22156 lines
606 KiB
JSON
22156 lines
606 KiB
JSON
{
|
|
"best_global_step": null,
|
|
"best_metric": null,
|
|
"best_model_checkpoint": null,
|
|
"epoch": 9.99136756019991,
|
|
"eval_steps": 1000,
|
|
"global_step": 11000,
|
|
"is_hyper_param_search": false,
|
|
"is_local_process_zero": true,
|
|
"is_world_process_zero": true,
|
|
"log_history": [
|
|
{
|
|
"entropy": 10.691572093963623,
|
|
"epoch": 0.004543389368468878,
|
|
"grad_norm": 13.0625,
|
|
"learning_rate": 2e-06,
|
|
"loss": 10.7962,
|
|
"mean_token_accuracy": 0.0,
|
|
"num_tokens": 10469.0,
|
|
"step": 5
|
|
},
|
|
{
|
|
"entropy": 10.69153709411621,
|
|
"epoch": 0.009086778736937756,
|
|
"grad_norm": 12.4375,
|
|
"learning_rate": 4.5e-06,
|
|
"loss": 10.7251,
|
|
"mean_token_accuracy": 0.0,
|
|
"num_tokens": 20770.0,
|
|
"step": 10
|
|
},
|
|
{
|
|
"entropy": 10.691234588623047,
|
|
"epoch": 0.013630168105406633,
|
|
"grad_norm": 9.625,
|
|
"learning_rate": 7e-06,
|
|
"loss": 10.4762,
|
|
"mean_token_accuracy": 0.019823318906128408,
|
|
"num_tokens": 31178.0,
|
|
"step": 15
|
|
},
|
|
{
|
|
"entropy": 10.682231140136718,
|
|
"epoch": 0.01817355747387551,
|
|
"grad_norm": 6.375,
|
|
"learning_rate": 9.5e-06,
|
|
"loss": 10.1698,
|
|
"mean_token_accuracy": 0.04362867064774036,
|
|
"num_tokens": 41482.0,
|
|
"step": 20
|
|
},
|
|
{
|
|
"entropy": 10.625249195098878,
|
|
"epoch": 0.02271694684234439,
|
|
"grad_norm": 3.84375,
|
|
"learning_rate": 1.2e-05,
|
|
"loss": 9.9154,
|
|
"mean_token_accuracy": 0.04354195147752762,
|
|
"num_tokens": 52412.0,
|
|
"step": 25
|
|
},
|
|
{
|
|
"entropy": 10.598425483703613,
|
|
"epoch": 0.027260336210813266,
|
|
"grad_norm": 3.21875,
|
|
"learning_rate": 1.4500000000000002e-05,
|
|
"loss": 9.7351,
|
|
"mean_token_accuracy": 0.042904840968549254,
|
|
"num_tokens": 62551.0,
|
|
"step": 30
|
|
},
|
|
{
|
|
"entropy": 10.609325218200684,
|
|
"epoch": 0.03180372557928214,
|
|
"grad_norm": 3.140625,
|
|
"learning_rate": 1.7000000000000003e-05,
|
|
"loss": 9.6541,
|
|
"mean_token_accuracy": 0.042877554334700106,
|
|
"num_tokens": 72196.0,
|
|
"step": 35
|
|
},
|
|
{
|
|
"entropy": 10.581289100646973,
|
|
"epoch": 0.03634711494775102,
|
|
"grad_norm": 2.390625,
|
|
"learning_rate": 1.95e-05,
|
|
"loss": 9.6326,
|
|
"mean_token_accuracy": 0.04586241915822029,
|
|
"num_tokens": 83372.0,
|
|
"step": 40
|
|
},
|
|
{
|
|
"entropy": 10.568495941162109,
|
|
"epoch": 0.0408905043162199,
|
|
"grad_norm": 2.578125,
|
|
"learning_rate": 2.2e-05,
|
|
"loss": 9.6045,
|
|
"mean_token_accuracy": 0.042813677340745926,
|
|
"num_tokens": 94673.0,
|
|
"step": 45
|
|
},
|
|
{
|
|
"entropy": 10.59875020980835,
|
|
"epoch": 0.04543389368468878,
|
|
"grad_norm": 2.703125,
|
|
"learning_rate": 2.4500000000000003e-05,
|
|
"loss": 9.4863,
|
|
"mean_token_accuracy": 0.044851933047175406,
|
|
"num_tokens": 104560.0,
|
|
"step": 50
|
|
},
|
|
{
|
|
"entropy": 10.577375888824463,
|
|
"epoch": 0.049977283053157656,
|
|
"grad_norm": 2.515625,
|
|
"learning_rate": 2.7e-05,
|
|
"loss": 9.471,
|
|
"mean_token_accuracy": 0.05021349526941776,
|
|
"num_tokens": 115359.0,
|
|
"step": 55
|
|
},
|
|
{
|
|
"entropy": 10.536783027648926,
|
|
"epoch": 0.05452067242162653,
|
|
"grad_norm": 2.3125,
|
|
"learning_rate": 2.95e-05,
|
|
"loss": 9.4476,
|
|
"mean_token_accuracy": 0.046129952371120456,
|
|
"num_tokens": 126504.0,
|
|
"step": 60
|
|
},
|
|
{
|
|
"entropy": 10.529264354705811,
|
|
"epoch": 0.059064061790095414,
|
|
"grad_norm": 2.390625,
|
|
"learning_rate": 3.2e-05,
|
|
"loss": 9.3051,
|
|
"mean_token_accuracy": 0.06012832373380661,
|
|
"num_tokens": 136449.0,
|
|
"step": 65
|
|
},
|
|
{
|
|
"entropy": 10.412603759765625,
|
|
"epoch": 0.06360745115856428,
|
|
"grad_norm": 2.3125,
|
|
"learning_rate": 3.4500000000000005e-05,
|
|
"loss": 9.155,
|
|
"mean_token_accuracy": 0.06461884267628193,
|
|
"num_tokens": 145959.0,
|
|
"step": 70
|
|
},
|
|
{
|
|
"entropy": 10.43828363418579,
|
|
"epoch": 0.06815084052703317,
|
|
"grad_norm": 2.28125,
|
|
"learning_rate": 3.7e-05,
|
|
"loss": 9.22,
|
|
"mean_token_accuracy": 0.059075624123215674,
|
|
"num_tokens": 158533.0,
|
|
"step": 75
|
|
},
|
|
{
|
|
"entropy": 10.466318130493164,
|
|
"epoch": 0.07269422989550205,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 3.95e-05,
|
|
"loss": 9.0343,
|
|
"mean_token_accuracy": 0.06960411444306373,
|
|
"num_tokens": 168776.0,
|
|
"step": 80
|
|
},
|
|
{
|
|
"entropy": 10.39024019241333,
|
|
"epoch": 0.07723761926397092,
|
|
"grad_norm": 2.34375,
|
|
"learning_rate": 4.2000000000000004e-05,
|
|
"loss": 8.9383,
|
|
"mean_token_accuracy": 0.07182483375072479,
|
|
"num_tokens": 179528.0,
|
|
"step": 85
|
|
},
|
|
{
|
|
"entropy": 10.281378364562988,
|
|
"epoch": 0.0817810086324398,
|
|
"grad_norm": 3.875,
|
|
"learning_rate": 4.45e-05,
|
|
"loss": 8.8613,
|
|
"mean_token_accuracy": 0.06785103790462017,
|
|
"num_tokens": 190092.0,
|
|
"step": 90
|
|
},
|
|
{
|
|
"entropy": 10.292144680023194,
|
|
"epoch": 0.08632439800090867,
|
|
"grad_norm": 2.265625,
|
|
"learning_rate": 4.7000000000000004e-05,
|
|
"loss": 8.7131,
|
|
"mean_token_accuracy": 0.07463023066520691,
|
|
"num_tokens": 200836.0,
|
|
"step": 95
|
|
},
|
|
{
|
|
"entropy": 10.18975601196289,
|
|
"epoch": 0.09086778736937756,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 4.9500000000000004e-05,
|
|
"loss": 8.5996,
|
|
"mean_token_accuracy": 0.07846152037382126,
|
|
"num_tokens": 210585.0,
|
|
"step": 100
|
|
},
|
|
{
|
|
"entropy": 10.163002014160156,
|
|
"epoch": 0.09541117673784644,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 5.2e-05,
|
|
"loss": 8.4849,
|
|
"mean_token_accuracy": 0.08028437122702599,
|
|
"num_tokens": 221439.0,
|
|
"step": 105
|
|
},
|
|
{
|
|
"entropy": 10.084406471252441,
|
|
"epoch": 0.09995456610631531,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 5.45e-05,
|
|
"loss": 8.4253,
|
|
"mean_token_accuracy": 0.07408776879310608,
|
|
"num_tokens": 232634.0,
|
|
"step": 110
|
|
},
|
|
{
|
|
"entropy": 10.001629829406738,
|
|
"epoch": 0.10449795547478419,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 5.7e-05,
|
|
"loss": 8.2732,
|
|
"mean_token_accuracy": 0.0823720321059227,
|
|
"num_tokens": 242753.0,
|
|
"step": 115
|
|
},
|
|
{
|
|
"entropy": 9.940981578826904,
|
|
"epoch": 0.10904134484325306,
|
|
"grad_norm": 1.953125,
|
|
"learning_rate": 5.9499999999999996e-05,
|
|
"loss": 8.1486,
|
|
"mean_token_accuracy": 0.08088770657777786,
|
|
"num_tokens": 252748.0,
|
|
"step": 120
|
|
},
|
|
{
|
|
"entropy": 9.771773052215575,
|
|
"epoch": 0.11358473421172194,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 6.2e-05,
|
|
"loss": 8.0161,
|
|
"mean_token_accuracy": 0.08380886614322662,
|
|
"num_tokens": 262772.0,
|
|
"step": 125
|
|
},
|
|
{
|
|
"entropy": 9.701642322540284,
|
|
"epoch": 0.11812812358019083,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 6.450000000000001e-05,
|
|
"loss": 7.9033,
|
|
"mean_token_accuracy": 0.07984891161322594,
|
|
"num_tokens": 273099.0,
|
|
"step": 130
|
|
},
|
|
{
|
|
"entropy": 9.504860591888427,
|
|
"epoch": 0.1226715129486597,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 6.7e-05,
|
|
"loss": 7.7777,
|
|
"mean_token_accuracy": 0.08303077444434166,
|
|
"num_tokens": 282882.0,
|
|
"step": 135
|
|
},
|
|
{
|
|
"entropy": 9.314452743530273,
|
|
"epoch": 0.12721490231712856,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 6.950000000000001e-05,
|
|
"loss": 7.7038,
|
|
"mean_token_accuracy": 0.08235853761434556,
|
|
"num_tokens": 294484.0,
|
|
"step": 140
|
|
},
|
|
{
|
|
"entropy": 9.094099140167236,
|
|
"epoch": 0.13175829168559747,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 7.2e-05,
|
|
"loss": 7.6156,
|
|
"mean_token_accuracy": 0.08289074972271919,
|
|
"num_tokens": 305154.0,
|
|
"step": 145
|
|
},
|
|
{
|
|
"entropy": 8.792550563812256,
|
|
"epoch": 0.13630168105406634,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 7.45e-05,
|
|
"loss": 7.4474,
|
|
"mean_token_accuracy": 0.09091320261359215,
|
|
"num_tokens": 315210.0,
|
|
"step": 150
|
|
},
|
|
{
|
|
"entropy": 8.602887630462646,
|
|
"epoch": 0.14084507042253522,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 7.7e-05,
|
|
"loss": 7.5223,
|
|
"mean_token_accuracy": 0.08537717014551163,
|
|
"num_tokens": 326043.0,
|
|
"step": 155
|
|
},
|
|
{
|
|
"entropy": 8.40032892227173,
|
|
"epoch": 0.1453884597910041,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 7.950000000000001e-05,
|
|
"loss": 7.4084,
|
|
"mean_token_accuracy": 0.0868705540895462,
|
|
"num_tokens": 335980.0,
|
|
"step": 160
|
|
},
|
|
{
|
|
"entropy": 8.238891696929931,
|
|
"epoch": 0.14993184915947297,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 8.2e-05,
|
|
"loss": 7.3518,
|
|
"mean_token_accuracy": 0.0846577376127243,
|
|
"num_tokens": 347094.0,
|
|
"step": 165
|
|
},
|
|
{
|
|
"entropy": 8.232883071899414,
|
|
"epoch": 0.15447523852794184,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 8.450000000000001e-05,
|
|
"loss": 7.3187,
|
|
"mean_token_accuracy": 0.0876984566450119,
|
|
"num_tokens": 358150.0,
|
|
"step": 170
|
|
},
|
|
{
|
|
"entropy": 7.981767082214356,
|
|
"epoch": 0.15901862789641072,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 8.7e-05,
|
|
"loss": 7.1827,
|
|
"mean_token_accuracy": 0.08798569217324256,
|
|
"num_tokens": 368996.0,
|
|
"step": 175
|
|
},
|
|
{
|
|
"entropy": 7.891178703308105,
|
|
"epoch": 0.1635620172648796,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 8.95e-05,
|
|
"loss": 7.2475,
|
|
"mean_token_accuracy": 0.09550588801503182,
|
|
"num_tokens": 378567.0,
|
|
"step": 180
|
|
},
|
|
{
|
|
"entropy": 7.948905992507934,
|
|
"epoch": 0.16810540663334847,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 9.2e-05,
|
|
"loss": 7.2813,
|
|
"mean_token_accuracy": 0.08694516271352767,
|
|
"num_tokens": 388461.0,
|
|
"step": 185
|
|
},
|
|
{
|
|
"entropy": 7.791938257217407,
|
|
"epoch": 0.17264879600181735,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 9.45e-05,
|
|
"loss": 7.1569,
|
|
"mean_token_accuracy": 0.09532128497958184,
|
|
"num_tokens": 399353.0,
|
|
"step": 190
|
|
},
|
|
{
|
|
"entropy": 7.853602457046509,
|
|
"epoch": 0.17719218537028622,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 9.7e-05,
|
|
"loss": 7.2436,
|
|
"mean_token_accuracy": 0.08666228726506234,
|
|
"num_tokens": 409282.0,
|
|
"step": 195
|
|
},
|
|
{
|
|
"entropy": 7.708158397674561,
|
|
"epoch": 0.18173557473875512,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 9.95e-05,
|
|
"loss": 7.1465,
|
|
"mean_token_accuracy": 0.09066225066781045,
|
|
"num_tokens": 420844.0,
|
|
"step": 200
|
|
},
|
|
{
|
|
"entropy": 7.8060750484466555,
|
|
"epoch": 0.186278964107224,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.000102,
|
|
"loss": 7.1545,
|
|
"mean_token_accuracy": 0.08872071430087089,
|
|
"num_tokens": 431681.0,
|
|
"step": 205
|
|
},
|
|
{
|
|
"entropy": 7.521131896972657,
|
|
"epoch": 0.19082235347569287,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00010449999999999999,
|
|
"loss": 7.1005,
|
|
"mean_token_accuracy": 0.09334186390042305,
|
|
"num_tokens": 441617.0,
|
|
"step": 210
|
|
},
|
|
{
|
|
"entropy": 7.723299789428711,
|
|
"epoch": 0.19536574284416175,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.000107,
|
|
"loss": 7.0738,
|
|
"mean_token_accuracy": 0.09614492207765579,
|
|
"num_tokens": 451165.0,
|
|
"step": 215
|
|
},
|
|
{
|
|
"entropy": 7.528104972839356,
|
|
"epoch": 0.19990913221263062,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0001095,
|
|
"loss": 7.047,
|
|
"mean_token_accuracy": 0.09558017253875732,
|
|
"num_tokens": 461205.0,
|
|
"step": 220
|
|
},
|
|
{
|
|
"entropy": 7.59382004737854,
|
|
"epoch": 0.2044525215810995,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.000112,
|
|
"loss": 7.0261,
|
|
"mean_token_accuracy": 0.09080673456192016,
|
|
"num_tokens": 471409.0,
|
|
"step": 225
|
|
},
|
|
{
|
|
"entropy": 7.570555877685547,
|
|
"epoch": 0.20899591094956838,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0001145,
|
|
"loss": 7.0239,
|
|
"mean_token_accuracy": 0.09434545040130615,
|
|
"num_tokens": 480741.0,
|
|
"step": 230
|
|
},
|
|
{
|
|
"entropy": 7.4990636825561525,
|
|
"epoch": 0.21353930031803725,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00011700000000000001,
|
|
"loss": 7.0382,
|
|
"mean_token_accuracy": 0.09171517789363862,
|
|
"num_tokens": 491576.0,
|
|
"step": 235
|
|
},
|
|
{
|
|
"entropy": 7.489644718170166,
|
|
"epoch": 0.21808268968650613,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00011949999999999999,
|
|
"loss": 7.0266,
|
|
"mean_token_accuracy": 0.09193908870220184,
|
|
"num_tokens": 503121.0,
|
|
"step": 240
|
|
},
|
|
{
|
|
"entropy": 7.529499769210815,
|
|
"epoch": 0.222626079054975,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.000122,
|
|
"loss": 6.9917,
|
|
"mean_token_accuracy": 0.08934131860733033,
|
|
"num_tokens": 513956.0,
|
|
"step": 245
|
|
},
|
|
{
|
|
"entropy": 7.528982019424438,
|
|
"epoch": 0.22716946842344388,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0001245,
|
|
"loss": 7.0225,
|
|
"mean_token_accuracy": 0.09366922527551651,
|
|
"num_tokens": 525043.0,
|
|
"step": 250
|
|
},
|
|
{
|
|
"entropy": 7.4644406795501705,
|
|
"epoch": 0.23171285779191278,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.000127,
|
|
"loss": 6.9558,
|
|
"mean_token_accuracy": 0.10055001303553582,
|
|
"num_tokens": 535824.0,
|
|
"step": 255
|
|
},
|
|
{
|
|
"entropy": 7.484562730789184,
|
|
"epoch": 0.23625624716038165,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0001295,
|
|
"loss": 6.9765,
|
|
"mean_token_accuracy": 0.09478841349482536,
|
|
"num_tokens": 546553.0,
|
|
"step": 260
|
|
},
|
|
{
|
|
"entropy": 7.449831628799439,
|
|
"epoch": 0.24079963652885053,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.000132,
|
|
"loss": 6.9221,
|
|
"mean_token_accuracy": 0.09788105860352517,
|
|
"num_tokens": 556637.0,
|
|
"step": 265
|
|
},
|
|
{
|
|
"entropy": 7.346249198913574,
|
|
"epoch": 0.2453430258973194,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00013450000000000002,
|
|
"loss": 6.9499,
|
|
"mean_token_accuracy": 0.09590627774596214,
|
|
"num_tokens": 568464.0,
|
|
"step": 270
|
|
},
|
|
{
|
|
"entropy": 7.440023136138916,
|
|
"epoch": 0.24988641526578828,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00013700000000000002,
|
|
"loss": 6.9988,
|
|
"mean_token_accuracy": 0.09769970029592515,
|
|
"num_tokens": 579387.0,
|
|
"step": 275
|
|
},
|
|
{
|
|
"entropy": 7.344238996505737,
|
|
"epoch": 0.25442980463425713,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0001395,
|
|
"loss": 7.0771,
|
|
"mean_token_accuracy": 0.09503750577569008,
|
|
"num_tokens": 590524.0,
|
|
"step": 280
|
|
},
|
|
{
|
|
"entropy": 7.465632104873658,
|
|
"epoch": 0.25897319400272606,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00014199999999999998,
|
|
"loss": 6.9365,
|
|
"mean_token_accuracy": 0.09854642376303673,
|
|
"num_tokens": 601570.0,
|
|
"step": 285
|
|
},
|
|
{
|
|
"entropy": 7.3490095138549805,
|
|
"epoch": 0.26351658337119493,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0001445,
|
|
"loss": 6.8802,
|
|
"mean_token_accuracy": 0.09717997089028359,
|
|
"num_tokens": 611615.0,
|
|
"step": 290
|
|
},
|
|
{
|
|
"entropy": 7.340326023101807,
|
|
"epoch": 0.2680599727396638,
|
|
"grad_norm": 2.34375,
|
|
"learning_rate": 0.000147,
|
|
"loss": 6.9172,
|
|
"mean_token_accuracy": 0.09668021574616432,
|
|
"num_tokens": 621077.0,
|
|
"step": 295
|
|
},
|
|
{
|
|
"entropy": 7.310168886184693,
|
|
"epoch": 0.2726033621081327,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0001495,
|
|
"loss": 6.865,
|
|
"mean_token_accuracy": 0.09947703778743744,
|
|
"num_tokens": 631235.0,
|
|
"step": 300
|
|
},
|
|
{
|
|
"entropy": 7.346650838851929,
|
|
"epoch": 0.27714675147660156,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.000152,
|
|
"loss": 6.8915,
|
|
"mean_token_accuracy": 0.10305262729525566,
|
|
"num_tokens": 641195.0,
|
|
"step": 305
|
|
},
|
|
{
|
|
"entropy": 7.243460988998413,
|
|
"epoch": 0.28169014084507044,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00015450000000000001,
|
|
"loss": 6.899,
|
|
"mean_token_accuracy": 0.09924287423491478,
|
|
"num_tokens": 651420.0,
|
|
"step": 310
|
|
},
|
|
{
|
|
"entropy": 7.327885532379151,
|
|
"epoch": 0.2862335302135393,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.000157,
|
|
"loss": 6.8654,
|
|
"mean_token_accuracy": 0.10240009650588036,
|
|
"num_tokens": 661370.0,
|
|
"step": 315
|
|
},
|
|
{
|
|
"entropy": 7.278406858444214,
|
|
"epoch": 0.2907769195820082,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0001595,
|
|
"loss": 6.8022,
|
|
"mean_token_accuracy": 0.09714617282152176,
|
|
"num_tokens": 672237.0,
|
|
"step": 320
|
|
},
|
|
{
|
|
"entropy": 7.201946496963501,
|
|
"epoch": 0.29532030895047706,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.000162,
|
|
"loss": 6.8708,
|
|
"mean_token_accuracy": 0.1012646809220314,
|
|
"num_tokens": 682478.0,
|
|
"step": 325
|
|
},
|
|
{
|
|
"entropy": 7.349485778808594,
|
|
"epoch": 0.29986369831894594,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00016450000000000001,
|
|
"loss": 6.9835,
|
|
"mean_token_accuracy": 0.09188964888453484,
|
|
"num_tokens": 693669.0,
|
|
"step": 330
|
|
},
|
|
{
|
|
"entropy": 7.099835443496704,
|
|
"epoch": 0.3044070876874148,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00016700000000000002,
|
|
"loss": 6.7072,
|
|
"mean_token_accuracy": 0.10328638926148415,
|
|
"num_tokens": 704260.0,
|
|
"step": 335
|
|
},
|
|
{
|
|
"entropy": 7.186357593536377,
|
|
"epoch": 0.3089504770558837,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.00016950000000000003,
|
|
"loss": 6.6935,
|
|
"mean_token_accuracy": 0.1045442394912243,
|
|
"num_tokens": 713924.0,
|
|
"step": 340
|
|
},
|
|
{
|
|
"entropy": 7.213700151443481,
|
|
"epoch": 0.31349386642435256,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00017199999999999998,
|
|
"loss": 6.8839,
|
|
"mean_token_accuracy": 0.0973054438829422,
|
|
"num_tokens": 724208.0,
|
|
"step": 345
|
|
},
|
|
{
|
|
"entropy": 7.211179637908936,
|
|
"epoch": 0.31803725579282144,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00017449999999999999,
|
|
"loss": 6.7871,
|
|
"mean_token_accuracy": 0.10154509842395783,
|
|
"num_tokens": 733730.0,
|
|
"step": 350
|
|
},
|
|
{
|
|
"entropy": 7.0504943370819095,
|
|
"epoch": 0.3225806451612903,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.000177,
|
|
"loss": 6.745,
|
|
"mean_token_accuracy": 0.10221930891275406,
|
|
"num_tokens": 743467.0,
|
|
"step": 355
|
|
},
|
|
{
|
|
"entropy": 7.2732799530029295,
|
|
"epoch": 0.3271240345297592,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0001795,
|
|
"loss": 6.878,
|
|
"mean_token_accuracy": 0.10214311555027962,
|
|
"num_tokens": 753446.0,
|
|
"step": 360
|
|
},
|
|
{
|
|
"entropy": 7.161293411254883,
|
|
"epoch": 0.33166742389822806,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.000182,
|
|
"loss": 6.8045,
|
|
"mean_token_accuracy": 0.09740775153040886,
|
|
"num_tokens": 763257.0,
|
|
"step": 365
|
|
},
|
|
{
|
|
"entropy": 7.1125328540802,
|
|
"epoch": 0.33621081326669694,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0001845,
|
|
"loss": 6.7808,
|
|
"mean_token_accuracy": 0.10515827611088753,
|
|
"num_tokens": 773322.0,
|
|
"step": 370
|
|
},
|
|
{
|
|
"entropy": 7.063180541992187,
|
|
"epoch": 0.3407542026351658,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.000187,
|
|
"loss": 6.8664,
|
|
"mean_token_accuracy": 0.09914991706609726,
|
|
"num_tokens": 784297.0,
|
|
"step": 375
|
|
},
|
|
{
|
|
"entropy": 7.194390058517456,
|
|
"epoch": 0.3452975920036347,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0001895,
|
|
"loss": 6.8432,
|
|
"mean_token_accuracy": 0.0979395940899849,
|
|
"num_tokens": 795186.0,
|
|
"step": 380
|
|
},
|
|
{
|
|
"entropy": 7.138232707977295,
|
|
"epoch": 0.34984098137210357,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000192,
|
|
"loss": 6.7456,
|
|
"mean_token_accuracy": 0.10714830458164215,
|
|
"num_tokens": 805802.0,
|
|
"step": 385
|
|
},
|
|
{
|
|
"entropy": 7.068744134902954,
|
|
"epoch": 0.35438437074057244,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0001945,
|
|
"loss": 6.7036,
|
|
"mean_token_accuracy": 0.10414793938398362,
|
|
"num_tokens": 816581.0,
|
|
"step": 390
|
|
},
|
|
{
|
|
"entropy": 7.050993919372559,
|
|
"epoch": 0.35892776010904137,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00019700000000000002,
|
|
"loss": 6.7162,
|
|
"mean_token_accuracy": 0.10066760554909707,
|
|
"num_tokens": 826724.0,
|
|
"step": 395
|
|
},
|
|
{
|
|
"entropy": 7.132152462005616,
|
|
"epoch": 0.36347114947751025,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00019950000000000002,
|
|
"loss": 6.7557,
|
|
"mean_token_accuracy": 0.10789255201816558,
|
|
"num_tokens": 836431.0,
|
|
"step": 400
|
|
},
|
|
{
|
|
"entropy": 6.924490213394165,
|
|
"epoch": 0.3680145388459791,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.000202,
|
|
"loss": 6.673,
|
|
"mean_token_accuracy": 0.10689961239695549,
|
|
"num_tokens": 846888.0,
|
|
"step": 405
|
|
},
|
|
{
|
|
"entropy": 7.120433712005616,
|
|
"epoch": 0.372557928214448,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00020449999999999998,
|
|
"loss": 6.7498,
|
|
"mean_token_accuracy": 0.10389859899878502,
|
|
"num_tokens": 856062.0,
|
|
"step": 410
|
|
},
|
|
{
|
|
"entropy": 7.0627799987792965,
|
|
"epoch": 0.3771013175829169,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.000207,
|
|
"loss": 6.7656,
|
|
"mean_token_accuracy": 0.10278895348310471,
|
|
"num_tokens": 866489.0,
|
|
"step": 415
|
|
},
|
|
{
|
|
"entropy": 6.958880233764648,
|
|
"epoch": 0.38164470695138575,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0002095,
|
|
"loss": 6.6184,
|
|
"mean_token_accuracy": 0.1000476323068142,
|
|
"num_tokens": 876895.0,
|
|
"step": 420
|
|
},
|
|
{
|
|
"entropy": 7.133209085464477,
|
|
"epoch": 0.3861880963198546,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.000212,
|
|
"loss": 6.7897,
|
|
"mean_token_accuracy": 0.10413167849183083,
|
|
"num_tokens": 886931.0,
|
|
"step": 425
|
|
},
|
|
{
|
|
"entropy": 7.022590970993042,
|
|
"epoch": 0.3907314856883235,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0002145,
|
|
"loss": 6.7075,
|
|
"mean_token_accuracy": 0.10023215562105178,
|
|
"num_tokens": 896229.0,
|
|
"step": 430
|
|
},
|
|
{
|
|
"entropy": 6.995979881286621,
|
|
"epoch": 0.3952748750567924,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00021700000000000002,
|
|
"loss": 6.6555,
|
|
"mean_token_accuracy": 0.10956079438328743,
|
|
"num_tokens": 906668.0,
|
|
"step": 435
|
|
},
|
|
{
|
|
"entropy": 6.940561723709107,
|
|
"epoch": 0.39981826442526125,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0002195,
|
|
"loss": 6.648,
|
|
"mean_token_accuracy": 0.10910732224583626,
|
|
"num_tokens": 915868.0,
|
|
"step": 440
|
|
},
|
|
{
|
|
"entropy": 6.948301935195923,
|
|
"epoch": 0.4043616537937301,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.000222,
|
|
"loss": 6.7005,
|
|
"mean_token_accuracy": 0.10821465030312538,
|
|
"num_tokens": 926050.0,
|
|
"step": 445
|
|
},
|
|
{
|
|
"entropy": 6.959620666503906,
|
|
"epoch": 0.408905043162199,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0002245,
|
|
"loss": 6.5741,
|
|
"mean_token_accuracy": 0.1120890200138092,
|
|
"num_tokens": 936543.0,
|
|
"step": 450
|
|
},
|
|
{
|
|
"entropy": 6.945019960403442,
|
|
"epoch": 0.4134484325306679,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00022700000000000002,
|
|
"loss": 6.7137,
|
|
"mean_token_accuracy": 0.0983024187386036,
|
|
"num_tokens": 946895.0,
|
|
"step": 455
|
|
},
|
|
{
|
|
"entropy": 7.044814252853394,
|
|
"epoch": 0.41799182189913675,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00022950000000000002,
|
|
"loss": 6.7416,
|
|
"mean_token_accuracy": 0.10709839686751366,
|
|
"num_tokens": 956074.0,
|
|
"step": 460
|
|
},
|
|
{
|
|
"entropy": 6.954236841201782,
|
|
"epoch": 0.4225352112676056,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00023200000000000003,
|
|
"loss": 6.6696,
|
|
"mean_token_accuracy": 0.10691480711102486,
|
|
"num_tokens": 966264.0,
|
|
"step": 465
|
|
},
|
|
{
|
|
"entropy": 6.965500164031982,
|
|
"epoch": 0.4270786006360745,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00023449999999999998,
|
|
"loss": 6.7345,
|
|
"mean_token_accuracy": 0.1096844032406807,
|
|
"num_tokens": 976369.0,
|
|
"step": 470
|
|
},
|
|
{
|
|
"entropy": 6.890221691131591,
|
|
"epoch": 0.4316219900045434,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.000237,
|
|
"loss": 6.7048,
|
|
"mean_token_accuracy": 0.11195428147912026,
|
|
"num_tokens": 986948.0,
|
|
"step": 475
|
|
},
|
|
{
|
|
"entropy": 6.929348278045654,
|
|
"epoch": 0.43616537937301225,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0002395,
|
|
"loss": 6.6449,
|
|
"mean_token_accuracy": 0.10682991668581962,
|
|
"num_tokens": 996920.0,
|
|
"step": 480
|
|
},
|
|
{
|
|
"entropy": 6.977197074890137,
|
|
"epoch": 0.4407087687414811,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.000242,
|
|
"loss": 6.6733,
|
|
"mean_token_accuracy": 0.10687830671668053,
|
|
"num_tokens": 1006343.0,
|
|
"step": 485
|
|
},
|
|
{
|
|
"entropy": 6.894662284851075,
|
|
"epoch": 0.44525215810995,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0002445,
|
|
"loss": 6.5875,
|
|
"mean_token_accuracy": 0.1086734913289547,
|
|
"num_tokens": 1017156.0,
|
|
"step": 490
|
|
},
|
|
{
|
|
"entropy": 6.851984214782715,
|
|
"epoch": 0.4497955474784189,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.000247,
|
|
"loss": 6.6272,
|
|
"mean_token_accuracy": 0.10609063655138015,
|
|
"num_tokens": 1027082.0,
|
|
"step": 495
|
|
},
|
|
{
|
|
"entropy": 6.872963380813599,
|
|
"epoch": 0.45433893684688775,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0002495,
|
|
"loss": 6.6524,
|
|
"mean_token_accuracy": 0.10921891406178474,
|
|
"num_tokens": 1037458.0,
|
|
"step": 500
|
|
},
|
|
{
|
|
"entropy": 6.879157161712646,
|
|
"epoch": 0.45888232621535663,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.000252,
|
|
"loss": 6.6272,
|
|
"mean_token_accuracy": 0.10627908930182457,
|
|
"num_tokens": 1048391.0,
|
|
"step": 505
|
|
},
|
|
{
|
|
"entropy": 6.818037796020508,
|
|
"epoch": 0.46342571558382556,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0002545,
|
|
"loss": 6.5941,
|
|
"mean_token_accuracy": 0.10977126732468605,
|
|
"num_tokens": 1058281.0,
|
|
"step": 510
|
|
},
|
|
{
|
|
"entropy": 6.928041458129883,
|
|
"epoch": 0.46796910495229443,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000257,
|
|
"loss": 6.6453,
|
|
"mean_token_accuracy": 0.10617673844099045,
|
|
"num_tokens": 1069157.0,
|
|
"step": 515
|
|
},
|
|
{
|
|
"entropy": 6.9156416893005375,
|
|
"epoch": 0.4725124943207633,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0002595,
|
|
"loss": 6.6717,
|
|
"mean_token_accuracy": 0.11312429681420326,
|
|
"num_tokens": 1079986.0,
|
|
"step": 520
|
|
},
|
|
{
|
|
"entropy": 6.849049139022827,
|
|
"epoch": 0.4770558836892322,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.000262,
|
|
"loss": 6.6691,
|
|
"mean_token_accuracy": 0.1143962450325489,
|
|
"num_tokens": 1090414.0,
|
|
"step": 525
|
|
},
|
|
{
|
|
"entropy": 6.789116430282593,
|
|
"epoch": 0.48159927305770106,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00026450000000000003,
|
|
"loss": 6.5645,
|
|
"mean_token_accuracy": 0.11084540784358979,
|
|
"num_tokens": 1100909.0,
|
|
"step": 530
|
|
},
|
|
{
|
|
"entropy": 6.932785320281982,
|
|
"epoch": 0.48614266242616994,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00026700000000000004,
|
|
"loss": 6.6774,
|
|
"mean_token_accuracy": 0.11115043088793755,
|
|
"num_tokens": 1110780.0,
|
|
"step": 535
|
|
},
|
|
{
|
|
"entropy": 6.846625757217407,
|
|
"epoch": 0.4906860517946388,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00026950000000000005,
|
|
"loss": 6.5804,
|
|
"mean_token_accuracy": 0.10537252500653267,
|
|
"num_tokens": 1121669.0,
|
|
"step": 540
|
|
},
|
|
{
|
|
"entropy": 6.735438680648803,
|
|
"epoch": 0.4952294411631077,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00027200000000000005,
|
|
"loss": 6.5973,
|
|
"mean_token_accuracy": 0.11126141846179963,
|
|
"num_tokens": 1131892.0,
|
|
"step": 545
|
|
},
|
|
{
|
|
"entropy": 6.797910976409912,
|
|
"epoch": 0.49977283053157656,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0002745,
|
|
"loss": 6.5769,
|
|
"mean_token_accuracy": 0.10420559868216514,
|
|
"num_tokens": 1143911.0,
|
|
"step": 550
|
|
},
|
|
{
|
|
"entropy": 6.850543737411499,
|
|
"epoch": 0.5043162199000454,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000277,
|
|
"loss": 6.6045,
|
|
"mean_token_accuracy": 0.10880815088748932,
|
|
"num_tokens": 1154826.0,
|
|
"step": 555
|
|
},
|
|
{
|
|
"entropy": 6.842674684524536,
|
|
"epoch": 0.5088596092685143,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0002795,
|
|
"loss": 6.5888,
|
|
"mean_token_accuracy": 0.1078294150531292,
|
|
"num_tokens": 1164343.0,
|
|
"step": 560
|
|
},
|
|
{
|
|
"entropy": 6.748653364181519,
|
|
"epoch": 0.5134029986369832,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00028199999999999997,
|
|
"loss": 6.6014,
|
|
"mean_token_accuracy": 0.11128783077001572,
|
|
"num_tokens": 1174447.0,
|
|
"step": 565
|
|
},
|
|
{
|
|
"entropy": 6.780460023880005,
|
|
"epoch": 0.5179463880054521,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0002845,
|
|
"loss": 6.4939,
|
|
"mean_token_accuracy": 0.10823575183749198,
|
|
"num_tokens": 1186092.0,
|
|
"step": 570
|
|
},
|
|
{
|
|
"entropy": 6.844918966293335,
|
|
"epoch": 0.522489777373921,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.000287,
|
|
"loss": 6.6552,
|
|
"mean_token_accuracy": 0.11681408137083053,
|
|
"num_tokens": 1195151.0,
|
|
"step": 575
|
|
},
|
|
{
|
|
"entropy": 6.7070849418640135,
|
|
"epoch": 0.5270331667423899,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0002895,
|
|
"loss": 6.4827,
|
|
"mean_token_accuracy": 0.11342033669352532,
|
|
"num_tokens": 1204756.0,
|
|
"step": 580
|
|
},
|
|
{
|
|
"entropy": 6.668478345870971,
|
|
"epoch": 0.5315765561108587,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000292,
|
|
"loss": 6.4956,
|
|
"mean_token_accuracy": 0.11778365448117256,
|
|
"num_tokens": 1213573.0,
|
|
"step": 585
|
|
},
|
|
{
|
|
"entropy": 6.8163121223449705,
|
|
"epoch": 0.5361199454793276,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0002945,
|
|
"loss": 6.5003,
|
|
"mean_token_accuracy": 0.10915512219071388,
|
|
"num_tokens": 1224031.0,
|
|
"step": 590
|
|
},
|
|
{
|
|
"entropy": 6.67197813987732,
|
|
"epoch": 0.5406633348477965,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000297,
|
|
"loss": 6.5227,
|
|
"mean_token_accuracy": 0.11702188551425934,
|
|
"num_tokens": 1233679.0,
|
|
"step": 595
|
|
},
|
|
{
|
|
"entropy": 6.769627475738526,
|
|
"epoch": 0.5452067242162654,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0002995,
|
|
"loss": 6.5126,
|
|
"mean_token_accuracy": 0.12154011651873589,
|
|
"num_tokens": 1243877.0,
|
|
"step": 600
|
|
},
|
|
{
|
|
"entropy": 6.721151685714721,
|
|
"epoch": 0.5497501135847342,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000302,
|
|
"loss": 6.496,
|
|
"mean_token_accuracy": 0.12043491527438163,
|
|
"num_tokens": 1253913.0,
|
|
"step": 605
|
|
},
|
|
{
|
|
"entropy": 6.748045492172241,
|
|
"epoch": 0.5542935029532031,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0003045,
|
|
"loss": 6.5398,
|
|
"mean_token_accuracy": 0.11470362469553948,
|
|
"num_tokens": 1263895.0,
|
|
"step": 610
|
|
},
|
|
{
|
|
"entropy": 6.681035137176513,
|
|
"epoch": 0.558836892321672,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000307,
|
|
"loss": 6.5484,
|
|
"mean_token_accuracy": 0.10923809856176377,
|
|
"num_tokens": 1273695.0,
|
|
"step": 615
|
|
},
|
|
{
|
|
"entropy": 6.7565836906433105,
|
|
"epoch": 0.5633802816901409,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0003095,
|
|
"loss": 6.6568,
|
|
"mean_token_accuracy": 0.11423956826329232,
|
|
"num_tokens": 1285093.0,
|
|
"step": 620
|
|
},
|
|
{
|
|
"entropy": 6.78377594947815,
|
|
"epoch": 0.5679236710586097,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.000312,
|
|
"loss": 6.6084,
|
|
"mean_token_accuracy": 0.1104039043188095,
|
|
"num_tokens": 1295354.0,
|
|
"step": 625
|
|
},
|
|
{
|
|
"entropy": 6.641982460021973,
|
|
"epoch": 0.5724670604270786,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0003145,
|
|
"loss": 6.5779,
|
|
"mean_token_accuracy": 0.10812898948788643,
|
|
"num_tokens": 1305869.0,
|
|
"step": 630
|
|
},
|
|
{
|
|
"entropy": 6.779891061782837,
|
|
"epoch": 0.5770104497955475,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.000317,
|
|
"loss": 6.5507,
|
|
"mean_token_accuracy": 0.11241080686450004,
|
|
"num_tokens": 1315845.0,
|
|
"step": 635
|
|
},
|
|
{
|
|
"entropy": 6.662394618988037,
|
|
"epoch": 0.5815538391640164,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0003195,
|
|
"loss": 6.5999,
|
|
"mean_token_accuracy": 0.11409554556012154,
|
|
"num_tokens": 1326056.0,
|
|
"step": 640
|
|
},
|
|
{
|
|
"entropy": 6.768114376068115,
|
|
"epoch": 0.5860972285324852,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000322,
|
|
"loss": 6.5209,
|
|
"mean_token_accuracy": 0.11618900150060654,
|
|
"num_tokens": 1336843.0,
|
|
"step": 645
|
|
},
|
|
{
|
|
"entropy": 6.638251924514771,
|
|
"epoch": 0.5906406179009541,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00032450000000000003,
|
|
"loss": 6.3885,
|
|
"mean_token_accuracy": 0.12263384908437729,
|
|
"num_tokens": 1346106.0,
|
|
"step": 650
|
|
},
|
|
{
|
|
"entropy": 6.7041887760162355,
|
|
"epoch": 0.595184007269423,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00032700000000000003,
|
|
"loss": 6.498,
|
|
"mean_token_accuracy": 0.11787696108222008,
|
|
"num_tokens": 1356321.0,
|
|
"step": 655
|
|
},
|
|
{
|
|
"entropy": 6.629571962356567,
|
|
"epoch": 0.5997273966378919,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00032950000000000004,
|
|
"loss": 6.5542,
|
|
"mean_token_accuracy": 0.11547330170869827,
|
|
"num_tokens": 1367452.0,
|
|
"step": 660
|
|
},
|
|
{
|
|
"entropy": 6.644501113891602,
|
|
"epoch": 0.6042707860063607,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00033200000000000005,
|
|
"loss": 6.4496,
|
|
"mean_token_accuracy": 0.12300742790102959,
|
|
"num_tokens": 1377099.0,
|
|
"step": 665
|
|
},
|
|
{
|
|
"entropy": 6.647049760818481,
|
|
"epoch": 0.6088141753748296,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00033450000000000005,
|
|
"loss": 6.4602,
|
|
"mean_token_accuracy": 0.1089586578309536,
|
|
"num_tokens": 1387768.0,
|
|
"step": 670
|
|
},
|
|
{
|
|
"entropy": 6.568883752822876,
|
|
"epoch": 0.6133575647432985,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000337,
|
|
"loss": 6.4266,
|
|
"mean_token_accuracy": 0.11893959119915962,
|
|
"num_tokens": 1398703.0,
|
|
"step": 675
|
|
},
|
|
{
|
|
"entropy": 6.646634721755982,
|
|
"epoch": 0.6179009541117674,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0003395,
|
|
"loss": 6.4899,
|
|
"mean_token_accuracy": 0.11673004627227783,
|
|
"num_tokens": 1409059.0,
|
|
"step": 680
|
|
},
|
|
{
|
|
"entropy": 6.548872947692871,
|
|
"epoch": 0.6224443434802363,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.000342,
|
|
"loss": 6.4303,
|
|
"mean_token_accuracy": 0.12090117484331131,
|
|
"num_tokens": 1420100.0,
|
|
"step": 685
|
|
},
|
|
{
|
|
"entropy": 6.630219030380249,
|
|
"epoch": 0.6269877328487051,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00034449999999999997,
|
|
"loss": 6.4593,
|
|
"mean_token_accuracy": 0.11943159177899361,
|
|
"num_tokens": 1430052.0,
|
|
"step": 690
|
|
},
|
|
{
|
|
"entropy": 6.608811616897583,
|
|
"epoch": 0.631531122217174,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.000347,
|
|
"loss": 6.5102,
|
|
"mean_token_accuracy": 0.11295234113931656,
|
|
"num_tokens": 1441466.0,
|
|
"step": 695
|
|
},
|
|
{
|
|
"entropy": 6.656955623626709,
|
|
"epoch": 0.6360745115856429,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0003495,
|
|
"loss": 6.4618,
|
|
"mean_token_accuracy": 0.11585693284869195,
|
|
"num_tokens": 1451839.0,
|
|
"step": 700
|
|
},
|
|
{
|
|
"entropy": 6.55370454788208,
|
|
"epoch": 0.6406179009541118,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.000352,
|
|
"loss": 6.4039,
|
|
"mean_token_accuracy": 0.11986656337976456,
|
|
"num_tokens": 1461287.0,
|
|
"step": 705
|
|
},
|
|
{
|
|
"entropy": 6.56372971534729,
|
|
"epoch": 0.6451612903225806,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0003545,
|
|
"loss": 6.5055,
|
|
"mean_token_accuracy": 0.10829323157668114,
|
|
"num_tokens": 1471912.0,
|
|
"step": 710
|
|
},
|
|
{
|
|
"entropy": 6.684666442871094,
|
|
"epoch": 0.6497046796910495,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.000357,
|
|
"loss": 6.5568,
|
|
"mean_token_accuracy": 0.11624274030327797,
|
|
"num_tokens": 1482912.0,
|
|
"step": 715
|
|
},
|
|
{
|
|
"entropy": 6.4966638565063475,
|
|
"epoch": 0.6542480690595184,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0003595,
|
|
"loss": 6.4357,
|
|
"mean_token_accuracy": 0.11463170126080513,
|
|
"num_tokens": 1493226.0,
|
|
"step": 720
|
|
},
|
|
{
|
|
"entropy": 6.621252202987671,
|
|
"epoch": 0.6587914584279873,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000362,
|
|
"loss": 6.5498,
|
|
"mean_token_accuracy": 0.11490358039736748,
|
|
"num_tokens": 1503411.0,
|
|
"step": 725
|
|
},
|
|
{
|
|
"entropy": 6.703120422363281,
|
|
"epoch": 0.6633348477964561,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0003645,
|
|
"loss": 6.5453,
|
|
"mean_token_accuracy": 0.11521322354674339,
|
|
"num_tokens": 1513715.0,
|
|
"step": 730
|
|
},
|
|
{
|
|
"entropy": 6.6506260395050045,
|
|
"epoch": 0.667878237164925,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.000367,
|
|
"loss": 6.5034,
|
|
"mean_token_accuracy": 0.11211693659424782,
|
|
"num_tokens": 1524309.0,
|
|
"step": 735
|
|
},
|
|
{
|
|
"entropy": 6.5112879276275635,
|
|
"epoch": 0.6724216265333939,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0003695,
|
|
"loss": 6.5256,
|
|
"mean_token_accuracy": 0.1152856782078743,
|
|
"num_tokens": 1534901.0,
|
|
"step": 740
|
|
},
|
|
{
|
|
"entropy": 6.618919229507446,
|
|
"epoch": 0.6769650159018628,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000372,
|
|
"loss": 6.3946,
|
|
"mean_token_accuracy": 0.11816890388727189,
|
|
"num_tokens": 1544576.0,
|
|
"step": 745
|
|
},
|
|
{
|
|
"entropy": 6.500910997390747,
|
|
"epoch": 0.6815084052703316,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0003745,
|
|
"loss": 6.4213,
|
|
"mean_token_accuracy": 0.11983850598335266,
|
|
"num_tokens": 1554800.0,
|
|
"step": 750
|
|
},
|
|
{
|
|
"entropy": 6.617109727859497,
|
|
"epoch": 0.6860517946388005,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.000377,
|
|
"loss": 6.4735,
|
|
"mean_token_accuracy": 0.12086164802312852,
|
|
"num_tokens": 1565166.0,
|
|
"step": 755
|
|
},
|
|
{
|
|
"entropy": 6.552991437911987,
|
|
"epoch": 0.6905951840072694,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0003795,
|
|
"loss": 6.4959,
|
|
"mean_token_accuracy": 0.1172470510005951,
|
|
"num_tokens": 1576211.0,
|
|
"step": 760
|
|
},
|
|
{
|
|
"entropy": 6.579512023925782,
|
|
"epoch": 0.6951385733757383,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.000382,
|
|
"loss": 6.4105,
|
|
"mean_token_accuracy": 0.11526432931423188,
|
|
"num_tokens": 1586444.0,
|
|
"step": 765
|
|
},
|
|
{
|
|
"entropy": 6.611948537826538,
|
|
"epoch": 0.6996819627442071,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0003845,
|
|
"loss": 6.4112,
|
|
"mean_token_accuracy": 0.12121847867965699,
|
|
"num_tokens": 1596886.0,
|
|
"step": 770
|
|
},
|
|
{
|
|
"entropy": 6.387885427474975,
|
|
"epoch": 0.704225352112676,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00038700000000000003,
|
|
"loss": 6.3065,
|
|
"mean_token_accuracy": 0.12513158097863197,
|
|
"num_tokens": 1606383.0,
|
|
"step": 775
|
|
},
|
|
{
|
|
"entropy": 6.478776264190674,
|
|
"epoch": 0.7087687414811449,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00038950000000000003,
|
|
"loss": 6.4026,
|
|
"mean_token_accuracy": 0.11760507896542549,
|
|
"num_tokens": 1616747.0,
|
|
"step": 780
|
|
},
|
|
{
|
|
"entropy": 6.545230388641357,
|
|
"epoch": 0.7133121308496138,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00039200000000000004,
|
|
"loss": 6.3592,
|
|
"mean_token_accuracy": 0.12122382372617721,
|
|
"num_tokens": 1626760.0,
|
|
"step": 785
|
|
},
|
|
{
|
|
"entropy": 6.550805711746216,
|
|
"epoch": 0.7178555202180827,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00039450000000000005,
|
|
"loss": 6.5778,
|
|
"mean_token_accuracy": 0.11731743440032005,
|
|
"num_tokens": 1636419.0,
|
|
"step": 790
|
|
},
|
|
{
|
|
"entropy": 6.451327610015869,
|
|
"epoch": 0.7223989095865516,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00039700000000000005,
|
|
"loss": 6.3539,
|
|
"mean_token_accuracy": 0.12045771181583405,
|
|
"num_tokens": 1646349.0,
|
|
"step": 795
|
|
},
|
|
{
|
|
"entropy": 6.549941158294677,
|
|
"epoch": 0.7269422989550205,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0003995,
|
|
"loss": 6.425,
|
|
"mean_token_accuracy": 0.12031189724802971,
|
|
"num_tokens": 1657693.0,
|
|
"step": 800
|
|
},
|
|
{
|
|
"entropy": 6.502531576156616,
|
|
"epoch": 0.7314856883234894,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000402,
|
|
"loss": 6.369,
|
|
"mean_token_accuracy": 0.11813340857625007,
|
|
"num_tokens": 1667689.0,
|
|
"step": 805
|
|
},
|
|
{
|
|
"entropy": 6.473275232315063,
|
|
"epoch": 0.7360290776919582,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004045,
|
|
"loss": 6.3412,
|
|
"mean_token_accuracy": 0.127835476398468,
|
|
"num_tokens": 1677402.0,
|
|
"step": 810
|
|
},
|
|
{
|
|
"entropy": 6.365635585784912,
|
|
"epoch": 0.7405724670604271,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00040699999999999997,
|
|
"loss": 6.2735,
|
|
"mean_token_accuracy": 0.12139133512973785,
|
|
"num_tokens": 1687285.0,
|
|
"step": 815
|
|
},
|
|
{
|
|
"entropy": 6.558733177185059,
|
|
"epoch": 0.745115856428896,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004095,
|
|
"loss": 6.5708,
|
|
"mean_token_accuracy": 0.10980626493692398,
|
|
"num_tokens": 1697784.0,
|
|
"step": 820
|
|
},
|
|
{
|
|
"entropy": 6.504992198944092,
|
|
"epoch": 0.7496592457973649,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000412,
|
|
"loss": 6.3909,
|
|
"mean_token_accuracy": 0.11993959099054337,
|
|
"num_tokens": 1708313.0,
|
|
"step": 825
|
|
},
|
|
{
|
|
"entropy": 6.4220723628997805,
|
|
"epoch": 0.7542026351658337,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004145,
|
|
"loss": 6.3418,
|
|
"mean_token_accuracy": 0.12350277826189995,
|
|
"num_tokens": 1718278.0,
|
|
"step": 830
|
|
},
|
|
{
|
|
"entropy": 6.451784753799439,
|
|
"epoch": 0.7587460245343026,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000417,
|
|
"loss": 6.3756,
|
|
"mean_token_accuracy": 0.119990985840559,
|
|
"num_tokens": 1729430.0,
|
|
"step": 835
|
|
},
|
|
{
|
|
"entropy": 6.453255462646484,
|
|
"epoch": 0.7632894139027715,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004195,
|
|
"loss": 6.3419,
|
|
"mean_token_accuracy": 0.12214131876826287,
|
|
"num_tokens": 1740759.0,
|
|
"step": 840
|
|
},
|
|
{
|
|
"entropy": 6.459233808517456,
|
|
"epoch": 0.7678328032712404,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000422,
|
|
"loss": 6.4063,
|
|
"mean_token_accuracy": 0.1200601689517498,
|
|
"num_tokens": 1751519.0,
|
|
"step": 845
|
|
},
|
|
{
|
|
"entropy": 6.4423778533935545,
|
|
"epoch": 0.7723761926397092,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004245,
|
|
"loss": 6.3652,
|
|
"mean_token_accuracy": 0.12372113093733787,
|
|
"num_tokens": 1761731.0,
|
|
"step": 850
|
|
},
|
|
{
|
|
"entropy": 6.378735780715942,
|
|
"epoch": 0.7769195820081781,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000427,
|
|
"loss": 6.2778,
|
|
"mean_token_accuracy": 0.12224024012684823,
|
|
"num_tokens": 1771949.0,
|
|
"step": 855
|
|
},
|
|
{
|
|
"entropy": 6.358287000656128,
|
|
"epoch": 0.781462971376647,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004295,
|
|
"loss": 6.3825,
|
|
"mean_token_accuracy": 0.12915819510817528,
|
|
"num_tokens": 1782923.0,
|
|
"step": 860
|
|
},
|
|
{
|
|
"entropy": 6.5328343391418455,
|
|
"epoch": 0.7860063607451159,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.000432,
|
|
"loss": 6.4885,
|
|
"mean_token_accuracy": 0.1134648710489273,
|
|
"num_tokens": 1792986.0,
|
|
"step": 865
|
|
},
|
|
{
|
|
"entropy": 6.601466178894043,
|
|
"epoch": 0.7905497501135847,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004345,
|
|
"loss": 6.4821,
|
|
"mean_token_accuracy": 0.11608704775571824,
|
|
"num_tokens": 1804820.0,
|
|
"step": 870
|
|
},
|
|
{
|
|
"entropy": 6.368373203277588,
|
|
"epoch": 0.7950931394820536,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000437,
|
|
"loss": 6.4323,
|
|
"mean_token_accuracy": 0.12307631820440293,
|
|
"num_tokens": 1815360.0,
|
|
"step": 875
|
|
},
|
|
{
|
|
"entropy": 6.398289680480957,
|
|
"epoch": 0.7996365288505225,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004395,
|
|
"loss": 6.4034,
|
|
"mean_token_accuracy": 0.11827710643410683,
|
|
"num_tokens": 1826374.0,
|
|
"step": 880
|
|
},
|
|
{
|
|
"entropy": 6.460321140289307,
|
|
"epoch": 0.8041799182189914,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000442,
|
|
"loss": 6.3476,
|
|
"mean_token_accuracy": 0.11750650107860565,
|
|
"num_tokens": 1836535.0,
|
|
"step": 885
|
|
},
|
|
{
|
|
"entropy": 6.503727102279663,
|
|
"epoch": 0.8087233075874602,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004445,
|
|
"loss": 6.4294,
|
|
"mean_token_accuracy": 0.11657789722084999,
|
|
"num_tokens": 1846678.0,
|
|
"step": 890
|
|
},
|
|
{
|
|
"entropy": 6.358234071731568,
|
|
"epoch": 0.8132666969559291,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.000447,
|
|
"loss": 6.4212,
|
|
"mean_token_accuracy": 0.11958692297339439,
|
|
"num_tokens": 1856883.0,
|
|
"step": 895
|
|
},
|
|
{
|
|
"entropy": 6.430210161209106,
|
|
"epoch": 0.817810086324398,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00044950000000000003,
|
|
"loss": 6.3803,
|
|
"mean_token_accuracy": 0.12223695889115334,
|
|
"num_tokens": 1866814.0,
|
|
"step": 900
|
|
},
|
|
{
|
|
"entropy": 6.4646649837493895,
|
|
"epoch": 0.8223534756928669,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00045200000000000004,
|
|
"loss": 6.4072,
|
|
"mean_token_accuracy": 0.12242427542805671,
|
|
"num_tokens": 1877136.0,
|
|
"step": 905
|
|
},
|
|
{
|
|
"entropy": 6.434080982208252,
|
|
"epoch": 0.8268968650613358,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00045450000000000004,
|
|
"loss": 6.4273,
|
|
"mean_token_accuracy": 0.12286214902997017,
|
|
"num_tokens": 1887801.0,
|
|
"step": 910
|
|
},
|
|
{
|
|
"entropy": 6.391744661331177,
|
|
"epoch": 0.8314402544298046,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00045700000000000005,
|
|
"loss": 6.243,
|
|
"mean_token_accuracy": 0.12523403987288476,
|
|
"num_tokens": 1898313.0,
|
|
"step": 915
|
|
},
|
|
{
|
|
"entropy": 6.383115625381469,
|
|
"epoch": 0.8359836437982735,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00045950000000000006,
|
|
"loss": 6.3005,
|
|
"mean_token_accuracy": 0.1225958451628685,
|
|
"num_tokens": 1909306.0,
|
|
"step": 920
|
|
},
|
|
{
|
|
"entropy": 6.445513391494751,
|
|
"epoch": 0.8405270331667424,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.000462,
|
|
"loss": 6.3765,
|
|
"mean_token_accuracy": 0.12136013731360436,
|
|
"num_tokens": 1919406.0,
|
|
"step": 925
|
|
},
|
|
{
|
|
"entropy": 6.3957679271698,
|
|
"epoch": 0.8450704225352113,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004645,
|
|
"loss": 6.2993,
|
|
"mean_token_accuracy": 0.12907271087169647,
|
|
"num_tokens": 1929087.0,
|
|
"step": 930
|
|
},
|
|
{
|
|
"entropy": 6.272099876403809,
|
|
"epoch": 0.8496138119036801,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000467,
|
|
"loss": 6.2391,
|
|
"mean_token_accuracy": 0.12513313740491866,
|
|
"num_tokens": 1938647.0,
|
|
"step": 935
|
|
},
|
|
{
|
|
"entropy": 6.347430801391601,
|
|
"epoch": 0.854157201272149,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004695,
|
|
"loss": 6.2817,
|
|
"mean_token_accuracy": 0.12321201413869858,
|
|
"num_tokens": 1948237.0,
|
|
"step": 940
|
|
},
|
|
{
|
|
"entropy": 6.499377059936523,
|
|
"epoch": 0.8587005906406179,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000472,
|
|
"loss": 6.3808,
|
|
"mean_token_accuracy": 0.12037008255720139,
|
|
"num_tokens": 1958440.0,
|
|
"step": 945
|
|
},
|
|
{
|
|
"entropy": 6.301383686065674,
|
|
"epoch": 0.8632439800090868,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004745,
|
|
"loss": 6.2939,
|
|
"mean_token_accuracy": 0.12816702499985694,
|
|
"num_tokens": 1968388.0,
|
|
"step": 950
|
|
},
|
|
{
|
|
"entropy": 6.333843803405761,
|
|
"epoch": 0.8677873693775556,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000477,
|
|
"loss": 6.3915,
|
|
"mean_token_accuracy": 0.11608542948961258,
|
|
"num_tokens": 1979479.0,
|
|
"step": 955
|
|
},
|
|
{
|
|
"entropy": 6.333086395263672,
|
|
"epoch": 0.8723307587460245,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004795,
|
|
"loss": 6.2446,
|
|
"mean_token_accuracy": 0.12511033266782762,
|
|
"num_tokens": 1989680.0,
|
|
"step": 960
|
|
},
|
|
{
|
|
"entropy": 6.302000331878662,
|
|
"epoch": 0.8768741481144934,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000482,
|
|
"loss": 6.2962,
|
|
"mean_token_accuracy": 0.12111640349030495,
|
|
"num_tokens": 2000489.0,
|
|
"step": 965
|
|
},
|
|
{
|
|
"entropy": 6.3346357345581055,
|
|
"epoch": 0.8814175374829623,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004845,
|
|
"loss": 6.2418,
|
|
"mean_token_accuracy": 0.12388192564249038,
|
|
"num_tokens": 2010299.0,
|
|
"step": 970
|
|
},
|
|
{
|
|
"entropy": 6.205083179473877,
|
|
"epoch": 0.8859609268514311,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000487,
|
|
"loss": 6.2126,
|
|
"mean_token_accuracy": 0.1265421062707901,
|
|
"num_tokens": 2019374.0,
|
|
"step": 975
|
|
},
|
|
{
|
|
"entropy": 6.314967250823974,
|
|
"epoch": 0.8905043162199,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004895,
|
|
"loss": 6.2074,
|
|
"mean_token_accuracy": 0.13389402404427528,
|
|
"num_tokens": 2029222.0,
|
|
"step": 980
|
|
},
|
|
{
|
|
"entropy": 6.326553821563721,
|
|
"epoch": 0.8950477055883689,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000492,
|
|
"loss": 6.3335,
|
|
"mean_token_accuracy": 0.12566622868180274,
|
|
"num_tokens": 2041425.0,
|
|
"step": 985
|
|
},
|
|
{
|
|
"entropy": 6.355471420288086,
|
|
"epoch": 0.8995910949568378,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004945,
|
|
"loss": 6.4146,
|
|
"mean_token_accuracy": 0.12330245301127433,
|
|
"num_tokens": 2052618.0,
|
|
"step": 990
|
|
},
|
|
{
|
|
"entropy": 6.292330026626587,
|
|
"epoch": 0.9041344843253066,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000497,
|
|
"loss": 6.2855,
|
|
"mean_token_accuracy": 0.12251581624150276,
|
|
"num_tokens": 2064059.0,
|
|
"step": 995
|
|
},
|
|
{
|
|
"entropy": 6.2780286312103275,
|
|
"epoch": 0.9086778736937755,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004995,
|
|
"loss": 6.3067,
|
|
"mean_token_accuracy": 0.12127709686756134,
|
|
"num_tokens": 2075341.0,
|
|
"step": 1000
|
|
},
|
|
{
|
|
"epoch": 0.9086778736937755,
|
|
"eval_entropy": 6.218727421206097,
|
|
"eval_loss": 6.430349349975586,
|
|
"eval_mean_token_accuracy": 0.12361673391315826,
|
|
"eval_num_tokens": 2075341.0,
|
|
"eval_runtime": 2.6331,
|
|
"eval_samples_per_second": 1304.534,
|
|
"eval_steps_per_second": 163.304,
|
|
"step": 1000
|
|
},
|
|
{
|
|
"entropy": 6.206767177581787,
|
|
"epoch": 0.9132212630622444,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999998223471442,
|
|
"loss": 6.1819,
|
|
"mean_token_accuracy": 0.13016388192772865,
|
|
"num_tokens": 2085683.0,
|
|
"step": 1005
|
|
},
|
|
{
|
|
"entropy": 6.341091871261597,
|
|
"epoch": 0.9177646524307133,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999991006328981,
|
|
"loss": 6.3006,
|
|
"mean_token_accuracy": 0.12977074533700944,
|
|
"num_tokens": 2095183.0,
|
|
"step": 1010
|
|
},
|
|
{
|
|
"entropy": 6.186359834671021,
|
|
"epoch": 0.9223080417991822,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004999978237557377,
|
|
"loss": 6.167,
|
|
"mean_token_accuracy": 0.13407007083296776,
|
|
"num_tokens": 2104948.0,
|
|
"step": 1015
|
|
},
|
|
{
|
|
"entropy": 6.191218757629395,
|
|
"epoch": 0.9268514311676511,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999959917188137,
|
|
"loss": 6.1496,
|
|
"mean_token_accuracy": 0.13299431800842285,
|
|
"num_tokens": 2115122.0,
|
|
"step": 1020
|
|
},
|
|
{
|
|
"entropy": 6.343822002410889,
|
|
"epoch": 0.93139482053612,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999936045266462,
|
|
"loss": 6.2475,
|
|
"mean_token_accuracy": 0.12717320919036865,
|
|
"num_tokens": 2125665.0,
|
|
"step": 1025
|
|
},
|
|
{
|
|
"entropy": 6.183660650253296,
|
|
"epoch": 0.9359382099045889,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004999906621851255,
|
|
"loss": 6.1877,
|
|
"mean_token_accuracy": 0.1269860491156578,
|
|
"num_tokens": 2137119.0,
|
|
"step": 1030
|
|
},
|
|
{
|
|
"entropy": 6.218777894973755,
|
|
"epoch": 0.9404815992730577,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004999871647015115,
|
|
"loss": 6.2307,
|
|
"mean_token_accuracy": 0.12949277758598327,
|
|
"num_tokens": 2147506.0,
|
|
"step": 1035
|
|
},
|
|
{
|
|
"entropy": 6.268872499465942,
|
|
"epoch": 0.9450249886415266,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004999831120844339,
|
|
"loss": 6.2461,
|
|
"mean_token_accuracy": 0.13204365074634553,
|
|
"num_tokens": 2157054.0,
|
|
"step": 1040
|
|
},
|
|
{
|
|
"entropy": 6.353840112686157,
|
|
"epoch": 0.9495683780099955,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999785043438922,
|
|
"loss": 6.3052,
|
|
"mean_token_accuracy": 0.12659802213311194,
|
|
"num_tokens": 2167333.0,
|
|
"step": 1045
|
|
},
|
|
{
|
|
"entropy": 6.18822603225708,
|
|
"epoch": 0.9541117673784644,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999733414912555,
|
|
"loss": 6.2603,
|
|
"mean_token_accuracy": 0.12484889551997184,
|
|
"num_tokens": 2177876.0,
|
|
"step": 1050
|
|
},
|
|
{
|
|
"entropy": 6.28578929901123,
|
|
"epoch": 0.9586551567469332,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999676235392626,
|
|
"loss": 6.1924,
|
|
"mean_token_accuracy": 0.13271888494491577,
|
|
"num_tokens": 2187184.0,
|
|
"step": 1055
|
|
},
|
|
{
|
|
"entropy": 6.275188207626343,
|
|
"epoch": 0.9631985461154021,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999613505020219,
|
|
"loss": 6.23,
|
|
"mean_token_accuracy": 0.12417279556393623,
|
|
"num_tokens": 2197258.0,
|
|
"step": 1060
|
|
},
|
|
{
|
|
"entropy": 6.218803834915161,
|
|
"epoch": 0.967741935483871,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004999545223950116,
|
|
"loss": 6.2842,
|
|
"mean_token_accuracy": 0.1329876147210598,
|
|
"num_tokens": 2207440.0,
|
|
"step": 1065
|
|
},
|
|
{
|
|
"entropy": 6.341020202636718,
|
|
"epoch": 0.9722853248523399,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999471392350795,
|
|
"loss": 6.3201,
|
|
"mean_token_accuracy": 0.13476093709468842,
|
|
"num_tokens": 2216454.0,
|
|
"step": 1070
|
|
},
|
|
{
|
|
"entropy": 6.273011779785156,
|
|
"epoch": 0.9768287142208087,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004999392010404426,
|
|
"loss": 6.1687,
|
|
"mean_token_accuracy": 0.12653264328837394,
|
|
"num_tokens": 2226270.0,
|
|
"step": 1075
|
|
},
|
|
{
|
|
"entropy": 6.155029344558716,
|
|
"epoch": 0.9813721035892776,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004999307078306876,
|
|
"loss": 6.2223,
|
|
"mean_token_accuracy": 0.12701170668005943,
|
|
"num_tokens": 2235698.0,
|
|
"step": 1080
|
|
},
|
|
{
|
|
"entropy": 6.341498994827271,
|
|
"epoch": 0.9859154929577465,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999216596267708,
|
|
"loss": 6.2563,
|
|
"mean_token_accuracy": 0.13341840505599975,
|
|
"num_tokens": 2246309.0,
|
|
"step": 1085
|
|
},
|
|
{
|
|
"entropy": 6.215201282501221,
|
|
"epoch": 0.9904588823262154,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999120564510177,
|
|
"loss": 6.2721,
|
|
"mean_token_accuracy": 0.13170336931943893,
|
|
"num_tokens": 2257258.0,
|
|
"step": 1090
|
|
},
|
|
{
|
|
"entropy": 6.1683765888214115,
|
|
"epoch": 0.9950022716946842,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000499901898327123,
|
|
"loss": 6.2068,
|
|
"mean_token_accuracy": 0.12499793097376824,
|
|
"num_tokens": 2267825.0,
|
|
"step": 1095
|
|
},
|
|
{
|
|
"entropy": 6.333638763427734,
|
|
"epoch": 0.9995456610631531,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004998911852801512,
|
|
"loss": 6.3206,
|
|
"mean_token_accuracy": 0.12815747186541557,
|
|
"num_tokens": 2278727.0,
|
|
"step": 1100
|
|
},
|
|
{
|
|
"entropy": 6.311305787828234,
|
|
"epoch": 1.003634711494775,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004998799173365355,
|
|
"loss": 6.1588,
|
|
"mean_token_accuracy": 0.1277164104912016,
|
|
"num_tokens": 2287306.0,
|
|
"step": 1105
|
|
},
|
|
{
|
|
"entropy": 6.1962635040283205,
|
|
"epoch": 1.008178100863244,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004998680945240783,
|
|
"loss": 6.1096,
|
|
"mean_token_accuracy": 0.13211133405566217,
|
|
"num_tokens": 2299208.0,
|
|
"step": 1110
|
|
},
|
|
{
|
|
"entropy": 6.3119384765625,
|
|
"epoch": 1.0127214902317128,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004998557168719513,
|
|
"loss": 6.06,
|
|
"mean_token_accuracy": 0.13208466172218322,
|
|
"num_tokens": 2309196.0,
|
|
"step": 1115
|
|
},
|
|
{
|
|
"entropy": 6.21234393119812,
|
|
"epoch": 1.0172648796001817,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004998427844106954,
|
|
"loss": 6.1639,
|
|
"mean_token_accuracy": 0.12953464984893798,
|
|
"num_tokens": 2320255.0,
|
|
"step": 1120
|
|
},
|
|
{
|
|
"entropy": 6.236302614212036,
|
|
"epoch": 1.0218082689686505,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004998292971722197,
|
|
"loss": 6.0808,
|
|
"mean_token_accuracy": 0.1310319185256958,
|
|
"num_tokens": 2331661.0,
|
|
"step": 1125
|
|
},
|
|
{
|
|
"entropy": 6.1420262336730955,
|
|
"epoch": 1.0263516583371195,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000499815255189803,
|
|
"loss": 6.0517,
|
|
"mean_token_accuracy": 0.13892114236950875,
|
|
"num_tokens": 2341795.0,
|
|
"step": 1130
|
|
},
|
|
{
|
|
"entropy": 6.079546356201172,
|
|
"epoch": 1.0308950477055883,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004998006584980922,
|
|
"loss": 5.9691,
|
|
"mean_token_accuracy": 0.13563258126378058,
|
|
"num_tokens": 2351322.0,
|
|
"step": 1135
|
|
},
|
|
{
|
|
"entropy": 6.145311260223389,
|
|
"epoch": 1.0354384370740572,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004997855071331034,
|
|
"loss": 6.0101,
|
|
"mean_token_accuracy": 0.1399790108203888,
|
|
"num_tokens": 2361111.0,
|
|
"step": 1140
|
|
},
|
|
{
|
|
"entropy": 6.131455659866333,
|
|
"epoch": 1.039981826442526,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004997698011322211,
|
|
"loss": 6.0829,
|
|
"mean_token_accuracy": 0.13193223252892494,
|
|
"num_tokens": 2371481.0,
|
|
"step": 1145
|
|
},
|
|
{
|
|
"entropy": 6.159214019775391,
|
|
"epoch": 1.044525215810995,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000499753540534198,
|
|
"loss": 5.9465,
|
|
"mean_token_accuracy": 0.13461560755968094,
|
|
"num_tokens": 2382109.0,
|
|
"step": 1150
|
|
},
|
|
{
|
|
"entropy": 6.150908994674682,
|
|
"epoch": 1.049068605179464,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000499736725379156,
|
|
"loss": 6.1083,
|
|
"mean_token_accuracy": 0.13818338736891747,
|
|
"num_tokens": 2392451.0,
|
|
"step": 1155
|
|
},
|
|
{
|
|
"entropy": 6.15005316734314,
|
|
"epoch": 1.0536119945479328,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004997193557085844,
|
|
"loss": 5.9726,
|
|
"mean_token_accuracy": 0.1419435605406761,
|
|
"num_tokens": 2402043.0,
|
|
"step": 1160
|
|
},
|
|
{
|
|
"entropy": 6.23726077079773,
|
|
"epoch": 1.0581553839164017,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004997014315653413,
|
|
"loss": 6.1305,
|
|
"mean_token_accuracy": 0.13321863487362862,
|
|
"num_tokens": 2411730.0,
|
|
"step": 1165
|
|
},
|
|
{
|
|
"entropy": 6.111984491348267,
|
|
"epoch": 1.0626987732848705,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004996829529936527,
|
|
"loss": 6.0535,
|
|
"mean_token_accuracy": 0.1366070255637169,
|
|
"num_tokens": 2421881.0,
|
|
"step": 1170
|
|
},
|
|
{
|
|
"entropy": 6.155670213699341,
|
|
"epoch": 1.0672421626533395,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004996639200391126,
|
|
"loss": 6.0484,
|
|
"mean_token_accuracy": 0.14234526082873344,
|
|
"num_tokens": 2431702.0,
|
|
"step": 1175
|
|
},
|
|
{
|
|
"entropy": 6.079865741729736,
|
|
"epoch": 1.0717855520218083,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004996443327486831,
|
|
"loss": 5.9995,
|
|
"mean_token_accuracy": 0.13819927722215652,
|
|
"num_tokens": 2442327.0,
|
|
"step": 1180
|
|
},
|
|
{
|
|
"entropy": 6.146263885498047,
|
|
"epoch": 1.0763289413902772,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004996241911706937,
|
|
"loss": 6.0363,
|
|
"mean_token_accuracy": 0.13991880789399147,
|
|
"num_tokens": 2452155.0,
|
|
"step": 1185
|
|
},
|
|
{
|
|
"entropy": 6.133799982070923,
|
|
"epoch": 1.080872330758746,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004996034953548418,
|
|
"loss": 6.0365,
|
|
"mean_token_accuracy": 0.1321781098842621,
|
|
"num_tokens": 2462632.0,
|
|
"step": 1190
|
|
},
|
|
{
|
|
"entropy": 6.138056516647339,
|
|
"epoch": 1.085415720127215,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004995822453521924,
|
|
"loss": 5.9675,
|
|
"mean_token_accuracy": 0.14258275032043458,
|
|
"num_tokens": 2472326.0,
|
|
"step": 1195
|
|
},
|
|
{
|
|
"entropy": 6.116362905502319,
|
|
"epoch": 1.0899591094956838,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004995604412151776,
|
|
"loss": 6.0471,
|
|
"mean_token_accuracy": 0.13381395041942595,
|
|
"num_tokens": 2483394.0,
|
|
"step": 1200
|
|
},
|
|
{
|
|
"entropy": 6.082976675033569,
|
|
"epoch": 1.0945024988641527,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000499538082997597,
|
|
"loss": 6.0237,
|
|
"mean_token_accuracy": 0.13501874655485152,
|
|
"num_tokens": 2493863.0,
|
|
"step": 1205
|
|
},
|
|
{
|
|
"entropy": 6.173003053665161,
|
|
"epoch": 1.0990458882326215,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004995151707546172,
|
|
"loss": 6.0612,
|
|
"mean_token_accuracy": 0.12664901614189147,
|
|
"num_tokens": 2504565.0,
|
|
"step": 1210
|
|
},
|
|
{
|
|
"entropy": 6.11851019859314,
|
|
"epoch": 1.1035892776010905,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004994917045427721,
|
|
"loss": 6.1012,
|
|
"mean_token_accuracy": 0.13649318665266036,
|
|
"num_tokens": 2515323.0,
|
|
"step": 1215
|
|
},
|
|
{
|
|
"entropy": 6.114333629608154,
|
|
"epoch": 1.1081326669695593,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004994676844199621,
|
|
"loss": 6.042,
|
|
"mean_token_accuracy": 0.13800725415349008,
|
|
"num_tokens": 2526158.0,
|
|
"step": 1220
|
|
},
|
|
{
|
|
"entropy": 6.121361970901489,
|
|
"epoch": 1.1126760563380282,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004994431104454543,
|
|
"loss": 6.0556,
|
|
"mean_token_accuracy": 0.1371620051562786,
|
|
"num_tokens": 2536814.0,
|
|
"step": 1225
|
|
},
|
|
{
|
|
"entropy": 6.0955418109893795,
|
|
"epoch": 1.117219445706497,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004994179826798828,
|
|
"loss": 6.0267,
|
|
"mean_token_accuracy": 0.1353412687778473,
|
|
"num_tokens": 2547534.0,
|
|
"step": 1230
|
|
},
|
|
{
|
|
"entropy": 6.083361291885376,
|
|
"epoch": 1.121762835074966,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004993923011852477,
|
|
"loss": 6.071,
|
|
"mean_token_accuracy": 0.13434085100889206,
|
|
"num_tokens": 2558007.0,
|
|
"step": 1235
|
|
},
|
|
{
|
|
"entropy": 6.174566650390625,
|
|
"epoch": 1.1263062244434348,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004993660660249158,
|
|
"loss": 6.0718,
|
|
"mean_token_accuracy": 0.1386457212269306,
|
|
"num_tokens": 2569523.0,
|
|
"step": 1240
|
|
},
|
|
{
|
|
"entropy": 6.05771107673645,
|
|
"epoch": 1.1308496138119037,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004993392772636194,
|
|
"loss": 5.9552,
|
|
"mean_token_accuracy": 0.13412538096308707,
|
|
"num_tokens": 2580133.0,
|
|
"step": 1245
|
|
},
|
|
{
|
|
"entropy": 6.030849838256836,
|
|
"epoch": 1.1353930031803725,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004993119349674573,
|
|
"loss": 5.856,
|
|
"mean_token_accuracy": 0.1392548970878124,
|
|
"num_tokens": 2589994.0,
|
|
"step": 1250
|
|
},
|
|
{
|
|
"entropy": 6.008020687103271,
|
|
"epoch": 1.1399363925488415,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004992840392038938,
|
|
"loss": 6.0189,
|
|
"mean_token_accuracy": 0.13825450092554092,
|
|
"num_tokens": 2600675.0,
|
|
"step": 1255
|
|
},
|
|
{
|
|
"entropy": 6.147768020629883,
|
|
"epoch": 1.1444797819173103,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.000499255590041759,
|
|
"loss": 6.0472,
|
|
"mean_token_accuracy": 0.12776985839009286,
|
|
"num_tokens": 2611468.0,
|
|
"step": 1260
|
|
},
|
|
{
|
|
"entropy": 6.028980398178101,
|
|
"epoch": 1.1490231712857792,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004992265875512485,
|
|
"loss": 5.8744,
|
|
"mean_token_accuracy": 0.14487501680850984,
|
|
"num_tokens": 2621920.0,
|
|
"step": 1265
|
|
},
|
|
{
|
|
"entropy": 5.9842596530914305,
|
|
"epoch": 1.153566560654248,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004991970318039228,
|
|
"loss": 6.0354,
|
|
"mean_token_accuracy": 0.13384448885917663,
|
|
"num_tokens": 2632235.0,
|
|
"step": 1270
|
|
},
|
|
{
|
|
"entropy": 6.039266777038574,
|
|
"epoch": 1.158109950022717,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004991669228727078,
|
|
"loss": 5.9684,
|
|
"mean_token_accuracy": 0.14427078366279603,
|
|
"num_tokens": 2642124.0,
|
|
"step": 1275
|
|
},
|
|
{
|
|
"entropy": 6.068850898742676,
|
|
"epoch": 1.1626533393911858,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004991362608318947,
|
|
"loss": 5.9384,
|
|
"mean_token_accuracy": 0.14294721484184264,
|
|
"num_tokens": 2652706.0,
|
|
"step": 1280
|
|
},
|
|
{
|
|
"entropy": 5.983570957183838,
|
|
"epoch": 1.1671967287596547,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004991050457571384,
|
|
"loss": 5.9937,
|
|
"mean_token_accuracy": 0.1419117584824562,
|
|
"num_tokens": 2663432.0,
|
|
"step": 1285
|
|
},
|
|
{
|
|
"entropy": 6.102989578247071,
|
|
"epoch": 1.1717401181281235,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004990732777254594,
|
|
"loss": 6.0254,
|
|
"mean_token_accuracy": 0.13163735792040826,
|
|
"num_tokens": 2673049.0,
|
|
"step": 1290
|
|
},
|
|
{
|
|
"entropy": 6.130951070785523,
|
|
"epoch": 1.1762835074965925,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004990409568152422,
|
|
"loss": 6.056,
|
|
"mean_token_accuracy": 0.1352098412811756,
|
|
"num_tokens": 2683857.0,
|
|
"step": 1295
|
|
},
|
|
{
|
|
"entropy": 5.973699998855591,
|
|
"epoch": 1.1808268968650613,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004990080831062352,
|
|
"loss": 5.9929,
|
|
"mean_token_accuracy": 0.1435897931456566,
|
|
"num_tokens": 2694304.0,
|
|
"step": 1300
|
|
},
|
|
{
|
|
"entropy": 6.127169609069824,
|
|
"epoch": 1.1853702862335302,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004989746566795512,
|
|
"loss": 6.0485,
|
|
"mean_token_accuracy": 0.13189298063516616,
|
|
"num_tokens": 2704381.0,
|
|
"step": 1305
|
|
},
|
|
{
|
|
"entropy": 6.148133134841919,
|
|
"epoch": 1.189913675601999,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004989406776176665,
|
|
"loss": 6.0702,
|
|
"mean_token_accuracy": 0.1281648263335228,
|
|
"num_tokens": 2716006.0,
|
|
"step": 1310
|
|
},
|
|
{
|
|
"entropy": 6.052830934524536,
|
|
"epoch": 1.194457064970468,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.000498906146004421,
|
|
"loss": 6.0813,
|
|
"mean_token_accuracy": 0.13499361276626587,
|
|
"num_tokens": 2726012.0,
|
|
"step": 1315
|
|
},
|
|
{
|
|
"entropy": 6.102909851074219,
|
|
"epoch": 1.1990004543389368,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004988710619250181,
|
|
"loss": 6.0031,
|
|
"mean_token_accuracy": 0.13929674178361892,
|
|
"num_tokens": 2735532.0,
|
|
"step": 1320
|
|
},
|
|
{
|
|
"entropy": 6.080796909332276,
|
|
"epoch": 1.2035438437074057,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004988354254660244,
|
|
"loss": 6.0198,
|
|
"mean_token_accuracy": 0.14065880179405213,
|
|
"num_tokens": 2745172.0,
|
|
"step": 1325
|
|
},
|
|
{
|
|
"entropy": 5.985582876205444,
|
|
"epoch": 1.2080872330758745,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004987992367153691,
|
|
"loss": 5.9146,
|
|
"mean_token_accuracy": 0.14265609309077262,
|
|
"num_tokens": 2756211.0,
|
|
"step": 1330
|
|
},
|
|
{
|
|
"entropy": 6.039712905883789,
|
|
"epoch": 1.2126306224443435,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004987624957623443,
|
|
"loss": 6.1229,
|
|
"mean_token_accuracy": 0.133643551915884,
|
|
"num_tokens": 2767933.0,
|
|
"step": 1335
|
|
},
|
|
{
|
|
"entropy": 6.086614799499512,
|
|
"epoch": 1.2171740118128123,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004987252026976049,
|
|
"loss": 5.9834,
|
|
"mean_token_accuracy": 0.1415078692138195,
|
|
"num_tokens": 2778176.0,
|
|
"step": 1340
|
|
},
|
|
{
|
|
"entropy": 6.037263250350952,
|
|
"epoch": 1.2217174011812812,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004986873576131676,
|
|
"loss": 5.9931,
|
|
"mean_token_accuracy": 0.13973900973796843,
|
|
"num_tokens": 2788486.0,
|
|
"step": 1345
|
|
},
|
|
{
|
|
"entropy": 6.134681844711304,
|
|
"epoch": 1.22626079054975,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004986489606024116,
|
|
"loss": 6.0902,
|
|
"mean_token_accuracy": 0.13812331557273866,
|
|
"num_tokens": 2799549.0,
|
|
"step": 1350
|
|
},
|
|
{
|
|
"entropy": 6.029563140869141,
|
|
"epoch": 1.230804179918219,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004986100117600776,
|
|
"loss": 6.0134,
|
|
"mean_token_accuracy": 0.1400228500366211,
|
|
"num_tokens": 2810674.0,
|
|
"step": 1355
|
|
},
|
|
{
|
|
"entropy": 6.097317552566528,
|
|
"epoch": 1.235347569286688,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000498570511182268,
|
|
"loss": 5.9747,
|
|
"mean_token_accuracy": 0.13779623731970786,
|
|
"num_tokens": 2821011.0,
|
|
"step": 1360
|
|
},
|
|
{
|
|
"entropy": 6.012727117538452,
|
|
"epoch": 1.2398909586551567,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004985304589664465,
|
|
"loss": 5.9328,
|
|
"mean_token_accuracy": 0.14200753346085548,
|
|
"num_tokens": 2831245.0,
|
|
"step": 1365
|
|
},
|
|
{
|
|
"entropy": 6.065994548797607,
|
|
"epoch": 1.2444343480236255,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004984898552114381,
|
|
"loss": 5.9852,
|
|
"mean_token_accuracy": 0.1369895800948143,
|
|
"num_tokens": 2841397.0,
|
|
"step": 1370
|
|
},
|
|
{
|
|
"entropy": 6.114771318435669,
|
|
"epoch": 1.2489777373920945,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004984487000174283,
|
|
"loss": 6.0306,
|
|
"mean_token_accuracy": 0.13484285473823548,
|
|
"num_tokens": 2851971.0,
|
|
"step": 1375
|
|
},
|
|
{
|
|
"entropy": 5.974376487731933,
|
|
"epoch": 1.2535211267605635,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004984069934859637,
|
|
"loss": 5.9745,
|
|
"mean_token_accuracy": 0.14509348720312118,
|
|
"num_tokens": 2861882.0,
|
|
"step": 1380
|
|
},
|
|
{
|
|
"entropy": 6.04203724861145,
|
|
"epoch": 1.2580645161290323,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004983647357199509,
|
|
"loss": 6.0139,
|
|
"mean_token_accuracy": 0.14242928475141525,
|
|
"num_tokens": 2872888.0,
|
|
"step": 1385
|
|
},
|
|
{
|
|
"entropy": 5.974927806854248,
|
|
"epoch": 1.262607905497501,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004983219268236567,
|
|
"loss": 5.9679,
|
|
"mean_token_accuracy": 0.14272170662879943,
|
|
"num_tokens": 2883194.0,
|
|
"step": 1390
|
|
},
|
|
{
|
|
"entropy": 6.067883062362671,
|
|
"epoch": 1.26715129486597,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004982785669027079,
|
|
"loss": 5.9561,
|
|
"mean_token_accuracy": 0.14673515483736993,
|
|
"num_tokens": 2892672.0,
|
|
"step": 1395
|
|
},
|
|
{
|
|
"entropy": 5.952126836776733,
|
|
"epoch": 1.271694684234439,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004982346560640907,
|
|
"loss": 5.9802,
|
|
"mean_token_accuracy": 0.13936009705066682,
|
|
"num_tokens": 2902155.0,
|
|
"step": 1400
|
|
},
|
|
{
|
|
"entropy": 6.082441091537476,
|
|
"epoch": 1.2762380736029078,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004981901944161507,
|
|
"loss": 5.9298,
|
|
"mean_token_accuracy": 0.14501121267676353,
|
|
"num_tokens": 2911805.0,
|
|
"step": 1405
|
|
},
|
|
{
|
|
"entropy": 5.976729249954223,
|
|
"epoch": 1.2807814629713765,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004981451820685928,
|
|
"loss": 5.9421,
|
|
"mean_token_accuracy": 0.13730958774685859,
|
|
"num_tokens": 2922975.0,
|
|
"step": 1410
|
|
},
|
|
{
|
|
"entropy": 5.961244773864746,
|
|
"epoch": 1.2853248523398455,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004980996191324802,
|
|
"loss": 5.9758,
|
|
"mean_token_accuracy": 0.1435778558254242,
|
|
"num_tokens": 2932416.0,
|
|
"step": 1415
|
|
},
|
|
{
|
|
"entropy": 6.068545198440551,
|
|
"epoch": 1.2898682417083145,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004980535057202351,
|
|
"loss": 5.9246,
|
|
"mean_token_accuracy": 0.1430967390537262,
|
|
"num_tokens": 2943336.0,
|
|
"step": 1420
|
|
},
|
|
{
|
|
"entropy": 5.946337366104126,
|
|
"epoch": 1.2944116310767833,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004980068419456378,
|
|
"loss": 5.9097,
|
|
"mean_token_accuracy": 0.1428004875779152,
|
|
"num_tokens": 2953397.0,
|
|
"step": 1425
|
|
},
|
|
{
|
|
"entropy": 6.007153081893921,
|
|
"epoch": 1.2989550204452522,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004979596279238265,
|
|
"loss": 6.0119,
|
|
"mean_token_accuracy": 0.14089832603931426,
|
|
"num_tokens": 2963811.0,
|
|
"step": 1430
|
|
},
|
|
{
|
|
"entropy": 6.014495849609375,
|
|
"epoch": 1.303498409813721,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004979118637712969,
|
|
"loss": 5.9594,
|
|
"mean_token_accuracy": 0.13529563397169114,
|
|
"num_tokens": 2973309.0,
|
|
"step": 1435
|
|
},
|
|
{
|
|
"entropy": 6.009972476959229,
|
|
"epoch": 1.30804179918219,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004978635496059025,
|
|
"loss": 5.9054,
|
|
"mean_token_accuracy": 0.13381288573145866,
|
|
"num_tokens": 2984873.0,
|
|
"step": 1440
|
|
},
|
|
{
|
|
"entropy": 5.961966848373413,
|
|
"epoch": 1.3125851885506588,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004978146855468537,
|
|
"loss": 5.9804,
|
|
"mean_token_accuracy": 0.14162408858537673,
|
|
"num_tokens": 2995117.0,
|
|
"step": 1445
|
|
},
|
|
{
|
|
"entropy": 5.983718729019165,
|
|
"epoch": 1.3171285779191277,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004977652717147177,
|
|
"loss": 6.0084,
|
|
"mean_token_accuracy": 0.14052879959344863,
|
|
"num_tokens": 3005035.0,
|
|
"step": 1450
|
|
},
|
|
{
|
|
"entropy": 5.928684234619141,
|
|
"epoch": 1.3216719672875965,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004977153082314182,
|
|
"loss": 5.9406,
|
|
"mean_token_accuracy": 0.142349211871624,
|
|
"num_tokens": 3015091.0,
|
|
"step": 1455
|
|
},
|
|
{
|
|
"entropy": 6.030572557449341,
|
|
"epoch": 1.3262153566560655,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000497664795220235,
|
|
"loss": 6.023,
|
|
"mean_token_accuracy": 0.1426836997270584,
|
|
"num_tokens": 3025261.0,
|
|
"step": 1460
|
|
},
|
|
{
|
|
"entropy": 6.0664942264556885,
|
|
"epoch": 1.3307587460245343,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004976137328058042,
|
|
"loss": 6.0056,
|
|
"mean_token_accuracy": 0.1386928841471672,
|
|
"num_tokens": 3036198.0,
|
|
"step": 1465
|
|
},
|
|
{
|
|
"entropy": 5.9850257396697994,
|
|
"epoch": 1.3353021353930032,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000497562121114117,
|
|
"loss": 5.9862,
|
|
"mean_token_accuracy": 0.13778137564659118,
|
|
"num_tokens": 3047295.0,
|
|
"step": 1470
|
|
},
|
|
{
|
|
"entropy": 5.985382986068726,
|
|
"epoch": 1.339845524761472,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004975099602725202,
|
|
"loss": 5.941,
|
|
"mean_token_accuracy": 0.14224427342414855,
|
|
"num_tokens": 3057427.0,
|
|
"step": 1475
|
|
},
|
|
{
|
|
"entropy": 6.026016187667847,
|
|
"epoch": 1.344388914129941,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004974572504097154,
|
|
"loss": 5.9648,
|
|
"mean_token_accuracy": 0.14337582439184188,
|
|
"num_tokens": 3067774.0,
|
|
"step": 1480
|
|
},
|
|
{
|
|
"entropy": 6.028681468963623,
|
|
"epoch": 1.3489323034984098,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004974039916557591,
|
|
"loss": 5.9132,
|
|
"mean_token_accuracy": 0.14107456281781197,
|
|
"num_tokens": 3077286.0,
|
|
"step": 1485
|
|
},
|
|
{
|
|
"entropy": 6.127128171920776,
|
|
"epoch": 1.3534756928668787,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000497350184142062,
|
|
"loss": 5.9865,
|
|
"mean_token_accuracy": 0.13820576295256615,
|
|
"num_tokens": 3088195.0,
|
|
"step": 1490
|
|
},
|
|
{
|
|
"entropy": 5.905239915847778,
|
|
"epoch": 1.3580190822353475,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004972958280013886,
|
|
"loss": 5.8789,
|
|
"mean_token_accuracy": 0.13997682929039001,
|
|
"num_tokens": 3098158.0,
|
|
"step": 1495
|
|
},
|
|
{
|
|
"entropy": 5.993680334091186,
|
|
"epoch": 1.3625624716038165,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004972409233678575,
|
|
"loss": 5.9806,
|
|
"mean_token_accuracy": 0.14393218830227852,
|
|
"num_tokens": 3108456.0,
|
|
"step": 1500
|
|
},
|
|
{
|
|
"entropy": 5.955839443206787,
|
|
"epoch": 1.3671058609722853,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004971854703769401,
|
|
"loss": 5.8702,
|
|
"mean_token_accuracy": 0.14266545102000236,
|
|
"num_tokens": 3118366.0,
|
|
"step": 1505
|
|
},
|
|
{
|
|
"entropy": 6.0084840774536135,
|
|
"epoch": 1.3716492503407542,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004971294691654616,
|
|
"loss": 5.9273,
|
|
"mean_token_accuracy": 0.1385462649166584,
|
|
"num_tokens": 3128975.0,
|
|
"step": 1510
|
|
},
|
|
{
|
|
"entropy": 5.95463604927063,
|
|
"epoch": 1.376192639709223,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000497072919871599,
|
|
"loss": 5.9543,
|
|
"mean_token_accuracy": 0.1458298459649086,
|
|
"num_tokens": 3139299.0,
|
|
"step": 1515
|
|
},
|
|
{
|
|
"entropy": 5.927489757537842,
|
|
"epoch": 1.380736029077692,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004970158226348824,
|
|
"loss": 5.9245,
|
|
"mean_token_accuracy": 0.1443161353468895,
|
|
"num_tokens": 3149987.0,
|
|
"step": 1520
|
|
},
|
|
{
|
|
"entropy": 5.98699197769165,
|
|
"epoch": 1.3852794184461608,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004969581775961932,
|
|
"loss": 5.9591,
|
|
"mean_token_accuracy": 0.1391432523727417,
|
|
"num_tokens": 3160922.0,
|
|
"step": 1525
|
|
},
|
|
{
|
|
"entropy": 6.022416639328003,
|
|
"epoch": 1.3898228078146297,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004968999848977651,
|
|
"loss": 5.9974,
|
|
"mean_token_accuracy": 0.13953477665781974,
|
|
"num_tokens": 3172770.0,
|
|
"step": 1530
|
|
},
|
|
{
|
|
"entropy": 5.955699491500854,
|
|
"epoch": 1.3943661971830985,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004968412446831827,
|
|
"loss": 5.9561,
|
|
"mean_token_accuracy": 0.1413671687245369,
|
|
"num_tokens": 3183218.0,
|
|
"step": 1535
|
|
},
|
|
{
|
|
"entropy": 5.9225616455078125,
|
|
"epoch": 1.3989095865515675,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004967819570973816,
|
|
"loss": 5.7925,
|
|
"mean_token_accuracy": 0.1463052049279213,
|
|
"num_tokens": 3192737.0,
|
|
"step": 1540
|
|
},
|
|
{
|
|
"entropy": 5.961886882781982,
|
|
"epoch": 1.4034529759200365,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000496722122286648,
|
|
"loss": 6.0038,
|
|
"mean_token_accuracy": 0.13916029781103134,
|
|
"num_tokens": 3203802.0,
|
|
"step": 1545
|
|
},
|
|
{
|
|
"entropy": 6.000508880615234,
|
|
"epoch": 1.4079963652885052,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004966617403986185,
|
|
"loss": 5.9516,
|
|
"mean_token_accuracy": 0.14601216688752175,
|
|
"num_tokens": 3214232.0,
|
|
"step": 1550
|
|
},
|
|
{
|
|
"entropy": 6.122423076629639,
|
|
"epoch": 1.412539754656974,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004966008115822793,
|
|
"loss": 5.9903,
|
|
"mean_token_accuracy": 0.13714029863476754,
|
|
"num_tokens": 3225893.0,
|
|
"step": 1555
|
|
},
|
|
{
|
|
"entropy": 5.751972341537476,
|
|
"epoch": 1.417083144025443,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004965393359879662,
|
|
"loss": 5.8346,
|
|
"mean_token_accuracy": 0.14151518866419793,
|
|
"num_tokens": 3235118.0,
|
|
"step": 1560
|
|
},
|
|
{
|
|
"entropy": 6.064570665359497,
|
|
"epoch": 1.421626533393912,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004964773137673641,
|
|
"loss": 5.9124,
|
|
"mean_token_accuracy": 0.14920328110456466,
|
|
"num_tokens": 3245770.0,
|
|
"step": 1565
|
|
},
|
|
{
|
|
"entropy": 5.846122407913208,
|
|
"epoch": 1.4261699227623807,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004964147450735067,
|
|
"loss": 5.8949,
|
|
"mean_token_accuracy": 0.1421331949532032,
|
|
"num_tokens": 3255262.0,
|
|
"step": 1570
|
|
},
|
|
{
|
|
"entropy": 6.011489725112915,
|
|
"epoch": 1.4307133121308495,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000496351630060776,
|
|
"loss": 5.9839,
|
|
"mean_token_accuracy": 0.14037677198648452,
|
|
"num_tokens": 3265682.0,
|
|
"step": 1575
|
|
},
|
|
{
|
|
"entropy": 5.986287546157837,
|
|
"epoch": 1.4352567014993185,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004962879688849021,
|
|
"loss": 6.0301,
|
|
"mean_token_accuracy": 0.14520008191466333,
|
|
"num_tokens": 3275734.0,
|
|
"step": 1580
|
|
},
|
|
{
|
|
"entropy": 6.040392637252808,
|
|
"epoch": 1.4398000908677875,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004962237617029625,
|
|
"loss": 5.911,
|
|
"mean_token_accuracy": 0.13663775473833084,
|
|
"num_tokens": 3286186.0,
|
|
"step": 1585
|
|
},
|
|
{
|
|
"entropy": 6.068287038803101,
|
|
"epoch": 1.4443434802362562,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004961590086733821,
|
|
"loss": 6.0751,
|
|
"mean_token_accuracy": 0.13447670564055442,
|
|
"num_tokens": 3297543.0,
|
|
"step": 1590
|
|
},
|
|
{
|
|
"entropy": 5.971070957183838,
|
|
"epoch": 1.448886869604725,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004960937099559326,
|
|
"loss": 5.9092,
|
|
"mean_token_accuracy": 0.14828140735626222,
|
|
"num_tokens": 3307840.0,
|
|
"step": 1595
|
|
},
|
|
{
|
|
"entropy": 5.951090621948242,
|
|
"epoch": 1.453430258973194,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004960278657117321,
|
|
"loss": 5.9347,
|
|
"mean_token_accuracy": 0.14122510626912116,
|
|
"num_tokens": 3318502.0,
|
|
"step": 1600
|
|
},
|
|
{
|
|
"entropy": 5.972015810012818,
|
|
"epoch": 1.457973648341663,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004959614761032446,
|
|
"loss": 5.9201,
|
|
"mean_token_accuracy": 0.13903507143259047,
|
|
"num_tokens": 3329161.0,
|
|
"step": 1605
|
|
},
|
|
{
|
|
"entropy": 5.990231657028199,
|
|
"epoch": 1.4625170377101318,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00049589454129428,
|
|
"loss": 5.8633,
|
|
"mean_token_accuracy": 0.14469081088900565,
|
|
"num_tokens": 3338770.0,
|
|
"step": 1610
|
|
},
|
|
{
|
|
"entropy": 5.959870481491089,
|
|
"epoch": 1.4670604270786005,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004958270614499932,
|
|
"loss": 5.978,
|
|
"mean_token_accuracy": 0.1422998420894146,
|
|
"num_tokens": 3350807.0,
|
|
"step": 1615
|
|
},
|
|
{
|
|
"entropy": 5.944865751266479,
|
|
"epoch": 1.4716038164470695,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004957590367368841,
|
|
"loss": 5.8494,
|
|
"mean_token_accuracy": 0.14039375260472298,
|
|
"num_tokens": 3359943.0,
|
|
"step": 1620
|
|
},
|
|
{
|
|
"entropy": 6.028170776367188,
|
|
"epoch": 1.4761472058155385,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004956904673227968,
|
|
"loss": 5.9822,
|
|
"mean_token_accuracy": 0.14763114899396895,
|
|
"num_tokens": 3369560.0,
|
|
"step": 1625
|
|
},
|
|
{
|
|
"entropy": 5.860723352432251,
|
|
"epoch": 1.4806905951840073,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004956213533769195,
|
|
"loss": 5.9108,
|
|
"mean_token_accuracy": 0.14079108610749244,
|
|
"num_tokens": 3380541.0,
|
|
"step": 1630
|
|
},
|
|
{
|
|
"entropy": 6.023792171478272,
|
|
"epoch": 1.485233984552476,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004955516950697843,
|
|
"loss": 5.9863,
|
|
"mean_token_accuracy": 0.14471204578876495,
|
|
"num_tokens": 3392428.0,
|
|
"step": 1635
|
|
},
|
|
{
|
|
"entropy": 5.9620476245880125,
|
|
"epoch": 1.489777373920945,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004954814925732657,
|
|
"loss": 5.8748,
|
|
"mean_token_accuracy": 0.14238841086626053,
|
|
"num_tokens": 3403189.0,
|
|
"step": 1640
|
|
},
|
|
{
|
|
"entropy": 5.870425748825073,
|
|
"epoch": 1.494320763289414,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004954107460605816,
|
|
"loss": 5.842,
|
|
"mean_token_accuracy": 0.14517249315977096,
|
|
"num_tokens": 3413359.0,
|
|
"step": 1645
|
|
},
|
|
{
|
|
"entropy": 5.922900056838989,
|
|
"epoch": 1.4988641526578828,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004953394557062922,
|
|
"loss": 5.9348,
|
|
"mean_token_accuracy": 0.14482194930315018,
|
|
"num_tokens": 3424395.0,
|
|
"step": 1650
|
|
},
|
|
{
|
|
"entropy": 5.95229206085205,
|
|
"epoch": 1.5034075420263515,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004952676216862989,
|
|
"loss": 5.8959,
|
|
"mean_token_accuracy": 0.1466038256883621,
|
|
"num_tokens": 3434452.0,
|
|
"step": 1655
|
|
},
|
|
{
|
|
"entropy": 5.936011409759521,
|
|
"epoch": 1.5079509313948205,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004951952441778453,
|
|
"loss": 6.002,
|
|
"mean_token_accuracy": 0.14328072518110274,
|
|
"num_tokens": 3445075.0,
|
|
"step": 1660
|
|
},
|
|
{
|
|
"entropy": 6.050215101242065,
|
|
"epoch": 1.5124943207632895,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004951223233595158,
|
|
"loss": 5.8804,
|
|
"mean_token_accuracy": 0.15087313205003738,
|
|
"num_tokens": 3454862.0,
|
|
"step": 1665
|
|
},
|
|
{
|
|
"entropy": 5.9777295112609865,
|
|
"epoch": 1.5170377101317583,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000495048859411235,
|
|
"loss": 6.0501,
|
|
"mean_token_accuracy": 0.13969595432281495,
|
|
"num_tokens": 3466255.0,
|
|
"step": 1670
|
|
},
|
|
{
|
|
"entropy": 5.978166294097901,
|
|
"epoch": 1.521581099500227,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004949748525142681,
|
|
"loss": 5.8495,
|
|
"mean_token_accuracy": 0.14266801625490189,
|
|
"num_tokens": 3475810.0,
|
|
"step": 1675
|
|
},
|
|
{
|
|
"entropy": 5.911789226531982,
|
|
"epoch": 1.526124488868696,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004949003028512195,
|
|
"loss": 5.9071,
|
|
"mean_token_accuracy": 0.14459308981895447,
|
|
"num_tokens": 3486979.0,
|
|
"step": 1680
|
|
},
|
|
{
|
|
"entropy": 5.874098205566407,
|
|
"epoch": 1.530667878237165,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004948252106060334,
|
|
"loss": 5.8235,
|
|
"mean_token_accuracy": 0.1440264791250229,
|
|
"num_tokens": 3496678.0,
|
|
"step": 1685
|
|
},
|
|
{
|
|
"entropy": 5.995673894882202,
|
|
"epoch": 1.5352112676056338,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004947495759639923,
|
|
"loss": 5.9194,
|
|
"mean_token_accuracy": 0.14006965309381486,
|
|
"num_tokens": 3507330.0,
|
|
"step": 1690
|
|
},
|
|
{
|
|
"entropy": 5.7853700637817385,
|
|
"epoch": 1.5397546569741025,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004946733991117171,
|
|
"loss": 5.8492,
|
|
"mean_token_accuracy": 0.14746353328227996,
|
|
"num_tokens": 3516781.0,
|
|
"step": 1695
|
|
},
|
|
{
|
|
"entropy": 6.004105186462402,
|
|
"epoch": 1.5442980463425715,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004945966802371668,
|
|
"loss": 5.9066,
|
|
"mean_token_accuracy": 0.14546382948756217,
|
|
"num_tokens": 3526936.0,
|
|
"step": 1700
|
|
},
|
|
{
|
|
"entropy": 5.894688463211059,
|
|
"epoch": 1.5488414357110405,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004945194195296374,
|
|
"loss": 5.8427,
|
|
"mean_token_accuracy": 0.14690589904785156,
|
|
"num_tokens": 3537319.0,
|
|
"step": 1705
|
|
},
|
|
{
|
|
"entropy": 5.965080738067627,
|
|
"epoch": 1.5533848250795095,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000494441617179762,
|
|
"loss": 5.889,
|
|
"mean_token_accuracy": 0.14221190959215163,
|
|
"num_tokens": 3547448.0,
|
|
"step": 1710
|
|
},
|
|
{
|
|
"entropy": 5.873220205307007,
|
|
"epoch": 1.5579282144479782,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004943632733795104,
|
|
"loss": 5.8481,
|
|
"mean_token_accuracy": 0.14411542043089867,
|
|
"num_tokens": 3558939.0,
|
|
"step": 1715
|
|
},
|
|
{
|
|
"entropy": 5.913844060897827,
|
|
"epoch": 1.562471603816447,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004942843883221879,
|
|
"loss": 5.9341,
|
|
"mean_token_accuracy": 0.1473378099501133,
|
|
"num_tokens": 3569501.0,
|
|
"step": 1720
|
|
},
|
|
{
|
|
"entropy": 5.912490558624268,
|
|
"epoch": 1.567014993184916,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004942049622024357,
|
|
"loss": 5.9162,
|
|
"mean_token_accuracy": 0.14080541655421258,
|
|
"num_tokens": 3579262.0,
|
|
"step": 1725
|
|
},
|
|
{
|
|
"entropy": 5.953363609313965,
|
|
"epoch": 1.571558382553385,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004941249952162298,
|
|
"loss": 5.9164,
|
|
"mean_token_accuracy": 0.14955995380878448,
|
|
"num_tokens": 3589894.0,
|
|
"step": 1730
|
|
},
|
|
{
|
|
"entropy": 5.906908178329468,
|
|
"epoch": 1.5761017719218537,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004940444875608807,
|
|
"loss": 5.8796,
|
|
"mean_token_accuracy": 0.14327764958143235,
|
|
"num_tokens": 3600011.0,
|
|
"step": 1735
|
|
},
|
|
{
|
|
"entropy": 5.920686388015747,
|
|
"epoch": 1.5806451612903225,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004939634394350332,
|
|
"loss": 5.8318,
|
|
"mean_token_accuracy": 0.14824839904904366,
|
|
"num_tokens": 3609832.0,
|
|
"step": 1740
|
|
},
|
|
{
|
|
"entropy": 5.868525600433349,
|
|
"epoch": 1.5851885506587915,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004938818510386654,
|
|
"loss": 5.7622,
|
|
"mean_token_accuracy": 0.15004636198282242,
|
|
"num_tokens": 3620196.0,
|
|
"step": 1745
|
|
},
|
|
{
|
|
"entropy": 5.908840179443359,
|
|
"epoch": 1.5897319400272605,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004937997225730886,
|
|
"loss": 5.8677,
|
|
"mean_token_accuracy": 0.1446698360145092,
|
|
"num_tokens": 3630488.0,
|
|
"step": 1750
|
|
},
|
|
{
|
|
"entropy": 5.907616424560547,
|
|
"epoch": 1.5942753293957292,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004937170542409464,
|
|
"loss": 5.8445,
|
|
"mean_token_accuracy": 0.15007875561714173,
|
|
"num_tokens": 3640449.0,
|
|
"step": 1755
|
|
},
|
|
{
|
|
"entropy": 5.922990465164185,
|
|
"epoch": 1.598818718764198,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.000493633846246215,
|
|
"loss": 5.9154,
|
|
"mean_token_accuracy": 0.14311289340257644,
|
|
"num_tokens": 3650728.0,
|
|
"step": 1760
|
|
},
|
|
{
|
|
"entropy": 5.943247747421265,
|
|
"epoch": 1.603362108132667,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004935500987942018,
|
|
"loss": 5.8803,
|
|
"mean_token_accuracy": 0.14469165802001954,
|
|
"num_tokens": 3659739.0,
|
|
"step": 1765
|
|
},
|
|
{
|
|
"entropy": 5.981834411621094,
|
|
"epoch": 1.607905497501136,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004934658120915452,
|
|
"loss": 5.9898,
|
|
"mean_token_accuracy": 0.13959717378020287,
|
|
"num_tokens": 3671071.0,
|
|
"step": 1770
|
|
},
|
|
{
|
|
"entropy": 5.886190128326416,
|
|
"epoch": 1.6124488868696047,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004933809863462142,
|
|
"loss": 5.899,
|
|
"mean_token_accuracy": 0.14077742993831635,
|
|
"num_tokens": 3681289.0,
|
|
"step": 1775
|
|
},
|
|
{
|
|
"entropy": 5.8254108905792235,
|
|
"epoch": 1.6169922762380735,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004932956217675082,
|
|
"loss": 5.8237,
|
|
"mean_token_accuracy": 0.1419857293367386,
|
|
"num_tokens": 3691344.0,
|
|
"step": 1780
|
|
},
|
|
{
|
|
"entropy": 5.910706806182861,
|
|
"epoch": 1.6215356656065425,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004932097185660555,
|
|
"loss": 5.8268,
|
|
"mean_token_accuracy": 0.14990733712911605,
|
|
"num_tokens": 3702040.0,
|
|
"step": 1785
|
|
},
|
|
{
|
|
"entropy": 5.804446792602539,
|
|
"epoch": 1.6260790549750115,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004931232769538138,
|
|
"loss": 5.8653,
|
|
"mean_token_accuracy": 0.1472170442342758,
|
|
"num_tokens": 3711677.0,
|
|
"step": 1790
|
|
},
|
|
{
|
|
"entropy": 6.00853590965271,
|
|
"epoch": 1.6306224443434802,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004930362971440692,
|
|
"loss": 5.8915,
|
|
"mean_token_accuracy": 0.14570934921503068,
|
|
"num_tokens": 3721911.0,
|
|
"step": 1795
|
|
},
|
|
{
|
|
"entropy": 5.887213802337646,
|
|
"epoch": 1.635165833711949,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004929487793514358,
|
|
"loss": 5.8404,
|
|
"mean_token_accuracy": 0.15700444281101228,
|
|
"num_tokens": 3731817.0,
|
|
"step": 1800
|
|
},
|
|
{
|
|
"entropy": 5.898286199569702,
|
|
"epoch": 1.639709223080418,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.000492860723791855,
|
|
"loss": 5.8559,
|
|
"mean_token_accuracy": 0.14812351018190384,
|
|
"num_tokens": 3742052.0,
|
|
"step": 1805
|
|
},
|
|
{
|
|
"entropy": 5.916392612457275,
|
|
"epoch": 1.644252612448887,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004927721306825952,
|
|
"loss": 5.8246,
|
|
"mean_token_accuracy": 0.14850612059235574,
|
|
"num_tokens": 3751630.0,
|
|
"step": 1810
|
|
},
|
|
{
|
|
"entropy": 5.85957612991333,
|
|
"epoch": 1.6487960018173557,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004926830002422509,
|
|
"loss": 5.7883,
|
|
"mean_token_accuracy": 0.14857261329889299,
|
|
"num_tokens": 3761858.0,
|
|
"step": 1815
|
|
},
|
|
{
|
|
"entropy": 5.8779035091400145,
|
|
"epoch": 1.6533393911858245,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000492593332690743,
|
|
"loss": 5.8808,
|
|
"mean_token_accuracy": 0.1462581604719162,
|
|
"num_tokens": 3771679.0,
|
|
"step": 1820
|
|
},
|
|
{
|
|
"entropy": 5.983050107955933,
|
|
"epoch": 1.6578827805542935,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004925031282493167,
|
|
"loss": 5.8485,
|
|
"mean_token_accuracy": 0.14935702979564666,
|
|
"num_tokens": 3782777.0,
|
|
"step": 1825
|
|
},
|
|
{
|
|
"entropy": 5.779914617538452,
|
|
"epoch": 1.6624261699227625,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004924123871405428,
|
|
"loss": 5.7653,
|
|
"mean_token_accuracy": 0.15233860909938812,
|
|
"num_tokens": 3792863.0,
|
|
"step": 1830
|
|
},
|
|
{
|
|
"entropy": 5.8145787715911865,
|
|
"epoch": 1.6669695592912313,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004923211095883161,
|
|
"loss": 5.8622,
|
|
"mean_token_accuracy": 0.14865206852555274,
|
|
"num_tokens": 3802807.0,
|
|
"step": 1835
|
|
},
|
|
{
|
|
"entropy": 5.873548316955566,
|
|
"epoch": 1.6715129486597,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004922292958178546,
|
|
"loss": 5.7348,
|
|
"mean_token_accuracy": 0.15383028537034987,
|
|
"num_tokens": 3812284.0,
|
|
"step": 1840
|
|
},
|
|
{
|
|
"entropy": 5.887331914901734,
|
|
"epoch": 1.676056338028169,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004921369460557,
|
|
"loss": 5.8734,
|
|
"mean_token_accuracy": 0.14546664506196977,
|
|
"num_tokens": 3823274.0,
|
|
"step": 1845
|
|
},
|
|
{
|
|
"entropy": 5.917618370056152,
|
|
"epoch": 1.680599727396638,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004920440605297159,
|
|
"loss": 5.8205,
|
|
"mean_token_accuracy": 0.1530941680073738,
|
|
"num_tokens": 3833768.0,
|
|
"step": 1850
|
|
},
|
|
{
|
|
"entropy": 5.82075252532959,
|
|
"epoch": 1.6851431167651068,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000491950639469088,
|
|
"loss": 5.8264,
|
|
"mean_token_accuracy": 0.1495286628603935,
|
|
"num_tokens": 3843937.0,
|
|
"step": 1855
|
|
},
|
|
{
|
|
"entropy": 5.841720771789551,
|
|
"epoch": 1.6896865061335755,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004918566831043238,
|
|
"loss": 5.7541,
|
|
"mean_token_accuracy": 0.15494302958250045,
|
|
"num_tokens": 3855072.0,
|
|
"step": 1860
|
|
},
|
|
{
|
|
"entropy": 5.852200174331665,
|
|
"epoch": 1.6942298955020445,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000491762191667251,
|
|
"loss": 5.899,
|
|
"mean_token_accuracy": 0.1420705497264862,
|
|
"num_tokens": 3866160.0,
|
|
"step": 1865
|
|
},
|
|
{
|
|
"entropy": 5.91382098197937,
|
|
"epoch": 1.6987732848705135,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000491667165391018,
|
|
"loss": 5.8198,
|
|
"mean_token_accuracy": 0.1473158195614815,
|
|
"num_tokens": 3876863.0,
|
|
"step": 1870
|
|
},
|
|
{
|
|
"entropy": 5.841605949401855,
|
|
"epoch": 1.7033166742389823,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004915716045100927,
|
|
"loss": 5.8921,
|
|
"mean_token_accuracy": 0.1498577430844307,
|
|
"num_tokens": 3887754.0,
|
|
"step": 1875
|
|
},
|
|
{
|
|
"entropy": 5.968225002288818,
|
|
"epoch": 1.707860063607451,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004914755092602621,
|
|
"loss": 5.8684,
|
|
"mean_token_accuracy": 0.15568319112062454,
|
|
"num_tokens": 3897591.0,
|
|
"step": 1880
|
|
},
|
|
{
|
|
"entropy": 5.79333004951477,
|
|
"epoch": 1.71240345297592,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004913788798786314,
|
|
"loss": 5.9011,
|
|
"mean_token_accuracy": 0.14456812888383866,
|
|
"num_tokens": 3908250.0,
|
|
"step": 1885
|
|
},
|
|
{
|
|
"entropy": 6.038985109329223,
|
|
"epoch": 1.716946842344389,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004912817166036243,
|
|
"loss": 5.9343,
|
|
"mean_token_accuracy": 0.14368811398744583,
|
|
"num_tokens": 3919385.0,
|
|
"step": 1890
|
|
},
|
|
{
|
|
"entropy": 5.936837005615234,
|
|
"epoch": 1.7214902317128578,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004911840196749813,
|
|
"loss": 6.0785,
|
|
"mean_token_accuracy": 0.14032945781946182,
|
|
"num_tokens": 3929999.0,
|
|
"step": 1895
|
|
},
|
|
{
|
|
"entropy": 5.973236036300659,
|
|
"epoch": 1.7260336210813265,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004910857893337602,
|
|
"loss": 5.8643,
|
|
"mean_token_accuracy": 0.15427177473902703,
|
|
"num_tokens": 3941311.0,
|
|
"step": 1900
|
|
},
|
|
{
|
|
"entropy": 5.810912132263184,
|
|
"epoch": 1.7305770104497955,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004909870258223342,
|
|
"loss": 5.8158,
|
|
"mean_token_accuracy": 0.14748491644859313,
|
|
"num_tokens": 3951409.0,
|
|
"step": 1905
|
|
},
|
|
{
|
|
"entropy": 5.870548439025879,
|
|
"epoch": 1.7351203998182645,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004908877293843926,
|
|
"loss": 5.867,
|
|
"mean_token_accuracy": 0.1453956812620163,
|
|
"num_tokens": 3961089.0,
|
|
"step": 1910
|
|
},
|
|
{
|
|
"entropy": 5.914389753341675,
|
|
"epoch": 1.7396637891867333,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004907879002649395,
|
|
"loss": 5.764,
|
|
"mean_token_accuracy": 0.14613812118768693,
|
|
"num_tokens": 3970548.0,
|
|
"step": 1915
|
|
},
|
|
{
|
|
"entropy": 5.785353899002075,
|
|
"epoch": 1.744207178555202,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004906875387102935,
|
|
"loss": 5.7569,
|
|
"mean_token_accuracy": 0.14780572652816773,
|
|
"num_tokens": 3981826.0,
|
|
"step": 1920
|
|
},
|
|
{
|
|
"entropy": 5.979347085952758,
|
|
"epoch": 1.748750567923671,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004905866449680864,
|
|
"loss": 5.9131,
|
|
"mean_token_accuracy": 0.1467357024550438,
|
|
"num_tokens": 3992063.0,
|
|
"step": 1925
|
|
},
|
|
{
|
|
"entropy": 5.8702459812164305,
|
|
"epoch": 1.75329395729214,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004904852192872638,
|
|
"loss": 5.8519,
|
|
"mean_token_accuracy": 0.14846348389983177,
|
|
"num_tokens": 4002007.0,
|
|
"step": 1930
|
|
},
|
|
{
|
|
"entropy": 5.827515935897827,
|
|
"epoch": 1.757837346660609,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004903832619180834,
|
|
"loss": 5.7665,
|
|
"mean_token_accuracy": 0.15415919572114944,
|
|
"num_tokens": 4012087.0,
|
|
"step": 1935
|
|
},
|
|
{
|
|
"entropy": 5.825321817398072,
|
|
"epoch": 1.7623807360290777,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004902807731121147,
|
|
"loss": 5.8063,
|
|
"mean_token_accuracy": 0.1539552964270115,
|
|
"num_tokens": 4022862.0,
|
|
"step": 1940
|
|
},
|
|
{
|
|
"entropy": 5.952997779846191,
|
|
"epoch": 1.7669241253975465,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004901777531222389,
|
|
"loss": 5.972,
|
|
"mean_token_accuracy": 0.14374119713902472,
|
|
"num_tokens": 4034992.0,
|
|
"step": 1945
|
|
},
|
|
{
|
|
"entropy": 5.880403089523315,
|
|
"epoch": 1.7714675147660155,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004900742022026474,
|
|
"loss": 5.8525,
|
|
"mean_token_accuracy": 0.1453924223780632,
|
|
"num_tokens": 4045749.0,
|
|
"step": 1950
|
|
},
|
|
{
|
|
"entropy": 5.856936359405518,
|
|
"epoch": 1.7760109041344845,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004899701206088419,
|
|
"loss": 5.7837,
|
|
"mean_token_accuracy": 0.14623216465115546,
|
|
"num_tokens": 4055733.0,
|
|
"step": 1955
|
|
},
|
|
{
|
|
"entropy": 5.943859243392945,
|
|
"epoch": 1.7805542935029532,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004898655085976333,
|
|
"loss": 5.8698,
|
|
"mean_token_accuracy": 0.14584364071488382,
|
|
"num_tokens": 4066153.0,
|
|
"step": 1960
|
|
},
|
|
{
|
|
"entropy": 5.876303386688233,
|
|
"epoch": 1.785097682871422,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004897603664271413,
|
|
"loss": 5.8122,
|
|
"mean_token_accuracy": 0.15110410153865814,
|
|
"num_tokens": 4075737.0,
|
|
"step": 1965
|
|
},
|
|
{
|
|
"entropy": 5.836494112014771,
|
|
"epoch": 1.789641072239891,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000489654694356794,
|
|
"loss": 5.8644,
|
|
"mean_token_accuracy": 0.15041233897209166,
|
|
"num_tokens": 4085642.0,
|
|
"step": 1970
|
|
},
|
|
{
|
|
"entropy": 5.96187949180603,
|
|
"epoch": 1.79418446160836,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004895484926473265,
|
|
"loss": 5.8934,
|
|
"mean_token_accuracy": 0.15415116995573044,
|
|
"num_tokens": 4095930.0,
|
|
"step": 1975
|
|
},
|
|
{
|
|
"entropy": 5.879729413986206,
|
|
"epoch": 1.7987278509768287,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.000489441761560781,
|
|
"loss": 5.7855,
|
|
"mean_token_accuracy": 0.15090516060590745,
|
|
"num_tokens": 4105707.0,
|
|
"step": 1980
|
|
},
|
|
{
|
|
"entropy": 5.780129861831665,
|
|
"epoch": 1.8032712403452975,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000489334501360506,
|
|
"loss": 5.806,
|
|
"mean_token_accuracy": 0.1504233419895172,
|
|
"num_tokens": 4115891.0,
|
|
"step": 1985
|
|
},
|
|
{
|
|
"entropy": 5.896237373352051,
|
|
"epoch": 1.8078146297137665,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004892267123111551,
|
|
"loss": 5.8615,
|
|
"mean_token_accuracy": 0.15289803296327592,
|
|
"num_tokens": 4125873.0,
|
|
"step": 1990
|
|
},
|
|
{
|
|
"entropy": 5.788020658493042,
|
|
"epoch": 1.8123580190822355,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004891183946786873,
|
|
"loss": 5.8067,
|
|
"mean_token_accuracy": 0.1504621237516403,
|
|
"num_tokens": 4137162.0,
|
|
"step": 1995
|
|
},
|
|
{
|
|
"entropy": 5.849090909957885,
|
|
"epoch": 1.8169014084507042,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004890095487303655,
|
|
"loss": 5.7702,
|
|
"mean_token_accuracy": 0.14995464831590652,
|
|
"num_tokens": 4147431.0,
|
|
"step": 2000
|
|
},
|
|
{
|
|
"epoch": 1.8169014084507042,
|
|
"eval_entropy": 5.798743722605151,
|
|
"eval_loss": 6.04840087890625,
|
|
"eval_mean_token_accuracy": 0.14510284125111825,
|
|
"eval_num_tokens": 4147431.0,
|
|
"eval_runtime": 2.7705,
|
|
"eval_samples_per_second": 1239.862,
|
|
"eval_steps_per_second": 155.208,
|
|
"step": 2000
|
|
},
|
|
{
|
|
"entropy": 5.8538463592529295,
|
|
"epoch": 1.821444797819173,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004889001747347562,
|
|
"loss": 5.7016,
|
|
"mean_token_accuracy": 0.15428239703178406,
|
|
"num_tokens": 4157993.0,
|
|
"step": 2005
|
|
},
|
|
{
|
|
"entropy": 5.782310867309571,
|
|
"epoch": 1.825988187187642,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.000488790272961729,
|
|
"loss": 5.7934,
|
|
"mean_token_accuracy": 0.1466740481555462,
|
|
"num_tokens": 4168834.0,
|
|
"step": 2010
|
|
},
|
|
{
|
|
"entropy": 5.798112392425537,
|
|
"epoch": 1.830531576556111,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004886798436824556,
|
|
"loss": 5.7602,
|
|
"mean_token_accuracy": 0.15480059683322905,
|
|
"num_tokens": 4178169.0,
|
|
"step": 2015
|
|
},
|
|
{
|
|
"entropy": 5.9378913879394535,
|
|
"epoch": 1.8350749659245797,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004885688871694091,
|
|
"loss": 5.8643,
|
|
"mean_token_accuracy": 0.14928691685199738,
|
|
"num_tokens": 4187817.0,
|
|
"step": 2020
|
|
},
|
|
{
|
|
"entropy": 5.86795482635498,
|
|
"epoch": 1.8396183552930485,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004884574036963639,
|
|
"loss": 5.8506,
|
|
"mean_token_accuracy": 0.14527582824230195,
|
|
"num_tokens": 4197577.0,
|
|
"step": 2025
|
|
},
|
|
{
|
|
"entropy": 5.883553504943848,
|
|
"epoch": 1.8441617446615175,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004883453935383941,
|
|
"loss": 5.8191,
|
|
"mean_token_accuracy": 0.15160404443740844,
|
|
"num_tokens": 4208234.0,
|
|
"step": 2030
|
|
},
|
|
{
|
|
"entropy": 5.775835227966309,
|
|
"epoch": 1.8487051340299865,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004882328569718738,
|
|
"loss": 5.7836,
|
|
"mean_token_accuracy": 0.1517630860209465,
|
|
"num_tokens": 4218562.0,
|
|
"step": 2035
|
|
},
|
|
{
|
|
"entropy": 5.899999475479126,
|
|
"epoch": 1.8532485233984552,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004881197942744758,
|
|
"loss": 5.9088,
|
|
"mean_token_accuracy": 0.15091830641031265,
|
|
"num_tokens": 4229202.0,
|
|
"step": 2040
|
|
},
|
|
{
|
|
"entropy": 5.8124762058258055,
|
|
"epoch": 1.857791912766924,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004880062057251711,
|
|
"loss": 5.678,
|
|
"mean_token_accuracy": 0.15422003269195556,
|
|
"num_tokens": 4238765.0,
|
|
"step": 2045
|
|
},
|
|
{
|
|
"entropy": 5.8610889434814455,
|
|
"epoch": 1.862335302135393,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.000487892091604228,
|
|
"loss": 5.81,
|
|
"mean_token_accuracy": 0.14024123027920724,
|
|
"num_tokens": 4249453.0,
|
|
"step": 2050
|
|
},
|
|
{
|
|
"entropy": 5.743572092056274,
|
|
"epoch": 1.866878691503862,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00048777745219321186,
|
|
"loss": 5.7194,
|
|
"mean_token_accuracy": 0.14468740597367286,
|
|
"num_tokens": 4259738.0,
|
|
"step": 2055
|
|
},
|
|
{
|
|
"entropy": 5.831390285491944,
|
|
"epoch": 1.8714220808723308,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00048766228777498405,
|
|
"loss": 5.9026,
|
|
"mean_token_accuracy": 0.14582569003105164,
|
|
"num_tokens": 4269405.0,
|
|
"step": 2060
|
|
},
|
|
{
|
|
"entropy": 5.906390714645386,
|
|
"epoch": 1.8759654702407995,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00048754659863370125,
|
|
"loss": 5.7288,
|
|
"mean_token_accuracy": 0.14663628339767457,
|
|
"num_tokens": 4279821.0,
|
|
"step": 2065
|
|
},
|
|
{
|
|
"entropy": 5.712376976013184,
|
|
"epoch": 1.8805088596092685,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00048743038505481503,
|
|
"loss": 5.747,
|
|
"mean_token_accuracy": 0.14767933040857315,
|
|
"num_tokens": 4290625.0,
|
|
"step": 2070
|
|
},
|
|
{
|
|
"entropy": 5.834017515182495,
|
|
"epoch": 1.8850522489777375,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004873136473250708,
|
|
"loss": 5.8011,
|
|
"mean_token_accuracy": 0.14723728150129317,
|
|
"num_tokens": 4301327.0,
|
|
"step": 2075
|
|
},
|
|
{
|
|
"entropy": 5.735596513748169,
|
|
"epoch": 1.8895956383462063,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00048719638573250715,
|
|
"loss": 5.6988,
|
|
"mean_token_accuracy": 0.1526697278022766,
|
|
"num_tokens": 4311427.0,
|
|
"step": 2080
|
|
},
|
|
{
|
|
"entropy": 5.865527486801147,
|
|
"epoch": 1.894139027714675,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004870786005664555,
|
|
"loss": 5.8037,
|
|
"mean_token_accuracy": 0.14820494502782822,
|
|
"num_tokens": 4322258.0,
|
|
"step": 2085
|
|
},
|
|
{
|
|
"entropy": 5.896405649185181,
|
|
"epoch": 1.898682417083144,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004869602921175392,
|
|
"loss": 5.9037,
|
|
"mean_token_accuracy": 0.14564540088176728,
|
|
"num_tokens": 4332583.0,
|
|
"step": 2090
|
|
},
|
|
{
|
|
"entropy": 5.855921506881714,
|
|
"epoch": 1.903225806451613,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004868414606776724,
|
|
"loss": 5.9221,
|
|
"mean_token_accuracy": 0.14587701708078385,
|
|
"num_tokens": 4343027.0,
|
|
"step": 2095
|
|
},
|
|
{
|
|
"entropy": 5.971296787261963,
|
|
"epoch": 1.9077691958200818,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00048672210654005996,
|
|
"loss": 5.9664,
|
|
"mean_token_accuracy": 0.13993714973330498,
|
|
"num_tokens": 4353234.0,
|
|
"step": 2100
|
|
},
|
|
{
|
|
"entropy": 5.78577356338501,
|
|
"epoch": 1.9123125851885505,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00048660222999919616,
|
|
"loss": 5.7552,
|
|
"mean_token_accuracy": 0.15642950534820557,
|
|
"num_tokens": 4363074.0,
|
|
"step": 2105
|
|
},
|
|
{
|
|
"entropy": 5.752347373962403,
|
|
"epoch": 1.9168559745570195,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004864818313508647,
|
|
"loss": 5.7488,
|
|
"mean_token_accuracy": 0.1524498701095581,
|
|
"num_tokens": 4373303.0,
|
|
"step": 2110
|
|
},
|
|
{
|
|
"entropy": 5.875413036346435,
|
|
"epoch": 1.9213993639254885,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004863609108921372,
|
|
"loss": 5.758,
|
|
"mean_token_accuracy": 0.15022070854902267,
|
|
"num_tokens": 4382310.0,
|
|
"step": 2115
|
|
},
|
|
{
|
|
"entropy": 5.830654621124268,
|
|
"epoch": 1.9259427532939573,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004862394689213728,
|
|
"loss": 5.8264,
|
|
"mean_token_accuracy": 0.1505594179034233,
|
|
"num_tokens": 4393151.0,
|
|
"step": 2120
|
|
},
|
|
{
|
|
"entropy": 5.844172525405884,
|
|
"epoch": 1.930486142662426,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004861175057382175,
|
|
"loss": 5.7469,
|
|
"mean_token_accuracy": 0.15488230288028718,
|
|
"num_tokens": 4403036.0,
|
|
"step": 2125
|
|
},
|
|
{
|
|
"entropy": 5.8233729839324955,
|
|
"epoch": 1.935029532030895,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004859950216436034,
|
|
"loss": 5.7512,
|
|
"mean_token_accuracy": 0.14788225442171096,
|
|
"num_tokens": 4413703.0,
|
|
"step": 2130
|
|
},
|
|
{
|
|
"entropy": 5.837303209304809,
|
|
"epoch": 1.939572921399364,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004858720169397478,
|
|
"loss": 5.8395,
|
|
"mean_token_accuracy": 0.14474900364875792,
|
|
"num_tokens": 4424208.0,
|
|
"step": 2135
|
|
},
|
|
{
|
|
"entropy": 5.8106992721557615,
|
|
"epoch": 1.9441163107678328,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004857484919301525,
|
|
"loss": 5.8347,
|
|
"mean_token_accuracy": 0.14674064815044402,
|
|
"num_tokens": 4434077.0,
|
|
"step": 2140
|
|
},
|
|
{
|
|
"entropy": 5.826570606231689,
|
|
"epoch": 1.9486597001363015,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004856244469196034,
|
|
"loss": 5.7411,
|
|
"mean_token_accuracy": 0.15387579798698425,
|
|
"num_tokens": 4444344.0,
|
|
"step": 2145
|
|
},
|
|
{
|
|
"entropy": 5.7635636806488035,
|
|
"epoch": 1.9532030895047705,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.000485499882214169,
|
|
"loss": 5.6898,
|
|
"mean_token_accuracy": 0.157929727435112,
|
|
"num_tokens": 4453632.0,
|
|
"step": 2150
|
|
},
|
|
{
|
|
"entropy": 5.771280765533447,
|
|
"epoch": 1.9577464788732395,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004853747981212003,
|
|
"loss": 5.7936,
|
|
"mean_token_accuracy": 0.15230028629302977,
|
|
"num_tokens": 4464139.0,
|
|
"step": 2155
|
|
},
|
|
{
|
|
"entropy": 5.917464017868042,
|
|
"epoch": 1.9622898682417085,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004852491949493301,
|
|
"loss": 5.844,
|
|
"mean_token_accuracy": 0.15021804422140123,
|
|
"num_tokens": 4474006.0,
|
|
"step": 2160
|
|
},
|
|
{
|
|
"entropy": 5.7739355087280275,
|
|
"epoch": 1.9668332576101772,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004851230730084716,
|
|
"loss": 5.7715,
|
|
"mean_token_accuracy": 0.15631687343120576,
|
|
"num_tokens": 4484494.0,
|
|
"step": 2165
|
|
},
|
|
{
|
|
"entropy": 5.857206058502197,
|
|
"epoch": 1.971376646978646,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00048499643260981816,
|
|
"loss": 5.8,
|
|
"mean_token_accuracy": 0.15579398348927498,
|
|
"num_tokens": 4494694.0,
|
|
"step": 2170
|
|
},
|
|
{
|
|
"entropy": 5.734886598587036,
|
|
"epoch": 1.975920036347115,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004848692740658424,
|
|
"loss": 5.8027,
|
|
"mean_token_accuracy": 0.15389519929885864,
|
|
"num_tokens": 4504575.0,
|
|
"step": 2175
|
|
},
|
|
{
|
|
"entropy": 5.839699220657349,
|
|
"epoch": 1.980463425715584,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004847415976902954,
|
|
"loss": 5.8051,
|
|
"mean_token_accuracy": 0.14770661741495134,
|
|
"num_tokens": 4515767.0,
|
|
"step": 2180
|
|
},
|
|
{
|
|
"entropy": 5.863554525375366,
|
|
"epoch": 1.9850068150840527,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00048461340379820587,
|
|
"loss": 5.9073,
|
|
"mean_token_accuracy": 0.14469317942857743,
|
|
"num_tokens": 4526194.0,
|
|
"step": 2185
|
|
},
|
|
{
|
|
"entropy": 5.874572706222534,
|
|
"epoch": 1.9895502044525215,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00048448469270587945,
|
|
"loss": 5.8377,
|
|
"mean_token_accuracy": 0.14753615111112595,
|
|
"num_tokens": 4536662.0,
|
|
"step": 2190
|
|
},
|
|
{
|
|
"entropy": 5.851900196075439,
|
|
"epoch": 1.9940935938209905,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00048435546473089814,
|
|
"loss": 5.7767,
|
|
"mean_token_accuracy": 0.15122774839401246,
|
|
"num_tokens": 4546749.0,
|
|
"step": 2195
|
|
},
|
|
{
|
|
"entropy": 5.776758193969727,
|
|
"epoch": 1.9986369831894595,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00048422572019211896,
|
|
"loss": 5.703,
|
|
"mean_token_accuracy": 0.15339836329221726,
|
|
"num_tokens": 4556194.0,
|
|
"step": 2200
|
|
},
|
|
{
|
|
"entropy": 5.779335021972656,
|
|
"epoch": 2.0027260336210815,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00048409545940967375,
|
|
"loss": 5.576,
|
|
"mean_token_accuracy": 0.15858013927936554,
|
|
"num_tokens": 4563927.0,
|
|
"step": 2205
|
|
},
|
|
{
|
|
"entropy": 5.776248121261597,
|
|
"epoch": 2.00726942298955,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000483964682704968,
|
|
"loss": 5.4486,
|
|
"mean_token_accuracy": 0.16479917168617247,
|
|
"num_tokens": 4574800.0,
|
|
"step": 2210
|
|
},
|
|
{
|
|
"entropy": 5.733392667770386,
|
|
"epoch": 2.011812812358019,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00048383339040068024,
|
|
"loss": 5.5052,
|
|
"mean_token_accuracy": 0.1624051257967949,
|
|
"num_tokens": 4585810.0,
|
|
"step": 2215
|
|
},
|
|
{
|
|
"entropy": 5.806802272796631,
|
|
"epoch": 2.016356201726488,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004837015828207612,
|
|
"loss": 5.6278,
|
|
"mean_token_accuracy": 0.15674534142017366,
|
|
"num_tokens": 4596227.0,
|
|
"step": 2220
|
|
},
|
|
{
|
|
"entropy": 5.777090406417846,
|
|
"epoch": 2.020899591094957,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004835692602904329,
|
|
"loss": 5.4859,
|
|
"mean_token_accuracy": 0.16422860473394393,
|
|
"num_tokens": 4606435.0,
|
|
"step": 2225
|
|
},
|
|
{
|
|
"entropy": 5.76586217880249,
|
|
"epoch": 2.0254429804634255,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004834364231361882,
|
|
"loss": 5.5091,
|
|
"mean_token_accuracy": 0.15572037696838378,
|
|
"num_tokens": 4616130.0,
|
|
"step": 2230
|
|
},
|
|
{
|
|
"entropy": 5.777824401855469,
|
|
"epoch": 2.0299863698318945,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004833030716857894,
|
|
"loss": 5.5088,
|
|
"mean_token_accuracy": 0.16416359841823577,
|
|
"num_tokens": 4626529.0,
|
|
"step": 2235
|
|
},
|
|
{
|
|
"entropy": 5.775467109680176,
|
|
"epoch": 2.0345297592003635,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00048316920626826807,
|
|
"loss": 5.5025,
|
|
"mean_token_accuracy": 0.16245093941688538,
|
|
"num_tokens": 4637327.0,
|
|
"step": 2240
|
|
},
|
|
{
|
|
"entropy": 5.759325981140137,
|
|
"epoch": 2.0390731485688325,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00048303482721392363,
|
|
"loss": 5.4708,
|
|
"mean_token_accuracy": 0.16145365685224533,
|
|
"num_tokens": 4647412.0,
|
|
"step": 2245
|
|
},
|
|
{
|
|
"entropy": 5.776975536346436,
|
|
"epoch": 2.043616537937301,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00048289993485432325,
|
|
"loss": 5.5525,
|
|
"mean_token_accuracy": 0.15803057104349136,
|
|
"num_tokens": 4659095.0,
|
|
"step": 2250
|
|
},
|
|
{
|
|
"entropy": 5.723943281173706,
|
|
"epoch": 2.04815992730577,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00048276452952230036,
|
|
"loss": 5.4795,
|
|
"mean_token_accuracy": 0.17061184346675873,
|
|
"num_tokens": 4669239.0,
|
|
"step": 2255
|
|
},
|
|
{
|
|
"entropy": 5.823205375671387,
|
|
"epoch": 2.052703316674239,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00048262861155195407,
|
|
"loss": 5.5317,
|
|
"mean_token_accuracy": 0.1543350949883461,
|
|
"num_tokens": 4679199.0,
|
|
"step": 2260
|
|
},
|
|
{
|
|
"entropy": 5.710643100738525,
|
|
"epoch": 2.057246706042708,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004824921812786486,
|
|
"loss": 5.4819,
|
|
"mean_token_accuracy": 0.1558678813278675,
|
|
"num_tokens": 4689884.0,
|
|
"step": 2265
|
|
},
|
|
{
|
|
"entropy": 5.7122931480407715,
|
|
"epoch": 2.0617900954111765,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000482355239039012,
|
|
"loss": 5.5341,
|
|
"mean_token_accuracy": 0.15882748365402222,
|
|
"num_tokens": 4700271.0,
|
|
"step": 2270
|
|
},
|
|
{
|
|
"entropy": 5.693128299713135,
|
|
"epoch": 2.0663334847796455,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004822177851709356,
|
|
"loss": 5.4944,
|
|
"mean_token_accuracy": 0.16197725534439086,
|
|
"num_tokens": 4709880.0,
|
|
"step": 2275
|
|
},
|
|
{
|
|
"entropy": 5.725936937332153,
|
|
"epoch": 2.0708768741481145,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00048207982001357327,
|
|
"loss": 5.4663,
|
|
"mean_token_accuracy": 0.1579332634806633,
|
|
"num_tokens": 4720492.0,
|
|
"step": 2280
|
|
},
|
|
{
|
|
"entropy": 5.68801097869873,
|
|
"epoch": 2.0754202635165835,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004819413439073402,
|
|
"loss": 5.537,
|
|
"mean_token_accuracy": 0.1539834961295128,
|
|
"num_tokens": 4731213.0,
|
|
"step": 2285
|
|
},
|
|
{
|
|
"entropy": 5.793666934967041,
|
|
"epoch": 2.079963652885052,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004818023571939125,
|
|
"loss": 5.4712,
|
|
"mean_token_accuracy": 0.1569421648979187,
|
|
"num_tokens": 4741680.0,
|
|
"step": 2290
|
|
},
|
|
{
|
|
"entropy": 5.605185031890869,
|
|
"epoch": 2.084507042253521,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.000481662860216226,
|
|
"loss": 5.3746,
|
|
"mean_token_accuracy": 0.17384990006685258,
|
|
"num_tokens": 4750805.0,
|
|
"step": 2295
|
|
},
|
|
{
|
|
"entropy": 5.6640784740448,
|
|
"epoch": 2.08905043162199,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00048152285331847574,
|
|
"loss": 5.4417,
|
|
"mean_token_accuracy": 0.16408300250768662,
|
|
"num_tokens": 4760554.0,
|
|
"step": 2300
|
|
},
|
|
{
|
|
"entropy": 5.674292945861817,
|
|
"epoch": 2.093593820990459,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004813823368461148,
|
|
"loss": 5.3829,
|
|
"mean_token_accuracy": 0.16840588450431823,
|
|
"num_tokens": 4770528.0,
|
|
"step": 2305
|
|
},
|
|
{
|
|
"entropy": 5.661532211303711,
|
|
"epoch": 2.098137210358928,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004812413111458534,
|
|
"loss": 5.4174,
|
|
"mean_token_accuracy": 0.1606951981782913,
|
|
"num_tokens": 4781216.0,
|
|
"step": 2310
|
|
},
|
|
{
|
|
"entropy": 5.646615839004516,
|
|
"epoch": 2.1026805997273965,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004810997765656587,
|
|
"loss": 5.4912,
|
|
"mean_token_accuracy": 0.1671098828315735,
|
|
"num_tokens": 4790329.0,
|
|
"step": 2315
|
|
},
|
|
{
|
|
"entropy": 5.686977338790894,
|
|
"epoch": 2.1072239890958655,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00048095773345475294,
|
|
"loss": 5.4388,
|
|
"mean_token_accuracy": 0.1641346976161003,
|
|
"num_tokens": 4800393.0,
|
|
"step": 2320
|
|
},
|
|
{
|
|
"entropy": 5.707598876953125,
|
|
"epoch": 2.1117673784643345,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00048081518216361367,
|
|
"loss": 5.5388,
|
|
"mean_token_accuracy": 0.16286579817533492,
|
|
"num_tokens": 4810297.0,
|
|
"step": 2325
|
|
},
|
|
{
|
|
"entropy": 5.730789613723755,
|
|
"epoch": 2.1163107678328035,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004806721230439719,
|
|
"loss": 5.4454,
|
|
"mean_token_accuracy": 0.16205213963985443,
|
|
"num_tokens": 4819415.0,
|
|
"step": 2330
|
|
},
|
|
{
|
|
"entropy": 5.682396125793457,
|
|
"epoch": 2.120854157201272,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004805285564488117,
|
|
"loss": 5.5011,
|
|
"mean_token_accuracy": 0.1609583541750908,
|
|
"num_tokens": 4829958.0,
|
|
"step": 2335
|
|
},
|
|
{
|
|
"entropy": 5.691484546661377,
|
|
"epoch": 2.125397546569741,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004803844827323696,
|
|
"loss": 5.486,
|
|
"mean_token_accuracy": 0.16416887789964676,
|
|
"num_tokens": 4839591.0,
|
|
"step": 2340
|
|
},
|
|
{
|
|
"entropy": 5.799030828475952,
|
|
"epoch": 2.12994093593821,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004802399022501329,
|
|
"loss": 5.5559,
|
|
"mean_token_accuracy": 0.1574663907289505,
|
|
"num_tokens": 4850697.0,
|
|
"step": 2345
|
|
},
|
|
{
|
|
"entropy": 5.5817474842071535,
|
|
"epoch": 2.134484325306679,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004800948153588397,
|
|
"loss": 5.4699,
|
|
"mean_token_accuracy": 0.16589853763580323,
|
|
"num_tokens": 4862523.0,
|
|
"step": 2350
|
|
},
|
|
{
|
|
"entropy": 5.6902327060699465,
|
|
"epoch": 2.1390277146751475,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00047994922241647746,
|
|
"loss": 5.397,
|
|
"mean_token_accuracy": 0.16300795674324037,
|
|
"num_tokens": 4873432.0,
|
|
"step": 2355
|
|
},
|
|
{
|
|
"entropy": 5.673041486740113,
|
|
"epoch": 2.1435711040436165,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00047980312378228244,
|
|
"loss": 5.518,
|
|
"mean_token_accuracy": 0.15471220016479492,
|
|
"num_tokens": 4884199.0,
|
|
"step": 2360
|
|
},
|
|
{
|
|
"entropy": 5.730643081665039,
|
|
"epoch": 2.1481144934120855,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00047965651981673823,
|
|
"loss": 5.4789,
|
|
"mean_token_accuracy": 0.16016445010900499,
|
|
"num_tokens": 4894734.0,
|
|
"step": 2365
|
|
},
|
|
{
|
|
"entropy": 5.643956184387207,
|
|
"epoch": 2.1526578827805545,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00047950941088157576,
|
|
"loss": 5.4034,
|
|
"mean_token_accuracy": 0.1633806273341179,
|
|
"num_tokens": 4905536.0,
|
|
"step": 2370
|
|
},
|
|
{
|
|
"entropy": 5.665775442123413,
|
|
"epoch": 2.157201272149023,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004793617973397715,
|
|
"loss": 5.4018,
|
|
"mean_token_accuracy": 0.17174910604953766,
|
|
"num_tokens": 4915176.0,
|
|
"step": 2375
|
|
},
|
|
{
|
|
"entropy": 5.67309250831604,
|
|
"epoch": 2.161744661517492,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00047921367955554745,
|
|
"loss": 5.4644,
|
|
"mean_token_accuracy": 0.16488925367593765,
|
|
"num_tokens": 4925937.0,
|
|
"step": 2380
|
|
},
|
|
{
|
|
"entropy": 5.645473146438599,
|
|
"epoch": 2.166288050885961,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004790650578943693,
|
|
"loss": 5.4695,
|
|
"mean_token_accuracy": 0.16120921671390534,
|
|
"num_tokens": 4937272.0,
|
|
"step": 2385
|
|
},
|
|
{
|
|
"entropy": 5.632696533203125,
|
|
"epoch": 2.17083144025443,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00047891593272294636,
|
|
"loss": 5.5763,
|
|
"mean_token_accuracy": 0.1590942397713661,
|
|
"num_tokens": 4947798.0,
|
|
"step": 2390
|
|
},
|
|
{
|
|
"entropy": 5.696415376663208,
|
|
"epoch": 2.1753748296228985,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00047876630440923,
|
|
"loss": 5.5712,
|
|
"mean_token_accuracy": 0.15393886268138884,
|
|
"num_tokens": 4958150.0,
|
|
"step": 2395
|
|
},
|
|
{
|
|
"entropy": 5.698954343795776,
|
|
"epoch": 2.1799182189913675,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004786161733224134,
|
|
"loss": 5.4487,
|
|
"mean_token_accuracy": 0.1594776451587677,
|
|
"num_tokens": 4968588.0,
|
|
"step": 2400
|
|
},
|
|
{
|
|
"entropy": 5.663316869735718,
|
|
"epoch": 2.1844616083598365,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00047846553983293006,
|
|
"loss": 5.5337,
|
|
"mean_token_accuracy": 0.16152950376272202,
|
|
"num_tokens": 4979169.0,
|
|
"step": 2405
|
|
},
|
|
{
|
|
"entropy": 5.752840995788574,
|
|
"epoch": 2.1890049977283055,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00047831440431245307,
|
|
"loss": 5.612,
|
|
"mean_token_accuracy": 0.15289975255727767,
|
|
"num_tokens": 4990543.0,
|
|
"step": 2410
|
|
},
|
|
{
|
|
"entropy": 5.596266984939575,
|
|
"epoch": 2.193548387096774,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00047816276713389424,
|
|
"loss": 5.3947,
|
|
"mean_token_accuracy": 0.15945702493190766,
|
|
"num_tokens": 5000546.0,
|
|
"step": 2415
|
|
},
|
|
{
|
|
"entropy": 5.663093233108521,
|
|
"epoch": 2.198091776465243,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004780106286714034,
|
|
"loss": 5.5163,
|
|
"mean_token_accuracy": 0.16216596364974975,
|
|
"num_tokens": 5011092.0,
|
|
"step": 2420
|
|
},
|
|
{
|
|
"entropy": 5.6491169929504395,
|
|
"epoch": 2.202635165833712,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000477857989300367,
|
|
"loss": 5.4947,
|
|
"mean_token_accuracy": 0.16076005548238753,
|
|
"num_tokens": 5021317.0,
|
|
"step": 2425
|
|
},
|
|
{
|
|
"entropy": 5.694098377227784,
|
|
"epoch": 2.207178555202181,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00047770484939740757,
|
|
"loss": 5.3969,
|
|
"mean_token_accuracy": 0.16764315515756606,
|
|
"num_tokens": 5031120.0,
|
|
"step": 2430
|
|
},
|
|
{
|
|
"entropy": 5.648887586593628,
|
|
"epoch": 2.2117219445706495,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004775512093403824,
|
|
"loss": 5.5462,
|
|
"mean_token_accuracy": 0.1566228985786438,
|
|
"num_tokens": 5040768.0,
|
|
"step": 2435
|
|
},
|
|
{
|
|
"entropy": 5.678833961486816,
|
|
"epoch": 2.2162653339391185,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00047739706950838327,
|
|
"loss": 5.4971,
|
|
"mean_token_accuracy": 0.1628997728228569,
|
|
"num_tokens": 5050639.0,
|
|
"step": 2440
|
|
},
|
|
{
|
|
"entropy": 5.655918455123901,
|
|
"epoch": 2.2208087233075875,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00047724243028173484,
|
|
"loss": 5.4374,
|
|
"mean_token_accuracy": 0.16694911271333696,
|
|
"num_tokens": 5060624.0,
|
|
"step": 2445
|
|
},
|
|
{
|
|
"entropy": 5.62668809890747,
|
|
"epoch": 2.2253521126760565,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00047708729204199406,
|
|
"loss": 5.5167,
|
|
"mean_token_accuracy": 0.15899598151445388,
|
|
"num_tokens": 5071894.0,
|
|
"step": 2450
|
|
},
|
|
{
|
|
"entropy": 5.689900016784668,
|
|
"epoch": 2.229895502044525,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000476931655171949,
|
|
"loss": 5.4751,
|
|
"mean_token_accuracy": 0.16796932816505433,
|
|
"num_tokens": 5082453.0,
|
|
"step": 2455
|
|
},
|
|
{
|
|
"entropy": 5.69913387298584,
|
|
"epoch": 2.234438891412994,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004767755200556183,
|
|
"loss": 5.5617,
|
|
"mean_token_accuracy": 0.15929114818572998,
|
|
"num_tokens": 5093033.0,
|
|
"step": 2460
|
|
},
|
|
{
|
|
"entropy": 5.687612295150757,
|
|
"epoch": 2.238982280781463,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004766188870782497,
|
|
"loss": 5.5417,
|
|
"mean_token_accuracy": 0.16963887810707093,
|
|
"num_tokens": 5103908.0,
|
|
"step": 2465
|
|
},
|
|
{
|
|
"entropy": 5.69229302406311,
|
|
"epoch": 2.243525670149932,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00047646175662631967,
|
|
"loss": 5.5017,
|
|
"mean_token_accuracy": 0.16409752070903777,
|
|
"num_tokens": 5114302.0,
|
|
"step": 2470
|
|
},
|
|
{
|
|
"entropy": 5.608609914779663,
|
|
"epoch": 2.2480690595184005,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00047630412908753183,
|
|
"loss": 5.4077,
|
|
"mean_token_accuracy": 0.17001562267541886,
|
|
"num_tokens": 5124055.0,
|
|
"step": 2475
|
|
},
|
|
{
|
|
"entropy": 5.675837469100952,
|
|
"epoch": 2.2526124488868695,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00047614600485081657,
|
|
"loss": 5.5237,
|
|
"mean_token_accuracy": 0.1581522673368454,
|
|
"num_tokens": 5134496.0,
|
|
"step": 2480
|
|
},
|
|
{
|
|
"entropy": 5.691870307922363,
|
|
"epoch": 2.2571558382553385,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00047598738430632963,
|
|
"loss": 5.5511,
|
|
"mean_token_accuracy": 0.16181253939867019,
|
|
"num_tokens": 5146008.0,
|
|
"step": 2485
|
|
},
|
|
{
|
|
"entropy": 5.647511911392212,
|
|
"epoch": 2.2616992276238075,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00047582826784545146,
|
|
"loss": 5.4431,
|
|
"mean_token_accuracy": 0.1717854768037796,
|
|
"num_tokens": 5156733.0,
|
|
"step": 2490
|
|
},
|
|
{
|
|
"entropy": 5.7254432201385494,
|
|
"epoch": 2.266242616992276,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00047566865586078615,
|
|
"loss": 5.4999,
|
|
"mean_token_accuracy": 0.16349462866783143,
|
|
"num_tokens": 5166452.0,
|
|
"step": 2495
|
|
},
|
|
{
|
|
"entropy": 5.634735774993897,
|
|
"epoch": 2.270786006360745,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00047550854874616047,
|
|
"loss": 5.5769,
|
|
"mean_token_accuracy": 0.16026249378919602,
|
|
"num_tokens": 5177984.0,
|
|
"step": 2500
|
|
},
|
|
{
|
|
"entropy": 5.796362590789795,
|
|
"epoch": 2.275329395729214,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00047534794689662257,
|
|
"loss": 5.5637,
|
|
"mean_token_accuracy": 0.15804722011089326,
|
|
"num_tokens": 5187815.0,
|
|
"step": 2505
|
|
},
|
|
{
|
|
"entropy": 5.662720251083374,
|
|
"epoch": 2.279872785097683,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004751868507084418,
|
|
"loss": 5.522,
|
|
"mean_token_accuracy": 0.1579802542924881,
|
|
"num_tokens": 5198333.0,
|
|
"step": 2510
|
|
},
|
|
{
|
|
"entropy": 5.658054828643799,
|
|
"epoch": 2.284416174466152,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004750252605791068,
|
|
"loss": 5.4597,
|
|
"mean_token_accuracy": 0.17050717920064926,
|
|
"num_tokens": 5209068.0,
|
|
"step": 2515
|
|
},
|
|
{
|
|
"entropy": 5.637749052047729,
|
|
"epoch": 2.2889595638346205,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004748631769073254,
|
|
"loss": 5.4522,
|
|
"mean_token_accuracy": 0.16521517485380172,
|
|
"num_tokens": 5218986.0,
|
|
"step": 2520
|
|
},
|
|
{
|
|
"entropy": 5.607774448394776,
|
|
"epoch": 2.2935029532030895,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004747006000930227,
|
|
"loss": 5.4855,
|
|
"mean_token_accuracy": 0.1623449444770813,
|
|
"num_tokens": 5228242.0,
|
|
"step": 2525
|
|
},
|
|
{
|
|
"entropy": 5.673880338668823,
|
|
"epoch": 2.2980463425715585,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004745375305373409,
|
|
"loss": 5.4941,
|
|
"mean_token_accuracy": 0.16177093088626862,
|
|
"num_tokens": 5238772.0,
|
|
"step": 2530
|
|
},
|
|
{
|
|
"entropy": 5.633888149261475,
|
|
"epoch": 2.302589731940027,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00047437396864263804,
|
|
"loss": 5.4693,
|
|
"mean_token_accuracy": 0.16467007696628572,
|
|
"num_tokens": 5248588.0,
|
|
"step": 2535
|
|
},
|
|
{
|
|
"entropy": 5.623581743240356,
|
|
"epoch": 2.307133121308496,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004742099148124866,
|
|
"loss": 5.4498,
|
|
"mean_token_accuracy": 0.16977469027042388,
|
|
"num_tokens": 5258593.0,
|
|
"step": 2540
|
|
},
|
|
{
|
|
"entropy": 5.738746976852417,
|
|
"epoch": 2.311676510676965,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004740453694516734,
|
|
"loss": 5.5555,
|
|
"mean_token_accuracy": 0.15645188391208648,
|
|
"num_tokens": 5269639.0,
|
|
"step": 2545
|
|
},
|
|
{
|
|
"entropy": 5.588364028930664,
|
|
"epoch": 2.316219900045434,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00047388033296619746,
|
|
"loss": 5.5628,
|
|
"mean_token_accuracy": 0.16065715104341508,
|
|
"num_tokens": 5279428.0,
|
|
"step": 2550
|
|
},
|
|
{
|
|
"entropy": 5.7361993312835695,
|
|
"epoch": 2.320763289413903,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004737148057632701,
|
|
"loss": 5.4676,
|
|
"mean_token_accuracy": 0.1655708596110344,
|
|
"num_tokens": 5289986.0,
|
|
"step": 2555
|
|
},
|
|
{
|
|
"entropy": 5.563482046127319,
|
|
"epoch": 2.3253066787823715,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004735487882513131,
|
|
"loss": 5.422,
|
|
"mean_token_accuracy": 0.16048859804868698,
|
|
"num_tokens": 5300629.0,
|
|
"step": 2560
|
|
},
|
|
{
|
|
"entropy": 5.624101209640503,
|
|
"epoch": 2.3298500681508405,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004733822808399583,
|
|
"loss": 5.4688,
|
|
"mean_token_accuracy": 0.16383247971534728,
|
|
"num_tokens": 5310472.0,
|
|
"step": 2565
|
|
},
|
|
{
|
|
"entropy": 5.689055585861206,
|
|
"epoch": 2.3343934575193095,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00047321528394004615,
|
|
"loss": 5.4999,
|
|
"mean_token_accuracy": 0.16311483830213547,
|
|
"num_tokens": 5320981.0,
|
|
"step": 2570
|
|
},
|
|
{
|
|
"entropy": 5.57588529586792,
|
|
"epoch": 2.3389368468877785,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00047304779796362485,
|
|
"loss": 5.4144,
|
|
"mean_token_accuracy": 0.16940876841545105,
|
|
"num_tokens": 5330949.0,
|
|
"step": 2575
|
|
},
|
|
{
|
|
"entropy": 5.59773621559143,
|
|
"epoch": 2.343480236256247,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00047287982332394943,
|
|
"loss": 5.4522,
|
|
"mean_token_accuracy": 0.15855366736650467,
|
|
"num_tokens": 5340748.0,
|
|
"step": 2580
|
|
},
|
|
{
|
|
"entropy": 5.671061325073242,
|
|
"epoch": 2.348023625624716,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00047271136043548057,
|
|
"loss": 5.6066,
|
|
"mean_token_accuracy": 0.1577791079878807,
|
|
"num_tokens": 5352923.0,
|
|
"step": 2585
|
|
},
|
|
{
|
|
"entropy": 5.621159791946411,
|
|
"epoch": 2.352567014993185,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004725424097138838,
|
|
"loss": 5.4287,
|
|
"mean_token_accuracy": 0.16791379302740098,
|
|
"num_tokens": 5361923.0,
|
|
"step": 2590
|
|
},
|
|
{
|
|
"entropy": 5.703397512435913,
|
|
"epoch": 2.357110404361654,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00047237297157602816,
|
|
"loss": 5.5385,
|
|
"mean_token_accuracy": 0.16827826499938964,
|
|
"num_tokens": 5372268.0,
|
|
"step": 2595
|
|
},
|
|
{
|
|
"entropy": 5.669145345687866,
|
|
"epoch": 2.3616537937301225,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004722030464399854,
|
|
"loss": 5.4358,
|
|
"mean_token_accuracy": 0.1655590459704399,
|
|
"num_tokens": 5382071.0,
|
|
"step": 2600
|
|
},
|
|
{
|
|
"entropy": 5.599398756027222,
|
|
"epoch": 2.3661971830985915,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.000472032634725029,
|
|
"loss": 5.5129,
|
|
"mean_token_accuracy": 0.163224895298481,
|
|
"num_tokens": 5392139.0,
|
|
"step": 2605
|
|
},
|
|
{
|
|
"entropy": 5.694211149215699,
|
|
"epoch": 2.3707405724670605,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00047186173685163273,
|
|
"loss": 5.5247,
|
|
"mean_token_accuracy": 0.16626497358083725,
|
|
"num_tokens": 5402868.0,
|
|
"step": 2610
|
|
},
|
|
{
|
|
"entropy": 5.617294597625732,
|
|
"epoch": 2.3752839618355295,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00047169035324147023,
|
|
"loss": 5.5259,
|
|
"mean_token_accuracy": 0.1652606412768364,
|
|
"num_tokens": 5413029.0,
|
|
"step": 2615
|
|
},
|
|
{
|
|
"entropy": 5.5882978439331055,
|
|
"epoch": 2.379827351203998,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00047151848431741363,
|
|
"loss": 5.4675,
|
|
"mean_token_accuracy": 0.164324614405632,
|
|
"num_tokens": 5423145.0,
|
|
"step": 2620
|
|
},
|
|
{
|
|
"entropy": 5.6815375804901125,
|
|
"epoch": 2.384370740572467,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004713461305035322,
|
|
"loss": 5.4933,
|
|
"mean_token_accuracy": 0.16378677934408187,
|
|
"num_tokens": 5433715.0,
|
|
"step": 2625
|
|
},
|
|
{
|
|
"entropy": 5.533969593048096,
|
|
"epoch": 2.388914129940936,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000471173292225092,
|
|
"loss": 5.3966,
|
|
"mean_token_accuracy": 0.16783206909894943,
|
|
"num_tokens": 5444565.0,
|
|
"step": 2630
|
|
},
|
|
{
|
|
"entropy": 5.664507865905762,
|
|
"epoch": 2.393457519309405,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00047099996990855424,
|
|
"loss": 5.564,
|
|
"mean_token_accuracy": 0.16357118338346482,
|
|
"num_tokens": 5456955.0,
|
|
"step": 2635
|
|
},
|
|
{
|
|
"entropy": 5.67940583229065,
|
|
"epoch": 2.3980009086778735,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00047082616398157456,
|
|
"loss": 5.4963,
|
|
"mean_token_accuracy": 0.1606929361820221,
|
|
"num_tokens": 5466260.0,
|
|
"step": 2640
|
|
},
|
|
{
|
|
"entropy": 5.678316831588745,
|
|
"epoch": 2.4025442980463425,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004706518748730017,
|
|
"loss": 5.5533,
|
|
"mean_token_accuracy": 0.1584568589925766,
|
|
"num_tokens": 5478055.0,
|
|
"step": 2645
|
|
},
|
|
{
|
|
"entropy": 5.533257150650025,
|
|
"epoch": 2.4070876874148115,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004704771030128768,
|
|
"loss": 5.4014,
|
|
"mean_token_accuracy": 0.15996367260813713,
|
|
"num_tokens": 5487532.0,
|
|
"step": 2650
|
|
},
|
|
{
|
|
"entropy": 5.562580871582031,
|
|
"epoch": 2.4116310767832805,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00047030184883243203,
|
|
"loss": 5.5058,
|
|
"mean_token_accuracy": 0.1656596690416336,
|
|
"num_tokens": 5498197.0,
|
|
"step": 2655
|
|
},
|
|
{
|
|
"entropy": 5.656260013580322,
|
|
"epoch": 2.416174466151749,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00047012611276408964,
|
|
"loss": 5.3975,
|
|
"mean_token_accuracy": 0.16340485960245132,
|
|
"num_tokens": 5508320.0,
|
|
"step": 2660
|
|
},
|
|
{
|
|
"entropy": 5.488940572738647,
|
|
"epoch": 2.420717855520218,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004699498952414609,
|
|
"loss": 5.386,
|
|
"mean_token_accuracy": 0.17562676668167115,
|
|
"num_tokens": 5517392.0,
|
|
"step": 2665
|
|
},
|
|
{
|
|
"entropy": 5.5707038879394535,
|
|
"epoch": 2.425261244888687,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00046977319669934506,
|
|
"loss": 5.4478,
|
|
"mean_token_accuracy": 0.16371348202228547,
|
|
"num_tokens": 5527097.0,
|
|
"step": 2670
|
|
},
|
|
{
|
|
"entropy": 5.690631771087647,
|
|
"epoch": 2.429804634257156,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00046959601757372814,
|
|
"loss": 5.4562,
|
|
"mean_token_accuracy": 0.16645233631134032,
|
|
"num_tokens": 5536935.0,
|
|
"step": 2675
|
|
},
|
|
{
|
|
"entropy": 5.5774236679077145,
|
|
"epoch": 2.4343480236256245,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00046941835830178216,
|
|
"loss": 5.5162,
|
|
"mean_token_accuracy": 0.16189493536949157,
|
|
"num_tokens": 5547432.0,
|
|
"step": 2680
|
|
},
|
|
{
|
|
"entropy": 5.597412061691284,
|
|
"epoch": 2.4388914129940935,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00046924021932186357,
|
|
"loss": 5.434,
|
|
"mean_token_accuracy": 0.16296101212501526,
|
|
"num_tokens": 5558335.0,
|
|
"step": 2685
|
|
},
|
|
{
|
|
"entropy": 5.69479923248291,
|
|
"epoch": 2.4434348023625625,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00046906160107351263,
|
|
"loss": 5.5146,
|
|
"mean_token_accuracy": 0.1591379687190056,
|
|
"num_tokens": 5568474.0,
|
|
"step": 2690
|
|
},
|
|
{
|
|
"entropy": 5.502760219573974,
|
|
"epoch": 2.4479781917310315,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.00046888250399745217,
|
|
"loss": 5.5306,
|
|
"mean_token_accuracy": 0.1706564098596573,
|
|
"num_tokens": 5577310.0,
|
|
"step": 2695
|
|
},
|
|
{
|
|
"entropy": 5.678367328643799,
|
|
"epoch": 2.4525215810995,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00046870292853558646,
|
|
"loss": 5.4958,
|
|
"mean_token_accuracy": 0.16218772977590562,
|
|
"num_tokens": 5587791.0,
|
|
"step": 2700
|
|
},
|
|
{
|
|
"entropy": 5.741392707824707,
|
|
"epoch": 2.457064970467969,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00046852287513099997,
|
|
"loss": 5.5677,
|
|
"mean_token_accuracy": 0.1556030698120594,
|
|
"num_tokens": 5598783.0,
|
|
"step": 2705
|
|
},
|
|
{
|
|
"entropy": 5.569098949432373,
|
|
"epoch": 2.461608359836438,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004683423442279566,
|
|
"loss": 5.4301,
|
|
"mean_token_accuracy": 0.1574172407388687,
|
|
"num_tokens": 5609143.0,
|
|
"step": 2710
|
|
},
|
|
{
|
|
"entropy": 5.633760261535644,
|
|
"epoch": 2.466151749204907,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004681613362718985,
|
|
"loss": 5.4613,
|
|
"mean_token_accuracy": 0.1616216480731964,
|
|
"num_tokens": 5619657.0,
|
|
"step": 2715
|
|
},
|
|
{
|
|
"entropy": 5.630750751495361,
|
|
"epoch": 2.470695138573376,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004679798517094447,
|
|
"loss": 5.4737,
|
|
"mean_token_accuracy": 0.16256414353847504,
|
|
"num_tokens": 5630233.0,
|
|
"step": 2720
|
|
},
|
|
{
|
|
"entropy": 5.534254503250122,
|
|
"epoch": 2.4752385279418445,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00046779789098839043,
|
|
"loss": 5.4341,
|
|
"mean_token_accuracy": 0.16833728849887847,
|
|
"num_tokens": 5640878.0,
|
|
"step": 2725
|
|
},
|
|
{
|
|
"entropy": 5.665617895126343,
|
|
"epoch": 2.4797819173103135,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00046761545455770555,
|
|
"loss": 5.6317,
|
|
"mean_token_accuracy": 0.15832689255475998,
|
|
"num_tokens": 5651335.0,
|
|
"step": 2730
|
|
},
|
|
{
|
|
"entropy": 5.643316745758057,
|
|
"epoch": 2.4843253066787825,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004674325428675339,
|
|
"loss": 5.4929,
|
|
"mean_token_accuracy": 0.16712235361337663,
|
|
"num_tokens": 5661981.0,
|
|
"step": 2735
|
|
},
|
|
{
|
|
"entropy": 5.594733762741089,
|
|
"epoch": 2.488868696047251,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004672491563691919,
|
|
"loss": 5.4664,
|
|
"mean_token_accuracy": 0.16800144612789153,
|
|
"num_tokens": 5671551.0,
|
|
"step": 2740
|
|
},
|
|
{
|
|
"entropy": 5.590738105773926,
|
|
"epoch": 2.49341208541572,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00046706529551516753,
|
|
"loss": 5.4224,
|
|
"mean_token_accuracy": 0.16803559213876723,
|
|
"num_tokens": 5681185.0,
|
|
"step": 2745
|
|
},
|
|
{
|
|
"entropy": 5.583927965164184,
|
|
"epoch": 2.497955474784189,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00046688096075911905,
|
|
"loss": 5.4799,
|
|
"mean_token_accuracy": 0.167832550406456,
|
|
"num_tokens": 5690967.0,
|
|
"step": 2750
|
|
},
|
|
{
|
|
"entropy": 5.682482576370239,
|
|
"epoch": 2.502498864152658,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004666961525558743,
|
|
"loss": 5.5578,
|
|
"mean_token_accuracy": 0.15779926180839537,
|
|
"num_tokens": 5702011.0,
|
|
"step": 2755
|
|
},
|
|
{
|
|
"entropy": 5.672723388671875,
|
|
"epoch": 2.507042253521127,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.000466510871361429,
|
|
"loss": 5.4992,
|
|
"mean_token_accuracy": 0.16007170379161834,
|
|
"num_tokens": 5712062.0,
|
|
"step": 2760
|
|
},
|
|
{
|
|
"entropy": 5.571487760543823,
|
|
"epoch": 2.5115856428895955,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00046632511763294615,
|
|
"loss": 5.4567,
|
|
"mean_token_accuracy": 0.1650468647480011,
|
|
"num_tokens": 5722828.0,
|
|
"step": 2765
|
|
},
|
|
{
|
|
"entropy": 5.653512048721313,
|
|
"epoch": 2.5161290322580645,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004661388918287546,
|
|
"loss": 5.5415,
|
|
"mean_token_accuracy": 0.16156239062547684,
|
|
"num_tokens": 5732552.0,
|
|
"step": 2770
|
|
},
|
|
{
|
|
"entropy": 5.692649173736572,
|
|
"epoch": 2.5206724216265335,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004659521944083481,
|
|
"loss": 5.4988,
|
|
"mean_token_accuracy": 0.16152568012475968,
|
|
"num_tokens": 5743283.0,
|
|
"step": 2775
|
|
},
|
|
{
|
|
"entropy": 5.58889479637146,
|
|
"epoch": 2.525215810995002,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004657650258323838,
|
|
"loss": 5.4804,
|
|
"mean_token_accuracy": 0.16362597346305846,
|
|
"num_tokens": 5753803.0,
|
|
"step": 2780
|
|
},
|
|
{
|
|
"entropy": 5.607439422607422,
|
|
"epoch": 2.529759200363471,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00046557738656268166,
|
|
"loss": 5.461,
|
|
"mean_token_accuracy": 0.17017837166786193,
|
|
"num_tokens": 5764050.0,
|
|
"step": 2785
|
|
},
|
|
{
|
|
"entropy": 5.618855047225952,
|
|
"epoch": 2.53430258973194,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.000465389277062223,
|
|
"loss": 5.4213,
|
|
"mean_token_accuracy": 0.17354113161563872,
|
|
"num_tokens": 5774125.0,
|
|
"step": 2790
|
|
},
|
|
{
|
|
"entropy": 5.648334217071533,
|
|
"epoch": 2.538845979100409,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00046520069779514917,
|
|
"loss": 5.5519,
|
|
"mean_token_accuracy": 0.16256483793258666,
|
|
"num_tokens": 5784762.0,
|
|
"step": 2795
|
|
},
|
|
{
|
|
"entropy": 5.690959930419922,
|
|
"epoch": 2.543389368468878,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004650116492267609,
|
|
"loss": 5.4731,
|
|
"mean_token_accuracy": 0.15543195307254792,
|
|
"num_tokens": 5795593.0,
|
|
"step": 2800
|
|
},
|
|
{
|
|
"entropy": 5.632666778564453,
|
|
"epoch": 2.5479327578373465,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004648221318235165,
|
|
"loss": 5.4807,
|
|
"mean_token_accuracy": 0.16186553835868836,
|
|
"num_tokens": 5805757.0,
|
|
"step": 2805
|
|
},
|
|
{
|
|
"entropy": 5.618985414505005,
|
|
"epoch": 2.5524761472058155,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004646321460530316,
|
|
"loss": 5.477,
|
|
"mean_token_accuracy": 0.16880376040935516,
|
|
"num_tokens": 5816197.0,
|
|
"step": 2810
|
|
},
|
|
{
|
|
"entropy": 5.515861463546753,
|
|
"epoch": 2.5570195365742845,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.000464441692384077,
|
|
"loss": 5.484,
|
|
"mean_token_accuracy": 0.16270082890987397,
|
|
"num_tokens": 5826193.0,
|
|
"step": 2815
|
|
},
|
|
{
|
|
"entropy": 5.645616579055786,
|
|
"epoch": 2.561562925942753,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004642507712865784,
|
|
"loss": 5.4453,
|
|
"mean_token_accuracy": 0.16180969178676605,
|
|
"num_tokens": 5835934.0,
|
|
"step": 2820
|
|
},
|
|
{
|
|
"entropy": 5.575414037704467,
|
|
"epoch": 2.566106315311222,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00046405938323161453,
|
|
"loss": 5.3715,
|
|
"mean_token_accuracy": 0.1692644700407982,
|
|
"num_tokens": 5846376.0,
|
|
"step": 2825
|
|
},
|
|
{
|
|
"entropy": 5.579668664932251,
|
|
"epoch": 2.570649704679691,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00046386752869141624,
|
|
"loss": 5.5159,
|
|
"mean_token_accuracy": 0.1617092326283455,
|
|
"num_tokens": 5856741.0,
|
|
"step": 2830
|
|
},
|
|
{
|
|
"entropy": 5.617500591278076,
|
|
"epoch": 2.57519309404816,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004636752081393658,
|
|
"loss": 5.5385,
|
|
"mean_token_accuracy": 0.1621531665325165,
|
|
"num_tokens": 5867690.0,
|
|
"step": 2835
|
|
},
|
|
{
|
|
"entropy": 5.573635005950928,
|
|
"epoch": 2.579736483416629,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00046348242204999487,
|
|
"loss": 5.4427,
|
|
"mean_token_accuracy": 0.16709815710783005,
|
|
"num_tokens": 5878522.0,
|
|
"step": 2840
|
|
},
|
|
{
|
|
"entropy": 5.593231630325318,
|
|
"epoch": 2.5842798727850975,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00046328917089898396,
|
|
"loss": 5.4585,
|
|
"mean_token_accuracy": 0.1684649333357811,
|
|
"num_tokens": 5888702.0,
|
|
"step": 2845
|
|
},
|
|
{
|
|
"entropy": 5.594196224212647,
|
|
"epoch": 2.5888232621535665,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004630954551631612,
|
|
"loss": 5.5187,
|
|
"mean_token_accuracy": 0.16131021380424498,
|
|
"num_tokens": 5900040.0,
|
|
"step": 2850
|
|
},
|
|
{
|
|
"entropy": 5.568029356002808,
|
|
"epoch": 2.5933666515220355,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00046290127532050087,
|
|
"loss": 5.3928,
|
|
"mean_token_accuracy": 0.16215718686580657,
|
|
"num_tokens": 5911572.0,
|
|
"step": 2855
|
|
},
|
|
{
|
|
"entropy": 5.649325561523438,
|
|
"epoch": 2.5979100408905045,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004627066318501223,
|
|
"loss": 5.484,
|
|
"mean_token_accuracy": 0.16762312650680541,
|
|
"num_tokens": 5921106.0,
|
|
"step": 2860
|
|
},
|
|
{
|
|
"entropy": 5.540233564376831,
|
|
"epoch": 2.602453430258973,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00046251152523228906,
|
|
"loss": 5.4415,
|
|
"mean_token_accuracy": 0.16675643771886825,
|
|
"num_tokens": 5930809.0,
|
|
"step": 2865
|
|
},
|
|
{
|
|
"entropy": 5.535998296737671,
|
|
"epoch": 2.606996819627442,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004623159559484074,
|
|
"loss": 5.5051,
|
|
"mean_token_accuracy": 0.1679874151945114,
|
|
"num_tokens": 5941828.0,
|
|
"step": 2870
|
|
},
|
|
{
|
|
"entropy": 5.6888713359832765,
|
|
"epoch": 2.611540208995911,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004621199244810248,
|
|
"loss": 5.5442,
|
|
"mean_token_accuracy": 0.1616669088602066,
|
|
"num_tokens": 5951774.0,
|
|
"step": 2875
|
|
},
|
|
{
|
|
"entropy": 5.622589206695556,
|
|
"epoch": 2.61608359836438,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00046192343131382964,
|
|
"loss": 5.4613,
|
|
"mean_token_accuracy": 0.16773341298103334,
|
|
"num_tokens": 5961872.0,
|
|
"step": 2880
|
|
},
|
|
{
|
|
"entropy": 5.544913911819458,
|
|
"epoch": 2.620626987732849,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00046172647693164926,
|
|
"loss": 5.387,
|
|
"mean_token_accuracy": 0.17031843960285187,
|
|
"num_tokens": 5972635.0,
|
|
"step": 2885
|
|
},
|
|
{
|
|
"entropy": 5.54814453125,
|
|
"epoch": 2.6251703771013175,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004615290618204489,
|
|
"loss": 5.4411,
|
|
"mean_token_accuracy": 0.16277870833873748,
|
|
"num_tokens": 5983042.0,
|
|
"step": 2890
|
|
},
|
|
{
|
|
"entropy": 5.637651252746582,
|
|
"epoch": 2.6297137664697865,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004613311864673309,
|
|
"loss": 5.6537,
|
|
"mean_token_accuracy": 0.14904230907559396,
|
|
"num_tokens": 5993859.0,
|
|
"step": 2895
|
|
},
|
|
{
|
|
"entropy": 5.735480260848999,
|
|
"epoch": 2.6342571558382555,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00046113285136053286,
|
|
"loss": 5.5295,
|
|
"mean_token_accuracy": 0.16324471086263656,
|
|
"num_tokens": 6004210.0,
|
|
"step": 2900
|
|
},
|
|
{
|
|
"entropy": 5.65135760307312,
|
|
"epoch": 2.638800545206724,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.000460934056989427,
|
|
"loss": 5.3804,
|
|
"mean_token_accuracy": 0.16609495133161545,
|
|
"num_tokens": 6014476.0,
|
|
"step": 2905
|
|
},
|
|
{
|
|
"entropy": 5.5331555843353275,
|
|
"epoch": 2.643343934575193,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004607348038445187,
|
|
"loss": 5.4401,
|
|
"mean_token_accuracy": 0.15993242114782333,
|
|
"num_tokens": 6024454.0,
|
|
"step": 2910
|
|
},
|
|
{
|
|
"entropy": 5.581075191497803,
|
|
"epoch": 2.647887323943662,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00046053509241744526,
|
|
"loss": 5.4713,
|
|
"mean_token_accuracy": 0.17017142474651337,
|
|
"num_tokens": 6035041.0,
|
|
"step": 2915
|
|
},
|
|
{
|
|
"entropy": 5.606084251403809,
|
|
"epoch": 2.652430713312131,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00046033492320097483,
|
|
"loss": 5.4586,
|
|
"mean_token_accuracy": 0.17169903963804245,
|
|
"num_tokens": 6045005.0,
|
|
"step": 2920
|
|
},
|
|
{
|
|
"entropy": 5.65831184387207,
|
|
"epoch": 2.6569741026806,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004601342966890049,
|
|
"loss": 5.426,
|
|
"mean_token_accuracy": 0.17063144892454146,
|
|
"num_tokens": 6054973.0,
|
|
"step": 2925
|
|
},
|
|
{
|
|
"entropy": 5.569364929199219,
|
|
"epoch": 2.6615174920490685,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00045993321337656163,
|
|
"loss": 5.4,
|
|
"mean_token_accuracy": 0.16538814455270767,
|
|
"num_tokens": 6065857.0,
|
|
"step": 2930
|
|
},
|
|
{
|
|
"entropy": 5.584576749801636,
|
|
"epoch": 2.6660608814175375,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.000459731673759798,
|
|
"loss": 5.4347,
|
|
"mean_token_accuracy": 0.168292573094368,
|
|
"num_tokens": 6075568.0,
|
|
"step": 2935
|
|
},
|
|
{
|
|
"entropy": 5.6245733261108395,
|
|
"epoch": 2.6706042707860065,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00045952967833599303,
|
|
"loss": 5.5432,
|
|
"mean_token_accuracy": 0.1643181711435318,
|
|
"num_tokens": 6086103.0,
|
|
"step": 2940
|
|
},
|
|
{
|
|
"entropy": 5.609689474105835,
|
|
"epoch": 2.675147660154475,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004593272276035502,
|
|
"loss": 5.4723,
|
|
"mean_token_accuracy": 0.16511984616518022,
|
|
"num_tokens": 6096983.0,
|
|
"step": 2945
|
|
},
|
|
{
|
|
"entropy": 5.5687517642974855,
|
|
"epoch": 2.679691049522944,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004591243220619969,
|
|
"loss": 5.4509,
|
|
"mean_token_accuracy": 0.16505469083786012,
|
|
"num_tokens": 6106518.0,
|
|
"step": 2950
|
|
},
|
|
{
|
|
"entropy": 5.609748601913452,
|
|
"epoch": 2.684234438891413,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.000458920962211982,
|
|
"loss": 5.5302,
|
|
"mean_token_accuracy": 0.16398297548294066,
|
|
"num_tokens": 6118034.0,
|
|
"step": 2955
|
|
},
|
|
{
|
|
"entropy": 5.6170238018035885,
|
|
"epoch": 2.688777828259882,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004587171485552759,
|
|
"loss": 5.4812,
|
|
"mean_token_accuracy": 0.16860826909542084,
|
|
"num_tokens": 6128177.0,
|
|
"step": 2960
|
|
},
|
|
{
|
|
"entropy": 5.583043813705444,
|
|
"epoch": 2.693321217628351,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00045851288159476854,
|
|
"loss": 5.5264,
|
|
"mean_token_accuracy": 0.15912237763404846,
|
|
"num_tokens": 6138401.0,
|
|
"step": 2965
|
|
},
|
|
{
|
|
"entropy": 5.627243518829346,
|
|
"epoch": 2.6978646069968195,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004583081618344684,
|
|
"loss": 5.4292,
|
|
"mean_token_accuracy": 0.16771573275327684,
|
|
"num_tokens": 6148475.0,
|
|
"step": 2970
|
|
},
|
|
{
|
|
"entropy": 5.59838833808899,
|
|
"epoch": 2.7024079963652885,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.000458102989779501,
|
|
"loss": 5.5747,
|
|
"mean_token_accuracy": 0.16113339066505433,
|
|
"num_tokens": 6159457.0,
|
|
"step": 2975
|
|
},
|
|
{
|
|
"entropy": 5.731915092468261,
|
|
"epoch": 2.7069513857337575,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004578973659361081,
|
|
"loss": 5.5392,
|
|
"mean_token_accuracy": 0.15799466669559478,
|
|
"num_tokens": 6169576.0,
|
|
"step": 2980
|
|
},
|
|
{
|
|
"entropy": 5.649990749359131,
|
|
"epoch": 2.711494775102226,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00045769129081164596,
|
|
"loss": 5.4841,
|
|
"mean_token_accuracy": 0.16854571998119355,
|
|
"num_tokens": 6179292.0,
|
|
"step": 2985
|
|
},
|
|
{
|
|
"entropy": 5.518716049194336,
|
|
"epoch": 2.716038164470695,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004574847649145845,
|
|
"loss": 5.4587,
|
|
"mean_token_accuracy": 0.16538277864456177,
|
|
"num_tokens": 6190824.0,
|
|
"step": 2990
|
|
},
|
|
{
|
|
"entropy": 5.635785722732544,
|
|
"epoch": 2.720581553839164,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.000457277788754506,
|
|
"loss": 5.4653,
|
|
"mean_token_accuracy": 0.16698568016290666,
|
|
"num_tokens": 6201830.0,
|
|
"step": 2995
|
|
},
|
|
{
|
|
"entropy": 5.603476905822754,
|
|
"epoch": 2.725124943207633,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00045707036284210344,
|
|
"loss": 5.518,
|
|
"mean_token_accuracy": 0.1614304631948471,
|
|
"num_tokens": 6213063.0,
|
|
"step": 3000
|
|
},
|
|
{
|
|
"epoch": 2.725124943207633,
|
|
"eval_entropy": 5.448676344405773,
|
|
"eval_loss": 5.910400867462158,
|
|
"eval_mean_token_accuracy": 0.15391066744923593,
|
|
"eval_num_tokens": 6213063.0,
|
|
"eval_runtime": 2.5754,
|
|
"eval_samples_per_second": 1333.767,
|
|
"eval_steps_per_second": 166.964,
|
|
"step": 3000
|
|
},
|
|
{
|
|
"entropy": 5.644993019104004,
|
|
"epoch": 2.729668332576102,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004568624876891796,
|
|
"loss": 5.5416,
|
|
"mean_token_accuracy": 0.15871655941009521,
|
|
"num_tokens": 6223732.0,
|
|
"step": 3005
|
|
},
|
|
{
|
|
"entropy": 5.703949499130249,
|
|
"epoch": 2.7342117219445705,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00045665416380864587,
|
|
"loss": 5.5012,
|
|
"mean_token_accuracy": 0.1622459977865219,
|
|
"num_tokens": 6233290.0,
|
|
"step": 3010
|
|
},
|
|
{
|
|
"entropy": 5.568316555023193,
|
|
"epoch": 2.7387551113130395,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004564453917145206,
|
|
"loss": 5.4806,
|
|
"mean_token_accuracy": 0.1665453478693962,
|
|
"num_tokens": 6242927.0,
|
|
"step": 3015
|
|
},
|
|
{
|
|
"entropy": 5.60679292678833,
|
|
"epoch": 2.7432985006815085,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004562361719219283,
|
|
"loss": 5.4423,
|
|
"mean_token_accuracy": 0.16860672533512117,
|
|
"num_tokens": 6253787.0,
|
|
"step": 3020
|
|
},
|
|
{
|
|
"entropy": 5.585407972335815,
|
|
"epoch": 2.747841890049977,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00045602650494709786,
|
|
"loss": 5.4471,
|
|
"mean_token_accuracy": 0.17449164092540742,
|
|
"num_tokens": 6264935.0,
|
|
"step": 3025
|
|
},
|
|
{
|
|
"entropy": 5.6130051612854,
|
|
"epoch": 2.752385279418446,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00045581639130736173,
|
|
"loss": 5.4777,
|
|
"mean_token_accuracy": 0.17116669714450836,
|
|
"num_tokens": 6274920.0,
|
|
"step": 3030
|
|
},
|
|
{
|
|
"entropy": 5.604496335983276,
|
|
"epoch": 2.756928668786915,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004556058315211546,
|
|
"loss": 5.4412,
|
|
"mean_token_accuracy": 0.1728539362549782,
|
|
"num_tokens": 6285059.0,
|
|
"step": 3035
|
|
},
|
|
{
|
|
"entropy": 5.540521335601807,
|
|
"epoch": 2.761472058155384,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00045539482610801156,
|
|
"loss": 5.4384,
|
|
"mean_token_accuracy": 0.17148551642894744,
|
|
"num_tokens": 6295020.0,
|
|
"step": 3040
|
|
},
|
|
{
|
|
"entropy": 5.643183183670044,
|
|
"epoch": 2.766015447523853,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004551833755885677,
|
|
"loss": 5.5499,
|
|
"mean_token_accuracy": 0.16493684947490692,
|
|
"num_tokens": 6306757.0,
|
|
"step": 3045
|
|
},
|
|
{
|
|
"entropy": 5.553267097473144,
|
|
"epoch": 2.7705588368923215,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004549714804845561,
|
|
"loss": 5.3846,
|
|
"mean_token_accuracy": 0.16816687136888503,
|
|
"num_tokens": 6316749.0,
|
|
"step": 3050
|
|
},
|
|
{
|
|
"entropy": 5.537831497192383,
|
|
"epoch": 2.7751022262607905,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004547591413188068,
|
|
"loss": 5.5152,
|
|
"mean_token_accuracy": 0.16282387375831603,
|
|
"num_tokens": 6327931.0,
|
|
"step": 3055
|
|
},
|
|
{
|
|
"entropy": 5.627996253967285,
|
|
"epoch": 2.7796456156292595,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004545463586152456,
|
|
"loss": 5.4771,
|
|
"mean_token_accuracy": 0.17296275347471238,
|
|
"num_tokens": 6338946.0,
|
|
"step": 3060
|
|
},
|
|
{
|
|
"entropy": 5.59036283493042,
|
|
"epoch": 2.784189004997728,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004543331328988927,
|
|
"loss": 5.504,
|
|
"mean_token_accuracy": 0.15989039093255997,
|
|
"num_tokens": 6350178.0,
|
|
"step": 3065
|
|
},
|
|
{
|
|
"entropy": 5.541985940933228,
|
|
"epoch": 2.788732394366197,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004541194646958614,
|
|
"loss": 5.4087,
|
|
"mean_token_accuracy": 0.17232533246278764,
|
|
"num_tokens": 6358963.0,
|
|
"step": 3070
|
|
},
|
|
{
|
|
"entropy": 5.604146575927734,
|
|
"epoch": 2.793275783734666,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00045390535453335666,
|
|
"loss": 5.4777,
|
|
"mean_token_accuracy": 0.16232944577932357,
|
|
"num_tokens": 6369399.0,
|
|
"step": 3075
|
|
},
|
|
{
|
|
"entropy": 5.526879072189331,
|
|
"epoch": 2.797819173103135,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00045369080293967414,
|
|
"loss": 5.3649,
|
|
"mean_token_accuracy": 0.1715538963675499,
|
|
"num_tokens": 6379017.0,
|
|
"step": 3080
|
|
},
|
|
{
|
|
"entropy": 5.5233070850372314,
|
|
"epoch": 2.802362562471604,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.00045347581044419846,
|
|
"loss": 5.357,
|
|
"mean_token_accuracy": 0.16787079125642776,
|
|
"num_tokens": 6388124.0,
|
|
"step": 3085
|
|
},
|
|
{
|
|
"entropy": 5.554026651382446,
|
|
"epoch": 2.806905951840073,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00045326037757740216,
|
|
"loss": 5.3993,
|
|
"mean_token_accuracy": 0.1696319431066513,
|
|
"num_tokens": 6398236.0,
|
|
"step": 3090
|
|
},
|
|
{
|
|
"entropy": 5.494157600402832,
|
|
"epoch": 2.8114493412085415,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004530445048708447,
|
|
"loss": 5.3576,
|
|
"mean_token_accuracy": 0.16702686846256257,
|
|
"num_tokens": 6409406.0,
|
|
"step": 3095
|
|
},
|
|
{
|
|
"entropy": 5.632008028030396,
|
|
"epoch": 2.8159927305770105,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00045282819285717024,
|
|
"loss": 5.5157,
|
|
"mean_token_accuracy": 0.1591336250305176,
|
|
"num_tokens": 6420165.0,
|
|
"step": 3100
|
|
},
|
|
{
|
|
"entropy": 5.604083299636841,
|
|
"epoch": 2.8205361199454795,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.00045261144207010736,
|
|
"loss": 5.4367,
|
|
"mean_token_accuracy": 0.16982193142175675,
|
|
"num_tokens": 6430927.0,
|
|
"step": 3105
|
|
},
|
|
{
|
|
"entropy": 5.601340293884277,
|
|
"epoch": 2.825079509313948,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00045239425304446684,
|
|
"loss": 5.5333,
|
|
"mean_token_accuracy": 0.16132794320583344,
|
|
"num_tokens": 6441787.0,
|
|
"step": 3110
|
|
},
|
|
{
|
|
"entropy": 5.627665567398071,
|
|
"epoch": 2.829622898682417,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004521766263161413,
|
|
"loss": 5.5017,
|
|
"mean_token_accuracy": 0.16319774687290192,
|
|
"num_tokens": 6451603.0,
|
|
"step": 3115
|
|
},
|
|
{
|
|
"entropy": 5.6300276756286625,
|
|
"epoch": 2.834166288050886,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.000451958562422103,
|
|
"loss": 5.5686,
|
|
"mean_token_accuracy": 0.1559320718050003,
|
|
"num_tokens": 6463386.0,
|
|
"step": 3120
|
|
},
|
|
{
|
|
"entropy": 5.592286252975464,
|
|
"epoch": 2.838709677419355,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00045174006190040267,
|
|
"loss": 5.4029,
|
|
"mean_token_accuracy": 0.16535354405641556,
|
|
"num_tokens": 6474022.0,
|
|
"step": 3125
|
|
},
|
|
{
|
|
"entropy": 5.575218391418457,
|
|
"epoch": 2.843253066787824,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.000451521125290169,
|
|
"loss": 5.4947,
|
|
"mean_token_accuracy": 0.1622852623462677,
|
|
"num_tokens": 6485313.0,
|
|
"step": 3130
|
|
},
|
|
{
|
|
"entropy": 5.560710763931274,
|
|
"epoch": 2.8477964561562925,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.000451301753131606,
|
|
"loss": 5.4202,
|
|
"mean_token_accuracy": 0.16641468703746795,
|
|
"num_tokens": 6495951.0,
|
|
"step": 3135
|
|
},
|
|
{
|
|
"entropy": 5.588367176055908,
|
|
"epoch": 2.8523398455247615,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.00045108194596599286,
|
|
"loss": 5.3645,
|
|
"mean_token_accuracy": 0.1651519939303398,
|
|
"num_tokens": 6505171.0,
|
|
"step": 3140
|
|
},
|
|
{
|
|
"entropy": 5.5673552513122555,
|
|
"epoch": 2.8568832348932305,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004508617043356818,
|
|
"loss": 5.4398,
|
|
"mean_token_accuracy": 0.16626475155353546,
|
|
"num_tokens": 6515829.0,
|
|
"step": 3145
|
|
},
|
|
{
|
|
"entropy": 5.5346360206604,
|
|
"epoch": 2.861426624261699,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004506410287840972,
|
|
"loss": 5.3874,
|
|
"mean_token_accuracy": 0.1770617887377739,
|
|
"num_tokens": 6526008.0,
|
|
"step": 3150
|
|
},
|
|
{
|
|
"entropy": 5.638406753540039,
|
|
"epoch": 2.865970013630168,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.000450419919855734,
|
|
"loss": 5.4869,
|
|
"mean_token_accuracy": 0.16392494440078736,
|
|
"num_tokens": 6536221.0,
|
|
"step": 3155
|
|
},
|
|
{
|
|
"entropy": 5.647489738464356,
|
|
"epoch": 2.870513402998637,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004501983780961566,
|
|
"loss": 5.542,
|
|
"mean_token_accuracy": 0.16214743703603746,
|
|
"num_tokens": 6546278.0,
|
|
"step": 3160
|
|
},
|
|
{
|
|
"entropy": 5.591143178939819,
|
|
"epoch": 2.875056792367106,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004499764040519972,
|
|
"loss": 5.5046,
|
|
"mean_token_accuracy": 0.16632575690746307,
|
|
"num_tokens": 6556272.0,
|
|
"step": 3165
|
|
},
|
|
{
|
|
"entropy": 5.652001285552979,
|
|
"epoch": 2.879600181735575,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00044975399827095467,
|
|
"loss": 5.4946,
|
|
"mean_token_accuracy": 0.16214894950389863,
|
|
"num_tokens": 6566852.0,
|
|
"step": 3170
|
|
},
|
|
{
|
|
"entropy": 5.5523045539855955,
|
|
"epoch": 2.8841435711040435,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.00044953116130179313,
|
|
"loss": 5.433,
|
|
"mean_token_accuracy": 0.16800027340650558,
|
|
"num_tokens": 6576425.0,
|
|
"step": 3175
|
|
},
|
|
{
|
|
"entropy": 5.636137056350708,
|
|
"epoch": 2.8886869604725125,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004493078936943408,
|
|
"loss": 5.5175,
|
|
"mean_token_accuracy": 0.16905550956726073,
|
|
"num_tokens": 6586495.0,
|
|
"step": 3180
|
|
},
|
|
{
|
|
"entropy": 5.569518804550171,
|
|
"epoch": 2.8932303498409815,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004490841959994882,
|
|
"loss": 5.4412,
|
|
"mean_token_accuracy": 0.16209438145160676,
|
|
"num_tokens": 6596298.0,
|
|
"step": 3185
|
|
},
|
|
{
|
|
"entropy": 5.6018452644348145,
|
|
"epoch": 2.89777373920945,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00044886006876918716,
|
|
"loss": 5.4991,
|
|
"mean_token_accuracy": 0.16091723889112472,
|
|
"num_tokens": 6606799.0,
|
|
"step": 3190
|
|
},
|
|
{
|
|
"entropy": 5.680713891983032,
|
|
"epoch": 2.902317128577919,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004486355125564493,
|
|
"loss": 5.5959,
|
|
"mean_token_accuracy": 0.15950109660625458,
|
|
"num_tokens": 6617558.0,
|
|
"step": 3195
|
|
},
|
|
{
|
|
"entropy": 5.62776746749878,
|
|
"epoch": 2.906860517946388,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004484105279153449,
|
|
"loss": 5.4624,
|
|
"mean_token_accuracy": 0.16874861866235732,
|
|
"num_tokens": 6627966.0,
|
|
"step": 3200
|
|
},
|
|
{
|
|
"entropy": 5.582860469818115,
|
|
"epoch": 2.911403907314857,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.000448185115401001,
|
|
"loss": 5.4898,
|
|
"mean_token_accuracy": 0.16677092164754867,
|
|
"num_tokens": 6638152.0,
|
|
"step": 3205
|
|
},
|
|
{
|
|
"entropy": 5.525146722793579,
|
|
"epoch": 2.915947296683326,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004479592755696008,
|
|
"loss": 5.3959,
|
|
"mean_token_accuracy": 0.16967687904834747,
|
|
"num_tokens": 6647937.0,
|
|
"step": 3210
|
|
},
|
|
{
|
|
"entropy": 5.598087501525879,
|
|
"epoch": 2.9204906860517945,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00044773300897838137,
|
|
"loss": 5.4277,
|
|
"mean_token_accuracy": 0.16422719657421112,
|
|
"num_tokens": 6657749.0,
|
|
"step": 3215
|
|
},
|
|
{
|
|
"entropy": 5.49541392326355,
|
|
"epoch": 2.9250340754202635,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004475063161856332,
|
|
"loss": 5.3937,
|
|
"mean_token_accuracy": 0.16891833245754242,
|
|
"num_tokens": 6667376.0,
|
|
"step": 3220
|
|
},
|
|
{
|
|
"entropy": 5.581175851821899,
|
|
"epoch": 2.9295774647887325,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004472791977506983,
|
|
"loss": 5.4832,
|
|
"mean_token_accuracy": 0.166125650703907,
|
|
"num_tokens": 6677342.0,
|
|
"step": 3225
|
|
},
|
|
{
|
|
"entropy": 5.555107831954956,
|
|
"epoch": 2.934120854157201,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00044705165423396855,
|
|
"loss": 5.3931,
|
|
"mean_token_accuracy": 0.17118330150842667,
|
|
"num_tokens": 6687148.0,
|
|
"step": 3230
|
|
},
|
|
{
|
|
"entropy": 5.563992691040039,
|
|
"epoch": 2.93866424352567,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00044682368619688523,
|
|
"loss": 5.5165,
|
|
"mean_token_accuracy": 0.16058380007743836,
|
|
"num_tokens": 6697350.0,
|
|
"step": 3235
|
|
},
|
|
{
|
|
"entropy": 5.649809169769287,
|
|
"epoch": 2.943207632894139,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004465952942019367,
|
|
"loss": 5.5077,
|
|
"mean_token_accuracy": 0.16612699180841445,
|
|
"num_tokens": 6708751.0,
|
|
"step": 3240
|
|
},
|
|
{
|
|
"entropy": 5.607970809936523,
|
|
"epoch": 2.947751022262608,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.00044636647881265745,
|
|
"loss": 5.4182,
|
|
"mean_token_accuracy": 0.15913091152906417,
|
|
"num_tokens": 6718927.0,
|
|
"step": 3245
|
|
},
|
|
{
|
|
"entropy": 5.497457551956177,
|
|
"epoch": 2.952294411631077,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004461372405936269,
|
|
"loss": 5.4577,
|
|
"mean_token_accuracy": 0.16851513385772704,
|
|
"num_tokens": 6729191.0,
|
|
"step": 3250
|
|
},
|
|
{
|
|
"entropy": 5.6077875137329105,
|
|
"epoch": 2.9568378009995455,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0004459075801104673,
|
|
"loss": 5.5099,
|
|
"mean_token_accuracy": 0.15951488465070723,
|
|
"num_tokens": 6739838.0,
|
|
"step": 3255
|
|
},
|
|
{
|
|
"entropy": 5.574047470092774,
|
|
"epoch": 2.9613811903680145,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.00044567749792984325,
|
|
"loss": 5.4711,
|
|
"mean_token_accuracy": 0.17172538340091706,
|
|
"num_tokens": 6750299.0,
|
|
"step": 3260
|
|
},
|
|
{
|
|
"entropy": 5.563213062286377,
|
|
"epoch": 2.9659245797364835,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.00044544699461945966,
|
|
"loss": 5.443,
|
|
"mean_token_accuracy": 0.1675541251897812,
|
|
"num_tokens": 6759647.0,
|
|
"step": 3265
|
|
},
|
|
{
|
|
"entropy": 5.570685911178589,
|
|
"epoch": 2.970467969104952,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.00044521607074806037,
|
|
"loss": 5.5004,
|
|
"mean_token_accuracy": 0.16713315695524217,
|
|
"num_tokens": 6770833.0,
|
|
"step": 3270
|
|
},
|
|
{
|
|
"entropy": 5.695400524139404,
|
|
"epoch": 2.975011358473421,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004449847268854272,
|
|
"loss": 5.5627,
|
|
"mean_token_accuracy": 0.16010628491640091,
|
|
"num_tokens": 6781890.0,
|
|
"step": 3275
|
|
},
|
|
{
|
|
"entropy": 5.669206047058106,
|
|
"epoch": 2.97955474784189,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004447529636023782,
|
|
"loss": 5.4659,
|
|
"mean_token_accuracy": 0.16730637699365616,
|
|
"num_tokens": 6791592.0,
|
|
"step": 3280
|
|
},
|
|
{
|
|
"entropy": 5.667348718643188,
|
|
"epoch": 2.984098137210359,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00044452078147076614,
|
|
"loss": 5.5325,
|
|
"mean_token_accuracy": 0.15924001932144166,
|
|
"num_tokens": 6801937.0,
|
|
"step": 3285
|
|
},
|
|
{
|
|
"entropy": 5.487317609786987,
|
|
"epoch": 2.988641526578828,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004442881810634774,
|
|
"loss": 5.3937,
|
|
"mean_token_accuracy": 0.1764123797416687,
|
|
"num_tokens": 6812522.0,
|
|
"step": 3290
|
|
},
|
|
{
|
|
"entropy": 5.548979187011719,
|
|
"epoch": 2.9931849159472965,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004440551629544303,
|
|
"loss": 5.5043,
|
|
"mean_token_accuracy": 0.16152538806200029,
|
|
"num_tokens": 6823734.0,
|
|
"step": 3295
|
|
},
|
|
{
|
|
"entropy": 5.5735039710998535,
|
|
"epoch": 2.9977283053157655,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.00044382172771857383,
|
|
"loss": 5.3848,
|
|
"mean_token_accuracy": 0.1717434972524643,
|
|
"num_tokens": 6833846.0,
|
|
"step": 3300
|
|
},
|
|
{
|
|
"entropy": 5.666687594519721,
|
|
"epoch": 3.0018173557473875,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004435878759318864,
|
|
"loss": 5.3775,
|
|
"mean_token_accuracy": 0.16846522192160288,
|
|
"num_tokens": 6842717.0,
|
|
"step": 3305
|
|
},
|
|
{
|
|
"entropy": 5.62762041091919,
|
|
"epoch": 3.0063607451158565,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004433536081713738,
|
|
"loss": 5.2441,
|
|
"mean_token_accuracy": 0.1667865052819252,
|
|
"num_tokens": 6853289.0,
|
|
"step": 3310
|
|
},
|
|
{
|
|
"entropy": 5.511578512191773,
|
|
"epoch": 3.0109041344843255,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004431189250150686,
|
|
"loss": 5.1791,
|
|
"mean_token_accuracy": 0.1784422516822815,
|
|
"num_tokens": 6863174.0,
|
|
"step": 3315
|
|
},
|
|
{
|
|
"entropy": 5.568886995315552,
|
|
"epoch": 3.015447523852794,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00044288382704202816,
|
|
"loss": 5.1906,
|
|
"mean_token_accuracy": 0.17203080356121064,
|
|
"num_tokens": 6872724.0,
|
|
"step": 3320
|
|
},
|
|
{
|
|
"entropy": 5.53032956123352,
|
|
"epoch": 3.019990913221263,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.00044264831483233335,
|
|
"loss": 5.184,
|
|
"mean_token_accuracy": 0.1764652743935585,
|
|
"num_tokens": 6884133.0,
|
|
"step": 3325
|
|
},
|
|
{
|
|
"entropy": 5.527542209625244,
|
|
"epoch": 3.024534302589732,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00044241238896708716,
|
|
"loss": 5.2234,
|
|
"mean_token_accuracy": 0.17391203492879867,
|
|
"num_tokens": 6894474.0,
|
|
"step": 3330
|
|
},
|
|
{
|
|
"entropy": 5.522516298294067,
|
|
"epoch": 3.029077691958201,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004421760500284131,
|
|
"loss": 5.2047,
|
|
"mean_token_accuracy": 0.18113942593336105,
|
|
"num_tokens": 6903715.0,
|
|
"step": 3335
|
|
},
|
|
{
|
|
"entropy": 5.5164079666137695,
|
|
"epoch": 3.0336210813266695,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004419392985994541,
|
|
"loss": 5.1634,
|
|
"mean_token_accuracy": 0.180198934674263,
|
|
"num_tokens": 6913867.0,
|
|
"step": 3340
|
|
},
|
|
{
|
|
"entropy": 5.523637962341309,
|
|
"epoch": 3.0381644706951385,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.00044170213526437076,
|
|
"loss": 5.1384,
|
|
"mean_token_accuracy": 0.18331204056739808,
|
|
"num_tokens": 6923455.0,
|
|
"step": 3345
|
|
},
|
|
{
|
|
"entropy": 5.545493698120117,
|
|
"epoch": 3.0427078600636075,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00044146456060833994,
|
|
"loss": 5.2966,
|
|
"mean_token_accuracy": 0.1699403151869774,
|
|
"num_tokens": 6933761.0,
|
|
"step": 3350
|
|
},
|
|
{
|
|
"entropy": 5.553033971786499,
|
|
"epoch": 3.0472512494320765,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.00044122657521755373,
|
|
"loss": 5.2144,
|
|
"mean_token_accuracy": 0.16862233728170395,
|
|
"num_tokens": 6943859.0,
|
|
"step": 3355
|
|
},
|
|
{
|
|
"entropy": 5.4816125392913815,
|
|
"epoch": 3.051794638800545,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.00044098817967921716,
|
|
"loss": 5.1616,
|
|
"mean_token_accuracy": 0.1797292411327362,
|
|
"num_tokens": 6953835.0,
|
|
"step": 3360
|
|
},
|
|
{
|
|
"entropy": 5.619278812408448,
|
|
"epoch": 3.056338028169014,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.00044074937458154763,
|
|
"loss": 5.2797,
|
|
"mean_token_accuracy": 0.16758880913257598,
|
|
"num_tokens": 6964632.0,
|
|
"step": 3365
|
|
},
|
|
{
|
|
"entropy": 5.556300973892212,
|
|
"epoch": 3.060881417537483,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00044051016051377303,
|
|
"loss": 5.1581,
|
|
"mean_token_accuracy": 0.17627760767936707,
|
|
"num_tokens": 6974973.0,
|
|
"step": 3370
|
|
},
|
|
{
|
|
"entropy": 5.438958835601807,
|
|
"epoch": 3.065424806905952,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004402705380661302,
|
|
"loss": 5.1376,
|
|
"mean_token_accuracy": 0.17759540379047395,
|
|
"num_tokens": 6985154.0,
|
|
"step": 3375
|
|
},
|
|
{
|
|
"entropy": 5.522189474105835,
|
|
"epoch": 3.0699681962744205,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.00044003050782986377,
|
|
"loss": 5.1532,
|
|
"mean_token_accuracy": 0.17532388418912886,
|
|
"num_tokens": 6995962.0,
|
|
"step": 3380
|
|
},
|
|
{
|
|
"entropy": 5.499462747573853,
|
|
"epoch": 3.0745115856428895,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004397900703972245,
|
|
"loss": 5.2394,
|
|
"mean_token_accuracy": 0.16967660784721375,
|
|
"num_tokens": 7005537.0,
|
|
"step": 3385
|
|
},
|
|
{
|
|
"entropy": 5.497580289840698,
|
|
"epoch": 3.0790549750113585,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004395492263614677,
|
|
"loss": 5.0864,
|
|
"mean_token_accuracy": 0.1828851044178009,
|
|
"num_tokens": 7015246.0,
|
|
"step": 3390
|
|
},
|
|
{
|
|
"entropy": 5.4456311702728275,
|
|
"epoch": 3.0835983643798275,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00043930797631685234,
|
|
"loss": 5.1953,
|
|
"mean_token_accuracy": 0.1731215998530388,
|
|
"num_tokens": 7026059.0,
|
|
"step": 3395
|
|
},
|
|
{
|
|
"entropy": 5.462936687469482,
|
|
"epoch": 3.088141753748296,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00043906632085863876,
|
|
"loss": 5.2012,
|
|
"mean_token_accuracy": 0.17956603765487672,
|
|
"num_tokens": 7037044.0,
|
|
"step": 3400
|
|
},
|
|
{
|
|
"entropy": 5.498285961151123,
|
|
"epoch": 3.092685143116765,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00043882426058308775,
|
|
"loss": 5.0902,
|
|
"mean_token_accuracy": 0.18352673202753067,
|
|
"num_tokens": 7047165.0,
|
|
"step": 3405
|
|
},
|
|
{
|
|
"entropy": 5.5146543979644775,
|
|
"epoch": 3.097228532485234,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00043858179608745915,
|
|
"loss": 5.1853,
|
|
"mean_token_accuracy": 0.1854904741048813,
|
|
"num_tokens": 7057711.0,
|
|
"step": 3410
|
|
},
|
|
{
|
|
"entropy": 5.530605840682983,
|
|
"epoch": 3.101771921853703,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.0004383389279700098,
|
|
"loss": 5.2677,
|
|
"mean_token_accuracy": 0.17587135583162308,
|
|
"num_tokens": 7067893.0,
|
|
"step": 3415
|
|
},
|
|
{
|
|
"entropy": 5.429166698455811,
|
|
"epoch": 3.1063153112221715,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.00043809565682999274,
|
|
"loss": 5.1422,
|
|
"mean_token_accuracy": 0.18324554562568665,
|
|
"num_tokens": 7077296.0,
|
|
"step": 3420
|
|
},
|
|
{
|
|
"entropy": 5.477470541000367,
|
|
"epoch": 3.1108587005906405,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00043785198326765535,
|
|
"loss": 5.1672,
|
|
"mean_token_accuracy": 0.1850759953260422,
|
|
"num_tokens": 7086908.0,
|
|
"step": 3425
|
|
},
|
|
{
|
|
"entropy": 5.460258865356446,
|
|
"epoch": 3.1154020899591095,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00043760790788423785,
|
|
"loss": 5.1239,
|
|
"mean_token_accuracy": 0.186641426384449,
|
|
"num_tokens": 7098055.0,
|
|
"step": 3430
|
|
},
|
|
{
|
|
"entropy": 5.546933031082153,
|
|
"epoch": 3.1199454793275785,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.00043736343128197207,
|
|
"loss": 5.2634,
|
|
"mean_token_accuracy": 0.1701875150203705,
|
|
"num_tokens": 7108704.0,
|
|
"step": 3435
|
|
},
|
|
{
|
|
"entropy": 5.563092279434204,
|
|
"epoch": 3.124488868696047,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004371185540640796,
|
|
"loss": 5.2461,
|
|
"mean_token_accuracy": 0.1713597983121872,
|
|
"num_tokens": 7118768.0,
|
|
"step": 3440
|
|
},
|
|
{
|
|
"entropy": 5.41772084236145,
|
|
"epoch": 3.129032258064516,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00043687327683477077,
|
|
"loss": 5.2247,
|
|
"mean_token_accuracy": 0.17361920028924943,
|
|
"num_tokens": 7129022.0,
|
|
"step": 3445
|
|
},
|
|
{
|
|
"entropy": 5.446766710281372,
|
|
"epoch": 3.133575647432985,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004366276001992427,
|
|
"loss": 5.1722,
|
|
"mean_token_accuracy": 0.17573697566986085,
|
|
"num_tokens": 7139321.0,
|
|
"step": 3450
|
|
},
|
|
{
|
|
"entropy": 5.503610992431641,
|
|
"epoch": 3.138119036801454,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000436381524763678,
|
|
"loss": 5.1923,
|
|
"mean_token_accuracy": 0.17613299787044526,
|
|
"num_tokens": 7149869.0,
|
|
"step": 3455
|
|
},
|
|
{
|
|
"entropy": 5.5118592262268065,
|
|
"epoch": 3.142662426169923,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004361350511352435,
|
|
"loss": 5.217,
|
|
"mean_token_accuracy": 0.17797695994377136,
|
|
"num_tokens": 7160253.0,
|
|
"step": 3460
|
|
},
|
|
{
|
|
"entropy": 5.542374897003174,
|
|
"epoch": 3.1472058155383915,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004358881799220882,
|
|
"loss": 5.1676,
|
|
"mean_token_accuracy": 0.1796555444598198,
|
|
"num_tokens": 7170098.0,
|
|
"step": 3465
|
|
},
|
|
{
|
|
"entropy": 5.479652643203735,
|
|
"epoch": 3.1517492049068605,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00043564091173334236,
|
|
"loss": 5.1512,
|
|
"mean_token_accuracy": 0.18894060105085372,
|
|
"num_tokens": 7179660.0,
|
|
"step": 3470
|
|
},
|
|
{
|
|
"entropy": 5.440080165863037,
|
|
"epoch": 3.1562925942753295,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00043539324717911573,
|
|
"loss": 5.1737,
|
|
"mean_token_accuracy": 0.1778093844652176,
|
|
"num_tokens": 7189334.0,
|
|
"step": 3475
|
|
},
|
|
{
|
|
"entropy": 5.53488507270813,
|
|
"epoch": 3.1608359836437985,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00043514518687049587,
|
|
"loss": 5.1777,
|
|
"mean_token_accuracy": 0.181918141245842,
|
|
"num_tokens": 7199459.0,
|
|
"step": 3480
|
|
},
|
|
{
|
|
"entropy": 5.502063035964966,
|
|
"epoch": 3.165379373012267,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.000434896731419547,
|
|
"loss": 5.1835,
|
|
"mean_token_accuracy": 0.17694031149148942,
|
|
"num_tokens": 7209393.0,
|
|
"step": 3485
|
|
},
|
|
{
|
|
"entropy": 5.419578981399536,
|
|
"epoch": 3.169922762380736,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004346478814393082,
|
|
"loss": 5.2023,
|
|
"mean_token_accuracy": 0.16987435817718505,
|
|
"num_tokens": 7219361.0,
|
|
"step": 3490
|
|
},
|
|
{
|
|
"entropy": 5.5086626529693605,
|
|
"epoch": 3.174466151749205,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004343986375437921,
|
|
"loss": 5.1322,
|
|
"mean_token_accuracy": 0.17671380192041397,
|
|
"num_tokens": 7230096.0,
|
|
"step": 3495
|
|
},
|
|
{
|
|
"entropy": 5.4384668350219725,
|
|
"epoch": 3.179009541117674,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00043414900034798314,
|
|
"loss": 5.179,
|
|
"mean_token_accuracy": 0.18149669617414474,
|
|
"num_tokens": 7240387.0,
|
|
"step": 3500
|
|
},
|
|
{
|
|
"entropy": 5.451570224761963,
|
|
"epoch": 3.1835529304861425,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004338989704678364,
|
|
"loss": 5.2078,
|
|
"mean_token_accuracy": 0.1797627776861191,
|
|
"num_tokens": 7250438.0,
|
|
"step": 3505
|
|
},
|
|
{
|
|
"entropy": 5.45203046798706,
|
|
"epoch": 3.1880963198546115,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00043364854852027566,
|
|
"loss": 5.2339,
|
|
"mean_token_accuracy": 0.17833595871925353,
|
|
"num_tokens": 7261451.0,
|
|
"step": 3510
|
|
},
|
|
{
|
|
"entropy": 5.46013913154602,
|
|
"epoch": 3.1926397092230805,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004333977351231924,
|
|
"loss": 5.2665,
|
|
"mean_token_accuracy": 0.17236635684967042,
|
|
"num_tokens": 7271809.0,
|
|
"step": 3515
|
|
},
|
|
{
|
|
"entropy": 5.549579286575318,
|
|
"epoch": 3.1971830985915495,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00043314653089544336,
|
|
"loss": 5.198,
|
|
"mean_token_accuracy": 0.1771390050649643,
|
|
"num_tokens": 7282754.0,
|
|
"step": 3520
|
|
},
|
|
{
|
|
"entropy": 5.4571808815002445,
|
|
"epoch": 3.201726487960018,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004328949364568504,
|
|
"loss": 5.1881,
|
|
"mean_token_accuracy": 0.18121815472841263,
|
|
"num_tokens": 7292978.0,
|
|
"step": 3525
|
|
},
|
|
{
|
|
"entropy": 5.41859884262085,
|
|
"epoch": 3.206269877328487,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004326429524281975,
|
|
"loss": 5.2289,
|
|
"mean_token_accuracy": 0.17934320718050004,
|
|
"num_tokens": 7303429.0,
|
|
"step": 3530
|
|
},
|
|
{
|
|
"entropy": 5.586369848251342,
|
|
"epoch": 3.210813266696956,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004323905794312303,
|
|
"loss": 5.2877,
|
|
"mean_token_accuracy": 0.17108067125082016,
|
|
"num_tokens": 7313540.0,
|
|
"step": 3535
|
|
},
|
|
{
|
|
"entropy": 5.579029273986817,
|
|
"epoch": 3.215356656065425,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00043213781808865414,
|
|
"loss": 5.2977,
|
|
"mean_token_accuracy": 0.17102930843830108,
|
|
"num_tokens": 7324510.0,
|
|
"step": 3540
|
|
},
|
|
{
|
|
"entropy": 5.509274959564209,
|
|
"epoch": 3.2199000454338935,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004318846690241324,
|
|
"loss": 5.2734,
|
|
"mean_token_accuracy": 0.1723960354924202,
|
|
"num_tokens": 7335189.0,
|
|
"step": 3545
|
|
},
|
|
{
|
|
"entropy": 5.5241340637207035,
|
|
"epoch": 3.2244434348023625,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00043163113286228533,
|
|
"loss": 5.2023,
|
|
"mean_token_accuracy": 0.17286860793828965,
|
|
"num_tokens": 7345643.0,
|
|
"step": 3550
|
|
},
|
|
{
|
|
"entropy": 5.4811015129089355,
|
|
"epoch": 3.2289868241708315,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004313772102286882,
|
|
"loss": 5.1807,
|
|
"mean_token_accuracy": 0.1810322269797325,
|
|
"num_tokens": 7356000.0,
|
|
"step": 3555
|
|
},
|
|
{
|
|
"entropy": 5.420389842987061,
|
|
"epoch": 3.2335302135393005,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004311229017498698,
|
|
"loss": 5.2526,
|
|
"mean_token_accuracy": 0.17331068217754364,
|
|
"num_tokens": 7366604.0,
|
|
"step": 3560
|
|
},
|
|
{
|
|
"entropy": 5.504468011856079,
|
|
"epoch": 3.238073602907769,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.000430868208053311,
|
|
"loss": 5.2275,
|
|
"mean_token_accuracy": 0.17249813675880432,
|
|
"num_tokens": 7375728.0,
|
|
"step": 3565
|
|
},
|
|
{
|
|
"entropy": 5.47330756187439,
|
|
"epoch": 3.242616992276238,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00043061312976744326,
|
|
"loss": 5.2105,
|
|
"mean_token_accuracy": 0.18015266954898834,
|
|
"num_tokens": 7387355.0,
|
|
"step": 3570
|
|
},
|
|
{
|
|
"entropy": 5.499780797958374,
|
|
"epoch": 3.247160381644707,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004303576675216469,
|
|
"loss": 5.2114,
|
|
"mean_token_accuracy": 0.17820670455694199,
|
|
"num_tokens": 7397586.0,
|
|
"step": 3575
|
|
},
|
|
{
|
|
"entropy": 5.541110897064209,
|
|
"epoch": 3.251703771013176,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.00043010182194624957,
|
|
"loss": 5.2223,
|
|
"mean_token_accuracy": 0.17682168930768966,
|
|
"num_tokens": 7407075.0,
|
|
"step": 3580
|
|
},
|
|
{
|
|
"entropy": 5.409094905853271,
|
|
"epoch": 3.2562471603816445,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004298455936725248,
|
|
"loss": 5.0805,
|
|
"mean_token_accuracy": 0.189213427901268,
|
|
"num_tokens": 7416555.0,
|
|
"step": 3585
|
|
},
|
|
{
|
|
"entropy": 5.383451890945435,
|
|
"epoch": 3.2607905497501135,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004295889833326903,
|
|
"loss": 5.1033,
|
|
"mean_token_accuracy": 0.18772467225790024,
|
|
"num_tokens": 7426646.0,
|
|
"step": 3590
|
|
},
|
|
{
|
|
"entropy": 5.51010684967041,
|
|
"epoch": 3.2653339391185825,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00042933199155990675,
|
|
"loss": 5.2811,
|
|
"mean_token_accuracy": 0.17072547525167464,
|
|
"num_tokens": 7436901.0,
|
|
"step": 3595
|
|
},
|
|
{
|
|
"entropy": 5.433648586273193,
|
|
"epoch": 3.2698773284870515,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004290746189882757,
|
|
"loss": 5.2365,
|
|
"mean_token_accuracy": 0.17186834812164306,
|
|
"num_tokens": 7447356.0,
|
|
"step": 3600
|
|
},
|
|
{
|
|
"entropy": 5.47099232673645,
|
|
"epoch": 3.27442071785552,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00042881686625283844,
|
|
"loss": 5.2475,
|
|
"mean_token_accuracy": 0.1770731031894684,
|
|
"num_tokens": 7457578.0,
|
|
"step": 3605
|
|
},
|
|
{
|
|
"entropy": 5.43278317451477,
|
|
"epoch": 3.278964107223989,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004285587339895742,
|
|
"loss": 5.0979,
|
|
"mean_token_accuracy": 0.18953035175800323,
|
|
"num_tokens": 7466861.0,
|
|
"step": 3610
|
|
},
|
|
{
|
|
"entropy": 5.47501392364502,
|
|
"epoch": 3.283507496592458,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00042830022283539863,
|
|
"loss": 5.254,
|
|
"mean_token_accuracy": 0.18048491925001145,
|
|
"num_tokens": 7477989.0,
|
|
"step": 3615
|
|
},
|
|
{
|
|
"entropy": 5.478686809539795,
|
|
"epoch": 3.288050885960927,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004280413334281623,
|
|
"loss": 5.1428,
|
|
"mean_token_accuracy": 0.18880029618740082,
|
|
"num_tokens": 7488271.0,
|
|
"step": 3620
|
|
},
|
|
{
|
|
"entropy": 5.439047718048096,
|
|
"epoch": 3.292594275329396,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00042778206640664915,
|
|
"loss": 5.1962,
|
|
"mean_token_accuracy": 0.18515523225069047,
|
|
"num_tokens": 7498816.0,
|
|
"step": 3625
|
|
},
|
|
{
|
|
"entropy": 5.3733845233917235,
|
|
"epoch": 3.2971376646978645,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004275224224105748,
|
|
"loss": 5.1053,
|
|
"mean_token_accuracy": 0.18491126000881195,
|
|
"num_tokens": 7508691.0,
|
|
"step": 3630
|
|
},
|
|
{
|
|
"entropy": 5.494062662124634,
|
|
"epoch": 3.3016810540663335,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00042726240208058484,
|
|
"loss": 5.2147,
|
|
"mean_token_accuracy": 0.1793356105685234,
|
|
"num_tokens": 7519528.0,
|
|
"step": 3635
|
|
},
|
|
{
|
|
"entropy": 5.435370826721192,
|
|
"epoch": 3.3062244434348025,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004270020060582538,
|
|
"loss": 5.1979,
|
|
"mean_token_accuracy": 0.17892552465200423,
|
|
"num_tokens": 7529249.0,
|
|
"step": 3640
|
|
},
|
|
{
|
|
"entropy": 5.411064958572387,
|
|
"epoch": 3.310767832803271,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00042674123498608285,
|
|
"loss": 5.1989,
|
|
"mean_token_accuracy": 0.18231538832187652,
|
|
"num_tokens": 7539644.0,
|
|
"step": 3645
|
|
},
|
|
{
|
|
"entropy": 5.4302403926849365,
|
|
"epoch": 3.31531122217174,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00042648008950749877,
|
|
"loss": 5.1811,
|
|
"mean_token_accuracy": 0.18392549455165863,
|
|
"num_tokens": 7549900.0,
|
|
"step": 3650
|
|
},
|
|
{
|
|
"entropy": 5.515547418594361,
|
|
"epoch": 3.319854611540209,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.000426218570266852,
|
|
"loss": 5.2175,
|
|
"mean_token_accuracy": 0.18098709732294083,
|
|
"num_tokens": 7560341.0,
|
|
"step": 3655
|
|
},
|
|
{
|
|
"entropy": 5.463577795028686,
|
|
"epoch": 3.324398000908678,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00042595667790941536,
|
|
"loss": 5.1797,
|
|
"mean_token_accuracy": 0.18162664771080017,
|
|
"num_tokens": 7571111.0,
|
|
"step": 3660
|
|
},
|
|
{
|
|
"entropy": 5.489741373062134,
|
|
"epoch": 3.328941390277147,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00042569441308138204,
|
|
"loss": 5.195,
|
|
"mean_token_accuracy": 0.1769116312265396,
|
|
"num_tokens": 7581556.0,
|
|
"step": 3665
|
|
},
|
|
{
|
|
"entropy": 5.4523824691772464,
|
|
"epoch": 3.3334847796456155,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004254317764298645,
|
|
"loss": 5.1896,
|
|
"mean_token_accuracy": 0.1758448913693428,
|
|
"num_tokens": 7590864.0,
|
|
"step": 3670
|
|
},
|
|
{
|
|
"entropy": 5.410051441192627,
|
|
"epoch": 3.3380281690140845,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004251687686028927,
|
|
"loss": 5.1567,
|
|
"mean_token_accuracy": 0.18049866408109666,
|
|
"num_tokens": 7601434.0,
|
|
"step": 3675
|
|
},
|
|
{
|
|
"entropy": 5.45431752204895,
|
|
"epoch": 3.3425715583825535,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00042490539024941216,
|
|
"loss": 5.0672,
|
|
"mean_token_accuracy": 0.189472496509552,
|
|
"num_tokens": 7611618.0,
|
|
"step": 3680
|
|
},
|
|
{
|
|
"entropy": 5.355163288116455,
|
|
"epoch": 3.347114947751022,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.00042464164201928286,
|
|
"loss": 5.184,
|
|
"mean_token_accuracy": 0.1765318900346756,
|
|
"num_tokens": 7622505.0,
|
|
"step": 3685
|
|
},
|
|
{
|
|
"entropy": 5.49520468711853,
|
|
"epoch": 3.351658337119491,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00042437752456327734,
|
|
"loss": 5.2212,
|
|
"mean_token_accuracy": 0.17826685905456544,
|
|
"num_tokens": 7632502.0,
|
|
"step": 3690
|
|
},
|
|
{
|
|
"entropy": 5.453717660903931,
|
|
"epoch": 3.35620172648796,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.00042411303853307907,
|
|
"loss": 5.1489,
|
|
"mean_token_accuracy": 0.18170528262853622,
|
|
"num_tokens": 7642734.0,
|
|
"step": 3695
|
|
},
|
|
{
|
|
"entropy": 5.4162403583526615,
|
|
"epoch": 3.360745115856429,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004238481845812811,
|
|
"loss": 5.2377,
|
|
"mean_token_accuracy": 0.1770060256123543,
|
|
"num_tokens": 7653436.0,
|
|
"step": 3700
|
|
},
|
|
{
|
|
"entropy": 5.492572832107544,
|
|
"epoch": 3.365288505224898,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.00042358296336138436,
|
|
"loss": 5.1703,
|
|
"mean_token_accuracy": 0.17857989966869353,
|
|
"num_tokens": 7663745.0,
|
|
"step": 3705
|
|
},
|
|
{
|
|
"entropy": 5.487736368179322,
|
|
"epoch": 3.3698318945933665,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004233173755277956,
|
|
"loss": 5.2407,
|
|
"mean_token_accuracy": 0.17478348314762115,
|
|
"num_tokens": 7674014.0,
|
|
"step": 3710
|
|
},
|
|
{
|
|
"entropy": 5.424907684326172,
|
|
"epoch": 3.3743752839618355,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00042305142173582657,
|
|
"loss": 5.1972,
|
|
"mean_token_accuracy": 0.18172836750745774,
|
|
"num_tokens": 7683835.0,
|
|
"step": 3715
|
|
},
|
|
{
|
|
"entropy": 5.502959251403809,
|
|
"epoch": 3.3789186733303045,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.00042278510264169165,
|
|
"loss": 5.3349,
|
|
"mean_token_accuracy": 0.1760183349251747,
|
|
"num_tokens": 7693686.0,
|
|
"step": 3720
|
|
},
|
|
{
|
|
"entropy": 5.507215404510498,
|
|
"epoch": 3.3834620626987735,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00042251841890250696,
|
|
"loss": 5.2011,
|
|
"mean_token_accuracy": 0.17868974059820175,
|
|
"num_tokens": 7703341.0,
|
|
"step": 3725
|
|
},
|
|
{
|
|
"entropy": 5.448986482620239,
|
|
"epoch": 3.388005452067242,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.000422251371176288,
|
|
"loss": 5.1426,
|
|
"mean_token_accuracy": 0.17987417727708815,
|
|
"num_tokens": 7714183.0,
|
|
"step": 3730
|
|
},
|
|
{
|
|
"entropy": 5.419228982925415,
|
|
"epoch": 3.392548841435711,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00042198396012194854,
|
|
"loss": 5.197,
|
|
"mean_token_accuracy": 0.16598387956619262,
|
|
"num_tokens": 7724249.0,
|
|
"step": 3735
|
|
},
|
|
{
|
|
"entropy": 5.46609582901001,
|
|
"epoch": 3.39709223080418,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00042171618639929865,
|
|
"loss": 5.2353,
|
|
"mean_token_accuracy": 0.1757620707154274,
|
|
"num_tokens": 7734737.0,
|
|
"step": 3740
|
|
},
|
|
{
|
|
"entropy": 5.442388248443604,
|
|
"epoch": 3.401635620172649,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00042144805066904345,
|
|
"loss": 5.1683,
|
|
"mean_token_accuracy": 0.17997139245271682,
|
|
"num_tokens": 7744514.0,
|
|
"step": 3745
|
|
},
|
|
{
|
|
"entropy": 5.472032308578491,
|
|
"epoch": 3.4061790095411175,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00042117955359278125,
|
|
"loss": 5.1688,
|
|
"mean_token_accuracy": 0.18877988755702974,
|
|
"num_tokens": 7754754.0,
|
|
"step": 3750
|
|
},
|
|
{
|
|
"entropy": 5.493382263183594,
|
|
"epoch": 3.4107223989095865,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00042091069583300177,
|
|
"loss": 5.197,
|
|
"mean_token_accuracy": 0.17629809379577638,
|
|
"num_tokens": 7764723.0,
|
|
"step": 3755
|
|
},
|
|
{
|
|
"entropy": 5.441033124923706,
|
|
"epoch": 3.4152657882780555,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004206414780530849,
|
|
"loss": 5.2355,
|
|
"mean_token_accuracy": 0.17817626297473907,
|
|
"num_tokens": 7774616.0,
|
|
"step": 3760
|
|
},
|
|
{
|
|
"entropy": 5.541076517105102,
|
|
"epoch": 3.4198091776465245,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004203719009172987,
|
|
"loss": 5.287,
|
|
"mean_token_accuracy": 0.16537854671478272,
|
|
"num_tokens": 7786344.0,
|
|
"step": 3765
|
|
},
|
|
{
|
|
"entropy": 5.471768999099732,
|
|
"epoch": 3.424352567014993,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.000420101965090798,
|
|
"loss": 5.2017,
|
|
"mean_token_accuracy": 0.18040706664323808,
|
|
"num_tokens": 7797200.0,
|
|
"step": 3770
|
|
},
|
|
{
|
|
"entropy": 5.396575927734375,
|
|
"epoch": 3.428895956383462,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004198316712396226,
|
|
"loss": 5.1927,
|
|
"mean_token_accuracy": 0.18388626277446746,
|
|
"num_tokens": 7806282.0,
|
|
"step": 3775
|
|
},
|
|
{
|
|
"entropy": 5.493852043151856,
|
|
"epoch": 3.433439345751931,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.00041956102003069573,
|
|
"loss": 5.1726,
|
|
"mean_token_accuracy": 0.1814517691731453,
|
|
"num_tokens": 7815839.0,
|
|
"step": 3780
|
|
},
|
|
{
|
|
"entropy": 5.42592077255249,
|
|
"epoch": 3.4379827351204,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004192900121318223,
|
|
"loss": 5.213,
|
|
"mean_token_accuracy": 0.18745964616537095,
|
|
"num_tokens": 7825927.0,
|
|
"step": 3785
|
|
},
|
|
{
|
|
"entropy": 5.420536041259766,
|
|
"epoch": 3.4425261244888685,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004190186482116874,
|
|
"loss": 5.2455,
|
|
"mean_token_accuracy": 0.17166677117347717,
|
|
"num_tokens": 7836428.0,
|
|
"step": 3790
|
|
},
|
|
{
|
|
"entropy": 5.454354524612427,
|
|
"epoch": 3.4470695138573375,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004187469289398545,
|
|
"loss": 5.2325,
|
|
"mean_token_accuracy": 0.17582079023122787,
|
|
"num_tokens": 7847445.0,
|
|
"step": 3795
|
|
},
|
|
{
|
|
"entropy": 5.450703191757202,
|
|
"epoch": 3.4516129032258065,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00041847485498676385,
|
|
"loss": 5.2256,
|
|
"mean_token_accuracy": 0.17961232513189315,
|
|
"num_tokens": 7857495.0,
|
|
"step": 3800
|
|
},
|
|
{
|
|
"entropy": 5.436532878875733,
|
|
"epoch": 3.4561562925942755,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00041820242702373094,
|
|
"loss": 5.185,
|
|
"mean_token_accuracy": 0.17685455828905106,
|
|
"num_tokens": 7867664.0,
|
|
"step": 3805
|
|
},
|
|
{
|
|
"entropy": 5.399307107925415,
|
|
"epoch": 3.460699681962744,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004179296457229448,
|
|
"loss": 5.1385,
|
|
"mean_token_accuracy": 0.1867094963788986,
|
|
"num_tokens": 7878347.0,
|
|
"step": 3810
|
|
},
|
|
{
|
|
"entropy": 5.477291488647461,
|
|
"epoch": 3.465243071331213,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004176565117574659,
|
|
"loss": 5.1805,
|
|
"mean_token_accuracy": 0.1825316607952118,
|
|
"num_tokens": 7888984.0,
|
|
"step": 3815
|
|
},
|
|
{
|
|
"entropy": 5.449978971481324,
|
|
"epoch": 3.469786460699682,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.0004173830258012255,
|
|
"loss": 5.2324,
|
|
"mean_token_accuracy": 0.17495810687541963,
|
|
"num_tokens": 7899727.0,
|
|
"step": 3820
|
|
},
|
|
{
|
|
"entropy": 5.429280090332031,
|
|
"epoch": 3.474329850068151,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004171091885290226,
|
|
"loss": 5.186,
|
|
"mean_token_accuracy": 0.1805478647351265,
|
|
"num_tokens": 7908666.0,
|
|
"step": 3825
|
|
},
|
|
{
|
|
"entropy": 5.524430656433106,
|
|
"epoch": 3.4788732394366195,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004168350006165238,
|
|
"loss": 5.1821,
|
|
"mean_token_accuracy": 0.18650293052196504,
|
|
"num_tokens": 7919215.0,
|
|
"step": 3830
|
|
},
|
|
{
|
|
"entropy": 5.339998769760132,
|
|
"epoch": 3.4834166288050885,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.00041656046274026034,
|
|
"loss": 5.1709,
|
|
"mean_token_accuracy": 0.18508471548557281,
|
|
"num_tokens": 7929630.0,
|
|
"step": 3835
|
|
},
|
|
{
|
|
"entropy": 5.458227252960205,
|
|
"epoch": 3.4879600181735575,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004162855755776272,
|
|
"loss": 5.1974,
|
|
"mean_token_accuracy": 0.17996394485235215,
|
|
"num_tokens": 7940045.0,
|
|
"step": 3840
|
|
},
|
|
{
|
|
"entropy": 5.457459354400635,
|
|
"epoch": 3.4925034075420265,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00041601033980688106,
|
|
"loss": 5.2039,
|
|
"mean_token_accuracy": 0.18462169468402861,
|
|
"num_tokens": 7950306.0,
|
|
"step": 3845
|
|
},
|
|
{
|
|
"entropy": 5.466891574859619,
|
|
"epoch": 3.497046796910495,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004157347561071389,
|
|
"loss": 5.3388,
|
|
"mean_token_accuracy": 0.17064042687416076,
|
|
"num_tokens": 7961379.0,
|
|
"step": 3850
|
|
},
|
|
{
|
|
"entropy": 5.554404544830322,
|
|
"epoch": 3.501590186278964,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00041545882515837604,
|
|
"loss": 5.2581,
|
|
"mean_token_accuracy": 0.17428269535303115,
|
|
"num_tokens": 7972003.0,
|
|
"step": 3855
|
|
},
|
|
{
|
|
"entropy": 5.424347352981568,
|
|
"epoch": 3.506133575647433,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00041518254764142477,
|
|
"loss": 5.2475,
|
|
"mean_token_accuracy": 0.17852502763271333,
|
|
"num_tokens": 7982727.0,
|
|
"step": 3860
|
|
},
|
|
{
|
|
"entropy": 5.3957929611206055,
|
|
"epoch": 3.510676965015902,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.00041490592423797226,
|
|
"loss": 5.1762,
|
|
"mean_token_accuracy": 0.1746702402830124,
|
|
"num_tokens": 7993902.0,
|
|
"step": 3865
|
|
},
|
|
{
|
|
"entropy": 5.509116125106812,
|
|
"epoch": 3.515220354384371,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004146289556305594,
|
|
"loss": 5.2863,
|
|
"mean_token_accuracy": 0.1710102453827858,
|
|
"num_tokens": 8004632.0,
|
|
"step": 3870
|
|
},
|
|
{
|
|
"entropy": 5.493361616134644,
|
|
"epoch": 3.5197637437528395,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004143516425025786,
|
|
"loss": 5.2881,
|
|
"mean_token_accuracy": 0.17356898337602616,
|
|
"num_tokens": 8016099.0,
|
|
"step": 3875
|
|
},
|
|
{
|
|
"entropy": 5.560396480560303,
|
|
"epoch": 3.5243071331213085,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004140739855382724,
|
|
"loss": 5.2241,
|
|
"mean_token_accuracy": 0.177641399204731,
|
|
"num_tokens": 8027309.0,
|
|
"step": 3880
|
|
},
|
|
{
|
|
"entropy": 5.508320093154907,
|
|
"epoch": 3.5288505224897775,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00041379598542273197,
|
|
"loss": 5.2855,
|
|
"mean_token_accuracy": 0.17148041874170303,
|
|
"num_tokens": 8037886.0,
|
|
"step": 3885
|
|
},
|
|
{
|
|
"entropy": 5.4417970180511475,
|
|
"epoch": 3.533393911858246,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00041351764284189464,
|
|
"loss": 5.2676,
|
|
"mean_token_accuracy": 0.16962863951921464,
|
|
"num_tokens": 8048383.0,
|
|
"step": 3890
|
|
},
|
|
{
|
|
"entropy": 5.544815397262573,
|
|
"epoch": 3.537937301226715,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004132389584825433,
|
|
"loss": 5.2078,
|
|
"mean_token_accuracy": 0.18141960501670837,
|
|
"num_tokens": 8059686.0,
|
|
"step": 3895
|
|
},
|
|
{
|
|
"entropy": 5.455212020874024,
|
|
"epoch": 3.542480690595184,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.00041295993303230383,
|
|
"loss": 5.2444,
|
|
"mean_token_accuracy": 0.17774744480848312,
|
|
"num_tokens": 8069493.0,
|
|
"step": 3900
|
|
},
|
|
{
|
|
"entropy": 5.394187498092651,
|
|
"epoch": 3.547024079963653,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004126805671796438,
|
|
"loss": 5.1968,
|
|
"mean_token_accuracy": 0.17738135606050492,
|
|
"num_tokens": 8079667.0,
|
|
"step": 3905
|
|
},
|
|
{
|
|
"entropy": 5.4525641918182375,
|
|
"epoch": 3.551567469332122,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004124008616138707,
|
|
"loss": 5.1041,
|
|
"mean_token_accuracy": 0.18227862268686296,
|
|
"num_tokens": 8089406.0,
|
|
"step": 3910
|
|
},
|
|
{
|
|
"entropy": 5.50707311630249,
|
|
"epoch": 3.5561108587005905,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00041212081702513015,
|
|
"loss": 5.231,
|
|
"mean_token_accuracy": 0.18405496180057526,
|
|
"num_tokens": 8100406.0,
|
|
"step": 3915
|
|
},
|
|
{
|
|
"entropy": 5.407625341415406,
|
|
"epoch": 3.5606542480690595,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004118404341044044,
|
|
"loss": 5.2372,
|
|
"mean_token_accuracy": 0.17826576977968217,
|
|
"num_tokens": 8110913.0,
|
|
"step": 3920
|
|
},
|
|
{
|
|
"entropy": 5.491508054733276,
|
|
"epoch": 3.5651976374375285,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.00041155971354351034,
|
|
"loss": 5.1967,
|
|
"mean_token_accuracy": 0.18321506530046464,
|
|
"num_tokens": 8120599.0,
|
|
"step": 3925
|
|
},
|
|
{
|
|
"entropy": 5.446130847930908,
|
|
"epoch": 3.569741026805997,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.00041127865603509815,
|
|
"loss": 5.2262,
|
|
"mean_token_accuracy": 0.17785461544990538,
|
|
"num_tokens": 8131142.0,
|
|
"step": 3930
|
|
},
|
|
{
|
|
"entropy": 5.493320751190185,
|
|
"epoch": 3.574284416174466,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004109972622726493,
|
|
"loss": 5.2212,
|
|
"mean_token_accuracy": 0.17071423977613448,
|
|
"num_tokens": 8141332.0,
|
|
"step": 3935
|
|
},
|
|
{
|
|
"entropy": 5.524670886993408,
|
|
"epoch": 3.578827805542935,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00041071553295047485,
|
|
"loss": 5.2485,
|
|
"mean_token_accuracy": 0.1805952861905098,
|
|
"num_tokens": 8151952.0,
|
|
"step": 3940
|
|
},
|
|
{
|
|
"entropy": 5.3999958515167235,
|
|
"epoch": 3.583371194911404,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004104334687637139,
|
|
"loss": 5.211,
|
|
"mean_token_accuracy": 0.1788506969809532,
|
|
"num_tokens": 8162563.0,
|
|
"step": 3945
|
|
},
|
|
{
|
|
"entropy": 5.4916106224060055,
|
|
"epoch": 3.587914584279873,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.00041015107040833187,
|
|
"loss": 5.2355,
|
|
"mean_token_accuracy": 0.177272430062294,
|
|
"num_tokens": 8173428.0,
|
|
"step": 3950
|
|
},
|
|
{
|
|
"entropy": 5.480176019668579,
|
|
"epoch": 3.5924579736483415,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004098683385811185,
|
|
"loss": 5.2355,
|
|
"mean_token_accuracy": 0.18035785853862762,
|
|
"num_tokens": 8185139.0,
|
|
"step": 3955
|
|
},
|
|
{
|
|
"entropy": 5.393027591705322,
|
|
"epoch": 3.5970013630168105,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00040958527397968666,
|
|
"loss": 5.2542,
|
|
"mean_token_accuracy": 0.1696605294942856,
|
|
"num_tokens": 8196476.0,
|
|
"step": 3960
|
|
},
|
|
{
|
|
"entropy": 5.5399340152740475,
|
|
"epoch": 3.6015447523852795,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004093018773024699,
|
|
"loss": 5.2502,
|
|
"mean_token_accuracy": 0.17737207561731339,
|
|
"num_tokens": 8207325.0,
|
|
"step": 3965
|
|
},
|
|
{
|
|
"entropy": 5.469987964630127,
|
|
"epoch": 3.606088141753748,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004090181492487215,
|
|
"loss": 5.1651,
|
|
"mean_token_accuracy": 0.17676841020584105,
|
|
"num_tokens": 8217913.0,
|
|
"step": 3970
|
|
},
|
|
{
|
|
"entropy": 5.41141676902771,
|
|
"epoch": 3.610631531122217,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00040873409051851223,
|
|
"loss": 5.2025,
|
|
"mean_token_accuracy": 0.1811208963394165,
|
|
"num_tokens": 8227910.0,
|
|
"step": 3975
|
|
},
|
|
{
|
|
"entropy": 5.462663078308106,
|
|
"epoch": 3.615174920490686,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004084497018127286,
|
|
"loss": 5.2502,
|
|
"mean_token_accuracy": 0.16587285548448563,
|
|
"num_tokens": 8240566.0,
|
|
"step": 3980
|
|
},
|
|
{
|
|
"entropy": 5.453423976898193,
|
|
"epoch": 3.619718309859155,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004081649838330717,
|
|
"loss": 5.192,
|
|
"mean_token_accuracy": 0.1848574623465538,
|
|
"num_tokens": 8250518.0,
|
|
"step": 3985
|
|
},
|
|
{
|
|
"entropy": 5.419863557815551,
|
|
"epoch": 3.624261699227624,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00040787993728205464,
|
|
"loss": 5.2259,
|
|
"mean_token_accuracy": 0.18126198202371596,
|
|
"num_tokens": 8260576.0,
|
|
"step": 3990
|
|
},
|
|
{
|
|
"entropy": 5.405695581436158,
|
|
"epoch": 3.6288050885960925,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.00040759456286300154,
|
|
"loss": 5.1741,
|
|
"mean_token_accuracy": 0.1786780387163162,
|
|
"num_tokens": 8271293.0,
|
|
"step": 3995
|
|
},
|
|
{
|
|
"entropy": 5.4588617324829105,
|
|
"epoch": 3.6333484779645615,
|
|
"grad_norm": 1.921875,
|
|
"learning_rate": 0.00040730886128004544,
|
|
"loss": 5.1782,
|
|
"mean_token_accuracy": 0.18059180676937103,
|
|
"num_tokens": 8281745.0,
|
|
"step": 4000
|
|
},
|
|
{
|
|
"epoch": 3.6333484779645615,
|
|
"eval_entropy": 5.42356046410494,
|
|
"eval_loss": 5.841984748840332,
|
|
"eval_mean_token_accuracy": 0.1589083943256112,
|
|
"eval_num_tokens": 8281745.0,
|
|
"eval_runtime": 2.5713,
|
|
"eval_samples_per_second": 1335.9,
|
|
"eval_steps_per_second": 167.231,
|
|
"step": 4000
|
|
},
|
|
{
|
|
"entropy": 5.5291341781616214,
|
|
"epoch": 3.6378918673330305,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004070228332381266,
|
|
"loss": 5.2725,
|
|
"mean_token_accuracy": 0.17453757673501968,
|
|
"num_tokens": 8291120.0,
|
|
"step": 4005
|
|
},
|
|
{
|
|
"entropy": 5.44803524017334,
|
|
"epoch": 3.6424352567014995,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004067364794429908,
|
|
"loss": 5.2537,
|
|
"mean_token_accuracy": 0.17181315124034882,
|
|
"num_tokens": 8301339.0,
|
|
"step": 4010
|
|
},
|
|
{
|
|
"entropy": 5.428507995605469,
|
|
"epoch": 3.646978646069968,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004064498006011874,
|
|
"loss": 5.2102,
|
|
"mean_token_accuracy": 0.17865341007709504,
|
|
"num_tokens": 8310954.0,
|
|
"step": 4015
|
|
},
|
|
{
|
|
"entropy": 5.432149887084961,
|
|
"epoch": 3.651522035438437,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00040616279742006813,
|
|
"loss": 5.1254,
|
|
"mean_token_accuracy": 0.18629482686519622,
|
|
"num_tokens": 8321481.0,
|
|
"step": 4020
|
|
},
|
|
{
|
|
"entropy": 5.394993257522583,
|
|
"epoch": 3.656065424806906,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00040587547060778466,
|
|
"loss": 5.2748,
|
|
"mean_token_accuracy": 0.1753845691680908,
|
|
"num_tokens": 8330960.0,
|
|
"step": 4025
|
|
},
|
|
{
|
|
"entropy": 5.405106067657471,
|
|
"epoch": 3.660608814175375,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004055878208732874,
|
|
"loss": 5.1596,
|
|
"mean_token_accuracy": 0.18554015904664994,
|
|
"num_tokens": 8340419.0,
|
|
"step": 4030
|
|
},
|
|
{
|
|
"entropy": 5.44690899848938,
|
|
"epoch": 3.665152203543844,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00040529984892632363,
|
|
"loss": 5.1443,
|
|
"mean_token_accuracy": 0.18169436752796173,
|
|
"num_tokens": 8350796.0,
|
|
"step": 4035
|
|
},
|
|
{
|
|
"entropy": 5.513323497772217,
|
|
"epoch": 3.6696955929123125,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004050115554774353,
|
|
"loss": 5.2549,
|
|
"mean_token_accuracy": 0.17648565769195557,
|
|
"num_tokens": 8361946.0,
|
|
"step": 4040
|
|
},
|
|
{
|
|
"entropy": 5.50125789642334,
|
|
"epoch": 3.6742389822807815,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004047229412379578,
|
|
"loss": 5.2744,
|
|
"mean_token_accuracy": 0.17319637835025786,
|
|
"num_tokens": 8372113.0,
|
|
"step": 4045
|
|
},
|
|
{
|
|
"entropy": 5.345899152755737,
|
|
"epoch": 3.6787823716492505,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004044340069200183,
|
|
"loss": 5.1748,
|
|
"mean_token_accuracy": 0.17694563418626785,
|
|
"num_tokens": 8382241.0,
|
|
"step": 4050
|
|
},
|
|
{
|
|
"entropy": 5.48505482673645,
|
|
"epoch": 3.683325761017719,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00040414475323653326,
|
|
"loss": 5.2211,
|
|
"mean_token_accuracy": 0.16955616176128388,
|
|
"num_tokens": 8393294.0,
|
|
"step": 4055
|
|
},
|
|
{
|
|
"entropy": 5.448994779586792,
|
|
"epoch": 3.687869150386188,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004038551809012076,
|
|
"loss": 5.186,
|
|
"mean_token_accuracy": 0.18053057491779329,
|
|
"num_tokens": 8403586.0,
|
|
"step": 4060
|
|
},
|
|
{
|
|
"entropy": 5.472670221328736,
|
|
"epoch": 3.692412539754657,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004035652906285322,
|
|
"loss": 5.1973,
|
|
"mean_token_accuracy": 0.18297682404518129,
|
|
"num_tokens": 8413543.0,
|
|
"step": 4065
|
|
},
|
|
{
|
|
"entropy": 5.378189611434936,
|
|
"epoch": 3.696955929123126,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00040327508313378244,
|
|
"loss": 5.1677,
|
|
"mean_token_accuracy": 0.17790673524141312,
|
|
"num_tokens": 8423578.0,
|
|
"step": 4070
|
|
},
|
|
{
|
|
"entropy": 5.469921827316284,
|
|
"epoch": 3.701499318491595,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004029845591330164,
|
|
"loss": 5.1811,
|
|
"mean_token_accuracy": 0.17663831859827042,
|
|
"num_tokens": 8434140.0,
|
|
"step": 4075
|
|
},
|
|
{
|
|
"entropy": 5.508017683029175,
|
|
"epoch": 3.7060427078600635,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00040269371934307336,
|
|
"loss": 5.2794,
|
|
"mean_token_accuracy": 0.17830464988946915,
|
|
"num_tokens": 8445573.0,
|
|
"step": 4080
|
|
},
|
|
{
|
|
"entropy": 5.318528461456299,
|
|
"epoch": 3.7105860972285325,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00040240256448157146,
|
|
"loss": 5.1276,
|
|
"mean_token_accuracy": 0.18409459441900253,
|
|
"num_tokens": 8455437.0,
|
|
"step": 4085
|
|
},
|
|
{
|
|
"entropy": 5.451051425933838,
|
|
"epoch": 3.7151294865970015,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004021110952669065,
|
|
"loss": 5.1604,
|
|
"mean_token_accuracy": 0.17857249528169633,
|
|
"num_tokens": 8465629.0,
|
|
"step": 4090
|
|
},
|
|
{
|
|
"entropy": 5.525282478332519,
|
|
"epoch": 3.71967287596547,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004018193124182497,
|
|
"loss": 5.2305,
|
|
"mean_token_accuracy": 0.17360700964927672,
|
|
"num_tokens": 8477213.0,
|
|
"step": 4095
|
|
},
|
|
{
|
|
"entropy": 5.342419528961182,
|
|
"epoch": 3.724216265333939,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004015272166555462,
|
|
"loss": 5.298,
|
|
"mean_token_accuracy": 0.17276449799537658,
|
|
"num_tokens": 8487994.0,
|
|
"step": 4100
|
|
},
|
|
{
|
|
"entropy": 5.464218425750732,
|
|
"epoch": 3.728759654702408,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004012348086995132,
|
|
"loss": 5.2074,
|
|
"mean_token_accuracy": 0.17191025316715242,
|
|
"num_tokens": 8497630.0,
|
|
"step": 4105
|
|
},
|
|
{
|
|
"entropy": 5.410339069366455,
|
|
"epoch": 3.733303044070877,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004009420892716385,
|
|
"loss": 5.108,
|
|
"mean_token_accuracy": 0.18675794154405595,
|
|
"num_tokens": 8507770.0,
|
|
"step": 4110
|
|
},
|
|
{
|
|
"entropy": 5.485575485229492,
|
|
"epoch": 3.737846433439346,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004006490590941781,
|
|
"loss": 5.2766,
|
|
"mean_token_accuracy": 0.17658564299345017,
|
|
"num_tokens": 8517044.0,
|
|
"step": 4115
|
|
},
|
|
{
|
|
"entropy": 5.430522537231445,
|
|
"epoch": 3.7423898228078145,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004003557188901547,
|
|
"loss": 5.1542,
|
|
"mean_token_accuracy": 0.1890944540500641,
|
|
"num_tokens": 8527471.0,
|
|
"step": 4120
|
|
},
|
|
{
|
|
"entropy": 5.399834251403808,
|
|
"epoch": 3.7469332121762835,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004000620693833562,
|
|
"loss": 5.165,
|
|
"mean_token_accuracy": 0.18133367896080016,
|
|
"num_tokens": 8537065.0,
|
|
"step": 4125
|
|
},
|
|
{
|
|
"entropy": 5.392874717712402,
|
|
"epoch": 3.7514766015447525,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0003997681112983335,
|
|
"loss": 5.2093,
|
|
"mean_token_accuracy": 0.17683751732110978,
|
|
"num_tokens": 8547875.0,
|
|
"step": 4130
|
|
},
|
|
{
|
|
"entropy": 5.465796899795532,
|
|
"epoch": 3.756019990913221,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.00039947384536039905,
|
|
"loss": 5.1545,
|
|
"mean_token_accuracy": 0.18322011530399324,
|
|
"num_tokens": 8558334.0,
|
|
"step": 4135
|
|
},
|
|
{
|
|
"entropy": 5.47621636390686,
|
|
"epoch": 3.76056338028169,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.00039917927229562474,
|
|
"loss": 5.3175,
|
|
"mean_token_accuracy": 0.16869245916604997,
|
|
"num_tokens": 8568983.0,
|
|
"step": 4140
|
|
},
|
|
{
|
|
"entropy": 5.405741596221924,
|
|
"epoch": 3.765106769650159,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.00039888439283084035,
|
|
"loss": 5.2309,
|
|
"mean_token_accuracy": 0.17227526903152465,
|
|
"num_tokens": 8578995.0,
|
|
"step": 4145
|
|
},
|
|
{
|
|
"entropy": 5.513731336593628,
|
|
"epoch": 3.769650159018628,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00039858920769363164,
|
|
"loss": 5.2736,
|
|
"mean_token_accuracy": 0.17099927514791488,
|
|
"num_tokens": 8589393.0,
|
|
"step": 4150
|
|
},
|
|
{
|
|
"entropy": 5.471535348892212,
|
|
"epoch": 3.774193548387097,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0003982937176123386,
|
|
"loss": 5.2093,
|
|
"mean_token_accuracy": 0.1821272626519203,
|
|
"num_tokens": 8599978.0,
|
|
"step": 4155
|
|
},
|
|
{
|
|
"entropy": 5.4272901058197025,
|
|
"epoch": 3.7787369377555655,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00039799792331605364,
|
|
"loss": 5.2038,
|
|
"mean_token_accuracy": 0.18003834187984466,
|
|
"num_tokens": 8611313.0,
|
|
"step": 4160
|
|
},
|
|
{
|
|
"entropy": 5.44575605392456,
|
|
"epoch": 3.7832803271240345,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00039770182553461965,
|
|
"loss": 5.2211,
|
|
"mean_token_accuracy": 0.18152208775281906,
|
|
"num_tokens": 8621592.0,
|
|
"step": 4165
|
|
},
|
|
{
|
|
"entropy": 5.45830888748169,
|
|
"epoch": 3.7878237164925035,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00039740542499862866,
|
|
"loss": 5.0798,
|
|
"mean_token_accuracy": 0.18924971371889115,
|
|
"num_tokens": 8631373.0,
|
|
"step": 4170
|
|
},
|
|
{
|
|
"entropy": 5.406582832336426,
|
|
"epoch": 3.792367105860972,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0003971087224394194,
|
|
"loss": 5.2189,
|
|
"mean_token_accuracy": 0.18058714568614959,
|
|
"num_tokens": 8642004.0,
|
|
"step": 4175
|
|
},
|
|
{
|
|
"entropy": 5.420920753479004,
|
|
"epoch": 3.796910495229441,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0003968117185890761,
|
|
"loss": 5.2275,
|
|
"mean_token_accuracy": 0.1781480520963669,
|
|
"num_tokens": 8651877.0,
|
|
"step": 4180
|
|
},
|
|
{
|
|
"entropy": 5.520320034027099,
|
|
"epoch": 3.80145388459791,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00039651441418042606,
|
|
"loss": 5.1802,
|
|
"mean_token_accuracy": 0.17863254398107528,
|
|
"num_tokens": 8663426.0,
|
|
"step": 4185
|
|
},
|
|
{
|
|
"entropy": 5.424657201766967,
|
|
"epoch": 3.805997273966379,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0003962168099470384,
|
|
"loss": 5.2202,
|
|
"mean_token_accuracy": 0.17193590998649597,
|
|
"num_tokens": 8673723.0,
|
|
"step": 4190
|
|
},
|
|
{
|
|
"entropy": 5.453806018829345,
|
|
"epoch": 3.810540663334848,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.000395918906623222,
|
|
"loss": 5.2355,
|
|
"mean_token_accuracy": 0.17725314646959306,
|
|
"num_tokens": 8683609.0,
|
|
"step": 4195
|
|
},
|
|
{
|
|
"entropy": 5.5232000827789305,
|
|
"epoch": 3.8150840527033165,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.0003956207049440238,
|
|
"loss": 5.2625,
|
|
"mean_token_accuracy": 0.17435407489538193,
|
|
"num_tokens": 8693993.0,
|
|
"step": 4200
|
|
},
|
|
{
|
|
"entropy": 5.487712955474853,
|
|
"epoch": 3.8196274420717855,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0003953222056452265,
|
|
"loss": 5.2556,
|
|
"mean_token_accuracy": 0.16565096825361253,
|
|
"num_tokens": 8704498.0,
|
|
"step": 4205
|
|
},
|
|
{
|
|
"entropy": 5.408457565307617,
|
|
"epoch": 3.8241708314402545,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0003950234094633479,
|
|
"loss": 5.2092,
|
|
"mean_token_accuracy": 0.17543325424194336,
|
|
"num_tokens": 8715625.0,
|
|
"step": 4210
|
|
},
|
|
{
|
|
"entropy": 5.365530633926392,
|
|
"epoch": 3.828714220808723,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00039472431713563746,
|
|
"loss": 5.1226,
|
|
"mean_token_accuracy": 0.18442826569080353,
|
|
"num_tokens": 8725565.0,
|
|
"step": 4215
|
|
},
|
|
{
|
|
"entropy": 5.457325029373169,
|
|
"epoch": 3.833257610177192,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.000394424929400076,
|
|
"loss": 5.2252,
|
|
"mean_token_accuracy": 0.17616413682699203,
|
|
"num_tokens": 8736170.0,
|
|
"step": 4220
|
|
},
|
|
{
|
|
"entropy": 5.441134691238403,
|
|
"epoch": 3.837800999545661,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0003941252469953729,
|
|
"loss": 5.1524,
|
|
"mean_token_accuracy": 0.18503619730472565,
|
|
"num_tokens": 8747093.0,
|
|
"step": 4225
|
|
},
|
|
{
|
|
"entropy": 5.448698043823242,
|
|
"epoch": 3.84234438891413,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0003938252706609647,
|
|
"loss": 5.2413,
|
|
"mean_token_accuracy": 0.1762436881661415,
|
|
"num_tokens": 8757304.0,
|
|
"step": 4230
|
|
},
|
|
{
|
|
"entropy": 5.414624166488648,
|
|
"epoch": 3.846887778282599,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0003935250011370132,
|
|
"loss": 5.1996,
|
|
"mean_token_accuracy": 0.18881602436304093,
|
|
"num_tokens": 8767181.0,
|
|
"step": 4235
|
|
},
|
|
{
|
|
"entropy": 5.465357494354248,
|
|
"epoch": 3.851431167651068,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0003932244391644037,
|
|
"loss": 5.1633,
|
|
"mean_token_accuracy": 0.17758932560682297,
|
|
"num_tokens": 8777131.0,
|
|
"step": 4240
|
|
},
|
|
{
|
|
"entropy": 5.4338702201843265,
|
|
"epoch": 3.8559745570195365,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0003929235854847428,
|
|
"loss": 5.1776,
|
|
"mean_token_accuracy": 0.18129560053348542,
|
|
"num_tokens": 8787025.0,
|
|
"step": 4245
|
|
},
|
|
{
|
|
"entropy": 5.433534860610962,
|
|
"epoch": 3.8605179463880055,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.00039262244084035724,
|
|
"loss": 5.2379,
|
|
"mean_token_accuracy": 0.1800116091966629,
|
|
"num_tokens": 8796537.0,
|
|
"step": 4250
|
|
},
|
|
{
|
|
"entropy": 5.42926516532898,
|
|
"epoch": 3.8650613357564745,
|
|
"grad_norm": 2.765625,
|
|
"learning_rate": 0.00039232100597429143,
|
|
"loss": 5.2342,
|
|
"mean_token_accuracy": 0.18129930198192595,
|
|
"num_tokens": 8807191.0,
|
|
"step": 4255
|
|
},
|
|
{
|
|
"entropy": 5.501903676986695,
|
|
"epoch": 3.869604725124943,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00039201928163030584,
|
|
"loss": 5.1633,
|
|
"mean_token_accuracy": 0.18733880221843718,
|
|
"num_tokens": 8817623.0,
|
|
"step": 4260
|
|
},
|
|
{
|
|
"entropy": 5.441175937652588,
|
|
"epoch": 3.874148114493412,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00039171726855287544,
|
|
"loss": 5.2005,
|
|
"mean_token_accuracy": 0.18381727188825608,
|
|
"num_tokens": 8828274.0,
|
|
"step": 4265
|
|
},
|
|
{
|
|
"entropy": 5.41581711769104,
|
|
"epoch": 3.878691503861881,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.00039141496748718735,
|
|
"loss": 5.2092,
|
|
"mean_token_accuracy": 0.17923459857702256,
|
|
"num_tokens": 8838416.0,
|
|
"step": 4270
|
|
},
|
|
{
|
|
"entropy": 5.479474782943726,
|
|
"epoch": 3.88323489323035,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0003911123791791395,
|
|
"loss": 5.1911,
|
|
"mean_token_accuracy": 0.18462371528148652,
|
|
"num_tokens": 8849647.0,
|
|
"step": 4275
|
|
},
|
|
{
|
|
"entropy": 5.456370544433594,
|
|
"epoch": 3.887778282598819,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0003908095043753384,
|
|
"loss": 5.2343,
|
|
"mean_token_accuracy": 0.18020307272672653,
|
|
"num_tokens": 8860637.0,
|
|
"step": 4280
|
|
},
|
|
{
|
|
"entropy": 5.384213876724243,
|
|
"epoch": 3.8923216719672875,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00039050634382309753,
|
|
"loss": 5.1635,
|
|
"mean_token_accuracy": 0.17960731089115142,
|
|
"num_tokens": 8870494.0,
|
|
"step": 4285
|
|
},
|
|
{
|
|
"entropy": 5.419296407699585,
|
|
"epoch": 3.8968650613357565,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0003902028982704355,
|
|
"loss": 5.2075,
|
|
"mean_token_accuracy": 0.17803939133882524,
|
|
"num_tokens": 8881187.0,
|
|
"step": 4290
|
|
},
|
|
{
|
|
"entropy": 5.433315849304199,
|
|
"epoch": 3.9014084507042255,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0003898991684660738,
|
|
"loss": 5.2775,
|
|
"mean_token_accuracy": 0.17603085190057755,
|
|
"num_tokens": 8891290.0,
|
|
"step": 4295
|
|
},
|
|
{
|
|
"entropy": 5.4231729984283445,
|
|
"epoch": 3.905951840072694,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0003895951551594358,
|
|
"loss": 5.1796,
|
|
"mean_token_accuracy": 0.18032593578100203,
|
|
"num_tokens": 8901560.0,
|
|
"step": 4300
|
|
},
|
|
{
|
|
"entropy": 5.4363758087158205,
|
|
"epoch": 3.910495229441163,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.000389290859100644,
|
|
"loss": 5.1975,
|
|
"mean_token_accuracy": 0.1844823032617569,
|
|
"num_tokens": 8912310.0,
|
|
"step": 4305
|
|
},
|
|
{
|
|
"entropy": 5.341080617904663,
|
|
"epoch": 3.915038618809632,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0003889862810405187,
|
|
"loss": 5.1533,
|
|
"mean_token_accuracy": 0.18248962759971618,
|
|
"num_tokens": 8922669.0,
|
|
"step": 4310
|
|
},
|
|
{
|
|
"entropy": 5.480225849151611,
|
|
"epoch": 3.919582008178101,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.000388681421730576,
|
|
"loss": 5.2087,
|
|
"mean_token_accuracy": 0.1796492487192154,
|
|
"num_tokens": 8933352.0,
|
|
"step": 4315
|
|
},
|
|
{
|
|
"entropy": 5.423327159881592,
|
|
"epoch": 3.92412539754657,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0003883762819230259,
|
|
"loss": 5.2,
|
|
"mean_token_accuracy": 0.17268395870923997,
|
|
"num_tokens": 8944124.0,
|
|
"step": 4320
|
|
},
|
|
{
|
|
"entropy": 5.3118428707122805,
|
|
"epoch": 3.9286687869150385,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00038807086237077057,
|
|
"loss": 5.1198,
|
|
"mean_token_accuracy": 0.188446606695652,
|
|
"num_tokens": 8954272.0,
|
|
"step": 4325
|
|
},
|
|
{
|
|
"entropy": 5.464400911331177,
|
|
"epoch": 3.9332121762835075,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.00038776516382740237,
|
|
"loss": 5.226,
|
|
"mean_token_accuracy": 0.18085191547870635,
|
|
"num_tokens": 8965456.0,
|
|
"step": 4330
|
|
},
|
|
{
|
|
"entropy": 5.451799154281616,
|
|
"epoch": 3.9377555656519765,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00038745918704720205,
|
|
"loss": 5.1548,
|
|
"mean_token_accuracy": 0.19036811739206314,
|
|
"num_tokens": 8975157.0,
|
|
"step": 4335
|
|
},
|
|
{
|
|
"entropy": 5.331761169433594,
|
|
"epoch": 3.942298955020445,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.00038715293278513693,
|
|
"loss": 5.1904,
|
|
"mean_token_accuracy": 0.18353113979101182,
|
|
"num_tokens": 8984549.0,
|
|
"step": 4340
|
|
},
|
|
{
|
|
"entropy": 5.435685873031616,
|
|
"epoch": 3.946842344388914,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.00038684640179685896,
|
|
"loss": 5.1589,
|
|
"mean_token_accuracy": 0.18212351500988005,
|
|
"num_tokens": 8994572.0,
|
|
"step": 4345
|
|
},
|
|
{
|
|
"entropy": 5.481965160369873,
|
|
"epoch": 3.951385733757383,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0003865395948387029,
|
|
"loss": 5.234,
|
|
"mean_token_accuracy": 0.17645334601402282,
|
|
"num_tokens": 9005568.0,
|
|
"step": 4350
|
|
},
|
|
{
|
|
"entropy": 5.342183923721313,
|
|
"epoch": 3.955929123125852,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00038623251266768437,
|
|
"loss": 5.1845,
|
|
"mean_token_accuracy": 0.18008915781974794,
|
|
"num_tokens": 9015818.0,
|
|
"step": 4355
|
|
},
|
|
{
|
|
"entropy": 5.486167764663696,
|
|
"epoch": 3.960472512494321,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00038592515604149815,
|
|
"loss": 5.2212,
|
|
"mean_token_accuracy": 0.1761232167482376,
|
|
"num_tokens": 9026414.0,
|
|
"step": 4360
|
|
},
|
|
{
|
|
"entropy": 5.5199377059936525,
|
|
"epoch": 3.9650159018627895,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0003856175257185162,
|
|
"loss": 5.2928,
|
|
"mean_token_accuracy": 0.166163569688797,
|
|
"num_tokens": 9037891.0,
|
|
"step": 4365
|
|
},
|
|
{
|
|
"entropy": 5.433918523788452,
|
|
"epoch": 3.9695592912312585,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.00038530962245778564,
|
|
"loss": 5.1903,
|
|
"mean_token_accuracy": 0.1828097954392433,
|
|
"num_tokens": 9047877.0,
|
|
"step": 4370
|
|
},
|
|
{
|
|
"entropy": 5.388544797897339,
|
|
"epoch": 3.9741026805997275,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0003850014470190272,
|
|
"loss": 5.1816,
|
|
"mean_token_accuracy": 0.17716721296310425,
|
|
"num_tokens": 9057599.0,
|
|
"step": 4375
|
|
},
|
|
{
|
|
"entropy": 5.433516597747802,
|
|
"epoch": 3.978646069968196,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0003846930001626332,
|
|
"loss": 5.281,
|
|
"mean_token_accuracy": 0.1683693751692772,
|
|
"num_tokens": 9068820.0,
|
|
"step": 4380
|
|
},
|
|
{
|
|
"entropy": 5.518597078323364,
|
|
"epoch": 3.983189459336665,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0003843842826496656,
|
|
"loss": 5.245,
|
|
"mean_token_accuracy": 0.17853791117668152,
|
|
"num_tokens": 9079350.0,
|
|
"step": 4385
|
|
},
|
|
{
|
|
"entropy": 5.470326900482178,
|
|
"epoch": 3.987732848705134,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.000384075295241854,
|
|
"loss": 5.1808,
|
|
"mean_token_accuracy": 0.17537155896425247,
|
|
"num_tokens": 9090118.0,
|
|
"step": 4390
|
|
},
|
|
{
|
|
"entropy": 5.455416011810303,
|
|
"epoch": 3.992276238073603,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0003837660387015944,
|
|
"loss": 5.2158,
|
|
"mean_token_accuracy": 0.17393864095211028,
|
|
"num_tokens": 9099808.0,
|
|
"step": 4395
|
|
},
|
|
{
|
|
"entropy": 5.499893379211426,
|
|
"epoch": 3.996819627442072,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0003834565137919463,
|
|
"loss": 5.2582,
|
|
"mean_token_accuracy": 0.17829536348581315,
|
|
"num_tokens": 9110453.0,
|
|
"step": 4400
|
|
},
|
|
{
|
|
"entropy": 5.45589378145006,
|
|
"epoch": 4.000908677873694,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0003831467212766318,
|
|
"loss": 5.1872,
|
|
"mean_token_accuracy": 0.18454202678468493,
|
|
"num_tokens": 9120143.0,
|
|
"step": 4405
|
|
},
|
|
{
|
|
"entropy": 5.386088848114014,
|
|
"epoch": 4.005452067242163,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0003828366619200331,
|
|
"loss": 4.9129,
|
|
"mean_token_accuracy": 0.19461703449487686,
|
|
"num_tokens": 9131074.0,
|
|
"step": 4410
|
|
},
|
|
{
|
|
"entropy": 5.424530553817749,
|
|
"epoch": 4.009995456610632,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0003825263364871908,
|
|
"loss": 4.9407,
|
|
"mean_token_accuracy": 0.19262357503175737,
|
|
"num_tokens": 9141293.0,
|
|
"step": 4415
|
|
},
|
|
{
|
|
"entropy": 5.382290887832641,
|
|
"epoch": 4.0145388459791,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0003822157457438022,
|
|
"loss": 4.9531,
|
|
"mean_token_accuracy": 0.1975314810872078,
|
|
"num_tokens": 9151194.0,
|
|
"step": 4420
|
|
},
|
|
{
|
|
"entropy": 5.3933545589447025,
|
|
"epoch": 4.019082235347569,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00038190489045621893,
|
|
"loss": 4.925,
|
|
"mean_token_accuracy": 0.19789094775915145,
|
|
"num_tokens": 9161041.0,
|
|
"step": 4425
|
|
},
|
|
{
|
|
"entropy": 5.35072922706604,
|
|
"epoch": 4.023625624716038,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0003815937713914455,
|
|
"loss": 4.952,
|
|
"mean_token_accuracy": 0.1921598955988884,
|
|
"num_tokens": 9171491.0,
|
|
"step": 4430
|
|
},
|
|
{
|
|
"entropy": 5.395011711120605,
|
|
"epoch": 4.028169014084507,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.00038128238931713743,
|
|
"loss": 4.9867,
|
|
"mean_token_accuracy": 0.19419898986816406,
|
|
"num_tokens": 9181207.0,
|
|
"step": 4435
|
|
},
|
|
{
|
|
"entropy": 5.426538181304932,
|
|
"epoch": 4.032712403452976,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00038097074500159883,
|
|
"loss": 4.9667,
|
|
"mean_token_accuracy": 0.1928500324487686,
|
|
"num_tokens": 9191167.0,
|
|
"step": 4440
|
|
},
|
|
{
|
|
"entropy": 5.3545316696167,
|
|
"epoch": 4.037255792821445,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00038065883921378123,
|
|
"loss": 4.9515,
|
|
"mean_token_accuracy": 0.1935017451643944,
|
|
"num_tokens": 9201850.0,
|
|
"step": 4445
|
|
},
|
|
{
|
|
"entropy": 5.389241123199463,
|
|
"epoch": 4.041799182189914,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0003803466727232811,
|
|
"loss": 4.9562,
|
|
"mean_token_accuracy": 0.18940048962831496,
|
|
"num_tokens": 9210981.0,
|
|
"step": 4450
|
|
},
|
|
{
|
|
"entropy": 5.399062252044677,
|
|
"epoch": 4.046342571558383,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0003800342463003383,
|
|
"loss": 4.9573,
|
|
"mean_token_accuracy": 0.1964713454246521,
|
|
"num_tokens": 9221582.0,
|
|
"step": 4455
|
|
},
|
|
{
|
|
"entropy": 5.462539577484131,
|
|
"epoch": 4.050885960926851,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00037972156071583386,
|
|
"loss": 5.0981,
|
|
"mean_token_accuracy": 0.17974426448345185,
|
|
"num_tokens": 9233382.0,
|
|
"step": 4460
|
|
},
|
|
{
|
|
"entropy": 5.388675832748413,
|
|
"epoch": 4.05542935029532,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0003794086167412884,
|
|
"loss": 4.996,
|
|
"mean_token_accuracy": 0.18684257566928864,
|
|
"num_tokens": 9243966.0,
|
|
"step": 4465
|
|
},
|
|
{
|
|
"entropy": 5.440121650695801,
|
|
"epoch": 4.059972739663789,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0003790954151488601,
|
|
"loss": 4.9545,
|
|
"mean_token_accuracy": 0.1884762868285179,
|
|
"num_tokens": 9255042.0,
|
|
"step": 4470
|
|
},
|
|
{
|
|
"entropy": 5.376422595977783,
|
|
"epoch": 4.064516129032258,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0003787819567113427,
|
|
"loss": 5.0144,
|
|
"mean_token_accuracy": 0.17815936505794525,
|
|
"num_tokens": 9266370.0,
|
|
"step": 4475
|
|
},
|
|
{
|
|
"entropy": 5.380577611923218,
|
|
"epoch": 4.069059518400727,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0003784682422021638,
|
|
"loss": 4.9745,
|
|
"mean_token_accuracy": 0.1958342671394348,
|
|
"num_tokens": 9276407.0,
|
|
"step": 4480
|
|
},
|
|
{
|
|
"entropy": 5.359003400802612,
|
|
"epoch": 4.073602907769196,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 0.0003781542723953828,
|
|
"loss": 4.9393,
|
|
"mean_token_accuracy": 0.19430035948753357,
|
|
"num_tokens": 9286059.0,
|
|
"step": 4485
|
|
},
|
|
{
|
|
"entropy": 5.390214967727661,
|
|
"epoch": 4.078146297137665,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.00037784004806568885,
|
|
"loss": 4.9713,
|
|
"mean_token_accuracy": 0.1892659679055214,
|
|
"num_tokens": 9296453.0,
|
|
"step": 4490
|
|
},
|
|
{
|
|
"entropy": 5.400541591644287,
|
|
"epoch": 4.082689686506134,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00037752556998839934,
|
|
"loss": 5.0465,
|
|
"mean_token_accuracy": 0.18000573962926864,
|
|
"num_tokens": 9307081.0,
|
|
"step": 4495
|
|
},
|
|
{
|
|
"entropy": 5.357937574386597,
|
|
"epoch": 4.087233075874602,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0003772108389394576,
|
|
"loss": 4.9592,
|
|
"mean_token_accuracy": 0.19790471643209456,
|
|
"num_tokens": 9317442.0,
|
|
"step": 4500
|
|
},
|
|
{
|
|
"entropy": 5.363749885559082,
|
|
"epoch": 4.091776465243071,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.00037689585569543137,
|
|
"loss": 5.0778,
|
|
"mean_token_accuracy": 0.18445213735103608,
|
|
"num_tokens": 9327994.0,
|
|
"step": 4505
|
|
},
|
|
{
|
|
"entropy": 5.4291106224060055,
|
|
"epoch": 4.09631985461154,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0003765806210335103,
|
|
"loss": 4.9886,
|
|
"mean_token_accuracy": 0.19103595465421677,
|
|
"num_tokens": 9337936.0,
|
|
"step": 4510
|
|
},
|
|
{
|
|
"entropy": 5.430002164840698,
|
|
"epoch": 4.100863243980009,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.00037626513573150473,
|
|
"loss": 4.9719,
|
|
"mean_token_accuracy": 0.18540833592414857,
|
|
"num_tokens": 9347414.0,
|
|
"step": 4515
|
|
},
|
|
{
|
|
"entropy": 5.369181394577026,
|
|
"epoch": 4.105406633348478,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00037594940056784315,
|
|
"loss": 5.0515,
|
|
"mean_token_accuracy": 0.1840366616845131,
|
|
"num_tokens": 9358189.0,
|
|
"step": 4520
|
|
},
|
|
{
|
|
"entropy": 5.3340929508209225,
|
|
"epoch": 4.109950022716947,
|
|
"grad_norm": 2.359375,
|
|
"learning_rate": 0.0003756334163215708,
|
|
"loss": 4.9668,
|
|
"mean_token_accuracy": 0.1893339291214943,
|
|
"num_tokens": 9368511.0,
|
|
"step": 4525
|
|
},
|
|
{
|
|
"entropy": 5.384105968475342,
|
|
"epoch": 4.114493412085416,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.00037531718377234723,
|
|
"loss": 4.9306,
|
|
"mean_token_accuracy": 0.1926949754357338,
|
|
"num_tokens": 9379115.0,
|
|
"step": 4530
|
|
},
|
|
{
|
|
"entropy": 5.31406307220459,
|
|
"epoch": 4.119036801453885,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0003750007037004451,
|
|
"loss": 4.9476,
|
|
"mean_token_accuracy": 0.18703602403402328,
|
|
"num_tokens": 9389554.0,
|
|
"step": 4535
|
|
},
|
|
{
|
|
"entropy": 5.349987411499024,
|
|
"epoch": 4.123580190822353,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0003746839768867473,
|
|
"loss": 4.9999,
|
|
"mean_token_accuracy": 0.19675760269165038,
|
|
"num_tokens": 9399466.0,
|
|
"step": 4540
|
|
},
|
|
{
|
|
"entropy": 5.416618347167969,
|
|
"epoch": 4.128123580190822,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0003743670041127458,
|
|
"loss": 4.9555,
|
|
"mean_token_accuracy": 0.19103783071041108,
|
|
"num_tokens": 9409607.0,
|
|
"step": 4545
|
|
},
|
|
{
|
|
"entropy": 5.3814984321594235,
|
|
"epoch": 4.132666969559291,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0003740497861605395,
|
|
"loss": 5.0207,
|
|
"mean_token_accuracy": 0.1879616990685463,
|
|
"num_tokens": 9420084.0,
|
|
"step": 4550
|
|
},
|
|
{
|
|
"entropy": 5.41513991355896,
|
|
"epoch": 4.13721035892776,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.000373732323812832,
|
|
"loss": 5.0052,
|
|
"mean_token_accuracy": 0.18005961179733276,
|
|
"num_tokens": 9430960.0,
|
|
"step": 4555
|
|
},
|
|
{
|
|
"entropy": 5.393219661712647,
|
|
"epoch": 4.141753748296229,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.00037341461785293025,
|
|
"loss": 4.9796,
|
|
"mean_token_accuracy": 0.19567920565605162,
|
|
"num_tokens": 9441433.0,
|
|
"step": 4560
|
|
},
|
|
{
|
|
"entropy": 5.363883590698242,
|
|
"epoch": 4.146297137664698,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0003730966690647421,
|
|
"loss": 5.0548,
|
|
"mean_token_accuracy": 0.18693674504756927,
|
|
"num_tokens": 9451721.0,
|
|
"step": 4565
|
|
},
|
|
{
|
|
"entropy": 5.373025512695312,
|
|
"epoch": 4.150840527033167,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.00037277847823277444,
|
|
"loss": 4.9932,
|
|
"mean_token_accuracy": 0.18778621703386306,
|
|
"num_tokens": 9461892.0,
|
|
"step": 4570
|
|
},
|
|
{
|
|
"entropy": 5.461536979675293,
|
|
"epoch": 4.155383916401636,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.00037246004614213164,
|
|
"loss": 4.9869,
|
|
"mean_token_accuracy": 0.19366397708654404,
|
|
"num_tokens": 9471959.0,
|
|
"step": 4575
|
|
},
|
|
{
|
|
"entropy": 5.356639814376831,
|
|
"epoch": 4.159927305770104,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0003721413735785132,
|
|
"loss": 4.9722,
|
|
"mean_token_accuracy": 0.19820376485586166,
|
|
"num_tokens": 9482630.0,
|
|
"step": 4580
|
|
},
|
|
{
|
|
"entropy": 5.337252283096314,
|
|
"epoch": 4.164470695138573,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.000371822461328212,
|
|
"loss": 4.9653,
|
|
"mean_token_accuracy": 0.1953589841723442,
|
|
"num_tokens": 9492804.0,
|
|
"step": 4585
|
|
},
|
|
{
|
|
"entropy": 5.420544052124024,
|
|
"epoch": 4.169014084507042,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.00037150331017811233,
|
|
"loss": 5.0403,
|
|
"mean_token_accuracy": 0.19014741778373717,
|
|
"num_tokens": 9502610.0,
|
|
"step": 4590
|
|
},
|
|
{
|
|
"entropy": 5.371463108062744,
|
|
"epoch": 4.173557473875511,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0003711839209156878,
|
|
"loss": 4.9747,
|
|
"mean_token_accuracy": 0.18912022709846496,
|
|
"num_tokens": 9512338.0,
|
|
"step": 4595
|
|
},
|
|
{
|
|
"entropy": 5.33294906616211,
|
|
"epoch": 4.17810086324398,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0003708642943289999,
|
|
"loss": 4.9271,
|
|
"mean_token_accuracy": 0.19705564081668853,
|
|
"num_tokens": 9522510.0,
|
|
"step": 4600
|
|
},
|
|
{
|
|
"entropy": 5.3216564655303955,
|
|
"epoch": 4.182644252612449,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0003705444312066953,
|
|
"loss": 4.9582,
|
|
"mean_token_accuracy": 0.18852249681949615,
|
|
"num_tokens": 9533289.0,
|
|
"step": 4605
|
|
},
|
|
{
|
|
"entropy": 5.302569723129272,
|
|
"epoch": 4.187187641980918,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0003702243323380045,
|
|
"loss": 4.9453,
|
|
"mean_token_accuracy": 0.1895934149622917,
|
|
"num_tokens": 9543713.0,
|
|
"step": 4610
|
|
},
|
|
{
|
|
"entropy": 5.350919580459594,
|
|
"epoch": 4.191731031349387,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.00036990399851273965,
|
|
"loss": 4.9438,
|
|
"mean_token_accuracy": 0.19295375645160676,
|
|
"num_tokens": 9553752.0,
|
|
"step": 4615
|
|
},
|
|
{
|
|
"entropy": 5.338162994384765,
|
|
"epoch": 4.196274420717856,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0003695834305212925,
|
|
"loss": 4.9803,
|
|
"mean_token_accuracy": 0.1936208724975586,
|
|
"num_tokens": 9563938.0,
|
|
"step": 4620
|
|
},
|
|
{
|
|
"entropy": 5.3507099628448485,
|
|
"epoch": 4.200817810086324,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.00036926262915463294,
|
|
"loss": 4.9844,
|
|
"mean_token_accuracy": 0.18736658841371537,
|
|
"num_tokens": 9573688.0,
|
|
"step": 4625
|
|
},
|
|
{
|
|
"entropy": 5.367381000518799,
|
|
"epoch": 4.205361199454793,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00036894159520430616,
|
|
"loss": 4.953,
|
|
"mean_token_accuracy": 0.19540759027004242,
|
|
"num_tokens": 9583821.0,
|
|
"step": 4630
|
|
},
|
|
{
|
|
"entropy": 5.426737308502197,
|
|
"epoch": 4.209904588823262,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.00036862032946243173,
|
|
"loss": 4.9396,
|
|
"mean_token_accuracy": 0.19043983221054078,
|
|
"num_tokens": 9593244.0,
|
|
"step": 4635
|
|
},
|
|
{
|
|
"entropy": 5.285001516342163,
|
|
"epoch": 4.214447978191731,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00036829883272170087,
|
|
"loss": 4.9295,
|
|
"mean_token_accuracy": 0.19546271562576295,
|
|
"num_tokens": 9603338.0,
|
|
"step": 4640
|
|
},
|
|
{
|
|
"entropy": 5.367602300643921,
|
|
"epoch": 4.2189913675602,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.00036797710577537486,
|
|
"loss": 5.0628,
|
|
"mean_token_accuracy": 0.18692491948604584,
|
|
"num_tokens": 9614598.0,
|
|
"step": 4645
|
|
},
|
|
{
|
|
"entropy": 5.42457127571106,
|
|
"epoch": 4.223534756928669,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00036765514941728295,
|
|
"loss": 4.9841,
|
|
"mean_token_accuracy": 0.18504495769739152,
|
|
"num_tokens": 9625236.0,
|
|
"step": 4650
|
|
},
|
|
{
|
|
"entropy": 5.404557895660401,
|
|
"epoch": 4.228078146297138,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0003673329644418204,
|
|
"loss": 4.9747,
|
|
"mean_token_accuracy": 0.19604744464159013,
|
|
"num_tokens": 9636186.0,
|
|
"step": 4655
|
|
},
|
|
{
|
|
"entropy": 5.2663177967071535,
|
|
"epoch": 4.232621535665607,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.00036701055164394664,
|
|
"loss": 4.9372,
|
|
"mean_token_accuracy": 0.19671034216880798,
|
|
"num_tokens": 9644996.0,
|
|
"step": 4660
|
|
},
|
|
{
|
|
"entropy": 5.333033418655395,
|
|
"epoch": 4.237164925034075,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.00036668791181918313,
|
|
"loss": 4.9989,
|
|
"mean_token_accuracy": 0.1984211429953575,
|
|
"num_tokens": 9655602.0,
|
|
"step": 4665
|
|
},
|
|
{
|
|
"entropy": 5.322667598724365,
|
|
"epoch": 4.241708314402544,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0003663650457636117,
|
|
"loss": 4.9812,
|
|
"mean_token_accuracy": 0.19847874939441681,
|
|
"num_tokens": 9666575.0,
|
|
"step": 4670
|
|
},
|
|
{
|
|
"entropy": 5.37543625831604,
|
|
"epoch": 4.246251703771013,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0003660419542738722,
|
|
"loss": 5.0167,
|
|
"mean_token_accuracy": 0.18761178255081176,
|
|
"num_tokens": 9677540.0,
|
|
"step": 4675
|
|
},
|
|
{
|
|
"entropy": 5.392806434631348,
|
|
"epoch": 4.250795093139482,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0003657186381471608,
|
|
"loss": 5.0186,
|
|
"mean_token_accuracy": 0.19178631156682968,
|
|
"num_tokens": 9687406.0,
|
|
"step": 4680
|
|
},
|
|
{
|
|
"entropy": 5.332634353637696,
|
|
"epoch": 4.255338482507951,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00036539509818122765,
|
|
"loss": 5.0075,
|
|
"mean_token_accuracy": 0.1853974550962448,
|
|
"num_tokens": 9697303.0,
|
|
"step": 4685
|
|
},
|
|
{
|
|
"entropy": 5.410250473022461,
|
|
"epoch": 4.25988187187642,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0003650713351743758,
|
|
"loss": 5.0332,
|
|
"mean_token_accuracy": 0.19208229184150696,
|
|
"num_tokens": 9707113.0,
|
|
"step": 4690
|
|
},
|
|
{
|
|
"entropy": 5.393611860275269,
|
|
"epoch": 4.264425261244889,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0003647473499254581,
|
|
"loss": 4.9591,
|
|
"mean_token_accuracy": 0.1875597596168518,
|
|
"num_tokens": 9717288.0,
|
|
"step": 4695
|
|
},
|
|
{
|
|
"entropy": 5.332955265045166,
|
|
"epoch": 4.268968650613358,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.000364423143233876,
|
|
"loss": 4.8476,
|
|
"mean_token_accuracy": 0.20174643248319626,
|
|
"num_tokens": 9728073.0,
|
|
"step": 4700
|
|
},
|
|
{
|
|
"entropy": 5.280930471420288,
|
|
"epoch": 4.273512039981826,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.00036409871589957723,
|
|
"loss": 4.8409,
|
|
"mean_token_accuracy": 0.20191654562950134,
|
|
"num_tokens": 9737199.0,
|
|
"step": 4705
|
|
},
|
|
{
|
|
"entropy": 5.265670442581177,
|
|
"epoch": 4.278055429350295,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.000363774068723054,
|
|
"loss": 4.9919,
|
|
"mean_token_accuracy": 0.19121912717819214,
|
|
"num_tokens": 9747710.0,
|
|
"step": 4710
|
|
},
|
|
{
|
|
"entropy": 5.346691417694092,
|
|
"epoch": 4.282598818718764,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.00036344920250534106,
|
|
"loss": 5.0264,
|
|
"mean_token_accuracy": 0.19124362319707872,
|
|
"num_tokens": 9758721.0,
|
|
"step": 4715
|
|
},
|
|
{
|
|
"entropy": 5.434129095077514,
|
|
"epoch": 4.287142208087233,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0003631241180480133,
|
|
"loss": 4.9984,
|
|
"mean_token_accuracy": 0.18652019500732422,
|
|
"num_tokens": 9769487.0,
|
|
"step": 4720
|
|
},
|
|
{
|
|
"entropy": 5.375432920455933,
|
|
"epoch": 4.291685597455702,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0003627988161531845,
|
|
"loss": 5.0461,
|
|
"mean_token_accuracy": 0.18744058012962342,
|
|
"num_tokens": 9780429.0,
|
|
"step": 4725
|
|
},
|
|
{
|
|
"entropy": 5.320342206954956,
|
|
"epoch": 4.296228986824171,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0003624732976235046,
|
|
"loss": 4.9409,
|
|
"mean_token_accuracy": 0.195818193256855,
|
|
"num_tokens": 9790156.0,
|
|
"step": 4730
|
|
},
|
|
{
|
|
"entropy": 5.36504898071289,
|
|
"epoch": 4.30077237619264,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0003621475632621584,
|
|
"loss": 4.9897,
|
|
"mean_token_accuracy": 0.19361872971057892,
|
|
"num_tokens": 9800217.0,
|
|
"step": 4735
|
|
},
|
|
{
|
|
"entropy": 5.400382137298584,
|
|
"epoch": 4.305315765561109,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0003618216138728627,
|
|
"loss": 5.062,
|
|
"mean_token_accuracy": 0.1856027588248253,
|
|
"num_tokens": 9811275.0,
|
|
"step": 4740
|
|
},
|
|
{
|
|
"entropy": 5.274557828903198,
|
|
"epoch": 4.309859154929577,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.00036149545025986567,
|
|
"loss": 4.9083,
|
|
"mean_token_accuracy": 0.20112839490175247,
|
|
"num_tokens": 9821409.0,
|
|
"step": 4745
|
|
},
|
|
{
|
|
"entropy": 5.381450986862182,
|
|
"epoch": 4.314402544298046,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00036116907322794335,
|
|
"loss": 5.0234,
|
|
"mean_token_accuracy": 0.18458011895418167,
|
|
"num_tokens": 9832674.0,
|
|
"step": 4750
|
|
},
|
|
{
|
|
"entropy": 5.452517032623291,
|
|
"epoch": 4.318945933666515,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00036084248358239857,
|
|
"loss": 5.0538,
|
|
"mean_token_accuracy": 0.18491816967725755,
|
|
"num_tokens": 9844076.0,
|
|
"step": 4755
|
|
},
|
|
{
|
|
"entropy": 5.390411710739135,
|
|
"epoch": 4.323489323034984,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.00036051568212905897,
|
|
"loss": 5.0579,
|
|
"mean_token_accuracy": 0.18977658003568648,
|
|
"num_tokens": 9854147.0,
|
|
"step": 4760
|
|
},
|
|
{
|
|
"entropy": 5.338499689102173,
|
|
"epoch": 4.328032712403453,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.0003601886696742745,
|
|
"loss": 5.0351,
|
|
"mean_token_accuracy": 0.18919701427221297,
|
|
"num_tokens": 9864926.0,
|
|
"step": 4765
|
|
},
|
|
{
|
|
"entropy": 5.36517014503479,
|
|
"epoch": 4.332576101771922,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.000359861447024916,
|
|
"loss": 4.9414,
|
|
"mean_token_accuracy": 0.19574884176254273,
|
|
"num_tokens": 9875039.0,
|
|
"step": 4770
|
|
},
|
|
{
|
|
"entropy": 5.446039152145386,
|
|
"epoch": 4.337119491140391,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 0.00035953401498837285,
|
|
"loss": 5.1017,
|
|
"mean_token_accuracy": 0.1865892991423607,
|
|
"num_tokens": 9885132.0,
|
|
"step": 4775
|
|
},
|
|
{
|
|
"entropy": 5.378859043121338,
|
|
"epoch": 4.34166288050886,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.00035920637437255096,
|
|
"loss": 4.879,
|
|
"mean_token_accuracy": 0.21089768409729004,
|
|
"num_tokens": 9895419.0,
|
|
"step": 4780
|
|
},
|
|
{
|
|
"entropy": 5.36444845199585,
|
|
"epoch": 4.346206269877328,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.000358878525985871,
|
|
"loss": 5.0491,
|
|
"mean_token_accuracy": 0.1867358237504959,
|
|
"num_tokens": 9905024.0,
|
|
"step": 4785
|
|
},
|
|
{
|
|
"entropy": 5.3888145923614506,
|
|
"epoch": 4.350749659245797,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0003585504706372663,
|
|
"loss": 4.9795,
|
|
"mean_token_accuracy": 0.19860973358154296,
|
|
"num_tokens": 9915386.0,
|
|
"step": 4790
|
|
},
|
|
{
|
|
"entropy": 5.358844757080078,
|
|
"epoch": 4.355293048614266,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0003582222091361808,
|
|
"loss": 4.955,
|
|
"mean_token_accuracy": 0.20420272499322892,
|
|
"num_tokens": 9924647.0,
|
|
"step": 4795
|
|
},
|
|
{
|
|
"entropy": 5.3580591678619385,
|
|
"epoch": 4.359836437982735,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0003578937422925671,
|
|
"loss": 5.0369,
|
|
"mean_token_accuracy": 0.18615963757038118,
|
|
"num_tokens": 9934848.0,
|
|
"step": 4800
|
|
},
|
|
{
|
|
"entropy": 5.407044267654419,
|
|
"epoch": 4.364379827351204,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.0003575650709168846,
|
|
"loss": 5.004,
|
|
"mean_token_accuracy": 0.18749181032180787,
|
|
"num_tokens": 9945032.0,
|
|
"step": 4805
|
|
},
|
|
{
|
|
"entropy": 5.349762296676635,
|
|
"epoch": 4.368923216719673,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.00035723619582009715,
|
|
"loss": 4.9866,
|
|
"mean_token_accuracy": 0.18728580921888352,
|
|
"num_tokens": 9955026.0,
|
|
"step": 4810
|
|
},
|
|
{
|
|
"entropy": 5.373504734039306,
|
|
"epoch": 4.373466606088142,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.00035690711781367137,
|
|
"loss": 4.9895,
|
|
"mean_token_accuracy": 0.1904720187187195,
|
|
"num_tokens": 9965894.0,
|
|
"step": 4815
|
|
},
|
|
{
|
|
"entropy": 5.305029821395874,
|
|
"epoch": 4.378009995456611,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0003565778377095744,
|
|
"loss": 4.9736,
|
|
"mean_token_accuracy": 0.19106718003749848,
|
|
"num_tokens": 9976263.0,
|
|
"step": 4820
|
|
},
|
|
{
|
|
"entropy": 5.24720139503479,
|
|
"epoch": 4.38255338482508,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0003562483563202724,
|
|
"loss": 4.872,
|
|
"mean_token_accuracy": 0.1990128666162491,
|
|
"num_tokens": 9986197.0,
|
|
"step": 4825
|
|
},
|
|
{
|
|
"entropy": 5.286457586288452,
|
|
"epoch": 4.387096774193548,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.00035591867445872784,
|
|
"loss": 4.9646,
|
|
"mean_token_accuracy": 0.18578277081251143,
|
|
"num_tokens": 9996147.0,
|
|
"step": 4830
|
|
},
|
|
{
|
|
"entropy": 5.381393194198608,
|
|
"epoch": 4.391640163562017,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.000355588792938398,
|
|
"loss": 5.0142,
|
|
"mean_token_accuracy": 0.1932905599474907,
|
|
"num_tokens": 10006413.0,
|
|
"step": 4835
|
|
},
|
|
{
|
|
"entropy": 5.4062848567962645,
|
|
"epoch": 4.396183552930486,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0003552587125732326,
|
|
"loss": 4.9406,
|
|
"mean_token_accuracy": 0.19311447590589523,
|
|
"num_tokens": 10016002.0,
|
|
"step": 4840
|
|
},
|
|
{
|
|
"entropy": 5.348485279083252,
|
|
"epoch": 4.400726942298955,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.00035492843417767224,
|
|
"loss": 5.0293,
|
|
"mean_token_accuracy": 0.19068242758512496,
|
|
"num_tokens": 10026490.0,
|
|
"step": 4845
|
|
},
|
|
{
|
|
"entropy": 5.368588876724243,
|
|
"epoch": 4.405270331667424,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.000354597958566646,
|
|
"loss": 4.9738,
|
|
"mean_token_accuracy": 0.19240988045930862,
|
|
"num_tokens": 10036942.0,
|
|
"step": 4850
|
|
},
|
|
{
|
|
"entropy": 5.260595369338989,
|
|
"epoch": 4.409813721035893,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.00035426728655556954,
|
|
"loss": 4.9714,
|
|
"mean_token_accuracy": 0.19440948218107224,
|
|
"num_tokens": 10047045.0,
|
|
"step": 4855
|
|
},
|
|
{
|
|
"entropy": 5.369774532318115,
|
|
"epoch": 4.414357110404362,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0003539364189603433,
|
|
"loss": 4.9453,
|
|
"mean_token_accuracy": 0.19212349355220795,
|
|
"num_tokens": 10056946.0,
|
|
"step": 4860
|
|
},
|
|
{
|
|
"entropy": 5.326255846023559,
|
|
"epoch": 4.418900499772831,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.00035360535659735006,
|
|
"loss": 5.0647,
|
|
"mean_token_accuracy": 0.1883133053779602,
|
|
"num_tokens": 10067450.0,
|
|
"step": 4865
|
|
},
|
|
{
|
|
"entropy": 5.366024351119995,
|
|
"epoch": 4.423443889141299,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0003532741002834534,
|
|
"loss": 5.0077,
|
|
"mean_token_accuracy": 0.18956485241651536,
|
|
"num_tokens": 10078052.0,
|
|
"step": 4870
|
|
},
|
|
{
|
|
"entropy": 5.37428650856018,
|
|
"epoch": 4.427987278509768,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.00035294265083599526,
|
|
"loss": 5.0325,
|
|
"mean_token_accuracy": 0.183209627866745,
|
|
"num_tokens": 10089190.0,
|
|
"step": 4875
|
|
},
|
|
{
|
|
"entropy": 5.308315467834473,
|
|
"epoch": 4.432530667878237,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0003526110090727942,
|
|
"loss": 4.9582,
|
|
"mean_token_accuracy": 0.19284679144620895,
|
|
"num_tokens": 10099629.0,
|
|
"step": 4880
|
|
},
|
|
{
|
|
"entropy": 5.363161993026734,
|
|
"epoch": 4.437074057246706,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0003522791758121434,
|
|
"loss": 5.0181,
|
|
"mean_token_accuracy": 0.19046489000320435,
|
|
"num_tokens": 10109902.0,
|
|
"step": 4885
|
|
},
|
|
{
|
|
"entropy": 5.404345464706421,
|
|
"epoch": 4.441617446615175,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00035194715187280835,
|
|
"loss": 4.9485,
|
|
"mean_token_accuracy": 0.19603970199823378,
|
|
"num_tokens": 10120058.0,
|
|
"step": 4890
|
|
},
|
|
{
|
|
"entropy": 5.377800989151001,
|
|
"epoch": 4.446160835983644,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0003516149380740252,
|
|
"loss": 4.9897,
|
|
"mean_token_accuracy": 0.18937026411294938,
|
|
"num_tokens": 10131091.0,
|
|
"step": 4895
|
|
},
|
|
{
|
|
"entropy": 5.307609891891479,
|
|
"epoch": 4.450704225352113,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0003512825352354983,
|
|
"loss": 4.9659,
|
|
"mean_token_accuracy": 0.1857193574309349,
|
|
"num_tokens": 10141370.0,
|
|
"step": 4900
|
|
},
|
|
{
|
|
"entropy": 5.322268486022949,
|
|
"epoch": 4.455247614720582,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.00035094994417739884,
|
|
"loss": 4.9215,
|
|
"mean_token_accuracy": 0.20073866993188857,
|
|
"num_tokens": 10151457.0,
|
|
"step": 4905
|
|
},
|
|
{
|
|
"entropy": 5.332928895950317,
|
|
"epoch": 4.45979100408905,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.000350617165720362,
|
|
"loss": 4.9808,
|
|
"mean_token_accuracy": 0.18821330964565278,
|
|
"num_tokens": 10160984.0,
|
|
"step": 4910
|
|
},
|
|
{
|
|
"entropy": 5.394413328170776,
|
|
"epoch": 4.464334393457519,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.00035028420068548567,
|
|
"loss": 5.041,
|
|
"mean_token_accuracy": 0.18793283849954606,
|
|
"num_tokens": 10171991.0,
|
|
"step": 4915
|
|
},
|
|
{
|
|
"entropy": 5.342994832992554,
|
|
"epoch": 4.468877782825988,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0003499510498943279,
|
|
"loss": 5.0112,
|
|
"mean_token_accuracy": 0.19039562493562698,
|
|
"num_tokens": 10183537.0,
|
|
"step": 4920
|
|
},
|
|
{
|
|
"entropy": 5.37651252746582,
|
|
"epoch": 4.473421172194457,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.00034961771416890526,
|
|
"loss": 5.0093,
|
|
"mean_token_accuracy": 0.19253278970718385,
|
|
"num_tokens": 10193639.0,
|
|
"step": 4925
|
|
},
|
|
{
|
|
"entropy": 5.350864124298096,
|
|
"epoch": 4.477964561562926,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.0003492841943316903,
|
|
"loss": 5.034,
|
|
"mean_token_accuracy": 0.18480442464351654,
|
|
"num_tokens": 10203264.0,
|
|
"step": 4930
|
|
},
|
|
{
|
|
"entropy": 5.406899738311767,
|
|
"epoch": 4.482507950931395,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0003489504912056103,
|
|
"loss": 4.95,
|
|
"mean_token_accuracy": 0.1981717735528946,
|
|
"num_tokens": 10213364.0,
|
|
"step": 4935
|
|
},
|
|
{
|
|
"entropy": 5.399414825439453,
|
|
"epoch": 4.487051340299864,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0003486166056140445,
|
|
"loss": 5.0232,
|
|
"mean_token_accuracy": 0.18794037401676178,
|
|
"num_tokens": 10224168.0,
|
|
"step": 4940
|
|
},
|
|
{
|
|
"entropy": 5.406442070007325,
|
|
"epoch": 4.491594729668333,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.00034828253838082223,
|
|
"loss": 5.0685,
|
|
"mean_token_accuracy": 0.18398260325193405,
|
|
"num_tokens": 10235014.0,
|
|
"step": 4945
|
|
},
|
|
{
|
|
"entropy": 5.371935796737671,
|
|
"epoch": 4.496138119036801,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00034794829033022134,
|
|
"loss": 5.0886,
|
|
"mean_token_accuracy": 0.18309501111507415,
|
|
"num_tokens": 10246869.0,
|
|
"step": 4950
|
|
},
|
|
{
|
|
"entropy": 5.36165976524353,
|
|
"epoch": 4.50068150840527,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0003476138622869657,
|
|
"loss": 4.9015,
|
|
"mean_token_accuracy": 0.20478581488132477,
|
|
"num_tokens": 10256590.0,
|
|
"step": 4955
|
|
},
|
|
{
|
|
"entropy": 5.3876629829406735,
|
|
"epoch": 4.505224897773739,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0003472792550762232,
|
|
"loss": 5.0999,
|
|
"mean_token_accuracy": 0.18458822518587112,
|
|
"num_tokens": 10267472.0,
|
|
"step": 4960
|
|
},
|
|
{
|
|
"entropy": 5.379286766052246,
|
|
"epoch": 4.509768287142208,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0003469444695236038,
|
|
"loss": 5.0147,
|
|
"mean_token_accuracy": 0.18269276171922683,
|
|
"num_tokens": 10277827.0,
|
|
"step": 4965
|
|
},
|
|
{
|
|
"entropy": 5.400478553771973,
|
|
"epoch": 4.514311676510677,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.00034660950645515765,
|
|
"loss": 5.015,
|
|
"mean_token_accuracy": 0.1988950252532959,
|
|
"num_tokens": 10288630.0,
|
|
"step": 4970
|
|
},
|
|
{
|
|
"entropy": 5.289052486419678,
|
|
"epoch": 4.518855065879146,
|
|
"grad_norm": 3.125,
|
|
"learning_rate": 0.0003462743666973728,
|
|
"loss": 4.963,
|
|
"mean_token_accuracy": 0.19424212276935576,
|
|
"num_tokens": 10298301.0,
|
|
"step": 4975
|
|
},
|
|
{
|
|
"entropy": 5.327270984649658,
|
|
"epoch": 4.523398455247615,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0003459390510771734,
|
|
"loss": 4.9079,
|
|
"mean_token_accuracy": 0.19313258677721024,
|
|
"num_tokens": 10309622.0,
|
|
"step": 4980
|
|
},
|
|
{
|
|
"entropy": 5.3962116718292235,
|
|
"epoch": 4.527941844616084,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0003456035604219172,
|
|
"loss": 5.0351,
|
|
"mean_token_accuracy": 0.18926991224288942,
|
|
"num_tokens": 10319400.0,
|
|
"step": 4985
|
|
},
|
|
{
|
|
"entropy": 5.329410648345947,
|
|
"epoch": 4.532485233984552,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.0003452678955593942,
|
|
"loss": 5.0049,
|
|
"mean_token_accuracy": 0.19311991930007935,
|
|
"num_tokens": 10329639.0,
|
|
"step": 4990
|
|
},
|
|
{
|
|
"entropy": 5.372669506072998,
|
|
"epoch": 4.537028623353021,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.000344932057317824,
|
|
"loss": 5.0671,
|
|
"mean_token_accuracy": 0.18275750130414964,
|
|
"num_tokens": 10340276.0,
|
|
"step": 4995
|
|
},
|
|
{
|
|
"entropy": 5.45879635810852,
|
|
"epoch": 4.54157201272149,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0003445960465258542,
|
|
"loss": 4.9377,
|
|
"mean_token_accuracy": 0.19943904131650925,
|
|
"num_tokens": 10350280.0,
|
|
"step": 5000
|
|
},
|
|
{
|
|
"epoch": 4.54157201272149,
|
|
"eval_entropy": 5.303881861442743,
|
|
"eval_loss": 5.7956342697143555,
|
|
"eval_mean_token_accuracy": 0.16387990669802177,
|
|
"eval_num_tokens": 10350280.0,
|
|
"eval_runtime": 2.5876,
|
|
"eval_samples_per_second": 1327.493,
|
|
"eval_steps_per_second": 166.178,
|
|
"step": 5000
|
|
},
|
|
{
|
|
"entropy": 5.3635515689849855,
|
|
"epoch": 4.546115402089959,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0003442598640125578,
|
|
"loss": 5.0659,
|
|
"mean_token_accuracy": 0.18127573132514954,
|
|
"num_tokens": 10360843.0,
|
|
"step": 5005
|
|
},
|
|
{
|
|
"entropy": 5.340345048904419,
|
|
"epoch": 4.550658791458428,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.000343923510607432,
|
|
"loss": 5.0682,
|
|
"mean_token_accuracy": 0.18878625184297562,
|
|
"num_tokens": 10370538.0,
|
|
"step": 5010
|
|
},
|
|
{
|
|
"entropy": 5.35289421081543,
|
|
"epoch": 4.555202180826897,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0003435869871403952,
|
|
"loss": 4.9749,
|
|
"mean_token_accuracy": 0.19000385701656342,
|
|
"num_tokens": 10380202.0,
|
|
"step": 5015
|
|
},
|
|
{
|
|
"entropy": 5.39669885635376,
|
|
"epoch": 4.559745570195366,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.00034325029444178565,
|
|
"loss": 5.0013,
|
|
"mean_token_accuracy": 0.1956571713089943,
|
|
"num_tokens": 10389938.0,
|
|
"step": 5020
|
|
},
|
|
{
|
|
"entropy": 5.37724986076355,
|
|
"epoch": 4.564288959563835,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.00034291343334235915,
|
|
"loss": 4.9879,
|
|
"mean_token_accuracy": 0.19516463726758956,
|
|
"num_tokens": 10399661.0,
|
|
"step": 5025
|
|
},
|
|
{
|
|
"entropy": 5.38032636642456,
|
|
"epoch": 4.568832348932304,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0003425764046732869,
|
|
"loss": 4.9662,
|
|
"mean_token_accuracy": 0.1918170765042305,
|
|
"num_tokens": 10409357.0,
|
|
"step": 5030
|
|
},
|
|
{
|
|
"entropy": 5.272043752670288,
|
|
"epoch": 4.573375738300772,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.00034223920926615376,
|
|
"loss": 4.912,
|
|
"mean_token_accuracy": 0.19491752684116365,
|
|
"num_tokens": 10418641.0,
|
|
"step": 5035
|
|
},
|
|
{
|
|
"entropy": 5.3492865562438965,
|
|
"epoch": 4.577919127669241,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.00034190184795295577,
|
|
"loss": 5.0589,
|
|
"mean_token_accuracy": 0.1881226569414139,
|
|
"num_tokens": 10429161.0,
|
|
"step": 5040
|
|
},
|
|
{
|
|
"entropy": 5.3930130958557125,
|
|
"epoch": 4.58246251703771,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.00034156432156609844,
|
|
"loss": 5.0314,
|
|
"mean_token_accuracy": 0.1867027461528778,
|
|
"num_tokens": 10438922.0,
|
|
"step": 5045
|
|
},
|
|
{
|
|
"entropy": 5.352369356155395,
|
|
"epoch": 4.587005906406179,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.00034122663093839466,
|
|
"loss": 4.9497,
|
|
"mean_token_accuracy": 0.19548133611679078,
|
|
"num_tokens": 10448773.0,
|
|
"step": 5050
|
|
},
|
|
{
|
|
"entropy": 5.35884051322937,
|
|
"epoch": 4.591549295774648,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0003408887769030624,
|
|
"loss": 4.9416,
|
|
"mean_token_accuracy": 0.19737975299358368,
|
|
"num_tokens": 10459493.0,
|
|
"step": 5055
|
|
},
|
|
{
|
|
"entropy": 5.361433124542236,
|
|
"epoch": 4.596092685143117,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.000340550760293723,
|
|
"loss": 4.9982,
|
|
"mean_token_accuracy": 0.19219645410776137,
|
|
"num_tokens": 10470390.0,
|
|
"step": 5060
|
|
},
|
|
{
|
|
"entropy": 5.31828088760376,
|
|
"epoch": 4.600636074511586,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.00034021258194439876,
|
|
"loss": 4.9752,
|
|
"mean_token_accuracy": 0.19420106410980226,
|
|
"num_tokens": 10479823.0,
|
|
"step": 5065
|
|
},
|
|
{
|
|
"entropy": 5.448393487930298,
|
|
"epoch": 4.605179463880054,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 0.00033987424268951117,
|
|
"loss": 5.1195,
|
|
"mean_token_accuracy": 0.18326234966516494,
|
|
"num_tokens": 10490364.0,
|
|
"step": 5070
|
|
},
|
|
{
|
|
"entropy": 5.399215459823608,
|
|
"epoch": 4.609722853248523,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.00033953574336387867,
|
|
"loss": 4.9811,
|
|
"mean_token_accuracy": 0.1936163693666458,
|
|
"num_tokens": 10500801.0,
|
|
"step": 5075
|
|
},
|
|
{
|
|
"entropy": 5.312294149398804,
|
|
"epoch": 4.614266242616992,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0003391970848027148,
|
|
"loss": 4.9233,
|
|
"mean_token_accuracy": 0.1946146920323372,
|
|
"num_tokens": 10510481.0,
|
|
"step": 5080
|
|
},
|
|
{
|
|
"entropy": 5.257641172409057,
|
|
"epoch": 4.618809631985461,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.0003388582678416257,
|
|
"loss": 4.9752,
|
|
"mean_token_accuracy": 0.19493146240711212,
|
|
"num_tokens": 10520098.0,
|
|
"step": 5085
|
|
},
|
|
{
|
|
"entropy": 5.391381502151489,
|
|
"epoch": 4.62335302135393,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.00033851929331660876,
|
|
"loss": 5.0618,
|
|
"mean_token_accuracy": 0.18692270815372466,
|
|
"num_tokens": 10530784.0,
|
|
"step": 5090
|
|
},
|
|
{
|
|
"entropy": 5.4522803783416744,
|
|
"epoch": 4.627896410722399,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.00033818016206404983,
|
|
"loss": 5.0267,
|
|
"mean_token_accuracy": 0.1910538747906685,
|
|
"num_tokens": 10540835.0,
|
|
"step": 5095
|
|
},
|
|
{
|
|
"entropy": 5.383860731124878,
|
|
"epoch": 4.632439800090868,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.0003378408749207215,
|
|
"loss": 5.0472,
|
|
"mean_token_accuracy": 0.1850649043917656,
|
|
"num_tokens": 10552239.0,
|
|
"step": 5100
|
|
},
|
|
{
|
|
"entropy": 5.35516095161438,
|
|
"epoch": 4.636983189459337,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0003375014327237812,
|
|
"loss": 5.0082,
|
|
"mean_token_accuracy": 0.1896214097738266,
|
|
"num_tokens": 10563181.0,
|
|
"step": 5105
|
|
},
|
|
{
|
|
"entropy": 5.427487802505493,
|
|
"epoch": 4.641526578827806,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0003371618363107686,
|
|
"loss": 5.0339,
|
|
"mean_token_accuracy": 0.1952664241194725,
|
|
"num_tokens": 10573318.0,
|
|
"step": 5110
|
|
},
|
|
{
|
|
"entropy": 5.4746147155761715,
|
|
"epoch": 4.646069968196274,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00033682208651960444,
|
|
"loss": 5.1195,
|
|
"mean_token_accuracy": 0.17999903708696366,
|
|
"num_tokens": 10585609.0,
|
|
"step": 5115
|
|
},
|
|
{
|
|
"entropy": 5.384831333160401,
|
|
"epoch": 4.650613357564743,
|
|
"grad_norm": 1.9140625,
|
|
"learning_rate": 0.00033648218418858716,
|
|
"loss": 5.0321,
|
|
"mean_token_accuracy": 0.1928780898451805,
|
|
"num_tokens": 10595331.0,
|
|
"step": 5120
|
|
},
|
|
{
|
|
"entropy": 5.369912433624267,
|
|
"epoch": 4.655156746933212,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0003361421301563922,
|
|
"loss": 5.0524,
|
|
"mean_token_accuracy": 0.18236440867185594,
|
|
"num_tokens": 10608116.0,
|
|
"step": 5125
|
|
},
|
|
{
|
|
"entropy": 5.358732509613037,
|
|
"epoch": 4.659700136301681,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0003358019252620691,
|
|
"loss": 5.0226,
|
|
"mean_token_accuracy": 0.1902290776371956,
|
|
"num_tokens": 10618826.0,
|
|
"step": 5130
|
|
},
|
|
{
|
|
"entropy": 5.341248369216919,
|
|
"epoch": 4.66424352567015,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.00033546157034503954,
|
|
"loss": 4.9859,
|
|
"mean_token_accuracy": 0.1937431961297989,
|
|
"num_tokens": 10629225.0,
|
|
"step": 5135
|
|
},
|
|
{
|
|
"entropy": 5.356293535232544,
|
|
"epoch": 4.668786915038619,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0003351210662450955,
|
|
"loss": 4.9807,
|
|
"mean_token_accuracy": 0.19553062617778777,
|
|
"num_tokens": 10640014.0,
|
|
"step": 5140
|
|
},
|
|
{
|
|
"entropy": 5.341473484039307,
|
|
"epoch": 4.673330304407088,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0003347804138023968,
|
|
"loss": 4.9751,
|
|
"mean_token_accuracy": 0.19321381002664567,
|
|
"num_tokens": 10650414.0,
|
|
"step": 5145
|
|
},
|
|
{
|
|
"entropy": 5.325892782211303,
|
|
"epoch": 4.677873693775557,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0003344396138574698,
|
|
"loss": 5.0606,
|
|
"mean_token_accuracy": 0.18831819742918016,
|
|
"num_tokens": 10660172.0,
|
|
"step": 5150
|
|
},
|
|
{
|
|
"entropy": 5.287520408630371,
|
|
"epoch": 4.682417083144026,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0003340986672512042,
|
|
"loss": 4.9484,
|
|
"mean_token_accuracy": 0.19362518042325974,
|
|
"num_tokens": 10670087.0,
|
|
"step": 5155
|
|
},
|
|
{
|
|
"entropy": 5.307422208786011,
|
|
"epoch": 4.686960472512494,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0003337575748248521,
|
|
"loss": 4.9509,
|
|
"mean_token_accuracy": 0.19455549120903015,
|
|
"num_tokens": 10680328.0,
|
|
"step": 5160
|
|
},
|
|
{
|
|
"entropy": 5.373631477355957,
|
|
"epoch": 4.691503861880963,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.00033341633742002503,
|
|
"loss": 4.9819,
|
|
"mean_token_accuracy": 0.19595362544059752,
|
|
"num_tokens": 10690860.0,
|
|
"step": 5165
|
|
},
|
|
{
|
|
"entropy": 5.379030179977417,
|
|
"epoch": 4.696047251249432,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0003330749558786924,
|
|
"loss": 4.9793,
|
|
"mean_token_accuracy": 0.1909372791647911,
|
|
"num_tokens": 10701501.0,
|
|
"step": 5170
|
|
},
|
|
{
|
|
"entropy": 5.342676210403442,
|
|
"epoch": 4.700590640617901,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0003327334310431791,
|
|
"loss": 5.0205,
|
|
"mean_token_accuracy": 0.19347345232963561,
|
|
"num_tokens": 10712155.0,
|
|
"step": 5175
|
|
},
|
|
{
|
|
"entropy": 5.283579397201538,
|
|
"epoch": 4.70513402998637,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0003323917637561638,
|
|
"loss": 4.9378,
|
|
"mean_token_accuracy": 0.19576390087604523,
|
|
"num_tokens": 10721908.0,
|
|
"step": 5180
|
|
},
|
|
{
|
|
"entropy": 5.301788234710694,
|
|
"epoch": 4.709677419354839,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00033204995486067664,
|
|
"loss": 4.9222,
|
|
"mean_token_accuracy": 0.19340729713439941,
|
|
"num_tokens": 10731911.0,
|
|
"step": 5185
|
|
},
|
|
{
|
|
"entropy": 5.314837026596069,
|
|
"epoch": 4.714220808723308,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.00033170800520009703,
|
|
"loss": 4.9262,
|
|
"mean_token_accuracy": 0.19825991690158845,
|
|
"num_tokens": 10741953.0,
|
|
"step": 5190
|
|
},
|
|
{
|
|
"entropy": 5.301791334152222,
|
|
"epoch": 4.718764198091776,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0003313659156181518,
|
|
"loss": 4.998,
|
|
"mean_token_accuracy": 0.1965102270245552,
|
|
"num_tokens": 10752717.0,
|
|
"step": 5195
|
|
},
|
|
{
|
|
"entropy": 5.338494396209716,
|
|
"epoch": 4.723307587460245,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.00033102368695891283,
|
|
"loss": 4.9642,
|
|
"mean_token_accuracy": 0.19066573530435563,
|
|
"num_tokens": 10763584.0,
|
|
"step": 5200
|
|
},
|
|
{
|
|
"entropy": 5.3086809635162355,
|
|
"epoch": 4.727850976828714,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.00033068132006679554,
|
|
"loss": 4.9152,
|
|
"mean_token_accuracy": 0.19494625478982924,
|
|
"num_tokens": 10774727.0,
|
|
"step": 5205
|
|
},
|
|
{
|
|
"entropy": 5.371332788467408,
|
|
"epoch": 4.732394366197183,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.00033033881578655605,
|
|
"loss": 5.0819,
|
|
"mean_token_accuracy": 0.18389152288436889,
|
|
"num_tokens": 10785102.0,
|
|
"step": 5210
|
|
},
|
|
{
|
|
"entropy": 5.416839361190796,
|
|
"epoch": 4.736937755565652,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.0003299961749632898,
|
|
"loss": 4.9924,
|
|
"mean_token_accuracy": 0.1990410193800926,
|
|
"num_tokens": 10795382.0,
|
|
"step": 5215
|
|
},
|
|
{
|
|
"entropy": 5.440488243103028,
|
|
"epoch": 4.741481144934121,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.00032965339844242864,
|
|
"loss": 5.027,
|
|
"mean_token_accuracy": 0.19164412021636962,
|
|
"num_tokens": 10805324.0,
|
|
"step": 5220
|
|
},
|
|
{
|
|
"entropy": 5.352798891067505,
|
|
"epoch": 4.74602453430259,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0003293104870697399,
|
|
"loss": 5.0712,
|
|
"mean_token_accuracy": 0.1856606647372246,
|
|
"num_tokens": 10816589.0,
|
|
"step": 5225
|
|
},
|
|
{
|
|
"entropy": 5.3825188159942625,
|
|
"epoch": 4.750567923671059,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.00032896744169132305,
|
|
"loss": 5.0777,
|
|
"mean_token_accuracy": 0.1869180515408516,
|
|
"num_tokens": 10826622.0,
|
|
"step": 5230
|
|
},
|
|
{
|
|
"entropy": 5.445313167572022,
|
|
"epoch": 4.755111313039528,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0003286242631536087,
|
|
"loss": 5.1028,
|
|
"mean_token_accuracy": 0.18410775065422058,
|
|
"num_tokens": 10836984.0,
|
|
"step": 5235
|
|
},
|
|
{
|
|
"entropy": 5.391966533660889,
|
|
"epoch": 4.759654702407996,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.00032828095230335555,
|
|
"loss": 4.9461,
|
|
"mean_token_accuracy": 0.196729476749897,
|
|
"num_tokens": 10846597.0,
|
|
"step": 5240
|
|
},
|
|
{
|
|
"entropy": 5.3575005531311035,
|
|
"epoch": 4.764198091776465,
|
|
"grad_norm": 1.9453125,
|
|
"learning_rate": 0.0003279375099876491,
|
|
"loss": 5.0585,
|
|
"mean_token_accuracy": 0.18383645564317702,
|
|
"num_tokens": 10857198.0,
|
|
"step": 5245
|
|
},
|
|
{
|
|
"entropy": 5.296354007720947,
|
|
"epoch": 4.768741481144934,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0003275939370538992,
|
|
"loss": 4.9792,
|
|
"mean_token_accuracy": 0.19625834226608277,
|
|
"num_tokens": 10866916.0,
|
|
"step": 5250
|
|
},
|
|
{
|
|
"entropy": 5.33270115852356,
|
|
"epoch": 4.773284870513403,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.00032725023434983767,
|
|
"loss": 4.9564,
|
|
"mean_token_accuracy": 0.19789022952318192,
|
|
"num_tokens": 10876946.0,
|
|
"step": 5255
|
|
},
|
|
{
|
|
"entropy": 5.316235017776489,
|
|
"epoch": 4.777828259881872,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00032690640272351715,
|
|
"loss": 4.9766,
|
|
"mean_token_accuracy": 0.19078431278467178,
|
|
"num_tokens": 10887895.0,
|
|
"step": 5260
|
|
},
|
|
{
|
|
"entropy": 5.283466243743897,
|
|
"epoch": 4.782371649250341,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0003265624430233076,
|
|
"loss": 4.9189,
|
|
"mean_token_accuracy": 0.19831792414188384,
|
|
"num_tokens": 10898597.0,
|
|
"step": 5265
|
|
},
|
|
{
|
|
"entropy": 5.243177890777588,
|
|
"epoch": 4.78691503861881,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0003262183560978956,
|
|
"loss": 4.9293,
|
|
"mean_token_accuracy": 0.20153808891773223,
|
|
"num_tokens": 10908671.0,
|
|
"step": 5270
|
|
},
|
|
{
|
|
"entropy": 5.405533027648926,
|
|
"epoch": 4.791458427987278,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0003258741427962814,
|
|
"loss": 5.0639,
|
|
"mean_token_accuracy": 0.184534552693367,
|
|
"num_tokens": 10920441.0,
|
|
"step": 5275
|
|
},
|
|
{
|
|
"entropy": 5.3325279712677,
|
|
"epoch": 4.796001817355747,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00032552980396777714,
|
|
"loss": 4.9898,
|
|
"mean_token_accuracy": 0.1876162275671959,
|
|
"num_tokens": 10930681.0,
|
|
"step": 5280
|
|
},
|
|
{
|
|
"entropy": 5.337083339691162,
|
|
"epoch": 4.800545206724216,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00032518534046200464,
|
|
"loss": 4.9736,
|
|
"mean_token_accuracy": 0.18869089633226394,
|
|
"num_tokens": 10941819.0,
|
|
"step": 5285
|
|
},
|
|
{
|
|
"entropy": 5.333998918533325,
|
|
"epoch": 4.805088596092685,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0003248407531288932,
|
|
"loss": 5.0255,
|
|
"mean_token_accuracy": 0.19110700041055678,
|
|
"num_tokens": 10951626.0,
|
|
"step": 5290
|
|
},
|
|
{
|
|
"entropy": 5.3591395854949955,
|
|
"epoch": 4.809631985461154,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.000324496042818678,
|
|
"loss": 5.1172,
|
|
"mean_token_accuracy": 0.1789785534143448,
|
|
"num_tokens": 10961970.0,
|
|
"step": 5295
|
|
},
|
|
{
|
|
"entropy": 5.335942363739013,
|
|
"epoch": 4.814175374829623,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.00032415121038189746,
|
|
"loss": 4.9166,
|
|
"mean_token_accuracy": 0.19967204332351685,
|
|
"num_tokens": 10972869.0,
|
|
"step": 5300
|
|
},
|
|
{
|
|
"entropy": 5.32960352897644,
|
|
"epoch": 4.818718764198092,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.00032380625666939125,
|
|
"loss": 4.9988,
|
|
"mean_token_accuracy": 0.189892540872097,
|
|
"num_tokens": 10984306.0,
|
|
"step": 5305
|
|
},
|
|
{
|
|
"entropy": 5.280833673477173,
|
|
"epoch": 4.823262153566561,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00032346118253229834,
|
|
"loss": 5.0116,
|
|
"mean_token_accuracy": 0.18963059186935424,
|
|
"num_tokens": 10995488.0,
|
|
"step": 5310
|
|
},
|
|
{
|
|
"entropy": 5.358375215530396,
|
|
"epoch": 4.82780554293503,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.00032311598882205496,
|
|
"loss": 4.9801,
|
|
"mean_token_accuracy": 0.19681648463010787,
|
|
"num_tokens": 11006209.0,
|
|
"step": 5315
|
|
},
|
|
{
|
|
"entropy": 5.359938430786133,
|
|
"epoch": 4.832348932303498,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.00032277067639039216,
|
|
"loss": 5.0489,
|
|
"mean_token_accuracy": 0.18875264823436738,
|
|
"num_tokens": 11016297.0,
|
|
"step": 5320
|
|
},
|
|
{
|
|
"entropy": 5.304664611816406,
|
|
"epoch": 4.836892321671967,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.00032242524608933423,
|
|
"loss": 5.0174,
|
|
"mean_token_accuracy": 0.1913877785205841,
|
|
"num_tokens": 11026788.0,
|
|
"step": 5325
|
|
},
|
|
{
|
|
"entropy": 5.410329437255859,
|
|
"epoch": 4.841435711040436,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.00032207969877119587,
|
|
"loss": 5.0489,
|
|
"mean_token_accuracy": 0.1897216632962227,
|
|
"num_tokens": 11037148.0,
|
|
"step": 5330
|
|
},
|
|
{
|
|
"entropy": 5.3662299633026125,
|
|
"epoch": 4.845979100408905,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.00032173403528858093,
|
|
"loss": 4.9943,
|
|
"mean_token_accuracy": 0.19192123413085938,
|
|
"num_tokens": 11046986.0,
|
|
"step": 5335
|
|
},
|
|
{
|
|
"entropy": 5.3752483367919925,
|
|
"epoch": 4.850522489777374,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0003213882564943796,
|
|
"loss": 5.0244,
|
|
"mean_token_accuracy": 0.18799861669540405,
|
|
"num_tokens": 11057824.0,
|
|
"step": 5340
|
|
},
|
|
{
|
|
"entropy": 5.280523633956909,
|
|
"epoch": 4.855065879145843,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0003210423632417666,
|
|
"loss": 4.9343,
|
|
"mean_token_accuracy": 0.2010989233851433,
|
|
"num_tokens": 11068856.0,
|
|
"step": 5345
|
|
},
|
|
{
|
|
"entropy": 5.295340299606323,
|
|
"epoch": 4.859609268514312,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0003206963563841993,
|
|
"loss": 4.9689,
|
|
"mean_token_accuracy": 0.19400161057710646,
|
|
"num_tokens": 11079468.0,
|
|
"step": 5350
|
|
},
|
|
{
|
|
"entropy": 5.339853429794312,
|
|
"epoch": 4.86415265788278,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.00032035023677541515,
|
|
"loss": 4.9857,
|
|
"mean_token_accuracy": 0.19154063761234283,
|
|
"num_tokens": 11089609.0,
|
|
"step": 5355
|
|
},
|
|
{
|
|
"entropy": 5.390847492218017,
|
|
"epoch": 4.868696047251249,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0003200040052694299,
|
|
"loss": 5.042,
|
|
"mean_token_accuracy": 0.18596290647983552,
|
|
"num_tokens": 11099071.0,
|
|
"step": 5360
|
|
},
|
|
{
|
|
"entropy": 5.3668091773986815,
|
|
"epoch": 4.873239436619718,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.00031965766272053534,
|
|
"loss": 4.9664,
|
|
"mean_token_accuracy": 0.19028736650943756,
|
|
"num_tokens": 11109242.0,
|
|
"step": 5365
|
|
},
|
|
{
|
|
"entropy": 5.354577112197876,
|
|
"epoch": 4.877782825988187,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.00031931120998329737,
|
|
"loss": 5.0521,
|
|
"mean_token_accuracy": 0.19236235767602922,
|
|
"num_tokens": 11118837.0,
|
|
"step": 5370
|
|
},
|
|
{
|
|
"entropy": 5.338931083679199,
|
|
"epoch": 4.882326215356656,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0003189646479125536,
|
|
"loss": 5.0203,
|
|
"mean_token_accuracy": 0.18859934508800508,
|
|
"num_tokens": 11130435.0,
|
|
"step": 5375
|
|
},
|
|
{
|
|
"entropy": 5.357939386367798,
|
|
"epoch": 4.886869604725125,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0003186179773634115,
|
|
"loss": 5.053,
|
|
"mean_token_accuracy": 0.1883614704012871,
|
|
"num_tokens": 11141477.0,
|
|
"step": 5380
|
|
},
|
|
{
|
|
"entropy": 5.391132068634033,
|
|
"epoch": 4.891412994093594,
|
|
"grad_norm": 1.9140625,
|
|
"learning_rate": 0.00031827119919124614,
|
|
"loss": 4.9467,
|
|
"mean_token_accuracy": 0.19824953079223634,
|
|
"num_tokens": 11150989.0,
|
|
"step": 5385
|
|
},
|
|
{
|
|
"entropy": 5.375834321975708,
|
|
"epoch": 4.895956383462063,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.00031792431425169826,
|
|
"loss": 4.988,
|
|
"mean_token_accuracy": 0.19155981689691542,
|
|
"num_tokens": 11161407.0,
|
|
"step": 5390
|
|
},
|
|
{
|
|
"entropy": 5.339215326309204,
|
|
"epoch": 4.900499772830532,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.00031757732340067195,
|
|
"loss": 4.9426,
|
|
"mean_token_accuracy": 0.19466377496719361,
|
|
"num_tokens": 11171132.0,
|
|
"step": 5395
|
|
},
|
|
{
|
|
"entropy": 5.440320730209351,
|
|
"epoch": 4.905043162199,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.00031723022749433267,
|
|
"loss": 5.0328,
|
|
"mean_token_accuracy": 0.19335440546274185,
|
|
"num_tokens": 11181402.0,
|
|
"step": 5400
|
|
},
|
|
{
|
|
"entropy": 5.4028308391571045,
|
|
"epoch": 4.909586551567469,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.000316883027389105,
|
|
"loss": 4.9803,
|
|
"mean_token_accuracy": 0.19636130183935166,
|
|
"num_tokens": 11190820.0,
|
|
"step": 5405
|
|
},
|
|
{
|
|
"entropy": 5.355147790908814,
|
|
"epoch": 4.914129940935938,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0003165357239416706,
|
|
"loss": 4.9931,
|
|
"mean_token_accuracy": 0.19062133133411407,
|
|
"num_tokens": 11200215.0,
|
|
"step": 5410
|
|
},
|
|
{
|
|
"entropy": 5.265058374404907,
|
|
"epoch": 4.918673330304407,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0003161883180089665,
|
|
"loss": 4.9529,
|
|
"mean_token_accuracy": 0.19606461226940156,
|
|
"num_tokens": 11209732.0,
|
|
"step": 5415
|
|
},
|
|
{
|
|
"entropy": 5.391970777511597,
|
|
"epoch": 4.923216719672876,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0003158408104481821,
|
|
"loss": 5.0428,
|
|
"mean_token_accuracy": 0.1873098775744438,
|
|
"num_tokens": 11220735.0,
|
|
"step": 5420
|
|
},
|
|
{
|
|
"entropy": 5.320717906951904,
|
|
"epoch": 4.927760109041345,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.00031549320211675776,
|
|
"loss": 4.9135,
|
|
"mean_token_accuracy": 0.19409168362617493,
|
|
"num_tokens": 11231668.0,
|
|
"step": 5425
|
|
},
|
|
{
|
|
"entropy": 5.3090211868286135,
|
|
"epoch": 4.932303498409814,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.00031514549387238246,
|
|
"loss": 5.0989,
|
|
"mean_token_accuracy": 0.19203329980373382,
|
|
"num_tokens": 11242666.0,
|
|
"step": 5430
|
|
},
|
|
{
|
|
"entropy": 5.323944759368897,
|
|
"epoch": 4.936846887778283,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0003147976865729918,
|
|
"loss": 4.9871,
|
|
"mean_token_accuracy": 0.18537170588970184,
|
|
"num_tokens": 11253024.0,
|
|
"step": 5435
|
|
},
|
|
{
|
|
"entropy": 5.330201911926269,
|
|
"epoch": 4.941390277146752,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.00031444978107676567,
|
|
"loss": 4.9962,
|
|
"mean_token_accuracy": 0.1894350215792656,
|
|
"num_tokens": 11263135.0,
|
|
"step": 5440
|
|
},
|
|
{
|
|
"entropy": 5.324851369857788,
|
|
"epoch": 4.94593366651522,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.00031410177824212635,
|
|
"loss": 4.9447,
|
|
"mean_token_accuracy": 0.19058672040700914,
|
|
"num_tokens": 11272865.0,
|
|
"step": 5445
|
|
},
|
|
{
|
|
"entropy": 5.41461706161499,
|
|
"epoch": 4.950477055883689,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0003137536789277362,
|
|
"loss": 5.0239,
|
|
"mean_token_accuracy": 0.19884902983903885,
|
|
"num_tokens": 11283736.0,
|
|
"step": 5450
|
|
},
|
|
{
|
|
"entropy": 5.3570396900177,
|
|
"epoch": 4.955020445252158,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0003134054839924957,
|
|
"loss": 5.0275,
|
|
"mean_token_accuracy": 0.18326819390058519,
|
|
"num_tokens": 11295000.0,
|
|
"step": 5455
|
|
},
|
|
{
|
|
"entropy": 5.329272127151489,
|
|
"epoch": 4.959563834620627,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.00031305719429554124,
|
|
"loss": 4.954,
|
|
"mean_token_accuracy": 0.20229892283678055,
|
|
"num_tokens": 11304924.0,
|
|
"step": 5460
|
|
},
|
|
{
|
|
"entropy": 5.363986444473267,
|
|
"epoch": 4.964107223989096,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0003127088106962429,
|
|
"loss": 4.9894,
|
|
"mean_token_accuracy": 0.1885639563202858,
|
|
"num_tokens": 11315793.0,
|
|
"step": 5465
|
|
},
|
|
{
|
|
"entropy": 5.37711763381958,
|
|
"epoch": 4.968650613357565,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.00031236033405420284,
|
|
"loss": 5.0167,
|
|
"mean_token_accuracy": 0.19418932348489762,
|
|
"num_tokens": 11325626.0,
|
|
"step": 5470
|
|
},
|
|
{
|
|
"entropy": 5.306945276260376,
|
|
"epoch": 4.973194002726034,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.00031201176522925236,
|
|
"loss": 4.9989,
|
|
"mean_token_accuracy": 0.1964153081178665,
|
|
"num_tokens": 11336206.0,
|
|
"step": 5475
|
|
},
|
|
{
|
|
"entropy": 5.293835592269898,
|
|
"epoch": 4.977737392094502,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0003116631050814503,
|
|
"loss": 5.0915,
|
|
"mean_token_accuracy": 0.18724937736988068,
|
|
"num_tokens": 11346842.0,
|
|
"step": 5480
|
|
},
|
|
{
|
|
"entropy": 5.38566484451294,
|
|
"epoch": 4.982280781462971,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.00031131435447108116,
|
|
"loss": 4.9792,
|
|
"mean_token_accuracy": 0.19666886925697327,
|
|
"num_tokens": 11357590.0,
|
|
"step": 5485
|
|
},
|
|
{
|
|
"entropy": 5.399775981903076,
|
|
"epoch": 4.98682417083144,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0003109655142586521,
|
|
"loss": 5.0207,
|
|
"mean_token_accuracy": 0.1900867447257042,
|
|
"num_tokens": 11366874.0,
|
|
"step": 5490
|
|
},
|
|
{
|
|
"entropy": 5.358940076828003,
|
|
"epoch": 4.991367560199909,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.00031061658530489195,
|
|
"loss": 4.9925,
|
|
"mean_token_accuracy": 0.19058748334646225,
|
|
"num_tokens": 11376864.0,
|
|
"step": 5495
|
|
},
|
|
{
|
|
"entropy": 5.305967855453491,
|
|
"epoch": 4.995910949568378,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.00031026756847074804,
|
|
"loss": 5.0297,
|
|
"mean_token_accuracy": 0.19055143892765045,
|
|
"num_tokens": 11387686.0,
|
|
"step": 5500
|
|
},
|
|
{
|
|
"entropy": 5.3604626125759545,
|
|
"epoch": 5.0,
|
|
"grad_norm": 2.734375,
|
|
"learning_rate": 0.0003099184646173849,
|
|
"loss": 5.0164,
|
|
"mean_token_accuracy": 0.18273275759485033,
|
|
"num_tokens": 11396985.0,
|
|
"step": 5505
|
|
},
|
|
{
|
|
"entropy": 5.4241690158844,
|
|
"epoch": 5.004543389368469,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00030956927460618126,
|
|
"loss": 4.8307,
|
|
"mean_token_accuracy": 0.20089125037193298,
|
|
"num_tokens": 11407498.0,
|
|
"step": 5510
|
|
},
|
|
{
|
|
"entropy": 5.299976396560669,
|
|
"epoch": 5.009086778736938,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0003092199992987291,
|
|
"loss": 4.7705,
|
|
"mean_token_accuracy": 0.2060692474246025,
|
|
"num_tokens": 11417613.0,
|
|
"step": 5515
|
|
},
|
|
{
|
|
"entropy": 5.234093856811524,
|
|
"epoch": 5.013630168105407,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00030887063955683044,
|
|
"loss": 4.7313,
|
|
"mean_token_accuracy": 0.20872837156057358,
|
|
"num_tokens": 11427302.0,
|
|
"step": 5520
|
|
},
|
|
{
|
|
"entropy": 5.30947093963623,
|
|
"epoch": 5.018173557473876,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.00030852119624249553,
|
|
"loss": 4.8158,
|
|
"mean_token_accuracy": 0.2061762884259224,
|
|
"num_tokens": 11437118.0,
|
|
"step": 5525
|
|
},
|
|
{
|
|
"entropy": 5.348355674743653,
|
|
"epoch": 5.022716946842344,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.0003081716702179412,
|
|
"loss": 4.7133,
|
|
"mean_token_accuracy": 0.21127792149782182,
|
|
"num_tokens": 11447113.0,
|
|
"step": 5530
|
|
},
|
|
{
|
|
"entropy": 5.316198205947876,
|
|
"epoch": 5.027260336210813,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.000307822062345588,
|
|
"loss": 4.8001,
|
|
"mean_token_accuracy": 0.20694794356822968,
|
|
"num_tokens": 11457939.0,
|
|
"step": 5535
|
|
},
|
|
{
|
|
"entropy": 5.320601844787598,
|
|
"epoch": 5.031803725579282,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0003074723734880588,
|
|
"loss": 4.7968,
|
|
"mean_token_accuracy": 0.20518019944429397,
|
|
"num_tokens": 11468620.0,
|
|
"step": 5540
|
|
},
|
|
{
|
|
"entropy": 5.335376119613647,
|
|
"epoch": 5.036347114947751,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.000307122604508176,
|
|
"loss": 4.8104,
|
|
"mean_token_accuracy": 0.1975176900625229,
|
|
"num_tokens": 11478456.0,
|
|
"step": 5545
|
|
},
|
|
{
|
|
"entropy": 5.275946855545044,
|
|
"epoch": 5.04089050431622,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0003067727562689598,
|
|
"loss": 4.8045,
|
|
"mean_token_accuracy": 0.20643910616636277,
|
|
"num_tokens": 11488663.0,
|
|
"step": 5550
|
|
},
|
|
{
|
|
"entropy": 5.26479024887085,
|
|
"epoch": 5.045433893684689,
|
|
"grad_norm": 1.84375,
|
|
"learning_rate": 0.0003064228296336259,
|
|
"loss": 4.7294,
|
|
"mean_token_accuracy": 0.20833629220724106,
|
|
"num_tokens": 11498327.0,
|
|
"step": 5555
|
|
},
|
|
{
|
|
"entropy": 5.347030878067017,
|
|
"epoch": 5.049977283053158,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0003060728254655836,
|
|
"loss": 4.848,
|
|
"mean_token_accuracy": 0.2030338764190674,
|
|
"num_tokens": 11508339.0,
|
|
"step": 5560
|
|
},
|
|
{
|
|
"entropy": 5.397200965881348,
|
|
"epoch": 5.054520672421627,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.00030572274462843327,
|
|
"loss": 4.9535,
|
|
"mean_token_accuracy": 0.19030862748622895,
|
|
"num_tokens": 11519461.0,
|
|
"step": 5565
|
|
},
|
|
{
|
|
"entropy": 5.3387054920196535,
|
|
"epoch": 5.059064061790095,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.00030537258798596465,
|
|
"loss": 4.8187,
|
|
"mean_token_accuracy": 0.20316300094127654,
|
|
"num_tokens": 11529837.0,
|
|
"step": 5570
|
|
},
|
|
{
|
|
"entropy": 5.329079627990723,
|
|
"epoch": 5.063607451158564,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.0003050223564021543,
|
|
"loss": 4.7369,
|
|
"mean_token_accuracy": 0.2066208079457283,
|
|
"num_tokens": 11539249.0,
|
|
"step": 5575
|
|
},
|
|
{
|
|
"entropy": 5.274517297744751,
|
|
"epoch": 5.068150840527033,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.0003046720507411641,
|
|
"loss": 4.8282,
|
|
"mean_token_accuracy": 0.20620599389076233,
|
|
"num_tokens": 11549908.0,
|
|
"step": 5580
|
|
},
|
|
{
|
|
"entropy": 5.300417852401734,
|
|
"epoch": 5.072694229895502,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.0003043216718673383,
|
|
"loss": 4.7996,
|
|
"mean_token_accuracy": 0.20480708181858062,
|
|
"num_tokens": 11560277.0,
|
|
"step": 5585
|
|
},
|
|
{
|
|
"entropy": 5.345212078094482,
|
|
"epoch": 5.077237619263971,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.00030397122064520186,
|
|
"loss": 4.8698,
|
|
"mean_token_accuracy": 0.20727277249097825,
|
|
"num_tokens": 11569452.0,
|
|
"step": 5590
|
|
},
|
|
{
|
|
"entropy": 5.285889339447022,
|
|
"epoch": 5.08178100863244,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.00030362069793945856,
|
|
"loss": 4.7955,
|
|
"mean_token_accuracy": 0.2037023514509201,
|
|
"num_tokens": 11580218.0,
|
|
"step": 5595
|
|
},
|
|
{
|
|
"entropy": 5.336301994323731,
|
|
"epoch": 5.086324398000909,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0003032701046149881,
|
|
"loss": 4.8075,
|
|
"mean_token_accuracy": 0.20149038583040238,
|
|
"num_tokens": 11590955.0,
|
|
"step": 5600
|
|
},
|
|
{
|
|
"entropy": 5.3221289157867435,
|
|
"epoch": 5.090867787369378,
|
|
"grad_norm": 1.9375,
|
|
"learning_rate": 0.0003029194415368448,
|
|
"loss": 4.816,
|
|
"mean_token_accuracy": 0.2047172635793686,
|
|
"num_tokens": 11600553.0,
|
|
"step": 5605
|
|
},
|
|
{
|
|
"entropy": 5.318461990356445,
|
|
"epoch": 5.095411176737846,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.0003025687095702548,
|
|
"loss": 4.7535,
|
|
"mean_token_accuracy": 0.21455857753753663,
|
|
"num_tokens": 11610706.0,
|
|
"step": 5610
|
|
},
|
|
{
|
|
"entropy": 5.352125835418701,
|
|
"epoch": 5.099954566106315,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0003022179095806146,
|
|
"loss": 4.8387,
|
|
"mean_token_accuracy": 0.19663550704717636,
|
|
"num_tokens": 11620293.0,
|
|
"step": 5615
|
|
},
|
|
{
|
|
"entropy": 5.304862403869629,
|
|
"epoch": 5.104497955474784,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.000301867042433488,
|
|
"loss": 4.7363,
|
|
"mean_token_accuracy": 0.2085326373577118,
|
|
"num_tokens": 11631096.0,
|
|
"step": 5620
|
|
},
|
|
{
|
|
"entropy": 5.297146797180176,
|
|
"epoch": 5.109041344843253,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.00030151610899460505,
|
|
"loss": 4.9283,
|
|
"mean_token_accuracy": 0.1915547803044319,
|
|
"num_tokens": 11642189.0,
|
|
"step": 5625
|
|
},
|
|
{
|
|
"entropy": 5.353310394287109,
|
|
"epoch": 5.113584734211722,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.00030116511012985916,
|
|
"loss": 4.9007,
|
|
"mean_token_accuracy": 0.19234026968479156,
|
|
"num_tokens": 11652948.0,
|
|
"step": 5630
|
|
},
|
|
{
|
|
"entropy": 5.3586156368255615,
|
|
"epoch": 5.118128123580191,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0003008140467053048,
|
|
"loss": 4.8293,
|
|
"mean_token_accuracy": 0.20528754144906997,
|
|
"num_tokens": 11663144.0,
|
|
"step": 5635
|
|
},
|
|
{
|
|
"entropy": 5.303511142730713,
|
|
"epoch": 5.12267151294866,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0003004629195871565,
|
|
"loss": 4.7438,
|
|
"mean_token_accuracy": 0.20706187933683395,
|
|
"num_tokens": 11673434.0,
|
|
"step": 5640
|
|
},
|
|
{
|
|
"entropy": 5.322103881835938,
|
|
"epoch": 5.127214902317129,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0003001117296417852,
|
|
"loss": 4.8272,
|
|
"mean_token_accuracy": 0.19901088774204254,
|
|
"num_tokens": 11683859.0,
|
|
"step": 5645
|
|
},
|
|
{
|
|
"entropy": 5.288669157028198,
|
|
"epoch": 5.131758291685597,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0002997604777357173,
|
|
"loss": 4.809,
|
|
"mean_token_accuracy": 0.20828791856765747,
|
|
"num_tokens": 11693754.0,
|
|
"step": 5650
|
|
},
|
|
{
|
|
"entropy": 5.375597429275513,
|
|
"epoch": 5.136301681054066,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.000299409164735632,
|
|
"loss": 4.8281,
|
|
"mean_token_accuracy": 0.2026832640171051,
|
|
"num_tokens": 11705301.0,
|
|
"step": 5655
|
|
},
|
|
{
|
|
"entropy": 5.258410120010376,
|
|
"epoch": 5.140845070422535,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0002990577915083591,
|
|
"loss": 4.7743,
|
|
"mean_token_accuracy": 0.19967305809259414,
|
|
"num_tokens": 11715165.0,
|
|
"step": 5660
|
|
},
|
|
{
|
|
"entropy": 5.261981582641601,
|
|
"epoch": 5.145388459791004,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.00029870635892087716,
|
|
"loss": 4.7833,
|
|
"mean_token_accuracy": 0.20387240052223204,
|
|
"num_tokens": 11724475.0,
|
|
"step": 5665
|
|
},
|
|
{
|
|
"entropy": 5.291424751281738,
|
|
"epoch": 5.149931849159473,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0002983548678403112,
|
|
"loss": 4.7607,
|
|
"mean_token_accuracy": 0.20230522751808167,
|
|
"num_tokens": 11734577.0,
|
|
"step": 5670
|
|
},
|
|
{
|
|
"entropy": 5.309701013565063,
|
|
"epoch": 5.154475238527942,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0002980033191339305,
|
|
"loss": 4.7911,
|
|
"mean_token_accuracy": 0.2090888276696205,
|
|
"num_tokens": 11744501.0,
|
|
"step": 5675
|
|
},
|
|
{
|
|
"entropy": 5.33240966796875,
|
|
"epoch": 5.159018627896411,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.0002976517136691465,
|
|
"loss": 4.891,
|
|
"mean_token_accuracy": 0.19865501075983047,
|
|
"num_tokens": 11755688.0,
|
|
"step": 5680
|
|
},
|
|
{
|
|
"entropy": 5.343625783920288,
|
|
"epoch": 5.16356201726488,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.00029730005231351074,
|
|
"loss": 4.886,
|
|
"mean_token_accuracy": 0.20000392198562622,
|
|
"num_tokens": 11765880.0,
|
|
"step": 5685
|
|
},
|
|
{
|
|
"entropy": 5.364861345291137,
|
|
"epoch": 5.168105406633348,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0002969483359347127,
|
|
"loss": 4.8461,
|
|
"mean_token_accuracy": 0.20376210212707518,
|
|
"num_tokens": 11776528.0,
|
|
"step": 5690
|
|
},
|
|
{
|
|
"entropy": 5.342062091827392,
|
|
"epoch": 5.172648796001817,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0002965965654005776,
|
|
"loss": 4.9199,
|
|
"mean_token_accuracy": 0.19346130788326263,
|
|
"num_tokens": 11788036.0,
|
|
"step": 5695
|
|
},
|
|
{
|
|
"entropy": 5.323707103729248,
|
|
"epoch": 5.177192185370286,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0002962447415790642,
|
|
"loss": 4.8116,
|
|
"mean_token_accuracy": 0.20060003846883773,
|
|
"num_tokens": 11798028.0,
|
|
"step": 5700
|
|
},
|
|
{
|
|
"entropy": 5.335442590713501,
|
|
"epoch": 5.181735574738755,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.00029589286533826276,
|
|
"loss": 4.8156,
|
|
"mean_token_accuracy": 0.2030690997838974,
|
|
"num_tokens": 11808007.0,
|
|
"step": 5705
|
|
},
|
|
{
|
|
"entropy": 5.3358180046081545,
|
|
"epoch": 5.186278964107224,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0002955409375463931,
|
|
"loss": 4.8934,
|
|
"mean_token_accuracy": 0.19563875943422318,
|
|
"num_tokens": 11818954.0,
|
|
"step": 5710
|
|
},
|
|
{
|
|
"entropy": 5.3060096263885494,
|
|
"epoch": 5.190822353475693,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0002951889590718019,
|
|
"loss": 4.7848,
|
|
"mean_token_accuracy": 0.20695229470729828,
|
|
"num_tokens": 11829626.0,
|
|
"step": 5715
|
|
},
|
|
{
|
|
"entropy": 5.240945720672608,
|
|
"epoch": 5.195365742844162,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0002948369307829612,
|
|
"loss": 4.762,
|
|
"mean_token_accuracy": 0.2133689433336258,
|
|
"num_tokens": 11839824.0,
|
|
"step": 5720
|
|
},
|
|
{
|
|
"entropy": 5.351646184921265,
|
|
"epoch": 5.199909132212631,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0002944848535484656,
|
|
"loss": 4.8263,
|
|
"mean_token_accuracy": 0.20012809336185455,
|
|
"num_tokens": 11850905.0,
|
|
"step": 5725
|
|
},
|
|
{
|
|
"entropy": 5.2983818531036375,
|
|
"epoch": 5.2044525215811,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.00029413272823703085,
|
|
"loss": 4.7968,
|
|
"mean_token_accuracy": 0.20804608017206191,
|
|
"num_tokens": 11861648.0,
|
|
"step": 5730
|
|
},
|
|
{
|
|
"entropy": 5.240070104598999,
|
|
"epoch": 5.208995910949568,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0002937805557174911,
|
|
"loss": 4.8338,
|
|
"mean_token_accuracy": 0.20307734310626985,
|
|
"num_tokens": 11871841.0,
|
|
"step": 5735
|
|
},
|
|
{
|
|
"entropy": 5.27209997177124,
|
|
"epoch": 5.213539300318037,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00029342833685879713,
|
|
"loss": 4.7988,
|
|
"mean_token_accuracy": 0.19914903193712236,
|
|
"num_tokens": 11883217.0,
|
|
"step": 5740
|
|
},
|
|
{
|
|
"entropy": 5.327469539642334,
|
|
"epoch": 5.218082689686506,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0002930760725300137,
|
|
"loss": 4.8091,
|
|
"mean_token_accuracy": 0.20309193581342697,
|
|
"num_tokens": 11893028.0,
|
|
"step": 5745
|
|
},
|
|
{
|
|
"entropy": 5.251752710342407,
|
|
"epoch": 5.222626079054975,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.00029272376360031833,
|
|
"loss": 4.7485,
|
|
"mean_token_accuracy": 0.20631260573863983,
|
|
"num_tokens": 11903237.0,
|
|
"step": 5750
|
|
},
|
|
{
|
|
"entropy": 5.3539060115814205,
|
|
"epoch": 5.227169468423444,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.00029237141093899804,
|
|
"loss": 4.8598,
|
|
"mean_token_accuracy": 0.1989493578672409,
|
|
"num_tokens": 11914129.0,
|
|
"step": 5755
|
|
},
|
|
{
|
|
"entropy": 5.3019054412841795,
|
|
"epoch": 5.231712857791913,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.00029201901541544824,
|
|
"loss": 4.8532,
|
|
"mean_token_accuracy": 0.19478944838047027,
|
|
"num_tokens": 11924090.0,
|
|
"step": 5760
|
|
},
|
|
{
|
|
"entropy": 5.267965698242188,
|
|
"epoch": 5.236256247160382,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0002916665778991696,
|
|
"loss": 4.8064,
|
|
"mean_token_accuracy": 0.2044772058725357,
|
|
"num_tokens": 11933943.0,
|
|
"step": 5765
|
|
},
|
|
{
|
|
"entropy": 5.261118650436401,
|
|
"epoch": 5.240799636528851,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0002913140992597668,
|
|
"loss": 4.8075,
|
|
"mean_token_accuracy": 0.20092179030179977,
|
|
"num_tokens": 11944410.0,
|
|
"step": 5770
|
|
},
|
|
{
|
|
"entropy": 5.295876502990723,
|
|
"epoch": 5.245343025897319,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0002909615803669458,
|
|
"loss": 4.7908,
|
|
"mean_token_accuracy": 0.20390776097774505,
|
|
"num_tokens": 11955317.0,
|
|
"step": 5775
|
|
},
|
|
{
|
|
"entropy": 5.228341007232666,
|
|
"epoch": 5.249886415265788,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0002906090220905119,
|
|
"loss": 4.7889,
|
|
"mean_token_accuracy": 0.19886881709098816,
|
|
"num_tokens": 11965450.0,
|
|
"step": 5780
|
|
},
|
|
{
|
|
"entropy": 5.268054437637329,
|
|
"epoch": 5.254429804634257,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0002902564253003677,
|
|
"loss": 4.7965,
|
|
"mean_token_accuracy": 0.20076684653759003,
|
|
"num_tokens": 11975090.0,
|
|
"step": 5785
|
|
},
|
|
{
|
|
"entropy": 5.298431825637818,
|
|
"epoch": 5.258973194002726,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0002899037908665106,
|
|
"loss": 4.8839,
|
|
"mean_token_accuracy": 0.19314879775047303,
|
|
"num_tokens": 11985102.0,
|
|
"step": 5790
|
|
},
|
|
{
|
|
"entropy": 5.299476861953735,
|
|
"epoch": 5.263516583371195,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.0002895511196590312,
|
|
"loss": 4.8215,
|
|
"mean_token_accuracy": 0.19797307401895523,
|
|
"num_tokens": 11995663.0,
|
|
"step": 5795
|
|
},
|
|
{
|
|
"entropy": 5.35582127571106,
|
|
"epoch": 5.268059972739664,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0002891984125481104,
|
|
"loss": 4.7929,
|
|
"mean_token_accuracy": 0.20957164764404296,
|
|
"num_tokens": 12006031.0,
|
|
"step": 5800
|
|
},
|
|
{
|
|
"entropy": 5.242889881134033,
|
|
"epoch": 5.272603362108133,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.00028884567040401814,
|
|
"loss": 4.7558,
|
|
"mean_token_accuracy": 0.20336291342973709,
|
|
"num_tokens": 12015589.0,
|
|
"step": 5805
|
|
},
|
|
{
|
|
"entropy": 5.278609943389893,
|
|
"epoch": 5.277146751476602,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0002884928940971105,
|
|
"loss": 4.7822,
|
|
"mean_token_accuracy": 0.20466556549072265,
|
|
"num_tokens": 12025319.0,
|
|
"step": 5810
|
|
},
|
|
{
|
|
"entropy": 5.294900178909302,
|
|
"epoch": 5.28169014084507,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.000288140084497828,
|
|
"loss": 4.801,
|
|
"mean_token_accuracy": 0.21199169009923935,
|
|
"num_tokens": 12035071.0,
|
|
"step": 5815
|
|
},
|
|
{
|
|
"entropy": 5.278777647018432,
|
|
"epoch": 5.286233530213539,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0002877872424766932,
|
|
"loss": 4.828,
|
|
"mean_token_accuracy": 0.20273132771253585,
|
|
"num_tokens": 12046535.0,
|
|
"step": 5820
|
|
},
|
|
{
|
|
"entropy": 5.295928430557251,
|
|
"epoch": 5.290776919582008,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.0002874343689043086,
|
|
"loss": 4.8499,
|
|
"mean_token_accuracy": 0.2037402182817459,
|
|
"num_tokens": 12056986.0,
|
|
"step": 5825
|
|
},
|
|
{
|
|
"entropy": 5.319525527954101,
|
|
"epoch": 5.295320308950477,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.000287081464651355,
|
|
"loss": 4.8829,
|
|
"mean_token_accuracy": 0.19714448004961013,
|
|
"num_tokens": 12069112.0,
|
|
"step": 5830
|
|
},
|
|
{
|
|
"entropy": 5.3044023513793945,
|
|
"epoch": 5.299863698318946,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0002867285305885882,
|
|
"loss": 4.767,
|
|
"mean_token_accuracy": 0.20671482980251313,
|
|
"num_tokens": 12079399.0,
|
|
"step": 5835
|
|
},
|
|
{
|
|
"entropy": 5.351959991455078,
|
|
"epoch": 5.304407087687415,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.00028637556758683816,
|
|
"loss": 4.8311,
|
|
"mean_token_accuracy": 0.2009331464767456,
|
|
"num_tokens": 12090618.0,
|
|
"step": 5840
|
|
},
|
|
{
|
|
"entropy": 5.24814395904541,
|
|
"epoch": 5.308950477055884,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0002860225765170058,
|
|
"loss": 4.8404,
|
|
"mean_token_accuracy": 0.19793758392333985,
|
|
"num_tokens": 12101527.0,
|
|
"step": 5845
|
|
},
|
|
{
|
|
"entropy": 5.1991339206695555,
|
|
"epoch": 5.313493866424353,
|
|
"grad_norm": 1.9375,
|
|
"learning_rate": 0.00028566955825006174,
|
|
"loss": 4.7863,
|
|
"mean_token_accuracy": 0.20712051391601563,
|
|
"num_tokens": 12110882.0,
|
|
"step": 5850
|
|
},
|
|
{
|
|
"entropy": 5.384664487838745,
|
|
"epoch": 5.318037255792821,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.00028531651365704325,
|
|
"loss": 4.8911,
|
|
"mean_token_accuracy": 0.20576143264770508,
|
|
"num_tokens": 12121365.0,
|
|
"step": 5855
|
|
},
|
|
{
|
|
"entropy": 5.276581716537476,
|
|
"epoch": 5.32258064516129,
|
|
"grad_norm": 1.90625,
|
|
"learning_rate": 0.00028496344360905287,
|
|
"loss": 4.7662,
|
|
"mean_token_accuracy": 0.20258297324180602,
|
|
"num_tokens": 12132556.0,
|
|
"step": 5860
|
|
},
|
|
{
|
|
"entropy": 5.296639633178711,
|
|
"epoch": 5.327124034529759,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 0.00028461034897725587,
|
|
"loss": 4.8465,
|
|
"mean_token_accuracy": 0.20571750551462173,
|
|
"num_tokens": 12142408.0,
|
|
"step": 5865
|
|
},
|
|
{
|
|
"entropy": 5.383998870849609,
|
|
"epoch": 5.331667423898228,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.00028425723063287803,
|
|
"loss": 4.8797,
|
|
"mean_token_accuracy": 0.20464642494916915,
|
|
"num_tokens": 12152697.0,
|
|
"step": 5870
|
|
},
|
|
{
|
|
"entropy": 5.242600059509277,
|
|
"epoch": 5.336210813266697,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.00028390408944720385,
|
|
"loss": 4.756,
|
|
"mean_token_accuracy": 0.20183449238538742,
|
|
"num_tokens": 12162229.0,
|
|
"step": 5875
|
|
},
|
|
{
|
|
"entropy": 5.270735263824463,
|
|
"epoch": 5.340754202635166,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0002835509262915741,
|
|
"loss": 4.7678,
|
|
"mean_token_accuracy": 0.20891119688749313,
|
|
"num_tokens": 12171803.0,
|
|
"step": 5880
|
|
},
|
|
{
|
|
"entropy": 5.31595664024353,
|
|
"epoch": 5.345297592003635,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.00028319774203738375,
|
|
"loss": 4.8081,
|
|
"mean_token_accuracy": 0.20544808059930803,
|
|
"num_tokens": 12181487.0,
|
|
"step": 5885
|
|
},
|
|
{
|
|
"entropy": 5.301922130584717,
|
|
"epoch": 5.349840981372104,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0002828445375560798,
|
|
"loss": 4.8187,
|
|
"mean_token_accuracy": 0.2007838562130928,
|
|
"num_tokens": 12192091.0,
|
|
"step": 5890
|
|
},
|
|
{
|
|
"entropy": 5.2636260986328125,
|
|
"epoch": 5.354384370740572,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.00028249131371915927,
|
|
"loss": 4.7693,
|
|
"mean_token_accuracy": 0.2020486682653427,
|
|
"num_tokens": 12201841.0,
|
|
"step": 5895
|
|
},
|
|
{
|
|
"entropy": 5.311943387985229,
|
|
"epoch": 5.358927760109041,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0002821380713981668,
|
|
"loss": 4.8479,
|
|
"mean_token_accuracy": 0.1998163178563118,
|
|
"num_tokens": 12212553.0,
|
|
"step": 5900
|
|
},
|
|
{
|
|
"entropy": 5.237157821655273,
|
|
"epoch": 5.36347114947751,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.00028178481146469273,
|
|
"loss": 4.7954,
|
|
"mean_token_accuracy": 0.2068718522787094,
|
|
"num_tokens": 12222517.0,
|
|
"step": 5905
|
|
},
|
|
{
|
|
"entropy": 5.277577877044678,
|
|
"epoch": 5.368014538845979,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0002814315347903709,
|
|
"loss": 4.8201,
|
|
"mean_token_accuracy": 0.21417056918144226,
|
|
"num_tokens": 12231558.0,
|
|
"step": 5910
|
|
},
|
|
{
|
|
"entropy": 5.276502990722657,
|
|
"epoch": 5.372557928214448,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0002810782422468763,
|
|
"loss": 4.8176,
|
|
"mean_token_accuracy": 0.19866762608289718,
|
|
"num_tokens": 12241828.0,
|
|
"step": 5915
|
|
},
|
|
{
|
|
"entropy": 5.236698770523072,
|
|
"epoch": 5.377101317582917,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.00028072493470592317,
|
|
"loss": 4.7972,
|
|
"mean_token_accuracy": 0.2016886740922928,
|
|
"num_tokens": 12251767.0,
|
|
"step": 5920
|
|
},
|
|
{
|
|
"entropy": 5.288699722290039,
|
|
"epoch": 5.381644706951386,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.00028037161303926265,
|
|
"loss": 4.9314,
|
|
"mean_token_accuracy": 0.19834955930709838,
|
|
"num_tokens": 12263210.0,
|
|
"step": 5925
|
|
},
|
|
{
|
|
"entropy": 5.2799335479736325,
|
|
"epoch": 5.386188096319855,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.000280018278118681,
|
|
"loss": 4.8293,
|
|
"mean_token_accuracy": 0.20525913685560226,
|
|
"num_tokens": 12273587.0,
|
|
"step": 5930
|
|
},
|
|
{
|
|
"entropy": 5.259347581863404,
|
|
"epoch": 5.390731485688324,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.000279664930815997,
|
|
"loss": 4.826,
|
|
"mean_token_accuracy": 0.20510140359401702,
|
|
"num_tokens": 12284076.0,
|
|
"step": 5935
|
|
},
|
|
{
|
|
"entropy": 5.289797449111939,
|
|
"epoch": 5.395274875056792,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0002793115720030599,
|
|
"loss": 4.7697,
|
|
"mean_token_accuracy": 0.20902263075113298,
|
|
"num_tokens": 12293751.0,
|
|
"step": 5940
|
|
},
|
|
{
|
|
"entropy": 5.338681221008301,
|
|
"epoch": 5.399818264425261,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0002789582025517474,
|
|
"loss": 4.8811,
|
|
"mean_token_accuracy": 0.19423489272594452,
|
|
"num_tokens": 12303925.0,
|
|
"step": 5945
|
|
},
|
|
{
|
|
"entropy": 5.232827758789062,
|
|
"epoch": 5.40436165379373,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0002786048233339637,
|
|
"loss": 4.7924,
|
|
"mean_token_accuracy": 0.21205779761075974,
|
|
"num_tokens": 12314669.0,
|
|
"step": 5950
|
|
},
|
|
{
|
|
"entropy": 5.320423412322998,
|
|
"epoch": 5.408905043162199,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.00027825143522163675,
|
|
"loss": 4.8814,
|
|
"mean_token_accuracy": 0.19919709116220474,
|
|
"num_tokens": 12325478.0,
|
|
"step": 5955
|
|
},
|
|
{
|
|
"entropy": 5.262748861312867,
|
|
"epoch": 5.413448432530668,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0002778980390867165,
|
|
"loss": 4.7034,
|
|
"mean_token_accuracy": 0.21623935997486116,
|
|
"num_tokens": 12335528.0,
|
|
"step": 5960
|
|
},
|
|
{
|
|
"entropy": 5.293112421035767,
|
|
"epoch": 5.417991821899137,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.00027754463580117306,
|
|
"loss": 4.874,
|
|
"mean_token_accuracy": 0.2038433998823166,
|
|
"num_tokens": 12345692.0,
|
|
"step": 5965
|
|
},
|
|
{
|
|
"entropy": 5.233303594589233,
|
|
"epoch": 5.422535211267606,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.00027719122623699353,
|
|
"loss": 4.7593,
|
|
"mean_token_accuracy": 0.20713752061128615,
|
|
"num_tokens": 12355406.0,
|
|
"step": 5970
|
|
},
|
|
{
|
|
"entropy": 5.329917478561401,
|
|
"epoch": 5.427078600636074,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0002768378112661813,
|
|
"loss": 5.013,
|
|
"mean_token_accuracy": 0.19317860901355743,
|
|
"num_tokens": 12366343.0,
|
|
"step": 5975
|
|
},
|
|
{
|
|
"entropy": 5.35524353981018,
|
|
"epoch": 5.431621990004543,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0002764843917607523,
|
|
"loss": 4.8037,
|
|
"mean_token_accuracy": 0.21159234493970872,
|
|
"num_tokens": 12377051.0,
|
|
"step": 5980
|
|
},
|
|
{
|
|
"entropy": 5.327628660202026,
|
|
"epoch": 5.436165379373012,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0002761309685927343,
|
|
"loss": 4.8555,
|
|
"mean_token_accuracy": 0.1993535950779915,
|
|
"num_tokens": 12387190.0,
|
|
"step": 5985
|
|
},
|
|
{
|
|
"entropy": 5.316190433502197,
|
|
"epoch": 5.440708768741481,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0002757775426341636,
|
|
"loss": 4.7866,
|
|
"mean_token_accuracy": 0.2031787410378456,
|
|
"num_tokens": 12398308.0,
|
|
"step": 5990
|
|
},
|
|
{
|
|
"entropy": 5.352301216125488,
|
|
"epoch": 5.44525215810995,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.00027542411475708385,
|
|
"loss": 4.9122,
|
|
"mean_token_accuracy": 0.1933620512485504,
|
|
"num_tokens": 12408291.0,
|
|
"step": 5995
|
|
},
|
|
{
|
|
"entropy": 5.367377185821534,
|
|
"epoch": 5.449795547478419,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.00027507068583354304,
|
|
"loss": 4.8847,
|
|
"mean_token_accuracy": 0.1979081705212593,
|
|
"num_tokens": 12419306.0,
|
|
"step": 6000
|
|
},
|
|
{
|
|
"epoch": 5.449795547478419,
|
|
"eval_entropy": 5.217286997063216,
|
|
"eval_loss": 5.753686904907227,
|
|
"eval_mean_token_accuracy": 0.1674427209378675,
|
|
"eval_num_tokens": 12419306.0,
|
|
"eval_runtime": 2.6035,
|
|
"eval_samples_per_second": 1319.402,
|
|
"eval_steps_per_second": 165.165,
|
|
"step": 6000
|
|
},
|
|
{
|
|
"entropy": 5.28089714050293,
|
|
"epoch": 5.454338936846888,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00027471725673559205,
|
|
"loss": 4.8168,
|
|
"mean_token_accuracy": 0.20474095940589904,
|
|
"num_tokens": 12429306.0,
|
|
"step": 6005
|
|
},
|
|
{
|
|
"entropy": 5.323255729675293,
|
|
"epoch": 5.458882326215357,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.00027436382833528184,
|
|
"loss": 4.8676,
|
|
"mean_token_accuracy": 0.20208284258842468,
|
|
"num_tokens": 12439286.0,
|
|
"step": 6010
|
|
},
|
|
{
|
|
"entropy": 5.359365701675415,
|
|
"epoch": 5.463425715583826,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0002740104015046621,
|
|
"loss": 4.8035,
|
|
"mean_token_accuracy": 0.20787250101566315,
|
|
"num_tokens": 12449237.0,
|
|
"step": 6015
|
|
},
|
|
{
|
|
"entropy": 5.296931409835816,
|
|
"epoch": 5.467969104952294,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.00027365697711577815,
|
|
"loss": 4.8008,
|
|
"mean_token_accuracy": 0.20492820143699647,
|
|
"num_tokens": 12459701.0,
|
|
"step": 6020
|
|
},
|
|
{
|
|
"entropy": 5.334848690032959,
|
|
"epoch": 5.472512494320763,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0002733035560406697,
|
|
"loss": 4.8262,
|
|
"mean_token_accuracy": 0.20819955468177795,
|
|
"num_tokens": 12470072.0,
|
|
"step": 6025
|
|
},
|
|
{
|
|
"entropy": 5.2966491222381595,
|
|
"epoch": 5.477055883689232,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00027295013915136805,
|
|
"loss": 4.796,
|
|
"mean_token_accuracy": 0.20560968667268753,
|
|
"num_tokens": 12479953.0,
|
|
"step": 6030
|
|
},
|
|
{
|
|
"entropy": 5.3081659317016605,
|
|
"epoch": 5.481599273057701,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.00027259672731989436,
|
|
"loss": 4.8424,
|
|
"mean_token_accuracy": 0.19850560426712036,
|
|
"num_tokens": 12490546.0,
|
|
"step": 6035
|
|
},
|
|
{
|
|
"entropy": 5.310545253753662,
|
|
"epoch": 5.48614266242617,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.000272243321418257,
|
|
"loss": 4.8341,
|
|
"mean_token_accuracy": 0.19818889051675798,
|
|
"num_tokens": 12500253.0,
|
|
"step": 6040
|
|
},
|
|
{
|
|
"entropy": 5.2280144691467285,
|
|
"epoch": 5.490686051794639,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0002718899223184501,
|
|
"loss": 4.7731,
|
|
"mean_token_accuracy": 0.2158951461315155,
|
|
"num_tokens": 12510388.0,
|
|
"step": 6045
|
|
},
|
|
{
|
|
"entropy": 5.317040824890137,
|
|
"epoch": 5.495229441163108,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00027153653089245067,
|
|
"loss": 4.849,
|
|
"mean_token_accuracy": 0.19647378474473953,
|
|
"num_tokens": 12522082.0,
|
|
"step": 6050
|
|
},
|
|
{
|
|
"entropy": 5.305241680145263,
|
|
"epoch": 5.499772830531577,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.000271183148012217,
|
|
"loss": 4.7642,
|
|
"mean_token_accuracy": 0.2098957970738411,
|
|
"num_tokens": 12532074.0,
|
|
"step": 6055
|
|
},
|
|
{
|
|
"entropy": 5.263378715515136,
|
|
"epoch": 5.504316219900045,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0002708297745496861,
|
|
"loss": 4.7979,
|
|
"mean_token_accuracy": 0.20219234973192216,
|
|
"num_tokens": 12542490.0,
|
|
"step": 6060
|
|
},
|
|
{
|
|
"entropy": 5.261361312866211,
|
|
"epoch": 5.508859609268514,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00027047641137677213,
|
|
"loss": 4.9067,
|
|
"mean_token_accuracy": 0.19745700806379318,
|
|
"num_tokens": 12551995.0,
|
|
"step": 6065
|
|
},
|
|
{
|
|
"entropy": 5.283073949813843,
|
|
"epoch": 5.513402998636983,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0002701230593653632,
|
|
"loss": 4.8011,
|
|
"mean_token_accuracy": 0.20543096959590912,
|
|
"num_tokens": 12561589.0,
|
|
"step": 6070
|
|
},
|
|
{
|
|
"entropy": 5.386230421066284,
|
|
"epoch": 5.517946388005452,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0002697697193873207,
|
|
"loss": 4.8297,
|
|
"mean_token_accuracy": 0.20288927108049393,
|
|
"num_tokens": 12572990.0,
|
|
"step": 6075
|
|
},
|
|
{
|
|
"entropy": 5.408089923858642,
|
|
"epoch": 5.522489777373921,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.00026941639231447547,
|
|
"loss": 4.9347,
|
|
"mean_token_accuracy": 0.20002181082963943,
|
|
"num_tokens": 12582694.0,
|
|
"step": 6080
|
|
},
|
|
{
|
|
"entropy": 5.307639741897583,
|
|
"epoch": 5.52703316674239,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0002690630790186273,
|
|
"loss": 4.8819,
|
|
"mean_token_accuracy": 0.19454077929258345,
|
|
"num_tokens": 12592421.0,
|
|
"step": 6085
|
|
},
|
|
{
|
|
"entropy": 5.255243301391602,
|
|
"epoch": 5.531576556110859,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00026870978037154137,
|
|
"loss": 4.8409,
|
|
"mean_token_accuracy": 0.2037093758583069,
|
|
"num_tokens": 12603001.0,
|
|
"step": 6090
|
|
},
|
|
{
|
|
"entropy": 5.318074178695679,
|
|
"epoch": 5.536119945479328,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0002683564972449472,
|
|
"loss": 4.8189,
|
|
"mean_token_accuracy": 0.203626848757267,
|
|
"num_tokens": 12613450.0,
|
|
"step": 6095
|
|
},
|
|
{
|
|
"entropy": 5.349953508377075,
|
|
"epoch": 5.540663334847796,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0002680032305105355,
|
|
"loss": 4.8321,
|
|
"mean_token_accuracy": 0.1988368272781372,
|
|
"num_tokens": 12623120.0,
|
|
"step": 6100
|
|
},
|
|
{
|
|
"entropy": 5.2941618919372555,
|
|
"epoch": 5.545206724216265,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0002676499810399572,
|
|
"loss": 4.8409,
|
|
"mean_token_accuracy": 0.20413766652345658,
|
|
"num_tokens": 12633859.0,
|
|
"step": 6105
|
|
},
|
|
{
|
|
"entropy": 5.303717994689942,
|
|
"epoch": 5.549750113584734,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00026729674970481985,
|
|
"loss": 4.8899,
|
|
"mean_token_accuracy": 0.1989706426858902,
|
|
"num_tokens": 12645287.0,
|
|
"step": 6110
|
|
},
|
|
{
|
|
"entropy": 5.30036153793335,
|
|
"epoch": 5.554293502953203,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00026694353737668705,
|
|
"loss": 4.8175,
|
|
"mean_token_accuracy": 0.2081730604171753,
|
|
"num_tokens": 12657006.0,
|
|
"step": 6115
|
|
},
|
|
{
|
|
"entropy": 5.299380254745484,
|
|
"epoch": 5.558836892321672,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00026659034492707473,
|
|
"loss": 4.9028,
|
|
"mean_token_accuracy": 0.1949128732085228,
|
|
"num_tokens": 12667581.0,
|
|
"step": 6120
|
|
},
|
|
{
|
|
"entropy": 5.347793817520142,
|
|
"epoch": 5.563380281690141,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0002662371732274504,
|
|
"loss": 4.8047,
|
|
"mean_token_accuracy": 0.20612967163324356,
|
|
"num_tokens": 12677528.0,
|
|
"step": 6125
|
|
},
|
|
{
|
|
"entropy": 5.298254537582397,
|
|
"epoch": 5.56792367105861,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00026588402314923,
|
|
"loss": 4.721,
|
|
"mean_token_accuracy": 0.20920313745737076,
|
|
"num_tokens": 12687464.0,
|
|
"step": 6130
|
|
},
|
|
{
|
|
"entropy": 5.2673779964447025,
|
|
"epoch": 5.572467060427079,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0002655308955637763,
|
|
"loss": 4.8333,
|
|
"mean_token_accuracy": 0.21132666170597075,
|
|
"num_tokens": 12698192.0,
|
|
"step": 6135
|
|
},
|
|
{
|
|
"entropy": 5.323918867111206,
|
|
"epoch": 5.577010449795548,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0002651777913423965,
|
|
"loss": 4.9039,
|
|
"mean_token_accuracy": 0.19449111372232436,
|
|
"num_tokens": 12709697.0,
|
|
"step": 6140
|
|
},
|
|
{
|
|
"entropy": 5.286316299438477,
|
|
"epoch": 5.581553839164016,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0002648247113563402,
|
|
"loss": 4.7759,
|
|
"mean_token_accuracy": 0.2086230546236038,
|
|
"num_tokens": 12721130.0,
|
|
"step": 6145
|
|
},
|
|
{
|
|
"entropy": 5.228272390365601,
|
|
"epoch": 5.586097228532485,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.00026447165647679703,
|
|
"loss": 4.847,
|
|
"mean_token_accuracy": 0.20677539259195327,
|
|
"num_tokens": 12731701.0,
|
|
"step": 6150
|
|
},
|
|
{
|
|
"entropy": 5.330028438568116,
|
|
"epoch": 5.590640617900954,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.000264118627574895,
|
|
"loss": 4.8728,
|
|
"mean_token_accuracy": 0.20257183015346528,
|
|
"num_tokens": 12741886.0,
|
|
"step": 6155
|
|
},
|
|
{
|
|
"entropy": 5.346784830093384,
|
|
"epoch": 5.595184007269423,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.00026376562552169776,
|
|
"loss": 4.8446,
|
|
"mean_token_accuracy": 0.20482171773910524,
|
|
"num_tokens": 12751814.0,
|
|
"step": 6160
|
|
},
|
|
{
|
|
"entropy": 5.271879196166992,
|
|
"epoch": 5.599727396637892,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.00026341265118820284,
|
|
"loss": 4.8632,
|
|
"mean_token_accuracy": 0.20732915699481963,
|
|
"num_tokens": 12762302.0,
|
|
"step": 6165
|
|
},
|
|
{
|
|
"entropy": 5.271305751800537,
|
|
"epoch": 5.604270786006361,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.00026305970544533903,
|
|
"loss": 4.7597,
|
|
"mean_token_accuracy": 0.2103222653269768,
|
|
"num_tokens": 12771529.0,
|
|
"step": 6170
|
|
},
|
|
{
|
|
"entropy": 5.288051271438599,
|
|
"epoch": 5.60881417537483,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.00026270678916396527,
|
|
"loss": 4.7847,
|
|
"mean_token_accuracy": 0.20511832982301711,
|
|
"num_tokens": 12782270.0,
|
|
"step": 6175
|
|
},
|
|
{
|
|
"entropy": 5.259471321105957,
|
|
"epoch": 5.613357564743298,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.00026235390321486705,
|
|
"loss": 4.825,
|
|
"mean_token_accuracy": 0.20699097365140914,
|
|
"num_tokens": 12792742.0,
|
|
"step": 6180
|
|
},
|
|
{
|
|
"entropy": 5.314690399169922,
|
|
"epoch": 5.617900954111767,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.00026200104846875574,
|
|
"loss": 4.9042,
|
|
"mean_token_accuracy": 0.1921041265130043,
|
|
"num_tokens": 12802740.0,
|
|
"step": 6185
|
|
},
|
|
{
|
|
"entropy": 5.34870662689209,
|
|
"epoch": 5.622444343480236,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.000261648225796265,
|
|
"loss": 4.8621,
|
|
"mean_token_accuracy": 0.20101435035467147,
|
|
"num_tokens": 12813724.0,
|
|
"step": 6190
|
|
},
|
|
{
|
|
"entropy": 5.34779987335205,
|
|
"epoch": 5.626987732848705,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0002612954360679499,
|
|
"loss": 4.819,
|
|
"mean_token_accuracy": 0.20786981731653215,
|
|
"num_tokens": 12823835.0,
|
|
"step": 6195
|
|
},
|
|
{
|
|
"entropy": 5.251586866378784,
|
|
"epoch": 5.631531122217174,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.000260942680154284,
|
|
"loss": 4.744,
|
|
"mean_token_accuracy": 0.21594781428575516,
|
|
"num_tokens": 12834655.0,
|
|
"step": 6200
|
|
},
|
|
{
|
|
"entropy": 5.254903173446655,
|
|
"epoch": 5.636074511585643,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0002605899589256574,
|
|
"loss": 4.8965,
|
|
"mean_token_accuracy": 0.20015126317739487,
|
|
"num_tokens": 12846239.0,
|
|
"step": 6205
|
|
},
|
|
{
|
|
"entropy": 5.2797942638397215,
|
|
"epoch": 5.640617900954112,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00026023727325237463,
|
|
"loss": 4.7045,
|
|
"mean_token_accuracy": 0.21092440634965898,
|
|
"num_tokens": 12857074.0,
|
|
"step": 6210
|
|
},
|
|
{
|
|
"entropy": 5.236799907684326,
|
|
"epoch": 5.645161290322581,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0002598846240046527,
|
|
"loss": 4.715,
|
|
"mean_token_accuracy": 0.21212177276611327,
|
|
"num_tokens": 12867158.0,
|
|
"step": 6215
|
|
},
|
|
{
|
|
"entropy": 5.315386009216309,
|
|
"epoch": 5.64970467969105,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0002595320120526183,
|
|
"loss": 4.8761,
|
|
"mean_token_accuracy": 0.20389238446950914,
|
|
"num_tokens": 12877419.0,
|
|
"step": 6220
|
|
},
|
|
{
|
|
"entropy": 5.393869018554687,
|
|
"epoch": 5.654248069059518,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.00025917943826630666,
|
|
"loss": 4.8555,
|
|
"mean_token_accuracy": 0.20706769824028015,
|
|
"num_tokens": 12888081.0,
|
|
"step": 6225
|
|
},
|
|
{
|
|
"entropy": 5.256203508377075,
|
|
"epoch": 5.658791458427987,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0002588269035156584,
|
|
"loss": 4.8605,
|
|
"mean_token_accuracy": 0.1973317563533783,
|
|
"num_tokens": 12899686.0,
|
|
"step": 6230
|
|
},
|
|
{
|
|
"entropy": 5.244631099700928,
|
|
"epoch": 5.663334847796456,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.00025847440867051796,
|
|
"loss": 4.7916,
|
|
"mean_token_accuracy": 0.20899503380060197,
|
|
"num_tokens": 12910457.0,
|
|
"step": 6235
|
|
},
|
|
{
|
|
"entropy": 5.278490495681763,
|
|
"epoch": 5.667878237164925,
|
|
"grad_norm": 3.9375,
|
|
"learning_rate": 0.0002581219546006314,
|
|
"loss": 4.8052,
|
|
"mean_token_accuracy": 0.20906989574432372,
|
|
"num_tokens": 12920307.0,
|
|
"step": 6240
|
|
},
|
|
{
|
|
"entropy": 5.331907176971436,
|
|
"epoch": 5.672421626533394,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.0002577695421756441,
|
|
"loss": 4.8504,
|
|
"mean_token_accuracy": 0.20317302346229554,
|
|
"num_tokens": 12930818.0,
|
|
"step": 6245
|
|
},
|
|
{
|
|
"entropy": 5.386770725250244,
|
|
"epoch": 5.676965015901863,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0002574171722650986,
|
|
"loss": 4.8768,
|
|
"mean_token_accuracy": 0.19577325731515885,
|
|
"num_tokens": 12941186.0,
|
|
"step": 6250
|
|
},
|
|
{
|
|
"entropy": 5.24178147315979,
|
|
"epoch": 5.681508405270332,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.00025706484573843273,
|
|
"loss": 4.789,
|
|
"mean_token_accuracy": 0.2064160466194153,
|
|
"num_tokens": 12950851.0,
|
|
"step": 6255
|
|
},
|
|
{
|
|
"entropy": 5.281412410736084,
|
|
"epoch": 5.6860517946388,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.000256712563464977,
|
|
"loss": 4.7662,
|
|
"mean_token_accuracy": 0.2097165197134018,
|
|
"num_tokens": 12961572.0,
|
|
"step": 6260
|
|
},
|
|
{
|
|
"entropy": 5.313152742385864,
|
|
"epoch": 5.690595184007269,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0002563603263139532,
|
|
"loss": 4.8509,
|
|
"mean_token_accuracy": 0.19909529834985734,
|
|
"num_tokens": 12972311.0,
|
|
"step": 6265
|
|
},
|
|
{
|
|
"entropy": 5.345450496673584,
|
|
"epoch": 5.695138573375738,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0002560081351544711,
|
|
"loss": 4.8852,
|
|
"mean_token_accuracy": 0.19997814446687698,
|
|
"num_tokens": 12982792.0,
|
|
"step": 6270
|
|
},
|
|
{
|
|
"entropy": 5.221708631515503,
|
|
"epoch": 5.699681962744207,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.00025565599085552776,
|
|
"loss": 4.7051,
|
|
"mean_token_accuracy": 0.2197858899831772,
|
|
"num_tokens": 12992258.0,
|
|
"step": 6275
|
|
},
|
|
{
|
|
"entropy": 5.27285532951355,
|
|
"epoch": 5.704225352112676,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.00025530389428600394,
|
|
"loss": 4.8733,
|
|
"mean_token_accuracy": 0.20247237384319305,
|
|
"num_tokens": 13001799.0,
|
|
"step": 6280
|
|
},
|
|
{
|
|
"entropy": 5.29549241065979,
|
|
"epoch": 5.708768741481145,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0002549518463146631,
|
|
"loss": 4.8518,
|
|
"mean_token_accuracy": 0.2011947050690651,
|
|
"num_tokens": 13012075.0,
|
|
"step": 6285
|
|
},
|
|
{
|
|
"entropy": 5.283776044845581,
|
|
"epoch": 5.713312130849614,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0002545998478101485,
|
|
"loss": 4.9137,
|
|
"mean_token_accuracy": 0.19863687008619307,
|
|
"num_tokens": 13022718.0,
|
|
"step": 6290
|
|
},
|
|
{
|
|
"entropy": 5.25758547782898,
|
|
"epoch": 5.717855520218083,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.00025424789964098154,
|
|
"loss": 4.7685,
|
|
"mean_token_accuracy": 0.20087330937385559,
|
|
"num_tokens": 13032665.0,
|
|
"step": 6295
|
|
},
|
|
{
|
|
"entropy": 5.329877853393555,
|
|
"epoch": 5.722398909586552,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0002538960026755593,
|
|
"loss": 4.9188,
|
|
"mean_token_accuracy": 0.2033736765384674,
|
|
"num_tokens": 13044353.0,
|
|
"step": 6300
|
|
},
|
|
{
|
|
"entropy": 5.3729346752166744,
|
|
"epoch": 5.72694229895502,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00025354415778215255,
|
|
"loss": 4.8968,
|
|
"mean_token_accuracy": 0.2015911117196083,
|
|
"num_tokens": 13055358.0,
|
|
"step": 6305
|
|
},
|
|
{
|
|
"entropy": 5.320140171051025,
|
|
"epoch": 5.731485688323489,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.00025319236582890364,
|
|
"loss": 4.8217,
|
|
"mean_token_accuracy": 0.20425540804862977,
|
|
"num_tokens": 13065036.0,
|
|
"step": 6310
|
|
},
|
|
{
|
|
"entropy": 5.282344579696655,
|
|
"epoch": 5.736029077691958,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.00025284062768382424,
|
|
"loss": 4.8058,
|
|
"mean_token_accuracy": 0.2105084776878357,
|
|
"num_tokens": 13076242.0,
|
|
"step": 6315
|
|
},
|
|
{
|
|
"entropy": 5.272106075286866,
|
|
"epoch": 5.740572467060427,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.0002524889442147932,
|
|
"loss": 4.8052,
|
|
"mean_token_accuracy": 0.20533551275730133,
|
|
"num_tokens": 13086341.0,
|
|
"step": 6320
|
|
},
|
|
{
|
|
"entropy": 5.30084376335144,
|
|
"epoch": 5.745115856428896,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.00025213731628955454,
|
|
"loss": 4.8014,
|
|
"mean_token_accuracy": 0.2030757710337639,
|
|
"num_tokens": 13096257.0,
|
|
"step": 6325
|
|
},
|
|
{
|
|
"entropy": 5.313975667953491,
|
|
"epoch": 5.749659245797365,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.00025178574477571525,
|
|
"loss": 4.8754,
|
|
"mean_token_accuracy": 0.2006542831659317,
|
|
"num_tokens": 13106102.0,
|
|
"step": 6330
|
|
},
|
|
{
|
|
"entropy": 5.2740801811218265,
|
|
"epoch": 5.754202635165834,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00025143423054074305,
|
|
"loss": 4.8857,
|
|
"mean_token_accuracy": 0.20097437053918837,
|
|
"num_tokens": 13116702.0,
|
|
"step": 6335
|
|
},
|
|
{
|
|
"entropy": 5.291833400726318,
|
|
"epoch": 5.758746024534303,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0002510827744519644,
|
|
"loss": 4.8522,
|
|
"mean_token_accuracy": 0.20854814052581788,
|
|
"num_tokens": 13127556.0,
|
|
"step": 6340
|
|
},
|
|
{
|
|
"entropy": 5.252009916305542,
|
|
"epoch": 5.763289413902772,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.00025073137737656226,
|
|
"loss": 4.8028,
|
|
"mean_token_accuracy": 0.2025488257408142,
|
|
"num_tokens": 13136966.0,
|
|
"step": 6345
|
|
},
|
|
{
|
|
"entropy": 5.280330467224121,
|
|
"epoch": 5.76783280327124,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.0002503800401815739,
|
|
"loss": 4.7873,
|
|
"mean_token_accuracy": 0.21039822548627854,
|
|
"num_tokens": 13146374.0,
|
|
"step": 6350
|
|
},
|
|
{
|
|
"entropy": 5.288543701171875,
|
|
"epoch": 5.772376192639709,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.00025002876373388913,
|
|
"loss": 4.8374,
|
|
"mean_token_accuracy": 0.20258293449878692,
|
|
"num_tokens": 13155908.0,
|
|
"step": 6355
|
|
},
|
|
{
|
|
"entropy": 5.305267572402954,
|
|
"epoch": 5.776919582008178,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.00024967754890024737,
|
|
"loss": 4.852,
|
|
"mean_token_accuracy": 0.20167469084262848,
|
|
"num_tokens": 13166626.0,
|
|
"step": 6360
|
|
},
|
|
{
|
|
"entropy": 5.32277512550354,
|
|
"epoch": 5.781462971376647,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0002493263965472366,
|
|
"loss": 4.7285,
|
|
"mean_token_accuracy": 0.213124680519104,
|
|
"num_tokens": 13176798.0,
|
|
"step": 6365
|
|
},
|
|
{
|
|
"entropy": 5.223952341079712,
|
|
"epoch": 5.786006360745116,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0002489753075412901,
|
|
"loss": 4.7742,
|
|
"mean_token_accuracy": 0.21115970611572266,
|
|
"num_tokens": 13186693.0,
|
|
"step": 6370
|
|
},
|
|
{
|
|
"entropy": 5.281402683258056,
|
|
"epoch": 5.790549750113585,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00024862428274868533,
|
|
"loss": 4.826,
|
|
"mean_token_accuracy": 0.19970700442790984,
|
|
"num_tokens": 13197426.0,
|
|
"step": 6375
|
|
},
|
|
{
|
|
"entropy": 5.282175970077515,
|
|
"epoch": 5.795093139482054,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0002482733230355408,
|
|
"loss": 4.888,
|
|
"mean_token_accuracy": 0.19400685876607895,
|
|
"num_tokens": 13207077.0,
|
|
"step": 6380
|
|
},
|
|
{
|
|
"entropy": 5.281008529663086,
|
|
"epoch": 5.799636528850522,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.00024792242926781495,
|
|
"loss": 4.8253,
|
|
"mean_token_accuracy": 0.20408454537391663,
|
|
"num_tokens": 13217179.0,
|
|
"step": 6385
|
|
},
|
|
{
|
|
"entropy": 5.292789125442505,
|
|
"epoch": 5.804179918218991,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.00024757160231130313,
|
|
"loss": 4.8165,
|
|
"mean_token_accuracy": 0.20210576057434082,
|
|
"num_tokens": 13228145.0,
|
|
"step": 6390
|
|
},
|
|
{
|
|
"entropy": 5.406154823303223,
|
|
"epoch": 5.80872330758746,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00024722084303163607,
|
|
"loss": 4.9337,
|
|
"mean_token_accuracy": 0.19519146382808686,
|
|
"num_tokens": 13240050.0,
|
|
"step": 6395
|
|
},
|
|
{
|
|
"entropy": 5.304234886169434,
|
|
"epoch": 5.813266696955929,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0002468701522942774,
|
|
"loss": 4.8113,
|
|
"mean_token_accuracy": 0.20464200973510743,
|
|
"num_tokens": 13251074.0,
|
|
"step": 6400
|
|
},
|
|
{
|
|
"entropy": 5.299965238571167,
|
|
"epoch": 5.817810086324398,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.00024651953096452165,
|
|
"loss": 4.864,
|
|
"mean_token_accuracy": 0.20773452371358872,
|
|
"num_tokens": 13262348.0,
|
|
"step": 6405
|
|
},
|
|
{
|
|
"entropy": 5.294148778915405,
|
|
"epoch": 5.822353475692867,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.00024616897990749196,
|
|
"loss": 4.8723,
|
|
"mean_token_accuracy": 0.1923010379076004,
|
|
"num_tokens": 13272288.0,
|
|
"step": 6410
|
|
},
|
|
{
|
|
"entropy": 5.304819536209107,
|
|
"epoch": 5.826896865061336,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0002458184999881385,
|
|
"loss": 4.8938,
|
|
"mean_token_accuracy": 0.19674990624189376,
|
|
"num_tokens": 13283697.0,
|
|
"step": 6415
|
|
},
|
|
{
|
|
"entropy": 5.331755352020264,
|
|
"epoch": 5.831440254429805,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.00024546809207123534,
|
|
"loss": 4.8596,
|
|
"mean_token_accuracy": 0.20009735375642776,
|
|
"num_tokens": 13294938.0,
|
|
"step": 6420
|
|
},
|
|
{
|
|
"entropy": 5.3148797988891605,
|
|
"epoch": 5.835983643798274,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0002451177570213794,
|
|
"loss": 4.7733,
|
|
"mean_token_accuracy": 0.19766794443130492,
|
|
"num_tokens": 13305358.0,
|
|
"step": 6425
|
|
},
|
|
{
|
|
"entropy": 5.329317712783814,
|
|
"epoch": 5.840527033166742,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.00024476749570298746,
|
|
"loss": 4.8723,
|
|
"mean_token_accuracy": 0.2034990519285202,
|
|
"num_tokens": 13316670.0,
|
|
"step": 6430
|
|
},
|
|
{
|
|
"entropy": 5.300758647918701,
|
|
"epoch": 5.845070422535211,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.00024441730898029456,
|
|
"loss": 4.9439,
|
|
"mean_token_accuracy": 0.19010388106107712,
|
|
"num_tokens": 13327410.0,
|
|
"step": 6435
|
|
},
|
|
{
|
|
"entropy": 5.220479917526245,
|
|
"epoch": 5.84961381190368,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.00024406719771735165,
|
|
"loss": 4.7286,
|
|
"mean_token_accuracy": 0.2064904034137726,
|
|
"num_tokens": 13337280.0,
|
|
"step": 6440
|
|
},
|
|
{
|
|
"entropy": 5.273105192184448,
|
|
"epoch": 5.854157201272149,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.0002437171627780234,
|
|
"loss": 4.8116,
|
|
"mean_token_accuracy": 0.20107331722974778,
|
|
"num_tokens": 13347821.0,
|
|
"step": 6445
|
|
},
|
|
{
|
|
"entropy": 5.286908292770386,
|
|
"epoch": 5.858700590640618,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00024336720502598624,
|
|
"loss": 4.7531,
|
|
"mean_token_accuracy": 0.209895958006382,
|
|
"num_tokens": 13358229.0,
|
|
"step": 6450
|
|
},
|
|
{
|
|
"entropy": 5.253410291671753,
|
|
"epoch": 5.863243980009087,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0002430173253247262,
|
|
"loss": 4.7909,
|
|
"mean_token_accuracy": 0.211697256565094,
|
|
"num_tokens": 13367671.0,
|
|
"step": 6455
|
|
},
|
|
{
|
|
"entropy": 5.23955717086792,
|
|
"epoch": 5.867787369377556,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.00024266752453753655,
|
|
"loss": 4.7667,
|
|
"mean_token_accuracy": 0.2068983182311058,
|
|
"num_tokens": 13377922.0,
|
|
"step": 6460
|
|
},
|
|
{
|
|
"entropy": 5.278090000152588,
|
|
"epoch": 5.872330758746024,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00024231780352751615,
|
|
"loss": 4.8973,
|
|
"mean_token_accuracy": 0.200993849337101,
|
|
"num_tokens": 13388372.0,
|
|
"step": 6465
|
|
},
|
|
{
|
|
"entropy": 5.309360456466675,
|
|
"epoch": 5.876874148114493,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00024196816315756665,
|
|
"loss": 4.8068,
|
|
"mean_token_accuracy": 0.20603621304035186,
|
|
"num_tokens": 13398567.0,
|
|
"step": 6470
|
|
},
|
|
{
|
|
"entropy": 5.267154741287231,
|
|
"epoch": 5.881417537482962,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0002416186042903909,
|
|
"loss": 4.7627,
|
|
"mean_token_accuracy": 0.20913417339324952,
|
|
"num_tokens": 13408192.0,
|
|
"step": 6475
|
|
},
|
|
{
|
|
"entropy": 5.248782348632813,
|
|
"epoch": 5.885960926851431,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.00024126912778849074,
|
|
"loss": 4.8294,
|
|
"mean_token_accuracy": 0.20187100023031235,
|
|
"num_tokens": 13417849.0,
|
|
"step": 6480
|
|
},
|
|
{
|
|
"entropy": 5.308184337615967,
|
|
"epoch": 5.8905043162199,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.00024091973451416472,
|
|
"loss": 4.8583,
|
|
"mean_token_accuracy": 0.20481356233358383,
|
|
"num_tokens": 13429422.0,
|
|
"step": 6485
|
|
},
|
|
{
|
|
"entropy": 5.2476941585540775,
|
|
"epoch": 5.895047705588369,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.00024057042532950597,
|
|
"loss": 4.7908,
|
|
"mean_token_accuracy": 0.21133127957582473,
|
|
"num_tokens": 13439641.0,
|
|
"step": 6490
|
|
},
|
|
{
|
|
"entropy": 5.325441026687622,
|
|
"epoch": 5.899591094956838,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0002402212010964001,
|
|
"loss": 4.8729,
|
|
"mean_token_accuracy": 0.20350584387779236,
|
|
"num_tokens": 13450336.0,
|
|
"step": 6495
|
|
},
|
|
{
|
|
"entropy": 5.283818531036377,
|
|
"epoch": 5.904134484325307,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.00023987206267652334,
|
|
"loss": 4.8413,
|
|
"mean_token_accuracy": 0.20751823782920836,
|
|
"num_tokens": 13461692.0,
|
|
"step": 6500
|
|
},
|
|
{
|
|
"entropy": 5.212767744064331,
|
|
"epoch": 5.908677873693776,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.00023952301093133993,
|
|
"loss": 4.7632,
|
|
"mean_token_accuracy": 0.20289840847253798,
|
|
"num_tokens": 13471517.0,
|
|
"step": 6505
|
|
},
|
|
{
|
|
"entropy": 5.289446210861206,
|
|
"epoch": 5.913221263062244,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.00023917404672210046,
|
|
"loss": 4.8318,
|
|
"mean_token_accuracy": 0.20647483319044113,
|
|
"num_tokens": 13481429.0,
|
|
"step": 6510
|
|
},
|
|
{
|
|
"entropy": 5.276659154891968,
|
|
"epoch": 5.917764652430713,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0002388251709098392,
|
|
"loss": 4.8664,
|
|
"mean_token_accuracy": 0.19550444930791855,
|
|
"num_tokens": 13491404.0,
|
|
"step": 6515
|
|
},
|
|
{
|
|
"entropy": 5.310987329483032,
|
|
"epoch": 5.922308041799182,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00023847638435537283,
|
|
"loss": 4.7292,
|
|
"mean_token_accuracy": 0.21933771371841432,
|
|
"num_tokens": 13500898.0,
|
|
"step": 6520
|
|
},
|
|
{
|
|
"entropy": 5.324627828598023,
|
|
"epoch": 5.926851431167651,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.00023812768791929724,
|
|
"loss": 4.9544,
|
|
"mean_token_accuracy": 0.19979878813028334,
|
|
"num_tokens": 13511654.0,
|
|
"step": 6525
|
|
},
|
|
{
|
|
"entropy": 5.300374174118042,
|
|
"epoch": 5.93139482053612,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.00023777908246198643,
|
|
"loss": 4.7942,
|
|
"mean_token_accuracy": 0.20922391563653947,
|
|
"num_tokens": 13521231.0,
|
|
"step": 6530
|
|
},
|
|
{
|
|
"entropy": 5.291025590896607,
|
|
"epoch": 5.935938209904589,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00023743056884358954,
|
|
"loss": 4.8363,
|
|
"mean_token_accuracy": 0.20721910297870635,
|
|
"num_tokens": 13531738.0,
|
|
"step": 6535
|
|
},
|
|
{
|
|
"entropy": 5.328839206695557,
|
|
"epoch": 5.940481599273058,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.00023708214792402942,
|
|
"loss": 4.8733,
|
|
"mean_token_accuracy": 0.20368369668722153,
|
|
"num_tokens": 13542356.0,
|
|
"step": 6540
|
|
},
|
|
{
|
|
"entropy": 5.199660778045654,
|
|
"epoch": 5.945024988641527,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.00023673382056299997,
|
|
"loss": 4.7457,
|
|
"mean_token_accuracy": 0.21825962960720063,
|
|
"num_tokens": 13551792.0,
|
|
"step": 6545
|
|
},
|
|
{
|
|
"entropy": 5.289476823806763,
|
|
"epoch": 5.949568378009996,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.00023638558761996436,
|
|
"loss": 4.8142,
|
|
"mean_token_accuracy": 0.20456357300281525,
|
|
"num_tokens": 13562568.0,
|
|
"step": 6550
|
|
},
|
|
{
|
|
"entropy": 5.25400676727295,
|
|
"epoch": 5.954111767378464,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00023603744995415277,
|
|
"loss": 4.8429,
|
|
"mean_token_accuracy": 0.20056818723678588,
|
|
"num_tokens": 13573257.0,
|
|
"step": 6555
|
|
},
|
|
{
|
|
"entropy": 5.3117866039276125,
|
|
"epoch": 5.958655156746933,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.00023568940842456026,
|
|
"loss": 4.8712,
|
|
"mean_token_accuracy": 0.20112573951482773,
|
|
"num_tokens": 13584654.0,
|
|
"step": 6560
|
|
},
|
|
{
|
|
"entropy": 5.247479963302612,
|
|
"epoch": 5.963198546115402,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0002353414638899447,
|
|
"loss": 4.7133,
|
|
"mean_token_accuracy": 0.20851473808288573,
|
|
"num_tokens": 13595348.0,
|
|
"step": 6565
|
|
},
|
|
{
|
|
"entropy": 5.305371999740601,
|
|
"epoch": 5.967741935483871,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.00023499361720882468,
|
|
"loss": 4.8986,
|
|
"mean_token_accuracy": 0.20342582911252977,
|
|
"num_tokens": 13605310.0,
|
|
"step": 6570
|
|
},
|
|
{
|
|
"entropy": 5.275442886352539,
|
|
"epoch": 5.97228532485234,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.00023464586923947718,
|
|
"loss": 4.8384,
|
|
"mean_token_accuracy": 0.20134772807359697,
|
|
"num_tokens": 13614944.0,
|
|
"step": 6575
|
|
},
|
|
{
|
|
"entropy": 5.307401514053344,
|
|
"epoch": 5.976828714220809,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00023429822083993596,
|
|
"loss": 4.8148,
|
|
"mean_token_accuracy": 0.20442976355552672,
|
|
"num_tokens": 13624390.0,
|
|
"step": 6580
|
|
},
|
|
{
|
|
"entropy": 5.305225276947022,
|
|
"epoch": 5.981372103589278,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00023395067286798872,
|
|
"loss": 4.8643,
|
|
"mean_token_accuracy": 0.2072729378938675,
|
|
"num_tokens": 13634835.0,
|
|
"step": 6585
|
|
},
|
|
{
|
|
"entropy": 5.315335369110107,
|
|
"epoch": 5.985915492957746,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.00023360322618117563,
|
|
"loss": 4.8654,
|
|
"mean_token_accuracy": 0.1982490211725235,
|
|
"num_tokens": 13645442.0,
|
|
"step": 6590
|
|
},
|
|
{
|
|
"entropy": 5.343017578125,
|
|
"epoch": 5.990458882326215,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00023325588163678674,
|
|
"loss": 4.8846,
|
|
"mean_token_accuracy": 0.2015834778547287,
|
|
"num_tokens": 13655902.0,
|
|
"step": 6595
|
|
},
|
|
{
|
|
"entropy": 5.316901683807373,
|
|
"epoch": 5.995002271694684,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00023290864009186036,
|
|
"loss": 4.8239,
|
|
"mean_token_accuracy": 0.19795109182596207,
|
|
"num_tokens": 13666313.0,
|
|
"step": 6600
|
|
},
|
|
{
|
|
"entropy": 5.333668518066406,
|
|
"epoch": 5.999545661063153,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00023256150240318025,
|
|
"loss": 4.8188,
|
|
"mean_token_accuracy": 0.2079523891210556,
|
|
"num_tokens": 13675428.0,
|
|
"step": 6605
|
|
},
|
|
{
|
|
"entropy": 5.300758308834499,
|
|
"epoch": 6.003634711494775,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00023221446942727438,
|
|
"loss": 4.7453,
|
|
"mean_token_accuracy": 0.2063457253906462,
|
|
"num_tokens": 13684496.0,
|
|
"step": 6610
|
|
},
|
|
{
|
|
"entropy": 5.303838777542114,
|
|
"epoch": 6.008178100863244,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0002318675420204119,
|
|
"loss": 4.7059,
|
|
"mean_token_accuracy": 0.2143103823065758,
|
|
"num_tokens": 13695298.0,
|
|
"step": 6615
|
|
},
|
|
{
|
|
"entropy": 5.268079376220703,
|
|
"epoch": 6.012721490231713,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00023152072103860188,
|
|
"loss": 4.6226,
|
|
"mean_token_accuracy": 0.22000378519296646,
|
|
"num_tokens": 13706042.0,
|
|
"step": 6620
|
|
},
|
|
{
|
|
"entropy": 5.2233161449432375,
|
|
"epoch": 6.017264879600182,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.00023117400733759053,
|
|
"loss": 4.6655,
|
|
"mean_token_accuracy": 0.2098398342728615,
|
|
"num_tokens": 13715511.0,
|
|
"step": 6625
|
|
},
|
|
{
|
|
"entropy": 5.2467933177948,
|
|
"epoch": 6.021808268968651,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0002308274017728595,
|
|
"loss": 4.6088,
|
|
"mean_token_accuracy": 0.2254095569252968,
|
|
"num_tokens": 13725855.0,
|
|
"step": 6630
|
|
},
|
|
{
|
|
"entropy": 5.302747631072998,
|
|
"epoch": 6.026351658337119,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0002304809051996235,
|
|
"loss": 4.6769,
|
|
"mean_token_accuracy": 0.21722275465726854,
|
|
"num_tokens": 13736738.0,
|
|
"step": 6635
|
|
},
|
|
{
|
|
"entropy": 5.2568371295928955,
|
|
"epoch": 6.030895047705588,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0002301345184728284,
|
|
"loss": 4.6811,
|
|
"mean_token_accuracy": 0.2119759812951088,
|
|
"num_tokens": 13746812.0,
|
|
"step": 6640
|
|
},
|
|
{
|
|
"entropy": 5.302924156188965,
|
|
"epoch": 6.035438437074057,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00022978824244714903,
|
|
"loss": 4.6562,
|
|
"mean_token_accuracy": 0.2170855313539505,
|
|
"num_tokens": 13756706.0,
|
|
"step": 6645
|
|
},
|
|
{
|
|
"entropy": 5.303907251358032,
|
|
"epoch": 6.039981826442526,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.00022944207797698707,
|
|
"loss": 4.6744,
|
|
"mean_token_accuracy": 0.2107068568468094,
|
|
"num_tokens": 13767164.0,
|
|
"step": 6650
|
|
},
|
|
{
|
|
"entropy": 5.247895908355713,
|
|
"epoch": 6.044525215810995,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0002290960259164689,
|
|
"loss": 4.6344,
|
|
"mean_token_accuracy": 0.22454475313425065,
|
|
"num_tokens": 13776633.0,
|
|
"step": 6655
|
|
},
|
|
{
|
|
"entropy": 5.253283739089966,
|
|
"epoch": 6.049068605179464,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00022875008711944355,
|
|
"loss": 4.6869,
|
|
"mean_token_accuracy": 0.2164640709757805,
|
|
"num_tokens": 13788281.0,
|
|
"step": 6660
|
|
},
|
|
{
|
|
"entropy": 5.328848266601563,
|
|
"epoch": 6.053611994547933,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.00022840426243948077,
|
|
"loss": 4.7526,
|
|
"mean_token_accuracy": 0.20842964500188826,
|
|
"num_tokens": 13798645.0,
|
|
"step": 6665
|
|
},
|
|
{
|
|
"entropy": 5.3090088844299315,
|
|
"epoch": 6.058155383916402,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00022805855272986842,
|
|
"loss": 4.7669,
|
|
"mean_token_accuracy": 0.20915213376283645,
|
|
"num_tokens": 13809556.0,
|
|
"step": 6670
|
|
},
|
|
{
|
|
"entropy": 5.293160390853882,
|
|
"epoch": 6.062698773284871,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.00022771295884361088,
|
|
"loss": 4.6572,
|
|
"mean_token_accuracy": 0.21649229526519775,
|
|
"num_tokens": 13819842.0,
|
|
"step": 6675
|
|
},
|
|
{
|
|
"entropy": 5.28773455619812,
|
|
"epoch": 6.067242162653339,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0002273674816334268,
|
|
"loss": 4.6823,
|
|
"mean_token_accuracy": 0.21002487242221832,
|
|
"num_tokens": 13829964.0,
|
|
"step": 6680
|
|
},
|
|
{
|
|
"entropy": 5.3475902557373045,
|
|
"epoch": 6.071785552021808,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.00022702212195174664,
|
|
"loss": 4.7507,
|
|
"mean_token_accuracy": 0.21119715124368668,
|
|
"num_tokens": 13840938.0,
|
|
"step": 6685
|
|
},
|
|
{
|
|
"entropy": 5.229467678070068,
|
|
"epoch": 6.076328941390277,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.00022667688065071146,
|
|
"loss": 4.6758,
|
|
"mean_token_accuracy": 0.20808837860822677,
|
|
"num_tokens": 13851045.0,
|
|
"step": 6690
|
|
},
|
|
{
|
|
"entropy": 5.21354570388794,
|
|
"epoch": 6.080872330758746,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.00022633175858216936,
|
|
"loss": 4.5859,
|
|
"mean_token_accuracy": 0.22918188869953154,
|
|
"num_tokens": 13860381.0,
|
|
"step": 6695
|
|
},
|
|
{
|
|
"entropy": 5.2693229675292965,
|
|
"epoch": 6.085415720127215,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00022598675659767515,
|
|
"loss": 4.6508,
|
|
"mean_token_accuracy": 0.2196001335978508,
|
|
"num_tokens": 13872038.0,
|
|
"step": 6700
|
|
},
|
|
{
|
|
"entropy": 5.2937578678131105,
|
|
"epoch": 6.089959109495684,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.00022564187554848663,
|
|
"loss": 4.688,
|
|
"mean_token_accuracy": 0.21878438591957092,
|
|
"num_tokens": 13882714.0,
|
|
"step": 6705
|
|
},
|
|
{
|
|
"entropy": 5.296074295043946,
|
|
"epoch": 6.094502498864153,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.00022529711628556387,
|
|
"loss": 4.6541,
|
|
"mean_token_accuracy": 0.22347534596920013,
|
|
"num_tokens": 13892597.0,
|
|
"step": 6710
|
|
},
|
|
{
|
|
"entropy": 5.2081780433654785,
|
|
"epoch": 6.099045888232622,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00022495247965956567,
|
|
"loss": 4.7513,
|
|
"mean_token_accuracy": 0.20633437037467955,
|
|
"num_tokens": 13902876.0,
|
|
"step": 6715
|
|
},
|
|
{
|
|
"entropy": 5.2399986743927,
|
|
"epoch": 6.10358927760109,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0002246079665208489,
|
|
"loss": 4.62,
|
|
"mean_token_accuracy": 0.21566052287817,
|
|
"num_tokens": 13912750.0,
|
|
"step": 6720
|
|
},
|
|
{
|
|
"entropy": 5.284758567810059,
|
|
"epoch": 6.108132666969559,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00022426357771946544,
|
|
"loss": 4.6563,
|
|
"mean_token_accuracy": 0.21934360563755034,
|
|
"num_tokens": 13922872.0,
|
|
"step": 6725
|
|
},
|
|
{
|
|
"entropy": 5.233842086791992,
|
|
"epoch": 6.112676056338028,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.00022391931410516036,
|
|
"loss": 4.6802,
|
|
"mean_token_accuracy": 0.21330174207687377,
|
|
"num_tokens": 13933299.0,
|
|
"step": 6730
|
|
},
|
|
{
|
|
"entropy": 5.289356994628906,
|
|
"epoch": 6.117219445706497,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00022357517652736992,
|
|
"loss": 4.72,
|
|
"mean_token_accuracy": 0.20811694115400314,
|
|
"num_tokens": 13944277.0,
|
|
"step": 6735
|
|
},
|
|
{
|
|
"entropy": 5.306623220443726,
|
|
"epoch": 6.121762835074966,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.00022323116583521948,
|
|
"loss": 4.7115,
|
|
"mean_token_accuracy": 0.2180721417069435,
|
|
"num_tokens": 13955273.0,
|
|
"step": 6740
|
|
},
|
|
{
|
|
"entropy": 5.273564386367798,
|
|
"epoch": 6.126306224443435,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.00022288728287752109,
|
|
"loss": 4.7051,
|
|
"mean_token_accuracy": 0.21054616570472717,
|
|
"num_tokens": 13965452.0,
|
|
"step": 6745
|
|
},
|
|
{
|
|
"entropy": 5.3288990497589115,
|
|
"epoch": 6.130849613811904,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0002225435285027719,
|
|
"loss": 4.7726,
|
|
"mean_token_accuracy": 0.20762681365013122,
|
|
"num_tokens": 13976424.0,
|
|
"step": 6750
|
|
},
|
|
{
|
|
"entropy": 5.323043489456177,
|
|
"epoch": 6.135393003180373,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.00022219990355915148,
|
|
"loss": 4.7459,
|
|
"mean_token_accuracy": 0.2089594855904579,
|
|
"num_tokens": 13987265.0,
|
|
"step": 6755
|
|
},
|
|
{
|
|
"entropy": 5.311524391174316,
|
|
"epoch": 6.139936392548841,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.00022185640889452036,
|
|
"loss": 4.6701,
|
|
"mean_token_accuracy": 0.21382488459348678,
|
|
"num_tokens": 13996838.0,
|
|
"step": 6760
|
|
},
|
|
{
|
|
"entropy": 5.2443584442138675,
|
|
"epoch": 6.14447978191731,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.00022151304535641747,
|
|
"loss": 4.6526,
|
|
"mean_token_accuracy": 0.21288501620292663,
|
|
"num_tokens": 14007829.0,
|
|
"step": 6765
|
|
},
|
|
{
|
|
"entropy": 5.223824787139892,
|
|
"epoch": 6.149023171285779,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.0002211698137920582,
|
|
"loss": 4.6471,
|
|
"mean_token_accuracy": 0.22127153873443603,
|
|
"num_tokens": 14017993.0,
|
|
"step": 6770
|
|
},
|
|
{
|
|
"entropy": 5.234405183792115,
|
|
"epoch": 6.153566560654248,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.00022082671504833223,
|
|
"loss": 4.6606,
|
|
"mean_token_accuracy": 0.21845913976430892,
|
|
"num_tokens": 14026898.0,
|
|
"step": 6775
|
|
},
|
|
{
|
|
"entropy": 5.166975688934326,
|
|
"epoch": 6.158109950022717,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.00022048374997180175,
|
|
"loss": 4.5696,
|
|
"mean_token_accuracy": 0.22379710376262665,
|
|
"num_tokens": 14037435.0,
|
|
"step": 6780
|
|
},
|
|
{
|
|
"entropy": 5.230389976501465,
|
|
"epoch": 6.162653339391186,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.00022014091940869885,
|
|
"loss": 4.7179,
|
|
"mean_token_accuracy": 0.20694623440504073,
|
|
"num_tokens": 14047243.0,
|
|
"step": 6785
|
|
},
|
|
{
|
|
"entropy": 5.277534866333008,
|
|
"epoch": 6.167196728759655,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.00021979822420492402,
|
|
"loss": 4.6515,
|
|
"mean_token_accuracy": 0.22078562825918197,
|
|
"num_tokens": 14057599.0,
|
|
"step": 6790
|
|
},
|
|
{
|
|
"entropy": 5.285295581817627,
|
|
"epoch": 6.171740118128124,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.00021945566520604337,
|
|
"loss": 4.671,
|
|
"mean_token_accuracy": 0.22439902573823928,
|
|
"num_tokens": 14067603.0,
|
|
"step": 6795
|
|
},
|
|
{
|
|
"entropy": 5.275923395156861,
|
|
"epoch": 6.176283507496592,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0002191132432572875,
|
|
"loss": 4.6401,
|
|
"mean_token_accuracy": 0.218772554397583,
|
|
"num_tokens": 14077805.0,
|
|
"step": 6800
|
|
},
|
|
{
|
|
"entropy": 5.224980401992798,
|
|
"epoch": 6.180826896865061,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00021877095920354818,
|
|
"loss": 4.688,
|
|
"mean_token_accuracy": 0.20523217618465422,
|
|
"num_tokens": 14088552.0,
|
|
"step": 6805
|
|
},
|
|
{
|
|
"entropy": 5.299047756195068,
|
|
"epoch": 6.18537028623353,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.00021842881388937764,
|
|
"loss": 4.73,
|
|
"mean_token_accuracy": 0.21157353073358537,
|
|
"num_tokens": 14099516.0,
|
|
"step": 6810
|
|
},
|
|
{
|
|
"entropy": 5.251043605804443,
|
|
"epoch": 6.189913675601999,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.00021808680815898508,
|
|
"loss": 4.6777,
|
|
"mean_token_accuracy": 0.21392340064048768,
|
|
"num_tokens": 14109155.0,
|
|
"step": 6815
|
|
},
|
|
{
|
|
"entropy": 5.235681438446045,
|
|
"epoch": 6.194457064970468,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.00021774494285623598,
|
|
"loss": 4.6954,
|
|
"mean_token_accuracy": 0.2137138694524765,
|
|
"num_tokens": 14119524.0,
|
|
"step": 6820
|
|
},
|
|
{
|
|
"entropy": 5.299565219879151,
|
|
"epoch": 6.199000454338937,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0002174032188246487,
|
|
"loss": 4.7365,
|
|
"mean_token_accuracy": 0.21564421355724334,
|
|
"num_tokens": 14129761.0,
|
|
"step": 6825
|
|
},
|
|
{
|
|
"entropy": 5.259761142730713,
|
|
"epoch": 6.203543843707406,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.00021706163690739344,
|
|
"loss": 4.6008,
|
|
"mean_token_accuracy": 0.22136663347482682,
|
|
"num_tokens": 14140101.0,
|
|
"step": 6830
|
|
},
|
|
{
|
|
"entropy": 5.289936494827271,
|
|
"epoch": 6.208087233075875,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.00021672019794728963,
|
|
"loss": 4.6927,
|
|
"mean_token_accuracy": 0.20562959909439088,
|
|
"num_tokens": 14150560.0,
|
|
"step": 6835
|
|
},
|
|
{
|
|
"entropy": 5.251890468597412,
|
|
"epoch": 6.212630622444343,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00021637890278680406,
|
|
"loss": 4.5535,
|
|
"mean_token_accuracy": 0.22206026315689087,
|
|
"num_tokens": 14160422.0,
|
|
"step": 6840
|
|
},
|
|
{
|
|
"entropy": 5.270682001113892,
|
|
"epoch": 6.217174011812812,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.00021603775226804845,
|
|
"loss": 4.6893,
|
|
"mean_token_accuracy": 0.20979681760072708,
|
|
"num_tokens": 14170727.0,
|
|
"step": 6845
|
|
},
|
|
{
|
|
"entropy": 5.2603497982025145,
|
|
"epoch": 6.221717401181281,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.00021569674723277783,
|
|
"loss": 4.7469,
|
|
"mean_token_accuracy": 0.20801469981670379,
|
|
"num_tokens": 14181230.0,
|
|
"step": 6850
|
|
},
|
|
{
|
|
"entropy": 5.302300977706909,
|
|
"epoch": 6.22626079054975,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00021535588852238823,
|
|
"loss": 4.7678,
|
|
"mean_token_accuracy": 0.20663876682519913,
|
|
"num_tokens": 14192421.0,
|
|
"step": 6855
|
|
},
|
|
{
|
|
"entropy": 5.25348391532898,
|
|
"epoch": 6.230804179918219,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.00021501517697791479,
|
|
"loss": 4.7247,
|
|
"mean_token_accuracy": 0.2023857891559601,
|
|
"num_tokens": 14202576.0,
|
|
"step": 6860
|
|
},
|
|
{
|
|
"entropy": 5.273741054534912,
|
|
"epoch": 6.235347569286688,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0002146746134400291,
|
|
"loss": 4.7143,
|
|
"mean_token_accuracy": 0.212098228931427,
|
|
"num_tokens": 14213303.0,
|
|
"step": 6865
|
|
},
|
|
{
|
|
"entropy": 5.290825891494751,
|
|
"epoch": 6.239890958655157,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00021433419874903803,
|
|
"loss": 4.6758,
|
|
"mean_token_accuracy": 0.2155788853764534,
|
|
"num_tokens": 14223991.0,
|
|
"step": 6870
|
|
},
|
|
{
|
|
"entropy": 5.246870756149292,
|
|
"epoch": 6.244434348023626,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.00021399393374488097,
|
|
"loss": 4.6759,
|
|
"mean_token_accuracy": 0.22171267718076706,
|
|
"num_tokens": 14234261.0,
|
|
"step": 6875
|
|
},
|
|
{
|
|
"entropy": 5.281177806854248,
|
|
"epoch": 6.248977737392094,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.00021365381926712797,
|
|
"loss": 4.7386,
|
|
"mean_token_accuracy": 0.21424374729394913,
|
|
"num_tokens": 14244719.0,
|
|
"step": 6880
|
|
},
|
|
{
|
|
"entropy": 5.261745595932007,
|
|
"epoch": 6.253521126760563,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00021331385615497756,
|
|
"loss": 4.6916,
|
|
"mean_token_accuracy": 0.2176838904619217,
|
|
"num_tokens": 14256243.0,
|
|
"step": 6885
|
|
},
|
|
{
|
|
"entropy": 5.233337450027466,
|
|
"epoch": 6.258064516129032,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0002129740452472552,
|
|
"loss": 4.6324,
|
|
"mean_token_accuracy": 0.2198032408952713,
|
|
"num_tokens": 14266107.0,
|
|
"step": 6890
|
|
},
|
|
{
|
|
"entropy": 5.225032949447632,
|
|
"epoch": 6.262607905497501,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.00021263438738241026,
|
|
"loss": 4.7226,
|
|
"mean_token_accuracy": 0.20759667307138444,
|
|
"num_tokens": 14275681.0,
|
|
"step": 6895
|
|
},
|
|
{
|
|
"entropy": 5.268295955657959,
|
|
"epoch": 6.26715129486597,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00021229488339851498,
|
|
"loss": 4.6519,
|
|
"mean_token_accuracy": 0.2200671672821045,
|
|
"num_tokens": 14286140.0,
|
|
"step": 6900
|
|
},
|
|
{
|
|
"entropy": 5.293314123153687,
|
|
"epoch": 6.271694684234439,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00021195553413326146,
|
|
"loss": 4.656,
|
|
"mean_token_accuracy": 0.21476451754570008,
|
|
"num_tokens": 14296054.0,
|
|
"step": 6905
|
|
},
|
|
{
|
|
"entropy": 5.214747381210327,
|
|
"epoch": 6.276238073602908,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0002116163404239605,
|
|
"loss": 4.6181,
|
|
"mean_token_accuracy": 0.22793291956186296,
|
|
"num_tokens": 14304500.0,
|
|
"step": 6910
|
|
},
|
|
{
|
|
"entropy": 5.235941982269287,
|
|
"epoch": 6.280781462971377,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00021127730310753866,
|
|
"loss": 4.6783,
|
|
"mean_token_accuracy": 0.2150118976831436,
|
|
"num_tokens": 14314707.0,
|
|
"step": 6915
|
|
},
|
|
{
|
|
"entropy": 5.252275466918945,
|
|
"epoch": 6.285324852339846,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.00021093842302053706,
|
|
"loss": 4.6958,
|
|
"mean_token_accuracy": 0.2079486608505249,
|
|
"num_tokens": 14325302.0,
|
|
"step": 6920
|
|
},
|
|
{
|
|
"entropy": 5.206436729431152,
|
|
"epoch": 6.289868241708314,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.00021059970099910835,
|
|
"loss": 4.7031,
|
|
"mean_token_accuracy": 0.21147979646921158,
|
|
"num_tokens": 14335202.0,
|
|
"step": 6925
|
|
},
|
|
{
|
|
"entropy": 5.322984409332276,
|
|
"epoch": 6.294411631076783,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.00021026113787901568,
|
|
"loss": 4.701,
|
|
"mean_token_accuracy": 0.21540770828723907,
|
|
"num_tokens": 14345394.0,
|
|
"step": 6930
|
|
},
|
|
{
|
|
"entropy": 5.228574800491333,
|
|
"epoch": 6.298955020445252,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.00020992273449562966,
|
|
"loss": 4.647,
|
|
"mean_token_accuracy": 0.22374314367771148,
|
|
"num_tokens": 14355926.0,
|
|
"step": 6935
|
|
},
|
|
{
|
|
"entropy": 5.234753179550171,
|
|
"epoch": 6.303498409813721,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.00020958449168392723,
|
|
"loss": 4.6542,
|
|
"mean_token_accuracy": 0.21779245287179946,
|
|
"num_tokens": 14366380.0,
|
|
"step": 6940
|
|
},
|
|
{
|
|
"entropy": 5.189261722564697,
|
|
"epoch": 6.30804179918219,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0002092464102784888,
|
|
"loss": 4.65,
|
|
"mean_token_accuracy": 0.20998911261558534,
|
|
"num_tokens": 14378258.0,
|
|
"step": 6945
|
|
},
|
|
{
|
|
"entropy": 5.3020116806030275,
|
|
"epoch": 6.312585188550659,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.00020890849111349663,
|
|
"loss": 4.7509,
|
|
"mean_token_accuracy": 0.20844779163599014,
|
|
"num_tokens": 14389370.0,
|
|
"step": 6950
|
|
},
|
|
{
|
|
"entropy": 5.259016275405884,
|
|
"epoch": 6.317128577919128,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00020857073502273266,
|
|
"loss": 4.6756,
|
|
"mean_token_accuracy": 0.22197697460651397,
|
|
"num_tokens": 14399009.0,
|
|
"step": 6955
|
|
},
|
|
{
|
|
"entropy": 5.298092555999756,
|
|
"epoch": 6.321671967287597,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0002082331428395765,
|
|
"loss": 4.6825,
|
|
"mean_token_accuracy": 0.21556483954191208,
|
|
"num_tokens": 14408974.0,
|
|
"step": 6960
|
|
},
|
|
{
|
|
"entropy": 5.240135431289673,
|
|
"epoch": 6.326215356656065,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00020789571539700326,
|
|
"loss": 4.6637,
|
|
"mean_token_accuracy": 0.21823609471321107,
|
|
"num_tokens": 14418801.0,
|
|
"step": 6965
|
|
},
|
|
{
|
|
"entropy": 5.183378887176514,
|
|
"epoch": 6.330758746024534,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.00020755845352758175,
|
|
"loss": 4.6018,
|
|
"mean_token_accuracy": 0.21820259392261504,
|
|
"num_tokens": 14427723.0,
|
|
"step": 6970
|
|
},
|
|
{
|
|
"entropy": 5.326410341262817,
|
|
"epoch": 6.335302135393003,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0002072213580634718,
|
|
"loss": 4.7458,
|
|
"mean_token_accuracy": 0.2103436455130577,
|
|
"num_tokens": 14438963.0,
|
|
"step": 6975
|
|
},
|
|
{
|
|
"entropy": 5.25321774482727,
|
|
"epoch": 6.339845524761472,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0002068844298364233,
|
|
"loss": 4.6227,
|
|
"mean_token_accuracy": 0.21571854799985885,
|
|
"num_tokens": 14449223.0,
|
|
"step": 6980
|
|
},
|
|
{
|
|
"entropy": 5.271266794204712,
|
|
"epoch": 6.344388914129941,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00020654766967777288,
|
|
"loss": 4.6611,
|
|
"mean_token_accuracy": 0.2182995930314064,
|
|
"num_tokens": 14459339.0,
|
|
"step": 6985
|
|
},
|
|
{
|
|
"entropy": 5.28457555770874,
|
|
"epoch": 6.34893230349841,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0002062110784184431,
|
|
"loss": 4.7577,
|
|
"mean_token_accuracy": 0.21234021633863448,
|
|
"num_tokens": 14469093.0,
|
|
"step": 6990
|
|
},
|
|
{
|
|
"entropy": 5.22853274345398,
|
|
"epoch": 6.353475692866879,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.00020587465688893904,
|
|
"loss": 4.7202,
|
|
"mean_token_accuracy": 0.20766536444425582,
|
|
"num_tokens": 14479237.0,
|
|
"step": 6995
|
|
},
|
|
{
|
|
"entropy": 5.27394585609436,
|
|
"epoch": 6.358019082235348,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00020553840591934765,
|
|
"loss": 4.6496,
|
|
"mean_token_accuracy": 0.22202855795621873,
|
|
"num_tokens": 14489647.0,
|
|
"step": 7000
|
|
},
|
|
{
|
|
"epoch": 6.358019082235348,
|
|
"eval_entropy": 5.229576747362004,
|
|
"eval_loss": 5.718924045562744,
|
|
"eval_mean_token_accuracy": 0.17056437588708345,
|
|
"eval_num_tokens": 14489647.0,
|
|
"eval_runtime": 2.7689,
|
|
"eval_samples_per_second": 1240.559,
|
|
"eval_steps_per_second": 155.296,
|
|
"step": 7000
|
|
},
|
|
{
|
|
"entropy": 5.264692163467407,
|
|
"epoch": 6.362562471603816,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0002052023263393346,
|
|
"loss": 4.6711,
|
|
"mean_token_accuracy": 0.21547216922044754,
|
|
"num_tokens": 14500365.0,
|
|
"step": 7005
|
|
},
|
|
{
|
|
"entropy": 5.290500068664551,
|
|
"epoch": 6.367105860972285,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.00020486641897814295,
|
|
"loss": 4.7171,
|
|
"mean_token_accuracy": 0.21604400873184204,
|
|
"num_tokens": 14511181.0,
|
|
"step": 7010
|
|
},
|
|
{
|
|
"entropy": 5.216070556640625,
|
|
"epoch": 6.371649250340754,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.00020453068466459067,
|
|
"loss": 4.5919,
|
|
"mean_token_accuracy": 0.22294471114873887,
|
|
"num_tokens": 14521856.0,
|
|
"step": 7015
|
|
},
|
|
{
|
|
"entropy": 5.238204622268677,
|
|
"epoch": 6.376192639709223,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.00020419512422706893,
|
|
"loss": 4.6888,
|
|
"mean_token_accuracy": 0.2162366673350334,
|
|
"num_tokens": 14531684.0,
|
|
"step": 7020
|
|
},
|
|
{
|
|
"entropy": 5.271568822860718,
|
|
"epoch": 6.380736029077692,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.00020385973849353957,
|
|
"loss": 4.6246,
|
|
"mean_token_accuracy": 0.22239257395267487,
|
|
"num_tokens": 14542353.0,
|
|
"step": 7025
|
|
},
|
|
{
|
|
"entropy": 5.3163152694702145,
|
|
"epoch": 6.385279418446161,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.00020352452829153369,
|
|
"loss": 4.8016,
|
|
"mean_token_accuracy": 0.20455887913703918,
|
|
"num_tokens": 14553138.0,
|
|
"step": 7030
|
|
},
|
|
{
|
|
"entropy": 5.178069639205932,
|
|
"epoch": 6.38982280781463,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.000203189494448149,
|
|
"loss": 4.56,
|
|
"mean_token_accuracy": 0.22111973613500596,
|
|
"num_tokens": 14562602.0,
|
|
"step": 7035
|
|
},
|
|
{
|
|
"entropy": 5.275231790542603,
|
|
"epoch": 6.394366197183099,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00020285463779004837,
|
|
"loss": 4.7185,
|
|
"mean_token_accuracy": 0.21841692477464675,
|
|
"num_tokens": 14573097.0,
|
|
"step": 7040
|
|
},
|
|
{
|
|
"entropy": 5.298450326919555,
|
|
"epoch": 6.398909586551568,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00020251995914345722,
|
|
"loss": 4.7365,
|
|
"mean_token_accuracy": 0.20870611518621446,
|
|
"num_tokens": 14583454.0,
|
|
"step": 7045
|
|
},
|
|
{
|
|
"entropy": 5.316253614425659,
|
|
"epoch": 6.403452975920036,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.00020218545933416181,
|
|
"loss": 4.7167,
|
|
"mean_token_accuracy": 0.2085965484380722,
|
|
"num_tokens": 14594901.0,
|
|
"step": 7050
|
|
},
|
|
{
|
|
"entropy": 5.303460502624512,
|
|
"epoch": 6.407996365288505,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00020185113918750724,
|
|
"loss": 4.7934,
|
|
"mean_token_accuracy": 0.20977483093738555,
|
|
"num_tokens": 14604981.0,
|
|
"step": 7055
|
|
},
|
|
{
|
|
"entropy": 5.295700168609619,
|
|
"epoch": 6.412539754656974,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0002015169995283952,
|
|
"loss": 4.6948,
|
|
"mean_token_accuracy": 0.21246739774942397,
|
|
"num_tokens": 14614848.0,
|
|
"step": 7060
|
|
},
|
|
{
|
|
"entropy": 5.255443811416626,
|
|
"epoch": 6.417083144025443,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.00020118304118128211,
|
|
"loss": 4.6921,
|
|
"mean_token_accuracy": 0.2182166561484337,
|
|
"num_tokens": 14625130.0,
|
|
"step": 7065
|
|
},
|
|
{
|
|
"entropy": 5.275456428527832,
|
|
"epoch": 6.421626533393912,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.00020084926497017703,
|
|
"loss": 4.6953,
|
|
"mean_token_accuracy": 0.21121886968612671,
|
|
"num_tokens": 14635378.0,
|
|
"step": 7070
|
|
},
|
|
{
|
|
"entropy": 5.318049049377441,
|
|
"epoch": 6.426169922762381,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.00020051567171863944,
|
|
"loss": 4.7331,
|
|
"mean_token_accuracy": 0.207826629281044,
|
|
"num_tokens": 14645834.0,
|
|
"step": 7075
|
|
},
|
|
{
|
|
"entropy": 5.262417221069336,
|
|
"epoch": 6.43071331213085,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0002001822622497777,
|
|
"loss": 4.6163,
|
|
"mean_token_accuracy": 0.21683394014835358,
|
|
"num_tokens": 14656391.0,
|
|
"step": 7080
|
|
},
|
|
{
|
|
"entropy": 5.187600374221802,
|
|
"epoch": 6.435256701499318,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.00019984903738624632,
|
|
"loss": 4.6225,
|
|
"mean_token_accuracy": 0.21401940733194352,
|
|
"num_tokens": 14665109.0,
|
|
"step": 7085
|
|
},
|
|
{
|
|
"entropy": 5.267483329772949,
|
|
"epoch": 6.439800090867787,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00019951599795024478,
|
|
"loss": 4.7538,
|
|
"mean_token_accuracy": 0.2081582710146904,
|
|
"num_tokens": 14675608.0,
|
|
"step": 7090
|
|
},
|
|
{
|
|
"entropy": 5.322311162948608,
|
|
"epoch": 6.444343480236256,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.00019918314476351462,
|
|
"loss": 4.7085,
|
|
"mean_token_accuracy": 0.2172422379255295,
|
|
"num_tokens": 14685961.0,
|
|
"step": 7095
|
|
},
|
|
{
|
|
"entropy": 5.281126832962036,
|
|
"epoch": 6.448886869604725,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.00019885047864733803,
|
|
"loss": 4.7245,
|
|
"mean_token_accuracy": 0.21191031187772752,
|
|
"num_tokens": 14695650.0,
|
|
"step": 7100
|
|
},
|
|
{
|
|
"entropy": 5.2004344940185545,
|
|
"epoch": 6.453430258973194,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.00019851800042253553,
|
|
"loss": 4.676,
|
|
"mean_token_accuracy": 0.21180218309164048,
|
|
"num_tokens": 14706490.0,
|
|
"step": 7105
|
|
},
|
|
{
|
|
"entropy": 5.192320728302002,
|
|
"epoch": 6.457973648341663,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0001981857109094642,
|
|
"loss": 4.6054,
|
|
"mean_token_accuracy": 0.2179740384221077,
|
|
"num_tokens": 14715855.0,
|
|
"step": 7110
|
|
},
|
|
{
|
|
"entropy": 5.2093058109283445,
|
|
"epoch": 6.462517037710132,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.00019785361092801524,
|
|
"loss": 4.6322,
|
|
"mean_token_accuracy": 0.2178729310631752,
|
|
"num_tokens": 14726268.0,
|
|
"step": 7115
|
|
},
|
|
{
|
|
"entropy": 5.332222747802734,
|
|
"epoch": 6.467060427078601,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00019752170129761244,
|
|
"loss": 4.7424,
|
|
"mean_token_accuracy": 0.2126945823431015,
|
|
"num_tokens": 14736973.0,
|
|
"step": 7120
|
|
},
|
|
{
|
|
"entropy": 5.1741221904754635,
|
|
"epoch": 6.47160381644707,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0001971899828372098,
|
|
"loss": 4.6658,
|
|
"mean_token_accuracy": 0.21522094160318375,
|
|
"num_tokens": 14747125.0,
|
|
"step": 7125
|
|
},
|
|
{
|
|
"entropy": 5.19835844039917,
|
|
"epoch": 6.476147205815538,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.00019685845636528972,
|
|
"loss": 4.6506,
|
|
"mean_token_accuracy": 0.2157699301838875,
|
|
"num_tokens": 14758036.0,
|
|
"step": 7130
|
|
},
|
|
{
|
|
"entropy": 5.270655393600464,
|
|
"epoch": 6.480690595184007,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.00019652712269986074,
|
|
"loss": 4.7452,
|
|
"mean_token_accuracy": 0.20893458276987076,
|
|
"num_tokens": 14768945.0,
|
|
"step": 7135
|
|
},
|
|
{
|
|
"entropy": 5.272125768661499,
|
|
"epoch": 6.485233984552476,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.00019619598265845556,
|
|
"loss": 4.7366,
|
|
"mean_token_accuracy": 0.21471496373414994,
|
|
"num_tokens": 14779245.0,
|
|
"step": 7140
|
|
},
|
|
{
|
|
"entropy": 5.247568273544312,
|
|
"epoch": 6.489777373920945,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00019586503705812969,
|
|
"loss": 4.6849,
|
|
"mean_token_accuracy": 0.2088216468691826,
|
|
"num_tokens": 14789660.0,
|
|
"step": 7145
|
|
},
|
|
{
|
|
"entropy": 5.2985913276672365,
|
|
"epoch": 6.494320763289414,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0001955342867154582,
|
|
"loss": 4.7505,
|
|
"mean_token_accuracy": 0.2071563795208931,
|
|
"num_tokens": 14799883.0,
|
|
"step": 7150
|
|
},
|
|
{
|
|
"entropy": 5.287864780426025,
|
|
"epoch": 6.498864152657883,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.00019520373244653484,
|
|
"loss": 4.7769,
|
|
"mean_token_accuracy": 0.20970506668090821,
|
|
"num_tokens": 14810433.0,
|
|
"step": 7155
|
|
},
|
|
{
|
|
"entropy": 5.294009256362915,
|
|
"epoch": 6.503407542026352,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0001948733750669693,
|
|
"loss": 4.7066,
|
|
"mean_token_accuracy": 0.2181763842701912,
|
|
"num_tokens": 14820786.0,
|
|
"step": 7160
|
|
},
|
|
{
|
|
"entropy": 5.262348747253418,
|
|
"epoch": 6.50795093139482,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.00019454321539188568,
|
|
"loss": 4.6512,
|
|
"mean_token_accuracy": 0.22108953446149826,
|
|
"num_tokens": 14831558.0,
|
|
"step": 7165
|
|
},
|
|
{
|
|
"entropy": 5.288450288772583,
|
|
"epoch": 6.512494320763289,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.00019421325423592007,
|
|
"loss": 4.7035,
|
|
"mean_token_accuracy": 0.2065589740872383,
|
|
"num_tokens": 14841595.0,
|
|
"step": 7170
|
|
},
|
|
{
|
|
"entropy": 5.213559532165528,
|
|
"epoch": 6.517037710131758,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0001938834924132189,
|
|
"loss": 4.7037,
|
|
"mean_token_accuracy": 0.21330006867647172,
|
|
"num_tokens": 14852102.0,
|
|
"step": 7175
|
|
},
|
|
{
|
|
"entropy": 5.250514125823974,
|
|
"epoch": 6.521581099500227,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0001935539307374366,
|
|
"loss": 4.6647,
|
|
"mean_token_accuracy": 0.21566102802753448,
|
|
"num_tokens": 14862115.0,
|
|
"step": 7180
|
|
},
|
|
{
|
|
"entropy": 5.272056913375854,
|
|
"epoch": 6.526124488868696,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.00019322457002173395,
|
|
"loss": 4.6859,
|
|
"mean_token_accuracy": 0.21799432188272477,
|
|
"num_tokens": 14872240.0,
|
|
"step": 7185
|
|
},
|
|
{
|
|
"entropy": 5.2884684085845945,
|
|
"epoch": 6.530667878237165,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.00019289541107877562,
|
|
"loss": 4.6901,
|
|
"mean_token_accuracy": 0.22175280302762984,
|
|
"num_tokens": 14882736.0,
|
|
"step": 7190
|
|
},
|
|
{
|
|
"entropy": 5.23567681312561,
|
|
"epoch": 6.535211267605634,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.00019256645472072876,
|
|
"loss": 4.7261,
|
|
"mean_token_accuracy": 0.2145736262202263,
|
|
"num_tokens": 14893378.0,
|
|
"step": 7195
|
|
},
|
|
{
|
|
"entropy": 5.3204028606414795,
|
|
"epoch": 6.539754656974103,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.00019223770175926032,
|
|
"loss": 4.7833,
|
|
"mean_token_accuracy": 0.21397204399108888,
|
|
"num_tokens": 14903525.0,
|
|
"step": 7200
|
|
},
|
|
{
|
|
"entropy": 5.348037147521973,
|
|
"epoch": 6.544298046342572,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.00019190915300553574,
|
|
"loss": 4.79,
|
|
"mean_token_accuracy": 0.20053121596574783,
|
|
"num_tokens": 14915053.0,
|
|
"step": 7205
|
|
},
|
|
{
|
|
"entropy": 5.3619061470031735,
|
|
"epoch": 6.54884143571104,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0001915808092702162,
|
|
"loss": 4.8042,
|
|
"mean_token_accuracy": 0.20370916426181793,
|
|
"num_tokens": 14925583.0,
|
|
"step": 7210
|
|
},
|
|
{
|
|
"entropy": 5.287526178359985,
|
|
"epoch": 6.553384825079509,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0001912526713634574,
|
|
"loss": 4.6488,
|
|
"mean_token_accuracy": 0.214762544631958,
|
|
"num_tokens": 14935919.0,
|
|
"step": 7215
|
|
},
|
|
{
|
|
"entropy": 5.254004430770874,
|
|
"epoch": 6.557928214447978,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0001909247400949069,
|
|
"loss": 4.6553,
|
|
"mean_token_accuracy": 0.21520740687847137,
|
|
"num_tokens": 14947335.0,
|
|
"step": 7220
|
|
},
|
|
{
|
|
"entropy": 5.270236492156982,
|
|
"epoch": 6.562471603816447,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.00019059701627370263,
|
|
"loss": 4.7096,
|
|
"mean_token_accuracy": 0.210871185362339,
|
|
"num_tokens": 14959128.0,
|
|
"step": 7225
|
|
},
|
|
{
|
|
"entropy": 5.2503032207489015,
|
|
"epoch": 6.567014993184916,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.00019026950070847025,
|
|
"loss": 4.7173,
|
|
"mean_token_accuracy": 0.21242766231298446,
|
|
"num_tokens": 14969146.0,
|
|
"step": 7230
|
|
},
|
|
{
|
|
"entropy": 5.233587265014648,
|
|
"epoch": 6.571558382553385,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00018994219420732228,
|
|
"loss": 4.697,
|
|
"mean_token_accuracy": 0.21392729729413987,
|
|
"num_tokens": 14980606.0,
|
|
"step": 7235
|
|
},
|
|
{
|
|
"entropy": 5.236815023422241,
|
|
"epoch": 6.576101771921854,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.00018961509757785462,
|
|
"loss": 4.663,
|
|
"mean_token_accuracy": 0.21330504715442658,
|
|
"num_tokens": 14991313.0,
|
|
"step": 7240
|
|
},
|
|
{
|
|
"entropy": 5.30941367149353,
|
|
"epoch": 6.580645161290323,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.00018928821162714587,
|
|
"loss": 4.6768,
|
|
"mean_token_accuracy": 0.21665696203708648,
|
|
"num_tokens": 15000744.0,
|
|
"step": 7245
|
|
},
|
|
{
|
|
"entropy": 5.300522089004517,
|
|
"epoch": 6.585188550658792,
|
|
"grad_norm": 1.8984375,
|
|
"learning_rate": 0.00018896153716175458,
|
|
"loss": 4.6855,
|
|
"mean_token_accuracy": 0.21189938336610795,
|
|
"num_tokens": 15012020.0,
|
|
"step": 7250
|
|
},
|
|
{
|
|
"entropy": 5.200489473342896,
|
|
"epoch": 6.58973194002726,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0001886350749877175,
|
|
"loss": 4.717,
|
|
"mean_token_accuracy": 0.2094978243112564,
|
|
"num_tokens": 15023348.0,
|
|
"step": 7255
|
|
},
|
|
{
|
|
"entropy": 5.173420047760009,
|
|
"epoch": 6.594275329395729,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0001883088259105476,
|
|
"loss": 4.6163,
|
|
"mean_token_accuracy": 0.21609856337308883,
|
|
"num_tokens": 15034029.0,
|
|
"step": 7260
|
|
},
|
|
{
|
|
"entropy": 5.236416149139404,
|
|
"epoch": 6.598818718764198,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.00018798279073523204,
|
|
"loss": 4.755,
|
|
"mean_token_accuracy": 0.20846616327762604,
|
|
"num_tokens": 15043940.0,
|
|
"step": 7265
|
|
},
|
|
{
|
|
"entropy": 5.2414576530456545,
|
|
"epoch": 6.603362108132667,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.00018765697026623017,
|
|
"loss": 4.6581,
|
|
"mean_token_accuracy": 0.21777539253234862,
|
|
"num_tokens": 15054136.0,
|
|
"step": 7270
|
|
},
|
|
{
|
|
"entropy": 5.264234161376953,
|
|
"epoch": 6.607905497501136,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0001873313653074718,
|
|
"loss": 4.617,
|
|
"mean_token_accuracy": 0.22337822169065474,
|
|
"num_tokens": 15064999.0,
|
|
"step": 7275
|
|
},
|
|
{
|
|
"entropy": 5.337272119522095,
|
|
"epoch": 6.612448886869605,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.00018700597666235452,
|
|
"loss": 4.7703,
|
|
"mean_token_accuracy": 0.21523786932229996,
|
|
"num_tokens": 15075033.0,
|
|
"step": 7280
|
|
},
|
|
{
|
|
"entropy": 5.2868541240692135,
|
|
"epoch": 6.616992276238074,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.00018668080513374268,
|
|
"loss": 4.6958,
|
|
"mean_token_accuracy": 0.21372384577989578,
|
|
"num_tokens": 15084694.0,
|
|
"step": 7285
|
|
},
|
|
{
|
|
"entropy": 5.309821701049804,
|
|
"epoch": 6.621535665606542,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.00018635585152396457,
|
|
"loss": 4.7326,
|
|
"mean_token_accuracy": 0.21297669410705566,
|
|
"num_tokens": 15096036.0,
|
|
"step": 7290
|
|
},
|
|
{
|
|
"entropy": 5.229312324523926,
|
|
"epoch": 6.626079054975011,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.000186031116634811,
|
|
"loss": 4.7115,
|
|
"mean_token_accuracy": 0.21172612756490708,
|
|
"num_tokens": 15106036.0,
|
|
"step": 7295
|
|
},
|
|
{
|
|
"entropy": 5.226747846603393,
|
|
"epoch": 6.63062244434348,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.00018570660126753291,
|
|
"loss": 4.6347,
|
|
"mean_token_accuracy": 0.21066423058509826,
|
|
"num_tokens": 15115425.0,
|
|
"step": 7300
|
|
},
|
|
{
|
|
"entropy": 5.192046403884888,
|
|
"epoch": 6.635165833711949,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0001853823062228399,
|
|
"loss": 4.7544,
|
|
"mean_token_accuracy": 0.21067144721746445,
|
|
"num_tokens": 15126244.0,
|
|
"step": 7305
|
|
},
|
|
{
|
|
"entropy": 5.313112258911133,
|
|
"epoch": 6.639709223080418,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.00018505823230089758,
|
|
"loss": 4.7639,
|
|
"mean_token_accuracy": 0.20651431232690812,
|
|
"num_tokens": 15136654.0,
|
|
"step": 7310
|
|
},
|
|
{
|
|
"entropy": 5.320553827285766,
|
|
"epoch": 6.644252612448887,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.00018473438030132633,
|
|
"loss": 4.7314,
|
|
"mean_token_accuracy": 0.21880156248807908,
|
|
"num_tokens": 15146894.0,
|
|
"step": 7315
|
|
},
|
|
{
|
|
"entropy": 5.2643293857574465,
|
|
"epoch": 6.648796001817356,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0001844107510231985,
|
|
"loss": 4.6707,
|
|
"mean_token_accuracy": 0.21097416281700135,
|
|
"num_tokens": 15157123.0,
|
|
"step": 7320
|
|
},
|
|
{
|
|
"entropy": 5.2234776496887205,
|
|
"epoch": 6.653339391185825,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.00018408734526503744,
|
|
"loss": 4.7773,
|
|
"mean_token_accuracy": 0.20782003551721573,
|
|
"num_tokens": 15168214.0,
|
|
"step": 7325
|
|
},
|
|
{
|
|
"entropy": 5.2911478042602536,
|
|
"epoch": 6.657882780554294,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.00018376416382481442,
|
|
"loss": 4.7023,
|
|
"mean_token_accuracy": 0.2146631062030792,
|
|
"num_tokens": 15178508.0,
|
|
"step": 7330
|
|
},
|
|
{
|
|
"entropy": 5.253564119338989,
|
|
"epoch": 6.662426169922762,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.00018344120749994787,
|
|
"loss": 4.7224,
|
|
"mean_token_accuracy": 0.2133822575211525,
|
|
"num_tokens": 15189471.0,
|
|
"step": 7335
|
|
},
|
|
{
|
|
"entropy": 5.298365354537964,
|
|
"epoch": 6.666969559291231,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.00018311847708730005,
|
|
"loss": 4.6916,
|
|
"mean_token_accuracy": 0.21255020201206207,
|
|
"num_tokens": 15199269.0,
|
|
"step": 7340
|
|
},
|
|
{
|
|
"entropy": 5.2467235088348385,
|
|
"epoch": 6.6715129486597,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0001827959733831765,
|
|
"loss": 4.746,
|
|
"mean_token_accuracy": 0.20643223822116852,
|
|
"num_tokens": 15209746.0,
|
|
"step": 7345
|
|
},
|
|
{
|
|
"entropy": 5.260730743408203,
|
|
"epoch": 6.676056338028169,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.00018247369718332274,
|
|
"loss": 4.7239,
|
|
"mean_token_accuracy": 0.21039548963308335,
|
|
"num_tokens": 15219476.0,
|
|
"step": 7350
|
|
},
|
|
{
|
|
"entropy": 5.283915710449219,
|
|
"epoch": 6.680599727396638,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.00018215164928292354,
|
|
"loss": 4.757,
|
|
"mean_token_accuracy": 0.21095311641693115,
|
|
"num_tokens": 15229053.0,
|
|
"step": 7355
|
|
},
|
|
{
|
|
"entropy": 5.2208695888519285,
|
|
"epoch": 6.685143116765107,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00018182983047659984,
|
|
"loss": 4.6641,
|
|
"mean_token_accuracy": 0.21401648074388505,
|
|
"num_tokens": 15238657.0,
|
|
"step": 7360
|
|
},
|
|
{
|
|
"entropy": 5.270431566238403,
|
|
"epoch": 6.689686506133576,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.00018150824155840778,
|
|
"loss": 4.6784,
|
|
"mean_token_accuracy": 0.21246907413005828,
|
|
"num_tokens": 15248876.0,
|
|
"step": 7365
|
|
},
|
|
{
|
|
"entropy": 5.31629581451416,
|
|
"epoch": 6.694229895502044,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0001811868833218358,
|
|
"loss": 4.7709,
|
|
"mean_token_accuracy": 0.2151926651597023,
|
|
"num_tokens": 15259836.0,
|
|
"step": 7370
|
|
},
|
|
{
|
|
"entropy": 5.303498458862305,
|
|
"epoch": 6.698773284870513,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00018086575655980376,
|
|
"loss": 4.6535,
|
|
"mean_token_accuracy": 0.21660005450248718,
|
|
"num_tokens": 15270151.0,
|
|
"step": 7375
|
|
},
|
|
{
|
|
"entropy": 5.2867570400238035,
|
|
"epoch": 6.703316674238982,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00018054486206465952,
|
|
"loss": 4.7713,
|
|
"mean_token_accuracy": 0.20624330639839172,
|
|
"num_tokens": 15281538.0,
|
|
"step": 7380
|
|
},
|
|
{
|
|
"entropy": 5.267093086242676,
|
|
"epoch": 6.707860063607451,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0001802242006281788,
|
|
"loss": 4.6533,
|
|
"mean_token_accuracy": 0.20972132235765456,
|
|
"num_tokens": 15291821.0,
|
|
"step": 7385
|
|
},
|
|
{
|
|
"entropy": 5.250594854354858,
|
|
"epoch": 6.71240345297592,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00017990377304156165,
|
|
"loss": 4.6904,
|
|
"mean_token_accuracy": 0.2164827585220337,
|
|
"num_tokens": 15302772.0,
|
|
"step": 7390
|
|
},
|
|
{
|
|
"entropy": 5.219211626052856,
|
|
"epoch": 6.716946842344389,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0001795835800954312,
|
|
"loss": 4.6926,
|
|
"mean_token_accuracy": 0.2107630267739296,
|
|
"num_tokens": 15314172.0,
|
|
"step": 7395
|
|
},
|
|
{
|
|
"entropy": 5.265444421768189,
|
|
"epoch": 6.721490231712858,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.00017926362257983174,
|
|
"loss": 4.7905,
|
|
"mean_token_accuracy": 0.2070370301604271,
|
|
"num_tokens": 15324849.0,
|
|
"step": 7400
|
|
},
|
|
{
|
|
"entropy": 5.308561038970947,
|
|
"epoch": 6.726033621081327,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0001789439012842269,
|
|
"loss": 4.6947,
|
|
"mean_token_accuracy": 0.2060231789946556,
|
|
"num_tokens": 15334985.0,
|
|
"step": 7405
|
|
},
|
|
{
|
|
"entropy": 5.326310777664185,
|
|
"epoch": 6.730577010449796,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00017862441699749687,
|
|
"loss": 4.7264,
|
|
"mean_token_accuracy": 0.21369918882846833,
|
|
"num_tokens": 15346511.0,
|
|
"step": 7410
|
|
},
|
|
{
|
|
"entropy": 5.36603364944458,
|
|
"epoch": 6.735120399818264,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0001783051705079375,
|
|
"loss": 4.8138,
|
|
"mean_token_accuracy": 0.20637497007846833,
|
|
"num_tokens": 15356859.0,
|
|
"step": 7415
|
|
},
|
|
{
|
|
"entropy": 5.218096399307251,
|
|
"epoch": 6.739663789186733,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.00017798616260325767,
|
|
"loss": 4.6837,
|
|
"mean_token_accuracy": 0.2139544352889061,
|
|
"num_tokens": 15367124.0,
|
|
"step": 7420
|
|
},
|
|
{
|
|
"entropy": 5.216539669036865,
|
|
"epoch": 6.744207178555202,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0001776673940705778,
|
|
"loss": 4.6952,
|
|
"mean_token_accuracy": 0.21083905398845673,
|
|
"num_tokens": 15376931.0,
|
|
"step": 7425
|
|
},
|
|
{
|
|
"entropy": 5.2629852294921875,
|
|
"epoch": 6.748750567923671,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0001773488656964276,
|
|
"loss": 4.7029,
|
|
"mean_token_accuracy": 0.21056810170412063,
|
|
"num_tokens": 15386488.0,
|
|
"step": 7430
|
|
},
|
|
{
|
|
"entropy": 5.279999732971191,
|
|
"epoch": 6.75329395729214,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.000177030578266744,
|
|
"loss": 4.6248,
|
|
"mean_token_accuracy": 0.22530110478401183,
|
|
"num_tokens": 15395776.0,
|
|
"step": 7435
|
|
},
|
|
{
|
|
"entropy": 5.307156038284302,
|
|
"epoch": 6.757837346660609,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.00017671253256686963,
|
|
"loss": 4.7596,
|
|
"mean_token_accuracy": 0.21363162696361543,
|
|
"num_tokens": 15406733.0,
|
|
"step": 7440
|
|
},
|
|
{
|
|
"entropy": 5.255329179763794,
|
|
"epoch": 6.762380736029078,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00017639472938155075,
|
|
"loss": 4.6802,
|
|
"mean_token_accuracy": 0.22396357208490372,
|
|
"num_tokens": 15416697.0,
|
|
"step": 7445
|
|
},
|
|
{
|
|
"entropy": 5.2115545749664305,
|
|
"epoch": 6.766924125397547,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.00017607716949493514,
|
|
"loss": 4.6027,
|
|
"mean_token_accuracy": 0.22271675765514373,
|
|
"num_tokens": 15426445.0,
|
|
"step": 7450
|
|
},
|
|
{
|
|
"entropy": 5.2136040210723875,
|
|
"epoch": 6.771467514766016,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.00017575985369057008,
|
|
"loss": 4.6142,
|
|
"mean_token_accuracy": 0.21914252787828445,
|
|
"num_tokens": 15436861.0,
|
|
"step": 7455
|
|
},
|
|
{
|
|
"entropy": 5.230067110061645,
|
|
"epoch": 6.776010904134484,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0001754427827514008,
|
|
"loss": 4.6953,
|
|
"mean_token_accuracy": 0.2138902187347412,
|
|
"num_tokens": 15448167.0,
|
|
"step": 7460
|
|
},
|
|
{
|
|
"entropy": 5.208525848388672,
|
|
"epoch": 6.780554293502953,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00017512595745976855,
|
|
"loss": 4.6333,
|
|
"mean_token_accuracy": 0.21863898187875747,
|
|
"num_tokens": 15458340.0,
|
|
"step": 7465
|
|
},
|
|
{
|
|
"entropy": 5.246536064147949,
|
|
"epoch": 6.785097682871422,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.00017480937859740793,
|
|
"loss": 4.6817,
|
|
"mean_token_accuracy": 0.2208716943860054,
|
|
"num_tokens": 15469475.0,
|
|
"step": 7470
|
|
},
|
|
{
|
|
"entropy": 5.288869333267212,
|
|
"epoch": 6.789641072239891,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00017449304694544608,
|
|
"loss": 4.7307,
|
|
"mean_token_accuracy": 0.2094472572207451,
|
|
"num_tokens": 15480077.0,
|
|
"step": 7475
|
|
},
|
|
{
|
|
"entropy": 5.229336309432983,
|
|
"epoch": 6.79418446160836,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.00017417696328439974,
|
|
"loss": 4.7049,
|
|
"mean_token_accuracy": 0.21399389803409577,
|
|
"num_tokens": 15490716.0,
|
|
"step": 7480
|
|
},
|
|
{
|
|
"entropy": 5.253655529022216,
|
|
"epoch": 6.798727850976829,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.00017386112839417402,
|
|
"loss": 4.6504,
|
|
"mean_token_accuracy": 0.21386270672082902,
|
|
"num_tokens": 15501310.0,
|
|
"step": 7485
|
|
},
|
|
{
|
|
"entropy": 5.304090738296509,
|
|
"epoch": 6.803271240345298,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00017354554305405994,
|
|
"loss": 4.7318,
|
|
"mean_token_accuracy": 0.21294136494398117,
|
|
"num_tokens": 15512325.0,
|
|
"step": 7490
|
|
},
|
|
{
|
|
"entropy": 5.223036670684815,
|
|
"epoch": 6.807814629713766,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0001732302080427332,
|
|
"loss": 4.6834,
|
|
"mean_token_accuracy": 0.21471725702285765,
|
|
"num_tokens": 15522963.0,
|
|
"step": 7495
|
|
},
|
|
{
|
|
"entropy": 5.242479133605957,
|
|
"epoch": 6.812358019082235,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.00017291512413825148,
|
|
"loss": 4.6929,
|
|
"mean_token_accuracy": 0.22209383696317672,
|
|
"num_tokens": 15533163.0,
|
|
"step": 7500
|
|
},
|
|
{
|
|
"entropy": 5.316690731048584,
|
|
"epoch": 6.816901408450704,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.00017260029211805297,
|
|
"loss": 4.782,
|
|
"mean_token_accuracy": 0.20672075301408768,
|
|
"num_tokens": 15543623.0,
|
|
"step": 7505
|
|
},
|
|
{
|
|
"entropy": 5.277825832366943,
|
|
"epoch": 6.821444797819173,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.00017228571275895434,
|
|
"loss": 4.7208,
|
|
"mean_token_accuracy": 0.2110538974404335,
|
|
"num_tokens": 15554050.0,
|
|
"step": 7510
|
|
},
|
|
{
|
|
"entropy": 5.219334363937378,
|
|
"epoch": 6.825988187187642,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00017197138683714902,
|
|
"loss": 4.6157,
|
|
"mean_token_accuracy": 0.22442324608564376,
|
|
"num_tokens": 15563241.0,
|
|
"step": 7515
|
|
},
|
|
{
|
|
"entropy": 5.226173067092896,
|
|
"epoch": 6.830531576556111,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0001716573151282049,
|
|
"loss": 4.6919,
|
|
"mean_token_accuracy": 0.21207820028066635,
|
|
"num_tokens": 15573497.0,
|
|
"step": 7520
|
|
},
|
|
{
|
|
"entropy": 5.264763402938843,
|
|
"epoch": 6.83507496592458,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0001713434984070627,
|
|
"loss": 4.7554,
|
|
"mean_token_accuracy": 0.20804878175258637,
|
|
"num_tokens": 15583806.0,
|
|
"step": 7525
|
|
},
|
|
{
|
|
"entropy": 5.2838132858276365,
|
|
"epoch": 6.839618355293049,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.00017102993744803392,
|
|
"loss": 4.7775,
|
|
"mean_token_accuracy": 0.20453995019197463,
|
|
"num_tokens": 15593548.0,
|
|
"step": 7530
|
|
},
|
|
{
|
|
"entropy": 5.239691972732544,
|
|
"epoch": 6.844161744661518,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.00017071663302479923,
|
|
"loss": 4.6738,
|
|
"mean_token_accuracy": 0.2162626266479492,
|
|
"num_tokens": 15604772.0,
|
|
"step": 7535
|
|
},
|
|
{
|
|
"entropy": 5.241588497161866,
|
|
"epoch": 6.848705134029986,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00017040358591040606,
|
|
"loss": 4.6617,
|
|
"mean_token_accuracy": 0.21749851554632188,
|
|
"num_tokens": 15615448.0,
|
|
"step": 7540
|
|
},
|
|
{
|
|
"entropy": 5.232385063171387,
|
|
"epoch": 6.853248523398455,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.000170090796877267,
|
|
"loss": 4.6813,
|
|
"mean_token_accuracy": 0.2170141264796257,
|
|
"num_tokens": 15626054.0,
|
|
"step": 7545
|
|
},
|
|
{
|
|
"entropy": 5.305236721038819,
|
|
"epoch": 6.857791912766924,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.00016977826669715783,
|
|
"loss": 4.7381,
|
|
"mean_token_accuracy": 0.21257566213607787,
|
|
"num_tokens": 15635384.0,
|
|
"step": 7550
|
|
},
|
|
{
|
|
"entropy": 5.3189826011657715,
|
|
"epoch": 6.862335302135393,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.000169465996141216,
|
|
"loss": 4.7931,
|
|
"mean_token_accuracy": 0.2103201314806938,
|
|
"num_tokens": 15645564.0,
|
|
"step": 7555
|
|
},
|
|
{
|
|
"entropy": 5.266808557510376,
|
|
"epoch": 6.866878691503862,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0001691539859799377,
|
|
"loss": 4.6027,
|
|
"mean_token_accuracy": 0.22175280302762984,
|
|
"num_tokens": 15654680.0,
|
|
"step": 7560
|
|
},
|
|
{
|
|
"entropy": 5.234835815429688,
|
|
"epoch": 6.871422080872331,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00016884223698317722,
|
|
"loss": 4.6662,
|
|
"mean_token_accuracy": 0.2134086847305298,
|
|
"num_tokens": 15665051.0,
|
|
"step": 7565
|
|
},
|
|
{
|
|
"entropy": 5.240856313705445,
|
|
"epoch": 6.8759654702408,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0001685307499201441,
|
|
"loss": 4.7275,
|
|
"mean_token_accuracy": 0.21559721678495408,
|
|
"num_tokens": 15675567.0,
|
|
"step": 7570
|
|
},
|
|
{
|
|
"entropy": 5.274003314971924,
|
|
"epoch": 6.880508859609268,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0001682195255594019,
|
|
"loss": 4.6757,
|
|
"mean_token_accuracy": 0.21032726019620895,
|
|
"num_tokens": 15685137.0,
|
|
"step": 7575
|
|
},
|
|
{
|
|
"entropy": 5.251150608062744,
|
|
"epoch": 6.885052248977737,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.00016790856466886544,
|
|
"loss": 4.7028,
|
|
"mean_token_accuracy": 0.21748256236314772,
|
|
"num_tokens": 15695806.0,
|
|
"step": 7580
|
|
},
|
|
{
|
|
"entropy": 5.261500310897827,
|
|
"epoch": 6.889595638346206,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00016759786801580018,
|
|
"loss": 4.7877,
|
|
"mean_token_accuracy": 0.20877626687288284,
|
|
"num_tokens": 15705994.0,
|
|
"step": 7585
|
|
},
|
|
{
|
|
"entropy": 5.216836643218994,
|
|
"epoch": 6.894139027714675,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.00016728743636681897,
|
|
"loss": 4.6302,
|
|
"mean_token_accuracy": 0.223364520072937,
|
|
"num_tokens": 15716209.0,
|
|
"step": 7590
|
|
},
|
|
{
|
|
"entropy": 5.261210298538208,
|
|
"epoch": 6.898682417083144,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00016697727048788118,
|
|
"loss": 4.7512,
|
|
"mean_token_accuracy": 0.21472457945346832,
|
|
"num_tokens": 15726851.0,
|
|
"step": 7595
|
|
},
|
|
{
|
|
"entropy": 5.2699919700622555,
|
|
"epoch": 6.903225806451613,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00016666737114429017,
|
|
"loss": 4.6625,
|
|
"mean_token_accuracy": 0.21965292096138,
|
|
"num_tokens": 15737693.0,
|
|
"step": 7600
|
|
},
|
|
{
|
|
"entropy": 5.285038995742798,
|
|
"epoch": 6.907769195820082,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0001663577391006919,
|
|
"loss": 4.6319,
|
|
"mean_token_accuracy": 0.22462470531463624,
|
|
"num_tokens": 15747768.0,
|
|
"step": 7605
|
|
},
|
|
{
|
|
"entropy": 5.298560619354248,
|
|
"epoch": 6.912312585188551,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.00016604837512107263,
|
|
"loss": 4.756,
|
|
"mean_token_accuracy": 0.2145906001329422,
|
|
"num_tokens": 15757203.0,
|
|
"step": 7610
|
|
},
|
|
{
|
|
"entropy": 5.336838960647583,
|
|
"epoch": 6.91685597455702,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00016573927996875714,
|
|
"loss": 4.7275,
|
|
"mean_token_accuracy": 0.21850882470607758,
|
|
"num_tokens": 15769096.0,
|
|
"step": 7615
|
|
},
|
|
{
|
|
"entropy": 5.1565868854522705,
|
|
"epoch": 6.921399363925488,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00016543045440640697,
|
|
"loss": 4.6464,
|
|
"mean_token_accuracy": 0.22044724971055984,
|
|
"num_tokens": 15779427.0,
|
|
"step": 7620
|
|
},
|
|
{
|
|
"entropy": 5.190261363983154,
|
|
"epoch": 6.925942753293957,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.00016512189919601865,
|
|
"loss": 4.6595,
|
|
"mean_token_accuracy": 0.21732058972120286,
|
|
"num_tokens": 15789068.0,
|
|
"step": 7625
|
|
},
|
|
{
|
|
"entropy": 5.201836633682251,
|
|
"epoch": 6.930486142662426,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0001648136150989214,
|
|
"loss": 4.6224,
|
|
"mean_token_accuracy": 0.21843535602092742,
|
|
"num_tokens": 15798678.0,
|
|
"step": 7630
|
|
},
|
|
{
|
|
"entropy": 5.305319309234619,
|
|
"epoch": 6.935029532030895,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0001645056028757756,
|
|
"loss": 4.7305,
|
|
"mean_token_accuracy": 0.21115941554307938,
|
|
"num_tokens": 15809330.0,
|
|
"step": 7635
|
|
},
|
|
{
|
|
"entropy": 5.314718246459961,
|
|
"epoch": 6.939572921399364,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00016419786328657066,
|
|
"loss": 4.7263,
|
|
"mean_token_accuracy": 0.2176973655819893,
|
|
"num_tokens": 15820011.0,
|
|
"step": 7640
|
|
},
|
|
{
|
|
"entropy": 5.285129737854004,
|
|
"epoch": 6.944116310767833,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00016389039709062376,
|
|
"loss": 4.7271,
|
|
"mean_token_accuracy": 0.21102142035961152,
|
|
"num_tokens": 15830395.0,
|
|
"step": 7645
|
|
},
|
|
{
|
|
"entropy": 5.24210114479065,
|
|
"epoch": 6.948659700136302,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00016358320504657677,
|
|
"loss": 4.6922,
|
|
"mean_token_accuracy": 0.214350163936615,
|
|
"num_tokens": 15840605.0,
|
|
"step": 7650
|
|
},
|
|
{
|
|
"entropy": 5.245719385147095,
|
|
"epoch": 6.95320308950477,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00016327628791239576,
|
|
"loss": 4.7135,
|
|
"mean_token_accuracy": 0.21477331072092057,
|
|
"num_tokens": 15850632.0,
|
|
"step": 7655
|
|
},
|
|
{
|
|
"entropy": 5.22693567276001,
|
|
"epoch": 6.957746478873239,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.00016296964644536816,
|
|
"loss": 4.6366,
|
|
"mean_token_accuracy": 0.21379828006029128,
|
|
"num_tokens": 15860929.0,
|
|
"step": 7660
|
|
},
|
|
{
|
|
"entropy": 5.332159090042114,
|
|
"epoch": 6.962289868241708,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0001626632814021015,
|
|
"loss": 4.7033,
|
|
"mean_token_accuracy": 0.21682854145765304,
|
|
"num_tokens": 15871983.0,
|
|
"step": 7665
|
|
},
|
|
{
|
|
"entropy": 5.246991920471191,
|
|
"epoch": 6.966833257610177,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.00016235719353852079,
|
|
"loss": 4.6884,
|
|
"mean_token_accuracy": 0.21538904756307603,
|
|
"num_tokens": 15882437.0,
|
|
"step": 7670
|
|
},
|
|
{
|
|
"entropy": 5.176268863677978,
|
|
"epoch": 6.971376646978646,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00016205138360986753,
|
|
"loss": 4.6579,
|
|
"mean_token_accuracy": 0.21808396577835082,
|
|
"num_tokens": 15892627.0,
|
|
"step": 7675
|
|
},
|
|
{
|
|
"entropy": 5.278589391708374,
|
|
"epoch": 6.975920036347115,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00016174585237069738,
|
|
"loss": 4.6705,
|
|
"mean_token_accuracy": 0.22202298790216446,
|
|
"num_tokens": 15903336.0,
|
|
"step": 7680
|
|
},
|
|
{
|
|
"entropy": 5.265566778182984,
|
|
"epoch": 6.980463425715584,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00016144060057487824,
|
|
"loss": 4.7305,
|
|
"mean_token_accuracy": 0.21383863538503647,
|
|
"num_tokens": 15913877.0,
|
|
"step": 7685
|
|
},
|
|
{
|
|
"entropy": 5.246555519104004,
|
|
"epoch": 6.985006815084053,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00016113562897558849,
|
|
"loss": 4.6108,
|
|
"mean_token_accuracy": 0.2205919787287712,
|
|
"num_tokens": 15923991.0,
|
|
"step": 7690
|
|
},
|
|
{
|
|
"entropy": 5.237468624114991,
|
|
"epoch": 6.989550204452522,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0001608309383253154,
|
|
"loss": 4.6741,
|
|
"mean_token_accuracy": 0.2117405503988266,
|
|
"num_tokens": 15933793.0,
|
|
"step": 7695
|
|
},
|
|
{
|
|
"entropy": 5.262516975402832,
|
|
"epoch": 6.99409359382099,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0001605265293758528,
|
|
"loss": 4.7089,
|
|
"mean_token_accuracy": 0.2017163097858429,
|
|
"num_tokens": 15943901.0,
|
|
"step": 7700
|
|
},
|
|
{
|
|
"entropy": 5.204751443862915,
|
|
"epoch": 6.998636983189459,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00016022240287829947,
|
|
"loss": 4.5572,
|
|
"mean_token_accuracy": 0.2285539448261261,
|
|
"num_tokens": 15953244.0,
|
|
"step": 7705
|
|
},
|
|
{
|
|
"entropy": 5.2212371826171875,
|
|
"epoch": 7.002726033621081,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.00015991855958305724,
|
|
"loss": 4.6001,
|
|
"mean_token_accuracy": 0.22644261519114176,
|
|
"num_tokens": 15961922.0,
|
|
"step": 7710
|
|
},
|
|
{
|
|
"entropy": 5.261759519577026,
|
|
"epoch": 7.00726942298955,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.00015961500023982945,
|
|
"loss": 4.5679,
|
|
"mean_token_accuracy": 0.22495882362127304,
|
|
"num_tokens": 15972298.0,
|
|
"step": 7715
|
|
},
|
|
{
|
|
"entropy": 5.261226034164428,
|
|
"epoch": 7.011812812358019,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.00015931172559761848,
|
|
"loss": 4.6254,
|
|
"mean_token_accuracy": 0.22781113386154175,
|
|
"num_tokens": 15982279.0,
|
|
"step": 7720
|
|
},
|
|
{
|
|
"entropy": 5.20067777633667,
|
|
"epoch": 7.016356201726488,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0001590087364047243,
|
|
"loss": 4.5176,
|
|
"mean_token_accuracy": 0.22630156427621842,
|
|
"num_tokens": 15992397.0,
|
|
"step": 7725
|
|
},
|
|
{
|
|
"entropy": 5.345102787017822,
|
|
"epoch": 7.020899591094957,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00015870603340874267,
|
|
"loss": 4.7062,
|
|
"mean_token_accuracy": 0.2164225086569786,
|
|
"num_tokens": 16002683.0,
|
|
"step": 7730
|
|
},
|
|
{
|
|
"entropy": 5.30378737449646,
|
|
"epoch": 7.025442980463426,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.00015840361735656333,
|
|
"loss": 4.608,
|
|
"mean_token_accuracy": 0.22884936034679412,
|
|
"num_tokens": 16013431.0,
|
|
"step": 7735
|
|
},
|
|
{
|
|
"entropy": 5.243222618103028,
|
|
"epoch": 7.029986369831895,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00015810148899436747,
|
|
"loss": 4.5289,
|
|
"mean_token_accuracy": 0.2237053096294403,
|
|
"num_tokens": 16024165.0,
|
|
"step": 7740
|
|
},
|
|
{
|
|
"entropy": 5.282573080062866,
|
|
"epoch": 7.034529759200363,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00015779964906762706,
|
|
"loss": 4.6042,
|
|
"mean_token_accuracy": 0.22363857477903365,
|
|
"num_tokens": 16034880.0,
|
|
"step": 7745
|
|
},
|
|
{
|
|
"entropy": 5.268727827072143,
|
|
"epoch": 7.039073148568832,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.00015749809832110197,
|
|
"loss": 4.601,
|
|
"mean_token_accuracy": 0.2236470490694046,
|
|
"num_tokens": 16045265.0,
|
|
"step": 7750
|
|
},
|
|
{
|
|
"entropy": 5.27425103187561,
|
|
"epoch": 7.043616537937301,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0001571968374988389,
|
|
"loss": 4.5509,
|
|
"mean_token_accuracy": 0.22617185711860657,
|
|
"num_tokens": 16055493.0,
|
|
"step": 7755
|
|
},
|
|
{
|
|
"entropy": 5.2253295421600345,
|
|
"epoch": 7.04815992730577,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00015689586734416876,
|
|
"loss": 4.5112,
|
|
"mean_token_accuracy": 0.2303482100367546,
|
|
"num_tokens": 16065795.0,
|
|
"step": 7760
|
|
},
|
|
{
|
|
"entropy": 5.272696304321289,
|
|
"epoch": 7.052703316674239,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.00015659518859970545,
|
|
"loss": 4.5885,
|
|
"mean_token_accuracy": 0.22269229143857955,
|
|
"num_tokens": 16076157.0,
|
|
"step": 7765
|
|
},
|
|
{
|
|
"entropy": 5.232531404495239,
|
|
"epoch": 7.057246706042708,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0001562948020073441,
|
|
"loss": 4.7013,
|
|
"mean_token_accuracy": 0.20985913276672363,
|
|
"num_tokens": 16087130.0,
|
|
"step": 7770
|
|
},
|
|
{
|
|
"entropy": 5.236211633682251,
|
|
"epoch": 7.061790095411177,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.00015599470830825868,
|
|
"loss": 4.6037,
|
|
"mean_token_accuracy": 0.2244306892156601,
|
|
"num_tokens": 16097251.0,
|
|
"step": 7775
|
|
},
|
|
{
|
|
"entropy": 5.200172281265258,
|
|
"epoch": 7.066333484779646,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.00015569490824290054,
|
|
"loss": 4.4869,
|
|
"mean_token_accuracy": 0.2255580469965935,
|
|
"num_tokens": 16107270.0,
|
|
"step": 7780
|
|
},
|
|
{
|
|
"entropy": 5.2800366401672365,
|
|
"epoch": 7.070876874148114,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00015539540255099643,
|
|
"loss": 4.5929,
|
|
"mean_token_accuracy": 0.2251557856798172,
|
|
"num_tokens": 16117857.0,
|
|
"step": 7785
|
|
},
|
|
{
|
|
"entropy": 5.19622392654419,
|
|
"epoch": 7.075420263516583,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00015509619197154705,
|
|
"loss": 4.5194,
|
|
"mean_token_accuracy": 0.23319271504878997,
|
|
"num_tokens": 16128710.0,
|
|
"step": 7790
|
|
},
|
|
{
|
|
"entropy": 5.299012041091919,
|
|
"epoch": 7.079963652885052,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00015479727724282476,
|
|
"loss": 4.653,
|
|
"mean_token_accuracy": 0.21787756830453872,
|
|
"num_tokens": 16140372.0,
|
|
"step": 7795
|
|
},
|
|
{
|
|
"entropy": 5.260278224945068,
|
|
"epoch": 7.084507042253521,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.00015449865910237184,
|
|
"loss": 4.5664,
|
|
"mean_token_accuracy": 0.2253394678235054,
|
|
"num_tokens": 16150504.0,
|
|
"step": 7800
|
|
},
|
|
{
|
|
"entropy": 5.233803749084473,
|
|
"epoch": 7.08905043162199,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00015420033828699882,
|
|
"loss": 4.7129,
|
|
"mean_token_accuracy": 0.20941591560840606,
|
|
"num_tokens": 16161497.0,
|
|
"step": 7805
|
|
},
|
|
{
|
|
"entropy": 5.231043672561645,
|
|
"epoch": 7.093593820990459,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0001539023155327829,
|
|
"loss": 4.5251,
|
|
"mean_token_accuracy": 0.22786746621131898,
|
|
"num_tokens": 16171557.0,
|
|
"step": 7810
|
|
},
|
|
{
|
|
"entropy": 5.247286367416382,
|
|
"epoch": 7.098137210358928,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.00015360459157506525,
|
|
"loss": 4.5859,
|
|
"mean_token_accuracy": 0.21839048266410827,
|
|
"num_tokens": 16182064.0,
|
|
"step": 7815
|
|
},
|
|
{
|
|
"entropy": 5.288149166107178,
|
|
"epoch": 7.102680599727397,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.00015330716714845048,
|
|
"loss": 4.6188,
|
|
"mean_token_accuracy": 0.22273563146591185,
|
|
"num_tokens": 16192875.0,
|
|
"step": 7820
|
|
},
|
|
{
|
|
"entropy": 5.265992927551269,
|
|
"epoch": 7.107223989095866,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0001530100429868035,
|
|
"loss": 4.6341,
|
|
"mean_token_accuracy": 0.22011971175670625,
|
|
"num_tokens": 16203726.0,
|
|
"step": 7825
|
|
},
|
|
{
|
|
"entropy": 5.261337423324585,
|
|
"epoch": 7.111767378464334,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00015271321982324892,
|
|
"loss": 4.6734,
|
|
"mean_token_accuracy": 0.2084024205803871,
|
|
"num_tokens": 16214605.0,
|
|
"step": 7830
|
|
},
|
|
{
|
|
"entropy": 5.290814638137817,
|
|
"epoch": 7.116310767832803,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00015241669839016818,
|
|
"loss": 4.6087,
|
|
"mean_token_accuracy": 0.2235221803188324,
|
|
"num_tokens": 16224172.0,
|
|
"step": 7835
|
|
},
|
|
{
|
|
"entropy": 5.2928056716918945,
|
|
"epoch": 7.120854157201272,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.00015212047941919854,
|
|
"loss": 4.6284,
|
|
"mean_token_accuracy": 0.22523733079433442,
|
|
"num_tokens": 16234878.0,
|
|
"step": 7840
|
|
},
|
|
{
|
|
"entropy": 5.223490428924561,
|
|
"epoch": 7.125397546569741,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00015182456364123086,
|
|
"loss": 4.5849,
|
|
"mean_token_accuracy": 0.22669566422700882,
|
|
"num_tokens": 16244927.0,
|
|
"step": 7845
|
|
},
|
|
{
|
|
"entropy": 5.191789865493774,
|
|
"epoch": 7.12994093593821,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.00015152895178640788,
|
|
"loss": 4.5172,
|
|
"mean_token_accuracy": 0.23243796527385713,
|
|
"num_tokens": 16255793.0,
|
|
"step": 7850
|
|
},
|
|
{
|
|
"entropy": 5.285650396347046,
|
|
"epoch": 7.134484325306679,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0001512336445841224,
|
|
"loss": 4.6298,
|
|
"mean_token_accuracy": 0.21884144693613053,
|
|
"num_tokens": 16265946.0,
|
|
"step": 7855
|
|
},
|
|
{
|
|
"entropy": 5.221054601669311,
|
|
"epoch": 7.139027714675148,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00015093864276301573,
|
|
"loss": 4.5097,
|
|
"mean_token_accuracy": 0.23706830888986588,
|
|
"num_tokens": 16276261.0,
|
|
"step": 7860
|
|
},
|
|
{
|
|
"entropy": 5.24621901512146,
|
|
"epoch": 7.143571104043617,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.00015064394705097546,
|
|
"loss": 4.6212,
|
|
"mean_token_accuracy": 0.22705402225255966,
|
|
"num_tokens": 16287610.0,
|
|
"step": 7865
|
|
},
|
|
{
|
|
"entropy": 5.234105587005615,
|
|
"epoch": 7.148114493412085,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.00015034955817513397,
|
|
"loss": 4.5949,
|
|
"mean_token_accuracy": 0.2250899687409401,
|
|
"num_tokens": 16298104.0,
|
|
"step": 7870
|
|
},
|
|
{
|
|
"entropy": 5.204725837707519,
|
|
"epoch": 7.152657882780554,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0001500554768618665,
|
|
"loss": 4.5799,
|
|
"mean_token_accuracy": 0.22348266392946242,
|
|
"num_tokens": 16308476.0,
|
|
"step": 7875
|
|
},
|
|
{
|
|
"entropy": 5.2159261226654055,
|
|
"epoch": 7.157201272149023,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00014976170383678954,
|
|
"loss": 4.5094,
|
|
"mean_token_accuracy": 0.23351897150278092,
|
|
"num_tokens": 16318623.0,
|
|
"step": 7880
|
|
},
|
|
{
|
|
"entropy": 5.3513671398162845,
|
|
"epoch": 7.161744661517492,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.00014946823982475883,
|
|
"loss": 4.6873,
|
|
"mean_token_accuracy": 0.22054418176412582,
|
|
"num_tokens": 16330011.0,
|
|
"step": 7885
|
|
},
|
|
{
|
|
"entropy": 5.240450382232666,
|
|
"epoch": 7.166288050885961,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.00014917508554986754,
|
|
"loss": 4.6108,
|
|
"mean_token_accuracy": 0.21615472435951233,
|
|
"num_tokens": 16339801.0,
|
|
"step": 7890
|
|
},
|
|
{
|
|
"entropy": 5.271219253540039,
|
|
"epoch": 7.17083144025443,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.00014888224173544476,
|
|
"loss": 4.6518,
|
|
"mean_token_accuracy": 0.21730009019374846,
|
|
"num_tokens": 16350953.0,
|
|
"step": 7895
|
|
},
|
|
{
|
|
"entropy": 5.264876508712769,
|
|
"epoch": 7.175374829622899,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.00014858970910405368,
|
|
"loss": 4.589,
|
|
"mean_token_accuracy": 0.22046989351511,
|
|
"num_tokens": 16360873.0,
|
|
"step": 7900
|
|
},
|
|
{
|
|
"entropy": 5.2787100315094,
|
|
"epoch": 7.179918218991368,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.00014829748837748906,
|
|
"loss": 4.5993,
|
|
"mean_token_accuracy": 0.22561246603727342,
|
|
"num_tokens": 16370986.0,
|
|
"step": 7905
|
|
},
|
|
{
|
|
"entropy": 5.2694169044494625,
|
|
"epoch": 7.184461608359836,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0001480055802767769,
|
|
"loss": 4.5703,
|
|
"mean_token_accuracy": 0.23221857398748397,
|
|
"num_tokens": 16381563.0,
|
|
"step": 7910
|
|
},
|
|
{
|
|
"entropy": 5.248657321929931,
|
|
"epoch": 7.189004997728305,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00014771398552217114,
|
|
"loss": 4.6085,
|
|
"mean_token_accuracy": 0.21701397001743317,
|
|
"num_tokens": 16391532.0,
|
|
"step": 7915
|
|
},
|
|
{
|
|
"entropy": 5.321373796463012,
|
|
"epoch": 7.193548387096774,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00014742270483315319,
|
|
"loss": 4.5981,
|
|
"mean_token_accuracy": 0.222526390850544,
|
|
"num_tokens": 16402712.0,
|
|
"step": 7920
|
|
},
|
|
{
|
|
"entropy": 5.223284292221069,
|
|
"epoch": 7.198091776465243,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.00014713173892842878,
|
|
"loss": 4.6269,
|
|
"mean_token_accuracy": 0.22407705038785936,
|
|
"num_tokens": 16413308.0,
|
|
"step": 7925
|
|
},
|
|
{
|
|
"entropy": 5.245853996276855,
|
|
"epoch": 7.202635165833712,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00014684108852592765,
|
|
"loss": 4.6751,
|
|
"mean_token_accuracy": 0.21230973154306412,
|
|
"num_tokens": 16425076.0,
|
|
"step": 7930
|
|
},
|
|
{
|
|
"entropy": 5.241740894317627,
|
|
"epoch": 7.207178555202181,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00014655075434280064,
|
|
"loss": 4.5773,
|
|
"mean_token_accuracy": 0.22469925731420518,
|
|
"num_tokens": 16435307.0,
|
|
"step": 7935
|
|
},
|
|
{
|
|
"entropy": 5.271661710739136,
|
|
"epoch": 7.21172194457065,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.00014626073709541853,
|
|
"loss": 4.6326,
|
|
"mean_token_accuracy": 0.2226276859641075,
|
|
"num_tokens": 16446453.0,
|
|
"step": 7940
|
|
},
|
|
{
|
|
"entropy": 5.286002588272095,
|
|
"epoch": 7.216265333939119,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.00014597103749937,
|
|
"loss": 4.6496,
|
|
"mean_token_accuracy": 0.2121767967939377,
|
|
"num_tokens": 16457664.0,
|
|
"step": 7945
|
|
},
|
|
{
|
|
"entropy": 5.205934047698975,
|
|
"epoch": 7.220808723307587,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.00014568165626946012,
|
|
"loss": 4.5654,
|
|
"mean_token_accuracy": 0.22986571937799455,
|
|
"num_tokens": 16468599.0,
|
|
"step": 7950
|
|
},
|
|
{
|
|
"entropy": 5.220121288299561,
|
|
"epoch": 7.225352112676056,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.00014539259411970823,
|
|
"loss": 4.5749,
|
|
"mean_token_accuracy": 0.22303611189126968,
|
|
"num_tokens": 16479157.0,
|
|
"step": 7955
|
|
},
|
|
{
|
|
"entropy": 5.220082187652588,
|
|
"epoch": 7.229895502044525,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0001451038517633465,
|
|
"loss": 4.5621,
|
|
"mean_token_accuracy": 0.23433253169059753,
|
|
"num_tokens": 16489477.0,
|
|
"step": 7960
|
|
},
|
|
{
|
|
"entropy": 5.265118789672852,
|
|
"epoch": 7.234438891412994,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.00014481542991281782,
|
|
"loss": 4.6028,
|
|
"mean_token_accuracy": 0.2178284928202629,
|
|
"num_tokens": 16499901.0,
|
|
"step": 7965
|
|
},
|
|
{
|
|
"entropy": 5.310929965972901,
|
|
"epoch": 7.238982280781463,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00014452732927977465,
|
|
"loss": 4.6555,
|
|
"mean_token_accuracy": 0.218108232319355,
|
|
"num_tokens": 16510498.0,
|
|
"step": 7970
|
|
},
|
|
{
|
|
"entropy": 5.200837564468384,
|
|
"epoch": 7.243525670149932,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0001442395505750766,
|
|
"loss": 4.5698,
|
|
"mean_token_accuracy": 0.22503569424152375,
|
|
"num_tokens": 16521410.0,
|
|
"step": 7975
|
|
},
|
|
{
|
|
"entropy": 5.198737859725952,
|
|
"epoch": 7.248069059518401,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.00014395209450878899,
|
|
"loss": 4.6153,
|
|
"mean_token_accuracy": 0.21573067903518678,
|
|
"num_tokens": 16531184.0,
|
|
"step": 7980
|
|
},
|
|
{
|
|
"entropy": 5.143011379241943,
|
|
"epoch": 7.25261244888687,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.000143664961790181,
|
|
"loss": 4.5148,
|
|
"mean_token_accuracy": 0.22729084640741348,
|
|
"num_tokens": 16540948.0,
|
|
"step": 7985
|
|
},
|
|
{
|
|
"entropy": 5.274073839187622,
|
|
"epoch": 7.257155838255338,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0001433781531277243,
|
|
"loss": 4.6444,
|
|
"mean_token_accuracy": 0.2223571851849556,
|
|
"num_tokens": 16551935.0,
|
|
"step": 7990
|
|
},
|
|
{
|
|
"entropy": 5.331174325942993,
|
|
"epoch": 7.261699227623807,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0001430916692290905,
|
|
"loss": 4.6505,
|
|
"mean_token_accuracy": 0.2201610818505287,
|
|
"num_tokens": 16561405.0,
|
|
"step": 7995
|
|
},
|
|
{
|
|
"entropy": 5.210624408721924,
|
|
"epoch": 7.266242616992276,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00014280551080115032,
|
|
"loss": 4.4548,
|
|
"mean_token_accuracy": 0.2347921162843704,
|
|
"num_tokens": 16571105.0,
|
|
"step": 8000
|
|
},
|
|
{
|
|
"epoch": 7.266242616992276,
|
|
"eval_entropy": 5.171509283642436,
|
|
"eval_loss": 5.700132846832275,
|
|
"eval_mean_token_accuracy": 0.17259258147935536,
|
|
"eval_num_tokens": 16571105.0,
|
|
"eval_runtime": 2.5803,
|
|
"eval_samples_per_second": 1331.259,
|
|
"eval_steps_per_second": 166.65,
|
|
"step": 8000
|
|
},
|
|
{
|
|
"entropy": 5.21971435546875,
|
|
"epoch": 7.270786006360745,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.00014251967854997106,
|
|
"loss": 4.4554,
|
|
"mean_token_accuracy": 0.241530142724514,
|
|
"num_tokens": 16580717.0,
|
|
"step": 8005
|
|
},
|
|
{
|
|
"entropy": 5.230045366287231,
|
|
"epoch": 7.275329395729214,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00014223417318081572,
|
|
"loss": 4.607,
|
|
"mean_token_accuracy": 0.2250858411192894,
|
|
"num_tokens": 16592755.0,
|
|
"step": 8010
|
|
},
|
|
{
|
|
"entropy": 5.205086946487427,
|
|
"epoch": 7.279872785097683,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00014194899539814,
|
|
"loss": 4.6201,
|
|
"mean_token_accuracy": 0.22276343703269957,
|
|
"num_tokens": 16603249.0,
|
|
"step": 8015
|
|
},
|
|
{
|
|
"entropy": 5.242693185806274,
|
|
"epoch": 7.284416174466152,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.00014166414590559197,
|
|
"loss": 4.6064,
|
|
"mean_token_accuracy": 0.22001224160194396,
|
|
"num_tokens": 16612466.0,
|
|
"step": 8020
|
|
},
|
|
{
|
|
"entropy": 5.254310083389282,
|
|
"epoch": 7.288959563834621,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.00014137962540600944,
|
|
"loss": 4.5997,
|
|
"mean_token_accuracy": 0.22463713139295577,
|
|
"num_tokens": 16622782.0,
|
|
"step": 8025
|
|
},
|
|
{
|
|
"entropy": 5.205763149261474,
|
|
"epoch": 7.29350295320309,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.00014109543460141837,
|
|
"loss": 4.5818,
|
|
"mean_token_accuracy": 0.22595252841711044,
|
|
"num_tokens": 16633363.0,
|
|
"step": 8030
|
|
},
|
|
{
|
|
"entropy": 5.2052594184875485,
|
|
"epoch": 7.298046342571558,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0001408115741930313,
|
|
"loss": 4.5508,
|
|
"mean_token_accuracy": 0.23029475957155227,
|
|
"num_tokens": 16643372.0,
|
|
"step": 8035
|
|
},
|
|
{
|
|
"entropy": 5.257339286804199,
|
|
"epoch": 7.302589731940027,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.00014052804488124575,
|
|
"loss": 4.5887,
|
|
"mean_token_accuracy": 0.2236703708767891,
|
|
"num_tokens": 16652912.0,
|
|
"step": 8040
|
|
},
|
|
{
|
|
"entropy": 5.211137866973877,
|
|
"epoch": 7.307133121308496,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.00014024484736564196,
|
|
"loss": 4.5761,
|
|
"mean_token_accuracy": 0.22465971857309341,
|
|
"num_tokens": 16663341.0,
|
|
"step": 8045
|
|
},
|
|
{
|
|
"entropy": 5.2381096363067625,
|
|
"epoch": 7.311676510676965,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0001399619823449817,
|
|
"loss": 4.6096,
|
|
"mean_token_accuracy": 0.22627812176942824,
|
|
"num_tokens": 16673078.0,
|
|
"step": 8050
|
|
},
|
|
{
|
|
"entropy": 5.272232627868652,
|
|
"epoch": 7.316219900045434,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00013967945051720614,
|
|
"loss": 4.6058,
|
|
"mean_token_accuracy": 0.21872266680002211,
|
|
"num_tokens": 16683565.0,
|
|
"step": 8055
|
|
},
|
|
{
|
|
"entropy": 5.238610696792603,
|
|
"epoch": 7.320763289413903,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.00013939725257943475,
|
|
"loss": 4.5548,
|
|
"mean_token_accuracy": 0.22727288156747819,
|
|
"num_tokens": 16694080.0,
|
|
"step": 8060
|
|
},
|
|
{
|
|
"entropy": 5.255322122573853,
|
|
"epoch": 7.325306678782372,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00013911538922796275,
|
|
"loss": 4.579,
|
|
"mean_token_accuracy": 0.22324889600276948,
|
|
"num_tokens": 16704251.0,
|
|
"step": 8065
|
|
},
|
|
{
|
|
"entropy": 5.226661205291748,
|
|
"epoch": 7.32985006815084,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00013883386115825984,
|
|
"loss": 4.6201,
|
|
"mean_token_accuracy": 0.22108918577432632,
|
|
"num_tokens": 16715058.0,
|
|
"step": 8070
|
|
},
|
|
{
|
|
"entropy": 5.238469028472901,
|
|
"epoch": 7.334393457519309,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.00013855266906496867,
|
|
"loss": 4.5549,
|
|
"mean_token_accuracy": 0.23285359293222427,
|
|
"num_tokens": 16725657.0,
|
|
"step": 8075
|
|
},
|
|
{
|
|
"entropy": 5.2180126190185545,
|
|
"epoch": 7.338936846887778,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00013827181364190288,
|
|
"loss": 4.5759,
|
|
"mean_token_accuracy": 0.2215049907565117,
|
|
"num_tokens": 16735568.0,
|
|
"step": 8080
|
|
},
|
|
{
|
|
"entropy": 5.270995426177978,
|
|
"epoch": 7.343480236256247,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.00013799129558204505,
|
|
"loss": 4.6263,
|
|
"mean_token_accuracy": 0.21317509561777115,
|
|
"num_tokens": 16745988.0,
|
|
"step": 8085
|
|
},
|
|
{
|
|
"entropy": 5.254117155075074,
|
|
"epoch": 7.348023625624716,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00013771111557754577,
|
|
"loss": 4.5564,
|
|
"mean_token_accuracy": 0.22504522949457167,
|
|
"num_tokens": 16756151.0,
|
|
"step": 8090
|
|
},
|
|
{
|
|
"entropy": 5.20003867149353,
|
|
"epoch": 7.352567014993185,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.00013743127431972124,
|
|
"loss": 4.5183,
|
|
"mean_token_accuracy": 0.2289905548095703,
|
|
"num_tokens": 16766192.0,
|
|
"step": 8095
|
|
},
|
|
{
|
|
"entropy": 5.265207529067993,
|
|
"epoch": 7.357110404361654,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0001371517724990522,
|
|
"loss": 4.5974,
|
|
"mean_token_accuracy": 0.22620775699615478,
|
|
"num_tokens": 16776585.0,
|
|
"step": 8100
|
|
},
|
|
{
|
|
"entropy": 5.173593473434448,
|
|
"epoch": 7.361653793730123,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0001368726108051813,
|
|
"loss": 4.5358,
|
|
"mean_token_accuracy": 0.22163415998220443,
|
|
"num_tokens": 16786536.0,
|
|
"step": 8105
|
|
},
|
|
{
|
|
"entropy": 5.219452810287476,
|
|
"epoch": 7.366197183098592,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.00013659378992691244,
|
|
"loss": 4.5739,
|
|
"mean_token_accuracy": 0.22626343965530396,
|
|
"num_tokens": 16796758.0,
|
|
"step": 8110
|
|
},
|
|
{
|
|
"entropy": 5.227691984176635,
|
|
"epoch": 7.37074057246706,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00013631531055220835,
|
|
"loss": 4.5859,
|
|
"mean_token_accuracy": 0.22720132917165756,
|
|
"num_tokens": 16807947.0,
|
|
"step": 8115
|
|
},
|
|
{
|
|
"entropy": 5.1959577083587645,
|
|
"epoch": 7.375283961835529,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.00013603717336818934,
|
|
"loss": 4.5247,
|
|
"mean_token_accuracy": 0.22404551059007644,
|
|
"num_tokens": 16817114.0,
|
|
"step": 8120
|
|
},
|
|
{
|
|
"entropy": 5.197970676422119,
|
|
"epoch": 7.379827351203998,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.00013575937906113095,
|
|
"loss": 4.5397,
|
|
"mean_token_accuracy": 0.22902910113334657,
|
|
"num_tokens": 16827739.0,
|
|
"step": 8125
|
|
},
|
|
{
|
|
"entropy": 5.2710957527160645,
|
|
"epoch": 7.384370740572467,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0001354819283164634,
|
|
"loss": 4.5502,
|
|
"mean_token_accuracy": 0.22670188397169114,
|
|
"num_tokens": 16837398.0,
|
|
"step": 8130
|
|
},
|
|
{
|
|
"entropy": 5.27916898727417,
|
|
"epoch": 7.388914129940936,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0001352048218187686,
|
|
"loss": 4.6449,
|
|
"mean_token_accuracy": 0.22103723436594008,
|
|
"num_tokens": 16847565.0,
|
|
"step": 8135
|
|
},
|
|
{
|
|
"entropy": 5.229299259185791,
|
|
"epoch": 7.393457519309405,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.00013492806025177935,
|
|
"loss": 4.59,
|
|
"mean_token_accuracy": 0.222672238945961,
|
|
"num_tokens": 16857550.0,
|
|
"step": 8140
|
|
},
|
|
{
|
|
"entropy": 5.269249391555786,
|
|
"epoch": 7.398000908677874,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00013465164429837716,
|
|
"loss": 4.6367,
|
|
"mean_token_accuracy": 0.21913417130708696,
|
|
"num_tokens": 16867646.0,
|
|
"step": 8145
|
|
},
|
|
{
|
|
"entropy": 5.226283359527588,
|
|
"epoch": 7.402544298046343,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0001343755746405912,
|
|
"loss": 4.5437,
|
|
"mean_token_accuracy": 0.2313619762659073,
|
|
"num_tokens": 16876634.0,
|
|
"step": 8150
|
|
},
|
|
{
|
|
"entropy": 5.269350051879883,
|
|
"epoch": 7.407087687414811,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00013409985195959574,
|
|
"loss": 4.6107,
|
|
"mean_token_accuracy": 0.2267676994204521,
|
|
"num_tokens": 16886934.0,
|
|
"step": 8155
|
|
},
|
|
{
|
|
"entropy": 5.177730321884155,
|
|
"epoch": 7.41163107678328,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.00013382447693570908,
|
|
"loss": 4.5334,
|
|
"mean_token_accuracy": 0.2284277707338333,
|
|
"num_tokens": 16896591.0,
|
|
"step": 8160
|
|
},
|
|
{
|
|
"entropy": 5.2688497543334964,
|
|
"epoch": 7.416174466151749,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.00013354945024839166,
|
|
"loss": 4.6055,
|
|
"mean_token_accuracy": 0.21706879884004593,
|
|
"num_tokens": 16907388.0,
|
|
"step": 8165
|
|
},
|
|
{
|
|
"entropy": 5.238101434707642,
|
|
"epoch": 7.420717855520218,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00013327477257624466,
|
|
"loss": 4.562,
|
|
"mean_token_accuracy": 0.2223723441362381,
|
|
"num_tokens": 16918698.0,
|
|
"step": 8170
|
|
},
|
|
{
|
|
"entropy": 5.226699161529541,
|
|
"epoch": 7.425261244888687,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0001330004445970078,
|
|
"loss": 4.5404,
|
|
"mean_token_accuracy": 0.2297973722219467,
|
|
"num_tokens": 16928857.0,
|
|
"step": 8175
|
|
},
|
|
{
|
|
"entropy": 5.305631113052368,
|
|
"epoch": 7.429804634257156,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00013272646698755816,
|
|
"loss": 4.6203,
|
|
"mean_token_accuracy": 0.21966859847307205,
|
|
"num_tokens": 16940498.0,
|
|
"step": 8180
|
|
},
|
|
{
|
|
"entropy": 5.244188976287842,
|
|
"epoch": 7.434348023625625,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00013245284042390814,
|
|
"loss": 4.6134,
|
|
"mean_token_accuracy": 0.22533451318740844,
|
|
"num_tokens": 16951069.0,
|
|
"step": 8185
|
|
},
|
|
{
|
|
"entropy": 5.209710168838501,
|
|
"epoch": 7.438891412994094,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.00013217956558120436,
|
|
"loss": 4.6,
|
|
"mean_token_accuracy": 0.21810985058546067,
|
|
"num_tokens": 16961447.0,
|
|
"step": 8190
|
|
},
|
|
{
|
|
"entropy": 5.24697265625,
|
|
"epoch": 7.443434802362562,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.000131906643133725,
|
|
"loss": 4.5968,
|
|
"mean_token_accuracy": 0.22285253256559373,
|
|
"num_tokens": 16971753.0,
|
|
"step": 8195
|
|
},
|
|
{
|
|
"entropy": 5.237619495391845,
|
|
"epoch": 7.447978191731031,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.00013163407375487926,
|
|
"loss": 4.6652,
|
|
"mean_token_accuracy": 0.2192755773663521,
|
|
"num_tokens": 16982582.0,
|
|
"step": 8200
|
|
},
|
|
{
|
|
"entropy": 5.267025947570801,
|
|
"epoch": 7.4525215810995,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00013136185811720496,
|
|
"loss": 4.6169,
|
|
"mean_token_accuracy": 0.23453416228294371,
|
|
"num_tokens": 16992831.0,
|
|
"step": 8205
|
|
},
|
|
{
|
|
"entropy": 5.232826900482178,
|
|
"epoch": 7.457064970467969,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0001310899968923671,
|
|
"loss": 4.5877,
|
|
"mean_token_accuracy": 0.22097362875938414,
|
|
"num_tokens": 17002791.0,
|
|
"step": 8210
|
|
},
|
|
{
|
|
"entropy": 5.172960329055786,
|
|
"epoch": 7.461608359836438,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0001308184907511562,
|
|
"loss": 4.5091,
|
|
"mean_token_accuracy": 0.22792909890413285,
|
|
"num_tokens": 17012196.0,
|
|
"step": 8215
|
|
},
|
|
{
|
|
"entropy": 5.2521802425384525,
|
|
"epoch": 7.466151749204907,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00013054734036348675,
|
|
"loss": 4.5877,
|
|
"mean_token_accuracy": 0.22095251232385635,
|
|
"num_tokens": 17022369.0,
|
|
"step": 8220
|
|
},
|
|
{
|
|
"entropy": 5.210633182525635,
|
|
"epoch": 7.470695138573376,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.00013027654639839536,
|
|
"loss": 4.5387,
|
|
"mean_token_accuracy": 0.22353728860616684,
|
|
"num_tokens": 17031733.0,
|
|
"step": 8225
|
|
},
|
|
{
|
|
"entropy": 5.235988330841065,
|
|
"epoch": 7.475238527941845,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.00013000610952403917,
|
|
"loss": 4.6247,
|
|
"mean_token_accuracy": 0.21689840406179428,
|
|
"num_tokens": 17042503.0,
|
|
"step": 8230
|
|
},
|
|
{
|
|
"entropy": 5.222130680084229,
|
|
"epoch": 7.479781917310314,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00012973603040769427,
|
|
"loss": 4.6621,
|
|
"mean_token_accuracy": 0.21795820742845534,
|
|
"num_tokens": 17053167.0,
|
|
"step": 8235
|
|
},
|
|
{
|
|
"entropy": 5.195062685012817,
|
|
"epoch": 7.484325306678782,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.00012946630971575414,
|
|
"loss": 4.5618,
|
|
"mean_token_accuracy": 0.22161236703395842,
|
|
"num_tokens": 17064377.0,
|
|
"step": 8240
|
|
},
|
|
{
|
|
"entropy": 5.225052976608277,
|
|
"epoch": 7.488868696047251,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.00012919694811372768,
|
|
"loss": 4.5405,
|
|
"mean_token_accuracy": 0.22260430604219436,
|
|
"num_tokens": 17074215.0,
|
|
"step": 8245
|
|
},
|
|
{
|
|
"entropy": 5.296510553359985,
|
|
"epoch": 7.49341208541572,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.00012892794626623793,
|
|
"loss": 4.5949,
|
|
"mean_token_accuracy": 0.22167352885007857,
|
|
"num_tokens": 17084012.0,
|
|
"step": 8250
|
|
},
|
|
{
|
|
"entropy": 5.2260760307312015,
|
|
"epoch": 7.497955474784189,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0001286593048370201,
|
|
"loss": 4.5195,
|
|
"mean_token_accuracy": 0.23077500909566878,
|
|
"num_tokens": 17094363.0,
|
|
"step": 8255
|
|
},
|
|
{
|
|
"entropy": 5.217116498947144,
|
|
"epoch": 7.502498864152658,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.00012839102448892033,
|
|
"loss": 4.5756,
|
|
"mean_token_accuracy": 0.23287174552679063,
|
|
"num_tokens": 17104014.0,
|
|
"step": 8260
|
|
},
|
|
{
|
|
"entropy": 5.279367065429687,
|
|
"epoch": 7.507042253521127,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.00012812310588389367,
|
|
"loss": 4.6066,
|
|
"mean_token_accuracy": 0.22338744699954988,
|
|
"num_tokens": 17113722.0,
|
|
"step": 8265
|
|
},
|
|
{
|
|
"entropy": 5.2975109100341795,
|
|
"epoch": 7.511585642889596,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00012785554968300266,
|
|
"loss": 4.6719,
|
|
"mean_token_accuracy": 0.21950333416461945,
|
|
"num_tokens": 17124726.0,
|
|
"step": 8270
|
|
},
|
|
{
|
|
"entropy": 5.238125133514404,
|
|
"epoch": 7.516129032258064,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.00012758835654641548,
|
|
"loss": 4.5587,
|
|
"mean_token_accuracy": 0.22188551276922225,
|
|
"num_tokens": 17133694.0,
|
|
"step": 8275
|
|
},
|
|
{
|
|
"entropy": 5.24217963218689,
|
|
"epoch": 7.520672421626533,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.000127321527133405,
|
|
"loss": 4.6177,
|
|
"mean_token_accuracy": 0.22859080880880356,
|
|
"num_tokens": 17143458.0,
|
|
"step": 8280
|
|
},
|
|
{
|
|
"entropy": 5.189266538619995,
|
|
"epoch": 7.525215810995002,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.00012705506210234583,
|
|
"loss": 4.5523,
|
|
"mean_token_accuracy": 0.22972798645496367,
|
|
"num_tokens": 17154168.0,
|
|
"step": 8285
|
|
},
|
|
{
|
|
"entropy": 5.242132568359375,
|
|
"epoch": 7.529759200363471,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.00012678896211071422,
|
|
"loss": 4.6115,
|
|
"mean_token_accuracy": 0.22150552719831468,
|
|
"num_tokens": 17164529.0,
|
|
"step": 8290
|
|
},
|
|
{
|
|
"entropy": 5.255318355560303,
|
|
"epoch": 7.53430258973194,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0001265232278150854,
|
|
"loss": 4.5426,
|
|
"mean_token_accuracy": 0.2286658391356468,
|
|
"num_tokens": 17174506.0,
|
|
"step": 8295
|
|
},
|
|
{
|
|
"entropy": 5.194357633590698,
|
|
"epoch": 7.538845979100409,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0001262578598711323,
|
|
"loss": 4.4934,
|
|
"mean_token_accuracy": 0.23366003334522248,
|
|
"num_tokens": 17184371.0,
|
|
"step": 8300
|
|
},
|
|
{
|
|
"entropy": 5.307074546813965,
|
|
"epoch": 7.543389368468878,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0001259928589336239,
|
|
"loss": 4.6496,
|
|
"mean_token_accuracy": 0.21567799746990204,
|
|
"num_tokens": 17194286.0,
|
|
"step": 8305
|
|
},
|
|
{
|
|
"entropy": 5.319255018234253,
|
|
"epoch": 7.547932757837347,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00012572822565642378,
|
|
"loss": 4.6312,
|
|
"mean_token_accuracy": 0.22197648733854294,
|
|
"num_tokens": 17206602.0,
|
|
"step": 8310
|
|
},
|
|
{
|
|
"entropy": 5.224184131622314,
|
|
"epoch": 7.552476147205816,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.00012546396069248813,
|
|
"loss": 4.6427,
|
|
"mean_token_accuracy": 0.21749546825885774,
|
|
"num_tokens": 17216133.0,
|
|
"step": 8315
|
|
},
|
|
{
|
|
"entropy": 5.203413724899292,
|
|
"epoch": 7.557019536574284,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.00012520006469386458,
|
|
"loss": 4.5933,
|
|
"mean_token_accuracy": 0.21509534418582915,
|
|
"num_tokens": 17226488.0,
|
|
"step": 8320
|
|
},
|
|
{
|
|
"entropy": 5.233631324768067,
|
|
"epoch": 7.561562925942753,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00012493653831169014,
|
|
"loss": 4.5637,
|
|
"mean_token_accuracy": 0.22984999567270278,
|
|
"num_tokens": 17236808.0,
|
|
"step": 8325
|
|
},
|
|
{
|
|
"entropy": 5.23598461151123,
|
|
"epoch": 7.566106315311222,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00012467338219619015,
|
|
"loss": 4.591,
|
|
"mean_token_accuracy": 0.22976426780223846,
|
|
"num_tokens": 17247024.0,
|
|
"step": 8330
|
|
},
|
|
{
|
|
"entropy": 5.2589506149292,
|
|
"epoch": 7.570649704679691,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.000124410596996676,
|
|
"loss": 4.6047,
|
|
"mean_token_accuracy": 0.22641662657260894,
|
|
"num_tokens": 17257307.0,
|
|
"step": 8335
|
|
},
|
|
{
|
|
"entropy": 5.264531898498535,
|
|
"epoch": 7.57519309404816,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0001241481833615442,
|
|
"loss": 4.6395,
|
|
"mean_token_accuracy": 0.2186436578631401,
|
|
"num_tokens": 17268107.0,
|
|
"step": 8340
|
|
},
|
|
{
|
|
"entropy": 5.2091916561126705,
|
|
"epoch": 7.579736483416629,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00012388614193827407,
|
|
"loss": 4.4944,
|
|
"mean_token_accuracy": 0.2298985928297043,
|
|
"num_tokens": 17278107.0,
|
|
"step": 8345
|
|
},
|
|
{
|
|
"entropy": 5.197417497634888,
|
|
"epoch": 7.584279872785098,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.000123624473373427,
|
|
"loss": 4.5053,
|
|
"mean_token_accuracy": 0.23842529356479644,
|
|
"num_tokens": 17289298.0,
|
|
"step": 8350
|
|
},
|
|
{
|
|
"entropy": 5.220920372009277,
|
|
"epoch": 7.588823262153566,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.00012336317831264411,
|
|
"loss": 4.5756,
|
|
"mean_token_accuracy": 0.22084664255380632,
|
|
"num_tokens": 17300367.0,
|
|
"step": 8355
|
|
},
|
|
{
|
|
"entropy": 5.190892553329467,
|
|
"epoch": 7.593366651522036,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.00012310225740064498,
|
|
"loss": 4.5785,
|
|
"mean_token_accuracy": 0.22462510764598848,
|
|
"num_tokens": 17311187.0,
|
|
"step": 8360
|
|
},
|
|
{
|
|
"entropy": 5.244633531570434,
|
|
"epoch": 7.597910040890504,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0001228417112812259,
|
|
"loss": 4.6608,
|
|
"mean_token_accuracy": 0.21413560062646866,
|
|
"num_tokens": 17322063.0,
|
|
"step": 8365
|
|
},
|
|
{
|
|
"entropy": 5.214219093322754,
|
|
"epoch": 7.602453430258973,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00012258154059725877,
|
|
"loss": 4.5935,
|
|
"mean_token_accuracy": 0.2187523975968361,
|
|
"num_tokens": 17333333.0,
|
|
"step": 8370
|
|
},
|
|
{
|
|
"entropy": 5.253532981872558,
|
|
"epoch": 7.606996819627442,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0001223217459906886,
|
|
"loss": 4.6321,
|
|
"mean_token_accuracy": 0.22106881588697433,
|
|
"num_tokens": 17343178.0,
|
|
"step": 8375
|
|
},
|
|
{
|
|
"entropy": 5.290698480606079,
|
|
"epoch": 7.611540208995911,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.00012206232810253297,
|
|
"loss": 4.6357,
|
|
"mean_token_accuracy": 0.217315873503685,
|
|
"num_tokens": 17352984.0,
|
|
"step": 8380
|
|
},
|
|
{
|
|
"entropy": 5.269513845443726,
|
|
"epoch": 7.61608359836438,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00012180328757287967,
|
|
"loss": 4.5837,
|
|
"mean_token_accuracy": 0.22582034915685653,
|
|
"num_tokens": 17364875.0,
|
|
"step": 8385
|
|
},
|
|
{
|
|
"entropy": 5.297912454605102,
|
|
"epoch": 7.620626987732849,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00012154462504088545,
|
|
"loss": 4.5988,
|
|
"mean_token_accuracy": 0.23276531398296357,
|
|
"num_tokens": 17374981.0,
|
|
"step": 8390
|
|
},
|
|
{
|
|
"entropy": 5.201811695098877,
|
|
"epoch": 7.625170377101318,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0001212863411447744,
|
|
"loss": 4.5447,
|
|
"mean_token_accuracy": 0.2251238375902176,
|
|
"num_tokens": 17385515.0,
|
|
"step": 8395
|
|
},
|
|
{
|
|
"entropy": 5.229623889923095,
|
|
"epoch": 7.629713766469786,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.00012102843652183628,
|
|
"loss": 4.5232,
|
|
"mean_token_accuracy": 0.23514792025089265,
|
|
"num_tokens": 17395310.0,
|
|
"step": 8400
|
|
},
|
|
{
|
|
"entropy": 5.265518474578857,
|
|
"epoch": 7.634257155838255,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.00012077091180842523,
|
|
"loss": 4.6928,
|
|
"mean_token_accuracy": 0.2197713300585747,
|
|
"num_tokens": 17406482.0,
|
|
"step": 8405
|
|
},
|
|
{
|
|
"entropy": 5.308226585388184,
|
|
"epoch": 7.638800545206724,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.00012051376763995784,
|
|
"loss": 4.6118,
|
|
"mean_token_accuracy": 0.22742566019296645,
|
|
"num_tokens": 17415975.0,
|
|
"step": 8410
|
|
},
|
|
{
|
|
"entropy": 5.192042827606201,
|
|
"epoch": 7.643343934575193,
|
|
"grad_norm": 1.984375,
|
|
"learning_rate": 0.00012025700465091177,
|
|
"loss": 4.5543,
|
|
"mean_token_accuracy": 0.2187726080417633,
|
|
"num_tokens": 17425569.0,
|
|
"step": 8415
|
|
},
|
|
{
|
|
"entropy": 5.206367158889771,
|
|
"epoch": 7.647887323943662,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.00012000062347482413,
|
|
"loss": 4.5166,
|
|
"mean_token_accuracy": 0.23625647127628327,
|
|
"num_tokens": 17436028.0,
|
|
"step": 8420
|
|
},
|
|
{
|
|
"entropy": 5.214018821716309,
|
|
"epoch": 7.652430713312131,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00011974462474429015,
|
|
"loss": 4.5258,
|
|
"mean_token_accuracy": 0.22425899058580398,
|
|
"num_tokens": 17445413.0,
|
|
"step": 8425
|
|
},
|
|
{
|
|
"entropy": 5.253574848175049,
|
|
"epoch": 7.6569741026806,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.00011948900909096101,
|
|
"loss": 4.5908,
|
|
"mean_token_accuracy": 0.22261404395103454,
|
|
"num_tokens": 17455528.0,
|
|
"step": 8430
|
|
},
|
|
{
|
|
"entropy": 5.221394491195679,
|
|
"epoch": 7.661517492049069,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0001192337771455431,
|
|
"loss": 4.6128,
|
|
"mean_token_accuracy": 0.220120632648468,
|
|
"num_tokens": 17465928.0,
|
|
"step": 8435
|
|
},
|
|
{
|
|
"entropy": 5.271670913696289,
|
|
"epoch": 7.666060881417538,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.00011897892953779576,
|
|
"loss": 4.6321,
|
|
"mean_token_accuracy": 0.21780228465795518,
|
|
"num_tokens": 17476129.0,
|
|
"step": 8440
|
|
},
|
|
{
|
|
"entropy": 5.2148512840271,
|
|
"epoch": 7.670604270786006,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.00011872446689653032,
|
|
"loss": 4.6168,
|
|
"mean_token_accuracy": 0.2252160370349884,
|
|
"num_tokens": 17486593.0,
|
|
"step": 8445
|
|
},
|
|
{
|
|
"entropy": 5.2285887718200685,
|
|
"epoch": 7.675147660154475,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0001184703898496078,
|
|
"loss": 4.584,
|
|
"mean_token_accuracy": 0.22332363873720168,
|
|
"num_tokens": 17496453.0,
|
|
"step": 8450
|
|
},
|
|
{
|
|
"entropy": 5.2538511753082275,
|
|
"epoch": 7.679691049522944,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.00011821669902393823,
|
|
"loss": 4.6199,
|
|
"mean_token_accuracy": 0.22462223768234252,
|
|
"num_tokens": 17506886.0,
|
|
"step": 8455
|
|
},
|
|
{
|
|
"entropy": 5.192443418502807,
|
|
"epoch": 7.684234438891413,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00011796339504547846,
|
|
"loss": 4.5871,
|
|
"mean_token_accuracy": 0.2246616527438164,
|
|
"num_tokens": 17517785.0,
|
|
"step": 8460
|
|
},
|
|
{
|
|
"entropy": 5.225991153717041,
|
|
"epoch": 7.688777828259882,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00011771047853923086,
|
|
"loss": 4.6018,
|
|
"mean_token_accuracy": 0.22950150966644287,
|
|
"num_tokens": 17527863.0,
|
|
"step": 8465
|
|
},
|
|
{
|
|
"entropy": 5.202744722366333,
|
|
"epoch": 7.693321217628351,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.00011745795012924169,
|
|
"loss": 4.5706,
|
|
"mean_token_accuracy": 0.22013471871614457,
|
|
"num_tokens": 17538226.0,
|
|
"step": 8470
|
|
},
|
|
{
|
|
"entropy": 5.259958744049072,
|
|
"epoch": 7.69786460699682,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.00011720581043859988,
|
|
"loss": 4.6148,
|
|
"mean_token_accuracy": 0.22631852328777313,
|
|
"num_tokens": 17549603.0,
|
|
"step": 8475
|
|
},
|
|
{
|
|
"entropy": 5.250685024261474,
|
|
"epoch": 7.702407996365288,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.00011695406008943495,
|
|
"loss": 4.6006,
|
|
"mean_token_accuracy": 0.22418200373649597,
|
|
"num_tokens": 17558942.0,
|
|
"step": 8480
|
|
},
|
|
{
|
|
"entropy": 5.240614891052246,
|
|
"epoch": 7.706951385733757,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.00011670269970291584,
|
|
"loss": 4.6084,
|
|
"mean_token_accuracy": 0.21848942339420319,
|
|
"num_tokens": 17568542.0,
|
|
"step": 8485
|
|
},
|
|
{
|
|
"entropy": 5.201620435714721,
|
|
"epoch": 7.711494775102226,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0001164517298992493,
|
|
"loss": 4.6037,
|
|
"mean_token_accuracy": 0.22573217749595642,
|
|
"num_tokens": 17578882.0,
|
|
"step": 8490
|
|
},
|
|
{
|
|
"entropy": 5.211170291900634,
|
|
"epoch": 7.716038164470695,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.00011620115129767848,
|
|
"loss": 4.5937,
|
|
"mean_token_accuracy": 0.22593149095773696,
|
|
"num_tokens": 17588136.0,
|
|
"step": 8495
|
|
},
|
|
{
|
|
"entropy": 5.21201000213623,
|
|
"epoch": 7.720581553839164,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.00011595096451648111,
|
|
"loss": 4.5738,
|
|
"mean_token_accuracy": 0.22615616917610168,
|
|
"num_tokens": 17598800.0,
|
|
"step": 8500
|
|
},
|
|
{
|
|
"entropy": 5.240731430053711,
|
|
"epoch": 7.725124943207633,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.00011570117017296819,
|
|
"loss": 4.5526,
|
|
"mean_token_accuracy": 0.22549129277467728,
|
|
"num_tokens": 17609793.0,
|
|
"step": 8505
|
|
},
|
|
{
|
|
"entropy": 5.234430027008057,
|
|
"epoch": 7.729668332576102,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00011545176888348237,
|
|
"loss": 4.57,
|
|
"mean_token_accuracy": 0.22369823157787322,
|
|
"num_tokens": 17620575.0,
|
|
"step": 8510
|
|
},
|
|
{
|
|
"entropy": 5.282596206665039,
|
|
"epoch": 7.734211721944571,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.00011520276126339667,
|
|
"loss": 4.6567,
|
|
"mean_token_accuracy": 0.212042173743248,
|
|
"num_tokens": 17631169.0,
|
|
"step": 8515
|
|
},
|
|
{
|
|
"entropy": 5.231482696533203,
|
|
"epoch": 7.73875511131304,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00011495414792711259,
|
|
"loss": 4.6203,
|
|
"mean_token_accuracy": 0.22163946479558944,
|
|
"num_tokens": 17642161.0,
|
|
"step": 8520
|
|
},
|
|
{
|
|
"entropy": 5.259270143508911,
|
|
"epoch": 7.743298500681508,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.00011470592948805882,
|
|
"loss": 4.5825,
|
|
"mean_token_accuracy": 0.22297884970903398,
|
|
"num_tokens": 17651802.0,
|
|
"step": 8525
|
|
},
|
|
{
|
|
"entropy": 5.222069644927979,
|
|
"epoch": 7.747841890049977,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00011445810655868957,
|
|
"loss": 4.5221,
|
|
"mean_token_accuracy": 0.22848703116178512,
|
|
"num_tokens": 17661705.0,
|
|
"step": 8530
|
|
},
|
|
{
|
|
"entropy": 5.2680400848388675,
|
|
"epoch": 7.752385279418446,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.00011421067975048355,
|
|
"loss": 4.6183,
|
|
"mean_token_accuracy": 0.22346510589122773,
|
|
"num_tokens": 17672639.0,
|
|
"step": 8535
|
|
},
|
|
{
|
|
"entropy": 5.296177577972412,
|
|
"epoch": 7.756928668786915,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00011396364967394152,
|
|
"loss": 4.6585,
|
|
"mean_token_accuracy": 0.2173726588487625,
|
|
"num_tokens": 17682859.0,
|
|
"step": 8540
|
|
},
|
|
{
|
|
"entropy": 5.243993091583252,
|
|
"epoch": 7.761472058155384,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.00011371701693858582,
|
|
"loss": 4.6418,
|
|
"mean_token_accuracy": 0.225145523250103,
|
|
"num_tokens": 17692953.0,
|
|
"step": 8545
|
|
},
|
|
{
|
|
"entropy": 5.203941869735718,
|
|
"epoch": 7.766015447523853,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00011347078215295817,
|
|
"loss": 4.5279,
|
|
"mean_token_accuracy": 0.2231159970164299,
|
|
"num_tokens": 17702923.0,
|
|
"step": 8550
|
|
},
|
|
{
|
|
"entropy": 5.234547233581543,
|
|
"epoch": 7.770558836892322,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00011322494592461839,
|
|
"loss": 4.5664,
|
|
"mean_token_accuracy": 0.22831373214721679,
|
|
"num_tokens": 17713556.0,
|
|
"step": 8555
|
|
},
|
|
{
|
|
"entropy": 5.240524387359619,
|
|
"epoch": 7.77510222626079,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.00011297950886014292,
|
|
"loss": 4.5887,
|
|
"mean_token_accuracy": 0.22552619278430938,
|
|
"num_tokens": 17723565.0,
|
|
"step": 8560
|
|
},
|
|
{
|
|
"entropy": 5.272353553771973,
|
|
"epoch": 7.779645615629259,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0001127344715651234,
|
|
"loss": 4.6681,
|
|
"mean_token_accuracy": 0.2221914142370224,
|
|
"num_tokens": 17735946.0,
|
|
"step": 8565
|
|
},
|
|
{
|
|
"entropy": 5.28435263633728,
|
|
"epoch": 7.784189004997728,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.00011248983464416497,
|
|
"loss": 4.6107,
|
|
"mean_token_accuracy": 0.2238333836197853,
|
|
"num_tokens": 17745854.0,
|
|
"step": 8570
|
|
},
|
|
{
|
|
"entropy": 5.217532062530518,
|
|
"epoch": 7.788732394366197,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00011224559870088488,
|
|
"loss": 4.5664,
|
|
"mean_token_accuracy": 0.22895309776067735,
|
|
"num_tokens": 17755263.0,
|
|
"step": 8575
|
|
},
|
|
{
|
|
"entropy": 5.253269863128662,
|
|
"epoch": 7.793275783734666,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.00011200176433791101,
|
|
"loss": 4.6282,
|
|
"mean_token_accuracy": 0.22899096459150314,
|
|
"num_tokens": 17766223.0,
|
|
"step": 8580
|
|
},
|
|
{
|
|
"entropy": 5.223010444641114,
|
|
"epoch": 7.797819173103135,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0001117583321568805,
|
|
"loss": 4.6568,
|
|
"mean_token_accuracy": 0.2201021730899811,
|
|
"num_tokens": 17776626.0,
|
|
"step": 8585
|
|
},
|
|
{
|
|
"entropy": 5.195793151855469,
|
|
"epoch": 7.802362562471604,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00011151530275843805,
|
|
"loss": 4.6038,
|
|
"mean_token_accuracy": 0.22669109404087068,
|
|
"num_tokens": 17788292.0,
|
|
"step": 8590
|
|
},
|
|
{
|
|
"entropy": 5.28113317489624,
|
|
"epoch": 7.806905951840073,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.00011127267674223449,
|
|
"loss": 4.6663,
|
|
"mean_token_accuracy": 0.21619390845298767,
|
|
"num_tokens": 17799092.0,
|
|
"step": 8595
|
|
},
|
|
{
|
|
"entropy": 5.187128734588623,
|
|
"epoch": 7.811449341208542,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00011103045470692532,
|
|
"loss": 4.4693,
|
|
"mean_token_accuracy": 0.23302374482154847,
|
|
"num_tokens": 17808949.0,
|
|
"step": 8600
|
|
},
|
|
{
|
|
"entropy": 5.206726169586181,
|
|
"epoch": 7.81599273057701,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.00011078863725016955,
|
|
"loss": 4.5911,
|
|
"mean_token_accuracy": 0.2214356392621994,
|
|
"num_tokens": 17818527.0,
|
|
"step": 8605
|
|
},
|
|
{
|
|
"entropy": 5.196780157089234,
|
|
"epoch": 7.820536119945479,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00011054722496862759,
|
|
"loss": 4.5809,
|
|
"mean_token_accuracy": 0.22012218385934829,
|
|
"num_tokens": 17828721.0,
|
|
"step": 8610
|
|
},
|
|
{
|
|
"entropy": 5.2014833927154545,
|
|
"epoch": 7.825079509313948,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.00011030621845796021,
|
|
"loss": 4.5679,
|
|
"mean_token_accuracy": 0.22215764820575715,
|
|
"num_tokens": 17839394.0,
|
|
"step": 8615
|
|
},
|
|
{
|
|
"entropy": 5.278484058380127,
|
|
"epoch": 7.829622898682417,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00011006561831282703,
|
|
"loss": 4.6342,
|
|
"mean_token_accuracy": 0.22224525809288026,
|
|
"num_tokens": 17850687.0,
|
|
"step": 8620
|
|
},
|
|
{
|
|
"entropy": 5.27368574142456,
|
|
"epoch": 7.834166288050886,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.00010982542512688515,
|
|
"loss": 4.5419,
|
|
"mean_token_accuracy": 0.22483647465705872,
|
|
"num_tokens": 17860674.0,
|
|
"step": 8625
|
|
},
|
|
{
|
|
"entropy": 5.215876913070678,
|
|
"epoch": 7.838709677419355,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.00010958563949278711,
|
|
"loss": 4.5419,
|
|
"mean_token_accuracy": 0.2225261762738228,
|
|
"num_tokens": 17870407.0,
|
|
"step": 8630
|
|
},
|
|
{
|
|
"entropy": 5.263442802429199,
|
|
"epoch": 7.843253066787824,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00010934626200218032,
|
|
"loss": 4.6258,
|
|
"mean_token_accuracy": 0.22175122201442718,
|
|
"num_tokens": 17881184.0,
|
|
"step": 8635
|
|
},
|
|
{
|
|
"entropy": 5.239336633682251,
|
|
"epoch": 7.847796456156293,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.00010910729324570488,
|
|
"loss": 4.6158,
|
|
"mean_token_accuracy": 0.22228046506643295,
|
|
"num_tokens": 17891125.0,
|
|
"step": 8640
|
|
},
|
|
{
|
|
"entropy": 5.24975700378418,
|
|
"epoch": 7.852339845524762,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00010886873381299248,
|
|
"loss": 4.5884,
|
|
"mean_token_accuracy": 0.231185245513916,
|
|
"num_tokens": 17901733.0,
|
|
"step": 8645
|
|
},
|
|
{
|
|
"entropy": 5.238559818267822,
|
|
"epoch": 7.85688323489323,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.00010863058429266469,
|
|
"loss": 4.6041,
|
|
"mean_token_accuracy": 0.21702755689620973,
|
|
"num_tokens": 17911430.0,
|
|
"step": 8650
|
|
},
|
|
{
|
|
"entropy": 5.278924894332886,
|
|
"epoch": 7.861426624261699,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00010839284527233192,
|
|
"loss": 4.6113,
|
|
"mean_token_accuracy": 0.21381099820137023,
|
|
"num_tokens": 17921394.0,
|
|
"step": 8655
|
|
},
|
|
{
|
|
"entropy": 5.210942888259888,
|
|
"epoch": 7.865970013630168,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.00010815551733859153,
|
|
"loss": 4.5713,
|
|
"mean_token_accuracy": 0.2212771490216255,
|
|
"num_tokens": 17931364.0,
|
|
"step": 8660
|
|
},
|
|
{
|
|
"entropy": 5.23438515663147,
|
|
"epoch": 7.870513402998637,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.00010791860107702658,
|
|
"loss": 4.6071,
|
|
"mean_token_accuracy": 0.21951406300067902,
|
|
"num_tokens": 17940831.0,
|
|
"step": 8665
|
|
},
|
|
{
|
|
"entropy": 5.221070289611816,
|
|
"epoch": 7.875056792367106,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00010768209707220435,
|
|
"loss": 4.6016,
|
|
"mean_token_accuracy": 0.22218939960002898,
|
|
"num_tokens": 17950996.0,
|
|
"step": 8670
|
|
},
|
|
{
|
|
"entropy": 5.256055879592895,
|
|
"epoch": 7.879600181735575,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00010744600590767504,
|
|
"loss": 4.5924,
|
|
"mean_token_accuracy": 0.23343569785356522,
|
|
"num_tokens": 17960997.0,
|
|
"step": 8675
|
|
},
|
|
{
|
|
"entropy": 5.191085433959961,
|
|
"epoch": 7.884143571104044,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00010721032816597012,
|
|
"loss": 4.5856,
|
|
"mean_token_accuracy": 0.22482268810272216,
|
|
"num_tokens": 17971551.0,
|
|
"step": 8680
|
|
},
|
|
{
|
|
"entropy": 5.231211757659912,
|
|
"epoch": 7.888686960472512,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.000106975064428601,
|
|
"loss": 4.5955,
|
|
"mean_token_accuracy": 0.22652197629213333,
|
|
"num_tokens": 17982572.0,
|
|
"step": 8685
|
|
},
|
|
{
|
|
"entropy": 5.234357595443726,
|
|
"epoch": 7.893230349840981,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.00010674021527605742,
|
|
"loss": 4.5757,
|
|
"mean_token_accuracy": 0.2176394432783127,
|
|
"num_tokens": 17993409.0,
|
|
"step": 8690
|
|
},
|
|
{
|
|
"entropy": 5.2333512783050535,
|
|
"epoch": 7.89777373920945,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.00010650578128780656,
|
|
"loss": 4.6224,
|
|
"mean_token_accuracy": 0.23022335320711135,
|
|
"num_tokens": 18003830.0,
|
|
"step": 8695
|
|
},
|
|
{
|
|
"entropy": 5.208551025390625,
|
|
"epoch": 7.902317128577919,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0001062717630422908,
|
|
"loss": 4.5069,
|
|
"mean_token_accuracy": 0.23539864122867585,
|
|
"num_tokens": 18013808.0,
|
|
"step": 8700
|
|
},
|
|
{
|
|
"entropy": 5.269066047668457,
|
|
"epoch": 7.906860517946388,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00010603816111692699,
|
|
"loss": 4.6413,
|
|
"mean_token_accuracy": 0.22203868627548218,
|
|
"num_tokens": 18024783.0,
|
|
"step": 8705
|
|
},
|
|
{
|
|
"entropy": 5.207152843475342,
|
|
"epoch": 7.911403907314857,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.00010580497608810455,
|
|
"loss": 4.496,
|
|
"mean_token_accuracy": 0.23212267309427262,
|
|
"num_tokens": 18035050.0,
|
|
"step": 8710
|
|
},
|
|
{
|
|
"entropy": 5.270180606842041,
|
|
"epoch": 7.915947296683326,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.00010557220853118456,
|
|
"loss": 4.6399,
|
|
"mean_token_accuracy": 0.2226980835199356,
|
|
"num_tokens": 18046045.0,
|
|
"step": 8715
|
|
},
|
|
{
|
|
"entropy": 5.240881156921387,
|
|
"epoch": 7.920490686051795,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00010533985902049755,
|
|
"loss": 4.6055,
|
|
"mean_token_accuracy": 0.2236250102519989,
|
|
"num_tokens": 18055798.0,
|
|
"step": 8720
|
|
},
|
|
{
|
|
"entropy": 5.243751859664917,
|
|
"epoch": 7.925034075420264,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.00010510792812934307,
|
|
"loss": 4.6979,
|
|
"mean_token_accuracy": 0.2198784440755844,
|
|
"num_tokens": 18067934.0,
|
|
"step": 8725
|
|
},
|
|
{
|
|
"entropy": 5.262060308456421,
|
|
"epoch": 7.929577464788732,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00010487641642998746,
|
|
"loss": 4.596,
|
|
"mean_token_accuracy": 0.21991827636957167,
|
|
"num_tokens": 18077624.0,
|
|
"step": 8730
|
|
},
|
|
{
|
|
"entropy": 5.260528612136841,
|
|
"epoch": 7.934120854157201,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00010464532449366281,
|
|
"loss": 4.5855,
|
|
"mean_token_accuracy": 0.23315042704343797,
|
|
"num_tokens": 18087639.0,
|
|
"step": 8735
|
|
},
|
|
{
|
|
"entropy": 5.278159713745117,
|
|
"epoch": 7.93866424352567,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.00010441465289056548,
|
|
"loss": 4.5688,
|
|
"mean_token_accuracy": 0.22915111035108565,
|
|
"num_tokens": 18096872.0,
|
|
"step": 8740
|
|
},
|
|
{
|
|
"entropy": 5.225435066223144,
|
|
"epoch": 7.943207632894139,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.00010418440218985482,
|
|
"loss": 4.588,
|
|
"mean_token_accuracy": 0.2248292326927185,
|
|
"num_tokens": 18106400.0,
|
|
"step": 8745
|
|
},
|
|
{
|
|
"entropy": 5.214668703079224,
|
|
"epoch": 7.947751022262608,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00010395457295965143,
|
|
"loss": 4.581,
|
|
"mean_token_accuracy": 0.22069708853960038,
|
|
"num_tokens": 18118111.0,
|
|
"step": 8750
|
|
},
|
|
{
|
|
"entropy": 5.23864049911499,
|
|
"epoch": 7.952294411631077,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.00010372516576703617,
|
|
"loss": 4.5319,
|
|
"mean_token_accuracy": 0.2254407823085785,
|
|
"num_tokens": 18127134.0,
|
|
"step": 8755
|
|
},
|
|
{
|
|
"entropy": 5.237250852584839,
|
|
"epoch": 7.956837800999546,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0001034961811780484,
|
|
"loss": 4.5901,
|
|
"mean_token_accuracy": 0.22170754969120027,
|
|
"num_tokens": 18136708.0,
|
|
"step": 8760
|
|
},
|
|
{
|
|
"entropy": 5.264269828796387,
|
|
"epoch": 7.961381190368014,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00010326761975768492,
|
|
"loss": 4.5865,
|
|
"mean_token_accuracy": 0.2202468380331993,
|
|
"num_tokens": 18148144.0,
|
|
"step": 8765
|
|
},
|
|
{
|
|
"entropy": 5.202373695373535,
|
|
"epoch": 7.965924579736483,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.00010303948206989827,
|
|
"loss": 4.5284,
|
|
"mean_token_accuracy": 0.23033823668956757,
|
|
"num_tokens": 18156977.0,
|
|
"step": 8770
|
|
},
|
|
{
|
|
"entropy": 5.19195876121521,
|
|
"epoch": 7.970467969104952,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00010281176867759556,
|
|
"loss": 4.6017,
|
|
"mean_token_accuracy": 0.21916496455669404,
|
|
"num_tokens": 18167747.0,
|
|
"step": 8775
|
|
},
|
|
{
|
|
"entropy": 5.171042537689209,
|
|
"epoch": 7.975011358473421,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.00010258448014263682,
|
|
"loss": 4.5676,
|
|
"mean_token_accuracy": 0.22215010076761246,
|
|
"num_tokens": 18178926.0,
|
|
"step": 8780
|
|
},
|
|
{
|
|
"entropy": 5.225767755508423,
|
|
"epoch": 7.97955474784189,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.00010235761702583405,
|
|
"loss": 4.6201,
|
|
"mean_token_accuracy": 0.2163267567753792,
|
|
"num_tokens": 18189428.0,
|
|
"step": 8785
|
|
},
|
|
{
|
|
"entropy": 5.250021028518677,
|
|
"epoch": 7.984098137210359,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00010213117988694944,
|
|
"loss": 4.6145,
|
|
"mean_token_accuracy": 0.21921925842761994,
|
|
"num_tokens": 18199767.0,
|
|
"step": 8790
|
|
},
|
|
{
|
|
"entropy": 5.222245740890503,
|
|
"epoch": 7.988641526578828,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.00010190516928469407,
|
|
"loss": 4.566,
|
|
"mean_token_accuracy": 0.22461459934711456,
|
|
"num_tokens": 18209504.0,
|
|
"step": 8795
|
|
},
|
|
{
|
|
"entropy": 5.257276773452759,
|
|
"epoch": 7.993184915947297,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.00010167958577672654,
|
|
"loss": 4.654,
|
|
"mean_token_accuracy": 0.22394256442785263,
|
|
"num_tokens": 18220422.0,
|
|
"step": 8800
|
|
},
|
|
{
|
|
"entropy": 5.270177936553955,
|
|
"epoch": 7.997728305315766,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.00010145442991965198,
|
|
"loss": 4.6444,
|
|
"mean_token_accuracy": 0.2240256831049919,
|
|
"num_tokens": 18230508.0,
|
|
"step": 8805
|
|
},
|
|
{
|
|
"entropy": 5.185753769344753,
|
|
"epoch": 8.001817355747388,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.00010122970226901981,
|
|
"loss": 4.5232,
|
|
"mean_token_accuracy": 0.23061166372564104,
|
|
"num_tokens": 18239276.0,
|
|
"step": 8810
|
|
},
|
|
{
|
|
"entropy": 5.21862564086914,
|
|
"epoch": 8.006360745115856,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00010100540337932339,
|
|
"loss": 4.5071,
|
|
"mean_token_accuracy": 0.22774101346731185,
|
|
"num_tokens": 18249366.0,
|
|
"step": 8815
|
|
},
|
|
{
|
|
"entropy": 5.258246278762817,
|
|
"epoch": 8.010904134484326,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.00010078153380399773,
|
|
"loss": 4.5459,
|
|
"mean_token_accuracy": 0.22882290482521056,
|
|
"num_tokens": 18259310.0,
|
|
"step": 8820
|
|
},
|
|
{
|
|
"entropy": 5.2630597114562985,
|
|
"epoch": 8.015447523852794,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00010055809409541902,
|
|
"loss": 4.5619,
|
|
"mean_token_accuracy": 0.22914685755968095,
|
|
"num_tokens": 18271299.0,
|
|
"step": 8825
|
|
},
|
|
{
|
|
"entropy": 5.246363639831543,
|
|
"epoch": 8.019990913221264,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.00010033508480490222,
|
|
"loss": 4.5398,
|
|
"mean_token_accuracy": 0.22742610275745392,
|
|
"num_tokens": 18281406.0,
|
|
"step": 8830
|
|
},
|
|
{
|
|
"entropy": 5.225062465667724,
|
|
"epoch": 8.024534302589732,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.00010011250648270081,
|
|
"loss": 4.5982,
|
|
"mean_token_accuracy": 0.2236950010061264,
|
|
"num_tokens": 18291413.0,
|
|
"step": 8835
|
|
},
|
|
{
|
|
"entropy": 5.251197862625122,
|
|
"epoch": 8.0290776919582,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 9.98903596780046e-05,
|
|
"loss": 4.4742,
|
|
"mean_token_accuracy": 0.24258511811494826,
|
|
"num_tokens": 18301774.0,
|
|
"step": 8840
|
|
},
|
|
{
|
|
"entropy": 5.226791858673096,
|
|
"epoch": 8.03362108132667,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 9.966864493893876e-05,
|
|
"loss": 4.5203,
|
|
"mean_token_accuracy": 0.23053203225135804,
|
|
"num_tokens": 18311627.0,
|
|
"step": 8845
|
|
},
|
|
{
|
|
"entropy": 5.237873554229736,
|
|
"epoch": 8.038164470695138,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 9.94473628125623e-05,
|
|
"loss": 4.5615,
|
|
"mean_token_accuracy": 0.23119665384292604,
|
|
"num_tokens": 18322403.0,
|
|
"step": 8850
|
|
},
|
|
{
|
|
"entropy": 5.277161502838135,
|
|
"epoch": 8.042707860063608,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 9.922651384486695e-05,
|
|
"loss": 4.6418,
|
|
"mean_token_accuracy": 0.21659382581710815,
|
|
"num_tokens": 18334146.0,
|
|
"step": 8855
|
|
},
|
|
{
|
|
"entropy": 5.23591194152832,
|
|
"epoch": 8.047251249432076,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 9.900609858077562e-05,
|
|
"loss": 4.4752,
|
|
"mean_token_accuracy": 0.24106486588716508,
|
|
"num_tokens": 18343553.0,
|
|
"step": 8860
|
|
},
|
|
{
|
|
"entropy": 5.238624191284179,
|
|
"epoch": 8.051794638800546,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 9.878611756414094e-05,
|
|
"loss": 4.4441,
|
|
"mean_token_accuracy": 0.24091731011867523,
|
|
"num_tokens": 18353923.0,
|
|
"step": 8865
|
|
},
|
|
{
|
|
"entropy": 5.268097162246704,
|
|
"epoch": 8.056338028169014,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 9.856657133774424e-05,
|
|
"loss": 4.5007,
|
|
"mean_token_accuracy": 0.22645235061645508,
|
|
"num_tokens": 18364249.0,
|
|
"step": 8870
|
|
},
|
|
{
|
|
"entropy": 5.206813955307007,
|
|
"epoch": 8.060881417537482,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 9.834746044329411e-05,
|
|
"loss": 4.4891,
|
|
"mean_token_accuracy": 0.23394214808940889,
|
|
"num_tokens": 18374519.0,
|
|
"step": 8875
|
|
},
|
|
{
|
|
"entropy": 5.228153419494629,
|
|
"epoch": 8.065424806905952,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 9.81287854214248e-05,
|
|
"loss": 4.5158,
|
|
"mean_token_accuracy": 0.23242498934268951,
|
|
"num_tokens": 18385898.0,
|
|
"step": 8880
|
|
},
|
|
{
|
|
"entropy": 5.281903457641602,
|
|
"epoch": 8.06996819627442,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 9.791054681169522e-05,
|
|
"loss": 4.5868,
|
|
"mean_token_accuracy": 0.2206410974264145,
|
|
"num_tokens": 18396976.0,
|
|
"step": 8885
|
|
},
|
|
{
|
|
"entropy": 5.2222353458404545,
|
|
"epoch": 8.07451158564289,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 9.769274515258739e-05,
|
|
"loss": 4.4842,
|
|
"mean_token_accuracy": 0.23168586939573288,
|
|
"num_tokens": 18407611.0,
|
|
"step": 8890
|
|
},
|
|
{
|
|
"entropy": 5.18948974609375,
|
|
"epoch": 8.079054975011358,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 9.747538098150539e-05,
|
|
"loss": 4.5012,
|
|
"mean_token_accuracy": 0.2311040461063385,
|
|
"num_tokens": 18417227.0,
|
|
"step": 8895
|
|
},
|
|
{
|
|
"entropy": 5.235753774642944,
|
|
"epoch": 8.083598364379828,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 9.725845483477352e-05,
|
|
"loss": 4.5126,
|
|
"mean_token_accuracy": 0.23069011867046357,
|
|
"num_tokens": 18427621.0,
|
|
"step": 8900
|
|
},
|
|
{
|
|
"entropy": 5.235489368438721,
|
|
"epoch": 8.088141753748296,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 9.704196724763565e-05,
|
|
"loss": 4.5009,
|
|
"mean_token_accuracy": 0.2336835592985153,
|
|
"num_tokens": 18437353.0,
|
|
"step": 8905
|
|
},
|
|
{
|
|
"entropy": 5.262318229675293,
|
|
"epoch": 8.092685143116766,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 9.682591875425323e-05,
|
|
"loss": 4.5414,
|
|
"mean_token_accuracy": 0.2359580874443054,
|
|
"num_tokens": 18447692.0,
|
|
"step": 8910
|
|
},
|
|
{
|
|
"entropy": 5.221208095550537,
|
|
"epoch": 8.097228532485234,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 9.661030988770463e-05,
|
|
"loss": 4.5241,
|
|
"mean_token_accuracy": 0.22543893307447432,
|
|
"num_tokens": 18457525.0,
|
|
"step": 8915
|
|
},
|
|
{
|
|
"entropy": 5.287770080566406,
|
|
"epoch": 8.101771921853702,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 9.63951411799831e-05,
|
|
"loss": 4.6518,
|
|
"mean_token_accuracy": 0.22670187801122665,
|
|
"num_tokens": 18468131.0,
|
|
"step": 8920
|
|
},
|
|
{
|
|
"entropy": 5.214785766601563,
|
|
"epoch": 8.106315311222172,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 9.618041316199617e-05,
|
|
"loss": 4.5249,
|
|
"mean_token_accuracy": 0.2334849402308464,
|
|
"num_tokens": 18479251.0,
|
|
"step": 8925
|
|
},
|
|
{
|
|
"entropy": 5.177601957321167,
|
|
"epoch": 8.11085870059064,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 9.596612636356383e-05,
|
|
"loss": 4.4306,
|
|
"mean_token_accuracy": 0.23585728406906128,
|
|
"num_tokens": 18489781.0,
|
|
"step": 8930
|
|
},
|
|
{
|
|
"entropy": 5.222140884399414,
|
|
"epoch": 8.11540208995911,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 9.575228131341745e-05,
|
|
"loss": 4.5611,
|
|
"mean_token_accuracy": 0.22398663610219954,
|
|
"num_tokens": 18500294.0,
|
|
"step": 8935
|
|
},
|
|
{
|
|
"entropy": 5.222820711135864,
|
|
"epoch": 8.119945479327578,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 9.55388785391984e-05,
|
|
"loss": 4.4889,
|
|
"mean_token_accuracy": 0.23940533846616746,
|
|
"num_tokens": 18510464.0,
|
|
"step": 8940
|
|
},
|
|
{
|
|
"entropy": 5.251266145706177,
|
|
"epoch": 8.124488868696048,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 9.532591856745689e-05,
|
|
"loss": 4.5128,
|
|
"mean_token_accuracy": 0.2286805361509323,
|
|
"num_tokens": 18520773.0,
|
|
"step": 8945
|
|
},
|
|
{
|
|
"entropy": 5.2837419509887695,
|
|
"epoch": 8.129032258064516,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 9.511340192365044e-05,
|
|
"loss": 4.5751,
|
|
"mean_token_accuracy": 0.226841738820076,
|
|
"num_tokens": 18531920.0,
|
|
"step": 8950
|
|
},
|
|
{
|
|
"entropy": 5.252134132385254,
|
|
"epoch": 8.133575647432984,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 9.490132913214277e-05,
|
|
"loss": 4.5233,
|
|
"mean_token_accuracy": 0.2302626371383667,
|
|
"num_tokens": 18542134.0,
|
|
"step": 8955
|
|
},
|
|
{
|
|
"entropy": 5.1924591064453125,
|
|
"epoch": 8.138119036801454,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 9.468970071620231e-05,
|
|
"loss": 4.4763,
|
|
"mean_token_accuracy": 0.2369143232703209,
|
|
"num_tokens": 18552824.0,
|
|
"step": 8960
|
|
},
|
|
{
|
|
"entropy": 5.185634326934815,
|
|
"epoch": 8.142662426169922,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 9.447851719800126e-05,
|
|
"loss": 4.4849,
|
|
"mean_token_accuracy": 0.24468807727098466,
|
|
"num_tokens": 18562900.0,
|
|
"step": 8965
|
|
},
|
|
{
|
|
"entropy": 5.210503673553466,
|
|
"epoch": 8.147205815538392,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 9.426777909861395e-05,
|
|
"loss": 4.4447,
|
|
"mean_token_accuracy": 0.235501666367054,
|
|
"num_tokens": 18572735.0,
|
|
"step": 8970
|
|
},
|
|
{
|
|
"entropy": 5.2651420593261715,
|
|
"epoch": 8.15174920490686,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 9.405748693801562e-05,
|
|
"loss": 4.5568,
|
|
"mean_token_accuracy": 0.229338900744915,
|
|
"num_tokens": 18583372.0,
|
|
"step": 8975
|
|
},
|
|
{
|
|
"entropy": 5.256136655807495,
|
|
"epoch": 8.15629259427533,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 9.384764123508124e-05,
|
|
"loss": 4.5535,
|
|
"mean_token_accuracy": 0.22272869050502778,
|
|
"num_tokens": 18593569.0,
|
|
"step": 8980
|
|
},
|
|
{
|
|
"entropy": 5.228545045852661,
|
|
"epoch": 8.160835983643798,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 9.363824250758443e-05,
|
|
"loss": 4.5456,
|
|
"mean_token_accuracy": 0.232030089199543,
|
|
"num_tokens": 18604302.0,
|
|
"step": 8985
|
|
},
|
|
{
|
|
"entropy": 5.230408573150635,
|
|
"epoch": 8.165379373012268,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 9.34292912721955e-05,
|
|
"loss": 4.4959,
|
|
"mean_token_accuracy": 0.2291339710354805,
|
|
"num_tokens": 18615473.0,
|
|
"step": 8990
|
|
},
|
|
{
|
|
"entropy": 5.226939249038696,
|
|
"epoch": 8.169922762380736,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 9.322078804448095e-05,
|
|
"loss": 4.5619,
|
|
"mean_token_accuracy": 0.22670039534568787,
|
|
"num_tokens": 18625849.0,
|
|
"step": 8995
|
|
},
|
|
{
|
|
"entropy": 5.200363254547119,
|
|
"epoch": 8.174466151749204,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 9.301273333890171e-05,
|
|
"loss": 4.4991,
|
|
"mean_token_accuracy": 0.2294518232345581,
|
|
"num_tokens": 18635352.0,
|
|
"step": 9000
|
|
},
|
|
{
|
|
"epoch": 8.174466151749204,
|
|
"eval_entropy": 5.158863165212232,
|
|
"eval_loss": 5.687122821807861,
|
|
"eval_mean_token_accuracy": 0.1733093827789606,
|
|
"eval_num_tokens": 18635352.0,
|
|
"eval_runtime": 2.7459,
|
|
"eval_samples_per_second": 1250.973,
|
|
"eval_steps_per_second": 156.599,
|
|
"step": 9000
|
|
},
|
|
{
|
|
"entropy": 5.275108051300049,
|
|
"epoch": 8.179009541117674,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 9.280512766881227e-05,
|
|
"loss": 4.552,
|
|
"mean_token_accuracy": 0.22467280328273773,
|
|
"num_tokens": 18647143.0,
|
|
"step": 9005
|
|
},
|
|
{
|
|
"entropy": 5.279839754104614,
|
|
"epoch": 8.183552930486142,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 9.25979715464588e-05,
|
|
"loss": 4.5505,
|
|
"mean_token_accuracy": 0.22540920376777648,
|
|
"num_tokens": 18657858.0,
|
|
"step": 9010
|
|
},
|
|
{
|
|
"entropy": 5.272215509414673,
|
|
"epoch": 8.188096319854612,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 9.23912654829784e-05,
|
|
"loss": 4.6121,
|
|
"mean_token_accuracy": 0.21450207084417344,
|
|
"num_tokens": 18669055.0,
|
|
"step": 9015
|
|
},
|
|
{
|
|
"entropy": 5.224110221862793,
|
|
"epoch": 8.19263970922308,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 9.218500998839794e-05,
|
|
"loss": 4.489,
|
|
"mean_token_accuracy": 0.23409368842840195,
|
|
"num_tokens": 18678966.0,
|
|
"step": 9020
|
|
},
|
|
{
|
|
"entropy": 5.209978103637695,
|
|
"epoch": 8.19718309859155,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 9.197920557163215e-05,
|
|
"loss": 4.4282,
|
|
"mean_token_accuracy": 0.24474566876888276,
|
|
"num_tokens": 18688413.0,
|
|
"step": 9025
|
|
},
|
|
{
|
|
"entropy": 5.241014766693115,
|
|
"epoch": 8.201726487960018,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 9.177385274048312e-05,
|
|
"loss": 4.5833,
|
|
"mean_token_accuracy": 0.2193273976445198,
|
|
"num_tokens": 18699467.0,
|
|
"step": 9030
|
|
},
|
|
{
|
|
"entropy": 5.1977614402771,
|
|
"epoch": 8.206269877328488,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 9.156895200163837e-05,
|
|
"loss": 4.4108,
|
|
"mean_token_accuracy": 0.2496635228395462,
|
|
"num_tokens": 18709521.0,
|
|
"step": 9035
|
|
},
|
|
{
|
|
"entropy": 5.200184154510498,
|
|
"epoch": 8.210813266696956,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 9.13645038606703e-05,
|
|
"loss": 4.5715,
|
|
"mean_token_accuracy": 0.21268383264541627,
|
|
"num_tokens": 18720878.0,
|
|
"step": 9040
|
|
},
|
|
{
|
|
"entropy": 5.212477159500122,
|
|
"epoch": 8.215356656065424,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 9.116050882203427e-05,
|
|
"loss": 4.499,
|
|
"mean_token_accuracy": 0.22995140850543977,
|
|
"num_tokens": 18731340.0,
|
|
"step": 9045
|
|
},
|
|
{
|
|
"entropy": 5.229914617538452,
|
|
"epoch": 8.219900045433894,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 9.09569673890678e-05,
|
|
"loss": 4.5762,
|
|
"mean_token_accuracy": 0.22674094140529633,
|
|
"num_tokens": 18742406.0,
|
|
"step": 9050
|
|
},
|
|
{
|
|
"entropy": 5.266318988800049,
|
|
"epoch": 8.224443434802362,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 9.075388006398907e-05,
|
|
"loss": 4.5648,
|
|
"mean_token_accuracy": 0.2260959729552269,
|
|
"num_tokens": 18752914.0,
|
|
"step": 9055
|
|
},
|
|
{
|
|
"entropy": 5.235313940048218,
|
|
"epoch": 8.228986824170832,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 9.0551247347896e-05,
|
|
"loss": 4.5209,
|
|
"mean_token_accuracy": 0.22582284659147261,
|
|
"num_tokens": 18763640.0,
|
|
"step": 9060
|
|
},
|
|
{
|
|
"entropy": 5.26997652053833,
|
|
"epoch": 8.2335302135393,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 9.034906974076449e-05,
|
|
"loss": 4.4982,
|
|
"mean_token_accuracy": 0.23370928913354874,
|
|
"num_tokens": 18773245.0,
|
|
"step": 9065
|
|
},
|
|
{
|
|
"entropy": 5.176637172698975,
|
|
"epoch": 8.23807360290777,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 9.014734774144784e-05,
|
|
"loss": 4.4391,
|
|
"mean_token_accuracy": 0.22894425839185714,
|
|
"num_tokens": 18784025.0,
|
|
"step": 9070
|
|
},
|
|
{
|
|
"entropy": 5.1917119979858395,
|
|
"epoch": 8.242616992276238,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 8.994608184767491e-05,
|
|
"loss": 4.4816,
|
|
"mean_token_accuracy": 0.22964385002851487,
|
|
"num_tokens": 18794715.0,
|
|
"step": 9075
|
|
},
|
|
{
|
|
"entropy": 5.191939496994019,
|
|
"epoch": 8.247160381644706,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 8.97452725560495e-05,
|
|
"loss": 4.473,
|
|
"mean_token_accuracy": 0.23019960671663284,
|
|
"num_tokens": 18804450.0,
|
|
"step": 9080
|
|
},
|
|
{
|
|
"entropy": 5.224881172180176,
|
|
"epoch": 8.251703771013176,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 8.954492036204829e-05,
|
|
"loss": 4.5592,
|
|
"mean_token_accuracy": 0.22930746972560884,
|
|
"num_tokens": 18815327.0,
|
|
"step": 9085
|
|
},
|
|
{
|
|
"entropy": 5.224856662750244,
|
|
"epoch": 8.256247160381644,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 8.934502576002059e-05,
|
|
"loss": 4.5259,
|
|
"mean_token_accuracy": 0.22935317754745482,
|
|
"num_tokens": 18825523.0,
|
|
"step": 9090
|
|
},
|
|
{
|
|
"entropy": 5.200793933868408,
|
|
"epoch": 8.260790549750114,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 8.914558924318643e-05,
|
|
"loss": 4.4655,
|
|
"mean_token_accuracy": 0.23980457782745362,
|
|
"num_tokens": 18834609.0,
|
|
"step": 9095
|
|
},
|
|
{
|
|
"entropy": 5.281197738647461,
|
|
"epoch": 8.265333939118582,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 8.894661130363557e-05,
|
|
"loss": 4.6415,
|
|
"mean_token_accuracy": 0.21635418087244035,
|
|
"num_tokens": 18844006.0,
|
|
"step": 9100
|
|
},
|
|
{
|
|
"entropy": 5.214982557296753,
|
|
"epoch": 8.269877328487052,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 8.874809243232624e-05,
|
|
"loss": 4.5326,
|
|
"mean_token_accuracy": 0.22034887969493866,
|
|
"num_tokens": 18854597.0,
|
|
"step": 9105
|
|
},
|
|
{
|
|
"entropy": 5.288031435012817,
|
|
"epoch": 8.27442071785552,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 8.85500331190841e-05,
|
|
"loss": 4.5165,
|
|
"mean_token_accuracy": 0.22759910225868224,
|
|
"num_tokens": 18865130.0,
|
|
"step": 9110
|
|
},
|
|
{
|
|
"entropy": 5.319898319244385,
|
|
"epoch": 8.27896410722399,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 8.835243385260083e-05,
|
|
"loss": 4.5534,
|
|
"mean_token_accuracy": 0.22831053286790848,
|
|
"num_tokens": 18875084.0,
|
|
"step": 9115
|
|
},
|
|
{
|
|
"entropy": 5.262097644805908,
|
|
"epoch": 8.283507496592458,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 8.815529512043293e-05,
|
|
"loss": 4.6123,
|
|
"mean_token_accuracy": 0.21894555389881135,
|
|
"num_tokens": 18887235.0,
|
|
"step": 9120
|
|
},
|
|
{
|
|
"entropy": 5.212887144088745,
|
|
"epoch": 8.288050885960926,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 8.795861740900061e-05,
|
|
"loss": 4.5159,
|
|
"mean_token_accuracy": 0.23247533142566681,
|
|
"num_tokens": 18897653.0,
|
|
"step": 9125
|
|
},
|
|
{
|
|
"entropy": 5.239365434646606,
|
|
"epoch": 8.292594275329396,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 8.77624012035866e-05,
|
|
"loss": 4.5863,
|
|
"mean_token_accuracy": 0.22183734327554702,
|
|
"num_tokens": 18907783.0,
|
|
"step": 9130
|
|
},
|
|
{
|
|
"entropy": 5.238541889190674,
|
|
"epoch": 8.297137664697864,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 8.756664698833492e-05,
|
|
"loss": 4.4441,
|
|
"mean_token_accuracy": 0.23970645815134048,
|
|
"num_tokens": 18918195.0,
|
|
"step": 9135
|
|
},
|
|
{
|
|
"entropy": 5.213078022003174,
|
|
"epoch": 8.301681054066334,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 8.737135524624959e-05,
|
|
"loss": 4.4743,
|
|
"mean_token_accuracy": 0.23606644868850707,
|
|
"num_tokens": 18927346.0,
|
|
"step": 9140
|
|
},
|
|
{
|
|
"entropy": 5.2433398246765135,
|
|
"epoch": 8.306224443434802,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 8.717652645919352e-05,
|
|
"loss": 4.5338,
|
|
"mean_token_accuracy": 0.2275206044316292,
|
|
"num_tokens": 18937464.0,
|
|
"step": 9145
|
|
},
|
|
{
|
|
"entropy": 5.232105493545532,
|
|
"epoch": 8.310767832803272,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 8.698216110788753e-05,
|
|
"loss": 4.5876,
|
|
"mean_token_accuracy": 0.22207542061805724,
|
|
"num_tokens": 18948760.0,
|
|
"step": 9150
|
|
},
|
|
{
|
|
"entropy": 5.221767568588257,
|
|
"epoch": 8.31531122217174,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 8.67882596719086e-05,
|
|
"loss": 4.5132,
|
|
"mean_token_accuracy": 0.23457239270210267,
|
|
"num_tokens": 18959032.0,
|
|
"step": 9155
|
|
},
|
|
{
|
|
"entropy": 5.227011871337891,
|
|
"epoch": 8.319854611540208,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 8.659482262968943e-05,
|
|
"loss": 4.5524,
|
|
"mean_token_accuracy": 0.22931526303291322,
|
|
"num_tokens": 18970082.0,
|
|
"step": 9160
|
|
},
|
|
{
|
|
"entropy": 5.310136890411377,
|
|
"epoch": 8.324398000908678,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 8.640185045851653e-05,
|
|
"loss": 4.5673,
|
|
"mean_token_accuracy": 0.2223695009946823,
|
|
"num_tokens": 18980923.0,
|
|
"step": 9165
|
|
},
|
|
{
|
|
"entropy": 5.2747584819793705,
|
|
"epoch": 8.328941390277146,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 8.620934363452973e-05,
|
|
"loss": 4.4947,
|
|
"mean_token_accuracy": 0.23084720373153686,
|
|
"num_tokens": 18992231.0,
|
|
"step": 9170
|
|
},
|
|
{
|
|
"entropy": 5.232693481445312,
|
|
"epoch": 8.333484779645616,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 8.601730263272034e-05,
|
|
"loss": 4.5551,
|
|
"mean_token_accuracy": 0.22306984215974807,
|
|
"num_tokens": 19002455.0,
|
|
"step": 9175
|
|
},
|
|
{
|
|
"entropy": 5.202978992462159,
|
|
"epoch": 8.338028169014084,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 8.58257279269305e-05,
|
|
"loss": 4.4772,
|
|
"mean_token_accuracy": 0.24068198055028917,
|
|
"num_tokens": 19011404.0,
|
|
"step": 9180
|
|
},
|
|
{
|
|
"entropy": 5.193587684631348,
|
|
"epoch": 8.342571558382554,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 8.563461998985172e-05,
|
|
"loss": 4.4758,
|
|
"mean_token_accuracy": 0.23236075341701506,
|
|
"num_tokens": 19020713.0,
|
|
"step": 9185
|
|
},
|
|
{
|
|
"entropy": 5.239758443832398,
|
|
"epoch": 8.347114947751022,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 8.544397929302389e-05,
|
|
"loss": 4.5267,
|
|
"mean_token_accuracy": 0.22960152924060823,
|
|
"num_tokens": 19030530.0,
|
|
"step": 9190
|
|
},
|
|
{
|
|
"entropy": 5.247308921813965,
|
|
"epoch": 8.351658337119492,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 8.525380630683389e-05,
|
|
"loss": 4.5244,
|
|
"mean_token_accuracy": 0.22614581882953644,
|
|
"num_tokens": 19041349.0,
|
|
"step": 9195
|
|
},
|
|
{
|
|
"entropy": 5.223901033401489,
|
|
"epoch": 8.35620172648796,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 8.506410150051478e-05,
|
|
"loss": 4.5051,
|
|
"mean_token_accuracy": 0.23456546813249587,
|
|
"num_tokens": 19051796.0,
|
|
"step": 9200
|
|
},
|
|
{
|
|
"entropy": 5.210023736953735,
|
|
"epoch": 8.360745115856428,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 8.487486534214423e-05,
|
|
"loss": 4.517,
|
|
"mean_token_accuracy": 0.24103037565946578,
|
|
"num_tokens": 19061751.0,
|
|
"step": 9205
|
|
},
|
|
{
|
|
"entropy": 5.271628999710083,
|
|
"epoch": 8.365288505224898,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 8.468609829864366e-05,
|
|
"loss": 4.5364,
|
|
"mean_token_accuracy": 0.2276193231344223,
|
|
"num_tokens": 19071284.0,
|
|
"step": 9210
|
|
},
|
|
{
|
|
"entropy": 5.209068298339844,
|
|
"epoch": 8.369831894593366,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 8.449780083577697e-05,
|
|
"loss": 4.5407,
|
|
"mean_token_accuracy": 0.23016533702611924,
|
|
"num_tokens": 19081089.0,
|
|
"step": 9215
|
|
},
|
|
{
|
|
"entropy": 5.2485260486602785,
|
|
"epoch": 8.374375283961836,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 8.430997341814947e-05,
|
|
"loss": 4.5382,
|
|
"mean_token_accuracy": 0.23106775432825089,
|
|
"num_tokens": 19090584.0,
|
|
"step": 9220
|
|
},
|
|
{
|
|
"entropy": 5.236415672302246,
|
|
"epoch": 8.378918673330304,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 8.41226165092066e-05,
|
|
"loss": 4.4766,
|
|
"mean_token_accuracy": 0.23603845238685608,
|
|
"num_tokens": 19100349.0,
|
|
"step": 9225
|
|
},
|
|
{
|
|
"entropy": 5.1926532745361325,
|
|
"epoch": 8.383462062698774,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 8.393573057123299e-05,
|
|
"loss": 4.4842,
|
|
"mean_token_accuracy": 0.23525285273790358,
|
|
"num_tokens": 19110846.0,
|
|
"step": 9230
|
|
},
|
|
{
|
|
"entropy": 5.2145326137542725,
|
|
"epoch": 8.388005452067242,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 8.374931606535099e-05,
|
|
"loss": 4.589,
|
|
"mean_token_accuracy": 0.22713644653558732,
|
|
"num_tokens": 19122177.0,
|
|
"step": 9235
|
|
},
|
|
{
|
|
"entropy": 5.224031400680542,
|
|
"epoch": 8.392548841435712,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 8.356337345152002e-05,
|
|
"loss": 4.4951,
|
|
"mean_token_accuracy": 0.23516712188720704,
|
|
"num_tokens": 19131871.0,
|
|
"step": 9240
|
|
},
|
|
{
|
|
"entropy": 5.154409503936767,
|
|
"epoch": 8.39709223080418,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 8.33779031885348e-05,
|
|
"loss": 4.4564,
|
|
"mean_token_accuracy": 0.2287144958972931,
|
|
"num_tokens": 19141375.0,
|
|
"step": 9245
|
|
},
|
|
{
|
|
"entropy": 5.277838468551636,
|
|
"epoch": 8.401635620172648,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 8.319290573402494e-05,
|
|
"loss": 4.5318,
|
|
"mean_token_accuracy": 0.2343215137720108,
|
|
"num_tokens": 19150914.0,
|
|
"step": 9250
|
|
},
|
|
{
|
|
"entropy": 5.241430044174194,
|
|
"epoch": 8.406179009541118,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 8.300838154445314e-05,
|
|
"loss": 4.519,
|
|
"mean_token_accuracy": 0.23212882727384568,
|
|
"num_tokens": 19160683.0,
|
|
"step": 9255
|
|
},
|
|
{
|
|
"entropy": 5.1860404968261715,
|
|
"epoch": 8.410722398909586,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 8.282433107511466e-05,
|
|
"loss": 4.5542,
|
|
"mean_token_accuracy": 0.22307749539613725,
|
|
"num_tokens": 19171477.0,
|
|
"step": 9260
|
|
},
|
|
{
|
|
"entropy": 5.243020629882812,
|
|
"epoch": 8.415265788278056,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 8.264075478013552e-05,
|
|
"loss": 4.5352,
|
|
"mean_token_accuracy": 0.22371068745851516,
|
|
"num_tokens": 19181854.0,
|
|
"step": 9265
|
|
},
|
|
{
|
|
"entropy": 5.172072553634644,
|
|
"epoch": 8.419809177646524,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 8.245765311247216e-05,
|
|
"loss": 4.541,
|
|
"mean_token_accuracy": 0.22736697494983674,
|
|
"num_tokens": 19192165.0,
|
|
"step": 9270
|
|
},
|
|
{
|
|
"entropy": 5.258321475982666,
|
|
"epoch": 8.424352567014994,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 8.227502652390968e-05,
|
|
"loss": 4.5178,
|
|
"mean_token_accuracy": 0.24100998789072037,
|
|
"num_tokens": 19203735.0,
|
|
"step": 9275
|
|
},
|
|
{
|
|
"entropy": 5.213497829437256,
|
|
"epoch": 8.428895956383462,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 8.2092875465061e-05,
|
|
"loss": 4.4773,
|
|
"mean_token_accuracy": 0.23049004673957824,
|
|
"num_tokens": 19213275.0,
|
|
"step": 9280
|
|
},
|
|
{
|
|
"entropy": 5.260906600952149,
|
|
"epoch": 8.43343934575193,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 8.191120038536575e-05,
|
|
"loss": 4.497,
|
|
"mean_token_accuracy": 0.2312250554561615,
|
|
"num_tokens": 19224012.0,
|
|
"step": 9285
|
|
},
|
|
{
|
|
"entropy": 5.220722436904907,
|
|
"epoch": 8.4379827351204,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 8.173000173308921e-05,
|
|
"loss": 4.5614,
|
|
"mean_token_accuracy": 0.22335334569215776,
|
|
"num_tokens": 19234356.0,
|
|
"step": 9290
|
|
},
|
|
{
|
|
"entropy": 5.228305816650391,
|
|
"epoch": 8.442526124488868,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 8.154927995532098e-05,
|
|
"loss": 4.5832,
|
|
"mean_token_accuracy": 0.2224121779203415,
|
|
"num_tokens": 19245297.0,
|
|
"step": 9295
|
|
},
|
|
{
|
|
"entropy": 5.245227956771851,
|
|
"epoch": 8.447069513857338,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 8.136903549797408e-05,
|
|
"loss": 4.5167,
|
|
"mean_token_accuracy": 0.23111643344163896,
|
|
"num_tokens": 19254922.0,
|
|
"step": 9300
|
|
},
|
|
{
|
|
"entropy": 5.269691371917725,
|
|
"epoch": 8.451612903225806,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 8.118926880578378e-05,
|
|
"loss": 4.6202,
|
|
"mean_token_accuracy": 0.22602852433919907,
|
|
"num_tokens": 19265712.0,
|
|
"step": 9305
|
|
},
|
|
{
|
|
"entropy": 5.225082445144653,
|
|
"epoch": 8.456156292594276,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 8.100998032230656e-05,
|
|
"loss": 4.4816,
|
|
"mean_token_accuracy": 0.23018349558115006,
|
|
"num_tokens": 19275725.0,
|
|
"step": 9310
|
|
},
|
|
{
|
|
"entropy": 5.198310899734497,
|
|
"epoch": 8.460699681962744,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 8.083117048991895e-05,
|
|
"loss": 4.4936,
|
|
"mean_token_accuracy": 0.23143236339092255,
|
|
"num_tokens": 19285880.0,
|
|
"step": 9315
|
|
},
|
|
{
|
|
"entropy": 5.206596708297729,
|
|
"epoch": 8.465243071331214,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 8.065283974981638e-05,
|
|
"loss": 4.5184,
|
|
"mean_token_accuracy": 0.218496872484684,
|
|
"num_tokens": 19296294.0,
|
|
"step": 9320
|
|
},
|
|
{
|
|
"entropy": 5.240231657028199,
|
|
"epoch": 8.469786460699682,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 8.047498854201222e-05,
|
|
"loss": 4.5316,
|
|
"mean_token_accuracy": 0.22735022157430648,
|
|
"num_tokens": 19306670.0,
|
|
"step": 9325
|
|
},
|
|
{
|
|
"entropy": 5.2919717788696286,
|
|
"epoch": 8.47432985006815,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 8.029761730533678e-05,
|
|
"loss": 4.61,
|
|
"mean_token_accuracy": 0.2160082221031189,
|
|
"num_tokens": 19317635.0,
|
|
"step": 9330
|
|
},
|
|
{
|
|
"entropy": 5.28932638168335,
|
|
"epoch": 8.47887323943662,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 8.012072647743569e-05,
|
|
"loss": 4.5987,
|
|
"mean_token_accuracy": 0.21901443600654602,
|
|
"num_tokens": 19328663.0,
|
|
"step": 9335
|
|
},
|
|
{
|
|
"entropy": 5.211911249160766,
|
|
"epoch": 8.483416628805088,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 7.994431649476974e-05,
|
|
"loss": 4.4714,
|
|
"mean_token_accuracy": 0.2363119974732399,
|
|
"num_tokens": 19338319.0,
|
|
"step": 9340
|
|
},
|
|
{
|
|
"entropy": 5.235103416442871,
|
|
"epoch": 8.487960018173558,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 7.976838779261285e-05,
|
|
"loss": 4.4327,
|
|
"mean_token_accuracy": 0.2369816094636917,
|
|
"num_tokens": 19347448.0,
|
|
"step": 9345
|
|
},
|
|
{
|
|
"entropy": 5.232003116607666,
|
|
"epoch": 8.492503407542026,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 7.959294080505179e-05,
|
|
"loss": 4.5088,
|
|
"mean_token_accuracy": 0.2268419235944748,
|
|
"num_tokens": 19358077.0,
|
|
"step": 9350
|
|
},
|
|
{
|
|
"entropy": 5.268125677108765,
|
|
"epoch": 8.497046796910496,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 7.941797596498435e-05,
|
|
"loss": 4.5723,
|
|
"mean_token_accuracy": 0.2271113723516464,
|
|
"num_tokens": 19368795.0,
|
|
"step": 9355
|
|
},
|
|
{
|
|
"entropy": 5.251529693603516,
|
|
"epoch": 8.501590186278964,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 7.924349370411904e-05,
|
|
"loss": 4.6225,
|
|
"mean_token_accuracy": 0.21757382154464722,
|
|
"num_tokens": 19379791.0,
|
|
"step": 9360
|
|
},
|
|
{
|
|
"entropy": 5.244750547409057,
|
|
"epoch": 8.506133575647432,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 7.906949445297342e-05,
|
|
"loss": 4.5716,
|
|
"mean_token_accuracy": 0.22136852890253067,
|
|
"num_tokens": 19390146.0,
|
|
"step": 9365
|
|
},
|
|
{
|
|
"entropy": 5.251524019241333,
|
|
"epoch": 8.510676965015902,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 7.889597864087336e-05,
|
|
"loss": 4.5754,
|
|
"mean_token_accuracy": 0.22505573481321334,
|
|
"num_tokens": 19400950.0,
|
|
"step": 9370
|
|
},
|
|
{
|
|
"entropy": 5.254938173294067,
|
|
"epoch": 8.51522035438437,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 7.872294669595185e-05,
|
|
"loss": 4.4857,
|
|
"mean_token_accuracy": 0.23549168854951857,
|
|
"num_tokens": 19411131.0,
|
|
"step": 9375
|
|
},
|
|
{
|
|
"entropy": 5.204954719543457,
|
|
"epoch": 8.51976374375284,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 7.855039904514808e-05,
|
|
"loss": 4.5126,
|
|
"mean_token_accuracy": 0.22805588245391845,
|
|
"num_tokens": 19421062.0,
|
|
"step": 9380
|
|
},
|
|
{
|
|
"entropy": 5.239051675796508,
|
|
"epoch": 8.524307133121308,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 7.837833611420618e-05,
|
|
"loss": 4.5382,
|
|
"mean_token_accuracy": 0.22770656794309616,
|
|
"num_tokens": 19430919.0,
|
|
"step": 9385
|
|
},
|
|
{
|
|
"entropy": 5.241811323165893,
|
|
"epoch": 8.528850522489778,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 7.820675832767435e-05,
|
|
"loss": 4.5629,
|
|
"mean_token_accuracy": 0.2208409368991852,
|
|
"num_tokens": 19442082.0,
|
|
"step": 9390
|
|
},
|
|
{
|
|
"entropy": 5.251900482177734,
|
|
"epoch": 8.533393911858246,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 7.803566610890365e-05,
|
|
"loss": 4.5677,
|
|
"mean_token_accuracy": 0.22302346527576447,
|
|
"num_tokens": 19453029.0,
|
|
"step": 9395
|
|
},
|
|
{
|
|
"entropy": 5.21443190574646,
|
|
"epoch": 8.537937301226716,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 7.786505988004722e-05,
|
|
"loss": 4.5589,
|
|
"mean_token_accuracy": 0.22053912729024888,
|
|
"num_tokens": 19463066.0,
|
|
"step": 9400
|
|
},
|
|
{
|
|
"entropy": 5.253060626983642,
|
|
"epoch": 8.542480690595184,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 7.769494006205894e-05,
|
|
"loss": 4.5902,
|
|
"mean_token_accuracy": 0.2248321458697319,
|
|
"num_tokens": 19474599.0,
|
|
"step": 9405
|
|
},
|
|
{
|
|
"entropy": 5.25119457244873,
|
|
"epoch": 8.547024079963652,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 7.752530707469252e-05,
|
|
"loss": 4.5609,
|
|
"mean_token_accuracy": 0.22573293894529342,
|
|
"num_tokens": 19484678.0,
|
|
"step": 9410
|
|
},
|
|
{
|
|
"entropy": 5.247981882095337,
|
|
"epoch": 8.551567469332122,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 7.73561613365005e-05,
|
|
"loss": 4.5729,
|
|
"mean_token_accuracy": 0.22442823946475982,
|
|
"num_tokens": 19494932.0,
|
|
"step": 9415
|
|
},
|
|
{
|
|
"entropy": 5.237647581100464,
|
|
"epoch": 8.55611085870059,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 7.718750326483321e-05,
|
|
"loss": 4.4804,
|
|
"mean_token_accuracy": 0.22829496562480928,
|
|
"num_tokens": 19504471.0,
|
|
"step": 9420
|
|
},
|
|
{
|
|
"entropy": 5.228067207336426,
|
|
"epoch": 8.56065424806906,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 7.701933327583766e-05,
|
|
"loss": 4.5225,
|
|
"mean_token_accuracy": 0.23134373426437377,
|
|
"num_tokens": 19514400.0,
|
|
"step": 9425
|
|
},
|
|
{
|
|
"entropy": 5.214640808105469,
|
|
"epoch": 8.565197637437528,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 7.685165178445658e-05,
|
|
"loss": 4.5401,
|
|
"mean_token_accuracy": 0.22638291567564012,
|
|
"num_tokens": 19524923.0,
|
|
"step": 9430
|
|
},
|
|
{
|
|
"entropy": 5.209314298629761,
|
|
"epoch": 8.569741026805998,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 7.668445920442732e-05,
|
|
"loss": 4.5498,
|
|
"mean_token_accuracy": 0.2299617901444435,
|
|
"num_tokens": 19535975.0,
|
|
"step": 9435
|
|
},
|
|
{
|
|
"entropy": 5.228262853622437,
|
|
"epoch": 8.574284416174466,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 7.651775594828112e-05,
|
|
"loss": 4.5653,
|
|
"mean_token_accuracy": 0.23294532299041748,
|
|
"num_tokens": 19546457.0,
|
|
"step": 9440
|
|
},
|
|
{
|
|
"entropy": 5.255066442489624,
|
|
"epoch": 8.578827805542936,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 7.635154242734146e-05,
|
|
"loss": 4.5917,
|
|
"mean_token_accuracy": 0.23208603113889695,
|
|
"num_tokens": 19557345.0,
|
|
"step": 9445
|
|
},
|
|
{
|
|
"entropy": 5.164909839630127,
|
|
"epoch": 8.583371194911404,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 7.618581905172385e-05,
|
|
"loss": 4.3855,
|
|
"mean_token_accuracy": 0.24225981682538986,
|
|
"num_tokens": 19566983.0,
|
|
"step": 9450
|
|
},
|
|
{
|
|
"entropy": 5.2450737953186035,
|
|
"epoch": 8.587914584279872,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 7.60205862303342e-05,
|
|
"loss": 4.549,
|
|
"mean_token_accuracy": 0.22877457439899446,
|
|
"num_tokens": 19578030.0,
|
|
"step": 9455
|
|
},
|
|
{
|
|
"entropy": 5.314523935317993,
|
|
"epoch": 8.592457973648342,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 7.585584437086806e-05,
|
|
"loss": 4.6361,
|
|
"mean_token_accuracy": 0.2175690546631813,
|
|
"num_tokens": 19587956.0,
|
|
"step": 9460
|
|
},
|
|
{
|
|
"entropy": 5.212931299209595,
|
|
"epoch": 8.59700136301681,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 7.569159387980958e-05,
|
|
"loss": 4.4874,
|
|
"mean_token_accuracy": 0.23831190466880797,
|
|
"num_tokens": 19597505.0,
|
|
"step": 9465
|
|
},
|
|
{
|
|
"entropy": 5.2571978092193605,
|
|
"epoch": 8.60154475238528,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 7.552783516243056e-05,
|
|
"loss": 4.5827,
|
|
"mean_token_accuracy": 0.2251001015305519,
|
|
"num_tokens": 19608461.0,
|
|
"step": 9470
|
|
},
|
|
{
|
|
"entropy": 5.209439611434936,
|
|
"epoch": 8.606088141753748,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 7.536456862278936e-05,
|
|
"loss": 4.5101,
|
|
"mean_token_accuracy": 0.2273036703467369,
|
|
"num_tokens": 19618430.0,
|
|
"step": 9475
|
|
},
|
|
{
|
|
"entropy": 5.311567211151123,
|
|
"epoch": 8.610631531122218,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 7.520179466372988e-05,
|
|
"loss": 4.6358,
|
|
"mean_token_accuracy": 0.21547872722148895,
|
|
"num_tokens": 19628504.0,
|
|
"step": 9480
|
|
},
|
|
{
|
|
"entropy": 5.242528247833252,
|
|
"epoch": 8.615174920490686,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 7.503951368688068e-05,
|
|
"loss": 4.5736,
|
|
"mean_token_accuracy": 0.22367301732301711,
|
|
"num_tokens": 19639201.0,
|
|
"step": 9485
|
|
},
|
|
{
|
|
"entropy": 5.185754680633545,
|
|
"epoch": 8.619718309859154,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 7.487772609265401e-05,
|
|
"loss": 4.467,
|
|
"mean_token_accuracy": 0.2358046904206276,
|
|
"num_tokens": 19649367.0,
|
|
"step": 9490
|
|
},
|
|
{
|
|
"entropy": 5.225733470916748,
|
|
"epoch": 8.624261699227624,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 7.471643228024466e-05,
|
|
"loss": 4.5408,
|
|
"mean_token_accuracy": 0.22812853902578353,
|
|
"num_tokens": 19659466.0,
|
|
"step": 9495
|
|
},
|
|
{
|
|
"entropy": 5.2247038841247555,
|
|
"epoch": 8.628805088596092,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 7.455563264762903e-05,
|
|
"loss": 4.5094,
|
|
"mean_token_accuracy": 0.23056551367044448,
|
|
"num_tokens": 19669875.0,
|
|
"step": 9500
|
|
},
|
|
{
|
|
"entropy": 5.230162763595581,
|
|
"epoch": 8.633348477964562,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 7.439532759156422e-05,
|
|
"loss": 4.5401,
|
|
"mean_token_accuracy": 0.23308224380016326,
|
|
"num_tokens": 19679688.0,
|
|
"step": 9505
|
|
},
|
|
{
|
|
"entropy": 5.197892522811889,
|
|
"epoch": 8.63789186733303,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 7.423551750758711e-05,
|
|
"loss": 4.508,
|
|
"mean_token_accuracy": 0.23602869361639023,
|
|
"num_tokens": 19690170.0,
|
|
"step": 9510
|
|
},
|
|
{
|
|
"entropy": 5.20199990272522,
|
|
"epoch": 8.6424352567015,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 7.407620279001315e-05,
|
|
"loss": 4.507,
|
|
"mean_token_accuracy": 0.23074384331703185,
|
|
"num_tokens": 19701515.0,
|
|
"step": 9515
|
|
},
|
|
{
|
|
"entropy": 5.2756510257720945,
|
|
"epoch": 8.646978646069968,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 7.391738383193553e-05,
|
|
"loss": 4.5868,
|
|
"mean_token_accuracy": 0.2284209117293358,
|
|
"num_tokens": 19712491.0,
|
|
"step": 9520
|
|
},
|
|
{
|
|
"entropy": 5.218889284133911,
|
|
"epoch": 8.651522035438438,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 7.375906102522423e-05,
|
|
"loss": 4.5423,
|
|
"mean_token_accuracy": 0.23464427143335342,
|
|
"num_tokens": 19722800.0,
|
|
"step": 9525
|
|
},
|
|
{
|
|
"entropy": 5.253188562393189,
|
|
"epoch": 8.656065424806906,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 7.360123476052519e-05,
|
|
"loss": 4.5107,
|
|
"mean_token_accuracy": 0.23263811469078063,
|
|
"num_tokens": 19732364.0,
|
|
"step": 9530
|
|
},
|
|
{
|
|
"entropy": 5.194964456558227,
|
|
"epoch": 8.660608814175374,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 7.344390542725882e-05,
|
|
"loss": 4.4871,
|
|
"mean_token_accuracy": 0.23038142025470734,
|
|
"num_tokens": 19742368.0,
|
|
"step": 9535
|
|
},
|
|
{
|
|
"entropy": 5.310920858383179,
|
|
"epoch": 8.665152203543844,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 7.328707341361975e-05,
|
|
"loss": 4.5699,
|
|
"mean_token_accuracy": 0.23072726428508758,
|
|
"num_tokens": 19753087.0,
|
|
"step": 9540
|
|
},
|
|
{
|
|
"entropy": 5.232931900024414,
|
|
"epoch": 8.669695592912312,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 7.313073910657535e-05,
|
|
"loss": 4.5459,
|
|
"mean_token_accuracy": 0.22900285422801972,
|
|
"num_tokens": 19764115.0,
|
|
"step": 9545
|
|
},
|
|
{
|
|
"entropy": 5.257305097579956,
|
|
"epoch": 8.674238982280782,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 7.297490289186495e-05,
|
|
"loss": 4.557,
|
|
"mean_token_accuracy": 0.2360237181186676,
|
|
"num_tokens": 19775778.0,
|
|
"step": 9550
|
|
},
|
|
{
|
|
"entropy": 5.216531658172608,
|
|
"epoch": 8.67878237164925,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 7.281956515399891e-05,
|
|
"loss": 4.5041,
|
|
"mean_token_accuracy": 0.23199820071458815,
|
|
"num_tokens": 19785022.0,
|
|
"step": 9555
|
|
},
|
|
{
|
|
"entropy": 5.232565593719483,
|
|
"epoch": 8.68332576101772,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 7.266472627625776e-05,
|
|
"loss": 4.5335,
|
|
"mean_token_accuracy": 0.23294007927179336,
|
|
"num_tokens": 19795280.0,
|
|
"step": 9560
|
|
},
|
|
{
|
|
"entropy": 5.212299823760986,
|
|
"epoch": 8.687869150386188,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 7.251038664069094e-05,
|
|
"loss": 4.5455,
|
|
"mean_token_accuracy": 0.22932133972644805,
|
|
"num_tokens": 19804703.0,
|
|
"step": 9565
|
|
},
|
|
{
|
|
"entropy": 5.203427267074585,
|
|
"epoch": 8.692412539754656,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 7.235654662811618e-05,
|
|
"loss": 4.5236,
|
|
"mean_token_accuracy": 0.23057784736156464,
|
|
"num_tokens": 19815013.0,
|
|
"step": 9570
|
|
},
|
|
{
|
|
"entropy": 5.280163431167603,
|
|
"epoch": 8.696955929123126,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 7.22032066181184e-05,
|
|
"loss": 4.6089,
|
|
"mean_token_accuracy": 0.22960792779922484,
|
|
"num_tokens": 19825696.0,
|
|
"step": 9575
|
|
},
|
|
{
|
|
"entropy": 5.230686807632447,
|
|
"epoch": 8.701499318491594,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 7.205036698904888e-05,
|
|
"loss": 4.5176,
|
|
"mean_token_accuracy": 0.23178810477256775,
|
|
"num_tokens": 19835218.0,
|
|
"step": 9580
|
|
},
|
|
{
|
|
"entropy": 5.235781621932984,
|
|
"epoch": 8.706042707860064,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 7.18980281180242e-05,
|
|
"loss": 4.5428,
|
|
"mean_token_accuracy": 0.23563148975372314,
|
|
"num_tokens": 19846055.0,
|
|
"step": 9585
|
|
},
|
|
{
|
|
"entropy": 5.276301908493042,
|
|
"epoch": 8.710586097228532,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 7.174619038092537e-05,
|
|
"loss": 4.5644,
|
|
"mean_token_accuracy": 0.22868630588054656,
|
|
"num_tokens": 19856821.0,
|
|
"step": 9590
|
|
},
|
|
{
|
|
"entropy": 5.218929147720337,
|
|
"epoch": 8.715129486597002,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 7.159485415239685e-05,
|
|
"loss": 4.5289,
|
|
"mean_token_accuracy": 0.22849793285131453,
|
|
"num_tokens": 19867269.0,
|
|
"step": 9595
|
|
},
|
|
{
|
|
"entropy": 5.258653545379639,
|
|
"epoch": 8.71967287596547,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 7.144401980584584e-05,
|
|
"loss": 4.5753,
|
|
"mean_token_accuracy": 0.22764002084732055,
|
|
"num_tokens": 19878430.0,
|
|
"step": 9600
|
|
},
|
|
{
|
|
"entropy": 5.227108716964722,
|
|
"epoch": 8.72421626533394,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 7.129368771344108e-05,
|
|
"loss": 4.5461,
|
|
"mean_token_accuracy": 0.22789574712514876,
|
|
"num_tokens": 19889022.0,
|
|
"step": 9605
|
|
},
|
|
{
|
|
"entropy": 5.212688827514649,
|
|
"epoch": 8.728759654702408,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 7.114385824611203e-05,
|
|
"loss": 4.5067,
|
|
"mean_token_accuracy": 0.24074479639530183,
|
|
"num_tokens": 19900064.0,
|
|
"step": 9610
|
|
},
|
|
{
|
|
"entropy": 5.25842776298523,
|
|
"epoch": 8.733303044070876,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 7.099453177354797e-05,
|
|
"loss": 4.5716,
|
|
"mean_token_accuracy": 0.22418853044509887,
|
|
"num_tokens": 19909425.0,
|
|
"step": 9615
|
|
},
|
|
{
|
|
"entropy": 5.209220695495605,
|
|
"epoch": 8.737846433439346,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 7.084570866419727e-05,
|
|
"loss": 4.5531,
|
|
"mean_token_accuracy": 0.22591091245412825,
|
|
"num_tokens": 19919551.0,
|
|
"step": 9620
|
|
},
|
|
{
|
|
"entropy": 5.213638639450073,
|
|
"epoch": 8.742389822807814,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 7.069738928526597e-05,
|
|
"loss": 4.4901,
|
|
"mean_token_accuracy": 0.22993624210357666,
|
|
"num_tokens": 19930289.0,
|
|
"step": 9625
|
|
},
|
|
{
|
|
"entropy": 5.21535062789917,
|
|
"epoch": 8.746933212176284,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 7.054957400271751e-05,
|
|
"loss": 4.5529,
|
|
"mean_token_accuracy": 0.21830520331859588,
|
|
"num_tokens": 19940941.0,
|
|
"step": 9630
|
|
},
|
|
{
|
|
"entropy": 5.166788339614868,
|
|
"epoch": 8.751476601544752,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 7.040226318127142e-05,
|
|
"loss": 4.4913,
|
|
"mean_token_accuracy": 0.23649603128433228,
|
|
"num_tokens": 19951346.0,
|
|
"step": 9635
|
|
},
|
|
{
|
|
"entropy": 5.243351316452026,
|
|
"epoch": 8.756019990913222,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 7.025545718440245e-05,
|
|
"loss": 4.4982,
|
|
"mean_token_accuracy": 0.22831236869096755,
|
|
"num_tokens": 19961519.0,
|
|
"step": 9640
|
|
},
|
|
{
|
|
"entropy": 5.235562372207641,
|
|
"epoch": 8.76056338028169,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 7.01091563743398e-05,
|
|
"loss": 4.5148,
|
|
"mean_token_accuracy": 0.2328753501176834,
|
|
"num_tokens": 19970919.0,
|
|
"step": 9645
|
|
},
|
|
{
|
|
"entropy": 5.210250806808472,
|
|
"epoch": 8.76510676965016,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 6.996336111206619e-05,
|
|
"loss": 4.476,
|
|
"mean_token_accuracy": 0.2314284160733223,
|
|
"num_tokens": 19980591.0,
|
|
"step": 9650
|
|
},
|
|
{
|
|
"entropy": 5.253487539291382,
|
|
"epoch": 8.769650159018628,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 6.981807175731698e-05,
|
|
"loss": 4.5108,
|
|
"mean_token_accuracy": 0.23007301092147828,
|
|
"num_tokens": 19990492.0,
|
|
"step": 9655
|
|
},
|
|
{
|
|
"entropy": 5.2021904468536375,
|
|
"epoch": 8.774193548387096,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 6.967328866857915e-05,
|
|
"loss": 4.5813,
|
|
"mean_token_accuracy": 0.2225154906511307,
|
|
"num_tokens": 20002575.0,
|
|
"step": 9660
|
|
},
|
|
{
|
|
"entropy": 5.210224962234497,
|
|
"epoch": 8.778736937755566,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 6.952901220309063e-05,
|
|
"loss": 4.5002,
|
|
"mean_token_accuracy": 0.23272244185209273,
|
|
"num_tokens": 20012592.0,
|
|
"step": 9665
|
|
},
|
|
{
|
|
"entropy": 5.267421531677246,
|
|
"epoch": 8.783280327124034,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 6.938524271683918e-05,
|
|
"loss": 4.5293,
|
|
"mean_token_accuracy": 0.23242655843496324,
|
|
"num_tokens": 20022790.0,
|
|
"step": 9670
|
|
},
|
|
{
|
|
"entropy": 5.220283365249633,
|
|
"epoch": 8.787823716492504,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 6.924198056456185e-05,
|
|
"loss": 4.5375,
|
|
"mean_token_accuracy": 0.23306997567415239,
|
|
"num_tokens": 20032538.0,
|
|
"step": 9675
|
|
},
|
|
{
|
|
"entropy": 5.261009073257446,
|
|
"epoch": 8.792367105860972,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 6.90992260997436e-05,
|
|
"loss": 4.532,
|
|
"mean_token_accuracy": 0.23372114300727845,
|
|
"num_tokens": 20042603.0,
|
|
"step": 9680
|
|
},
|
|
{
|
|
"entropy": 5.234548950195313,
|
|
"epoch": 8.796910495229442,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 6.895697967461699e-05,
|
|
"loss": 4.5249,
|
|
"mean_token_accuracy": 0.22962442338466643,
|
|
"num_tokens": 20052827.0,
|
|
"step": 9685
|
|
},
|
|
{
|
|
"entropy": 5.146759843826294,
|
|
"epoch": 8.80145388459791,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 6.881524164016087e-05,
|
|
"loss": 4.4543,
|
|
"mean_token_accuracy": 0.23587699681520463,
|
|
"num_tokens": 20062689.0,
|
|
"step": 9690
|
|
},
|
|
{
|
|
"entropy": 5.170178508758545,
|
|
"epoch": 8.805997273966378,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 6.867401234609985e-05,
|
|
"loss": 4.4381,
|
|
"mean_token_accuracy": 0.24923290461301803,
|
|
"num_tokens": 20072094.0,
|
|
"step": 9695
|
|
},
|
|
{
|
|
"entropy": 5.263170003890991,
|
|
"epoch": 8.810540663334848,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 6.853329214090304e-05,
|
|
"loss": 4.544,
|
|
"mean_token_accuracy": 0.22242841869592667,
|
|
"num_tokens": 20082755.0,
|
|
"step": 9700
|
|
},
|
|
{
|
|
"entropy": 5.259328413009643,
|
|
"epoch": 8.815084052703316,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 6.839308137178363e-05,
|
|
"loss": 4.6004,
|
|
"mean_token_accuracy": 0.22155316919088364,
|
|
"num_tokens": 20093917.0,
|
|
"step": 9705
|
|
},
|
|
{
|
|
"entropy": 5.205179977416992,
|
|
"epoch": 8.819627442071786,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 6.825338038469778e-05,
|
|
"loss": 4.5192,
|
|
"mean_token_accuracy": 0.2296544909477234,
|
|
"num_tokens": 20103092.0,
|
|
"step": 9710
|
|
},
|
|
{
|
|
"entropy": 5.284274244308472,
|
|
"epoch": 8.824170831440254,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 6.811418952434375e-05,
|
|
"loss": 4.647,
|
|
"mean_token_accuracy": 0.21642469316720964,
|
|
"num_tokens": 20113934.0,
|
|
"step": 9715
|
|
},
|
|
{
|
|
"entropy": 5.247504615783692,
|
|
"epoch": 8.828714220808724,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 6.797550913416111e-05,
|
|
"loss": 4.4934,
|
|
"mean_token_accuracy": 0.23877303600311278,
|
|
"num_tokens": 20123782.0,
|
|
"step": 9720
|
|
},
|
|
{
|
|
"entropy": 5.231781387329102,
|
|
"epoch": 8.833257610177192,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 6.783733955633004e-05,
|
|
"loss": 4.5235,
|
|
"mean_token_accuracy": 0.22728776782751084,
|
|
"num_tokens": 20133364.0,
|
|
"step": 9725
|
|
},
|
|
{
|
|
"entropy": 5.245758724212647,
|
|
"epoch": 8.837800999545662,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 6.769968113177016e-05,
|
|
"loss": 4.581,
|
|
"mean_token_accuracy": 0.2252163589000702,
|
|
"num_tokens": 20145302.0,
|
|
"step": 9730
|
|
},
|
|
{
|
|
"entropy": 5.193823575973511,
|
|
"epoch": 8.84234438891413,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 6.756253420013996e-05,
|
|
"loss": 4.5169,
|
|
"mean_token_accuracy": 0.23015155047178268,
|
|
"num_tokens": 20156451.0,
|
|
"step": 9735
|
|
},
|
|
{
|
|
"entropy": 5.201619625091553,
|
|
"epoch": 8.846887778282598,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 6.742589909983586e-05,
|
|
"loss": 4.5328,
|
|
"mean_token_accuracy": 0.2313736766576767,
|
|
"num_tokens": 20166151.0,
|
|
"step": 9740
|
|
},
|
|
{
|
|
"entropy": 5.231419420242309,
|
|
"epoch": 8.851431167651068,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 6.728977616799144e-05,
|
|
"loss": 4.5073,
|
|
"mean_token_accuracy": 0.23775599300861358,
|
|
"num_tokens": 20175516.0,
|
|
"step": 9745
|
|
},
|
|
{
|
|
"entropy": 5.22851243019104,
|
|
"epoch": 8.855974557019536,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 6.715416574047645e-05,
|
|
"loss": 4.5669,
|
|
"mean_token_accuracy": 0.22351596653461456,
|
|
"num_tokens": 20186015.0,
|
|
"step": 9750
|
|
},
|
|
{
|
|
"entropy": 5.171449136734009,
|
|
"epoch": 8.860517946388006,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 6.701906815189613e-05,
|
|
"loss": 4.4104,
|
|
"mean_token_accuracy": 0.24298245459794998,
|
|
"num_tokens": 20196863.0,
|
|
"step": 9755
|
|
},
|
|
{
|
|
"entropy": 5.188689374923706,
|
|
"epoch": 8.865061335756474,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 6.688448373559037e-05,
|
|
"loss": 4.459,
|
|
"mean_token_accuracy": 0.23554110527038574,
|
|
"num_tokens": 20207856.0,
|
|
"step": 9760
|
|
},
|
|
{
|
|
"entropy": 5.24181637763977,
|
|
"epoch": 8.869604725124944,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 6.675041282363286e-05,
|
|
"loss": 4.5028,
|
|
"mean_token_accuracy": 0.2341596633195877,
|
|
"num_tokens": 20217881.0,
|
|
"step": 9765
|
|
},
|
|
{
|
|
"entropy": 5.268863153457642,
|
|
"epoch": 8.874148114493412,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 6.661685574683021e-05,
|
|
"loss": 4.5771,
|
|
"mean_token_accuracy": 0.226200732588768,
|
|
"num_tokens": 20227799.0,
|
|
"step": 9770
|
|
},
|
|
{
|
|
"entropy": 5.248539066314697,
|
|
"epoch": 8.87869150386188,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 6.648381283472128e-05,
|
|
"loss": 4.5403,
|
|
"mean_token_accuracy": 0.23037189543247222,
|
|
"num_tokens": 20238154.0,
|
|
"step": 9775
|
|
},
|
|
{
|
|
"entropy": 5.263778209686279,
|
|
"epoch": 8.88323489323035,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 6.635128441557615e-05,
|
|
"loss": 4.5925,
|
|
"mean_token_accuracy": 0.218518228828907,
|
|
"num_tokens": 20248740.0,
|
|
"step": 9780
|
|
},
|
|
{
|
|
"entropy": 5.299910020828247,
|
|
"epoch": 8.887778282598818,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 6.621927081639563e-05,
|
|
"loss": 4.62,
|
|
"mean_token_accuracy": 0.2284785181283951,
|
|
"num_tokens": 20259166.0,
|
|
"step": 9785
|
|
},
|
|
{
|
|
"entropy": 5.1845290184021,
|
|
"epoch": 8.892321671967288,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 6.608777236291003e-05,
|
|
"loss": 4.4902,
|
|
"mean_token_accuracy": 0.23163673728704454,
|
|
"num_tokens": 20270263.0,
|
|
"step": 9790
|
|
},
|
|
{
|
|
"entropy": 5.267273759841919,
|
|
"epoch": 8.896865061335756,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 6.59567893795788e-05,
|
|
"loss": 4.4815,
|
|
"mean_token_accuracy": 0.23424373865127562,
|
|
"num_tokens": 20279639.0,
|
|
"step": 9795
|
|
},
|
|
{
|
|
"entropy": 5.284946489334106,
|
|
"epoch": 8.901408450704226,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 6.58263221895894e-05,
|
|
"loss": 4.6012,
|
|
"mean_token_accuracy": 0.22579760402441024,
|
|
"num_tokens": 20289662.0,
|
|
"step": 9800
|
|
},
|
|
{
|
|
"entropy": 5.198963737487793,
|
|
"epoch": 8.905951840072694,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 6.569637111485666e-05,
|
|
"loss": 4.4713,
|
|
"mean_token_accuracy": 0.23619935065507888,
|
|
"num_tokens": 20300564.0,
|
|
"step": 9805
|
|
},
|
|
{
|
|
"entropy": 5.182671737670899,
|
|
"epoch": 8.910495229441164,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 6.556693647602191e-05,
|
|
"loss": 4.5371,
|
|
"mean_token_accuracy": 0.22914608418941498,
|
|
"num_tokens": 20311085.0,
|
|
"step": 9810
|
|
},
|
|
{
|
|
"entropy": 5.220917415618897,
|
|
"epoch": 8.915038618809632,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 6.543801859245229e-05,
|
|
"loss": 4.581,
|
|
"mean_token_accuracy": 0.21957394629716873,
|
|
"num_tokens": 20321470.0,
|
|
"step": 9815
|
|
},
|
|
{
|
|
"entropy": 5.269989728927612,
|
|
"epoch": 8.9195820081781,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 6.530961778223988e-05,
|
|
"loss": 4.5651,
|
|
"mean_token_accuracy": 0.2251200333237648,
|
|
"num_tokens": 20331699.0,
|
|
"step": 9820
|
|
},
|
|
{
|
|
"entropy": 5.228421878814697,
|
|
"epoch": 8.92412539754657,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 6.518173436220089e-05,
|
|
"loss": 4.5488,
|
|
"mean_token_accuracy": 0.22203637510538102,
|
|
"num_tokens": 20342267.0,
|
|
"step": 9825
|
|
},
|
|
{
|
|
"entropy": 5.216590404510498,
|
|
"epoch": 8.928668786915038,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 6.505436864787489e-05,
|
|
"loss": 4.5418,
|
|
"mean_token_accuracy": 0.22578488737344743,
|
|
"num_tokens": 20352859.0,
|
|
"step": 9830
|
|
},
|
|
{
|
|
"entropy": 5.227667188644409,
|
|
"epoch": 8.933212176283508,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 6.49275209535242e-05,
|
|
"loss": 4.4464,
|
|
"mean_token_accuracy": 0.23869647085666656,
|
|
"num_tokens": 20363743.0,
|
|
"step": 9835
|
|
},
|
|
{
|
|
"entropy": 5.204774236679077,
|
|
"epoch": 8.937755565651976,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 6.480119159213288e-05,
|
|
"loss": 4.5146,
|
|
"mean_token_accuracy": 0.22970598340034484,
|
|
"num_tokens": 20373942.0,
|
|
"step": 9840
|
|
},
|
|
{
|
|
"entropy": 5.199889850616455,
|
|
"epoch": 8.942298955020446,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 6.467538087540606e-05,
|
|
"loss": 4.4979,
|
|
"mean_token_accuracy": 0.2337929978966713,
|
|
"num_tokens": 20384284.0,
|
|
"step": 9845
|
|
},
|
|
{
|
|
"entropy": 5.219797992706299,
|
|
"epoch": 8.946842344388914,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 6.455008911376914e-05,
|
|
"loss": 4.5189,
|
|
"mean_token_accuracy": 0.2305069461464882,
|
|
"num_tokens": 20395304.0,
|
|
"step": 9850
|
|
},
|
|
{
|
|
"entropy": 5.241052579879761,
|
|
"epoch": 8.951385733757384,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 6.442531661636715e-05,
|
|
"loss": 4.5309,
|
|
"mean_token_accuracy": 0.2244285061955452,
|
|
"num_tokens": 20405788.0,
|
|
"step": 9855
|
|
},
|
|
{
|
|
"entropy": 5.243068504333496,
|
|
"epoch": 8.955929123125852,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 6.430106369106381e-05,
|
|
"loss": 4.5651,
|
|
"mean_token_accuracy": 0.22922795563936232,
|
|
"num_tokens": 20416581.0,
|
|
"step": 9860
|
|
},
|
|
{
|
|
"entropy": 5.279593563079834,
|
|
"epoch": 8.96047251249432,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 6.417733064444083e-05,
|
|
"loss": 4.6301,
|
|
"mean_token_accuracy": 0.22021029889583588,
|
|
"num_tokens": 20427969.0,
|
|
"step": 9865
|
|
},
|
|
{
|
|
"entropy": 5.1886180400848385,
|
|
"epoch": 8.96501590186279,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 6.405411778179722e-05,
|
|
"loss": 4.4665,
|
|
"mean_token_accuracy": 0.23078786432743073,
|
|
"num_tokens": 20437757.0,
|
|
"step": 9870
|
|
},
|
|
{
|
|
"entropy": 5.2900224208831785,
|
|
"epoch": 8.969559291231258,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 6.39314254071485e-05,
|
|
"loss": 4.5434,
|
|
"mean_token_accuracy": 0.23046631664037703,
|
|
"num_tokens": 20447278.0,
|
|
"step": 9875
|
|
},
|
|
{
|
|
"entropy": 5.24150276184082,
|
|
"epoch": 8.974102680599728,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 6.380925382322584e-05,
|
|
"loss": 4.5292,
|
|
"mean_token_accuracy": 0.22799777388572692,
|
|
"num_tokens": 20456566.0,
|
|
"step": 9880
|
|
},
|
|
{
|
|
"entropy": 5.231875419616699,
|
|
"epoch": 8.978646069968196,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 6.368760333147555e-05,
|
|
"loss": 4.5405,
|
|
"mean_token_accuracy": 0.23025715798139573,
|
|
"num_tokens": 20466794.0,
|
|
"step": 9885
|
|
},
|
|
{
|
|
"entropy": 5.229581117630005,
|
|
"epoch": 8.983189459336666,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 6.356647423205809e-05,
|
|
"loss": 4.5369,
|
|
"mean_token_accuracy": 0.224705271422863,
|
|
"num_tokens": 20476778.0,
|
|
"step": 9890
|
|
},
|
|
{
|
|
"entropy": 5.226847982406616,
|
|
"epoch": 8.987732848705134,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 6.344586682384748e-05,
|
|
"loss": 4.4965,
|
|
"mean_token_accuracy": 0.2329073891043663,
|
|
"num_tokens": 20487724.0,
|
|
"step": 9895
|
|
},
|
|
{
|
|
"entropy": 5.189176464080811,
|
|
"epoch": 8.992276238073602,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 6.332578140443045e-05,
|
|
"loss": 4.4838,
|
|
"mean_token_accuracy": 0.22950035184621811,
|
|
"num_tokens": 20498186.0,
|
|
"step": 9900
|
|
},
|
|
{
|
|
"entropy": 5.2191352367401125,
|
|
"epoch": 8.996819627442072,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 6.320621827010595e-05,
|
|
"loss": 4.5376,
|
|
"mean_token_accuracy": 0.22828880995512008,
|
|
"num_tokens": 20508212.0,
|
|
"step": 9905
|
|
},
|
|
{
|
|
"entropy": 5.160486963060167,
|
|
"epoch": 9.000908677873694,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 6.308717771588407e-05,
|
|
"loss": 4.4568,
|
|
"mean_token_accuracy": 0.24089167184299892,
|
|
"num_tokens": 20516399.0,
|
|
"step": 9910
|
|
},
|
|
{
|
|
"entropy": 5.221367597579956,
|
|
"epoch": 9.005452067242162,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 6.296866003548555e-05,
|
|
"loss": 4.5267,
|
|
"mean_token_accuracy": 0.22571078687906265,
|
|
"num_tokens": 20525985.0,
|
|
"step": 9915
|
|
},
|
|
{
|
|
"entropy": 5.239675569534302,
|
|
"epoch": 9.009995456610632,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 6.285066552134091e-05,
|
|
"loss": 4.5183,
|
|
"mean_token_accuracy": 0.2310733512043953,
|
|
"num_tokens": 20537229.0,
|
|
"step": 9920
|
|
},
|
|
{
|
|
"entropy": 5.237780427932739,
|
|
"epoch": 9.0145388459791,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 6.273319446459002e-05,
|
|
"loss": 4.503,
|
|
"mean_token_accuracy": 0.2331226035952568,
|
|
"num_tokens": 20547822.0,
|
|
"step": 9925
|
|
},
|
|
{
|
|
"entropy": 5.1997284412384035,
|
|
"epoch": 9.01908223534757,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 6.261624715508095e-05,
|
|
"loss": 4.4455,
|
|
"mean_token_accuracy": 0.24104345291852952,
|
|
"num_tokens": 20557954.0,
|
|
"step": 9930
|
|
},
|
|
{
|
|
"entropy": 5.22488226890564,
|
|
"epoch": 9.023625624716038,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 6.249982388136958e-05,
|
|
"loss": 4.4975,
|
|
"mean_token_accuracy": 0.23631449043750763,
|
|
"num_tokens": 20568129.0,
|
|
"step": 9935
|
|
},
|
|
{
|
|
"entropy": 5.238377904891967,
|
|
"epoch": 9.028169014084508,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 6.238392493071873e-05,
|
|
"loss": 4.5232,
|
|
"mean_token_accuracy": 0.23070875704288482,
|
|
"num_tokens": 20578218.0,
|
|
"step": 9940
|
|
},
|
|
{
|
|
"entropy": 5.207782220840454,
|
|
"epoch": 9.032712403452976,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 6.226855058909762e-05,
|
|
"loss": 4.473,
|
|
"mean_token_accuracy": 0.23204725831747056,
|
|
"num_tokens": 20587018.0,
|
|
"step": 9945
|
|
},
|
|
{
|
|
"entropy": 5.292781114578247,
|
|
"epoch": 9.037255792821444,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 6.215370114118092e-05,
|
|
"loss": 4.5532,
|
|
"mean_token_accuracy": 0.23056037724018097,
|
|
"num_tokens": 20597008.0,
|
|
"step": 9950
|
|
},
|
|
{
|
|
"entropy": 5.211698961257935,
|
|
"epoch": 9.041799182189914,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 6.203937687034822e-05,
|
|
"loss": 4.4621,
|
|
"mean_token_accuracy": 0.24110229164361954,
|
|
"num_tokens": 20607281.0,
|
|
"step": 9955
|
|
},
|
|
{
|
|
"entropy": 5.175335311889649,
|
|
"epoch": 9.046342571558382,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 6.192557805868328e-05,
|
|
"loss": 4.4452,
|
|
"mean_token_accuracy": 0.2387310430407524,
|
|
"num_tokens": 20616931.0,
|
|
"step": 9960
|
|
},
|
|
{
|
|
"entropy": 5.211600112915039,
|
|
"epoch": 9.050885960926852,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 6.181230498697343e-05,
|
|
"loss": 4.4852,
|
|
"mean_token_accuracy": 0.2303295314311981,
|
|
"num_tokens": 20627538.0,
|
|
"step": 9965
|
|
},
|
|
{
|
|
"entropy": 5.235451555252075,
|
|
"epoch": 9.05542935029532,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 6.169955793470859e-05,
|
|
"loss": 4.5315,
|
|
"mean_token_accuracy": 0.22524880319833757,
|
|
"num_tokens": 20639057.0,
|
|
"step": 9970
|
|
},
|
|
{
|
|
"entropy": 5.210330057144165,
|
|
"epoch": 9.05997273966379,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 6.158733718008102e-05,
|
|
"loss": 4.5047,
|
|
"mean_token_accuracy": 0.23207108080387115,
|
|
"num_tokens": 20648930.0,
|
|
"step": 9975
|
|
},
|
|
{
|
|
"entropy": 5.216629362106323,
|
|
"epoch": 9.064516129032258,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 6.147564299998422e-05,
|
|
"loss": 4.4778,
|
|
"mean_token_accuracy": 0.24301124215126038,
|
|
"num_tokens": 20660267.0,
|
|
"step": 9980
|
|
},
|
|
{
|
|
"entropy": 5.255053281784058,
|
|
"epoch": 9.069059518400726,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 6.136447567001251e-05,
|
|
"loss": 4.5146,
|
|
"mean_token_accuracy": 0.23564112484455108,
|
|
"num_tokens": 20671607.0,
|
|
"step": 9985
|
|
},
|
|
{
|
|
"entropy": 5.204305791854859,
|
|
"epoch": 9.073602907769196,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 6.125383546446015e-05,
|
|
"loss": 4.4479,
|
|
"mean_token_accuracy": 0.23726065307855607,
|
|
"num_tokens": 20681391.0,
|
|
"step": 9990
|
|
},
|
|
{
|
|
"entropy": 5.242854452133178,
|
|
"epoch": 9.078146297137664,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 6.114372265632095e-05,
|
|
"loss": 4.4955,
|
|
"mean_token_accuracy": 0.23196815252304076,
|
|
"num_tokens": 20691031.0,
|
|
"step": 9995
|
|
},
|
|
{
|
|
"entropy": 5.2010785102844235,
|
|
"epoch": 9.082689686506134,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 6.1034137517287256e-05,
|
|
"loss": 4.4876,
|
|
"mean_token_accuracy": 0.22782512307167052,
|
|
"num_tokens": 20700446.0,
|
|
"step": 10000
|
|
},
|
|
{
|
|
"epoch": 9.082689686506134,
|
|
"eval_entropy": 5.158197808820148,
|
|
"eval_loss": 5.681859493255615,
|
|
"eval_mean_token_accuracy": 0.17400492531962172,
|
|
"eval_num_tokens": 20700446.0,
|
|
"eval_runtime": 2.5738,
|
|
"eval_samples_per_second": 1334.626,
|
|
"eval_steps_per_second": 167.071,
|
|
"step": 10000
|
|
},
|
|
{
|
|
"entropy": 5.212341070175171,
|
|
"epoch": 9.087233075874602,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 6.092508031774954e-05,
|
|
"loss": 4.5411,
|
|
"mean_token_accuracy": 0.22510440796613693,
|
|
"num_tokens": 20711190.0,
|
|
"step": 10005
|
|
},
|
|
{
|
|
"entropy": 5.236629247665405,
|
|
"epoch": 9.091776465243072,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 6.081655132679551e-05,
|
|
"loss": 4.4972,
|
|
"mean_token_accuracy": 0.23272550404071807,
|
|
"num_tokens": 20720194.0,
|
|
"step": 10010
|
|
},
|
|
{
|
|
"entropy": 5.2374927520751955,
|
|
"epoch": 9.09631985461154,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 6.07085508122098e-05,
|
|
"loss": 4.5233,
|
|
"mean_token_accuracy": 0.23639775365591048,
|
|
"num_tokens": 20729877.0,
|
|
"step": 10015
|
|
},
|
|
{
|
|
"entropy": 5.217492532730103,
|
|
"epoch": 9.10086324398001,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 6.060107904047288e-05,
|
|
"loss": 4.4832,
|
|
"mean_token_accuracy": 0.23519552052021026,
|
|
"num_tokens": 20739825.0,
|
|
"step": 10020
|
|
},
|
|
{
|
|
"entropy": 5.222026538848877,
|
|
"epoch": 9.105406633348478,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 6.0494136276760635e-05,
|
|
"loss": 4.4677,
|
|
"mean_token_accuracy": 0.2326893076300621,
|
|
"num_tokens": 20750199.0,
|
|
"step": 10025
|
|
},
|
|
{
|
|
"entropy": 5.246247100830078,
|
|
"epoch": 9.109950022716946,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 6.03877227849437e-05,
|
|
"loss": 4.5376,
|
|
"mean_token_accuracy": 0.23021015524864197,
|
|
"num_tokens": 20761554.0,
|
|
"step": 10030
|
|
},
|
|
{
|
|
"entropy": 5.311245965957641,
|
|
"epoch": 9.114493412085416,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 6.028183882758685e-05,
|
|
"loss": 4.6278,
|
|
"mean_token_accuracy": 0.22566632479429244,
|
|
"num_tokens": 20774021.0,
|
|
"step": 10035
|
|
},
|
|
{
|
|
"entropy": 5.247481060028076,
|
|
"epoch": 9.119036801453884,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 6.01764846659482e-05,
|
|
"loss": 4.4871,
|
|
"mean_token_accuracy": 0.2331893563270569,
|
|
"num_tokens": 20785081.0,
|
|
"step": 10040
|
|
},
|
|
{
|
|
"entropy": 5.279779672622681,
|
|
"epoch": 9.123580190822354,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 6.0071660559978645e-05,
|
|
"loss": 4.5232,
|
|
"mean_token_accuracy": 0.2267613783478737,
|
|
"num_tokens": 20794862.0,
|
|
"step": 10045
|
|
},
|
|
{
|
|
"entropy": 5.222015905380249,
|
|
"epoch": 9.128123580190822,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 5.996736676832124e-05,
|
|
"loss": 4.5161,
|
|
"mean_token_accuracy": 0.22535496652126313,
|
|
"num_tokens": 20806313.0,
|
|
"step": 10050
|
|
},
|
|
{
|
|
"entropy": 5.183051300048828,
|
|
"epoch": 9.132666969559292,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 5.9863603548310646e-05,
|
|
"loss": 4.4519,
|
|
"mean_token_accuracy": 0.2387003034353256,
|
|
"num_tokens": 20817020.0,
|
|
"step": 10055
|
|
},
|
|
{
|
|
"entropy": 5.230503845214844,
|
|
"epoch": 9.13721035892776,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 5.976037115597215e-05,
|
|
"loss": 4.4963,
|
|
"mean_token_accuracy": 0.22798358798027038,
|
|
"num_tokens": 20828109.0,
|
|
"step": 10060
|
|
},
|
|
{
|
|
"entropy": 5.2111084938049315,
|
|
"epoch": 9.141753748296228,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 5.965766984602149e-05,
|
|
"loss": 4.4739,
|
|
"mean_token_accuracy": 0.23293609768152237,
|
|
"num_tokens": 20839703.0,
|
|
"step": 10065
|
|
},
|
|
{
|
|
"entropy": 5.174225521087647,
|
|
"epoch": 9.146297137664698,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 5.9555499871863955e-05,
|
|
"loss": 4.4426,
|
|
"mean_token_accuracy": 0.22992291301488876,
|
|
"num_tokens": 20849834.0,
|
|
"step": 10070
|
|
},
|
|
{
|
|
"entropy": 5.20725736618042,
|
|
"epoch": 9.150840527033166,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 5.9453861485593794e-05,
|
|
"loss": 4.451,
|
|
"mean_token_accuracy": 0.23237294852733612,
|
|
"num_tokens": 20859693.0,
|
|
"step": 10075
|
|
},
|
|
{
|
|
"entropy": 5.211972904205322,
|
|
"epoch": 9.155383916401636,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 5.9352754937993586e-05,
|
|
"loss": 4.5164,
|
|
"mean_token_accuracy": 0.22997296005487441,
|
|
"num_tokens": 20870612.0,
|
|
"step": 10080
|
|
},
|
|
{
|
|
"entropy": 5.316764783859253,
|
|
"epoch": 9.159927305770104,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 5.925218047853371e-05,
|
|
"loss": 4.5612,
|
|
"mean_token_accuracy": 0.22943894267082215,
|
|
"num_tokens": 20881913.0,
|
|
"step": 10085
|
|
},
|
|
{
|
|
"entropy": 5.263126230239868,
|
|
"epoch": 9.164470695138574,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 5.9152138355371646e-05,
|
|
"loss": 4.5508,
|
|
"mean_token_accuracy": 0.22893294394016267,
|
|
"num_tokens": 20892295.0,
|
|
"step": 10090
|
|
},
|
|
{
|
|
"entropy": 5.246053457260132,
|
|
"epoch": 9.169014084507042,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 5.9052628815351416e-05,
|
|
"loss": 4.5264,
|
|
"mean_token_accuracy": 0.23586791157722473,
|
|
"num_tokens": 20902869.0,
|
|
"step": 10095
|
|
},
|
|
{
|
|
"entropy": 5.190705442428589,
|
|
"epoch": 9.173557473875512,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 5.8953652104002825e-05,
|
|
"loss": 4.4669,
|
|
"mean_token_accuracy": 0.23296012133359909,
|
|
"num_tokens": 20913005.0,
|
|
"step": 10100
|
|
},
|
|
{
|
|
"entropy": 5.2176789283752445,
|
|
"epoch": 9.17810086324398,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 5.885520846554119e-05,
|
|
"loss": 4.4898,
|
|
"mean_token_accuracy": 0.2344430536031723,
|
|
"num_tokens": 20923070.0,
|
|
"step": 10105
|
|
},
|
|
{
|
|
"entropy": 5.27490930557251,
|
|
"epoch": 9.182644252612448,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 5.875729814286634e-05,
|
|
"loss": 4.5921,
|
|
"mean_token_accuracy": 0.223652882874012,
|
|
"num_tokens": 20933234.0,
|
|
"step": 10110
|
|
},
|
|
{
|
|
"entropy": 5.265173292160034,
|
|
"epoch": 9.187187641980918,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 5.865992137756225e-05,
|
|
"loss": 4.582,
|
|
"mean_token_accuracy": 0.22351630926132202,
|
|
"num_tokens": 20944887.0,
|
|
"step": 10115
|
|
},
|
|
{
|
|
"entropy": 5.2654523849487305,
|
|
"epoch": 9.191731031349386,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 5.856307840989642e-05,
|
|
"loss": 4.5798,
|
|
"mean_token_accuracy": 0.22206340432167054,
|
|
"num_tokens": 20956483.0,
|
|
"step": 10120
|
|
},
|
|
{
|
|
"entropy": 5.313501787185669,
|
|
"epoch": 9.196274420717856,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 5.846676947881927e-05,
|
|
"loss": 4.595,
|
|
"mean_token_accuracy": 0.22244976758956908,
|
|
"num_tokens": 20966060.0,
|
|
"step": 10125
|
|
},
|
|
{
|
|
"entropy": 5.238079786300659,
|
|
"epoch": 9.200817810086324,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 5.8370994821963514e-05,
|
|
"loss": 4.5352,
|
|
"mean_token_accuracy": 0.22596606463193894,
|
|
"num_tokens": 20977759.0,
|
|
"step": 10130
|
|
},
|
|
{
|
|
"entropy": 5.278149795532227,
|
|
"epoch": 9.205361199454794,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 5.8275754675643565e-05,
|
|
"loss": 4.5377,
|
|
"mean_token_accuracy": 0.2417357534170151,
|
|
"num_tokens": 20987557.0,
|
|
"step": 10135
|
|
},
|
|
{
|
|
"entropy": 5.256988525390625,
|
|
"epoch": 9.209904588823262,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 5.8181049274855013e-05,
|
|
"loss": 4.5472,
|
|
"mean_token_accuracy": 0.2312825307250023,
|
|
"num_tokens": 20998476.0,
|
|
"step": 10140
|
|
},
|
|
{
|
|
"entropy": 5.2209563732147215,
|
|
"epoch": 9.214447978191732,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 5.80868788532741e-05,
|
|
"loss": 4.512,
|
|
"mean_token_accuracy": 0.2350417658686638,
|
|
"num_tokens": 21008110.0,
|
|
"step": 10145
|
|
},
|
|
{
|
|
"entropy": 5.255310487747193,
|
|
"epoch": 9.2189913675602,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 5.7993243643256854e-05,
|
|
"loss": 4.5258,
|
|
"mean_token_accuracy": 0.2306294023990631,
|
|
"num_tokens": 21018680.0,
|
|
"step": 10150
|
|
},
|
|
{
|
|
"entropy": 5.177554035186768,
|
|
"epoch": 9.223534756928668,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 5.790014387583895e-05,
|
|
"loss": 4.4369,
|
|
"mean_token_accuracy": 0.23493572920560837,
|
|
"num_tokens": 21028669.0,
|
|
"step": 10155
|
|
},
|
|
{
|
|
"entropy": 5.273680210113525,
|
|
"epoch": 9.228078146297138,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 5.780757978073474e-05,
|
|
"loss": 4.5303,
|
|
"mean_token_accuracy": 0.2258996844291687,
|
|
"num_tokens": 21038699.0,
|
|
"step": 10160
|
|
},
|
|
{
|
|
"entropy": 5.263378429412842,
|
|
"epoch": 9.232621535665606,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 5.771555158633699e-05,
|
|
"loss": 4.5836,
|
|
"mean_token_accuracy": 0.2252327173948288,
|
|
"num_tokens": 21048129.0,
|
|
"step": 10165
|
|
},
|
|
{
|
|
"entropy": 5.226581239700318,
|
|
"epoch": 9.237164925034076,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 5.762405951971607e-05,
|
|
"loss": 4.4509,
|
|
"mean_token_accuracy": 0.235052190721035,
|
|
"num_tokens": 21058643.0,
|
|
"step": 10170
|
|
},
|
|
{
|
|
"entropy": 5.192672395706177,
|
|
"epoch": 9.241708314402544,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 5.75331038066196e-05,
|
|
"loss": 4.3815,
|
|
"mean_token_accuracy": 0.2378944128751755,
|
|
"num_tokens": 21068626.0,
|
|
"step": 10175
|
|
},
|
|
{
|
|
"entropy": 5.214349699020386,
|
|
"epoch": 9.246251703771014,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 5.744268467147174e-05,
|
|
"loss": 4.5061,
|
|
"mean_token_accuracy": 0.23119211792945862,
|
|
"num_tokens": 21079737.0,
|
|
"step": 10180
|
|
},
|
|
{
|
|
"entropy": 5.242608880996704,
|
|
"epoch": 9.250795093139482,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 5.7352802337372724e-05,
|
|
"loss": 4.515,
|
|
"mean_token_accuracy": 0.22854937314987184,
|
|
"num_tokens": 21090812.0,
|
|
"step": 10185
|
|
},
|
|
{
|
|
"entropy": 5.305475187301636,
|
|
"epoch": 9.25533848250795,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 5.726345702609824e-05,
|
|
"loss": 4.498,
|
|
"mean_token_accuracy": 0.23573122620582582,
|
|
"num_tokens": 21100565.0,
|
|
"step": 10190
|
|
},
|
|
{
|
|
"entropy": 5.230843830108642,
|
|
"epoch": 9.25988187187642,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 5.7174648958099e-05,
|
|
"loss": 4.5425,
|
|
"mean_token_accuracy": 0.23875022381544114,
|
|
"num_tokens": 21110065.0,
|
|
"step": 10195
|
|
},
|
|
{
|
|
"entropy": 5.253233766555786,
|
|
"epoch": 9.264425261244888,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 5.7086378352500096e-05,
|
|
"loss": 4.4814,
|
|
"mean_token_accuracy": 0.23273683190345765,
|
|
"num_tokens": 21119558.0,
|
|
"step": 10200
|
|
},
|
|
{
|
|
"entropy": 5.19466724395752,
|
|
"epoch": 9.268968650613358,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 5.6998645427100456e-05,
|
|
"loss": 4.4899,
|
|
"mean_token_accuracy": 0.23611655086278915,
|
|
"num_tokens": 21129337.0,
|
|
"step": 10205
|
|
},
|
|
{
|
|
"entropy": 5.20298662185669,
|
|
"epoch": 9.273512039981826,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 5.691145039837231e-05,
|
|
"loss": 4.5028,
|
|
"mean_token_accuracy": 0.2367205873131752,
|
|
"num_tokens": 21140273.0,
|
|
"step": 10210
|
|
},
|
|
{
|
|
"entropy": 5.259261989593506,
|
|
"epoch": 9.278055429350296,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 5.682479348146081e-05,
|
|
"loss": 4.5425,
|
|
"mean_token_accuracy": 0.22973474711179734,
|
|
"num_tokens": 21150663.0,
|
|
"step": 10215
|
|
},
|
|
{
|
|
"entropy": 5.224862813949585,
|
|
"epoch": 9.282598818718764,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 5.673867489018322e-05,
|
|
"loss": 4.4767,
|
|
"mean_token_accuracy": 0.23633719235658646,
|
|
"num_tokens": 21161295.0,
|
|
"step": 10220
|
|
},
|
|
{
|
|
"entropy": 5.206584405899048,
|
|
"epoch": 9.287142208087234,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 5.6653094837028626e-05,
|
|
"loss": 4.4443,
|
|
"mean_token_accuracy": 0.23356961458921432,
|
|
"num_tokens": 21171225.0,
|
|
"step": 10225
|
|
},
|
|
{
|
|
"entropy": 5.189030265808105,
|
|
"epoch": 9.291685597455702,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 5.6568053533157275e-05,
|
|
"loss": 4.4761,
|
|
"mean_token_accuracy": 0.2303988128900528,
|
|
"num_tokens": 21181362.0,
|
|
"step": 10230
|
|
},
|
|
{
|
|
"entropy": 5.256940412521362,
|
|
"epoch": 9.29622898682417,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 5.648355118840018e-05,
|
|
"loss": 4.5357,
|
|
"mean_token_accuracy": 0.22952287942171096,
|
|
"num_tokens": 21191014.0,
|
|
"step": 10235
|
|
},
|
|
{
|
|
"entropy": 5.240517902374267,
|
|
"epoch": 9.30077237619264,
|
|
"grad_norm": 2.78125,
|
|
"learning_rate": 5.639958801125842e-05,
|
|
"loss": 4.5154,
|
|
"mean_token_accuracy": 0.2309959650039673,
|
|
"num_tokens": 21201286.0,
|
|
"step": 10240
|
|
},
|
|
{
|
|
"entropy": 5.234212350845337,
|
|
"epoch": 9.305315765561108,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 5.6316164208902844e-05,
|
|
"loss": 4.5398,
|
|
"mean_token_accuracy": 0.23771369606256484,
|
|
"num_tokens": 21211600.0,
|
|
"step": 10245
|
|
},
|
|
{
|
|
"entropy": 5.242322969436645,
|
|
"epoch": 9.309859154929578,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 5.623327998717334e-05,
|
|
"loss": 4.53,
|
|
"mean_token_accuracy": 0.2274201512336731,
|
|
"num_tokens": 21221983.0,
|
|
"step": 10250
|
|
},
|
|
{
|
|
"entropy": 5.232030153274536,
|
|
"epoch": 9.314402544298046,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 5.615093555057853e-05,
|
|
"loss": 4.5077,
|
|
"mean_token_accuracy": 0.2361540123820305,
|
|
"num_tokens": 21232424.0,
|
|
"step": 10255
|
|
},
|
|
{
|
|
"entropy": 5.227560663223267,
|
|
"epoch": 9.318945933666516,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 5.606913110229511e-05,
|
|
"loss": 4.5018,
|
|
"mean_token_accuracy": 0.23080524057149887,
|
|
"num_tokens": 21242737.0,
|
|
"step": 10260
|
|
},
|
|
{
|
|
"entropy": 5.195528221130371,
|
|
"epoch": 9.323489323034984,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 5.598786684416738e-05,
|
|
"loss": 4.46,
|
|
"mean_token_accuracy": 0.232476706802845,
|
|
"num_tokens": 21253452.0,
|
|
"step": 10265
|
|
},
|
|
{
|
|
"entropy": 5.197288370132446,
|
|
"epoch": 9.328032712403452,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 5.59071429767069e-05,
|
|
"loss": 4.5298,
|
|
"mean_token_accuracy": 0.2384089484810829,
|
|
"num_tokens": 21263659.0,
|
|
"step": 10270
|
|
},
|
|
{
|
|
"entropy": 5.197641515731812,
|
|
"epoch": 9.332576101771922,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 5.5826959699091725e-05,
|
|
"loss": 4.4831,
|
|
"mean_token_accuracy": 0.2339094191789627,
|
|
"num_tokens": 21273447.0,
|
|
"step": 10275
|
|
},
|
|
{
|
|
"entropy": 5.184268617630005,
|
|
"epoch": 9.33711949114039,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 5.574731720916617e-05,
|
|
"loss": 4.5205,
|
|
"mean_token_accuracy": 0.23103657960891724,
|
|
"num_tokens": 21284398.0,
|
|
"step": 10280
|
|
},
|
|
{
|
|
"entropy": 5.2529802322387695,
|
|
"epoch": 9.34166288050886,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 5.56682157034401e-05,
|
|
"loss": 4.4821,
|
|
"mean_token_accuracy": 0.2389346107840538,
|
|
"num_tokens": 21294306.0,
|
|
"step": 10285
|
|
},
|
|
{
|
|
"entropy": 5.210506629943848,
|
|
"epoch": 9.346206269877328,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 5.558965537708867e-05,
|
|
"loss": 4.5247,
|
|
"mean_token_accuracy": 0.23553949743509292,
|
|
"num_tokens": 21304707.0,
|
|
"step": 10290
|
|
},
|
|
{
|
|
"entropy": 5.2608434677124025,
|
|
"epoch": 9.350749659245798,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 5.551163642395165e-05,
|
|
"loss": 4.5416,
|
|
"mean_token_accuracy": 0.23285799771547316,
|
|
"num_tokens": 21314228.0,
|
|
"step": 10295
|
|
},
|
|
{
|
|
"entropy": 5.207255125045776,
|
|
"epoch": 9.355293048614266,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 5.543415903653307e-05,
|
|
"loss": 4.4867,
|
|
"mean_token_accuracy": 0.23012380301952362,
|
|
"num_tokens": 21324648.0,
|
|
"step": 10300
|
|
},
|
|
{
|
|
"entropy": 5.24846568107605,
|
|
"epoch": 9.359836437982736,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 5.535722340600065e-05,
|
|
"loss": 4.4173,
|
|
"mean_token_accuracy": 0.23681580126285554,
|
|
"num_tokens": 21335182.0,
|
|
"step": 10305
|
|
},
|
|
{
|
|
"entropy": 5.217264127731323,
|
|
"epoch": 9.364379827351204,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 5.528082972218548e-05,
|
|
"loss": 4.4965,
|
|
"mean_token_accuracy": 0.22824637740850448,
|
|
"num_tokens": 21344882.0,
|
|
"step": 10310
|
|
},
|
|
{
|
|
"entropy": 5.207862377166748,
|
|
"epoch": 9.368923216719672,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 5.520497817358129e-05,
|
|
"loss": 4.4913,
|
|
"mean_token_accuracy": 0.235914845764637,
|
|
"num_tokens": 21355623.0,
|
|
"step": 10315
|
|
},
|
|
{
|
|
"entropy": 5.2255536079406735,
|
|
"epoch": 9.373466606088142,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 5.5129668947344275e-05,
|
|
"loss": 4.5383,
|
|
"mean_token_accuracy": 0.22421696335077285,
|
|
"num_tokens": 21365905.0,
|
|
"step": 10320
|
|
},
|
|
{
|
|
"entropy": 5.136585903167725,
|
|
"epoch": 9.37800999545661,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 5.505490222929246e-05,
|
|
"loss": 4.431,
|
|
"mean_token_accuracy": 0.23781015127897262,
|
|
"num_tokens": 21375677.0,
|
|
"step": 10325
|
|
},
|
|
{
|
|
"entropy": 5.2406542778015135,
|
|
"epoch": 9.38255338482508,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 5.498067820390537e-05,
|
|
"loss": 4.4904,
|
|
"mean_token_accuracy": 0.23194583952426912,
|
|
"num_tokens": 21385342.0,
|
|
"step": 10330
|
|
},
|
|
{
|
|
"entropy": 5.332115364074707,
|
|
"epoch": 9.387096774193548,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 5.4906997054323245e-05,
|
|
"loss": 4.6108,
|
|
"mean_token_accuracy": 0.22571997195482255,
|
|
"num_tokens": 21396288.0,
|
|
"step": 10335
|
|
},
|
|
{
|
|
"entropy": 5.222583818435669,
|
|
"epoch": 9.391640163562018,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 5.483385896234714e-05,
|
|
"loss": 4.4554,
|
|
"mean_token_accuracy": 0.24027026295661927,
|
|
"num_tokens": 21406199.0,
|
|
"step": 10340
|
|
},
|
|
{
|
|
"entropy": 5.240982627868652,
|
|
"epoch": 9.396183552930486,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 5.4761264108437966e-05,
|
|
"loss": 4.4536,
|
|
"mean_token_accuracy": 0.23237175047397612,
|
|
"num_tokens": 21415903.0,
|
|
"step": 10345
|
|
},
|
|
{
|
|
"entropy": 5.259026622772216,
|
|
"epoch": 9.400726942298956,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 5.4689212671716335e-05,
|
|
"loss": 4.5458,
|
|
"mean_token_accuracy": 0.2237927198410034,
|
|
"num_tokens": 21427339.0,
|
|
"step": 10350
|
|
},
|
|
{
|
|
"entropy": 5.236463308334351,
|
|
"epoch": 9.405270331667424,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 5.461770482996194e-05,
|
|
"loss": 4.4956,
|
|
"mean_token_accuracy": 0.22952023297548294,
|
|
"num_tokens": 21437309.0,
|
|
"step": 10355
|
|
},
|
|
{
|
|
"entropy": 5.2717639923095705,
|
|
"epoch": 9.409813721035892,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 5.4546740759613354e-05,
|
|
"loss": 4.5073,
|
|
"mean_token_accuracy": 0.2402883753180504,
|
|
"num_tokens": 21447462.0,
|
|
"step": 10360
|
|
},
|
|
{
|
|
"entropy": 5.204332637786865,
|
|
"epoch": 9.414357110404362,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 5.447632063576734e-05,
|
|
"loss": 4.4269,
|
|
"mean_token_accuracy": 0.23582995682954788,
|
|
"num_tokens": 21457262.0,
|
|
"step": 10365
|
|
},
|
|
{
|
|
"entropy": 5.190329122543335,
|
|
"epoch": 9.41890049977283,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 5.4406444632178515e-05,
|
|
"loss": 4.4763,
|
|
"mean_token_accuracy": 0.23791206777095794,
|
|
"num_tokens": 21468032.0,
|
|
"step": 10370
|
|
},
|
|
{
|
|
"entropy": 5.176095342636108,
|
|
"epoch": 9.4234438891413,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 5.4337112921259005e-05,
|
|
"loss": 4.5328,
|
|
"mean_token_accuracy": 0.23077142089605332,
|
|
"num_tokens": 21478260.0,
|
|
"step": 10375
|
|
},
|
|
{
|
|
"entropy": 5.2602301120758055,
|
|
"epoch": 9.427987278509768,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 5.426832567407794e-05,
|
|
"loss": 4.5693,
|
|
"mean_token_accuracy": 0.21910831481218337,
|
|
"num_tokens": 21489879.0,
|
|
"step": 10380
|
|
},
|
|
{
|
|
"entropy": 5.2827925205230715,
|
|
"epoch": 9.432530667878238,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 5.420008306036098e-05,
|
|
"loss": 4.6214,
|
|
"mean_token_accuracy": 0.22333039790391923,
|
|
"num_tokens": 21500731.0,
|
|
"step": 10385
|
|
},
|
|
{
|
|
"entropy": 5.2279129981994625,
|
|
"epoch": 9.437074057246706,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 5.413238524848998e-05,
|
|
"loss": 4.5136,
|
|
"mean_token_accuracy": 0.2238654911518097,
|
|
"num_tokens": 21510858.0,
|
|
"step": 10390
|
|
},
|
|
{
|
|
"entropy": 5.267981147766113,
|
|
"epoch": 9.441617446615174,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 5.4065232405502576e-05,
|
|
"loss": 4.5735,
|
|
"mean_token_accuracy": 0.22041811645030976,
|
|
"num_tokens": 21521103.0,
|
|
"step": 10395
|
|
},
|
|
{
|
|
"entropy": 5.281785678863526,
|
|
"epoch": 9.446160835983644,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 5.399862469709175e-05,
|
|
"loss": 4.5013,
|
|
"mean_token_accuracy": 0.2313188672065735,
|
|
"num_tokens": 21531520.0,
|
|
"step": 10400
|
|
},
|
|
{
|
|
"entropy": 5.23607063293457,
|
|
"epoch": 9.450704225352112,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 5.3932562287605364e-05,
|
|
"loss": 4.469,
|
|
"mean_token_accuracy": 0.23959304839372636,
|
|
"num_tokens": 21541614.0,
|
|
"step": 10405
|
|
},
|
|
{
|
|
"entropy": 5.268381547927857,
|
|
"epoch": 9.455247614720582,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 5.38670453400459e-05,
|
|
"loss": 4.4773,
|
|
"mean_token_accuracy": 0.24184639155864715,
|
|
"num_tokens": 21551377.0,
|
|
"step": 10410
|
|
},
|
|
{
|
|
"entropy": 5.203541564941406,
|
|
"epoch": 9.45979100408905,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 5.3802074016069835e-05,
|
|
"loss": 4.4906,
|
|
"mean_token_accuracy": 0.23692905604839326,
|
|
"num_tokens": 21562048.0,
|
|
"step": 10415
|
|
},
|
|
{
|
|
"entropy": 5.243898010253906,
|
|
"epoch": 9.46433439345752,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 5.373764847598756e-05,
|
|
"loss": 4.5074,
|
|
"mean_token_accuracy": 0.232526034116745,
|
|
"num_tokens": 21573394.0,
|
|
"step": 10420
|
|
},
|
|
{
|
|
"entropy": 5.220481634140015,
|
|
"epoch": 9.468877782825988,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 5.3673768878762564e-05,
|
|
"loss": 4.5358,
|
|
"mean_token_accuracy": 0.22616366297006607,
|
|
"num_tokens": 21584482.0,
|
|
"step": 10425
|
|
},
|
|
{
|
|
"entropy": 5.190046930313111,
|
|
"epoch": 9.473421172194458,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 5.361043538201152e-05,
|
|
"loss": 4.4808,
|
|
"mean_token_accuracy": 0.23104159533977509,
|
|
"num_tokens": 21595658.0,
|
|
"step": 10430
|
|
},
|
|
{
|
|
"entropy": 5.270818471908569,
|
|
"epoch": 9.477964561562926,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 5.3547648142003454e-05,
|
|
"loss": 4.5474,
|
|
"mean_token_accuracy": 0.23012982457876205,
|
|
"num_tokens": 21607249.0,
|
|
"step": 10435
|
|
},
|
|
{
|
|
"entropy": 5.212713956832886,
|
|
"epoch": 9.482507950931394,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 5.348540731365968e-05,
|
|
"loss": 4.5339,
|
|
"mean_token_accuracy": 0.22979553937911987,
|
|
"num_tokens": 21618972.0,
|
|
"step": 10440
|
|
},
|
|
{
|
|
"entropy": 5.242522382736206,
|
|
"epoch": 9.487051340299864,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 5.342371305055323e-05,
|
|
"loss": 4.5094,
|
|
"mean_token_accuracy": 0.2299122154712677,
|
|
"num_tokens": 21628485.0,
|
|
"step": 10445
|
|
},
|
|
{
|
|
"entropy": 5.271591377258301,
|
|
"epoch": 9.491594729668332,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 5.3362565504908595e-05,
|
|
"loss": 4.5288,
|
|
"mean_token_accuracy": 0.23303497582674026,
|
|
"num_tokens": 21638706.0,
|
|
"step": 10450
|
|
},
|
|
{
|
|
"entropy": 5.2222082138061525,
|
|
"epoch": 9.496138119036802,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 5.330196482760126e-05,
|
|
"loss": 4.4431,
|
|
"mean_token_accuracy": 0.23525581806898116,
|
|
"num_tokens": 21648729.0,
|
|
"step": 10455
|
|
},
|
|
{
|
|
"entropy": 5.276511335372925,
|
|
"epoch": 9.50068150840527,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 5.324191116815735e-05,
|
|
"loss": 4.5332,
|
|
"mean_token_accuracy": 0.23115993440151214,
|
|
"num_tokens": 21659442.0,
|
|
"step": 10460
|
|
},
|
|
{
|
|
"entropy": 5.226965141296387,
|
|
"epoch": 9.50522489777374,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 5.31824046747533e-05,
|
|
"loss": 4.4508,
|
|
"mean_token_accuracy": 0.23751475065946578,
|
|
"num_tokens": 21669052.0,
|
|
"step": 10465
|
|
},
|
|
{
|
|
"entropy": 5.208908367156982,
|
|
"epoch": 9.509768287142208,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 5.312344549421547e-05,
|
|
"loss": 4.5062,
|
|
"mean_token_accuracy": 0.23143183439970016,
|
|
"num_tokens": 21678988.0,
|
|
"step": 10470
|
|
},
|
|
{
|
|
"entropy": 5.254044723510742,
|
|
"epoch": 9.514311676510676,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 5.306503377201981e-05,
|
|
"loss": 4.5051,
|
|
"mean_token_accuracy": 0.2313864126801491,
|
|
"num_tokens": 21688393.0,
|
|
"step": 10475
|
|
},
|
|
{
|
|
"entropy": 5.197321224212646,
|
|
"epoch": 9.518855065879146,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 5.300716965229141e-05,
|
|
"loss": 4.4837,
|
|
"mean_token_accuracy": 0.23679476231336594,
|
|
"num_tokens": 21698070.0,
|
|
"step": 10480
|
|
},
|
|
{
|
|
"entropy": 5.184717082977295,
|
|
"epoch": 9.523398455247614,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 5.294985327780423e-05,
|
|
"loss": 4.4408,
|
|
"mean_token_accuracy": 0.24494290053844453,
|
|
"num_tokens": 21708520.0,
|
|
"step": 10485
|
|
},
|
|
{
|
|
"entropy": 5.265604257583618,
|
|
"epoch": 9.527941844616084,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 5.289308478998076e-05,
|
|
"loss": 4.596,
|
|
"mean_token_accuracy": 0.22199410945177078,
|
|
"num_tokens": 21719484.0,
|
|
"step": 10490
|
|
},
|
|
{
|
|
"entropy": 5.201817893981934,
|
|
"epoch": 9.532485233984552,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 5.2836864328891533e-05,
|
|
"loss": 4.5326,
|
|
"mean_token_accuracy": 0.22416315227746964,
|
|
"num_tokens": 21730172.0,
|
|
"step": 10495
|
|
},
|
|
{
|
|
"entropy": 5.223015546798706,
|
|
"epoch": 9.537028623353022,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 5.278119203325501e-05,
|
|
"loss": 4.5023,
|
|
"mean_token_accuracy": 0.2310138985514641,
|
|
"num_tokens": 21739428.0,
|
|
"step": 10500
|
|
},
|
|
{
|
|
"entropy": 5.248493432998657,
|
|
"epoch": 9.54157201272149,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 5.272606804043701e-05,
|
|
"loss": 4.5583,
|
|
"mean_token_accuracy": 0.22825373113155364,
|
|
"num_tokens": 21750543.0,
|
|
"step": 10505
|
|
},
|
|
{
|
|
"entropy": 5.249394369125366,
|
|
"epoch": 9.54611540208996,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 5.267149248645054e-05,
|
|
"loss": 4.4734,
|
|
"mean_token_accuracy": 0.23470331281423568,
|
|
"num_tokens": 21760925.0,
|
|
"step": 10510
|
|
},
|
|
{
|
|
"entropy": 5.290477848052978,
|
|
"epoch": 9.550658791458428,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 5.2617465505955324e-05,
|
|
"loss": 4.5107,
|
|
"mean_token_accuracy": 0.23140929341316224,
|
|
"num_tokens": 21770631.0,
|
|
"step": 10515
|
|
},
|
|
{
|
|
"entropy": 5.252996778488159,
|
|
"epoch": 9.555202180826896,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 5.256398723225758e-05,
|
|
"loss": 4.5256,
|
|
"mean_token_accuracy": 0.2284479632973671,
|
|
"num_tokens": 21781189.0,
|
|
"step": 10520
|
|
},
|
|
{
|
|
"entropy": 5.205735158920288,
|
|
"epoch": 9.559745570195366,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 5.251105779730963e-05,
|
|
"loss": 4.4521,
|
|
"mean_token_accuracy": 0.23986880332231522,
|
|
"num_tokens": 21791487.0,
|
|
"step": 10525
|
|
},
|
|
{
|
|
"entropy": 5.281984043121338,
|
|
"epoch": 9.564288959563834,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 5.2458677331709585e-05,
|
|
"loss": 4.61,
|
|
"mean_token_accuracy": 0.2193015068769455,
|
|
"num_tokens": 21801184.0,
|
|
"step": 10530
|
|
},
|
|
{
|
|
"entropy": 5.1958965301513675,
|
|
"epoch": 9.568832348932304,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 5.240684596470104e-05,
|
|
"loss": 4.5048,
|
|
"mean_token_accuracy": 0.22872274369001389,
|
|
"num_tokens": 21811074.0,
|
|
"step": 10535
|
|
},
|
|
{
|
|
"entropy": 5.23944878578186,
|
|
"epoch": 9.573375738300772,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 5.2355563824172744e-05,
|
|
"loss": 4.4857,
|
|
"mean_token_accuracy": 0.23652201443910598,
|
|
"num_tokens": 21820642.0,
|
|
"step": 10540
|
|
},
|
|
{
|
|
"entropy": 5.283715629577637,
|
|
"epoch": 9.577919127669242,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 5.23048310366583e-05,
|
|
"loss": 4.5272,
|
|
"mean_token_accuracy": 0.23295110762119292,
|
|
"num_tokens": 21830310.0,
|
|
"step": 10545
|
|
},
|
|
{
|
|
"entropy": 5.262804698944092,
|
|
"epoch": 9.58246251703771,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 5.2254647727335795e-05,
|
|
"loss": 4.558,
|
|
"mean_token_accuracy": 0.2224996954202652,
|
|
"num_tokens": 21840563.0,
|
|
"step": 10550
|
|
},
|
|
{
|
|
"entropy": 5.237605476379395,
|
|
"epoch": 9.58700590640618,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 5.220501402002755e-05,
|
|
"loss": 4.5335,
|
|
"mean_token_accuracy": 0.23342836350202562,
|
|
"num_tokens": 21852907.0,
|
|
"step": 10555
|
|
},
|
|
{
|
|
"entropy": 5.286276006698609,
|
|
"epoch": 9.591549295774648,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 5.215593003719981e-05,
|
|
"loss": 4.55,
|
|
"mean_token_accuracy": 0.2293238252401352,
|
|
"num_tokens": 21864463.0,
|
|
"step": 10560
|
|
},
|
|
{
|
|
"entropy": 5.2174841403961185,
|
|
"epoch": 9.596092685143116,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 5.210739589996245e-05,
|
|
"loss": 4.5058,
|
|
"mean_token_accuracy": 0.22288836240768434,
|
|
"num_tokens": 21875529.0,
|
|
"step": 10565
|
|
},
|
|
{
|
|
"entropy": 5.256234741210937,
|
|
"epoch": 9.600636074511586,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 5.2059411728068595e-05,
|
|
"loss": 4.524,
|
|
"mean_token_accuracy": 0.23083068877458573,
|
|
"num_tokens": 21885051.0,
|
|
"step": 10570
|
|
},
|
|
{
|
|
"entropy": 5.252417325973511,
|
|
"epoch": 9.605179463880054,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 5.201197763991444e-05,
|
|
"loss": 4.512,
|
|
"mean_token_accuracy": 0.2306112065911293,
|
|
"num_tokens": 21894979.0,
|
|
"step": 10575
|
|
},
|
|
{
|
|
"entropy": 5.2204491138458256,
|
|
"epoch": 9.609722853248524,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 5.196509375253887e-05,
|
|
"loss": 4.4803,
|
|
"mean_token_accuracy": 0.23341310024261475,
|
|
"num_tokens": 21905488.0,
|
|
"step": 10580
|
|
},
|
|
{
|
|
"entropy": 5.267101287841797,
|
|
"epoch": 9.614266242616992,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 5.19187601816232e-05,
|
|
"loss": 4.495,
|
|
"mean_token_accuracy": 0.23668002635240554,
|
|
"num_tokens": 21915534.0,
|
|
"step": 10585
|
|
},
|
|
{
|
|
"entropy": 5.194937229156494,
|
|
"epoch": 9.618809631985462,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 5.187297704149094e-05,
|
|
"loss": 4.4869,
|
|
"mean_token_accuracy": 0.2311507821083069,
|
|
"num_tokens": 21925517.0,
|
|
"step": 10590
|
|
},
|
|
{
|
|
"entropy": 5.193051671981811,
|
|
"epoch": 9.62335302135393,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 5.182774444510744e-05,
|
|
"loss": 4.4135,
|
|
"mean_token_accuracy": 0.24126302003860473,
|
|
"num_tokens": 21934427.0,
|
|
"step": 10595
|
|
},
|
|
{
|
|
"entropy": 5.237682342529297,
|
|
"epoch": 9.627896410722398,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 5.178306250407963e-05,
|
|
"loss": 4.5493,
|
|
"mean_token_accuracy": 0.2296896457672119,
|
|
"num_tokens": 21945717.0,
|
|
"step": 10600
|
|
},
|
|
{
|
|
"entropy": 5.231707668304443,
|
|
"epoch": 9.632439800090868,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 5.1738931328655714e-05,
|
|
"loss": 4.4596,
|
|
"mean_token_accuracy": 0.23067666590213776,
|
|
"num_tokens": 21956652.0,
|
|
"step": 10605
|
|
},
|
|
{
|
|
"entropy": 5.290403938293457,
|
|
"epoch": 9.636983189459336,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 5.1695351027725054e-05,
|
|
"loss": 4.6831,
|
|
"mean_token_accuracy": 0.21686378717422486,
|
|
"num_tokens": 21967381.0,
|
|
"step": 10610
|
|
},
|
|
{
|
|
"entropy": 5.185414743423462,
|
|
"epoch": 9.641526578827806,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 5.1652321708817646e-05,
|
|
"loss": 4.4398,
|
|
"mean_token_accuracy": 0.24275955706834793,
|
|
"num_tokens": 21977552.0,
|
|
"step": 10615
|
|
},
|
|
{
|
|
"entropy": 5.235084438323975,
|
|
"epoch": 9.646069968196274,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 5.160984347810409e-05,
|
|
"loss": 4.4749,
|
|
"mean_token_accuracy": 0.23289595544338226,
|
|
"num_tokens": 21987915.0,
|
|
"step": 10620
|
|
},
|
|
{
|
|
"entropy": 5.199057626724243,
|
|
"epoch": 9.650613357564744,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 5.15679164403952e-05,
|
|
"loss": 4.4616,
|
|
"mean_token_accuracy": 0.23805072754621506,
|
|
"num_tokens": 21997475.0,
|
|
"step": 10625
|
|
},
|
|
{
|
|
"entropy": 5.282834005355835,
|
|
"epoch": 9.655156746933212,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 5.152654069914177e-05,
|
|
"loss": 4.5129,
|
|
"mean_token_accuracy": 0.22769084870815276,
|
|
"num_tokens": 22008316.0,
|
|
"step": 10630
|
|
},
|
|
{
|
|
"entropy": 5.257405471801758,
|
|
"epoch": 9.65970013630168,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 5.1485716356434315e-05,
|
|
"loss": 4.5712,
|
|
"mean_token_accuracy": 0.22037355452775956,
|
|
"num_tokens": 22019885.0,
|
|
"step": 10635
|
|
},
|
|
{
|
|
"entropy": 5.202559089660644,
|
|
"epoch": 9.66424352567015,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 5.144544351300285e-05,
|
|
"loss": 4.4774,
|
|
"mean_token_accuracy": 0.22850582450628282,
|
|
"num_tokens": 22029791.0,
|
|
"step": 10640
|
|
},
|
|
{
|
|
"entropy": 5.20889630317688,
|
|
"epoch": 9.668786915038618,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 5.14057222682166e-05,
|
|
"loss": 4.5626,
|
|
"mean_token_accuracy": 0.22196783721446992,
|
|
"num_tokens": 22040772.0,
|
|
"step": 10645
|
|
},
|
|
{
|
|
"entropy": 5.245989179611206,
|
|
"epoch": 9.673330304407088,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 5.136655272008381e-05,
|
|
"loss": 4.5666,
|
|
"mean_token_accuracy": 0.2282787650823593,
|
|
"num_tokens": 22052696.0,
|
|
"step": 10650
|
|
},
|
|
{
|
|
"entropy": 5.280193662643432,
|
|
"epoch": 9.677873693775556,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 5.1327934965251445e-05,
|
|
"loss": 4.5032,
|
|
"mean_token_accuracy": 0.2263406291604042,
|
|
"num_tokens": 22063142.0,
|
|
"step": 10655
|
|
},
|
|
{
|
|
"entropy": 5.16491961479187,
|
|
"epoch": 9.682417083144026,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 5.128986909900499e-05,
|
|
"loss": 4.4969,
|
|
"mean_token_accuracy": 0.22918330281972885,
|
|
"num_tokens": 22073869.0,
|
|
"step": 10660
|
|
},
|
|
{
|
|
"entropy": 5.206924867630005,
|
|
"epoch": 9.686960472512494,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 5.125235521526814e-05,
|
|
"loss": 4.4705,
|
|
"mean_token_accuracy": 0.22959572672843934,
|
|
"num_tokens": 22084908.0,
|
|
"step": 10665
|
|
},
|
|
{
|
|
"entropy": 5.217195749282837,
|
|
"epoch": 9.691503861880964,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 5.121539340660269e-05,
|
|
"loss": 4.4772,
|
|
"mean_token_accuracy": 0.2333854168653488,
|
|
"num_tokens": 22094290.0,
|
|
"step": 10670
|
|
},
|
|
{
|
|
"entropy": 5.185244226455689,
|
|
"epoch": 9.696047251249432,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 5.117898376420827e-05,
|
|
"loss": 4.4704,
|
|
"mean_token_accuracy": 0.23057629019021988,
|
|
"num_tokens": 22104396.0,
|
|
"step": 10675
|
|
},
|
|
{
|
|
"entropy": 5.239530611038208,
|
|
"epoch": 9.7005906406179,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 5.1143126377922e-05,
|
|
"loss": 4.4793,
|
|
"mean_token_accuracy": 0.2289775162935257,
|
|
"num_tokens": 22114960.0,
|
|
"step": 10680
|
|
},
|
|
{
|
|
"entropy": 5.2025604248046875,
|
|
"epoch": 9.70513402998637,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 5.110782133621843e-05,
|
|
"loss": 4.5437,
|
|
"mean_token_accuracy": 0.22825152426958084,
|
|
"num_tokens": 22126174.0,
|
|
"step": 10685
|
|
},
|
|
{
|
|
"entropy": 5.205691194534301,
|
|
"epoch": 9.709677419354838,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 5.107306872620926e-05,
|
|
"loss": 4.5303,
|
|
"mean_token_accuracy": 0.23077984154224396,
|
|
"num_tokens": 22136096.0,
|
|
"step": 10690
|
|
},
|
|
{
|
|
"entropy": 5.274991798400879,
|
|
"epoch": 9.714220808723308,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 5.10388686336431e-05,
|
|
"loss": 4.5163,
|
|
"mean_token_accuracy": 0.24132453948259353,
|
|
"num_tokens": 22146167.0,
|
|
"step": 10695
|
|
},
|
|
{
|
|
"entropy": 5.269649934768677,
|
|
"epoch": 9.718764198091776,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 5.1005221142905254e-05,
|
|
"loss": 4.5175,
|
|
"mean_token_accuracy": 0.23383591026067735,
|
|
"num_tokens": 22156978.0,
|
|
"step": 10700
|
|
},
|
|
{
|
|
"entropy": 5.194292402267456,
|
|
"epoch": 9.723307587460246,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 5.0972126337017575e-05,
|
|
"loss": 4.4279,
|
|
"mean_token_accuracy": 0.234496633708477,
|
|
"num_tokens": 22166959.0,
|
|
"step": 10705
|
|
},
|
|
{
|
|
"entropy": 5.213622999191284,
|
|
"epoch": 9.727850976828714,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 5.093958429763821e-05,
|
|
"loss": 4.5072,
|
|
"mean_token_accuracy": 0.2367963284254074,
|
|
"num_tokens": 22176575.0,
|
|
"step": 10710
|
|
},
|
|
{
|
|
"entropy": 5.267104244232177,
|
|
"epoch": 9.732394366197184,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 5.090759510506138e-05,
|
|
"loss": 4.5522,
|
|
"mean_token_accuracy": 0.2286095604300499,
|
|
"num_tokens": 22187283.0,
|
|
"step": 10715
|
|
},
|
|
{
|
|
"entropy": 5.166283464431762,
|
|
"epoch": 9.736937755565652,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 5.087615883821728e-05,
|
|
"loss": 4.4226,
|
|
"mean_token_accuracy": 0.2435694232583046,
|
|
"num_tokens": 22197045.0,
|
|
"step": 10720
|
|
},
|
|
{
|
|
"entropy": 5.257946634292603,
|
|
"epoch": 9.74148114493412,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 5.084527557467175e-05,
|
|
"loss": 4.4753,
|
|
"mean_token_accuracy": 0.23874990195035933,
|
|
"num_tokens": 22207200.0,
|
|
"step": 10725
|
|
},
|
|
{
|
|
"entropy": 5.203625106811524,
|
|
"epoch": 9.74602453430259,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 5.0814945390626174e-05,
|
|
"loss": 4.461,
|
|
"mean_token_accuracy": 0.23088328391313553,
|
|
"num_tokens": 22216880.0,
|
|
"step": 10730
|
|
},
|
|
{
|
|
"entropy": 5.15642237663269,
|
|
"epoch": 9.750567923671058,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 5.0785168360917285e-05,
|
|
"loss": 4.3682,
|
|
"mean_token_accuracy": 0.23982539772987366,
|
|
"num_tokens": 22227189.0,
|
|
"step": 10735
|
|
},
|
|
{
|
|
"entropy": 5.239428377151489,
|
|
"epoch": 9.755111313039528,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 5.075594455901691e-05,
|
|
"loss": 4.5355,
|
|
"mean_token_accuracy": 0.22547104209661484,
|
|
"num_tokens": 22237839.0,
|
|
"step": 10740
|
|
},
|
|
{
|
|
"entropy": 5.2285120487213135,
|
|
"epoch": 9.759654702407996,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 5.072727405703189e-05,
|
|
"loss": 4.556,
|
|
"mean_token_accuracy": 0.22495072036981584,
|
|
"num_tokens": 22248337.0,
|
|
"step": 10745
|
|
},
|
|
{
|
|
"entropy": 5.248315143585205,
|
|
"epoch": 9.764198091776466,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 5.0699156925703846e-05,
|
|
"loss": 4.4713,
|
|
"mean_token_accuracy": 0.22734574228525162,
|
|
"num_tokens": 22258421.0,
|
|
"step": 10750
|
|
},
|
|
{
|
|
"entropy": 5.221819353103638,
|
|
"epoch": 9.768741481144934,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 5.0671593234409e-05,
|
|
"loss": 4.5399,
|
|
"mean_token_accuracy": 0.22833095788955687,
|
|
"num_tokens": 22269366.0,
|
|
"step": 10755
|
|
},
|
|
{
|
|
"entropy": 5.20825047492981,
|
|
"epoch": 9.773284870513404,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 5.0644583051158005e-05,
|
|
"loss": 4.551,
|
|
"mean_token_accuracy": 0.23122321218252181,
|
|
"num_tokens": 22280016.0,
|
|
"step": 10760
|
|
},
|
|
{
|
|
"entropy": 5.213593196868897,
|
|
"epoch": 9.777828259881872,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 5.061812644259582e-05,
|
|
"loss": 4.5788,
|
|
"mean_token_accuracy": 0.225633205473423,
|
|
"num_tokens": 22290892.0,
|
|
"step": 10765
|
|
},
|
|
{
|
|
"entropy": 5.184381675720215,
|
|
"epoch": 9.78237164925034,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 5.059222347400151e-05,
|
|
"loss": 4.4922,
|
|
"mean_token_accuracy": 0.2298300087451935,
|
|
"num_tokens": 22300969.0,
|
|
"step": 10770
|
|
},
|
|
{
|
|
"entropy": 5.158545255661011,
|
|
"epoch": 9.78691503861881,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 5.056687420928805e-05,
|
|
"loss": 4.4821,
|
|
"mean_token_accuracy": 0.22926753461360933,
|
|
"num_tokens": 22311080.0,
|
|
"step": 10775
|
|
},
|
|
{
|
|
"entropy": 5.239044094085694,
|
|
"epoch": 9.791458427987278,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 5.0542078711002246e-05,
|
|
"loss": 4.5283,
|
|
"mean_token_accuracy": 0.22685044258832932,
|
|
"num_tokens": 22321841.0,
|
|
"step": 10780
|
|
},
|
|
{
|
|
"entropy": 5.236127471923828,
|
|
"epoch": 9.796001817355748,
|
|
"grad_norm": 1.9765625,
|
|
"learning_rate": 5.0517837040324515e-05,
|
|
"loss": 4.5428,
|
|
"mean_token_accuracy": 0.2285653054714203,
|
|
"num_tokens": 22332656.0,
|
|
"step": 10785
|
|
},
|
|
{
|
|
"entropy": 5.219241046905518,
|
|
"epoch": 9.800545206724216,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 5.049414925706877e-05,
|
|
"loss": 4.5142,
|
|
"mean_token_accuracy": 0.22772664725780487,
|
|
"num_tokens": 22341911.0,
|
|
"step": 10790
|
|
},
|
|
{
|
|
"entropy": 5.216530990600586,
|
|
"epoch": 9.805088596092686,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 5.0471015419682273e-05,
|
|
"loss": 4.4923,
|
|
"mean_token_accuracy": 0.2353979155421257,
|
|
"num_tokens": 22351891.0,
|
|
"step": 10795
|
|
},
|
|
{
|
|
"entropy": 5.171959590911865,
|
|
"epoch": 9.809631985461154,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 5.044843558524547e-05,
|
|
"loss": 4.4244,
|
|
"mean_token_accuracy": 0.24126698523759843,
|
|
"num_tokens": 22362707.0,
|
|
"step": 10800
|
|
},
|
|
{
|
|
"entropy": 5.187639760971069,
|
|
"epoch": 9.814175374829622,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 5.042640980947183e-05,
|
|
"loss": 4.4849,
|
|
"mean_token_accuracy": 0.23345002830028533,
|
|
"num_tokens": 22373081.0,
|
|
"step": 10805
|
|
},
|
|
{
|
|
"entropy": 5.237658596038818,
|
|
"epoch": 9.818718764198092,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 5.0404938146707766e-05,
|
|
"loss": 4.4912,
|
|
"mean_token_accuracy": 0.23830211609601976,
|
|
"num_tokens": 22382818.0,
|
|
"step": 10810
|
|
},
|
|
{
|
|
"entropy": 5.196129846572876,
|
|
"epoch": 9.82326215356656,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 5.038402064993251e-05,
|
|
"loss": 4.4749,
|
|
"mean_token_accuracy": 0.23495252579450607,
|
|
"num_tokens": 22392912.0,
|
|
"step": 10815
|
|
},
|
|
{
|
|
"entropy": 5.249113607406616,
|
|
"epoch": 9.82780554293503,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 5.036365737075789e-05,
|
|
"loss": 4.5166,
|
|
"mean_token_accuracy": 0.23860115110874175,
|
|
"num_tokens": 22403180.0,
|
|
"step": 10820
|
|
},
|
|
{
|
|
"entropy": 5.255233526229858,
|
|
"epoch": 9.832348932303498,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 5.034384835942826e-05,
|
|
"loss": 4.4673,
|
|
"mean_token_accuracy": 0.23594636619091033,
|
|
"num_tokens": 22413963.0,
|
|
"step": 10825
|
|
},
|
|
{
|
|
"entropy": 5.214558458328247,
|
|
"epoch": 9.836892321671968,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 5.032459366482041e-05,
|
|
"loss": 4.47,
|
|
"mean_token_accuracy": 0.22774625867605208,
|
|
"num_tokens": 22424860.0,
|
|
"step": 10830
|
|
},
|
|
{
|
|
"entropy": 5.291085481643677,
|
|
"epoch": 9.841435711040436,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 5.0305893334443346e-05,
|
|
"loss": 4.589,
|
|
"mean_token_accuracy": 0.22496835440397261,
|
|
"num_tokens": 22434996.0,
|
|
"step": 10835
|
|
},
|
|
{
|
|
"entropy": 5.226725482940674,
|
|
"epoch": 9.845979100408904,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 5.02877474144383e-05,
|
|
"loss": 4.5338,
|
|
"mean_token_accuracy": 0.22828300893306733,
|
|
"num_tokens": 22445583.0,
|
|
"step": 10840
|
|
},
|
|
{
|
|
"entropy": 5.231715393066406,
|
|
"epoch": 9.850522489777374,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 5.0270155949578526e-05,
|
|
"loss": 4.4867,
|
|
"mean_token_accuracy": 0.23988510370254518,
|
|
"num_tokens": 22455607.0,
|
|
"step": 10845
|
|
},
|
|
{
|
|
"entropy": 5.246537828445435,
|
|
"epoch": 9.855065879145842,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 5.025311898326922e-05,
|
|
"loss": 4.5902,
|
|
"mean_token_accuracy": 0.22410898357629777,
|
|
"num_tokens": 22465788.0,
|
|
"step": 10850
|
|
},
|
|
{
|
|
"entropy": 5.2350146770477295,
|
|
"epoch": 9.859609268514312,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 5.02366365575474e-05,
|
|
"loss": 4.5104,
|
|
"mean_token_accuracy": 0.2325457140803337,
|
|
"num_tokens": 22475733.0,
|
|
"step": 10855
|
|
},
|
|
{
|
|
"entropy": 5.2058309555053714,
|
|
"epoch": 9.86415265788278,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 5.022070871308179e-05,
|
|
"loss": 4.5369,
|
|
"mean_token_accuracy": 0.23211126774549484,
|
|
"num_tokens": 22487756.0,
|
|
"step": 10860
|
|
},
|
|
{
|
|
"entropy": 5.219606542587281,
|
|
"epoch": 9.86869604725125,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 5.020533548917279e-05,
|
|
"loss": 4.5126,
|
|
"mean_token_accuracy": 0.23065461069345475,
|
|
"num_tokens": 22497480.0,
|
|
"step": 10865
|
|
},
|
|
{
|
|
"entropy": 5.277222394943237,
|
|
"epoch": 9.873239436619718,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 5.01905169237523e-05,
|
|
"loss": 4.5736,
|
|
"mean_token_accuracy": 0.2268942266702652,
|
|
"num_tokens": 22508305.0,
|
|
"step": 10870
|
|
},
|
|
{
|
|
"entropy": 5.233856725692749,
|
|
"epoch": 9.877782825988188,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 5.017625305338363e-05,
|
|
"loss": 4.5018,
|
|
"mean_token_accuracy": 0.23238373696804046,
|
|
"num_tokens": 22518351.0,
|
|
"step": 10875
|
|
},
|
|
{
|
|
"entropy": 5.250752305984497,
|
|
"epoch": 9.882326215356656,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 5.01625439132615e-05,
|
|
"loss": 4.4763,
|
|
"mean_token_accuracy": 0.2276984006166458,
|
|
"num_tokens": 22528372.0,
|
|
"step": 10880
|
|
},
|
|
{
|
|
"entropy": 5.213549709320068,
|
|
"epoch": 9.886869604725124,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 5.0149389537211824e-05,
|
|
"loss": 4.5109,
|
|
"mean_token_accuracy": 0.2281554937362671,
|
|
"num_tokens": 22539041.0,
|
|
"step": 10885
|
|
},
|
|
{
|
|
"entropy": 5.192021226882934,
|
|
"epoch": 9.891412994093594,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 5.013678995769173e-05,
|
|
"loss": 4.4667,
|
|
"mean_token_accuracy": 0.2393447533249855,
|
|
"num_tokens": 22549132.0,
|
|
"step": 10890
|
|
},
|
|
{
|
|
"entropy": 5.206980514526367,
|
|
"epoch": 9.895956383462062,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 5.012474520578942e-05,
|
|
"loss": 4.4462,
|
|
"mean_token_accuracy": 0.23524446338415145,
|
|
"num_tokens": 22559786.0,
|
|
"step": 10895
|
|
},
|
|
{
|
|
"entropy": 5.139940595626831,
|
|
"epoch": 9.900499772830532,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 5.0113255311224107e-05,
|
|
"loss": 4.4049,
|
|
"mean_token_accuracy": 0.2428631916642189,
|
|
"num_tokens": 22568654.0,
|
|
"step": 10900
|
|
},
|
|
{
|
|
"entropy": 5.234427452087402,
|
|
"epoch": 9.905043162199,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 5.0102320302345996e-05,
|
|
"loss": 4.5141,
|
|
"mean_token_accuracy": 0.2349957376718521,
|
|
"num_tokens": 22579277.0,
|
|
"step": 10905
|
|
},
|
|
{
|
|
"entropy": 5.185927963256836,
|
|
"epoch": 9.90958655156747,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 5.0091940206136123e-05,
|
|
"loss": 4.4952,
|
|
"mean_token_accuracy": 0.2294794112443924,
|
|
"num_tokens": 22589685.0,
|
|
"step": 10910
|
|
},
|
|
{
|
|
"entropy": 5.1988903999328615,
|
|
"epoch": 9.914129940935938,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 5.008211504820635e-05,
|
|
"loss": 4.4658,
|
|
"mean_token_accuracy": 0.23947690576314926,
|
|
"num_tokens": 22600196.0,
|
|
"step": 10915
|
|
},
|
|
{
|
|
"entropy": 5.167146492004394,
|
|
"epoch": 9.918673330304408,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 5.007284485279925e-05,
|
|
"loss": 4.4131,
|
|
"mean_token_accuracy": 0.24371343702077866,
|
|
"num_tokens": 22609836.0,
|
|
"step": 10920
|
|
},
|
|
{
|
|
"entropy": 5.2091302394866945,
|
|
"epoch": 9.923216719672876,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 5.006412964278816e-05,
|
|
"loss": 4.4643,
|
|
"mean_token_accuracy": 0.22690886557102202,
|
|
"num_tokens": 22620611.0,
|
|
"step": 10925
|
|
},
|
|
{
|
|
"entropy": 5.194605731964112,
|
|
"epoch": 9.927760109041344,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 5.0055969439676925e-05,
|
|
"loss": 4.4751,
|
|
"mean_token_accuracy": 0.2316679209470749,
|
|
"num_tokens": 22630588.0,
|
|
"step": 10930
|
|
},
|
|
{
|
|
"entropy": 5.301447772979737,
|
|
"epoch": 9.932303498409814,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 5.004836426360008e-05,
|
|
"loss": 4.5957,
|
|
"mean_token_accuracy": 0.22346774488687515,
|
|
"num_tokens": 22641901.0,
|
|
"step": 10935
|
|
},
|
|
{
|
|
"entropy": 5.178872108459473,
|
|
"epoch": 9.936846887778282,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 5.004131413332263e-05,
|
|
"loss": 4.4738,
|
|
"mean_token_accuracy": 0.22486219108104705,
|
|
"num_tokens": 22652115.0,
|
|
"step": 10940
|
|
},
|
|
{
|
|
"entropy": 5.203425550460816,
|
|
"epoch": 9.941390277146752,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 5.003481906624009e-05,
|
|
"loss": 4.4975,
|
|
"mean_token_accuracy": 0.23352746963500975,
|
|
"num_tokens": 22662904.0,
|
|
"step": 10945
|
|
},
|
|
{
|
|
"entropy": 5.176844310760498,
|
|
"epoch": 9.94593366651522,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 5.002887907837835e-05,
|
|
"loss": 4.4582,
|
|
"mean_token_accuracy": 0.23695881962776183,
|
|
"num_tokens": 22672901.0,
|
|
"step": 10950
|
|
},
|
|
{
|
|
"entropy": 5.186959981918335,
|
|
"epoch": 9.95047705588369,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 5.002349418439379e-05,
|
|
"loss": 4.4967,
|
|
"mean_token_accuracy": 0.2327476769685745,
|
|
"num_tokens": 22684678.0,
|
|
"step": 10955
|
|
},
|
|
{
|
|
"entropy": 5.219868421554565,
|
|
"epoch": 9.955020445252158,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 5.001866439757306e-05,
|
|
"loss": 4.5808,
|
|
"mean_token_accuracy": 0.22822954803705214,
|
|
"num_tokens": 22695046.0,
|
|
"step": 10960
|
|
},
|
|
{
|
|
"entropy": 5.182281494140625,
|
|
"epoch": 9.959563834620628,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 5.00143897298332e-05,
|
|
"loss": 4.435,
|
|
"mean_token_accuracy": 0.23827849179506302,
|
|
"num_tokens": 22705342.0,
|
|
"step": 10965
|
|
},
|
|
{
|
|
"entropy": 5.2673118114471436,
|
|
"epoch": 9.964107223989096,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 5.001067019172151e-05,
|
|
"loss": 4.584,
|
|
"mean_token_accuracy": 0.2241557240486145,
|
|
"num_tokens": 22715693.0,
|
|
"step": 10970
|
|
},
|
|
{
|
|
"entropy": 5.203149318695068,
|
|
"epoch": 9.968650613357564,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 5.00075057924156e-05,
|
|
"loss": 4.4453,
|
|
"mean_token_accuracy": 0.23642986118793488,
|
|
"num_tokens": 22726224.0,
|
|
"step": 10975
|
|
},
|
|
{
|
|
"entropy": 5.217801189422607,
|
|
"epoch": 9.973194002726034,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 5.000489653972332e-05,
|
|
"loss": 4.4453,
|
|
"mean_token_accuracy": 0.2332183063030243,
|
|
"num_tokens": 22735725.0,
|
|
"step": 10980
|
|
},
|
|
{
|
|
"entropy": 5.233771753311157,
|
|
"epoch": 9.977737392094502,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 5.0002842440082713e-05,
|
|
"loss": 4.4742,
|
|
"mean_token_accuracy": 0.24227555096149445,
|
|
"num_tokens": 22745789.0,
|
|
"step": 10985
|
|
},
|
|
{
|
|
"entropy": 5.2577873229980465,
|
|
"epoch": 9.982280781462972,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 5.000134349856208e-05,
|
|
"loss": 4.5125,
|
|
"mean_token_accuracy": 0.2330923408269882,
|
|
"num_tokens": 22755964.0,
|
|
"step": 10990
|
|
},
|
|
{
|
|
"entropy": 5.234239816665649,
|
|
"epoch": 9.98682417083144,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 5.000039971885989e-05,
|
|
"loss": 4.4778,
|
|
"mean_token_accuracy": 0.2365758389234543,
|
|
"num_tokens": 22765630.0,
|
|
"step": 10995
|
|
},
|
|
{
|
|
"entropy": 5.254246091842651,
|
|
"epoch": 9.99136756019991,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 5.0000011103304856e-05,
|
|
"loss": 4.4811,
|
|
"mean_token_accuracy": 0.23598322570323943,
|
|
"num_tokens": 22774660.0,
|
|
"step": 11000
|
|
},
|
|
{
|
|
"epoch": 9.99136756019991,
|
|
"eval_entropy": 5.166232839850492,
|
|
"eval_loss": 5.679841995239258,
|
|
"eval_mean_token_accuracy": 0.17421225607395172,
|
|
"eval_num_tokens": 22774660.0,
|
|
"eval_runtime": 2.5837,
|
|
"eval_samples_per_second": 1329.496,
|
|
"eval_steps_per_second": 166.429,
|
|
"step": 11000
|
|
}
|
|
],
|
|
"logging_steps": 5,
|
|
"max_steps": 11000,
|
|
"num_input_tokens_seen": 0,
|
|
"num_train_epochs": 10,
|
|
"save_steps": 1000,
|
|
"stateful_callbacks": {
|
|
"TrainerControl": {
|
|
"args": {
|
|
"should_epoch_stop": false,
|
|
"should_evaluate": false,
|
|
"should_log": false,
|
|
"should_save": true,
|
|
"should_training_stop": true
|
|
},
|
|
"attributes": {}
|
|
}
|
|
},
|
|
"total_flos": 3.29755009824e+16,
|
|
"train_batch_size": 16,
|
|
"trial_name": null,
|
|
"trial_params": null
|
|
}
|