error577's picture
Training in progress, epoch 0, checkpoint
72f4338 verified
raw
history blame
18 kB
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.007842983470912335,
"eval_steps": 500,
"global_step": 100,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 7.842983470912334e-05,
"grad_norm": 8.825519561767578,
"learning_rate": 1e-05,
"loss": 2.8016,
"step": 1
},
{
"epoch": 0.0001568596694182467,
"grad_norm": 12.083088874816895,
"learning_rate": 2e-05,
"loss": 3.6411,
"step": 2
},
{
"epoch": 0.00023528950412737005,
"grad_norm": 15.9275541305542,
"learning_rate": 3e-05,
"loss": 4.9024,
"step": 3
},
{
"epoch": 0.0003137193388364934,
"grad_norm": 21.615602493286133,
"learning_rate": 4e-05,
"loss": 6.0083,
"step": 4
},
{
"epoch": 0.00039214917354561674,
"grad_norm": 22.12832260131836,
"learning_rate": 5e-05,
"loss": 5.5202,
"step": 5
},
{
"epoch": 0.0004705790082547401,
"grad_norm": 9.948811531066895,
"learning_rate": 6e-05,
"loss": 2.9518,
"step": 6
},
{
"epoch": 0.0005490088429638635,
"grad_norm": 15.534398078918457,
"learning_rate": 7e-05,
"loss": 4.1157,
"step": 7
},
{
"epoch": 0.0006274386776729868,
"grad_norm": 16.559049606323242,
"learning_rate": 8e-05,
"loss": 5.0582,
"step": 8
},
{
"epoch": 0.0007058685123821102,
"grad_norm": 42.421512603759766,
"learning_rate": 9e-05,
"loss": 6.5426,
"step": 9
},
{
"epoch": 0.0007842983470912335,
"grad_norm": 20.62925148010254,
"learning_rate": 0.0001,
"loss": 4.6693,
"step": 10
},
{
"epoch": 0.0008627281818003569,
"grad_norm": 15.661595344543457,
"learning_rate": 9.99695413509548e-05,
"loss": 3.6362,
"step": 11
},
{
"epoch": 0.0009411580165094802,
"grad_norm": 14.2806978225708,
"learning_rate": 9.987820251299122e-05,
"loss": 2.3931,
"step": 12
},
{
"epoch": 0.0010195878512186036,
"grad_norm": 28.024402618408203,
"learning_rate": 9.972609476841367e-05,
"loss": 3.4275,
"step": 13
},
{
"epoch": 0.001098017685927727,
"grad_norm": 16.453929901123047,
"learning_rate": 9.951340343707852e-05,
"loss": 2.1056,
"step": 14
},
{
"epoch": 0.0011764475206368502,
"grad_norm": 22.603105545043945,
"learning_rate": 9.924038765061042e-05,
"loss": 2.0804,
"step": 15
},
{
"epoch": 0.0012548773553459735,
"grad_norm": 25.013137817382812,
"learning_rate": 9.890738003669029e-05,
"loss": 2.4932,
"step": 16
},
{
"epoch": 0.001333307190055097,
"grad_norm": 22.514392852783203,
"learning_rate": 9.851478631379982e-05,
"loss": 2.5763,
"step": 17
},
{
"epoch": 0.0014117370247642203,
"grad_norm": 29.10135841369629,
"learning_rate": 9.806308479691595e-05,
"loss": 1.8406,
"step": 18
},
{
"epoch": 0.0014901668594733436,
"grad_norm": 12.27782917022705,
"learning_rate": 9.755282581475769e-05,
"loss": 1.4448,
"step": 19
},
{
"epoch": 0.001568596694182467,
"grad_norm": 36.448997497558594,
"learning_rate": 9.698463103929542e-05,
"loss": 2.9484,
"step": 20
},
{
"epoch": 0.0016470265288915905,
"grad_norm": 11.227051734924316,
"learning_rate": 9.635919272833938e-05,
"loss": 1.8091,
"step": 21
},
{
"epoch": 0.0017254563636007138,
"grad_norm": 14.083976745605469,
"learning_rate": 9.567727288213005e-05,
"loss": 1.3116,
"step": 22
},
{
"epoch": 0.001803886198309837,
"grad_norm": 14.545560836791992,
"learning_rate": 9.493970231495835e-05,
"loss": 1.6795,
"step": 23
},
{
"epoch": 0.0018823160330189604,
"grad_norm": 15.083060264587402,
"learning_rate": 9.414737964294636e-05,
"loss": 1.7426,
"step": 24
},
{
"epoch": 0.0019607458677280837,
"grad_norm": 14.212522506713867,
"learning_rate": 9.330127018922194e-05,
