pythia-oa / trainer_state.json
TinyPixel's picture
Upload folder using huggingface_hub
7c52d61
raw
history blame
32.5 kB
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.9984729715972717,
"eval_steps": 500,
"global_step": 613,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 1.832,
"step": 2
},
{
"epoch": 0.01,
"learning_rate": 0.0002,
"loss": 1.7302,
"step": 4
},
{
"epoch": 0.01,
"learning_rate": 0.0002,
"loss": 1.7378,
"step": 6
},
{
"epoch": 0.01,
"learning_rate": 0.0002,
"loss": 1.7793,
"step": 8
},
{
"epoch": 0.02,
"learning_rate": 0.0002,
"loss": 1.7485,
"step": 10
},
{
"epoch": 0.02,
"learning_rate": 0.0002,
"loss": 1.7227,
"step": 12
},
{
"epoch": 0.02,
"learning_rate": 0.0002,
"loss": 1.7285,
"step": 14
},
{
"epoch": 0.03,
"learning_rate": 0.0002,
"loss": 1.7326,
"step": 16
},
{
"epoch": 0.03,
"learning_rate": 0.0002,
"loss": 1.8654,
"step": 18
},
{
"epoch": 0.03,
"learning_rate": 0.0002,
"loss": 1.7466,
"step": 20
},
{
"epoch": 0.04,
"learning_rate": 0.0002,
"loss": 1.7182,
"step": 22
},
{
"epoch": 0.04,
"learning_rate": 0.0002,
"loss": 1.7394,
"step": 24
},
{
"epoch": 0.04,
"learning_rate": 0.0002,
"loss": 1.7596,
"step": 26
},
{
"epoch": 0.05,
"learning_rate": 0.0002,
"loss": 1.8005,
"step": 28
},
{
"epoch": 0.05,
"learning_rate": 0.0002,
"loss": 1.7609,
"step": 30
},
{
"epoch": 0.05,
"learning_rate": 0.0002,
"loss": 1.8792,
"step": 32
},
{
"epoch": 0.06,
"learning_rate": 0.0002,
"loss": 1.8621,
"step": 34
},
{
"epoch": 0.06,
"learning_rate": 0.0002,
"loss": 1.7995,
"step": 36
},
{
"epoch": 0.06,
"learning_rate": 0.0002,
"loss": 2.0867,
"step": 38
},
{
"epoch": 0.07,
"learning_rate": 0.0002,
"loss": 2.0513,
"step": 40
},
{
"epoch": 0.07,
"learning_rate": 0.0002,
"loss": 1.8084,
"step": 42
},
{
"epoch": 0.07,
"learning_rate": 0.0002,
"loss": 1.8203,
"step": 44
},
{
"epoch": 0.07,
"learning_rate": 0.0002,
"loss": 1.7905,
"step": 46
},
{
"epoch": 0.08,
"learning_rate": 0.0002,
"loss": 1.7966,
"step": 48
},
{
"epoch": 0.08,
"learning_rate": 0.0002,
"loss": 1.295,
"step": 50
},
{
"epoch": 0.08,
"learning_rate": 0.0002,
"loss": 1.6161,
"step": 52
},
{
"epoch": 0.09,
"learning_rate": 0.0002,
"loss": 1.6371,
"step": 54
},
{
"epoch": 0.09,
"learning_rate": 0.0002,
"loss": 1.7243,
"step": 56
},
{
"epoch": 0.09,
"learning_rate": 0.0002,
"loss": 1.5343,
"step": 58
},
{
"epoch": 0.1,
"learning_rate": 0.0002,
"loss": 1.5573,
"step": 60
},
{
"epoch": 0.1,
"learning_rate": 0.0002,
"loss": 1.5717,
"step": 62
},
{
"epoch": 0.1,
"learning_rate": 0.0002,
"loss": 1.591,
"step": 64
},
{
"epoch": 0.11,
"learning_rate": 0.0002,
"loss": 1.8383,
"step": 66
},
{
"epoch": 0.11,
"learning_rate": 0.0002,
"loss": 1.6448,
"step": 68
},
{
"epoch": 0.11,
"learning_rate": 0.0002,
"loss": 1.6847,
"step": 70
},
{
"epoch": 0.12,
"learning_rate": 0.0002,
"loss": 1.626,
"step": 72
},
{
"epoch": 0.12,
