m2m100_418M_en_twi_rel_news / trainer_state.json
Davlan's picture
add MT model
a479412
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 3.0,
"global_step": 181296,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.01,
"learning_rate": 4.986210396258053e-05,
"loss": 2.8171,
"step": 500
},
{
"epoch": 0.02,
"learning_rate": 4.9724207925161064e-05,
"loss": 2.0072,
"step": 1000
},
{
"epoch": 0.02,
"learning_rate": 4.95863118877416e-05,
"loss": 1.7607,
"step": 1500
},
{
"epoch": 0.03,
"learning_rate": 4.9448415850322125e-05,
"loss": 1.6134,
"step": 2000
},
{
"epoch": 0.04,
"learning_rate": 4.931051981290266e-05,
"loss": 1.536,
"step": 2500
},
{
"epoch": 0.05,
"learning_rate": 4.917262377548319e-05,
"loss": 1.4503,
"step": 3000
},
{
"epoch": 0.06,
"learning_rate": 4.9034727738063724e-05,
"loss": 1.4208,
"step": 3500
},
{
"epoch": 0.07,
"learning_rate": 4.8896831700644255e-05,
"loss": 1.3709,
"step": 4000
},
{
"epoch": 0.07,
"learning_rate": 4.8758935663224786e-05,
"loss": 1.3472,
"step": 4500
},
{
"epoch": 0.08,
"learning_rate": 4.862103962580532e-05,
"loss": 1.3117,
"step": 5000
},
{
"epoch": 0.09,
"learning_rate": 4.848314358838585e-05,
"loss": 1.2615,
"step": 5500
},
{
"epoch": 0.1,
"learning_rate": 4.834524755096638e-05,
"loss": 1.2461,
"step": 6000
},
{
"epoch": 0.11,
"learning_rate": 4.820735151354691e-05,
"loss": 1.2356,
"step": 6500
},
{
"epoch": 0.12,
"learning_rate": 4.806945547612744e-05,
"loss": 1.218,
"step": 7000
},
{
"epoch": 0.12,
"learning_rate": 4.793155943870797e-05,
"loss": 1.2006,
"step": 7500
},
{
"epoch": 0.13,
"learning_rate": 4.77936634012885e-05,
"loss": 1.172,
"step": 8000
},
{
"epoch": 0.14,
"learning_rate": 4.765576736386904e-05,
"loss": 1.1617,
"step": 8500
},
{
"epoch": 0.15,
"learning_rate": 4.751787132644956e-05,
"loss": 1.1568,
"step": 9000
},
{
"epoch": 0.16,
"learning_rate": 4.73799752890301e-05,
"loss": 1.1374,
"step": 9500
},
{
"epoch": 0.17,
"learning_rate": 4.7242079251610624e-05,
"loss": 1.1234,
"step": 10000
},
{
"epoch": 0.17,
"learning_rate": 4.710418321419116e-05,
"loss": 1.1088,
"step": 10500
},
{
"epoch": 0.18,
"learning_rate": 4.696628717677169e-05,
"loss": 1.0915,
"step": 11000
},
{
"epoch": 0.19,
"learning_rate": 4.682839113935222e-05,
"loss": 1.0999,
"step": 11500
},
{
"epoch": 0.2,
"learning_rate": 4.6690495101932754e-05,
"loss": 1.0745,
"step": 12000
},
{
"epoch": 0.21,
"learning_rate": 4.6552599064513285e-05,
"loss": 1.0702,
"step": 12500
},
{
"epoch": 0.22,
"learning_rate": 4.6414703027093815e-05,
"loss": 1.0665,
"step": 13000
},
{
"epoch": 0.22,
"learning_rate": 4.6276806989674346e-05,
"loss": 1.0546,
"step": 13500
},
{
"epoch": 0.23,
"learning_rate": 4.613891095225488e-05,
"loss": 1.0611,
"step": 14000
},
{
"epoch": 0.24,
"learning_rate": 4.600101491483541e-05,
"loss": 1.0603,
"step": 14500
},
{
"epoch": 0.25,
"learning_rate": 4.586311887741594e-05,
"loss": 1.0343,
"step": 15000
},
{
"epoch": 0.26,
"learning_rate": 4.5725222839996476e-05,
"loss": 1.0327,
"step": 15500
},
{
"epoch": 0.26,
"learning_rate": 4.5587326802577e-05,
"loss": 1.0223,
"step": 16000
},
{
"epoch": 0.27,
"learning_rate": 4.544943076515754e-05,
"loss": 1.0156,
"step": 16500
},
{
"epoch": 0.28,
"learning_rate": 4.531153472773806e-05,
"loss": 1.0112,
"step": 17000
},
{
"epoch": 0.29,
"learning_rate": 4.51736386903186e-05,
"loss": 1.005,
"step": 17500
},
{
"epoch": 0.3,
"learning_rate": 4.503574265289913e-05,
"loss": 0.9836,
"step": 18000
},
{
"epoch": 0.31,
"learning_rate": 4.489784661547966e-05,
"loss": 0.9939,
"step": 18500
},
{
"epoch": 0.31,
"learning_rate": 4.475995057806019e-05,
"loss": 0.9986,
"step": 19000
},
{
"epoch": 0.32,
"learning_rate": 4.462205454064072e-05,
"loss": 0.9881,
"step": 19500
},
{
"epoch": 0.33,
"learning_rate": 4.448415850322125e-05,
"loss": 0.9716,
"step": 20000
},
{
"epoch": 0.34,
"learning_rate": 4.434626246580178e-05,
"loss": 0.9729,
"step": 20500
},
{
"epoch": 0.35,
"learning_rate": 4.4208366428382314e-05,
"loss": 0.9703,
"step": 21000
},
{
"epoch": 0.36,
"learning_rate": 4.4070470390962845e-05,
"loss": 0.9553,
"step": 21500
},
{
"epoch": 0.36,
"learning_rate": 4.3932574353543376e-05,
"loss": 0.9543,
"step": 22000
},
{
"epoch": 0.37,
"learning_rate": 4.379467831612391e-05,
"loss": 0.9639,
"step": 22500
},
{
"epoch": 0.38,
"learning_rate": 4.365678227870444e-05,
"loss": 0.9482,
"step": 23000
},
{
"epoch": 0.39,
"learning_rate": 4.3518886241284975e-05,
"loss": 0.9403,
"step": 23500
},
{
"epoch": 0.4,
"learning_rate": 4.33809902038655e-05,
"loss": 0.9338,
"step": 24000
},
{
"epoch": 0.41,
"learning_rate": 4.3243094166446036e-05,
"loss": 0.9471,
"step": 24500
},
{
"epoch": 0.41,
"learning_rate": 4.310519812902657e-05,
"loss": 0.9351,
"step": 25000
},
{
"epoch": 0.42,
"learning_rate": 4.29673020916071e-05,
"loss": 0.9187,
"step": 25500
},
{
"epoch": 0.43,
"learning_rate": 4.282940605418763e-05,
"loss": 0.9264,
"step": 26000
},
{
"epoch": 0.44,
"learning_rate": 4.269151001676816e-05,
"loss": 0.9177,
"step": 26500
},
{
"epoch": 0.45,
"learning_rate": 4.255361397934869e-05,
"loss": 0.9299,
"step": 27000
},
{
"epoch": 0.46,
"learning_rate": 4.241571794192922e-05,
"loss": 0.9184,
"step": 27500
},
{
"epoch": 0.46,
"learning_rate": 4.227782190450976e-05,
"loss": 0.9216,
"step": 28000
},
{
"epoch": 0.47,
"learning_rate": 4.213992586709028e-05,
"loss": 0.9113,
"step": 28500
},
{
"epoch": 0.48,
"learning_rate": 4.200202982967082e-05,
"loss": 0.8962,
"step": 29000
},
{
"epoch": 0.49,
"learning_rate": 4.186413379225135e-05,
"loss": 0.9086,
"step": 29500
},
{
"epoch": 0.5,
"learning_rate": 4.172623775483188e-05,
"loss": 0.9235,
"step": 30000
},
{
"epoch": 0.5,
"learning_rate": 4.158834171741241e-05,
"loss": 0.9018,
"step": 30500
},
{
"epoch": 0.51,
"learning_rate": 4.145044567999294e-05,
"loss": 0.903,
"step": 31000
},
{
"epoch": 0.52,
"learning_rate": 4.131254964257347e-05,
"loss": 0.8975,
"step": 31500
},
{
"epoch": 0.53,
"learning_rate": 4.1174653605154004e-05,
"loss": 0.8943,
"step": 32000
},
{
"epoch": 0.54,
"learning_rate": 4.1036757567734535e-05,
"loss": 0.8875,
"step": 32500
},
{
"epoch": 0.55,
"learning_rate": 4.089886153031507e-05,
"loss": 0.8919,
"step": 33000
},
{
"epoch": 0.55,
"learning_rate": 4.0760965492895596e-05,
"loss": 0.879,
"step": 33500
},
{
"epoch": 0.56,
"learning_rate": 4.0623069455476134e-05,
"loss": 0.8875,
"step": 34000
},
{
"epoch": 0.57,
"learning_rate": 4.048517341805666e-05,
"loss": 0.8633,
"step": 34500
},
{
"epoch": 0.58,
"learning_rate": 4.0347277380637195e-05,
"loss": 0.8776,
"step": 35000
},
{
"epoch": 0.59,
"learning_rate": 4.020938134321772e-05,
"loss": 0.8702,
"step": 35500
},
{
"epoch": 0.6,
"learning_rate": 4.007148530579826e-05,
"loss": 0.866,
"step": 36000
},
{
"epoch": 0.6,
"learning_rate": 3.993358926837879e-05,
"loss": 0.8634,
"step": 36500
},
{
"epoch": 0.61,
"learning_rate": 3.979569323095932e-05,
"loss": 0.883,
"step": 37000
},
{
"epoch": 0.62,
"learning_rate": 3.965779719353985e-05,
"loss": 0.8519,
"step": 37500
},
{
"epoch": 0.63,
"learning_rate": 3.951990115612038e-05,
"loss": 0.8643,
"step": 38000
},
{
"epoch": 0.64,
"learning_rate": 3.938200511870091e-05,
"loss": 0.8454,
"step": 38500
},
{
"epoch": 0.65,
"learning_rate": 3.924410908128144e-05,
"loss": 0.8666,
"step": 39000
},
{
"epoch": 0.65,
"learning_rate": 3.910621304386197e-05,
"loss": 0.8514,
"step": 39500
},
{
"epoch": 0.66,
"learning_rate": 3.896831700644251e-05,
"loss": 0.8454,
"step": 40000
},
{
"epoch": 0.67,
"learning_rate": 3.8830420969023034e-05,
"loss": 0.8615,
"step": 40500
},
{
"epoch": 0.68,
"learning_rate": 3.869252493160357e-05,
"loss": 0.8516,
"step": 41000
},
{
"epoch": 0.69,
"learning_rate": 3.8554628894184095e-05,
"loss": 0.8502,
"step": 41500
},
{
"epoch": 0.69,
"learning_rate": 3.841673285676463e-05,
"loss": 0.8455,
"step": 42000
},
{
"epoch": 0.7,
"learning_rate": 3.827883681934516e-05,
"loss": 0.8323,
"step": 42500
},
{
"epoch": 0.71,
"learning_rate": 3.8140940781925694e-05,
"loss": 0.8408,
"step": 43000
},
{
"epoch": 0.72,
"learning_rate": 3.8003044744506225e-05,
"loss": 0.8478,
"step": 43500
},
{
"epoch": 0.73,
"learning_rate": 3.7865148707086756e-05,
"loss": 0.8428,
"step": 44000
},
{
"epoch": 0.74,
"learning_rate": 3.7727252669667286e-05,
"loss": 0.838,
"step": 44500
},
{
"epoch": 0.74,
"learning_rate": 3.758935663224782e-05,
"loss": 0.843,
"step": 45000
},
{
"epoch": 0.75,
"learning_rate": 3.745146059482835e-05,
"loss": 0.8388,
"step": 45500
},
{
"epoch": 0.76,
"learning_rate": 3.731356455740888e-05,
"loss": 0.8256,
"step": 46000
},
{
"epoch": 0.77,
"learning_rate": 3.717566851998941e-05,
"loss": 0.8393,
"step": 46500
},
{
"epoch": 0.78,
"learning_rate": 3.703777248256994e-05,
"loss": 0.8295,
"step": 47000
},
{
"epoch": 0.79,
"learning_rate": 3.689987644515047e-05,
"loss": 0.8194,
"step": 47500
},
{
"epoch": 0.79,
"learning_rate": 3.676198040773101e-05,
"loss": 0.8262,
"step": 48000
},
{
"epoch": 0.8,
"learning_rate": 3.662408437031153e-05,
"loss": 0.8368,
"step": 48500
},
{
"epoch": 0.81,
"learning_rate": 3.648618833289207e-05,
"loss": 0.8226,
"step": 49000
},
{
"epoch": 0.82,
"learning_rate": 3.6348292295472594e-05,
"loss": 0.8207,
"step": 49500
},
{
"epoch": 0.83,
"learning_rate": 3.621039625805313e-05,
"loss": 0.8131,
"step": 50000
},
{
"epoch": 0.84,
"learning_rate": 3.607250022063366e-05,
"loss": 0.8253,
"step": 50500
},
{
"epoch": 0.84,
"learning_rate": 3.593460418321419e-05,
"loss": 0.8082,
"step": 51000
},
{
"epoch": 0.85,
"learning_rate": 3.5796708145794724e-05,
"loss": 0.8191,
"step": 51500
},
{
"epoch": 0.86,
"learning_rate": 3.5658812108375254e-05,
"loss": 0.8167,
"step": 52000
},
{
"epoch": 0.87,
"learning_rate": 3.5520916070955785e-05,
"loss": 0.7956,
"step": 52500
},
{
"epoch": 0.88,
"learning_rate": 3.5383020033536316e-05,
"loss": 0.804,
"step": 53000
},
{
"epoch": 0.89,
"learning_rate": 3.524512399611685e-05,
"loss": 0.7958,
"step": 53500
},
{
"epoch": 0.89,
"learning_rate": 3.510722795869738e-05,
"loss": 0.8147,
"step": 54000
},
{
"epoch": 0.9,
"learning_rate": 3.496933192127791e-05,
"loss": 0.8106,
"step": 54500
},
{
"epoch": 0.91,
"learning_rate": 3.4831435883858446e-05,
"loss": 0.8114,
"step": 55000
},
{
"epoch": 0.92,
"learning_rate": 3.4693539846438976e-05,
"loss": 0.8079,
"step": 55500
},
{
"epoch": 0.93,
"learning_rate": 3.455564380901951e-05,
"loss": 0.8037,
"step": 56000
},
{
"epoch": 0.93,
"learning_rate": 3.441774777160004e-05,
"loss": 0.7862,
"step": 56500
},
{
"epoch": 0.94,
"learning_rate": 3.427985173418057e-05,
"loss": 0.8013,
"step": 57000
},
{
"epoch": 0.95,
"learning_rate": 3.41419556967611e-05,
"loss": 0.7932,
"step": 57500
},
{
"epoch": 0.96,
"learning_rate": 3.400405965934163e-05,
"loss": 0.7843,
"step": 58000
},
{
"epoch": 0.97,
"learning_rate": 3.386616362192217e-05,
"loss": 0.7878,
"step": 58500
},
{
"epoch": 0.98,
"learning_rate": 3.372826758450269e-05,
"loss": 0.794,
"step": 59000
},
{
"epoch": 0.98,
"learning_rate": 3.359037154708323e-05,
"loss": 0.7875,
"step": 59500
},
{
"epoch": 0.99,
"learning_rate": 3.345247550966375e-05,
"loss": 0.7934,
"step": 60000
},
{
"epoch": 1.0,
"learning_rate": 3.331457947224429e-05,
"loss": 0.7802,
"step": 60500
},
{
"epoch": 1.01,
"learning_rate": 3.3176683434824815e-05,
"loss": 0.7117,
"step": 61000
},
{
"epoch": 1.02,
"learning_rate": 3.303878739740535e-05,
"loss": 0.7064,
"step": 61500
},
{
"epoch": 1.03,
"learning_rate": 3.290089135998588e-05,
"loss": 0.7223,
"step": 62000
},
{
"epoch": 1.03,
"learning_rate": 3.2762995322566414e-05,
"loss": 0.7159,
"step": 62500
},
{
"epoch": 1.04,
"learning_rate": 3.2625099285146944e-05,
"loss": 0.7211,
"step": 63000
},
{
"epoch": 1.05,
"learning_rate": 3.2487203247727475e-05,
"loss": 0.7173,
"step": 63500
},
{
"epoch": 1.06,
"learning_rate": 3.2349307210308006e-05,
"loss": 0.7173,
"step": 64000
},
{
"epoch": 1.07,
"learning_rate": 3.221141117288854e-05,
"loss": 0.7046,
"step": 64500
},
{
"epoch": 1.08,
"learning_rate": 3.207351513546907e-05,
"loss": 0.7106,
"step": 65000
},
{
"epoch": 1.08,
"learning_rate": 3.1935619098049605e-05,
"loss": 0.7023,
"step": 65500
},
{
"epoch": 1.09,
"learning_rate": 3.179772306063013e-05,
"loss": 0.7028,
"step": 66000
},
{
"epoch": 1.1,
"learning_rate": 3.1659827023210666e-05,
"loss": 0.7283,
"step": 66500
},
{
"epoch": 1.11,
"learning_rate": 3.152193098579119e-05,
"loss": 0.7025,
"step": 67000
},
{
"epoch": 1.12,
"learning_rate": 3.138403494837173e-05,
"loss": 0.716,
"step": 67500
},
{
"epoch": 1.13,
"learning_rate": 3.124613891095225e-05,
"loss": 0.7063,
"step": 68000
},
{
"epoch": 1.13,
"learning_rate": 3.110824287353279e-05,
"loss": 0.7079,
"step": 68500
},
{
"epoch": 1.14,
"learning_rate": 3.097034683611332e-05,
"loss": 0.7025,
"step": 69000
},
{
"epoch": 1.15,
"learning_rate": 3.083245079869385e-05,
"loss": 0.7029,
"step": 69500
},
{
"epoch": 1.16,
"learning_rate": 3.069455476127438e-05,
"loss": 0.7003,
"step": 70000
},
{
"epoch": 1.17,
"learning_rate": 3.055665872385491e-05,
"loss": 0.7013,
"step": 70500
},
{
"epoch": 1.17,
"learning_rate": 3.0418762686435443e-05,
"loss": 0.7154,
"step": 71000
},
{
"epoch": 1.18,
"learning_rate": 3.0280866649015977e-05,
"loss": 0.7059,
"step": 71500
},
{
"epoch": 1.19,
"learning_rate": 3.0142970611596505e-05,
"loss": 0.7047,
"step": 72000
},
{
"epoch": 1.2,
"learning_rate": 3.000507457417704e-05,
"loss": 0.7047,
"step": 72500
},
{
"epoch": 1.21,
"learning_rate": 2.9867178536757566e-05,
"loss": 0.6962,
"step": 73000
},
{
"epoch": 1.22,
"learning_rate": 2.97292824993381e-05,
"loss": 0.708,
"step": 73500
},
{
"epoch": 1.22,
"learning_rate": 2.959138646191863e-05,
"loss": 0.6973,
"step": 74000
},
{
"epoch": 1.23,
"learning_rate": 2.9453490424499165e-05,
"loss": 0.7049,
"step": 74500
},
{
"epoch": 1.24,
"learning_rate": 2.9315594387079692e-05,
"loss": 0.7052,
"step": 75000
},
{
"epoch": 1.25,
"learning_rate": 2.9177698349660227e-05,
"loss": 0.6949,
"step": 75500
},
{
"epoch": 1.26,
"learning_rate": 2.9039802312240754e-05,
"loss": 0.7017,
"step": 76000
},
{
"epoch": 1.27,
"learning_rate": 2.8901906274821288e-05,
"loss": 0.702,
"step": 76500
},
{
"epoch": 1.27,
"learning_rate": 2.876401023740182e-05,
"loss": 0.7055,
"step": 77000
},
{
"epoch": 1.28,
"learning_rate": 2.862611419998235e-05,
"loss": 0.701,
"step": 77500
},
{
"epoch": 1.29,
"learning_rate": 2.848821816256288e-05,
"loss": 0.7046,
"step": 78000
},
{
"epoch": 1.3,
"learning_rate": 2.8350322125143414e-05,
"loss": 0.6899,
"step": 78500
},
{
"epoch": 1.31,
"learning_rate": 2.8212426087723942e-05,
"loss": 0.7043,
"step": 79000
},
{
"epoch": 1.32,
"learning_rate": 2.8074530050304476e-05,
"loss": 0.6923,
"step": 79500
},
{
"epoch": 1.32,
"learning_rate": 2.7936634012885003e-05,
"loss": 0.7001,
"step": 80000
},
{
"epoch": 1.33,
"learning_rate": 2.7798737975465537e-05,
"loss": 0.6947,
"step": 80500
},
{
"epoch": 1.34,
"learning_rate": 2.7660841938046068e-05,
"loss": 0.6971,
"step": 81000
},
{
"epoch": 1.35,
"learning_rate": 2.7522945900626602e-05,
"loss": 0.6927,
"step": 81500
},
{
"epoch": 1.36,
"learning_rate": 2.738504986320713e-05,
"loss": 0.6936,
"step": 82000
},
{
"epoch": 1.37,
"learning_rate": 2.7247153825787664e-05,
"loss": 0.6914,
"step": 82500
},
{
"epoch": 1.37,
"learning_rate": 2.7109257788368198e-05,
"loss": 0.6899,
"step": 83000
},
{
"epoch": 1.38,
"learning_rate": 2.6971361750948725e-05,
"loss": 0.6901,
"step": 83500
},
{
"epoch": 1.39,
"learning_rate": 2.683346571352926e-05,
"loss": 0.6909,
"step": 84000
},
{
"epoch": 1.4,
"learning_rate": 2.6695569676109787e-05,
"loss": 0.69,
"step": 84500
},
{
"epoch": 1.41,
"learning_rate": 2.655767363869032e-05,
"loss": 0.6937,
"step": 85000
},
{
"epoch": 1.41,
"learning_rate": 2.6419777601270852e-05,
"loss": 0.7011,
"step": 85500
},
{
"epoch": 1.42,
"learning_rate": 2.6281881563851386e-05,
"loss": 0.6917,
"step": 86000
},
{
"epoch": 1.43,
"learning_rate": 2.6143985526431913e-05,
"loss": 0.682,
"step": 86500
},
{
"epoch": 1.44,
"learning_rate": 2.6006089489012447e-05,
"loss": 0.6827,
"step": 87000
},
{
"epoch": 1.45,
"learning_rate": 2.5868193451592975e-05,
"loss": 0.6902,
"step": 87500
},
{
"epoch": 1.46,
"learning_rate": 2.573029741417351e-05,
"loss": 0.6854,
"step": 88000
},
{
"epoch": 1.46,
"learning_rate": 2.559240137675404e-05,
"loss": 0.6903,
"step": 88500
},
{
"epoch": 1.47,
"learning_rate": 2.5454505339334574e-05,
"loss": 0.6813,
"step": 89000
},
{
"epoch": 1.48,
"learning_rate": 2.53166093019151e-05,
"loss": 0.6778,
"step": 89500
},
{
"epoch": 1.49,
"learning_rate": 2.5178713264495635e-05,
"loss": 0.6808,
"step": 90000
},
{
"epoch": 1.5,
"learning_rate": 2.5040817227076163e-05,
"loss": 0.6912,
"step": 90500
},
{
"epoch": 1.51,
"learning_rate": 2.4902921189656693e-05,
"loss": 0.684,
"step": 91000
},
{
"epoch": 1.51,
"learning_rate": 2.4765025152237224e-05,
"loss": 0.6771,
"step": 91500
},
{
"epoch": 1.52,
"learning_rate": 2.4627129114817758e-05,
"loss": 0.6751,
"step": 92000
},
{
"epoch": 1.53,
"learning_rate": 2.448923307739829e-05,
"loss": 0.6796,
"step": 92500
},
{
"epoch": 1.54,
"learning_rate": 2.435133703997882e-05,
"loss": 0.6758,
"step": 93000
},
{
"epoch": 1.55,
"learning_rate": 2.421344100255935e-05,
"loss": 0.6761,
"step": 93500
},
{
"epoch": 1.56,
"learning_rate": 2.407554496513988e-05,
"loss": 0.6821,
"step": 94000
},
{
"epoch": 1.56,
"learning_rate": 2.3937648927720412e-05,
"loss": 0.6711,
"step": 94500
},
{
"epoch": 1.57,
"learning_rate": 2.3799752890300943e-05,
"loss": 0.6862,
"step": 95000
},
{
"epoch": 1.58,
"learning_rate": 2.3661856852881477e-05,
"loss": 0.6844,
"step": 95500
},
{
"epoch": 1.59,
"learning_rate": 2.3523960815462008e-05,
"loss": 0.6841,
"step": 96000
},
{
"epoch": 1.6,
"learning_rate": 2.338606477804254e-05,
"loss": 0.6683,
"step": 96500
},
{
"epoch": 1.61,
"learning_rate": 2.3248168740623072e-05,
"loss": 0.6622,
"step": 97000
},
{
"epoch": 1.61,
"learning_rate": 2.3110272703203603e-05,
"loss": 0.6732,
"step": 97500
},
{
"epoch": 1.62,
"learning_rate": 2.2972376665784134e-05,
"loss": 0.6839,
"step": 98000
},
{
"epoch": 1.63,
"learning_rate": 2.2834480628364665e-05,
"loss": 0.6773,
"step": 98500
},
{
"epoch": 1.64,
"learning_rate": 2.2696584590945195e-05,
"loss": 0.6622,
"step": 99000
},
{
"epoch": 1.65,
"learning_rate": 2.255868855352573e-05,
"loss": 0.6745,
"step": 99500
},
{
"epoch": 1.65,
"learning_rate": 2.242079251610626e-05,
"loss": 0.6776,
"step": 100000
},
{
"epoch": 1.66,
"learning_rate": 2.228289647868679e-05,
"loss": 0.6706,
"step": 100500
},
{
"epoch": 1.67,
"learning_rate": 2.2145000441267322e-05,
"loss": 0.6631,
"step": 101000
},
{
"epoch": 1.68,
"learning_rate": 2.2007104403847853e-05,
"loss": 0.6722,
"step": 101500
},
{
"epoch": 1.69,
"learning_rate": 2.1869208366428383e-05,
"loss": 0.6729,
"step": 102000
},
{
"epoch": 1.7,
"learning_rate": 2.1731312329008914e-05,
"loss": 0.6899,
"step": 102500
},
{
"epoch": 1.7,
"learning_rate": 2.1593416291589448e-05,
"loss": 0.6523,
"step": 103000
},
{
"epoch": 1.71,
"learning_rate": 2.145552025416998e-05,
"loss": 0.6654,
"step": 103500
},
{
"epoch": 1.72,
"learning_rate": 2.131762421675051e-05,
"loss": 0.666,
"step": 104000
},
{
"epoch": 1.73,
"learning_rate": 2.117972817933104e-05,
"loss": 0.67,
"step": 104500
},
{
"epoch": 1.74,
"learning_rate": 2.104183214191157e-05,
"loss": 0.6795,
"step": 105000
},
{
"epoch": 1.75,
"learning_rate": 2.0903936104492102e-05,
"loss": 0.6666,
"step": 105500
},
{
"epoch": 1.75,
"learning_rate": 2.0766040067072633e-05,
"loss": 0.6661,
"step": 106000
},
{
"epoch": 1.76,
"learning_rate": 2.0628144029653167e-05,
"loss": 0.6701,
"step": 106500
},
{
"epoch": 1.77,
"learning_rate": 2.0490247992233698e-05,
"loss": 0.6628,
"step": 107000
},
{
"epoch": 1.78,
"learning_rate": 2.035235195481423e-05,
"loss": 0.6629,
"step": 107500
},
{
"epoch": 1.79,
"learning_rate": 2.021445591739476e-05,
"loss": 0.6626,
"step": 108000
},
{
"epoch": 1.8,
"learning_rate": 2.007655987997529e-05,
"loss": 0.657,
"step": 108500
},
{
"epoch": 1.8,
"learning_rate": 1.993866384255582e-05,
"loss": 0.6594,
"step": 109000
},
{
"epoch": 1.81,
"learning_rate": 1.980076780513635e-05,
"loss": 0.6637,
"step": 109500
},
{
"epoch": 1.82,
"learning_rate": 1.9662871767716885e-05,
"loss": 0.6474,
"step": 110000
},
{
"epoch": 1.83,
"learning_rate": 1.9524975730297416e-05,
"loss": 0.6607,
"step": 110500
},
{
"epoch": 1.84,
"learning_rate": 1.9387079692877947e-05,
"loss": 0.6569,
"step": 111000
},
{
"epoch": 1.85,
"learning_rate": 1.9249183655458478e-05,
"loss": 0.6644,
"step": 111500
},
{
"epoch": 1.85,
"learning_rate": 1.911128761803901e-05,
"loss": 0.6611,
"step": 112000
},
{
"epoch": 1.86,
"learning_rate": 1.897339158061954e-05,
"loss": 0.6597,
"step": 112500
},
{
"epoch": 1.87,
"learning_rate": 1.883549554320007e-05,
"loss": 0.665,
"step": 113000
},
{
"epoch": 1.88,
"learning_rate": 1.8697599505780604e-05,
"loss": 0.6434,
"step": 113500
},
{
"epoch": 1.89,
"learning_rate": 1.8559703468361135e-05,
"loss": 0.656,
"step": 114000
},
{
"epoch": 1.89,
"learning_rate": 1.8421807430941666e-05,
"loss": 0.6572,
"step": 114500
},
{
"epoch": 1.9,
"learning_rate": 1.8283911393522196e-05,
"loss": 0.6424,
"step": 115000
},
{
"epoch": 1.91,
"learning_rate": 1.8146015356102727e-05,
"loss": 0.6396,
"step": 115500
},
{
"epoch": 1.92,
"learning_rate": 1.8008119318683258e-05,
"loss": 0.644,
"step": 116000
},
{
"epoch": 1.93,
"learning_rate": 1.787022328126379e-05,
"loss": 0.6509,
"step": 116500
},
{
"epoch": 1.94,
"learning_rate": 1.7732327243844323e-05,
"loss": 0.6475,
"step": 117000
},
{
"epoch": 1.94,
"learning_rate": 1.7594431206424853e-05,
"loss": 0.6514,
"step": 117500
},
{
"epoch": 1.95,
"learning_rate": 1.7456535169005384e-05,
"loss": 0.6419,
"step": 118000
},
{
"epoch": 1.96,
"learning_rate": 1.7318639131585915e-05,
"loss": 0.6415,
"step": 118500
},
{
"epoch": 1.97,
"learning_rate": 1.7180743094166446e-05,
"loss": 0.655,
"step": 119000
},
{
"epoch": 1.98,
"learning_rate": 1.7042847056746976e-05,
"loss": 0.6384,
"step": 119500
},
{
"epoch": 1.99,
"learning_rate": 1.6904951019327507e-05,
"loss": 0.6439,
"step": 120000
},
{
"epoch": 1.99,
"learning_rate": 1.676705498190804e-05,
"loss": 0.6484,
"step": 120500
},
{
"epoch": 2.0,
"learning_rate": 1.6629158944488572e-05,
"loss": 0.6205,
"step": 121000
},
{
"epoch": 2.01,
"learning_rate": 1.6491262907069103e-05,
"loss": 0.5833,
"step": 121500
},
{
"epoch": 2.02,
"learning_rate": 1.6353366869649634e-05,
"loss": 0.5594,
"step": 122000
},
{
"epoch": 2.03,
"learning_rate": 1.6215470832230164e-05,
"loss": 0.5598,
"step": 122500
},
{
"epoch": 2.04,
"learning_rate": 1.6077574794810695e-05,
"loss": 0.5795,
"step": 123000
},
{
"epoch": 2.04,
"learning_rate": 1.5939678757391226e-05,
"loss": 0.5747,
"step": 123500
},
{
"epoch": 2.05,
"learning_rate": 1.580178271997176e-05,
"loss": 0.5647,
"step": 124000
},
{
"epoch": 2.06,
"learning_rate": 1.566388668255229e-05,
"loss": 0.5687,
"step": 124500
},
{
"epoch": 2.07,
"learning_rate": 1.5525990645132825e-05,
"loss": 0.5627,
"step": 125000
},
{
"epoch": 2.08,
"learning_rate": 1.5388094607713356e-05,
"loss": 0.5649,
"step": 125500
},
{
"epoch": 2.08,
"learning_rate": 1.5250198570293886e-05,
"loss": 0.5696,
"step": 126000
},
{
"epoch": 2.09,
"learning_rate": 1.5112302532874417e-05,
"loss": 0.5581,
"step": 126500
},
{
"epoch": 2.1,
"learning_rate": 1.4974406495454948e-05,
"loss": 0.5764,
"step": 127000
},
{
"epoch": 2.11,
"learning_rate": 1.483651045803548e-05,
"loss": 0.5727,
"step": 127500
},
{
"epoch": 2.12,
"learning_rate": 1.4698614420616011e-05,
"loss": 0.571,
"step": 128000
},
{
"epoch": 2.13,
"learning_rate": 1.4560718383196542e-05,
"loss": 0.5697,
"step": 128500
},
{
"epoch": 2.13,
"learning_rate": 1.4422822345777073e-05,
"loss": 0.5622,
"step": 129000
},
{
"epoch": 2.14,
"learning_rate": 1.4284926308357605e-05,
"loss": 0.5686,
"step": 129500
},
{
"epoch": 2.15,
"learning_rate": 1.4147030270938136e-05,
"loss": 0.5634,
"step": 130000
},
{
"epoch": 2.16,
"learning_rate": 1.4009134233518666e-05,
"loss": 0.5667,
"step": 130500
},
{
"epoch": 2.17,
"learning_rate": 1.3871238196099199e-05,
"loss": 0.5726,
"step": 131000
},
{
"epoch": 2.18,
"learning_rate": 1.373334215867973e-05,
"loss": 0.5589,
"step": 131500
},
{
"epoch": 2.18,
"learning_rate": 1.359544612126026e-05,
"loss": 0.5704,
"step": 132000
},
{
"epoch": 2.19,
"learning_rate": 1.3457550083840791e-05,
"loss": 0.5682,
"step": 132500
},
{
"epoch": 2.2,
"learning_rate": 1.3319654046421324e-05,
"loss": 0.5632,
"step": 133000
},
{
"epoch": 2.21,
"learning_rate": 1.3181758009001854e-05,
"loss": 0.5751,
"step": 133500
},
{
"epoch": 2.22,
"learning_rate": 1.3043861971582385e-05,
"loss": 0.5628,
"step": 134000
},
{
"epoch": 2.23,
"learning_rate": 1.2905965934162918e-05,
"loss": 0.5564,
"step": 134500
},
{
"epoch": 2.23,
"learning_rate": 1.2768069896743448e-05,
"loss": 0.5705,
"step": 135000
},
{
"epoch": 2.24,
"learning_rate": 1.2630173859323979e-05,
"loss": 0.5648,
"step": 135500
},
{
"epoch": 2.25,
"learning_rate": 1.249227782190451e-05,
"loss": 0.5666,
"step": 136000
},
{
"epoch": 2.26,
"learning_rate": 1.2354381784485042e-05,
"loss": 0.5694,
"step": 136500
},
{
"epoch": 2.27,
"learning_rate": 1.2216485747065573e-05,
"loss": 0.5712,
"step": 137000
},
{
"epoch": 2.28,
"learning_rate": 1.2078589709646104e-05,
"loss": 0.5756,
"step": 137500
},
{
"epoch": 2.28,
"learning_rate": 1.1940693672226636e-05,
"loss": 0.5672,
"step": 138000
},
{
"epoch": 2.29,
"learning_rate": 1.1802797634807167e-05,
"loss": 0.5718,
"step": 138500
},
{
"epoch": 2.3,
"learning_rate": 1.1664901597387698e-05,
"loss": 0.5551,
"step": 139000
},
{
"epoch": 2.31,
"learning_rate": 1.1527005559968228e-05,
"loss": 0.569,
"step": 139500
},
{
"epoch": 2.32,
"learning_rate": 1.138910952254876e-05,
"loss": 0.5707,
"step": 140000
},
{
"epoch": 2.32,
"learning_rate": 1.1251213485129292e-05,
"loss": 0.5576,
"step": 140500
},
{
"epoch": 2.33,
"learning_rate": 1.1113317447709822e-05,
"loss": 0.5793,
"step": 141000
},
{
"epoch": 2.34,
"learning_rate": 1.0975421410290355e-05,
"loss": 0.5605,
"step": 141500
},
{
"epoch": 2.35,
"learning_rate": 1.0837525372870886e-05,
"loss": 0.5587,
"step": 142000
},
{
"epoch": 2.36,
"learning_rate": 1.0699629335451416e-05,
"loss": 0.5652,
"step": 142500
},
{
"epoch": 2.37,
"learning_rate": 1.0561733298031947e-05,
"loss": 0.5503,
"step": 143000
},
{
"epoch": 2.37,
"learning_rate": 1.042383726061248e-05,
"loss": 0.5543,
"step": 143500
},
{
"epoch": 2.38,
"learning_rate": 1.028594122319301e-05,
"loss": 0.5702,
"step": 144000
},
{
"epoch": 2.39,
"learning_rate": 1.0148045185773541e-05,
"loss": 0.5558,
"step": 144500
},
{
"epoch": 2.4,
"learning_rate": 1.0010149148354073e-05,
"loss": 0.5527,
"step": 145000
},
{
"epoch": 2.41,
"learning_rate": 9.872253110934606e-06,
"loss": 0.5619,
"step": 145500
},
{
"epoch": 2.42,
"learning_rate": 9.734357073515137e-06,
"loss": 0.5557,
"step": 146000
},
{
"epoch": 2.42,
"learning_rate": 9.596461036095667e-06,
"loss": 0.5621,
"step": 146500
},
{
"epoch": 2.43,
"learning_rate": 9.4585649986762e-06,
"loss": 0.5554,
"step": 147000
},
{
"epoch": 2.44,
"learning_rate": 9.32066896125673e-06,
"loss": 0.5612,
"step": 147500
},
{
"epoch": 2.45,
"learning_rate": 9.182772923837261e-06,
"loss": 0.5614,
"step": 148000
},
{
"epoch": 2.46,
"learning_rate": 9.044876886417792e-06,
"loss": 0.5645,
"step": 148500
},
{
"epoch": 2.47,
"learning_rate": 8.906980848998324e-06,
"loss": 0.5613,
"step": 149000
},
{
"epoch": 2.47,
"learning_rate": 8.769084811578855e-06,
"loss": 0.5572,
"step": 149500
},
{
"epoch": 2.48,
"learning_rate": 8.631188774159386e-06,
"loss": 0.5582,
"step": 150000
},
{
"epoch": 2.49,
"learning_rate": 8.493292736739918e-06,
"loss": 0.5516,
"step": 150500
},
{
"epoch": 2.5,
"learning_rate": 8.355396699320449e-06,
"loss": 0.5477,
"step": 151000
},
{
"epoch": 2.51,
"learning_rate": 8.21750066190098e-06,
"loss": 0.5676,
"step": 151500
},
{
"epoch": 2.52,
"learning_rate": 8.07960462448151e-06,
"loss": 0.5593,
"step": 152000
},
{
"epoch": 2.52,
"learning_rate": 7.941708587062043e-06,
"loss": 0.565,
"step": 152500
},
{
"epoch": 2.53,
"learning_rate": 7.803812549642574e-06,
"loss": 0.5651,
"step": 153000
},
{
"epoch": 2.54,
"learning_rate": 7.665916512223105e-06,
"loss": 0.5492,
"step": 153500
},
{
"epoch": 2.55,
"learning_rate": 7.528020474803636e-06,
"loss": 0.5516,
"step": 154000
},
{
"epoch": 2.56,
"learning_rate": 7.390124437384168e-06,
"loss": 0.5579,
"step": 154500
},
{
"epoch": 2.56,
"learning_rate": 7.2522283999646985e-06,
"loss": 0.5543,
"step": 155000
},
{
"epoch": 2.57,
"learning_rate": 7.11433236254523e-06,
"loss": 0.5518,
"step": 155500
},
{
"epoch": 2.58,
"learning_rate": 6.976436325125761e-06,
"loss": 0.5446,
"step": 156000
},
{
"epoch": 2.59,
"learning_rate": 6.8385402877062925e-06,
"loss": 0.5551,
"step": 156500
},
{
"epoch": 2.6,
"learning_rate": 6.700644250286823e-06,
"loss": 0.5474,
"step": 157000
},
{
"epoch": 2.61,
"learning_rate": 6.562748212867355e-06,
"loss": 0.55,
"step": 157500
},
{
"epoch": 2.61,
"learning_rate": 6.424852175447886e-06,
"loss": 0.5522,
"step": 158000
},
{
"epoch": 2.62,
"learning_rate": 6.286956138028417e-06,
"loss": 0.5631,
"step": 158500
},
{
"epoch": 2.63,
"learning_rate": 6.14906010060895e-06,
"loss": 0.5435,
"step": 159000
},
{
"epoch": 2.64,
"learning_rate": 6.01116406318948e-06,
"loss": 0.5492,
"step": 159500
},
{
"epoch": 2.65,
"learning_rate": 5.873268025770012e-06,
"loss": 0.5424,
"step": 160000
},
{
"epoch": 2.66,
"learning_rate": 5.735371988350543e-06,
"loss": 0.5493,
"step": 160500
},
{
"epoch": 2.66,
"learning_rate": 5.597475950931074e-06,
"loss": 0.5415,
"step": 161000
},
{
"epoch": 2.67,
"learning_rate": 5.459579913511605e-06,
"loss": 0.5574,
"step": 161500
},
{
"epoch": 2.68,
"learning_rate": 5.321683876092137e-06,
"loss": 0.5408,
"step": 162000
},
{
"epoch": 2.69,
"learning_rate": 5.183787838672668e-06,
"loss": 0.5486,
"step": 162500
},
{
"epoch": 2.7,
"learning_rate": 5.0458918012532e-06,
"loss": 0.5493,
"step": 163000
},
{
"epoch": 2.71,
"learning_rate": 4.9079957638337306e-06,
"loss": 0.542,
"step": 163500
},
{
"epoch": 2.71,
"learning_rate": 4.770099726414262e-06,
"loss": 0.5444,
"step": 164000
},
{
"epoch": 2.72,
"learning_rate": 4.632203688994794e-06,
"loss": 0.5445,
"step": 164500
},
{
"epoch": 2.73,
"learning_rate": 4.4943076515753245e-06,
"loss": 0.5449,
"step": 165000
},
{
"epoch": 2.74,
"learning_rate": 4.356411614155856e-06,
"loss": 0.5479,
"step": 165500
},
{
"epoch": 2.75,
"learning_rate": 4.218515576736387e-06,
"loss": 0.5568,
"step": 166000
},
{
"epoch": 2.76,
"learning_rate": 4.0806195393169184e-06,
"loss": 0.5467,
"step": 166500
},
{
"epoch": 2.76,
"learning_rate": 3.942723501897449e-06,
"loss": 0.5464,
"step": 167000
},
{
"epoch": 2.77,
"learning_rate": 3.8048274644779808e-06,
"loss": 0.544,
"step": 167500
},
{
"epoch": 2.78,
"learning_rate": 3.666931427058512e-06,
"loss": 0.5423,
"step": 168000
},
{
"epoch": 2.79,
"learning_rate": 3.529035389639043e-06,
"loss": 0.5406,
"step": 168500
},
{
"epoch": 2.8,
"learning_rate": 3.3911393522195743e-06,
"loss": 0.5413,
"step": 169000
},
{
"epoch": 2.8,
"learning_rate": 3.2532433148001063e-06,
"loss": 0.543,
"step": 169500
},
{
"epoch": 2.81,
"learning_rate": 3.1153472773806375e-06,
"loss": 0.538,
"step": 170000
},
{
"epoch": 2.82,
"learning_rate": 2.9774512399611686e-06,
"loss": 0.5364,
"step": 170500
},
{
"epoch": 2.83,
"learning_rate": 2.8395552025417e-06,
"loss": 0.5379,
"step": 171000
},
{
"epoch": 2.84,
"learning_rate": 2.7016591651222314e-06,
"loss": 0.5479,
"step": 171500
},
{
"epoch": 2.85,
"learning_rate": 2.5637631277027626e-06,
"loss": 0.5438,
"step": 172000
},
{
"epoch": 2.85,
"learning_rate": 2.4258670902832938e-06,
"loss": 0.5335,
"step": 172500
},
{
"epoch": 2.86,
"learning_rate": 2.287971052863825e-06,
"loss": 0.5426,
"step": 173000
},
{
"epoch": 2.87,
"learning_rate": 2.150075015444356e-06,
"loss": 0.5287,
"step": 173500
},
{
"epoch": 2.88,
"learning_rate": 2.0121789780248873e-06,
"loss": 0.5423,
"step": 174000
},
{
"epoch": 2.89,
"learning_rate": 1.874282940605419e-06,
"loss": 0.5384,
"step": 174500
},
{
"epoch": 2.9,
"learning_rate": 1.7363869031859502e-06,
"loss": 0.5377,
"step": 175000
},
{
"epoch": 2.9,
"learning_rate": 1.5984908657664814e-06,
"loss": 0.532,
"step": 175500
},
{
"epoch": 2.91,
"learning_rate": 1.4605948283470128e-06,
"loss": 0.5463,
"step": 176000
},
{
"epoch": 2.92,
"learning_rate": 1.322698790927544e-06,
"loss": 0.5345,
"step": 176500
},
{
"epoch": 2.93,
"learning_rate": 1.1848027535080751e-06,
"loss": 0.5428,
"step": 177000
},
{
"epoch": 2.94,
"learning_rate": 1.0469067160886065e-06,
"loss": 0.5413,
"step": 177500
},
{
"epoch": 2.95,
"learning_rate": 9.090106786691378e-07,
"loss": 0.538,
"step": 178000
},
{
"epoch": 2.95,
"learning_rate": 7.711146412496691e-07,
"loss": 0.536,
"step": 178500
},
{
"epoch": 2.96,
"learning_rate": 6.332186038302004e-07,
"loss": 0.5484,
"step": 179000
},
{
"epoch": 2.97,
"learning_rate": 4.953225664107316e-07,
"loss": 0.548,
"step": 179500
},
{
"epoch": 2.98,
"learning_rate": 3.574265289912629e-07,
"loss": 0.5335,
"step": 180000
},
{
"epoch": 2.99,
"learning_rate": 2.195304915717942e-07,
"loss": 0.5375,
"step": 180500
},
{
"epoch": 3.0,
"learning_rate": 8.163445415232549e-08,
"loss": 0.5442,
"step": 181000
},
{
"epoch": 3.0,
"step": 181296,
"total_flos": 2.0627822520336384e+17,
"train_loss": 0.7403765432559616,
"train_runtime": 55016.1932,
"train_samples_per_second": 32.953,
"train_steps_per_second": 3.295
}
],
"max_steps": 181296,
"num_train_epochs": 3,
"total_flos": 2.0627822520336384e+17,
"trial_name": null,
"trial_params": null
}