"loss": 1.732,
"step": 25
},
{
"epoch": 0.002039175702437207,
"grad_norm": 11.611138343811035,
"learning_rate": 9.24024048078213e-05,
"loss": 1.2554,
"step": 26
},
{
"epoch": 0.0021176055371463303,
"grad_norm": 10.914994239807129,
"learning_rate": 9.145187862775209e-05,
"loss": 1.394,
"step": 27
},
{
"epoch": 0.002196035371855454,
"grad_norm": 20.15048599243164,
"learning_rate": 9.045084971874738e-05,
"loss": 2.1326,
"step": 28
},
{
"epoch": 0.0022744652065645773,
"grad_norm": 14.226958274841309,
"learning_rate": 8.940053768033609e-05,
"loss": 1.411,
"step": 29
},
{
"epoch": 0.0023528950412737004,
"grad_norm": 15.308096885681152,
"learning_rate": 8.83022221559489e-05,
"loss": 2.2317,
"step": 30
},
{
"epoch": 0.002431324875982824,
"grad_norm": 37.11000442504883,
"learning_rate": 8.715724127386972e-05,
"loss": 3.0994,
"step": 31
},
{
"epoch": 0.002509754710691947,
"grad_norm": 13.671127319335938,
"learning_rate": 8.596699001693255e-05,
"loss": 2.3658,
"step": 32
},
{
"epoch": 0.0025881845454010705,
"grad_norm": 11.981795310974121,
"learning_rate": 8.473291852294987e-05,
"loss": 1.7347,
"step": 33
},
{
"epoch": 0.002666614380110194,
"grad_norm": 17.430723190307617,
"learning_rate": 8.345653031794292e-05,
"loss": 2.2345,
"step": 34
},
{
"epoch": 0.002745044214819317,
"grad_norm": 14.712089538574219,
"learning_rate": 8.213938048432697e-05,
"loss": 2.2161,
"step": 35
},
{
"epoch": 0.0028234740495284407,
"grad_norm": 12.411870956420898,
"learning_rate": 8.07830737662829e-05,
"loss": 1.6571,
"step": 36
},
{
"epoch": 0.0029019038842375638,
"grad_norm": 11.750947952270508,
"learning_rate": 7.938926261462366e-05,
"loss": 1.3471,
"step": 37
},
{
"epoch": 0.0029803337189466873,
"grad_norm": 18.219520568847656,
"learning_rate": 7.795964517353735e-05,
"loss": 2.2844,
"step": 38
},
{
"epoch": 0.003058763553655811,
"grad_norm": 8.215274810791016,
"learning_rate": 7.649596321166024e-05,
"loss": 1.379,
"step": 39
},
{
"epoch": 0.003137193388364934,
"grad_norm": 10.532532691955566,
"learning_rate": 7.500000000000001e-05,
"loss": 1.8841,
"step": 40
},
{
"epoch": 0.0032156232230740574,
"grad_norm": 12.455815315246582,
"learning_rate": 7.347357813929454e-05,
"loss": 1.7141,
"step": 41
},
{
"epoch": 0.003294053057783181,
"grad_norm": 10.054532051086426,
"learning_rate": 7.191855733945387e-05,
"loss": 1.6398,
"step": 42
},
{
"epoch": 0.003372482892492304,
"grad_norm": 10.613759994506836,
"learning_rate": 7.033683215379002e-05,
"loss": 1.7214,
"step": 43
},
{
"epoch": 0.0034509127272014275,
"grad_norm": 10.810108184814453,
"learning_rate": 6.873032967079561e-05,
"loss": 2.3159,
"step": 44
},
{
"epoch": 0.0035293425619105506,
"grad_norm": 11.261944770812988,
"learning_rate": 6.710100716628344e-05,
"loss": 1.463,
"step": 45
},
{
"epoch": 0.003607772396619674,
"grad_norm": 11.900640487670898,
"learning_rate": 6.545084971874738e-05,
"loss": 1.5287,
"step": 46
},
{
"epoch": 0.0036862022313287977,
"grad_norm": 14.910116195678711,
"learning_rate": 6.378186779084995e-05,
"loss": 2.1966,
"step": 47
},
{
"epoch": 0.0037646320660379208,
"grad_norm": 11.18796157836914,
"learning_rate": 6.209609477998338e-05,
"loss": 1.7811,
"step": 48
},
{
"epoch": 0.0038430619007470443,
"grad_norm": 15.256511688232422,
"learning_rate": 6.0395584540887963e-05,
"loss": 1.3157,
"step": 49
},
{
"epoch": 0.003921491735456167,
"grad_norm": 10.210933685302734,
"learning_rate": 5.868240888334653e-05,
"loss": 1.5167,
"step": 50
},
{
"epoch": 0.003999921570165291,
"grad_norm": 14.052650451660156,
"learning_rate": 5.695865504800327e-05,
"loss": 1.7569,
"step": 51
},
{
"epoch": 0.004078351404874414,
"grad_norm": 14.927163124084473,
"learning_rate": 5.522642316338268e-05,
"loss": 1.4792,
"step": 52
},
{
"epoch": 0.004156781239583538,
"grad_norm": 18.198444366455078,
"learning_rate": 5.348782368720626e-05,
"loss": 3.5506,
"step": 53
},
{
"epoch": 0.004235211074292661,
"grad_norm": 13.294053077697754,
"learning_rate": 5.174497483512506e-05,
"loss": 1.4432,
"step": 54
},
{
"epoch": 0.004313640909001784,
"grad_norm": 11.814456939697266,
"learning_rate": 5e-05,
"loss": 1.4172,
"step": 55
},
{
"epoch": 0.004392070743710908,
"grad_norm": 8.617324829101562,
"learning_rate": 4.825502516487497e-05,
"loss": 1.3786,
"step": 56
},
{
"epoch": 0.004470500578420031,
"grad_norm": 14.102591514587402,
"learning_rate": 4.6512176312793736e-05,
"loss": 1.9422,
"step": 57
},
{
"epoch": 0.004548930413129155,
"grad_norm": 10.432605743408203,
"learning_rate": 4.477357683661734e-05,
"loss": 1.3672,
"step": 58
},
{
"epoch": 0.004627360247838277,
"grad_norm": 11.157849311828613,
"learning_rate": 4.3041344951996746e-05,
"loss": 1.5081,
"step": 59
},
{
"epoch": 0.004705790082547401,
"grad_norm": 10.752006530761719,
"learning_rate": 4.131759111665349e-05,
"loss": 1.763,
"step": 60
},
{
"epoch": 0.004784219917256524,
"grad_norm": 7.7650017738342285,
"learning_rate": 3.960441545911204e-05,
"loss": 1.338,
"step": 61
},
{
"epoch": 0.004862649751965648,
"grad_norm": 9.609498977661133,
"learning_rate": 3.790390522001662e-05,
"loss": 1.5723,
"step": 62
},
{
"epoch": 0.004941079586674771,
"grad_norm": 10.62063980102539,
"learning_rate": 3.6218132209150045e-05,
"loss": 1.6656,
"step": 63
},
{
"epoch": 0.005019509421383894,
"grad_norm": 8.951350212097168,
"learning_rate": 3.4549150281252636e-05,
"loss": 1.2429,
"step": 64
},
{
"epoch": 0.005097939256093018,
"grad_norm": 18.992971420288086,
"learning_rate": 3.289899283371657e-05,
"loss": 3.1177,
"step": 65
},
{
"epoch": 0.005176369090802141,
"grad_norm": 13.394461631774902,
"learning_rate": 3.12696703292044e-05,
"loss": 1.8502,
"step": 66
},
{
"epoch": 0.005254798925511265,
"grad_norm": 12.403133392333984,
"learning_rate": 2.9663167846209998e-05,
"loss": 1.1488,
"step": 67
},
{
"epoch": 0.005333228760220388,
"grad_norm": 7.903024673461914,
"learning_rate": 2.8081442660546125e-05,
"loss": 1.2091,
"step": 68
},
{
"epoch": 0.005411658594929511,
"grad_norm": 11.113040924072266,
"learning_rate": 2.6526421860705473e-05,
"loss": 1.6937,
"step": 69
},
{
"epoch": 0.005490088429638634,
"grad_norm": 15.218375205993652,
"learning_rate": 2.500000000000001e-05,
"loss": 1.9523,
"step": 70
},
{
"epoch": 0.005568518264347758,
"grad_norm": 10.67128849029541,
"learning_rate": 2.350403678833976e-05,
"loss": 1.3664,
"step": 71
},
{
"epoch": 0.005646948099056881,
"grad_norm": 9.806090354919434,
"learning_rate": 2.2040354826462668e-05,
"loss": 1.4883,
"step": 72
},
{
"epoch": 0.005725377933766005,
"grad_norm": 11.227718353271484,
"learning_rate": 2.061073738537635e-05,
"loss": 1.1364,
"step": 73
},
{
"epoch": 0.0058038077684751275,
"grad_norm": 17.53663444519043,
"learning_rate": 1.9216926233717085e-05,
"loss": 1.8685,
"step": 74
},
{
"epoch": 0.005882237603184251,
"grad_norm": 6.851722240447998,
"learning_rate": 1.7860619515673033e-05,
"loss": 1.0575,
"step": 75
},
{
"epoch": 0.0059606674378933746,
"grad_norm": 9.295647621154785,
"learning_rate": 1.6543469682057106e-05,
"loss": 1.0835,
"step": 76
},
{
"epoch": 0.006039097272602498,
"grad_norm": 9.07209300994873,
"learning_rate": 1.526708147705013e-05,
"loss": 1.1428,
"step": 77
},
{
"epoch": 0.006117527107311622,
"grad_norm": 8.919276237487793,
"learning_rate": 1.4033009983067452e-05,
"loss": 1.6744,
"step": 78
},
{
"epoch": 0.006195956942020745,
"grad_norm": 14.970587730407715,
"learning_rate": 1.2842758726130283e-05,
"loss": 1.7913,
"step": 79
},
{
"epoch": 0.006274386776729868,
"grad_norm": 7.171314239501953,
"learning_rate": 1.1697777844051105e-05,
"loss": 1.5177,
"step": 80
},
{
"epoch": 0.006352816611438991,
"grad_norm": 7.902921676635742,
"learning_rate": 1.0599462319663905e-05,
"loss": 1.3037,
"step": 81
},
{
"epoch": 0.006431246446148115,
"grad_norm": 6.716002941131592,
"learning_rate": 9.549150281252633e-06,
"loss": 0.962,
"step": 82
},
{
"epoch": 0.006509676280857238,
"grad_norm": 10.144266128540039,
"learning_rate": 8.548121372247918e-06,
"loss": 1.4771,
"step": 83
},
{
"epoch": 0.006588106115566362,
"grad_norm": 8.199270248413086,
"learning_rate": 7.597595192178702e-06,
"loss": 1.2546,
"step": 84
},
{
"epoch": 0.0066665359502754845,
"grad_norm": 11.108482360839844,
"learning_rate": 6.698729810778065e-06,
"loss": 1.3973,
"step": 85
},
{
"epoch": 0.006744965784984608,
"grad_norm": 8.652900695800781,
"learning_rate": 5.852620357053651e-06,
"loss": 1.3762,
"step": 86
},
{
"epoch": 0.0068233956196937316,
"grad_norm": 14.958466529846191,
"learning_rate": 5.060297685041659e-06,
"loss": 1.7316,
"step": 87
},
{
"epoch": 0.006901825454402855,
"grad_norm": 6.1512227058410645,
"learning_rate": 4.322727117869951e-06,
"loss": 1.1393,
"step": 88
},
{
"epoch": 0.006980255289111979,
"grad_norm": 9.555928230285645,
"learning_rate": 3.6408072716606346e-06,
"loss": 1.3302,
"step": 89
},
{
"epoch": 0.007058685123821101,
"grad_norm": 9.107611656188965,
"learning_rate": 3.0153689607045845e-06,
"loss": 1.2227,
"step": 90
},
{
"epoch": 0.007137114958530225,
"grad_norm": 5.744083881378174,
"learning_rate": 2.4471741852423237e-06,
"loss": 1.0086,
"step": 91
},
{
"epoch": 0.007215544793239348,
"grad_norm": 13.552300453186035,
"learning_rate": 1.9369152030840556e-06,
"loss": 1.7774,
"step": 92
},
{
"epoch": 0.007293974627948472,
"grad_norm": 16.62940788269043,
"learning_rate": 1.4852136862001764e-06,
"loss": 1.7008,
"step": 93
},
{
"epoch": 0.007372404462657595,
"grad_norm": 12.544093132019043,
"learning_rate": 1.0926199633097157e-06,
"loss": 1.6784,
"step": 94
},
{
"epoch": 0.007450834297366718,
"grad_norm": 10.599544525146484,
"learning_rate": 7.596123493895991e-07,
"loss": 1.5247,
"step": 95
},
{
"epoch": 0.0075292641320758415,
"grad_norm": 11.64220142364502,
"learning_rate": 4.865965629214819e-07,
"loss": 1.5947,
"step": 96
},
{
"epoch": 0.007607693966784965,
"grad_norm": 7.192104339599609,
"learning_rate": 2.7390523158633554e-07,
"loss": 1.3408,
"step": 97
},
{
"epoch": 0.0076861238014940885,
"grad_norm": 12.79780101776123,
"learning_rate": 1.2179748700879012e-07,
"loss": 2.0013,
"step": 98
},
{
"epoch": 0.007764553636203212,
"grad_norm": 8.97789478302002,
"learning_rate": 3.04586490452119e-08,
"loss": 1.5413,
"step": 99
},
{
"epoch": 0.007842983470912335,
"grad_norm": 13.65710735321045,
"learning_rate": 0.0,
"loss": 2.3571,
"step": 100
}
],
"logging_steps": 1,
"max_steps": 100,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 500,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 9442519318265856.0,
"train_batch_size": 1,
"trial_name": null,
"trial_params": null
}