ds-guanaco / trainer_state.json
TinyPixel's picture
Upload folder using huggingface_hub
12ea6cd
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.9993906154783668,
"eval_steps": 500,
"global_step": 615,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0,
"learning_rate": 7.142857142857143e-07,
"loss": 1.2236,
"step": 2
},
{
"epoch": 0.01,
"learning_rate": 1.4285714285714286e-06,
"loss": 1.4631,
"step": 4
},
{
"epoch": 0.01,
"learning_rate": 2.1428571428571427e-06,
"loss": 1.405,
"step": 6
},
{
"epoch": 0.01,
"learning_rate": 2.8571428571428573e-06,
"loss": 1.7103,
"step": 8
},
{
"epoch": 0.02,
"learning_rate": 3.5714285714285718e-06,
"loss": 1.6165,
"step": 10
},
{
"epoch": 0.02,
"learning_rate": 4.2857142857142855e-06,
"loss": 1.7487,
"step": 12
},
{
"epoch": 0.02,
"learning_rate": 5e-06,
"loss": 1.7254,
"step": 14
},
{
"epoch": 0.03,
"learning_rate": 5.7142857142857145e-06,
"loss": 1.6604,
"step": 16
},
{
"epoch": 0.03,
"learning_rate": 6.4285714285714295e-06,
"loss": 1.622,
"step": 18
},
{
"epoch": 0.03,
"learning_rate": 7.1428571428571436e-06,
"loss": 1.8001,
"step": 20
},
{
"epoch": 0.04,
"learning_rate": 7.857142857142858e-06,
"loss": 1.5987,
"step": 22
},
{
"epoch": 0.04,
"learning_rate": 8.571428571428571e-06,
"loss": 1.7409,
"step": 24
},
{
"epoch": 0.04,
"learning_rate": 9.285714285714288e-06,
"loss": 1.9162,
"step": 26
},
{
"epoch": 0.05,
"learning_rate": 1e-05,
"loss": 1.8572,
"step": 28
},
{
"epoch": 0.05,
"learning_rate": 1.0714285714285714e-05,
"loss": 1.9669,
"step": 30
},
{
"epoch": 0.05,
"learning_rate": 1.1428571428571429e-05,
"loss": 1.9432,
"step": 32
},
{
"epoch": 0.06,
"learning_rate": 1.2142857142857142e-05,
"loss": 1.9297,
"step": 34
},
{
"epoch": 0.06,
"learning_rate": 1.2857142857142859e-05,
"loss": 2.0854,
"step": 36
},
{
"epoch": 0.06,
"learning_rate": 1.3571428571428574e-05,
"loss": 2.092,
"step": 38
},
{
"epoch": 0.07,
"learning_rate": 1.4285714285714287e-05,
"loss": 2.1925,
"step": 40
},
{
"epoch": 0.07,
"learning_rate": 1.5000000000000002e-05,
"loss": 2.3367,
"step": 42
},
{
"epoch": 0.07,
"learning_rate": 1.5714285714285715e-05,
"loss": 2.4136,
"step": 44
},
{
"epoch": 0.07,
"learning_rate": 1.642857142857143e-05,
"loss": 2.5252,
"step": 46
},
{
"epoch": 0.08,
"learning_rate": 1.7142857142857142e-05,
"loss": 2.5727,
"step": 48
},
{
"epoch": 0.08,
"learning_rate": 1.785714285714286e-05,
"loss": 3.1009,
"step": 50
},
{
"epoch": 0.08,
"learning_rate": 1.8571428571428575e-05,
"loss": 1.4247,
"step": 52
},
{
"epoch": 0.09,
"learning_rate": 1.928571428571429e-05,
"loss": 1.3148,
"step": 54
},
{
"epoch": 0.09,
"learning_rate": 2e-05,
"loss": 1.6329,
"step": 56
},
{
"epoch": 0.09,
"learning_rate": 1.999993832507735e-05,
"loss": 1.4144,
"step": 58
},
{
"epoch": 0.1,
"learning_rate": 1.9999753301070156e-05,
"loss": 1.6329,
"step": 60
},
{
"epoch": 0.1,
"learning_rate": 1.9999444930260684e-05,
"loss": 1.5957,
"step": 62
},
{
"epoch": 0.1,
"learning_rate": 1.9999013216452688e-05,
"loss": 1.4545,
"step": 64
},
{
"epoch": 0.11,
"learning_rate": 1.999845816497135e-05,
"loss": 1.7986,
"step": 66
},
{
"epoch": 0.11,
"learning_rate": 1.9997779782663217e-05,
"loss": 1.7363,
"step": 68
},
{
"epoch": 0.11,
"learning_rate": 1.999697807789613e-05,
"loss": 1.7775,
"step": 70
},
{
"epoch": 0.12,
"learning_rate": 1.99960530605591e-05,
"loss": 1.6756,
"step": 72
},
{
"epoch": 0.12,
"learning_rate": 1.9995004742062206e-05,
"loss": 1.5798,
"step": 74
},
{
"epoch": 0.12,
"learning_rate": 1.999383313533644e-05,
"loss": 1.8129,
"step": 76
},
{
"epoch": 0.13,
"learning_rate": 1.9992538254833548e-05,
"loss": 1.7426,
"step": 78
},
{
"epoch": 0.13,
"learning_rate": 1.9991120116525866e-05,
"loss": 1.7854,
"step": 80
},
{
"epoch": 0.13,
"learning_rate": 1.9989578737906107e-05,
"loss": 1.9305,
"step": 82
},
{
"epoch": 0.14,
"learning_rate": 1.9987914137987153e-05,
"loss": 1.9058,
"step": 84
},
{
"epoch": 0.14,
"learning_rate": 1.9986126337301814e-05,
"loss": 1.8474,
"step": 86
},
{
"epoch": 0.14,
"learning_rate": 1.9984215357902586e-05,
"loss": 1.8505,
"step": 88
},
{
"epoch": 0.15,
"learning_rate": 1.9982181223361373e-05,
"loss": 1.8879,
"step": 90
},
{
"epoch": 0.15,
"learning_rate": 1.9980023958769195e-05,
"loss": 2.229,
"step": 92
},
{
"epoch": 0.15,
"learning_rate": 1.9977743590735866e-05,
"loss": 2.0788,
"step": 94
},
{
"epoch": 0.16,
"learning_rate": 1.9975340147389707e-05,
"loss": 2.3521,
"step": 96
},
{
"epoch": 0.16,
"learning_rate": 1.997281365837714e-05,
"loss": 2.2187,
"step": 98
},
{
"epoch": 0.16,
"learning_rate": 1.9970164154862375e-05,
"loss": 2.2225,
"step": 100
},
{
"epoch": 0.17,
"learning_rate": 1.9967391669526995e-05,
"loss": 1.2585,
"step": 102
},
{
"epoch": 0.17,
"learning_rate": 1.996449623656956e-05,
"loss": 1.4347,
"step": 104
},
{
"epoch": 0.17,
"learning_rate": 1.9961477891705203e-05,
"loss": 1.552,
"step": 106
},
{
"epoch": 0.18,
"learning_rate": 1.9958336672165147e-05,
"loss": 1.571,
"step": 108
},
{
"epoch": 0.18,
"learning_rate": 1.9955072616696294e-05,
"loss": 1.5051,
"step": 110
},
{
"epoch": 0.18,
"learning_rate": 1.9951685765560717e-05,
"loss": 1.6931,
"step": 112
},
{
"epoch": 0.19,
"learning_rate": 1.994817616053517e-05,
"loss": 1.5936,
"step": 114
},
{
"epoch": 0.19,
"learning_rate": 1.994454384491058e-05,
"loss": 1.5303,
"step": 116
},
{
"epoch": 0.19,
"learning_rate": 1.9940788863491503e-05,
"loss": 1.5092,
"step": 118
},
{
"epoch": 0.2,
"learning_rate": 1.9936911262595574e-05,
"loss": 1.678,
"step": 120
},
{
"epoch": 0.2,
"learning_rate": 1.993291109005294e-05,
"loss": 1.4946,
"step": 122
},
{
"epoch": 0.2,
"learning_rate": 1.9928788395205673e-05,
"loss": 1.7905,
"step": 124
},
{
"epoch": 0.2,
"learning_rate": 1.9924543228907147e-05,
"loss": 1.788,
"step": 126
},
{
"epoch": 0.21,
"learning_rate": 1.992017564352142e-05,
"loss": 1.6872,
"step": 128
},
{
"epoch": 0.21,
"learning_rate": 1.9915685692922592e-05,
"loss": 1.7038,
"step": 130
},
{
"epoch": 0.21,
"learning_rate": 1.9911073432494138e-05,
"loss": 1.7661,
"step": 132
},
{
"epoch": 0.22,
"learning_rate": 1.9906338919128214e-05,
"loss": 1.7958,
"step": 134
},
{
"epoch": 0.22,
"learning_rate": 1.990148221122497e-05,
"loss": 1.8836,
"step": 136
},
{
"epoch": 0.22,
"learning_rate": 1.9896503368691826e-05,
"loss": 1.9028,
"step": 138
},
{
"epoch": 0.23,
"learning_rate": 1.989140245294272e-05,
"loss": 2.077,
"step": 140
},
{
"epoch": 0.23,
"learning_rate": 1.988617952689738e-05,
"loss": 1.9555,
"step": 142
},
{
"epoch": 0.23,
"learning_rate": 1.988083465498051e-05,
"loss": 2.2974,
"step": 144
},
{
"epoch": 0.24,
"learning_rate": 1.9875367903121022e-05,
"loss": 2.1295,
"step": 146
},
{
"epoch": 0.24,
"learning_rate": 1.9869779338751217e-05,
"loss": 2.2783,
"step": 148
},
{
"epoch": 0.24,
"learning_rate": 1.9864069030805955e-05,
"loss": 2.0852,
"step": 150
},
{
"epoch": 0.25,
"learning_rate": 1.9858237049721793e-05,
"loss": 1.5204,
"step": 152
},
