| { | |
| "best_metric": 2.0878255367279053, | |
| "best_model_checkpoint": "path_to_your_model_and_data/pose/results/2k-32k-yarn/checkpoint-1000", | |
| "epoch": 0.6896551724137931, | |
| "eval_steps": 50, | |
| "global_step": 1000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 1.2041199826559246e-05, | |
| "loss": 1.6869, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 1.9084850188786497e-05, | |
| "loss": 1.6045, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 1.993939393939394e-05, | |
| "loss": 1.5365, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 1.985858585858586e-05, | |
| "loss": 1.6548, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 1.975757575757576e-05, | |
| "loss": 1.7008, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 1.9656565656565658e-05, | |
| "loss": 1.6702, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 1.9555555555555557e-05, | |
| "loss": 1.6943, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 1.9454545454545457e-05, | |
| "loss": 1.6775, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 1.9353535353535356e-05, | |
| "loss": 1.7281, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 1.9252525252525252e-05, | |
| "loss": 1.6746, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "eval_loss": 2.0998010635375977, | |
| "eval_runtime": 127.4969, | |
| "eval_samples_per_second": 0.784, | |
| "eval_steps_per_second": 0.102, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 1.9151515151515152e-05, | |
| "loss": 1.7754, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 1.905050505050505e-05, | |
| "loss": 1.7094, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 1.894949494949495e-05, | |
| "loss": 1.6483, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 1.886868686868687e-05, | |
| "loss": 1.7341, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 1.876767676767677e-05, | |
| "loss": 1.6221, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 1.866666666666667e-05, | |
| "loss": 1.5681, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 1.8565656565656568e-05, | |
| "loss": 1.6668, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 1.8464646464646464e-05, | |
| "loss": 1.6743, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 1.8363636363636367e-05, | |
| "loss": 1.7875, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 1.8262626262626263e-05, | |
| "loss": 1.7397, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "eval_loss": 2.1947836875915527, | |
| "eval_runtime": 127.4557, | |
| "eval_samples_per_second": 0.785, | |
| "eval_steps_per_second": 0.102, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 1.8161616161616163e-05, | |
| "loss": 1.6912, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 1.8060606060606062e-05, | |
| "loss": 1.7995, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 1.795959595959596e-05, | |
| "loss": 1.6217, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 1.785858585858586e-05, | |
| "loss": 1.7081, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 1.775757575757576e-05, | |
| "loss": 1.7041, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 1.765656565656566e-05, | |
| "loss": 1.6235, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 1.7555555555555556e-05, | |
| "loss": 1.6583, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 1.7454545454545456e-05, | |
| "loss": 1.7467, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 1.7353535353535355e-05, | |
| "loss": 1.6531, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 1.7252525252525255e-05, | |
| "loss": 1.7272, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "eval_loss": 2.1845450401306152, | |
| "eval_runtime": 127.0346, | |
| "eval_samples_per_second": 0.787, | |
| "eval_steps_per_second": 0.102, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 1.715151515151515e-05, | |
| "loss": 1.6193, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 1.7050505050505054e-05, | |
| "loss": 1.6174, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 1.694949494949495e-05, | |
| "loss": 1.665, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 1.684848484848485e-05, | |
| "loss": 1.7045, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 1.674747474747475e-05, | |
| "loss": 1.7124, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 1.6646464646464648e-05, | |
| "loss": 1.8402, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 1.6545454545454548e-05, | |
| "loss": 1.6673, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 1.6444444444444444e-05, | |
| "loss": 1.7193, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 1.6343434343434346e-05, | |
| "loss": 1.6832, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 1.6242424242424243e-05, | |
| "loss": 1.6866, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "eval_loss": 2.1831867694854736, | |
| "eval_runtime": 127.2543, | |
| "eval_samples_per_second": 0.786, | |
| "eval_steps_per_second": 0.102, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 1.6141414141414142e-05, | |
| "loss": 1.6387, | |
| "step": 205 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 1.604040404040404e-05, | |
| "loss": 1.7822, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 1.593939393939394e-05, | |
| "loss": 1.6705, | |
| "step": 215 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 1.585858585858586e-05, | |
| "loss": 1.6592, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 1.575757575757576e-05, | |
| "loss": 1.6256, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 1.565656565656566e-05, | |
| "loss": 1.6946, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 1.555555555555556e-05, | |
| "loss": 1.6859, | |
| "step": 235 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 1.5454545454545454e-05, | |
| "loss": 1.674, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 1.5353535353535354e-05, | |
| "loss": 1.7687, | |
| "step": 245 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 1.5252525252525255e-05, | |
| "loss": 1.6456, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "eval_loss": 2.1776535511016846, | |
| "eval_runtime": 127.5296, | |
| "eval_samples_per_second": 0.784, | |
| "eval_steps_per_second": 0.102, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 1.5151515151515153e-05, | |
| "loss": 1.6896, | |
| "step": 255 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 1.505050505050505e-05, | |
| "loss": 1.7209, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 1.4949494949494952e-05, | |
| "loss": 1.66, | |
| "step": 265 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 1.484848484848485e-05, | |
| "loss": 1.6708, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 1.4747474747474747e-05, | |
| "loss": 1.6432, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 1.4646464646464649e-05, | |
| "loss": 1.6676, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 1.4545454545454546e-05, | |
| "loss": 1.6768, | |
| "step": 285 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 1.4444444444444446e-05, | |
| "loss": 1.7592, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 1.4343434343434344e-05, | |
| "loss": 1.6192, | |
| "step": 295 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 1.4242424242424245e-05, | |
| "loss": 1.5604, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "eval_loss": 2.1859655380249023, | |
| "eval_runtime": 127.9048, | |
| "eval_samples_per_second": 0.782, | |
| "eval_steps_per_second": 0.102, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 1.4141414141414143e-05, | |
| "loss": 1.6379, | |
| "step": 305 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 1.404040404040404e-05, | |
| "loss": 1.6012, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 1.3939393939393942e-05, | |
| "loss": 1.7011, | |
| "step": 315 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 1.383838383838384e-05, | |
| "loss": 1.6168, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 1.3737373737373739e-05, | |
| "loss": 1.6507, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 1.3636363636363637e-05, | |
| "loss": 1.7676, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 1.3535353535353538e-05, | |
| "loss": 1.6707, | |
| "step": 335 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 1.3434343434343436e-05, | |
| "loss": 1.6062, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 1.3333333333333333e-05, | |
| "loss": 1.7136, | |
| "step": 345 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 1.3232323232323234e-05, | |
| "loss": 1.661, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "eval_loss": 2.189072370529175, | |
| "eval_runtime": 127.1833, | |
| "eval_samples_per_second": 0.786, | |
| "eval_steps_per_second": 0.102, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 1.3131313131313132e-05, | |
| "loss": 1.6766, | |
| "step": 355 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 1.3030303030303032e-05, | |
| "loss": 1.6497, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 1.2929292929292931e-05, | |
| "loss": 1.6738, | |
| "step": 365 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 1.2828282828282829e-05, | |
| "loss": 1.6673, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 1.2727272727272728e-05, | |
| "loss": 1.6767, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 1.2626262626262626e-05, | |
| "loss": 1.7335, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 1.2525252525252527e-05, | |
| "loss": 1.5885, | |
| "step": 385 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 1.2424242424242425e-05, | |
| "loss": 1.5992, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 1.2323232323232323e-05, | |
| "loss": 1.6115, | |
| "step": 395 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 1.2222222222222224e-05, | |
| "loss": 1.7397, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "eval_loss": 2.1878244876861572, | |
| "eval_runtime": 127.871, | |
| "eval_samples_per_second": 0.782, | |
| "eval_steps_per_second": 0.102, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 1.2121212121212122e-05, | |
| "loss": 1.6486, | |
| "step": 405 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 1.2020202020202021e-05, | |
| "loss": 1.6822, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 1.191919191919192e-05, | |
| "loss": 1.6529, | |
| "step": 415 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 1.181818181818182e-05, | |
| "loss": 1.6155, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 1.1717171717171718e-05, | |
| "loss": 1.6216, | |
| "step": 425 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 1.1616161616161616e-05, | |
| "loss": 1.5922, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 1.1515151515151517e-05, | |
| "loss": 1.7198, | |
| "step": 435 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 1.1414141414141415e-05, | |
| "loss": 1.5924, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 1.1313131313131314e-05, | |
| "loss": 1.6722, | |
| "step": 445 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 1.1212121212121212e-05, | |
| "loss": 1.5975, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "eval_loss": 2.185619592666626, | |
| "eval_runtime": 127.8889, | |
| "eval_samples_per_second": 0.782, | |
| "eval_steps_per_second": 0.102, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 1.1111111111111113e-05, | |
| "loss": 1.6218, | |
| "step": 455 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 1.1010101010101011e-05, | |
| "loss": 1.613, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 1.0909090909090909e-05, | |
| "loss": 1.7023, | |
| "step": 465 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 1.080808080808081e-05, | |
| "loss": 1.6097, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 1.0707070707070708e-05, | |
| "loss": 1.5922, | |
| "step": 475 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 1.0606060606060606e-05, | |
| "loss": 1.6736, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 1.0505050505050507e-05, | |
| "loss": 1.6033, | |
| "step": 485 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 1.0404040404040405e-05, | |
| "loss": 1.6552, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 1.0303030303030304e-05, | |
| "loss": 1.6533, | |
| "step": 495 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 1.0202020202020202e-05, | |
| "loss": 1.6899, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "eval_loss": 2.1731319427490234, | |
| "eval_runtime": 127.9869, | |
| "eval_samples_per_second": 0.781, | |
| "eval_steps_per_second": 0.102, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 1.0101010101010103e-05, | |
| "loss": 1.6272, | |
| "step": 505 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 1e-05, | |
| "loss": 1.6105, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 9.8989898989899e-06, | |
| "loss": 1.522, | |
| "step": 515 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 9.797979797979798e-06, | |
| "loss": 1.6022, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 9.696969696969698e-06, | |
| "loss": 1.6157, | |
| "step": 525 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 9.595959595959597e-06, | |
| "loss": 1.7323, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 9.494949494949497e-06, | |
| "loss": 1.5535, | |
| "step": 535 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 9.393939393939396e-06, | |
| "loss": 1.6378, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 9.292929292929294e-06, | |
| "loss": 1.5394, | |
| "step": 545 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 9.191919191919193e-06, | |
| "loss": 1.6862, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "eval_loss": 2.1638994216918945, | |
| "eval_runtime": 127.6725, | |
| "eval_samples_per_second": 0.783, | |
| "eval_steps_per_second": 0.102, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 9.090909090909091e-06, | |
| "loss": 1.5748, | |
| "step": 555 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 8.98989898989899e-06, | |
| "loss": 1.6246, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 8.888888888888888e-06, | |
| "loss": 1.6118, | |
| "step": 565 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 8.787878787878788e-06, | |
| "loss": 1.5606, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 8.686868686868687e-06, | |
| "loss": 1.5704, | |
| "step": 575 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 8.585858585858587e-06, | |
| "loss": 1.6683, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 8.484848484848486e-06, | |
| "loss": 1.6215, | |
| "step": 585 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 8.383838383838384e-06, | |
| "loss": 1.6727, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 8.282828282828283e-06, | |
| "loss": 1.5615, | |
| "step": 595 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 8.181818181818183e-06, | |
| "loss": 1.6431, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "eval_loss": 2.1520442962646484, | |
| "eval_runtime": 127.6384, | |
| "eval_samples_per_second": 0.783, | |
| "eval_steps_per_second": 0.102, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 8.08080808080808e-06, | |
| "loss": 1.5967, | |
| "step": 605 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 7.97979797979798e-06, | |
| "loss": 1.6016, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 7.87878787878788e-06, | |
| "loss": 1.5905, | |
| "step": 615 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 7.77777777777778e-06, | |
| "loss": 1.6387, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 7.676767676767677e-06, | |
| "loss": 1.6255, | |
| "step": 625 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 7.5757575757575764e-06, | |
| "loss": 1.642, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 7.474747474747476e-06, | |
| "loss": 1.6004, | |
| "step": 635 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 7.373737373737374e-06, | |
| "loss": 1.5635, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 7.272727272727273e-06, | |
| "loss": 1.6266, | |
| "step": 645 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 7.171717171717172e-06, | |
| "loss": 1.5906, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "eval_loss": 2.1461074352264404, | |
| "eval_runtime": 126.7907, | |
| "eval_samples_per_second": 0.789, | |
| "eval_steps_per_second": 0.103, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 7.070707070707071e-06, | |
| "loss": 1.5335, | |
| "step": 655 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 6.969696969696971e-06, | |
| "loss": 1.5319, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 6.868686868686869e-06, | |
| "loss": 1.5643, | |
| "step": 665 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 6.767676767676769e-06, | |
| "loss": 1.635, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 6.666666666666667e-06, | |
| "loss": 1.5881, | |
| "step": 675 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 6.565656565656566e-06, | |
| "loss": 1.5855, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 6.464646464646466e-06, | |
| "loss": 1.5281, | |
| "step": 685 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 6.363636363636364e-06, | |
| "loss": 1.5686, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 6.262626262626264e-06, | |
| "loss": 1.5815, | |
| "step": 695 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 6.1616161616161615e-06, | |
| "loss": 1.6277, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "eval_loss": 2.1339261531829834, | |
| "eval_runtime": 127.7156, | |
| "eval_samples_per_second": 0.783, | |
| "eval_steps_per_second": 0.102, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 6.060606060606061e-06, | |
| "loss": 1.6068, | |
| "step": 705 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 5.95959595959596e-06, | |
| "loss": 1.6653, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 5.858585858585859e-06, | |
| "loss": 1.5389, | |
| "step": 715 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 5.7575757575757586e-06, | |
| "loss": 1.5535, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 5.656565656565657e-06, | |
| "loss": 1.621, | |
| "step": 725 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 5.555555555555557e-06, | |
| "loss": 1.56, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 5.4545454545454545e-06, | |
| "loss": 1.5491, | |
| "step": 735 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 5.353535353535354e-06, | |
| "loss": 1.5151, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 5.252525252525253e-06, | |
| "loss": 1.5135, | |
| "step": 745 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 5.151515151515152e-06, | |
| "loss": 1.4665, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "eval_loss": 2.127960681915283, | |
| "eval_runtime": 126.9672, | |
| "eval_samples_per_second": 0.788, | |
| "eval_steps_per_second": 0.102, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 5.0505050505050515e-06, | |
| "loss": 1.5305, | |
| "step": 755 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 4.94949494949495e-06, | |
| "loss": 1.531, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 4.848484848484849e-06, | |
| "loss": 1.6151, | |
| "step": 765 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 4.747474747474748e-06, | |
| "loss": 1.5451, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 4.646464646464647e-06, | |
| "loss": 1.5876, | |
| "step": 775 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 4.5454545454545455e-06, | |
| "loss": 1.4907, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 4.444444444444444e-06, | |
| "loss": 1.5307, | |
| "step": 785 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 4.343434343434344e-06, | |
| "loss": 1.4979, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 4.242424242424243e-06, | |
| "loss": 1.5098, | |
| "step": 795 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 4.141414141414142e-06, | |
| "loss": 1.6528, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "eval_loss": 2.1138248443603516, | |
| "eval_runtime": 127.0916, | |
| "eval_samples_per_second": 0.787, | |
| "eval_steps_per_second": 0.102, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 4.04040404040404e-06, | |
| "loss": 1.5037, | |
| "step": 805 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 3.93939393939394e-06, | |
| "loss": 1.5584, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 3.8383838383838385e-06, | |
| "loss": 1.5794, | |
| "step": 815 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 3.737373737373738e-06, | |
| "loss": 1.4932, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 3.6363636363636366e-06, | |
| "loss": 1.5709, | |
| "step": 825 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 3.5353535353535356e-06, | |
| "loss": 1.5937, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 3.4343434343434347e-06, | |
| "loss": 1.5733, | |
| "step": 835 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 3.3333333333333333e-06, | |
| "loss": 1.5532, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 3.232323232323233e-06, | |
| "loss": 1.531, | |
| "step": 845 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 3.131313131313132e-06, | |
| "loss": 1.4618, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "eval_loss": 2.104820489883423, | |
| "eval_runtime": 126.9789, | |
| "eval_samples_per_second": 0.788, | |
| "eval_steps_per_second": 0.102, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 3.0303030303030305e-06, | |
| "loss": 1.5802, | |
| "step": 855 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 2.9292929292929295e-06, | |
| "loss": 1.4664, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 2.8282828282828286e-06, | |
| "loss": 1.6319, | |
| "step": 865 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 2.7272727272727272e-06, | |
| "loss": 1.5629, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 2.6262626262626267e-06, | |
| "loss": 1.5942, | |
| "step": 875 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 2.5252525252525258e-06, | |
| "loss": 1.5522, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 2.4242424242424244e-06, | |
| "loss": 1.5326, | |
| "step": 885 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 2.3232323232323234e-06, | |
| "loss": 1.5492, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 2.222222222222222e-06, | |
| "loss": 1.483, | |
| "step": 895 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 2.1212121212121216e-06, | |
| "loss": 1.4871, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "eval_loss": 2.096195936203003, | |
| "eval_runtime": 127.2807, | |
| "eval_samples_per_second": 0.786, | |
| "eval_steps_per_second": 0.102, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 2.02020202020202e-06, | |
| "loss": 1.4819, | |
| "step": 905 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 1.9191919191919192e-06, | |
| "loss": 1.5326, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 1.8181818181818183e-06, | |
| "loss": 1.5267, | |
| "step": 915 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 1.7171717171717173e-06, | |
| "loss": 1.422, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 1.6161616161616164e-06, | |
| "loss": 1.5205, | |
| "step": 925 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 1.5151515151515152e-06, | |
| "loss": 1.5186, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 1.4141414141414143e-06, | |
| "loss": 1.5456, | |
| "step": 935 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 1.3131313131313134e-06, | |
| "loss": 1.5378, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 1.2121212121212122e-06, | |
| "loss": 1.4828, | |
| "step": 945 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 1.111111111111111e-06, | |
| "loss": 1.6019, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "eval_loss": 2.090965509414673, | |
| "eval_runtime": 126.05, | |
| "eval_samples_per_second": 0.793, | |
| "eval_steps_per_second": 0.103, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 1.01010101010101e-06, | |
| "loss": 1.4365, | |
| "step": 955 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 9.090909090909091e-07, | |
| "loss": 1.4373, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 8.080808080808082e-07, | |
| "loss": 1.5253, | |
| "step": 965 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 7.070707070707071e-07, | |
| "loss": 1.6014, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 6.060606060606061e-07, | |
| "loss": 1.549, | |
| "step": 975 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 5.05050505050505e-07, | |
| "loss": 1.5057, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 4.040404040404041e-07, | |
| "loss": 1.4688, | |
| "step": 985 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 3.0303030303030305e-07, | |
| "loss": 1.4982, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 2.0202020202020205e-07, | |
| "loss": 1.5032, | |
| "step": 995 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 1.0101010101010103e-07, | |
| "loss": 1.5359, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "eval_loss": 2.0878255367279053, | |
| "eval_runtime": 126.9736, | |
| "eval_samples_per_second": 0.788, | |
| "eval_steps_per_second": 0.102, | |
| "step": 1000 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 1000, | |
| "num_train_epochs": 1, | |
| "save_steps": 100, | |
| "total_flos": 50751528222720.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |