checkpoint-200 / trainer_state.json
XuyaoWang's picture
Upload folder using huggingface_hub
355e2b9 verified
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 1.941747572815534,
"eval_steps": 500,
"global_step": 200,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.009708737864077669,
"grad_norm": 13.123837981408181,
"learning_rate": 2.3809523809523811e-07,
"loss": 3.4152,
"step": 1
},
{
"epoch": 0.019417475728155338,
"grad_norm": 11.341939206512826,
"learning_rate": 4.7619047619047623e-07,
"loss": 3.3469,
"step": 2
},
{
"epoch": 0.02912621359223301,
"grad_norm": 12.666841013000388,
"learning_rate": 7.142857142857143e-07,
"loss": 3.3404,
"step": 3
},
{
"epoch": 0.038834951456310676,
"grad_norm": 12.38576292589342,
"learning_rate": 9.523809523809525e-07,
"loss": 3.3661,
"step": 4
},
{
"epoch": 0.04854368932038835,
"grad_norm": 13.50943060392901,
"learning_rate": 1.1904761904761906e-06,
"loss": 3.6456,
"step": 5
},
{
"epoch": 0.05825242718446602,
"grad_norm": 12.60070687752704,
"learning_rate": 1.4285714285714286e-06,
"loss": 3.4586,
"step": 6
},
{
"epoch": 0.06796116504854369,
"grad_norm": 12.207104870760183,
"learning_rate": 1.6666666666666667e-06,
"loss": 3.3265,
"step": 7
},
{
"epoch": 0.07766990291262135,
"grad_norm": 11.396052085771197,
"learning_rate": 1.904761904761905e-06,
"loss": 3.1192,
"step": 8
},
{
"epoch": 0.08737864077669903,
"grad_norm": 10.849802772604386,
"learning_rate": 2.1428571428571427e-06,
"loss": 3.2892,
"step": 9
},
{
"epoch": 0.0970873786407767,
"grad_norm": 9.303944959402013,
"learning_rate": 2.380952380952381e-06,
"loss": 2.9846,
"step": 10
},
{
"epoch": 0.10679611650485436,
"grad_norm": 9.020909167429956,
"learning_rate": 2.6190476190476192e-06,
"loss": 3.0565,
"step": 11
},
{
"epoch": 0.11650485436893204,
"grad_norm": 8.408768996145499,
"learning_rate": 2.8571428571428573e-06,
"loss": 3.1117,
"step": 12
},
{
"epoch": 0.1262135922330097,
"grad_norm": 5.2970938586045,
"learning_rate": 3.0952380952380957e-06,
"loss": 2.6557,
"step": 13
},
{
"epoch": 0.13592233009708737,
"grad_norm": 4.966874609089927,
"learning_rate": 3.3333333333333333e-06,
"loss": 2.5166,
"step": 14
},
{
"epoch": 0.14563106796116504,
"grad_norm": 5.3359290318286865,
"learning_rate": 3.5714285714285718e-06,
"loss": 2.5143,
"step": 15
},
{
"epoch": 0.1553398058252427,
"grad_norm": 5.692915225500684,
"learning_rate": 3.80952380952381e-06,
"loss": 2.4596,
"step": 16
},
{
"epoch": 0.1650485436893204,
"grad_norm": 5.942402422601951,
"learning_rate": 4.047619047619048e-06,
"loss": 2.3662,
"step": 17
},
{
"epoch": 0.17475728155339806,
"grad_norm": 10.92147820851386,
"learning_rate": 4.2857142857142855e-06,
"loss": 2.1289,
"step": 18
},
{
"epoch": 0.18446601941747573,
"grad_norm": 8.249551104487301,
"learning_rate": 4.523809523809524e-06,
"loss": 1.9372,
"step": 19
},
{
"epoch": 0.1941747572815534,
"grad_norm": 5.912610258594789,
"learning_rate": 4.761904761904762e-06,
"loss": 1.9367,
"step": 20
},
{
"epoch": 0.20388349514563106,
"grad_norm": 3.466900934428963,
"learning_rate": 5e-06,
"loss": 1.9218,
"step": 21
},
{
"epoch": 0.21359223300970873,
"grad_norm": 2.3996812791210087,
"learning_rate": 5.2380952380952384e-06,
"loss": 1.7494,
"step": 22
},
{
"epoch": 0.22330097087378642,
"grad_norm": 2.071520914915747,
"learning_rate": 5.476190476190477e-06,
"loss": 1.7066,
"step": 23
},
{
"epoch": 0.23300970873786409,
"grad_norm": 1.9787564899007526,
"learning_rate": 5.7142857142857145e-06,
"loss": 1.679,
"step": 24
},
{
"epoch": 0.24271844660194175,
"grad_norm": 2.0523892248740663,
"learning_rate": 5.9523809523809525e-06,
"loss": 1.6847,
"step": 25
},
{
"epoch": 0.2524271844660194,
"grad_norm": 2.728014645148073,
"learning_rate": 6.1904761904761914e-06,
"loss": 1.5834,
"step": 26
},
{
"epoch": 0.2621359223300971,
"grad_norm": 1.9243753468407738,
"learning_rate": 6.4285714285714295e-06,
"loss": 1.6023,
"step": 27
},
{
"epoch": 0.27184466019417475,
"grad_norm": 1.7443060926437244,
"learning_rate": 6.666666666666667e-06,
"loss": 1.5585,
"step": 28
},
{
"epoch": 0.2815533980582524,
"grad_norm": 1.9667089972611325,
"learning_rate": 6.9047619047619055e-06,
"loss": 1.5523,
"step": 29
},
{
"epoch": 0.2912621359223301,
"grad_norm": 1.6638656525516557,
"learning_rate": 7.1428571428571436e-06,
"loss": 1.4028,
"step": 30
},
{
"epoch": 0.30097087378640774,
"grad_norm": 1.8288468644809657,
"learning_rate": 7.380952380952382e-06,
"loss": 1.5225,
"step": 31
},
{
"epoch": 0.3106796116504854,
"grad_norm": 1.9316948734534611,
"learning_rate": 7.61904761904762e-06,
"loss": 1.6076,
"step": 32
},
{
"epoch": 0.32038834951456313,
"grad_norm": 1.994402411129292,
"learning_rate": 7.857142857142858e-06,
"loss": 1.6018,
"step": 33
},
{
"epoch": 0.3300970873786408,
"grad_norm": 2.0025094595893855,
"learning_rate": 8.095238095238097e-06,
"loss": 1.5295,
"step": 34
},
{
"epoch": 0.33980582524271846,
"grad_norm": 2.198795362858049,
"learning_rate": 8.333333333333334e-06,
"loss": 1.5475,
"step": 35
},
{
"epoch": 0.34951456310679613,
"grad_norm": 2.0797645643032685,
"learning_rate": 8.571428571428571e-06,
"loss": 1.4739,
"step": 36
},
{
"epoch": 0.3592233009708738,
"grad_norm": 2.071926286682864,
"learning_rate": 8.80952380952381e-06,
"loss": 1.4679,
"step": 37
},
{
"epoch": 0.36893203883495146,
"grad_norm": 2.4010215614859707,
"learning_rate": 9.047619047619049e-06,
"loss": 1.4364,
"step": 38
},
{
"epoch": 0.3786407766990291,
"grad_norm": 2.1438204031361723,
"learning_rate": 9.285714285714288e-06,
"loss": 1.365,
"step": 39
},
{
"epoch": 0.3883495145631068,
"grad_norm": 1.9436034900136812,
"learning_rate": 9.523809523809525e-06,
"loss": 1.4371,
"step": 40
},
{
"epoch": 0.39805825242718446,
"grad_norm": 2.5388267486674665,
"learning_rate": 9.761904761904762e-06,
"loss": 1.4111,
"step": 41
},
{
"epoch": 0.4077669902912621,
"grad_norm": 2.113398146300134,
"learning_rate": 1e-05,
"loss": 1.29,
"step": 42
},
{
"epoch": 0.4174757281553398,
"grad_norm": 2.375511847477045,
"learning_rate": 9.999819767255175e-06,
"loss": 1.5152,
"step": 43
},
{
"epoch": 0.42718446601941745,
"grad_norm": 2.2832270982086604,
"learning_rate": 9.999279082014233e-06,
"loss": 1.3026,
"step": 44
},
{
"epoch": 0.4368932038834951,
"grad_norm": 2.180896773052596,
"learning_rate": 9.998377983256851e-06,
"loss": 1.2955,
"step": 45
},
{
"epoch": 0.44660194174757284,
"grad_norm": 2.2006360002608916,
"learning_rate": 9.997116535946028e-06,
"loss": 1.284,
"step": 46
},
{
"epoch": 0.4563106796116505,
"grad_norm": 2.013155184934404,
"learning_rate": 9.99549483102341e-06,
"loss": 1.357,
"step": 47
},
{
"epoch": 0.46601941747572817,
"grad_norm": 2.0776157335492043,
"learning_rate": 9.993512985402724e-06,
"loss": 1.3026,
"step": 48
},
{
"epoch": 0.47572815533980584,
"grad_norm": 1.9996729741636705,
"learning_rate": 9.99117114196137e-06,
"loss": 1.2625,
"step": 49
},
{
"epoch": 0.4854368932038835,
"grad_norm": 1.9864825080235484,
"learning_rate": 9.988469469530086e-06,
"loss": 1.2091,
"step": 50
},
{
"epoch": 0.49514563106796117,
"grad_norm": 1.8435037809122465,
"learning_rate": 9.985408162880813e-06,
"loss": 1.1999,
"step": 51
},
{
"epoch": 0.5048543689320388,
"grad_norm": 1.9791449702400086,
"learning_rate": 9.981987442712634e-06,
"loss": 1.2577,
"step": 52
},
{
"epoch": 0.5145631067961165,
"grad_norm": 1.9659977957936314,
"learning_rate": 9.978207555635856e-06,
"loss": 1.26,
"step": 53
},
{
"epoch": 0.5242718446601942,
"grad_norm": 2.0385176269260747,
"learning_rate": 9.974068774154252e-06,
"loss": 1.2092,
"step": 54
},
{
"epoch": 0.5339805825242718,
"grad_norm": 2.1519843859764816,
"learning_rate": 9.9695713966454e-06,
"loss": 1.3111,
"step": 55
},
{
"epoch": 0.5436893203883495,
"grad_norm": 1.9718179273705034,
"learning_rate": 9.964715747339178e-06,
"loss": 1.1383,
"step": 56
},
{
"epoch": 0.5533980582524272,
"grad_norm": 1.8488095555708863,
"learning_rate": 9.959502176294384e-06,
"loss": 1.1171,
"step": 57
},
{
"epoch": 0.5631067961165048,
"grad_norm": 1.8823723202588312,
"learning_rate": 9.95393105937351e-06,
"loss": 1.1922,
"step": 58
},
{
"epoch": 0.5728155339805825,
"grad_norm": 2.130166627458029,
"learning_rate": 9.948002798215632e-06,
"loss": 1.1811,
"step": 59
},
{
"epoch": 0.5825242718446602,
"grad_norm": 1.972322379680146,
"learning_rate": 9.941717820207461e-06,
"loss": 1.122,
"step": 60
},
{
"epoch": 0.5922330097087378,
"grad_norm": 1.9974554600923444,
"learning_rate": 9.935076578452535e-06,
"loss": 1.1378,
"step": 61
},
{
"epoch": 0.6019417475728155,
"grad_norm": 2.1883383076564726,
"learning_rate": 9.928079551738542e-06,
"loss": 1.0968,
"step": 62
},
{
"epoch": 0.6116504854368932,
"grad_norm": 1.8247180245095709,
"learning_rate": 9.92072724450282e-06,
"loss": 1.2031,
"step": 63
},
{
"epoch": 0.6213592233009708,
"grad_norm": 1.8317145241143062,
"learning_rate": 9.913020186795967e-06,
"loss": 1.0359,
"step": 64
},
{
"epoch": 0.6310679611650486,
"grad_norm": 1.8482608019696258,
"learning_rate": 9.904958934243655e-06,
"loss": 1.1466,
"step": 65
},
{
"epoch": 0.6407766990291263,
"grad_norm": 2.0820089056154076,
"learning_rate": 9.89654406800655e-06,
"loss": 1.174,
"step": 66
},
{
"epoch": 0.6504854368932039,
"grad_norm": 1.8203921553393068,
"learning_rate": 9.887776194738433e-06,
"loss": 1.0907,
"step": 67
},
{
"epoch": 0.6601941747572816,
"grad_norm": 1.8417874931856297,
"learning_rate": 9.878655946542443e-06,
"loss": 1.0885,
"step": 68
},
{
"epoch": 0.6699029126213593,
"grad_norm": 1.7661948434512647,
"learning_rate": 9.869183980925531e-06,
"loss": 1.1211,
"step": 69
},
{
"epoch": 0.6796116504854369,
"grad_norm": 1.8387238745376497,
"learning_rate": 9.85936098075104e-06,
"loss": 1.0653,
"step": 70
},
{
"epoch": 0.6893203883495146,
"grad_norm": 1.8949611010862242,
"learning_rate": 9.849187654189486e-06,
"loss": 1.1204,
"step": 71
},
{
"epoch": 0.6990291262135923,
"grad_norm": 1.805814771954187,
"learning_rate": 9.838664734667496e-06,
"loss": 1.0253,
"step": 72
},
{
"epoch": 0.7087378640776699,
"grad_norm": 1.6208527085431477,
"learning_rate": 9.827792980814934e-06,
"loss": 1.0949,
"step": 73
},
{
"epoch": 0.7184466019417476,
"grad_norm": 1.7031116347714181,
"learning_rate": 9.81657317641022e-06,
"loss": 0.9673,
"step": 74
},
{
"epoch": 0.7281553398058253,
"grad_norm": 1.6938233899501458,
"learning_rate": 9.80500613032381e-06,
"loss": 1.1198,
"step": 75
},
{
"epoch": 0.7378640776699029,
"grad_norm": 1.7001778982567737,
"learning_rate": 9.79309267645989e-06,
"loss": 1.081,
"step": 76
},
{
"epoch": 0.7475728155339806,
"grad_norm": 1.4923266262441406,
"learning_rate": 9.780833673696255e-06,
"loss": 1.0177,
"step": 77
},
{
"epoch": 0.7572815533980582,
"grad_norm": 1.7039304530928836,
"learning_rate": 9.768230005822394e-06,
"loss": 1.0759,
"step": 78
},
{
"epoch": 0.7669902912621359,
"grad_norm": 1.5967078271617257,
"learning_rate": 9.755282581475769e-06,
"loss": 1.0678,
"step": 79
},
{
"epoch": 0.7766990291262136,
"grad_norm": 1.6218746165164817,
"learning_rate": 9.741992334076309e-06,
"loss": 1.033,
"step": 80
},
{
"epoch": 0.7864077669902912,
"grad_norm": 1.4392158120730842,
"learning_rate": 9.728360221759125e-06,
"loss": 1.0064,
"step": 81
},
{
"epoch": 0.7961165048543689,
"grad_norm": 1.5842251493264055,
"learning_rate": 9.714387227305422e-06,
"loss": 1.001,
"step": 82
},
{
"epoch": 0.8058252427184466,
"grad_norm": 1.4858409988510537,
"learning_rate": 9.700074358071658e-06,
"loss": 1.0617,
"step": 83
},
{
"epoch": 0.8155339805825242,
"grad_norm": 1.511143998651756,
"learning_rate": 9.68542264591692e-06,
"loss": 1.0232,
"step": 84
},
{
"epoch": 0.8252427184466019,
"grad_norm": 1.477684418863534,
"learning_rate": 9.670433147128522e-06,
"loss": 1.0368,
"step": 85
},
{
"epoch": 0.8349514563106796,
"grad_norm": 1.3902620258730627,
"learning_rate": 9.65510694234587e-06,
"loss": 1.0055,
"step": 86
},
{
"epoch": 0.8446601941747572,
"grad_norm": 1.4791276503499884,
"learning_rate": 9.639445136482549e-06,
"loss": 0.9644,
"step": 87
},
{
"epoch": 0.8543689320388349,
"grad_norm": 1.2960748086935863,
"learning_rate": 9.623448858646658e-06,
"loss": 1.0314,
"step": 88
},
{
"epoch": 0.8640776699029126,
"grad_norm": 1.4330209334150434,
"learning_rate": 9.607119262059426e-06,
"loss": 0.9931,
"step": 89
},
{
"epoch": 0.8737864077669902,
"grad_norm": 1.4711730042923779,
"learning_rate": 9.590457523972055e-06,
"loss": 1.0706,
"step": 90
},
{
"epoch": 0.883495145631068,
"grad_norm": 1.2162238046460445,
"learning_rate": 9.573464845580864e-06,
"loss": 0.9255,
"step": 91
},
{
"epoch": 0.8932038834951457,
"grad_norm": 1.512646007631836,
"learning_rate": 9.55614245194068e-06,
"loss": 1.0073,
"step": 92
},
{
"epoch": 0.9029126213592233,
"grad_norm": 1.1882859794319478,
"learning_rate": 9.538491591876522e-06,
"loss": 0.9323,
"step": 93
},
{
"epoch": 0.912621359223301,
"grad_norm": 1.3411887286252628,
"learning_rate": 9.520513537893574e-06,
"loss": 0.9872,
"step": 94
},
{
"epoch": 0.9223300970873787,
"grad_norm": 1.4043520951877004,
"learning_rate": 9.502209586085444e-06,
"loss": 0.9911,
"step": 95
},
{
"epoch": 0.9320388349514563,
"grad_norm": 1.3308705634842204,
"learning_rate": 9.48358105604072e-06,
"loss": 1.0069,
"step": 96
},
{
"epoch": 0.941747572815534,
"grad_norm": 1.2655373953481186,
"learning_rate": 9.464629290747844e-06,
"loss": 0.8943,
"step": 97
},
{
"epoch": 0.9514563106796117,
"grad_norm": 1.2978200030362377,
"learning_rate": 9.445355656498284e-06,
"loss": 1.042,
"step": 98
},
{
"epoch": 0.9611650485436893,
"grad_norm": 1.364983716861643,
"learning_rate": 9.425761542788049e-06,
"loss": 0.9119,
"step": 99
},
{
"epoch": 0.970873786407767,
"grad_norm": 1.2833466396457305,
"learning_rate": 9.40584836221749e-06,
"loss": 0.9067,
"step": 100
},
{
"epoch": 0.9805825242718447,
"grad_norm": 1.3691910240046643,
"learning_rate": 9.38561755038949e-06,
"loss": 0.9509,
"step": 101
},
{
"epoch": 0.9902912621359223,
"grad_norm": 1.4140939858483665,
"learning_rate": 9.365070565805941e-06,
"loss": 0.8915,
"step": 102
},
{
"epoch": 1.0,
"grad_norm": 1.2298760928406687,
"learning_rate": 9.34420888976262e-06,
"loss": 0.9611,
"step": 103
},
{
"epoch": 1.0097087378640777,
"grad_norm": 1.1700332930023898,
"learning_rate": 9.323034026242378e-06,
"loss": 0.7946,
"step": 104
},
{
"epoch": 1.0194174757281553,
"grad_norm": 1.2030270990453835,
"learning_rate": 9.301547501806725e-06,
"loss": 0.7579,
"step": 105
},
{
"epoch": 1.029126213592233,
"grad_norm": 1.1566037512030418,
"learning_rate": 9.279750865485772e-06,
"loss": 0.7817,
"step": 106
},
{
"epoch": 1.0388349514563107,
"grad_norm": 1.2824945991000376,
"learning_rate": 9.257645688666557e-06,
"loss": 0.8459,
"step": 107
},
{
"epoch": 1.0485436893203883,
"grad_norm": 1.192436325000586,
"learning_rate": 9.235233564979756e-06,
"loss": 0.7788,
"step": 108
},
{
"epoch": 1.058252427184466,
"grad_norm": 1.2523853200153154,
"learning_rate": 9.212516110184794e-06,
"loss": 0.8145,
"step": 109
},
{
"epoch": 1.0679611650485437,
"grad_norm": 1.180542349517411,
"learning_rate": 9.18949496205337e-06,
"loss": 0.803,
"step": 110
},
{
"epoch": 1.0776699029126213,
"grad_norm": 1.162079773122146,
"learning_rate": 9.166171780251365e-06,
"loss": 0.7449,
"step": 111
},
{
"epoch": 1.087378640776699,
"grad_norm": 1.244662719759827,
"learning_rate": 9.142548246219212e-06,
"loss": 0.8265,
"step": 112
},
{
"epoch": 1.0970873786407767,
"grad_norm": 1.1330628483376846,
"learning_rate": 9.118626063050661e-06,
"loss": 0.8005,
"step": 113
},
{
"epoch": 1.1067961165048543,
"grad_norm": 1.1569031627998947,
"learning_rate": 9.09440695537001e-06,
"loss": 0.7452,
"step": 114
},
{
"epoch": 1.116504854368932,
"grad_norm": 1.2810507561815097,
"learning_rate": 9.069892669207757e-06,
"loss": 0.866,
"step": 115
},
{
"epoch": 1.1262135922330097,
"grad_norm": 1.0927498157835924,
"learning_rate": 9.045084971874738e-06,
"loss": 0.7016,
"step": 116
},
{
"epoch": 1.1359223300970873,
"grad_norm": 1.0548124074919196,
"learning_rate": 9.019985651834703e-06,
"loss": 0.7704,
"step": 117
},
{
"epoch": 1.145631067961165,
"grad_norm": 1.1211671094064979,
"learning_rate": 8.994596518575393e-06,
"loss": 0.7425,
"step": 118
},
{
"epoch": 1.1553398058252426,
"grad_norm": 1.13515459595643,
"learning_rate": 8.968919402478076e-06,
"loss": 0.7805,
"step": 119
},
{
"epoch": 1.1650485436893203,
"grad_norm": 1.1759276131825478,
"learning_rate": 8.942956154685596e-06,
"loss": 0.7369,
"step": 120
},
{
"epoch": 1.174757281553398,
"grad_norm": 1.1070873796167529,
"learning_rate": 8.916708646968924e-06,
"loss": 0.8016,
"step": 121
},
{
"epoch": 1.1844660194174756,
"grad_norm": 1.0511845426686406,
"learning_rate": 8.890178771592198e-06,
"loss": 0.7011,
"step": 122
},
{
"epoch": 1.1941747572815533,
"grad_norm": 1.0579418108836893,
"learning_rate": 8.863368441176326e-06,
"loss": 0.7059,
"step": 123
},
{
"epoch": 1.203883495145631,
"grad_norm": 1.1049403220659926,
"learning_rate": 8.836279588561084e-06,
"loss": 0.7075,
"step": 124
},
{
"epoch": 1.2135922330097086,
"grad_norm": 1.0755124949327624,
"learning_rate": 8.808914166665773e-06,
"loss": 0.7112,
"step": 125
},
{
"epoch": 1.2233009708737863,
"grad_norm": 1.0976870364730078,
"learning_rate": 8.781274148348438e-06,
"loss": 0.7248,
"step": 126
},
{
"epoch": 1.233009708737864,
"grad_norm": 1.2025667720330029,
"learning_rate": 8.753361526263622e-06,
"loss": 0.7521,
"step": 127
},
{
"epoch": 1.2427184466019416,
"grad_norm": 1.1124911845617471,
"learning_rate": 8.725178312718727e-06,
"loss": 0.7417,
"step": 128
},
{
"epoch": 1.2524271844660193,
"grad_norm": 1.2386224168172428,
"learning_rate": 8.696726539528924e-06,
"loss": 0.7229,
"step": 129
},
{
"epoch": 1.262135922330097,
"grad_norm": 1.0679761458027965,
"learning_rate": 8.668008257870684e-06,
"loss": 0.7551,
"step": 130
},
{
"epoch": 1.2718446601941746,
"grad_norm": 1.0235025944068437,
"learning_rate": 8.639025538133899e-06,
"loss": 0.7074,
"step": 131
},
{
"epoch": 1.2815533980582523,
"grad_norm": 0.9990534132254134,
"learning_rate": 8.609780469772623e-06,
"loss": 0.6883,
"step": 132
},
{
"epoch": 1.29126213592233,
"grad_norm": 1.0705087766695287,
"learning_rate": 8.580275161154432e-06,
"loss": 0.7848,
"step": 133
},
{
"epoch": 1.3009708737864076,
"grad_norm": 1.0702664701898648,
"learning_rate": 8.550511739408428e-06,
"loss": 0.685,
"step": 134
},
{
"epoch": 1.3106796116504853,
"grad_norm": 1.0357856853514515,
"learning_rate": 8.520492350271895e-06,
"loss": 0.7346,
"step": 135
},
{
"epoch": 1.3203883495145632,
"grad_norm": 0.9933104397502625,
"learning_rate": 8.490219157935589e-06,
"loss": 0.7512,
"step": 136
},
{
"epoch": 1.3300970873786409,
"grad_norm": 0.9959095652454518,
"learning_rate": 8.459694344887732e-06,
"loss": 0.7059,
"step": 137
},
{
"epoch": 1.3398058252427185,
"grad_norm": 1.0857087498373814,
"learning_rate": 8.428920111756658e-06,
"loss": 0.7045,
"step": 138
},
{
"epoch": 1.3495145631067962,
"grad_norm": 0.978326232822382,
"learning_rate": 8.397898677152173e-06,
"loss": 0.655,
"step": 139
},
{
"epoch": 1.3592233009708738,
"grad_norm": 1.1179745234558807,
"learning_rate": 8.366632277505598e-06,
"loss": 0.759,
"step": 140
},
{
"epoch": 1.3689320388349515,
"grad_norm": 0.9862359110930711,
"learning_rate": 8.335123166908544e-06,
"loss": 0.6789,
"step": 141
},
{
"epoch": 1.3786407766990292,
"grad_norm": 0.9490832081233238,
"learning_rate": 8.303373616950408e-06,
"loss": 0.6631,
"step": 142
},
{
"epoch": 1.3883495145631068,
"grad_norm": 0.9707214432827141,
"learning_rate": 8.271385916554605e-06,
"loss": 0.6937,
"step": 143
},
{
"epoch": 1.3980582524271845,
"grad_norm": 1.0214073506468517,
"learning_rate": 8.239162371813552e-06,
"loss": 0.6327,
"step": 144
},
{
"epoch": 1.4077669902912622,
"grad_norm": 1.0274559550351532,
"learning_rate": 8.206705305822414e-06,
"loss": 0.7009,
"step": 145
},
{
"epoch": 1.4174757281553398,
"grad_norm": 1.0594563883841244,
"learning_rate": 8.17401705851163e-06,
"loss": 0.745,
"step": 146
},
{
"epoch": 1.4271844660194175,
"grad_norm": 0.9655417791148342,
"learning_rate": 8.141099986478212e-06,
"loss": 0.6486,
"step": 147
},
{
"epoch": 1.4368932038834952,
"grad_norm": 1.0220480965295933,
"learning_rate": 8.107956462815862e-06,
"loss": 0.6688,
"step": 148
},
{
"epoch": 1.4466019417475728,
"grad_norm": 0.9683390807392493,
"learning_rate": 8.074588876943872e-06,
"loss": 0.659,
"step": 149
},
{
"epoch": 1.4563106796116505,
"grad_norm": 1.0767779292378918,
"learning_rate": 8.040999634434883e-06,
"loss": 0.685,
"step": 150
},
{
"epoch": 1.4660194174757282,
"grad_norm": 0.9698677024653224,
"learning_rate": 8.00719115684144e-06,
"loss": 0.6567,
"step": 151
},
{
"epoch": 1.4757281553398058,
"grad_norm": 1.077389631746702,
"learning_rate": 7.973165881521435e-06,
"loss": 0.6843,
"step": 152
},
{
"epoch": 1.4854368932038835,
"grad_norm": 0.9955066354735376,
"learning_rate": 7.938926261462366e-06,
"loss": 0.6845,
"step": 153
},
{
"epoch": 1.4951456310679612,
"grad_norm": 0.9488957169160419,
"learning_rate": 7.90447476510452e-06,
"loss": 0.6019,
"step": 154
},
{
"epoch": 1.5048543689320388,
"grad_norm": 0.9938234421719504,
"learning_rate": 7.869813876162997e-06,
"loss": 0.7082,
"step": 155
},
{
"epoch": 1.5145631067961165,
"grad_norm": 0.9603100487668675,
"learning_rate": 7.834946093448658e-06,
"loss": 0.6412,
"step": 156
},
{
"epoch": 1.5242718446601942,
"grad_norm": 1.005992503007623,
"learning_rate": 7.799873930687979e-06,
"loss": 0.6879,
"step": 157
},
{
"epoch": 1.5339805825242718,
"grad_norm": 0.9916500135350472,
"learning_rate": 7.764599916341817e-06,
"loss": 0.6709,
"step": 158
},
{
"epoch": 1.5436893203883495,
"grad_norm": 0.9257591953412015,
"learning_rate": 7.729126593423151e-06,
"loss": 0.6196,
"step": 159
},
{
"epoch": 1.5533980582524272,
"grad_norm": 1.0569458652900285,
"learning_rate": 7.69345651931372e-06,
"loss": 0.696,
"step": 160
},
{
"epoch": 1.5631067961165048,
"grad_norm": 0.9735255979741266,
"learning_rate": 7.65759226557967e-06,
"loss": 0.6523,
"step": 161
},
{
"epoch": 1.5728155339805825,
"grad_norm": 0.9767326365838914,
"learning_rate": 7.621536417786159e-06,
"loss": 0.6609,
"step": 162
},
{
"epoch": 1.5825242718446602,
"grad_norm": 1.0593912081912753,
"learning_rate": 7.585291575310952e-06,
"loss": 0.664,
"step": 163
},
{
"epoch": 1.5922330097087378,
"grad_norm": 0.942168510730449,
"learning_rate": 7.548860351157028e-06,
"loss": 0.5929,
"step": 164
},
{
"epoch": 1.6019417475728155,
"grad_norm": 1.0180139630792668,
"learning_rate": 7.512245371764197e-06,
"loss": 0.6571,
"step": 165
},
{
"epoch": 1.6116504854368932,
"grad_norm": 0.9895426752938254,
"learning_rate": 7.475449276819753e-06,
"loss": 0.6581,
"step": 166
},
{
"epoch": 1.6213592233009708,
"grad_norm": 1.0191365953291556,
"learning_rate": 7.438474719068174e-06,
"loss": 0.726,
"step": 167
},
{
"epoch": 1.6310679611650487,
"grad_norm": 1.0066738404323723,
"learning_rate": 7.401324364119872e-06,
"loss": 0.6901,
"step": 168
},
{
"epoch": 1.6407766990291264,
"grad_norm": 1.002278806498304,
"learning_rate": 7.364000890259024e-06,
"loss": 0.6324,
"step": 169
},
{
"epoch": 1.650485436893204,
"grad_norm": 0.907526837788578,
"learning_rate": 7.326506988250488e-06,
"loss": 0.6219,
"step": 170
},
{
"epoch": 1.6601941747572817,
"grad_norm": 1.1098079007322723,
"learning_rate": 7.288845361145812e-06,
"loss": 0.7004,
"step": 171
},
{
"epoch": 1.6699029126213594,
"grad_norm": 1.0550771463928161,
"learning_rate": 7.251018724088367e-06,
"loss": 0.6032,
"step": 172
},
{
"epoch": 1.679611650485437,
"grad_norm": 1.0536071947022911,
"learning_rate": 7.213029804117604e-06,
"loss": 0.6874,
"step": 173
},
{
"epoch": 1.6893203883495147,
"grad_norm": 0.9509232087171413,
"learning_rate": 7.174881339972448e-06,
"loss": 0.6271,
"step": 174
},
{
"epoch": 1.6990291262135924,
"grad_norm": 0.9765447626747497,
"learning_rate": 7.136576081893863e-06,
"loss": 0.578,
"step": 175
},
{
"epoch": 1.70873786407767,
"grad_norm": 0.8766277871753961,
"learning_rate": 7.09811679142657e-06,
"loss": 0.62,
"step": 176
},
{
"epoch": 1.7184466019417477,
"grad_norm": 0.9544049210539662,
"learning_rate": 7.059506241219964e-06,
"loss": 0.6478,
"step": 177
},
{
"epoch": 1.7281553398058254,
"grad_norm": 0.9873530148187425,
"learning_rate": 7.020747214828221e-06,
"loss": 0.5994,
"step": 178
},
{
"epoch": 1.737864077669903,
"grad_norm": 0.902538459879482,
"learning_rate": 6.981842506509626e-06,
"loss": 0.5824,
"step": 179
},
{
"epoch": 1.7475728155339807,
"grad_norm": 1.0465611114075961,
"learning_rate": 6.942794921025127e-06,
"loss": 0.6444,
"step": 180
},
{
"epoch": 1.7572815533980584,
"grad_norm": 0.9406932219924345,
"learning_rate": 6.903607273436128e-06,
"loss": 0.6602,
"step": 181
},
{
"epoch": 1.766990291262136,
"grad_norm": 1.9912252671577682,
"learning_rate": 6.864282388901544e-06,
"loss": 0.6426,
"step": 182
},
{
"epoch": 1.7766990291262137,
"grad_norm": 0.9157876015013201,
"learning_rate": 6.824823102474127e-06,
"loss": 0.6018,
"step": 183
},
{
"epoch": 1.7864077669902914,
"grad_norm": 0.9118371479046088,
"learning_rate": 6.785232258896078e-06,
"loss": 0.6573,
"step": 184
},
{
"epoch": 1.796116504854369,
"grad_norm": 0.8991339248484931,
"learning_rate": 6.745512712393958e-06,
"loss": 0.6388,
"step": 185
},
{
"epoch": 1.8058252427184467,
"grad_norm": 0.9972017158456973,
"learning_rate": 6.705667326472926e-06,
"loss": 0.5934,
"step": 186
},
{
"epoch": 1.8155339805825244,
"grad_norm": 0.9988069506780758,
"learning_rate": 6.665698973710289e-06,
"loss": 0.5952,
"step": 187
},
{
"epoch": 1.825242718446602,
"grad_norm": 0.8514983462528519,
"learning_rate": 6.625610535548418e-06,
"loss": 0.5318,
"step": 188
},
{
"epoch": 1.8349514563106797,
"grad_norm": 0.9294990543655399,
"learning_rate": 6.585404902087011e-06,
"loss": 0.5717,
"step": 189
},
{
"epoch": 1.8446601941747574,
"grad_norm": 0.9938842716480702,
"learning_rate": 6.545084971874738e-06,
"loss": 0.6195,
"step": 190
},
{
"epoch": 1.854368932038835,
"grad_norm": 0.9123365141247879,
"learning_rate": 6.504653651700278e-06,
"loss": 0.5967,
"step": 191
},
{
"epoch": 1.8640776699029127,
"grad_norm": 1.0008141571407345,
"learning_rate": 6.464113856382752e-06,
"loss": 0.6277,
"step": 192
},
{
"epoch": 1.8737864077669903,
"grad_norm": 0.8919950398755992,
"learning_rate": 6.423468508561599e-06,
"loss": 0.5958,
"step": 193
},
{
"epoch": 1.883495145631068,
"grad_norm": 0.9351239526172137,
"learning_rate": 6.382720538485856e-06,
"loss": 0.5581,
"step": 194
},
{
"epoch": 1.8932038834951457,
"grad_norm": 1.0249486162494306,
"learning_rate": 6.341872883802923e-06,
"loss": 0.6901,
"step": 195
},
{
"epoch": 1.9029126213592233,
"grad_norm": 0.8637050153467829,
"learning_rate": 6.3009284893467655e-06,
"loss": 0.6034,
"step": 196
},
{
"epoch": 1.912621359223301,
"grad_norm": 0.9202467333329478,
"learning_rate": 6.259890306925627e-06,
"loss": 0.5609,
"step": 197
},
{
"epoch": 1.9223300970873787,
"grad_norm": 0.9798270645068964,
"learning_rate": 6.218761295109209e-06,
"loss": 0.6688,
"step": 198
},
{
"epoch": 1.9320388349514563,
"grad_norm": 1.0149231730700408,
"learning_rate": 6.177544419015388e-06,
"loss": 0.573,
"step": 199
},
{
"epoch": 1.941747572815534,
"grad_norm": 1.008333410310924,
"learning_rate": 6.136242650096451e-06,
"loss": 0.6607,
"step": 200
}
],
"logging_steps": 1.0,
"max_steps": 412,
"num_input_tokens_seen": 0,
"num_train_epochs": 4,
"save_steps": 100,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 161207176396800.0,
"train_batch_size": 1,
"trial_name": null,
"trial_params": null
}