| { | |
| "best_metric": 0.9835737347602844, | |
| "best_model_checkpoint": "wav2vec2-base-lang-id/checkpoint-1557", | |
| "epoch": 9.997118155619596, | |
| "global_step": 1730, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 1.7341040462427742e-05, | |
| "loss": 3.8045, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 3.4682080924855485e-05, | |
| "loss": 3.795, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 5.2023121387283234e-05, | |
| "loss": 3.7695, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 6.936416184971097e-05, | |
| "loss": 3.748, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 8.670520231213873e-05, | |
| "loss": 3.7078, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 0.00010404624277456647, | |
| "loss": 3.7034, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 0.00012138728323699421, | |
| "loss": 3.6422, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 0.00013872832369942194, | |
| "loss": 3.5837, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 0.00015606936416184968, | |
| "loss": 3.4935, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 0.00017341040462427745, | |
| "loss": 3.4542, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 0.0001907514450867052, | |
| "loss": 3.3921, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 0.00020809248554913294, | |
| "loss": 3.3001, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 0.00022543352601156065, | |
| "loss": 3.272, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 0.00024277456647398842, | |
| "loss": 3.1537, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 0.00026011560693641616, | |
| "loss": 3.1013, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 0.0002774566473988439, | |
| "loss": 2.9714, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 0.00029479768786127165, | |
| "loss": 2.9568, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.11463994565217392, | |
| "eval_loss": 3.2865560054779053, | |
| "eval_runtime": 166.1472, | |
| "eval_samples_per_second": 35.438, | |
| "eval_steps_per_second": 8.86, | |
| "step": 173 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "learning_rate": 0.00029865125240847784, | |
| "loss": 3.2585, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "learning_rate": 0.0002967244701348747, | |
| "loss": 2.9694, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "learning_rate": 0.00029479768786127165, | |
| "loss": 2.7459, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "learning_rate": 0.0002928709055876686, | |
| "loss": 2.6486, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "learning_rate": 0.0002909441233140655, | |
| "loss": 2.6249, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "learning_rate": 0.0002890173410404624, | |
| "loss": 2.5935, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "learning_rate": 0.0002870905587668593, | |
| "loss": 2.422, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "learning_rate": 0.0002851637764932562, | |
| "loss": 2.4574, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "learning_rate": 0.0002832369942196532, | |
| "loss": 2.427, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "learning_rate": 0.00028131021194605007, | |
| "loss": 2.3682, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 1.62, | |
| "learning_rate": 0.000279383429672447, | |
| "loss": 2.2995, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "learning_rate": 0.0002774566473988439, | |
| "loss": 2.1737, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 1.73, | |
| "learning_rate": 0.0002755298651252408, | |
| "loss": 2.1063, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 1.79, | |
| "learning_rate": 0.00027360308285163774, | |
| "loss": 2.0759, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 1.85, | |
| "learning_rate": 0.0002716763005780347, | |
| "loss": 1.9768, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 1.9, | |
| "learning_rate": 0.00026974951830443155, | |
| "loss": 2.0376, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 1.96, | |
| "learning_rate": 0.0002678227360308285, | |
| "loss": 1.9243, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.38400135869565216, | |
| "eval_loss": 2.124117612838745, | |
| "eval_runtime": 166.2747, | |
| "eval_samples_per_second": 35.411, | |
| "eval_steps_per_second": 8.853, | |
| "step": 346 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "learning_rate": 0.0002658959537572254, | |
| "loss": 1.8395, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 2.08, | |
| "learning_rate": 0.00026396917148362235, | |
| "loss": 1.7052, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 2.14, | |
| "learning_rate": 0.00026204238921001923, | |
| "loss": 1.6084, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 2.2, | |
| "learning_rate": 0.00026011560693641616, | |
| "loss": 1.5298, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 2.25, | |
| "learning_rate": 0.0002581888246628131, | |
| "loss": 1.5755, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 2.31, | |
| "learning_rate": 0.00025626204238921, | |
| "loss": 1.4869, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 2.37, | |
| "learning_rate": 0.0002543352601156069, | |
| "loss": 1.5374, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 2.43, | |
| "learning_rate": 0.00025240847784200384, | |
| "loss": 1.448, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 2.48, | |
| "learning_rate": 0.00025048169556840077, | |
| "loss": 1.4246, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 2.54, | |
| "learning_rate": 0.00024855491329479765, | |
| "loss": 1.4545, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 2.6, | |
| "learning_rate": 0.0002466281310211946, | |
| "loss": 1.4417, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 2.66, | |
| "learning_rate": 0.00024470134874759146, | |
| "loss": 1.3385, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 2.71, | |
| "learning_rate": 0.00024277456647398842, | |
| "loss": 1.4229, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 2.77, | |
| "learning_rate": 0.00024084778420038535, | |
| "loss": 1.4225, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 2.83, | |
| "learning_rate": 0.00023892100192678226, | |
| "loss": 1.4259, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 2.89, | |
| "learning_rate": 0.00023699421965317916, | |
| "loss": 1.3656, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 2.95, | |
| "learning_rate": 0.00023506743737957607, | |
| "loss": 1.2923, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.5489130434782609, | |
| "eval_loss": 1.5498348474502563, | |
| "eval_runtime": 166.2498, | |
| "eval_samples_per_second": 35.417, | |
| "eval_steps_per_second": 8.854, | |
| "step": 519 | |
| }, | |
| { | |
| "epoch": 3.01, | |
| "learning_rate": 0.00023314065510597303, | |
| "loss": 1.3854, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 3.06, | |
| "learning_rate": 0.00023121387283236994, | |
| "loss": 1.1289, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 3.12, | |
| "learning_rate": 0.00022928709055876684, | |
| "loss": 0.921, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 3.18, | |
| "learning_rate": 0.00022736030828516375, | |
| "loss": 1.004, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 3.24, | |
| "learning_rate": 0.00022543352601156065, | |
| "loss": 1.0642, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 3.29, | |
| "learning_rate": 0.0002235067437379576, | |
| "loss": 1.0275, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 3.35, | |
| "learning_rate": 0.00022157996146435452, | |
| "loss": 0.9369, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 3.41, | |
| "learning_rate": 0.00021965317919075142, | |
| "loss": 0.9486, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 3.47, | |
| "learning_rate": 0.00021772639691714833, | |
| "loss": 1.0021, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 3.52, | |
| "learning_rate": 0.00021579961464354526, | |
| "loss": 0.8916, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 3.58, | |
| "learning_rate": 0.0002138728323699422, | |
| "loss": 0.9455, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 3.64, | |
| "learning_rate": 0.0002119460500963391, | |
| "loss": 0.9796, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 3.7, | |
| "learning_rate": 0.000210019267822736, | |
| "loss": 0.8681, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 3.76, | |
| "learning_rate": 0.00020809248554913294, | |
| "loss": 0.948, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 3.81, | |
| "learning_rate": 0.00020616570327552984, | |
| "loss": 0.9276, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 3.87, | |
| "learning_rate": 0.00020423892100192677, | |
| "loss": 0.847, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 3.93, | |
| "learning_rate": 0.00020231213872832368, | |
| "loss": 0.9261, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 3.99, | |
| "learning_rate": 0.0002003853564547206, | |
| "loss": 0.8659, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.6126019021739131, | |
| "eval_loss": 1.4952939748764038, | |
| "eval_runtime": 165.9075, | |
| "eval_samples_per_second": 35.49, | |
| "eval_steps_per_second": 8.872, | |
| "step": 692 | |
| }, | |
| { | |
| "epoch": 4.05, | |
| "learning_rate": 0.00019845857418111752, | |
| "loss": 0.6758, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 4.1, | |
| "learning_rate": 0.00019653179190751442, | |
| "loss": 0.5885, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 4.16, | |
| "learning_rate": 0.00019460500963391133, | |
| "loss": 0.6432, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 4.22, | |
| "learning_rate": 0.0001926782273603083, | |
| "loss": 0.6774, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 4.28, | |
| "learning_rate": 0.0001907514450867052, | |
| "loss": 0.7333, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 4.33, | |
| "learning_rate": 0.0001888246628131021, | |
| "loss": 0.6775, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 4.39, | |
| "learning_rate": 0.000186897880539499, | |
| "loss": 0.6461, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 4.45, | |
| "learning_rate": 0.0001849710982658959, | |
| "loss": 0.6192, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 4.51, | |
| "learning_rate": 0.00018304431599229287, | |
| "loss": 0.569, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 4.56, | |
| "learning_rate": 0.00018131021194605008, | |
| "loss": 0.6447, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 4.62, | |
| "learning_rate": 0.00017938342967244698, | |
| "loss": 0.556, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 4.68, | |
| "learning_rate": 0.0001774566473988439, | |
| "loss": 0.6883, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 4.74, | |
| "learning_rate": 0.00017552986512524085, | |
| "loss": 0.6146, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 4.8, | |
| "learning_rate": 0.00017360308285163775, | |
| "loss": 0.6318, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 4.85, | |
| "learning_rate": 0.00017167630057803466, | |
| "loss": 0.5785, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 4.91, | |
| "learning_rate": 0.00016974951830443156, | |
| "loss": 0.6383, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 4.97, | |
| "learning_rate": 0.0001678227360308285, | |
| "loss": 0.5539, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.6925951086956522, | |
| "eval_loss": 1.2430508136749268, | |
| "eval_runtime": 166.7541, | |
| "eval_samples_per_second": 35.309, | |
| "eval_steps_per_second": 8.827, | |
| "step": 865 | |
| }, | |
| { | |
| "epoch": 5.03, | |
| "learning_rate": 0.00016589595375722543, | |
| "loss": 0.5354, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 5.09, | |
| "learning_rate": 0.00016396917148362233, | |
| "loss": 0.4011, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 5.14, | |
| "learning_rate": 0.00016204238921001924, | |
| "loss": 0.4009, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 5.2, | |
| "learning_rate": 0.00016011560693641617, | |
| "loss": 0.459, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 5.26, | |
| "learning_rate": 0.00015818882466281308, | |
| "loss": 0.3829, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 5.32, | |
| "learning_rate": 0.00015626204238921, | |
| "loss": 0.428, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 5.37, | |
| "learning_rate": 0.00015433526011560692, | |
| "loss": 0.4654, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 5.43, | |
| "learning_rate": 0.00015240847784200385, | |
| "loss": 0.4531, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 5.49, | |
| "learning_rate": 0.00015067437379576106, | |
| "loss": 0.4221, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 5.55, | |
| "learning_rate": 0.000148747591522158, | |
| "loss": 0.3927, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 5.61, | |
| "learning_rate": 0.0001468208092485549, | |
| "loss": 0.4451, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 5.66, | |
| "learning_rate": 0.00014489402697495183, | |
| "loss": 0.4363, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 5.72, | |
| "learning_rate": 0.00014296724470134873, | |
| "loss": 0.4583, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 5.78, | |
| "learning_rate": 0.00014104046242774566, | |
| "loss": 0.3788, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 5.84, | |
| "learning_rate": 0.00013911368015414257, | |
| "loss": 0.4333, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 5.89, | |
| "learning_rate": 0.0001371868978805395, | |
| "loss": 0.3448, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 5.95, | |
| "learning_rate": 0.0001352601156069364, | |
| "loss": 0.4101, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.7231657608695652, | |
| "eval_loss": 1.1443275213241577, | |
| "eval_runtime": 167.1514, | |
| "eval_samples_per_second": 35.226, | |
| "eval_steps_per_second": 8.806, | |
| "step": 1038 | |
| }, | |
| { | |
| "epoch": 6.01, | |
| "learning_rate": 0.0001333333333333333, | |
| "loss": 0.4535, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 6.07, | |
| "learning_rate": 0.00013140655105973025, | |
| "loss": 0.3461, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 6.13, | |
| "learning_rate": 0.00012947976878612715, | |
| "loss": 0.2761, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 6.18, | |
| "learning_rate": 0.00012755298651252408, | |
| "loss": 0.2911, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 6.24, | |
| "learning_rate": 0.000125626204238921, | |
| "loss": 0.2985, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 6.3, | |
| "learning_rate": 0.0001236994219653179, | |
| "loss": 0.2858, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 6.36, | |
| "learning_rate": 0.00012177263969171483, | |
| "loss": 0.3162, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 6.41, | |
| "learning_rate": 0.00011984585741811175, | |
| "loss": 0.3326, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 6.47, | |
| "learning_rate": 0.00011791907514450866, | |
| "loss": 0.3024, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 6.53, | |
| "learning_rate": 0.00011599229287090558, | |
| "loss": 0.2981, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 6.59, | |
| "learning_rate": 0.00011406551059730249, | |
| "loss": 0.3112, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 6.65, | |
| "learning_rate": 0.00011213872832369942, | |
| "loss": 0.2206, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 6.7, | |
| "learning_rate": 0.00011021194605009633, | |
| "loss": 0.3052, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 6.76, | |
| "learning_rate": 0.00010828516377649323, | |
| "loss": 0.2799, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 6.82, | |
| "learning_rate": 0.00010635838150289017, | |
| "loss": 0.2793, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 6.88, | |
| "learning_rate": 0.00010443159922928707, | |
| "loss": 0.2992, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 6.93, | |
| "learning_rate": 0.000102504816955684, | |
| "loss": 0.3151, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 6.99, | |
| "learning_rate": 0.00010057803468208092, | |
| "loss": 0.2945, | |
| "step": 1210 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_accuracy": 0.7544157608695652, | |
| "eval_loss": 1.0869863033294678, | |
| "eval_runtime": 167.4711, | |
| "eval_samples_per_second": 35.158, | |
| "eval_steps_per_second": 8.79, | |
| "step": 1211 | |
| }, | |
| { | |
| "epoch": 7.05, | |
| "learning_rate": 9.865125240847783e-05, | |
| "loss": 0.2053, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 7.11, | |
| "learning_rate": 9.672447013487476e-05, | |
| "loss": 0.1619, | |
| "step": 1230 | |
| }, | |
| { | |
| "epoch": 7.17, | |
| "learning_rate": 9.479768786127167e-05, | |
| "loss": 0.2176, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 7.22, | |
| "learning_rate": 9.28709055876686e-05, | |
| "loss": 0.1907, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 7.28, | |
| "learning_rate": 9.09441233140655e-05, | |
| "loss": 0.1517, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 7.34, | |
| "learning_rate": 8.901734104046241e-05, | |
| "loss": 0.1932, | |
| "step": 1270 | |
| }, | |
| { | |
| "epoch": 7.4, | |
| "learning_rate": 8.709055876685934e-05, | |
| "loss": 0.2175, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 7.46, | |
| "learning_rate": 8.516377649325625e-05, | |
| "loss": 0.1794, | |
| "step": 1290 | |
| }, | |
| { | |
| "epoch": 7.51, | |
| "learning_rate": 8.323699421965317e-05, | |
| "loss": 0.1934, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 7.57, | |
| "learning_rate": 8.131021194605009e-05, | |
| "loss": 0.2138, | |
| "step": 1310 | |
| }, | |
| { | |
| "epoch": 7.63, | |
| "learning_rate": 7.9383429672447e-05, | |
| "loss": 0.1451, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 7.69, | |
| "learning_rate": 7.745664739884392e-05, | |
| "loss": 0.1691, | |
| "step": 1330 | |
| }, | |
| { | |
| "epoch": 7.74, | |
| "learning_rate": 7.552986512524084e-05, | |
| "loss": 0.1672, | |
| "step": 1340 | |
| }, | |
| { | |
| "epoch": 7.8, | |
| "learning_rate": 7.360308285163776e-05, | |
| "loss": 0.2004, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 7.86, | |
| "learning_rate": 7.167630057803468e-05, | |
| "loss": 0.1925, | |
| "step": 1360 | |
| }, | |
| { | |
| "epoch": 7.92, | |
| "learning_rate": 6.974951830443159e-05, | |
| "loss": 0.1649, | |
| "step": 1370 | |
| }, | |
| { | |
| "epoch": 7.97, | |
| "learning_rate": 6.78227360308285e-05, | |
| "loss": 0.1552, | |
| "step": 1380 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.7661345108695652, | |
| "eval_loss": 1.1080151796340942, | |
| "eval_runtime": 167.1864, | |
| "eval_samples_per_second": 35.218, | |
| "eval_steps_per_second": 8.805, | |
| "step": 1384 | |
| }, | |
| { | |
| "epoch": 8.03, | |
| "learning_rate": 6.589595375722542e-05, | |
| "loss": 0.1643, | |
| "step": 1390 | |
| }, | |
| { | |
| "epoch": 8.09, | |
| "learning_rate": 6.396917148362234e-05, | |
| "loss": 0.08, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 8.15, | |
| "learning_rate": 6.204238921001926e-05, | |
| "loss": 0.1022, | |
| "step": 1410 | |
| }, | |
| { | |
| "epoch": 8.21, | |
| "learning_rate": 6.0115606936416174e-05, | |
| "loss": 0.1466, | |
| "step": 1420 | |
| }, | |
| { | |
| "epoch": 8.27, | |
| "learning_rate": 5.81888246628131e-05, | |
| "loss": 0.1262, | |
| "step": 1430 | |
| }, | |
| { | |
| "epoch": 8.32, | |
| "learning_rate": 5.626204238921002e-05, | |
| "loss": 0.0895, | |
| "step": 1440 | |
| }, | |
| { | |
| "epoch": 8.38, | |
| "learning_rate": 5.433526011560694e-05, | |
| "loss": 0.1155, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 8.44, | |
| "learning_rate": 5.2408477842003843e-05, | |
| "loss": 0.1205, | |
| "step": 1460 | |
| }, | |
| { | |
| "epoch": 8.5, | |
| "learning_rate": 5.048169556840076e-05, | |
| "loss": 0.1196, | |
| "step": 1470 | |
| }, | |
| { | |
| "epoch": 8.55, | |
| "learning_rate": 4.855491329479768e-05, | |
| "loss": 0.1488, | |
| "step": 1480 | |
| }, | |
| { | |
| "epoch": 8.61, | |
| "learning_rate": 4.66281310211946e-05, | |
| "loss": 0.1263, | |
| "step": 1490 | |
| }, | |
| { | |
| "epoch": 8.67, | |
| "learning_rate": 4.470134874759151e-05, | |
| "loss": 0.1289, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 8.73, | |
| "learning_rate": 4.277456647398843e-05, | |
| "loss": 0.1628, | |
| "step": 1510 | |
| }, | |
| { | |
| "epoch": 8.78, | |
| "learning_rate": 4.084778420038535e-05, | |
| "loss": 0.1665, | |
| "step": 1520 | |
| }, | |
| { | |
| "epoch": 8.84, | |
| "learning_rate": 3.892100192678227e-05, | |
| "loss": 0.1234, | |
| "step": 1530 | |
| }, | |
| { | |
| "epoch": 8.9, | |
| "learning_rate": 3.699421965317919e-05, | |
| "loss": 0.1146, | |
| "step": 1540 | |
| }, | |
| { | |
| "epoch": 8.96, | |
| "learning_rate": 3.506743737957611e-05, | |
| "loss": 0.0968, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_accuracy": 0.7944972826086957, | |
| "eval_loss": 0.9835737347602844, | |
| "eval_runtime": 167.3463, | |
| "eval_samples_per_second": 35.185, | |
| "eval_steps_per_second": 8.796, | |
| "step": 1557 | |
| }, | |
| { | |
| "epoch": 9.02, | |
| "learning_rate": 3.314065510597302e-05, | |
| "loss": 0.1091, | |
| "step": 1560 | |
| }, | |
| { | |
| "epoch": 9.07, | |
| "learning_rate": 3.121387283236994e-05, | |
| "loss": 0.1036, | |
| "step": 1570 | |
| }, | |
| { | |
| "epoch": 9.13, | |
| "learning_rate": 2.9287090558766855e-05, | |
| "loss": 0.1183, | |
| "step": 1580 | |
| }, | |
| { | |
| "epoch": 9.19, | |
| "learning_rate": 2.7360308285163774e-05, | |
| "loss": 0.0903, | |
| "step": 1590 | |
| }, | |
| { | |
| "epoch": 9.25, | |
| "learning_rate": 2.543352601156069e-05, | |
| "loss": 0.0808, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 9.31, | |
| "learning_rate": 2.350674373795761e-05, | |
| "loss": 0.0749, | |
| "step": 1610 | |
| }, | |
| { | |
| "epoch": 9.36, | |
| "learning_rate": 2.1579961464354524e-05, | |
| "loss": 0.0523, | |
| "step": 1620 | |
| }, | |
| { | |
| "epoch": 9.42, | |
| "learning_rate": 1.9653179190751443e-05, | |
| "loss": 0.1112, | |
| "step": 1630 | |
| }, | |
| { | |
| "epoch": 9.48, | |
| "learning_rate": 1.7726396917148362e-05, | |
| "loss": 0.0949, | |
| "step": 1640 | |
| }, | |
| { | |
| "epoch": 9.54, | |
| "learning_rate": 1.5799614643545278e-05, | |
| "loss": 0.0858, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 9.59, | |
| "learning_rate": 1.3872832369942195e-05, | |
| "loss": 0.0603, | |
| "step": 1660 | |
| }, | |
| { | |
| "epoch": 9.65, | |
| "learning_rate": 1.1946050096339112e-05, | |
| "loss": 0.0718, | |
| "step": 1670 | |
| }, | |
| { | |
| "epoch": 9.71, | |
| "learning_rate": 1.0019267822736031e-05, | |
| "loss": 0.069, | |
| "step": 1680 | |
| }, | |
| { | |
| "epoch": 9.77, | |
| "learning_rate": 8.092485549132947e-06, | |
| "loss": 0.0748, | |
| "step": 1690 | |
| }, | |
| { | |
| "epoch": 9.82, | |
| "learning_rate": 6.165703275529864e-06, | |
| "loss": 0.0831, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 9.88, | |
| "learning_rate": 4.2389210019267816e-06, | |
| "loss": 0.0635, | |
| "step": 1710 | |
| }, | |
| { | |
| "epoch": 9.94, | |
| "learning_rate": 2.3121387283236993e-06, | |
| "loss": 0.0675, | |
| "step": 1720 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "learning_rate": 3.853564547206165e-07, | |
| "loss": 0.0623, | |
| "step": 1730 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_accuracy": 0.7992527173913043, | |
| "eval_loss": 1.0252065658569336, | |
| "eval_runtime": 167.8251, | |
| "eval_samples_per_second": 35.084, | |
| "eval_steps_per_second": 8.771, | |
| "step": 1730 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "step": 1730, | |
| "total_flos": 1.8408056270747849e+19, | |
| "train_loss": 1.0006333545797823, | |
| "train_runtime": 3643.6893, | |
| "train_samples_per_second": 60.911, | |
| "train_steps_per_second": 0.475 | |
| } | |
| ], | |
| "max_steps": 1730, | |
| "num_train_epochs": 10, | |
| "total_flos": 1.8408056270747849e+19, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |