egor-letov / trainer_state.json
AlekseyKorshuk's picture
huggingartists
e355cf0
{
"best_metric": 1.4437962770462036,
"best_model_checkpoint": "output/egor-letov/checkpoint-1113",
"epoch": 7.0,
"global_step": 1113,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.03,
"learning_rate": 0.00013686550750800417,
"loss": 1.7651,
"step": 5
},
{
"epoch": 0.06,
"learning_rate": 0.00013586529199199337,
"loss": 1.744,
"step": 10
},
{
"epoch": 0.09,
"learning_rate": 0.00013420910752136943,
"loss": 1.6316,
"step": 15
},
{
"epoch": 0.13,
"learning_rate": 0.0001319131051535897,
"loss": 1.6707,
"step": 20
},
{
"epoch": 0.16,
"learning_rate": 0.0001289996754295761,
"loss": 1.6026,
"step": 25
},
{
"epoch": 0.19,
"learning_rate": 0.00012549723002188386,
"loss": 1.6338,
"step": 30
},
{
"epoch": 0.22,
"learning_rate": 0.00012143992466498807,
"loss": 1.592,
"step": 35
},
{
"epoch": 0.25,
"learning_rate": 0.00011686732606966479,
"loss": 1.6485,
"step": 40
},
{
"epoch": 0.28,
"learning_rate": 0.00011182402606970537,
"loss": 1.5618,
"step": 45
},
{
"epoch": 0.31,
"learning_rate": 0.00010635920676379414,
"loss": 1.639,
"step": 50
},
{
"epoch": 0.35,
"learning_rate": 0.00010052616089327038,
"loss": 1.616,
"step": 55
},
{
"epoch": 0.38,
"learning_rate": 9.438177213303676e-05,
"loss": 1.6779,
"step": 60
},
{
"epoch": 0.41,
"learning_rate": 8.798596036379876e-05,
"loss": 1.6006,
"step": 65
},
{
"epoch": 0.44,
"learning_rate": 8.140109733532407e-05,
"loss": 1.6413,
"step": 70
},
{
"epoch": 0.47,
"learning_rate": 7.469139841915332e-05,
"loss": 1.6066,
"step": 75
},
{
"epoch": 0.5,
"learning_rate": 6.792229638237148e-05,
"loss": 1.5749,
"step": 80
},
{
"epoch": 0.53,
"learning_rate": 6.11598032893766e-05,
"loss": 1.5668,
"step": 85
},
{
"epoch": 0.57,
"learning_rate": 5.446986675436074e-05,
"loss": 1.6693,
"step": 90
},
{
"epoch": 0.6,
"learning_rate": 4.7917726822305834e-05,
"loss": 1.5177,
"step": 95
},
{
"epoch": 0.63,
"learning_rate": 4.156727975017365e-05,
"loss": 1.5749,
"step": 100
},
{
"epoch": 0.66,
"learning_rate": 3.5480454892670955e-05,
"loss": 1.7175,
"step": 105
},
{
"epoch": 0.69,
"learning_rate": 2.9716610769183376e-05,
"loss": 1.5363,
"step": 110
},
{
"epoch": 0.72,
"learning_rate": 2.433195620141175e-05,
"loss": 1.5101,
"step": 115
},
{
"epoch": 0.75,
"learning_rate": 1.9379002166758904e-05,
"loss": 1.454,
"step": 120
},
{
"epoch": 0.79,
"learning_rate": 1.4906049712973773e-05,
"loss": 1.5586,
"step": 125
},
{
"epoch": 0.82,
"learning_rate": 1.0956718927894408e-05,
"loss": 1.5785,
"step": 130
},
{
"epoch": 0.85,
"learning_rate": 7.569523557760334e-06,
"loss": 1.542,
"step": 135
},
{
"epoch": 0.88,
"learning_rate": 4.777495422403531e-06,
"loss": 1.5961,
"step": 140
},
{
"epoch": 0.91,
"learning_rate": 2.607862290008129e-06,
"loss": 1.5725,
"step": 145
},
{
"epoch": 0.94,
"learning_rate": 1.0817823527948728e-06,
"loss": 1.5678,
"step": 150
},
{
"epoch": 0.97,
"learning_rate": 2.1413789301400542e-07,
"loss": 1.5592,
"step": 155
},
{
"epoch": 1.0,
"eval_loss": 1.5221866369247437,
"eval_runtime": 5.3885,
"eval_samples_per_second": 44.725,
"eval_steps_per_second": 5.753,
"step": 159
},
{
"epoch": 1.01,
"learning_rate": 1.339015140952895e-08,
"loss": 1.5752,
"step": 160
},
{
"epoch": 1.04,
"learning_rate": 4.814968134727319e-07,
"loss": 1.6004,
"step": 165
},
{
"epoch": 1.07,
"learning_rate": 1.6138929181565955e-06,
"loss": 1.6208,
"step": 170
},
{
"epoch": 1.1,
"learning_rate": 3.399535375228382e-06,
"loss": 1.5048,
"step": 175
},
{
"epoch": 1.13,
"learning_rate": 5.821010657128918e-06,
"loss": 1.5368,
"step": 180
},
{
"epoch": 1.16,
"learning_rate": 8.854704615130833e-06,
"loss": 1.4625,
"step": 185
},
{
"epoch": 1.19,
"learning_rate": 1.247103276375417e-05,
"loss": 1.5028,
"step": 190
},
{
"epoch": 1.23,
"learning_rate": 1.663472878771286e-05,
"loss": 1.5655,
"step": 195
},
{
"epoch": 1.26,
"learning_rate": 2.130518845788256e-05,
"loss": 1.6462,
"step": 200
},
{
"epoch": 1.29,
"learning_rate": 2.6436865602431155e-05,
"loss": 1.5009,
"step": 205
},
{
"epoch": 1.32,
"learning_rate": 3.197971627161538e-05,
"loss": 1.4222,
"step": 210
},
{
"epoch": 1.35,
"learning_rate": 3.7879686764761665e-05,
"loss": 1.4581,
"step": 215
},
{
"epoch": 1.38,
"learning_rate": 4.407924076020964e-05,
"loss": 1.5815,
"step": 220
},
{
"epoch": 1.42,
"learning_rate": 5.0517920407661895e-05,
"loss": 1.4586,
"step": 225
},
{
"epoch": 1.45,
"learning_rate": 5.713293591118741e-05,
"loss": 1.6639,
"step": 230
},
{
"epoch": 1.48,
"learning_rate": 6.385977785328257e-05,
"loss": 1.4835,
"step": 235
},
{
"epoch": 1.51,
"learning_rate": 7.063284628862755e-05,
"loss": 1.4511,
"step": 240
},
{
"epoch": 1.54,
"learning_rate": 7.738609047263356e-05,
"loss": 1.5574,
"step": 245
},
{
"epoch": 1.57,
"learning_rate": 8.405365298617052e-05,
"loss": 1.5211,
"step": 250
},
{
"epoch": 1.6,
"learning_rate": 9.057051197499065e-05,
"loss": 1.5923,
"step": 255
},
{
"epoch": 1.64,
"learning_rate": 9.687311524075133e-05,
"loss": 1.4926,
"step": 260
},
{
"epoch": 1.67,
"learning_rate": 0.00010289999999999994,
"loss": 1.5,
"step": 265
},
{
"epoch": 1.7,
"learning_rate": 0.00010859239226725281,
"loss": 1.6531,
"step": 270
},
{
"epoch": 1.73,
"learning_rate": 0.00011389478001700268,
"loss": 1.5839,
"step": 275
},
{
"epoch": 1.76,
"learning_rate": 0.0001187554545351989,
"loss": 1.5527,
"step": 280
},
{
"epoch": 1.79,
"learning_rate": 0.00012312701468095597,
"loss": 1.4811,
"step": 285
},
{
"epoch": 1.82,
"learning_rate": 0.0001269668291409485,
"loss": 1.6154,
"step": 290
},
{
"epoch": 1.86,
"learning_rate": 0.0001302374521686013,
"loss": 1.611,
"step": 295
},
{
"epoch": 1.89,
"learning_rate": 0.00013290698875380067,
"loss": 1.5892,
"step": 300
},
{
"epoch": 1.92,
"learning_rate": 0.0001349494056620028,
"loss": 1.4601,
"step": 305
},
{
"epoch": 1.95,
"learning_rate": 0.0001363447853094957,
"loss": 1.4863,
"step": 310
},
{
"epoch": 1.98,
"learning_rate": 0.00013707951999903243,
"loss": 1.5381,
"step": 315
},
{
"epoch": 2.0,
"eval_loss": 1.5293655395507812,
"eval_runtime": 5.7302,
"eval_samples_per_second": 42.058,
"eval_steps_per_second": 5.41,
"step": 318
},
{
"epoch": 2.01,
"learning_rate": 0.00013714644462165502,
"loss": 1.4756,
"step": 320
},
{
"epoch": 2.04,
"learning_rate": 0.00013654490653060552,
"loss": 1.538,
"step": 325
},
{
"epoch": 2.08,
"learning_rate": 0.00013528077190591619,
"loss": 1.4616,
"step": 330
},
{
"epoch": 2.11,
"learning_rate": 0.00013336636854761124,
"loss": 1.4735,
"step": 335
},
{
"epoch": 2.14,
"learning_rate": 0.00013082036565539916,
"loss": 1.3918,
"step": 340
},
{
"epoch": 2.17,
"learning_rate": 0.00012766759176724058,
"loss": 1.4803,
"step": 345
},
{
"epoch": 2.2,
"learning_rate": 0.00012393879263224768,
"loss": 1.6293,
"step": 350
},
{
"epoch": 2.23,
"learning_rate": 0.00011967033137913236,
"loss": 1.5226,
"step": 355
},
{
"epoch": 2.26,
"learning_rate": 0.00011490383390414918,
"loss": 1.5126,
"step": 360
},
{
"epoch": 2.3,
"learning_rate": 0.00010968578293670085,
"loss": 1.5304,
"step": 365
},
{
"epoch": 2.33,
"learning_rate": 0.00010406706474126147,
"loss": 1.4686,
"step": 370
},
{
"epoch": 2.36,
"learning_rate": 9.810247287616943e-05,
"loss": 1.4261,
"step": 375
},
{
"epoch": 2.39,
"learning_rate": 9.185017384861683e-05,
"loss": 1.4695,
"step": 380
},
{
"epoch": 2.42,
"learning_rate": 8.537113987675073e-05,
"loss": 1.4489,
"step": 385
},
{
"epoch": 2.45,
"learning_rate": 7.872855429057032e-05,
"loss": 1.5209,
"step": 390
},
{
"epoch": 2.48,
"learning_rate": 7.198719537013416e-05,
"loss": 1.4409,
"step": 395
},
{
"epoch": 2.52,
"learning_rate": 6.521280462986591e-05,
"loss": 1.4272,
"step": 400
},
{
"epoch": 2.55,
"learning_rate": 5.847144570942975e-05,
"loss": 1.4187,
"step": 405
},
{
"epoch": 2.58,
"learning_rate": 5.1828860123249337e-05,
"loss": 1.4412,
"step": 410
},
{
"epoch": 2.61,
"learning_rate": 4.5349826151383235e-05,
"loss": 1.536,
"step": 415
},
{
"epoch": 2.64,
"learning_rate": 3.909752712383064e-05,
"loss": 1.468,
"step": 420
},
{
"epoch": 2.67,
"learning_rate": 3.31329352587386e-05,
"loss": 1.4604,
"step": 425
},
{
"epoch": 2.7,
"learning_rate": 2.7514217063299194e-05,
"loss": 1.4515,
"step": 430
},
{
"epoch": 2.74,
"learning_rate": 2.229616609585087e-05,
"loss": 1.4215,
"step": 435
},
{
"epoch": 2.77,
"learning_rate": 1.7529668620867685e-05,
"loss": 1.4177,
"step": 440
},
{
"epoch": 2.8,
"learning_rate": 1.3261207367752373e-05,
"loss": 1.4707,
"step": 445
},
{
"epoch": 2.83,
"learning_rate": 9.53240823275947e-06,
"loss": 1.4591,
"step": 450
},
{
"epoch": 2.86,
"learning_rate": 6.379634344600892e-06,
"loss": 1.5216,
"step": 455
},
{
"epoch": 2.89,
"learning_rate": 3.833631452388783e-06,
"loss": 1.4972,
"step": 460
},
{
"epoch": 2.92,
"learning_rate": 1.919228094083838e-06,
"loss": 1.5209,
"step": 465
},
{
"epoch": 2.96,
"learning_rate": 6.550934693944858e-07,
"loss": 1.45,
"step": 470
},
{
"epoch": 2.99,
"learning_rate": 5.35553783449795e-08,
"loss": 1.4454,
"step": 475
},
{
"epoch": 3.0,
"eval_loss": 1.4749490022659302,
"eval_runtime": 5.7804,
"eval_samples_per_second": 41.693,
"eval_steps_per_second": 5.363,
"step": 477
},
{
"epoch": 3.02,
"learning_rate": 1.2048000096755528e-07,
"loss": 1.5049,
"step": 480
},
{
"epoch": 3.05,
"learning_rate": 8.552146905042678e-07,
"loss": 1.4016,
"step": 485
},
{
"epoch": 3.08,
"learning_rate": 2.2505943379971545e-06,
"loss": 1.4147,
"step": 490
},
{
"epoch": 3.11,
"learning_rate": 4.293011246199337e-06,
"loss": 1.3828,
"step": 495
},
{
"epoch": 3.14,
"learning_rate": 6.9625478313987545e-06,
"loss": 1.431,
"step": 500
},
{
"epoch": 3.18,
"learning_rate": 1.023317085905152e-05,
"loss": 1.4227,
"step": 505
},
{
"epoch": 3.21,
"learning_rate": 1.4072985319043966e-05,
"loss": 1.4611,
"step": 510
},
{
"epoch": 3.24,
"learning_rate": 1.8444545464801038e-05,
"loss": 1.3548,
"step": 515
},
{
"epoch": 3.27,
"learning_rate": 2.330521998299726e-05,
"loss": 1.4269,
"step": 520
},
{
"epoch": 3.3,
"learning_rate": 2.8607607732747138e-05,
"loss": 1.4122,
"step": 525
},
{
"epoch": 3.33,
"learning_rate": 3.429999999999989e-05,
"loss": 1.42,
"step": 530
},
{
"epoch": 3.36,
"learning_rate": 4.032688475924871e-05,
"loss": 1.388,
"step": 535
},
{
"epoch": 3.4,
"learning_rate": 4.66294880250094e-05,
"loss": 1.369,
"step": 540
},
{
"epoch": 3.43,
"learning_rate": 5.3146347013829526e-05,
"loss": 1.3512,
"step": 545
},
{
"epoch": 3.46,
"learning_rate": 5.981390952736637e-05,
"loss": 1.3807,
"step": 550
},
{
"epoch": 3.49,
"learning_rate": 6.656715371137237e-05,
"loss": 1.466,
"step": 555
},
{
"epoch": 3.52,
"learning_rate": 7.334022214671736e-05,
"loss": 1.3711,
"step": 560
},
{
"epoch": 3.55,
"learning_rate": 8.006706408881251e-05,
"loss": 1.3797,
"step": 565
},
{
"epoch": 3.58,
"learning_rate": 8.668207959233792e-05,
"loss": 1.413,
"step": 570
},
{
"epoch": 3.62,
"learning_rate": 9.312075923979041e-05,
"loss": 1.3859,
"step": 575
},
{
"epoch": 3.65,
"learning_rate": 9.932031323523837e-05,
"loss": 1.4853,
"step": 580
},
{
"epoch": 3.68,
"learning_rate": 0.00010522028372838466,
"loss": 1.3925,
"step": 585
},
{
"epoch": 3.71,
"learning_rate": 0.0001107631343975688,
"loss": 1.4442,
"step": 590
},
{
"epoch": 3.74,
"learning_rate": 0.00011589481154211739,
"loss": 1.5125,
"step": 595
},
{
"epoch": 3.77,
"learning_rate": 0.00012056527121228708,
"loss": 1.3964,
"step": 600
},
{
"epoch": 3.81,
"learning_rate": 0.0001247289672362458,
"loss": 1.4655,
"step": 605
},
{
"epoch": 3.84,
"learning_rate": 0.00012834529538486908,
"loss": 1.3898,
"step": 610
},
{
"epoch": 3.87,
"learning_rate": 0.00013137898934287108,
"loss": 1.4001,
"step": 615
},
{
"epoch": 3.9,
"learning_rate": 0.00013380046462477163,
"loss": 1.4248,
"step": 620
},
{
"epoch": 3.93,
"learning_rate": 0.0001355861070818434,
"loss": 1.3956,
"step": 625
},
{
"epoch": 3.96,
"learning_rate": 0.00013671850318652725,
"loss": 1.4704,
"step": 630
},
{
"epoch": 3.99,
"learning_rate": 0.0001371866098485905,
"loss": 1.4419,
"step": 635
},
{
"epoch": 4.0,
"eval_loss": 1.4980032444000244,
"eval_runtime": 5.8381,
"eval_samples_per_second": 41.28,
"eval_steps_per_second": 5.31,
"step": 636
},
{
"epoch": 4.03,
"learning_rate": 0.000136985862106986,
"loss": 1.3728,
"step": 640
},
{
"epoch": 4.06,
"learning_rate": 0.00013611821764720515,
"loss": 1.3237,
"step": 645
},
{
"epoch": 4.09,
"learning_rate": 0.00013459213770999185,
"loss": 1.3533,
"step": 650
},
{
"epoch": 4.12,
"learning_rate": 0.00013242250457759646,
"loss": 1.4508,
"step": 655
},
{
"epoch": 4.15,
"learning_rate": 0.00012963047644223966,
"loss": 1.4551,
"step": 660
},
{
"epoch": 4.18,
"learning_rate": 0.00012624328107210575,
"loss": 1.3913,
"step": 665
},
{
"epoch": 4.21,
"learning_rate": 0.00012229395028702628,
"loss": 1.3365,
"step": 670
},
{
"epoch": 4.25,
"learning_rate": 0.00011782099783324114,
"loss": 1.4044,
"step": 675
},
{
"epoch": 4.28,
"learning_rate": 0.00011286804379858831,
"loss": 1.3806,
"step": 680
},
{
"epoch": 4.31,
"learning_rate": 0.00010748338923081678,
"loss": 1.3692,
"step": 685
},
{
"epoch": 4.34,
"learning_rate": 0.00010171954510732902,
"loss": 1.3377,
"step": 690
},
{
"epoch": 4.37,
"learning_rate": 9.56327202498263e-05,
"loss": 1.3899,
"step": 695
},
{
"epoch": 4.4,
"learning_rate": 8.928227317769412e-05,
"loss": 1.3824,
"step": 700
},
{
"epoch": 4.43,
"learning_rate": 8.273013324563958e-05,
"loss": 1.3517,
"step": 705
},
{
"epoch": 4.47,
"learning_rate": 7.604019671062341e-05,
"loss": 1.3471,
"step": 710
},
{
"epoch": 4.5,
"learning_rate": 6.927770361762859e-05,
"loss": 1.363,
"step": 715
},
{
"epoch": 4.53,
"learning_rate": 6.250860158084675e-05,
"loss": 1.4238,
"step": 720
},
{
"epoch": 4.56,
"learning_rate": 5.5798902664676055e-05,
"loss": 1.3159,
"step": 725
},
{
"epoch": 4.59,
"learning_rate": 4.921403963620114e-05,
"loss": 1.3496,
"step": 730
},
{
"epoch": 4.62,
"learning_rate": 4.2818227866963195e-05,
"loss": 1.3717,
"step": 735
},
{
"epoch": 4.65,
"learning_rate": 3.667383910672979e-05,
"loss": 1.4263,
"step": 740
},
{
"epoch": 4.69,
"learning_rate": 3.084079323620607e-05,
"loss": 1.4238,
"step": 745
},
{
"epoch": 4.72,
"learning_rate": 2.537597393029464e-05,
"loss": 1.3789,
"step": 750
},
{
"epoch": 4.75,
"learning_rate": 2.0332673930335262e-05,
"loss": 1.2943,
"step": 755
},
{
"epoch": 4.78,
"learning_rate": 1.576007533501198e-05,
"loss": 1.4457,
"step": 760
},
{
"epoch": 4.81,
"learning_rate": 1.170276997811622e-05,
"loss": 1.3882,
"step": 765
},
{
"epoch": 4.84,
"learning_rate": 8.200324570423858e-06,
"loss": 1.3435,
"step": 770
},
{
"epoch": 4.87,
"learning_rate": 5.286894846410311e-06,
"loss": 1.3625,
"step": 775
},
{
"epoch": 4.91,
"learning_rate": 2.9908924786306224e-06,
"loss": 1.3336,
"step": 780
},
{
"epoch": 4.94,
"learning_rate": 1.3347080080066949e-06,
"loss": 1.3698,
"step": 785
},
{
"epoch": 4.97,
"learning_rate": 3.34492491995841e-07,
"loss": 1.3109,
"step": 790
},
{
"epoch": 5.0,
"learning_rate": 0.0,
"loss": 1.3807,
"step": 795
},
{
"epoch": 5.0,
"eval_loss": 1.4533822536468506,
"eval_runtime": 5.8855,
"eval_samples_per_second": 40.948,
"eval_steps_per_second": 5.267,
"step": 795
},
{
"epoch": 5.03,
"learning_rate": 3.3449249199583335e-07,
"loss": 1.2678,
"step": 800
},
{
"epoch": 5.06,
"learning_rate": 1.334708008006672e-06,
"loss": 1.2155,
"step": 805
},
{
"epoch": 5.09,
"learning_rate": 2.990892478630592e-06,
"loss": 1.265,
"step": 810
},
{
"epoch": 5.13,
"learning_rate": 5.286894846410265e-06,
"loss": 1.2533,
"step": 815
},
{
"epoch": 5.16,
"learning_rate": 8.200324570423804e-06,
"loss": 1.2628,
"step": 820
},
{
"epoch": 5.19,
"learning_rate": 1.1702769978116159e-05,
"loss": 1.321,
"step": 825
},
{
"epoch": 5.22,
"learning_rate": 1.5760075335011905e-05,
"loss": 1.3229,
"step": 830
},
{
"epoch": 5.25,
"learning_rate": 2.0332673930335177e-05,
"loss": 1.3257,
"step": 835
},
{
"epoch": 5.28,
"learning_rate": 2.537597393029455e-05,
"loss": 1.3373,
"step": 840
},
{
"epoch": 5.31,
"learning_rate": 3.0840793236205985e-05,
"loss": 1.2971,
"step": 845
},
{
"epoch": 5.35,
"learning_rate": 3.667383910672968e-05,
"loss": 1.1974,
"step": 850
},
{
"epoch": 5.38,
"learning_rate": 4.281822786696309e-05,
"loss": 1.3887,
"step": 855
},
{
"epoch": 5.41,
"learning_rate": 4.921403963620103e-05,
"loss": 1.3505,
"step": 860
},
{
"epoch": 5.44,
"learning_rate": 5.579890266467594e-05,
"loss": 1.319,
"step": 865
},
{
"epoch": 5.47,
"learning_rate": 6.250860158084664e-05,
"loss": 1.3255,
"step": 870
},
{
"epoch": 5.5,
"learning_rate": 6.927770361762848e-05,
"loss": 1.2311,
"step": 875
},
{
"epoch": 5.53,
"learning_rate": 7.604019671062329e-05,
"loss": 1.3552,
"step": 880
},
{
"epoch": 5.57,
"learning_rate": 8.273013324563947e-05,
"loss": 1.3885,
"step": 885
},
{
"epoch": 5.6,
"learning_rate": 8.928227317769401e-05,
"loss": 1.3314,
"step": 890
},
{
"epoch": 5.63,
"learning_rate": 9.563272024982619e-05,
"loss": 1.3202,
"step": 895
},
{
"epoch": 5.66,
"learning_rate": 0.00010171954510732891,
"loss": 1.3272,
"step": 900
},
{
"epoch": 5.69,
"learning_rate": 0.00010748338923081667,
"loss": 1.2248,
"step": 905
},
{
"epoch": 5.72,
"learning_rate": 0.00011286804379858823,
"loss": 1.3777,
"step": 910
},
{
"epoch": 5.75,
"learning_rate": 0.00011782099783324106,
"loss": 1.3051,
"step": 915
},
{
"epoch": 5.79,
"learning_rate": 0.0001222939502870262,
"loss": 1.3295,
"step": 920
},
{
"epoch": 5.82,
"learning_rate": 0.0001262432810721057,
"loss": 1.3102,
"step": 925
},
{
"epoch": 5.85,
"learning_rate": 0.00012963047644223957,
"loss": 1.409,
"step": 930
},
{
"epoch": 5.88,
"learning_rate": 0.0001324225045775964,
"loss": 1.3435,
"step": 935
},
{
"epoch": 5.91,
"learning_rate": 0.00013459213770999182,
"loss": 1.3775,
"step": 940
},
{
"epoch": 5.94,
"learning_rate": 0.00013611821764720515,
"loss": 1.3406,
"step": 945
},
{
"epoch": 5.97,
"learning_rate": 0.000136985862106986,
"loss": 1.4464,
"step": 950
},
{
"epoch": 6.0,
"eval_loss": 1.4797894954681396,
"eval_runtime": 5.9157,
"eval_samples_per_second": 40.739,
"eval_steps_per_second": 5.24,
"step": 954
},
{
"epoch": 6.01,
"learning_rate": 0.0001371866098485905,
"loss": 1.2626,
"step": 955
},
{
"epoch": 6.04,
"learning_rate": 0.00013671850318652725,
"loss": 1.2796,
"step": 960
},
{
"epoch": 6.07,
"learning_rate": 0.00013558610708184343,
"loss": 1.1514,
"step": 965
},
{
"epoch": 6.1,
"learning_rate": 0.00013380046462477168,
"loss": 1.3043,
"step": 970
},
{
"epoch": 6.13,
"learning_rate": 0.00013137898934287106,
"loss": 1.327,
"step": 975
},
{
"epoch": 6.16,
"learning_rate": 0.00012834529538486924,
"loss": 1.214,
"step": 980
},
{
"epoch": 6.19,
"learning_rate": 0.00012472896723624585,
"loss": 1.1638,
"step": 985
},
{
"epoch": 6.23,
"learning_rate": 0.00012056527121228703,
"loss": 1.3165,
"step": 990
},
{
"epoch": 6.26,
"learning_rate": 0.00011589481154211748,
"loss": 1.3327,
"step": 995
},
{
"epoch": 6.29,
"learning_rate": 0.00011076313439756889,
"loss": 1.3318,
"step": 1000
},
{
"epoch": 6.32,
"learning_rate": 0.00010522028372838475,
"loss": 1.3088,
"step": 1005
},
{
"epoch": 6.35,
"learning_rate": 9.932031323523849e-05,
"loss": 1.4023,
"step": 1010
},
{
"epoch": 6.38,
"learning_rate": 9.312075923979029e-05,
"loss": 1.2767,
"step": 1015
},
{
"epoch": 6.42,
"learning_rate": 8.668207959233826e-05,
"loss": 1.3357,
"step": 1020
},
{
"epoch": 6.45,
"learning_rate": 8.006706408881263e-05,
"loss": 1.2732,
"step": 1025
},
{
"epoch": 6.48,
"learning_rate": 7.334022214671723e-05,
"loss": 1.2055,
"step": 1030
},
{
"epoch": 6.51,
"learning_rate": 6.656715371137249e-05,
"loss": 1.3083,
"step": 1035
},
{
"epoch": 6.54,
"learning_rate": 5.981390952736648e-05,
"loss": 1.3757,
"step": 1040
},
{
"epoch": 6.57,
"learning_rate": 5.314634701382964e-05,
"loss": 1.2944,
"step": 1045
},
{
"epoch": 6.6,
"learning_rate": 4.66294880250095e-05,
"loss": 1.3276,
"step": 1050
},
{
"epoch": 6.64,
"learning_rate": 4.032688475924859e-05,
"loss": 1.2886,
"step": 1055
},
{
"epoch": 6.67,
"learning_rate": 3.4300000000000204e-05,
"loss": 1.2137,
"step": 1060
},
{
"epoch": 6.7,
"learning_rate": 2.8607607732747236e-05,
"loss": 1.2814,
"step": 1065
},
{
"epoch": 6.73,
"learning_rate": 2.3305219982997162e-05,
"loss": 1.2878,
"step": 1070
},
{
"epoch": 6.76,
"learning_rate": 1.844454546480112e-05,
"loss": 1.2616,
"step": 1075
},
{
"epoch": 6.79,
"learning_rate": 1.4072985319044034e-05,
"loss": 1.2864,
"step": 1080
},
{
"epoch": 6.82,
"learning_rate": 1.0233170859051581e-05,
"loss": 1.3714,
"step": 1085
},
{
"epoch": 6.86,
"learning_rate": 6.962547831398808e-06,
"loss": 1.2827,
"step": 1090
},
{
"epoch": 6.89,
"learning_rate": 4.293011246199291e-06,
"loss": 1.3028,
"step": 1095
},
{
"epoch": 6.92,
"learning_rate": 2.250594337997246e-06,
"loss": 1.2778,
"step": 1100
},
{
"epoch": 6.95,
"learning_rate": 8.552146905042907e-07,
"loss": 1.2184,
"step": 1105
},
{
"epoch": 6.98,
"learning_rate": 1.2048000096754006e-07,
"loss": 1.241,
"step": 1110
},
{
"epoch": 7.0,
"eval_loss": 1.4437962770462036,
"eval_runtime": 5.9385,
"eval_samples_per_second": 40.583,
"eval_steps_per_second": 5.22,
"step": 1113
}
],
"max_steps": 1908,
"num_train_epochs": 12,
"total_flos": 1163272126464000.0,
"trial_name": null,
"trial_params": null
}