nttx's picture
Training in progress, step 200, checkpoint
26f5808 verified
raw
history blame
37 kB
{
"best_metric": 0.6421379446983337,
"best_model_checkpoint": "miner_id_24/checkpoint-150",
"epoch": 0.009240863096613223,
"eval_steps": 50,
"global_step": 200,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 4.620431548306612e-05,
"grad_norm": 0.5076673030853271,
"learning_rate": 3.3333333333333333e-06,
"loss": 1.2688,
"step": 1
},
{
"epoch": 4.620431548306612e-05,
"eval_loss": 2.6150074005126953,
"eval_runtime": 957.4031,
"eval_samples_per_second": 38.073,
"eval_steps_per_second": 19.037,
"step": 1
},
{
"epoch": 9.240863096613223e-05,
"grad_norm": 0.4707164168357849,
"learning_rate": 6.666666666666667e-06,
"loss": 1.4034,
"step": 2
},
{
"epoch": 0.00013861294644919834,
"grad_norm": 0.49893462657928467,
"learning_rate": 1e-05,
"loss": 1.3002,
"step": 3
},
{
"epoch": 0.00018481726193226447,
"grad_norm": 0.4544735550880432,
"learning_rate": 1.3333333333333333e-05,
"loss": 1.3597,
"step": 4
},
{
"epoch": 0.0002310215774153306,
"grad_norm": 0.5113587975502014,
"learning_rate": 1.6666666666666667e-05,
"loss": 1.4907,
"step": 5
},
{
"epoch": 0.0002772258928983967,
"grad_norm": 0.49932631850242615,
"learning_rate": 2e-05,
"loss": 1.5368,
"step": 6
},
{
"epoch": 0.00032343020838146284,
"grad_norm": 0.49129220843315125,
"learning_rate": 2.3333333333333336e-05,
"loss": 1.4715,
"step": 7
},
{
"epoch": 0.00036963452386452894,
"grad_norm": 0.5280050039291382,
"learning_rate": 2.6666666666666667e-05,
"loss": 1.5247,
"step": 8
},
{
"epoch": 0.0004158388393475951,
"grad_norm": 0.5901511311531067,
"learning_rate": 3e-05,
"loss": 1.6846,
"step": 9
},
{
"epoch": 0.0004620431548306612,
"grad_norm": 0.5997692346572876,
"learning_rate": 3.3333333333333335e-05,
"loss": 1.7587,
"step": 10
},
{
"epoch": 0.0005082474703137273,
"grad_norm": 0.5347150564193726,
"learning_rate": 3.6666666666666666e-05,
"loss": 1.5797,
"step": 11
},
{
"epoch": 0.0005544517857967934,
"grad_norm": 0.5770092606544495,
"learning_rate": 4e-05,
"loss": 1.8065,
"step": 12
},
{
"epoch": 0.0006006561012798596,
"grad_norm": 0.640047550201416,
"learning_rate": 4.3333333333333334e-05,
"loss": 1.756,
"step": 13
},
{
"epoch": 0.0006468604167629257,
"grad_norm": 0.6685127019882202,
"learning_rate": 4.666666666666667e-05,
"loss": 1.8463,
"step": 14
},
{
"epoch": 0.0006930647322459918,
"grad_norm": 0.6096793413162231,
"learning_rate": 5e-05,
"loss": 1.7731,
"step": 15
},
{
"epoch": 0.0007392690477290579,
"grad_norm": 0.47331157326698303,
"learning_rate": 5.333333333333333e-05,
"loss": 1.5453,
"step": 16
},
{
"epoch": 0.000785473363212124,
"grad_norm": 0.6507935523986816,
"learning_rate": 5.666666666666667e-05,
"loss": 1.9544,
"step": 17
},
{
"epoch": 0.0008316776786951902,
"grad_norm": 0.5391093492507935,
"learning_rate": 6e-05,
"loss": 1.7061,
"step": 18
},
{
"epoch": 0.0008778819941782563,
"grad_norm": 0.5378036499023438,
"learning_rate": 6.333333333333333e-05,
"loss": 1.5813,
"step": 19
},
{
"epoch": 0.0009240863096613224,
"grad_norm": 0.47087186574935913,
"learning_rate": 6.666666666666667e-05,
"loss": 1.4304,
"step": 20
},
{
"epoch": 0.0009702906251443885,
"grad_norm": 0.5405943989753723,
"learning_rate": 7e-05,
"loss": 1.706,
"step": 21
},
{
"epoch": 0.0010164949406274546,
"grad_norm": 0.4968361258506775,
"learning_rate": 7.333333333333333e-05,
"loss": 1.4416,
"step": 22
},
{
"epoch": 0.0010626992561105207,
"grad_norm": 0.6123631596565247,
"learning_rate": 7.666666666666667e-05,
"loss": 1.6009,
"step": 23
},
{
"epoch": 0.0011089035715935868,
"grad_norm": 0.651899516582489,
"learning_rate": 8e-05,
"loss": 1.6598,
"step": 24
},
{
"epoch": 0.0011551078870766529,
"grad_norm": 0.6122700572013855,
"learning_rate": 8.333333333333334e-05,
"loss": 1.5412,
"step": 25
},
{
"epoch": 0.0012013122025597192,
"grad_norm": 0.5154715776443481,
"learning_rate": 8.666666666666667e-05,
"loss": 1.3952,
"step": 26
},
{
"epoch": 0.0012475165180427853,
"grad_norm": 0.5692221522331238,
"learning_rate": 9e-05,
"loss": 1.4373,
"step": 27
},
{
"epoch": 0.0012937208335258514,
"grad_norm": 0.6106476187705994,
"learning_rate": 9.333333333333334e-05,
"loss": 1.4265,
"step": 28
},
{
"epoch": 0.0013399251490089175,
"grad_norm": 0.5000233054161072,
"learning_rate": 9.666666666666667e-05,
"loss": 1.0467,
"step": 29
},
{
"epoch": 0.0013861294644919836,
"grad_norm": 0.5108127593994141,
"learning_rate": 0.0001,
"loss": 0.9634,
"step": 30
},
{
"epoch": 0.0014323337799750497,
"grad_norm": 0.5342124104499817,
"learning_rate": 9.999146252290264e-05,
"loss": 1.0977,
"step": 31
},
{
"epoch": 0.0014785380954581157,
"grad_norm": 0.475253164768219,
"learning_rate": 9.996585300715116e-05,
"loss": 1.1091,
"step": 32
},
{
"epoch": 0.0015247424109411818,
"grad_norm": 0.4190135896205902,
"learning_rate": 9.99231801983717e-05,
"loss": 1.0745,
"step": 33
},
{
"epoch": 0.001570946726424248,
"grad_norm": 0.454335480928421,
"learning_rate": 9.986345866928941e-05,
"loss": 0.9677,
"step": 34
},
{
"epoch": 0.001617151041907314,
"grad_norm": 0.5590494871139526,
"learning_rate": 9.978670881475172e-05,
"loss": 1.1762,
"step": 35
},
{
"epoch": 0.0016633553573903804,
"grad_norm": 0.5425230860710144,
"learning_rate": 9.96929568447637e-05,
"loss": 0.8319,
"step": 36
},
{
"epoch": 0.0017095596728734464,
"grad_norm": 0.5821622610092163,
"learning_rate": 9.958223477553714e-05,
"loss": 1.1842,
"step": 37
},
{
"epoch": 0.0017557639883565125,
"grad_norm": 0.6131502985954285,
"learning_rate": 9.94545804185573e-05,
"loss": 1.0638,
"step": 38
},
{
"epoch": 0.0018019683038395786,
"grad_norm": 0.7071466445922852,
"learning_rate": 9.931003736767013e-05,
"loss": 0.8615,
"step": 39
},
{
"epoch": 0.0018481726193226447,
"grad_norm": 0.5414029359817505,
"learning_rate": 9.91486549841951e-05,
"loss": 0.928,
"step": 40
},
{
"epoch": 0.0018943769348057108,
"grad_norm": 0.5337193012237549,
"learning_rate": 9.89704883800683e-05,
"loss": 0.8243,
"step": 41
},
{
"epoch": 0.001940581250288777,
"grad_norm": 0.5797553658485413,
"learning_rate": 9.877559839902184e-05,
"loss": 1.0262,
"step": 42
},
{
"epoch": 0.001986785565771843,
"grad_norm": 0.42586958408355713,
"learning_rate": 9.85640515958057e-05,
"loss": 0.7431,
"step": 43
},
{
"epoch": 0.002032989881254909,
"grad_norm": 0.4883628189563751,
"learning_rate": 9.833592021345937e-05,
"loss": 1.0385,
"step": 44
},
{
"epoch": 0.0020791941967379752,
"grad_norm": 0.49928346276283264,
"learning_rate": 9.809128215864097e-05,
"loss": 0.9741,
"step": 45
},
{
"epoch": 0.0021253985122210413,
"grad_norm": 0.4869343638420105,
"learning_rate": 9.783022097502204e-05,
"loss": 0.9224,
"step": 46
},
{
"epoch": 0.0021716028277041074,
"grad_norm": 0.5011721849441528,
"learning_rate": 9.755282581475769e-05,
"loss": 0.9387,
"step": 47
},
{
"epoch": 0.0022178071431871735,
"grad_norm": 0.4684049189090729,
"learning_rate": 9.725919140804099e-05,
"loss": 1.0372,
"step": 48
},
{
"epoch": 0.0022640114586702396,
"grad_norm": 0.4781642258167267,
"learning_rate": 9.694941803075283e-05,
"loss": 0.9302,
"step": 49
},
{
"epoch": 0.0023102157741533057,
"grad_norm": 0.4801224172115326,
"learning_rate": 9.662361147021779e-05,
"loss": 0.8316,
"step": 50
},
{
"epoch": 0.0023102157741533057,
"eval_loss": 0.7963826656341553,
"eval_runtime": 949.1046,
"eval_samples_per_second": 38.406,
"eval_steps_per_second": 19.203,
"step": 50
},
{
"epoch": 0.0023564200896363722,
"grad_norm": 0.3222690522670746,
"learning_rate": 9.628188298907782e-05,
"loss": 0.6702,
"step": 51
},
{
"epoch": 0.0024026244051194383,
"grad_norm": 0.3845457136631012,
"learning_rate": 9.592434928729616e-05,
"loss": 0.3937,
"step": 52
},
{
"epoch": 0.0024488287206025044,
"grad_norm": 0.4016472399234772,
"learning_rate": 9.555113246230442e-05,
"loss": 0.5014,
"step": 53
},
{
"epoch": 0.0024950330360855705,
"grad_norm": 0.21051602065563202,
"learning_rate": 9.516235996730645e-05,
"loss": 0.3835,
"step": 54
},
{
"epoch": 0.0025412373515686366,
"grad_norm": 0.32177630066871643,
"learning_rate": 9.475816456775313e-05,
"loss": 0.52,
"step": 55
},
{
"epoch": 0.0025874416670517027,
"grad_norm": 0.3018689751625061,
"learning_rate": 9.43386842960031e-05,
"loss": 0.5665,
"step": 56
},
{
"epoch": 0.002633645982534769,
"grad_norm": 0.24280551075935364,
"learning_rate": 9.39040624041849e-05,
"loss": 0.4877,
"step": 57
},
{
"epoch": 0.002679850298017835,
"grad_norm": 0.20828717947006226,
"learning_rate": 9.345444731527642e-05,
"loss": 0.4176,
"step": 58
},
{
"epoch": 0.002726054613500901,
"grad_norm": 0.18063269555568695,
"learning_rate": 9.298999257241863e-05,
"loss": 0.5384,
"step": 59
},
{
"epoch": 0.002772258928983967,
"grad_norm": 0.277569442987442,
"learning_rate": 9.251085678648072e-05,
"loss": 0.4104,
"step": 60
},
{
"epoch": 0.002818463244467033,
"grad_norm": 0.29315823316574097,
"learning_rate": 9.201720358189464e-05,
"loss": 0.5355,
"step": 61
},
{
"epoch": 0.0028646675599500993,
"grad_norm": 0.24790503084659576,
"learning_rate": 9.150920154077754e-05,
"loss": 0.5383,
"step": 62
},
{
"epoch": 0.0029108718754331654,
"grad_norm": 0.22097140550613403,
"learning_rate": 9.098702414536107e-05,
"loss": 0.536,
"step": 63
},
{
"epoch": 0.0029570761909162315,
"grad_norm": 0.23576390743255615,
"learning_rate": 9.045084971874738e-05,
"loss": 0.4857,
"step": 64
},
{
"epoch": 0.0030032805063992976,
"grad_norm": 0.31752127408981323,
"learning_rate": 8.9900861364012e-05,
"loss": 0.5439,
"step": 65
},
{
"epoch": 0.0030494848218823637,
"grad_norm": 0.33295369148254395,
"learning_rate": 8.933724690167417e-05,
"loss": 0.6619,
"step": 66
},
{
"epoch": 0.00309568913736543,
"grad_norm": 0.24967357516288757,
"learning_rate": 8.876019880555649e-05,
"loss": 0.4586,
"step": 67
},
{
"epoch": 0.003141893452848496,
"grad_norm": 0.3030238449573517,
"learning_rate": 8.816991413705516e-05,
"loss": 0.6095,
"step": 68
},
{
"epoch": 0.003188097768331562,
"grad_norm": 0.2835695147514343,
"learning_rate": 8.756659447784368e-05,
"loss": 0.6811,
"step": 69
},
{
"epoch": 0.003234302083814628,
"grad_norm": 0.21882100403308868,
"learning_rate": 8.695044586103296e-05,
"loss": 0.4792,
"step": 70
},
{
"epoch": 0.0032805063992976946,
"grad_norm": 0.31645792722702026,
"learning_rate": 8.632167870081121e-05,
"loss": 0.6682,
"step": 71
},
{
"epoch": 0.0033267107147807607,
"grad_norm": 0.17226547002792358,
"learning_rate": 8.568050772058762e-05,
"loss": 0.3664,
"step": 72
},
{
"epoch": 0.003372915030263827,
"grad_norm": 0.21164900064468384,
"learning_rate": 8.502715187966455e-05,
"loss": 0.5181,
"step": 73
},
{
"epoch": 0.003419119345746893,
"grad_norm": 0.2374795526266098,
"learning_rate": 8.436183429846313e-05,
"loss": 0.5285,
"step": 74
},
{
"epoch": 0.003465323661229959,
"grad_norm": 0.2672363817691803,
"learning_rate": 8.368478218232787e-05,
"loss": 0.5057,
"step": 75
},
{
"epoch": 0.003511527976713025,
"grad_norm": 0.23033465445041656,
"learning_rate": 8.299622674393614e-05,
"loss": 0.5224,
"step": 76
},
{
"epoch": 0.003557732292196091,
"grad_norm": 0.2521456778049469,
"learning_rate": 8.229640312433937e-05,
"loss": 0.5363,
"step": 77
},
{
"epoch": 0.0036039366076791573,
"grad_norm": 0.3108648657798767,
"learning_rate": 8.158555031266254e-05,
"loss": 0.5886,
"step": 78
},
{
"epoch": 0.0036501409231622234,
"grad_norm": 0.2801637351512909,
"learning_rate": 8.086391106448965e-05,
"loss": 0.5706,
"step": 79
},
{
"epoch": 0.0036963452386452895,
"grad_norm": 0.2559647262096405,
"learning_rate": 8.013173181896283e-05,
"loss": 0.5647,
"step": 80
},
{
"epoch": 0.0037425495541283556,
"grad_norm": 0.23344534635543823,
"learning_rate": 7.938926261462366e-05,
"loss": 0.4891,
"step": 81
},
{
"epoch": 0.0037887538696114217,
"grad_norm": 0.2664535939693451,
"learning_rate": 7.863675700402526e-05,
"loss": 0.5494,
"step": 82
},
{
"epoch": 0.0038349581850944878,
"grad_norm": 0.31824880838394165,
"learning_rate": 7.787447196714427e-05,
"loss": 0.6566,
"step": 83
},
{
"epoch": 0.003881162500577554,
"grad_norm": 0.29656538367271423,
"learning_rate": 7.710266782362247e-05,
"loss": 0.6361,
"step": 84
},
{
"epoch": 0.00392736681606062,
"grad_norm": 0.30476269125938416,
"learning_rate": 7.63216081438678e-05,
"loss": 0.6621,
"step": 85
},
{
"epoch": 0.003973571131543686,
"grad_norm": 0.29754209518432617,
"learning_rate": 7.553155965904535e-05,
"loss": 0.7092,
"step": 86
},
{
"epoch": 0.004019775447026752,
"grad_norm": 0.28509530425071716,
"learning_rate": 7.473279216998895e-05,
"loss": 0.6042,
"step": 87
},
{
"epoch": 0.004065979762509818,
"grad_norm": 0.39861199259757996,
"learning_rate": 7.392557845506432e-05,
"loss": 0.8293,
"step": 88
},
{
"epoch": 0.004112184077992884,
"grad_norm": 0.28901976346969604,
"learning_rate": 7.311019417701566e-05,
"loss": 0.5748,
"step": 89
},
{
"epoch": 0.0041583883934759504,
"grad_norm": 0.3572286367416382,
"learning_rate": 7.228691778882693e-05,
"loss": 0.6117,
"step": 90
},
{
"epoch": 0.0042045927089590165,
"grad_norm": 0.3332473039627075,
"learning_rate": 7.145603043863045e-05,
"loss": 0.653,
"step": 91
},
{
"epoch": 0.004250797024442083,
"grad_norm": 0.3621080815792084,
"learning_rate": 7.061781587369519e-05,
"loss": 0.6299,
"step": 92
},
{
"epoch": 0.004297001339925149,
"grad_norm": 0.4089956283569336,
"learning_rate": 6.977256034352712e-05,
"loss": 0.8945,
"step": 93
},
{
"epoch": 0.004343205655408215,
"grad_norm": 0.3218964636325836,
"learning_rate": 6.892055250211552e-05,
"loss": 0.7201,
"step": 94
},
{
"epoch": 0.004389409970891281,
"grad_norm": 0.3587651252746582,
"learning_rate": 6.806208330935766e-05,
"loss": 0.7803,
"step": 95
},
{
"epoch": 0.004435614286374347,
"grad_norm": 0.3168658912181854,
"learning_rate": 6.719744593169641e-05,
"loss": 0.7799,
"step": 96
},
{
"epoch": 0.004481818601857413,
"grad_norm": 0.4870496988296509,
"learning_rate": 6.632693564200416e-05,
"loss": 0.9183,
"step": 97
},
{
"epoch": 0.004528022917340479,
"grad_norm": 0.31272202730178833,
"learning_rate": 6.545084971874738e-05,
"loss": 0.768,
"step": 98
},
{
"epoch": 0.004574227232823545,
"grad_norm": 0.300275057554245,
"learning_rate": 6.456948734446624e-05,
"loss": 0.6447,
"step": 99
},
{
"epoch": 0.004620431548306611,
"grad_norm": 0.377289354801178,
"learning_rate": 6.368314950360415e-05,
"loss": 0.7445,
"step": 100
},
{
"epoch": 0.004620431548306611,
"eval_loss": 0.6734322309494019,
"eval_runtime": 950.0633,
"eval_samples_per_second": 38.367,
"eval_steps_per_second": 19.184,
"step": 100
},
{
"epoch": 0.004666635863789678,
"grad_norm": 0.2588423788547516,
"learning_rate": 6.279213887972179e-05,
"loss": 0.7065,
"step": 101
},
{
"epoch": 0.0047128401792727445,
"grad_norm": 0.21197082102298737,
"learning_rate": 6.189675975213094e-05,
"loss": 0.2932,
"step": 102
},
{
"epoch": 0.004759044494755811,
"grad_norm": 0.22588442265987396,
"learning_rate": 6.099731789198344e-05,
"loss": 0.3405,
"step": 103
},
{
"epoch": 0.004805248810238877,
"grad_norm": 0.25069916248321533,
"learning_rate": 6.009412045785051e-05,
"loss": 0.4191,
"step": 104
},
{
"epoch": 0.004851453125721943,
"grad_norm": 0.24258778989315033,
"learning_rate": 5.918747589082853e-05,
"loss": 0.355,
"step": 105
},
{
"epoch": 0.004897657441205009,
"grad_norm": 0.20508873462677002,
"learning_rate": 5.82776938092065e-05,
"loss": 0.3554,
"step": 106
},
{
"epoch": 0.004943861756688075,
"grad_norm": 0.2670445442199707,
"learning_rate": 5.736508490273188e-05,
"loss": 0.5443,
"step": 107
},
{
"epoch": 0.004990066072171141,
"grad_norm": 0.24584536254405975,
"learning_rate": 5.644996082651017e-05,
"loss": 0.4639,
"step": 108
},
{
"epoch": 0.005036270387654207,
"grad_norm": 0.2456938475370407,
"learning_rate": 5.553263409457504e-05,
"loss": 0.4195,
"step": 109
},
{
"epoch": 0.005082474703137273,
"grad_norm": 0.25109416246414185,
"learning_rate": 5.4613417973165106e-05,
"loss": 0.487,
"step": 110
},
{
"epoch": 0.005128679018620339,
"grad_norm": 0.1877359002828598,
"learning_rate": 5.3692626373743706e-05,
"loss": 0.4365,
"step": 111
},
{
"epoch": 0.0051748833341034054,
"grad_norm": 0.19817650318145752,
"learning_rate": 5.27705737457985e-05,
"loss": 0.327,
"step": 112
},
{
"epoch": 0.0052210876495864715,
"grad_norm": 0.198269784450531,
"learning_rate": 5.184757496945726e-05,
"loss": 0.4454,
"step": 113
},
{
"epoch": 0.005267291965069538,
"grad_norm": 0.22586289048194885,
"learning_rate": 5.092394524795649e-05,
"loss": 0.4795,
"step": 114
},
{
"epoch": 0.005313496280552604,
"grad_norm": 0.2628689706325531,
"learning_rate": 5e-05,
"loss": 0.4899,
"step": 115
},
{
"epoch": 0.00535970059603567,
"grad_norm": 0.2354358434677124,
"learning_rate": 4.907605475204352e-05,
"loss": 0.4658,
"step": 116
},
{
"epoch": 0.005405904911518736,
"grad_norm": 0.23226183652877808,
"learning_rate": 4.8152425030542766e-05,
"loss": 0.5188,
"step": 117
},
{
"epoch": 0.005452109227001802,
"grad_norm": 0.25832581520080566,
"learning_rate": 4.72294262542015e-05,
"loss": 0.482,
"step": 118
},
{
"epoch": 0.005498313542484868,
"grad_norm": 0.21811699867248535,
"learning_rate": 4.6307373626256306e-05,
"loss": 0.4764,
"step": 119
},
{
"epoch": 0.005544517857967934,
"grad_norm": 0.19816286861896515,
"learning_rate": 4.5386582026834906e-05,
"loss": 0.4253,
"step": 120
},
{
"epoch": 0.005590722173451,
"grad_norm": 0.3619321286678314,
"learning_rate": 4.446736590542497e-05,
"loss": 0.5297,
"step": 121
},
{
"epoch": 0.005636926488934066,
"grad_norm": 0.31721270084381104,
"learning_rate": 4.3550039173489845e-05,
"loss": 0.5815,
"step": 122
},
{
"epoch": 0.0056831308044171325,
"grad_norm": 0.2503688633441925,
"learning_rate": 4.2634915097268115e-05,
"loss": 0.5621,
"step": 123
},
{
"epoch": 0.005729335119900199,
"grad_norm": 0.25126245617866516,
"learning_rate": 4.1722306190793495e-05,
"loss": 0.3979,
"step": 124
},
{
"epoch": 0.005775539435383265,
"grad_norm": 0.24463218450546265,
"learning_rate": 4.0812524109171476e-05,
"loss": 0.5177,
"step": 125
},
{
"epoch": 0.005821743750866331,
"grad_norm": 0.33323267102241516,
"learning_rate": 3.99058795421495e-05,
"loss": 0.5103,
"step": 126
},
{
"epoch": 0.005867948066349397,
"grad_norm": 0.2861713171005249,
"learning_rate": 3.9002682108016585e-05,
"loss": 0.5381,
"step": 127
},
{
"epoch": 0.005914152381832463,
"grad_norm": 0.3225221037864685,
"learning_rate": 3.8103240247869075e-05,
"loss": 0.6206,
"step": 128
},
{
"epoch": 0.005960356697315529,
"grad_norm": 0.23997412621974945,
"learning_rate": 3.720786112027822e-05,
"loss": 0.4345,
"step": 129
},
{
"epoch": 0.006006561012798595,
"grad_norm": 0.22723270952701569,
"learning_rate": 3.631685049639586e-05,
"loss": 0.5091,
"step": 130
},
{
"epoch": 0.006052765328281661,
"grad_norm": 0.31986862421035767,
"learning_rate": 3.543051265553377e-05,
"loss": 0.5041,
"step": 131
},
{
"epoch": 0.006098969643764727,
"grad_norm": 0.4289882481098175,
"learning_rate": 3.4549150281252636e-05,
"loss": 0.6675,
"step": 132
},
{
"epoch": 0.0061451739592477935,
"grad_norm": 0.24950823187828064,
"learning_rate": 3.367306435799584e-05,
"loss": 0.5478,
"step": 133
},
{
"epoch": 0.00619137827473086,
"grad_norm": 0.292449027299881,
"learning_rate": 3.2802554068303596e-05,
"loss": 0.5382,
"step": 134
},
{
"epoch": 0.006237582590213926,
"grad_norm": 0.27559009194374084,
"learning_rate": 3.1937916690642356e-05,
"loss": 0.5363,
"step": 135
},
{
"epoch": 0.006283786905696992,
"grad_norm": 0.27184924483299255,
"learning_rate": 3.107944749788449e-05,
"loss": 0.6343,
"step": 136
},
{
"epoch": 0.006329991221180058,
"grad_norm": 0.26460501551628113,
"learning_rate": 3.0227439656472877e-05,
"loss": 0.5129,
"step": 137
},
{
"epoch": 0.006376195536663124,
"grad_norm": 0.31789299845695496,
"learning_rate": 2.9382184126304834e-05,
"loss": 0.5976,
"step": 138
},
{
"epoch": 0.00642239985214619,
"grad_norm": 0.3732602000236511,
"learning_rate": 2.8543969561369556e-05,
"loss": 0.6542,
"step": 139
},
{
"epoch": 0.006468604167629256,
"grad_norm": 0.4154840111732483,
"learning_rate": 2.771308221117309e-05,
"loss": 0.6341,
"step": 140
},
{
"epoch": 0.006514808483112323,
"grad_norm": 0.43639206886291504,
"learning_rate": 2.688980582298435e-05,
"loss": 0.6507,
"step": 141
},
{
"epoch": 0.006561012798595389,
"grad_norm": 0.2488391399383545,
"learning_rate": 2.607442154493568e-05,
"loss": 0.5045,
"step": 142
},
{
"epoch": 0.006607217114078455,
"grad_norm": 0.2505655586719513,
"learning_rate": 2.5267207830011068e-05,
"loss": 0.539,
"step": 143
},
{
"epoch": 0.006653421429561521,
"grad_norm": 0.3137003779411316,
"learning_rate": 2.446844034095466e-05,
"loss": 0.741,
"step": 144
},
{
"epoch": 0.0066996257450445875,
"grad_norm": 0.4721606969833374,
"learning_rate": 2.3678391856132204e-05,
"loss": 0.8028,
"step": 145
},
{
"epoch": 0.006745830060527654,
"grad_norm": 0.325411856174469,
"learning_rate": 2.2897332176377528e-05,
"loss": 0.6541,
"step": 146
},
{
"epoch": 0.00679203437601072,
"grad_norm": 0.434574693441391,
"learning_rate": 2.2125528032855724e-05,
"loss": 0.8358,
"step": 147
},
{
"epoch": 0.006838238691493786,
"grad_norm": 0.299848735332489,
"learning_rate": 2.136324299597474e-05,
"loss": 0.6771,
"step": 148
},
{
"epoch": 0.006884443006976852,
"grad_norm": 0.3632323741912842,
"learning_rate": 2.061073738537635e-05,
"loss": 0.8139,
"step": 149
},
{
"epoch": 0.006930647322459918,
"grad_norm": 0.3702452778816223,
"learning_rate": 1.9868268181037185e-05,
"loss": 0.7374,
"step": 150
},
{
"epoch": 0.006930647322459918,
"eval_loss": 0.6421379446983337,
"eval_runtime": 951.4779,
"eval_samples_per_second": 38.31,
"eval_steps_per_second": 19.155,
"step": 150
},
{
"epoch": 0.006976851637942984,
"grad_norm": 0.2505011260509491,
"learning_rate": 1.9136088935510362e-05,
"loss": 0.7066,
"step": 151
},
{
"epoch": 0.00702305595342605,
"grad_norm": 0.22771523892879486,
"learning_rate": 1.8414449687337464e-05,
"loss": 0.2777,
"step": 152
},
{
"epoch": 0.007069260268909116,
"grad_norm": 0.19011437892913818,
"learning_rate": 1.7703596875660645e-05,
"loss": 0.3103,
"step": 153
},
{
"epoch": 0.007115464584392182,
"grad_norm": 0.217951238155365,
"learning_rate": 1.700377325606388e-05,
"loss": 0.394,
"step": 154
},
{
"epoch": 0.0071616688998752485,
"grad_norm": 0.2236698716878891,
"learning_rate": 1.631521781767214e-05,
"loss": 0.2915,
"step": 155
},
{
"epoch": 0.007207873215358315,
"grad_norm": 0.18969488143920898,
"learning_rate": 1.5638165701536868e-05,
"loss": 0.3511,
"step": 156
},
{
"epoch": 0.007254077530841381,
"grad_norm": 0.24837560951709747,
"learning_rate": 1.4972848120335453e-05,
"loss": 0.3537,
"step": 157
},
{
"epoch": 0.007300281846324447,
"grad_norm": 0.19340603053569794,
"learning_rate": 1.4319492279412388e-05,
"loss": 0.3308,
"step": 158
},
{
"epoch": 0.007346486161807513,
"grad_norm": 0.22562357783317566,
"learning_rate": 1.3678321299188801e-05,
"loss": 0.349,
"step": 159
},
{
"epoch": 0.007392690477290579,
"grad_norm": 0.22165030241012573,
"learning_rate": 1.3049554138967051e-05,
"loss": 0.4201,
"step": 160
},
{
"epoch": 0.007438894792773645,
"grad_norm": 0.19497385621070862,
"learning_rate": 1.2433405522156332e-05,
"loss": 0.3438,
"step": 161
},
{
"epoch": 0.007485099108256711,
"grad_norm": 0.24119050800800323,
"learning_rate": 1.183008586294485e-05,
"loss": 0.4641,
"step": 162
},
{
"epoch": 0.007531303423739777,
"grad_norm": 0.18582989275455475,
"learning_rate": 1.1239801194443506e-05,
"loss": 0.315,
"step": 163
},
{
"epoch": 0.007577507739222843,
"grad_norm": 0.25035154819488525,
"learning_rate": 1.066275309832584e-05,
"loss": 0.4704,
"step": 164
},
{
"epoch": 0.0076237120547059094,
"grad_norm": 0.24834051728248596,
"learning_rate": 1.0099138635988026e-05,
"loss": 0.4988,
"step": 165
},
{
"epoch": 0.0076699163701889755,
"grad_norm": 0.24904410541057587,
"learning_rate": 9.549150281252633e-06,
"loss": 0.4457,
"step": 166
},
{
"epoch": 0.007716120685672042,
"grad_norm": 0.2082366645336151,
"learning_rate": 9.012975854638949e-06,
"loss": 0.4532,
"step": 167
},
{
"epoch": 0.007762325001155108,
"grad_norm": 0.2391825169324875,
"learning_rate": 8.490798459222476e-06,
"loss": 0.4345,
"step": 168
},
{
"epoch": 0.007808529316638174,
"grad_norm": 0.25518763065338135,
"learning_rate": 7.982796418105371e-06,
"loss": 0.5175,
"step": 169
},
{
"epoch": 0.00785473363212124,
"grad_norm": 0.18920768797397614,
"learning_rate": 7.489143213519301e-06,
"loss": 0.4119,
"step": 170
},
{
"epoch": 0.007900937947604306,
"grad_norm": 0.27596113085746765,
"learning_rate": 7.010007427581378e-06,
"loss": 0.4418,
"step": 171
},
{
"epoch": 0.007947142263087372,
"grad_norm": 0.18986520171165466,
"learning_rate": 6.5455526847235825e-06,
"loss": 0.4393,
"step": 172
},
{
"epoch": 0.007993346578570438,
"grad_norm": 0.28557878732681274,
"learning_rate": 6.0959375958151045e-06,
"loss": 0.3656,
"step": 173
},
{
"epoch": 0.008039550894053504,
"grad_norm": 0.24311548471450806,
"learning_rate": 5.6613157039969055e-06,
"loss": 0.5238,
"step": 174
},
{
"epoch": 0.00808575520953657,
"grad_norm": 0.22532469034194946,
"learning_rate": 5.241835432246889e-06,
"loss": 0.6135,
"step": 175
},
{
"epoch": 0.008131959525019637,
"grad_norm": 0.21544504165649414,
"learning_rate": 4.837640032693558e-06,
"loss": 0.4251,
"step": 176
},
{
"epoch": 0.008178163840502703,
"grad_norm": 0.22226200997829437,
"learning_rate": 4.448867537695578e-06,
"loss": 0.4952,
"step": 177
},
{
"epoch": 0.008224368155985769,
"grad_norm": 0.22834548354148865,
"learning_rate": 4.075650712703849e-06,
"loss": 0.5105,
"step": 178
},
{
"epoch": 0.008270572471468835,
"grad_norm": 0.2550305724143982,
"learning_rate": 3.71811701092219e-06,
"loss": 0.576,
"step": 179
},
{
"epoch": 0.008316776786951901,
"grad_norm": 0.2729456424713135,
"learning_rate": 3.376388529782215e-06,
"loss": 0.5614,
"step": 180
},
{
"epoch": 0.008362981102434967,
"grad_norm": 0.3093857169151306,
"learning_rate": 3.0505819692471792e-06,
"loss": 0.5891,
"step": 181
},
{
"epoch": 0.008409185417918033,
"grad_norm": 0.23913784325122833,
"learning_rate": 2.7408085919590264e-06,
"loss": 0.5029,
"step": 182
},
{
"epoch": 0.0084553897334011,
"grad_norm": 0.2879793643951416,
"learning_rate": 2.4471741852423237e-06,
"loss": 0.6654,
"step": 183
},
{
"epoch": 0.008501594048884165,
"grad_norm": 0.28612762689590454,
"learning_rate": 2.1697790249779636e-06,
"loss": 0.5423,
"step": 184
},
{
"epoch": 0.008547798364367231,
"grad_norm": 0.2573546767234802,
"learning_rate": 1.908717841359048e-06,
"loss": 0.5354,
"step": 185
},
{
"epoch": 0.008594002679850297,
"grad_norm": 0.2628982365131378,
"learning_rate": 1.6640797865406288e-06,
"loss": 0.546,
"step": 186
},
{
"epoch": 0.008640206995333364,
"grad_norm": 0.34436121582984924,
"learning_rate": 1.4359484041943038e-06,
"loss": 0.5221,
"step": 187
},
{
"epoch": 0.00868641131081643,
"grad_norm": 0.2856992483139038,
"learning_rate": 1.2244016009781701e-06,
"loss": 0.5188,
"step": 188
},
{
"epoch": 0.008732615626299496,
"grad_norm": 0.2615925669670105,
"learning_rate": 1.0295116199317057e-06,
"loss": 0.5459,
"step": 189
},
{
"epoch": 0.008778819941782562,
"grad_norm": 0.30612173676490784,
"learning_rate": 8.513450158049108e-07,
"loss": 0.692,
"step": 190
},
{
"epoch": 0.008825024257265628,
"grad_norm": 0.4444868564605713,
"learning_rate": 6.899626323298713e-07,
"loss": 0.7948,
"step": 191
},
{
"epoch": 0.008871228572748694,
"grad_norm": 0.40465953946113586,
"learning_rate": 5.454195814427021e-07,
"loss": 0.6784,
"step": 192
},
{
"epoch": 0.00891743288823176,
"grad_norm": 0.3131570518016815,
"learning_rate": 4.177652244628627e-07,
"loss": 0.694,
"step": 193
},
{
"epoch": 0.008963637203714826,
"grad_norm": 0.2531670928001404,
"learning_rate": 3.0704315523631953e-07,
"loss": 0.502,
"step": 194
},
{
"epoch": 0.009009841519197892,
"grad_norm": 0.266597718000412,
"learning_rate": 2.1329118524827662e-07,
"loss": 0.5612,
"step": 195
},
{
"epoch": 0.009056045834680958,
"grad_norm": 0.33451199531555176,
"learning_rate": 1.3654133071059893e-07,
"loss": 0.6737,
"step": 196
},
{
"epoch": 0.009102250150164025,
"grad_norm": 0.39705005288124084,
"learning_rate": 7.681980162830282e-08,
"loss": 0.6853,
"step": 197
},
{
"epoch": 0.00914845446564709,
"grad_norm": 0.44060179591178894,
"learning_rate": 3.4146992848854695e-08,
"loss": 0.8037,
"step": 198
},
{
"epoch": 0.009194658781130157,
"grad_norm": 0.39385107159614563,
"learning_rate": 8.537477097364522e-09,
"loss": 0.7855,
"step": 199
},
{
"epoch": 0.009240863096613223,
"grad_norm": 0.42565372586250305,
"learning_rate": 0.0,
"loss": 0.7798,
"step": 200
},
{
"epoch": 0.009240863096613223,
"eval_loss": 0.642300009727478,
"eval_runtime": 953.0502,
"eval_samples_per_second": 38.247,
"eval_steps_per_second": 19.124,
"step": 200
}
],
"logging_steps": 1,
"max_steps": 200,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 50,
"stateful_callbacks": {
"EarlyStoppingCallback": {
"args": {
"early_stopping_patience": 5,
"early_stopping_threshold": 0.0
},
"attributes": {
"early_stopping_patience_counter": 1
}
},
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 1.394382546665472e+16,
"train_batch_size": 8,
"trial_name": null,
"trial_params": null
}