{
"epoch": 0.25,
"learning_rate": 1.9852283467436124e-05,
"loss": 1.4498,
"step": 154
},
{
"epoch": 0.25,
"learning_rate": 1.98462083573863e-05,
"loss": 1.4835,
"step": 156
},
{
"epoch": 0.26,
"learning_rate": 1.9840011794508702e-05,
"loss": 1.5079,
"step": 158
},
{
"epoch": 0.26,
"learning_rate": 1.983369385523784e-05,
"loss": 1.5743,
"step": 160
},
{
"epoch": 0.26,
"learning_rate": 1.98272546175054e-05,
"loss": 1.5409,
"step": 162
},
{
"epoch": 0.27,
"learning_rate": 1.982069416073928e-05,
"loss": 1.5208,
"step": 164
},
{
"epoch": 0.27,
"learning_rate": 1.9814012565862607e-05,
"loss": 1.7327,
"step": 166
},
{
"epoch": 0.27,
"learning_rate": 1.9807209915292754e-05,
"loss": 1.7466,
"step": 168
},
{
"epoch": 0.28,
"learning_rate": 1.9800286292940313e-05,
"loss": 1.6901,
"step": 170
},
{
"epoch": 0.28,
"learning_rate": 1.9793241784208054e-05,
"loss": 1.7233,
"step": 172
},
{
"epoch": 0.28,
"learning_rate": 1.978607647598989e-05,
"loss": 1.6692,
"step": 174
},
{
"epoch": 0.29,
"learning_rate": 1.9778790456669777e-05,
"loss": 1.7248,
"step": 176
},
{
"epoch": 0.29,
"learning_rate": 1.9771383816120658e-05,
"loss": 1.8977,
"step": 178
},
{
"epoch": 0.29,
"learning_rate": 1.976385664570333e-05,
"loss": 1.8373,
"step": 180
},
{
"epoch": 0.3,
"learning_rate": 1.9756209038265317e-05,
"loss": 1.8188,
"step": 182
},
{
"epoch": 0.3,
"learning_rate": 1.9748441088139746e-05,
"loss": 1.8918,
"step": 184
},
{
"epoch": 0.3,
"learning_rate": 1.9740552891144157e-05,
"loss": 1.9215,
"step": 186
},
{
"epoch": 0.31,
"learning_rate": 1.973254454457934e-05,
"loss": 1.9047,
"step": 188
},
{
"epoch": 0.31,
"learning_rate": 1.9724416147228127e-05,
"loss": 2.0088,
"step": 190
},
{
"epoch": 0.31,
"learning_rate": 1.971616779935417e-05,
"loss": 2.1103,
"step": 192
},
{
"epoch": 0.32,
"learning_rate": 1.9707799602700712e-05,
"loss": 2.1014,
"step": 194
},
{
"epoch": 0.32,
"learning_rate": 1.9699311660489333e-05,
"loss": 1.8813,
"step": 196
},
{
"epoch": 0.32,
"learning_rate": 1.969070407741867e-05,
"loss": 2.2869,
"step": 198
},
{
"epoch": 0.33,
"learning_rate": 1.968197695966312e-05,
"loss": 2.2136,
"step": 200
},
{
"epoch": 0.33,
"learning_rate": 1.9673130414871556e-05,
"loss": 1.473,
"step": 202
},
{
"epoch": 0.33,
"learning_rate": 1.9664164552165957e-05,
"loss": 1.4018,
"step": 204
},
{
"epoch": 0.33,
"learning_rate": 1.9655079482140115e-05,
"loss": 1.3433,
"step": 206
},
{
"epoch": 0.34,
"learning_rate": 1.964587531685822e-05,
"loss": 1.4818,
"step": 208
},
{
"epoch": 0.34,
"learning_rate": 1.9636552169853514e-05,
"loss": 1.5572,
"step": 210
},
{
"epoch": 0.34,
"learning_rate": 1.9627110156126862e-05,
"loss": 1.5843,
"step": 212
},
{
"epoch": 0.35,
"learning_rate": 1.9617549392145365e-05,
"loss": 1.6586,
"step": 214
},
{
"epoch": 0.35,
"learning_rate": 1.96078699958409e-05,
"loss": 1.4021,
"step": 216
},
{
"epoch": 0.35,
"learning_rate": 1.9598072086608663e-05,
"loss": 1.4863,
"step": 218
},
{
"epoch": 0.36,
"learning_rate": 1.958815578530572e-05,
"loss": 1.6731,
"step": 220
},
{
"epoch": 0.36,
"learning_rate": 1.9578121214249485e-05,
"loss": 1.6004,
"step": 222
},
{
"epoch": 0.36,
"learning_rate": 1.956796849721625e-05,
"loss": 1.5723,
"step": 224
},
{
"epoch": 0.37,
"learning_rate": 1.9557697759439613e-05,
"loss": 1.7214,
"step": 226
},
{
"epoch": 0.37,
"learning_rate": 1.954730912760897e-05,
"loss": 1.7316,
"step": 228
},
{
"epoch": 0.37,
"learning_rate": 1.9536802729867926e-05,
"loss": 1.7336,
"step": 230
},
{
"epoch": 0.38,
"learning_rate": 1.9526178695812747e-05,
"loss": 1.7207,
"step": 232
},
{
"epoch": 0.38,
"learning_rate": 1.9515437156490724e-05,
"loss": 2.0022,
"step": 234
},
{
"epoch": 0.38,
"learning_rate": 1.950457824439857e-05,
"loss": 1.7205,
"step": 236
},
{
"epoch": 0.39,
"learning_rate": 1.9493602093480807e-05,
"loss": 1.9002,
"step": 238
},
{
"epoch": 0.39,
"learning_rate": 1.9482508839128087e-05,
"loss": 2.0414,
"step": 240
},
{
"epoch": 0.39,
"learning_rate": 1.9471298618175523e-05,
"loss": 2.1061,
"step": 242
},
{
"epoch": 0.4,
"learning_rate": 1.9459971568901026e-05,
"loss": 2.2256,
"step": 244
},
{
"epoch": 0.4,
"learning_rate": 1.944852783102357e-05,
"loss": 2.0902,
"step": 246
},
{
"epoch": 0.4,
"learning_rate": 1.9436967545701485e-05,
"loss": 2.1776,
"step": 248
},
{
"epoch": 0.41,
"learning_rate": 1.9425290855530705e-05,
"loss": 2.1136,
"step": 250
},
{
"epoch": 0.41,
"learning_rate": 1.9413497904543033e-05,
"loss": 1.2511,
"step": 252
},
{
"epoch": 0.41,
"learning_rate": 1.9401588838204334e-05,
"loss": 1.3177,
"step": 254
},
{
"epoch": 0.42,
"learning_rate": 1.9389563803412753e-05,
"loss": 1.4358,
"step": 256
},
{
"epoch": 0.42,
"learning_rate": 1.9377422948496912e-05,
"loss": 1.672,
"step": 258
},
{
"epoch": 0.42,
"learning_rate": 1.9365166423214065e-05,
"loss": 1.6008,
"step": 260
},
{
"epoch": 0.43,
"learning_rate": 1.9352794378748267e-05,
"loss": 1.5744,
"step": 262
},
{
"epoch": 0.43,
"learning_rate": 1.934030696770849e-05,
"loss": 1.4593,
"step": 264
},
{
"epoch": 0.43,
"learning_rate": 1.932770434412676e-05,
"loss": 1.7566,
"step": 266
},
{
"epoch": 0.44,
"learning_rate": 1.931498666345624e-05,
"loss": 1.6279,
"step": 268
},
{
"epoch": 0.44,
"learning_rate": 1.9302154082569328e-05,
"loss": 1.5859,
"step": 270
},
{
"epoch": 0.44,
"learning_rate": 1.928920675975571e-05,
"loss": 1.5577,
"step": 272
},
{
"epoch": 0.45,
"learning_rate": 1.9276144854720412e-05,
"loss": 1.5837,
"step": 274
},
{
"epoch": 0.45,
"learning_rate": 1.9262968528581828e-05,
"loss": 1.6993,
"step": 276
},
{
"epoch": 0.45,
"learning_rate": 1.9249677943869742e-05,
"loss": 1.6503,
"step": 278
},
{
"epoch": 0.46,
"learning_rate": 1.9236273264523304e-05,
"loss": 1.8387,
"step": 280
},
{
"epoch": 0.46,
"learning_rate": 1.9222754655889035e-05,
"loss": 1.7513,
"step": 282
},
{
"epoch": 0.46,
"learning_rate": 1.9209122284718757e-05,
"loss": 1.842,
"step": 284
},
{
"epoch": 0.46,
"learning_rate": 1.919537631916756e-05,
"loss": 1.9954,
"step": 286
},
{
"epoch": 0.47,
"learning_rate": 1.9181516928791715e-05,
"loss": 2.0364,
"step": 288
},
{
"epoch": 0.47,
"learning_rate": 1.916754428454659e-05,
"loss": 2.0113,
"step": 290
},
{
"epoch": 0.47,
"learning_rate": 1.9153458558784536e-05,
"loss": 2.0972,
"step": 292
},
{
"epoch": 0.48,
"learning_rate": 1.9139259925252756e-05,
"loss": 2.1826,
"step": 294
},
{
"epoch": 0.48,
"learning_rate": 1.912494855909118e-05,
"loss": 2.2134,
"step": 296
},
{
"epoch": 0.48,
"learning_rate": 1.911052463683029e-05,
"loss": 2.1347,
"step": 298
},
{
"epoch": 0.49,
"learning_rate": 1.9095988336388945e-05,
"loss": 2.1557,
"step": 300
},
{
"epoch": 0.49,
"learning_rate": 1.908133983707218e-05,
"loss": 1.6206,
"step": 302
},
{
"epoch": 0.49,
"learning_rate": 1.906657931956901e-05,
"loss": 1.466,
"step": 304
},
{
"epoch": 0.5,
"learning_rate": 1.9051706965950192e-05,
"loss": 1.4884,
"step": 306
},
{
"epoch": 0.5,
"learning_rate": 1.9036722959665975e-05,
"loss": 1.485,
"step": 308
},
{
"epoch": 0.5,
"learning_rate": 1.9021627485543844e-05,
"loss": 1.6297,
"step": 310
},
{
"epoch": 0.51,
"learning_rate": 1.9006420729786246e-05,
"loss": 1.6544,
"step": 312
},
{
"epoch": 0.51,
"learning_rate": 1.899110287996827e-05,
"loss": 1.552,
"step": 314
},
{
"epoch": 0.51,
"learning_rate": 1.897567412503536e-05,
"loss": 1.7586,
"step": 316
},
{
"epoch": 0.52,
"learning_rate": 1.8960134655300966e-05,
"loss": 1.6673,
"step": 318
},
{
"epoch": 0.52,
"learning_rate": 1.894448466244421e-05,
"loss": 1.6194,
"step": 320
},
{
"epoch": 0.52,
"learning_rate": 1.8928724339507515e-05,
"loss": 1.4731,
"step": 322
},
{
"epoch": 0.53,
"learning_rate": 1.8912853880894215e-05,
"loss": 1.6042,
"step": 324
},
{
"epoch": 0.53,
"learning_rate": 1.8896873482366173e-05,
"loss": 1.7247,
"step": 326
},
{
"epoch": 0.53,
"learning_rate": 1.8880783341041357e-05,
"loss": 1.7958,
"step": 328
},
{
"epoch": 0.54,
"learning_rate": 1.8864583655391417e-05,
"loss": 1.6097,
"step": 330
},
{
"epoch": 0.54,
"learning_rate": 1.8848274625239216e-05,
"loss": 1.7074,
"step": 332
},
{
"epoch": 0.54,
"learning_rate": 1.8831856451756394e-05,
"loss": 1.928,
"step": 334
},
{
"epoch": 0.55,
"learning_rate": 1.881532933746087e-05,
"loss": 1.7286,
"step": 336
},
{
"epoch": 0.55,
"learning_rate": 1.879869348621433e-05,
"loss": 1.7516,
"step": 338
},
{
"epoch": 0.55,
"learning_rate": 1.8781949103219758e-05,
"loss": 1.95,
"step": 340
},
{
"epoch": 0.56,
"learning_rate": 1.876509639501885e-05,
"loss": 1.893,
"step": 342
},
{
"epoch": 0.56,
"learning_rate": 1.8748135569489504e-05,
"loss": 2.0016,
"step": 344
},
{
"epoch": 0.56,
"learning_rate": 1.8731066835843237e-05,
"loss": 2.1922,
"step": 346
},
{
"epoch": 0.57,
"learning_rate": 1.8713890404622618e-05,
"loss": 2.1049,
"step": 348
},
{
"epoch": 0.57,
"learning_rate": 1.869660648769866e-05,
"loss": 2.3154,
"step": 350
},
{
"epoch": 0.57,
"learning_rate": 1.867921529826821e-05,
"loss": 1.2,
"step": 352
},
{
"epoch": 0.58,
"learning_rate": 1.8661717050851323e-05,
"loss": 1.3897,
"step": 354
},
{
"epoch": 0.58,
"learning_rate": 1.8644111961288605e-05,
"loss": 1.4177,
"step": 356
},
{
"epoch": 0.58,
"learning_rate": 1.8626400246738568e-05,
"loss": 1.3511,
"step": 358
},
{
"epoch": 0.59,
"learning_rate": 1.8608582125674933e-05,
"loss": 1.6614,
"step": 360
},
{
"epoch": 0.59,
"learning_rate": 1.8590657817883952e-05,
"loss": 1.5387,
"step": 362
},
{
"epoch": 0.59,
"learning_rate": 1.8572627544461682e-05,
"loss": 1.6492,
"step": 364
},
{
"epoch": 0.59,
"learning_rate": 1.8554491527811266e-05,
"loss": 1.5073,
"step": 366
},
{
"epoch": 0.6,
"learning_rate": 1.8536249991640192e-05,
"loss": 1.7497,
"step": 368
},
{
"epoch": 0.6,
"learning_rate": 1.8517903160957523e-05,
"loss": 1.4961,
"step": 370
},
{
"epoch": 0.6,
"learning_rate": 1.8499451262071134e-05,
"loss": 1.7061,
"step": 372
},
{
"epoch": 0.61,
"learning_rate": 1.848089452258491e-05,
"loss": 1.6356,
"step": 374
},
{
"epoch": 0.61,
"learning_rate": 1.846223317139595e-05,
"loss": 1.6088,
"step": 376
},
{
"epoch": 0.61,
"learning_rate": 1.844346743869173e-05,
"loss": 1.6825,
"step": 378
},
{
"epoch": 0.62,
"learning_rate": 1.8424597555947268e-05,
"loss": 1.6737,
"step": 380
},
{
"epoch": 0.62,
"learning_rate": 1.840562375592228e-05,
"loss": 1.8381,
"step": 382
},
{
"epoch": 0.62,
"learning_rate": 1.8386546272658296e-05,
"loss": 1.8862,
"step": 384
},
{
"epoch": 0.63,
"learning_rate": 1.8367365341475777e-05,
"loss": 1.8186,
"step": 386
},
{
"epoch": 0.63,
"learning_rate": 1.834808119897121e-05,
"loss": 1.8536,
"step": 388
},
{
"epoch": 0.63,
"learning_rate": 1.8328694083014196e-05,
"loss": 2.0862,
"step": 390
},
{
"epoch": 0.64,
"learning_rate": 1.830920423274451e-05,
"loss": 2.2656,
"step": 392
},
{
"epoch": 0.64,
"learning_rate": 1.8289611888569158e-05,
"loss": 2.085,
"step": 394
},
{
"epoch": 0.64,
"learning_rate": 1.8269917292159393e-05,
"loss": 2.2241,
"step": 396
},
{
"epoch": 0.65,
"learning_rate": 1.8250120686447767e-05,
"loss": 2.0626,
"step": 398
},
{
"epoch": 0.65,
"learning_rate": 1.82302223156251e-05,
"loss": 2.3965,
"step": 400
},
{
"epoch": 0.65,
"learning_rate": 1.8210222425137485e-05,
"loss": 1.4121,
"step": 402
},
{
"epoch": 0.66,
"learning_rate": 1.8190121261683268e-05,
"loss": 1.4354,
"step": 404
},
{
"epoch": 0.66,
"learning_rate": 1.816991907320999e-05,
"loss": 1.493,
"step": 406
},
{
"epoch": 0.66,
"learning_rate": 1.8149616108911327e-05,
"loss": 1.5228,
"step": 408
},
{
"epoch": 0.67,
"learning_rate": 1.8129212619224034e-05,
"loss": 1.4622,
"step": 410
},
{
"epoch": 0.67,
"learning_rate": 1.8108708855824838e-05,
"loss": 1.6105,
"step": 412
},
{
"epoch": 0.67,
"learning_rate": 1.808810507162735e-05,
"loss": 1.4222,
"step": 414
},
{
"epoch": 0.68,
"learning_rate": 1.8067401520778918e-05,
"loss": 1.5116,
"step": 416
},
{
"epoch": 0.68,
"learning_rate": 1.8046598458657528e-05,
"loss": 1.6267,
"step": 418
},
{
"epoch": 0.68,
"learning_rate": 1.8025696141868635e-05,
"loss": 1.6338,
"step": 420
},
{
"epoch": 0.69,
"learning_rate": 1.800469482824198e-05,
"loss": 1.6313,
"step": 422
},
{
"epoch": 0.69,
"learning_rate": 1.798359477682845e-05,
"loss": 1.6542,
"step": 424
},
{
"epoch": 0.69,
"learning_rate": 1.7962396247896855e-05,
"loss": 1.7611,
"step": 426
},
{
"epoch": 0.7,
"learning_rate": 1.7941099502930716e-05,
"loss": 1.6318,
"step": 428
},
{
"epoch": 0.7,
"learning_rate": 1.7919704804625055e-05,
"loss": 1.7348,
"step": 430
},
{
"epoch": 0.7,
"learning_rate": 1.789821241688315e-05,
"loss": 1.7121,
"step": 432
},
{
"epoch": 0.71,
"learning_rate": 1.787662260481326e-05,
"loss": 1.8076,
"step": 434
},
{
"epoch": 0.71,
"learning_rate": 1.785493563472539e-05,
"loss": 1.9255,
"step": 436
},
{
"epoch": 0.71,
"learning_rate": 1.7833151774127978e-05,
"loss": 1.8057,
"step": 438
},
{
"epoch": 0.72,
"learning_rate": 1.781127129172461e-05,
"loss": 1.8363,
"step": 440
},
{
"epoch": 0.72,
"learning_rate": 1.7789294457410693e-05,
"loss": 2.1584,
"step": 442
},
{
"epoch": 0.72,
"learning_rate": 1.7767221542270146e-05,
"loss": 2.0338,
"step": 444
},
{
"epoch": 0.72,
"learning_rate": 1.7745052818572033e-05,
"loss": 2.1332,
"step": 446
},
{
"epoch": 0.73,
"learning_rate": 1.772278855976721e-05,
"loss": 2.0207,
"step": 448
},
{
"epoch": 0.73,
"learning_rate": 1.770042904048498e-05,
"loss": 1.9562,
"step": 450
},
{
"epoch": 0.73,
"learning_rate": 1.7677974536529657e-05,
"loss": 1.4179,
"step": 452
},
{
"epoch": 0.74,
"learning_rate": 1.76554253248772e-05,
"loss": 1.306,
"step": 454
},
{
"epoch": 0.74,
"learning_rate": 1.7632781683671787e-05,
"loss": 1.5095,
"step": 456
},
{
"epoch": 0.74,
"learning_rate": 1.7610043892222382e-05,
"loss": 1.4135,
"step": 458
},
{
"epoch": 0.75,
"learning_rate": 1.7587212230999298e-05,
"loss": 1.665,
"step": 460
},
{
"epoch": 0.75,
"learning_rate": 1.7564286981630713e-05,
"loss": 1.527,
"step": 462
},
{
"epoch": 0.75,
"learning_rate": 1.7541268426899222e-05,
"loss": 1.515,
"step": 464
},
{
"epoch": 0.76,
"learning_rate": 1.751815685073835e-05,
"loss": 1.544,
"step": 466
},
{
"epoch": 0.76,
"learning_rate": 1.7494952538229034e-05,
"loss": 1.6127,
"step": 468
},
{
"epoch": 0.76,
"learning_rate": 1.7471655775596097e-05,
"loss": 1.5762,
"step": 470
},
{
"epoch": 0.77,
"learning_rate": 1.7448266850204754e-05,
"loss": 1.7019,
"step": 472
},
{
"epoch": 0.77,
"learning_rate": 1.7424786050557036e-05,
"loss": 1.6097,
"step": 474
},
{
"epoch": 0.77,
"learning_rate": 1.740121366628824e-05,
"loss": 1.6101,
"step": 476
},
{
"epoch": 0.78,
"learning_rate": 1.7377549988163373e-05,
"loss": 1.6759,
"step": 478
},
{
"epoch": 0.78,
"learning_rate": 1.7353795308073526e-05,
"loss": 1.7808,
"step": 480
},
{
"epoch": 0.78,
"learning_rate": 1.7329949919032315e-05,
"loss": 1.6366,
"step": 482
},
{
"epoch": 0.79,
"learning_rate": 1.7306014115172244e-05,
"loss": 1.8784,
"step": 484
},
{
"epoch": 0.79,
"learning_rate": 1.7281988191741085e-05,
"loss": 1.7896,
"step": 486
},
{
"epoch": 0.79,
"learning_rate": 1.7257872445098232e-05,
"loss": 1.9701,
"step": 488
},
{
"epoch": 0.8,
"learning_rate": 1.7233667172711045e-05,
"loss": 1.7598,
"step": 490
},
{
"epoch": 0.8,
"learning_rate": 1.7209372673151186e-05,
"loss": 1.993,
"step": 492
},
{
"epoch": 0.8,
"learning_rate": 1.718498924609093e-05,
"loss": 1.9188,
"step": 494
},
{
"epoch": 0.81,
"learning_rate": 1.7160517192299474e-05,
"loss": 2.099,
"step": 496
},
{
"epoch": 0.81,
"learning_rate": 1.7135956813639222e-05,
"loss": 2.0652,
"step": 498
},
{
"epoch": 0.81,
"learning_rate": 1.7111308413062063e-05,
"loss": 2.0021,
"step": 500
},
{
"epoch": 0.82,
"learning_rate": 1.7086572294605642e-05,
"loss": 1.3524,
"step": 502
},
{
"epoch": 0.82,
"learning_rate": 1.7061748763389593e-05,
"loss": 1.3037,
"step": 504
},
{
"epoch": 0.82,
"learning_rate": 1.703683812561179e-05,
"loss": 1.6416,
"step": 506
},
{
"epoch": 0.83,
"learning_rate": 1.701184068854457e-05,
"loss": 1.3975,
"step": 508
},
{
"epoch": 0.83,
"learning_rate": 1.698675676053092e-05,
"loss": 1.3872,
"step": 510
},
{
"epoch": 0.83,
"learning_rate": 1.696158665098072e-05,
"loss": 1.5235,
"step": 512
},
{
"epoch": 0.84,
"learning_rate": 1.6936330670366867e-05,
"loss": 1.6902,
"step": 514
},
{
"epoch": 0.84,
"learning_rate": 1.69109891302215e-05,
"loss": 1.6784,
"step": 516
},
{
"epoch": 0.84,
"learning_rate": 1.6885562343132124e-05,
"loss": 1.7635,
"step": 518
},
{
"epoch": 0.85,
"learning_rate": 1.6860050622737764e-05,
"loss": 1.5534,
"step": 520
},
{
"epoch": 0.85,
"learning_rate": 1.6834454283725094e-05,
"loss": 1.6135,
"step": 522
},
{
"epoch": 0.85,
"learning_rate": 1.6808773641824562e-05,
"loss": 1.6691,
"step": 524
},
{
"epoch": 0.85,
"learning_rate": 1.678300901380649e-05,
"loss": 1.6357,
"step": 526
},
{
"epoch": 0.86,
"learning_rate": 1.6757160717477157e-05,
"loss": 1.6624,
"step": 528
},
{
"epoch": 0.86,
"learning_rate": 1.6731229071674914e-05,
"loss": 1.6901,
"step": 530
},
{
"epoch": 0.86,
"learning_rate": 1.6705214396266196e-05,
"loss": 1.8505,
"step": 532
},
{
"epoch": 0.87,
"learning_rate": 1.667911701214163e-05,
"loss": 1.9421,
"step": 534
},
{
"epoch": 0.87,
"learning_rate": 1.665293724121204e-05,
"loss": 1.9344,
"step": 536
},
{
"epoch": 0.87,
"learning_rate": 1.6626675406404503e-05,
"loss": 1.9095,
"step": 538
},
{
"epoch": 0.88,
"learning_rate": 1.660033183165834e-05,
"loss": 2.0502,
"step": 540
},
{
"epoch": 0.88,
"learning_rate": 1.6573906841921138e-05,
"loss": 2.2613,
"step": 542
},
{
"epoch": 0.88,
"learning_rate": 1.654740076314474e-05,
"loss": 2.0965,
"step": 544
},
{
"epoch": 0.89,
"learning_rate": 1.652081392228121e-05,
"loss": 2.1539,
"step": 546
},
{
"epoch": 0.89,
"learning_rate": 1.649414664727883e-05,
"loss": 2.1094,
"step": 548
},
{
"epoch": 0.89,
"learning_rate": 1.646739926707801e-05,
"loss": 2.0737,
"step": 550
},
{
"epoch": 0.9,
"learning_rate": 1.6440572111607287e-05,
"loss": 1.2207,
"step": 552
},
{
"epoch": 0.9,
"learning_rate": 1.6413665511779197e-05,
"loss": 1.45,
"step": 554
},
{
"epoch": 0.9,
"learning_rate": 1.6386679799486236e-05,
"loss": 1.4834,
"step": 556
},
{
"epoch": 0.91,
"learning_rate": 1.635961530759675e-05,
"loss": 1.3523,
"step": 558
},
{
"epoch": 0.91,
"learning_rate": 1.6332472369950828e-05,
"loss": 1.3546,
"step": 560
},
{
"epoch": 0.91,
"learning_rate": 1.6305251321356183e-05,
"loss": 1.5468,
"step": 562
},
{
"epoch": 0.92,
"learning_rate": 1.6277952497584027e-05,
"loss": 1.5853,
"step": 564
},
{
"epoch": 0.92,
"learning_rate": 1.6250576235364938e-05,
"loss": 1.5904,
"step": 566
},
{
"epoch": 0.92,
"learning_rate": 1.6223122872384675e-05,
"loss": 1.6946,
"step": 568
},
{
"epoch": 0.93,
"learning_rate": 1.619559274728005e-05,
"loss": 1.5193,
"step": 570
},
{
"epoch": 0.93,
"learning_rate": 1.6167986199634732e-05,
"loss": 1.6101,
"step": 572
},
{
"epoch": 0.93,
"learning_rate": 1.6140303569975064e-05,
"loss": 1.7246,
"step": 574
},
{
"epoch": 0.94,
"learning_rate": 1.6112545199765844e-05,
"loss": 1.7018,
"step": 576
},
{
"epoch": 0.94,
"learning_rate": 1.6084711431406144e-05,
"loss": 1.7813,
"step": 578
},
{
"epoch": 0.94,
"learning_rate": 1.605680260822507e-05,
"loss": 1.7158,
"step": 580
},
{
"epoch": 0.95,
"learning_rate": 1.6028819074477517e-05,
"loss": 1.6571,
"step": 582
},
{
"epoch": 0.95,
"learning_rate": 1.6000761175339944e-05,
"loss": 1.8461,
"step": 584
},
{
"epoch": 0.95,
"learning_rate": 1.5972629256906105e-05,
"loss": 1.7805,
"step": 586
},
{
"epoch": 0.96,
"learning_rate": 1.5944423666182776e-05,
"loss": 2.0146,
"step": 588
},
{
"epoch": 0.96,
"learning_rate": 1.5916144751085485e-05,
"loss": 1.9301,
"step": 590
},
{
"epoch": 0.96,
"learning_rate": 1.5887792860434207e-05,
"loss": 2.0717,
"step": 592
},
{
"epoch": 0.97,
"learning_rate": 1.5859368343949084e-05,
"loss": 2.1568,
"step": 594
},
{
"epoch": 0.97,
"learning_rate": 1.5830871552246076e-05,
"loss": 2.0925,
"step": 596
},
{
"epoch": 0.97,
"learning_rate": 1.5802302836832673e-05,
"loss": 2.119,
"step": 598
},
{
"epoch": 0.98,
"learning_rate": 1.577366255010354e-05,
"loss": 2.1738,
"step": 600
},
{
"epoch": 0.98,
"learning_rate": 1.5744951045336166e-05,
"loss": 1.5105,
"step": 602
},
{
"epoch": 0.98,
"learning_rate": 1.5716168676686523e-05,
"loss": 1.486,
"step": 604
},
{
"epoch": 0.98,
"learning_rate": 1.568731579918468e-05,
"loss": 1.6528,
"step": 606
},
{
"epoch": 0.99,
"learning_rate": 1.5658392768730434e-05,
"loss": 1.6643,
"step": 608
},
{
"epoch": 0.99,
"learning_rate": 1.562939994208892e-05,
"loss": 1.7925,
"step": 610
},
{
"epoch": 0.99,
"learning_rate": 1.5600337676886205e-05,
"loss": 1.8235,
"step": 612
},
{
"epoch": 1.0,
"learning_rate": 1.5571206331604885e-05,
"loss": 2.0644,
"step": 614
}
],
"logging_steps": 2,
"max_steps": 1845,
"num_train_epochs": 3,
"save_steps": 500,
"total_flos": 3.3933426003492864e+16,
"trial_name": null,
"trial_params": null
}