| }, | |
| { | |
| "epoch": 127.0, | |
| "learning_rate": 1.2206902300766923e-05, | |
| "loss": 0.0, | |
| "step": 226949 | |
| }, | |
| { | |
| "epoch": 127.0, | |
| "eval_accuracy": 0.63958607925068, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2.3572, | |
| "eval_samples_per_second": 203.207, | |
| "eval_steps_per_second": 1.697, | |
| "step": 226949 | |
| }, | |
| { | |
| "epoch": 128.0, | |
| "learning_rate": 1.1908969656552186e-05, | |
| "loss": 0.0, | |
| "step": 228736 | |
| }, | |
| { | |
| "epoch": 128.0, | |
| "eval_accuracy": 0.6355922615680507, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2.0355, | |
| "eval_samples_per_second": 235.321, | |
| "eval_steps_per_second": 1.965, | |
| "step": 228736 | |
| }, | |
| { | |
| "epoch": 129.0, | |
| "learning_rate": 1.1611037012337446e-05, | |
| "loss": 0.0, | |
| "step": 230523 | |
| }, | |
| { | |
| "epoch": 129.0, | |
| "eval_accuracy": 0.6431967398686892, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2.3821, | |
| "eval_samples_per_second": 201.084, | |
| "eval_steps_per_second": 1.679, | |
| "step": 230523 | |
| }, | |
| { | |
| "epoch": 130.0, | |
| "learning_rate": 1.1313104368122709e-05, | |
| "loss": 0.0, | |
| "step": 232310 | |
| }, | |
| { | |
| "epoch": 130.0, | |
| "eval_accuracy": 0.6384714590108781, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2.3962, | |
| "eval_samples_per_second": 199.899, | |
| "eval_steps_per_second": 1.669, | |
| "step": 232310 | |
| }, | |
| { | |
| "epoch": 131.0, | |
| "learning_rate": 1.101517172390797e-05, | |
| "loss": 0.0, | |
| "step": 234097 | |
| }, | |
| { | |
| "epoch": 131.0, | |
| "eval_accuracy": 0.6337281095644365, | |
| "eval_loss": NaN, | |
| "eval_runtime": 1.8635, | |
| "eval_samples_per_second": 257.042, | |
| "eval_steps_per_second": 2.146, | |
| "step": 234097 | |
| }, | |
| { | |
| "epoch": 132.0, | |
| "learning_rate": 1.0717239079693232e-05, | |
| "loss": 0.0, | |
| "step": 235884 | |
| }, | |
| { | |
| "epoch": 132.0, | |
| "eval_accuracy": 0.6389531480810502, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2.3837, | |
| "eval_samples_per_second": 200.947, | |
| "eval_steps_per_second": 1.678, | |
| "step": 235884 | |
| }, | |
| { | |
| "epoch": 133.0, | |
| "learning_rate": 1.0419306435478493e-05, | |
| "loss": 0.0, | |
| "step": 237671 | |
| }, | |
| { | |
| "epoch": 133.0, | |
| "eval_accuracy": 0.636236112669734, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2.4808, | |
| "eval_samples_per_second": 193.082, | |
| "eval_steps_per_second": 1.612, | |
| "step": 237671 | |
| }, | |
| { | |
| "epoch": 134.0, | |
| "learning_rate": 1.0121373791263755e-05, | |
| "loss": 0.0, | |
| "step": 239458 | |
| }, | |
| { | |
| "epoch": 134.0, | |
| "eval_accuracy": 0.6331533837934105, | |
| "eval_loss": NaN, | |
| "eval_runtime": 1.8767, | |
| "eval_samples_per_second": 255.23, | |
| "eval_steps_per_second": 2.131, | |
| "step": 239458 | |
| }, | |
| { | |
| "epoch": 135.0, | |
| "learning_rate": 9.823441147049018e-06, | |
| "loss": 0.0, | |
| "step": 241245 | |
| }, | |
| { | |
| "epoch": 135.0, | |
| "eval_accuracy": 0.636656406748746, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2.2751, | |
