ast-model-bp-v1 / trainer_state.json
aryamtos's picture
Upload 8 files
76d9a17
{
"best_metric": 0.677589476108551,
"best_model_checkpoint": "ast-finetuned-audioset-10-10-0.4593-finetuning1-bp-v2/checkpoint-626",
"epoch": 5.0,
"eval_steps": 500,
"global_step": 1565,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.01,
"learning_rate": 2.9961661341853036e-05,
"loss": 0.6441,
"step": 2
},
{
"epoch": 0.01,
"learning_rate": 2.992332268370607e-05,
"loss": 0.6289,
"step": 4
},
{
"epoch": 0.02,
"learning_rate": 2.9884984025559106e-05,
"loss": 0.6572,
"step": 6
},
{
"epoch": 0.03,
"learning_rate": 2.984664536741214e-05,
"loss": 0.6638,
"step": 8
},
{
"epoch": 0.03,
"learning_rate": 2.9808306709265177e-05,
"loss": 0.6765,
"step": 10
},
{
"epoch": 0.04,
"learning_rate": 2.9769968051118212e-05,
"loss": 0.6938,
"step": 12
},
{
"epoch": 0.04,
"learning_rate": 2.9731629392971247e-05,
"loss": 0.6715,
"step": 14
},
{
"epoch": 0.05,
"learning_rate": 2.9693290734824282e-05,
"loss": 0.7168,
"step": 16
},
{
"epoch": 0.06,
"learning_rate": 2.9654952076677317e-05,
"loss": 0.5864,
"step": 18
},
{
"epoch": 0.06,
"learning_rate": 2.961661341853035e-05,
"loss": 0.6593,
"step": 20
},
{
"epoch": 0.07,
"learning_rate": 2.9578274760383384e-05,
"loss": 0.6444,
"step": 22
},
{
"epoch": 0.08,
"learning_rate": 2.9539936102236423e-05,
"loss": 0.7718,
"step": 24
},
{
"epoch": 0.08,
"learning_rate": 2.9501597444089458e-05,
"loss": 0.6247,
"step": 26
},
{
"epoch": 0.09,
"learning_rate": 2.9463258785942493e-05,
"loss": 0.7347,
"step": 28
},
{
"epoch": 0.1,
"learning_rate": 2.9424920127795528e-05,
"loss": 0.7123,
"step": 30
},
{
"epoch": 0.1,
"learning_rate": 2.9386581469648563e-05,
"loss": 0.6798,
"step": 32
},
{
"epoch": 0.11,
"learning_rate": 2.93482428115016e-05,
"loss": 0.6984,
"step": 34
},
{
"epoch": 0.12,
"learning_rate": 2.9309904153354634e-05,
"loss": 0.7256,
"step": 36
},
{
"epoch": 0.12,
"learning_rate": 2.927156549520767e-05,
"loss": 0.7119,
"step": 38
},
{
"epoch": 0.13,
"learning_rate": 2.9233226837060704e-05,
"loss": 0.666,
"step": 40
},
{
"epoch": 0.13,
"learning_rate": 2.919488817891374e-05,
"loss": 0.6492,
"step": 42
},
{
"epoch": 0.14,
"learning_rate": 2.9156549520766774e-05,
"loss": 0.701,
"step": 44
},
{
"epoch": 0.15,
"learning_rate": 2.911821086261981e-05,
"loss": 0.7348,
"step": 46
},
{
"epoch": 0.15,
"learning_rate": 2.9079872204472845e-05,
"loss": 0.6921,
"step": 48
},
{
"epoch": 0.16,
"learning_rate": 2.904153354632588e-05,
"loss": 0.7379,
"step": 50
},
{
"epoch": 0.17,
"learning_rate": 2.9003194888178915e-05,
"loss": 0.666,
"step": 52
},
{
"epoch": 0.17,
"learning_rate": 2.896485623003195e-05,
"loss": 0.5985,
"step": 54
},
{
"epoch": 0.18,
"learning_rate": 2.8926517571884985e-05,
"loss": 0.7178,
"step": 56
},
{
"epoch": 0.19,
"learning_rate": 2.888817891373802e-05,
"loss": 0.6295,
"step": 58
},
{
"epoch": 0.19,
"learning_rate": 2.8849840255591052e-05,
"loss": 0.7068,
"step": 60
},
{
"epoch": 0.2,
"learning_rate": 2.8811501597444087e-05,
"loss": 0.7146,
"step": 62
},
{
"epoch": 0.2,
"learning_rate": 2.8773162939297123e-05,
"loss": 0.6619,
"step": 64
},
{
"epoch": 0.21,
"learning_rate": 2.8734824281150158e-05,
"loss": 0.6854,
"step": 66
},
{
"epoch": 0.22,
"learning_rate": 2.8696485623003196e-05,
"loss": 0.6631,
"step": 68
},
{
"epoch": 0.22,
"learning_rate": 2.865814696485623e-05,
"loss": 0.668,
"step": 70
},
{
"epoch": 0.23,
"learning_rate": 2.8619808306709267e-05,
"loss": 0.7906,
"step": 72
},
{
"epoch": 0.24,
"learning_rate": 2.8581469648562302e-05,
"loss": 0.7034,
"step": 74
},
{
"epoch": 0.24,
"learning_rate": 2.8543130990415337e-05,
"loss": 0.7359,
"step": 76
},
{
"epoch": 0.25,
"learning_rate": 2.8504792332268372e-05,
"loss": 0.6615,
"step": 78
},
{
"epoch": 0.26,
"learning_rate": 2.8466453674121407e-05,
"loss": 0.6664,
"step": 80
},
{
"epoch": 0.26,
"learning_rate": 2.8428115015974443e-05,
"loss": 0.6841,
"step": 82
},
{
"epoch": 0.27,
"learning_rate": 2.8389776357827478e-05,
"loss": 0.7221,
"step": 84
},
{
"epoch": 0.27,
"learning_rate": 2.8351437699680513e-05,
"loss": 0.6912,
"step": 86
},
{
"epoch": 0.28,
"learning_rate": 2.8313099041533548e-05,
"loss": 0.7097,
"step": 88
},
{
"epoch": 0.29,
"learning_rate": 2.8274760383386583e-05,
"loss": 0.6062,
"step": 90
},
{
"epoch": 0.29,
"learning_rate": 2.823642172523962e-05,
"loss": 0.6829,
"step": 92
},
{
"epoch": 0.3,
"learning_rate": 2.8198083067092653e-05,
"loss": 0.6543,
"step": 94
},
{
"epoch": 0.31,
"learning_rate": 2.815974440894569e-05,
"loss": 0.6051,
"step": 96
},
{
"epoch": 0.31,
"learning_rate": 2.8121405750798724e-05,
"loss": 0.6734,
"step": 98
},
{
"epoch": 0.32,
"learning_rate": 2.8083067092651756e-05,
"loss": 0.6618,
"step": 100
},
{
"epoch": 0.33,
"learning_rate": 2.804472843450479e-05,
"loss": 0.6416,
"step": 102
},
{
"epoch": 0.33,
"learning_rate": 2.8006389776357826e-05,
"loss": 0.6395,
"step": 104
},
{
"epoch": 0.34,
"learning_rate": 2.796805111821086e-05,
"loss": 0.6068,
"step": 106
},
{
"epoch": 0.35,
"learning_rate": 2.7929712460063896e-05,
"loss": 0.687,
"step": 108
},
{
"epoch": 0.35,
"learning_rate": 2.789137380191693e-05,
"loss": 0.6594,
"step": 110
},
{
"epoch": 0.36,
"learning_rate": 2.7853035143769967e-05,
"loss": 0.6232,
"step": 112
},
{
"epoch": 0.36,
"learning_rate": 2.7814696485623005e-05,
"loss": 0.6892,
"step": 114
},
{
"epoch": 0.37,
"learning_rate": 2.777635782747604e-05,
"loss": 0.6637,
"step": 116
},
{
"epoch": 0.38,
"learning_rate": 2.7738019169329075e-05,
"loss": 0.7069,
"step": 118
},
{
"epoch": 0.38,
"learning_rate": 2.769968051118211e-05,
"loss": 0.7056,
"step": 120
},
{
"epoch": 0.39,
"learning_rate": 2.7661341853035146e-05,
"loss": 0.6551,
"step": 122
},
{
"epoch": 0.4,
"learning_rate": 2.762300319488818e-05,
"loss": 0.6612,
"step": 124
},
{
"epoch": 0.4,
"learning_rate": 2.7584664536741216e-05,
"loss": 0.6477,
"step": 126
},
{
"epoch": 0.41,
"learning_rate": 2.754632587859425e-05,
"loss": 0.6746,
"step": 128
},
{
"epoch": 0.42,
"learning_rate": 2.7507987220447286e-05,
"loss": 0.635,
"step": 130
},
{
"epoch": 0.42,
"learning_rate": 2.746964856230032e-05,
"loss": 0.6964,
"step": 132
},
{
"epoch": 0.43,
"learning_rate": 2.7431309904153357e-05,
"loss": 0.705,
"step": 134
},
{
"epoch": 0.43,
"learning_rate": 2.7392971246006392e-05,
"loss": 0.6138,
"step": 136
},
{
"epoch": 0.44,
"learning_rate": 2.7354632587859427e-05,
"loss": 0.6568,
"step": 138
},
{
"epoch": 0.45,
"learning_rate": 2.731629392971246e-05,
"loss": 0.6016,
"step": 140
},
{
"epoch": 0.45,
"learning_rate": 2.7277955271565494e-05,
"loss": 0.6527,
"step": 142
},
{
"epoch": 0.46,
"learning_rate": 2.723961661341853e-05,
"loss": 0.6552,
"step": 144
},
{
"epoch": 0.47,
"learning_rate": 2.7201277955271564e-05,
"loss": 0.693,
"step": 146
},
{
"epoch": 0.47,
"learning_rate": 2.71629392971246e-05,
"loss": 0.6139,
"step": 148
},
{
"epoch": 0.48,
"learning_rate": 2.7124600638977635e-05,
"loss": 0.6431,
"step": 150
},
{
"epoch": 0.49,
"learning_rate": 2.708626198083067e-05,
"loss": 0.6479,
"step": 152
},
{
"epoch": 0.49,
"learning_rate": 2.7047923322683705e-05,
"loss": 0.6459,
"step": 154
},
{
"epoch": 0.5,
"learning_rate": 2.700958466453674e-05,
"loss": 0.6273,
"step": 156
},
{
"epoch": 0.5,
"learning_rate": 2.6971246006389775e-05,
"loss": 0.6341,
"step": 158
},
{
"epoch": 0.51,
"learning_rate": 2.6932907348242814e-05,
"loss": 0.6776,
"step": 160
},
{
"epoch": 0.52,
"learning_rate": 2.689456869009585e-05,
"loss": 0.6508,
"step": 162
},
{
"epoch": 0.52,
"learning_rate": 2.6856230031948884e-05,
"loss": 0.6779,
"step": 164
},
{
"epoch": 0.53,
"learning_rate": 2.681789137380192e-05,
"loss": 0.5938,
"step": 166
},
{
"epoch": 0.54,
"learning_rate": 2.6779552715654955e-05,
"loss": 0.6443,
"step": 168
},
{
"epoch": 0.54,
"learning_rate": 2.674121405750799e-05,
"loss": 0.6245,
"step": 170
},
{
"epoch": 0.55,
"learning_rate": 2.6702875399361025e-05,
"loss": 0.6271,
"step": 172
},
{
"epoch": 0.56,
"learning_rate": 2.666453674121406e-05,
"loss": 0.6683,
"step": 174
},
{
"epoch": 0.56,
"learning_rate": 2.6626198083067095e-05,
"loss": 0.6095,
"step": 176
},
{
"epoch": 0.57,
"learning_rate": 2.658785942492013e-05,
"loss": 0.6363,
"step": 178
},
{
"epoch": 0.58,
"learning_rate": 2.6549520766773162e-05,
"loss": 0.6222,
"step": 180
},
{
"epoch": 0.58,
"learning_rate": 2.6511182108626197e-05,
"loss": 0.6411,
"step": 182
},
{
"epoch": 0.59,
"learning_rate": 2.6472843450479233e-05,
"loss": 0.6477,
"step": 184
},
{
"epoch": 0.59,
"learning_rate": 2.6434504792332268e-05,
"loss": 0.6633,
"step": 186
},
{
"epoch": 0.6,
"learning_rate": 2.6396166134185303e-05,
"loss": 0.6431,
"step": 188
},
{
"epoch": 0.61,
"learning_rate": 2.6357827476038338e-05,
"loss": 0.611,
"step": 190
},
{
"epoch": 0.61,
"learning_rate": 2.6319488817891373e-05,
"loss": 0.6429,
"step": 192
},
{
"epoch": 0.62,
"learning_rate": 2.628115015974441e-05,
"loss": 0.6201,
"step": 194
},
{
"epoch": 0.63,
"learning_rate": 2.6242811501597443e-05,
"loss": 0.6753,
"step": 196
},
{
"epoch": 0.63,
"learning_rate": 2.620447284345048e-05,
"loss": 0.6661,
"step": 198
},
{
"epoch": 0.64,
"learning_rate": 2.6166134185303514e-05,
"loss": 0.6058,
"step": 200
},
{
"epoch": 0.65,
"learning_rate": 2.612779552715655e-05,
"loss": 0.6615,
"step": 202
},
{
"epoch": 0.65,
"learning_rate": 2.6089456869009584e-05,
"loss": 0.6526,
"step": 204
},
{
"epoch": 0.66,
"learning_rate": 2.6051118210862623e-05,
"loss": 0.6457,
"step": 206
},
{
"epoch": 0.66,
"learning_rate": 2.6012779552715658e-05,
"loss": 0.697,
"step": 208
},
{
"epoch": 0.67,
"learning_rate": 2.5974440894568693e-05,
"loss": 0.6243,
"step": 210
},
{
"epoch": 0.68,
"learning_rate": 2.5936102236421728e-05,
"loss": 0.6342,
"step": 212
},
{
"epoch": 0.68,
"learning_rate": 2.5897763578274763e-05,
"loss": 0.6882,
"step": 214
},
{
"epoch": 0.69,
"learning_rate": 2.58594249201278e-05,
"loss": 0.608,
"step": 216
},
{
"epoch": 0.7,
"learning_rate": 2.582108626198083e-05,
"loss": 0.6117,
"step": 218
},
{
"epoch": 0.7,
"learning_rate": 2.5782747603833865e-05,
"loss": 0.6661,
"step": 220
},
{
"epoch": 0.71,
"learning_rate": 2.57444089456869e-05,
"loss": 0.6656,
"step": 222
},
{
"epoch": 0.72,
"learning_rate": 2.5706070287539936e-05,
"loss": 0.6372,
"step": 224
},
{
"epoch": 0.72,
"learning_rate": 2.566773162939297e-05,
"loss": 0.5845,
"step": 226
},
{
"epoch": 0.73,
"learning_rate": 2.5629392971246006e-05,
"loss": 0.6524,
"step": 228
},
{
"epoch": 0.73,
"learning_rate": 2.559105431309904e-05,
"loss": 0.6034,
"step": 230
},
{
"epoch": 0.74,
"learning_rate": 2.5552715654952076e-05,
"loss": 0.7123,
"step": 232
},
{
"epoch": 0.75,
"learning_rate": 2.551437699680511e-05,
"loss": 0.6529,
"step": 234
},
{
"epoch": 0.75,
"learning_rate": 2.5476038338658147e-05,
"loss": 0.6544,
"step": 236
},
{
"epoch": 0.76,
"learning_rate": 2.5437699680511182e-05,
"loss": 0.6274,
"step": 238
},
{
"epoch": 0.77,
"learning_rate": 2.5399361022364217e-05,
"loss": 0.7083,
"step": 240
},
{
"epoch": 0.77,
"learning_rate": 2.5361022364217252e-05,
"loss": 0.6452,
"step": 242
},
{
"epoch": 0.78,
"learning_rate": 2.5322683706070287e-05,
"loss": 0.5892,
"step": 244
},
{
"epoch": 0.79,
"learning_rate": 2.5284345047923323e-05,
"loss": 0.6619,
"step": 246
},
{
"epoch": 0.79,
"learning_rate": 2.5246006389776358e-05,
"loss": 0.5389,
"step": 248
},
{
"epoch": 0.8,
"learning_rate": 2.5207667731629396e-05,
"loss": 0.6233,
"step": 250
},
{
"epoch": 0.81,
"learning_rate": 2.516932907348243e-05,
"loss": 0.6089,
"step": 252
},
{
"epoch": 0.81,
"learning_rate": 2.5130990415335467e-05,
"loss": 0.6321,
"step": 254
},
{
"epoch": 0.82,
"learning_rate": 2.5092651757188502e-05,
"loss": 0.6448,
"step": 256
},
{
"epoch": 0.82,
"learning_rate": 2.5054313099041534e-05,
"loss": 0.6556,
"step": 258
},
{
"epoch": 0.83,
"learning_rate": 2.501597444089457e-05,
"loss": 0.6326,
"step": 260
},
{
"epoch": 0.84,
"learning_rate": 2.4977635782747604e-05,
"loss": 0.6171,
"step": 262
},
{
"epoch": 0.84,
"learning_rate": 2.493929712460064e-05,
"loss": 0.6909,
"step": 264
},
{
"epoch": 0.85,
"learning_rate": 2.4900958466453674e-05,
"loss": 0.6293,
"step": 266
},
{
"epoch": 0.86,
"learning_rate": 2.486261980830671e-05,
"loss": 0.7043,
"step": 268
},
{
"epoch": 0.86,
"learning_rate": 2.4824281150159745e-05,
"loss": 0.6922,
"step": 270
},
{
"epoch": 0.87,
"learning_rate": 2.478594249201278e-05,
"loss": 0.5919,
"step": 272
},
{
"epoch": 0.88,
"learning_rate": 2.4747603833865815e-05,
"loss": 0.5831,
"step": 274
},
{
"epoch": 0.88,
"learning_rate": 2.470926517571885e-05,
"loss": 0.6656,
"step": 276
},
{
"epoch": 0.89,
"learning_rate": 2.4670926517571885e-05,
"loss": 0.6388,
"step": 278
},
{
"epoch": 0.89,
"learning_rate": 2.463258785942492e-05,
"loss": 0.647,
"step": 280
},
{
"epoch": 0.9,
"learning_rate": 2.4594249201277956e-05,
"loss": 0.6672,
"step": 282
},
{
"epoch": 0.91,
"learning_rate": 2.455591054313099e-05,
"loss": 0.6203,
"step": 284
},
{
"epoch": 0.91,
"learning_rate": 2.4517571884984026e-05,
"loss": 0.6143,
"step": 286
},
{
"epoch": 0.92,
"learning_rate": 2.447923322683706e-05,
"loss": 0.6173,
"step": 288
},
{
"epoch": 0.93,
"learning_rate": 2.4440894568690096e-05,
"loss": 0.6131,
"step": 290
},
{
"epoch": 0.93,
"learning_rate": 2.440255591054313e-05,
"loss": 0.6613,
"step": 292
},
{
"epoch": 0.94,
"learning_rate": 2.4364217252396167e-05,
"loss": 0.6702,
"step": 294
},
{
"epoch": 0.95,
"learning_rate": 2.4325878594249205e-05,
"loss": 0.6413,
"step": 296
},
{
"epoch": 0.95,
"learning_rate": 2.4287539936102237e-05,
"loss": 0.5822,
"step": 298
},
{
"epoch": 0.96,
"learning_rate": 2.4249201277955272e-05,
"loss": 0.6207,
"step": 300
},
{
"epoch": 0.96,
"learning_rate": 2.4210862619808307e-05,
"loss": 0.5617,
"step": 302
},
{
"epoch": 0.97,
"learning_rate": 2.4172523961661342e-05,
"loss": 0.6764,
"step": 304
},
{
"epoch": 0.98,
"learning_rate": 2.4134185303514378e-05,
"loss": 0.5974,
"step": 306
},
{
"epoch": 0.98,
"learning_rate": 2.4095846645367413e-05,
"loss": 0.7435,
"step": 308
},
{
"epoch": 0.99,
"learning_rate": 2.4057507987220448e-05,
"loss": 0.6443,
"step": 310
},
{
"epoch": 1.0,
"learning_rate": 2.4019169329073483e-05,
"loss": 0.6656,
"step": 312
},
{
"epoch": 1.0,
"eval_accuracy": 0.5688009262084961,
"eval_loss": 0.7357929348945618,
"eval_runtime": 3203.0791,
"eval_samples_per_second": 1.341,
"eval_steps_per_second": 0.042,
"step": 313
},
{
"epoch": 1.0,
"learning_rate": 2.3980830670926518e-05,
"loss": 0.6123,
"step": 314
},
{
"epoch": 1.01,
"learning_rate": 2.3942492012779553e-05,
"loss": 0.6665,
"step": 316
},
{
"epoch": 1.02,
"learning_rate": 2.390415335463259e-05,
"loss": 0.6232,
"step": 318
},
{
"epoch": 1.02,
"learning_rate": 2.3865814696485624e-05,
"loss": 0.6205,
"step": 320
},
{
"epoch": 1.03,
"learning_rate": 2.382747603833866e-05,
"loss": 0.631,
"step": 322
},
{
"epoch": 1.04,
"learning_rate": 2.3789137380191694e-05,
"loss": 0.6061,
"step": 324
},
{
"epoch": 1.04,
"learning_rate": 2.375079872204473e-05,
"loss": 0.6014,
"step": 326
},
{
"epoch": 1.05,
"learning_rate": 2.3712460063897764e-05,
"loss": 0.6176,
"step": 328
},
{
"epoch": 1.05,
"learning_rate": 2.36741214057508e-05,
"loss": 0.6523,
"step": 330
},
{
"epoch": 1.06,
"learning_rate": 2.3635782747603835e-05,
"loss": 0.6511,
"step": 332
},
{
"epoch": 1.07,
"learning_rate": 2.359744408945687e-05,
"loss": 0.6543,
"step": 334
},
{
"epoch": 1.07,
"learning_rate": 2.3559105431309905e-05,
"loss": 0.6375,
"step": 336
},
{
"epoch": 1.08,
"learning_rate": 2.3520766773162937e-05,
"loss": 0.6704,
"step": 338
},
{
"epoch": 1.09,
"learning_rate": 2.3482428115015975e-05,
"loss": 0.5776,
"step": 340
},
{
"epoch": 1.09,
"learning_rate": 2.344408945686901e-05,
"loss": 0.6643,
"step": 342
},
{
"epoch": 1.1,
"learning_rate": 2.3405750798722046e-05,
"loss": 0.643,
"step": 344
},
{
"epoch": 1.11,
"learning_rate": 2.336741214057508e-05,
"loss": 0.6681,
"step": 346
},
{
"epoch": 1.11,
"learning_rate": 2.3329073482428116e-05,
"loss": 0.5931,
"step": 348
},
{
"epoch": 1.12,
"learning_rate": 2.329073482428115e-05,
"loss": 0.6165,
"step": 350
},
{
"epoch": 1.12,
"learning_rate": 2.3252396166134186e-05,
"loss": 0.6805,
"step": 352
},
{
"epoch": 1.13,
"learning_rate": 2.321405750798722e-05,
"loss": 0.6017,
"step": 354
},
{
"epoch": 1.14,
"learning_rate": 2.3175718849840257e-05,
"loss": 0.6375,
"step": 356
},
{
"epoch": 1.14,
"learning_rate": 2.3137380191693292e-05,
"loss": 0.6365,
"step": 358
},
{
"epoch": 1.15,
"learning_rate": 2.3099041533546327e-05,
"loss": 0.6069,
"step": 360
},
{
"epoch": 1.16,
"learning_rate": 2.3060702875399362e-05,
"loss": 0.6181,
"step": 362
},
{
"epoch": 1.16,
"learning_rate": 2.3022364217252397e-05,
"loss": 0.7057,
"step": 364
},
{
"epoch": 1.17,
"learning_rate": 2.2984025559105432e-05,
"loss": 0.6879,
"step": 366
},
{
"epoch": 1.18,
"learning_rate": 2.2945686900958468e-05,
"loss": 0.6772,
"step": 368
},
{
"epoch": 1.18,
"learning_rate": 2.2907348242811503e-05,
"loss": 0.6226,
"step": 370
},
{
"epoch": 1.19,
"learning_rate": 2.2869009584664538e-05,
"loss": 0.6852,
"step": 372
},
{
"epoch": 1.19,
"learning_rate": 2.2830670926517573e-05,
"loss": 0.6546,
"step": 374
},
{
"epoch": 1.2,
"learning_rate": 2.2792332268370608e-05,
"loss": 0.6118,
"step": 376
},
{
"epoch": 1.21,
"learning_rate": 2.275399361022364e-05,
"loss": 0.6018,
"step": 378
},
{
"epoch": 1.21,
"learning_rate": 2.2715654952076675e-05,
"loss": 0.6146,
"step": 380
},
{
"epoch": 1.22,
"learning_rate": 2.267731629392971e-05,
"loss": 0.6137,
"step": 382
},
{
"epoch": 1.23,
"learning_rate": 2.2638977635782746e-05,
"loss": 0.5415,
"step": 384
},
{
"epoch": 1.23,
"learning_rate": 2.2600638977635784e-05,
"loss": 0.6223,
"step": 386
},
{
"epoch": 1.24,
"learning_rate": 2.256230031948882e-05,
"loss": 0.6453,
"step": 388
},
{
"epoch": 1.25,
"learning_rate": 2.2523961661341854e-05,
"loss": 0.666,
"step": 390
},
{
"epoch": 1.25,
"learning_rate": 2.248562300319489e-05,
"loss": 0.6117,
"step": 392
},
{
"epoch": 1.26,
"learning_rate": 2.2447284345047925e-05,
"loss": 0.5793,
"step": 394
},
{
"epoch": 1.27,
"learning_rate": 2.240894568690096e-05,
"loss": 0.6421,
"step": 396
},
{
"epoch": 1.27,
"learning_rate": 2.2370607028753995e-05,
"loss": 0.6118,
"step": 398
},
{
"epoch": 1.28,
"learning_rate": 2.233226837060703e-05,
"loss": 0.7204,
"step": 400
},
{
"epoch": 1.28,
"learning_rate": 2.2293929712460065e-05,
"loss": 0.6333,
"step": 402
},
{
"epoch": 1.29,
"learning_rate": 2.22555910543131e-05,
"loss": 0.6228,
"step": 404
},
{
"epoch": 1.3,
"learning_rate": 2.2217252396166136e-05,
"loss": 0.6447,
"step": 406
},
{
"epoch": 1.3,
"learning_rate": 2.217891373801917e-05,
"loss": 0.5787,
"step": 408
},
{
"epoch": 1.31,
"learning_rate": 2.2140575079872206e-05,
"loss": 0.6639,
"step": 410
},
{
"epoch": 1.32,
"learning_rate": 2.210223642172524e-05,
"loss": 0.5804,
"step": 412
},
{
"epoch": 1.32,
"learning_rate": 2.2063897763578276e-05,
"loss": 0.5911,
"step": 414
},
{
"epoch": 1.33,
"learning_rate": 2.202555910543131e-05,
"loss": 0.703,
"step": 416
},
{
"epoch": 1.34,
"learning_rate": 2.1987220447284343e-05,
"loss": 0.679,
"step": 418
},
{
"epoch": 1.34,
"learning_rate": 2.194888178913738e-05,
"loss": 0.7204,
"step": 420
},
{
"epoch": 1.35,
"learning_rate": 2.1910543130990414e-05,
"loss": 0.6614,
"step": 422
},
{
"epoch": 1.35,
"learning_rate": 2.187220447284345e-05,
"loss": 0.6194,
"step": 424
},
{
"epoch": 1.36,
"learning_rate": 2.1833865814696484e-05,
"loss": 0.6539,
"step": 426
},
{
"epoch": 1.37,
"learning_rate": 2.179552715654952e-05,
"loss": 0.6258,
"step": 428
},
{
"epoch": 1.37,
"learning_rate": 2.1757188498402554e-05,
"loss": 0.5879,
"step": 430
},
{
"epoch": 1.38,
"learning_rate": 2.1718849840255593e-05,
"loss": 0.5875,
"step": 432
},
{
"epoch": 1.39,
"learning_rate": 2.1680511182108628e-05,
"loss": 0.6386,
"step": 434
},
{
"epoch": 1.39,
"learning_rate": 2.1642172523961663e-05,
"loss": 0.6548,
"step": 436
},
{
"epoch": 1.4,
"learning_rate": 2.16038338658147e-05,
"loss": 0.5866,
"step": 438
},
{
"epoch": 1.41,
"learning_rate": 2.1565495207667734e-05,
"loss": 0.6489,
"step": 440
},
{
"epoch": 1.41,
"learning_rate": 2.152715654952077e-05,
"loss": 0.6885,
"step": 442
},
{
"epoch": 1.42,
"learning_rate": 2.1488817891373804e-05,
"loss": 0.6796,
"step": 444
},
{
"epoch": 1.42,
"learning_rate": 2.145047923322684e-05,
"loss": 0.5876,
"step": 446
},
{
"epoch": 1.43,
"learning_rate": 2.1412140575079874e-05,
"loss": 0.6219,
"step": 448
},
{
"epoch": 1.44,
"learning_rate": 2.137380191693291e-05,
"loss": 0.5989,
"step": 450
},
{
"epoch": 1.44,
"learning_rate": 2.1335463258785945e-05,
"loss": 0.5825,
"step": 452
},
{
"epoch": 1.45,
"learning_rate": 2.129712460063898e-05,
"loss": 0.5712,
"step": 454
},
{
"epoch": 1.46,
"learning_rate": 2.125878594249201e-05,
"loss": 0.6612,
"step": 456
},
{
"epoch": 1.46,
"learning_rate": 2.1220447284345047e-05,
"loss": 0.5837,
"step": 458
},
{
"epoch": 1.47,
"learning_rate": 2.1182108626198082e-05,
"loss": 0.612,
"step": 460
},
{
"epoch": 1.48,
"learning_rate": 2.1143769968051117e-05,
"loss": 0.6559,
"step": 462
},
{
"epoch": 1.48,
"learning_rate": 2.1105431309904152e-05,
"loss": 0.6591,
"step": 464
},
{
"epoch": 1.49,
"learning_rate": 2.1067092651757187e-05,
"loss": 0.6288,
"step": 466
},
{
"epoch": 1.5,
"learning_rate": 2.1028753993610222e-05,
"loss": 0.6524,
"step": 468
},
{
"epoch": 1.5,
"learning_rate": 2.0990415335463258e-05,
"loss": 0.6079,
"step": 470
},
{
"epoch": 1.51,
"learning_rate": 2.0952076677316293e-05,
"loss": 0.6039,
"step": 472
},
{
"epoch": 1.51,
"learning_rate": 2.0913738019169328e-05,
"loss": 0.5888,
"step": 474
},
{
"epoch": 1.52,
"learning_rate": 2.0875399361022363e-05,
"loss": 0.6099,
"step": 476
},
{
"epoch": 1.53,
"learning_rate": 2.08370607028754e-05,
"loss": 0.5547,
"step": 478
},
{
"epoch": 1.53,
"learning_rate": 2.0798722044728437e-05,
"loss": 0.6258,
"step": 480
},
{
"epoch": 1.54,
"learning_rate": 2.0760383386581472e-05,
"loss": 0.5904,
"step": 482
},
{
"epoch": 1.55,
"learning_rate": 2.0722044728434507e-05,
"loss": 0.5921,
"step": 484
},
{
"epoch": 1.55,
"learning_rate": 2.0683706070287542e-05,
"loss": 0.581,
"step": 486
},
{
"epoch": 1.56,
"learning_rate": 2.0645367412140577e-05,
"loss": 0.6627,
"step": 488
},
{
"epoch": 1.57,
"learning_rate": 2.0607028753993613e-05,
"loss": 0.6303,
"step": 490
},
{
"epoch": 1.57,
"learning_rate": 2.0568690095846648e-05,
"loss": 0.6454,
"step": 492
},
{
"epoch": 1.58,
"learning_rate": 2.0530351437699683e-05,
"loss": 0.6391,
"step": 494
},
{
"epoch": 1.58,
"learning_rate": 2.0492012779552715e-05,
"loss": 0.5063,
"step": 496
},
{
"epoch": 1.59,
"learning_rate": 2.045367412140575e-05,
"loss": 0.5964,
"step": 498
},
{
"epoch": 1.6,
"learning_rate": 2.0415335463258785e-05,
"loss": 0.5932,
"step": 500
},
{
"epoch": 1.6,
"learning_rate": 2.037699680511182e-05,
"loss": 0.6138,
"step": 502
},
{
"epoch": 1.61,
"learning_rate": 2.0338658146964855e-05,
"loss": 0.5428,
"step": 504
},
{
"epoch": 1.62,
"learning_rate": 2.030031948881789e-05,
"loss": 0.6472,
"step": 506
},
{
"epoch": 1.62,
"learning_rate": 2.0261980830670926e-05,
"loss": 0.6685,
"step": 508
},
{
"epoch": 1.63,
"learning_rate": 2.022364217252396e-05,
"loss": 0.6025,
"step": 510
},
{
"epoch": 1.64,
"learning_rate": 2.0185303514376996e-05,
"loss": 0.6466,
"step": 512
},
{
"epoch": 1.64,
"learning_rate": 2.014696485623003e-05,
"loss": 0.5887,
"step": 514
},
{
"epoch": 1.65,
"learning_rate": 2.0108626198083066e-05,
"loss": 0.7098,
"step": 516
},
{
"epoch": 1.65,
"learning_rate": 2.00702875399361e-05,
"loss": 0.6376,
"step": 518
},
{
"epoch": 1.66,
"learning_rate": 2.0031948881789137e-05,
"loss": 0.5713,
"step": 520
},
{
"epoch": 1.67,
"learning_rate": 1.9993610223642175e-05,
"loss": 0.6579,
"step": 522
},
{
"epoch": 1.67,
"learning_rate": 1.995527156549521e-05,
"loss": 0.6616,
"step": 524
},
{
"epoch": 1.68,
"learning_rate": 1.9916932907348246e-05,
"loss": 0.652,
"step": 526
},
{
"epoch": 1.69,
"learning_rate": 1.987859424920128e-05,
"loss": 0.634,
"step": 528
},
{
"epoch": 1.69,
"learning_rate": 1.9840255591054316e-05,
"loss": 0.6714,
"step": 530
},
{
"epoch": 1.7,
"learning_rate": 1.980191693290735e-05,
"loss": 0.6627,
"step": 532
},
{
"epoch": 1.71,
"learning_rate": 1.9763578274760386e-05,
"loss": 0.6686,
"step": 534
},
{
"epoch": 1.71,
"learning_rate": 1.9725239616613418e-05,
"loss": 0.6024,
"step": 536
},
{
"epoch": 1.72,
"learning_rate": 1.9686900958466453e-05,
"loss": 0.5986,
"step": 538
},
{
"epoch": 1.73,
"learning_rate": 1.964856230031949e-05,
"loss": 0.4928,
"step": 540
},
{
"epoch": 1.73,
"learning_rate": 1.9610223642172524e-05,
"loss": 0.5281,
"step": 542
},
{
"epoch": 1.74,
"learning_rate": 1.957188498402556e-05,
"loss": 0.5763,
"step": 544
},
{
"epoch": 1.74,
"learning_rate": 1.9533546325878594e-05,
"loss": 0.6374,
"step": 546
},
{
"epoch": 1.75,
"learning_rate": 1.949520766773163e-05,
"loss": 0.6591,
"step": 548
},
{
"epoch": 1.76,
"learning_rate": 1.9456869009584664e-05,
"loss": 0.5999,
"step": 550
},
{
"epoch": 1.76,
"learning_rate": 1.94185303514377e-05,
"loss": 0.7151,
"step": 552
},
{
"epoch": 1.77,
"learning_rate": 1.9380191693290735e-05,
"loss": 0.5627,
"step": 554
},
{
"epoch": 1.78,
"learning_rate": 1.934185303514377e-05,
"loss": 0.6144,
"step": 556
},
{
"epoch": 1.78,
"learning_rate": 1.9303514376996805e-05,
"loss": 0.6194,
"step": 558
},
{
"epoch": 1.79,
"learning_rate": 1.926517571884984e-05,
"loss": 0.6374,
"step": 560
},
{
"epoch": 1.8,
"learning_rate": 1.9226837060702875e-05,
"loss": 0.6647,
"step": 562
},
{
"epoch": 1.8,
"learning_rate": 1.918849840255591e-05,
"loss": 0.6892,
"step": 564
},
{
"epoch": 1.81,
"learning_rate": 1.9150159744408946e-05,
"loss": 0.6928,
"step": 566
},
{
"epoch": 1.81,
"learning_rate": 1.9111821086261984e-05,
"loss": 0.698,
"step": 568
},
{
"epoch": 1.82,
"learning_rate": 1.907348242811502e-05,
"loss": 0.5687,
"step": 570
},
{
"epoch": 1.83,
"learning_rate": 1.9035143769968054e-05,
"loss": 0.6076,
"step": 572
},
{
"epoch": 1.83,
"learning_rate": 1.899680511182109e-05,
"loss": 0.584,
"step": 574
},
{
"epoch": 1.84,
"learning_rate": 1.895846645367412e-05,
"loss": 0.681,
"step": 576
},
{
"epoch": 1.85,
"learning_rate": 1.8920127795527157e-05,
"loss": 0.5812,
"step": 578
},
{
"epoch": 1.85,
"learning_rate": 1.888178913738019e-05,
"loss": 0.6194,
"step": 580
},
{
"epoch": 1.86,
"learning_rate": 1.8843450479233227e-05,
"loss": 0.5849,
"step": 582
},
{
"epoch": 1.87,
"learning_rate": 1.8805111821086262e-05,
"loss": 0.6218,
"step": 584
},
{
"epoch": 1.87,
"learning_rate": 1.8766773162939297e-05,
"loss": 0.6273,
"step": 586
},
{
"epoch": 1.88,
"learning_rate": 1.8728434504792332e-05,
"loss": 0.6592,
"step": 588
},
{
"epoch": 1.88,
"learning_rate": 1.8690095846645367e-05,
"loss": 0.6193,
"step": 590
},
{
"epoch": 1.89,
"learning_rate": 1.8651757188498403e-05,
"loss": 0.5703,
"step": 592
},
{
"epoch": 1.9,
"learning_rate": 1.8613418530351438e-05,
"loss": 0.501,
"step": 594
},
{
"epoch": 1.9,
"learning_rate": 1.8575079872204473e-05,
"loss": 0.6547,
"step": 596
},
{
"epoch": 1.91,
"learning_rate": 1.8536741214057508e-05,
"loss": 0.594,
"step": 598
},
{
"epoch": 1.92,
"learning_rate": 1.8498402555910543e-05,
"loss": 0.6213,
"step": 600
},
{
"epoch": 1.92,
"learning_rate": 1.846006389776358e-05,
"loss": 0.6633,
"step": 602
},
{
"epoch": 1.93,
"learning_rate": 1.8421725239616614e-05,
"loss": 0.6737,
"step": 604
},
{
"epoch": 1.94,
"learning_rate": 1.838338658146965e-05,
"loss": 0.6047,
"step": 606
},
{
"epoch": 1.94,
"learning_rate": 1.8345047923322684e-05,
"loss": 0.6795,
"step": 608
},
{
"epoch": 1.95,
"learning_rate": 1.830670926517572e-05,
"loss": 0.6357,
"step": 610
},
{
"epoch": 1.96,
"learning_rate": 1.8268370607028754e-05,
"loss": 0.6206,
"step": 612
},
{
"epoch": 1.96,
"learning_rate": 1.8230031948881793e-05,
"loss": 0.7065,
"step": 614
},
{
"epoch": 1.97,
"learning_rate": 1.8191693290734825e-05,
"loss": 0.6732,
"step": 616
},
{
"epoch": 1.97,
"learning_rate": 1.815335463258786e-05,
"loss": 0.5882,
"step": 618
},
{
"epoch": 1.98,
"learning_rate": 1.8115015974440895e-05,
"loss": 0.5762,
"step": 620
},
{
"epoch": 1.99,
"learning_rate": 1.807667731629393e-05,
"loss": 0.5851,
"step": 622
},
{
"epoch": 1.99,
"learning_rate": 1.8038338658146965e-05,
"loss": 0.6224,
"step": 624
},
{
"epoch": 2.0,
"learning_rate": 1.8e-05,
"loss": 0.6934,
"step": 626
},
{
"epoch": 2.0,
"eval_accuracy": 0.6025611162185669,
"eval_loss": 0.677589476108551,
"eval_runtime": 3149.7711,
"eval_samples_per_second": 1.364,
"eval_steps_per_second": 0.043,
"step": 626
},
{
"epoch": 2.01,
"learning_rate": 1.7961661341853036e-05,
"loss": 0.615,
"step": 628
},
{
"epoch": 2.01,
"learning_rate": 1.792332268370607e-05,
"loss": 0.6546,
"step": 630
},
{
"epoch": 2.02,
"learning_rate": 1.7884984025559106e-05,
"loss": 0.5759,
"step": 632
},
{
"epoch": 2.03,
"learning_rate": 1.784664536741214e-05,
"loss": 0.7322,
"step": 634
},
{
"epoch": 2.03,
"learning_rate": 1.7808306709265176e-05,
"loss": 0.629,
"step": 636
},
{
"epoch": 2.04,
"learning_rate": 1.776996805111821e-05,
"loss": 0.6263,
"step": 638
},
{
"epoch": 2.04,
"learning_rate": 1.7731629392971247e-05,
"loss": 0.6228,
"step": 640
},
{
"epoch": 2.05,
"learning_rate": 1.7693290734824282e-05,
"loss": 0.5817,
"step": 642
},
{
"epoch": 2.06,
"learning_rate": 1.7654952076677317e-05,
"loss": 0.6373,
"step": 644
},
{
"epoch": 2.06,
"learning_rate": 1.7616613418530352e-05,
"loss": 0.5643,
"step": 646
},
{
"epoch": 2.07,
"learning_rate": 1.7578274760383387e-05,
"loss": 0.6174,
"step": 648
},
{
"epoch": 2.08,
"learning_rate": 1.7539936102236422e-05,
"loss": 0.6153,
"step": 650
},
{
"epoch": 2.08,
"learning_rate": 1.7501597444089458e-05,
"loss": 0.6134,
"step": 652
},
{
"epoch": 2.09,
"learning_rate": 1.746325878594249e-05,
"loss": 0.5695,
"step": 654
},
{
"epoch": 2.1,
"learning_rate": 1.7424920127795525e-05,
"loss": 0.6241,
"step": 656
},
{
"epoch": 2.1,
"learning_rate": 1.7386581469648563e-05,
"loss": 0.569,
"step": 658
},
{
"epoch": 2.11,
"learning_rate": 1.7348242811501598e-05,
"loss": 0.6013,
"step": 660
},
{
"epoch": 2.12,
"learning_rate": 1.7309904153354633e-05,
"loss": 0.5607,
"step": 662
},
{
"epoch": 2.12,
"learning_rate": 1.727156549520767e-05,
"loss": 0.6161,
"step": 664
},
{
"epoch": 2.13,
"learning_rate": 1.7233226837060704e-05,
"loss": 0.5929,
"step": 666
},
{
"epoch": 2.13,
"learning_rate": 1.719488817891374e-05,
"loss": 0.6489,
"step": 668
},
{
"epoch": 2.14,
"learning_rate": 1.7156549520766774e-05,
"loss": 0.5791,
"step": 670
},
{
"epoch": 2.15,
"learning_rate": 1.711821086261981e-05,
"loss": 0.5774,
"step": 672
},
{
"epoch": 2.15,
"learning_rate": 1.7079872204472844e-05,
"loss": 0.6839,
"step": 674
},
{
"epoch": 2.16,
"learning_rate": 1.704153354632588e-05,
"loss": 0.5733,
"step": 676
},
{
"epoch": 2.17,
"learning_rate": 1.7003194888178915e-05,
"loss": 0.5827,
"step": 678
},
{
"epoch": 2.17,
"learning_rate": 1.696485623003195e-05,
"loss": 0.5698,
"step": 680
},
{
"epoch": 2.18,
"learning_rate": 1.6926517571884985e-05,
"loss": 0.5815,
"step": 682
},
{
"epoch": 2.19,
"learning_rate": 1.688817891373802e-05,
"loss": 0.6066,
"step": 684
},
{
"epoch": 2.19,
"learning_rate": 1.6849840255591055e-05,
"loss": 0.6197,
"step": 686
},
{
"epoch": 2.2,
"learning_rate": 1.681150159744409e-05,
"loss": 0.5718,
"step": 688
},
{
"epoch": 2.2,
"learning_rate": 1.6773162939297126e-05,
"loss": 0.5479,
"step": 690
},
{
"epoch": 2.21,
"learning_rate": 1.673482428115016e-05,
"loss": 0.6439,
"step": 692
},
{
"epoch": 2.22,
"learning_rate": 1.6696485623003193e-05,
"loss": 0.6525,
"step": 694
},
{
"epoch": 2.22,
"learning_rate": 1.6658146964856228e-05,
"loss": 0.5945,
"step": 696
},
{
"epoch": 2.23,
"learning_rate": 1.6619808306709263e-05,
"loss": 0.5785,
"step": 698
},
{
"epoch": 2.24,
"learning_rate": 1.6581469648562298e-05,
"loss": 0.6794,
"step": 700
},
{
"epoch": 2.24,
"learning_rate": 1.6543130990415333e-05,
"loss": 0.5943,
"step": 702
},
{
"epoch": 2.25,
"learning_rate": 1.6504792332268372e-05,
"loss": 0.5477,
"step": 704
},
{
"epoch": 2.26,
"learning_rate": 1.6466453674121407e-05,
"loss": 0.609,
"step": 706
},
{
"epoch": 2.26,
"learning_rate": 1.6428115015974442e-05,
"loss": 0.6088,
"step": 708
},
{
"epoch": 2.27,
"learning_rate": 1.6389776357827477e-05,
"loss": 0.5371,
"step": 710
},
{
"epoch": 2.27,
"learning_rate": 1.6351437699680513e-05,
"loss": 0.5081,
"step": 712
},
{
"epoch": 2.28,
"learning_rate": 1.6313099041533548e-05,
"loss": 0.6044,
"step": 714
},
{
"epoch": 2.29,
"learning_rate": 1.6274760383386583e-05,
"loss": 0.6805,
"step": 716
},
{
"epoch": 2.29,
"learning_rate": 1.6236421725239618e-05,
"loss": 0.5758,
"step": 718
},
{
"epoch": 2.3,
"learning_rate": 1.6198083067092653e-05,
"loss": 0.5951,
"step": 720
},
{
"epoch": 2.31,
"learning_rate": 1.615974440894569e-05,
"loss": 0.5904,
"step": 722
},
{
"epoch": 2.31,
"learning_rate": 1.6121405750798724e-05,
"loss": 0.6482,
"step": 724
},
{
"epoch": 2.32,
"learning_rate": 1.608306709265176e-05,
"loss": 0.6821,
"step": 726
},
{
"epoch": 2.33,
"learning_rate": 1.6044728434504794e-05,
"loss": 0.5993,
"step": 728
},
{
"epoch": 2.33,
"learning_rate": 1.600638977635783e-05,
"loss": 0.6405,
"step": 730
},
{
"epoch": 2.34,
"learning_rate": 1.5968051118210864e-05,
"loss": 0.5977,
"step": 732
},
{
"epoch": 2.35,
"learning_rate": 1.5929712460063896e-05,
"loss": 0.6535,
"step": 734
},
{
"epoch": 2.35,
"learning_rate": 1.589137380191693e-05,
"loss": 0.6182,
"step": 736
},
{
"epoch": 2.36,
"learning_rate": 1.5853035143769966e-05,
"loss": 0.5556,
"step": 738
},
{
"epoch": 2.36,
"learning_rate": 1.5814696485623e-05,
"loss": 0.6626,
"step": 740
},
{
"epoch": 2.37,
"learning_rate": 1.5776357827476037e-05,
"loss": 0.6106,
"step": 742
},
{
"epoch": 2.38,
"learning_rate": 1.5738019169329072e-05,
"loss": 0.5401,
"step": 744
},
{
"epoch": 2.38,
"learning_rate": 1.5699680511182107e-05,
"loss": 0.5346,
"step": 746
},
{
"epoch": 2.39,
"learning_rate": 1.5661341853035142e-05,
"loss": 0.6638,
"step": 748
},
{
"epoch": 2.4,
"learning_rate": 1.562300319488818e-05,
"loss": 0.5947,
"step": 750
},
{
"epoch": 2.4,
"learning_rate": 1.5584664536741216e-05,
"loss": 0.5658,
"step": 752
},
{
"epoch": 2.41,
"learning_rate": 1.554632587859425e-05,
"loss": 0.6878,
"step": 754
},
{
"epoch": 2.42,
"learning_rate": 1.5507987220447286e-05,
"loss": 0.6821,
"step": 756
},
{
"epoch": 2.42,
"learning_rate": 1.546964856230032e-05,
"loss": 0.7108,
"step": 758
},
{
"epoch": 2.43,
"learning_rate": 1.5431309904153356e-05,
"loss": 0.5898,
"step": 760
},
{
"epoch": 2.43,
"learning_rate": 1.539297124600639e-05,
"loss": 0.5722,
"step": 762
},
{
"epoch": 2.44,
"learning_rate": 1.5354632587859427e-05,
"loss": 0.5794,
"step": 764
},
{
"epoch": 2.45,
"learning_rate": 1.5316293929712462e-05,
"loss": 0.6522,
"step": 766
},
{
"epoch": 2.45,
"learning_rate": 1.5277955271565497e-05,
"loss": 0.6789,
"step": 768
},
{
"epoch": 2.46,
"learning_rate": 1.5239616613418532e-05,
"loss": 0.6487,
"step": 770
},
{
"epoch": 2.47,
"learning_rate": 1.5201277955271567e-05,
"loss": 0.6435,
"step": 772
},
{
"epoch": 2.47,
"learning_rate": 1.51629392971246e-05,
"loss": 0.5946,
"step": 774
},
{
"epoch": 2.48,
"learning_rate": 1.5124600638977634e-05,
"loss": 0.6257,
"step": 776
},
{
"epoch": 2.49,
"learning_rate": 1.508626198083067e-05,
"loss": 0.7132,
"step": 778
},
{
"epoch": 2.49,
"learning_rate": 1.5047923322683705e-05,
"loss": 0.5461,
"step": 780
},
{
"epoch": 2.5,
"learning_rate": 1.500958466453674e-05,
"loss": 0.5636,
"step": 782
},
{
"epoch": 2.5,
"learning_rate": 1.4971246006389777e-05,
"loss": 0.6666,
"step": 784
},
{
"epoch": 2.51,
"learning_rate": 1.4932907348242812e-05,
"loss": 0.6291,
"step": 786
},
{
"epoch": 2.52,
"learning_rate": 1.4894568690095847e-05,
"loss": 0.5995,
"step": 788
},
{
"epoch": 2.52,
"learning_rate": 1.4856230031948882e-05,
"loss": 0.5494,
"step": 790
},
{
"epoch": 2.53,
"learning_rate": 1.4817891373801917e-05,
"loss": 0.6506,
"step": 792
},
{
"epoch": 2.54,
"learning_rate": 1.4779552715654953e-05,
"loss": 0.583,
"step": 794
},
{
"epoch": 2.54,
"learning_rate": 1.4741214057507988e-05,
"loss": 0.6563,
"step": 796
},
{
"epoch": 2.55,
"learning_rate": 1.4702875399361023e-05,
"loss": 0.5912,
"step": 798
},
{
"epoch": 2.56,
"learning_rate": 1.4664536741214058e-05,
"loss": 0.6305,
"step": 800
},
{
"epoch": 2.56,
"learning_rate": 1.4626198083067093e-05,
"loss": 0.572,
"step": 802
},
{
"epoch": 2.57,
"learning_rate": 1.4587859424920127e-05,
"loss": 0.6084,
"step": 804
},
{
"epoch": 2.58,
"learning_rate": 1.4549520766773164e-05,
"loss": 0.5786,
"step": 806
},
{
"epoch": 2.58,
"learning_rate": 1.4511182108626199e-05,
"loss": 0.614,
"step": 808
},
{
"epoch": 2.59,
"learning_rate": 1.4472843450479234e-05,
"loss": 0.6951,
"step": 810
},
{
"epoch": 2.59,
"learning_rate": 1.4434504792332269e-05,
"loss": 0.5806,
"step": 812
},
{
"epoch": 2.6,
"learning_rate": 1.4396166134185304e-05,
"loss": 0.6374,
"step": 814
},
{
"epoch": 2.61,
"learning_rate": 1.435782747603834e-05,
"loss": 0.5693,
"step": 816
},
{
"epoch": 2.61,
"learning_rate": 1.4319488817891375e-05,
"loss": 0.7299,
"step": 818
},
{
"epoch": 2.62,
"learning_rate": 1.428115015974441e-05,
"loss": 0.5376,
"step": 820
},
{
"epoch": 2.63,
"learning_rate": 1.4242811501597445e-05,
"loss": 0.6866,
"step": 822
},
{
"epoch": 2.63,
"learning_rate": 1.4204472843450478e-05,
"loss": 0.6129,
"step": 824
},
{
"epoch": 2.64,
"learning_rate": 1.4166134185303514e-05,
"loss": 0.6229,
"step": 826
},
{
"epoch": 2.65,
"learning_rate": 1.412779552715655e-05,
"loss": 0.6042,
"step": 828
},
{
"epoch": 2.65,
"learning_rate": 1.4089456869009586e-05,
"loss": 0.6098,
"step": 830
},
{
"epoch": 2.66,
"learning_rate": 1.405111821086262e-05,
"loss": 0.576,
"step": 832
},
{
"epoch": 2.66,
"learning_rate": 1.4012779552715656e-05,
"loss": 0.6003,
"step": 834
},
{
"epoch": 2.67,
"learning_rate": 1.3974440894568691e-05,
"loss": 0.6046,
"step": 836
},
{
"epoch": 2.68,
"learning_rate": 1.3936102236421726e-05,
"loss": 0.6067,
"step": 838
},
{
"epoch": 2.68,
"learning_rate": 1.3897763578274761e-05,
"loss": 0.5585,
"step": 840
},
{
"epoch": 2.69,
"learning_rate": 1.3859424920127795e-05,
"loss": 0.6436,
"step": 842
},
{
"epoch": 2.7,
"learning_rate": 1.382108626198083e-05,
"loss": 0.591,
"step": 844
},
{
"epoch": 2.7,
"learning_rate": 1.3782747603833865e-05,
"loss": 0.5908,
"step": 846
},
{
"epoch": 2.71,
"learning_rate": 1.37444089456869e-05,
"loss": 0.5671,
"step": 848
},
{
"epoch": 2.72,
"learning_rate": 1.3706070287539935e-05,
"loss": 0.6422,
"step": 850
},
{
"epoch": 2.72,
"learning_rate": 1.3667731629392972e-05,
"loss": 0.6385,
"step": 852
},
{
"epoch": 2.73,
"learning_rate": 1.3629392971246008e-05,
"loss": 0.6338,
"step": 854
},
{
"epoch": 2.73,
"learning_rate": 1.3591054313099043e-05,
"loss": 0.6053,
"step": 856
},
{
"epoch": 2.74,
"learning_rate": 1.3552715654952078e-05,
"loss": 0.5647,
"step": 858
},
{
"epoch": 2.75,
"learning_rate": 1.3514376996805113e-05,
"loss": 0.5518,
"step": 860
},
{
"epoch": 2.75,
"learning_rate": 1.3476038338658146e-05,
"loss": 0.6357,
"step": 862
},
{
"epoch": 2.76,
"learning_rate": 1.3437699680511182e-05,
"loss": 0.6535,
"step": 864
},
{
"epoch": 2.77,
"learning_rate": 1.3399361022364217e-05,
"loss": 0.6778,
"step": 866
},
{
"epoch": 2.77,
"learning_rate": 1.3361022364217252e-05,
"loss": 0.5676,
"step": 868
},
{
"epoch": 2.78,
"learning_rate": 1.3322683706070287e-05,
"loss": 0.6081,
"step": 870
},
{
"epoch": 2.79,
"learning_rate": 1.3284345047923322e-05,
"loss": 0.6059,
"step": 872
},
{
"epoch": 2.79,
"learning_rate": 1.324600638977636e-05,
"loss": 0.6292,
"step": 874
},
{
"epoch": 2.8,
"learning_rate": 1.3207667731629394e-05,
"loss": 0.618,
"step": 876
},
{
"epoch": 2.81,
"learning_rate": 1.316932907348243e-05,
"loss": 0.5128,
"step": 878
},
{
"epoch": 2.81,
"learning_rate": 1.3130990415335465e-05,
"loss": 0.5484,
"step": 880
},
{
"epoch": 2.82,
"learning_rate": 1.3092651757188498e-05,
"loss": 0.5384,
"step": 882
},
{
"epoch": 2.82,
"learning_rate": 1.3054313099041533e-05,
"loss": 0.7096,
"step": 884
},
{
"epoch": 2.83,
"learning_rate": 1.3015974440894568e-05,
"loss": 0.6335,
"step": 886
},
{
"epoch": 2.84,
"learning_rate": 1.2977635782747604e-05,
"loss": 0.625,
"step": 888
},
{
"epoch": 2.84,
"learning_rate": 1.2939297124600639e-05,
"loss": 0.7057,
"step": 890
},
{
"epoch": 2.85,
"learning_rate": 1.2900958466453674e-05,
"loss": 0.6188,
"step": 892
},
{
"epoch": 2.86,
"learning_rate": 1.2862619808306709e-05,
"loss": 0.5762,
"step": 894
},
{
"epoch": 2.86,
"learning_rate": 1.2824281150159746e-05,
"loss": 0.5937,
"step": 896
},
{
"epoch": 2.87,
"learning_rate": 1.2785942492012781e-05,
"loss": 0.6604,
"step": 898
},
{
"epoch": 2.88,
"learning_rate": 1.2747603833865816e-05,
"loss": 0.6576,
"step": 900
},
{
"epoch": 2.88,
"learning_rate": 1.270926517571885e-05,
"loss": 0.6,
"step": 902
},
{
"epoch": 2.89,
"learning_rate": 1.2670926517571885e-05,
"loss": 0.5268,
"step": 904
},
{
"epoch": 2.89,
"learning_rate": 1.263258785942492e-05,
"loss": 0.6061,
"step": 906
},
{
"epoch": 2.9,
"learning_rate": 1.2594249201277955e-05,
"loss": 0.5935,
"step": 908
},
{
"epoch": 2.91,
"learning_rate": 1.255591054313099e-05,
"loss": 0.5937,
"step": 910
},
{
"epoch": 2.91,
"learning_rate": 1.2517571884984026e-05,
"loss": 0.5415,
"step": 912
},
{
"epoch": 2.92,
"learning_rate": 1.247923322683706e-05,
"loss": 0.5544,
"step": 914
},
{
"epoch": 2.93,
"learning_rate": 1.2440894568690096e-05,
"loss": 0.5166,
"step": 916
},
{
"epoch": 2.93,
"learning_rate": 1.2402555910543131e-05,
"loss": 0.5572,
"step": 918
},
{
"epoch": 2.94,
"learning_rate": 1.2364217252396168e-05,
"loss": 0.6462,
"step": 920
},
{
"epoch": 2.95,
"learning_rate": 1.2325878594249201e-05,
"loss": 0.5443,
"step": 922
},
{
"epoch": 2.95,
"learning_rate": 1.2287539936102237e-05,
"loss": 0.6136,
"step": 924
},
{
"epoch": 2.96,
"learning_rate": 1.2249201277955272e-05,
"loss": 0.6082,
"step": 926
},
{
"epoch": 2.96,
"learning_rate": 1.2210862619808307e-05,
"loss": 0.6294,
"step": 928
},
{
"epoch": 2.97,
"learning_rate": 1.2172523961661342e-05,
"loss": 0.6205,
"step": 930
},
{
"epoch": 2.98,
"learning_rate": 1.2134185303514377e-05,
"loss": 0.6345,
"step": 932
},
{
"epoch": 2.98,
"learning_rate": 1.2095846645367412e-05,
"loss": 0.6088,
"step": 934
},
{
"epoch": 2.99,
"learning_rate": 1.2057507987220448e-05,
"loss": 0.6511,
"step": 936
},
{
"epoch": 3.0,
"learning_rate": 1.2019169329073483e-05,
"loss": 0.7065,
"step": 938
},
{
"epoch": 3.0,
"eval_accuracy": 0.584400475025177,
"eval_loss": 0.7319782972335815,
"eval_runtime": 3278.4387,
"eval_samples_per_second": 1.31,
"eval_steps_per_second": 0.041,
"step": 939
},
{
"epoch": 3.0,
"learning_rate": 1.1980830670926518e-05,
"loss": 0.5738,
"step": 940
},
{
"epoch": 3.01,
"learning_rate": 1.1942492012779553e-05,
"loss": 0.6859,
"step": 942
},
{
"epoch": 3.02,
"learning_rate": 1.1904153354632588e-05,
"loss": 0.6642,
"step": 944
},
{
"epoch": 3.02,
"learning_rate": 1.1865814696485623e-05,
"loss": 0.5589,
"step": 946
},
{
"epoch": 3.03,
"learning_rate": 1.1827476038338659e-05,
"loss": 0.598,
"step": 948
},
{
"epoch": 3.04,
"learning_rate": 1.1789137380191694e-05,
"loss": 0.6001,
"step": 950
},
{
"epoch": 3.04,
"learning_rate": 1.1750798722044729e-05,
"loss": 0.6187,
"step": 952
},
{
"epoch": 3.05,
"learning_rate": 1.1712460063897764e-05,
"loss": 0.5764,
"step": 954
},
{
"epoch": 3.05,
"learning_rate": 1.16741214057508e-05,
"loss": 0.6732,
"step": 956
},
{
"epoch": 3.06,
"learning_rate": 1.1635782747603834e-05,
"loss": 0.6053,
"step": 958
},
{
"epoch": 3.07,
"learning_rate": 1.159744408945687e-05,
"loss": 0.6293,
"step": 960
},
{
"epoch": 3.07,
"learning_rate": 1.1559105431309903e-05,
"loss": 0.5773,
"step": 962
},
{
"epoch": 3.08,
"learning_rate": 1.152076677316294e-05,
"loss": 0.5236,
"step": 964
},
{
"epoch": 3.09,
"learning_rate": 1.1482428115015975e-05,
"loss": 0.59,
"step": 966
},
{
"epoch": 3.09,
"learning_rate": 1.144408945686901e-05,
"loss": 0.5683,
"step": 968
},
{
"epoch": 3.1,
"learning_rate": 1.1405750798722045e-05,
"loss": 0.6164,
"step": 970
},
{
"epoch": 3.11,
"learning_rate": 1.136741214057508e-05,
"loss": 0.6331,
"step": 972
},
{
"epoch": 3.11,
"learning_rate": 1.1329073482428116e-05,
"loss": 0.6055,
"step": 974
},
{
"epoch": 3.12,
"learning_rate": 1.129073482428115e-05,
"loss": 0.6308,
"step": 976
},
{
"epoch": 3.12,
"learning_rate": 1.1252396166134186e-05,
"loss": 0.4942,
"step": 978
},
{
"epoch": 3.13,
"learning_rate": 1.1214057507987221e-05,
"loss": 0.5791,
"step": 980
},
{
"epoch": 3.14,
"learning_rate": 1.1175718849840255e-05,
"loss": 0.6238,
"step": 982
},
{
"epoch": 3.14,
"learning_rate": 1.113738019169329e-05,
"loss": 0.6092,
"step": 984
},
{
"epoch": 3.15,
"learning_rate": 1.1099041533546325e-05,
"loss": 0.5716,
"step": 986
},
{
"epoch": 3.16,
"learning_rate": 1.1060702875399362e-05,
"loss": 0.677,
"step": 988
},
{
"epoch": 3.16,
"learning_rate": 1.1022364217252397e-05,
"loss": 0.5756,
"step": 990
},
{
"epoch": 3.17,
"learning_rate": 1.0984025559105432e-05,
"loss": 0.6124,
"step": 992
},
{
"epoch": 3.18,
"learning_rate": 1.0945686900958467e-05,
"loss": 0.6069,
"step": 994
},
{
"epoch": 3.18,
"learning_rate": 1.0907348242811502e-05,
"loss": 0.6916,
"step": 996
},
{
"epoch": 3.19,
"learning_rate": 1.0869009584664538e-05,
"loss": 0.6452,
"step": 998
},
{
"epoch": 3.19,
"learning_rate": 1.0830670926517573e-05,
"loss": 0.7066,
"step": 1000
},
{
"epoch": 3.2,
"learning_rate": 1.0792332268370606e-05,
"loss": 0.6098,
"step": 1002
},
{
"epoch": 3.21,
"learning_rate": 1.0753993610223641e-05,
"loss": 0.6323,
"step": 1004
},
{
"epoch": 3.21,
"learning_rate": 1.0715654952076677e-05,
"loss": 0.6131,
"step": 1006
},
{
"epoch": 3.22,
"learning_rate": 1.0677316293929712e-05,
"loss": 0.6357,
"step": 1008
},
{
"epoch": 3.23,
"learning_rate": 1.0638977635782749e-05,
"loss": 0.5846,
"step": 1010
},
{
"epoch": 3.23,
"learning_rate": 1.0600638977635784e-05,
"loss": 0.5387,
"step": 1012
},
{
"epoch": 3.24,
"learning_rate": 1.0562300319488819e-05,
"loss": 0.5785,
"step": 1014
},
{
"epoch": 3.25,
"learning_rate": 1.0523961661341854e-05,
"loss": 0.6075,
"step": 1016
},
{
"epoch": 3.25,
"learning_rate": 1.048562300319489e-05,
"loss": 0.6335,
"step": 1018
},
{
"epoch": 3.26,
"learning_rate": 1.0447284345047924e-05,
"loss": 0.6515,
"step": 1020
},
{
"epoch": 3.27,
"learning_rate": 1.0408945686900958e-05,
"loss": 0.5713,
"step": 1022
},
{
"epoch": 3.27,
"learning_rate": 1.0370607028753993e-05,
"loss": 0.556,
"step": 1024
},
{
"epoch": 3.28,
"learning_rate": 1.0332268370607028e-05,
"loss": 0.6185,
"step": 1026
},
{
"epoch": 3.28,
"learning_rate": 1.0293929712460063e-05,
"loss": 0.4983,
"step": 1028
},
{
"epoch": 3.29,
"learning_rate": 1.0255591054313099e-05,
"loss": 0.5656,
"step": 1030
},
{
"epoch": 3.3,
"learning_rate": 1.0217252396166134e-05,
"loss": 0.4931,
"step": 1032
},
{
"epoch": 3.3,
"learning_rate": 1.017891373801917e-05,
"loss": 0.6462,
"step": 1034
},
{
"epoch": 3.31,
"learning_rate": 1.0140575079872206e-05,
"loss": 0.6749,
"step": 1036
},
{
"epoch": 3.32,
"learning_rate": 1.0102236421725241e-05,
"loss": 0.5857,
"step": 1038
},
{
"epoch": 3.32,
"learning_rate": 1.0063897763578276e-05,
"loss": 0.5665,
"step": 1040
},
{
"epoch": 3.33,
"learning_rate": 1.002555910543131e-05,
"loss": 0.7366,
"step": 1042
},
{
"epoch": 3.34,
"learning_rate": 9.987220447284345e-06,
"loss": 0.6487,
"step": 1044
},
{
"epoch": 3.34,
"learning_rate": 9.94888178913738e-06,
"loss": 0.5507,
"step": 1046
},
{
"epoch": 3.35,
"learning_rate": 9.910543130990415e-06,
"loss": 0.5857,
"step": 1048
},
{
"epoch": 3.35,
"learning_rate": 9.87220447284345e-06,
"loss": 0.5882,
"step": 1050
},
{
"epoch": 3.36,
"learning_rate": 9.833865814696485e-06,
"loss": 0.6147,
"step": 1052
},
{
"epoch": 3.37,
"learning_rate": 9.79552715654952e-06,
"loss": 0.6745,
"step": 1054
},
{
"epoch": 3.37,
"learning_rate": 9.757188498402557e-06,
"loss": 0.5957,
"step": 1056
},
{
"epoch": 3.38,
"learning_rate": 9.718849840255593e-06,
"loss": 0.644,
"step": 1058
},
{
"epoch": 3.39,
"learning_rate": 9.680511182108626e-06,
"loss": 0.6858,
"step": 1060
},
{
"epoch": 3.39,
"learning_rate": 9.642172523961661e-06,
"loss": 0.5156,
"step": 1062
},
{
"epoch": 3.4,
"learning_rate": 9.603833865814696e-06,
"loss": 0.5538,
"step": 1064
},
{
"epoch": 3.41,
"learning_rate": 9.565495207667732e-06,
"loss": 0.6102,
"step": 1066
},
{
"epoch": 3.41,
"learning_rate": 9.527156549520767e-06,
"loss": 0.5974,
"step": 1068
},
{
"epoch": 3.42,
"learning_rate": 9.488817891373802e-06,
"loss": 0.5425,
"step": 1070
},
{
"epoch": 3.42,
"learning_rate": 9.450479233226837e-06,
"loss": 0.5704,
"step": 1072
},
{
"epoch": 3.43,
"learning_rate": 9.412140575079872e-06,
"loss": 0.68,
"step": 1074
},
{
"epoch": 3.44,
"learning_rate": 9.373801916932907e-06,
"loss": 0.6226,
"step": 1076
},
{
"epoch": 3.44,
"learning_rate": 9.335463258785944e-06,
"loss": 0.6597,
"step": 1078
},
{
"epoch": 3.45,
"learning_rate": 9.297124600638978e-06,
"loss": 0.6329,
"step": 1080
},
{
"epoch": 3.46,
"learning_rate": 9.258785942492013e-06,
"loss": 0.5686,
"step": 1082
},
{
"epoch": 3.46,
"learning_rate": 9.220447284345048e-06,
"loss": 0.5101,
"step": 1084
},
{
"epoch": 3.47,
"learning_rate": 9.182108626198083e-06,
"loss": 0.595,
"step": 1086
},
{
"epoch": 3.48,
"learning_rate": 9.143769968051118e-06,
"loss": 0.6005,
"step": 1088
},
{
"epoch": 3.48,
"learning_rate": 9.105431309904154e-06,
"loss": 0.5928,
"step": 1090
},
{
"epoch": 3.49,
"learning_rate": 9.067092651757189e-06,
"loss": 0.6318,
"step": 1092
},
{
"epoch": 3.5,
"learning_rate": 9.028753993610224e-06,
"loss": 0.6383,
"step": 1094
},
{
"epoch": 3.5,
"learning_rate": 8.990415335463259e-06,
"loss": 0.5876,
"step": 1096
},
{
"epoch": 3.51,
"learning_rate": 8.952076677316294e-06,
"loss": 0.6298,
"step": 1098
},
{
"epoch": 3.51,
"learning_rate": 8.91373801916933e-06,
"loss": 0.5772,
"step": 1100
},
{
"epoch": 3.52,
"learning_rate": 8.875399361022365e-06,
"loss": 0.7086,
"step": 1102
},
{
"epoch": 3.53,
"learning_rate": 8.8370607028754e-06,
"loss": 0.5835,
"step": 1104
},
{
"epoch": 3.53,
"learning_rate": 8.798722044728435e-06,
"loss": 0.596,
"step": 1106
},
{
"epoch": 3.54,
"learning_rate": 8.76038338658147e-06,
"loss": 0.6359,
"step": 1108
},
{
"epoch": 3.55,
"learning_rate": 8.722044728434505e-06,
"loss": 0.5388,
"step": 1110
},
{
"epoch": 3.55,
"learning_rate": 8.68370607028754e-06,
"loss": 0.6212,
"step": 1112
},
{
"epoch": 3.56,
"learning_rate": 8.645367412140575e-06,
"loss": 0.6414,
"step": 1114
},
{
"epoch": 3.57,
"learning_rate": 8.60702875399361e-06,
"loss": 0.6626,
"step": 1116
},
{
"epoch": 3.57,
"learning_rate": 8.568690095846646e-06,
"loss": 0.6268,
"step": 1118
},
{
"epoch": 3.58,
"learning_rate": 8.53035143769968e-06,
"loss": 0.6053,
"step": 1120
},
{
"epoch": 3.58,
"learning_rate": 8.492012779552714e-06,
"loss": 0.592,
"step": 1122
},
{
"epoch": 3.59,
"learning_rate": 8.453674121405751e-06,
"loss": 0.5316,
"step": 1124
},
{
"epoch": 3.6,
"learning_rate": 8.415335463258786e-06,
"loss": 0.6674,
"step": 1126
},
{
"epoch": 3.6,
"learning_rate": 8.376996805111822e-06,
"loss": 0.6909,
"step": 1128
},
{
"epoch": 3.61,
"learning_rate": 8.338658146964857e-06,
"loss": 0.6631,
"step": 1130
},
{
"epoch": 3.62,
"learning_rate": 8.300319488817892e-06,
"loss": 0.5916,
"step": 1132
},
{
"epoch": 3.62,
"learning_rate": 8.261980830670927e-06,
"loss": 0.6679,
"step": 1134
},
{
"epoch": 3.63,
"learning_rate": 8.223642172523962e-06,
"loss": 0.6809,
"step": 1136
},
{
"epoch": 3.64,
"learning_rate": 8.185303514376997e-06,
"loss": 0.592,
"step": 1138
},
{
"epoch": 3.64,
"learning_rate": 8.146964856230031e-06,
"loss": 0.6234,
"step": 1140
},
{
"epoch": 3.65,
"learning_rate": 8.108626198083066e-06,
"loss": 0.6471,
"step": 1142
},
{
"epoch": 3.65,
"learning_rate": 8.070287539936101e-06,
"loss": 0.5573,
"step": 1144
},
{
"epoch": 3.66,
"learning_rate": 8.031948881789138e-06,
"loss": 0.5794,
"step": 1146
},
{
"epoch": 3.67,
"learning_rate": 7.993610223642173e-06,
"loss": 0.5485,
"step": 1148
},
{
"epoch": 3.67,
"learning_rate": 7.955271565495208e-06,
"loss": 0.5733,
"step": 1150
},
{
"epoch": 3.68,
"learning_rate": 7.916932907348244e-06,
"loss": 0.6405,
"step": 1152
},
{
"epoch": 3.69,
"learning_rate": 7.878594249201279e-06,
"loss": 0.5716,
"step": 1154
},
{
"epoch": 3.69,
"learning_rate": 7.840255591054314e-06,
"loss": 0.5821,
"step": 1156
},
{
"epoch": 3.7,
"learning_rate": 7.801916932907349e-06,
"loss": 0.5737,
"step": 1158
},
{
"epoch": 3.71,
"learning_rate": 7.763578274760383e-06,
"loss": 0.652,
"step": 1160
},
{
"epoch": 3.71,
"learning_rate": 7.725239616613418e-06,
"loss": 0.5798,
"step": 1162
},
{
"epoch": 3.72,
"learning_rate": 7.686900958466453e-06,
"loss": 0.7334,
"step": 1164
},
{
"epoch": 3.73,
"learning_rate": 7.648562300319488e-06,
"loss": 0.6044,
"step": 1166
},
{
"epoch": 3.73,
"learning_rate": 7.610223642172524e-06,
"loss": 0.6463,
"step": 1168
},
{
"epoch": 3.74,
"learning_rate": 7.571884984025559e-06,
"loss": 0.5535,
"step": 1170
},
{
"epoch": 3.74,
"learning_rate": 7.533546325878594e-06,
"loss": 0.6259,
"step": 1172
},
{
"epoch": 3.75,
"learning_rate": 7.49520766773163e-06,
"loss": 0.5918,
"step": 1174
},
{
"epoch": 3.76,
"learning_rate": 7.456869009584665e-06,
"loss": 0.5644,
"step": 1176
},
{
"epoch": 3.76,
"learning_rate": 7.4185303514377e-06,
"loss": 0.583,
"step": 1178
},
{
"epoch": 3.77,
"learning_rate": 7.380191693290735e-06,
"loss": 0.6453,
"step": 1180
},
{
"epoch": 3.78,
"learning_rate": 7.34185303514377e-06,
"loss": 0.6408,
"step": 1182
},
{
"epoch": 3.78,
"learning_rate": 7.3035143769968046e-06,
"loss": 0.5768,
"step": 1184
},
{
"epoch": 3.79,
"learning_rate": 7.2651757188498406e-06,
"loss": 0.5839,
"step": 1186
},
{
"epoch": 3.8,
"learning_rate": 7.226837060702876e-06,
"loss": 0.5691,
"step": 1188
},
{
"epoch": 3.8,
"learning_rate": 7.188498402555911e-06,
"loss": 0.5965,
"step": 1190
},
{
"epoch": 3.81,
"learning_rate": 7.150159744408946e-06,
"loss": 0.5495,
"step": 1192
},
{
"epoch": 3.81,
"learning_rate": 7.11182108626198e-06,
"loss": 0.5967,
"step": 1194
},
{
"epoch": 3.82,
"learning_rate": 7.0734824281150155e-06,
"loss": 0.6737,
"step": 1196
},
{
"epoch": 3.83,
"learning_rate": 7.0351437699680516e-06,
"loss": 0.5666,
"step": 1198
},
{
"epoch": 3.83,
"learning_rate": 6.996805111821087e-06,
"loss": 0.6234,
"step": 1200
},
{
"epoch": 3.84,
"learning_rate": 6.958466453674122e-06,
"loss": 0.5168,
"step": 1202
},
{
"epoch": 3.85,
"learning_rate": 6.920127795527156e-06,
"loss": 0.578,
"step": 1204
},
{
"epoch": 3.85,
"learning_rate": 6.881789137380191e-06,
"loss": 0.7034,
"step": 1206
},
{
"epoch": 3.86,
"learning_rate": 6.843450479233227e-06,
"loss": 0.6059,
"step": 1208
},
{
"epoch": 3.87,
"learning_rate": 6.8051118210862625e-06,
"loss": 0.5167,
"step": 1210
},
{
"epoch": 3.87,
"learning_rate": 6.766773162939298e-06,
"loss": 0.5822,
"step": 1212
},
{
"epoch": 3.88,
"learning_rate": 6.728434504792332e-06,
"loss": 0.632,
"step": 1214
},
{
"epoch": 3.88,
"learning_rate": 6.690095846645367e-06,
"loss": 0.5465,
"step": 1216
},
{
"epoch": 3.89,
"learning_rate": 6.651757188498402e-06,
"loss": 0.5827,
"step": 1218
},
{
"epoch": 3.9,
"learning_rate": 6.613418530351438e-06,
"loss": 0.612,
"step": 1220
},
{
"epoch": 3.9,
"learning_rate": 6.5750798722044735e-06,
"loss": 0.6313,
"step": 1222
},
{
"epoch": 3.91,
"learning_rate": 6.536741214057508e-06,
"loss": 0.607,
"step": 1224
},
{
"epoch": 3.92,
"learning_rate": 6.498402555910543e-06,
"loss": 0.5467,
"step": 1226
},
{
"epoch": 3.92,
"learning_rate": 6.460063897763578e-06,
"loss": 0.6058,
"step": 1228
},
{
"epoch": 3.93,
"learning_rate": 6.421725239616613e-06,
"loss": 0.586,
"step": 1230
},
{
"epoch": 3.94,
"learning_rate": 6.383386581469649e-06,
"loss": 0.631,
"step": 1232
},
{
"epoch": 3.94,
"learning_rate": 6.345047923322684e-06,
"loss": 0.5772,
"step": 1234
},
{
"epoch": 3.95,
"learning_rate": 6.306709265175719e-06,
"loss": 0.5529,
"step": 1236
},
{
"epoch": 3.96,
"learning_rate": 6.268370607028754e-06,
"loss": 0.6076,
"step": 1238
},
{
"epoch": 3.96,
"learning_rate": 6.230031948881789e-06,
"loss": 0.5828,
"step": 1240
},
{
"epoch": 3.97,
"learning_rate": 6.191693290734825e-06,
"loss": 0.5867,
"step": 1242
},
{
"epoch": 3.97,
"learning_rate": 6.1533546325878595e-06,
"loss": 0.6618,
"step": 1244
},
{
"epoch": 3.98,
"learning_rate": 6.115015974440895e-06,
"loss": 0.6218,
"step": 1246
},
{
"epoch": 3.99,
"learning_rate": 6.07667731629393e-06,
"loss": 0.6347,
"step": 1248
},
{
"epoch": 3.99,
"learning_rate": 6.038338658146965e-06,
"loss": 0.6346,
"step": 1250
},
{
"epoch": 4.0,
"learning_rate": 6e-06,
"loss": 0.6353,
"step": 1252
},
{
"epoch": 4.0,
"eval_accuracy": 0.5885913968086243,
"eval_loss": 0.723468542098999,
"eval_runtime": 3297.4284,
"eval_samples_per_second": 1.303,
"eval_steps_per_second": 0.041,
"step": 1252
},
{
"epoch": 4.01,
"learning_rate": 5.961661341853035e-06,
"loss": 0.6546,
"step": 1254
},
{
"epoch": 4.01,
"learning_rate": 5.9233226837060705e-06,
"loss": 0.5473,
"step": 1256
},
{
"epoch": 4.02,
"learning_rate": 5.884984025559106e-06,
"loss": 0.6159,
"step": 1258
},
{
"epoch": 4.03,
"learning_rate": 5.846645367412141e-06,
"loss": 0.5975,
"step": 1260
},
{
"epoch": 4.03,
"learning_rate": 5.808306709265176e-06,
"loss": 0.5331,
"step": 1262
},
{
"epoch": 4.04,
"learning_rate": 5.76996805111821e-06,
"loss": 0.5184,
"step": 1264
},
{
"epoch": 4.04,
"learning_rate": 5.731629392971246e-06,
"loss": 0.5705,
"step": 1266
},
{
"epoch": 4.05,
"learning_rate": 5.6932907348242815e-06,
"loss": 0.6562,
"step": 1268
},
{
"epoch": 4.06,
"learning_rate": 5.654952076677317e-06,
"loss": 0.5881,
"step": 1270
},
{
"epoch": 4.06,
"learning_rate": 5.616613418530352e-06,
"loss": 0.6068,
"step": 1272
},
{
"epoch": 4.07,
"learning_rate": 5.578274760383386e-06,
"loss": 0.5763,
"step": 1274
},
{
"epoch": 4.08,
"learning_rate": 5.539936102236422e-06,
"loss": 0.6508,
"step": 1276
},
{
"epoch": 4.08,
"learning_rate": 5.501597444089457e-06,
"loss": 0.6145,
"step": 1278
},
{
"epoch": 4.09,
"learning_rate": 5.4632587859424925e-06,
"loss": 0.632,
"step": 1280
},
{
"epoch": 4.1,
"learning_rate": 5.424920127795528e-06,
"loss": 0.6083,
"step": 1282
},
{
"epoch": 4.1,
"learning_rate": 5.386581469648562e-06,
"loss": 0.4836,
"step": 1284
},
{
"epoch": 4.11,
"learning_rate": 5.348242811501597e-06,
"loss": 0.5213,
"step": 1286
},
{
"epoch": 4.12,
"learning_rate": 5.309904153354633e-06,
"loss": 0.6166,
"step": 1288
},
{
"epoch": 4.12,
"learning_rate": 5.271565495207668e-06,
"loss": 0.6271,
"step": 1290
},
{
"epoch": 4.13,
"learning_rate": 5.2332268370607034e-06,
"loss": 0.5967,
"step": 1292
},
{
"epoch": 4.13,
"learning_rate": 5.194888178913738e-06,
"loss": 0.6001,
"step": 1294
},
{
"epoch": 4.14,
"learning_rate": 5.156549520766773e-06,
"loss": 0.5936,
"step": 1296
},
{
"epoch": 4.15,
"learning_rate": 5.118210862619808e-06,
"loss": 0.6392,
"step": 1298
},
{
"epoch": 4.15,
"learning_rate": 5.079872204472844e-06,
"loss": 0.6299,
"step": 1300
},
{
"epoch": 4.16,
"learning_rate": 5.041533546325879e-06,
"loss": 0.5395,
"step": 1302
},
{
"epoch": 4.17,
"learning_rate": 5.003194888178914e-06,
"loss": 0.6005,
"step": 1304
},
{
"epoch": 4.17,
"learning_rate": 4.964856230031949e-06,
"loss": 0.5863,
"step": 1306
},
{
"epoch": 4.18,
"learning_rate": 4.926517571884984e-06,
"loss": 0.5981,
"step": 1308
},
{
"epoch": 4.19,
"learning_rate": 4.88817891373802e-06,
"loss": 0.5974,
"step": 1310
},
{
"epoch": 4.19,
"learning_rate": 4.849840255591055e-06,
"loss": 0.6026,
"step": 1312
},
{
"epoch": 4.2,
"learning_rate": 4.811501597444089e-06,
"loss": 0.5244,
"step": 1314
},
{
"epoch": 4.2,
"learning_rate": 4.7731629392971246e-06,
"loss": 0.6554,
"step": 1316
},
{
"epoch": 4.21,
"learning_rate": 4.73482428115016e-06,
"loss": 0.6832,
"step": 1318
},
{
"epoch": 4.22,
"learning_rate": 4.696485623003195e-06,
"loss": 0.5667,
"step": 1320
},
{
"epoch": 4.22,
"learning_rate": 4.658146964856231e-06,
"loss": 0.6229,
"step": 1322
},
{
"epoch": 4.23,
"learning_rate": 4.619808306709265e-06,
"loss": 0.6106,
"step": 1324
},
{
"epoch": 4.24,
"learning_rate": 4.5814696485623e-06,
"loss": 0.6337,
"step": 1326
},
{
"epoch": 4.24,
"learning_rate": 4.5431309904153356e-06,
"loss": 0.5657,
"step": 1328
},
{
"epoch": 4.25,
"learning_rate": 4.504792332268371e-06,
"loss": 0.5111,
"step": 1330
},
{
"epoch": 4.26,
"learning_rate": 4.466453674121406e-06,
"loss": 0.5832,
"step": 1332
},
{
"epoch": 4.26,
"learning_rate": 4.428115015974441e-06,
"loss": 0.6349,
"step": 1334
},
{
"epoch": 4.27,
"learning_rate": 4.389776357827476e-06,
"loss": 0.6079,
"step": 1336
},
{
"epoch": 4.27,
"learning_rate": 4.351437699680511e-06,
"loss": 0.6025,
"step": 1338
},
{
"epoch": 4.28,
"learning_rate": 4.3130990415335465e-06,
"loss": 0.6749,
"step": 1340
},
{
"epoch": 4.29,
"learning_rate": 4.274760383386582e-06,
"loss": 0.4955,
"step": 1342
},
{
"epoch": 4.29,
"learning_rate": 4.236421725239617e-06,
"loss": 0.6526,
"step": 1344
},
{
"epoch": 4.3,
"learning_rate": 4.198083067092652e-06,
"loss": 0.5981,
"step": 1346
},
{
"epoch": 4.31,
"learning_rate": 4.159744408945687e-06,
"loss": 0.5532,
"step": 1348
},
{
"epoch": 4.31,
"learning_rate": 4.121405750798722e-06,
"loss": 0.5531,
"step": 1350
},
{
"epoch": 4.32,
"learning_rate": 4.0830670926517575e-06,
"loss": 0.7127,
"step": 1352
},
{
"epoch": 4.33,
"learning_rate": 4.044728434504792e-06,
"loss": 0.5255,
"step": 1354
},
{
"epoch": 4.33,
"learning_rate": 4.006389776357828e-06,
"loss": 0.5767,
"step": 1356
},
{
"epoch": 4.34,
"learning_rate": 3.968051118210863e-06,
"loss": 0.5786,
"step": 1358
},
{
"epoch": 4.35,
"learning_rate": 3.929712460063898e-06,
"loss": 0.612,
"step": 1360
},
{
"epoch": 4.35,
"learning_rate": 3.8913738019169325e-06,
"loss": 0.5656,
"step": 1362
},
{
"epoch": 4.36,
"learning_rate": 3.853035143769968e-06,
"loss": 0.5889,
"step": 1364
},
{
"epoch": 4.36,
"learning_rate": 3.8146964856230033e-06,
"loss": 0.5623,
"step": 1366
},
{
"epoch": 4.37,
"learning_rate": 3.7763578274760384e-06,
"loss": 0.5682,
"step": 1368
},
{
"epoch": 4.38,
"learning_rate": 3.7380191693290736e-06,
"loss": 0.6046,
"step": 1370
},
{
"epoch": 4.38,
"learning_rate": 3.6996805111821087e-06,
"loss": 0.5539,
"step": 1372
},
{
"epoch": 4.39,
"learning_rate": 3.661341853035144e-06,
"loss": 0.5942,
"step": 1374
},
{
"epoch": 4.4,
"learning_rate": 3.623003194888179e-06,
"loss": 0.5913,
"step": 1376
},
{
"epoch": 4.4,
"learning_rate": 3.5846645367412142e-06,
"loss": 0.6728,
"step": 1378
},
{
"epoch": 4.41,
"learning_rate": 3.546325878594249e-06,
"loss": 0.6059,
"step": 1380
},
{
"epoch": 4.42,
"learning_rate": 3.5079872204472846e-06,
"loss": 0.5953,
"step": 1382
},
{
"epoch": 4.42,
"learning_rate": 3.4696485623003197e-06,
"loss": 0.514,
"step": 1384
},
{
"epoch": 4.43,
"learning_rate": 3.4313099041533545e-06,
"loss": 0.5795,
"step": 1386
},
{
"epoch": 4.43,
"learning_rate": 3.39297124600639e-06,
"loss": 0.5996,
"step": 1388
},
{
"epoch": 4.44,
"learning_rate": 3.354632587859425e-06,
"loss": 0.7118,
"step": 1390
},
{
"epoch": 4.45,
"learning_rate": 3.31629392971246e-06,
"loss": 0.5451,
"step": 1392
},
{
"epoch": 4.45,
"learning_rate": 3.2779552715654956e-06,
"loss": 0.6372,
"step": 1394
},
{
"epoch": 4.46,
"learning_rate": 3.2396166134185303e-06,
"loss": 0.5097,
"step": 1396
},
{
"epoch": 4.47,
"learning_rate": 3.201277955271566e-06,
"loss": 0.7025,
"step": 1398
},
{
"epoch": 4.47,
"learning_rate": 3.1629392971246006e-06,
"loss": 0.5575,
"step": 1400
},
{
"epoch": 4.48,
"learning_rate": 3.124600638977636e-06,
"loss": 0.6481,
"step": 1402
},
{
"epoch": 4.49,
"learning_rate": 3.0862619808306714e-06,
"loss": 0.6648,
"step": 1404
},
{
"epoch": 4.49,
"learning_rate": 3.047923322683706e-06,
"loss": 0.6175,
"step": 1406
},
{
"epoch": 4.5,
"learning_rate": 3.0095846645367413e-06,
"loss": 0.6202,
"step": 1408
},
{
"epoch": 4.5,
"learning_rate": 2.9712460063897764e-06,
"loss": 0.6417,
"step": 1410
},
{
"epoch": 4.51,
"learning_rate": 2.9329073482428116e-06,
"loss": 0.5969,
"step": 1412
},
{
"epoch": 4.52,
"learning_rate": 2.8945686900958464e-06,
"loss": 0.6495,
"step": 1414
},
{
"epoch": 4.52,
"learning_rate": 2.856230031948882e-06,
"loss": 0.5732,
"step": 1416
},
{
"epoch": 4.53,
"learning_rate": 2.817891373801917e-06,
"loss": 0.6285,
"step": 1418
},
{
"epoch": 4.54,
"learning_rate": 2.779552715654952e-06,
"loss": 0.5838,
"step": 1420
},
{
"epoch": 4.54,
"learning_rate": 2.7412140575079874e-06,
"loss": 0.5399,
"step": 1422
},
{
"epoch": 4.55,
"learning_rate": 2.702875399361022e-06,
"loss": 0.6276,
"step": 1424
},
{
"epoch": 4.56,
"learning_rate": 2.6645367412140573e-06,
"loss": 0.6091,
"step": 1426
},
{
"epoch": 4.56,
"learning_rate": 2.626198083067093e-06,
"loss": 0.6779,
"step": 1428
},
{
"epoch": 4.57,
"learning_rate": 2.5878594249201277e-06,
"loss": 0.6196,
"step": 1430
},
{
"epoch": 4.58,
"learning_rate": 2.5495207667731633e-06,
"loss": 0.5829,
"step": 1432
},
{
"epoch": 4.58,
"learning_rate": 2.511182108626198e-06,
"loss": 0.6665,
"step": 1434
},
{
"epoch": 4.59,
"learning_rate": 2.472843450479233e-06,
"loss": 0.6329,
"step": 1436
},
{
"epoch": 4.59,
"learning_rate": 2.4345047923322688e-06,
"loss": 0.6559,
"step": 1438
},
{
"epoch": 4.6,
"learning_rate": 2.3961661341853035e-06,
"loss": 0.6463,
"step": 1440
},
{
"epoch": 4.61,
"learning_rate": 2.3578274760383387e-06,
"loss": 0.6325,
"step": 1442
},
{
"epoch": 4.61,
"learning_rate": 2.319488817891374e-06,
"loss": 0.6303,
"step": 1444
},
{
"epoch": 4.62,
"learning_rate": 2.281150159744409e-06,
"loss": 0.661,
"step": 1446
},
{
"epoch": 4.63,
"learning_rate": 2.242811501597444e-06,
"loss": 0.5913,
"step": 1448
},
{
"epoch": 4.63,
"learning_rate": 2.2044728434504793e-06,
"loss": 0.5916,
"step": 1450
},
{
"epoch": 4.64,
"learning_rate": 2.1661341853035145e-06,
"loss": 0.6081,
"step": 1452
},
{
"epoch": 4.65,
"learning_rate": 2.1277955271565492e-06,
"loss": 0.6071,
"step": 1454
},
{
"epoch": 4.65,
"learning_rate": 2.089456869009585e-06,
"loss": 0.6329,
"step": 1456
},
{
"epoch": 4.66,
"learning_rate": 2.05111821086262e-06,
"loss": 0.6528,
"step": 1458
},
{
"epoch": 4.66,
"learning_rate": 2.0127795527156547e-06,
"loss": 0.5985,
"step": 1460
},
{
"epoch": 4.67,
"learning_rate": 1.9744408945686903e-06,
"loss": 0.56,
"step": 1462
},
{
"epoch": 4.68,
"learning_rate": 1.936102236421725e-06,
"loss": 0.5896,
"step": 1464
},
{
"epoch": 4.68,
"learning_rate": 1.8977635782747604e-06,
"loss": 0.5485,
"step": 1466
},
{
"epoch": 4.69,
"learning_rate": 1.8594249201277956e-06,
"loss": 0.5567,
"step": 1468
},
{
"epoch": 4.7,
"learning_rate": 1.8210862619808305e-06,
"loss": 0.5926,
"step": 1470
},
{
"epoch": 4.7,
"learning_rate": 1.782747603833866e-06,
"loss": 0.5978,
"step": 1472
},
{
"epoch": 4.71,
"learning_rate": 1.744408945686901e-06,
"loss": 0.6255,
"step": 1474
},
{
"epoch": 4.72,
"learning_rate": 1.7060702875399362e-06,
"loss": 0.6374,
"step": 1476
},
{
"epoch": 4.72,
"learning_rate": 1.6677316293929712e-06,
"loss": 0.5902,
"step": 1478
},
{
"epoch": 4.73,
"learning_rate": 1.6293929712460064e-06,
"loss": 0.5465,
"step": 1480
},
{
"epoch": 4.73,
"learning_rate": 1.5910543130990417e-06,
"loss": 0.6076,
"step": 1482
},
{
"epoch": 4.74,
"learning_rate": 1.5527156549520767e-06,
"loss": 0.5938,
"step": 1484
},
{
"epoch": 4.75,
"learning_rate": 1.5143769968051119e-06,
"loss": 0.6822,
"step": 1486
},
{
"epoch": 4.75,
"learning_rate": 1.476038338658147e-06,
"loss": 0.6091,
"step": 1488
},
{
"epoch": 4.76,
"learning_rate": 1.4376996805111822e-06,
"loss": 0.6528,
"step": 1490
},
{
"epoch": 4.77,
"learning_rate": 1.3993610223642171e-06,
"loss": 0.4949,
"step": 1492
},
{
"epoch": 4.77,
"learning_rate": 1.3610223642172525e-06,
"loss": 0.564,
"step": 1494
},
{
"epoch": 4.78,
"learning_rate": 1.3226837060702877e-06,
"loss": 0.5988,
"step": 1496
},
{
"epoch": 4.79,
"learning_rate": 1.2843450479233226e-06,
"loss": 0.6042,
"step": 1498
},
{
"epoch": 4.79,
"learning_rate": 1.2460063897763578e-06,
"loss": 0.6425,
"step": 1500
},
{
"epoch": 4.8,
"learning_rate": 1.207667731629393e-06,
"loss": 0.6112,
"step": 1502
},
{
"epoch": 4.81,
"learning_rate": 1.1693290734824281e-06,
"loss": 0.6148,
"step": 1504
},
{
"epoch": 4.81,
"learning_rate": 1.1309904153354633e-06,
"loss": 0.6198,
"step": 1506
},
{
"epoch": 4.82,
"learning_rate": 1.0926517571884984e-06,
"loss": 0.5613,
"step": 1508
},
{
"epoch": 4.82,
"learning_rate": 1.0543130990415336e-06,
"loss": 0.6095,
"step": 1510
},
{
"epoch": 4.83,
"learning_rate": 1.0159744408945686e-06,
"loss": 0.5758,
"step": 1512
},
{
"epoch": 4.84,
"learning_rate": 9.77635782747604e-07,
"loss": 0.5765,
"step": 1514
},
{
"epoch": 4.84,
"learning_rate": 9.39297124600639e-07,
"loss": 0.5575,
"step": 1516
},
{
"epoch": 4.85,
"learning_rate": 9.009584664536742e-07,
"loss": 0.6533,
"step": 1518
},
{
"epoch": 4.86,
"learning_rate": 8.626198083067092e-07,
"loss": 0.5958,
"step": 1520
},
{
"epoch": 4.86,
"learning_rate": 8.242811501597445e-07,
"loss": 0.6021,
"step": 1522
},
{
"epoch": 4.87,
"learning_rate": 7.859424920127796e-07,
"loss": 0.6594,
"step": 1524
},
{
"epoch": 4.88,
"learning_rate": 7.476038338658146e-07,
"loss": 0.6509,
"step": 1526
},
{
"epoch": 4.88,
"learning_rate": 7.092651757188499e-07,
"loss": 0.5746,
"step": 1528
},
{
"epoch": 4.89,
"learning_rate": 6.709265175718849e-07,
"loss": 0.6054,
"step": 1530
},
{
"epoch": 4.89,
"learning_rate": 6.325878594249202e-07,
"loss": 0.6509,
"step": 1532
},
{
"epoch": 4.9,
"learning_rate": 5.942492012779553e-07,
"loss": 0.6549,
"step": 1534
},
{
"epoch": 4.91,
"learning_rate": 5.559105431309904e-07,
"loss": 0.6603,
"step": 1536
},
{
"epoch": 4.91,
"learning_rate": 5.175718849840256e-07,
"loss": 0.5868,
"step": 1538
},
{
"epoch": 4.92,
"learning_rate": 4.792332268370607e-07,
"loss": 0.5623,
"step": 1540
},
{
"epoch": 4.93,
"learning_rate": 4.408945686900959e-07,
"loss": 0.5934,
"step": 1542
},
{
"epoch": 4.93,
"learning_rate": 4.02555910543131e-07,
"loss": 0.5603,
"step": 1544
},
{
"epoch": 4.94,
"learning_rate": 3.6421725239616615e-07,
"loss": 0.6026,
"step": 1546
},
{
"epoch": 4.95,
"learning_rate": 3.2587859424920126e-07,
"loss": 0.6624,
"step": 1548
},
{
"epoch": 4.95,
"learning_rate": 2.875399361022364e-07,
"loss": 0.5714,
"step": 1550
},
{
"epoch": 4.96,
"learning_rate": 2.492012779552716e-07,
"loss": 0.649,
"step": 1552
},
{
"epoch": 4.96,
"learning_rate": 2.1086261980830673e-07,
"loss": 0.6734,
"step": 1554
},
{
"epoch": 4.97,
"learning_rate": 1.7252396166134187e-07,
"loss": 0.566,
"step": 1556
},
{
"epoch": 4.98,
"learning_rate": 1.34185303514377e-07,
"loss": 0.4991,
"step": 1558
},
{
"epoch": 4.98,
"learning_rate": 9.584664536741214e-08,
"loss": 0.5879,
"step": 1560
},
{
"epoch": 4.99,
"learning_rate": 5.7507987220447286e-08,
"loss": 0.7251,
"step": 1562
},
{
"epoch": 5.0,
"learning_rate": 1.9169329073482428e-08,
"loss": 0.6032,
"step": 1564
},
{
"epoch": 5.0,
"eval_accuracy": 0.5890570282936096,
"eval_loss": 0.7185935974121094,
"eval_runtime": 3283.9525,
"eval_samples_per_second": 1.308,
"eval_steps_per_second": 0.041,
"step": 1565
}
],
"logging_steps": 2,
"max_steps": 1565,
"num_train_epochs": 5,
"save_steps": 500,
"total_flos": 3.4123046191104e+18,
"trial_name": null,
"trial_params": null
}