CooperW's picture
Training in progress, step 100, checkpoint
57dd742 verified
raw
history blame
18 kB
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.07581141909500118,
"eval_steps": 500,
"global_step": 100,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0007581141909500118,
"grad_norm": 1.77621328830719,
"learning_rate": 2e-05,
"loss": 1.4596,
"step": 1
},
{
"epoch": 0.0015162283819000236,
"grad_norm": 1.7604256868362427,
"learning_rate": 4e-05,
"loss": 1.4375,
"step": 2
},
{
"epoch": 0.0022743425728500356,
"grad_norm": 0.8544202446937561,
"learning_rate": 6e-05,
"loss": 1.3992,
"step": 3
},
{
"epoch": 0.0030324567638000473,
"grad_norm": 0.7290700078010559,
"learning_rate": 8e-05,
"loss": 1.2861,
"step": 4
},
{
"epoch": 0.0037905709547500594,
"grad_norm": 0.6216087341308594,
"learning_rate": 0.0001,
"loss": 1.1906,
"step": 5
},
{
"epoch": 0.004548685145700071,
"grad_norm": 0.6320084929466248,
"learning_rate": 0.00012,
"loss": 1.0423,
"step": 6
},
{
"epoch": 0.005306799336650083,
"grad_norm": 0.620789110660553,
"learning_rate": 0.00014,
"loss": 0.8656,
"step": 7
},
{
"epoch": 0.006064913527600095,
"grad_norm": 0.509087085723877,
"learning_rate": 0.00016,
"loss": 0.6594,
"step": 8
},
{
"epoch": 0.006823027718550106,
"grad_norm": 1.0617144107818604,
"learning_rate": 0.00018,
"loss": 0.5612,
"step": 9
},
{
"epoch": 0.007581141909500119,
"grad_norm": 0.43339547514915466,
"learning_rate": 0.0002,
"loss": 0.3805,
"step": 10
},
{
"epoch": 0.00833925610045013,
"grad_norm": 0.4575250744819641,
"learning_rate": 0.0001999390827019096,
"loss": 0.3066,
"step": 11
},
{
"epoch": 0.009097370291400142,
"grad_norm": 0.3520224392414093,
"learning_rate": 0.00019975640502598244,
"loss": 0.2506,
"step": 12
},
{
"epoch": 0.009855484482350154,
"grad_norm": 0.13390159606933594,
"learning_rate": 0.00019945218953682734,
"loss": 0.2106,
"step": 13
},
{
"epoch": 0.010613598673300166,
"grad_norm": 0.13238006830215454,
"learning_rate": 0.00019902680687415705,
"loss": 0.2027,
"step": 14
},
{
"epoch": 0.011371712864250177,
"grad_norm": 0.1745949536561966,
"learning_rate": 0.00019848077530122083,
"loss": 0.178,
"step": 15
},
{
"epoch": 0.01212982705520019,
"grad_norm": 0.1583506315946579,
"learning_rate": 0.00019781476007338058,
"loss": 0.1865,
"step": 16
},
{
"epoch": 0.012887941246150201,
"grad_norm": 0.10310098528862,
"learning_rate": 0.00019702957262759965,
"loss": 0.1722,
"step": 17
},
{
"epoch": 0.013646055437100213,
"grad_norm": 0.08868539333343506,
"learning_rate": 0.0001961261695938319,
"loss": 0.1685,
"step": 18
},
{
"epoch": 0.014404169628050224,
"grad_norm": 0.06325000524520874,
"learning_rate": 0.00019510565162951537,
"loss": 0.1596,
"step": 19
},
{
"epoch": 0.015162283819000238,
"grad_norm": 0.07059483975172043,
"learning_rate": 0.00019396926207859084,
"loss": 0.1617,
"step": 20
},
{
"epoch": 0.015920398009950248,
"grad_norm": 0.067365363240242,
"learning_rate": 0.00019271838545667876,
"loss": 0.1517,
"step": 21
},
{
"epoch": 0.01667851220090026,
"grad_norm": 0.07025124877691269,
"learning_rate": 0.0001913545457642601,
"loss": 0.1639,
"step": 22
},
{
"epoch": 0.01743662639185027,
"grad_norm": 0.06402155756950378,
"learning_rate": 0.0001898794046299167,
"loss": 0.1505,
"step": 23
},
{
"epoch": 0.018194740582800285,
"grad_norm": 0.074811652302742,
"learning_rate": 0.00018829475928589271,
"loss": 0.1481,
"step": 24
},
{
"epoch": 0.018952854773750295,
"grad_norm": 0.07151901721954346,
"learning_rate": 0.00018660254037844388,
"loss": 0.1595,
"step": 25
},
{
"epoch": 0.019710968964700308,
"grad_norm": 0.06124258041381836,
"learning_rate": 0.0001848048096156426,
"loss": 0.146,
"step": 26
},
{
"epoch": 0.02046908315565032,
"grad_norm": 0.06529385596513748,
"learning_rate": 0.00018290375725550417,
"loss": 0.1358,
"step": 27
},
{
"epoch": 0.02122719734660033,
"grad_norm": 0.060589537024497986,
"learning_rate": 0.00018090169943749476,
"loss": 0.1424,
"step": 28
},
{
"epoch": 0.021985311537550345,
"grad_norm": 0.06462966650724411,
"learning_rate": 0.00017880107536067218,
"loss": 0.1393,
"step": 29
},
{
"epoch": 0.022743425728500355,
"grad_norm": 0.06316369026899338,
"learning_rate": 0.0001766044443118978,
"loss": 0.1221,
"step": 30
},
{
"epoch": 0.02350153991945037,
"grad_norm": 0.06809717416763306,
"learning_rate": 0.00017431448254773944,
"loss": 0.1295,
"step": 31
},
{
"epoch": 0.02425965411040038,
"grad_norm": 0.055948369204998016,
"learning_rate": 0.0001719339800338651,
"loss": 0.1316,
"step": 32
},
{
"epoch": 0.025017768301350392,
"grad_norm": 0.06291463971138,
"learning_rate": 0.00016946583704589973,
"loss": 0.113,
"step": 33
},
{
"epoch": 0.025775882492300402,
"grad_norm": 0.06223299354314804,
"learning_rate": 0.00016691306063588583,
"loss": 0.1208,
"step": 34
},
{
"epoch": 0.026533996683250415,
"grad_norm": 0.06080786883831024,
"learning_rate": 0.00016427876096865394,
"loss": 0.1167,
"step": 35
},
{
"epoch": 0.027292110874200425,
"grad_norm": 0.052656594663858414,
"learning_rate": 0.0001615661475325658,
"loss": 0.1205,
"step": 36
},
{
"epoch": 0.02805022506515044,
"grad_norm": 0.05521203577518463,
"learning_rate": 0.00015877852522924732,
"loss": 0.1292,
"step": 37
},
{
"epoch": 0.02880833925610045,
"grad_norm": 0.0701892152428627,
"learning_rate": 0.0001559192903470747,
"loss": 0.1186,
"step": 38
},
{
"epoch": 0.029566453447050462,
"grad_norm": 0.06418278068304062,
"learning_rate": 0.0001529919264233205,
"loss": 0.1193,
"step": 39
},
{
"epoch": 0.030324567638000476,
"grad_norm": 0.0714295357465744,
"learning_rate": 0.00015000000000000001,
"loss": 0.1225,
"step": 40
},
{
"epoch": 0.031082681828950486,
"grad_norm": 0.05452275648713112,
"learning_rate": 0.00014694715627858908,
"loss": 0.1093,
"step": 41
},
{
"epoch": 0.031840796019900496,
"grad_norm": 0.08698414266109467,
"learning_rate": 0.00014383711467890774,
"loss": 0.1107,
"step": 42
},
{
"epoch": 0.03259891021085051,
"grad_norm": 0.07267863303422928,
"learning_rate": 0.00014067366430758004,
"loss": 0.1195,
"step": 43
},
{
"epoch": 0.03335702440180052,
"grad_norm": 0.07162914425134659,
"learning_rate": 0.00013746065934159123,
"loss": 0.1146,
"step": 44
},
{
"epoch": 0.03411513859275053,
"grad_norm": 0.05877028778195381,
"learning_rate": 0.00013420201433256689,
"loss": 0.1096,
"step": 45
},
{
"epoch": 0.03487325278370054,
"grad_norm": 0.0560929961502552,
"learning_rate": 0.00013090169943749476,
"loss": 0.1202,
"step": 46
},
{
"epoch": 0.03563136697465056,
"grad_norm": 0.07029124349355698,
"learning_rate": 0.0001275637355816999,
"loss": 0.1029,
"step": 47
},
{
"epoch": 0.03638948116560057,
"grad_norm": 0.043535735458135605,
"learning_rate": 0.00012419218955996676,
"loss": 0.1079,
"step": 48
},
{
"epoch": 0.03714759535655058,
"grad_norm": 0.05880381911993027,
"learning_rate": 0.00012079116908177593,
"loss": 0.1223,
"step": 49
},
{
"epoch": 0.03790570954750059,
"grad_norm": 0.05926327407360077,
"learning_rate": 0.00011736481776669306,
"loss": 0.116,
"step": 50
},
{
"epoch": 0.038663823738450606,
"grad_norm": 0.0628269761800766,
"learning_rate": 0.00011391731009600654,
"loss": 0.1068,
"step": 51
},
{
"epoch": 0.039421937929400616,
"grad_norm": 0.07782096415758133,
"learning_rate": 0.00011045284632676536,
"loss": 0.1124,
"step": 52
},
{
"epoch": 0.040180052120350626,
"grad_norm": 0.07580537348985672,
"learning_rate": 0.00010697564737441252,
"loss": 0.1038,
"step": 53
},
{
"epoch": 0.04093816631130064,
"grad_norm": 0.05523601919412613,
"learning_rate": 0.00010348994967025012,
"loss": 0.1,
"step": 54
},
{
"epoch": 0.04169628050225065,
"grad_norm": 0.056455422192811966,
"learning_rate": 0.0001,
"loss": 0.1046,
"step": 55
},
{
"epoch": 0.04245439469320066,
"grad_norm": 0.052510254085063934,
"learning_rate": 9.651005032974994e-05,
"loss": 0.1025,
"step": 56
},
{
"epoch": 0.04321250888415067,
"grad_norm": 0.053201328963041306,
"learning_rate": 9.302435262558747e-05,
"loss": 0.0956,
"step": 57
},
{
"epoch": 0.04397062307510069,
"grad_norm": 0.05429815128445625,
"learning_rate": 8.954715367323468e-05,
"loss": 0.0915,
"step": 58
},
{
"epoch": 0.0447287372660507,
"grad_norm": 0.05565072223544121,
"learning_rate": 8.608268990399349e-05,
"loss": 0.1037,
"step": 59
},
{
"epoch": 0.04548685145700071,
"grad_norm": 0.06064201518893242,
"learning_rate": 8.263518223330697e-05,
"loss": 0.0996,
"step": 60
},
{
"epoch": 0.04624496564795072,
"grad_norm": 0.053189653903245926,
"learning_rate": 7.920883091822408e-05,
"loss": 0.0972,
"step": 61
},
{
"epoch": 0.04700307983890074,
"grad_norm": 0.0630035251379013,
"learning_rate": 7.580781044003324e-05,
"loss": 0.0957,
"step": 62
},
{
"epoch": 0.04776119402985075,
"grad_norm": 0.05781060457229614,
"learning_rate": 7.243626441830009e-05,
"loss": 0.1116,
"step": 63
},
{
"epoch": 0.04851930822080076,
"grad_norm": 0.05752211809158325,
"learning_rate": 6.909830056250527e-05,
"loss": 0.1015,
"step": 64
},
{
"epoch": 0.04927742241175077,
"grad_norm": 0.05063620209693909,
"learning_rate": 6.579798566743314e-05,
"loss": 0.1083,
"step": 65
},
{
"epoch": 0.050035536602700784,
"grad_norm": 0.0517071969807148,
"learning_rate": 6.25393406584088e-05,
"loss": 0.0946,
"step": 66
},
{
"epoch": 0.050793650793650794,
"grad_norm": 0.04985162615776062,
"learning_rate": 5.9326335692419995e-05,
"loss": 0.1058,
"step": 67
},
{
"epoch": 0.051551764984600804,
"grad_norm": 0.04708476364612579,
"learning_rate": 5.616288532109225e-05,
"loss": 0.0921,
"step": 68
},
{
"epoch": 0.05230987917555082,
"grad_norm": 0.05587763711810112,
"learning_rate": 5.305284372141095e-05,
"loss": 0.0927,
"step": 69
},
{
"epoch": 0.05306799336650083,
"grad_norm": 0.05187711864709854,
"learning_rate": 5.000000000000002e-05,
"loss": 0.1022,
"step": 70
},
{
"epoch": 0.05382610755745084,
"grad_norm": 0.05270811542868614,
"learning_rate": 4.700807357667952e-05,
"loss": 0.1022,
"step": 71
},
{
"epoch": 0.05458422174840085,
"grad_norm": 0.050687965005636215,
"learning_rate": 4.4080709652925336e-05,
"loss": 0.0999,
"step": 72
},
{
"epoch": 0.05534233593935087,
"grad_norm": 0.04412781447172165,
"learning_rate": 4.12214747707527e-05,
"loss": 0.0989,
"step": 73
},
{
"epoch": 0.05610045013030088,
"grad_norm": 0.04820292443037033,
"learning_rate": 3.843385246743417e-05,
"loss": 0.0882,
"step": 74
},
{
"epoch": 0.05685856432125089,
"grad_norm": 0.05101883411407471,
"learning_rate": 3.5721239031346066e-05,
"loss": 0.0896,
"step": 75
},
{
"epoch": 0.0576166785122009,
"grad_norm": 0.056556086987257004,
"learning_rate": 3.308693936411421e-05,
"loss": 0.0951,
"step": 76
},
{
"epoch": 0.058374792703150914,
"grad_norm": 0.05035807937383652,
"learning_rate": 3.053416295410026e-05,
"loss": 0.0911,
"step": 77
},
{
"epoch": 0.059132906894100924,
"grad_norm": 0.043333761394023895,
"learning_rate": 2.8066019966134904e-05,
"loss": 0.089,
"step": 78
},
{
"epoch": 0.059891021085050934,
"grad_norm": 0.047586455941200256,
"learning_rate": 2.5685517452260567e-05,
"loss": 0.0874,
"step": 79
},
{
"epoch": 0.06064913527600095,
"grad_norm": 0.0488692931830883,
"learning_rate": 2.339555568810221e-05,
"loss": 0.0925,
"step": 80
},
{
"epoch": 0.06140724946695096,
"grad_norm": 0.05427223816514015,
"learning_rate": 2.119892463932781e-05,
"loss": 0.0927,
"step": 81
},
{
"epoch": 0.06216536365790097,
"grad_norm": 0.057675670832395554,
"learning_rate": 1.9098300562505266e-05,
"loss": 0.0978,
"step": 82
},
{
"epoch": 0.06292347784885098,
"grad_norm": 0.05663346126675606,
"learning_rate": 1.7096242744495837e-05,
"loss": 0.1041,
"step": 83
},
{
"epoch": 0.06368159203980099,
"grad_norm": 0.054945193231105804,
"learning_rate": 1.5195190384357404e-05,
"loss": 0.0847,
"step": 84
},
{
"epoch": 0.064439706230751,
"grad_norm": 0.05341991409659386,
"learning_rate": 1.339745962155613e-05,
"loss": 0.0877,
"step": 85
},
{
"epoch": 0.06519782042170102,
"grad_norm": 0.0533662885427475,
"learning_rate": 1.1705240714107302e-05,
"loss": 0.1052,
"step": 86
},
{
"epoch": 0.06595593461265103,
"grad_norm": 0.045474544167518616,
"learning_rate": 1.0120595370083318e-05,
"loss": 0.0863,
"step": 87
},
{
"epoch": 0.06671404880360104,
"grad_norm": 0.043375492095947266,
"learning_rate": 8.645454235739903e-06,
"loss": 0.0904,
"step": 88
},
{
"epoch": 0.06747216299455105,
"grad_norm": 0.05601764842867851,
"learning_rate": 7.281614543321269e-06,
"loss": 0.094,
"step": 89
},
{
"epoch": 0.06823027718550106,
"grad_norm": 0.0548299178481102,
"learning_rate": 6.030737921409169e-06,
"loss": 0.0857,
"step": 90
},
{
"epoch": 0.06898839137645107,
"grad_norm": 0.04874192178249359,
"learning_rate": 4.8943483704846475e-06,
"loss": 0.0885,
"step": 91
},
{
"epoch": 0.06974650556740108,
"grad_norm": 0.05287107825279236,
"learning_rate": 3.873830406168111e-06,
"loss": 0.1027,
"step": 92
},
{
"epoch": 0.0705046197583511,
"grad_norm": 0.04792382940649986,
"learning_rate": 2.970427372400353e-06,
"loss": 0.0849,
"step": 93
},
{
"epoch": 0.07126273394930112,
"grad_norm": 0.04913964122533798,
"learning_rate": 2.1852399266194314e-06,
"loss": 0.0848,
"step": 94
},
{
"epoch": 0.07202084814025113,
"grad_norm": 0.04982119798660278,
"learning_rate": 1.5192246987791981e-06,
"loss": 0.0959,
"step": 95
},
{
"epoch": 0.07277896233120114,
"grad_norm": 0.04819797724485397,
"learning_rate": 9.731931258429638e-07,
"loss": 0.0881,
"step": 96
},
{
"epoch": 0.07353707652215115,
"grad_norm": 0.050941213965415955,
"learning_rate": 5.478104631726711e-07,
"loss": 0.0957,
"step": 97
},
{
"epoch": 0.07429519071310116,
"grad_norm": 0.046391792595386505,
"learning_rate": 2.4359497401758024e-07,
"loss": 0.0859,
"step": 98
},
{
"epoch": 0.07505330490405117,
"grad_norm": 0.0439014732837677,
"learning_rate": 6.09172980904238e-08,
"loss": 0.0963,
"step": 99
},
{
"epoch": 0.07581141909500118,
"grad_norm": 0.04594559594988823,
"learning_rate": 0.0,
"loss": 0.091,
"step": 100
}
],
"logging_steps": 1,
"max_steps": 100,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 50,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 1.162003273287598e+17,
"train_batch_size": 8,
"trial_name": null,
"trial_params": null
}