| "eval_samples_per_second": 210.541, | |
| "eval_steps_per_second": 1.758, | |
| "step": 241245 | |
| }, | |
| { | |
| "epoch": 136.0, | |
| "learning_rate": 9.525508502834278e-06, | |
| "loss": 0.0016, | |
| "step": 243032 | |
| }, | |
| { | |
| "epoch": 136.0, | |
| "eval_accuracy": 0.6333677196308585, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2.3276, | |
| "eval_samples_per_second": 205.787, | |
| "eval_steps_per_second": 1.718, | |
| "step": 243032 | |
| }, | |
| { | |
| "epoch": 137.0, | |
| "learning_rate": 9.227575858619541e-06, | |
| "loss": 0.0, | |
| "step": 244819 | |
| }, | |
| { | |
| "epoch": 137.0, | |
| "eval_accuracy": 0.6411590941060628, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2.7102, | |
| "eval_samples_per_second": 176.741, | |
| "eval_steps_per_second": 1.476, | |
| "step": 244819 | |
| }, | |
| { | |
| "epoch": 138.0, | |
| "learning_rate": 8.929643214404802e-06, | |
| "loss": 0.0, | |
| "step": 246606 | |
| }, | |
| { | |
| "epoch": 138.0, | |
| "eval_accuracy": 0.63665891972111, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2.397, | |
| "eval_samples_per_second": 199.829, | |
| "eval_steps_per_second": 1.669, | |
| "step": 246606 | |
| }, | |
| { | |
| "epoch": 139.0, | |
| "learning_rate": 8.631710570190064e-06, | |
| "loss": 0.0, | |
| "step": 248393 | |
| }, | |
| { | |
| "epoch": 139.0, | |
| "eval_accuracy": 0.637815760763141, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2.2977, | |
| "eval_samples_per_second": 208.473, | |
| "eval_steps_per_second": 1.741, | |
| "step": 248393 | |
| }, | |
| { | |
| "epoch": 140.0, | |
| "learning_rate": 8.333777925975325e-06, | |
| "loss": 0.0, | |
| "step": 250180 | |
| }, | |
| { | |
| "epoch": 140.0, | |
| "eval_accuracy": 0.6389793548752514, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2.4084, | |
| "eval_samples_per_second": 198.888, | |
| "eval_steps_per_second": 1.661, | |
| "step": 250180 | |
| }, | |
| { | |
| "epoch": 141.0, | |
| "learning_rate": 8.035845281760587e-06, | |
| "loss": 0.0, | |
| "step": 251967 | |
| }, | |
| { | |
| "epoch": 141.0, | |
| "eval_accuracy": 0.6375586326994916, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2.1944, | |
| "eval_samples_per_second": 218.284, | |
| "eval_steps_per_second": 1.823, | |
| "step": 251967 | |
| }, | |
| { | |
| "epoch": 142.0, | |
| "learning_rate": 7.73791263754585e-06, | |
| "loss": 0.0, | |
| "step": 253754 | |
| }, | |
| { | |
| "epoch": 142.0, | |
| "eval_accuracy": 0.6363045444268596, | |
| "eval_loss": NaN, | |
| "eval_runtime": 1.9755, | |
| "eval_samples_per_second": 242.476, | |
| "eval_steps_per_second": 2.025, | |
| "step": 253754 | |
| }, | |
| { | |
| "epoch": 143.0, | |
| "learning_rate": 7.43997999333111e-06, | |
| "loss": 0.0033, | |
| "step": 255541 | |
| }, | |
| { | |
| "epoch": 143.0, | |
| "eval_accuracy": 0.642540373190528, | |
| "eval_loss": NaN, | |
| "eval_runtime": 1.9855, | |
| "eval_samples_per_second": 241.25, | |
| "eval_steps_per_second": 2.015, | |
| "step": 255541 | |
| }, | |
| { | |
| "epoch": 144.0, | |
| "learning_rate": 7.142047349116372e-06, | |
| "loss": 0.0, | |
| "step": 257328 | |
