pszemraj's picture
Model save
d46422e
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 2.9991575400168493,
"eval_steps": 100,
"global_step": 1335,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.01,
"learning_rate": 2.2388059701492536e-05,
"loss": 10.8621,
"step": 3
},
{
"epoch": 0.01,
"learning_rate": 4.477611940298507e-05,
"loss": 10.767,
"step": 6
},
{
"epoch": 0.02,
"learning_rate": 6.716417910447761e-05,
"loss": 10.5723,
"step": 9
},
{
"epoch": 0.03,
"learning_rate": 8.955223880597014e-05,
"loss": 10.4057,
"step": 12
},
{
"epoch": 0.03,
"learning_rate": 0.00011194029850746269,
"loss": 10.2623,
"step": 15
},
{
"epoch": 0.04,
"learning_rate": 0.00013432835820895522,
"loss": 10.0998,
"step": 18
},
{
"epoch": 0.05,
"learning_rate": 0.00015671641791044778,
"loss": 9.9577,
"step": 21
},
{
"epoch": 0.05,
"learning_rate": 0.00017910447761194028,
"loss": 9.8105,
"step": 24
},
{
"epoch": 0.06,
"learning_rate": 0.00020149253731343284,
"loss": 9.5994,
"step": 27
},
{
"epoch": 0.07,
"learning_rate": 0.00022388059701492538,
"loss": 9.4189,
"step": 30
},
{
"epoch": 0.07,
"learning_rate": 0.0002462686567164179,
"loss": 9.1967,
"step": 33
},
{
"epoch": 0.08,
"learning_rate": 0.00026865671641791044,
"loss": 8.9757,
"step": 36
},
{
"epoch": 0.09,
"learning_rate": 0.00029104477611940297,
"loss": 8.7393,
"step": 39
},
{
"epoch": 0.09,
"learning_rate": 0.00031343283582089556,
"loss": 8.4736,
"step": 42
},
{
"epoch": 0.1,
"learning_rate": 0.0003358208955223881,
"loss": 8.3719,
"step": 45
},
{
"epoch": 0.11,
"learning_rate": 0.00035820895522388057,
"loss": 8.1845,
"step": 48
},
{
"epoch": 0.11,
"learning_rate": 0.00038059701492537315,
"loss": 7.9457,
"step": 51
},
{
"epoch": 0.12,
"learning_rate": 0.0004029850746268657,
"loss": 7.7169,
"step": 54
},
{
"epoch": 0.13,
"learning_rate": 0.0004253731343283582,
"loss": 7.4515,
"step": 57
},
{
"epoch": 0.13,
"learning_rate": 0.00044776119402985075,
"loss": 7.3122,
"step": 60
},
{
"epoch": 0.14,
"learning_rate": 0.00047014925373134334,
"loss": 7.0979,
"step": 63
},
{
"epoch": 0.15,
"learning_rate": 0.0004925373134328358,
"loss": 7.0553,
"step": 66
},
{
"epoch": 0.16,
"learning_rate": 0.0004927003381249152,
"loss": 6.9408,
"step": 69
},
{
"epoch": 0.16,
"learning_rate": 0.00048232653761625933,
"loss": 6.7523,
"step": 72
},
{
"epoch": 0.17,
"learning_rate": 0.00047258156262526085,
"loss": 6.5754,
"step": 75
},
{
"epoch": 0.18,
"learning_rate": 0.0004634043479981492,
"loss": 6.2952,
"step": 78
},
{
"epoch": 0.18,
"learning_rate": 0.00045474182065958054,
"loss": 6.3841,
"step": 81
},
{
"epoch": 0.19,
"learning_rate": 0.00044654760317883456,
"loss": 6.3261,
"step": 84
},
{
"epoch": 0.2,
"learning_rate": 0.0004387809654396872,
"loss": 6.2896,
"step": 87
},
{
"epoch": 0.2,
"learning_rate": 0.0004314059701848262,
"loss": 6.3229,
"step": 90
},
{
"epoch": 0.21,
"learning_rate": 0.0004243907714379761,
"loss": 6.0904,
"step": 93
},
{
"epoch": 0.22,
"learning_rate": 0.00041770703449507126,
"loss": 6.0741,
"step": 96
},
{
"epoch": 0.22,
"learning_rate": 0.00041132945334843116,
"loss": 6.077,
"step": 99
},
{
"epoch": 0.22,
"eval_accuracy": 0.24181827063996092,
"eval_loss": 5.63174295425415,
"eval_runtime": 15.0735,
"eval_samples_per_second": 33.171,
"eval_steps_per_second": 16.585,
"step": 100
},
{
"epoch": 0.23,
"learning_rate": 0.00040523534677334083,
"loss": 6.0036,
"step": 102
},
{
"epoch": 0.24,
"learning_rate": 0.0003994043183589901,
"loss": 5.9912,
"step": 105
},
{
"epoch": 0.24,
"learning_rate": 0.000393817968854384,
"loss": 5.9011,
"step": 108
},
{
"epoch": 0.25,
"learning_rate": 0.00038845965157388086,
"loss": 5.944,
"step": 111
},
{
"epoch": 0.26,
"learning_rate": 0.00038331426344633137,
"loss": 5.6939,
"step": 114
},
{
"epoch": 0.26,
"learning_rate": 0.00037836806572753097,
"loss": 5.8592,
"step": 117
},
{
"epoch": 0.27,
"learning_rate": 0.0003736085295243316,
"loss": 5.6326,
"step": 120
},
{
"epoch": 0.28,
"learning_rate": 0.0003690242021719143,
"loss": 5.6688,
"step": 123
},
{
"epoch": 0.28,
"learning_rate": 0.0003646045912169894,
"loss": 5.668,
"step": 126
},
{
"epoch": 0.29,
"learning_rate": 0.0003603400633295028,
"loss": 5.7459,
"step": 129
},
{
"epoch": 0.3,
"learning_rate": 0.00035622175592450755,
"loss": 5.7216,
"step": 132
},
{
"epoch": 0.3,
"learning_rate": 0.00035224149964771913,
"loss": 5.498,
"step": 135
},
{
"epoch": 0.31,
"learning_rate": 0.0003483917501810324,
"loss": 5.4487,
"step": 138
},
{
"epoch": 0.32,
"learning_rate": 0.000344665528071977,
"loss": 5.764,
"step": 141
},
{
"epoch": 0.32,
"learning_rate": 0.0003410563654946854,
"loss": 5.5443,
"step": 144
},
{
"epoch": 0.33,
"learning_rate": 0.0003375582590180435,
"loss": 5.4449,
"step": 147
},
{
"epoch": 0.34,
"learning_rate": 0.0003341656275960571,
"loss": 5.5276,
"step": 150
},
{
"epoch": 0.34,
"learning_rate": 0.0003308732751114942,
"loss": 5.6636,
"step": 153
},
{
"epoch": 0.35,
"learning_rate": 0.000327676356900822,
"loss": 5.4768,
"step": 156
},
{
"epoch": 0.36,
"learning_rate": 0.00032457034976979266,
"loss": 5.4652,
"step": 159
},
{
"epoch": 0.36,
"learning_rate": 0.00032155102507750626,
"loss": 5.3164,
"step": 162
},
{
"epoch": 0.37,
"learning_rate": 0.00031861442452461495,
"loss": 5.4037,
"step": 165
},
{
"epoch": 0.38,
"learning_rate": 0.0003157568383303535,
"loss": 5.4498,
"step": 168
},
{
"epoch": 0.38,
"learning_rate": 0.00031297478552475916,
"loss": 5.324,
"step": 171
},
{
"epoch": 0.39,
"learning_rate": 0.00031026499611798295,
"loss": 5.315,
"step": 174
},
{
"epoch": 0.4,
"learning_rate": 0.0003076243949389936,
"loss": 5.3265,
"step": 177
},
{
"epoch": 0.4,
"learning_rate": 0.0003050500869620521,
"loss": 5.3672,
"step": 180
},
{
"epoch": 0.41,
"learning_rate": 0.0003025393439617544,
"loss": 5.4474,
"step": 183
},
{
"epoch": 0.42,
"learning_rate": 0.000300089592356783,
"loss": 5.1284,
"step": 186
},
{
"epoch": 0.42,
"learning_rate": 0.00029769840211922306,
"loss": 5.3965,
"step": 189
},
{
"epoch": 0.43,
"learning_rate": 0.000295363476640788,
"loss": 5.3393,
"step": 192
},
{
"epoch": 0.44,
"learning_rate": 0.0002930826434598881,
"loss": 5.303,
"step": 195
},
{
"epoch": 0.44,
"learning_rate": 0.0002908538457644313,
"loss": 5.2531,
"step": 198
},
{
"epoch": 0.45,
"eval_accuracy": 0.3039560332193454,
"eval_loss": 4.939572811126709,
"eval_runtime": 15.0765,
"eval_samples_per_second": 33.164,
"eval_steps_per_second": 16.582,
"step": 200
},
{
"epoch": 0.45,
"learning_rate": 0.00028867513459481295,
"loss": 5.3185,
"step": 201
},
{
"epoch": 0.46,
"learning_rate": 0.00028654466167991145,
"loss": 5.3985,
"step": 204
},
{
"epoch": 0.47,
"learning_rate": 0.00028446067284623944,
"loss": 5.1464,
"step": 207
},
{
"epoch": 0.47,
"learning_rate": 0.0002824215019468326,
"loss": 5.4369,
"step": 210
},
{
"epoch": 0.48,
"learning_rate": 0.0002804255652621247,
"loss": 5.1641,
"step": 213
},
{
"epoch": 0.49,
"learning_rate": 0.0002784713563300476,
"loss": 5.2121,
"step": 216
},
{
"epoch": 0.49,
"learning_rate": 0.0002765574411670027,
"loss": 5.2232,
"step": 219
},
{
"epoch": 0.5,
"learning_rate": 0.00027468245384525467,
"loss": 5.4016,
"step": 222
},
{
"epoch": 0.51,
"learning_rate": 0.00027284509239574835,
"loss": 5.1446,
"step": 225
},
{
"epoch": 0.51,
"learning_rate": 0.0002710441150084276,
"loss": 5.1719,
"step": 228
},
{
"epoch": 0.52,
"learning_rate": 0.0002692783365048561,
"loss": 5.3019,
"step": 231
},
{
"epoch": 0.53,
"learning_rate": 0.00026754662506037446,
"loss": 5.2286,
"step": 234
},
{
"epoch": 0.53,
"learning_rate": 0.0002658478991551975,
"loss": 5.2272,
"step": 237
},
{
"epoch": 0.54,
"learning_rate": 0.0002641811247357893,
"loss": 5.282,
"step": 240
},
{
"epoch": 0.55,
"learning_rate": 0.00026254531256958934,
"loss": 4.952,
"step": 243
},
{
"epoch": 0.55,
"learning_rate": 0.0002609395157777161,
"loss": 5.1267,
"step": 246
},
{
"epoch": 0.56,
"learning_rate": 0.00025936282753166636,
"loss": 5.1316,
"step": 249
},
{
"epoch": 0.57,
"learning_rate": 0.0002578143789012823,
"loss": 4.9848,
"step": 252
},
{
"epoch": 0.57,
"learning_rate": 0.00025629333684238444,
"loss": 4.7754,
"step": 255
},
{
"epoch": 0.58,
"learning_rate": 0.0002547989023134814,
"loss": 5.2225,
"step": 258
},
{
"epoch": 0.59,
"learning_rate": 0.0002533303085118872,
"loss": 5.1217,
"step": 261
},
{
"epoch": 0.59,
"learning_rate": 0.0002518868192203985,
"loss": 4.8745,
"step": 264
},
{
"epoch": 0.6,
"learning_rate": 0.0002504677272564347,
"loss": 5.0165,
"step": 267
},
{
"epoch": 0.61,
"learning_rate": 0.00024907235301622105,
"loss": 5.0835,
"step": 270
},
{
"epoch": 0.61,
"learning_rate": 0.0002477000431072053,
"loss": 5.2976,
"step": 273
},
{
"epoch": 0.62,
"learning_rate": 0.0002463501690624576,
"loss": 4.7942,
"step": 276
},
{
"epoch": 0.63,
"learning_rate": 0.0002450221261313084,
"loss": 5.0896,
"step": 279
},
{
"epoch": 0.63,
"learning_rate": 0.00024371533214093726,
"loss": 5.0112,
"step": 282
},
{
"epoch": 0.64,
"learning_rate": 0.0002424292264240461,
"loss": 4.9796,
"step": 285
},
{
"epoch": 0.65,
"learning_rate": 0.00024116326880812967,
"loss": 5.1468,
"step": 288
},
{
"epoch": 0.65,
"learning_rate": 0.0002399169386622059,
"loss": 4.7967,
"step": 291
},
{
"epoch": 0.66,
"learning_rate": 0.00023868973399718358,
"loss": 4.973,
"step": 294
},
{
"epoch": 0.67,
"learning_rate": 0.00023748117061633836,
"loss": 5.1543,
"step": 297
},
{
"epoch": 0.67,
"learning_rate": 0.00023629078131263043,
"loss": 4.8465,
"step": 300
},
{
"epoch": 0.67,
"eval_accuracy": 0.333695163654128,
"eval_loss": 4.60669469833374,
"eval_runtime": 15.1591,
"eval_samples_per_second": 32.984,
"eval_steps_per_second": 16.492,
"step": 300
},
{
"epoch": 0.68,
"learning_rate": 0.0002351181151098428,
"loss": 4.8838,
"step": 303
},
{
"epoch": 0.69,
"learning_rate": 0.00023396273654473972,
"loss": 4.8887,
"step": 306
},
{
"epoch": 0.69,
"learning_rate": 0.00023282422498765095,
"loss": 4.9501,
"step": 309
},
{
"epoch": 0.7,
"learning_rate": 0.0002317021739990746,
"loss": 4.7838,
"step": 312
},
{
"epoch": 0.71,
"learning_rate": 0.00023059619072006193,
"loss": 4.9579,
"step": 315
},
{
"epoch": 0.71,
"learning_rate": 0.00022950589529430995,
"loss": 4.8143,
"step": 318
},
{
"epoch": 0.72,
"learning_rate": 0.00022843092032002904,
"loss": 4.8685,
"step": 321
},
{
"epoch": 0.73,
"learning_rate": 0.00022737091032979027,
"loss": 4.782,
"step": 324
},
{
"epoch": 0.73,
"learning_rate": 0.00022632552129668023,
"loss": 4.9198,
"step": 327
},
{
"epoch": 0.74,
"learning_rate": 0.00022529442016520462,
"loss": 5.005,
"step": 330
},
{
"epoch": 0.75,
"learning_rate": 0.00022427728440548833,
"loss": 4.9693,
"step": 333
},
{
"epoch": 0.75,
"learning_rate": 0.00022327380158941728,
"loss": 4.9218,
"step": 336
},
{
"epoch": 0.76,
"learning_rate": 0.00022228366898745637,
"loss": 4.9192,
"step": 339
},
{
"epoch": 0.77,
"learning_rate": 0.00022130659318496252,
"loss": 4.8076,
"step": 342
},
{
"epoch": 0.78,
"learning_rate": 0.00022034228971688836,
"loss": 4.7961,
"step": 345
},
{
"epoch": 0.78,
"learning_rate": 0.0002193904827198436,
"loss": 4.5936,
"step": 348
},
{
"epoch": 0.79,
"learning_rate": 0.00021845090460054803,
"loss": 4.8138,
"step": 351
},
{
"epoch": 0.8,
"learning_rate": 0.00021752329571977103,
"loss": 4.7873,
"step": 354
},
{
"epoch": 0.8,
"learning_rate": 0.00021660740409091007,
"loss": 4.8076,
"step": 357
},
{
"epoch": 0.81,
"learning_rate": 0.0002157029850924131,
"loss": 4.6999,
"step": 360
},
{
"epoch": 0.82,
"learning_rate": 0.00021480980119330037,
"loss": 4.8198,
"step": 363
},
{
"epoch": 0.82,
"learning_rate": 0.00021392762169108589,
"loss": 4.7778,
"step": 366
},
{
"epoch": 0.83,
"learning_rate": 0.0002130562224614416,
"loss": 4.8642,
"step": 369
},
{
"epoch": 0.84,
"learning_rate": 0.00021219538571898804,
"loss": 4.934,
"step": 372
},
{
"epoch": 0.84,
"learning_rate": 0.00021134489978863144,
"loss": 4.777,
"step": 375
},
{
"epoch": 0.85,
"learning_rate": 0.0002105045588869023,
"loss": 4.7246,
"step": 378
},
{
"epoch": 0.86,
"learning_rate": 0.00020967416291278203,
"loss": 4.6483,
"step": 381
},
{
"epoch": 0.86,
"learning_rate": 0.00020885351724753563,
"loss": 4.688,
"step": 384
},
{
"epoch": 0.87,
"learning_rate": 0.00020804243256309523,
"loss": 4.7668,
"step": 387
},
{
"epoch": 0.88,
"learning_rate": 0.00020724072463856603,
"loss": 4.7151,
"step": 390
},
{
"epoch": 0.88,
"learning_rate": 0.00020644821418445137,
"loss": 4.5894,
"step": 393
},
{
"epoch": 0.89,
"learning_rate": 0.00020566472667421558,
"loss": 4.8375,
"step": 396
},
{
"epoch": 0.9,
"learning_rate": 0.00020489009218282547,
"loss": 4.7991,
"step": 399
},
{
"epoch": 0.9,
"eval_accuracy": 0.35269369809477286,
"eval_loss": 4.39344596862793,
"eval_runtime": 15.1249,
"eval_samples_per_second": 33.058,
"eval_steps_per_second": 16.529,
"step": 400
},
{
"epoch": 0.9,
"learning_rate": 0.00020412414523193154,
"loss": 4.857,
"step": 402
},
{
"epoch": 0.91,
"learning_rate": 0.00020336672464136806,
"loss": 4.9338,
"step": 405
},
{
"epoch": 0.92,
"learning_rate": 0.00020261767338667041,
"loss": 4.6781,
"step": 408
},
{
"epoch": 0.92,
"learning_rate": 0.00020187683846232233,
"loss": 4.7474,
"step": 411
},
{
"epoch": 0.93,
"learning_rate": 0.00020114407075046392,
"loss": 4.7408,
"step": 414
},
{
"epoch": 0.94,
"learning_rate": 0.00020041922489480405,
"loss": 4.8301,
"step": 417
},
{
"epoch": 0.94,
"learning_rate": 0.00019970215917949506,
"loss": 4.5838,
"step": 420
},
{
"epoch": 0.95,
"learning_rate": 0.00019899273541274044,
"loss": 4.6515,
"step": 423
},
{
"epoch": 0.96,
"learning_rate": 0.0001982908188149191,
"loss": 4.7319,
"step": 426
},
{
"epoch": 0.96,
"learning_rate": 0.00019759627791102,
"loss": 4.6515,
"step": 429
},
{
"epoch": 0.97,
"learning_rate": 0.000196908984427192,
"loss": 4.7311,
"step": 432
},
{
"epoch": 0.98,
"learning_rate": 0.00019622881319122527,
"loss": 4.6038,
"step": 435
},
{
"epoch": 0.98,
"learning_rate": 0.00019555564203678732,
"loss": 4.7496,
"step": 438
},
{
"epoch": 0.99,
"learning_rate": 0.0001948893517112488,
"loss": 4.6959,
"step": 441
},
{
"epoch": 1.0,
"learning_rate": 0.00019422982578694043,
"loss": 4.5849,
"step": 444
},
{
"epoch": 1.0,
"learning_rate": 0.00019357695057569082,
"loss": 4.655,
"step": 447
},
{
"epoch": 1.01,
"learning_rate": 0.00019293061504650376,
"loss": 4.7408,
"step": 450
},
{
"epoch": 1.02,
"learning_rate": 0.00019229071074623857,
"loss": 4.7902,
"step": 453
},
{
"epoch": 1.02,
"learning_rate": 0.00019165713172316568,
"loss": 4.6149,
"step": 456
},
{
"epoch": 1.03,
"learning_rate": 0.0001910297744532743,
"loss": 4.6644,
"step": 459
},
{
"epoch": 1.04,
"learning_rate": 0.00019040853776921678,
"loss": 4.613,
"step": 462
},
{
"epoch": 1.04,
"learning_rate": 0.00018979332279177815,
"loss": 4.542,
"step": 465
},
{
"epoch": 1.05,
"learning_rate": 0.00018918403286376548,
"loss": 4.7666,
"step": 468
},
{
"epoch": 1.06,
"learning_rate": 0.00018858057348621743,
"loss": 4.6471,
"step": 471
},
{
"epoch": 1.06,
"learning_rate": 0.0001879828522568376,
"loss": 4.5803,
"step": 474
},
{
"epoch": 1.07,
"learning_rate": 0.00018739077881056078,
"loss": 4.5415,
"step": 477
},
{
"epoch": 1.08,
"learning_rate": 0.0001868042647621658,
"loss": 4.5641,
"step": 480
},
{
"epoch": 1.09,
"learning_rate": 0.00018622322365085167,
"loss": 4.6407,
"step": 483
},
{
"epoch": 1.09,
"learning_rate": 0.00018564757088669834,
"loss": 4.7945,
"step": 486
},
{
"epoch": 1.1,
"learning_rate": 0.00018507722369893691,
"loss": 4.4922,
"step": 489
},
{
"epoch": 1.11,
"learning_rate": 0.00018451210108595716,
"loss": 4.4105,
"step": 492
},
{
"epoch": 1.11,
"learning_rate": 0.0001839521237669841,
"loss": 4.5781,
"step": 495
},
{
"epoch": 1.12,
"learning_rate": 0.00018339721413535823,
"loss": 4.2787,
"step": 498
},
{
"epoch": 1.12,
"eval_accuracy": 0.36416707376648755,
"eval_loss": 4.238906383514404,
"eval_runtime": 15.1858,
"eval_samples_per_second": 32.925,
"eval_steps_per_second": 16.463,
"step": 500
},
{
"epoch": 1.13,
"learning_rate": 0.0001828472962133565,
"loss": 4.4456,
"step": 501
},
{
"epoch": 1.13,
"learning_rate": 0.0001823022956084947,
"loss": 4.5287,
"step": 504
},
{
"epoch": 1.14,
"learning_rate": 0.00018176213947125418,
"loss": 4.5194,
"step": 507
},
{
"epoch": 1.15,
"learning_rate": 0.00018122675645417804,
"loss": 4.4069,
"step": 510
},
{
"epoch": 1.15,
"learning_rate": 0.0001806960766722851,
"loss": 4.6053,
"step": 513
},
{
"epoch": 1.16,
"learning_rate": 0.0001801700316647514,
"loss": 4.4653,
"step": 516
},
{
"epoch": 1.17,
"learning_rate": 0.00017964855435781174,
"loss": 4.3869,
"step": 519
},
{
"epoch": 1.17,
"learning_rate": 0.0001791315790288356,
"loss": 4.5346,
"step": 522
},
{
"epoch": 1.18,
"learning_rate": 0.00017861904127153383,
"loss": 4.3397,
"step": 525
},
{
"epoch": 1.19,
"learning_rate": 0.00017811087796225377,
"loss": 4.4981,
"step": 528
},
{
"epoch": 1.19,
"learning_rate": 0.00017760702722732373,
"loss": 4.4315,
"step": 531
},
{
"epoch": 1.2,
"learning_rate": 0.0001771074284114076,
"loss": 4.4401,
"step": 534
},
{
"epoch": 1.21,
"learning_rate": 0.00017661202204683334,
"loss": 4.2521,
"step": 537
},
{
"epoch": 1.21,
"learning_rate": 0.00017612074982385957,
"loss": 4.663,
"step": 540
},
{
"epoch": 1.22,
"learning_rate": 0.00017563355456184752,
"loss": 4.5429,
"step": 543
},
{
"epoch": 1.23,
"learning_rate": 0.00017515038018130498,
"loss": 4.6201,
"step": 546
},
{
"epoch": 1.23,
"learning_rate": 0.00017467117167677167,
"loss": 4.5178,
"step": 549
},
{
"epoch": 1.24,
"learning_rate": 0.0001741958750905162,
"loss": 4.4457,
"step": 552
},
{
"epoch": 1.25,
"learning_rate": 0.00017372443748701614,
"loss": 4.4784,
"step": 555
},
{
"epoch": 1.25,
"learning_rate": 0.00017325680692819372,
"loss": 4.6209,
"step": 558
},
{
"epoch": 1.26,
"learning_rate": 0.00017279293244938095,
"loss": 4.4459,
"step": 561
},
{
"epoch": 1.27,
"learning_rate": 0.0001723327640359885,
"loss": 4.4116,
"step": 564
},
{
"epoch": 1.27,
"learning_rate": 0.0001718762526008549,
"loss": 4.414,
"step": 567
},
{
"epoch": 1.28,
"learning_rate": 0.00017142334996225191,
"loss": 4.6379,
"step": 570
},
{
"epoch": 1.29,
"learning_rate": 0.00017097400882252448,
"loss": 4.4434,
"step": 573
},
{
"epoch": 1.29,
"learning_rate": 0.0001705281827473427,
"loss": 4.3952,
"step": 576
},
{
"epoch": 1.3,
"learning_rate": 0.00017008582614554666,
"loss": 4.2903,
"step": 579
},
{
"epoch": 1.31,
"learning_rate": 0.0001696468942495628,
"loss": 4.5144,
"step": 582
},
{
"epoch": 1.31,
"learning_rate": 0.0001692113430963735,
"loss": 4.3821,
"step": 585
},
{
"epoch": 1.32,
"learning_rate": 0.00016877912950902176,
"loss": 4.5597,
"step": 588
},
{
"epoch": 1.33,
"learning_rate": 0.00016835021107863206,
"loss": 4.4296,
"step": 591
},
{
"epoch": 1.33,
"learning_rate": 0.00016792454614693233,
"loss": 4.2632,
"step": 594
},
{
"epoch": 1.34,
"learning_rate": 0.00016750209378925862,
"loss": 4.2681,
"step": 597
},
{
"epoch": 1.35,
"learning_rate": 0.00016708281379802854,
"loss": 4.4893,
"step": 600
},
{
"epoch": 1.35,
"eval_accuracy": 0.3719882755251588,
"eval_loss": 4.1261677742004395,
"eval_runtime": 15.1896,
"eval_samples_per_second": 32.917,
"eval_steps_per_second": 16.459,
"step": 600
},
{
"epoch": 1.35,
"learning_rate": 0.00016666666666666666,
"loss": 4.4189,
"step": 603
},
{
"epoch": 1.36,
"learning_rate": 0.00016625361357396908,
"loss": 4.3687,
"step": 606
},
{
"epoch": 1.37,
"learning_rate": 0.0001658436163688913,
"loss": 4.5189,
"step": 609
},
{
"epoch": 1.37,
"learning_rate": 0.0001654366375557471,
"loss": 4.3339,
"step": 612
},
{
"epoch": 1.38,
"learning_rate": 0.00016503264027980518,
"loss": 4.3293,
"step": 615
},
{
"epoch": 1.39,
"learning_rate": 0.00016463158831327043,
"loss": 4.4765,
"step": 618
},
{
"epoch": 1.4,
"learning_rate": 0.00016423344604163842,
"loss": 4.4114,
"step": 621
},
{
"epoch": 1.4,
"learning_rate": 0.000163838178450411,
"loss": 4.4124,
"step": 624
},
{
"epoch": 1.41,
"learning_rate": 0.00016344575111216204,
"loss": 4.4381,
"step": 627
},
{
"epoch": 1.42,
"learning_rate": 0.00016305613017394223,
"loss": 4.3048,
"step": 630
},
{
"epoch": 1.42,
"learning_rate": 0.0001626692823450125,
"loss": 4.4025,
"step": 633
},
{
"epoch": 1.43,
"learning_rate": 0.00016228517488489633,
"loss": 4.4779,
"step": 636
},
{
"epoch": 1.44,
"learning_rate": 0.00016190377559174065,
"loss": 4.3395,
"step": 639
},
{
"epoch": 1.44,
"learning_rate": 0.00016152505279097643,
"loss": 4.4437,
"step": 642
},
{
"epoch": 1.45,
"learning_rate": 0.00016114897532426946,
"loss": 4.4231,
"step": 645
},
{
"epoch": 1.46,
"learning_rate": 0.00016077551253875313,
"loss": 4.284,
"step": 648
},
{
"epoch": 1.46,
"learning_rate": 0.00016040463427653402,
"loss": 4.2703,
"step": 651
},
{
"epoch": 1.47,
"learning_rate": 0.00016003631086446298,
"loss": 4.5442,
"step": 654
},
{
"epoch": 1.48,
"learning_rate": 0.00015967051310416313,
"loss": 4.4264,
"step": 657
},
{
"epoch": 1.48,
"learning_rate": 0.00015930721226230747,
"loss": 4.4124,
"step": 660
},
{
"epoch": 1.49,
"learning_rate": 0.00015894638006113876,
"loss": 4.2462,
"step": 663
},
{
"epoch": 1.5,
"learning_rate": 0.0001585879886692247,
"loss": 4.4239,
"step": 666
},
{
"epoch": 1.5,
"learning_rate": 0.00015823201069244109,
"loss": 4.3737,
"step": 669
},
{
"epoch": 1.51,
"learning_rate": 0.00015787841916517674,
"loss": 4.3488,
"step": 672
},
{
"epoch": 1.52,
"learning_rate": 0.00015752718754175364,
"loss": 4.3232,
"step": 675
},
{
"epoch": 1.52,
"learning_rate": 0.0001571782896880563,
"loss": 4.3468,
"step": 678
},
{
"epoch": 1.53,
"learning_rate": 0.00015683169987336384,
"loss": 4.2461,
"step": 681
},
{
"epoch": 1.54,
"learning_rate": 0.00015648739276237958,
"loss": 4.3453,
"step": 684
},
{
"epoch": 1.54,
"learning_rate": 0.00015614534340745214,
"loss": 4.3133,
"step": 687
},
{
"epoch": 1.55,
"learning_rate": 0.00015580552724098266,
"loss": 4.4003,
"step": 690
},
{
"epoch": 1.56,
"learning_rate": 0.0001554679200680133,
"loss": 4.4224,
"step": 693
},
{
"epoch": 1.56,
"learning_rate": 0.00015513249805899147,
"loss": 4.3176,
"step": 696
},
{
"epoch": 1.57,
"learning_rate": 0.00015479923774270487,
"loss": 4.346,
"step": 699
},
{
"epoch": 1.57,
"eval_accuracy": 0.3792750366389839,
"eval_loss": 4.030762672424316,
"eval_runtime": 15.1012,
"eval_samples_per_second": 33.11,
"eval_steps_per_second": 16.555,
"step": 700
},
{
"epoch": 1.58,
"learning_rate": 0.00015446811599938306,
"loss": 4.4625,
"step": 702
},
{
"epoch": 1.58,
"learning_rate": 0.00015413911005396052,
"loss": 4.3274,
"step": 705
},
{
"epoch": 1.59,
"learning_rate": 0.0001538121974694968,
"loss": 4.4441,
"step": 708
},
{
"epoch": 1.6,
"learning_rate": 0.00015348735614074976,
"loss": 4.1558,
"step": 711
},
{
"epoch": 1.6,
"learning_rate": 0.0001531645642878972,
"loss": 4.3941,
"step": 714
},
{
"epoch": 1.61,
"learning_rate": 0.0001528438004504034,
"loss": 4.1691,
"step": 717
},
{
"epoch": 1.62,
"learning_rate": 0.00015252504348102605,
"loss": 4.4237,
"step": 720
},
{
"epoch": 1.62,
"learning_rate": 0.0001522082725399605,
"loss": 4.314,
"step": 723
},
{
"epoch": 1.63,
"learning_rate": 0.00015189346708911682,
"loss": 4.2329,
"step": 726
},
{
"epoch": 1.64,
"learning_rate": 0.00015158060688652685,
"loss": 4.2591,
"step": 729
},
{
"epoch": 1.64,
"learning_rate": 0.0001512696719808772,
"loss": 4.3707,
"step": 732
},
{
"epoch": 1.65,
"learning_rate": 0.00015096064270616534,
"loss": 4.3054,
"step": 735
},
{
"epoch": 1.66,
"learning_rate": 0.000150653499676475,
"loss": 4.466,
"step": 738
},
{
"epoch": 1.66,
"learning_rate": 0.00015034822378086837,
"loss": 4.2339,
"step": 741
},
{
"epoch": 1.67,
"learning_rate": 0.0001500447961783915,
"loss": 4.2401,
"step": 744
},
{
"epoch": 1.68,
"learning_rate": 0.00014974319829319003,
"loss": 4.1819,
"step": 747
},
{
"epoch": 1.68,
"learning_rate": 0.00014944341180973263,
"loss": 4.2786,
"step": 750
},
{
"epoch": 1.69,
"learning_rate": 0.0001491454186681393,
"loss": 4.3168,
"step": 753
},
{
"epoch": 1.7,
"learning_rate": 0.00014884920105961153,
"loss": 4.266,
"step": 756
},
{
"epoch": 1.71,
"learning_rate": 0.00014855474142196195,
"loss": 4.1603,
"step": 759
},
{
"epoch": 1.71,
"learning_rate": 0.00014826202243524108,
"loss": 4.2068,
"step": 762
},
{
"epoch": 1.72,
"learning_rate": 0.00014797102701745806,
"loss": 4.1314,
"step": 765
},
{
"epoch": 1.73,
"learning_rate": 0.000147681738320394,
"loss": 4.201,
"step": 768
},
{
"epoch": 1.73,
"learning_rate": 0.00014739413972550443,
"loss": 4.1408,
"step": 771
},
{
"epoch": 1.74,
"learning_rate": 0.00014710821483990966,
"loss": 4.1985,
"step": 774
},
{
"epoch": 1.75,
"learning_rate": 0.0001468239474924699,
"loss": 4.3132,
"step": 777
},
{
"epoch": 1.75,
"learning_rate": 0.00014654132172994404,
"loss": 4.1763,
"step": 780
},
{
"epoch": 1.76,
"learning_rate": 0.00014626032181322903,
"loss": 4.2122,
"step": 783
},
{
"epoch": 1.77,
"learning_rate": 0.00014598093221367836,
"loss": 4.0161,
"step": 786
},
{
"epoch": 1.77,
"learning_rate": 0.0001457031376094977,
"loss": 4.3279,
"step": 789
},
{
"epoch": 1.78,
"learning_rate": 0.00014542692288221565,
"loss": 4.26,
"step": 792
},
{
"epoch": 1.79,
"learning_rate": 0.0001451522731132279,
"loss": 4.2826,
"step": 795
},
{
"epoch": 1.79,
"learning_rate": 0.00014487917358041273,
"loss": 4.1878,
"step": 798
},
{
"epoch": 1.8,
"eval_accuracy": 0.3845920859794822,
"eval_loss": 3.957355499267578,
"eval_runtime": 15.1878,
"eval_samples_per_second": 32.921,
"eval_steps_per_second": 16.461,
"step": 800
},
{
"epoch": 1.8,
"learning_rate": 0.00014460760975481632,
"loss": 4.3063,
"step": 801
},
{
"epoch": 1.81,
"learning_rate": 0.00014433756729740648,
"loss": 4.1148,
"step": 804
},
{
"epoch": 1.81,
"learning_rate": 0.00014406903205589218,
"loss": 4.1089,
"step": 807
},
{
"epoch": 1.82,
"learning_rate": 0.00014380199006160872,
"loss": 4.1745,
"step": 810
},
{
"epoch": 1.83,
"learning_rate": 0.00014353642752646544,
"loss": 4.2486,
"step": 813
},
{
"epoch": 1.83,
"learning_rate": 0.00014327233083995573,
"loss": 4.2344,
"step": 816
},
{
"epoch": 1.84,
"learning_rate": 0.00014300968656622687,
"loss": 4.0578,
"step": 819
},
{
"epoch": 1.85,
"learning_rate": 0.00014274848144120935,
"loss": 4.2833,
"step": 822
},
{
"epoch": 1.85,
"learning_rate": 0.000142488702369803,
"loss": 4.1856,
"step": 825
},
{
"epoch": 1.86,
"learning_rate": 0.00014223033642311972,
"loss": 4.2869,
"step": 828
},
{
"epoch": 1.87,
"learning_rate": 0.0001419733708357808,
"loss": 4.1484,
"step": 831
},
{
"epoch": 1.87,
"learning_rate": 0.00014171779300326768,
"loss": 4.3338,
"step": 834
},
{
"epoch": 1.88,
"learning_rate": 0.00014146359047932533,
"loss": 4.0804,
"step": 837
},
{
"epoch": 1.89,
"learning_rate": 0.0001412107509734163,
"loss": 4.2786,
"step": 840
},
{
"epoch": 1.89,
"learning_rate": 0.0001409592623482247,
"loss": 4.2871,
"step": 843
},
{
"epoch": 1.9,
"learning_rate": 0.0001407091126172092,
"loss": 4.4272,
"step": 846
},
{
"epoch": 1.91,
"learning_rate": 0.0001404602899422033,
"loss": 4.1707,
"step": 849
},
{
"epoch": 1.91,
"learning_rate": 0.00014021278263106235,
"loss": 4.1172,
"step": 852
},
{
"epoch": 1.92,
"learning_rate": 0.00013996657913535574,
"loss": 4.3611,
"step": 855
},
{
"epoch": 1.93,
"learning_rate": 0.00013972166804810385,
"loss": 4.2268,
"step": 858
},
{
"epoch": 1.93,
"learning_rate": 0.00013947803810155813,
"loss": 4.1159,
"step": 861
},
{
"epoch": 1.94,
"learning_rate": 0.0001392356781650238,
"loss": 4.3072,
"step": 864
},
{
"epoch": 1.95,
"learning_rate": 0.00013899457724272379,
"loss": 4.1207,
"step": 867
},
{
"epoch": 1.95,
"learning_rate": 0.00013875472447170365,
"loss": 4.2149,
"step": 870
},
{
"epoch": 1.96,
"learning_rate": 0.0001385161091197755,
"loss": 4.2332,
"step": 873
},
{
"epoch": 1.97,
"learning_rate": 0.00013827872058350135,
"loss": 4.3785,
"step": 876
},
{
"epoch": 1.97,
"learning_rate": 0.00013804254838621383,
"loss": 4.2428,
"step": 879
},
{
"epoch": 1.98,
"learning_rate": 0.0001378075821760741,
"loss": 4.0385,
"step": 882
},
{
"epoch": 1.99,
"learning_rate": 0.0001375738117241664,
"loss": 4.3084,
"step": 885
},
{
"epoch": 1.99,
"learning_rate": 0.00013734122692262733,
"loss": 4.1674,
"step": 888
},
{
"epoch": 2.0,
"learning_rate": 0.0001371098177828104,
"loss": 4.2508,
"step": 891
},
{
"epoch": 2.01,
"learning_rate": 0.00013687957443348414,
"loss": 4.246,
"step": 894
},
{
"epoch": 2.02,
"learning_rate": 0.0001366504871190636,
"loss": 4.125,
"step": 897
},
{
"epoch": 2.02,
"learning_rate": 0.00013642254619787418,
"loss": 4.2311,
"step": 900
},
{
"epoch": 2.02,
"eval_accuracy": 0.38997361993160723,
"eval_loss": 3.894345283508301,
"eval_runtime": 15.1182,
"eval_samples_per_second": 33.073,
"eval_steps_per_second": 16.536,
"step": 900
},
{
"epoch": 2.03,
"learning_rate": 0.00013619574214044708,
"loss": 3.9819,
"step": 903
},
{
"epoch": 2.04,
"learning_rate": 0.00013597006552784624,
"loss": 4.1381,
"step": 906
},
{
"epoch": 2.04,
"learning_rate": 0.00013574550705002514,
"loss": 4.1994,
"step": 909
},
{
"epoch": 2.05,
"learning_rate": 0.0001355220575042138,
"loss": 4.3326,
"step": 912
},
{
"epoch": 2.06,
"learning_rate": 0.00013529970779333468,
"loss": 4.09,
"step": 915
},
{
"epoch": 2.06,
"learning_rate": 0.00013507844892444694,
"loss": 4.1256,
"step": 918
},
{
"epoch": 2.07,
"learning_rate": 0.000134858272007219,
"loss": 4.043,
"step": 921
},
{
"epoch": 2.08,
"learning_rate": 0.00013463916825242806,
"loss": 4.1771,
"step": 924
},
{
"epoch": 2.08,
"learning_rate": 0.00013442112897048627,
"loss": 4.175,
"step": 927
},
{
"epoch": 2.09,
"learning_rate": 0.00013420414556999363,
"loss": 4.1617,
"step": 930
},
{
"epoch": 2.1,
"learning_rate": 0.00013398820955631575,
"loss": 4.1036,
"step": 933
},
{
"epoch": 2.1,
"learning_rate": 0.00013377331253018723,
"loss": 4.1814,
"step": 936
},
{
"epoch": 2.11,
"learning_rate": 0.00013355944618633945,
"loss": 4.1713,
"step": 939
},
{
"epoch": 2.12,
"learning_rate": 0.0001333466023121524,
"loss": 3.9674,
"step": 942
},
{
"epoch": 2.12,
"learning_rate": 0.00013313477278633005,
"loss": 4.1862,
"step": 945
},
{
"epoch": 2.13,
"learning_rate": 0.00013292394957759875,
"loss": 3.9531,
"step": 948
},
{
"epoch": 2.14,
"learning_rate": 0.0001327141247434285,
"loss": 4.2624,
"step": 951
},
{
"epoch": 2.14,
"learning_rate": 0.0001325052904287759,
"loss": 4.2659,
"step": 954
},
{
"epoch": 2.15,
"learning_rate": 0.0001322974388648493,
"loss": 4.1861,
"step": 957
},
{
"epoch": 2.16,
"learning_rate": 0.00013209056236789465,
"loss": 4.1348,
"step": 960
},
{
"epoch": 2.16,
"learning_rate": 0.0001318846533380027,
"loss": 4.0551,
"step": 963
},
{
"epoch": 2.17,
"learning_rate": 0.00013167970425793625,
"loss": 4.1224,
"step": 966
},
{
"epoch": 2.18,
"learning_rate": 0.00013147570769197746,
"loss": 4.223,
"step": 969
},
{
"epoch": 2.18,
"learning_rate": 0.00013127265628479467,
"loss": 4.2638,
"step": 972
},
{
"epoch": 2.19,
"learning_rate": 0.00013107054276032882,
"loss": 4.187,
"step": 975
},
{
"epoch": 2.2,
"learning_rate": 0.0001308693599206979,
"loss": 4.2086,
"step": 978
},
{
"epoch": 2.2,
"learning_rate": 0.00013066910064512072,
"loss": 4.0953,
"step": 981
},
{
"epoch": 2.21,
"learning_rate": 0.00013046975788885806,
"loss": 4.0066,
"step": 984
},
{
"epoch": 2.22,
"learning_rate": 0.0001302713246821718,
"loss": 4.0972,
"step": 987
},
{
"epoch": 2.22,
"learning_rate": 0.00013007379412930154,
"loss": 4.0935,
"step": 990
},
{
"epoch": 2.23,
"learning_rate": 0.00012987715940745797,
"loss": 4.2207,
"step": 993
},
{
"epoch": 2.24,
"learning_rate": 0.00012968141376583318,
"loss": 4.2459,
"step": 996
},
{
"epoch": 2.24,
"learning_rate": 0.00012948655052462697,
"loss": 3.9241,
"step": 999
},
{
"epoch": 2.25,
"eval_accuracy": 0.3940625305324866,
"eval_loss": 3.8381006717681885,
"eval_runtime": 15.2257,
"eval_samples_per_second": 32.839,
"eval_steps_per_second": 16.42,
"step": 1000
},
{
"epoch": 2.25,
"learning_rate": 0.0001292925630740897,
"loss": 3.9667,
"step": 1002
},
{
"epoch": 2.26,
"learning_rate": 0.00012909944487358055,
"loss": 3.9541,
"step": 1005
},
{
"epoch": 2.26,
"learning_rate": 0.00012890718945064115,
"loss": 4.17,
"step": 1008
},
{
"epoch": 2.27,
"learning_rate": 0.00012871579040008455,
"loss": 4.2002,
"step": 1011
},
{
"epoch": 2.28,
"learning_rate": 0.00012852524138309883,
"loss": 3.8889,
"step": 1014
},
{
"epoch": 2.28,
"learning_rate": 0.00012833553612636562,
"loss": 4.1517,
"step": 1017
},
{
"epoch": 2.29,
"learning_rate": 0.00012814666842119222,
"loss": 4.0006,
"step": 1020
},
{
"epoch": 2.3,
"learning_rate": 0.0001279586321226585,
"loss": 4.1701,
"step": 1023
},
{
"epoch": 2.3,
"learning_rate": 0.0001277714211487771,
"loss": 4.0948,
"step": 1026
},
{
"epoch": 2.31,
"learning_rate": 0.00012758502947966702,
"loss": 3.8545,
"step": 1029
},
{
"epoch": 2.32,
"learning_rate": 0.0001273994511567407,
"loss": 4.0275,
"step": 1032
},
{
"epoch": 2.33,
"learning_rate": 0.000127214680281904,
"loss": 4.0691,
"step": 1035
},
{
"epoch": 2.33,
"learning_rate": 0.00012703071101676877,
"loss": 4.2064,
"step": 1038
},
{
"epoch": 2.34,
"learning_rate": 0.00012684753758187807,
"loss": 4.0849,
"step": 1041
},
{
"epoch": 2.35,
"learning_rate": 0.0001266651542559436,
"loss": 4.07,
"step": 1044
},
{
"epoch": 2.35,
"learning_rate": 0.00012648355537509508,
"loss": 4.0875,
"step": 1047
},
{
"epoch": 2.36,
"learning_rate": 0.00012630273533214138,
"loss": 4.1563,
"step": 1050
},
{
"epoch": 2.37,
"learning_rate": 0.00012612268857584364,
"loss": 3.9259,
"step": 1053
},
{
"epoch": 2.37,
"learning_rate": 0.00012594340961019924,
"loss": 4.0386,
"step": 1056
},
{
"epoch": 2.38,
"learning_rate": 0.00012576489299373717,
"loss": 4.1156,
"step": 1059
},
{
"epoch": 2.39,
"learning_rate": 0.00012558713333882439,
"loss": 4.1451,
"step": 1062
},
{
"epoch": 2.39,
"learning_rate": 0.0001254101253109829,
"loss": 4.1658,
"step": 1065
},
{
"epoch": 2.4,
"learning_rate": 0.00012523386362821735,
"loss": 3.9714,
"step": 1068
},
{
"epoch": 2.41,
"learning_rate": 0.00012505834306035296,
"loss": 4.054,
"step": 1071
},
{
"epoch": 2.41,
"learning_rate": 0.00012488355842838386,
"loss": 4.3048,
"step": 1074
},
{
"epoch": 2.42,
"learning_rate": 0.00012470950460383105,
"loss": 4.1463,
"step": 1077
},
{
"epoch": 2.43,
"learning_rate": 0.00012453617650811052,
"loss": 4.1869,
"step": 1080
},
{
"epoch": 2.43,
"learning_rate": 0.00012436356911191076,
"loss": 4.1841,
"step": 1083
},
{
"epoch": 2.44,
"learning_rate": 0.00012419167743457984,
"loss": 4.1018,
"step": 1086
},
{
"epoch": 2.45,
"learning_rate": 0.00012402049654352198,
"loss": 4.0625,
"step": 1089
},
{
"epoch": 2.45,
"learning_rate": 0.00012385002155360265,
"loss": 3.9801,
"step": 1092
},
{
"epoch": 2.46,
"learning_rate": 0.0001236802476265634,
"loss": 3.8948,
"step": 1095
},
{
"epoch": 2.47,
"learning_rate": 0.0001235111699704449,
"loss": 4.0892,
"step": 1098
},
{
"epoch": 2.47,
"eval_accuracy": 0.40057449926722033,
"eval_loss": 3.7851128578186035,
"eval_runtime": 15.1297,
"eval_samples_per_second": 33.047,
"eval_steps_per_second": 16.524,
"step": 1100
},
{
"epoch": 2.47,
"learning_rate": 0.00012334278383901892,
"loss": 4.1253,
"step": 1101
},
{
"epoch": 2.48,
"learning_rate": 0.0001231750845312288,
"loss": 4.1474,
"step": 1104
},
{
"epoch": 2.49,
"learning_rate": 0.0001230080673906381,
"loss": 3.9774,
"step": 1107
},
{
"epoch": 2.49,
"learning_rate": 0.00012284172780488756,
"loss": 3.9692,
"step": 1110
},
{
"epoch": 2.5,
"learning_rate": 0.00012267606120516025,
"loss": 4.1343,
"step": 1113
},
{
"epoch": 2.51,
"learning_rate": 0.0001225110630656542,
"loss": 3.9415,
"step": 1116
},
{
"epoch": 2.51,
"learning_rate": 0.00012234672890306351,
"loss": 4.1099,
"step": 1119
},
{
"epoch": 2.52,
"learning_rate": 0.0001221830542760663,
"loss": 4.1696,
"step": 1122
},
{
"epoch": 2.53,
"learning_rate": 0.00012202003478482084,
"loss": 4.078,
"step": 1125
},
{
"epoch": 2.53,
"learning_rate": 0.00012185766607046863,
"loss": 4.0812,
"step": 1128
},
{
"epoch": 2.54,
"learning_rate": 0.00012169594381464496,
"loss": 3.9068,
"step": 1131
},
{
"epoch": 2.55,
"learning_rate": 0.00012153486373899648,
"loss": 4.1278,
"step": 1134
},
{
"epoch": 2.55,
"learning_rate": 0.00012137442160470578,
"loss": 3.9715,
"step": 1137
},
{
"epoch": 2.56,
"learning_rate": 0.00012121461321202305,
"loss": 4.1367,
"step": 1140
},
{
"epoch": 2.57,
"learning_rate": 0.00012105543439980414,
"loss": 4.0155,
"step": 1143
},
{
"epoch": 2.57,
"learning_rate": 0.00012089688104505568,
"loss": 3.9383,
"step": 1146
},
{
"epoch": 2.58,
"learning_rate": 0.00012073894906248632,
"loss": 4.0753,
"step": 1149
},
{
"epoch": 2.59,
"learning_rate": 0.00012058163440406483,
"loss": 3.9593,
"step": 1152
},
{
"epoch": 2.59,
"learning_rate": 0.00012042493305858426,
"loss": 4.022,
"step": 1155
},
{
"epoch": 2.6,
"learning_rate": 0.00012026884105123223,
"loss": 3.9807,
"step": 1158
},
{
"epoch": 2.61,
"learning_rate": 0.00012011335444316761,
"loss": 3.956,
"step": 1161
},
{
"epoch": 2.61,
"learning_rate": 0.00011995846933110294,
"loss": 3.9439,
"step": 1164
},
{
"epoch": 2.62,
"learning_rate": 0.0001198041818468931,
"loss": 3.8425,
"step": 1167
},
{
"epoch": 2.63,
"learning_rate": 0.00011965048815712919,
"loss": 3.7483,
"step": 1170
},
{
"epoch": 2.64,
"learning_rate": 0.00011949738446273892,
"loss": 3.8322,
"step": 1173
},
{
"epoch": 2.64,
"learning_rate": 0.00011934486699859179,
"loss": 4.0349,
"step": 1176
},
{
"epoch": 2.65,
"learning_rate": 0.00011919293203311051,
"loss": 4.0348,
"step": 1179
},
{
"epoch": 2.66,
"learning_rate": 0.00011904157586788735,
"loss": 3.9782,
"step": 1182
},
{
"epoch": 2.66,
"learning_rate": 0.0001188907948373061,
"loss": 4.0214,
"step": 1185
},
{
"epoch": 2.67,
"learning_rate": 0.00011874058530816918,
"loss": 4.03,
"step": 1188
},
{
"epoch": 2.68,
"learning_rate": 0.00011859094367932986,
"loss": 3.8793,
"step": 1191
},
{
"epoch": 2.68,
"learning_rate": 0.00011844186638132986,
"loss": 4.0513,
"step": 1194
},
{
"epoch": 2.69,
"learning_rate": 0.00011829334987604151,
"loss": 3.9717,
"step": 1197
},
{
"epoch": 2.7,
"learning_rate": 0.00011814539065631521,
"loss": 3.8988,
"step": 1200
},
{
"epoch": 2.7,
"eval_accuracy": 0.40605862237420615,
"eval_loss": 3.735245704650879,
"eval_runtime": 15.2272,
"eval_samples_per_second": 32.836,
"eval_steps_per_second": 16.418,
"step": 1200
},
{
"epoch": 2.7,
"learning_rate": 0.00011799798524563149,
"loss": 4.0729,
"step": 1203
},
{
"epoch": 2.71,
"learning_rate": 0.00011785113019775794,
"loss": 3.9832,
"step": 1206
},
{
"epoch": 2.72,
"learning_rate": 0.00011770482209641084,
"loss": 4.0265,
"step": 1209
},
{
"epoch": 2.72,
"learning_rate": 0.0001175590575549214,
"loss": 3.8835,
"step": 1212
},
{
"epoch": 2.73,
"learning_rate": 0.00011741383321590637,
"loss": 4.047,
"step": 1215
},
{
"epoch": 2.74,
"learning_rate": 0.00011726914575094334,
"loss": 3.9129,
"step": 1218
},
{
"epoch": 2.74,
"learning_rate": 0.00011712499186025038,
"loss": 4.1231,
"step": 1221
},
{
"epoch": 2.75,
"learning_rate": 0.00011698136827236986,
"loss": 3.909,
"step": 1224
},
{
"epoch": 2.76,
"learning_rate": 0.00011683827174385659,
"loss": 3.9995,
"step": 1227
},
{
"epoch": 2.76,
"learning_rate": 0.00011669569905897041,
"loss": 3.8527,
"step": 1230
},
{
"epoch": 2.77,
"learning_rate": 0.00011655364702937239,
"loss": 3.943,
"step": 1233
},
{
"epoch": 2.78,
"learning_rate": 0.00011641211249382548,
"loss": 3.9862,
"step": 1236
},
{
"epoch": 2.78,
"learning_rate": 0.0001162710923178991,
"loss": 4.0563,
"step": 1239
},
{
"epoch": 2.79,
"learning_rate": 0.00011613058339367746,
"loss": 3.8894,
"step": 1242
},
{
"epoch": 2.8,
"learning_rate": 0.00011599058263947197,
"loss": 4.0139,
"step": 1245
},
{
"epoch": 2.8,
"learning_rate": 0.0001158510869995373,
"loss": 4.077,
"step": 1248
},
{
"epoch": 2.81,
"learning_rate": 0.00011571209344379127,
"loss": 3.997,
"step": 1251
},
{
"epoch": 2.82,
"learning_rate": 0.00011557359896753848,
"loss": 4.1008,
"step": 1254
},
{
"epoch": 2.82,
"learning_rate": 0.00011543560059119733,
"loss": 3.9626,
"step": 1257
},
{
"epoch": 2.83,
"learning_rate": 0.00011529809536003097,
"loss": 4.166,
"step": 1260
},
{
"epoch": 2.84,
"learning_rate": 0.00011516108034388144,
"loss": 3.9516,
"step": 1263
},
{
"epoch": 2.84,
"learning_rate": 0.00011502455263690746,
"loss": 3.8293,
"step": 1266
},
{
"epoch": 2.85,
"learning_rate": 0.00011488850935732566,
"loss": 3.9151,
"step": 1269
},
{
"epoch": 2.86,
"learning_rate": 0.00011475294764715498,
"loss": 3.8377,
"step": 1272
},
{
"epoch": 2.86,
"learning_rate": 0.00011461786467196458,
"loss": 3.9941,
"step": 1275
},
{
"epoch": 2.87,
"learning_rate": 0.00011448325762062485,
"loss": 3.9573,
"step": 1278
},
{
"epoch": 2.88,
"learning_rate": 0.00011434912370506185,
"loss": 4.0494,
"step": 1281
},
{
"epoch": 2.88,
"learning_rate": 0.00011421546016001452,
"loss": 4.0166,
"step": 1284
},
{
"epoch": 2.89,
"learning_rate": 0.00011408226424279549,
"loss": 4.0949,
"step": 1287
},
{
"epoch": 2.9,
"learning_rate": 0.00011394953323305457,
"loss": 4.0741,
"step": 1290
},
{
"epoch": 2.9,
"learning_rate": 0.00011381726443254541,
"loss": 3.9583,
"step": 1293
},
{
"epoch": 2.91,
"learning_rate": 0.00011368545516489513,
"loss": 3.9649,
"step": 1296
},
{
"epoch": 2.92,
"learning_rate": 0.00011355410277537692,
"loss": 3.9169,
"step": 1299
},
{
"epoch": 2.92,
"eval_accuracy": 0.4101592574499267,
"eval_loss": 3.6907660961151123,
"eval_runtime": 15.2368,
"eval_samples_per_second": 32.815,
"eval_steps_per_second": 16.408,
"step": 1300
},
{
"epoch": 2.93,
"learning_rate": 0.00011342320463068534,
"loss": 4.0254,
"step": 1302
},
{
"epoch": 2.93,
"learning_rate": 0.00011329275811871468,
"loss": 3.9481,
"step": 1305
},
{
"epoch": 2.94,
"learning_rate": 0.00011316276064834012,
"loss": 3.8534,
"step": 1308
},
{
"epoch": 2.95,
"learning_rate": 0.00011303320964920135,
"loss": 3.8253,
"step": 1311
},
{
"epoch": 2.95,
"learning_rate": 0.00011290410257148924,
"loss": 3.8843,
"step": 1314
},
{
"epoch": 2.96,
"learning_rate": 0.00011277543688573506,
"loss": 3.987,
"step": 1317
},
{
"epoch": 2.97,
"learning_rate": 0.00011264721008260231,
"loss": 3.9692,
"step": 1320
},
{
"epoch": 2.97,
"learning_rate": 0.00011251941967268115,
"loss": 3.8917,
"step": 1323
},
{
"epoch": 2.98,
"learning_rate": 0.00011239206318628546,
"loss": 4.0324,
"step": 1326
},
{
"epoch": 2.99,
"learning_rate": 0.00011226513817325236,
"loss": 3.8372,
"step": 1329
},
{
"epoch": 2.99,
"learning_rate": 0.00011213864220274417,
"loss": 3.9239,
"step": 1332
},
{
"epoch": 3.0,
"learning_rate": 0.00011201257286305297,
"loss": 3.8253,
"step": 1335
},
{
"epoch": 3.0,
"step": 1335,
"total_flos": 1.849574515802112e+16,
"train_loss": 4.728262927737576,
"train_runtime": 4788.6915,
"train_samples_per_second": 17.847,
"train_steps_per_second": 0.279
}
],
"logging_steps": 3,
"max_steps": 1335,
"num_train_epochs": 3,
"save_steps": 100,
"total_flos": 1.849574515802112e+16,
"trial_name": null,
"trial_params": null
}