| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.9781021897810218, | |
| "eval_steps": 20, | |
| "global_step": 136, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.014598540145985401, | |
| "grad_norm": 5.558824092078288, | |
| "learning_rate": 1e-05, | |
| "loss": 0.7048, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.029197080291970802, | |
| "grad_norm": 5.39781753446926, | |
| "learning_rate": 2e-05, | |
| "loss": 0.706, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.043795620437956206, | |
| "grad_norm": 2.5767987530959293, | |
| "learning_rate": 3e-05, | |
| "loss": 0.6427, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.058394160583941604, | |
| "grad_norm": 5.332582144004997, | |
| "learning_rate": 4e-05, | |
| "loss": 0.7227, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.072992700729927, | |
| "grad_norm": 6.654038960215542, | |
| "learning_rate": 5e-05, | |
| "loss": 0.8235, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.08759124087591241, | |
| "grad_norm": 6.676666009964554, | |
| "learning_rate": 4.9992811366328926e-05, | |
| "loss": 0.8702, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.10218978102189781, | |
| "grad_norm": 4.274269796378038, | |
| "learning_rate": 4.997124959943201e-05, | |
| "loss": 0.7634, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.11678832116788321, | |
| "grad_norm": 9.488201233376888, | |
| "learning_rate": 4.993532709928075e-05, | |
| "loss": 0.7925, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.13138686131386862, | |
| "grad_norm": 5.052354667424013, | |
| "learning_rate": 4.9885064524570665e-05, | |
| "loss": 0.7246, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.145985401459854, | |
| "grad_norm": 1.5775620837406379, | |
| "learning_rate": 4.982049078084071e-05, | |
| "loss": 0.6298, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.16058394160583941, | |
| "grad_norm": 2.0338294097415694, | |
| "learning_rate": 4.974164300384998e-05, | |
| "loss": 0.5719, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.17518248175182483, | |
| "grad_norm": 1.4271467759265182, | |
| "learning_rate": 4.964856653822122e-05, | |
| "loss": 0.5577, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.1897810218978102, | |
| "grad_norm": 1.4553670927449545, | |
| "learning_rate": 4.954131491136362e-05, | |
| "loss": 0.484, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.20437956204379562, | |
| "grad_norm": 1.270113333054875, | |
| "learning_rate": 4.9419949802689666e-05, | |
| "loss": 0.4394, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.21897810218978103, | |
| "grad_norm": 1.2876560129600205, | |
| "learning_rate": 4.92845410081439e-05, | |
| "loss": 0.4575, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.23357664233576642, | |
| "grad_norm": 1.3643309071212184, | |
| "learning_rate": 4.913516640006392e-05, | |
| "loss": 0.4642, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.24817518248175183, | |
| "grad_norm": 1.1729936051973566, | |
| "learning_rate": 4.897191188239667e-05, | |
| "loss": 0.434, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.26277372262773724, | |
| "grad_norm": 1.1621979050371054, | |
| "learning_rate": 4.8794871341296e-05, | |
| "loss": 0.405, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.2773722627737226, | |
| "grad_norm": 1.1218709581501245, | |
| "learning_rate": 4.8604146591129485e-05, | |
| "loss": 0.3909, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.291970802919708, | |
| "grad_norm": 1.0395959826090466, | |
| "learning_rate": 4.8399847315926e-05, | |
| "loss": 0.4086, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.291970802919708, | |
| "eval_loss": 0.5058628916740417, | |
| "eval_runtime": 2.3522, | |
| "eval_samples_per_second": 30.184, | |
| "eval_steps_per_second": 1.275, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.30656934306569344, | |
| "grad_norm": 1.1417380012049692, | |
| "learning_rate": 4.818209100629745e-05, | |
| "loss": 0.3901, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.32116788321167883, | |
| "grad_norm": 1.0254963744794567, | |
| "learning_rate": 4.795100289187099e-05, | |
| "loss": 0.3723, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.3357664233576642, | |
| "grad_norm": 1.0470804323692136, | |
| "learning_rate": 4.7706715869270635e-05, | |
| "loss": 0.3757, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.35036496350364965, | |
| "grad_norm": 0.9566801844725584, | |
| "learning_rate": 4.74493704256897e-05, | |
| "loss": 0.377, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.36496350364963503, | |
| "grad_norm": 0.8719622478856044, | |
| "learning_rate": 4.717911455809782e-05, | |
| "loss": 0.3599, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.3795620437956204, | |
| "grad_norm": 0.8993416168257213, | |
| "learning_rate": 4.6896103688129385e-05, | |
| "loss": 0.3235, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.39416058394160586, | |
| "grad_norm": 0.9295183450455919, | |
| "learning_rate": 4.660050057270191e-05, | |
| "loss": 0.3538, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.40875912408759124, | |
| "grad_norm": 0.8210997173864658, | |
| "learning_rate": 4.6292475210416106e-05, | |
| "loss": 0.347, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.4233576642335766, | |
| "grad_norm": 0.9109711747983845, | |
| "learning_rate": 4.597220474379125e-05, | |
| "loss": 0.3239, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.43795620437956206, | |
| "grad_norm": 0.917876136961733, | |
| "learning_rate": 4.563987335739216e-05, | |
| "loss": 0.3172, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.45255474452554745, | |
| "grad_norm": 0.8348657603950833, | |
| "learning_rate": 4.5295672171906364e-05, | |
| "loss": 0.3161, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.46715328467153283, | |
| "grad_norm": 0.9628144830881412, | |
| "learning_rate": 4.49397991342324e-05, | |
| "loss": 0.3231, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.48175182481751827, | |
| "grad_norm": 0.8758205697486683, | |
| "learning_rate": 4.4572458903642354e-05, | |
| "loss": 0.3305, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.49635036496350365, | |
| "grad_norm": 0.8177550425000464, | |
| "learning_rate": 4.419386273408428e-05, | |
| "loss": 0.3384, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.5109489051094891, | |
| "grad_norm": 0.7707655080363717, | |
| "learning_rate": 4.3804228352691935e-05, | |
| "loss": 0.3178, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.5255474452554745, | |
| "grad_norm": 0.8191298252366446, | |
| "learning_rate": 4.3403779834572004e-05, | |
| "loss": 0.3346, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.5401459854014599, | |
| "grad_norm": 0.9406397953710217, | |
| "learning_rate": 4.2992747473940556e-05, | |
| "loss": 0.3268, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.5547445255474452, | |
| "grad_norm": 0.757783885677172, | |
| "learning_rate": 4.2571367651683e-05, | |
| "loss": 0.2861, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.5693430656934306, | |
| "grad_norm": 0.7275760878949353, | |
| "learning_rate": 4.213988269941362e-05, | |
| "loss": 0.2516, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.583941605839416, | |
| "grad_norm": 0.9299663609616579, | |
| "learning_rate": 4.169854076011292e-05, | |
| "loss": 0.2844, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.583941605839416, | |
| "eval_loss": 0.5329129099845886, | |
| "eval_runtime": 1.6671, | |
| "eval_samples_per_second": 42.589, | |
| "eval_steps_per_second": 1.8, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.5985401459854015, | |
| "grad_norm": 0.7884853681211518, | |
| "learning_rate": 4.124759564542295e-05, | |
| "loss": 0.2759, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.6131386861313869, | |
| "grad_norm": 0.7356673142072975, | |
| "learning_rate": 4.078730668968253e-05, | |
| "loss": 0.2614, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.6277372262773723, | |
| "grad_norm": 0.7411930478686042, | |
| "learning_rate": 4.031793860078649e-05, | |
| "loss": 0.2577, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.6423357664233577, | |
| "grad_norm": 0.6945647014688631, | |
| "learning_rate": 3.9839761307954675e-05, | |
| "loss": 0.2518, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.656934306569343, | |
| "grad_norm": 0.758841305493356, | |
| "learning_rate": 3.935304980649813e-05, | |
| "loss": 0.3, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.6715328467153284, | |
| "grad_norm": 0.7083671932224866, | |
| "learning_rate": 3.8858083999671855e-05, | |
| "loss": 0.2604, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.6861313868613139, | |
| "grad_norm": 0.7105677438159481, | |
| "learning_rate": 3.835514853770505e-05, | |
| "loss": 0.2716, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.7007299270072993, | |
| "grad_norm": 0.6955300432925063, | |
| "learning_rate": 3.784453265410141e-05, | |
| "loss": 0.2535, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.7153284671532847, | |
| "grad_norm": 0.6251239165395376, | |
| "learning_rate": 3.732652999930364e-05, | |
| "loss": 0.2341, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.7299270072992701, | |
| "grad_norm": 0.7101720555562038, | |
| "learning_rate": 3.680143847181783e-05, | |
| "loss": 0.2702, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.7445255474452555, | |
| "grad_norm": 0.7982281837079658, | |
| "learning_rate": 3.6269560046894766e-05, | |
| "loss": 0.2579, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.7591240875912408, | |
| "grad_norm": 0.6679783854698054, | |
| "learning_rate": 3.573120060286679e-05, | |
| "loss": 0.2287, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.7737226277372263, | |
| "grad_norm": 0.6971062669945208, | |
| "learning_rate": 3.5186669745240026e-05, | |
| "loss": 0.2501, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.7883211678832117, | |
| "grad_norm": 0.6212428454824916, | |
| "learning_rate": 3.463628062864312e-05, | |
| "loss": 0.2195, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.8029197080291971, | |
| "grad_norm": 0.6621251726886289, | |
| "learning_rate": 3.4080349776734925e-05, | |
| "loss": 0.2243, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.8175182481751825, | |
| "grad_norm": 0.618969299596716, | |
| "learning_rate": 3.351919690017473e-05, | |
| "loss": 0.2184, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.8321167883211679, | |
| "grad_norm": 0.6210248745374214, | |
| "learning_rate": 3.2953144712759545e-05, | |
| "loss": 0.2255, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.8467153284671532, | |
| "grad_norm": 0.648626857719657, | |
| "learning_rate": 3.238251874583452e-05, | |
| "loss": 0.24, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.8613138686131386, | |
| "grad_norm": 0.6442995895157195, | |
| "learning_rate": 3.1807647161082795e-05, | |
| "loss": 0.2246, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.8759124087591241, | |
| "grad_norm": 0.5822022754916901, | |
| "learning_rate": 3.122886056180284e-05, | |
| "loss": 0.232, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.8759124087591241, | |
| "eval_loss": 0.5338236093521118, | |
| "eval_runtime": 1.6696, | |
| "eval_samples_per_second": 42.525, | |
| "eval_steps_per_second": 1.797, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.8905109489051095, | |
| "grad_norm": 0.6753004591751348, | |
| "learning_rate": 3.064649180278152e-05, | |
| "loss": 0.2636, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.9051094890510949, | |
| "grad_norm": 0.6326351355678477, | |
| "learning_rate": 3.006087579887244e-05, | |
| "loss": 0.2112, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.9197080291970803, | |
| "grad_norm": 0.5944744601386913, | |
| "learning_rate": 2.9472349332389525e-05, | |
| "loss": 0.1924, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.9343065693430657, | |
| "grad_norm": 0.6089460479407833, | |
| "learning_rate": 2.8881250859426646e-05, | |
| "loss": 0.2254, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.948905109489051, | |
| "grad_norm": 0.5901015804515078, | |
| "learning_rate": 2.8287920315214643e-05, | |
| "loss": 0.2074, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.9635036496350365, | |
| "grad_norm": 0.5482779301116911, | |
| "learning_rate": 2.7692698918627778e-05, | |
| "loss": 0.1833, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.9781021897810219, | |
| "grad_norm": 0.619204984698149, | |
| "learning_rate": 2.7095928975951913e-05, | |
| "loss": 0.2125, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.9927007299270073, | |
| "grad_norm": 0.5754857994127854, | |
| "learning_rate": 2.649795368402735e-05, | |
| "loss": 0.2373, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 0.5754857994127854, | |
| "learning_rate": 2.649795368402735e-05, | |
| "loss": 0.1027, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 1.0145985401459854, | |
| "grad_norm": 0.5481032621072542, | |
| "learning_rate": 2.5899116932879534e-05, | |
| "loss": 0.1039, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 1.0291970802919708, | |
| "grad_norm": 0.44573568671990305, | |
| "learning_rate": 2.529976310795108e-05, | |
| "loss": 0.1075, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 1.0437956204379562, | |
| "grad_norm": 0.46800129257717743, | |
| "learning_rate": 2.470023689204893e-05, | |
| "loss": 0.1053, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 1.0583941605839415, | |
| "grad_norm": 0.5217427141578048, | |
| "learning_rate": 2.4100883067120475e-05, | |
| "loss": 0.1048, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 1.072992700729927, | |
| "grad_norm": 0.46349892807310117, | |
| "learning_rate": 2.3502046315972656e-05, | |
| "loss": 0.0987, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 1.0875912408759123, | |
| "grad_norm": 0.4835213983318123, | |
| "learning_rate": 2.290407102404809e-05, | |
| "loss": 0.0836, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 1.102189781021898, | |
| "grad_norm": 0.5194340907634253, | |
| "learning_rate": 2.2307301081372224e-05, | |
| "loss": 0.1159, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 1.1167883211678833, | |
| "grad_norm": 0.5807960446197283, | |
| "learning_rate": 2.1712079684785363e-05, | |
| "loss": 0.0816, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 1.1313868613138687, | |
| "grad_norm": 0.5578387906848328, | |
| "learning_rate": 2.111874914057336e-05, | |
| "loss": 0.1141, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 1.145985401459854, | |
| "grad_norm": 0.5639933149192473, | |
| "learning_rate": 2.0527650667610478e-05, | |
| "loss": 0.1146, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 1.1605839416058394, | |
| "grad_norm": 0.5239001485998342, | |
| "learning_rate": 1.993912420112756e-05, | |
| "loss": 0.0847, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 1.1605839416058394, | |
| "eval_loss": 0.6174606084823608, | |
| "eval_runtime": 1.6663, | |
| "eval_samples_per_second": 42.61, | |
| "eval_steps_per_second": 1.8, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 1.1751824817518248, | |
| "grad_norm": 0.4929761742504611, | |
| "learning_rate": 1.935350819721849e-05, | |
| "loss": 0.1019, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 1.1897810218978102, | |
| "grad_norm": 0.5544859652703089, | |
| "learning_rate": 1.8771139438197168e-05, | |
| "loss": 0.1077, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 1.2043795620437956, | |
| "grad_norm": 0.5164965039818554, | |
| "learning_rate": 1.819235283891721e-05, | |
| "loss": 0.091, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 1.218978102189781, | |
| "grad_norm": 0.49567303589016076, | |
| "learning_rate": 1.7617481254165487e-05, | |
| "loss": 0.1081, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 1.2335766423357664, | |
| "grad_norm": 0.4587304943562019, | |
| "learning_rate": 1.704685528724046e-05, | |
| "loss": 0.1087, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 1.2481751824817517, | |
| "grad_norm": 0.5758635229758376, | |
| "learning_rate": 1.648080309982528e-05, | |
| "loss": 0.1094, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 1.2627737226277373, | |
| "grad_norm": 0.4790913429309353, | |
| "learning_rate": 1.591965022326507e-05, | |
| "loss": 0.1018, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 1.2773722627737225, | |
| "grad_norm": 0.42743049770737657, | |
| "learning_rate": 1.536371937135688e-05, | |
| "loss": 0.0921, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 1.2919708029197081, | |
| "grad_norm": 0.4874948888356134, | |
| "learning_rate": 1.4813330254759985e-05, | |
| "loss": 0.1044, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 1.3065693430656935, | |
| "grad_norm": 0.4772485634630385, | |
| "learning_rate": 1.426879939713322e-05, | |
| "loss": 0.0816, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 1.3211678832116789, | |
| "grad_norm": 0.40079927908899615, | |
| "learning_rate": 1.3730439953105243e-05, | |
| "loss": 0.0842, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 1.3357664233576643, | |
| "grad_norm": 0.4275504239180154, | |
| "learning_rate": 1.3198561528182183e-05, | |
| "loss": 0.0744, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 1.3503649635036497, | |
| "grad_norm": 0.3793648773284397, | |
| "learning_rate": 1.2673470000696364e-05, | |
| "loss": 0.1033, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 1.364963503649635, | |
| "grad_norm": 0.5181460659792264, | |
| "learning_rate": 1.2155467345898602e-05, | |
| "loss": 0.1001, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 1.3795620437956204, | |
| "grad_norm": 0.45318669096336833, | |
| "learning_rate": 1.1644851462294957e-05, | |
| "loss": 0.101, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 1.3941605839416058, | |
| "grad_norm": 0.4766867331350184, | |
| "learning_rate": 1.114191600032815e-05, | |
| "loss": 0.0863, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 1.4087591240875912, | |
| "grad_norm": 0.4080689197803639, | |
| "learning_rate": 1.064695019350187e-05, | |
| "loss": 0.0855, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 1.4233576642335766, | |
| "grad_norm": 0.4653770430519792, | |
| "learning_rate": 1.0160238692045332e-05, | |
| "loss": 0.111, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 1.437956204379562, | |
| "grad_norm": 0.45097632263026527, | |
| "learning_rate": 9.682061399213525e-06, | |
| "loss": 0.0939, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 1.4525547445255476, | |
| "grad_norm": 0.4496977114474888, | |
| "learning_rate": 9.21269331031748e-06, | |
| "loss": 0.0882, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.4525547445255476, | |
| "eval_loss": 0.5955010652542114, | |
| "eval_runtime": 1.6733, | |
| "eval_samples_per_second": 42.432, | |
| "eval_steps_per_second": 1.793, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.4671532846715327, | |
| "grad_norm": 0.45643797377810924, | |
| "learning_rate": 8.752404354577052e-06, | |
| "loss": 0.0937, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 1.4817518248175183, | |
| "grad_norm": 0.38809063898842117, | |
| "learning_rate": 8.301459239887074e-06, | |
| "loss": 0.0803, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 1.4963503649635037, | |
| "grad_norm": 0.4599787928563747, | |
| "learning_rate": 7.860117300586383e-06, | |
| "loss": 0.1008, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 1.510948905109489, | |
| "grad_norm": 0.4265168032214748, | |
| "learning_rate": 7.428632348317005e-06, | |
| "loss": 0.0731, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 1.5255474452554745, | |
| "grad_norm": 0.4408034300546994, | |
| "learning_rate": 7.007252526059446e-06, | |
| "loss": 0.075, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 1.5401459854014599, | |
| "grad_norm": 0.36837598605703786, | |
| "learning_rate": 6.596220165428002e-06, | |
| "loss": 0.0797, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 1.5547445255474452, | |
| "grad_norm": 0.45686833811722544, | |
| "learning_rate": 6.195771647308074e-06, | |
| "loss": 0.1031, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 1.5693430656934306, | |
| "grad_norm": 0.43293441847585606, | |
| "learning_rate": 5.806137265915732e-06, | |
| "loss": 0.0876, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 1.583941605839416, | |
| "grad_norm": 0.4018622232704113, | |
| "learning_rate": 5.427541096357647e-06, | |
| "loss": 0.0859, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 1.5985401459854014, | |
| "grad_norm": 0.42651961163568564, | |
| "learning_rate": 5.060200865767606e-06, | |
| "loss": 0.0914, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 1.613138686131387, | |
| "grad_norm": 0.45501350150501924, | |
| "learning_rate": 4.704327828093641e-06, | |
| "loss": 0.0891, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 1.6277372262773722, | |
| "grad_norm": 0.4018716741861915, | |
| "learning_rate": 4.3601266426078426e-06, | |
| "loss": 0.0802, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 1.6423357664233578, | |
| "grad_norm": 0.4381477464449764, | |
| "learning_rate": 4.02779525620875e-06, | |
| "loss": 0.0837, | |
| "step": 113 | |
| }, | |
| { | |
| "epoch": 1.656934306569343, | |
| "grad_norm": 0.38056775027295703, | |
| "learning_rate": 3.707524789583891e-06, | |
| "loss": 0.0733, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 1.6715328467153285, | |
| "grad_norm": 0.38615940067266047, | |
| "learning_rate": 3.3994994272980946e-06, | |
| "loss": 0.0816, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 1.686131386861314, | |
| "grad_norm": 0.4083027079839302, | |
| "learning_rate": 3.1038963118706244e-06, | |
| "loss": 0.0947, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 1.7007299270072993, | |
| "grad_norm": 0.4281395329269055, | |
| "learning_rate": 2.8208854419021824e-06, | |
| "loss": 0.0807, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 1.7153284671532847, | |
| "grad_norm": 0.33771309316638104, | |
| "learning_rate": 2.5506295743103094e-06, | |
| "loss": 0.0576, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 1.72992700729927, | |
| "grad_norm": 0.3862388702821623, | |
| "learning_rate": 2.2932841307293644e-06, | |
| "loss": 0.0857, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 1.7445255474452555, | |
| "grad_norm": 0.3825839529168523, | |
| "learning_rate": 2.0489971081290195e-06, | |
| "loss": 0.0868, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 1.7445255474452555, | |
| "eval_loss": 0.6069221496582031, | |
| "eval_runtime": 1.6811, | |
| "eval_samples_per_second": 42.233, | |
| "eval_steps_per_second": 1.785, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 1.7591240875912408, | |
| "grad_norm": 0.40516989643017143, | |
| "learning_rate": 1.817908993702555e-06, | |
| "loss": 0.0781, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 1.7737226277372264, | |
| "grad_norm": 0.37108997015823786, | |
| "learning_rate": 1.6001526840740049e-06, | |
| "loss": 0.0773, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 1.7883211678832116, | |
| "grad_norm": 0.4152153354127059, | |
| "learning_rate": 1.3958534088705206e-06, | |
| "loss": 0.0648, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 1.8029197080291972, | |
| "grad_norm": 0.3350032112266357, | |
| "learning_rate": 1.205128658704005e-06, | |
| "loss": 0.0685, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 1.8175182481751824, | |
| "grad_norm": 0.37253550313302386, | |
| "learning_rate": 1.028088117603332e-06, | |
| "loss": 0.0597, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 1.832116788321168, | |
| "grad_norm": 0.3646815056116574, | |
| "learning_rate": 8.648335999360935e-07, | |
| "loss": 0.0851, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 1.8467153284671531, | |
| "grad_norm": 0.40006480391539845, | |
| "learning_rate": 7.154589918561022e-07, | |
| "loss": 0.0775, | |
| "step": 127 | |
| }, | |
| { | |
| "epoch": 1.8613138686131387, | |
| "grad_norm": 0.3998882921725406, | |
| "learning_rate": 5.800501973103362e-07, | |
| "loss": 0.0837, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 1.8759124087591241, | |
| "grad_norm": 0.45939594997920835, | |
| "learning_rate": 4.586850886363875e-07, | |
| "loss": 0.104, | |
| "step": 129 | |
| }, | |
| { | |
| "epoch": 1.8905109489051095, | |
| "grad_norm": 0.415499645321787, | |
| "learning_rate": 3.514334617787857e-07, | |
| "loss": 0.0694, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 1.905109489051095, | |
| "grad_norm": 0.3572513685399802, | |
| "learning_rate": 2.5835699615002764e-07, | |
| "loss": 0.0617, | |
| "step": 131 | |
| }, | |
| { | |
| "epoch": 1.9197080291970803, | |
| "grad_norm": 0.3824291555094829, | |
| "learning_rate": 1.7950921915928788e-07, | |
| "loss": 0.0792, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 1.9343065693430657, | |
| "grad_norm": 0.42192592913917887, | |
| "learning_rate": 1.1493547542933969e-07, | |
| "loss": 0.0919, | |
| "step": 133 | |
| }, | |
| { | |
| "epoch": 1.948905109489051, | |
| "grad_norm": 0.40497490119047314, | |
| "learning_rate": 6.467290071925647e-08, | |
| "loss": 0.0655, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 1.9635036496350367, | |
| "grad_norm": 0.3653261951630353, | |
| "learning_rate": 2.8750400567992274e-08, | |
| "loss": 0.0607, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 1.9781021897810218, | |
| "grad_norm": 0.40679528870310416, | |
| "learning_rate": 7.188633671079137e-09, | |
| "loss": 0.0823, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 1.9781021897810218, | |
| "step": 136, | |
| "total_flos": 89096184856576.0, | |
| "train_loss": 0.23073186133714282, | |
| "train_runtime": 917.4487, | |
| "train_samples_per_second": 11.959, | |
| "train_steps_per_second": 0.148 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 136, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "save_steps": 1, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 89096184856576.0, | |
| "train_batch_size": 5, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |