longt5_xl_gov_bp_10 / trainer_state.json
learn3r's picture
End of training
beb326e
{
"best_metric": 1.2562931776046753,
"best_model_checkpoint": "/exports/eddie/scratch/s1970716/models/summarization/longt5_xl_gov_bp_10/checkpoint-136",
"epoch": 4.985679917516325,
"eval_steps": 500,
"global_step": 680,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.01,
"learning_rate": 0.001,
"loss": 0.6069,
"step": 2
},
{
"epoch": 0.03,
"learning_rate": 0.001,
"loss": 0.613,
"step": 4
},
{
"epoch": 0.04,
"learning_rate": 0.001,
"loss": 0.614,
"step": 6
},
{
"epoch": 0.06,
"learning_rate": 0.001,
"loss": 0.6007,
"step": 8
},
{
"epoch": 0.07,
"learning_rate": 0.001,
"loss": 0.6327,
"step": 10
},
{
"epoch": 0.09,
"learning_rate": 0.001,
"loss": 0.6199,
"step": 12
},
{
"epoch": 0.1,
"learning_rate": 0.001,
"loss": 0.6412,
"step": 14
},
{
"epoch": 0.12,
"learning_rate": 0.001,
"loss": 0.6363,
"step": 16
},
{
"epoch": 0.13,
"learning_rate": 0.001,
"loss": 0.6423,
"step": 18
},
{
"epoch": 0.15,
"learning_rate": 0.001,
"loss": 0.617,
"step": 20
},
{
"epoch": 0.16,
"learning_rate": 0.001,
"loss": 0.651,
"step": 22
},
{
"epoch": 0.18,
"learning_rate": 0.001,
"loss": 0.6137,
"step": 24
},
{
"epoch": 0.19,
"learning_rate": 0.001,
"loss": 0.6255,
"step": 26
},
{
"epoch": 0.21,
"learning_rate": 0.001,
"loss": 0.6372,
"step": 28
},
{
"epoch": 0.22,
"learning_rate": 0.001,
"loss": 0.6233,
"step": 30
},
{
"epoch": 0.23,
"learning_rate": 0.001,
"loss": 0.6407,
"step": 32
},
{
"epoch": 0.25,
"learning_rate": 0.001,
"loss": 0.6175,
"step": 34
},
{
"epoch": 0.26,
"learning_rate": 0.001,
"loss": 0.6223,
"step": 36
},
{
"epoch": 0.28,
"learning_rate": 0.001,
"loss": 0.6108,
"step": 38
},
{
"epoch": 0.29,
"learning_rate": 0.001,
"loss": 0.6334,
"step": 40
},
{
"epoch": 0.31,
"learning_rate": 0.001,
"loss": 0.6492,
"step": 42
},
{
"epoch": 0.32,
"learning_rate": 0.001,
"loss": 0.649,
"step": 44
},
{
"epoch": 0.34,
"learning_rate": 0.001,
"loss": 0.626,
"step": 46
},
{
"epoch": 0.35,
"learning_rate": 0.001,
"loss": 0.5869,
"step": 48
},
{
"epoch": 0.37,
"learning_rate": 0.001,
"loss": 0.6138,
"step": 50
},
{
"epoch": 0.38,
"learning_rate": 0.001,
"loss": 0.6572,
"step": 52
},
{
"epoch": 0.4,
"learning_rate": 0.001,
"loss": 0.5962,
"step": 54
},
{
"epoch": 0.41,
"learning_rate": 0.001,
"loss": 0.6108,
"step": 56
},
{
"epoch": 0.43,
"learning_rate": 0.001,
"loss": 0.6002,
"step": 58
},
{
"epoch": 0.44,
"learning_rate": 0.001,
"loss": 0.6064,
"step": 60
},
{
"epoch": 0.45,
"learning_rate": 0.001,
"loss": 0.6107,
"step": 62
},
{
"epoch": 0.47,
"learning_rate": 0.001,
"loss": 0.5941,
"step": 64
},
{
"epoch": 0.48,
"learning_rate": 0.001,
"loss": 0.5938,
"step": 66
},
{
"epoch": 0.5,
"learning_rate": 0.001,
"loss": 0.5879,
"step": 68
},
{
"epoch": 0.51,
"learning_rate": 0.001,
"loss": 0.5902,
"step": 70
},
{
"epoch": 0.53,
"learning_rate": 0.001,
"loss": 0.5898,
"step": 72
},
{
"epoch": 0.54,
"learning_rate": 0.001,
"loss": 0.6088,
"step": 74
},
{
"epoch": 0.56,
"learning_rate": 0.001,
"loss": 0.6191,
"step": 76
},
{
"epoch": 0.57,
"learning_rate": 0.001,
"loss": 0.6172,
"step": 78
},
{
"epoch": 0.59,
"learning_rate": 0.001,
"loss": 0.5627,
"step": 80
},
{
"epoch": 0.6,
"learning_rate": 0.001,
"loss": 0.5927,
"step": 82
},
{
"epoch": 0.62,
"learning_rate": 0.001,
"loss": 0.5971,
"step": 84
},
{
"epoch": 0.63,
"learning_rate": 0.001,
"loss": 0.5761,
"step": 86
},
{
"epoch": 0.65,
"learning_rate": 0.001,
"loss": 0.5747,
"step": 88
},
{
"epoch": 0.66,
"learning_rate": 0.001,
"loss": 0.5944,
"step": 90
},
{
"epoch": 0.67,
"learning_rate": 0.001,
"loss": 0.5936,
"step": 92
},
{
"epoch": 0.69,
"learning_rate": 0.001,
"loss": 0.5924,
"step": 94
},
{
"epoch": 0.7,
"learning_rate": 0.001,
"loss": 0.5699,
"step": 96
},
{
"epoch": 0.72,
"learning_rate": 0.001,
"loss": 0.5706,
"step": 98
},
{
"epoch": 0.73,
"learning_rate": 0.001,
"loss": 0.5873,
"step": 100
},
{
"epoch": 0.75,
"learning_rate": 0.001,
"loss": 0.5875,
"step": 102
},
{
"epoch": 0.76,
"learning_rate": 0.001,
"loss": 0.6015,
"step": 104
},
{
"epoch": 0.78,
"learning_rate": 0.001,
"loss": 0.5662,
"step": 106
},
{
"epoch": 0.79,
"learning_rate": 0.001,
"loss": 0.5891,
"step": 108
},
{
"epoch": 0.81,
"learning_rate": 0.001,
"loss": 0.6821,
"step": 110
},
{
"epoch": 0.82,
"learning_rate": 0.001,
"loss": 0.6768,
"step": 112
},
{
"epoch": 0.84,
"learning_rate": 0.001,
"loss": 0.6164,
"step": 114
},
{
"epoch": 0.85,
"learning_rate": 0.001,
"loss": 0.633,
"step": 116
},
{
"epoch": 0.87,
"learning_rate": 0.001,
"loss": 0.5875,
"step": 118
},
{
"epoch": 0.88,
"learning_rate": 0.001,
"loss": 0.6182,
"step": 120
},
{
"epoch": 0.89,
"learning_rate": 0.001,
"loss": 0.6053,
"step": 122
},
{
"epoch": 0.91,
"learning_rate": 0.001,
"loss": 0.6169,
"step": 124
},
{
"epoch": 0.92,
"learning_rate": 0.001,
"loss": 0.584,
"step": 126
},
{
"epoch": 0.94,
"learning_rate": 0.001,
"loss": 0.5848,
"step": 128
},
{
"epoch": 0.95,
"learning_rate": 0.001,
"loss": 0.6082,
"step": 130
},
{
"epoch": 0.97,
"learning_rate": 0.001,
"loss": 0.5876,
"step": 132
},
{
"epoch": 0.98,
"learning_rate": 0.001,
"loss": 0.5913,
"step": 134
},
{
"epoch": 1.0,
"learning_rate": 0.001,
"loss": 0.5843,
"step": 136
},
{
"epoch": 1.0,
"eval_loss": 1.2562931776046753,
"eval_runtime": 355.3389,
"eval_samples_per_second": 2.735,
"eval_steps_per_second": 1.368,
"step": 136
},
{
"epoch": 1.01,
"learning_rate": 0.001,
"loss": 0.5001,
"step": 138
},
{
"epoch": 1.03,
"learning_rate": 0.001,
"loss": 0.4942,
"step": 140
},
{
"epoch": 1.04,
"learning_rate": 0.001,
"loss": 0.4475,
"step": 142
},
{
"epoch": 1.06,
"learning_rate": 0.001,
"loss": 0.449,
"step": 144
},
{
"epoch": 1.07,
"learning_rate": 0.001,
"loss": 0.4784,
"step": 146
},
{
"epoch": 1.09,
"learning_rate": 0.001,
"loss": 0.4611,
"step": 148
},
{
"epoch": 1.1,
"learning_rate": 0.001,
"loss": 0.4659,
"step": 150
},
{
"epoch": 1.11,
"learning_rate": 0.001,
"loss": 0.4549,
"step": 152
},
{
"epoch": 1.13,
"learning_rate": 0.001,
"loss": 0.4695,
"step": 154
},
{
"epoch": 1.14,
"learning_rate": 0.001,
"loss": 0.4762,
"step": 156
},
{
"epoch": 1.16,
"learning_rate": 0.001,
"loss": 0.4736,
"step": 158
},
{
"epoch": 1.17,
"learning_rate": 0.001,
"loss": 0.4566,
"step": 160
},
{
"epoch": 1.19,
"learning_rate": 0.001,
"loss": 0.4797,
"step": 162
},
{
"epoch": 1.2,
"learning_rate": 0.001,
"loss": 0.4876,
"step": 164
},
{
"epoch": 1.22,
"learning_rate": 0.001,
"loss": 0.4821,
"step": 166
},
{
"epoch": 1.23,
"learning_rate": 0.001,
"loss": 0.47,
"step": 168
},
{
"epoch": 1.25,
"learning_rate": 0.001,
"loss": 0.4777,
"step": 170
},
{
"epoch": 1.26,
"learning_rate": 0.001,
"loss": 0.4889,
"step": 172
},
{
"epoch": 1.28,
"learning_rate": 0.001,
"loss": 0.4722,
"step": 174
},
{
"epoch": 1.29,
"learning_rate": 0.001,
"loss": 0.4549,
"step": 176
},
{
"epoch": 1.31,
"learning_rate": 0.001,
"loss": 0.4673,
"step": 178
},
{
"epoch": 1.32,
"learning_rate": 0.001,
"loss": 0.4775,
"step": 180
},
{
"epoch": 1.33,
"learning_rate": 0.001,
"loss": 0.4822,
"step": 182
},
{
"epoch": 1.35,
"learning_rate": 0.001,
"loss": 0.4909,
"step": 184
},
{
"epoch": 1.36,
"learning_rate": 0.001,
"loss": 0.4719,
"step": 186
},
{
"epoch": 1.38,
"learning_rate": 0.001,
"loss": 0.475,
"step": 188
},
{
"epoch": 1.39,
"learning_rate": 0.001,
"loss": 0.4837,
"step": 190
},
{
"epoch": 1.41,
"learning_rate": 0.001,
"loss": 0.5012,
"step": 192
},
{
"epoch": 1.42,
"learning_rate": 0.001,
"loss": 0.4644,
"step": 194
},
{
"epoch": 1.44,
"learning_rate": 0.001,
"loss": 0.4683,
"step": 196
},
{
"epoch": 1.45,
"learning_rate": 0.001,
"loss": 0.4517,
"step": 198
},
{
"epoch": 1.47,
"learning_rate": 0.001,
"loss": 0.4835,
"step": 200
},
{
"epoch": 1.48,
"learning_rate": 0.001,
"loss": 0.4782,
"step": 202
},
{
"epoch": 1.5,
"learning_rate": 0.001,
"loss": 0.4722,
"step": 204
},
{
"epoch": 1.51,
"learning_rate": 0.001,
"loss": 0.472,
"step": 206
},
{
"epoch": 1.53,
"learning_rate": 0.001,
"loss": 0.555,
"step": 208
},
{
"epoch": 1.54,
"learning_rate": 0.001,
"loss": 0.447,
"step": 210
},
{
"epoch": 1.55,
"learning_rate": 0.001,
"loss": 0.4509,
"step": 212
},
{
"epoch": 1.57,
"learning_rate": 0.001,
"loss": 0.4786,
"step": 214
},
{
"epoch": 1.58,
"learning_rate": 0.001,
"loss": 0.4842,
"step": 216
},
{
"epoch": 1.6,
"learning_rate": 0.001,
"loss": 0.4827,
"step": 218
},
{
"epoch": 1.61,
"learning_rate": 0.001,
"loss": 0.5015,
"step": 220
},
{
"epoch": 1.63,
"learning_rate": 0.001,
"loss": 0.4921,
"step": 222
},
{
"epoch": 1.64,
"learning_rate": 0.001,
"loss": 0.4739,
"step": 224
},
{
"epoch": 1.66,
"learning_rate": 0.001,
"loss": 0.4903,
"step": 226
},
{
"epoch": 1.67,
"learning_rate": 0.001,
"loss": 0.5007,
"step": 228
},
{
"epoch": 1.69,
"learning_rate": 0.001,
"loss": 0.4855,
"step": 230
},
{
"epoch": 1.7,
"learning_rate": 0.001,
"loss": 0.4819,
"step": 232
},
{
"epoch": 1.72,
"learning_rate": 0.001,
"loss": 0.483,
"step": 234
},
{
"epoch": 1.73,
"learning_rate": 0.001,
"loss": 0.4827,
"step": 236
},
{
"epoch": 1.74,
"learning_rate": 0.001,
"loss": 0.4774,
"step": 238
},
{
"epoch": 1.76,
"learning_rate": 0.001,
"loss": 0.4816,
"step": 240
},
{
"epoch": 1.77,
"learning_rate": 0.001,
"loss": 0.4982,
"step": 242
},
{
"epoch": 1.79,
"learning_rate": 0.001,
"loss": 0.4914,
"step": 244
},
{
"epoch": 1.8,
"learning_rate": 0.001,
"loss": 0.4855,
"step": 246
},
{
"epoch": 1.82,
"learning_rate": 0.001,
"loss": 0.5041,
"step": 248
},
{
"epoch": 1.83,
"learning_rate": 0.001,
"loss": 0.4721,
"step": 250
},
{
"epoch": 1.85,
"learning_rate": 0.001,
"loss": 0.4708,
"step": 252
},
{
"epoch": 1.86,
"learning_rate": 0.001,
"loss": 0.4737,
"step": 254
},
{
"epoch": 1.88,
"learning_rate": 0.001,
"loss": 0.4811,
"step": 256
},
{
"epoch": 1.89,
"learning_rate": 0.001,
"loss": 0.4778,
"step": 258
},
{
"epoch": 1.91,
"learning_rate": 0.001,
"loss": 0.4884,
"step": 260
},
{
"epoch": 1.92,
"learning_rate": 0.001,
"loss": 0.4693,
"step": 262
},
{
"epoch": 1.94,
"learning_rate": 0.001,
"loss": 0.4558,
"step": 264
},
{
"epoch": 1.95,
"learning_rate": 0.001,
"loss": 0.4806,
"step": 266
},
{
"epoch": 1.96,
"learning_rate": 0.001,
"loss": 0.4643,
"step": 268
},
{
"epoch": 1.98,
"learning_rate": 0.001,
"loss": 0.4829,
"step": 270
},
{
"epoch": 1.99,
"learning_rate": 0.001,
"loss": 0.4908,
"step": 272
},
{
"epoch": 1.99,
"eval_loss": 1.2934502363204956,
"eval_runtime": 355.588,
"eval_samples_per_second": 2.734,
"eval_steps_per_second": 1.367,
"step": 272
},
{
"epoch": 2.01,
"learning_rate": 0.001,
"loss": 0.4513,
"step": 274
},
{
"epoch": 2.02,
"learning_rate": 0.001,
"loss": 0.3608,
"step": 276
},
{
"epoch": 2.04,
"learning_rate": 0.001,
"loss": 0.3675,
"step": 278
},
{
"epoch": 2.05,
"learning_rate": 0.001,
"loss": 0.3811,
"step": 280
},
{
"epoch": 2.07,
"learning_rate": 0.001,
"loss": 0.3715,
"step": 282
},
{
"epoch": 2.08,
"learning_rate": 0.001,
"loss": 0.3688,
"step": 284
},
{
"epoch": 2.1,
"learning_rate": 0.001,
"loss": 0.3657,
"step": 286
},
{
"epoch": 2.11,
"learning_rate": 0.001,
"loss": 0.3594,
"step": 288
},
{
"epoch": 2.13,
"learning_rate": 0.001,
"loss": 0.3624,
"step": 290
},
{
"epoch": 2.14,
"learning_rate": 0.001,
"loss": 0.3828,
"step": 292
},
{
"epoch": 2.16,
"learning_rate": 0.001,
"loss": 0.3982,
"step": 294
},
{
"epoch": 2.17,
"learning_rate": 0.001,
"loss": 0.381,
"step": 296
},
{
"epoch": 2.18,
"learning_rate": 0.001,
"loss": 0.3666,
"step": 298
},
{
"epoch": 2.2,
"learning_rate": 0.001,
"loss": 0.3733,
"step": 300
},
{
"epoch": 2.21,
"learning_rate": 0.001,
"loss": 0.368,
"step": 302
},
{
"epoch": 2.23,
"learning_rate": 0.001,
"loss": 0.3587,
"step": 304
},
{
"epoch": 2.24,
"learning_rate": 0.001,
"loss": 0.3651,
"step": 306
},
{
"epoch": 2.26,
"learning_rate": 0.001,
"loss": 0.3632,
"step": 308
},
{
"epoch": 2.27,
"learning_rate": 0.001,
"loss": 0.3732,
"step": 310
},
{
"epoch": 2.29,
"learning_rate": 0.001,
"loss": 0.3713,
"step": 312
},
{
"epoch": 2.3,
"learning_rate": 0.001,
"loss": 0.3805,
"step": 314
},
{
"epoch": 2.32,
"learning_rate": 0.001,
"loss": 0.3889,
"step": 316
},
{
"epoch": 2.33,
"learning_rate": 0.001,
"loss": 0.3933,
"step": 318
},
{
"epoch": 2.35,
"learning_rate": 0.001,
"loss": 0.4042,
"step": 320
},
{
"epoch": 2.36,
"learning_rate": 0.001,
"loss": 0.3946,
"step": 322
},
{
"epoch": 2.38,
"learning_rate": 0.001,
"loss": 0.3913,
"step": 324
},
{
"epoch": 2.39,
"learning_rate": 0.001,
"loss": 0.3951,
"step": 326
},
{
"epoch": 2.4,
"learning_rate": 0.001,
"loss": 0.3816,
"step": 328
},
{
"epoch": 2.42,
"learning_rate": 0.001,
"loss": 0.3758,
"step": 330
},
{
"epoch": 2.43,
"learning_rate": 0.001,
"loss": 0.3881,
"step": 332
},
{
"epoch": 2.45,
"learning_rate": 0.001,
"loss": 0.3866,
"step": 334
},
{
"epoch": 2.46,
"learning_rate": 0.001,
"loss": 0.3711,
"step": 336
},
{
"epoch": 2.48,
"learning_rate": 0.001,
"loss": 0.3865,
"step": 338
},
{
"epoch": 2.49,
"learning_rate": 0.001,
"loss": 0.3918,
"step": 340
},
{
"epoch": 2.51,
"learning_rate": 0.001,
"loss": 0.3658,
"step": 342
},
{
"epoch": 2.52,
"learning_rate": 0.001,
"loss": 0.3869,
"step": 344
},
{
"epoch": 2.54,
"learning_rate": 0.001,
"loss": 0.3782,
"step": 346
},
{
"epoch": 2.55,
"learning_rate": 0.001,
"loss": 0.3763,
"step": 348
},
{
"epoch": 2.57,
"learning_rate": 0.001,
"loss": 0.3687,
"step": 350
},
{
"epoch": 2.58,
"learning_rate": 0.001,
"loss": 0.3794,
"step": 352
},
{
"epoch": 2.6,
"learning_rate": 0.001,
"loss": 0.3879,
"step": 354
},
{
"epoch": 2.61,
"learning_rate": 0.001,
"loss": 0.4182,
"step": 356
},
{
"epoch": 2.62,
"learning_rate": 0.001,
"loss": 0.398,
"step": 358
},
{
"epoch": 2.64,
"learning_rate": 0.001,
"loss": 0.3924,
"step": 360
},
{
"epoch": 2.65,
"learning_rate": 0.001,
"loss": 0.3965,
"step": 362
},
{
"epoch": 2.67,
"learning_rate": 0.001,
"loss": 0.3856,
"step": 364
},
{
"epoch": 2.68,
"learning_rate": 0.001,
"loss": 0.3968,
"step": 366
},
{
"epoch": 2.7,
"learning_rate": 0.001,
"loss": 0.3848,
"step": 368
},
{
"epoch": 2.71,
"learning_rate": 0.001,
"loss": 0.3861,
"step": 370
},
{
"epoch": 2.73,
"learning_rate": 0.001,
"loss": 0.3864,
"step": 372
},
{
"epoch": 2.74,
"learning_rate": 0.001,
"loss": 0.3988,
"step": 374
},
{
"epoch": 2.76,
"learning_rate": 0.001,
"loss": 0.3938,
"step": 376
},
{
"epoch": 2.77,
"learning_rate": 0.001,
"loss": 0.3922,
"step": 378
},
{
"epoch": 2.79,
"learning_rate": 0.001,
"loss": 0.3869,
"step": 380
},
{
"epoch": 2.8,
"learning_rate": 0.001,
"loss": 0.3879,
"step": 382
},
{
"epoch": 2.82,
"learning_rate": 0.001,
"loss": 0.398,
"step": 384
},
{
"epoch": 2.83,
"learning_rate": 0.001,
"loss": 0.3988,
"step": 386
},
{
"epoch": 2.84,
"learning_rate": 0.001,
"loss": 0.3928,
"step": 388
},
{
"epoch": 2.86,
"learning_rate": 0.001,
"loss": 0.4018,
"step": 390
},
{
"epoch": 2.87,
"learning_rate": 0.001,
"loss": 0.4079,
"step": 392
},
{
"epoch": 2.89,
"learning_rate": 0.001,
"loss": 0.3965,
"step": 394
},
{
"epoch": 2.9,
"learning_rate": 0.001,
"loss": 0.3908,
"step": 396
},
{
"epoch": 2.92,
"learning_rate": 0.001,
"loss": 0.4095,
"step": 398
},
{
"epoch": 2.93,
"learning_rate": 0.001,
"loss": 0.3877,
"step": 400
},
{
"epoch": 2.95,
"learning_rate": 0.001,
"loss": 0.4033,
"step": 402
},
{
"epoch": 2.96,
"learning_rate": 0.001,
"loss": 0.3889,
"step": 404
},
{
"epoch": 2.98,
"learning_rate": 0.001,
"loss": 0.3948,
"step": 406
},
{
"epoch": 2.99,
"learning_rate": 0.001,
"loss": 0.4059,
"step": 408
},
{
"epoch": 3.0,
"eval_loss": 1.4195482730865479,
"eval_runtime": 355.2346,
"eval_samples_per_second": 2.736,
"eval_steps_per_second": 1.368,
"step": 409
},
{
"epoch": 3.01,
"learning_rate": 0.001,
"loss": 0.3745,
"step": 410
},
{
"epoch": 3.02,
"learning_rate": 0.001,
"loss": 0.3099,
"step": 412
},
{
"epoch": 3.04,
"learning_rate": 0.001,
"loss": 0.3068,
"step": 414
},
{
"epoch": 3.05,
"learning_rate": 0.001,
"loss": 0.2907,
"step": 416
},
{
"epoch": 3.06,
"learning_rate": 0.001,
"loss": 0.2966,
"step": 418
},
{
"epoch": 3.08,
"learning_rate": 0.001,
"loss": 0.2964,
"step": 420
},
{
"epoch": 3.09,
"learning_rate": 0.001,
"loss": 0.2928,
"step": 422
},
{
"epoch": 3.11,
"learning_rate": 0.001,
"loss": 0.3016,
"step": 424
},
{
"epoch": 3.12,
"learning_rate": 0.001,
"loss": 0.318,
"step": 426
},
{
"epoch": 3.14,
"learning_rate": 0.001,
"loss": 0.3017,
"step": 428
},
{
"epoch": 3.15,
"learning_rate": 0.001,
"loss": 0.294,
"step": 430
},
{
"epoch": 3.17,
"learning_rate": 0.001,
"loss": 0.3041,
"step": 432
},
{
"epoch": 3.18,
"learning_rate": 0.001,
"loss": 0.3071,
"step": 434
},
{
"epoch": 3.2,
"learning_rate": 0.001,
"loss": 0.3075,
"step": 436
},
{
"epoch": 3.21,
"learning_rate": 0.001,
"loss": 0.295,
"step": 438
},
{
"epoch": 3.23,
"learning_rate": 0.001,
"loss": 0.3034,
"step": 440
},
{
"epoch": 3.24,
"learning_rate": 0.001,
"loss": 0.3084,
"step": 442
},
{
"epoch": 3.26,
"learning_rate": 0.001,
"loss": 0.2999,
"step": 444
},
{
"epoch": 3.27,
"learning_rate": 0.001,
"loss": 0.2899,
"step": 446
},
{
"epoch": 3.28,
"learning_rate": 0.001,
"loss": 0.3182,
"step": 448
},
{
"epoch": 3.3,
"learning_rate": 0.001,
"loss": 0.3199,
"step": 450
},
{
"epoch": 3.31,
"learning_rate": 0.001,
"loss": 0.3141,
"step": 452
},
{
"epoch": 3.33,
"learning_rate": 0.001,
"loss": 0.3125,
"step": 454
},
{
"epoch": 3.34,
"learning_rate": 0.001,
"loss": 0.313,
"step": 456
},
{
"epoch": 3.36,
"learning_rate": 0.001,
"loss": 0.324,
"step": 458
},
{
"epoch": 3.37,
"learning_rate": 0.001,
"loss": 0.3165,
"step": 460
},
{
"epoch": 3.39,
"learning_rate": 0.001,
"loss": 0.3156,
"step": 462
},
{
"epoch": 3.4,
"learning_rate": 0.001,
"loss": 0.307,
"step": 464
},
{
"epoch": 3.42,
"learning_rate": 0.001,
"loss": 0.3142,
"step": 466
},
{
"epoch": 3.43,
"learning_rate": 0.001,
"loss": 0.3169,
"step": 468
},
{
"epoch": 3.45,
"learning_rate": 0.001,
"loss": 0.3071,
"step": 470
},
{
"epoch": 3.46,
"learning_rate": 0.001,
"loss": 0.3142,
"step": 472
},
{
"epoch": 3.48,
"learning_rate": 0.001,
"loss": 0.3098,
"step": 474
},
{
"epoch": 3.49,
"learning_rate": 0.001,
"loss": 0.3238,
"step": 476
},
{
"epoch": 3.5,
"learning_rate": 0.001,
"loss": 0.3138,
"step": 478
},
{
"epoch": 3.52,
"learning_rate": 0.001,
"loss": 0.3229,
"step": 480
},
{
"epoch": 3.53,
"learning_rate": 0.001,
"loss": 0.3118,
"step": 482
},
{
"epoch": 3.55,
"learning_rate": 0.001,
"loss": 0.3129,
"step": 484
},
{
"epoch": 3.56,
"learning_rate": 0.001,
"loss": 0.3055,
"step": 486
},
{
"epoch": 3.58,
"learning_rate": 0.001,
"loss": 0.3277,
"step": 488
},
{
"epoch": 3.59,
"learning_rate": 0.001,
"loss": 0.326,
"step": 490
},
{
"epoch": 3.61,
"learning_rate": 0.001,
"loss": 0.3204,
"step": 492
},
{
"epoch": 3.62,
"learning_rate": 0.001,
"loss": 0.3211,
"step": 494
},
{
"epoch": 3.64,
"learning_rate": 0.001,
"loss": 0.3275,
"step": 496
},
{
"epoch": 3.65,
"learning_rate": 0.001,
"loss": 0.3249,
"step": 498
},
{
"epoch": 3.67,
"learning_rate": 0.001,
"loss": 0.3102,
"step": 500
},
{
"epoch": 3.68,
"learning_rate": 0.001,
"loss": 0.3097,
"step": 502
},
{
"epoch": 3.7,
"learning_rate": 0.001,
"loss": 0.3199,
"step": 504
},
{
"epoch": 3.71,
"learning_rate": 0.001,
"loss": 0.3166,
"step": 506
},
{
"epoch": 3.72,
"learning_rate": 0.001,
"loss": 0.3204,
"step": 508
},
{
"epoch": 3.74,
"learning_rate": 0.001,
"loss": 0.3164,
"step": 510
},
{
"epoch": 3.75,
"learning_rate": 0.001,
"loss": 0.3192,
"step": 512
},
{
"epoch": 3.77,
"learning_rate": 0.001,
"loss": 0.3369,
"step": 514
},
{
"epoch": 3.78,
"learning_rate": 0.001,
"loss": 0.3328,
"step": 516
},
{
"epoch": 3.8,
"learning_rate": 0.001,
"loss": 0.3292,
"step": 518
},
{
"epoch": 3.81,
"learning_rate": 0.001,
"loss": 0.3202,
"step": 520
},
{
"epoch": 3.83,
"learning_rate": 0.001,
"loss": 0.3311,
"step": 522
},
{
"epoch": 3.84,
"learning_rate": 0.001,
"loss": 0.3272,
"step": 524
},
{
"epoch": 3.86,
"learning_rate": 0.001,
"loss": 0.3189,
"step": 526
},
{
"epoch": 3.87,
"learning_rate": 0.001,
"loss": 0.3393,
"step": 528
},
{
"epoch": 3.89,
"learning_rate": 0.001,
"loss": 0.3376,
"step": 530
},
{
"epoch": 3.9,
"learning_rate": 0.001,
"loss": 0.34,
"step": 532
},
{
"epoch": 3.92,
"learning_rate": 0.001,
"loss": 0.3187,
"step": 534
},
{
"epoch": 3.93,
"learning_rate": 0.001,
"loss": 0.3199,
"step": 536
},
{
"epoch": 3.94,
"learning_rate": 0.001,
"loss": 0.3512,
"step": 538
},
{
"epoch": 3.96,
"learning_rate": 0.001,
"loss": 0.3,
"step": 540
},
{
"epoch": 3.97,
"learning_rate": 0.001,
"loss": 0.3265,
"step": 542
},
{
"epoch": 3.99,
"learning_rate": 0.001,
"loss": 0.3207,
"step": 544
},
{
"epoch": 4.0,
"eval_loss": 1.5143067836761475,
"eval_runtime": 355.3551,
"eval_samples_per_second": 2.735,
"eval_steps_per_second": 1.368,
"step": 545
},
{
"epoch": 4.0,
"learning_rate": 0.001,
"loss": 0.316,
"step": 546
},
{
"epoch": 4.02,
"learning_rate": 0.001,
"loss": 0.2397,
"step": 548
},
{
"epoch": 4.03,
"learning_rate": 0.001,
"loss": 0.2345,
"step": 550
},
{
"epoch": 4.05,
"learning_rate": 0.001,
"loss": 0.2247,
"step": 552
},
{
"epoch": 4.06,
"learning_rate": 0.001,
"loss": 0.2524,
"step": 554
},
{
"epoch": 4.08,
"learning_rate": 0.001,
"loss": 0.245,
"step": 556
},
{
"epoch": 4.09,
"learning_rate": 0.001,
"loss": 0.2431,
"step": 558
},
{
"epoch": 4.11,
"learning_rate": 0.001,
"loss": 0.2476,
"step": 560
},
{
"epoch": 4.12,
"learning_rate": 0.001,
"loss": 0.254,
"step": 562
},
{
"epoch": 4.14,
"learning_rate": 0.001,
"loss": 0.2513,
"step": 564
},
{
"epoch": 4.15,
"learning_rate": 0.001,
"loss": 0.261,
"step": 566
},
{
"epoch": 4.16,
"learning_rate": 0.001,
"loss": 0.2585,
"step": 568
},
{
"epoch": 4.18,
"learning_rate": 0.001,
"loss": 0.2496,
"step": 570
},
{
"epoch": 4.19,
"learning_rate": 0.001,
"loss": 0.2476,
"step": 572
},
{
"epoch": 4.21,
"learning_rate": 0.001,
"loss": 0.2437,
"step": 574
},
{
"epoch": 4.22,
"learning_rate": 0.001,
"loss": 0.2461,
"step": 576
},
{
"epoch": 4.24,
"learning_rate": 0.001,
"loss": 0.2646,
"step": 578
},
{
"epoch": 4.25,
"learning_rate": 0.001,
"loss": 0.2499,
"step": 580
},
{
"epoch": 4.27,
"learning_rate": 0.001,
"loss": 0.2456,
"step": 582
},
{
"epoch": 4.28,
"learning_rate": 0.001,
"loss": 0.2516,
"step": 584
},
{
"epoch": 4.3,
"learning_rate": 0.001,
"loss": 0.2581,
"step": 586
},
{
"epoch": 4.31,
"learning_rate": 0.001,
"loss": 0.267,
"step": 588
},
{
"epoch": 4.33,
"learning_rate": 0.001,
"loss": 0.2524,
"step": 590
},
{
"epoch": 4.34,
"learning_rate": 0.001,
"loss": 0.262,
"step": 592
},
{
"epoch": 4.36,
"learning_rate": 0.001,
"loss": 0.2643,
"step": 594
},
{
"epoch": 4.37,
"learning_rate": 0.001,
"loss": 0.2565,
"step": 596
},
{
"epoch": 4.38,
"learning_rate": 0.001,
"loss": 0.2595,
"step": 598
},
{
"epoch": 4.4,
"learning_rate": 0.001,
"loss": 0.2552,
"step": 600
},
{
"epoch": 4.41,
"learning_rate": 0.001,
"loss": 0.2515,
"step": 602
},
{
"epoch": 4.43,
"learning_rate": 0.001,
"loss": 0.2551,
"step": 604
},
{
"epoch": 4.44,
"learning_rate": 0.001,
"loss": 0.2606,
"step": 606
},
{
"epoch": 4.46,
"learning_rate": 0.001,
"loss": 0.252,
"step": 608
},
{
"epoch": 4.47,
"learning_rate": 0.001,
"loss": 0.2617,
"step": 610
},
{
"epoch": 4.49,
"learning_rate": 0.001,
"loss": 0.2667,
"step": 612
},
{
"epoch": 4.5,
"learning_rate": 0.001,
"loss": 0.2565,
"step": 614
},
{
"epoch": 4.52,
"learning_rate": 0.001,
"loss": 0.2662,
"step": 616
},
{
"epoch": 4.53,
"learning_rate": 0.001,
"loss": 0.2763,
"step": 618
},
{
"epoch": 4.55,
"learning_rate": 0.001,
"loss": 0.2783,
"step": 620
},
{
"epoch": 4.56,
"learning_rate": 0.001,
"loss": 0.2685,
"step": 622
},
{
"epoch": 4.58,
"learning_rate": 0.001,
"loss": 0.2655,
"step": 624
},
{
"epoch": 4.59,
"learning_rate": 0.001,
"loss": 0.2776,
"step": 626
},
{
"epoch": 4.6,
"learning_rate": 0.001,
"loss": 0.265,
"step": 628
},
{
"epoch": 4.62,
"learning_rate": 0.001,
"loss": 0.2623,
"step": 630
},
{
"epoch": 4.63,
"learning_rate": 0.001,
"loss": 0.2611,
"step": 632
},
{
"epoch": 4.65,
"learning_rate": 0.001,
"loss": 0.2758,
"step": 634
},
{
"epoch": 4.66,
"learning_rate": 0.001,
"loss": 0.2705,
"step": 636
},
{
"epoch": 4.68,
"learning_rate": 0.001,
"loss": 0.2635,
"step": 638
},
{
"epoch": 4.69,
"learning_rate": 0.001,
"loss": 0.2639,
"step": 640
},
{
"epoch": 4.71,
"learning_rate": 0.001,
"loss": 0.2708,
"step": 642
},
{
"epoch": 4.72,
"learning_rate": 0.001,
"loss": 0.2808,
"step": 644
},
{
"epoch": 4.74,
"learning_rate": 0.001,
"loss": 0.2867,
"step": 646
},
{
"epoch": 4.75,
"learning_rate": 0.001,
"loss": 0.271,
"step": 648
},
{
"epoch": 4.77,
"learning_rate": 0.001,
"loss": 0.2677,
"step": 650
},
{
"epoch": 4.78,
"learning_rate": 0.001,
"loss": 0.2638,
"step": 652
},
{
"epoch": 4.8,
"learning_rate": 0.001,
"loss": 0.271,
"step": 654
},
{
"epoch": 4.81,
"learning_rate": 0.001,
"loss": 0.2652,
"step": 656
},
{
"epoch": 4.82,
"learning_rate": 0.001,
"loss": 0.2716,
"step": 658
},
{
"epoch": 4.84,
"learning_rate": 0.001,
"loss": 0.2746,
"step": 660
},
{
"epoch": 4.85,
"learning_rate": 0.001,
"loss": 0.2705,
"step": 662
},
{
"epoch": 4.87,
"learning_rate": 0.001,
"loss": 0.2683,
"step": 664
},
{
"epoch": 4.88,
"learning_rate": 0.001,
"loss": 0.2623,
"step": 666
},
{
"epoch": 4.9,
"learning_rate": 0.001,
"loss": 0.2742,
"step": 668
},
{
"epoch": 4.91,
"learning_rate": 0.001,
"loss": 0.2762,
"step": 670
},
{
"epoch": 4.93,
"learning_rate": 0.001,
"loss": 0.2734,
"step": 672
},
{
"epoch": 4.94,
"learning_rate": 0.001,
"loss": 0.2775,
"step": 674
},
{
"epoch": 4.96,
"learning_rate": 0.001,
"loss": 0.2686,
"step": 676
},
{
"epoch": 4.97,
"learning_rate": 0.001,
"loss": 0.2768,
"step": 678
},
{
"epoch": 4.99,
"learning_rate": 0.001,
"loss": 0.2705,
"step": 680
},
{
"epoch": 4.99,
"eval_loss": 1.550490140914917,
"eval_runtime": 355.5311,
"eval_samples_per_second": 2.734,
"eval_steps_per_second": 1.367,
"step": 680
},
{
"epoch": 4.99,
"step": 680,
"total_flos": 5.939593565767631e+18,
"train_loss": 0.41042166549493286,
"train_runtime": 118164.981,
"train_samples_per_second": 0.739,
"train_steps_per_second": 0.006
}
],
"logging_steps": 2,
"max_steps": 680,
"num_train_epochs": 5,
"save_steps": 500,
"total_flos": 5.939593565767631e+18,
"trial_name": null,
"trial_params": null
}