| { |
| "best_global_step": 625, |
| "best_metric": 0.18495811522006989, |
| "best_model_checkpoint": "./results/checkpoint-625", |
| "epoch": 2.0, |
| "eval_steps": 500, |
| "global_step": 1250, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.016, |
| "grad_norm": 19.218093872070312, |
| "learning_rate": 4.9640000000000006e-05, |
| "loss": 0.09028505682945251, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.032, |
| "grad_norm": 1.0261529684066772, |
| "learning_rate": 4.924e-05, |
| "loss": 0.15324625968933106, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.048, |
| "grad_norm": 21.003023147583008, |
| "learning_rate": 4.884e-05, |
| "loss": 0.22774670124053956, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.064, |
| "grad_norm": 7.388162612915039, |
| "learning_rate": 4.8440000000000004e-05, |
| "loss": 0.4121945858001709, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.08, |
| "grad_norm": 4.979572296142578, |
| "learning_rate": 4.804e-05, |
| "loss": 0.38861570358276365, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.096, |
| "grad_norm": 5.862935543060303, |
| "learning_rate": 4.7640000000000005e-05, |
| "loss": 0.29872808456420896, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.112, |
| "grad_norm": 8.852452278137207, |
| "learning_rate": 4.724e-05, |
| "loss": 0.3256639242172241, |
| "step": 70 |
| }, |
| { |
| "epoch": 0.128, |
| "grad_norm": 3.3186402320861816, |
| "learning_rate": 4.684e-05, |
| "loss": 0.3397534847259521, |
| "step": 80 |
| }, |
| { |
| "epoch": 0.144, |
| "grad_norm": 5.926950931549072, |
| "learning_rate": 4.644e-05, |
| "loss": 0.19672555923461915, |
| "step": 90 |
| }, |
| { |
| "epoch": 0.16, |
| "grad_norm": 9.196661949157715, |
| "learning_rate": 4.604e-05, |
| "loss": 0.2907862663269043, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.176, |
| "grad_norm": 5.412224292755127, |
| "learning_rate": 4.564e-05, |
| "loss": 0.2230736255645752, |
| "step": 110 |
| }, |
| { |
| "epoch": 0.192, |
| "grad_norm": 2.8200976848602295, |
| "learning_rate": 4.524000000000001e-05, |
| "loss": 0.3943183422088623, |
| "step": 120 |
| }, |
| { |
| "epoch": 0.208, |
| "grad_norm": 11.510780334472656, |
| "learning_rate": 4.4840000000000004e-05, |
| "loss": 0.28646397590637207, |
| "step": 130 |
| }, |
| { |
| "epoch": 0.224, |
| "grad_norm": 3.909830093383789, |
| "learning_rate": 4.444e-05, |
| "loss": 0.346493124961853, |
| "step": 140 |
| }, |
| { |
| "epoch": 0.24, |
| "grad_norm": 3.446835517883301, |
| "learning_rate": 4.4040000000000005e-05, |
| "loss": 0.2555964946746826, |
| "step": 150 |
| }, |
| { |
| "epoch": 0.256, |
| "grad_norm": 8.182538032531738, |
| "learning_rate": 4.364e-05, |
| "loss": 0.24913170337677001, |
| "step": 160 |
| }, |
| { |
| "epoch": 0.272, |
| "grad_norm": 4.328517913818359, |
| "learning_rate": 4.324e-05, |
| "loss": 0.3257677316665649, |
| "step": 170 |
| }, |
| { |
| "epoch": 0.288, |
| "grad_norm": 4.964771270751953, |
| "learning_rate": 4.284e-05, |
| "loss": 0.28899221420288085, |
| "step": 180 |
| }, |
| { |
| "epoch": 0.304, |
| "grad_norm": 9.758742332458496, |
| "learning_rate": 4.244e-05, |
| "loss": 0.2279355764389038, |
| "step": 190 |
| }, |
| { |
| "epoch": 0.32, |
| "grad_norm": 4.366827964782715, |
| "learning_rate": 4.2040000000000004e-05, |
| "loss": 0.31453232765197753, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.336, |
| "grad_norm": 2.277212381362915, |
| "learning_rate": 4.164e-05, |
| "loss": 0.20993876457214355, |
| "step": 210 |
| }, |
| { |
| "epoch": 0.352, |
| "grad_norm": 4.816099166870117, |
| "learning_rate": 4.124e-05, |
| "loss": 0.27517788410186766, |
| "step": 220 |
| }, |
| { |
| "epoch": 0.368, |
| "grad_norm": 3.51198673248291, |
| "learning_rate": 4.084e-05, |
| "loss": 0.22087533473968507, |
| "step": 230 |
| }, |
| { |
| "epoch": 0.384, |
| "grad_norm": 5.840693950653076, |
| "learning_rate": 4.044e-05, |
| "loss": 0.20846953392028808, |
| "step": 240 |
| }, |
| { |
| "epoch": 0.4, |
| "grad_norm": 3.9098050594329834, |
| "learning_rate": 4.004e-05, |
| "loss": 0.26031317710876467, |
| "step": 250 |
| }, |
| { |
| "epoch": 0.416, |
| "grad_norm": 3.918344020843506, |
| "learning_rate": 3.964e-05, |
| "loss": 0.2516783714294434, |
| "step": 260 |
| }, |
| { |
| "epoch": 0.432, |
| "grad_norm": 8.892339706420898, |
| "learning_rate": 3.9240000000000004e-05, |
| "loss": 0.2795307159423828, |
| "step": 270 |
| }, |
| { |
| "epoch": 0.448, |
| "grad_norm": 4.103593826293945, |
| "learning_rate": 3.884e-05, |
| "loss": 0.23137011528015136, |
| "step": 280 |
| }, |
| { |
| "epoch": 0.464, |
| "grad_norm": 6.328890800476074, |
| "learning_rate": 3.8440000000000005e-05, |
| "loss": 0.22461700439453125, |
| "step": 290 |
| }, |
| { |
| "epoch": 0.48, |
| "grad_norm": 6.5414719581604, |
| "learning_rate": 3.804e-05, |
| "loss": 0.21610186100006104, |
| "step": 300 |
| }, |
| { |
| "epoch": 0.496, |
| "grad_norm": 3.691993474960327, |
| "learning_rate": 3.7640000000000006e-05, |
| "loss": 0.24925684928894043, |
| "step": 310 |
| }, |
| { |
| "epoch": 0.512, |
| "grad_norm": 4.344432353973389, |
| "learning_rate": 3.724e-05, |
| "loss": 0.21005148887634278, |
| "step": 320 |
| }, |
| { |
| "epoch": 0.528, |
| "grad_norm": 7.790218353271484, |
| "learning_rate": 3.684e-05, |
| "loss": 0.17650561332702636, |
| "step": 330 |
| }, |
| { |
| "epoch": 0.544, |
| "grad_norm": 7.356423854827881, |
| "learning_rate": 3.6440000000000003e-05, |
| "loss": 0.2985139131546021, |
| "step": 340 |
| }, |
| { |
| "epoch": 0.56, |
| "grad_norm": 2.8463327884674072, |
| "learning_rate": 3.604e-05, |
| "loss": 0.20631999969482423, |
| "step": 350 |
| }, |
| { |
| "epoch": 0.576, |
| "grad_norm": 7.239101409912109, |
| "learning_rate": 3.5640000000000004e-05, |
| "loss": 0.2260190486907959, |
| "step": 360 |
| }, |
| { |
| "epoch": 0.592, |
| "grad_norm": 6.864079475402832, |
| "learning_rate": 3.524e-05, |
| "loss": 0.29787819385528563, |
| "step": 370 |
| }, |
| { |
| "epoch": 0.608, |
| "grad_norm": 4.634511947631836, |
| "learning_rate": 3.484e-05, |
| "loss": 0.2093559741973877, |
| "step": 380 |
| }, |
| { |
| "epoch": 0.624, |
| "grad_norm": 8.057502746582031, |
| "learning_rate": 3.444e-05, |
| "loss": 0.23704848289489747, |
| "step": 390 |
| }, |
| { |
| "epoch": 0.64, |
| "grad_norm": 2.670377731323242, |
| "learning_rate": 3.404e-05, |
| "loss": 0.20256345272064208, |
| "step": 400 |
| }, |
| { |
| "epoch": 0.656, |
| "grad_norm": 5.436578273773193, |
| "learning_rate": 3.3639999999999996e-05, |
| "loss": 0.2178948402404785, |
| "step": 410 |
| }, |
| { |
| "epoch": 0.672, |
| "grad_norm": 2.7397665977478027, |
| "learning_rate": 3.324e-05, |
| "loss": 0.28787732124328613, |
| "step": 420 |
| }, |
| { |
| "epoch": 0.688, |
| "grad_norm": 7.691206455230713, |
| "learning_rate": 3.2840000000000004e-05, |
| "loss": 0.2569857358932495, |
| "step": 430 |
| }, |
| { |
| "epoch": 0.704, |
| "grad_norm": 2.859588623046875, |
| "learning_rate": 3.244e-05, |
| "loss": 0.21177470684051514, |
| "step": 440 |
| }, |
| { |
| "epoch": 0.72, |
| "grad_norm": 8.864638328552246, |
| "learning_rate": 3.2040000000000005e-05, |
| "loss": 0.21835825443267823, |
| "step": 450 |
| }, |
| { |
| "epoch": 0.736, |
| "grad_norm": 3.5713469982147217, |
| "learning_rate": 3.164e-05, |
| "loss": 0.18327864408493041, |
| "step": 460 |
| }, |
| { |
| "epoch": 0.752, |
| "grad_norm": 4.1505351066589355, |
| "learning_rate": 3.1240000000000006e-05, |
| "loss": 0.23397378921508788, |
| "step": 470 |
| }, |
| { |
| "epoch": 0.768, |
| "grad_norm": 7.102250099182129, |
| "learning_rate": 3.084e-05, |
| "loss": 0.2387765645980835, |
| "step": 480 |
| }, |
| { |
| "epoch": 0.784, |
| "grad_norm": 2.268003225326538, |
| "learning_rate": 3.0440000000000003e-05, |
| "loss": 0.24410586357116698, |
| "step": 490 |
| }, |
| { |
| "epoch": 0.8, |
| "grad_norm": 7.200525760650635, |
| "learning_rate": 3.004e-05, |
| "loss": 0.22940239906311036, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.816, |
| "grad_norm": 6.109457015991211, |
| "learning_rate": 2.964e-05, |
| "loss": 0.23941683769226074, |
| "step": 510 |
| }, |
| { |
| "epoch": 0.832, |
| "grad_norm": 2.041025400161743, |
| "learning_rate": 2.924e-05, |
| "loss": 0.2272693157196045, |
| "step": 520 |
| }, |
| { |
| "epoch": 0.848, |
| "grad_norm": 3.117744207382202, |
| "learning_rate": 2.8840000000000002e-05, |
| "loss": 0.3034891843795776, |
| "step": 530 |
| }, |
| { |
| "epoch": 0.864, |
| "grad_norm": 3.5636343955993652, |
| "learning_rate": 2.844e-05, |
| "loss": 0.22543411254882811, |
| "step": 540 |
| }, |
| { |
| "epoch": 0.88, |
| "grad_norm": 5.813530921936035, |
| "learning_rate": 2.804e-05, |
| "loss": 0.15515211820602418, |
| "step": 550 |
| }, |
| { |
| "epoch": 0.896, |
| "grad_norm": 3.961332082748413, |
| "learning_rate": 2.764e-05, |
| "loss": 0.18014708757400513, |
| "step": 560 |
| }, |
| { |
| "epoch": 0.912, |
| "grad_norm": 4.513957500457764, |
| "learning_rate": 2.724e-05, |
| "loss": 0.15350849628448487, |
| "step": 570 |
| }, |
| { |
| "epoch": 0.928, |
| "grad_norm": 4.664239406585693, |
| "learning_rate": 2.6840000000000004e-05, |
| "loss": 0.17080495357513428, |
| "step": 580 |
| }, |
| { |
| "epoch": 0.944, |
| "grad_norm": 4.640005588531494, |
| "learning_rate": 2.6440000000000004e-05, |
| "loss": 0.2014240026473999, |
| "step": 590 |
| }, |
| { |
| "epoch": 0.96, |
| "grad_norm": 4.601800441741943, |
| "learning_rate": 2.6040000000000005e-05, |
| "loss": 0.14860270023345948, |
| "step": 600 |
| }, |
| { |
| "epoch": 0.976, |
| "grad_norm": 3.3365046977996826, |
| "learning_rate": 2.5640000000000002e-05, |
| "loss": 0.16999433040618897, |
| "step": 610 |
| }, |
| { |
| "epoch": 0.992, |
| "grad_norm": 11.081926345825195, |
| "learning_rate": 2.5240000000000002e-05, |
| "loss": 0.2594302177429199, |
| "step": 620 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_loss": 0.18495811522006989, |
| "eval_runtime": 154.2281, |
| "eval_samples_per_second": 32.42, |
| "eval_steps_per_second": 1.018, |
| "step": 625 |
| }, |
| { |
| "epoch": 1.008, |
| "grad_norm": 1.409481406211853, |
| "learning_rate": 2.4840000000000003e-05, |
| "loss": 0.23080673217773437, |
| "step": 630 |
| }, |
| { |
| "epoch": 1.024, |
| "grad_norm": 3.118706703186035, |
| "learning_rate": 2.4440000000000003e-05, |
| "loss": 0.12968307733535767, |
| "step": 640 |
| }, |
| { |
| "epoch": 1.04, |
| "grad_norm": 4.754483699798584, |
| "learning_rate": 2.404e-05, |
| "loss": 0.11642718315124512, |
| "step": 650 |
| }, |
| { |
| "epoch": 1.056, |
| "grad_norm": 8.341479301452637, |
| "learning_rate": 2.364e-05, |
| "loss": 0.13068459033966065, |
| "step": 660 |
| }, |
| { |
| "epoch": 1.072, |
| "grad_norm": 4.099249362945557, |
| "learning_rate": 2.324e-05, |
| "loss": 0.16937563419342042, |
| "step": 670 |
| }, |
| { |
| "epoch": 1.088, |
| "grad_norm": 4.4017720222473145, |
| "learning_rate": 2.284e-05, |
| "loss": 0.1266240119934082, |
| "step": 680 |
| }, |
| { |
| "epoch": 1.104, |
| "grad_norm": 5.481026649475098, |
| "learning_rate": 2.244e-05, |
| "loss": 0.08416222333908081, |
| "step": 690 |
| }, |
| { |
| "epoch": 1.12, |
| "grad_norm": 4.0869140625, |
| "learning_rate": 2.2040000000000002e-05, |
| "loss": 0.13754202127456666, |
| "step": 700 |
| }, |
| { |
| "epoch": 1.1360000000000001, |
| "grad_norm": 12.687203407287598, |
| "learning_rate": 2.1640000000000003e-05, |
| "loss": 0.07033992409706116, |
| "step": 710 |
| }, |
| { |
| "epoch": 1.152, |
| "grad_norm": 2.744762897491455, |
| "learning_rate": 2.124e-05, |
| "loss": 0.10703094005584717, |
| "step": 720 |
| }, |
| { |
| "epoch": 1.168, |
| "grad_norm": 7.220569133758545, |
| "learning_rate": 2.084e-05, |
| "loss": 0.13606520891189575, |
| "step": 730 |
| }, |
| { |
| "epoch": 1.184, |
| "grad_norm": 6.549191474914551, |
| "learning_rate": 2.044e-05, |
| "loss": 0.13524794578552246, |
| "step": 740 |
| }, |
| { |
| "epoch": 1.2, |
| "grad_norm": 4.867711067199707, |
| "learning_rate": 2.004e-05, |
| "loss": 0.10759615898132324, |
| "step": 750 |
| }, |
| { |
| "epoch": 1.216, |
| "grad_norm": 4.896305561065674, |
| "learning_rate": 1.9640000000000002e-05, |
| "loss": 0.10973103046417236, |
| "step": 760 |
| }, |
| { |
| "epoch": 1.232, |
| "grad_norm": 10.444025039672852, |
| "learning_rate": 1.924e-05, |
| "loss": 0.05662683844566345, |
| "step": 770 |
| }, |
| { |
| "epoch": 1.248, |
| "grad_norm": 15.567150115966797, |
| "learning_rate": 1.8840000000000003e-05, |
| "loss": 0.11076383590698242, |
| "step": 780 |
| }, |
| { |
| "epoch": 1.264, |
| "grad_norm": 2.87619948387146, |
| "learning_rate": 1.8440000000000003e-05, |
| "loss": 0.09802154898643493, |
| "step": 790 |
| }, |
| { |
| "epoch": 1.28, |
| "grad_norm": 9.998023986816406, |
| "learning_rate": 1.804e-05, |
| "loss": 0.1250164270401001, |
| "step": 800 |
| }, |
| { |
| "epoch": 1.296, |
| "grad_norm": 7.159102439880371, |
| "learning_rate": 1.764e-05, |
| "loss": 0.09611091613769532, |
| "step": 810 |
| }, |
| { |
| "epoch": 1.312, |
| "grad_norm": 8.660289764404297, |
| "learning_rate": 1.724e-05, |
| "loss": 0.1441337823867798, |
| "step": 820 |
| }, |
| { |
| "epoch": 1.328, |
| "grad_norm": 5.77480936050415, |
| "learning_rate": 1.684e-05, |
| "loss": 0.15176002979278563, |
| "step": 830 |
| }, |
| { |
| "epoch": 1.3439999999999999, |
| "grad_norm": 4.082831382751465, |
| "learning_rate": 1.644e-05, |
| "loss": 0.08848962783813477, |
| "step": 840 |
| }, |
| { |
| "epoch": 1.3599999999999999, |
| "grad_norm": 2.577115774154663, |
| "learning_rate": 1.604e-05, |
| "loss": 0.10309876203536987, |
| "step": 850 |
| }, |
| { |
| "epoch": 1.376, |
| "grad_norm": 3.0724472999572754, |
| "learning_rate": 1.5640000000000003e-05, |
| "loss": 0.10082556009292602, |
| "step": 860 |
| }, |
| { |
| "epoch": 1.392, |
| "grad_norm": 3.345585584640503, |
| "learning_rate": 1.5240000000000001e-05, |
| "loss": 0.0675260603427887, |
| "step": 870 |
| }, |
| { |
| "epoch": 1.408, |
| "grad_norm": 1.7632936239242554, |
| "learning_rate": 1.4840000000000002e-05, |
| "loss": 0.11104966402053833, |
| "step": 880 |
| }, |
| { |
| "epoch": 1.424, |
| "grad_norm": 9.795392990112305, |
| "learning_rate": 1.444e-05, |
| "loss": 0.1164703130722046, |
| "step": 890 |
| }, |
| { |
| "epoch": 1.44, |
| "grad_norm": 0.41051211953163147, |
| "learning_rate": 1.4040000000000001e-05, |
| "loss": 0.09447898268699646, |
| "step": 900 |
| }, |
| { |
| "epoch": 1.456, |
| "grad_norm": 4.203612804412842, |
| "learning_rate": 1.364e-05, |
| "loss": 0.14231808185577394, |
| "step": 910 |
| }, |
| { |
| "epoch": 1.472, |
| "grad_norm": 7.408661842346191, |
| "learning_rate": 1.324e-05, |
| "loss": 0.06679580807685852, |
| "step": 920 |
| }, |
| { |
| "epoch": 1.488, |
| "grad_norm": 7.812554359436035, |
| "learning_rate": 1.2839999999999999e-05, |
| "loss": 0.08085909485816956, |
| "step": 930 |
| }, |
| { |
| "epoch": 1.504, |
| "grad_norm": 8.036355972290039, |
| "learning_rate": 1.244e-05, |
| "loss": 0.14998269081115723, |
| "step": 940 |
| }, |
| { |
| "epoch": 1.52, |
| "grad_norm": 2.2026758193969727, |
| "learning_rate": 1.204e-05, |
| "loss": 0.09423889517784119, |
| "step": 950 |
| }, |
| { |
| "epoch": 1.536, |
| "grad_norm": 7.581295490264893, |
| "learning_rate": 1.164e-05, |
| "loss": 0.07243572473526001, |
| "step": 960 |
| }, |
| { |
| "epoch": 1.552, |
| "grad_norm": 7.5626935958862305, |
| "learning_rate": 1.124e-05, |
| "loss": 0.1211039662361145, |
| "step": 970 |
| }, |
| { |
| "epoch": 1.568, |
| "grad_norm": 8.267356872558594, |
| "learning_rate": 1.084e-05, |
| "loss": 0.0996507465839386, |
| "step": 980 |
| }, |
| { |
| "epoch": 1.584, |
| "grad_norm": 0.8569573760032654, |
| "learning_rate": 1.0440000000000002e-05, |
| "loss": 0.036824467778205874, |
| "step": 990 |
| }, |
| { |
| "epoch": 1.6, |
| "grad_norm": 2.5389115810394287, |
| "learning_rate": 1.004e-05, |
| "loss": 0.11773452758789063, |
| "step": 1000 |
| }, |
| { |
| "epoch": 1.616, |
| "grad_norm": 2.706822156906128, |
| "learning_rate": 9.640000000000001e-06, |
| "loss": 0.19166380167007446, |
| "step": 1010 |
| }, |
| { |
| "epoch": 1.6320000000000001, |
| "grad_norm": 9.506473541259766, |
| "learning_rate": 9.24e-06, |
| "loss": 0.16758540868759156, |
| "step": 1020 |
| }, |
| { |
| "epoch": 1.6480000000000001, |
| "grad_norm": 0.3241702616214752, |
| "learning_rate": 8.840000000000002e-06, |
| "loss": 0.1203872561454773, |
| "step": 1030 |
| }, |
| { |
| "epoch": 1.6640000000000001, |
| "grad_norm": 3.3109052181243896, |
| "learning_rate": 8.44e-06, |
| "loss": 0.0420354425907135, |
| "step": 1040 |
| }, |
| { |
| "epoch": 1.6800000000000002, |
| "grad_norm": 8.419422149658203, |
| "learning_rate": 8.040000000000001e-06, |
| "loss": 0.10436058044433594, |
| "step": 1050 |
| }, |
| { |
| "epoch": 1.696, |
| "grad_norm": 1.2641408443450928, |
| "learning_rate": 7.64e-06, |
| "loss": 0.09875598549842834, |
| "step": 1060 |
| }, |
| { |
| "epoch": 1.712, |
| "grad_norm": 1.592099666595459, |
| "learning_rate": 7.240000000000001e-06, |
| "loss": 0.07384807467460633, |
| "step": 1070 |
| }, |
| { |
| "epoch": 1.728, |
| "grad_norm": 2.490544557571411, |
| "learning_rate": 6.840000000000001e-06, |
| "loss": 0.1242129921913147, |
| "step": 1080 |
| }, |
| { |
| "epoch": 1.744, |
| "grad_norm": 5.5718889236450195, |
| "learning_rate": 6.44e-06, |
| "loss": 0.11525803804397583, |
| "step": 1090 |
| }, |
| { |
| "epoch": 1.76, |
| "grad_norm": 6.5801520347595215, |
| "learning_rate": 6.040000000000001e-06, |
| "loss": 0.0572867214679718, |
| "step": 1100 |
| }, |
| { |
| "epoch": 1.776, |
| "grad_norm": 0.25566336512565613, |
| "learning_rate": 5.64e-06, |
| "loss": 0.06712960004806519, |
| "step": 1110 |
| }, |
| { |
| "epoch": 1.792, |
| "grad_norm": 5.010447978973389, |
| "learning_rate": 5.240000000000001e-06, |
| "loss": 0.09681461453437805, |
| "step": 1120 |
| }, |
| { |
| "epoch": 1.808, |
| "grad_norm": 7.9100751876831055, |
| "learning_rate": 4.84e-06, |
| "loss": 0.07983118295669556, |
| "step": 1130 |
| }, |
| { |
| "epoch": 1.8239999999999998, |
| "grad_norm": 2.053251028060913, |
| "learning_rate": 4.440000000000001e-06, |
| "loss": 0.05444978475570679, |
| "step": 1140 |
| }, |
| { |
| "epoch": 1.8399999999999999, |
| "grad_norm": 1.8897933959960938, |
| "learning_rate": 4.04e-06, |
| "loss": 0.10996910333633422, |
| "step": 1150 |
| }, |
| { |
| "epoch": 1.8559999999999999, |
| "grad_norm": 7.506521224975586, |
| "learning_rate": 3.6400000000000003e-06, |
| "loss": 0.10293327569961548, |
| "step": 1160 |
| }, |
| { |
| "epoch": 1.8719999999999999, |
| "grad_norm": 7.165153980255127, |
| "learning_rate": 3.24e-06, |
| "loss": 0.13498435020446778, |
| "step": 1170 |
| }, |
| { |
| "epoch": 1.888, |
| "grad_norm": 5.471543312072754, |
| "learning_rate": 2.8400000000000003e-06, |
| "loss": 0.14159295558929444, |
| "step": 1180 |
| }, |
| { |
| "epoch": 1.904, |
| "grad_norm": 1.521297574043274, |
| "learning_rate": 2.4400000000000004e-06, |
| "loss": 0.12328060865402221, |
| "step": 1190 |
| }, |
| { |
| "epoch": 1.92, |
| "grad_norm": 5.420016288757324, |
| "learning_rate": 2.0400000000000004e-06, |
| "loss": 0.0512222945690155, |
| "step": 1200 |
| }, |
| { |
| "epoch": 1.936, |
| "grad_norm": 4.897031784057617, |
| "learning_rate": 1.6400000000000002e-06, |
| "loss": 0.09001591801643372, |
| "step": 1210 |
| }, |
| { |
| "epoch": 1.952, |
| "grad_norm": 2.213510036468506, |
| "learning_rate": 1.24e-06, |
| "loss": 0.11251969337463379, |
| "step": 1220 |
| }, |
| { |
| "epoch": 1.968, |
| "grad_norm": 0.9154443740844727, |
| "learning_rate": 8.4e-07, |
| "loss": 0.12515219449996948, |
| "step": 1230 |
| }, |
| { |
| "epoch": 1.984, |
| "grad_norm": 13.852690696716309, |
| "learning_rate": 4.4e-07, |
| "loss": 0.07310597896575928, |
| "step": 1240 |
| }, |
| { |
| "epoch": 2.0, |
| "grad_norm": 2.5578453540802, |
| "learning_rate": 4e-08, |
| "loss": 0.132768714427948, |
| "step": 1250 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_loss": 0.18955644965171814, |
| "eval_runtime": 154.3037, |
| "eval_samples_per_second": 32.404, |
| "eval_steps_per_second": 1.017, |
| "step": 1250 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 1250, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 2, |
| "save_steps": 500, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 1.05244422144e+16, |
| "train_batch_size": 32, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