| }, | |
| { | |
| "epoch": 144.0, | |
| "eval_accuracy": 0.6360186889423758, | |
| "eval_loss": NaN, | |
| "eval_runtime": 1.9778, | |
| "eval_samples_per_second": 242.187, | |
| "eval_steps_per_second": 2.022, | |
| "step": 257328 | |
| }, | |
| { | |
| "epoch": 145.0, | |
| "learning_rate": 6.844114704901635e-06, | |
| "loss": 0.0, | |
| "step": 259115 | |
| }, | |
| { | |
| "epoch": 145.0, | |
| "eval_accuracy": 0.6377054679637706, | |
| "eval_loss": NaN, | |
| "eval_runtime": 1.9561, | |
| "eval_samples_per_second": 244.876, | |
| "eval_steps_per_second": 2.045, | |
| "step": 259115 | |
| }, | |
| { | |
| "epoch": 146.0, | |
| "learning_rate": 6.546182060686896e-06, | |
| "loss": 0.0, | |
| "step": 260902 | |
| }, | |
| { | |
| "epoch": 146.0, | |
| "eval_accuracy": 0.630178854426081, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2.1068, | |
| "eval_samples_per_second": 227.357, | |
| "eval_steps_per_second": 1.899, | |
| "step": 260902 | |
| }, | |
| { | |
| "epoch": 147.0, | |
| "learning_rate": 6.248249416472158e-06, | |
| "loss": 0.0, | |
| "step": 262689 | |
| }, | |
| { | |
| "epoch": 147.0, | |
| "eval_accuracy": 0.6320312280603219, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2.051, | |
| "eval_samples_per_second": 233.54, | |
| "eval_steps_per_second": 1.95, | |
| "step": 262689 | |
| }, | |
| { | |
| "epoch": 148.0, | |
| "learning_rate": 5.950316772257419e-06, | |
| "loss": 0.0, | |
| "step": 264476 | |
| }, | |
| { | |
| "epoch": 148.0, | |
| "eval_accuracy": 0.6358165946266633, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2.0868, | |
| "eval_samples_per_second": 229.54, | |
| "eval_steps_per_second": 1.917, | |
| "step": 264476 | |
| }, | |
| { | |
| "epoch": 149.0, | |
| "learning_rate": 5.6523841280426815e-06, | |
| "loss": 0.0, | |
| "step": 266263 | |
| }, | |
| { | |
| "epoch": 149.0, | |
| "eval_accuracy": 0.6381050924242848, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2.0799, | |
| "eval_samples_per_second": 230.305, | |
| "eval_steps_per_second": 1.923, | |
| "step": 266263 | |
| }, | |
| { | |
| "epoch": 150.0, | |
| "learning_rate": 5.354451483827943e-06, | |
| "loss": 0.0, | |
| "step": 268050 | |
| }, | |
| { | |
| "epoch": 150.0, | |
| "eval_accuracy": 0.6414367457934395, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2.0658, | |
| "eval_samples_per_second": 231.876, | |
| "eval_steps_per_second": 1.936, | |
| "step": 268050 | |
| }, | |
| { | |
| "epoch": 151.0, | |
| "learning_rate": 5.0565188396132045e-06, | |
| "loss": 0.0, | |
| "step": 269837 | |
| }, | |
| { | |
| "epoch": 151.0, | |
| "eval_accuracy": 0.640085841757497, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2.0508, | |
| "eval_samples_per_second": 233.571, | |
| "eval_steps_per_second": 1.95, | |
| "step": 269837 | |
| }, | |
| { | |
| "epoch": 152.0, | |
| "learning_rate": 4.758586195398467e-06, | |
| "loss": 0.0012, | |
| "step": 271624 | |
| }, | |
| { | |
| "epoch": 152.0, | |
| "eval_accuracy": 0.6415057319841915, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2.0208, | |
| "eval_samples_per_second": 237.04, | |
| "eval_steps_per_second": 1.979, | |
| "step": 271624 | |
| }, | |
| { | |
| "epoch": 153.0, | |
| "learning_rate": 4.4606535511837275e-06, | |
| "loss": 0.0, | |
| "step": 273411 | |
| }, | |
| { | |
| "epoch": 153.0, | |
| "eval_accuracy": 0.6424933908445805, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2.1125, | |
| "eval_samples_per_second": 226.742, | |
| "eval_steps_per_second": 1.893, | |
| "step": 273411 | |
| }, | |
| { | |
| "epoch": 154.0, | |
| "learning_rate": 4.16272090696899e-06, | |
| "loss": 0.0, | |
| "step": 275198 | |
| }, | |
| { | |
| "epoch": 154.0, | |
| "eval_accuracy": 0.6366794508365293, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2.1748, | |
| "eval_samples_per_second": 220.247, | |
| "eval_steps_per_second": 1.839, | |
| "step": 275198 | |
| }, | |
| { | |
| "epoch": 155.0, | |
| "learning_rate": 3.864788262754251e-06, | |
| "loss": 0.0, | |
| "step": 276985 | |
| }, | |
| { | |
| "epoch": 155.0, | |
| "eval_accuracy": 0.6356290122761572, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2.0784, | |
| "eval_samples_per_second": 230.462, | |
| "eval_steps_per_second": 1.925, | |
| "step": 276985 | |
| }, | |
| { | |
| "epoch": 156.0, | |
| "learning_rate": 3.5668556185395137e-06, | |
| "loss": 0.0, | |
| "step": 278772 | |
| }, | |
| { | |
| "epoch": 156.0, | |
| "eval_accuracy": 0.6411258795934324, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2.0969, | |
| "eval_samples_per_second": 228.428, | |
| "eval_steps_per_second": 1.908, | |
| "step": 278772 | |
| }, | |
| { | |
| "epoch": 157.0, | |
| "learning_rate": 3.268922974324775e-06, | |
| "loss": 0.0, | |
| "step": 280559 | |
| }, | |
| { | |
| "epoch": 157.0, | |
| "eval_accuracy": 0.6343390602592582, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2.0784, | |
| "eval_samples_per_second": 230.468, | |
| "eval_steps_per_second": 1.925, | |
| "step": 280559 | |
| }, | |
| { | |
| "epoch": 158.0, | |
| "learning_rate": 2.9709903301100367e-06, | |
| "loss": 0.0007, | |
| "step": 282346 | |
| }, | |
| { | |
| "epoch": 158.0, | |
| "eval_accuracy": 0.6368964554842311, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2.0391, | |
| "eval_samples_per_second": 234.912, | |
| "eval_steps_per_second": 1.962, | |
| "step": 282346 | |
| }, | |
| { | |
| "epoch": 159.0, | |
| "learning_rate": 2.6730576858952986e-06, | |
| "loss": 0.0, | |
| "step": 284133 | |
| }, | |
| { | |
| "epoch": 159.0, | |
| "eval_accuracy": 0.636098163643511, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2.1494, | |
| "eval_samples_per_second": 222.857, | |
| "eval_steps_per_second": 1.861, | |
| "step": 284133 | |
| }, | |
| { | |
| "epoch": 160.0, | |
| "learning_rate": 2.3751250416805605e-06, | |
| "loss": 0.0013, | |
| "step": 285920 | |
| }, | |
| { | |
| "epoch": 160.0, | |
| "eval_accuracy": 0.6396206236631768, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2.0359, | |
| "eval_samples_per_second": 235.272, | |
| "eval_steps_per_second": 1.965, | |
| "step": 285920 | |
| }, | |
| { | |
| "epoch": 161.0, | |
| "learning_rate": 2.077192397465822e-06, | |
| "loss": 0.0008, | |
| "step": 287707 | |
| }, | |
| { | |
| "epoch": 161.0, | |
| "eval_accuracy": 0.6381123797738906, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2.4553, | |
| "eval_samples_per_second": 195.089, | |
| "eval_steps_per_second": 1.629, | |
| "step": 287707 | |
| }, | |
| { | |
| "epoch": 162.0, | |
| "learning_rate": 1.779259753251084e-06, | |
| "loss": 0.0, | |
| "step": 289494 | |
| }, | |
| { | |
| "epoch": 162.0, | |
| "eval_accuracy": 0.6351684010294282, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2.0507, | |
| "eval_samples_per_second": 233.583, | |
| "eval_steps_per_second": 1.951, | |
| "step": 289494 | |
| }, | |
| { | |
| "epoch": 163.0, | |
| "learning_rate": 1.4813271090363454e-06, | |
| "loss": 0.0, | |
| "step": 291281 | |
| }, | |
| { | |
| "epoch": 163.0, | |
| "eval_accuracy": 0.6370490792387252, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2.0888, | |
| "eval_samples_per_second": 229.314, | |
| "eval_steps_per_second": 1.915, | |
| "step": 291281 | |
| }, | |
| { | |
| "epoch": 164.0, | |
| "learning_rate": 1.1833944648216071e-06, | |
| "loss": 0.0, | |
| "step": 293068 | |
| }, | |
| { | |
| "epoch": 164.0, | |
| "eval_accuracy": 0.6399250601196801, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2.061, | |
| "eval_samples_per_second": 232.411, | |
| "eval_steps_per_second": 1.941, | |
| "step": 293068 | |
| }, | |
| { | |
| "epoch": 165.0, | |
| "learning_rate": 8.854618206068691e-07, | |
| "loss": 0.0031, | |
| "step": 294855 | |
| }, | |
| { | |
| "epoch": 165.0, | |
| "eval_accuracy": 0.6401486145381321, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2.2403, | |
| "eval_samples_per_second": 213.812, | |
| "eval_steps_per_second": 1.785, | |
| "step": 294855 | |
| }, | |
| { | |
| "epoch": 166.0, | |
| "learning_rate": 5.875291763921307e-07, | |
| "loss": 0.0, | |
| "step": 296642 | |
| }, | |
| { | |
| "epoch": 166.0, | |
| "eval_accuracy": 0.6357598978288633, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2.2206, | |
| "eval_samples_per_second": 215.711, | |
| "eval_steps_per_second": 1.801, | |
| "step": 296642 | |
| }, | |
| { | |
| "epoch": 167.0, | |
| "learning_rate": 2.895965321773925e-07, | |
| "loss": 0.0, | |
| "step": 298429 | |
| }, | |
| { | |
| "epoch": 167.0, | |
| "eval_accuracy": 0.6389859154929578, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2.2354, | |
| "eval_samples_per_second": 214.281, | |
| "eval_steps_per_second": 1.789, | |
| "step": 298429 | |
| }, | |
| { | |
| "epoch": 167.88, | |
| "learning_rate": 2.7675891963987998e-08, | |
| "loss": 0.0, | |
| "step": 300000 | |
| }, | |
| { | |
| "epoch": 167.88, | |
| "eval_accuracy": 0.6354230747721045, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2.133, | |
| "eval_samples_per_second": 224.569, | |
| "eval_steps_per_second": 1.875, | |
| "step": 300000 | |
| }, | |
| { | |
| "epoch": 167.88, | |
| "step": 300000, | |
| "total_flos": 3.823595109857886e+18, | |
| "train_loss": 0.00019481298685073851, | |
| "train_runtime": 193101.3534, | |
| "train_samples_per_second": 198.859, | |
| "train_steps_per_second": 1.554 | |
| } | |
| ], | |
| "max_steps": 300000, | |
| "num_train_epochs": 168, | |
| "total_flos": 3.823595109857886e+18, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |