7112 lines
193 KiB
JSON
7112 lines
193 KiB
JSON
|
{
|
||
|
|
"best_global_step": null,
|
||
|
|
"best_metric": null,
|
||
|
|
"best_model_checkpoint": null,
|
||
|
|
"epoch": 3.179009541117674,
|
||
|
|
"eval_steps": 500,
|
||
|
|
"global_step": 3500,
|
||
|
|
"is_hyper_param_search": false,
|
||
|
|
"is_local_process_zero": true,
|
||
|
|
"is_world_process_zero": true,
|
||
|
|
"log_history": [
|
||
|
|
{
|
||
|
|
"entropy": 10.69198923110962,
|
||
|
|
"epoch": 0.004543389368468878,
|
||
|
|
"grad_norm": 14.25,
|
||
|
|
"learning_rate": 2e-06,
|
||
|
|
"loss": 10.8255,
|
||
|
|
"mean_token_accuracy": 0.0,
|
||
|
|
"num_tokens": 10131.0,
|
||
|
|
"step": 5
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.691961860656738,
|
||
|
|
"epoch": 0.009086778736937756,
|
||
|
|
"grad_norm": 13.9375,
|
||
|
|
"learning_rate": 4.5e-06,
|
||
|
|
"loss": 10.7543,
|
||
|
|
"mean_token_accuracy": 0.00033454534714110195,
|
||
|
|
"num_tokens": 20042.0,
|
||
|
|
"step": 10
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.690863990783692,
|
||
|
|
"epoch": 0.013630168105406633,
|
||
|
|
"grad_norm": 9.8125,
|
||
|
|
"learning_rate": 7e-06,
|
||
|
|
"loss": 10.5076,
|
||
|
|
"mean_token_accuracy": 0.02908163322135806,
|
||
|
|
"num_tokens": 30596.0,
|
||
|
|
"step": 15
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.680220794677734,
|
||
|
|
"epoch": 0.01817355747387551,
|
||
|
|
"grad_norm": 6.5625,
|
||
|
|
"learning_rate": 9.5e-06,
|
||
|
|
"loss": 10.1604,
|
||
|
|
"mean_token_accuracy": 0.04479682110249996,
|
||
|
|
"num_tokens": 40667.0,
|
||
|
|
"step": 20
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.61959457397461,
|
||
|
|
"epoch": 0.02271694684234439,
|
||
|
|
"grad_norm": 4.78125,
|
||
|
|
"learning_rate": 1.2e-05,
|
||
|
|
"loss": 9.8647,
|
||
|
|
"mean_token_accuracy": 0.04831764362752437,
|
||
|
|
"num_tokens": 51027.0,
|
||
|
|
"step": 25
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.559894180297851,
|
||
|
|
"epoch": 0.027260336210813266,
|
||
|
|
"grad_norm": 3.3125,
|
||
|
|
"learning_rate": 1.4500000000000002e-05,
|
||
|
|
"loss": 9.7234,
|
||
|
|
"mean_token_accuracy": 0.043796106800436975,
|
||
|
|
"num_tokens": 61860.0,
|
||
|
|
"step": 30
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.580874252319337,
|
||
|
|
"epoch": 0.03180372557928214,
|
||
|
|
"grad_norm": 2.75,
|
||
|
|
"learning_rate": 1.7000000000000003e-05,
|
||
|
|
"loss": 9.5845,
|
||
|
|
"mean_token_accuracy": 0.042750259116292,
|
||
|
|
"num_tokens": 72136.0,
|
||
|
|
"step": 35
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.5773193359375,
|
||
|
|
"epoch": 0.03634711494775102,
|
||
|
|
"grad_norm": 2.796875,
|
||
|
|
"learning_rate": 1.95e-05,
|
||
|
|
"loss": 9.561,
|
||
|
|
"mean_token_accuracy": 0.0454920094460249,
|
||
|
|
"num_tokens": 82611.0,
|
||
|
|
"step": 40
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.545099830627441,
|
||
|
|
"epoch": 0.0408905043162199,
|
||
|
|
"grad_norm": 2.71875,
|
||
|
|
"learning_rate": 2.2e-05,
|
||
|
|
"loss": 9.5763,
|
||
|
|
"mean_token_accuracy": 0.04643099419772625,
|
||
|
|
"num_tokens": 92722.0,
|
||
|
|
"step": 45
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.54197654724121,
|
||
|
|
"epoch": 0.04543389368468878,
|
||
|
|
"grad_norm": 2.578125,
|
||
|
|
"learning_rate": 2.4500000000000003e-05,
|
||
|
|
"loss": 9.4838,
|
||
|
|
"mean_token_accuracy": 0.051533405855298045,
|
||
|
|
"num_tokens": 103258.0,
|
||
|
|
"step": 50
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.54912166595459,
|
||
|
|
"epoch": 0.049977283053157656,
|
||
|
|
"grad_norm": 2.59375,
|
||
|
|
"learning_rate": 2.7e-05,
|
||
|
|
"loss": 9.4581,
|
||
|
|
"mean_token_accuracy": 0.050457367300987245,
|
||
|
|
"num_tokens": 114277.0,
|
||
|
|
"step": 55
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.54041051864624,
|
||
|
|
"epoch": 0.05452067242162653,
|
||
|
|
"grad_norm": 2.59375,
|
||
|
|
"learning_rate": 2.95e-05,
|
||
|
|
"loss": 9.3354,
|
||
|
|
"mean_token_accuracy": 0.06432176940143108,
|
||
|
|
"num_tokens": 124098.0,
|
||
|
|
"step": 60
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.39171543121338,
|
||
|
|
"epoch": 0.059064061790095414,
|
||
|
|
"grad_norm": 2.640625,
|
||
|
|
"learning_rate": 3.2e-05,
|
||
|
|
"loss": 9.2163,
|
||
|
|
"mean_token_accuracy": 0.059896310418844224,
|
||
|
|
"num_tokens": 133775.0,
|
||
|
|
"step": 65
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.376233863830567,
|
||
|
|
"epoch": 0.06360745115856428,
|
||
|
|
"grad_norm": 2.546875,
|
||
|
|
"learning_rate": 3.4500000000000005e-05,
|
||
|
|
"loss": 9.1789,
|
||
|
|
"mean_token_accuracy": 0.06541561521589756,
|
||
|
|
"num_tokens": 144765.0,
|
||
|
|
"step": 70
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.435562705993652,
|
||
|
|
"epoch": 0.06815084052703317,
|
||
|
|
"grad_norm": 2.671875,
|
||
|
|
"learning_rate": 3.7e-05,
|
||
|
|
"loss": 9.0237,
|
||
|
|
"mean_token_accuracy": 0.07151055298745632,
|
||
|
|
"num_tokens": 154641.0,
|
||
|
|
"step": 75
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.328177547454834,
|
||
|
|
"epoch": 0.07269422989550205,
|
||
|
|
"grad_norm": 2.65625,
|
||
|
|
"learning_rate": 3.95e-05,
|
||
|
|
"loss": 8.9198,
|
||
|
|
"mean_token_accuracy": 0.07580552473664284,
|
||
|
|
"num_tokens": 164728.0,
|
||
|
|
"step": 80
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.30659589767456,
|
||
|
|
"epoch": 0.07723761926397092,
|
||
|
|
"grad_norm": 2.796875,
|
||
|
|
"learning_rate": 4.2000000000000004e-05,
|
||
|
|
"loss": 8.8567,
|
||
|
|
"mean_token_accuracy": 0.06854435540735722,
|
||
|
|
"num_tokens": 174739.0,
|
||
|
|
"step": 85
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.201157188415527,
|
||
|
|
"epoch": 0.0817810086324398,
|
||
|
|
"grad_norm": 2.234375,
|
||
|
|
"learning_rate": 4.45e-05,
|
||
|
|
"loss": 8.7127,
|
||
|
|
"mean_token_accuracy": 0.07744735479354858,
|
||
|
|
"num_tokens": 184580.0,
|
||
|
|
"step": 90
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.151866340637207,
|
||
|
|
"epoch": 0.08632439800090867,
|
||
|
|
"grad_norm": 2.1875,
|
||
|
|
"learning_rate": 4.7000000000000004e-05,
|
||
|
|
"loss": 8.6842,
|
||
|
|
"mean_token_accuracy": 0.07533066719770432,
|
||
|
|
"num_tokens": 195243.0,
|
||
|
|
"step": 95
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.13199291229248,
|
||
|
|
"epoch": 0.09086778736937756,
|
||
|
|
"grad_norm": 2.5,
|
||
|
|
"learning_rate": 4.9500000000000004e-05,
|
||
|
|
"loss": 8.5675,
|
||
|
|
"mean_token_accuracy": 0.08015098795294762,
|
||
|
|
"num_tokens": 205751.0,
|
||
|
|
"step": 100
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.04837646484375,
|
||
|
|
"epoch": 0.09541117673784644,
|
||
|
|
"grad_norm": 2.21875,
|
||
|
|
"learning_rate": 5.2e-05,
|
||
|
|
"loss": 8.4086,
|
||
|
|
"mean_token_accuracy": 0.07969476953148842,
|
||
|
|
"num_tokens": 217283.0,
|
||
|
|
"step": 105
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.001432323455811,
|
||
|
|
"epoch": 0.09995456610631531,
|
||
|
|
"grad_norm": 1.9921875,
|
||
|
|
"learning_rate": 5.45e-05,
|
||
|
|
"loss": 8.3112,
|
||
|
|
"mean_token_accuracy": 0.07908041924238204,
|
||
|
|
"num_tokens": 226909.0,
|
||
|
|
"step": 110
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 9.96151065826416,
|
||
|
|
"epoch": 0.10449795547478419,
|
||
|
|
"grad_norm": 1.9375,
|
||
|
|
"learning_rate": 5.7e-05,
|
||
|
|
"loss": 8.2717,
|
||
|
|
"mean_token_accuracy": 0.0716276228427887,
|
||
|
|
"num_tokens": 237343.0,
|
||
|
|
"step": 115
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 9.76609468460083,
|
||
|
|
"epoch": 0.10904134484325306,
|
||
|
|
"grad_norm": 1.828125,
|
||
|
|
"learning_rate": 5.9499999999999996e-05,
|
||
|
|
"loss": 8.0896,
|
||
|
|
"mean_token_accuracy": 0.08059490025043488,
|
||
|
|
"num_tokens": 246601.0,
|
||
|
|
"step": 120
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 9.774349784851074,
|
||
|
|
"epoch": 0.11358473421172194,
|
||
|
|
"grad_norm": 2.046875,
|
||
|
|
"learning_rate": 6.2e-05,
|
||
|
|
"loss": 7.9819,
|
||
|
|
"mean_token_accuracy": 0.08241913989186286,
|
||
|
|
"num_tokens": 256818.0,
|
||
|
|
"step": 125
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 9.546303367614746,
|
||
|
|
"epoch": 0.11812812358019083,
|
||
|
|
"grad_norm": 1.671875,
|
||
|
|
"learning_rate": 6.450000000000001e-05,
|
||
|
|
"loss": 7.792,
|
||
|
|
"mean_token_accuracy": 0.08451972156763077,
|
||
|
|
"num_tokens": 267157.0,
|
||
|
|
"step": 130
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 9.346164798736572,
|
||
|
|
"epoch": 0.1226715129486597,
|
||
|
|
"grad_norm": 1.5625,
|
||
|
|
"learning_rate": 6.7e-05,
|
||
|
|
"loss": 7.729,
|
||
|
|
"mean_token_accuracy": 0.08054408058524132,
|
||
|
|
"num_tokens": 277370.0,
|
||
|
|
"step": 135
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 9.197631072998046,
|
||
|
|
"epoch": 0.12721490231712856,
|
||
|
|
"grad_norm": 1.8125,
|
||
|
|
"learning_rate": 6.950000000000001e-05,
|
||
|
|
"loss": 7.6448,
|
||
|
|
"mean_token_accuracy": 0.07991334870457649,
|
||
|
|
"num_tokens": 287851.0,
|
||
|
|
"step": 140
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.952075290679932,
|
||
|
|
"epoch": 0.13175829168559747,
|
||
|
|
"grad_norm": 1.9765625,
|
||
|
|
"learning_rate": 7.2e-05,
|
||
|
|
"loss": 7.6049,
|
||
|
|
"mean_token_accuracy": 0.08717379048466682,
|
||
|
|
"num_tokens": 299043.0,
|
||
|
|
"step": 145
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.753842163085938,
|
||
|
|
"epoch": 0.13630168105406634,
|
||
|
|
"grad_norm": 1.390625,
|
||
|
|
"learning_rate": 7.45e-05,
|
||
|
|
"loss": 7.514,
|
||
|
|
"mean_token_accuracy": 0.08479600548744201,
|
||
|
|
"num_tokens": 308525.0,
|
||
|
|
"step": 150
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.543214130401612,
|
||
|
|
"epoch": 0.14084507042253522,
|
||
|
|
"grad_norm": 2.0625,
|
||
|
|
"learning_rate": 7.7e-05,
|
||
|
|
"loss": 7.3998,
|
||
|
|
"mean_token_accuracy": 0.08677626475691795,
|
||
|
|
"num_tokens": 318301.0,
|
||
|
|
"step": 155
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.366859912872314,
|
||
|
|
"epoch": 0.1453884597910041,
|
||
|
|
"grad_norm": 1.2578125,
|
||
|
|
"learning_rate": 7.950000000000001e-05,
|
||
|
|
"loss": 7.3808,
|
||
|
|
"mean_token_accuracy": 0.08776860758662224,
|
||
|
|
"num_tokens": 329599.0,
|
||
|
|
"step": 160
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.208882141113282,
|
||
|
|
"epoch": 0.14993184915947297,
|
||
|
|
"grad_norm": 1.4296875,
|
||
|
|
"learning_rate": 8.2e-05,
|
||
|
|
"loss": 7.2913,
|
||
|
|
"mean_token_accuracy": 0.08820515275001525,
|
||
|
|
"num_tokens": 339446.0,
|
||
|
|
"step": 165
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.189261150360107,
|
||
|
|
"epoch": 0.15447523852794184,
|
||
|
|
"grad_norm": 1.515625,
|
||
|
|
"learning_rate": 8.450000000000001e-05,
|
||
|
|
"loss": 7.361,
|
||
|
|
"mean_token_accuracy": 0.08676841780543328,
|
||
|
|
"num_tokens": 349579.0,
|
||
|
|
"step": 170
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.030198335647583,
|
||
|
|
"epoch": 0.15901862789641072,
|
||
|
|
"grad_norm": 1.3203125,
|
||
|
|
"learning_rate": 8.7e-05,
|
||
|
|
"loss": 7.2959,
|
||
|
|
"mean_token_accuracy": 0.08807415291666984,
|
||
|
|
"num_tokens": 359452.0,
|
||
|
|
"step": 175
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.909095239639282,
|
||
|
|
"epoch": 0.1635620172648796,
|
||
|
|
"grad_norm": 1.359375,
|
||
|
|
"learning_rate": 8.95e-05,
|
||
|
|
"loss": 7.2007,
|
||
|
|
"mean_token_accuracy": 0.09265701398253441,
|
||
|
|
"num_tokens": 369558.0,
|
||
|
|
"step": 180
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.885198545455933,
|
||
|
|
"epoch": 0.16810540663334847,
|
||
|
|
"grad_norm": 1.5234375,
|
||
|
|
"learning_rate": 9.2e-05,
|
||
|
|
"loss": 7.2374,
|
||
|
|
"mean_token_accuracy": 0.09019400030374528,
|
||
|
|
"num_tokens": 380458.0,
|
||
|
|
"step": 185
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.863682413101197,
|
||
|
|
"epoch": 0.17264879600181735,
|
||
|
|
"grad_norm": 1.3046875,
|
||
|
|
"learning_rate": 9.45e-05,
|
||
|
|
"loss": 7.2124,
|
||
|
|
"mean_token_accuracy": 0.09065315276384353,
|
||
|
|
"num_tokens": 390051.0,
|
||
|
|
"step": 190
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.756366014480591,
|
||
|
|
"epoch": 0.17719218537028622,
|
||
|
|
"grad_norm": 1.5234375,
|
||
|
|
"learning_rate": 9.7e-05,
|
||
|
|
"loss": 7.1623,
|
||
|
|
"mean_token_accuracy": 0.09404176101088524,
|
||
|
|
"num_tokens": 400343.0,
|
||
|
|
"step": 195
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.77233304977417,
|
||
|
|
"epoch": 0.18173557473875512,
|
||
|
|
"grad_norm": 1.2734375,
|
||
|
|
"learning_rate": 9.95e-05,
|
||
|
|
"loss": 7.1858,
|
||
|
|
"mean_token_accuracy": 0.09119251668453217,
|
||
|
|
"num_tokens": 410004.0,
|
||
|
|
"step": 200
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.71948881149292,
|
||
|
|
"epoch": 0.186278964107224,
|
||
|
|
"grad_norm": 1.3203125,
|
||
|
|
"learning_rate": 0.000102,
|
||
|
|
"loss": 7.1628,
|
||
|
|
"mean_token_accuracy": 0.08677014708518982,
|
||
|
|
"num_tokens": 421286.0,
|
||
|
|
"step": 205
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.720707845687866,
|
||
|
|
"epoch": 0.19082235347569287,
|
||
|
|
"grad_norm": 1.0546875,
|
||
|
|
"learning_rate": 0.00010449999999999999,
|
||
|
|
"loss": 7.1961,
|
||
|
|
"mean_token_accuracy": 0.08782461136579514,
|
||
|
|
"num_tokens": 432351.0,
|
||
|
|
"step": 210
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.727673149108886,
|
||
|
|
"epoch": 0.19536574284416175,
|
||
|
|
"grad_norm": 1.4609375,
|
||
|
|
"learning_rate": 0.000107,
|
||
|
|
"loss": 7.1924,
|
||
|
|
"mean_token_accuracy": 0.09309446811676025,
|
||
|
|
"num_tokens": 442843.0,
|
||
|
|
"step": 215
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.621369409561157,
|
||
|
|
"epoch": 0.19990913221263062,
|
||
|
|
"grad_norm": 1.3828125,
|
||
|
|
"learning_rate": 0.0001095,
|
||
|
|
"loss": 7.0629,
|
||
|
|
"mean_token_accuracy": 0.09052515476942062,
|
||
|
|
"num_tokens": 453370.0,
|
||
|
|
"step": 220
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.63883638381958,
|
||
|
|
"epoch": 0.2044525215810995,
|
||
|
|
"grad_norm": 1.4609375,
|
||
|
|
"learning_rate": 0.000112,
|
||
|
|
"loss": 7.2184,
|
||
|
|
"mean_token_accuracy": 0.0872538447380066,
|
||
|
|
"num_tokens": 464715.0,
|
||
|
|
"step": 225
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.644190263748169,
|
||
|
|
"epoch": 0.20899591094956838,
|
||
|
|
"grad_norm": 1.15625,
|
||
|
|
"learning_rate": 0.0001145,
|
||
|
|
"loss": 7.0549,
|
||
|
|
"mean_token_accuracy": 0.0908614382147789,
|
||
|
|
"num_tokens": 475086.0,
|
||
|
|
"step": 230
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.491489458084106,
|
||
|
|
"epoch": 0.21353930031803725,
|
||
|
|
"grad_norm": 1.171875,
|
||
|
|
"learning_rate": 0.00011700000000000001,
|
||
|
|
"loss": 7.1148,
|
||
|
|
"mean_token_accuracy": 0.10133155509829521,
|
||
|
|
"num_tokens": 486088.0,
|
||
|
|
"step": 235
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.578480529785156,
|
||
|
|
"epoch": 0.21808268968650613,
|
||
|
|
"grad_norm": 1.4921875,
|
||
|
|
"learning_rate": 0.00011949999999999999,
|
||
|
|
"loss": 7.0797,
|
||
|
|
"mean_token_accuracy": 0.09119723215699196,
|
||
|
|
"num_tokens": 496978.0,
|
||
|
|
"step": 240
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.449330139160156,
|
||
|
|
"epoch": 0.222626079054975,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.000122,
|
||
|
|
"loss": 6.864,
|
||
|
|
"mean_token_accuracy": 0.1022227019071579,
|
||
|
|
"num_tokens": 507794.0,
|
||
|
|
"step": 245
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.454753732681274,
|
||
|
|
"epoch": 0.22716946842344388,
|
||
|
|
"grad_norm": 1.5078125,
|
||
|
|
"learning_rate": 0.0001245,
|
||
|
|
"loss": 7.0454,
|
||
|
|
"mean_token_accuracy": 0.09052475318312644,
|
||
|
|
"num_tokens": 517763.0,
|
||
|
|
"step": 250
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.496077680587769,
|
||
|
|
"epoch": 0.23171285779191278,
|
||
|
|
"grad_norm": 1.53125,
|
||
|
|
"learning_rate": 0.000127,
|
||
|
|
"loss": 6.9487,
|
||
|
|
"mean_token_accuracy": 0.0943218432366848,
|
||
|
|
"num_tokens": 527374.0,
|
||
|
|
"step": 255
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.425622415542603,
|
||
|
|
"epoch": 0.23625624716038165,
|
||
|
|
"grad_norm": 1.390625,
|
||
|
|
"learning_rate": 0.0001295,
|
||
|
|
"loss": 7.0141,
|
||
|
|
"mean_token_accuracy": 0.09675498828291892,
|
||
|
|
"num_tokens": 537435.0,
|
||
|
|
"step": 260
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.358550405502319,
|
||
|
|
"epoch": 0.24079963652885053,
|
||
|
|
"grad_norm": 1.390625,
|
||
|
|
"learning_rate": 0.000132,
|
||
|
|
"loss": 6.978,
|
||
|
|
"mean_token_accuracy": 0.09722853824496269,
|
||
|
|
"num_tokens": 547236.0,
|
||
|
|
"step": 265
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.3646965503692625,
|
||
|
|
"epoch": 0.2453430258973194,
|
||
|
|
"grad_norm": 1.3671875,
|
||
|
|
"learning_rate": 0.00013450000000000002,
|
||
|
|
"loss": 6.954,
|
||
|
|
"mean_token_accuracy": 0.09657247290015221,
|
||
|
|
"num_tokens": 557130.0,
|
||
|
|
"step": 270
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.437637186050415,
|
||
|
|
"epoch": 0.24988641526578828,
|
||
|
|
"grad_norm": 1.28125,
|
||
|
|
"learning_rate": 0.00013700000000000002,
|
||
|
|
"loss": 6.968,
|
||
|
|
"mean_token_accuracy": 0.09677831679582596,
|
||
|
|
"num_tokens": 567482.0,
|
||
|
|
"step": 275
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.320119571685791,
|
||
|
|
"epoch": 0.25442980463425713,
|
||
|
|
"grad_norm": 1.3046875,
|
||
|
|
"learning_rate": 0.0001395,
|
||
|
|
"loss": 6.862,
|
||
|
|
"mean_token_accuracy": 0.0923498347401619,
|
||
|
|
"num_tokens": 577084.0,
|
||
|
|
"step": 280
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.309446048736572,
|
||
|
|
"epoch": 0.25897319400272606,
|
||
|
|
"grad_norm": 1.328125,
|
||
|
|
"learning_rate": 0.00014199999999999998,
|
||
|
|
"loss": 6.972,
|
||
|
|
"mean_token_accuracy": 0.09742946326732635,
|
||
|
|
"num_tokens": 587980.0,
|
||
|
|
"step": 285
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.299356460571289,
|
||
|
|
"epoch": 0.26351658337119493,
|
||
|
|
"grad_norm": 1.3203125,
|
||
|
|
"learning_rate": 0.0001445,
|
||
|
|
"loss": 6.8505,
|
||
|
|
"mean_token_accuracy": 0.10278590098023414,
|
||
|
|
"num_tokens": 598989.0,
|
||
|
|
"step": 290
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.4622321128845215,
|
||
|
|
"epoch": 0.2680599727396638,
|
||
|
|
"grad_norm": 1.3359375,
|
||
|
|
"learning_rate": 0.000147,
|
||
|
|
"loss": 7.0462,
|
||
|
|
"mean_token_accuracy": 0.09367327913641929,
|
||
|
|
"num_tokens": 608599.0,
|
||
|
|
"step": 295
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.311740112304688,
|
||
|
|
"epoch": 0.2726033621081327,
|
||
|
|
"grad_norm": 1.21875,
|
||
|
|
"learning_rate": 0.0001495,
|
||
|
|
"loss": 6.8489,
|
||
|
|
"mean_token_accuracy": 0.09894169121980667,
|
||
|
|
"num_tokens": 619267.0,
|
||
|
|
"step": 300
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.329383373260498,
|
||
|
|
"epoch": 0.27714675147660156,
|
||
|
|
"grad_norm": 1.2578125,
|
||
|
|
"learning_rate": 0.000152,
|
||
|
|
"loss": 7.0237,
|
||
|
|
"mean_token_accuracy": 0.0995009183883667,
|
||
|
|
"num_tokens": 629991.0,
|
||
|
|
"step": 305
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.334739446640015,
|
||
|
|
"epoch": 0.28169014084507044,
|
||
|
|
"grad_norm": 1.34375,
|
||
|
|
"learning_rate": 0.00015450000000000001,
|
||
|
|
"loss": 6.9751,
|
||
|
|
"mean_token_accuracy": 0.09126680493354797,
|
||
|
|
"num_tokens": 641311.0,
|
||
|
|
"step": 310
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.340094423294067,
|
||
|
|
"epoch": 0.2862335302135393,
|
||
|
|
"grad_norm": 0.953125,
|
||
|
|
"learning_rate": 0.000157,
|
||
|
|
"loss": 6.9349,
|
||
|
|
"mean_token_accuracy": 0.0958991676568985,
|
||
|
|
"num_tokens": 651812.0,
|
||
|
|
"step": 315
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.323620367050171,
|
||
|
|
"epoch": 0.2907769195820082,
|
||
|
|
"grad_norm": 1.203125,
|
||
|
|
"learning_rate": 0.0001595,
|
||
|
|
"loss": 6.8849,
|
||
|
|
"mean_token_accuracy": 0.10023088753223419,
|
||
|
|
"num_tokens": 662387.0,
|
||
|
|
"step": 320
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.2562236309051515,
|
||
|
|
"epoch": 0.29532030895047706,
|
||
|
|
"grad_norm": 1.375,
|
||
|
|
"learning_rate": 0.000162,
|
||
|
|
"loss": 6.8697,
|
||
|
|
"mean_token_accuracy": 0.09553462415933608,
|
||
|
|
"num_tokens": 673018.0,
|
||
|
|
"step": 325
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.216851282119751,
|
||
|
|
"epoch": 0.29986369831894594,
|
||
|
|
"grad_norm": 1.328125,
|
||
|
|
"learning_rate": 0.00016450000000000001,
|
||
|
|
"loss": 6.8094,
|
||
|
|
"mean_token_accuracy": 0.09729016497731209,
|
||
|
|
"num_tokens": 683192.0,
|
||
|
|
"step": 330
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.253824520111084,
|
||
|
|
"epoch": 0.3044070876874148,
|
||
|
|
"grad_norm": 1.5,
|
||
|
|
"learning_rate": 0.00016700000000000002,
|
||
|
|
"loss": 6.9097,
|
||
|
|
"mean_token_accuracy": 0.10488839745521546,
|
||
|
|
"num_tokens": 692747.0,
|
||
|
|
"step": 335
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.1223766803741455,
|
||
|
|
"epoch": 0.3089504770558837,
|
||
|
|
"grad_norm": 1.0625,
|
||
|
|
"learning_rate": 0.00016950000000000003,
|
||
|
|
"loss": 6.8912,
|
||
|
|
"mean_token_accuracy": 0.09245335534214974,
|
||
|
|
"num_tokens": 705109.0,
|
||
|
|
"step": 340
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.2870441436767575,
|
||
|
|
"epoch": 0.31349386642435256,
|
||
|
|
"grad_norm": 1.234375,
|
||
|
|
"learning_rate": 0.00017199999999999998,
|
||
|
|
"loss": 6.8193,
|
||
|
|
"mean_token_accuracy": 0.09904048666357994,
|
||
|
|
"num_tokens": 715658.0,
|
||
|
|
"step": 345
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.1810273170471195,
|
||
|
|
"epoch": 0.31803725579282144,
|
||
|
|
"grad_norm": 1.25,
|
||
|
|
"learning_rate": 0.00017449999999999999,
|
||
|
|
"loss": 6.8301,
|
||
|
|
"mean_token_accuracy": 0.10451033040881157,
|
||
|
|
"num_tokens": 724961.0,
|
||
|
|
"step": 350
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.068193769454956,
|
||
|
|
"epoch": 0.3225806451612903,
|
||
|
|
"grad_norm": 1.3359375,
|
||
|
|
"learning_rate": 0.000177,
|
||
|
|
"loss": 6.7801,
|
||
|
|
"mean_token_accuracy": 0.10440796837210656,
|
||
|
|
"num_tokens": 735416.0,
|
||
|
|
"step": 355
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.2093346118927,
|
||
|
|
"epoch": 0.3271240345297592,
|
||
|
|
"grad_norm": 1.8046875,
|
||
|
|
"learning_rate": 0.0001795,
|
||
|
|
"loss": 6.8719,
|
||
|
|
"mean_token_accuracy": 0.10421840399503708,
|
||
|
|
"num_tokens": 745005.0,
|
||
|
|
"step": 360
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.2864179611206055,
|
||
|
|
"epoch": 0.33166742389822806,
|
||
|
|
"grad_norm": 1.328125,
|
||
|
|
"learning_rate": 0.000182,
|
||
|
|
"loss": 6.9046,
|
||
|
|
"mean_token_accuracy": 0.10184969678521157,
|
||
|
|
"num_tokens": 754743.0,
|
||
|
|
"step": 365
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.0180971145629885,
|
||
|
|
"epoch": 0.33621081326669694,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.0001845,
|
||
|
|
"loss": 6.7603,
|
||
|
|
"mean_token_accuracy": 0.10306568518280983,
|
||
|
|
"num_tokens": 764897.0,
|
||
|
|
"step": 370
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.152372789382935,
|
||
|
|
"epoch": 0.3407542026351658,
|
||
|
|
"grad_norm": 1.1796875,
|
||
|
|
"learning_rate": 0.000187,
|
||
|
|
"loss": 6.8267,
|
||
|
|
"mean_token_accuracy": 0.09857897013425827,
|
||
|
|
"num_tokens": 775302.0,
|
||
|
|
"step": 375
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.124710941314698,
|
||
|
|
"epoch": 0.3452975920036347,
|
||
|
|
"grad_norm": 1.28125,
|
||
|
|
"learning_rate": 0.0001895,
|
||
|
|
"loss": 6.7588,
|
||
|
|
"mean_token_accuracy": 0.10548576042056083,
|
||
|
|
"num_tokens": 785694.0,
|
||
|
|
"step": 380
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.054194736480713,
|
||
|
|
"epoch": 0.34984098137210357,
|
||
|
|
"grad_norm": 1.2265625,
|
||
|
|
"learning_rate": 0.000192,
|
||
|
|
"loss": 6.72,
|
||
|
|
"mean_token_accuracy": 0.11008026450872421,
|
||
|
|
"num_tokens": 795045.0,
|
||
|
|
"step": 385
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.09068751335144,
|
||
|
|
"epoch": 0.35438437074057244,
|
||
|
|
"grad_norm": 1.265625,
|
||
|
|
"learning_rate": 0.0001945,
|
||
|
|
"loss": 6.781,
|
||
|
|
"mean_token_accuracy": 0.10049664527177811,
|
||
|
|
"num_tokens": 805579.0,
|
||
|
|
"step": 390
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.095667552947998,
|
||
|
|
"epoch": 0.35892776010904137,
|
||
|
|
"grad_norm": 1.109375,
|
||
|
|
"learning_rate": 0.00019700000000000002,
|
||
|
|
"loss": 6.6838,
|
||
|
|
"mean_token_accuracy": 0.10740630999207497,
|
||
|
|
"num_tokens": 816743.0,
|
||
|
|
"step": 395
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.093503808975219,
|
||
|
|
"epoch": 0.36347114947751025,
|
||
|
|
"grad_norm": 1.3046875,
|
||
|
|
"learning_rate": 0.00019950000000000002,
|
||
|
|
"loss": 6.8234,
|
||
|
|
"mean_token_accuracy": 0.09930850043892861,
|
||
|
|
"num_tokens": 827217.0,
|
||
|
|
"step": 400
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.012804555892944,
|
||
|
|
"epoch": 0.3680145388459791,
|
||
|
|
"grad_norm": 1.2265625,
|
||
|
|
"learning_rate": 0.000202,
|
||
|
|
"loss": 6.6731,
|
||
|
|
"mean_token_accuracy": 0.10424429401755334,
|
||
|
|
"num_tokens": 837555.0,
|
||
|
|
"step": 405
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.039196920394898,
|
||
|
|
"epoch": 0.372557928214448,
|
||
|
|
"grad_norm": 1.3203125,
|
||
|
|
"learning_rate": 0.00020449999999999998,
|
||
|
|
"loss": 6.7459,
|
||
|
|
"mean_token_accuracy": 0.10508461520075799,
|
||
|
|
"num_tokens": 846726.0,
|
||
|
|
"step": 410
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.120304107666016,
|
||
|
|
"epoch": 0.3771013175829169,
|
||
|
|
"grad_norm": 1.1015625,
|
||
|
|
"learning_rate": 0.000207,
|
||
|
|
"loss": 6.7475,
|
||
|
|
"mean_token_accuracy": 0.10223370566964149,
|
||
|
|
"num_tokens": 856535.0,
|
||
|
|
"step": 415
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.005828332901001,
|
||
|
|
"epoch": 0.38164470695138575,
|
||
|
|
"grad_norm": 1.125,
|
||
|
|
"learning_rate": 0.0002095,
|
||
|
|
"loss": 6.8069,
|
||
|
|
"mean_token_accuracy": 0.09859322756528854,
|
||
|
|
"num_tokens": 866973.0,
|
||
|
|
"step": 420
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.085656690597534,
|
||
|
|
"epoch": 0.3861880963198546,
|
||
|
|
"grad_norm": 1.2734375,
|
||
|
|
"learning_rate": 0.000212,
|
||
|
|
"loss": 6.7415,
|
||
|
|
"mean_token_accuracy": 0.1009980633854866,
|
||
|
|
"num_tokens": 877873.0,
|
||
|
|
"step": 425
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.018812036514282,
|
||
|
|
"epoch": 0.3907314856883235,
|
||
|
|
"grad_norm": 1.2265625,
|
||
|
|
"learning_rate": 0.0002145,
|
||
|
|
"loss": 6.7335,
|
||
|
|
"mean_token_accuracy": 0.10494705140590668,
|
||
|
|
"num_tokens": 887135.0,
|
||
|
|
"step": 430
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.096279811859131,
|
||
|
|
"epoch": 0.3952748750567924,
|
||
|
|
"grad_norm": 1.1640625,
|
||
|
|
"learning_rate": 0.00021700000000000002,
|
||
|
|
"loss": 6.7514,
|
||
|
|
"mean_token_accuracy": 0.10019353330135346,
|
||
|
|
"num_tokens": 897206.0,
|
||
|
|
"step": 435
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.024485397338867,
|
||
|
|
"epoch": 0.39981826442526125,
|
||
|
|
"grad_norm": 1.234375,
|
||
|
|
"learning_rate": 0.0002195,
|
||
|
|
"loss": 6.7353,
|
||
|
|
"mean_token_accuracy": 0.10563584491610527,
|
||
|
|
"num_tokens": 906808.0,
|
||
|
|
"step": 440
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.898047828674317,
|
||
|
|
"epoch": 0.4043616537937301,
|
||
|
|
"grad_norm": 1.265625,
|
||
|
|
"learning_rate": 0.000222,
|
||
|
|
"loss": 6.6422,
|
||
|
|
"mean_token_accuracy": 0.11458711996674538,
|
||
|
|
"num_tokens": 917177.0,
|
||
|
|
"step": 445
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.959504508972168,
|
||
|
|
"epoch": 0.408905043162199,
|
||
|
|
"grad_norm": 1.265625,
|
||
|
|
"learning_rate": 0.0002245,
|
||
|
|
"loss": 6.6907,
|
||
|
|
"mean_token_accuracy": 0.10576008260250092,
|
||
|
|
"num_tokens": 927229.0,
|
||
|
|
"step": 450
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.006360816955566,
|
||
|
|
"epoch": 0.4134484325306679,
|
||
|
|
"grad_norm": 1.2109375,
|
||
|
|
"learning_rate": 0.00022700000000000002,
|
||
|
|
"loss": 6.6812,
|
||
|
|
"mean_token_accuracy": 0.11021844074130058,
|
||
|
|
"num_tokens": 937832.0,
|
||
|
|
"step": 455
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.870974111557007,
|
||
|
|
"epoch": 0.41799182189913675,
|
||
|
|
"grad_norm": 1.21875,
|
||
|
|
"learning_rate": 0.00022950000000000002,
|
||
|
|
"loss": 6.6064,
|
||
|
|
"mean_token_accuracy": 0.10718697234988213,
|
||
|
|
"num_tokens": 948038.0,
|
||
|
|
"step": 460
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.002683067321778,
|
||
|
|
"epoch": 0.4225352112676056,
|
||
|
|
"grad_norm": 1.1015625,
|
||
|
|
"learning_rate": 0.00023200000000000003,
|
||
|
|
"loss": 6.7181,
|
||
|
|
"mean_token_accuracy": 0.10097691044211388,
|
||
|
|
"num_tokens": 957924.0,
|
||
|
|
"step": 465
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.933505868911743,
|
||
|
|
"epoch": 0.4270786006360745,
|
||
|
|
"grad_norm": 1.0078125,
|
||
|
|
"learning_rate": 0.00023449999999999998,
|
||
|
|
"loss": 6.6792,
|
||
|
|
"mean_token_accuracy": 0.10600680485367775,
|
||
|
|
"num_tokens": 968497.0,
|
||
|
|
"step": 470
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.915420055389404,
|
||
|
|
"epoch": 0.4316219900045434,
|
||
|
|
"grad_norm": 1.125,
|
||
|
|
"learning_rate": 0.000237,
|
||
|
|
"loss": 6.6043,
|
||
|
|
"mean_token_accuracy": 0.11050590574741363,
|
||
|
|
"num_tokens": 978878.0,
|
||
|
|
"step": 475
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.828244590759278,
|
||
|
|
"epoch": 0.43616537937301225,
|
||
|
|
"grad_norm": 1.2265625,
|
||
|
|
"learning_rate": 0.0002395,
|
||
|
|
"loss": 6.7024,
|
||
|
|
"mean_token_accuracy": 0.10729977861046791,
|
||
|
|
"num_tokens": 989984.0,
|
||
|
|
"step": 480
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.974292421340943,
|
||
|
|
"epoch": 0.4407087687414811,
|
||
|
|
"grad_norm": 1.125,
|
||
|
|
"learning_rate": 0.000242,
|
||
|
|
"loss": 6.6266,
|
||
|
|
"mean_token_accuracy": 0.1099898062646389,
|
||
|
|
"num_tokens": 1000254.0,
|
||
|
|
"step": 485
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.815394496917724,
|
||
|
|
"epoch": 0.44525215810995,
|
||
|
|
"grad_norm": 1.1640625,
|
||
|
|
"learning_rate": 0.0002445,
|
||
|
|
"loss": 6.687,
|
||
|
|
"mean_token_accuracy": 0.10523343607783317,
|
||
|
|
"num_tokens": 1010697.0,
|
||
|
|
"step": 490
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.067700672149658,
|
||
|
|
"epoch": 0.4497955474784189,
|
||
|
|
"grad_norm": 1.1171875,
|
||
|
|
"learning_rate": 0.000247,
|
||
|
|
"loss": 6.7775,
|
||
|
|
"mean_token_accuracy": 0.10482538044452668,
|
||
|
|
"num_tokens": 1020892.0,
|
||
|
|
"step": 495
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.969514179229736,
|
||
|
|
"epoch": 0.45433893684688775,
|
||
|
|
"grad_norm": 1.2421875,
|
||
|
|
"learning_rate": 0.0002495,
|
||
|
|
"loss": 6.6552,
|
||
|
|
"mean_token_accuracy": 0.11519927084445954,
|
||
|
|
"num_tokens": 1030380.0,
|
||
|
|
"step": 500
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.45433893684688775,
|
||
|
|
"eval_entropy": 6.938153394432955,
|
||
|
|
"eval_loss": 6.763866901397705,
|
||
|
|
"eval_mean_token_accuracy": 0.10726368882974913,
|
||
|
|
"eval_num_tokens": 1030380.0,
|
||
|
|
"eval_runtime": 2.6364,
|
||
|
|
"eval_samples_per_second": 1302.937,
|
||
|
|
"eval_steps_per_second": 163.104,
|
||
|
|
"step": 500
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.912630319595337,
|
||
|
|
"epoch": 0.45888232621535663,
|
||
|
|
"grad_norm": 1.3203125,
|
||
|
|
"learning_rate": 0.000252,
|
||
|
|
"loss": 6.7031,
|
||
|
|
"mean_token_accuracy": 0.10474735051393509,
|
||
|
|
"num_tokens": 1040301.0,
|
||
|
|
"step": 505
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.821575069427491,
|
||
|
|
"epoch": 0.46342571558382556,
|
||
|
|
"grad_norm": 1.2421875,
|
||
|
|
"learning_rate": 0.0002545,
|
||
|
|
"loss": 6.5677,
|
||
|
|
"mean_token_accuracy": 0.11079607084393502,
|
||
|
|
"num_tokens": 1051999.0,
|
||
|
|
"step": 510
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.036813116073608,
|
||
|
|
"epoch": 0.46796910495229443,
|
||
|
|
"grad_norm": 1.1640625,
|
||
|
|
"learning_rate": 0.000257,
|
||
|
|
"loss": 6.7879,
|
||
|
|
"mean_token_accuracy": 0.10318484753370286,
|
||
|
|
"num_tokens": 1063133.0,
|
||
|
|
"step": 515
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.810295963287354,
|
||
|
|
"epoch": 0.4725124943207633,
|
||
|
|
"grad_norm": 1.296875,
|
||
|
|
"learning_rate": 0.0002595,
|
||
|
|
"loss": 6.6059,
|
||
|
|
"mean_token_accuracy": 0.10231919735670089,
|
||
|
|
"num_tokens": 1073972.0,
|
||
|
|
"step": 520
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.8240800380706785,
|
||
|
|
"epoch": 0.4770558836892322,
|
||
|
|
"grad_norm": 1.484375,
|
||
|
|
"learning_rate": 0.000262,
|
||
|
|
"loss": 6.5935,
|
||
|
|
"mean_token_accuracy": 0.10545961037278176,
|
||
|
|
"num_tokens": 1084050.0,
|
||
|
|
"step": 525
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.935742712020874,
|
||
|
|
"epoch": 0.48159927305770106,
|
||
|
|
"grad_norm": 1.34375,
|
||
|
|
"learning_rate": 0.00026450000000000003,
|
||
|
|
"loss": 6.7033,
|
||
|
|
"mean_token_accuracy": 0.1093459077179432,
|
||
|
|
"num_tokens": 1094415.0,
|
||
|
|
"step": 530
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.71245813369751,
|
||
|
|
"epoch": 0.48614266242616994,
|
||
|
|
"grad_norm": 1.2109375,
|
||
|
|
"learning_rate": 0.00026700000000000004,
|
||
|
|
"loss": 6.6194,
|
||
|
|
"mean_token_accuracy": 0.10769399031996726,
|
||
|
|
"num_tokens": 1105133.0,
|
||
|
|
"step": 535
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.876086091995239,
|
||
|
|
"epoch": 0.4906860517946388,
|
||
|
|
"grad_norm": 1.1015625,
|
||
|
|
"learning_rate": 0.00026950000000000005,
|
||
|
|
"loss": 6.5726,
|
||
|
|
"mean_token_accuracy": 0.11468547657132148,
|
||
|
|
"num_tokens": 1115266.0,
|
||
|
|
"step": 540
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.729256963729858,
|
||
|
|
"epoch": 0.4952294411631077,
|
||
|
|
"grad_norm": 1.140625,
|
||
|
|
"learning_rate": 0.00027200000000000005,
|
||
|
|
"loss": 6.5545,
|
||
|
|
"mean_token_accuracy": 0.1140455037355423,
|
||
|
|
"num_tokens": 1124775.0,
|
||
|
|
"step": 545
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.831462669372558,
|
||
|
|
"epoch": 0.49977283053157656,
|
||
|
|
"grad_norm": 1.078125,
|
||
|
|
"learning_rate": 0.0002745,
|
||
|
|
"loss": 6.6004,
|
||
|
|
"mean_token_accuracy": 0.11026408672332763,
|
||
|
|
"num_tokens": 1134498.0,
|
||
|
|
"step": 550
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.807862949371338,
|
||
|
|
"epoch": 0.5043162199000454,
|
||
|
|
"grad_norm": 1.4609375,
|
||
|
|
"learning_rate": 0.000277,
|
||
|
|
"loss": 6.6423,
|
||
|
|
"mean_token_accuracy": 0.10805548503994941,
|
||
|
|
"num_tokens": 1146067.0,
|
||
|
|
"step": 555
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.918079137802124,
|
||
|
|
"epoch": 0.5088596092685143,
|
||
|
|
"grad_norm": 1.25,
|
||
|
|
"learning_rate": 0.0002795,
|
||
|
|
"loss": 6.6528,
|
||
|
|
"mean_token_accuracy": 0.10948517173528671,
|
||
|
|
"num_tokens": 1156349.0,
|
||
|
|
"step": 560
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.835301733016967,
|
||
|
|
"epoch": 0.5134029986369832,
|
||
|
|
"grad_norm": 1.1328125,
|
||
|
|
"learning_rate": 0.00028199999999999997,
|
||
|
|
"loss": 6.5719,
|
||
|
|
"mean_token_accuracy": 0.10832828059792518,
|
||
|
|
"num_tokens": 1166851.0,
|
||
|
|
"step": 565
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.76150369644165,
|
||
|
|
"epoch": 0.5179463880054521,
|
||
|
|
"grad_norm": 1.15625,
|
||
|
|
"learning_rate": 0.0002845,
|
||
|
|
"loss": 6.527,
|
||
|
|
"mean_token_accuracy": 0.11024561673402786,
|
||
|
|
"num_tokens": 1176899.0,
|
||
|
|
"step": 570
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.7258953094482425,
|
||
|
|
"epoch": 0.522489777373921,
|
||
|
|
"grad_norm": 0.95703125,
|
||
|
|
"learning_rate": 0.000287,
|
||
|
|
"loss": 6.6245,
|
||
|
|
"mean_token_accuracy": 0.10835396870970726,
|
||
|
|
"num_tokens": 1187383.0,
|
||
|
|
"step": 575
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.841786193847656,
|
||
|
|
"epoch": 0.5270331667423899,
|
||
|
|
"grad_norm": 1.1015625,
|
||
|
|
"learning_rate": 0.0002895,
|
||
|
|
"loss": 6.601,
|
||
|
|
"mean_token_accuracy": 0.11034611463546753,
|
||
|
|
"num_tokens": 1197836.0,
|
||
|
|
"step": 580
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.7962751388549805,
|
||
|
|
"epoch": 0.5315765561108587,
|
||
|
|
"grad_norm": 1.1328125,
|
||
|
|
"learning_rate": 0.000292,
|
||
|
|
"loss": 6.5547,
|
||
|
|
"mean_token_accuracy": 0.1168977290391922,
|
||
|
|
"num_tokens": 1208533.0,
|
||
|
|
"step": 585
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.752965354919434,
|
||
|
|
"epoch": 0.5361199454793276,
|
||
|
|
"grad_norm": 1.1484375,
|
||
|
|
"learning_rate": 0.0002945,
|
||
|
|
"loss": 6.5959,
|
||
|
|
"mean_token_accuracy": 0.10688599348068237,
|
||
|
|
"num_tokens": 1219397.0,
|
||
|
|
"step": 590
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.719386243820191,
|
||
|
|
"epoch": 0.5406633348477965,
|
||
|
|
"grad_norm": 1.0625,
|
||
|
|
"learning_rate": 0.000297,
|
||
|
|
"loss": 6.5847,
|
||
|
|
"mean_token_accuracy": 0.10793909430503845,
|
||
|
|
"num_tokens": 1229991.0,
|
||
|
|
"step": 595
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.685470914840698,
|
||
|
|
"epoch": 0.5452067242162654,
|
||
|
|
"grad_norm": 1.140625,
|
||
|
|
"learning_rate": 0.0002995,
|
||
|
|
"loss": 6.487,
|
||
|
|
"mean_token_accuracy": 0.10784793198108673,
|
||
|
|
"num_tokens": 1240343.0,
|
||
|
|
"step": 600
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.747214031219483,
|
||
|
|
"epoch": 0.5497501135847342,
|
||
|
|
"grad_norm": 1.1484375,
|
||
|
|
"learning_rate": 0.000302,
|
||
|
|
"loss": 6.5528,
|
||
|
|
"mean_token_accuracy": 0.10783586576581002,
|
||
|
|
"num_tokens": 1250432.0,
|
||
|
|
"step": 605
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.683514261245728,
|
||
|
|
"epoch": 0.5542935029532031,
|
||
|
|
"grad_norm": 1.125,
|
||
|
|
"learning_rate": 0.0003045,
|
||
|
|
"loss": 6.4859,
|
||
|
|
"mean_token_accuracy": 0.11751269921660423,
|
||
|
|
"num_tokens": 1260744.0,
|
||
|
|
"step": 610
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.735761070251465,
|
||
|
|
"epoch": 0.558836892321672,
|
||
|
|
"grad_norm": 1.1875,
|
||
|
|
"learning_rate": 0.000307,
|
||
|
|
"loss": 6.516,
|
||
|
|
"mean_token_accuracy": 0.11311889961361885,
|
||
|
|
"num_tokens": 1272155.0,
|
||
|
|
"step": 615
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.594959259033203,
|
||
|
|
"epoch": 0.5633802816901409,
|
||
|
|
"grad_norm": 1.234375,
|
||
|
|
"learning_rate": 0.0003095,
|
||
|
|
"loss": 6.3957,
|
||
|
|
"mean_token_accuracy": 0.11406432464718819,
|
||
|
|
"num_tokens": 1282240.0,
|
||
|
|
"step": 620
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.700835132598877,
|
||
|
|
"epoch": 0.5679236710586097,
|
||
|
|
"grad_norm": 1.1328125,
|
||
|
|
"learning_rate": 0.000312,
|
||
|
|
"loss": 6.5768,
|
||
|
|
"mean_token_accuracy": 0.11421498507261277,
|
||
|
|
"num_tokens": 1292169.0,
|
||
|
|
"step": 625
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.643769598007202,
|
||
|
|
"epoch": 0.5724670604270786,
|
||
|
|
"grad_norm": 1.171875,
|
||
|
|
"learning_rate": 0.0003145,
|
||
|
|
"loss": 6.474,
|
||
|
|
"mean_token_accuracy": 0.11547293737530709,
|
||
|
|
"num_tokens": 1302010.0,
|
||
|
|
"step": 630
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.698951387405396,
|
||
|
|
"epoch": 0.5770104497955475,
|
||
|
|
"grad_norm": 1.0546875,
|
||
|
|
"learning_rate": 0.000317,
|
||
|
|
"loss": 6.5299,
|
||
|
|
"mean_token_accuracy": 0.11720511168241501,
|
||
|
|
"num_tokens": 1312596.0,
|
||
|
|
"step": 635
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.670014810562134,
|
||
|
|
"epoch": 0.5815538391640164,
|
||
|
|
"grad_norm": 1.203125,
|
||
|
|
"learning_rate": 0.0003195,
|
||
|
|
"loss": 6.4806,
|
||
|
|
"mean_token_accuracy": 0.10972161293029785,
|
||
|
|
"num_tokens": 1321753.0,
|
||
|
|
"step": 640
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.6802314758300785,
|
||
|
|
"epoch": 0.5860972285324852,
|
||
|
|
"grad_norm": 1.1953125,
|
||
|
|
"learning_rate": 0.000322,
|
||
|
|
"loss": 6.5269,
|
||
|
|
"mean_token_accuracy": 0.11095310598611832,
|
||
|
|
"num_tokens": 1332059.0,
|
||
|
|
"step": 645
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.659747362136841,
|
||
|
|
"epoch": 0.5906406179009541,
|
||
|
|
"grad_norm": 1.140625,
|
||
|
|
"learning_rate": 0.00032450000000000003,
|
||
|
|
"loss": 6.5006,
|
||
|
|
"mean_token_accuracy": 0.11720726266503334,
|
||
|
|
"num_tokens": 1341517.0,
|
||
|
|
"step": 650
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.768359041213989,
|
||
|
|
"epoch": 0.595184007269423,
|
||
|
|
"grad_norm": 1.171875,
|
||
|
|
"learning_rate": 0.00032700000000000003,
|
||
|
|
"loss": 6.5744,
|
||
|
|
"mean_token_accuracy": 0.11781106889247894,
|
||
|
|
"num_tokens": 1351439.0,
|
||
|
|
"step": 655
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.605283737182617,
|
||
|
|
"epoch": 0.5997273966378919,
|
||
|
|
"grad_norm": 1.1875,
|
||
|
|
"learning_rate": 0.00032950000000000004,
|
||
|
|
"loss": 6.4471,
|
||
|
|
"mean_token_accuracy": 0.11385733485221863,
|
||
|
|
"num_tokens": 1360745.0,
|
||
|
|
"step": 660
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.614739894866943,
|
||
|
|
"epoch": 0.6042707860063607,
|
||
|
|
"grad_norm": 1.1171875,
|
||
|
|
"learning_rate": 0.00033200000000000005,
|
||
|
|
"loss": 6.4547,
|
||
|
|
"mean_token_accuracy": 0.11523936912417412,
|
||
|
|
"num_tokens": 1371931.0,
|
||
|
|
"step": 665
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.524019193649292,
|
||
|
|
"epoch": 0.6088141753748296,
|
||
|
|
"grad_norm": 1.1640625,
|
||
|
|
"learning_rate": 0.00033450000000000005,
|
||
|
|
"loss": 6.4051,
|
||
|
|
"mean_token_accuracy": 0.11907100528478623,
|
||
|
|
"num_tokens": 1382040.0,
|
||
|
|
"step": 670
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.583529663085938,
|
||
|
|
"epoch": 0.6133575647432985,
|
||
|
|
"grad_norm": 1.1875,
|
||
|
|
"learning_rate": 0.000337,
|
||
|
|
"loss": 6.4651,
|
||
|
|
"mean_token_accuracy": 0.10969016775488853,
|
||
|
|
"num_tokens": 1392690.0,
|
||
|
|
"step": 675
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.671084403991699,
|
||
|
|
"epoch": 0.6179009541117674,
|
||
|
|
"grad_norm": 1.2421875,
|
||
|
|
"learning_rate": 0.0003395,
|
||
|
|
"loss": 6.4711,
|
||
|
|
"mean_token_accuracy": 0.11799429208040238,
|
||
|
|
"num_tokens": 1403060.0,
|
||
|
|
"step": 680
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.62229208946228,
|
||
|
|
"epoch": 0.6224443434802363,
|
||
|
|
"grad_norm": 1.109375,
|
||
|
|
"learning_rate": 0.000342,
|
||
|
|
"loss": 6.4732,
|
||
|
|
"mean_token_accuracy": 0.11298275738954544,
|
||
|
|
"num_tokens": 1412895.0,
|
||
|
|
"step": 685
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.59600863456726,
|
||
|
|
"epoch": 0.6269877328487051,
|
||
|
|
"grad_norm": 1.234375,
|
||
|
|
"learning_rate": 0.00034449999999999997,
|
||
|
|
"loss": 6.425,
|
||
|
|
"mean_token_accuracy": 0.12277772873640061,
|
||
|
|
"num_tokens": 1423024.0,
|
||
|
|
"step": 690
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.580408048629761,
|
||
|
|
"epoch": 0.631531122217174,
|
||
|
|
"grad_norm": 1.125,
|
||
|
|
"learning_rate": 0.000347,
|
||
|
|
"loss": 6.4492,
|
||
|
|
"mean_token_accuracy": 0.11523076891899109,
|
||
|
|
"num_tokens": 1433578.0,
|
||
|
|
"step": 695
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.551895475387573,
|
||
|
|
"epoch": 0.6360745115856429,
|
||
|
|
"grad_norm": 1.203125,
|
||
|
|
"learning_rate": 0.0003495,
|
||
|
|
"loss": 6.4945,
|
||
|
|
"mean_token_accuracy": 0.11739786639809609,
|
||
|
|
"num_tokens": 1444473.0,
|
||
|
|
"step": 700
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.677528762817383,
|
||
|
|
"epoch": 0.6406179009541118,
|
||
|
|
"grad_norm": 1.125,
|
||
|
|
"learning_rate": 0.000352,
|
||
|
|
"loss": 6.513,
|
||
|
|
"mean_token_accuracy": 0.11457236558198929,
|
||
|
|
"num_tokens": 1454553.0,
|
||
|
|
"step": 705
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.594537878036499,
|
||
|
|
"epoch": 0.6451612903225806,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.0003545,
|
||
|
|
"loss": 6.368,
|
||
|
|
"mean_token_accuracy": 0.11736505180597305,
|
||
|
|
"num_tokens": 1464162.0,
|
||
|
|
"step": 710
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.536549663543701,
|
||
|
|
"epoch": 0.6497046796910495,
|
||
|
|
"grad_norm": 0.984375,
|
||
|
|
"learning_rate": 0.000357,
|
||
|
|
"loss": 6.4261,
|
||
|
|
"mean_token_accuracy": 0.11977096050977706,
|
||
|
|
"num_tokens": 1474691.0,
|
||
|
|
"step": 715
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.626703071594238,
|
||
|
|
"epoch": 0.6542480690595184,
|
||
|
|
"grad_norm": 1.28125,
|
||
|
|
"learning_rate": 0.0003595,
|
||
|
|
"loss": 6.5126,
|
||
|
|
"mean_token_accuracy": 0.11911239996552467,
|
||
|
|
"num_tokens": 1484650.0,
|
||
|
|
"step": 720
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.5932032585144045,
|
||
|
|
"epoch": 0.6587914584279873,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.000362,
|
||
|
|
"loss": 6.4708,
|
||
|
|
"mean_token_accuracy": 0.11753673776984215,
|
||
|
|
"num_tokens": 1494788.0,
|
||
|
|
"step": 725
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.577540493011474,
|
||
|
|
"epoch": 0.6633348477964561,
|
||
|
|
"grad_norm": 1.2578125,
|
||
|
|
"learning_rate": 0.0003645,
|
||
|
|
"loss": 6.4192,
|
||
|
|
"mean_token_accuracy": 0.11684553176164628,
|
||
|
|
"num_tokens": 1506574.0,
|
||
|
|
"step": 730
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.492519283294678,
|
||
|
|
"epoch": 0.667878237164925,
|
||
|
|
"grad_norm": 1.2265625,
|
||
|
|
"learning_rate": 0.000367,
|
||
|
|
"loss": 6.44,
|
||
|
|
"mean_token_accuracy": 0.11481376960873604,
|
||
|
|
"num_tokens": 1517505.0,
|
||
|
|
"step": 735
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.5567238330841064,
|
||
|
|
"epoch": 0.6724216265333939,
|
||
|
|
"grad_norm": 1.1484375,
|
||
|
|
"learning_rate": 0.0003695,
|
||
|
|
"loss": 6.3389,
|
||
|
|
"mean_token_accuracy": 0.12622489854693414,
|
||
|
|
"num_tokens": 1526662.0,
|
||
|
|
"step": 740
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.474819231033325,
|
||
|
|
"epoch": 0.6769650159018628,
|
||
|
|
"grad_norm": 1.1875,
|
||
|
|
"learning_rate": 0.000372,
|
||
|
|
"loss": 6.4503,
|
||
|
|
"mean_token_accuracy": 0.117062958329916,
|
||
|
|
"num_tokens": 1536798.0,
|
||
|
|
"step": 745
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.589357805252075,
|
||
|
|
"epoch": 0.6815084052703316,
|
||
|
|
"grad_norm": 1.21875,
|
||
|
|
"learning_rate": 0.0003745,
|
||
|
|
"loss": 6.3611,
|
||
|
|
"mean_token_accuracy": 0.12048957645893096,
|
||
|
|
"num_tokens": 1546673.0,
|
||
|
|
"step": 750
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.47542667388916,
|
||
|
|
"epoch": 0.6860517946388005,
|
||
|
|
"grad_norm": 1.171875,
|
||
|
|
"learning_rate": 0.000377,
|
||
|
|
"loss": 6.3815,
|
||
|
|
"mean_token_accuracy": 0.12386295571923256,
|
||
|
|
"num_tokens": 1556793.0,
|
||
|
|
"step": 755
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.547279596328735,
|
||
|
|
"epoch": 0.6905951840072694,
|
||
|
|
"grad_norm": 1.2890625,
|
||
|
|
"learning_rate": 0.0003795,
|
||
|
|
"loss": 6.4267,
|
||
|
|
"mean_token_accuracy": 0.12142022401094436,
|
||
|
|
"num_tokens": 1566450.0,
|
||
|
|
"step": 760
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.490754413604736,
|
||
|
|
"epoch": 0.6951385733757383,
|
||
|
|
"grad_norm": 1.171875,
|
||
|
|
"learning_rate": 0.000382,
|
||
|
|
"loss": 6.4515,
|
||
|
|
"mean_token_accuracy": 0.12024893313646316,
|
||
|
|
"num_tokens": 1576353.0,
|
||
|
|
"step": 765
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.525695848464966,
|
||
|
|
"epoch": 0.6996819627442071,
|
||
|
|
"grad_norm": 1.0625,
|
||
|
|
"learning_rate": 0.0003845,
|
||
|
|
"loss": 6.3332,
|
||
|
|
"mean_token_accuracy": 0.12352794036269188,
|
||
|
|
"num_tokens": 1586318.0,
|
||
|
|
"step": 770
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.536564779281616,
|
||
|
|
"epoch": 0.704225352112676,
|
||
|
|
"grad_norm": 1.1953125,
|
||
|
|
"learning_rate": 0.00038700000000000003,
|
||
|
|
"loss": 6.4345,
|
||
|
|
"mean_token_accuracy": 0.11370632126927376,
|
||
|
|
"num_tokens": 1596839.0,
|
||
|
|
"step": 775
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.4864342212677,
|
||
|
|
"epoch": 0.7087687414811449,
|
||
|
|
"grad_norm": 1.234375,
|
||
|
|
"learning_rate": 0.00038950000000000003,
|
||
|
|
"loss": 6.4529,
|
||
|
|
"mean_token_accuracy": 0.12249588519334793,
|
||
|
|
"num_tokens": 1606843.0,
|
||
|
|
"step": 780
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.363466262817383,
|
||
|
|
"epoch": 0.7133121308496138,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.00039200000000000004,
|
||
|
|
"loss": 6.4148,
|
||
|
|
"mean_token_accuracy": 0.11689037606120109,
|
||
|
|
"num_tokens": 1617048.0,
|
||
|
|
"step": 785
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.529700660705567,
|
||
|
|
"epoch": 0.7178555202180827,
|
||
|
|
"grad_norm": 1.078125,
|
||
|
|
"learning_rate": 0.00039450000000000005,
|
||
|
|
"loss": 6.3213,
|
||
|
|
"mean_token_accuracy": 0.12030550986528396,
|
||
|
|
"num_tokens": 1627472.0,
|
||
|
|
"step": 790
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.547754430770874,
|
||
|
|
"epoch": 0.7223989095865516,
|
||
|
|
"grad_norm": 1.1171875,
|
||
|
|
"learning_rate": 0.00039700000000000005,
|
||
|
|
"loss": 6.429,
|
||
|
|
"mean_token_accuracy": 0.11561316847801209,
|
||
|
|
"num_tokens": 1637716.0,
|
||
|
|
"step": 795
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.427017641067505,
|
||
|
|
"epoch": 0.7269422989550205,
|
||
|
|
"grad_norm": 1.140625,
|
||
|
|
"learning_rate": 0.0003995,
|
||
|
|
"loss": 6.4385,
|
||
|
|
"mean_token_accuracy": 0.11526587828993798,
|
||
|
|
"num_tokens": 1648119.0,
|
||
|
|
"step": 800
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.5540087699890135,
|
||
|
|
"epoch": 0.7314856883234894,
|
||
|
|
"grad_norm": 1.140625,
|
||
|
|
"learning_rate": 0.000402,
|
||
|
|
"loss": 6.3766,
|
||
|
|
"mean_token_accuracy": 0.1245071604847908,
|
||
|
|
"num_tokens": 1658214.0,
|
||
|
|
"step": 805
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.3835773944854735,
|
||
|
|
"epoch": 0.7360290776919582,
|
||
|
|
"grad_norm": 1.0625,
|
||
|
|
"learning_rate": 0.0004045,
|
||
|
|
"loss": 6.3437,
|
||
|
|
"mean_token_accuracy": 0.12322835624217987,
|
||
|
|
"num_tokens": 1668725.0,
|
||
|
|
"step": 810
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.435897397994995,
|
||
|
|
"epoch": 0.7405724670604271,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.00040699999999999997,
|
||
|
|
"loss": 6.4166,
|
||
|
|
"mean_token_accuracy": 0.12298030406236649,
|
||
|
|
"num_tokens": 1678891.0,
|
||
|
|
"step": 815
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.519479846954345,
|
||
|
|
"epoch": 0.745115856428896,
|
||
|
|
"grad_norm": 1.140625,
|
||
|
|
"learning_rate": 0.0004095,
|
||
|
|
"loss": 6.3176,
|
||
|
|
"mean_token_accuracy": 0.12078626230359077,
|
||
|
|
"num_tokens": 1688749.0,
|
||
|
|
"step": 820
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.44858684539795,
|
||
|
|
"epoch": 0.7496592457973649,
|
||
|
|
"grad_norm": 1.109375,
|
||
|
|
"learning_rate": 0.000412,
|
||
|
|
"loss": 6.4246,
|
||
|
|
"mean_token_accuracy": 0.11904875412583352,
|
||
|
|
"num_tokens": 1699166.0,
|
||
|
|
"step": 825
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.509427452087403,
|
||
|
|
"epoch": 0.7542026351658337,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.0004145,
|
||
|
|
"loss": 6.348,
|
||
|
|
"mean_token_accuracy": 0.12165467068552971,
|
||
|
|
"num_tokens": 1710690.0,
|
||
|
|
"step": 830
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.475676584243774,
|
||
|
|
"epoch": 0.7587460245343026,
|
||
|
|
"grad_norm": 1.1640625,
|
||
|
|
"learning_rate": 0.000417,
|
||
|
|
"loss": 6.4505,
|
||
|
|
"mean_token_accuracy": 0.11575704216957092,
|
||
|
|
"num_tokens": 1721169.0,
|
||
|
|
"step": 835
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.419601774215698,
|
||
|
|
"epoch": 0.7632894139027715,
|
||
|
|
"grad_norm": 1.171875,
|
||
|
|
"learning_rate": 0.0004195,
|
||
|
|
"loss": 6.3168,
|
||
|
|
"mean_token_accuracy": 0.11946589276194572,
|
||
|
|
"num_tokens": 1731523.0,
|
||
|
|
"step": 840
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.477061462402344,
|
||
|
|
"epoch": 0.7678328032712404,
|
||
|
|
"grad_norm": 1.0546875,
|
||
|
|
"learning_rate": 0.000422,
|
||
|
|
"loss": 6.3088,
|
||
|
|
"mean_token_accuracy": 0.11968929320573807,
|
||
|
|
"num_tokens": 1742316.0,
|
||
|
|
"step": 845
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.44489312171936,
|
||
|
|
"epoch": 0.7723761926397092,
|
||
|
|
"grad_norm": 1.15625,
|
||
|
|
"learning_rate": 0.0004245,
|
||
|
|
"loss": 6.4524,
|
||
|
|
"mean_token_accuracy": 0.12095453590154648,
|
||
|
|
"num_tokens": 1753424.0,
|
||
|
|
"step": 850
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.338519668579101,
|
||
|
|
"epoch": 0.7769195820081781,
|
||
|
|
"grad_norm": 1.2734375,
|
||
|
|
"learning_rate": 0.000427,
|
||
|
|
"loss": 6.2815,
|
||
|
|
"mean_token_accuracy": 0.12474420070648193,
|
||
|
|
"num_tokens": 1762814.0,
|
||
|
|
"step": 855
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.428976821899414,
|
||
|
|
"epoch": 0.781462971376647,
|
||
|
|
"grad_norm": 1.1171875,
|
||
|
|
"learning_rate": 0.0004295,
|
||
|
|
"loss": 6.4394,
|
||
|
|
"mean_token_accuracy": 0.11995334699749946,
|
||
|
|
"num_tokens": 1773096.0,
|
||
|
|
"step": 860
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.479230260848999,
|
||
|
|
"epoch": 0.7860063607451159,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.000432,
|
||
|
|
"loss": 6.3472,
|
||
|
|
"mean_token_accuracy": 0.12182644307613373,
|
||
|
|
"num_tokens": 1783499.0,
|
||
|
|
"step": 865
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.607985353469848,
|
||
|
|
"epoch": 0.7905497501135847,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.0004345,
|
||
|
|
"loss": 6.5456,
|
||
|
|
"mean_token_accuracy": 0.1136684074997902,
|
||
|
|
"num_tokens": 1794107.0,
|
||
|
|
"step": 870
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.4030835151672365,
|
||
|
|
"epoch": 0.7950931394820536,
|
||
|
|
"grad_norm": 1.2578125,
|
||
|
|
"learning_rate": 0.000437,
|
||
|
|
"loss": 6.4216,
|
||
|
|
"mean_token_accuracy": 0.1149469256401062,
|
||
|
|
"num_tokens": 1805151.0,
|
||
|
|
"step": 875
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.488826656341553,
|
||
|
|
"epoch": 0.7996365288505225,
|
||
|
|
"grad_norm": 1.15625,
|
||
|
|
"learning_rate": 0.0004395,
|
||
|
|
"loss": 6.391,
|
||
|
|
"mean_token_accuracy": 0.11763054057955742,
|
||
|
|
"num_tokens": 1815205.0,
|
||
|
|
"step": 880
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.399917316436768,
|
||
|
|
"epoch": 0.8041799182189914,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.000442,
|
||
|
|
"loss": 6.3587,
|
||
|
|
"mean_token_accuracy": 0.1239665150642395,
|
||
|
|
"num_tokens": 1825301.0,
|
||
|
|
"step": 885
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.424862003326416,
|
||
|
|
"epoch": 0.8087233075874602,
|
||
|
|
"grad_norm": 1.1171875,
|
||
|
|
"learning_rate": 0.0004445,
|
||
|
|
"loss": 6.379,
|
||
|
|
"mean_token_accuracy": 0.12152353450655937,
|
||
|
|
"num_tokens": 1835634.0,
|
||
|
|
"step": 890
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.472187471389771,
|
||
|
|
"epoch": 0.8132666969559291,
|
||
|
|
"grad_norm": 1.0078125,
|
||
|
|
"learning_rate": 0.000447,
|
||
|
|
"loss": 6.3892,
|
||
|
|
"mean_token_accuracy": 0.11498059630393982,
|
||
|
|
"num_tokens": 1846855.0,
|
||
|
|
"step": 895
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.382741403579712,
|
||
|
|
"epoch": 0.817810086324398,
|
||
|
|
"grad_norm": 1.1171875,
|
||
|
|
"learning_rate": 0.00044950000000000003,
|
||
|
|
"loss": 6.3587,
|
||
|
|
"mean_token_accuracy": 0.12044938951730728,
|
||
|
|
"num_tokens": 1857747.0,
|
||
|
|
"step": 900
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.446867799758911,
|
||
|
|
"epoch": 0.8223534756928669,
|
||
|
|
"grad_norm": 1.15625,
|
||
|
|
"learning_rate": 0.00045200000000000004,
|
||
|
|
"loss": 6.4105,
|
||
|
|
"mean_token_accuracy": 0.12059052139520646,
|
||
|
|
"num_tokens": 1868098.0,
|
||
|
|
"step": 905
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.350548887252808,
|
||
|
|
"epoch": 0.8268968650613358,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.00045450000000000004,
|
||
|
|
"loss": 6.3093,
|
||
|
|
"mean_token_accuracy": 0.12493439465761184,
|
||
|
|
"num_tokens": 1879682.0,
|
||
|
|
"step": 910
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.432272911071777,
|
||
|
|
"epoch": 0.8314402544298046,
|
||
|
|
"grad_norm": 1.1171875,
|
||
|
|
"learning_rate": 0.00045700000000000005,
|
||
|
|
"loss": 6.3316,
|
||
|
|
"mean_token_accuracy": 0.12454040497541427,
|
||
|
|
"num_tokens": 1890605.0,
|
||
|
|
"step": 915
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.39534969329834,
|
||
|
|
"epoch": 0.8359836437982735,
|
||
|
|
"grad_norm": 1.15625,
|
||
|
|
"learning_rate": 0.00045950000000000006,
|
||
|
|
"loss": 6.3699,
|
||
|
|
"mean_token_accuracy": 0.12763101756572723,
|
||
|
|
"num_tokens": 1900861.0,
|
||
|
|
"step": 920
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.398876667022705,
|
||
|
|
"epoch": 0.8405270331667424,
|
||
|
|
"grad_norm": 1.28125,
|
||
|
|
"learning_rate": 0.000462,
|
||
|
|
"loss": 6.3464,
|
||
|
|
"mean_token_accuracy": 0.12193151786923409,
|
||
|
|
"num_tokens": 1910867.0,
|
||
|
|
"step": 925
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.434603929519653,
|
||
|
|
"epoch": 0.8450704225352113,
|
||
|
|
"grad_norm": 1.078125,
|
||
|
|
"learning_rate": 0.0004645,
|
||
|
|
"loss": 6.3612,
|
||
|
|
"mean_token_accuracy": 0.11605243608355523,
|
||
|
|
"num_tokens": 1921424.0,
|
||
|
|
"step": 930
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.368513393402099,
|
||
|
|
"epoch": 0.8496138119036801,
|
||
|
|
"grad_norm": 1.1484375,
|
||
|
|
"learning_rate": 0.000467,
|
||
|
|
"loss": 6.3433,
|
||
|
|
"mean_token_accuracy": 0.1275160454213619,
|
||
|
|
"num_tokens": 1930784.0,
|
||
|
|
"step": 935
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.395671701431274,
|
||
|
|
"epoch": 0.854157201272149,
|
||
|
|
"grad_norm": 1.0859375,
|
||
|
|
"learning_rate": 0.0004695,
|
||
|
|
"loss": 6.3324,
|
||
|
|
"mean_token_accuracy": 0.12198550030589103,
|
||
|
|
"num_tokens": 1940325.0,
|
||
|
|
"step": 940
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.335153245925904,
|
||
|
|
"epoch": 0.8587005906406179,
|
||
|
|
"grad_norm": 1.171875,
|
||
|
|
"learning_rate": 0.000472,
|
||
|
|
"loss": 6.3475,
|
||
|
|
"mean_token_accuracy": 0.12423227652907372,
|
||
|
|
"num_tokens": 1951799.0,
|
||
|
|
"step": 945
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.4373150825500485,
|
||
|
|
"epoch": 0.8632439800090868,
|
||
|
|
"grad_norm": 1.1015625,
|
||
|
|
"learning_rate": 0.0004745,
|
||
|
|
"loss": 6.3262,
|
||
|
|
"mean_token_accuracy": 0.11780767813324929,
|
||
|
|
"num_tokens": 1962311.0,
|
||
|
|
"step": 950
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.351272106170654,
|
||
|
|
"epoch": 0.8677873693775556,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.000477,
|
||
|
|
"loss": 6.338,
|
||
|
|
"mean_token_accuracy": 0.12228847667574883,
|
||
|
|
"num_tokens": 1974128.0,
|
||
|
|
"step": 955
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.251103639602661,
|
||
|
|
"epoch": 0.8723307587460245,
|
||
|
|
"grad_norm": 1.125,
|
||
|
|
"learning_rate": 0.0004795,
|
||
|
|
"loss": 6.2644,
|
||
|
|
"mean_token_accuracy": 0.12811544090509414,
|
||
|
|
"num_tokens": 1983765.0,
|
||
|
|
"step": 960
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.386243391036987,
|
||
|
|
"epoch": 0.8768741481144934,
|
||
|
|
"grad_norm": 1.140625,
|
||
|
|
"learning_rate": 0.000482,
|
||
|
|
"loss": 6.3339,
|
||
|
|
"mean_token_accuracy": 0.1216882549226284,
|
||
|
|
"num_tokens": 1994045.0,
|
||
|
|
"step": 965
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.403064489364624,
|
||
|
|
"epoch": 0.8814175374829623,
|
||
|
|
"grad_norm": 0.9453125,
|
||
|
|
"learning_rate": 0.0004845,
|
||
|
|
"loss": 6.4084,
|
||
|
|
"mean_token_accuracy": 0.11930646523833274,
|
||
|
|
"num_tokens": 2005353.0,
|
||
|
|
"step": 970
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.219151544570923,
|
||
|
|
"epoch": 0.8859609268514311,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.000487,
|
||
|
|
"loss": 6.2239,
|
||
|
|
"mean_token_accuracy": 0.12836714312434197,
|
||
|
|
"num_tokens": 2015808.0,
|
||
|
|
"step": 975
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.362400388717651,
|
||
|
|
"epoch": 0.8905043162199,
|
||
|
|
"grad_norm": 1.078125,
|
||
|
|
"learning_rate": 0.0004895,
|
||
|
|
"loss": 6.2823,
|
||
|
|
"mean_token_accuracy": 0.1286115452647209,
|
||
|
|
"num_tokens": 2025824.0,
|
||
|
|
"step": 980
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.220054244995117,
|
||
|
|
"epoch": 0.8950477055883689,
|
||
|
|
"grad_norm": 0.96875,
|
||
|
|
"learning_rate": 0.000492,
|
||
|
|
"loss": 6.2977,
|
||
|
|
"mean_token_accuracy": 0.1320819690823555,
|
||
|
|
"num_tokens": 2036924.0,
|
||
|
|
"step": 985
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.383143568038941,
|
||
|
|
"epoch": 0.8995910949568378,
|
||
|
|
"grad_norm": 1.0703125,
|
||
|
|
"learning_rate": 0.0004945,
|
||
|
|
"loss": 6.3253,
|
||
|
|
"mean_token_accuracy": 0.12373943105340005,
|
||
|
|
"num_tokens": 2047302.0,
|
||
|
|
"step": 990
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.269778537750244,
|
||
|
|
"epoch": 0.9041344843253066,
|
||
|
|
"grad_norm": 1.15625,
|
||
|
|
"learning_rate": 0.000497,
|
||
|
|
"loss": 6.3067,
|
||
|
|
"mean_token_accuracy": 0.12240820974111558,
|
||
|
|
"num_tokens": 2057972.0,
|
||
|
|
"step": 995
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.2414275169372555,
|
||
|
|
"epoch": 0.9086778736937755,
|
||
|
|
"grad_norm": 1.1171875,
|
||
|
|
"learning_rate": 0.0004995,
|
||
|
|
"loss": 6.154,
|
||
|
|
"mean_token_accuracy": 0.12995185926556588,
|
||
|
|
"num_tokens": 2067916.0,
|
||
|
|
"step": 1000
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.9086778736937755,
|
||
|
|
"eval_entropy": 6.18265976351361,
|
||
|
|
"eval_loss": 6.422311782836914,
|
||
|
|
"eval_mean_token_accuracy": 0.12340358548559421,
|
||
|
|
"eval_num_tokens": 2067916.0,
|
||
|
|
"eval_runtime": 2.5935,
|
||
|
|
"eval_samples_per_second": 1324.482,
|
||
|
|
"eval_steps_per_second": 165.801,
|
||
|
|
"step": 1000
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.2358527183532715,
|
||
|
|
"epoch": 0.9132212630622444,
|
||
|
|
"grad_norm": 1.3671875,
|
||
|
|
"learning_rate": 0.0004999998223471442,
|
||
|
|
"loss": 6.3354,
|
||
|
|
"mean_token_accuracy": 0.1269114390015602,
|
||
|
|
"num_tokens": 2079119.0,
|
||
|
|
"step": 1005
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.302850770950317,
|
||
|
|
"epoch": 0.9177646524307133,
|
||
|
|
"grad_norm": 1.0703125,
|
||
|
|
"learning_rate": 0.0004999991006328981,
|
||
|
|
"loss": 6.224,
|
||
|
|
"mean_token_accuracy": 0.12514718621969223,
|
||
|
|
"num_tokens": 2090080.0,
|
||
|
|
"step": 1010
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.266329765319824,
|
||
|
|
"epoch": 0.9223080417991822,
|
||
|
|
"grad_norm": 1.2109375,
|
||
|
|
"learning_rate": 0.0004999978237557377,
|
||
|
|
"loss": 6.2681,
|
||
|
|
"mean_token_accuracy": 0.12983603328466414,
|
||
|
|
"num_tokens": 2100541.0,
|
||
|
|
"step": 1015
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.328331470489502,
|
||
|
|
"epoch": 0.9268514311676511,
|
||
|
|
"grad_norm": 1.0078125,
|
||
|
|
"learning_rate": 0.0004999959917188137,
|
||
|
|
"loss": 6.2368,
|
||
|
|
"mean_token_accuracy": 0.12401319071650505,
|
||
|
|
"num_tokens": 2111213.0,
|
||
|
|
"step": 1020
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.298262405395508,
|
||
|
|
"epoch": 0.93139482053612,
|
||
|
|
"grad_norm": 1.2109375,
|
||
|
|
"learning_rate": 0.0004999936045266462,
|
||
|
|
"loss": 6.3306,
|
||
|
|
"mean_token_accuracy": 0.12413369193673134,
|
||
|
|
"num_tokens": 2121714.0,
|
||
|
|
"step": 1025
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.274141407012939,
|
||
|
|
"epoch": 0.9359382099045889,
|
||
|
|
"grad_norm": 1.234375,
|
||
|
|
"learning_rate": 0.0004999906621851255,
|
||
|
|
"loss": 6.2165,
|
||
|
|
"mean_token_accuracy": 0.12441339045763015,
|
||
|
|
"num_tokens": 2131226.0,
|
||
|
|
"step": 1030
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.270669841766358,
|
||
|
|
"epoch": 0.9404815992730577,
|
||
|
|
"grad_norm": 0.98828125,
|
||
|
|
"learning_rate": 0.0004999871647015115,
|
||
|
|
"loss": 6.2877,
|
||
|
|
"mean_token_accuracy": 0.11828686073422431,
|
||
|
|
"num_tokens": 2143179.0,
|
||
|
|
"step": 1035
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.220635652542114,
|
||
|
|
"epoch": 0.9450249886415266,
|
||
|
|
"grad_norm": 1.1171875,
|
||
|
|
"learning_rate": 0.0004999831120844339,
|
||
|
|
"loss": 6.2705,
|
||
|
|
"mean_token_accuracy": 0.12587330713868142,
|
||
|
|
"num_tokens": 2153646.0,
|
||
|
|
"step": 1040
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.198286867141723,
|
||
|
|
"epoch": 0.9495683780099955,
|
||
|
|
"grad_norm": 1.109375,
|
||
|
|
"learning_rate": 0.0004999785043438922,
|
||
|
|
"loss": 6.2264,
|
||
|
|
"mean_token_accuracy": 0.12276902943849563,
|
||
|
|
"num_tokens": 2163267.0,
|
||
|
|
"step": 1045
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.2652397632598875,
|
||
|
|
"epoch": 0.9541117673784644,
|
||
|
|
"grad_norm": 1.140625,
|
||
|
|
"learning_rate": 0.0004999733414912555,
|
||
|
|
"loss": 6.1411,
|
||
|
|
"mean_token_accuracy": 0.1308826483786106,
|
||
|
|
"num_tokens": 2173282.0,
|
||
|
|
"step": 1050
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.211602592468262,
|
||
|
|
"epoch": 0.9586551567469332,
|
||
|
|
"grad_norm": 1.0,
|
||
|
|
"learning_rate": 0.0004999676235392626,
|
||
|
|
"loss": 6.2276,
|
||
|
|
"mean_token_accuracy": 0.12286282628774643,
|
||
|
|
"num_tokens": 2184202.0,
|
||
|
|
"step": 1055
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.3284876346588135,
|
||
|
|
"epoch": 0.9631985461154021,
|
||
|
|
"grad_norm": 1.0546875,
|
||
|
|
"learning_rate": 0.0004999613505020219,
|
||
|
|
"loss": 6.2028,
|
||
|
|
"mean_token_accuracy": 0.12903301566839218,
|
||
|
|
"num_tokens": 2194342.0,
|
||
|
|
"step": 1060
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.160139703750611,
|
||
|
|
"epoch": 0.967741935483871,
|
||
|
|
"grad_norm": 1.1484375,
|
||
|
|
"learning_rate": 0.0004999545223950116,
|
||
|
|
"loss": 6.198,
|
||
|
|
"mean_token_accuracy": 0.1318102538585663,
|
||
|
|
"num_tokens": 2204817.0,
|
||
|
|
"step": 1065
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.2580382347106935,
|
||
|
|
"epoch": 0.9722853248523399,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.0004999471392350795,
|
||
|
|
"loss": 6.2727,
|
||
|
|
"mean_token_accuracy": 0.13099218532443047,
|
||
|
|
"num_tokens": 2215281.0,
|
||
|
|
"step": 1070
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.3193916320800785,
|
||
|
|
"epoch": 0.9768287142208087,
|
||
|
|
"grad_norm": 1.2265625,
|
||
|
|
"learning_rate": 0.0004999392010404426,
|
||
|
|
"loss": 6.2859,
|
||
|
|
"mean_token_accuracy": 0.1294151432812214,
|
||
|
|
"num_tokens": 2225784.0,
|
||
|
|
"step": 1075
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.138168430328369,
|
||
|
|
"epoch": 0.9813721035892776,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.0004999307078306876,
|
||
|
|
"loss": 6.2205,
|
||
|
|
"mean_token_accuracy": 0.1334165170788765,
|
||
|
|
"num_tokens": 2235357.0,
|
||
|
|
"step": 1080
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.378276205062866,
|
||
|
|
"epoch": 0.9859154929577465,
|
||
|
|
"grad_norm": 1.125,
|
||
|
|
"learning_rate": 0.0004999216596267708,
|
||
|
|
"loss": 6.2359,
|
||
|
|
"mean_token_accuracy": 0.13057358041405678,
|
||
|
|
"num_tokens": 2246438.0,
|
||
|
|
"step": 1085
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.202377271652222,
|
||
|
|
"epoch": 0.9904588823262154,
|
||
|
|
"grad_norm": 1.125,
|
||
|
|
"learning_rate": 0.0004999120564510177,
|
||
|
|
"loss": 6.2261,
|
||
|
|
"mean_token_accuracy": 0.12415477558970452,
|
||
|
|
"num_tokens": 2257528.0,
|
||
|
|
"step": 1090
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.155335521697998,
|
||
|
|
"epoch": 0.9950022716946842,
|
||
|
|
"grad_norm": 1.125,
|
||
|
|
"learning_rate": 0.000499901898327123,
|
||
|
|
"loss": 6.2498,
|
||
|
|
"mean_token_accuracy": 0.13259016051888467,
|
||
|
|
"num_tokens": 2267572.0,
|
||
|
|
"step": 1095
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.226053190231323,
|
||
|
|
"epoch": 0.9995456610631531,
|
||
|
|
"grad_norm": 0.921875,
|
||
|
|
"learning_rate": 0.0004998911852801512,
|
||
|
|
"loss": 6.1789,
|
||
|
|
"mean_token_accuracy": 0.13369767963886262,
|
||
|
|
"num_tokens": 2278520.0,
|
||
|
|
"step": 1100
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.2539831267462835,
|
||
|
|
"epoch": 1.003634711494775,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.0004998799173365355,
|
||
|
|
"loss": 6.0826,
|
||
|
|
"mean_token_accuracy": 0.1368540914522277,
|
||
|
|
"num_tokens": 2286991.0,
|
||
|
|
"step": 1105
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.170029067993164,
|
||
|
|
"epoch": 1.008178100863244,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.0004998680945240783,
|
||
|
|
"loss": 6.1303,
|
||
|
|
"mean_token_accuracy": 0.12599217817187308,
|
||
|
|
"num_tokens": 2297857.0,
|
||
|
|
"step": 1110
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.261499547958374,
|
||
|
|
"epoch": 1.0127214902317128,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.0004998557168719513,
|
||
|
|
"loss": 6.1702,
|
||
|
|
"mean_token_accuracy": 0.13075068444013596,
|
||
|
|
"num_tokens": 2308621.0,
|
||
|
|
"step": 1115
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.14419322013855,
|
||
|
|
"epoch": 1.0172648796001817,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.0004998427844106954,
|
||
|
|
"loss": 5.9933,
|
||
|
|
"mean_token_accuracy": 0.14160198718309402,
|
||
|
|
"num_tokens": 2318654.0,
|
||
|
|
"step": 1120
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.1928181648254395,
|
||
|
|
"epoch": 1.0218082689686505,
|
||
|
|
"grad_norm": 1.1640625,
|
||
|
|
"learning_rate": 0.0004998292971722197,
|
||
|
|
"loss": 6.045,
|
||
|
|
"mean_token_accuracy": 0.1332675762474537,
|
||
|
|
"num_tokens": 2329064.0,
|
||
|
|
"step": 1125
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.150006675720215,
|
||
|
|
"epoch": 1.0263516583371195,
|
||
|
|
"grad_norm": 1.0546875,
|
||
|
|
"learning_rate": 0.000499815255189803,
|
||
|
|
"loss": 6.1098,
|
||
|
|
"mean_token_accuracy": 0.12820298597216606,
|
||
|
|
"num_tokens": 2339843.0,
|
||
|
|
"step": 1130
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.200477075576782,
|
||
|
|
"epoch": 1.0308950477055883,
|
||
|
|
"grad_norm": 1.1953125,
|
||
|
|
"learning_rate": 0.0004998006584980922,
|
||
|
|
"loss": 6.0436,
|
||
|
|
"mean_token_accuracy": 0.13033792674541472,
|
||
|
|
"num_tokens": 2350715.0,
|
||
|
|
"step": 1135
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.130117893218994,
|
||
|
|
"epoch": 1.0354384370740572,
|
||
|
|
"grad_norm": 1.0703125,
|
||
|
|
"learning_rate": 0.0004997855071331034,
|
||
|
|
"loss": 6.0068,
|
||
|
|
"mean_token_accuracy": 0.13114059641957282,
|
||
|
|
"num_tokens": 2360635.0,
|
||
|
|
"step": 1140
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.180344820022583,
|
||
|
|
"epoch": 1.039981826442526,
|
||
|
|
"grad_norm": 1.1015625,
|
||
|
|
"learning_rate": 0.0004997698011322211,
|
||
|
|
"loss": 6.0305,
|
||
|
|
"mean_token_accuracy": 0.13138258829712868,
|
||
|
|
"num_tokens": 2370627.0,
|
||
|
|
"step": 1145
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.147628831863403,
|
||
|
|
"epoch": 1.044525215810995,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.000499753540534198,
|
||
|
|
"loss": 6.0424,
|
||
|
|
"mean_token_accuracy": 0.13276968747377396,
|
||
|
|
"num_tokens": 2381790.0,
|
||
|
|
"step": 1150
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.058908224105835,
|
||
|
|
"epoch": 1.049068605179464,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.000499736725379156,
|
||
|
|
"loss": 5.9905,
|
||
|
|
"mean_token_accuracy": 0.13258678764104842,
|
||
|
|
"num_tokens": 2392685.0,
|
||
|
|
"step": 1155
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.140621614456177,
|
||
|
|
"epoch": 1.0536119945479328,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.0004997193557085844,
|
||
|
|
"loss": 6.0486,
|
||
|
|
"mean_token_accuracy": 0.13231537640094757,
|
||
|
|
"num_tokens": 2403722.0,
|
||
|
|
"step": 1160
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.107622337341309,
|
||
|
|
"epoch": 1.0581553839164017,
|
||
|
|
"grad_norm": 0.94140625,
|
||
|
|
"learning_rate": 0.0004997014315653413,
|
||
|
|
"loss": 6.0933,
|
||
|
|
"mean_token_accuracy": 0.12645822986960412,
|
||
|
|
"num_tokens": 2415311.0,
|
||
|
|
"step": 1165
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.148067760467529,
|
||
|
|
"epoch": 1.0626987732848705,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.0004996829529936527,
|
||
|
|
"loss": 5.9773,
|
||
|
|
"mean_token_accuracy": 0.13930070772767067,
|
||
|
|
"num_tokens": 2425116.0,
|
||
|
|
"step": 1170
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.2148473262786865,
|
||
|
|
"epoch": 1.0672421626533395,
|
||
|
|
"grad_norm": 0.98046875,
|
||
|
|
"learning_rate": 0.0004996639200391126,
|
||
|
|
"loss": 6.1548,
|
||
|
|
"mean_token_accuracy": 0.1310862734913826,
|
||
|
|
"num_tokens": 2435916.0,
|
||
|
|
"step": 1175
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.043871068954468,
|
||
|
|
"epoch": 1.0717855520218083,
|
||
|
|
"grad_norm": 1.0703125,
|
||
|
|
"learning_rate": 0.0004996443327486831,
|
||
|
|
"loss": 6.0384,
|
||
|
|
"mean_token_accuracy": 0.12819197103381158,
|
||
|
|
"num_tokens": 2446920.0,
|
||
|
|
"step": 1180
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.161314392089844,
|
||
|
|
"epoch": 1.0763289413902772,
|
||
|
|
"grad_norm": 1.1015625,
|
||
|
|
"learning_rate": 0.0004996241911706937,
|
||
|
|
"loss": 5.9899,
|
||
|
|
"mean_token_accuracy": 0.1420701712369919,
|
||
|
|
"num_tokens": 2456367.0,
|
||
|
|
"step": 1185
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.064000463485717,
|
||
|
|
"epoch": 1.080872330758746,
|
||
|
|
"grad_norm": 1.0546875,
|
||
|
|
"learning_rate": 0.0004996034953548418,
|
||
|
|
"loss": 5.9537,
|
||
|
|
"mean_token_accuracy": 0.13507229685783387,
|
||
|
|
"num_tokens": 2466790.0,
|
||
|
|
"step": 1190
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.089735412597657,
|
||
|
|
"epoch": 1.085415720127215,
|
||
|
|
"grad_norm": 1.171875,
|
||
|
|
"learning_rate": 0.0004995822453521924,
|
||
|
|
"loss": 5.968,
|
||
|
|
"mean_token_accuracy": 0.1441962629556656,
|
||
|
|
"num_tokens": 2476419.0,
|
||
|
|
"step": 1195
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.057880926132202,
|
||
|
|
"epoch": 1.0899591094956838,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.0004995604412151776,
|
||
|
|
"loss": 6.1084,
|
||
|
|
"mean_token_accuracy": 0.13047450110316278,
|
||
|
|
"num_tokens": 2487295.0,
|
||
|
|
"step": 1200
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.063084745407105,
|
||
|
|
"epoch": 1.0945024988641527,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.000499538082997597,
|
||
|
|
"loss": 5.9996,
|
||
|
|
"mean_token_accuracy": 0.12964291498064995,
|
||
|
|
"num_tokens": 2497545.0,
|
||
|
|
"step": 1205
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.217773675918579,
|
||
|
|
"epoch": 1.0990458882326215,
|
||
|
|
"grad_norm": 1.0546875,
|
||
|
|
"learning_rate": 0.0004995151707546172,
|
||
|
|
"loss": 6.1494,
|
||
|
|
"mean_token_accuracy": 0.12842334657907487,
|
||
|
|
"num_tokens": 2507805.0,
|
||
|
|
"step": 1210
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.087493848800659,
|
||
|
|
"epoch": 1.1035892776010905,
|
||
|
|
"grad_norm": 0.9765625,
|
||
|
|
"learning_rate": 0.0004994917045427721,
|
||
|
|
"loss": 6.0238,
|
||
|
|
"mean_token_accuracy": 0.13358174711465837,
|
||
|
|
"num_tokens": 2518474.0,
|
||
|
|
"step": 1215
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.1921933650970455,
|
||
|
|
"epoch": 1.1081326669695593,
|
||
|
|
"grad_norm": 1.0859375,
|
||
|
|
"learning_rate": 0.0004994676844199621,
|
||
|
|
"loss": 6.047,
|
||
|
|
"mean_token_accuracy": 0.14280006289482117,
|
||
|
|
"num_tokens": 2528974.0,
|
||
|
|
"step": 1220
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.036006498336792,
|
||
|
|
"epoch": 1.1126760563380282,
|
||
|
|
"grad_norm": 0.953125,
|
||
|
|
"learning_rate": 0.0004994431104454543,
|
||
|
|
"loss": 6.0951,
|
||
|
|
"mean_token_accuracy": 0.12937285155057907,
|
||
|
|
"num_tokens": 2540675.0,
|
||
|
|
"step": 1225
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.117119979858399,
|
||
|
|
"epoch": 1.117219445706497,
|
||
|
|
"grad_norm": 1.1484375,
|
||
|
|
"learning_rate": 0.0004994179826798828,
|
||
|
|
"loss": 5.9689,
|
||
|
|
"mean_token_accuracy": 0.1407436214387417,
|
||
|
|
"num_tokens": 2551367.0,
|
||
|
|
"step": 1230
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.063678407669068,
|
||
|
|
"epoch": 1.121762835074966,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.0004993923011852477,
|
||
|
|
"loss": 6.062,
|
||
|
|
"mean_token_accuracy": 0.13190347701311111,
|
||
|
|
"num_tokens": 2562096.0,
|
||
|
|
"step": 1235
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.158404207229614,
|
||
|
|
"epoch": 1.1263062244434348,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.0004993660660249158,
|
||
|
|
"loss": 6.1277,
|
||
|
|
"mean_token_accuracy": 0.13364789113402367,
|
||
|
|
"num_tokens": 2572917.0,
|
||
|
|
"step": 1240
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.0960992813110355,
|
||
|
|
"epoch": 1.1308496138119037,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.0004993392772636194,
|
||
|
|
"loss": 5.9614,
|
||
|
|
"mean_token_accuracy": 0.1394283317029476,
|
||
|
|
"num_tokens": 2582971.0,
|
||
|
|
"step": 1245
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.16928243637085,
|
||
|
|
"epoch": 1.1353930031803725,
|
||
|
|
"grad_norm": 0.9140625,
|
||
|
|
"learning_rate": 0.0004993119349674573,
|
||
|
|
"loss": 6.1091,
|
||
|
|
"mean_token_accuracy": 0.13041222244501113,
|
||
|
|
"num_tokens": 2593186.0,
|
||
|
|
"step": 1250
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.133707523345947,
|
||
|
|
"epoch": 1.1399363925488415,
|
||
|
|
"grad_norm": 0.96484375,
|
||
|
|
"learning_rate": 0.0004992840392038938,
|
||
|
|
"loss": 6.0997,
|
||
|
|
"mean_token_accuracy": 0.13235297948122024,
|
||
|
|
"num_tokens": 2604359.0,
|
||
|
|
"step": 1255
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.136443281173706,
|
||
|
|
"epoch": 1.1444797819173103,
|
||
|
|
"grad_norm": 1.1328125,
|
||
|
|
"learning_rate": 0.000499255590041759,
|
||
|
|
"loss": 6.0249,
|
||
|
|
"mean_token_accuracy": 0.13984801024198532,
|
||
|
|
"num_tokens": 2614436.0,
|
||
|
|
"step": 1260
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.983046245574951,
|
||
|
|
"epoch": 1.1490231712857792,
|
||
|
|
"grad_norm": 1.1015625,
|
||
|
|
"learning_rate": 0.0004992265875512485,
|
||
|
|
"loss": 5.9837,
|
||
|
|
"mean_token_accuracy": 0.13748598098754883,
|
||
|
|
"num_tokens": 2624175.0,
|
||
|
|
"step": 1265
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.080909395217896,
|
||
|
|
"epoch": 1.153566560654248,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.0004991970318039228,
|
||
|
|
"loss": 6.0246,
|
||
|
|
"mean_token_accuracy": 0.13808856904506683,
|
||
|
|
"num_tokens": 2634898.0,
|
||
|
|
"step": 1270
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.203506231307983,
|
||
|
|
"epoch": 1.158109950022717,
|
||
|
|
"grad_norm": 1.078125,
|
||
|
|
"learning_rate": 0.0004991669228727078,
|
||
|
|
"loss": 6.0522,
|
||
|
|
"mean_token_accuracy": 0.13835761845111846,
|
||
|
|
"num_tokens": 2645590.0,
|
||
|
|
"step": 1275
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.1103081703186035,
|
||
|
|
"epoch": 1.1626533393911858,
|
||
|
|
"grad_norm": 1.1640625,
|
||
|
|
"learning_rate": 0.0004991362608318947,
|
||
|
|
"loss": 6.039,
|
||
|
|
"mean_token_accuracy": 0.13795397132635118,
|
||
|
|
"num_tokens": 2656115.0,
|
||
|
|
"step": 1280
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.081531190872193,
|
||
|
|
"epoch": 1.1671967287596547,
|
||
|
|
"grad_norm": 1.078125,
|
||
|
|
"learning_rate": 0.0004991050457571384,
|
||
|
|
"loss": 6.0248,
|
||
|
|
"mean_token_accuracy": 0.1361389346420765,
|
||
|
|
"num_tokens": 2666760.0,
|
||
|
|
"step": 1285
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.077518939971924,
|
||
|
|
"epoch": 1.1717401181281235,
|
||
|
|
"grad_norm": 1.0859375,
|
||
|
|
"learning_rate": 0.0004990732777254594,
|
||
|
|
"loss": 5.98,
|
||
|
|
"mean_token_accuracy": 0.13790025189518929,
|
||
|
|
"num_tokens": 2676763.0,
|
||
|
|
"step": 1290
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.0636731624603275,
|
||
|
|
"epoch": 1.1762835074965925,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.0004990409568152422,
|
||
|
|
"loss": 6.0108,
|
||
|
|
"mean_token_accuracy": 0.13075025081634523,
|
||
|
|
"num_tokens": 2686598.0,
|
||
|
|
"step": 1295
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.058450698852539,
|
||
|
|
"epoch": 1.1808268968650613,
|
||
|
|
"grad_norm": 1.078125,
|
||
|
|
"learning_rate": 0.0004990080831062352,
|
||
|
|
"loss": 5.9813,
|
||
|
|
"mean_token_accuracy": 0.13843700140714646,
|
||
|
|
"num_tokens": 2697767.0,
|
||
|
|
"step": 1300
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.048785066604614,
|
||
|
|
"epoch": 1.1853702862335302,
|
||
|
|
"grad_norm": 1.15625,
|
||
|
|
"learning_rate": 0.0004989746566795512,
|
||
|
|
"loss": 5.9743,
|
||
|
|
"mean_token_accuracy": 0.1362238995730877,
|
||
|
|
"num_tokens": 2707081.0,
|
||
|
|
"step": 1305
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.002673721313476,
|
||
|
|
"epoch": 1.189913675601999,
|
||
|
|
"grad_norm": 0.91796875,
|
||
|
|
"learning_rate": 0.0004989406776176665,
|
||
|
|
"loss": 6.0005,
|
||
|
|
"mean_token_accuracy": 0.1412185825407505,
|
||
|
|
"num_tokens": 2717312.0,
|
||
|
|
"step": 1310
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.1222405433654785,
|
||
|
|
"epoch": 1.194457064970468,
|
||
|
|
"grad_norm": 1.078125,
|
||
|
|
"learning_rate": 0.000498906146004421,
|
||
|
|
"loss": 6.0165,
|
||
|
|
"mean_token_accuracy": 0.1373762771487236,
|
||
|
|
"num_tokens": 2728108.0,
|
||
|
|
"step": 1315
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.153705739974976,
|
||
|
|
"epoch": 1.1990004543389368,
|
||
|
|
"grad_norm": 0.93359375,
|
||
|
|
"learning_rate": 0.0004988710619250181,
|
||
|
|
"loss": 6.2116,
|
||
|
|
"mean_token_accuracy": 0.1348584771156311,
|
||
|
|
"num_tokens": 2738860.0,
|
||
|
|
"step": 1320
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.08194637298584,
|
||
|
|
"epoch": 1.2035438437074057,
|
||
|
|
"grad_norm": 0.9921875,
|
||
|
|
"learning_rate": 0.0004988354254660244,
|
||
|
|
"loss": 6.0351,
|
||
|
|
"mean_token_accuracy": 0.14144043251872063,
|
||
|
|
"num_tokens": 2749786.0,
|
||
|
|
"step": 1325
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.067605495452881,
|
||
|
|
"epoch": 1.2080872330758745,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.0004987992367153691,
|
||
|
|
"loss": 5.9576,
|
||
|
|
"mean_token_accuracy": 0.1407739117741585,
|
||
|
|
"num_tokens": 2760018.0,
|
||
|
|
"step": 1330
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.014369344711303,
|
||
|
|
"epoch": 1.2126306224443435,
|
||
|
|
"grad_norm": 1.0625,
|
||
|
|
"learning_rate": 0.0004987624957623443,
|
||
|
|
"loss": 5.9924,
|
||
|
|
"mean_token_accuracy": 0.13832346946001053,
|
||
|
|
"num_tokens": 2770572.0,
|
||
|
|
"step": 1335
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.000287675857544,
|
||
|
|
"epoch": 1.2171740118128123,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.0004987252026976049,
|
||
|
|
"loss": 5.9557,
|
||
|
|
"mean_token_accuracy": 0.14493367075920105,
|
||
|
|
"num_tokens": 2780297.0,
|
||
|
|
"step": 1340
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.126511573791504,
|
||
|
|
"epoch": 1.2217174011812812,
|
||
|
|
"grad_norm": 1.1015625,
|
||
|
|
"learning_rate": 0.0004986873576131676,
|
||
|
|
"loss": 6.0754,
|
||
|
|
"mean_token_accuracy": 0.1383805565536022,
|
||
|
|
"num_tokens": 2790454.0,
|
||
|
|
"step": 1345
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.051705694198608,
|
||
|
|
"epoch": 1.22626079054975,
|
||
|
|
"grad_norm": 1.171875,
|
||
|
|
"learning_rate": 0.0004986489606024116,
|
||
|
|
"loss": 5.9269,
|
||
|
|
"mean_token_accuracy": 0.14142982065677642,
|
||
|
|
"num_tokens": 2800034.0,
|
||
|
|
"step": 1350
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.937855005264282,
|
||
|
|
"epoch": 1.230804179918219,
|
||
|
|
"grad_norm": 0.99609375,
|
||
|
|
"learning_rate": 0.0004986100117600776,
|
||
|
|
"loss": 5.9515,
|
||
|
|
"mean_token_accuracy": 0.14328320026397706,
|
||
|
|
"num_tokens": 2810157.0,
|
||
|
|
"step": 1355
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.0591309547424315,
|
||
|
|
"epoch": 1.235347569286688,
|
||
|
|
"grad_norm": 1.125,
|
||
|
|
"learning_rate": 0.000498570511182268,
|
||
|
|
"loss": 5.9721,
|
||
|
|
"mean_token_accuracy": 0.1326573297381401,
|
||
|
|
"num_tokens": 2819404.0,
|
||
|
|
"step": 1360
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.9855554580688475,
|
||
|
|
"epoch": 1.2398909586551567,
|
||
|
|
"grad_norm": 1.1640625,
|
||
|
|
"learning_rate": 0.0004985304589664465,
|
||
|
|
"loss": 5.912,
|
||
|
|
"mean_token_accuracy": 0.13907658755779267,
|
||
|
|
"num_tokens": 2829551.0,
|
||
|
|
"step": 1365
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.990193843841553,
|
||
|
|
"epoch": 1.2444343480236255,
|
||
|
|
"grad_norm": 1.15625,
|
||
|
|
"learning_rate": 0.0004984898552114381,
|
||
|
|
"loss": 5.9849,
|
||
|
|
"mean_token_accuracy": 0.1325812466442585,
|
||
|
|
"num_tokens": 2840381.0,
|
||
|
|
"step": 1370
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.0108177185058596,
|
||
|
|
"epoch": 1.2489777373920945,
|
||
|
|
"grad_norm": 1.140625,
|
||
|
|
"learning_rate": 0.0004984487000174283,
|
||
|
|
"loss": 5.9657,
|
||
|
|
"mean_token_accuracy": 0.14018113762140275,
|
||
|
|
"num_tokens": 2850279.0,
|
||
|
|
"step": 1375
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.081850671768189,
|
||
|
|
"epoch": 1.2535211267605635,
|
||
|
|
"grad_norm": 1.15625,
|
||
|
|
"learning_rate": 0.0004984069934859637,
|
||
|
|
"loss": 5.999,
|
||
|
|
"mean_token_accuracy": 0.1427960455417633,
|
||
|
|
"num_tokens": 2860209.0,
|
||
|
|
"step": 1380
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.986414766311645,
|
||
|
|
"epoch": 1.2580645161290323,
|
||
|
|
"grad_norm": 1.125,
|
||
|
|
"learning_rate": 0.0004983647357199509,
|
||
|
|
"loss": 6.0065,
|
||
|
|
"mean_token_accuracy": 0.1422063134610653,
|
||
|
|
"num_tokens": 2870932.0,
|
||
|
|
"step": 1385
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.154019975662232,
|
||
|
|
"epoch": 1.262607905497501,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.0004983219268236567,
|
||
|
|
"loss": 5.9905,
|
||
|
|
"mean_token_accuracy": 0.13413980305194856,
|
||
|
|
"num_tokens": 2881139.0,
|
||
|
|
"step": 1390
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.022779893875122,
|
||
|
|
"epoch": 1.26715129486597,
|
||
|
|
"grad_norm": 1.0859375,
|
||
|
|
"learning_rate": 0.0004982785669027079,
|
||
|
|
"loss": 5.9898,
|
||
|
|
"mean_token_accuracy": 0.13735412806272507,
|
||
|
|
"num_tokens": 2890774.0,
|
||
|
|
"step": 1395
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.014951515197754,
|
||
|
|
"epoch": 1.271694684234439,
|
||
|
|
"grad_norm": 1.109375,
|
||
|
|
"learning_rate": 0.0004982346560640907,
|
||
|
|
"loss": 5.9483,
|
||
|
|
"mean_token_accuracy": 0.14736960977315902,
|
||
|
|
"num_tokens": 2900259.0,
|
||
|
|
"step": 1400
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.024165916442871,
|
||
|
|
"epoch": 1.2762380736029078,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.0004981901944161507,
|
||
|
|
"loss": 5.954,
|
||
|
|
"mean_token_accuracy": 0.14006007090210915,
|
||
|
|
"num_tokens": 2911365.0,
|
||
|
|
"step": 1405
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.027864694595337,
|
||
|
|
"epoch": 1.2807814629713765,
|
||
|
|
"grad_norm": 1.15625,
|
||
|
|
"learning_rate": 0.0004981451820685928,
|
||
|
|
"loss": 5.9561,
|
||
|
|
"mean_token_accuracy": 0.13755545094609262,
|
||
|
|
"num_tokens": 2921189.0,
|
||
|
|
"step": 1410
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.897766399383545,
|
||
|
|
"epoch": 1.2853248523398455,
|
||
|
|
"grad_norm": 1.25,
|
||
|
|
"learning_rate": 0.0004980996191324802,
|
||
|
|
"loss": 5.9868,
|
||
|
|
"mean_token_accuracy": 0.1411122649908066,
|
||
|
|
"num_tokens": 2931271.0,
|
||
|
|
"step": 1415
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.041615962982178,
|
||
|
|
"epoch": 1.2898682417083145,
|
||
|
|
"grad_norm": 1.1328125,
|
||
|
|
"learning_rate": 0.0004980535057202351,
|
||
|
|
"loss": 5.9812,
|
||
|
|
"mean_token_accuracy": 0.13669976145029067,
|
||
|
|
"num_tokens": 2941557.0,
|
||
|
|
"step": 1420
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.959131717681885,
|
||
|
|
"epoch": 1.2944116310767833,
|
||
|
|
"grad_norm": 1.15625,
|
||
|
|
"learning_rate": 0.0004980068419456378,
|
||
|
|
"loss": 5.8968,
|
||
|
|
"mean_token_accuracy": 0.14948886036872863,
|
||
|
|
"num_tokens": 2951305.0,
|
||
|
|
"step": 1425
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.962688350677491,
|
||
|
|
"epoch": 1.2989550204452522,
|
||
|
|
"grad_norm": 1.109375,
|
||
|
|
"learning_rate": 0.0004979596279238265,
|
||
|
|
"loss": 5.9791,
|
||
|
|
"mean_token_accuracy": 0.14904043525457383,
|
||
|
|
"num_tokens": 2961948.0,
|
||
|
|
"step": 1430
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.03700361251831,
|
||
|
|
"epoch": 1.303498409813721,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.0004979118637712969,
|
||
|
|
"loss": 6.0435,
|
||
|
|
"mean_token_accuracy": 0.1346405990421772,
|
||
|
|
"num_tokens": 2973300.0,
|
||
|
|
"step": 1435
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.081942367553711,
|
||
|
|
"epoch": 1.30804179918219,
|
||
|
|
"grad_norm": 1.1015625,
|
||
|
|
"learning_rate": 0.0004978635496059025,
|
||
|
|
"loss": 5.9856,
|
||
|
|
"mean_token_accuracy": 0.13874733671545983,
|
||
|
|
"num_tokens": 2984114.0,
|
||
|
|
"step": 1440
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.880176210403443,
|
||
|
|
"epoch": 1.3125851885506588,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.0004978146855468537,
|
||
|
|
"loss": 5.8527,
|
||
|
|
"mean_token_accuracy": 0.1486996442079544,
|
||
|
|
"num_tokens": 2993940.0,
|
||
|
|
"step": 1445
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.036293983459473,
|
||
|
|
"epoch": 1.3171285779191277,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.0004977652717147177,
|
||
|
|
"loss": 5.9607,
|
||
|
|
"mean_token_accuracy": 0.1445149928331375,
|
||
|
|
"num_tokens": 3004093.0,
|
||
|
|
"step": 1450
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.859427356719971,
|
||
|
|
"epoch": 1.3216719672875965,
|
||
|
|
"grad_norm": 1.2109375,
|
||
|
|
"learning_rate": 0.0004977153082314182,
|
||
|
|
"loss": 5.894,
|
||
|
|
"mean_token_accuracy": 0.14320220649242402,
|
||
|
|
"num_tokens": 3013537.0,
|
||
|
|
"step": 1455
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.090070915222168,
|
||
|
|
"epoch": 1.3262153566560655,
|
||
|
|
"grad_norm": 1.0859375,
|
||
|
|
"learning_rate": 0.000497664795220235,
|
||
|
|
"loss": 5.8986,
|
||
|
|
"mean_token_accuracy": 0.14571946561336518,
|
||
|
|
"num_tokens": 3023502.0,
|
||
|
|
"step": 1460
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.919493579864502,
|
||
|
|
"epoch": 1.3307587460245343,
|
||
|
|
"grad_norm": 1.1015625,
|
||
|
|
"learning_rate": 0.0004976137328058042,
|
||
|
|
"loss": 5.9456,
|
||
|
|
"mean_token_accuracy": 0.13945504799485206,
|
||
|
|
"num_tokens": 3033910.0,
|
||
|
|
"step": 1465
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.9833661079406735,
|
||
|
|
"epoch": 1.3353021353930032,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.000497562121114117,
|
||
|
|
"loss": 5.9951,
|
||
|
|
"mean_token_accuracy": 0.14348382130265236,
|
||
|
|
"num_tokens": 3043500.0,
|
||
|
|
"step": 1470
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.971828985214233,
|
||
|
|
"epoch": 1.339845524761472,
|
||
|
|
"grad_norm": 1.125,
|
||
|
|
"learning_rate": 0.0004975099602725202,
|
||
|
|
"loss": 5.9641,
|
||
|
|
"mean_token_accuracy": 0.14203015938401223,
|
||
|
|
"num_tokens": 3054776.0,
|
||
|
|
"step": 1475
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.034963607788086,
|
||
|
|
"epoch": 1.344388914129941,
|
||
|
|
"grad_norm": 1.1328125,
|
||
|
|
"learning_rate": 0.0004974572504097154,
|
||
|
|
"loss": 5.9249,
|
||
|
|
"mean_token_accuracy": 0.14127751886844636,
|
||
|
|
"num_tokens": 3065403.0,
|
||
|
|
"step": 1480
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.924037456512451,
|
||
|
|
"epoch": 1.3489323034984098,
|
||
|
|
"grad_norm": 1.1484375,
|
||
|
|
"learning_rate": 0.0004974039916557591,
|
||
|
|
"loss": 5.9545,
|
||
|
|
"mean_token_accuracy": 0.14617739617824554,
|
||
|
|
"num_tokens": 3074661.0,
|
||
|
|
"step": 1485
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.930827283859253,
|
||
|
|
"epoch": 1.3534756928668787,
|
||
|
|
"grad_norm": 1.171875,
|
||
|
|
"learning_rate": 0.000497350184142062,
|
||
|
|
"loss": 5.9193,
|
||
|
|
"mean_token_accuracy": 0.13931230902671815,
|
||
|
|
"num_tokens": 3085319.0,
|
||
|
|
"step": 1490
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.930323791503906,
|
||
|
|
"epoch": 1.3580190822353475,
|
||
|
|
"grad_norm": 0.984375,
|
||
|
|
"learning_rate": 0.0004972958280013886,
|
||
|
|
"loss": 5.9068,
|
||
|
|
"mean_token_accuracy": 0.1437447987496853,
|
||
|
|
"num_tokens": 3095115.0,
|
||
|
|
"step": 1495
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.019172143936157,
|
||
|
|
"epoch": 1.3625624716038165,
|
||
|
|
"grad_norm": 1.078125,
|
||
|
|
"learning_rate": 0.0004972409233678575,
|
||
|
|
"loss": 6.0843,
|
||
|
|
"mean_token_accuracy": 0.13452800139784812,
|
||
|
|
"num_tokens": 3104841.0,
|
||
|
|
"step": 1500
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 1.3625624716038165,
|
||
|
|
"eval_entropy": 5.952520974846774,
|
||
|
|
"eval_loss": 6.207791805267334,
|
||
|
|
"eval_mean_token_accuracy": 0.13844329656729865,
|
||
|
|
"eval_num_tokens": 3104841.0,
|
||
|
|
"eval_runtime": 2.7946,
|
||
|
|
"eval_samples_per_second": 1229.15,
|
||
|
|
"eval_steps_per_second": 153.867,
|
||
|
|
"step": 1500
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.99462194442749,
|
||
|
|
"epoch": 1.3671058609722853,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.0004971854703769401,
|
||
|
|
"loss": 5.9409,
|
||
|
|
"mean_token_accuracy": 0.14266305193305015,
|
||
|
|
"num_tokens": 3115098.0,
|
||
|
|
"step": 1505
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.979383325576782,
|
||
|
|
"epoch": 1.3716492503407542,
|
||
|
|
"grad_norm": 1.109375,
|
||
|
|
"learning_rate": 0.0004971294691654616,
|
||
|
|
"loss": 5.8424,
|
||
|
|
"mean_token_accuracy": 0.15014744699001312,
|
||
|
|
"num_tokens": 3124831.0,
|
||
|
|
"step": 1510
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.916868686676025,
|
||
|
|
"epoch": 1.376192639709223,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.000497072919871599,
|
||
|
|
"loss": 6.0054,
|
||
|
|
"mean_token_accuracy": 0.13746115788817406,
|
||
|
|
"num_tokens": 3136113.0,
|
||
|
|
"step": 1515
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.122059392929077,
|
||
|
|
"epoch": 1.380736029077692,
|
||
|
|
"grad_norm": 1.171875,
|
||
|
|
"learning_rate": 0.0004970158226348824,
|
||
|
|
"loss": 5.9268,
|
||
|
|
"mean_token_accuracy": 0.15368309766054153,
|
||
|
|
"num_tokens": 3145617.0,
|
||
|
|
"step": 1520
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.852825069427491,
|
||
|
|
"epoch": 1.3852794184461608,
|
||
|
|
"grad_norm": 1.109375,
|
||
|
|
"learning_rate": 0.0004969581775961932,
|
||
|
|
"loss": 6.0147,
|
||
|
|
"mean_token_accuracy": 0.14040548503398895,
|
||
|
|
"num_tokens": 3156913.0,
|
||
|
|
"step": 1525
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.042289066314697,
|
||
|
|
"epoch": 1.3898228078146297,
|
||
|
|
"grad_norm": 1.1953125,
|
||
|
|
"learning_rate": 0.0004968999848977651,
|
||
|
|
"loss": 5.9586,
|
||
|
|
"mean_token_accuracy": 0.13911829963326455,
|
||
|
|
"num_tokens": 3167506.0,
|
||
|
|
"step": 1530
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.871926736831665,
|
||
|
|
"epoch": 1.3943661971830985,
|
||
|
|
"grad_norm": 1.0703125,
|
||
|
|
"learning_rate": 0.0004968412446831827,
|
||
|
|
"loss": 5.8468,
|
||
|
|
"mean_token_accuracy": 0.14407547563314438,
|
||
|
|
"num_tokens": 3177956.0,
|
||
|
|
"step": 1535
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.061702823638916,
|
||
|
|
"epoch": 1.3989095865515675,
|
||
|
|
"grad_norm": 1.0078125,
|
||
|
|
"learning_rate": 0.0004967819570973816,
|
||
|
|
"loss": 6.0998,
|
||
|
|
"mean_token_accuracy": 0.14125556200742723,
|
||
|
|
"num_tokens": 3189172.0,
|
||
|
|
"step": 1540
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.007503175735474,
|
||
|
|
"epoch": 1.4034529759200365,
|
||
|
|
"grad_norm": 1.1484375,
|
||
|
|
"learning_rate": 0.000496722122286648,
|
||
|
|
"loss": 6.0076,
|
||
|
|
"mean_token_accuracy": 0.1400210067629814,
|
||
|
|
"num_tokens": 3200188.0,
|
||
|
|
"step": 1545
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.946048545837402,
|
||
|
|
"epoch": 1.4079963652885052,
|
||
|
|
"grad_norm": 0.99609375,
|
||
|
|
"learning_rate": 0.0004966617403986185,
|
||
|
|
"loss": 5.8475,
|
||
|
|
"mean_token_accuracy": 0.14049874618649483,
|
||
|
|
"num_tokens": 3210171.0,
|
||
|
|
"step": 1550
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.00736141204834,
|
||
|
|
"epoch": 1.412539754656974,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.0004966008115822793,
|
||
|
|
"loss": 6.0701,
|
||
|
|
"mean_token_accuracy": 0.13583848625421524,
|
||
|
|
"num_tokens": 3221201.0,
|
||
|
|
"step": 1555
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.953229236602783,
|
||
|
|
"epoch": 1.417083144025443,
|
||
|
|
"grad_norm": 1.1484375,
|
||
|
|
"learning_rate": 0.0004965393359879662,
|
||
|
|
"loss": 5.921,
|
||
|
|
"mean_token_accuracy": 0.1424741789698601,
|
||
|
|
"num_tokens": 3231825.0,
|
||
|
|
"step": 1560
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.091651391983032,
|
||
|
|
"epoch": 1.421626533393912,
|
||
|
|
"grad_norm": 1.109375,
|
||
|
|
"learning_rate": 0.0004964773137673641,
|
||
|
|
"loss": 6.114,
|
||
|
|
"mean_token_accuracy": 0.13234196305274964,
|
||
|
|
"num_tokens": 3241860.0,
|
||
|
|
"step": 1565
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.877058601379394,
|
||
|
|
"epoch": 1.4261699227623807,
|
||
|
|
"grad_norm": 1.1796875,
|
||
|
|
"learning_rate": 0.0004964147450735067,
|
||
|
|
"loss": 5.7883,
|
||
|
|
"mean_token_accuracy": 0.15056520849466323,
|
||
|
|
"num_tokens": 3251893.0,
|
||
|
|
"step": 1570
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.967958641052246,
|
||
|
|
"epoch": 1.4307133121308495,
|
||
|
|
"grad_norm": 0.98046875,
|
||
|
|
"learning_rate": 0.000496351630060776,
|
||
|
|
"loss": 5.9205,
|
||
|
|
"mean_token_accuracy": 0.13848666921257974,
|
||
|
|
"num_tokens": 3262748.0,
|
||
|
|
"step": 1575
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.038754320144653,
|
||
|
|
"epoch": 1.4352567014993185,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.0004962879688849021,
|
||
|
|
"loss": 6.0288,
|
||
|
|
"mean_token_accuracy": 0.13997522443532945,
|
||
|
|
"num_tokens": 3273035.0,
|
||
|
|
"step": 1580
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.02143964767456,
|
||
|
|
"epoch": 1.4398000908677875,
|
||
|
|
"grad_norm": 1.0546875,
|
||
|
|
"learning_rate": 0.0004962237617029625,
|
||
|
|
"loss": 5.9559,
|
||
|
|
"mean_token_accuracy": 0.14435344338417053,
|
||
|
|
"num_tokens": 3283413.0,
|
||
|
|
"step": 1585
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.952090311050415,
|
||
|
|
"epoch": 1.4443434802362562,
|
||
|
|
"grad_norm": 0.99609375,
|
||
|
|
"learning_rate": 0.0004961590086733821,
|
||
|
|
"loss": 5.9434,
|
||
|
|
"mean_token_accuracy": 0.1430325210094452,
|
||
|
|
"num_tokens": 3294628.0,
|
||
|
|
"step": 1590
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.941321563720703,
|
||
|
|
"epoch": 1.448886869604725,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.0004960937099559326,
|
||
|
|
"loss": 5.9281,
|
||
|
|
"mean_token_accuracy": 0.15504622757434844,
|
||
|
|
"num_tokens": 3304631.0,
|
||
|
|
"step": 1595
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.942373561859131,
|
||
|
|
"epoch": 1.453430258973194,
|
||
|
|
"grad_norm": 0.99609375,
|
||
|
|
"learning_rate": 0.0004960278657117321,
|
||
|
|
"loss": 5.9472,
|
||
|
|
"mean_token_accuracy": 0.14010237380862237,
|
||
|
|
"num_tokens": 3315481.0,
|
||
|
|
"step": 1600
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.963896894454956,
|
||
|
|
"epoch": 1.457973648341663,
|
||
|
|
"grad_norm": 1.203125,
|
||
|
|
"learning_rate": 0.0004959614761032446,
|
||
|
|
"loss": 5.8896,
|
||
|
|
"mean_token_accuracy": 0.14427914768457412,
|
||
|
|
"num_tokens": 3326493.0,
|
||
|
|
"step": 1605
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.1022755146026615,
|
||
|
|
"epoch": 1.4625170377101318,
|
||
|
|
"grad_norm": 1.0078125,
|
||
|
|
"learning_rate": 0.00049589454129428,
|
||
|
|
"loss": 6.0348,
|
||
|
|
"mean_token_accuracy": 0.1388540171086788,
|
||
|
|
"num_tokens": 3338358.0,
|
||
|
|
"step": 1610
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.969568681716919,
|
||
|
|
"epoch": 1.4670604270786005,
|
||
|
|
"grad_norm": 1.2265625,
|
||
|
|
"learning_rate": 0.0004958270614499932,
|
||
|
|
"loss": 5.9892,
|
||
|
|
"mean_token_accuracy": 0.1384444311261177,
|
||
|
|
"num_tokens": 3347961.0,
|
||
|
|
"step": 1615
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.955298995971679,
|
||
|
|
"epoch": 1.4716038164470695,
|
||
|
|
"grad_norm": 1.0703125,
|
||
|
|
"learning_rate": 0.0004957590367368841,
|
||
|
|
"loss": 5.918,
|
||
|
|
"mean_token_accuracy": 0.14495049715042113,
|
||
|
|
"num_tokens": 3358544.0,
|
||
|
|
"step": 1620
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.940098476409912,
|
||
|
|
"epoch": 1.4761472058155385,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.0004956904673227968,
|
||
|
|
"loss": 5.9163,
|
||
|
|
"mean_token_accuracy": 0.14714469611644745,
|
||
|
|
"num_tokens": 3368233.0,
|
||
|
|
"step": 1625
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.891028165817261,
|
||
|
|
"epoch": 1.4806905951840073,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.0004956213533769195,
|
||
|
|
"loss": 5.8798,
|
||
|
|
"mean_token_accuracy": 0.14687413945794106,
|
||
|
|
"num_tokens": 3379065.0,
|
||
|
|
"step": 1630
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.050700235366821,
|
||
|
|
"epoch": 1.485233984552476,
|
||
|
|
"grad_norm": 1.0703125,
|
||
|
|
"learning_rate": 0.0004955516950697843,
|
||
|
|
"loss": 5.9705,
|
||
|
|
"mean_token_accuracy": 0.1408476561307907,
|
||
|
|
"num_tokens": 3389251.0,
|
||
|
|
"step": 1635
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.947952032089233,
|
||
|
|
"epoch": 1.489777373920945,
|
||
|
|
"grad_norm": 1.0546875,
|
||
|
|
"learning_rate": 0.0004954814925732657,
|
||
|
|
"loss": 5.904,
|
||
|
|
"mean_token_accuracy": 0.14892102256417275,
|
||
|
|
"num_tokens": 3399660.0,
|
||
|
|
"step": 1640
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.9753376007080075,
|
||
|
|
"epoch": 1.494320763289414,
|
||
|
|
"grad_norm": 1.1328125,
|
||
|
|
"learning_rate": 0.0004954107460605816,
|
||
|
|
"loss": 5.952,
|
||
|
|
"mean_token_accuracy": 0.14645659551024437,
|
||
|
|
"num_tokens": 3409395.0,
|
||
|
|
"step": 1645
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.021202087402344,
|
||
|
|
"epoch": 1.4988641526578828,
|
||
|
|
"grad_norm": 1.109375,
|
||
|
|
"learning_rate": 0.0004953394557062922,
|
||
|
|
"loss": 5.9398,
|
||
|
|
"mean_token_accuracy": 0.136006910353899,
|
||
|
|
"num_tokens": 3419881.0,
|
||
|
|
"step": 1650
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.926182079315185,
|
||
|
|
"epoch": 1.5034075420263515,
|
||
|
|
"grad_norm": 0.9609375,
|
||
|
|
"learning_rate": 0.0004952676216862989,
|
||
|
|
"loss": 5.9319,
|
||
|
|
"mean_token_accuracy": 0.14269742593169213,
|
||
|
|
"num_tokens": 3430316.0,
|
||
|
|
"step": 1655
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.884389495849609,
|
||
|
|
"epoch": 1.5079509313948205,
|
||
|
|
"grad_norm": 1.1171875,
|
||
|
|
"learning_rate": 0.0004951952441778453,
|
||
|
|
"loss": 5.8264,
|
||
|
|
"mean_token_accuracy": 0.15141425877809525,
|
||
|
|
"num_tokens": 3440174.0,
|
||
|
|
"step": 1660
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.954122495651245,
|
||
|
|
"epoch": 1.5124943207632895,
|
||
|
|
"grad_norm": 0.984375,
|
||
|
|
"learning_rate": 0.0004951223233595158,
|
||
|
|
"loss": 5.9859,
|
||
|
|
"mean_token_accuracy": 0.13919273614883423,
|
||
|
|
"num_tokens": 3451141.0,
|
||
|
|
"step": 1665
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.008854818344116,
|
||
|
|
"epoch": 1.5170377101317583,
|
||
|
|
"grad_norm": 0.984375,
|
||
|
|
"learning_rate": 0.000495048859411235,
|
||
|
|
"loss": 5.8835,
|
||
|
|
"mean_token_accuracy": 0.14436262398958205,
|
||
|
|
"num_tokens": 3461767.0,
|
||
|
|
"step": 1670
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.854226875305176,
|
||
|
|
"epoch": 1.521581099500227,
|
||
|
|
"grad_norm": 1.140625,
|
||
|
|
"learning_rate": 0.0004949748525142681,
|
||
|
|
"loss": 5.8325,
|
||
|
|
"mean_token_accuracy": 0.15278302133083344,
|
||
|
|
"num_tokens": 3470937.0,
|
||
|
|
"step": 1675
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.9624449729919435,
|
||
|
|
"epoch": 1.526124488868696,
|
||
|
|
"grad_norm": 1.078125,
|
||
|
|
"learning_rate": 0.0004949003028512195,
|
||
|
|
"loss": 5.9211,
|
||
|
|
"mean_token_accuracy": 0.13923487737774848,
|
||
|
|
"num_tokens": 3482130.0,
|
||
|
|
"step": 1680
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.961441612243652,
|
||
|
|
"epoch": 1.530667878237165,
|
||
|
|
"grad_norm": 1.140625,
|
||
|
|
"learning_rate": 0.0004948252106060334,
|
||
|
|
"loss": 5.9873,
|
||
|
|
"mean_token_accuracy": 0.14150320515036582,
|
||
|
|
"num_tokens": 3491992.0,
|
||
|
|
"step": 1685
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.8464337348937985,
|
||
|
|
"epoch": 1.5352112676056338,
|
||
|
|
"grad_norm": 1.1328125,
|
||
|
|
"learning_rate": 0.0004947495759639923,
|
||
|
|
"loss": 5.844,
|
||
|
|
"mean_token_accuracy": 0.15078289955854415,
|
||
|
|
"num_tokens": 3501437.0,
|
||
|
|
"step": 1690
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.876981639862061,
|
||
|
|
"epoch": 1.5397546569741025,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.0004946733991117171,
|
||
|
|
"loss": 5.9118,
|
||
|
|
"mean_token_accuracy": 0.14388926029205323,
|
||
|
|
"num_tokens": 3511625.0,
|
||
|
|
"step": 1695
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.918456602096557,
|
||
|
|
"epoch": 1.5442980463425715,
|
||
|
|
"grad_norm": 1.109375,
|
||
|
|
"learning_rate": 0.0004945966802371668,
|
||
|
|
"loss": 5.7004,
|
||
|
|
"mean_token_accuracy": 0.15261678099632264,
|
||
|
|
"num_tokens": 3520428.0,
|
||
|
|
"step": 1700
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.920832633972168,
|
||
|
|
"epoch": 1.5488414357110405,
|
||
|
|
"grad_norm": 0.96875,
|
||
|
|
"learning_rate": 0.0004945194195296374,
|
||
|
|
"loss": 5.9139,
|
||
|
|
"mean_token_accuracy": 0.14273062944412232,
|
||
|
|
"num_tokens": 3532218.0,
|
||
|
|
"step": 1705
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.941348266601563,
|
||
|
|
"epoch": 1.5533848250795095,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.000494441617179762,
|
||
|
|
"loss": 5.8974,
|
||
|
|
"mean_token_accuracy": 0.14131915792822838,
|
||
|
|
"num_tokens": 3543177.0,
|
||
|
|
"step": 1710
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.9505699634552,
|
||
|
|
"epoch": 1.5579282144479782,
|
||
|
|
"grad_norm": 1.2109375,
|
||
|
|
"learning_rate": 0.0004943632733795104,
|
||
|
|
"loss": 5.8494,
|
||
|
|
"mean_token_accuracy": 0.1531837522983551,
|
||
|
|
"num_tokens": 3552833.0,
|
||
|
|
"step": 1715
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.805274772644043,
|
||
|
|
"epoch": 1.562471603816447,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.0004942843883221879,
|
||
|
|
"loss": 5.9233,
|
||
|
|
"mean_token_accuracy": 0.1416128844022751,
|
||
|
|
"num_tokens": 3563558.0,
|
||
|
|
"step": 1720
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.891717195510864,
|
||
|
|
"epoch": 1.567014993184916,
|
||
|
|
"grad_norm": 1.1015625,
|
||
|
|
"learning_rate": 0.0004942049622024357,
|
||
|
|
"loss": 5.8716,
|
||
|
|
"mean_token_accuracy": 0.15252673625946045,
|
||
|
|
"num_tokens": 3574993.0,
|
||
|
|
"step": 1725
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.977005434036255,
|
||
|
|
"epoch": 1.571558382553385,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.0004941249952162298,
|
||
|
|
"loss": 5.89,
|
||
|
|
"mean_token_accuracy": 0.14125805348157883,
|
||
|
|
"num_tokens": 3584586.0,
|
||
|
|
"step": 1730
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.831153774261475,
|
||
|
|
"epoch": 1.5761017719218537,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.0004940444875608807,
|
||
|
|
"loss": 5.8367,
|
||
|
|
"mean_token_accuracy": 0.15189587622880935,
|
||
|
|
"num_tokens": 3595029.0,
|
||
|
|
"step": 1735
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.910392475128174,
|
||
|
|
"epoch": 1.5806451612903225,
|
||
|
|
"grad_norm": 1.0703125,
|
||
|
|
"learning_rate": 0.0004939634394350332,
|
||
|
|
"loss": 5.8994,
|
||
|
|
"mean_token_accuracy": 0.145536919683218,
|
||
|
|
"num_tokens": 3606034.0,
|
||
|
|
"step": 1740
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.950764417648315,
|
||
|
|
"epoch": 1.5851885506587915,
|
||
|
|
"grad_norm": 1.1328125,
|
||
|
|
"learning_rate": 0.0004938818510386654,
|
||
|
|
"loss": 5.8402,
|
||
|
|
"mean_token_accuracy": 0.14515646025538445,
|
||
|
|
"num_tokens": 3615551.0,
|
||
|
|
"step": 1745
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.84814076423645,
|
||
|
|
"epoch": 1.5897319400272605,
|
||
|
|
"grad_norm": 1.1328125,
|
||
|
|
"learning_rate": 0.0004937997225730886,
|
||
|
|
"loss": 5.9831,
|
||
|
|
"mean_token_accuracy": 0.1476181536912918,
|
||
|
|
"num_tokens": 3626811.0,
|
||
|
|
"step": 1750
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.922665405273437,
|
||
|
|
"epoch": 1.5942753293957292,
|
||
|
|
"grad_norm": 1.1171875,
|
||
|
|
"learning_rate": 0.0004937170542409464,
|
||
|
|
"loss": 5.8358,
|
||
|
|
"mean_token_accuracy": 0.14447919875383378,
|
||
|
|
"num_tokens": 3637338.0,
|
||
|
|
"step": 1755
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.839316034317017,
|
||
|
|
"epoch": 1.598818718764198,
|
||
|
|
"grad_norm": 1.0625,
|
||
|
|
"learning_rate": 0.000493633846246215,
|
||
|
|
"loss": 5.7726,
|
||
|
|
"mean_token_accuracy": 0.14876675009727477,
|
||
|
|
"num_tokens": 3648650.0,
|
||
|
|
"step": 1760
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.943630695343018,
|
||
|
|
"epoch": 1.603362108132667,
|
||
|
|
"grad_norm": 1.109375,
|
||
|
|
"learning_rate": 0.0004935500987942018,
|
||
|
|
"loss": 5.9341,
|
||
|
|
"mean_token_accuracy": 0.14553604349493982,
|
||
|
|
"num_tokens": 3659331.0,
|
||
|
|
"step": 1765
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.960559415817261,
|
||
|
|
"epoch": 1.607905497501136,
|
||
|
|
"grad_norm": 1.0078125,
|
||
|
|
"learning_rate": 0.0004934658120915452,
|
||
|
|
"loss": 6.0046,
|
||
|
|
"mean_token_accuracy": 0.13882950097322463,
|
||
|
|
"num_tokens": 3670757.0,
|
||
|
|
"step": 1770
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.938638305664062,
|
||
|
|
"epoch": 1.6124488868696047,
|
||
|
|
"grad_norm": 1.125,
|
||
|
|
"learning_rate": 0.0004933809863462142,
|
||
|
|
"loss": 5.8411,
|
||
|
|
"mean_token_accuracy": 0.14908881187438966,
|
||
|
|
"num_tokens": 3681286.0,
|
||
|
|
"step": 1775
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.86508994102478,
|
||
|
|
"epoch": 1.6169922762380735,
|
||
|
|
"grad_norm": 1.1484375,
|
||
|
|
"learning_rate": 0.0004932956217675082,
|
||
|
|
"loss": 5.8322,
|
||
|
|
"mean_token_accuracy": 0.15267545282840728,
|
||
|
|
"num_tokens": 3690733.0,
|
||
|
|
"step": 1780
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.98020076751709,
|
||
|
|
"epoch": 1.6215356656065425,
|
||
|
|
"grad_norm": 1.1328125,
|
||
|
|
"learning_rate": 0.0004932097185660555,
|
||
|
|
"loss": 6.0158,
|
||
|
|
"mean_token_accuracy": 0.14166081100702285,
|
||
|
|
"num_tokens": 3701263.0,
|
||
|
|
"step": 1785
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.95297589302063,
|
||
|
|
"epoch": 1.6260790549750115,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.0004931232769538138,
|
||
|
|
"loss": 5.9148,
|
||
|
|
"mean_token_accuracy": 0.14752905070781708,
|
||
|
|
"num_tokens": 3711578.0,
|
||
|
|
"step": 1790
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.993722248077392,
|
||
|
|
"epoch": 1.6306224443434802,
|
||
|
|
"grad_norm": 1.15625,
|
||
|
|
"learning_rate": 0.0004930362971440692,
|
||
|
|
"loss": 5.9086,
|
||
|
|
"mean_token_accuracy": 0.14346786960959435,
|
||
|
|
"num_tokens": 3722140.0,
|
||
|
|
"step": 1795
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.804684638977051,
|
||
|
|
"epoch": 1.635165833711949,
|
||
|
|
"grad_norm": 1.2578125,
|
||
|
|
"learning_rate": 0.0004929487793514358,
|
||
|
|
"loss": 5.6267,
|
||
|
|
"mean_token_accuracy": 0.1540088638663292,
|
||
|
|
"num_tokens": 3732019.0,
|
||
|
|
"step": 1800
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.840555429458618,
|
||
|
|
"epoch": 1.639709223080418,
|
||
|
|
"grad_norm": 1.171875,
|
||
|
|
"learning_rate": 0.000492860723791855,
|
||
|
|
"loss": 5.8349,
|
||
|
|
"mean_token_accuracy": 0.14961637333035469,
|
||
|
|
"num_tokens": 3741912.0,
|
||
|
|
"step": 1805
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.951719141006469,
|
||
|
|
"epoch": 1.644252612448887,
|
||
|
|
"grad_norm": 1.203125,
|
||
|
|
"learning_rate": 0.0004927721306825952,
|
||
|
|
"loss": 5.8284,
|
||
|
|
"mean_token_accuracy": 0.14838206619024277,
|
||
|
|
"num_tokens": 3751365.0,
|
||
|
|
"step": 1810
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.806200456619263,
|
||
|
|
"epoch": 1.6487960018173557,
|
||
|
|
"grad_norm": 1.0625,
|
||
|
|
"learning_rate": 0.0004926830002422509,
|
||
|
|
"loss": 5.8056,
|
||
|
|
"mean_token_accuracy": 0.14574428796768188,
|
||
|
|
"num_tokens": 3762160.0,
|
||
|
|
"step": 1815
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.896996021270752,
|
||
|
|
"epoch": 1.6533393911858245,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.000492593332690743,
|
||
|
|
"loss": 5.8481,
|
||
|
|
"mean_token_accuracy": 0.14969197660684586,
|
||
|
|
"num_tokens": 3772608.0,
|
||
|
|
"step": 1820
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.856444787979126,
|
||
|
|
"epoch": 1.6578827805542935,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.0004925031282493167,
|
||
|
|
"loss": 5.8851,
|
||
|
|
"mean_token_accuracy": 0.14442452415823936,
|
||
|
|
"num_tokens": 3783344.0,
|
||
|
|
"step": 1825
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.943165874481201,
|
||
|
|
"epoch": 1.6624261699227625,
|
||
|
|
"grad_norm": 1.140625,
|
||
|
|
"learning_rate": 0.0004924123871405428,
|
||
|
|
"loss": 5.8967,
|
||
|
|
"mean_token_accuracy": 0.14382675886154175,
|
||
|
|
"num_tokens": 3794103.0,
|
||
|
|
"step": 1830
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.821027517318726,
|
||
|
|
"epoch": 1.6669695592912313,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.0004923211095883161,
|
||
|
|
"loss": 5.82,
|
||
|
|
"mean_token_accuracy": 0.15115977749228476,
|
||
|
|
"num_tokens": 3804537.0,
|
||
|
|
"step": 1835
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.911714172363281,
|
||
|
|
"epoch": 1.6715129486597,
|
||
|
|
"grad_norm": 1.171875,
|
||
|
|
"learning_rate": 0.0004922292958178546,
|
||
|
|
"loss": 5.8419,
|
||
|
|
"mean_token_accuracy": 0.14932646602392197,
|
||
|
|
"num_tokens": 3814147.0,
|
||
|
|
"step": 1840
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.96919002532959,
|
||
|
|
"epoch": 1.676056338028169,
|
||
|
|
"grad_norm": 1.203125,
|
||
|
|
"learning_rate": 0.0004921369460557,
|
||
|
|
"loss": 5.9412,
|
||
|
|
"mean_token_accuracy": 0.14370580911636352,
|
||
|
|
"num_tokens": 3823640.0,
|
||
|
|
"step": 1845
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.846808624267578,
|
||
|
|
"epoch": 1.680599727396638,
|
||
|
|
"grad_norm": 1.0546875,
|
||
|
|
"learning_rate": 0.0004920440605297159,
|
||
|
|
"loss": 5.7682,
|
||
|
|
"mean_token_accuracy": 0.1589408814907074,
|
||
|
|
"num_tokens": 3833418.0,
|
||
|
|
"step": 1850
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.839104270935058,
|
||
|
|
"epoch": 1.6851431167651068,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.000491950639469088,
|
||
|
|
"loss": 5.788,
|
||
|
|
"mean_token_accuracy": 0.15187744349241256,
|
||
|
|
"num_tokens": 3844998.0,
|
||
|
|
"step": 1855
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.784125089645386,
|
||
|
|
"epoch": 1.6896865061335755,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.0004918566831043238,
|
||
|
|
"loss": 5.7262,
|
||
|
|
"mean_token_accuracy": 0.15564873069524765,
|
||
|
|
"num_tokens": 3855549.0,
|
||
|
|
"step": 1860
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.813870859146118,
|
||
|
|
"epoch": 1.6942298955020445,
|
||
|
|
"grad_norm": 1.25,
|
||
|
|
"learning_rate": 0.000491762191667251,
|
||
|
|
"loss": 5.8403,
|
||
|
|
"mean_token_accuracy": 0.15067547261714936,
|
||
|
|
"num_tokens": 3865287.0,
|
||
|
|
"step": 1865
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.872530603408814,
|
||
|
|
"epoch": 1.6987732848705135,
|
||
|
|
"grad_norm": 1.1484375,
|
||
|
|
"learning_rate": 0.000491667165391018,
|
||
|
|
"loss": 5.8987,
|
||
|
|
"mean_token_accuracy": 0.14980295076966285,
|
||
|
|
"num_tokens": 3875914.0,
|
||
|
|
"step": 1870
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.950064992904663,
|
||
|
|
"epoch": 1.7033166742389823,
|
||
|
|
"grad_norm": 1.1875,
|
||
|
|
"learning_rate": 0.0004915716045100927,
|
||
|
|
"loss": 5.889,
|
||
|
|
"mean_token_accuracy": 0.14314936101436615,
|
||
|
|
"num_tokens": 3885196.0,
|
||
|
|
"step": 1875
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.89986743927002,
|
||
|
|
"epoch": 1.707860063607451,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.0004914755092602621,
|
||
|
|
"loss": 5.9203,
|
||
|
|
"mean_token_accuracy": 0.13913992792367935,
|
||
|
|
"num_tokens": 3895227.0,
|
||
|
|
"step": 1880
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.864428567886352,
|
||
|
|
"epoch": 1.71240345297592,
|
||
|
|
"grad_norm": 1.171875,
|
||
|
|
"learning_rate": 0.0004913788798786314,
|
||
|
|
"loss": 5.7911,
|
||
|
|
"mean_token_accuracy": 0.14839531779289244,
|
||
|
|
"num_tokens": 3905926.0,
|
||
|
|
"step": 1885
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.850302410125733,
|
||
|
|
"epoch": 1.716946842344389,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.0004912817166036243,
|
||
|
|
"loss": 5.8262,
|
||
|
|
"mean_token_accuracy": 0.15205959975719452,
|
||
|
|
"num_tokens": 3916982.0,
|
||
|
|
"step": 1890
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.825182247161865,
|
||
|
|
"epoch": 1.7214902317128578,
|
||
|
|
"grad_norm": 1.0859375,
|
||
|
|
"learning_rate": 0.0004911840196749813,
|
||
|
|
"loss": 5.7642,
|
||
|
|
"mean_token_accuracy": 0.14805149286985397,
|
||
|
|
"num_tokens": 3926889.0,
|
||
|
|
"step": 1895
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.894171237945557,
|
||
|
|
"epoch": 1.7260336210813265,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.0004910857893337602,
|
||
|
|
"loss": 5.7834,
|
||
|
|
"mean_token_accuracy": 0.1433366745710373,
|
||
|
|
"num_tokens": 3936734.0,
|
||
|
|
"step": 1900
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.856796789169311,
|
||
|
|
"epoch": 1.7305770104497955,
|
||
|
|
"grad_norm": 1.078125,
|
||
|
|
"learning_rate": 0.0004909870258223342,
|
||
|
|
"loss": 5.9236,
|
||
|
|
"mean_token_accuracy": 0.14193570539355277,
|
||
|
|
"num_tokens": 3948001.0,
|
||
|
|
"step": 1905
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.9134862422943115,
|
||
|
|
"epoch": 1.7351203998182645,
|
||
|
|
"grad_norm": 1.1015625,
|
||
|
|
"learning_rate": 0.0004908877293843926,
|
||
|
|
"loss": 5.8093,
|
||
|
|
"mean_token_accuracy": 0.14628526121377944,
|
||
|
|
"num_tokens": 3957433.0,
|
||
|
|
"step": 1910
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.915403604507446,
|
||
|
|
"epoch": 1.7396637891867333,
|
||
|
|
"grad_norm": 0.9921875,
|
||
|
|
"learning_rate": 0.0004907879002649395,
|
||
|
|
"loss": 5.888,
|
||
|
|
"mean_token_accuracy": 0.1475825399160385,
|
||
|
|
"num_tokens": 3967375.0,
|
||
|
|
"step": 1915
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.898691177368164,
|
||
|
|
"epoch": 1.744207178555202,
|
||
|
|
"grad_norm": 1.2578125,
|
||
|
|
"learning_rate": 0.0004906875387102935,
|
||
|
|
"loss": 5.8661,
|
||
|
|
"mean_token_accuracy": 0.1420122355222702,
|
||
|
|
"num_tokens": 3977190.0,
|
||
|
|
"step": 1920
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.882886171340942,
|
||
|
|
"epoch": 1.748750567923671,
|
||
|
|
"grad_norm": 1.1015625,
|
||
|
|
"learning_rate": 0.0004905866449680864,
|
||
|
|
"loss": 5.8512,
|
||
|
|
"mean_token_accuracy": 0.1531060181558132,
|
||
|
|
"num_tokens": 3987878.0,
|
||
|
|
"step": 1925
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.875026750564575,
|
||
|
|
"epoch": 1.75329395729214,
|
||
|
|
"grad_norm": 1.125,
|
||
|
|
"learning_rate": 0.0004904852192872638,
|
||
|
|
"loss": 5.845,
|
||
|
|
"mean_token_accuracy": 0.14857483953237532,
|
||
|
|
"num_tokens": 3997166.0,
|
||
|
|
"step": 1930
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.897173833847046,
|
||
|
|
"epoch": 1.757837346660609,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.0004903832619180834,
|
||
|
|
"loss": 5.8326,
|
||
|
|
"mean_token_accuracy": 0.14652054458856584,
|
||
|
|
"num_tokens": 4007711.0,
|
||
|
|
"step": 1935
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.9265892028808596,
|
||
|
|
"epoch": 1.7623807360290777,
|
||
|
|
"grad_norm": 1.1875,
|
||
|
|
"learning_rate": 0.0004902807731121147,
|
||
|
|
"loss": 5.9763,
|
||
|
|
"mean_token_accuracy": 0.14133203625679017,
|
||
|
|
"num_tokens": 4018907.0,
|
||
|
|
"step": 1940
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.867978954315186,
|
||
|
|
"epoch": 1.7669241253975465,
|
||
|
|
"grad_norm": 1.140625,
|
||
|
|
"learning_rate": 0.0004901777531222389,
|
||
|
|
"loss": 5.864,
|
||
|
|
"mean_token_accuracy": 0.1498611330986023,
|
||
|
|
"num_tokens": 4030006.0,
|
||
|
|
"step": 1945
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.989753198623657,
|
||
|
|
"epoch": 1.7714675147660155,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.0004900742022026474,
|
||
|
|
"loss": 5.9589,
|
||
|
|
"mean_token_accuracy": 0.1504744090139866,
|
||
|
|
"num_tokens": 4040609.0,
|
||
|
|
"step": 1950
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.826623916625977,
|
||
|
|
"epoch": 1.7760109041344845,
|
||
|
|
"grad_norm": 1.1796875,
|
||
|
|
"learning_rate": 0.0004899701206088419,
|
||
|
|
"loss": 5.7838,
|
||
|
|
"mean_token_accuracy": 0.14803807586431503,
|
||
|
|
"num_tokens": 4050392.0,
|
||
|
|
"step": 1955
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.823447513580322,
|
||
|
|
"epoch": 1.7805542935029532,
|
||
|
|
"grad_norm": 1.1796875,
|
||
|
|
"learning_rate": 0.0004898655085976333,
|
||
|
|
"loss": 5.8851,
|
||
|
|
"mean_token_accuracy": 0.1428491950035095,
|
||
|
|
"num_tokens": 4060156.0,
|
||
|
|
"step": 1960
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.940966033935547,
|
||
|
|
"epoch": 1.785097682871422,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.0004897603664271413,
|
||
|
|
"loss": 5.7626,
|
||
|
|
"mean_token_accuracy": 0.15149431079626083,
|
||
|
|
"num_tokens": 4069670.0,
|
||
|
|
"step": 1965
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.776753520965576,
|
||
|
|
"epoch": 1.789641072239891,
|
||
|
|
"grad_norm": 1.1015625,
|
||
|
|
"learning_rate": 0.000489654694356794,
|
||
|
|
"loss": 5.7935,
|
||
|
|
"mean_token_accuracy": 0.1449214018881321,
|
||
|
|
"num_tokens": 4080738.0,
|
||
|
|
"step": 1970
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.7570106983184814,
|
||
|
|
"epoch": 1.79418446160836,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.0004895484926473265,
|
||
|
|
"loss": 5.7594,
|
||
|
|
"mean_token_accuracy": 0.1536009728908539,
|
||
|
|
"num_tokens": 4091122.0,
|
||
|
|
"step": 1975
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.933842706680298,
|
||
|
|
"epoch": 1.7987278509768287,
|
||
|
|
"grad_norm": 1.1015625,
|
||
|
|
"learning_rate": 0.000489441761560781,
|
||
|
|
"loss": 5.8733,
|
||
|
|
"mean_token_accuracy": 0.14600196480751038,
|
||
|
|
"num_tokens": 4101055.0,
|
||
|
|
"step": 1980
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.904268646240235,
|
||
|
|
"epoch": 1.8032712403452975,
|
||
|
|
"grad_norm": 1.1328125,
|
||
|
|
"learning_rate": 0.000489334501360506,
|
||
|
|
"loss": 5.8308,
|
||
|
|
"mean_token_accuracy": 0.15079639106988907,
|
||
|
|
"num_tokens": 4110631.0,
|
||
|
|
"step": 1985
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.8311481952667235,
|
||
|
|
"epoch": 1.8078146297137665,
|
||
|
|
"grad_norm": 1.1484375,
|
||
|
|
"learning_rate": 0.0004892267123111551,
|
||
|
|
"loss": 5.8281,
|
||
|
|
"mean_token_accuracy": 0.14489958733320235,
|
||
|
|
"num_tokens": 4121120.0,
|
||
|
|
"step": 1990
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.924700593948364,
|
||
|
|
"epoch": 1.8123580190822355,
|
||
|
|
"grad_norm": 1.1953125,
|
||
|
|
"learning_rate": 0.0004891183946786873,
|
||
|
|
"loss": 5.7857,
|
||
|
|
"mean_token_accuracy": 0.14904456734657287,
|
||
|
|
"num_tokens": 4132106.0,
|
||
|
|
"step": 1995
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.833415603637695,
|
||
|
|
"epoch": 1.8169014084507042,
|
||
|
|
"grad_norm": 1.1640625,
|
||
|
|
"learning_rate": 0.0004890095487303655,
|
||
|
|
"loss": 5.8293,
|
||
|
|
"mean_token_accuracy": 0.1477825567126274,
|
||
|
|
"num_tokens": 4142216.0,
|
||
|
|
"step": 2000
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 1.8169014084507042,
|
||
|
|
"eval_entropy": 5.819109145985093,
|
||
|
|
"eval_loss": 6.050093173980713,
|
||
|
|
"eval_mean_token_accuracy": 0.14379453367965167,
|
||
|
|
"eval_num_tokens": 4142216.0,
|
||
|
|
"eval_runtime": 2.5968,
|
||
|
|
"eval_samples_per_second": 1322.778,
|
||
|
|
"eval_steps_per_second": 165.588,
|
||
|
|
"step": 2000
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.883230972290039,
|
||
|
|
"epoch": 1.821444797819173,
|
||
|
|
"grad_norm": 1.25,
|
||
|
|
"learning_rate": 0.0004889001747347562,
|
||
|
|
"loss": 5.8701,
|
||
|
|
"mean_token_accuracy": 0.14971277937293054,
|
||
|
|
"num_tokens": 4152168.0,
|
||
|
|
"step": 2005
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.882227420806885,
|
||
|
|
"epoch": 1.825988187187642,
|
||
|
|
"grad_norm": 1.171875,
|
||
|
|
"learning_rate": 0.000488790272961729,
|
||
|
|
"loss": 5.8578,
|
||
|
|
"mean_token_accuracy": 0.14443953037261964,
|
||
|
|
"num_tokens": 4162085.0,
|
||
|
|
"step": 2010
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.899635696411133,
|
||
|
|
"epoch": 1.830531576556111,
|
||
|
|
"grad_norm": 1.203125,
|
||
|
|
"learning_rate": 0.0004886798436824556,
|
||
|
|
"loss": 5.88,
|
||
|
|
"mean_token_accuracy": 0.14574271067976952,
|
||
|
|
"num_tokens": 4171168.0,
|
||
|
|
"step": 2015
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.8919424533844,
|
||
|
|
"epoch": 1.8350749659245797,
|
||
|
|
"grad_norm": 1.0546875,
|
||
|
|
"learning_rate": 0.0004885688871694091,
|
||
|
|
"loss": 5.8192,
|
||
|
|
"mean_token_accuracy": 0.1483355924487114,
|
||
|
|
"num_tokens": 4181804.0,
|
||
|
|
"step": 2020
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.960490989685058,
|
||
|
|
"epoch": 1.8396183552930485,
|
||
|
|
"grad_norm": 1.171875,
|
||
|
|
"learning_rate": 0.0004884574036963639,
|
||
|
|
"loss": 5.8872,
|
||
|
|
"mean_token_accuracy": 0.14367986619472503,
|
||
|
|
"num_tokens": 4192483.0,
|
||
|
|
"step": 2025
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.817529487609863,
|
||
|
|
"epoch": 1.8441617446615175,
|
||
|
|
"grad_norm": 1.0703125,
|
||
|
|
"learning_rate": 0.0004883453935383941,
|
||
|
|
"loss": 5.7738,
|
||
|
|
"mean_token_accuracy": 0.15300548374652861,
|
||
|
|
"num_tokens": 4202214.0,
|
||
|
|
"step": 2030
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.889630556106567,
|
||
|
|
"epoch": 1.8487051340299865,
|
||
|
|
"grad_norm": 1.1484375,
|
||
|
|
"learning_rate": 0.0004882328569718738,
|
||
|
|
"loss": 5.8652,
|
||
|
|
"mean_token_accuracy": 0.1525376059114933,
|
||
|
|
"num_tokens": 4212440.0,
|
||
|
|
"step": 2035
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.852598476409912,
|
||
|
|
"epoch": 1.8532485233984552,
|
||
|
|
"grad_norm": 1.2109375,
|
||
|
|
"learning_rate": 0.0004881197942744758,
|
||
|
|
"loss": 5.8168,
|
||
|
|
"mean_token_accuracy": 0.15018621683120728,
|
||
|
|
"num_tokens": 4222780.0,
|
||
|
|
"step": 2040
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.833838605880738,
|
||
|
|
"epoch": 1.857791912766924,
|
||
|
|
"grad_norm": 1.2265625,
|
||
|
|
"learning_rate": 0.0004880062057251711,
|
||
|
|
"loss": 5.7536,
|
||
|
|
"mean_token_accuracy": 0.1566378265619278,
|
||
|
|
"num_tokens": 4232895.0,
|
||
|
|
"step": 2045
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.815893507003784,
|
||
|
|
"epoch": 1.862335302135393,
|
||
|
|
"grad_norm": 1.140625,
|
||
|
|
"learning_rate": 0.000487892091604228,
|
||
|
|
"loss": 5.8325,
|
||
|
|
"mean_token_accuracy": 0.15336491912603378,
|
||
|
|
"num_tokens": 4244287.0,
|
||
|
|
"step": 2050
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.836065149307251,
|
||
|
|
"epoch": 1.866878691503862,
|
||
|
|
"grad_norm": 1.125,
|
||
|
|
"learning_rate": 0.00048777745219321186,
|
||
|
|
"loss": 5.8025,
|
||
|
|
"mean_token_accuracy": 0.1468632087111473,
|
||
|
|
"num_tokens": 4254327.0,
|
||
|
|
"step": 2055
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.906033039093018,
|
||
|
|
"epoch": 1.8714220808723308,
|
||
|
|
"grad_norm": 1.1484375,
|
||
|
|
"learning_rate": 0.00048766228777498405,
|
||
|
|
"loss": 5.8389,
|
||
|
|
"mean_token_accuracy": 0.1460307225584984,
|
||
|
|
"num_tokens": 4264540.0,
|
||
|
|
"step": 2060
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.867164373397827,
|
||
|
|
"epoch": 1.8759654702407995,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.00048754659863370125,
|
||
|
|
"loss": 5.8125,
|
||
|
|
"mean_token_accuracy": 0.1475397951900959,
|
||
|
|
"num_tokens": 4274946.0,
|
||
|
|
"step": 2065
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.828709363937378,
|
||
|
|
"epoch": 1.8805088596092685,
|
||
|
|
"grad_norm": 1.171875,
|
||
|
|
"learning_rate": 0.00048743038505481503,
|
||
|
|
"loss": 5.7574,
|
||
|
|
"mean_token_accuracy": 0.15103001445531844,
|
||
|
|
"num_tokens": 4284395.0,
|
||
|
|
"step": 2070
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.880394220352173,
|
||
|
|
"epoch": 1.8850522489777375,
|
||
|
|
"grad_norm": 1.2421875,
|
||
|
|
"learning_rate": 0.0004873136473250708,
|
||
|
|
"loss": 5.8516,
|
||
|
|
"mean_token_accuracy": 0.1469341918826103,
|
||
|
|
"num_tokens": 4294887.0,
|
||
|
|
"step": 2075
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.829086589813232,
|
||
|
|
"epoch": 1.8895956383462063,
|
||
|
|
"grad_norm": 1.25,
|
||
|
|
"learning_rate": 0.00048719638573250715,
|
||
|
|
"loss": 5.856,
|
||
|
|
"mean_token_accuracy": 0.1443422928452492,
|
||
|
|
"num_tokens": 4304794.0,
|
||
|
|
"step": 2080
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.8116350173950195,
|
||
|
|
"epoch": 1.894139027714675,
|
||
|
|
"grad_norm": 1.109375,
|
||
|
|
"learning_rate": 0.0004870786005664555,
|
||
|
|
"loss": 5.7663,
|
||
|
|
"mean_token_accuracy": 0.148785400390625,
|
||
|
|
"num_tokens": 4314810.0,
|
||
|
|
"step": 2085
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.871056842803955,
|
||
|
|
"epoch": 1.898682417083144,
|
||
|
|
"grad_norm": 1.0546875,
|
||
|
|
"learning_rate": 0.0004869602921175392,
|
||
|
|
"loss": 5.8192,
|
||
|
|
"mean_token_accuracy": 0.14579248204827308,
|
||
|
|
"num_tokens": 4325444.0,
|
||
|
|
"step": 2090
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.896946716308594,
|
||
|
|
"epoch": 1.903225806451613,
|
||
|
|
"grad_norm": 1.1015625,
|
||
|
|
"learning_rate": 0.0004868414606776724,
|
||
|
|
"loss": 5.8431,
|
||
|
|
"mean_token_accuracy": 0.1450091317296028,
|
||
|
|
"num_tokens": 4335620.0,
|
||
|
|
"step": 2095
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.843059062957764,
|
||
|
|
"epoch": 1.9077691958200818,
|
||
|
|
"grad_norm": 1.1640625,
|
||
|
|
"learning_rate": 0.00048672210654005996,
|
||
|
|
"loss": 5.8229,
|
||
|
|
"mean_token_accuracy": 0.15126920714974404,
|
||
|
|
"num_tokens": 4345006.0,
|
||
|
|
"step": 2100
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.874631357192993,
|
||
|
|
"epoch": 1.9123125851885505,
|
||
|
|
"grad_norm": 1.171875,
|
||
|
|
"learning_rate": 0.00048660222999919616,
|
||
|
|
"loss": 5.7532,
|
||
|
|
"mean_token_accuracy": 0.14949243068695067,
|
||
|
|
"num_tokens": 4354805.0,
|
||
|
|
"step": 2105
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.850671720504761,
|
||
|
|
"epoch": 1.9168559745570195,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.0004864818313508647,
|
||
|
|
"loss": 5.9075,
|
||
|
|
"mean_token_accuracy": 0.1483994260430336,
|
||
|
|
"num_tokens": 4365881.0,
|
||
|
|
"step": 2110
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.93496618270874,
|
||
|
|
"epoch": 1.9213993639254885,
|
||
|
|
"grad_norm": 1.1484375,
|
||
|
|
"learning_rate": 0.0004863609108921372,
|
||
|
|
"loss": 5.8826,
|
||
|
|
"mean_token_accuracy": 0.14093863144516944,
|
||
|
|
"num_tokens": 4376368.0,
|
||
|
|
"step": 2115
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.822841024398803,
|
||
|
|
"epoch": 1.9259427532939573,
|
||
|
|
"grad_norm": 1.140625,
|
||
|
|
"learning_rate": 0.0004862394689213728,
|
||
|
|
"loss": 5.8036,
|
||
|
|
"mean_token_accuracy": 0.15454284250736236,
|
||
|
|
"num_tokens": 4386695.0,
|
||
|
|
"step": 2120
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.945070791244507,
|
||
|
|
"epoch": 1.930486142662426,
|
||
|
|
"grad_norm": 1.1484375,
|
||
|
|
"learning_rate": 0.0004861175057382175,
|
||
|
|
"loss": 5.8144,
|
||
|
|
"mean_token_accuracy": 0.14849908351898194,
|
||
|
|
"num_tokens": 4396837.0,
|
||
|
|
"step": 2125
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.75476770401001,
|
||
|
|
"epoch": 1.935029532030895,
|
||
|
|
"grad_norm": 1.0625,
|
||
|
|
"learning_rate": 0.0004859950216436034,
|
||
|
|
"loss": 5.7906,
|
||
|
|
"mean_token_accuracy": 0.1520374372601509,
|
||
|
|
"num_tokens": 4407310.0,
|
||
|
|
"step": 2130
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.8474101543426515,
|
||
|
|
"epoch": 1.939572921399364,
|
||
|
|
"grad_norm": 1.2421875,
|
||
|
|
"learning_rate": 0.0004858720169397478,
|
||
|
|
"loss": 5.8292,
|
||
|
|
"mean_token_accuracy": 0.15293561220169066,
|
||
|
|
"num_tokens": 4417544.0,
|
||
|
|
"step": 2135
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.841001033782959,
|
||
|
|
"epoch": 1.9441163107678328,
|
||
|
|
"grad_norm": 1.1640625,
|
||
|
|
"learning_rate": 0.0004857484919301525,
|
||
|
|
"loss": 5.7706,
|
||
|
|
"mean_token_accuracy": 0.1506148397922516,
|
||
|
|
"num_tokens": 4428228.0,
|
||
|
|
"step": 2140
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.782240533828736,
|
||
|
|
"epoch": 1.9486597001363015,
|
||
|
|
"grad_norm": 1.1484375,
|
||
|
|
"learning_rate": 0.0004856244469196034,
|
||
|
|
"loss": 5.7882,
|
||
|
|
"mean_token_accuracy": 0.1523190841078758,
|
||
|
|
"num_tokens": 4439088.0,
|
||
|
|
"step": 2145
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.873093318939209,
|
||
|
|
"epoch": 1.9532030895047705,
|
||
|
|
"grad_norm": 1.078125,
|
||
|
|
"learning_rate": 0.000485499882214169,
|
||
|
|
"loss": 5.8911,
|
||
|
|
"mean_token_accuracy": 0.14140778854489328,
|
||
|
|
"num_tokens": 4449715.0,
|
||
|
|
"step": 2150
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.786935186386108,
|
||
|
|
"epoch": 1.9577464788732395,
|
||
|
|
"grad_norm": 1.2109375,
|
||
|
|
"learning_rate": 0.0004853747981212003,
|
||
|
|
"loss": 5.7443,
|
||
|
|
"mean_token_accuracy": 0.15438926517963408,
|
||
|
|
"num_tokens": 4460233.0,
|
||
|
|
"step": 2155
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.798536014556885,
|
||
|
|
"epoch": 1.9622898682417085,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.0004852491949493301,
|
||
|
|
"loss": 5.6887,
|
||
|
|
"mean_token_accuracy": 0.15654485523700715,
|
||
|
|
"num_tokens": 4471401.0,
|
||
|
|
"step": 2160
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.7939526557922365,
|
||
|
|
"epoch": 1.9668332576101772,
|
||
|
|
"grad_norm": 1.21875,
|
||
|
|
"learning_rate": 0.0004851230730084716,
|
||
|
|
"loss": 5.7489,
|
||
|
|
"mean_token_accuracy": 0.1589686781167984,
|
||
|
|
"num_tokens": 4481185.0,
|
||
|
|
"step": 2165
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.780501890182495,
|
||
|
|
"epoch": 1.971376646978646,
|
||
|
|
"grad_norm": 1.1171875,
|
||
|
|
"learning_rate": 0.00048499643260981816,
|
||
|
|
"loss": 5.7891,
|
||
|
|
"mean_token_accuracy": 0.1477307014167309,
|
||
|
|
"num_tokens": 4492342.0,
|
||
|
|
"step": 2170
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.935231685638428,
|
||
|
|
"epoch": 1.975920036347115,
|
||
|
|
"grad_norm": 1.1953125,
|
||
|
|
"learning_rate": 0.0004848692740658424,
|
||
|
|
"loss": 5.8854,
|
||
|
|
"mean_token_accuracy": 0.1487235024571419,
|
||
|
|
"num_tokens": 4504277.0,
|
||
|
|
"step": 2175
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.8527364253997805,
|
||
|
|
"epoch": 1.980463425715584,
|
||
|
|
"grad_norm": 1.3515625,
|
||
|
|
"learning_rate": 0.0004847415976902954,
|
||
|
|
"loss": 5.8389,
|
||
|
|
"mean_token_accuracy": 0.1489283800125122,
|
||
|
|
"num_tokens": 4514178.0,
|
||
|
|
"step": 2180
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.838755083084107,
|
||
|
|
"epoch": 1.9850068150840527,
|
||
|
|
"grad_norm": 1.125,
|
||
|
|
"learning_rate": 0.00048461340379820587,
|
||
|
|
"loss": 5.7981,
|
||
|
|
"mean_token_accuracy": 0.15372906774282455,
|
||
|
|
"num_tokens": 4524559.0,
|
||
|
|
"step": 2185
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.845714664459228,
|
||
|
|
"epoch": 1.9895502044525215,
|
||
|
|
"grad_norm": 1.296875,
|
||
|
|
"learning_rate": 0.00048448469270587945,
|
||
|
|
"loss": 5.7546,
|
||
|
|
"mean_token_accuracy": 0.15459949672222137,
|
||
|
|
"num_tokens": 4535168.0,
|
||
|
|
"step": 2190
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.879129028320312,
|
||
|
|
"epoch": 1.9940935938209905,
|
||
|
|
"grad_norm": 1.2265625,
|
||
|
|
"learning_rate": 0.00048435546473089814,
|
||
|
|
"loss": 5.8311,
|
||
|
|
"mean_token_accuracy": 0.14930276274681092,
|
||
|
|
"num_tokens": 4546105.0,
|
||
|
|
"step": 2195
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.856486082077026,
|
||
|
|
"epoch": 1.9986369831894595,
|
||
|
|
"grad_norm": 1.265625,
|
||
|
|
"learning_rate": 0.00048422572019211896,
|
||
|
|
"loss": 5.77,
|
||
|
|
"mean_token_accuracy": 0.15297604352235794,
|
||
|
|
"num_tokens": 4556498.0,
|
||
|
|
"step": 2200
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.700125482347277,
|
||
|
|
"epoch": 2.0027260336210815,
|
||
|
|
"grad_norm": 1.28125,
|
||
|
|
"learning_rate": 0.00048409545940967375,
|
||
|
|
"loss": 5.5762,
|
||
|
|
"mean_token_accuracy": 0.14985370801554787,
|
||
|
|
"num_tokens": 4565029.0,
|
||
|
|
"step": 2205
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.850874900817871,
|
||
|
|
"epoch": 2.00726942298955,
|
||
|
|
"grad_norm": 1.171875,
|
||
|
|
"learning_rate": 0.000483964682704968,
|
||
|
|
"loss": 5.5442,
|
||
|
|
"mean_token_accuracy": 0.154378442466259,
|
||
|
|
"num_tokens": 4575232.0,
|
||
|
|
"step": 2210
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.784826231002808,
|
||
|
|
"epoch": 2.011812812358019,
|
||
|
|
"grad_norm": 1.1796875,
|
||
|
|
"learning_rate": 0.00048383339040068024,
|
||
|
|
"loss": 5.5174,
|
||
|
|
"mean_token_accuracy": 0.15894271433353424,
|
||
|
|
"num_tokens": 4585818.0,
|
||
|
|
"step": 2215
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.703923082351684,
|
||
|
|
"epoch": 2.016356201726488,
|
||
|
|
"grad_norm": 1.15625,
|
||
|
|
"learning_rate": 0.0004837015828207612,
|
||
|
|
"loss": 5.481,
|
||
|
|
"mean_token_accuracy": 0.16246529668569565,
|
||
|
|
"num_tokens": 4595823.0,
|
||
|
|
"step": 2220
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.780557489395141,
|
||
|
|
"epoch": 2.020899591094957,
|
||
|
|
"grad_norm": 1.125,
|
||
|
|
"learning_rate": 0.0004835692602904329,
|
||
|
|
"loss": 5.4601,
|
||
|
|
"mean_token_accuracy": 0.16049877256155015,
|
||
|
|
"num_tokens": 4606537.0,
|
||
|
|
"step": 2225
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.799535465240479,
|
||
|
|
"epoch": 2.0254429804634255,
|
||
|
|
"grad_norm": 1.1640625,
|
||
|
|
"learning_rate": 0.0004834364231361882,
|
||
|
|
"loss": 5.4903,
|
||
|
|
"mean_token_accuracy": 0.15943138301372528,
|
||
|
|
"num_tokens": 4616096.0,
|
||
|
|
"step": 2230
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.776993227005005,
|
||
|
|
"epoch": 2.0299863698318945,
|
||
|
|
"grad_norm": 1.1328125,
|
||
|
|
"learning_rate": 0.0004833030716857894,
|
||
|
|
"loss": 5.5149,
|
||
|
|
"mean_token_accuracy": 0.15986263900995254,
|
||
|
|
"num_tokens": 4626287.0,
|
||
|
|
"step": 2235
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.737018346786499,
|
||
|
|
"epoch": 2.0345297592003635,
|
||
|
|
"grad_norm": 1.078125,
|
||
|
|
"learning_rate": 0.00048316920626826807,
|
||
|
|
"loss": 5.5113,
|
||
|
|
"mean_token_accuracy": 0.15839564353227614,
|
||
|
|
"num_tokens": 4636898.0,
|
||
|
|
"step": 2240
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.675017547607422,
|
||
|
|
"epoch": 2.0390731485688325,
|
||
|
|
"grad_norm": 1.2421875,
|
||
|
|
"learning_rate": 0.00048303482721392363,
|
||
|
|
"loss": 5.4703,
|
||
|
|
"mean_token_accuracy": 0.16265783458948135,
|
||
|
|
"num_tokens": 4646263.0,
|
||
|
|
"step": 2245
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.818978929519654,
|
||
|
|
"epoch": 2.043616537937301,
|
||
|
|
"grad_norm": 1.28125,
|
||
|
|
"learning_rate": 0.00048289993485432325,
|
||
|
|
"loss": 5.51,
|
||
|
|
"mean_token_accuracy": 0.1600583478808403,
|
||
|
|
"num_tokens": 4656463.0,
|
||
|
|
"step": 2250
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.7211040496826175,
|
||
|
|
"epoch": 2.04815992730577,
|
||
|
|
"grad_norm": 1.2421875,
|
||
|
|
"learning_rate": 0.00048276452952230036,
|
||
|
|
"loss": 5.5389,
|
||
|
|
"mean_token_accuracy": 0.16089007407426834,
|
||
|
|
"num_tokens": 4666824.0,
|
||
|
|
"step": 2255
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.666584920883179,
|
||
|
|
"epoch": 2.052703316674239,
|
||
|
|
"grad_norm": 1.171875,
|
||
|
|
"learning_rate": 0.00048262861155195407,
|
||
|
|
"loss": 5.4265,
|
||
|
|
"mean_token_accuracy": 0.16442574113607406,
|
||
|
|
"num_tokens": 4676793.0,
|
||
|
|
"step": 2260
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.815246295928955,
|
||
|
|
"epoch": 2.057246706042708,
|
||
|
|
"grad_norm": 1.1875,
|
||
|
|
"learning_rate": 0.0004824921812786486,
|
||
|
|
"loss": 5.581,
|
||
|
|
"mean_token_accuracy": 0.15934282541275024,
|
||
|
|
"num_tokens": 4687124.0,
|
||
|
|
"step": 2265
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.7452959537506105,
|
||
|
|
"epoch": 2.0617900954111765,
|
||
|
|
"grad_norm": 1.203125,
|
||
|
|
"learning_rate": 0.000482355239039012,
|
||
|
|
"loss": 5.7288,
|
||
|
|
"mean_token_accuracy": 0.15075535774230958,
|
||
|
|
"num_tokens": 4698074.0,
|
||
|
|
"step": 2270
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.82332558631897,
|
||
|
|
"epoch": 2.0663334847796455,
|
||
|
|
"grad_norm": 1.453125,
|
||
|
|
"learning_rate": 0.0004822177851709356,
|
||
|
|
"loss": 5.5919,
|
||
|
|
"mean_token_accuracy": 0.15656624138355255,
|
||
|
|
"num_tokens": 4709177.0,
|
||
|
|
"step": 2275
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.848820304870605,
|
||
|
|
"epoch": 2.0708768741481145,
|
||
|
|
"grad_norm": 1.1953125,
|
||
|
|
"learning_rate": 0.00048207982001357327,
|
||
|
|
"loss": 5.5109,
|
||
|
|
"mean_token_accuracy": 0.15775267779827118,
|
||
|
|
"num_tokens": 4719649.0,
|
||
|
|
"step": 2280
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.709406423568725,
|
||
|
|
"epoch": 2.0754202635165835,
|
||
|
|
"grad_norm": 1.0625,
|
||
|
|
"learning_rate": 0.0004819413439073402,
|
||
|
|
"loss": 5.5799,
|
||
|
|
"mean_token_accuracy": 0.15765960812568663,
|
||
|
|
"num_tokens": 4731685.0,
|
||
|
|
"step": 2285
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.7174700736999515,
|
||
|
|
"epoch": 2.079963652885052,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.0004818023571939125,
|
||
|
|
"loss": 5.5289,
|
||
|
|
"mean_token_accuracy": 0.15760382562875747,
|
||
|
|
"num_tokens": 4742854.0,
|
||
|
|
"step": 2290
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.7340339660644535,
|
||
|
|
"epoch": 2.084507042253521,
|
||
|
|
"grad_norm": 1.2265625,
|
||
|
|
"learning_rate": 0.000481662860216226,
|
||
|
|
"loss": 5.5131,
|
||
|
|
"mean_token_accuracy": 0.15671638399362564,
|
||
|
|
"num_tokens": 4754088.0,
|
||
|
|
"step": 2295
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.714247369766236,
|
||
|
|
"epoch": 2.08905043162199,
|
||
|
|
"grad_norm": 1.3046875,
|
||
|
|
"learning_rate": 0.00048152285331847574,
|
||
|
|
"loss": 5.5341,
|
||
|
|
"mean_token_accuracy": 0.15981189608573915,
|
||
|
|
"num_tokens": 4764090.0,
|
||
|
|
"step": 2300
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.711434459686279,
|
||
|
|
"epoch": 2.093593820990459,
|
||
|
|
"grad_norm": 1.125,
|
||
|
|
"learning_rate": 0.0004813823368461148,
|
||
|
|
"loss": 5.5242,
|
||
|
|
"mean_token_accuracy": 0.16334791630506515,
|
||
|
|
"num_tokens": 4773704.0,
|
||
|
|
"step": 2305
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.770476484298706,
|
||
|
|
"epoch": 2.098137210358928,
|
||
|
|
"grad_norm": 1.2109375,
|
||
|
|
"learning_rate": 0.0004812413111458534,
|
||
|
|
"loss": 5.554,
|
||
|
|
"mean_token_accuracy": 0.1621487781405449,
|
||
|
|
"num_tokens": 4783678.0,
|
||
|
|
"step": 2310
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.663452053070069,
|
||
|
|
"epoch": 2.1026805997273965,
|
||
|
|
"grad_norm": 1.0546875,
|
||
|
|
"learning_rate": 0.0004810997765656587,
|
||
|
|
"loss": 5.4558,
|
||
|
|
"mean_token_accuracy": 0.16795776933431625,
|
||
|
|
"num_tokens": 4794183.0,
|
||
|
|
"step": 2315
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.65028862953186,
|
||
|
|
"epoch": 2.1072239890958655,
|
||
|
|
"grad_norm": 1.0703125,
|
||
|
|
"learning_rate": 0.00048095773345475294,
|
||
|
|
"loss": 5.4312,
|
||
|
|
"mean_token_accuracy": 0.16061999499797822,
|
||
|
|
"num_tokens": 4803670.0,
|
||
|
|
"step": 2320
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.70339150428772,
|
||
|
|
"epoch": 2.1117673784643345,
|
||
|
|
"grad_norm": 1.1875,
|
||
|
|
"learning_rate": 0.00048081518216361367,
|
||
|
|
"loss": 5.4528,
|
||
|
|
"mean_token_accuracy": 0.16460076123476028,
|
||
|
|
"num_tokens": 4813611.0,
|
||
|
|
"step": 2325
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.655531644821167,
|
||
|
|
"epoch": 2.1163107678328035,
|
||
|
|
"grad_norm": 1.203125,
|
||
|
|
"learning_rate": 0.0004806721230439719,
|
||
|
|
"loss": 5.5207,
|
||
|
|
"mean_token_accuracy": 0.15569410920143129,
|
||
|
|
"num_tokens": 4824356.0,
|
||
|
|
"step": 2330
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.789508867263794,
|
||
|
|
"epoch": 2.120854157201272,
|
||
|
|
"grad_norm": 1.1484375,
|
||
|
|
"learning_rate": 0.0004805285564488117,
|
||
|
|
"loss": 5.5484,
|
||
|
|
"mean_token_accuracy": 0.15906214267015456,
|
||
|
|
"num_tokens": 4834410.0,
|
||
|
|
"step": 2335
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.648446416854858,
|
||
|
|
"epoch": 2.125397546569741,
|
||
|
|
"grad_norm": 1.2421875,
|
||
|
|
"learning_rate": 0.0004803844827323696,
|
||
|
|
"loss": 5.4117,
|
||
|
|
"mean_token_accuracy": 0.1643962562084198,
|
||
|
|
"num_tokens": 4844975.0,
|
||
|
|
"step": 2340
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.662750911712647,
|
||
|
|
"epoch": 2.12994093593821,
|
||
|
|
"grad_norm": 1.1484375,
|
||
|
|
"learning_rate": 0.0004802399022501329,
|
||
|
|
"loss": 5.5309,
|
||
|
|
"mean_token_accuracy": 0.16364205926656722,
|
||
|
|
"num_tokens": 4856419.0,
|
||
|
|
"step": 2345
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.66937484741211,
|
||
|
|
"epoch": 2.134484325306679,
|
||
|
|
"grad_norm": 1.171875,
|
||
|
|
"learning_rate": 0.0004800948153588397,
|
||
|
|
"loss": 5.4444,
|
||
|
|
"mean_token_accuracy": 0.165959732234478,
|
||
|
|
"num_tokens": 4867115.0,
|
||
|
|
"step": 2350
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.703761243820191,
|
||
|
|
"epoch": 2.1390277146751475,
|
||
|
|
"grad_norm": 1.171875,
|
||
|
|
"learning_rate": 0.00047994922241647746,
|
||
|
|
"loss": 5.5108,
|
||
|
|
"mean_token_accuracy": 0.16079539358615874,
|
||
|
|
"num_tokens": 4876675.0,
|
||
|
|
"step": 2355
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.720136308670044,
|
||
|
|
"epoch": 2.1435711040436165,
|
||
|
|
"grad_norm": 1.1171875,
|
||
|
|
"learning_rate": 0.00047980312378228244,
|
||
|
|
"loss": 5.5404,
|
||
|
|
"mean_token_accuracy": 0.1617947369813919,
|
||
|
|
"num_tokens": 4887868.0,
|
||
|
|
"step": 2360
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.6826314449310305,
|
||
|
|
"epoch": 2.1481144934120855,
|
||
|
|
"grad_norm": 1.21875,
|
||
|
|
"learning_rate": 0.00047965651981673823,
|
||
|
|
"loss": 5.5123,
|
||
|
|
"mean_token_accuracy": 0.16172491312026976,
|
||
|
|
"num_tokens": 4896878.0,
|
||
|
|
"step": 2365
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.664020633697509,
|
||
|
|
"epoch": 2.1526578827805545,
|
||
|
|
"grad_norm": 1.3125,
|
||
|
|
"learning_rate": 0.00047950941088157576,
|
||
|
|
"loss": 5.4854,
|
||
|
|
"mean_token_accuracy": 0.16069988757371903,
|
||
|
|
"num_tokens": 4906683.0,
|
||
|
|
"step": 2370
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.680099058151245,
|
||
|
|
"epoch": 2.157201272149023,
|
||
|
|
"grad_norm": 1.1171875,
|
||
|
|
"learning_rate": 0.0004793617973397715,
|
||
|
|
"loss": 5.4707,
|
||
|
|
"mean_token_accuracy": 0.16708637923002242,
|
||
|
|
"num_tokens": 4917184.0,
|
||
|
|
"step": 2375
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.683479261398316,
|
||
|
|
"epoch": 2.161744661517492,
|
||
|
|
"grad_norm": 1.2265625,
|
||
|
|
"learning_rate": 0.00047921367955554745,
|
||
|
|
"loss": 5.5037,
|
||
|
|
"mean_token_accuracy": 0.15707164853811265,
|
||
|
|
"num_tokens": 4927337.0,
|
||
|
|
"step": 2380
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.729428672790528,
|
||
|
|
"epoch": 2.166288050885961,
|
||
|
|
"grad_norm": 1.0703125,
|
||
|
|
"learning_rate": 0.0004790650578943693,
|
||
|
|
"loss": 5.5124,
|
||
|
|
"mean_token_accuracy": 0.15443907007575036,
|
||
|
|
"num_tokens": 4937661.0,
|
||
|
|
"step": 2385
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.729527378082276,
|
||
|
|
"epoch": 2.17083144025443,
|
||
|
|
"grad_norm": 1.2578125,
|
||
|
|
"learning_rate": 0.00047891593272294636,
|
||
|
|
"loss": 5.5584,
|
||
|
|
"mean_token_accuracy": 0.15152359902858734,
|
||
|
|
"num_tokens": 4948068.0,
|
||
|
|
"step": 2390
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.660752439498902,
|
||
|
|
"epoch": 2.1753748296228985,
|
||
|
|
"grad_norm": 1.2890625,
|
||
|
|
"learning_rate": 0.00047876630440923,
|
||
|
|
"loss": 5.4923,
|
||
|
|
"mean_token_accuracy": 0.16463814526796341,
|
||
|
|
"num_tokens": 4958703.0,
|
||
|
|
"step": 2395
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.6649699211120605,
|
||
|
|
"epoch": 2.1799182189913675,
|
||
|
|
"grad_norm": 1.0546875,
|
||
|
|
"learning_rate": 0.0004786161733224134,
|
||
|
|
"loss": 5.5129,
|
||
|
|
"mean_token_accuracy": 0.1626749038696289,
|
||
|
|
"num_tokens": 4969190.0,
|
||
|
|
"step": 2400
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.644364356994629,
|
||
|
|
"epoch": 2.1844616083598365,
|
||
|
|
"grad_norm": 1.1875,
|
||
|
|
"learning_rate": 0.00047846553983293006,
|
||
|
|
"loss": 5.4013,
|
||
|
|
"mean_token_accuracy": 0.16723495423793794,
|
||
|
|
"num_tokens": 4978663.0,
|
||
|
|
"step": 2405
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.743815612792969,
|
||
|
|
"epoch": 2.1890049977283055,
|
||
|
|
"grad_norm": 1.15625,
|
||
|
|
"learning_rate": 0.00047831440431245307,
|
||
|
|
"loss": 5.5922,
|
||
|
|
"mean_token_accuracy": 0.16085838675498962,
|
||
|
|
"num_tokens": 4989839.0,
|
||
|
|
"step": 2410
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.603341817855835,
|
||
|
|
"epoch": 2.193548387096774,
|
||
|
|
"grad_norm": 1.3125,
|
||
|
|
"learning_rate": 0.00047816276713389424,
|
||
|
|
"loss": 5.3917,
|
||
|
|
"mean_token_accuracy": 0.16587418615818023,
|
||
|
|
"num_tokens": 5000030.0,
|
||
|
|
"step": 2415
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.701595258712769,
|
||
|
|
"epoch": 2.198091776465243,
|
||
|
|
"grad_norm": 1.25,
|
||
|
|
"learning_rate": 0.0004780106286714034,
|
||
|
|
"loss": 5.5925,
|
||
|
|
"mean_token_accuracy": 0.16056383699178695,
|
||
|
|
"num_tokens": 5010229.0,
|
||
|
|
"step": 2420
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.726330900192261,
|
||
|
|
"epoch": 2.202635165833712,
|
||
|
|
"grad_norm": 1.0546875,
|
||
|
|
"learning_rate": 0.000477857989300367,
|
||
|
|
"loss": 5.5118,
|
||
|
|
"mean_token_accuracy": 0.1618313744664192,
|
||
|
|
"num_tokens": 5021000.0,
|
||
|
|
"step": 2425
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.677479362487793,
|
||
|
|
"epoch": 2.207178555202181,
|
||
|
|
"grad_norm": 1.1875,
|
||
|
|
"learning_rate": 0.00047770484939740757,
|
||
|
|
"loss": 5.4199,
|
||
|
|
"mean_token_accuracy": 0.16339841037988662,
|
||
|
|
"num_tokens": 5031319.0,
|
||
|
|
"step": 2430
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.613199663162232,
|
||
|
|
"epoch": 2.2117219445706495,
|
||
|
|
"grad_norm": 1.171875,
|
||
|
|
"learning_rate": 0.0004775512093403824,
|
||
|
|
"loss": 5.4571,
|
||
|
|
"mean_token_accuracy": 0.16850902140140533,
|
||
|
|
"num_tokens": 5041892.0,
|
||
|
|
"step": 2435
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.629352140426636,
|
||
|
|
"epoch": 2.2162653339391185,
|
||
|
|
"grad_norm": 1.1171875,
|
||
|
|
"learning_rate": 0.00047739706950838327,
|
||
|
|
"loss": 5.5338,
|
||
|
|
"mean_token_accuracy": 0.16332726627588273,
|
||
|
|
"num_tokens": 5052363.0,
|
||
|
|
"step": 2440
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.762828731536866,
|
||
|
|
"epoch": 2.2208087233075875,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.00047724243028173484,
|
||
|
|
"loss": 5.5622,
|
||
|
|
"mean_token_accuracy": 0.15506864935159684,
|
||
|
|
"num_tokens": 5063342.0,
|
||
|
|
"step": 2445
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.688890409469605,
|
||
|
|
"epoch": 2.2253521126760565,
|
||
|
|
"grad_norm": 1.4921875,
|
||
|
|
"learning_rate": 0.00047708729204199406,
|
||
|
|
"loss": 5.4758,
|
||
|
|
"mean_token_accuracy": 0.15885344594717027,
|
||
|
|
"num_tokens": 5073393.0,
|
||
|
|
"step": 2450
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.57670488357544,
|
||
|
|
"epoch": 2.229895502044525,
|
||
|
|
"grad_norm": 1.328125,
|
||
|
|
"learning_rate": 0.000476931655171949,
|
||
|
|
"loss": 5.4403,
|
||
|
|
"mean_token_accuracy": 0.1676219493150711,
|
||
|
|
"num_tokens": 5082417.0,
|
||
|
|
"step": 2455
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.78955774307251,
|
||
|
|
"epoch": 2.234438891412994,
|
||
|
|
"grad_norm": 1.1171875,
|
||
|
|
"learning_rate": 0.0004767755200556183,
|
||
|
|
"loss": 5.6069,
|
||
|
|
"mean_token_accuracy": 0.15390974432229995,
|
||
|
|
"num_tokens": 5093383.0,
|
||
|
|
"step": 2460
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.580852699279785,
|
||
|
|
"epoch": 2.238982280781463,
|
||
|
|
"grad_norm": 1.25,
|
||
|
|
"learning_rate": 0.0004766188870782497,
|
||
|
|
"loss": 5.3906,
|
||
|
|
"mean_token_accuracy": 0.16938741654157638,
|
||
|
|
"num_tokens": 5104346.0,
|
||
|
|
"step": 2465
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.638398218154907,
|
||
|
|
"epoch": 2.243525670149932,
|
||
|
|
"grad_norm": 1.5625,
|
||
|
|
"learning_rate": 0.00047646175662631967,
|
||
|
|
"loss": 5.561,
|
||
|
|
"mean_token_accuracy": 0.15911775380373,
|
||
|
|
"num_tokens": 5114375.0,
|
||
|
|
"step": 2470
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.732828569412232,
|
||
|
|
"epoch": 2.2480690595184005,
|
||
|
|
"grad_norm": 1.2109375,
|
||
|
|
"learning_rate": 0.00047630412908753183,
|
||
|
|
"loss": 5.5355,
|
||
|
|
"mean_token_accuracy": 0.1595481425523758,
|
||
|
|
"num_tokens": 5125035.0,
|
||
|
|
"step": 2475
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.6798309803009035,
|
||
|
|
"epoch": 2.2526124488868695,
|
||
|
|
"grad_norm": 1.1875,
|
||
|
|
"learning_rate": 0.00047614600485081657,
|
||
|
|
"loss": 5.5463,
|
||
|
|
"mean_token_accuracy": 0.152773617208004,
|
||
|
|
"num_tokens": 5135869.0,
|
||
|
|
"step": 2480
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.720887184143066,
|
||
|
|
"epoch": 2.2571558382553385,
|
||
|
|
"grad_norm": 1.21875,
|
||
|
|
"learning_rate": 0.00047598738430632963,
|
||
|
|
"loss": 5.5134,
|
||
|
|
"mean_token_accuracy": 0.15898497104644777,
|
||
|
|
"num_tokens": 5146615.0,
|
||
|
|
"step": 2485
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.560636568069458,
|
||
|
|
"epoch": 2.2616992276238075,
|
||
|
|
"grad_norm": 1.3359375,
|
||
|
|
"learning_rate": 0.00047582826784545146,
|
||
|
|
"loss": 5.4127,
|
||
|
|
"mean_token_accuracy": 0.16486843973398208,
|
||
|
|
"num_tokens": 5157490.0,
|
||
|
|
"step": 2490
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.648875522613525,
|
||
|
|
"epoch": 2.266242616992276,
|
||
|
|
"grad_norm": 1.4765625,
|
||
|
|
"learning_rate": 0.00047566865586078615,
|
||
|
|
"loss": 5.55,
|
||
|
|
"mean_token_accuracy": 0.15591932386159896,
|
||
|
|
"num_tokens": 5168693.0,
|
||
|
|
"step": 2495
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.7419291019439695,
|
||
|
|
"epoch": 2.270786006360745,
|
||
|
|
"grad_norm": 1.265625,
|
||
|
|
"learning_rate": 0.00047550854874616047,
|
||
|
|
"loss": 5.5106,
|
||
|
|
"mean_token_accuracy": 0.15850055515766143,
|
||
|
|
"num_tokens": 5179232.0,
|
||
|
|
"step": 2500
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 2.270786006360745,
|
||
|
|
"eval_entropy": 5.491250712372536,
|
||
|
|
"eval_loss": 5.986842632293701,
|
||
|
|
"eval_mean_token_accuracy": 0.14950340444785218,
|
||
|
|
"eval_num_tokens": 5179232.0,
|
||
|
|
"eval_runtime": 2.5975,
|
||
|
|
"eval_samples_per_second": 1322.426,
|
||
|
|
"eval_steps_per_second": 165.544,
|
||
|
|
"step": 2500
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.627499151229858,
|
||
|
|
"epoch": 2.275329395729214,
|
||
|
|
"grad_norm": 1.2109375,
|
||
|
|
"learning_rate": 0.00047534794689662257,
|
||
|
|
"loss": 5.5545,
|
||
|
|
"mean_token_accuracy": 0.1652067631483078,
|
||
|
|
"num_tokens": 5188613.0,
|
||
|
|
"step": 2505
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.633312320709228,
|
||
|
|
"epoch": 2.279872785097683,
|
||
|
|
"grad_norm": 1.171875,
|
||
|
|
"learning_rate": 0.0004751868507084418,
|
||
|
|
"loss": 5.4399,
|
||
|
|
"mean_token_accuracy": 0.1668851926922798,
|
||
|
|
"num_tokens": 5198441.0,
|
||
|
|
"step": 2510
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.610636854171753,
|
||
|
|
"epoch": 2.284416174466152,
|
||
|
|
"grad_norm": 1.421875,
|
||
|
|
"learning_rate": 0.0004750252605791068,
|
||
|
|
"loss": 5.5087,
|
||
|
|
"mean_token_accuracy": 0.16499845832586288,
|
||
|
|
"num_tokens": 5208466.0,
|
||
|
|
"step": 2515
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.565611696243286,
|
||
|
|
"epoch": 2.2889595638346205,
|
||
|
|
"grad_norm": 1.296875,
|
||
|
|
"learning_rate": 0.0004748631769073254,
|
||
|
|
"loss": 5.4865,
|
||
|
|
"mean_token_accuracy": 0.16280112117528917,
|
||
|
|
"num_tokens": 5218847.0,
|
||
|
|
"step": 2520
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.737601947784424,
|
||
|
|
"epoch": 2.2935029532030895,
|
||
|
|
"grad_norm": 1.1796875,
|
||
|
|
"learning_rate": 0.0004747006000930227,
|
||
|
|
"loss": 5.5237,
|
||
|
|
"mean_token_accuracy": 0.15756618082523347,
|
||
|
|
"num_tokens": 5228870.0,
|
||
|
|
"step": 2525
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.713624429702759,
|
||
|
|
"epoch": 2.2980463425715585,
|
||
|
|
"grad_norm": 1.171875,
|
||
|
|
"learning_rate": 0.0004745375305373409,
|
||
|
|
"loss": 5.4729,
|
||
|
|
"mean_token_accuracy": 0.16696099787950516,
|
||
|
|
"num_tokens": 5238186.0,
|
||
|
|
"step": 2530
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.617369508743286,
|
||
|
|
"epoch": 2.302589731940027,
|
||
|
|
"grad_norm": 1.2265625,
|
||
|
|
"learning_rate": 0.00047437396864263804,
|
||
|
|
"loss": 5.5339,
|
||
|
|
"mean_token_accuracy": 0.16417384147644043,
|
||
|
|
"num_tokens": 5247478.0,
|
||
|
|
"step": 2535
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.709841299057007,
|
||
|
|
"epoch": 2.307133121308496,
|
||
|
|
"grad_norm": 1.2109375,
|
||
|
|
"learning_rate": 0.0004742099148124866,
|
||
|
|
"loss": 5.4687,
|
||
|
|
"mean_token_accuracy": 0.1602501317858696,
|
||
|
|
"num_tokens": 5258519.0,
|
||
|
|
"step": 2540
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.698099279403687,
|
||
|
|
"epoch": 2.311676510676965,
|
||
|
|
"grad_norm": 1.203125,
|
||
|
|
"learning_rate": 0.0004740453694516734,
|
||
|
|
"loss": 5.5135,
|
||
|
|
"mean_token_accuracy": 0.1668350026011467,
|
||
|
|
"num_tokens": 5268218.0,
|
||
|
|
"step": 2545
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.506252813339233,
|
||
|
|
"epoch": 2.316219900045434,
|
||
|
|
"grad_norm": 1.34375,
|
||
|
|
"learning_rate": 0.00047388033296619746,
|
||
|
|
"loss": 5.4552,
|
||
|
|
"mean_token_accuracy": 0.1638593629002571,
|
||
|
|
"num_tokens": 5277926.0,
|
||
|
|
"step": 2550
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.658507204055786,
|
||
|
|
"epoch": 2.320763289413903,
|
||
|
|
"grad_norm": 1.203125,
|
||
|
|
"learning_rate": 0.0004737148057632701,
|
||
|
|
"loss": 5.4999,
|
||
|
|
"mean_token_accuracy": 0.16297332048416138,
|
||
|
|
"num_tokens": 5287735.0,
|
||
|
|
"step": 2555
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.676133441925049,
|
||
|
|
"epoch": 2.3253066787823715,
|
||
|
|
"grad_norm": 1.1484375,
|
||
|
|
"learning_rate": 0.0004735487882513131,
|
||
|
|
"loss": 5.4182,
|
||
|
|
"mean_token_accuracy": 0.17203330993652344,
|
||
|
|
"num_tokens": 5297120.0,
|
||
|
|
"step": 2560
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.489224767684936,
|
||
|
|
"epoch": 2.3298500681508405,
|
||
|
|
"grad_norm": 1.1484375,
|
||
|
|
"learning_rate": 0.0004733822808399583,
|
||
|
|
"loss": 5.4428,
|
||
|
|
"mean_token_accuracy": 0.16497790664434434,
|
||
|
|
"num_tokens": 5307448.0,
|
||
|
|
"step": 2565
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.675883531570435,
|
||
|
|
"epoch": 2.3343934575193095,
|
||
|
|
"grad_norm": 1.171875,
|
||
|
|
"learning_rate": 0.00047321528394004615,
|
||
|
|
"loss": 5.4505,
|
||
|
|
"mean_token_accuracy": 0.16972960382699967,
|
||
|
|
"num_tokens": 5317914.0,
|
||
|
|
"step": 2570
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.675877332687378,
|
||
|
|
"epoch": 2.3389368468877785,
|
||
|
|
"grad_norm": 1.1171875,
|
||
|
|
"learning_rate": 0.00047304779796362485,
|
||
|
|
"loss": 5.4562,
|
||
|
|
"mean_token_accuracy": 0.16813937127590178,
|
||
|
|
"num_tokens": 5328471.0,
|
||
|
|
"step": 2575
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.571584844589234,
|
||
|
|
"epoch": 2.343480236256247,
|
||
|
|
"grad_norm": 1.2109375,
|
||
|
|
"learning_rate": 0.00047287982332394943,
|
||
|
|
"loss": 5.462,
|
||
|
|
"mean_token_accuracy": 0.1582278087735176,
|
||
|
|
"num_tokens": 5339118.0,
|
||
|
|
"step": 2580
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.678888940811158,
|
||
|
|
"epoch": 2.348023625624716,
|
||
|
|
"grad_norm": 1.2734375,
|
||
|
|
"learning_rate": 0.00047271136043548057,
|
||
|
|
"loss": 5.568,
|
||
|
|
"mean_token_accuracy": 0.15406795740127563,
|
||
|
|
"num_tokens": 5350183.0,
|
||
|
|
"step": 2585
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.663352632522583,
|
||
|
|
"epoch": 2.352567014993185,
|
||
|
|
"grad_norm": 1.3125,
|
||
|
|
"learning_rate": 0.0004725424097138838,
|
||
|
|
"loss": 5.4974,
|
||
|
|
"mean_token_accuracy": 0.15896444842219354,
|
||
|
|
"num_tokens": 5361317.0,
|
||
|
|
"step": 2590
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.649419784545898,
|
||
|
|
"epoch": 2.357110404361654,
|
||
|
|
"grad_norm": 1.296875,
|
||
|
|
"learning_rate": 0.00047237297157602816,
|
||
|
|
"loss": 5.4983,
|
||
|
|
"mean_token_accuracy": 0.16494401395320893,
|
||
|
|
"num_tokens": 5371338.0,
|
||
|
|
"step": 2595
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.732968187332153,
|
||
|
|
"epoch": 2.3616537937301225,
|
||
|
|
"grad_norm": 1.2265625,
|
||
|
|
"learning_rate": 0.0004722030464399854,
|
||
|
|
"loss": 5.6042,
|
||
|
|
"mean_token_accuracy": 0.15870766192674637,
|
||
|
|
"num_tokens": 5382043.0,
|
||
|
|
"step": 2600
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.698143482208252,
|
||
|
|
"epoch": 2.3661971830985915,
|
||
|
|
"grad_norm": 1.2109375,
|
||
|
|
"learning_rate": 0.000472032634725029,
|
||
|
|
"loss": 5.5121,
|
||
|
|
"mean_token_accuracy": 0.16373514086008073,
|
||
|
|
"num_tokens": 5392547.0,
|
||
|
|
"step": 2605
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.527518653869629,
|
||
|
|
"epoch": 2.3707405724670605,
|
||
|
|
"grad_norm": 1.296875,
|
||
|
|
"learning_rate": 0.00047186173685163273,
|
||
|
|
"loss": 5.3983,
|
||
|
|
"mean_token_accuracy": 0.17403582781553267,
|
||
|
|
"num_tokens": 5402455.0,
|
||
|
|
"step": 2610
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.584602308273316,
|
||
|
|
"epoch": 2.3752839618355295,
|
||
|
|
"grad_norm": 1.15625,
|
||
|
|
"learning_rate": 0.00047169035324147023,
|
||
|
|
"loss": 5.5633,
|
||
|
|
"mean_token_accuracy": 0.15951344221830369,
|
||
|
|
"num_tokens": 5413925.0,
|
||
|
|
"step": 2615
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.713425874710083,
|
||
|
|
"epoch": 2.379827351203998,
|
||
|
|
"grad_norm": 1.296875,
|
||
|
|
"learning_rate": 0.00047151848431741363,
|
||
|
|
"loss": 5.5907,
|
||
|
|
"mean_token_accuracy": 0.1547597050666809,
|
||
|
|
"num_tokens": 5425344.0,
|
||
|
|
"step": 2620
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.61894736289978,
|
||
|
|
"epoch": 2.384370740572467,
|
||
|
|
"grad_norm": 1.2578125,
|
||
|
|
"learning_rate": 0.0004713461305035322,
|
||
|
|
"loss": 5.5202,
|
||
|
|
"mean_token_accuracy": 0.16069943457841873,
|
||
|
|
"num_tokens": 5435197.0,
|
||
|
|
"step": 2625
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.728053712844849,
|
||
|
|
"epoch": 2.388914129940936,
|
||
|
|
"grad_norm": 1.25,
|
||
|
|
"learning_rate": 0.000471173292225092,
|
||
|
|
"loss": 5.5248,
|
||
|
|
"mean_token_accuracy": 0.16462774872779845,
|
||
|
|
"num_tokens": 5445683.0,
|
||
|
|
"step": 2630
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.610408639907837,
|
||
|
|
"epoch": 2.393457519309405,
|
||
|
|
"grad_norm": 1.1328125,
|
||
|
|
"learning_rate": 0.00047099996990855424,
|
||
|
|
"loss": 5.3851,
|
||
|
|
"mean_token_accuracy": 0.1635379433631897,
|
||
|
|
"num_tokens": 5456846.0,
|
||
|
|
"step": 2635
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.581979417800904,
|
||
|
|
"epoch": 2.3980009086778735,
|
||
|
|
"grad_norm": 1.15625,
|
||
|
|
"learning_rate": 0.00047082616398157456,
|
||
|
|
"loss": 5.4559,
|
||
|
|
"mean_token_accuracy": 0.1690095007419586,
|
||
|
|
"num_tokens": 5467701.0,
|
||
|
|
"step": 2640
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.623260831832885,
|
||
|
|
"epoch": 2.4025442980463425,
|
||
|
|
"grad_norm": 1.2890625,
|
||
|
|
"learning_rate": 0.0004706518748730017,
|
||
|
|
"loss": 5.5023,
|
||
|
|
"mean_token_accuracy": 0.15982526838779448,
|
||
|
|
"num_tokens": 5478246.0,
|
||
|
|
"step": 2645
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.644440841674805,
|
||
|
|
"epoch": 2.4070876874148115,
|
||
|
|
"grad_norm": 1.21875,
|
||
|
|
"learning_rate": 0.0004704771030128768,
|
||
|
|
"loss": 5.505,
|
||
|
|
"mean_token_accuracy": 0.16287316530942916,
|
||
|
|
"num_tokens": 5488107.0,
|
||
|
|
"step": 2650
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.7388874053955075,
|
||
|
|
"epoch": 2.4116310767832805,
|
||
|
|
"grad_norm": 1.640625,
|
||
|
|
"learning_rate": 0.00047030184883243203,
|
||
|
|
"loss": 5.4915,
|
||
|
|
"mean_token_accuracy": 0.16001203134655953,
|
||
|
|
"num_tokens": 5498521.0,
|
||
|
|
"step": 2655
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.569246292114258,
|
||
|
|
"epoch": 2.416174466151749,
|
||
|
|
"grad_norm": 1.2421875,
|
||
|
|
"learning_rate": 0.00047012611276408964,
|
||
|
|
"loss": 5.5285,
|
||
|
|
"mean_token_accuracy": 0.1563582494854927,
|
||
|
|
"num_tokens": 5509450.0,
|
||
|
|
"step": 2660
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.6742730140686035,
|
||
|
|
"epoch": 2.420717855520218,
|
||
|
|
"grad_norm": 1.21875,
|
||
|
|
"learning_rate": 0.0004699498952414609,
|
||
|
|
"loss": 5.4336,
|
||
|
|
"mean_token_accuracy": 0.16480647027492523,
|
||
|
|
"num_tokens": 5519662.0,
|
||
|
|
"step": 2665
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.586445379257202,
|
||
|
|
"epoch": 2.425261244888687,
|
||
|
|
"grad_norm": 1.15625,
|
||
|
|
"learning_rate": 0.00046977319669934506,
|
||
|
|
"loss": 5.4131,
|
||
|
|
"mean_token_accuracy": 0.16713995933532716,
|
||
|
|
"num_tokens": 5529499.0,
|
||
|
|
"step": 2670
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.622071361541748,
|
||
|
|
"epoch": 2.429804634257156,
|
||
|
|
"grad_norm": 1.140625,
|
||
|
|
"learning_rate": 0.00046959601757372814,
|
||
|
|
"loss": 5.5849,
|
||
|
|
"mean_token_accuracy": 0.15462029725313187,
|
||
|
|
"num_tokens": 5540938.0,
|
||
|
|
"step": 2675
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.657432556152344,
|
||
|
|
"epoch": 2.4343480236256245,
|
||
|
|
"grad_norm": 1.234375,
|
||
|
|
"learning_rate": 0.00046941835830178216,
|
||
|
|
"loss": 5.4632,
|
||
|
|
"mean_token_accuracy": 0.16584471315145494,
|
||
|
|
"num_tokens": 5552120.0,
|
||
|
|
"step": 2680
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.603826475143433,
|
||
|
|
"epoch": 2.4388914129940935,
|
||
|
|
"grad_norm": 1.3203125,
|
||
|
|
"learning_rate": 0.00046924021932186357,
|
||
|
|
"loss": 5.4356,
|
||
|
|
"mean_token_accuracy": 0.16504934132099153,
|
||
|
|
"num_tokens": 5561590.0,
|
||
|
|
"step": 2685
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.567124700546264,
|
||
|
|
"epoch": 2.4434348023625625,
|
||
|
|
"grad_norm": 1.203125,
|
||
|
|
"learning_rate": 0.00046906160107351263,
|
||
|
|
"loss": 5.4165,
|
||
|
|
"mean_token_accuracy": 0.1707810118794441,
|
||
|
|
"num_tokens": 5571682.0,
|
||
|
|
"step": 2690
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.615508699417115,
|
||
|
|
"epoch": 2.4479781917310315,
|
||
|
|
"grad_norm": 1.3125,
|
||
|
|
"learning_rate": 0.00046888250399745217,
|
||
|
|
"loss": 5.4673,
|
||
|
|
"mean_token_accuracy": 0.1730094686150551,
|
||
|
|
"num_tokens": 5581299.0,
|
||
|
|
"step": 2695
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.545977163314819,
|
||
|
|
"epoch": 2.4525215810995,
|
||
|
|
"grad_norm": 1.328125,
|
||
|
|
"learning_rate": 0.00046870292853558646,
|
||
|
|
"loss": 5.4154,
|
||
|
|
"mean_token_accuracy": 0.16748601645231248,
|
||
|
|
"num_tokens": 5590766.0,
|
||
|
|
"step": 2700
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.622316646575928,
|
||
|
|
"epoch": 2.457064970467969,
|
||
|
|
"grad_norm": 1.2578125,
|
||
|
|
"learning_rate": 0.00046852287513099997,
|
||
|
|
"loss": 5.5316,
|
||
|
|
"mean_token_accuracy": 0.16143546551465987,
|
||
|
|
"num_tokens": 5600898.0,
|
||
|
|
"step": 2705
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.66291880607605,
|
||
|
|
"epoch": 2.461608359836438,
|
||
|
|
"grad_norm": 1.1484375,
|
||
|
|
"learning_rate": 0.0004683423442279566,
|
||
|
|
"loss": 5.5158,
|
||
|
|
"mean_token_accuracy": 0.16342089623212813,
|
||
|
|
"num_tokens": 5612052.0,
|
||
|
|
"step": 2710
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.660036611557007,
|
||
|
|
"epoch": 2.466151749204907,
|
||
|
|
"grad_norm": 1.375,
|
||
|
|
"learning_rate": 0.0004681613362718985,
|
||
|
|
"loss": 5.5874,
|
||
|
|
"mean_token_accuracy": 0.16431321948766708,
|
||
|
|
"num_tokens": 5622847.0,
|
||
|
|
"step": 2715
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.567380332946778,
|
||
|
|
"epoch": 2.470695138573376,
|
||
|
|
"grad_norm": 1.1640625,
|
||
|
|
"learning_rate": 0.0004679798517094447,
|
||
|
|
"loss": 5.4144,
|
||
|
|
"mean_token_accuracy": 0.17110821902751921,
|
||
|
|
"num_tokens": 5633134.0,
|
||
|
|
"step": 2720
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.652763843536377,
|
||
|
|
"epoch": 2.4752385279418445,
|
||
|
|
"grad_norm": 1.3359375,
|
||
|
|
"learning_rate": 0.00046779789098839043,
|
||
|
|
"loss": 5.5767,
|
||
|
|
"mean_token_accuracy": 0.16604768484830856,
|
||
|
|
"num_tokens": 5644223.0,
|
||
|
|
"step": 2725
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.593555927276611,
|
||
|
|
"epoch": 2.4797819173103135,
|
||
|
|
"grad_norm": 1.40625,
|
||
|
|
"learning_rate": 0.00046761545455770555,
|
||
|
|
"loss": 5.5115,
|
||
|
|
"mean_token_accuracy": 0.16058846265077592,
|
||
|
|
"num_tokens": 5653620.0,
|
||
|
|
"step": 2730
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.677840805053711,
|
||
|
|
"epoch": 2.4843253066787825,
|
||
|
|
"grad_norm": 1.1171875,
|
||
|
|
"learning_rate": 0.0004674325428675339,
|
||
|
|
"loss": 5.4237,
|
||
|
|
"mean_token_accuracy": 0.16867171376943588,
|
||
|
|
"num_tokens": 5663800.0,
|
||
|
|
"step": 2735
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.608797216415406,
|
||
|
|
"epoch": 2.488868696047251,
|
||
|
|
"grad_norm": 1.2578125,
|
||
|
|
"learning_rate": 0.0004672491563691919,
|
||
|
|
"loss": 5.4756,
|
||
|
|
"mean_token_accuracy": 0.16562926769256592,
|
||
|
|
"num_tokens": 5674606.0,
|
||
|
|
"step": 2740
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.664605760574341,
|
||
|
|
"epoch": 2.49341208541572,
|
||
|
|
"grad_norm": 1.078125,
|
||
|
|
"learning_rate": 0.00046706529551516753,
|
||
|
|
"loss": 5.5954,
|
||
|
|
"mean_token_accuracy": 0.16185092478990554,
|
||
|
|
"num_tokens": 5684975.0,
|
||
|
|
"step": 2745
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.600146913528443,
|
||
|
|
"epoch": 2.497955474784189,
|
||
|
|
"grad_norm": 1.3125,
|
||
|
|
"learning_rate": 0.00046688096075911905,
|
||
|
|
"loss": 5.435,
|
||
|
|
"mean_token_accuracy": 0.16718858629465103,
|
||
|
|
"num_tokens": 5695336.0,
|
||
|
|
"step": 2750
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.6710587501525875,
|
||
|
|
"epoch": 2.502498864152658,
|
||
|
|
"grad_norm": 1.171875,
|
||
|
|
"learning_rate": 0.0004666961525558743,
|
||
|
|
"loss": 5.4596,
|
||
|
|
"mean_token_accuracy": 0.16664838194847106,
|
||
|
|
"num_tokens": 5706027.0,
|
||
|
|
"step": 2755
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.599521589279175,
|
||
|
|
"epoch": 2.507042253521127,
|
||
|
|
"grad_norm": 1.21875,
|
||
|
|
"learning_rate": 0.000466510871361429,
|
||
|
|
"loss": 5.51,
|
||
|
|
"mean_token_accuracy": 0.1608511984348297,
|
||
|
|
"num_tokens": 5716026.0,
|
||
|
|
"step": 2760
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.6033525466918945,
|
||
|
|
"epoch": 2.5115856428895955,
|
||
|
|
"grad_norm": 1.3046875,
|
||
|
|
"learning_rate": 0.00046632511763294615,
|
||
|
|
"loss": 5.499,
|
||
|
|
"mean_token_accuracy": 0.16632484197616576,
|
||
|
|
"num_tokens": 5726055.0,
|
||
|
|
"step": 2765
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.6622168064117435,
|
||
|
|
"epoch": 2.5161290322580645,
|
||
|
|
"grad_norm": 1.1953125,
|
||
|
|
"learning_rate": 0.0004661388918287546,
|
||
|
|
"loss": 5.542,
|
||
|
|
"mean_token_accuracy": 0.15696141570806504,
|
||
|
|
"num_tokens": 5736562.0,
|
||
|
|
"step": 2770
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.73774094581604,
|
||
|
|
"epoch": 2.5206724216265335,
|
||
|
|
"grad_norm": 1.4140625,
|
||
|
|
"learning_rate": 0.0004659521944083481,
|
||
|
|
"loss": 5.5769,
|
||
|
|
"mean_token_accuracy": 0.15729292780160903,
|
||
|
|
"num_tokens": 5747297.0,
|
||
|
|
"step": 2775
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.619591951370239,
|
||
|
|
"epoch": 2.525215810995002,
|
||
|
|
"grad_norm": 1.21875,
|
||
|
|
"learning_rate": 0.0004657650258323838,
|
||
|
|
"loss": 5.5425,
|
||
|
|
"mean_token_accuracy": 0.16078144162893296,
|
||
|
|
"num_tokens": 5756801.0,
|
||
|
|
"step": 2780
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.670393371582032,
|
||
|
|
"epoch": 2.529759200363471,
|
||
|
|
"grad_norm": 1.328125,
|
||
|
|
"learning_rate": 0.00046557738656268166,
|
||
|
|
"loss": 5.5367,
|
||
|
|
"mean_token_accuracy": 0.1635377436876297,
|
||
|
|
"num_tokens": 5767493.0,
|
||
|
|
"step": 2785
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.616514539718628,
|
||
|
|
"epoch": 2.53430258973194,
|
||
|
|
"grad_norm": 1.21875,
|
||
|
|
"learning_rate": 0.000465389277062223,
|
||
|
|
"loss": 5.4336,
|
||
|
|
"mean_token_accuracy": 0.1742817223072052,
|
||
|
|
"num_tokens": 5777539.0,
|
||
|
|
"step": 2790
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.591523456573486,
|
||
|
|
"epoch": 2.538845979100409,
|
||
|
|
"grad_norm": 1.28125,
|
||
|
|
"learning_rate": 0.00046520069779514917,
|
||
|
|
"loss": 5.459,
|
||
|
|
"mean_token_accuracy": 0.167883762717247,
|
||
|
|
"num_tokens": 5787202.0,
|
||
|
|
"step": 2795
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.6892999649047855,
|
||
|
|
"epoch": 2.543389368468878,
|
||
|
|
"grad_norm": 1.2265625,
|
||
|
|
"learning_rate": 0.0004650116492267609,
|
||
|
|
"loss": 5.5049,
|
||
|
|
"mean_token_accuracy": 0.1640034094452858,
|
||
|
|
"num_tokens": 5798023.0,
|
||
|
|
"step": 2800
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.523151063919068,
|
||
|
|
"epoch": 2.5479327578373465,
|
||
|
|
"grad_norm": 1.40625,
|
||
|
|
"learning_rate": 0.0004648221318235165,
|
||
|
|
"loss": 5.4072,
|
||
|
|
"mean_token_accuracy": 0.16618600934743882,
|
||
|
|
"num_tokens": 5807711.0,
|
||
|
|
"step": 2805
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.562091875076294,
|
||
|
|
"epoch": 2.5524761472058155,
|
||
|
|
"grad_norm": 1.3203125,
|
||
|
|
"learning_rate": 0.0004646321460530316,
|
||
|
|
"loss": 5.412,
|
||
|
|
"mean_token_accuracy": 0.16975668370723723,
|
||
|
|
"num_tokens": 5817053.0,
|
||
|
|
"step": 2810
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.569506883621216,
|
||
|
|
"epoch": 2.5570195365742845,
|
||
|
|
"grad_norm": 1.3828125,
|
||
|
|
"learning_rate": 0.000464441692384077,
|
||
|
|
"loss": 5.5157,
|
||
|
|
"mean_token_accuracy": 0.16288599371910095,
|
||
|
|
"num_tokens": 5827792.0,
|
||
|
|
"step": 2815
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.600739526748657,
|
||
|
|
"epoch": 2.561562925942753,
|
||
|
|
"grad_norm": 1.3046875,
|
||
|
|
"learning_rate": 0.0004642507712865784,
|
||
|
|
"loss": 5.4074,
|
||
|
|
"mean_token_accuracy": 0.16991793662309645,
|
||
|
|
"num_tokens": 5837702.0,
|
||
|
|
"step": 2820
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.692067098617554,
|
||
|
|
"epoch": 2.566106315311222,
|
||
|
|
"grad_norm": 1.3359375,
|
||
|
|
"learning_rate": 0.00046405938323161453,
|
||
|
|
"loss": 5.5546,
|
||
|
|
"mean_token_accuracy": 0.16360698789358138,
|
||
|
|
"num_tokens": 5847973.0,
|
||
|
|
"step": 2825
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.637374544143677,
|
||
|
|
"epoch": 2.570649704679691,
|
||
|
|
"grad_norm": 1.484375,
|
||
|
|
"learning_rate": 0.00046386752869141624,
|
||
|
|
"loss": 5.5499,
|
||
|
|
"mean_token_accuracy": 0.15725272595882417,
|
||
|
|
"num_tokens": 5857591.0,
|
||
|
|
"step": 2830
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.565674448013306,
|
||
|
|
"epoch": 2.57519309404816,
|
||
|
|
"grad_norm": 1.1484375,
|
||
|
|
"learning_rate": 0.0004636752081393658,
|
||
|
|
"loss": 5.5059,
|
||
|
|
"mean_token_accuracy": 0.1634950265288353,
|
||
|
|
"num_tokens": 5868616.0,
|
||
|
|
"step": 2835
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.650606632232666,
|
||
|
|
"epoch": 2.579736483416629,
|
||
|
|
"grad_norm": 1.3359375,
|
||
|
|
"learning_rate": 0.00046348242204999487,
|
||
|
|
"loss": 5.4348,
|
||
|
|
"mean_token_accuracy": 0.16790513396263124,
|
||
|
|
"num_tokens": 5878526.0,
|
||
|
|
"step": 2840
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.590163040161133,
|
||
|
|
"epoch": 2.5842798727850975,
|
||
|
|
"grad_norm": 1.28125,
|
||
|
|
"learning_rate": 0.00046328917089898396,
|
||
|
|
"loss": 5.4355,
|
||
|
|
"mean_token_accuracy": 0.1749364659190178,
|
||
|
|
"num_tokens": 5887844.0,
|
||
|
|
"step": 2845
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.644021272659302,
|
||
|
|
"epoch": 2.5888232621535665,
|
||
|
|
"grad_norm": 1.296875,
|
||
|
|
"learning_rate": 0.0004630954551631612,
|
||
|
|
"loss": 5.5451,
|
||
|
|
"mean_token_accuracy": 0.16367463767528534,
|
||
|
|
"num_tokens": 5898523.0,
|
||
|
|
"step": 2850
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.603885507583618,
|
||
|
|
"epoch": 2.5933666515220355,
|
||
|
|
"grad_norm": 1.25,
|
||
|
|
"learning_rate": 0.00046290127532050087,
|
||
|
|
"loss": 5.5536,
|
||
|
|
"mean_token_accuracy": 0.15856787636876107,
|
||
|
|
"num_tokens": 5909671.0,
|
||
|
|
"step": 2855
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.59442548751831,
|
||
|
|
"epoch": 2.5979100408905045,
|
||
|
|
"grad_norm": 1.21875,
|
||
|
|
"learning_rate": 0.0004627066318501223,
|
||
|
|
"loss": 5.4891,
|
||
|
|
"mean_token_accuracy": 0.15759917497634887,
|
||
|
|
"num_tokens": 5920451.0,
|
||
|
|
"step": 2860
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.675187778472901,
|
||
|
|
"epoch": 2.602453430258973,
|
||
|
|
"grad_norm": 1.2578125,
|
||
|
|
"learning_rate": 0.00046251152523228906,
|
||
|
|
"loss": 5.4765,
|
||
|
|
"mean_token_accuracy": 0.16859863847494125,
|
||
|
|
"num_tokens": 5931218.0,
|
||
|
|
"step": 2865
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.48574743270874,
|
||
|
|
"epoch": 2.606996819627442,
|
||
|
|
"grad_norm": 1.9765625,
|
||
|
|
"learning_rate": 0.0004623159559484074,
|
||
|
|
"loss": 5.4751,
|
||
|
|
"mean_token_accuracy": 0.16344277709722518,
|
||
|
|
"num_tokens": 5941380.0,
|
||
|
|
"step": 2870
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.614834976196289,
|
||
|
|
"epoch": 2.611540208995911,
|
||
|
|
"grad_norm": 1.3046875,
|
||
|
|
"learning_rate": 0.0004621199244810248,
|
||
|
|
"loss": 5.4402,
|
||
|
|
"mean_token_accuracy": 0.16504250317811966,
|
||
|
|
"num_tokens": 5951989.0,
|
||
|
|
"step": 2875
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.634076070785523,
|
||
|
|
"epoch": 2.61608359836438,
|
||
|
|
"grad_norm": 1.234375,
|
||
|
|
"learning_rate": 0.00046192343131382964,
|
||
|
|
"loss": 5.5061,
|
||
|
|
"mean_token_accuracy": 0.1620146870613098,
|
||
|
|
"num_tokens": 5961982.0,
|
||
|
|
"step": 2880
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.624727010726929,
|
||
|
|
"epoch": 2.620626987732849,
|
||
|
|
"grad_norm": 1.2421875,
|
||
|
|
"learning_rate": 0.00046172647693164926,
|
||
|
|
"loss": 5.5309,
|
||
|
|
"mean_token_accuracy": 0.16035393476486207,
|
||
|
|
"num_tokens": 5972184.0,
|
||
|
|
"step": 2885
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.671657609939575,
|
||
|
|
"epoch": 2.6251703771013175,
|
||
|
|
"grad_norm": 1.2734375,
|
||
|
|
"learning_rate": 0.0004615290618204489,
|
||
|
|
"loss": 5.4491,
|
||
|
|
"mean_token_accuracy": 0.168126380443573,
|
||
|
|
"num_tokens": 5981912.0,
|
||
|
|
"step": 2890
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.61940746307373,
|
||
|
|
"epoch": 2.6297137664697865,
|
||
|
|
"grad_norm": 1.1953125,
|
||
|
|
"learning_rate": 0.0004613311864673309,
|
||
|
|
"loss": 5.4409,
|
||
|
|
"mean_token_accuracy": 0.16417238712310792,
|
||
|
|
"num_tokens": 5992460.0,
|
||
|
|
"step": 2895
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.6031458377838135,
|
||
|
|
"epoch": 2.6342571558382555,
|
||
|
|
"grad_norm": 1.3984375,
|
||
|
|
"learning_rate": 0.00046113285136053286,
|
||
|
|
"loss": 5.5058,
|
||
|
|
"mean_token_accuracy": 0.16285987943410873,
|
||
|
|
"num_tokens": 6002170.0,
|
||
|
|
"step": 2900
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.573065280914307,
|
||
|
|
"epoch": 2.638800545206724,
|
||
|
|
"grad_norm": 1.28125,
|
||
|
|
"learning_rate": 0.000460934056989427,
|
||
|
|
"loss": 5.4317,
|
||
|
|
"mean_token_accuracy": 0.1615881845355034,
|
||
|
|
"num_tokens": 6012240.0,
|
||
|
|
"step": 2905
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.630006313323975,
|
||
|
|
"epoch": 2.643343934575193,
|
||
|
|
"grad_norm": 1.265625,
|
||
|
|
"learning_rate": 0.0004607348038445187,
|
||
|
|
"loss": 5.4057,
|
||
|
|
"mean_token_accuracy": 0.16957840621471404,
|
||
|
|
"num_tokens": 6022289.0,
|
||
|
|
"step": 2910
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.642009019851685,
|
||
|
|
"epoch": 2.647887323943662,
|
||
|
|
"grad_norm": 1.2890625,
|
||
|
|
"learning_rate": 0.00046053509241744526,
|
||
|
|
"loss": 5.524,
|
||
|
|
"mean_token_accuracy": 0.15756816565990447,
|
||
|
|
"num_tokens": 6032268.0,
|
||
|
|
"step": 2915
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.702442169189453,
|
||
|
|
"epoch": 2.652430713312131,
|
||
|
|
"grad_norm": 1.203125,
|
||
|
|
"learning_rate": 0.00046033492320097483,
|
||
|
|
"loss": 5.5905,
|
||
|
|
"mean_token_accuracy": 0.15488297939300538,
|
||
|
|
"num_tokens": 6042574.0,
|
||
|
|
"step": 2920
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.769234132766724,
|
||
|
|
"epoch": 2.6569741026806,
|
||
|
|
"grad_norm": 1.1953125,
|
||
|
|
"learning_rate": 0.0004601342966890049,
|
||
|
|
"loss": 5.5579,
|
||
|
|
"mean_token_accuracy": 0.1582654058933258,
|
||
|
|
"num_tokens": 6052508.0,
|
||
|
|
"step": 2925
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.549481201171875,
|
||
|
|
"epoch": 2.6615174920490685,
|
||
|
|
"grad_norm": 1.3203125,
|
||
|
|
"learning_rate": 0.00045993321337656163,
|
||
|
|
"loss": 5.419,
|
||
|
|
"mean_token_accuracy": 0.1712830290198326,
|
||
|
|
"num_tokens": 6062541.0,
|
||
|
|
"step": 2930
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.540633487701416,
|
||
|
|
"epoch": 2.6660608814175375,
|
||
|
|
"grad_norm": 1.3671875,
|
||
|
|
"learning_rate": 0.000459731673759798,
|
||
|
|
"loss": 5.5691,
|
||
|
|
"mean_token_accuracy": 0.15504138320684432,
|
||
|
|
"num_tokens": 6072532.0,
|
||
|
|
"step": 2935
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.653427791595459,
|
||
|
|
"epoch": 2.6706042707860065,
|
||
|
|
"grad_norm": 2.703125,
|
||
|
|
"learning_rate": 0.00045952967833599303,
|
||
|
|
"loss": 5.4532,
|
||
|
|
"mean_token_accuracy": 0.16891696751117707,
|
||
|
|
"num_tokens": 6082518.0,
|
||
|
|
"step": 2940
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.657943344116211,
|
||
|
|
"epoch": 2.675147660154475,
|
||
|
|
"grad_norm": 1.296875,
|
||
|
|
"learning_rate": 0.0004593272276035502,
|
||
|
|
"loss": 5.4468,
|
||
|
|
"mean_token_accuracy": 0.164460127055645,
|
||
|
|
"num_tokens": 6092356.0,
|
||
|
|
"step": 2945
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.634619855880738,
|
||
|
|
"epoch": 2.679691049522944,
|
||
|
|
"grad_norm": 1.25,
|
||
|
|
"learning_rate": 0.0004591243220619969,
|
||
|
|
"loss": 5.5382,
|
||
|
|
"mean_token_accuracy": 0.165224651992321,
|
||
|
|
"num_tokens": 6103450.0,
|
||
|
|
"step": 2950
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.653062343597412,
|
||
|
|
"epoch": 2.684234438891413,
|
||
|
|
"grad_norm": 1.375,
|
||
|
|
"learning_rate": 0.000458920962211982,
|
||
|
|
"loss": 5.4301,
|
||
|
|
"mean_token_accuracy": 0.17163696736097336,
|
||
|
|
"num_tokens": 6113708.0,
|
||
|
|
"step": 2955
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.558749485015869,
|
||
|
|
"epoch": 2.688777828259882,
|
||
|
|
"grad_norm": 1.375,
|
||
|
|
"learning_rate": 0.0004587171485552759,
|
||
|
|
"loss": 5.5134,
|
||
|
|
"mean_token_accuracy": 0.16230242252349852,
|
||
|
|
"num_tokens": 6124508.0,
|
||
|
|
"step": 2960
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.692312717437744,
|
||
|
|
"epoch": 2.693321217628351,
|
||
|
|
"grad_norm": 1.296875,
|
||
|
|
"learning_rate": 0.00045851288159476854,
|
||
|
|
"loss": 5.4872,
|
||
|
|
"mean_token_accuracy": 0.17191842198371887,
|
||
|
|
"num_tokens": 6135516.0,
|
||
|
|
"step": 2965
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.566852283477783,
|
||
|
|
"epoch": 2.6978646069968195,
|
||
|
|
"grad_norm": 2.625,
|
||
|
|
"learning_rate": 0.0004583081618344684,
|
||
|
|
"loss": 5.412,
|
||
|
|
"mean_token_accuracy": 0.16392800360918044,
|
||
|
|
"num_tokens": 6146206.0,
|
||
|
|
"step": 2970
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.518176746368408,
|
||
|
|
"epoch": 2.7024079963652885,
|
||
|
|
"grad_norm": 1.34375,
|
||
|
|
"learning_rate": 0.000458102989779501,
|
||
|
|
"loss": 5.383,
|
||
|
|
"mean_token_accuracy": 0.17127594947814942,
|
||
|
|
"num_tokens": 6156244.0,
|
||
|
|
"step": 2975
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.447549772262573,
|
||
|
|
"epoch": 2.7069513857337575,
|
||
|
|
"grad_norm": 1.1875,
|
||
|
|
"learning_rate": 0.0004578973659361081,
|
||
|
|
"loss": 5.4112,
|
||
|
|
"mean_token_accuracy": 0.16063664257526397,
|
||
|
|
"num_tokens": 6167091.0,
|
||
|
|
"step": 2980
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.6188061237335205,
|
||
|
|
"epoch": 2.711494775102226,
|
||
|
|
"grad_norm": 1.40625,
|
||
|
|
"learning_rate": 0.00045769129081164596,
|
||
|
|
"loss": 5.4903,
|
||
|
|
"mean_token_accuracy": 0.16669660359621047,
|
||
|
|
"num_tokens": 6177993.0,
|
||
|
|
"step": 2985
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.576446056365967,
|
||
|
|
"epoch": 2.716038164470695,
|
||
|
|
"grad_norm": 1.484375,
|
||
|
|
"learning_rate": 0.0004574847649145845,
|
||
|
|
"loss": 5.5158,
|
||
|
|
"mean_token_accuracy": 0.16666642427444459,
|
||
|
|
"num_tokens": 6187963.0,
|
||
|
|
"step": 2990
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.595619201660156,
|
||
|
|
"epoch": 2.720581553839164,
|
||
|
|
"grad_norm": 1.296875,
|
||
|
|
"learning_rate": 0.000457277788754506,
|
||
|
|
"loss": 5.4884,
|
||
|
|
"mean_token_accuracy": 0.1625219315290451,
|
||
|
|
"num_tokens": 6198442.0,
|
||
|
|
"step": 2995
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.610590934753418,
|
||
|
|
"epoch": 2.725124943207633,
|
||
|
|
"grad_norm": 1.375,
|
||
|
|
"learning_rate": 0.00045707036284210344,
|
||
|
|
"loss": 5.4934,
|
||
|
|
"mean_token_accuracy": 0.1641159787774086,
|
||
|
|
"num_tokens": 6209332.0,
|
||
|
|
"step": 3000
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 2.725124943207633,
|
||
|
|
"eval_entropy": 5.522899136432382,
|
||
|
|
"eval_loss": 5.916890621185303,
|
||
|
|
"eval_mean_token_accuracy": 0.15391022185253542,
|
||
|
|
"eval_num_tokens": 6209332.0,
|
||
|
|
"eval_runtime": 2.5974,
|
||
|
|
"eval_samples_per_second": 1322.454,
|
||
|
|
"eval_steps_per_second": 165.547,
|
||
|
|
"step": 3000
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.542118501663208,
|
||
|
|
"epoch": 2.729668332576102,
|
||
|
|
"grad_norm": 1.40625,
|
||
|
|
"learning_rate": 0.0004568624876891796,
|
||
|
|
"loss": 5.4611,
|
||
|
|
"mean_token_accuracy": 0.16434952467679978,
|
||
|
|
"num_tokens": 6219467.0,
|
||
|
|
"step": 3005
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.56941180229187,
|
||
|
|
"epoch": 2.7342117219445705,
|
||
|
|
"grad_norm": 1.375,
|
||
|
|
"learning_rate": 0.00045665416380864587,
|
||
|
|
"loss": 5.4806,
|
||
|
|
"mean_token_accuracy": 0.16400491297245026,
|
||
|
|
"num_tokens": 6229277.0,
|
||
|
|
"step": 3010
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.6014204025268555,
|
||
|
|
"epoch": 2.7387551113130395,
|
||
|
|
"grad_norm": 1.3515625,
|
||
|
|
"learning_rate": 0.0004564453917145206,
|
||
|
|
"loss": 5.4096,
|
||
|
|
"mean_token_accuracy": 0.17019634395837785,
|
||
|
|
"num_tokens": 6239191.0,
|
||
|
|
"step": 3015
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.62946047782898,
|
||
|
|
"epoch": 2.7432985006815085,
|
||
|
|
"grad_norm": 1.2890625,
|
||
|
|
"learning_rate": 0.0004562361719219283,
|
||
|
|
"loss": 5.5286,
|
||
|
|
"mean_token_accuracy": 0.15971722453832626,
|
||
|
|
"num_tokens": 6249539.0,
|
||
|
|
"step": 3020
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.610321807861328,
|
||
|
|
"epoch": 2.747841890049977,
|
||
|
|
"grad_norm": 1.3046875,
|
||
|
|
"learning_rate": 0.00045602650494709786,
|
||
|
|
"loss": 5.5419,
|
||
|
|
"mean_token_accuracy": 0.15591299384832383,
|
||
|
|
"num_tokens": 6260896.0,
|
||
|
|
"step": 3025
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.642046976089477,
|
||
|
|
"epoch": 2.752385279418446,
|
||
|
|
"grad_norm": 1.2421875,
|
||
|
|
"learning_rate": 0.00045581639130736173,
|
||
|
|
"loss": 5.5078,
|
||
|
|
"mean_token_accuracy": 0.1603671833872795,
|
||
|
|
"num_tokens": 6271828.0,
|
||
|
|
"step": 3030
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.7217706680297855,
|
||
|
|
"epoch": 2.756928668786915,
|
||
|
|
"grad_norm": 1.1328125,
|
||
|
|
"learning_rate": 0.0004556058315211546,
|
||
|
|
"loss": 5.5258,
|
||
|
|
"mean_token_accuracy": 0.1675170913338661,
|
||
|
|
"num_tokens": 6282698.0,
|
||
|
|
"step": 3035
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.603877973556519,
|
||
|
|
"epoch": 2.761472058155384,
|
||
|
|
"grad_norm": 1.328125,
|
||
|
|
"learning_rate": 0.00045539482610801156,
|
||
|
|
"loss": 5.4467,
|
||
|
|
"mean_token_accuracy": 0.16894223988056184,
|
||
|
|
"num_tokens": 6291905.0,
|
||
|
|
"step": 3040
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.514861536026001,
|
||
|
|
"epoch": 2.766015447523853,
|
||
|
|
"grad_norm": 1.1796875,
|
||
|
|
"learning_rate": 0.0004551833755885677,
|
||
|
|
"loss": 5.4646,
|
||
|
|
"mean_token_accuracy": 0.16589600890874862,
|
||
|
|
"num_tokens": 6301579.0,
|
||
|
|
"step": 3045
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.605765104293823,
|
||
|
|
"epoch": 2.7705588368923215,
|
||
|
|
"grad_norm": 1.21875,
|
||
|
|
"learning_rate": 0.0004549714804845561,
|
||
|
|
"loss": 5.4336,
|
||
|
|
"mean_token_accuracy": 0.163409923017025,
|
||
|
|
"num_tokens": 6311209.0,
|
||
|
|
"step": 3050
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.548905897140503,
|
||
|
|
"epoch": 2.7751022262607905,
|
||
|
|
"grad_norm": 1.625,
|
||
|
|
"learning_rate": 0.0004547591413188068,
|
||
|
|
"loss": 5.4224,
|
||
|
|
"mean_token_accuracy": 0.16202747374773024,
|
||
|
|
"num_tokens": 6321601.0,
|
||
|
|
"step": 3055
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.635558700561523,
|
||
|
|
"epoch": 2.7796456156292595,
|
||
|
|
"grad_norm": 1.3046875,
|
||
|
|
"learning_rate": 0.0004545463586152456,
|
||
|
|
"loss": 5.5434,
|
||
|
|
"mean_token_accuracy": 0.1665214255452156,
|
||
|
|
"num_tokens": 6331070.0,
|
||
|
|
"step": 3060
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.641869592666626,
|
||
|
|
"epoch": 2.784189004997728,
|
||
|
|
"grad_norm": 1.21875,
|
||
|
|
"learning_rate": 0.0004543331328988927,
|
||
|
|
"loss": 5.5106,
|
||
|
|
"mean_token_accuracy": 0.16080092936754226,
|
||
|
|
"num_tokens": 6341772.0,
|
||
|
|
"step": 3065
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.501345205307007,
|
||
|
|
"epoch": 2.788732394366197,
|
||
|
|
"grad_norm": 1.15625,
|
||
|
|
"learning_rate": 0.0004541194646958614,
|
||
|
|
"loss": 5.4593,
|
||
|
|
"mean_token_accuracy": 0.16531397253274918,
|
||
|
|
"num_tokens": 6352237.0,
|
||
|
|
"step": 3070
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.66186408996582,
|
||
|
|
"epoch": 2.793275783734666,
|
||
|
|
"grad_norm": 1.25,
|
||
|
|
"learning_rate": 0.00045390535453335666,
|
||
|
|
"loss": 5.5752,
|
||
|
|
"mean_token_accuracy": 0.1561602458357811,
|
||
|
|
"num_tokens": 6363645.0,
|
||
|
|
"step": 3075
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.593492650985718,
|
||
|
|
"epoch": 2.797819173103135,
|
||
|
|
"grad_norm": 1.2265625,
|
||
|
|
"learning_rate": 0.00045369080293967414,
|
||
|
|
"loss": 5.4502,
|
||
|
|
"mean_token_accuracy": 0.16789142787456512,
|
||
|
|
"num_tokens": 6373559.0,
|
||
|
|
"step": 3080
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.634049940109253,
|
||
|
|
"epoch": 2.802362562471604,
|
||
|
|
"grad_norm": 1.484375,
|
||
|
|
"learning_rate": 0.00045347581044419846,
|
||
|
|
"loss": 5.4521,
|
||
|
|
"mean_token_accuracy": 0.16563277840614318,
|
||
|
|
"num_tokens": 6384197.0,
|
||
|
|
"step": 3085
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.543875408172608,
|
||
|
|
"epoch": 2.806905951840073,
|
||
|
|
"grad_norm": 1.234375,
|
||
|
|
"learning_rate": 0.00045326037757740216,
|
||
|
|
"loss": 5.3581,
|
||
|
|
"mean_token_accuracy": 0.16752002090215684,
|
||
|
|
"num_tokens": 6394834.0,
|
||
|
|
"step": 3090
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.521064758300781,
|
||
|
|
"epoch": 2.8114493412085415,
|
||
|
|
"grad_norm": 1.359375,
|
||
|
|
"learning_rate": 0.0004530445048708447,
|
||
|
|
"loss": 5.4675,
|
||
|
|
"mean_token_accuracy": 0.16238887161016463,
|
||
|
|
"num_tokens": 6405515.0,
|
||
|
|
"step": 3095
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.627286958694458,
|
||
|
|
"epoch": 2.8159927305770105,
|
||
|
|
"grad_norm": 1.265625,
|
||
|
|
"learning_rate": 0.00045282819285717024,
|
||
|
|
"loss": 5.4825,
|
||
|
|
"mean_token_accuracy": 0.1663505971431732,
|
||
|
|
"num_tokens": 6415885.0,
|
||
|
|
"step": 3100
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.531750583648682,
|
||
|
|
"epoch": 2.8205361199454795,
|
||
|
|
"grad_norm": 1.3203125,
|
||
|
|
"learning_rate": 0.00045261144207010736,
|
||
|
|
"loss": 5.4094,
|
||
|
|
"mean_token_accuracy": 0.17296303808689117,
|
||
|
|
"num_tokens": 6426053.0,
|
||
|
|
"step": 3105
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.590877294540405,
|
||
|
|
"epoch": 2.825079509313948,
|
||
|
|
"grad_norm": 1.34375,
|
||
|
|
"learning_rate": 0.00045239425304446684,
|
||
|
|
"loss": 5.5346,
|
||
|
|
"mean_token_accuracy": 0.15836047381162643,
|
||
|
|
"num_tokens": 6436024.0,
|
||
|
|
"step": 3110
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.668206977844238,
|
||
|
|
"epoch": 2.829622898682417,
|
||
|
|
"grad_norm": 1.1953125,
|
||
|
|
"learning_rate": 0.0004521766263161413,
|
||
|
|
"loss": 5.4838,
|
||
|
|
"mean_token_accuracy": 0.16192781776189805,
|
||
|
|
"num_tokens": 6446847.0,
|
||
|
|
"step": 3115
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.558481979370117,
|
||
|
|
"epoch": 2.834166288050886,
|
||
|
|
"grad_norm": 1.140625,
|
||
|
|
"learning_rate": 0.000451958562422103,
|
||
|
|
"loss": 5.3953,
|
||
|
|
"mean_token_accuracy": 0.16717706322669984,
|
||
|
|
"num_tokens": 6456901.0,
|
||
|
|
"step": 3120
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.591206884384155,
|
||
|
|
"epoch": 2.838709677419355,
|
||
|
|
"grad_norm": 1.4609375,
|
||
|
|
"learning_rate": 0.00045174006190040267,
|
||
|
|
"loss": 5.4445,
|
||
|
|
"mean_token_accuracy": 0.16293987035751342,
|
||
|
|
"num_tokens": 6467308.0,
|
||
|
|
"step": 3125
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.593704891204834,
|
||
|
|
"epoch": 2.843253066787824,
|
||
|
|
"grad_norm": 1.28125,
|
||
|
|
"learning_rate": 0.000451521125290169,
|
||
|
|
"loss": 5.4211,
|
||
|
|
"mean_token_accuracy": 0.17131438106298447,
|
||
|
|
"num_tokens": 6477071.0,
|
||
|
|
"step": 3130
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.549534797668457,
|
||
|
|
"epoch": 2.8477964561562925,
|
||
|
|
"grad_norm": 1.3515625,
|
||
|
|
"learning_rate": 0.000451301753131606,
|
||
|
|
"loss": 5.4829,
|
||
|
|
"mean_token_accuracy": 0.16538456529378892,
|
||
|
|
"num_tokens": 6488300.0,
|
||
|
|
"step": 3135
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.593517780303955,
|
||
|
|
"epoch": 2.8523398455247615,
|
||
|
|
"grad_norm": 1.40625,
|
||
|
|
"learning_rate": 0.00045108194596599286,
|
||
|
|
"loss": 5.5347,
|
||
|
|
"mean_token_accuracy": 0.1554817885160446,
|
||
|
|
"num_tokens": 6499515.0,
|
||
|
|
"step": 3140
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.576261425018311,
|
||
|
|
"epoch": 2.8568832348932305,
|
||
|
|
"grad_norm": 1.328125,
|
||
|
|
"learning_rate": 0.0004508617043356818,
|
||
|
|
"loss": 5.4665,
|
||
|
|
"mean_token_accuracy": 0.16541536748409272,
|
||
|
|
"num_tokens": 6509167.0,
|
||
|
|
"step": 3145
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.620144462585449,
|
||
|
|
"epoch": 2.861426624261699,
|
||
|
|
"grad_norm": 1.28125,
|
||
|
|
"learning_rate": 0.0004506410287840972,
|
||
|
|
"loss": 5.4938,
|
||
|
|
"mean_token_accuracy": 0.1609639495611191,
|
||
|
|
"num_tokens": 6520899.0,
|
||
|
|
"step": 3150
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.574986457824707,
|
||
|
|
"epoch": 2.865970013630168,
|
||
|
|
"grad_norm": 1.4375,
|
||
|
|
"learning_rate": 0.000450419919855734,
|
||
|
|
"loss": 5.4851,
|
||
|
|
"mean_token_accuracy": 0.1607181578874588,
|
||
|
|
"num_tokens": 6531293.0,
|
||
|
|
"step": 3155
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.5995519161224365,
|
||
|
|
"epoch": 2.870513402998637,
|
||
|
|
"grad_norm": 1.5,
|
||
|
|
"learning_rate": 0.0004501983780961566,
|
||
|
|
"loss": 5.4723,
|
||
|
|
"mean_token_accuracy": 0.16596077978610993,
|
||
|
|
"num_tokens": 6541039.0,
|
||
|
|
"step": 3160
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.549083566665649,
|
||
|
|
"epoch": 2.875056792367106,
|
||
|
|
"grad_norm": 1.328125,
|
||
|
|
"learning_rate": 0.0004499764040519972,
|
||
|
|
"loss": 5.4627,
|
||
|
|
"mean_token_accuracy": 0.16740722060203553,
|
||
|
|
"num_tokens": 6551948.0,
|
||
|
|
"step": 3165
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.598315238952637,
|
||
|
|
"epoch": 2.879600181735575,
|
||
|
|
"grad_norm": 1.3046875,
|
||
|
|
"learning_rate": 0.00044975399827095467,
|
||
|
|
"loss": 5.3923,
|
||
|
|
"mean_token_accuracy": 0.17182673662900924,
|
||
|
|
"num_tokens": 6562158.0,
|
||
|
|
"step": 3170
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.658646774291992,
|
||
|
|
"epoch": 2.8841435711040435,
|
||
|
|
"grad_norm": 1.2890625,
|
||
|
|
"learning_rate": 0.00044953116130179313,
|
||
|
|
"loss": 5.4917,
|
||
|
|
"mean_token_accuracy": 0.15569328814744948,
|
||
|
|
"num_tokens": 6572605.0,
|
||
|
|
"step": 3175
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.440945434570312,
|
||
|
|
"epoch": 2.8886869604725125,
|
||
|
|
"grad_norm": 1.3515625,
|
||
|
|
"learning_rate": 0.0004493078936943408,
|
||
|
|
"loss": 5.4675,
|
||
|
|
"mean_token_accuracy": 0.16961103230714797,
|
||
|
|
"num_tokens": 6583247.0,
|
||
|
|
"step": 3180
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.695300912857055,
|
||
|
|
"epoch": 2.8932303498409815,
|
||
|
|
"grad_norm": 1.3046875,
|
||
|
|
"learning_rate": 0.0004490841959994882,
|
||
|
|
"loss": 5.5686,
|
||
|
|
"mean_token_accuracy": 0.1563364863395691,
|
||
|
|
"num_tokens": 6593371.0,
|
||
|
|
"step": 3185
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.651923990249633,
|
||
|
|
"epoch": 2.89777373920945,
|
||
|
|
"grad_norm": 1.2109375,
|
||
|
|
"learning_rate": 0.00044886006876918716,
|
||
|
|
"loss": 5.3677,
|
||
|
|
"mean_token_accuracy": 0.16403858959674836,
|
||
|
|
"num_tokens": 6603777.0,
|
||
|
|
"step": 3190
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.640544652938843,
|
||
|
|
"epoch": 2.902317128577919,
|
||
|
|
"grad_norm": 1.3203125,
|
||
|
|
"learning_rate": 0.0004486355125564493,
|
||
|
|
"loss": 5.617,
|
||
|
|
"mean_token_accuracy": 0.1627153292298317,
|
||
|
|
"num_tokens": 6615654.0,
|
||
|
|
"step": 3195
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.612918472290039,
|
||
|
|
"epoch": 2.906860517946388,
|
||
|
|
"grad_norm": 1.34375,
|
||
|
|
"learning_rate": 0.0004484105279153449,
|
||
|
|
"loss": 5.481,
|
||
|
|
"mean_token_accuracy": 0.1598746582865715,
|
||
|
|
"num_tokens": 6626079.0,
|
||
|
|
"step": 3200
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.603912115097046,
|
||
|
|
"epoch": 2.911403907314857,
|
||
|
|
"grad_norm": 1.3515625,
|
||
|
|
"learning_rate": 0.000448185115401001,
|
||
|
|
"loss": 5.3813,
|
||
|
|
"mean_token_accuracy": 0.17635067105293273,
|
||
|
|
"num_tokens": 6636047.0,
|
||
|
|
"step": 3205
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.550787734985351,
|
||
|
|
"epoch": 2.915947296683326,
|
||
|
|
"grad_norm": 1.390625,
|
||
|
|
"learning_rate": 0.0004479592755696008,
|
||
|
|
"loss": 5.5585,
|
||
|
|
"mean_token_accuracy": 0.1557467296719551,
|
||
|
|
"num_tokens": 6646670.0,
|
||
|
|
"step": 3210
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.618472671508789,
|
||
|
|
"epoch": 2.9204906860517945,
|
||
|
|
"grad_norm": 1.3359375,
|
||
|
|
"learning_rate": 0.00044773300897838137,
|
||
|
|
"loss": 5.56,
|
||
|
|
"mean_token_accuracy": 0.1680152416229248,
|
||
|
|
"num_tokens": 6658027.0,
|
||
|
|
"step": 3215
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.682929754257202,
|
||
|
|
"epoch": 2.9250340754202635,
|
||
|
|
"grad_norm": 1.421875,
|
||
|
|
"learning_rate": 0.0004475063161856332,
|
||
|
|
"loss": 5.4835,
|
||
|
|
"mean_token_accuracy": 0.16703135073184966,
|
||
|
|
"num_tokens": 6668446.0,
|
||
|
|
"step": 3220
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.5976167678833,
|
||
|
|
"epoch": 2.9295774647887325,
|
||
|
|
"grad_norm": 1.40625,
|
||
|
|
"learning_rate": 0.0004472791977506983,
|
||
|
|
"loss": 5.4931,
|
||
|
|
"mean_token_accuracy": 0.16511500924825667,
|
||
|
|
"num_tokens": 6679038.0,
|
||
|
|
"step": 3225
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.570468425750732,
|
||
|
|
"epoch": 2.934120854157201,
|
||
|
|
"grad_norm": 1.265625,
|
||
|
|
"learning_rate": 0.00044705165423396855,
|
||
|
|
"loss": 5.4106,
|
||
|
|
"mean_token_accuracy": 0.17460913509130477,
|
||
|
|
"num_tokens": 6689207.0,
|
||
|
|
"step": 3230
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.579809331893921,
|
||
|
|
"epoch": 2.93866424352567,
|
||
|
|
"grad_norm": 1.3515625,
|
||
|
|
"learning_rate": 0.00044682368619688523,
|
||
|
|
"loss": 5.4336,
|
||
|
|
"mean_token_accuracy": 0.16403188556432724,
|
||
|
|
"num_tokens": 6699264.0,
|
||
|
|
"step": 3235
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.5837079048156735,
|
||
|
|
"epoch": 2.943207632894139,
|
||
|
|
"grad_norm": 1.484375,
|
||
|
|
"learning_rate": 0.0004465952942019367,
|
||
|
|
"loss": 5.4814,
|
||
|
|
"mean_token_accuracy": 0.16315781474113464,
|
||
|
|
"num_tokens": 6709309.0,
|
||
|
|
"step": 3240
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.583945989608765,
|
||
|
|
"epoch": 2.947751022262608,
|
||
|
|
"grad_norm": 1.3359375,
|
||
|
|
"learning_rate": 0.00044636647881265745,
|
||
|
|
"loss": 5.4598,
|
||
|
|
"mean_token_accuracy": 0.16575903296470643,
|
||
|
|
"num_tokens": 6719302.0,
|
||
|
|
"step": 3245
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.6043600082397464,
|
||
|
|
"epoch": 2.952294411631077,
|
||
|
|
"grad_norm": 1.5390625,
|
||
|
|
"learning_rate": 0.0004461372405936269,
|
||
|
|
"loss": 5.4156,
|
||
|
|
"mean_token_accuracy": 0.16708488315343856,
|
||
|
|
"num_tokens": 6730668.0,
|
||
|
|
"step": 3250
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.567113971710205,
|
||
|
|
"epoch": 2.9568378009995455,
|
||
|
|
"grad_norm": 1.53125,
|
||
|
|
"learning_rate": 0.0004459075801104673,
|
||
|
|
"loss": 5.4059,
|
||
|
|
"mean_token_accuracy": 0.1614591509103775,
|
||
|
|
"num_tokens": 6740140.0,
|
||
|
|
"step": 3255
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.56418924331665,
|
||
|
|
"epoch": 2.9613811903680145,
|
||
|
|
"grad_norm": 1.265625,
|
||
|
|
"learning_rate": 0.00044567749792984325,
|
||
|
|
"loss": 5.4405,
|
||
|
|
"mean_token_accuracy": 0.16615875363349913,
|
||
|
|
"num_tokens": 6751864.0,
|
||
|
|
"step": 3260
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.595006847381592,
|
||
|
|
"epoch": 2.9659245797364835,
|
||
|
|
"grad_norm": 2.171875,
|
||
|
|
"learning_rate": 0.00044544699461945966,
|
||
|
|
"loss": 5.5575,
|
||
|
|
"mean_token_accuracy": 0.16195874959230422,
|
||
|
|
"num_tokens": 6762375.0,
|
||
|
|
"step": 3265
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.631557178497315,
|
||
|
|
"epoch": 2.970467969104952,
|
||
|
|
"grad_norm": 1.390625,
|
||
|
|
"learning_rate": 0.00044521607074806037,
|
||
|
|
"loss": 5.481,
|
||
|
|
"mean_token_accuracy": 0.16731629520654678,
|
||
|
|
"num_tokens": 6772181.0,
|
||
|
|
"step": 3270
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.606076002120972,
|
||
|
|
"epoch": 2.975011358473421,
|
||
|
|
"grad_norm": 1.65625,
|
||
|
|
"learning_rate": 0.0004449847268854272,
|
||
|
|
"loss": 5.505,
|
||
|
|
"mean_token_accuracy": 0.16299747973680495,
|
||
|
|
"num_tokens": 6782402.0,
|
||
|
|
"step": 3275
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.538914012908935,
|
||
|
|
"epoch": 2.97955474784189,
|
||
|
|
"grad_norm": 1.390625,
|
||
|
|
"learning_rate": 0.0004447529636023782,
|
||
|
|
"loss": 5.4477,
|
||
|
|
"mean_token_accuracy": 0.16805306524038316,
|
||
|
|
"num_tokens": 6792671.0,
|
||
|
|
"step": 3280
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.545539808273316,
|
||
|
|
"epoch": 2.984098137210359,
|
||
|
|
"grad_norm": 1.4296875,
|
||
|
|
"learning_rate": 0.00044452078147076614,
|
||
|
|
"loss": 5.3382,
|
||
|
|
"mean_token_accuracy": 0.17342765033245086,
|
||
|
|
"num_tokens": 6802111.0,
|
||
|
|
"step": 3285
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.557024621963501,
|
||
|
|
"epoch": 2.988641526578828,
|
||
|
|
"grad_norm": 1.25,
|
||
|
|
"learning_rate": 0.0004442881810634774,
|
||
|
|
"loss": 5.4287,
|
||
|
|
"mean_token_accuracy": 0.1697560280561447,
|
||
|
|
"num_tokens": 6812651.0,
|
||
|
|
"step": 3290
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.606369972229004,
|
||
|
|
"epoch": 2.9931849159472965,
|
||
|
|
"grad_norm": 1.21875,
|
||
|
|
"learning_rate": 0.0004440551629544303,
|
||
|
|
"loss": 5.4691,
|
||
|
|
"mean_token_accuracy": 0.1571819603443146,
|
||
|
|
"num_tokens": 6823208.0,
|
||
|
|
"step": 3295
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.634217262268066,
|
||
|
|
"epoch": 2.9977283053157655,
|
||
|
|
"grad_norm": 1.296875,
|
||
|
|
"learning_rate": 0.00044382172771857383,
|
||
|
|
"loss": 5.4588,
|
||
|
|
"mean_token_accuracy": 0.16337359845638275,
|
||
|
|
"num_tokens": 6833412.0,
|
||
|
|
"step": 3300
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.580940617455377,
|
||
|
|
"epoch": 3.0018173557473875,
|
||
|
|
"grad_norm": 1.234375,
|
||
|
|
"learning_rate": 0.0004435878759318864,
|
||
|
|
"loss": 5.3437,
|
||
|
|
"mean_token_accuracy": 0.17550832198725808,
|
||
|
|
"num_tokens": 6841977.0,
|
||
|
|
"step": 3305
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.554789781570435,
|
||
|
|
"epoch": 3.0063607451158565,
|
||
|
|
"grad_norm": 1.2890625,
|
||
|
|
"learning_rate": 0.0004433536081713738,
|
||
|
|
"loss": 5.1528,
|
||
|
|
"mean_token_accuracy": 0.17688107937574388,
|
||
|
|
"num_tokens": 6852571.0,
|
||
|
|
"step": 3310
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.574832582473755,
|
||
|
|
"epoch": 3.0109041344843255,
|
||
|
|
"grad_norm": 1.2734375,
|
||
|
|
"learning_rate": 0.0004431189250150686,
|
||
|
|
"loss": 5.2011,
|
||
|
|
"mean_token_accuracy": 0.1709735944867134,
|
||
|
|
"num_tokens": 6861451.0,
|
||
|
|
"step": 3315
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.565835571289062,
|
||
|
|
"epoch": 3.015447523852794,
|
||
|
|
"grad_norm": 1.4453125,
|
||
|
|
"learning_rate": 0.00044288382704202816,
|
||
|
|
"loss": 5.1644,
|
||
|
|
"mean_token_accuracy": 0.17401813119649887,
|
||
|
|
"num_tokens": 6872134.0,
|
||
|
|
"step": 3320
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.51848726272583,
|
||
|
|
"epoch": 3.019990913221263,
|
||
|
|
"grad_norm": 1.1796875,
|
||
|
|
"learning_rate": 0.00044264831483233335,
|
||
|
|
"loss": 5.2244,
|
||
|
|
"mean_token_accuracy": 0.1795010522007942,
|
||
|
|
"num_tokens": 6882477.0,
|
||
|
|
"step": 3325
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.538839435577392,
|
||
|
|
"epoch": 3.024534302589732,
|
||
|
|
"grad_norm": 1.390625,
|
||
|
|
"learning_rate": 0.00044241238896708716,
|
||
|
|
"loss": 5.159,
|
||
|
|
"mean_token_accuracy": 0.1787806823849678,
|
||
|
|
"num_tokens": 6892233.0,
|
||
|
|
"step": 3330
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.501246976852417,
|
||
|
|
"epoch": 3.029077691958201,
|
||
|
|
"grad_norm": 1.6796875,
|
||
|
|
"learning_rate": 0.0004421760500284131,
|
||
|
|
"loss": 5.1321,
|
||
|
|
"mean_token_accuracy": 0.17679936289787293,
|
||
|
|
"num_tokens": 6902090.0,
|
||
|
|
"step": 3335
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.521198511123657,
|
||
|
|
"epoch": 3.0336210813266695,
|
||
|
|
"grad_norm": 1.4765625,
|
||
|
|
"learning_rate": 0.0004419392985994541,
|
||
|
|
"loss": 5.23,
|
||
|
|
"mean_token_accuracy": 0.17728585004806519,
|
||
|
|
"num_tokens": 6912295.0,
|
||
|
|
"step": 3340
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.693401622772217,
|
||
|
|
"epoch": 3.0381644706951385,
|
||
|
|
"grad_norm": 1.2265625,
|
||
|
|
"learning_rate": 0.00044170213526437076,
|
||
|
|
"loss": 5.2554,
|
||
|
|
"mean_token_accuracy": 0.1622602179646492,
|
||
|
|
"num_tokens": 6923064.0,
|
||
|
|
"step": 3345
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.577483129501343,
|
||
|
|
"epoch": 3.0427078600636075,
|
||
|
|
"grad_norm": 1.3828125,
|
||
|
|
"learning_rate": 0.00044146456060833994,
|
||
|
|
"loss": 5.1667,
|
||
|
|
"mean_token_accuracy": 0.17781320512294768,
|
||
|
|
"num_tokens": 6932825.0,
|
||
|
|
"step": 3350
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.401189756393433,
|
||
|
|
"epoch": 3.0472512494320765,
|
||
|
|
"grad_norm": 1.4140625,
|
||
|
|
"learning_rate": 0.00044122657521755373,
|
||
|
|
"loss": 5.0949,
|
||
|
|
"mean_token_accuracy": 0.18163834810256957,
|
||
|
|
"num_tokens": 6943188.0,
|
||
|
|
"step": 3355
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.481717348098755,
|
||
|
|
"epoch": 3.051794638800545,
|
||
|
|
"grad_norm": 1.5234375,
|
||
|
|
"learning_rate": 0.00044098817967921716,
|
||
|
|
"loss": 5.1947,
|
||
|
|
"mean_token_accuracy": 0.17781210392713548,
|
||
|
|
"num_tokens": 6953864.0,
|
||
|
|
"step": 3360
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.508717584609985,
|
||
|
|
"epoch": 3.056338028169014,
|
||
|
|
"grad_norm": 1.3359375,
|
||
|
|
"learning_rate": 0.00044074937458154763,
|
||
|
|
"loss": 5.1865,
|
||
|
|
"mean_token_accuracy": 0.17617179155349733,
|
||
|
|
"num_tokens": 6963745.0,
|
||
|
|
"step": 3365
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.519685840606689,
|
||
|
|
"epoch": 3.060881417537483,
|
||
|
|
"grad_norm": 1.3828125,
|
||
|
|
"learning_rate": 0.00044051016051377303,
|
||
|
|
"loss": 5.1977,
|
||
|
|
"mean_token_accuracy": 0.17872464656829834,
|
||
|
|
"num_tokens": 6973933.0,
|
||
|
|
"step": 3370
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.437633657455445,
|
||
|
|
"epoch": 3.065424806905952,
|
||
|
|
"grad_norm": 2.171875,
|
||
|
|
"learning_rate": 0.0004402705380661302,
|
||
|
|
"loss": 5.1608,
|
||
|
|
"mean_token_accuracy": 0.17672280818223954,
|
||
|
|
"num_tokens": 6984314.0,
|
||
|
|
"step": 3375
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.550196599960327,
|
||
|
|
"epoch": 3.0699681962744205,
|
||
|
|
"grad_norm": 1.5703125,
|
||
|
|
"learning_rate": 0.00044003050782986377,
|
||
|
|
"loss": 5.312,
|
||
|
|
"mean_token_accuracy": 0.16897685527801515,
|
||
|
|
"num_tokens": 6995921.0,
|
||
|
|
"step": 3380
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.630539894104004,
|
||
|
|
"epoch": 3.0745115856428895,
|
||
|
|
"grad_norm": 1.4140625,
|
||
|
|
"learning_rate": 0.0004397900703972245,
|
||
|
|
"loss": 5.2937,
|
||
|
|
"mean_token_accuracy": 0.170492485165596,
|
||
|
|
"num_tokens": 7006910.0,
|
||
|
|
"step": 3385
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.5243175506591795,
|
||
|
|
"epoch": 3.0790549750113585,
|
||
|
|
"grad_norm": 1.390625,
|
||
|
|
"learning_rate": 0.0004395492263614677,
|
||
|
|
"loss": 5.166,
|
||
|
|
"mean_token_accuracy": 0.17316992282867433,
|
||
|
|
"num_tokens": 7017229.0,
|
||
|
|
"step": 3390
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.532933950424194,
|
||
|
|
"epoch": 3.0835983643798275,
|
||
|
|
"grad_norm": 1.25,
|
||
|
|
"learning_rate": 0.00043930797631685234,
|
||
|
|
"loss": 5.2619,
|
||
|
|
"mean_token_accuracy": 0.17371898293495178,
|
||
|
|
"num_tokens": 7027934.0,
|
||
|
|
"step": 3395
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.5187013149261475,
|
||
|
|
"epoch": 3.088141753748296,
|
||
|
|
"grad_norm": 1.34375,
|
||
|
|
"learning_rate": 0.00043906632085863876,
|
||
|
|
"loss": 5.1739,
|
||
|
|
"mean_token_accuracy": 0.17809343934059144,
|
||
|
|
"num_tokens": 7037964.0,
|
||
|
|
"step": 3400
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.540422010421753,
|
||
|
|
"epoch": 3.092685143116765,
|
||
|
|
"grad_norm": 1.28125,
|
||
|
|
"learning_rate": 0.00043882426058308775,
|
||
|
|
"loss": 5.1946,
|
||
|
|
"mean_token_accuracy": 0.1763277605175972,
|
||
|
|
"num_tokens": 7048275.0,
|
||
|
|
"step": 3405
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.471914529800415,
|
||
|
|
"epoch": 3.097228532485234,
|
||
|
|
"grad_norm": 1.4921875,
|
||
|
|
"learning_rate": 0.00043858179608745915,
|
||
|
|
"loss": 5.2035,
|
||
|
|
"mean_token_accuracy": 0.1735120266675949,
|
||
|
|
"num_tokens": 7058488.0,
|
||
|
|
"step": 3410
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.574077606201172,
|
||
|
|
"epoch": 3.101771921853703,
|
||
|
|
"grad_norm": 1.359375,
|
||
|
|
"learning_rate": 0.0004383389279700098,
|
||
|
|
"loss": 5.2382,
|
||
|
|
"mean_token_accuracy": 0.17403238117694855,
|
||
|
|
"num_tokens": 7069195.0,
|
||
|
|
"step": 3415
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.495459032058716,
|
||
|
|
"epoch": 3.1063153112221715,
|
||
|
|
"grad_norm": 1.3828125,
|
||
|
|
"learning_rate": 0.00043809565682999274,
|
||
|
|
"loss": 5.1664,
|
||
|
|
"mean_token_accuracy": 0.17585339099168779,
|
||
|
|
"num_tokens": 7078858.0,
|
||
|
|
"step": 3420
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.472033739089966,
|
||
|
|
"epoch": 3.1108587005906405,
|
||
|
|
"grad_norm": 1.5078125,
|
||
|
|
"learning_rate": 0.00043785198326765535,
|
||
|
|
"loss": 5.2061,
|
||
|
|
"mean_token_accuracy": 0.17319677025079727,
|
||
|
|
"num_tokens": 7088551.0,
|
||
|
|
"step": 3425
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.483696031570434,
|
||
|
|
"epoch": 3.1154020899591095,
|
||
|
|
"grad_norm": 1.296875,
|
||
|
|
"learning_rate": 0.00043760790788423785,
|
||
|
|
"loss": 5.1836,
|
||
|
|
"mean_token_accuracy": 0.18097377121448516,
|
||
|
|
"num_tokens": 7098987.0,
|
||
|
|
"step": 3430
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.475705194473266,
|
||
|
|
"epoch": 3.1199454793275785,
|
||
|
|
"grad_norm": 1.3203125,
|
||
|
|
"learning_rate": 0.00043736343128197207,
|
||
|
|
"loss": 5.195,
|
||
|
|
"mean_token_accuracy": 0.17989107817411423,
|
||
|
|
"num_tokens": 7108337.0,
|
||
|
|
"step": 3435
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.507874584197998,
|
||
|
|
"epoch": 3.124488868696047,
|
||
|
|
"grad_norm": 1.265625,
|
||
|
|
"learning_rate": 0.0004371185540640796,
|
||
|
|
"loss": 5.2332,
|
||
|
|
"mean_token_accuracy": 0.1778836131095886,
|
||
|
|
"num_tokens": 7118267.0,
|
||
|
|
"step": 3440
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.508310413360595,
|
||
|
|
"epoch": 3.129032258064516,
|
||
|
|
"grad_norm": 1.3671875,
|
||
|
|
"learning_rate": 0.00043687327683477077,
|
||
|
|
"loss": 5.2724,
|
||
|
|
"mean_token_accuracy": 0.17600389271974565,
|
||
|
|
"num_tokens": 7129780.0,
|
||
|
|
"step": 3445
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.481181001663208,
|
||
|
|
"epoch": 3.133575647432985,
|
||
|
|
"grad_norm": 1.59375,
|
||
|
|
"learning_rate": 0.0004366276001992427,
|
||
|
|
"loss": 5.2253,
|
||
|
|
"mean_token_accuracy": 0.1728798419237137,
|
||
|
|
"num_tokens": 7139581.0,
|
||
|
|
"step": 3450
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.502482795715332,
|
||
|
|
"epoch": 3.138119036801454,
|
||
|
|
"grad_norm": 1.3359375,
|
||
|
|
"learning_rate": 0.000436381524763678,
|
||
|
|
"loss": 5.2064,
|
||
|
|
"mean_token_accuracy": 0.17794367671012878,
|
||
|
|
"num_tokens": 7150093.0,
|
||
|
|
"step": 3455
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.512056636810303,
|
||
|
|
"epoch": 3.142662426169923,
|
||
|
|
"grad_norm": 1.3046875,
|
||
|
|
"learning_rate": 0.0004361350511352435,
|
||
|
|
"loss": 5.1546,
|
||
|
|
"mean_token_accuracy": 0.17750439494848252,
|
||
|
|
"num_tokens": 7159668.0,
|
||
|
|
"step": 3460
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.5208704471588135,
|
||
|
|
"epoch": 3.1472058155383915,
|
||
|
|
"grad_norm": 1.296875,
|
||
|
|
"learning_rate": 0.0004358881799220882,
|
||
|
|
"loss": 5.2479,
|
||
|
|
"mean_token_accuracy": 0.17130112051963806,
|
||
|
|
"num_tokens": 7169713.0,
|
||
|
|
"step": 3465
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.461503219604492,
|
||
|
|
"epoch": 3.1517492049068605,
|
||
|
|
"grad_norm": 1.6640625,
|
||
|
|
"learning_rate": 0.00043564091173334236,
|
||
|
|
"loss": 5.2274,
|
||
|
|
"mean_token_accuracy": 0.17079599052667618,
|
||
|
|
"num_tokens": 7180681.0,
|
||
|
|
"step": 3470
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.476870107650757,
|
||
|
|
"epoch": 3.1562925942753295,
|
||
|
|
"grad_norm": 1.453125,
|
||
|
|
"learning_rate": 0.00043539324717911573,
|
||
|
|
"loss": 5.1048,
|
||
|
|
"mean_token_accuracy": 0.18265012800693511,
|
||
|
|
"num_tokens": 7189922.0,
|
||
|
|
"step": 3475
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.488419866561889,
|
||
|
|
"epoch": 3.1608359836437985,
|
||
|
|
"grad_norm": 1.375,
|
||
|
|
"learning_rate": 0.00043514518687049587,
|
||
|
|
"loss": 5.1901,
|
||
|
|
"mean_token_accuracy": 0.18352550715208055,
|
||
|
|
"num_tokens": 7200388.0,
|
||
|
|
"step": 3480
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.485075950622559,
|
||
|
|
"epoch": 3.165379373012267,
|
||
|
|
"grad_norm": 1.359375,
|
||
|
|
"learning_rate": 0.000434896731419547,
|
||
|
|
"loss": 5.2307,
|
||
|
|
"mean_token_accuracy": 0.17967755049467088,
|
||
|
|
"num_tokens": 7211219.0,
|
||
|
|
"step": 3485
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.404648113250732,
|
||
|
|
"epoch": 3.169922762380736,
|
||
|
|
"grad_norm": 1.53125,
|
||
|
|
"learning_rate": 0.0004346478814393082,
|
||
|
|
"loss": 5.0352,
|
||
|
|
"mean_token_accuracy": 0.187244413793087,
|
||
|
|
"num_tokens": 7220585.0,
|
||
|
|
"step": 3490
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.471985101699829,
|
||
|
|
"epoch": 3.174466151749205,
|
||
|
|
"grad_norm": 1.2578125,
|
||
|
|
"learning_rate": 0.0004343986375437921,
|
||
|
|
"loss": 5.192,
|
||
|
|
"mean_token_accuracy": 0.1802661970257759,
|
||
|
|
"num_tokens": 7231123.0,
|
||
|
|
"step": 3495
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.510929727554322,
|
||
|
|
"epoch": 3.179009541117674,
|
||
|
|
"grad_norm": 1.3125,
|
||
|
|
"learning_rate": 0.00043414900034798314,
|
||
|
|
"loss": 5.1987,
|
||
|
|
"mean_token_accuracy": 0.17463556230068206,
|
||
|
|
"num_tokens": 7241802.0,
|
||
|
|
"step": 3500
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 3.179009541117674,
|
||
|
|
"eval_entropy": 5.382433459925097,
|
||
|
|
"eval_loss": 5.899746894836426,
|
||
|
|
"eval_mean_token_accuracy": 0.15575186327792878,
|
||
|
|
"eval_num_tokens": 7241802.0,
|
||
|
|
"eval_runtime": 2.595,
|
||
|
|
"eval_samples_per_second": 1323.696,
|
||
|
|
"eval_steps_per_second": 165.703,
|
||
|
|
"step": 3500
|
||
|
|
}
|
||
|
|
],
|
||
|
|
"logging_steps": 5,
|
||
|
|
"max_steps": 11000,
|
||
|
|
"num_input_tokens_seen": 0,
|
||
|
|
"num_train_epochs": 10,
|
||
|
|
"save_steps": 500,
|
||
|
|
"stateful_callbacks": {
|
||
|
|
"TrainerControl": {
|
||
|
|
"args": {
|
||
|
|
"should_epoch_stop": false,
|
||
|
|
"should_evaluate": false,
|
||
|
|
"should_log": false,
|
||
|
|
"should_save": true,
|
||
|
|
"should_training_stop": false
|
||
|
|
},
|
||
|
|
"attributes": {}
|
||
|
|
}
|
||
|
|
},
|
||
|
|
"total_flos": 1.0472512685184e+16,
|
||
|
|
"train_batch_size": 16,
|
||
|
|
"trial_name": null,
|
||
|
|
"trial_params": null
|
||
|
|
}
|