971 lines
26 KiB
JSON
971 lines
26 KiB
JSON
{
|
|
"best_metric": null,
|
|
"best_model_checkpoint": null,
|
|
"epoch": 4.0,
|
|
"eval_steps": 500,
|
|
"global_step": 116,
|
|
"is_hyper_param_search": false,
|
|
"is_local_process_zero": true,
|
|
"is_world_process_zero": true,
|
|
"log_history": [
|
|
{
|
|
"epoch": 0.034482758620689655,
|
|
"grad_norm": 40.85477828979492,
|
|
"learning_rate": 8.333333333333333e-07,
|
|
"loss": 1.3774,
|
|
"mean_token_accuracy": 0.740469753742218,
|
|
"step": 1
|
|
},
|
|
{
|
|
"epoch": 0.06896551724137931,
|
|
"grad_norm": 31.841533660888672,
|
|
"learning_rate": 1.6666666666666667e-06,
|
|
"loss": 1.1835,
|
|
"mean_token_accuracy": 0.7526056170463562,
|
|
"step": 2
|
|
},
|
|
{
|
|
"epoch": 0.10344827586206896,
|
|
"grad_norm": 35.83158493041992,
|
|
"learning_rate": 2.5e-06,
|
|
"loss": 1.1499,
|
|
"mean_token_accuracy": 0.7815449237823486,
|
|
"step": 3
|
|
},
|
|
{
|
|
"epoch": 0.13793103448275862,
|
|
"grad_norm": 32.397979736328125,
|
|
"learning_rate": 3.3333333333333333e-06,
|
|
"loss": 1.2419,
|
|
"mean_token_accuracy": 0.7577303051948547,
|
|
"step": 4
|
|
},
|
|
{
|
|
"epoch": 0.1724137931034483,
|
|
"grad_norm": 31.138023376464844,
|
|
"learning_rate": 4.166666666666667e-06,
|
|
"loss": 1.244,
|
|
"mean_token_accuracy": 0.746874988079071,
|
|
"step": 5
|
|
},
|
|
{
|
|
"epoch": 0.20689655172413793,
|
|
"grad_norm": 18.774599075317383,
|
|
"learning_rate": 5e-06,
|
|
"loss": 1.007,
|
|
"mean_token_accuracy": 0.7697392702102661,
|
|
"step": 6
|
|
},
|
|
{
|
|
"epoch": 0.2413793103448276,
|
|
"grad_norm": 17.945812225341797,
|
|
"learning_rate": 5.833333333333334e-06,
|
|
"loss": 1.0226,
|
|
"mean_token_accuracy": 0.7652671933174133,
|
|
"step": 7
|
|
},
|
|
{
|
|
"epoch": 0.27586206896551724,
|
|
"grad_norm": 8.929885864257812,
|
|
"learning_rate": 6.666666666666667e-06,
|
|
"loss": 1.0524,
|
|
"mean_token_accuracy": 0.7645803689956665,
|
|
"step": 8
|
|
},
|
|
{
|
|
"epoch": 0.3103448275862069,
|
|
"grad_norm": 7.886545181274414,
|
|
"learning_rate": 7.500000000000001e-06,
|
|
"loss": 0.7061,
|
|
"mean_token_accuracy": 0.8247748017311096,
|
|
"step": 9
|
|
},
|
|
{
|
|
"epoch": 0.3448275862068966,
|
|
"grad_norm": 6.431151390075684,
|
|
"learning_rate": 8.333333333333334e-06,
|
|
"loss": 0.7137,
|
|
"mean_token_accuracy": 0.8260869383811951,
|
|
"step": 10
|
|
},
|
|
{
|
|
"epoch": 0.3793103448275862,
|
|
"grad_norm": 6.6982502937316895,
|
|
"learning_rate": 9.166666666666666e-06,
|
|
"loss": 0.9198,
|
|
"mean_token_accuracy": 0.7834821343421936,
|
|
"step": 11
|
|
},
|
|
{
|
|
"epoch": 0.41379310344827586,
|
|
"grad_norm": 6.049954414367676,
|
|
"learning_rate": 1e-05,
|
|
"loss": 0.853,
|
|
"mean_token_accuracy": 0.7753646969795227,
|
|
"step": 12
|
|
},
|
|
{
|
|
"epoch": 0.4482758620689655,
|
|
"grad_norm": 6.920111656188965,
|
|
"learning_rate": 9.997947030202901e-06,
|
|
"loss": 0.7117,
|
|
"mean_token_accuracy": 0.8271827101707458,
|
|
"step": 13
|
|
},
|
|
{
|
|
"epoch": 0.4827586206896552,
|
|
"grad_norm": 6.141343593597412,
|
|
"learning_rate": 9.991789994004929e-06,
|
|
"loss": 0.7161,
|
|
"mean_token_accuracy": 0.8164419531822205,
|
|
"step": 14
|
|
},
|
|
{
|
|
"epoch": 0.5172413793103449,
|
|
"grad_norm": 5.594657897949219,
|
|
"learning_rate": 9.98153450927691e-06,
|
|
"loss": 0.623,
|
|
"mean_token_accuracy": 0.842275083065033,
|
|
"step": 15
|
|
},
|
|
{
|
|
"epoch": 0.5517241379310345,
|
|
"grad_norm": 5.3693742752075195,
|
|
"learning_rate": 9.967189933441243e-06,
|
|
"loss": 0.7262,
|
|
"mean_token_accuracy": 0.8148788809776306,
|
|
"step": 16
|
|
},
|
|
{
|
|
"epoch": 0.5862068965517241,
|
|
"grad_norm": 5.857855796813965,
|
|
"learning_rate": 9.948769354933905e-06,
|
|
"loss": 0.7161,
|
|
"mean_token_accuracy": 0.7958254218101501,
|
|
"step": 17
|
|
},
|
|
{
|
|
"epoch": 0.6206896551724138,
|
|
"grad_norm": 4.9951581954956055,
|
|
"learning_rate": 9.926289581262147e-06,
|
|
"loss": 0.7478,
|
|
"mean_token_accuracy": 0.7893890738487244,
|
|
"step": 18
|
|
},
|
|
{
|
|
"epoch": 0.6551724137931034,
|
|
"grad_norm": 5.202838897705078,
|
|
"learning_rate": 9.899771123668811e-06,
|
|
"loss": 0.6994,
|
|
"mean_token_accuracy": 0.8181459307670593,
|
|
"step": 19
|
|
},
|
|
{
|
|
"epoch": 0.6896551724137931,
|
|
"grad_norm": 5.341423988342285,
|
|
"learning_rate": 9.869238178417235e-06,
|
|
"loss": 0.618,
|
|
"mean_token_accuracy": 0.8386844396591187,
|
|
"step": 20
|
|
},
|
|
{
|
|
"epoch": 0.7241379310344828,
|
|
"grad_norm": 5.327294826507568,
|
|
"learning_rate": 9.834718604713825e-06,
|
|
"loss": 0.7653,
|
|
"mean_token_accuracy": 0.8060739040374756,
|
|
"step": 21
|
|
},
|
|
{
|
|
"epoch": 0.7586206896551724,
|
|
"grad_norm": 5.64478874206543,
|
|
"learning_rate": 9.796243899288455e-06,
|
|
"loss": 0.7214,
|
|
"mean_token_accuracy": 0.8227323889732361,
|
|
"step": 22
|
|
},
|
|
{
|
|
"epoch": 0.7931034482758621,
|
|
"grad_norm": 5.176536560058594,
|
|
"learning_rate": 9.753849167655881e-06,
|
|
"loss": 0.8185,
|
|
"mean_token_accuracy": 0.8079403042793274,
|
|
"step": 23
|
|
},
|
|
{
|
|
"epoch": 0.8275862068965517,
|
|
"grad_norm": 4.750691890716553,
|
|
"learning_rate": 9.707573092084368e-06,
|
|
"loss": 0.7444,
|
|
"mean_token_accuracy": 0.8039276003837585,
|
|
"step": 24
|
|
},
|
|
{
|
|
"epoch": 0.8620689655172413,
|
|
"grad_norm": 5.0928473472595215,
|
|
"learning_rate": 9.65745789630079e-06,
|
|
"loss": 0.5925,
|
|
"mean_token_accuracy": 0.8463665246963501,
|
|
"step": 25
|
|
},
|
|
{
|
|
"epoch": 0.896551724137931,
|
|
"grad_norm": 4.8972086906433105,
|
|
"learning_rate": 9.603549306964408e-06,
|
|
"loss": 0.6491,
|
|
"mean_token_accuracy": 0.8238112926483154,
|
|
"step": 26
|
|
},
|
|
{
|
|
"epoch": 0.9310344827586207,
|
|
"grad_norm": 5.463573932647705,
|
|
"learning_rate": 9.545896511944416e-06,
|
|
"loss": 0.7093,
|
|
"mean_token_accuracy": 0.8327044248580933,
|
|
"step": 27
|
|
},
|
|
{
|
|
"epoch": 0.9655172413793104,
|
|
"grad_norm": 4.660519599914551,
|
|
"learning_rate": 9.484552115439445e-06,
|
|
"loss": 0.6958,
|
|
"mean_token_accuracy": 0.8255624175071716,
|
|
"step": 28
|
|
},
|
|
{
|
|
"epoch": 1.0,
|
|
"grad_norm": 5.265268325805664,
|
|
"learning_rate": 9.419572089979821e-06,
|
|
"loss": 0.8103,
|
|
"mean_token_accuracy": 0.8134814500808716,
|
|
"step": 29
|
|
},
|
|
{
|
|
"epoch": 1.0344827586206897,
|
|
"grad_norm": 6.0437774658203125,
|
|
"learning_rate": 9.351015725356515e-06,
|
|
"loss": 0.4465,
|
|
"mean_token_accuracy": 0.896746814250946,
|
|
"step": 30
|
|
},
|
|
{
|
|
"epoch": 1.0689655172413792,
|
|
"grad_norm": 4.806868553161621,
|
|
"learning_rate": 9.278945574523293e-06,
|
|
"loss": 0.5036,
|
|
"mean_token_accuracy": 0.8651062250137329,
|
|
"step": 31
|
|
},
|
|
{
|
|
"epoch": 1.103448275862069,
|
|
"grad_norm": 5.691929817199707,
|
|
"learning_rate": 9.203427396521454e-06,
|
|
"loss": 0.523,
|
|
"mean_token_accuracy": 0.8620548248291016,
|
|
"step": 32
|
|
},
|
|
{
|
|
"epoch": 1.1379310344827587,
|
|
"grad_norm": 4.686606407165527,
|
|
"learning_rate": 9.124530096479258e-06,
|
|
"loss": 0.5221,
|
|
"mean_token_accuracy": 0.8660033345222473,
|
|
"step": 33
|
|
},
|
|
{
|
|
"epoch": 1.1724137931034484,
|
|
"grad_norm": 3.97752046585083,
|
|
"learning_rate": 9.042325662740726e-06,
|
|
"loss": 0.5354,
|
|
"mean_token_accuracy": 0.8449214100837708,
|
|
"step": 34
|
|
},
|
|
{
|
|
"epoch": 1.206896551724138,
|
|
"grad_norm": 5.035070896148682,
|
|
"learning_rate": 8.956889101181262e-06,
|
|
"loss": 0.4946,
|
|
"mean_token_accuracy": 0.8720434308052063,
|
|
"step": 35
|
|
},
|
|
{
|
|
"epoch": 1.2413793103448276,
|
|
"grad_norm": 4.9860100746154785,
|
|
"learning_rate": 8.868298366769956e-06,
|
|
"loss": 0.6021,
|
|
"mean_token_accuracy": 0.8342487812042236,
|
|
"step": 36
|
|
},
|
|
{
|
|
"epoch": 1.2758620689655173,
|
|
"grad_norm": 4.826323509216309,
|
|
"learning_rate": 8.776634292441049e-06,
|
|
"loss": 0.4321,
|
|
"mean_token_accuracy": 0.884772002696991,
|
|
"step": 37
|
|
},
|
|
{
|
|
"epoch": 1.3103448275862069,
|
|
"grad_norm": 5.355347633361816,
|
|
"learning_rate": 8.681980515339464e-06,
|
|
"loss": 0.4768,
|
|
"mean_token_accuracy": 0.8703784346580505,
|
|
"step": 38
|
|
},
|
|
{
|
|
"epoch": 1.3448275862068966,
|
|
"grad_norm": 5.1744842529296875,
|
|
"learning_rate": 8.584423400507679e-06,
|
|
"loss": 0.4668,
|
|
"mean_token_accuracy": 0.8853046298027039,
|
|
"step": 39
|
|
},
|
|
{
|
|
"epoch": 1.3793103448275863,
|
|
"grad_norm": 5.17063045501709,
|
|
"learning_rate": 8.484051962083579e-06,
|
|
"loss": 0.4847,
|
|
"mean_token_accuracy": 0.8667626976966858,
|
|
"step": 40
|
|
},
|
|
{
|
|
"epoch": 1.4137931034482758,
|
|
"grad_norm": 4.590514183044434,
|
|
"learning_rate": 8.380957782081198e-06,
|
|
"loss": 0.42,
|
|
"mean_token_accuracy": 0.8825867176055908,
|
|
"step": 41
|
|
},
|
|
{
|
|
"epoch": 1.4482758620689655,
|
|
"grad_norm": 5.383031845092773,
|
|
"learning_rate": 8.275234926828446e-06,
|
|
"loss": 0.3628,
|
|
"mean_token_accuracy": 0.9045745134353638,
|
|
"step": 42
|
|
},
|
|
{
|
|
"epoch": 1.4827586206896552,
|
|
"grad_norm": 4.623243808746338,
|
|
"learning_rate": 8.166979861138076e-06,
|
|
"loss": 0.4927,
|
|
"mean_token_accuracy": 0.8554299473762512,
|
|
"step": 43
|
|
},
|
|
{
|
|
"epoch": 1.5172413793103448,
|
|
"grad_norm": 4.59343147277832,
|
|
"learning_rate": 8.056291360290202e-06,
|
|
"loss": 0.339,
|
|
"mean_token_accuracy": 0.9112599492073059,
|
|
"step": 44
|
|
},
|
|
{
|
|
"epoch": 1.5517241379310345,
|
|
"grad_norm": 4.420445442199707,
|
|
"learning_rate": 7.943270419906655e-06,
|
|
"loss": 0.4281,
|
|
"mean_token_accuracy": 0.8751758337020874,
|
|
"step": 45
|
|
},
|
|
{
|
|
"epoch": 1.5862068965517242,
|
|
"grad_norm": 4.380794048309326,
|
|
"learning_rate": 7.828020163799455e-06,
|
|
"loss": 0.4444,
|
|
"mean_token_accuracy": 0.8713410496711731,
|
|
"step": 46
|
|
},
|
|
{
|
|
"epoch": 1.6206896551724137,
|
|
"grad_norm": 4.382615566253662,
|
|
"learning_rate": 7.710645749877448e-06,
|
|
"loss": 0.3932,
|
|
"mean_token_accuracy": 0.8761938214302063,
|
|
"step": 47
|
|
},
|
|
{
|
|
"epoch": 1.6551724137931034,
|
|
"grad_norm": 4.465359210968018,
|
|
"learning_rate": 7.5912542741969585e-06,
|
|
"loss": 0.4346,
|
|
"mean_token_accuracy": 0.8759894371032715,
|
|
"step": 48
|
|
},
|
|
{
|
|
"epoch": 1.6896551724137931,
|
|
"grad_norm": 4.440632343292236,
|
|
"learning_rate": 7.469954673244032e-06,
|
|
"loss": 0.38,
|
|
"mean_token_accuracy": 0.8933333158493042,
|
|
"step": 49
|
|
},
|
|
{
|
|
"epoch": 1.7241379310344827,
|
|
"grad_norm": 4.296090126037598,
|
|
"learning_rate": 7.346857624537407e-06,
|
|
"loss": 0.4955,
|
|
"mean_token_accuracy": 0.861520528793335,
|
|
"step": 50
|
|
},
|
|
{
|
|
"epoch": 1.7586206896551724,
|
|
"grad_norm": 4.688018798828125,
|
|
"learning_rate": 7.222075445642904e-06,
|
|
"loss": 0.3928,
|
|
"mean_token_accuracy": 0.8793990015983582,
|
|
"step": 51
|
|
},
|
|
{
|
|
"epoch": 1.793103448275862,
|
|
"grad_norm": 4.597250461578369,
|
|
"learning_rate": 7.095721991691411e-06,
|
|
"loss": 0.4669,
|
|
"mean_token_accuracy": 0.8728665709495544,
|
|
"step": 52
|
|
},
|
|
{
|
|
"epoch": 1.8275862068965516,
|
|
"grad_norm": 4.70115852355957,
|
|
"learning_rate": 6.967912551493913e-06,
|
|
"loss": 0.3774,
|
|
"mean_token_accuracy": 0.904330313205719,
|
|
"step": 53
|
|
},
|
|
{
|
|
"epoch": 1.8620689655172413,
|
|
"grad_norm": 3.8735404014587402,
|
|
"learning_rate": 6.838763742348414e-06,
|
|
"loss": 0.4539,
|
|
"mean_token_accuracy": 0.8638014793395996,
|
|
"step": 54
|
|
},
|
|
{
|
|
"epoch": 1.896551724137931,
|
|
"grad_norm": 3.819071054458618,
|
|
"learning_rate": 6.708393403634696e-06,
|
|
"loss": 0.3833,
|
|
"mean_token_accuracy": 0.8801261782646179,
|
|
"step": 55
|
|
},
|
|
{
|
|
"epoch": 1.9310344827586206,
|
|
"grad_norm": 3.6699230670928955,
|
|
"learning_rate": 6.576920489294011e-06,
|
|
"loss": 0.4962,
|
|
"mean_token_accuracy": 0.8549042344093323,
|
|
"step": 56
|
|
},
|
|
{
|
|
"epoch": 1.9655172413793105,
|
|
"grad_norm": 3.6867268085479736,
|
|
"learning_rate": 6.444464959291814e-06,
|
|
"loss": 0.4416,
|
|
"mean_token_accuracy": 0.8705803751945496,
|
|
"step": 57
|
|
},
|
|
{
|
|
"epoch": 2.0,
|
|
"grad_norm": 3.870262861251831,
|
|
"learning_rate": 6.311147670162576e-06,
|
|
"loss": 0.4248,
|
|
"mean_token_accuracy": 0.8728753328323364,
|
|
"step": 58
|
|
},
|
|
{
|
|
"epoch": 2.0344827586206895,
|
|
"grad_norm": 3.8891749382019043,
|
|
"learning_rate": 6.177090264736525e-06,
|
|
"loss": 0.2321,
|
|
"mean_token_accuracy": 0.929407000541687,
|
|
"step": 59
|
|
},
|
|
{
|
|
"epoch": 2.0689655172413794,
|
|
"grad_norm": 3.4715583324432373,
|
|
"learning_rate": 6.042415061148954e-06,
|
|
"loss": 0.2797,
|
|
"mean_token_accuracy": 0.9197627305984497,
|
|
"step": 60
|
|
},
|
|
{
|
|
"epoch": 2.103448275862069,
|
|
"grad_norm": 4.050957679748535,
|
|
"learning_rate": 5.907244941233371e-06,
|
|
"loss": 0.2365,
|
|
"mean_token_accuracy": 0.9324618577957153,
|
|
"step": 61
|
|
},
|
|
{
|
|
"epoch": 2.1379310344827585,
|
|
"grad_norm": 3.6912150382995605,
|
|
"learning_rate": 5.771703238400288e-06,
|
|
"loss": 0.209,
|
|
"mean_token_accuracy": 0.9365726709365845,
|
|
"step": 62
|
|
},
|
|
{
|
|
"epoch": 2.1724137931034484,
|
|
"grad_norm": 3.456387758255005,
|
|
"learning_rate": 5.635913625104001e-06,
|
|
"loss": 0.2006,
|
|
"mean_token_accuracy": 0.9414021372795105,
|
|
"step": 63
|
|
},
|
|
{
|
|
"epoch": 2.206896551724138,
|
|
"grad_norm": 3.8323400020599365,
|
|
"learning_rate": 5.500000000000001e-06,
|
|
"loss": 0.1921,
|
|
"mean_token_accuracy": 0.9395722150802612,
|
|
"step": 64
|
|
},
|
|
{
|
|
"epoch": 2.2413793103448274,
|
|
"grad_norm": 3.9986572265625,
|
|
"learning_rate": 5.3640863748960016e-06,
|
|
"loss": 0.1956,
|
|
"mean_token_accuracy": 0.9349231719970703,
|
|
"step": 65
|
|
},
|
|
{
|
|
"epoch": 2.2758620689655173,
|
|
"grad_norm": 4.387889862060547,
|
|
"learning_rate": 5.228296761599713e-06,
|
|
"loss": 0.1881,
|
|
"mean_token_accuracy": 0.9423368573188782,
|
|
"step": 66
|
|
},
|
|
{
|
|
"epoch": 2.310344827586207,
|
|
"grad_norm": 3.891286849975586,
|
|
"learning_rate": 5.092755058766631e-06,
|
|
"loss": 0.1887,
|
|
"mean_token_accuracy": 0.9313790798187256,
|
|
"step": 67
|
|
},
|
|
{
|
|
"epoch": 2.344827586206897,
|
|
"grad_norm": 4.44399356842041,
|
|
"learning_rate": 4.957584938851048e-06,
|
|
"loss": 0.2098,
|
|
"mean_token_accuracy": 0.9372294545173645,
|
|
"step": 68
|
|
},
|
|
{
|
|
"epoch": 2.3793103448275863,
|
|
"grad_norm": 4.2808051109313965,
|
|
"learning_rate": 4.822909735263477e-06,
|
|
"loss": 0.2379,
|
|
"mean_token_accuracy": 0.923653244972229,
|
|
"step": 69
|
|
},
|
|
{
|
|
"epoch": 2.413793103448276,
|
|
"grad_norm": 4.003400802612305,
|
|
"learning_rate": 4.6888523298374245e-06,
|
|
"loss": 0.1771,
|
|
"mean_token_accuracy": 0.9492968320846558,
|
|
"step": 70
|
|
},
|
|
{
|
|
"epoch": 2.4482758620689653,
|
|
"grad_norm": 3.573258399963379,
|
|
"learning_rate": 4.555535040708186e-06,
|
|
"loss": 0.1843,
|
|
"mean_token_accuracy": 0.9385930895805359,
|
|
"step": 71
|
|
},
|
|
{
|
|
"epoch": 2.4827586206896552,
|
|
"grad_norm": 3.7771646976470947,
|
|
"learning_rate": 4.423079510705992e-06,
|
|
"loss": 0.2245,
|
|
"mean_token_accuracy": 0.9214980006217957,
|
|
"step": 72
|
|
},
|
|
{
|
|
"epoch": 2.5172413793103448,
|
|
"grad_norm": 3.48586106300354,
|
|
"learning_rate": 4.2916065963653045e-06,
|
|
"loss": 0.2004,
|
|
"mean_token_accuracy": 0.9363507628440857,
|
|
"step": 73
|
|
},
|
|
{
|
|
"epoch": 2.5517241379310347,
|
|
"grad_norm": 3.424337863922119,
|
|
"learning_rate": 4.1612362576515875e-06,
|
|
"loss": 0.2171,
|
|
"mean_token_accuracy": 0.9295426607131958,
|
|
"step": 74
|
|
},
|
|
{
|
|
"epoch": 2.586206896551724,
|
|
"grad_norm": 3.287777900695801,
|
|
"learning_rate": 4.032087448506089e-06,
|
|
"loss": 0.2347,
|
|
"mean_token_accuracy": 0.9248573184013367,
|
|
"step": 75
|
|
},
|
|
{
|
|
"epoch": 2.6206896551724137,
|
|
"grad_norm": 3.127174139022827,
|
|
"learning_rate": 3.904278008308589e-06,
|
|
"loss": 0.2315,
|
|
"mean_token_accuracy": 0.919683575630188,
|
|
"step": 76
|
|
},
|
|
{
|
|
"epoch": 2.655172413793103,
|
|
"grad_norm": 2.9863779544830322,
|
|
"learning_rate": 3.777924554357096e-06,
|
|
"loss": 0.2087,
|
|
"mean_token_accuracy": 0.9256926774978638,
|
|
"step": 77
|
|
},
|
|
{
|
|
"epoch": 2.689655172413793,
|
|
"grad_norm": 3.1884548664093018,
|
|
"learning_rate": 3.653142375462596e-06,
|
|
"loss": 0.2092,
|
|
"mean_token_accuracy": 0.9343122243881226,
|
|
"step": 78
|
|
},
|
|
{
|
|
"epoch": 2.7241379310344827,
|
|
"grad_norm": 2.532046318054199,
|
|
"learning_rate": 3.5300453267559676e-06,
|
|
"loss": 0.2545,
|
|
"mean_token_accuracy": 0.9118472933769226,
|
|
"step": 79
|
|
},
|
|
{
|
|
"epoch": 2.7586206896551726,
|
|
"grad_norm": 2.7691566944122314,
|
|
"learning_rate": 3.408745725803042e-06,
|
|
"loss": 0.2153,
|
|
"mean_token_accuracy": 0.9324372410774231,
|
|
"step": 80
|
|
},
|
|
{
|
|
"epoch": 2.793103448275862,
|
|
"grad_norm": 2.883653402328491,
|
|
"learning_rate": 3.2893542501225535e-06,
|
|
"loss": 0.177,
|
|
"mean_token_accuracy": 0.946940541267395,
|
|
"step": 81
|
|
},
|
|
{
|
|
"epoch": 2.8275862068965516,
|
|
"grad_norm": 3.113863706588745,
|
|
"learning_rate": 3.1719798362005444e-06,
|
|
"loss": 0.2499,
|
|
"mean_token_accuracy": 0.9145299196243286,
|
|
"step": 82
|
|
},
|
|
{
|
|
"epoch": 2.862068965517241,
|
|
"grad_norm": 2.6909308433532715,
|
|
"learning_rate": 3.056729580093346e-06,
|
|
"loss": 0.2271,
|
|
"mean_token_accuracy": 0.9211804270744324,
|
|
"step": 83
|
|
},
|
|
{
|
|
"epoch": 2.896551724137931,
|
|
"grad_norm": 2.7156546115875244,
|
|
"learning_rate": 2.9437086397097996e-06,
|
|
"loss": 0.2328,
|
|
"mean_token_accuracy": 0.9269275069236755,
|
|
"step": 84
|
|
},
|
|
{
|
|
"epoch": 2.9310344827586206,
|
|
"grad_norm": 2.657344102859497,
|
|
"learning_rate": 2.8330201388619257e-06,
|
|
"loss": 0.2214,
|
|
"mean_token_accuracy": 0.9271735548973083,
|
|
"step": 85
|
|
},
|
|
{
|
|
"epoch": 2.9655172413793105,
|
|
"grad_norm": 2.594271183013916,
|
|
"learning_rate": 2.7247650731715563e-06,
|
|
"loss": 0.1721,
|
|
"mean_token_accuracy": 0.9469696879386902,
|
|
"step": 86
|
|
},
|
|
{
|
|
"epoch": 3.0,
|
|
"grad_norm": 3.0993478298187256,
|
|
"learning_rate": 2.6190422179188046e-06,
|
|
"loss": 0.2366,
|
|
"mean_token_accuracy": 0.9250257015228271,
|
|
"step": 87
|
|
},
|
|
{
|
|
"epoch": 3.0344827586206895,
|
|
"grad_norm": 2.1011862754821777,
|
|
"learning_rate": 2.515948037916423e-06,
|
|
"loss": 0.1081,
|
|
"mean_token_accuracy": 0.9683519601821899,
|
|
"step": 88
|
|
},
|
|
{
|
|
"epoch": 3.0689655172413794,
|
|
"grad_norm": 2.291515588760376,
|
|
"learning_rate": 2.415576599492321e-06,
|
|
"loss": 0.1186,
|
|
"mean_token_accuracy": 0.961465060710907,
|
|
"step": 89
|
|
},
|
|
{
|
|
"epoch": 3.103448275862069,
|
|
"grad_norm": 2.1782500743865967,
|
|
"learning_rate": 2.3180194846605367e-06,
|
|
"loss": 0.0928,
|
|
"mean_token_accuracy": 0.9697393178939819,
|
|
"step": 90
|
|
},
|
|
{
|
|
"epoch": 3.1379310344827585,
|
|
"grad_norm": 2.3693504333496094,
|
|
"learning_rate": 2.223365707558953e-06,
|
|
"loss": 0.0922,
|
|
"mean_token_accuracy": 0.9721619486808777,
|
|
"step": 91
|
|
},
|
|
{
|
|
"epoch": 3.1724137931034484,
|
|
"grad_norm": 2.1274962425231934,
|
|
"learning_rate": 2.131701633230045e-06,
|
|
"loss": 0.0829,
|
|
"mean_token_accuracy": 0.9756795167922974,
|
|
"step": 92
|
|
},
|
|
{
|
|
"epoch": 3.206896551724138,
|
|
"grad_norm": 1.9486541748046875,
|
|
"learning_rate": 2.043110898818738e-06,
|
|
"loss": 0.0728,
|
|
"mean_token_accuracy": 0.9797441363334656,
|
|
"step": 93
|
|
},
|
|
{
|
|
"epoch": 3.2413793103448274,
|
|
"grad_norm": 2.245460033416748,
|
|
"learning_rate": 1.957674337259275e-06,
|
|
"loss": 0.1177,
|
|
"mean_token_accuracy": 0.9649968147277832,
|
|
"step": 94
|
|
},
|
|
{
|
|
"epoch": 3.2758620689655173,
|
|
"grad_norm": 2.6302707195281982,
|
|
"learning_rate": 1.875469903520743e-06,
|
|
"loss": 0.1082,
|
|
"mean_token_accuracy": 0.9706632494926453,
|
|
"step": 95
|
|
},
|
|
{
|
|
"epoch": 3.310344827586207,
|
|
"grad_norm": 2.351165533065796,
|
|
"learning_rate": 1.7965726034785466e-06,
|
|
"loss": 0.0791,
|
|
"mean_token_accuracy": 0.9741272926330566,
|
|
"step": 96
|
|
},
|
|
{
|
|
"epoch": 3.344827586206897,
|
|
"grad_norm": 2.1048247814178467,
|
|
"learning_rate": 1.7210544254767098e-06,
|
|
"loss": 0.0611,
|
|
"mean_token_accuracy": 0.977523684501648,
|
|
"step": 97
|
|
},
|
|
{
|
|
"epoch": 3.3793103448275863,
|
|
"grad_norm": 2.681243419647217,
|
|
"learning_rate": 1.648984274643487e-06,
|
|
"loss": 0.0869,
|
|
"mean_token_accuracy": 0.9723304510116577,
|
|
"step": 98
|
|
},
|
|
{
|
|
"epoch": 3.413793103448276,
|
|
"grad_norm": 2.781121015548706,
|
|
"learning_rate": 1.5804279100201799e-06,
|
|
"loss": 0.0826,
|
|
"mean_token_accuracy": 0.969332754611969,
|
|
"step": 99
|
|
},
|
|
{
|
|
"epoch": 3.4482758620689653,
|
|
"grad_norm": 3.5514438152313232,
|
|
"learning_rate": 1.515447884560556e-06,
|
|
"loss": 0.0885,
|
|
"mean_token_accuracy": 0.9686388373374939,
|
|
"step": 100
|
|
},
|
|
{
|
|
"epoch": 3.4827586206896552,
|
|
"grad_norm": 2.2951314449310303,
|
|
"learning_rate": 1.4541034880555837e-06,
|
|
"loss": 0.077,
|
|
"mean_token_accuracy": 0.9765592217445374,
|
|
"step": 101
|
|
},
|
|
{
|
|
"epoch": 3.5172413793103448,
|
|
"grad_norm": 2.6437036991119385,
|
|
"learning_rate": 1.3964506930355947e-06,
|
|
"loss": 0.0775,
|
|
"mean_token_accuracy": 0.9763970971107483,
|
|
"step": 102
|
|
},
|
|
{
|
|
"epoch": 3.5517241379310347,
|
|
"grad_norm": 3.129058599472046,
|
|
"learning_rate": 1.3425421036992098e-06,
|
|
"loss": 0.0979,
|
|
"mean_token_accuracy": 0.9674403667449951,
|
|
"step": 103
|
|
},
|
|
{
|
|
"epoch": 3.586206896551724,
|
|
"grad_norm": 2.5986857414245605,
|
|
"learning_rate": 1.292426907915634e-06,
|
|
"loss": 0.0914,
|
|
"mean_token_accuracy": 0.9685618877410889,
|
|
"step": 104
|
|
},
|
|
{
|
|
"epoch": 3.6206896551724137,
|
|
"grad_norm": 2.418269634246826,
|
|
"learning_rate": 1.2461508323441185e-06,
|
|
"loss": 0.0777,
|
|
"mean_token_accuracy": 0.9750581979751587,
|
|
"step": 105
|
|
},
|
|
{
|
|
"epoch": 3.655172413793103,
|
|
"grad_norm": 2.7729599475860596,
|
|
"learning_rate": 1.203756100711545e-06,
|
|
"loss": 0.0733,
|
|
"mean_token_accuracy": 0.9765625,
|
|
"step": 106
|
|
},
|
|
{
|
|
"epoch": 3.689655172413793,
|
|
"grad_norm": 2.909587860107422,
|
|
"learning_rate": 1.165281395286177e-06,
|
|
"loss": 0.0986,
|
|
"mean_token_accuracy": 0.9670926332473755,
|
|
"step": 107
|
|
},
|
|
{
|
|
"epoch": 3.7241379310344827,
|
|
"grad_norm": 2.416217803955078,
|
|
"learning_rate": 1.130761821582766e-06,
|
|
"loss": 0.0695,
|
|
"mean_token_accuracy": 0.9779465198516846,
|
|
"step": 108
|
|
},
|
|
{
|
|
"epoch": 3.7586206896551726,
|
|
"grad_norm": 2.8723764419555664,
|
|
"learning_rate": 1.1002288763311892e-06,
|
|
"loss": 0.0989,
|
|
"mean_token_accuracy": 0.968372642993927,
|
|
"step": 109
|
|
},
|
|
{
|
|
"epoch": 3.793103448275862,
|
|
"grad_norm": 2.604686975479126,
|
|
"learning_rate": 1.0737104187378543e-06,
|
|
"loss": 0.0971,
|
|
"mean_token_accuracy": 0.9691616892814636,
|
|
"step": 110
|
|
},
|
|
{
|
|
"epoch": 3.8275862068965516,
|
|
"grad_norm": 2.554763078689575,
|
|
"learning_rate": 1.0512306450660966e-06,
|
|
"loss": 0.0877,
|
|
"mean_token_accuracy": 0.9676067233085632,
|
|
"step": 111
|
|
},
|
|
{
|
|
"epoch": 3.862068965517241,
|
|
"grad_norm": 2.778059482574463,
|
|
"learning_rate": 1.0328100665587573e-06,
|
|
"loss": 0.0753,
|
|
"mean_token_accuracy": 0.9727236032485962,
|
|
"step": 112
|
|
},
|
|
{
|
|
"epoch": 3.896551724137931,
|
|
"grad_norm": 2.484534502029419,
|
|
"learning_rate": 1.0184654907230909e-06,
|
|
"loss": 0.0851,
|
|
"mean_token_accuracy": 0.9729294180870056,
|
|
"step": 113
|
|
},
|
|
{
|
|
"epoch": 3.9310344827586206,
|
|
"grad_norm": 2.6316423416137695,
|
|
"learning_rate": 1.0082100059950713e-06,
|
|
"loss": 0.0697,
|
|
"mean_token_accuracy": 0.972983717918396,
|
|
"step": 114
|
|
},
|
|
{
|
|
"epoch": 3.9655172413793105,
|
|
"grad_norm": 2.666123867034912,
|
|
"learning_rate": 1.0020529697970998e-06,
|
|
"loss": 0.0832,
|
|
"mean_token_accuracy": 0.9710332751274109,
|
|
"step": 115
|
|
},
|
|
{
|
|
"epoch": 4.0,
|
|
"grad_norm": 2.6746883392333984,
|
|
"learning_rate": 1.0000000000000002e-06,
|
|
"loss": 0.089,
|
|
"mean_token_accuracy": 0.9708768725395203,
|
|
"step": 116
|
|
},
|
|
{
|
|
"epoch": 4.0,
|
|
"step": 116,
|
|
"total_flos": 1.2005510253379584e+17,
|
|
"train_loss": 0.40030854754149914,
|
|
"train_runtime": 469.3197,
|
|
"train_samples_per_second": 7.901,
|
|
"train_steps_per_second": 0.247
|
|
}
|
|
],
|
|
"logging_steps": 1,
|
|
"max_steps": 116,
|
|
"num_input_tokens_seen": 0,
|
|
"num_train_epochs": 4,
|
|
"save_steps": 500,
|
|
"stateful_callbacks": {
|
|
"TrainerControl": {
|
|
"args": {
|
|
"should_epoch_stop": false,
|
|
"should_evaluate": false,
|
|
"should_log": false,
|
|
"should_save": false,
|
|
"should_training_stop": false
|
|
},
|
|
"attributes": {}
|
|
}
|
|
},
|
|
"total_flos": 1.2005510253379584e+17,
|
|
"train_batch_size": 4,
|
|
"trial_name": null,
|
|
"trial_params": null
|
|
}
|