| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 76.61883408071749, | |
| "eval_steps": 500, | |
| "global_step": 10626, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 2.561117578579744e-06, | |
| "loss": 1.3932, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 5.122235157159488e-06, | |
| "loss": 1.3231, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 7.683352735739232e-06, | |
| "loss": 1.3235, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "learning_rate": 1.0244470314318976e-05, | |
| "loss": 1.2242, | |
| "step": 176 | |
| }, | |
| { | |
| "epoch": 1.37, | |
| "learning_rate": 1.2805587892898722e-05, | |
| "loss": 1.1413, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 1.57, | |
| "learning_rate": 1.5366705471478464e-05, | |
| "loss": 1.0589, | |
| "step": 264 | |
| }, | |
| { | |
| "epoch": 2.14, | |
| "learning_rate": 1.7927823050058208e-05, | |
| "loss": 0.8778, | |
| "step": 308 | |
| }, | |
| { | |
| "epoch": 2.34, | |
| "learning_rate": 2.0488940628637952e-05, | |
| "loss": 0.9339, | |
| "step": 352 | |
| }, | |
| { | |
| "epoch": 2.54, | |
| "learning_rate": 2.3050058207217696e-05, | |
| "loss": 0.8231, | |
| "step": 396 | |
| }, | |
| { | |
| "epoch": 3.12, | |
| "learning_rate": 2.5611175785797444e-05, | |
| "loss": 0.7623, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 3.31, | |
| "learning_rate": 2.8172293364377184e-05, | |
| "loss": 0.7676, | |
| "step": 484 | |
| }, | |
| { | |
| "epoch": 3.51, | |
| "learning_rate": 3.073341094295693e-05, | |
| "loss": 0.7446, | |
| "step": 528 | |
| }, | |
| { | |
| "epoch": 4.09, | |
| "learning_rate": 3.329452852153667e-05, | |
| "loss": 0.7007, | |
| "step": 572 | |
| }, | |
| { | |
| "epoch": 4.29, | |
| "learning_rate": 3.5855646100116416e-05, | |
| "loss": 0.6539, | |
| "step": 616 | |
| }, | |
| { | |
| "epoch": 4.48, | |
| "learning_rate": 3.841676367869616e-05, | |
| "loss": 0.6692, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 5.06, | |
| "learning_rate": 4.0977881257275904e-05, | |
| "loss": 0.6142, | |
| "step": 704 | |
| }, | |
| { | |
| "epoch": 5.26, | |
| "learning_rate": 4.353899883585565e-05, | |
| "loss": 0.5731, | |
| "step": 748 | |
| }, | |
| { | |
| "epoch": 5.46, | |
| "learning_rate": 4.60419091967404e-05, | |
| "loss": 0.6002, | |
| "step": 792 | |
| }, | |
| { | |
| "epoch": 6.04, | |
| "learning_rate": 4.860302677532014e-05, | |
| "loss": 0.6326, | |
| "step": 836 | |
| }, | |
| { | |
| "epoch": 6.23, | |
| "learning_rate": 5.116414435389989e-05, | |
| "loss": 0.5305, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 6.43, | |
| "learning_rate": 5.372526193247963e-05, | |
| "loss": 0.5346, | |
| "step": 924 | |
| }, | |
| { | |
| "epoch": 7.01, | |
| "learning_rate": 5.6286379511059375e-05, | |
| "loss": 0.5423, | |
| "step": 968 | |
| }, | |
| { | |
| "epoch": 7.21, | |
| "learning_rate": 5.884749708963911e-05, | |
| "loss": 0.4862, | |
| "step": 1012 | |
| }, | |
| { | |
| "epoch": 7.4, | |
| "learning_rate": 6.140861466821886e-05, | |
| "loss": 0.5019, | |
| "step": 1056 | |
| }, | |
| { | |
| "epoch": 7.6, | |
| "learning_rate": 6.396973224679861e-05, | |
| "loss": 0.4905, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 8.18, | |
| "learning_rate": 6.653084982537835e-05, | |
| "loss": 0.4358, | |
| "step": 1144 | |
| }, | |
| { | |
| "epoch": 8.38, | |
| "learning_rate": 6.90919674039581e-05, | |
| "loss": 0.4369, | |
| "step": 1188 | |
| }, | |
| { | |
| "epoch": 8.57, | |
| "learning_rate": 7.165308498253784e-05, | |
| "loss": 0.4566, | |
| "step": 1232 | |
| }, | |
| { | |
| "epoch": 9.15, | |
| "learning_rate": 7.421420256111758e-05, | |
| "loss": 0.4201, | |
| "step": 1276 | |
| }, | |
| { | |
| "epoch": 9.35, | |
| "learning_rate": 7.677532013969733e-05, | |
| "loss": 0.3598, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 9.55, | |
| "learning_rate": 7.933643771827707e-05, | |
| "loss": 0.4108, | |
| "step": 1364 | |
| }, | |
| { | |
| "epoch": 10.13, | |
| "learning_rate": 8.189755529685681e-05, | |
| "loss": 0.3463, | |
| "step": 1408 | |
| }, | |
| { | |
| "epoch": 10.32, | |
| "learning_rate": 8.445867287543656e-05, | |
| "loss": 0.3552, | |
| "step": 1452 | |
| }, | |
| { | |
| "epoch": 10.52, | |
| "learning_rate": 8.70197904540163e-05, | |
| "loss": 0.3687, | |
| "step": 1496 | |
| }, | |
| { | |
| "epoch": 11.1, | |
| "learning_rate": 8.958090803259605e-05, | |
| "loss": 0.3342, | |
| "step": 1540 | |
| }, | |
| { | |
| "epoch": 11.3, | |
| "learning_rate": 9.214202561117579e-05, | |
| "loss": 0.31, | |
| "step": 1584 | |
| }, | |
| { | |
| "epoch": 11.49, | |
| "learning_rate": 9.470314318975554e-05, | |
| "loss": 0.2917, | |
| "step": 1628 | |
| }, | |
| { | |
| "epoch": 12.07, | |
| "learning_rate": 9.726426076833528e-05, | |
| "loss": 0.3055, | |
| "step": 1672 | |
| }, | |
| { | |
| "epoch": 12.27, | |
| "learning_rate": 9.982537834691502e-05, | |
| "loss": 0.2541, | |
| "step": 1716 | |
| }, | |
| { | |
| "epoch": 12.47, | |
| "learning_rate": 9.973467935028797e-05, | |
| "loss": 0.277, | |
| "step": 1760 | |
| }, | |
| { | |
| "epoch": 13.04, | |
| "learning_rate": 9.944994499449946e-05, | |
| "loss": 0.2611, | |
| "step": 1804 | |
| }, | |
| { | |
| "epoch": 13.24, | |
| "learning_rate": 9.916521063871093e-05, | |
| "loss": 0.208, | |
| "step": 1848 | |
| }, | |
| { | |
| "epoch": 13.44, | |
| "learning_rate": 9.888047628292242e-05, | |
| "loss": 0.2238, | |
| "step": 1892 | |
| }, | |
| { | |
| "epoch": 14.02, | |
| "learning_rate": 9.85957419271339e-05, | |
| "loss": 0.2341, | |
| "step": 1936 | |
| }, | |
| { | |
| "epoch": 14.22, | |
| "learning_rate": 9.831100757134537e-05, | |
| "loss": 0.1703, | |
| "step": 1980 | |
| }, | |
| { | |
| "epoch": 14.41, | |
| "learning_rate": 9.802627321555685e-05, | |
| "loss": 0.2005, | |
| "step": 2024 | |
| }, | |
| { | |
| "epoch": 14.61, | |
| "learning_rate": 9.774153885976833e-05, | |
| "loss": 0.1763, | |
| "step": 2068 | |
| }, | |
| { | |
| "epoch": 15.19, | |
| "learning_rate": 9.745680450397982e-05, | |
| "loss": 0.1496, | |
| "step": 2112 | |
| }, | |
| { | |
| "epoch": 15.39, | |
| "learning_rate": 9.71720701481913e-05, | |
| "loss": 0.1414, | |
| "step": 2156 | |
| }, | |
| { | |
| "epoch": 15.58, | |
| "learning_rate": 9.688733579240278e-05, | |
| "loss": 0.1597, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 16.16, | |
| "learning_rate": 9.660260143661426e-05, | |
| "loss": 0.1234, | |
| "step": 2244 | |
| }, | |
| { | |
| "epoch": 16.36, | |
| "learning_rate": 9.631786708082572e-05, | |
| "loss": 0.1305, | |
| "step": 2288 | |
| }, | |
| { | |
| "epoch": 16.56, | |
| "learning_rate": 9.603313272503721e-05, | |
| "loss": 0.1265, | |
| "step": 2332 | |
| }, | |
| { | |
| "epoch": 17.13, | |
| "learning_rate": 9.574839836924869e-05, | |
| "loss": 0.1109, | |
| "step": 2376 | |
| }, | |
| { | |
| "epoch": 17.33, | |
| "learning_rate": 9.546366401346017e-05, | |
| "loss": 0.0975, | |
| "step": 2420 | |
| }, | |
| { | |
| "epoch": 17.53, | |
| "learning_rate": 9.517892965767166e-05, | |
| "loss": 0.1044, | |
| "step": 2464 | |
| }, | |
| { | |
| "epoch": 18.11, | |
| "learning_rate": 9.489419530188314e-05, | |
| "loss": 0.1009, | |
| "step": 2508 | |
| }, | |
| { | |
| "epoch": 18.3, | |
| "learning_rate": 9.460946094609462e-05, | |
| "loss": 0.0852, | |
| "step": 2552 | |
| }, | |
| { | |
| "epoch": 18.5, | |
| "learning_rate": 9.432472659030608e-05, | |
| "loss": 0.0989, | |
| "step": 2596 | |
| }, | |
| { | |
| "epoch": 19.08, | |
| "learning_rate": 9.403999223451757e-05, | |
| "loss": 0.0802, | |
| "step": 2640 | |
| }, | |
| { | |
| "epoch": 19.28, | |
| "learning_rate": 9.375525787872906e-05, | |
| "loss": 0.0675, | |
| "step": 2684 | |
| }, | |
| { | |
| "epoch": 19.48, | |
| "learning_rate": 9.347052352294053e-05, | |
| "loss": 0.0803, | |
| "step": 2728 | |
| }, | |
| { | |
| "epoch": 20.05, | |
| "learning_rate": 9.318578916715202e-05, | |
| "loss": 0.0766, | |
| "step": 2772 | |
| }, | |
| { | |
| "epoch": 20.25, | |
| "learning_rate": 9.29010548113635e-05, | |
| "loss": 0.0601, | |
| "step": 2816 | |
| }, | |
| { | |
| "epoch": 20.45, | |
| "learning_rate": 9.261632045557498e-05, | |
| "loss": 0.0699, | |
| "step": 2860 | |
| }, | |
| { | |
| "epoch": 21.03, | |
| "learning_rate": 9.233158609978645e-05, | |
| "loss": 0.0648, | |
| "step": 2904 | |
| }, | |
| { | |
| "epoch": 21.22, | |
| "learning_rate": 9.204685174399793e-05, | |
| "loss": 0.0517, | |
| "step": 2948 | |
| }, | |
| { | |
| "epoch": 21.42, | |
| "learning_rate": 9.176211738820942e-05, | |
| "loss": 0.0609, | |
| "step": 2992 | |
| }, | |
| { | |
| "epoch": 21.62, | |
| "learning_rate": 9.147738303242089e-05, | |
| "loss": 0.0569, | |
| "step": 3036 | |
| }, | |
| { | |
| "epoch": 22.2, | |
| "learning_rate": 9.119264867663238e-05, | |
| "loss": 0.0463, | |
| "step": 3080 | |
| }, | |
| { | |
| "epoch": 22.39, | |
| "learning_rate": 9.090791432084385e-05, | |
| "loss": 0.051, | |
| "step": 3124 | |
| }, | |
| { | |
| "epoch": 22.59, | |
| "learning_rate": 9.062317996505534e-05, | |
| "loss": 0.0512, | |
| "step": 3168 | |
| }, | |
| { | |
| "epoch": 23.17, | |
| "learning_rate": 9.033844560926681e-05, | |
| "loss": 0.0422, | |
| "step": 3212 | |
| }, | |
| { | |
| "epoch": 23.37, | |
| "learning_rate": 9.005371125347829e-05, | |
| "loss": 0.0415, | |
| "step": 3256 | |
| }, | |
| { | |
| "epoch": 23.57, | |
| "learning_rate": 8.976897689768977e-05, | |
| "loss": 0.0466, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 24.14, | |
| "learning_rate": 8.948424254190125e-05, | |
| "loss": 0.0401, | |
| "step": 3344 | |
| }, | |
| { | |
| "epoch": 24.34, | |
| "learning_rate": 8.919950818611274e-05, | |
| "loss": 0.0386, | |
| "step": 3388 | |
| }, | |
| { | |
| "epoch": 24.54, | |
| "learning_rate": 8.891477383032421e-05, | |
| "loss": 0.0394, | |
| "step": 3432 | |
| }, | |
| { | |
| "epoch": 25.12, | |
| "learning_rate": 8.86300394745357e-05, | |
| "loss": 0.0368, | |
| "step": 3476 | |
| }, | |
| { | |
| "epoch": 25.31, | |
| "learning_rate": 8.834530511874717e-05, | |
| "loss": 0.0357, | |
| "step": 3520 | |
| }, | |
| { | |
| "epoch": 25.51, | |
| "learning_rate": 8.806057076295865e-05, | |
| "loss": 0.0372, | |
| "step": 3564 | |
| }, | |
| { | |
| "epoch": 26.09, | |
| "learning_rate": 8.777583640717013e-05, | |
| "loss": 0.0314, | |
| "step": 3608 | |
| }, | |
| { | |
| "epoch": 26.29, | |
| "learning_rate": 8.749110205138161e-05, | |
| "loss": 0.032, | |
| "step": 3652 | |
| }, | |
| { | |
| "epoch": 26.48, | |
| "learning_rate": 8.72063676955931e-05, | |
| "loss": 0.0324, | |
| "step": 3696 | |
| }, | |
| { | |
| "epoch": 27.06, | |
| "learning_rate": 8.692163333980458e-05, | |
| "loss": 0.0309, | |
| "step": 3740 | |
| }, | |
| { | |
| "epoch": 27.26, | |
| "learning_rate": 8.663689898401606e-05, | |
| "loss": 0.0296, | |
| "step": 3784 | |
| }, | |
| { | |
| "epoch": 27.46, | |
| "learning_rate": 8.635216462822753e-05, | |
| "loss": 0.0311, | |
| "step": 3828 | |
| }, | |
| { | |
| "epoch": 28.04, | |
| "learning_rate": 8.6067430272439e-05, | |
| "loss": 0.0304, | |
| "step": 3872 | |
| }, | |
| { | |
| "epoch": 28.23, | |
| "learning_rate": 8.578269591665049e-05, | |
| "loss": 0.0249, | |
| "step": 3916 | |
| }, | |
| { | |
| "epoch": 28.43, | |
| "learning_rate": 8.549796156086198e-05, | |
| "loss": 0.0267, | |
| "step": 3960 | |
| }, | |
| { | |
| "epoch": 29.01, | |
| "learning_rate": 8.521322720507345e-05, | |
| "loss": 0.0299, | |
| "step": 4004 | |
| }, | |
| { | |
| "epoch": 29.21, | |
| "learning_rate": 8.492849284928494e-05, | |
| "loss": 0.0222, | |
| "step": 4048 | |
| }, | |
| { | |
| "epoch": 29.4, | |
| "learning_rate": 8.464375849349641e-05, | |
| "loss": 0.0266, | |
| "step": 4092 | |
| }, | |
| { | |
| "epoch": 29.6, | |
| "learning_rate": 8.435902413770789e-05, | |
| "loss": 0.0293, | |
| "step": 4136 | |
| }, | |
| { | |
| "epoch": 30.18, | |
| "learning_rate": 8.407428978191936e-05, | |
| "loss": 0.0203, | |
| "step": 4180 | |
| }, | |
| { | |
| "epoch": 30.38, | |
| "learning_rate": 8.378955542613085e-05, | |
| "loss": 0.0239, | |
| "step": 4224 | |
| }, | |
| { | |
| "epoch": 30.57, | |
| "learning_rate": 8.350482107034234e-05, | |
| "loss": 0.0263, | |
| "step": 4268 | |
| }, | |
| { | |
| "epoch": 31.15, | |
| "learning_rate": 8.322008671455381e-05, | |
| "loss": 0.0197, | |
| "step": 4312 | |
| }, | |
| { | |
| "epoch": 31.35, | |
| "learning_rate": 8.29353523587653e-05, | |
| "loss": 0.0221, | |
| "step": 4356 | |
| }, | |
| { | |
| "epoch": 31.55, | |
| "learning_rate": 8.265061800297677e-05, | |
| "loss": 0.0225, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 32.13, | |
| "learning_rate": 8.236588364718825e-05, | |
| "loss": 0.0201, | |
| "step": 4444 | |
| }, | |
| { | |
| "epoch": 32.32, | |
| "learning_rate": 8.208114929139973e-05, | |
| "loss": 0.0204, | |
| "step": 4488 | |
| }, | |
| { | |
| "epoch": 32.52, | |
| "learning_rate": 8.179641493561121e-05, | |
| "loss": 0.0213, | |
| "step": 4532 | |
| }, | |
| { | |
| "epoch": 33.1, | |
| "learning_rate": 8.15116805798227e-05, | |
| "loss": 0.0189, | |
| "step": 4576 | |
| }, | |
| { | |
| "epoch": 33.3, | |
| "learning_rate": 8.122694622403417e-05, | |
| "loss": 0.0197, | |
| "step": 4620 | |
| }, | |
| { | |
| "epoch": 33.49, | |
| "learning_rate": 8.094221186824566e-05, | |
| "loss": 0.0201, | |
| "step": 4664 | |
| }, | |
| { | |
| "epoch": 34.07, | |
| "learning_rate": 8.065747751245713e-05, | |
| "loss": 0.0204, | |
| "step": 4708 | |
| }, | |
| { | |
| "epoch": 34.27, | |
| "learning_rate": 8.037921439202744e-05, | |
| "loss": 0.0176, | |
| "step": 4752 | |
| }, | |
| { | |
| "epoch": 34.47, | |
| "learning_rate": 8.009448003623892e-05, | |
| "loss": 0.0206, | |
| "step": 4796 | |
| }, | |
| { | |
| "epoch": 35.04, | |
| "learning_rate": 7.980974568045039e-05, | |
| "loss": 0.0175, | |
| "step": 4840 | |
| }, | |
| { | |
| "epoch": 35.24, | |
| "learning_rate": 7.952501132466188e-05, | |
| "loss": 0.017, | |
| "step": 4884 | |
| }, | |
| { | |
| "epoch": 35.44, | |
| "learning_rate": 7.924027696887337e-05, | |
| "loss": 0.0185, | |
| "step": 4928 | |
| }, | |
| { | |
| "epoch": 36.02, | |
| "learning_rate": 7.895554261308484e-05, | |
| "loss": 0.0168, | |
| "step": 4972 | |
| }, | |
| { | |
| "epoch": 36.22, | |
| "learning_rate": 7.867080825729633e-05, | |
| "loss": 0.0161, | |
| "step": 5016 | |
| }, | |
| { | |
| "epoch": 36.41, | |
| "learning_rate": 7.83860739015078e-05, | |
| "loss": 0.0166, | |
| "step": 5060 | |
| }, | |
| { | |
| "epoch": 36.61, | |
| "learning_rate": 7.810133954571928e-05, | |
| "loss": 0.0178, | |
| "step": 5104 | |
| }, | |
| { | |
| "epoch": 37.19, | |
| "learning_rate": 7.781660518993076e-05, | |
| "loss": 0.0151, | |
| "step": 5148 | |
| }, | |
| { | |
| "epoch": 37.39, | |
| "learning_rate": 7.753187083414224e-05, | |
| "loss": 0.0152, | |
| "step": 5192 | |
| }, | |
| { | |
| "epoch": 37.58, | |
| "learning_rate": 7.724713647835373e-05, | |
| "loss": 0.0167, | |
| "step": 5236 | |
| }, | |
| { | |
| "epoch": 38.16, | |
| "learning_rate": 7.69624021225652e-05, | |
| "loss": 0.0133, | |
| "step": 5280 | |
| }, | |
| { | |
| "epoch": 38.36, | |
| "learning_rate": 7.667766776677669e-05, | |
| "loss": 0.0164, | |
| "step": 5324 | |
| }, | |
| { | |
| "epoch": 38.56, | |
| "learning_rate": 7.639293341098816e-05, | |
| "loss": 0.016, | |
| "step": 5368 | |
| }, | |
| { | |
| "epoch": 39.13, | |
| "learning_rate": 7.610819905519963e-05, | |
| "loss": 0.0144, | |
| "step": 5412 | |
| }, | |
| { | |
| "epoch": 39.33, | |
| "learning_rate": 7.582346469941112e-05, | |
| "loss": 0.0133, | |
| "step": 5456 | |
| }, | |
| { | |
| "epoch": 39.53, | |
| "learning_rate": 7.55387303436226e-05, | |
| "loss": 0.0156, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 40.11, | |
| "learning_rate": 7.525399598783408e-05, | |
| "loss": 0.0142, | |
| "step": 5544 | |
| }, | |
| { | |
| "epoch": 40.3, | |
| "learning_rate": 7.496926163204556e-05, | |
| "loss": 0.0143, | |
| "step": 5588 | |
| }, | |
| { | |
| "epoch": 40.5, | |
| "learning_rate": 7.468452727625704e-05, | |
| "loss": 0.0128, | |
| "step": 5632 | |
| }, | |
| { | |
| "epoch": 41.08, | |
| "learning_rate": 7.439979292046852e-05, | |
| "loss": 0.0135, | |
| "step": 5676 | |
| }, | |
| { | |
| "epoch": 41.28, | |
| "learning_rate": 7.411505856467999e-05, | |
| "loss": 0.011, | |
| "step": 5720 | |
| }, | |
| { | |
| "epoch": 41.48, | |
| "learning_rate": 7.383032420889148e-05, | |
| "loss": 0.0132, | |
| "step": 5764 | |
| }, | |
| { | |
| "epoch": 42.05, | |
| "learning_rate": 7.354558985310295e-05, | |
| "loss": 0.0136, | |
| "step": 5808 | |
| }, | |
| { | |
| "epoch": 42.25, | |
| "learning_rate": 7.326085549731444e-05, | |
| "loss": 0.0112, | |
| "step": 5852 | |
| }, | |
| { | |
| "epoch": 42.45, | |
| "learning_rate": 7.297612114152592e-05, | |
| "loss": 0.0122, | |
| "step": 5896 | |
| }, | |
| { | |
| "epoch": 43.03, | |
| "learning_rate": 7.26913867857374e-05, | |
| "loss": 0.0138, | |
| "step": 5940 | |
| }, | |
| { | |
| "epoch": 43.22, | |
| "learning_rate": 7.240665242994889e-05, | |
| "loss": 0.0108, | |
| "step": 5984 | |
| }, | |
| { | |
| "epoch": 43.42, | |
| "learning_rate": 7.212191807416036e-05, | |
| "loss": 0.0119, | |
| "step": 6028 | |
| }, | |
| { | |
| "epoch": 43.62, | |
| "learning_rate": 7.183718371837184e-05, | |
| "loss": 0.0108, | |
| "step": 6072 | |
| }, | |
| { | |
| "epoch": 44.2, | |
| "learning_rate": 7.155244936258331e-05, | |
| "loss": 0.0105, | |
| "step": 6116 | |
| }, | |
| { | |
| "epoch": 44.39, | |
| "learning_rate": 7.12677150067948e-05, | |
| "loss": 0.0108, | |
| "step": 6160 | |
| }, | |
| { | |
| "epoch": 44.59, | |
| "learning_rate": 7.098298065100629e-05, | |
| "loss": 0.0117, | |
| "step": 6204 | |
| }, | |
| { | |
| "epoch": 45.17, | |
| "learning_rate": 7.069824629521776e-05, | |
| "loss": 0.0109, | |
| "step": 6248 | |
| }, | |
| { | |
| "epoch": 45.37, | |
| "learning_rate": 7.041998317478807e-05, | |
| "loss": 0.0108, | |
| "step": 6292 | |
| }, | |
| { | |
| "epoch": 45.57, | |
| "learning_rate": 7.013524881899955e-05, | |
| "loss": 0.012, | |
| "step": 6336 | |
| }, | |
| { | |
| "epoch": 46.14, | |
| "learning_rate": 6.985051446321102e-05, | |
| "loss": 0.0101, | |
| "step": 6380 | |
| }, | |
| { | |
| "epoch": 46.34, | |
| "learning_rate": 6.956578010742251e-05, | |
| "loss": 0.0096, | |
| "step": 6424 | |
| }, | |
| { | |
| "epoch": 46.54, | |
| "learning_rate": 6.928104575163398e-05, | |
| "loss": 0.0102, | |
| "step": 6468 | |
| }, | |
| { | |
| "epoch": 47.12, | |
| "learning_rate": 6.899631139584547e-05, | |
| "loss": 0.0091, | |
| "step": 6512 | |
| }, | |
| { | |
| "epoch": 47.31, | |
| "learning_rate": 6.871157704005695e-05, | |
| "loss": 0.0092, | |
| "step": 6556 | |
| }, | |
| { | |
| "epoch": 47.51, | |
| "learning_rate": 6.842684268426843e-05, | |
| "loss": 0.0096, | |
| "step": 6600 | |
| }, | |
| { | |
| "epoch": 48.09, | |
| "learning_rate": 6.814210832847992e-05, | |
| "loss": 0.0091, | |
| "step": 6644 | |
| }, | |
| { | |
| "epoch": 48.29, | |
| "learning_rate": 6.785737397269138e-05, | |
| "loss": 0.0091, | |
| "step": 6688 | |
| }, | |
| { | |
| "epoch": 48.48, | |
| "learning_rate": 6.757263961690287e-05, | |
| "loss": 0.0097, | |
| "step": 6732 | |
| }, | |
| { | |
| "epoch": 49.06, | |
| "learning_rate": 6.728790526111434e-05, | |
| "loss": 0.0104, | |
| "step": 6776 | |
| }, | |
| { | |
| "epoch": 49.26, | |
| "learning_rate": 6.700317090532583e-05, | |
| "loss": 0.0091, | |
| "step": 6820 | |
| }, | |
| { | |
| "epoch": 49.46, | |
| "learning_rate": 6.671843654953732e-05, | |
| "loss": 0.0087, | |
| "step": 6864 | |
| }, | |
| { | |
| "epoch": 50.04, | |
| "learning_rate": 6.643370219374879e-05, | |
| "loss": 0.0097, | |
| "step": 6908 | |
| }, | |
| { | |
| "epoch": 50.23, | |
| "learning_rate": 6.614896783796028e-05, | |
| "loss": 0.009, | |
| "step": 6952 | |
| }, | |
| { | |
| "epoch": 50.43, | |
| "learning_rate": 6.586423348217174e-05, | |
| "loss": 0.0087, | |
| "step": 6996 | |
| }, | |
| { | |
| "epoch": 51.01, | |
| "learning_rate": 6.557949912638323e-05, | |
| "loss": 0.009, | |
| "step": 7040 | |
| }, | |
| { | |
| "epoch": 51.21, | |
| "learning_rate": 6.529476477059471e-05, | |
| "loss": 0.0076, | |
| "step": 7084 | |
| }, | |
| { | |
| "epoch": 51.4, | |
| "learning_rate": 6.501003041480619e-05, | |
| "loss": 0.0083, | |
| "step": 7128 | |
| }, | |
| { | |
| "epoch": 51.6, | |
| "learning_rate": 6.472529605901768e-05, | |
| "loss": 0.0079, | |
| "step": 7172 | |
| }, | |
| { | |
| "epoch": 52.18, | |
| "learning_rate": 6.444056170322915e-05, | |
| "loss": 0.0075, | |
| "step": 7216 | |
| }, | |
| { | |
| "epoch": 52.38, | |
| "learning_rate": 6.415582734744064e-05, | |
| "loss": 0.0077, | |
| "step": 7260 | |
| }, | |
| { | |
| "epoch": 52.57, | |
| "learning_rate": 6.38710929916521e-05, | |
| "loss": 0.0069, | |
| "step": 7304 | |
| }, | |
| { | |
| "epoch": 53.15, | |
| "learning_rate": 6.358635863586358e-05, | |
| "loss": 0.0078, | |
| "step": 7348 | |
| }, | |
| { | |
| "epoch": 53.35, | |
| "learning_rate": 6.330162428007507e-05, | |
| "loss": 0.0077, | |
| "step": 7392 | |
| }, | |
| { | |
| "epoch": 53.55, | |
| "learning_rate": 6.301688992428655e-05, | |
| "loss": 0.0074, | |
| "step": 7436 | |
| }, | |
| { | |
| "epoch": 54.13, | |
| "learning_rate": 6.273215556849803e-05, | |
| "loss": 0.0071, | |
| "step": 7480 | |
| }, | |
| { | |
| "epoch": 54.32, | |
| "learning_rate": 6.244742121270951e-05, | |
| "loss": 0.0068, | |
| "step": 7524 | |
| }, | |
| { | |
| "epoch": 54.52, | |
| "learning_rate": 6.2162686856921e-05, | |
| "loss": 0.0081, | |
| "step": 7568 | |
| }, | |
| { | |
| "epoch": 55.1, | |
| "learning_rate": 6.187795250113247e-05, | |
| "loss": 0.0069, | |
| "step": 7612 | |
| }, | |
| { | |
| "epoch": 55.3, | |
| "learning_rate": 6.159321814534394e-05, | |
| "loss": 0.0064, | |
| "step": 7656 | |
| }, | |
| { | |
| "epoch": 55.49, | |
| "learning_rate": 6.130848378955543e-05, | |
| "loss": 0.0076, | |
| "step": 7700 | |
| }, | |
| { | |
| "epoch": 56.07, | |
| "learning_rate": 6.102374943376691e-05, | |
| "loss": 0.0067, | |
| "step": 7744 | |
| }, | |
| { | |
| "epoch": 56.27, | |
| "learning_rate": 6.073901507797839e-05, | |
| "loss": 0.0065, | |
| "step": 7788 | |
| }, | |
| { | |
| "epoch": 56.47, | |
| "learning_rate": 6.045428072218987e-05, | |
| "loss": 0.0067, | |
| "step": 7832 | |
| }, | |
| { | |
| "epoch": 57.04, | |
| "learning_rate": 6.016954636640135e-05, | |
| "loss": 0.0078, | |
| "step": 7876 | |
| }, | |
| { | |
| "epoch": 57.24, | |
| "learning_rate": 5.9884812010612834e-05, | |
| "loss": 0.0065, | |
| "step": 7920 | |
| }, | |
| { | |
| "epoch": 57.44, | |
| "learning_rate": 5.96000776548243e-05, | |
| "loss": 0.0074, | |
| "step": 7964 | |
| }, | |
| { | |
| "epoch": 58.02, | |
| "learning_rate": 5.931534329903579e-05, | |
| "loss": 0.0081, | |
| "step": 8008 | |
| }, | |
| { | |
| "epoch": 58.22, | |
| "learning_rate": 5.903060894324727e-05, | |
| "loss": 0.0071, | |
| "step": 8052 | |
| }, | |
| { | |
| "epoch": 58.41, | |
| "learning_rate": 5.874587458745875e-05, | |
| "loss": 0.0058, | |
| "step": 8096 | |
| }, | |
| { | |
| "epoch": 58.61, | |
| "learning_rate": 5.846114023167023e-05, | |
| "loss": 0.007, | |
| "step": 8140 | |
| }, | |
| { | |
| "epoch": 59.19, | |
| "learning_rate": 5.817640587588171e-05, | |
| "loss": 0.0054, | |
| "step": 8184 | |
| }, | |
| { | |
| "epoch": 59.39, | |
| "learning_rate": 5.789167152009319e-05, | |
| "loss": 0.0062, | |
| "step": 8228 | |
| }, | |
| { | |
| "epoch": 59.58, | |
| "learning_rate": 5.7606937164304666e-05, | |
| "loss": 0.0058, | |
| "step": 8272 | |
| }, | |
| { | |
| "epoch": 60.16, | |
| "learning_rate": 5.732220280851615e-05, | |
| "loss": 0.0056, | |
| "step": 8316 | |
| }, | |
| { | |
| "epoch": 60.36, | |
| "learning_rate": 5.703746845272763e-05, | |
| "loss": 0.0056, | |
| "step": 8360 | |
| }, | |
| { | |
| "epoch": 60.56, | |
| "learning_rate": 5.675273409693911e-05, | |
| "loss": 0.0061, | |
| "step": 8404 | |
| }, | |
| { | |
| "epoch": 61.13, | |
| "learning_rate": 5.646799974115059e-05, | |
| "loss": 0.0043, | |
| "step": 8448 | |
| }, | |
| { | |
| "epoch": 61.33, | |
| "learning_rate": 5.618326538536207e-05, | |
| "loss": 0.005, | |
| "step": 8492 | |
| }, | |
| { | |
| "epoch": 61.53, | |
| "learning_rate": 5.589853102957355e-05, | |
| "loss": 0.0055, | |
| "step": 8536 | |
| }, | |
| { | |
| "epoch": 62.11, | |
| "learning_rate": 5.5613796673785025e-05, | |
| "loss": 0.0051, | |
| "step": 8580 | |
| }, | |
| { | |
| "epoch": 62.3, | |
| "learning_rate": 5.5329062317996505e-05, | |
| "loss": 0.0049, | |
| "step": 8624 | |
| }, | |
| { | |
| "epoch": 62.5, | |
| "learning_rate": 5.5044327962207986e-05, | |
| "loss": 0.0062, | |
| "step": 8668 | |
| }, | |
| { | |
| "epoch": 63.08, | |
| "learning_rate": 5.475959360641947e-05, | |
| "loss": 0.0058, | |
| "step": 8712 | |
| }, | |
| { | |
| "epoch": 63.28, | |
| "learning_rate": 5.447485925063095e-05, | |
| "loss": 0.0069, | |
| "step": 8756 | |
| }, | |
| { | |
| "epoch": 63.48, | |
| "learning_rate": 5.419012489484243e-05, | |
| "loss": 0.0064, | |
| "step": 8800 | |
| }, | |
| { | |
| "epoch": 64.05, | |
| "learning_rate": 5.3905390539053916e-05, | |
| "loss": 0.006, | |
| "step": 8844 | |
| }, | |
| { | |
| "epoch": 64.25, | |
| "learning_rate": 5.362065618326538e-05, | |
| "loss": 0.0059, | |
| "step": 8888 | |
| }, | |
| { | |
| "epoch": 64.45, | |
| "learning_rate": 5.3335921827476864e-05, | |
| "loss": 0.005, | |
| "step": 8932 | |
| }, | |
| { | |
| "epoch": 65.03, | |
| "learning_rate": 5.3051187471688344e-05, | |
| "loss": 0.0066, | |
| "step": 8976 | |
| }, | |
| { | |
| "epoch": 65.22, | |
| "learning_rate": 5.2766453115899825e-05, | |
| "loss": 0.0054, | |
| "step": 9020 | |
| }, | |
| { | |
| "epoch": 65.42, | |
| "learning_rate": 5.248171876011131e-05, | |
| "loss": 0.0059, | |
| "step": 9064 | |
| }, | |
| { | |
| "epoch": 65.62, | |
| "learning_rate": 5.219698440432279e-05, | |
| "loss": 0.0059, | |
| "step": 9108 | |
| }, | |
| { | |
| "epoch": 66.2, | |
| "learning_rate": 5.1912250048534274e-05, | |
| "loss": 0.0059, | |
| "step": 9152 | |
| }, | |
| { | |
| "epoch": 66.39, | |
| "learning_rate": 5.162751569274574e-05, | |
| "loss": 0.0058, | |
| "step": 9196 | |
| }, | |
| { | |
| "epoch": 66.59, | |
| "learning_rate": 5.134278133695722e-05, | |
| "loss": 0.0059, | |
| "step": 9240 | |
| }, | |
| { | |
| "epoch": 67.17, | |
| "learning_rate": 5.10580469811687e-05, | |
| "loss": 0.0045, | |
| "step": 9284 | |
| }, | |
| { | |
| "epoch": 67.37, | |
| "learning_rate": 5.077331262538019e-05, | |
| "loss": 0.0054, | |
| "step": 9328 | |
| }, | |
| { | |
| "epoch": 67.57, | |
| "learning_rate": 5.048857826959167e-05, | |
| "loss": 0.0052, | |
| "step": 9372 | |
| }, | |
| { | |
| "epoch": 68.14, | |
| "learning_rate": 5.020384391380315e-05, | |
| "loss": 0.005, | |
| "step": 9416 | |
| }, | |
| { | |
| "epoch": 68.34, | |
| "learning_rate": 4.9919109558014625e-05, | |
| "loss": 0.0051, | |
| "step": 9460 | |
| }, | |
| { | |
| "epoch": 68.54, | |
| "learning_rate": 4.9634375202226106e-05, | |
| "loss": 0.005, | |
| "step": 9504 | |
| }, | |
| { | |
| "epoch": 69.12, | |
| "learning_rate": 4.934964084643759e-05, | |
| "loss": 0.0054, | |
| "step": 9548 | |
| }, | |
| { | |
| "epoch": 69.31, | |
| "learning_rate": 4.906490649064907e-05, | |
| "loss": 0.0055, | |
| "step": 9592 | |
| }, | |
| { | |
| "epoch": 69.51, | |
| "learning_rate": 4.878017213486055e-05, | |
| "loss": 0.0053, | |
| "step": 9636 | |
| }, | |
| { | |
| "epoch": 70.09, | |
| "learning_rate": 4.849543777907203e-05, | |
| "loss": 0.0051, | |
| "step": 9680 | |
| }, | |
| { | |
| "epoch": 70.29, | |
| "learning_rate": 4.821070342328351e-05, | |
| "loss": 0.0047, | |
| "step": 9724 | |
| }, | |
| { | |
| "epoch": 70.48, | |
| "learning_rate": 4.7925969067494984e-05, | |
| "loss": 0.0053, | |
| "step": 9768 | |
| }, | |
| { | |
| "epoch": 71.06, | |
| "learning_rate": 4.7641234711706464e-05, | |
| "loss": 0.0047, | |
| "step": 9812 | |
| }, | |
| { | |
| "epoch": 71.26, | |
| "learning_rate": 4.735650035591795e-05, | |
| "loss": 0.0049, | |
| "step": 9856 | |
| }, | |
| { | |
| "epoch": 71.46, | |
| "learning_rate": 4.7071766000129426e-05, | |
| "loss": 0.0049, | |
| "step": 9900 | |
| }, | |
| { | |
| "epoch": 72.04, | |
| "learning_rate": 4.6787031644340907e-05, | |
| "loss": 0.005, | |
| "step": 9944 | |
| }, | |
| { | |
| "epoch": 72.23, | |
| "learning_rate": 4.650229728855239e-05, | |
| "loss": 0.0038, | |
| "step": 9988 | |
| }, | |
| { | |
| "epoch": 72.43, | |
| "learning_rate": 4.621756293276387e-05, | |
| "loss": 0.0045, | |
| "step": 10032 | |
| }, | |
| { | |
| "epoch": 73.01, | |
| "learning_rate": 4.593282857697534e-05, | |
| "loss": 0.004, | |
| "step": 10076 | |
| }, | |
| { | |
| "epoch": 73.21, | |
| "learning_rate": 4.564809422118683e-05, | |
| "loss": 0.004, | |
| "step": 10120 | |
| }, | |
| { | |
| "epoch": 73.4, | |
| "learning_rate": 4.536335986539831e-05, | |
| "loss": 0.0042, | |
| "step": 10164 | |
| }, | |
| { | |
| "epoch": 73.6, | |
| "learning_rate": 4.5078625509609784e-05, | |
| "loss": 0.0048, | |
| "step": 10208 | |
| }, | |
| { | |
| "epoch": 74.18, | |
| "learning_rate": 4.4793891153821265e-05, | |
| "loss": 0.0038, | |
| "step": 10252 | |
| }, | |
| { | |
| "epoch": 74.38, | |
| "learning_rate": 4.4509156798032745e-05, | |
| "loss": 0.0034, | |
| "step": 10296 | |
| }, | |
| { | |
| "epoch": 74.57, | |
| "learning_rate": 4.4224422442244226e-05, | |
| "loss": 0.0044, | |
| "step": 10340 | |
| }, | |
| { | |
| "epoch": 75.15, | |
| "learning_rate": 4.393968808645571e-05, | |
| "loss": 0.0034, | |
| "step": 10384 | |
| }, | |
| { | |
| "epoch": 75.35, | |
| "learning_rate": 4.365495373066719e-05, | |
| "loss": 0.0036, | |
| "step": 10428 | |
| }, | |
| { | |
| "epoch": 75.55, | |
| "learning_rate": 4.337021937487867e-05, | |
| "loss": 0.0047, | |
| "step": 10472 | |
| }, | |
| { | |
| "epoch": 76.13, | |
| "learning_rate": 4.308548501909014e-05, | |
| "loss": 0.0034, | |
| "step": 10516 | |
| }, | |
| { | |
| "epoch": 76.32, | |
| "learning_rate": 4.280075066330162e-05, | |
| "loss": 0.0034, | |
| "step": 10560 | |
| }, | |
| { | |
| "epoch": 76.52, | |
| "learning_rate": 4.2516016307513104e-05, | |
| "loss": 0.0039, | |
| "step": 10604 | |
| } | |
| ], | |
| "logging_steps": 44, | |
| "max_steps": 17171, | |
| "num_train_epochs": 77, | |
| "save_steps": 500, | |
| "total_flos": 9.293451052135219e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |