mistral-10p / trainer_state.json
terry69's picture
Model save
68bd957 verified
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.9994869163673679,
"eval_steps": 500,
"global_step": 974,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0,
"grad_norm": 0.28735690720469315,
"learning_rate": 2.040816326530612e-06,
"loss": 0.8613,
"step": 1
},
{
"epoch": 0.01,
"grad_norm": 0.3167433972327598,
"learning_rate": 1.0204081632653061e-05,
"loss": 0.7893,
"step": 5
},
{
"epoch": 0.01,
"grad_norm": 0.2897093230208272,
"learning_rate": 2.0408163265306123e-05,
"loss": 0.8123,
"step": 10
},
{
"epoch": 0.02,
"grad_norm": 0.32529746878796306,
"learning_rate": 3.061224489795919e-05,
"loss": 0.8337,
"step": 15
},
{
"epoch": 0.02,
"grad_norm": 0.41596863358989566,
"learning_rate": 4.0816326530612245e-05,
"loss": 0.7853,
"step": 20
},
{
"epoch": 0.03,
"grad_norm": 0.24343841042790573,
"learning_rate": 5.102040816326531e-05,
"loss": 0.7278,
"step": 25
},
{
"epoch": 0.03,
"grad_norm": 0.23881432693463991,
"learning_rate": 6.122448979591838e-05,
"loss": 0.7748,
"step": 30
},
{
"epoch": 0.04,
"grad_norm": 0.26488823170135234,
"learning_rate": 7.142857142857143e-05,
"loss": 0.7369,
"step": 35
},
{
"epoch": 0.04,
"grad_norm": 0.2139946375583922,
"learning_rate": 8.163265306122449e-05,
"loss": 0.7414,
"step": 40
},
{
"epoch": 0.05,
"grad_norm": 0.21151116397910674,
"learning_rate": 9.183673469387756e-05,
"loss": 0.7377,
"step": 45
},
{
"epoch": 0.05,
"grad_norm": 0.22393538825183892,
"learning_rate": 0.00010204081632653062,
"loss": 0.7804,
"step": 50
},
{
"epoch": 0.06,
"grad_norm": 0.23672135676179382,
"learning_rate": 0.00011224489795918367,
"loss": 0.7587,
"step": 55
},
{
"epoch": 0.06,
"grad_norm": 0.19299901899888663,
"learning_rate": 0.00012244897959183676,
"loss": 0.7395,
"step": 60
},
{
"epoch": 0.07,
"grad_norm": 0.216886150554683,
"learning_rate": 0.0001326530612244898,
"loss": 0.7301,
"step": 65
},
{
"epoch": 0.07,
"grad_norm": 0.23673356651710506,
"learning_rate": 0.00014285714285714287,
"loss": 0.7038,
"step": 70
},
{
"epoch": 0.08,
"grad_norm": 0.24221298858964754,
"learning_rate": 0.0001530612244897959,
"loss": 0.7223,
"step": 75
},
{
"epoch": 0.08,
"grad_norm": 0.2281125789539668,
"learning_rate": 0.00016326530612244898,
"loss": 0.6883,
"step": 80
},
{
"epoch": 0.09,
"grad_norm": 0.20472032849324356,
"learning_rate": 0.00017346938775510205,
"loss": 0.7637,
"step": 85
},
{
"epoch": 0.09,
"grad_norm": 0.262981845017497,
"learning_rate": 0.00018367346938775512,
"loss": 0.7539,
"step": 90
},
{
"epoch": 0.1,
"grad_norm": 0.2045459660012419,
"learning_rate": 0.00019387755102040816,
"loss": 0.7145,
"step": 95
},
{
"epoch": 0.1,
"grad_norm": 0.19901520782139356,
"learning_rate": 0.0001999974277115551,
"loss": 0.746,
"step": 100
},
{
"epoch": 0.11,
"grad_norm": 0.20406293825215613,
"learning_rate": 0.00019996849098629418,
"loss": 0.6897,
"step": 105
},
{
"epoch": 0.11,
"grad_norm": 0.21959287502020255,
"learning_rate": 0.00019990741151022301,
"loss": 0.7047,
"step": 110
},
{
"epoch": 0.12,
"grad_norm": 0.2674905077734418,
"learning_rate": 0.0001998142089221534,
"loss": 0.7807,
"step": 115
},
{
"epoch": 0.12,
"grad_norm": 0.19121955233560559,
"learning_rate": 0.0001996889131894033,
"loss": 0.7405,
"step": 120
},
{
"epoch": 0.13,
"grad_norm": 0.2273017831695812,
"learning_rate": 0.00019953156459816179,
"loss": 0.7068,
"step": 125
},
{
"epoch": 0.13,
"grad_norm": 0.20355662352048876,
"learning_rate": 0.0001993422137405354,
"loss": 0.7405,
"step": 130
},
{
"epoch": 0.14,
"grad_norm": 0.20243555943079916,
"learning_rate": 0.00019912092149828174,
"loss": 0.77,
"step": 135
},
{
"epoch": 0.14,
"grad_norm": 0.2187163182490927,
"learning_rate": 0.00019886775902323405,
"loss": 0.7517,
"step": 140
},
{
"epoch": 0.15,
"grad_norm": 0.21898481894502772,
"learning_rate": 0.00019858280771442385,
"loss": 0.7449,
"step": 145
},
{
"epoch": 0.15,
"grad_norm": 0.2741369175466676,
"learning_rate": 0.00019826615919190887,
"loss": 0.7293,
"step": 150
},
{
"epoch": 0.16,
"grad_norm": 0.1963482017199379,
"learning_rate": 0.00019791791526731445,
"loss": 0.7338,
"step": 155
},
{
"epoch": 0.16,
"grad_norm": 0.2252716807662381,
"learning_rate": 0.00019753818791109828,
"loss": 0.7165,
"step": 160
},
{
"epoch": 0.17,
"grad_norm": 0.20760666448279344,
"learning_rate": 0.0001971270992165486,
"loss": 0.6738,
"step": 165
},
{
"epoch": 0.17,
"grad_norm": 0.20386126764416265,
"learning_rate": 0.00019668478136052774,
"loss": 0.6954,
"step": 170
},
{
"epoch": 0.18,
"grad_norm": 0.2044311112622246,
"learning_rate": 0.0001962113765609735,
"loss": 0.6905,
"step": 175
},
{
"epoch": 0.18,
"grad_norm": 0.19608231248059868,
"learning_rate": 0.0001957070370311717,
"loss": 0.7291,
"step": 180
},
{
"epoch": 0.19,
"grad_norm": 0.2344659008650863,
"learning_rate": 0.00019517192493081565,
"loss": 0.7213,
"step": 185
},
{
"epoch": 0.19,
"grad_norm": 0.2066414920484931,
"learning_rate": 0.00019460621231386676,
"loss": 0.7669,
"step": 190
},
{
"epoch": 0.2,
"grad_norm": 0.18973265779951576,
"learning_rate": 0.00019401008107323455,
"loss": 0.735,
"step": 195
},
{
"epoch": 0.21,
"grad_norm": 0.21253574311911852,
"learning_rate": 0.0001933837228822925,
"loss": 0.71,
"step": 200
},
{
"epoch": 0.21,
"grad_norm": 0.21426682728436638,
"learning_rate": 0.0001927273391332499,
"loss": 0.7394,
"step": 205
},
{
"epoch": 0.22,
"grad_norm": 0.19895817515454003,
"learning_rate": 0.00019204114087239806,
"loss": 0.7458,
"step": 210
},
{
"epoch": 0.22,
"grad_norm": 0.20302093776022942,
"learning_rate": 0.00019132534873225323,
"loss": 0.7314,
"step": 215
},
{
"epoch": 0.23,
"grad_norm": 0.2144349163303807,
"learning_rate": 0.00019058019286061665,
"loss": 0.7152,
"step": 220
},
{
"epoch": 0.23,
"grad_norm": 0.1971709726410862,
"learning_rate": 0.00018980591284657535,
"loss": 0.7365,
"step": 225
},
{
"epoch": 0.24,
"grad_norm": 0.22203472003740699,
"learning_rate": 0.00018900275764346768,
"loss": 0.7188,
"step": 230
},
{
"epoch": 0.24,
"grad_norm": 0.21934841651902945,
"learning_rate": 0.0001881709854888372,
"loss": 0.7107,
"step": 235
},
{
"epoch": 0.25,
"grad_norm": 0.1801668247807498,
"learning_rate": 0.00018731086382140226,
"loss": 0.725,
"step": 240
},
{
"epoch": 0.25,
"grad_norm": 0.21531423468010022,
"learning_rate": 0.00018642266919506644,
"loss": 0.728,
"step": 245
},
{
"epoch": 0.26,
"grad_norm": 0.22094698505169547,
"learning_rate": 0.00018550668718999872,
"loss": 0.6933,
"step": 250
},
{
"epoch": 0.26,
"grad_norm": 0.1773217147142517,
"learning_rate": 0.0001845632123208111,
"loss": 0.7513,
"step": 255
},
{
"epoch": 0.27,
"grad_norm": 0.2055315923802406,
"learning_rate": 0.0001835925479418637,
"loss": 0.7519,
"step": 260
},
{
"epoch": 0.27,
"grad_norm": 0.16963560799229266,
"learning_rate": 0.0001825950061497276,
"loss": 0.6841,
"step": 265
},
{
"epoch": 0.28,
"grad_norm": 0.22358671455728935,
"learning_rate": 0.00018157090768283678,
"loss": 0.7031,
"step": 270
},
{
"epoch": 0.28,
"grad_norm": 0.19649622034513511,
"learning_rate": 0.00018052058181836151,
"loss": 0.7152,
"step": 275
},
{
"epoch": 0.29,
"grad_norm": 0.23337948032120506,
"learning_rate": 0.00017944436626633623,
"loss": 0.7344,
"step": 280
},
{
"epoch": 0.29,
"grad_norm": 0.2230560456920727,
"learning_rate": 0.00017834260706107595,
"loss": 0.7048,
"step": 285
},
{
"epoch": 0.3,
"grad_norm": 0.18683201628360252,
"learning_rate": 0.00017721565844991643,
"loss": 0.6804,
"step": 290
},
{
"epoch": 0.3,
"grad_norm": 0.23557766421834736,
"learning_rate": 0.00017606388277931328,
"loss": 0.7466,
"step": 295
},
{
"epoch": 0.31,
"grad_norm": 0.20807682466726182,
"learning_rate": 0.0001748876503783373,
"loss": 0.7311,
"step": 300
},
{
"epoch": 0.31,
"grad_norm": 0.20735258362025547,
"learning_rate": 0.00017368733943960276,
"loss": 0.7272,
"step": 305
},
{
"epoch": 0.32,
"grad_norm": 0.20304702188871634,
"learning_rate": 0.00017246333589766787,
"loss": 0.745,
"step": 310
},
{
"epoch": 0.32,
"grad_norm": 0.20320219594683134,
"learning_rate": 0.00017121603330494544,
"loss": 0.7519,
"step": 315
},
{
"epoch": 0.33,
"grad_norm": 0.21213293638896646,
"learning_rate": 0.0001699458327051647,
"loss": 0.7359,
"step": 320
},
{
"epoch": 0.33,
"grad_norm": 0.21793747848007688,
"learning_rate": 0.00016865314250442398,
"loss": 0.7055,
"step": 325
},
{
"epoch": 0.34,
"grad_norm": 0.22141216826722213,
"learning_rate": 0.00016733837833987633,
"loss": 0.7037,
"step": 330
},
{
"epoch": 0.34,
"grad_norm": 0.22853984000819327,
"learning_rate": 0.00016600196294609045,
"loss": 0.7059,
"step": 335
},
{
"epoch": 0.35,
"grad_norm": 0.20663633655741356,
"learning_rate": 0.00016464432601912912,
"loss": 0.7177,
"step": 340
},
{
"epoch": 0.35,
"grad_norm": 0.18810130620976084,
"learning_rate": 0.0001632659040783897,
"loss": 0.7284,
"step": 345
},
{
"epoch": 0.36,
"grad_norm": 0.20429229628784093,
"learning_rate": 0.00016186714032625035,
"loss": 0.7408,
"step": 350
},
{
"epoch": 0.36,
"grad_norm": 0.22545843123823847,
"learning_rate": 0.00016044848450556787,
"loss": 0.7167,
"step": 355
},
{
"epoch": 0.37,
"grad_norm": 0.20814059355174414,
"learning_rate": 0.00015901039275507245,
"loss": 0.7119,
"step": 360
},
{
"epoch": 0.37,
"grad_norm": 0.20573234266098542,
"learning_rate": 0.00015755332746270572,
"loss": 0.7023,
"step": 365
},
{
"epoch": 0.38,
"grad_norm": 0.22027836397935158,
"learning_rate": 0.00015607775711694977,
"loss": 0.7145,
"step": 370
},
{
"epoch": 0.38,
"grad_norm": 0.23097511819867636,
"learning_rate": 0.00015458415615619484,
"loss": 0.7037,
"step": 375
},
{
"epoch": 0.39,
"grad_norm": 0.18436146046862298,
"learning_rate": 0.00015307300481619333,
"loss": 0.7419,
"step": 380
},
{
"epoch": 0.4,
"grad_norm": 0.21587522416498928,
"learning_rate": 0.00015154478897565045,
"loss": 0.76,
"step": 385
},
{
"epoch": 0.4,
"grad_norm": 0.18717033363542637,
"learning_rate": 0.00015000000000000001,
"loss": 0.7144,
"step": 390
},
{
"epoch": 0.41,
"grad_norm": 0.20860152567696305,
"learning_rate": 0.00014843913458341645,
"loss": 0.6931,
"step": 395
},
{
"epoch": 0.41,
"grad_norm": 0.23965643462280595,
"learning_rate": 0.00014686269458911332,
"loss": 0.7057,
"step": 400
},
{
"epoch": 0.42,
"grad_norm": 0.20436937033016242,
"learning_rate": 0.00014527118688797963,
"loss": 0.7508,
"step": 405
},
{
"epoch": 0.42,
"grad_norm": 0.23533937009710554,
"learning_rate": 0.0001436651231956064,
"loss": 0.7168,
"step": 410
},
{
"epoch": 0.43,
"grad_norm": 0.22180461462318066,
"learning_rate": 0.00014204501990775533,
"loss": 0.7335,
"step": 415
},
{
"epoch": 0.43,
"grad_norm": 0.1996738235990708,
"learning_rate": 0.00014041139793432274,
"loss": 0.7162,
"step": 420
},
{
"epoch": 0.44,
"grad_norm": 0.21103614768476256,
"learning_rate": 0.00013876478253185183,
"loss": 0.7331,
"step": 425
},
{
"epoch": 0.44,
"grad_norm": 0.22289372370077495,
"learning_rate": 0.00013710570313464778,
"loss": 0.7044,
"step": 430
},
{
"epoch": 0.45,
"grad_norm": 0.229537262499816,
"learning_rate": 0.0001354346931845492,
"loss": 0.75,
"step": 435
},
{
"epoch": 0.45,
"grad_norm": 0.19323768910419992,
"learning_rate": 0.00013375228995941133,
"loss": 0.7351,
"step": 440
},
{
"epoch": 0.46,
"grad_norm": 0.2047265000452632,
"learning_rate": 0.0001320590344003557,
"loss": 0.7332,
"step": 445
},
{
"epoch": 0.46,
"grad_norm": 0.21689200679001508,
"learning_rate": 0.00013035547093784186,
"loss": 0.7193,
"step": 450
},
{
"epoch": 0.47,
"grad_norm": 0.18177975055261658,
"learning_rate": 0.00012864214731661742,
"loss": 0.7062,
"step": 455
},
{
"epoch": 0.47,
"grad_norm": 0.22823965854179848,
"learning_rate": 0.00012691961441960238,
"loss": 0.6943,
"step": 460
},
{
"epoch": 0.48,
"grad_norm": 0.19970723650312586,
"learning_rate": 0.00012518842609076413,
"loss": 0.7188,
"step": 465
},
{
"epoch": 0.48,
"grad_norm": 0.21665273924724815,
"learning_rate": 0.00012344913895704097,
"loss": 0.7296,
"step": 470
},
{
"epoch": 0.49,
"grad_norm": 0.20693546255073467,
"learning_rate": 0.00012170231224937032,
"loss": 0.7084,
"step": 475
},
{
"epoch": 0.49,
"grad_norm": 0.2230052437580283,
"learning_rate": 0.00011994850762287989,
"loss": 0.7286,
"step": 480
},
{
"epoch": 0.5,
"grad_norm": 0.20642193075079962,
"learning_rate": 0.0001181882889762994,
"loss": 0.739,
"step": 485
},
{
"epoch": 0.5,
"grad_norm": 0.19372424148062226,
"learning_rate": 0.00011642222227065089,
"loss": 0.7072,
"step": 490
},
{
"epoch": 0.51,
"grad_norm": 0.23927300164054763,
"learning_rate": 0.00011465087534727587,
"loss": 0.779,
"step": 495
},
{
"epoch": 0.51,
"grad_norm": 0.2284386096464582,
"learning_rate": 0.0001128748177452581,
"loss": 0.7125,
"step": 500
},
{
"epoch": 0.52,
"grad_norm": 0.1914737248165551,
"learning_rate": 0.00011109462051830017,
"loss": 0.7672,
"step": 505
},
{
"epoch": 0.52,
"grad_norm": 0.19448312525913036,
"learning_rate": 0.00010931085605111354,
"loss": 0.6975,
"step": 510
},
{
"epoch": 0.53,
"grad_norm": 0.21441915676709558,
"learning_rate": 0.00010752409787538,
"loss": 0.7269,
"step": 515
},
{
"epoch": 0.53,
"grad_norm": 0.19881919454925634,
"learning_rate": 0.00010573492048534515,
"loss": 0.6814,
"step": 520
},
{
"epoch": 0.54,
"grad_norm": 0.19972824907153813,
"learning_rate": 0.00010394389915310149,
"loss": 0.68,
"step": 525
},
{
"epoch": 0.54,
"grad_norm": 0.2406076929176273,
"learning_rate": 0.00010215160974362223,
"loss": 0.7707,
"step": 530
},
{
"epoch": 0.55,
"grad_norm": 0.20777439386702035,
"learning_rate": 0.00010035862852960387,
"loss": 0.7491,
"step": 535
},
{
"epoch": 0.55,
"grad_norm": 0.24747809376637386,
"learning_rate": 9.856553200617805e-05,
"loss": 0.6889,
"step": 540
},
{
"epoch": 0.56,
"grad_norm": 0.20716823780350135,
"learning_rate": 9.677289670555169e-05,
"loss": 0.7247,
"step": 545
},
{
"epoch": 0.56,
"grad_norm": 0.1991885456295323,
"learning_rate": 9.49812990116353e-05,
"loss": 0.7411,
"step": 550
},
{
"epoch": 0.57,
"grad_norm": 0.20535559514249033,
"learning_rate": 9.319131497471894e-05,
"loss": 0.75,
"step": 555
},
{
"epoch": 0.57,
"grad_norm": 0.18612767193322602,
"learning_rate": 9.140352012625537e-05,
"loss": 0.7214,
"step": 560
},
{
"epoch": 0.58,
"grad_norm": 0.21568066556853366,
"learning_rate": 8.961848929381026e-05,
"loss": 0.7378,
"step": 565
},
{
"epoch": 0.58,
"grad_norm": 0.20352009266326396,
"learning_rate": 8.783679641623845e-05,
"loss": 0.7332,
"step": 570
},
{
"epoch": 0.59,
"grad_norm": 0.23303296784518934,
"learning_rate": 8.605901435914607e-05,
"loss": 0.7005,
"step": 575
},
{
"epoch": 0.6,
"grad_norm": 0.19779884278017262,
"learning_rate": 8.428571473069775e-05,
"loss": 0.7281,
"step": 580
},
{
"epoch": 0.6,
"grad_norm": 0.23013073874335851,
"learning_rate": 8.25174676978282e-05,
"loss": 0.6749,
"step": 585
},
{
"epoch": 0.61,
"grad_norm": 0.2248906461637265,
"learning_rate": 8.075484180291701e-05,
"loss": 0.6938,
"step": 590
},
{
"epoch": 0.61,
"grad_norm": 0.18810582346079818,
"learning_rate": 7.899840378098588e-05,
"loss": 0.7388,
"step": 595
},
{
"epoch": 0.62,
"grad_norm": 0.20884410793300284,
"learning_rate": 7.724871837747707e-05,
"loss": 0.7373,
"step": 600
},
{
"epoch": 0.62,
"grad_norm": 0.2166745910351328,
"learning_rate": 7.550634816667142e-05,
"loss": 0.6979,
"step": 605
},
{
"epoch": 0.63,
"grad_norm": 0.24100998404487434,
"learning_rate": 7.377185337080442e-05,
"loss": 0.7076,
"step": 610
},
{
"epoch": 0.63,
"grad_norm": 0.2256882455993147,
"learning_rate": 7.204579167993881e-05,
"loss": 0.731,
"step": 615
},
{
"epoch": 0.64,
"grad_norm": 0.18574834794500147,
"learning_rate": 7.032871807265096e-05,
"loss": 0.7473,
"step": 620
},
{
"epoch": 0.64,
"grad_norm": 0.19595704844512632,
"learning_rate": 6.862118463758943e-05,
"loss": 0.7123,
"step": 625
},
{
"epoch": 0.65,
"grad_norm": 0.1922152988123935,
"learning_rate": 6.69237403959624e-05,
"loss": 0.7155,
"step": 630
},
{
"epoch": 0.65,
"grad_norm": 0.22349381871955526,
"learning_rate": 6.52369311250116e-05,
"loss": 0.6986,
"step": 635
},
{
"epoch": 0.66,
"grad_norm": 0.1860191514854131,
"learning_rate": 6.356129918252927e-05,
"loss": 0.7194,
"step": 640
},
{
"epoch": 0.66,
"grad_norm": 0.21287065828060023,
"learning_rate": 6.189738333247432e-05,
"loss": 0.6888,
"step": 645
},
{
"epoch": 0.67,
"grad_norm": 0.21736641037698234,
"learning_rate": 6.024571857174443e-05,
"loss": 0.74,
"step": 650
},
{
"epoch": 0.67,
"grad_norm": 0.2161329163446709,
"learning_rate": 5.860683595815893e-05,
"loss": 0.6949,
"step": 655
},
{
"epoch": 0.68,
"grad_norm": 0.19032361730874883,
"learning_rate": 5.698126243970845e-05,
"loss": 0.7027,
"step": 660
},
{
"epoch": 0.68,
"grad_norm": 0.20020919043570076,
"learning_rate": 5.536952068512608e-05,
"loss": 0.7079,
"step": 665
},
{
"epoch": 0.69,
"grad_norm": 0.19493600127593236,
"learning_rate": 5.3772128915834184e-05,
"loss": 0.7946,
"step": 670
},
{
"epoch": 0.69,
"grad_norm": 0.1937560205349817,
"learning_rate": 5.218960073932122e-05,
"loss": 0.7512,
"step": 675
},
{
"epoch": 0.7,
"grad_norm": 0.20929045061919116,
"learning_rate": 5.062244498400228e-05,
"loss": 0.7401,
"step": 680
},
{
"epoch": 0.7,
"grad_norm": 0.19822387763869162,
"learning_rate": 4.907116553561607e-05,
"loss": 0.7035,
"step": 685
},
{
"epoch": 0.71,
"grad_norm": 0.18973790696605586,
"learning_rate": 4.753626117521103e-05,
"loss": 0.6855,
"step": 690
},
{
"epoch": 0.71,
"grad_norm": 0.1951787661520754,
"learning_rate": 4.601822541877291e-05,
"loss": 0.697,
"step": 695
},
{
"epoch": 0.72,
"grad_norm": 0.23171207370747388,
"learning_rate": 4.451754635854517e-05,
"loss": 0.7174,
"step": 700
},
{
"epoch": 0.72,
"grad_norm": 0.20672883919318008,
"learning_rate": 4.303470650609325e-05,
"loss": 0.6991,
"step": 705
},
{
"epoch": 0.73,
"grad_norm": 0.20596139821563042,
"learning_rate": 4.1570182637163155e-05,
"loss": 0.7579,
"step": 710
},
{
"epoch": 0.73,
"grad_norm": 0.21052057640954702,
"learning_rate": 4.0124445638384366e-05,
"loss": 0.6564,
"step": 715
},
{
"epoch": 0.74,
"grad_norm": 0.2194425673779361,
"learning_rate": 3.869796035586625e-05,
"loss": 0.7112,
"step": 720
},
{
"epoch": 0.74,
"grad_norm": 0.18864013157813014,
"learning_rate": 3.7291185445736444e-05,
"loss": 0.7009,
"step": 725
},
{
"epoch": 0.75,
"grad_norm": 0.20033201942780526,
"learning_rate": 3.590457322666997e-05,
"loss": 0.7412,
"step": 730
},
{
"epoch": 0.75,
"grad_norm": 0.21557678658312107,
"learning_rate": 3.453856953445557e-05,
"loss": 0.7384,
"step": 735
},
{
"epoch": 0.76,
"grad_norm": 0.1793703740528382,
"learning_rate": 3.319361357864663e-05,
"loss": 0.7098,
"step": 740
},
{
"epoch": 0.76,
"grad_norm": 0.1804784138992169,
"learning_rate": 3.187013780134291e-05,
"loss": 0.7287,
"step": 745
},
{
"epoch": 0.77,
"grad_norm": 0.1868508163249596,
"learning_rate": 3.05685677381475e-05,
"loss": 0.7472,
"step": 750
},
{
"epoch": 0.77,
"grad_norm": 0.21833090239816652,
"learning_rate": 2.9289321881345254e-05,
"loss": 0.7121,
"step": 755
},
{
"epoch": 0.78,
"grad_norm": 0.22900968128450175,
"learning_rate": 2.8032811545345294e-05,
"loss": 0.7631,
"step": 760
},
{
"epoch": 0.79,
"grad_norm": 0.25207875961572096,
"learning_rate": 2.679944073443158e-05,
"loss": 0.717,
"step": 765
},
{
"epoch": 0.79,
"grad_norm": 0.21435265220399202,
"learning_rate": 2.5589606012863963e-05,
"loss": 0.7391,
"step": 770
},
{
"epoch": 0.8,
"grad_norm": 0.21363241574566763,
"learning_rate": 2.4403696377371142e-05,
"loss": 0.7446,
"step": 775
},
{
"epoch": 0.8,
"grad_norm": 0.20585815945916697,
"learning_rate": 2.324209313207736e-05,
"loss": 0.7582,
"step": 780
},
{
"epoch": 0.81,
"grad_norm": 0.20004345669038107,
"learning_rate": 2.210516976590179e-05,
"loss": 0.7302,
"step": 785
},
{
"epoch": 0.81,
"grad_norm": 0.22895803213623186,
"learning_rate": 2.099329183247126e-05,
"loss": 0.7175,
"step": 790
},
{
"epoch": 0.82,
"grad_norm": 0.19029034354303137,
"learning_rate": 1.9906816832584253e-05,
"loss": 0.6968,
"step": 795
},
{
"epoch": 0.82,
"grad_norm": 0.18984158225134234,
"learning_rate": 1.8846094099263912e-05,
"loss": 0.7259,
"step": 800
},
{
"epoch": 0.83,
"grad_norm": 0.20694620466818364,
"learning_rate": 1.781146468543765e-05,
"loss": 0.6664,
"step": 805
},
{
"epoch": 0.83,
"grad_norm": 0.1880785385367806,
"learning_rate": 1.6803261254278636e-05,
"loss": 0.6995,
"step": 810
},
{
"epoch": 0.84,
"grad_norm": 0.23959056489828764,
"learning_rate": 1.582180797224507e-05,
"loss": 0.7076,
"step": 815
},
{
"epoch": 0.84,
"grad_norm": 0.2074947617084518,
"learning_rate": 1.4867420404851307e-05,
"loss": 0.7257,
"step": 820
},
{
"epoch": 0.85,
"grad_norm": 0.1697947347606707,
"learning_rate": 1.3940405415204416e-05,
"loss": 0.729,
"step": 825
},
{
"epoch": 0.85,
"grad_norm": 0.19240120017654297,
"learning_rate": 1.30410610653389e-05,
"loss": 0.7579,
"step": 830
},
{
"epoch": 0.86,
"grad_norm": 0.22247780509078305,
"learning_rate": 1.2169676520381168e-05,
"loss": 0.7197,
"step": 835
},
{
"epoch": 0.86,
"grad_norm": 0.2186893700102881,
"learning_rate": 1.1326531955574526e-05,
"loss": 0.7392,
"step": 840
},
{
"epoch": 0.87,
"grad_norm": 0.19758258278741933,
"learning_rate": 1.0511898466194903e-05,
"loss": 0.7161,
"step": 845
},
{
"epoch": 0.87,
"grad_norm": 0.1935470586238971,
"learning_rate": 9.726037980385738e-06,
"loss": 0.6866,
"step": 850
},
{
"epoch": 0.88,
"grad_norm": 0.20632207102948852,
"learning_rate": 8.969203174940654e-06,
"loss": 0.7005,
"step": 855
},
{
"epoch": 0.88,
"grad_norm": 0.1864625802291902,
"learning_rate": 8.24163739406062e-06,
"loss": 0.7332,
"step": 860
},
{
"epoch": 0.89,
"grad_norm": 0.1856036197326992,
"learning_rate": 7.543574571111655e-06,
"loss": 0.7387,
"step": 865
},
{
"epoch": 0.89,
"grad_norm": 0.21017043077001935,
"learning_rate": 6.875239153408542e-06,
"loss": 0.6983,
"step": 870
},
{
"epoch": 0.9,
"grad_norm": 0.22653212036464043,
"learning_rate": 6.236846030048604e-06,
"loss": 0.7,
"step": 875
},
{
"epoch": 0.9,
"grad_norm": 0.1799402029152891,
"learning_rate": 5.6286004628186675e-06,
"loss": 0.7291,
"step": 880
},
{
"epoch": 0.91,
"grad_norm": 0.20533686230996426,
"learning_rate": 5.0506980201973974e-06,
"loss": 0.7303,
"step": 885
},
{
"epoch": 0.91,
"grad_norm": 0.20499691124412314,
"learning_rate": 4.503324514474483e-06,
"loss": 0.7543,
"step": 890
},
{
"epoch": 0.92,
"grad_norm": 0.20195822302653685,
"learning_rate": 3.986655942006579e-06,
"loss": 0.7246,
"step": 895
},
{
"epoch": 0.92,
"grad_norm": 0.23109568891518523,
"learning_rate": 3.5008584266294386e-06,
"loss": 0.7003,
"step": 900
},
{
"epoch": 0.93,
"grad_norm": 0.2213682915194419,
"learning_rate": 3.0460881662442763e-06,
"loss": 0.7511,
"step": 905
},
{
"epoch": 0.93,
"grad_norm": 0.21218423218406246,
"learning_rate": 2.622491382595693e-06,
"loss": 0.7221,
"step": 910
},
{
"epoch": 0.94,
"grad_norm": 0.21119477478168394,
"learning_rate": 2.2302042742571193e-06,
"loss": 0.7139,
"step": 915
},
{
"epoch": 0.94,
"grad_norm": 0.19455625533472815,
"learning_rate": 1.869352972839067e-06,
"loss": 0.7059,
"step": 920
},
{
"epoch": 0.95,
"grad_norm": 0.2364635036372563,
"learning_rate": 1.5400535024342022e-06,
"loss": 0.6871,
"step": 925
},
{
"epoch": 0.95,
"grad_norm": 0.23010554295931945,
"learning_rate": 1.2424117423122328e-06,
"loss": 0.7364,
"step": 930
},
{
"epoch": 0.96,
"grad_norm": 0.18952563182659934,
"learning_rate": 9.765233928766493e-07,
"loss": 0.7058,
"step": 935
},
{
"epoch": 0.96,
"grad_norm": 0.21828660241676695,
"learning_rate": 7.42473944894384e-07,
"loss": 0.6962,
"step": 940
},
{
"epoch": 0.97,
"grad_norm": 0.18672947784161634,
"learning_rate": 5.403386520079323e-07,
"loss": 0.6808,
"step": 945
},
{
"epoch": 0.97,
"grad_norm": 0.1911360941907681,
"learning_rate": 3.701825065392184e-07,
"loss": 0.7428,
"step": 950
},
{
"epoch": 0.98,
"grad_norm": 0.18259404077794916,
"learning_rate": 2.320602185927001e-07,
"loss": 0.6799,
"step": 955
},
{
"epoch": 0.99,
"grad_norm": 0.20002215130980527,
"learning_rate": 1.2601619846444035e-07,
"loss": 0.7611,
"step": 960
},
{
"epoch": 0.99,
"grad_norm": 0.19193385733473736,
"learning_rate": 5.208454236296234e-08,
"loss": 0.7183,
"step": 965
},
{
"epoch": 1.0,
"grad_norm": 0.22837515366442288,
"learning_rate": 1.0289021446308056e-08,
"loss": 0.7474,
"step": 970
},
{
"epoch": 1.0,
"eval_loss": NaN,
"eval_runtime": 1509.2466,
"eval_samples_per_second": 1.531,
"eval_steps_per_second": 0.383,
"step": 974
},
{
"epoch": 1.0,
"step": 974,
"total_flos": 1.1274999981146112e+16,
"train_loss": 0.7250666028420294,
"train_runtime": 36380.3803,
"train_samples_per_second": 1.714,
"train_steps_per_second": 0.027
}
],
"logging_steps": 5,
"max_steps": 974,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 100,
"total_flos": 1.1274999981146112e+16,
"train_batch_size": 8,
"trial_name": null,
"trial_params": null
}