| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 6.98989898989899, | |
| "eval_steps": 1, | |
| "global_step": 173, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.04040404040404041, | |
| "grad_norm": 2.088834762573242, | |
| "learning_rate": 8.333333333333333e-07, | |
| "loss": 5.4688, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.04040404040404041, | |
| "eval_loss": 5.470384120941162, | |
| "eval_runtime": 4.8066, | |
| "eval_samples_per_second": 34.536, | |
| "eval_steps_per_second": 0.624, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.08080808080808081, | |
| "grad_norm": 2.0961971282958984, | |
| "learning_rate": 1.6666666666666667e-06, | |
| "loss": 5.4731, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.08080808080808081, | |
| "eval_loss": 5.4689249992370605, | |
| "eval_runtime": 4.8593, | |
| "eval_samples_per_second": 34.161, | |
| "eval_steps_per_second": 0.617, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.12121212121212122, | |
| "grad_norm": 2.0940349102020264, | |
| "learning_rate": 2.5e-06, | |
| "loss": 5.4803, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.12121212121212122, | |
| "eval_loss": 5.467825412750244, | |
| "eval_runtime": 4.9081, | |
| "eval_samples_per_second": 33.822, | |
| "eval_steps_per_second": 0.611, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.16161616161616163, | |
| "grad_norm": 2.095174551010132, | |
| "learning_rate": 3.3333333333333333e-06, | |
| "loss": 5.5119, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.16161616161616163, | |
| "eval_loss": 5.465516567230225, | |
| "eval_runtime": 4.8615, | |
| "eval_samples_per_second": 34.146, | |
| "eval_steps_per_second": 0.617, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.20202020202020202, | |
| "grad_norm": 2.1109118461608887, | |
| "learning_rate": 4.166666666666667e-06, | |
| "loss": 5.4662, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.20202020202020202, | |
| "eval_loss": 5.4626851081848145, | |
| "eval_runtime": 4.844, | |
| "eval_samples_per_second": 34.27, | |
| "eval_steps_per_second": 0.619, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.24242424242424243, | |
| "grad_norm": 2.1030592918395996, | |
| "learning_rate": 5e-06, | |
| "loss": 5.4691, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.24242424242424243, | |
| "eval_loss": 5.45806884765625, | |
| "eval_runtime": 4.8388, | |
| "eval_samples_per_second": 34.306, | |
| "eval_steps_per_second": 0.62, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.2828282828282828, | |
| "grad_norm": 2.1202447414398193, | |
| "learning_rate": 5.833333333333334e-06, | |
| "loss": 5.4851, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.2828282828282828, | |
| "eval_loss": 5.449892520904541, | |
| "eval_runtime": 4.8431, | |
| "eval_samples_per_second": 34.276, | |
| "eval_steps_per_second": 0.619, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.32323232323232326, | |
| "grad_norm": 2.090963363647461, | |
| "learning_rate": 6.666666666666667e-06, | |
| "loss": 5.4228, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.32323232323232326, | |
| "eval_loss": 5.442515850067139, | |
| "eval_runtime": 4.8605, | |
| "eval_samples_per_second": 34.153, | |
| "eval_steps_per_second": 0.617, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.36363636363636365, | |
| "grad_norm": 2.112323760986328, | |
| "learning_rate": 7.500000000000001e-06, | |
| "loss": 5.4715, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.36363636363636365, | |
| "eval_loss": 5.4345855712890625, | |
| "eval_runtime": 4.8796, | |
| "eval_samples_per_second": 34.019, | |
| "eval_steps_per_second": 0.615, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.40404040404040403, | |
| "grad_norm": 2.1456995010375977, | |
| "learning_rate": 8.333333333333334e-06, | |
| "loss": 5.4211, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.40404040404040403, | |
| "eval_loss": 5.424546718597412, | |
| "eval_runtime": 4.9274, | |
| "eval_samples_per_second": 33.689, | |
| "eval_steps_per_second": 0.609, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.4444444444444444, | |
| "grad_norm": 2.1602349281311035, | |
| "learning_rate": 9.166666666666666e-06, | |
| "loss": 5.4301, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.4444444444444444, | |
| "eval_loss": 5.41035795211792, | |
| "eval_runtime": 4.9819, | |
| "eval_samples_per_second": 33.32, | |
| "eval_steps_per_second": 0.602, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.48484848484848486, | |
| "grad_norm": 2.1762421131134033, | |
| "learning_rate": 1e-05, | |
| "loss": 5.4158, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.48484848484848486, | |
| "eval_loss": 5.400452613830566, | |
| "eval_runtime": 5.0737, | |
| "eval_samples_per_second": 32.718, | |
| "eval_steps_per_second": 0.591, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.5252525252525253, | |
| "grad_norm": 2.2415969371795654, | |
| "learning_rate": 1.0833333333333334e-05, | |
| "loss": 5.3986, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.5252525252525253, | |
| "eval_loss": 5.382190227508545, | |
| "eval_runtime": 4.9555, | |
| "eval_samples_per_second": 33.498, | |
| "eval_steps_per_second": 0.605, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.5656565656565656, | |
| "grad_norm": 2.2669475078582764, | |
| "learning_rate": 1.1666666666666668e-05, | |
| "loss": 5.428, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.5656565656565656, | |
| "eval_loss": 5.3634443283081055, | |
| "eval_runtime": 4.9029, | |
| "eval_samples_per_second": 33.857, | |
| "eval_steps_per_second": 0.612, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.6060606060606061, | |
| "grad_norm": 2.262896776199341, | |
| "learning_rate": 1.25e-05, | |
| "loss": 5.3741, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.6060606060606061, | |
| "eval_loss": 5.347131729125977, | |
| "eval_runtime": 4.8934, | |
| "eval_samples_per_second": 33.923, | |
| "eval_steps_per_second": 0.613, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.6464646464646465, | |
| "grad_norm": 2.3363702297210693, | |
| "learning_rate": 1.3333333333333333e-05, | |
| "loss": 5.4134, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.6464646464646465, | |
| "eval_loss": 5.321357250213623, | |
| "eval_runtime": 4.9027, | |
| "eval_samples_per_second": 33.859, | |
| "eval_steps_per_second": 0.612, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.6868686868686869, | |
| "grad_norm": 2.3906755447387695, | |
| "learning_rate": 1.416666666666667e-05, | |
| "loss": 5.3305, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.6868686868686869, | |
| "eval_loss": 5.292910099029541, | |
| "eval_runtime": 4.9268, | |
| "eval_samples_per_second": 33.693, | |
| "eval_steps_per_second": 0.609, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.7272727272727273, | |
| "grad_norm": 2.44368839263916, | |
| "learning_rate": 1.5000000000000002e-05, | |
| "loss": 5.3406, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.7272727272727273, | |
| "eval_loss": 5.257543563842773, | |
| "eval_runtime": 4.9839, | |
| "eval_samples_per_second": 33.308, | |
| "eval_steps_per_second": 0.602, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.7676767676767676, | |
| "grad_norm": 2.4937825202941895, | |
| "learning_rate": 1.5833333333333333e-05, | |
| "loss": 5.3134, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.7676767676767676, | |
| "eval_loss": 5.225679874420166, | |
| "eval_runtime": 5.1205, | |
| "eval_samples_per_second": 32.419, | |
| "eval_steps_per_second": 0.586, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.8080808080808081, | |
| "grad_norm": 2.547194480895996, | |
| "learning_rate": 1.6666666666666667e-05, | |
| "loss": 5.2303, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.8080808080808081, | |
| "eval_loss": 5.183907985687256, | |
| "eval_runtime": 5.1208, | |
| "eval_samples_per_second": 32.417, | |
| "eval_steps_per_second": 0.586, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.8484848484848485, | |
| "grad_norm": 2.5578083992004395, | |
| "learning_rate": 1.7500000000000002e-05, | |
| "loss": 5.1255, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.8484848484848485, | |
| "eval_loss": 5.136340141296387, | |
| "eval_runtime": 5.1161, | |
| "eval_samples_per_second": 32.446, | |
| "eval_steps_per_second": 0.586, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.8888888888888888, | |
| "grad_norm": 2.6553032398223877, | |
| "learning_rate": 1.8333333333333333e-05, | |
| "loss": 5.1376, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.8888888888888888, | |
| "eval_loss": 5.085525035858154, | |
| "eval_runtime": 5.1496, | |
| "eval_samples_per_second": 32.236, | |
| "eval_steps_per_second": 0.583, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.9292929292929293, | |
| "grad_norm": 2.733492374420166, | |
| "learning_rate": 1.916666666666667e-05, | |
| "loss": 5.1051, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.9292929292929293, | |
| "eval_loss": 5.0193634033203125, | |
| "eval_runtime": 5.0473, | |
| "eval_samples_per_second": 32.889, | |
| "eval_steps_per_second": 0.594, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.9696969696969697, | |
| "grad_norm": 2.765582799911499, | |
| "learning_rate": 2e-05, | |
| "loss": 5.0082, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.9696969696969697, | |
| "eval_loss": 4.950736999511719, | |
| "eval_runtime": 4.989, | |
| "eval_samples_per_second": 33.273, | |
| "eval_steps_per_second": 0.601, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 1.0101010101010102, | |
| "grad_norm": 2.8943891525268555, | |
| "learning_rate": 1.990740740740741e-05, | |
| "loss": 4.9736, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.0101010101010102, | |
| "eval_loss": 4.87933349609375, | |
| "eval_runtime": 4.991, | |
| "eval_samples_per_second": 33.26, | |
| "eval_steps_per_second": 0.601, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.0505050505050506, | |
| "grad_norm": 2.9802019596099854, | |
| "learning_rate": 1.9814814814814816e-05, | |
| "loss": 4.8728, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 1.0505050505050506, | |
| "eval_loss": 4.796956539154053, | |
| "eval_runtime": 5.0224, | |
| "eval_samples_per_second": 33.052, | |
| "eval_steps_per_second": 0.597, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 1.0909090909090908, | |
| "grad_norm": 3.068443536758423, | |
| "learning_rate": 1.9722222222222224e-05, | |
| "loss": 4.8132, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 1.0909090909090908, | |
| "eval_loss": 4.7025275230407715, | |
| "eval_runtime": 5.1226, | |
| "eval_samples_per_second": 32.406, | |
| "eval_steps_per_second": 0.586, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 1.1313131313131313, | |
| "grad_norm": 3.2245917320251465, | |
| "learning_rate": 1.962962962962963e-05, | |
| "loss": 4.7175, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 1.1313131313131313, | |
| "eval_loss": 4.607891082763672, | |
| "eval_runtime": 5.0927, | |
| "eval_samples_per_second": 32.596, | |
| "eval_steps_per_second": 0.589, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 1.1717171717171717, | |
| "grad_norm": 3.3136157989501953, | |
| "learning_rate": 1.9537037037037038e-05, | |
| "loss": 4.6429, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 1.1717171717171717, | |
| "eval_loss": 4.510694980621338, | |
| "eval_runtime": 5.0136, | |
| "eval_samples_per_second": 33.11, | |
| "eval_steps_per_second": 0.598, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 1.2121212121212122, | |
| "grad_norm": 3.329773426055908, | |
| "learning_rate": 1.9444444444444445e-05, | |
| "loss": 4.4686, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.2121212121212122, | |
| "eval_loss": 4.406045913696289, | |
| "eval_runtime": 4.9753, | |
| "eval_samples_per_second": 33.365, | |
| "eval_steps_per_second": 0.603, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.2525252525252526, | |
| "grad_norm": 3.5462117195129395, | |
| "learning_rate": 1.9351851851851853e-05, | |
| "loss": 4.427, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 1.2525252525252526, | |
| "eval_loss": 4.309689998626709, | |
| "eval_runtime": 4.9974, | |
| "eval_samples_per_second": 33.217, | |
| "eval_steps_per_second": 0.6, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 1.2929292929292928, | |
| "grad_norm": 3.6190805435180664, | |
| "learning_rate": 1.925925925925926e-05, | |
| "loss": 4.2899, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 1.2929292929292928, | |
| "eval_loss": 4.215596675872803, | |
| "eval_runtime": 5.0637, | |
| "eval_samples_per_second": 32.782, | |
| "eval_steps_per_second": 0.592, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 1.3333333333333333, | |
| "grad_norm": 3.698317289352417, | |
| "learning_rate": 1.916666666666667e-05, | |
| "loss": 4.1752, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 1.3333333333333333, | |
| "eval_loss": 4.106834411621094, | |
| "eval_runtime": 5.1651, | |
| "eval_samples_per_second": 32.139, | |
| "eval_steps_per_second": 0.581, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 1.3737373737373737, | |
| "grad_norm": 3.4807214736938477, | |
| "learning_rate": 1.9074074074074075e-05, | |
| "loss": 4.1277, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 1.3737373737373737, | |
| "eval_loss": 4.001583099365234, | |
| "eval_runtime": 5.0567, | |
| "eval_samples_per_second": 32.828, | |
| "eval_steps_per_second": 0.593, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 1.4141414141414141, | |
| "grad_norm": 3.1380534172058105, | |
| "learning_rate": 1.8981481481481482e-05, | |
| "loss": 4.0069, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 1.4141414141414141, | |
| "eval_loss": 3.9105026721954346, | |
| "eval_runtime": 5.07, | |
| "eval_samples_per_second": 32.741, | |
| "eval_steps_per_second": 0.592, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 1.4545454545454546, | |
| "grad_norm": 2.9076974391937256, | |
| "learning_rate": 1.888888888888889e-05, | |
| "loss": 3.8911, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 1.4545454545454546, | |
| "eval_loss": 3.838275194168091, | |
| "eval_runtime": 5.1402, | |
| "eval_samples_per_second": 32.295, | |
| "eval_steps_per_second": 0.584, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 1.494949494949495, | |
| "grad_norm": 2.4755232334136963, | |
| "learning_rate": 1.8796296296296296e-05, | |
| "loss": 3.8522, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 1.494949494949495, | |
| "eval_loss": 3.776526689529419, | |
| "eval_runtime": 5.1768, | |
| "eval_samples_per_second": 32.066, | |
| "eval_steps_per_second": 0.58, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 1.5353535353535355, | |
| "grad_norm": 2.1607069969177246, | |
| "learning_rate": 1.8703703703703707e-05, | |
| "loss": 3.7828, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 1.5353535353535355, | |
| "eval_loss": 3.7257139682769775, | |
| "eval_runtime": 5.1584, | |
| "eval_samples_per_second": 32.181, | |
| "eval_steps_per_second": 0.582, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 1.5757575757575757, | |
| "grad_norm": 1.9251853227615356, | |
| "learning_rate": 1.8611111111111114e-05, | |
| "loss": 3.7511, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 1.5757575757575757, | |
| "eval_loss": 3.680651903152466, | |
| "eval_runtime": 5.139, | |
| "eval_samples_per_second": 32.302, | |
| "eval_steps_per_second": 0.584, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 1.6161616161616161, | |
| "grad_norm": 1.8553980588912964, | |
| "learning_rate": 1.851851851851852e-05, | |
| "loss": 3.7108, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.6161616161616161, | |
| "eval_loss": 3.633517026901245, | |
| "eval_runtime": 5.1036, | |
| "eval_samples_per_second": 32.526, | |
| "eval_steps_per_second": 0.588, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.6565656565656566, | |
| "grad_norm": 1.831110954284668, | |
| "learning_rate": 1.8425925925925926e-05, | |
| "loss": 3.6165, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 1.6565656565656566, | |
| "eval_loss": 3.5877223014831543, | |
| "eval_runtime": 5.1287, | |
| "eval_samples_per_second": 32.367, | |
| "eval_steps_per_second": 0.585, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 1.696969696969697, | |
| "grad_norm": 1.8035303354263306, | |
| "learning_rate": 1.8333333333333333e-05, | |
| "loss": 3.5555, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 1.696969696969697, | |
| "eval_loss": 3.5403287410736084, | |
| "eval_runtime": 5.1001, | |
| "eval_samples_per_second": 32.549, | |
| "eval_steps_per_second": 0.588, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 1.7373737373737375, | |
| "grad_norm": 1.7953453063964844, | |
| "learning_rate": 1.8240740740740744e-05, | |
| "loss": 3.5437, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 1.7373737373737375, | |
| "eval_loss": 3.492953300476074, | |
| "eval_runtime": 5.1541, | |
| "eval_samples_per_second": 32.207, | |
| "eval_steps_per_second": 0.582, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 1.7777777777777777, | |
| "grad_norm": 1.7807087898254395, | |
| "learning_rate": 1.814814814814815e-05, | |
| "loss": 3.4676, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 1.7777777777777777, | |
| "eval_loss": 3.443131446838379, | |
| "eval_runtime": 5.1066, | |
| "eval_samples_per_second": 32.507, | |
| "eval_steps_per_second": 0.587, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 1.8181818181818183, | |
| "grad_norm": 1.8204630613327026, | |
| "learning_rate": 1.8055555555555558e-05, | |
| "loss": 3.4517, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 1.8181818181818183, | |
| "eval_loss": 3.396712303161621, | |
| "eval_runtime": 5.1475, | |
| "eval_samples_per_second": 32.249, | |
| "eval_steps_per_second": 0.583, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 1.8585858585858586, | |
| "grad_norm": 1.8122252225875854, | |
| "learning_rate": 1.7962962962962965e-05, | |
| "loss": 3.4189, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 1.8585858585858586, | |
| "eval_loss": 3.3434314727783203, | |
| "eval_runtime": 5.0828, | |
| "eval_samples_per_second": 32.659, | |
| "eval_steps_per_second": 0.59, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 1.898989898989899, | |
| "grad_norm": 1.8433269262313843, | |
| "learning_rate": 1.7870370370370373e-05, | |
| "loss": 3.3537, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 1.898989898989899, | |
| "eval_loss": 3.294283628463745, | |
| "eval_runtime": 5.1195, | |
| "eval_samples_per_second": 32.425, | |
| "eval_steps_per_second": 0.586, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 1.9393939393939394, | |
| "grad_norm": 1.833533763885498, | |
| "learning_rate": 1.7777777777777777e-05, | |
| "loss": 3.3034, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 1.9393939393939394, | |
| "eval_loss": 3.2412631511688232, | |
| "eval_runtime": 5.1404, | |
| "eval_samples_per_second": 32.293, | |
| "eval_steps_per_second": 0.584, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 1.9797979797979797, | |
| "grad_norm": 1.823169469833374, | |
| "learning_rate": 1.7685185185185187e-05, | |
| "loss": 3.2457, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 1.9797979797979797, | |
| "eval_loss": 3.1890854835510254, | |
| "eval_runtime": 5.1319, | |
| "eval_samples_per_second": 32.347, | |
| "eval_steps_per_second": 0.585, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 2.0202020202020203, | |
| "grad_norm": 1.796790361404419, | |
| "learning_rate": 1.7592592592592595e-05, | |
| "loss": 3.1915, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 2.0202020202020203, | |
| "eval_loss": 3.1396946907043457, | |
| "eval_runtime": 5.1262, | |
| "eval_samples_per_second": 32.383, | |
| "eval_steps_per_second": 0.585, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 2.0606060606060606, | |
| "grad_norm": 1.7133023738861084, | |
| "learning_rate": 1.7500000000000002e-05, | |
| "loss": 3.1475, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 2.0606060606060606, | |
| "eval_loss": 3.093197822570801, | |
| "eval_runtime": 5.141, | |
| "eval_samples_per_second": 32.29, | |
| "eval_steps_per_second": 0.584, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 2.101010101010101, | |
| "grad_norm": 1.637424111366272, | |
| "learning_rate": 1.740740740740741e-05, | |
| "loss": 3.0912, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 2.101010101010101, | |
| "eval_loss": 3.0486488342285156, | |
| "eval_runtime": 5.1578, | |
| "eval_samples_per_second": 32.185, | |
| "eval_steps_per_second": 0.582, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 2.1414141414141414, | |
| "grad_norm": 1.5733733177185059, | |
| "learning_rate": 1.7314814814814816e-05, | |
| "loss": 3.0493, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 2.1414141414141414, | |
| "eval_loss": 3.007200002670288, | |
| "eval_runtime": 5.1715, | |
| "eval_samples_per_second": 32.099, | |
| "eval_steps_per_second": 0.58, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 2.1818181818181817, | |
| "grad_norm": 1.579100251197815, | |
| "learning_rate": 1.7222222222222224e-05, | |
| "loss": 3.0007, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 2.1818181818181817, | |
| "eval_loss": 2.9646313190460205, | |
| "eval_runtime": 5.1737, | |
| "eval_samples_per_second": 32.085, | |
| "eval_steps_per_second": 0.58, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 2.2222222222222223, | |
| "grad_norm": 1.5558359622955322, | |
| "learning_rate": 1.712962962962963e-05, | |
| "loss": 2.955, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 2.2222222222222223, | |
| "eval_loss": 2.9225423336029053, | |
| "eval_runtime": 5.1649, | |
| "eval_samples_per_second": 32.14, | |
| "eval_steps_per_second": 0.581, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 2.2626262626262625, | |
| "grad_norm": 1.5695600509643555, | |
| "learning_rate": 1.7037037037037038e-05, | |
| "loss": 2.9242, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 2.2626262626262625, | |
| "eval_loss": 2.883842706680298, | |
| "eval_runtime": 5.1565, | |
| "eval_samples_per_second": 32.192, | |
| "eval_steps_per_second": 0.582, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 2.303030303030303, | |
| "grad_norm": 1.5856674909591675, | |
| "learning_rate": 1.6944444444444446e-05, | |
| "loss": 2.8626, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 2.303030303030303, | |
| "eval_loss": 2.8435447216033936, | |
| "eval_runtime": 5.1634, | |
| "eval_samples_per_second": 32.15, | |
| "eval_steps_per_second": 0.581, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 2.3434343434343434, | |
| "grad_norm": 1.5780515670776367, | |
| "learning_rate": 1.6851851851851853e-05, | |
| "loss": 2.8522, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 2.3434343434343434, | |
| "eval_loss": 2.8028392791748047, | |
| "eval_runtime": 5.1666, | |
| "eval_samples_per_second": 32.129, | |
| "eval_steps_per_second": 0.581, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 2.3838383838383836, | |
| "grad_norm": 1.5944206714630127, | |
| "learning_rate": 1.675925925925926e-05, | |
| "loss": 2.8222, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 2.3838383838383836, | |
| "eval_loss": 2.7607803344726562, | |
| "eval_runtime": 5.1662, | |
| "eval_samples_per_second": 32.132, | |
| "eval_steps_per_second": 0.581, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 2.4242424242424243, | |
| "grad_norm": 1.6033095121383667, | |
| "learning_rate": 1.6666666666666667e-05, | |
| "loss": 2.7291, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 2.4242424242424243, | |
| "eval_loss": 2.7191247940063477, | |
| "eval_runtime": 5.1631, | |
| "eval_samples_per_second": 32.151, | |
| "eval_steps_per_second": 0.581, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 2.4646464646464645, | |
| "grad_norm": 1.621768593788147, | |
| "learning_rate": 1.6574074074074075e-05, | |
| "loss": 2.7046, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 2.4646464646464645, | |
| "eval_loss": 2.6788933277130127, | |
| "eval_runtime": 5.1728, | |
| "eval_samples_per_second": 32.091, | |
| "eval_steps_per_second": 0.58, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 2.505050505050505, | |
| "grad_norm": 1.6213834285736084, | |
| "learning_rate": 1.6481481481481482e-05, | |
| "loss": 2.6548, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 2.505050505050505, | |
| "eval_loss": 2.6340527534484863, | |
| "eval_runtime": 5.1628, | |
| "eval_samples_per_second": 32.153, | |
| "eval_steps_per_second": 0.581, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 2.5454545454545454, | |
| "grad_norm": 1.607869267463684, | |
| "learning_rate": 1.638888888888889e-05, | |
| "loss": 2.6232, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 2.5454545454545454, | |
| "eval_loss": 2.594001531600952, | |
| "eval_runtime": 5.1624, | |
| "eval_samples_per_second": 32.155, | |
| "eval_steps_per_second": 0.581, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 2.5858585858585856, | |
| "grad_norm": 1.583896279335022, | |
| "learning_rate": 1.6296296296296297e-05, | |
| "loss": 2.6068, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 2.5858585858585856, | |
| "eval_loss": 2.5528736114501953, | |
| "eval_runtime": 5.1694, | |
| "eval_samples_per_second": 32.112, | |
| "eval_steps_per_second": 0.58, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 2.6262626262626263, | |
| "grad_norm": 1.5254372358322144, | |
| "learning_rate": 1.6203703703703707e-05, | |
| "loss": 2.5629, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 2.6262626262626263, | |
| "eval_loss": 2.5128839015960693, | |
| "eval_runtime": 5.1624, | |
| "eval_samples_per_second": 32.155, | |
| "eval_steps_per_second": 0.581, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 2.6666666666666665, | |
| "grad_norm": 1.4735966920852661, | |
| "learning_rate": 1.6111111111111115e-05, | |
| "loss": 2.523, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 2.6666666666666665, | |
| "eval_loss": 2.4759180545806885, | |
| "eval_runtime": 5.1612, | |
| "eval_samples_per_second": 32.163, | |
| "eval_steps_per_second": 0.581, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 2.707070707070707, | |
| "grad_norm": 1.4135326147079468, | |
| "learning_rate": 1.601851851851852e-05, | |
| "loss": 2.5069, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 2.707070707070707, | |
| "eval_loss": 2.4382143020629883, | |
| "eval_runtime": 5.1435, | |
| "eval_samples_per_second": 32.274, | |
| "eval_steps_per_second": 0.583, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 2.7474747474747474, | |
| "grad_norm": 1.3859189748764038, | |
| "learning_rate": 1.5925925925925926e-05, | |
| "loss": 2.449, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 2.7474747474747474, | |
| "eval_loss": 2.3999476432800293, | |
| "eval_runtime": 5.0261, | |
| "eval_samples_per_second": 33.028, | |
| "eval_steps_per_second": 0.597, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 2.787878787878788, | |
| "grad_norm": 1.3678818941116333, | |
| "learning_rate": 1.5833333333333333e-05, | |
| "loss": 2.3977, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 2.787878787878788, | |
| "eval_loss": 2.365516424179077, | |
| "eval_runtime": 4.9945, | |
| "eval_samples_per_second": 33.237, | |
| "eval_steps_per_second": 0.601, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 2.8282828282828283, | |
| "grad_norm": 1.372074842453003, | |
| "learning_rate": 1.5740740740740744e-05, | |
| "loss": 2.3556, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 2.8282828282828283, | |
| "eval_loss": 2.3320348262786865, | |
| "eval_runtime": 5.0457, | |
| "eval_samples_per_second": 32.899, | |
| "eval_steps_per_second": 0.595, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 2.8686868686868685, | |
| "grad_norm": 1.355190634727478, | |
| "learning_rate": 1.564814814814815e-05, | |
| "loss": 2.3269, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 2.8686868686868685, | |
| "eval_loss": 2.2980406284332275, | |
| "eval_runtime": 5.1448, | |
| "eval_samples_per_second": 32.265, | |
| "eval_steps_per_second": 0.583, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 2.909090909090909, | |
| "grad_norm": 1.34852135181427, | |
| "learning_rate": 1.555555555555556e-05, | |
| "loss": 2.2962, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 2.909090909090909, | |
| "eval_loss": 2.262707233428955, | |
| "eval_runtime": 5.1599, | |
| "eval_samples_per_second": 32.171, | |
| "eval_steps_per_second": 0.581, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 2.9494949494949494, | |
| "grad_norm": 1.3559976816177368, | |
| "learning_rate": 1.5462962962962966e-05, | |
| "loss": 2.2534, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 2.9494949494949494, | |
| "eval_loss": 2.2291126251220703, | |
| "eval_runtime": 5.0794, | |
| "eval_samples_per_second": 32.681, | |
| "eval_steps_per_second": 0.591, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 2.98989898989899, | |
| "grad_norm": 1.3566159009933472, | |
| "learning_rate": 1.537037037037037e-05, | |
| "loss": 2.2061, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 2.98989898989899, | |
| "eval_loss": 2.193363904953003, | |
| "eval_runtime": 5.0616, | |
| "eval_samples_per_second": 32.796, | |
| "eval_steps_per_second": 0.593, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 3.0303030303030303, | |
| "grad_norm": 1.3466676473617554, | |
| "learning_rate": 1.5277777777777777e-05, | |
| "loss": 2.1815, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 3.0303030303030303, | |
| "eval_loss": 2.159188985824585, | |
| "eval_runtime": 5.0978, | |
| "eval_samples_per_second": 32.563, | |
| "eval_steps_per_second": 0.588, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 3.0707070707070705, | |
| "grad_norm": 1.354913592338562, | |
| "learning_rate": 1.5185185185185187e-05, | |
| "loss": 2.1622, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 3.0707070707070705, | |
| "eval_loss": 2.124568462371826, | |
| "eval_runtime": 5.1439, | |
| "eval_samples_per_second": 32.271, | |
| "eval_steps_per_second": 0.583, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 3.111111111111111, | |
| "grad_norm": 1.360551357269287, | |
| "learning_rate": 1.5092592592592595e-05, | |
| "loss": 2.1079, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 3.111111111111111, | |
| "eval_loss": 2.092242956161499, | |
| "eval_runtime": 5.1333, | |
| "eval_samples_per_second": 32.338, | |
| "eval_steps_per_second": 0.584, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 3.1515151515151514, | |
| "grad_norm": 1.3474143743515015, | |
| "learning_rate": 1.5000000000000002e-05, | |
| "loss": 2.1036, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 3.1515151515151514, | |
| "eval_loss": 2.0584089756011963, | |
| "eval_runtime": 5.1757, | |
| "eval_samples_per_second": 32.073, | |
| "eval_steps_per_second": 0.58, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 3.191919191919192, | |
| "grad_norm": 1.368388295173645, | |
| "learning_rate": 1.4907407407407408e-05, | |
| "loss": 2.0527, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 3.191919191919192, | |
| "eval_loss": 2.0241854190826416, | |
| "eval_runtime": 5.1747, | |
| "eval_samples_per_second": 32.079, | |
| "eval_steps_per_second": 0.58, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 3.2323232323232323, | |
| "grad_norm": 1.3582555055618286, | |
| "learning_rate": 1.4814814814814815e-05, | |
| "loss": 1.9958, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 3.2323232323232323, | |
| "eval_loss": 1.990015983581543, | |
| "eval_runtime": 5.1542, | |
| "eval_samples_per_second": 32.207, | |
| "eval_steps_per_second": 0.582, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 3.2727272727272725, | |
| "grad_norm": 1.3820135593414307, | |
| "learning_rate": 1.4722222222222224e-05, | |
| "loss": 1.9878, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 3.2727272727272725, | |
| "eval_loss": 1.9560723304748535, | |
| "eval_runtime": 5.176, | |
| "eval_samples_per_second": 32.071, | |
| "eval_steps_per_second": 0.58, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 3.313131313131313, | |
| "grad_norm": 1.4004285335540771, | |
| "learning_rate": 1.4629629629629631e-05, | |
| "loss": 1.9533, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 3.313131313131313, | |
| "eval_loss": 1.9231067895889282, | |
| "eval_runtime": 5.1634, | |
| "eval_samples_per_second": 32.149, | |
| "eval_steps_per_second": 0.581, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 3.3535353535353534, | |
| "grad_norm": 1.4260685443878174, | |
| "learning_rate": 1.4537037037037039e-05, | |
| "loss": 1.9066, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 3.3535353535353534, | |
| "eval_loss": 1.8882259130477905, | |
| "eval_runtime": 5.1573, | |
| "eval_samples_per_second": 32.187, | |
| "eval_steps_per_second": 0.582, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 3.393939393939394, | |
| "grad_norm": 1.4351316690444946, | |
| "learning_rate": 1.4444444444444446e-05, | |
| "loss": 1.8803, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 3.393939393939394, | |
| "eval_loss": 1.8546966314315796, | |
| "eval_runtime": 5.1748, | |
| "eval_samples_per_second": 32.078, | |
| "eval_steps_per_second": 0.58, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 3.4343434343434343, | |
| "grad_norm": 1.4154078960418701, | |
| "learning_rate": 1.4351851851851853e-05, | |
| "loss": 1.8668, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 3.4343434343434343, | |
| "eval_loss": 1.820953369140625, | |
| "eval_runtime": 5.1325, | |
| "eval_samples_per_second": 32.343, | |
| "eval_steps_per_second": 0.585, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 3.474747474747475, | |
| "grad_norm": 1.4371109008789062, | |
| "learning_rate": 1.4259259259259259e-05, | |
| "loss": 1.822, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 3.474747474747475, | |
| "eval_loss": 1.7877326011657715, | |
| "eval_runtime": 5.1654, | |
| "eval_samples_per_second": 32.137, | |
| "eval_steps_per_second": 0.581, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 3.515151515151515, | |
| "grad_norm": 1.4090356826782227, | |
| "learning_rate": 1.416666666666667e-05, | |
| "loss": 1.7796, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 3.515151515151515, | |
| "eval_loss": 1.7542084455490112, | |
| "eval_runtime": 5.1712, | |
| "eval_samples_per_second": 32.101, | |
| "eval_steps_per_second": 0.58, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 3.5555555555555554, | |
| "grad_norm": 1.382804036140442, | |
| "learning_rate": 1.4074074074074075e-05, | |
| "loss": 1.7457, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 3.5555555555555554, | |
| "eval_loss": 1.7219429016113281, | |
| "eval_runtime": 5.165, | |
| "eval_samples_per_second": 32.139, | |
| "eval_steps_per_second": 0.581, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 3.595959595959596, | |
| "grad_norm": 1.4041632413864136, | |
| "learning_rate": 1.3981481481481482e-05, | |
| "loss": 1.7043, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 3.595959595959596, | |
| "eval_loss": 1.689993977546692, | |
| "eval_runtime": 5.1401, | |
| "eval_samples_per_second": 32.295, | |
| "eval_steps_per_second": 0.584, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 3.6363636363636362, | |
| "grad_norm": 1.3862537145614624, | |
| "learning_rate": 1.388888888888889e-05, | |
| "loss": 1.6742, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 3.6363636363636362, | |
| "eval_loss": 1.659338116645813, | |
| "eval_runtime": 5.1347, | |
| "eval_samples_per_second": 32.329, | |
| "eval_steps_per_second": 0.584, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 3.676767676767677, | |
| "grad_norm": 1.3727890253067017, | |
| "learning_rate": 1.3796296296296297e-05, | |
| "loss": 1.6502, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 3.676767676767677, | |
| "eval_loss": 1.628204345703125, | |
| "eval_runtime": 5.1623, | |
| "eval_samples_per_second": 32.156, | |
| "eval_steps_per_second": 0.581, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 3.717171717171717, | |
| "grad_norm": 1.400058388710022, | |
| "learning_rate": 1.3703703703703706e-05, | |
| "loss": 1.6396, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 3.717171717171717, | |
| "eval_loss": 1.5992398262023926, | |
| "eval_runtime": 5.1584, | |
| "eval_samples_per_second": 32.181, | |
| "eval_steps_per_second": 0.582, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 3.757575757575758, | |
| "grad_norm": 1.4236724376678467, | |
| "learning_rate": 1.3611111111111113e-05, | |
| "loss": 1.6123, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 3.757575757575758, | |
| "eval_loss": 1.5681532621383667, | |
| "eval_runtime": 5.157, | |
| "eval_samples_per_second": 32.189, | |
| "eval_steps_per_second": 0.582, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 3.797979797979798, | |
| "grad_norm": 1.4351081848144531, | |
| "learning_rate": 1.351851851851852e-05, | |
| "loss": 1.5512, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 3.797979797979798, | |
| "eval_loss": 1.5355143547058105, | |
| "eval_runtime": 5.1597, | |
| "eval_samples_per_second": 32.172, | |
| "eval_steps_per_second": 0.581, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 3.8383838383838382, | |
| "grad_norm": 1.4533002376556396, | |
| "learning_rate": 1.3425925925925926e-05, | |
| "loss": 1.5697, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 3.8383838383838382, | |
| "eval_loss": 1.506730318069458, | |
| "eval_runtime": 5.1659, | |
| "eval_samples_per_second": 32.134, | |
| "eval_steps_per_second": 0.581, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 3.878787878787879, | |
| "grad_norm": 1.4752202033996582, | |
| "learning_rate": 1.3333333333333333e-05, | |
| "loss": 1.495, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 3.878787878787879, | |
| "eval_loss": 1.4759498834609985, | |
| "eval_runtime": 5.1618, | |
| "eval_samples_per_second": 32.159, | |
| "eval_steps_per_second": 0.581, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 3.919191919191919, | |
| "grad_norm": 1.4492502212524414, | |
| "learning_rate": 1.3240740740740742e-05, | |
| "loss": 1.4681, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 3.919191919191919, | |
| "eval_loss": 1.4438410997390747, | |
| "eval_runtime": 5.1618, | |
| "eval_samples_per_second": 32.159, | |
| "eval_steps_per_second": 0.581, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 3.9595959595959593, | |
| "grad_norm": 1.4566094875335693, | |
| "learning_rate": 1.314814814814815e-05, | |
| "loss": 1.4542, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 3.9595959595959593, | |
| "eval_loss": 1.4141173362731934, | |
| "eval_runtime": 5.1691, | |
| "eval_samples_per_second": 32.114, | |
| "eval_steps_per_second": 0.58, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "grad_norm": 1.47097647190094, | |
| "learning_rate": 1.3055555555555557e-05, | |
| "loss": 1.4428, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_loss": 1.381595492362976, | |
| "eval_runtime": 5.1554, | |
| "eval_samples_per_second": 32.199, | |
| "eval_steps_per_second": 0.582, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 4.040404040404041, | |
| "grad_norm": 1.4813333749771118, | |
| "learning_rate": 1.2962962962962964e-05, | |
| "loss": 1.403, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 4.040404040404041, | |
| "eval_loss": 1.3522053956985474, | |
| "eval_runtime": 5.1659, | |
| "eval_samples_per_second": 32.134, | |
| "eval_steps_per_second": 0.581, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 4.08080808080808, | |
| "grad_norm": 1.500218391418457, | |
| "learning_rate": 1.2870370370370371e-05, | |
| "loss": 1.3289, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 4.08080808080808, | |
| "eval_loss": 1.3220492601394653, | |
| "eval_runtime": 5.1719, | |
| "eval_samples_per_second": 32.096, | |
| "eval_steps_per_second": 0.58, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 4.121212121212121, | |
| "grad_norm": 1.4614801406860352, | |
| "learning_rate": 1.2777777777777777e-05, | |
| "loss": 1.3151, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 4.121212121212121, | |
| "eval_loss": 1.2928389310836792, | |
| "eval_runtime": 5.1718, | |
| "eval_samples_per_second": 32.097, | |
| "eval_steps_per_second": 0.58, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 4.161616161616162, | |
| "grad_norm": 1.4137208461761475, | |
| "learning_rate": 1.2685185185185188e-05, | |
| "loss": 1.2993, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 4.161616161616162, | |
| "eval_loss": 1.2663666009902954, | |
| "eval_runtime": 5.1665, | |
| "eval_samples_per_second": 32.13, | |
| "eval_steps_per_second": 0.581, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 4.202020202020202, | |
| "grad_norm": 1.347014307975769, | |
| "learning_rate": 1.2592592592592593e-05, | |
| "loss": 1.2506, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 4.202020202020202, | |
| "eval_loss": 1.242059588432312, | |
| "eval_runtime": 5.1713, | |
| "eval_samples_per_second": 32.101, | |
| "eval_steps_per_second": 0.58, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 4.242424242424242, | |
| "grad_norm": 1.3283647298812866, | |
| "learning_rate": 1.25e-05, | |
| "loss": 1.2453, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 4.242424242424242, | |
| "eval_loss": 1.2196069955825806, | |
| "eval_runtime": 5.1174, | |
| "eval_samples_per_second": 32.438, | |
| "eval_steps_per_second": 0.586, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 4.282828282828283, | |
| "grad_norm": 1.2796555757522583, | |
| "learning_rate": 1.2407407407407408e-05, | |
| "loss": 1.1805, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 4.282828282828283, | |
| "eval_loss": 1.1993300914764404, | |
| "eval_runtime": 5.125, | |
| "eval_samples_per_second": 32.39, | |
| "eval_steps_per_second": 0.585, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 4.3232323232323235, | |
| "grad_norm": 1.264662742614746, | |
| "learning_rate": 1.2314814814814815e-05, | |
| "loss": 1.1939, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 4.3232323232323235, | |
| "eval_loss": 1.1796401739120483, | |
| "eval_runtime": 5.154, | |
| "eval_samples_per_second": 32.208, | |
| "eval_steps_per_second": 0.582, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 4.363636363636363, | |
| "grad_norm": 1.2420271635055542, | |
| "learning_rate": 1.2222222222222224e-05, | |
| "loss": 1.1684, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 4.363636363636363, | |
| "eval_loss": 1.161789894104004, | |
| "eval_runtime": 5.1599, | |
| "eval_samples_per_second": 32.171, | |
| "eval_steps_per_second": 0.581, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 4.404040404040404, | |
| "grad_norm": 1.2369439601898193, | |
| "learning_rate": 1.2129629629629631e-05, | |
| "loss": 1.1893, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 4.404040404040404, | |
| "eval_loss": 1.1432855129241943, | |
| "eval_runtime": 5.1704, | |
| "eval_samples_per_second": 32.106, | |
| "eval_steps_per_second": 0.58, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 4.444444444444445, | |
| "grad_norm": 1.1795873641967773, | |
| "learning_rate": 1.2037037037037039e-05, | |
| "loss": 1.1554, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 4.444444444444445, | |
| "eval_loss": 1.126727819442749, | |
| "eval_runtime": 5.1629, | |
| "eval_samples_per_second": 32.153, | |
| "eval_steps_per_second": 0.581, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 4.484848484848484, | |
| "grad_norm": 1.1451513767242432, | |
| "learning_rate": 1.1944444444444444e-05, | |
| "loss": 1.1276, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 4.484848484848484, | |
| "eval_loss": 1.1112148761749268, | |
| "eval_runtime": 5.1514, | |
| "eval_samples_per_second": 32.224, | |
| "eval_steps_per_second": 0.582, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 4.525252525252525, | |
| "grad_norm": 1.124099612236023, | |
| "learning_rate": 1.1851851851851852e-05, | |
| "loss": 1.0972, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 4.525252525252525, | |
| "eval_loss": 1.0960901975631714, | |
| "eval_runtime": 5.092, | |
| "eval_samples_per_second": 32.6, | |
| "eval_steps_per_second": 0.589, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 4.565656565656566, | |
| "grad_norm": 1.090491533279419, | |
| "learning_rate": 1.1759259259259259e-05, | |
| "loss": 1.0821, | |
| "step": 113 | |
| }, | |
| { | |
| "epoch": 4.565656565656566, | |
| "eval_loss": 1.0813062191009521, | |
| "eval_runtime": 5.0997, | |
| "eval_samples_per_second": 32.551, | |
| "eval_steps_per_second": 0.588, | |
| "step": 113 | |
| }, | |
| { | |
| "epoch": 4.606060606060606, | |
| "grad_norm": 1.0799589157104492, | |
| "learning_rate": 1.1666666666666668e-05, | |
| "loss": 1.038, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 4.606060606060606, | |
| "eval_loss": 1.0665714740753174, | |
| "eval_runtime": 5.1435, | |
| "eval_samples_per_second": 32.273, | |
| "eval_steps_per_second": 0.583, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 4.646464646464646, | |
| "grad_norm": 1.0503891706466675, | |
| "learning_rate": 1.1574074074074075e-05, | |
| "loss": 1.0584, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 4.646464646464646, | |
| "eval_loss": 1.0545704364776611, | |
| "eval_runtime": 5.1517, | |
| "eval_samples_per_second": 32.222, | |
| "eval_steps_per_second": 0.582, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 4.686868686868687, | |
| "grad_norm": 1.043385624885559, | |
| "learning_rate": 1.1481481481481482e-05, | |
| "loss": 1.0329, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 4.686868686868687, | |
| "eval_loss": 1.0427477359771729, | |
| "eval_runtime": 5.1504, | |
| "eval_samples_per_second": 32.23, | |
| "eval_steps_per_second": 0.582, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 4.7272727272727275, | |
| "grad_norm": 1.0548285245895386, | |
| "learning_rate": 1.138888888888889e-05, | |
| "loss": 1.0256, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 4.7272727272727275, | |
| "eval_loss": 1.0287798643112183, | |
| "eval_runtime": 5.1603, | |
| "eval_samples_per_second": 32.168, | |
| "eval_steps_per_second": 0.581, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 4.767676767676767, | |
| "grad_norm": 1.0389068126678467, | |
| "learning_rate": 1.1296296296296297e-05, | |
| "loss": 1.0192, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 4.767676767676767, | |
| "eval_loss": 1.0174580812454224, | |
| "eval_runtime": 5.1433, | |
| "eval_samples_per_second": 32.275, | |
| "eval_steps_per_second": 0.583, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 4.808080808080808, | |
| "grad_norm": 1.035844087600708, | |
| "learning_rate": 1.1203703703703706e-05, | |
| "loss": 1.0101, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 4.808080808080808, | |
| "eval_loss": 1.006226658821106, | |
| "eval_runtime": 5.1693, | |
| "eval_samples_per_second": 32.113, | |
| "eval_steps_per_second": 0.58, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 4.848484848484849, | |
| "grad_norm": 1.050945520401001, | |
| "learning_rate": 1.1111111111111113e-05, | |
| "loss": 1.0403, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 4.848484848484849, | |
| "eval_loss": 0.9945307374000549, | |
| "eval_runtime": 5.1581, | |
| "eval_samples_per_second": 32.182, | |
| "eval_steps_per_second": 0.582, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 4.888888888888889, | |
| "grad_norm": 1.027295708656311, | |
| "learning_rate": 1.1018518518518519e-05, | |
| "loss": 1.0038, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 4.888888888888889, | |
| "eval_loss": 0.9830649495124817, | |
| "eval_runtime": 5.1555, | |
| "eval_samples_per_second": 32.199, | |
| "eval_steps_per_second": 0.582, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 4.929292929292929, | |
| "grad_norm": 1.035843014717102, | |
| "learning_rate": 1.0925925925925926e-05, | |
| "loss": 0.9544, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 4.929292929292929, | |
| "eval_loss": 0.9728271961212158, | |
| "eval_runtime": 5.1521, | |
| "eval_samples_per_second": 32.22, | |
| "eval_steps_per_second": 0.582, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 4.96969696969697, | |
| "grad_norm": 1.050779938697815, | |
| "learning_rate": 1.0833333333333334e-05, | |
| "loss": 0.9393, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 4.96969696969697, | |
| "eval_loss": 0.9609534740447998, | |
| "eval_runtime": 5.1551, | |
| "eval_samples_per_second": 32.201, | |
| "eval_steps_per_second": 0.582, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 5.01010101010101, | |
| "grad_norm": 1.0694254636764526, | |
| "learning_rate": 1.0740740740740742e-05, | |
| "loss": 0.9578, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 5.01010101010101, | |
| "eval_loss": 0.9495998620986938, | |
| "eval_runtime": 5.1502, | |
| "eval_samples_per_second": 32.232, | |
| "eval_steps_per_second": 0.583, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 5.05050505050505, | |
| "grad_norm": 1.0505897998809814, | |
| "learning_rate": 1.064814814814815e-05, | |
| "loss": 0.9228, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 5.05050505050505, | |
| "eval_loss": 0.9396913051605225, | |
| "eval_runtime": 5.1544, | |
| "eval_samples_per_second": 32.205, | |
| "eval_steps_per_second": 0.582, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 5.090909090909091, | |
| "grad_norm": 1.082509160041809, | |
| "learning_rate": 1.0555555555555557e-05, | |
| "loss": 0.9583, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 5.090909090909091, | |
| "eval_loss": 0.9291126132011414, | |
| "eval_runtime": 5.1661, | |
| "eval_samples_per_second": 32.132, | |
| "eval_steps_per_second": 0.581, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 5.1313131313131315, | |
| "grad_norm": 1.0709625482559204, | |
| "learning_rate": 1.0462962962962964e-05, | |
| "loss": 0.9163, | |
| "step": 127 | |
| }, | |
| { | |
| "epoch": 5.1313131313131315, | |
| "eval_loss": 0.9183955192565918, | |
| "eval_runtime": 5.159, | |
| "eval_samples_per_second": 32.177, | |
| "eval_steps_per_second": 0.582, | |
| "step": 127 | |
| }, | |
| { | |
| "epoch": 5.171717171717171, | |
| "grad_norm": 1.042419195175171, | |
| "learning_rate": 1.037037037037037e-05, | |
| "loss": 0.923, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 5.171717171717171, | |
| "eval_loss": 0.9072820544242859, | |
| "eval_runtime": 5.1597, | |
| "eval_samples_per_second": 32.172, | |
| "eval_steps_per_second": 0.581, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 5.212121212121212, | |
| "grad_norm": 1.0583133697509766, | |
| "learning_rate": 1.0277777777777777e-05, | |
| "loss": 0.9328, | |
| "step": 129 | |
| }, | |
| { | |
| "epoch": 5.212121212121212, | |
| "eval_loss": 0.897919237613678, | |
| "eval_runtime": 5.15, | |
| "eval_samples_per_second": 32.233, | |
| "eval_steps_per_second": 0.583, | |
| "step": 129 | |
| }, | |
| { | |
| "epoch": 5.252525252525253, | |
| "grad_norm": 1.0396648645401, | |
| "learning_rate": 1.0185185185185186e-05, | |
| "loss": 0.9001, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 5.252525252525253, | |
| "eval_loss": 0.8888950347900391, | |
| "eval_runtime": 5.1631, | |
| "eval_samples_per_second": 32.151, | |
| "eval_steps_per_second": 0.581, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 5.292929292929293, | |
| "grad_norm": 1.0212734937667847, | |
| "learning_rate": 1.0092592592592594e-05, | |
| "loss": 0.8731, | |
| "step": 131 | |
| }, | |
| { | |
| "epoch": 5.292929292929293, | |
| "eval_loss": 0.8788275718688965, | |
| "eval_runtime": 5.1742, | |
| "eval_samples_per_second": 32.082, | |
| "eval_steps_per_second": 0.58, | |
| "step": 131 | |
| }, | |
| { | |
| "epoch": 5.333333333333333, | |
| "grad_norm": 1.0188337564468384, | |
| "learning_rate": 1e-05, | |
| "loss": 0.8328, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 5.333333333333333, | |
| "eval_loss": 0.8719209432601929, | |
| "eval_runtime": 5.1515, | |
| "eval_samples_per_second": 32.224, | |
| "eval_steps_per_second": 0.582, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 5.373737373737374, | |
| "grad_norm": 1.010650873184204, | |
| "learning_rate": 9.907407407407408e-06, | |
| "loss": 0.8401, | |
| "step": 133 | |
| }, | |
| { | |
| "epoch": 5.373737373737374, | |
| "eval_loss": 0.8616573810577393, | |
| "eval_runtime": 5.1695, | |
| "eval_samples_per_second": 32.111, | |
| "eval_steps_per_second": 0.58, | |
| "step": 133 | |
| }, | |
| { | |
| "epoch": 5.414141414141414, | |
| "grad_norm": 0.9998605847358704, | |
| "learning_rate": 9.814814814814815e-06, | |
| "loss": 0.8664, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 5.414141414141414, | |
| "eval_loss": 0.8543541431427002, | |
| "eval_runtime": 5.1642, | |
| "eval_samples_per_second": 32.144, | |
| "eval_steps_per_second": 0.581, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 5.454545454545454, | |
| "grad_norm": 0.9973117113113403, | |
| "learning_rate": 9.722222222222223e-06, | |
| "loss": 0.8414, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 5.454545454545454, | |
| "eval_loss": 0.8471528887748718, | |
| "eval_runtime": 5.1595, | |
| "eval_samples_per_second": 32.173, | |
| "eval_steps_per_second": 0.581, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 5.494949494949495, | |
| "grad_norm": 1.0174371004104614, | |
| "learning_rate": 9.62962962962963e-06, | |
| "loss": 0.863, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 5.494949494949495, | |
| "eval_loss": 0.839015543460846, | |
| "eval_runtime": 5.1632, | |
| "eval_samples_per_second": 32.15, | |
| "eval_steps_per_second": 0.581, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 5.5353535353535355, | |
| "grad_norm": 1.0131112337112427, | |
| "learning_rate": 9.537037037037037e-06, | |
| "loss": 0.8296, | |
| "step": 137 | |
| }, | |
| { | |
| "epoch": 5.5353535353535355, | |
| "eval_loss": 0.831695556640625, | |
| "eval_runtime": 5.1598, | |
| "eval_samples_per_second": 32.172, | |
| "eval_steps_per_second": 0.581, | |
| "step": 137 | |
| }, | |
| { | |
| "epoch": 5.575757575757576, | |
| "grad_norm": 1.0262633562088013, | |
| "learning_rate": 9.444444444444445e-06, | |
| "loss": 0.854, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 5.575757575757576, | |
| "eval_loss": 0.8235994577407837, | |
| "eval_runtime": 5.1621, | |
| "eval_samples_per_second": 32.158, | |
| "eval_steps_per_second": 0.581, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 5.616161616161616, | |
| "grad_norm": 1.0295422077178955, | |
| "learning_rate": 9.351851851851854e-06, | |
| "loss": 0.8194, | |
| "step": 139 | |
| }, | |
| { | |
| "epoch": 5.616161616161616, | |
| "eval_loss": 0.8169118762016296, | |
| "eval_runtime": 5.168, | |
| "eval_samples_per_second": 32.121, | |
| "eval_steps_per_second": 0.58, | |
| "step": 139 | |
| }, | |
| { | |
| "epoch": 5.656565656565657, | |
| "grad_norm": 1.0281344652175903, | |
| "learning_rate": 9.25925925925926e-06, | |
| "loss": 0.7902, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 5.656565656565657, | |
| "eval_loss": 0.8098058104515076, | |
| "eval_runtime": 5.1581, | |
| "eval_samples_per_second": 32.183, | |
| "eval_steps_per_second": 0.582, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 5.696969696969697, | |
| "grad_norm": 1.0528678894042969, | |
| "learning_rate": 9.166666666666666e-06, | |
| "loss": 0.7939, | |
| "step": 141 | |
| }, | |
| { | |
| "epoch": 5.696969696969697, | |
| "eval_loss": 0.8031502366065979, | |
| "eval_runtime": 5.1541, | |
| "eval_samples_per_second": 32.207, | |
| "eval_steps_per_second": 0.582, | |
| "step": 141 | |
| }, | |
| { | |
| "epoch": 5.737373737373737, | |
| "grad_norm": 1.0525215864181519, | |
| "learning_rate": 9.074074074074075e-06, | |
| "loss": 0.8127, | |
| "step": 142 | |
| }, | |
| { | |
| "epoch": 5.737373737373737, | |
| "eval_loss": 0.7957438230514526, | |
| "eval_runtime": 5.1544, | |
| "eval_samples_per_second": 32.205, | |
| "eval_steps_per_second": 0.582, | |
| "step": 142 | |
| }, | |
| { | |
| "epoch": 5.777777777777778, | |
| "grad_norm": 1.0634738206863403, | |
| "learning_rate": 8.981481481481483e-06, | |
| "loss": 0.7831, | |
| "step": 143 | |
| }, | |
| { | |
| "epoch": 5.777777777777778, | |
| "eval_loss": 0.7881508469581604, | |
| "eval_runtime": 5.1489, | |
| "eval_samples_per_second": 32.24, | |
| "eval_steps_per_second": 0.583, | |
| "step": 143 | |
| }, | |
| { | |
| "epoch": 5.818181818181818, | |
| "grad_norm": 1.0633102655410767, | |
| "learning_rate": 8.888888888888888e-06, | |
| "loss": 0.7511, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 5.818181818181818, | |
| "eval_loss": 0.7818319201469421, | |
| "eval_runtime": 5.169, | |
| "eval_samples_per_second": 32.115, | |
| "eval_steps_per_second": 0.58, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 5.858585858585858, | |
| "grad_norm": 1.053615689277649, | |
| "learning_rate": 8.796296296296297e-06, | |
| "loss": 0.75, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 5.858585858585858, | |
| "eval_loss": 0.7745649814605713, | |
| "eval_runtime": 5.1694, | |
| "eval_samples_per_second": 32.112, | |
| "eval_steps_per_second": 0.58, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 5.898989898989899, | |
| "grad_norm": 1.0772610902786255, | |
| "learning_rate": 8.703703703703705e-06, | |
| "loss": 0.7929, | |
| "step": 146 | |
| }, | |
| { | |
| "epoch": 5.898989898989899, | |
| "eval_loss": 0.7681305408477783, | |
| "eval_runtime": 5.1618, | |
| "eval_samples_per_second": 32.16, | |
| "eval_steps_per_second": 0.581, | |
| "step": 146 | |
| }, | |
| { | |
| "epoch": 5.9393939393939394, | |
| "grad_norm": 1.0765084028244019, | |
| "learning_rate": 8.611111111111112e-06, | |
| "loss": 0.7642, | |
| "step": 147 | |
| }, | |
| { | |
| "epoch": 5.9393939393939394, | |
| "eval_loss": 0.7618209719657898, | |
| "eval_runtime": 5.1689, | |
| "eval_samples_per_second": 32.115, | |
| "eval_steps_per_second": 0.58, | |
| "step": 147 | |
| }, | |
| { | |
| "epoch": 5.97979797979798, | |
| "grad_norm": 1.0824408531188965, | |
| "learning_rate": 8.518518518518519e-06, | |
| "loss": 0.7387, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 5.97979797979798, | |
| "eval_loss": 0.755460798740387, | |
| "eval_runtime": 5.1544, | |
| "eval_samples_per_second": 32.206, | |
| "eval_steps_per_second": 0.582, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 6.02020202020202, | |
| "grad_norm": 1.0975412130355835, | |
| "learning_rate": 8.425925925925926e-06, | |
| "loss": 0.7218, | |
| "step": 149 | |
| }, | |
| { | |
| "epoch": 6.02020202020202, | |
| "eval_loss": 0.749002993106842, | |
| "eval_runtime": 5.1624, | |
| "eval_samples_per_second": 32.156, | |
| "eval_steps_per_second": 0.581, | |
| "step": 149 | |
| }, | |
| { | |
| "epoch": 6.0606060606060606, | |
| "grad_norm": 1.1096184253692627, | |
| "learning_rate": 8.333333333333334e-06, | |
| "loss": 0.712, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 6.0606060606060606, | |
| "eval_loss": 0.7422470450401306, | |
| "eval_runtime": 5.1674, | |
| "eval_samples_per_second": 32.124, | |
| "eval_steps_per_second": 0.581, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 6.101010101010101, | |
| "grad_norm": 1.1530879735946655, | |
| "learning_rate": 8.240740740740741e-06, | |
| "loss": 0.7268, | |
| "step": 151 | |
| }, | |
| { | |
| "epoch": 6.101010101010101, | |
| "eval_loss": 0.7364265322685242, | |
| "eval_runtime": 5.1645, | |
| "eval_samples_per_second": 32.142, | |
| "eval_steps_per_second": 0.581, | |
| "step": 151 | |
| }, | |
| { | |
| "epoch": 6.141414141414141, | |
| "grad_norm": 1.1592988967895508, | |
| "learning_rate": 8.148148148148148e-06, | |
| "loss": 0.7258, | |
| "step": 152 | |
| }, | |
| { | |
| "epoch": 6.141414141414141, | |
| "eval_loss": 0.7302441596984863, | |
| "eval_runtime": 5.1636, | |
| "eval_samples_per_second": 32.148, | |
| "eval_steps_per_second": 0.581, | |
| "step": 152 | |
| }, | |
| { | |
| "epoch": 6.181818181818182, | |
| "grad_norm": 1.1833539009094238, | |
| "learning_rate": 8.055555555555557e-06, | |
| "loss": 0.7224, | |
| "step": 153 | |
| }, | |
| { | |
| "epoch": 6.181818181818182, | |
| "eval_loss": 0.7228173017501831, | |
| "eval_runtime": 5.1641, | |
| "eval_samples_per_second": 32.145, | |
| "eval_steps_per_second": 0.581, | |
| "step": 153 | |
| }, | |
| { | |
| "epoch": 6.222222222222222, | |
| "grad_norm": 1.1936936378479004, | |
| "learning_rate": 7.962962962962963e-06, | |
| "loss": 0.6966, | |
| "step": 154 | |
| }, | |
| { | |
| "epoch": 6.222222222222222, | |
| "eval_loss": 0.716472327709198, | |
| "eval_runtime": 5.1605, | |
| "eval_samples_per_second": 32.167, | |
| "eval_steps_per_second": 0.581, | |
| "step": 154 | |
| }, | |
| { | |
| "epoch": 6.262626262626263, | |
| "grad_norm": 1.245132565498352, | |
| "learning_rate": 7.870370370370372e-06, | |
| "loss": 0.7028, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 6.262626262626263, | |
| "eval_loss": 0.7087136507034302, | |
| "eval_runtime": 5.1583, | |
| "eval_samples_per_second": 32.181, | |
| "eval_steps_per_second": 0.582, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 6.303030303030303, | |
| "grad_norm": 1.2659085988998413, | |
| "learning_rate": 7.77777777777778e-06, | |
| "loss": 0.7051, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 6.303030303030303, | |
| "eval_loss": 0.7009304165840149, | |
| "eval_runtime": 5.1665, | |
| "eval_samples_per_second": 32.13, | |
| "eval_steps_per_second": 0.581, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 6.343434343434343, | |
| "grad_norm": 1.3588238954544067, | |
| "learning_rate": 7.685185185185185e-06, | |
| "loss": 0.7004, | |
| "step": 157 | |
| }, | |
| { | |
| "epoch": 6.343434343434343, | |
| "eval_loss": 0.6932580471038818, | |
| "eval_runtime": 5.1604, | |
| "eval_samples_per_second": 32.168, | |
| "eval_steps_per_second": 0.581, | |
| "step": 157 | |
| }, | |
| { | |
| "epoch": 6.383838383838384, | |
| "grad_norm": 1.3982634544372559, | |
| "learning_rate": 7.592592592592594e-06, | |
| "loss": 0.68, | |
| "step": 158 | |
| }, | |
| { | |
| "epoch": 6.383838383838384, | |
| "eval_loss": 0.6845574378967285, | |
| "eval_runtime": 5.1575, | |
| "eval_samples_per_second": 32.186, | |
| "eval_steps_per_second": 0.582, | |
| "step": 158 | |
| }, | |
| { | |
| "epoch": 6.424242424242424, | |
| "grad_norm": 1.426499605178833, | |
| "learning_rate": 7.500000000000001e-06, | |
| "loss": 0.6641, | |
| "step": 159 | |
| }, | |
| { | |
| "epoch": 6.424242424242424, | |
| "eval_loss": 0.6760482788085938, | |
| "eval_runtime": 5.1632, | |
| "eval_samples_per_second": 32.151, | |
| "eval_steps_per_second": 0.581, | |
| "step": 159 | |
| }, | |
| { | |
| "epoch": 6.4646464646464645, | |
| "grad_norm": 1.4880263805389404, | |
| "learning_rate": 7.4074074074074075e-06, | |
| "loss": 0.695, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 6.4646464646464645, | |
| "eval_loss": 0.6670196652412415, | |
| "eval_runtime": 5.1633, | |
| "eval_samples_per_second": 32.15, | |
| "eval_steps_per_second": 0.581, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 6.505050505050505, | |
| "grad_norm": 1.524919033050537, | |
| "learning_rate": 7.314814814814816e-06, | |
| "loss": 0.6316, | |
| "step": 161 | |
| }, | |
| { | |
| "epoch": 6.505050505050505, | |
| "eval_loss": 0.6562865972518921, | |
| "eval_runtime": 5.1726, | |
| "eval_samples_per_second": 32.092, | |
| "eval_steps_per_second": 0.58, | |
| "step": 161 | |
| }, | |
| { | |
| "epoch": 6.545454545454545, | |
| "grad_norm": 1.542138934135437, | |
| "learning_rate": 7.222222222222223e-06, | |
| "loss": 0.6491, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 6.545454545454545, | |
| "eval_loss": 0.6472378969192505, | |
| "eval_runtime": 5.1671, | |
| "eval_samples_per_second": 32.126, | |
| "eval_steps_per_second": 0.581, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 6.585858585858586, | |
| "grad_norm": 1.5400753021240234, | |
| "learning_rate": 7.129629629629629e-06, | |
| "loss": 0.6324, | |
| "step": 163 | |
| }, | |
| { | |
| "epoch": 6.585858585858586, | |
| "eval_loss": 0.6379138231277466, | |
| "eval_runtime": 5.1556, | |
| "eval_samples_per_second": 32.198, | |
| "eval_steps_per_second": 0.582, | |
| "step": 163 | |
| }, | |
| { | |
| "epoch": 6.626262626262626, | |
| "grad_norm": 1.4753589630126953, | |
| "learning_rate": 7.0370370370370375e-06, | |
| "loss": 0.6473, | |
| "step": 164 | |
| }, | |
| { | |
| "epoch": 6.626262626262626, | |
| "eval_loss": 0.6301048994064331, | |
| "eval_runtime": 5.1423, | |
| "eval_samples_per_second": 32.281, | |
| "eval_steps_per_second": 0.583, | |
| "step": 164 | |
| }, | |
| { | |
| "epoch": 6.666666666666667, | |
| "grad_norm": 1.370703935623169, | |
| "learning_rate": 6.944444444444445e-06, | |
| "loss": 0.6255, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 6.666666666666667, | |
| "eval_loss": 0.6244276762008667, | |
| "eval_runtime": 5.1569, | |
| "eval_samples_per_second": 32.19, | |
| "eval_steps_per_second": 0.582, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 6.707070707070707, | |
| "grad_norm": 1.2907015085220337, | |
| "learning_rate": 6.851851851851853e-06, | |
| "loss": 0.6029, | |
| "step": 166 | |
| }, | |
| { | |
| "epoch": 6.707070707070707, | |
| "eval_loss": 0.6191242933273315, | |
| "eval_runtime": 5.1685, | |
| "eval_samples_per_second": 32.118, | |
| "eval_steps_per_second": 0.58, | |
| "step": 166 | |
| }, | |
| { | |
| "epoch": 6.747474747474747, | |
| "grad_norm": 1.206007480621338, | |
| "learning_rate": 6.75925925925926e-06, | |
| "loss": 0.5831, | |
| "step": 167 | |
| }, | |
| { | |
| "epoch": 6.747474747474747, | |
| "eval_loss": 0.6155738830566406, | |
| "eval_runtime": 5.1689, | |
| "eval_samples_per_second": 32.115, | |
| "eval_steps_per_second": 0.58, | |
| "step": 167 | |
| }, | |
| { | |
| "epoch": 6.787878787878788, | |
| "grad_norm": 1.14729642868042, | |
| "learning_rate": 6.666666666666667e-06, | |
| "loss": 0.6167, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 6.787878787878788, | |
| "eval_loss": 0.6123696565628052, | |
| "eval_runtime": 5.1612, | |
| "eval_samples_per_second": 32.163, | |
| "eval_steps_per_second": 0.581, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 6.828282828282829, | |
| "grad_norm": 1.1298456192016602, | |
| "learning_rate": 6.574074074074075e-06, | |
| "loss": 0.597, | |
| "step": 169 | |
| }, | |
| { | |
| "epoch": 6.828282828282829, | |
| "eval_loss": 0.6096829771995544, | |
| "eval_runtime": 5.1532, | |
| "eval_samples_per_second": 32.213, | |
| "eval_steps_per_second": 0.582, | |
| "step": 169 | |
| }, | |
| { | |
| "epoch": 6.8686868686868685, | |
| "grad_norm": 1.129176378250122, | |
| "learning_rate": 6.481481481481482e-06, | |
| "loss": 0.6278, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 6.8686868686868685, | |
| "eval_loss": 0.6058310270309448, | |
| "eval_runtime": 5.1654, | |
| "eval_samples_per_second": 32.137, | |
| "eval_steps_per_second": 0.581, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 6.909090909090909, | |
| "grad_norm": 1.1008386611938477, | |
| "learning_rate": 6.3888888888888885e-06, | |
| "loss": 0.5974, | |
| "step": 171 | |
| }, | |
| { | |
| "epoch": 6.909090909090909, | |
| "eval_loss": 0.6041752696037292, | |
| "eval_runtime": 5.1564, | |
| "eval_samples_per_second": 32.193, | |
| "eval_steps_per_second": 0.582, | |
| "step": 171 | |
| }, | |
| { | |
| "epoch": 6.94949494949495, | |
| "grad_norm": 1.0789906978607178, | |
| "learning_rate": 6.296296296296297e-06, | |
| "loss": 0.5983, | |
| "step": 172 | |
| }, | |
| { | |
| "epoch": 6.94949494949495, | |
| "eval_loss": 0.6021236181259155, | |
| "eval_runtime": 5.1613, | |
| "eval_samples_per_second": 32.163, | |
| "eval_steps_per_second": 0.581, | |
| "step": 172 | |
| }, | |
| { | |
| "epoch": 6.98989898989899, | |
| "grad_norm": 1.1015055179595947, | |
| "learning_rate": 6.203703703703704e-06, | |
| "loss": 0.6138, | |
| "step": 173 | |
| }, | |
| { | |
| "epoch": 6.98989898989899, | |
| "eval_loss": 0.6002500653266907, | |
| "eval_runtime": 5.1625, | |
| "eval_samples_per_second": 32.155, | |
| "eval_steps_per_second": 0.581, | |
| "step": 173 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 240, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 10, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 4.466076308815872e+16, | |
| "train_batch_size": 32, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |