EthioLLM-b-70k / trainer_state.json
Seid Muhie Yimam
ethio-xlmr base
07fad2a
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 6.621639517944643,
"eval_steps": 500,
"global_step": 100000,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.03,
"learning_rate": 4.983445901205139e-05,
"loss": 7.9646,
"step": 500
},
{
"epoch": 0.07,
"learning_rate": 4.9668918024102774e-05,
"loss": 7.067,
"step": 1000
},
{
"epoch": 0.1,
"learning_rate": 4.950337703615415e-05,
"loss": 6.6489,
"step": 1500
},
{
"epoch": 0.13,
"learning_rate": 4.933783604820554e-05,
"loss": 6.4267,
"step": 2000
},
{
"epoch": 0.17,
"learning_rate": 4.9172295060256924e-05,
"loss": 6.2394,
"step": 2500
},
{
"epoch": 0.2,
"learning_rate": 4.900675407230831e-05,
"loss": 6.1117,
"step": 3000
},
{
"epoch": 0.23,
"learning_rate": 4.884121308435969e-05,
"loss": 5.9807,
"step": 3500
},
{
"epoch": 0.26,
"learning_rate": 4.8675672096411075e-05,
"loss": 5.8532,
"step": 4000
},
{
"epoch": 0.3,
"learning_rate": 4.851013110846246e-05,
"loss": 5.7589,
"step": 4500
},
{
"epoch": 0.33,
"learning_rate": 4.8344590120513846e-05,
"loss": 5.661,
"step": 5000
},
{
"epoch": 0.36,
"learning_rate": 4.8179049132565225e-05,
"loss": 5.5663,
"step": 5500
},
{
"epoch": 0.4,
"learning_rate": 4.801350814461661e-05,
"loss": 5.5025,
"step": 6000
},
{
"epoch": 0.43,
"learning_rate": 4.7847967156667996e-05,
"loss": 5.4251,
"step": 6500
},
{
"epoch": 0.46,
"learning_rate": 4.768242616871938e-05,
"loss": 5.35,
"step": 7000
},
{
"epoch": 0.5,
"learning_rate": 4.751688518077076e-05,
"loss": 5.2991,
"step": 7500
},
{
"epoch": 0.53,
"learning_rate": 4.735134419282215e-05,
"loss": 5.2476,
"step": 8000
},
{
"epoch": 0.56,
"learning_rate": 4.718580320487353e-05,
"loss": 5.1949,
"step": 8500
},
{
"epoch": 0.6,
"learning_rate": 4.702026221692492e-05,
"loss": 5.1361,
"step": 9000
},
{
"epoch": 0.63,
"learning_rate": 4.68547212289763e-05,
"loss": 5.0988,
"step": 9500
},
{
"epoch": 0.66,
"learning_rate": 4.668918024102768e-05,
"loss": 5.0639,
"step": 10000
},
{
"epoch": 0.7,
"learning_rate": 4.652363925307907e-05,
"loss": 5.037,
"step": 10500
},
{
"epoch": 0.73,
"learning_rate": 4.6358098265130454e-05,
"loss": 4.9896,
"step": 11000
},
{
"epoch": 0.76,
"learning_rate": 4.619255727718183e-05,
"loss": 4.9501,
"step": 11500
},
{
"epoch": 0.79,
"learning_rate": 4.602701628923322e-05,
"loss": 4.9465,
"step": 12000
},
{
"epoch": 0.83,
"learning_rate": 4.58614753012846e-05,
"loss": 4.9,
"step": 12500
},
{
"epoch": 0.86,
"learning_rate": 4.569593431333598e-05,
"loss": 4.8633,
"step": 13000
},
{
"epoch": 0.89,
"learning_rate": 4.553039332538737e-05,
"loss": 4.8352,
"step": 13500
},
{
"epoch": 0.93,
"learning_rate": 4.536485233743875e-05,
"loss": 4.7846,
"step": 14000
},
{
"epoch": 0.96,
"learning_rate": 4.5199311349490134e-05,
"loss": 4.775,
"step": 14500
},
{
"epoch": 0.99,
"learning_rate": 4.503377036154152e-05,
"loss": 4.7556,
"step": 15000
},
{
"epoch": 1.03,
"learning_rate": 4.48682293735929e-05,
"loss": 4.7332,
"step": 15500
},
{
"epoch": 1.06,
"learning_rate": 4.4702688385644284e-05,
"loss": 4.7188,
"step": 16000
},
{
"epoch": 1.09,
"learning_rate": 4.453714739769567e-05,
"loss": 4.6928,
"step": 16500
},
{
"epoch": 1.13,
"learning_rate": 4.4371606409747055e-05,
"loss": 4.6792,
"step": 17000
},
{
"epoch": 1.16,
"learning_rate": 4.4206065421798434e-05,
"loss": 4.6542,
"step": 17500
},
{
"epoch": 1.19,
"learning_rate": 4.404052443384982e-05,
"loss": 4.6433,
"step": 18000
},
{
"epoch": 1.23,
"learning_rate": 4.3874983445901206e-05,
"loss": 4.616,
"step": 18500
},
{
"epoch": 1.26,
"learning_rate": 4.370944245795259e-05,
"loss": 4.6071,
"step": 19000
},
{
"epoch": 1.29,
"learning_rate": 4.354390147000397e-05,
"loss": 4.5814,
"step": 19500
},
{
"epoch": 1.32,
"learning_rate": 4.3378360482055356e-05,
"loss": 4.5617,
"step": 20000
},
{
"epoch": 1.36,
"learning_rate": 4.321281949410674e-05,
"loss": 4.5472,
"step": 20500
},
{
"epoch": 1.39,
"learning_rate": 4.304727850615813e-05,
"loss": 4.5401,
"step": 21000
},
{
"epoch": 1.42,
"learning_rate": 4.2881737518209507e-05,
"loss": 4.5001,
"step": 21500
},
{
"epoch": 1.46,
"learning_rate": 4.271619653026089e-05,
"loss": 4.4979,
"step": 22000
},
{
"epoch": 1.49,
"learning_rate": 4.255065554231228e-05,
"loss": 4.4717,
"step": 22500
},
{
"epoch": 1.52,
"learning_rate": 4.2385114554363664e-05,
"loss": 4.4488,
"step": 23000
},
{
"epoch": 1.56,
"learning_rate": 4.221957356641504e-05,
"loss": 4.4499,
"step": 23500
},
{
"epoch": 1.59,
"learning_rate": 4.205403257846643e-05,
"loss": 4.4122,
"step": 24000
},
{
"epoch": 1.62,
"learning_rate": 4.1888491590517814e-05,
"loss": 4.4016,
"step": 24500
},
{
"epoch": 1.66,
"learning_rate": 4.17229506025692e-05,
"loss": 4.3926,
"step": 25000
},
{
"epoch": 1.69,
"learning_rate": 4.155740961462058e-05,
"loss": 4.3787,
"step": 25500
},
{
"epoch": 1.72,
"learning_rate": 4.1391868626671964e-05,
"loss": 4.379,
"step": 26000
},
{
"epoch": 1.75,
"learning_rate": 4.122632763872335e-05,
"loss": 4.3696,
"step": 26500
},
{
"epoch": 1.79,
"learning_rate": 4.1060786650774736e-05,
"loss": 4.3436,
"step": 27000
},
{
"epoch": 1.82,
"learning_rate": 4.089524566282612e-05,
"loss": 4.3236,
"step": 27500
},
{
"epoch": 1.85,
"learning_rate": 4.07297046748775e-05,
"loss": 4.3132,
"step": 28000
},
{
"epoch": 1.89,
"learning_rate": 4.0564163686928886e-05,
"loss": 4.3176,
"step": 28500
},
{
"epoch": 1.92,
"learning_rate": 4.039862269898027e-05,
"loss": 4.2956,
"step": 29000
},
{
"epoch": 1.95,
"learning_rate": 4.023308171103166e-05,
"loss": 4.2884,
"step": 29500
},
{
"epoch": 1.99,
"learning_rate": 4.0067540723083036e-05,
"loss": 4.2735,
"step": 30000
},
{
"epoch": 2.02,
"learning_rate": 3.990199973513442e-05,
"loss": 4.2596,
"step": 30500
},
{
"epoch": 2.05,
"learning_rate": 3.973645874718581e-05,
"loss": 4.2534,
"step": 31000
},
{
"epoch": 2.09,
"learning_rate": 3.9570917759237194e-05,
"loss": 4.2429,
"step": 31500
},
{
"epoch": 2.12,
"learning_rate": 3.940537677128857e-05,
"loss": 4.2193,
"step": 32000
},
{
"epoch": 2.15,
"learning_rate": 3.923983578333996e-05,
"loss": 4.2025,
"step": 32500
},
{
"epoch": 2.19,
"learning_rate": 3.9074294795391344e-05,
"loss": 4.1868,
"step": 33000
},
{
"epoch": 2.22,
"learning_rate": 3.890875380744273e-05,
"loss": 4.1895,
"step": 33500
},
{
"epoch": 2.25,
"learning_rate": 3.874321281949411e-05,
"loss": 4.1681,
"step": 34000
},
{
"epoch": 2.28,
"learning_rate": 3.8577671831545494e-05,
"loss": 4.18,
"step": 34500
},
{
"epoch": 2.32,
"learning_rate": 3.841213084359688e-05,
"loss": 4.1666,
"step": 35000
},
{
"epoch": 2.35,
"learning_rate": 3.8246589855648266e-05,
"loss": 4.136,
"step": 35500
},
{
"epoch": 2.38,
"learning_rate": 3.8081048867699645e-05,
"loss": 4.1456,
"step": 36000
},
{
"epoch": 2.42,
"learning_rate": 3.791550787975103e-05,
"loss": 4.1194,
"step": 36500
},
{
"epoch": 2.45,
"learning_rate": 3.7749966891802416e-05,
"loss": 4.1111,
"step": 37000
},
{
"epoch": 2.48,
"learning_rate": 3.7584425903853795e-05,
"loss": 4.092,
"step": 37500
},
{
"epoch": 2.52,
"learning_rate": 3.741888491590518e-05,
"loss": 4.0972,
"step": 38000
},
{
"epoch": 2.55,
"learning_rate": 3.7253343927956566e-05,
"loss": 4.0929,
"step": 38500
},
{
"epoch": 2.58,
"learning_rate": 3.7087802940007945e-05,
"loss": 4.0645,
"step": 39000
},
{
"epoch": 2.62,
"learning_rate": 3.692226195205933e-05,
"loss": 4.0618,
"step": 39500
},
{
"epoch": 2.65,
"learning_rate": 3.675672096411072e-05,
"loss": 4.0674,
"step": 40000
},
{
"epoch": 2.68,
"learning_rate": 3.6591179976162096e-05,
"loss": 4.0467,
"step": 40500
},
{
"epoch": 2.71,
"learning_rate": 3.642563898821348e-05,
"loss": 4.0345,
"step": 41000
},
{
"epoch": 2.75,
"learning_rate": 3.626009800026487e-05,
"loss": 4.01,
"step": 41500
},
{
"epoch": 2.78,
"learning_rate": 3.6094557012316246e-05,
"loss": 4.0087,
"step": 42000
},
{
"epoch": 2.81,
"learning_rate": 3.592901602436763e-05,
"loss": 4.0112,
"step": 42500
},
{
"epoch": 2.85,
"learning_rate": 3.576347503641902e-05,
"loss": 4.0137,
"step": 43000
},
{
"epoch": 2.88,
"learning_rate": 3.55979340484704e-05,
"loss": 4.005,
"step": 43500
},
{
"epoch": 2.91,
"learning_rate": 3.543239306052178e-05,
"loss": 4.0055,
"step": 44000
},
{
"epoch": 2.95,
"learning_rate": 3.526685207257317e-05,
"loss": 3.98,
"step": 44500
},
{
"epoch": 2.98,
"learning_rate": 3.5101311084624553e-05,
"loss": 3.9646,
"step": 45000
},
{
"epoch": 3.01,
"learning_rate": 3.493577009667594e-05,
"loss": 3.9678,
"step": 45500
},
{
"epoch": 3.05,
"learning_rate": 3.477022910872732e-05,
"loss": 3.9427,
"step": 46000
},
{
"epoch": 3.08,
"learning_rate": 3.4604688120778704e-05,
"loss": 3.9335,
"step": 46500
},
{
"epoch": 3.11,
"learning_rate": 3.443914713283009e-05,
"loss": 3.9361,
"step": 47000
},
{
"epoch": 3.15,
"learning_rate": 3.4273606144881475e-05,
"loss": 3.9476,
"step": 47500
},
{
"epoch": 3.18,
"learning_rate": 3.4108065156932854e-05,
"loss": 3.924,
"step": 48000
},
{
"epoch": 3.21,
"learning_rate": 3.394252416898424e-05,
"loss": 3.9141,
"step": 48500
},
{
"epoch": 3.24,
"learning_rate": 3.3776983181035626e-05,
"loss": 3.9092,
"step": 49000
},
{
"epoch": 3.28,
"learning_rate": 3.361144219308701e-05,
"loss": 3.8767,
"step": 49500
},
{
"epoch": 3.31,
"learning_rate": 3.344590120513839e-05,
"loss": 3.9022,
"step": 50000
},
{
"epoch": 3.34,
"learning_rate": 3.3280360217189776e-05,
"loss": 3.8732,
"step": 50500
},
{
"epoch": 3.38,
"learning_rate": 3.311481922924116e-05,
"loss": 3.8522,
"step": 51000
},
{
"epoch": 3.41,
"learning_rate": 3.294927824129255e-05,
"loss": 3.8773,
"step": 51500
},
{
"epoch": 3.44,
"learning_rate": 3.2783737253343926e-05,
"loss": 3.8715,
"step": 52000
},
{
"epoch": 3.48,
"learning_rate": 3.261819626539531e-05,
"loss": 3.8549,
"step": 52500
},
{
"epoch": 3.51,
"learning_rate": 3.24526552774467e-05,
"loss": 3.8547,
"step": 53000
},
{
"epoch": 3.54,
"learning_rate": 3.228711428949808e-05,
"loss": 3.8408,
"step": 53500
},
{
"epoch": 3.58,
"learning_rate": 3.212157330154946e-05,
"loss": 3.8309,
"step": 54000
},
{
"epoch": 3.61,
"learning_rate": 3.195603231360085e-05,
"loss": 3.8275,
"step": 54500
},
{
"epoch": 3.64,
"learning_rate": 3.1790491325652234e-05,
"loss": 3.8257,
"step": 55000
},
{
"epoch": 3.68,
"learning_rate": 3.162495033770362e-05,
"loss": 3.8233,
"step": 55500
},
{
"epoch": 3.71,
"learning_rate": 3.1459409349755005e-05,
"loss": 3.8184,
"step": 56000
},
{
"epoch": 3.74,
"learning_rate": 3.1293868361806384e-05,
"loss": 3.7942,
"step": 56500
},
{
"epoch": 3.77,
"learning_rate": 3.112832737385777e-05,
"loss": 3.8072,
"step": 57000
},
{
"epoch": 3.81,
"learning_rate": 3.0962786385909155e-05,
"loss": 3.787,
"step": 57500
},
{
"epoch": 3.84,
"learning_rate": 3.079724539796054e-05,
"loss": 3.7954,
"step": 58000
},
{
"epoch": 3.87,
"learning_rate": 3.063170441001192e-05,
"loss": 3.7816,
"step": 58500
},
{
"epoch": 3.91,
"learning_rate": 3.0466163422063302e-05,
"loss": 3.7723,
"step": 59000
},
{
"epoch": 3.94,
"learning_rate": 3.0300622434114688e-05,
"loss": 3.7713,
"step": 59500
},
{
"epoch": 3.97,
"learning_rate": 3.0135081446166074e-05,
"loss": 3.7619,
"step": 60000
},
{
"epoch": 4.01,
"learning_rate": 2.9969540458217453e-05,
"loss": 3.7479,
"step": 60500
},
{
"epoch": 4.04,
"learning_rate": 2.980399947026884e-05,
"loss": 3.7411,
"step": 61000
},
{
"epoch": 4.07,
"learning_rate": 2.9638458482320224e-05,
"loss": 3.7416,
"step": 61500
},
{
"epoch": 4.11,
"learning_rate": 2.947291749437161e-05,
"loss": 3.7423,
"step": 62000
},
{
"epoch": 4.14,
"learning_rate": 2.930737650642299e-05,
"loss": 3.7344,
"step": 62500
},
{
"epoch": 4.17,
"learning_rate": 2.9141835518474375e-05,
"loss": 3.7244,
"step": 63000
},
{
"epoch": 4.2,
"learning_rate": 2.897629453052576e-05,
"loss": 3.739,
"step": 63500
},
{
"epoch": 4.24,
"learning_rate": 2.8810753542577146e-05,
"loss": 3.7142,
"step": 64000
},
{
"epoch": 4.27,
"learning_rate": 2.8645212554628525e-05,
"loss": 3.7158,
"step": 64500
},
{
"epoch": 4.3,
"learning_rate": 2.847967156667991e-05,
"loss": 3.7159,
"step": 65000
},
{
"epoch": 4.34,
"learning_rate": 2.8314130578731296e-05,
"loss": 3.6938,
"step": 65500
},
{
"epoch": 4.37,
"learning_rate": 2.8148589590782682e-05,
"loss": 3.692,
"step": 66000
},
{
"epoch": 4.4,
"learning_rate": 2.798304860283406e-05,
"loss": 3.6779,
"step": 66500
},
{
"epoch": 4.44,
"learning_rate": 2.7817507614885447e-05,
"loss": 3.6856,
"step": 67000
},
{
"epoch": 4.47,
"learning_rate": 2.7651966626936832e-05,
"loss": 3.6771,
"step": 67500
},
{
"epoch": 4.5,
"learning_rate": 2.7486425638988218e-05,
"loss": 3.672,
"step": 68000
},
{
"epoch": 4.54,
"learning_rate": 2.7320884651039597e-05,
"loss": 3.6788,
"step": 68500
},
{
"epoch": 4.57,
"learning_rate": 2.7155343663090983e-05,
"loss": 3.6562,
"step": 69000
},
{
"epoch": 4.6,
"learning_rate": 2.698980267514237e-05,
"loss": 3.6582,
"step": 69500
},
{
"epoch": 4.64,
"learning_rate": 2.682426168719375e-05,
"loss": 3.6605,
"step": 70000
},
{
"epoch": 4.67,
"learning_rate": 2.6658720699245133e-05,
"loss": 3.6535,
"step": 70500
},
{
"epoch": 4.7,
"learning_rate": 2.649317971129652e-05,
"loss": 3.649,
"step": 71000
},
{
"epoch": 4.73,
"learning_rate": 2.63276387233479e-05,
"loss": 3.6455,
"step": 71500
},
{
"epoch": 4.77,
"learning_rate": 2.6162097735399287e-05,
"loss": 3.6437,
"step": 72000
},
{
"epoch": 4.8,
"learning_rate": 2.599655674745067e-05,
"loss": 3.6402,
"step": 72500
},
{
"epoch": 4.83,
"learning_rate": 2.583101575950205e-05,
"loss": 3.6257,
"step": 73000
},
{
"epoch": 4.87,
"learning_rate": 2.5665474771553437e-05,
"loss": 3.6125,
"step": 73500
},
{
"epoch": 4.9,
"learning_rate": 2.5499933783604823e-05,
"loss": 3.6132,
"step": 74000
},
{
"epoch": 4.93,
"learning_rate": 2.5334392795656202e-05,
"loss": 3.612,
"step": 74500
},
{
"epoch": 4.97,
"learning_rate": 2.5168851807707588e-05,
"loss": 3.6139,
"step": 75000
},
{
"epoch": 5.0,
"learning_rate": 2.5003310819758973e-05,
"loss": 3.5995,
"step": 75500
},
{
"epoch": 5.03,
"learning_rate": 2.4837769831810356e-05,
"loss": 3.6016,
"step": 76000
},
{
"epoch": 5.07,
"learning_rate": 2.467222884386174e-05,
"loss": 3.5882,
"step": 76500
},
{
"epoch": 5.1,
"learning_rate": 2.4506687855913124e-05,
"loss": 3.6023,
"step": 77000
},
{
"epoch": 5.13,
"learning_rate": 2.434114686796451e-05,
"loss": 3.6025,
"step": 77500
},
{
"epoch": 5.16,
"learning_rate": 2.417560588001589e-05,
"loss": 3.5897,
"step": 78000
},
{
"epoch": 5.2,
"learning_rate": 2.4010064892067277e-05,
"loss": 3.5767,
"step": 78500
},
{
"epoch": 5.23,
"learning_rate": 2.384452390411866e-05,
"loss": 3.5835,
"step": 79000
},
{
"epoch": 5.26,
"learning_rate": 2.3678982916170045e-05,
"loss": 3.5579,
"step": 79500
},
{
"epoch": 5.3,
"learning_rate": 2.3513441928221428e-05,
"loss": 3.5708,
"step": 80000
},
{
"epoch": 5.33,
"learning_rate": 2.3347900940272813e-05,
"loss": 3.5613,
"step": 80500
},
{
"epoch": 5.36,
"learning_rate": 2.3182359952324196e-05,
"loss": 3.5632,
"step": 81000
},
{
"epoch": 5.4,
"learning_rate": 2.301681896437558e-05,
"loss": 3.5688,
"step": 81500
},
{
"epoch": 5.43,
"learning_rate": 2.2851277976426967e-05,
"loss": 3.5563,
"step": 82000
},
{
"epoch": 5.46,
"learning_rate": 2.268573698847835e-05,
"loss": 3.5438,
"step": 82500
},
{
"epoch": 5.5,
"learning_rate": 2.2520196000529735e-05,
"loss": 3.5384,
"step": 83000
},
{
"epoch": 5.53,
"learning_rate": 2.2354655012581117e-05,
"loss": 3.5491,
"step": 83500
},
{
"epoch": 5.56,
"learning_rate": 2.21891140246325e-05,
"loss": 3.5491,
"step": 84000
},
{
"epoch": 5.6,
"learning_rate": 2.2023573036683885e-05,
"loss": 3.5437,
"step": 84500
},
{
"epoch": 5.63,
"learning_rate": 2.1858032048735268e-05,
"loss": 3.5335,
"step": 85000
},
{
"epoch": 5.66,
"learning_rate": 2.169249106078665e-05,
"loss": 3.5302,
"step": 85500
},
{
"epoch": 5.69,
"learning_rate": 2.1526950072838036e-05,
"loss": 3.5227,
"step": 86000
},
{
"epoch": 5.73,
"learning_rate": 2.1361409084889418e-05,
"loss": 3.5239,
"step": 86500
},
{
"epoch": 5.76,
"learning_rate": 2.1195868096940804e-05,
"loss": 3.5148,
"step": 87000
},
{
"epoch": 5.79,
"learning_rate": 2.1030327108992186e-05,
"loss": 3.5282,
"step": 87500
},
{
"epoch": 5.83,
"learning_rate": 2.0864786121043572e-05,
"loss": 3.5222,
"step": 88000
},
{
"epoch": 5.86,
"learning_rate": 2.0699245133094954e-05,
"loss": 3.5179,
"step": 88500
},
{
"epoch": 5.89,
"learning_rate": 2.053370414514634e-05,
"loss": 3.4973,
"step": 89000
},
{
"epoch": 5.93,
"learning_rate": 2.0368163157197722e-05,
"loss": 3.5072,
"step": 89500
},
{
"epoch": 5.96,
"learning_rate": 2.0202622169249108e-05,
"loss": 3.5043,
"step": 90000
},
{
"epoch": 5.99,
"learning_rate": 2.003708118130049e-05,
"loss": 3.5099,
"step": 90500
},
{
"epoch": 6.03,
"learning_rate": 1.9871540193351876e-05,
"loss": 3.4962,
"step": 91000
},
{
"epoch": 6.06,
"learning_rate": 1.9705999205403258e-05,
"loss": 3.4934,
"step": 91500
},
{
"epoch": 6.09,
"learning_rate": 1.9540458217454644e-05,
"loss": 3.484,
"step": 92000
},
{
"epoch": 6.13,
"learning_rate": 1.9374917229506026e-05,
"loss": 3.4683,
"step": 92500
},
{
"epoch": 6.16,
"learning_rate": 1.9209376241557412e-05,
"loss": 3.4929,
"step": 93000
},
{
"epoch": 6.19,
"learning_rate": 1.9043835253608794e-05,
"loss": 3.4759,
"step": 93500
},
{
"epoch": 6.22,
"learning_rate": 1.887829426566018e-05,
"loss": 3.4733,
"step": 94000
},
{
"epoch": 6.26,
"learning_rate": 1.8712753277711562e-05,
"loss": 3.4746,
"step": 94500
},
{
"epoch": 6.29,
"learning_rate": 1.8547212289762948e-05,
"loss": 3.4734,
"step": 95000
},
{
"epoch": 6.32,
"learning_rate": 1.838167130181433e-05,
"loss": 3.4738,
"step": 95500
},
{
"epoch": 6.36,
"learning_rate": 1.8216130313865716e-05,
"loss": 3.4768,
"step": 96000
},
{
"epoch": 6.39,
"learning_rate": 1.80505893259171e-05,
"loss": 3.4731,
"step": 96500
},
{
"epoch": 6.42,
"learning_rate": 1.7885048337968484e-05,
"loss": 3.4659,
"step": 97000
},
{
"epoch": 6.46,
"learning_rate": 1.7719507350019866e-05,
"loss": 3.4642,
"step": 97500
},
{
"epoch": 6.49,
"learning_rate": 1.755396636207125e-05,
"loss": 3.4595,
"step": 98000
},
{
"epoch": 6.52,
"learning_rate": 1.738842537412263e-05,
"loss": 3.4715,
"step": 98500
},
{
"epoch": 6.56,
"learning_rate": 1.7222884386174017e-05,
"loss": 3.4457,
"step": 99000
},
{
"epoch": 6.59,
"learning_rate": 1.70573433982254e-05,
"loss": 3.4621,
"step": 99500
},
{
"epoch": 6.62,
"learning_rate": 1.6891802410276785e-05,
"loss": 3.446,
"step": 100000
}
],
"logging_steps": 500,
"max_steps": 151020,
"num_train_epochs": 10,
"save_steps": 100000,
"total_flos": 1.2639573579451392e+18,
"trial_name": null,
"trial_params": null
}