| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "eval_steps": 0, | |
| "global_step": 495, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00202020202020202, | |
| "grad_norm": 0.466796875, | |
| "learning_rate": 9.97979797979798e-06, | |
| "loss": 1.793, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00404040404040404, | |
| "grad_norm": 0.4453125, | |
| "learning_rate": 9.95959595959596e-06, | |
| "loss": 1.8337, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.006060606060606061, | |
| "grad_norm": 0.4296875, | |
| "learning_rate": 9.939393939393939e-06, | |
| "loss": 1.829, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00808080808080808, | |
| "grad_norm": 0.43359375, | |
| "learning_rate": 9.91919191919192e-06, | |
| "loss": 1.7952, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.010101010101010102, | |
| "grad_norm": 0.412109375, | |
| "learning_rate": 9.8989898989899e-06, | |
| "loss": 1.8804, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.012121212121212121, | |
| "grad_norm": 0.5390625, | |
| "learning_rate": 9.87878787878788e-06, | |
| "loss": 1.8649, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.014141414141414142, | |
| "grad_norm": 0.365234375, | |
| "learning_rate": 9.85858585858586e-06, | |
| "loss": 1.8901, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.01616161616161616, | |
| "grad_norm": 0.33203125, | |
| "learning_rate": 9.838383838383839e-06, | |
| "loss": 1.7955, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.01818181818181818, | |
| "grad_norm": 0.32421875, | |
| "learning_rate": 9.81818181818182e-06, | |
| "loss": 1.8151, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.020202020202020204, | |
| "grad_norm": 0.310546875, | |
| "learning_rate": 9.797979797979798e-06, | |
| "loss": 1.7557, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.022222222222222223, | |
| "grad_norm": 0.31640625, | |
| "learning_rate": 9.777777777777779e-06, | |
| "loss": 1.7174, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.024242424242424242, | |
| "grad_norm": 0.287109375, | |
| "learning_rate": 9.757575757575758e-06, | |
| "loss": 1.7118, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.026262626262626262, | |
| "grad_norm": 0.279296875, | |
| "learning_rate": 9.737373737373738e-06, | |
| "loss": 1.5918, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.028282828282828285, | |
| "grad_norm": 0.302734375, | |
| "learning_rate": 9.717171717171719e-06, | |
| "loss": 1.6372, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.030303030303030304, | |
| "grad_norm": 0.283203125, | |
| "learning_rate": 9.696969696969698e-06, | |
| "loss": 1.6647, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.03232323232323232, | |
| "grad_norm": 0.296875, | |
| "learning_rate": 9.676767676767678e-06, | |
| "loss": 1.6657, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.03434343434343434, | |
| "grad_norm": 0.283203125, | |
| "learning_rate": 9.656565656565657e-06, | |
| "loss": 1.4841, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.03636363636363636, | |
| "grad_norm": 0.2890625, | |
| "learning_rate": 9.636363636363638e-06, | |
| "loss": 1.5899, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.03838383838383838, | |
| "grad_norm": 0.29296875, | |
| "learning_rate": 9.616161616161616e-06, | |
| "loss": 1.6603, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.04040404040404041, | |
| "grad_norm": 0.275390625, | |
| "learning_rate": 9.595959595959597e-06, | |
| "loss": 1.5316, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.04242424242424243, | |
| "grad_norm": 0.30859375, | |
| "learning_rate": 9.575757575757576e-06, | |
| "loss": 1.6512, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.044444444444444446, | |
| "grad_norm": 0.25390625, | |
| "learning_rate": 9.555555555555556e-06, | |
| "loss": 1.499, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.046464646464646465, | |
| "grad_norm": 0.263671875, | |
| "learning_rate": 9.535353535353537e-06, | |
| "loss": 1.5049, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.048484848484848485, | |
| "grad_norm": 0.25, | |
| "learning_rate": 9.515151515151516e-06, | |
| "loss": 1.5328, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.050505050505050504, | |
| "grad_norm": 0.240234375, | |
| "learning_rate": 9.494949494949497e-06, | |
| "loss": 1.5673, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.052525252525252523, | |
| "grad_norm": 0.259765625, | |
| "learning_rate": 9.474747474747475e-06, | |
| "loss": 1.5331, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.05454545454545454, | |
| "grad_norm": 0.2373046875, | |
| "learning_rate": 9.454545454545456e-06, | |
| "loss": 1.5281, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.05656565656565657, | |
| "grad_norm": 0.220703125, | |
| "learning_rate": 9.434343434343435e-06, | |
| "loss": 1.4541, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.05858585858585859, | |
| "grad_norm": 0.2431640625, | |
| "learning_rate": 9.414141414141414e-06, | |
| "loss": 1.5046, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.06060606060606061, | |
| "grad_norm": 0.234375, | |
| "learning_rate": 9.393939393939396e-06, | |
| "loss": 1.4657, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.06262626262626263, | |
| "grad_norm": 0.2275390625, | |
| "learning_rate": 9.373737373737375e-06, | |
| "loss": 1.3571, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.06464646464646465, | |
| "grad_norm": 0.296875, | |
| "learning_rate": 9.353535353535354e-06, | |
| "loss": 1.3992, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.06666666666666667, | |
| "grad_norm": 0.287109375, | |
| "learning_rate": 9.333333333333334e-06, | |
| "loss": 1.4552, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.06868686868686869, | |
| "grad_norm": 0.216796875, | |
| "learning_rate": 9.313131313131313e-06, | |
| "loss": 1.4571, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.0707070707070707, | |
| "grad_norm": 0.2265625, | |
| "learning_rate": 9.292929292929294e-06, | |
| "loss": 1.4078, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.07272727272727272, | |
| "grad_norm": 0.279296875, | |
| "learning_rate": 9.272727272727273e-06, | |
| "loss": 1.3755, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.07474747474747474, | |
| "grad_norm": 0.2021484375, | |
| "learning_rate": 9.252525252525253e-06, | |
| "loss": 1.3593, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.07676767676767676, | |
| "grad_norm": 0.1923828125, | |
| "learning_rate": 9.232323232323232e-06, | |
| "loss": 1.2517, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.07878787878787878, | |
| "grad_norm": 0.33984375, | |
| "learning_rate": 9.212121212121213e-06, | |
| "loss": 1.3804, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.08080808080808081, | |
| "grad_norm": 0.2001953125, | |
| "learning_rate": 9.191919191919193e-06, | |
| "loss": 1.3428, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.08282828282828283, | |
| "grad_norm": 0.2109375, | |
| "learning_rate": 9.171717171717172e-06, | |
| "loss": 1.3576, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.08484848484848485, | |
| "grad_norm": 0.197265625, | |
| "learning_rate": 9.151515151515153e-06, | |
| "loss": 1.3772, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.08686868686868687, | |
| "grad_norm": 0.1826171875, | |
| "learning_rate": 9.131313131313132e-06, | |
| "loss": 1.2995, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.08888888888888889, | |
| "grad_norm": 0.185546875, | |
| "learning_rate": 9.111111111111112e-06, | |
| "loss": 1.3324, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.09090909090909091, | |
| "grad_norm": 0.1953125, | |
| "learning_rate": 9.090909090909091e-06, | |
| "loss": 1.324, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.09292929292929293, | |
| "grad_norm": 0.1923828125, | |
| "learning_rate": 9.070707070707072e-06, | |
| "loss": 1.3671, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.09494949494949495, | |
| "grad_norm": 0.1826171875, | |
| "learning_rate": 9.050505050505052e-06, | |
| "loss": 1.3559, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.09696969696969697, | |
| "grad_norm": 0.1728515625, | |
| "learning_rate": 9.030303030303031e-06, | |
| "loss": 1.3197, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.09898989898989899, | |
| "grad_norm": 0.171875, | |
| "learning_rate": 9.010101010101012e-06, | |
| "loss": 1.2988, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.10101010101010101, | |
| "grad_norm": 0.35546875, | |
| "learning_rate": 8.98989898989899e-06, | |
| "loss": 1.29, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.10303030303030303, | |
| "grad_norm": 0.1787109375, | |
| "learning_rate": 8.969696969696971e-06, | |
| "loss": 1.2839, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.10505050505050505, | |
| "grad_norm": 0.1650390625, | |
| "learning_rate": 8.94949494949495e-06, | |
| "loss": 1.244, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.10707070707070707, | |
| "grad_norm": 0.1689453125, | |
| "learning_rate": 8.92929292929293e-06, | |
| "loss": 1.2877, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.10909090909090909, | |
| "grad_norm": 0.1787109375, | |
| "learning_rate": 8.90909090909091e-06, | |
| "loss": 1.269, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.1111111111111111, | |
| "grad_norm": 0.171875, | |
| "learning_rate": 8.888888888888888e-06, | |
| "loss": 1.3108, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.11313131313131314, | |
| "grad_norm": 0.16796875, | |
| "learning_rate": 8.86868686868687e-06, | |
| "loss": 1.3129, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.11515151515151516, | |
| "grad_norm": 0.1728515625, | |
| "learning_rate": 8.84848484848485e-06, | |
| "loss": 1.1976, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.11717171717171718, | |
| "grad_norm": 0.169921875, | |
| "learning_rate": 8.82828282828283e-06, | |
| "loss": 1.283, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.1191919191919192, | |
| "grad_norm": 0.15625, | |
| "learning_rate": 8.808080808080809e-06, | |
| "loss": 1.2786, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.12121212121212122, | |
| "grad_norm": 0.197265625, | |
| "learning_rate": 8.787878787878788e-06, | |
| "loss": 1.2718, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.12323232323232323, | |
| "grad_norm": 0.181640625, | |
| "learning_rate": 8.767676767676768e-06, | |
| "loss": 1.3529, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.12525252525252525, | |
