taufiqsyed's picture
End of training
043b71d verified
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.9915764139590855,
"eval_steps": 25,
"global_step": 103,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.009626955475330927,
"grad_norm": 76.00764465332031,
"learning_rate": 9.997674418116759e-06,
"loss": 10.061,
"step": 1
},
{
"epoch": 0.019253910950661854,
"grad_norm": 68.18009185791016,
"learning_rate": 9.99069983579947e-06,
"loss": 9.9795,
"step": 2
},
{
"epoch": 0.02888086642599278,
"grad_norm": 46.29243850708008,
"learning_rate": 9.979082741033047e-06,
"loss": 9.5387,
"step": 3
},
{
"epoch": 0.03850782190132371,
"grad_norm": Infinity,
"learning_rate": 9.979082741033047e-06,
"loss": 9.6956,
"step": 4
},
{
"epoch": 0.048134777376654635,
"grad_norm": 55.74219512939453,
"learning_rate": 9.96283394041954e-06,
"loss": 9.7291,
"step": 5
},
{
"epoch": 0.05776173285198556,
"grad_norm": Infinity,
"learning_rate": 9.96283394041954e-06,
"loss": 9.7559,
"step": 6
},
{
"epoch": 0.06738868832731648,
"grad_norm": 74.81196594238281,
"learning_rate": 9.941968549125481e-06,
"loss": 9.8749,
"step": 7
},
{
"epoch": 0.07701564380264742,
"grad_norm": 93.73626708984375,
"learning_rate": 9.916505976821262e-06,
"loss": 9.9976,
"step": 8
},
{
"epoch": 0.08664259927797834,
"grad_norm": 66.88408660888672,
"learning_rate": 9.886469909625624e-06,
"loss": 9.8316,
"step": 9
},
{
"epoch": 0.09626955475330927,
"grad_norm": 51.5136833190918,
"learning_rate": 9.851888288072053e-06,
"loss": 9.653,
"step": 10
},
{
"epoch": 0.10589651022864019,
"grad_norm": 58.80715560913086,
"learning_rate": 9.81279328111758e-06,
"loss": 9.6294,
"step": 11
},
{
"epoch": 0.11552346570397112,
"grad_norm": 49.53478240966797,
"learning_rate": 9.769221256218165e-06,
"loss": 9.5226,
"step": 12
},
{
"epoch": 0.12515042117930206,
"grad_norm": 50.32080841064453,
"learning_rate": 9.721212745498493e-06,
"loss": 9.4886,
"step": 13
},
{
"epoch": 0.13477737665463296,
"grad_norm": 72.49040222167969,
"learning_rate": 9.66881240804768e-06,
"loss": 9.7044,
"step": 14
},
{
"epoch": 0.1444043321299639,
"grad_norm": 65.08924865722656,
"learning_rate": 9.612068988375898e-06,
"loss": 9.596,
"step": 15
},
{
"epoch": 0.15403128760529483,
"grad_norm": 51.38800811767578,
"learning_rate": 9.551035271070665e-06,
"loss": 9.4843,
"step": 16
},
{
"epoch": 0.16365824308062576,
"grad_norm": 65.1738510131836,
"learning_rate": 9.485768031694872e-06,
"loss": 9.5644,
"step": 17
},
{
"epoch": 0.17328519855595667,
"grad_norm": 71.97135162353516,
"learning_rate": 9.416327983972304e-06,
"loss": 9.574,
"step": 18
},
{
"epoch": 0.1829121540312876,
"grad_norm": 61.20840835571289,
"learning_rate": 9.342779723309746e-06,
"loss": 9.4448,
"step": 19
},
{
"epoch": 0.19253910950661854,
"grad_norm": 53.58602523803711,
"learning_rate": 9.26519166670821e-06,
"loss": 9.3692,
"step": 20
},
{
"epoch": 0.20216606498194944,
"grad_norm": 46.41659927368164,
"learning_rate": 9.183635989119211e-06,
"loss": 9.3402,
"step": 21
},
{
"epoch": 0.21179302045728038,
"grad_norm": 57.2279052734375,
"learning_rate": 9.098188556305262e-06,
"loss": 9.3307,
"step": 22
},
{
"epoch": 0.2214199759326113,
"grad_norm": 69.78079223632812,
"learning_rate": 9.008928854267054e-06,
"loss": 9.3439,
"step": 23
},
{
"epoch": 0.23104693140794225,
"grad_norm": 98.2174301147461,
"learning_rate": 8.91593991530297e-06,
"loss": 9.3648,
"step": 24
},
{
"epoch": 0.24067388688327315,
"grad_norm": 62.788814544677734,
"learning_rate": 8.819308240769726e-06,
"loss": 9.2964,
"step": 25
},
{
"epoch": 0.24067388688327315,
"eval_clap": 0.23925480246543884,
"eval_loss": 3.6824278831481934,
"eval_runtime": 551.8966,
"eval_samples_per_second": 0.058,
"eval_steps_per_second": 0.058,
"step": 25
},
{
"epoch": 0.2503008423586041,
"grad_norm": 67.70923614501953,
"learning_rate": 8.71912372061598e-06,
"loss": 9.2203,
"step": 26
},
{
"epoch": 0.259927797833935,
"grad_norm": 55.661197662353516,
"learning_rate": 8.615479549763756e-06,
"loss": 9.1849,
"step": 27
},
{
"epoch": 0.2695547533092659,
"grad_norm": 50.55519104003906,
"learning_rate": 8.508472141415468e-06,
"loss": 9.1337,
"step": 28
},
{
"epoch": 0.27918170878459686,
"grad_norm": 44.694305419921875,
"learning_rate": 8.398201037367202e-06,
"loss": 9.1279,
"step": 29
},
{
"epoch": 0.2888086642599278,
"grad_norm": 45.560523986816406,
"learning_rate": 8.284768815411693e-06,
"loss": 9.1314,
"step": 30
},
{
"epoch": 0.29843561973525873,
"grad_norm": 49.15139389038086,
"learning_rate": 8.168280993917078e-06,
"loss": 9.0014,
"step": 31
},
{
"epoch": 0.30806257521058966,
"grad_norm": 80.88079833984375,
"learning_rate": 8.048845933670274e-06,
"loss": 9.0433,
"step": 32
},
{
"epoch": 0.3176895306859206,
"grad_norm": 56.16194534301758,
"learning_rate": 7.92657473707621e-06,
"loss": 8.9263,
"step": 33
},
{
"epoch": 0.32731648616125153,
"grad_norm": 90.87415313720703,
"learning_rate": 7.801581144806752e-06,
"loss": 8.9342,
"step": 34
},
{
"epoch": 0.3369434416365824,
"grad_norm": 71.51280212402344,
"learning_rate": 7.673981429995372e-06,
"loss": 8.9876,
"step": 35
},
{
"epoch": 0.34657039711191334,
"grad_norm": 74.96561431884766,
"learning_rate": 7.5438942900761035e-06,
"loss": 8.9411,
"step": 36
},
{
"epoch": 0.3561973525872443,
"grad_norm": 65.20281982421875,
"learning_rate": 7.411440736367281e-06,
"loss": 8.8483,
"step": 37
},
{
"epoch": 0.3658243080625752,
"grad_norm": 88.80401611328125,
"learning_rate": 7.276743981502856e-06,
"loss": 8.854,
"step": 38
},
{
"epoch": 0.37545126353790614,
"grad_norm": 57.629215240478516,
"learning_rate": 7.139929324815965e-06,
"loss": 8.7488,
"step": 39
},
{
"epoch": 0.3850782190132371,
"grad_norm": 68.3960952758789,
"learning_rate": 7.00112403578139e-06,
"loss": 8.6557,
"step": 40
},
{
"epoch": 0.394705174488568,
"grad_norm": Infinity,
"learning_rate": 7.00112403578139e-06,
"loss": 8.6279,
"step": 41
},
{
"epoch": 0.4043321299638989,
"grad_norm": 60.18490982055664,
"learning_rate": 6.860457235625322e-06,
"loss": 8.7681,
"step": 42
},
{
"epoch": 0.4139590854392298,
"grad_norm": 47.897037506103516,
"learning_rate": 6.7180597772125665e-06,
"loss": 8.6985,
"step": 43
},
{
"epoch": 0.42358604091456076,
"grad_norm": 67.03247833251953,
"learning_rate": 6.574064123322925e-06,
"loss": 8.8191,
"step": 44
},
{
"epoch": 0.4332129963898917,
"grad_norm": 81.16341400146484,
"learning_rate": 6.42860422342998e-06,
"loss": 8.4126,
"step": 45
},
{
"epoch": 0.4428399518652226,
"grad_norm": 60.89366912841797,
"learning_rate": 6.281815389096903e-06,
"loss": 8.5561,
"step": 46
},
{
"epoch": 0.45246690734055356,
"grad_norm": 65.52647399902344,
"learning_rate": 6.133834168105206e-06,
"loss": 8.4911,
"step": 47
},
{
"epoch": 0.4620938628158845,
"grad_norm": 51.18867111206055,
"learning_rate": 5.9847982174335314e-06,
"loss": 8.5119,
"step": 48
},
{
"epoch": 0.4717208182912154,
"grad_norm": 82.5035171508789,
"learning_rate": 5.834846175204612e-06,
"loss": 8.416,
"step": 49
},
{
"epoch": 0.4813477737665463,
"grad_norm": 51.8901252746582,
"learning_rate": 5.684117531719552e-06,
"loss": 8.452,
"step": 50
},
{
"epoch": 0.4813477737665463,
"eval_clap": 0.22033847868442535,
"eval_loss": 3.7089993953704834,
"eval_runtime": 552.5298,
"eval_samples_per_second": 0.058,
"eval_steps_per_second": 0.058,
"step": 50
},
{
"epoch": 0.49097472924187724,
"grad_norm": 52.55012893676758,
"learning_rate": 5.532752499699381e-06,
"loss": 8.4129,
"step": 51
},
{
"epoch": 0.5006016847172082,
"grad_norm": 51.49845886230469,
"learning_rate": 5.380891883854591e-06,
"loss": 8.4629,
"step": 52
},
{
"epoch": 0.5102286401925391,
"grad_norm": 61.926048278808594,
"learning_rate": 5.228676949903974e-06,
"loss": 8.3679,
"step": 53
},
{
"epoch": 0.51985559566787,
"grad_norm": 52.02131652832031,
"learning_rate": 5.07624929316463e-06,
"loss": 8.4213,
"step": 54
},
{
"epoch": 0.529482551143201,
"grad_norm": 57.23763656616211,
"learning_rate": 4.923750706835371e-06,
"loss": 8.436,
"step": 55
},
{
"epoch": 0.5391095066185319,
"grad_norm": 42.910003662109375,
"learning_rate": 4.771323050096028e-06,
"loss": 8.4824,
"step": 56
},
{
"epoch": 0.5487364620938628,
"grad_norm": 66.24418640136719,
"learning_rate": 4.619108116145411e-06,
"loss": 8.1537,
"step": 57
},
{
"epoch": 0.5583634175691937,
"grad_norm": 40.68498229980469,
"learning_rate": 4.467247500300621e-06,
"loss": 8.437,
"step": 58
},
{
"epoch": 0.5679903730445247,
"grad_norm": 42.7538948059082,
"learning_rate": 4.31588246828045e-06,
"loss": 8.3363,
"step": 59
},
{
"epoch": 0.5776173285198556,
"grad_norm": 57.252750396728516,
"learning_rate": 4.165153824795391e-06,
"loss": 8.0644,
"step": 60
},
{
"epoch": 0.5872442839951865,
"grad_norm": 67.81254577636719,
"learning_rate": 4.015201782566471e-06,
"loss": 8.0197,
"step": 61
},
{
"epoch": 0.5968712394705175,
"grad_norm": 52.997032165527344,
"learning_rate": 3.866165831894796e-06,
"loss": 8.2462,
"step": 62
},
{
"epoch": 0.6064981949458483,
"grad_norm": 52.59479522705078,
"learning_rate": 3.7181846109031007e-06,
"loss": 8.1063,
"step": 63
},
{
"epoch": 0.6161251504211793,
"grad_norm": 49.231109619140625,
"learning_rate": 3.5713957765700224e-06,
"loss": 8.1307,
"step": 64
},
{
"epoch": 0.6257521058965102,
"grad_norm": 88.22990417480469,
"learning_rate": 3.425935876677077e-06,
"loss": 7.6548,
"step": 65
},
{
"epoch": 0.6353790613718412,
"grad_norm": 38.582950592041016,
"learning_rate": 3.2819402227874364e-06,
"loss": 8.2685,
"step": 66
},
{
"epoch": 0.6450060168471721,
"grad_norm": 44.78527069091797,
"learning_rate": 3.1395427643746802e-06,
"loss": 8.1258,
"step": 67
},
{
"epoch": 0.6546329723225031,
"grad_norm": 53.792606353759766,
"learning_rate": 2.99887596421861e-06,
"loss": 8.0466,
"step": 68
},
{
"epoch": 0.6642599277978339,
"grad_norm": 54.07836151123047,
"learning_rate": 2.860070675184036e-06,
"loss": 7.8841,
"step": 69
},
{
"epoch": 0.6738868832731648,
"grad_norm": 59.08965301513672,
"learning_rate": 2.7232560184971437e-06,
"loss": 7.8315,
"step": 70
},
{
"epoch": 0.6835138387484958,
"grad_norm": 60.553993225097656,
"learning_rate": 2.588559263632719e-06,
"loss": 7.9891,
"step": 71
},
{
"epoch": 0.6931407942238267,
"grad_norm": 29.405763626098633,
"learning_rate": 2.4561057099238973e-06,
"loss": 8.3634,
"step": 72
},
{
"epoch": 0.7027677496991577,
"grad_norm": 53.22356033325195,
"learning_rate": 2.3260185700046295e-06,
"loss": 7.921,
"step": 73
},
{
"epoch": 0.7123947051744886,
"grad_norm": 33.783748626708984,
"learning_rate": 2.1984188551932513e-06,
"loss": 8.2299,
"step": 74
},
{
"epoch": 0.7220216606498195,
"grad_norm": 34.38785934448242,
"learning_rate": 2.0734252629237892e-06,
"loss": 8.2681,
"step": 75
},
{
"epoch": 0.7220216606498195,
"eval_clap": 0.19338133931159973,
"eval_loss": 3.7505452632904053,
"eval_runtime": 552.0559,
"eval_samples_per_second": 0.058,
"eval_steps_per_second": 0.058,
"step": 75
},
{
"epoch": 0.7316486161251504,
"grad_norm": 60.097808837890625,
"learning_rate": 1.9511540663297284e-06,
"loss": 7.715,
"step": 76
},
{
"epoch": 0.7412755716004813,
"grad_norm": 37.17088317871094,
"learning_rate": 1.8317190060829242e-06,
"loss": 8.0466,
"step": 77
},
{
"epoch": 0.7509025270758123,
"grad_norm": 38.48884963989258,
"learning_rate": 1.7152311845883096e-06,
"loss": 8.0262,
"step": 78
},
{
"epoch": 0.7605294825511432,
"grad_norm": 41.10515594482422,
"learning_rate": 1.601798962632799e-06,
"loss": 7.9378,
"step": 79
},
{
"epoch": 0.7701564380264742,
"grad_norm": 53.396087646484375,
"learning_rate": 1.491527858584535e-06,
"loss": 7.7085,
"step": 80
},
{
"epoch": 0.779783393501805,
"grad_norm": 40.815067291259766,
"learning_rate": 1.3845204502362442e-06,
"loss": 7.9538,
"step": 81
},
{
"epoch": 0.789410348977136,
"grad_norm": 35.33771896362305,
"learning_rate": 1.28087627938402e-06,
"loss": 8.1486,
"step": 82
},
{
"epoch": 0.7990373044524669,
"grad_norm": 49.30295944213867,
"learning_rate": 1.1806917592302763e-06,
"loss": 7.9905,
"step": 83
},
{
"epoch": 0.8086642599277978,
"grad_norm": 53.45514678955078,
"learning_rate": 1.0840600846970333e-06,
"loss": 7.7255,
"step": 84
},
{
"epoch": 0.8182912154031288,
"grad_norm": 59.27412796020508,
"learning_rate": 9.91071145732948e-07,
"loss": 7.8194,
"step": 85
},
{
"epoch": 0.8279181708784596,
"grad_norm": 39.87610626220703,
"learning_rate": 9.018114436947373e-07,
"loss": 7.9528,
"step": 86
},
{
"epoch": 0.8375451263537906,
"grad_norm": 74.84903717041016,
"learning_rate": 8.163640108807897e-07,
"loss": 7.5929,
"step": 87
},
{
"epoch": 0.8471720818291215,
"grad_norm": 36.163143157958984,
"learning_rate": 7.348083332917927e-07,
"loss": 8.0817,
"step": 88
},
{
"epoch": 0.8567990373044525,
"grad_norm": 75.65863037109375,
"learning_rate": 6.572202766902569e-07,
"loss": 7.7245,
"step": 89
},
{
"epoch": 0.8664259927797834,
"grad_norm": 34.32239532470703,
"learning_rate": 5.836720160276971e-07,
"loss": 8.0978,
"step": 90
},
{
"epoch": 0.8760529482551144,
"grad_norm": 47.71330642700195,
"learning_rate": 5.1423196830513e-07,
"loss": 7.9117,
"step": 91
},
{
"epoch": 0.8856799037304453,
"grad_norm": 60.308658599853516,
"learning_rate": 4.4896472892933693e-07,
"loss": 7.5789,
"step": 92
},
{
"epoch": 0.8953068592057761,
"grad_norm": 32.330928802490234,
"learning_rate": 3.8793101162410417e-07,
"loss": 8.0885,
"step": 93
},
{
"epoch": 0.9049338146811071,
"grad_norm": 66.5735855102539,
"learning_rate": 3.3118759195232273e-07,
"loss": 7.4854,
"step": 94
},
{
"epoch": 0.914560770156438,
"grad_norm": 35.20449447631836,
"learning_rate": 2.787872545015069e-07,
"loss": 8.0211,
"step": 95
},
{
"epoch": 0.924187725631769,
"grad_norm": 37.92588424682617,
"learning_rate": 2.307787437818365e-07,
"loss": 8.1618,
"step": 96
},
{
"epoch": 0.9338146811070999,
"grad_norm": 61.763824462890625,
"learning_rate": 1.8720671888242058e-07,
"loss": 7.7689,
"step": 97
},
{
"epoch": 0.9434416365824309,
"grad_norm": 42.408660888671875,
"learning_rate": 1.4811171192794628e-07,
"loss": 8.0395,
"step": 98
},
{
"epoch": 0.9530685920577617,
"grad_norm": 53.46616744995117,
"learning_rate": 1.1353009037437523e-07,
"loss": 7.6451,
"step": 99
},
{
"epoch": 0.9626955475330926,
"grad_norm": 34.209293365478516,
"learning_rate": 8.34940231787379e-08,
"loss": 8.0758,
"step": 100
},
{
"epoch": 0.9626955475330926,
"eval_clap": 0.20374518632888794,
"eval_loss": 3.7648110389709473,
"eval_runtime": 557.5953,
"eval_samples_per_second": 0.057,
"eval_steps_per_second": 0.057,
"step": 100
},
{
"epoch": 0.9723225030084236,
"grad_norm": 63.23237228393555,
"learning_rate": 5.803145087451945e-08,
"loss": 7.5566,
"step": 101
},
{
"epoch": 0.9819494584837545,
"grad_norm": 52.794029235839844,
"learning_rate": 3.716605958046071e-08,
"loss": 7.7234,
"step": 102
},
{
"epoch": 0.9915764139590855,
"grad_norm": 46.99095916748047,
"learning_rate": 2.0917258966953735e-08,
"loss": 7.7302,
"step": 103
},
{
"epoch": 0.9915764139590855,
"step": 103,
"total_flos": 168544032748224.0,
"train_loss": 8.598366718847775,
"train_runtime": 2954.9231,
"train_samples_per_second": 0.281,
"train_steps_per_second": 0.035
}
],
"logging_steps": 1.0,
"max_steps": 103,
"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": 168544032748224.0,
"train_batch_size": 1,
"trial_name": null,
"trial_params": null
}