nttx's picture
Training in progress, step 100, checkpoint
7a65b9a verified
raw
history blame
19.5 kB
{
"best_metric": 0.11629380285739899,
"best_model_checkpoint": "miner_id_24/checkpoint-100",
"epoch": 0.015054006247412592,
"eval_steps": 25,
"global_step": 100,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.00015054006247412592,
"grad_norm": 0.13432709872722626,
"learning_rate": 2.9999999999999997e-05,
"loss": 0.192,
"step": 1
},
{
"epoch": 0.00015054006247412592,
"eval_loss": 0.2719675600528717,
"eval_runtime": 5.8281,
"eval_samples_per_second": 8.579,
"eval_steps_per_second": 1.201,
"step": 1
},
{
"epoch": 0.00030108012494825184,
"grad_norm": 0.13893114030361176,
"learning_rate": 5.9999999999999995e-05,
"loss": 0.2357,
"step": 2
},
{
"epoch": 0.00045162018742237776,
"grad_norm": 0.23538532853126526,
"learning_rate": 8.999999999999999e-05,
"loss": 0.2321,
"step": 3
},
{
"epoch": 0.0006021602498965037,
"grad_norm": 0.12552545964717865,
"learning_rate": 0.00011999999999999999,
"loss": 0.153,
"step": 4
},
{
"epoch": 0.0007527003123706296,
"grad_norm": 0.12770973145961761,
"learning_rate": 0.00015,
"loss": 0.2248,
"step": 5
},
{
"epoch": 0.0009032403748447555,
"grad_norm": 0.13605402410030365,
"learning_rate": 0.00017999999999999998,
"loss": 0.201,
"step": 6
},
{
"epoch": 0.0010537804373188814,
"grad_norm": 0.1637810617685318,
"learning_rate": 0.00020999999999999998,
"loss": 0.2183,
"step": 7
},
{
"epoch": 0.0012043204997930074,
"grad_norm": 0.12221050262451172,
"learning_rate": 0.00023999999999999998,
"loss": 0.124,
"step": 8
},
{
"epoch": 0.0013548605622671333,
"grad_norm": 0.1582375317811966,
"learning_rate": 0.00027,
"loss": 0.162,
"step": 9
},
{
"epoch": 0.0015054006247412592,
"grad_norm": 0.13441474735736847,
"learning_rate": 0.0003,
"loss": 0.1341,
"step": 10
},
{
"epoch": 0.0016559406872153851,
"grad_norm": 0.17374110221862793,
"learning_rate": 0.0002999794957488703,
"loss": 0.2062,
"step": 11
},
{
"epoch": 0.001806480749689511,
"grad_norm": 0.14382176101207733,
"learning_rate": 0.0002999179886011389,
"loss": 0.1631,
"step": 12
},
{
"epoch": 0.001957020812163637,
"grad_norm": 0.11867301911115646,
"learning_rate": 0.0002998154953722457,
"loss": 0.1372,
"step": 13
},
{
"epoch": 0.002107560874637763,
"grad_norm": 0.10297456383705139,
"learning_rate": 0.00029967204408281613,
"loss": 0.1205,
"step": 14
},
{
"epoch": 0.002258100937111889,
"grad_norm": 0.13378922641277313,
"learning_rate": 0.00029948767395100045,
"loss": 0.173,
"step": 15
},
{
"epoch": 0.0024086409995860147,
"grad_norm": 0.2846575081348419,
"learning_rate": 0.0002992624353817517,
"loss": 0.2639,
"step": 16
},
{
"epoch": 0.0025591810620601407,
"grad_norm": 0.21519090235233307,
"learning_rate": 0.0002989963899530457,
"loss": 0.2581,
"step": 17
},
{
"epoch": 0.0027097211245342666,
"grad_norm": 0.19943968951702118,
"learning_rate": 0.00029868961039904624,
"loss": 0.2171,
"step": 18
},
{
"epoch": 0.0028602611870083925,
"grad_norm": 0.20476272702217102,
"learning_rate": 0.00029834218059022024,
"loss": 0.3608,
"step": 19
},
{
"epoch": 0.0030108012494825184,
"grad_norm": 0.18420757353305817,
"learning_rate": 0.00029795419551040833,
"loss": 0.2178,
"step": 20
},
{
"epoch": 0.0031613413119566443,
"grad_norm": 0.1748962551355362,
"learning_rate": 0.00029752576123085736,
"loss": 0.2517,
"step": 21
},
{
"epoch": 0.0033118813744307703,
"grad_norm": 0.20323532819747925,
"learning_rate": 0.0002970569948812214,
"loss": 0.2238,
"step": 22
},
{
"epoch": 0.003462421436904896,
"grad_norm": 0.2342359721660614,
"learning_rate": 0.0002965480246175399,
"loss": 0.2862,
"step": 23
},
{
"epoch": 0.003612961499379022,
"grad_norm": 0.14597725868225098,
"learning_rate": 0.0002959989895872009,
"loss": 0.1902,
"step": 24
},
{
"epoch": 0.003763501561853148,
"grad_norm": 0.1760072559118271,
"learning_rate": 0.0002954100398908995,
"loss": 0.2673,
"step": 25
},
{
"epoch": 0.003763501561853148,
"eval_loss": 0.1731989085674286,
"eval_runtime": 5.8861,
"eval_samples_per_second": 8.495,
"eval_steps_per_second": 1.189,
"step": 25
},
{
"epoch": 0.003914041624327274,
"grad_norm": 0.16469714045524597,
"learning_rate": 0.0002947813365416023,
"loss": 0.2375,
"step": 26
},
{
"epoch": 0.0040645816868014,
"grad_norm": 0.1807279884815216,
"learning_rate": 0.0002941130514205272,
"loss": 0.2787,
"step": 27
},
{
"epoch": 0.004215121749275526,
"grad_norm": 0.1720961630344391,
"learning_rate": 0.0002934053672301536,
"loss": 0.2626,
"step": 28
},
{
"epoch": 0.004365661811749652,
"grad_norm": 0.17341332137584686,
"learning_rate": 0.00029265847744427303,
"loss": 0.2325,
"step": 29
},
{
"epoch": 0.004516201874223778,
"grad_norm": 0.16063857078552246,
"learning_rate": 0.00029187258625509513,
"loss": 0.2144,
"step": 30
},
{
"epoch": 0.0046667419366979036,
"grad_norm": 0.166489839553833,
"learning_rate": 0.00029104790851742417,
"loss": 0.2199,
"step": 31
},
{
"epoch": 0.0048172819991720295,
"grad_norm": 0.1735871136188507,
"learning_rate": 0.0002901846696899191,
"loss": 0.2436,
"step": 32
},
{
"epoch": 0.004967822061646155,
"grad_norm": 0.17148464918136597,
"learning_rate": 0.00028928310577345606,
"loss": 0.2547,
"step": 33
},
{
"epoch": 0.005118362124120281,
"grad_norm": 0.17381110787391663,
"learning_rate": 0.0002883434632466077,
"loss": 0.2313,
"step": 34
},
{
"epoch": 0.005268902186594407,
"grad_norm": 0.19464297592639923,
"learning_rate": 0.00028736599899825856,
"loss": 0.2857,
"step": 35
},
{
"epoch": 0.005419442249068533,
"grad_norm": 0.17032398283481598,
"learning_rate": 0.00028635098025737434,
"loss": 0.2546,
"step": 36
},
{
"epoch": 0.005569982311542659,
"grad_norm": 0.190896674990654,
"learning_rate": 0.00028529868451994384,
"loss": 0.2831,
"step": 37
},
{
"epoch": 0.005720522374016785,
"grad_norm": 0.24636401236057281,
"learning_rate": 0.0002842093994731145,
"loss": 0.3094,
"step": 38
},
{
"epoch": 0.005871062436490911,
"grad_norm": 0.17670078575611115,
"learning_rate": 0.00028308342291654174,
"loss": 0.2858,
"step": 39
},
{
"epoch": 0.006021602498965037,
"grad_norm": 0.23208720982074738,
"learning_rate": 0.00028192106268097334,
"loss": 0.3023,
"step": 40
},
{
"epoch": 0.006172142561439163,
"grad_norm": 0.22071202099323273,
"learning_rate": 0.00028072263654409154,
"loss": 0.3636,
"step": 41
},
{
"epoch": 0.006322682623913289,
"grad_norm": 0.19284580647945404,
"learning_rate": 0.0002794884721436361,
"loss": 0.2341,
"step": 42
},
{
"epoch": 0.006473222686387415,
"grad_norm": 0.20681974291801453,
"learning_rate": 0.00027821890688783083,
"loss": 0.2126,
"step": 43
},
{
"epoch": 0.0066237627488615405,
"grad_norm": 0.22657203674316406,
"learning_rate": 0.0002769142878631403,
"loss": 0.2376,
"step": 44
},
{
"epoch": 0.0067743028113356665,
"grad_norm": 0.2658374309539795,
"learning_rate": 0.00027557497173937923,
"loss": 0.2796,
"step": 45
},
{
"epoch": 0.006924842873809792,
"grad_norm": 0.19090871512889862,
"learning_rate": 0.000274201324672203,
"loss": 0.1877,
"step": 46
},
{
"epoch": 0.007075382936283918,
"grad_norm": 0.2513241767883301,
"learning_rate": 0.00027279372220300385,
"loss": 0.2573,
"step": 47
},
{
"epoch": 0.007225922998758044,
"grad_norm": 0.29451292753219604,
"learning_rate": 0.0002713525491562421,
"loss": 0.264,
"step": 48
},
{
"epoch": 0.00737646306123217,
"grad_norm": 0.2619107663631439,
"learning_rate": 0.00026987819953423867,
"loss": 0.2481,
"step": 49
},
{
"epoch": 0.007527003123706296,
"grad_norm": 0.3190884590148926,
"learning_rate": 0.00026837107640945905,
"loss": 0.2778,
"step": 50
},
{
"epoch": 0.007527003123706296,
"eval_loss": 0.15092426538467407,
"eval_runtime": 5.883,
"eval_samples_per_second": 8.499,
"eval_steps_per_second": 1.19,
"step": 50
},
{
"epoch": 0.007677543186180422,
"grad_norm": 0.1401667445898056,
"learning_rate": 0.0002668315918143169,
"loss": 0.1223,
"step": 51
},
{
"epoch": 0.007828083248654548,
"grad_norm": 0.13726787269115448,
"learning_rate": 0.00026526016662852886,
"loss": 0.1403,
"step": 52
},
{
"epoch": 0.007978623311128674,
"grad_norm": 0.14362362027168274,
"learning_rate": 0.00026365723046405023,
"loss": 0.1686,
"step": 53
},
{
"epoch": 0.0081291633736028,
"grad_norm": 0.1130962073802948,
"learning_rate": 0.0002620232215476231,
"loss": 0.1077,
"step": 54
},
{
"epoch": 0.008279703436076926,
"grad_norm": 0.11369391530752182,
"learning_rate": 0.0002603585866009697,
"loss": 0.1216,
"step": 55
},
{
"epoch": 0.008430243498551052,
"grad_norm": 0.1306382417678833,
"learning_rate": 0.00025866378071866334,
"loss": 0.086,
"step": 56
},
{
"epoch": 0.008580783561025178,
"grad_norm": 0.14394906163215637,
"learning_rate": 0.00025693926724370956,
"loss": 0.097,
"step": 57
},
{
"epoch": 0.008731323623499303,
"grad_norm": 0.1420009285211563,
"learning_rate": 0.00025518551764087326,
"loss": 0.139,
"step": 58
},
{
"epoch": 0.00888186368597343,
"grad_norm": 0.13858570158481598,
"learning_rate": 0.00025340301136778483,
"loss": 0.1434,
"step": 59
},
{
"epoch": 0.009032403748447555,
"grad_norm": 0.11388222873210907,
"learning_rate": 0.00025159223574386114,
"loss": 0.0768,
"step": 60
},
{
"epoch": 0.009182943810921681,
"grad_norm": 0.11433927714824677,
"learning_rate": 0.0002497536858170772,
"loss": 0.0825,
"step": 61
},
{
"epoch": 0.009333483873395807,
"grad_norm": 0.11547299474477768,
"learning_rate": 0.00024788786422862526,
"loss": 0.1096,
"step": 62
},
{
"epoch": 0.009484023935869933,
"grad_norm": 0.12787331640720367,
"learning_rate": 0.00024599528107549745,
"loss": 0.117,
"step": 63
},
{
"epoch": 0.009634563998344059,
"grad_norm": 0.10538256913423538,
"learning_rate": 0.00024407645377103054,
"loss": 0.07,
"step": 64
},
{
"epoch": 0.009785104060818185,
"grad_norm": 0.1287563145160675,
"learning_rate": 0.00024213190690345018,
"loss": 0.0919,
"step": 65
},
{
"epoch": 0.00993564412329231,
"grad_norm": 0.11719094216823578,
"learning_rate": 0.00024016217209245374,
"loss": 0.0887,
"step": 66
},
{
"epoch": 0.010086184185766437,
"grad_norm": 0.17247700691223145,
"learning_rate": 0.00023816778784387094,
"loss": 0.1397,
"step": 67
},
{
"epoch": 0.010236724248240563,
"grad_norm": 0.24622748792171478,
"learning_rate": 0.0002361492994024415,
"loss": 0.1682,
"step": 68
},
{
"epoch": 0.010387264310714689,
"grad_norm": 0.2091142237186432,
"learning_rate": 0.0002341072586027509,
"loss": 0.1091,
"step": 69
},
{
"epoch": 0.010537804373188814,
"grad_norm": 0.24608778953552246,
"learning_rate": 0.00023204222371836405,
"loss": 0.2397,
"step": 70
},
{
"epoch": 0.01068834443566294,
"grad_norm": 0.308851033449173,
"learning_rate": 0.00022995475930919905,
"loss": 0.1596,
"step": 71
},
{
"epoch": 0.010838884498137066,
"grad_norm": 0.23022933304309845,
"learning_rate": 0.00022784543606718227,
"loss": 0.1739,
"step": 72
},
{
"epoch": 0.010989424560611192,
"grad_norm": 0.1964433789253235,
"learning_rate": 0.00022571483066022657,
"loss": 0.1933,
"step": 73
},
{
"epoch": 0.011139964623085318,
"grad_norm": 0.2195066511631012,
"learning_rate": 0.0002235635255745762,
"loss": 0.2146,
"step": 74
},
{
"epoch": 0.011290504685559444,
"grad_norm": 0.21165235340595245,
"learning_rate": 0.00022139210895556104,
"loss": 0.1528,
"step": 75
},
{
"epoch": 0.011290504685559444,
"eval_loss": 0.12030501663684845,
"eval_runtime": 5.8823,
"eval_samples_per_second": 8.5,
"eval_steps_per_second": 1.19,
"step": 75
},
{
"epoch": 0.01144104474803357,
"grad_norm": 0.30299341678619385,
"learning_rate": 0.00021920117444680317,
"loss": 0.2136,
"step": 76
},
{
"epoch": 0.011591584810507696,
"grad_norm": 0.2567080855369568,
"learning_rate": 0.00021699132102792097,
"loss": 0.1794,
"step": 77
},
{
"epoch": 0.011742124872981822,
"grad_norm": 0.19719505310058594,
"learning_rate": 0.0002147631528507739,
"loss": 0.1988,
"step": 78
},
{
"epoch": 0.011892664935455948,
"grad_norm": 0.22220024466514587,
"learning_rate": 0.00021251727907429355,
"loss": 0.1759,
"step": 79
},
{
"epoch": 0.012043204997930074,
"grad_norm": 0.18353872001171112,
"learning_rate": 0.0002102543136979454,
"loss": 0.1792,
"step": 80
},
{
"epoch": 0.0121937450604042,
"grad_norm": 0.18121051788330078,
"learning_rate": 0.0002079748753938678,
"loss": 0.1299,
"step": 81
},
{
"epoch": 0.012344285122878326,
"grad_norm": 0.2993931174278259,
"learning_rate": 0.0002056795873377331,
"loss": 0.1858,
"step": 82
},
{
"epoch": 0.012494825185352451,
"grad_norm": 0.28290849924087524,
"learning_rate": 0.00020336907703837748,
"loss": 0.241,
"step": 83
},
{
"epoch": 0.012645365247826577,
"grad_norm": 0.2094016671180725,
"learning_rate": 0.00020104397616624645,
"loss": 0.221,
"step": 84
},
{
"epoch": 0.012795905310300703,
"grad_norm": 0.18955637514591217,
"learning_rate": 0.00019870492038070252,
"loss": 0.1413,
"step": 85
},
{
"epoch": 0.01294644537277483,
"grad_norm": 0.20471981167793274,
"learning_rate": 0.0001963525491562421,
"loss": 0.2158,
"step": 86
},
{
"epoch": 0.013096985435248955,
"grad_norm": 0.20053322613239288,
"learning_rate": 0.0001939875056076697,
"loss": 0.2066,
"step": 87
},
{
"epoch": 0.013247525497723081,
"grad_norm": 0.2138388454914093,
"learning_rate": 0.00019161043631427666,
"loss": 0.228,
"step": 88
},
{
"epoch": 0.013398065560197207,
"grad_norm": 0.2082088589668274,
"learning_rate": 0.00018922199114307294,
"loss": 0.1788,
"step": 89
},
{
"epoch": 0.013548605622671333,
"grad_norm": 0.37482932209968567,
"learning_rate": 0.00018682282307111987,
"loss": 0.1592,
"step": 90
},
{
"epoch": 0.013699145685145459,
"grad_norm": 0.292537122964859,
"learning_rate": 0.00018441358800701273,
"loss": 0.2572,
"step": 91
},
{
"epoch": 0.013849685747619585,
"grad_norm": 0.2552037239074707,
"learning_rate": 0.00018199494461156203,
"loss": 0.1872,
"step": 92
},
{
"epoch": 0.01400022581009371,
"grad_norm": 0.2402886003255844,
"learning_rate": 0.000179567554117722,
"loss": 0.2123,
"step": 93
},
{
"epoch": 0.014150765872567837,
"grad_norm": 0.24449338018894196,
"learning_rate": 0.00017713208014981648,
"loss": 0.2047,
"step": 94
},
{
"epoch": 0.014301305935041963,
"grad_norm": 0.26285871863365173,
"learning_rate": 0.00017468918854211007,
"loss": 0.2038,
"step": 95
},
{
"epoch": 0.014451845997516088,
"grad_norm": 0.25671887397766113,
"learning_rate": 0.00017223954715677627,
"loss": 0.2015,
"step": 96
},
{
"epoch": 0.014602386059990214,
"grad_norm": 0.2887267768383026,
"learning_rate": 0.00016978382570131034,
"loss": 0.1925,
"step": 97
},
{
"epoch": 0.01475292612246434,
"grad_norm": 0.28670281171798706,
"learning_rate": 0.00016732269554543794,
"loss": 0.1805,
"step": 98
},
{
"epoch": 0.014903466184938466,
"grad_norm": 0.3724100887775421,
"learning_rate": 0.00016485682953756942,
"loss": 0.2652,
"step": 99
},
{
"epoch": 0.015054006247412592,
"grad_norm": 0.3608229458332062,
"learning_rate": 0.00016238690182084986,
"loss": 0.226,
"step": 100
},
{
"epoch": 0.015054006247412592,
"eval_loss": 0.11629380285739899,
"eval_runtime": 5.8921,
"eval_samples_per_second": 8.486,
"eval_steps_per_second": 1.188,
"step": 100
}
],
"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": 1,
"early_stopping_threshold": 0.0
},
"attributes": {
"early_stopping_patience_counter": 0
}
},
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 8.00028945827758e+16,
"train_batch_size": 8,
"trial_name": null,
"trial_params": null
}