| "grad_norm": 0.16015625, | |
| "learning_rate": 8.747474747474747e-06, | |
| "loss": 1.1866, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.12727272727272726, | |
| "grad_norm": 0.1630859375, | |
| "learning_rate": 8.727272727272728e-06, | |
| "loss": 1.2852, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.1292929292929293, | |
| "grad_norm": 0.171875, | |
| "learning_rate": 8.707070707070707e-06, | |
| "loss": 1.2611, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.13131313131313133, | |
| "grad_norm": 0.2451171875, | |
| "learning_rate": 8.686868686868687e-06, | |
| "loss": 1.1993, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.13333333333333333, | |
| "grad_norm": 0.1572265625, | |
| "learning_rate": 8.666666666666668e-06, | |
| "loss": 1.2068, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.13535353535353536, | |
| "grad_norm": 0.1611328125, | |
| "learning_rate": 8.646464646464647e-06, | |
| "loss": 1.2273, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.13737373737373737, | |
| "grad_norm": 0.17578125, | |
| "learning_rate": 8.626262626262627e-06, | |
| "loss": 1.1792, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.1393939393939394, | |
| "grad_norm": 0.177734375, | |
| "learning_rate": 8.606060606060606e-06, | |
| "loss": 1.2232, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.1414141414141414, | |
| "grad_norm": 0.1748046875, | |
| "learning_rate": 8.585858585858587e-06, | |
| "loss": 1.1552, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.14343434343434344, | |
| "grad_norm": 0.1533203125, | |
| "learning_rate": 8.565656565656566e-06, | |
| "loss": 1.1916, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.14545454545454545, | |
| "grad_norm": 0.1552734375, | |
| "learning_rate": 8.545454545454546e-06, | |
| "loss": 1.1712, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.14747474747474748, | |
| "grad_norm": 0.162109375, | |
| "learning_rate": 8.525252525252527e-06, | |
| "loss": 1.2027, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.1494949494949495, | |
| "grad_norm": 0.1787109375, | |
| "learning_rate": 8.505050505050506e-06, | |
| "loss": 1.2892, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.15151515151515152, | |
| "grad_norm": 0.150390625, | |
| "learning_rate": 8.484848484848486e-06, | |
| "loss": 1.1894, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.15353535353535352, | |
| "grad_norm": 0.158203125, | |
| "learning_rate": 8.464646464646465e-06, | |
| "loss": 1.1829, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.15555555555555556, | |
| "grad_norm": 0.1455078125, | |
| "learning_rate": 8.444444444444446e-06, | |
| "loss": 1.1127, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.15757575757575756, | |
| "grad_norm": 0.1533203125, | |
| "learning_rate": 8.424242424242425e-06, | |
| "loss": 1.2093, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.1595959595959596, | |
| "grad_norm": 0.150390625, | |
| "learning_rate": 8.404040404040405e-06, | |
| "loss": 1.1844, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.16161616161616163, | |
| "grad_norm": 0.1650390625, | |
| "learning_rate": 8.383838383838384e-06, | |
| "loss": 1.175, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.16363636363636364, | |
| "grad_norm": 0.1962890625, | |
| "learning_rate": 8.363636363636365e-06, | |
| "loss": 1.1569, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.16565656565656567, | |
| "grad_norm": 0.197265625, | |
| "learning_rate": 8.343434343434345e-06, | |
| "loss": 1.2603, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.16767676767676767, | |
| "grad_norm": 0.1484375, | |
| "learning_rate": 8.323232323232324e-06, | |
| "loss": 1.1733, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.1696969696969697, | |
| "grad_norm": 0.1591796875, | |
| "learning_rate": 8.303030303030305e-06, | |
| "loss": 1.2082, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.1717171717171717, | |
| "grad_norm": 0.1982421875, | |
| "learning_rate": 8.282828282828283e-06, | |
| "loss": 1.1991, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.17373737373737375, | |
| "grad_norm": 0.15234375, | |
| "learning_rate": 8.262626262626264e-06, | |
| "loss": 1.1648, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.17575757575757575, | |
| "grad_norm": 0.2216796875, | |
| "learning_rate": 8.242424242424243e-06, | |
| "loss": 1.1292, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.17777777777777778, | |
| "grad_norm": 0.1552734375, | |
| "learning_rate": 8.222222222222222e-06, | |
| "loss": 1.1936, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.1797979797979798, | |
| "grad_norm": 0.1728515625, | |
| "learning_rate": 8.202020202020202e-06, | |
| "loss": 1.1531, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 0.18181818181818182, | |
| "grad_norm": 0.1513671875, | |
| "learning_rate": 8.181818181818183e-06, | |
| "loss": 1.1727, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.18383838383838383, | |
| "grad_norm": 0.162109375, | |
| "learning_rate": 8.161616161616162e-06, | |
| "loss": 1.1873, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.18585858585858586, | |
| "grad_norm": 0.1953125, | |
| "learning_rate": 8.141414141414142e-06, | |
| "loss": 1.1735, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.18787878787878787, | |
| "grad_norm": 0.1923828125, | |
| "learning_rate": 8.121212121212121e-06, | |
| "loss": 1.1552, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.1898989898989899, | |
| "grad_norm": 0.1669921875, | |
| "learning_rate": 8.101010101010102e-06, | |
| "loss": 1.1441, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 0.1919191919191919, | |
| "grad_norm": 0.1728515625, | |
| "learning_rate": 8.08080808080808e-06, | |
| "loss": 1.164, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.19393939393939394, | |
| "grad_norm": 0.1552734375, | |
| "learning_rate": 8.060606060606061e-06, | |
| "loss": 1.1634, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.19595959595959597, | |
| "grad_norm": 0.224609375, | |
| "learning_rate": 8.04040404040404e-06, | |
| "loss": 1.1828, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 0.19797979797979798, | |
| "grad_norm": 0.181640625, | |
| "learning_rate": 8.02020202020202e-06, | |
| "loss": 1.1501, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "grad_norm": 0.166015625, | |
| "learning_rate": 8.000000000000001e-06, | |
| "loss": 1.1776, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.20202020202020202, | |
| "grad_norm": 0.1533203125, | |
| "learning_rate": 7.97979797979798e-06, | |
| "loss": 1.1401, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.20404040404040405, | |
| "grad_norm": 0.15234375, | |
| "learning_rate": 7.95959595959596e-06, | |
| "loss": 1.1554, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 0.20606060606060606, | |
| "grad_norm": 0.166015625, | |
| "learning_rate": 7.93939393939394e-06, | |
| "loss": 1.2024, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 0.2080808080808081, | |
| "grad_norm": 0.154296875, | |
| "learning_rate": 7.91919191919192e-06, | |
| "loss": 1.141, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 0.2101010101010101, | |
| "grad_norm": 0.158203125, | |
| "learning_rate": 7.898989898989899e-06, | |
| "loss": 1.1776, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 0.21212121212121213, | |
| "grad_norm": 0.1640625, | |
| "learning_rate": 7.87878787878788e-06, | |
| "loss": 1.1885, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.21414141414141413, | |
| "grad_norm": 0.201171875, | |
| "learning_rate": 7.858585858585859e-06, | |
| "loss": 1.1369, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 0.21616161616161617, | |
| "grad_norm": 0.162109375, | |
| "learning_rate": 7.838383838383839e-06, | |
| "loss": 1.1101, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 0.21818181818181817, | |
| "grad_norm": 0.185546875, | |
| "learning_rate": 7.81818181818182e-06, | |
| "loss": 1.1358, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 0.2202020202020202, | |
| "grad_norm": 0.1689453125, | |
| "learning_rate": 7.797979797979799e-06, | |
| "loss": 1.1267, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 0.2222222222222222, | |
| "grad_norm": 0.1689453125, | |
| "learning_rate": 7.77777777777778e-06, | |
| "loss": 1.1339, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.22424242424242424, | |
| "grad_norm": 0.19140625, | |
| "learning_rate": 7.757575757575758e-06, | |
| "loss": 1.0777, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 0.22626262626262628, | |
| "grad_norm": 0.16015625, | |
| "learning_rate": 7.737373737373739e-06, | |
| "loss": 1.1315, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 0.22828282828282828, | |
| "grad_norm": 0.15234375, | |
| "learning_rate": 7.717171717171717e-06, | |
| "loss": 1.096, | |
| "step": 113 | |
| }, | |
| { | |
| "epoch": 0.23030303030303031, | |
| "grad_norm": 0.1787109375, | |
| "learning_rate": 7.696969696969696e-06, | |
| "loss": 1.1127, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 0.23232323232323232, | |
| "grad_norm": 0.1904296875, | |
| "learning_rate": 7.676767676767677e-06, | |
| "loss": 1.181, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.23434343434343435, | |
| "grad_norm": 0.1630859375, | |
| "learning_rate": 7.656565656565658e-06, | |
| "loss": 1.1442, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 0.23636363636363636, | |
| "grad_norm": 0.208984375, | |
| "learning_rate": 7.636363636363638e-06, | |
| "loss": 1.1313, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 0.2383838383838384, | |
| "grad_norm": 0.1630859375, | |
| "learning_rate": 7.616161616161617e-06, | |
| "loss": 1.1727, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 0.2404040404040404, | |
| "grad_norm": 0.16015625, | |
| "learning_rate": 7.595959595959597e-06, | |
| "loss": 1.0959, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 0.24242424242424243, | |
| "grad_norm": 0.2197265625, | |
| "learning_rate": 7.5757575757575764e-06, | |
| "loss": 1.1908, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.24444444444444444, | |
| "grad_norm": 0.197265625, | |
| "learning_rate": 7.555555555555556e-06, | |
| "loss": 1.1209, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 0.24646464646464647, | |
| "grad_norm": 0.1591796875, | |
| "learning_rate": 7.535353535353536e-06, | |
| "loss": 1.1523, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 0.24848484848484848, | |
| "grad_norm": 0.1767578125, | |
| "learning_rate": 7.515151515151516e-06, | |