"learning_rate": 0.0002,
"loss": 1.64,
"step": 74
},
{
"epoch": 0.12,
"learning_rate": 0.0002,
"loss": 1.6266,
"step": 76
},
{
"epoch": 0.13,
"learning_rate": 0.0002,
"loss": 1.8701,
"step": 78
},
{
"epoch": 0.13,
"learning_rate": 0.0002,
"loss": 1.825,
"step": 80
},
{
"epoch": 0.13,
"learning_rate": 0.0002,
"loss": 1.6469,
"step": 82
},
{
"epoch": 0.14,
"learning_rate": 0.0002,
"loss": 1.6921,
"step": 84
},
{
"epoch": 0.14,
"learning_rate": 0.0002,
"loss": 1.6931,
"step": 86
},
{
"epoch": 0.14,
"learning_rate": 0.0002,
"loss": 1.7856,
"step": 88
},
{
"epoch": 0.15,
"learning_rate": 0.0002,
"loss": 1.8564,
"step": 90
},
{
"epoch": 0.15,
"learning_rate": 0.0002,
"loss": 1.8208,
"step": 92
},
{
"epoch": 0.15,
"learning_rate": 0.0002,
"loss": 1.8388,
"step": 94
},
{
"epoch": 0.16,
"learning_rate": 0.0002,
"loss": 1.7202,
"step": 96
},
{
"epoch": 0.16,
"learning_rate": 0.0002,
"loss": 1.7919,
"step": 98
},
{
"epoch": 0.16,
"learning_rate": 0.0002,
"loss": 1.5837,
"step": 100
},
{
"epoch": 0.17,
"learning_rate": 0.0002,
"loss": 1.6023,
"step": 102
},
{
"epoch": 0.17,
"learning_rate": 0.0002,
"loss": 1.5409,
"step": 104
},
{
"epoch": 0.17,
"learning_rate": 0.0002,
"loss": 1.5498,
"step": 106
},
{
"epoch": 0.18,
"learning_rate": 0.0002,
"loss": 1.5299,
"step": 108
},
{
"epoch": 0.18,
"learning_rate": 0.0002,
"loss": 1.7106,
"step": 110
},
{
"epoch": 0.18,
"learning_rate": 0.0002,
"loss": 1.6908,
"step": 112
},
{
"epoch": 0.19,
"learning_rate": 0.0002,
"loss": 1.6457,
"step": 114
},
{
"epoch": 0.19,
"learning_rate": 0.0002,
"loss": 1.6573,
"step": 116
},
{
"epoch": 0.19,
"learning_rate": 0.0002,
"loss": 1.6344,
"step": 118
},
{
"epoch": 0.2,
"learning_rate": 0.0002,
"loss": 1.6821,
"step": 120
},
{
"epoch": 0.2,
"learning_rate": 0.0002,
"loss": 1.5921,
"step": 122
},
{
"epoch": 0.2,
"learning_rate": 0.0002,
"loss": 1.7669,
"step": 124
},
{
"epoch": 0.21,
"learning_rate": 0.0002,
"loss": 1.6449,
"step": 126
},
{
"epoch": 0.21,
"learning_rate": 0.0002,
"loss": 1.7399,
"step": 128
},
{
"epoch": 0.21,
"learning_rate": 0.0002,
"loss": 1.6255,
"step": 130
},
{
"epoch": 0.22,
"learning_rate": 0.0002,
"loss": 1.6353,
"step": 132
},
{
"epoch": 0.22,
"learning_rate": 0.0002,
"loss": 1.7772,
"step": 134
},
{
"epoch": 0.22,
"learning_rate": 0.0002,
"loss": 1.6832,
"step": 136
},
{
"epoch": 0.22,
"learning_rate": 0.0002,
"loss": 1.9061,
"step": 138
},
{
"epoch": 0.23,
"learning_rate": 0.0002,
"loss": 1.9422,
"step": 140
},
{
"epoch": 0.23,
"learning_rate": 0.0002,
"loss": 1.8643,
"step": 142
},
{
"epoch": 0.23,
"learning_rate": 0.0002,
"loss": 1.8782,
"step": 144
},
{
"epoch": 0.24,
"learning_rate": 0.0002,
"loss": 1.8023,
"step": 146
},
{
"epoch": 0.24,
"learning_rate": 0.0002,
"loss": 1.7753,
"step": 148
},
{
"epoch": 0.24,
"learning_rate": 0.0002,
"loss": 1.4318,
"step": 150
},
{
"epoch": 0.25,
"learning_rate": 0.0002,
"loss": 1.5817,
"step": 152
},
{
"epoch": 0.25,
"learning_rate": 0.0002,
"loss": 1.5097,
"step": 154
},
{
"epoch": 0.25,
"learning_rate": 0.0002,
"loss": 1.5909,
"step": 156
},
{
"epoch": 0.26,
"learning_rate": 0.0002,
"loss": 1.5129,
"step": 158
},
{
"epoch": 0.26,
"learning_rate": 0.0002,
"loss": 1.5801,
"step": 160
},
{
"epoch": 0.26,
"learning_rate": 0.0002,
"loss": 1.6804,
"step": 162
},
{
"epoch": 0.27,
"learning_rate": 0.0002,
"loss": 1.6172,
"step": 164
},
{
"epoch": 0.27,
"learning_rate": 0.0002,
"loss": 1.6786,
"step": 166
},
{
"epoch": 0.27,
"learning_rate": 0.0002,
"loss": 1.592,
"step": 168
},
{
"epoch": 0.28,
"learning_rate": 0.0002,
"loss": 1.6977,
"step": 170
},
{
"epoch": 0.28,
"learning_rate": 0.0002,
"loss": 1.6936,
"step": 172
},
{
"epoch": 0.28,
"learning_rate": 0.0002,
"loss": 1.6187,
"step": 174
},
{
"epoch": 0.29,
"learning_rate": 0.0002,
"loss": 1.6936,
"step": 176
},
{
"epoch": 0.29,
"learning_rate": 0.0002,
"loss": 1.7276,
"step": 178
},
{
"epoch": 0.29,
"learning_rate": 0.0002,
"loss": 1.6662,
"step": 180
},
{
"epoch": 0.3,
"learning_rate": 0.0002,
"loss": 1.7768,
"step": 182
},
{
"epoch": 0.3,
"learning_rate": 0.0002,
"loss": 1.6908,
"step": 184
},
{
"epoch": 0.3,
"learning_rate": 0.0002,
"loss": 1.7045,
"step": 186
},
{
"epoch": 0.31,
"learning_rate": 0.0002,
"loss": 1.8561,
"step": 188
},
{
"epoch": 0.31,
"learning_rate": 0.0002,
"loss": 1.757,
"step": 190
},
{
"epoch": 0.31,
"learning_rate": 0.0002,
"loss": 1.8863,
"step": 192
},
{
"epoch": 0.32,
"learning_rate": 0.0002,
"loss": 1.7737,
"step": 194
},
{
"epoch": 0.32,
"learning_rate": 0.0002,
"loss": 1.7499,
"step": 196
},
{
"epoch": 0.32,
"learning_rate": 0.0002,
"loss": 1.6848,
"step": 198
},
{
"epoch": 0.33,
"learning_rate": 0.0002,
"loss": 1.3447,
"step": 200
},
{
"epoch": 0.33,
"learning_rate": 0.0002,
"loss": 1.6347,
"step": 202
},
{
"epoch": 0.33,
"learning_rate": 0.0002,
"loss": 1.5359,
"step": 204
},
{
"epoch": 0.34,
"learning_rate": 0.0002,
"loss": 1.6026,
"step": 206
},
{
"epoch": 0.34,
"learning_rate": 0.0002,
"loss": 1.606,
"step": 208
},
{
"epoch": 0.34,
"learning_rate": 0.0002,
"loss": 1.6077,
"step": 210
},
{
"epoch": 0.35,
"learning_rate": 0.0002,
"loss": 1.7816,
"step": 212
},
{
"epoch": 0.35,
"learning_rate": 0.0002,
"loss": 1.6046,
"step": 214
},
{
"epoch": 0.35,
"learning_rate": 0.0002,
"loss": 1.698,
"step": 216
},
{
"epoch": 0.36,
"learning_rate": 0.0002,
"loss": 1.7219,
"step": 218
},
{
"epoch": 0.36,
"learning_rate": 0.0002,
"loss": 1.8967,
"step": 220
},
{
"epoch": 0.36,
"learning_rate": 0.0002,
"loss": 1.6255,
"step": 222
},
{
"epoch": 0.36,
"learning_rate": 0.0002,
"loss": 1.5728,
"step": 224
},
{
"epoch": 0.37,
"learning_rate": 0.0002,
"loss": 1.6896,
"step": 226
},
{
"epoch": 0.37,
"learning_rate": 0.0002,
"loss": 1.5951,
"step": 228
},
{
"epoch": 0.37,
"learning_rate": 0.0002,
"loss": 1.6148,
"step": 230
},
{
"epoch": 0.38,
"learning_rate": 0.0002,
"loss": 1.9197,
"step": 232
},
{
"epoch": 0.38,
"learning_rate": 0.0002,
"loss": 1.8497,
"step": 234
},
{
"epoch": 0.38,
"learning_rate": 0.0002,
"loss": 1.7573,
"step": 236
},
{
"epoch": 0.39,
"learning_rate": 0.0002,
"loss": 1.7234,
"step": 238
},
{
"epoch": 0.39,
"learning_rate": 0.0002,
"loss": 1.7904,
"step": 240
},
{
"epoch": 0.39,
"learning_rate": 0.0002,
"loss": 1.72,
"step": 242
},
{
"epoch": 0.4,
"learning_rate": 0.0002,
"loss": 1.9269,
"step": 244
},
{
"epoch": 0.4,
"learning_rate": 0.0002,
"loss": 1.8646,
"step": 246
},
{
"epoch": 0.4,
"learning_rate": 0.0002,
"loss": 1.7174,
"step": 248
},
{
"epoch": 0.41,
"learning_rate": 0.0002,
"loss": 1.3772,
"step": 250
},
{
"epoch": 0.41,
"learning_rate": 0.0002,
"loss": 1.5485,
"step": 252
},
{
"epoch": 0.41,
"learning_rate": 0.0002,
"loss": 1.5269,
"step": 254
},
{
"epoch": 0.42,
"learning_rate": 0.0002,
"loss": 1.4701,
"step": 256
},
{
"epoch": 0.42,
"learning_rate": 0.0002,
"loss": 1.5889,
"step": 258
},
{
"epoch": 0.42,
"learning_rate": 0.0002,
"loss": 1.5645,
"step": 260
},
{
"epoch": 0.43,
"learning_rate": 0.0002,
"loss": 1.6054,
"step": 262
},
{
"epoch": 0.43,
"learning_rate": 0.0002,
"loss": 1.5589,
"step": 264
},
{
"epoch": 0.43,
"learning_rate": 0.0002,
"loss": 1.6552,
"step": 266
},
{
"epoch": 0.44,
"learning_rate": 0.0002,
"loss": 1.5181,
"step": 268
},
{
"epoch": 0.44,
"learning_rate": 0.0002,
"loss": 1.6459,
"step": 270
},
{
"epoch": 0.44,
"learning_rate": 0.0002,
"loss": 1.722,
"step": 272
},
{
"epoch": 0.45,
"learning_rate": 0.0002,
"loss": 1.5711,
"step": 274
},
{
"epoch": 0.45,
"learning_rate": 0.0002,
"loss": 1.6919,
"step": 276
},
{
"epoch": 0.45,
"learning_rate": 0.0002,
"loss": 1.6426,
"step": 278
},
{
"epoch": 0.46,
"learning_rate": 0.0002,
"loss": 1.6417,
"step": 280
},
{
"epoch": 0.46,
"learning_rate": 0.0002,
"loss": 1.6409,
"step": 282
},
{
"epoch": 0.46,
"learning_rate": 0.0002,
"loss": 1.824,
"step": 284
},
{
"epoch": 0.47,
"learning_rate": 0.0002,
"loss": 1.7294,
"step": 286
},
{
"epoch": 0.47,
"learning_rate": 0.0002,
"loss": 1.6698,
"step": 288
},
{
"epoch": 0.47,
"learning_rate": 0.0002,
"loss": 1.7013,
"step": 290
},
{
"epoch": 0.48,
"learning_rate": 0.0002,
"loss": 1.699,
"step": 292
},
{
"epoch": 0.48,
"learning_rate": 0.0002,
"loss": 1.7408,
"step": 294
},
{
"epoch": 0.48,
"learning_rate": 0.0002,
"loss": 1.7299,
"step": 296
},
{
"epoch": 0.49,
"learning_rate": 0.0002,
"loss": 1.7278,
"step": 298
},
{
"epoch": 0.49,
"learning_rate": 0.0002,
"loss": 1.2081,
"step": 300
},
{
"epoch": 0.49,
"learning_rate": 0.0002,
"loss": 1.5635,
"step": 302
},
{
"epoch": 0.5,
"learning_rate": 0.0002,
"loss": 1.443,
"step": 304
},
{
"epoch": 0.5,
"learning_rate": 0.0002,
"loss": 1.4373,
"step": 306
},
{
"epoch": 0.5,
"learning_rate": 0.0002,
"loss": 1.5823,
"step": 308
},
{
"epoch": 0.5,
"learning_rate": 0.0002,
"loss": 1.6226,
"step": 310
},
{
"epoch": 0.51,
"learning_rate": 0.0002,
"loss": 1.452,
"step": 312
},
{
"epoch": 0.51,
"learning_rate": 0.0002,
"loss": 1.6459,
"step": 314
},
{
"epoch": 0.51,
"learning_rate": 0.0002,
"loss": 1.5302,
"step": 316
},
{
"epoch": 0.52,
"learning_rate": 0.0002,
"loss": 1.5737,
"step": 318
},
{
"epoch": 0.52,
"learning_rate": 0.0002,
"loss": 1.6102,
"step": 320
},
{
"epoch": 0.52,
"learning_rate": 0.0002,
"loss": 1.6705,
"step": 322
},
{
"epoch": 0.53,
"learning_rate": 0.0002,
"loss": 1.6721,
"step": 324
},
{
"epoch": 0.53,
"learning_rate": 0.0002,
"loss": 1.8056,
"step": 326
},
{
"epoch": 0.53,
"learning_rate": 0.0002,
"loss": 1.5095,
"step": 328
},
{
"epoch": 0.54,
"learning_rate": 0.0002,
"loss": 1.7423,
"step": 330
},
{
"epoch": 0.54,
"learning_rate": 0.0002,
"loss": 1.9658,
"step": 332
},
{
"epoch": 0.54,
"learning_rate": 0.0002,
"loss": 1.6538,
"step": 334
},
{
"epoch": 0.55,
"learning_rate": 0.0002,
"loss": 1.706,
"step": 336
},
{
"epoch": 0.55,
"learning_rate": 0.0002,
"loss": 1.6369,
"step": 338
},
{
"epoch": 0.55,
"learning_rate": 0.0002,
"loss": 1.8973,
"step": 340
},
{
"epoch": 0.56,
"learning_rate": 0.0002,
"loss": 1.9755,
"step": 342
},
{
"epoch": 0.56,
"learning_rate": 0.0002,
"loss": 1.9015,
"step": 344
},
{
"epoch": 0.56,
"learning_rate": 0.0002,
"loss": 1.6174,
"step": 346
},
{
"epoch": 0.57,
"learning_rate": 0.0002,
"loss": 1.7096,
"step": 348
},
{
"epoch": 0.57,
"learning_rate": 0.0002,
"loss": 1.4354,
"step": 350
},
{
"epoch": 0.57,
"learning_rate": 0.0002,
"loss": 1.5231,
"step": 352
},
{
"epoch": 0.58,
"learning_rate": 0.0002,
"loss": 1.5751,
"step": 354
},
{
"epoch": 0.58,
"learning_rate": 0.0002,
"loss": 1.6965,
"step": 356
},
{
"epoch": 0.58,
"learning_rate": 0.0002,
"loss": 1.5387,
"step": 358
},
{
"epoch": 0.59,
"learning_rate": 0.0002,
"loss": 1.6912,
"step": 360
},
{
"epoch": 0.59,
"learning_rate": 0.0002,
"loss": 1.7088,
"step": 362
},
{
"epoch": 0.59,
"learning_rate": 0.0002,
"loss": 1.6569,
"step": 364
},
{
"epoch": 0.6,
"learning_rate": 0.0002,
"loss": 1.4839,
"step": 366
},
{
"epoch": 0.6,
"learning_rate": 0.0002,
"loss": 1.6253,
"step": 368
},
{
"epoch": 0.6,
"learning_rate": 0.0002,
"loss": 1.6165,
"step": 370
},
{
"epoch": 0.61,
"learning_rate": 0.0002,
"loss": 1.6116,
"step": 372
},
{
"epoch": 0.61,
"learning_rate": 0.0002,
"loss": 1.6778,
"step": 374
},
{
"epoch": 0.61,
"learning_rate": 0.0002,
"loss": 1.5795,
"step": 376
},
{
"epoch": 0.62,
"learning_rate": 0.0002,
"loss": 1.5197,
"step": 378
},
{
"epoch": 0.62,
"learning_rate": 0.0002,
"loss": 1.7243,
"step": 380
},
{
"epoch": 0.62,
"learning_rate": 0.0002,
"loss": 1.7019,
"step": 382
},
{
"epoch": 0.63,
"learning_rate": 0.0002,
"loss": 1.7285,
"step": 384
},
{
"epoch": 0.63,
"learning_rate": 0.0002,
"loss": 1.8612,
"step": 386
},
{
"epoch": 0.63,
"learning_rate": 0.0002,
"loss": 1.8324,
"step": 388
},
{
"epoch": 0.64,
"learning_rate": 0.0002,
"loss": 1.828,
"step": 390
},
{
"epoch": 0.64,
"learning_rate": 0.0002,
"loss": 1.8997,
"step": 392
},
{
"epoch": 0.64,
"learning_rate": 0.0002,
"loss": 1.7828,
"step": 394
},
{
"epoch": 0.65,
"learning_rate": 0.0002,
"loss": 1.7951,
"step": 396
},
{
"epoch": 0.65,
"learning_rate": 0.0002,
"loss": 1.6725,
"step": 398
},
{
"epoch": 0.65,
"learning_rate": 0.0002,
"loss": 1.3894,
"step": 400
},
{
"epoch": 0.65,
"learning_rate": 0.0002,
"loss": 1.5686,
"step": 402
},
{
"epoch": 0.66,
"learning_rate": 0.0002,
"loss": 1.5029,
"step": 404
},
{
"epoch": 0.66,
"learning_rate": 0.0002,
"loss": 1.5377,
"step": 406
},
{
"epoch": 0.66,
"learning_rate": 0.0002,
"loss": 1.5741,
"step": 408
},
{
"epoch": 0.67,
"learning_rate": 0.0002,
"loss": 1.6417,
"step": 410
},
{
"epoch": 0.67,
"learning_rate": 0.0002,
"loss": 1.6645,
"step": 412
},
{
"epoch": 0.67,
"learning_rate": 0.0002,
"loss": 1.507,
"step": 414
},
{
"epoch": 0.68,
"learning_rate": 0.0002,
"loss": 1.5731,
"step": 416
},
{
"epoch": 0.68,
"learning_rate": 0.0002,
"loss": 1.6381,
"step": 418
},
{
"epoch": 0.68,
"learning_rate": 0.0002,
"loss": 1.6473,
"step": 420
},
{
"epoch": 0.69,
"learning_rate": 0.0002,
"loss": 1.572,
"step": 422
},
{
"epoch": 0.69,
"learning_rate": 0.0002,
"loss": 1.6077,
"step": 424
},
{
"epoch": 0.69,
"learning_rate": 0.0002,
"loss": 1.5529,
"step": 426
},
{
"epoch": 0.7,
"learning_rate": 0.0002,
"loss": 1.6884,
"step": 428
},
{
"epoch": 0.7,
"learning_rate": 0.0002,
"loss": 1.7012,
"step": 430
},
{
"epoch": 0.7,
"learning_rate": 0.0002,
"loss": 1.8241,
"step": 432
},
{
"epoch": 0.71,
"learning_rate": 0.0002,
"loss": 1.5989,
"step": 434
},
{
"epoch": 0.71,
"learning_rate": 0.0002,
"loss": 1.8149,
"step": 436
},
{
"epoch": 0.71,
"learning_rate": 0.0002,
"loss": 1.7036,
"step": 438
},
{
"epoch": 0.72,
"learning_rate": 0.0002,
"loss": 1.8744,
"step": 440
},
{
"epoch": 0.72,
"learning_rate": 0.0002,
"loss": 1.8474,
"step": 442
},
{
"epoch": 0.72,
"learning_rate": 0.0002,
"loss": 1.9166,
"step": 444
},
{
"epoch": 0.73,
"learning_rate": 0.0002,
"loss": 1.7282,
"step": 446
},
{
"epoch": 0.73,
"learning_rate": 0.0002,
"loss": 1.5606,
"step": 448
},
{
"epoch": 0.73,
"learning_rate": 0.0002,
"loss": 1.344,
"step": 450
},
{
"epoch": 0.74,
"learning_rate": 0.0002,
"loss": 1.5517,
"step": 452
},
{
"epoch": 0.74,
"learning_rate": 0.0002,
"loss": 1.6024,
"step": 454
},
{
"epoch": 0.74,
"learning_rate": 0.0002,
"loss": 1.5216,
"step": 456
},
{
"epoch": 0.75,
"learning_rate": 0.0002,
"loss": 1.4755,
"step": 458
},
{
"epoch": 0.75,
"learning_rate": 0.0002,
"loss": 1.6639,
"step": 460
},
{
"epoch": 0.75,
"learning_rate": 0.0002,
"loss": 1.581,
"step": 462
},
{
"epoch": 0.76,
"learning_rate": 0.0002,
"loss": 1.6928,
"step": 464
},
{
"epoch": 0.76,
"learning_rate": 0.0002,
"loss": 1.6463,
"step": 466
},
{
"epoch": 0.76,
"learning_rate": 0.0002,
"loss": 1.5748,
"step": 468
},
{
"epoch": 0.77,
"learning_rate": 0.0002,
"loss": 1.4912,
"step": 470
},
{
"epoch": 0.77,
"learning_rate": 0.0002,
"loss": 1.5931,
"step": 472
},
{
"epoch": 0.77,
"learning_rate": 0.0002,
"loss": 1.5764,
"step": 474
},
{
"epoch": 0.78,
"learning_rate": 0.0002,
"loss": 1.7494,
"step": 476
},
{
"epoch": 0.78,
"learning_rate": 0.0002,
"loss": 1.5696,
"step": 478
},
{
"epoch": 0.78,
"learning_rate": 0.0002,
"loss": 1.7536,
"step": 480
},
{
"epoch": 0.79,
"learning_rate": 0.0002,
"loss": 1.6516,
"step": 482
},
{
"epoch": 0.79,
"learning_rate": 0.0002,
"loss": 1.7752,
"step": 484
},
{
"epoch": 0.79,
"learning_rate": 0.0002,
"loss": 1.7401,
"step": 486
},
{
"epoch": 0.79,
"learning_rate": 0.0002,
"loss": 1.7159,
"step": 488
},
{
"epoch": 0.8,
"learning_rate": 0.0002,
"loss": 1.8925,
"step": 490
},
{
"epoch": 0.8,
"learning_rate": 0.0002,
"loss": 1.7296,
"step": 492
},
{
"epoch": 0.8,
"learning_rate": 0.0002,
"loss": 1.8207,
"step": 494
},
{
"epoch": 0.81,
"learning_rate": 0.0002,
"loss": 1.8015,
"step": 496
},
{
"epoch": 0.81,
"learning_rate": 0.0002,
"loss": 1.6387,
"step": 498
},
{
"epoch": 0.81,
"learning_rate": 0.0002,
"loss": 1.4543,
"step": 500
},
{
"epoch": 0.82,
"learning_rate": 0.0002,
"loss": 1.7365,
"step": 502
},
{
"epoch": 0.82,
"learning_rate": 0.0002,
"loss": 1.4881,
"step": 504
},
{
"epoch": 0.82,
"learning_rate": 0.0002,
"loss": 1.5554,
"step": 506
},
{
"epoch": 0.83,
"learning_rate": 0.0002,
"loss": 1.5883,
"step": 508
},
{
"epoch": 0.83,
"learning_rate": 0.0002,
"loss": 1.5758,
"step": 510
},
{
"epoch": 0.83,
"learning_rate": 0.0002,
"loss": 1.6395,
"step": 512
},
{
"epoch": 0.84,
"learning_rate": 0.0002,
"loss": 1.5694,
"step": 514
},
{
"epoch": 0.84,
"learning_rate": 0.0002,
"loss": 1.5924,
"step": 516
},
{
"epoch": 0.84,
"learning_rate": 0.0002,
"loss": 1.5662,
"step": 518
},
{
"epoch": 0.85,
"learning_rate": 0.0002,
"loss": 1.6818,
"step": 520
},
{
"epoch": 0.85,
"learning_rate": 0.0002,
"loss": 1.597,
"step": 522
},
{
"epoch": 0.85,
"learning_rate": 0.0002,
"loss": 1.4934,
"step": 524
},
{
"epoch": 0.86,
"learning_rate": 0.0002,
"loss": 1.5606,
"step": 526
},
{
"epoch": 0.86,
"learning_rate": 0.0002,
"loss": 1.65,
"step": 528
},
{
"epoch": 0.86,
"learning_rate": 0.0002,
"loss": 1.6129,
"step": 530
},
{
"epoch": 0.87,
"learning_rate": 0.0002,
"loss": 1.6428,
"step": 532
},
{
"epoch": 0.87,
"learning_rate": 0.0002,
"loss": 1.749,
"step": 534
},
{
"epoch": 0.87,
"learning_rate": 0.0002,
"loss": 1.8281,
"step": 536
},
{
"epoch": 0.88,
"learning_rate": 0.0002,
"loss": 1.8625,
"step": 538
},
{
"epoch": 0.88,
"learning_rate": 0.0002,
"loss": 1.7948,
"step": 540
},
{
"epoch": 0.88,
"learning_rate": 0.0002,
"loss": 1.7721,
"step": 542
},
{
"epoch": 0.89,
"learning_rate": 0.0002,
"loss": 1.754,
"step": 544
},
{
"epoch": 0.89,
"learning_rate": 0.0002,
"loss": 1.6903,
"step": 546
},
{
"epoch": 0.89,
"learning_rate": 0.0002,
"loss": 1.6885,
"step": 548
},
{
"epoch": 0.9,
"learning_rate": 0.0002,
"loss": 1.2445,
"step": 550
},
{
"epoch": 0.9,
"learning_rate": 0.0002,
"loss": 1.5882,
"step": 552
},
{
"epoch": 0.9,
"learning_rate": 0.0002,
"loss": 1.5998,
"step": 554
},
{
"epoch": 0.91,
"learning_rate": 0.0002,
"loss": 1.5478,
"step": 556
},
{
"epoch": 0.91,
"learning_rate": 0.0002,
"loss": 1.5459,
"step": 558
},
{
"epoch": 0.91,
"learning_rate": 0.0002,
"loss": 1.4364,
"step": 560
},
{
"epoch": 0.92,
"learning_rate": 0.0002,
"loss": 1.6224,
"step": 562
},
{
"epoch": 0.92,
"learning_rate": 0.0002,
"loss": 1.6231,
"step": 564
},
{
"epoch": 0.92,
"learning_rate": 0.0002,
"loss": 1.7122,
"step": 566
},
{
"epoch": 0.93,
"learning_rate": 0.0002,
"loss": 1.5924,
"step": 568
},
{
"epoch": 0.93,
"learning_rate": 0.0002,
"loss": 1.5887,
"step": 570
},
{
"epoch": 0.93,
"learning_rate": 0.0002,
"loss": 1.5342,
"step": 572
},
{
"epoch": 0.93,
"learning_rate": 0.0002,
"loss": 1.5421,
"step": 574
},
{
"epoch": 0.94,
"learning_rate": 0.0002,
"loss": 1.4875,
"step": 576
},
{
"epoch": 0.94,
"learning_rate": 0.0002,
"loss": 1.7105,
"step": 578
},
{
"epoch": 0.94,
"learning_rate": 0.0002,
"loss": 1.7716,
"step": 580
},
{
"epoch": 0.95,
"learning_rate": 0.0002,
"loss": 1.6903,
"step": 582
},
{
"epoch": 0.95,
"learning_rate": 0.0002,
"loss": 1.7758,
"step": 584
},
{
"epoch": 0.95,
"learning_rate": 0.0002,
"loss": 1.7753,
"step": 586
},
{
"epoch": 0.96,
"learning_rate": 0.0002,
"loss": 1.8266,
"step": 588
},
{
"epoch": 0.96,
"learning_rate": 0.0002,
"loss": 1.819,
"step": 590
},
{
"epoch": 0.96,
"learning_rate": 0.0002,
"loss": 1.8032,
"step": 592
},
{
"epoch": 0.97,
"learning_rate": 0.0002,
"loss": 1.8289,
"step": 594
},
{
"epoch": 0.97,
"learning_rate": 0.0002,
"loss": 1.797,
"step": 596
},
{
"epoch": 0.97,
"learning_rate": 0.0002,
"loss": 1.708,
"step": 598
},
{
"epoch": 0.98,
"learning_rate": 0.0002,
"loss": 1.2649,
"step": 600
},
{
"epoch": 0.98,
"learning_rate": 0.0002,
"loss": 1.517,
"step": 602
},
{
"epoch": 0.98,
"learning_rate": 0.0002,
"loss": 1.5548,
"step": 604
},
{
"epoch": 0.99,
"learning_rate": 0.0002,
"loss": 1.5797,
"step": 606
},
{
"epoch": 0.99,
"learning_rate": 0.0002,
"loss": 1.7261,
"step": 608
},
{
"epoch": 0.99,
"learning_rate": 0.0002,
"loss": 1.6101,
"step": 610
},
{
"epoch": 1.0,
"learning_rate": 0.0002,
"loss": 1.9315,
"step": 612
}
],
"logging_steps": 2,
"max_steps": 613,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 500,
"total_flos": 2.371840324637491e+16,
"train_batch_size": 1,
"trial_name": null,
"trial_params": null
}