| "loss": 1.1379, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 0.2505050505050505, | |
| "grad_norm": 0.1865234375, | |
| "learning_rate": 7.494949494949496e-06, | |
| "loss": 1.1438, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 0.25252525252525254, | |
| "grad_norm": 0.16015625, | |
| "learning_rate": 7.474747474747476e-06, | |
| "loss": 1.1362, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.2545454545454545, | |
| "grad_norm": 0.1630859375, | |
| "learning_rate": 7.454545454545456e-06, | |
| "loss": 1.118, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 0.25656565656565655, | |
| "grad_norm": 0.17578125, | |
| "learning_rate": 7.434343434343435e-06, | |
| "loss": 1.0866, | |
| "step": 127 | |
| }, | |
| { | |
| "epoch": 0.2585858585858586, | |
| "grad_norm": 0.2353515625, | |
| "learning_rate": 7.414141414141415e-06, | |
| "loss": 1.0837, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 0.2606060606060606, | |
| "grad_norm": 0.177734375, | |
| "learning_rate": 7.393939393939395e-06, | |
| "loss": 1.1266, | |
| "step": 129 | |
| }, | |
| { | |
| "epoch": 0.26262626262626265, | |
| "grad_norm": 0.162109375, | |
| "learning_rate": 7.373737373737374e-06, | |
| "loss": 1.164, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.26464646464646463, | |
| "grad_norm": 0.177734375, | |
| "learning_rate": 7.353535353535353e-06, | |
| "loss": 1.071, | |
| "step": 131 | |
| }, | |
| { | |
| "epoch": 0.26666666666666666, | |
| "grad_norm": 0.19140625, | |
| "learning_rate": 7.333333333333333e-06, | |
| "loss": 1.1683, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 0.2686868686868687, | |
| "grad_norm": 0.2177734375, | |
| "learning_rate": 7.3131313131313146e-06, | |
| "loss": 1.1239, | |
| "step": 133 | |
| }, | |
| { | |
| "epoch": 0.27070707070707073, | |
| "grad_norm": 0.16015625, | |
| "learning_rate": 7.2929292929292934e-06, | |
| "loss": 1.1213, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 0.2727272727272727, | |
| "grad_norm": 0.158203125, | |
| "learning_rate": 7.272727272727273e-06, | |
| "loss": 1.0712, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.27474747474747474, | |
| "grad_norm": 0.1630859375, | |
| "learning_rate": 7.252525252525253e-06, | |
| "loss": 1.109, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 0.2767676767676768, | |
| "grad_norm": 0.75, | |
| "learning_rate": 7.232323232323233e-06, | |
| "loss": 1.113, | |
| "step": 137 | |
| }, | |
| { | |
| "epoch": 0.2787878787878788, | |
| "grad_norm": 0.1640625, | |
| "learning_rate": 7.212121212121212e-06, | |
| "loss": 1.0855, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 0.2808080808080808, | |
| "grad_norm": 0.1630859375, | |
| "learning_rate": 7.191919191919192e-06, | |
| "loss": 1.1196, | |
| "step": 139 | |
| }, | |
| { | |
| "epoch": 0.2828282828282828, | |
| "grad_norm": 0.1884765625, | |
| "learning_rate": 7.171717171717172e-06, | |
| "loss": 1.1559, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.28484848484848485, | |
| "grad_norm": 0.1953125, | |
| "learning_rate": 7.151515151515152e-06, | |
| "loss": 1.1031, | |
| "step": 141 | |
| }, | |
| { | |
| "epoch": 0.2868686868686869, | |
| "grad_norm": 0.16015625, | |
| "learning_rate": 7.131313131313132e-06, | |
| "loss": 1.0808, | |
| "step": 142 | |
| }, | |
| { | |
| "epoch": 0.28888888888888886, | |
| "grad_norm": 0.193359375, | |
| "learning_rate": 7.111111111111112e-06, | |
| "loss": 1.0975, | |
| "step": 143 | |
| }, | |
| { | |
| "epoch": 0.2909090909090909, | |
| "grad_norm": 0.1845703125, | |
| "learning_rate": 7.0909090909090916e-06, | |
| "loss": 1.1093, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 0.29292929292929293, | |
| "grad_norm": 0.166015625, | |
| "learning_rate": 7.070707070707071e-06, | |
| "loss": 1.1066, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.29494949494949496, | |
| "grad_norm": 0.20703125, | |
| "learning_rate": 7.050505050505051e-06, | |
| "loss": 1.1233, | |
| "step": 146 | |
| }, | |
| { | |
| "epoch": 0.296969696969697, | |
| "grad_norm": 0.1748046875, | |
| "learning_rate": 7.030303030303031e-06, | |
| "loss": 1.1179, | |
| "step": 147 | |
| }, | |
| { | |
| "epoch": 0.298989898989899, | |
| "grad_norm": 0.177734375, | |
| "learning_rate": 7.0101010101010105e-06, | |
| "loss": 1.1154, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 0.301010101010101, | |
| "grad_norm": 0.1953125, | |
| "learning_rate": 6.98989898989899e-06, | |
| "loss": 1.0917, | |
| "step": 149 | |
| }, | |
| { | |
| "epoch": 0.30303030303030304, | |
| "grad_norm": 0.19140625, | |
| "learning_rate": 6.969696969696971e-06, | |
| "loss": 1.0864, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.30505050505050507, | |
| "grad_norm": 0.1962890625, | |
| "learning_rate": 6.9494949494949505e-06, | |
| "loss": 1.1178, | |
| "step": 151 | |
| }, | |
| { | |
| "epoch": 0.30707070707070705, | |
| "grad_norm": 0.1630859375, | |
| "learning_rate": 6.92929292929293e-06, | |
| "loss": 1.1425, | |
| "step": 152 | |
| }, | |
| { | |
| "epoch": 0.3090909090909091, | |
| "grad_norm": 0.1728515625, | |
| "learning_rate": 6.90909090909091e-06, | |
| "loss": 1.0966, | |
| "step": 153 | |
| }, | |
| { | |
| "epoch": 0.3111111111111111, | |
| "grad_norm": 0.25, | |
| "learning_rate": 6.88888888888889e-06, | |
| "loss": 1.0981, | |
| "step": 154 | |
| }, | |
| { | |
| "epoch": 0.31313131313131315, | |
| "grad_norm": 0.1650390625, | |
| "learning_rate": 6.868686868686869e-06, | |
| "loss": 1.0782, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.3151515151515151, | |
| "grad_norm": 0.1875, | |
| "learning_rate": 6.848484848484849e-06, | |
| "loss": 1.1391, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 0.31717171717171716, | |
| "grad_norm": 0.1689453125, | |
| "learning_rate": 6.828282828282828e-06, | |
| "loss": 1.0521, | |
| "step": 157 | |
| }, | |
| { | |
| "epoch": 0.3191919191919192, | |
| "grad_norm": 0.2119140625, | |
| "learning_rate": 6.808080808080809e-06, | |
| "loss": 1.0959, | |
| "step": 158 | |
| }, | |
| { | |
| "epoch": 0.3212121212121212, | |
| "grad_norm": 0.1669921875, | |
| "learning_rate": 6.787878787878789e-06, | |
| "loss": 1.0973, | |
| "step": 159 | |
| }, | |
| { | |
| "epoch": 0.32323232323232326, | |
| "grad_norm": 0.1630859375, | |
| "learning_rate": 6.767676767676769e-06, | |
| "loss": 1.0526, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.32525252525252524, | |
| "grad_norm": 0.201171875, | |
| "learning_rate": 6.747474747474749e-06, | |
| "loss": 1.0886, | |
| "step": 161 | |
| }, | |
| { | |
| "epoch": 0.32727272727272727, | |
| "grad_norm": 0.1650390625, | |
| "learning_rate": 6.7272727272727275e-06, | |
| "loss": 1.0519, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 0.3292929292929293, | |
| "grad_norm": 0.224609375, | |
| "learning_rate": 6.707070707070707e-06, | |
| "loss": 1.0623, | |
| "step": 163 | |
| }, | |
| { | |
| "epoch": 0.33131313131313134, | |
| "grad_norm": 0.3359375, | |
| "learning_rate": 6.686868686868687e-06, | |
| "loss": 1.0819, | |
| "step": 164 | |
| }, | |
| { | |
| "epoch": 0.3333333333333333, | |
| "grad_norm": 0.205078125, | |
| "learning_rate": 6.666666666666667e-06, | |
| "loss": 1.1033, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.33535353535353535, | |
| "grad_norm": 0.365234375, | |
| "learning_rate": 6.646464646464646e-06, | |
| "loss": 1.108, | |
| "step": 166 | |
| }, | |
| { | |
| "epoch": 0.3373737373737374, | |
| "grad_norm": 0.2421875, | |
| "learning_rate": 6.626262626262627e-06, | |
| "loss": 1.0995, | |
| "step": 167 | |
| }, | |
| { | |
| "epoch": 0.3393939393939394, | |
| "grad_norm": 0.1630859375, | |
| "learning_rate": 6.606060606060607e-06, | |
| "loss": 1.066, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 0.3414141414141414, | |
| "grad_norm": 0.2197265625, | |
| "learning_rate": 6.585858585858586e-06, | |
| "loss": 1.113, | |
| "step": 169 | |
| }, | |
| { | |
| "epoch": 0.3434343434343434, | |
| "grad_norm": 0.1923828125, | |
| "learning_rate": 6.565656565656566e-06, | |
| "loss": 1.1046, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.34545454545454546, | |
| "grad_norm": 0.1669921875, | |
| "learning_rate": 6.545454545454546e-06, | |
| "loss": 1.129, | |
| "step": 171 | |
| }, | |
| { | |
| "epoch": 0.3474747474747475, | |
| "grad_norm": 0.1845703125, | |
| "learning_rate": 6.525252525252526e-06, | |
| "loss": 1.0712, | |
| "step": 172 | |
| }, | |
| { | |
| "epoch": 0.34949494949494947, | |
| "grad_norm": 0.166015625, | |
| "learning_rate": 6.505050505050505e-06, | |
| "loss": 1.0549, | |
| "step": 173 | |
| }, | |
| { | |
| "epoch": 0.3515151515151515, | |
| "grad_norm": 0.1953125, | |
| "learning_rate": 6.484848484848485e-06, | |
| "loss": 1.0983, | |
| "step": 174 | |
| }, | |
| { | |
| "epoch": 0.35353535353535354, | |
| "grad_norm": 0.1689453125, | |
| "learning_rate": 6.464646464646466e-06, | |
| "loss": 1.1056, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.35555555555555557, | |
| "grad_norm": 0.177734375, | |
| "learning_rate": 6.444444444444445e-06, | |
| "loss": 1.1125, | |
| "step": 176 | |
| }, | |
| { | |
| "epoch": 0.3575757575757576, | |
| "grad_norm": 0.1708984375, | |
| "learning_rate": 6.424242424242425e-06, | |
| "loss": 1.143, | |
| "step": 177 | |
| }, | |
| { | |
| "epoch": 0.3595959595959596, | |
| "grad_norm": 0.265625, | |
| "learning_rate": 6.404040404040405e-06, | |
| "loss": 1.0382, | |
| "step": 178 | |
| }, | |
| { | |
| "epoch": 0.3616161616161616, | |
| "grad_norm": 0.1767578125, | |
| "learning_rate": 6.3838383838383845e-06, | |
| "loss": 1.1309, | |
| "step": 179 | |
| }, | |
| { | |
| "epoch": 0.36363636363636365, | |
| "grad_norm": 0.27734375, | |
| "learning_rate": 6.363636363636364e-06, | |
| "loss": 1.0753, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.3656565656565657, | |
| "grad_norm": 0.1728515625, | |
| "learning_rate": 6.343434343434344e-06, | |
| "loss": 1.0436, | |
| "step": 181 | |
| }, | |
| { | |
| "epoch": 0.36767676767676766, | |
| "grad_norm": 0.189453125, | |
| "learning_rate": 6.323232323232324e-06, | |
| "loss": 1.0809, | |
| "step": 182 | |
| }, | |
| { | |
| "epoch": 0.3696969696969697, | |
| "grad_norm": 0.1767578125, | |
| "learning_rate": 6.303030303030303e-06, | |
| "loss": 1.0613, | |
| "step": 183 | |
| }, | |
| { | |
| "epoch": 0.3717171717171717, | |
| "grad_norm": 0.1826171875, | |
| "learning_rate": 6.282828282828284e-06, | |
| "loss": 1.0975, | |
| "step": 184 | |
| }, | |
| { | |
| "epoch": 0.37373737373737376, | |
| "grad_norm": 0.1708984375, | |
| "learning_rate": 6.262626262626264e-06, | |
| "loss": 1.0774, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 0.37575757575757573, | |
| "grad_norm": 0.1884765625, | |
| "learning_rate": 6.2424242424242434e-06, | |
| "loss": 1.0811, | |
| "step": 186 | |
| }, | |
| { | |
| "epoch": 0.37777777777777777, | |
| "grad_norm": 0.1845703125, | |
| "learning_rate": 6.222222222222223e-06, | |
| "loss": 1.1261, | |
| "step": 187 | |
| }, | |
| { | |
| "epoch": 0.3797979797979798, | |
| "grad_norm": 0.1943359375, | |
| "learning_rate": 6.202020202020203e-06, | |
| "loss": 1.0866, | |
| "step": 188 | |
| }, | |
| { | |
| "epoch": 0.38181818181818183, | |
| "grad_norm": 0.1728515625, | |
| "learning_rate": 6.181818181818182e-06, | |
| "loss": 1.0776, | |
| "step": 189 | |
| }, | |
| { | |
| "epoch": 0.3838383838383838, | |
| "grad_norm": 0.205078125, | |
| "learning_rate": 6.1616161616161615e-06, | |
| "loss": 1.0764, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.38585858585858585, | |
| "grad_norm": 0.32421875, | |
| "learning_rate": 6.141414141414141e-06, | |
| "loss": 1.0798, | |
| "step": 191 | |
| }, | |
| { | |
| "epoch": 0.3878787878787879, | |
| "grad_norm": 0.1806640625, | |
| "learning_rate": 6.121212121212121e-06, | |
| "loss": 0.987, | |
| "step": 192 | |
| }, | |
| { | |
| "epoch": 0.3898989898989899, | |
| "grad_norm": 0.1923828125, | |
| "learning_rate": 6.1010101010101015e-06, | |
| "loss": 1.068, | |
| "step": 193 | |
| }, | |
| { | |
| "epoch": 0.39191919191919194, | |
| "grad_norm": 0.1640625, | |
| "learning_rate": 6.080808080808081e-06, | |
| "loss": 1.0608, | |
| "step": 194 | |
| }, | |
| { | |
| "epoch": 0.3939393939393939, | |
| "grad_norm": 0.1845703125, | |
| "learning_rate": 6.060606060606061e-06, | |
| "loss": 1.0785, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 0.39595959595959596, | |
| "grad_norm": 0.193359375, | |
| "learning_rate": 6.040404040404041e-06, | |
| "loss": 1.1016, | |
| "step": 196 | |
| }, | |
| { | |
| "epoch": 0.397979797979798, | |
| "grad_norm": 0.169921875, | |
| "learning_rate": 6.0202020202020204e-06, | |
| "loss": 1.0731, | |
| "step": 197 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "grad_norm": 1.75, | |
| "learning_rate": 6e-06, | |
| "loss": 1.0454, | |
| "step": 198 | |
| }, | |
| { | |
| "epoch": 0.402020202020202, | |
| "grad_norm": 0.1865234375, | |
| "learning_rate": 5.97979797979798e-06, | |
| "loss": 1.0912, | |
| "step": 199 | |
| }, | |
| { | |
| "epoch": 0.40404040404040403, | |
| "grad_norm": 0.1689453125, | |
| "learning_rate": 5.95959595959596e-06, | |
| "loss": 1.0457, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.40606060606060607, | |
| "grad_norm": 0.166015625, | |
| "learning_rate": 5.93939393939394e-06, | |
| "loss": 1.0382, | |
| "step": 201 | |
| }, | |
| { | |
| "epoch": 0.4080808080808081, | |
| "grad_norm": 0.201171875, | |
| "learning_rate": 5.91919191919192e-06, | |
| "loss": 1.1034, | |
| "step": 202 | |
| }, | |
| { | |
| "epoch": 0.4101010101010101, | |
| "grad_norm": 0.236328125, | |
| "learning_rate": 5.8989898989899e-06, | |
| "loss": 1.0624, | |
| "step": 203 | |
| }, | |
| { | |
| "epoch": 0.4121212121212121, | |
| "grad_norm": 0.181640625, | |
| "learning_rate": 5.878787878787879e-06, | |
| "loss": 1.088, | |
| "step": 204 | |
| }, | |
| { | |
| "epoch": 0.41414141414141414, | |
| "grad_norm": 0.1982421875, | |
| "learning_rate": 5.858585858585859e-06, | |
| "loss": 1.0434, | |
| "step": 205 | |
| }, | |
| { | |
| "epoch": 0.4161616161616162, | |
| "grad_norm": 0.1728515625, | |
| "learning_rate": 5.838383838383839e-06, | |
| "loss": 1.0536, | |
| "step": 206 | |
| }, | |
| { | |
| "epoch": 0.41818181818181815, | |
| "grad_norm": 0.2216796875, | |
| "learning_rate": 5.8181818181818185e-06, | |
| "loss": 1.0236, | |
| "step": 207 | |
| }, | |
| { | |
| "epoch": 0.4202020202020202, | |
| "grad_norm": 0.1904296875, | |
| "learning_rate": 5.797979797979798e-06, | |
| "loss": 1.013, | |
| "step": 208 | |
| }, | |
| { | |
| "epoch": 0.4222222222222222, | |
| "grad_norm": 0.1787109375, | |
| "learning_rate": 5.777777777777778e-06, | |
| "loss": 1.0562, | |
| "step": 209 | |
| }, | |
| { | |
| "epoch": 0.42424242424242425, | |
| "grad_norm": 0.1806640625, | |
| "learning_rate": 5.7575757575757586e-06, | |
| "loss": 1.0232, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.4262626262626263, | |
| "grad_norm": 0.1787109375, | |
| "learning_rate": 5.737373737373738e-06, | |
| "loss": 1.0425, | |
| "step": 211 | |
| }, | |
| { | |
| "epoch": 0.42828282828282827, | |
| "grad_norm": 0.173828125, | |
| "learning_rate": 5.717171717171718e-06, | |
| "loss": 1.0381, | |
| "step": 212 | |
| }, | |
| { | |
| "epoch": 0.4303030303030303, | |
| "grad_norm": 0.197265625, | |
| "learning_rate": 5.696969696969698e-06, | |
| "loss": 1.0393, | |
| "step": 213 | |
| }, | |
| { | |
| "epoch": 0.43232323232323233, | |
| "grad_norm": 0.26171875, | |
| "learning_rate": 5.6767676767676775e-06, | |
| "loss": 1.0934, | |
| "step": 214 | |
| }, | |
| { | |
| "epoch": 0.43434343434343436, | |
| "grad_norm": 0.1708984375, | |
| "learning_rate": 5.656565656565657e-06, | |
| "loss": 1.0685, | |
| "step": 215 | |
| }, | |
| { | |
| "epoch": 0.43636363636363634, | |
| "grad_norm": 0.236328125, | |
| "learning_rate": 5.636363636363636e-06, | |
| "loss": 1.0601, | |
| "step": 216 | |
| }, | |
| { | |
| "epoch": 0.4383838383838384, | |
| "grad_norm": 0.1748046875, | |
| "learning_rate": 5.616161616161616e-06, | |
| "loss": 1.0923, | |
| "step": 217 | |
| }, | |
| { | |
| "epoch": 0.4404040404040404, | |
| "grad_norm": 0.1845703125, | |
| "learning_rate": 5.595959595959597e-06, | |
| "loss": 1.0975, | |
| "step": 218 | |
| }, | |
| { | |
| "epoch": 0.44242424242424244, | |
| "grad_norm": 0.25390625, | |
| "learning_rate": 5.575757575757577e-06, | |
| "loss": 1.098, | |
| "step": 219 | |
| }, | |
| { | |
| "epoch": 0.4444444444444444, | |
| "grad_norm": 0.1943359375, | |
| "learning_rate": 5.555555555555557e-06, | |
| "loss": 1.0009, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.44646464646464645, | |
| "grad_norm": 0.17578125, | |
| "learning_rate": 5.5353535353535355e-06, | |
| "loss": 1.0145, | |
| "step": 221 | |
| }, | |
| { | |
| "epoch": 0.4484848484848485, | |
| "grad_norm": 0.17578125, | |
| "learning_rate": 5.515151515151515e-06, | |
| "loss": 1.0652, | |
| "step": 222 | |
| }, | |
| { | |
| "epoch": 0.4505050505050505, | |
| "grad_norm": 0.173828125, | |
| "learning_rate": 5.494949494949495e-06, | |
| "loss": 1.0448, | |
| "step": 223 | |
| }, | |
| { | |
| "epoch": 0.45252525252525255, | |
| "grad_norm": 0.1728515625, | |
| "learning_rate": 5.474747474747475e-06, | |
| "loss": 1.0548, | |
| "step": 224 | |
| }, | |
| { | |
| "epoch": 0.45454545454545453, | |
| "grad_norm": 0.2060546875, | |
| "learning_rate": 5.4545454545454545e-06, | |
| "loss": 1.0661, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 0.45656565656565656, | |
| "grad_norm": 0.1826171875, | |
| "learning_rate": 5.434343434343434e-06, | |
| "loss": 1.0833, | |
| "step": 226 | |
| }, | |
| { | |
| "epoch": 0.4585858585858586, | |
| "grad_norm": 0.1787109375, | |
| "learning_rate": 5.414141414141415e-06, | |
| "loss": 1.0515, | |
| "step": 227 | |
| }, | |
| { | |
| "epoch": 0.46060606060606063, | |
| "grad_norm": 0.1708984375, | |
| "learning_rate": 5.3939393939393945e-06, | |
| "loss": 1.0603, | |
| "step": 228 | |
| }, | |
| { | |
| "epoch": 0.4626262626262626, | |
| "grad_norm": 0.1923828125, | |
| "learning_rate": 5.373737373737374e-06, | |
| "loss": 1.073, | |
| "step": 229 | |
| }, | |
| { | |
| "epoch": 0.46464646464646464, | |
| "grad_norm": 0.1826171875, | |
| "learning_rate": 5.353535353535354e-06, | |
| "loss": 1.0903, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.4666666666666667, | |
| "grad_norm": 0.1845703125, | |
| "learning_rate": 5.333333333333334e-06, | |
| "loss": 1.054, | |
| "step": 231 | |
| }, | |
| { | |
| "epoch": 0.4686868686868687, | |
| "grad_norm": 0.1787109375, | |
| "learning_rate": 5.313131313131313e-06, | |
| "loss": 1.0634, | |
| "step": 232 | |
| }, | |
| { | |
| "epoch": 0.4707070707070707, | |
| "grad_norm": 0.2275390625, | |
| "learning_rate": 5.292929292929293e-06, | |
| "loss": 1.0463, | |
| "step": 233 | |
| }, | |
| { | |
| "epoch": 0.4727272727272727, | |
| "grad_norm": 0.1884765625, | |
| "learning_rate": 5.272727272727273e-06, | |
| "loss": 1.0138, | |
| "step": 234 | |
| }, | |
| { | |
| "epoch": 0.47474747474747475, | |
| "grad_norm": 0.17578125, | |
| "learning_rate": 5.252525252525253e-06, | |
| "loss": 0.9779, | |
| "step": 235 | |
| }, | |
| { | |
| "epoch": 0.4767676767676768, | |
| "grad_norm": 0.1943359375, | |
| "learning_rate": 5.232323232323233e-06, | |
| "loss": 1.112, | |
| "step": 236 | |
| }, | |
| { | |
| "epoch": 0.47878787878787876, | |
| "grad_norm": 0.21875, | |
| "learning_rate": 5.212121212121213e-06, | |
| "loss": 1.079, | |
| "step": 237 | |
| }, | |
| { | |
| "epoch": 0.4808080808080808, | |
| "grad_norm": 0.1826171875, | |
| "learning_rate": 5.191919191919193e-06, | |
| "loss": 1.0357, | |
| "step": 238 | |
| }, | |
| { | |
| "epoch": 0.48282828282828283, | |
| "grad_norm": 0.30859375, | |
| "learning_rate": 5.171717171717172e-06, | |
| "loss": 1.0545, | |
| "step": 239 | |
| }, | |
| { | |
| "epoch": 0.48484848484848486, | |
| "grad_norm": 0.1787109375, | |
| "learning_rate": 5.151515151515152e-06, | |
| "loss": 1.0452, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.4868686868686869, | |
| "grad_norm": 0.181640625, | |
| "learning_rate": 5.131313131313132e-06, | |
| "loss": 1.0302, | |
| "step": 241 | |
| }, | |
| { | |
| "epoch": 0.4888888888888889, | |
| "grad_norm": 0.1787109375, | |
| "learning_rate": 5.1111111111111115e-06, | |
| "loss": 1.03, | |
| "step": 242 | |
| }, | |
| { | |
| "epoch": 0.4909090909090909, | |
| "grad_norm": 0.189453125, | |
| "learning_rate": 5.090909090909091e-06, | |
| "loss": 0.9899, | |
| "step": 243 | |
| }, | |
| { | |
| "epoch": 0.49292929292929294, | |
| "grad_norm": 0.2080078125, | |
| "learning_rate": 5.070707070707072e-06, | |
| "loss": 1.0448, | |
| "step": 244 | |
| }, | |
| { | |
| "epoch": 0.494949494949495, | |
| "grad_norm": 0.203125, | |
| "learning_rate": 5.0505050505050515e-06, | |
| "loss": 1.0938, | |
| "step": 245 | |
| }, | |
| { | |
| "epoch": 0.49696969696969695, | |
| "grad_norm": 0.17578125, | |
| "learning_rate": 5.030303030303031e-06, | |
| "loss": 1.0318, | |
| "step": 246 | |
| }, | |
| { | |
| "epoch": 0.498989898989899, | |
| "grad_norm": 0.1689453125, | |
| "learning_rate": 5.010101010101011e-06, | |
| "loss": 0.9649, | |
| "step": 247 | |
| }, | |
| { | |
| "epoch": 0.501010101010101, | |
| "grad_norm": 0.1865234375, | |
| "learning_rate": 4.98989898989899e-06, | |
| "loss": 1.0887, | |
| "step": 248 | |
| }, | |
| { | |
| "epoch": 0.503030303030303, | |
| "grad_norm": 0.345703125, | |
| "learning_rate": 4.9696969696969696e-06, | |
| "loss": 1.0543, | |
| "step": 249 | |
| }, | |
| { | |
| "epoch": 0.5050505050505051, | |
| "grad_norm": 0.18359375, | |
| "learning_rate": 4.94949494949495e-06, | |
| "loss": 1.0052, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.5070707070707071, | |
| "grad_norm": 0.1904296875, | |
| "learning_rate": 4.92929292929293e-06, | |
| "loss": 1.0364, | |
| "step": 251 | |
| }, | |
| { | |
| "epoch": 0.509090909090909, | |
| "grad_norm": 0.1796875, | |
| "learning_rate": 4.90909090909091e-06, | |
| "loss": 1.0756, | |
| "step": 252 | |
| }, | |
| { | |
| "epoch": 0.5111111111111111, | |
| "grad_norm": 0.2041015625, | |
| "learning_rate": 4.888888888888889e-06, | |
| "loss": 1.0512, | |
| "step": 253 | |
| }, | |
| { | |
| "epoch": 0.5131313131313131, | |
| "grad_norm": 0.201171875, | |
| "learning_rate": 4.868686868686869e-06, | |
| "loss": 1.0372, | |
| "step": 254 | |
| }, | |
| { | |
| "epoch": 0.5151515151515151, | |
| "grad_norm": 0.28125, | |
| "learning_rate": 4.848484848484849e-06, | |
| "loss": 1.1119, | |
| "step": 255 | |
| }, | |
| { | |
| "epoch": 0.5171717171717172, | |
| "grad_norm": 0.181640625, | |
| "learning_rate": 4.8282828282828285e-06, | |
| "loss": 1.077, | |
| "step": 256 | |
| }, | |
| { | |
| "epoch": 0.5191919191919192, | |
| "grad_norm": 0.19140625, | |
| "learning_rate": 4.808080808080808e-06, | |
| "loss": 1.1184, | |
| "step": 257 | |
| }, | |
| { | |
| "epoch": 0.5212121212121212, | |
| "grad_norm": 0.208984375, | |
| "learning_rate": 4.787878787878788e-06, | |
| "loss": 1.0886, | |
| "step": 258 | |
| }, | |
| { | |
| "epoch": 0.5232323232323233, | |
| "grad_norm": 0.1875, | |
| "learning_rate": 4.7676767676767685e-06, | |
| "loss": 1.0095, | |
| "step": 259 | |
| }, | |
| { | |
| "epoch": 0.5252525252525253, | |
| "grad_norm": 0.205078125, | |
| "learning_rate": 4.747474747474748e-06, | |
| "loss": 1.045, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.5272727272727272, | |
| "grad_norm": 0.1904296875, | |
| "learning_rate": 4.727272727272728e-06, | |
| "loss": 1.0381, | |
| "step": 261 | |
| }, | |
| { | |
| "epoch": 0.5292929292929293, | |
| "grad_norm": 0.1826171875, | |
| "learning_rate": 4.707070707070707e-06, | |
| "loss": 1.0379, | |
| "step": 262 | |
| }, | |
| { | |
| "epoch": 0.5313131313131313, | |
| "grad_norm": 0.1748046875, | |
| "learning_rate": 4.6868686868686874e-06, | |
| "loss": 1.0157, | |
| "step": 263 | |
| }, | |
| { | |
| "epoch": 0.5333333333333333, | |
| "grad_norm": 0.18359375, | |
| "learning_rate": 4.666666666666667e-06, | |
| "loss": 1.0467, | |
| "step": 264 | |
| }, | |
| { | |
| "epoch": 0.5353535353535354, | |
| "grad_norm": 0.1796875, | |
| "learning_rate": 4.646464646464647e-06, | |
| "loss": 1.045, | |
| "step": 265 | |
| }, | |
| { | |
| "epoch": 0.5373737373737374, | |
| "grad_norm": 0.185546875, | |
| "learning_rate": 4.626262626262627e-06, | |
| "loss": 1.0524, | |
| "step": 266 | |
| }, | |
| { | |
| "epoch": 0.5393939393939394, | |
| "grad_norm": 0.265625, | |
| "learning_rate": 4.606060606060606e-06, | |
| "loss": 1.0835, | |
| "step": 267 | |
| }, | |
| { | |
| "epoch": 0.5414141414141415, | |
| "grad_norm": 0.1962890625, | |
| "learning_rate": 4.585858585858586e-06, | |
| "loss": 1.0561, | |
| "step": 268 | |
| }, | |
| { | |
| "epoch": 0.5434343434343434, | |
| "grad_norm": 0.1748046875, | |
| "learning_rate": 4.565656565656566e-06, | |
| "loss": 1.0416, | |
| "step": 269 | |
| }, | |
| { | |
| "epoch": 0.5454545454545454, | |
| "grad_norm": 0.2158203125, | |
| "learning_rate": 4.5454545454545455e-06, | |
| "loss": 1.0629, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.5474747474747474, | |
| "grad_norm": 0.2099609375, | |
| "learning_rate": 4.525252525252526e-06, | |
| "loss": 1.0639, | |
| "step": 271 | |
| }, | |
| { | |
| "epoch": 0.5494949494949495, | |
| "grad_norm": 0.1904296875, | |
| "learning_rate": 4.505050505050506e-06, | |
| "loss": 1.0732, | |
| "step": 272 | |
| }, | |
| { | |
| "epoch": 0.5515151515151515, | |
| "grad_norm": 0.1904296875, | |
| "learning_rate": 4.4848484848484855e-06, | |
| "loss": 1.1106, | |
| "step": 273 | |
| }, | |
| { | |
| "epoch": 0.5535353535353535, | |
| "grad_norm": 0.185546875, | |
| "learning_rate": 4.464646464646465e-06, | |
| "loss": 1.0459, | |
| "step": 274 | |
| }, | |
| { | |
| "epoch": 0.5555555555555556, | |
| "grad_norm": 0.1943359375, | |
| "learning_rate": 4.444444444444444e-06, | |
| "loss": 1.0037, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 0.5575757575757576, | |
| "grad_norm": 0.197265625, | |
| "learning_rate": 4.424242424242425e-06, | |
| "loss": 1.0369, | |
| "step": 276 | |
| }, | |
| { | |
| "epoch": 0.5595959595959596, | |
| "grad_norm": 0.234375, | |
| "learning_rate": 4.4040404040404044e-06, | |
| "loss": 1.0844, | |
| "step": 277 | |
| }, | |
| { | |
| "epoch": 0.5616161616161616, | |
| "grad_norm": 0.18359375, | |
| "learning_rate": 4.383838383838384e-06, | |
| "loss": 1.0097, | |
| "step": 278 | |
| }, | |
| { | |
| "epoch": 0.5636363636363636, | |
| "grad_norm": 0.1787109375, | |
| "learning_rate": 4.363636363636364e-06, | |
| "loss": 1.0342, | |
| "step": 279 | |
| }, | |
| { | |
| "epoch": 0.5656565656565656, | |
| "grad_norm": 0.2177734375, | |
| "learning_rate": 4.343434343434344e-06, | |
| "loss": 1.0167, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.5676767676767677, | |
| "grad_norm": 0.1796875, | |
| "learning_rate": 4.323232323232323e-06, | |
| "loss": 1.0203, | |
| "step": 281 | |
| }, | |
| { | |
| "epoch": 0.5696969696969697, | |
| "grad_norm": 0.251953125, | |
| "learning_rate": 4.303030303030303e-06, | |
| "loss": 1.0382, | |
| "step": 282 | |
| }, | |
| { | |
| "epoch": 0.5717171717171717, | |
| "grad_norm": 0.19921875, | |
| "learning_rate": 4.282828282828283e-06, | |
| "loss": 1.0358, | |
| "step": 283 | |
| }, | |
| { | |
| "epoch": 0.5737373737373738, | |
| "grad_norm": 0.173828125, | |
| "learning_rate": 4.262626262626263e-06, | |
| "loss": 1.072, | |
| "step": 284 | |
| }, | |
| { | |
| "epoch": 0.5757575757575758, | |
| "grad_norm": 0.19140625, | |
| "learning_rate": 4.242424242424243e-06, | |
| "loss": 1.0884, | |
| "step": 285 | |
| }, | |
| { | |
| "epoch": 0.5777777777777777, | |
| "grad_norm": 0.1787109375, | |
| "learning_rate": 4.222222222222223e-06, | |
| "loss": 1.032, | |
| "step": 286 | |
| }, | |
| { | |
| "epoch": 0.5797979797979798, | |
| "grad_norm": 0.1884765625, | |
| "learning_rate": 4.2020202020202026e-06, | |
| "loss": 1.039, | |
| "step": 287 | |
| }, | |
| { | |
| "epoch": 0.5818181818181818, | |
| "grad_norm": 0.17578125, | |
| "learning_rate": 4.181818181818182e-06, | |
| "loss": 1.0533, | |
| "step": 288 | |
| }, | |
| { | |
| "epoch": 0.5838383838383838, | |
| "grad_norm": 0.17578125, | |
| "learning_rate": 4.161616161616162e-06, | |
| "loss": 1.027, | |
| "step": 289 | |
| }, | |
| { | |
| "epoch": 0.5858585858585859, | |
| "grad_norm": 0.2109375, | |
| "learning_rate": 4.141414141414142e-06, | |
| "loss": 1.046, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.5878787878787879, | |
| "grad_norm": 0.17578125, | |
| "learning_rate": 4.1212121212121215e-06, | |
| "loss": 1.0367, | |
| "step": 291 | |
| }, | |
| { | |
| "epoch": 0.5898989898989899, | |
| "grad_norm": 0.2431640625, | |
| "learning_rate": 4.101010101010101e-06, | |
| "loss": 1.0158, | |
| "step": 292 | |
| }, | |
| { | |
| "epoch": 0.591919191919192, | |
| "grad_norm": 0.189453125, | |
| "learning_rate": 4.080808080808081e-06, | |
| "loss": 0.9974, | |
| "step": 293 | |
| }, | |
| { | |
| "epoch": 0.593939393939394, | |
| "grad_norm": 0.1982421875, | |
| "learning_rate": 4.060606060606061e-06, | |
| "loss": 0.9762, | |
| "step": 294 | |
| }, | |
| { | |
| "epoch": 0.5959595959595959, | |
| "grad_norm": 0.177734375, | |
| "learning_rate": 4.04040404040404e-06, | |
| "loss": 1.0425, | |
| "step": 295 | |
| }, | |
| { | |
| "epoch": 0.597979797979798, | |
| "grad_norm": 0.1708984375, | |
| "learning_rate": 4.02020202020202e-06, | |
| "loss": 0.9974, | |
| "step": 296 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "grad_norm": 0.17578125, | |
| "learning_rate": 4.000000000000001e-06, | |
| "loss": 1.0481, | |
| "step": 297 | |
| }, | |
| { | |
| "epoch": 0.602020202020202, | |
| "grad_norm": 0.2333984375, | |
| "learning_rate": 3.97979797979798e-06, | |
| "loss": 1.0446, | |
| "step": 298 | |
| }, | |
| { | |
| "epoch": 0.604040404040404, | |
| "grad_norm": 0.17578125, | |
| "learning_rate": 3.95959595959596e-06, | |
| "loss": 1.0086, | |
| "step": 299 | |
| }, | |
| { | |
| "epoch": 0.6060606060606061, | |
| "grad_norm": 0.298828125, | |
| "learning_rate": 3.93939393939394e-06, | |
| "loss": 1.1283, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.6080808080808081, | |
| "grad_norm": 0.1884765625, | |
| "learning_rate": 3.9191919191919196e-06, | |
| "loss": 1.0657, | |
| "step": 301 | |
| }, | |
| { | |
| "epoch": 0.6101010101010101, | |
| "grad_norm": 0.208984375, | |
| "learning_rate": 3.898989898989899e-06, | |
| "loss": 0.9508, | |
| "step": 302 | |
| }, | |
| { | |
| "epoch": 0.6121212121212121, | |
| "grad_norm": 0.1923828125, | |
| "learning_rate": 3.878787878787879e-06, | |
| "loss": 1.0725, | |
| "step": 303 | |
| }, | |
| { | |
| "epoch": 0.6141414141414141, | |
| "grad_norm": 0.1953125, | |
| "learning_rate": 3.858585858585859e-06, | |
| "loss": 1.0317, | |
| "step": 304 | |
| }, | |
| { | |
| "epoch": 0.6161616161616161, | |
| "grad_norm": 0.1826171875, | |
| "learning_rate": 3.8383838383838385e-06, | |
| "loss": 1.0252, | |
| "step": 305 | |
| }, | |
| { | |
| "epoch": 0.6181818181818182, | |
| "grad_norm": 0.2001953125, | |
| "learning_rate": 3.818181818181819e-06, | |
| "loss": 0.9875, | |
| "step": 306 | |
| }, | |
| { | |
| "epoch": 0.6202020202020202, | |
| "grad_norm": 0.3984375, | |
| "learning_rate": 3.7979797979797984e-06, | |
| "loss": 1.0311, | |
| "step": 307 | |
| }, | |
| { | |
| "epoch": 0.6222222222222222, | |
| "grad_norm": 0.18359375, | |
| "learning_rate": 3.777777777777778e-06, | |
| "loss": 1.0357, | |
| "step": 308 | |
| }, | |
| { | |
| "epoch": 0.6242424242424243, | |
| "grad_norm": 0.2060546875, | |
| "learning_rate": 3.757575757575758e-06, | |
| "loss": 1.019, | |
| "step": 309 | |
| }, | |
| { | |
| "epoch": 0.6262626262626263, | |
| "grad_norm": 0.181640625, | |
| "learning_rate": 3.737373737373738e-06, | |
| "loss": 1.0169, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.6282828282828283, | |
| "grad_norm": 0.1845703125, | |
| "learning_rate": 3.7171717171717177e-06, | |
| "loss": 1.0063, | |
| "step": 311 | |
| }, | |
| { | |
| "epoch": 0.6303030303030303, | |
| "grad_norm": 0.2392578125, | |
| "learning_rate": 3.6969696969696974e-06, | |
| "loss": 1.0391, | |
| "step": 312 | |
| }, | |
| { | |
| "epoch": 0.6323232323232323, | |
| "grad_norm": 0.1943359375, | |
| "learning_rate": 3.6767676767676767e-06, | |
| "loss": 1.0459, | |
| "step": 313 | |
| }, | |
| { | |
| "epoch": 0.6343434343434343, | |
| "grad_norm": 0.1806640625, | |
| "learning_rate": 3.6565656565656573e-06, | |
| "loss": 1.0434, | |
| "step": 314 | |
| }, | |
| { | |
| "epoch": 0.6363636363636364, | |
| "grad_norm": 0.185546875, | |
| "learning_rate": 3.6363636363636366e-06, | |
| "loss": 0.9825, | |
| "step": 315 | |
| }, | |
| { | |
| "epoch": 0.6383838383838384, | |
| "grad_norm": 0.1904296875, | |
| "learning_rate": 3.6161616161616163e-06, | |
| "loss": 1.0962, | |
| "step": 316 | |
| }, | |
| { | |
| "epoch": 0.6404040404040404, | |
| "grad_norm": 0.240234375, | |
| "learning_rate": 3.595959595959596e-06, | |
| "loss": 1.0104, | |
| "step": 317 | |
| }, | |
| { | |
| "epoch": 0.6424242424242425, | |
| "grad_norm": 0.1767578125, | |
| "learning_rate": 3.575757575757576e-06, | |
| "loss": 0.9901, | |
| "step": 318 | |
| }, | |
| { | |
| "epoch": 0.6444444444444445, | |
| "grad_norm": 0.18359375, | |
| "learning_rate": 3.555555555555556e-06, | |
| "loss": 1.0571, | |
| "step": 319 | |
| }, | |
| { | |
| "epoch": 0.6464646464646465, | |
| "grad_norm": 0.1962890625, | |
| "learning_rate": 3.5353535353535356e-06, | |
| "loss": 0.959, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.6484848484848484, | |
| "grad_norm": 0.1884765625, | |
| "learning_rate": 3.5151515151515154e-06, | |
| "loss": 1.0403, | |
| "step": 321 | |
| }, | |
| { | |
| "epoch": 0.6505050505050505, | |
| "grad_norm": 0.1923828125, | |
| "learning_rate": 3.494949494949495e-06, | |
| "loss": 1.0236, | |
| "step": 322 | |
| }, | |
| { | |
| "epoch": 0.6525252525252525, | |
| "grad_norm": 0.1923828125, | |
| "learning_rate": 3.4747474747474752e-06, | |
| "loss": 1.0587, | |
| "step": 323 | |
| }, | |
| { | |
| "epoch": 0.6545454545454545, | |
| "grad_norm": 0.1962890625, | |
| "learning_rate": 3.454545454545455e-06, | |
| "loss": 1.0402, | |
| "step": 324 | |
| }, | |
| { | |
| "epoch": 0.6565656565656566, | |
| "grad_norm": 0.18359375, | |
| "learning_rate": 3.4343434343434347e-06, | |
| "loss": 1.0342, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 0.6585858585858586, | |
| "grad_norm": 0.205078125, | |
| "learning_rate": 3.414141414141414e-06, | |
| "loss": 1.0657, | |
| "step": 326 | |
| }, | |
| { | |
| "epoch": 0.6606060606060606, | |
| "grad_norm": 0.1806640625, | |
| "learning_rate": 3.3939393939393946e-06, | |
| "loss": 1.0749, | |
| "step": 327 | |
| }, | |
| { | |
| "epoch": 0.6626262626262627, | |
| "grad_norm": 0.181640625, | |
| "learning_rate": 3.3737373737373743e-06, | |
| "loss": 0.9923, | |
| "step": 328 | |
| }, | |
| { | |
| "epoch": 0.6646464646464646, | |
| "grad_norm": 0.1708984375, | |
| "learning_rate": 3.3535353535353536e-06, | |
| "loss": 1.0401, | |
| "step": 329 | |
| }, | |
| { | |
| "epoch": 0.6666666666666666, | |
| "grad_norm": 0.18359375, | |
| "learning_rate": 3.3333333333333333e-06, | |
| "loss": 1.0066, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.6686868686868687, | |
| "grad_norm": 0.19921875, | |
| "learning_rate": 3.3131313131313135e-06, | |
| "loss": 1.0443, | |
| "step": 331 | |
| }, | |
| { | |
| "epoch": 0.6707070707070707, | |
| "grad_norm": 0.287109375, | |
| "learning_rate": 3.292929292929293e-06, | |
| "loss": 1.0418, | |
| "step": 332 | |
| }, | |
| { | |
| "epoch": 0.6727272727272727, | |
| "grad_norm": 0.17578125, | |
| "learning_rate": 3.272727272727273e-06, | |
| "loss": 1.0639, | |
| "step": 333 | |
| }, | |
| { | |
| "epoch": 0.6747474747474748, | |
| "grad_norm": 0.2158203125, | |
| "learning_rate": 3.2525252525252527e-06, | |
| "loss": 0.9951, | |
| "step": 334 | |
| }, | |
| { | |
| "epoch": 0.6767676767676768, | |
| "grad_norm": 0.2431640625, | |
| "learning_rate": 3.232323232323233e-06, | |
| "loss": 1.0334, | |
| "step": 335 | |
| }, | |
| { | |
| "epoch": 0.6787878787878788, | |
| "grad_norm": 0.31640625, | |
| "learning_rate": 3.2121212121212125e-06, | |
| "loss": 1.0239, | |
| "step": 336 | |
| }, | |
| { | |
| "epoch": 0.6808080808080809, | |
| "grad_norm": 0.26171875, | |
| "learning_rate": 3.1919191919191923e-06, | |
| "loss": 1.0718, | |
| "step": 337 | |
| }, | |
| { | |
| "epoch": 0.6828282828282828, | |
| "grad_norm": 0.1982421875, | |
| "learning_rate": 3.171717171717172e-06, | |
| "loss": 1.0556, | |
| "step": 338 | |
| }, | |
| { | |
| "epoch": 0.6848484848484848, | |
| "grad_norm": 0.19140625, | |
| "learning_rate": 3.1515151515151517e-06, | |
| "loss": 0.9692, | |
| "step": 339 | |
| }, | |
| { | |
| "epoch": 0.6868686868686869, | |
| "grad_norm": 0.1943359375, | |
| "learning_rate": 3.131313131313132e-06, | |
| "loss": 1.0153, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.6888888888888889, | |
| "grad_norm": 0.201171875, | |
| "learning_rate": 3.1111111111111116e-06, | |
| "loss": 1.0404, | |
| "step": 341 | |
| }, | |
| { | |
| "epoch": 0.6909090909090909, | |
| "grad_norm": 0.2001953125, | |
| "learning_rate": 3.090909090909091e-06, | |
| "loss": 0.9807, | |
| "step": 342 | |
| }, | |
| { | |
| "epoch": 0.692929292929293, | |
| "grad_norm": 0.185546875, | |
| "learning_rate": 3.0707070707070706e-06, | |
| "loss": 1.0399, | |
| "step": 343 | |
| }, | |
| { | |
| "epoch": 0.694949494949495, | |
| "grad_norm": 0.1953125, | |
| "learning_rate": 3.0505050505050508e-06, | |
| "loss": 1.0141, | |
| "step": 344 | |
| }, | |
| { | |
| "epoch": 0.696969696969697, | |
| "grad_norm": 0.193359375, | |
| "learning_rate": 3.0303030303030305e-06, | |
| "loss": 1.0309, | |
| "step": 345 | |
| }, | |
| { | |
| "epoch": 0.6989898989898989, | |
| "grad_norm": 0.1904296875, | |
| "learning_rate": 3.0101010101010102e-06, | |
| "loss": 1.0634, | |
| "step": 346 | |
| }, | |
| { | |
| "epoch": 0.701010101010101, | |
| "grad_norm": 0.1923828125, | |
| "learning_rate": 2.98989898989899e-06, | |
| "loss": 1.0344, | |
| "step": 347 | |
| }, | |
| { | |
| "epoch": 0.703030303030303, | |
| "grad_norm": 0.1826171875, | |
| "learning_rate": 2.96969696969697e-06, | |
| "loss": 1.0023, | |
| "step": 348 | |
| }, | |
| { | |
| "epoch": 0.705050505050505, | |
| "grad_norm": 0.19921875, | |
| "learning_rate": 2.94949494949495e-06, | |
| "loss": 1.0559, | |
| "step": 349 | |
| }, | |
| { | |
| "epoch": 0.7070707070707071, | |
| "grad_norm": 0.1982421875, | |
| "learning_rate": 2.9292929292929295e-06, | |
| "loss": 0.9863, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.7090909090909091, | |
| "grad_norm": 0.1845703125, | |
| "learning_rate": 2.9090909090909093e-06, | |
| "loss": 1.0229, | |
| "step": 351 | |
| }, | |
| { | |
| "epoch": 0.7111111111111111, | |
| "grad_norm": 0.20703125, | |
| "learning_rate": 2.888888888888889e-06, | |
| "loss": 1.044, | |
| "step": 352 | |
| }, | |
| { | |
| "epoch": 0.7131313131313132, | |
| "grad_norm": 0.1923828125, | |
| "learning_rate": 2.868686868686869e-06, | |
| "loss": 1.0886, | |
| "step": 353 | |
| }, | |
| { | |
| "epoch": 0.7151515151515152, | |
| "grad_norm": 0.2177734375, | |
| "learning_rate": 2.848484848484849e-06, | |
| "loss": 1.0104, | |
| "step": 354 | |
| }, | |
| { | |
| "epoch": 0.7171717171717171, | |
| "grad_norm": 0.2197265625, | |
| "learning_rate": 2.8282828282828286e-06, | |
| "loss": 1.0258, | |
| "step": 355 | |
| }, | |
| { | |
| "epoch": 0.7191919191919192, | |
| "grad_norm": 0.1845703125, | |
| "learning_rate": 2.808080808080808e-06, | |
| "loss": 1.0074, | |
| "step": 356 | |
| }, | |
| { | |
| "epoch": 0.7212121212121212, | |
| "grad_norm": 0.18359375, | |
| "learning_rate": 2.7878787878787885e-06, | |
| "loss": 1.0737, | |
| "step": 357 | |
| }, | |
| { | |
| "epoch": 0.7232323232323232, | |
| "grad_norm": 0.197265625, | |
| "learning_rate": 2.7676767676767678e-06, | |
| "loss": 1.0597, | |
| "step": 358 | |
| }, | |
| { | |
| "epoch": 0.7252525252525253, | |
| "grad_norm": 0.1875, | |
| "learning_rate": 2.7474747474747475e-06, | |
| "loss": 1.0295, | |
| "step": 359 | |
| }, | |
| { | |
| "epoch": 0.7272727272727273, | |
| "grad_norm": 0.1826171875, | |
| "learning_rate": 2.7272727272727272e-06, | |
| "loss": 1.0305, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.7292929292929293, | |
| "grad_norm": 0.1845703125, | |
| "learning_rate": 2.7070707070707074e-06, | |
| "loss": 1.0508, | |
| "step": 361 | |
| }, | |
| { | |
| "epoch": 0.7313131313131314, | |
| "grad_norm": 0.1953125, | |
| "learning_rate": 2.686868686868687e-06, | |
| "loss": 1.008, | |
| "step": 362 | |
| }, | |
| { | |
| "epoch": 0.7333333333333333, | |
| "grad_norm": 0.1806640625, | |
| "learning_rate": 2.666666666666667e-06, | |
| "loss": 0.9775, | |
| "step": 363 | |
| }, | |
| { | |
| "epoch": 0.7353535353535353, | |
| "grad_norm": 0.1953125, | |
| "learning_rate": 2.6464646464646466e-06, | |
| "loss": 1.033, | |
| "step": 364 | |
| }, | |
| { | |
| "epoch": 0.7373737373737373, | |
| "grad_norm": 0.2099609375, | |
| "learning_rate": 2.6262626262626267e-06, | |
| "loss": 1.0351, | |
| "step": 365 | |
| }, | |
| { | |
| "epoch": 0.7393939393939394, | |
| "grad_norm": 0.166015625, | |
| "learning_rate": 2.6060606060606064e-06, | |
| "loss": 0.9793, | |
| "step": 366 | |
| }, | |
| { | |
| "epoch": 0.7414141414141414, | |
| "grad_norm": 0.2060546875, | |
| "learning_rate": 2.585858585858586e-06, | |
| "loss": 1.0528, | |
| "step": 367 | |
| }, | |
| { | |
| "epoch": 0.7434343434343434, | |
| "grad_norm": 0.2099609375, | |
| "learning_rate": 2.565656565656566e-06, | |
| "loss": 1.03, | |
| "step": 368 | |
| }, | |
| { | |
| "epoch": 0.7454545454545455, | |
| "grad_norm": 0.1826171875, | |
| "learning_rate": 2.5454545454545456e-06, | |
| "loss": 1.0614, | |
| "step": 369 | |
| }, | |
| { | |
| "epoch": 0.7474747474747475, | |
| "grad_norm": 0.181640625, | |
| "learning_rate": 2.5252525252525258e-06, | |
| "loss": 1.0243, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.7494949494949495, | |
| "grad_norm": 0.2060546875, | |
| "learning_rate": 2.5050505050505055e-06, | |
| "loss": 1.0558, | |
| "step": 371 | |
| }, | |
| { | |
| "epoch": 0.7515151515151515, | |
| "grad_norm": 0.18359375, | |
| "learning_rate": 2.4848484848484848e-06, | |
| "loss": 1.0429, | |
| "step": 372 | |
| }, | |
| { | |
| "epoch": 0.7535353535353535, | |
| "grad_norm": 0.21484375, | |
| "learning_rate": 2.464646464646465e-06, | |
| "loss": 1.1272, | |
| "step": 373 | |
| }, | |
| { | |
| "epoch": 0.7555555555555555, | |
| "grad_norm": 0.28515625, | |
| "learning_rate": 2.4444444444444447e-06, | |
| "loss": 1.0403, | |
| "step": 374 | |
| }, | |
| { | |
| "epoch": 0.7575757575757576, | |
| "grad_norm": 0.1943359375, | |
| "learning_rate": 2.4242424242424244e-06, | |
| "loss": 1.0417, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 0.7595959595959596, | |
| "grad_norm": 0.177734375, | |
| "learning_rate": 2.404040404040404e-06, | |
| "loss": 1.0172, | |
| "step": 376 | |
| }, | |
| { | |
| "epoch": 0.7616161616161616, | |
| "grad_norm": 0.18359375, | |
| "learning_rate": 2.3838383838383843e-06, | |
| "loss": 1.0566, | |
| "step": 377 | |
| }, | |
| { | |
| "epoch": 0.7636363636363637, | |
| "grad_norm": 0.234375, | |
| "learning_rate": 2.363636363636364e-06, | |
| "loss": 1.0459, | |
| "step": 378 | |
| }, | |
| { | |
| "epoch": 0.7656565656565657, | |
| "grad_norm": 0.17578125, | |
| "learning_rate": 2.3434343434343437e-06, | |
| "loss": 1.0115, | |
| "step": 379 | |
| }, | |
| { | |
| "epoch": 0.7676767676767676, | |
| "grad_norm": 0.197265625, | |
| "learning_rate": 2.3232323232323234e-06, | |
| "loss": 1.0139, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.7696969696969697, | |
| "grad_norm": 0.1865234375, | |
| "learning_rate": 2.303030303030303e-06, | |
| "loss": 1.0304, | |
| "step": 381 | |
| }, | |
| { | |
| "epoch": 0.7717171717171717, | |
| "grad_norm": 0.2470703125, | |
| "learning_rate": 2.282828282828283e-06, | |
| "loss": 0.9806, | |
| "step": 382 | |
| }, | |
| { | |
| "epoch": 0.7737373737373737, | |
| "grad_norm": 0.21484375, | |
| "learning_rate": 2.262626262626263e-06, | |
| "loss": 1.0062, | |
| "step": 383 | |
| }, | |
| { | |
| "epoch": 0.7757575757575758, | |
| "grad_norm": 0.1875, | |
| "learning_rate": 2.2424242424242428e-06, | |
| "loss": 1.0253, | |
| "step": 384 | |
| }, | |
| { | |
| "epoch": 0.7777777777777778, | |
| "grad_norm": 0.2109375, | |
| "learning_rate": 2.222222222222222e-06, | |
| "loss": 1.0317, | |
| "step": 385 | |
| }, | |
| { | |
| "epoch": 0.7797979797979798, | |
| "grad_norm": 0.18359375, | |
| "learning_rate": 2.2020202020202022e-06, | |
| "loss": 1.0146, | |
| "step": 386 | |
| }, | |
| { | |
| "epoch": 0.7818181818181819, | |
| "grad_norm": 0.2001953125, | |
| "learning_rate": 2.181818181818182e-06, | |
| "loss": 0.9777, | |
| "step": 387 | |
| }, | |
| { | |
| "epoch": 0.7838383838383839, | |
| "grad_norm": 0.25390625, | |
| "learning_rate": 2.1616161616161617e-06, | |
| "loss": 1.0182, | |
| "step": 388 | |
| }, | |
| { | |
| "epoch": 0.7858585858585858, | |
| "grad_norm": 0.2060546875, | |
| "learning_rate": 2.1414141414141414e-06, | |
| "loss": 1.0215, | |
| "step": 389 | |
| }, | |
| { | |
| "epoch": 0.7878787878787878, | |
| "grad_norm": 0.1904296875, | |
| "learning_rate": 2.1212121212121216e-06, | |
| "loss": 1.0146, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.7898989898989899, | |
| "grad_norm": 0.181640625, | |
| "learning_rate": 2.1010101010101013e-06, | |
| "loss": 1.002, | |
| "step": 391 | |
| }, | |
| { | |
| "epoch": 0.7919191919191919, | |
| "grad_norm": 0.1748046875, | |
| "learning_rate": 2.080808080808081e-06, | |
| "loss": 1.0192, | |
| "step": 392 | |
| }, | |
| { | |
| "epoch": 0.793939393939394, | |
| "grad_norm": 0.1806640625, | |
| "learning_rate": 2.0606060606060607e-06, | |
| "loss": 0.9827, | |
| "step": 393 | |
| }, | |
| { | |
| "epoch": 0.795959595959596, | |
| "grad_norm": 0.421875, | |
| "learning_rate": 2.0404040404040405e-06, | |
| "loss": 1.0718, | |
| "step": 394 | |
| }, | |
| { | |
| "epoch": 0.797979797979798, | |
| "grad_norm": 0.1884765625, | |
| "learning_rate": 2.02020202020202e-06, | |
| "loss": 1.0095, | |
| "step": 395 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "grad_norm": 0.21875, | |
| "learning_rate": 2.0000000000000003e-06, | |
| "loss": 1.0553, | |
| "step": 396 | |
| }, | |
| { | |
| "epoch": 0.802020202020202, | |
| "grad_norm": 0.2412109375, | |
| "learning_rate": 1.97979797979798e-06, | |
| "loss": 0.9963, | |
| "step": 397 | |
| }, | |
| { | |
| "epoch": 0.804040404040404, | |
| "grad_norm": 0.18359375, | |
| "learning_rate": 1.9595959595959598e-06, | |
| "loss": 1.0107, | |
| "step": 398 | |
| }, | |
| { | |
| "epoch": 0.806060606060606, | |
| "grad_norm": 0.25390625, | |
| "learning_rate": 1.9393939393939395e-06, | |
| "loss": 1.036, | |
| "step": 399 | |
| }, | |
| { | |
| "epoch": 0.8080808080808081, | |
| "grad_norm": 0.1865234375, | |
| "learning_rate": 1.9191919191919192e-06, | |
| "loss": 1.0436, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.8101010101010101, | |
| "grad_norm": 0.1953125, | |
| "learning_rate": 1.8989898989898992e-06, | |
| "loss": 1.0567, | |
| "step": 401 | |
| }, | |
| { | |
| "epoch": 0.8121212121212121, | |
| "grad_norm": 0.1806640625, | |
| "learning_rate": 1.878787878787879e-06, | |
| "loss": 0.975, | |
| "step": 402 | |
| }, | |
| { | |
| "epoch": 0.8141414141414142, | |
| "grad_norm": 0.2158203125, | |
| "learning_rate": 1.8585858585858588e-06, | |
| "loss": 1.0012, | |
| "step": 403 | |
| }, | |
| { | |
| "epoch": 0.8161616161616162, | |
| "grad_norm": 0.1943359375, | |
| "learning_rate": 1.8383838383838384e-06, | |
| "loss": 1.051, | |
| "step": 404 | |
| }, | |
| { | |
| "epoch": 0.8181818181818182, | |
| "grad_norm": 0.26171875, | |
| "learning_rate": 1.8181818181818183e-06, | |
| "loss": 1.0274, | |
| "step": 405 | |
| }, | |
| { | |
| "epoch": 0.8202020202020202, | |
| "grad_norm": 0.1982421875, | |
| "learning_rate": 1.797979797979798e-06, | |
| "loss": 0.9988, | |
| "step": 406 | |
| }, | |
| { | |
| "epoch": 0.8222222222222222, | |
| "grad_norm": 0.2216796875, | |
| "learning_rate": 1.777777777777778e-06, | |
| "loss": 1.0229, | |
| "step": 407 | |
| }, | |
| { | |
| "epoch": 0.8242424242424242, | |
| "grad_norm": 0.1787109375, | |
| "learning_rate": 1.7575757575757577e-06, | |
| "loss": 1.0392, | |
| "step": 408 | |
| }, | |
| { | |
| "epoch": 0.8262626262626263, | |
| "grad_norm": 0.1796875, | |
| "learning_rate": 1.7373737373737376e-06, | |
| "loss": 1.002, | |
| "step": 409 | |
| }, | |
| { | |
| "epoch": 0.8282828282828283, | |
| "grad_norm": 0.2099609375, | |
| "learning_rate": 1.7171717171717173e-06, | |
| "loss": 1.0471, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.8303030303030303, | |
| "grad_norm": 0.21484375, | |
| "learning_rate": 1.6969696969696973e-06, | |
| "loss": 1.0112, | |
| "step": 411 | |
| }, | |
| { | |
| "epoch": 0.8323232323232324, | |
| "grad_norm": 0.2001953125, | |
| "learning_rate": 1.6767676767676768e-06, | |
| "loss": 1.0887, | |
| "step": 412 | |
| }, | |
| { | |
| "epoch": 0.8343434343434344, | |
| "grad_norm": 0.181640625, | |
| "learning_rate": 1.6565656565656567e-06, | |
| "loss": 1.014, | |
| "step": 413 | |
| }, | |
| { | |
| "epoch": 0.8363636363636363, | |
| "grad_norm": 0.25390625, | |
| "learning_rate": 1.6363636363636365e-06, | |
| "loss": 0.9878, | |
| "step": 414 | |
| }, | |
| { | |
| "epoch": 0.8383838383838383, | |
| "grad_norm": 0.1796875, | |
| "learning_rate": 1.6161616161616164e-06, | |
| "loss": 0.9874, | |
| "step": 415 | |
| }, | |
| { | |
| "epoch": 0.8404040404040404, | |
| "grad_norm": 0.224609375, | |
| "learning_rate": 1.5959595959595961e-06, | |
| "loss": 1.0532, | |
| "step": 416 | |
| }, | |
| { | |
| "epoch": 0.8424242424242424, | |
| "grad_norm": 0.1826171875, | |
| "learning_rate": 1.5757575757575759e-06, | |
| "loss": 0.9955, | |
| "step": 417 | |
| }, | |
| { | |
| "epoch": 0.8444444444444444, | |
| "grad_norm": 0.1748046875, | |
| "learning_rate": 1.5555555555555558e-06, | |
| "loss": 1.0148, | |
| "step": 418 | |
| }, | |
| { | |
| "epoch": 0.8464646464646465, | |
| "grad_norm": 0.197265625, | |
| "learning_rate": 1.5353535353535353e-06, | |
| "loss": 1.0331, | |
| "step": 419 | |
| }, | |
| { | |
| "epoch": 0.8484848484848485, | |
| "grad_norm": 0.1748046875, | |
| "learning_rate": 1.5151515151515152e-06, | |
| "loss": 1.0199, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.8505050505050505, | |
| "grad_norm": 0.185546875, | |
| "learning_rate": 1.494949494949495e-06, | |
| "loss": 0.9248, | |
| "step": 421 | |
| }, | |
| { | |
| "epoch": 0.8525252525252526, | |
| "grad_norm": 0.18359375, | |
| "learning_rate": 1.474747474747475e-06, | |
| "loss": 1.0306, | |
| "step": 422 | |
| }, | |
| { | |
| "epoch": 0.8545454545454545, | |
| "grad_norm": 0.1748046875, | |
| "learning_rate": 1.4545454545454546e-06, | |
| "loss": 1.0285, | |
| "step": 423 | |
| }, | |
| { | |
| "epoch": 0.8565656565656565, | |
| "grad_norm": 0.2060546875, | |
| "learning_rate": 1.4343434343434346e-06, | |
| "loss": 1.0151, | |
| "step": 424 | |
| }, | |
| { | |
| "epoch": 0.8585858585858586, | |
| "grad_norm": 0.1845703125, | |
| "learning_rate": 1.4141414141414143e-06, | |
| "loss": 1.0575, | |
| "step": 425 | |
| }, | |
| { | |
| "epoch": 0.8606060606060606, | |
| "grad_norm": 0.197265625, | |
| "learning_rate": 1.3939393939393942e-06, | |
| "loss": 1.0269, | |
| "step": 426 | |
| }, | |
| { | |
| "epoch": 0.8626262626262626, | |
| "grad_norm": 0.2216796875, | |
| "learning_rate": 1.3737373737373738e-06, | |
| "loss": 1.0597, | |
| "step": 427 | |
| }, | |
| { | |
| "epoch": 0.8646464646464647, | |
| "grad_norm": 0.224609375, | |
| "learning_rate": 1.3535353535353537e-06, | |
| "loss": 0.997, | |
| "step": 428 | |
| }, | |
| { | |
| "epoch": 0.8666666666666667, | |
| "grad_norm": 0.208984375, | |
| "learning_rate": 1.3333333333333334e-06, | |
| "loss": 1.0348, | |
| "step": 429 | |
| }, | |
| { | |
| "epoch": 0.8686868686868687, | |
| "grad_norm": 0.1787109375, | |
| "learning_rate": 1.3131313131313134e-06, | |
| "loss": 0.978, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.8707070707070707, | |
| "grad_norm": 0.2470703125, | |
| "learning_rate": 1.292929292929293e-06, | |
| "loss": 1.0392, | |
| "step": 431 | |
| }, | |
| { | |
| "epoch": 0.8727272727272727, | |
| "grad_norm": 0.1796875, | |
| "learning_rate": 1.2727272727272728e-06, | |
| "loss": 1.003, | |
| "step": 432 | |
| }, | |
| { | |
| "epoch": 0.8747474747474747, | |
| "grad_norm": 0.189453125, | |
| "learning_rate": 1.2525252525252527e-06, | |
| "loss": 1.0488, | |
| "step": 433 | |
| }, | |
| { | |
| "epoch": 0.8767676767676768, | |
| "grad_norm": 0.1875, | |
| "learning_rate": 1.2323232323232325e-06, | |
| "loss": 1.0134, | |
| "step": 434 | |
| }, | |
| { | |
| "epoch": 0.8787878787878788, | |
| "grad_norm": 0.1943359375, | |
| "learning_rate": 1.2121212121212122e-06, | |
| "loss": 1.0099, | |
| "step": 435 | |
| }, | |
| { | |
| "epoch": 0.8808080808080808, | |
| "grad_norm": 0.181640625, | |
| "learning_rate": 1.1919191919191921e-06, | |
| "loss": 1.0093, | |
| "step": 436 | |
| }, | |
| { | |
| "epoch": 0.8828282828282829, | |
| "grad_norm": 0.197265625, | |
| "learning_rate": 1.1717171717171719e-06, | |
| "loss": 1.041, | |
| "step": 437 | |
| }, | |
| { | |
| "epoch": 0.8848484848484849, | |
| "grad_norm": 0.1904296875, | |
| "learning_rate": 1.1515151515151516e-06, | |
| "loss": 1.0555, | |
| "step": 438 | |
| }, | |
| { | |
| "epoch": 0.8868686868686869, | |
| "grad_norm": 0.1962890625, | |
| "learning_rate": 1.1313131313131315e-06, | |
| "loss": 0.996, | |
| "step": 439 | |
| }, | |
| { | |
| "epoch": 0.8888888888888888, | |
| "grad_norm": 0.26953125, | |
| "learning_rate": 1.111111111111111e-06, | |
| "loss": 1.0446, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.8909090909090909, | |
| "grad_norm": 0.279296875, | |
| "learning_rate": 1.090909090909091e-06, | |
| "loss": 1.0465, | |
| "step": 441 | |
| }, | |
| { | |
| "epoch": 0.8929292929292929, | |
| "grad_norm": 0.2294921875, | |
| "learning_rate": 1.0707070707070707e-06, | |
| "loss": 1.0364, | |
| "step": 442 | |
| }, | |
| { | |
| "epoch": 0.8949494949494949, | |
| "grad_norm": 0.185546875, | |
| "learning_rate": 1.0505050505050506e-06, | |
| "loss": 1.0254, | |
| "step": 443 | |
| }, | |
| { | |
| "epoch": 0.896969696969697, | |
| "grad_norm": 0.2138671875, | |
| "learning_rate": 1.0303030303030304e-06, | |
| "loss": 0.9752, | |
| "step": 444 | |
| }, | |
| { | |
| "epoch": 0.898989898989899, | |
| "grad_norm": 0.2255859375, | |
| "learning_rate": 1.01010101010101e-06, | |
| "loss": 1.0568, | |
| "step": 445 | |
| }, | |
| { | |
| "epoch": 0.901010101010101, | |
| "grad_norm": 0.181640625, | |
| "learning_rate": 9.8989898989899e-07, | |
| "loss": 1.0076, | |
| "step": 446 | |
| }, | |
| { | |
| "epoch": 0.9030303030303031, | |
| "grad_norm": 0.189453125, | |
| "learning_rate": 9.696969696969698e-07, | |
| "loss": 1.0118, | |
| "step": 447 | |
| }, | |
| { | |
| "epoch": 0.9050505050505051, | |
| "grad_norm": 0.294921875, | |
| "learning_rate": 9.494949494949496e-07, | |
| "loss": 1.0203, | |
| "step": 448 | |
| }, | |
| { | |
| "epoch": 0.907070707070707, | |
| "grad_norm": 0.2138671875, | |
| "learning_rate": 9.292929292929294e-07, | |
| "loss": 1.0872, | |
| "step": 449 | |
| }, | |
| { | |
| "epoch": 0.9090909090909091, | |
| "grad_norm": 0.1796875, | |
| "learning_rate": 9.090909090909091e-07, | |
| "loss": 1.0107, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.9111111111111111, | |
| "grad_norm": 0.5234375, | |
| "learning_rate": 8.88888888888889e-07, | |
| "loss": 0.9961, | |
| "step": 451 | |
| }, | |
| { | |
| "epoch": 0.9131313131313131, | |
| "grad_norm": 0.376953125, | |
| "learning_rate": 8.686868686868688e-07, | |
| "loss": 0.9945, | |
| "step": 452 | |
| }, | |
| { | |
| "epoch": 0.9151515151515152, | |
| "grad_norm": 0.185546875, | |
| "learning_rate": 8.484848484848486e-07, | |
| "loss": 1.0275, | |
| "step": 453 | |
| }, | |
| { | |
| "epoch": 0.9171717171717172, | |
| "grad_norm": 0.22265625, | |
| "learning_rate": 8.282828282828284e-07, | |
| "loss": 1.0274, | |
| "step": 454 | |
| }, | |
| { | |
| "epoch": 0.9191919191919192, | |
| "grad_norm": 0.1826171875, | |
| "learning_rate": 8.080808080808082e-07, | |
| "loss": 1.0346, | |
| "step": 455 | |
| }, | |
| { | |
| "epoch": 0.9212121212121213, | |
| "grad_norm": 0.2314453125, | |
| "learning_rate": 7.878787878787879e-07, | |
| "loss": 1.098, | |
| "step": 456 | |
| }, | |
| { | |
| "epoch": 0.9232323232323232, | |
| "grad_norm": 0.28125, | |
| "learning_rate": 7.676767676767677e-07, | |
| "loss": 0.9775, | |
| "step": 457 | |
| }, | |
| { | |
| "epoch": 0.9252525252525252, | |
| "grad_norm": 0.1923828125, | |
| "learning_rate": 7.474747474747475e-07, | |
| "loss": 1.0375, | |
| "step": 458 | |
| }, | |
| { | |
| "epoch": 0.9272727272727272, | |
| "grad_norm": 0.57421875, | |
| "learning_rate": 7.272727272727273e-07, | |
| "loss": 1.0435, | |
| "step": 459 | |
| }, | |
| { | |
| "epoch": 0.9292929292929293, | |
| "grad_norm": 0.2099609375, | |
| "learning_rate": 7.070707070707071e-07, | |
| "loss": 0.9988, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.9313131313131313, | |
| "grad_norm": 0.2216796875, | |
| "learning_rate": 6.868686868686869e-07, | |
| "loss": 1.0125, | |
| "step": 461 | |
| }, | |
| { | |
| "epoch": 0.9333333333333333, | |
| "grad_norm": 0.18359375, | |
| "learning_rate": 6.666666666666667e-07, | |
| "loss": 1.0182, | |
| "step": 462 | |
| }, | |
| { | |
| "epoch": 0.9353535353535354, | |
| "grad_norm": 0.2041015625, | |
| "learning_rate": 6.464646464646465e-07, | |
| "loss": 0.9986, | |
| "step": 463 | |
| }, | |
| { | |
| "epoch": 0.9373737373737374, | |
| "grad_norm": 0.1953125, | |
| "learning_rate": 6.262626262626264e-07, | |
| "loss": 1.0093, | |
| "step": 464 | |
| }, | |
| { | |
| "epoch": 0.9393939393939394, | |
| "grad_norm": 0.189453125, | |
| "learning_rate": 6.060606060606061e-07, | |
| "loss": 0.9871, | |
| "step": 465 | |
| }, | |
| { | |
| "epoch": 0.9414141414141414, | |
| "grad_norm": 0.255859375, | |
| "learning_rate": 5.858585858585859e-07, | |
| "loss": 1.0191, | |
| "step": 466 | |
| }, | |
| { | |
| "epoch": 0.9434343434343434, | |
| "grad_norm": 0.265625, | |
| "learning_rate": 5.656565656565658e-07, | |
| "loss": 1.0001, | |
| "step": 467 | |
| }, | |
| { | |
| "epoch": 0.9454545454545454, | |
| "grad_norm": 0.2001953125, | |
| "learning_rate": 5.454545454545455e-07, | |
| "loss": 0.9726, | |
| "step": 468 | |
| }, | |
| { | |
| "epoch": 0.9474747474747475, | |
| "grad_norm": 0.1962890625, | |
| "learning_rate": 5.252525252525253e-07, | |
| "loss": 1.069, | |
| "step": 469 | |
| }, | |
| { | |
| "epoch": 0.9494949494949495, | |
| "grad_norm": 0.2373046875, | |
| "learning_rate": 5.05050505050505e-07, | |
| "loss": 1.0334, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 0.9515151515151515, | |
| "grad_norm": 0.177734375, | |
| "learning_rate": 4.848484848484849e-07, | |
| "loss": 1.0442, | |
| "step": 471 | |
| }, | |
| { | |
| "epoch": 0.9535353535353536, | |
| "grad_norm": 0.1806640625, | |
| "learning_rate": 4.646464646464647e-07, | |
| "loss": 1.0116, | |
| "step": 472 | |
| }, | |
| { | |
| "epoch": 0.9555555555555556, | |
| "grad_norm": 0.69921875, | |
| "learning_rate": 4.444444444444445e-07, | |
| "loss": 0.9919, | |
| "step": 473 | |
| }, | |
| { | |
| "epoch": 0.9575757575757575, | |
| "grad_norm": 0.1865234375, | |
| "learning_rate": 4.242424242424243e-07, | |
| "loss": 1.012, | |
| "step": 474 | |
| }, | |
| { | |
| "epoch": 0.9595959595959596, | |
| "grad_norm": 0.19140625, | |
| "learning_rate": 4.040404040404041e-07, | |
| "loss": 0.9972, | |
| "step": 475 | |
| }, | |
| { | |
| "epoch": 0.9616161616161616, | |
| "grad_norm": 0.216796875, | |
| "learning_rate": 3.838383838383838e-07, | |
| "loss": 1.0253, | |
| "step": 476 | |
| }, | |
| { | |
| "epoch": 0.9636363636363636, | |
| "grad_norm": 0.1796875, | |
| "learning_rate": 3.6363636363636366e-07, | |
| "loss": 1.0101, | |
| "step": 477 | |
| }, | |
| { | |
| "epoch": 0.9656565656565657, | |
| "grad_norm": 0.1796875, | |
| "learning_rate": 3.4343434343434344e-07, | |
| "loss": 0.9982, | |
| "step": 478 | |
| }, | |
| { | |
| "epoch": 0.9676767676767677, | |
| "grad_norm": 0.1982421875, | |
| "learning_rate": 3.2323232323232327e-07, | |
| "loss": 1.0391, | |
| "step": 479 | |
| }, | |
| { | |
| "epoch": 0.9696969696969697, | |
| "grad_norm": 0.1787109375, | |
| "learning_rate": 3.0303030303030305e-07, | |
| "loss": 1.0184, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.9717171717171718, | |
| "grad_norm": 0.181640625, | |
| "learning_rate": 2.828282828282829e-07, | |
| "loss": 1.0248, | |
| "step": 481 | |
| }, | |
| { | |
| "epoch": 0.9737373737373738, | |
| "grad_norm": 0.177734375, | |
| "learning_rate": 2.6262626262626266e-07, | |
| "loss": 0.9759, | |
| "step": 482 | |
| }, | |
| { | |
| "epoch": 0.9757575757575757, | |
| "grad_norm": 0.185546875, | |
| "learning_rate": 2.4242424242424244e-07, | |
| "loss": 1.0363, | |
| "step": 483 | |
| }, | |
| { | |
| "epoch": 0.9777777777777777, | |
| "grad_norm": 0.177734375, | |
| "learning_rate": 2.2222222222222224e-07, | |
| "loss": 1.0131, | |
| "step": 484 | |
| }, | |
| { | |
| "epoch": 0.9797979797979798, | |
| "grad_norm": 0.197265625, | |
| "learning_rate": 2.0202020202020205e-07, | |
| "loss": 1.0333, | |
| "step": 485 | |
| }, | |
| { | |
| "epoch": 0.9818181818181818, | |
| "grad_norm": 0.1962890625, | |
| "learning_rate": 1.8181818181818183e-07, | |
| "loss": 1.057, | |
| "step": 486 | |
| }, | |
| { | |
| "epoch": 0.9838383838383838, | |
| "grad_norm": 0.1865234375, | |
| "learning_rate": 1.6161616161616163e-07, | |
| "loss": 1.0465, | |
| "step": 487 | |
| }, | |
| { | |
| "epoch": 0.9858585858585859, | |
| "grad_norm": 0.1943359375, | |
| "learning_rate": 1.4141414141414144e-07, | |
| "loss": 1.0177, | |
| "step": 488 | |
| }, | |
| { | |
| "epoch": 0.9878787878787879, | |
| "grad_norm": 0.251953125, | |
| "learning_rate": 1.2121212121212122e-07, | |
| "loss": 1.0767, | |
| "step": 489 | |
| }, | |
| { | |
| "epoch": 0.98989898989899, | |
| "grad_norm": 0.2099609375, | |
| "learning_rate": 1.0101010101010103e-07, | |
| "loss": 1.0518, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 0.9919191919191919, | |
| "grad_norm": 0.1796875, | |
| "learning_rate": 8.080808080808082e-08, | |
| "loss": 1.0433, | |
| "step": 491 | |
| }, | |
| { | |
| "epoch": 0.9939393939393939, | |
| "grad_norm": 0.208984375, | |
| "learning_rate": 6.060606060606061e-08, | |
| "loss": 1.0402, | |
| "step": 492 | |
| }, | |
| { | |
| "epoch": 0.9959595959595959, | |
| "grad_norm": 0.443359375, | |
| "learning_rate": 4.040404040404041e-08, | |
| "loss": 1.0026, | |
| "step": 493 | |
| }, | |
| { | |
| "epoch": 0.997979797979798, | |
| "grad_norm": 0.228515625, | |
| "learning_rate": 2.0202020202020204e-08, | |
| "loss": 1.1265, | |
| "step": 494 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 0.1806640625, | |
| "learning_rate": 0.0, | |
| "loss": 1.0203, | |
| "step": 495 | |
| } | |
| ], | |
| "logging_steps": 1.0, | |
| "max_steps": 495, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 0, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.5810777051205468e+18, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |