0e207e3c54
Model: fpadovani/ita-latn-10mb-after-ppt-shuff-dyck-100mb-ckpt500_seed3407 Source: Original Platform
48123 lines
1.3 MiB
48123 lines
1.3 MiB
{
|
|
"best_global_step": null,
|
|
"best_metric": null,
|
|
"best_model_checkpoint": null,
|
|
"epoch": 2.3818975784041285,
|
|
"eval_steps": 3000,
|
|
"global_step": 24000,
|
|
"is_hyper_param_search": false,
|
|
"is_local_process_zero": true,
|
|
"is_world_process_zero": true,
|
|
"log_history": [
|
|
{
|
|
"entropy": 4.898969125747681,
|
|
"epoch": 0.0004962286621675268,
|
|
"grad_norm": 13.5625,
|
|
"learning_rate": 2e-06,
|
|
"loss": 14.3924,
|
|
"mean_token_accuracy": 0.0,
|
|
"num_tokens": 11448.0,
|
|
"step": 5
|
|
},
|
|
{
|
|
"entropy": 4.908018112182617,
|
|
"epoch": 0.0009924573243350536,
|
|
"grad_norm": 13.875,
|
|
"learning_rate": 4.5e-06,
|
|
"loss": 14.4058,
|
|
"mean_token_accuracy": 0.0,
|
|
"num_tokens": 22646.0,
|
|
"step": 10
|
|
},
|
|
{
|
|
"entropy": 4.919006061553955,
|
|
"epoch": 0.0014886859865025804,
|
|
"grad_norm": 13.875,
|
|
"learning_rate": 7e-06,
|
|
"loss": 14.3319,
|
|
"mean_token_accuracy": 6.66666659526527e-05,
|
|
"num_tokens": 34011.0,
|
|
"step": 15
|
|
},
|
|
{
|
|
"entropy": 4.953374242782592,
|
|
"epoch": 0.001984914648670107,
|
|
"grad_norm": 17.0,
|
|
"learning_rate": 9.5e-06,
|
|
"loss": 14.1459,
|
|
"mean_token_accuracy": 0.0,
|
|
"num_tokens": 44566.0,
|
|
"step": 20
|
|
},
|
|
{
|
|
"entropy": 5.0529521942138675,
|
|
"epoch": 0.002481143310837634,
|
|
"grad_norm": 20.375,
|
|
"learning_rate": 1.2e-05,
|
|
"loss": 13.7995,
|
|
"mean_token_accuracy": 8.56164377182722e-05,
|
|
"num_tokens": 56274.0,
|
|
"step": 25
|
|
},
|
|
{
|
|
"entropy": 5.29259762763977,
|
|
"epoch": 0.0029773719730051607,
|
|
"grad_norm": 25.75,
|
|
"learning_rate": 1.4500000000000002e-05,
|
|
"loss": 13.2456,
|
|
"mean_token_accuracy": 0.0,
|
|
"num_tokens": 66584.0,
|
|
"step": 30
|
|
},
|
|
{
|
|
"entropy": 6.583654308319092,
|
|
"epoch": 0.0034736006351726877,
|
|
"grad_norm": 25.625,
|
|
"learning_rate": 1.7000000000000003e-05,
|
|
"loss": 12.143,
|
|
"mean_token_accuracy": 0.0,
|
|
"num_tokens": 76948.0,
|
|
"step": 35
|
|
},
|
|
{
|
|
"entropy": 9.861779689788818,
|
|
"epoch": 0.003969829297340214,
|
|
"grad_norm": 3.375,
|
|
"learning_rate": 1.95e-05,
|
|
"loss": 10.9562,
|
|
"mean_token_accuracy": 0.00021723387762904168,
|
|
"num_tokens": 87253.0,
|
|
"step": 40
|
|
},
|
|
{
|
|
"entropy": 10.708572006225586,
|
|
"epoch": 0.004466057959507741,
|
|
"grad_norm": 3.4375,
|
|
"learning_rate": 2.2e-05,
|
|
"loss": 10.7237,
|
|
"mean_token_accuracy": 0.010100901639088989,
|
|
"num_tokens": 98273.0,
|
|
"step": 45
|
|
},
|
|
{
|
|
"entropy": 10.741462326049804,
|
|
"epoch": 0.004962286621675268,
|
|
"grad_norm": 3.015625,
|
|
"learning_rate": 2.4500000000000003e-05,
|
|
"loss": 10.5536,
|
|
"mean_token_accuracy": 0.017115887999534608,
|
|
"num_tokens": 107788.0,
|
|
"step": 50
|
|
},
|
|
{
|
|
"entropy": 10.71127405166626,
|
|
"epoch": 0.0054585152838427945,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 2.7e-05,
|
|
"loss": 10.3864,
|
|
"mean_token_accuracy": 0.015602491609752179,
|
|
"num_tokens": 118632.0,
|
|
"step": 55
|
|
},
|
|
{
|
|
"entropy": 10.660900974273682,
|
|
"epoch": 0.0059547439460103215,
|
|
"grad_norm": 2.3125,
|
|
"learning_rate": 2.95e-05,
|
|
"loss": 10.1743,
|
|
"mean_token_accuracy": 0.016560734901577234,
|
|
"num_tokens": 128649.0,
|
|
"step": 60
|
|
},
|
|
{
|
|
"entropy": 10.705959510803222,
|
|
"epoch": 0.0064509726081778485,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 3.2e-05,
|
|
"loss": 10.0457,
|
|
"mean_token_accuracy": 0.01719390321522951,
|
|
"num_tokens": 138958.0,
|
|
"step": 65
|
|
},
|
|
{
|
|
"entropy": 10.725889587402344,
|
|
"epoch": 0.0069472012703453755,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 3.4500000000000005e-05,
|
|
"loss": 9.9768,
|
|
"mean_token_accuracy": 0.04213028624653816,
|
|
"num_tokens": 151445.0,
|
|
"step": 70
|
|
},
|
|
{
|
|
"entropy": 10.721480083465575,
|
|
"epoch": 0.007443429932512902,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 3.7e-05,
|
|
"loss": 9.8683,
|
|
"mean_token_accuracy": 0.04831866100430489,
|
|
"num_tokens": 162239.0,
|
|
"step": 75
|
|
},
|
|
{
|
|
"entropy": 10.70771484375,
|
|
"epoch": 0.007939658594680429,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 3.95e-05,
|
|
"loss": 9.8133,
|
|
"mean_token_accuracy": 0.042871393263339996,
|
|
"num_tokens": 173261.0,
|
|
"step": 80
|
|
},
|
|
{
|
|
"entropy": 10.706668090820312,
|
|
"epoch": 0.008435887256847956,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 4.2000000000000004e-05,
|
|
"loss": 9.6933,
|
|
"mean_token_accuracy": 0.042860785871744154,
|
|
"num_tokens": 183857.0,
|
|
"step": 85
|
|
},
|
|
{
|
|
"entropy": 10.696372127532959,
|
|
"epoch": 0.008932115919015483,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 4.45e-05,
|
|
"loss": 9.6957,
|
|
"mean_token_accuracy": 0.04004955124109984,
|
|
"num_tokens": 196635.0,
|
|
"step": 90
|
|
},
|
|
{
|
|
"entropy": 10.685241222381592,
|
|
"epoch": 0.00942834458118301,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 4.7000000000000004e-05,
|
|
"loss": 9.5188,
|
|
"mean_token_accuracy": 0.04844313133507967,
|
|
"num_tokens": 208700.0,
|
|
"step": 95
|
|
},
|
|
{
|
|
"entropy": 10.666670799255371,
|
|
"epoch": 0.009924573243350537,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 4.9500000000000004e-05,
|
|
"loss": 9.3761,
|
|
"mean_token_accuracy": 0.046723760291934015,
|
|
"num_tokens": 218915.0,
|
|
"step": 100
|
|
},
|
|
{
|
|
"entropy": 10.638776302337646,
|
|
"epoch": 0.010420801905518062,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 5.2e-05,
|
|
"loss": 9.2697,
|
|
"mean_token_accuracy": 0.052684008702635766,
|
|
"num_tokens": 230211.0,
|
|
"step": 105
|
|
},
|
|
{
|
|
"entropy": 10.60411787033081,
|
|
"epoch": 0.010917030567685589,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 5.45e-05,
|
|
"loss": 9.1633,
|
|
"mean_token_accuracy": 0.05152133964002133,
|
|
"num_tokens": 241174.0,
|
|
"step": 110
|
|
},
|
|
{
|
|
"entropy": 10.56174831390381,
|
|
"epoch": 0.011413259229853116,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 5.7e-05,
|
|
"loss": 9.0895,
|
|
"mean_token_accuracy": 0.047252026945352556,
|
|
"num_tokens": 251708.0,
|
|
"step": 115
|
|
},
|
|
{
|
|
"entropy": 10.521473789215088,
|
|
"epoch": 0.011909487892020643,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 5.9499999999999996e-05,
|
|
"loss": 9.0937,
|
|
"mean_token_accuracy": 0.045639040693640706,
|
|
"num_tokens": 263287.0,
|
|
"step": 120
|
|
},
|
|
{
|
|
"entropy": 10.479307842254638,
|
|
"epoch": 0.01240571655418817,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 6.2e-05,
|
|
"loss": 8.924,
|
|
"mean_token_accuracy": 0.043540829047560695,
|
|
"num_tokens": 275179.0,
|
|
"step": 125
|
|
},
|
|
{
|
|
"entropy": 10.418986606597901,
|
|
"epoch": 0.012901945216355697,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 6.450000000000001e-05,
|
|
"loss": 8.7387,
|
|
"mean_token_accuracy": 0.04855534341186285,
|
|
"num_tokens": 287223.0,
|
|
"step": 130
|
|
},
|
|
{
|
|
"entropy": 10.346403312683105,
|
|
"epoch": 0.013398173878523224,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 6.7e-05,
|
|
"loss": 8.6159,
|
|
"mean_token_accuracy": 0.04886538349092007,
|
|
"num_tokens": 297868.0,
|
|
"step": 135
|
|
},
|
|
{
|
|
"entropy": 10.254747295379639,
|
|
"epoch": 0.013894402540690751,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 6.950000000000001e-05,
|
|
"loss": 8.5351,
|
|
"mean_token_accuracy": 0.050269151106476784,
|
|
"num_tokens": 309702.0,
|
|
"step": 140
|
|
},
|
|
{
|
|
"entropy": 10.153191566467285,
|
|
"epoch": 0.014390631202858276,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 7.2e-05,
|
|
"loss": 8.5012,
|
|
"mean_token_accuracy": 0.045820210874080655,
|
|
"num_tokens": 321613.0,
|
|
"step": 145
|
|
},
|
|
{
|
|
"entropy": 10.02096643447876,
|
|
"epoch": 0.014886859865025803,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 7.45e-05,
|
|
"loss": 8.3155,
|
|
"mean_token_accuracy": 0.050194774940609935,
|
|
"num_tokens": 332668.0,
|
|
"step": 150
|
|
},
|
|
{
|
|
"entropy": 9.884018039703369,
|
|
"epoch": 0.01538308852719333,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 7.7e-05,
|
|
"loss": 8.2768,
|
|
"mean_token_accuracy": 0.050016530230641364,
|
|
"num_tokens": 342579.0,
|
|
"step": 155
|
|
},
|
|
{
|
|
"entropy": 9.711176681518555,
|
|
"epoch": 0.015879317189360857,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 7.950000000000001e-05,
|
|
"loss": 8.126,
|
|
"mean_token_accuracy": 0.04717333130538463,
|
|
"num_tokens": 352271.0,
|
|
"step": 160
|
|
},
|
|
{
|
|
"entropy": 9.53788137435913,
|
|
"epoch": 0.016375545851528384,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 8.2e-05,
|
|
"loss": 8.0862,
|
|
"mean_token_accuracy": 0.05482652448117733,
|
|
"num_tokens": 364033.0,
|
|
"step": 165
|
|
},
|
|
{
|
|
"entropy": 9.262330722808837,
|
|
"epoch": 0.01687177451369591,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 8.450000000000001e-05,
|
|
"loss": 7.9892,
|
|
"mean_token_accuracy": 0.04694691449403763,
|
|
"num_tokens": 373788.0,
|
|
"step": 170
|
|
},
|
|
{
|
|
"entropy": 9.129754638671875,
|
|
"epoch": 0.01736800317586344,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 8.7e-05,
|
|
"loss": 7.9617,
|
|
"mean_token_accuracy": 0.044896982982754706,
|
|
"num_tokens": 384883.0,
|
|
"step": 175
|
|
},
|
|
{
|
|
"entropy": 8.975637817382813,
|
|
"epoch": 0.017864231838030965,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 8.95e-05,
|
|
"loss": 7.8555,
|
|
"mean_token_accuracy": 0.04881042614579201,
|
|
"num_tokens": 396044.0,
|
|
"step": 180
|
|
},
|
|
{
|
|
"entropy": 8.740224266052246,
|
|
"epoch": 0.018360460500198492,
|
|
"grad_norm": 0.76953125,
|
|
"learning_rate": 9.2e-05,
|
|
"loss": 7.9152,
|
|
"mean_token_accuracy": 0.047916683554649356,
|
|
"num_tokens": 406995.0,
|
|
"step": 185
|
|
},
|
|
{
|
|
"entropy": 8.553805732727051,
|
|
"epoch": 0.01885668916236602,
|
|
"grad_norm": 0.78515625,
|
|
"learning_rate": 9.45e-05,
|
|
"loss": 7.7613,
|
|
"mean_token_accuracy": 0.05165142118930817,
|
|
"num_tokens": 417238.0,
|
|
"step": 190
|
|
},
|
|
{
|
|
"entropy": 8.464924621582032,
|
|
"epoch": 0.019352917824533546,
|
|
"grad_norm": 0.734375,
|
|
"learning_rate": 9.7e-05,
|
|
"loss": 7.8352,
|
|
"mean_token_accuracy": 0.044884103909134866,
|
|
"num_tokens": 427263.0,
|
|
"step": 195
|
|
},
|
|
{
|
|
"entropy": 8.39473524093628,
|
|
"epoch": 0.019849146486701073,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 9.95e-05,
|
|
"loss": 7.7506,
|
|
"mean_token_accuracy": 0.04875692799687385,
|
|
"num_tokens": 438357.0,
|
|
"step": 200
|
|
},
|
|
{
|
|
"entropy": 8.318683052062989,
|
|
"epoch": 0.0203453751488686,
|
|
"grad_norm": 0.67578125,
|
|
"learning_rate": 0.000102,
|
|
"loss": 7.7541,
|
|
"mean_token_accuracy": 0.04936891198158264,
|
|
"num_tokens": 448738.0,
|
|
"step": 205
|
|
},
|
|
{
|
|
"entropy": 8.268324375152588,
|
|
"epoch": 0.020841603811036124,
|
|
"grad_norm": 0.71875,
|
|
"learning_rate": 0.00010449999999999999,
|
|
"loss": 7.76,
|
|
"mean_token_accuracy": 0.056964365392923356,
|
|
"num_tokens": 457873.0,
|
|
"step": 210
|
|
},
|
|
{
|
|
"entropy": 8.257455635070801,
|
|
"epoch": 0.02133783247320365,
|
|
"grad_norm": 0.71875,
|
|
"learning_rate": 0.000107,
|
|
"loss": 7.7046,
|
|
"mean_token_accuracy": 0.05989706926047802,
|
|
"num_tokens": 468640.0,
|
|
"step": 215
|
|
},
|
|
{
|
|
"entropy": 8.317792892456055,
|
|
"epoch": 0.021834061135371178,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0001095,
|
|
"loss": 7.7039,
|
|
"mean_token_accuracy": 0.06188451088964939,
|
|
"num_tokens": 479922.0,
|
|
"step": 220
|
|
},
|
|
{
|
|
"entropy": 8.245875453948974,
|
|
"epoch": 0.022330289797538705,
|
|
"grad_norm": 0.75390625,
|
|
"learning_rate": 0.000112,
|
|
"loss": 7.663,
|
|
"mean_token_accuracy": 0.053246379271149634,
|
|
"num_tokens": 491056.0,
|
|
"step": 225
|
|
},
|
|
{
|
|
"entropy": 8.234527969360352,
|
|
"epoch": 0.022826518459706232,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0001145,
|
|
"loss": 7.7427,
|
|
"mean_token_accuracy": 0.05878411866724491,
|
|
"num_tokens": 504365.0,
|
|
"step": 230
|
|
},
|
|
{
|
|
"entropy": 8.225464916229248,
|
|
"epoch": 0.02332274712187376,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00011700000000000001,
|
|
"loss": 7.638,
|
|
"mean_token_accuracy": 0.057496064156293866,
|
|
"num_tokens": 514347.0,
|
|
"step": 235
|
|
},
|
|
{
|
|
"entropy": 8.184865188598632,
|
|
"epoch": 0.023818975784041286,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00011949999999999999,
|
|
"loss": 7.6521,
|
|
"mean_token_accuracy": 0.062484626099467276,
|
|
"num_tokens": 525912.0,
|
|
"step": 240
|
|
},
|
|
{
|
|
"entropy": 8.202389526367188,
|
|
"epoch": 0.024315204446208813,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000122,
|
|
"loss": 7.5455,
|
|
"mean_token_accuracy": 0.06251657865941525,
|
|
"num_tokens": 535566.0,
|
|
"step": 245
|
|
},
|
|
{
|
|
"entropy": 8.209773063659668,
|
|
"epoch": 0.02481143310837634,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0001245,
|
|
"loss": 7.593,
|
|
"mean_token_accuracy": 0.0647435687482357,
|
|
"num_tokens": 546474.0,
|
|
"step": 250
|
|
},
|
|
{
|
|
"entropy": 8.14191026687622,
|
|
"epoch": 0.025307661770543867,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.000127,
|
|
"loss": 7.6509,
|
|
"mean_token_accuracy": 0.061424101889133456,
|
|
"num_tokens": 558132.0,
|
|
"step": 255
|
|
},
|
|
{
|
|
"entropy": 8.203132820129394,
|
|
"epoch": 0.025803890432711394,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0001295,
|
|
"loss": 7.6428,
|
|
"mean_token_accuracy": 0.06428770869970321,
|
|
"num_tokens": 568309.0,
|
|
"step": 260
|
|
},
|
|
{
|
|
"entropy": 8.081572723388671,
|
|
"epoch": 0.02630011909487892,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.000132,
|
|
"loss": 7.5249,
|
|
"mean_token_accuracy": 0.06533985063433648,
|
|
"num_tokens": 579701.0,
|
|
"step": 265
|
|
},
|
|
{
|
|
"entropy": 8.113927555084228,
|
|
"epoch": 0.026796347757046448,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00013450000000000002,
|
|
"loss": 7.4971,
|
|
"mean_token_accuracy": 0.06705491952598094,
|
|
"num_tokens": 590832.0,
|
|
"step": 270
|
|
},
|
|
{
|
|
"entropy": 8.06861686706543,
|
|
"epoch": 0.027292576419213975,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00013700000000000002,
|
|
"loss": 7.4523,
|
|
"mean_token_accuracy": 0.06724155806005001,
|
|
"num_tokens": 601094.0,
|
|
"step": 275
|
|
},
|
|
{
|
|
"entropy": 8.04738645553589,
|
|
"epoch": 0.027788805081381502,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0001395,
|
|
"loss": 7.4503,
|
|
"mean_token_accuracy": 0.0721239697188139,
|
|
"num_tokens": 612027.0,
|
|
"step": 280
|
|
},
|
|
{
|
|
"entropy": 7.953780841827393,
|
|
"epoch": 0.02828503374354903,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.00014199999999999998,
|
|
"loss": 7.4716,
|
|
"mean_token_accuracy": 0.0679593924432993,
|
|
"num_tokens": 623698.0,
|
|
"step": 285
|
|
},
|
|
{
|
|
"entropy": 7.966112470626831,
|
|
"epoch": 0.028781262405716553,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0001445,
|
|
"loss": 7.4753,
|
|
"mean_token_accuracy": 0.06937897726893424,
|
|
"num_tokens": 635631.0,
|
|
"step": 290
|
|
},
|
|
{
|
|
"entropy": 7.981750106811523,
|
|
"epoch": 0.02927749106788408,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.000147,
|
|
"loss": 7.4567,
|
|
"mean_token_accuracy": 0.06901448890566826,
|
|
"num_tokens": 647663.0,
|
|
"step": 295
|
|
},
|
|
{
|
|
"entropy": 7.9344415187835695,
|
|
"epoch": 0.029773719730051607,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0001495,
|
|
"loss": 7.4202,
|
|
"mean_token_accuracy": 0.06708400063216687,
|
|
"num_tokens": 659352.0,
|
|
"step": 300
|
|
},
|
|
{
|
|
"entropy": 7.962864351272583,
|
|
"epoch": 0.030269948392219134,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.000152,
|
|
"loss": 7.3883,
|
|
"mean_token_accuracy": 0.0732420600950718,
|
|
"num_tokens": 669379.0,
|
|
"step": 305
|
|
},
|
|
{
|
|
"entropy": 7.942562055587769,
|
|
"epoch": 0.03076617705438666,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00015450000000000001,
|
|
"loss": 7.3844,
|
|
"mean_token_accuracy": 0.07024326287209988,
|
|
"num_tokens": 680144.0,
|
|
"step": 310
|
|
},
|
|
{
|
|
"entropy": 7.996751976013184,
|
|
"epoch": 0.03126240571655419,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000157,
|
|
"loss": 7.3426,
|
|
"mean_token_accuracy": 0.06623242497444153,
|
|
"num_tokens": 691165.0,
|
|
"step": 315
|
|
},
|
|
{
|
|
"entropy": 7.823547601699829,
|
|
"epoch": 0.031758634378721715,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0001595,
|
|
"loss": 7.3996,
|
|
"mean_token_accuracy": 0.06626546904444694,
|
|
"num_tokens": 703767.0,
|
|
"step": 320
|
|
},
|
|
{
|
|
"entropy": 7.798118686676025,
|
|
"epoch": 0.032254863040889245,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000162,
|
|
"loss": 7.389,
|
|
"mean_token_accuracy": 0.07417060770094394,
|
|
"num_tokens": 714298.0,
|
|
"step": 325
|
|
},
|
|
{
|
|
"entropy": 7.857796287536621,
|
|
"epoch": 0.03275109170305677,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00016450000000000001,
|
|
"loss": 7.3782,
|
|
"mean_token_accuracy": 0.07758076079189777,
|
|
"num_tokens": 724135.0,
|
|
"step": 330
|
|
},
|
|
{
|
|
"entropy": 7.84428334236145,
|
|
"epoch": 0.03324732036522429,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00016700000000000002,
|
|
"loss": 7.4209,
|
|
"mean_token_accuracy": 0.06709365807473659,
|
|
"num_tokens": 735050.0,
|
|
"step": 335
|
|
},
|
|
{
|
|
"entropy": 7.832436752319336,
|
|
"epoch": 0.03374354902739182,
|
|
"grad_norm": 0.7265625,
|
|
"learning_rate": 0.00016950000000000003,
|
|
"loss": 7.3356,
|
|
"mean_token_accuracy": 0.07104014568030834,
|
|
"num_tokens": 746073.0,
|
|
"step": 340
|
|
},
|
|
{
|
|
"entropy": 7.795631265640258,
|
|
"epoch": 0.034239777689559346,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.00017199999999999998,
|
|
"loss": 7.3294,
|
|
"mean_token_accuracy": 0.06888764202594758,
|
|
"num_tokens": 758998.0,
|
|
"step": 345
|
|
},
|
|
{
|
|
"entropy": 7.798632431030273,
|
|
"epoch": 0.03473600635172688,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00017449999999999999,
|
|
"loss": 7.2774,
|
|
"mean_token_accuracy": 0.06999869644641876,
|
|
"num_tokens": 771608.0,
|
|
"step": 350
|
|
},
|
|
{
|
|
"entropy": 7.839082527160644,
|
|
"epoch": 0.0352322350138944,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.000177,
|
|
"loss": 7.3336,
|
|
"mean_token_accuracy": 0.07213714122772216,
|
|
"num_tokens": 782394.0,
|
|
"step": 355
|
|
},
|
|
{
|
|
"entropy": 7.719696950912476,
|
|
"epoch": 0.03572846367606193,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0001795,
|
|
"loss": 7.2421,
|
|
"mean_token_accuracy": 0.07258376255631446,
|
|
"num_tokens": 792389.0,
|
|
"step": 360
|
|
},
|
|
{
|
|
"entropy": 7.709195804595947,
|
|
"epoch": 0.036224692338229454,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.000182,
|
|
"loss": 7.2874,
|
|
"mean_token_accuracy": 0.07547833137214184,
|
|
"num_tokens": 803219.0,
|
|
"step": 365
|
|
},
|
|
{
|
|
"entropy": 7.799539947509766,
|
|
"epoch": 0.036720921000396985,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0001845,
|
|
"loss": 7.3472,
|
|
"mean_token_accuracy": 0.07126162201166153,
|
|
"num_tokens": 814249.0,
|
|
"step": 370
|
|
},
|
|
{
|
|
"entropy": 7.732659769058228,
|
|
"epoch": 0.03721714966256451,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.000187,
|
|
"loss": 7.2464,
|
|
"mean_token_accuracy": 0.07738562412559986,
|
|
"num_tokens": 825138.0,
|
|
"step": 375
|
|
},
|
|
{
|
|
"entropy": 7.711156368255615,
|
|
"epoch": 0.03771337832473204,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0001895,
|
|
"loss": 7.2878,
|
|
"mean_token_accuracy": 0.07714832685887814,
|
|
"num_tokens": 836024.0,
|
|
"step": 380
|
|
},
|
|
{
|
|
"entropy": 7.6839886665344235,
|
|
"epoch": 0.03820960698689956,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.000192,
|
|
"loss": 7.28,
|
|
"mean_token_accuracy": 0.0712902493774891,
|
|
"num_tokens": 847765.0,
|
|
"step": 385
|
|
},
|
|
{
|
|
"entropy": 7.674788284301758,
|
|
"epoch": 0.03870583564906709,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0001945,
|
|
"loss": 7.274,
|
|
"mean_token_accuracy": 0.07328340820968152,
|
|
"num_tokens": 859980.0,
|
|
"step": 390
|
|
},
|
|
{
|
|
"entropy": 7.707912158966065,
|
|
"epoch": 0.039202064311234616,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00019700000000000002,
|
|
"loss": 7.2697,
|
|
"mean_token_accuracy": 0.07509268596768379,
|
|
"num_tokens": 871514.0,
|
|
"step": 395
|
|
},
|
|
{
|
|
"entropy": 7.807592153549194,
|
|
"epoch": 0.03969829297340215,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00019950000000000002,
|
|
"loss": 7.2594,
|
|
"mean_token_accuracy": 0.06952392719686032,
|
|
"num_tokens": 881984.0,
|
|
"step": 400
|
|
},
|
|
{
|
|
"entropy": 7.621029710769653,
|
|
"epoch": 0.04019452163556967,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.000202,
|
|
"loss": 7.2334,
|
|
"mean_token_accuracy": 0.07512535229325294,
|
|
"num_tokens": 894198.0,
|
|
"step": 405
|
|
},
|
|
{
|
|
"entropy": 7.6571179866790775,
|
|
"epoch": 0.0406907502977372,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.00020449999999999998,
|
|
"loss": 7.2387,
|
|
"mean_token_accuracy": 0.07779023945331573,
|
|
"num_tokens": 905394.0,
|
|
"step": 410
|
|
},
|
|
{
|
|
"entropy": 7.729351425170899,
|
|
"epoch": 0.041186978959904724,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.000207,
|
|
"loss": 7.2892,
|
|
"mean_token_accuracy": 0.0726883053779602,
|
|
"num_tokens": 917010.0,
|
|
"step": 415
|
|
},
|
|
{
|
|
"entropy": 7.617552757263184,
|
|
"epoch": 0.04168320762207225,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0002095,
|
|
"loss": 7.1201,
|
|
"mean_token_accuracy": 0.07954838424921036,
|
|
"num_tokens": 926761.0,
|
|
"step": 420
|
|
},
|
|
{
|
|
"entropy": 7.515660905838013,
|
|
"epoch": 0.04217943628423978,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.000212,
|
|
"loss": 7.1273,
|
|
"mean_token_accuracy": 0.07839518934488296,
|
|
"num_tokens": 938385.0,
|
|
"step": 425
|
|
},
|
|
{
|
|
"entropy": 7.5848071575164795,
|
|
"epoch": 0.0426756649464073,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0002145,
|
|
"loss": 7.1617,
|
|
"mean_token_accuracy": 0.07512866109609603,
|
|
"num_tokens": 949709.0,
|
|
"step": 430
|
|
},
|
|
{
|
|
"entropy": 7.638444280624389,
|
|
"epoch": 0.04317189360857483,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00021700000000000002,
|
|
"loss": 7.2004,
|
|
"mean_token_accuracy": 0.07354060970246792,
|
|
"num_tokens": 960837.0,
|
|
"step": 435
|
|
},
|
|
{
|
|
"entropy": 7.593792295455932,
|
|
"epoch": 0.043668122270742356,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0002195,
|
|
"loss": 7.0385,
|
|
"mean_token_accuracy": 0.08071191161870957,
|
|
"num_tokens": 971036.0,
|
|
"step": 440
|
|
},
|
|
{
|
|
"entropy": 7.5954118251800535,
|
|
"epoch": 0.044164350932909886,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000222,
|
|
"loss": 7.1804,
|
|
"mean_token_accuracy": 0.0766368854790926,
|
|
"num_tokens": 983057.0,
|
|
"step": 445
|
|
},
|
|
{
|
|
"entropy": 7.580991935729981,
|
|
"epoch": 0.04466057959507741,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0002245,
|
|
"loss": 7.1365,
|
|
"mean_token_accuracy": 0.08031548969447613,
|
|
"num_tokens": 994303.0,
|
|
"step": 450
|
|
},
|
|
{
|
|
"entropy": 7.499250650405884,
|
|
"epoch": 0.04515680825724494,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00022700000000000002,
|
|
"loss": 7.135,
|
|
"mean_token_accuracy": 0.07660448849201203,
|
|
"num_tokens": 1005033.0,
|
|
"step": 455
|
|
},
|
|
{
|
|
"entropy": 7.613832330703735,
|
|
"epoch": 0.045653036919412464,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.00022950000000000002,
|
|
"loss": 7.193,
|
|
"mean_token_accuracy": 0.08052344620227814,
|
|
"num_tokens": 1015940.0,
|
|
"step": 460
|
|
},
|
|
{
|
|
"entropy": 7.549146223068237,
|
|
"epoch": 0.046149265581579994,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00023200000000000003,
|
|
"loss": 7.1365,
|
|
"mean_token_accuracy": 0.08448440171778202,
|
|
"num_tokens": 1027582.0,
|
|
"step": 465
|
|
},
|
|
{
|
|
"entropy": 7.550874137878418,
|
|
"epoch": 0.04664549424374752,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00023449999999999998,
|
|
"loss": 7.1147,
|
|
"mean_token_accuracy": 0.07626789584755897,
|
|
"num_tokens": 1040046.0,
|
|
"step": 470
|
|
},
|
|
{
|
|
"entropy": 7.5545329570770265,
|
|
"epoch": 0.04714172290591505,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.000237,
|
|
"loss": 7.1922,
|
|
"mean_token_accuracy": 0.0756704431027174,
|
|
"num_tokens": 1050636.0,
|
|
"step": 475
|
|
},
|
|
{
|
|
"entropy": 7.618306350708008,
|
|
"epoch": 0.04763795156808257,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0002395,
|
|
"loss": 7.0724,
|
|
"mean_token_accuracy": 0.08306895196437836,
|
|
"num_tokens": 1060748.0,
|
|
"step": 480
|
|
},
|
|
{
|
|
"entropy": 7.600764751434326,
|
|
"epoch": 0.0481341802302501,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.000242,
|
|
"loss": 7.1277,
|
|
"mean_token_accuracy": 0.07725501246750355,
|
|
"num_tokens": 1071940.0,
|
|
"step": 485
|
|
},
|
|
{
|
|
"entropy": 7.485190486907959,
|
|
"epoch": 0.048630408892417626,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0002445,
|
|
"loss": 7.1243,
|
|
"mean_token_accuracy": 0.08531232550740242,
|
|
"num_tokens": 1082962.0,
|
|
"step": 490
|
|
},
|
|
{
|
|
"entropy": 7.577714586257935,
|
|
"epoch": 0.04912663755458515,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000247,
|
|
"loss": 7.0988,
|
|
"mean_token_accuracy": 0.08504232913255691,
|
|
"num_tokens": 1093082.0,
|
|
"step": 495
|
|
},
|
|
{
|
|
"entropy": 7.54087610244751,
|
|
"epoch": 0.04962286621675268,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0002495,
|
|
"loss": 7.161,
|
|
"mean_token_accuracy": 0.07727786526083946,
|
|
"num_tokens": 1103528.0,
|
|
"step": 500
|
|
},
|
|
{
|
|
"entropy": 7.444737100601197,
|
|
"epoch": 0.0501190948789202,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.000252,
|
|
"loss": 7.0602,
|
|
"mean_token_accuracy": 0.07846606895327568,
|
|
"num_tokens": 1114813.0,
|
|
"step": 505
|
|
},
|
|
{
|
|
"entropy": 7.511781406402588,
|
|
"epoch": 0.050615323541087734,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0002545,
|
|
"loss": 7.0536,
|
|
"mean_token_accuracy": 0.07985799759626389,
|
|
"num_tokens": 1125345.0,
|
|
"step": 510
|
|
},
|
|
{
|
|
"entropy": 7.452861642837524,
|
|
"epoch": 0.05111155220325526,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.000257,
|
|
"loss": 7.0618,
|
|
"mean_token_accuracy": 0.08063343465328217,
|
|
"num_tokens": 1134985.0,
|
|
"step": 515
|
|
},
|
|
{
|
|
"entropy": 7.497338771820068,
|
|
"epoch": 0.05160778086542279,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0002595,
|
|
"loss": 7.0742,
|
|
"mean_token_accuracy": 0.08803893476724625,
|
|
"num_tokens": 1145796.0,
|
|
"step": 520
|
|
},
|
|
{
|
|
"entropy": 7.637927579879761,
|
|
"epoch": 0.05210400952759031,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000262,
|
|
"loss": 7.207,
|
|
"mean_token_accuracy": 0.07291420958936215,
|
|
"num_tokens": 1156936.0,
|
|
"step": 525
|
|
},
|
|
{
|
|
"entropy": 7.462926721572876,
|
|
"epoch": 0.05260023818975784,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00026450000000000003,
|
|
"loss": 7.057,
|
|
"mean_token_accuracy": 0.08704347461462021,
|
|
"num_tokens": 1167526.0,
|
|
"step": 530
|
|
},
|
|
{
|
|
"entropy": 7.486857652664185,
|
|
"epoch": 0.053096466851925365,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00026700000000000004,
|
|
"loss": 7.1034,
|
|
"mean_token_accuracy": 0.0767381489276886,
|
|
"num_tokens": 1177647.0,
|
|
"step": 535
|
|
},
|
|
{
|
|
"entropy": 7.492286443710327,
|
|
"epoch": 0.053592695514092896,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00026950000000000005,
|
|
"loss": 7.0725,
|
|
"mean_token_accuracy": 0.08671703785657883,
|
|
"num_tokens": 1188255.0,
|
|
"step": 540
|
|
},
|
|
{
|
|
"entropy": 7.378701829910279,
|
|
"epoch": 0.05408892417626042,
|
|
"grad_norm": 0.796875,
|
|
"learning_rate": 0.00027200000000000005,
|
|
"loss": 6.9983,
|
|
"mean_token_accuracy": 0.09135269373655319,
|
|
"num_tokens": 1199433.0,
|
|
"step": 545
|
|
},
|
|
{
|
|
"entropy": 7.424235725402832,
|
|
"epoch": 0.05458515283842795,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0002745,
|
|
"loss": 7.0643,
|
|
"mean_token_accuracy": 0.08066366724669934,
|
|
"num_tokens": 1210067.0,
|
|
"step": 550
|
|
},
|
|
{
|
|
"entropy": 7.368731451034546,
|
|
"epoch": 0.055081381500595473,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000277,
|
|
"loss": 6.956,
|
|
"mean_token_accuracy": 0.0897083193063736,
|
|
"num_tokens": 1220639.0,
|
|
"step": 555
|
|
},
|
|
{
|
|
"entropy": 7.4522312641143795,
|
|
"epoch": 0.055577610162763004,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0002795,
|
|
"loss": 7.005,
|
|
"mean_token_accuracy": 0.08417323902249337,
|
|
"num_tokens": 1233158.0,
|
|
"step": 560
|
|
},
|
|
{
|
|
"entropy": 7.401830005645752,
|
|
"epoch": 0.05607383882493053,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00028199999999999997,
|
|
"loss": 6.9805,
|
|
"mean_token_accuracy": 0.08172584101557731,
|
|
"num_tokens": 1244552.0,
|
|
"step": 565
|
|
},
|
|
{
|
|
"entropy": 7.434595537185669,
|
|
"epoch": 0.05657006748709806,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0002845,
|
|
"loss": 7.0868,
|
|
"mean_token_accuracy": 0.07824886590242386,
|
|
"num_tokens": 1255478.0,
|
|
"step": 570
|
|
},
|
|
{
|
|
"entropy": 7.333680963516235,
|
|
"epoch": 0.05706629614926558,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.000287,
|
|
"loss": 6.9104,
|
|
"mean_token_accuracy": 0.09092385321855545,
|
|
"num_tokens": 1267507.0,
|
|
"step": 575
|
|
},
|
|
{
|
|
"entropy": 7.288129615783691,
|
|
"epoch": 0.057562524811433105,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0002895,
|
|
"loss": 6.9139,
|
|
"mean_token_accuracy": 0.08322850465774537,
|
|
"num_tokens": 1279377.0,
|
|
"step": 580
|
|
},
|
|
{
|
|
"entropy": 7.501294803619385,
|
|
"epoch": 0.058058753473600636,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.000292,
|
|
"loss": 7.0026,
|
|
"mean_token_accuracy": 0.09129699394106865,
|
|
"num_tokens": 1290671.0,
|
|
"step": 585
|
|
},
|
|
{
|
|
"entropy": 7.294687795639038,
|
|
"epoch": 0.05855498213576816,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0002945,
|
|
"loss": 6.9489,
|
|
"mean_token_accuracy": 0.09131397828459739,
|
|
"num_tokens": 1302792.0,
|
|
"step": 590
|
|
},
|
|
{
|
|
"entropy": 7.357182216644287,
|
|
"epoch": 0.05905121079793569,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000297,
|
|
"loss": 6.9027,
|
|
"mean_token_accuracy": 0.0812704510986805,
|
|
"num_tokens": 1313315.0,
|
|
"step": 595
|
|
},
|
|
{
|
|
"entropy": 7.276323318481445,
|
|
"epoch": 0.05954743946010321,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0002995,
|
|
"loss": 6.9766,
|
|
"mean_token_accuracy": 0.0856074646115303,
|
|
"num_tokens": 1326358.0,
|
|
"step": 600
|
|
},
|
|
{
|
|
"entropy": 7.370176696777344,
|
|
"epoch": 0.060043668122270744,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.000302,
|
|
"loss": 6.859,
|
|
"mean_token_accuracy": 0.08850097134709359,
|
|
"num_tokens": 1336266.0,
|
|
"step": 605
|
|
},
|
|
{
|
|
"entropy": 7.235168743133545,
|
|
"epoch": 0.06053989678443827,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0003045,
|
|
"loss": 6.8108,
|
|
"mean_token_accuracy": 0.0915584422647953,
|
|
"num_tokens": 1347610.0,
|
|
"step": 610
|
|
},
|
|
{
|
|
"entropy": 7.234266328811645,
|
|
"epoch": 0.0610361254466058,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000307,
|
|
"loss": 6.7687,
|
|
"mean_token_accuracy": 0.09413886740803719,
|
|
"num_tokens": 1358317.0,
|
|
"step": 615
|
|
},
|
|
{
|
|
"entropy": 7.267807722091675,
|
|
"epoch": 0.06153235410877332,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0003095,
|
|
"loss": 6.8764,
|
|
"mean_token_accuracy": 0.08720959722995758,
|
|
"num_tokens": 1370126.0,
|
|
"step": 620
|
|
},
|
|
{
|
|
"entropy": 7.298430395126343,
|
|
"epoch": 0.06202858277094085,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.000312,
|
|
"loss": 6.837,
|
|
"mean_token_accuracy": 0.0917629949748516,
|
|
"num_tokens": 1381571.0,
|
|
"step": 625
|
|
},
|
|
{
|
|
"entropy": 7.124814748764038,
|
|
"epoch": 0.06252481143310838,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0003145,
|
|
"loss": 6.8635,
|
|
"mean_token_accuracy": 0.09271070286631584,
|
|
"num_tokens": 1392486.0,
|
|
"step": 630
|
|
},
|
|
{
|
|
"entropy": 7.334286689758301,
|
|
"epoch": 0.0630210400952759,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.000317,
|
|
"loss": 6.8681,
|
|
"mean_token_accuracy": 0.08915356397628785,
|
|
"num_tokens": 1403086.0,
|
|
"step": 635
|
|
},
|
|
{
|
|
"entropy": 7.2069190502166744,
|
|
"epoch": 0.06351726875744343,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0003195,
|
|
"loss": 6.8319,
|
|
"mean_token_accuracy": 0.09226809442043304,
|
|
"num_tokens": 1414537.0,
|
|
"step": 640
|
|
},
|
|
{
|
|
"entropy": 7.251292371749878,
|
|
"epoch": 0.06401349741961096,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.000322,
|
|
"loss": 6.8459,
|
|
"mean_token_accuracy": 0.09251495376229286,
|
|
"num_tokens": 1426998.0,
|
|
"step": 645
|
|
},
|
|
{
|
|
"entropy": 7.164758586883545,
|
|
"epoch": 0.06450972608177849,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00032450000000000003,
|
|
"loss": 6.874,
|
|
"mean_token_accuracy": 0.09265056326985359,
|
|
"num_tokens": 1437667.0,
|
|
"step": 650
|
|
},
|
|
{
|
|
"entropy": 7.226160907745362,
|
|
"epoch": 0.065005954743946,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00032700000000000003,
|
|
"loss": 6.7432,
|
|
"mean_token_accuracy": 0.0969434417784214,
|
|
"num_tokens": 1448280.0,
|
|
"step": 655
|
|
},
|
|
{
|
|
"entropy": 7.15698504447937,
|
|
"epoch": 0.06550218340611354,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00032950000000000004,
|
|
"loss": 6.8019,
|
|
"mean_token_accuracy": 0.0953099973499775,
|
|
"num_tokens": 1458608.0,
|
|
"step": 660
|
|
},
|
|
{
|
|
"entropy": 7.315108156204223,
|
|
"epoch": 0.06599841206828107,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.00033200000000000005,
|
|
"loss": 6.9802,
|
|
"mean_token_accuracy": 0.08709674105048179,
|
|
"num_tokens": 1470435.0,
|
|
"step": 665
|
|
},
|
|
{
|
|
"entropy": 7.140678405761719,
|
|
"epoch": 0.06649464073044858,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00033450000000000005,
|
|
"loss": 6.8258,
|
|
"mean_token_accuracy": 0.09219390302896499,
|
|
"num_tokens": 1481959.0,
|
|
"step": 670
|
|
},
|
|
{
|
|
"entropy": 7.185245370864868,
|
|
"epoch": 0.06699086939261611,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000337,
|
|
"loss": 6.8687,
|
|
"mean_token_accuracy": 0.08819933906197548,
|
|
"num_tokens": 1493798.0,
|
|
"step": 675
|
|
},
|
|
{
|
|
"entropy": 7.220840215682983,
|
|
"epoch": 0.06748709805478365,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0003395,
|
|
"loss": 6.6833,
|
|
"mean_token_accuracy": 0.0931725412607193,
|
|
"num_tokens": 1502969.0,
|
|
"step": 680
|
|
},
|
|
{
|
|
"entropy": 7.103082990646362,
|
|
"epoch": 0.06798332671695118,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000342,
|
|
"loss": 6.8289,
|
|
"mean_token_accuracy": 0.09088226556777954,
|
|
"num_tokens": 1513825.0,
|
|
"step": 685
|
|
},
|
|
{
|
|
"entropy": 7.194331789016724,
|
|
"epoch": 0.06847955537911869,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00034449999999999997,
|
|
"loss": 6.7387,
|
|
"mean_token_accuracy": 0.09087632670998573,
|
|
"num_tokens": 1525328.0,
|
|
"step": 690
|
|
},
|
|
{
|
|
"entropy": 7.107731008529663,
|
|
"epoch": 0.06897578404128622,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.000347,
|
|
"loss": 6.7526,
|
|
"mean_token_accuracy": 0.09229976609349251,
|
|
"num_tokens": 1537383.0,
|
|
"step": 695
|
|
},
|
|
{
|
|
"entropy": 7.252395153045654,
|
|
"epoch": 0.06947201270345375,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0003495,
|
|
"loss": 6.8497,
|
|
"mean_token_accuracy": 0.09393966495990753,
|
|
"num_tokens": 1549671.0,
|
|
"step": 700
|
|
},
|
|
{
|
|
"entropy": 7.091624927520752,
|
|
"epoch": 0.06996824136562128,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.000352,
|
|
"loss": 6.728,
|
|
"mean_token_accuracy": 0.08959824368357658,
|
|
"num_tokens": 1559974.0,
|
|
"step": 705
|
|
},
|
|
{
|
|
"entropy": 7.1363232135772705,
|
|
"epoch": 0.0704644700277888,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0003545,
|
|
"loss": 6.8239,
|
|
"mean_token_accuracy": 0.08678433373570442,
|
|
"num_tokens": 1570890.0,
|
|
"step": 710
|
|
},
|
|
{
|
|
"entropy": 7.107376194000244,
|
|
"epoch": 0.07096069868995633,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.000357,
|
|
"loss": 6.7323,
|
|
"mean_token_accuracy": 0.0978621043264866,
|
|
"num_tokens": 1581434.0,
|
|
"step": 715
|
|
},
|
|
{
|
|
"entropy": 7.089070653915405,
|
|
"epoch": 0.07145692735212386,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0003595,
|
|
"loss": 6.7863,
|
|
"mean_token_accuracy": 0.09178474843502045,
|
|
"num_tokens": 1593710.0,
|
|
"step": 720
|
|
},
|
|
{
|
|
"entropy": 7.1520946502685545,
|
|
"epoch": 0.07195315601429139,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.000362,
|
|
"loss": 6.7536,
|
|
"mean_token_accuracy": 0.09313018918037415,
|
|
"num_tokens": 1604635.0,
|
|
"step": 725
|
|
},
|
|
{
|
|
"entropy": 7.222806167602539,
|
|
"epoch": 0.07244938467645891,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0003645,
|
|
"loss": 6.8202,
|
|
"mean_token_accuracy": 0.09525534659624099,
|
|
"num_tokens": 1615258.0,
|
|
"step": 730
|
|
},
|
|
{
|
|
"entropy": 7.074941730499267,
|
|
"epoch": 0.07294561333862644,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.000367,
|
|
"loss": 6.7125,
|
|
"mean_token_accuracy": 0.09651728793978691,
|
|
"num_tokens": 1625942.0,
|
|
"step": 735
|
|
},
|
|
{
|
|
"entropy": 7.0538249015808105,
|
|
"epoch": 0.07344184200079397,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0003695,
|
|
"loss": 6.7046,
|
|
"mean_token_accuracy": 0.1009585440158844,
|
|
"num_tokens": 1636270.0,
|
|
"step": 740
|
|
},
|
|
{
|
|
"entropy": 7.074357271194458,
|
|
"epoch": 0.07393807066296149,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000372,
|
|
"loss": 6.6799,
|
|
"mean_token_accuracy": 0.0913244754076004,
|
|
"num_tokens": 1647029.0,
|
|
"step": 745
|
|
},
|
|
{
|
|
"entropy": 7.095760726928711,
|
|
"epoch": 0.07443429932512902,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0003745,
|
|
"loss": 6.8498,
|
|
"mean_token_accuracy": 0.09200523346662522,
|
|
"num_tokens": 1659483.0,
|
|
"step": 750
|
|
},
|
|
{
|
|
"entropy": 6.94871416091919,
|
|
"epoch": 0.07493052798729655,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.000377,
|
|
"loss": 6.7055,
|
|
"mean_token_accuracy": 0.09416541829705238,
|
|
"num_tokens": 1669425.0,
|
|
"step": 755
|
|
},
|
|
{
|
|
"entropy": 7.080055141448975,
|
|
"epoch": 0.07542675664946408,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0003795,
|
|
"loss": 6.6949,
|
|
"mean_token_accuracy": 0.09541306495666504,
|
|
"num_tokens": 1680426.0,
|
|
"step": 760
|
|
},
|
|
{
|
|
"entropy": 7.007839250564575,
|
|
"epoch": 0.0759229853116316,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.000382,
|
|
"loss": 6.7124,
|
|
"mean_token_accuracy": 0.09531945809721946,
|
|
"num_tokens": 1692803.0,
|
|
"step": 765
|
|
},
|
|
{
|
|
"entropy": 7.0682658672332765,
|
|
"epoch": 0.07641921397379912,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0003845,
|
|
"loss": 6.7343,
|
|
"mean_token_accuracy": 0.09483553916215896,
|
|
"num_tokens": 1703919.0,
|
|
"step": 770
|
|
},
|
|
{
|
|
"entropy": 7.002940464019775,
|
|
"epoch": 0.07691544263596665,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00038700000000000003,
|
|
"loss": 6.7095,
|
|
"mean_token_accuracy": 0.10153669938445091,
|
|
"num_tokens": 1714487.0,
|
|
"step": 775
|
|
},
|
|
{
|
|
"entropy": 7.094982624053955,
|
|
"epoch": 0.07741167129813419,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00038950000000000003,
|
|
"loss": 6.7585,
|
|
"mean_token_accuracy": 0.09340820983052253,
|
|
"num_tokens": 1726601.0,
|
|
"step": 780
|
|
},
|
|
{
|
|
"entropy": 7.01391978263855,
|
|
"epoch": 0.0779078999603017,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00039200000000000004,
|
|
"loss": 6.6475,
|
|
"mean_token_accuracy": 0.09487889260053635,
|
|
"num_tokens": 1738743.0,
|
|
"step": 785
|
|
},
|
|
{
|
|
"entropy": 6.975992584228516,
|
|
"epoch": 0.07840412862246923,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00039450000000000005,
|
|
"loss": 6.7308,
|
|
"mean_token_accuracy": 0.0951120376586914,
|
|
"num_tokens": 1748286.0,
|
|
"step": 790
|
|
},
|
|
{
|
|
"entropy": 6.987929821014404,
|
|
"epoch": 0.07890035728463676,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00039700000000000005,
|
|
"loss": 6.7515,
|
|
"mean_token_accuracy": 0.0957480825483799,
|
|
"num_tokens": 1758917.0,
|
|
"step": 795
|
|
},
|
|
{
|
|
"entropy": 6.972993183135986,
|
|
"epoch": 0.0793965859468043,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0003995,
|
|
"loss": 6.5889,
|
|
"mean_token_accuracy": 0.09930885285139084,
|
|
"num_tokens": 1769179.0,
|
|
"step": 800
|
|
},
|
|
{
|
|
"entropy": 6.96280460357666,
|
|
"epoch": 0.07989281460897181,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.000402,
|
|
"loss": 6.7138,
|
|
"mean_token_accuracy": 0.08964183181524277,
|
|
"num_tokens": 1782369.0,
|
|
"step": 805
|
|
},
|
|
{
|
|
"entropy": 6.994895315170288,
|
|
"epoch": 0.08038904327113934,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004045,
|
|
"loss": 6.7162,
|
|
"mean_token_accuracy": 0.10041663944721221,
|
|
"num_tokens": 1795992.0,
|
|
"step": 810
|
|
},
|
|
{
|
|
"entropy": 6.964673948287964,
|
|
"epoch": 0.08088527193330687,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.00040699999999999997,
|
|
"loss": 6.6023,
|
|
"mean_token_accuracy": 0.10524952039122581,
|
|
"num_tokens": 1806938.0,
|
|
"step": 815
|
|
},
|
|
{
|
|
"entropy": 6.863758850097656,
|
|
"epoch": 0.0813815005954744,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004095,
|
|
"loss": 6.5447,
|
|
"mean_token_accuracy": 0.0992793746292591,
|
|
"num_tokens": 1817663.0,
|
|
"step": 820
|
|
},
|
|
{
|
|
"entropy": 6.998508739471435,
|
|
"epoch": 0.08187772925764192,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.000412,
|
|
"loss": 6.6978,
|
|
"mean_token_accuracy": 0.09649931266903877,
|
|
"num_tokens": 1828254.0,
|
|
"step": 825
|
|
},
|
|
{
|
|
"entropy": 6.933160877227783,
|
|
"epoch": 0.08237395791980945,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004145,
|
|
"loss": 6.6293,
|
|
"mean_token_accuracy": 0.09699171110987663,
|
|
"num_tokens": 1839001.0,
|
|
"step": 830
|
|
},
|
|
{
|
|
"entropy": 6.939033889770508,
|
|
"epoch": 0.08287018658197698,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000417,
|
|
"loss": 6.7288,
|
|
"mean_token_accuracy": 0.09662937819957733,
|
|
"num_tokens": 1849906.0,
|
|
"step": 835
|
|
},
|
|
{
|
|
"entropy": 6.815816164016724,
|
|
"epoch": 0.0833664152441445,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004195,
|
|
"loss": 6.6076,
|
|
"mean_token_accuracy": 0.09685141816735268,
|
|
"num_tokens": 1860982.0,
|
|
"step": 840
|
|
},
|
|
{
|
|
"entropy": 7.031003141403199,
|
|
"epoch": 0.08386264390631203,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.000422,
|
|
"loss": 6.5616,
|
|
"mean_token_accuracy": 0.10065253376960755,
|
|
"num_tokens": 1872177.0,
|
|
"step": 845
|
|
},
|
|
{
|
|
"entropy": 6.826659727096557,
|
|
"epoch": 0.08435887256847956,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004245,
|
|
"loss": 6.5362,
|
|
"mean_token_accuracy": 0.0993971161544323,
|
|
"num_tokens": 1882783.0,
|
|
"step": 850
|
|
},
|
|
{
|
|
"entropy": 7.006473255157471,
|
|
"epoch": 0.08485510123064709,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000427,
|
|
"loss": 6.7184,
|
|
"mean_token_accuracy": 0.08898815661668777,
|
|
"num_tokens": 1893706.0,
|
|
"step": 855
|
|
},
|
|
{
|
|
"entropy": 6.823424482345581,
|
|
"epoch": 0.0853513298928146,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004295,
|
|
"loss": 6.5757,
|
|
"mean_token_accuracy": 0.09971656277775764,
|
|
"num_tokens": 1903852.0,
|
|
"step": 860
|
|
},
|
|
{
|
|
"entropy": 6.9098859310150145,
|
|
"epoch": 0.08584755855498213,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.000432,
|
|
"loss": 6.6087,
|
|
"mean_token_accuracy": 0.09987007081508636,
|
|
"num_tokens": 1914157.0,
|
|
"step": 865
|
|
},
|
|
{
|
|
"entropy": 6.880821752548218,
|
|
"epoch": 0.08634378721714966,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004345,
|
|
"loss": 6.5541,
|
|
"mean_token_accuracy": 0.09982468262314796,
|
|
"num_tokens": 1924684.0,
|
|
"step": 870
|
|
},
|
|
{
|
|
"entropy": 6.945840787887573,
|
|
"epoch": 0.0868400158793172,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.000437,
|
|
"loss": 6.7066,
|
|
"mean_token_accuracy": 0.0949609711766243,
|
|
"num_tokens": 1935657.0,
|
|
"step": 875
|
|
},
|
|
{
|
|
"entropy": 6.870462036132812,
|
|
"epoch": 0.08733624454148471,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004395,
|
|
"loss": 6.5897,
|
|
"mean_token_accuracy": 0.09813723415136337,
|
|
"num_tokens": 1946735.0,
|
|
"step": 880
|
|
},
|
|
{
|
|
"entropy": 6.932937145233154,
|
|
"epoch": 0.08783247320365224,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000442,
|
|
"loss": 6.7502,
|
|
"mean_token_accuracy": 0.09312896803021431,
|
|
"num_tokens": 1957871.0,
|
|
"step": 885
|
|
},
|
|
{
|
|
"entropy": 6.838114881515503,
|
|
"epoch": 0.08832870186581977,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004445,
|
|
"loss": 6.5663,
|
|
"mean_token_accuracy": 0.10240828990936279,
|
|
"num_tokens": 1969032.0,
|
|
"step": 890
|
|
},
|
|
{
|
|
"entropy": 6.92586464881897,
|
|
"epoch": 0.0888249305279873,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.000447,
|
|
"loss": 6.6063,
|
|
"mean_token_accuracy": 0.09725166410207749,
|
|
"num_tokens": 1980212.0,
|
|
"step": 895
|
|
},
|
|
{
|
|
"entropy": 6.780085325241089,
|
|
"epoch": 0.08932115919015482,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00044950000000000003,
|
|
"loss": 6.5267,
|
|
"mean_token_accuracy": 0.10072881132364273,
|
|
"num_tokens": 1990333.0,
|
|
"step": 900
|
|
},
|
|
{
|
|
"entropy": 6.879197597503662,
|
|
"epoch": 0.08981738785232235,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00045200000000000004,
|
|
"loss": 6.6025,
|
|
"mean_token_accuracy": 0.10396269112825393,
|
|
"num_tokens": 2001486.0,
|
|
"step": 905
|
|
},
|
|
{
|
|
"entropy": 6.857023143768311,
|
|
"epoch": 0.09031361651448988,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00045450000000000004,
|
|
"loss": 6.5679,
|
|
"mean_token_accuracy": 0.1022559143602848,
|
|
"num_tokens": 2012535.0,
|
|
"step": 910
|
|
},
|
|
{
|
|
"entropy": 6.766489458084107,
|
|
"epoch": 0.0908098451766574,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00045700000000000005,
|
|
"loss": 6.5318,
|
|
"mean_token_accuracy": 0.10583447441458702,
|
|
"num_tokens": 2024116.0,
|
|
"step": 915
|
|
},
|
|
{
|
|
"entropy": 6.746376848220825,
|
|
"epoch": 0.09130607383882493,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.00045950000000000006,
|
|
"loss": 6.5749,
|
|
"mean_token_accuracy": 0.09981027767062187,
|
|
"num_tokens": 2036341.0,
|
|
"step": 920
|
|
},
|
|
{
|
|
"entropy": 6.938368415832519,
|
|
"epoch": 0.09180230250099246,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.000462,
|
|
"loss": 6.5504,
|
|
"mean_token_accuracy": 0.10081811845302582,
|
|
"num_tokens": 2046768.0,
|
|
"step": 925
|
|
},
|
|
{
|
|
"entropy": 6.7602132797241214,
|
|
"epoch": 0.09229853116315999,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004645,
|
|
"loss": 6.5178,
|
|
"mean_token_accuracy": 0.09979332089424134,
|
|
"num_tokens": 2057315.0,
|
|
"step": 930
|
|
},
|
|
{
|
|
"entropy": 6.767438125610352,
|
|
"epoch": 0.0927947598253275,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000467,
|
|
"loss": 6.4968,
|
|
"mean_token_accuracy": 0.10354413539171219,
|
|
"num_tokens": 2068267.0,
|
|
"step": 935
|
|
},
|
|
{
|
|
"entropy": 6.767202854156494,
|
|
"epoch": 0.09329098848749504,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004695,
|
|
"loss": 6.5673,
|
|
"mean_token_accuracy": 0.10121043622493744,
|
|
"num_tokens": 2078271.0,
|
|
"step": 940
|
|
},
|
|
{
|
|
"entropy": 6.74484601020813,
|
|
"epoch": 0.09378721714966257,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000472,
|
|
"loss": 6.4897,
|
|
"mean_token_accuracy": 0.09888025969266892,
|
|
"num_tokens": 2088381.0,
|
|
"step": 945
|
|
},
|
|
{
|
|
"entropy": 6.789056253433228,
|
|
"epoch": 0.0942834458118301,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004745,
|
|
"loss": 6.451,
|
|
"mean_token_accuracy": 0.09835516735911369,
|
|
"num_tokens": 2098899.0,
|
|
"step": 950
|
|
},
|
|
{
|
|
"entropy": 6.749150371551513,
|
|
"epoch": 0.09477967447399761,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000477,
|
|
"loss": 6.5972,
|
|
"mean_token_accuracy": 0.09927409738302231,
|
|
"num_tokens": 2110057.0,
|
|
"step": 955
|
|
},
|
|
{
|
|
"entropy": 6.713812303543091,
|
|
"epoch": 0.09527590313616514,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004795,
|
|
"loss": 6.5065,
|
|
"mean_token_accuracy": 0.09916102886199951,
|
|
"num_tokens": 2121758.0,
|
|
"step": 960
|
|
},
|
|
{
|
|
"entropy": 6.771513843536377,
|
|
"epoch": 0.09577213179833267,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.000482,
|
|
"loss": 6.5131,
|
|
"mean_token_accuracy": 0.10310358032584191,
|
|
"num_tokens": 2131840.0,
|
|
"step": 965
|
|
},
|
|
{
|
|
"entropy": 6.744855642318726,
|
|
"epoch": 0.0962683604605002,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004845,
|
|
"loss": 6.5007,
|
|
"mean_token_accuracy": 0.1013672724366188,
|
|
"num_tokens": 2142084.0,
|
|
"step": 970
|
|
},
|
|
{
|
|
"entropy": 6.749075984954834,
|
|
"epoch": 0.09676458912266772,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000487,
|
|
"loss": 6.5483,
|
|
"mean_token_accuracy": 0.10051179081201553,
|
|
"num_tokens": 2152785.0,
|
|
"step": 975
|
|
},
|
|
{
|
|
"entropy": 6.751393842697143,
|
|
"epoch": 0.09726081778483525,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004895,
|
|
"loss": 6.5224,
|
|
"mean_token_accuracy": 0.1026117317378521,
|
|
"num_tokens": 2163774.0,
|
|
"step": 980
|
|
},
|
|
{
|
|
"entropy": 6.7088648796081545,
|
|
"epoch": 0.09775704644700278,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.000492,
|
|
"loss": 6.4589,
|
|
"mean_token_accuracy": 0.10463614240288735,
|
|
"num_tokens": 2175378.0,
|
|
"step": 985
|
|
},
|
|
{
|
|
"entropy": 6.910195636749267,
|
|
"epoch": 0.0982532751091703,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004945,
|
|
"loss": 6.6604,
|
|
"mean_token_accuracy": 0.09883119091391564,
|
|
"num_tokens": 2186510.0,
|
|
"step": 990
|
|
},
|
|
{
|
|
"entropy": 6.734104061126709,
|
|
"epoch": 0.09874950377133783,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.000497,
|
|
"loss": 6.4553,
|
|
"mean_token_accuracy": 0.10956107974052429,
|
|
"num_tokens": 2197482.0,
|
|
"step": 995
|
|
},
|
|
{
|
|
"entropy": 6.622636842727661,
|
|
"epoch": 0.09924573243350536,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004995,
|
|
"loss": 6.4604,
|
|
"mean_token_accuracy": 0.10386316254734992,
|
|
"num_tokens": 2208329.0,
|
|
"step": 1000
|
|
},
|
|
{
|
|
"entropy": 6.609873104095459,
|
|
"epoch": 0.09974196109567289,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004999999982145551,
|
|
"loss": 6.362,
|
|
"mean_token_accuracy": 0.10516428351402282,
|
|
"num_tokens": 2218632.0,
|
|
"step": 1005
|
|
},
|
|
{
|
|
"entropy": 6.709473085403443,
|
|
"epoch": 0.1002381897578404,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004999999909611855,
|
|
"loss": 6.4814,
|
|
"mean_token_accuracy": 0.09935311302542686,
|
|
"num_tokens": 2231335.0,
|
|
"step": 1010
|
|
},
|
|
{
|
|
"entropy": 6.6939784526824955,
|
|
"epoch": 0.10073441842000794,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999999781283008,
|
|
"loss": 6.4733,
|
|
"mean_token_accuracy": 0.10079516991972923,
|
|
"num_tokens": 2241704.0,
|
|
"step": 1015
|
|
},
|
|
{
|
|
"entropy": 6.665507650375366,
|
|
"epoch": 0.10123064708217547,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004999999597159017,
|
|
"loss": 6.505,
|
|
"mean_token_accuracy": 0.1012033224105835,
|
|
"num_tokens": 2252310.0,
|
|
"step": 1020
|
|
},
|
|
{
|
|
"entropy": 6.7658100605010985,
|
|
"epoch": 0.101726875744343,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999999357239882,
|
|
"loss": 6.4323,
|
|
"mean_token_accuracy": 0.10344030633568764,
|
|
"num_tokens": 2262270.0,
|
|
"step": 1025
|
|
},
|
|
{
|
|
"entropy": 6.723705816268921,
|
|
"epoch": 0.10222310440651051,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004999999061525612,
|
|
"loss": 6.5677,
|
|
"mean_token_accuracy": 0.10005603730678558,
|
|
"num_tokens": 2273986.0,
|
|
"step": 1030
|
|
},
|
|
{
|
|
"entropy": 6.7837742328643795,
|
|
"epoch": 0.10271933306867805,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999998710016214,
|
|
"loss": 6.4629,
|
|
"mean_token_accuracy": 0.10525803044438362,
|
|
"num_tokens": 2283430.0,
|
|
"step": 1035
|
|
},
|
|
{
|
|
"entropy": 6.677142333984375,
|
|
"epoch": 0.10321556173084558,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004999998302711696,
|
|
"loss": 6.4669,
|
|
"mean_token_accuracy": 0.10035635456442833,
|
|
"num_tokens": 2294201.0,
|
|
"step": 1040
|
|
},
|
|
{
|
|
"entropy": 6.609557294845581,
|
|
"epoch": 0.1037117903930131,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004999997839612069,
|
|
"loss": 6.3612,
|
|
"mean_token_accuracy": 0.1090113341808319,
|
|
"num_tokens": 2303876.0,
|
|
"step": 1045
|
|
},
|
|
{
|
|
"entropy": 6.626906967163086,
|
|
"epoch": 0.10420801905518062,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004999997320717342,
|
|
"loss": 6.4015,
|
|
"mean_token_accuracy": 0.10890848338603973,
|
|
"num_tokens": 2313713.0,
|
|
"step": 1050
|
|
},
|
|
{
|
|
"entropy": 6.605928659439087,
|
|
"epoch": 0.10470424771734815,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004999996746027531,
|
|
"loss": 6.4148,
|
|
"mean_token_accuracy": 0.10125040039420127,
|
|
"num_tokens": 2324862.0,
|
|
"step": 1055
|
|
},
|
|
{
|
|
"entropy": 6.717818832397461,
|
|
"epoch": 0.10520047637951568,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000499999611554265,
|
|
"loss": 6.4953,
|
|
"mean_token_accuracy": 0.10330296978354454,
|
|
"num_tokens": 2334974.0,
|
|
"step": 1060
|
|
},
|
|
{
|
|
"entropy": 6.62673773765564,
|
|
"epoch": 0.10569670504168321,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004999995429262712,
|
|
"loss": 6.5196,
|
|
"mean_token_accuracy": 0.10395341366529465,
|
|
"num_tokens": 2345945.0,
|
|
"step": 1065
|
|
},
|
|
{
|
|
"entropy": 6.722126197814942,
|
|
"epoch": 0.10619293370385073,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999994687187737,
|
|
"loss": 6.4608,
|
|
"mean_token_accuracy": 0.10263997614383698,
|
|
"num_tokens": 2356749.0,
|
|
"step": 1070
|
|
},
|
|
{
|
|
"entropy": 6.70174617767334,
|
|
"epoch": 0.10668916236601826,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004999993889317742,
|
|
"loss": 6.5289,
|
|
"mean_token_accuracy": 0.10041191279888154,
|
|
"num_tokens": 2368181.0,
|
|
"step": 1075
|
|
},
|
|
{
|
|
"entropy": 6.65612006187439,
|
|
"epoch": 0.10718539102818579,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999993035652746,
|
|
"loss": 6.432,
|
|
"mean_token_accuracy": 0.10550632029771805,
|
|
"num_tokens": 2377737.0,
|
|
"step": 1080
|
|
},
|
|
{
|
|
"entropy": 6.570956897735596,
|
|
"epoch": 0.10768161969035331,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004999992126192771,
|
|
"loss": 6.3551,
|
|
"mean_token_accuracy": 0.10739153623580933,
|
|
"num_tokens": 2388944.0,
|
|
"step": 1085
|
|
},
|
|
{
|
|
"entropy": 6.695246934890747,
|
|
"epoch": 0.10817784835252084,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.000499999116093784,
|
|
"loss": 6.4357,
|
|
"mean_token_accuracy": 0.10068753212690354,
|
|
"num_tokens": 2400758.0,
|
|
"step": 1090
|
|
},
|
|
{
|
|
"entropy": 6.534470844268799,
|
|
"epoch": 0.10867407701468837,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004999990139887976,
|
|
"loss": 6.4253,
|
|
"mean_token_accuracy": 0.10705526322126388,
|
|
"num_tokens": 2411916.0,
|
|
"step": 1095
|
|
},
|
|
{
|
|
"entropy": 6.811460256576538,
|
|
"epoch": 0.1091703056768559,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004999989063043206,
|
|
"loss": 6.463,
|
|
"mean_token_accuracy": 0.10148089230060578,
|
|
"num_tokens": 2423310.0,
|
|
"step": 1100
|
|
},
|
|
{
|
|
"entropy": 6.5493433475494385,
|
|
"epoch": 0.10966653433902342,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999987930403555,
|
|
"loss": 6.3854,
|
|
"mean_token_accuracy": 0.10383407324552536,
|
|
"num_tokens": 2432100.0,
|
|
"step": 1105
|
|
},
|
|
{
|
|
"entropy": 6.6149815082550045,
|
|
"epoch": 0.11016276300119095,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004999986741969051,
|
|
"loss": 6.4639,
|
|
"mean_token_accuracy": 0.10388477817177773,
|
|
"num_tokens": 2443563.0,
|
|
"step": 1110
|
|
},
|
|
{
|
|
"entropy": 6.726413249969482,
|
|
"epoch": 0.11065899166335848,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999985497739724,
|
|
"loss": 6.4566,
|
|
"mean_token_accuracy": 0.10313622802495956,
|
|
"num_tokens": 2455435.0,
|
|
"step": 1115
|
|
},
|
|
{
|
|
"entropy": 6.534851551055908,
|
|
"epoch": 0.11115522032552601,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004999984197715606,
|
|
"loss": 6.3981,
|
|
"mean_token_accuracy": 0.10903462842106819,
|
|
"num_tokens": 2466173.0,
|
|
"step": 1120
|
|
},
|
|
{
|
|
"entropy": 6.549497175216675,
|
|
"epoch": 0.11165144898769352,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004999982841896728,
|
|
"loss": 6.3521,
|
|
"mean_token_accuracy": 0.10385128781199456,
|
|
"num_tokens": 2476349.0,
|
|
"step": 1125
|
|
},
|
|
{
|
|
"entropy": 6.66382737159729,
|
|
"epoch": 0.11214767764986106,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004999981430283123,
|
|
"loss": 6.4763,
|
|
"mean_token_accuracy": 0.10946066528558732,
|
|
"num_tokens": 2487864.0,
|
|
"step": 1130
|
|
},
|
|
{
|
|
"entropy": 6.5958610534667965,
|
|
"epoch": 0.11264390631202859,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004999979962874827,
|
|
"loss": 6.4164,
|
|
"mean_token_accuracy": 0.10289325043559075,
|
|
"num_tokens": 2499188.0,
|
|
"step": 1135
|
|
},
|
|
{
|
|
"entropy": 6.616852045059204,
|
|
"epoch": 0.11314013497419612,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004999978439671877,
|
|
"loss": 6.3896,
|
|
"mean_token_accuracy": 0.10375408679246903,
|
|
"num_tokens": 2509813.0,
|
|
"step": 1140
|
|
},
|
|
{
|
|
"entropy": 6.66924524307251,
|
|
"epoch": 0.11363636363636363,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.0004999976860674309,
|
|
"loss": 6.4185,
|
|
"mean_token_accuracy": 0.10202216356992722,
|
|
"num_tokens": 2520813.0,
|
|
"step": 1145
|
|
},
|
|
{
|
|
"entropy": 6.483026504516602,
|
|
"epoch": 0.11413259229853116,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004999975225882164,
|
|
"loss": 6.4173,
|
|
"mean_token_accuracy": 0.1033550575375557,
|
|
"num_tokens": 2531802.0,
|
|
"step": 1150
|
|
},
|
|
{
|
|
"entropy": 6.586180353164673,
|
|
"epoch": 0.1146288209606987,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000499997353529548,
|
|
"loss": 6.2121,
|
|
"mean_token_accuracy": 0.1153721533715725,
|
|
"num_tokens": 2541935.0,
|
|
"step": 1155
|
|
},
|
|
{
|
|
"entropy": 6.49102201461792,
|
|
"epoch": 0.11512504962286621,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004999971788914303,
|
|
"loss": 6.3252,
|
|
"mean_token_accuracy": 0.10732494816184043,
|
|
"num_tokens": 2553224.0,
|
|
"step": 1160
|
|
},
|
|
{
|
|
"entropy": 6.557978200912475,
|
|
"epoch": 0.11562127828503374,
|
|
"grad_norm": 0.7421875,
|
|
"learning_rate": 0.0004999969986738672,
|
|
"loss": 6.3578,
|
|
"mean_token_accuracy": 0.10425093993544579,
|
|
"num_tokens": 2565355.0,
|
|
"step": 1165
|
|
},
|
|
{
|
|
"entropy": 6.631026411056519,
|
|
"epoch": 0.11611750694720127,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999968128768634,
|
|
"loss": 6.4405,
|
|
"mean_token_accuracy": 0.10526153668761254,
|
|
"num_tokens": 2575962.0,
|
|
"step": 1170
|
|
},
|
|
{
|
|
"entropy": 6.586783170700073,
|
|
"epoch": 0.1166137356093688,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004999966215004236,
|
|
"loss": 6.4478,
|
|
"mean_token_accuracy": 0.11039511635899543,
|
|
"num_tokens": 2588136.0,
|
|
"step": 1175
|
|
},
|
|
{
|
|
"entropy": 6.563306188583374,
|
|
"epoch": 0.11710996427153632,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004999964245445522,
|
|
"loss": 6.3313,
|
|
"mean_token_accuracy": 0.10910526439547538,
|
|
"num_tokens": 2597785.0,
|
|
"step": 1180
|
|
},
|
|
{
|
|
"entropy": 6.518818330764771,
|
|
"epoch": 0.11760619293370385,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004999962220092545,
|
|
"loss": 6.3785,
|
|
"mean_token_accuracy": 0.11630177646875381,
|
|
"num_tokens": 2609738.0,
|
|
"step": 1185
|
|
},
|
|
{
|
|
"entropy": 6.455830097198486,
|
|
"epoch": 0.11810242159587138,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0004999960138945351,
|
|
"loss": 6.2671,
|
|
"mean_token_accuracy": 0.11771797314286232,
|
|
"num_tokens": 2620179.0,
|
|
"step": 1190
|
|
},
|
|
{
|
|
"entropy": 6.5756360530853275,
|
|
"epoch": 0.11859865025803891,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004999958002003996,
|
|
"loss": 6.3035,
|
|
"mean_token_accuracy": 0.11005059778690338,
|
|
"num_tokens": 2631550.0,
|
|
"step": 1195
|
|
},
|
|
{
|
|
"entropy": 6.5420623302459715,
|
|
"epoch": 0.11909487892020643,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004999955809268529,
|
|
"loss": 6.3474,
|
|
"mean_token_accuracy": 0.1102082036435604,
|
|
"num_tokens": 2642467.0,
|
|
"step": 1200
|
|
},
|
|
{
|
|
"entropy": 6.430347681045532,
|
|
"epoch": 0.11959110758237396,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999953560739008,
|
|
"loss": 6.3182,
|
|
"mean_token_accuracy": 0.1130327932536602,
|
|
"num_tokens": 2652132.0,
|
|
"step": 1205
|
|
},
|
|
{
|
|
"entropy": 6.609172010421753,
|
|
"epoch": 0.12008733624454149,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.0004999951256415485,
|
|
"loss": 6.3786,
|
|
"mean_token_accuracy": 0.1051353357732296,
|
|
"num_tokens": 2663336.0,
|
|
"step": 1210
|
|
},
|
|
{
|
|
"entropy": 6.602077627182007,
|
|
"epoch": 0.12058356490670902,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.000499994889629802,
|
|
"loss": 6.4557,
|
|
"mean_token_accuracy": 0.09855944886803628,
|
|
"num_tokens": 2674201.0,
|
|
"step": 1215
|
|
},
|
|
{
|
|
"entropy": 6.591161394119263,
|
|
"epoch": 0.12107979356887653,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.000499994648038667,
|
|
"loss": 6.3755,
|
|
"mean_token_accuracy": 0.11215761303901672,
|
|
"num_tokens": 2685073.0,
|
|
"step": 1220
|
|
},
|
|
{
|
|
"entropy": 6.588635969161987,
|
|
"epoch": 0.12157602223104406,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004999944008681496,
|
|
"loss": 6.3189,
|
|
"mean_token_accuracy": 0.11205925047397614,
|
|
"num_tokens": 2695024.0,
|
|
"step": 1225
|
|
},
|
|
{
|
|
"entropy": 6.502772092819214,
|
|
"epoch": 0.1220722508932116,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004999941481182559,
|
|
"loss": 6.4082,
|
|
"mean_token_accuracy": 0.10132400244474411,
|
|
"num_tokens": 2706232.0,
|
|
"step": 1230
|
|
},
|
|
{
|
|
"entropy": 6.634514093399048,
|
|
"epoch": 0.12256847955537911,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999938897889921,
|
|
"loss": 6.3776,
|
|
"mean_token_accuracy": 0.11380477249622345,
|
|
"num_tokens": 2715874.0,
|
|
"step": 1235
|
|
},
|
|
{
|
|
"entropy": 6.467554330825806,
|
|
"epoch": 0.12306470821754664,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.0004999936258803647,
|
|
"loss": 6.3171,
|
|
"mean_token_accuracy": 0.11320996284484863,
|
|
"num_tokens": 2727409.0,
|
|
"step": 1240
|
|
},
|
|
{
|
|
"entropy": 6.4485221862792965,
|
|
"epoch": 0.12356093687971417,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004999933563923802,
|
|
"loss": 6.2336,
|
|
"mean_token_accuracy": 0.11560766994953156,
|
|
"num_tokens": 2737259.0,
|
|
"step": 1245
|
|
},
|
|
{
|
|
"entropy": 6.5671069622039795,
|
|
"epoch": 0.1240571655418817,
|
|
"grad_norm": 0.7734375,
|
|
"learning_rate": 0.0004999930813250451,
|
|
"loss": 6.3636,
|
|
"mean_token_accuracy": 0.10681080147624016,
|
|
"num_tokens": 2748416.0,
|
|
"step": 1250
|
|
},
|
|
{
|
|
"entropy": 6.504324531555175,
|
|
"epoch": 0.12455339420404922,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004999928006783667,
|
|
"loss": 6.3299,
|
|
"mean_token_accuracy": 0.10958396941423416,
|
|
"num_tokens": 2760470.0,
|
|
"step": 1255
|
|
},
|
|
{
|
|
"entropy": 6.538706254959107,
|
|
"epoch": 0.12504962286621676,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004999925144523515,
|
|
"loss": 6.3608,
|
|
"mean_token_accuracy": 0.10441428348422051,
|
|
"num_tokens": 2770222.0,
|
|
"step": 1260
|
|
},
|
|
{
|
|
"entropy": 6.533433151245117,
|
|
"epoch": 0.12554585152838427,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004999922226470066,
|
|
"loss": 6.2804,
|
|
"mean_token_accuracy": 0.10863575115799903,
|
|
"num_tokens": 2780212.0,
|
|
"step": 1265
|
|
},
|
|
{
|
|
"entropy": 6.4365581512451175,
|
|
"epoch": 0.1260420801905518,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004999919252623397,
|
|
"loss": 6.2603,
|
|
"mean_token_accuracy": 0.11084286272525787,
|
|
"num_tokens": 2790239.0,
|
|
"step": 1270
|
|
},
|
|
{
|
|
"entropy": 6.580913019180298,
|
|
"epoch": 0.12653830885271933,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999916222983577,
|
|
"loss": 6.2971,
|
|
"mean_token_accuracy": 0.1081952191889286,
|
|
"num_tokens": 2801902.0,
|
|
"step": 1275
|
|
},
|
|
{
|
|
"entropy": 6.360956907272339,
|
|
"epoch": 0.12703453751488686,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004999913137550682,
|
|
"loss": 6.2987,
|
|
"mean_token_accuracy": 0.10948901474475861,
|
|
"num_tokens": 2813268.0,
|
|
"step": 1280
|
|
},
|
|
{
|
|
"entropy": 6.5253222465515135,
|
|
"epoch": 0.1275307661770544,
|
|
"grad_norm": 0.80078125,
|
|
"learning_rate": 0.0004999909996324791,
|
|
"loss": 6.3583,
|
|
"mean_token_accuracy": 0.1083506740629673,
|
|
"num_tokens": 2824506.0,
|
|
"step": 1285
|
|
},
|
|
{
|
|
"entropy": 6.4849005222320555,
|
|
"epoch": 0.12802699483922192,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.000499990679930598,
|
|
"loss": 6.2729,
|
|
"mean_token_accuracy": 0.11370046511292457,
|
|
"num_tokens": 2835144.0,
|
|
"step": 1290
|
|
},
|
|
{
|
|
"entropy": 6.4290557384490965,
|
|
"epoch": 0.12852322350138945,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004999903546494327,
|
|
"loss": 6.2832,
|
|
"mean_token_accuracy": 0.1095927357673645,
|
|
"num_tokens": 2845382.0,
|
|
"step": 1295
|
|
},
|
|
{
|
|
"entropy": 6.500859642028809,
|
|
"epoch": 0.12901945216355698,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004999900237889916,
|
|
"loss": 6.2942,
|
|
"mean_token_accuracy": 0.11329072564840317,
|
|
"num_tokens": 2854697.0,
|
|
"step": 1300
|
|
},
|
|
{
|
|
"entropy": 6.496008634567261,
|
|
"epoch": 0.12951568082572448,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004999896873492827,
|
|
"loss": 6.313,
|
|
"mean_token_accuracy": 0.10269764885306358,
|
|
"num_tokens": 2866216.0,
|
|
"step": 1305
|
|
},
|
|
{
|
|
"entropy": 6.478988075256348,
|
|
"epoch": 0.130011909487892,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004999893453303143,
|
|
"loss": 6.2662,
|
|
"mean_token_accuracy": 0.11140501946210861,
|
|
"num_tokens": 2877734.0,
|
|
"step": 1310
|
|
},
|
|
{
|
|
"entropy": 6.496612596511841,
|
|
"epoch": 0.13050813815005954,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004999889977320949,
|
|
"loss": 6.3097,
|
|
"mean_token_accuracy": 0.11451938673853874,
|
|
"num_tokens": 2889445.0,
|
|
"step": 1315
|
|
},
|
|
{
|
|
"entropy": 6.386645030975342,
|
|
"epoch": 0.13100436681222707,
|
|
"grad_norm": 0.796875,
|
|
"learning_rate": 0.0004999886445546332,
|
|
"loss": 6.2526,
|
|
"mean_token_accuracy": 0.117067901045084,
|
|
"num_tokens": 2900485.0,
|
|
"step": 1320
|
|
},
|
|
{
|
|
"entropy": 6.536042022705078,
|
|
"epoch": 0.1315005954743946,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.000499988285797938,
|
|
"loss": 6.2462,
|
|
"mean_token_accuracy": 0.11725969165563584,
|
|
"num_tokens": 2909795.0,
|
|
"step": 1325
|
|
},
|
|
{
|
|
"entropy": 6.310559272766113,
|
|
"epoch": 0.13199682413656214,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.000499987921462018,
|
|
"loss": 6.2739,
|
|
"mean_token_accuracy": 0.120875982940197,
|
|
"num_tokens": 2920153.0,
|
|
"step": 1330
|
|
},
|
|
{
|
|
"entropy": 6.545910024642945,
|
|
"epoch": 0.13249305279872967,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004999875515468825,
|
|
"loss": 6.2668,
|
|
"mean_token_accuracy": 0.11391363963484764,
|
|
"num_tokens": 2930457.0,
|
|
"step": 1335
|
|
},
|
|
{
|
|
"entropy": 6.387372589111328,
|
|
"epoch": 0.13298928146089717,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004999871760525403,
|
|
"loss": 6.3293,
|
|
"mean_token_accuracy": 0.11570871099829674,
|
|
"num_tokens": 2941305.0,
|
|
"step": 1340
|
|
},
|
|
{
|
|
"entropy": 6.462648534774781,
|
|
"epoch": 0.1334855101230647,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999867949790011,
|
|
"loss": 6.2594,
|
|
"mean_token_accuracy": 0.11346142515540122,
|
|
"num_tokens": 2951798.0,
|
|
"step": 1345
|
|
},
|
|
{
|
|
"entropy": 6.408753728866577,
|
|
"epoch": 0.13398173878523223,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004999864083262743,
|
|
"loss": 6.1704,
|
|
"mean_token_accuracy": 0.11709224805235863,
|
|
"num_tokens": 2962486.0,
|
|
"step": 1350
|
|
},
|
|
{
|
|
"entropy": 6.384300184249878,
|
|
"epoch": 0.13447796744739976,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004999860160943691,
|
|
"loss": 6.2681,
|
|
"mean_token_accuracy": 0.11269479319453239,
|
|
"num_tokens": 2974317.0,
|
|
"step": 1355
|
|
},
|
|
{
|
|
"entropy": 6.450789546966552,
|
|
"epoch": 0.1349741961095673,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004999856182832958,
|
|
"loss": 6.1904,
|
|
"mean_token_accuracy": 0.11520234048366547,
|
|
"num_tokens": 2985440.0,
|
|
"step": 1360
|
|
},
|
|
{
|
|
"entropy": 6.400120830535888,
|
|
"epoch": 0.13547042477173482,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004999852148930637,
|
|
"loss": 6.2605,
|
|
"mean_token_accuracy": 0.10958047136664391,
|
|
"num_tokens": 2997044.0,
|
|
"step": 1365
|
|
},
|
|
{
|
|
"entropy": 6.447021579742431,
|
|
"epoch": 0.13596665343390235,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999848059236832,
|
|
"loss": 6.2687,
|
|
"mean_token_accuracy": 0.1083021655678749,
|
|
"num_tokens": 3005965.0,
|
|
"step": 1370
|
|
},
|
|
{
|
|
"entropy": 6.3724065780639645,
|
|
"epoch": 0.13646288209606988,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004999843913751643,
|
|
"loss": 6.1383,
|
|
"mean_token_accuracy": 0.11827749311923981,
|
|
"num_tokens": 3015031.0,
|
|
"step": 1375
|
|
},
|
|
{
|
|
"entropy": 6.378967905044556,
|
|
"epoch": 0.13695911075823738,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004999839712475174,
|
|
"loss": 6.2074,
|
|
"mean_token_accuracy": 0.1124014399945736,
|
|
"num_tokens": 3026275.0,
|
|
"step": 1380
|
|
},
|
|
{
|
|
"entropy": 6.385042381286621,
|
|
"epoch": 0.13745533942040492,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004999835455407526,
|
|
"loss": 6.2493,
|
|
"mean_token_accuracy": 0.11228244602680207,
|
|
"num_tokens": 3036778.0,
|
|
"step": 1385
|
|
},
|
|
{
|
|
"entropy": 6.488673353195191,
|
|
"epoch": 0.13795156808257245,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004999831142548808,
|
|
"loss": 6.3516,
|
|
"mean_token_accuracy": 0.11366798952221871,
|
|
"num_tokens": 3048149.0,
|
|
"step": 1390
|
|
},
|
|
{
|
|
"entropy": 6.426563882827759,
|
|
"epoch": 0.13844779674473998,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004999826773899124,
|
|
"loss": 6.2154,
|
|
"mean_token_accuracy": 0.11358957141637802,
|
|
"num_tokens": 3059149.0,
|
|
"step": 1395
|
|
},
|
|
{
|
|
"entropy": 6.404417276382446,
|
|
"epoch": 0.1389440254069075,
|
|
"grad_norm": 0.74609375,
|
|
"learning_rate": 0.0004999822349458586,
|
|
"loss": 6.2257,
|
|
"mean_token_accuracy": 0.11496646702289581,
|
|
"num_tokens": 3071613.0,
|
|
"step": 1400
|
|
},
|
|
{
|
|
"entropy": 6.5001030445098875,
|
|
"epoch": 0.13944025406907504,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004999817869227301,
|
|
"loss": 6.369,
|
|
"mean_token_accuracy": 0.1097478836774826,
|
|
"num_tokens": 3084742.0,
|
|
"step": 1405
|
|
},
|
|
{
|
|
"entropy": 6.461193561553955,
|
|
"epoch": 0.13993648273124257,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999813333205381,
|
|
"loss": 6.2857,
|
|
"mean_token_accuracy": 0.11472547352313996,
|
|
"num_tokens": 3095356.0,
|
|
"step": 1410
|
|
},
|
|
{
|
|
"entropy": 6.409702301025391,
|
|
"epoch": 0.14043271139341007,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004999808741392937,
|
|
"loss": 6.2669,
|
|
"mean_token_accuracy": 0.10798696279525757,
|
|
"num_tokens": 3107717.0,
|
|
"step": 1415
|
|
},
|
|
{
|
|
"entropy": 6.36297869682312,
|
|
"epoch": 0.1409289400555776,
|
|
"grad_norm": 0.80078125,
|
|
"learning_rate": 0.0004999804093790086,
|
|
"loss": 6.2518,
|
|
"mean_token_accuracy": 0.1127444364130497,
|
|
"num_tokens": 3119205.0,
|
|
"step": 1420
|
|
},
|
|
{
|
|
"entropy": 6.448381614685059,
|
|
"epoch": 0.14142516871774513,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.000499979939039694,
|
|
"loss": 6.3038,
|
|
"mean_token_accuracy": 0.11262011229991913,
|
|
"num_tokens": 3130564.0,
|
|
"step": 1425
|
|
},
|
|
{
|
|
"entropy": 6.450186538696289,
|
|
"epoch": 0.14192139737991266,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004999794631213618,
|
|
"loss": 6.2395,
|
|
"mean_token_accuracy": 0.11082697659730911,
|
|
"num_tokens": 3141883.0,
|
|
"step": 1430
|
|
},
|
|
{
|
|
"entropy": 6.420169115066528,
|
|
"epoch": 0.1424176260420802,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004999789816240236,
|
|
"loss": 6.2394,
|
|
"mean_token_accuracy": 0.10963290259242058,
|
|
"num_tokens": 3152817.0,
|
|
"step": 1435
|
|
},
|
|
{
|
|
"entropy": 6.358748054504394,
|
|
"epoch": 0.14291385470424772,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999784945476915,
|
|
"loss": 6.1567,
|
|
"mean_token_accuracy": 0.11966277733445167,
|
|
"num_tokens": 3163546.0,
|
|
"step": 1440
|
|
},
|
|
{
|
|
"entropy": 6.412687873840332,
|
|
"epoch": 0.14341008336641525,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999780018923775,
|
|
"loss": 6.207,
|
|
"mean_token_accuracy": 0.10822459608316422,
|
|
"num_tokens": 3173899.0,
|
|
"step": 1445
|
|
},
|
|
{
|
|
"entropy": 6.287933111190796,
|
|
"epoch": 0.14390631202858278,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004999775036580939,
|
|
"loss": 6.11,
|
|
"mean_token_accuracy": 0.11830191910266877,
|
|
"num_tokens": 3184433.0,
|
|
"step": 1450
|
|
},
|
|
{
|
|
"entropy": 6.4349367141723635,
|
|
"epoch": 0.1444025406907503,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004999769998448529,
|
|
"loss": 6.22,
|
|
"mean_token_accuracy": 0.11617036014795304,
|
|
"num_tokens": 3196077.0,
|
|
"step": 1455
|
|
},
|
|
{
|
|
"entropy": 6.256659460067749,
|
|
"epoch": 0.14489876935291782,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004999764904526672,
|
|
"loss": 6.1422,
|
|
"mean_token_accuracy": 0.11813490390777588,
|
|
"num_tokens": 3206645.0,
|
|
"step": 1460
|
|
},
|
|
{
|
|
"entropy": 6.442942762374878,
|
|
"epoch": 0.14539499801508535,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004999759754815492,
|
|
"loss": 6.2781,
|
|
"mean_token_accuracy": 0.11664444580674171,
|
|
"num_tokens": 3216786.0,
|
|
"step": 1465
|
|
},
|
|
{
|
|
"entropy": 6.370675897598266,
|
|
"epoch": 0.14589122667725288,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004999754549315118,
|
|
"loss": 6.1909,
|
|
"mean_token_accuracy": 0.11156717166304589,
|
|
"num_tokens": 3227384.0,
|
|
"step": 1470
|
|
},
|
|
{
|
|
"entropy": 6.271988248825073,
|
|
"epoch": 0.1463874553394204,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.000499974928802568,
|
|
"loss": 6.0496,
|
|
"mean_token_accuracy": 0.1194495476782322,
|
|
"num_tokens": 3238800.0,
|
|
"step": 1475
|
|
},
|
|
{
|
|
"entropy": 6.343875980377197,
|
|
"epoch": 0.14688368400158794,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004999743970947306,
|
|
"loss": 6.1983,
|
|
"mean_token_accuracy": 0.11200206577777863,
|
|
"num_tokens": 3248627.0,
|
|
"step": 1480
|
|
},
|
|
{
|
|
"entropy": 6.364979076385498,
|
|
"epoch": 0.14737991266375547,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.000499973859808013,
|
|
"loss": 6.2264,
|
|
"mean_token_accuracy": 0.11476045995950698,
|
|
"num_tokens": 3258989.0,
|
|
"step": 1485
|
|
},
|
|
{
|
|
"entropy": 6.351506185531616,
|
|
"epoch": 0.14787614132592297,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004999733169424284,
|
|
"loss": 6.1945,
|
|
"mean_token_accuracy": 0.12000712603330613,
|
|
"num_tokens": 3269474.0,
|
|
"step": 1490
|
|
},
|
|
{
|
|
"entropy": 6.345127201080322,
|
|
"epoch": 0.1483723699880905,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004999727684979904,
|
|
"loss": 6.1851,
|
|
"mean_token_accuracy": 0.11789674162864686,
|
|
"num_tokens": 3280453.0,
|
|
"step": 1495
|
|
},
|
|
{
|
|
"entropy": 6.31245641708374,
|
|
"epoch": 0.14886859865025803,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004999722144747125,
|
|
"loss": 6.1203,
|
|
"mean_token_accuracy": 0.11437854543328285,
|
|
"num_tokens": 3290234.0,
|
|
"step": 1500
|
|
},
|
|
{
|
|
"entropy": 6.290363025665283,
|
|
"epoch": 0.14936482731242556,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999716548726085,
|
|
"loss": 6.1151,
|
|
"mean_token_accuracy": 0.12060677483677865,
|
|
"num_tokens": 3300943.0,
|
|
"step": 1505
|
|
},
|
|
{
|
|
"entropy": 6.312642621994018,
|
|
"epoch": 0.1498610559745931,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004999710896916921,
|
|
"loss": 6.0684,
|
|
"mean_token_accuracy": 0.11790815740823746,
|
|
"num_tokens": 3311296.0,
|
|
"step": 1510
|
|
},
|
|
{
|
|
"entropy": 6.33518762588501,
|
|
"epoch": 0.15035728463676062,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999705189319774,
|
|
"loss": 6.2183,
|
|
"mean_token_accuracy": 0.11259444132447242,
|
|
"num_tokens": 3322310.0,
|
|
"step": 1515
|
|
},
|
|
{
|
|
"entropy": 6.35755672454834,
|
|
"epoch": 0.15085351329892815,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004999699425934788,
|
|
"loss": 6.2299,
|
|
"mean_token_accuracy": 0.11464733257889748,
|
|
"num_tokens": 3334176.0,
|
|
"step": 1520
|
|
},
|
|
{
|
|
"entropy": 6.353241586685181,
|
|
"epoch": 0.15134974196109569,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004999693606762103,
|
|
"loss": 6.2134,
|
|
"mean_token_accuracy": 0.11368680894374847,
|
|
"num_tokens": 3344839.0,
|
|
"step": 1525
|
|
},
|
|
{
|
|
"entropy": 6.369286584854126,
|
|
"epoch": 0.1518459706232632,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004999687731801865,
|
|
"loss": 6.1841,
|
|
"mean_token_accuracy": 0.11411794796586036,
|
|
"num_tokens": 3357046.0,
|
|
"step": 1530
|
|
},
|
|
{
|
|
"entropy": 6.3504150867462155,
|
|
"epoch": 0.15234219928543072,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004999681801054217,
|
|
"loss": 6.2434,
|
|
"mean_token_accuracy": 0.11438931301236152,
|
|
"num_tokens": 3367783.0,
|
|
"step": 1535
|
|
},
|
|
{
|
|
"entropy": 6.324097442626953,
|
|
"epoch": 0.15283842794759825,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.000499967581451931,
|
|
"loss": 6.1145,
|
|
"mean_token_accuracy": 0.11726456582546234,
|
|
"num_tokens": 3378529.0,
|
|
"step": 1540
|
|
},
|
|
{
|
|
"entropy": 6.375859260559082,
|
|
"epoch": 0.15333465660976578,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000499966977219729,
|
|
"loss": 6.3061,
|
|
"mean_token_accuracy": 0.11245756894350052,
|
|
"num_tokens": 3389318.0,
|
|
"step": 1545
|
|
},
|
|
{
|
|
"entropy": 6.410177373886109,
|
|
"epoch": 0.1538308852719333,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004999663674088306,
|
|
"loss": 6.3082,
|
|
"mean_token_accuracy": 0.1074009008705616,
|
|
"num_tokens": 3400603.0,
|
|
"step": 1550
|
|
},
|
|
{
|
|
"entropy": 6.406285333633423,
|
|
"epoch": 0.15432711393410084,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999657520192511,
|
|
"loss": 6.2016,
|
|
"mean_token_accuracy": 0.11285926327109337,
|
|
"num_tokens": 3410316.0,
|
|
"step": 1555
|
|
},
|
|
{
|
|
"entropy": 6.356779527664185,
|
|
"epoch": 0.15482334259626837,
|
|
"grad_norm": 0.79296875,
|
|
"learning_rate": 0.0004999651310510058,
|
|
"loss": 6.1416,
|
|
"mean_token_accuracy": 0.1178070843219757,
|
|
"num_tokens": 3422155.0,
|
|
"step": 1560
|
|
},
|
|
{
|
|
"entropy": 6.345295333862305,
|
|
"epoch": 0.15531957125843587,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004999645045041099,
|
|
"loss": 6.0819,
|
|
"mean_token_accuracy": 0.11718083545565605,
|
|
"num_tokens": 3432892.0,
|
|
"step": 1565
|
|
},
|
|
{
|
|
"entropy": 6.321739959716797,
|
|
"epoch": 0.1558157999206034,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004999638723785791,
|
|
"loss": 6.2004,
|
|
"mean_token_accuracy": 0.11840709745883941,
|
|
"num_tokens": 3443967.0,
|
|
"step": 1570
|
|
},
|
|
{
|
|
"entropy": 6.270855236053467,
|
|
"epoch": 0.15631202858277093,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.000499963234674429,
|
|
"loss": 6.0916,
|
|
"mean_token_accuracy": 0.12166468054056168,
|
|
"num_tokens": 3454354.0,
|
|
"step": 1575
|
|
},
|
|
{
|
|
"entropy": 6.233002376556397,
|
|
"epoch": 0.15680825724493846,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004999625913916754,
|
|
"loss": 6.1319,
|
|
"mean_token_accuracy": 0.11802673935890198,
|
|
"num_tokens": 3465232.0,
|
|
"step": 1580
|
|
},
|
|
{
|
|
"entropy": 6.242019701004028,
|
|
"epoch": 0.157304485907106,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004999619425303343,
|
|
"loss": 6.0925,
|
|
"mean_token_accuracy": 0.11856844201683998,
|
|
"num_tokens": 3475443.0,
|
|
"step": 1585
|
|
},
|
|
{
|
|
"entropy": 6.3711628913879395,
|
|
"epoch": 0.15780071456927353,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004999612880904219,
|
|
"loss": 6.1274,
|
|
"mean_token_accuracy": 0.11918400153517723,
|
|
"num_tokens": 3486643.0,
|
|
"step": 1590
|
|
},
|
|
{
|
|
"entropy": 6.28782172203064,
|
|
"epoch": 0.15829694323144106,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004999606280719542,
|
|
"loss": 6.185,
|
|
"mean_token_accuracy": 0.11784008368849755,
|
|
"num_tokens": 3497557.0,
|
|
"step": 1595
|
|
},
|
|
{
|
|
"entropy": 6.421589040756226,
|
|
"epoch": 0.1587931718936086,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999599624749475,
|
|
"loss": 6.1637,
|
|
"mean_token_accuracy": 0.11806859821081161,
|
|
"num_tokens": 3509790.0,
|
|
"step": 1600
|
|
},
|
|
{
|
|
"entropy": 6.215350532531739,
|
|
"epoch": 0.1592894005557761,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004999592912994187,
|
|
"loss": 6.0908,
|
|
"mean_token_accuracy": 0.11676915585994721,
|
|
"num_tokens": 3521577.0,
|
|
"step": 1605
|
|
},
|
|
{
|
|
"entropy": 6.3262897491455075,
|
|
"epoch": 0.15978562921794362,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004999586145453842,
|
|
"loss": 6.1432,
|
|
"mean_token_accuracy": 0.11143859475851059,
|
|
"num_tokens": 3532126.0,
|
|
"step": 1610
|
|
},
|
|
{
|
|
"entropy": 6.2068733215332035,
|
|
"epoch": 0.16028185788011115,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004999579322128608,
|
|
"loss": 5.972,
|
|
"mean_token_accuracy": 0.11642664968967438,
|
|
"num_tokens": 3542560.0,
|
|
"step": 1615
|
|
},
|
|
{
|
|
"entropy": 6.257067346572876,
|
|
"epoch": 0.16077808654227868,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004999572443018654,
|
|
"loss": 6.1404,
|
|
"mean_token_accuracy": 0.11960313320159913,
|
|
"num_tokens": 3553863.0,
|
|
"step": 1620
|
|
},
|
|
{
|
|
"entropy": 6.282857131958008,
|
|
"epoch": 0.1612743152044462,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004999565508124151,
|
|
"loss": 6.1603,
|
|
"mean_token_accuracy": 0.12152265384793282,
|
|
"num_tokens": 3564953.0,
|
|
"step": 1625
|
|
},
|
|
{
|
|
"entropy": 6.252542781829834,
|
|
"epoch": 0.16177054386661374,
|
|
"grad_norm": 0.78125,
|
|
"learning_rate": 0.000499955851744527,
|
|
"loss": 6.1588,
|
|
"mean_token_accuracy": 0.1182580165565014,
|
|
"num_tokens": 3576247.0,
|
|
"step": 1630
|
|
},
|
|
{
|
|
"entropy": 6.4327959537506105,
|
|
"epoch": 0.16226677252878127,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004999551470982185,
|
|
"loss": 6.1834,
|
|
"mean_token_accuracy": 0.11378399357199669,
|
|
"num_tokens": 3587600.0,
|
|
"step": 1635
|
|
},
|
|
{
|
|
"entropy": 6.352491140365601,
|
|
"epoch": 0.1627630011909488,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999544368735073,
|
|
"loss": 6.1676,
|
|
"mean_token_accuracy": 0.1208123430609703,
|
|
"num_tokens": 3597727.0,
|
|
"step": 1640
|
|
},
|
|
{
|
|
"entropy": 6.288443946838379,
|
|
"epoch": 0.1632592298531163,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004999537210704106,
|
|
"loss": 6.1383,
|
|
"mean_token_accuracy": 0.1199887067079544,
|
|
"num_tokens": 3608066.0,
|
|
"step": 1645
|
|
},
|
|
{
|
|
"entropy": 6.309280347824097,
|
|
"epoch": 0.16375545851528384,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004999529996889463,
|
|
"loss": 6.2006,
|
|
"mean_token_accuracy": 0.11445491313934326,
|
|
"num_tokens": 3618263.0,
|
|
"step": 1650
|
|
},
|
|
{
|
|
"entropy": 6.344433927536011,
|
|
"epoch": 0.16425168717745137,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004999522727291325,
|
|
"loss": 6.1369,
|
|
"mean_token_accuracy": 0.12186064049601555,
|
|
"num_tokens": 3629465.0,
|
|
"step": 1655
|
|
},
|
|
{
|
|
"entropy": 6.342315721511841,
|
|
"epoch": 0.1647479158396189,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.000499951540190987,
|
|
"loss": 6.1583,
|
|
"mean_token_accuracy": 0.11373883932828903,
|
|
"num_tokens": 3639657.0,
|
|
"step": 1660
|
|
},
|
|
{
|
|
"entropy": 6.328229236602783,
|
|
"epoch": 0.16524414450178643,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004999508020745281,
|
|
"loss": 6.1261,
|
|
"mean_token_accuracy": 0.11836064383387565,
|
|
"num_tokens": 3652374.0,
|
|
"step": 1665
|
|
},
|
|
{
|
|
"entropy": 6.265553331375122,
|
|
"epoch": 0.16574037316395396,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.0004999500583797739,
|
|
"loss": 6.1072,
|
|
"mean_token_accuracy": 0.12078006193041801,
|
|
"num_tokens": 3664083.0,
|
|
"step": 1670
|
|
},
|
|
{
|
|
"entropy": 6.2652623653411865,
|
|
"epoch": 0.1662366018261215,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004999493091067431,
|
|
"loss": 6.1452,
|
|
"mean_token_accuracy": 0.12134512290358543,
|
|
"num_tokens": 3675314.0,
|
|
"step": 1675
|
|
},
|
|
{
|
|
"entropy": 6.273673057556152,
|
|
"epoch": 0.166732830488289,
|
|
"grad_norm": 0.796875,
|
|
"learning_rate": 0.0004999485542554541,
|
|
"loss": 6.0998,
|
|
"mean_token_accuracy": 0.11119712963700294,
|
|
"num_tokens": 3686019.0,
|
|
"step": 1680
|
|
},
|
|
{
|
|
"entropy": 6.370255327224731,
|
|
"epoch": 0.16722905915045652,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004999477938259256,
|
|
"loss": 6.2015,
|
|
"mean_token_accuracy": 0.1111437164247036,
|
|
"num_tokens": 3698170.0,
|
|
"step": 1685
|
|
},
|
|
{
|
|
"entropy": 6.2584208965301515,
|
|
"epoch": 0.16772528781262405,
|
|
"grad_norm": 0.796875,
|
|
"learning_rate": 0.0004999470278181766,
|
|
"loss": 6.181,
|
|
"mean_token_accuracy": 0.11148267313838005,
|
|
"num_tokens": 3709243.0,
|
|
"step": 1690
|
|
},
|
|
{
|
|
"entropy": 6.344109964370728,
|
|
"epoch": 0.16822151647479158,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999462562322261,
|
|
"loss": 6.1492,
|
|
"mean_token_accuracy": 0.11816644594073296,
|
|
"num_tokens": 3720196.0,
|
|
"step": 1695
|
|
},
|
|
{
|
|
"entropy": 6.374466037750244,
|
|
"epoch": 0.1687177451369591,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.000499945479068093,
|
|
"loss": 6.1937,
|
|
"mean_token_accuracy": 0.1157242514193058,
|
|
"num_tokens": 3732714.0,
|
|
"step": 1700
|
|
},
|
|
{
|
|
"entropy": 6.284525728225708,
|
|
"epoch": 0.16921397379912664,
|
|
"grad_norm": 0.72265625,
|
|
"learning_rate": 0.0004999446963257969,
|
|
"loss": 6.1734,
|
|
"mean_token_accuracy": 0.11130392551422119,
|
|
"num_tokens": 3746474.0,
|
|
"step": 1705
|
|
},
|
|
{
|
|
"entropy": 6.26992883682251,
|
|
"epoch": 0.16971020246129417,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004999439080053571,
|
|
"loss": 6.0446,
|
|
"mean_token_accuracy": 0.12372053563594818,
|
|
"num_tokens": 3757528.0,
|
|
"step": 1710
|
|
},
|
|
{
|
|
"entropy": 6.382873582839966,
|
|
"epoch": 0.1702064311234617,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004999431141067928,
|
|
"loss": 6.18,
|
|
"mean_token_accuracy": 0.11336961910128593,
|
|
"num_tokens": 3768360.0,
|
|
"step": 1715
|
|
},
|
|
{
|
|
"entropy": 6.226411628723144,
|
|
"epoch": 0.1707026597856292,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004999423146301242,
|
|
"loss": 6.053,
|
|
"mean_token_accuracy": 0.11719192564487457,
|
|
"num_tokens": 3779809.0,
|
|
"step": 1720
|
|
},
|
|
{
|
|
"entropy": 6.197938585281372,
|
|
"epoch": 0.17119888844779674,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004999415095753709,
|
|
"loss": 6.0517,
|
|
"mean_token_accuracy": 0.11497935056686401,
|
|
"num_tokens": 3791455.0,
|
|
"step": 1725
|
|
},
|
|
{
|
|
"entropy": 6.194182014465332,
|
|
"epoch": 0.17169511710996427,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004999406989425527,
|
|
"loss": 6.0768,
|
|
"mean_token_accuracy": 0.11933901458978653,
|
|
"num_tokens": 3803209.0,
|
|
"step": 1730
|
|
},
|
|
{
|
|
"entropy": 6.272842121124268,
|
|
"epoch": 0.1721913457721318,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004999398827316901,
|
|
"loss": 6.118,
|
|
"mean_token_accuracy": 0.11888522580265999,
|
|
"num_tokens": 3813553.0,
|
|
"step": 1735
|
|
},
|
|
{
|
|
"entropy": 6.242817163467407,
|
|
"epoch": 0.17268757443429933,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.000499939060942803,
|
|
"loss": 6.1491,
|
|
"mean_token_accuracy": 0.1162618339061737,
|
|
"num_tokens": 3824856.0,
|
|
"step": 1740
|
|
},
|
|
{
|
|
"entropy": 6.3598274230957035,
|
|
"epoch": 0.17318380309646686,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004999382335759119,
|
|
"loss": 6.226,
|
|
"mean_token_accuracy": 0.1098976731300354,
|
|
"num_tokens": 3835489.0,
|
|
"step": 1745
|
|
},
|
|
{
|
|
"entropy": 6.3387504577636715,
|
|
"epoch": 0.1736800317586344,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999374006310372,
|
|
"loss": 6.0514,
|
|
"mean_token_accuracy": 0.11634560897946358,
|
|
"num_tokens": 3844838.0,
|
|
"step": 1750
|
|
},
|
|
{
|
|
"entropy": 6.168754911422729,
|
|
"epoch": 0.1741762604208019,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004999365621081999,
|
|
"loss": 6.0342,
|
|
"mean_token_accuracy": 0.11432853490114211,
|
|
"num_tokens": 3855288.0,
|
|
"step": 1755
|
|
},
|
|
{
|
|
"entropy": 6.248133897781372,
|
|
"epoch": 0.17467248908296942,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999357180074204,
|
|
"loss": 6.0702,
|
|
"mean_token_accuracy": 0.12020740732550621,
|
|
"num_tokens": 3865585.0,
|
|
"step": 1760
|
|
},
|
|
{
|
|
"entropy": 6.307549571990966,
|
|
"epoch": 0.17516871774513695,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004999348683287199,
|
|
"loss": 6.0612,
|
|
"mean_token_accuracy": 0.11682183891534806,
|
|
"num_tokens": 3877694.0,
|
|
"step": 1765
|
|
},
|
|
{
|
|
"entropy": 6.190867567062378,
|
|
"epoch": 0.17566494640730448,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004999340130721192,
|
|
"loss": 6.0438,
|
|
"mean_token_accuracy": 0.12537719830870628,
|
|
"num_tokens": 3888802.0,
|
|
"step": 1770
|
|
},
|
|
{
|
|
"entropy": 6.209321069717407,
|
|
"epoch": 0.17616117506947201,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004999331522376396,
|
|
"loss": 6.0208,
|
|
"mean_token_accuracy": 0.11791236400604248,
|
|
"num_tokens": 3900294.0,
|
|
"step": 1775
|
|
},
|
|
{
|
|
"entropy": 6.202359390258789,
|
|
"epoch": 0.17665740373163955,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004999322858253027,
|
|
"loss": 6.0417,
|
|
"mean_token_accuracy": 0.12317918911576271,
|
|
"num_tokens": 3910865.0,
|
|
"step": 1780
|
|
},
|
|
{
|
|
"entropy": 6.220766210556031,
|
|
"epoch": 0.17715363239380708,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004999314138351297,
|
|
"loss": 6.1082,
|
|
"mean_token_accuracy": 0.1180627316236496,
|
|
"num_tokens": 3921960.0,
|
|
"step": 1785
|
|
},
|
|
{
|
|
"entropy": 6.266336345672608,
|
|
"epoch": 0.1776498610559746,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004999305362671424,
|
|
"loss": 6.1053,
|
|
"mean_token_accuracy": 0.11726907566189766,
|
|
"num_tokens": 3934085.0,
|
|
"step": 1790
|
|
},
|
|
{
|
|
"entropy": 6.166120910644532,
|
|
"epoch": 0.1781460897181421,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004999296531213624,
|
|
"loss": 5.9587,
|
|
"mean_token_accuracy": 0.1321515955030918,
|
|
"num_tokens": 3944532.0,
|
|
"step": 1795
|
|
},
|
|
{
|
|
"entropy": 6.186281824111939,
|
|
"epoch": 0.17864231838030964,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004999287643978117,
|
|
"loss": 5.9965,
|
|
"mean_token_accuracy": 0.12600135430693626,
|
|
"num_tokens": 3954995.0,
|
|
"step": 1800
|
|
},
|
|
{
|
|
"entropy": 6.13634295463562,
|
|
"epoch": 0.17913854704247717,
|
|
"grad_norm": 0.796875,
|
|
"learning_rate": 0.0004999278700965124,
|
|
"loss": 6.045,
|
|
"mean_token_accuracy": 0.12481234520673752,
|
|
"num_tokens": 3966621.0,
|
|
"step": 1805
|
|
},
|
|
{
|
|
"entropy": 6.31223611831665,
|
|
"epoch": 0.1796347757046447,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004999269702174866,
|
|
"loss": 6.1086,
|
|
"mean_token_accuracy": 0.11732375845313073,
|
|
"num_tokens": 3977568.0,
|
|
"step": 1810
|
|
},
|
|
{
|
|
"entropy": 6.178112936019898,
|
|
"epoch": 0.18013100436681223,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004999260647607565,
|
|
"loss": 6.1296,
|
|
"mean_token_accuracy": 0.11571917533874512,
|
|
"num_tokens": 3988571.0,
|
|
"step": 1815
|
|
},
|
|
{
|
|
"entropy": 6.251215600967408,
|
|
"epoch": 0.18062723302897976,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004999251537263448,
|
|
"loss": 5.9563,
|
|
"mean_token_accuracy": 0.12610897570848464,
|
|
"num_tokens": 3998380.0,
|
|
"step": 1820
|
|
},
|
|
{
|
|
"entropy": 6.153609037399292,
|
|
"epoch": 0.1811234616911473,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004999242371142739,
|
|
"loss": 6.1257,
|
|
"mean_token_accuracy": 0.12231617867946624,
|
|
"num_tokens": 4010017.0,
|
|
"step": 1825
|
|
},
|
|
{
|
|
"entropy": 6.336256694793701,
|
|
"epoch": 0.1816196903533148,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004999233149245665,
|
|
"loss": 6.0924,
|
|
"mean_token_accuracy": 0.11703047156333923,
|
|
"num_tokens": 4020922.0,
|
|
"step": 1830
|
|
},
|
|
{
|
|
"entropy": 6.280692195892334,
|
|
"epoch": 0.18211591901548232,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004999223871572456,
|
|
"loss": 6.0664,
|
|
"mean_token_accuracy": 0.1190974049270153,
|
|
"num_tokens": 4030927.0,
|
|
"step": 1835
|
|
},
|
|
{
|
|
"entropy": 6.214899921417237,
|
|
"epoch": 0.18261214767764986,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004999214538123342,
|
|
"loss": 6.1446,
|
|
"mean_token_accuracy": 0.11380955725908279,
|
|
"num_tokens": 4041375.0,
|
|
"step": 1840
|
|
},
|
|
{
|
|
"entropy": 6.2237224102020265,
|
|
"epoch": 0.18310837633981739,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004999205148898554,
|
|
"loss": 6.1269,
|
|
"mean_token_accuracy": 0.11845389157533645,
|
|
"num_tokens": 4053213.0,
|
|
"step": 1845
|
|
},
|
|
{
|
|
"entropy": 6.275475740432739,
|
|
"epoch": 0.18360460500198492,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999195703898325,
|
|
"loss": 5.9784,
|
|
"mean_token_accuracy": 0.12606104388833045,
|
|
"num_tokens": 4064536.0,
|
|
"step": 1850
|
|
},
|
|
{
|
|
"entropy": 6.190648603439331,
|
|
"epoch": 0.18410083366415245,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999186203122889,
|
|
"loss": 6.06,
|
|
"mean_token_accuracy": 0.12409329041838646,
|
|
"num_tokens": 4075282.0,
|
|
"step": 1855
|
|
},
|
|
{
|
|
"entropy": 6.171055507659912,
|
|
"epoch": 0.18459706232631998,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004999176646572482,
|
|
"loss": 6.057,
|
|
"mean_token_accuracy": 0.12450164556503296,
|
|
"num_tokens": 4085501.0,
|
|
"step": 1860
|
|
},
|
|
{
|
|
"entropy": 6.222785091400146,
|
|
"epoch": 0.1850932909884875,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.000499916703424734,
|
|
"loss": 6.0077,
|
|
"mean_token_accuracy": 0.11859095394611359,
|
|
"num_tokens": 4095697.0,
|
|
"step": 1865
|
|
},
|
|
{
|
|
"entropy": 6.199232578277588,
|
|
"epoch": 0.185589519650655,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004999157366147702,
|
|
"loss": 6.0605,
|
|
"mean_token_accuracy": 0.1195147417485714,
|
|
"num_tokens": 4106459.0,
|
|
"step": 1870
|
|
},
|
|
{
|
|
"entropy": 6.221849536895752,
|
|
"epoch": 0.18608574831282254,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004999147642273809,
|
|
"loss": 5.9945,
|
|
"mean_token_accuracy": 0.12537158504128457,
|
|
"num_tokens": 4118320.0,
|
|
"step": 1875
|
|
},
|
|
{
|
|
"entropy": 6.132491636276245,
|
|
"epoch": 0.18658197697499007,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.00049991378626259,
|
|
"loss": 6.018,
|
|
"mean_token_accuracy": 0.12773770093917847,
|
|
"num_tokens": 4131249.0,
|
|
"step": 1880
|
|
},
|
|
{
|
|
"entropy": 6.259493064880371,
|
|
"epoch": 0.1870782056371576,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004999128027204219,
|
|
"loss": 6.0923,
|
|
"mean_token_accuracy": 0.12224588692188262,
|
|
"num_tokens": 4141480.0,
|
|
"step": 1885
|
|
},
|
|
{
|
|
"entropy": 6.227820491790771,
|
|
"epoch": 0.18757443429932513,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.000499911813600901,
|
|
"loss": 6.1457,
|
|
"mean_token_accuracy": 0.11545902863144875,
|
|
"num_tokens": 4152344.0,
|
|
"step": 1890
|
|
},
|
|
{
|
|
"entropy": 6.2940919399261475,
|
|
"epoch": 0.18807066296149266,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004999108189040516,
|
|
"loss": 6.1088,
|
|
"mean_token_accuracy": 0.12004400044679642,
|
|
"num_tokens": 4164772.0,
|
|
"step": 1895
|
|
},
|
|
{
|
|
"entropy": 6.163094329833984,
|
|
"epoch": 0.1885668916236602,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004999098186298986,
|
|
"loss": 6.0398,
|
|
"mean_token_accuracy": 0.11989247053861618,
|
|
"num_tokens": 4175511.0,
|
|
"step": 1900
|
|
},
|
|
{
|
|
"entropy": 6.184041833877563,
|
|
"epoch": 0.1890631202858277,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004999088127784667,
|
|
"loss": 6.0138,
|
|
"mean_token_accuracy": 0.1198397345840931,
|
|
"num_tokens": 4187445.0,
|
|
"step": 1905
|
|
},
|
|
{
|
|
"entropy": 6.224808263778686,
|
|
"epoch": 0.18955934894799523,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.000499907801349781,
|
|
"loss": 5.9992,
|
|
"mean_token_accuracy": 0.1206267774105072,
|
|
"num_tokens": 4198124.0,
|
|
"step": 1910
|
|
},
|
|
{
|
|
"entropy": 6.183636951446533,
|
|
"epoch": 0.19005557761016276,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004999067843438664,
|
|
"loss": 6.0454,
|
|
"mean_token_accuracy": 0.11894752085208893,
|
|
"num_tokens": 4208954.0,
|
|
"step": 1915
|
|
},
|
|
{
|
|
"entropy": 6.204626941680909,
|
|
"epoch": 0.1905518062723303,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004999057617607482,
|
|
"loss": 6.1093,
|
|
"mean_token_accuracy": 0.1197871819138527,
|
|
"num_tokens": 4218896.0,
|
|
"step": 1920
|
|
},
|
|
{
|
|
"entropy": 6.1618143081665036,
|
|
"epoch": 0.19104803493449782,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004999047336004517,
|
|
"loss": 6.0051,
|
|
"mean_token_accuracy": 0.11776421442627907,
|
|
"num_tokens": 4228851.0,
|
|
"step": 1925
|
|
},
|
|
{
|
|
"entropy": 6.110290908813477,
|
|
"epoch": 0.19154426359666535,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004999036998630024,
|
|
"loss": 5.9683,
|
|
"mean_token_accuracy": 0.12174378857016563,
|
|
"num_tokens": 4240377.0,
|
|
"step": 1930
|
|
},
|
|
{
|
|
"entropy": 6.116988277435302,
|
|
"epoch": 0.19204049225883288,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.000499902660548426,
|
|
"loss": 5.9615,
|
|
"mean_token_accuracy": 0.12193656638264656,
|
|
"num_tokens": 4251341.0,
|
|
"step": 1935
|
|
},
|
|
{
|
|
"entropy": 6.247050094604492,
|
|
"epoch": 0.1925367209210004,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004999016156567482,
|
|
"loss": 6.0695,
|
|
"mean_token_accuracy": 0.12280801013112068,
|
|
"num_tokens": 4261206.0,
|
|
"step": 1940
|
|
},
|
|
{
|
|
"entropy": 6.215968275070191,
|
|
"epoch": 0.1930329495831679,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.000499900565187995,
|
|
"loss": 6.0677,
|
|
"mean_token_accuracy": 0.1141348622739315,
|
|
"num_tokens": 4272662.0,
|
|
"step": 1945
|
|
},
|
|
{
|
|
"entropy": 6.240064001083374,
|
|
"epoch": 0.19352917824533544,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004998995091421924,
|
|
"loss": 6.0459,
|
|
"mean_token_accuracy": 0.11888503208756447,
|
|
"num_tokens": 4283302.0,
|
|
"step": 1950
|
|
},
|
|
{
|
|
"entropy": 6.114093589782715,
|
|
"epoch": 0.19402540690750297,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004998984475193665,
|
|
"loss": 5.9975,
|
|
"mean_token_accuracy": 0.1221638023853302,
|
|
"num_tokens": 4296087.0,
|
|
"step": 1955
|
|
},
|
|
{
|
|
"entropy": 6.181862306594849,
|
|
"epoch": 0.1945216355696705,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004998973803195439,
|
|
"loss": 6.0053,
|
|
"mean_token_accuracy": 0.12597885355353355,
|
|
"num_tokens": 4305918.0,
|
|
"step": 1960
|
|
},
|
|
{
|
|
"entropy": 6.123769617080688,
|
|
"epoch": 0.19501786423183803,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004998963075427508,
|
|
"loss": 6.0646,
|
|
"mean_token_accuracy": 0.12296420186758042,
|
|
"num_tokens": 4316507.0,
|
|
"step": 1965
|
|
},
|
|
{
|
|
"entropy": 6.2180873394012455,
|
|
"epoch": 0.19551409289400556,
|
|
"grad_norm": 0.76953125,
|
|
"learning_rate": 0.0004998952291890138,
|
|
"loss": 6.0,
|
|
"mean_token_accuracy": 0.12596616744995118,
|
|
"num_tokens": 4329091.0,
|
|
"step": 1970
|
|
},
|
|
{
|
|
"entropy": 6.206251239776611,
|
|
"epoch": 0.1960103215561731,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004998941452583599,
|
|
"loss": 6.0603,
|
|
"mean_token_accuracy": 0.12475561425089836,
|
|
"num_tokens": 4339266.0,
|
|
"step": 1975
|
|
},
|
|
{
|
|
"entropy": 6.0974133014678955,
|
|
"epoch": 0.1965065502183406,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004998930557508156,
|
|
"loss": 5.984,
|
|
"mean_token_accuracy": 0.1275751493871212,
|
|
"num_tokens": 4349300.0,
|
|
"step": 1980
|
|
},
|
|
{
|
|
"entropy": 6.0830080032348635,
|
|
"epoch": 0.19700277888050813,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004998919606664082,
|
|
"loss": 5.9019,
|
|
"mean_token_accuracy": 0.13283863738179208,
|
|
"num_tokens": 4360314.0,
|
|
"step": 1985
|
|
},
|
|
{
|
|
"entropy": 6.183152389526367,
|
|
"epoch": 0.19749900754267566,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004998908600051648,
|
|
"loss": 5.9678,
|
|
"mean_token_accuracy": 0.1221761591732502,
|
|
"num_tokens": 4370077.0,
|
|
"step": 1990
|
|
},
|
|
{
|
|
"entropy": 6.084688329696656,
|
|
"epoch": 0.1979952362048432,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004998897537671126,
|
|
"loss": 5.9713,
|
|
"mean_token_accuracy": 0.12218144908547401,
|
|
"num_tokens": 4381000.0,
|
|
"step": 1995
|
|
},
|
|
{
|
|
"entropy": 6.211720275878906,
|
|
"epoch": 0.19849146486701072,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004998886419522792,
|
|
"loss": 6.1942,
|
|
"mean_token_accuracy": 0.11456988155841827,
|
|
"num_tokens": 4393485.0,
|
|
"step": 2000
|
|
},
|
|
{
|
|
"entropy": 6.298164701461792,
|
|
"epoch": 0.19898769352917825,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004998875245606919,
|
|
"loss": 6.0114,
|
|
"mean_token_accuracy": 0.12225927039980888,
|
|
"num_tokens": 4404354.0,
|
|
"step": 2005
|
|
},
|
|
{
|
|
"entropy": 6.105899810791016,
|
|
"epoch": 0.19948392219134578,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004998864015923788,
|
|
"loss": 6.1597,
|
|
"mean_token_accuracy": 0.12076655179262161,
|
|
"num_tokens": 4414818.0,
|
|
"step": 2010
|
|
},
|
|
{
|
|
"entropy": 6.200961780548096,
|
|
"epoch": 0.1999801508535133,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004998852730473674,
|
|
"loss": 6.0344,
|
|
"mean_token_accuracy": 0.11524304151535034,
|
|
"num_tokens": 4426271.0,
|
|
"step": 2015
|
|
},
|
|
{
|
|
"entropy": 6.12263708114624,
|
|
"epoch": 0.2004763795156808,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004998841389256859,
|
|
"loss": 6.0903,
|
|
"mean_token_accuracy": 0.12121652588248252,
|
|
"num_tokens": 4436981.0,
|
|
"step": 2020
|
|
},
|
|
{
|
|
"entropy": 6.139917802810669,
|
|
"epoch": 0.20097260817784834,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004998829992273622,
|
|
"loss": 5.9254,
|
|
"mean_token_accuracy": 0.12804987505078316,
|
|
"num_tokens": 4446494.0,
|
|
"step": 2025
|
|
},
|
|
{
|
|
"entropy": 6.094701433181763,
|
|
"epoch": 0.20146883684001587,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004998818539524248,
|
|
"loss": 6.007,
|
|
"mean_token_accuracy": 0.12410036325454712,
|
|
"num_tokens": 4458535.0,
|
|
"step": 2030
|
|
},
|
|
{
|
|
"entropy": 6.231687307357788,
|
|
"epoch": 0.2019650655021834,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.000499880703100902,
|
|
"loss": 5.9882,
|
|
"mean_token_accuracy": 0.1257662445306778,
|
|
"num_tokens": 4469025.0,
|
|
"step": 2035
|
|
},
|
|
{
|
|
"entropy": 6.119232892990112,
|
|
"epoch": 0.20246129416435094,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004998795466728223,
|
|
"loss": 5.9832,
|
|
"mean_token_accuracy": 0.1266017124056816,
|
|
"num_tokens": 4478431.0,
|
|
"step": 2040
|
|
},
|
|
{
|
|
"entropy": 6.141779518127441,
|
|
"epoch": 0.20295752282651847,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004998783846682144,
|
|
"loss": 6.1012,
|
|
"mean_token_accuracy": 0.12176022753119468,
|
|
"num_tokens": 4490215.0,
|
|
"step": 2045
|
|
},
|
|
{
|
|
"entropy": 6.160814476013184,
|
|
"epoch": 0.203453751488686,
|
|
"grad_norm": 0.76171875,
|
|
"learning_rate": 0.0004998772170871072,
|
|
"loss": 5.9883,
|
|
"mean_token_accuracy": 0.12457352355122567,
|
|
"num_tokens": 4502895.0,
|
|
"step": 2050
|
|
},
|
|
{
|
|
"entropy": 6.102251768112183,
|
|
"epoch": 0.20394998015085353,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004998760439295295,
|
|
"loss": 6.0066,
|
|
"mean_token_accuracy": 0.12112522423267365,
|
|
"num_tokens": 4514468.0,
|
|
"step": 2055
|
|
},
|
|
{
|
|
"entropy": 6.218370962142944,
|
|
"epoch": 0.20444620881302103,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004998748651955105,
|
|
"loss": 6.0276,
|
|
"mean_token_accuracy": 0.11916945278644561,
|
|
"num_tokens": 4525787.0,
|
|
"step": 2060
|
|
},
|
|
{
|
|
"entropy": 6.161030578613281,
|
|
"epoch": 0.20494243747518856,
|
|
"grad_norm": 0.765625,
|
|
"learning_rate": 0.0004998736808850795,
|
|
"loss": 6.1047,
|
|
"mean_token_accuracy": 0.11898912787437439,
|
|
"num_tokens": 4537536.0,
|
|
"step": 2065
|
|
},
|
|
{
|
|
"entropy": 6.2428888320922855,
|
|
"epoch": 0.2054386661373561,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004998724909982656,
|
|
"loss": 6.0472,
|
|
"mean_token_accuracy": 0.12252518236637115,
|
|
"num_tokens": 4549619.0,
|
|
"step": 2070
|
|
},
|
|
{
|
|
"entropy": 6.097667264938354,
|
|
"epoch": 0.20593489479952362,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004998712955350986,
|
|
"loss": 5.9866,
|
|
"mean_token_accuracy": 0.12310111299157142,
|
|
"num_tokens": 4560248.0,
|
|
"step": 2075
|
|
},
|
|
{
|
|
"entropy": 6.195798301696778,
|
|
"epoch": 0.20643112346169115,
|
|
"grad_norm": 0.79296875,
|
|
"learning_rate": 0.0004998700944956081,
|
|
"loss": 6.0975,
|
|
"mean_token_accuracy": 0.12141188234090805,
|
|
"num_tokens": 4571888.0,
|
|
"step": 2080
|
|
},
|
|
{
|
|
"entropy": 6.179491949081421,
|
|
"epoch": 0.20692735212385868,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004998688878798237,
|
|
"loss": 5.9365,
|
|
"mean_token_accuracy": 0.1305774599313736,
|
|
"num_tokens": 4583234.0,
|
|
"step": 2085
|
|
},
|
|
{
|
|
"entropy": 6.161084604263306,
|
|
"epoch": 0.2074235807860262,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004998676756877753,
|
|
"loss": 6.1601,
|
|
"mean_token_accuracy": 0.11846253573894501,
|
|
"num_tokens": 4595252.0,
|
|
"step": 2090
|
|
},
|
|
{
|
|
"entropy": 6.131542110443116,
|
|
"epoch": 0.20791980944819372,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004998664579194934,
|
|
"loss": 5.9236,
|
|
"mean_token_accuracy": 0.1237091027200222,
|
|
"num_tokens": 4607091.0,
|
|
"step": 2095
|
|
},
|
|
{
|
|
"entropy": 6.140899753570556,
|
|
"epoch": 0.20841603811036125,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004998652345750077,
|
|
"loss": 5.8958,
|
|
"mean_token_accuracy": 0.1278851717710495,
|
|
"num_tokens": 4618003.0,
|
|
"step": 2100
|
|
},
|
|
{
|
|
"entropy": 6.041016483306885,
|
|
"epoch": 0.20891226677252878,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.0004998640056543487,
|
|
"loss": 5.8996,
|
|
"mean_token_accuracy": 0.12397338300943375,
|
|
"num_tokens": 4628429.0,
|
|
"step": 2105
|
|
},
|
|
{
|
|
"entropy": 6.15621018409729,
|
|
"epoch": 0.2094084954346963,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004998627711575469,
|
|
"loss": 5.9676,
|
|
"mean_token_accuracy": 0.12933185324072838,
|
|
"num_tokens": 4639414.0,
|
|
"step": 2110
|
|
},
|
|
{
|
|
"entropy": 6.167100429534912,
|
|
"epoch": 0.20990472409686384,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.000499861531084633,
|
|
"loss": 6.0398,
|
|
"mean_token_accuracy": 0.12240175604820251,
|
|
"num_tokens": 4652594.0,
|
|
"step": 2115
|
|
},
|
|
{
|
|
"entropy": 6.079341125488281,
|
|
"epoch": 0.21040095275903137,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004998602854356376,
|
|
"loss": 5.8855,
|
|
"mean_token_accuracy": 0.1307040624320507,
|
|
"num_tokens": 4662981.0,
|
|
"step": 2120
|
|
},
|
|
{
|
|
"entropy": 6.053981876373291,
|
|
"epoch": 0.2108971814211989,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004998590342105917,
|
|
"loss": 5.9951,
|
|
"mean_token_accuracy": 0.12460904493927956,
|
|
"num_tokens": 4672469.0,
|
|
"step": 2125
|
|
},
|
|
{
|
|
"entropy": 6.146594381332397,
|
|
"epoch": 0.21139341008336643,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004998577774095262,
|
|
"loss": 5.9799,
|
|
"mean_token_accuracy": 0.12103921249508857,
|
|
"num_tokens": 4683640.0,
|
|
"step": 2130
|
|
},
|
|
{
|
|
"entropy": 6.100749874114991,
|
|
"epoch": 0.21188963874553393,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004998565150324724,
|
|
"loss": 5.9284,
|
|
"mean_token_accuracy": 0.12689334973692895,
|
|
"num_tokens": 4694032.0,
|
|
"step": 2135
|
|
},
|
|
{
|
|
"entropy": 6.005304336547852,
|
|
"epoch": 0.21238586740770146,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004998552470794616,
|
|
"loss": 5.8162,
|
|
"mean_token_accuracy": 0.12930263206362724,
|
|
"num_tokens": 4704253.0,
|
|
"step": 2140
|
|
},
|
|
{
|
|
"entropy": 6.0581738471984865,
|
|
"epoch": 0.212882096069869,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004998539735505251,
|
|
"loss": 5.9544,
|
|
"mean_token_accuracy": 0.12062570005655289,
|
|
"num_tokens": 4715327.0,
|
|
"step": 2145
|
|
},
|
|
{
|
|
"entropy": 6.2206943988800045,
|
|
"epoch": 0.21337832473203652,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004998526944456946,
|
|
"loss": 5.9851,
|
|
"mean_token_accuracy": 0.12153983116149902,
|
|
"num_tokens": 4726450.0,
|
|
"step": 2150
|
|
},
|
|
{
|
|
"entropy": 6.0526422500610355,
|
|
"epoch": 0.21387455339420405,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004998514097650018,
|
|
"loss": 6.0067,
|
|
"mean_token_accuracy": 0.12227371484041213,
|
|
"num_tokens": 4736630.0,
|
|
"step": 2155
|
|
},
|
|
{
|
|
"entropy": 6.161049175262451,
|
|
"epoch": 0.21437078205637158,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004998501195084786,
|
|
"loss": 5.8963,
|
|
"mean_token_accuracy": 0.12918635457754135,
|
|
"num_tokens": 4746592.0,
|
|
"step": 2160
|
|
},
|
|
{
|
|
"entropy": 6.086433601379395,
|
|
"epoch": 0.21486701071853911,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004998488236761569,
|
|
"loss": 6.072,
|
|
"mean_token_accuracy": 0.12488910630345344,
|
|
"num_tokens": 4757824.0,
|
|
"step": 2165
|
|
},
|
|
{
|
|
"entropy": 6.144498586654663,
|
|
"epoch": 0.21536323938070662,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004998475222680688,
|
|
"loss": 5.9959,
|
|
"mean_token_accuracy": 0.1257177084684372,
|
|
"num_tokens": 4768453.0,
|
|
"step": 2170
|
|
},
|
|
{
|
|
"entropy": 6.051328659057617,
|
|
"epoch": 0.21585946804287415,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004998462152842468,
|
|
"loss": 5.9771,
|
|
"mean_token_accuracy": 0.12266893535852433,
|
|
"num_tokens": 4779664.0,
|
|
"step": 2175
|
|
},
|
|
{
|
|
"entropy": 6.203923177719116,
|
|
"epoch": 0.21635569670504168,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.000499844902724723,
|
|
"loss": 5.997,
|
|
"mean_token_accuracy": 0.12400704175233841,
|
|
"num_tokens": 4791012.0,
|
|
"step": 2180
|
|
},
|
|
{
|
|
"entropy": 6.080739498138428,
|
|
"epoch": 0.2168519253672092,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004998435845895302,
|
|
"loss": 5.8727,
|
|
"mean_token_accuracy": 0.1246095396578312,
|
|
"num_tokens": 4800578.0,
|
|
"step": 2185
|
|
},
|
|
{
|
|
"entropy": 6.023191165924072,
|
|
"epoch": 0.21734815402937674,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.000499842260878701,
|
|
"loss": 5.8847,
|
|
"mean_token_accuracy": 0.12296021655201912,
|
|
"num_tokens": 4810940.0,
|
|
"step": 2190
|
|
},
|
|
{
|
|
"entropy": 6.089705514907837,
|
|
"epoch": 0.21784438269154427,
|
|
"grad_norm": 0.7734375,
|
|
"learning_rate": 0.0004998409315922683,
|
|
"loss": 6.0182,
|
|
"mean_token_accuracy": 0.12229126617312432,
|
|
"num_tokens": 4822696.0,
|
|
"step": 2195
|
|
},
|
|
{
|
|
"entropy": 6.09975118637085,
|
|
"epoch": 0.2183406113537118,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004998395967302649,
|
|
"loss": 5.8893,
|
|
"mean_token_accuracy": 0.12959264144301413,
|
|
"num_tokens": 4833669.0,
|
|
"step": 2200
|
|
},
|
|
{
|
|
"entropy": 6.1851764678955075,
|
|
"epoch": 0.21883684001587933,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.000499838256292724,
|
|
"loss": 6.0744,
|
|
"mean_token_accuracy": 0.12145713344216347,
|
|
"num_tokens": 4844021.0,
|
|
"step": 2205
|
|
},
|
|
{
|
|
"entropy": 6.052931642532348,
|
|
"epoch": 0.21933306867804683,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004998369102796787,
|
|
"loss": 5.9505,
|
|
"mean_token_accuracy": 0.12860263735055924,
|
|
"num_tokens": 4855336.0,
|
|
"step": 2210
|
|
},
|
|
{
|
|
"entropy": 6.104745626449585,
|
|
"epoch": 0.21982929734021436,
|
|
"grad_norm": 0.7734375,
|
|
"learning_rate": 0.0004998355586911627,
|
|
"loss": 5.9443,
|
|
"mean_token_accuracy": 0.12385106608271598,
|
|
"num_tokens": 4867713.0,
|
|
"step": 2215
|
|
},
|
|
{
|
|
"entropy": 6.0858691215515135,
|
|
"epoch": 0.2203255260023819,
|
|
"grad_norm": 0.78515625,
|
|
"learning_rate": 0.0004998342015272093,
|
|
"loss": 5.9244,
|
|
"mean_token_accuracy": 0.1223891668021679,
|
|
"num_tokens": 4879134.0,
|
|
"step": 2220
|
|
},
|
|
{
|
|
"entropy": 6.108216285705566,
|
|
"epoch": 0.22082175466454942,
|
|
"grad_norm": 0.796875,
|
|
"learning_rate": 0.0004998328387878521,
|
|
"loss": 6.0808,
|
|
"mean_token_accuracy": 0.12277590483427048,
|
|
"num_tokens": 4891755.0,
|
|
"step": 2225
|
|
},
|
|
{
|
|
"entropy": 6.2470619678497314,
|
|
"epoch": 0.22131798332671695,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004998314704731249,
|
|
"loss": 6.0916,
|
|
"mean_token_accuracy": 0.12046385034918786,
|
|
"num_tokens": 4903264.0,
|
|
"step": 2230
|
|
},
|
|
{
|
|
"entropy": 6.077593660354614,
|
|
"epoch": 0.22181421198888449,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004998300965830618,
|
|
"loss": 5.9,
|
|
"mean_token_accuracy": 0.12378231808543205,
|
|
"num_tokens": 4912533.0,
|
|
"step": 2235
|
|
},
|
|
{
|
|
"entropy": 5.9839921474456785,
|
|
"epoch": 0.22231044065105202,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004998287171176968,
|
|
"loss": 5.8996,
|
|
"mean_token_accuracy": 0.1311133660376072,
|
|
"num_tokens": 4923288.0,
|
|
"step": 2240
|
|
},
|
|
{
|
|
"entropy": 6.105050659179687,
|
|
"epoch": 0.22280666931321952,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004998273320770641,
|
|
"loss": 5.9154,
|
|
"mean_token_accuracy": 0.12592516243457794,
|
|
"num_tokens": 4934759.0,
|
|
"step": 2245
|
|
},
|
|
{
|
|
"entropy": 6.072722053527832,
|
|
"epoch": 0.22330289797538705,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.000499825941461198,
|
|
"loss": 5.9621,
|
|
"mean_token_accuracy": 0.12398277670145035,
|
|
"num_tokens": 4947024.0,
|
|
"step": 2250
|
|
},
|
|
{
|
|
"entropy": 6.092696714401245,
|
|
"epoch": 0.22379912663755458,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004998245452701329,
|
|
"loss": 5.9152,
|
|
"mean_token_accuracy": 0.12754956483840943,
|
|
"num_tokens": 4959281.0,
|
|
"step": 2255
|
|
},
|
|
{
|
|
"entropy": 6.13616452217102,
|
|
"epoch": 0.2242953552997221,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004998231435039036,
|
|
"loss": 5.9725,
|
|
"mean_token_accuracy": 0.12141189724206924,
|
|
"num_tokens": 4970466.0,
|
|
"step": 2260
|
|
},
|
|
{
|
|
"entropy": 6.069933271408081,
|
|
"epoch": 0.22479158396188964,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004998217361625449,
|
|
"loss": 5.9236,
|
|
"mean_token_accuracy": 0.12711238041520118,
|
|
"num_tokens": 4981135.0,
|
|
"step": 2265
|
|
},
|
|
{
|
|
"entropy": 6.105356216430664,
|
|
"epoch": 0.22528781262405717,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004998203232460915,
|
|
"loss": 5.9797,
|
|
"mean_token_accuracy": 0.12980691865086555,
|
|
"num_tokens": 4991292.0,
|
|
"step": 2270
|
|
},
|
|
{
|
|
"entropy": 6.059658765792847,
|
|
"epoch": 0.2257840412862247,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004998189047545785,
|
|
"loss": 5.9345,
|
|
"mean_token_accuracy": 0.13011907190084457,
|
|
"num_tokens": 5002806.0,
|
|
"step": 2275
|
|
},
|
|
{
|
|
"entropy": 6.100206136703491,
|
|
"epoch": 0.22628026994839223,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004998174806880411,
|
|
"loss": 5.8843,
|
|
"mean_token_accuracy": 0.1296177588403225,
|
|
"num_tokens": 5013474.0,
|
|
"step": 2280
|
|
},
|
|
{
|
|
"entropy": 6.06908540725708,
|
|
"epoch": 0.22677649861055973,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004998160510465146,
|
|
"loss": 5.9249,
|
|
"mean_token_accuracy": 0.1318567730486393,
|
|
"num_tokens": 5025151.0,
|
|
"step": 2285
|
|
},
|
|
{
|
|
"entropy": 5.967230415344238,
|
|
"epoch": 0.22727272727272727,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004998146158300345,
|
|
"loss": 5.9196,
|
|
"mean_token_accuracy": 0.1306504562497139,
|
|
"num_tokens": 5037166.0,
|
|
"step": 2290
|
|
},
|
|
{
|
|
"entropy": 6.142732429504394,
|
|
"epoch": 0.2277689559348948,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004998131750386364,
|
|
"loss": 5.9706,
|
|
"mean_token_accuracy": 0.12619220688939095,
|
|
"num_tokens": 5047452.0,
|
|
"step": 2295
|
|
},
|
|
{
|
|
"entropy": 6.048137044906616,
|
|
"epoch": 0.22826518459706233,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004998117286723559,
|
|
"loss": 5.9756,
|
|
"mean_token_accuracy": 0.12324338406324387,
|
|
"num_tokens": 5058501.0,
|
|
"step": 2300
|
|
},
|
|
{
|
|
"entropy": 6.132171249389648,
|
|
"epoch": 0.22876141325922986,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.000499810276731229,
|
|
"loss": 5.974,
|
|
"mean_token_accuracy": 0.12393502593040466,
|
|
"num_tokens": 5069716.0,
|
|
"step": 2305
|
|
},
|
|
{
|
|
"entropy": 6.158532667160034,
|
|
"epoch": 0.2292576419213974,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004998088192152918,
|
|
"loss": 5.9587,
|
|
"mean_token_accuracy": 0.12171528786420822,
|
|
"num_tokens": 5078509.0,
|
|
"step": 2310
|
|
},
|
|
{
|
|
"entropy": 6.056684732437134,
|
|
"epoch": 0.22975387058356492,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004998073561245801,
|
|
"loss": 5.9908,
|
|
"mean_token_accuracy": 0.12283852398395538,
|
|
"num_tokens": 5090355.0,
|
|
"step": 2315
|
|
},
|
|
{
|
|
"entropy": 6.118961763381958,
|
|
"epoch": 0.23025009924573242,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004998058874591305,
|
|
"loss": 5.8839,
|
|
"mean_token_accuracy": 0.12737965807318688,
|
|
"num_tokens": 5100582.0,
|
|
"step": 2320
|
|
},
|
|
{
|
|
"entropy": 6.098464822769165,
|
|
"epoch": 0.23074632790789995,
|
|
"grad_norm": 0.76953125,
|
|
"learning_rate": 0.0004998044132189793,
|
|
"loss": 5.9514,
|
|
"mean_token_accuracy": 0.12292122989892959,
|
|
"num_tokens": 5112176.0,
|
|
"step": 2325
|
|
},
|
|
{
|
|
"entropy": 6.076971912384034,
|
|
"epoch": 0.23124255657006748,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000499802933404163,
|
|
"loss": 5.8787,
|
|
"mean_token_accuracy": 0.1285627380013466,
|
|
"num_tokens": 5122840.0,
|
|
"step": 2330
|
|
},
|
|
{
|
|
"entropy": 6.050347518920899,
|
|
"epoch": 0.231738785232235,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004998014480147183,
|
|
"loss": 5.8587,
|
|
"mean_token_accuracy": 0.13070411905646323,
|
|
"num_tokens": 5132926.0,
|
|
"step": 2335
|
|
},
|
|
{
|
|
"entropy": 6.0548614978790285,
|
|
"epoch": 0.23223501389440254,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004997999570506823,
|
|
"loss": 5.8476,
|
|
"mean_token_accuracy": 0.12983267456293107,
|
|
"num_tokens": 5143394.0,
|
|
"step": 2340
|
|
},
|
|
{
|
|
"entropy": 5.978992509841919,
|
|
"epoch": 0.23273124255657007,
|
|
"grad_norm": 0.80078125,
|
|
"learning_rate": 0.0004997984605120917,
|
|
"loss": 5.8757,
|
|
"mean_token_accuracy": 0.12346786707639694,
|
|
"num_tokens": 5155710.0,
|
|
"step": 2345
|
|
},
|
|
{
|
|
"entropy": 5.942594051361084,
|
|
"epoch": 0.2332274712187376,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004997969583989835,
|
|
"loss": 5.7929,
|
|
"mean_token_accuracy": 0.12445841357111931,
|
|
"num_tokens": 5167065.0,
|
|
"step": 2350
|
|
},
|
|
{
|
|
"entropy": 6.06046576499939,
|
|
"epoch": 0.23372369988090513,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004997954507113952,
|
|
"loss": 5.9018,
|
|
"mean_token_accuracy": 0.12778859511017798,
|
|
"num_tokens": 5177535.0,
|
|
"step": 2355
|
|
},
|
|
{
|
|
"entropy": 6.021834182739258,
|
|
"epoch": 0.23421992854307264,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004997939374493642,
|
|
"loss": 5.8305,
|
|
"mean_token_accuracy": 0.12911173850297927,
|
|
"num_tokens": 5188324.0,
|
|
"step": 2360
|
|
},
|
|
{
|
|
"entropy": 6.018092298507691,
|
|
"epoch": 0.23471615720524017,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.000499792418612928,
|
|
"loss": 5.9024,
|
|
"mean_token_accuracy": 0.13002333790063858,
|
|
"num_tokens": 5199223.0,
|
|
"step": 2365
|
|
},
|
|
{
|
|
"entropy": 5.9740711688995365,
|
|
"epoch": 0.2352123858674077,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004997908942021241,
|
|
"loss": 5.89,
|
|
"mean_token_accuracy": 0.13267461881041526,
|
|
"num_tokens": 5210080.0,
|
|
"step": 2370
|
|
},
|
|
{
|
|
"entropy": 6.135750961303711,
|
|
"epoch": 0.23570861452957523,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004997893642169904,
|
|
"loss": 6.0108,
|
|
"mean_token_accuracy": 0.12664430662989618,
|
|
"num_tokens": 5220867.0,
|
|
"step": 2375
|
|
},
|
|
{
|
|
"entropy": 6.101852035522461,
|
|
"epoch": 0.23620484319174276,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004997878286575648,
|
|
"loss": 5.8597,
|
|
"mean_token_accuracy": 0.12812694609165193,
|
|
"num_tokens": 5231451.0,
|
|
"step": 2380
|
|
},
|
|
{
|
|
"entropy": 6.028659343719482,
|
|
"epoch": 0.2367010718539103,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004997862875238855,
|
|
"loss": 5.9642,
|
|
"mean_token_accuracy": 0.12428494766354561,
|
|
"num_tokens": 5244643.0,
|
|
"step": 2385
|
|
},
|
|
{
|
|
"entropy": 6.113288068771363,
|
|
"epoch": 0.23719730051607782,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004997847408159907,
|
|
"loss": 5.979,
|
|
"mean_token_accuracy": 0.12018007338047028,
|
|
"num_tokens": 5256279.0,
|
|
"step": 2390
|
|
},
|
|
{
|
|
"entropy": 6.0652384757995605,
|
|
"epoch": 0.23769352917824532,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004997831885339186,
|
|
"loss": 5.9475,
|
|
"mean_token_accuracy": 0.1281052775681019,
|
|
"num_tokens": 5268498.0,
|
|
"step": 2395
|
|
},
|
|
{
|
|
"entropy": 6.014727401733398,
|
|
"epoch": 0.23818975784041285,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004997816306777077,
|
|
"loss": 5.908,
|
|
"mean_token_accuracy": 0.1289649024605751,
|
|
"num_tokens": 5280869.0,
|
|
"step": 2400
|
|
},
|
|
{
|
|
"entropy": 6.235253620147705,
|
|
"epoch": 0.23868598650258038,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004997800672473969,
|
|
"loss": 6.0058,
|
|
"mean_token_accuracy": 0.12169916182756424,
|
|
"num_tokens": 5293082.0,
|
|
"step": 2405
|
|
},
|
|
{
|
|
"entropy": 5.997746467590332,
|
|
"epoch": 0.2391822151647479,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004997784982430247,
|
|
"loss": 5.8106,
|
|
"mean_token_accuracy": 0.13437482044100763,
|
|
"num_tokens": 5304039.0,
|
|
"step": 2410
|
|
},
|
|
{
|
|
"entropy": 5.944843721389771,
|
|
"epoch": 0.23967844382691544,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004997769236646301,
|
|
"loss": 5.8851,
|
|
"mean_token_accuracy": 0.1293253131210804,
|
|
"num_tokens": 5315016.0,
|
|
"step": 2415
|
|
},
|
|
{
|
|
"entropy": 6.173792791366577,
|
|
"epoch": 0.24017467248908297,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004997753435122522,
|
|
"loss": 6.0082,
|
|
"mean_token_accuracy": 0.12303022742271423,
|
|
"num_tokens": 5326090.0,
|
|
"step": 2420
|
|
},
|
|
{
|
|
"entropy": 6.016424989700317,
|
|
"epoch": 0.2406709011512505,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.00049977375778593,
|
|
"loss": 5.7936,
|
|
"mean_token_accuracy": 0.1281319923698902,
|
|
"num_tokens": 5336423.0,
|
|
"step": 2425
|
|
},
|
|
{
|
|
"entropy": 6.052116632461548,
|
|
"epoch": 0.24116712981341804,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004997721664857032,
|
|
"loss": 5.9728,
|
|
"mean_token_accuracy": 0.12626754492521286,
|
|
"num_tokens": 5346982.0,
|
|
"step": 2430
|
|
},
|
|
{
|
|
"entropy": 5.9658690929412845,
|
|
"epoch": 0.24166335847558554,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004997705696116108,
|
|
"loss": 5.8618,
|
|
"mean_token_accuracy": 0.1352499283850193,
|
|
"num_tokens": 5359210.0,
|
|
"step": 2435
|
|
},
|
|
{
|
|
"entropy": 6.060595321655273,
|
|
"epoch": 0.24215958713775307,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.0004997689671636926,
|
|
"loss": 5.8833,
|
|
"mean_token_accuracy": 0.1232607200741768,
|
|
"num_tokens": 5369891.0,
|
|
"step": 2440
|
|
},
|
|
{
|
|
"entropy": 6.024409484863281,
|
|
"epoch": 0.2426558157999206,
|
|
"grad_norm": 0.80078125,
|
|
"learning_rate": 0.0004997673591419884,
|
|
"loss": 5.8619,
|
|
"mean_token_accuracy": 0.1305900402367115,
|
|
"num_tokens": 5380850.0,
|
|
"step": 2445
|
|
},
|
|
{
|
|
"entropy": 6.061957502365113,
|
|
"epoch": 0.24315204446208813,
|
|
"grad_norm": 0.7890625,
|
|
"learning_rate": 0.0004997657455465381,
|
|
"loss": 5.928,
|
|
"mean_token_accuracy": 0.13309514969587327,
|
|
"num_tokens": 5391903.0,
|
|
"step": 2450
|
|
},
|
|
{
|
|
"entropy": 6.0940954208374025,
|
|
"epoch": 0.24364827312425566,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004997641263773815,
|
|
"loss": 5.978,
|
|
"mean_token_accuracy": 0.12671018466353418,
|
|
"num_tokens": 5402517.0,
|
|
"step": 2455
|
|
},
|
|
{
|
|
"entropy": 5.941332578659058,
|
|
"epoch": 0.2441445017864232,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.000499762501634559,
|
|
"loss": 5.8878,
|
|
"mean_token_accuracy": 0.12774158492684365,
|
|
"num_tokens": 5414110.0,
|
|
"step": 2460
|
|
},
|
|
{
|
|
"entropy": 6.125403642654419,
|
|
"epoch": 0.24464073044859072,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004997608713181108,
|
|
"loss": 5.9006,
|
|
"mean_token_accuracy": 0.12905448973178862,
|
|
"num_tokens": 5424466.0,
|
|
"step": 2465
|
|
},
|
|
{
|
|
"entropy": 6.040532350540161,
|
|
"epoch": 0.24513695911075822,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004997592354280772,
|
|
"loss": 5.9095,
|
|
"mean_token_accuracy": 0.134385783970356,
|
|
"num_tokens": 5434461.0,
|
|
"step": 2470
|
|
},
|
|
{
|
|
"entropy": 5.967836189270019,
|
|
"epoch": 0.24563318777292575,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.000499757593964499,
|
|
"loss": 5.8913,
|
|
"mean_token_accuracy": 0.11896291747689247,
|
|
"num_tokens": 5445921.0,
|
|
"step": 2475
|
|
},
|
|
{
|
|
"entropy": 6.038508701324463,
|
|
"epoch": 0.24612941643509328,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004997559469274166,
|
|
"loss": 5.8771,
|
|
"mean_token_accuracy": 0.13031587675213813,
|
|
"num_tokens": 5456283.0,
|
|
"step": 2480
|
|
},
|
|
{
|
|
"entropy": 6.024613332748413,
|
|
"epoch": 0.24662564509726081,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004997542943168712,
|
|
"loss": 5.9114,
|
|
"mean_token_accuracy": 0.1300675705075264,
|
|
"num_tokens": 5467616.0,
|
|
"step": 2485
|
|
},
|
|
{
|
|
"entropy": 6.012180805206299,
|
|
"epoch": 0.24712187375942835,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004997526361329035,
|
|
"loss": 5.8744,
|
|
"mean_token_accuracy": 0.13522633239626886,
|
|
"num_tokens": 5478050.0,
|
|
"step": 2490
|
|
},
|
|
{
|
|
"entropy": 6.102998495101929,
|
|
"epoch": 0.24761810242159588,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004997509723755547,
|
|
"loss": 5.8714,
|
|
"mean_token_accuracy": 0.12875011935830116,
|
|
"num_tokens": 5487185.0,
|
|
"step": 2495
|
|
},
|
|
{
|
|
"entropy": 5.998979711532593,
|
|
"epoch": 0.2481143310837634,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004997493030448662,
|
|
"loss": 5.8924,
|
|
"mean_token_accuracy": 0.12383673936128617,
|
|
"num_tokens": 5498802.0,
|
|
"step": 2500
|
|
},
|
|
{
|
|
"entropy": 6.0036334037780765,
|
|
"epoch": 0.24861055974593094,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004997476281408793,
|
|
"loss": 5.9009,
|
|
"mean_token_accuracy": 0.12360760122537613,
|
|
"num_tokens": 5510285.0,
|
|
"step": 2505
|
|
},
|
|
{
|
|
"entropy": 6.045953416824341,
|
|
"epoch": 0.24910678840809844,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004997459476636354,
|
|
"loss": 5.7868,
|
|
"mean_token_accuracy": 0.13784014880657197,
|
|
"num_tokens": 5520028.0,
|
|
"step": 2510
|
|
},
|
|
{
|
|
"entropy": 5.9735174655914305,
|
|
"epoch": 0.24960301707026597,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004997442616131763,
|
|
"loss": 5.912,
|
|
"mean_token_accuracy": 0.12859713956713675,
|
|
"num_tokens": 5529271.0,
|
|
"step": 2515
|
|
},
|
|
{
|
|
"entropy": 6.054106569290161,
|
|
"epoch": 0.25009924573243353,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004997425699895438,
|
|
"loss": 5.826,
|
|
"mean_token_accuracy": 0.12208940386772156,
|
|
"num_tokens": 5539396.0,
|
|
"step": 2520
|
|
},
|
|
{
|
|
"entropy": 6.049839782714844,
|
|
"epoch": 0.25059547439460106,
|
|
"grad_norm": 0.76953125,
|
|
"learning_rate": 0.0004997408727927798,
|
|
"loss": 5.9723,
|
|
"mean_token_accuracy": 0.1294700786471367,
|
|
"num_tokens": 5551674.0,
|
|
"step": 2525
|
|
},
|
|
{
|
|
"entropy": 6.055530405044555,
|
|
"epoch": 0.25109170305676853,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004997391700229264,
|
|
"loss": 5.8948,
|
|
"mean_token_accuracy": 0.1298077531158924,
|
|
"num_tokens": 5562749.0,
|
|
"step": 2530
|
|
},
|
|
{
|
|
"entropy": 6.030540132522583,
|
|
"epoch": 0.25158793171893606,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.000499737461680026,
|
|
"loss": 5.9,
|
|
"mean_token_accuracy": 0.12933559864759445,
|
|
"num_tokens": 5573478.0,
|
|
"step": 2535
|
|
},
|
|
{
|
|
"entropy": 5.963146209716797,
|
|
"epoch": 0.2520841603811036,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004997357477641207,
|
|
"loss": 5.8908,
|
|
"mean_token_accuracy": 0.13493381813168526,
|
|
"num_tokens": 5584546.0,
|
|
"step": 2540
|
|
},
|
|
{
|
|
"entropy": 5.964659547805786,
|
|
"epoch": 0.2525803890432711,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004997340282752532,
|
|
"loss": 5.7847,
|
|
"mean_token_accuracy": 0.1342097096145153,
|
|
"num_tokens": 5594004.0,
|
|
"step": 2545
|
|
},
|
|
{
|
|
"entropy": 6.085031366348266,
|
|
"epoch": 0.25307661770543866,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.000499732303213466,
|
|
"loss": 5.8353,
|
|
"mean_token_accuracy": 0.12420367822051048,
|
|
"num_tokens": 5606095.0,
|
|
"step": 2550
|
|
},
|
|
{
|
|
"entropy": 6.014924669265747,
|
|
"epoch": 0.2535728463676062,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004997305725788019,
|
|
"loss": 5.8899,
|
|
"mean_token_accuracy": 0.12461917325854302,
|
|
"num_tokens": 5615596.0,
|
|
"step": 2555
|
|
},
|
|
{
|
|
"entropy": 5.9634756565094,
|
|
"epoch": 0.2540690750297737,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.000499728836371304,
|
|
"loss": 5.8139,
|
|
"mean_token_accuracy": 0.12745841071009636,
|
|
"num_tokens": 5626753.0,
|
|
"step": 2560
|
|
},
|
|
{
|
|
"entropy": 5.963172578811646,
|
|
"epoch": 0.25456530369194125,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004997270945910151,
|
|
"loss": 5.8388,
|
|
"mean_token_accuracy": 0.12756719589233398,
|
|
"num_tokens": 5636135.0,
|
|
"step": 2565
|
|
},
|
|
{
|
|
"entropy": 6.079827070236206,
|
|
"epoch": 0.2550615323541088,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004997253472379785,
|
|
"loss": 5.9086,
|
|
"mean_token_accuracy": 0.12276982814073563,
|
|
"num_tokens": 5647074.0,
|
|
"step": 2570
|
|
},
|
|
{
|
|
"entropy": 6.04095311164856,
|
|
"epoch": 0.2555577610162763,
|
|
"grad_norm": 0.78515625,
|
|
"learning_rate": 0.0004997235943122375,
|
|
"loss": 5.9298,
|
|
"mean_token_accuracy": 0.12193780019879341,
|
|
"num_tokens": 5658600.0,
|
|
"step": 2575
|
|
},
|
|
{
|
|
"entropy": 5.954120779037476,
|
|
"epoch": 0.25605398967844384,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004997218358138356,
|
|
"loss": 5.8184,
|
|
"mean_token_accuracy": 0.12850069105625153,
|
|
"num_tokens": 5668453.0,
|
|
"step": 2580
|
|
},
|
|
{
|
|
"entropy": 6.052977800369263,
|
|
"epoch": 0.25655021834061137,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004997200717428165,
|
|
"loss": 5.8802,
|
|
"mean_token_accuracy": 0.12774283811450005,
|
|
"num_tokens": 5678855.0,
|
|
"step": 2585
|
|
},
|
|
{
|
|
"entropy": 6.0446836948394775,
|
|
"epoch": 0.2570464470027789,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004997183020992237,
|
|
"loss": 5.9438,
|
|
"mean_token_accuracy": 0.12405224218964576,
|
|
"num_tokens": 5690063.0,
|
|
"step": 2590
|
|
},
|
|
{
|
|
"entropy": 5.979913902282715,
|
|
"epoch": 0.25754267566494643,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004997165268831014,
|
|
"loss": 5.843,
|
|
"mean_token_accuracy": 0.1319989301264286,
|
|
"num_tokens": 5701487.0,
|
|
"step": 2595
|
|
},
|
|
{
|
|
"entropy": 5.977937984466553,
|
|
"epoch": 0.25803890432711396,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0004997147460944933,
|
|
"loss": 5.8313,
|
|
"mean_token_accuracy": 0.131146914511919,
|
|
"num_tokens": 5713034.0,
|
|
"step": 2600
|
|
},
|
|
{
|
|
"entropy": 6.07123966217041,
|
|
"epoch": 0.25853513298928144,
|
|
"grad_norm": 0.80078125,
|
|
"learning_rate": 0.0004997129597334438,
|
|
"loss": 5.8811,
|
|
"mean_token_accuracy": 0.13053280711174012,
|
|
"num_tokens": 5725469.0,
|
|
"step": 2605
|
|
},
|
|
{
|
|
"entropy": 5.960973072052002,
|
|
"epoch": 0.25903136165144897,
|
|
"grad_norm": 0.7890625,
|
|
"learning_rate": 0.0004997111677999971,
|
|
"loss": 5.87,
|
|
"mean_token_accuracy": 0.12475038319826126,
|
|
"num_tokens": 5737099.0,
|
|
"step": 2610
|
|
},
|
|
{
|
|
"entropy": 6.032576656341552,
|
|
"epoch": 0.2595275903136165,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0004997093702941976,
|
|
"loss": 5.872,
|
|
"mean_token_accuracy": 0.1248766042292118,
|
|
"num_tokens": 5748756.0,
|
|
"step": 2615
|
|
},
|
|
{
|
|
"entropy": 6.0417296409606935,
|
|
"epoch": 0.260023818975784,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00049970756721609,
|
|
"loss": 5.8727,
|
|
"mean_token_accuracy": 0.12974709644913673,
|
|
"num_tokens": 5759598.0,
|
|
"step": 2620
|
|
},
|
|
{
|
|
"entropy": 6.012347316741943,
|
|
"epoch": 0.26052004763795156,
|
|
"grad_norm": 0.796875,
|
|
"learning_rate": 0.000499705758565719,
|
|
"loss": 5.9157,
|
|
"mean_token_accuracy": 0.12809571251273155,
|
|
"num_tokens": 5770397.0,
|
|
"step": 2625
|
|
},
|
|
{
|
|
"entropy": 6.098965167999268,
|
|
"epoch": 0.2610162763001191,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004997039443431292,
|
|
"loss": 5.983,
|
|
"mean_token_accuracy": 0.11926335170865059,
|
|
"num_tokens": 5780935.0,
|
|
"step": 2630
|
|
},
|
|
{
|
|
"entropy": 6.08192253112793,
|
|
"epoch": 0.2615125049622866,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004997021245483659,
|
|
"loss": 5.8366,
|
|
"mean_token_accuracy": 0.12855549082159995,
|
|
"num_tokens": 5791557.0,
|
|
"step": 2635
|
|
},
|
|
{
|
|
"entropy": 5.944977807998657,
|
|
"epoch": 0.26200873362445415,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.000499700299181474,
|
|
"loss": 5.874,
|
|
"mean_token_accuracy": 0.12412384524941444,
|
|
"num_tokens": 5802233.0,
|
|
"step": 2640
|
|
},
|
|
{
|
|
"entropy": 5.984538125991821,
|
|
"epoch": 0.2625049622866217,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004996984682424989,
|
|
"loss": 5.7929,
|
|
"mean_token_accuracy": 0.13563756346702577,
|
|
"num_tokens": 5813424.0,
|
|
"step": 2645
|
|
},
|
|
{
|
|
"entropy": 5.963291454315185,
|
|
"epoch": 0.2630011909487892,
|
|
"grad_norm": 0.74609375,
|
|
"learning_rate": 0.000499696631731486,
|
|
"loss": 5.7802,
|
|
"mean_token_accuracy": 0.13106578662991525,
|
|
"num_tokens": 5825652.0,
|
|
"step": 2650
|
|
},
|
|
{
|
|
"entropy": 6.034928655624389,
|
|
"epoch": 0.26349741961095674,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004996947896484809,
|
|
"loss": 5.865,
|
|
"mean_token_accuracy": 0.13201481997966766,
|
|
"num_tokens": 5836603.0,
|
|
"step": 2655
|
|
},
|
|
{
|
|
"entropy": 5.982569742202759,
|
|
"epoch": 0.26399364827312427,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.000499692941993529,
|
|
"loss": 5.9128,
|
|
"mean_token_accuracy": 0.1318881943821907,
|
|
"num_tokens": 5849365.0,
|
|
"step": 2660
|
|
},
|
|
{
|
|
"entropy": 6.044679498672485,
|
|
"epoch": 0.2644898769352918,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004996910887666765,
|
|
"loss": 5.8354,
|
|
"mean_token_accuracy": 0.1336039572954178,
|
|
"num_tokens": 5860305.0,
|
|
"step": 2665
|
|
},
|
|
{
|
|
"entropy": 5.926130056381226,
|
|
"epoch": 0.26498610559745933,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.000499689229967969,
|
|
"loss": 5.7666,
|
|
"mean_token_accuracy": 0.13250631913542749,
|
|
"num_tokens": 5872272.0,
|
|
"step": 2670
|
|
},
|
|
{
|
|
"entropy": 5.9937135696411135,
|
|
"epoch": 0.26548233425962686,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004996873655974529,
|
|
"loss": 5.8152,
|
|
"mean_token_accuracy": 0.12750425711274146,
|
|
"num_tokens": 5884107.0,
|
|
"step": 2675
|
|
},
|
|
{
|
|
"entropy": 5.906749153137207,
|
|
"epoch": 0.26597856292179434,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004996854956551743,
|
|
"loss": 5.8092,
|
|
"mean_token_accuracy": 0.13456383347511292,
|
|
"num_tokens": 5894060.0,
|
|
"step": 2680
|
|
},
|
|
{
|
|
"entropy": 5.9789345264434814,
|
|
"epoch": 0.26647479158396187,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004996836201411794,
|
|
"loss": 5.8238,
|
|
"mean_token_accuracy": 0.1331551544368267,
|
|
"num_tokens": 5904804.0,
|
|
"step": 2685
|
|
},
|
|
{
|
|
"entropy": 6.056610536575318,
|
|
"epoch": 0.2669710202461294,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000499681739055515,
|
|
"loss": 5.8861,
|
|
"mean_token_accuracy": 0.1274963565170765,
|
|
"num_tokens": 5916496.0,
|
|
"step": 2690
|
|
},
|
|
{
|
|
"entropy": 5.9887939453125,
|
|
"epoch": 0.26746724890829693,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004996798523982276,
|
|
"loss": 5.831,
|
|
"mean_token_accuracy": 0.1256636656820774,
|
|
"num_tokens": 5926920.0,
|
|
"step": 2695
|
|
},
|
|
{
|
|
"entropy": 6.095494651794434,
|
|
"epoch": 0.26796347757046446,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.000499677960169364,
|
|
"loss": 5.935,
|
|
"mean_token_accuracy": 0.12686496153473853,
|
|
"num_tokens": 5940098.0,
|
|
"step": 2700
|
|
},
|
|
{
|
|
"entropy": 5.972264385223388,
|
|
"epoch": 0.268459706232632,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004996760623689711,
|
|
"loss": 5.7841,
|
|
"mean_token_accuracy": 0.13265340775251389,
|
|
"num_tokens": 5949687.0,
|
|
"step": 2705
|
|
},
|
|
{
|
|
"entropy": 5.992936277389527,
|
|
"epoch": 0.2689559348947995,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.000499674158997096,
|
|
"loss": 5.9045,
|
|
"mean_token_accuracy": 0.1267220564186573,
|
|
"num_tokens": 5960777.0,
|
|
"step": 2710
|
|
},
|
|
{
|
|
"entropy": 6.038538122177124,
|
|
"epoch": 0.26945216355696705,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004996722500537859,
|
|
"loss": 5.8095,
|
|
"mean_token_accuracy": 0.12924240455031394,
|
|
"num_tokens": 5972298.0,
|
|
"step": 2715
|
|
},
|
|
{
|
|
"entropy": 5.961693143844604,
|
|
"epoch": 0.2699483922191346,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004996703355390881,
|
|
"loss": 5.9214,
|
|
"mean_token_accuracy": 0.12794365584850312,
|
|
"num_tokens": 5985613.0,
|
|
"step": 2720
|
|
},
|
|
{
|
|
"entropy": 6.043231201171875,
|
|
"epoch": 0.2704446208813021,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.00049966841545305,
|
|
"loss": 5.9656,
|
|
"mean_token_accuracy": 0.1257025733590126,
|
|
"num_tokens": 5997530.0,
|
|
"step": 2725
|
|
},
|
|
{
|
|
"entropy": 6.031536388397217,
|
|
"epoch": 0.27094084954346964,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004996664897957195,
|
|
"loss": 5.8365,
|
|
"mean_token_accuracy": 0.12756068184971808,
|
|
"num_tokens": 6008123.0,
|
|
"step": 2730
|
|
},
|
|
{
|
|
"entropy": 6.018695735931397,
|
|
"epoch": 0.2714370782056372,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004996645585671441,
|
|
"loss": 5.852,
|
|
"mean_token_accuracy": 0.13391014859080314,
|
|
"num_tokens": 6020578.0,
|
|
"step": 2735
|
|
},
|
|
{
|
|
"entropy": 5.907762765884399,
|
|
"epoch": 0.2719333068678047,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004996626217673717,
|
|
"loss": 5.7793,
|
|
"mean_token_accuracy": 0.1337601587176323,
|
|
"num_tokens": 6031625.0,
|
|
"step": 2740
|
|
},
|
|
{
|
|
"entropy": 5.958955860137939,
|
|
"epoch": 0.27242953552997223,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004996606793964504,
|
|
"loss": 5.8286,
|
|
"mean_token_accuracy": 0.13649252206087112,
|
|
"num_tokens": 6041320.0,
|
|
"step": 2745
|
|
},
|
|
{
|
|
"entropy": 6.01719069480896,
|
|
"epoch": 0.27292576419213976,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004996587314544284,
|
|
"loss": 5.8369,
|
|
"mean_token_accuracy": 0.12664347812533377,
|
|
"num_tokens": 6052627.0,
|
|
"step": 2750
|
|
},
|
|
{
|
|
"entropy": 5.954709434509278,
|
|
"epoch": 0.27342199285430724,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004996567779413539,
|
|
"loss": 5.8036,
|
|
"mean_token_accuracy": 0.13628075420856475,
|
|
"num_tokens": 6063468.0,
|
|
"step": 2755
|
|
},
|
|
{
|
|
"entropy": 5.991281652450562,
|
|
"epoch": 0.27391822151647477,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004996548188572755,
|
|
"loss": 5.7814,
|
|
"mean_token_accuracy": 0.1363678827881813,
|
|
"num_tokens": 6074208.0,
|
|
"step": 2760
|
|
},
|
|
{
|
|
"entropy": 5.994483947753906,
|
|
"epoch": 0.2744144501786423,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004996528542022416,
|
|
"loss": 5.8366,
|
|
"mean_token_accuracy": 0.12587395310401917,
|
|
"num_tokens": 6085068.0,
|
|
"step": 2765
|
|
},
|
|
{
|
|
"entropy": 5.959670734405518,
|
|
"epoch": 0.27491067884080983,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.000499650883976301,
|
|
"loss": 5.844,
|
|
"mean_token_accuracy": 0.12782294154167176,
|
|
"num_tokens": 6096445.0,
|
|
"step": 2770
|
|
},
|
|
{
|
|
"entropy": 5.91315975189209,
|
|
"epoch": 0.27540690750297736,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004996489081795026,
|
|
"loss": 5.7401,
|
|
"mean_token_accuracy": 0.13289162740111352,
|
|
"num_tokens": 6106527.0,
|
|
"step": 2775
|
|
},
|
|
{
|
|
"entropy": 5.91305251121521,
|
|
"epoch": 0.2759031361651449,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004996469268118953,
|
|
"loss": 5.7589,
|
|
"mean_token_accuracy": 0.13679778575897217,
|
|
"num_tokens": 6115923.0,
|
|
"step": 2780
|
|
},
|
|
{
|
|
"entropy": 5.868895196914673,
|
|
"epoch": 0.2763993648273124,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004996449398735283,
|
|
"loss": 5.6526,
|
|
"mean_token_accuracy": 0.13616614267230034,
|
|
"num_tokens": 6125861.0,
|
|
"step": 2785
|
|
},
|
|
{
|
|
"entropy": 6.010179805755615,
|
|
"epoch": 0.27689559348947995,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.0004996429473644509,
|
|
"loss": 5.8537,
|
|
"mean_token_accuracy": 0.13069555088877677,
|
|
"num_tokens": 6137189.0,
|
|
"step": 2790
|
|
},
|
|
{
|
|
"entropy": 5.97644534111023,
|
|
"epoch": 0.2773918221516475,
|
|
"grad_norm": 0.77734375,
|
|
"learning_rate": 0.0004996409492847124,
|
|
"loss": 5.7804,
|
|
"mean_token_accuracy": 0.13484650626778602,
|
|
"num_tokens": 6147920.0,
|
|
"step": 2795
|
|
},
|
|
{
|
|
"entropy": 5.939912557601929,
|
|
"epoch": 0.277888050813815,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004996389456343624,
|
|
"loss": 5.7712,
|
|
"mean_token_accuracy": 0.13595055788755417,
|
|
"num_tokens": 6159371.0,
|
|
"step": 2800
|
|
},
|
|
{
|
|
"entropy": 6.066695976257324,
|
|
"epoch": 0.27838427947598254,
|
|
"grad_norm": 0.75,
|
|
"learning_rate": 0.0004996369364134507,
|
|
"loss": 5.9699,
|
|
"mean_token_accuracy": 0.12258584052324295,
|
|
"num_tokens": 6172679.0,
|
|
"step": 2805
|
|
},
|
|
{
|
|
"entropy": 5.927506589889527,
|
|
"epoch": 0.2788805081381501,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.000499634921622027,
|
|
"loss": 5.8298,
|
|
"mean_token_accuracy": 0.12628915533423424,
|
|
"num_tokens": 6184244.0,
|
|
"step": 2810
|
|
},
|
|
{
|
|
"entropy": 5.933115148544312,
|
|
"epoch": 0.2793767368003176,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004996329012601413,
|
|
"loss": 5.706,
|
|
"mean_token_accuracy": 0.1285858377814293,
|
|
"num_tokens": 6194826.0,
|
|
"step": 2815
|
|
},
|
|
{
|
|
"entropy": 5.979615592956543,
|
|
"epoch": 0.27987296546248513,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004996308753278437,
|
|
"loss": 5.8456,
|
|
"mean_token_accuracy": 0.13074849992990495,
|
|
"num_tokens": 6206808.0,
|
|
"step": 2820
|
|
},
|
|
{
|
|
"entropy": 6.013004970550537,
|
|
"epoch": 0.28036919412465267,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004996288438251843,
|
|
"loss": 5.8605,
|
|
"mean_token_accuracy": 0.12552075758576392,
|
|
"num_tokens": 6217303.0,
|
|
"step": 2825
|
|
},
|
|
{
|
|
"entropy": 5.992705678939819,
|
|
"epoch": 0.28086542278682014,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004996268067522137,
|
|
"loss": 5.8603,
|
|
"mean_token_accuracy": 0.12485205754637718,
|
|
"num_tokens": 6227965.0,
|
|
"step": 2830
|
|
},
|
|
{
|
|
"entropy": 6.082558679580688,
|
|
"epoch": 0.28136165144898767,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004996247641089823,
|
|
"loss": 5.919,
|
|
"mean_token_accuracy": 0.12674327939748764,
|
|
"num_tokens": 6239011.0,
|
|
"step": 2835
|
|
},
|
|
{
|
|
"entropy": 5.880522966384888,
|
|
"epoch": 0.2818578801111552,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004996227158955409,
|
|
"loss": 5.7612,
|
|
"mean_token_accuracy": 0.13352836593985556,
|
|
"num_tokens": 6249084.0,
|
|
"step": 2840
|
|
},
|
|
{
|
|
"entropy": 5.958843946456909,
|
|
"epoch": 0.28235410877332273,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.00049962066211194,
|
|
"loss": 5.8334,
|
|
"mean_token_accuracy": 0.12839528918266296,
|
|
"num_tokens": 6260706.0,
|
|
"step": 2845
|
|
},
|
|
{
|
|
"entropy": 5.931930923461914,
|
|
"epoch": 0.28285033743549026,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004996186027582308,
|
|
"loss": 5.7522,
|
|
"mean_token_accuracy": 0.13635355457663537,
|
|
"num_tokens": 6272848.0,
|
|
"step": 2850
|
|
},
|
|
{
|
|
"entropy": 5.946898508071899,
|
|
"epoch": 0.2833465660976578,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004996165378344642,
|
|
"loss": 5.7663,
|
|
"mean_token_accuracy": 0.13342537730932236,
|
|
"num_tokens": 6283820.0,
|
|
"step": 2855
|
|
},
|
|
{
|
|
"entropy": 5.972999238967896,
|
|
"epoch": 0.2838427947598253,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004996144673406914,
|
|
"loss": 5.9339,
|
|
"mean_token_accuracy": 0.12071966528892517,
|
|
"num_tokens": 6294193.0,
|
|
"step": 2860
|
|
},
|
|
{
|
|
"entropy": 5.960216379165649,
|
|
"epoch": 0.28433902342199285,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004996123912769639,
|
|
"loss": 5.7676,
|
|
"mean_token_accuracy": 0.1383022852241993,
|
|
"num_tokens": 6304407.0,
|
|
"step": 2865
|
|
},
|
|
{
|
|
"entropy": 5.893539810180664,
|
|
"epoch": 0.2848352520841604,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.0004996103096433332,
|
|
"loss": 5.8421,
|
|
"mean_token_accuracy": 0.12886647060513495,
|
|
"num_tokens": 6316311.0,
|
|
"step": 2870
|
|
},
|
|
{
|
|
"entropy": 6.00091586112976,
|
|
"epoch": 0.2853314807463279,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004996082224398506,
|
|
"loss": 5.8144,
|
|
"mean_token_accuracy": 0.13291785418987273,
|
|
"num_tokens": 6327248.0,
|
|
"step": 2875
|
|
},
|
|
{
|
|
"entropy": 5.986534309387207,
|
|
"epoch": 0.28582770940849545,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004996061296665682,
|
|
"loss": 5.8325,
|
|
"mean_token_accuracy": 0.12824170365929605,
|
|
"num_tokens": 6338494.0,
|
|
"step": 2880
|
|
},
|
|
{
|
|
"entropy": 5.9684656143188475,
|
|
"epoch": 0.286323938070663,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004996040313235377,
|
|
"loss": 5.7233,
|
|
"mean_token_accuracy": 0.13372908607125283,
|
|
"num_tokens": 6349038.0,
|
|
"step": 2885
|
|
},
|
|
{
|
|
"entropy": 5.902253913879394,
|
|
"epoch": 0.2868201667328305,
|
|
"grad_norm": 0.80078125,
|
|
"learning_rate": 0.0004996019274108112,
|
|
"loss": 5.8233,
|
|
"mean_token_accuracy": 0.13003271594643592,
|
|
"num_tokens": 6360180.0,
|
|
"step": 2890
|
|
},
|
|
{
|
|
"entropy": 5.906910562515259,
|
|
"epoch": 0.28731639539499804,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.000499599817928441,
|
|
"loss": 5.7596,
|
|
"mean_token_accuracy": 0.13310305699706076,
|
|
"num_tokens": 6370931.0,
|
|
"step": 2895
|
|
},
|
|
{
|
|
"entropy": 5.877241802215576,
|
|
"epoch": 0.28781262405716557,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004995977028764792,
|
|
"loss": 5.7375,
|
|
"mean_token_accuracy": 0.13817125037312508,
|
|
"num_tokens": 6381810.0,
|
|
"step": 2900
|
|
},
|
|
{
|
|
"entropy": 5.958535528182983,
|
|
"epoch": 0.28830885271933304,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004995955822549783,
|
|
"loss": 5.7447,
|
|
"mean_token_accuracy": 0.1337203674018383,
|
|
"num_tokens": 6392268.0,
|
|
"step": 2905
|
|
},
|
|
{
|
|
"entropy": 5.885456800460815,
|
|
"epoch": 0.2888050813815006,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004995934560639909,
|
|
"loss": 5.8172,
|
|
"mean_token_accuracy": 0.13473332896828652,
|
|
"num_tokens": 6403650.0,
|
|
"step": 2910
|
|
},
|
|
{
|
|
"entropy": 5.995740032196045,
|
|
"epoch": 0.2893013100436681,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004995913243035699,
|
|
"loss": 5.7959,
|
|
"mean_token_accuracy": 0.12757119312882423,
|
|
"num_tokens": 6414672.0,
|
|
"step": 2915
|
|
},
|
|
{
|
|
"entropy": 5.970022487640381,
|
|
"epoch": 0.28979753870583563,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004995891869737678,
|
|
"loss": 5.8593,
|
|
"mean_token_accuracy": 0.12999678775668144,
|
|
"num_tokens": 6424916.0,
|
|
"step": 2920
|
|
},
|
|
{
|
|
"entropy": 5.960818958282471,
|
|
"epoch": 0.29029376736800316,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004995870440746379,
|
|
"loss": 5.8059,
|
|
"mean_token_accuracy": 0.13466615676879884,
|
|
"num_tokens": 6435950.0,
|
|
"step": 2925
|
|
},
|
|
{
|
|
"entropy": 5.905315399169922,
|
|
"epoch": 0.2907899960301707,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.0004995848956062333,
|
|
"loss": 5.7742,
|
|
"mean_token_accuracy": 0.1341630332171917,
|
|
"num_tokens": 6446336.0,
|
|
"step": 2930
|
|
},
|
|
{
|
|
"entropy": 5.917783546447754,
|
|
"epoch": 0.2912862246923382,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004995827415686071,
|
|
"loss": 5.8452,
|
|
"mean_token_accuracy": 0.13145026564598083,
|
|
"num_tokens": 6457655.0,
|
|
"step": 2935
|
|
},
|
|
{
|
|
"entropy": 5.985751056671143,
|
|
"epoch": 0.29178245335450576,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.000499580581961813,
|
|
"loss": 5.7235,
|
|
"mean_token_accuracy": 0.13669102862477303,
|
|
"num_tokens": 6469627.0,
|
|
"step": 2940
|
|
},
|
|
{
|
|
"entropy": 5.918372678756714,
|
|
"epoch": 0.2922786820166733,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004995784167859043,
|
|
"loss": 5.825,
|
|
"mean_token_accuracy": 0.129074639827013,
|
|
"num_tokens": 6480351.0,
|
|
"step": 2945
|
|
},
|
|
{
|
|
"entropy": 6.008989477157593,
|
|
"epoch": 0.2927749106788408,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004995762460409349,
|
|
"loss": 5.8548,
|
|
"mean_token_accuracy": 0.1337804116308689,
|
|
"num_tokens": 6491651.0,
|
|
"step": 2950
|
|
},
|
|
{
|
|
"entropy": 5.920342969894409,
|
|
"epoch": 0.29327113934100835,
|
|
"grad_norm": 0.79296875,
|
|
"learning_rate": 0.0004995740697269584,
|
|
"loss": 5.6923,
|
|
"mean_token_accuracy": 0.13204924538731574,
|
|
"num_tokens": 6502531.0,
|
|
"step": 2955
|
|
},
|
|
{
|
|
"entropy": 5.878091621398926,
|
|
"epoch": 0.2937673680031759,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004995718878440289,
|
|
"loss": 5.7131,
|
|
"mean_token_accuracy": 0.14013013020157813,
|
|
"num_tokens": 6511938.0,
|
|
"step": 2960
|
|
},
|
|
{
|
|
"entropy": 6.0145423412323,
|
|
"epoch": 0.2942635966653434,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004995697003922006,
|
|
"loss": 5.8628,
|
|
"mean_token_accuracy": 0.1239828608930111,
|
|
"num_tokens": 6522775.0,
|
|
"step": 2965
|
|
},
|
|
{
|
|
"entropy": 5.953707361221314,
|
|
"epoch": 0.29475982532751094,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.0004995675073715274,
|
|
"loss": 5.681,
|
|
"mean_token_accuracy": 0.13056408539414405,
|
|
"num_tokens": 6534660.0,
|
|
"step": 2970
|
|
},
|
|
{
|
|
"entropy": 5.901784515380859,
|
|
"epoch": 0.29525605398967847,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004995653087820641,
|
|
"loss": 5.8299,
|
|
"mean_token_accuracy": 0.13245153054594994,
|
|
"num_tokens": 6545673.0,
|
|
"step": 2975
|
|
},
|
|
{
|
|
"entropy": 5.9352250576019285,
|
|
"epoch": 0.29575228265184594,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.000499563104623865,
|
|
"loss": 5.7862,
|
|
"mean_token_accuracy": 0.1360513038933277,
|
|
"num_tokens": 6556912.0,
|
|
"step": 2980
|
|
},
|
|
{
|
|
"entropy": 5.981804084777832,
|
|
"epoch": 0.2962485113140135,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004995608948969849,
|
|
"loss": 5.8789,
|
|
"mean_token_accuracy": 0.12770932540297508,
|
|
"num_tokens": 6567532.0,
|
|
"step": 2985
|
|
},
|
|
{
|
|
"entropy": 5.955900192260742,
|
|
"epoch": 0.296744739976181,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004995586796014784,
|
|
"loss": 5.8553,
|
|
"mean_token_accuracy": 0.13003772795200347,
|
|
"num_tokens": 6577830.0,
|
|
"step": 2990
|
|
},
|
|
{
|
|
"entropy": 5.927827978134156,
|
|
"epoch": 0.29724096863834853,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004995564587374005,
|
|
"loss": 5.7476,
|
|
"mean_token_accuracy": 0.13181802555918692,
|
|
"num_tokens": 6587254.0,
|
|
"step": 2995
|
|
},
|
|
{
|
|
"entropy": 5.962104320526123,
|
|
"epoch": 0.29773719730051607,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004995542323048063,
|
|
"loss": 5.934,
|
|
"mean_token_accuracy": 0.12504435703158379,
|
|
"num_tokens": 6598294.0,
|
|
"step": 3000
|
|
},
|
|
{
|
|
"epoch": 0.29773719730051607,
|
|
"eval_entropy": 5.7928955505681055,
|
|
"eval_loss": 5.8702263832092285,
|
|
"eval_mean_token_accuracy": 0.13254506512458533,
|
|
"eval_num_tokens": 6598294.0,
|
|
"eval_runtime": 20.7058,
|
|
"eval_samples_per_second": 1626.066,
|
|
"eval_steps_per_second": 203.276,
|
|
"step": 3000
|
|
},
|
|
{
|
|
"entropy": 6.02299394607544,
|
|
"epoch": 0.2982334259626836,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.000499552000303751,
|
|
"loss": 5.8132,
|
|
"mean_token_accuracy": 0.13359044566750528,
|
|
"num_tokens": 6608772.0,
|
|
"step": 3005
|
|
},
|
|
{
|
|
"entropy": 5.907866477966309,
|
|
"epoch": 0.2987296546248511,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.00049954976273429,
|
|
"loss": 5.8093,
|
|
"mean_token_accuracy": 0.1337615132331848,
|
|
"num_tokens": 6619973.0,
|
|
"step": 3010
|
|
},
|
|
{
|
|
"entropy": 5.9264623641967775,
|
|
"epoch": 0.29922588328701866,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004995475195964787,
|
|
"loss": 5.8292,
|
|
"mean_token_accuracy": 0.13057641312479973,
|
|
"num_tokens": 6631172.0,
|
|
"step": 3015
|
|
},
|
|
{
|
|
"entropy": 5.9544103145599365,
|
|
"epoch": 0.2997221119491862,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004995452708903727,
|
|
"loss": 5.8188,
|
|
"mean_token_accuracy": 0.12836946919560432,
|
|
"num_tokens": 6641343.0,
|
|
"step": 3020
|
|
},
|
|
{
|
|
"entropy": 5.912361097335816,
|
|
"epoch": 0.3002183406113537,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.000499543016616028,
|
|
"loss": 5.7628,
|
|
"mean_token_accuracy": 0.13423253819346428,
|
|
"num_tokens": 6652892.0,
|
|
"step": 3025
|
|
},
|
|
{
|
|
"entropy": 5.965789175033569,
|
|
"epoch": 0.30071456927352125,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004995407567735002,
|
|
"loss": 5.7887,
|
|
"mean_token_accuracy": 0.13260234743356705,
|
|
"num_tokens": 6664177.0,
|
|
"step": 3030
|
|
},
|
|
{
|
|
"entropy": 5.903903007507324,
|
|
"epoch": 0.3012107979356888,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004995384913628456,
|
|
"loss": 5.7612,
|
|
"mean_token_accuracy": 0.13183784186840058,
|
|
"num_tokens": 6674402.0,
|
|
"step": 3035
|
|
},
|
|
{
|
|
"entropy": 5.972148370742798,
|
|
"epoch": 0.3017070265978563,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004995362203841202,
|
|
"loss": 5.8938,
|
|
"mean_token_accuracy": 0.12839276492595672,
|
|
"num_tokens": 6684886.0,
|
|
"step": 3040
|
|
},
|
|
{
|
|
"entropy": 5.954754209518432,
|
|
"epoch": 0.30220325526002384,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004995339438373804,
|
|
"loss": 5.7202,
|
|
"mean_token_accuracy": 0.135014508664608,
|
|
"num_tokens": 6694774.0,
|
|
"step": 3045
|
|
},
|
|
{
|
|
"entropy": 5.888301420211792,
|
|
"epoch": 0.30269948392219137,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004995316617226825,
|
|
"loss": 5.7818,
|
|
"mean_token_accuracy": 0.13432007953524588,
|
|
"num_tokens": 6705346.0,
|
|
"step": 3050
|
|
},
|
|
{
|
|
"entropy": 5.871857500076294,
|
|
"epoch": 0.30319571258435885,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004995293740400833,
|
|
"loss": 5.7312,
|
|
"mean_token_accuracy": 0.13942001089453698,
|
|
"num_tokens": 6715579.0,
|
|
"step": 3055
|
|
},
|
|
{
|
|
"entropy": 5.8535606384277346,
|
|
"epoch": 0.3036919412465264,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004995270807896395,
|
|
"loss": 5.6946,
|
|
"mean_token_accuracy": 0.13676538467407226,
|
|
"num_tokens": 6726382.0,
|
|
"step": 3060
|
|
},
|
|
{
|
|
"entropy": 5.935056352615357,
|
|
"epoch": 0.3041881699086939,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004995247819714079,
|
|
"loss": 5.7698,
|
|
"mean_token_accuracy": 0.1337558187544346,
|
|
"num_tokens": 6737245.0,
|
|
"step": 3065
|
|
},
|
|
{
|
|
"entropy": 5.979394245147705,
|
|
"epoch": 0.30468439857086144,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004995224775854454,
|
|
"loss": 5.9624,
|
|
"mean_token_accuracy": 0.12612314149737358,
|
|
"num_tokens": 6749113.0,
|
|
"step": 3070
|
|
},
|
|
{
|
|
"entropy": 6.009639263153076,
|
|
"epoch": 0.30518062723302897,
|
|
"grad_norm": 0.78125,
|
|
"learning_rate": 0.0004995201676318093,
|
|
"loss": 5.8219,
|
|
"mean_token_accuracy": 0.1318033404648304,
|
|
"num_tokens": 6761987.0,
|
|
"step": 3075
|
|
},
|
|
{
|
|
"entropy": 5.9234983921051025,
|
|
"epoch": 0.3056768558951965,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004995178521105568,
|
|
"loss": 5.766,
|
|
"mean_token_accuracy": 0.12556311190128328,
|
|
"num_tokens": 6771279.0,
|
|
"step": 3080
|
|
},
|
|
{
|
|
"entropy": 5.889677429199219,
|
|
"epoch": 0.30617308455736403,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004995155310217454,
|
|
"loss": 5.6911,
|
|
"mean_token_accuracy": 0.1361276350915432,
|
|
"num_tokens": 6781038.0,
|
|
"step": 3085
|
|
},
|
|
{
|
|
"entropy": 5.8956520557403564,
|
|
"epoch": 0.30666931321953156,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004995132043654327,
|
|
"loss": 5.8346,
|
|
"mean_token_accuracy": 0.13275470435619355,
|
|
"num_tokens": 6792686.0,
|
|
"step": 3090
|
|
},
|
|
{
|
|
"entropy": 5.951267910003662,
|
|
"epoch": 0.3071655418816991,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.0004995108721416763,
|
|
"loss": 5.8074,
|
|
"mean_token_accuracy": 0.139174947142601,
|
|
"num_tokens": 6804414.0,
|
|
"step": 3095
|
|
},
|
|
{
|
|
"entropy": 5.929559230804443,
|
|
"epoch": 0.3076617705438666,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004995085343505339,
|
|
"loss": 5.7652,
|
|
"mean_token_accuracy": 0.13180396631360053,
|
|
"num_tokens": 6816180.0,
|
|
"step": 3100
|
|
},
|
|
{
|
|
"entropy": 5.945132160186768,
|
|
"epoch": 0.30815799920603415,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004995061909920638,
|
|
"loss": 5.778,
|
|
"mean_token_accuracy": 0.1298554077744484,
|
|
"num_tokens": 6827114.0,
|
|
"step": 3105
|
|
},
|
|
{
|
|
"entropy": 5.969542980194092,
|
|
"epoch": 0.3086542278682017,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004995038420663238,
|
|
"loss": 5.8373,
|
|
"mean_token_accuracy": 0.13185039311647415,
|
|
"num_tokens": 6836953.0,
|
|
"step": 3110
|
|
},
|
|
{
|
|
"entropy": 5.944265985488892,
|
|
"epoch": 0.3091504565303692,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004995014875733724,
|
|
"loss": 5.8746,
|
|
"mean_token_accuracy": 0.12786564826965333,
|
|
"num_tokens": 6847963.0,
|
|
"step": 3115
|
|
},
|
|
{
|
|
"entropy": 5.981411457061768,
|
|
"epoch": 0.30964668519253674,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004994991275132678,
|
|
"loss": 5.8869,
|
|
"mean_token_accuracy": 0.12628084421157837,
|
|
"num_tokens": 6858264.0,
|
|
"step": 3120
|
|
},
|
|
{
|
|
"entropy": 5.948660182952881,
|
|
"epoch": 0.31014291385470427,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004994967618860685,
|
|
"loss": 5.7736,
|
|
"mean_token_accuracy": 0.13805429711937905,
|
|
"num_tokens": 6868861.0,
|
|
"step": 3125
|
|
},
|
|
{
|
|
"entropy": 5.981192207336425,
|
|
"epoch": 0.31063914251687175,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004994943906918333,
|
|
"loss": 5.7972,
|
|
"mean_token_accuracy": 0.13693608418107034,
|
|
"num_tokens": 6879797.0,
|
|
"step": 3130
|
|
},
|
|
{
|
|
"entropy": 5.884922504425049,
|
|
"epoch": 0.3111353711790393,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004994920139306211,
|
|
"loss": 5.7463,
|
|
"mean_token_accuracy": 0.13194068968296052,
|
|
"num_tokens": 6891323.0,
|
|
"step": 3135
|
|
},
|
|
{
|
|
"entropy": 5.909702634811401,
|
|
"epoch": 0.3116315998412068,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004994896316024906,
|
|
"loss": 5.8044,
|
|
"mean_token_accuracy": 0.13013609647750854,
|
|
"num_tokens": 6903345.0,
|
|
"step": 3140
|
|
},
|
|
{
|
|
"entropy": 5.932398700714112,
|
|
"epoch": 0.31212782850337434,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.000499487243707501,
|
|
"loss": 5.7547,
|
|
"mean_token_accuracy": 0.13403790220618247,
|
|
"num_tokens": 6914342.0,
|
|
"step": 3145
|
|
},
|
|
{
|
|
"entropy": 5.918168926239014,
|
|
"epoch": 0.31262405716554187,
|
|
"grad_norm": 0.79296875,
|
|
"learning_rate": 0.0004994848502457114,
|
|
"loss": 5.8166,
|
|
"mean_token_accuracy": 0.13116133585572243,
|
|
"num_tokens": 6926691.0,
|
|
"step": 3150
|
|
},
|
|
{
|
|
"entropy": 5.885048723220825,
|
|
"epoch": 0.3131202858277094,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004994824512171812,
|
|
"loss": 5.7052,
|
|
"mean_token_accuracy": 0.13244526460766792,
|
|
"num_tokens": 6937841.0,
|
|
"step": 3155
|
|
},
|
|
{
|
|
"entropy": 5.895932054519653,
|
|
"epoch": 0.31361651448987693,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004994800466219701,
|
|
"loss": 5.781,
|
|
"mean_token_accuracy": 0.12934989854693413,
|
|
"num_tokens": 6948601.0,
|
|
"step": 3160
|
|
},
|
|
{
|
|
"entropy": 5.95720477104187,
|
|
"epoch": 0.31411274315204446,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004994776364601374,
|
|
"loss": 5.7171,
|
|
"mean_token_accuracy": 0.13609042316675185,
|
|
"num_tokens": 6959775.0,
|
|
"step": 3165
|
|
},
|
|
{
|
|
"entropy": 5.85569396018982,
|
|
"epoch": 0.314608971814212,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004994752207317431,
|
|
"loss": 5.7471,
|
|
"mean_token_accuracy": 0.1365107588469982,
|
|
"num_tokens": 6969202.0,
|
|
"step": 3170
|
|
},
|
|
{
|
|
"entropy": 5.846676874160766,
|
|
"epoch": 0.3151052004763795,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.000499472799436847,
|
|
"loss": 5.7296,
|
|
"mean_token_accuracy": 0.136111731082201,
|
|
"num_tokens": 6978633.0,
|
|
"step": 3175
|
|
},
|
|
{
|
|
"entropy": 6.046626424789428,
|
|
"epoch": 0.31560142913854705,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004994703725755092,
|
|
"loss": 5.7934,
|
|
"mean_token_accuracy": 0.13145529180765153,
|
|
"num_tokens": 6989638.0,
|
|
"step": 3180
|
|
},
|
|
{
|
|
"entropy": 5.903738021850586,
|
|
"epoch": 0.3160976578007146,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004994679401477899,
|
|
"loss": 5.7616,
|
|
"mean_token_accuracy": 0.1309955298900604,
|
|
"num_tokens": 7001606.0,
|
|
"step": 3185
|
|
},
|
|
{
|
|
"entropy": 5.860150480270386,
|
|
"epoch": 0.3165938864628821,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004994655021537492,
|
|
"loss": 5.7334,
|
|
"mean_token_accuracy": 0.13141413554549217,
|
|
"num_tokens": 7012915.0,
|
|
"step": 3190
|
|
},
|
|
{
|
|
"entropy": 5.89152774810791,
|
|
"epoch": 0.31709011512504964,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004994630585934478,
|
|
"loss": 5.7898,
|
|
"mean_token_accuracy": 0.12930853962898253,
|
|
"num_tokens": 7023191.0,
|
|
"step": 3195
|
|
},
|
|
{
|
|
"entropy": 5.914811658859253,
|
|
"epoch": 0.3175863437872172,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004994606094669463,
|
|
"loss": 5.681,
|
|
"mean_token_accuracy": 0.13937111124396323,
|
|
"num_tokens": 7032506.0,
|
|
"step": 3200
|
|
},
|
|
{
|
|
"entropy": 5.89855432510376,
|
|
"epoch": 0.3180825724493847,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004994581547743053,
|
|
"loss": 5.814,
|
|
"mean_token_accuracy": 0.12698504626750945,
|
|
"num_tokens": 7046098.0,
|
|
"step": 3205
|
|
},
|
|
{
|
|
"entropy": 6.016089820861817,
|
|
"epoch": 0.3185788011115522,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004994556945155857,
|
|
"loss": 5.8264,
|
|
"mean_token_accuracy": 0.13558279499411582,
|
|
"num_tokens": 7057434.0,
|
|
"step": 3210
|
|
},
|
|
{
|
|
"entropy": 5.82761664390564,
|
|
"epoch": 0.3190750297737197,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004994532286908486,
|
|
"loss": 5.7577,
|
|
"mean_token_accuracy": 0.12784940525889396,
|
|
"num_tokens": 7067674.0,
|
|
"step": 3215
|
|
},
|
|
{
|
|
"entropy": 5.943560075759888,
|
|
"epoch": 0.31957125843588724,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000499450757300155,
|
|
"loss": 5.8249,
|
|
"mean_token_accuracy": 0.13068325966596603,
|
|
"num_tokens": 7077898.0,
|
|
"step": 3220
|
|
},
|
|
{
|
|
"entropy": 5.973318004608155,
|
|
"epoch": 0.32006748709805477,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004994482803435664,
|
|
"loss": 5.7882,
|
|
"mean_token_accuracy": 0.12848865017294883,
|
|
"num_tokens": 7088566.0,
|
|
"step": 3225
|
|
},
|
|
{
|
|
"entropy": 5.90263147354126,
|
|
"epoch": 0.3205637157602223,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.000499445797821144,
|
|
"loss": 5.7808,
|
|
"mean_token_accuracy": 0.13472721502184867,
|
|
"num_tokens": 7099533.0,
|
|
"step": 3230
|
|
},
|
|
{
|
|
"entropy": 5.94389238357544,
|
|
"epoch": 0.32105994442238983,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004994433097329494,
|
|
"loss": 5.7632,
|
|
"mean_token_accuracy": 0.13370973244309425,
|
|
"num_tokens": 7112254.0,
|
|
"step": 3235
|
|
},
|
|
{
|
|
"entropy": 5.9783838272094725,
|
|
"epoch": 0.32155617308455736,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004994408160790444,
|
|
"loss": 5.7846,
|
|
"mean_token_accuracy": 0.13278804942965508,
|
|
"num_tokens": 7124704.0,
|
|
"step": 3240
|
|
},
|
|
{
|
|
"entropy": 6.045426225662231,
|
|
"epoch": 0.3220524017467249,
|
|
"grad_norm": 0.77734375,
|
|
"learning_rate": 0.0004994383168594907,
|
|
"loss": 5.9735,
|
|
"mean_token_accuracy": 0.11922514736652375,
|
|
"num_tokens": 7137741.0,
|
|
"step": 3245
|
|
},
|
|
{
|
|
"entropy": 5.94087586402893,
|
|
"epoch": 0.3225486304088924,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004994358120743506,
|
|
"loss": 5.7579,
|
|
"mean_token_accuracy": 0.12984591871500015,
|
|
"num_tokens": 7147888.0,
|
|
"step": 3250
|
|
},
|
|
{
|
|
"entropy": 5.7819092750549315,
|
|
"epoch": 0.32304485907105995,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004994333017236858,
|
|
"loss": 5.7076,
|
|
"mean_token_accuracy": 0.14143425077199936,
|
|
"num_tokens": 7158950.0,
|
|
"step": 3255
|
|
},
|
|
{
|
|
"entropy": 5.94332447052002,
|
|
"epoch": 0.3235410877332275,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004994307858075587,
|
|
"loss": 5.8421,
|
|
"mean_token_accuracy": 0.12570593357086182,
|
|
"num_tokens": 7170156.0,
|
|
"step": 3260
|
|
},
|
|
{
|
|
"entropy": 5.932934379577636,
|
|
"epoch": 0.324037316395395,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004994282643260319,
|
|
"loss": 5.7048,
|
|
"mean_token_accuracy": 0.13710035309195517,
|
|
"num_tokens": 7180576.0,
|
|
"step": 3265
|
|
},
|
|
{
|
|
"entropy": 5.811103487014771,
|
|
"epoch": 0.32453354505756254,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004994257372791676,
|
|
"loss": 5.7565,
|
|
"mean_token_accuracy": 0.13245908543467522,
|
|
"num_tokens": 7192380.0,
|
|
"step": 3270
|
|
},
|
|
{
|
|
"entropy": 5.963694858551025,
|
|
"epoch": 0.3250297737197301,
|
|
"grad_norm": 0.78515625,
|
|
"learning_rate": 0.0004994232046670286,
|
|
"loss": 5.8183,
|
|
"mean_token_accuracy": 0.13459155336022377,
|
|
"num_tokens": 7203898.0,
|
|
"step": 3275
|
|
},
|
|
{
|
|
"entropy": 5.989812850952148,
|
|
"epoch": 0.3255260023818976,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004994206664896778,
|
|
"loss": 5.7841,
|
|
"mean_token_accuracy": 0.13584727346897124,
|
|
"num_tokens": 7215241.0,
|
|
"step": 3280
|
|
},
|
|
{
|
|
"entropy": 5.931274271011352,
|
|
"epoch": 0.3260222310440651,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004994181227471779,
|
|
"loss": 5.7383,
|
|
"mean_token_accuracy": 0.13464230597019194,
|
|
"num_tokens": 7226039.0,
|
|
"step": 3285
|
|
},
|
|
{
|
|
"entropy": 5.8311902523040775,
|
|
"epoch": 0.3265184597062326,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004994155734395923,
|
|
"loss": 5.7687,
|
|
"mean_token_accuracy": 0.13406949862837791,
|
|
"num_tokens": 7237148.0,
|
|
"step": 3290
|
|
},
|
|
{
|
|
"entropy": 5.923242807388306,
|
|
"epoch": 0.32701468836840014,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.000499413018566984,
|
|
"loss": 5.7621,
|
|
"mean_token_accuracy": 0.1315522961318493,
|
|
"num_tokens": 7249284.0,
|
|
"step": 3295
|
|
},
|
|
{
|
|
"entropy": 5.875470447540283,
|
|
"epoch": 0.32751091703056767,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004994104581294163,
|
|
"loss": 5.7631,
|
|
"mean_token_accuracy": 0.12935446053743363,
|
|
"num_tokens": 7259967.0,
|
|
"step": 3300
|
|
},
|
|
{
|
|
"entropy": 5.827996301651001,
|
|
"epoch": 0.3280071456927352,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004994078921269529,
|
|
"loss": 5.7235,
|
|
"mean_token_accuracy": 0.13562380596995355,
|
|
"num_tokens": 7271145.0,
|
|
"step": 3305
|
|
},
|
|
{
|
|
"entropy": 6.002976369857788,
|
|
"epoch": 0.32850337435490273,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004994053205596573,
|
|
"loss": 5.7351,
|
|
"mean_token_accuracy": 0.13544280007481574,
|
|
"num_tokens": 7281872.0,
|
|
"step": 3310
|
|
},
|
|
{
|
|
"entropy": 5.815413761138916,
|
|
"epoch": 0.32899960301707026,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.0004994027434275934,
|
|
"loss": 5.7639,
|
|
"mean_token_accuracy": 0.1359103187918663,
|
|
"num_tokens": 7293330.0,
|
|
"step": 3315
|
|
},
|
|
{
|
|
"entropy": 5.9990698337554935,
|
|
"epoch": 0.3294958316792378,
|
|
"grad_norm": 0.765625,
|
|
"learning_rate": 0.0004994001607308249,
|
|
"loss": 5.8214,
|
|
"mean_token_accuracy": 0.12711838632822037,
|
|
"num_tokens": 7304187.0,
|
|
"step": 3320
|
|
},
|
|
{
|
|
"entropy": 5.941404533386231,
|
|
"epoch": 0.3299920603414053,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.000499397572469416,
|
|
"loss": 5.7195,
|
|
"mean_token_accuracy": 0.13139874935150148,
|
|
"num_tokens": 7314756.0,
|
|
"step": 3325
|
|
},
|
|
{
|
|
"entropy": 5.826371097564698,
|
|
"epoch": 0.33048828900357285,
|
|
"grad_norm": 0.78515625,
|
|
"learning_rate": 0.0004993949786434308,
|
|
"loss": 5.7561,
|
|
"mean_token_accuracy": 0.13403744399547576,
|
|
"num_tokens": 7325711.0,
|
|
"step": 3330
|
|
},
|
|
{
|
|
"entropy": 5.872751712799072,
|
|
"epoch": 0.3309845176657404,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004993923792529337,
|
|
"loss": 5.6831,
|
|
"mean_token_accuracy": 0.1406965471804142,
|
|
"num_tokens": 7335639.0,
|
|
"step": 3335
|
|
},
|
|
{
|
|
"entropy": 5.956606531143189,
|
|
"epoch": 0.3314807463279079,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004993897742979892,
|
|
"loss": 5.8027,
|
|
"mean_token_accuracy": 0.13377716019749641,
|
|
"num_tokens": 7346621.0,
|
|
"step": 3340
|
|
},
|
|
{
|
|
"entropy": 5.9286905288696286,
|
|
"epoch": 0.33197697499007545,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004993871637786616,
|
|
"loss": 5.7705,
|
|
"mean_token_accuracy": 0.13041678220033645,
|
|
"num_tokens": 7358950.0,
|
|
"step": 3345
|
|
},
|
|
{
|
|
"entropy": 5.821332550048828,
|
|
"epoch": 0.332473203652243,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.000499384547695016,
|
|
"loss": 5.626,
|
|
"mean_token_accuracy": 0.13846936598420143,
|
|
"num_tokens": 7369629.0,
|
|
"step": 3350
|
|
},
|
|
{
|
|
"entropy": 5.872072839736939,
|
|
"epoch": 0.3329694323144105,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.000499381926047117,
|
|
"loss": 5.7262,
|
|
"mean_token_accuracy": 0.13408969193696976,
|
|
"num_tokens": 7379853.0,
|
|
"step": 3355
|
|
},
|
|
{
|
|
"entropy": 5.865009212493897,
|
|
"epoch": 0.333465660976578,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.00049937929883503,
|
|
"loss": 5.7563,
|
|
"mean_token_accuracy": 0.13046114146709442,
|
|
"num_tokens": 7391323.0,
|
|
"step": 3360
|
|
},
|
|
{
|
|
"entropy": 5.887697219848633,
|
|
"epoch": 0.3339618896387455,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004993766660588196,
|
|
"loss": 5.7304,
|
|
"mean_token_accuracy": 0.13350997790694236,
|
|
"num_tokens": 7402201.0,
|
|
"step": 3365
|
|
},
|
|
{
|
|
"entropy": 6.01474552154541,
|
|
"epoch": 0.33445811830091304,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004993740277185515,
|
|
"loss": 5.9623,
|
|
"mean_token_accuracy": 0.12484050020575524,
|
|
"num_tokens": 7413783.0,
|
|
"step": 3370
|
|
},
|
|
{
|
|
"entropy": 5.840613555908203,
|
|
"epoch": 0.3349543469630806,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.000499371383814291,
|
|
"loss": 5.7223,
|
|
"mean_token_accuracy": 0.13400618061423303,
|
|
"num_tokens": 7425909.0,
|
|
"step": 3375
|
|
},
|
|
{
|
|
"entropy": 5.847539567947388,
|
|
"epoch": 0.3354505756252481,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004993687343461036,
|
|
"loss": 5.6318,
|
|
"mean_token_accuracy": 0.13809972107410431,
|
|
"num_tokens": 7436346.0,
|
|
"step": 3380
|
|
},
|
|
{
|
|
"entropy": 5.904675722122192,
|
|
"epoch": 0.33594680428741563,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004993660793140551,
|
|
"loss": 5.6827,
|
|
"mean_token_accuracy": 0.14161865711212157,
|
|
"num_tokens": 7446596.0,
|
|
"step": 3385
|
|
},
|
|
{
|
|
"entropy": 5.782830667495728,
|
|
"epoch": 0.33644303294958317,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004993634187182113,
|
|
"loss": 5.7883,
|
|
"mean_token_accuracy": 0.12615693137049674,
|
|
"num_tokens": 7457697.0,
|
|
"step": 3390
|
|
},
|
|
{
|
|
"entropy": 6.065376043319702,
|
|
"epoch": 0.3369392616117507,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004993607525586381,
|
|
"loss": 5.8802,
|
|
"mean_token_accuracy": 0.131008081138134,
|
|
"num_tokens": 7468541.0,
|
|
"step": 3395
|
|
},
|
|
{
|
|
"entropy": 5.9343438148498535,
|
|
"epoch": 0.3374354902739182,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.0004993580808354018,
|
|
"loss": 5.7764,
|
|
"mean_token_accuracy": 0.13551992177963257,
|
|
"num_tokens": 7479781.0,
|
|
"step": 3400
|
|
},
|
|
{
|
|
"entropy": 5.837701988220215,
|
|
"epoch": 0.33793171893608576,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004993554035485685,
|
|
"loss": 5.6816,
|
|
"mean_token_accuracy": 0.1342918574810028,
|
|
"num_tokens": 7490722.0,
|
|
"step": 3405
|
|
},
|
|
{
|
|
"entropy": 5.948045158386231,
|
|
"epoch": 0.3384279475982533,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004993527206982047,
|
|
"loss": 5.7867,
|
|
"mean_token_accuracy": 0.13522917330265044,
|
|
"num_tokens": 7502293.0,
|
|
"step": 3410
|
|
},
|
|
{
|
|
"entropy": 5.918159008026123,
|
|
"epoch": 0.3389241762604208,
|
|
"grad_norm": 0.75390625,
|
|
"learning_rate": 0.0004993500322843767,
|
|
"loss": 5.7208,
|
|
"mean_token_accuracy": 0.13539437279105188,
|
|
"num_tokens": 7513846.0,
|
|
"step": 3415
|
|
},
|
|
{
|
|
"entropy": 5.830818223953247,
|
|
"epoch": 0.33942040492258835,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004993473383071514,
|
|
"loss": 5.7466,
|
|
"mean_token_accuracy": 0.13467329666018485,
|
|
"num_tokens": 7524062.0,
|
|
"step": 3420
|
|
},
|
|
{
|
|
"entropy": 5.901687240600586,
|
|
"epoch": 0.3399166335847559,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004993446387665956,
|
|
"loss": 5.7989,
|
|
"mean_token_accuracy": 0.13709105178713799,
|
|
"num_tokens": 7535533.0,
|
|
"step": 3425
|
|
},
|
|
{
|
|
"entropy": 5.914133930206299,
|
|
"epoch": 0.3404128622469234,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004993419336627761,
|
|
"loss": 5.6902,
|
|
"mean_token_accuracy": 0.13548238351941108,
|
|
"num_tokens": 7545951.0,
|
|
"step": 3430
|
|
},
|
|
{
|
|
"entropy": 5.817704439163208,
|
|
"epoch": 0.3409090909090909,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004993392229957602,
|
|
"loss": 5.6334,
|
|
"mean_token_accuracy": 0.1382601298391819,
|
|
"num_tokens": 7557320.0,
|
|
"step": 3435
|
|
},
|
|
{
|
|
"entropy": 5.805458402633667,
|
|
"epoch": 0.3414053195712584,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004993365067656148,
|
|
"loss": 5.7513,
|
|
"mean_token_accuracy": 0.1329974986612797,
|
|
"num_tokens": 7568078.0,
|
|
"step": 3440
|
|
},
|
|
{
|
|
"entropy": 5.883556461334228,
|
|
"epoch": 0.34190154823342594,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004993337849724076,
|
|
"loss": 5.7412,
|
|
"mean_token_accuracy": 0.13214808478951454,
|
|
"num_tokens": 7578940.0,
|
|
"step": 3445
|
|
},
|
|
{
|
|
"entropy": 5.893185567855835,
|
|
"epoch": 0.3423977768955935,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004993310576162059,
|
|
"loss": 5.7479,
|
|
"mean_token_accuracy": 0.13639405518770217,
|
|
"num_tokens": 7589864.0,
|
|
"step": 3450
|
|
},
|
|
{
|
|
"entropy": 5.922738981246948,
|
|
"epoch": 0.342894005557761,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004993283246970772,
|
|
"loss": 5.7057,
|
|
"mean_token_accuracy": 0.13013398125767708,
|
|
"num_tokens": 7599795.0,
|
|
"step": 3455
|
|
},
|
|
{
|
|
"entropy": 5.854125308990478,
|
|
"epoch": 0.34339023421992854,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004993255862150896,
|
|
"loss": 5.6876,
|
|
"mean_token_accuracy": 0.13669478967785836,
|
|
"num_tokens": 7610056.0,
|
|
"step": 3460
|
|
},
|
|
{
|
|
"entropy": 5.802547788619995,
|
|
"epoch": 0.34388646288209607,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004993228421703108,
|
|
"loss": 5.6874,
|
|
"mean_token_accuracy": 0.13286467269062996,
|
|
"num_tokens": 7620218.0,
|
|
"step": 3465
|
|
},
|
|
{
|
|
"entropy": 5.884554147720337,
|
|
"epoch": 0.3443826915442636,
|
|
"grad_norm": 0.796875,
|
|
"learning_rate": 0.0004993200925628088,
|
|
"loss": 5.7779,
|
|
"mean_token_accuracy": 0.1346588559448719,
|
|
"num_tokens": 7632781.0,
|
|
"step": 3470
|
|
},
|
|
{
|
|
"entropy": 5.8774271488189695,
|
|
"epoch": 0.3448789202064311,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.000499317337392652,
|
|
"loss": 5.7513,
|
|
"mean_token_accuracy": 0.13203491717576982,
|
|
"num_tokens": 7643845.0,
|
|
"step": 3475
|
|
},
|
|
{
|
|
"entropy": 5.910117483139038,
|
|
"epoch": 0.34537514886859866,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004993145766599085,
|
|
"loss": 5.7793,
|
|
"mean_token_accuracy": 0.13024887666106225,
|
|
"num_tokens": 7654583.0,
|
|
"step": 3480
|
|
},
|
|
{
|
|
"entropy": 5.8562994480133055,
|
|
"epoch": 0.3458713775307662,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004993118103646469,
|
|
"loss": 5.6299,
|
|
"mean_token_accuracy": 0.14034538567066193,
|
|
"num_tokens": 7665714.0,
|
|
"step": 3485
|
|
},
|
|
{
|
|
"entropy": 5.8359884262084964,
|
|
"epoch": 0.3463676061929337,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004993090385069357,
|
|
"loss": 5.6924,
|
|
"mean_token_accuracy": 0.1398855820298195,
|
|
"num_tokens": 7676011.0,
|
|
"step": 3490
|
|
},
|
|
{
|
|
"entropy": 5.825574779510498,
|
|
"epoch": 0.34686383485510125,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004993062610868437,
|
|
"loss": 5.7376,
|
|
"mean_token_accuracy": 0.13499814942479132,
|
|
"num_tokens": 7686927.0,
|
|
"step": 3495
|
|
},
|
|
{
|
|
"entropy": 5.846639966964721,
|
|
"epoch": 0.3473600635172688,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004993034781044398,
|
|
"loss": 5.6989,
|
|
"mean_token_accuracy": 0.135499270260334,
|
|
"num_tokens": 7698419.0,
|
|
"step": 3500
|
|
},
|
|
{
|
|
"entropy": 5.902319765090942,
|
|
"epoch": 0.3478562921794363,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.000499300689559793,
|
|
"loss": 5.6731,
|
|
"mean_token_accuracy": 0.13935840278863906,
|
|
"num_tokens": 7709695.0,
|
|
"step": 3505
|
|
},
|
|
{
|
|
"entropy": 5.833289051055909,
|
|
"epoch": 0.3483525208416038,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004992978954529724,
|
|
"loss": 5.6456,
|
|
"mean_token_accuracy": 0.1389060892164707,
|
|
"num_tokens": 7721309.0,
|
|
"step": 3510
|
|
},
|
|
{
|
|
"entropy": 5.848011827468872,
|
|
"epoch": 0.3488487495037713,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004992950957840473,
|
|
"loss": 5.7182,
|
|
"mean_token_accuracy": 0.13931151628494262,
|
|
"num_tokens": 7732074.0,
|
|
"step": 3515
|
|
},
|
|
{
|
|
"entropy": 5.895964670181274,
|
|
"epoch": 0.34934497816593885,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.000499292290553087,
|
|
"loss": 5.7953,
|
|
"mean_token_accuracy": 0.13158057406544685,
|
|
"num_tokens": 7742869.0,
|
|
"step": 3520
|
|
},
|
|
{
|
|
"entropy": 5.8405561447143555,
|
|
"epoch": 0.3498412068281064,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004992894797601614,
|
|
"loss": 5.6901,
|
|
"mean_token_accuracy": 0.13555181324481963,
|
|
"num_tokens": 7754895.0,
|
|
"step": 3525
|
|
},
|
|
{
|
|
"entropy": 5.8825901508331295,
|
|
"epoch": 0.3503374354902739,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.00049928666340534,
|
|
"loss": 5.6677,
|
|
"mean_token_accuracy": 0.13643246665596961,
|
|
"num_tokens": 7765262.0,
|
|
"step": 3530
|
|
},
|
|
{
|
|
"entropy": 5.8095235347747805,
|
|
"epoch": 0.35083366415244144,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004992838414886925,
|
|
"loss": 5.739,
|
|
"mean_token_accuracy": 0.1327873632311821,
|
|
"num_tokens": 7777348.0,
|
|
"step": 3535
|
|
},
|
|
{
|
|
"entropy": 5.916355848312378,
|
|
"epoch": 0.35132989281460897,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004992810140102891,
|
|
"loss": 5.7297,
|
|
"mean_token_accuracy": 0.13413830399513244,
|
|
"num_tokens": 7788161.0,
|
|
"step": 3540
|
|
},
|
|
{
|
|
"entropy": 5.840317058563232,
|
|
"epoch": 0.3518261214767765,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004992781809701999,
|
|
"loss": 5.7161,
|
|
"mean_token_accuracy": 0.13731137067079544,
|
|
"num_tokens": 7798629.0,
|
|
"step": 3545
|
|
},
|
|
{
|
|
"entropy": 5.829579782485962,
|
|
"epoch": 0.35232235013894403,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004992753423684951,
|
|
"loss": 5.7198,
|
|
"mean_token_accuracy": 0.13580114766955376,
|
|
"num_tokens": 7810148.0,
|
|
"step": 3550
|
|
},
|
|
{
|
|
"entropy": 5.863365554809571,
|
|
"epoch": 0.35281857880111156,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004992724982052449,
|
|
"loss": 5.71,
|
|
"mean_token_accuracy": 0.13254974409937859,
|
|
"num_tokens": 7821667.0,
|
|
"step": 3555
|
|
},
|
|
{
|
|
"entropy": 5.798212766647339,
|
|
"epoch": 0.3533148074632791,
|
|
"grad_norm": 0.7890625,
|
|
"learning_rate": 0.00049926964848052,
|
|
"loss": 5.6957,
|
|
"mean_token_accuracy": 0.13729101940989494,
|
|
"num_tokens": 7832184.0,
|
|
"step": 3560
|
|
},
|
|
{
|
|
"entropy": 5.927416610717773,
|
|
"epoch": 0.3538110361254466,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004992667931943913,
|
|
"loss": 5.7183,
|
|
"mean_token_accuracy": 0.13577507585287094,
|
|
"num_tokens": 7842983.0,
|
|
"step": 3565
|
|
},
|
|
{
|
|
"entropy": 5.856418895721435,
|
|
"epoch": 0.35430726478761415,
|
|
"grad_norm": 0.7734375,
|
|
"learning_rate": 0.0004992639323469293,
|
|
"loss": 5.6354,
|
|
"mean_token_accuracy": 0.14334375709295272,
|
|
"num_tokens": 7854783.0,
|
|
"step": 3570
|
|
},
|
|
{
|
|
"entropy": 5.773731470108032,
|
|
"epoch": 0.3548034934497817,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.000499261065938205,
|
|
"loss": 5.6583,
|
|
"mean_token_accuracy": 0.1432967111468315,
|
|
"num_tokens": 7864684.0,
|
|
"step": 3575
|
|
},
|
|
{
|
|
"entropy": 5.895873069763184,
|
|
"epoch": 0.3552997221119492,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004992581939682895,
|
|
"loss": 5.8056,
|
|
"mean_token_accuracy": 0.1261812210083008,
|
|
"num_tokens": 7876846.0,
|
|
"step": 3580
|
|
},
|
|
{
|
|
"entropy": 5.935712575912476,
|
|
"epoch": 0.3557959507741167,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.000499255316437254,
|
|
"loss": 5.6779,
|
|
"mean_token_accuracy": 0.1337505742907524,
|
|
"num_tokens": 7886826.0,
|
|
"step": 3585
|
|
},
|
|
{
|
|
"entropy": 5.801439237594605,
|
|
"epoch": 0.3562921794362842,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004992524333451699,
|
|
"loss": 5.7537,
|
|
"mean_token_accuracy": 0.13139742091298104,
|
|
"num_tokens": 7898941.0,
|
|
"step": 3590
|
|
},
|
|
{
|
|
"entropy": 5.849826717376709,
|
|
"epoch": 0.35678840809845175,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004992495446921087,
|
|
"loss": 5.6674,
|
|
"mean_token_accuracy": 0.13365738093852997,
|
|
"num_tokens": 7909916.0,
|
|
"step": 3595
|
|
},
|
|
{
|
|
"entropy": 5.808553171157837,
|
|
"epoch": 0.3572846367606193,
|
|
"grad_norm": 0.78125,
|
|
"learning_rate": 0.0004992466504781419,
|
|
"loss": 5.6792,
|
|
"mean_token_accuracy": 0.13627909868955612,
|
|
"num_tokens": 7922137.0,
|
|
"step": 3600
|
|
},
|
|
{
|
|
"entropy": 5.79820442199707,
|
|
"epoch": 0.3577808654227868,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004992437507033415,
|
|
"loss": 5.616,
|
|
"mean_token_accuracy": 0.13959808573126792,
|
|
"num_tokens": 7932940.0,
|
|
"step": 3605
|
|
},
|
|
{
|
|
"entropy": 5.881356430053711,
|
|
"epoch": 0.35827709408495434,
|
|
"grad_norm": 0.80078125,
|
|
"learning_rate": 0.0004992408453677792,
|
|
"loss": 5.7851,
|
|
"mean_token_accuracy": 0.12732164859771727,
|
|
"num_tokens": 7943735.0,
|
|
"step": 3610
|
|
},
|
|
{
|
|
"entropy": 5.798199939727783,
|
|
"epoch": 0.35877332274712187,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004992379344715273,
|
|
"loss": 5.672,
|
|
"mean_token_accuracy": 0.13556718379259108,
|
|
"num_tokens": 7955323.0,
|
|
"step": 3615
|
|
},
|
|
{
|
|
"entropy": 5.827555418014526,
|
|
"epoch": 0.3592695514092894,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004992350180146577,
|
|
"loss": 5.6371,
|
|
"mean_token_accuracy": 0.13796332776546477,
|
|
"num_tokens": 7966073.0,
|
|
"step": 3620
|
|
},
|
|
{
|
|
"entropy": 5.883342456817627,
|
|
"epoch": 0.35976578007145693,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004992320959972428,
|
|
"loss": 5.7951,
|
|
"mean_token_accuracy": 0.13291794434189796,
|
|
"num_tokens": 7977027.0,
|
|
"step": 3625
|
|
},
|
|
{
|
|
"entropy": 5.816143798828125,
|
|
"epoch": 0.36026200873362446,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004992291684193551,
|
|
"loss": 5.6621,
|
|
"mean_token_accuracy": 0.13837531432509423,
|
|
"num_tokens": 7987368.0,
|
|
"step": 3630
|
|
},
|
|
{
|
|
"entropy": 5.862054634094238,
|
|
"epoch": 0.360758237395792,
|
|
"grad_norm": 0.78125,
|
|
"learning_rate": 0.0004992262352810672,
|
|
"loss": 5.7323,
|
|
"mean_token_accuracy": 0.13465685471892358,
|
|
"num_tokens": 8000060.0,
|
|
"step": 3635
|
|
},
|
|
{
|
|
"entropy": 5.904985523223877,
|
|
"epoch": 0.3612544660579595,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004992232965824518,
|
|
"loss": 5.779,
|
|
"mean_token_accuracy": 0.13045103549957277,
|
|
"num_tokens": 8011388.0,
|
|
"step": 3640
|
|
},
|
|
{
|
|
"entropy": 5.78095817565918,
|
|
"epoch": 0.36175069472012705,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.000499220352323582,
|
|
"loss": 5.6446,
|
|
"mean_token_accuracy": 0.13995237201452254,
|
|
"num_tokens": 8021682.0,
|
|
"step": 3645
|
|
},
|
|
{
|
|
"entropy": 5.828157138824463,
|
|
"epoch": 0.3622469233822946,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004992174025045304,
|
|
"loss": 5.6637,
|
|
"mean_token_accuracy": 0.1378515474498272,
|
|
"num_tokens": 8032799.0,
|
|
"step": 3650
|
|
},
|
|
{
|
|
"entropy": 5.791543912887573,
|
|
"epoch": 0.3627431520444621,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004992144471253704,
|
|
"loss": 5.5542,
|
|
"mean_token_accuracy": 0.14514420479536055,
|
|
"num_tokens": 8042742.0,
|
|
"step": 3655
|
|
},
|
|
{
|
|
"entropy": 5.836719179153443,
|
|
"epoch": 0.3632393807066296,
|
|
"grad_norm": 0.79296875,
|
|
"learning_rate": 0.0004992114861861753,
|
|
"loss": 5.726,
|
|
"mean_token_accuracy": 0.13775497898459435,
|
|
"num_tokens": 8054068.0,
|
|
"step": 3660
|
|
},
|
|
{
|
|
"entropy": 5.895388793945313,
|
|
"epoch": 0.3637356093687971,
|
|
"grad_norm": 0.79296875,
|
|
"learning_rate": 0.0004992085196870184,
|
|
"loss": 5.7041,
|
|
"mean_token_accuracy": 0.13520997688174247,
|
|
"num_tokens": 8065286.0,
|
|
"step": 3665
|
|
},
|
|
{
|
|
"entropy": 5.8350739002227785,
|
|
"epoch": 0.36423183803096465,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004992055476279734,
|
|
"loss": 5.7644,
|
|
"mean_token_accuracy": 0.12864286303520203,
|
|
"num_tokens": 8077122.0,
|
|
"step": 3670
|
|
},
|
|
{
|
|
"entropy": 5.914077806472778,
|
|
"epoch": 0.3647280666931322,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004992025700091139,
|
|
"loss": 5.7053,
|
|
"mean_token_accuracy": 0.1394345611333847,
|
|
"num_tokens": 8087036.0,
|
|
"step": 3675
|
|
},
|
|
{
|
|
"entropy": 5.887608432769776,
|
|
"epoch": 0.3652242953552997,
|
|
"grad_norm": 0.796875,
|
|
"learning_rate": 0.0004991995868305138,
|
|
"loss": 5.7439,
|
|
"mean_token_accuracy": 0.13455166965723037,
|
|
"num_tokens": 8098517.0,
|
|
"step": 3680
|
|
},
|
|
{
|
|
"entropy": 5.778636121749878,
|
|
"epoch": 0.36572052401746724,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004991965980922471,
|
|
"loss": 5.6182,
|
|
"mean_token_accuracy": 0.13923544213175773,
|
|
"num_tokens": 8107475.0,
|
|
"step": 3685
|
|
},
|
|
{
|
|
"entropy": 5.82491021156311,
|
|
"epoch": 0.36621675267963477,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.0004991936037943878,
|
|
"loss": 5.7266,
|
|
"mean_token_accuracy": 0.1303709253668785,
|
|
"num_tokens": 8118529.0,
|
|
"step": 3690
|
|
},
|
|
{
|
|
"entropy": 5.9018360614776615,
|
|
"epoch": 0.3667129813418023,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004991906039370104,
|
|
"loss": 5.6292,
|
|
"mean_token_accuracy": 0.14039468988776208,
|
|
"num_tokens": 8128951.0,
|
|
"step": 3695
|
|
},
|
|
{
|
|
"entropy": 5.746214437484741,
|
|
"epoch": 0.36720921000396983,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004991875985201889,
|
|
"loss": 5.6492,
|
|
"mean_token_accuracy": 0.1410698860883713,
|
|
"num_tokens": 8139385.0,
|
|
"step": 3700
|
|
},
|
|
{
|
|
"entropy": 5.918550968170166,
|
|
"epoch": 0.36770543866613736,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.000499184587543998,
|
|
"loss": 5.6843,
|
|
"mean_token_accuracy": 0.1389869749546051,
|
|
"num_tokens": 8149376.0,
|
|
"step": 3705
|
|
},
|
|
{
|
|
"entropy": 5.8605245590209964,
|
|
"epoch": 0.3682016673283049,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0004991815710085126,
|
|
"loss": 5.7092,
|
|
"mean_token_accuracy": 0.13653566539287568,
|
|
"num_tokens": 8160687.0,
|
|
"step": 3710
|
|
},
|
|
{
|
|
"entropy": 5.872888708114624,
|
|
"epoch": 0.3686978959904724,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0004991785489138072,
|
|
"loss": 5.7141,
|
|
"mean_token_accuracy": 0.1377060107886791,
|
|
"num_tokens": 8171762.0,
|
|
"step": 3715
|
|
},
|
|
{
|
|
"entropy": 5.724028301239014,
|
|
"epoch": 0.36919412465263995,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004991755212599569,
|
|
"loss": 5.4791,
|
|
"mean_token_accuracy": 0.14507829397916794,
|
|
"num_tokens": 8181643.0,
|
|
"step": 3720
|
|
},
|
|
{
|
|
"entropy": 5.697611093521118,
|
|
"epoch": 0.3696903533148075,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004991724880470366,
|
|
"loss": 5.7306,
|
|
"mean_token_accuracy": 0.13918372690677644,
|
|
"num_tokens": 8192692.0,
|
|
"step": 3725
|
|
},
|
|
{
|
|
"entropy": 5.91280164718628,
|
|
"epoch": 0.370186581976975,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004991694492751217,
|
|
"loss": 5.678,
|
|
"mean_token_accuracy": 0.13002298176288604,
|
|
"num_tokens": 8202941.0,
|
|
"step": 3730
|
|
},
|
|
{
|
|
"entropy": 5.799401473999024,
|
|
"epoch": 0.3706828106391425,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004991664049442876,
|
|
"loss": 5.6749,
|
|
"mean_token_accuracy": 0.13614187836647035,
|
|
"num_tokens": 8214206.0,
|
|
"step": 3735
|
|
},
|
|
{
|
|
"entropy": 5.792055654525757,
|
|
"epoch": 0.37117903930131,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004991633550546097,
|
|
"loss": 5.5088,
|
|
"mean_token_accuracy": 0.15157946944236755,
|
|
"num_tokens": 8223672.0,
|
|
"step": 3740
|
|
},
|
|
{
|
|
"entropy": 5.7840086936950685,
|
|
"epoch": 0.37167526796347755,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004991602996061635,
|
|
"loss": 5.6511,
|
|
"mean_token_accuracy": 0.14170872122049333,
|
|
"num_tokens": 8234189.0,
|
|
"step": 3745
|
|
},
|
|
{
|
|
"entropy": 5.839711046218872,
|
|
"epoch": 0.3721714966256451,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004991572385990249,
|
|
"loss": 5.6868,
|
|
"mean_token_accuracy": 0.139129176735878,
|
|
"num_tokens": 8245382.0,
|
|
"step": 3750
|
|
},
|
|
{
|
|
"entropy": 5.895852756500244,
|
|
"epoch": 0.3726677252878126,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004991541720332698,
|
|
"loss": 5.6406,
|
|
"mean_token_accuracy": 0.13922024741768838,
|
|
"num_tokens": 8254530.0,
|
|
"step": 3755
|
|
},
|
|
{
|
|
"entropy": 5.741476011276245,
|
|
"epoch": 0.37316395394998014,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004991510999089743,
|
|
"loss": 5.6856,
|
|
"mean_token_accuracy": 0.13898830264806747,
|
|
"num_tokens": 8264030.0,
|
|
"step": 3760
|
|
},
|
|
{
|
|
"entropy": 5.792221021652222,
|
|
"epoch": 0.3736601826121477,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004991480222262145,
|
|
"loss": 5.6503,
|
|
"mean_token_accuracy": 0.14368472024798393,
|
|
"num_tokens": 8273537.0,
|
|
"step": 3765
|
|
},
|
|
{
|
|
"entropy": 5.88636155128479,
|
|
"epoch": 0.3741564112743152,
|
|
"grad_norm": 0.70703125,
|
|
"learning_rate": 0.0004991449389850668,
|
|
"loss": 5.6834,
|
|
"mean_token_accuracy": 0.13585606068372727,
|
|
"num_tokens": 8286123.0,
|
|
"step": 3770
|
|
},
|
|
{
|
|
"entropy": 5.796380996704102,
|
|
"epoch": 0.37465263993648273,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004991418501856076,
|
|
"loss": 5.7091,
|
|
"mean_token_accuracy": 0.13685489520430566,
|
|
"num_tokens": 8298115.0,
|
|
"step": 3775
|
|
},
|
|
{
|
|
"entropy": 5.87733302116394,
|
|
"epoch": 0.37514886859865026,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004991387558279134,
|
|
"loss": 5.7145,
|
|
"mean_token_accuracy": 0.1364159256219864,
|
|
"num_tokens": 8309376.0,
|
|
"step": 3780
|
|
},
|
|
{
|
|
"entropy": 5.805009841918945,
|
|
"epoch": 0.3756450972608178,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004991356559120612,
|
|
"loss": 5.6778,
|
|
"mean_token_accuracy": 0.13979559317231177,
|
|
"num_tokens": 8319272.0,
|
|
"step": 3785
|
|
},
|
|
{
|
|
"entropy": 5.818359422683716,
|
|
"epoch": 0.3761413259229853,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004991325504381275,
|
|
"loss": 5.6691,
|
|
"mean_token_accuracy": 0.13450096398591996,
|
|
"num_tokens": 8330042.0,
|
|
"step": 3790
|
|
},
|
|
{
|
|
"entropy": 5.800448036193847,
|
|
"epoch": 0.37663755458515286,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.0004991294394061896,
|
|
"loss": 5.622,
|
|
"mean_token_accuracy": 0.1370707221329212,
|
|
"num_tokens": 8340394.0,
|
|
"step": 3795
|
|
},
|
|
{
|
|
"entropy": 5.775977277755738,
|
|
"epoch": 0.3771337832473204,
|
|
"grad_norm": 0.80078125,
|
|
"learning_rate": 0.0004991263228163246,
|
|
"loss": 5.6841,
|
|
"mean_token_accuracy": 0.1365865007042885,
|
|
"num_tokens": 8351103.0,
|
|
"step": 3800
|
|
},
|
|
{
|
|
"entropy": 5.865830612182617,
|
|
"epoch": 0.3776300119094879,
|
|
"grad_norm": 0.78515625,
|
|
"learning_rate": 0.0004991232006686096,
|
|
"loss": 5.6929,
|
|
"mean_token_accuracy": 0.13774350062012672,
|
|
"num_tokens": 8363215.0,
|
|
"step": 3805
|
|
},
|
|
{
|
|
"entropy": 5.919228649139404,
|
|
"epoch": 0.3781262405716554,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004991200729631223,
|
|
"loss": 5.7373,
|
|
"mean_token_accuracy": 0.12794058844447137,
|
|
"num_tokens": 8374602.0,
|
|
"step": 3810
|
|
},
|
|
{
|
|
"entropy": 5.787239599227905,
|
|
"epoch": 0.3786224692338229,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004991169396999401,
|
|
"loss": 5.6555,
|
|
"mean_token_accuracy": 0.13108878657221795,
|
|
"num_tokens": 8386470.0,
|
|
"step": 3815
|
|
},
|
|
{
|
|
"entropy": 5.842096328735352,
|
|
"epoch": 0.37911869789599045,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004991138008791408,
|
|
"loss": 5.6799,
|
|
"mean_token_accuracy": 0.13508746549487113,
|
|
"num_tokens": 8396284.0,
|
|
"step": 3820
|
|
},
|
|
{
|
|
"entropy": 5.8682530403137205,
|
|
"epoch": 0.379614926558158,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004991106565008021,
|
|
"loss": 5.7021,
|
|
"mean_token_accuracy": 0.13416668847203256,
|
|
"num_tokens": 8407856.0,
|
|
"step": 3825
|
|
},
|
|
{
|
|
"entropy": 5.822223329544068,
|
|
"epoch": 0.3801111552203255,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004991075065650019,
|
|
"loss": 5.6105,
|
|
"mean_token_accuracy": 0.1422433525323868,
|
|
"num_tokens": 8419560.0,
|
|
"step": 3830
|
|
},
|
|
{
|
|
"entropy": 5.871718502044677,
|
|
"epoch": 0.38060738388249304,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004991043510718186,
|
|
"loss": 5.6177,
|
|
"mean_token_accuracy": 0.1404113858938217,
|
|
"num_tokens": 8430594.0,
|
|
"step": 3835
|
|
},
|
|
{
|
|
"entropy": 5.7367877006530765,
|
|
"epoch": 0.3811036125446606,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004991011900213303,
|
|
"loss": 5.588,
|
|
"mean_token_accuracy": 0.1445833697915077,
|
|
"num_tokens": 8440549.0,
|
|
"step": 3840
|
|
},
|
|
{
|
|
"entropy": 5.7166365623474125,
|
|
"epoch": 0.3815998412068281,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004990980234136152,
|
|
"loss": 5.6232,
|
|
"mean_token_accuracy": 0.13667350262403488,
|
|
"num_tokens": 8451553.0,
|
|
"step": 3845
|
|
},
|
|
{
|
|
"entropy": 5.814205455780029,
|
|
"epoch": 0.38209606986899564,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004990948512487522,
|
|
"loss": 5.6252,
|
|
"mean_token_accuracy": 0.1421022191643715,
|
|
"num_tokens": 8462899.0,
|
|
"step": 3850
|
|
},
|
|
{
|
|
"entropy": 5.8078104019165036,
|
|
"epoch": 0.38259229853116317,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004990916735268198,
|
|
"loss": 5.6796,
|
|
"mean_token_accuracy": 0.13645819798111916,
|
|
"num_tokens": 8474566.0,
|
|
"step": 3855
|
|
},
|
|
{
|
|
"entropy": 5.869540357589722,
|
|
"epoch": 0.3830885271933307,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004990884902478966,
|
|
"loss": 5.6865,
|
|
"mean_token_accuracy": 0.14038145467638968,
|
|
"num_tokens": 8484786.0,
|
|
"step": 3860
|
|
},
|
|
{
|
|
"entropy": 5.750705623626709,
|
|
"epoch": 0.3835847558554982,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004990853014120619,
|
|
"loss": 5.625,
|
|
"mean_token_accuracy": 0.14226635843515395,
|
|
"num_tokens": 8496416.0,
|
|
"step": 3865
|
|
},
|
|
{
|
|
"entropy": 5.798192834854126,
|
|
"epoch": 0.38408098451766576,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004990821070193944,
|
|
"loss": 5.6561,
|
|
"mean_token_accuracy": 0.136373158544302,
|
|
"num_tokens": 8507287.0,
|
|
"step": 3870
|
|
},
|
|
{
|
|
"entropy": 5.865294790267944,
|
|
"epoch": 0.3845772131798333,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004990789070699736,
|
|
"loss": 5.6948,
|
|
"mean_token_accuracy": 0.13455733358860017,
|
|
"num_tokens": 8517922.0,
|
|
"step": 3875
|
|
},
|
|
{
|
|
"entropy": 5.765826034545898,
|
|
"epoch": 0.3850734418420008,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004990757015638787,
|
|
"loss": 5.631,
|
|
"mean_token_accuracy": 0.14302095845341684,
|
|
"num_tokens": 8529532.0,
|
|
"step": 3880
|
|
},
|
|
{
|
|
"entropy": 5.816843843460083,
|
|
"epoch": 0.3855696705041683,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004990724905011894,
|
|
"loss": 5.6033,
|
|
"mean_token_accuracy": 0.14065930545330046,
|
|
"num_tokens": 8540207.0,
|
|
"step": 3885
|
|
},
|
|
{
|
|
"entropy": 5.801877880096436,
|
|
"epoch": 0.3860658991663358,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.000499069273881985,
|
|
"loss": 5.6383,
|
|
"mean_token_accuracy": 0.13733408302068711,
|
|
"num_tokens": 8551634.0,
|
|
"step": 3890
|
|
},
|
|
{
|
|
"entropy": 5.8024838924407955,
|
|
"epoch": 0.38656212782850335,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.0004990660517063455,
|
|
"loss": 5.7033,
|
|
"mean_token_accuracy": 0.1306481033563614,
|
|
"num_tokens": 8563256.0,
|
|
"step": 3895
|
|
},
|
|
{
|
|
"entropy": 5.81333646774292,
|
|
"epoch": 0.3870583564906709,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004990628239743508,
|
|
"loss": 5.7163,
|
|
"mean_token_accuracy": 0.13748448565602303,
|
|
"num_tokens": 8573833.0,
|
|
"step": 3900
|
|
},
|
|
{
|
|
"entropy": 5.79175386428833,
|
|
"epoch": 0.3875545851528384,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004990595906860807,
|
|
"loss": 5.6222,
|
|
"mean_token_accuracy": 0.1423626087605953,
|
|
"num_tokens": 8584283.0,
|
|
"step": 3905
|
|
},
|
|
{
|
|
"entropy": 5.789517545700074,
|
|
"epoch": 0.38805081381500595,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004990563518416157,
|
|
"loss": 5.6789,
|
|
"mean_token_accuracy": 0.1358125925064087,
|
|
"num_tokens": 8595344.0,
|
|
"step": 3910
|
|
},
|
|
{
|
|
"entropy": 5.814813470840454,
|
|
"epoch": 0.3885470424771735,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004990531074410358,
|
|
"loss": 5.6036,
|
|
"mean_token_accuracy": 0.137834145873785,
|
|
"num_tokens": 8605625.0,
|
|
"step": 3915
|
|
},
|
|
{
|
|
"entropy": 5.7738450050354,
|
|
"epoch": 0.389043271139341,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004990498574844218,
|
|
"loss": 5.5894,
|
|
"mean_token_accuracy": 0.14018410369753836,
|
|
"num_tokens": 8616259.0,
|
|
"step": 3920
|
|
},
|
|
{
|
|
"entropy": 5.82464485168457,
|
|
"epoch": 0.38953949980150854,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004990466019718542,
|
|
"loss": 5.6034,
|
|
"mean_token_accuracy": 0.1412269026041031,
|
|
"num_tokens": 8627179.0,
|
|
"step": 3925
|
|
},
|
|
{
|
|
"entropy": 5.831127595901489,
|
|
"epoch": 0.39003572846367607,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004990433409034134,
|
|
"loss": 5.71,
|
|
"mean_token_accuracy": 0.14471403062343596,
|
|
"num_tokens": 8637448.0,
|
|
"step": 3930
|
|
},
|
|
{
|
|
"entropy": 5.725909614562989,
|
|
"epoch": 0.3905319571258436,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004990400742791806,
|
|
"loss": 5.6293,
|
|
"mean_token_accuracy": 0.1356988586485386,
|
|
"num_tokens": 8649168.0,
|
|
"step": 3935
|
|
},
|
|
{
|
|
"entropy": 5.88536319732666,
|
|
"epoch": 0.39102818578801113,
|
|
"grad_norm": 0.796875,
|
|
"learning_rate": 0.0004990368020992368,
|
|
"loss": 5.7237,
|
|
"mean_token_accuracy": 0.13518148735165597,
|
|
"num_tokens": 8660653.0,
|
|
"step": 3940
|
|
},
|
|
{
|
|
"entropy": 5.793624401092529,
|
|
"epoch": 0.39152441445017866,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.000499033524363663,
|
|
"loss": 5.6971,
|
|
"mean_token_accuracy": 0.1437949612736702,
|
|
"num_tokens": 8672000.0,
|
|
"step": 3945
|
|
},
|
|
{
|
|
"entropy": 5.733256244659424,
|
|
"epoch": 0.3920206431123462,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004990302410725405,
|
|
"loss": 5.6268,
|
|
"mean_token_accuracy": 0.14762071818113326,
|
|
"num_tokens": 8682455.0,
|
|
"step": 3950
|
|
},
|
|
{
|
|
"entropy": 5.769017505645752,
|
|
"epoch": 0.3925168717745137,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004990269522259509,
|
|
"loss": 5.6153,
|
|
"mean_token_accuracy": 0.1415529504418373,
|
|
"num_tokens": 8692975.0,
|
|
"step": 3955
|
|
},
|
|
{
|
|
"entropy": 5.729673624038696,
|
|
"epoch": 0.3930131004366812,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004990236578239755,
|
|
"loss": 5.5754,
|
|
"mean_token_accuracy": 0.14106195271015168,
|
|
"num_tokens": 8703569.0,
|
|
"step": 3960
|
|
},
|
|
{
|
|
"entropy": 5.820702600479126,
|
|
"epoch": 0.3935093290988487,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004990203578666962,
|
|
"loss": 5.6878,
|
|
"mean_token_accuracy": 0.13368871957063674,
|
|
"num_tokens": 8713734.0,
|
|
"step": 3965
|
|
},
|
|
{
|
|
"entropy": 5.783185625076294,
|
|
"epoch": 0.39400555776101626,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004990170523541948,
|
|
"loss": 5.5848,
|
|
"mean_token_accuracy": 0.14641537964344026,
|
|
"num_tokens": 8723852.0,
|
|
"step": 3970
|
|
},
|
|
{
|
|
"entropy": 5.793915796279907,
|
|
"epoch": 0.3945017864231838,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004990137412865531,
|
|
"loss": 5.747,
|
|
"mean_token_accuracy": 0.13510857298970222,
|
|
"num_tokens": 8734300.0,
|
|
"step": 3975
|
|
},
|
|
{
|
|
"entropy": 5.898438024520874,
|
|
"epoch": 0.3949980150853513,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004990104246638533,
|
|
"loss": 5.7356,
|
|
"mean_token_accuracy": 0.1344385825097561,
|
|
"num_tokens": 8745022.0,
|
|
"step": 3980
|
|
},
|
|
{
|
|
"entropy": 5.785170221328736,
|
|
"epoch": 0.39549424374751885,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004990071024861778,
|
|
"loss": 5.6298,
|
|
"mean_token_accuracy": 0.13691987618803977,
|
|
"num_tokens": 8754870.0,
|
|
"step": 3985
|
|
},
|
|
{
|
|
"entropy": 5.872950315475464,
|
|
"epoch": 0.3959904724096864,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004990037747536087,
|
|
"loss": 5.6865,
|
|
"mean_token_accuracy": 0.1410525433719158,
|
|
"num_tokens": 8765536.0,
|
|
"step": 3990
|
|
},
|
|
{
|
|
"entropy": 5.788661527633667,
|
|
"epoch": 0.3964867010718539,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004990004414662288,
|
|
"loss": 5.6444,
|
|
"mean_token_accuracy": 0.13316506817936896,
|
|
"num_tokens": 8776898.0,
|
|
"step": 3995
|
|
},
|
|
{
|
|
"entropy": 5.795246744155884,
|
|
"epoch": 0.39698292973402144,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004989971026241205,
|
|
"loss": 5.7092,
|
|
"mean_token_accuracy": 0.1341576285660267,
|
|
"num_tokens": 8788176.0,
|
|
"step": 4000
|
|
},
|
|
{
|
|
"entropy": 5.745181846618652,
|
|
"epoch": 0.39747915839618897,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004989937582273668,
|
|
"loss": 5.6423,
|
|
"mean_token_accuracy": 0.13551107943058013,
|
|
"num_tokens": 8798939.0,
|
|
"step": 4005
|
|
},
|
|
{
|
|
"entropy": 5.790009880065918,
|
|
"epoch": 0.3979753870583565,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004989904082760506,
|
|
"loss": 5.6695,
|
|
"mean_token_accuracy": 0.14157403707504274,
|
|
"num_tokens": 8809092.0,
|
|
"step": 4010
|
|
},
|
|
{
|
|
"entropy": 5.820794916152954,
|
|
"epoch": 0.39847161572052403,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.000498987052770255,
|
|
"loss": 5.5906,
|
|
"mean_token_accuracy": 0.14081012904644014,
|
|
"num_tokens": 8819352.0,
|
|
"step": 4015
|
|
},
|
|
{
|
|
"entropy": 5.824670314788818,
|
|
"epoch": 0.39896784438269156,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.000498983691710063,
|
|
"loss": 5.7098,
|
|
"mean_token_accuracy": 0.1329125739634037,
|
|
"num_tokens": 8829878.0,
|
|
"step": 4020
|
|
},
|
|
{
|
|
"entropy": 5.778005743026734,
|
|
"epoch": 0.3994640730448591,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.000498980325095558,
|
|
"loss": 5.5798,
|
|
"mean_token_accuracy": 0.1393500655889511,
|
|
"num_tokens": 8840364.0,
|
|
"step": 4025
|
|
},
|
|
{
|
|
"entropy": 5.7912201404571535,
|
|
"epoch": 0.3999603017070266,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004989769529268238,
|
|
"loss": 5.6914,
|
|
"mean_token_accuracy": 0.1342613399028778,
|
|
"num_tokens": 8851340.0,
|
|
"step": 4030
|
|
},
|
|
{
|
|
"entropy": 5.750426435470581,
|
|
"epoch": 0.4004565303691941,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004989735752039436,
|
|
"loss": 5.6583,
|
|
"mean_token_accuracy": 0.13800134211778642,
|
|
"num_tokens": 8862571.0,
|
|
"step": 4035
|
|
},
|
|
{
|
|
"entropy": 5.796105480194091,
|
|
"epoch": 0.4009527590313616,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004989701919270015,
|
|
"loss": 5.6605,
|
|
"mean_token_accuracy": 0.1415472649037838,
|
|
"num_tokens": 8873927.0,
|
|
"step": 4040
|
|
},
|
|
{
|
|
"entropy": 5.866248321533203,
|
|
"epoch": 0.40144898769352916,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004989668030960812,
|
|
"loss": 5.8541,
|
|
"mean_token_accuracy": 0.12870026156306266,
|
|
"num_tokens": 8886542.0,
|
|
"step": 4045
|
|
},
|
|
{
|
|
"entropy": 5.886906385421753,
|
|
"epoch": 0.4019452163556967,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004989634087112667,
|
|
"loss": 5.6018,
|
|
"mean_token_accuracy": 0.1396520234644413,
|
|
"num_tokens": 8896114.0,
|
|
"step": 4050
|
|
},
|
|
{
|
|
"entropy": 5.802579689025879,
|
|
"epoch": 0.4024414450178642,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004989600087726425,
|
|
"loss": 5.6846,
|
|
"mean_token_accuracy": 0.1316719926893711,
|
|
"num_tokens": 8906303.0,
|
|
"step": 4055
|
|
},
|
|
{
|
|
"entropy": 5.829805946350097,
|
|
"epoch": 0.40293767368003175,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004989566032802924,
|
|
"loss": 5.7132,
|
|
"mean_token_accuracy": 0.13243434056639672,
|
|
"num_tokens": 8916961.0,
|
|
"step": 4060
|
|
},
|
|
{
|
|
"entropy": 5.879288005828857,
|
|
"epoch": 0.4034339023421993,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004989531922343013,
|
|
"loss": 5.805,
|
|
"mean_token_accuracy": 0.13305630013346673,
|
|
"num_tokens": 8927700.0,
|
|
"step": 4065
|
|
},
|
|
{
|
|
"entropy": 5.819786024093628,
|
|
"epoch": 0.4039301310043668,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.0004989497756347534,
|
|
"loss": 5.6316,
|
|
"mean_token_accuracy": 0.13920575231313706,
|
|
"num_tokens": 8939655.0,
|
|
"step": 4070
|
|
},
|
|
{
|
|
"entropy": 5.780047941207886,
|
|
"epoch": 0.40442635966653434,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004989463534817339,
|
|
"loss": 5.5705,
|
|
"mean_token_accuracy": 0.14523619860410691,
|
|
"num_tokens": 8951238.0,
|
|
"step": 4075
|
|
},
|
|
{
|
|
"entropy": 5.802511358261109,
|
|
"epoch": 0.40492258832870187,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004989429257753273,
|
|
"loss": 5.6305,
|
|
"mean_token_accuracy": 0.14453877732157708,
|
|
"num_tokens": 8962019.0,
|
|
"step": 4080
|
|
},
|
|
{
|
|
"entropy": 5.7828209400177,
|
|
"epoch": 0.4054188169908694,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004989394925156187,
|
|
"loss": 5.6351,
|
|
"mean_token_accuracy": 0.13892287462949754,
|
|
"num_tokens": 8973861.0,
|
|
"step": 4085
|
|
},
|
|
{
|
|
"entropy": 5.741808176040649,
|
|
"epoch": 0.40591504565303693,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.0004989360537026932,
|
|
"loss": 5.6414,
|
|
"mean_token_accuracy": 0.14035039395093918,
|
|
"num_tokens": 8985981.0,
|
|
"step": 4090
|
|
},
|
|
{
|
|
"entropy": 5.7918037414550785,
|
|
"epoch": 0.40641127431520446,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.000498932609336636,
|
|
"loss": 5.5418,
|
|
"mean_token_accuracy": 0.14218456000089646,
|
|
"num_tokens": 8995318.0,
|
|
"step": 4095
|
|
},
|
|
{
|
|
"entropy": 5.7594521045684814,
|
|
"epoch": 0.406907502977372,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004989291594175327,
|
|
"loss": 5.5765,
|
|
"mean_token_accuracy": 0.1396835669875145,
|
|
"num_tokens": 9004679.0,
|
|
"step": 4100
|
|
},
|
|
{
|
|
"entropy": 5.91703233718872,
|
|
"epoch": 0.4074037316395395,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004989257039454689,
|
|
"loss": 5.7059,
|
|
"mean_token_accuracy": 0.1379046157002449,
|
|
"num_tokens": 9016422.0,
|
|
"step": 4105
|
|
},
|
|
{
|
|
"entropy": 5.724780511856079,
|
|
"epoch": 0.40789996030170705,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.00049892224292053,
|
|
"loss": 5.6229,
|
|
"mean_token_accuracy": 0.14078758656978607,
|
|
"num_tokens": 9027914.0,
|
|
"step": 4110
|
|
},
|
|
{
|
|
"entropy": 5.761678218841553,
|
|
"epoch": 0.40839618896387453,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.0004989187763428021,
|
|
"loss": 5.5918,
|
|
"mean_token_accuracy": 0.144223216176033,
|
|
"num_tokens": 9038701.0,
|
|
"step": 4115
|
|
},
|
|
{
|
|
"entropy": 5.768312168121338,
|
|
"epoch": 0.40889241762604206,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.000498915304212371,
|
|
"loss": 5.6561,
|
|
"mean_token_accuracy": 0.13807908743619918,
|
|
"num_tokens": 9050620.0,
|
|
"step": 4120
|
|
},
|
|
{
|
|
"entropy": 5.846501874923706,
|
|
"epoch": 0.4093886462882096,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004989118265293228,
|
|
"loss": 5.6829,
|
|
"mean_token_accuracy": 0.14339982569217682,
|
|
"num_tokens": 9060900.0,
|
|
"step": 4125
|
|
},
|
|
{
|
|
"entropy": 5.792847585678101,
|
|
"epoch": 0.4098848749503771,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004989083432937439,
|
|
"loss": 5.5866,
|
|
"mean_token_accuracy": 0.13959128633141518,
|
|
"num_tokens": 9072122.0,
|
|
"step": 4130
|
|
},
|
|
{
|
|
"entropy": 5.749606561660767,
|
|
"epoch": 0.41038110361254465,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004989048545057204,
|
|
"loss": 5.617,
|
|
"mean_token_accuracy": 0.13930945098400116,
|
|
"num_tokens": 9082780.0,
|
|
"step": 4135
|
|
},
|
|
{
|
|
"entropy": 5.782565975189209,
|
|
"epoch": 0.4108773322747122,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004989013601653391,
|
|
"loss": 5.6658,
|
|
"mean_token_accuracy": 0.1379122644662857,
|
|
"num_tokens": 9093518.0,
|
|
"step": 4140
|
|
},
|
|
{
|
|
"entropy": 5.767605924606324,
|
|
"epoch": 0.4113735609368797,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.0004988978602726866,
|
|
"loss": 5.6779,
|
|
"mean_token_accuracy": 0.1437633991241455,
|
|
"num_tokens": 9105035.0,
|
|
"step": 4145
|
|
},
|
|
{
|
|
"entropy": 5.812577152252198,
|
|
"epoch": 0.41186978959904724,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004988943548278494,
|
|
"loss": 5.587,
|
|
"mean_token_accuracy": 0.14110235944390298,
|
|
"num_tokens": 9117154.0,
|
|
"step": 4150
|
|
},
|
|
{
|
|
"entropy": 5.77940182685852,
|
|
"epoch": 0.4123660182612148,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004988908438309149,
|
|
"loss": 5.6667,
|
|
"mean_token_accuracy": 0.13823975771665573,
|
|
"num_tokens": 9128818.0,
|
|
"step": 4155
|
|
},
|
|
{
|
|
"entropy": 5.8112109184265135,
|
|
"epoch": 0.4128622469233823,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.0004988873272819697,
|
|
"loss": 5.67,
|
|
"mean_token_accuracy": 0.1413659855723381,
|
|
"num_tokens": 9140188.0,
|
|
"step": 4160
|
|
},
|
|
{
|
|
"entropy": 5.94907431602478,
|
|
"epoch": 0.41335847558554983,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004988838051811014,
|
|
"loss": 5.7523,
|
|
"mean_token_accuracy": 0.134553412348032,
|
|
"num_tokens": 9150565.0,
|
|
"step": 4165
|
|
},
|
|
{
|
|
"entropy": 5.801510667800903,
|
|
"epoch": 0.41385470424771736,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.000498880277528397,
|
|
"loss": 5.6054,
|
|
"mean_token_accuracy": 0.13975557759404184,
|
|
"num_tokens": 9160130.0,
|
|
"step": 4170
|
|
},
|
|
{
|
|
"entropy": 5.799229383468628,
|
|
"epoch": 0.4143509329098849,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004988767443239443,
|
|
"loss": 5.6117,
|
|
"mean_token_accuracy": 0.1398836188018322,
|
|
"num_tokens": 9171740.0,
|
|
"step": 4175
|
|
},
|
|
{
|
|
"entropy": 5.76237120628357,
|
|
"epoch": 0.4148471615720524,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004988732055678307,
|
|
"loss": 5.5544,
|
|
"mean_token_accuracy": 0.15382059216499328,
|
|
"num_tokens": 9182459.0,
|
|
"step": 4180
|
|
},
|
|
{
|
|
"entropy": 5.805677366256714,
|
|
"epoch": 0.41534339023421996,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.000498869661260144,
|
|
"loss": 5.6322,
|
|
"mean_token_accuracy": 0.14206244200468063,
|
|
"num_tokens": 9192284.0,
|
|
"step": 4185
|
|
},
|
|
{
|
|
"entropy": 5.780238819122315,
|
|
"epoch": 0.41583961889638743,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.000498866111400972,
|
|
"loss": 5.6115,
|
|
"mean_token_accuracy": 0.1399123787879944,
|
|
"num_tokens": 9202700.0,
|
|
"step": 4190
|
|
},
|
|
{
|
|
"entropy": 5.7953057289123535,
|
|
"epoch": 0.41633584755855496,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004988625559904029,
|
|
"loss": 5.6243,
|
|
"mean_token_accuracy": 0.13381586745381355,
|
|
"num_tokens": 9213013.0,
|
|
"step": 4195
|
|
},
|
|
{
|
|
"entropy": 5.83180456161499,
|
|
"epoch": 0.4168320762207225,
|
|
"grad_norm": 0.7421875,
|
|
"learning_rate": 0.0004988589950285248,
|
|
"loss": 5.6966,
|
|
"mean_token_accuracy": 0.13726072534918785,
|
|
"num_tokens": 9224568.0,
|
|
"step": 4200
|
|
},
|
|
{
|
|
"entropy": 5.76538610458374,
|
|
"epoch": 0.41732830488289,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004988554285154259,
|
|
"loss": 5.5748,
|
|
"mean_token_accuracy": 0.13923351615667343,
|
|
"num_tokens": 9233791.0,
|
|
"step": 4205
|
|
},
|
|
{
|
|
"entropy": 5.792706155776978,
|
|
"epoch": 0.41782453354505755,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004988518564511948,
|
|
"loss": 5.6178,
|
|
"mean_token_accuracy": 0.13635936975479127,
|
|
"num_tokens": 9245048.0,
|
|
"step": 4210
|
|
},
|
|
{
|
|
"entropy": 5.860803031921387,
|
|
"epoch": 0.4183207622072251,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004988482788359202,
|
|
"loss": 5.6396,
|
|
"mean_token_accuracy": 0.14628660529851914,
|
|
"num_tokens": 9256508.0,
|
|
"step": 4215
|
|
},
|
|
{
|
|
"entropy": 5.803260707855225,
|
|
"epoch": 0.4188169908693926,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004988446956696904,
|
|
"loss": 5.668,
|
|
"mean_token_accuracy": 0.14071763530373574,
|
|
"num_tokens": 9267871.0,
|
|
"step": 4220
|
|
},
|
|
{
|
|
"entropy": 5.85851092338562,
|
|
"epoch": 0.41931321953156014,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004988411069525947,
|
|
"loss": 5.7168,
|
|
"mean_token_accuracy": 0.13775873184204102,
|
|
"num_tokens": 9279287.0,
|
|
"step": 4225
|
|
},
|
|
{
|
|
"entropy": 5.862564992904663,
|
|
"epoch": 0.4198094481937277,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004988375126847216,
|
|
"loss": 5.7249,
|
|
"mean_token_accuracy": 0.13378578275442124,
|
|
"num_tokens": 9291257.0,
|
|
"step": 4230
|
|
},
|
|
{
|
|
"entropy": 5.840371370315552,
|
|
"epoch": 0.4203056768558952,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004988339128661607,
|
|
"loss": 5.7021,
|
|
"mean_token_accuracy": 0.1337619088590145,
|
|
"num_tokens": 9302590.0,
|
|
"step": 4235
|
|
},
|
|
{
|
|
"entropy": 5.699577569961548,
|
|
"epoch": 0.42080190551806274,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.000498830307497001,
|
|
"loss": 5.5512,
|
|
"mean_token_accuracy": 0.14313922077417374,
|
|
"num_tokens": 9313174.0,
|
|
"step": 4240
|
|
},
|
|
{
|
|
"entropy": 5.794048738479614,
|
|
"epoch": 0.42129813418023027,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.000498826696577332,
|
|
"loss": 5.6396,
|
|
"mean_token_accuracy": 0.1417992301285267,
|
|
"num_tokens": 9325034.0,
|
|
"step": 4245
|
|
},
|
|
{
|
|
"entropy": 5.806614542007447,
|
|
"epoch": 0.4217943628423978,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004988230801072432,
|
|
"loss": 5.6206,
|
|
"mean_token_accuracy": 0.13834859877824784,
|
|
"num_tokens": 9336834.0,
|
|
"step": 4250
|
|
},
|
|
{
|
|
"entropy": 5.737400197982788,
|
|
"epoch": 0.4222905915045653,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004988194580868244,
|
|
"loss": 5.6237,
|
|
"mean_token_accuracy": 0.13811139315366744,
|
|
"num_tokens": 9347747.0,
|
|
"step": 4255
|
|
},
|
|
{
|
|
"entropy": 5.771370553970337,
|
|
"epoch": 0.42278682016673286,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004988158305161654,
|
|
"loss": 5.6391,
|
|
"mean_token_accuracy": 0.1432290256023407,
|
|
"num_tokens": 9359186.0,
|
|
"step": 4260
|
|
},
|
|
{
|
|
"entropy": 5.782405090332031,
|
|
"epoch": 0.42328304882890033,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.000498812197395356,
|
|
"loss": 5.5621,
|
|
"mean_token_accuracy": 0.14198907613754272,
|
|
"num_tokens": 9369485.0,
|
|
"step": 4265
|
|
},
|
|
{
|
|
"entropy": 5.782733201980591,
|
|
"epoch": 0.42377927749106786,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004988085587244863,
|
|
"loss": 5.6577,
|
|
"mean_token_accuracy": 0.13524223864078522,
|
|
"num_tokens": 9382658.0,
|
|
"step": 4270
|
|
},
|
|
{
|
|
"entropy": 5.74179515838623,
|
|
"epoch": 0.4242755061532354,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0004988049145036466,
|
|
"loss": 5.6175,
|
|
"mean_token_accuracy": 0.1354674480855465,
|
|
"num_tokens": 9394151.0,
|
|
"step": 4275
|
|
},
|
|
{
|
|
"entropy": 5.861121129989624,
|
|
"epoch": 0.4247717348154029,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004988012647329273,
|
|
"loss": 5.7112,
|
|
"mean_token_accuracy": 0.13729124367237092,
|
|
"num_tokens": 9405956.0,
|
|
"step": 4280
|
|
},
|
|
{
|
|
"entropy": 5.821110439300537,
|
|
"epoch": 0.42526796347757045,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.000498797609412419,
|
|
"loss": 5.6038,
|
|
"mean_token_accuracy": 0.13974196910858155,
|
|
"num_tokens": 9416889.0,
|
|
"step": 4285
|
|
},
|
|
{
|
|
"entropy": 5.7748674869537355,
|
|
"epoch": 0.425764192139738,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004987939485422122,
|
|
"loss": 5.7055,
|
|
"mean_token_accuracy": 0.136608724296093,
|
|
"num_tokens": 9427602.0,
|
|
"step": 4290
|
|
},
|
|
{
|
|
"entropy": 5.823736667633057,
|
|
"epoch": 0.4262604208019055,
|
|
"grad_norm": 0.7578125,
|
|
"learning_rate": 0.0004987902821223976,
|
|
"loss": 5.629,
|
|
"mean_token_accuracy": 0.14252188354730605,
|
|
"num_tokens": 9438557.0,
|
|
"step": 4295
|
|
},
|
|
{
|
|
"entropy": 5.777904653549195,
|
|
"epoch": 0.42675664946407305,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.0004987866101530663,
|
|
"loss": 5.667,
|
|
"mean_token_accuracy": 0.13800618946552276,
|
|
"num_tokens": 9449598.0,
|
|
"step": 4300
|
|
},
|
|
{
|
|
"entropy": 5.8158505916595455,
|
|
"epoch": 0.4272528781262406,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004987829326343092,
|
|
"loss": 5.6076,
|
|
"mean_token_accuracy": 0.14416556805372238,
|
|
"num_tokens": 9459740.0,
|
|
"step": 4305
|
|
},
|
|
{
|
|
"entropy": 5.753842973709107,
|
|
"epoch": 0.4277491067884081,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004987792495662177,
|
|
"loss": 5.6073,
|
|
"mean_token_accuracy": 0.14074130430817605,
|
|
"num_tokens": 9469835.0,
|
|
"step": 4310
|
|
},
|
|
{
|
|
"entropy": 5.818010139465332,
|
|
"epoch": 0.42824533545057564,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.000498775560948883,
|
|
"loss": 5.6917,
|
|
"mean_token_accuracy": 0.13898994252085686,
|
|
"num_tokens": 9480735.0,
|
|
"step": 4315
|
|
},
|
|
{
|
|
"entropy": 5.785709524154663,
|
|
"epoch": 0.42874156411274317,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004987718667823965,
|
|
"loss": 5.5887,
|
|
"mean_token_accuracy": 0.14314745515584945,
|
|
"num_tokens": 9491321.0,
|
|
"step": 4320
|
|
},
|
|
{
|
|
"entropy": 5.817282676696777,
|
|
"epoch": 0.4292377927749107,
|
|
"grad_norm": 0.78125,
|
|
"learning_rate": 0.00049876816706685,
|
|
"loss": 5.721,
|
|
"mean_token_accuracy": 0.13546350300312043,
|
|
"num_tokens": 9503507.0,
|
|
"step": 4325
|
|
},
|
|
{
|
|
"entropy": 5.835805463790893,
|
|
"epoch": 0.42973402143707823,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.000498764461802335,
|
|
"loss": 5.7267,
|
|
"mean_token_accuracy": 0.14347420930862426,
|
|
"num_tokens": 9514404.0,
|
|
"step": 4330
|
|
},
|
|
{
|
|
"entropy": 5.736133670806884,
|
|
"epoch": 0.43023025009924576,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004987607509889437,
|
|
"loss": 5.5945,
|
|
"mean_token_accuracy": 0.13721355572342872,
|
|
"num_tokens": 9525555.0,
|
|
"step": 4335
|
|
},
|
|
{
|
|
"entropy": 5.844026803970337,
|
|
"epoch": 0.43072647876141323,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004987570346267677,
|
|
"loss": 5.593,
|
|
"mean_token_accuracy": 0.14471945762634278,
|
|
"num_tokens": 9535084.0,
|
|
"step": 4340
|
|
},
|
|
{
|
|
"entropy": 5.716549587249756,
|
|
"epoch": 0.43122270742358076,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0004987533127158996,
|
|
"loss": 5.5996,
|
|
"mean_token_accuracy": 0.1444016769528389,
|
|
"num_tokens": 9546170.0,
|
|
"step": 4345
|
|
},
|
|
{
|
|
"entropy": 5.811110973358154,
|
|
"epoch": 0.4317189360857483,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004987495852564314,
|
|
"loss": 5.6225,
|
|
"mean_token_accuracy": 0.14201515763998032,
|
|
"num_tokens": 9556793.0,
|
|
"step": 4350
|
|
},
|
|
{
|
|
"entropy": 5.784374189376831,
|
|
"epoch": 0.4322151647479158,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004987458522484556,
|
|
"loss": 5.566,
|
|
"mean_token_accuracy": 0.14575942158699035,
|
|
"num_tokens": 9568114.0,
|
|
"step": 4355
|
|
},
|
|
{
|
|
"entropy": 5.740352964401245,
|
|
"epoch": 0.43271139341008336,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004987421136920648,
|
|
"loss": 5.5771,
|
|
"mean_token_accuracy": 0.13610847890377045,
|
|
"num_tokens": 9579119.0,
|
|
"step": 4360
|
|
},
|
|
{
|
|
"entropy": 5.722053813934326,
|
|
"epoch": 0.4332076220722509,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004987383695873517,
|
|
"loss": 5.6147,
|
|
"mean_token_accuracy": 0.14022180810570717,
|
|
"num_tokens": 9590259.0,
|
|
"step": 4365
|
|
},
|
|
{
|
|
"entropy": 5.802224493026733,
|
|
"epoch": 0.4337038507344184,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004987346199344092,
|
|
"loss": 5.6512,
|
|
"mean_token_accuracy": 0.13241124674677848,
|
|
"num_tokens": 9600431.0,
|
|
"step": 4370
|
|
},
|
|
{
|
|
"entropy": 5.747055196762085,
|
|
"epoch": 0.43420007939658595,
|
|
"grad_norm": 0.79296875,
|
|
"learning_rate": 0.0004987308647333303,
|
|
"loss": 5.6298,
|
|
"mean_token_accuracy": 0.14093587100505828,
|
|
"num_tokens": 9610286.0,
|
|
"step": 4375
|
|
},
|
|
{
|
|
"entropy": 5.844609880447388,
|
|
"epoch": 0.4346963080587535,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004987271039842079,
|
|
"loss": 5.6392,
|
|
"mean_token_accuracy": 0.14039682298898698,
|
|
"num_tokens": 9621148.0,
|
|
"step": 4380
|
|
},
|
|
{
|
|
"entropy": 5.768031358718872,
|
|
"epoch": 0.435192536720921,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004987233376871355,
|
|
"loss": 5.5234,
|
|
"mean_token_accuracy": 0.1461140587925911,
|
|
"num_tokens": 9631300.0,
|
|
"step": 4385
|
|
},
|
|
{
|
|
"entropy": 5.78350191116333,
|
|
"epoch": 0.43568876538308854,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004987195658422063,
|
|
"loss": 5.6269,
|
|
"mean_token_accuracy": 0.13842125460505486,
|
|
"num_tokens": 9641986.0,
|
|
"step": 4390
|
|
},
|
|
{
|
|
"entropy": 5.781039094924926,
|
|
"epoch": 0.43618499404525607,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.0004987157884495141,
|
|
"loss": 5.6395,
|
|
"mean_token_accuracy": 0.1402071826159954,
|
|
"num_tokens": 9652962.0,
|
|
"step": 4395
|
|
},
|
|
{
|
|
"entropy": 5.757225465774536,
|
|
"epoch": 0.4366812227074236,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004987120055091523,
|
|
"loss": 5.6788,
|
|
"mean_token_accuracy": 0.13589339554309846,
|
|
"num_tokens": 9664084.0,
|
|
"step": 4400
|
|
},
|
|
{
|
|
"entropy": 5.754967546463012,
|
|
"epoch": 0.43717745136959113,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004987082170212149,
|
|
"loss": 5.5724,
|
|
"mean_token_accuracy": 0.1397831603884697,
|
|
"num_tokens": 9675821.0,
|
|
"step": 4405
|
|
},
|
|
{
|
|
"entropy": 5.774995422363281,
|
|
"epoch": 0.43767368003175866,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004987044229857957,
|
|
"loss": 5.6874,
|
|
"mean_token_accuracy": 0.1395527347922325,
|
|
"num_tokens": 9687964.0,
|
|
"step": 4410
|
|
},
|
|
{
|
|
"entropy": 5.788907766342163,
|
|
"epoch": 0.43816990869392614,
|
|
"grad_norm": 0.796875,
|
|
"learning_rate": 0.0004987006234029889,
|
|
"loss": 5.6718,
|
|
"mean_token_accuracy": 0.139390766620636,
|
|
"num_tokens": 9699653.0,
|
|
"step": 4415
|
|
},
|
|
{
|
|
"entropy": 5.857262229919433,
|
|
"epoch": 0.43866613735609367,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004986968182728885,
|
|
"loss": 5.6781,
|
|
"mean_token_accuracy": 0.13918035179376603,
|
|
"num_tokens": 9709872.0,
|
|
"step": 4420
|
|
},
|
|
{
|
|
"entropy": 5.817832374572754,
|
|
"epoch": 0.4391623660182612,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004986930075955892,
|
|
"loss": 5.601,
|
|
"mean_token_accuracy": 0.13685947135090828,
|
|
"num_tokens": 9720589.0,
|
|
"step": 4425
|
|
},
|
|
{
|
|
"entropy": 5.700802898406982,
|
|
"epoch": 0.4396585946804287,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004986891913711853,
|
|
"loss": 5.5351,
|
|
"mean_token_accuracy": 0.14478714317083358,
|
|
"num_tokens": 9731862.0,
|
|
"step": 4430
|
|
},
|
|
{
|
|
"entropy": 5.73977108001709,
|
|
"epoch": 0.44015482334259626,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004986853695997715,
|
|
"loss": 5.6872,
|
|
"mean_token_accuracy": 0.14369284883141517,
|
|
"num_tokens": 9743710.0,
|
|
"step": 4435
|
|
},
|
|
{
|
|
"entropy": 5.799801588058472,
|
|
"epoch": 0.4406510520047638,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004986815422814425,
|
|
"loss": 5.6418,
|
|
"mean_token_accuracy": 0.13150426223874093,
|
|
"num_tokens": 9753855.0,
|
|
"step": 4440
|
|
},
|
|
{
|
|
"entropy": 5.875456953048706,
|
|
"epoch": 0.4411472806669313,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004986777094162932,
|
|
"loss": 5.6379,
|
|
"mean_token_accuracy": 0.14705183878540992,
|
|
"num_tokens": 9763883.0,
|
|
"step": 4445
|
|
},
|
|
{
|
|
"entropy": 5.748485708236695,
|
|
"epoch": 0.44164350932909885,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004986738710044187,
|
|
"loss": 5.5989,
|
|
"mean_token_accuracy": 0.14280258789658545,
|
|
"num_tokens": 9774890.0,
|
|
"step": 4450
|
|
},
|
|
{
|
|
"entropy": 5.732300472259522,
|
|
"epoch": 0.4421397379912664,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004986700270459142,
|
|
"loss": 5.5783,
|
|
"mean_token_accuracy": 0.1434408903121948,
|
|
"num_tokens": 9785249.0,
|
|
"step": 4455
|
|
},
|
|
{
|
|
"entropy": 5.791567468643189,
|
|
"epoch": 0.4426359666534339,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004986661775408749,
|
|
"loss": 5.5913,
|
|
"mean_token_accuracy": 0.14472425431013108,
|
|
"num_tokens": 9795723.0,
|
|
"step": 4460
|
|
},
|
|
{
|
|
"entropy": 5.7759202003479,
|
|
"epoch": 0.44313219531560144,
|
|
"grad_norm": 0.79296875,
|
|
"learning_rate": 0.0004986623224893965,
|
|
"loss": 5.5394,
|
|
"mean_token_accuracy": 0.1415581427514553,
|
|
"num_tokens": 9807637.0,
|
|
"step": 4465
|
|
},
|
|
{
|
|
"entropy": 5.784197425842285,
|
|
"epoch": 0.44362842397776897,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004986584618915744,
|
|
"loss": 5.648,
|
|
"mean_token_accuracy": 0.1421603761613369,
|
|
"num_tokens": 9820298.0,
|
|
"step": 4470
|
|
},
|
|
{
|
|
"entropy": 5.709079837799072,
|
|
"epoch": 0.4441246526399365,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004986545957475045,
|
|
"loss": 5.5383,
|
|
"mean_token_accuracy": 0.14711108356714248,
|
|
"num_tokens": 9831251.0,
|
|
"step": 4475
|
|
},
|
|
{
|
|
"entropy": 5.734958457946777,
|
|
"epoch": 0.44462088130210403,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004986507240572825,
|
|
"loss": 5.596,
|
|
"mean_token_accuracy": 0.14287913516163825,
|
|
"num_tokens": 9842884.0,
|
|
"step": 4480
|
|
},
|
|
{
|
|
"entropy": 5.72746171951294,
|
|
"epoch": 0.44511710996427156,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004986468468210042,
|
|
"loss": 5.4933,
|
|
"mean_token_accuracy": 0.14691198095679284,
|
|
"num_tokens": 9854413.0,
|
|
"step": 4485
|
|
},
|
|
{
|
|
"entropy": 5.793558883666992,
|
|
"epoch": 0.44561333862643904,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004986429640387663,
|
|
"loss": 5.6508,
|
|
"mean_token_accuracy": 0.1404290720820427,
|
|
"num_tokens": 9865771.0,
|
|
"step": 4490
|
|
},
|
|
{
|
|
"entropy": 5.766204071044922,
|
|
"epoch": 0.44610956728860657,
|
|
"grad_norm": 0.7734375,
|
|
"learning_rate": 0.0004986390757106648,
|
|
"loss": 5.5707,
|
|
"mean_token_accuracy": 0.1469174288213253,
|
|
"num_tokens": 9876717.0,
|
|
"step": 4495
|
|
},
|
|
{
|
|
"entropy": 5.730377721786499,
|
|
"epoch": 0.4466057959507741,
|
|
"grad_norm": 0.79296875,
|
|
"learning_rate": 0.0004986351818367959,
|
|
"loss": 5.6486,
|
|
"mean_token_accuracy": 0.140429724752903,
|
|
"num_tokens": 9887616.0,
|
|
"step": 4500
|
|
},
|
|
{
|
|
"entropy": 5.818638896942138,
|
|
"epoch": 0.44710202461294163,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004986312824172566,
|
|
"loss": 5.595,
|
|
"mean_token_accuracy": 0.14335185587406157,
|
|
"num_tokens": 9898979.0,
|
|
"step": 4505
|
|
},
|
|
{
|
|
"entropy": 5.797679376602173,
|
|
"epoch": 0.44759825327510916,
|
|
"grad_norm": 0.7890625,
|
|
"learning_rate": 0.0004986273774521433,
|
|
"loss": 5.6306,
|
|
"mean_token_accuracy": 0.13533177375793456,
|
|
"num_tokens": 9912158.0,
|
|
"step": 4510
|
|
},
|
|
{
|
|
"entropy": 5.7367393493652346,
|
|
"epoch": 0.4480944819372767,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004986234669415529,
|
|
"loss": 5.6312,
|
|
"mean_token_accuracy": 0.13736921548843384,
|
|
"num_tokens": 9923886.0,
|
|
"step": 4515
|
|
},
|
|
{
|
|
"entropy": 5.776280212402344,
|
|
"epoch": 0.4485907105994442,
|
|
"grad_norm": 0.79296875,
|
|
"learning_rate": 0.0004986195508855824,
|
|
"loss": 5.6023,
|
|
"mean_token_accuracy": 0.14297038465738296,
|
|
"num_tokens": 9934979.0,
|
|
"step": 4520
|
|
},
|
|
{
|
|
"entropy": 5.79187970161438,
|
|
"epoch": 0.44908693926161175,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.000498615629284329,
|
|
"loss": 5.7071,
|
|
"mean_token_accuracy": 0.13817890509963035,
|
|
"num_tokens": 9944715.0,
|
|
"step": 4525
|
|
},
|
|
{
|
|
"entropy": 5.775436878204346,
|
|
"epoch": 0.4495831679237793,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004986117021378896,
|
|
"loss": 5.5741,
|
|
"mean_token_accuracy": 0.14012717232108116,
|
|
"num_tokens": 9954736.0,
|
|
"step": 4530
|
|
},
|
|
{
|
|
"entropy": 5.79448766708374,
|
|
"epoch": 0.4500793965859468,
|
|
"grad_norm": 0.75,
|
|
"learning_rate": 0.000498607769446362,
|
|
"loss": 5.6594,
|
|
"mean_token_accuracy": 0.1388283774256706,
|
|
"num_tokens": 9965952.0,
|
|
"step": 4535
|
|
},
|
|
{
|
|
"entropy": 5.7624434471130375,
|
|
"epoch": 0.45057562524811434,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004986038312098435,
|
|
"loss": 5.604,
|
|
"mean_token_accuracy": 0.14314566776156426,
|
|
"num_tokens": 9976428.0,
|
|
"step": 4540
|
|
},
|
|
{
|
|
"entropy": 5.75066294670105,
|
|
"epoch": 0.4510718539102819,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004985998874284319,
|
|
"loss": 5.546,
|
|
"mean_token_accuracy": 0.1484223261475563,
|
|
"num_tokens": 9986100.0,
|
|
"step": 4545
|
|
},
|
|
{
|
|
"entropy": 5.655505847930908,
|
|
"epoch": 0.4515680825724494,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004985959381022248,
|
|
"loss": 5.5458,
|
|
"mean_token_accuracy": 0.14303347319364548,
|
|
"num_tokens": 9996584.0,
|
|
"step": 4550
|
|
},
|
|
{
|
|
"entropy": 5.739107084274292,
|
|
"epoch": 0.45206431123461693,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004985919832313203,
|
|
"loss": 5.557,
|
|
"mean_token_accuracy": 0.14798323214054107,
|
|
"num_tokens": 10007792.0,
|
|
"step": 4555
|
|
},
|
|
{
|
|
"entropy": 5.851394081115723,
|
|
"epoch": 0.45256053989678446,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004985880228158164,
|
|
"loss": 5.756,
|
|
"mean_token_accuracy": 0.13254465758800507,
|
|
"num_tokens": 10019615.0,
|
|
"step": 4560
|
|
},
|
|
{
|
|
"entropy": 5.697079610824585,
|
|
"epoch": 0.45305676855895194,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004985840568558112,
|
|
"loss": 5.5814,
|
|
"mean_token_accuracy": 0.14153416082262993,
|
|
"num_tokens": 10030223.0,
|
|
"step": 4565
|
|
},
|
|
{
|
|
"entropy": 5.775788831710815,
|
|
"epoch": 0.45355299722111947,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004985800853514033,
|
|
"loss": 5.5967,
|
|
"mean_token_accuracy": 0.137832148373127,
|
|
"num_tokens": 10041522.0,
|
|
"step": 4570
|
|
},
|
|
{
|
|
"entropy": 5.785793733596802,
|
|
"epoch": 0.454049225883287,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004985761083026911,
|
|
"loss": 5.5212,
|
|
"mean_token_accuracy": 0.15029784739017488,
|
|
"num_tokens": 10052847.0,
|
|
"step": 4575
|
|
},
|
|
{
|
|
"entropy": 5.655645513534546,
|
|
"epoch": 0.45454545454545453,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004985721257097731,
|
|
"loss": 5.5434,
|
|
"mean_token_accuracy": 0.14386311173439026,
|
|
"num_tokens": 10062259.0,
|
|
"step": 4580
|
|
},
|
|
{
|
|
"entropy": 5.820441770553589,
|
|
"epoch": 0.45504168320762206,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004985681375727482,
|
|
"loss": 5.7118,
|
|
"mean_token_accuracy": 0.13377906680107116,
|
|
"num_tokens": 10073341.0,
|
|
"step": 4585
|
|
},
|
|
{
|
|
"entropy": 5.822879838943481,
|
|
"epoch": 0.4555379118697896,
|
|
"grad_norm": 0.7890625,
|
|
"learning_rate": 0.0004985641438917151,
|
|
"loss": 5.5629,
|
|
"mean_token_accuracy": 0.14327463507652283,
|
|
"num_tokens": 10083992.0,
|
|
"step": 4590
|
|
},
|
|
{
|
|
"entropy": 5.765067672729492,
|
|
"epoch": 0.4560341405319571,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004985601446667731,
|
|
"loss": 5.5608,
|
|
"mean_token_accuracy": 0.14663187712430953,
|
|
"num_tokens": 10094245.0,
|
|
"step": 4595
|
|
},
|
|
{
|
|
"entropy": 5.7631641864776615,
|
|
"epoch": 0.45653036919412465,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004985561398980213,
|
|
"loss": 5.5366,
|
|
"mean_token_accuracy": 0.14789687395095824,
|
|
"num_tokens": 10105976.0,
|
|
"step": 4600
|
|
},
|
|
{
|
|
"entropy": 5.672163963317871,
|
|
"epoch": 0.4570265978562922,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004985521295855588,
|
|
"loss": 5.6168,
|
|
"mean_token_accuracy": 0.14210953339934349,
|
|
"num_tokens": 10117373.0,
|
|
"step": 4605
|
|
},
|
|
{
|
|
"entropy": 5.754079294204712,
|
|
"epoch": 0.4575228265184597,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004985481137294853,
|
|
"loss": 5.5685,
|
|
"mean_token_accuracy": 0.13775459825992584,
|
|
"num_tokens": 10128470.0,
|
|
"step": 4610
|
|
},
|
|
{
|
|
"entropy": 5.714517211914062,
|
|
"epoch": 0.45801905518062724,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.0004985440923299002,
|
|
"loss": 5.5662,
|
|
"mean_token_accuracy": 0.1423081412911415,
|
|
"num_tokens": 10140217.0,
|
|
"step": 4615
|
|
},
|
|
{
|
|
"entropy": 5.710232543945312,
|
|
"epoch": 0.4585152838427948,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004985400653869034,
|
|
"loss": 5.633,
|
|
"mean_token_accuracy": 0.14135775342583656,
|
|
"num_tokens": 10152308.0,
|
|
"step": 4620
|
|
},
|
|
{
|
|
"entropy": 5.8700785636901855,
|
|
"epoch": 0.4590115125049623,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004985360329005945,
|
|
"loss": 5.6582,
|
|
"mean_token_accuracy": 0.14096900820732117,
|
|
"num_tokens": 10164234.0,
|
|
"step": 4625
|
|
},
|
|
{
|
|
"entropy": 5.874130821228027,
|
|
"epoch": 0.45950774116712984,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004985319948710738,
|
|
"loss": 5.7163,
|
|
"mean_token_accuracy": 0.13750708624720573,
|
|
"num_tokens": 10175287.0,
|
|
"step": 4630
|
|
},
|
|
{
|
|
"entropy": 5.801472568511963,
|
|
"epoch": 0.46000396982929737,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004985279512984413,
|
|
"loss": 5.5875,
|
|
"mean_token_accuracy": 0.14970208927989007,
|
|
"num_tokens": 10184658.0,
|
|
"step": 4635
|
|
},
|
|
{
|
|
"entropy": 5.737123918533325,
|
|
"epoch": 0.46050019849146484,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004985239021827972,
|
|
"loss": 5.5849,
|
|
"mean_token_accuracy": 0.1390370771288872,
|
|
"num_tokens": 10194593.0,
|
|
"step": 4640
|
|
},
|
|
{
|
|
"entropy": 5.701331233978271,
|
|
"epoch": 0.46099642715363237,
|
|
"grad_norm": 0.79296875,
|
|
"learning_rate": 0.000498519847524242,
|
|
"loss": 5.5092,
|
|
"mean_token_accuracy": 0.1458827719092369,
|
|
"num_tokens": 10205200.0,
|
|
"step": 4645
|
|
},
|
|
{
|
|
"entropy": 5.724951648712159,
|
|
"epoch": 0.4614926558157999,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004985157873228762,
|
|
"loss": 5.5194,
|
|
"mean_token_accuracy": 0.14664195030927657,
|
|
"num_tokens": 10216848.0,
|
|
"step": 4650
|
|
},
|
|
{
|
|
"entropy": 5.757262468338013,
|
|
"epoch": 0.46198888447796743,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004985117215788005,
|
|
"loss": 5.5703,
|
|
"mean_token_accuracy": 0.14250332042574881,
|
|
"num_tokens": 10228188.0,
|
|
"step": 4655
|
|
},
|
|
{
|
|
"entropy": 5.751273918151855,
|
|
"epoch": 0.46248511314013496,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004985076502921158,
|
|
"loss": 5.659,
|
|
"mean_token_accuracy": 0.1386226199567318,
|
|
"num_tokens": 10238253.0,
|
|
"step": 4660
|
|
},
|
|
{
|
|
"entropy": 5.799253034591675,
|
|
"epoch": 0.4629813418023025,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.000498503573462923,
|
|
"loss": 5.604,
|
|
"mean_token_accuracy": 0.14217669069766997,
|
|
"num_tokens": 10248169.0,
|
|
"step": 4665
|
|
},
|
|
{
|
|
"entropy": 5.719962024688721,
|
|
"epoch": 0.46347757046447,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004984994910913232,
|
|
"loss": 5.4916,
|
|
"mean_token_accuracy": 0.14536735266447068,
|
|
"num_tokens": 10258962.0,
|
|
"step": 4670
|
|
},
|
|
{
|
|
"entropy": 5.754688787460327,
|
|
"epoch": 0.46397379912663755,
|
|
"grad_norm": 0.765625,
|
|
"learning_rate": 0.0004984954031774175,
|
|
"loss": 5.5963,
|
|
"mean_token_accuracy": 0.14113237708806992,
|
|
"num_tokens": 10270303.0,
|
|
"step": 4675
|
|
},
|
|
{
|
|
"entropy": 5.649554014205933,
|
|
"epoch": 0.4644700277888051,
|
|
"grad_norm": 0.7421875,
|
|
"learning_rate": 0.0004984913097213075,
|
|
"loss": 5.5111,
|
|
"mean_token_accuracy": 0.1448366239666939,
|
|
"num_tokens": 10281782.0,
|
|
"step": 4680
|
|
},
|
|
{
|
|
"entropy": 5.7514485836029055,
|
|
"epoch": 0.4649662564509726,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004984872107230945,
|
|
"loss": 5.5542,
|
|
"mean_token_accuracy": 0.14501627534627914,
|
|
"num_tokens": 10292937.0,
|
|
"step": 4685
|
|
},
|
|
{
|
|
"entropy": 5.758346080780029,
|
|
"epoch": 0.46546248511314015,
|
|
"grad_norm": 0.796875,
|
|
"learning_rate": 0.0004984831061828803,
|
|
"loss": 5.606,
|
|
"mean_token_accuracy": 0.13853585198521615,
|
|
"num_tokens": 10305443.0,
|
|
"step": 4690
|
|
},
|
|
{
|
|
"entropy": 5.717559385299682,
|
|
"epoch": 0.4659587137753077,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004984789961007667,
|
|
"loss": 5.5427,
|
|
"mean_token_accuracy": 0.14828034415841101,
|
|
"num_tokens": 10316489.0,
|
|
"step": 4695
|
|
},
|
|
{
|
|
"entropy": 5.701294040679931,
|
|
"epoch": 0.4664549424374752,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004984748804768554,
|
|
"loss": 5.5884,
|
|
"mean_token_accuracy": 0.1406767785549164,
|
|
"num_tokens": 10326690.0,
|
|
"step": 4700
|
|
},
|
|
{
|
|
"entropy": 5.7987219333648685,
|
|
"epoch": 0.46695117109964274,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004984707593112487,
|
|
"loss": 5.5973,
|
|
"mean_token_accuracy": 0.13755468428134918,
|
|
"num_tokens": 10337059.0,
|
|
"step": 4705
|
|
},
|
|
{
|
|
"entropy": 5.678113794326782,
|
|
"epoch": 0.46744739976181027,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004984666326040487,
|
|
"loss": 5.4636,
|
|
"mean_token_accuracy": 0.15040105506777762,
|
|
"num_tokens": 10347035.0,
|
|
"step": 4710
|
|
},
|
|
{
|
|
"entropy": 5.685402202606201,
|
|
"epoch": 0.46794362842397774,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004984625003553578,
|
|
"loss": 5.5931,
|
|
"mean_token_accuracy": 0.14260579720139505,
|
|
"num_tokens": 10359492.0,
|
|
"step": 4715
|
|
},
|
|
{
|
|
"entropy": 5.814010429382324,
|
|
"epoch": 0.4684398570861453,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004984583625652783,
|
|
"loss": 5.573,
|
|
"mean_token_accuracy": 0.1426217183470726,
|
|
"num_tokens": 10370128.0,
|
|
"step": 4720
|
|
},
|
|
{
|
|
"entropy": 5.729959917068482,
|
|
"epoch": 0.4689360857483128,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.000498454219233913,
|
|
"loss": 5.5762,
|
|
"mean_token_accuracy": 0.13988015651702881,
|
|
"num_tokens": 10380276.0,
|
|
"step": 4725
|
|
},
|
|
{
|
|
"entropy": 5.6514264106750485,
|
|
"epoch": 0.46943231441048033,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004984500703613645,
|
|
"loss": 5.5602,
|
|
"mean_token_accuracy": 0.1456937611103058,
|
|
"num_tokens": 10392489.0,
|
|
"step": 4730
|
|
},
|
|
{
|
|
"entropy": 5.83931975364685,
|
|
"epoch": 0.46992854307264786,
|
|
"grad_norm": 0.7421875,
|
|
"learning_rate": 0.0004984459159477358,
|
|
"loss": 5.6432,
|
|
"mean_token_accuracy": 0.13943550512194633,
|
|
"num_tokens": 10404259.0,
|
|
"step": 4735
|
|
},
|
|
{
|
|
"entropy": 5.690709781646729,
|
|
"epoch": 0.4704247717348154,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004984417559931298,
|
|
"loss": 5.5047,
|
|
"mean_token_accuracy": 0.14229437559843064,
|
|
"num_tokens": 10415000.0,
|
|
"step": 4740
|
|
},
|
|
{
|
|
"entropy": 5.74327278137207,
|
|
"epoch": 0.4709210003969829,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004984375904976498,
|
|
"loss": 5.6375,
|
|
"mean_token_accuracy": 0.13753386437892914,
|
|
"num_tokens": 10426078.0,
|
|
"step": 4745
|
|
},
|
|
{
|
|
"entropy": 5.792974853515625,
|
|
"epoch": 0.47141722905915046,
|
|
"grad_norm": 0.78125,
|
|
"learning_rate": 0.0004984334194613989,
|
|
"loss": 5.5616,
|
|
"mean_token_accuracy": 0.14064555689692498,
|
|
"num_tokens": 10436838.0,
|
|
"step": 4750
|
|
},
|
|
{
|
|
"entropy": 5.712934160232544,
|
|
"epoch": 0.471913457721318,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004984292428844809,
|
|
"loss": 5.5534,
|
|
"mean_token_accuracy": 0.1431037314236164,
|
|
"num_tokens": 10448544.0,
|
|
"step": 4755
|
|
},
|
|
{
|
|
"entropy": 5.819026613235474,
|
|
"epoch": 0.4724096863834855,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004984250607669989,
|
|
"loss": 5.6213,
|
|
"mean_token_accuracy": 0.1387665741145611,
|
|
"num_tokens": 10459730.0,
|
|
"step": 4760
|
|
},
|
|
{
|
|
"entropy": 5.8150371551513675,
|
|
"epoch": 0.47290591504565305,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004984208731090569,
|
|
"loss": 5.6797,
|
|
"mean_token_accuracy": 0.14077720865607263,
|
|
"num_tokens": 10470257.0,
|
|
"step": 4765
|
|
},
|
|
{
|
|
"entropy": 5.776945304870606,
|
|
"epoch": 0.4734021437078206,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004984166799107587,
|
|
"loss": 5.6371,
|
|
"mean_token_accuracy": 0.14257957339286803,
|
|
"num_tokens": 10480835.0,
|
|
"step": 4770
|
|
},
|
|
{
|
|
"entropy": 5.759775972366333,
|
|
"epoch": 0.4738983723699881,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004984124811722081,
|
|
"loss": 5.6488,
|
|
"mean_token_accuracy": 0.14650474786758422,
|
|
"num_tokens": 10491720.0,
|
|
"step": 4775
|
|
},
|
|
{
|
|
"entropy": 5.753606271743775,
|
|
"epoch": 0.47439460103215564,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004984082768935096,
|
|
"loss": 5.6651,
|
|
"mean_token_accuracy": 0.14373267889022828,
|
|
"num_tokens": 10502313.0,
|
|
"step": 4780
|
|
},
|
|
{
|
|
"entropy": 5.78562560081482,
|
|
"epoch": 0.47489082969432317,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004984040670747672,
|
|
"loss": 5.54,
|
|
"mean_token_accuracy": 0.14707302302122116,
|
|
"num_tokens": 10513333.0,
|
|
"step": 4785
|
|
},
|
|
{
|
|
"entropy": 5.711219787597656,
|
|
"epoch": 0.47538705835649064,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004983998517160852,
|
|
"loss": 5.5278,
|
|
"mean_token_accuracy": 0.15109342858195304,
|
|
"num_tokens": 10522766.0,
|
|
"step": 4790
|
|
},
|
|
{
|
|
"entropy": 5.755279207229615,
|
|
"epoch": 0.4758832870186582,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004983956308175684,
|
|
"loss": 5.5675,
|
|
"mean_token_accuracy": 0.14042461812496185,
|
|
"num_tokens": 10534362.0,
|
|
"step": 4795
|
|
},
|
|
{
|
|
"entropy": 5.7386070728302006,
|
|
"epoch": 0.4763795156808257,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004983914043793212,
|
|
"loss": 5.5811,
|
|
"mean_token_accuracy": 0.14227042123675346,
|
|
"num_tokens": 10545072.0,
|
|
"step": 4800
|
|
},
|
|
{
|
|
"entropy": 5.673999500274658,
|
|
"epoch": 0.47687574434299324,
|
|
"grad_norm": 0.796875,
|
|
"learning_rate": 0.0004983871724014487,
|
|
"loss": 5.5169,
|
|
"mean_token_accuracy": 0.14101085662841797,
|
|
"num_tokens": 10555953.0,
|
|
"step": 4805
|
|
},
|
|
{
|
|
"entropy": 5.778817129135132,
|
|
"epoch": 0.47737197300516077,
|
|
"grad_norm": 0.77734375,
|
|
"learning_rate": 0.0004983829348840556,
|
|
"loss": 5.5675,
|
|
"mean_token_accuracy": 0.14799523502588272,
|
|
"num_tokens": 10567757.0,
|
|
"step": 4810
|
|
},
|
|
{
|
|
"entropy": 5.668074464797973,
|
|
"epoch": 0.4778682016673283,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.000498378691827247,
|
|
"loss": 5.4701,
|
|
"mean_token_accuracy": 0.1479513630270958,
|
|
"num_tokens": 10579390.0,
|
|
"step": 4815
|
|
},
|
|
{
|
|
"entropy": 5.742642593383789,
|
|
"epoch": 0.4783644303294958,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004983744432311282,
|
|
"loss": 5.6669,
|
|
"mean_token_accuracy": 0.13707347735762596,
|
|
"num_tokens": 10589624.0,
|
|
"step": 4820
|
|
},
|
|
{
|
|
"entropy": 5.829803085327148,
|
|
"epoch": 0.47886065899166336,
|
|
"grad_norm": 0.796875,
|
|
"learning_rate": 0.0004983701890958046,
|
|
"loss": 5.6361,
|
|
"mean_token_accuracy": 0.13275278136134147,
|
|
"num_tokens": 10601927.0,
|
|
"step": 4825
|
|
},
|
|
{
|
|
"entropy": 5.667952632904052,
|
|
"epoch": 0.4793568876538309,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004983659294213815,
|
|
"loss": 5.5147,
|
|
"mean_token_accuracy": 0.1479553312063217,
|
|
"num_tokens": 10614073.0,
|
|
"step": 4830
|
|
},
|
|
{
|
|
"entropy": 5.720580911636352,
|
|
"epoch": 0.4798531163159984,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004983616642079649,
|
|
"loss": 5.5511,
|
|
"mean_token_accuracy": 0.1447890058159828,
|
|
"num_tokens": 10625535.0,
|
|
"step": 4835
|
|
},
|
|
{
|
|
"entropy": 5.812899208068847,
|
|
"epoch": 0.48034934497816595,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004983573934556601,
|
|
"loss": 5.5241,
|
|
"mean_token_accuracy": 0.1474653646349907,
|
|
"num_tokens": 10637160.0,
|
|
"step": 4840
|
|
},
|
|
{
|
|
"entropy": 5.780987215042114,
|
|
"epoch": 0.4808455736403335,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004983531171645734,
|
|
"loss": 5.6279,
|
|
"mean_token_accuracy": 0.14129644334316255,
|
|
"num_tokens": 10649061.0,
|
|
"step": 4845
|
|
},
|
|
{
|
|
"entropy": 5.638265609741211,
|
|
"epoch": 0.481341802302501,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004983488353348106,
|
|
"loss": 5.4829,
|
|
"mean_token_accuracy": 0.14804023057222365,
|
|
"num_tokens": 10661130.0,
|
|
"step": 4850
|
|
},
|
|
{
|
|
"entropy": 5.721083116531372,
|
|
"epoch": 0.48183803096466854,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004983445479664779,
|
|
"loss": 5.5476,
|
|
"mean_token_accuracy": 0.1464819297194481,
|
|
"num_tokens": 10673017.0,
|
|
"step": 4855
|
|
},
|
|
{
|
|
"entropy": 5.7977289199829105,
|
|
"epoch": 0.48233425962683607,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004983402550596817,
|
|
"loss": 5.6084,
|
|
"mean_token_accuracy": 0.14504522681236268,
|
|
"num_tokens": 10683268.0,
|
|
"step": 4860
|
|
},
|
|
{
|
|
"entropy": 5.833132791519165,
|
|
"epoch": 0.48283048828900355,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004983359566145285,
|
|
"loss": 5.6222,
|
|
"mean_token_accuracy": 0.14250127971172333,
|
|
"num_tokens": 10694220.0,
|
|
"step": 4865
|
|
},
|
|
{
|
|
"entropy": 5.747547292709351,
|
|
"epoch": 0.4833267169511711,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004983316526311248,
|
|
"loss": 5.5401,
|
|
"mean_token_accuracy": 0.14009479209780692,
|
|
"num_tokens": 10704829.0,
|
|
"step": 4870
|
|
},
|
|
{
|
|
"entropy": 5.74469518661499,
|
|
"epoch": 0.4838229456133386,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004983273431095773,
|
|
"loss": 5.7219,
|
|
"mean_token_accuracy": 0.13392212018370628,
|
|
"num_tokens": 10717160.0,
|
|
"step": 4875
|
|
},
|
|
{
|
|
"entropy": 5.78354058265686,
|
|
"epoch": 0.48431917427550614,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004983230280499929,
|
|
"loss": 5.5425,
|
|
"mean_token_accuracy": 0.14195659756660461,
|
|
"num_tokens": 10728638.0,
|
|
"step": 4880
|
|
},
|
|
{
|
|
"entropy": 5.737115001678466,
|
|
"epoch": 0.48481540293767367,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004983187074524787,
|
|
"loss": 5.5888,
|
|
"mean_token_accuracy": 0.13973118513822555,
|
|
"num_tokens": 10740122.0,
|
|
"step": 4885
|
|
},
|
|
{
|
|
"entropy": 5.766622018814087,
|
|
"epoch": 0.4853116315998412,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004983143813171418,
|
|
"loss": 5.5563,
|
|
"mean_token_accuracy": 0.1492931678891182,
|
|
"num_tokens": 10751103.0,
|
|
"step": 4890
|
|
},
|
|
{
|
|
"entropy": 5.706625509262085,
|
|
"epoch": 0.48580786026200873,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004983100496440895,
|
|
"loss": 5.5063,
|
|
"mean_token_accuracy": 0.1490258678793907,
|
|
"num_tokens": 10761937.0,
|
|
"step": 4895
|
|
},
|
|
{
|
|
"entropy": 5.796269845962525,
|
|
"epoch": 0.48630408892417626,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.000498305712433429,
|
|
"loss": 5.7346,
|
|
"mean_token_accuracy": 0.14223510399460793,
|
|
"num_tokens": 10773527.0,
|
|
"step": 4900
|
|
},
|
|
{
|
|
"entropy": 5.765747499465943,
|
|
"epoch": 0.4868003175863438,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.000498301369685268,
|
|
"loss": 5.5754,
|
|
"mean_token_accuracy": 0.14397116079926492,
|
|
"num_tokens": 10783873.0,
|
|
"step": 4905
|
|
},
|
|
{
|
|
"entropy": 5.6565389156341555,
|
|
"epoch": 0.4872965462485113,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004982970213997142,
|
|
"loss": 5.4238,
|
|
"mean_token_accuracy": 0.15091024041175843,
|
|
"num_tokens": 10796124.0,
|
|
"step": 4910
|
|
},
|
|
{
|
|
"entropy": 5.614575958251953,
|
|
"epoch": 0.48779277491067885,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004982926675768756,
|
|
"loss": 5.5215,
|
|
"mean_token_accuracy": 0.14468540474772454,
|
|
"num_tokens": 10806468.0,
|
|
"step": 4915
|
|
},
|
|
{
|
|
"entropy": 5.737712860107422,
|
|
"epoch": 0.4882890035728464,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004982883082168599,
|
|
"loss": 5.5778,
|
|
"mean_token_accuracy": 0.14341849982738494,
|
|
"num_tokens": 10817126.0,
|
|
"step": 4920
|
|
},
|
|
{
|
|
"entropy": 5.780298519134521,
|
|
"epoch": 0.4887852322350139,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004982839433197752,
|
|
"loss": 5.597,
|
|
"mean_token_accuracy": 0.13673522770404817,
|
|
"num_tokens": 10828985.0,
|
|
"step": 4925
|
|
},
|
|
{
|
|
"entropy": 5.686007690429688,
|
|
"epoch": 0.48928146089718144,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.00049827957288573,
|
|
"loss": 5.5045,
|
|
"mean_token_accuracy": 0.14484182596206666,
|
|
"num_tokens": 10840528.0,
|
|
"step": 4930
|
|
},
|
|
{
|
|
"entropy": 5.708341026306153,
|
|
"epoch": 0.48977768955934897,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004982751969148324,
|
|
"loss": 5.5301,
|
|
"mean_token_accuracy": 0.14575338512659072,
|
|
"num_tokens": 10851312.0,
|
|
"step": 4935
|
|
},
|
|
{
|
|
"entropy": 5.67660961151123,
|
|
"epoch": 0.49027391822151645,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004982708154071912,
|
|
"loss": 5.4893,
|
|
"mean_token_accuracy": 0.1472529575228691,
|
|
"num_tokens": 10861882.0,
|
|
"step": 4940
|
|
},
|
|
{
|
|
"entropy": 5.73410964012146,
|
|
"epoch": 0.490770146883684,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004982664283629147,
|
|
"loss": 5.6418,
|
|
"mean_token_accuracy": 0.135673226416111,
|
|
"num_tokens": 10873187.0,
|
|
"step": 4945
|
|
},
|
|
{
|
|
"entropy": 5.750768995285034,
|
|
"epoch": 0.4912663755458515,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004982620357821118,
|
|
"loss": 5.529,
|
|
"mean_token_accuracy": 0.1487978346645832,
|
|
"num_tokens": 10884254.0,
|
|
"step": 4950
|
|
},
|
|
{
|
|
"entropy": 5.62707486152649,
|
|
"epoch": 0.49176260420801904,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004982576376648918,
|
|
"loss": 5.5165,
|
|
"mean_token_accuracy": 0.14257091730833055,
|
|
"num_tokens": 10895770.0,
|
|
"step": 4955
|
|
},
|
|
{
|
|
"entropy": 5.730557155609131,
|
|
"epoch": 0.49225883287018657,
|
|
"grad_norm": 0.79296875,
|
|
"learning_rate": 0.0004982532340113633,
|
|
"loss": 5.5434,
|
|
"mean_token_accuracy": 0.14722897857427597,
|
|
"num_tokens": 10906436.0,
|
|
"step": 4960
|
|
},
|
|
{
|
|
"entropy": 5.758408737182617,
|
|
"epoch": 0.4927550615323541,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004982488248216357,
|
|
"loss": 5.4945,
|
|
"mean_token_accuracy": 0.14825854152441026,
|
|
"num_tokens": 10917655.0,
|
|
"step": 4965
|
|
},
|
|
{
|
|
"entropy": 5.69063892364502,
|
|
"epoch": 0.49325129019452163,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004982444100958182,
|
|
"loss": 5.515,
|
|
"mean_token_accuracy": 0.1498719871044159,
|
|
"num_tokens": 10928359.0,
|
|
"step": 4970
|
|
},
|
|
{
|
|
"entropy": 5.748080778121948,
|
|
"epoch": 0.49374751885668916,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.0004982399898340205,
|
|
"loss": 5.6798,
|
|
"mean_token_accuracy": 0.1363233283162117,
|
|
"num_tokens": 10940494.0,
|
|
"step": 4975
|
|
},
|
|
{
|
|
"entropy": 5.799513626098633,
|
|
"epoch": 0.4942437475188567,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.000498235564036352,
|
|
"loss": 5.6694,
|
|
"mean_token_accuracy": 0.13602429032325744,
|
|
"num_tokens": 10951298.0,
|
|
"step": 4980
|
|
},
|
|
{
|
|
"entropy": 5.7167809963226315,
|
|
"epoch": 0.4947399761810242,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004982311327029226,
|
|
"loss": 5.565,
|
|
"mean_token_accuracy": 0.14564179703593255,
|
|
"num_tokens": 10961680.0,
|
|
"step": 4985
|
|
},
|
|
{
|
|
"entropy": 5.820360136032105,
|
|
"epoch": 0.49523620484319175,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004982266958338421,
|
|
"loss": 5.6719,
|
|
"mean_token_accuracy": 0.14173018112778663,
|
|
"num_tokens": 10974968.0,
|
|
"step": 4990
|
|
},
|
|
{
|
|
"entropy": 5.712174558639527,
|
|
"epoch": 0.4957324335053593,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004982222534292205,
|
|
"loss": 5.6018,
|
|
"mean_token_accuracy": 0.13866912946105003,
|
|
"num_tokens": 10986383.0,
|
|
"step": 4995
|
|
},
|
|
{
|
|
"entropy": 5.779634046554565,
|
|
"epoch": 0.4962286621675268,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004982178054891681,
|
|
"loss": 5.6601,
|
|
"mean_token_accuracy": 0.14250716120004653,
|
|
"num_tokens": 10998384.0,
|
|
"step": 5000
|
|
},
|
|
{
|
|
"entropy": 5.722892570495605,
|
|
"epoch": 0.49672489082969434,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004982133520137951,
|
|
"loss": 5.4276,
|
|
"mean_token_accuracy": 0.15285419523715973,
|
|
"num_tokens": 11009420.0,
|
|
"step": 5005
|
|
},
|
|
{
|
|
"entropy": 5.763294076919555,
|
|
"epoch": 0.4972211194918619,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004982088930032119,
|
|
"loss": 5.5968,
|
|
"mean_token_accuracy": 0.1417885646224022,
|
|
"num_tokens": 11019601.0,
|
|
"step": 5010
|
|
},
|
|
{
|
|
"entropy": 5.721580982208252,
|
|
"epoch": 0.4977173481540294,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004982044284575293,
|
|
"loss": 5.5333,
|
|
"mean_token_accuracy": 0.1445724494755268,
|
|
"num_tokens": 11031138.0,
|
|
"step": 5015
|
|
},
|
|
{
|
|
"entropy": 5.723393726348877,
|
|
"epoch": 0.4982135768161969,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004981999583768576,
|
|
"loss": 5.5418,
|
|
"mean_token_accuracy": 0.14509216398000718,
|
|
"num_tokens": 11041643.0,
|
|
"step": 5020
|
|
},
|
|
{
|
|
"entropy": 5.676524686813354,
|
|
"epoch": 0.4987098054783644,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.000498195482761308,
|
|
"loss": 5.5537,
|
|
"mean_token_accuracy": 0.13784084841609,
|
|
"num_tokens": 11052116.0,
|
|
"step": 5025
|
|
},
|
|
{
|
|
"entropy": 5.821243333816528,
|
|
"epoch": 0.49920603414053194,
|
|
"grad_norm": 0.79296875,
|
|
"learning_rate": 0.0004981910016109914,
|
|
"loss": 5.734,
|
|
"mean_token_accuracy": 0.136544182151556,
|
|
"num_tokens": 11064796.0,
|
|
"step": 5030
|
|
},
|
|
{
|
|
"entropy": 5.8484121799469,
|
|
"epoch": 0.49970226280269947,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004981865149260189,
|
|
"loss": 5.5833,
|
|
"mean_token_accuracy": 0.14325116872787474,
|
|
"num_tokens": 11075029.0,
|
|
"step": 5035
|
|
},
|
|
{
|
|
"entropy": 5.731780004501343,
|
|
"epoch": 0.5001984914648671,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.0004981820227065016,
|
|
"loss": 5.6085,
|
|
"mean_token_accuracy": 0.14171847850084304,
|
|
"num_tokens": 11086702.0,
|
|
"step": 5040
|
|
},
|
|
{
|
|
"entropy": 5.700930786132813,
|
|
"epoch": 0.5006947201270345,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004981775249525513,
|
|
"loss": 5.5816,
|
|
"mean_token_accuracy": 0.1423800431191921,
|
|
"num_tokens": 11097417.0,
|
|
"step": 5045
|
|
},
|
|
{
|
|
"entropy": 5.67112922668457,
|
|
"epoch": 0.5011909487892021,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004981730216642791,
|
|
"loss": 5.4835,
|
|
"mean_token_accuracy": 0.14785366728901864,
|
|
"num_tokens": 11108458.0,
|
|
"step": 5050
|
|
},
|
|
{
|
|
"entropy": 5.775296688079834,
|
|
"epoch": 0.5016871774513696,
|
|
"grad_norm": 0.78125,
|
|
"learning_rate": 0.0004981685128417969,
|
|
"loss": 5.6521,
|
|
"mean_token_accuracy": 0.1389369361102581,
|
|
"num_tokens": 11121466.0,
|
|
"step": 5055
|
|
},
|
|
{
|
|
"entropy": 5.7190674304962155,
|
|
"epoch": 0.5021834061135371,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004981639984852165,
|
|
"loss": 5.5956,
|
|
"mean_token_accuracy": 0.13504938408732414,
|
|
"num_tokens": 11132489.0,
|
|
"step": 5060
|
|
},
|
|
{
|
|
"entropy": 5.695435190200806,
|
|
"epoch": 0.5026796347757047,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004981594785946498,
|
|
"loss": 5.5532,
|
|
"mean_token_accuracy": 0.14500434398651124,
|
|
"num_tokens": 11143087.0,
|
|
"step": 5065
|
|
},
|
|
{
|
|
"entropy": 5.7991992950439455,
|
|
"epoch": 0.5031758634378721,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004981549531702089,
|
|
"loss": 5.5835,
|
|
"mean_token_accuracy": 0.1371206223964691,
|
|
"num_tokens": 11154229.0,
|
|
"step": 5070
|
|
},
|
|
{
|
|
"entropy": 5.748044872283936,
|
|
"epoch": 0.5036720921000397,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.000498150422212006,
|
|
"loss": 5.5454,
|
|
"mean_token_accuracy": 0.143742111325264,
|
|
"num_tokens": 11165698.0,
|
|
"step": 5075
|
|
},
|
|
{
|
|
"entropy": 5.725100755691528,
|
|
"epoch": 0.5041683207622072,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004981458857201534,
|
|
"loss": 5.5462,
|
|
"mean_token_accuracy": 0.14240316525101662,
|
|
"num_tokens": 11177025.0,
|
|
"step": 5080
|
|
},
|
|
{
|
|
"entropy": 5.78506989479065,
|
|
"epoch": 0.5046645494243748,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004981413436947639,
|
|
"loss": 5.6209,
|
|
"mean_token_accuracy": 0.14323396608233452,
|
|
"num_tokens": 11188766.0,
|
|
"step": 5085
|
|
},
|
|
{
|
|
"entropy": 5.720196533203125,
|
|
"epoch": 0.5051607780865423,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004981367961359496,
|
|
"loss": 5.6546,
|
|
"mean_token_accuracy": 0.13432737216353416,
|
|
"num_tokens": 11201626.0,
|
|
"step": 5090
|
|
},
|
|
{
|
|
"entropy": 5.732619857788086,
|
|
"epoch": 0.5056570067487098,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004981322430438239,
|
|
"loss": 5.564,
|
|
"mean_token_accuracy": 0.13936000987887381,
|
|
"num_tokens": 11213975.0,
|
|
"step": 5095
|
|
},
|
|
{
|
|
"entropy": 5.688735437393189,
|
|
"epoch": 0.5061532354108773,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004981276844184991,
|
|
"loss": 5.5301,
|
|
"mean_token_accuracy": 0.14741144627332686,
|
|
"num_tokens": 11223636.0,
|
|
"step": 5100
|
|
},
|
|
{
|
|
"entropy": 5.6913628578186035,
|
|
"epoch": 0.5066494640730449,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004981231202600886,
|
|
"loss": 5.497,
|
|
"mean_token_accuracy": 0.14770336896181108,
|
|
"num_tokens": 11233549.0,
|
|
"step": 5105
|
|
},
|
|
{
|
|
"entropy": 5.639012718200684,
|
|
"epoch": 0.5071456927352124,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004981185505687056,
|
|
"loss": 5.5018,
|
|
"mean_token_accuracy": 0.14809941947460176,
|
|
"num_tokens": 11242915.0,
|
|
"step": 5110
|
|
},
|
|
{
|
|
"entropy": 5.788972234725952,
|
|
"epoch": 0.50764192139738,
|
|
"grad_norm": 0.80078125,
|
|
"learning_rate": 0.0004981139753444632,
|
|
"loss": 5.6213,
|
|
"mean_token_accuracy": 0.13717583566904068,
|
|
"num_tokens": 11254370.0,
|
|
"step": 5115
|
|
},
|
|
{
|
|
"entropy": 5.745554065704345,
|
|
"epoch": 0.5081381500595474,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004981093945874752,
|
|
"loss": 5.5478,
|
|
"mean_token_accuracy": 0.15008534342050553,
|
|
"num_tokens": 11264226.0,
|
|
"step": 5120
|
|
},
|
|
{
|
|
"entropy": 5.689509296417237,
|
|
"epoch": 0.508634378721715,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004981048082978547,
|
|
"loss": 5.4536,
|
|
"mean_token_accuracy": 0.1530928671360016,
|
|
"num_tokens": 11275304.0,
|
|
"step": 5125
|
|
},
|
|
{
|
|
"entropy": 5.705717992782593,
|
|
"epoch": 0.5091306073838825,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004981002164757158,
|
|
"loss": 5.5157,
|
|
"mean_token_accuracy": 0.14436992928385733,
|
|
"num_tokens": 11286179.0,
|
|
"step": 5130
|
|
},
|
|
{
|
|
"entropy": 5.761962938308716,
|
|
"epoch": 0.50962683604605,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004980956191211723,
|
|
"loss": 5.5448,
|
|
"mean_token_accuracy": 0.14527795910835267,
|
|
"num_tokens": 11297244.0,
|
|
"step": 5135
|
|
},
|
|
{
|
|
"entropy": 5.739287281036377,
|
|
"epoch": 0.5101230647082176,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004980910162343382,
|
|
"loss": 5.5531,
|
|
"mean_token_accuracy": 0.14658074975013732,
|
|
"num_tokens": 11307251.0,
|
|
"step": 5140
|
|
},
|
|
{
|
|
"entropy": 5.726897239685059,
|
|
"epoch": 0.510619293370385,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004980864078153275,
|
|
"loss": 5.5294,
|
|
"mean_token_accuracy": 0.1411370761692524,
|
|
"num_tokens": 11318441.0,
|
|
"step": 5145
|
|
},
|
|
{
|
|
"entropy": 5.605728054046631,
|
|
"epoch": 0.5111155220325526,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004980817938642548,
|
|
"loss": 5.497,
|
|
"mean_token_accuracy": 0.1480163112282753,
|
|
"num_tokens": 11328743.0,
|
|
"step": 5150
|
|
},
|
|
{
|
|
"entropy": 5.608948802947998,
|
|
"epoch": 0.5116117506947201,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.000498077174381234,
|
|
"loss": 5.4985,
|
|
"mean_token_accuracy": 0.148304795473814,
|
|
"num_tokens": 11340745.0,
|
|
"step": 5155
|
|
},
|
|
{
|
|
"entropy": 5.767784595489502,
|
|
"epoch": 0.5121079793568877,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004980725493663802,
|
|
"loss": 5.5726,
|
|
"mean_token_accuracy": 0.14685158357024192,
|
|
"num_tokens": 11352060.0,
|
|
"step": 5160
|
|
},
|
|
{
|
|
"entropy": 5.702456951141357,
|
|
"epoch": 0.5126042080190552,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004980679188198078,
|
|
"loss": 5.5702,
|
|
"mean_token_accuracy": 0.14360618591308594,
|
|
"num_tokens": 11363097.0,
|
|
"step": 5165
|
|
},
|
|
{
|
|
"entropy": 5.721812438964844,
|
|
"epoch": 0.5131004366812227,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004980632827416317,
|
|
"loss": 5.602,
|
|
"mean_token_accuracy": 0.15401604920625686,
|
|
"num_tokens": 11373410.0,
|
|
"step": 5170
|
|
},
|
|
{
|
|
"entropy": 5.758921146392822,
|
|
"epoch": 0.5135966653433902,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004980586411319669,
|
|
"loss": 5.6816,
|
|
"mean_token_accuracy": 0.13971229791641235,
|
|
"num_tokens": 11385615.0,
|
|
"step": 5175
|
|
},
|
|
{
|
|
"entropy": 5.666999673843383,
|
|
"epoch": 0.5140928940055578,
|
|
"grad_norm": 0.76953125,
|
|
"learning_rate": 0.0004980539939909283,
|
|
"loss": 5.4783,
|
|
"mean_token_accuracy": 0.14054736942052842,
|
|
"num_tokens": 11396492.0,
|
|
"step": 5180
|
|
},
|
|
{
|
|
"entropy": 5.781865406036377,
|
|
"epoch": 0.5145891226677253,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004980493413186314,
|
|
"loss": 5.5828,
|
|
"mean_token_accuracy": 0.13886439129710199,
|
|
"num_tokens": 11406377.0,
|
|
"step": 5185
|
|
},
|
|
{
|
|
"entropy": 5.740067386627198,
|
|
"epoch": 0.5150853513298929,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004980446831151914,
|
|
"loss": 5.5575,
|
|
"mean_token_accuracy": 0.1424478217959404,
|
|
"num_tokens": 11416862.0,
|
|
"step": 5190
|
|
},
|
|
{
|
|
"entropy": 5.631788444519043,
|
|
"epoch": 0.5155815799920603,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004980400193807239,
|
|
"loss": 5.5077,
|
|
"mean_token_accuracy": 0.14980673640966416,
|
|
"num_tokens": 11428246.0,
|
|
"step": 5195
|
|
},
|
|
{
|
|
"entropy": 5.748811864852906,
|
|
"epoch": 0.5160778086542279,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004980353501153446,
|
|
"loss": 5.5369,
|
|
"mean_token_accuracy": 0.14516637101769447,
|
|
"num_tokens": 11438147.0,
|
|
"step": 5200
|
|
},
|
|
{
|
|
"entropy": 5.762879467010498,
|
|
"epoch": 0.5165740373163954,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004980306753191691,
|
|
"loss": 5.6576,
|
|
"mean_token_accuracy": 0.13611230552196502,
|
|
"num_tokens": 11449154.0,
|
|
"step": 5205
|
|
},
|
|
{
|
|
"entropy": 5.747657585144043,
|
|
"epoch": 0.5170702659785629,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004980259949923135,
|
|
"loss": 5.5571,
|
|
"mean_token_accuracy": 0.14405836015939713,
|
|
"num_tokens": 11459262.0,
|
|
"step": 5210
|
|
},
|
|
{
|
|
"entropy": 5.719294309616089,
|
|
"epoch": 0.5175664946407305,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004980213091348938,
|
|
"loss": 5.5391,
|
|
"mean_token_accuracy": 0.14385731667280197,
|
|
"num_tokens": 11471991.0,
|
|
"step": 5215
|
|
},
|
|
{
|
|
"entropy": 5.700556945800781,
|
|
"epoch": 0.5180627233028979,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004980166177470262,
|
|
"loss": 5.4846,
|
|
"mean_token_accuracy": 0.14262256026268005,
|
|
"num_tokens": 11483176.0,
|
|
"step": 5220
|
|
},
|
|
{
|
|
"entropy": 5.722855520248413,
|
|
"epoch": 0.5185589519650655,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004980119208288271,
|
|
"loss": 5.5731,
|
|
"mean_token_accuracy": 0.14170767962932587,
|
|
"num_tokens": 11494015.0,
|
|
"step": 5225
|
|
},
|
|
{
|
|
"entropy": 5.6596784591674805,
|
|
"epoch": 0.519055180627233,
|
|
"grad_norm": 0.7421875,
|
|
"learning_rate": 0.0004980072183804128,
|
|
"loss": 5.4895,
|
|
"mean_token_accuracy": 0.1490239754319191,
|
|
"num_tokens": 11506365.0,
|
|
"step": 5230
|
|
},
|
|
{
|
|
"entropy": 5.706877708435059,
|
|
"epoch": 0.5195514092894006,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004980025104019,
|
|
"loss": 5.5856,
|
|
"mean_token_accuracy": 0.15004663541913033,
|
|
"num_tokens": 11517199.0,
|
|
"step": 5235
|
|
},
|
|
{
|
|
"entropy": 5.682269048690796,
|
|
"epoch": 0.520047637951568,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004979977968934056,
|
|
"loss": 5.4337,
|
|
"mean_token_accuracy": 0.15386080890893936,
|
|
"num_tokens": 11527591.0,
|
|
"step": 5240
|
|
},
|
|
{
|
|
"entropy": 5.74504714012146,
|
|
"epoch": 0.5205438666137356,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004979930778550463,
|
|
"loss": 5.6126,
|
|
"mean_token_accuracy": 0.14512009173631668,
|
|
"num_tokens": 11538657.0,
|
|
"step": 5245
|
|
},
|
|
{
|
|
"entropy": 5.662412548065186,
|
|
"epoch": 0.5210400952759031,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004979883532869392,
|
|
"loss": 5.4288,
|
|
"mean_token_accuracy": 0.16117970496416092,
|
|
"num_tokens": 11549513.0,
|
|
"step": 5250
|
|
},
|
|
{
|
|
"entropy": 5.721430921554566,
|
|
"epoch": 0.5215363239380707,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004979836231892013,
|
|
"loss": 5.5206,
|
|
"mean_token_accuracy": 0.1425759568810463,
|
|
"num_tokens": 11560376.0,
|
|
"step": 5255
|
|
},
|
|
{
|
|
"entropy": 5.672984027862549,
|
|
"epoch": 0.5220325526002382,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004979788875619501,
|
|
"loss": 5.4948,
|
|
"mean_token_accuracy": 0.14300124421715737,
|
|
"num_tokens": 11571218.0,
|
|
"step": 5260
|
|
},
|
|
{
|
|
"entropy": 5.7140038967132565,
|
|
"epoch": 0.5225287812624058,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.000497974146405303,
|
|
"loss": 5.5693,
|
|
"mean_token_accuracy": 0.14280975982546806,
|
|
"num_tokens": 11581981.0,
|
|
"step": 5265
|
|
},
|
|
{
|
|
"entropy": 5.675239849090576,
|
|
"epoch": 0.5230250099245732,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004979693997193776,
|
|
"loss": 5.5226,
|
|
"mean_token_accuracy": 0.14427190124988556,
|
|
"num_tokens": 11592561.0,
|
|
"step": 5270
|
|
},
|
|
{
|
|
"entropy": 5.732921123504639,
|
|
"epoch": 0.5235212385867408,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004979646475042914,
|
|
"loss": 5.4962,
|
|
"mean_token_accuracy": 0.14883433431386947,
|
|
"num_tokens": 11601933.0,
|
|
"step": 5275
|
|
},
|
|
{
|
|
"entropy": 5.660780525207519,
|
|
"epoch": 0.5240174672489083,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004979598897601625,
|
|
"loss": 5.4274,
|
|
"mean_token_accuracy": 0.15457454025745393,
|
|
"num_tokens": 11613938.0,
|
|
"step": 5280
|
|
},
|
|
{
|
|
"entropy": 5.766283369064331,
|
|
"epoch": 0.5245136959110758,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004979551264871088,
|
|
"loss": 5.6035,
|
|
"mean_token_accuracy": 0.13649525493383408,
|
|
"num_tokens": 11624890.0,
|
|
"step": 5285
|
|
},
|
|
{
|
|
"entropy": 5.738007640838623,
|
|
"epoch": 0.5250099245732434,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004979503576852482,
|
|
"loss": 5.6069,
|
|
"mean_token_accuracy": 0.14732139855623244,
|
|
"num_tokens": 11635080.0,
|
|
"step": 5290
|
|
},
|
|
{
|
|
"entropy": 5.656884241104126,
|
|
"epoch": 0.5255061532354108,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004979455833546994,
|
|
"loss": 5.5011,
|
|
"mean_token_accuracy": 0.14415451809763907,
|
|
"num_tokens": 11645180.0,
|
|
"step": 5295
|
|
},
|
|
{
|
|
"entropy": 5.749808835983276,
|
|
"epoch": 0.5260023818975784,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004979408034955804,
|
|
"loss": 5.5431,
|
|
"mean_token_accuracy": 0.14449771195650102,
|
|
"num_tokens": 11657599.0,
|
|
"step": 5300
|
|
},
|
|
{
|
|
"entropy": 5.738276576995849,
|
|
"epoch": 0.5264986105597459,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004979360181080099,
|
|
"loss": 5.5817,
|
|
"mean_token_accuracy": 0.13297581300139427,
|
|
"num_tokens": 11669177.0,
|
|
"step": 5305
|
|
},
|
|
{
|
|
"entropy": 5.658540487289429,
|
|
"epoch": 0.5269948392219135,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004979312271921065,
|
|
"loss": 5.4448,
|
|
"mean_token_accuracy": 0.14841168075799943,
|
|
"num_tokens": 11679756.0,
|
|
"step": 5310
|
|
},
|
|
{
|
|
"entropy": 5.681262445449829,
|
|
"epoch": 0.527491067884081,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.000497926430747989,
|
|
"loss": 5.5043,
|
|
"mean_token_accuracy": 0.1484253525733948,
|
|
"num_tokens": 11689805.0,
|
|
"step": 5315
|
|
},
|
|
{
|
|
"entropy": 5.6945432186126705,
|
|
"epoch": 0.5279872965462485,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004979216287757764,
|
|
"loss": 5.5277,
|
|
"mean_token_accuracy": 0.14734025299549103,
|
|
"num_tokens": 11701150.0,
|
|
"step": 5320
|
|
},
|
|
{
|
|
"entropy": 5.623287963867187,
|
|
"epoch": 0.528483525208416,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.000497916821275588,
|
|
"loss": 5.4639,
|
|
"mean_token_accuracy": 0.1452282652258873,
|
|
"num_tokens": 11712256.0,
|
|
"step": 5325
|
|
},
|
|
{
|
|
"entropy": 5.703384447097778,
|
|
"epoch": 0.5289797538705836,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004979120082475424,
|
|
"loss": 5.5123,
|
|
"mean_token_accuracy": 0.14741147682070732,
|
|
"num_tokens": 11722547.0,
|
|
"step": 5330
|
|
},
|
|
{
|
|
"entropy": 5.716305112838745,
|
|
"epoch": 0.5294759825327511,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004979071896917595,
|
|
"loss": 5.522,
|
|
"mean_token_accuracy": 0.1516739696264267,
|
|
"num_tokens": 11732309.0,
|
|
"step": 5335
|
|
},
|
|
{
|
|
"entropy": 5.720453691482544,
|
|
"epoch": 0.5299722111949187,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004979023656083586,
|
|
"loss": 5.5843,
|
|
"mean_token_accuracy": 0.14252596721053123,
|
|
"num_tokens": 11743982.0,
|
|
"step": 5340
|
|
},
|
|
{
|
|
"entropy": 5.66952691078186,
|
|
"epoch": 0.5304684398570861,
|
|
"grad_norm": 0.79296875,
|
|
"learning_rate": 0.0004978975359974594,
|
|
"loss": 5.5189,
|
|
"mean_token_accuracy": 0.14486275911331176,
|
|
"num_tokens": 11755506.0,
|
|
"step": 5345
|
|
},
|
|
{
|
|
"entropy": 5.751617050170898,
|
|
"epoch": 0.5309646685192537,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004978927008591816,
|
|
"loss": 5.5216,
|
|
"mean_token_accuracy": 0.14368319660425186,
|
|
"num_tokens": 11767024.0,
|
|
"step": 5350
|
|
},
|
|
{
|
|
"entropy": 5.774104166030884,
|
|
"epoch": 0.5314608971814212,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004978878601936451,
|
|
"loss": 5.5214,
|
|
"mean_token_accuracy": 0.14008311927318573,
|
|
"num_tokens": 11777625.0,
|
|
"step": 5355
|
|
},
|
|
{
|
|
"entropy": 5.676749420166016,
|
|
"epoch": 0.5319571258435887,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004978830140009698,
|
|
"loss": 5.4998,
|
|
"mean_token_accuracy": 0.15135693401098252,
|
|
"num_tokens": 11788610.0,
|
|
"step": 5360
|
|
},
|
|
{
|
|
"entropy": 5.6927237033844,
|
|
"epoch": 0.5324533545057563,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004978781622812762,
|
|
"loss": 5.5998,
|
|
"mean_token_accuracy": 0.14594103246927262,
|
|
"num_tokens": 11800828.0,
|
|
"step": 5365
|
|
},
|
|
{
|
|
"entropy": 5.745589065551758,
|
|
"epoch": 0.5329495831679237,
|
|
"grad_norm": 0.78515625,
|
|
"learning_rate": 0.0004978733050346844,
|
|
"loss": 5.598,
|
|
"mean_token_accuracy": 0.14758748263120652,
|
|
"num_tokens": 11811729.0,
|
|
"step": 5370
|
|
},
|
|
{
|
|
"entropy": 5.737847137451172,
|
|
"epoch": 0.5334458118300913,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004978684422613149,
|
|
"loss": 5.6203,
|
|
"mean_token_accuracy": 0.14279971048235893,
|
|
"num_tokens": 11822081.0,
|
|
"step": 5375
|
|
},
|
|
{
|
|
"entropy": 5.704253196716309,
|
|
"epoch": 0.5339420404922588,
|
|
"grad_norm": 0.79296875,
|
|
"learning_rate": 0.0004978635739612882,
|
|
"loss": 5.4959,
|
|
"mean_token_accuracy": 0.1478683464229107,
|
|
"num_tokens": 11832984.0,
|
|
"step": 5380
|
|
},
|
|
{
|
|
"entropy": 5.69680380821228,
|
|
"epoch": 0.5344382691544264,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004978587001347252,
|
|
"loss": 5.4676,
|
|
"mean_token_accuracy": 0.1478103816509247,
|
|
"num_tokens": 11842918.0,
|
|
"step": 5385
|
|
},
|
|
{
|
|
"entropy": 5.63281888961792,
|
|
"epoch": 0.5349344978165939,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004978538207817465,
|
|
"loss": 5.501,
|
|
"mean_token_accuracy": 0.1504437059164047,
|
|
"num_tokens": 11854364.0,
|
|
"step": 5390
|
|
},
|
|
{
|
|
"entropy": 5.684811115264893,
|
|
"epoch": 0.5354307264787614,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004978489359024734,
|
|
"loss": 5.5732,
|
|
"mean_token_accuracy": 0.1437056079506874,
|
|
"num_tokens": 11866400.0,
|
|
"step": 5395
|
|
},
|
|
{
|
|
"entropy": 5.774307823181152,
|
|
"epoch": 0.5359269551409289,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004978440454970268,
|
|
"loss": 5.5738,
|
|
"mean_token_accuracy": 0.14117259830236434,
|
|
"num_tokens": 11877094.0,
|
|
"step": 5400
|
|
},
|
|
{
|
|
"entropy": 5.687881755828857,
|
|
"epoch": 0.5364231838030965,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004978391495655281,
|
|
"loss": 5.5245,
|
|
"mean_token_accuracy": 0.14514778330922126,
|
|
"num_tokens": 11887289.0,
|
|
"step": 5405
|
|
},
|
|
{
|
|
"entropy": 5.739621353149414,
|
|
"epoch": 0.536919412465264,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004978342481080987,
|
|
"loss": 5.5079,
|
|
"mean_token_accuracy": 0.14592916518449783,
|
|
"num_tokens": 11897700.0,
|
|
"step": 5410
|
|
},
|
|
{
|
|
"entropy": 5.5940704345703125,
|
|
"epoch": 0.5374156411274316,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004978293411248601,
|
|
"loss": 5.4367,
|
|
"mean_token_accuracy": 0.15131850391626359,
|
|
"num_tokens": 11908623.0,
|
|
"step": 5415
|
|
},
|
|
{
|
|
"entropy": 5.679359340667725,
|
|
"epoch": 0.537911869789599,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004978244286159339,
|
|
"loss": 5.4525,
|
|
"mean_token_accuracy": 0.15489538311958312,
|
|
"num_tokens": 11917883.0,
|
|
"step": 5420
|
|
},
|
|
{
|
|
"entropy": 5.658584928512573,
|
|
"epoch": 0.5384080984517666,
|
|
"grad_norm": 0.71875,
|
|
"learning_rate": 0.0004978195105814421,
|
|
"loss": 5.4932,
|
|
"mean_token_accuracy": 0.1469782829284668,
|
|
"num_tokens": 11929145.0,
|
|
"step": 5425
|
|
},
|
|
{
|
|
"entropy": 5.692590570449829,
|
|
"epoch": 0.5389043271139341,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.0004978145870215065,
|
|
"loss": 5.4835,
|
|
"mean_token_accuracy": 0.1445659376680851,
|
|
"num_tokens": 11940073.0,
|
|
"step": 5430
|
|
},
|
|
{
|
|
"entropy": 5.716174697875976,
|
|
"epoch": 0.5394005557761016,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004978096579362493,
|
|
"loss": 5.6122,
|
|
"mean_token_accuracy": 0.14428975731134414,
|
|
"num_tokens": 11953140.0,
|
|
"step": 5435
|
|
},
|
|
{
|
|
"entropy": 5.725712585449219,
|
|
"epoch": 0.5398967844382692,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004978047233257927,
|
|
"loss": 5.5355,
|
|
"mean_token_accuracy": 0.1476729243993759,
|
|
"num_tokens": 11963853.0,
|
|
"step": 5440
|
|
},
|
|
{
|
|
"entropy": 5.696603202819825,
|
|
"epoch": 0.5403930131004366,
|
|
"grad_norm": 0.7734375,
|
|
"learning_rate": 0.0004977997831902591,
|
|
"loss": 5.4953,
|
|
"mean_token_accuracy": 0.14950083196163177,
|
|
"num_tokens": 11975469.0,
|
|
"step": 5445
|
|
},
|
|
{
|
|
"entropy": 5.667461633682251,
|
|
"epoch": 0.5408892417626042,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004977948375297709,
|
|
"loss": 5.4805,
|
|
"mean_token_accuracy": 0.1535550147294998,
|
|
"num_tokens": 11985227.0,
|
|
"step": 5450
|
|
},
|
|
{
|
|
"entropy": 5.554087400436401,
|
|
"epoch": 0.5413854704247717,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004977898863444509,
|
|
"loss": 5.4905,
|
|
"mean_token_accuracy": 0.1473379760980606,
|
|
"num_tokens": 11995459.0,
|
|
"step": 5455
|
|
},
|
|
{
|
|
"entropy": 5.694110012054443,
|
|
"epoch": 0.5418816990869393,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004977849296344217,
|
|
"loss": 5.5509,
|
|
"mean_token_accuracy": 0.14240046888589858,
|
|
"num_tokens": 12007705.0,
|
|
"step": 5460
|
|
},
|
|
{
|
|
"entropy": 5.6833288192749025,
|
|
"epoch": 0.5423779277491068,
|
|
"grad_norm": 0.78125,
|
|
"learning_rate": 0.0004977799673998063,
|
|
"loss": 5.4428,
|
|
"mean_token_accuracy": 0.14829470664262773,
|
|
"num_tokens": 12019729.0,
|
|
"step": 5465
|
|
},
|
|
{
|
|
"entropy": 5.694163846969604,
|
|
"epoch": 0.5428741564112743,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004977749996407278,
|
|
"loss": 5.5204,
|
|
"mean_token_accuracy": 0.14065904766321183,
|
|
"num_tokens": 12031009.0,
|
|
"step": 5470
|
|
},
|
|
{
|
|
"entropy": 5.71015944480896,
|
|
"epoch": 0.5433703850734418,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004977700263573094,
|
|
"loss": 5.4757,
|
|
"mean_token_accuracy": 0.149942646920681,
|
|
"num_tokens": 12041396.0,
|
|
"step": 5475
|
|
},
|
|
{
|
|
"entropy": 5.714011335372925,
|
|
"epoch": 0.5438666137356094,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.0004977650475496743,
|
|
"loss": 5.6327,
|
|
"mean_token_accuracy": 0.13937563449144363,
|
|
"num_tokens": 12053112.0,
|
|
"step": 5480
|
|
},
|
|
{
|
|
"entropy": 5.701058769226075,
|
|
"epoch": 0.5443628423977769,
|
|
"grad_norm": 0.76953125,
|
|
"learning_rate": 0.0004977600632179459,
|
|
"loss": 5.4853,
|
|
"mean_token_accuracy": 0.1432749643921852,
|
|
"num_tokens": 12064823.0,
|
|
"step": 5485
|
|
},
|
|
{
|
|
"entropy": 5.741170930862427,
|
|
"epoch": 0.5448590710599445,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004977550733622482,
|
|
"loss": 5.611,
|
|
"mean_token_accuracy": 0.1431275188922882,
|
|
"num_tokens": 12076656.0,
|
|
"step": 5490
|
|
},
|
|
{
|
|
"entropy": 5.702113914489746,
|
|
"epoch": 0.5453552997221119,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004977500779827045,
|
|
"loss": 5.417,
|
|
"mean_token_accuracy": 0.14641434401273729,
|
|
"num_tokens": 12086324.0,
|
|
"step": 5495
|
|
},
|
|
{
|
|
"entropy": 5.584799289703369,
|
|
"epoch": 0.5458515283842795,
|
|
"grad_norm": 0.78125,
|
|
"learning_rate": 0.0004977450770794389,
|
|
"loss": 5.4573,
|
|
"mean_token_accuracy": 0.14669612646102906,
|
|
"num_tokens": 12098076.0,
|
|
"step": 5500
|
|
},
|
|
{
|
|
"entropy": 5.658282661437989,
|
|
"epoch": 0.546347757046447,
|
|
"grad_norm": 0.734375,
|
|
"learning_rate": 0.0004977400706525755,
|
|
"loss": 5.5176,
|
|
"mean_token_accuracy": 0.14338865503668785,
|
|
"num_tokens": 12111282.0,
|
|
"step": 5505
|
|
},
|
|
{
|
|
"entropy": 5.67042498588562,
|
|
"epoch": 0.5468439857086145,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004977350587022381,
|
|
"loss": 5.4646,
|
|
"mean_token_accuracy": 0.15267725735902787,
|
|
"num_tokens": 12121932.0,
|
|
"step": 5510
|
|
},
|
|
{
|
|
"entropy": 5.663971471786499,
|
|
"epoch": 0.5473402143707821,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004977300412285513,
|
|
"loss": 5.4506,
|
|
"mean_token_accuracy": 0.1547014519572258,
|
|
"num_tokens": 12133040.0,
|
|
"step": 5515
|
|
},
|
|
{
|
|
"entropy": 5.7008575916290285,
|
|
"epoch": 0.5478364430329495,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004977250182316394,
|
|
"loss": 5.5286,
|
|
"mean_token_accuracy": 0.14612772613763808,
|
|
"num_tokens": 12142577.0,
|
|
"step": 5520
|
|
},
|
|
{
|
|
"entropy": 5.695830965042115,
|
|
"epoch": 0.5483326716951171,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.000497719989711627,
|
|
"loss": 5.4969,
|
|
"mean_token_accuracy": 0.1528421387076378,
|
|
"num_tokens": 12153941.0,
|
|
"step": 5525
|
|
},
|
|
{
|
|
"entropy": 5.6863785743713375,
|
|
"epoch": 0.5488289003572846,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004977149556686387,
|
|
"loss": 5.5501,
|
|
"mean_token_accuracy": 0.14650570154190062,
|
|
"num_tokens": 12165347.0,
|
|
"step": 5530
|
|
},
|
|
{
|
|
"entropy": 5.599493026733398,
|
|
"epoch": 0.5493251290194522,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004977099161027996,
|
|
"loss": 5.4374,
|
|
"mean_token_accuracy": 0.14999375939369203,
|
|
"num_tokens": 12175705.0,
|
|
"step": 5535
|
|
},
|
|
{
|
|
"entropy": 5.706617259979248,
|
|
"epoch": 0.5498213576816197,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004977048710142342,
|
|
"loss": 5.4914,
|
|
"mean_token_accuracy": 0.1500910520553589,
|
|
"num_tokens": 12186781.0,
|
|
"step": 5540
|
|
},
|
|
{
|
|
"entropy": 5.7512706279754635,
|
|
"epoch": 0.5503175863437872,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004976998204030681,
|
|
"loss": 5.5249,
|
|
"mean_token_accuracy": 0.14498836621642114,
|
|
"num_tokens": 12197145.0,
|
|
"step": 5545
|
|
},
|
|
{
|
|
"entropy": 5.624058055877685,
|
|
"epoch": 0.5508138150059547,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004976947642694262,
|
|
"loss": 5.5192,
|
|
"mean_token_accuracy": 0.15011530891060829,
|
|
"num_tokens": 12207637.0,
|
|
"step": 5550
|
|
},
|
|
{
|
|
"entropy": 5.618358469009399,
|
|
"epoch": 0.5513100436681223,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004976897026134341,
|
|
"loss": 5.4405,
|
|
"mean_token_accuracy": 0.15141630321741104,
|
|
"num_tokens": 12218156.0,
|
|
"step": 5555
|
|
},
|
|
{
|
|
"entropy": 5.689433479309082,
|
|
"epoch": 0.5518062723302898,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004976846354352172,
|
|
"loss": 5.528,
|
|
"mean_token_accuracy": 0.1447851613163948,
|
|
"num_tokens": 12229987.0,
|
|
"step": 5560
|
|
},
|
|
{
|
|
"entropy": 5.69376802444458,
|
|
"epoch": 0.5523025009924574,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004976795627349012,
|
|
"loss": 5.5116,
|
|
"mean_token_accuracy": 0.1453092396259308,
|
|
"num_tokens": 12240508.0,
|
|
"step": 5565
|
|
},
|
|
{
|
|
"entropy": 5.652896738052368,
|
|
"epoch": 0.5527987296546248,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004976744845126118,
|
|
"loss": 5.4503,
|
|
"mean_token_accuracy": 0.1521064132452011,
|
|
"num_tokens": 12250317.0,
|
|
"step": 5570
|
|
},
|
|
{
|
|
"entropy": 5.620663976669311,
|
|
"epoch": 0.5532949583167924,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004976694007684751,
|
|
"loss": 5.4953,
|
|
"mean_token_accuracy": 0.1509055018424988,
|
|
"num_tokens": 12262104.0,
|
|
"step": 5575
|
|
},
|
|
{
|
|
"entropy": 5.74803204536438,
|
|
"epoch": 0.5537911869789599,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.000497664311502617,
|
|
"loss": 5.5393,
|
|
"mean_token_accuracy": 0.1466676525771618,
|
|
"num_tokens": 12273259.0,
|
|
"step": 5580
|
|
},
|
|
{
|
|
"entropy": 5.736172199249268,
|
|
"epoch": 0.5542874156411274,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004976592167151638,
|
|
"loss": 5.5704,
|
|
"mean_token_accuracy": 0.13990923017263412,
|
|
"num_tokens": 12285504.0,
|
|
"step": 5585
|
|
},
|
|
{
|
|
"entropy": 5.692285537719727,
|
|
"epoch": 0.554783644303295,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004976541164062418,
|
|
"loss": 5.4988,
|
|
"mean_token_accuracy": 0.14217816665768623,
|
|
"num_tokens": 12296512.0,
|
|
"step": 5590
|
|
},
|
|
{
|
|
"entropy": 5.577828121185303,
|
|
"epoch": 0.5552798729654624,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004976490105759774,
|
|
"loss": 5.3666,
|
|
"mean_token_accuracy": 0.15274341851472856,
|
|
"num_tokens": 12307948.0,
|
|
"step": 5595
|
|
},
|
|
{
|
|
"entropy": 5.6738968849182125,
|
|
"epoch": 0.55577610162763,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004976438992244976,
|
|
"loss": 5.5376,
|
|
"mean_token_accuracy": 0.14299441426992415,
|
|
"num_tokens": 12320020.0,
|
|
"step": 5600
|
|
},
|
|
{
|
|
"entropy": 5.689694452285766,
|
|
"epoch": 0.5562723302897975,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004976387823519286,
|
|
"loss": 5.4035,
|
|
"mean_token_accuracy": 0.1494772896170616,
|
|
"num_tokens": 12331091.0,
|
|
"step": 5605
|
|
},
|
|
{
|
|
"entropy": 5.6960502624511715,
|
|
"epoch": 0.5567685589519651,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004976336599583975,
|
|
"loss": 5.5089,
|
|
"mean_token_accuracy": 0.14410399943590163,
|
|
"num_tokens": 12342621.0,
|
|
"step": 5610
|
|
},
|
|
{
|
|
"entropy": 5.788615989685058,
|
|
"epoch": 0.5572647876141326,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004976285320440315,
|
|
"loss": 5.7636,
|
|
"mean_token_accuracy": 0.13273412361741066,
|
|
"num_tokens": 12353330.0,
|
|
"step": 5615
|
|
},
|
|
{
|
|
"entropy": 5.751302766799927,
|
|
"epoch": 0.5577610162763001,
|
|
"grad_norm": 0.77734375,
|
|
"learning_rate": 0.0004976233986089577,
|
|
"loss": 5.4999,
|
|
"mean_token_accuracy": 0.14577182084321977,
|
|
"num_tokens": 12364418.0,
|
|
"step": 5620
|
|
},
|
|
{
|
|
"entropy": 5.610360383987427,
|
|
"epoch": 0.5582572449384676,
|
|
"grad_norm": 0.80078125,
|
|
"learning_rate": 0.0004976182596533031,
|
|
"loss": 5.4916,
|
|
"mean_token_accuracy": 0.1467949479818344,
|
|
"num_tokens": 12377022.0,
|
|
"step": 5625
|
|
},
|
|
{
|
|
"entropy": 5.739885330200195,
|
|
"epoch": 0.5587534736006352,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004976131151771955,
|
|
"loss": 5.548,
|
|
"mean_token_accuracy": 0.14481229856610298,
|
|
"num_tokens": 12387799.0,
|
|
"step": 5630
|
|
},
|
|
{
|
|
"entropy": 5.670582485198975,
|
|
"epoch": 0.5592497022628027,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004976079651807623,
|
|
"loss": 5.5007,
|
|
"mean_token_accuracy": 0.14010098576545715,
|
|
"num_tokens": 12397387.0,
|
|
"step": 5635
|
|
},
|
|
{
|
|
"entropy": 5.609793567657471,
|
|
"epoch": 0.5597459309249703,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004976028096641313,
|
|
"loss": 5.4277,
|
|
"mean_token_accuracy": 0.15353151261806489,
|
|
"num_tokens": 12407994.0,
|
|
"step": 5640
|
|
},
|
|
{
|
|
"entropy": 5.786797094345093,
|
|
"epoch": 0.5602421595871377,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004975976486274302,
|
|
"loss": 5.6054,
|
|
"mean_token_accuracy": 0.14164167046546935,
|
|
"num_tokens": 12419124.0,
|
|
"step": 5645
|
|
},
|
|
{
|
|
"entropy": 5.701025772094726,
|
|
"epoch": 0.5607383882493053,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004975924820707872,
|
|
"loss": 5.4893,
|
|
"mean_token_accuracy": 0.14726104438304902,
|
|
"num_tokens": 12428699.0,
|
|
"step": 5650
|
|
},
|
|
{
|
|
"entropy": 5.689584064483642,
|
|
"epoch": 0.5612346169114728,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004975873099943302,
|
|
"loss": 5.57,
|
|
"mean_token_accuracy": 0.14373983442783356,
|
|
"num_tokens": 12439025.0,
|
|
"step": 5655
|
|
},
|
|
{
|
|
"entropy": 5.737751007080078,
|
|
"epoch": 0.5617308455736403,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.0004975821323981875,
|
|
"loss": 5.5221,
|
|
"mean_token_accuracy": 0.14871042519807814,
|
|
"num_tokens": 12449439.0,
|
|
"step": 5660
|
|
},
|
|
{
|
|
"entropy": 5.723925542831421,
|
|
"epoch": 0.5622270742358079,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004975769492824877,
|
|
"loss": 5.4628,
|
|
"mean_token_accuracy": 0.14492267221212388,
|
|
"num_tokens": 12460066.0,
|
|
"step": 5665
|
|
},
|
|
{
|
|
"entropy": 5.664363098144531,
|
|
"epoch": 0.5627233028979753,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004975717606473589,
|
|
"loss": 5.4883,
|
|
"mean_token_accuracy": 0.15085864216089248,
|
|
"num_tokens": 12471093.0,
|
|
"step": 5670
|
|
},
|
|
{
|
|
"entropy": 5.739382266998291,
|
|
"epoch": 0.5632195315601429,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004975665664929302,
|
|
"loss": 5.513,
|
|
"mean_token_accuracy": 0.14348138272762298,
|
|
"num_tokens": 12481181.0,
|
|
"step": 5675
|
|
},
|
|
{
|
|
"entropy": 5.70921950340271,
|
|
"epoch": 0.5637157602223104,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004975613668193303,
|
|
"loss": 5.528,
|
|
"mean_token_accuracy": 0.14321721345186234,
|
|
"num_tokens": 12493068.0,
|
|
"step": 5680
|
|
},
|
|
{
|
|
"entropy": 5.631594800949097,
|
|
"epoch": 0.564211988884478,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.000497556161626688,
|
|
"loss": 5.4839,
|
|
"mean_token_accuracy": 0.1489529438316822,
|
|
"num_tokens": 12504025.0,
|
|
"step": 5685
|
|
},
|
|
{
|
|
"entropy": 5.679368209838867,
|
|
"epoch": 0.5647082175466455,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004975509509151325,
|
|
"loss": 5.4858,
|
|
"mean_token_accuracy": 0.1454532712697983,
|
|
"num_tokens": 12514567.0,
|
|
"step": 5690
|
|
},
|
|
{
|
|
"entropy": 5.785870027542114,
|
|
"epoch": 0.565204446208813,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004975457346847929,
|
|
"loss": 5.5249,
|
|
"mean_token_accuracy": 0.1441642612218857,
|
|
"num_tokens": 12525088.0,
|
|
"step": 5695
|
|
},
|
|
{
|
|
"entropy": 5.677102327346802,
|
|
"epoch": 0.5657006748709805,
|
|
"grad_norm": 0.79296875,
|
|
"learning_rate": 0.0004975405129357986,
|
|
"loss": 5.4866,
|
|
"mean_token_accuracy": 0.14762923568487168,
|
|
"num_tokens": 12536002.0,
|
|
"step": 5700
|
|
},
|
|
{
|
|
"entropy": 5.676094245910645,
|
|
"epoch": 0.5661969035331481,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004975352856682792,
|
|
"loss": 5.4974,
|
|
"mean_token_accuracy": 0.15148521959781647,
|
|
"num_tokens": 12547468.0,
|
|
"step": 5705
|
|
},
|
|
{
|
|
"entropy": 5.715325212478637,
|
|
"epoch": 0.5666931321953156,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004975300528823642,
|
|
"loss": 5.4656,
|
|
"mean_token_accuracy": 0.1467609941959381,
|
|
"num_tokens": 12557670.0,
|
|
"step": 5710
|
|
},
|
|
{
|
|
"entropy": 5.710341072082519,
|
|
"epoch": 0.5671893608574832,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004975248145781834,
|
|
"loss": 5.5278,
|
|
"mean_token_accuracy": 0.1446359783411026,
|
|
"num_tokens": 12568425.0,
|
|
"step": 5715
|
|
},
|
|
{
|
|
"entropy": 5.608817863464355,
|
|
"epoch": 0.5676855895196506,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004975195707558667,
|
|
"loss": 5.4998,
|
|
"mean_token_accuracy": 0.14632719457149507,
|
|
"num_tokens": 12579138.0,
|
|
"step": 5720
|
|
},
|
|
{
|
|
"entropy": 5.64209623336792,
|
|
"epoch": 0.5681818181818182,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004975143214155443,
|
|
"loss": 5.4958,
|
|
"mean_token_accuracy": 0.14967800229787825,
|
|
"num_tokens": 12589743.0,
|
|
"step": 5725
|
|
},
|
|
{
|
|
"entropy": 5.688083267211914,
|
|
"epoch": 0.5686780468439857,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004975090665573459,
|
|
"loss": 5.4851,
|
|
"mean_token_accuracy": 0.152118718624115,
|
|
"num_tokens": 12600648.0,
|
|
"step": 5730
|
|
},
|
|
{
|
|
"entropy": 5.645006799697876,
|
|
"epoch": 0.5691742755061532,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004975038061814023,
|
|
"loss": 5.5031,
|
|
"mean_token_accuracy": 0.14906034767627716,
|
|
"num_tokens": 12611369.0,
|
|
"step": 5735
|
|
},
|
|
{
|
|
"entropy": 5.7086090564727785,
|
|
"epoch": 0.5696705041683208,
|
|
"grad_norm": 0.78515625,
|
|
"learning_rate": 0.0004974985402878437,
|
|
"loss": 5.4672,
|
|
"mean_token_accuracy": 0.1463977113366127,
|
|
"num_tokens": 12621992.0,
|
|
"step": 5740
|
|
},
|
|
{
|
|
"entropy": 5.697903108596802,
|
|
"epoch": 0.5701667328304882,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004974932688768007,
|
|
"loss": 5.5454,
|
|
"mean_token_accuracy": 0.14656417667865754,
|
|
"num_tokens": 12632463.0,
|
|
"step": 5745
|
|
},
|
|
{
|
|
"entropy": 5.6192210674285885,
|
|
"epoch": 0.5706629614926558,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004974879919484042,
|
|
"loss": 5.4058,
|
|
"mean_token_accuracy": 0.15206122696399688,
|
|
"num_tokens": 12642282.0,
|
|
"step": 5750
|
|
},
|
|
{
|
|
"entropy": 5.636960077285766,
|
|
"epoch": 0.5711591901548233,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004974827095027848,
|
|
"loss": 5.4346,
|
|
"mean_token_accuracy": 0.15423172563314438,
|
|
"num_tokens": 12653495.0,
|
|
"step": 5755
|
|
},
|
|
{
|
|
"entropy": 5.664530849456787,
|
|
"epoch": 0.5716554188169909,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0004974774215400736,
|
|
"loss": 5.3785,
|
|
"mean_token_accuracy": 0.15366745442152024,
|
|
"num_tokens": 12664322.0,
|
|
"step": 5760
|
|
},
|
|
{
|
|
"entropy": 5.542517852783203,
|
|
"epoch": 0.5721516474791584,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004974721280604019,
|
|
"loss": 5.4768,
|
|
"mean_token_accuracy": 0.14642566740512847,
|
|
"num_tokens": 12673981.0,
|
|
"step": 5765
|
|
},
|
|
{
|
|
"entropy": 5.599040508270264,
|
|
"epoch": 0.572647876141326,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004974668290639007,
|
|
"loss": 5.4781,
|
|
"mean_token_accuracy": 0.14832795709371566,
|
|
"num_tokens": 12684778.0,
|
|
"step": 5770
|
|
},
|
|
{
|
|
"entropy": 5.705513000488281,
|
|
"epoch": 0.5731441048034934,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004974615245507014,
|
|
"loss": 5.4421,
|
|
"mean_token_accuracy": 0.14995291382074355,
|
|
"num_tokens": 12695287.0,
|
|
"step": 5775
|
|
},
|
|
{
|
|
"entropy": 5.598648929595948,
|
|
"epoch": 0.573640333465661,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004974562145209359,
|
|
"loss": 5.5041,
|
|
"mean_token_accuracy": 0.14448004961013794,
|
|
"num_tokens": 12705773.0,
|
|
"step": 5780
|
|
},
|
|
{
|
|
"entropy": 5.6014838218688965,
|
|
"epoch": 0.5741365621278285,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004974508989747354,
|
|
"loss": 5.4276,
|
|
"mean_token_accuracy": 0.15292005538940429,
|
|
"num_tokens": 12716783.0,
|
|
"step": 5785
|
|
},
|
|
{
|
|
"entropy": 5.6707727909088135,
|
|
"epoch": 0.5746327907899961,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004974455779122321,
|
|
"loss": 5.4976,
|
|
"mean_token_accuracy": 0.14310954585671426,
|
|
"num_tokens": 12728146.0,
|
|
"step": 5790
|
|
},
|
|
{
|
|
"entropy": 5.705024862289429,
|
|
"epoch": 0.5751290194521635,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004974402513335577,
|
|
"loss": 5.5146,
|
|
"mean_token_accuracy": 0.14299591705203057,
|
|
"num_tokens": 12739683.0,
|
|
"step": 5795
|
|
},
|
|
{
|
|
"entropy": 5.713213539123535,
|
|
"epoch": 0.5756252481143311,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004974349192388444,
|
|
"loss": 5.4891,
|
|
"mean_token_accuracy": 0.14356330558657646,
|
|
"num_tokens": 12750257.0,
|
|
"step": 5800
|
|
},
|
|
{
|
|
"entropy": 5.72646746635437,
|
|
"epoch": 0.5761214767764986,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0004974295816282245,
|
|
"loss": 5.5675,
|
|
"mean_token_accuracy": 0.14630476087331773,
|
|
"num_tokens": 12761055.0,
|
|
"step": 5805
|
|
},
|
|
{
|
|
"entropy": 5.67992148399353,
|
|
"epoch": 0.5766177054386661,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004974242385018303,
|
|
"loss": 5.5052,
|
|
"mean_token_accuracy": 0.14898856729269028,
|
|
"num_tokens": 12771014.0,
|
|
"step": 5810
|
|
},
|
|
{
|
|
"entropy": 5.635032606124878,
|
|
"epoch": 0.5771139341008337,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.000497418889859794,
|
|
"loss": 5.424,
|
|
"mean_token_accuracy": 0.15025612711906433,
|
|
"num_tokens": 12782623.0,
|
|
"step": 5815
|
|
},
|
|
{
|
|
"entropy": 5.713941335678101,
|
|
"epoch": 0.5776101627630011,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004974135357022488,
|
|
"loss": 5.543,
|
|
"mean_token_accuracy": 0.14384849816560746,
|
|
"num_tokens": 12793533.0,
|
|
"step": 5820
|
|
},
|
|
{
|
|
"entropy": 5.593503761291504,
|
|
"epoch": 0.5781063914251687,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004974081760293269,
|
|
"loss": 5.4105,
|
|
"mean_token_accuracy": 0.14829638749361038,
|
|
"num_tokens": 12804389.0,
|
|
"step": 5825
|
|
},
|
|
{
|
|
"entropy": 5.666346645355224,
|
|
"epoch": 0.5786026200873362,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.0004974028108411617,
|
|
"loss": 5.512,
|
|
"mean_token_accuracy": 0.15230901390314103,
|
|
"num_tokens": 12815672.0,
|
|
"step": 5830
|
|
},
|
|
{
|
|
"entropy": 5.732553863525391,
|
|
"epoch": 0.5790988487495038,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004973974401378859,
|
|
"loss": 5.5116,
|
|
"mean_token_accuracy": 0.15112632364034653,
|
|
"num_tokens": 12826113.0,
|
|
"step": 5835
|
|
},
|
|
{
|
|
"entropy": 5.612425994873047,
|
|
"epoch": 0.5795950774116713,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004973920639196329,
|
|
"loss": 5.4408,
|
|
"mean_token_accuracy": 0.1494893580675125,
|
|
"num_tokens": 12835941.0,
|
|
"step": 5840
|
|
},
|
|
{
|
|
"entropy": 5.639367532730103,
|
|
"epoch": 0.5800913060738389,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004973866821865358,
|
|
"loss": 5.5282,
|
|
"mean_token_accuracy": 0.14228470176458358,
|
|
"num_tokens": 12846186.0,
|
|
"step": 5845
|
|
},
|
|
{
|
|
"entropy": 5.718220901489258,
|
|
"epoch": 0.5805875347360063,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004973812949387283,
|
|
"loss": 5.4929,
|
|
"mean_token_accuracy": 0.14542728066444396,
|
|
"num_tokens": 12856380.0,
|
|
"step": 5850
|
|
},
|
|
{
|
|
"entropy": 5.649071073532104,
|
|
"epoch": 0.5810837633981739,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004973759021763439,
|
|
"loss": 5.5286,
|
|
"mean_token_accuracy": 0.14764680862426757,
|
|
"num_tokens": 12865999.0,
|
|
"step": 5855
|
|
},
|
|
{
|
|
"entropy": 5.68231954574585,
|
|
"epoch": 0.5815799920603414,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004973705038995162,
|
|
"loss": 5.4126,
|
|
"mean_token_accuracy": 0.14954375773668288,
|
|
"num_tokens": 12876388.0,
|
|
"step": 5860
|
|
},
|
|
{
|
|
"entropy": 5.625105524063111,
|
|
"epoch": 0.582076220722509,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004973651001083792,
|
|
"loss": 5.4145,
|
|
"mean_token_accuracy": 0.14912877306342126,
|
|
"num_tokens": 12885862.0,
|
|
"step": 5865
|
|
},
|
|
{
|
|
"entropy": 5.605915117263794,
|
|
"epoch": 0.5825724493846764,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004973596908030669,
|
|
"loss": 5.5022,
|
|
"mean_token_accuracy": 0.1445961207151413,
|
|
"num_tokens": 12897489.0,
|
|
"step": 5870
|
|
},
|
|
{
|
|
"entropy": 5.703808736801148,
|
|
"epoch": 0.583068678046844,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004973542759837135,
|
|
"loss": 5.5464,
|
|
"mean_token_accuracy": 0.14082904383540154,
|
|
"num_tokens": 12907395.0,
|
|
"step": 5875
|
|
},
|
|
{
|
|
"entropy": 5.62304458618164,
|
|
"epoch": 0.5835649067090115,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.000497348855650453,
|
|
"loss": 5.4717,
|
|
"mean_token_accuracy": 0.1517767146229744,
|
|
"num_tokens": 12919439.0,
|
|
"step": 5880
|
|
},
|
|
{
|
|
"entropy": 5.69926609992981,
|
|
"epoch": 0.584061135371179,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004973434298034201,
|
|
"loss": 5.5616,
|
|
"mean_token_accuracy": 0.14480644688010216,
|
|
"num_tokens": 12931892.0,
|
|
"step": 5885
|
|
},
|
|
{
|
|
"entropy": 5.770834016799927,
|
|
"epoch": 0.5845573640333466,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004973379984427492,
|
|
"loss": 5.603,
|
|
"mean_token_accuracy": 0.14584836214780808,
|
|
"num_tokens": 12943189.0,
|
|
"step": 5890
|
|
},
|
|
{
|
|
"entropy": 5.670014476776123,
|
|
"epoch": 0.585053592695514,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.000497332561568575,
|
|
"loss": 5.5406,
|
|
"mean_token_accuracy": 0.14588731974363328,
|
|
"num_tokens": 12954662.0,
|
|
"step": 5895
|
|
},
|
|
{
|
|
"entropy": 5.63857250213623,
|
|
"epoch": 0.5855498213576816,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004973271191810325,
|
|
"loss": 5.4833,
|
|
"mean_token_accuracy": 0.14281948506832123,
|
|
"num_tokens": 12964924.0,
|
|
"step": 5900
|
|
},
|
|
{
|
|
"entropy": 5.689583873748779,
|
|
"epoch": 0.5860460500198491,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004973216712802564,
|
|
"loss": 5.5549,
|
|
"mean_token_accuracy": 0.14132398664951323,
|
|
"num_tokens": 12976483.0,
|
|
"step": 5905
|
|
},
|
|
{
|
|
"entropy": 5.654120254516601,
|
|
"epoch": 0.5865422786820167,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.000497316217866382,
|
|
"loss": 5.4601,
|
|
"mean_token_accuracy": 0.15196489095687865,
|
|
"num_tokens": 12988054.0,
|
|
"step": 5910
|
|
},
|
|
{
|
|
"entropy": 5.69523344039917,
|
|
"epoch": 0.5870385073441842,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004973107589395444,
|
|
"loss": 5.5062,
|
|
"mean_token_accuracy": 0.1495279923081398,
|
|
"num_tokens": 13000596.0,
|
|
"step": 5915
|
|
},
|
|
{
|
|
"entropy": 5.558714103698731,
|
|
"epoch": 0.5875347360063518,
|
|
"grad_norm": 0.80078125,
|
|
"learning_rate": 0.0004973052944998791,
|
|
"loss": 5.3601,
|
|
"mean_token_accuracy": 0.15159481316804885,
|
|
"num_tokens": 13012360.0,
|
|
"step": 5920
|
|
},
|
|
{
|
|
"entropy": 5.637037706375122,
|
|
"epoch": 0.5880309646685192,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004972998245475214,
|
|
"loss": 5.5061,
|
|
"mean_token_accuracy": 0.14521099850535393,
|
|
"num_tokens": 13023806.0,
|
|
"step": 5925
|
|
},
|
|
{
|
|
"entropy": 5.674616146087646,
|
|
"epoch": 0.5885271933306868,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.000497294349082607,
|
|
"loss": 5.4444,
|
|
"mean_token_accuracy": 0.14743458330631257,
|
|
"num_tokens": 13034049.0,
|
|
"step": 5930
|
|
},
|
|
{
|
|
"entropy": 5.698005294799804,
|
|
"epoch": 0.5890234219928543,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004972888681052719,
|
|
"loss": 5.5418,
|
|
"mean_token_accuracy": 0.14588503241539003,
|
|
"num_tokens": 13045006.0,
|
|
"step": 5935
|
|
},
|
|
{
|
|
"entropy": 5.713470411300659,
|
|
"epoch": 0.5895196506550219,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004972833816156518,
|
|
"loss": 5.454,
|
|
"mean_token_accuracy": 0.151131209731102,
|
|
"num_tokens": 13055337.0,
|
|
"step": 5940
|
|
},
|
|
{
|
|
"entropy": 5.613440036773682,
|
|
"epoch": 0.5900158793171894,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004972778896138828,
|
|
"loss": 5.4414,
|
|
"mean_token_accuracy": 0.151805180311203,
|
|
"num_tokens": 13065267.0,
|
|
"step": 5945
|
|
},
|
|
{
|
|
"entropy": 5.648981380462646,
|
|
"epoch": 0.5905121079793569,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004972723921001011,
|
|
"loss": 5.5115,
|
|
"mean_token_accuracy": 0.14798768609762192,
|
|
"num_tokens": 13075173.0,
|
|
"step": 5950
|
|
},
|
|
{
|
|
"entropy": 5.707030391693115,
|
|
"epoch": 0.5910083366415244,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004972668890744431,
|
|
"loss": 5.4911,
|
|
"mean_token_accuracy": 0.14562270641326905,
|
|
"num_tokens": 13086848.0,
|
|
"step": 5955
|
|
},
|
|
{
|
|
"entropy": 5.640896415710449,
|
|
"epoch": 0.5915045653036919,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004972613805370452,
|
|
"loss": 5.4768,
|
|
"mean_token_accuracy": 0.1498607374727726,
|
|
"num_tokens": 13096865.0,
|
|
"step": 5960
|
|
},
|
|
{
|
|
"entropy": 5.612109804153443,
|
|
"epoch": 0.5920007939658595,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004972558664880439,
|
|
"loss": 5.4543,
|
|
"mean_token_accuracy": 0.14806280583143233,
|
|
"num_tokens": 13107907.0,
|
|
"step": 5965
|
|
},
|
|
{
|
|
"entropy": 5.591845846176147,
|
|
"epoch": 0.592497022628027,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000497250346927576,
|
|
"loss": 5.373,
|
|
"mean_token_accuracy": 0.15522033870220184,
|
|
"num_tokens": 13118171.0,
|
|
"step": 5970
|
|
},
|
|
{
|
|
"entropy": 5.639474821090698,
|
|
"epoch": 0.5929932512901945,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004972448218557785,
|
|
"loss": 5.3608,
|
|
"mean_token_accuracy": 0.15381580740213394,
|
|
"num_tokens": 13127042.0,
|
|
"step": 5975
|
|
},
|
|
{
|
|
"entropy": 5.682769632339477,
|
|
"epoch": 0.593489479952362,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004972392912727882,
|
|
"loss": 5.6267,
|
|
"mean_token_accuracy": 0.1483294628560543,
|
|
"num_tokens": 13137026.0,
|
|
"step": 5980
|
|
},
|
|
{
|
|
"entropy": 5.6737512111663815,
|
|
"epoch": 0.5939857086145296,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004972337551787425,
|
|
"loss": 5.4745,
|
|
"mean_token_accuracy": 0.15264537185430527,
|
|
"num_tokens": 13146947.0,
|
|
"step": 5985
|
|
},
|
|
{
|
|
"entropy": 5.762002801895141,
|
|
"epoch": 0.5944819372766971,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004972282135737785,
|
|
"loss": 5.528,
|
|
"mean_token_accuracy": 0.14844981729984283,
|
|
"num_tokens": 13158714.0,
|
|
"step": 5990
|
|
},
|
|
{
|
|
"entropy": 5.709932327270508,
|
|
"epoch": 0.5949781659388647,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004972226664580337,
|
|
"loss": 5.5318,
|
|
"mean_token_accuracy": 0.14496293887495995,
|
|
"num_tokens": 13170156.0,
|
|
"step": 5995
|
|
},
|
|
{
|
|
"entropy": 5.593976449966431,
|
|
"epoch": 0.5954743946010321,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004972171138316456,
|
|
"loss": 5.4315,
|
|
"mean_token_accuracy": 0.14985745549201965,
|
|
"num_tokens": 13179919.0,
|
|
"step": 6000
|
|
},
|
|
{
|
|
"epoch": 0.5954743946010321,
|
|
"eval_entropy": 5.474441283727434,
|
|
"eval_loss": 5.552264213562012,
|
|
"eval_mean_token_accuracy": 0.14955780961736417,
|
|
"eval_num_tokens": 13179919.0,
|
|
"eval_runtime": 20.3484,
|
|
"eval_samples_per_second": 1654.624,
|
|
"eval_steps_per_second": 206.846,
|
|
"step": 6000
|
|
},
|
|
{
|
|
"entropy": 5.6688230514526365,
|
|
"epoch": 0.5959706232631997,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004972115556947518,
|
|
"loss": 5.5127,
|
|
"mean_token_accuracy": 0.14665141627192496,
|
|
"num_tokens": 13190777.0,
|
|
"step": 6005
|
|
},
|
|
{
|
|
"entropy": 5.711255836486816,
|
|
"epoch": 0.5964668519253672,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004972059920474904,
|
|
"loss": 5.5007,
|
|
"mean_token_accuracy": 0.14610673263669013,
|
|
"num_tokens": 13202179.0,
|
|
"step": 6010
|
|
},
|
|
{
|
|
"entropy": 5.662798738479614,
|
|
"epoch": 0.5969630805875348,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004972004228899991,
|
|
"loss": 5.4586,
|
|
"mean_token_accuracy": 0.15040792152285576,
|
|
"num_tokens": 13212764.0,
|
|
"step": 6015
|
|
},
|
|
{
|
|
"entropy": 5.642608690261841,
|
|
"epoch": 0.5974593092497023,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004971948482224162,
|
|
"loss": 5.5022,
|
|
"mean_token_accuracy": 0.1451937548816204,
|
|
"num_tokens": 13223343.0,
|
|
"step": 6020
|
|
},
|
|
{
|
|
"entropy": 5.653862953186035,
|
|
"epoch": 0.5979555379118698,
|
|
"grad_norm": 0.80078125,
|
|
"learning_rate": 0.0004971892680448798,
|
|
"loss": 5.4709,
|
|
"mean_token_accuracy": 0.1503230482339859,
|
|
"num_tokens": 13233839.0,
|
|
"step": 6025
|
|
},
|
|
{
|
|
"entropy": 5.720564508438111,
|
|
"epoch": 0.5984517665740373,
|
|
"grad_norm": 0.78125,
|
|
"learning_rate": 0.0004971836823575283,
|
|
"loss": 5.5738,
|
|
"mean_token_accuracy": 0.1428346298635006,
|
|
"num_tokens": 13243854.0,
|
|
"step": 6030
|
|
},
|
|
{
|
|
"entropy": 5.697343015670777,
|
|
"epoch": 0.5989479952362048,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.0004971780911605003,
|
|
"loss": 5.4835,
|
|
"mean_token_accuracy": 0.1490764081478119,
|
|
"num_tokens": 13256073.0,
|
|
"step": 6035
|
|
},
|
|
{
|
|
"entropy": 5.665929317474365,
|
|
"epoch": 0.5994442238983724,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004971724944539343,
|
|
"loss": 5.515,
|
|
"mean_token_accuracy": 0.14822529405355453,
|
|
"num_tokens": 13267568.0,
|
|
"step": 6040
|
|
},
|
|
{
|
|
"entropy": 5.720554208755493,
|
|
"epoch": 0.5999404525605398,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004971668922379692,
|
|
"loss": 5.4985,
|
|
"mean_token_accuracy": 0.1423833392560482,
|
|
"num_tokens": 13278829.0,
|
|
"step": 6045
|
|
},
|
|
{
|
|
"entropy": 5.669347763061523,
|
|
"epoch": 0.6004366812227074,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.000497161284512744,
|
|
"loss": 5.458,
|
|
"mean_token_accuracy": 0.15174900591373444,
|
|
"num_tokens": 13289156.0,
|
|
"step": 6050
|
|
},
|
|
{
|
|
"entropy": 5.547655439376831,
|
|
"epoch": 0.6009329098848749,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004971556712783976,
|
|
"loss": 5.3382,
|
|
"mean_token_accuracy": 0.15496094673871993,
|
|
"num_tokens": 13299817.0,
|
|
"step": 6055
|
|
},
|
|
{
|
|
"entropy": 5.56444673538208,
|
|
"epoch": 0.6014291385470425,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004971500525350692,
|
|
"loss": 5.4054,
|
|
"mean_token_accuracy": 0.15332763493061066,
|
|
"num_tokens": 13310290.0,
|
|
"step": 6060
|
|
},
|
|
{
|
|
"entropy": 5.607007026672363,
|
|
"epoch": 0.60192536720921,
|
|
"grad_norm": 0.76953125,
|
|
"learning_rate": 0.0004971444282828983,
|
|
"loss": 5.5244,
|
|
"mean_token_accuracy": 0.1488925039768219,
|
|
"num_tokens": 13321747.0,
|
|
"step": 6065
|
|
},
|
|
{
|
|
"entropy": 5.725985717773438,
|
|
"epoch": 0.6024215958713776,
|
|
"grad_norm": 0.80078125,
|
|
"learning_rate": 0.0004971387985220242,
|
|
"loss": 5.4554,
|
|
"mean_token_accuracy": 0.15337199568748475,
|
|
"num_tokens": 13333249.0,
|
|
"step": 6070
|
|
},
|
|
{
|
|
"entropy": 5.558460092544555,
|
|
"epoch": 0.602917824533545,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004971331632525866,
|
|
"loss": 5.4383,
|
|
"mean_token_accuracy": 0.1514162078499794,
|
|
"num_tokens": 13345336.0,
|
|
"step": 6075
|
|
},
|
|
{
|
|
"entropy": 5.7256739139556885,
|
|
"epoch": 0.6034140531957126,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.000497127522474725,
|
|
"loss": 5.5893,
|
|
"mean_token_accuracy": 0.14125749319791794,
|
|
"num_tokens": 13355797.0,
|
|
"step": 6080
|
|
},
|
|
{
|
|
"entropy": 5.720564508438111,
|
|
"epoch": 0.6039102818578801,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004971218761885797,
|
|
"loss": 5.5372,
|
|
"mean_token_accuracy": 0.14828825294971465,
|
|
"num_tokens": 13367058.0,
|
|
"step": 6085
|
|
},
|
|
{
|
|
"entropy": 5.668391180038452,
|
|
"epoch": 0.6044065105200477,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004971162243942904,
|
|
"loss": 5.4761,
|
|
"mean_token_accuracy": 0.14879498779773712,
|
|
"num_tokens": 13378579.0,
|
|
"step": 6090
|
|
},
|
|
{
|
|
"entropy": 5.670612144470215,
|
|
"epoch": 0.6049027391822152,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004971105670919975,
|
|
"loss": 5.4647,
|
|
"mean_token_accuracy": 0.14927419573068618,
|
|
"num_tokens": 13389240.0,
|
|
"step": 6095
|
|
},
|
|
{
|
|
"entropy": 5.708739519119263,
|
|
"epoch": 0.6053989678443827,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.000497104904281841,
|
|
"loss": 5.5996,
|
|
"mean_token_accuracy": 0.14185432642698287,
|
|
"num_tokens": 13401895.0,
|
|
"step": 6100
|
|
},
|
|
{
|
|
"entropy": 5.748668956756592,
|
|
"epoch": 0.6058951965065502,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004970992359639616,
|
|
"loss": 5.5673,
|
|
"mean_token_accuracy": 0.1404925614595413,
|
|
"num_tokens": 13413334.0,
|
|
"step": 6105
|
|
},
|
|
{
|
|
"entropy": 5.686299133300781,
|
|
"epoch": 0.6063914251687177,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004970935621384996,
|
|
"loss": 5.4763,
|
|
"mean_token_accuracy": 0.15073925480246544,
|
|
"num_tokens": 13423371.0,
|
|
"step": 6110
|
|
},
|
|
{
|
|
"entropy": 5.716171646118164,
|
|
"epoch": 0.6068876538308853,
|
|
"grad_norm": 1.875,
|
|
"learning_rate": 0.0004970878828055959,
|
|
"loss": 5.4628,
|
|
"mean_token_accuracy": 0.15296884328126908,
|
|
"num_tokens": 13434782.0,
|
|
"step": 6115
|
|
},
|
|
{
|
|
"entropy": 5.639015197753906,
|
|
"epoch": 0.6073838824930528,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004970821979653912,
|
|
"loss": 5.4516,
|
|
"mean_token_accuracy": 0.1492540270090103,
|
|
"num_tokens": 13444493.0,
|
|
"step": 6120
|
|
},
|
|
{
|
|
"entropy": 5.634776020050049,
|
|
"epoch": 0.6078801111552203,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004970765076180265,
|
|
"loss": 5.4336,
|
|
"mean_token_accuracy": 0.14924686998128892,
|
|
"num_tokens": 13455518.0,
|
|
"step": 6125
|
|
},
|
|
{
|
|
"entropy": 5.729962301254273,
|
|
"epoch": 0.6083763398173878,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004970708117636431,
|
|
"loss": 5.5256,
|
|
"mean_token_accuracy": 0.15012605488300323,
|
|
"num_tokens": 13467631.0,
|
|
"step": 6130
|
|
},
|
|
{
|
|
"entropy": 5.6114765167236325,
|
|
"epoch": 0.6088725684795554,
|
|
"grad_norm": 0.80078125,
|
|
"learning_rate": 0.000497065110402382,
|
|
"loss": 5.4627,
|
|
"mean_token_accuracy": 0.14560690820217131,
|
|
"num_tokens": 13478217.0,
|
|
"step": 6135
|
|
},
|
|
{
|
|
"entropy": 5.63499870300293,
|
|
"epoch": 0.6093687971417229,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004970594035343846,
|
|
"loss": 5.4374,
|
|
"mean_token_accuracy": 0.15331496596336364,
|
|
"num_tokens": 13489169.0,
|
|
"step": 6140
|
|
},
|
|
{
|
|
"entropy": 5.675707912445068,
|
|
"epoch": 0.6098650258038905,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004970536911597926,
|
|
"loss": 5.4679,
|
|
"mean_token_accuracy": 0.14365995824337005,
|
|
"num_tokens": 13499273.0,
|
|
"step": 6145
|
|
},
|
|
{
|
|
"entropy": 5.737535095214843,
|
|
"epoch": 0.6103612544660579,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004970479732787476,
|
|
"loss": 5.4907,
|
|
"mean_token_accuracy": 0.15293558239936828,
|
|
"num_tokens": 13509664.0,
|
|
"step": 6150
|
|
},
|
|
{
|
|
"entropy": 5.632332801818848,
|
|
"epoch": 0.6108574831282255,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004970422498913911,
|
|
"loss": 5.383,
|
|
"mean_token_accuracy": 0.14625990018248558,
|
|
"num_tokens": 13520288.0,
|
|
"step": 6155
|
|
},
|
|
{
|
|
"entropy": 5.617789173126221,
|
|
"epoch": 0.611353711790393,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004970365209978655,
|
|
"loss": 5.482,
|
|
"mean_token_accuracy": 0.14435981065034867,
|
|
"num_tokens": 13531167.0,
|
|
"step": 6160
|
|
},
|
|
{
|
|
"entropy": 5.633021974563599,
|
|
"epoch": 0.6118499404525606,
|
|
"grad_norm": 0.77734375,
|
|
"learning_rate": 0.0004970307865983124,
|
|
"loss": 5.5136,
|
|
"mean_token_accuracy": 0.15051327794790267,
|
|
"num_tokens": 13544109.0,
|
|
"step": 6165
|
|
},
|
|
{
|
|
"entropy": 5.711878728866577,
|
|
"epoch": 0.6123461691147281,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004970250466928744,
|
|
"loss": 5.4445,
|
|
"mean_token_accuracy": 0.15177036300301552,
|
|
"num_tokens": 13554935.0,
|
|
"step": 6170
|
|
},
|
|
{
|
|
"entropy": 5.650032234191895,
|
|
"epoch": 0.6128423977768956,
|
|
"grad_norm": 0.796875,
|
|
"learning_rate": 0.0004970193012816936,
|
|
"loss": 5.4592,
|
|
"mean_token_accuracy": 0.1498909927904606,
|
|
"num_tokens": 13565959.0,
|
|
"step": 6175
|
|
},
|
|
{
|
|
"entropy": 5.586412048339843,
|
|
"epoch": 0.6133386264390631,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004970135503649125,
|
|
"loss": 5.4659,
|
|
"mean_token_accuracy": 0.14620325416326524,
|
|
"num_tokens": 13577883.0,
|
|
"step": 6180
|
|
},
|
|
{
|
|
"entropy": 5.672992372512818,
|
|
"epoch": 0.6138348551012306,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004970077939426738,
|
|
"loss": 5.4442,
|
|
"mean_token_accuracy": 0.1484336093068123,
|
|
"num_tokens": 13588597.0,
|
|
"step": 6185
|
|
},
|
|
{
|
|
"entropy": 5.665392017364502,
|
|
"epoch": 0.6143310837633982,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004970020320151202,
|
|
"loss": 5.3882,
|
|
"mean_token_accuracy": 0.15516335219144822,
|
|
"num_tokens": 13598772.0,
|
|
"step": 6190
|
|
},
|
|
{
|
|
"entropy": 5.672236442565918,
|
|
"epoch": 0.6148273124255657,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004969962645823946,
|
|
"loss": 5.4717,
|
|
"mean_token_accuracy": 0.1497521921992302,
|
|
"num_tokens": 13609696.0,
|
|
"step": 6195
|
|
},
|
|
{
|
|
"entropy": 5.592589807510376,
|
|
"epoch": 0.6153235410877332,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.00049699049164464,
|
|
"loss": 5.4598,
|
|
"mean_token_accuracy": 0.15013887584209443,
|
|
"num_tokens": 13619389.0,
|
|
"step": 6200
|
|
},
|
|
{
|
|
"entropy": 5.624180746078491,
|
|
"epoch": 0.6158197697499007,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.0004969847132019995,
|
|
"loss": 5.4294,
|
|
"mean_token_accuracy": 0.15189450085163117,
|
|
"num_tokens": 13632133.0,
|
|
"step": 6205
|
|
},
|
|
{
|
|
"entropy": 5.660528612136841,
|
|
"epoch": 0.6163159984120683,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004969789292546164,
|
|
"loss": 5.3865,
|
|
"mean_token_accuracy": 0.1556358143687248,
|
|
"num_tokens": 13642715.0,
|
|
"step": 6210
|
|
},
|
|
{
|
|
"entropy": 5.621987342834473,
|
|
"epoch": 0.6168122270742358,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004969731398026343,
|
|
"loss": 5.4931,
|
|
"mean_token_accuracy": 0.14751377552747727,
|
|
"num_tokens": 13653223.0,
|
|
"step": 6215
|
|
},
|
|
{
|
|
"entropy": 5.559430122375488,
|
|
"epoch": 0.6173084557364034,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004969673448461966,
|
|
"loss": 5.4629,
|
|
"mean_token_accuracy": 0.1489397704601288,
|
|
"num_tokens": 13664206.0,
|
|
"step": 6220
|
|
},
|
|
{
|
|
"entropy": 5.66539363861084,
|
|
"epoch": 0.6178046843985708,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.000496961544385447,
|
|
"loss": 5.486,
|
|
"mean_token_accuracy": 0.14996751099824907,
|
|
"num_tokens": 13673974.0,
|
|
"step": 6225
|
|
},
|
|
{
|
|
"entropy": 5.628175449371338,
|
|
"epoch": 0.6183009130607384,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004969557384205295,
|
|
"loss": 5.4018,
|
|
"mean_token_accuracy": 0.15043520480394362,
|
|
"num_tokens": 13685189.0,
|
|
"step": 6230
|
|
},
|
|
{
|
|
"entropy": 5.642521572113037,
|
|
"epoch": 0.6187971417229059,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004969499269515878,
|
|
"loss": 5.4195,
|
|
"mean_token_accuracy": 0.15626146644353867,
|
|
"num_tokens": 13696181.0,
|
|
"step": 6235
|
|
},
|
|
{
|
|
"entropy": 5.738152933120728,
|
|
"epoch": 0.6192933703850735,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004969441099787663,
|
|
"loss": 5.5273,
|
|
"mean_token_accuracy": 0.14354099780321122,
|
|
"num_tokens": 13706719.0,
|
|
"step": 6240
|
|
},
|
|
{
|
|
"entropy": 5.740992403030395,
|
|
"epoch": 0.619789599047241,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.000496938287502209,
|
|
"loss": 5.4874,
|
|
"mean_token_accuracy": 0.1491748109459877,
|
|
"num_tokens": 13716653.0,
|
|
"step": 6245
|
|
},
|
|
{
|
|
"entropy": 5.581117296218872,
|
|
"epoch": 0.6202858277094085,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004969324595220605,
|
|
"loss": 5.3952,
|
|
"mean_token_accuracy": 0.15741943269968034,
|
|
"num_tokens": 13728220.0,
|
|
"step": 6250
|
|
},
|
|
{
|
|
"entropy": 5.562930679321289,
|
|
"epoch": 0.620782056371576,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004969266260384652,
|
|
"loss": 5.3781,
|
|
"mean_token_accuracy": 0.15155331492424012,
|
|
"num_tokens": 13738103.0,
|
|
"step": 6255
|
|
},
|
|
{
|
|
"entropy": 5.641094112396241,
|
|
"epoch": 0.6212782850337435,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.0004969207870515678,
|
|
"loss": 5.4541,
|
|
"mean_token_accuracy": 0.1509600356221199,
|
|
"num_tokens": 13749845.0,
|
|
"step": 6260
|
|
},
|
|
{
|
|
"entropy": 5.6544554233551025,
|
|
"epoch": 0.6217745136959111,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.000496914942561513,
|
|
"loss": 5.4965,
|
|
"mean_token_accuracy": 0.15008585378527642,
|
|
"num_tokens": 13759983.0,
|
|
"step": 6265
|
|
},
|
|
{
|
|
"entropy": 5.687742471694946,
|
|
"epoch": 0.6222707423580786,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004969090925684459,
|
|
"loss": 5.5695,
|
|
"mean_token_accuracy": 0.14714422523975373,
|
|
"num_tokens": 13770045.0,
|
|
"step": 6270
|
|
},
|
|
{
|
|
"entropy": 5.5897331714630125,
|
|
"epoch": 0.6227669710202461,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004969032370725114,
|
|
"loss": 5.428,
|
|
"mean_token_accuracy": 0.15328796654939653,
|
|
"num_tokens": 13779823.0,
|
|
"step": 6275
|
|
},
|
|
{
|
|
"entropy": 5.629849863052368,
|
|
"epoch": 0.6232631996824136,
|
|
"grad_norm": 0.78515625,
|
|
"learning_rate": 0.0004968973760738548,
|
|
"loss": 5.4199,
|
|
"mean_token_accuracy": 0.1493604764342308,
|
|
"num_tokens": 13791165.0,
|
|
"step": 6280
|
|
},
|
|
{
|
|
"entropy": 5.711244440078735,
|
|
"epoch": 0.6237594283445812,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004968915095726216,
|
|
"loss": 5.5162,
|
|
"mean_token_accuracy": 0.1434049963951111,
|
|
"num_tokens": 13802872.0,
|
|
"step": 6285
|
|
},
|
|
{
|
|
"entropy": 5.658536672592163,
|
|
"epoch": 0.6242556570067487,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004968856375689568,
|
|
"loss": 5.4538,
|
|
"mean_token_accuracy": 0.15151210278272628,
|
|
"num_tokens": 13813893.0,
|
|
"step": 6290
|
|
},
|
|
{
|
|
"entropy": 5.6452268123626705,
|
|
"epoch": 0.6247518856689163,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004968797600630065,
|
|
"loss": 5.5219,
|
|
"mean_token_accuracy": 0.15299668312072753,
|
|
"num_tokens": 13823613.0,
|
|
"step": 6295
|
|
},
|
|
{
|
|
"entropy": 5.7115713596344,
|
|
"epoch": 0.6252481143310837,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004968738770549162,
|
|
"loss": 5.525,
|
|
"mean_token_accuracy": 0.14985218942165374,
|
|
"num_tokens": 13835413.0,
|
|
"step": 6300
|
|
},
|
|
{
|
|
"entropy": 5.634415054321289,
|
|
"epoch": 0.6257443429932513,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004968679885448318,
|
|
"loss": 5.4584,
|
|
"mean_token_accuracy": 0.14723524004220961,
|
|
"num_tokens": 13845806.0,
|
|
"step": 6305
|
|
},
|
|
{
|
|
"entropy": 5.693110227584839,
|
|
"epoch": 0.6262405716554188,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004968620945328995,
|
|
"loss": 5.5625,
|
|
"mean_token_accuracy": 0.14774496108293533,
|
|
"num_tokens": 13856540.0,
|
|
"step": 6310
|
|
},
|
|
{
|
|
"entropy": 5.641265916824341,
|
|
"epoch": 0.6267368003175864,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004968561950192652,
|
|
"loss": 5.4035,
|
|
"mean_token_accuracy": 0.15361193418502808,
|
|
"num_tokens": 13867609.0,
|
|
"step": 6315
|
|
},
|
|
{
|
|
"entropy": 5.698054599761963,
|
|
"epoch": 0.6272330289797539,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0004968502900040753,
|
|
"loss": 5.4735,
|
|
"mean_token_accuracy": 0.14571210592985154,
|
|
"num_tokens": 13878299.0,
|
|
"step": 6320
|
|
},
|
|
{
|
|
"entropy": 5.694347095489502,
|
|
"epoch": 0.6277292576419214,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004968443794874764,
|
|
"loss": 5.4807,
|
|
"mean_token_accuracy": 0.14888293594121932,
|
|
"num_tokens": 13889625.0,
|
|
"step": 6325
|
|
},
|
|
{
|
|
"entropy": 5.62461142539978,
|
|
"epoch": 0.6282254863040889,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004968384634696149,
|
|
"loss": 5.4585,
|
|
"mean_token_accuracy": 0.1475509375333786,
|
|
"num_tokens": 13899680.0,
|
|
"step": 6330
|
|
},
|
|
{
|
|
"entropy": 5.574176692962647,
|
|
"epoch": 0.6287217149662565,
|
|
"grad_norm": 0.78125,
|
|
"learning_rate": 0.0004968325419506375,
|
|
"loss": 5.4308,
|
|
"mean_token_accuracy": 0.15305441319942475,
|
|
"num_tokens": 13910883.0,
|
|
"step": 6335
|
|
},
|
|
{
|
|
"entropy": 5.608674001693726,
|
|
"epoch": 0.629217943628424,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004968266149306909,
|
|
"loss": 5.4367,
|
|
"mean_token_accuracy": 0.15015380084514618,
|
|
"num_tokens": 13921442.0,
|
|
"step": 6340
|
|
},
|
|
{
|
|
"entropy": 5.6577832221984865,
|
|
"epoch": 0.6297141722905915,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004968206824099224,
|
|
"loss": 5.4799,
|
|
"mean_token_accuracy": 0.15244491249322892,
|
|
"num_tokens": 13930309.0,
|
|
"step": 6345
|
|
},
|
|
{
|
|
"entropy": 5.672576761245727,
|
|
"epoch": 0.630210400952759,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004968147443884789,
|
|
"loss": 5.4624,
|
|
"mean_token_accuracy": 0.1559087797999382,
|
|
"num_tokens": 13941346.0,
|
|
"step": 6350
|
|
},
|
|
{
|
|
"entropy": 5.636896467208862,
|
|
"epoch": 0.6307066296149265,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004968088008665078,
|
|
"loss": 5.4418,
|
|
"mean_token_accuracy": 0.1529480427503586,
|
|
"num_tokens": 13951933.0,
|
|
"step": 6355
|
|
},
|
|
{
|
|
"entropy": 5.587031555175781,
|
|
"epoch": 0.6312028582770941,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004968028518441563,
|
|
"loss": 5.4884,
|
|
"mean_token_accuracy": 0.1458326257765293,
|
|
"num_tokens": 13963112.0,
|
|
"step": 6360
|
|
},
|
|
{
|
|
"entropy": 5.713586330413818,
|
|
"epoch": 0.6316990869392616,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004967968973215721,
|
|
"loss": 5.5219,
|
|
"mean_token_accuracy": 0.15321382731199265,
|
|
"num_tokens": 13974218.0,
|
|
"step": 6365
|
|
},
|
|
{
|
|
"entropy": 5.71185941696167,
|
|
"epoch": 0.6321953156014292,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004967909372989027,
|
|
"loss": 5.4483,
|
|
"mean_token_accuracy": 0.15306579768657685,
|
|
"num_tokens": 13984841.0,
|
|
"step": 6370
|
|
},
|
|
{
|
|
"entropy": 5.609977102279663,
|
|
"epoch": 0.6326915442635966,
|
|
"grad_norm": 0.78515625,
|
|
"learning_rate": 0.0004967849717762959,
|
|
"loss": 5.4589,
|
|
"mean_token_accuracy": 0.1499641492962837,
|
|
"num_tokens": 13997504.0,
|
|
"step": 6375
|
|
},
|
|
{
|
|
"entropy": 5.571201181411743,
|
|
"epoch": 0.6331877729257642,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004967790007538999,
|
|
"loss": 5.4043,
|
|
"mean_token_accuracy": 0.15468272864818572,
|
|
"num_tokens": 14009244.0,
|
|
"step": 6380
|
|
},
|
|
{
|
|
"entropy": 5.617036819458008,
|
|
"epoch": 0.6336840015879317,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004967730242318624,
|
|
"loss": 5.439,
|
|
"mean_token_accuracy": 0.1511642351746559,
|
|
"num_tokens": 14021190.0,
|
|
"step": 6385
|
|
},
|
|
{
|
|
"entropy": 5.607939720153809,
|
|
"epoch": 0.6341802302500993,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.000496767042210332,
|
|
"loss": 5.3981,
|
|
"mean_token_accuracy": 0.1521475076675415,
|
|
"num_tokens": 14032191.0,
|
|
"step": 6390
|
|
},
|
|
{
|
|
"entropy": 5.543286514282227,
|
|
"epoch": 0.6346764589122668,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004967610546894566,
|
|
"loss": 5.3764,
|
|
"mean_token_accuracy": 0.15400539189577103,
|
|
"num_tokens": 14042817.0,
|
|
"step": 6395
|
|
},
|
|
{
|
|
"entropy": 5.626496887207031,
|
|
"epoch": 0.6351726875744343,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.000496755061669385,
|
|
"loss": 5.3917,
|
|
"mean_token_accuracy": 0.15254785865545273,
|
|
"num_tokens": 14052725.0,
|
|
"step": 6400
|
|
},
|
|
{
|
|
"entropy": 5.65068039894104,
|
|
"epoch": 0.6356689162366018,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004967490631502656,
|
|
"loss": 5.4728,
|
|
"mean_token_accuracy": 0.14567496478557587,
|
|
"num_tokens": 14063621.0,
|
|
"step": 6405
|
|
},
|
|
{
|
|
"entropy": 5.735702085494995,
|
|
"epoch": 0.6361651448987694,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004967430591322474,
|
|
"loss": 5.5721,
|
|
"mean_token_accuracy": 0.147471821308136,
|
|
"num_tokens": 14074350.0,
|
|
"step": 6410
|
|
},
|
|
{
|
|
"entropy": 5.694315576553345,
|
|
"epoch": 0.6366613735609369,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004967370496154791,
|
|
"loss": 5.5215,
|
|
"mean_token_accuracy": 0.1483861267566681,
|
|
"num_tokens": 14084600.0,
|
|
"step": 6415
|
|
},
|
|
{
|
|
"entropy": 5.700325345993042,
|
|
"epoch": 0.6371576022231044,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004967310346001098,
|
|
"loss": 5.4329,
|
|
"mean_token_accuracy": 0.1556906893849373,
|
|
"num_tokens": 14094739.0,
|
|
"step": 6420
|
|
},
|
|
{
|
|
"entropy": 5.769415760040284,
|
|
"epoch": 0.6376538308852719,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004967250140862885,
|
|
"loss": 5.594,
|
|
"mean_token_accuracy": 0.1452789142727852,
|
|
"num_tokens": 14106020.0,
|
|
"step": 6425
|
|
},
|
|
{
|
|
"entropy": 5.731551599502564,
|
|
"epoch": 0.6381500595474394,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004967189880741647,
|
|
"loss": 5.5722,
|
|
"mean_token_accuracy": 0.14545285180211068,
|
|
"num_tokens": 14117699.0,
|
|
"step": 6430
|
|
},
|
|
{
|
|
"entropy": 5.623116683959961,
|
|
"epoch": 0.638646288209607,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004967129565638878,
|
|
"loss": 5.4402,
|
|
"mean_token_accuracy": 0.1498525395989418,
|
|
"num_tokens": 14128901.0,
|
|
"step": 6435
|
|
},
|
|
{
|
|
"entropy": 5.62310471534729,
|
|
"epoch": 0.6391425168717745,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004967069195556073,
|
|
"loss": 5.4796,
|
|
"mean_token_accuracy": 0.14773380234837533,
|
|
"num_tokens": 14140832.0,
|
|
"step": 6440
|
|
},
|
|
{
|
|
"entropy": 5.678237342834473,
|
|
"epoch": 0.6396387455339421,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.000496700877049473,
|
|
"loss": 5.5207,
|
|
"mean_token_accuracy": 0.15002197176218032,
|
|
"num_tokens": 14151936.0,
|
|
"step": 6445
|
|
},
|
|
{
|
|
"entropy": 5.700641059875489,
|
|
"epoch": 0.6401349741961095,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004966948290456345,
|
|
"loss": 5.518,
|
|
"mean_token_accuracy": 0.149015374481678,
|
|
"num_tokens": 14160945.0,
|
|
"step": 6450
|
|
},
|
|
{
|
|
"entropy": 5.624499082565308,
|
|
"epoch": 0.6406312028582771,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004966887755442421,
|
|
"loss": 5.4147,
|
|
"mean_token_accuracy": 0.14972492605447768,
|
|
"num_tokens": 14172052.0,
|
|
"step": 6455
|
|
},
|
|
{
|
|
"entropy": 5.65600733757019,
|
|
"epoch": 0.6411274315204446,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004966827165454456,
|
|
"loss": 5.4815,
|
|
"mean_token_accuracy": 0.1499800741672516,
|
|
"num_tokens": 14181788.0,
|
|
"step": 6460
|
|
},
|
|
{
|
|
"entropy": 5.7158653259277346,
|
|
"epoch": 0.6416236601826122,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.0004966766520493956,
|
|
"loss": 5.5606,
|
|
"mean_token_accuracy": 0.14471029564738275,
|
|
"num_tokens": 14193668.0,
|
|
"step": 6465
|
|
},
|
|
{
|
|
"entropy": 5.702195644378662,
|
|
"epoch": 0.6421198888447797,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004966705820562422,
|
|
"loss": 5.4357,
|
|
"mean_token_accuracy": 0.15261470079421996,
|
|
"num_tokens": 14203665.0,
|
|
"step": 6470
|
|
},
|
|
{
|
|
"entropy": 5.655112648010254,
|
|
"epoch": 0.6426161175069472,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004966645065661361,
|
|
"loss": 5.4806,
|
|
"mean_token_accuracy": 0.14383687674999238,
|
|
"num_tokens": 14214213.0,
|
|
"step": 6475
|
|
},
|
|
{
|
|
"entropy": 5.683132743835449,
|
|
"epoch": 0.6431123461691147,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004966584255792279,
|
|
"loss": 5.5541,
|
|
"mean_token_accuracy": 0.14166881144046783,
|
|
"num_tokens": 14225754.0,
|
|
"step": 6480
|
|
},
|
|
{
|
|
"entropy": 5.671842384338379,
|
|
"epoch": 0.6436085748312823,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004966523390956683,
|
|
"loss": 5.4547,
|
|
"mean_token_accuracy": 0.1519224651157856,
|
|
"num_tokens": 14236508.0,
|
|
"step": 6485
|
|
},
|
|
{
|
|
"entropy": 5.710225915908813,
|
|
"epoch": 0.6441048034934498,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004966462471156083,
|
|
"loss": 5.4941,
|
|
"mean_token_accuracy": 0.15028066784143448,
|
|
"num_tokens": 14247719.0,
|
|
"step": 6490
|
|
},
|
|
{
|
|
"entropy": 5.667965984344482,
|
|
"epoch": 0.6446010321556173,
|
|
"grad_norm": 0.78125,
|
|
"learning_rate": 0.0004966401496391989,
|
|
"loss": 5.5546,
|
|
"mean_token_accuracy": 0.13857395723462104,
|
|
"num_tokens": 14258667.0,
|
|
"step": 6495
|
|
},
|
|
{
|
|
"entropy": 5.68690299987793,
|
|
"epoch": 0.6450972608177848,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004966340466665915,
|
|
"loss": 5.5441,
|
|
"mean_token_accuracy": 0.14910787716507912,
|
|
"num_tokens": 14269666.0,
|
|
"step": 6500
|
|
},
|
|
{
|
|
"entropy": 5.591238164901734,
|
|
"epoch": 0.6455934894799523,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004966279381979373,
|
|
"loss": 5.4538,
|
|
"mean_token_accuracy": 0.1470872327685356,
|
|
"num_tokens": 14280862.0,
|
|
"step": 6505
|
|
},
|
|
{
|
|
"entropy": 5.715922689437866,
|
|
"epoch": 0.6460897181421199,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004966218242333879,
|
|
"loss": 5.5827,
|
|
"mean_token_accuracy": 0.13394412621855736,
|
|
"num_tokens": 14292505.0,
|
|
"step": 6510
|
|
},
|
|
{
|
|
"entropy": 5.672628402709961,
|
|
"epoch": 0.6465859468042874,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004966157047730945,
|
|
"loss": 5.3881,
|
|
"mean_token_accuracy": 0.1511433869600296,
|
|
"num_tokens": 14302547.0,
|
|
"step": 6515
|
|
},
|
|
{
|
|
"entropy": 5.617307519912719,
|
|
"epoch": 0.647082175466455,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004966095798172095,
|
|
"loss": 5.5199,
|
|
"mean_token_accuracy": 0.1442197382450104,
|
|
"num_tokens": 14313585.0,
|
|
"step": 6520
|
|
},
|
|
{
|
|
"entropy": 5.6147984027862545,
|
|
"epoch": 0.6475784041286224,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0004966034493658843,
|
|
"loss": 5.4025,
|
|
"mean_token_accuracy": 0.14724294617772102,
|
|
"num_tokens": 14323665.0,
|
|
"step": 6525
|
|
},
|
|
{
|
|
"entropy": 5.619630432128906,
|
|
"epoch": 0.64807463279079,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.0004965973134192711,
|
|
"loss": 5.43,
|
|
"mean_token_accuracy": 0.15175018832087517,
|
|
"num_tokens": 14334257.0,
|
|
"step": 6530
|
|
},
|
|
{
|
|
"entropy": 5.702003145217896,
|
|
"epoch": 0.6485708614529575,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.000496591171977522,
|
|
"loss": 5.4548,
|
|
"mean_token_accuracy": 0.15189530849456787,
|
|
"num_tokens": 14345350.0,
|
|
"step": 6535
|
|
},
|
|
{
|
|
"entropy": 5.690001726150513,
|
|
"epoch": 0.6490670901151251,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004965850250407893,
|
|
"loss": 5.4552,
|
|
"mean_token_accuracy": 0.15488422363996507,
|
|
"num_tokens": 14355593.0,
|
|
"step": 6540
|
|
},
|
|
{
|
|
"entropy": 5.604142856597901,
|
|
"epoch": 0.6495633187772926,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.0004965788726092256,
|
|
"loss": 5.3459,
|
|
"mean_token_accuracy": 0.1584514856338501,
|
|
"num_tokens": 14366405.0,
|
|
"step": 6545
|
|
},
|
|
{
|
|
"entropy": 5.601662302017212,
|
|
"epoch": 0.6500595474394602,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.0004965727146829832,
|
|
"loss": 5.4235,
|
|
"mean_token_accuracy": 0.14971744865179062,
|
|
"num_tokens": 14377228.0,
|
|
"step": 6550
|
|
},
|
|
{
|
|
"entropy": 5.766236972808838,
|
|
"epoch": 0.6505557761016276,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004965665512622148,
|
|
"loss": 5.576,
|
|
"mean_token_accuracy": 0.14476309791207315,
|
|
"num_tokens": 14387113.0,
|
|
"step": 6555
|
|
},
|
|
{
|
|
"entropy": 5.6732823848724365,
|
|
"epoch": 0.6510520047637952,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004965603823470735,
|
|
"loss": 5.46,
|
|
"mean_token_accuracy": 0.15242564380168916,
|
|
"num_tokens": 14397980.0,
|
|
"step": 6560
|
|
},
|
|
{
|
|
"entropy": 5.6098064422607425,
|
|
"epoch": 0.6515482334259627,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004965542079377122,
|
|
"loss": 5.3773,
|
|
"mean_token_accuracy": 0.15433671772480012,
|
|
"num_tokens": 14409063.0,
|
|
"step": 6565
|
|
},
|
|
{
|
|
"entropy": 5.568036031723023,
|
|
"epoch": 0.6520444620881302,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004965480280342839,
|
|
"loss": 5.364,
|
|
"mean_token_accuracy": 0.1615317314863205,
|
|
"num_tokens": 14421056.0,
|
|
"step": 6570
|
|
},
|
|
{
|
|
"entropy": 5.611463165283203,
|
|
"epoch": 0.6525406907502977,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004965418426369419,
|
|
"loss": 5.353,
|
|
"mean_token_accuracy": 0.15946202576160431,
|
|
"num_tokens": 14430778.0,
|
|
"step": 6575
|
|
},
|
|
{
|
|
"entropy": 5.614991188049316,
|
|
"epoch": 0.6530369194124652,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004965356517458395,
|
|
"loss": 5.3768,
|
|
"mean_token_accuracy": 0.15489154756069184,
|
|
"num_tokens": 14441544.0,
|
|
"step": 6580
|
|
},
|
|
{
|
|
"entropy": 5.607758903503418,
|
|
"epoch": 0.6535331480746328,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004965294553611303,
|
|
"loss": 5.5202,
|
|
"mean_token_accuracy": 0.15016790255904197,
|
|
"num_tokens": 14453062.0,
|
|
"step": 6585
|
|
},
|
|
{
|
|
"entropy": 5.680311822891236,
|
|
"epoch": 0.6540293767368003,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.000496523253482968,
|
|
"loss": 5.4446,
|
|
"mean_token_accuracy": 0.15107833594083786,
|
|
"num_tokens": 14464402.0,
|
|
"step": 6590
|
|
},
|
|
{
|
|
"entropy": 5.682463645935059,
|
|
"epoch": 0.6545256053989679,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004965170461115065,
|
|
"loss": 5.536,
|
|
"mean_token_accuracy": 0.1490773156285286,
|
|
"num_tokens": 14476595.0,
|
|
"step": 6595
|
|
},
|
|
{
|
|
"entropy": 5.70050892829895,
|
|
"epoch": 0.6550218340611353,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004965108332468994,
|
|
"loss": 5.5022,
|
|
"mean_token_accuracy": 0.1478926882147789,
|
|
"num_tokens": 14487298.0,
|
|
"step": 6600
|
|
},
|
|
{
|
|
"entropy": 5.653990840911865,
|
|
"epoch": 0.6555180627233029,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004965046148893011,
|
|
"loss": 5.4201,
|
|
"mean_token_accuracy": 0.15270100384950638,
|
|
"num_tokens": 14499708.0,
|
|
"step": 6605
|
|
},
|
|
{
|
|
"entropy": 5.637703609466553,
|
|
"epoch": 0.6560142913854704,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004964983910388654,
|
|
"loss": 5.4779,
|
|
"mean_token_accuracy": 0.14862264692783356,
|
|
"num_tokens": 14511773.0,
|
|
"step": 6610
|
|
},
|
|
{
|
|
"entropy": 5.576990079879761,
|
|
"epoch": 0.656510520047638,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.0004964921616957471,
|
|
"loss": 5.3809,
|
|
"mean_token_accuracy": 0.14810700714588165,
|
|
"num_tokens": 14523024.0,
|
|
"step": 6615
|
|
},
|
|
{
|
|
"entropy": 5.658850431442261,
|
|
"epoch": 0.6570067487098055,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004964859268601005,
|
|
"loss": 5.4527,
|
|
"mean_token_accuracy": 0.15175904259085654,
|
|
"num_tokens": 14532915.0,
|
|
"step": 6620
|
|
},
|
|
{
|
|
"entropy": 5.683317947387695,
|
|
"epoch": 0.657502977371973,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004964796865320801,
|
|
"loss": 5.4417,
|
|
"mean_token_accuracy": 0.1551850751042366,
|
|
"num_tokens": 14543627.0,
|
|
"step": 6625
|
|
},
|
|
{
|
|
"entropy": 5.5610107421875,
|
|
"epoch": 0.6579992060341405,
|
|
"grad_norm": 0.78515625,
|
|
"learning_rate": 0.0004964734407118406,
|
|
"loss": 5.3949,
|
|
"mean_token_accuracy": 0.15504732429981233,
|
|
"num_tokens": 14555181.0,
|
|
"step": 6630
|
|
},
|
|
{
|
|
"entropy": 5.605614471435547,
|
|
"epoch": 0.6584954346963081,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004964671893995372,
|
|
"loss": 5.4025,
|
|
"mean_token_accuracy": 0.1500137612223625,
|
|
"num_tokens": 14565542.0,
|
|
"step": 6635
|
|
},
|
|
{
|
|
"entropy": 5.685685634613037,
|
|
"epoch": 0.6589916633584756,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004964609325953245,
|
|
"loss": 5.4629,
|
|
"mean_token_accuracy": 0.15267691314220427,
|
|
"num_tokens": 14575395.0,
|
|
"step": 6640
|
|
},
|
|
{
|
|
"entropy": 5.671268796920776,
|
|
"epoch": 0.6594878920206431,
|
|
"grad_norm": 0.78515625,
|
|
"learning_rate": 0.0004964546702993581,
|
|
"loss": 5.499,
|
|
"mean_token_accuracy": 0.15098451375961303,
|
|
"num_tokens": 14587206.0,
|
|
"step": 6645
|
|
},
|
|
{
|
|
"entropy": 5.686512517929077,
|
|
"epoch": 0.6599841206828106,
|
|
"grad_norm": 0.7734375,
|
|
"learning_rate": 0.000496448402511793,
|
|
"loss": 5.505,
|
|
"mean_token_accuracy": 0.15307042002677917,
|
|
"num_tokens": 14599048.0,
|
|
"step": 6650
|
|
},
|
|
{
|
|
"entropy": 5.68162202835083,
|
|
"epoch": 0.6604803493449781,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004964421292327847,
|
|
"loss": 5.4835,
|
|
"mean_token_accuracy": 0.1511673018336296,
|
|
"num_tokens": 14609633.0,
|
|
"step": 6655
|
|
},
|
|
{
|
|
"entropy": 5.630779695510864,
|
|
"epoch": 0.6609765780071457,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004964358504624887,
|
|
"loss": 5.381,
|
|
"mean_token_accuracy": 0.15312047600746154,
|
|
"num_tokens": 14620373.0,
|
|
"step": 6660
|
|
},
|
|
{
|
|
"entropy": 5.623717641830444,
|
|
"epoch": 0.6614728066693132,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004964295662010608,
|
|
"loss": 5.3234,
|
|
"mean_token_accuracy": 0.15719757080078126,
|
|
"num_tokens": 14630463.0,
|
|
"step": 6665
|
|
},
|
|
{
|
|
"entropy": 5.7358582496643065,
|
|
"epoch": 0.6619690353314808,
|
|
"grad_norm": 0.80078125,
|
|
"learning_rate": 0.0004964232764486568,
|
|
"loss": 5.5689,
|
|
"mean_token_accuracy": 0.1434595428407192,
|
|
"num_tokens": 14641523.0,
|
|
"step": 6670
|
|
},
|
|
{
|
|
"entropy": 5.620292282104492,
|
|
"epoch": 0.6624652639936482,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004964169812054326,
|
|
"loss": 5.398,
|
|
"mean_token_accuracy": 0.1509662389755249,
|
|
"num_tokens": 14651812.0,
|
|
"step": 6675
|
|
},
|
|
{
|
|
"entropy": 5.62327766418457,
|
|
"epoch": 0.6629614926558158,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004964106804715444,
|
|
"loss": 5.3856,
|
|
"mean_token_accuracy": 0.15855159610509872,
|
|
"num_tokens": 14661982.0,
|
|
"step": 6680
|
|
},
|
|
{
|
|
"entropy": 5.599073123931885,
|
|
"epoch": 0.6634577213179833,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004964043742471486,
|
|
"loss": 5.4146,
|
|
"mean_token_accuracy": 0.15977433919906617,
|
|
"num_tokens": 14671981.0,
|
|
"step": 6685
|
|
},
|
|
{
|
|
"entropy": 5.659870243072509,
|
|
"epoch": 0.6639539499801509,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004963980625324012,
|
|
"loss": 5.4266,
|
|
"mean_token_accuracy": 0.1492961347103119,
|
|
"num_tokens": 14682478.0,
|
|
"step": 6690
|
|
},
|
|
{
|
|
"entropy": 5.6607927799224855,
|
|
"epoch": 0.6644501786423184,
|
|
"grad_norm": 0.78515625,
|
|
"learning_rate": 0.000496391745327459,
|
|
"loss": 5.4959,
|
|
"mean_token_accuracy": 0.1413546122610569,
|
|
"num_tokens": 14695197.0,
|
|
"step": 6695
|
|
},
|
|
{
|
|
"entropy": 5.6239784240722654,
|
|
"epoch": 0.664946407304486,
|
|
"grad_norm": 0.75390625,
|
|
"learning_rate": 0.0004963854226324785,
|
|
"loss": 5.4102,
|
|
"mean_token_accuracy": 0.15093137323856354,
|
|
"num_tokens": 14705702.0,
|
|
"step": 6700
|
|
},
|
|
{
|
|
"entropy": 5.663140916824341,
|
|
"epoch": 0.6654426359666534,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0004963790944476167,
|
|
"loss": 5.4238,
|
|
"mean_token_accuracy": 0.15778421014547347,
|
|
"num_tokens": 14715370.0,
|
|
"step": 6705
|
|
},
|
|
{
|
|
"entropy": 5.676147842407227,
|
|
"epoch": 0.665938864628821,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004963727607730303,
|
|
"loss": 5.4436,
|
|
"mean_token_accuracy": 0.15048911571502685,
|
|
"num_tokens": 14725481.0,
|
|
"step": 6710
|
|
},
|
|
{
|
|
"entropy": 5.605512475967407,
|
|
"epoch": 0.6664350932909885,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.0004963664216088764,
|
|
"loss": 5.3706,
|
|
"mean_token_accuracy": 0.1536024570465088,
|
|
"num_tokens": 14735250.0,
|
|
"step": 6715
|
|
},
|
|
{
|
|
"entropy": 5.615908527374268,
|
|
"epoch": 0.666931321953156,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004963600769553124,
|
|
"loss": 5.3774,
|
|
"mean_token_accuracy": 0.15871376693248748,
|
|
"num_tokens": 14744741.0,
|
|
"step": 6720
|
|
},
|
|
{
|
|
"entropy": 5.659100103378296,
|
|
"epoch": 0.6674275506153236,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.0004963537268124953,
|
|
"loss": 5.409,
|
|
"mean_token_accuracy": 0.15116407573223115,
|
|
"num_tokens": 14755865.0,
|
|
"step": 6725
|
|
},
|
|
{
|
|
"entropy": 5.574926137924194,
|
|
"epoch": 0.667923779277491,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004963473711805829,
|
|
"loss": 5.3635,
|
|
"mean_token_accuracy": 0.1572342410683632,
|
|
"num_tokens": 14766154.0,
|
|
"step": 6730
|
|
},
|
|
{
|
|
"entropy": 5.636857652664185,
|
|
"epoch": 0.6684200079396586,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004963410100597326,
|
|
"loss": 5.4038,
|
|
"mean_token_accuracy": 0.15145311057567595,
|
|
"num_tokens": 14776940.0,
|
|
"step": 6735
|
|
},
|
|
{
|
|
"entropy": 5.624228191375733,
|
|
"epoch": 0.6689162366018261,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004963346434501021,
|
|
"loss": 5.5153,
|
|
"mean_token_accuracy": 0.14711894020438193,
|
|
"num_tokens": 14788367.0,
|
|
"step": 6740
|
|
},
|
|
{
|
|
"entropy": 5.558290672302246,
|
|
"epoch": 0.6694124652639937,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004963282713518495,
|
|
"loss": 5.427,
|
|
"mean_token_accuracy": 0.15619889050722122,
|
|
"num_tokens": 14798751.0,
|
|
"step": 6745
|
|
},
|
|
{
|
|
"entropy": 5.571211624145508,
|
|
"epoch": 0.6699086939261611,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004963218937651326,
|
|
"loss": 5.3549,
|
|
"mean_token_accuracy": 0.15779270827770234,
|
|
"num_tokens": 14808748.0,
|
|
"step": 6750
|
|
},
|
|
{
|
|
"entropy": 5.694025945663452,
|
|
"epoch": 0.6704049225883287,
|
|
"grad_norm": 0.77734375,
|
|
"learning_rate": 0.0004963155106901098,
|
|
"loss": 5.5211,
|
|
"mean_token_accuracy": 0.14606630355119704,
|
|
"num_tokens": 14820524.0,
|
|
"step": 6755
|
|
},
|
|
{
|
|
"entropy": 5.737807846069336,
|
|
"epoch": 0.6709011512504962,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004963091221269391,
|
|
"loss": 5.5529,
|
|
"mean_token_accuracy": 0.1397723875939846,
|
|
"num_tokens": 14832485.0,
|
|
"step": 6760
|
|
},
|
|
{
|
|
"entropy": 5.638651561737061,
|
|
"epoch": 0.6713973799126638,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.000496302728075779,
|
|
"loss": 5.3592,
|
|
"mean_token_accuracy": 0.1506928727030754,
|
|
"num_tokens": 14843951.0,
|
|
"step": 6765
|
|
},
|
|
{
|
|
"entropy": 5.599717283248902,
|
|
"epoch": 0.6718936085748313,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004962963285367882,
|
|
"loss": 5.4688,
|
|
"mean_token_accuracy": 0.1526104286313057,
|
|
"num_tokens": 14855502.0,
|
|
"step": 6770
|
|
},
|
|
{
|
|
"entropy": 5.599081659317017,
|
|
"epoch": 0.6723898372369989,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.0004962899235101253,
|
|
"loss": 5.3763,
|
|
"mean_token_accuracy": 0.15440474897623063,
|
|
"num_tokens": 14866305.0,
|
|
"step": 6775
|
|
},
|
|
{
|
|
"entropy": 5.632352066040039,
|
|
"epoch": 0.6728860658991663,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004962835129959491,
|
|
"loss": 5.3947,
|
|
"mean_token_accuracy": 0.14619243144989014,
|
|
"num_tokens": 14877222.0,
|
|
"step": 6780
|
|
},
|
|
{
|
|
"entropy": 5.59601092338562,
|
|
"epoch": 0.6733822945613339,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004962770969944186,
|
|
"loss": 5.4778,
|
|
"mean_token_accuracy": 0.14912765175104142,
|
|
"num_tokens": 14888099.0,
|
|
"step": 6785
|
|
},
|
|
{
|
|
"entropy": 5.617529344558716,
|
|
"epoch": 0.6738785232235014,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.000496270675505693,
|
|
"loss": 5.3948,
|
|
"mean_token_accuracy": 0.15923409014940262,
|
|
"num_tokens": 14899042.0,
|
|
"step": 6790
|
|
},
|
|
{
|
|
"entropy": 5.664507579803467,
|
|
"epoch": 0.6743747518856689,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004962642485299314,
|
|
"loss": 5.4518,
|
|
"mean_token_accuracy": 0.14887820482254027,
|
|
"num_tokens": 14908837.0,
|
|
"step": 6795
|
|
},
|
|
{
|
|
"entropy": 5.581243324279785,
|
|
"epoch": 0.6748709805478365,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004962578160672931,
|
|
"loss": 5.3936,
|
|
"mean_token_accuracy": 0.15571052581071854,
|
|
"num_tokens": 14920773.0,
|
|
"step": 6800
|
|
},
|
|
{
|
|
"entropy": 5.607238864898681,
|
|
"epoch": 0.6753672092100039,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004962513781179379,
|
|
"loss": 5.3926,
|
|
"mean_token_accuracy": 0.15196526497602464,
|
|
"num_tokens": 14930970.0,
|
|
"step": 6805
|
|
},
|
|
{
|
|
"entropy": 5.623500776290894,
|
|
"epoch": 0.6758634378721715,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004962449346820251,
|
|
"loss": 5.4507,
|
|
"mean_token_accuracy": 0.148509182035923,
|
|
"num_tokens": 14942378.0,
|
|
"step": 6810
|
|
},
|
|
{
|
|
"entropy": 5.616042423248291,
|
|
"epoch": 0.676359666534339,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004962384857597148,
|
|
"loss": 5.4876,
|
|
"mean_token_accuracy": 0.14774132370948792,
|
|
"num_tokens": 14953020.0,
|
|
"step": 6815
|
|
},
|
|
{
|
|
"entropy": 5.712278175354004,
|
|
"epoch": 0.6768558951965066,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004962320313511668,
|
|
"loss": 5.5508,
|
|
"mean_token_accuracy": 0.1478928282856941,
|
|
"num_tokens": 14962340.0,
|
|
"step": 6820
|
|
},
|
|
{
|
|
"entropy": 5.709672260284424,
|
|
"epoch": 0.677352123858674,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004962255714565409,
|
|
"loss": 5.4271,
|
|
"mean_token_accuracy": 0.15248478353023528,
|
|
"num_tokens": 14972792.0,
|
|
"step": 6825
|
|
},
|
|
{
|
|
"entropy": 5.645695447921753,
|
|
"epoch": 0.6778483525208416,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004962191060759978,
|
|
"loss": 5.425,
|
|
"mean_token_accuracy": 0.15230261087417601,
|
|
"num_tokens": 14983698.0,
|
|
"step": 6830
|
|
},
|
|
{
|
|
"entropy": 5.651081132888794,
|
|
"epoch": 0.6783445811830091,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004962126352096973,
|
|
"loss": 5.3993,
|
|
"mean_token_accuracy": 0.151994052529335,
|
|
"num_tokens": 14994583.0,
|
|
"step": 6835
|
|
},
|
|
{
|
|
"entropy": 5.557571125030518,
|
|
"epoch": 0.6788408098451767,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004962061588578004,
|
|
"loss": 5.3352,
|
|
"mean_token_accuracy": 0.15464683324098588,
|
|
"num_tokens": 15005325.0,
|
|
"step": 6840
|
|
},
|
|
{
|
|
"entropy": 5.658808660507202,
|
|
"epoch": 0.6793370385073442,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004961996770204673,
|
|
"loss": 5.4081,
|
|
"mean_token_accuracy": 0.1543305680155754,
|
|
"num_tokens": 15015155.0,
|
|
"step": 6845
|
|
},
|
|
{
|
|
"entropy": 5.643760108947754,
|
|
"epoch": 0.6798332671695118,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004961931896978588,
|
|
"loss": 5.472,
|
|
"mean_token_accuracy": 0.14792029708623886,
|
|
"num_tokens": 15026529.0,
|
|
"step": 6850
|
|
},
|
|
{
|
|
"entropy": 5.5619231224060055,
|
|
"epoch": 0.6803294958316792,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004961866968901359,
|
|
"loss": 5.3866,
|
|
"mean_token_accuracy": 0.15590434223413469,
|
|
"num_tokens": 15037632.0,
|
|
"step": 6855
|
|
},
|
|
{
|
|
"entropy": 5.61463098526001,
|
|
"epoch": 0.6808257244938468,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004961801985974595,
|
|
"loss": 5.4668,
|
|
"mean_token_accuracy": 0.1518971860408783,
|
|
"num_tokens": 15050397.0,
|
|
"step": 6860
|
|
},
|
|
{
|
|
"entropy": 5.609272766113281,
|
|
"epoch": 0.6813219531560143,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.0004961736948199907,
|
|
"loss": 5.3782,
|
|
"mean_token_accuracy": 0.1546167850494385,
|
|
"num_tokens": 15061505.0,
|
|
"step": 6865
|
|
},
|
|
{
|
|
"entropy": 5.7006994724273685,
|
|
"epoch": 0.6818181818181818,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004961671855578909,
|
|
"loss": 5.5625,
|
|
"mean_token_accuracy": 0.147130286693573,
|
|
"num_tokens": 15073752.0,
|
|
"step": 6870
|
|
},
|
|
{
|
|
"entropy": 5.666177415847779,
|
|
"epoch": 0.6823144104803494,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0004961606708113216,
|
|
"loss": 5.4674,
|
|
"mean_token_accuracy": 0.14928337261080743,
|
|
"num_tokens": 15084730.0,
|
|
"step": 6875
|
|
},
|
|
{
|
|
"entropy": 5.645604085922241,
|
|
"epoch": 0.6828106391425168,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004961541505804441,
|
|
"loss": 5.371,
|
|
"mean_token_accuracy": 0.15932557433843614,
|
|
"num_tokens": 15095811.0,
|
|
"step": 6880
|
|
},
|
|
{
|
|
"entropy": 5.6254149913787845,
|
|
"epoch": 0.6833068678046844,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004961476248654202,
|
|
"loss": 5.3637,
|
|
"mean_token_accuracy": 0.1530770927667618,
|
|
"num_tokens": 15106102.0,
|
|
"step": 6885
|
|
},
|
|
{
|
|
"entropy": 5.635340595245362,
|
|
"epoch": 0.6838030964668519,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004961410936664118,
|
|
"loss": 5.4507,
|
|
"mean_token_accuracy": 0.14996094182133674,
|
|
"num_tokens": 15115907.0,
|
|
"step": 6890
|
|
},
|
|
{
|
|
"entropy": 5.613401889801025,
|
|
"epoch": 0.6842993251290195,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004961345569835807,
|
|
"loss": 5.4362,
|
|
"mean_token_accuracy": 0.14937734454870225,
|
|
"num_tokens": 15126788.0,
|
|
"step": 6895
|
|
},
|
|
{
|
|
"entropy": 5.6303540706634525,
|
|
"epoch": 0.684795553791187,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004961280148170892,
|
|
"loss": 5.3864,
|
|
"mean_token_accuracy": 0.1516811415553093,
|
|
"num_tokens": 15137814.0,
|
|
"step": 6900
|
|
},
|
|
{
|
|
"entropy": 5.699887800216675,
|
|
"epoch": 0.6852917824533545,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004961214671670994,
|
|
"loss": 5.6138,
|
|
"mean_token_accuracy": 0.1388474315404892,
|
|
"num_tokens": 15148597.0,
|
|
"step": 6905
|
|
},
|
|
{
|
|
"entropy": 5.662448787689209,
|
|
"epoch": 0.685788011115522,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004961149140337737,
|
|
"loss": 5.4277,
|
|
"mean_token_accuracy": 0.1468920439481735,
|
|
"num_tokens": 15158985.0,
|
|
"step": 6910
|
|
},
|
|
{
|
|
"entropy": 5.618693494796753,
|
|
"epoch": 0.6862842397776896,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004961083554172745,
|
|
"loss": 5.4185,
|
|
"mean_token_accuracy": 0.15202739387750625,
|
|
"num_tokens": 15170242.0,
|
|
"step": 6915
|
|
},
|
|
{
|
|
"entropy": 5.596062803268433,
|
|
"epoch": 0.6867804684398571,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004961017913177646,
|
|
"loss": 5.3707,
|
|
"mean_token_accuracy": 0.1583961695432663,
|
|
"num_tokens": 15180353.0,
|
|
"step": 6920
|
|
},
|
|
{
|
|
"entropy": 5.544697618484497,
|
|
"epoch": 0.6872766971020247,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004960952217354066,
|
|
"loss": 5.3256,
|
|
"mean_token_accuracy": 0.16041142493486404,
|
|
"num_tokens": 15191955.0,
|
|
"step": 6925
|
|
},
|
|
{
|
|
"entropy": 5.5882710933685305,
|
|
"epoch": 0.6877729257641921,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004960886466703636,
|
|
"loss": 5.411,
|
|
"mean_token_accuracy": 0.15261018127202988,
|
|
"num_tokens": 15202088.0,
|
|
"step": 6930
|
|
},
|
|
{
|
|
"entropy": 5.533545112609863,
|
|
"epoch": 0.6882691544263597,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004960820661227987,
|
|
"loss": 5.3694,
|
|
"mean_token_accuracy": 0.15650452077388763,
|
|
"num_tokens": 15212291.0,
|
|
"step": 6935
|
|
},
|
|
{
|
|
"entropy": 5.591097450256347,
|
|
"epoch": 0.6887653830885272,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004960754800928748,
|
|
"loss": 5.4021,
|
|
"mean_token_accuracy": 0.15690786093473436,
|
|
"num_tokens": 15223315.0,
|
|
"step": 6940
|
|
},
|
|
{
|
|
"entropy": 5.718151521682739,
|
|
"epoch": 0.6892616117506947,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004960688885807553,
|
|
"loss": 5.52,
|
|
"mean_token_accuracy": 0.15194137990474701,
|
|
"num_tokens": 15233416.0,
|
|
"step": 6945
|
|
},
|
|
{
|
|
"entropy": 5.639258575439453,
|
|
"epoch": 0.6897578404128623,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004960622915866038,
|
|
"loss": 5.3451,
|
|
"mean_token_accuracy": 0.16188562661409378,
|
|
"num_tokens": 15242951.0,
|
|
"step": 6950
|
|
},
|
|
{
|
|
"entropy": 5.5644447803497314,
|
|
"epoch": 0.6902540690750297,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004960556891105839,
|
|
"loss": 5.4409,
|
|
"mean_token_accuracy": 0.1520864710211754,
|
|
"num_tokens": 15253145.0,
|
|
"step": 6955
|
|
},
|
|
{
|
|
"entropy": 5.5503040790557865,
|
|
"epoch": 0.6907502977371973,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004960490811528591,
|
|
"loss": 5.3893,
|
|
"mean_token_accuracy": 0.15682558864355087,
|
|
"num_tokens": 15263712.0,
|
|
"step": 6960
|
|
},
|
|
{
|
|
"entropy": 5.753786373138428,
|
|
"epoch": 0.6912465263993648,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004960424677135935,
|
|
"loss": 5.5061,
|
|
"mean_token_accuracy": 0.15282690972089769,
|
|
"num_tokens": 15273609.0,
|
|
"step": 6965
|
|
},
|
|
{
|
|
"entropy": 5.620067453384399,
|
|
"epoch": 0.6917427550615324,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004960358487929511,
|
|
"loss": 5.3677,
|
|
"mean_token_accuracy": 0.16024328172206878,
|
|
"num_tokens": 15283934.0,
|
|
"step": 6970
|
|
},
|
|
{
|
|
"entropy": 5.573494482040405,
|
|
"epoch": 0.6922389837236999,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004960292243910958,
|
|
"loss": 5.4345,
|
|
"mean_token_accuracy": 0.1531072050333023,
|
|
"num_tokens": 15294394.0,
|
|
"step": 6975
|
|
},
|
|
{
|
|
"entropy": 5.604720544815064,
|
|
"epoch": 0.6927352123858674,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.000496022594508192,
|
|
"loss": 5.3812,
|
|
"mean_token_accuracy": 0.16022567003965377,
|
|
"num_tokens": 15304622.0,
|
|
"step": 6980
|
|
},
|
|
{
|
|
"entropy": 5.60088357925415,
|
|
"epoch": 0.6932314410480349,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004960159591444041,
|
|
"loss": 5.2983,
|
|
"mean_token_accuracy": 0.16009942144155503,
|
|
"num_tokens": 15314094.0,
|
|
"step": 6985
|
|
},
|
|
{
|
|
"entropy": 5.567172193527222,
|
|
"epoch": 0.6937276697102025,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004960093182998968,
|
|
"loss": 5.4139,
|
|
"mean_token_accuracy": 0.15786027461290358,
|
|
"num_tokens": 15324313.0,
|
|
"step": 6990
|
|
},
|
|
{
|
|
"entropy": 5.530042266845703,
|
|
"epoch": 0.69422389837237,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004960026719748346,
|
|
"loss": 5.2982,
|
|
"mean_token_accuracy": 0.17230096459388733,
|
|
"num_tokens": 15335195.0,
|
|
"step": 6995
|
|
},
|
|
{
|
|
"entropy": 5.735844707489013,
|
|
"epoch": 0.6947201270345376,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004959960201693822,
|
|
"loss": 5.5125,
|
|
"mean_token_accuracy": 0.15034665167331696,
|
|
"num_tokens": 15345798.0,
|
|
"step": 7000
|
|
},
|
|
{
|
|
"entropy": 5.632916975021362,
|
|
"epoch": 0.695216355696705,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004959893628837048,
|
|
"loss": 5.3691,
|
|
"mean_token_accuracy": 0.15174235850572587,
|
|
"num_tokens": 15356340.0,
|
|
"step": 7005
|
|
},
|
|
{
|
|
"entropy": 5.639342164993286,
|
|
"epoch": 0.6957125843588726,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004959827001179675,
|
|
"loss": 5.4657,
|
|
"mean_token_accuracy": 0.14688759297132492,
|
|
"num_tokens": 15367795.0,
|
|
"step": 7010
|
|
},
|
|
{
|
|
"entropy": 5.632861709594726,
|
|
"epoch": 0.6962088130210401,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004959760318723353,
|
|
"loss": 5.5909,
|
|
"mean_token_accuracy": 0.1438564896583557,
|
|
"num_tokens": 15379214.0,
|
|
"step": 7015
|
|
},
|
|
{
|
|
"entropy": 5.636499547958374,
|
|
"epoch": 0.6967050416832076,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004959693581469736,
|
|
"loss": 5.4438,
|
|
"mean_token_accuracy": 0.1585008829832077,
|
|
"num_tokens": 15390242.0,
|
|
"step": 7020
|
|
},
|
|
{
|
|
"entropy": 5.600987768173217,
|
|
"epoch": 0.6972012703453752,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004959626789420481,
|
|
"loss": 5.3733,
|
|
"mean_token_accuracy": 0.1531446322798729,
|
|
"num_tokens": 15402600.0,
|
|
"step": 7025
|
|
},
|
|
{
|
|
"entropy": 5.60857572555542,
|
|
"epoch": 0.6976974990075426,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004959559942577243,
|
|
"loss": 5.4076,
|
|
"mean_token_accuracy": 0.15517537593841552,
|
|
"num_tokens": 15412883.0,
|
|
"step": 7030
|
|
},
|
|
{
|
|
"entropy": 5.653280925750733,
|
|
"epoch": 0.6981937276697102,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.0004959493040941678,
|
|
"loss": 5.4398,
|
|
"mean_token_accuracy": 0.149055640399456,
|
|
"num_tokens": 15425919.0,
|
|
"step": 7035
|
|
},
|
|
{
|
|
"entropy": 5.598724746704102,
|
|
"epoch": 0.6986899563318777,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004959426084515448,
|
|
"loss": 5.3766,
|
|
"mean_token_accuracy": 0.15377127379179,
|
|
"num_tokens": 15437604.0,
|
|
"step": 7040
|
|
},
|
|
{
|
|
"entropy": 5.588111400604248,
|
|
"epoch": 0.6991861849940453,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004959359073300212,
|
|
"loss": 5.442,
|
|
"mean_token_accuracy": 0.1484801024198532,
|
|
"num_tokens": 15449023.0,
|
|
"step": 7045
|
|
},
|
|
{
|
|
"entropy": 5.67562313079834,
|
|
"epoch": 0.6996824136562128,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004959292007297631,
|
|
"loss": 5.4976,
|
|
"mean_token_accuracy": 0.15364296585321427,
|
|
"num_tokens": 15459567.0,
|
|
"step": 7050
|
|
},
|
|
{
|
|
"entropy": 5.648920297622681,
|
|
"epoch": 0.7001786423183803,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.000495922488650937,
|
|
"loss": 5.409,
|
|
"mean_token_accuracy": 0.156674388051033,
|
|
"num_tokens": 15470950.0,
|
|
"step": 7055
|
|
},
|
|
{
|
|
"entropy": 5.588835096359253,
|
|
"epoch": 0.7006748709805478,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004959157710937092,
|
|
"loss": 5.4154,
|
|
"mean_token_accuracy": 0.15452724248170852,
|
|
"num_tokens": 15481258.0,
|
|
"step": 7060
|
|
},
|
|
{
|
|
"entropy": 5.636629056930542,
|
|
"epoch": 0.7011710996427154,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.0004959090480582462,
|
|
"loss": 5.3459,
|
|
"mean_token_accuracy": 0.15606230050325393,
|
|
"num_tokens": 15491672.0,
|
|
"step": 7065
|
|
},
|
|
{
|
|
"entropy": 5.559443807601928,
|
|
"epoch": 0.7016673283048829,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004959023195447148,
|
|
"loss": 5.4015,
|
|
"mean_token_accuracy": 0.15582506060600282,
|
|
"num_tokens": 15502342.0,
|
|
"step": 7070
|
|
},
|
|
{
|
|
"entropy": 5.6122541427612305,
|
|
"epoch": 0.7021635569670505,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.000495895585553282,
|
|
"loss": 5.4419,
|
|
"mean_token_accuracy": 0.1493886798620224,
|
|
"num_tokens": 15513430.0,
|
|
"step": 7075
|
|
},
|
|
{
|
|
"entropy": 5.807034015655518,
|
|
"epoch": 0.7026597856292179,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004958888460841147,
|
|
"loss": 5.543,
|
|
"mean_token_accuracy": 0.1481260783970356,
|
|
"num_tokens": 15524889.0,
|
|
"step": 7080
|
|
},
|
|
{
|
|
"entropy": 5.5820581912994385,
|
|
"epoch": 0.7031560142913855,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004958821011373798,
|
|
"loss": 5.3579,
|
|
"mean_token_accuracy": 0.15555054545402527,
|
|
"num_tokens": 15534998.0,
|
|
"step": 7085
|
|
},
|
|
{
|
|
"entropy": 5.565367937088013,
|
|
"epoch": 0.703652242953553,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004958753507132449,
|
|
"loss": 5.3706,
|
|
"mean_token_accuracy": 0.15571859925985337,
|
|
"num_tokens": 15544752.0,
|
|
"step": 7090
|
|
},
|
|
{
|
|
"entropy": 5.614150714874268,
|
|
"epoch": 0.7041484716157205,
|
|
"grad_norm": 0.78125,
|
|
"learning_rate": 0.0004958685948118772,
|
|
"loss": 5.3921,
|
|
"mean_token_accuracy": 0.15620832443237304,
|
|
"num_tokens": 15555490.0,
|
|
"step": 7095
|
|
},
|
|
{
|
|
"entropy": 5.582898569107056,
|
|
"epoch": 0.7046447002778881,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004958618334334443,
|
|
"loss": 5.3252,
|
|
"mean_token_accuracy": 0.1558916062116623,
|
|
"num_tokens": 15565752.0,
|
|
"step": 7100
|
|
},
|
|
{
|
|
"entropy": 5.594721269607544,
|
|
"epoch": 0.7051409289400555,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004958550665781138,
|
|
"loss": 5.4522,
|
|
"mean_token_accuracy": 0.15302032232284546,
|
|
"num_tokens": 15576368.0,
|
|
"step": 7105
|
|
},
|
|
{
|
|
"entropy": 5.696494007110596,
|
|
"epoch": 0.7056371576022231,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004958482942460536,
|
|
"loss": 5.4426,
|
|
"mean_token_accuracy": 0.15190984383225442,
|
|
"num_tokens": 15587972.0,
|
|
"step": 7110
|
|
},
|
|
{
|
|
"entropy": 5.705682229995728,
|
|
"epoch": 0.7061333862643906,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004958415164374316,
|
|
"loss": 5.4789,
|
|
"mean_token_accuracy": 0.15410581678152085,
|
|
"num_tokens": 15599951.0,
|
|
"step": 7115
|
|
},
|
|
{
|
|
"entropy": 5.595183038711548,
|
|
"epoch": 0.7066296149265582,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004958347331524158,
|
|
"loss": 5.4646,
|
|
"mean_token_accuracy": 0.1483406215906143,
|
|
"num_tokens": 15610183.0,
|
|
"step": 7120
|
|
},
|
|
{
|
|
"entropy": 5.609962606430054,
|
|
"epoch": 0.7071258435887257,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004958279443911745,
|
|
"loss": 5.484,
|
|
"mean_token_accuracy": 0.14564593136310577,
|
|
"num_tokens": 15621074.0,
|
|
"step": 7125
|
|
},
|
|
{
|
|
"entropy": 5.703958988189697,
|
|
"epoch": 0.7076220722508932,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.000495821150153876,
|
|
"loss": 5.48,
|
|
"mean_token_accuracy": 0.14798002392053605,
|
|
"num_tokens": 15632752.0,
|
|
"step": 7130
|
|
},
|
|
{
|
|
"entropy": 5.608168315887451,
|
|
"epoch": 0.7081183009130607,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.000495814350440689,
|
|
"loss": 5.4443,
|
|
"mean_token_accuracy": 0.14783835858106614,
|
|
"num_tokens": 15644703.0,
|
|
"step": 7135
|
|
},
|
|
{
|
|
"entropy": 5.590032243728638,
|
|
"epoch": 0.7086145295752283,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004958075452517816,
|
|
"loss": 5.4155,
|
|
"mean_token_accuracy": 0.15188954621553422,
|
|
"num_tokens": 15655278.0,
|
|
"step": 7140
|
|
},
|
|
{
|
|
"entropy": 5.609332180023193,
|
|
"epoch": 0.7091107582373958,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004958007345873232,
|
|
"loss": 5.4376,
|
|
"mean_token_accuracy": 0.1562029853463173,
|
|
"num_tokens": 15665998.0,
|
|
"step": 7145
|
|
},
|
|
{
|
|
"entropy": 5.614063835144043,
|
|
"epoch": 0.7096069868995634,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004957939184474821,
|
|
"loss": 5.3326,
|
|
"mean_token_accuracy": 0.15620039105415345,
|
|
"num_tokens": 15676343.0,
|
|
"step": 7150
|
|
},
|
|
{
|
|
"entropy": 5.6093193054199215,
|
|
"epoch": 0.7101032155617308,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004957870968324277,
|
|
"loss": 5.4335,
|
|
"mean_token_accuracy": 0.14923603609204292,
|
|
"num_tokens": 15686520.0,
|
|
"step": 7155
|
|
},
|
|
{
|
|
"entropy": 5.624302196502685,
|
|
"epoch": 0.7105994442238984,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004957802697423291,
|
|
"loss": 5.5335,
|
|
"mean_token_accuracy": 0.14949338436126708,
|
|
"num_tokens": 15698302.0,
|
|
"step": 7160
|
|
},
|
|
{
|
|
"entropy": 5.577978181838989,
|
|
"epoch": 0.7110956728860659,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004957734371773554,
|
|
"loss": 5.2967,
|
|
"mean_token_accuracy": 0.15855092704296112,
|
|
"num_tokens": 15708462.0,
|
|
"step": 7165
|
|
},
|
|
{
|
|
"entropy": 5.615873384475708,
|
|
"epoch": 0.7115919015482334,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004957665991376763,
|
|
"loss": 5.4112,
|
|
"mean_token_accuracy": 0.15870108604431152,
|
|
"num_tokens": 15719234.0,
|
|
"step": 7170
|
|
},
|
|
{
|
|
"entropy": 5.5790088176727295,
|
|
"epoch": 0.712088130210401,
|
|
"grad_norm": 0.76953125,
|
|
"learning_rate": 0.0004957597556234613,
|
|
"loss": 5.4382,
|
|
"mean_token_accuracy": 0.14830014258623123,
|
|
"num_tokens": 15732245.0,
|
|
"step": 7175
|
|
},
|
|
{
|
|
"entropy": 5.621543312072754,
|
|
"epoch": 0.7125843588725684,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004957529066348799,
|
|
"loss": 5.4147,
|
|
"mean_token_accuracy": 0.15519314706325532,
|
|
"num_tokens": 15742403.0,
|
|
"step": 7180
|
|
},
|
|
{
|
|
"entropy": 5.536786890029907,
|
|
"epoch": 0.713080587534736,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004957460521721022,
|
|
"loss": 5.3183,
|
|
"mean_token_accuracy": 0.16017779111862182,
|
|
"num_tokens": 15752100.0,
|
|
"step": 7185
|
|
},
|
|
{
|
|
"entropy": 5.575576448440552,
|
|
"epoch": 0.7135768161969035,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.000495739192235298,
|
|
"loss": 5.4034,
|
|
"mean_token_accuracy": 0.15700195580720902,
|
|
"num_tokens": 15762315.0,
|
|
"step": 7190
|
|
},
|
|
{
|
|
"entropy": 5.581356811523437,
|
|
"epoch": 0.7140730448590711,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004957323268246376,
|
|
"loss": 5.4223,
|
|
"mean_token_accuracy": 0.15435817688703538,
|
|
"num_tokens": 15773841.0,
|
|
"step": 7195
|
|
},
|
|
{
|
|
"entropy": 5.6099649429321286,
|
|
"epoch": 0.7145692735212386,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004957254559402911,
|
|
"loss": 5.3688,
|
|
"mean_token_accuracy": 0.15388270914554597,
|
|
"num_tokens": 15785511.0,
|
|
"step": 7200
|
|
},
|
|
{
|
|
"entropy": 5.574761009216308,
|
|
"epoch": 0.7150655021834061,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004957185795824288,
|
|
"loss": 5.4027,
|
|
"mean_token_accuracy": 0.14808241724967958,
|
|
"num_tokens": 15795394.0,
|
|
"step": 7205
|
|
},
|
|
{
|
|
"entropy": 5.578614854812622,
|
|
"epoch": 0.7155617308455736,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0004957116977512214,
|
|
"loss": 5.3716,
|
|
"mean_token_accuracy": 0.15402503162622452,
|
|
"num_tokens": 15805894.0,
|
|
"step": 7210
|
|
},
|
|
{
|
|
"entropy": 5.67041802406311,
|
|
"epoch": 0.7160579595077412,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004957048104468395,
|
|
"loss": 5.4228,
|
|
"mean_token_accuracy": 0.14573368281126023,
|
|
"num_tokens": 15816595.0,
|
|
"step": 7215
|
|
},
|
|
{
|
|
"entropy": 5.591230201721191,
|
|
"epoch": 0.7165541881699087,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0004956979176694539,
|
|
"loss": 5.3706,
|
|
"mean_token_accuracy": 0.1590556561946869,
|
|
"num_tokens": 15827638.0,
|
|
"step": 7220
|
|
},
|
|
{
|
|
"entropy": 5.582176876068115,
|
|
"epoch": 0.7170504168320763,
|
|
"grad_norm": 0.78125,
|
|
"learning_rate": 0.0004956910194192355,
|
|
"loss": 5.4427,
|
|
"mean_token_accuracy": 0.15021601766347886,
|
|
"num_tokens": 15838437.0,
|
|
"step": 7225
|
|
},
|
|
{
|
|
"entropy": 5.712309551239014,
|
|
"epoch": 0.7175466454942437,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.0004956841156963553,
|
|
"loss": 5.5378,
|
|
"mean_token_accuracy": 0.15349817723035813,
|
|
"num_tokens": 15850110.0,
|
|
"step": 7230
|
|
},
|
|
{
|
|
"entropy": 5.600798845291138,
|
|
"epoch": 0.7180428741564113,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004956772065009846,
|
|
"loss": 5.4096,
|
|
"mean_token_accuracy": 0.14814347252249718,
|
|
"num_tokens": 15861786.0,
|
|
"step": 7235
|
|
},
|
|
{
|
|
"entropy": 5.612291049957276,
|
|
"epoch": 0.7185391028185788,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004956702918332948,
|
|
"loss": 5.3802,
|
|
"mean_token_accuracy": 0.15146298035979272,
|
|
"num_tokens": 15871574.0,
|
|
"step": 7240
|
|
},
|
|
{
|
|
"entropy": 5.6134391784667965,
|
|
"epoch": 0.7190353314807463,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004956633716934572,
|
|
"loss": 5.3772,
|
|
"mean_token_accuracy": 0.15983042120933533,
|
|
"num_tokens": 15881944.0,
|
|
"step": 7245
|
|
},
|
|
{
|
|
"entropy": 5.58657751083374,
|
|
"epoch": 0.7195315601429139,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004956564460816433,
|
|
"loss": 5.3772,
|
|
"mean_token_accuracy": 0.1547867901623249,
|
|
"num_tokens": 15892511.0,
|
|
"step": 7250
|
|
},
|
|
{
|
|
"entropy": 5.601710176467895,
|
|
"epoch": 0.7200277888050813,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004956495149980252,
|
|
"loss": 5.3936,
|
|
"mean_token_accuracy": 0.14862362146377564,
|
|
"num_tokens": 15903387.0,
|
|
"step": 7255
|
|
},
|
|
{
|
|
"entropy": 5.620168542861938,
|
|
"epoch": 0.7205240174672489,
|
|
"grad_norm": 0.796875,
|
|
"learning_rate": 0.0004956425784427745,
|
|
"loss": 5.437,
|
|
"mean_token_accuracy": 0.15066849887371064,
|
|
"num_tokens": 15915117.0,
|
|
"step": 7260
|
|
},
|
|
{
|
|
"entropy": 5.559117650985717,
|
|
"epoch": 0.7210202461294164,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004956356364160634,
|
|
"loss": 5.3937,
|
|
"mean_token_accuracy": 0.1504781186580658,
|
|
"num_tokens": 15925163.0,
|
|
"step": 7265
|
|
},
|
|
{
|
|
"entropy": 5.514855098724365,
|
|
"epoch": 0.721516474791584,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004956286889180639,
|
|
"loss": 5.2844,
|
|
"mean_token_accuracy": 0.16543339639902116,
|
|
"num_tokens": 15935021.0,
|
|
"step": 7270
|
|
},
|
|
{
|
|
"entropy": 5.568548679351807,
|
|
"epoch": 0.7220127034537515,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004956217359489483,
|
|
"loss": 5.407,
|
|
"mean_token_accuracy": 0.14721074551343918,
|
|
"num_tokens": 15945416.0,
|
|
"step": 7275
|
|
},
|
|
{
|
|
"entropy": 5.690412378311157,
|
|
"epoch": 0.722508932115919,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.000495614777508889,
|
|
"loss": 5.5183,
|
|
"mean_token_accuracy": 0.14687851220369338,
|
|
"num_tokens": 15955388.0,
|
|
"step": 7280
|
|
},
|
|
{
|
|
"entropy": 5.701138687133789,
|
|
"epoch": 0.7230051607780865,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004956078135980586,
|
|
"loss": 5.5243,
|
|
"mean_token_accuracy": 0.14872784465551375,
|
|
"num_tokens": 15966721.0,
|
|
"step": 7285
|
|
},
|
|
{
|
|
"entropy": 5.627881479263306,
|
|
"epoch": 0.7235013894402541,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004956008442166299,
|
|
"loss": 5.4569,
|
|
"mean_token_accuracy": 0.15040554478764534,
|
|
"num_tokens": 15976388.0,
|
|
"step": 7290
|
|
},
|
|
{
|
|
"entropy": 5.589539098739624,
|
|
"epoch": 0.7239976181024216,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004955938693647756,
|
|
"loss": 5.3362,
|
|
"mean_token_accuracy": 0.1562737390398979,
|
|
"num_tokens": 15986632.0,
|
|
"step": 7295
|
|
},
|
|
{
|
|
"entropy": 5.5868932723999025,
|
|
"epoch": 0.7244938467645892,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004955868890426686,
|
|
"loss": 5.3907,
|
|
"mean_token_accuracy": 0.14940914288163185,
|
|
"num_tokens": 15996626.0,
|
|
"step": 7300
|
|
},
|
|
{
|
|
"entropy": 5.561647605895996,
|
|
"epoch": 0.7249900754267566,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.0004955799032504821,
|
|
"loss": 5.3716,
|
|
"mean_token_accuracy": 0.15110146403312683,
|
|
"num_tokens": 16007055.0,
|
|
"step": 7305
|
|
},
|
|
{
|
|
"entropy": 5.682785081863403,
|
|
"epoch": 0.7254863040889242,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004955729119883893,
|
|
"loss": 5.4265,
|
|
"mean_token_accuracy": 0.15077741891145707,
|
|
"num_tokens": 16019087.0,
|
|
"step": 7310
|
|
},
|
|
{
|
|
"entropy": 5.6372357368469235,
|
|
"epoch": 0.7259825327510917,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004955659152565636,
|
|
"loss": 5.433,
|
|
"mean_token_accuracy": 0.14655008614063264,
|
|
"num_tokens": 16029980.0,
|
|
"step": 7315
|
|
},
|
|
{
|
|
"entropy": 5.614037990570068,
|
|
"epoch": 0.7264787614132592,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.0004955589130551784,
|
|
"loss": 5.4099,
|
|
"mean_token_accuracy": 0.15711937397718428,
|
|
"num_tokens": 16040932.0,
|
|
"step": 7320
|
|
},
|
|
{
|
|
"entropy": 5.526982545852661,
|
|
"epoch": 0.7269749900754268,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004955519053844076,
|
|
"loss": 5.3706,
|
|
"mean_token_accuracy": 0.1539077416062355,
|
|
"num_tokens": 16051809.0,
|
|
"step": 7325
|
|
},
|
|
{
|
|
"entropy": 5.629569101333618,
|
|
"epoch": 0.7274712187375942,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0004955448922444246,
|
|
"loss": 5.4086,
|
|
"mean_token_accuracy": 0.15429458543658256,
|
|
"num_tokens": 16062957.0,
|
|
"step": 7330
|
|
},
|
|
{
|
|
"entropy": 5.649728870391845,
|
|
"epoch": 0.7279674473997618,
|
|
"grad_norm": 0.7890625,
|
|
"learning_rate": 0.0004955378736354036,
|
|
"loss": 5.4582,
|
|
"mean_token_accuracy": 0.15688300281763076,
|
|
"num_tokens": 16073592.0,
|
|
"step": 7335
|
|
},
|
|
{
|
|
"entropy": 5.5612717628479,
|
|
"epoch": 0.7284636760619293,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004955308495575185,
|
|
"loss": 5.3993,
|
|
"mean_token_accuracy": 0.15492410361766815,
|
|
"num_tokens": 16085054.0,
|
|
"step": 7340
|
|
},
|
|
{
|
|
"entropy": 5.658267307281494,
|
|
"epoch": 0.7289599047240969,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004955238200109436,
|
|
"loss": 5.484,
|
|
"mean_token_accuracy": 0.14988485276699065,
|
|
"num_tokens": 16096936.0,
|
|
"step": 7345
|
|
},
|
|
{
|
|
"entropy": 5.668556070327758,
|
|
"epoch": 0.7294561333862644,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004955167849958531,
|
|
"loss": 5.4861,
|
|
"mean_token_accuracy": 0.14705898761749267,
|
|
"num_tokens": 16107673.0,
|
|
"step": 7350
|
|
},
|
|
{
|
|
"entropy": 5.624842739105224,
|
|
"epoch": 0.729952362048432,
|
|
"grad_norm": 0.7890625,
|
|
"learning_rate": 0.0004955097445124215,
|
|
"loss": 5.3686,
|
|
"mean_token_accuracy": 0.155429670214653,
|
|
"num_tokens": 16117941.0,
|
|
"step": 7355
|
|
},
|
|
{
|
|
"entropy": 5.587152671813965,
|
|
"epoch": 0.7304485907105994,
|
|
"grad_norm": 0.78515625,
|
|
"learning_rate": 0.0004955026985608235,
|
|
"loss": 5.3349,
|
|
"mean_token_accuracy": 0.15884690582752228,
|
|
"num_tokens": 16128737.0,
|
|
"step": 7360
|
|
},
|
|
{
|
|
"entropy": 5.716961622238159,
|
|
"epoch": 0.730944819372767,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004954956471412336,
|
|
"loss": 5.4776,
|
|
"mean_token_accuracy": 0.15179453343153,
|
|
"num_tokens": 16139599.0,
|
|
"step": 7365
|
|
},
|
|
{
|
|
"entropy": 5.514989519119263,
|
|
"epoch": 0.7314410480349345,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004954885902538269,
|
|
"loss": 5.3162,
|
|
"mean_token_accuracy": 0.14936128705739976,
|
|
"num_tokens": 16150796.0,
|
|
"step": 7370
|
|
},
|
|
{
|
|
"entropy": 5.581525039672852,
|
|
"epoch": 0.7319372766971021,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004954815278987781,
|
|
"loss": 5.3853,
|
|
"mean_token_accuracy": 0.157125623524189,
|
|
"num_tokens": 16161236.0,
|
|
"step": 7375
|
|
},
|
|
{
|
|
"entropy": 5.63885269165039,
|
|
"epoch": 0.7324335053592695,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004954744600762627,
|
|
"loss": 5.4908,
|
|
"mean_token_accuracy": 0.15243475139141083,
|
|
"num_tokens": 16172210.0,
|
|
"step": 7380
|
|
},
|
|
{
|
|
"entropy": 5.567775249481201,
|
|
"epoch": 0.7329297340214371,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004954673867864555,
|
|
"loss": 5.3399,
|
|
"mean_token_accuracy": 0.16127611994743346,
|
|
"num_tokens": 16182950.0,
|
|
"step": 7385
|
|
},
|
|
{
|
|
"entropy": 5.563462209701538,
|
|
"epoch": 0.7334259626836046,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004954603080295323,
|
|
"loss": 5.2683,
|
|
"mean_token_accuracy": 0.16479185819625855,
|
|
"num_tokens": 16193971.0,
|
|
"step": 7390
|
|
},
|
|
{
|
|
"entropy": 5.576210641860962,
|
|
"epoch": 0.7339221913457721,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004954532238056686,
|
|
"loss": 5.3896,
|
|
"mean_token_accuracy": 0.1563618466258049,
|
|
"num_tokens": 16205774.0,
|
|
"step": 7395
|
|
},
|
|
{
|
|
"entropy": 5.580049991607666,
|
|
"epoch": 0.7344184200079397,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004954461341150399,
|
|
"loss": 5.3774,
|
|
"mean_token_accuracy": 0.15467396080493928,
|
|
"num_tokens": 16216626.0,
|
|
"step": 7400
|
|
},
|
|
{
|
|
"entropy": 5.616230535507202,
|
|
"epoch": 0.7349146486701071,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004954390389578222,
|
|
"loss": 5.4602,
|
|
"mean_token_accuracy": 0.14845651984214783,
|
|
"num_tokens": 16227748.0,
|
|
"step": 7405
|
|
},
|
|
{
|
|
"entropy": 5.667726373672485,
|
|
"epoch": 0.7354108773322747,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004954319383341912,
|
|
"loss": 5.4267,
|
|
"mean_token_accuracy": 0.1550072394311428,
|
|
"num_tokens": 16240390.0,
|
|
"step": 7410
|
|
},
|
|
{
|
|
"entropy": 5.603915071487426,
|
|
"epoch": 0.7359071059944422,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004954248322443232,
|
|
"loss": 5.3715,
|
|
"mean_token_accuracy": 0.1643430009484291,
|
|
"num_tokens": 16250563.0,
|
|
"step": 7415
|
|
},
|
|
{
|
|
"entropy": 5.588047456741333,
|
|
"epoch": 0.7364033346566098,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004954177206883943,
|
|
"loss": 5.4464,
|
|
"mean_token_accuracy": 0.14566802456974984,
|
|
"num_tokens": 16260722.0,
|
|
"step": 7420
|
|
},
|
|
{
|
|
"entropy": 5.731152868270874,
|
|
"epoch": 0.7368995633187773,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004954106036665809,
|
|
"loss": 5.4487,
|
|
"mean_token_accuracy": 0.1545932948589325,
|
|
"num_tokens": 16270258.0,
|
|
"step": 7425
|
|
},
|
|
{
|
|
"entropy": 5.6218890190124515,
|
|
"epoch": 0.7373957919809448,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004954034811790594,
|
|
"loss": 5.3149,
|
|
"mean_token_accuracy": 0.16307952105998993,
|
|
"num_tokens": 16279504.0,
|
|
"step": 7430
|
|
},
|
|
{
|
|
"entropy": 5.524782609939575,
|
|
"epoch": 0.7378920206431123,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0004953963532260067,
|
|
"loss": 5.3344,
|
|
"mean_token_accuracy": 0.1574219733476639,
|
|
"num_tokens": 16291327.0,
|
|
"step": 7435
|
|
},
|
|
{
|
|
"entropy": 5.609736680984497,
|
|
"epoch": 0.7383882493052799,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004953892198075991,
|
|
"loss": 5.4628,
|
|
"mean_token_accuracy": 0.1531672716140747,
|
|
"num_tokens": 16302778.0,
|
|
"step": 7440
|
|
},
|
|
{
|
|
"entropy": 5.65271110534668,
|
|
"epoch": 0.7388844779674474,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.0004953820809240138,
|
|
"loss": 5.4211,
|
|
"mean_token_accuracy": 0.14703194200992584,
|
|
"num_tokens": 16314373.0,
|
|
"step": 7445
|
|
},
|
|
{
|
|
"entropy": 5.618282842636108,
|
|
"epoch": 0.739380706629615,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004953749365754279,
|
|
"loss": 5.3871,
|
|
"mean_token_accuracy": 0.15660699158906938,
|
|
"num_tokens": 16324518.0,
|
|
"step": 7450
|
|
},
|
|
{
|
|
"entropy": 5.589332103729248,
|
|
"epoch": 0.7398769352917824,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004953677867620184,
|
|
"loss": 5.3121,
|
|
"mean_token_accuracy": 0.15828358829021455,
|
|
"num_tokens": 16335657.0,
|
|
"step": 7455
|
|
},
|
|
{
|
|
"entropy": 5.636603212356567,
|
|
"epoch": 0.74037316395395,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.0004953606314839626,
|
|
"loss": 5.5165,
|
|
"mean_token_accuracy": 0.14771938398480416,
|
|
"num_tokens": 16346497.0,
|
|
"step": 7460
|
|
},
|
|
{
|
|
"entropy": 5.570276975631714,
|
|
"epoch": 0.7408693926161175,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.000495353470741438,
|
|
"loss": 5.3815,
|
|
"mean_token_accuracy": 0.15153775215148926,
|
|
"num_tokens": 16358175.0,
|
|
"step": 7465
|
|
},
|
|
{
|
|
"entropy": 5.668294286727905,
|
|
"epoch": 0.741365621278285,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.000495346304534622,
|
|
"loss": 5.5129,
|
|
"mean_token_accuracy": 0.14579920768737792,
|
|
"num_tokens": 16369803.0,
|
|
"step": 7470
|
|
},
|
|
{
|
|
"entropy": 5.545563459396362,
|
|
"epoch": 0.7418618499404526,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004953391328636926,
|
|
"loss": 5.2069,
|
|
"mean_token_accuracy": 0.16389822214841843,
|
|
"num_tokens": 16380535.0,
|
|
"step": 7475
|
|
},
|
|
{
|
|
"entropy": 5.540350866317749,
|
|
"epoch": 0.74235807860262,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004953319557288275,
|
|
"loss": 5.3862,
|
|
"mean_token_accuracy": 0.15173779129981996,
|
|
"num_tokens": 16390518.0,
|
|
"step": 7480
|
|
},
|
|
{
|
|
"entropy": 5.594494771957398,
|
|
"epoch": 0.7428543072647876,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004953247731302046,
|
|
"loss": 5.4005,
|
|
"mean_token_accuracy": 0.14989829510450364,
|
|
"num_tokens": 16400627.0,
|
|
"step": 7485
|
|
},
|
|
{
|
|
"entropy": 5.635437822341919,
|
|
"epoch": 0.7433505359269551,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004953175850680022,
|
|
"loss": 5.4593,
|
|
"mean_token_accuracy": 0.15600887238979338,
|
|
"num_tokens": 16411136.0,
|
|
"step": 7490
|
|
},
|
|
{
|
|
"entropy": 5.661326122283936,
|
|
"epoch": 0.7438467645891227,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004953103915423983,
|
|
"loss": 5.3886,
|
|
"mean_token_accuracy": 0.15466448217630385,
|
|
"num_tokens": 16422830.0,
|
|
"step": 7495
|
|
},
|
|
{
|
|
"entropy": 5.560624313354492,
|
|
"epoch": 0.7443429932512902,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004953031925535715,
|
|
"loss": 5.3382,
|
|
"mean_token_accuracy": 0.16099384129047395,
|
|
"num_tokens": 16434158.0,
|
|
"step": 7500
|
|
},
|
|
{
|
|
"entropy": 5.588740110397339,
|
|
"epoch": 0.7448392219134577,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004952959881017003,
|
|
"loss": 5.3764,
|
|
"mean_token_accuracy": 0.1568423628807068,
|
|
"num_tokens": 16444562.0,
|
|
"step": 7505
|
|
},
|
|
{
|
|
"entropy": 5.597737884521484,
|
|
"epoch": 0.7453354505756252,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004952887781869631,
|
|
"loss": 5.411,
|
|
"mean_token_accuracy": 0.15375222265720367,
|
|
"num_tokens": 16456353.0,
|
|
"step": 7510
|
|
},
|
|
{
|
|
"entropy": 5.634686660766602,
|
|
"epoch": 0.7458316792377928,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004952815628095391,
|
|
"loss": 5.431,
|
|
"mean_token_accuracy": 0.14708781838417054,
|
|
"num_tokens": 16465756.0,
|
|
"step": 7515
|
|
},
|
|
{
|
|
"entropy": 5.600973129272461,
|
|
"epoch": 0.7463279078999603,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.0004952743419696069,
|
|
"loss": 5.3766,
|
|
"mean_token_accuracy": 0.15321100056171416,
|
|
"num_tokens": 16477562.0,
|
|
"step": 7520
|
|
},
|
|
{
|
|
"entropy": 5.621348571777344,
|
|
"epoch": 0.7468241365621279,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004952671156673456,
|
|
"loss": 5.4081,
|
|
"mean_token_accuracy": 0.1518675997853279,
|
|
"num_tokens": 16488134.0,
|
|
"step": 7525
|
|
},
|
|
{
|
|
"entropy": 5.649428272247315,
|
|
"epoch": 0.7473203652242953,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.0004952598839029345,
|
|
"loss": 5.396,
|
|
"mean_token_accuracy": 0.15431894212961197,
|
|
"num_tokens": 16499146.0,
|
|
"step": 7530
|
|
},
|
|
{
|
|
"entropy": 5.630555915832519,
|
|
"epoch": 0.7478165938864629,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004952526466765529,
|
|
"loss": 5.4354,
|
|
"mean_token_accuracy": 0.15253461599349977,
|
|
"num_tokens": 16510334.0,
|
|
"step": 7535
|
|
},
|
|
{
|
|
"entropy": 5.563698196411133,
|
|
"epoch": 0.7483128225486304,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004952454039883804,
|
|
"loss": 5.3178,
|
|
"mean_token_accuracy": 0.1540248841047287,
|
|
"num_tokens": 16520574.0,
|
|
"step": 7540
|
|
},
|
|
{
|
|
"entropy": 5.65339503288269,
|
|
"epoch": 0.7488090512107979,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004952381558385963,
|
|
"loss": 5.4607,
|
|
"mean_token_accuracy": 0.1469207674264908,
|
|
"num_tokens": 16532246.0,
|
|
"step": 7545
|
|
},
|
|
{
|
|
"entropy": 5.731358623504638,
|
|
"epoch": 0.7493052798729655,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004952309022273805,
|
|
"loss": 5.4305,
|
|
"mean_token_accuracy": 0.14792006388306617,
|
|
"num_tokens": 16541756.0,
|
|
"step": 7550
|
|
},
|
|
{
|
|
"entropy": 5.617871379852295,
|
|
"epoch": 0.7498015085351329,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004952236431549129,
|
|
"loss": 5.4353,
|
|
"mean_token_accuracy": 0.14994454085826875,
|
|
"num_tokens": 16551061.0,
|
|
"step": 7555
|
|
},
|
|
{
|
|
"entropy": 5.5954522609710695,
|
|
"epoch": 0.7502977371973005,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004952163786213735,
|
|
"loss": 5.3906,
|
|
"mean_token_accuracy": 0.14958487153053285,
|
|
"num_tokens": 16561155.0,
|
|
"step": 7560
|
|
},
|
|
{
|
|
"entropy": 5.601016807556152,
|
|
"epoch": 0.750793965859468,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004952091086269425,
|
|
"loss": 5.3398,
|
|
"mean_token_accuracy": 0.15005064383149147,
|
|
"num_tokens": 16571843.0,
|
|
"step": 7565
|
|
},
|
|
{
|
|
"entropy": 5.583734369277954,
|
|
"epoch": 0.7512901945216356,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004952018331718001,
|
|
"loss": 5.4233,
|
|
"mean_token_accuracy": 0.15418492630124092,
|
|
"num_tokens": 16583395.0,
|
|
"step": 7570
|
|
},
|
|
{
|
|
"entropy": 5.698184967041016,
|
|
"epoch": 0.7517864231838031,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004951945522561268,
|
|
"loss": 5.4716,
|
|
"mean_token_accuracy": 0.15085942968726157,
|
|
"num_tokens": 16594545.0,
|
|
"step": 7575
|
|
},
|
|
{
|
|
"entropy": 5.723637819290161,
|
|
"epoch": 0.7522826518459707,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004951872658801029,
|
|
"loss": 5.5345,
|
|
"mean_token_accuracy": 0.1519157476723194,
|
|
"num_tokens": 16605901.0,
|
|
"step": 7580
|
|
},
|
|
{
|
|
"entropy": 5.634394741058349,
|
|
"epoch": 0.7527788805081381,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004951799740439093,
|
|
"loss": 5.4775,
|
|
"mean_token_accuracy": 0.1472939819097519,
|
|
"num_tokens": 16616783.0,
|
|
"step": 7585
|
|
},
|
|
{
|
|
"entropy": 5.624340486526489,
|
|
"epoch": 0.7532751091703057,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.000495172676747727,
|
|
"loss": 5.4087,
|
|
"mean_token_accuracy": 0.1570548430085182,
|
|
"num_tokens": 16628655.0,
|
|
"step": 7590
|
|
},
|
|
{
|
|
"entropy": 5.643128490447998,
|
|
"epoch": 0.7537713378324732,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004951653739917366,
|
|
"loss": 5.427,
|
|
"mean_token_accuracy": 0.15031962543725969,
|
|
"num_tokens": 16639403.0,
|
|
"step": 7595
|
|
},
|
|
{
|
|
"entropy": 5.658723402023315,
|
|
"epoch": 0.7542675664946408,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004951580657761192,
|
|
"loss": 5.4345,
|
|
"mean_token_accuracy": 0.15885126292705537,
|
|
"num_tokens": 16649937.0,
|
|
"step": 7600
|
|
},
|
|
{
|
|
"entropy": 5.52188630104065,
|
|
"epoch": 0.7547637951568082,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004951507521010563,
|
|
"loss": 5.322,
|
|
"mean_token_accuracy": 0.15973489731550217,
|
|
"num_tokens": 16661466.0,
|
|
"step": 7605
|
|
},
|
|
{
|
|
"entropy": 5.564820241928101,
|
|
"epoch": 0.7552600238189758,
|
|
"grad_norm": 0.796875,
|
|
"learning_rate": 0.0004951434329667293,
|
|
"loss": 5.3423,
|
|
"mean_token_accuracy": 0.15731873214244843,
|
|
"num_tokens": 16673362.0,
|
|
"step": 7610
|
|
},
|
|
{
|
|
"entropy": 5.585936450958252,
|
|
"epoch": 0.7557562524811433,
|
|
"grad_norm": 0.7734375,
|
|
"learning_rate": 0.0004951361083733192,
|
|
"loss": 5.3876,
|
|
"mean_token_accuracy": 0.15195401906967163,
|
|
"num_tokens": 16685555.0,
|
|
"step": 7615
|
|
},
|
|
{
|
|
"entropy": 5.596336078643799,
|
|
"epoch": 0.7562524811433108,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004951287783210082,
|
|
"loss": 5.365,
|
|
"mean_token_accuracy": 0.15113281160593034,
|
|
"num_tokens": 16696006.0,
|
|
"step": 7620
|
|
},
|
|
{
|
|
"entropy": 5.592251348495483,
|
|
"epoch": 0.7567487098054784,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.0004951214428099778,
|
|
"loss": 5.3806,
|
|
"mean_token_accuracy": 0.15848406106233598,
|
|
"num_tokens": 16706784.0,
|
|
"step": 7625
|
|
},
|
|
{
|
|
"entropy": 5.532399702072143,
|
|
"epoch": 0.7572449384676458,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004951141018404099,
|
|
"loss": 5.3461,
|
|
"mean_token_accuracy": 0.16066349446773528,
|
|
"num_tokens": 16718492.0,
|
|
"step": 7630
|
|
},
|
|
{
|
|
"entropy": 5.607969093322754,
|
|
"epoch": 0.7577411671298134,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004951067554124865,
|
|
"loss": 5.4142,
|
|
"mean_token_accuracy": 0.1540622740983963,
|
|
"num_tokens": 16729711.0,
|
|
"step": 7635
|
|
},
|
|
{
|
|
"entropy": 5.604937648773193,
|
|
"epoch": 0.7582373957919809,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.00049509940352639,
|
|
"loss": 5.3967,
|
|
"mean_token_accuracy": 0.1564691573381424,
|
|
"num_tokens": 16739913.0,
|
|
"step": 7640
|
|
},
|
|
{
|
|
"entropy": 5.666071844100952,
|
|
"epoch": 0.7587336244541485,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004950920461823024,
|
|
"loss": 5.4327,
|
|
"mean_token_accuracy": 0.14718462899327278,
|
|
"num_tokens": 16752273.0,
|
|
"step": 7645
|
|
},
|
|
{
|
|
"entropy": 5.584566307067871,
|
|
"epoch": 0.759229853116316,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004950846833804064,
|
|
"loss": 5.3707,
|
|
"mean_token_accuracy": 0.15428989231586457,
|
|
"num_tokens": 16762050.0,
|
|
"step": 7650
|
|
},
|
|
{
|
|
"entropy": 5.55289249420166,
|
|
"epoch": 0.7597260817784836,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004950773151208845,
|
|
"loss": 5.4317,
|
|
"mean_token_accuracy": 0.15732259303331375,
|
|
"num_tokens": 16772376.0,
|
|
"step": 7655
|
|
},
|
|
{
|
|
"entropy": 5.606362676620483,
|
|
"epoch": 0.760222310440651,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004950699414039194,
|
|
"loss": 5.3972,
|
|
"mean_token_accuracy": 0.15157591700553893,
|
|
"num_tokens": 16783307.0,
|
|
"step": 7660
|
|
},
|
|
{
|
|
"entropy": 5.606588840484619,
|
|
"epoch": 0.7607185391028186,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.000495062562229694,
|
|
"loss": 5.2773,
|
|
"mean_token_accuracy": 0.15962879210710526,
|
|
"num_tokens": 16793582.0,
|
|
"step": 7665
|
|
},
|
|
{
|
|
"entropy": 5.545598363876342,
|
|
"epoch": 0.7612147677649861,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004950551775983912,
|
|
"loss": 5.3762,
|
|
"mean_token_accuracy": 0.15512028336524963,
|
|
"num_tokens": 16805160.0,
|
|
"step": 7670
|
|
},
|
|
{
|
|
"entropy": 5.589273405075073,
|
|
"epoch": 0.7617109964271537,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004950477875101942,
|
|
"loss": 5.4339,
|
|
"mean_token_accuracy": 0.15162828862667083,
|
|
"num_tokens": 16816108.0,
|
|
"step": 7675
|
|
},
|
|
{
|
|
"entropy": 5.565524578094482,
|
|
"epoch": 0.7622072250893211,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004950403919652863,
|
|
"loss": 5.3094,
|
|
"mean_token_accuracy": 0.15955265760421752,
|
|
"num_tokens": 16828126.0,
|
|
"step": 7680
|
|
},
|
|
{
|
|
"entropy": 5.60766282081604,
|
|
"epoch": 0.7627034537514887,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004950329909638507,
|
|
"loss": 5.3882,
|
|
"mean_token_accuracy": 0.15282055735588074,
|
|
"num_tokens": 16838186.0,
|
|
"step": 7685
|
|
},
|
|
{
|
|
"entropy": 5.576896286010742,
|
|
"epoch": 0.7631996824136562,
|
|
"grad_norm": 0.78515625,
|
|
"learning_rate": 0.000495025584506071,
|
|
"loss": 5.3379,
|
|
"mean_token_accuracy": 0.15614795535802842,
|
|
"num_tokens": 16848588.0,
|
|
"step": 7690
|
|
},
|
|
{
|
|
"entropy": 5.615791654586792,
|
|
"epoch": 0.7636959110758237,
|
|
"grad_norm": 0.7890625,
|
|
"learning_rate": 0.0004950181725921311,
|
|
"loss": 5.4474,
|
|
"mean_token_accuracy": 0.15467110872268677,
|
|
"num_tokens": 16860269.0,
|
|
"step": 7695
|
|
},
|
|
{
|
|
"entropy": 5.623138427734375,
|
|
"epoch": 0.7641921397379913,
|
|
"grad_norm": 0.76953125,
|
|
"learning_rate": 0.0004950107552222145,
|
|
"loss": 5.4568,
|
|
"mean_token_accuracy": 0.152884541451931,
|
|
"num_tokens": 16872221.0,
|
|
"step": 7700
|
|
},
|
|
{
|
|
"entropy": 5.584514093399048,
|
|
"epoch": 0.7646883684001587,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004950033323965052,
|
|
"loss": 5.3396,
|
|
"mean_token_accuracy": 0.14964289963245392,
|
|
"num_tokens": 16882588.0,
|
|
"step": 7705
|
|
},
|
|
{
|
|
"entropy": 5.637409830093384,
|
|
"epoch": 0.7651845970623263,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004949959041151875,
|
|
"loss": 5.3837,
|
|
"mean_token_accuracy": 0.15608891993761062,
|
|
"num_tokens": 16894278.0,
|
|
"step": 7710
|
|
},
|
|
{
|
|
"entropy": 5.625741958618164,
|
|
"epoch": 0.7656808257244938,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004949884703784453,
|
|
"loss": 5.3701,
|
|
"mean_token_accuracy": 0.15537020415067673,
|
|
"num_tokens": 16905448.0,
|
|
"step": 7715
|
|
},
|
|
{
|
|
"entropy": 5.576999235153198,
|
|
"epoch": 0.7661770543866614,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.000494981031186463,
|
|
"loss": 5.4053,
|
|
"mean_token_accuracy": 0.15578350722789763,
|
|
"num_tokens": 16914960.0,
|
|
"step": 7720
|
|
},
|
|
{
|
|
"entropy": 5.601236581802368,
|
|
"epoch": 0.7666732830488289,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004949735865394253,
|
|
"loss": 5.4705,
|
|
"mean_token_accuracy": 0.15467178598046302,
|
|
"num_tokens": 16926839.0,
|
|
"step": 7725
|
|
},
|
|
{
|
|
"entropy": 5.6161126613616945,
|
|
"epoch": 0.7671695117109965,
|
|
"grad_norm": 0.79296875,
|
|
"learning_rate": 0.0004949661364375167,
|
|
"loss": 5.3373,
|
|
"mean_token_accuracy": 0.16146927922964097,
|
|
"num_tokens": 16938553.0,
|
|
"step": 7730
|
|
},
|
|
{
|
|
"entropy": 5.628966236114502,
|
|
"epoch": 0.7676657403731639,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004949586808809217,
|
|
"loss": 5.4079,
|
|
"mean_token_accuracy": 0.1493507981300354,
|
|
"num_tokens": 16947987.0,
|
|
"step": 7735
|
|
},
|
|
{
|
|
"entropy": 5.5130181312561035,
|
|
"epoch": 0.7681619690353315,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004949512198698256,
|
|
"loss": 5.3523,
|
|
"mean_token_accuracy": 0.15001057609915733,
|
|
"num_tokens": 16959359.0,
|
|
"step": 7740
|
|
},
|
|
{
|
|
"entropy": 5.6035068988800045,
|
|
"epoch": 0.768658197697499,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.000494943753404413,
|
|
"loss": 5.406,
|
|
"mean_token_accuracy": 0.15714000016450883,
|
|
"num_tokens": 16970731.0,
|
|
"step": 7745
|
|
},
|
|
{
|
|
"entropy": 5.550115060806275,
|
|
"epoch": 0.7691544263596666,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004949362814848693,
|
|
"loss": 5.3534,
|
|
"mean_token_accuracy": 0.15779167264699936,
|
|
"num_tokens": 16981868.0,
|
|
"step": 7750
|
|
},
|
|
{
|
|
"entropy": 5.617550277709961,
|
|
"epoch": 0.769650655021834,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.0004949288041113799,
|
|
"loss": 5.398,
|
|
"mean_token_accuracy": 0.15382955670356752,
|
|
"num_tokens": 16994639.0,
|
|
"step": 7755
|
|
},
|
|
{
|
|
"entropy": 5.579612159729004,
|
|
"epoch": 0.7701468836840016,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004949213212841299,
|
|
"loss": 5.3921,
|
|
"mean_token_accuracy": 0.15306416451931,
|
|
"num_tokens": 17005067.0,
|
|
"step": 7760
|
|
},
|
|
{
|
|
"entropy": 5.584072113037109,
|
|
"epoch": 0.7706431123461691,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.000494913833003305,
|
|
"loss": 5.3078,
|
|
"mean_token_accuracy": 0.16076150983572007,
|
|
"num_tokens": 17015102.0,
|
|
"step": 7765
|
|
},
|
|
{
|
|
"entropy": 5.595542287826538,
|
|
"epoch": 0.7711393410083366,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.000494906339269091,
|
|
"loss": 5.3431,
|
|
"mean_token_accuracy": 0.1601025342941284,
|
|
"num_tokens": 17026290.0,
|
|
"step": 7770
|
|
},
|
|
{
|
|
"entropy": 5.544939613342285,
|
|
"epoch": 0.7716355696705042,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004948988400816736,
|
|
"loss": 5.304,
|
|
"mean_token_accuracy": 0.1543511003255844,
|
|
"num_tokens": 17035445.0,
|
|
"step": 7775
|
|
},
|
|
{
|
|
"entropy": 5.618521976470947,
|
|
"epoch": 0.7721317983326716,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004948913354412388,
|
|
"loss": 5.4166,
|
|
"mean_token_accuracy": 0.1582753151655197,
|
|
"num_tokens": 17046515.0,
|
|
"step": 7780
|
|
},
|
|
{
|
|
"entropy": 5.6145752429962155,
|
|
"epoch": 0.7726280269948392,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004948838253479727,
|
|
"loss": 5.3804,
|
|
"mean_token_accuracy": 0.15358736515045165,
|
|
"num_tokens": 17056988.0,
|
|
"step": 7785
|
|
},
|
|
{
|
|
"entropy": 5.623727321624756,
|
|
"epoch": 0.7731242556570067,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.0004948763098020616,
|
|
"loss": 5.4372,
|
|
"mean_token_accuracy": 0.14646037817001342,
|
|
"num_tokens": 17068304.0,
|
|
"step": 7790
|
|
},
|
|
{
|
|
"entropy": 5.576439571380615,
|
|
"epoch": 0.7736204843191743,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004948687888036918,
|
|
"loss": 5.3575,
|
|
"mean_token_accuracy": 0.15362756103277206,
|
|
"num_tokens": 17078405.0,
|
|
"step": 7795
|
|
},
|
|
{
|
|
"entropy": 5.527836894989013,
|
|
"epoch": 0.7741167129813418,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004948612623530497,
|
|
"loss": 5.2609,
|
|
"mean_token_accuracy": 0.1611561506986618,
|
|
"num_tokens": 17087839.0,
|
|
"step": 7800
|
|
},
|
|
{
|
|
"entropy": 5.504787445068359,
|
|
"epoch": 0.7746129416435094,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0004948537304503221,
|
|
"loss": 5.3644,
|
|
"mean_token_accuracy": 0.1575997367501259,
|
|
"num_tokens": 17099386.0,
|
|
"step": 7805
|
|
},
|
|
{
|
|
"entropy": 5.627182912826538,
|
|
"epoch": 0.7751091703056768,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004948461930956959,
|
|
"loss": 5.4202,
|
|
"mean_token_accuracy": 0.14962111711502074,
|
|
"num_tokens": 17111754.0,
|
|
"step": 7810
|
|
},
|
|
{
|
|
"entropy": 5.579688787460327,
|
|
"epoch": 0.7756053989678444,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004948386502893577,
|
|
"loss": 5.3019,
|
|
"mean_token_accuracy": 0.1589604452252388,
|
|
"num_tokens": 17122882.0,
|
|
"step": 7815
|
|
},
|
|
{
|
|
"entropy": 5.5752345561981205,
|
|
"epoch": 0.7761016276300119,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004948311020314946,
|
|
"loss": 5.4222,
|
|
"mean_token_accuracy": 0.14875626266002656,
|
|
"num_tokens": 17133986.0,
|
|
"step": 7820
|
|
},
|
|
{
|
|
"entropy": 5.595411729812622,
|
|
"epoch": 0.7765978562921795,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004948235483222941,
|
|
"loss": 5.3939,
|
|
"mean_token_accuracy": 0.157666178047657,
|
|
"num_tokens": 17144784.0,
|
|
"step": 7825
|
|
},
|
|
{
|
|
"entropy": 5.6028642654418945,
|
|
"epoch": 0.777094084954347,
|
|
"grad_norm": 0.79296875,
|
|
"learning_rate": 0.0004948159891619431,
|
|
"loss": 5.4863,
|
|
"mean_token_accuracy": 0.14774239808321,
|
|
"num_tokens": 17156328.0,
|
|
"step": 7830
|
|
},
|
|
{
|
|
"entropy": 5.66780309677124,
|
|
"epoch": 0.7775903136165145,
|
|
"grad_norm": 0.7890625,
|
|
"learning_rate": 0.0004948084245506293,
|
|
"loss": 5.3128,
|
|
"mean_token_accuracy": 0.15449730008840562,
|
|
"num_tokens": 17168062.0,
|
|
"step": 7835
|
|
},
|
|
{
|
|
"entropy": 5.607169485092163,
|
|
"epoch": 0.778086542278682,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.00049480085448854,
|
|
"loss": 5.3554,
|
|
"mean_token_accuracy": 0.15255675166845323,
|
|
"num_tokens": 17178872.0,
|
|
"step": 7840
|
|
},
|
|
{
|
|
"entropy": 5.571358346939087,
|
|
"epoch": 0.7785827709408495,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004947932789758635,
|
|
"loss": 5.3901,
|
|
"mean_token_accuracy": 0.15869444906711577,
|
|
"num_tokens": 17189445.0,
|
|
"step": 7845
|
|
},
|
|
{
|
|
"entropy": 5.55828332901001,
|
|
"epoch": 0.7790789996030171,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.000494785698012787,
|
|
"loss": 5.3445,
|
|
"mean_token_accuracy": 0.15926823616027833,
|
|
"num_tokens": 17199454.0,
|
|
"step": 7850
|
|
},
|
|
{
|
|
"entropy": 5.600518465042114,
|
|
"epoch": 0.7795752282651845,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004947781115994989,
|
|
"loss": 5.4097,
|
|
"mean_token_accuracy": 0.1518603652715683,
|
|
"num_tokens": 17210729.0,
|
|
"step": 7855
|
|
},
|
|
{
|
|
"entropy": 5.604863548278809,
|
|
"epoch": 0.7800714569273521,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.0004947705197361872,
|
|
"loss": 5.4599,
|
|
"mean_token_accuracy": 0.15032342523336412,
|
|
"num_tokens": 17222961.0,
|
|
"step": 7860
|
|
},
|
|
{
|
|
"entropy": 5.564748811721802,
|
|
"epoch": 0.7805676855895196,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.0004947629224230401,
|
|
"loss": 5.3427,
|
|
"mean_token_accuracy": 0.1614825740456581,
|
|
"num_tokens": 17234026.0,
|
|
"step": 7865
|
|
},
|
|
{
|
|
"entropy": 5.655606985092163,
|
|
"epoch": 0.7810639142516872,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004947553196602461,
|
|
"loss": 5.4654,
|
|
"mean_token_accuracy": 0.15531426221132277,
|
|
"num_tokens": 17244643.0,
|
|
"step": 7870
|
|
},
|
|
{
|
|
"entropy": 5.649674892425537,
|
|
"epoch": 0.7815601429138547,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004947477114479939,
|
|
"loss": 5.4009,
|
|
"mean_token_accuracy": 0.15609394907951354,
|
|
"num_tokens": 17255382.0,
|
|
"step": 7875
|
|
},
|
|
{
|
|
"entropy": 5.534345436096191,
|
|
"epoch": 0.7820563715760223,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004947400977864718,
|
|
"loss": 5.3716,
|
|
"mean_token_accuracy": 0.1518067568540573,
|
|
"num_tokens": 17265860.0,
|
|
"step": 7880
|
|
},
|
|
{
|
|
"entropy": 5.606201410293579,
|
|
"epoch": 0.7825526002381897,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004947324786758688,
|
|
"loss": 5.4483,
|
|
"mean_token_accuracy": 0.15152227655053138,
|
|
"num_tokens": 17277570.0,
|
|
"step": 7885
|
|
},
|
|
{
|
|
"entropy": 5.7140497207641605,
|
|
"epoch": 0.7830488289003573,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004947248541163738,
|
|
"loss": 5.5029,
|
|
"mean_token_accuracy": 0.1465599298477173,
|
|
"num_tokens": 17288684.0,
|
|
"step": 7890
|
|
},
|
|
{
|
|
"entropy": 5.599674224853516,
|
|
"epoch": 0.7835450575625248,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004947172241081759,
|
|
"loss": 5.3324,
|
|
"mean_token_accuracy": 0.1590951293706894,
|
|
"num_tokens": 17299541.0,
|
|
"step": 7895
|
|
},
|
|
{
|
|
"entropy": 5.610669946670532,
|
|
"epoch": 0.7840412862246924,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004947095886514643,
|
|
"loss": 5.2983,
|
|
"mean_token_accuracy": 0.1621933788061142,
|
|
"num_tokens": 17310243.0,
|
|
"step": 7900
|
|
},
|
|
{
|
|
"entropy": 5.6187296390533445,
|
|
"epoch": 0.7845375148868599,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004947019477464283,
|
|
"loss": 5.409,
|
|
"mean_token_accuracy": 0.152819262444973,
|
|
"num_tokens": 17321167.0,
|
|
"step": 7905
|
|
},
|
|
{
|
|
"entropy": 5.508659219741821,
|
|
"epoch": 0.7850337435490274,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004946943013932574,
|
|
"loss": 5.3912,
|
|
"mean_token_accuracy": 0.15561124607920646,
|
|
"num_tokens": 17331076.0,
|
|
"step": 7910
|
|
},
|
|
{
|
|
"entropy": 5.622127485275269,
|
|
"epoch": 0.7855299722111949,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004946866495921413,
|
|
"loss": 5.3515,
|
|
"mean_token_accuracy": 0.15189367532730103,
|
|
"num_tokens": 17341337.0,
|
|
"step": 7915
|
|
},
|
|
{
|
|
"entropy": 5.627335453033448,
|
|
"epoch": 0.7860262008733624,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0004946789923432695,
|
|
"loss": 5.3794,
|
|
"mean_token_accuracy": 0.15439552217721939,
|
|
"num_tokens": 17353055.0,
|
|
"step": 7920
|
|
},
|
|
{
|
|
"entropy": 5.504520225524902,
|
|
"epoch": 0.78652242953553,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.0004946713296468322,
|
|
"loss": 5.2988,
|
|
"mean_token_accuracy": 0.15451223403215408,
|
|
"num_tokens": 17364442.0,
|
|
"step": 7925
|
|
},
|
|
{
|
|
"entropy": 5.581909465789795,
|
|
"epoch": 0.7870186581976975,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004946636615030192,
|
|
"loss": 5.403,
|
|
"mean_token_accuracy": 0.15277259051799774,
|
|
"num_tokens": 17376237.0,
|
|
"step": 7930
|
|
},
|
|
{
|
|
"entropy": 5.62790265083313,
|
|
"epoch": 0.787514886859865,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004946559879120208,
|
|
"loss": 5.3441,
|
|
"mean_token_accuracy": 0.15403714030981064,
|
|
"num_tokens": 17386188.0,
|
|
"step": 7935
|
|
},
|
|
{
|
|
"entropy": 5.498153209686279,
|
|
"epoch": 0.7880111155220325,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004946483088740273,
|
|
"loss": 5.3213,
|
|
"mean_token_accuracy": 0.1592441275715828,
|
|
"num_tokens": 17397058.0,
|
|
"step": 7940
|
|
},
|
|
{
|
|
"entropy": 5.653704309463501,
|
|
"epoch": 0.7885073441842001,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004946406243892289,
|
|
"loss": 5.3937,
|
|
"mean_token_accuracy": 0.1570437327027321,
|
|
"num_tokens": 17408191.0,
|
|
"step": 7945
|
|
},
|
|
{
|
|
"entropy": 5.627149391174316,
|
|
"epoch": 0.7890035728463676,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004946329344578163,
|
|
"loss": 5.3575,
|
|
"mean_token_accuracy": 0.15499195754528045,
|
|
"num_tokens": 17418472.0,
|
|
"step": 7950
|
|
},
|
|
{
|
|
"entropy": 5.56838550567627,
|
|
"epoch": 0.7894998015085352,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004946252390799803,
|
|
"loss": 5.2977,
|
|
"mean_token_accuracy": 0.15691063553094864,
|
|
"num_tokens": 17429556.0,
|
|
"step": 7955
|
|
},
|
|
{
|
|
"entropy": 5.6031248569488525,
|
|
"epoch": 0.7899960301707026,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004946175382559116,
|
|
"loss": 5.4561,
|
|
"mean_token_accuracy": 0.15173669755458832,
|
|
"num_tokens": 17440950.0,
|
|
"step": 7960
|
|
},
|
|
{
|
|
"entropy": 5.548545217514038,
|
|
"epoch": 0.7904922588328702,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.000494609831985801,
|
|
"loss": 5.3304,
|
|
"mean_token_accuracy": 0.15893898159265518,
|
|
"num_tokens": 17453724.0,
|
|
"step": 7965
|
|
},
|
|
{
|
|
"entropy": 5.588298702239991,
|
|
"epoch": 0.7909884874950377,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00049460212026984,
|
|
"loss": 5.3704,
|
|
"mean_token_accuracy": 0.1552225574851036,
|
|
"num_tokens": 17464623.0,
|
|
"step": 7970
|
|
},
|
|
{
|
|
"entropy": 5.584340000152588,
|
|
"epoch": 0.7914847161572053,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004945944031082195,
|
|
"loss": 5.3725,
|
|
"mean_token_accuracy": 0.15697754621505738,
|
|
"num_tokens": 17474919.0,
|
|
"step": 7975
|
|
},
|
|
{
|
|
"entropy": 5.652498531341553,
|
|
"epoch": 0.7919809448193728,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.000494586680501131,
|
|
"loss": 5.3671,
|
|
"mean_token_accuracy": 0.1519192174077034,
|
|
"num_tokens": 17484747.0,
|
|
"step": 7980
|
|
},
|
|
{
|
|
"entropy": 5.587380027770996,
|
|
"epoch": 0.7924771734815403,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.000494578952448766,
|
|
"loss": 5.3069,
|
|
"mean_token_accuracy": 0.15586603283882142,
|
|
"num_tokens": 17496299.0,
|
|
"step": 7985
|
|
},
|
|
{
|
|
"entropy": 5.640566015243531,
|
|
"epoch": 0.7929734021437078,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0004945712189513161,
|
|
"loss": 5.4597,
|
|
"mean_token_accuracy": 0.14641395658254625,
|
|
"num_tokens": 17507448.0,
|
|
"step": 7990
|
|
},
|
|
{
|
|
"entropy": 5.677541446685791,
|
|
"epoch": 0.7934696308058753,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004945634800089733,
|
|
"loss": 5.4385,
|
|
"mean_token_accuracy": 0.149424247443676,
|
|
"num_tokens": 17520112.0,
|
|
"step": 7995
|
|
},
|
|
{
|
|
"entropy": 5.625305986404419,
|
|
"epoch": 0.7939658594680429,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004945557356219291,
|
|
"loss": 5.4249,
|
|
"mean_token_accuracy": 0.14955083578824996,
|
|
"num_tokens": 17531368.0,
|
|
"step": 8000
|
|
},
|
|
{
|
|
"entropy": 5.523750829696655,
|
|
"epoch": 0.7944620881302104,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004945479857903758,
|
|
"loss": 5.3778,
|
|
"mean_token_accuracy": 0.1584137961268425,
|
|
"num_tokens": 17542082.0,
|
|
"step": 8005
|
|
},
|
|
{
|
|
"entropy": 5.6196800708770756,
|
|
"epoch": 0.7949583167923779,
|
|
"grad_norm": 0.79296875,
|
|
"learning_rate": 0.0004945402305145056,
|
|
"loss": 5.3994,
|
|
"mean_token_accuracy": 0.15377297550439833,
|
|
"num_tokens": 17555518.0,
|
|
"step": 8010
|
|
},
|
|
{
|
|
"entropy": 5.638475561141968,
|
|
"epoch": 0.7954545454545454,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004945324697945107,
|
|
"loss": 5.3718,
|
|
"mean_token_accuracy": 0.15810612440109253,
|
|
"num_tokens": 17566110.0,
|
|
"step": 8015
|
|
},
|
|
{
|
|
"entropy": 5.51535472869873,
|
|
"epoch": 0.795950774116713,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004945247036305836,
|
|
"loss": 5.2934,
|
|
"mean_token_accuracy": 0.15774129033088685,
|
|
"num_tokens": 17575942.0,
|
|
"step": 8020
|
|
},
|
|
{
|
|
"entropy": 5.557010507583618,
|
|
"epoch": 0.7964470027788805,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004945169320229169,
|
|
"loss": 5.3712,
|
|
"mean_token_accuracy": 0.16034497767686845,
|
|
"num_tokens": 17586001.0,
|
|
"step": 8025
|
|
},
|
|
{
|
|
"entropy": 5.682870721817016,
|
|
"epoch": 0.7969432314410481,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004945091549717033,
|
|
"loss": 5.5149,
|
|
"mean_token_accuracy": 0.1454322263598442,
|
|
"num_tokens": 17596774.0,
|
|
"step": 8030
|
|
},
|
|
{
|
|
"entropy": 5.618385601043701,
|
|
"epoch": 0.7974394601032155,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004945013724771356,
|
|
"loss": 5.3812,
|
|
"mean_token_accuracy": 0.15872787684202194,
|
|
"num_tokens": 17606557.0,
|
|
"step": 8035
|
|
},
|
|
{
|
|
"entropy": 5.497632646560669,
|
|
"epoch": 0.7979356887653831,
|
|
"grad_norm": 0.80078125,
|
|
"learning_rate": 0.0004944935845394069,
|
|
"loss": 5.2506,
|
|
"mean_token_accuracy": 0.15902817547321318,
|
|
"num_tokens": 17616465.0,
|
|
"step": 8040
|
|
},
|
|
{
|
|
"entropy": 5.638848829269409,
|
|
"epoch": 0.7984319174275506,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004944857911587103,
|
|
"loss": 5.4258,
|
|
"mean_token_accuracy": 0.15399444103240967,
|
|
"num_tokens": 17626907.0,
|
|
"step": 8045
|
|
},
|
|
{
|
|
"entropy": 5.685809516906739,
|
|
"epoch": 0.7989281460897182,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004944779923352389,
|
|
"loss": 5.4188,
|
|
"mean_token_accuracy": 0.1529553696513176,
|
|
"num_tokens": 17638660.0,
|
|
"step": 8050
|
|
},
|
|
{
|
|
"entropy": 5.539503812789917,
|
|
"epoch": 0.7994243747518857,
|
|
"grad_norm": 0.80078125,
|
|
"learning_rate": 0.0004944701880691864,
|
|
"loss": 5.3393,
|
|
"mean_token_accuracy": 0.16294268518686295,
|
|
"num_tokens": 17650135.0,
|
|
"step": 8055
|
|
},
|
|
{
|
|
"entropy": 5.5205878734588625,
|
|
"epoch": 0.7999206034140532,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.000494462378360746,
|
|
"loss": 5.3665,
|
|
"mean_token_accuracy": 0.15941154807806016,
|
|
"num_tokens": 17660987.0,
|
|
"step": 8060
|
|
},
|
|
{
|
|
"entropy": 5.620557451248169,
|
|
"epoch": 0.8004168320762207,
|
|
"grad_norm": 0.75,
|
|
"learning_rate": 0.0004944545632101117,
|
|
"loss": 5.2929,
|
|
"mean_token_accuracy": 0.15972078293561937,
|
|
"num_tokens": 17672520.0,
|
|
"step": 8065
|
|
},
|
|
{
|
|
"entropy": 5.607070207595825,
|
|
"epoch": 0.8009130607383882,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004944467426174769,
|
|
"loss": 5.3607,
|
|
"mean_token_accuracy": 0.156748728454113,
|
|
"num_tokens": 17683688.0,
|
|
"step": 8070
|
|
},
|
|
{
|
|
"entropy": 5.535247707366944,
|
|
"epoch": 0.8014092894005558,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.000494438916583036,
|
|
"loss": 5.2892,
|
|
"mean_token_accuracy": 0.1605285659432411,
|
|
"num_tokens": 17695213.0,
|
|
"step": 8075
|
|
},
|
|
{
|
|
"entropy": 5.575884532928467,
|
|
"epoch": 0.8019055180627233,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004944310851069826,
|
|
"loss": 5.38,
|
|
"mean_token_accuracy": 0.1581933856010437,
|
|
"num_tokens": 17705545.0,
|
|
"step": 8080
|
|
},
|
|
{
|
|
"entropy": 5.591823387145996,
|
|
"epoch": 0.8024017467248908,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.0004944232481895112,
|
|
"loss": 5.3581,
|
|
"mean_token_accuracy": 0.16412023603916168,
|
|
"num_tokens": 17715855.0,
|
|
"step": 8085
|
|
},
|
|
{
|
|
"entropy": 5.627885055541992,
|
|
"epoch": 0.8028979753870583,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.000494415405830816,
|
|
"loss": 5.4226,
|
|
"mean_token_accuracy": 0.15787064135074616,
|
|
"num_tokens": 17727764.0,
|
|
"step": 8090
|
|
},
|
|
{
|
|
"entropy": 5.612554740905762,
|
|
"epoch": 0.8033942040492259,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004944075580310916,
|
|
"loss": 5.4117,
|
|
"mean_token_accuracy": 0.15614206790924073,
|
|
"num_tokens": 17738464.0,
|
|
"step": 8095
|
|
},
|
|
{
|
|
"entropy": 5.606903982162476,
|
|
"epoch": 0.8038904327113934,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004943997047905325,
|
|
"loss": 5.3996,
|
|
"mean_token_accuracy": 0.16208686232566832,
|
|
"num_tokens": 17747502.0,
|
|
"step": 8100
|
|
},
|
|
{
|
|
"entropy": 5.565347719192505,
|
|
"epoch": 0.804386661373561,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004943918461093335,
|
|
"loss": 5.3872,
|
|
"mean_token_accuracy": 0.15283362567424774,
|
|
"num_tokens": 17759520.0,
|
|
"step": 8105
|
|
},
|
|
{
|
|
"entropy": 5.5941112518310545,
|
|
"epoch": 0.8048828900357284,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004943839819876894,
|
|
"loss": 5.3623,
|
|
"mean_token_accuracy": 0.15686660557985305,
|
|
"num_tokens": 17770631.0,
|
|
"step": 8110
|
|
},
|
|
{
|
|
"entropy": 5.634806537628174,
|
|
"epoch": 0.805379118697896,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004943761124257954,
|
|
"loss": 5.3226,
|
|
"mean_token_accuracy": 0.15570886433124542,
|
|
"num_tokens": 17781320.0,
|
|
"step": 8115
|
|
},
|
|
{
|
|
"entropy": 5.596116304397583,
|
|
"epoch": 0.8058753473600635,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004943682374238464,
|
|
"loss": 5.379,
|
|
"mean_token_accuracy": 0.15654406771063806,
|
|
"num_tokens": 17792627.0,
|
|
"step": 8120
|
|
},
|
|
{
|
|
"entropy": 5.584414863586426,
|
|
"epoch": 0.8063715760222311,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.000494360356982038,
|
|
"loss": 5.4261,
|
|
"mean_token_accuracy": 0.15325156450271607,
|
|
"num_tokens": 17803286.0,
|
|
"step": 8125
|
|
},
|
|
{
|
|
"entropy": 5.517915105819702,
|
|
"epoch": 0.8068678046843986,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004943524711005653,
|
|
"loss": 5.2346,
|
|
"mean_token_accuracy": 0.15880848467350006,
|
|
"num_tokens": 17813631.0,
|
|
"step": 8130
|
|
},
|
|
{
|
|
"entropy": 5.547467565536499,
|
|
"epoch": 0.8073640333465661,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.000494344579779624,
|
|
"loss": 5.3388,
|
|
"mean_token_accuracy": 0.15715861767530442,
|
|
"num_tokens": 17823467.0,
|
|
"step": 8135
|
|
},
|
|
{
|
|
"entropy": 5.576457691192627,
|
|
"epoch": 0.8078602620087336,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004943366830194098,
|
|
"loss": 5.3278,
|
|
"mean_token_accuracy": 0.1577102318406105,
|
|
"num_tokens": 17833600.0,
|
|
"step": 8140
|
|
},
|
|
{
|
|
"entropy": 5.565642213821411,
|
|
"epoch": 0.8083564906709012,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004943287808201183,
|
|
"loss": 5.3374,
|
|
"mean_token_accuracy": 0.1486472576856613,
|
|
"num_tokens": 17843112.0,
|
|
"step": 8145
|
|
},
|
|
{
|
|
"entropy": 5.606211566925049,
|
|
"epoch": 0.8088527193330687,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004943208731819459,
|
|
"loss": 5.3357,
|
|
"mean_token_accuracy": 0.15949689447879792,
|
|
"num_tokens": 17853678.0,
|
|
"step": 8150
|
|
},
|
|
{
|
|
"entropy": 5.571245861053467,
|
|
"epoch": 0.8093489479952362,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004943129601050883,
|
|
"loss": 5.3215,
|
|
"mean_token_accuracy": 0.16115986406803132,
|
|
"num_tokens": 17863537.0,
|
|
"step": 8155
|
|
},
|
|
{
|
|
"entropy": 5.566862392425537,
|
|
"epoch": 0.8098451766574037,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.000494305041589742,
|
|
"loss": 5.3981,
|
|
"mean_token_accuracy": 0.15240979045629502,
|
|
"num_tokens": 17873511.0,
|
|
"step": 8160
|
|
},
|
|
{
|
|
"entropy": 5.5311808586120605,
|
|
"epoch": 0.8103414053195712,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004942971176361031,
|
|
"loss": 5.32,
|
|
"mean_token_accuracy": 0.16108133643865585,
|
|
"num_tokens": 17884546.0,
|
|
"step": 8165
|
|
},
|
|
{
|
|
"entropy": 5.535860157012939,
|
|
"epoch": 0.8108376339817388,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004942891882443682,
|
|
"loss": 5.2846,
|
|
"mean_token_accuracy": 0.15900460928678511,
|
|
"num_tokens": 17895331.0,
|
|
"step": 8170
|
|
},
|
|
{
|
|
"entropy": 5.60030689239502,
|
|
"epoch": 0.8113338626439063,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.000494281253414734,
|
|
"loss": 5.4444,
|
|
"mean_token_accuracy": 0.152166049182415,
|
|
"num_tokens": 17906465.0,
|
|
"step": 8175
|
|
},
|
|
{
|
|
"entropy": 5.5684957027435305,
|
|
"epoch": 0.8118300913060739,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004942733131473973,
|
|
"loss": 5.3821,
|
|
"mean_token_accuracy": 0.1505785420536995,
|
|
"num_tokens": 17916936.0,
|
|
"step": 8180
|
|
},
|
|
{
|
|
"entropy": 5.655961799621582,
|
|
"epoch": 0.8123263199682413,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004942653674425548,
|
|
"loss": 5.3866,
|
|
"mean_token_accuracy": 0.15095711797475814,
|
|
"num_tokens": 17927522.0,
|
|
"step": 8185
|
|
},
|
|
{
|
|
"entropy": 5.614254665374756,
|
|
"epoch": 0.8128225486304089,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004942574163004038,
|
|
"loss": 5.4485,
|
|
"mean_token_accuracy": 0.15291159600019455,
|
|
"num_tokens": 17938216.0,
|
|
"step": 8190
|
|
},
|
|
{
|
|
"entropy": 5.6159416198730465,
|
|
"epoch": 0.8133187772925764,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004942494597211412,
|
|
"loss": 5.3388,
|
|
"mean_token_accuracy": 0.155377659201622,
|
|
"num_tokens": 17949333.0,
|
|
"step": 8195
|
|
},
|
|
{
|
|
"entropy": 5.63876485824585,
|
|
"epoch": 0.813815005954744,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004942414977049646,
|
|
"loss": 5.3974,
|
|
"mean_token_accuracy": 0.1446226179599762,
|
|
"num_tokens": 17960178.0,
|
|
"step": 8200
|
|
},
|
|
{
|
|
"entropy": 5.559086084365845,
|
|
"epoch": 0.8143112346169115,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.000494233530252071,
|
|
"loss": 5.3627,
|
|
"mean_token_accuracy": 0.15392488539218901,
|
|
"num_tokens": 17971180.0,
|
|
"step": 8205
|
|
},
|
|
{
|
|
"entropy": 5.58487868309021,
|
|
"epoch": 0.814807463279079,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004942255573626585,
|
|
"loss": 5.3904,
|
|
"mean_token_accuracy": 0.15401293933391572,
|
|
"num_tokens": 17982572.0,
|
|
"step": 8210
|
|
},
|
|
{
|
|
"entropy": 5.636579418182373,
|
|
"epoch": 0.8153036919412465,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004942175790369244,
|
|
"loss": 5.3313,
|
|
"mean_token_accuracy": 0.15755854845046996,
|
|
"num_tokens": 17993236.0,
|
|
"step": 8215
|
|
},
|
|
{
|
|
"entropy": 5.603274631500244,
|
|
"epoch": 0.8157999206034141,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004942095952750669,
|
|
"loss": 5.4466,
|
|
"mean_token_accuracy": 0.15470776259899138,
|
|
"num_tokens": 18004215.0,
|
|
"step": 8220
|
|
},
|
|
{
|
|
"entropy": 5.5473466396331785,
|
|
"epoch": 0.8162961492655816,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004942016060772837,
|
|
"loss": 5.3344,
|
|
"mean_token_accuracy": 0.1581986740231514,
|
|
"num_tokens": 18013880.0,
|
|
"step": 8225
|
|
},
|
|
{
|
|
"entropy": 5.577635002136231,
|
|
"epoch": 0.8167923779277491,
|
|
"grad_norm": 0.796875,
|
|
"learning_rate": 0.0004941936114437731,
|
|
"loss": 5.3905,
|
|
"mean_token_accuracy": 0.15430509746074678,
|
|
"num_tokens": 18024928.0,
|
|
"step": 8230
|
|
},
|
|
{
|
|
"entropy": 5.578258991241455,
|
|
"epoch": 0.8172886065899166,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004941856113747331,
|
|
"loss": 5.3504,
|
|
"mean_token_accuracy": 0.15071632713079453,
|
|
"num_tokens": 18035857.0,
|
|
"step": 8235
|
|
},
|
|
{
|
|
"entropy": 5.641419172286987,
|
|
"epoch": 0.8177848352520841,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004941776058703623,
|
|
"loss": 5.4625,
|
|
"mean_token_accuracy": 0.1520865350961685,
|
|
"num_tokens": 18046776.0,
|
|
"step": 8240
|
|
},
|
|
{
|
|
"entropy": 5.623132038116455,
|
|
"epoch": 0.8182810639142517,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004941695949308593,
|
|
"loss": 5.409,
|
|
"mean_token_accuracy": 0.15991352796554564,
|
|
"num_tokens": 18057167.0,
|
|
"step": 8245
|
|
},
|
|
{
|
|
"entropy": 5.624783039093018,
|
|
"epoch": 0.8187772925764192,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004941615785564224,
|
|
"loss": 5.4301,
|
|
"mean_token_accuracy": 0.14956261664628984,
|
|
"num_tokens": 18066953.0,
|
|
"step": 8250
|
|
},
|
|
{
|
|
"entropy": 5.58717827796936,
|
|
"epoch": 0.8192735212385868,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004941535567472506,
|
|
"loss": 5.2657,
|
|
"mean_token_accuracy": 0.15928489118814468,
|
|
"num_tokens": 18077977.0,
|
|
"step": 8255
|
|
},
|
|
{
|
|
"entropy": 5.5626789093017575,
|
|
"epoch": 0.8197697499007542,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.000494145529503543,
|
|
"loss": 5.3594,
|
|
"mean_token_accuracy": 0.15167167633771897,
|
|
"num_tokens": 18087581.0,
|
|
"step": 8260
|
|
},
|
|
{
|
|
"entropy": 5.519986772537232,
|
|
"epoch": 0.8202659785629218,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004941374968254985,
|
|
"loss": 5.2653,
|
|
"mean_token_accuracy": 0.15741712152957915,
|
|
"num_tokens": 18098193.0,
|
|
"step": 8265
|
|
},
|
|
{
|
|
"entropy": 5.584941959381103,
|
|
"epoch": 0.8207622072250893,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004941294587133161,
|
|
"loss": 5.3791,
|
|
"mean_token_accuracy": 0.1589309900999069,
|
|
"num_tokens": 18110830.0,
|
|
"step": 8270
|
|
},
|
|
{
|
|
"entropy": 5.654639673233032,
|
|
"epoch": 0.8212584358872569,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.0004941214151671954,
|
|
"loss": 5.4134,
|
|
"mean_token_accuracy": 0.15107691287994385,
|
|
"num_tokens": 18122073.0,
|
|
"step": 8275
|
|
},
|
|
{
|
|
"entropy": 5.548416185379028,
|
|
"epoch": 0.8217546645494244,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004941133661873357,
|
|
"loss": 5.3926,
|
|
"mean_token_accuracy": 0.15540233254432678,
|
|
"num_tokens": 18132777.0,
|
|
"step": 8280
|
|
},
|
|
{
|
|
"entropy": 5.526298189163208,
|
|
"epoch": 0.822250893211592,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004941053117739367,
|
|
"loss": 5.3013,
|
|
"mean_token_accuracy": 0.15420641452074052,
|
|
"num_tokens": 18143232.0,
|
|
"step": 8285
|
|
},
|
|
{
|
|
"entropy": 5.59205904006958,
|
|
"epoch": 0.8227471218737594,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004940972519271982,
|
|
"loss": 5.4754,
|
|
"mean_token_accuracy": 0.1535163328051567,
|
|
"num_tokens": 18155225.0,
|
|
"step": 8290
|
|
},
|
|
{
|
|
"entropy": 5.646539306640625,
|
|
"epoch": 0.823243350535927,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004940891866473199,
|
|
"loss": 5.3967,
|
|
"mean_token_accuracy": 0.1553361311554909,
|
|
"num_tokens": 18165945.0,
|
|
"step": 8295
|
|
},
|
|
{
|
|
"entropy": 5.665407943725586,
|
|
"epoch": 0.8237395791980945,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004940811159345017,
|
|
"loss": 5.4304,
|
|
"mean_token_accuracy": 0.14958547353744506,
|
|
"num_tokens": 18177271.0,
|
|
"step": 8300
|
|
},
|
|
{
|
|
"entropy": 5.663650274276733,
|
|
"epoch": 0.824235807860262,
|
|
"grad_norm": 0.79296875,
|
|
"learning_rate": 0.0004940730397889441,
|
|
"loss": 5.3737,
|
|
"mean_token_accuracy": 0.15421211272478103,
|
|
"num_tokens": 18189732.0,
|
|
"step": 8305
|
|
},
|
|
{
|
|
"entropy": 5.594327116012574,
|
|
"epoch": 0.8247320365224295,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004940649582108472,
|
|
"loss": 5.4713,
|
|
"mean_token_accuracy": 0.1524760343134403,
|
|
"num_tokens": 18200731.0,
|
|
"step": 8310
|
|
},
|
|
{
|
|
"entropy": 5.6143065929412845,
|
|
"epoch": 0.825228265184597,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004940568712004113,
|
|
"loss": 5.3943,
|
|
"mean_token_accuracy": 0.1596961349248886,
|
|
"num_tokens": 18210873.0,
|
|
"step": 8315
|
|
},
|
|
{
|
|
"entropy": 5.679521274566651,
|
|
"epoch": 0.8257244938467646,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004940487787578369,
|
|
"loss": 5.3819,
|
|
"mean_token_accuracy": 0.15673448145389557,
|
|
"num_tokens": 18222072.0,
|
|
"step": 8320
|
|
},
|
|
{
|
|
"entropy": 5.530484390258789,
|
|
"epoch": 0.8262207225089321,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.000494040680883325,
|
|
"loss": 5.2823,
|
|
"mean_token_accuracy": 0.15844718366861343,
|
|
"num_tokens": 18232522.0,
|
|
"step": 8325
|
|
},
|
|
{
|
|
"entropy": 5.625659942626953,
|
|
"epoch": 0.8267169511710997,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004940325775770762,
|
|
"loss": 5.3908,
|
|
"mean_token_accuracy": 0.14972957149147986,
|
|
"num_tokens": 18243587.0,
|
|
"step": 8330
|
|
},
|
|
{
|
|
"entropy": 5.575936985015869,
|
|
"epoch": 0.8272131798332671,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.0004940244688392913,
|
|
"loss": 5.2986,
|
|
"mean_token_accuracy": 0.16298762559890748,
|
|
"num_tokens": 18254965.0,
|
|
"step": 8335
|
|
},
|
|
{
|
|
"entropy": 5.571698570251465,
|
|
"epoch": 0.8277094084954347,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004940163546701716,
|
|
"loss": 5.32,
|
|
"mean_token_accuracy": 0.15952432304620742,
|
|
"num_tokens": 18265892.0,
|
|
"step": 8340
|
|
},
|
|
{
|
|
"entropy": 5.585426902770996,
|
|
"epoch": 0.8282056371576022,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004940082350699183,
|
|
"loss": 5.3184,
|
|
"mean_token_accuracy": 0.15753851234912872,
|
|
"num_tokens": 18276713.0,
|
|
"step": 8345
|
|
},
|
|
{
|
|
"entropy": 5.659633779525757,
|
|
"epoch": 0.8287018658197698,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004940001100387325,
|
|
"loss": 5.3726,
|
|
"mean_token_accuracy": 0.14980877786874772,
|
|
"num_tokens": 18288846.0,
|
|
"step": 8350
|
|
},
|
|
{
|
|
"entropy": 5.639483165740967,
|
|
"epoch": 0.8291980944819373,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004939919795768161,
|
|
"loss": 5.3987,
|
|
"mean_token_accuracy": 0.15961014479398727,
|
|
"num_tokens": 18298750.0,
|
|
"step": 8355
|
|
},
|
|
{
|
|
"entropy": 5.580147314071655,
|
|
"epoch": 0.8296943231441049,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004939838436843704,
|
|
"loss": 5.3744,
|
|
"mean_token_accuracy": 0.15533585399389266,
|
|
"num_tokens": 18310065.0,
|
|
"step": 8360
|
|
},
|
|
{
|
|
"entropy": 5.584295177459717,
|
|
"epoch": 0.8301905518062723,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004939757023615973,
|
|
"loss": 5.3345,
|
|
"mean_token_accuracy": 0.15667842626571654,
|
|
"num_tokens": 18319498.0,
|
|
"step": 8365
|
|
},
|
|
{
|
|
"entropy": 5.558476495742798,
|
|
"epoch": 0.8306867804684399,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004939675556086986,
|
|
"loss": 5.2902,
|
|
"mean_token_accuracy": 0.16425713449716567,
|
|
"num_tokens": 18329718.0,
|
|
"step": 8370
|
|
},
|
|
{
|
|
"entropy": 5.550742244720459,
|
|
"epoch": 0.8311830091306074,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004939594034258763,
|
|
"loss": 5.3006,
|
|
"mean_token_accuracy": 0.16241085529327393,
|
|
"num_tokens": 18341628.0,
|
|
"step": 8375
|
|
},
|
|
{
|
|
"entropy": 5.5619243621826175,
|
|
"epoch": 0.8316792377927749,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004939512458133326,
|
|
"loss": 5.3473,
|
|
"mean_token_accuracy": 0.16096800416707993,
|
|
"num_tokens": 18352869.0,
|
|
"step": 8380
|
|
},
|
|
{
|
|
"entropy": 5.5964590549469,
|
|
"epoch": 0.8321754664549424,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004939430827712698,
|
|
"loss": 5.362,
|
|
"mean_token_accuracy": 0.15447923466563224,
|
|
"num_tokens": 18363664.0,
|
|
"step": 8385
|
|
},
|
|
{
|
|
"entropy": 5.630773496627808,
|
|
"epoch": 0.8326716951171099,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004939349142998905,
|
|
"loss": 5.3507,
|
|
"mean_token_accuracy": 0.1544475883245468,
|
|
"num_tokens": 18374325.0,
|
|
"step": 8390
|
|
},
|
|
{
|
|
"entropy": 5.584388971328735,
|
|
"epoch": 0.8331679237792775,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004939267403993968,
|
|
"loss": 5.3453,
|
|
"mean_token_accuracy": 0.15908517688512802,
|
|
"num_tokens": 18384547.0,
|
|
"step": 8395
|
|
},
|
|
{
|
|
"entropy": 5.596279573440552,
|
|
"epoch": 0.833664152441445,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.000493918561069992,
|
|
"loss": 5.3211,
|
|
"mean_token_accuracy": 0.15538033843040466,
|
|
"num_tokens": 18395141.0,
|
|
"step": 8400
|
|
},
|
|
{
|
|
"entropy": 5.537204551696777,
|
|
"epoch": 0.8341603811036126,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004939103763118784,
|
|
"loss": 5.3197,
|
|
"mean_token_accuracy": 0.15610468983650208,
|
|
"num_tokens": 18406326.0,
|
|
"step": 8405
|
|
},
|
|
{
|
|
"entropy": 5.60677318572998,
|
|
"epoch": 0.83465660976578,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.0004939021861252593,
|
|
"loss": 5.3866,
|
|
"mean_token_accuracy": 0.15724660605192184,
|
|
"num_tokens": 18417521.0,
|
|
"step": 8410
|
|
},
|
|
{
|
|
"entropy": 5.616010284423828,
|
|
"epoch": 0.8351528384279476,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004938939905103376,
|
|
"loss": 5.3199,
|
|
"mean_token_accuracy": 0.15721606761217116,
|
|
"num_tokens": 18426813.0,
|
|
"step": 8415
|
|
},
|
|
{
|
|
"entropy": 5.561202621459961,
|
|
"epoch": 0.8356490670901151,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004938857894673166,
|
|
"loss": 5.2708,
|
|
"mean_token_accuracy": 0.15798320472240449,
|
|
"num_tokens": 18438227.0,
|
|
"step": 8420
|
|
},
|
|
{
|
|
"entropy": 5.571479034423828,
|
|
"epoch": 0.8361452957522827,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004938775829963997,
|
|
"loss": 5.4019,
|
|
"mean_token_accuracy": 0.15177630186080932,
|
|
"num_tokens": 18448915.0,
|
|
"step": 8425
|
|
},
|
|
{
|
|
"entropy": 5.604960298538208,
|
|
"epoch": 0.8366415244144502,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004938693710977904,
|
|
"loss": 5.2908,
|
|
"mean_token_accuracy": 0.15932296812534333,
|
|
"num_tokens": 18459330.0,
|
|
"step": 8430
|
|
},
|
|
{
|
|
"entropy": 5.559336471557617,
|
|
"epoch": 0.8371377530766178,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004938611537716922,
|
|
"loss": 5.2693,
|
|
"mean_token_accuracy": 0.16089767962694168,
|
|
"num_tokens": 18469813.0,
|
|
"step": 8435
|
|
},
|
|
{
|
|
"entropy": 5.538674449920654,
|
|
"epoch": 0.8376339817387852,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004938529310183091,
|
|
"loss": 5.3194,
|
|
"mean_token_accuracy": 0.15382401794195175,
|
|
"num_tokens": 18479783.0,
|
|
"step": 8440
|
|
},
|
|
{
|
|
"entropy": 5.53818678855896,
|
|
"epoch": 0.8381302104009528,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.000493844702837845,
|
|
"loss": 5.3445,
|
|
"mean_token_accuracy": 0.1606591448187828,
|
|
"num_tokens": 18489640.0,
|
|
"step": 8445
|
|
},
|
|
{
|
|
"entropy": 5.638463020324707,
|
|
"epoch": 0.8386264390631203,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004938364692305036,
|
|
"loss": 5.4002,
|
|
"mean_token_accuracy": 0.15992128252983093,
|
|
"num_tokens": 18500744.0,
|
|
"step": 8450
|
|
},
|
|
{
|
|
"entropy": 5.617222642898559,
|
|
"epoch": 0.8391226677252878,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004938282301964896,
|
|
"loss": 5.3049,
|
|
"mean_token_accuracy": 0.15640706121921538,
|
|
"num_tokens": 18513286.0,
|
|
"step": 8455
|
|
},
|
|
{
|
|
"entropy": 5.613192081451416,
|
|
"epoch": 0.8396188963874553,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004938199857360068,
|
|
"loss": 5.2865,
|
|
"mean_token_accuracy": 0.15690700858831405,
|
|
"num_tokens": 18522934.0,
|
|
"step": 8460
|
|
},
|
|
{
|
|
"entropy": 5.5160599708557125,
|
|
"epoch": 0.8401151250496228,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.00049381173584926,
|
|
"loss": 5.3489,
|
|
"mean_token_accuracy": 0.15866285264492036,
|
|
"num_tokens": 18534828.0,
|
|
"step": 8465
|
|
},
|
|
{
|
|
"entropy": 5.553909063339233,
|
|
"epoch": 0.8406113537117904,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004938034805364535,
|
|
"loss": 5.3089,
|
|
"mean_token_accuracy": 0.1571136400103569,
|
|
"num_tokens": 18544733.0,
|
|
"step": 8470
|
|
},
|
|
{
|
|
"entropy": 5.582355403900147,
|
|
"epoch": 0.8411075823739579,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004937952197977923,
|
|
"loss": 5.3596,
|
|
"mean_token_accuracy": 0.15624982565641404,
|
|
"num_tokens": 18554583.0,
|
|
"step": 8475
|
|
},
|
|
{
|
|
"entropy": 5.679518318176269,
|
|
"epoch": 0.8416038110361255,
|
|
"grad_norm": 0.7890625,
|
|
"learning_rate": 0.000493786953633481,
|
|
"loss": 5.4003,
|
|
"mean_token_accuracy": 0.1517256587743759,
|
|
"num_tokens": 18566503.0,
|
|
"step": 8480
|
|
},
|
|
{
|
|
"entropy": 5.59273943901062,
|
|
"epoch": 0.842100039698293,
|
|
"grad_norm": 0.73828125,
|
|
"learning_rate": 0.0004937786820437248,
|
|
"loss": 5.3433,
|
|
"mean_token_accuracy": 0.15839931070804597,
|
|
"num_tokens": 18578161.0,
|
|
"step": 8485
|
|
},
|
|
{
|
|
"entropy": 5.565155076980591,
|
|
"epoch": 0.8425962683604605,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004937704050287286,
|
|
"loss": 5.4025,
|
|
"mean_token_accuracy": 0.1599843755364418,
|
|
"num_tokens": 18588212.0,
|
|
"step": 8490
|
|
},
|
|
{
|
|
"entropy": 5.683433914184571,
|
|
"epoch": 0.843092497022628,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.0004937621225886978,
|
|
"loss": 5.3947,
|
|
"mean_token_accuracy": 0.14981088191270828,
|
|
"num_tokens": 18601293.0,
|
|
"step": 8495
|
|
},
|
|
{
|
|
"entropy": 5.619963788986206,
|
|
"epoch": 0.8435887256847956,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004937538347238378,
|
|
"loss": 5.443,
|
|
"mean_token_accuracy": 0.15082540810108186,
|
|
"num_tokens": 18613316.0,
|
|
"step": 8500
|
|
},
|
|
{
|
|
"entropy": 5.584312963485718,
|
|
"epoch": 0.8440849543469631,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.000493745541434354,
|
|
"loss": 5.3798,
|
|
"mean_token_accuracy": 0.1587498351931572,
|
|
"num_tokens": 18624461.0,
|
|
"step": 8505
|
|
},
|
|
{
|
|
"entropy": 5.616329383850098,
|
|
"epoch": 0.8445811830091307,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004937372427204522,
|
|
"loss": 5.286,
|
|
"mean_token_accuracy": 0.15837130844593048,
|
|
"num_tokens": 18635165.0,
|
|
"step": 8510
|
|
},
|
|
{
|
|
"entropy": 5.602617645263672,
|
|
"epoch": 0.8450774116712981,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004937289385823382,
|
|
"loss": 5.3381,
|
|
"mean_token_accuracy": 0.16230068504810333,
|
|
"num_tokens": 18646649.0,
|
|
"step": 8515
|
|
},
|
|
{
|
|
"entropy": 5.515107536315918,
|
|
"epoch": 0.8455736403334657,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004937206290202176,
|
|
"loss": 5.3213,
|
|
"mean_token_accuracy": 0.15529693216085433,
|
|
"num_tokens": 18658527.0,
|
|
"step": 8520
|
|
},
|
|
{
|
|
"entropy": 5.590562391281128,
|
|
"epoch": 0.8460698689956332,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004937123140342969,
|
|
"loss": 5.3092,
|
|
"mean_token_accuracy": 0.1559583380818367,
|
|
"num_tokens": 18669463.0,
|
|
"step": 8525
|
|
},
|
|
{
|
|
"entropy": 5.620056390762329,
|
|
"epoch": 0.8465660976578007,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.000493703993624782,
|
|
"loss": 5.3604,
|
|
"mean_token_accuracy": 0.15542348027229308,
|
|
"num_tokens": 18680806.0,
|
|
"step": 8530
|
|
},
|
|
{
|
|
"entropy": 5.5720561981201175,
|
|
"epoch": 0.8470623263199683,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004936956677918794,
|
|
"loss": 5.3553,
|
|
"mean_token_accuracy": 0.15351967364549637,
|
|
"num_tokens": 18692124.0,
|
|
"step": 8535
|
|
},
|
|
{
|
|
"entropy": 5.618325567245483,
|
|
"epoch": 0.8475585549821357,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004936873365357955,
|
|
"loss": 5.3882,
|
|
"mean_token_accuracy": 0.1555369660258293,
|
|
"num_tokens": 18702017.0,
|
|
"step": 8540
|
|
},
|
|
{
|
|
"entropy": 5.524436569213867,
|
|
"epoch": 0.8480547836443033,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004936789998567368,
|
|
"loss": 5.2841,
|
|
"mean_token_accuracy": 0.16143308579921722,
|
|
"num_tokens": 18713205.0,
|
|
"step": 8545
|
|
},
|
|
{
|
|
"entropy": 5.585800981521606,
|
|
"epoch": 0.8485510123064708,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004936706577549101,
|
|
"loss": 5.2979,
|
|
"mean_token_accuracy": 0.15933337211608886,
|
|
"num_tokens": 18724165.0,
|
|
"step": 8550
|
|
},
|
|
{
|
|
"entropy": 5.595956087112427,
|
|
"epoch": 0.8490472409686384,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004936623102305223,
|
|
"loss": 5.3747,
|
|
"mean_token_accuracy": 0.1568777233362198,
|
|
"num_tokens": 18735155.0,
|
|
"step": 8555
|
|
},
|
|
{
|
|
"entropy": 5.600664472579956,
|
|
"epoch": 0.8495434696308058,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004936539572837804,
|
|
"loss": 5.4374,
|
|
"mean_token_accuracy": 0.1557487815618515,
|
|
"num_tokens": 18746228.0,
|
|
"step": 8560
|
|
},
|
|
{
|
|
"entropy": 5.60756025314331,
|
|
"epoch": 0.8500396982929734,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004936455989148916,
|
|
"loss": 5.3961,
|
|
"mean_token_accuracy": 0.15620139092206956,
|
|
"num_tokens": 18756638.0,
|
|
"step": 8565
|
|
},
|
|
{
|
|
"entropy": 5.643007850646972,
|
|
"epoch": 0.8505359269551409,
|
|
"grad_norm": 0.78125,
|
|
"learning_rate": 0.0004936372351240629,
|
|
"loss": 5.3628,
|
|
"mean_token_accuracy": 0.15929753482341766,
|
|
"num_tokens": 18768651.0,
|
|
"step": 8570
|
|
},
|
|
{
|
|
"entropy": 5.695384788513183,
|
|
"epoch": 0.8510321556173085,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.000493628865911502,
|
|
"loss": 5.4583,
|
|
"mean_token_accuracy": 0.15153556019067765,
|
|
"num_tokens": 18780399.0,
|
|
"step": 8575
|
|
},
|
|
{
|
|
"entropy": 5.554955005645752,
|
|
"epoch": 0.851528384279476,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004936204912774163,
|
|
"loss": 5.3225,
|
|
"mean_token_accuracy": 0.15521062090992926,
|
|
"num_tokens": 18791927.0,
|
|
"step": 8580
|
|
},
|
|
{
|
|
"entropy": 5.536719274520874,
|
|
"epoch": 0.8520246129416436,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004936121112220135,
|
|
"loss": 5.313,
|
|
"mean_token_accuracy": 0.15647718459367752,
|
|
"num_tokens": 18802779.0,
|
|
"step": 8585
|
|
},
|
|
{
|
|
"entropy": 5.569678592681885,
|
|
"epoch": 0.852520841603811,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004936037257455015,
|
|
"loss": 5.3167,
|
|
"mean_token_accuracy": 0.15982182323932648,
|
|
"num_tokens": 18813123.0,
|
|
"step": 8590
|
|
},
|
|
{
|
|
"entropy": 5.558087778091431,
|
|
"epoch": 0.8530170702659786,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.000493595334848088,
|
|
"loss": 5.3132,
|
|
"mean_token_accuracy": 0.16583057940006257,
|
|
"num_tokens": 18823699.0,
|
|
"step": 8595
|
|
},
|
|
{
|
|
"entropy": 5.650063419342041,
|
|
"epoch": 0.8535132989281461,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004935869385299813,
|
|
"loss": 5.4673,
|
|
"mean_token_accuracy": 0.14959802478551865,
|
|
"num_tokens": 18835450.0,
|
|
"step": 8600
|
|
},
|
|
{
|
|
"entropy": 5.563158893585205,
|
|
"epoch": 0.8540095275903136,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004935785367913896,
|
|
"loss": 5.3156,
|
|
"mean_token_accuracy": 0.15441120266914368,
|
|
"num_tokens": 18845919.0,
|
|
"step": 8605
|
|
},
|
|
{
|
|
"entropy": 5.624350547790527,
|
|
"epoch": 0.8545057562524812,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004935701296325212,
|
|
"loss": 5.4302,
|
|
"mean_token_accuracy": 0.1497267834842205,
|
|
"num_tokens": 18858376.0,
|
|
"step": 8610
|
|
},
|
|
{
|
|
"entropy": 5.6011314868927,
|
|
"epoch": 0.8550019849146486,
|
|
"grad_norm": 0.7578125,
|
|
"learning_rate": 0.0004935617170535845,
|
|
"loss": 5.3874,
|
|
"mean_token_accuracy": 0.1607848286628723,
|
|
"num_tokens": 18870456.0,
|
|
"step": 8615
|
|
},
|
|
{
|
|
"entropy": 5.594962406158447,
|
|
"epoch": 0.8554982135768162,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004935532990547882,
|
|
"loss": 5.3963,
|
|
"mean_token_accuracy": 0.157123002409935,
|
|
"num_tokens": 18882174.0,
|
|
"step": 8620
|
|
},
|
|
{
|
|
"entropy": 5.691591024398804,
|
|
"epoch": 0.8559944422389837,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004935448756363409,
|
|
"loss": 5.5157,
|
|
"mean_token_accuracy": 0.15398339480161666,
|
|
"num_tokens": 18892982.0,
|
|
"step": 8625
|
|
},
|
|
{
|
|
"entropy": 5.6582964897155765,
|
|
"epoch": 0.8564906709011513,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004935364467984518,
|
|
"loss": 5.3306,
|
|
"mean_token_accuracy": 0.16034651547670364,
|
|
"num_tokens": 18903557.0,
|
|
"step": 8630
|
|
},
|
|
{
|
|
"entropy": 5.655878257751465,
|
|
"epoch": 0.8569868995633187,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004935280125413295,
|
|
"loss": 5.4761,
|
|
"mean_token_accuracy": 0.15420986860990524,
|
|
"num_tokens": 18914912.0,
|
|
"step": 8635
|
|
},
|
|
{
|
|
"entropy": 5.65370626449585,
|
|
"epoch": 0.8574831282254863,
|
|
"grad_norm": 0.7890625,
|
|
"learning_rate": 0.0004935195728651836,
|
|
"loss": 5.4052,
|
|
"mean_token_accuracy": 0.1553529679775238,
|
|
"num_tokens": 18927773.0,
|
|
"step": 8640
|
|
},
|
|
{
|
|
"entropy": 5.596816492080689,
|
|
"epoch": 0.8579793568876538,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.000493511127770223,
|
|
"loss": 5.3631,
|
|
"mean_token_accuracy": 0.15304585546255112,
|
|
"num_tokens": 18938313.0,
|
|
"step": 8645
|
|
},
|
|
{
|
|
"entropy": 5.556548643112182,
|
|
"epoch": 0.8584755855498214,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004935026772566574,
|
|
"loss": 5.3083,
|
|
"mean_token_accuracy": 0.16367752850055695,
|
|
"num_tokens": 18948600.0,
|
|
"step": 8650
|
|
},
|
|
{
|
|
"entropy": 5.638124942779541,
|
|
"epoch": 0.8589718142119889,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004934942213246961,
|
|
"loss": 5.3981,
|
|
"mean_token_accuracy": 0.1521536260843277,
|
|
"num_tokens": 18958927.0,
|
|
"step": 8655
|
|
},
|
|
{
|
|
"entropy": 5.583178329467773,
|
|
"epoch": 0.8594680428741565,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.000493485759974549,
|
|
"loss": 5.331,
|
|
"mean_token_accuracy": 0.15029305815696717,
|
|
"num_tokens": 18968625.0,
|
|
"step": 8660
|
|
},
|
|
{
|
|
"entropy": 5.485573816299438,
|
|
"epoch": 0.8599642715363239,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004934772932064259,
|
|
"loss": 5.2701,
|
|
"mean_token_accuracy": 0.1593043938279152,
|
|
"num_tokens": 18979772.0,
|
|
"step": 8665
|
|
},
|
|
{
|
|
"entropy": 5.617111444473267,
|
|
"epoch": 0.8604605001984915,
|
|
"grad_norm": 0.77734375,
|
|
"learning_rate": 0.0004934688210205367,
|
|
"loss": 5.4254,
|
|
"mean_token_accuracy": 0.1574472039937973,
|
|
"num_tokens": 18991522.0,
|
|
"step": 8670
|
|
},
|
|
{
|
|
"entropy": 5.635264205932617,
|
|
"epoch": 0.860956728860659,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004934603434170913,
|
|
"loss": 5.3878,
|
|
"mean_token_accuracy": 0.15423630475997924,
|
|
"num_tokens": 19002479.0,
|
|
"step": 8675
|
|
},
|
|
{
|
|
"entropy": 5.612432909011841,
|
|
"epoch": 0.8614529575228265,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004934518603963003,
|
|
"loss": 5.4496,
|
|
"mean_token_accuracy": 0.15168481767177583,
|
|
"num_tokens": 19013254.0,
|
|
"step": 8680
|
|
},
|
|
{
|
|
"entropy": 5.559790992736817,
|
|
"epoch": 0.861949186184994,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004934433719583739,
|
|
"loss": 5.2852,
|
|
"mean_token_accuracy": 0.1610727444291115,
|
|
"num_tokens": 19023943.0,
|
|
"step": 8685
|
|
},
|
|
{
|
|
"entropy": 5.655515956878662,
|
|
"epoch": 0.8624454148471615,
|
|
"grad_norm": 0.77734375,
|
|
"learning_rate": 0.0004934348781035226,
|
|
"loss": 5.4075,
|
|
"mean_token_accuracy": 0.15645059943199158,
|
|
"num_tokens": 19034672.0,
|
|
"step": 8690
|
|
},
|
|
{
|
|
"entropy": 5.66617374420166,
|
|
"epoch": 0.8629416435093291,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.000493426378831957,
|
|
"loss": 5.4038,
|
|
"mean_token_accuracy": 0.16310026049613952,
|
|
"num_tokens": 19045758.0,
|
|
"step": 8695
|
|
},
|
|
{
|
|
"entropy": 5.554395055770874,
|
|
"epoch": 0.8634378721714966,
|
|
"grad_norm": 0.77734375,
|
|
"learning_rate": 0.0004934178741438877,
|
|
"loss": 5.3877,
|
|
"mean_token_accuracy": 0.15989836752414704,
|
|
"num_tokens": 19057526.0,
|
|
"step": 8700
|
|
},
|
|
{
|
|
"entropy": 5.52222466468811,
|
|
"epoch": 0.8639341008336642,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.000493409364039526,
|
|
"loss": 5.2491,
|
|
"mean_token_accuracy": 0.15929249972105025,
|
|
"num_tokens": 19069657.0,
|
|
"step": 8705
|
|
},
|
|
{
|
|
"entropy": 5.575068140029908,
|
|
"epoch": 0.8644303294958317,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004934008485190825,
|
|
"loss": 5.3201,
|
|
"mean_token_accuracy": 0.15782753378152847,
|
|
"num_tokens": 19080699.0,
|
|
"step": 8710
|
|
},
|
|
{
|
|
"entropy": 5.545238065719604,
|
|
"epoch": 0.8649265581579992,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0004933923275827687,
|
|
"loss": 5.3345,
|
|
"mean_token_accuracy": 0.15497382283210753,
|
|
"num_tokens": 19093041.0,
|
|
"step": 8715
|
|
},
|
|
{
|
|
"entropy": 5.645983695983887,
|
|
"epoch": 0.8654227868201667,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004933838012307957,
|
|
"loss": 5.3964,
|
|
"mean_token_accuracy": 0.15230150669813156,
|
|
"num_tokens": 19104249.0,
|
|
"step": 8720
|
|
},
|
|
{
|
|
"entropy": 5.627114582061767,
|
|
"epoch": 0.8659190154823343,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.000493375269463375,
|
|
"loss": 5.364,
|
|
"mean_token_accuracy": 0.15343012809753417,
|
|
"num_tokens": 19114434.0,
|
|
"step": 8725
|
|
},
|
|
{
|
|
"entropy": 5.577263927459716,
|
|
"epoch": 0.8664152441445018,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004933667322807182,
|
|
"loss": 5.3651,
|
|
"mean_token_accuracy": 0.15154905319213868,
|
|
"num_tokens": 19124814.0,
|
|
"step": 8730
|
|
},
|
|
{
|
|
"entropy": 5.59411849975586,
|
|
"epoch": 0.8669114728066694,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.000493358189683037,
|
|
"loss": 5.3994,
|
|
"mean_token_accuracy": 0.15635800510644912,
|
|
"num_tokens": 19135205.0,
|
|
"step": 8735
|
|
},
|
|
{
|
|
"entropy": 5.556440114974976,
|
|
"epoch": 0.8674077014688368,
|
|
"grad_norm": 0.796875,
|
|
"learning_rate": 0.0004933496416705432,
|
|
"loss": 5.2619,
|
|
"mean_token_accuracy": 0.16255960166454314,
|
|
"num_tokens": 19147117.0,
|
|
"step": 8740
|
|
},
|
|
{
|
|
"entropy": 5.572934341430664,
|
|
"epoch": 0.8679039301310044,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004933410882434488,
|
|
"loss": 5.3638,
|
|
"mean_token_accuracy": 0.15515206605196,
|
|
"num_tokens": 19158131.0,
|
|
"step": 8745
|
|
},
|
|
{
|
|
"entropy": 5.547046804428101,
|
|
"epoch": 0.8684001587931719,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004933325294019659,
|
|
"loss": 5.2526,
|
|
"mean_token_accuracy": 0.1608527883887291,
|
|
"num_tokens": 19168820.0,
|
|
"step": 8750
|
|
},
|
|
{
|
|
"entropy": 5.623052787780762,
|
|
"epoch": 0.8688963874553394,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004933239651463068,
|
|
"loss": 5.3474,
|
|
"mean_token_accuracy": 0.16261591613292695,
|
|
"num_tokens": 19178845.0,
|
|
"step": 8755
|
|
},
|
|
{
|
|
"entropy": 5.588670635223389,
|
|
"epoch": 0.869392616117507,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004933153954766837,
|
|
"loss": 5.3112,
|
|
"mean_token_accuracy": 0.15922656804323196,
|
|
"num_tokens": 19190830.0,
|
|
"step": 8760
|
|
},
|
|
{
|
|
"entropy": 5.448131847381592,
|
|
"epoch": 0.8698888447796744,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004933068203933092,
|
|
"loss": 5.1773,
|
|
"mean_token_accuracy": 0.1624591201543808,
|
|
"num_tokens": 19202056.0,
|
|
"step": 8765
|
|
},
|
|
{
|
|
"entropy": 5.514496946334839,
|
|
"epoch": 0.870385073441842,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.000493298239896396,
|
|
"loss": 5.3821,
|
|
"mean_token_accuracy": 0.15466125309467316,
|
|
"num_tokens": 19213497.0,
|
|
"step": 8770
|
|
},
|
|
{
|
|
"entropy": 5.659720468521118,
|
|
"epoch": 0.8708813021040095,
|
|
"grad_norm": 0.7890625,
|
|
"learning_rate": 0.0004932896539861568,
|
|
"loss": 5.4068,
|
|
"mean_token_accuracy": 0.15293225944042205,
|
|
"num_tokens": 19226103.0,
|
|
"step": 8775
|
|
},
|
|
{
|
|
"entropy": 5.617606067657471,
|
|
"epoch": 0.8713775307661771,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004932810626628047,
|
|
"loss": 5.4197,
|
|
"mean_token_accuracy": 0.1572378620505333,
|
|
"num_tokens": 19237297.0,
|
|
"step": 8780
|
|
},
|
|
{
|
|
"entropy": 5.600645256042481,
|
|
"epoch": 0.8718737594283446,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004932724659265526,
|
|
"loss": 5.3421,
|
|
"mean_token_accuracy": 0.15571752786636353,
|
|
"num_tokens": 19247537.0,
|
|
"step": 8785
|
|
},
|
|
{
|
|
"entropy": 5.508291578292846,
|
|
"epoch": 0.8723699880905121,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.0004932638637776134,
|
|
"loss": 5.2609,
|
|
"mean_token_accuracy": 0.16021536141633988,
|
|
"num_tokens": 19260465.0,
|
|
"step": 8790
|
|
},
|
|
{
|
|
"entropy": 5.590749645233155,
|
|
"epoch": 0.8728662167526796,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.000493255256216201,
|
|
"loss": 5.3521,
|
|
"mean_token_accuracy": 0.15528776496648788,
|
|
"num_tokens": 19270534.0,
|
|
"step": 8795
|
|
},
|
|
{
|
|
"entropy": 5.553844165802002,
|
|
"epoch": 0.8733624454148472,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004932466432425284,
|
|
"loss": 5.3579,
|
|
"mean_token_accuracy": 0.15564285218715668,
|
|
"num_tokens": 19281551.0,
|
|
"step": 8800
|
|
},
|
|
{
|
|
"entropy": 5.538980484008789,
|
|
"epoch": 0.8738586740770147,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004932380248568094,
|
|
"loss": 5.2982,
|
|
"mean_token_accuracy": 0.15979526042938233,
|
|
"num_tokens": 19293300.0,
|
|
"step": 8805
|
|
},
|
|
{
|
|
"entropy": 5.5843109607696535,
|
|
"epoch": 0.8743549027391823,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004932294010592575,
|
|
"loss": 5.2429,
|
|
"mean_token_accuracy": 0.1628882959485054,
|
|
"num_tokens": 19302701.0,
|
|
"step": 8810
|
|
},
|
|
{
|
|
"entropy": 5.597626638412476,
|
|
"epoch": 0.8748511314013497,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004932207718500868,
|
|
"loss": 5.3214,
|
|
"mean_token_accuracy": 0.15882567018270494,
|
|
"num_tokens": 19313024.0,
|
|
"step": 8815
|
|
},
|
|
{
|
|
"entropy": 5.588980340957642,
|
|
"epoch": 0.8753473600635173,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004932121372295112,
|
|
"loss": 5.3338,
|
|
"mean_token_accuracy": 0.15698196291923522,
|
|
"num_tokens": 19324014.0,
|
|
"step": 8820
|
|
},
|
|
{
|
|
"entropy": 5.558774614334107,
|
|
"epoch": 0.8758435887256848,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004932034971977448,
|
|
"loss": 5.3609,
|
|
"mean_token_accuracy": 0.15866709500551224,
|
|
"num_tokens": 19334226.0,
|
|
"step": 8825
|
|
},
|
|
{
|
|
"entropy": 5.643746709823608,
|
|
"epoch": 0.8763398173878523,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004931948517550019,
|
|
"loss": 5.3976,
|
|
"mean_token_accuracy": 0.15261635184288025,
|
|
"num_tokens": 19344363.0,
|
|
"step": 8830
|
|
},
|
|
{
|
|
"entropy": 5.588718843460083,
|
|
"epoch": 0.8768360460500199,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004931862009014968,
|
|
"loss": 5.4166,
|
|
"mean_token_accuracy": 0.15612666457891464,
|
|
"num_tokens": 19354915.0,
|
|
"step": 8835
|
|
},
|
|
{
|
|
"entropy": 5.640223169326783,
|
|
"epoch": 0.8773322747121873,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.000493177544637444,
|
|
"loss": 5.4139,
|
|
"mean_token_accuracy": 0.15273035913705826,
|
|
"num_tokens": 19365570.0,
|
|
"step": 8840
|
|
},
|
|
{
|
|
"entropy": 5.627228689193726,
|
|
"epoch": 0.8778285033743549,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004931688829630582,
|
|
"loss": 5.3306,
|
|
"mean_token_accuracy": 0.16338916271924972,
|
|
"num_tokens": 19375731.0,
|
|
"step": 8845
|
|
},
|
|
{
|
|
"entropy": 5.562938117980957,
|
|
"epoch": 0.8783247320365224,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004931602158785544,
|
|
"loss": 5.2857,
|
|
"mean_token_accuracy": 0.16078079342842103,
|
|
"num_tokens": 19386248.0,
|
|
"step": 8850
|
|
},
|
|
{
|
|
"entropy": 5.56929874420166,
|
|
"epoch": 0.87882096069869,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004931515433841472,
|
|
"loss": 5.298,
|
|
"mean_token_accuracy": 0.163205586373806,
|
|
"num_tokens": 19397593.0,
|
|
"step": 8855
|
|
},
|
|
{
|
|
"entropy": 5.600165939331054,
|
|
"epoch": 0.8793171893608575,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004931428654800518,
|
|
"loss": 5.3875,
|
|
"mean_token_accuracy": 0.15078756362199783,
|
|
"num_tokens": 19409701.0,
|
|
"step": 8860
|
|
},
|
|
{
|
|
"entropy": 5.584780073165893,
|
|
"epoch": 0.879813418023025,
|
|
"grad_norm": 0.80078125,
|
|
"learning_rate": 0.0004931341821664834,
|
|
"loss": 5.3642,
|
|
"mean_token_accuracy": 0.15765655636787415,
|
|
"num_tokens": 19420280.0,
|
|
"step": 8865
|
|
},
|
|
{
|
|
"entropy": 5.602287340164184,
|
|
"epoch": 0.8803096466851925,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004931254934436573,
|
|
"loss": 5.3432,
|
|
"mean_token_accuracy": 0.15591977834701537,
|
|
"num_tokens": 19432208.0,
|
|
"step": 8870
|
|
},
|
|
{
|
|
"entropy": 5.682718276977539,
|
|
"epoch": 0.8808058753473601,
|
|
"grad_norm": 0.79296875,
|
|
"learning_rate": 0.0004931167993117891,
|
|
"loss": 5.453,
|
|
"mean_token_accuracy": 0.15500149577856065,
|
|
"num_tokens": 19443333.0,
|
|
"step": 8875
|
|
},
|
|
{
|
|
"entropy": 5.497708368301391,
|
|
"epoch": 0.8813021040095276,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004931080997710942,
|
|
"loss": 5.2273,
|
|
"mean_token_accuracy": 0.16059327721595765,
|
|
"num_tokens": 19452867.0,
|
|
"step": 8880
|
|
},
|
|
{
|
|
"entropy": 5.498044013977051,
|
|
"epoch": 0.8817983326716952,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0004930993948217884,
|
|
"loss": 5.2697,
|
|
"mean_token_accuracy": 0.16537645161151887,
|
|
"num_tokens": 19463021.0,
|
|
"step": 8885
|
|
},
|
|
{
|
|
"entropy": 5.6087535381317135,
|
|
"epoch": 0.8822945613338626,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004930906844640876,
|
|
"loss": 5.3973,
|
|
"mean_token_accuracy": 0.1516403153538704,
|
|
"num_tokens": 19474092.0,
|
|
"step": 8890
|
|
},
|
|
{
|
|
"entropy": 5.563568878173828,
|
|
"epoch": 0.8827907899960302,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004930819686982077,
|
|
"loss": 5.367,
|
|
"mean_token_accuracy": 0.15222940146923064,
|
|
"num_tokens": 19486035.0,
|
|
"step": 8895
|
|
},
|
|
{
|
|
"entropy": 5.539292335510254,
|
|
"epoch": 0.8832870186581977,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.000493073247524365,
|
|
"loss": 5.293,
|
|
"mean_token_accuracy": 0.1607646718621254,
|
|
"num_tokens": 19497484.0,
|
|
"step": 8900
|
|
},
|
|
{
|
|
"entropy": 5.5990314960479735,
|
|
"epoch": 0.8837832473203652,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004930645209427756,
|
|
"loss": 5.4007,
|
|
"mean_token_accuracy": 0.15190002620220183,
|
|
"num_tokens": 19508463.0,
|
|
"step": 8905
|
|
},
|
|
{
|
|
"entropy": 5.594696378707885,
|
|
"epoch": 0.8842794759825328,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.000493055788953656,
|
|
"loss": 5.3361,
|
|
"mean_token_accuracy": 0.15622231513261794,
|
|
"num_tokens": 19520260.0,
|
|
"step": 8910
|
|
},
|
|
{
|
|
"entropy": 5.547523164749146,
|
|
"epoch": 0.8847757046447002,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004930470515572227,
|
|
"loss": 5.2948,
|
|
"mean_token_accuracy": 0.15937747359275817,
|
|
"num_tokens": 19531621.0,
|
|
"step": 8915
|
|
},
|
|
{
|
|
"entropy": 5.589425563812256,
|
|
"epoch": 0.8852719333068678,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004930383087536923,
|
|
"loss": 5.2709,
|
|
"mean_token_accuracy": 0.15654692500829698,
|
|
"num_tokens": 19543271.0,
|
|
"step": 8920
|
|
},
|
|
{
|
|
"entropy": 5.649059867858886,
|
|
"epoch": 0.8857681619690353,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004930295605432818,
|
|
"loss": 5.4347,
|
|
"mean_token_accuracy": 0.16115086674690246,
|
|
"num_tokens": 19555178.0,
|
|
"step": 8925
|
|
},
|
|
{
|
|
"entropy": 5.625226259231567,
|
|
"epoch": 0.8862643906312029,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004930208069262079,
|
|
"loss": 5.3564,
|
|
"mean_token_accuracy": 0.15755318850278854,
|
|
"num_tokens": 19565153.0,
|
|
"step": 8930
|
|
},
|
|
{
|
|
"entropy": 5.525291490554809,
|
|
"epoch": 0.8867606192933704,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004930120479026878,
|
|
"loss": 5.2907,
|
|
"mean_token_accuracy": 0.16522422730922698,
|
|
"num_tokens": 19575608.0,
|
|
"step": 8935
|
|
},
|
|
{
|
|
"entropy": 5.594865846633911,
|
|
"epoch": 0.8872568479555379,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.0004930032834729388,
|
|
"loss": 5.25,
|
|
"mean_token_accuracy": 0.16316999047994613,
|
|
"num_tokens": 19587556.0,
|
|
"step": 8940
|
|
},
|
|
{
|
|
"entropy": 5.513002729415893,
|
|
"epoch": 0.8877530766177054,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.000492994513637178,
|
|
"loss": 5.3003,
|
|
"mean_token_accuracy": 0.15882664620876313,
|
|
"num_tokens": 19597341.0,
|
|
"step": 8945
|
|
},
|
|
{
|
|
"entropy": 5.5407734394073485,
|
|
"epoch": 0.888249305279873,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0004929857383956229,
|
|
"loss": 5.3284,
|
|
"mean_token_accuracy": 0.15448749512434007,
|
|
"num_tokens": 19608431.0,
|
|
"step": 8950
|
|
},
|
|
{
|
|
"entropy": 5.565536546707153,
|
|
"epoch": 0.8887455339420405,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004929769577484914,
|
|
"loss": 5.3106,
|
|
"mean_token_accuracy": 0.16429621279239653,
|
|
"num_tokens": 19619645.0,
|
|
"step": 8955
|
|
},
|
|
{
|
|
"entropy": 5.532659196853638,
|
|
"epoch": 0.8892417626042081,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.000492968171696001,
|
|
"loss": 5.2675,
|
|
"mean_token_accuracy": 0.16849614828824996,
|
|
"num_tokens": 19630412.0,
|
|
"step": 8960
|
|
},
|
|
{
|
|
"entropy": 5.61044225692749,
|
|
"epoch": 0.8897379912663755,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004929593802383696,
|
|
"loss": 5.3337,
|
|
"mean_token_accuracy": 0.15720237493515016,
|
|
"num_tokens": 19640055.0,
|
|
"step": 8965
|
|
},
|
|
{
|
|
"entropy": 5.5500359535217285,
|
|
"epoch": 0.8902342199285431,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004929505833758152,
|
|
"loss": 5.3467,
|
|
"mean_token_accuracy": 0.1521917000412941,
|
|
"num_tokens": 19650814.0,
|
|
"step": 8970
|
|
},
|
|
{
|
|
"entropy": 5.59323296546936,
|
|
"epoch": 0.8907304485907106,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004929417811085561,
|
|
"loss": 5.3229,
|
|
"mean_token_accuracy": 0.16198962926864624,
|
|
"num_tokens": 19663669.0,
|
|
"step": 8975
|
|
},
|
|
{
|
|
"entropy": 5.661463022232056,
|
|
"epoch": 0.8912266772528781,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004929329734368103,
|
|
"loss": 5.4089,
|
|
"mean_token_accuracy": 0.15372903198003768,
|
|
"num_tokens": 19675851.0,
|
|
"step": 8980
|
|
},
|
|
{
|
|
"entropy": 5.586727428436279,
|
|
"epoch": 0.8917229059150457,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004929241603607964,
|
|
"loss": 5.292,
|
|
"mean_token_accuracy": 0.16683239191770555,
|
|
"num_tokens": 19686613.0,
|
|
"step": 8985
|
|
},
|
|
{
|
|
"entropy": 5.494939517974854,
|
|
"epoch": 0.8922191345772131,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.000492915341880733,
|
|
"loss": 5.2283,
|
|
"mean_token_accuracy": 0.15991657227277756,
|
|
"num_tokens": 19696419.0,
|
|
"step": 8990
|
|
},
|
|
{
|
|
"entropy": 5.560398435592651,
|
|
"epoch": 0.8927153632393807,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004929065179968387,
|
|
"loss": 5.3245,
|
|
"mean_token_accuracy": 0.15727977454662323,
|
|
"num_tokens": 19707269.0,
|
|
"step": 8995
|
|
},
|
|
{
|
|
"entropy": 5.645032024383545,
|
|
"epoch": 0.8932115919015482,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004928976887093321,
|
|
"loss": 5.3703,
|
|
"mean_token_accuracy": 0.15670965164899825,
|
|
"num_tokens": 19716099.0,
|
|
"step": 9000
|
|
},
|
|
{
|
|
"epoch": 0.8932115919015482,
|
|
"eval_entropy": 5.385663988471853,
|
|
"eval_loss": 5.402402400970459,
|
|
"eval_mean_token_accuracy": 0.159667709009024,
|
|
"eval_num_tokens": 19716099.0,
|
|
"eval_runtime": 20.4365,
|
|
"eval_samples_per_second": 1647.492,
|
|
"eval_steps_per_second": 205.955,
|
|
"step": 9000
|
|
},
|
|
{
|
|
"entropy": 5.568923807144165,
|
|
"epoch": 0.8937078205637158,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004928888540184325,
|
|
"loss": 5.3618,
|
|
"mean_token_accuracy": 0.15348413735628127,
|
|
"num_tokens": 19726632.0,
|
|
"step": 9005
|
|
},
|
|
{
|
|
"entropy": 5.54155421257019,
|
|
"epoch": 0.8942040492258833,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004928800139243587,
|
|
"loss": 5.2618,
|
|
"mean_token_accuracy": 0.162228325009346,
|
|
"num_tokens": 19737929.0,
|
|
"step": 9010
|
|
},
|
|
{
|
|
"entropy": 5.564952373504639,
|
|
"epoch": 0.8947002778880508,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004928711684273302,
|
|
"loss": 5.2871,
|
|
"mean_token_accuracy": 0.15866970866918564,
|
|
"num_tokens": 19748191.0,
|
|
"step": 9015
|
|
},
|
|
{
|
|
"entropy": 5.584346628189087,
|
|
"epoch": 0.8951965065502183,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.0004928623175275661,
|
|
"loss": 5.3389,
|
|
"mean_token_accuracy": 0.16422507613897325,
|
|
"num_tokens": 19758892.0,
|
|
"step": 9020
|
|
},
|
|
{
|
|
"entropy": 5.53707799911499,
|
|
"epoch": 0.8956927352123859,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004928534612252862,
|
|
"loss": 5.2234,
|
|
"mean_token_accuracy": 0.16193969398736954,
|
|
"num_tokens": 19769120.0,
|
|
"step": 9025
|
|
},
|
|
{
|
|
"entropy": 5.522628831863403,
|
|
"epoch": 0.8961889638745534,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004928445995207095,
|
|
"loss": 5.2856,
|
|
"mean_token_accuracy": 0.16119020879268647,
|
|
"num_tokens": 19779484.0,
|
|
"step": 9030
|
|
},
|
|
{
|
|
"entropy": 5.590908098220825,
|
|
"epoch": 0.896685192536721,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004928357324140564,
|
|
"loss": 5.319,
|
|
"mean_token_accuracy": 0.15963810235261916,
|
|
"num_tokens": 19790438.0,
|
|
"step": 9035
|
|
},
|
|
{
|
|
"entropy": 5.64152512550354,
|
|
"epoch": 0.8971814211988884,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004928268599055465,
|
|
"loss": 5.4056,
|
|
"mean_token_accuracy": 0.15609167665243148,
|
|
"num_tokens": 19801646.0,
|
|
"step": 9040
|
|
},
|
|
{
|
|
"entropy": 5.561574840545655,
|
|
"epoch": 0.897677649861056,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004928179819953998,
|
|
"loss": 5.2805,
|
|
"mean_token_accuracy": 0.1638476550579071,
|
|
"num_tokens": 19812887.0,
|
|
"step": 9045
|
|
},
|
|
{
|
|
"entropy": 5.5434667587280275,
|
|
"epoch": 0.8981738785232235,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004928090986838366,
|
|
"loss": 5.3475,
|
|
"mean_token_accuracy": 0.1530725747346878,
|
|
"num_tokens": 19822938.0,
|
|
"step": 9050
|
|
},
|
|
{
|
|
"entropy": 5.565565156936645,
|
|
"epoch": 0.898670107185391,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000492800209971077,
|
|
"loss": 5.2934,
|
|
"mean_token_accuracy": 0.16092495620250702,
|
|
"num_tokens": 19833988.0,
|
|
"step": 9055
|
|
},
|
|
{
|
|
"entropy": 5.635081243515015,
|
|
"epoch": 0.8991663358475586,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004927913158573416,
|
|
"loss": 5.3763,
|
|
"mean_token_accuracy": 0.15459856390953064,
|
|
"num_tokens": 19845112.0,
|
|
"step": 9060
|
|
},
|
|
{
|
|
"entropy": 5.5673318862915036,
|
|
"epoch": 0.899662564509726,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004927824163428508,
|
|
"loss": 5.3355,
|
|
"mean_token_accuracy": 0.15746665894985198,
|
|
"num_tokens": 19856304.0,
|
|
"step": 9065
|
|
},
|
|
{
|
|
"entropy": 5.552544832229614,
|
|
"epoch": 0.9001587931718936,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004927735114278254,
|
|
"loss": 5.3159,
|
|
"mean_token_accuracy": 0.15865050554275512,
|
|
"num_tokens": 19866776.0,
|
|
"step": 9070
|
|
},
|
|
{
|
|
"entropy": 5.585403299331665,
|
|
"epoch": 0.9006550218340611,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004927646011124861,
|
|
"loss": 5.2922,
|
|
"mean_token_accuracy": 0.1570994071662426,
|
|
"num_tokens": 19876392.0,
|
|
"step": 9075
|
|
},
|
|
{
|
|
"entropy": 5.599952363967896,
|
|
"epoch": 0.9011512504962287,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004927556853970539,
|
|
"loss": 5.3235,
|
|
"mean_token_accuracy": 0.15793648958206177,
|
|
"num_tokens": 19887362.0,
|
|
"step": 9080
|
|
},
|
|
{
|
|
"entropy": 5.556565523147583,
|
|
"epoch": 0.9016474791583962,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004927467642817499,
|
|
"loss": 5.3017,
|
|
"mean_token_accuracy": 0.16025232523679733,
|
|
"num_tokens": 19898989.0,
|
|
"step": 9085
|
|
},
|
|
{
|
|
"entropy": 5.594432783126831,
|
|
"epoch": 0.9021437078205637,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004927378377667955,
|
|
"loss": 5.314,
|
|
"mean_token_accuracy": 0.15048023015260698,
|
|
"num_tokens": 19910112.0,
|
|
"step": 9090
|
|
},
|
|
{
|
|
"entropy": 5.634715747833252,
|
|
"epoch": 0.9026399364827312,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.000492728905852412,
|
|
"loss": 5.4243,
|
|
"mean_token_accuracy": 0.15499950647354127,
|
|
"num_tokens": 19922601.0,
|
|
"step": 9095
|
|
},
|
|
{
|
|
"entropy": 5.572630405426025,
|
|
"epoch": 0.9031361651448988,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004927199685388205,
|
|
"loss": 5.3382,
|
|
"mean_token_accuracy": 0.16147261261940002,
|
|
"num_tokens": 19934153.0,
|
|
"step": 9100
|
|
},
|
|
{
|
|
"entropy": 5.596471452713013,
|
|
"epoch": 0.9036323938070663,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.000492711025826243,
|
|
"loss": 5.2962,
|
|
"mean_token_accuracy": 0.16143666207790375,
|
|
"num_tokens": 19944572.0,
|
|
"step": 9105
|
|
},
|
|
{
|
|
"entropy": 5.578424310684204,
|
|
"epoch": 0.9041286224692339,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004927020777149014,
|
|
"loss": 5.4103,
|
|
"mean_token_accuracy": 0.15403326451778412,
|
|
"num_tokens": 19956431.0,
|
|
"step": 9110
|
|
},
|
|
{
|
|
"entropy": 5.610340118408203,
|
|
"epoch": 0.9046248511314013,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004926931242050171,
|
|
"loss": 5.3319,
|
|
"mean_token_accuracy": 0.15525012612342834,
|
|
"num_tokens": 19968118.0,
|
|
"step": 9115
|
|
},
|
|
{
|
|
"entropy": 5.596913480758667,
|
|
"epoch": 0.9051210797935689,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004926841652968125,
|
|
"loss": 5.3947,
|
|
"mean_token_accuracy": 0.16022013872861862,
|
|
"num_tokens": 19979545.0,
|
|
"step": 9120
|
|
},
|
|
{
|
|
"entropy": 5.583328580856323,
|
|
"epoch": 0.9056173084557364,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004926752009905099,
|
|
"loss": 5.3563,
|
|
"mean_token_accuracy": 0.15155109912157058,
|
|
"num_tokens": 19989832.0,
|
|
"step": 9125
|
|
},
|
|
{
|
|
"entropy": 5.5760022640228275,
|
|
"epoch": 0.9061135371179039,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004926662312863311,
|
|
"loss": 5.3614,
|
|
"mean_token_accuracy": 0.15715830028057098,
|
|
"num_tokens": 20000935.0,
|
|
"step": 9130
|
|
},
|
|
{
|
|
"entropy": 5.5620228290557865,
|
|
"epoch": 0.9066097657800715,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004926572561844988,
|
|
"loss": 5.3679,
|
|
"mean_token_accuracy": 0.15192281007766723,
|
|
"num_tokens": 20011485.0,
|
|
"step": 9135
|
|
},
|
|
{
|
|
"entropy": 5.557519960403442,
|
|
"epoch": 0.9071059944422389,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004926482756852356,
|
|
"loss": 5.2233,
|
|
"mean_token_accuracy": 0.16481838822364808,
|
|
"num_tokens": 20023043.0,
|
|
"step": 9140
|
|
},
|
|
{
|
|
"entropy": 5.61761155128479,
|
|
"epoch": 0.9076022231044065,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004926392897887642,
|
|
"loss": 5.3365,
|
|
"mean_token_accuracy": 0.164206799864769,
|
|
"num_tokens": 20032437.0,
|
|
"step": 9145
|
|
},
|
|
{
|
|
"entropy": 5.577384328842163,
|
|
"epoch": 0.908098451766574,
|
|
"grad_norm": 0.796875,
|
|
"learning_rate": 0.0004926302984953073,
|
|
"loss": 5.3653,
|
|
"mean_token_accuracy": 0.15488700121641158,
|
|
"num_tokens": 20044662.0,
|
|
"step": 9150
|
|
},
|
|
{
|
|
"entropy": 5.567062854766846,
|
|
"epoch": 0.9085946804287416,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004926213018050881,
|
|
"loss": 5.3657,
|
|
"mean_token_accuracy": 0.15862423181533813,
|
|
"num_tokens": 20055924.0,
|
|
"step": 9155
|
|
},
|
|
{
|
|
"entropy": 5.542328882217407,
|
|
"epoch": 0.9090909090909091,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004926122997183295,
|
|
"loss": 5.3124,
|
|
"mean_token_accuracy": 0.15485553443431854,
|
|
"num_tokens": 20067909.0,
|
|
"step": 9160
|
|
},
|
|
{
|
|
"entropy": 5.589487886428833,
|
|
"epoch": 0.9095871377530766,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004926032922352546,
|
|
"loss": 5.2896,
|
|
"mean_token_accuracy": 0.1649667114019394,
|
|
"num_tokens": 20079333.0,
|
|
"step": 9165
|
|
},
|
|
{
|
|
"entropy": 5.575442457199097,
|
|
"epoch": 0.9100833664152441,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0004925942793560872,
|
|
"loss": 5.2694,
|
|
"mean_token_accuracy": 0.1613793909549713,
|
|
"num_tokens": 20089741.0,
|
|
"step": 9170
|
|
},
|
|
{
|
|
"entropy": 5.530794143676758,
|
|
"epoch": 0.9105795950774117,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004925852610810504,
|
|
"loss": 5.3042,
|
|
"mean_token_accuracy": 0.15670829117298127,
|
|
"num_tokens": 20100267.0,
|
|
"step": 9175
|
|
},
|
|
{
|
|
"entropy": 5.515627527236939,
|
|
"epoch": 0.9110758237395792,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.000492576237410368,
|
|
"loss": 5.2667,
|
|
"mean_token_accuracy": 0.1595083385705948,
|
|
"num_tokens": 20111964.0,
|
|
"step": 9180
|
|
},
|
|
{
|
|
"entropy": 5.59562497138977,
|
|
"epoch": 0.9115720524017468,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004925672083442638,
|
|
"loss": 5.3399,
|
|
"mean_token_accuracy": 0.15084489285945893,
|
|
"num_tokens": 20123132.0,
|
|
"step": 9185
|
|
},
|
|
{
|
|
"entropy": 5.54755129814148,
|
|
"epoch": 0.9120682810639142,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004925581738829616,
|
|
"loss": 5.243,
|
|
"mean_token_accuracy": 0.1625302255153656,
|
|
"num_tokens": 20134050.0,
|
|
"step": 9190
|
|
},
|
|
{
|
|
"entropy": 5.547417402267456,
|
|
"epoch": 0.9125645097260818,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004925491340266855,
|
|
"loss": 5.3128,
|
|
"mean_token_accuracy": 0.16251576989889144,
|
|
"num_tokens": 20143814.0,
|
|
"step": 9195
|
|
},
|
|
{
|
|
"entropy": 5.597006225585938,
|
|
"epoch": 0.9130607383882493,
|
|
"grad_norm": 0.7890625,
|
|
"learning_rate": 0.0004925400887756596,
|
|
"loss": 5.3789,
|
|
"mean_token_accuracy": 0.1628500372171402,
|
|
"num_tokens": 20157647.0,
|
|
"step": 9200
|
|
},
|
|
{
|
|
"entropy": 5.598450517654419,
|
|
"epoch": 0.9135569670504168,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004925310381301083,
|
|
"loss": 5.3451,
|
|
"mean_token_accuracy": 0.1600103721022606,
|
|
"num_tokens": 20168366.0,
|
|
"step": 9205
|
|
},
|
|
{
|
|
"entropy": 5.6027578830719,
|
|
"epoch": 0.9140531957125844,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.000492521982090256,
|
|
"loss": 5.3884,
|
|
"mean_token_accuracy": 0.1589035838842392,
|
|
"num_tokens": 20179362.0,
|
|
"step": 9210
|
|
},
|
|
{
|
|
"entropy": 5.5816926002502445,
|
|
"epoch": 0.9145494243747518,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004925129206563273,
|
|
"loss": 5.2859,
|
|
"mean_token_accuracy": 0.1607089161872864,
|
|
"num_tokens": 20190320.0,
|
|
"step": 9215
|
|
},
|
|
{
|
|
"entropy": 5.527514171600342,
|
|
"epoch": 0.9150456530369194,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004925038538285467,
|
|
"loss": 5.2998,
|
|
"mean_token_accuracy": 0.15989586859941482,
|
|
"num_tokens": 20201114.0,
|
|
"step": 9220
|
|
},
|
|
{
|
|
"entropy": 5.6007684707641605,
|
|
"epoch": 0.9155418816990869,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004924947816071394,
|
|
"loss": 5.3214,
|
|
"mean_token_accuracy": 0.16533045768737792,
|
|
"num_tokens": 20213351.0,
|
|
"step": 9225
|
|
},
|
|
{
|
|
"entropy": 5.560990667343139,
|
|
"epoch": 0.9160381103612545,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00049248570399233,
|
|
"loss": 5.2319,
|
|
"mean_token_accuracy": 0.16471796929836274,
|
|
"num_tokens": 20223376.0,
|
|
"step": 9230
|
|
},
|
|
{
|
|
"entropy": 5.603248834609985,
|
|
"epoch": 0.916534339023422,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.000492476620984344,
|
|
"loss": 5.3694,
|
|
"mean_token_accuracy": 0.15361211448907852,
|
|
"num_tokens": 20234248.0,
|
|
"step": 9235
|
|
},
|
|
{
|
|
"entropy": 5.5417145729064945,
|
|
"epoch": 0.9170305676855895,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004924675325834063,
|
|
"loss": 5.2953,
|
|
"mean_token_accuracy": 0.1586267977952957,
|
|
"num_tokens": 20245823.0,
|
|
"step": 9240
|
|
},
|
|
{
|
|
"entropy": 5.612440586090088,
|
|
"epoch": 0.917526796347757,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004924584387897424,
|
|
"loss": 5.3455,
|
|
"mean_token_accuracy": 0.1560446783900261,
|
|
"num_tokens": 20257003.0,
|
|
"step": 9245
|
|
},
|
|
{
|
|
"entropy": 5.644407939910889,
|
|
"epoch": 0.9180230250099246,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004924493396035777,
|
|
"loss": 5.4769,
|
|
"mean_token_accuracy": 0.1485078290104866,
|
|
"num_tokens": 20268500.0,
|
|
"step": 9250
|
|
},
|
|
{
|
|
"entropy": 5.640565633773804,
|
|
"epoch": 0.9185192536720921,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.000492440235025138,
|
|
"loss": 5.3488,
|
|
"mean_token_accuracy": 0.1620658427476883,
|
|
"num_tokens": 20279301.0,
|
|
"step": 9255
|
|
},
|
|
{
|
|
"entropy": 5.704019403457641,
|
|
"epoch": 0.9190154823342597,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004924311250546491,
|
|
"loss": 5.4476,
|
|
"mean_token_accuracy": 0.1500500410795212,
|
|
"num_tokens": 20291263.0,
|
|
"step": 9260
|
|
},
|
|
{
|
|
"entropy": 5.563519525527954,
|
|
"epoch": 0.9195117109964271,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004924220096923367,
|
|
"loss": 5.3323,
|
|
"mean_token_accuracy": 0.16030509471893312,
|
|
"num_tokens": 20301554.0,
|
|
"step": 9265
|
|
},
|
|
{
|
|
"entropy": 5.636999130249023,
|
|
"epoch": 0.9200079396585947,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004924128889384271,
|
|
"loss": 5.3545,
|
|
"mean_token_accuracy": 0.1548002302646637,
|
|
"num_tokens": 20314299.0,
|
|
"step": 9270
|
|
},
|
|
{
|
|
"entropy": 5.541638326644898,
|
|
"epoch": 0.9205041683207622,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004924037627931463,
|
|
"loss": 5.3274,
|
|
"mean_token_accuracy": 0.15818847119808196,
|
|
"num_tokens": 20324595.0,
|
|
"step": 9275
|
|
},
|
|
{
|
|
"entropy": 5.573790740966797,
|
|
"epoch": 0.9210003969829297,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004923946312567206,
|
|
"loss": 5.2908,
|
|
"mean_token_accuracy": 0.15841273218393326,
|
|
"num_tokens": 20335744.0,
|
|
"step": 9280
|
|
},
|
|
{
|
|
"entropy": 5.513968849182129,
|
|
"epoch": 0.9214966256450973,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004923854943293765,
|
|
"loss": 5.2173,
|
|
"mean_token_accuracy": 0.15823314040899278,
|
|
"num_tokens": 20346072.0,
|
|
"step": 9285
|
|
},
|
|
{
|
|
"entropy": 5.556331920623779,
|
|
"epoch": 0.9219928543072647,
|
|
"grad_norm": 0.7578125,
|
|
"learning_rate": 0.0004923763520113406,
|
|
"loss": 5.2921,
|
|
"mean_token_accuracy": 0.16727010756731034,
|
|
"num_tokens": 20357747.0,
|
|
"step": 9290
|
|
},
|
|
{
|
|
"entropy": 5.60493221282959,
|
|
"epoch": 0.9224890829694323,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004923672043028395,
|
|
"loss": 5.2813,
|
|
"mean_token_accuracy": 0.1622532695531845,
|
|
"num_tokens": 20368838.0,
|
|
"step": 9295
|
|
},
|
|
{
|
|
"entropy": 5.570999622344971,
|
|
"epoch": 0.9229853116315998,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004923580512041001,
|
|
"loss": 5.3543,
|
|
"mean_token_accuracy": 0.15649488866329192,
|
|
"num_tokens": 20380844.0,
|
|
"step": 9300
|
|
},
|
|
{
|
|
"entropy": 5.5870014190673825,
|
|
"epoch": 0.9234815402937674,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004923488927153495,
|
|
"loss": 5.3599,
|
|
"mean_token_accuracy": 0.15315917357802392,
|
|
"num_tokens": 20391739.0,
|
|
"step": 9305
|
|
},
|
|
{
|
|
"entropy": 5.597708320617675,
|
|
"epoch": 0.9239777689559349,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004923397288368146,
|
|
"loss": 5.2452,
|
|
"mean_token_accuracy": 0.16886815428733826,
|
|
"num_tokens": 20402571.0,
|
|
"step": 9310
|
|
},
|
|
{
|
|
"entropy": 5.564769697189331,
|
|
"epoch": 0.9244739976181024,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004923305595687229,
|
|
"loss": 5.2931,
|
|
"mean_token_accuracy": 0.1555173598229885,
|
|
"num_tokens": 20414766.0,
|
|
"step": 9315
|
|
},
|
|
{
|
|
"entropy": 5.518140077590942,
|
|
"epoch": 0.9249702262802699,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004923213849113015,
|
|
"loss": 5.2667,
|
|
"mean_token_accuracy": 0.15986013263463975,
|
|
"num_tokens": 20425508.0,
|
|
"step": 9320
|
|
},
|
|
{
|
|
"entropy": 5.535608434677124,
|
|
"epoch": 0.9254664549424375,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004923122048647781,
|
|
"loss": 5.2539,
|
|
"mean_token_accuracy": 0.16222997456789018,
|
|
"num_tokens": 20436128.0,
|
|
"step": 9325
|
|
},
|
|
{
|
|
"entropy": 5.5474447250366214,
|
|
"epoch": 0.925962683604605,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004923030194293802,
|
|
"loss": 5.3542,
|
|
"mean_token_accuracy": 0.15925963670015336,
|
|
"num_tokens": 20447212.0,
|
|
"step": 9330
|
|
},
|
|
{
|
|
"entropy": 5.557111740112305,
|
|
"epoch": 0.9264589122667726,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004922938286053358,
|
|
"loss": 5.2775,
|
|
"mean_token_accuracy": 0.16774797141551973,
|
|
"num_tokens": 20457770.0,
|
|
"step": 9335
|
|
},
|
|
{
|
|
"entropy": 5.611376190185547,
|
|
"epoch": 0.92695514092894,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004922846323928726,
|
|
"loss": 5.3509,
|
|
"mean_token_accuracy": 0.15740771889686583,
|
|
"num_tokens": 20468172.0,
|
|
"step": 9340
|
|
},
|
|
{
|
|
"entropy": 5.600006580352783,
|
|
"epoch": 0.9274513695911076,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004922754307922188,
|
|
"loss": 5.2834,
|
|
"mean_token_accuracy": 0.1612941011786461,
|
|
"num_tokens": 20479429.0,
|
|
"step": 9345
|
|
},
|
|
{
|
|
"entropy": 5.548315954208374,
|
|
"epoch": 0.9279475982532751,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004922662238036024,
|
|
"loss": 5.2487,
|
|
"mean_token_accuracy": 0.1618860051035881,
|
|
"num_tokens": 20490373.0,
|
|
"step": 9350
|
|
},
|
|
{
|
|
"entropy": 5.612733983993531,
|
|
"epoch": 0.9284438269154426,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004922570114272518,
|
|
"loss": 5.3664,
|
|
"mean_token_accuracy": 0.1572950229048729,
|
|
"num_tokens": 20500002.0,
|
|
"step": 9355
|
|
},
|
|
{
|
|
"entropy": 5.613262462615967,
|
|
"epoch": 0.9289400555776102,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004922477936633955,
|
|
"loss": 5.4121,
|
|
"mean_token_accuracy": 0.1551825225353241,
|
|
"num_tokens": 20512990.0,
|
|
"step": 9360
|
|
},
|
|
{
|
|
"entropy": 5.530987501144409,
|
|
"epoch": 0.9294362842397776,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004922385705122621,
|
|
"loss": 5.3286,
|
|
"mean_token_accuracy": 0.16080232709646225,
|
|
"num_tokens": 20522979.0,
|
|
"step": 9365
|
|
},
|
|
{
|
|
"entropy": 5.543492984771729,
|
|
"epoch": 0.9299325129019452,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004922293419740802,
|
|
"loss": 5.2089,
|
|
"mean_token_accuracy": 0.16384829133749007,
|
|
"num_tokens": 20534620.0,
|
|
"step": 9370
|
|
},
|
|
{
|
|
"entropy": 5.591291666030884,
|
|
"epoch": 0.9304287415641127,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004922201080490787,
|
|
"loss": 5.3088,
|
|
"mean_token_accuracy": 0.15611242055892943,
|
|
"num_tokens": 20545526.0,
|
|
"step": 9375
|
|
},
|
|
{
|
|
"entropy": 5.628178215026855,
|
|
"epoch": 0.9309249702262803,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004922108687374867,
|
|
"loss": 5.4732,
|
|
"mean_token_accuracy": 0.15207466185092927,
|
|
"num_tokens": 20556665.0,
|
|
"step": 9380
|
|
},
|
|
{
|
|
"entropy": 5.604941940307617,
|
|
"epoch": 0.9314211988884478,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.000492201624039533,
|
|
"loss": 5.3144,
|
|
"mean_token_accuracy": 0.1533210664987564,
|
|
"num_tokens": 20566054.0,
|
|
"step": 9385
|
|
},
|
|
{
|
|
"entropy": 5.66755747795105,
|
|
"epoch": 0.9319174275506154,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004921923739554472,
|
|
"loss": 5.3927,
|
|
"mean_token_accuracy": 0.15216393172740936,
|
|
"num_tokens": 20577922.0,
|
|
"step": 9390
|
|
},
|
|
{
|
|
"entropy": 5.513110399246216,
|
|
"epoch": 0.9324136562127828,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004921831184854585,
|
|
"loss": 5.1973,
|
|
"mean_token_accuracy": 0.16484288424253463,
|
|
"num_tokens": 20588473.0,
|
|
"step": 9395
|
|
},
|
|
{
|
|
"entropy": 5.553794431686401,
|
|
"epoch": 0.9329098848749504,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004921738576297965,
|
|
"loss": 5.3837,
|
|
"mean_token_accuracy": 0.158964903652668,
|
|
"num_tokens": 20599371.0,
|
|
"step": 9400
|
|
},
|
|
{
|
|
"entropy": 5.541663026809692,
|
|
"epoch": 0.9334061135371179,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004921645913886907,
|
|
"loss": 5.2684,
|
|
"mean_token_accuracy": 0.15712719410657883,
|
|
"num_tokens": 20610066.0,
|
|
"step": 9405
|
|
},
|
|
{
|
|
"entropy": 5.582781600952148,
|
|
"epoch": 0.9339023421992855,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004921553197623711,
|
|
"loss": 5.373,
|
|
"mean_token_accuracy": 0.1548023119568825,
|
|
"num_tokens": 20621804.0,
|
|
"step": 9410
|
|
},
|
|
{
|
|
"entropy": 5.557465696334839,
|
|
"epoch": 0.934398570861453,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004921460427510674,
|
|
"loss": 5.2563,
|
|
"mean_token_accuracy": 0.16722989529371263,
|
|
"num_tokens": 20632706.0,
|
|
"step": 9415
|
|
},
|
|
{
|
|
"entropy": 5.557167625427246,
|
|
"epoch": 0.9348947995236205,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004921367603550098,
|
|
"loss": 5.3667,
|
|
"mean_token_accuracy": 0.1509762555360794,
|
|
"num_tokens": 20643303.0,
|
|
"step": 9420
|
|
},
|
|
{
|
|
"entropy": 5.596539688110352,
|
|
"epoch": 0.935391028185788,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004921274725744283,
|
|
"loss": 5.3155,
|
|
"mean_token_accuracy": 0.16477171033620835,
|
|
"num_tokens": 20653681.0,
|
|
"step": 9425
|
|
},
|
|
{
|
|
"entropy": 5.583985042572022,
|
|
"epoch": 0.9358872568479555,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004921181794095536,
|
|
"loss": 5.3219,
|
|
"mean_token_accuracy": 0.15845015048980712,
|
|
"num_tokens": 20665599.0,
|
|
"step": 9430
|
|
},
|
|
{
|
|
"entropy": 5.496887588500977,
|
|
"epoch": 0.9363834855101231,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004921088808606157,
|
|
"loss": 5.225,
|
|
"mean_token_accuracy": 0.16497879475355148,
|
|
"num_tokens": 20675726.0,
|
|
"step": 9435
|
|
},
|
|
{
|
|
"entropy": 5.586679458618164,
|
|
"epoch": 0.9368797141722905,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004920995769278454,
|
|
"loss": 5.4173,
|
|
"mean_token_accuracy": 0.1540427625179291,
|
|
"num_tokens": 20688083.0,
|
|
"step": 9440
|
|
},
|
|
{
|
|
"entropy": 5.63616795539856,
|
|
"epoch": 0.9373759428344581,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004920902676114734,
|
|
"loss": 5.2845,
|
|
"mean_token_accuracy": 0.16210053712129593,
|
|
"num_tokens": 20697642.0,
|
|
"step": 9445
|
|
},
|
|
{
|
|
"entropy": 5.618163156509399,
|
|
"epoch": 0.9378721714966256,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004920809529117306,
|
|
"loss": 5.3632,
|
|
"mean_token_accuracy": 0.15220556557178497,
|
|
"num_tokens": 20709172.0,
|
|
"step": 9450
|
|
},
|
|
{
|
|
"entropy": 5.606362199783325,
|
|
"epoch": 0.9383684001587932,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.0004920716328288479,
|
|
"loss": 5.4067,
|
|
"mean_token_accuracy": 0.15718362331390381,
|
|
"num_tokens": 20720563.0,
|
|
"step": 9455
|
|
},
|
|
{
|
|
"entropy": 5.5817773818969725,
|
|
"epoch": 0.9388646288209607,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004920623073630566,
|
|
"loss": 5.2902,
|
|
"mean_token_accuracy": 0.16570660322904587,
|
|
"num_tokens": 20730943.0,
|
|
"step": 9460
|
|
},
|
|
{
|
|
"entropy": 5.558560037612915,
|
|
"epoch": 0.9393608574831283,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004920529765145876,
|
|
"loss": 5.2801,
|
|
"mean_token_accuracy": 0.1606566086411476,
|
|
"num_tokens": 20740903.0,
|
|
"step": 9465
|
|
},
|
|
{
|
|
"entropy": 5.578950977325439,
|
|
"epoch": 0.9398570861452957,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004920436402836726,
|
|
"loss": 5.3513,
|
|
"mean_token_accuracy": 0.1639459028840065,
|
|
"num_tokens": 20750580.0,
|
|
"step": 9470
|
|
},
|
|
{
|
|
"entropy": 5.55942850112915,
|
|
"epoch": 0.9403533148074633,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.000492034298670543,
|
|
"loss": 5.2823,
|
|
"mean_token_accuracy": 0.15864358246326446,
|
|
"num_tokens": 20761357.0,
|
|
"step": 9475
|
|
},
|
|
{
|
|
"entropy": 5.63238263130188,
|
|
"epoch": 0.9408495434696308,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004920249516754304,
|
|
"loss": 5.4247,
|
|
"mean_token_accuracy": 0.1501690626144409,
|
|
"num_tokens": 20773273.0,
|
|
"step": 9480
|
|
},
|
|
{
|
|
"entropy": 5.5499388694763185,
|
|
"epoch": 0.9413457721317984,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004920155992985667,
|
|
"loss": 5.2721,
|
|
"mean_token_accuracy": 0.15872172266244888,
|
|
"num_tokens": 20784290.0,
|
|
"step": 9485
|
|
},
|
|
{
|
|
"entropy": 5.595738077163697,
|
|
"epoch": 0.9418420007939659,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004920062415401837,
|
|
"loss": 5.2966,
|
|
"mean_token_accuracy": 0.16069611459970473,
|
|
"num_tokens": 20794764.0,
|
|
"step": 9490
|
|
},
|
|
{
|
|
"entropy": 5.63782000541687,
|
|
"epoch": 0.9423382294561334,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004919968784005136,
|
|
"loss": 5.3506,
|
|
"mean_token_accuracy": 0.151334947347641,
|
|
"num_tokens": 20804863.0,
|
|
"step": 9495
|
|
},
|
|
{
|
|
"entropy": 5.649145221710205,
|
|
"epoch": 0.9428344581183009,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004919875098797886,
|
|
"loss": 5.4244,
|
|
"mean_token_accuracy": 0.15182149410247803,
|
|
"num_tokens": 20816445.0,
|
|
"step": 9500
|
|
},
|
|
{
|
|
"entropy": 5.596583557128906,
|
|
"epoch": 0.9433306867804684,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004919781359782407,
|
|
"loss": 5.2546,
|
|
"mean_token_accuracy": 0.16618213802576065,
|
|
"num_tokens": 20827141.0,
|
|
"step": 9505
|
|
},
|
|
{
|
|
"entropy": 5.553158521652222,
|
|
"epoch": 0.943826915442636,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004919687566961027,
|
|
"loss": 5.3127,
|
|
"mean_token_accuracy": 0.15420710295438766,
|
|
"num_tokens": 20838291.0,
|
|
"step": 9510
|
|
},
|
|
{
|
|
"entropy": 5.6420862674713135,
|
|
"epoch": 0.9443231441048034,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.000491959372033607,
|
|
"loss": 5.3006,
|
|
"mean_token_accuracy": 0.16112050563097,
|
|
"num_tokens": 20848839.0,
|
|
"step": 9515
|
|
},
|
|
{
|
|
"entropy": 5.588303565979004,
|
|
"epoch": 0.944819372766971,
|
|
"grad_norm": 0.80078125,
|
|
"learning_rate": 0.0004919499819909865,
|
|
"loss": 5.2852,
|
|
"mean_token_accuracy": 0.16203968077898026,
|
|
"num_tokens": 20859961.0,
|
|
"step": 9520
|
|
},
|
|
{
|
|
"entropy": 5.488934516906738,
|
|
"epoch": 0.9453156014291385,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004919405865684738,
|
|
"loss": 5.2296,
|
|
"mean_token_accuracy": 0.16484673768281938,
|
|
"num_tokens": 20869720.0,
|
|
"step": 9525
|
|
},
|
|
{
|
|
"entropy": 5.56879243850708,
|
|
"epoch": 0.9458118300913061,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.000491931185766302,
|
|
"loss": 5.3764,
|
|
"mean_token_accuracy": 0.16189633160829545,
|
|
"num_tokens": 20880513.0,
|
|
"step": 9530
|
|
},
|
|
{
|
|
"entropy": 5.624775218963623,
|
|
"epoch": 0.9463080587534736,
|
|
"grad_norm": 0.7890625,
|
|
"learning_rate": 0.0004919217795847044,
|
|
"loss": 5.2941,
|
|
"mean_token_accuracy": 0.16495498567819594,
|
|
"num_tokens": 20892456.0,
|
|
"step": 9535
|
|
},
|
|
{
|
|
"entropy": 5.552755737304688,
|
|
"epoch": 0.9468042874156412,
|
|
"grad_norm": 0.80078125,
|
|
"learning_rate": 0.0004919123680239139,
|
|
"loss": 5.293,
|
|
"mean_token_accuracy": 0.15933222323656082,
|
|
"num_tokens": 20904500.0,
|
|
"step": 9540
|
|
},
|
|
{
|
|
"entropy": 5.602396154403687,
|
|
"epoch": 0.9473005160778086,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004919029510841641,
|
|
"loss": 5.2781,
|
|
"mean_token_accuracy": 0.1620924264192581,
|
|
"num_tokens": 20915133.0,
|
|
"step": 9545
|
|
},
|
|
{
|
|
"entropy": 5.514210557937622,
|
|
"epoch": 0.9477967447399762,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004918935287656887,
|
|
"loss": 5.2799,
|
|
"mean_token_accuracy": 0.16024440079927443,
|
|
"num_tokens": 20924779.0,
|
|
"step": 9550
|
|
},
|
|
{
|
|
"entropy": 5.482671308517456,
|
|
"epoch": 0.9482929734021437,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.000491884101068721,
|
|
"loss": 5.2177,
|
|
"mean_token_accuracy": 0.1628309369087219,
|
|
"num_tokens": 20935387.0,
|
|
"step": 9555
|
|
},
|
|
{
|
|
"entropy": 5.635864973068237,
|
|
"epoch": 0.9487892020643113,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004918746679934949,
|
|
"loss": 5.3922,
|
|
"mean_token_accuracy": 0.1568456321954727,
|
|
"num_tokens": 20945432.0,
|
|
"step": 9560
|
|
},
|
|
{
|
|
"entropy": 5.56051926612854,
|
|
"epoch": 0.9492854307264788,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004918652295402444,
|
|
"loss": 5.2715,
|
|
"mean_token_accuracy": 0.16505309492349624,
|
|
"num_tokens": 20956777.0,
|
|
"step": 9565
|
|
},
|
|
{
|
|
"entropy": 5.552857446670532,
|
|
"epoch": 0.9497816593886463,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004918557857092036,
|
|
"loss": 5.3099,
|
|
"mean_token_accuracy": 0.15762278735637664,
|
|
"num_tokens": 20966057.0,
|
|
"step": 9570
|
|
},
|
|
{
|
|
"entropy": 5.595779657363892,
|
|
"epoch": 0.9502778880508138,
|
|
"grad_norm": 0.80078125,
|
|
"learning_rate": 0.0004918463365006065,
|
|
"loss": 5.4026,
|
|
"mean_token_accuracy": 0.1553104653954506,
|
|
"num_tokens": 20976838.0,
|
|
"step": 9575
|
|
},
|
|
{
|
|
"entropy": 5.643113613128662,
|
|
"epoch": 0.9507741167129813,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004918368819146875,
|
|
"loss": 5.3239,
|
|
"mean_token_accuracy": 0.15752324014902114,
|
|
"num_tokens": 20988553.0,
|
|
"step": 9580
|
|
},
|
|
{
|
|
"entropy": 5.56094331741333,
|
|
"epoch": 0.9512703453751489,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004918274219516811,
|
|
"loss": 5.3029,
|
|
"mean_token_accuracy": 0.15705730617046357,
|
|
"num_tokens": 20998983.0,
|
|
"step": 9585
|
|
},
|
|
{
|
|
"entropy": 5.6389594078063965,
|
|
"epoch": 0.9517665740373163,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004918179566118218,
|
|
"loss": 5.4099,
|
|
"mean_token_accuracy": 0.15401346534490584,
|
|
"num_tokens": 21010008.0,
|
|
"step": 9590
|
|
},
|
|
{
|
|
"entropy": 5.597928380966186,
|
|
"epoch": 0.9522628026994839,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004918084858953445,
|
|
"loss": 5.378,
|
|
"mean_token_accuracy": 0.16430667340755462,
|
|
"num_tokens": 21022826.0,
|
|
"step": 9595
|
|
},
|
|
{
|
|
"entropy": 5.593146514892578,
|
|
"epoch": 0.9527590313616514,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.0004917990098024839,
|
|
"loss": 5.3065,
|
|
"mean_token_accuracy": 0.16070859134197235,
|
|
"num_tokens": 21033457.0,
|
|
"step": 9600
|
|
},
|
|
{
|
|
"entropy": 5.5332756519317625,
|
|
"epoch": 0.953255260023819,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004917895283334749,
|
|
"loss": 5.3259,
|
|
"mean_token_accuracy": 0.15825341045856475,
|
|
"num_tokens": 21044640.0,
|
|
"step": 9605
|
|
},
|
|
{
|
|
"entropy": 5.59820818901062,
|
|
"epoch": 0.9537514886859865,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.000491780041488553,
|
|
"loss": 5.3125,
|
|
"mean_token_accuracy": 0.16587773263454436,
|
|
"num_tokens": 21055728.0,
|
|
"step": 9610
|
|
},
|
|
{
|
|
"entropy": 5.612208414077759,
|
|
"epoch": 0.9542477173481541,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004917705492679529,
|
|
"loss": 5.3012,
|
|
"mean_token_accuracy": 0.15372338593006135,
|
|
"num_tokens": 21066057.0,
|
|
"step": 9615
|
|
},
|
|
{
|
|
"entropy": 5.598805236816406,
|
|
"epoch": 0.9547439460103215,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004917610516719104,
|
|
"loss": 5.3228,
|
|
"mean_token_accuracy": 0.15715788900852204,
|
|
"num_tokens": 21075717.0,
|
|
"step": 9620
|
|
},
|
|
{
|
|
"entropy": 5.662686014175415,
|
|
"epoch": 0.9552401746724891,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004917515487006609,
|
|
"loss": 5.4111,
|
|
"mean_token_accuracy": 0.1507570505142212,
|
|
"num_tokens": 21087120.0,
|
|
"step": 9625
|
|
},
|
|
{
|
|
"entropy": 5.621013593673706,
|
|
"epoch": 0.9557364033346566,
|
|
"grad_norm": 0.796875,
|
|
"learning_rate": 0.00049174204035444,
|
|
"loss": 5.4172,
|
|
"mean_token_accuracy": 0.1534568190574646,
|
|
"num_tokens": 21100110.0,
|
|
"step": 9630
|
|
},
|
|
{
|
|
"entropy": 5.670272350311279,
|
|
"epoch": 0.9562326319968242,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004917325266334836,
|
|
"loss": 5.3487,
|
|
"mean_token_accuracy": 0.16352131813764573,
|
|
"num_tokens": 21110411.0,
|
|
"step": 9635
|
|
},
|
|
{
|
|
"entropy": 5.5196967124938965,
|
|
"epoch": 0.9567288606589917,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004917230075380276,
|
|
"loss": 5.2452,
|
|
"mean_token_accuracy": 0.1625675991177559,
|
|
"num_tokens": 21120303.0,
|
|
"step": 9640
|
|
},
|
|
{
|
|
"entropy": 5.565840482711792,
|
|
"epoch": 0.9572250893211592,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004917134830683079,
|
|
"loss": 5.3465,
|
|
"mean_token_accuracy": 0.1565359801054001,
|
|
"num_tokens": 21132312.0,
|
|
"step": 9645
|
|
},
|
|
{
|
|
"entropy": 5.641309928894043,
|
|
"epoch": 0.9577213179833267,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004917039532245608,
|
|
"loss": 5.3128,
|
|
"mean_token_accuracy": 0.16016699820756913,
|
|
"num_tokens": 21142472.0,
|
|
"step": 9650
|
|
},
|
|
{
|
|
"entropy": 5.602419042587281,
|
|
"epoch": 0.9582175466454942,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004916944180070226,
|
|
"loss": 5.3246,
|
|
"mean_token_accuracy": 0.15507960319519043,
|
|
"num_tokens": 21153306.0,
|
|
"step": 9655
|
|
},
|
|
{
|
|
"entropy": 5.651671934127807,
|
|
"epoch": 0.9587137753076618,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004916848774159299,
|
|
"loss": 5.3673,
|
|
"mean_token_accuracy": 0.15087900310754776,
|
|
"num_tokens": 21165606.0,
|
|
"step": 9660
|
|
},
|
|
{
|
|
"entropy": 5.605053329467774,
|
|
"epoch": 0.9592100039698293,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.000491675331451519,
|
|
"loss": 5.2977,
|
|
"mean_token_accuracy": 0.1654946967959404,
|
|
"num_tokens": 21176734.0,
|
|
"step": 9665
|
|
},
|
|
{
|
|
"entropy": 5.522690868377685,
|
|
"epoch": 0.9597062326319968,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004916657801140269,
|
|
"loss": 5.2466,
|
|
"mean_token_accuracy": 0.16344843357801436,
|
|
"num_tokens": 21187109.0,
|
|
"step": 9670
|
|
},
|
|
{
|
|
"entropy": 5.559283876419068,
|
|
"epoch": 0.9602024612941643,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004916562234036903,
|
|
"loss": 5.299,
|
|
"mean_token_accuracy": 0.16285582780838012,
|
|
"num_tokens": 21197281.0,
|
|
"step": 9675
|
|
},
|
|
{
|
|
"entropy": 5.571779775619507,
|
|
"epoch": 0.9606986899563319,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.0004916466613207462,
|
|
"loss": 5.3347,
|
|
"mean_token_accuracy": 0.16179765909910201,
|
|
"num_tokens": 21208767.0,
|
|
"step": 9680
|
|
},
|
|
{
|
|
"entropy": 5.5672523975372314,
|
|
"epoch": 0.9611949186184994,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004916370938654317,
|
|
"loss": 5.3166,
|
|
"mean_token_accuracy": 0.1586903601884842,
|
|
"num_tokens": 21219328.0,
|
|
"step": 9685
|
|
},
|
|
{
|
|
"entropy": 5.642516803741455,
|
|
"epoch": 0.961691147280667,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004916275210379841,
|
|
"loss": 5.4304,
|
|
"mean_token_accuracy": 0.15577488243579865,
|
|
"num_tokens": 21231476.0,
|
|
"step": 9690
|
|
},
|
|
{
|
|
"entropy": 5.667134475708008,
|
|
"epoch": 0.9621873759428344,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004916179428386408,
|
|
"loss": 5.3833,
|
|
"mean_token_accuracy": 0.1607624039053917,
|
|
"num_tokens": 21242445.0,
|
|
"step": 9695
|
|
},
|
|
{
|
|
"entropy": 5.540036630630493,
|
|
"epoch": 0.962683604605002,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.0004916083592676392,
|
|
"loss": 5.1989,
|
|
"mean_token_accuracy": 0.16129746437072753,
|
|
"num_tokens": 21253179.0,
|
|
"step": 9700
|
|
},
|
|
{
|
|
"entropy": 5.554250860214234,
|
|
"epoch": 0.9631798332671695,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004915987703252171,
|
|
"loss": 5.2254,
|
|
"mean_token_accuracy": 0.1666320875287056,
|
|
"num_tokens": 21263460.0,
|
|
"step": 9705
|
|
},
|
|
{
|
|
"entropy": 5.489849710464478,
|
|
"epoch": 0.9636760619293371,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004915891760116123,
|
|
"loss": 5.2927,
|
|
"mean_token_accuracy": 0.1543031245470047,
|
|
"num_tokens": 21274819.0,
|
|
"step": 9710
|
|
},
|
|
{
|
|
"entropy": 5.586282253265381,
|
|
"epoch": 0.9641722905915046,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004915795763270626,
|
|
"loss": 5.2564,
|
|
"mean_token_accuracy": 0.1650063179433346,
|
|
"num_tokens": 21286215.0,
|
|
"step": 9715
|
|
},
|
|
{
|
|
"entropy": 5.587061882019043,
|
|
"epoch": 0.9646685192536721,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.000491569971271806,
|
|
"loss": 5.2575,
|
|
"mean_token_accuracy": 0.16380464881658555,
|
|
"num_tokens": 21297033.0,
|
|
"step": 9720
|
|
},
|
|
{
|
|
"entropy": 5.498089981079102,
|
|
"epoch": 0.9651647479158396,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004915603608460809,
|
|
"loss": 5.2582,
|
|
"mean_token_accuracy": 0.15726491957902908,
|
|
"num_tokens": 21308019.0,
|
|
"step": 9725
|
|
},
|
|
{
|
|
"entropy": 5.559009122848511,
|
|
"epoch": 0.9656609765780071,
|
|
"grad_norm": 0.7734375,
|
|
"learning_rate": 0.0004915507450501254,
|
|
"loss": 5.3865,
|
|
"mean_token_accuracy": 0.15224374756217002,
|
|
"num_tokens": 21319313.0,
|
|
"step": 9730
|
|
},
|
|
{
|
|
"entropy": 5.576496982574463,
|
|
"epoch": 0.9661572052401747,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.000491541123884178,
|
|
"loss": 5.2896,
|
|
"mean_token_accuracy": 0.1618467316031456,
|
|
"num_tokens": 21329950.0,
|
|
"step": 9735
|
|
},
|
|
{
|
|
"entropy": 5.590175819396973,
|
|
"epoch": 0.9666534339023422,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004915314973484775,
|
|
"loss": 5.2652,
|
|
"mean_token_accuracy": 0.16106131225824355,
|
|
"num_tokens": 21339061.0,
|
|
"step": 9740
|
|
},
|
|
{
|
|
"entropy": 5.539566326141357,
|
|
"epoch": 0.9671496625645097,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004915218654432624,
|
|
"loss": 5.3507,
|
|
"mean_token_accuracy": 0.15383373200893402,
|
|
"num_tokens": 21350114.0,
|
|
"step": 9745
|
|
},
|
|
{
|
|
"entropy": 5.566125679016113,
|
|
"epoch": 0.9676458912266772,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004915122281687716,
|
|
"loss": 5.2697,
|
|
"mean_token_accuracy": 0.16104603707790374,
|
|
"num_tokens": 21361219.0,
|
|
"step": 9750
|
|
},
|
|
{
|
|
"entropy": 5.535313653945923,
|
|
"epoch": 0.9681421198888448,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004915025855252441,
|
|
"loss": 5.273,
|
|
"mean_token_accuracy": 0.16092607527971267,
|
|
"num_tokens": 21372722.0,
|
|
"step": 9755
|
|
},
|
|
{
|
|
"entropy": 5.600295639038086,
|
|
"epoch": 0.9686383485510123,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004914929375129188,
|
|
"loss": 5.3071,
|
|
"mean_token_accuracy": 0.1598965957760811,
|
|
"num_tokens": 21383350.0,
|
|
"step": 9760
|
|
},
|
|
{
|
|
"entropy": 5.589402151107788,
|
|
"epoch": 0.9691345772131799,
|
|
"grad_norm": 0.7734375,
|
|
"learning_rate": 0.0004914832841320353,
|
|
"loss": 5.3418,
|
|
"mean_token_accuracy": 0.16007469594478607,
|
|
"num_tokens": 21394656.0,
|
|
"step": 9765
|
|
},
|
|
{
|
|
"entropy": 5.592403602600098,
|
|
"epoch": 0.9696308058753473,
|
|
"grad_norm": 0.79296875,
|
|
"learning_rate": 0.000491473625382833,
|
|
"loss": 5.3327,
|
|
"mean_token_accuracy": 0.15597164034843444,
|
|
"num_tokens": 21406163.0,
|
|
"step": 9770
|
|
},
|
|
{
|
|
"entropy": 5.495397901535034,
|
|
"epoch": 0.9701270345375149,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.000491463961265551,
|
|
"loss": 5.228,
|
|
"mean_token_accuracy": 0.16503653675317764,
|
|
"num_tokens": 21418703.0,
|
|
"step": 9775
|
|
},
|
|
{
|
|
"entropy": 5.528452920913696,
|
|
"epoch": 0.9706232631996824,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004914542917804292,
|
|
"loss": 5.2247,
|
|
"mean_token_accuracy": 0.1663466528058052,
|
|
"num_tokens": 21428511.0,
|
|
"step": 9780
|
|
},
|
|
{
|
|
"entropy": 5.586885643005371,
|
|
"epoch": 0.97111949186185,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004914446169277075,
|
|
"loss": 5.2642,
|
|
"mean_token_accuracy": 0.16102582216262817,
|
|
"num_tokens": 21440350.0,
|
|
"step": 9785
|
|
},
|
|
{
|
|
"entropy": 5.656343078613281,
|
|
"epoch": 0.9716157205240175,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004914349367076258,
|
|
"loss": 5.378,
|
|
"mean_token_accuracy": 0.1604055270552635,
|
|
"num_tokens": 21451262.0,
|
|
"step": 9790
|
|
},
|
|
{
|
|
"entropy": 5.59821195602417,
|
|
"epoch": 0.972111949186185,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004914252511204238,
|
|
"loss": 5.3269,
|
|
"mean_token_accuracy": 0.16023993492126465,
|
|
"num_tokens": 21462587.0,
|
|
"step": 9795
|
|
},
|
|
{
|
|
"entropy": 5.590718078613281,
|
|
"epoch": 0.9726081778483525,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004914155601663422,
|
|
"loss": 5.2921,
|
|
"mean_token_accuracy": 0.16131409704685212,
|
|
"num_tokens": 21473452.0,
|
|
"step": 9800
|
|
},
|
|
{
|
|
"entropy": 5.5845705509185795,
|
|
"epoch": 0.97310440651052,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004914058638456208,
|
|
"loss": 5.2577,
|
|
"mean_token_accuracy": 0.16089966893196106,
|
|
"num_tokens": 21484011.0,
|
|
"step": 9805
|
|
},
|
|
{
|
|
"entropy": 5.459889936447143,
|
|
"epoch": 0.9736006351726876,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004913961621585003,
|
|
"loss": 5.2445,
|
|
"mean_token_accuracy": 0.1632186383008957,
|
|
"num_tokens": 21495959.0,
|
|
"step": 9810
|
|
},
|
|
{
|
|
"entropy": 5.507400798797607,
|
|
"epoch": 0.974096863834855,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004913864551052214,
|
|
"loss": 5.2857,
|
|
"mean_token_accuracy": 0.16949345022439957,
|
|
"num_tokens": 21507496.0,
|
|
"step": 9815
|
|
},
|
|
{
|
|
"entropy": 5.653198719024658,
|
|
"epoch": 0.9745930924970226,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004913767426860246,
|
|
"loss": 5.3691,
|
|
"mean_token_accuracy": 0.15034950897097588,
|
|
"num_tokens": 21517532.0,
|
|
"step": 9820
|
|
},
|
|
{
|
|
"entropy": 5.555367803573608,
|
|
"epoch": 0.9750893211591901,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004913670249011508,
|
|
"loss": 5.1951,
|
|
"mean_token_accuracy": 0.163184355199337,
|
|
"num_tokens": 21527969.0,
|
|
"step": 9825
|
|
},
|
|
{
|
|
"entropy": 5.525680065155029,
|
|
"epoch": 0.9755855498213577,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004913573017508411,
|
|
"loss": 5.309,
|
|
"mean_token_accuracy": 0.15447816699743272,
|
|
"num_tokens": 21538243.0,
|
|
"step": 9830
|
|
},
|
|
{
|
|
"entropy": 5.586614418029785,
|
|
"epoch": 0.9760817784835252,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004913475732353365,
|
|
"loss": 5.3026,
|
|
"mean_token_accuracy": 0.1621467411518097,
|
|
"num_tokens": 21548702.0,
|
|
"step": 9835
|
|
},
|
|
{
|
|
"entropy": 5.5326902866363525,
|
|
"epoch": 0.9765780071456928,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004913378393548784,
|
|
"loss": 5.2621,
|
|
"mean_token_accuracy": 0.16488298326730727,
|
|
"num_tokens": 21558583.0,
|
|
"step": 9840
|
|
},
|
|
{
|
|
"entropy": 5.57383246421814,
|
|
"epoch": 0.9770742358078602,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.0004913281001097078,
|
|
"loss": 5.2566,
|
|
"mean_token_accuracy": 0.16477205902338027,
|
|
"num_tokens": 21569845.0,
|
|
"step": 9845
|
|
},
|
|
{
|
|
"entropy": 5.626986360549926,
|
|
"epoch": 0.9775704644700278,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004913183555000667,
|
|
"loss": 5.4093,
|
|
"mean_token_accuracy": 0.1548849605023861,
|
|
"num_tokens": 21580540.0,
|
|
"step": 9850
|
|
},
|
|
{
|
|
"entropy": 5.584823036193848,
|
|
"epoch": 0.9780666931321953,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004913086055261963,
|
|
"loss": 5.2608,
|
|
"mean_token_accuracy": 0.1617264226078987,
|
|
"num_tokens": 21590982.0,
|
|
"step": 9855
|
|
},
|
|
{
|
|
"entropy": 5.542820787429809,
|
|
"epoch": 0.9785629217943629,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004912988501883387,
|
|
"loss": 5.2851,
|
|
"mean_token_accuracy": 0.16189356297254562,
|
|
"num_tokens": 21602817.0,
|
|
"step": 9860
|
|
},
|
|
{
|
|
"entropy": 5.594162940979004,
|
|
"epoch": 0.9790591504565304,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004912890894867357,
|
|
"loss": 5.3345,
|
|
"mean_token_accuracy": 0.15913430005311965,
|
|
"num_tokens": 21613422.0,
|
|
"step": 9865
|
|
},
|
|
{
|
|
"entropy": 5.548657035827636,
|
|
"epoch": 0.9795553791186979,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004912793234216293,
|
|
"loss": 5.314,
|
|
"mean_token_accuracy": 0.15511717051267623,
|
|
"num_tokens": 21624241.0,
|
|
"step": 9870
|
|
},
|
|
{
|
|
"entropy": 5.530315399169922,
|
|
"epoch": 0.9800516077808654,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004912695519932618,
|
|
"loss": 5.3152,
|
|
"mean_token_accuracy": 0.16225161999464036,
|
|
"num_tokens": 21636243.0,
|
|
"step": 9875
|
|
},
|
|
{
|
|
"entropy": 5.573291540145874,
|
|
"epoch": 0.9805478364430329,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004912597752018753,
|
|
"loss": 5.3316,
|
|
"mean_token_accuracy": 0.1610553279519081,
|
|
"num_tokens": 21647918.0,
|
|
"step": 9880
|
|
},
|
|
{
|
|
"entropy": 5.61486291885376,
|
|
"epoch": 0.9810440651052005,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004912499930477126,
|
|
"loss": 5.3078,
|
|
"mean_token_accuracy": 0.15688589364290237,
|
|
"num_tokens": 21659236.0,
|
|
"step": 9885
|
|
},
|
|
{
|
|
"entropy": 5.566563987731934,
|
|
"epoch": 0.981540293767368,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004912402055310158,
|
|
"loss": 5.3055,
|
|
"mean_token_accuracy": 0.16469915062189103,
|
|
"num_tokens": 21669647.0,
|
|
"step": 9890
|
|
},
|
|
{
|
|
"entropy": 5.535579442977905,
|
|
"epoch": 0.9820365224295355,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.0004912304126520279,
|
|
"loss": 5.3494,
|
|
"mean_token_accuracy": 0.15597899705171586,
|
|
"num_tokens": 21680369.0,
|
|
"step": 9895
|
|
},
|
|
{
|
|
"entropy": 5.631029987335205,
|
|
"epoch": 0.982532751091703,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004912206144109917,
|
|
"loss": 5.3534,
|
|
"mean_token_accuracy": 0.15765170902013778,
|
|
"num_tokens": 21690942.0,
|
|
"step": 9900
|
|
},
|
|
{
|
|
"entropy": 5.558161735534668,
|
|
"epoch": 0.9830289797538706,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004912108108081503,
|
|
"loss": 5.2878,
|
|
"mean_token_accuracy": 0.16257334798574447,
|
|
"num_tokens": 21701945.0,
|
|
"step": 9905
|
|
},
|
|
{
|
|
"entropy": 5.6102015495300295,
|
|
"epoch": 0.9835252084160381,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004912010018437465,
|
|
"loss": 5.3193,
|
|
"mean_token_accuracy": 0.15981239974498748,
|
|
"num_tokens": 21712246.0,
|
|
"step": 9910
|
|
},
|
|
{
|
|
"entropy": 5.678878927230835,
|
|
"epoch": 0.9840214370782057,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.000491191187518024,
|
|
"loss": 5.317,
|
|
"mean_token_accuracy": 0.16021854281425477,
|
|
"num_tokens": 21721660.0,
|
|
"step": 9915
|
|
},
|
|
{
|
|
"entropy": 5.551132726669311,
|
|
"epoch": 0.9845176657403731,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004911813678312257,
|
|
"loss": 5.2036,
|
|
"mean_token_accuracy": 0.16454039365053177,
|
|
"num_tokens": 21732157.0,
|
|
"step": 9920
|
|
},
|
|
{
|
|
"entropy": 5.543543910980224,
|
|
"epoch": 0.9850138944025407,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004911715427835953,
|
|
"loss": 5.3336,
|
|
"mean_token_accuracy": 0.15899271741509438,
|
|
"num_tokens": 21741727.0,
|
|
"step": 9925
|
|
},
|
|
{
|
|
"entropy": 5.574287223815918,
|
|
"epoch": 0.9855101230647082,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004911617123753765,
|
|
"loss": 5.27,
|
|
"mean_token_accuracy": 0.16396869122982025,
|
|
"num_tokens": 21752596.0,
|
|
"step": 9930
|
|
},
|
|
{
|
|
"entropy": 5.515794897079468,
|
|
"epoch": 0.9860063517268758,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004911518766068131,
|
|
"loss": 5.1856,
|
|
"mean_token_accuracy": 0.16887888461351394,
|
|
"num_tokens": 21763978.0,
|
|
"step": 9935
|
|
},
|
|
{
|
|
"entropy": 5.537166929244995,
|
|
"epoch": 0.9865025803890433,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004911420354781487,
|
|
"loss": 5.3282,
|
|
"mean_token_accuracy": 0.15229359567165374,
|
|
"num_tokens": 21774961.0,
|
|
"step": 9940
|
|
},
|
|
{
|
|
"entropy": 5.562363862991333,
|
|
"epoch": 0.9869988090512108,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004911321889896278,
|
|
"loss": 5.2447,
|
|
"mean_token_accuracy": 0.166769939661026,
|
|
"num_tokens": 21785387.0,
|
|
"step": 9945
|
|
},
|
|
{
|
|
"entropy": 5.573436832427978,
|
|
"epoch": 0.9874950377133783,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004911223371414943,
|
|
"loss": 5.294,
|
|
"mean_token_accuracy": 0.1654672920703888,
|
|
"num_tokens": 21795982.0,
|
|
"step": 9950
|
|
},
|
|
{
|
|
"entropy": 5.5942527770996096,
|
|
"epoch": 0.9879912663755459,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004911124799339924,
|
|
"loss": 5.3208,
|
|
"mean_token_accuracy": 0.15434270054101945,
|
|
"num_tokens": 21806768.0,
|
|
"step": 9955
|
|
},
|
|
{
|
|
"entropy": 5.58071460723877,
|
|
"epoch": 0.9884874950377134,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004911026173673667,
|
|
"loss": 5.2859,
|
|
"mean_token_accuracy": 0.16355279982089996,
|
|
"num_tokens": 21818563.0,
|
|
"step": 9960
|
|
},
|
|
{
|
|
"entropy": 5.596285247802735,
|
|
"epoch": 0.9889837236998809,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004910927494418619,
|
|
"loss": 5.3664,
|
|
"mean_token_accuracy": 0.1590631991624832,
|
|
"num_tokens": 21830253.0,
|
|
"step": 9965
|
|
},
|
|
{
|
|
"entropy": 5.6451211929321286,
|
|
"epoch": 0.9894799523620484,
|
|
"grad_norm": 0.7578125,
|
|
"learning_rate": 0.0004910828761577224,
|
|
"loss": 5.3322,
|
|
"mean_token_accuracy": 0.16312540024518968,
|
|
"num_tokens": 21842353.0,
|
|
"step": 9970
|
|
},
|
|
{
|
|
"entropy": 5.575357866287232,
|
|
"epoch": 0.9899761810242159,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004910729975151933,
|
|
"loss": 5.2749,
|
|
"mean_token_accuracy": 0.16515064537525176,
|
|
"num_tokens": 21852066.0,
|
|
"step": 9975
|
|
},
|
|
{
|
|
"entropy": 5.517587375640869,
|
|
"epoch": 0.9904724096863835,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004910631135145194,
|
|
"loss": 5.311,
|
|
"mean_token_accuracy": 0.1654649168252945,
|
|
"num_tokens": 21862754.0,
|
|
"step": 9980
|
|
},
|
|
{
|
|
"entropy": 5.467855453491211,
|
|
"epoch": 0.990968638348551,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004910532241559458,
|
|
"loss": 5.2208,
|
|
"mean_token_accuracy": 0.17459090799093246,
|
|
"num_tokens": 21873531.0,
|
|
"step": 9985
|
|
},
|
|
{
|
|
"entropy": 5.472586536407471,
|
|
"epoch": 0.9914648670107186,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004910433294397179,
|
|
"loss": 5.1661,
|
|
"mean_token_accuracy": 0.16823934763669968,
|
|
"num_tokens": 21884339.0,
|
|
"step": 9990
|
|
},
|
|
{
|
|
"entropy": 5.521728467941284,
|
|
"epoch": 0.991961095672886,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.000491033429366081,
|
|
"loss": 5.2675,
|
|
"mean_token_accuracy": 0.15773390531539916,
|
|
"num_tokens": 21895489.0,
|
|
"step": 9995
|
|
},
|
|
{
|
|
"entropy": 5.539831876754761,
|
|
"epoch": 0.9924573243350536,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004910235239352804,
|
|
"loss": 5.2592,
|
|
"mean_token_accuracy": 0.16699083596467973,
|
|
"num_tokens": 21906832.0,
|
|
"step": 10000
|
|
},
|
|
{
|
|
"entropy": 5.558729648590088,
|
|
"epoch": 0.9929535529972211,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.000491013613147562,
|
|
"loss": 5.2973,
|
|
"mean_token_accuracy": 0.159033165872097,
|
|
"num_tokens": 21916979.0,
|
|
"step": 10005
|
|
},
|
|
{
|
|
"entropy": 5.547304725646972,
|
|
"epoch": 0.9934497816593887,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004910036970031715,
|
|
"loss": 5.2002,
|
|
"mean_token_accuracy": 0.16779321283102036,
|
|
"num_tokens": 21927352.0,
|
|
"step": 10010
|
|
},
|
|
{
|
|
"entropy": 5.543372678756714,
|
|
"epoch": 0.9939460103215562,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004909937755023547,
|
|
"loss": 5.3249,
|
|
"mean_token_accuracy": 0.15822510719299315,
|
|
"num_tokens": 21937765.0,
|
|
"step": 10015
|
|
},
|
|
{
|
|
"entropy": 5.495730400085449,
|
|
"epoch": 0.9944422389837237,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004909838486453577,
|
|
"loss": 5.2208,
|
|
"mean_token_accuracy": 0.17041514962911605,
|
|
"num_tokens": 21948659.0,
|
|
"step": 10020
|
|
},
|
|
{
|
|
"entropy": 5.5643548488616945,
|
|
"epoch": 0.9949384676458912,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004909739164324267,
|
|
"loss": 5.3328,
|
|
"mean_token_accuracy": 0.1573019579052925,
|
|
"num_tokens": 21959356.0,
|
|
"step": 10025
|
|
},
|
|
{
|
|
"entropy": 5.721648168563843,
|
|
"epoch": 0.9954346963080588,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004909639788638079,
|
|
"loss": 5.4387,
|
|
"mean_token_accuracy": 0.14892093241214752,
|
|
"num_tokens": 21971321.0,
|
|
"step": 10030
|
|
},
|
|
{
|
|
"entropy": 5.552315521240234,
|
|
"epoch": 0.9959309249702263,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004909540359397477,
|
|
"loss": 5.3001,
|
|
"mean_token_accuracy": 0.15871900767087938,
|
|
"num_tokens": 21981252.0,
|
|
"step": 10035
|
|
},
|
|
{
|
|
"entropy": 5.56937460899353,
|
|
"epoch": 0.9964271536323938,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004909440876604929,
|
|
"loss": 5.3107,
|
|
"mean_token_accuracy": 0.15274860709905624,
|
|
"num_tokens": 21991820.0,
|
|
"step": 10040
|
|
},
|
|
{
|
|
"entropy": 5.545371580123901,
|
|
"epoch": 0.9969233822945613,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.00049093413402629,
|
|
"loss": 5.2753,
|
|
"mean_token_accuracy": 0.16395441740751265,
|
|
"num_tokens": 22003619.0,
|
|
"step": 10045
|
|
},
|
|
{
|
|
"entropy": 5.557806158065796,
|
|
"epoch": 0.9974196109567288,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004909241750373858,
|
|
"loss": 5.3071,
|
|
"mean_token_accuracy": 0.15856507569551467,
|
|
"num_tokens": 22016116.0,
|
|
"step": 10050
|
|
},
|
|
{
|
|
"entropy": 5.6003748893737795,
|
|
"epoch": 0.9979158396188964,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004909142106940275,
|
|
"loss": 5.2478,
|
|
"mean_token_accuracy": 0.16244348660111427,
|
|
"num_tokens": 22026115.0,
|
|
"step": 10055
|
|
},
|
|
{
|
|
"entropy": 5.572235727310181,
|
|
"epoch": 0.9984120682810639,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.000490904240996462,
|
|
"loss": 5.3147,
|
|
"mean_token_accuracy": 0.16750263571739196,
|
|
"num_tokens": 22038889.0,
|
|
"step": 10060
|
|
},
|
|
{
|
|
"entropy": 5.5575329780578615,
|
|
"epoch": 0.9989082969432315,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004908942659449364,
|
|
"loss": 5.2853,
|
|
"mean_token_accuracy": 0.16204715073108672,
|
|
"num_tokens": 22050773.0,
|
|
"step": 10065
|
|
},
|
|
{
|
|
"entropy": 5.546312522888184,
|
|
"epoch": 0.9994045256053989,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004908842855396982,
|
|
"loss": 5.2832,
|
|
"mean_token_accuracy": 0.1552201345562935,
|
|
"num_tokens": 22062869.0,
|
|
"step": 10070
|
|
},
|
|
{
|
|
"entropy": 5.548929119110108,
|
|
"epoch": 0.9999007542675665,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004908742997809951,
|
|
"loss": 5.3017,
|
|
"mean_token_accuracy": 0.1592031702399254,
|
|
"num_tokens": 22073898.0,
|
|
"step": 10075
|
|
},
|
|
{
|
|
"entropy": 5.624472570419312,
|
|
"epoch": 1.0003969829297341,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004908643086690744,
|
|
"loss": 5.2118,
|
|
"mean_token_accuracy": 0.15984300523996353,
|
|
"num_tokens": 22084383.0,
|
|
"step": 10080
|
|
},
|
|
{
|
|
"entropy": 5.565525245666504,
|
|
"epoch": 1.0008932115919016,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.000490854312204184,
|
|
"loss": 5.2519,
|
|
"mean_token_accuracy": 0.1635912373661995,
|
|
"num_tokens": 22094990.0,
|
|
"step": 10085
|
|
},
|
|
{
|
|
"entropy": 5.548325061798096,
|
|
"epoch": 1.001389440254069,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004908443103865719,
|
|
"loss": 5.2839,
|
|
"mean_token_accuracy": 0.1550723358988762,
|
|
"num_tokens": 22105259.0,
|
|
"step": 10090
|
|
},
|
|
{
|
|
"entropy": 5.555172777175903,
|
|
"epoch": 1.0018856689162365,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004908343032164859,
|
|
"loss": 5.2474,
|
|
"mean_token_accuracy": 0.1596066027879715,
|
|
"num_tokens": 22116348.0,
|
|
"step": 10095
|
|
},
|
|
{
|
|
"entropy": 5.595499801635742,
|
|
"epoch": 1.0023818975784042,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004908242906941743,
|
|
"loss": 5.2351,
|
|
"mean_token_accuracy": 0.16683860272169113,
|
|
"num_tokens": 22127311.0,
|
|
"step": 10100
|
|
},
|
|
{
|
|
"entropy": 5.601737976074219,
|
|
"epoch": 1.0028781262405717,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004908142728198853,
|
|
"loss": 5.2655,
|
|
"mean_token_accuracy": 0.15398730337619781,
|
|
"num_tokens": 22137929.0,
|
|
"step": 10105
|
|
},
|
|
{
|
|
"entropy": 5.657776546478272,
|
|
"epoch": 1.0033743549027392,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004908042495938673,
|
|
"loss": 5.3697,
|
|
"mean_token_accuracy": 0.15462761223316193,
|
|
"num_tokens": 22148202.0,
|
|
"step": 10110
|
|
},
|
|
{
|
|
"entropy": 5.566437387466431,
|
|
"epoch": 1.0038705835649067,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004907942210163692,
|
|
"loss": 5.1538,
|
|
"mean_token_accuracy": 0.16509081423282623,
|
|
"num_tokens": 22158955.0,
|
|
"step": 10115
|
|
},
|
|
{
|
|
"entropy": 5.543176460266113,
|
|
"epoch": 1.0043668122270741,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004907841870876392,
|
|
"loss": 5.2014,
|
|
"mean_token_accuracy": 0.16200576722621918,
|
|
"num_tokens": 22169569.0,
|
|
"step": 10120
|
|
},
|
|
{
|
|
"entropy": 5.5353536128997805,
|
|
"epoch": 1.0048630408892418,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004907741478079263,
|
|
"loss": 5.1761,
|
|
"mean_token_accuracy": 0.15873774886131287,
|
|
"num_tokens": 22180171.0,
|
|
"step": 10125
|
|
},
|
|
{
|
|
"entropy": 5.559956693649292,
|
|
"epoch": 1.0053592695514093,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004907641031774796,
|
|
"loss": 5.2753,
|
|
"mean_token_accuracy": 0.16398740112781524,
|
|
"num_tokens": 22190531.0,
|
|
"step": 10130
|
|
},
|
|
{
|
|
"entropy": 5.545996809005738,
|
|
"epoch": 1.0058554982135768,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.000490754053196548,
|
|
"loss": 5.1803,
|
|
"mean_token_accuracy": 0.16567456275224685,
|
|
"num_tokens": 22201495.0,
|
|
"step": 10135
|
|
},
|
|
{
|
|
"entropy": 5.619088268280029,
|
|
"epoch": 1.0063517268757443,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004907439978653809,
|
|
"loss": 5.2618,
|
|
"mean_token_accuracy": 0.15639659762382507,
|
|
"num_tokens": 22212941.0,
|
|
"step": 10140
|
|
},
|
|
{
|
|
"entropy": 5.636896085739136,
|
|
"epoch": 1.006847955537912,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004907339371842275,
|
|
"loss": 5.2993,
|
|
"mean_token_accuracy": 0.1600252002477646,
|
|
"num_tokens": 22225212.0,
|
|
"step": 10145
|
|
},
|
|
{
|
|
"entropy": 5.5214286804199215,
|
|
"epoch": 1.0073441842000794,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004907238711533373,
|
|
"loss": 5.2541,
|
|
"mean_token_accuracy": 0.1617978185415268,
|
|
"num_tokens": 22236370.0,
|
|
"step": 10150
|
|
},
|
|
{
|
|
"entropy": 5.557128143310547,
|
|
"epoch": 1.007840412862247,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004907137997729599,
|
|
"loss": 5.213,
|
|
"mean_token_accuracy": 0.1678090587258339,
|
|
"num_tokens": 22247641.0,
|
|
"step": 10155
|
|
},
|
|
{
|
|
"entropy": 5.515650749206543,
|
|
"epoch": 1.0083366415244144,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.000490703723043345,
|
|
"loss": 5.2724,
|
|
"mean_token_accuracy": 0.16332590878009795,
|
|
"num_tokens": 22258599.0,
|
|
"step": 10160
|
|
},
|
|
{
|
|
"entropy": 5.535066986083985,
|
|
"epoch": 1.008832870186582,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004906936409647428,
|
|
"loss": 5.1949,
|
|
"mean_token_accuracy": 0.1628037601709366,
|
|
"num_tokens": 22270913.0,
|
|
"step": 10165
|
|
},
|
|
{
|
|
"entropy": 5.539957666397095,
|
|
"epoch": 1.0093290988487496,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.000490683553537403,
|
|
"loss": 5.1037,
|
|
"mean_token_accuracy": 0.16978239566087722,
|
|
"num_tokens": 22281053.0,
|
|
"step": 10170
|
|
},
|
|
{
|
|
"entropy": 5.526017761230468,
|
|
"epoch": 1.009825327510917,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004906734607615758,
|
|
"loss": 5.1269,
|
|
"mean_token_accuracy": 0.1676328420639038,
|
|
"num_tokens": 22292570.0,
|
|
"step": 10175
|
|
},
|
|
{
|
|
"entropy": 5.509777212142945,
|
|
"epoch": 1.0103215561730845,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004906633626375114,
|
|
"loss": 5.2055,
|
|
"mean_token_accuracy": 0.16312919110059737,
|
|
"num_tokens": 22303548.0,
|
|
"step": 10180
|
|
},
|
|
{
|
|
"entropy": 5.563418865203857,
|
|
"epoch": 1.010817784835252,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004906532591654604,
|
|
"loss": 5.2281,
|
|
"mean_token_accuracy": 0.16960761696100235,
|
|
"num_tokens": 22314133.0,
|
|
"step": 10185
|
|
},
|
|
{
|
|
"entropy": 5.581880044937134,
|
|
"epoch": 1.0113140134974197,
|
|
"grad_norm": 0.76953125,
|
|
"learning_rate": 0.0004906431503456733,
|
|
"loss": 5.2008,
|
|
"mean_token_accuracy": 0.1627922311425209,
|
|
"num_tokens": 22326431.0,
|
|
"step": 10190
|
|
},
|
|
{
|
|
"entropy": 5.540881824493408,
|
|
"epoch": 1.0118102421595871,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004906330361784007,
|
|
"loss": 5.239,
|
|
"mean_token_accuracy": 0.16488454043865203,
|
|
"num_tokens": 22338507.0,
|
|
"step": 10195
|
|
},
|
|
{
|
|
"entropy": 5.517429780960083,
|
|
"epoch": 1.0123064708217546,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004906229166638936,
|
|
"loss": 5.2111,
|
|
"mean_token_accuracy": 0.16140173077583314,
|
|
"num_tokens": 22348863.0,
|
|
"step": 10200
|
|
},
|
|
{
|
|
"entropy": 5.484919691085816,
|
|
"epoch": 1.012802699483922,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004906127918024026,
|
|
"loss": 5.1588,
|
|
"mean_token_accuracy": 0.16300449669361114,
|
|
"num_tokens": 22359000.0,
|
|
"step": 10205
|
|
},
|
|
{
|
|
"entropy": 5.5954266548156735,
|
|
"epoch": 1.0132989281460898,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004906026615941791,
|
|
"loss": 5.2945,
|
|
"mean_token_accuracy": 0.157001593708992,
|
|
"num_tokens": 22369539.0,
|
|
"step": 10210
|
|
},
|
|
{
|
|
"entropy": 5.578581285476685,
|
|
"epoch": 1.0137951568082573,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004905925260394741,
|
|
"loss": 5.2615,
|
|
"mean_token_accuracy": 0.16177936643362045,
|
|
"num_tokens": 22380700.0,
|
|
"step": 10215
|
|
},
|
|
{
|
|
"entropy": 5.537117147445679,
|
|
"epoch": 1.0142913854704247,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.000490582385138539,
|
|
"loss": 5.2368,
|
|
"mean_token_accuracy": 0.1548960104584694,
|
|
"num_tokens": 22392151.0,
|
|
"step": 10220
|
|
},
|
|
{
|
|
"entropy": 5.526557683944702,
|
|
"epoch": 1.0147876141325922,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004905722388916254,
|
|
"loss": 5.212,
|
|
"mean_token_accuracy": 0.166645385324955,
|
|
"num_tokens": 22401735.0,
|
|
"step": 10225
|
|
},
|
|
{
|
|
"entropy": 5.570654678344726,
|
|
"epoch": 1.01528384279476,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004905620872989846,
|
|
"loss": 5.2798,
|
|
"mean_token_accuracy": 0.1610209047794342,
|
|
"num_tokens": 22412549.0,
|
|
"step": 10230
|
|
},
|
|
{
|
|
"entropy": 5.614617395401001,
|
|
"epoch": 1.0157800714569274,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004905519303608687,
|
|
"loss": 5.2633,
|
|
"mean_token_accuracy": 0.16019045561552048,
|
|
"num_tokens": 22424728.0,
|
|
"step": 10235
|
|
},
|
|
{
|
|
"entropy": 5.491592454910278,
|
|
"epoch": 1.0162763001190949,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004905417680775294,
|
|
"loss": 5.1436,
|
|
"mean_token_accuracy": 0.16299115121364594,
|
|
"num_tokens": 22434197.0,
|
|
"step": 10240
|
|
},
|
|
{
|
|
"entropy": 5.610570001602173,
|
|
"epoch": 1.0167725287812623,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004905316004492186,
|
|
"loss": 5.3314,
|
|
"mean_token_accuracy": 0.1562383472919464,
|
|
"num_tokens": 22444671.0,
|
|
"step": 10245
|
|
},
|
|
{
|
|
"entropy": 5.529538679122925,
|
|
"epoch": 1.01726875744343,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004905214274761885,
|
|
"loss": 5.1939,
|
|
"mean_token_accuracy": 0.16395601779222488,
|
|
"num_tokens": 22456636.0,
|
|
"step": 10250
|
|
},
|
|
{
|
|
"entropy": 5.4973588466644285,
|
|
"epoch": 1.0177649861055975,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004905112491586915,
|
|
"loss": 5.1375,
|
|
"mean_token_accuracy": 0.170780511200428,
|
|
"num_tokens": 22467011.0,
|
|
"step": 10255
|
|
},
|
|
{
|
|
"entropy": 5.523624897003174,
|
|
"epoch": 1.018261214767765,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00049050106549698,
|
|
"loss": 5.2321,
|
|
"mean_token_accuracy": 0.16345654129981996,
|
|
"num_tokens": 22477630.0,
|
|
"step": 10260
|
|
},
|
|
{
|
|
"entropy": 5.512229251861572,
|
|
"epoch": 1.0187574434299325,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004904908764913063,
|
|
"loss": 5.1867,
|
|
"mean_token_accuracy": 0.16930550932884217,
|
|
"num_tokens": 22488132.0,
|
|
"step": 10265
|
|
},
|
|
{
|
|
"entropy": 5.477755403518676,
|
|
"epoch": 1.0192536720921,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004904806821419233,
|
|
"loss": 5.2339,
|
|
"mean_token_accuracy": 0.15899064689874648,
|
|
"num_tokens": 22499430.0,
|
|
"step": 10270
|
|
},
|
|
{
|
|
"entropy": 5.541066360473633,
|
|
"epoch": 1.0197499007542676,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004904704824490835,
|
|
"loss": 5.1672,
|
|
"mean_token_accuracy": 0.1635948821902275,
|
|
"num_tokens": 22509728.0,
|
|
"step": 10275
|
|
},
|
|
{
|
|
"entropy": 5.577764987945557,
|
|
"epoch": 1.020246129416435,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004904602774130402,
|
|
"loss": 5.2761,
|
|
"mean_token_accuracy": 0.15536259561777116,
|
|
"num_tokens": 22520955.0,
|
|
"step": 10280
|
|
},
|
|
{
|
|
"entropy": 5.629702186584472,
|
|
"epoch": 1.0207423580786026,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004904500670340463,
|
|
"loss": 5.2964,
|
|
"mean_token_accuracy": 0.15821094959974288,
|
|
"num_tokens": 22530440.0,
|
|
"step": 10285
|
|
},
|
|
{
|
|
"entropy": 5.540016794204712,
|
|
"epoch": 1.02123858674077,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.000490439851312355,
|
|
"loss": 5.2475,
|
|
"mean_token_accuracy": 0.171015864610672,
|
|
"num_tokens": 22541539.0,
|
|
"step": 10290
|
|
},
|
|
{
|
|
"entropy": 5.544416809082032,
|
|
"epoch": 1.0217348154029378,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004904296302482196,
|
|
"loss": 5.2322,
|
|
"mean_token_accuracy": 0.16253914684057236,
|
|
"num_tokens": 22555717.0,
|
|
"step": 10295
|
|
},
|
|
{
|
|
"entropy": 5.613153886795044,
|
|
"epoch": 1.0222310440651052,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004904194038418935,
|
|
"loss": 5.3377,
|
|
"mean_token_accuracy": 0.1595346972346306,
|
|
"num_tokens": 22566938.0,
|
|
"step": 10300
|
|
},
|
|
{
|
|
"entropy": 5.665261459350586,
|
|
"epoch": 1.0227272727272727,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004904091720936305,
|
|
"loss": 5.2044,
|
|
"mean_token_accuracy": 0.1597888469696045,
|
|
"num_tokens": 22578725.0,
|
|
"step": 10305
|
|
},
|
|
{
|
|
"entropy": 5.555477476119995,
|
|
"epoch": 1.0232235013894402,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004903989350036841,
|
|
"loss": 5.133,
|
|
"mean_token_accuracy": 0.17128655016422273,
|
|
"num_tokens": 22588476.0,
|
|
"step": 10310
|
|
},
|
|
{
|
|
"entropy": 5.5689750671386715,
|
|
"epoch": 1.0237197300516079,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004903886925723083,
|
|
"loss": 5.3335,
|
|
"mean_token_accuracy": 0.1574925050139427,
|
|
"num_tokens": 22600294.0,
|
|
"step": 10315
|
|
},
|
|
{
|
|
"entropy": 5.60640025138855,
|
|
"epoch": 1.0242159587137754,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.000490378444799757,
|
|
"loss": 5.2219,
|
|
"mean_token_accuracy": 0.16590719819068908,
|
|
"num_tokens": 22610578.0,
|
|
"step": 10320
|
|
},
|
|
{
|
|
"entropy": 5.616174936294556,
|
|
"epoch": 1.0247121873759428,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004903681916862844,
|
|
"loss": 5.2451,
|
|
"mean_token_accuracy": 0.16193822175264358,
|
|
"num_tokens": 22620988.0,
|
|
"step": 10325
|
|
},
|
|
{
|
|
"entropy": 5.537631797790527,
|
|
"epoch": 1.0252084160381103,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004903579332321447,
|
|
"loss": 5.2202,
|
|
"mean_token_accuracy": 0.16445315182209014,
|
|
"num_tokens": 22632198.0,
|
|
"step": 10330
|
|
},
|
|
{
|
|
"entropy": 5.5386731147766115,
|
|
"epoch": 1.0257046447002778,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004903476694375924,
|
|
"loss": 5.2245,
|
|
"mean_token_accuracy": 0.17040131539106368,
|
|
"num_tokens": 22642543.0,
|
|
"step": 10335
|
|
},
|
|
{
|
|
"entropy": 5.565079832077027,
|
|
"epoch": 1.0262008733624455,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004903374003028819,
|
|
"loss": 5.2179,
|
|
"mean_token_accuracy": 0.16459809094667435,
|
|
"num_tokens": 22655453.0,
|
|
"step": 10340
|
|
},
|
|
{
|
|
"entropy": 5.510003232955933,
|
|
"epoch": 1.026697102024613,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004903271258282678,
|
|
"loss": 5.1604,
|
|
"mean_token_accuracy": 0.1727517679333687,
|
|
"num_tokens": 22667342.0,
|
|
"step": 10345
|
|
},
|
|
{
|
|
"entropy": 5.616212701797485,
|
|
"epoch": 1.0271933306867804,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004903168460140049,
|
|
"loss": 5.2466,
|
|
"mean_token_accuracy": 0.16790675669908522,
|
|
"num_tokens": 22676890.0,
|
|
"step": 10350
|
|
},
|
|
{
|
|
"entropy": 5.553227472305298,
|
|
"epoch": 1.027689559348948,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004903065608603484,
|
|
"loss": 5.239,
|
|
"mean_token_accuracy": 0.16413081735372542,
|
|
"num_tokens": 22687809.0,
|
|
"step": 10355
|
|
},
|
|
{
|
|
"entropy": 5.509211540222168,
|
|
"epoch": 1.0281857880111156,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.000490296270367553,
|
|
"loss": 5.2487,
|
|
"mean_token_accuracy": 0.16225795596837997,
|
|
"num_tokens": 22697938.0,
|
|
"step": 10360
|
|
},
|
|
{
|
|
"entropy": 5.625287103652954,
|
|
"epoch": 1.028682016673283,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004902859745358741,
|
|
"loss": 5.2398,
|
|
"mean_token_accuracy": 0.16604799926280975,
|
|
"num_tokens": 22708303.0,
|
|
"step": 10365
|
|
},
|
|
{
|
|
"entropy": 5.5169538974761965,
|
|
"epoch": 1.0291782453354505,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004902756733655668,
|
|
"loss": 5.1732,
|
|
"mean_token_accuracy": 0.16808167099952698,
|
|
"num_tokens": 22717987.0,
|
|
"step": 10370
|
|
},
|
|
{
|
|
"entropy": 5.515469884872436,
|
|
"epoch": 1.029674473997618,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004902653668568868,
|
|
"loss": 5.25,
|
|
"mean_token_accuracy": 0.16545470654964448,
|
|
"num_tokens": 22729672.0,
|
|
"step": 10375
|
|
},
|
|
{
|
|
"entropy": 5.574868202209473,
|
|
"epoch": 1.0301707026597857,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004902550550100896,
|
|
"loss": 5.2082,
|
|
"mean_token_accuracy": 0.17231257408857345,
|
|
"num_tokens": 22741296.0,
|
|
"step": 10380
|
|
},
|
|
{
|
|
"entropy": 5.56593770980835,
|
|
"epoch": 1.0306669313219532,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004902447378254307,
|
|
"loss": 5.2163,
|
|
"mean_token_accuracy": 0.16785264909267425,
|
|
"num_tokens": 22752337.0,
|
|
"step": 10385
|
|
},
|
|
{
|
|
"entropy": 5.578250932693481,
|
|
"epoch": 1.0311631599841207,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004902344153031663,
|
|
"loss": 5.2412,
|
|
"mean_token_accuracy": 0.16290030479431153,
|
|
"num_tokens": 22762681.0,
|
|
"step": 10390
|
|
},
|
|
{
|
|
"entropy": 5.6123497009277346,
|
|
"epoch": 1.0316593886462881,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.000490224087443552,
|
|
"loss": 5.283,
|
|
"mean_token_accuracy": 0.15981359630823136,
|
|
"num_tokens": 22774275.0,
|
|
"step": 10395
|
|
},
|
|
{
|
|
"entropy": 5.511215019226074,
|
|
"epoch": 1.0321556173084558,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004902137542468442,
|
|
"loss": 5.1508,
|
|
"mean_token_accuracy": 0.1674342632293701,
|
|
"num_tokens": 22785944.0,
|
|
"step": 10400
|
|
},
|
|
{
|
|
"entropy": 5.499436521530152,
|
|
"epoch": 1.0326518459706233,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004902034157132991,
|
|
"loss": 5.0925,
|
|
"mean_token_accuracy": 0.16678470075130464,
|
|
"num_tokens": 22796543.0,
|
|
"step": 10405
|
|
},
|
|
{
|
|
"entropy": 5.503799533843994,
|
|
"epoch": 1.0331480746327908,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004901930718431729,
|
|
"loss": 5.2084,
|
|
"mean_token_accuracy": 0.1636475369334221,
|
|
"num_tokens": 22807957.0,
|
|
"step": 10410
|
|
},
|
|
{
|
|
"entropy": 5.589832401275634,
|
|
"epoch": 1.0336443032949583,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004901827226367223,
|
|
"loss": 5.3044,
|
|
"mean_token_accuracy": 0.16381883323192598,
|
|
"num_tokens": 22818903.0,
|
|
"step": 10415
|
|
},
|
|
{
|
|
"entropy": 5.607730150222778,
|
|
"epoch": 1.0341405319571257,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004901723680942038,
|
|
"loss": 5.3367,
|
|
"mean_token_accuracy": 0.16103588938713073,
|
|
"num_tokens": 22829286.0,
|
|
"step": 10420
|
|
},
|
|
{
|
|
"entropy": 5.597163105010987,
|
|
"epoch": 1.0346367606192934,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004901620082158742,
|
|
"loss": 5.2421,
|
|
"mean_token_accuracy": 0.1619735226035118,
|
|
"num_tokens": 22839860.0,
|
|
"step": 10425
|
|
},
|
|
{
|
|
"entropy": 5.607494163513183,
|
|
"epoch": 1.035132989281461,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004901516430019905,
|
|
"loss": 5.2862,
|
|
"mean_token_accuracy": 0.15376426428556442,
|
|
"num_tokens": 22852238.0,
|
|
"step": 10430
|
|
},
|
|
{
|
|
"entropy": 5.581726598739624,
|
|
"epoch": 1.0356292179436284,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.0004901412724528097,
|
|
"loss": 5.2666,
|
|
"mean_token_accuracy": 0.1640608638525009,
|
|
"num_tokens": 22863013.0,
|
|
"step": 10435
|
|
},
|
|
{
|
|
"entropy": 5.523475646972656,
|
|
"epoch": 1.0361254466057959,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004901308965685889,
|
|
"loss": 5.1225,
|
|
"mean_token_accuracy": 0.16678005307912827,
|
|
"num_tokens": 22874233.0,
|
|
"step": 10440
|
|
},
|
|
{
|
|
"entropy": 5.572403764724731,
|
|
"epoch": 1.0366216752679636,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004901205153495853,
|
|
"loss": 5.2973,
|
|
"mean_token_accuracy": 0.15935328900814055,
|
|
"num_tokens": 22885313.0,
|
|
"step": 10445
|
|
},
|
|
{
|
|
"entropy": 5.534413146972656,
|
|
"epoch": 1.037117903930131,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004901101287960566,
|
|
"loss": 5.1848,
|
|
"mean_token_accuracy": 0.16433444768190383,
|
|
"num_tokens": 22895365.0,
|
|
"step": 10450
|
|
},
|
|
{
|
|
"entropy": 5.500718212127685,
|
|
"epoch": 1.0376141325922985,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004900997369082602,
|
|
"loss": 5.1861,
|
|
"mean_token_accuracy": 0.15906585305929183,
|
|
"num_tokens": 22906392.0,
|
|
"step": 10455
|
|
},
|
|
{
|
|
"entropy": 5.48196005821228,
|
|
"epoch": 1.038110361254466,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004900893396864539,
|
|
"loss": 5.1424,
|
|
"mean_token_accuracy": 0.16976341009140014,
|
|
"num_tokens": 22916760.0,
|
|
"step": 10460
|
|
},
|
|
{
|
|
"entropy": 5.570258903503418,
|
|
"epoch": 1.0386065899166337,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004900789371308953,
|
|
"loss": 5.2058,
|
|
"mean_token_accuracy": 0.16422784626483916,
|
|
"num_tokens": 22928070.0,
|
|
"step": 10465
|
|
},
|
|
{
|
|
"entropy": 5.470105075836182,
|
|
"epoch": 1.0391028185788012,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004900685292418425,
|
|
"loss": 5.1797,
|
|
"mean_token_accuracy": 0.1650763064622879,
|
|
"num_tokens": 22938815.0,
|
|
"step": 10470
|
|
},
|
|
{
|
|
"entropy": 5.53947172164917,
|
|
"epoch": 1.0395990472409686,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004900581160195537,
|
|
"loss": 5.2512,
|
|
"mean_token_accuracy": 0.15671544075012206,
|
|
"num_tokens": 22949806.0,
|
|
"step": 10475
|
|
},
|
|
{
|
|
"entropy": 5.5062002658844,
|
|
"epoch": 1.040095275903136,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.000490047697464287,
|
|
"loss": 5.0866,
|
|
"mean_token_accuracy": 0.16767628192901612,
|
|
"num_tokens": 22960880.0,
|
|
"step": 10480
|
|
},
|
|
{
|
|
"entropy": 5.567434787750244,
|
|
"epoch": 1.0405915045653038,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.0004900372735763009,
|
|
"loss": 5.2358,
|
|
"mean_token_accuracy": 0.16065094918012618,
|
|
"num_tokens": 22972828.0,
|
|
"step": 10485
|
|
},
|
|
{
|
|
"entropy": 5.480893564224243,
|
|
"epoch": 1.0410877332274713,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004900268443558536,
|
|
"loss": 5.1356,
|
|
"mean_token_accuracy": 0.1689052939414978,
|
|
"num_tokens": 22981869.0,
|
|
"step": 10490
|
|
},
|
|
{
|
|
"entropy": 5.588772296905518,
|
|
"epoch": 1.0415839618896388,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000490016409803204,
|
|
"loss": 5.2549,
|
|
"mean_token_accuracy": 0.1603129178285599,
|
|
"num_tokens": 22993111.0,
|
|
"step": 10495
|
|
},
|
|
{
|
|
"entropy": 5.554627847671509,
|
|
"epoch": 1.0420801905518062,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004900059699186108,
|
|
"loss": 5.2244,
|
|
"mean_token_accuracy": 0.16340605169534683,
|
|
"num_tokens": 23003115.0,
|
|
"step": 10500
|
|
},
|
|
{
|
|
"entropy": 5.618977880477905,
|
|
"epoch": 1.0425764192139737,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004899955247023328,
|
|
"loss": 5.2683,
|
|
"mean_token_accuracy": 0.16093970984220504,
|
|
"num_tokens": 23012587.0,
|
|
"step": 10505
|
|
},
|
|
{
|
|
"entropy": 5.584914302825927,
|
|
"epoch": 1.0430726478761414,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.000489985074154629,
|
|
"loss": 5.2885,
|
|
"mean_token_accuracy": 0.15495433360338212,
|
|
"num_tokens": 23024455.0,
|
|
"step": 10510
|
|
},
|
|
{
|
|
"entropy": 5.559906768798828,
|
|
"epoch": 1.0435688765383089,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004899746182757587,
|
|
"loss": 5.2154,
|
|
"mean_token_accuracy": 0.1636367544531822,
|
|
"num_tokens": 23034430.0,
|
|
"step": 10515
|
|
},
|
|
{
|
|
"entropy": 5.573592901229858,
|
|
"epoch": 1.0440651052004764,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004899641570659811,
|
|
"loss": 5.2827,
|
|
"mean_token_accuracy": 0.16297447830438613,
|
|
"num_tokens": 23044811.0,
|
|
"step": 10520
|
|
},
|
|
{
|
|
"entropy": 5.583052492141723,
|
|
"epoch": 1.0445613338626438,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004899536905255555,
|
|
"loss": 5.3092,
|
|
"mean_token_accuracy": 0.16133083999156952,
|
|
"num_tokens": 23056179.0,
|
|
"step": 10525
|
|
},
|
|
{
|
|
"entropy": 5.5573999881744385,
|
|
"epoch": 1.0450575625248115,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004899432186547416,
|
|
"loss": 5.2249,
|
|
"mean_token_accuracy": 0.16555059999227523,
|
|
"num_tokens": 23068331.0,
|
|
"step": 10530
|
|
},
|
|
{
|
|
"entropy": 5.532347536087036,
|
|
"epoch": 1.045553791186979,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004899327414537991,
|
|
"loss": 5.2172,
|
|
"mean_token_accuracy": 0.15943560004234314,
|
|
"num_tokens": 23079213.0,
|
|
"step": 10535
|
|
},
|
|
{
|
|
"entropy": 5.639857959747315,
|
|
"epoch": 1.0460500198491465,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004899222589229877,
|
|
"loss": 5.3245,
|
|
"mean_token_accuracy": 0.1575188159942627,
|
|
"num_tokens": 23089860.0,
|
|
"step": 10540
|
|
},
|
|
{
|
|
"entropy": 5.526367950439453,
|
|
"epoch": 1.046546248511314,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004899117710625674,
|
|
"loss": 5.1883,
|
|
"mean_token_accuracy": 0.17317425310611725,
|
|
"num_tokens": 23099431.0,
|
|
"step": 10545
|
|
},
|
|
{
|
|
"entropy": 5.567355155944824,
|
|
"epoch": 1.0470424771734816,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004899012778727983,
|
|
"loss": 5.2666,
|
|
"mean_token_accuracy": 0.1594635382294655,
|
|
"num_tokens": 23110947.0,
|
|
"step": 10550
|
|
},
|
|
{
|
|
"entropy": 5.594871854782104,
|
|
"epoch": 1.0475387058356491,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004898907793539406,
|
|
"loss": 5.3477,
|
|
"mean_token_accuracy": 0.16127041429281236,
|
|
"num_tokens": 23122782.0,
|
|
"step": 10555
|
|
},
|
|
{
|
|
"entropy": 5.639073514938355,
|
|
"epoch": 1.0480349344978166,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004898802755062546,
|
|
"loss": 5.2485,
|
|
"mean_token_accuracy": 0.16379223763942719,
|
|
"num_tokens": 23134254.0,
|
|
"step": 10560
|
|
},
|
|
{
|
|
"entropy": 5.5020448684692385,
|
|
"epoch": 1.048531163159984,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004898697663300007,
|
|
"loss": 5.0902,
|
|
"mean_token_accuracy": 0.17229089438915252,
|
|
"num_tokens": 23143851.0,
|
|
"step": 10565
|
|
},
|
|
{
|
|
"entropy": 5.543505001068115,
|
|
"epoch": 1.0490273918221515,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004898592518254398,
|
|
"loss": 5.2111,
|
|
"mean_token_accuracy": 0.1649421662092209,
|
|
"num_tokens": 23155966.0,
|
|
"step": 10570
|
|
},
|
|
{
|
|
"entropy": 5.5180806636810305,
|
|
"epoch": 1.0495236204843192,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004898487319928322,
|
|
"loss": 5.2171,
|
|
"mean_token_accuracy": 0.16143583357334138,
|
|
"num_tokens": 23165896.0,
|
|
"step": 10575
|
|
},
|
|
{
|
|
"entropy": 5.549243545532226,
|
|
"epoch": 1.0500198491464867,
|
|
"grad_norm": 0.7578125,
|
|
"learning_rate": 0.0004898382068324392,
|
|
"loss": 5.1975,
|
|
"mean_token_accuracy": 0.16661687195301056,
|
|
"num_tokens": 23177821.0,
|
|
"step": 10580
|
|
},
|
|
{
|
|
"entropy": 5.575086975097657,
|
|
"epoch": 1.0505160778086542,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004898276763445215,
|
|
"loss": 5.2779,
|
|
"mean_token_accuracy": 0.16044059693813323,
|
|
"num_tokens": 23188916.0,
|
|
"step": 10585
|
|
},
|
|
{
|
|
"entropy": 5.6137364387512205,
|
|
"epoch": 1.0510123064708217,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004898171405293404,
|
|
"loss": 5.2622,
|
|
"mean_token_accuracy": 0.16863634288311005,
|
|
"num_tokens": 23200490.0,
|
|
"step": 10590
|
|
},
|
|
{
|
|
"entropy": 5.5093831539154055,
|
|
"epoch": 1.0515085351329894,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004898065993871571,
|
|
"loss": 5.1958,
|
|
"mean_token_accuracy": 0.16129535883665086,
|
|
"num_tokens": 23212991.0,
|
|
"step": 10595
|
|
},
|
|
{
|
|
"entropy": 5.622107601165771,
|
|
"epoch": 1.0520047637951568,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.000489796052918233,
|
|
"loss": 5.3079,
|
|
"mean_token_accuracy": 0.15788715630769729,
|
|
"num_tokens": 23223361.0,
|
|
"step": 10600
|
|
},
|
|
{
|
|
"entropy": 5.596247768402099,
|
|
"epoch": 1.0525009924573243,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004897855011228295,
|
|
"loss": 5.2133,
|
|
"mean_token_accuracy": 0.16734395325183868,
|
|
"num_tokens": 23233765.0,
|
|
"step": 10605
|
|
},
|
|
{
|
|
"entropy": 5.5176421165466305,
|
|
"epoch": 1.0529972211194918,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004897749440012085,
|
|
"loss": 5.1477,
|
|
"mean_token_accuracy": 0.1680014982819557,
|
|
"num_tokens": 23246562.0,
|
|
"step": 10610
|
|
},
|
|
{
|
|
"entropy": 5.547542333602905,
|
|
"epoch": 1.0534934497816595,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004897643815536316,
|
|
"loss": 5.1867,
|
|
"mean_token_accuracy": 0.16317762434482574,
|
|
"num_tokens": 23256648.0,
|
|
"step": 10615
|
|
},
|
|
{
|
|
"entropy": 5.580404472351074,
|
|
"epoch": 1.053989678443827,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.000489753813780361,
|
|
"loss": 5.2331,
|
|
"mean_token_accuracy": 0.1619618281722069,
|
|
"num_tokens": 23267428.0,
|
|
"step": 10620
|
|
},
|
|
{
|
|
"entropy": 5.5343564510345455,
|
|
"epoch": 1.0544859071059944,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004897432406816585,
|
|
"loss": 5.1703,
|
|
"mean_token_accuracy": 0.16505475640296935,
|
|
"num_tokens": 23278440.0,
|
|
"step": 10625
|
|
},
|
|
{
|
|
"entropy": 5.544847297668457,
|
|
"epoch": 1.054982135768162,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004897326622577863,
|
|
"loss": 5.212,
|
|
"mean_token_accuracy": 0.1572507679462433,
|
|
"num_tokens": 23290571.0,
|
|
"step": 10630
|
|
},
|
|
{
|
|
"entropy": 5.620430898666382,
|
|
"epoch": 1.0554783644303294,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004897220785090067,
|
|
"loss": 5.3031,
|
|
"mean_token_accuracy": 0.15959957987070084,
|
|
"num_tokens": 23301634.0,
|
|
"step": 10635
|
|
},
|
|
{
|
|
"entropy": 5.508328247070312,
|
|
"epoch": 1.055974593092497,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004897114894355824,
|
|
"loss": 5.1701,
|
|
"mean_token_accuracy": 0.16848744302988053,
|
|
"num_tokens": 23313125.0,
|
|
"step": 10640
|
|
},
|
|
{
|
|
"entropy": 5.520039892196655,
|
|
"epoch": 1.0564708217546646,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004897008950377758,
|
|
"loss": 5.1828,
|
|
"mean_token_accuracy": 0.16111970990896224,
|
|
"num_tokens": 23323610.0,
|
|
"step": 10645
|
|
},
|
|
{
|
|
"entropy": 5.505582284927368,
|
|
"epoch": 1.056967050416832,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004896902953158497,
|
|
"loss": 5.1596,
|
|
"mean_token_accuracy": 0.16464336961507797,
|
|
"num_tokens": 23333652.0,
|
|
"step": 10650
|
|
},
|
|
{
|
|
"entropy": 5.500342750549317,
|
|
"epoch": 1.0574632790789995,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004896796902700667,
|
|
"loss": 5.2099,
|
|
"mean_token_accuracy": 0.16780153959989547,
|
|
"num_tokens": 23345954.0,
|
|
"step": 10655
|
|
},
|
|
{
|
|
"entropy": 5.5207911968231205,
|
|
"epoch": 1.0579595077411672,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004896690799006901,
|
|
"loss": 5.1939,
|
|
"mean_token_accuracy": 0.16783688515424727,
|
|
"num_tokens": 23357052.0,
|
|
"step": 10660
|
|
},
|
|
{
|
|
"entropy": 5.567644262313843,
|
|
"epoch": 1.0584557364033347,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004896584642079828,
|
|
"loss": 5.1852,
|
|
"mean_token_accuracy": 0.17200947701931,
|
|
"num_tokens": 23368837.0,
|
|
"step": 10665
|
|
},
|
|
{
|
|
"entropy": 5.510286521911621,
|
|
"epoch": 1.0589519650655022,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004896478431922083,
|
|
"loss": 5.1754,
|
|
"mean_token_accuracy": 0.16501798629760742,
|
|
"num_tokens": 23378608.0,
|
|
"step": 10670
|
|
},
|
|
{
|
|
"entropy": 5.577546834945679,
|
|
"epoch": 1.0594481937276696,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004896372168536297,
|
|
"loss": 5.2464,
|
|
"mean_token_accuracy": 0.16384269744157792,
|
|
"num_tokens": 23390094.0,
|
|
"step": 10675
|
|
},
|
|
{
|
|
"entropy": 5.521884918212891,
|
|
"epoch": 1.0599444223898373,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004896265851925107,
|
|
"loss": 5.1273,
|
|
"mean_token_accuracy": 0.16916622072458268,
|
|
"num_tokens": 23399991.0,
|
|
"step": 10680
|
|
},
|
|
{
|
|
"entropy": 5.565446949005127,
|
|
"epoch": 1.0604406510520048,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004896159482091148,
|
|
"loss": 5.3217,
|
|
"mean_token_accuracy": 0.15393658131361007,
|
|
"num_tokens": 23410705.0,
|
|
"step": 10685
|
|
},
|
|
{
|
|
"entropy": 5.490183115005493,
|
|
"epoch": 1.0609368797141723,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004896053059037058,
|
|
"loss": 5.1054,
|
|
"mean_token_accuracy": 0.17834767401218415,
|
|
"num_tokens": 23421939.0,
|
|
"step": 10690
|
|
},
|
|
{
|
|
"entropy": 5.547630167007446,
|
|
"epoch": 1.0614331083763398,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004895946582765477,
|
|
"loss": 5.2403,
|
|
"mean_token_accuracy": 0.1605248786509037,
|
|
"num_tokens": 23433252.0,
|
|
"step": 10695
|
|
},
|
|
{
|
|
"entropy": 5.649627161026001,
|
|
"epoch": 1.0619293370385074,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004895840053279045,
|
|
"loss": 5.3047,
|
|
"mean_token_accuracy": 0.1565993219614029,
|
|
"num_tokens": 23445582.0,
|
|
"step": 10700
|
|
},
|
|
{
|
|
"entropy": 5.60404782295227,
|
|
"epoch": 1.062425565700675,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004895733470580404,
|
|
"loss": 5.269,
|
|
"mean_token_accuracy": 0.155484139919281,
|
|
"num_tokens": 23456360.0,
|
|
"step": 10705
|
|
},
|
|
{
|
|
"entropy": 5.570484304428101,
|
|
"epoch": 1.0629217943628424,
|
|
"grad_norm": 0.7890625,
|
|
"learning_rate": 0.0004895626834672196,
|
|
"loss": 5.1499,
|
|
"mean_token_accuracy": 0.16302104145288468,
|
|
"num_tokens": 23466576.0,
|
|
"step": 10710
|
|
},
|
|
{
|
|
"entropy": 5.469333744049072,
|
|
"epoch": 1.0634180230250099,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004895520145557066,
|
|
"loss": 5.1063,
|
|
"mean_token_accuracy": 0.17305240035057068,
|
|
"num_tokens": 23476200.0,
|
|
"step": 10715
|
|
},
|
|
{
|
|
"entropy": 5.577377367019653,
|
|
"epoch": 1.0639142516871773,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004895413403237659,
|
|
"loss": 5.2998,
|
|
"mean_token_accuracy": 0.1634572774171829,
|
|
"num_tokens": 23487776.0,
|
|
"step": 10720
|
|
},
|
|
{
|
|
"entropy": 5.531701850891113,
|
|
"epoch": 1.064410480349345,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004895306607716624,
|
|
"loss": 5.1623,
|
|
"mean_token_accuracy": 0.17161939442157745,
|
|
"num_tokens": 23497517.0,
|
|
"step": 10725
|
|
},
|
|
{
|
|
"entropy": 5.566427087783813,
|
|
"epoch": 1.0649067090115125,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004895199758996607,
|
|
"loss": 5.186,
|
|
"mean_token_accuracy": 0.1692622035741806,
|
|
"num_tokens": 23507436.0,
|
|
"step": 10730
|
|
},
|
|
{
|
|
"entropy": 5.547843360900879,
|
|
"epoch": 1.06540293767368,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004895092857080258,
|
|
"loss": 5.1391,
|
|
"mean_token_accuracy": 0.15670267716050149,
|
|
"num_tokens": 23517170.0,
|
|
"step": 10735
|
|
},
|
|
{
|
|
"entropy": 5.523667716979981,
|
|
"epoch": 1.0658991663358475,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004894985901970229,
|
|
"loss": 5.1461,
|
|
"mean_token_accuracy": 0.17285354286432267,
|
|
"num_tokens": 23527329.0,
|
|
"step": 10740
|
|
},
|
|
{
|
|
"entropy": 5.546849012374878,
|
|
"epoch": 1.0663953949980152,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004894878893669171,
|
|
"loss": 5.2449,
|
|
"mean_token_accuracy": 0.1577153228223324,
|
|
"num_tokens": 23538341.0,
|
|
"step": 10745
|
|
},
|
|
{
|
|
"entropy": 5.55429220199585,
|
|
"epoch": 1.0668916236601826,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004894771832179739,
|
|
"loss": 5.1759,
|
|
"mean_token_accuracy": 0.1622370421886444,
|
|
"num_tokens": 23549522.0,
|
|
"step": 10750
|
|
},
|
|
{
|
|
"entropy": 5.601254224777222,
|
|
"epoch": 1.0673878523223501,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004894664717504587,
|
|
"loss": 5.212,
|
|
"mean_token_accuracy": 0.1650427684187889,
|
|
"num_tokens": 23559274.0,
|
|
"step": 10755
|
|
},
|
|
{
|
|
"entropy": 5.543829917907715,
|
|
"epoch": 1.0678840809845176,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004894557549646371,
|
|
"loss": 5.1676,
|
|
"mean_token_accuracy": 0.16680517047643661,
|
|
"num_tokens": 23570852.0,
|
|
"step": 10760
|
|
},
|
|
{
|
|
"entropy": 5.522302579879761,
|
|
"epoch": 1.0683803096466853,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004894450328607749,
|
|
"loss": 5.1753,
|
|
"mean_token_accuracy": 0.16622244268655778,
|
|
"num_tokens": 23582918.0,
|
|
"step": 10765
|
|
},
|
|
{
|
|
"entropy": 5.489535284042359,
|
|
"epoch": 1.0688765383088528,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004894343054391379,
|
|
"loss": 5.2023,
|
|
"mean_token_accuracy": 0.17074786126613617,
|
|
"num_tokens": 23594177.0,
|
|
"step": 10770
|
|
},
|
|
{
|
|
"entropy": 5.546436786651611,
|
|
"epoch": 1.0693727669710202,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004894235726999924,
|
|
"loss": 5.1724,
|
|
"mean_token_accuracy": 0.1656903401017189,
|
|
"num_tokens": 23605901.0,
|
|
"step": 10775
|
|
},
|
|
{
|
|
"entropy": 5.521238327026367,
|
|
"epoch": 1.0698689956331877,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.0004894128346436042,
|
|
"loss": 5.2198,
|
|
"mean_token_accuracy": 0.16673441082239152,
|
|
"num_tokens": 23617354.0,
|
|
"step": 10780
|
|
},
|
|
{
|
|
"entropy": 5.568436861038208,
|
|
"epoch": 1.0703652242953554,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004894020912702397,
|
|
"loss": 5.241,
|
|
"mean_token_accuracy": 0.16437995582818984,
|
|
"num_tokens": 23627603.0,
|
|
"step": 10785
|
|
},
|
|
{
|
|
"entropy": 5.4602922916412355,
|
|
"epoch": 1.0708614529575229,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004893913425801653,
|
|
"loss": 5.0669,
|
|
"mean_token_accuracy": 0.17634545862674714,
|
|
"num_tokens": 23637280.0,
|
|
"step": 10790
|
|
},
|
|
{
|
|
"entropy": 5.541663074493409,
|
|
"epoch": 1.0713576816196904,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004893805885736477,
|
|
"loss": 5.2737,
|
|
"mean_token_accuracy": 0.16722501814365387,
|
|
"num_tokens": 23649326.0,
|
|
"step": 10795
|
|
},
|
|
{
|
|
"entropy": 5.614739513397216,
|
|
"epoch": 1.0718539102818578,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004893698292509534,
|
|
"loss": 5.2817,
|
|
"mean_token_accuracy": 0.15696632862091064,
|
|
"num_tokens": 23659561.0,
|
|
"step": 10800
|
|
},
|
|
{
|
|
"entropy": 5.549629878997803,
|
|
"epoch": 1.0723501389440253,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004893590646123492,
|
|
"loss": 5.1827,
|
|
"mean_token_accuracy": 0.1700023129582405,
|
|
"num_tokens": 23673206.0,
|
|
"step": 10805
|
|
},
|
|
{
|
|
"entropy": 5.521047687530517,
|
|
"epoch": 1.072846367606193,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004893482946581022,
|
|
"loss": 5.231,
|
|
"mean_token_accuracy": 0.15918735712766646,
|
|
"num_tokens": 23683920.0,
|
|
"step": 10810
|
|
},
|
|
{
|
|
"entropy": 5.5158453464508055,
|
|
"epoch": 1.0733425962683605,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004893375193884793,
|
|
"loss": 5.1361,
|
|
"mean_token_accuracy": 0.1718864232301712,
|
|
"num_tokens": 23693990.0,
|
|
"step": 10815
|
|
},
|
|
{
|
|
"entropy": 5.59973783493042,
|
|
"epoch": 1.073838824930528,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004893267388037478,
|
|
"loss": 5.2571,
|
|
"mean_token_accuracy": 0.15837550908327103,
|
|
"num_tokens": 23704870.0,
|
|
"step": 10820
|
|
},
|
|
{
|
|
"entropy": 5.536206817626953,
|
|
"epoch": 1.0743350535926954,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.000489315952904175,
|
|
"loss": 5.2354,
|
|
"mean_token_accuracy": 0.16550104022026063,
|
|
"num_tokens": 23715159.0,
|
|
"step": 10825
|
|
},
|
|
{
|
|
"entropy": 5.517267560958862,
|
|
"epoch": 1.0748312822548631,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004893051616900283,
|
|
"loss": 5.1658,
|
|
"mean_token_accuracy": 0.16473808735609055,
|
|
"num_tokens": 23725252.0,
|
|
"step": 10830
|
|
},
|
|
{
|
|
"entropy": 5.476993989944458,
|
|
"epoch": 1.0753275109170306,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004892943651615756,
|
|
"loss": 5.1883,
|
|
"mean_token_accuracy": 0.16928842812776565,
|
|
"num_tokens": 23736472.0,
|
|
"step": 10835
|
|
},
|
|
{
|
|
"entropy": 5.572298336029053,
|
|
"epoch": 1.075823739579198,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004892835633190843,
|
|
"loss": 5.1026,
|
|
"mean_token_accuracy": 0.1639563947916031,
|
|
"num_tokens": 23747565.0,
|
|
"step": 10840
|
|
},
|
|
{
|
|
"entropy": 5.533527135848999,
|
|
"epoch": 1.0763199682413656,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004892727561628223,
|
|
"loss": 5.19,
|
|
"mean_token_accuracy": 0.16483999490737916,
|
|
"num_tokens": 23758201.0,
|
|
"step": 10845
|
|
},
|
|
{
|
|
"entropy": 5.554649829864502,
|
|
"epoch": 1.0768161969035333,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004892619436930577,
|
|
"loss": 5.2442,
|
|
"mean_token_accuracy": 0.16440054923295974,
|
|
"num_tokens": 23769087.0,
|
|
"step": 10850
|
|
},
|
|
{
|
|
"entropy": 5.540117359161377,
|
|
"epoch": 1.0773124255657007,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004892511259100585,
|
|
"loss": 5.2481,
|
|
"mean_token_accuracy": 0.16564065217971802,
|
|
"num_tokens": 23780598.0,
|
|
"step": 10855
|
|
},
|
|
{
|
|
"entropy": 5.536248350143433,
|
|
"epoch": 1.0778086542278682,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004892403028140932,
|
|
"loss": 5.1703,
|
|
"mean_token_accuracy": 0.15898965299129486,
|
|
"num_tokens": 23791449.0,
|
|
"step": 10860
|
|
},
|
|
{
|
|
"entropy": 5.516120576858521,
|
|
"epoch": 1.0783048828900357,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.00048922947440543,
|
|
"loss": 5.1474,
|
|
"mean_token_accuracy": 0.1687377378344536,
|
|
"num_tokens": 23803071.0,
|
|
"step": 10865
|
|
},
|
|
{
|
|
"entropy": 5.576876544952393,
|
|
"epoch": 1.0788011115522032,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004892186406843374,
|
|
"loss": 5.2267,
|
|
"mean_token_accuracy": 0.1598200261592865,
|
|
"num_tokens": 23813372.0,
|
|
"step": 10870
|
|
},
|
|
{
|
|
"entropy": 5.543317222595215,
|
|
"epoch": 1.0792973402143708,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004892078016510841,
|
|
"loss": 5.2064,
|
|
"mean_token_accuracy": 0.16511232703924178,
|
|
"num_tokens": 23824979.0,
|
|
"step": 10875
|
|
},
|
|
{
|
|
"entropy": 5.532471513748169,
|
|
"epoch": 1.0797935688765383,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.000489196957305939,
|
|
"loss": 5.1873,
|
|
"mean_token_accuracy": 0.16898007094860076,
|
|
"num_tokens": 23836335.0,
|
|
"step": 10880
|
|
},
|
|
{
|
|
"entropy": 5.516027307510376,
|
|
"epoch": 1.0802897975387058,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004891861076491709,
|
|
"loss": 5.1763,
|
|
"mean_token_accuracy": 0.16643766015768052,
|
|
"num_tokens": 23848147.0,
|
|
"step": 10885
|
|
},
|
|
{
|
|
"entropy": 5.485627222061157,
|
|
"epoch": 1.0807860262008733,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004891752526810488,
|
|
"loss": 5.1257,
|
|
"mean_token_accuracy": 0.17008547633886337,
|
|
"num_tokens": 23859502.0,
|
|
"step": 10890
|
|
},
|
|
{
|
|
"entropy": 5.558950901031494,
|
|
"epoch": 1.081282254863041,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.000489164392401842,
|
|
"loss": 5.2804,
|
|
"mean_token_accuracy": 0.16260500401258468,
|
|
"num_tokens": 23870433.0,
|
|
"step": 10895
|
|
},
|
|
{
|
|
"entropy": 5.533802032470703,
|
|
"epoch": 1.0817784835252084,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004891535268118196,
|
|
"loss": 5.1143,
|
|
"mean_token_accuracy": 0.17327011674642562,
|
|
"num_tokens": 23879581.0,
|
|
"step": 10900
|
|
},
|
|
{
|
|
"entropy": 5.481846332550049,
|
|
"epoch": 1.082274712187376,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004891426559112514,
|
|
"loss": 5.1806,
|
|
"mean_token_accuracy": 0.17126995623111724,
|
|
"num_tokens": 23890889.0,
|
|
"step": 10905
|
|
},
|
|
{
|
|
"entropy": 5.5440630435943605,
|
|
"epoch": 1.0827709408495434,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004891317797004066,
|
|
"loss": 5.1636,
|
|
"mean_token_accuracy": 0.1686042696237564,
|
|
"num_tokens": 23901577.0,
|
|
"step": 10910
|
|
},
|
|
{
|
|
"entropy": 5.522806215286255,
|
|
"epoch": 1.083267169511711,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004891208981795552,
|
|
"loss": 5.2405,
|
|
"mean_token_accuracy": 0.16895045787096025,
|
|
"num_tokens": 23912698.0,
|
|
"step": 10915
|
|
},
|
|
{
|
|
"entropy": 5.448703098297119,
|
|
"epoch": 1.0837633981738786,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004891100113489669,
|
|
"loss": 5.1132,
|
|
"mean_token_accuracy": 0.17265091836452484,
|
|
"num_tokens": 23923056.0,
|
|
"step": 10920
|
|
},
|
|
{
|
|
"entropy": 5.51653528213501,
|
|
"epoch": 1.084259626836046,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004890991192089116,
|
|
"loss": 5.2445,
|
|
"mean_token_accuracy": 0.16402831077575683,
|
|
"num_tokens": 23933998.0,
|
|
"step": 10925
|
|
},
|
|
{
|
|
"entropy": 5.573494100570679,
|
|
"epoch": 1.0847558554982135,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004890882217596595,
|
|
"loss": 5.1456,
|
|
"mean_token_accuracy": 0.17067973613739013,
|
|
"num_tokens": 23943980.0,
|
|
"step": 10930
|
|
},
|
|
{
|
|
"entropy": 5.516656303405762,
|
|
"epoch": 1.085252084160381,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004890773190014809,
|
|
"loss": 5.2213,
|
|
"mean_token_accuracy": 0.16332485824823378,
|
|
"num_tokens": 23955646.0,
|
|
"step": 10935
|
|
},
|
|
{
|
|
"entropy": 5.47779278755188,
|
|
"epoch": 1.0857483128225487,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.000489066410934646,
|
|
"loss": 5.1906,
|
|
"mean_token_accuracy": 0.17210307717323303,
|
|
"num_tokens": 23966381.0,
|
|
"step": 10940
|
|
},
|
|
{
|
|
"entropy": 5.61372389793396,
|
|
"epoch": 1.0862445414847162,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004890554975594255,
|
|
"loss": 5.251,
|
|
"mean_token_accuracy": 0.15600233227014543,
|
|
"num_tokens": 23978669.0,
|
|
"step": 10945
|
|
},
|
|
{
|
|
"entropy": 5.673389863967896,
|
|
"epoch": 1.0867407701468836,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004890445788760898,
|
|
"loss": 5.3326,
|
|
"mean_token_accuracy": 0.15747251212596894,
|
|
"num_tokens": 23989467.0,
|
|
"step": 10950
|
|
},
|
|
{
|
|
"entropy": 5.512957191467285,
|
|
"epoch": 1.0872369988090511,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004890336548849098,
|
|
"loss": 5.1343,
|
|
"mean_token_accuracy": 0.1714241921901703,
|
|
"num_tokens": 24000797.0,
|
|
"step": 10955
|
|
},
|
|
{
|
|
"entropy": 5.607582521438599,
|
|
"epoch": 1.0877332274712188,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004890227255861564,
|
|
"loss": 5.2898,
|
|
"mean_token_accuracy": 0.16513597071170807,
|
|
"num_tokens": 24013182.0,
|
|
"step": 10960
|
|
},
|
|
{
|
|
"entropy": 5.543015098571777,
|
|
"epoch": 1.0882294561333863,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004890117909801005,
|
|
"loss": 5.18,
|
|
"mean_token_accuracy": 0.17219192832708358,
|
|
"num_tokens": 24024005.0,
|
|
"step": 10965
|
|
},
|
|
{
|
|
"entropy": 5.516589260101318,
|
|
"epoch": 1.0887256847955538,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004890008510670134,
|
|
"loss": 5.1614,
|
|
"mean_token_accuracy": 0.1672101154923439,
|
|
"num_tokens": 24034524.0,
|
|
"step": 10970
|
|
},
|
|
{
|
|
"entropy": 5.5888190269470215,
|
|
"epoch": 1.0892219134577212,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004889899058471663,
|
|
"loss": 5.2204,
|
|
"mean_token_accuracy": 0.1629112109541893,
|
|
"num_tokens": 24045944.0,
|
|
"step": 10975
|
|
},
|
|
{
|
|
"entropy": 5.60032696723938,
|
|
"epoch": 1.089718142119889,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004889789553208306,
|
|
"loss": 5.2917,
|
|
"mean_token_accuracy": 0.16396206766366958,
|
|
"num_tokens": 24058612.0,
|
|
"step": 10980
|
|
},
|
|
{
|
|
"entropy": 5.54950361251831,
|
|
"epoch": 1.0902143707820564,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000488967999488278,
|
|
"loss": 5.1604,
|
|
"mean_token_accuracy": 0.16761168986558914,
|
|
"num_tokens": 24068912.0,
|
|
"step": 10985
|
|
},
|
|
{
|
|
"entropy": 5.464646720886231,
|
|
"epoch": 1.0907105994442239,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.00048895703834978,
|
|
"loss": 5.162,
|
|
"mean_token_accuracy": 0.16602682024240495,
|
|
"num_tokens": 24079879.0,
|
|
"step": 10990
|
|
},
|
|
{
|
|
"entropy": 5.52567458152771,
|
|
"epoch": 1.0912068281063914,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004889460719056085,
|
|
"loss": 5.1914,
|
|
"mean_token_accuracy": 0.16645094007253647,
|
|
"num_tokens": 24091268.0,
|
|
"step": 10995
|
|
},
|
|
{
|
|
"entropy": 5.5216775894165036,
|
|
"epoch": 1.091703056768559,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004889351001560354,
|
|
"loss": 5.2195,
|
|
"mean_token_accuracy": 0.166425521671772,
|
|
"num_tokens": 24101428.0,
|
|
"step": 11000
|
|
},
|
|
{
|
|
"entropy": 5.5186601161956785,
|
|
"epoch": 1.0921992854307265,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004889241231013329,
|
|
"loss": 5.1879,
|
|
"mean_token_accuracy": 0.16922087222337723,
|
|
"num_tokens": 24112920.0,
|
|
"step": 11005
|
|
},
|
|
{
|
|
"entropy": 5.474888849258423,
|
|
"epoch": 1.092695514092894,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.000488913140741773,
|
|
"loss": 5.1195,
|
|
"mean_token_accuracy": 0.1672017127275467,
|
|
"num_tokens": 24125731.0,
|
|
"step": 11010
|
|
},
|
|
{
|
|
"entropy": 5.485093688964843,
|
|
"epoch": 1.0931917427550615,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004889021530776282,
|
|
"loss": 5.1339,
|
|
"mean_token_accuracy": 0.16532045900821685,
|
|
"num_tokens": 24136606.0,
|
|
"step": 11015
|
|
},
|
|
{
|
|
"entropy": 5.549827671051025,
|
|
"epoch": 1.093687971417229,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004888911601091709,
|
|
"loss": 5.1493,
|
|
"mean_token_accuracy": 0.16973443180322648,
|
|
"num_tokens": 24146783.0,
|
|
"step": 11020
|
|
},
|
|
{
|
|
"entropy": 5.5369971752166744,
|
|
"epoch": 1.0941842000793967,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004888801618366737,
|
|
"loss": 5.2444,
|
|
"mean_token_accuracy": 0.16227903217077255,
|
|
"num_tokens": 24157412.0,
|
|
"step": 11025
|
|
},
|
|
{
|
|
"entropy": 5.546850252151489,
|
|
"epoch": 1.0946804287415641,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004888691582604095,
|
|
"loss": 5.2332,
|
|
"mean_token_accuracy": 0.16568017452955247,
|
|
"num_tokens": 24168077.0,
|
|
"step": 11030
|
|
},
|
|
{
|
|
"entropy": 5.568090295791626,
|
|
"epoch": 1.0951766574037316,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000488858149380651,
|
|
"loss": 5.2719,
|
|
"mean_token_accuracy": 0.16354267597198485,
|
|
"num_tokens": 24178913.0,
|
|
"step": 11035
|
|
},
|
|
{
|
|
"entropy": 5.637010669708252,
|
|
"epoch": 1.095672886065899,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.000488847135197671,
|
|
"loss": 5.3148,
|
|
"mean_token_accuracy": 0.15793400704860688,
|
|
"num_tokens": 24190356.0,
|
|
"step": 11040
|
|
},
|
|
{
|
|
"entropy": 5.6193829536437985,
|
|
"epoch": 1.0961691147280668,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.000488836115711743,
|
|
"loss": 5.2933,
|
|
"mean_token_accuracy": 0.15517248809337617,
|
|
"num_tokens": 24199772.0,
|
|
"step": 11045
|
|
},
|
|
{
|
|
"entropy": 5.565176010131836,
|
|
"epoch": 1.0966653433902342,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004888250909231401,
|
|
"loss": 5.1992,
|
|
"mean_token_accuracy": 0.16370121985673905,
|
|
"num_tokens": 24211807.0,
|
|
"step": 11050
|
|
},
|
|
{
|
|
"entropy": 5.500342893600464,
|
|
"epoch": 1.0971615720524017,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004888140608321357,
|
|
"loss": 5.1746,
|
|
"mean_token_accuracy": 0.170803065598011,
|
|
"num_tokens": 24223156.0,
|
|
"step": 11055
|
|
},
|
|
{
|
|
"entropy": 5.607478904724121,
|
|
"epoch": 1.0976578007145692,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004888030254390033,
|
|
"loss": 5.2322,
|
|
"mean_token_accuracy": 0.16016623750329018,
|
|
"num_tokens": 24234352.0,
|
|
"step": 11060
|
|
},
|
|
{
|
|
"entropy": 5.528764867782593,
|
|
"epoch": 1.098154029376737,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004887919847440166,
|
|
"loss": 5.1604,
|
|
"mean_token_accuracy": 0.17382446974515914,
|
|
"num_tokens": 24244137.0,
|
|
"step": 11065
|
|
},
|
|
{
|
|
"entropy": 5.478833484649658,
|
|
"epoch": 1.0986502580389044,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004887809387474494,
|
|
"loss": 5.1528,
|
|
"mean_token_accuracy": 0.16616191267967223,
|
|
"num_tokens": 24253250.0,
|
|
"step": 11070
|
|
},
|
|
{
|
|
"entropy": 5.570534372329712,
|
|
"epoch": 1.0991464867010718,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004887698874495755,
|
|
"loss": 5.2731,
|
|
"mean_token_accuracy": 0.16532145887613298,
|
|
"num_tokens": 24264551.0,
|
|
"step": 11075
|
|
},
|
|
{
|
|
"entropy": 5.548721599578857,
|
|
"epoch": 1.0996427153632393,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.000488758830850669,
|
|
"loss": 5.094,
|
|
"mean_token_accuracy": 0.174309666454792,
|
|
"num_tokens": 24275522.0,
|
|
"step": 11080
|
|
},
|
|
{
|
|
"entropy": 5.4962043285369875,
|
|
"epoch": 1.100138944025407,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004887477689510042,
|
|
"loss": 5.2571,
|
|
"mean_token_accuracy": 0.16220258325338363,
|
|
"num_tokens": 24286333.0,
|
|
"step": 11085
|
|
},
|
|
{
|
|
"entropy": 5.492782783508301,
|
|
"epoch": 1.1006351726875745,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004887367017508553,
|
|
"loss": 5.2564,
|
|
"mean_token_accuracy": 0.16658498495817184,
|
|
"num_tokens": 24297627.0,
|
|
"step": 11090
|
|
},
|
|
{
|
|
"entropy": 5.507976388931274,
|
|
"epoch": 1.101131401349742,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004887256292504967,
|
|
"loss": 5.2001,
|
|
"mean_token_accuracy": 0.1654631868004799,
|
|
"num_tokens": 24308246.0,
|
|
"step": 11095
|
|
},
|
|
{
|
|
"entropy": 5.56145453453064,
|
|
"epoch": 1.1016276300119094,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000488714551450203,
|
|
"loss": 5.2535,
|
|
"mean_token_accuracy": 0.15819311887025833,
|
|
"num_tokens": 24317718.0,
|
|
"step": 11100
|
|
},
|
|
{
|
|
"entropy": 5.531434106826782,
|
|
"epoch": 1.102123858674077,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.000488703468350249,
|
|
"loss": 5.1786,
|
|
"mean_token_accuracy": 0.16667785942554475,
|
|
"num_tokens": 24329242.0,
|
|
"step": 11105
|
|
},
|
|
{
|
|
"entropy": 5.640681743621826,
|
|
"epoch": 1.1026200873362446,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004886923799509095,
|
|
"loss": 5.3281,
|
|
"mean_token_accuracy": 0.15917756482958795,
|
|
"num_tokens": 24340146.0,
|
|
"step": 11110
|
|
},
|
|
{
|
|
"entropy": 5.588403940200806,
|
|
"epoch": 1.103116315998412,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004886812862524595,
|
|
"loss": 5.2353,
|
|
"mean_token_accuracy": 0.16205300241708756,
|
|
"num_tokens": 24349370.0,
|
|
"step": 11115
|
|
},
|
|
{
|
|
"entropy": 5.609292650222779,
|
|
"epoch": 1.1036125446605796,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004886701872551739,
|
|
"loss": 5.1904,
|
|
"mean_token_accuracy": 0.16353601068258286,
|
|
"num_tokens": 24359770.0,
|
|
"step": 11120
|
|
},
|
|
{
|
|
"entropy": 5.524088191986084,
|
|
"epoch": 1.104108773322747,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004886590829593281,
|
|
"loss": 5.221,
|
|
"mean_token_accuracy": 0.16579868793487548,
|
|
"num_tokens": 24370974.0,
|
|
"step": 11125
|
|
},
|
|
{
|
|
"entropy": 5.527943181991577,
|
|
"epoch": 1.1046050019849147,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004886479733651974,
|
|
"loss": 5.2428,
|
|
"mean_token_accuracy": 0.16564814150333404,
|
|
"num_tokens": 24381771.0,
|
|
"step": 11130
|
|
},
|
|
{
|
|
"entropy": 5.503493356704712,
|
|
"epoch": 1.1051012306470822,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004886368584730575,
|
|
"loss": 5.1979,
|
|
"mean_token_accuracy": 0.1624273732304573,
|
|
"num_tokens": 24393067.0,
|
|
"step": 11135
|
|
},
|
|
{
|
|
"entropy": 5.547466897964478,
|
|
"epoch": 1.1055974593092497,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004886257382831837,
|
|
"loss": 5.2638,
|
|
"mean_token_accuracy": 0.15839179530739783,
|
|
"num_tokens": 24402866.0,
|
|
"step": 11140
|
|
},
|
|
{
|
|
"entropy": 5.600502014160156,
|
|
"epoch": 1.1060936879714172,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.000488614612795852,
|
|
"loss": 5.2083,
|
|
"mean_token_accuracy": 0.1660041555762291,
|
|
"num_tokens": 24412956.0,
|
|
"step": 11145
|
|
},
|
|
{
|
|
"entropy": 5.5997397899627686,
|
|
"epoch": 1.1065899166335849,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004886034820113382,
|
|
"loss": 5.2651,
|
|
"mean_token_accuracy": 0.16328827440738677,
|
|
"num_tokens": 24424650.0,
|
|
"step": 11150
|
|
},
|
|
{
|
|
"entropy": 5.566668844223022,
|
|
"epoch": 1.1070861452957523,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004885923459299182,
|
|
"loss": 5.2725,
|
|
"mean_token_accuracy": 0.1630299359560013,
|
|
"num_tokens": 24436541.0,
|
|
"step": 11155
|
|
},
|
|
{
|
|
"entropy": 5.565120887756348,
|
|
"epoch": 1.1075823739579198,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004885812045518685,
|
|
"loss": 5.2507,
|
|
"mean_token_accuracy": 0.15863975435495375,
|
|
"num_tokens": 24447588.0,
|
|
"step": 11160
|
|
},
|
|
{
|
|
"entropy": 5.581294250488281,
|
|
"epoch": 1.1080786026200873,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.000488570057877465,
|
|
"loss": 5.1758,
|
|
"mean_token_accuracy": 0.16948388814926146,
|
|
"num_tokens": 24458854.0,
|
|
"step": 11165
|
|
},
|
|
{
|
|
"entropy": 5.57621202468872,
|
|
"epoch": 1.108574831282255,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004885589059069842,
|
|
"loss": 5.25,
|
|
"mean_token_accuracy": 0.1678898736834526,
|
|
"num_tokens": 24469427.0,
|
|
"step": 11170
|
|
},
|
|
{
|
|
"entropy": 5.500083971023559,
|
|
"epoch": 1.1090710599444225,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004885477486407028,
|
|
"loss": 5.2404,
|
|
"mean_token_accuracy": 0.15860867500305176,
|
|
"num_tokens": 24479352.0,
|
|
"step": 11175
|
|
},
|
|
{
|
|
"entropy": 5.61491756439209,
|
|
"epoch": 1.10956728860659,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004885365860788974,
|
|
"loss": 5.2464,
|
|
"mean_token_accuracy": 0.1635689303278923,
|
|
"num_tokens": 24489580.0,
|
|
"step": 11180
|
|
},
|
|
{
|
|
"entropy": 5.545247268676758,
|
|
"epoch": 1.1100635172687574,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004885254182218448,
|
|
"loss": 5.1802,
|
|
"mean_token_accuracy": 0.16670125126838684,
|
|
"num_tokens": 24501141.0,
|
|
"step": 11185
|
|
},
|
|
{
|
|
"entropy": 5.49181900024414,
|
|
"epoch": 1.1105597459309249,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004885142450698219,
|
|
"loss": 5.1794,
|
|
"mean_token_accuracy": 0.1701214224100113,
|
|
"num_tokens": 24512079.0,
|
|
"step": 11190
|
|
},
|
|
{
|
|
"entropy": 5.589020252227783,
|
|
"epoch": 1.1110559745930926,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004885030666231057,
|
|
"loss": 5.2397,
|
|
"mean_token_accuracy": 0.16306669265031815,
|
|
"num_tokens": 24521839.0,
|
|
"step": 11195
|
|
},
|
|
{
|
|
"entropy": 5.60635404586792,
|
|
"epoch": 1.11155220325526,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004884918828819738,
|
|
"loss": 5.2757,
|
|
"mean_token_accuracy": 0.16229153722524642,
|
|
"num_tokens": 24532704.0,
|
|
"step": 11200
|
|
},
|
|
{
|
|
"entropy": 5.569793033599853,
|
|
"epoch": 1.1120484319174275,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.000488480693846703,
|
|
"loss": 5.1815,
|
|
"mean_token_accuracy": 0.17026060372591018,
|
|
"num_tokens": 24543790.0,
|
|
"step": 11205
|
|
},
|
|
{
|
|
"entropy": 5.524898624420166,
|
|
"epoch": 1.112544660579595,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004884694995175711,
|
|
"loss": 5.2289,
|
|
"mean_token_accuracy": 0.1626759022474289,
|
|
"num_tokens": 24554765.0,
|
|
"step": 11210
|
|
},
|
|
{
|
|
"entropy": 5.662857723236084,
|
|
"epoch": 1.1130408892417627,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004884582998948555,
|
|
"loss": 5.3157,
|
|
"mean_token_accuracy": 0.15305445492267608,
|
|
"num_tokens": 24565888.0,
|
|
"step": 11215
|
|
},
|
|
{
|
|
"entropy": 5.523702001571655,
|
|
"epoch": 1.1135371179039302,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004884470949788342,
|
|
"loss": 5.1761,
|
|
"mean_token_accuracy": 0.16873531937599182,
|
|
"num_tokens": 24575482.0,
|
|
"step": 11220
|
|
},
|
|
{
|
|
"entropy": 5.596697044372559,
|
|
"epoch": 1.1140333465660976,
|
|
"grad_norm": 0.79296875,
|
|
"learning_rate": 0.0004884358847697847,
|
|
"loss": 5.2971,
|
|
"mean_token_accuracy": 0.1532044753432274,
|
|
"num_tokens": 24588249.0,
|
|
"step": 11225
|
|
},
|
|
{
|
|
"entropy": 5.625243711471557,
|
|
"epoch": 1.1145295752282651,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004884246692679852,
|
|
"loss": 5.2455,
|
|
"mean_token_accuracy": 0.167199943959713,
|
|
"num_tokens": 24599546.0,
|
|
"step": 11230
|
|
},
|
|
{
|
|
"entropy": 5.556321811676026,
|
|
"epoch": 1.1150258038904326,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004884134484737139,
|
|
"loss": 5.1773,
|
|
"mean_token_accuracy": 0.1655934751033783,
|
|
"num_tokens": 24611777.0,
|
|
"step": 11235
|
|
},
|
|
{
|
|
"entropy": 5.507972145080567,
|
|
"epoch": 1.1155220325526003,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004884022223872489,
|
|
"loss": 5.1588,
|
|
"mean_token_accuracy": 0.17026867121458053,
|
|
"num_tokens": 24623675.0,
|
|
"step": 11240
|
|
},
|
|
{
|
|
"entropy": 5.5565314292907715,
|
|
"epoch": 1.1160182612147678,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004883909910088686,
|
|
"loss": 5.1799,
|
|
"mean_token_accuracy": 0.16695850640535354,
|
|
"num_tokens": 24633929.0,
|
|
"step": 11245
|
|
},
|
|
{
|
|
"entropy": 5.533818960189819,
|
|
"epoch": 1.1165144898769352,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004883797543388515,
|
|
"loss": 5.1524,
|
|
"mean_token_accuracy": 0.16628415733575821,
|
|
"num_tokens": 24642800.0,
|
|
"step": 11250
|
|
},
|
|
{
|
|
"entropy": 5.5059174537658695,
|
|
"epoch": 1.1170107185391027,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004883685123774764,
|
|
"loss": 5.1531,
|
|
"mean_token_accuracy": 0.17160961478948594,
|
|
"num_tokens": 24653780.0,
|
|
"step": 11255
|
|
},
|
|
{
|
|
"entropy": 5.516745233535767,
|
|
"epoch": 1.1175069472012704,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004883572651250218,
|
|
"loss": 5.1827,
|
|
"mean_token_accuracy": 0.17066242396831513,
|
|
"num_tokens": 24663912.0,
|
|
"step": 11260
|
|
},
|
|
{
|
|
"entropy": 5.574978923797607,
|
|
"epoch": 1.118003175863438,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.0004883460125817669,
|
|
"loss": 5.2731,
|
|
"mean_token_accuracy": 0.16199380457401275,
|
|
"num_tokens": 24675222.0,
|
|
"step": 11265
|
|
},
|
|
{
|
|
"entropy": 5.577271175384522,
|
|
"epoch": 1.1184994045256054,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004883347547479905,
|
|
"loss": 5.276,
|
|
"mean_token_accuracy": 0.16459541767835617,
|
|
"num_tokens": 24686697.0,
|
|
"step": 11270
|
|
},
|
|
{
|
|
"entropy": 5.624046897888183,
|
|
"epoch": 1.1189956331877728,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.000488323491623972,
|
|
"loss": 5.2002,
|
|
"mean_token_accuracy": 0.1671757936477661,
|
|
"num_tokens": 24697067.0,
|
|
"step": 11275
|
|
},
|
|
{
|
|
"entropy": 5.577747583389282,
|
|
"epoch": 1.1194918618499405,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004883122232099905,
|
|
"loss": 5.2006,
|
|
"mean_token_accuracy": 0.16444696187973024,
|
|
"num_tokens": 24707989.0,
|
|
"step": 11280
|
|
},
|
|
{
|
|
"entropy": 5.4619499206542965,
|
|
"epoch": 1.119988090512108,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004883009495063256,
|
|
"loss": 5.1408,
|
|
"mean_token_accuracy": 0.17277270853519439,
|
|
"num_tokens": 24718826.0,
|
|
"step": 11285
|
|
},
|
|
{
|
|
"entropy": 5.597539281845092,
|
|
"epoch": 1.1204843191742755,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004882896705132566,
|
|
"loss": 5.2532,
|
|
"mean_token_accuracy": 0.1603585734963417,
|
|
"num_tokens": 24729913.0,
|
|
"step": 11290
|
|
},
|
|
{
|
|
"entropy": 5.481209945678711,
|
|
"epoch": 1.120980547836443,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.00048827838623106355,
|
|
"loss": 5.1073,
|
|
"mean_token_accuracy": 0.16847607791423796,
|
|
"num_tokens": 24741621.0,
|
|
"step": 11295
|
|
},
|
|
{
|
|
"entropy": 5.5243284702301025,
|
|
"epoch": 1.1214767764986107,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.000488267096660026,
|
|
"loss": 5.1724,
|
|
"mean_token_accuracy": 0.17016072571277618,
|
|
"num_tokens": 24753427.0,
|
|
"step": 11300
|
|
},
|
|
{
|
|
"entropy": 5.558738565444946,
|
|
"epoch": 1.1219730051607781,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00048825580180042406,
|
|
"loss": 5.2042,
|
|
"mean_token_accuracy": 0.16348448991775513,
|
|
"num_tokens": 24763580.0,
|
|
"step": 11305
|
|
},
|
|
{
|
|
"entropy": 5.497127676010132,
|
|
"epoch": 1.1224692338229456,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004882445016525377,
|
|
"loss": 5.2041,
|
|
"mean_token_accuracy": 0.1653308317065239,
|
|
"num_tokens": 24773955.0,
|
|
"step": 11310
|
|
},
|
|
{
|
|
"entropy": 5.513176345825196,
|
|
"epoch": 1.122965462485113,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.00048823319621664723,
|
|
"loss": 5.1112,
|
|
"mean_token_accuracy": 0.17569485306739807,
|
|
"num_tokens": 24784039.0,
|
|
"step": 11315
|
|
},
|
|
{
|
|
"entropy": 5.587033414840699,
|
|
"epoch": 1.1234616911472806,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.00048822188549303296,
|
|
"loss": 5.2307,
|
|
"mean_token_accuracy": 0.16120216846466065,
|
|
"num_tokens": 24794630.0,
|
|
"step": 11320
|
|
},
|
|
{
|
|
"entropy": 5.545216703414917,
|
|
"epoch": 1.1239579198094483,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004882105694819754,
|
|
"loss": 5.2779,
|
|
"mean_token_accuracy": 0.15836898982524872,
|
|
"num_tokens": 24805625.0,
|
|
"step": 11325
|
|
},
|
|
{
|
|
"entropy": 5.559854125976562,
|
|
"epoch": 1.1244541484716157,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004881992481837551,
|
|
"loss": 5.196,
|
|
"mean_token_accuracy": 0.1735105663537979,
|
|
"num_tokens": 24817356.0,
|
|
"step": 11330
|
|
},
|
|
{
|
|
"entropy": 5.561701059341431,
|
|
"epoch": 1.1249503771337832,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004881879215986529,
|
|
"loss": 5.1631,
|
|
"mean_token_accuracy": 0.16098037213087082,
|
|
"num_tokens": 24828349.0,
|
|
"step": 11335
|
|
},
|
|
{
|
|
"entropy": 5.554211711883545,
|
|
"epoch": 1.1254466057959507,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.00048817658972694967,
|
|
"loss": 5.2108,
|
|
"mean_token_accuracy": 0.16408946812152864,
|
|
"num_tokens": 24840138.0,
|
|
"step": 11340
|
|
},
|
|
{
|
|
"entropy": 5.532898616790772,
|
|
"epoch": 1.1259428344581184,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004881652525689263,
|
|
"loss": 5.1995,
|
|
"mean_token_accuracy": 0.16382676213979722,
|
|
"num_tokens": 24851570.0,
|
|
"step": 11345
|
|
},
|
|
{
|
|
"entropy": 5.441495895385742,
|
|
"epoch": 1.1264390631202859,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.000488153910124864,
|
|
"loss": 5.1163,
|
|
"mean_token_accuracy": 0.17039304226636887,
|
|
"num_tokens": 24861396.0,
|
|
"step": 11350
|
|
},
|
|
{
|
|
"entropy": 5.562624883651734,
|
|
"epoch": 1.1269352917824533,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.000488142562395044,
|
|
"loss": 5.2213,
|
|
"mean_token_accuracy": 0.1602090373635292,
|
|
"num_tokens": 24873519.0,
|
|
"step": 11355
|
|
},
|
|
{
|
|
"entropy": 5.5660299301147464,
|
|
"epoch": 1.1274315204446208,
|
|
"grad_norm": 0.76953125,
|
|
"learning_rate": 0.00048813120937974774,
|
|
"loss": 5.2435,
|
|
"mean_token_accuracy": 0.1628718212246895,
|
|
"num_tokens": 24886856.0,
|
|
"step": 11360
|
|
},
|
|
{
|
|
"entropy": 5.513981866836548,
|
|
"epoch": 1.1279277491067885,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.00048811985107925684,
|
|
"loss": 5.1994,
|
|
"mean_token_accuracy": 0.16299989074468613,
|
|
"num_tokens": 24897292.0,
|
|
"step": 11365
|
|
},
|
|
{
|
|
"entropy": 5.554580497741699,
|
|
"epoch": 1.128423977768956,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00048810848749385286,
|
|
"loss": 5.1944,
|
|
"mean_token_accuracy": 0.1647961512207985,
|
|
"num_tokens": 24907757.0,
|
|
"step": 11370
|
|
},
|
|
{
|
|
"entropy": 5.463225793838501,
|
|
"epoch": 1.1289202064311235,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.00048809711862381753,
|
|
"loss": 5.181,
|
|
"mean_token_accuracy": 0.17165081948041916,
|
|
"num_tokens": 24918071.0,
|
|
"step": 11375
|
|
},
|
|
{
|
|
"entropy": 5.507682466506958,
|
|
"epoch": 1.129416435093291,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.00048808574446943274,
|
|
"loss": 5.1673,
|
|
"mean_token_accuracy": 0.1700497329235077,
|
|
"num_tokens": 24927967.0,
|
|
"step": 11380
|
|
},
|
|
{
|
|
"entropy": 5.5919568061828615,
|
|
"epoch": 1.1299126637554586,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004880743650309808,
|
|
"loss": 5.2355,
|
|
"mean_token_accuracy": 0.167525714635849,
|
|
"num_tokens": 24939170.0,
|
|
"step": 11385
|
|
},
|
|
{
|
|
"entropy": 5.545287179946899,
|
|
"epoch": 1.130408892417626,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.00048806298030874373,
|
|
"loss": 5.2201,
|
|
"mean_token_accuracy": 0.16491880267858505,
|
|
"num_tokens": 24950937.0,
|
|
"step": 11390
|
|
},
|
|
{
|
|
"entropy": 5.542399215698242,
|
|
"epoch": 1.1309051210797936,
|
|
"grad_norm": 0.78515625,
|
|
"learning_rate": 0.00048805159030300383,
|
|
"loss": 5.2144,
|
|
"mean_token_accuracy": 0.16268894523382188,
|
|
"num_tokens": 24962813.0,
|
|
"step": 11395
|
|
},
|
|
{
|
|
"entropy": 5.517576360702515,
|
|
"epoch": 1.131401349741961,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.00048804019501404357,
|
|
"loss": 5.1137,
|
|
"mean_token_accuracy": 0.17117615193128585,
|
|
"num_tokens": 24974192.0,
|
|
"step": 11400
|
|
},
|
|
{
|
|
"entropy": 5.481450986862183,
|
|
"epoch": 1.1318975784041285,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.00048802879444214553,
|
|
"loss": 5.105,
|
|
"mean_token_accuracy": 0.17104082107543944,
|
|
"num_tokens": 24985353.0,
|
|
"step": 11405
|
|
},
|
|
{
|
|
"entropy": 5.536077547073364,
|
|
"epoch": 1.1323938070662962,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.00048801738858759243,
|
|
"loss": 5.2083,
|
|
"mean_token_accuracy": 0.17019502222537994,
|
|
"num_tokens": 24997259.0,
|
|
"step": 11410
|
|
},
|
|
{
|
|
"entropy": 5.536036491394043,
|
|
"epoch": 1.1328900357284637,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004880059774506671,
|
|
"loss": 5.1911,
|
|
"mean_token_accuracy": 0.16489135324954987,
|
|
"num_tokens": 25008222.0,
|
|
"step": 11415
|
|
},
|
|
{
|
|
"entropy": 5.502761554718018,
|
|
"epoch": 1.1333862643906312,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004879945610316525,
|
|
"loss": 5.2437,
|
|
"mean_token_accuracy": 0.159339103102684,
|
|
"num_tokens": 25020267.0,
|
|
"step": 11420
|
|
},
|
|
{
|
|
"entropy": 5.5328371047973635,
|
|
"epoch": 1.1338824930527986,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.00048798313933083175,
|
|
"loss": 5.2061,
|
|
"mean_token_accuracy": 0.16459888070821763,
|
|
"num_tokens": 25031212.0,
|
|
"step": 11425
|
|
},
|
|
{
|
|
"entropy": 5.535136032104492,
|
|
"epoch": 1.1343787217149663,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004879717123484882,
|
|
"loss": 5.1783,
|
|
"mean_token_accuracy": 0.15966017097234725,
|
|
"num_tokens": 25042204.0,
|
|
"step": 11430
|
|
},
|
|
{
|
|
"entropy": 5.563981008529663,
|
|
"epoch": 1.1348749503771338,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.000487960280084905,
|
|
"loss": 5.1957,
|
|
"mean_token_accuracy": 0.16630644202232361,
|
|
"num_tokens": 25052010.0,
|
|
"step": 11435
|
|
},
|
|
{
|
|
"entropy": 5.596749496459961,
|
|
"epoch": 1.1353711790393013,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004879488425403657,
|
|
"loss": 5.2621,
|
|
"mean_token_accuracy": 0.16078420653939246,
|
|
"num_tokens": 25062209.0,
|
|
"step": 11440
|
|
},
|
|
{
|
|
"entropy": 5.523932552337646,
|
|
"epoch": 1.1358674077014688,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.00048793739971515407,
|
|
"loss": 5.2328,
|
|
"mean_token_accuracy": 0.1643170580267906,
|
|
"num_tokens": 25072758.0,
|
|
"step": 11445
|
|
},
|
|
{
|
|
"entropy": 5.562268018722534,
|
|
"epoch": 1.1363636363636362,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.00048792595160955374,
|
|
"loss": 5.2846,
|
|
"mean_token_accuracy": 0.16242774128913878,
|
|
"num_tokens": 25084318.0,
|
|
"step": 11450
|
|
},
|
|
{
|
|
"entropy": 5.569331455230713,
|
|
"epoch": 1.136859865025804,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.00048791449822384856,
|
|
"loss": 5.1761,
|
|
"mean_token_accuracy": 0.17167195975780486,
|
|
"num_tokens": 25095715.0,
|
|
"step": 11455
|
|
},
|
|
{
|
|
"entropy": 5.564904832839966,
|
|
"epoch": 1.1373560936879714,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004879030395583226,
|
|
"loss": 5.2061,
|
|
"mean_token_accuracy": 0.16821445673704147,
|
|
"num_tokens": 25106163.0,
|
|
"step": 11460
|
|
},
|
|
{
|
|
"entropy": 5.5954526424407955,
|
|
"epoch": 1.137852322350139,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0004878915756132601,
|
|
"loss": 5.2656,
|
|
"mean_token_accuracy": 0.16299975514411927,
|
|
"num_tokens": 25118745.0,
|
|
"step": 11465
|
|
},
|
|
{
|
|
"entropy": 5.56226954460144,
|
|
"epoch": 1.1383485510123066,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.00048788010638894523,
|
|
"loss": 5.2574,
|
|
"mean_token_accuracy": 0.1571410268545151,
|
|
"num_tokens": 25130066.0,
|
|
"step": 11470
|
|
},
|
|
{
|
|
"entropy": 5.53004937171936,
|
|
"epoch": 1.138844779674474,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004878686318856624,
|
|
"loss": 5.103,
|
|
"mean_token_accuracy": 0.16741354912519454,
|
|
"num_tokens": 25139895.0,
|
|
"step": 11475
|
|
},
|
|
{
|
|
"entropy": 5.627090311050415,
|
|
"epoch": 1.1393410083366415,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.00048785715210369635,
|
|
"loss": 5.3192,
|
|
"mean_token_accuracy": 0.15703511238098145,
|
|
"num_tokens": 25150644.0,
|
|
"step": 11480
|
|
},
|
|
{
|
|
"entropy": 5.579454851150513,
|
|
"epoch": 1.139837236998809,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004878456670433314,
|
|
"loss": 5.2362,
|
|
"mean_token_accuracy": 0.1619833841919899,
|
|
"num_tokens": 25163038.0,
|
|
"step": 11485
|
|
},
|
|
{
|
|
"entropy": 5.523625373840332,
|
|
"epoch": 1.1403334656609765,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004878341767048527,
|
|
"loss": 5.153,
|
|
"mean_token_accuracy": 0.16821326911449433,
|
|
"num_tokens": 25174154.0,
|
|
"step": 11490
|
|
},
|
|
{
|
|
"entropy": 5.583241987228393,
|
|
"epoch": 1.1408296943231442,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.00048782268108854494,
|
|
"loss": 5.2622,
|
|
"mean_token_accuracy": 0.15985383093357086,
|
|
"num_tokens": 25185369.0,
|
|
"step": 11495
|
|
},
|
|
{
|
|
"entropy": 5.542490816116333,
|
|
"epoch": 1.1413259229853117,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004878111801946933,
|
|
"loss": 5.2562,
|
|
"mean_token_accuracy": 0.16156903952360152,
|
|
"num_tokens": 25197875.0,
|
|
"step": 11500
|
|
},
|
|
{
|
|
"entropy": 5.468142938613892,
|
|
"epoch": 1.1418221516474791,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00048779967402358296,
|
|
"loss": 5.1433,
|
|
"mean_token_accuracy": 0.17784634679555894,
|
|
"num_tokens": 25208362.0,
|
|
"step": 11505
|
|
},
|
|
{
|
|
"entropy": 5.606678915023804,
|
|
"epoch": 1.1423183803096466,
|
|
"grad_norm": 0.7578125,
|
|
"learning_rate": 0.0004877881625754993,
|
|
"loss": 5.3466,
|
|
"mean_token_accuracy": 0.1564700610935688,
|
|
"num_tokens": 25220441.0,
|
|
"step": 11510
|
|
},
|
|
{
|
|
"entropy": 5.545219135284424,
|
|
"epoch": 1.1428146089718143,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.00048777664585072765,
|
|
"loss": 5.1138,
|
|
"mean_token_accuracy": 0.165564888715744,
|
|
"num_tokens": 25231134.0,
|
|
"step": 11515
|
|
},
|
|
{
|
|
"entropy": 5.636066436767578,
|
|
"epoch": 1.1433108376339818,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004877651238495537,
|
|
"loss": 5.3777,
|
|
"mean_token_accuracy": 0.1574774593114853,
|
|
"num_tokens": 25242327.0,
|
|
"step": 11520
|
|
},
|
|
{
|
|
"entropy": 5.56852765083313,
|
|
"epoch": 1.1438070662961493,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00048775359657226316,
|
|
"loss": 5.1979,
|
|
"mean_token_accuracy": 0.16594454795122146,
|
|
"num_tokens": 25253571.0,
|
|
"step": 11525
|
|
},
|
|
{
|
|
"entropy": 5.497541189193726,
|
|
"epoch": 1.1443032949583167,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004877420640191418,
|
|
"loss": 5.1438,
|
|
"mean_token_accuracy": 0.1686657264828682,
|
|
"num_tokens": 25264573.0,
|
|
"step": 11530
|
|
},
|
|
{
|
|
"entropy": 5.549622297286987,
|
|
"epoch": 1.1447995236204842,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004877305261904758,
|
|
"loss": 5.235,
|
|
"mean_token_accuracy": 0.1609615996479988,
|
|
"num_tokens": 25275197.0,
|
|
"step": 11535
|
|
},
|
|
{
|
|
"entropy": 5.514175796508789,
|
|
"epoch": 1.145295752282652,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00048771898308655107,
|
|
"loss": 5.1227,
|
|
"mean_token_accuracy": 0.17143765240907669,
|
|
"num_tokens": 25286564.0,
|
|
"step": 11540
|
|
},
|
|
{
|
|
"entropy": 5.566322278976441,
|
|
"epoch": 1.1457919809448194,
|
|
"grad_norm": 0.80078125,
|
|
"learning_rate": 0.0004877074347076539,
|
|
"loss": 5.164,
|
|
"mean_token_accuracy": 0.16721051335334777,
|
|
"num_tokens": 25297874.0,
|
|
"step": 11545
|
|
},
|
|
{
|
|
"entropy": 5.590831518173218,
|
|
"epoch": 1.1462882096069869,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00048769588105407075,
|
|
"loss": 5.2417,
|
|
"mean_token_accuracy": 0.1635787934064865,
|
|
"num_tokens": 25308047.0,
|
|
"step": 11550
|
|
},
|
|
{
|
|
"entropy": 5.626078748703003,
|
|
"epoch": 1.1467844382691545,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.00048768432212608807,
|
|
"loss": 5.279,
|
|
"mean_token_accuracy": 0.15482100397348403,
|
|
"num_tokens": 25318527.0,
|
|
"step": 11555
|
|
},
|
|
{
|
|
"entropy": 5.576137542724609,
|
|
"epoch": 1.147280666931322,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004876727579239925,
|
|
"loss": 5.1988,
|
|
"mean_token_accuracy": 0.17010349482297898,
|
|
"num_tokens": 25328242.0,
|
|
"step": 11560
|
|
},
|
|
{
|
|
"entropy": 5.528227472305298,
|
|
"epoch": 1.1477768955934895,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004876611884480708,
|
|
"loss": 5.1689,
|
|
"mean_token_accuracy": 0.16878188848495485,
|
|
"num_tokens": 25338214.0,
|
|
"step": 11565
|
|
},
|
|
{
|
|
"entropy": 5.5525308609008786,
|
|
"epoch": 1.148273124255657,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.00048764961369860977,
|
|
"loss": 5.226,
|
|
"mean_token_accuracy": 0.16078789979219438,
|
|
"num_tokens": 25349762.0,
|
|
"step": 11570
|
|
},
|
|
{
|
|
"entropy": 5.550897598266602,
|
|
"epoch": 1.1487693529178244,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00048763803367589663,
|
|
"loss": 5.2265,
|
|
"mean_token_accuracy": 0.16498002856969834,
|
|
"num_tokens": 25361241.0,
|
|
"step": 11575
|
|
},
|
|
{
|
|
"entropy": 5.57495379447937,
|
|
"epoch": 1.1492655815799921,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.00048762644838021843,
|
|
"loss": 5.2522,
|
|
"mean_token_accuracy": 0.16064665466547012,
|
|
"num_tokens": 25373846.0,
|
|
"step": 11580
|
|
},
|
|
{
|
|
"entropy": 5.532123661041259,
|
|
"epoch": 1.1497618102421596,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.00048761485781186243,
|
|
"loss": 5.1808,
|
|
"mean_token_accuracy": 0.1658075273036957,
|
|
"num_tokens": 25385331.0,
|
|
"step": 11585
|
|
},
|
|
{
|
|
"entropy": 5.523156261444091,
|
|
"epoch": 1.150258038904327,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004876032619711162,
|
|
"loss": 5.1933,
|
|
"mean_token_accuracy": 0.17255775928497313,
|
|
"num_tokens": 25395140.0,
|
|
"step": 11590
|
|
},
|
|
{
|
|
"entropy": 5.60550479888916,
|
|
"epoch": 1.1507542675664946,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.00048759166085826714,
|
|
"loss": 5.2353,
|
|
"mean_token_accuracy": 0.15751099735498428,
|
|
"num_tokens": 25405455.0,
|
|
"step": 11595
|
|
},
|
|
{
|
|
"entropy": 5.561492872238159,
|
|
"epoch": 1.1512504962286623,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.000487580054473603,
|
|
"loss": 5.2428,
|
|
"mean_token_accuracy": 0.1647414207458496,
|
|
"num_tokens": 25417000.0,
|
|
"step": 11600
|
|
},
|
|
{
|
|
"entropy": 5.473997592926025,
|
|
"epoch": 1.1517467248908297,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00048756844281741156,
|
|
"loss": 5.1643,
|
|
"mean_token_accuracy": 0.1671366423368454,
|
|
"num_tokens": 25427808.0,
|
|
"step": 11605
|
|
},
|
|
{
|
|
"entropy": 5.541671848297119,
|
|
"epoch": 1.1522429535529972,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.00048755682588998085,
|
|
"loss": 5.196,
|
|
"mean_token_accuracy": 0.15793447494506835,
|
|
"num_tokens": 25438302.0,
|
|
"step": 11610
|
|
},
|
|
{
|
|
"entropy": 5.457865190505982,
|
|
"epoch": 1.1527391822151647,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004875452036915987,
|
|
"loss": 5.0917,
|
|
"mean_token_accuracy": 0.16701629757881165,
|
|
"num_tokens": 25449335.0,
|
|
"step": 11615
|
|
},
|
|
{
|
|
"entropy": 5.621621704101562,
|
|
"epoch": 1.1532354108773322,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004875335762225536,
|
|
"loss": 5.2763,
|
|
"mean_token_accuracy": 0.15871182680130005,
|
|
"num_tokens": 25461173.0,
|
|
"step": 11620
|
|
},
|
|
{
|
|
"entropy": 5.59500823020935,
|
|
"epoch": 1.1537316395394999,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00048752194348313383,
|
|
"loss": 5.1749,
|
|
"mean_token_accuracy": 0.16683193892240525,
|
|
"num_tokens": 25472538.0,
|
|
"step": 11625
|
|
},
|
|
{
|
|
"entropy": 5.507734775543213,
|
|
"epoch": 1.1542278682016673,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004875103054736278,
|
|
"loss": 5.2141,
|
|
"mean_token_accuracy": 0.16634899973869324,
|
|
"num_tokens": 25483386.0,
|
|
"step": 11630
|
|
},
|
|
{
|
|
"entropy": 5.572064542770386,
|
|
"epoch": 1.1547240968638348,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004874986621943241,
|
|
"loss": 5.2256,
|
|
"mean_token_accuracy": 0.1629209354519844,
|
|
"num_tokens": 25495505.0,
|
|
"step": 11635
|
|
},
|
|
{
|
|
"entropy": 5.56484956741333,
|
|
"epoch": 1.1552203255260023,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.00048748701364551147,
|
|
"loss": 5.2173,
|
|
"mean_token_accuracy": 0.1683715894818306,
|
|
"num_tokens": 25506144.0,
|
|
"step": 11640
|
|
},
|
|
{
|
|
"entropy": 5.5736268043518065,
|
|
"epoch": 1.15571655418817,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004874753598274787,
|
|
"loss": 5.2145,
|
|
"mean_token_accuracy": 0.16028875559568406,
|
|
"num_tokens": 25516185.0,
|
|
"step": 11645
|
|
},
|
|
{
|
|
"entropy": 5.6265936374664305,
|
|
"epoch": 1.1562127828503375,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004874637007405149,
|
|
"loss": 5.2912,
|
|
"mean_token_accuracy": 0.16133199632167816,
|
|
"num_tokens": 25526657.0,
|
|
"step": 11650
|
|
},
|
|
{
|
|
"entropy": 5.510714387893676,
|
|
"epoch": 1.156709011512505,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.00048745203638490917,
|
|
"loss": 5.151,
|
|
"mean_token_accuracy": 0.17050716876983643,
|
|
"num_tokens": 25537101.0,
|
|
"step": 11655
|
|
},
|
|
{
|
|
"entropy": 5.5446388721466064,
|
|
"epoch": 1.1572052401746724,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00048744036676095067,
|
|
"loss": 5.2395,
|
|
"mean_token_accuracy": 0.1617955043911934,
|
|
"num_tokens": 25547672.0,
|
|
"step": 11660
|
|
},
|
|
{
|
|
"entropy": 5.631325149536133,
|
|
"epoch": 1.15770146883684,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004874286918689289,
|
|
"loss": 5.2818,
|
|
"mean_token_accuracy": 0.16751983612775803,
|
|
"num_tokens": 25558408.0,
|
|
"step": 11665
|
|
},
|
|
{
|
|
"entropy": 5.627182912826538,
|
|
"epoch": 1.1581976974990076,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00048741701170913326,
|
|
"loss": 5.1884,
|
|
"mean_token_accuracy": 0.16304911375045777,
|
|
"num_tokens": 25569823.0,
|
|
"step": 11670
|
|
},
|
|
{
|
|
"entropy": 5.518573474884033,
|
|
"epoch": 1.158693926161175,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.00048740532628185353,
|
|
"loss": 5.2043,
|
|
"mean_token_accuracy": 0.16901672780513763,
|
|
"num_tokens": 25579705.0,
|
|
"step": 11675
|
|
},
|
|
{
|
|
"entropy": 5.5250725746154785,
|
|
"epoch": 1.1591901548233425,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004873936355873793,
|
|
"loss": 5.2614,
|
|
"mean_token_accuracy": 0.1624846026301384,
|
|
"num_tokens": 25590573.0,
|
|
"step": 11680
|
|
},
|
|
{
|
|
"entropy": 5.531937789916992,
|
|
"epoch": 1.1596863834855102,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004873819396260007,
|
|
"loss": 5.182,
|
|
"mean_token_accuracy": 0.16720510870218278,
|
|
"num_tokens": 25601418.0,
|
|
"step": 11685
|
|
},
|
|
{
|
|
"entropy": 5.5733130931854244,
|
|
"epoch": 1.1601826121476777,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00048737023839800754,
|
|
"loss": 5.2549,
|
|
"mean_token_accuracy": 0.1668507844209671,
|
|
"num_tokens": 25612409.0,
|
|
"step": 11690
|
|
},
|
|
{
|
|
"entropy": 5.512886333465576,
|
|
"epoch": 1.1606788408098452,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004873585319036901,
|
|
"loss": 5.1582,
|
|
"mean_token_accuracy": 0.16629520952701568,
|
|
"num_tokens": 25623547.0,
|
|
"step": 11695
|
|
},
|
|
{
|
|
"entropy": 5.586042976379394,
|
|
"epoch": 1.1611750694720127,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004873468201433387,
|
|
"loss": 5.3246,
|
|
"mean_token_accuracy": 0.1602830931544304,
|
|
"num_tokens": 25636537.0,
|
|
"step": 11700
|
|
},
|
|
{
|
|
"entropy": 5.556938934326172,
|
|
"epoch": 1.1616712981341801,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004873351031172437,
|
|
"loss": 5.1818,
|
|
"mean_token_accuracy": 0.17011043876409532,
|
|
"num_tokens": 25646734.0,
|
|
"step": 11705
|
|
},
|
|
{
|
|
"entropy": 5.6243524074554445,
|
|
"epoch": 1.1621675267963478,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00048732338082569564,
|
|
"loss": 5.2705,
|
|
"mean_token_accuracy": 0.1712836816906929,
|
|
"num_tokens": 25658058.0,
|
|
"step": 11710
|
|
},
|
|
{
|
|
"entropy": 5.507769775390625,
|
|
"epoch": 1.1626637554585153,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004873116532689853,
|
|
"loss": 5.1042,
|
|
"mean_token_accuracy": 0.16782689243555068,
|
|
"num_tokens": 25669630.0,
|
|
"step": 11715
|
|
},
|
|
{
|
|
"entropy": 5.463340520858765,
|
|
"epoch": 1.1631599841206828,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004872999204474035,
|
|
"loss": 5.1264,
|
|
"mean_token_accuracy": 0.16765623539686203,
|
|
"num_tokens": 25681928.0,
|
|
"step": 11720
|
|
},
|
|
{
|
|
"entropy": 5.452698564529419,
|
|
"epoch": 1.1636562127828503,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000487288182361241,
|
|
"loss": 5.1365,
|
|
"mean_token_accuracy": 0.16379121989011763,
|
|
"num_tokens": 25690653.0,
|
|
"step": 11725
|
|
},
|
|
{
|
|
"entropy": 5.582673168182373,
|
|
"epoch": 1.164152441445018,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004872764390107891,
|
|
"loss": 5.2413,
|
|
"mean_token_accuracy": 0.15922019481658936,
|
|
"num_tokens": 25701201.0,
|
|
"step": 11730
|
|
},
|
|
{
|
|
"entropy": 5.500560283660889,
|
|
"epoch": 1.1646486701071854,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.00048726469039633895,
|
|
"loss": 5.1521,
|
|
"mean_token_accuracy": 0.1659471109509468,
|
|
"num_tokens": 25710927.0,
|
|
"step": 11735
|
|
},
|
|
{
|
|
"entropy": 5.54877290725708,
|
|
"epoch": 1.165144898769353,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.00048725293651818183,
|
|
"loss": 5.2084,
|
|
"mean_token_accuracy": 0.16513376086950302,
|
|
"num_tokens": 25722136.0,
|
|
"step": 11740
|
|
},
|
|
{
|
|
"entropy": 5.517477798461914,
|
|
"epoch": 1.1656411274315204,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004872411773766093,
|
|
"loss": 5.0852,
|
|
"mean_token_accuracy": 0.1738223686814308,
|
|
"num_tokens": 25733386.0,
|
|
"step": 11745
|
|
},
|
|
{
|
|
"entropy": 5.5081868171691895,
|
|
"epoch": 1.1661373560936878,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.00048722941297191284,
|
|
"loss": 5.1887,
|
|
"mean_token_accuracy": 0.16425832211971284,
|
|
"num_tokens": 25742801.0,
|
|
"step": 11750
|
|
},
|
|
{
|
|
"entropy": 5.607944631576538,
|
|
"epoch": 1.1666335847558555,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004872176433043843,
|
|
"loss": 5.2764,
|
|
"mean_token_accuracy": 0.1629337713122368,
|
|
"num_tokens": 25755594.0,
|
|
"step": 11755
|
|
},
|
|
{
|
|
"entropy": 5.5814227104187015,
|
|
"epoch": 1.167129813418023,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004872058683743155,
|
|
"loss": 5.2251,
|
|
"mean_token_accuracy": 0.16832107603549956,
|
|
"num_tokens": 25766271.0,
|
|
"step": 11760
|
|
},
|
|
{
|
|
"entropy": 5.5676782608032225,
|
|
"epoch": 1.1676260420801905,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00048719408818199836,
|
|
"loss": 5.2576,
|
|
"mean_token_accuracy": 0.1625947266817093,
|
|
"num_tokens": 25777338.0,
|
|
"step": 11765
|
|
},
|
|
{
|
|
"entropy": 5.538753366470337,
|
|
"epoch": 1.1681222707423582,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.00048718230272772517,
|
|
"loss": 5.1361,
|
|
"mean_token_accuracy": 0.16893320381641388,
|
|
"num_tokens": 25787968.0,
|
|
"step": 11770
|
|
},
|
|
{
|
|
"entropy": 5.568584632873535,
|
|
"epoch": 1.1686184994045257,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.00048717051201178804,
|
|
"loss": 5.2143,
|
|
"mean_token_accuracy": 0.16679543107748032,
|
|
"num_tokens": 25798274.0,
|
|
"step": 11775
|
|
},
|
|
{
|
|
"entropy": 5.491327142715454,
|
|
"epoch": 1.1691147280666931,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004871587160344794,
|
|
"loss": 5.1753,
|
|
"mean_token_accuracy": 0.15845755189657212,
|
|
"num_tokens": 25809140.0,
|
|
"step": 11780
|
|
},
|
|
{
|
|
"entropy": 5.569497537612915,
|
|
"epoch": 1.1696109567288606,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004871469147960917,
|
|
"loss": 5.2178,
|
|
"mean_token_accuracy": 0.16689679473638536,
|
|
"num_tokens": 25821502.0,
|
|
"step": 11785
|
|
},
|
|
{
|
|
"entropy": 5.560224294662476,
|
|
"epoch": 1.170107185391028,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004871351082969177,
|
|
"loss": 5.1036,
|
|
"mean_token_accuracy": 0.174156291782856,
|
|
"num_tokens": 25833231.0,
|
|
"step": 11790
|
|
},
|
|
{
|
|
"entropy": 5.60383448600769,
|
|
"epoch": 1.1706034140531958,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004871232965372501,
|
|
"loss": 5.2728,
|
|
"mean_token_accuracy": 0.16255935728549958,
|
|
"num_tokens": 25844867.0,
|
|
"step": 11795
|
|
},
|
|
{
|
|
"entropy": 5.549636602401733,
|
|
"epoch": 1.1710996427153633,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004871114795173819,
|
|
"loss": 5.2436,
|
|
"mean_token_accuracy": 0.1703019618988037,
|
|
"num_tokens": 25855959.0,
|
|
"step": 11800
|
|
},
|
|
{
|
|
"entropy": 5.57716703414917,
|
|
"epoch": 1.1715958713775307,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004870996572376061,
|
|
"loss": 5.3213,
|
|
"mean_token_accuracy": 0.16501019299030303,
|
|
"num_tokens": 25866926.0,
|
|
"step": 11805
|
|
},
|
|
{
|
|
"entropy": 5.618939924240112,
|
|
"epoch": 1.1720921000396982,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004870878296982157,
|
|
"loss": 5.254,
|
|
"mean_token_accuracy": 0.15923433899879455,
|
|
"num_tokens": 25877699.0,
|
|
"step": 11810
|
|
},
|
|
{
|
|
"entropy": 5.629858064651489,
|
|
"epoch": 1.172588328701866,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004870759968995042,
|
|
"loss": 5.2138,
|
|
"mean_token_accuracy": 0.16843907088041304,
|
|
"num_tokens": 25888640.0,
|
|
"step": 11815
|
|
},
|
|
{
|
|
"entropy": 5.577797985076904,
|
|
"epoch": 1.1730845573640334,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.00048706415884176493,
|
|
"loss": 5.2014,
|
|
"mean_token_accuracy": 0.16519638150930405,
|
|
"num_tokens": 25900651.0,
|
|
"step": 11820
|
|
},
|
|
{
|
|
"entropy": 5.528300046920776,
|
|
"epoch": 1.1735807860262009,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004870523155252915,
|
|
"loss": 5.1725,
|
|
"mean_token_accuracy": 0.16927069127559663,
|
|
"num_tokens": 25911775.0,
|
|
"step": 11825
|
|
},
|
|
{
|
|
"entropy": 5.530733680725097,
|
|
"epoch": 1.1740770146883683,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004870404669503776,
|
|
"loss": 5.1528,
|
|
"mean_token_accuracy": 0.16928931176662446,
|
|
"num_tokens": 25922126.0,
|
|
"step": 11830
|
|
},
|
|
{
|
|
"entropy": 5.583652687072754,
|
|
"epoch": 1.1745732433505358,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.000487028613117317,
|
|
"loss": 5.2067,
|
|
"mean_token_accuracy": 0.16576076596975325,
|
|
"num_tokens": 25932945.0,
|
|
"step": 11835
|
|
},
|
|
{
|
|
"entropy": 5.597814893722534,
|
|
"epoch": 1.1750694720127035,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004870167540264037,
|
|
"loss": 5.257,
|
|
"mean_token_accuracy": 0.16133045703172683,
|
|
"num_tokens": 25944277.0,
|
|
"step": 11840
|
|
},
|
|
{
|
|
"entropy": 5.496471834182739,
|
|
"epoch": 1.175565700674871,
|
|
"grad_norm": 0.796875,
|
|
"learning_rate": 0.0004870048896779317,
|
|
"loss": 5.1171,
|
|
"mean_token_accuracy": 0.17152974456548692,
|
|
"num_tokens": 25956838.0,
|
|
"step": 11845
|
|
},
|
|
{
|
|
"entropy": 5.537053728103638,
|
|
"epoch": 1.1760619293370385,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.00048699302007219533,
|
|
"loss": 5.1889,
|
|
"mean_token_accuracy": 0.16208528131246566,
|
|
"num_tokens": 25966639.0,
|
|
"step": 11850
|
|
},
|
|
{
|
|
"entropy": 5.531539678573608,
|
|
"epoch": 1.1765581579992062,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004869811452094889,
|
|
"loss": 5.2242,
|
|
"mean_token_accuracy": 0.17045587301254272,
|
|
"num_tokens": 25978209.0,
|
|
"step": 11855
|
|
},
|
|
{
|
|
"entropy": 5.51884183883667,
|
|
"epoch": 1.1770543866613736,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.00048696926509010673,
|
|
"loss": 5.1486,
|
|
"mean_token_accuracy": 0.16951389610767365,
|
|
"num_tokens": 25989306.0,
|
|
"step": 11860
|
|
},
|
|
{
|
|
"entropy": 5.5544044971466064,
|
|
"epoch": 1.177550615323541,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004869573797143437,
|
|
"loss": 5.2569,
|
|
"mean_token_accuracy": 0.16379437744617462,
|
|
"num_tokens": 26000235.0,
|
|
"step": 11865
|
|
},
|
|
{
|
|
"entropy": 5.524611091613769,
|
|
"epoch": 1.1780468439857086,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004869454890824942,
|
|
"loss": 5.1549,
|
|
"mean_token_accuracy": 0.17138529419898987,
|
|
"num_tokens": 26010616.0,
|
|
"step": 11870
|
|
},
|
|
{
|
|
"entropy": 5.553587245941162,
|
|
"epoch": 1.178543072647876,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.00048693359319485337,
|
|
"loss": 5.2271,
|
|
"mean_token_accuracy": 0.1586771696805954,
|
|
"num_tokens": 26021303.0,
|
|
"step": 11875
|
|
},
|
|
{
|
|
"entropy": 5.5444655418396,
|
|
"epoch": 1.1790393013100438,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004869216920517161,
|
|
"loss": 5.1621,
|
|
"mean_token_accuracy": 0.16711566001176834,
|
|
"num_tokens": 26032386.0,
|
|
"step": 11880
|
|
},
|
|
{
|
|
"entropy": 5.468569278717041,
|
|
"epoch": 1.1795355299722112,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.00048690978565337753,
|
|
"loss": 5.1296,
|
|
"mean_token_accuracy": 0.1663554824888706,
|
|
"num_tokens": 26042889.0,
|
|
"step": 11885
|
|
},
|
|
{
|
|
"entropy": 5.5141987800598145,
|
|
"epoch": 1.1800317586343787,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00048689787400013287,
|
|
"loss": 5.2313,
|
|
"mean_token_accuracy": 0.16644604802131652,
|
|
"num_tokens": 26054299.0,
|
|
"step": 11890
|
|
},
|
|
{
|
|
"entropy": 5.612095355987549,
|
|
"epoch": 1.1805279872965462,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004868859570922775,
|
|
"loss": 5.2642,
|
|
"mean_token_accuracy": 0.1618034929037094,
|
|
"num_tokens": 26064587.0,
|
|
"step": 11895
|
|
},
|
|
{
|
|
"entropy": 5.624295282363891,
|
|
"epoch": 1.1810242159587139,
|
|
"grad_norm": 0.78125,
|
|
"learning_rate": 0.0004868740349301071,
|
|
"loss": 5.1959,
|
|
"mean_token_accuracy": 0.17469189912080765,
|
|
"num_tokens": 26076495.0,
|
|
"step": 11900
|
|
},
|
|
{
|
|
"entropy": 5.5879435539245605,
|
|
"epoch": 1.1815204446208813,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.000486862107513917,
|
|
"loss": 5.2002,
|
|
"mean_token_accuracy": 0.16503895819187164,
|
|
"num_tokens": 26086496.0,
|
|
"step": 11905
|
|
},
|
|
{
|
|
"entropy": 5.506546354293823,
|
|
"epoch": 1.1820166732830488,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004868501748440033,
|
|
"loss": 5.1837,
|
|
"mean_token_accuracy": 0.16451774090528487,
|
|
"num_tokens": 26097263.0,
|
|
"step": 11910
|
|
},
|
|
{
|
|
"entropy": 5.560457181930542,
|
|
"epoch": 1.1825129019452163,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004868382369206617,
|
|
"loss": 5.1795,
|
|
"mean_token_accuracy": 0.16694652587175368,
|
|
"num_tokens": 26108264.0,
|
|
"step": 11915
|
|
},
|
|
{
|
|
"entropy": 5.566349029541016,
|
|
"epoch": 1.1830091306073838,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004868262937441883,
|
|
"loss": 5.2521,
|
|
"mean_token_accuracy": 0.17175290882587432,
|
|
"num_tokens": 26119730.0,
|
|
"step": 11920
|
|
},
|
|
{
|
|
"entropy": 5.5816343307495115,
|
|
"epoch": 1.1835053592695515,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.00048681434531487925,
|
|
"loss": 5.1533,
|
|
"mean_token_accuracy": 0.16655018478631972,
|
|
"num_tokens": 26131055.0,
|
|
"step": 11925
|
|
},
|
|
{
|
|
"entropy": 5.500956201553345,
|
|
"epoch": 1.184001587931719,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.00048680239163303085,
|
|
"loss": 5.1596,
|
|
"mean_token_accuracy": 0.1692327693104744,
|
|
"num_tokens": 26141577.0,
|
|
"step": 11930
|
|
},
|
|
{
|
|
"entropy": 5.512574529647827,
|
|
"epoch": 1.1844978165938864,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004867904326989396,
|
|
"loss": 5.2005,
|
|
"mean_token_accuracy": 0.17093419134616852,
|
|
"num_tokens": 26152733.0,
|
|
"step": 11935
|
|
},
|
|
{
|
|
"entropy": 5.577522802352905,
|
|
"epoch": 1.184994045256054,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004867784685129019,
|
|
"loss": 5.2401,
|
|
"mean_token_accuracy": 0.16454808712005614,
|
|
"num_tokens": 26164763.0,
|
|
"step": 11940
|
|
},
|
|
{
|
|
"entropy": 5.536622810363769,
|
|
"epoch": 1.1854902739182216,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.00048676649907521455,
|
|
"loss": 5.1186,
|
|
"mean_token_accuracy": 0.17210778146982192,
|
|
"num_tokens": 26174391.0,
|
|
"step": 11945
|
|
},
|
|
{
|
|
"entropy": 5.442165374755859,
|
|
"epoch": 1.185986502580389,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.00048675452438617434,
|
|
"loss": 5.0972,
|
|
"mean_token_accuracy": 0.1761639818549156,
|
|
"num_tokens": 26184772.0,
|
|
"step": 11950
|
|
},
|
|
{
|
|
"entropy": 5.600083541870117,
|
|
"epoch": 1.1864827312425565,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004867425444460782,
|
|
"loss": 5.2579,
|
|
"mean_token_accuracy": 0.15648220777511596,
|
|
"num_tokens": 26195411.0,
|
|
"step": 11955
|
|
},
|
|
{
|
|
"entropy": 5.521206712722778,
|
|
"epoch": 1.186978959904724,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004867305592552233,
|
|
"loss": 5.1787,
|
|
"mean_token_accuracy": 0.1663449838757515,
|
|
"num_tokens": 26206719.0,
|
|
"step": 11960
|
|
},
|
|
{
|
|
"entropy": 5.496636438369751,
|
|
"epoch": 1.1874751885668917,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004867185688139067,
|
|
"loss": 5.122,
|
|
"mean_token_accuracy": 0.1714530736207962,
|
|
"num_tokens": 26217469.0,
|
|
"step": 11965
|
|
},
|
|
{
|
|
"entropy": 5.461162996292114,
|
|
"epoch": 1.1879714172290592,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004867065731224258,
|
|
"loss": 5.1429,
|
|
"mean_token_accuracy": 0.16440949887037276,
|
|
"num_tokens": 26228556.0,
|
|
"step": 11970
|
|
},
|
|
{
|
|
"entropy": 5.5642680644989015,
|
|
"epoch": 1.1884676458912267,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004866945721810781,
|
|
"loss": 5.2463,
|
|
"mean_token_accuracy": 0.16796668469905854,
|
|
"num_tokens": 26239891.0,
|
|
"step": 11975
|
|
},
|
|
{
|
|
"entropy": 5.570119047164917,
|
|
"epoch": 1.1889638745533941,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004866825659901612,
|
|
"loss": 5.1992,
|
|
"mean_token_accuracy": 0.17129147946834564,
|
|
"num_tokens": 26251793.0,
|
|
"step": 11980
|
|
},
|
|
{
|
|
"entropy": 5.473042297363281,
|
|
"epoch": 1.1894601032155618,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.00048667055454997276,
|
|
"loss": 5.0967,
|
|
"mean_token_accuracy": 0.16642365604639053,
|
|
"num_tokens": 26262367.0,
|
|
"step": 11985
|
|
},
|
|
{
|
|
"entropy": 5.500068712234497,
|
|
"epoch": 1.1899563318777293,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00048665853786081063,
|
|
"loss": 5.1787,
|
|
"mean_token_accuracy": 0.1641027122735977,
|
|
"num_tokens": 26272681.0,
|
|
"step": 11990
|
|
},
|
|
{
|
|
"entropy": 5.54545578956604,
|
|
"epoch": 1.1904525605398968,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00048664651592297294,
|
|
"loss": 5.249,
|
|
"mean_token_accuracy": 0.1640736386179924,
|
|
"num_tokens": 26281194.0,
|
|
"step": 11995
|
|
},
|
|
{
|
|
"entropy": 5.564527750015259,
|
|
"epoch": 1.1909487892020643,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.00048663448873675766,
|
|
"loss": 5.1344,
|
|
"mean_token_accuracy": 0.1650382623076439,
|
|
"num_tokens": 26292682.0,
|
|
"step": 12000
|
|
},
|
|
{
|
|
"epoch": 1.1909487892020643,
|
|
"eval_entropy": 5.415048342754847,
|
|
"eval_loss": 5.320173740386963,
|
|
"eval_mean_token_accuracy": 0.1656518037897599,
|
|
"eval_num_tokens": 26292682.0,
|
|
"eval_runtime": 20.3903,
|
|
"eval_samples_per_second": 1651.228,
|
|
"eval_steps_per_second": 206.422,
|
|
"step": 12000
|
|
},
|
|
{
|
|
"entropy": 5.578801870346069,
|
|
"epoch": 1.1914450178642317,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004866224563024631,
|
|
"loss": 5.2472,
|
|
"mean_token_accuracy": 0.15969247370958328,
|
|
"num_tokens": 26305500.0,
|
|
"step": 12005
|
|
},
|
|
{
|
|
"entropy": 5.550313234329224,
|
|
"epoch": 1.1919412465263994,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004866104186203877,
|
|
"loss": 5.144,
|
|
"mean_token_accuracy": 0.16529141068458558,
|
|
"num_tokens": 26317207.0,
|
|
"step": 12010
|
|
},
|
|
{
|
|
"entropy": 5.530046606063843,
|
|
"epoch": 1.192437475188567,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.00048659837569082977,
|
|
"loss": 5.1586,
|
|
"mean_token_accuracy": 0.16852137297391892,
|
|
"num_tokens": 26328728.0,
|
|
"step": 12015
|
|
},
|
|
{
|
|
"entropy": 5.606966304779053,
|
|
"epoch": 1.1929337038507344,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004865863275140882,
|
|
"loss": 5.1997,
|
|
"mean_token_accuracy": 0.1659929111599922,
|
|
"num_tokens": 26338622.0,
|
|
"step": 12020
|
|
},
|
|
{
|
|
"entropy": 5.561013460159302,
|
|
"epoch": 1.1934299325129019,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004865742740904615,
|
|
"loss": 5.1836,
|
|
"mean_token_accuracy": 0.16556894183158874,
|
|
"num_tokens": 26348807.0,
|
|
"step": 12025
|
|
},
|
|
{
|
|
"entropy": 5.472616577148438,
|
|
"epoch": 1.1939261611750696,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004865622154202488,
|
|
"loss": 5.15,
|
|
"mean_token_accuracy": 0.16642577350139617,
|
|
"num_tokens": 26358481.0,
|
|
"step": 12030
|
|
},
|
|
{
|
|
"entropy": 5.525966596603394,
|
|
"epoch": 1.194422389837237,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.00048655015150374904,
|
|
"loss": 5.2154,
|
|
"mean_token_accuracy": 0.1611705929040909,
|
|
"num_tokens": 26370519.0,
|
|
"step": 12035
|
|
},
|
|
{
|
|
"entropy": 5.602569627761841,
|
|
"epoch": 1.1949186184994045,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004865380823412613,
|
|
"loss": 5.2153,
|
|
"mean_token_accuracy": 0.16661960780620574,
|
|
"num_tokens": 26380988.0,
|
|
"step": 12040
|
|
},
|
|
{
|
|
"entropy": 5.512216520309448,
|
|
"epoch": 1.195414847161572,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.000486526007933085,
|
|
"loss": 5.1106,
|
|
"mean_token_accuracy": 0.17212731540203094,
|
|
"num_tokens": 26390308.0,
|
|
"step": 12045
|
|
},
|
|
{
|
|
"entropy": 5.556072664260864,
|
|
"epoch": 1.1959110758237395,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.00048651392827951944,
|
|
"loss": 5.2305,
|
|
"mean_token_accuracy": 0.15660665333271026,
|
|
"num_tokens": 26401145.0,
|
|
"step": 12050
|
|
},
|
|
{
|
|
"entropy": 5.550975894927978,
|
|
"epoch": 1.1964073044859072,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.00048650184338086436,
|
|
"loss": 5.1638,
|
|
"mean_token_accuracy": 0.168052639067173,
|
|
"num_tokens": 26411930.0,
|
|
"step": 12055
|
|
},
|
|
{
|
|
"entropy": 5.516152286529541,
|
|
"epoch": 1.1969035331480746,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00048648975323741916,
|
|
"loss": 5.1122,
|
|
"mean_token_accuracy": 0.16455964744091034,
|
|
"num_tokens": 26422320.0,
|
|
"step": 12060
|
|
},
|
|
{
|
|
"entropy": 5.615703058242798,
|
|
"epoch": 1.197399761810242,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00048647765784948395,
|
|
"loss": 5.2378,
|
|
"mean_token_accuracy": 0.16010700464248656,
|
|
"num_tokens": 26433760.0,
|
|
"step": 12065
|
|
},
|
|
{
|
|
"entropy": 5.595371055603027,
|
|
"epoch": 1.1978959904724098,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004864655572173584,
|
|
"loss": 5.1572,
|
|
"mean_token_accuracy": 0.1727421760559082,
|
|
"num_tokens": 26444256.0,
|
|
"step": 12070
|
|
},
|
|
{
|
|
"entropy": 5.536590480804444,
|
|
"epoch": 1.1983922191345773,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.00048645345134134274,
|
|
"loss": 5.2511,
|
|
"mean_token_accuracy": 0.16822822988033295,
|
|
"num_tokens": 26456433.0,
|
|
"step": 12075
|
|
},
|
|
{
|
|
"entropy": 5.569968271255493,
|
|
"epoch": 1.1988884477967447,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00048644134022173707,
|
|
"loss": 5.2169,
|
|
"mean_token_accuracy": 0.16848678588867189,
|
|
"num_tokens": 26466909.0,
|
|
"step": 12080
|
|
},
|
|
{
|
|
"entropy": 5.589114999771118,
|
|
"epoch": 1.1993846764589122,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004864292238588419,
|
|
"loss": 5.2187,
|
|
"mean_token_accuracy": 0.1713562101125717,
|
|
"num_tokens": 26478785.0,
|
|
"step": 12085
|
|
},
|
|
{
|
|
"entropy": 5.500128746032715,
|
|
"epoch": 1.1998809051210797,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00048641710225295746,
|
|
"loss": 5.2303,
|
|
"mean_token_accuracy": 0.1657616525888443,
|
|
"num_tokens": 26489596.0,
|
|
"step": 12090
|
|
},
|
|
{
|
|
"entropy": 5.528736543655396,
|
|
"epoch": 1.2003771337832474,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00048640497540438455,
|
|
"loss": 5.1644,
|
|
"mean_token_accuracy": 0.16949445754289627,
|
|
"num_tokens": 26500376.0,
|
|
"step": 12095
|
|
},
|
|
{
|
|
"entropy": 5.508809995651245,
|
|
"epoch": 1.2008733624454149,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004863928433134237,
|
|
"loss": 5.0949,
|
|
"mean_token_accuracy": 0.17248708307743071,
|
|
"num_tokens": 26510339.0,
|
|
"step": 12100
|
|
},
|
|
{
|
|
"entropy": 5.55097508430481,
|
|
"epoch": 1.2013695911075823,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.00048638070598037585,
|
|
"loss": 5.1962,
|
|
"mean_token_accuracy": 0.1656286373734474,
|
|
"num_tokens": 26521359.0,
|
|
"step": 12105
|
|
},
|
|
{
|
|
"entropy": 5.607142925262451,
|
|
"epoch": 1.2018658197697498,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000486368563405542,
|
|
"loss": 5.2709,
|
|
"mean_token_accuracy": 0.16035255342721938,
|
|
"num_tokens": 26532716.0,
|
|
"step": 12110
|
|
},
|
|
{
|
|
"entropy": 5.508362054824829,
|
|
"epoch": 1.2023620484319175,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004863564155892232,
|
|
"loss": 5.106,
|
|
"mean_token_accuracy": 0.16817451715469361,
|
|
"num_tokens": 26542624.0,
|
|
"step": 12115
|
|
},
|
|
{
|
|
"entropy": 5.583513975143433,
|
|
"epoch": 1.202858277094085,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004863442625317208,
|
|
"loss": 5.2313,
|
|
"mean_token_accuracy": 0.16890258938074112,
|
|
"num_tokens": 26552907.0,
|
|
"step": 12120
|
|
},
|
|
{
|
|
"entropy": 5.495972442626953,
|
|
"epoch": 1.2033545057562525,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.00048633210423333607,
|
|
"loss": 5.1739,
|
|
"mean_token_accuracy": 0.16416290402412415,
|
|
"num_tokens": 26564871.0,
|
|
"step": 12125
|
|
},
|
|
{
|
|
"entropy": 5.5188898086547855,
|
|
"epoch": 1.20385073441842,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004863199406943705,
|
|
"loss": 5.1736,
|
|
"mean_token_accuracy": 0.16844612807035447,
|
|
"num_tokens": 26576254.0,
|
|
"step": 12130
|
|
},
|
|
{
|
|
"entropy": 5.581023836135865,
|
|
"epoch": 1.2043469630805874,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.00048630777191512584,
|
|
"loss": 5.1916,
|
|
"mean_token_accuracy": 0.17156504690647126,
|
|
"num_tokens": 26587518.0,
|
|
"step": 12135
|
|
},
|
|
{
|
|
"entropy": 5.507179260253906,
|
|
"epoch": 1.2048431917427551,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00048629559789590366,
|
|
"loss": 5.103,
|
|
"mean_token_accuracy": 0.1670466184616089,
|
|
"num_tokens": 26597485.0,
|
|
"step": 12140
|
|
},
|
|
{
|
|
"entropy": 5.483174276351929,
|
|
"epoch": 1.2053394204049226,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.000486283418637006,
|
|
"loss": 5.1563,
|
|
"mean_token_accuracy": 0.16611899733543395,
|
|
"num_tokens": 26607696.0,
|
|
"step": 12145
|
|
},
|
|
{
|
|
"entropy": 5.561501216888428,
|
|
"epoch": 1.20583564906709,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004862712341387348,
|
|
"loss": 5.1882,
|
|
"mean_token_accuracy": 0.16724651902914048,
|
|
"num_tokens": 26618974.0,
|
|
"step": 12150
|
|
},
|
|
{
|
|
"entropy": 5.596035289764404,
|
|
"epoch": 1.2063318777292578,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004862590444013923,
|
|
"loss": 5.2305,
|
|
"mean_token_accuracy": 0.16883024722337722,
|
|
"num_tokens": 26629949.0,
|
|
"step": 12155
|
|
},
|
|
{
|
|
"entropy": 5.566052055358886,
|
|
"epoch": 1.2068281063914252,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004862468494252806,
|
|
"loss": 5.1598,
|
|
"mean_token_accuracy": 0.16777434647083284,
|
|
"num_tokens": 26641460.0,
|
|
"step": 12160
|
|
},
|
|
{
|
|
"entropy": 5.5983438968658445,
|
|
"epoch": 1.2073243350535927,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004862346492107024,
|
|
"loss": 5.2552,
|
|
"mean_token_accuracy": 0.16443577408790588,
|
|
"num_tokens": 26652553.0,
|
|
"step": 12165
|
|
},
|
|
{
|
|
"entropy": 5.518207979202271,
|
|
"epoch": 1.2078205637157602,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00048622244375796,
|
|
"loss": 5.1733,
|
|
"mean_token_accuracy": 0.16214610785245895,
|
|
"num_tokens": 26662479.0,
|
|
"step": 12170
|
|
},
|
|
{
|
|
"entropy": 5.574397182464599,
|
|
"epoch": 1.2083167923779277,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004862102330673561,
|
|
"loss": 5.2118,
|
|
"mean_token_accuracy": 0.16284110248088837,
|
|
"num_tokens": 26673326.0,
|
|
"step": 12175
|
|
},
|
|
{
|
|
"entropy": 5.598153114318848,
|
|
"epoch": 1.2088130210400954,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.00048619801713919357,
|
|
"loss": 5.2643,
|
|
"mean_token_accuracy": 0.159586501121521,
|
|
"num_tokens": 26684189.0,
|
|
"step": 12180
|
|
},
|
|
{
|
|
"entropy": 5.6394611358642575,
|
|
"epoch": 1.2093092497022628,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004861857959737753,
|
|
"loss": 5.2794,
|
|
"mean_token_accuracy": 0.16381492763757705,
|
|
"num_tokens": 26695399.0,
|
|
"step": 12185
|
|
},
|
|
{
|
|
"entropy": 5.595186042785644,
|
|
"epoch": 1.2098054783644303,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004861735695714044,
|
|
"loss": 5.2092,
|
|
"mean_token_accuracy": 0.1677875965833664,
|
|
"num_tokens": 26705993.0,
|
|
"step": 12190
|
|
},
|
|
{
|
|
"entropy": 5.562430095672608,
|
|
"epoch": 1.2103017070265978,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00048616133793238394,
|
|
"loss": 5.1838,
|
|
"mean_token_accuracy": 0.1704581633210182,
|
|
"num_tokens": 26716120.0,
|
|
"step": 12195
|
|
},
|
|
{
|
|
"entropy": 5.577006244659424,
|
|
"epoch": 1.2107979356887655,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00048614910105701737,
|
|
"loss": 5.3138,
|
|
"mean_token_accuracy": 0.15813263058662413,
|
|
"num_tokens": 26727736.0,
|
|
"step": 12200
|
|
},
|
|
{
|
|
"entropy": 5.603042507171631,
|
|
"epoch": 1.211294164350933,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004861368589456081,
|
|
"loss": 5.1655,
|
|
"mean_token_accuracy": 0.1643623873591423,
|
|
"num_tokens": 26737825.0,
|
|
"step": 12205
|
|
},
|
|
{
|
|
"entropy": 5.643135738372803,
|
|
"epoch": 1.2117903930131004,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004861246115984596,
|
|
"loss": 5.2516,
|
|
"mean_token_accuracy": 0.15876631587743759,
|
|
"num_tokens": 26748035.0,
|
|
"step": 12210
|
|
},
|
|
{
|
|
"entropy": 5.604583644866944,
|
|
"epoch": 1.212286621675268,
|
|
"grad_norm": 0.80078125,
|
|
"learning_rate": 0.00048611235901587575,
|
|
"loss": 5.1746,
|
|
"mean_token_accuracy": 0.1688556954264641,
|
|
"num_tokens": 26759899.0,
|
|
"step": 12215
|
|
},
|
|
{
|
|
"entropy": 5.462530183792114,
|
|
"epoch": 1.2127828503374354,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004861001011981602,
|
|
"loss": 5.1236,
|
|
"mean_token_accuracy": 0.17259134650230407,
|
|
"num_tokens": 26771562.0,
|
|
"step": 12220
|
|
},
|
|
{
|
|
"entropy": 5.569944047927857,
|
|
"epoch": 1.213279078999603,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004860878381456171,
|
|
"loss": 5.2354,
|
|
"mean_token_accuracy": 0.16821920722723008,
|
|
"num_tokens": 26783002.0,
|
|
"step": 12225
|
|
},
|
|
{
|
|
"entropy": 5.575166654586792,
|
|
"epoch": 1.2137753076617706,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00048607556985855047,
|
|
"loss": 5.2314,
|
|
"mean_token_accuracy": 0.1648027256131172,
|
|
"num_tokens": 26794136.0,
|
|
"step": 12230
|
|
},
|
|
{
|
|
"entropy": 5.460007524490356,
|
|
"epoch": 1.214271536323938,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.00048606329633726447,
|
|
"loss": 5.2025,
|
|
"mean_token_accuracy": 0.16251839250326156,
|
|
"num_tokens": 26804776.0,
|
|
"step": 12235
|
|
},
|
|
{
|
|
"entropy": 5.502743482589722,
|
|
"epoch": 1.2147677649861055,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004860510175820636,
|
|
"loss": 5.1362,
|
|
"mean_token_accuracy": 0.16850659400224685,
|
|
"num_tokens": 26816696.0,
|
|
"step": 12240
|
|
},
|
|
{
|
|
"entropy": 5.48726978302002,
|
|
"epoch": 1.2152639936482732,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004860387335932522,
|
|
"loss": 5.1801,
|
|
"mean_token_accuracy": 0.1710625782608986,
|
|
"num_tokens": 26827789.0,
|
|
"step": 12245
|
|
},
|
|
{
|
|
"entropy": 5.572609901428223,
|
|
"epoch": 1.2157602223104407,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004860264443711351,
|
|
"loss": 5.135,
|
|
"mean_token_accuracy": 0.16863904297351837,
|
|
"num_tokens": 26838763.0,
|
|
"step": 12250
|
|
},
|
|
{
|
|
"entropy": 5.502274799346924,
|
|
"epoch": 1.2162564509726081,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004860141499160167,
|
|
"loss": 5.1693,
|
|
"mean_token_accuracy": 0.1614042803645134,
|
|
"num_tokens": 26849304.0,
|
|
"step": 12255
|
|
},
|
|
{
|
|
"entropy": 5.53492226600647,
|
|
"epoch": 1.2167526796347756,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004860018502282022,
|
|
"loss": 5.2349,
|
|
"mean_token_accuracy": 0.16254792138934135,
|
|
"num_tokens": 26858777.0,
|
|
"step": 12260
|
|
},
|
|
{
|
|
"entropy": 5.595277976989746,
|
|
"epoch": 1.2172489082969433,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.00048598954530799644,
|
|
"loss": 5.1879,
|
|
"mean_token_accuracy": 0.16661825478076936,
|
|
"num_tokens": 26870286.0,
|
|
"step": 12265
|
|
},
|
|
{
|
|
"entropy": 5.582540559768677,
|
|
"epoch": 1.2177451369591108,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.00048597723515570465,
|
|
"loss": 5.1736,
|
|
"mean_token_accuracy": 0.1679397478699684,
|
|
"num_tokens": 26880485.0,
|
|
"step": 12270
|
|
},
|
|
{
|
|
"entropy": 5.436429119110107,
|
|
"epoch": 1.2182413656212783,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.000485964919771632,
|
|
"loss": 5.0799,
|
|
"mean_token_accuracy": 0.1702420324087143,
|
|
"num_tokens": 26893556.0,
|
|
"step": 12275
|
|
},
|
|
{
|
|
"entropy": 5.519435024261474,
|
|
"epoch": 1.2187375942834457,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.00048595259915608396,
|
|
"loss": 5.1668,
|
|
"mean_token_accuracy": 0.16302407830953597,
|
|
"num_tokens": 26905699.0,
|
|
"step": 12280
|
|
},
|
|
{
|
|
"entropy": 5.570646667480469,
|
|
"epoch": 1.2192338229456134,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.00048594027330936594,
|
|
"loss": 5.1946,
|
|
"mean_token_accuracy": 0.16270232051610947,
|
|
"num_tokens": 26917188.0,
|
|
"step": 12285
|
|
},
|
|
{
|
|
"entropy": 5.552227020263672,
|
|
"epoch": 1.219730051607781,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.00048592794223178374,
|
|
"loss": 5.1808,
|
|
"mean_token_accuracy": 0.1670808508992195,
|
|
"num_tokens": 26927905.0,
|
|
"step": 12290
|
|
},
|
|
{
|
|
"entropy": 5.465819072723389,
|
|
"epoch": 1.2202262802699484,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00048591560592364314,
|
|
"loss": 5.1508,
|
|
"mean_token_accuracy": 0.16758487820625306,
|
|
"num_tokens": 26938665.0,
|
|
"step": 12295
|
|
},
|
|
{
|
|
"entropy": 5.534365844726563,
|
|
"epoch": 1.2207225089321159,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004859032643852499,
|
|
"loss": 5.253,
|
|
"mean_token_accuracy": 0.16436808854341506,
|
|
"num_tokens": 26950516.0,
|
|
"step": 12300
|
|
},
|
|
{
|
|
"entropy": 5.635159540176391,
|
|
"epoch": 1.2212187375942833,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004858909176169102,
|
|
"loss": 5.2465,
|
|
"mean_token_accuracy": 0.17042109072208406,
|
|
"num_tokens": 26960018.0,
|
|
"step": 12305
|
|
},
|
|
{
|
|
"entropy": 5.563248777389527,
|
|
"epoch": 1.221714966256451,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00048587856561893014,
|
|
"loss": 5.1954,
|
|
"mean_token_accuracy": 0.16420393139123918,
|
|
"num_tokens": 26969825.0,
|
|
"step": 12310
|
|
},
|
|
{
|
|
"entropy": 5.587969255447388,
|
|
"epoch": 1.2222111949186185,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004858662083916161,
|
|
"loss": 5.2928,
|
|
"mean_token_accuracy": 0.1615210860967636,
|
|
"num_tokens": 26979873.0,
|
|
"step": 12315
|
|
},
|
|
{
|
|
"entropy": 5.62132625579834,
|
|
"epoch": 1.222707423580786,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004858538459352744,
|
|
"loss": 5.2605,
|
|
"mean_token_accuracy": 0.16628895476460456,
|
|
"num_tokens": 26990577.0,
|
|
"step": 12320
|
|
},
|
|
{
|
|
"entropy": 5.524898433685303,
|
|
"epoch": 1.2232036522429535,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004858414782502117,
|
|
"loss": 5.117,
|
|
"mean_token_accuracy": 0.17091183364391327,
|
|
"num_tokens": 27001598.0,
|
|
"step": 12325
|
|
},
|
|
{
|
|
"entropy": 5.49240665435791,
|
|
"epoch": 1.2236998809051212,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.00048582910533673474,
|
|
"loss": 5.1291,
|
|
"mean_token_accuracy": 0.17308679819107056,
|
|
"num_tokens": 27012535.0,
|
|
"step": 12330
|
|
},
|
|
{
|
|
"entropy": 5.531280088424682,
|
|
"epoch": 1.2241961095672886,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004858167271951502,
|
|
"loss": 5.2008,
|
|
"mean_token_accuracy": 0.1611105963587761,
|
|
"num_tokens": 27021867.0,
|
|
"step": 12335
|
|
},
|
|
{
|
|
"entropy": 5.474882888793945,
|
|
"epoch": 1.2246923382294561,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004858043438257651,
|
|
"loss": 5.1619,
|
|
"mean_token_accuracy": 0.16459438651800157,
|
|
"num_tokens": 27032540.0,
|
|
"step": 12340
|
|
},
|
|
{
|
|
"entropy": 5.458321809768677,
|
|
"epoch": 1.2251885668916236,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004857919552288865,
|
|
"loss": 5.1431,
|
|
"mean_token_accuracy": 0.16965974122285843,
|
|
"num_tokens": 27044008.0,
|
|
"step": 12345
|
|
},
|
|
{
|
|
"entropy": 5.583375597000122,
|
|
"epoch": 1.225684795553791,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004857795614048217,
|
|
"loss": 5.1638,
|
|
"mean_token_accuracy": 0.1659913569688797,
|
|
"num_tokens": 27053646.0,
|
|
"step": 12350
|
|
},
|
|
{
|
|
"entropy": 5.602629709243774,
|
|
"epoch": 1.2261810242159588,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00048576716235387786,
|
|
"loss": 5.2772,
|
|
"mean_token_accuracy": 0.16023823320865632,
|
|
"num_tokens": 27065834.0,
|
|
"step": 12355
|
|
},
|
|
{
|
|
"entropy": 5.517317819595337,
|
|
"epoch": 1.2266772528781262,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00048575475807636267,
|
|
"loss": 5.2164,
|
|
"mean_token_accuracy": 0.16655384600162507,
|
|
"num_tokens": 27077544.0,
|
|
"step": 12360
|
|
},
|
|
{
|
|
"entropy": 5.592941522598267,
|
|
"epoch": 1.2271734815402937,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00048574234857258356,
|
|
"loss": 5.2657,
|
|
"mean_token_accuracy": 0.1652846321463585,
|
|
"num_tokens": 27088294.0,
|
|
"step": 12365
|
|
},
|
|
{
|
|
"entropy": 5.559949636459351,
|
|
"epoch": 1.2276697102024614,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.00048572993384284833,
|
|
"loss": 5.1976,
|
|
"mean_token_accuracy": 0.16609010398387908,
|
|
"num_tokens": 27098848.0,
|
|
"step": 12370
|
|
},
|
|
{
|
|
"entropy": 5.482949447631836,
|
|
"epoch": 1.2281659388646289,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004857175138874648,
|
|
"loss": 5.1588,
|
|
"mean_token_accuracy": 0.1705593392252922,
|
|
"num_tokens": 27112319.0,
|
|
"step": 12375
|
|
},
|
|
{
|
|
"entropy": 5.582285785675049,
|
|
"epoch": 1.2286621675267964,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00048570508870674097,
|
|
"loss": 5.2312,
|
|
"mean_token_accuracy": 0.1679324045777321,
|
|
"num_tokens": 27121840.0,
|
|
"step": 12380
|
|
},
|
|
{
|
|
"entropy": 5.583931303024292,
|
|
"epoch": 1.2291583961889638,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.00048569265830098493,
|
|
"loss": 5.2412,
|
|
"mean_token_accuracy": 0.16400841474533082,
|
|
"num_tokens": 27133619.0,
|
|
"step": 12385
|
|
},
|
|
{
|
|
"entropy": 5.539572668075562,
|
|
"epoch": 1.2296546248511313,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.000485680222670505,
|
|
"loss": 5.2212,
|
|
"mean_token_accuracy": 0.1619301199913025,
|
|
"num_tokens": 27144161.0,
|
|
"step": 12390
|
|
},
|
|
{
|
|
"entropy": 5.528607940673828,
|
|
"epoch": 1.230150853513299,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004856677818156096,
|
|
"loss": 5.1353,
|
|
"mean_token_accuracy": 0.1702260345220566,
|
|
"num_tokens": 27154906.0,
|
|
"step": 12395
|
|
},
|
|
{
|
|
"entropy": 5.52781310081482,
|
|
"epoch": 1.2306470821754665,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.00048565533573660707,
|
|
"loss": 5.16,
|
|
"mean_token_accuracy": 0.16407609432935716,
|
|
"num_tokens": 27165746.0,
|
|
"step": 12400
|
|
},
|
|
{
|
|
"entropy": 5.500742769241333,
|
|
"epoch": 1.231143310837634,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004856428844338062,
|
|
"loss": 5.1437,
|
|
"mean_token_accuracy": 0.17028856575489043,
|
|
"num_tokens": 27176108.0,
|
|
"step": 12405
|
|
},
|
|
{
|
|
"entropy": 5.5010072708129885,
|
|
"epoch": 1.2316395394998014,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004856304279075156,
|
|
"loss": 5.2306,
|
|
"mean_token_accuracy": 0.16487469524145126,
|
|
"num_tokens": 27186721.0,
|
|
"step": 12410
|
|
},
|
|
{
|
|
"entropy": 5.525478410720825,
|
|
"epoch": 1.2321357681619691,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004856179661580444,
|
|
"loss": 5.0979,
|
|
"mean_token_accuracy": 0.17067277580499648,
|
|
"num_tokens": 27196120.0,
|
|
"step": 12415
|
|
},
|
|
{
|
|
"entropy": 5.60766110420227,
|
|
"epoch": 1.2326319968241366,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004856054991857013,
|
|
"loss": 5.233,
|
|
"mean_token_accuracy": 0.15933823734521865,
|
|
"num_tokens": 27207431.0,
|
|
"step": 12420
|
|
},
|
|
{
|
|
"entropy": 5.519527626037598,
|
|
"epoch": 1.233128225486304,
|
|
"grad_norm": 0.78515625,
|
|
"learning_rate": 0.00048559302699079576,
|
|
"loss": 5.1169,
|
|
"mean_token_accuracy": 0.17377728521823882,
|
|
"num_tokens": 27218489.0,
|
|
"step": 12425
|
|
},
|
|
{
|
|
"entropy": 5.568860244750977,
|
|
"epoch": 1.2336244541484715,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.0004855805495736369,
|
|
"loss": 5.2375,
|
|
"mean_token_accuracy": 0.16518362909555434,
|
|
"num_tokens": 27230849.0,
|
|
"step": 12430
|
|
},
|
|
{
|
|
"entropy": 5.56860466003418,
|
|
"epoch": 1.234120682810639,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004855680669345342,
|
|
"loss": 5.1956,
|
|
"mean_token_accuracy": 0.16450659632682801,
|
|
"num_tokens": 27242838.0,
|
|
"step": 12435
|
|
},
|
|
{
|
|
"entropy": 5.55742564201355,
|
|
"epoch": 1.2346169114728067,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.00048555557907379714,
|
|
"loss": 5.2193,
|
|
"mean_token_accuracy": 0.1727436289191246,
|
|
"num_tokens": 27253945.0,
|
|
"step": 12440
|
|
},
|
|
{
|
|
"entropy": 5.56047625541687,
|
|
"epoch": 1.2351131401349742,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00048554308599173544,
|
|
"loss": 5.2804,
|
|
"mean_token_accuracy": 0.16149513870477678,
|
|
"num_tokens": 27263999.0,
|
|
"step": 12445
|
|
},
|
|
{
|
|
"entropy": 5.587174415588379,
|
|
"epoch": 1.2356093687971417,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004855305876886589,
|
|
"loss": 5.1343,
|
|
"mean_token_accuracy": 0.1735944405198097,
|
|
"num_tokens": 27274677.0,
|
|
"step": 12450
|
|
},
|
|
{
|
|
"entropy": 5.560019540786743,
|
|
"epoch": 1.2361055974593094,
|
|
"grad_norm": 0.80078125,
|
|
"learning_rate": 0.00048551808416487743,
|
|
"loss": 5.1995,
|
|
"mean_token_accuracy": 0.16757825016975403,
|
|
"num_tokens": 27286512.0,
|
|
"step": 12455
|
|
},
|
|
{
|
|
"entropy": 5.513830327987671,
|
|
"epoch": 1.2366018261214768,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004855055754207011,
|
|
"loss": 5.2137,
|
|
"mean_token_accuracy": 0.16798983067274093,
|
|
"num_tokens": 27297620.0,
|
|
"step": 12460
|
|
},
|
|
{
|
|
"entropy": 5.58218092918396,
|
|
"epoch": 1.2370980547836443,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004854930614564401,
|
|
"loss": 5.2136,
|
|
"mean_token_accuracy": 0.1628502354025841,
|
|
"num_tokens": 27309963.0,
|
|
"step": 12465
|
|
},
|
|
{
|
|
"entropy": 5.662808084487915,
|
|
"epoch": 1.2375942834458118,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004854805422724047,
|
|
"loss": 5.301,
|
|
"mean_token_accuracy": 0.16280816197395326,
|
|
"num_tokens": 27320740.0,
|
|
"step": 12470
|
|
},
|
|
{
|
|
"entropy": 5.523580741882324,
|
|
"epoch": 1.2380905121079793,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004854680178689055,
|
|
"loss": 5.1203,
|
|
"mean_token_accuracy": 0.17369242906570434,
|
|
"num_tokens": 27331543.0,
|
|
"step": 12475
|
|
},
|
|
{
|
|
"entropy": 5.468808984756469,
|
|
"epoch": 1.238586740770147,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00048545548824625287,
|
|
"loss": 5.1065,
|
|
"mean_token_accuracy": 0.16945707947015762,
|
|
"num_tokens": 27343222.0,
|
|
"step": 12480
|
|
},
|
|
{
|
|
"entropy": 5.5376989364624025,
|
|
"epoch": 1.2390829694323144,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004854429534047577,
|
|
"loss": 5.1654,
|
|
"mean_token_accuracy": 0.17010142505168915,
|
|
"num_tokens": 27354694.0,
|
|
"step": 12485
|
|
},
|
|
{
|
|
"entropy": 5.51598424911499,
|
|
"epoch": 1.239579198094482,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004854304133447307,
|
|
"loss": 5.1617,
|
|
"mean_token_accuracy": 0.1636533945798874,
|
|
"num_tokens": 27365462.0,
|
|
"step": 12490
|
|
},
|
|
{
|
|
"entropy": 5.487661075592041,
|
|
"epoch": 1.2400754267566494,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.00048541786806648293,
|
|
"loss": 5.0887,
|
|
"mean_token_accuracy": 0.16731098741292955,
|
|
"num_tokens": 27377548.0,
|
|
"step": 12495
|
|
},
|
|
{
|
|
"entropy": 5.589825820922852,
|
|
"epoch": 1.240571655418817,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004854053175703254,
|
|
"loss": 5.207,
|
|
"mean_token_accuracy": 0.16157304495573044,
|
|
"num_tokens": 27388221.0,
|
|
"step": 12500
|
|
},
|
|
{
|
|
"entropy": 5.537165689468384,
|
|
"epoch": 1.2410678840809846,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004853927618565694,
|
|
"loss": 5.1935,
|
|
"mean_token_accuracy": 0.1684794694185257,
|
|
"num_tokens": 27400497.0,
|
|
"step": 12505
|
|
},
|
|
{
|
|
"entropy": 5.506247568130493,
|
|
"epoch": 1.241564112743152,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00048538020092552626,
|
|
"loss": 5.0914,
|
|
"mean_token_accuracy": 0.16751380562782286,
|
|
"num_tokens": 27410700.0,
|
|
"step": 12510
|
|
},
|
|
{
|
|
"entropy": 5.551796579360962,
|
|
"epoch": 1.2420603414053195,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00048536763477750747,
|
|
"loss": 5.2258,
|
|
"mean_token_accuracy": 0.1655466765165329,
|
|
"num_tokens": 27421286.0,
|
|
"step": 12515
|
|
},
|
|
{
|
|
"entropy": 5.626036262512207,
|
|
"epoch": 1.242556570067487,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004853550634128246,
|
|
"loss": 5.2336,
|
|
"mean_token_accuracy": 0.16408672034740449,
|
|
"num_tokens": 27433922.0,
|
|
"step": 12520
|
|
},
|
|
{
|
|
"entropy": 5.542233991622925,
|
|
"epoch": 1.2430527987296547,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004853424868317895,
|
|
"loss": 5.1626,
|
|
"mean_token_accuracy": 0.16384242922067643,
|
|
"num_tokens": 27444684.0,
|
|
"step": 12525
|
|
},
|
|
{
|
|
"entropy": 5.5254229545593265,
|
|
"epoch": 1.2435490273918222,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004853299050347139,
|
|
"loss": 5.1593,
|
|
"mean_token_accuracy": 0.16584260612726212,
|
|
"num_tokens": 27455494.0,
|
|
"step": 12530
|
|
},
|
|
{
|
|
"entropy": 5.602838563919067,
|
|
"epoch": 1.2440452560539896,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00048531731802190994,
|
|
"loss": 5.1972,
|
|
"mean_token_accuracy": 0.1603814661502838,
|
|
"num_tokens": 27464927.0,
|
|
"step": 12535
|
|
},
|
|
{
|
|
"entropy": 5.608969068527221,
|
|
"epoch": 1.244541484716157,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004853047257936897,
|
|
"loss": 5.1974,
|
|
"mean_token_accuracy": 0.16270526647567748,
|
|
"num_tokens": 27476228.0,
|
|
"step": 12540
|
|
},
|
|
{
|
|
"entropy": 5.559487533569336,
|
|
"epoch": 1.2450377133783248,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004852921283503653,
|
|
"loss": 5.1966,
|
|
"mean_token_accuracy": 0.16996813714504241,
|
|
"num_tokens": 27488835.0,
|
|
"step": 12545
|
|
},
|
|
{
|
|
"entropy": 5.550812721252441,
|
|
"epoch": 1.2455339420404923,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004852795256922494,
|
|
"loss": 5.1811,
|
|
"mean_token_accuracy": 0.1639793783426285,
|
|
"num_tokens": 27501481.0,
|
|
"step": 12550
|
|
},
|
|
{
|
|
"entropy": 5.571440935134888,
|
|
"epoch": 1.2460301707026598,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00048526691781965425,
|
|
"loss": 5.1766,
|
|
"mean_token_accuracy": 0.16824175864458085,
|
|
"num_tokens": 27512234.0,
|
|
"step": 12555
|
|
},
|
|
{
|
|
"entropy": 5.6053447246551515,
|
|
"epoch": 1.2465263993648272,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00048525430473289274,
|
|
"loss": 5.2434,
|
|
"mean_token_accuracy": 0.1635236144065857,
|
|
"num_tokens": 27523756.0,
|
|
"step": 12560
|
|
},
|
|
{
|
|
"entropy": 5.56353530883789,
|
|
"epoch": 1.247022628026995,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00048524168643227747,
|
|
"loss": 5.2457,
|
|
"mean_token_accuracy": 0.1614888444542885,
|
|
"num_tokens": 27534579.0,
|
|
"step": 12565
|
|
},
|
|
{
|
|
"entropy": 5.551519727706909,
|
|
"epoch": 1.2475188566891624,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.00048522906291812145,
|
|
"loss": 5.2725,
|
|
"mean_token_accuracy": 0.16104435324668884,
|
|
"num_tokens": 27546420.0,
|
|
"step": 12570
|
|
},
|
|
{
|
|
"entropy": 5.575799655914307,
|
|
"epoch": 1.2480150853513299,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00048521643419073763,
|
|
"loss": 5.1446,
|
|
"mean_token_accuracy": 0.16417765468358994,
|
|
"num_tokens": 27557701.0,
|
|
"step": 12575
|
|
},
|
|
{
|
|
"entropy": 5.517214632034301,
|
|
"epoch": 1.2485113140134974,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004852038002504392,
|
|
"loss": 5.1611,
|
|
"mean_token_accuracy": 0.1708637699484825,
|
|
"num_tokens": 27568592.0,
|
|
"step": 12580
|
|
},
|
|
{
|
|
"entropy": 5.543105173110962,
|
|
"epoch": 1.249007542675665,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.00048519116109753955,
|
|
"loss": 5.2086,
|
|
"mean_token_accuracy": 0.17284478098154069,
|
|
"num_tokens": 27579286.0,
|
|
"step": 12585
|
|
},
|
|
{
|
|
"entropy": 5.531618976593018,
|
|
"epoch": 1.2495037713378325,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.00048517851673235196,
|
|
"loss": 5.1354,
|
|
"mean_token_accuracy": 0.17142497897148132,
|
|
"num_tokens": 27590031.0,
|
|
"step": 12590
|
|
},
|
|
{
|
|
"entropy": 5.552273797988891,
|
|
"epoch": 1.25,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004851658671551901,
|
|
"loss": 5.1788,
|
|
"mean_token_accuracy": 0.16726864129304886,
|
|
"num_tokens": 27600999.0,
|
|
"step": 12595
|
|
},
|
|
{
|
|
"entropy": 5.520488452911377,
|
|
"epoch": 1.2504962286621675,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00048515321236636754,
|
|
"loss": 5.1668,
|
|
"mean_token_accuracy": 0.16250496804714204,
|
|
"num_tokens": 27613394.0,
|
|
"step": 12600
|
|
},
|
|
{
|
|
"entropy": 5.5385887145996096,
|
|
"epoch": 1.250992457324335,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004851405523661982,
|
|
"loss": 5.1414,
|
|
"mean_token_accuracy": 0.1739915832877159,
|
|
"num_tokens": 27624819.0,
|
|
"step": 12605
|
|
},
|
|
{
|
|
"entropy": 5.502660655975342,
|
|
"epoch": 1.2514886859865026,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.00048512788715499597,
|
|
"loss": 5.1651,
|
|
"mean_token_accuracy": 0.17367679625749588,
|
|
"num_tokens": 27635993.0,
|
|
"step": 12610
|
|
},
|
|
{
|
|
"entropy": 5.542938470840454,
|
|
"epoch": 1.2519849146486701,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004851152167330749,
|
|
"loss": 5.2446,
|
|
"mean_token_accuracy": 0.16339800804853438,
|
|
"num_tokens": 27647298.0,
|
|
"step": 12615
|
|
},
|
|
{
|
|
"entropy": 5.589235067367554,
|
|
"epoch": 1.2524811433108376,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.00048510254110074923,
|
|
"loss": 5.2128,
|
|
"mean_token_accuracy": 0.16768902838230132,
|
|
"num_tokens": 27659381.0,
|
|
"step": 12620
|
|
},
|
|
{
|
|
"entropy": 5.559755516052246,
|
|
"epoch": 1.2529773719730053,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004850898602583333,
|
|
"loss": 5.1878,
|
|
"mean_token_accuracy": 0.1667603462934494,
|
|
"num_tokens": 27671122.0,
|
|
"step": 12625
|
|
},
|
|
{
|
|
"entropy": 5.594545793533325,
|
|
"epoch": 1.2534736006351728,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.00048507717420614153,
|
|
"loss": 5.1907,
|
|
"mean_token_accuracy": 0.17167871445417404,
|
|
"num_tokens": 27683258.0,
|
|
"step": 12630
|
|
},
|
|
{
|
|
"entropy": 5.4619140625,
|
|
"epoch": 1.2539698292973402,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004850644829444884,
|
|
"loss": 5.0643,
|
|
"mean_token_accuracy": 0.17000673711299896,
|
|
"num_tokens": 27693116.0,
|
|
"step": 12635
|
|
},
|
|
{
|
|
"entropy": 5.4681346893310545,
|
|
"epoch": 1.2544660579595077,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.00048505178647368887,
|
|
"loss": 5.1512,
|
|
"mean_token_accuracy": 0.16957887262105942,
|
|
"num_tokens": 27704859.0,
|
|
"step": 12640
|
|
},
|
|
{
|
|
"entropy": 5.50218620300293,
|
|
"epoch": 1.2549622866216752,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004850390847940576,
|
|
"loss": 5.1032,
|
|
"mean_token_accuracy": 0.17045054137706755,
|
|
"num_tokens": 27715854.0,
|
|
"step": 12645
|
|
},
|
|
{
|
|
"entropy": 5.553264617919922,
|
|
"epoch": 1.2554585152838427,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004850263779059097,
|
|
"loss": 5.1458,
|
|
"mean_token_accuracy": 0.1721723720431328,
|
|
"num_tokens": 27726398.0,
|
|
"step": 12650
|
|
},
|
|
{
|
|
"entropy": 5.552562665939331,
|
|
"epoch": 1.2559547439460104,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004850136658095601,
|
|
"loss": 5.171,
|
|
"mean_token_accuracy": 0.17330212593078614,
|
|
"num_tokens": 27737337.0,
|
|
"step": 12655
|
|
},
|
|
{
|
|
"entropy": 5.524002265930176,
|
|
"epoch": 1.2564509726081778,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.00048500094850532417,
|
|
"loss": 5.1957,
|
|
"mean_token_accuracy": 0.16753595620393752,
|
|
"num_tokens": 27748593.0,
|
|
"step": 12660
|
|
},
|
|
{
|
|
"entropy": 5.563277959823608,
|
|
"epoch": 1.2569472012703453,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004849882259935172,
|
|
"loss": 5.1649,
|
|
"mean_token_accuracy": 0.16561111956834793,
|
|
"num_tokens": 27760908.0,
|
|
"step": 12665
|
|
},
|
|
{
|
|
"entropy": 5.589109563827515,
|
|
"epoch": 1.257443429932513,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004849754982744548,
|
|
"loss": 5.2399,
|
|
"mean_token_accuracy": 0.16375775039196014,
|
|
"num_tokens": 27772104.0,
|
|
"step": 12670
|
|
},
|
|
{
|
|
"entropy": 5.502607107162476,
|
|
"epoch": 1.2579396585946805,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004849627653484524,
|
|
"loss": 5.1899,
|
|
"mean_token_accuracy": 0.1701417937874794,
|
|
"num_tokens": 27781654.0,
|
|
"step": 12675
|
|
},
|
|
{
|
|
"entropy": 5.555015945434571,
|
|
"epoch": 1.258435887256848,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004849500272158259,
|
|
"loss": 5.1727,
|
|
"mean_token_accuracy": 0.16652282774448396,
|
|
"num_tokens": 27793026.0,
|
|
"step": 12680
|
|
},
|
|
{
|
|
"entropy": 5.548802280426026,
|
|
"epoch": 1.2589321159190154,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004849372838768911,
|
|
"loss": 5.1495,
|
|
"mean_token_accuracy": 0.1729058787226677,
|
|
"num_tokens": 27803447.0,
|
|
"step": 12685
|
|
},
|
|
{
|
|
"entropy": 5.615548849105835,
|
|
"epoch": 1.259428344581183,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000484924535331964,
|
|
"loss": 5.1546,
|
|
"mean_token_accuracy": 0.1635882079601288,
|
|
"num_tokens": 27814632.0,
|
|
"step": 12690
|
|
},
|
|
{
|
|
"entropy": 5.571075344085694,
|
|
"epoch": 1.2599245732433506,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.00048491178158136086,
|
|
"loss": 5.2367,
|
|
"mean_token_accuracy": 0.1636323943734169,
|
|
"num_tokens": 27826582.0,
|
|
"step": 12695
|
|
},
|
|
{
|
|
"entropy": 5.549906587600708,
|
|
"epoch": 1.260420801905518,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004848990226253978,
|
|
"loss": 5.0991,
|
|
"mean_token_accuracy": 0.16885340809822083,
|
|
"num_tokens": 27838065.0,
|
|
"step": 12700
|
|
},
|
|
{
|
|
"entropy": 5.4739526271820065,
|
|
"epoch": 1.2609170305676856,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00048488625846439135,
|
|
"loss": 5.1731,
|
|
"mean_token_accuracy": 0.1661983385682106,
|
|
"num_tokens": 27848182.0,
|
|
"step": 12705
|
|
},
|
|
{
|
|
"entropy": 5.585486602783203,
|
|
"epoch": 1.261413259229853,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004848734890986578,
|
|
"loss": 5.1727,
|
|
"mean_token_accuracy": 0.16330449134111405,
|
|
"num_tokens": 27858524.0,
|
|
"step": 12710
|
|
},
|
|
{
|
|
"entropy": 5.545848560333252,
|
|
"epoch": 1.2619094878920207,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004848607145285141,
|
|
"loss": 5.0946,
|
|
"mean_token_accuracy": 0.17027559280395507,
|
|
"num_tokens": 27868588.0,
|
|
"step": 12715
|
|
},
|
|
{
|
|
"entropy": 5.47784686088562,
|
|
"epoch": 1.2624057165541882,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004848479347542768,
|
|
"loss": 5.0962,
|
|
"mean_token_accuracy": 0.16958286762237548,
|
|
"num_tokens": 27878829.0,
|
|
"step": 12720
|
|
},
|
|
{
|
|
"entropy": 5.513685274124145,
|
|
"epoch": 1.2629019452163557,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.000484835149776263,
|
|
"loss": 5.1728,
|
|
"mean_token_accuracy": 0.17348767071962357,
|
|
"num_tokens": 27889872.0,
|
|
"step": 12725
|
|
},
|
|
{
|
|
"entropy": 5.5392392635345455,
|
|
"epoch": 1.2633981738785232,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00048482235959478953,
|
|
"loss": 5.2392,
|
|
"mean_token_accuracy": 0.16797590106725693,
|
|
"num_tokens": 27900567.0,
|
|
"step": 12730
|
|
},
|
|
{
|
|
"entropy": 5.547548723220825,
|
|
"epoch": 1.2638944025406906,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004848095642101737,
|
|
"loss": 5.1187,
|
|
"mean_token_accuracy": 0.16998957693576813,
|
|
"num_tokens": 27911594.0,
|
|
"step": 12735
|
|
},
|
|
{
|
|
"entropy": 5.577099561691284,
|
|
"epoch": 1.2643906312028583,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00048479676362273277,
|
|
"loss": 5.2251,
|
|
"mean_token_accuracy": 0.158519646525383,
|
|
"num_tokens": 27923694.0,
|
|
"step": 12740
|
|
},
|
|
{
|
|
"entropy": 5.561547088623047,
|
|
"epoch": 1.2648868598650258,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00048478395783278425,
|
|
"loss": 5.2971,
|
|
"mean_token_accuracy": 0.15378415286540986,
|
|
"num_tokens": 27934168.0,
|
|
"step": 12745
|
|
},
|
|
{
|
|
"entropy": 5.597050571441651,
|
|
"epoch": 1.2653830885271933,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004847711468406455,
|
|
"loss": 5.1886,
|
|
"mean_token_accuracy": 0.16538678854703903,
|
|
"num_tokens": 27944401.0,
|
|
"step": 12750
|
|
},
|
|
{
|
|
"entropy": 5.499141550064087,
|
|
"epoch": 1.265879317189361,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.00048475833064663443,
|
|
"loss": 5.0808,
|
|
"mean_token_accuracy": 0.17664188891649246,
|
|
"num_tokens": 27956219.0,
|
|
"step": 12755
|
|
},
|
|
{
|
|
"entropy": 5.547073936462402,
|
|
"epoch": 1.2663755458515285,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004847455092510687,
|
|
"loss": 5.1806,
|
|
"mean_token_accuracy": 0.1704688251018524,
|
|
"num_tokens": 27967457.0,
|
|
"step": 12760
|
|
},
|
|
{
|
|
"entropy": 5.5392418384552,
|
|
"epoch": 1.266871774513696,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004847326826542663,
|
|
"loss": 5.2006,
|
|
"mean_token_accuracy": 0.16247204542160035,
|
|
"num_tokens": 27978287.0,
|
|
"step": 12765
|
|
},
|
|
{
|
|
"entropy": 5.565428781509399,
|
|
"epoch": 1.2673680031758634,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.00048471985085654537,
|
|
"loss": 5.2134,
|
|
"mean_token_accuracy": 0.17096083909273146,
|
|
"num_tokens": 27989703.0,
|
|
"step": 12770
|
|
},
|
|
{
|
|
"entropy": 5.540671348571777,
|
|
"epoch": 1.2678642318380309,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.00048470701385822394,
|
|
"loss": 5.17,
|
|
"mean_token_accuracy": 0.168598735332489,
|
|
"num_tokens": 28002071.0,
|
|
"step": 12775
|
|
},
|
|
{
|
|
"entropy": 5.5525736808776855,
|
|
"epoch": 1.2683604605001986,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.00048469417165962047,
|
|
"loss": 5.2293,
|
|
"mean_token_accuracy": 0.17004916071891785,
|
|
"num_tokens": 28014517.0,
|
|
"step": 12780
|
|
},
|
|
{
|
|
"entropy": 5.554504776000977,
|
|
"epoch": 1.268856689162366,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004846813242610535,
|
|
"loss": 5.1979,
|
|
"mean_token_accuracy": 0.1747070163488388,
|
|
"num_tokens": 28025135.0,
|
|
"step": 12785
|
|
},
|
|
{
|
|
"entropy": 5.518036222457885,
|
|
"epoch": 1.2693529178245335,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004846684716628414,
|
|
"loss": 5.1215,
|
|
"mean_token_accuracy": 0.17613378763198853,
|
|
"num_tokens": 28036105.0,
|
|
"step": 12790
|
|
},
|
|
{
|
|
"entropy": 5.480977630615234,
|
|
"epoch": 1.269849146486701,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.000484655613865303,
|
|
"loss": 5.1611,
|
|
"mean_token_accuracy": 0.17135216891765595,
|
|
"num_tokens": 28048825.0,
|
|
"step": 12795
|
|
},
|
|
{
|
|
"entropy": 5.545332288742065,
|
|
"epoch": 1.2703453751488687,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.00048464275086875717,
|
|
"loss": 5.1196,
|
|
"mean_token_accuracy": 0.1681775078177452,
|
|
"num_tokens": 28060408.0,
|
|
"step": 12800
|
|
},
|
|
{
|
|
"entropy": 5.533175611495972,
|
|
"epoch": 1.2708416038110362,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004846298826735229,
|
|
"loss": 5.1877,
|
|
"mean_token_accuracy": 0.16483981162309647,
|
|
"num_tokens": 28072179.0,
|
|
"step": 12805
|
|
},
|
|
{
|
|
"entropy": 5.508754110336303,
|
|
"epoch": 1.2713378324732036,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004846170092799192,
|
|
"loss": 5.1751,
|
|
"mean_token_accuracy": 0.16775323301553727,
|
|
"num_tokens": 28083825.0,
|
|
"step": 12810
|
|
},
|
|
{
|
|
"entropy": 5.699008941650391,
|
|
"epoch": 1.2718340611353711,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.00048460413068826536,
|
|
"loss": 5.3208,
|
|
"mean_token_accuracy": 0.16472983807325364,
|
|
"num_tokens": 28095136.0,
|
|
"step": 12815
|
|
},
|
|
{
|
|
"entropy": 5.586997032165527,
|
|
"epoch": 1.2723302897975386,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004845912468988807,
|
|
"loss": 5.1461,
|
|
"mean_token_accuracy": 0.1671767935156822,
|
|
"num_tokens": 28104763.0,
|
|
"step": 12820
|
|
},
|
|
{
|
|
"entropy": 5.539486837387085,
|
|
"epoch": 1.2728265184597063,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004845783579120849,
|
|
"loss": 5.1947,
|
|
"mean_token_accuracy": 0.17052305340766907,
|
|
"num_tokens": 28115771.0,
|
|
"step": 12825
|
|
},
|
|
{
|
|
"entropy": 5.475801658630371,
|
|
"epoch": 1.2733227471218738,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004845654637281973,
|
|
"loss": 5.1209,
|
|
"mean_token_accuracy": 0.16984303593635558,
|
|
"num_tokens": 28128039.0,
|
|
"step": 12830
|
|
},
|
|
{
|
|
"entropy": 5.4931408882141115,
|
|
"epoch": 1.2738189757840412,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.00048455256434753774,
|
|
"loss": 5.1431,
|
|
"mean_token_accuracy": 0.17383018583059312,
|
|
"num_tokens": 28139163.0,
|
|
"step": 12835
|
|
},
|
|
{
|
|
"entropy": 5.526537895202637,
|
|
"epoch": 1.274315204446209,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004845396597704262,
|
|
"loss": 5.1763,
|
|
"mean_token_accuracy": 0.1646669551730156,
|
|
"num_tokens": 28150625.0,
|
|
"step": 12840
|
|
},
|
|
{
|
|
"entropy": 5.5661365509033205,
|
|
"epoch": 1.2748114331083764,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.00048452674999718257,
|
|
"loss": 5.2506,
|
|
"mean_token_accuracy": 0.16619838774204254,
|
|
"num_tokens": 28163072.0,
|
|
"step": 12845
|
|
},
|
|
{
|
|
"entropy": 5.602521657943726,
|
|
"epoch": 1.2753076617705439,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.00048451383502812705,
|
|
"loss": 5.2701,
|
|
"mean_token_accuracy": 0.162578547000885,
|
|
"num_tokens": 28174192.0,
|
|
"step": 12850
|
|
},
|
|
{
|
|
"entropy": 5.526638650894165,
|
|
"epoch": 1.2758038904327114,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00048450091486357987,
|
|
"loss": 5.141,
|
|
"mean_token_accuracy": 0.1731074795126915,
|
|
"num_tokens": 28184477.0,
|
|
"step": 12855
|
|
},
|
|
{
|
|
"entropy": 5.510159635543824,
|
|
"epoch": 1.2763001190948788,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.00048448798950386147,
|
|
"loss": 5.053,
|
|
"mean_token_accuracy": 0.16859374642372132,
|
|
"num_tokens": 28194552.0,
|
|
"step": 12860
|
|
},
|
|
{
|
|
"entropy": 5.533937597274781,
|
|
"epoch": 1.2767963477570463,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.00048447505894929233,
|
|
"loss": 5.2184,
|
|
"mean_token_accuracy": 0.168878173828125,
|
|
"num_tokens": 28205712.0,
|
|
"step": 12865
|
|
},
|
|
{
|
|
"entropy": 5.55695071220398,
|
|
"epoch": 1.277292576419214,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.00048446212320019306,
|
|
"loss": 5.1473,
|
|
"mean_token_accuracy": 0.17181674540042877,
|
|
"num_tokens": 28217246.0,
|
|
"step": 12870
|
|
},
|
|
{
|
|
"entropy": 5.537813138961792,
|
|
"epoch": 1.2777888050813815,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004844491822568846,
|
|
"loss": 5.1716,
|
|
"mean_token_accuracy": 0.16606325507164002,
|
|
"num_tokens": 28227933.0,
|
|
"step": 12875
|
|
},
|
|
{
|
|
"entropy": 5.523345565795898,
|
|
"epoch": 1.278285033743549,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.00048443623611968764,
|
|
"loss": 5.1863,
|
|
"mean_token_accuracy": 0.17389071732759476,
|
|
"num_tokens": 28239692.0,
|
|
"step": 12880
|
|
},
|
|
{
|
|
"entropy": 5.496372127532959,
|
|
"epoch": 1.2787812624057167,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00048442328478892334,
|
|
"loss": 5.1554,
|
|
"mean_token_accuracy": 0.17384358793497084,
|
|
"num_tokens": 28249815.0,
|
|
"step": 12885
|
|
},
|
|
{
|
|
"entropy": 5.605033826828003,
|
|
"epoch": 1.2792774910678841,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004844103282649128,
|
|
"loss": 5.1849,
|
|
"mean_token_accuracy": 0.1656591400504112,
|
|
"num_tokens": 28260385.0,
|
|
"step": 12890
|
|
},
|
|
{
|
|
"entropy": 5.528675222396851,
|
|
"epoch": 1.2797737197300516,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004843973665479774,
|
|
"loss": 5.2006,
|
|
"mean_token_accuracy": 0.16269042789936067,
|
|
"num_tokens": 28271858.0,
|
|
"step": 12895
|
|
},
|
|
{
|
|
"entropy": 5.5495401382446286,
|
|
"epoch": 1.280269948392219,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00048438439963843853,
|
|
"loss": 5.1878,
|
|
"mean_token_accuracy": 0.16631882786750793,
|
|
"num_tokens": 28283988.0,
|
|
"step": 12900
|
|
},
|
|
{
|
|
"entropy": 5.554886674880981,
|
|
"epoch": 1.2807661770543866,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00048437142753661775,
|
|
"loss": 5.2309,
|
|
"mean_token_accuracy": 0.16862109303474426,
|
|
"num_tokens": 28293281.0,
|
|
"step": 12905
|
|
},
|
|
{
|
|
"entropy": 5.606166076660156,
|
|
"epoch": 1.2812624057165543,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004843584502428367,
|
|
"loss": 5.1776,
|
|
"mean_token_accuracy": 0.16311835944652558,
|
|
"num_tokens": 28304468.0,
|
|
"step": 12910
|
|
},
|
|
{
|
|
"entropy": 5.464374637603759,
|
|
"epoch": 1.2817586343787217,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004843454677574173,
|
|
"loss": 5.1312,
|
|
"mean_token_accuracy": 0.17349398732185364,
|
|
"num_tokens": 28315864.0,
|
|
"step": 12915
|
|
},
|
|
{
|
|
"entropy": 5.518435478210449,
|
|
"epoch": 1.2822548630408892,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.00048433248008068123,
|
|
"loss": 5.1815,
|
|
"mean_token_accuracy": 0.170827279984951,
|
|
"num_tokens": 28327212.0,
|
|
"step": 12920
|
|
},
|
|
{
|
|
"entropy": 5.581830406188965,
|
|
"epoch": 1.282751091703057,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.00048431948721295085,
|
|
"loss": 5.1907,
|
|
"mean_token_accuracy": 0.17047163248062133,
|
|
"num_tokens": 28339256.0,
|
|
"step": 12925
|
|
},
|
|
{
|
|
"entropy": 5.577413654327392,
|
|
"epoch": 1.2832473203652244,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004843064891545482,
|
|
"loss": 5.2143,
|
|
"mean_token_accuracy": 0.16551536619663237,
|
|
"num_tokens": 28350196.0,
|
|
"step": 12930
|
|
},
|
|
{
|
|
"entropy": 5.52842082977295,
|
|
"epoch": 1.2837435490273919,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004842934859057956,
|
|
"loss": 5.1686,
|
|
"mean_token_accuracy": 0.16753441393375396,
|
|
"num_tokens": 28361241.0,
|
|
"step": 12935
|
|
},
|
|
{
|
|
"entropy": 5.627494764328003,
|
|
"epoch": 1.2842397776895593,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004842804774670156,
|
|
"loss": 5.3024,
|
|
"mean_token_accuracy": 0.16167117804288864,
|
|
"num_tokens": 28373369.0,
|
|
"step": 12940
|
|
},
|
|
{
|
|
"entropy": 5.568782329559326,
|
|
"epoch": 1.2847360063517268,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.00048426746383853066,
|
|
"loss": 5.127,
|
|
"mean_token_accuracy": 0.16794929206371306,
|
|
"num_tokens": 28384970.0,
|
|
"step": 12945
|
|
},
|
|
{
|
|
"entropy": 5.568664836883545,
|
|
"epoch": 1.2852322350138943,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00048425444502066354,
|
|
"loss": 5.1453,
|
|
"mean_token_accuracy": 0.16711928248405455,
|
|
"num_tokens": 28396469.0,
|
|
"step": 12950
|
|
},
|
|
{
|
|
"entropy": 5.528152179718018,
|
|
"epoch": 1.285728463676062,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00048424142101373706,
|
|
"loss": 5.195,
|
|
"mean_token_accuracy": 0.17144554257392883,
|
|
"num_tokens": 28406975.0,
|
|
"step": 12955
|
|
},
|
|
{
|
|
"entropy": 5.466510486602783,
|
|
"epoch": 1.2862246923382294,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.00048422839181807426,
|
|
"loss": 5.0706,
|
|
"mean_token_accuracy": 0.17831925451755523,
|
|
"num_tokens": 28418285.0,
|
|
"step": 12960
|
|
},
|
|
{
|
|
"entropy": 5.513025188446045,
|
|
"epoch": 1.286720921000397,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004842153574339982,
|
|
"loss": 5.2206,
|
|
"mean_token_accuracy": 0.16516928300261496,
|
|
"num_tokens": 28429769.0,
|
|
"step": 12965
|
|
},
|
|
{
|
|
"entropy": 5.506083345413208,
|
|
"epoch": 1.2872171496625646,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00048420231786183216,
|
|
"loss": 5.1595,
|
|
"mean_token_accuracy": 0.1747983694076538,
|
|
"num_tokens": 28441188.0,
|
|
"step": 12970
|
|
},
|
|
{
|
|
"entropy": 5.616161108016968,
|
|
"epoch": 1.287713378324732,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004841892731018994,
|
|
"loss": 5.2329,
|
|
"mean_token_accuracy": 0.16167017966508865,
|
|
"num_tokens": 28453504.0,
|
|
"step": 12975
|
|
},
|
|
{
|
|
"entropy": 5.578122282028199,
|
|
"epoch": 1.2882096069868996,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004841762231545233,
|
|
"loss": 5.1995,
|
|
"mean_token_accuracy": 0.17572660893201827,
|
|
"num_tokens": 28465930.0,
|
|
"step": 12980
|
|
},
|
|
{
|
|
"entropy": 5.494106912612915,
|
|
"epoch": 1.288705835649067,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00048416316802002776,
|
|
"loss": 5.1294,
|
|
"mean_token_accuracy": 0.1717277780175209,
|
|
"num_tokens": 28477803.0,
|
|
"step": 12985
|
|
},
|
|
{
|
|
"entropy": 5.583841276168823,
|
|
"epoch": 1.2892020643112345,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.00048415010769873625,
|
|
"loss": 5.233,
|
|
"mean_token_accuracy": 0.16571509540081025,
|
|
"num_tokens": 28488556.0,
|
|
"step": 12990
|
|
},
|
|
{
|
|
"entropy": 5.595171785354614,
|
|
"epoch": 1.2896982929734022,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004841370421909728,
|
|
"loss": 5.1394,
|
|
"mean_token_accuracy": 0.16938367933034898,
|
|
"num_tokens": 28499275.0,
|
|
"step": 12995
|
|
},
|
|
{
|
|
"entropy": 5.572546529769897,
|
|
"epoch": 1.2901945216355697,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.00048412397149706133,
|
|
"loss": 5.1668,
|
|
"mean_token_accuracy": 0.1695139303803444,
|
|
"num_tokens": 28511327.0,
|
|
"step": 13000
|
|
},
|
|
{
|
|
"entropy": 5.525767993927002,
|
|
"epoch": 1.2906907502977372,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.000484110895617326,
|
|
"loss": 5.1943,
|
|
"mean_token_accuracy": 0.1702712744474411,
|
|
"num_tokens": 28523937.0,
|
|
"step": 13005
|
|
},
|
|
{
|
|
"entropy": 5.451292610168457,
|
|
"epoch": 1.2911869789599046,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00048409781455209104,
|
|
"loss": 5.1005,
|
|
"mean_token_accuracy": 0.17020800113677978,
|
|
"num_tokens": 28534028.0,
|
|
"step": 13010
|
|
},
|
|
{
|
|
"entropy": 5.606750440597534,
|
|
"epoch": 1.2916832076220723,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004840847283016809,
|
|
"loss": 5.2013,
|
|
"mean_token_accuracy": 0.15455452352762222,
|
|
"num_tokens": 28545480.0,
|
|
"step": 13015
|
|
},
|
|
{
|
|
"entropy": 5.568125677108765,
|
|
"epoch": 1.2921794362842398,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00048407163686642,
|
|
"loss": 5.1594,
|
|
"mean_token_accuracy": 0.1739239364862442,
|
|
"num_tokens": 28555401.0,
|
|
"step": 13020
|
|
},
|
|
{
|
|
"entropy": 5.554666662216187,
|
|
"epoch": 1.2926756649464073,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000484058540246633,
|
|
"loss": 5.2059,
|
|
"mean_token_accuracy": 0.1698061391711235,
|
|
"num_tokens": 28565497.0,
|
|
"step": 13025
|
|
},
|
|
{
|
|
"entropy": 5.57824854850769,
|
|
"epoch": 1.2931718936085748,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004840454384426447,
|
|
"loss": 5.2922,
|
|
"mean_token_accuracy": 0.15998981446027755,
|
|
"num_tokens": 28576186.0,
|
|
"step": 13030
|
|
},
|
|
{
|
|
"entropy": 5.581986141204834,
|
|
"epoch": 1.2936681222707422,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004840323314547799,
|
|
"loss": 5.1656,
|
|
"mean_token_accuracy": 0.1692199230194092,
|
|
"num_tokens": 28586202.0,
|
|
"step": 13035
|
|
},
|
|
{
|
|
"entropy": 5.521803569793701,
|
|
"epoch": 1.29416435093291,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00048401921928336385,
|
|
"loss": 5.135,
|
|
"mean_token_accuracy": 0.16795178800821303,
|
|
"num_tokens": 28596486.0,
|
|
"step": 13040
|
|
},
|
|
{
|
|
"entropy": 5.572145986557007,
|
|
"epoch": 1.2946605795950774,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004840061019287215,
|
|
"loss": 5.1745,
|
|
"mean_token_accuracy": 0.1702177494764328,
|
|
"num_tokens": 28607934.0,
|
|
"step": 13045
|
|
},
|
|
{
|
|
"entropy": 5.610029458999634,
|
|
"epoch": 1.2951568082572449,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00048399297939117817,
|
|
"loss": 5.21,
|
|
"mean_token_accuracy": 0.16241537481546403,
|
|
"num_tokens": 28617673.0,
|
|
"step": 13050
|
|
},
|
|
{
|
|
"entropy": 5.622319078445434,
|
|
"epoch": 1.2956530369194126,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004839798516710593,
|
|
"loss": 5.2013,
|
|
"mean_token_accuracy": 0.16854730099439622,
|
|
"num_tokens": 28629811.0,
|
|
"step": 13055
|
|
},
|
|
{
|
|
"entropy": 5.602078294754028,
|
|
"epoch": 1.29614926558158,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004839667187686904,
|
|
"loss": 5.287,
|
|
"mean_token_accuracy": 0.16146073937416078,
|
|
"num_tokens": 28640371.0,
|
|
"step": 13060
|
|
},
|
|
{
|
|
"entropy": 5.5573790073394775,
|
|
"epoch": 1.2966454942437475,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004839535806843972,
|
|
"loss": 5.1969,
|
|
"mean_token_accuracy": 0.1657620057463646,
|
|
"num_tokens": 28651904.0,
|
|
"step": 13065
|
|
},
|
|
{
|
|
"entropy": 5.514594411849975,
|
|
"epoch": 1.297141722905915,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004839404374185054,
|
|
"loss": 5.1405,
|
|
"mean_token_accuracy": 0.1666380301117897,
|
|
"num_tokens": 28662241.0,
|
|
"step": 13070
|
|
},
|
|
{
|
|
"entropy": 5.5007569789886475,
|
|
"epoch": 1.2976379515680825,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.000483927288971341,
|
|
"loss": 5.099,
|
|
"mean_token_accuracy": 0.17499319612979888,
|
|
"num_tokens": 28672791.0,
|
|
"step": 13075
|
|
},
|
|
{
|
|
"entropy": 5.5438220500946045,
|
|
"epoch": 1.2981341802302502,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004839141353432301,
|
|
"loss": 5.2433,
|
|
"mean_token_accuracy": 0.1647740289568901,
|
|
"num_tokens": 28684218.0,
|
|
"step": 13080
|
|
},
|
|
{
|
|
"entropy": 5.5660436153411865,
|
|
"epoch": 1.2986304088924177,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004839009765344987,
|
|
"loss": 5.1839,
|
|
"mean_token_accuracy": 0.16340476721525193,
|
|
"num_tokens": 28694690.0,
|
|
"step": 13085
|
|
},
|
|
{
|
|
"entropy": 5.50096116065979,
|
|
"epoch": 1.2991266375545851,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.00048388781254547324,
|
|
"loss": 5.1645,
|
|
"mean_token_accuracy": 0.17385320067405702,
|
|
"num_tokens": 28705890.0,
|
|
"step": 13090
|
|
},
|
|
{
|
|
"entropy": 5.550221252441406,
|
|
"epoch": 1.2996228662167526,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00048387464337648026,
|
|
"loss": 5.1948,
|
|
"mean_token_accuracy": 0.16657274216413498,
|
|
"num_tokens": 28716935.0,
|
|
"step": 13095
|
|
},
|
|
{
|
|
"entropy": 5.6260992050170895,
|
|
"epoch": 1.3001190948789203,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.00048386146902784606,
|
|
"loss": 5.1926,
|
|
"mean_token_accuracy": 0.16981116384267808,
|
|
"num_tokens": 28728053.0,
|
|
"step": 13100
|
|
},
|
|
{
|
|
"entropy": 5.503963327407837,
|
|
"epoch": 1.3006153235410878,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00048384828949989757,
|
|
"loss": 5.1349,
|
|
"mean_token_accuracy": 0.17302269190549852,
|
|
"num_tokens": 28738940.0,
|
|
"step": 13105
|
|
},
|
|
{
|
|
"entropy": 5.5394786357879635,
|
|
"epoch": 1.3011115522032553,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00048383510479296153,
|
|
"loss": 5.2042,
|
|
"mean_token_accuracy": 0.1705235943198204,
|
|
"num_tokens": 28750259.0,
|
|
"step": 13110
|
|
},
|
|
{
|
|
"entropy": 5.572442293167114,
|
|
"epoch": 1.3016077808654227,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004838219149073649,
|
|
"loss": 5.1611,
|
|
"mean_token_accuracy": 0.17305178046226502,
|
|
"num_tokens": 28760119.0,
|
|
"step": 13115
|
|
},
|
|
{
|
|
"entropy": 5.591745042800904,
|
|
"epoch": 1.3021040095275902,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004838087198434347,
|
|
"loss": 5.1939,
|
|
"mean_token_accuracy": 0.16606315076351166,
|
|
"num_tokens": 28772022.0,
|
|
"step": 13120
|
|
},
|
|
{
|
|
"entropy": 5.582187938690185,
|
|
"epoch": 1.302600238189758,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004837955196014982,
|
|
"loss": 5.152,
|
|
"mean_token_accuracy": 0.16164156645536423,
|
|
"num_tokens": 28782935.0,
|
|
"step": 13125
|
|
},
|
|
{
|
|
"entropy": 5.586201763153076,
|
|
"epoch": 1.3030964668519254,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.00048378231418188275,
|
|
"loss": 5.2745,
|
|
"mean_token_accuracy": 0.1642395079135895,
|
|
"num_tokens": 28793604.0,
|
|
"step": 13130
|
|
},
|
|
{
|
|
"entropy": 5.56099305152893,
|
|
"epoch": 1.3035926955140928,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00048376910358491576,
|
|
"loss": 5.2239,
|
|
"mean_token_accuracy": 0.16122603565454482,
|
|
"num_tokens": 28803494.0,
|
|
"step": 13135
|
|
},
|
|
{
|
|
"entropy": 5.557882404327392,
|
|
"epoch": 1.3040889241762605,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004837558878109249,
|
|
"loss": 5.1895,
|
|
"mean_token_accuracy": 0.1622390329837799,
|
|
"num_tokens": 28816232.0,
|
|
"step": 13140
|
|
},
|
|
{
|
|
"entropy": 5.549216604232788,
|
|
"epoch": 1.304585152838428,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004837426668602378,
|
|
"loss": 5.1566,
|
|
"mean_token_accuracy": 0.17220099568367003,
|
|
"num_tokens": 28827056.0,
|
|
"step": 13145
|
|
},
|
|
{
|
|
"entropy": 5.509700107574463,
|
|
"epoch": 1.3050813815005955,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004837294407331825,
|
|
"loss": 5.1413,
|
|
"mean_token_accuracy": 0.17143516838550568,
|
|
"num_tokens": 28837217.0,
|
|
"step": 13150
|
|
},
|
|
{
|
|
"entropy": 5.472987222671509,
|
|
"epoch": 1.305577610162763,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004837162094300867,
|
|
"loss": 5.0571,
|
|
"mean_token_accuracy": 0.16928470134735107,
|
|
"num_tokens": 28846838.0,
|
|
"step": 13155
|
|
},
|
|
{
|
|
"entropy": 5.521747398376465,
|
|
"epoch": 1.3060738388249304,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004837029729512787,
|
|
"loss": 5.0973,
|
|
"mean_token_accuracy": 0.17382522225379943,
|
|
"num_tokens": 28856269.0,
|
|
"step": 13160
|
|
},
|
|
{
|
|
"entropy": 5.534066820144654,
|
|
"epoch": 1.306570067487098,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.00048368973129708667,
|
|
"loss": 5.1308,
|
|
"mean_token_accuracy": 0.17246145457029344,
|
|
"num_tokens": 28867142.0,
|
|
"step": 13165
|
|
},
|
|
{
|
|
"entropy": 5.549687194824219,
|
|
"epoch": 1.3070662961492656,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00048367648446783894,
|
|
"loss": 5.1031,
|
|
"mean_token_accuracy": 0.1684173509478569,
|
|
"num_tokens": 28877346.0,
|
|
"step": 13170
|
|
},
|
|
{
|
|
"entropy": 5.536315250396728,
|
|
"epoch": 1.307562524811433,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004836632324638642,
|
|
"loss": 5.1142,
|
|
"mean_token_accuracy": 0.16722597181797028,
|
|
"num_tokens": 28888425.0,
|
|
"step": 13175
|
|
},
|
|
{
|
|
"entropy": 5.506155681610108,
|
|
"epoch": 1.3080587534736006,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00048364997528549077,
|
|
"loss": 5.1404,
|
|
"mean_token_accuracy": 0.16865494847297668,
|
|
"num_tokens": 28899575.0,
|
|
"step": 13180
|
|
},
|
|
{
|
|
"entropy": 5.520729732513428,
|
|
"epoch": 1.3085549821357683,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.00048363671293304763,
|
|
"loss": 5.1346,
|
|
"mean_token_accuracy": 0.17176464796066285,
|
|
"num_tokens": 28910769.0,
|
|
"step": 13185
|
|
},
|
|
{
|
|
"entropy": 5.545792770385742,
|
|
"epoch": 1.3090512107979357,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004836234454068636,
|
|
"loss": 5.1282,
|
|
"mean_token_accuracy": 0.17846204042434693,
|
|
"num_tokens": 28921224.0,
|
|
"step": 13190
|
|
},
|
|
{
|
|
"entropy": 5.505349254608154,
|
|
"epoch": 1.3095474394601032,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00048361017270726764,
|
|
"loss": 5.1524,
|
|
"mean_token_accuracy": 0.16589900255203247,
|
|
"num_tokens": 28932585.0,
|
|
"step": 13195
|
|
},
|
|
{
|
|
"entropy": 5.492430877685547,
|
|
"epoch": 1.3100436681222707,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004835968948345889,
|
|
"loss": 5.1721,
|
|
"mean_token_accuracy": 0.170295087993145,
|
|
"num_tokens": 28943471.0,
|
|
"step": 13200
|
|
},
|
|
{
|
|
"entropy": 5.488894414901734,
|
|
"epoch": 1.3105398967844382,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.00048358361178915666,
|
|
"loss": 5.0959,
|
|
"mean_token_accuracy": 0.1799687534570694,
|
|
"num_tokens": 28956336.0,
|
|
"step": 13205
|
|
},
|
|
{
|
|
"entropy": 5.630616474151611,
|
|
"epoch": 1.3110361254466059,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004835703235713003,
|
|
"loss": 5.2232,
|
|
"mean_token_accuracy": 0.16556530743837355,
|
|
"num_tokens": 28966689.0,
|
|
"step": 13210
|
|
},
|
|
{
|
|
"entropy": 5.607818365097046,
|
|
"epoch": 1.3115323541087733,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00048355703018134935,
|
|
"loss": 5.32,
|
|
"mean_token_accuracy": 0.17158676236867904,
|
|
"num_tokens": 28978548.0,
|
|
"step": 13215
|
|
},
|
|
{
|
|
"entropy": 5.579065275192261,
|
|
"epoch": 1.3120285827709408,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004835437316196335,
|
|
"loss": 5.229,
|
|
"mean_token_accuracy": 0.16674552112817764,
|
|
"num_tokens": 28988899.0,
|
|
"step": 13220
|
|
},
|
|
{
|
|
"entropy": 5.509582948684693,
|
|
"epoch": 1.3125248114331085,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004835304278864824,
|
|
"loss": 5.154,
|
|
"mean_token_accuracy": 0.17324082553386688,
|
|
"num_tokens": 28999666.0,
|
|
"step": 13225
|
|
},
|
|
{
|
|
"entropy": 5.594459486007691,
|
|
"epoch": 1.313021040095276,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004835171189822261,
|
|
"loss": 5.1625,
|
|
"mean_token_accuracy": 0.16484105587005615,
|
|
"num_tokens": 29010185.0,
|
|
"step": 13230
|
|
},
|
|
{
|
|
"entropy": 5.535682582855225,
|
|
"epoch": 1.3135172687574435,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004835038049071945,
|
|
"loss": 5.1682,
|
|
"mean_token_accuracy": 0.16760471016168593,
|
|
"num_tokens": 29020761.0,
|
|
"step": 13235
|
|
},
|
|
{
|
|
"entropy": 5.585552406311035,
|
|
"epoch": 1.314013497419611,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004834904856617178,
|
|
"loss": 5.3137,
|
|
"mean_token_accuracy": 0.1671786919236183,
|
|
"num_tokens": 29031844.0,
|
|
"step": 13240
|
|
},
|
|
{
|
|
"entropy": 5.6389909267425535,
|
|
"epoch": 1.3145097260817784,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00048347716124612643,
|
|
"loss": 5.2712,
|
|
"mean_token_accuracy": 0.16106192171573638,
|
|
"num_tokens": 29043101.0,
|
|
"step": 13245
|
|
},
|
|
{
|
|
"entropy": 5.616788768768311,
|
|
"epoch": 1.3150059547439459,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004834638316607506,
|
|
"loss": 5.2044,
|
|
"mean_token_accuracy": 0.17278918176889418,
|
|
"num_tokens": 29054016.0,
|
|
"step": 13250
|
|
},
|
|
{
|
|
"entropy": 5.4927465438842775,
|
|
"epoch": 1.3155021834061136,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.00048345049690592105,
|
|
"loss": 5.1901,
|
|
"mean_token_accuracy": 0.16275459229946138,
|
|
"num_tokens": 29065127.0,
|
|
"step": 13255
|
|
},
|
|
{
|
|
"entropy": 5.581573867797852,
|
|
"epoch": 1.315998412068281,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.00048343715698196814,
|
|
"loss": 5.1544,
|
|
"mean_token_accuracy": 0.16777286380529405,
|
|
"num_tokens": 29075130.0,
|
|
"step": 13260
|
|
},
|
|
{
|
|
"entropy": 5.635171556472779,
|
|
"epoch": 1.3164946407304485,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004834238118892231,
|
|
"loss": 5.265,
|
|
"mean_token_accuracy": 0.16001363098621368,
|
|
"num_tokens": 29086405.0,
|
|
"step": 13265
|
|
},
|
|
{
|
|
"entropy": 5.600570344924927,
|
|
"epoch": 1.3169908693926162,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004834104616280165,
|
|
"loss": 5.2262,
|
|
"mean_token_accuracy": 0.1636667974293232,
|
|
"num_tokens": 29096945.0,
|
|
"step": 13270
|
|
},
|
|
{
|
|
"entropy": 5.600618743896485,
|
|
"epoch": 1.3174870980547837,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004833971061986796,
|
|
"loss": 5.2881,
|
|
"mean_token_accuracy": 0.1700609028339386,
|
|
"num_tokens": 29108275.0,
|
|
"step": 13275
|
|
},
|
|
{
|
|
"entropy": 5.555669546127319,
|
|
"epoch": 1.3179833267169512,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00048338374560154344,
|
|
"loss": 5.1227,
|
|
"mean_token_accuracy": 0.1661107361316681,
|
|
"num_tokens": 29118832.0,
|
|
"step": 13280
|
|
},
|
|
{
|
|
"entropy": 5.5101402759552,
|
|
"epoch": 1.3184795553791187,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004833703798369395,
|
|
"loss": 5.1365,
|
|
"mean_token_accuracy": 0.17052176594734192,
|
|
"num_tokens": 29130720.0,
|
|
"step": 13285
|
|
},
|
|
{
|
|
"entropy": 5.595566844940185,
|
|
"epoch": 1.3189757840412861,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004833570089051992,
|
|
"loss": 5.1475,
|
|
"mean_token_accuracy": 0.17092374265193938,
|
|
"num_tokens": 29140441.0,
|
|
"step": 13290
|
|
},
|
|
{
|
|
"entropy": 5.563398361206055,
|
|
"epoch": 1.3194720127034538,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00048334363280665393,
|
|
"loss": 5.2091,
|
|
"mean_token_accuracy": 0.16432921588420868,
|
|
"num_tokens": 29151544.0,
|
|
"step": 13295
|
|
},
|
|
{
|
|
"entropy": 5.595821905136108,
|
|
"epoch": 1.3199682413656213,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004833302515416355,
|
|
"loss": 5.2628,
|
|
"mean_token_accuracy": 0.16516421288251876,
|
|
"num_tokens": 29165475.0,
|
|
"step": 13300
|
|
},
|
|
{
|
|
"entropy": 5.523571920394898,
|
|
"epoch": 1.3204644700277888,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.00048331686511047584,
|
|
"loss": 5.1181,
|
|
"mean_token_accuracy": 0.165736648440361,
|
|
"num_tokens": 29177139.0,
|
|
"step": 13305
|
|
},
|
|
{
|
|
"entropy": 5.558342456817627,
|
|
"epoch": 1.3209606986899565,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00048330347351350676,
|
|
"loss": 5.1956,
|
|
"mean_token_accuracy": 0.17106725871562958,
|
|
"num_tokens": 29187812.0,
|
|
"step": 13310
|
|
},
|
|
{
|
|
"entropy": 5.482630729675293,
|
|
"epoch": 1.321456927352124,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00048329007675106036,
|
|
"loss": 5.0723,
|
|
"mean_token_accuracy": 0.17400735318660737,
|
|
"num_tokens": 29197932.0,
|
|
"step": 13315
|
|
},
|
|
{
|
|
"entropy": 5.491154193878174,
|
|
"epoch": 1.3219531560142914,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.00048327667482346895,
|
|
"loss": 5.1023,
|
|
"mean_token_accuracy": 0.17220928221940995,
|
|
"num_tokens": 29209529.0,
|
|
"step": 13320
|
|
},
|
|
{
|
|
"entropy": 5.505966997146606,
|
|
"epoch": 1.322449384676459,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004832632677310647,
|
|
"loss": 5.1667,
|
|
"mean_token_accuracy": 0.17061394900083543,
|
|
"num_tokens": 29219027.0,
|
|
"step": 13325
|
|
},
|
|
{
|
|
"entropy": 5.546169328689575,
|
|
"epoch": 1.3229456133386264,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.00048324985547418026,
|
|
"loss": 5.1817,
|
|
"mean_token_accuracy": 0.16532337069511413,
|
|
"num_tokens": 29229647.0,
|
|
"step": 13330
|
|
},
|
|
{
|
|
"entropy": 5.588563585281372,
|
|
"epoch": 1.3234418420007938,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004832364380531482,
|
|
"loss": 5.2094,
|
|
"mean_token_accuracy": 0.17632917761802674,
|
|
"num_tokens": 29240263.0,
|
|
"step": 13335
|
|
},
|
|
{
|
|
"entropy": 5.598335027694702,
|
|
"epoch": 1.3239380706629615,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.00048322301546830103,
|
|
"loss": 5.2309,
|
|
"mean_token_accuracy": 0.16411226987838745,
|
|
"num_tokens": 29251115.0,
|
|
"step": 13340
|
|
},
|
|
{
|
|
"entropy": 5.540830087661743,
|
|
"epoch": 1.324434299325129,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004832095877199718,
|
|
"loss": 5.1977,
|
|
"mean_token_accuracy": 0.165518681704998,
|
|
"num_tokens": 29261888.0,
|
|
"step": 13345
|
|
},
|
|
{
|
|
"entropy": 5.522991180419922,
|
|
"epoch": 1.3249305279872965,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.00048319615480849347,
|
|
"loss": 5.0953,
|
|
"mean_token_accuracy": 0.17710457146167755,
|
|
"num_tokens": 29271948.0,
|
|
"step": 13350
|
|
},
|
|
{
|
|
"entropy": 5.5838206768035885,
|
|
"epoch": 1.3254267566494642,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.00048318271673419914,
|
|
"loss": 5.1643,
|
|
"mean_token_accuracy": 0.16720860749483107,
|
|
"num_tokens": 29282449.0,
|
|
"step": 13355
|
|
},
|
|
{
|
|
"entropy": 5.556437206268311,
|
|
"epoch": 1.3259229853116317,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00048316927349742207,
|
|
"loss": 5.168,
|
|
"mean_token_accuracy": 0.16741278469562532,
|
|
"num_tokens": 29294280.0,
|
|
"step": 13360
|
|
},
|
|
{
|
|
"entropy": 5.566699028015137,
|
|
"epoch": 1.3264192139737991,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004831558250984955,
|
|
"loss": 5.161,
|
|
"mean_token_accuracy": 0.16971770375967027,
|
|
"num_tokens": 29305143.0,
|
|
"step": 13365
|
|
},
|
|
{
|
|
"entropy": 5.532807159423828,
|
|
"epoch": 1.3269154426359666,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00048314237153775303,
|
|
"loss": 5.0857,
|
|
"mean_token_accuracy": 0.17136003226041793,
|
|
"num_tokens": 29314697.0,
|
|
"step": 13370
|
|
},
|
|
{
|
|
"entropy": 5.483678770065308,
|
|
"epoch": 1.327411671298134,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004831289128155283,
|
|
"loss": 5.1114,
|
|
"mean_token_accuracy": 0.16558410972356796,
|
|
"num_tokens": 29325257.0,
|
|
"step": 13375
|
|
},
|
|
{
|
|
"entropy": 5.563903284072876,
|
|
"epoch": 1.3279078999603018,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.00048311544893215496,
|
|
"loss": 5.2156,
|
|
"mean_token_accuracy": 0.16387782990932465,
|
|
"num_tokens": 29335449.0,
|
|
"step": 13380
|
|
},
|
|
{
|
|
"entropy": 5.585507440567016,
|
|
"epoch": 1.3284041286224693,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.000483101979887967,
|
|
"loss": 5.2078,
|
|
"mean_token_accuracy": 0.16704815328121186,
|
|
"num_tokens": 29346898.0,
|
|
"step": 13385
|
|
},
|
|
{
|
|
"entropy": 5.61611499786377,
|
|
"epoch": 1.3289003572846367,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.00048308850568329825,
|
|
"loss": 5.1664,
|
|
"mean_token_accuracy": 0.16246731579303741,
|
|
"num_tokens": 29356118.0,
|
|
"step": 13390
|
|
},
|
|
{
|
|
"entropy": 5.564300537109375,
|
|
"epoch": 1.3293965859468042,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00048307502631848306,
|
|
"loss": 5.2394,
|
|
"mean_token_accuracy": 0.15915516018867493,
|
|
"num_tokens": 29367597.0,
|
|
"step": 13395
|
|
},
|
|
{
|
|
"entropy": 5.526433944702148,
|
|
"epoch": 1.329892814608972,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00048306154179385546,
|
|
"loss": 5.1232,
|
|
"mean_token_accuracy": 0.16847596168518067,
|
|
"num_tokens": 29377829.0,
|
|
"step": 13400
|
|
},
|
|
{
|
|
"entropy": 5.53847107887268,
|
|
"epoch": 1.3303890432711394,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004830480521097501,
|
|
"loss": 5.076,
|
|
"mean_token_accuracy": 0.17512914091348647,
|
|
"num_tokens": 29387945.0,
|
|
"step": 13405
|
|
},
|
|
{
|
|
"entropy": 5.48411340713501,
|
|
"epoch": 1.3308852719333069,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004830345572665012,
|
|
"loss": 5.0532,
|
|
"mean_token_accuracy": 0.17665792554616927,
|
|
"num_tokens": 29398269.0,
|
|
"step": 13410
|
|
},
|
|
{
|
|
"entropy": 5.576151895523071,
|
|
"epoch": 1.3313815005954743,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.00048302105726444366,
|
|
"loss": 5.2323,
|
|
"mean_token_accuracy": 0.16191613674163818,
|
|
"num_tokens": 29410946.0,
|
|
"step": 13415
|
|
},
|
|
{
|
|
"entropy": 5.498389053344726,
|
|
"epoch": 1.3318777292576418,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.00048300755210391205,
|
|
"loss": 5.0583,
|
|
"mean_token_accuracy": 0.17289605289697646,
|
|
"num_tokens": 29421770.0,
|
|
"step": 13420
|
|
},
|
|
{
|
|
"entropy": 5.563178682327271,
|
|
"epoch": 1.3323739579198095,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004829940417852415,
|
|
"loss": 5.2394,
|
|
"mean_token_accuracy": 0.16597738564014436,
|
|
"num_tokens": 29433717.0,
|
|
"step": 13425
|
|
},
|
|
{
|
|
"entropy": 5.485410499572754,
|
|
"epoch": 1.332870186581977,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004829805263087668,
|
|
"loss": 5.0662,
|
|
"mean_token_accuracy": 0.17547925263643266,
|
|
"num_tokens": 29444382.0,
|
|
"step": 13430
|
|
},
|
|
{
|
|
"entropy": 5.571080541610717,
|
|
"epoch": 1.3333664152441445,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00048296700567482324,
|
|
"loss": 5.1981,
|
|
"mean_token_accuracy": 0.16249519884586333,
|
|
"num_tokens": 29454680.0,
|
|
"step": 13435
|
|
},
|
|
{
|
|
"entropy": 5.621443223953247,
|
|
"epoch": 1.3338626439063122,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004829534798837461,
|
|
"loss": 5.1994,
|
|
"mean_token_accuracy": 0.16936905831098556,
|
|
"num_tokens": 29465065.0,
|
|
"step": 13440
|
|
},
|
|
{
|
|
"entropy": 5.583467960357666,
|
|
"epoch": 1.3343588725684796,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004829399489358707,
|
|
"loss": 5.1311,
|
|
"mean_token_accuracy": 0.16703284978866578,
|
|
"num_tokens": 29475704.0,
|
|
"step": 13445
|
|
},
|
|
{
|
|
"entropy": 5.513696384429932,
|
|
"epoch": 1.334855101230647,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004829264128315326,
|
|
"loss": 5.1712,
|
|
"mean_token_accuracy": 0.16665140837430953,
|
|
"num_tokens": 29486418.0,
|
|
"step": 13450
|
|
},
|
|
{
|
|
"entropy": 5.606047058105469,
|
|
"epoch": 1.3353513298928146,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004829128715710676,
|
|
"loss": 5.2418,
|
|
"mean_token_accuracy": 0.1586636483669281,
|
|
"num_tokens": 29498939.0,
|
|
"step": 13455
|
|
},
|
|
{
|
|
"entropy": 5.550904178619385,
|
|
"epoch": 1.335847558554982,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004828993251548114,
|
|
"loss": 5.0857,
|
|
"mean_token_accuracy": 0.17292490005493164,
|
|
"num_tokens": 29508525.0,
|
|
"step": 13460
|
|
},
|
|
{
|
|
"entropy": 5.563429927825927,
|
|
"epoch": 1.3363437872171495,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004828857735830999,
|
|
"loss": 5.1955,
|
|
"mean_token_accuracy": 0.17441526651382447,
|
|
"num_tokens": 29519962.0,
|
|
"step": 13465
|
|
},
|
|
{
|
|
"entropy": 5.532764673233032,
|
|
"epoch": 1.3368400158793172,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004828722168562691,
|
|
"loss": 5.1508,
|
|
"mean_token_accuracy": 0.16437328159809111,
|
|
"num_tokens": 29529586.0,
|
|
"step": 13470
|
|
},
|
|
{
|
|
"entropy": 5.536051225662232,
|
|
"epoch": 1.3373362445414847,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004828586549746553,
|
|
"loss": 5.2257,
|
|
"mean_token_accuracy": 0.16071384251117707,
|
|
"num_tokens": 29540670.0,
|
|
"step": 13475
|
|
},
|
|
{
|
|
"entropy": 5.555367660522461,
|
|
"epoch": 1.3378324732036522,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004828450879385947,
|
|
"loss": 5.1919,
|
|
"mean_token_accuracy": 0.16150649785995483,
|
|
"num_tokens": 29551484.0,
|
|
"step": 13480
|
|
},
|
|
{
|
|
"entropy": 5.580913972854614,
|
|
"epoch": 1.3383287018658199,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004828315157484239,
|
|
"loss": 5.1321,
|
|
"mean_token_accuracy": 0.16958364099264145,
|
|
"num_tokens": 29561596.0,
|
|
"step": 13485
|
|
},
|
|
{
|
|
"entropy": 5.588375091552734,
|
|
"epoch": 1.3388249305279873,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004828179384044793,
|
|
"loss": 5.1529,
|
|
"mean_token_accuracy": 0.16749670803546907,
|
|
"num_tokens": 29572837.0,
|
|
"step": 13490
|
|
},
|
|
{
|
|
"entropy": 5.527883672714234,
|
|
"epoch": 1.3393211591901548,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.00048280435590709756,
|
|
"loss": 5.1158,
|
|
"mean_token_accuracy": 0.16936204582452774,
|
|
"num_tokens": 29584095.0,
|
|
"step": 13495
|
|
},
|
|
{
|
|
"entropy": 5.551968097686768,
|
|
"epoch": 1.3398173878523223,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004827907682566157,
|
|
"loss": 5.1733,
|
|
"mean_token_accuracy": 0.16764944046735764,
|
|
"num_tokens": 29594903.0,
|
|
"step": 13500
|
|
},
|
|
{
|
|
"entropy": 5.600491905212403,
|
|
"epoch": 1.3403136165144898,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004827771754533704,
|
|
"loss": 5.1266,
|
|
"mean_token_accuracy": 0.17046167999505996,
|
|
"num_tokens": 29605199.0,
|
|
"step": 13505
|
|
},
|
|
{
|
|
"entropy": 5.615497827529907,
|
|
"epoch": 1.3408098451766575,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00048276357749769895,
|
|
"loss": 5.3054,
|
|
"mean_token_accuracy": 0.16074269488453866,
|
|
"num_tokens": 29617535.0,
|
|
"step": 13510
|
|
},
|
|
{
|
|
"entropy": 5.54388952255249,
|
|
"epoch": 1.341306073838825,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00048274997438993845,
|
|
"loss": 5.1119,
|
|
"mean_token_accuracy": 0.1747731849551201,
|
|
"num_tokens": 29628227.0,
|
|
"step": 13515
|
|
},
|
|
{
|
|
"entropy": 5.582678985595703,
|
|
"epoch": 1.3418023025009924,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00048273636613042626,
|
|
"loss": 5.2316,
|
|
"mean_token_accuracy": 0.1667240098118782,
|
|
"num_tokens": 29639112.0,
|
|
"step": 13520
|
|
},
|
|
{
|
|
"entropy": 5.500787687301636,
|
|
"epoch": 1.3422985311631601,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004827227527194998,
|
|
"loss": 5.1145,
|
|
"mean_token_accuracy": 0.16373225003480912,
|
|
"num_tokens": 29650768.0,
|
|
"step": 13525
|
|
},
|
|
{
|
|
"entropy": 5.563147640228271,
|
|
"epoch": 1.3427947598253276,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004827091341574967,
|
|
"loss": 5.2197,
|
|
"mean_token_accuracy": 0.17597340792417526,
|
|
"num_tokens": 29662388.0,
|
|
"step": 13530
|
|
},
|
|
{
|
|
"entropy": 5.548911285400391,
|
|
"epoch": 1.343290988487495,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004826955104447546,
|
|
"loss": 5.1121,
|
|
"mean_token_accuracy": 0.1745942071080208,
|
|
"num_tokens": 29672231.0,
|
|
"step": 13535
|
|
},
|
|
{
|
|
"entropy": 5.5248106002807615,
|
|
"epoch": 1.3437872171496625,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004826818815816114,
|
|
"loss": 5.1568,
|
|
"mean_token_accuracy": 0.1730260968208313,
|
|
"num_tokens": 29683019.0,
|
|
"step": 13540
|
|
},
|
|
{
|
|
"entropy": 5.5459236145019535,
|
|
"epoch": 1.34428344581183,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00048266824756840513,
|
|
"loss": 5.1853,
|
|
"mean_token_accuracy": 0.1690635859966278,
|
|
"num_tokens": 29694233.0,
|
|
"step": 13545
|
|
},
|
|
{
|
|
"entropy": 5.594381952285767,
|
|
"epoch": 1.3447796744739975,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004826546084054737,
|
|
"loss": 5.2073,
|
|
"mean_token_accuracy": 0.169435915350914,
|
|
"num_tokens": 29704023.0,
|
|
"step": 13550
|
|
},
|
|
{
|
|
"entropy": 5.6499780178070065,
|
|
"epoch": 1.3452759031361652,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004826409640931555,
|
|
"loss": 5.302,
|
|
"mean_token_accuracy": 0.16322341114282607,
|
|
"num_tokens": 29715407.0,
|
|
"step": 13555
|
|
},
|
|
{
|
|
"entropy": 5.49336805343628,
|
|
"epoch": 1.3457721317983327,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.00048262731463178884,
|
|
"loss": 5.1254,
|
|
"mean_token_accuracy": 0.1686178997159004,
|
|
"num_tokens": 29726223.0,
|
|
"step": 13560
|
|
},
|
|
{
|
|
"entropy": 5.51274528503418,
|
|
"epoch": 1.3462683604605001,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004826136600217121,
|
|
"loss": 5.0545,
|
|
"mean_token_accuracy": 0.1747345432639122,
|
|
"num_tokens": 29735850.0,
|
|
"step": 13565
|
|
},
|
|
{
|
|
"entropy": 5.562219142913818,
|
|
"epoch": 1.3467645891226678,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.000482600000263264,
|
|
"loss": 5.2147,
|
|
"mean_token_accuracy": 0.1668240875005722,
|
|
"num_tokens": 29747381.0,
|
|
"step": 13570
|
|
},
|
|
{
|
|
"entropy": 5.613744258880615,
|
|
"epoch": 1.3472608177848353,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004825863353567832,
|
|
"loss": 5.2523,
|
|
"mean_token_accuracy": 0.1672103449702263,
|
|
"num_tokens": 29758440.0,
|
|
"step": 13575
|
|
},
|
|
{
|
|
"entropy": 5.51864185333252,
|
|
"epoch": 1.3477570464470028,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00048257266530260865,
|
|
"loss": 5.1052,
|
|
"mean_token_accuracy": 0.17141530215740203,
|
|
"num_tokens": 29770606.0,
|
|
"step": 13580
|
|
},
|
|
{
|
|
"entropy": 5.505066061019898,
|
|
"epoch": 1.3482532751091703,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004825589901010792,
|
|
"loss": 5.1694,
|
|
"mean_token_accuracy": 0.17213753908872603,
|
|
"num_tokens": 29781469.0,
|
|
"step": 13585
|
|
},
|
|
{
|
|
"entropy": 5.534030342102051,
|
|
"epoch": 1.3487495037713377,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004825453097525341,
|
|
"loss": 5.2354,
|
|
"mean_token_accuracy": 0.17037178575992584,
|
|
"num_tokens": 29792847.0,
|
|
"step": 13590
|
|
},
|
|
{
|
|
"entropy": 5.569099855422974,
|
|
"epoch": 1.3492457324335054,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00048253162425731253,
|
|
"loss": 5.1555,
|
|
"mean_token_accuracy": 0.16667943447828293,
|
|
"num_tokens": 29802784.0,
|
|
"step": 13595
|
|
},
|
|
{
|
|
"entropy": 5.613606882095337,
|
|
"epoch": 1.349741961095673,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004825179336157539,
|
|
"loss": 5.1659,
|
|
"mean_token_accuracy": 0.16834889203310013,
|
|
"num_tokens": 29812849.0,
|
|
"step": 13600
|
|
},
|
|
{
|
|
"entropy": 5.5284843921661375,
|
|
"epoch": 1.3502381897578404,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00048250423782819765,
|
|
"loss": 5.1411,
|
|
"mean_token_accuracy": 0.1682274267077446,
|
|
"num_tokens": 29823495.0,
|
|
"step": 13605
|
|
},
|
|
{
|
|
"entropy": 5.552795934677124,
|
|
"epoch": 1.350734418420008,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004824905368949834,
|
|
"loss": 5.1903,
|
|
"mean_token_accuracy": 0.16858471184968948,
|
|
"num_tokens": 29835295.0,
|
|
"step": 13610
|
|
},
|
|
{
|
|
"entropy": 5.529150724411011,
|
|
"epoch": 1.3512306470821756,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004824768308164509,
|
|
"loss": 5.1193,
|
|
"mean_token_accuracy": 0.17711340337991716,
|
|
"num_tokens": 29845747.0,
|
|
"step": 13615
|
|
},
|
|
{
|
|
"entropy": 5.5408612251281735,
|
|
"epoch": 1.351726875744343,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004824631195929402,
|
|
"loss": 5.1786,
|
|
"mean_token_accuracy": 0.17181971967220305,
|
|
"num_tokens": 29857111.0,
|
|
"step": 13620
|
|
},
|
|
{
|
|
"entropy": 5.537961673736572,
|
|
"epoch": 1.3522231044065105,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004824494032247911,
|
|
"loss": 5.1826,
|
|
"mean_token_accuracy": 0.1715356096625328,
|
|
"num_tokens": 29866919.0,
|
|
"step": 13625
|
|
},
|
|
{
|
|
"entropy": 5.5413860321044925,
|
|
"epoch": 1.352719333068678,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004824356817123439,
|
|
"loss": 5.1216,
|
|
"mean_token_accuracy": 0.16942113339900972,
|
|
"num_tokens": 29878631.0,
|
|
"step": 13630
|
|
},
|
|
{
|
|
"entropy": 5.544751691818237,
|
|
"epoch": 1.3532155617308455,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.00048242195505593865,
|
|
"loss": 5.1539,
|
|
"mean_token_accuracy": 0.16985422968864441,
|
|
"num_tokens": 29890809.0,
|
|
"step": 13635
|
|
},
|
|
{
|
|
"entropy": 5.5777698993682865,
|
|
"epoch": 1.3537117903930131,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00048240822325591596,
|
|
"loss": 5.2335,
|
|
"mean_token_accuracy": 0.16819322258234023,
|
|
"num_tokens": 29901789.0,
|
|
"step": 13640
|
|
},
|
|
{
|
|
"entropy": 5.528992795944214,
|
|
"epoch": 1.3542080190551806,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004823944863126162,
|
|
"loss": 5.152,
|
|
"mean_token_accuracy": 0.16734090596437454,
|
|
"num_tokens": 29912576.0,
|
|
"step": 13645
|
|
},
|
|
{
|
|
"entropy": 5.6027082920074465,
|
|
"epoch": 1.354704247717348,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004823807442263801,
|
|
"loss": 5.2427,
|
|
"mean_token_accuracy": 0.1628077208995819,
|
|
"num_tokens": 29924076.0,
|
|
"step": 13650
|
|
},
|
|
{
|
|
"entropy": 5.54388427734375,
|
|
"epoch": 1.3552004763795158,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00048236699699754845,
|
|
"loss": 5.1475,
|
|
"mean_token_accuracy": 0.16844340562820434,
|
|
"num_tokens": 29935854.0,
|
|
"step": 13655
|
|
},
|
|
{
|
|
"entropy": 5.560317659378052,
|
|
"epoch": 1.3556967050416833,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.000482353244626462,
|
|
"loss": 5.1113,
|
|
"mean_token_accuracy": 0.1707082286477089,
|
|
"num_tokens": 29946389.0,
|
|
"step": 13660
|
|
},
|
|
{
|
|
"entropy": 5.56740894317627,
|
|
"epoch": 1.3561929337038507,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00048233948711346196,
|
|
"loss": 5.1661,
|
|
"mean_token_accuracy": 0.16355991512537002,
|
|
"num_tokens": 29958170.0,
|
|
"step": 13665
|
|
},
|
|
{
|
|
"entropy": 5.475707769393921,
|
|
"epoch": 1.3566891623660182,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.00048232572445888945,
|
|
"loss": 5.0695,
|
|
"mean_token_accuracy": 0.16982268244028093,
|
|
"num_tokens": 29969067.0,
|
|
"step": 13670
|
|
},
|
|
{
|
|
"entropy": 5.59179310798645,
|
|
"epoch": 1.3571853910281857,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004823119566630857,
|
|
"loss": 5.2087,
|
|
"mean_token_accuracy": 0.16459728628396988,
|
|
"num_tokens": 29979727.0,
|
|
"step": 13675
|
|
},
|
|
{
|
|
"entropy": 5.613336992263794,
|
|
"epoch": 1.3576816196903534,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00048229818372639216,
|
|
"loss": 5.1716,
|
|
"mean_token_accuracy": 0.17122318595647812,
|
|
"num_tokens": 29989397.0,
|
|
"step": 13680
|
|
},
|
|
{
|
|
"entropy": 5.461426305770874,
|
|
"epoch": 1.3581778483525209,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.00048228440564915026,
|
|
"loss": 5.0893,
|
|
"mean_token_accuracy": 0.16765320748090745,
|
|
"num_tokens": 29999415.0,
|
|
"step": 13685
|
|
},
|
|
{
|
|
"entropy": 5.517765140533447,
|
|
"epoch": 1.3586740770146883,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00048227062243170186,
|
|
"loss": 5.1292,
|
|
"mean_token_accuracy": 0.17012468576431275,
|
|
"num_tokens": 30010277.0,
|
|
"step": 13690
|
|
},
|
|
{
|
|
"entropy": 5.47207727432251,
|
|
"epoch": 1.3591703056768558,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004822568340743886,
|
|
"loss": 5.0397,
|
|
"mean_token_accuracy": 0.17928745299577714,
|
|
"num_tokens": 30020684.0,
|
|
"step": 13695
|
|
},
|
|
{
|
|
"entropy": 5.622174072265625,
|
|
"epoch": 1.3596665343390235,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004822430405775525,
|
|
"loss": 5.2378,
|
|
"mean_token_accuracy": 0.16153559684753419,
|
|
"num_tokens": 30030916.0,
|
|
"step": 13700
|
|
},
|
|
{
|
|
"entropy": 5.582497549057007,
|
|
"epoch": 1.360162763001191,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004822292419415355,
|
|
"loss": 5.1678,
|
|
"mean_token_accuracy": 0.16640244275331498,
|
|
"num_tokens": 30041140.0,
|
|
"step": 13705
|
|
},
|
|
{
|
|
"entropy": 5.500198459625244,
|
|
"epoch": 1.3606589916633585,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.00048221543816667984,
|
|
"loss": 5.1297,
|
|
"mean_token_accuracy": 0.17232650220394136,
|
|
"num_tokens": 30052765.0,
|
|
"step": 13710
|
|
},
|
|
{
|
|
"entropy": 5.496519613265991,
|
|
"epoch": 1.361155220325526,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00048220162925332786,
|
|
"loss": 5.15,
|
|
"mean_token_accuracy": 0.1708048865199089,
|
|
"num_tokens": 30062511.0,
|
|
"step": 13715
|
|
},
|
|
{
|
|
"entropy": 5.657969188690186,
|
|
"epoch": 1.3616514489876934,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.000482187815201822,
|
|
"loss": 5.2364,
|
|
"mean_token_accuracy": 0.1670539304614067,
|
|
"num_tokens": 30073404.0,
|
|
"step": 13720
|
|
},
|
|
{
|
|
"entropy": 5.501927328109741,
|
|
"epoch": 1.362147677649861,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.00048217399601250464,
|
|
"loss": 5.0816,
|
|
"mean_token_accuracy": 0.17502516508102417,
|
|
"num_tokens": 30084978.0,
|
|
"step": 13725
|
|
},
|
|
{
|
|
"entropy": 5.55900616645813,
|
|
"epoch": 1.3626439063120286,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004821601716857187,
|
|
"loss": 5.1526,
|
|
"mean_token_accuracy": 0.17103137522935868,
|
|
"num_tokens": 30094498.0,
|
|
"step": 13730
|
|
},
|
|
{
|
|
"entropy": 5.536233186721802,
|
|
"epoch": 1.363140134974196,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00048214634222180686,
|
|
"loss": 5.1838,
|
|
"mean_token_accuracy": 0.17339248061180115,
|
|
"num_tokens": 30104545.0,
|
|
"step": 13735
|
|
},
|
|
{
|
|
"entropy": 5.584895992279053,
|
|
"epoch": 1.3636363636363638,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004821325076211121,
|
|
"loss": 5.2483,
|
|
"mean_token_accuracy": 0.16983823627233505,
|
|
"num_tokens": 30114863.0,
|
|
"step": 13740
|
|
},
|
|
{
|
|
"entropy": 5.584507989883423,
|
|
"epoch": 1.3641325922985312,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00048211866788397753,
|
|
"loss": 5.1579,
|
|
"mean_token_accuracy": 0.16757967472076415,
|
|
"num_tokens": 30125101.0,
|
|
"step": 13745
|
|
},
|
|
{
|
|
"entropy": 5.562633943557739,
|
|
"epoch": 1.3646288209606987,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004821048230107462,
|
|
"loss": 5.2232,
|
|
"mean_token_accuracy": 0.16689809411764145,
|
|
"num_tokens": 30135081.0,
|
|
"step": 13750
|
|
},
|
|
{
|
|
"entropy": 5.663543605804444,
|
|
"epoch": 1.3651250496228662,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004820909730017616,
|
|
"loss": 5.2439,
|
|
"mean_token_accuracy": 0.1603972226381302,
|
|
"num_tokens": 30147169.0,
|
|
"step": 13755
|
|
},
|
|
{
|
|
"entropy": 5.575499391555786,
|
|
"epoch": 1.3656212782850337,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00048207711785736707,
|
|
"loss": 5.0667,
|
|
"mean_token_accuracy": 0.17057625353336334,
|
|
"num_tokens": 30157523.0,
|
|
"step": 13760
|
|
},
|
|
{
|
|
"entropy": 5.469462966918945,
|
|
"epoch": 1.3661175069472011,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.00048206325757790624,
|
|
"loss": 5.1463,
|
|
"mean_token_accuracy": 0.1721128538250923,
|
|
"num_tokens": 30168313.0,
|
|
"step": 13765
|
|
},
|
|
{
|
|
"entropy": 5.427523851394653,
|
|
"epoch": 1.3666137356093688,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00048204939216372285,
|
|
"loss": 5.1029,
|
|
"mean_token_accuracy": 0.17009972929954528,
|
|
"num_tokens": 30179173.0,
|
|
"step": 13770
|
|
},
|
|
{
|
|
"entropy": 5.586271905899048,
|
|
"epoch": 1.3671099642715363,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004820355216151607,
|
|
"loss": 5.1943,
|
|
"mean_token_accuracy": 0.16727735698223115,
|
|
"num_tokens": 30191666.0,
|
|
"step": 13775
|
|
},
|
|
{
|
|
"entropy": 5.627197122573852,
|
|
"epoch": 1.3676061929337038,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.00048202164593256363,
|
|
"loss": 5.1465,
|
|
"mean_token_accuracy": 0.16737007945775986,
|
|
"num_tokens": 30202752.0,
|
|
"step": 13780
|
|
},
|
|
{
|
|
"entropy": 5.533715486526489,
|
|
"epoch": 1.3681024215958715,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00048200776511627585,
|
|
"loss": 5.1701,
|
|
"mean_token_accuracy": 0.17021922171115875,
|
|
"num_tokens": 30213127.0,
|
|
"step": 13785
|
|
},
|
|
{
|
|
"entropy": 5.558139133453369,
|
|
"epoch": 1.368598650258039,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004819938791666416,
|
|
"loss": 5.2081,
|
|
"mean_token_accuracy": 0.1704016551375389,
|
|
"num_tokens": 30224782.0,
|
|
"step": 13790
|
|
},
|
|
{
|
|
"entropy": 5.539986085891724,
|
|
"epoch": 1.3690948789202064,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.00048197998808400524,
|
|
"loss": 5.2144,
|
|
"mean_token_accuracy": 0.17109808027744294,
|
|
"num_tokens": 30235129.0,
|
|
"step": 13795
|
|
},
|
|
{
|
|
"entropy": 5.587945127487183,
|
|
"epoch": 1.369591107582374,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004819660918687111,
|
|
"loss": 5.2157,
|
|
"mean_token_accuracy": 0.16336526721715927,
|
|
"num_tokens": 30247304.0,
|
|
"step": 13800
|
|
},
|
|
{
|
|
"entropy": 5.543242025375366,
|
|
"epoch": 1.3700873362445414,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004819521905211039,
|
|
"loss": 5.0962,
|
|
"mean_token_accuracy": 0.17269397526979446,
|
|
"num_tokens": 30257900.0,
|
|
"step": 13805
|
|
},
|
|
{
|
|
"entropy": 5.602170324325561,
|
|
"epoch": 1.370583564906709,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.00048193828404152826,
|
|
"loss": 5.2192,
|
|
"mean_token_accuracy": 0.1688413664698601,
|
|
"num_tokens": 30269741.0,
|
|
"step": 13810
|
|
},
|
|
{
|
|
"entropy": 5.543507671356201,
|
|
"epoch": 1.3710797935688765,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004819243724303291,
|
|
"loss": 5.2156,
|
|
"mean_token_accuracy": 0.16407763957977295,
|
|
"num_tokens": 30279382.0,
|
|
"step": 13815
|
|
},
|
|
{
|
|
"entropy": 5.5421445846557615,
|
|
"epoch": 1.371576022231044,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00048191045568785144,
|
|
"loss": 5.1928,
|
|
"mean_token_accuracy": 0.1694382518529892,
|
|
"num_tokens": 30289837.0,
|
|
"step": 13820
|
|
},
|
|
{
|
|
"entropy": 5.526802396774292,
|
|
"epoch": 1.3720722508932117,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.00048189653381444024,
|
|
"loss": 5.1353,
|
|
"mean_token_accuracy": 0.17473276555538178,
|
|
"num_tokens": 30302138.0,
|
|
"step": 13825
|
|
},
|
|
{
|
|
"entropy": 5.57561764717102,
|
|
"epoch": 1.3725684795553792,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004818826068104409,
|
|
"loss": 5.2207,
|
|
"mean_token_accuracy": 0.16866065412759781,
|
|
"num_tokens": 30313623.0,
|
|
"step": 13830
|
|
},
|
|
{
|
|
"entropy": 5.564894104003907,
|
|
"epoch": 1.3730647082175467,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004818686746761987,
|
|
"loss": 5.1698,
|
|
"mean_token_accuracy": 0.1662436842918396,
|
|
"num_tokens": 30324533.0,
|
|
"step": 13835
|
|
},
|
|
{
|
|
"entropy": 5.571521854400634,
|
|
"epoch": 1.3735609368797141,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004818547374120591,
|
|
"loss": 5.265,
|
|
"mean_token_accuracy": 0.15774538218975068,
|
|
"num_tokens": 30335819.0,
|
|
"step": 13840
|
|
},
|
|
{
|
|
"entropy": 5.550901889801025,
|
|
"epoch": 1.3740571655418816,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004818407950183678,
|
|
"loss": 5.1465,
|
|
"mean_token_accuracy": 0.1719643294811249,
|
|
"num_tokens": 30345947.0,
|
|
"step": 13845
|
|
},
|
|
{
|
|
"entropy": 5.523833751678467,
|
|
"epoch": 1.374553394204049,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004818268474954704,
|
|
"loss": 5.1193,
|
|
"mean_token_accuracy": 0.17062321901321412,
|
|
"num_tokens": 30356972.0,
|
|
"step": 13850
|
|
},
|
|
{
|
|
"entropy": 5.599646186828613,
|
|
"epoch": 1.3750496228662168,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004818128948437129,
|
|
"loss": 5.2143,
|
|
"mean_token_accuracy": 0.1654777243733406,
|
|
"num_tokens": 30368414.0,
|
|
"step": 13855
|
|
},
|
|
{
|
|
"entropy": 5.581432962417603,
|
|
"epoch": 1.3755458515283843,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004817989370634412,
|
|
"loss": 5.142,
|
|
"mean_token_accuracy": 0.17397802621126174,
|
|
"num_tokens": 30379141.0,
|
|
"step": 13860
|
|
},
|
|
{
|
|
"entropy": 5.524407482147216,
|
|
"epoch": 1.3760420801905517,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00048178497415500153,
|
|
"loss": 5.0933,
|
|
"mean_token_accuracy": 0.1796994298696518,
|
|
"num_tokens": 30388985.0,
|
|
"step": 13865
|
|
},
|
|
{
|
|
"entropy": 5.506087160110473,
|
|
"epoch": 1.3765383088527194,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004817710061187401,
|
|
"loss": 5.1407,
|
|
"mean_token_accuracy": 0.17578205913305284,
|
|
"num_tokens": 30399599.0,
|
|
"step": 13870
|
|
},
|
|
{
|
|
"entropy": 5.57473669052124,
|
|
"epoch": 1.377034537514887,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.00048175703295500323,
|
|
"loss": 5.229,
|
|
"mean_token_accuracy": 0.1658189907670021,
|
|
"num_tokens": 30411143.0,
|
|
"step": 13875
|
|
},
|
|
{
|
|
"entropy": 5.628584384918213,
|
|
"epoch": 1.3775307661770544,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.00048174305466413755,
|
|
"loss": 5.1992,
|
|
"mean_token_accuracy": 0.1683528795838356,
|
|
"num_tokens": 30422339.0,
|
|
"step": 13880
|
|
},
|
|
{
|
|
"entropy": 5.548181581497192,
|
|
"epoch": 1.3780269948392219,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.00048172907124648947,
|
|
"loss": 5.1343,
|
|
"mean_token_accuracy": 0.17108379751443864,
|
|
"num_tokens": 30432588.0,
|
|
"step": 13885
|
|
},
|
|
{
|
|
"entropy": 5.568365097045898,
|
|
"epoch": 1.3785232235013893,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004817150827024059,
|
|
"loss": 5.1966,
|
|
"mean_token_accuracy": 0.1727196380496025,
|
|
"num_tokens": 30442272.0,
|
|
"step": 13890
|
|
},
|
|
{
|
|
"entropy": 5.5229079246521,
|
|
"epoch": 1.379019452163557,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004817010890322338,
|
|
"loss": 5.1108,
|
|
"mean_token_accuracy": 0.1727242201566696,
|
|
"num_tokens": 30453142.0,
|
|
"step": 13895
|
|
},
|
|
{
|
|
"entropy": 5.565318965911866,
|
|
"epoch": 1.3795156808257245,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00048168709023632006,
|
|
"loss": 5.2039,
|
|
"mean_token_accuracy": 0.16730950325727462,
|
|
"num_tokens": 30465136.0,
|
|
"step": 13900
|
|
},
|
|
{
|
|
"entropy": 5.606248474121093,
|
|
"epoch": 1.380011909487892,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00048167308631501184,
|
|
"loss": 5.1513,
|
|
"mean_token_accuracy": 0.1690399691462517,
|
|
"num_tokens": 30476511.0,
|
|
"step": 13905
|
|
},
|
|
{
|
|
"entropy": 5.560820484161377,
|
|
"epoch": 1.3805081381500597,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00048165907726865643,
|
|
"loss": 5.2592,
|
|
"mean_token_accuracy": 0.16012985557317733,
|
|
"num_tokens": 30486547.0,
|
|
"step": 13910
|
|
},
|
|
{
|
|
"entropy": 5.591954755783081,
|
|
"epoch": 1.3810043668122272,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004816450630976012,
|
|
"loss": 5.2104,
|
|
"mean_token_accuracy": 0.17533600628376006,
|
|
"num_tokens": 30496163.0,
|
|
"step": 13915
|
|
},
|
|
{
|
|
"entropy": 5.546323442459107,
|
|
"epoch": 1.3815005954743946,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004816310438021937,
|
|
"loss": 5.2027,
|
|
"mean_token_accuracy": 0.16715382486581803,
|
|
"num_tokens": 30506979.0,
|
|
"step": 13920
|
|
},
|
|
{
|
|
"entropy": 5.561068534851074,
|
|
"epoch": 1.381996824136562,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00048161701938278156,
|
|
"loss": 5.233,
|
|
"mean_token_accuracy": 0.15811349898576738,
|
|
"num_tokens": 30517492.0,
|
|
"step": 13925
|
|
},
|
|
{
|
|
"entropy": 5.510106897354126,
|
|
"epoch": 1.3824930527987296,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.00048160298983971256,
|
|
"loss": 5.1111,
|
|
"mean_token_accuracy": 0.17669742405414582,
|
|
"num_tokens": 30528614.0,
|
|
"step": 13930
|
|
},
|
|
{
|
|
"entropy": 5.551264476776123,
|
|
"epoch": 1.382989281460897,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004815889551733346,
|
|
"loss": 5.2056,
|
|
"mean_token_accuracy": 0.16688290983438492,
|
|
"num_tokens": 30539479.0,
|
|
"step": 13935
|
|
},
|
|
{
|
|
"entropy": 5.602884340286255,
|
|
"epoch": 1.3834855101230648,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00048157491538399573,
|
|
"loss": 5.2234,
|
|
"mean_token_accuracy": 0.16950736194849014,
|
|
"num_tokens": 30549909.0,
|
|
"step": 13940
|
|
},
|
|
{
|
|
"entropy": 5.550446462631226,
|
|
"epoch": 1.3839817387852322,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00048156087047204407,
|
|
"loss": 5.1272,
|
|
"mean_token_accuracy": 0.17203201353549957,
|
|
"num_tokens": 30562265.0,
|
|
"step": 13945
|
|
},
|
|
{
|
|
"entropy": 5.57637996673584,
|
|
"epoch": 1.3844779674473997,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004815468204378279,
|
|
"loss": 5.1589,
|
|
"mean_token_accuracy": 0.16654592901468276,
|
|
"num_tokens": 30572622.0,
|
|
"step": 13950
|
|
},
|
|
{
|
|
"entropy": 5.519306898117065,
|
|
"epoch": 1.3849741961095674,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004815327652816957,
|
|
"loss": 5.1355,
|
|
"mean_token_accuracy": 0.17387963980436325,
|
|
"num_tokens": 30583300.0,
|
|
"step": 13955
|
|
},
|
|
{
|
|
"entropy": 5.50309271812439,
|
|
"epoch": 1.3854704247717349,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004815187050039959,
|
|
"loss": 5.0863,
|
|
"mean_token_accuracy": 0.17074283510446547,
|
|
"num_tokens": 30594460.0,
|
|
"step": 13960
|
|
},
|
|
{
|
|
"entropy": 5.5312470436096195,
|
|
"epoch": 1.3859666534339024,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.00048150463960507724,
|
|
"loss": 5.1283,
|
|
"mean_token_accuracy": 0.17126694470643997,
|
|
"num_tokens": 30604658.0,
|
|
"step": 13965
|
|
},
|
|
{
|
|
"entropy": 5.569334316253662,
|
|
"epoch": 1.3864628820960698,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.00048149056908528855,
|
|
"loss": 5.1333,
|
|
"mean_token_accuracy": 0.16687559485435485,
|
|
"num_tokens": 30616151.0,
|
|
"step": 13970
|
|
},
|
|
{
|
|
"entropy": 5.530208683013916,
|
|
"epoch": 1.3869591107582373,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004814764934449786,
|
|
"loss": 5.1825,
|
|
"mean_token_accuracy": 0.17159994393587114,
|
|
"num_tokens": 30627560.0,
|
|
"step": 13975
|
|
},
|
|
{
|
|
"entropy": 5.524506521224976,
|
|
"epoch": 1.387455339420405,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.00048146241268449665,
|
|
"loss": 5.163,
|
|
"mean_token_accuracy": 0.16732659041881562,
|
|
"num_tokens": 30638490.0,
|
|
"step": 13980
|
|
},
|
|
{
|
|
"entropy": 5.600838327407837,
|
|
"epoch": 1.3879515680825725,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004814483268041917,
|
|
"loss": 5.2644,
|
|
"mean_token_accuracy": 0.16585466265678406,
|
|
"num_tokens": 30649501.0,
|
|
"step": 13985
|
|
},
|
|
{
|
|
"entropy": 5.56956901550293,
|
|
"epoch": 1.38844779674474,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004814342358044131,
|
|
"loss": 5.1443,
|
|
"mean_token_accuracy": 0.17039851397275924,
|
|
"num_tokens": 30660479.0,
|
|
"step": 13990
|
|
},
|
|
{
|
|
"entropy": 5.6756126403808596,
|
|
"epoch": 1.3889440254069074,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00048142013968551026,
|
|
"loss": 5.3193,
|
|
"mean_token_accuracy": 0.15933064222335816,
|
|
"num_tokens": 30672015.0,
|
|
"step": 13995
|
|
},
|
|
{
|
|
"entropy": 5.475689506530761,
|
|
"epoch": 1.3894402540690751,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.00048140603844783273,
|
|
"loss": 5.1746,
|
|
"mean_token_accuracy": 0.16900611966848372,
|
|
"num_tokens": 30682612.0,
|
|
"step": 14000
|
|
},
|
|
{
|
|
"entropy": 5.476071882247925,
|
|
"epoch": 1.3899364827312426,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004813919320917303,
|
|
"loss": 5.1163,
|
|
"mean_token_accuracy": 0.16966806650161742,
|
|
"num_tokens": 30693289.0,
|
|
"step": 14005
|
|
},
|
|
{
|
|
"entropy": 5.544860315322876,
|
|
"epoch": 1.39043271139341,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00048137782061755265,
|
|
"loss": 5.1525,
|
|
"mean_token_accuracy": 0.17297138124704362,
|
|
"num_tokens": 30705346.0,
|
|
"step": 14010
|
|
},
|
|
{
|
|
"entropy": 5.522922992706299,
|
|
"epoch": 1.3909289400555775,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.00048136370402564974,
|
|
"loss": 5.1591,
|
|
"mean_token_accuracy": 0.1646505579352379,
|
|
"num_tokens": 30715968.0,
|
|
"step": 14015
|
|
},
|
|
{
|
|
"entropy": 5.53752064704895,
|
|
"epoch": 1.391425168717745,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004813495823163716,
|
|
"loss": 5.1106,
|
|
"mean_token_accuracy": 0.1739235997200012,
|
|
"num_tokens": 30726225.0,
|
|
"step": 14020
|
|
},
|
|
{
|
|
"entropy": 5.503029441833496,
|
|
"epoch": 1.3919213973799127,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004813354554900685,
|
|
"loss": 5.0886,
|
|
"mean_token_accuracy": 0.17494098991155624,
|
|
"num_tokens": 30735603.0,
|
|
"step": 14025
|
|
},
|
|
{
|
|
"entropy": 5.4948155879974365,
|
|
"epoch": 1.3924176260420802,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004813213235470907,
|
|
"loss": 5.1365,
|
|
"mean_token_accuracy": 0.1694853588938713,
|
|
"num_tokens": 30747414.0,
|
|
"step": 14030
|
|
},
|
|
{
|
|
"entropy": 5.570358467102051,
|
|
"epoch": 1.3929138547042477,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004813071864877887,
|
|
"loss": 5.1944,
|
|
"mean_token_accuracy": 0.16979669034481049,
|
|
"num_tokens": 30758389.0,
|
|
"step": 14035
|
|
},
|
|
{
|
|
"entropy": 5.578168058395386,
|
|
"epoch": 1.3934100833664154,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.000481293044312513,
|
|
"loss": 5.2126,
|
|
"mean_token_accuracy": 0.16620449870824813,
|
|
"num_tokens": 30769484.0,
|
|
"step": 14040
|
|
},
|
|
{
|
|
"entropy": 5.5113927841186525,
|
|
"epoch": 1.3939063120285828,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00048127889702161435,
|
|
"loss": 5.1298,
|
|
"mean_token_accuracy": 0.17630065977573395,
|
|
"num_tokens": 30779775.0,
|
|
"step": 14045
|
|
},
|
|
{
|
|
"entropy": 5.589673566818237,
|
|
"epoch": 1.3944025406907503,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004812647446154435,
|
|
"loss": 5.2281,
|
|
"mean_token_accuracy": 0.16023280918598176,
|
|
"num_tokens": 30791456.0,
|
|
"step": 14050
|
|
},
|
|
{
|
|
"entropy": 5.52322096824646,
|
|
"epoch": 1.3948987693529178,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004812505870943515,
|
|
"loss": 5.0514,
|
|
"mean_token_accuracy": 0.1758187085390091,
|
|
"num_tokens": 30801659.0,
|
|
"step": 14055
|
|
},
|
|
{
|
|
"entropy": 5.615298700332642,
|
|
"epoch": 1.3953949980150853,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004812364244586893,
|
|
"loss": 5.2849,
|
|
"mean_token_accuracy": 0.16573704034090042,
|
|
"num_tokens": 30813389.0,
|
|
"step": 14060
|
|
},
|
|
{
|
|
"entropy": 5.473172521591186,
|
|
"epoch": 1.395891226677253,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004812222567088082,
|
|
"loss": 5.0484,
|
|
"mean_token_accuracy": 0.1681053012609482,
|
|
"num_tokens": 30823725.0,
|
|
"step": 14065
|
|
},
|
|
{
|
|
"entropy": 5.481383562088013,
|
|
"epoch": 1.3963874553394204,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004812080838450596,
|
|
"loss": 5.056,
|
|
"mean_token_accuracy": 0.17506962269544601,
|
|
"num_tokens": 30834448.0,
|
|
"step": 14070
|
|
},
|
|
{
|
|
"entropy": 5.5361066341400145,
|
|
"epoch": 1.396883684001588,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004811939058677947,
|
|
"loss": 5.1252,
|
|
"mean_token_accuracy": 0.16739902049303054,
|
|
"num_tokens": 30845891.0,
|
|
"step": 14075
|
|
},
|
|
{
|
|
"entropy": 5.497674369812012,
|
|
"epoch": 1.3973799126637554,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004811797227773654,
|
|
"loss": 5.0618,
|
|
"mean_token_accuracy": 0.17847796231508256,
|
|
"num_tokens": 30855170.0,
|
|
"step": 14080
|
|
},
|
|
{
|
|
"entropy": 5.489937591552734,
|
|
"epoch": 1.397876141325923,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00048116553457412317,
|
|
"loss": 5.1531,
|
|
"mean_token_accuracy": 0.16629391461610793,
|
|
"num_tokens": 30866527.0,
|
|
"step": 14085
|
|
},
|
|
{
|
|
"entropy": 5.516706848144532,
|
|
"epoch": 1.3983723699880906,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00048115134125841993,
|
|
"loss": 5.0908,
|
|
"mean_token_accuracy": 0.1756426826119423,
|
|
"num_tokens": 30876292.0,
|
|
"step": 14090
|
|
},
|
|
{
|
|
"entropy": 5.534853887557984,
|
|
"epoch": 1.398868598650258,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004811371428306076,
|
|
"loss": 5.0916,
|
|
"mean_token_accuracy": 0.16869684159755707,
|
|
"num_tokens": 30887440.0,
|
|
"step": 14095
|
|
},
|
|
{
|
|
"entropy": 5.500794744491577,
|
|
"epoch": 1.3993648273124255,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004811229392910384,
|
|
"loss": 5.1372,
|
|
"mean_token_accuracy": 0.17133892476558685,
|
|
"num_tokens": 30897925.0,
|
|
"step": 14100
|
|
},
|
|
{
|
|
"entropy": 5.514557552337647,
|
|
"epoch": 1.399861055974593,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004811087306400644,
|
|
"loss": 5.1605,
|
|
"mean_token_accuracy": 0.17588270008563994,
|
|
"num_tokens": 30908413.0,
|
|
"step": 14105
|
|
},
|
|
{
|
|
"entropy": 5.584716844558716,
|
|
"epoch": 1.4003572846367607,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.00048109451687803804,
|
|
"loss": 5.2048,
|
|
"mean_token_accuracy": 0.16762253493070603,
|
|
"num_tokens": 30919149.0,
|
|
"step": 14110
|
|
},
|
|
{
|
|
"entropy": 5.5883903980255125,
|
|
"epoch": 1.4008535132989282,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004810802980053117,
|
|
"loss": 5.2168,
|
|
"mean_token_accuracy": 0.17158247977495195,
|
|
"num_tokens": 30929883.0,
|
|
"step": 14115
|
|
},
|
|
{
|
|
"entropy": 5.510629367828369,
|
|
"epoch": 1.4013497419610956,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00048106607402223815,
|
|
"loss": 5.1281,
|
|
"mean_token_accuracy": 0.16870941817760468,
|
|
"num_tokens": 30941358.0,
|
|
"step": 14120
|
|
},
|
|
{
|
|
"entropy": 5.556718921661377,
|
|
"epoch": 1.4018459706232633,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.00048105184492916995,
|
|
"loss": 5.1314,
|
|
"mean_token_accuracy": 0.16843397319316863,
|
|
"num_tokens": 30953289.0,
|
|
"step": 14125
|
|
},
|
|
{
|
|
"entropy": 5.51023678779602,
|
|
"epoch": 1.4023421992854308,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.00048103761072645993,
|
|
"loss": 5.0589,
|
|
"mean_token_accuracy": 0.17450836300849915,
|
|
"num_tokens": 30964304.0,
|
|
"step": 14130
|
|
},
|
|
{
|
|
"entropy": 5.471431589126587,
|
|
"epoch": 1.4028384279475983,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00048102337141446116,
|
|
"loss": 5.0987,
|
|
"mean_token_accuracy": 0.17722263038158417,
|
|
"num_tokens": 30974840.0,
|
|
"step": 14135
|
|
},
|
|
{
|
|
"entropy": 5.512514352798462,
|
|
"epoch": 1.4033346566097658,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.00048100912699352666,
|
|
"loss": 5.1543,
|
|
"mean_token_accuracy": 0.17313008904457092,
|
|
"num_tokens": 30985805.0,
|
|
"step": 14140
|
|
},
|
|
{
|
|
"entropy": 5.523301982879639,
|
|
"epoch": 1.4038308852719332,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004809948774640098,
|
|
"loss": 5.1589,
|
|
"mean_token_accuracy": 0.17004996538162231,
|
|
"num_tokens": 30998174.0,
|
|
"step": 14145
|
|
},
|
|
{
|
|
"entropy": 5.565105247497558,
|
|
"epoch": 1.4043271139341007,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004809806228262639,
|
|
"loss": 5.1708,
|
|
"mean_token_accuracy": 0.16836102306842804,
|
|
"num_tokens": 31010050.0,
|
|
"step": 14150
|
|
},
|
|
{
|
|
"entropy": 5.646402502059937,
|
|
"epoch": 1.4048233425962684,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00048096636308064236,
|
|
"loss": 5.2904,
|
|
"mean_token_accuracy": 0.16075037270784379,
|
|
"num_tokens": 31023069.0,
|
|
"step": 14155
|
|
},
|
|
{
|
|
"entropy": 5.5874903202056885,
|
|
"epoch": 1.4053195712584359,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004809520982274989,
|
|
"loss": 5.0953,
|
|
"mean_token_accuracy": 0.17480895817279815,
|
|
"num_tokens": 31033512.0,
|
|
"step": 14160
|
|
},
|
|
{
|
|
"entropy": 5.53944730758667,
|
|
"epoch": 1.4058157999206033,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.00048093782826718706,
|
|
"loss": 5.1332,
|
|
"mean_token_accuracy": 0.16568226963281632,
|
|
"num_tokens": 31045731.0,
|
|
"step": 14165
|
|
},
|
|
{
|
|
"entropy": 5.488059997558594,
|
|
"epoch": 1.406312028582771,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.00048092355320006086,
|
|
"loss": 5.0563,
|
|
"mean_token_accuracy": 0.17808159291744233,
|
|
"num_tokens": 31055443.0,
|
|
"step": 14170
|
|
},
|
|
{
|
|
"entropy": 5.4675720691680905,
|
|
"epoch": 1.4068082572449385,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004809092730264744,
|
|
"loss": 5.1355,
|
|
"mean_token_accuracy": 0.17498398423194886,
|
|
"num_tokens": 31067575.0,
|
|
"step": 14175
|
|
},
|
|
{
|
|
"entropy": 5.55556354522705,
|
|
"epoch": 1.407304485907106,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00048089498774678155,
|
|
"loss": 5.2358,
|
|
"mean_token_accuracy": 0.16588225066661835,
|
|
"num_tokens": 31078198.0,
|
|
"step": 14180
|
|
},
|
|
{
|
|
"entropy": 5.530391883850098,
|
|
"epoch": 1.4078007145692735,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.00048088069736133664,
|
|
"loss": 5.1155,
|
|
"mean_token_accuracy": 0.16887167096138,
|
|
"num_tokens": 31089961.0,
|
|
"step": 14185
|
|
},
|
|
{
|
|
"entropy": 5.524352073669434,
|
|
"epoch": 1.408296943231441,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004808664018704941,
|
|
"loss": 5.1244,
|
|
"mean_token_accuracy": 0.16945887804031373,
|
|
"num_tokens": 31100534.0,
|
|
"step": 14190
|
|
},
|
|
{
|
|
"entropy": 5.625082921981812,
|
|
"epoch": 1.4087931718936086,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004808521012746085,
|
|
"loss": 5.1527,
|
|
"mean_token_accuracy": 0.17784729450941086,
|
|
"num_tokens": 31112016.0,
|
|
"step": 14195
|
|
},
|
|
{
|
|
"entropy": 5.5022547245025635,
|
|
"epoch": 1.4092894005557761,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.00048083779557403424,
|
|
"loss": 5.1955,
|
|
"mean_token_accuracy": 0.16965552270412446,
|
|
"num_tokens": 31123659.0,
|
|
"step": 14200
|
|
},
|
|
{
|
|
"entropy": 5.548771905899048,
|
|
"epoch": 1.4097856292179436,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004808234847691262,
|
|
"loss": 5.1352,
|
|
"mean_token_accuracy": 0.16782886236906053,
|
|
"num_tokens": 31133872.0,
|
|
"step": 14205
|
|
},
|
|
{
|
|
"entropy": 5.587513971328735,
|
|
"epoch": 1.4102818578801113,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004808091688602393,
|
|
"loss": 5.1754,
|
|
"mean_token_accuracy": 0.16750812232494355,
|
|
"num_tokens": 31145834.0,
|
|
"step": 14210
|
|
},
|
|
{
|
|
"entropy": 5.561975383758545,
|
|
"epoch": 1.4107780865422788,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.00048079484784772854,
|
|
"loss": 5.2513,
|
|
"mean_token_accuracy": 0.16297162771224977,
|
|
"num_tokens": 31157037.0,
|
|
"step": 14215
|
|
},
|
|
{
|
|
"entropy": 5.539417314529419,
|
|
"epoch": 1.4112743152044462,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00048078052173194886,
|
|
"loss": 5.1374,
|
|
"mean_token_accuracy": 0.17294942885637282,
|
|
"num_tokens": 31166812.0,
|
|
"step": 14220
|
|
},
|
|
{
|
|
"entropy": 5.551455640792847,
|
|
"epoch": 1.4117705438666137,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004807661905132557,
|
|
"loss": 5.1318,
|
|
"mean_token_accuracy": 0.1633587971329689,
|
|
"num_tokens": 31177162.0,
|
|
"step": 14225
|
|
},
|
|
{
|
|
"entropy": 5.552932548522949,
|
|
"epoch": 1.4122667725287812,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004807518541920045,
|
|
"loss": 5.1582,
|
|
"mean_token_accuracy": 0.17218452095985412,
|
|
"num_tokens": 31187333.0,
|
|
"step": 14230
|
|
},
|
|
{
|
|
"entropy": 5.545293998718262,
|
|
"epoch": 1.4127630011909487,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00048073751276855056,
|
|
"loss": 5.1727,
|
|
"mean_token_accuracy": 0.16789565086364747,
|
|
"num_tokens": 31197869.0,
|
|
"step": 14235
|
|
},
|
|
{
|
|
"entropy": 5.540854740142822,
|
|
"epoch": 1.4132592298531164,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004807231662432497,
|
|
"loss": 5.1834,
|
|
"mean_token_accuracy": 0.16220247000455856,
|
|
"num_tokens": 31208199.0,
|
|
"step": 14240
|
|
},
|
|
{
|
|
"entropy": 5.563972520828247,
|
|
"epoch": 1.4137554585152838,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004807088146164575,
|
|
"loss": 5.1633,
|
|
"mean_token_accuracy": 0.1621552437543869,
|
|
"num_tokens": 31218903.0,
|
|
"step": 14245
|
|
},
|
|
{
|
|
"entropy": 5.5235213279724125,
|
|
"epoch": 1.4142516871774513,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004806944578885301,
|
|
"loss": 5.1668,
|
|
"mean_token_accuracy": 0.16414968222379683,
|
|
"num_tokens": 31231146.0,
|
|
"step": 14250
|
|
},
|
|
{
|
|
"entropy": 5.532286977767944,
|
|
"epoch": 1.414747915839619,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00048068009605982333,
|
|
"loss": 5.095,
|
|
"mean_token_accuracy": 0.17158334255218505,
|
|
"num_tokens": 31240980.0,
|
|
"step": 14255
|
|
},
|
|
{
|
|
"entropy": 5.51092381477356,
|
|
"epoch": 1.4152441445017865,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00048066572913069334,
|
|
"loss": 5.1316,
|
|
"mean_token_accuracy": 0.1706465005874634,
|
|
"num_tokens": 31252458.0,
|
|
"step": 14260
|
|
},
|
|
{
|
|
"entropy": 5.501100158691406,
|
|
"epoch": 1.415740373163954,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004806513571014965,
|
|
"loss": 5.1419,
|
|
"mean_token_accuracy": 0.16705355495214463,
|
|
"num_tokens": 31262979.0,
|
|
"step": 14265
|
|
},
|
|
{
|
|
"entropy": 5.523218441009521,
|
|
"epoch": 1.4162366018261214,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004806369799725891,
|
|
"loss": 5.1156,
|
|
"mean_token_accuracy": 0.1683339312672615,
|
|
"num_tokens": 31274811.0,
|
|
"step": 14270
|
|
},
|
|
{
|
|
"entropy": 5.510698366165161,
|
|
"epoch": 1.416732830488289,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004806225977443277,
|
|
"loss": 5.0926,
|
|
"mean_token_accuracy": 0.1792379304766655,
|
|
"num_tokens": 31285573.0,
|
|
"step": 14275
|
|
},
|
|
{
|
|
"entropy": 5.609202814102173,
|
|
"epoch": 1.4172290591504566,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004806082104170689,
|
|
"loss": 5.2536,
|
|
"mean_token_accuracy": 0.15575346797704698,
|
|
"num_tokens": 31296993.0,
|
|
"step": 14280
|
|
},
|
|
{
|
|
"entropy": 5.49761552810669,
|
|
"epoch": 1.417725287812624,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.00048059381799116967,
|
|
"loss": 5.1388,
|
|
"mean_token_accuracy": 0.1710622638463974,
|
|
"num_tokens": 31307217.0,
|
|
"step": 14285
|
|
},
|
|
{
|
|
"entropy": 5.503528642654419,
|
|
"epoch": 1.4182215164747916,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004805794204669867,
|
|
"loss": 5.1675,
|
|
"mean_token_accuracy": 0.16914174258708953,
|
|
"num_tokens": 31317939.0,
|
|
"step": 14290
|
|
},
|
|
{
|
|
"entropy": 5.604456090927124,
|
|
"epoch": 1.418717745136959,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00048056501784487707,
|
|
"loss": 5.1356,
|
|
"mean_token_accuracy": 0.1669573113322258,
|
|
"num_tokens": 31327731.0,
|
|
"step": 14295
|
|
},
|
|
{
|
|
"entropy": 5.688533210754395,
|
|
"epoch": 1.4192139737991267,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000480550610125198,
|
|
"loss": 5.3187,
|
|
"mean_token_accuracy": 0.155430468916893,
|
|
"num_tokens": 31339388.0,
|
|
"step": 14300
|
|
},
|
|
{
|
|
"entropy": 5.478641843795776,
|
|
"epoch": 1.4197102024612942,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004805361973083066,
|
|
"loss": 5.003,
|
|
"mean_token_accuracy": 0.1770283043384552,
|
|
"num_tokens": 31350186.0,
|
|
"step": 14305
|
|
},
|
|
{
|
|
"entropy": 5.53291425704956,
|
|
"epoch": 1.4202064311234617,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004805217793945605,
|
|
"loss": 5.1719,
|
|
"mean_token_accuracy": 0.16603127866983414,
|
|
"num_tokens": 31361219.0,
|
|
"step": 14310
|
|
},
|
|
{
|
|
"entropy": 5.526129961013794,
|
|
"epoch": 1.4207026597856292,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004805073563843171,
|
|
"loss": 5.1992,
|
|
"mean_token_accuracy": 0.16637402176856994,
|
|
"num_tokens": 31372820.0,
|
|
"step": 14315
|
|
},
|
|
{
|
|
"entropy": 5.534232807159424,
|
|
"epoch": 1.4211988884477966,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00048049292827793413,
|
|
"loss": 5.0818,
|
|
"mean_token_accuracy": 0.17799466252326965,
|
|
"num_tokens": 31382779.0,
|
|
"step": 14320
|
|
},
|
|
{
|
|
"entropy": 5.611496067047119,
|
|
"epoch": 1.4216951171099643,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004804784950757693,
|
|
"loss": 5.3072,
|
|
"mean_token_accuracy": 0.1644120469689369,
|
|
"num_tokens": 31394872.0,
|
|
"step": 14325
|
|
},
|
|
{
|
|
"entropy": 5.580011940002441,
|
|
"epoch": 1.4221913457721318,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00048046405677818057,
|
|
"loss": 5.1921,
|
|
"mean_token_accuracy": 0.1673213794827461,
|
|
"num_tokens": 31405767.0,
|
|
"step": 14330
|
|
},
|
|
{
|
|
"entropy": 5.563827133178711,
|
|
"epoch": 1.4226875744342993,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00048044961338552595,
|
|
"loss": 5.1744,
|
|
"mean_token_accuracy": 0.16784346848726273,
|
|
"num_tokens": 31417255.0,
|
|
"step": 14335
|
|
},
|
|
{
|
|
"entropy": 5.54085488319397,
|
|
"epoch": 1.423183803096467,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004804351648981636,
|
|
"loss": 5.1488,
|
|
"mean_token_accuracy": 0.17346104085445405,
|
|
"num_tokens": 31428494.0,
|
|
"step": 14340
|
|
},
|
|
{
|
|
"entropy": 5.522696399688721,
|
|
"epoch": 1.4236800317586344,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004804207113164519,
|
|
"loss": 5.0535,
|
|
"mean_token_accuracy": 0.17751450538635255,
|
|
"num_tokens": 31439221.0,
|
|
"step": 14345
|
|
},
|
|
{
|
|
"entropy": 5.544555425643921,
|
|
"epoch": 1.424176260420802,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.00048040625264074915,
|
|
"loss": 5.1371,
|
|
"mean_token_accuracy": 0.1722538113594055,
|
|
"num_tokens": 31450575.0,
|
|
"step": 14350
|
|
},
|
|
{
|
|
"entropy": 5.453340625762939,
|
|
"epoch": 1.4246724890829694,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.00048039178887141404,
|
|
"loss": 5.1356,
|
|
"mean_token_accuracy": 0.17231809943914414,
|
|
"num_tokens": 31462168.0,
|
|
"step": 14355
|
|
},
|
|
{
|
|
"entropy": 5.526081132888794,
|
|
"epoch": 1.4251687177451369,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00048037732000880503,
|
|
"loss": 5.1599,
|
|
"mean_token_accuracy": 0.17401762157678605,
|
|
"num_tokens": 31472619.0,
|
|
"step": 14360
|
|
},
|
|
{
|
|
"entropy": 5.584140920639038,
|
|
"epoch": 1.4256649464073046,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.00048036284605328106,
|
|
"loss": 5.2268,
|
|
"mean_token_accuracy": 0.16818679571151735,
|
|
"num_tokens": 31485246.0,
|
|
"step": 14365
|
|
},
|
|
{
|
|
"entropy": 5.550671482086182,
|
|
"epoch": 1.426161175069472,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004803483670052011,
|
|
"loss": 5.1557,
|
|
"mean_token_accuracy": 0.1648237943649292,
|
|
"num_tokens": 31496258.0,
|
|
"step": 14370
|
|
},
|
|
{
|
|
"entropy": 5.537722778320313,
|
|
"epoch": 1.4266574037316395,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.000480333882864924,
|
|
"loss": 5.1164,
|
|
"mean_token_accuracy": 0.17127072364091872,
|
|
"num_tokens": 31506671.0,
|
|
"step": 14375
|
|
},
|
|
{
|
|
"entropy": 5.574142408370972,
|
|
"epoch": 1.427153632393807,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004803193936328092,
|
|
"loss": 5.1543,
|
|
"mean_token_accuracy": 0.16316839307546616,
|
|
"num_tokens": 31517001.0,
|
|
"step": 14380
|
|
},
|
|
{
|
|
"entropy": 5.549087429046631,
|
|
"epoch": 1.4276498610559747,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004803048993092158,
|
|
"loss": 5.1566,
|
|
"mean_token_accuracy": 0.1722284361720085,
|
|
"num_tokens": 31529649.0,
|
|
"step": 14385
|
|
},
|
|
{
|
|
"entropy": 5.4671769618988035,
|
|
"epoch": 1.4281460897181422,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00048029039989450317,
|
|
"loss": 5.0957,
|
|
"mean_token_accuracy": 0.1762278273701668,
|
|
"num_tokens": 31540083.0,
|
|
"step": 14390
|
|
},
|
|
{
|
|
"entropy": 5.577415323257446,
|
|
"epoch": 1.4286423183803096,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00048027589538903115,
|
|
"loss": 5.1908,
|
|
"mean_token_accuracy": 0.16957178115844726,
|
|
"num_tokens": 31551400.0,
|
|
"step": 14395
|
|
},
|
|
{
|
|
"entropy": 5.592285776138306,
|
|
"epoch": 1.4291385470424771,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004802613857931592,
|
|
"loss": 5.2006,
|
|
"mean_token_accuracy": 0.16429416537284852,
|
|
"num_tokens": 31562430.0,
|
|
"step": 14400
|
|
},
|
|
{
|
|
"entropy": 5.598383378982544,
|
|
"epoch": 1.4296347757046446,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004802468711072472,
|
|
"loss": 5.2389,
|
|
"mean_token_accuracy": 0.16840045303106307,
|
|
"num_tokens": 31573173.0,
|
|
"step": 14405
|
|
},
|
|
{
|
|
"entropy": 5.570560121536255,
|
|
"epoch": 1.4301310043668123,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.000480232351331655,
|
|
"loss": 5.1784,
|
|
"mean_token_accuracy": 0.16820122450590133,
|
|
"num_tokens": 31584072.0,
|
|
"step": 14410
|
|
},
|
|
{
|
|
"entropy": 5.487016344070435,
|
|
"epoch": 1.4306272330289798,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00048021782646674277,
|
|
"loss": 5.1073,
|
|
"mean_token_accuracy": 0.17149910926818848,
|
|
"num_tokens": 31594993.0,
|
|
"step": 14415
|
|
},
|
|
{
|
|
"entropy": 5.5244057178497314,
|
|
"epoch": 1.4311234616911472,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00048020329651287064,
|
|
"loss": 5.1434,
|
|
"mean_token_accuracy": 0.17616817504167556,
|
|
"num_tokens": 31604284.0,
|
|
"step": 14420
|
|
},
|
|
{
|
|
"entropy": 5.498825597763061,
|
|
"epoch": 1.431619690353315,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.000480188761470399,
|
|
"loss": 5.2082,
|
|
"mean_token_accuracy": 0.17070335745811463,
|
|
"num_tokens": 31616188.0,
|
|
"step": 14425
|
|
},
|
|
{
|
|
"entropy": 5.595587110519409,
|
|
"epoch": 1.4321159190154824,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004801742213396881,
|
|
"loss": 5.1826,
|
|
"mean_token_accuracy": 0.17196833193302155,
|
|
"num_tokens": 31626606.0,
|
|
"step": 14430
|
|
},
|
|
{
|
|
"entropy": 5.502880573272705,
|
|
"epoch": 1.4326121476776499,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00048015967612109875,
|
|
"loss": 5.0826,
|
|
"mean_token_accuracy": 0.17779795527458192,
|
|
"num_tokens": 31638050.0,
|
|
"step": 14435
|
|
},
|
|
{
|
|
"entropy": 5.54227499961853,
|
|
"epoch": 1.4331083763398174,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.00048014512581499136,
|
|
"loss": 5.1027,
|
|
"mean_token_accuracy": 0.16992465257644654,
|
|
"num_tokens": 31648451.0,
|
|
"step": 14440
|
|
},
|
|
{
|
|
"entropy": 5.509846973419189,
|
|
"epoch": 1.4336046050019848,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.000480130570421727,
|
|
"loss": 5.1274,
|
|
"mean_token_accuracy": 0.16722584366798401,
|
|
"num_tokens": 31659310.0,
|
|
"step": 14445
|
|
},
|
|
{
|
|
"entropy": 5.508379030227661,
|
|
"epoch": 1.4341008336641523,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004801160099416665,
|
|
"loss": 5.1524,
|
|
"mean_token_accuracy": 0.17036597728729247,
|
|
"num_tokens": 31669594.0,
|
|
"step": 14450
|
|
},
|
|
{
|
|
"entropy": 5.557476282119751,
|
|
"epoch": 1.43459706232632,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004801014443751709,
|
|
"loss": 5.1491,
|
|
"mean_token_accuracy": 0.1631366103887558,
|
|
"num_tokens": 31682034.0,
|
|
"step": 14455
|
|
},
|
|
{
|
|
"entropy": 5.5781943798065186,
|
|
"epoch": 1.4350932909884875,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004800868737226015,
|
|
"loss": 5.1849,
|
|
"mean_token_accuracy": 0.17017990052700044,
|
|
"num_tokens": 31692390.0,
|
|
"step": 14460
|
|
},
|
|
{
|
|
"entropy": 5.553547954559326,
|
|
"epoch": 1.435589519650655,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00048007229798431946,
|
|
"loss": 5.1581,
|
|
"mean_token_accuracy": 0.17409306913614273,
|
|
"num_tokens": 31703690.0,
|
|
"step": 14465
|
|
},
|
|
{
|
|
"entropy": 5.571557331085205,
|
|
"epoch": 1.4360857483128227,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004800577171606864,
|
|
"loss": 5.1657,
|
|
"mean_token_accuracy": 0.16779595464468003,
|
|
"num_tokens": 31714655.0,
|
|
"step": 14470
|
|
},
|
|
{
|
|
"entropy": 5.5033680438995365,
|
|
"epoch": 1.4365819769749901,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004800431312520638,
|
|
"loss": 5.0764,
|
|
"mean_token_accuracy": 0.17734036296606065,
|
|
"num_tokens": 31727022.0,
|
|
"step": 14475
|
|
},
|
|
{
|
|
"entropy": 5.552882957458496,
|
|
"epoch": 1.4370782056371576,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004800285402588134,
|
|
"loss": 5.1085,
|
|
"mean_token_accuracy": 0.17871950417757035,
|
|
"num_tokens": 31738071.0,
|
|
"step": 14480
|
|
},
|
|
{
|
|
"entropy": 5.588936042785645,
|
|
"epoch": 1.437574434299325,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004800139441812969,
|
|
"loss": 5.2334,
|
|
"mean_token_accuracy": 0.16277743577957154,
|
|
"num_tokens": 31749342.0,
|
|
"step": 14485
|
|
},
|
|
{
|
|
"entropy": 5.597983121871948,
|
|
"epoch": 1.4380706629614926,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.00047999934301987644,
|
|
"loss": 5.2065,
|
|
"mean_token_accuracy": 0.1663838341832161,
|
|
"num_tokens": 31761218.0,
|
|
"step": 14490
|
|
},
|
|
{
|
|
"entropy": 5.555614423751831,
|
|
"epoch": 1.4385668916236602,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.000479984736774914,
|
|
"loss": 5.2175,
|
|
"mean_token_accuracy": 0.16957231163978576,
|
|
"num_tokens": 31773111.0,
|
|
"step": 14495
|
|
},
|
|
{
|
|
"entropy": 5.590849876403809,
|
|
"epoch": 1.4390631202858277,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00047997012544677176,
|
|
"loss": 5.1684,
|
|
"mean_token_accuracy": 0.16931167244911194,
|
|
"num_tokens": 31782948.0,
|
|
"step": 14500
|
|
},
|
|
{
|
|
"entropy": 5.618510818481445,
|
|
"epoch": 1.4395593489479952,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004799555090358121,
|
|
"loss": 5.153,
|
|
"mean_token_accuracy": 0.1706443354487419,
|
|
"num_tokens": 31793992.0,
|
|
"step": 14505
|
|
},
|
|
{
|
|
"entropy": 5.5874392032623295,
|
|
"epoch": 1.440055577610163,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004799408875423975,
|
|
"loss": 5.1657,
|
|
"mean_token_accuracy": 0.16228770464658737,
|
|
"num_tokens": 31804830.0,
|
|
"step": 14510
|
|
},
|
|
{
|
|
"entropy": 5.493667936325073,
|
|
"epoch": 1.4405518062723304,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004799262609668904,
|
|
"loss": 5.152,
|
|
"mean_token_accuracy": 0.16971576064825059,
|
|
"num_tokens": 31817200.0,
|
|
"step": 14515
|
|
},
|
|
{
|
|
"entropy": 5.541617822647095,
|
|
"epoch": 1.4410480349344978,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004799116293096537,
|
|
"loss": 5.1986,
|
|
"mean_token_accuracy": 0.17282797545194625,
|
|
"num_tokens": 31828226.0,
|
|
"step": 14520
|
|
},
|
|
{
|
|
"entropy": 5.529183864593506,
|
|
"epoch": 1.4415442635966653,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004798969925710501,
|
|
"loss": 5.0854,
|
|
"mean_token_accuracy": 0.1796392396092415,
|
|
"num_tokens": 31839635.0,
|
|
"step": 14525
|
|
},
|
|
{
|
|
"entropy": 5.54269700050354,
|
|
"epoch": 1.4420404922588328,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00047988235075144254,
|
|
"loss": 5.1265,
|
|
"mean_token_accuracy": 0.17201922684907914,
|
|
"num_tokens": 31850333.0,
|
|
"step": 14530
|
|
},
|
|
{
|
|
"entropy": 5.543643379211426,
|
|
"epoch": 1.4425367209210003,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004798677038511942,
|
|
"loss": 5.1091,
|
|
"mean_token_accuracy": 0.16935644000768663,
|
|
"num_tokens": 31861002.0,
|
|
"step": 14535
|
|
},
|
|
{
|
|
"entropy": 5.570112562179565,
|
|
"epoch": 1.443032949583168,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004798530518706683,
|
|
"loss": 5.1883,
|
|
"mean_token_accuracy": 0.1678013578057289,
|
|
"num_tokens": 31871713.0,
|
|
"step": 14540
|
|
},
|
|
{
|
|
"entropy": 5.563977193832398,
|
|
"epoch": 1.4435291782453354,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004798383948102281,
|
|
"loss": 5.1084,
|
|
"mean_token_accuracy": 0.17264219522476196,
|
|
"num_tokens": 31882381.0,
|
|
"step": 14545
|
|
},
|
|
{
|
|
"entropy": 5.567434024810791,
|
|
"epoch": 1.444025406907503,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004798237326702371,
|
|
"loss": 5.1588,
|
|
"mean_token_accuracy": 0.17382670044898987,
|
|
"num_tokens": 31892347.0,
|
|
"step": 14550
|
|
},
|
|
{
|
|
"entropy": 5.614115762710571,
|
|
"epoch": 1.4445216355696706,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00047980906545105884,
|
|
"loss": 5.2588,
|
|
"mean_token_accuracy": 0.16123803406953813,
|
|
"num_tokens": 31902751.0,
|
|
"step": 14555
|
|
},
|
|
{
|
|
"entropy": 5.529605722427368,
|
|
"epoch": 1.445017864231838,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004797943931530571,
|
|
"loss": 5.132,
|
|
"mean_token_accuracy": 0.1714739426970482,
|
|
"num_tokens": 31913294.0,
|
|
"step": 14560
|
|
},
|
|
{
|
|
"entropy": 5.526498317718506,
|
|
"epoch": 1.4455140928940056,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004797797157765958,
|
|
"loss": 5.2439,
|
|
"mean_token_accuracy": 0.16959428191184997,
|
|
"num_tokens": 31925678.0,
|
|
"step": 14565
|
|
},
|
|
{
|
|
"entropy": 5.505324792861939,
|
|
"epoch": 1.446010321556173,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004797650333220387,
|
|
"loss": 5.0682,
|
|
"mean_token_accuracy": 0.17543325573205948,
|
|
"num_tokens": 31934578.0,
|
|
"step": 14570
|
|
},
|
|
{
|
|
"entropy": 5.510114860534668,
|
|
"epoch": 1.4465065502183405,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00047975034578975006,
|
|
"loss": 5.1093,
|
|
"mean_token_accuracy": 0.17227471321821214,
|
|
"num_tokens": 31945482.0,
|
|
"step": 14575
|
|
},
|
|
{
|
|
"entropy": 5.547610950469971,
|
|
"epoch": 1.4470027788805082,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.000479735653180094,
|
|
"loss": 5.2171,
|
|
"mean_token_accuracy": 0.17302812039852142,
|
|
"num_tokens": 31957303.0,
|
|
"step": 14580
|
|
},
|
|
{
|
|
"entropy": 5.533083152770996,
|
|
"epoch": 1.4474990075426757,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004797209554934349,
|
|
"loss": 5.1343,
|
|
"mean_token_accuracy": 0.16546977162361146,
|
|
"num_tokens": 31968601.0,
|
|
"step": 14585
|
|
},
|
|
{
|
|
"entropy": 5.525278902053833,
|
|
"epoch": 1.4479952362048432,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004797062527301373,
|
|
"loss": 5.1689,
|
|
"mean_token_accuracy": 0.17269700914621353,
|
|
"num_tokens": 31978987.0,
|
|
"step": 14590
|
|
},
|
|
{
|
|
"entropy": 5.554373645782471,
|
|
"epoch": 1.4484914648670106,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004796915448905657,
|
|
"loss": 5.1443,
|
|
"mean_token_accuracy": 0.16631865054368972,
|
|
"num_tokens": 31990950.0,
|
|
"step": 14595
|
|
},
|
|
{
|
|
"entropy": 5.614176273345947,
|
|
"epoch": 1.4489876935291783,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00047967683197508486,
|
|
"loss": 5.164,
|
|
"mean_token_accuracy": 0.1636600226163864,
|
|
"num_tokens": 32001795.0,
|
|
"step": 14600
|
|
},
|
|
{
|
|
"entropy": 5.5594127655029295,
|
|
"epoch": 1.4494839221913458,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.00047966211398405966,
|
|
"loss": 5.1741,
|
|
"mean_token_accuracy": 0.16618093103170395,
|
|
"num_tokens": 32011775.0,
|
|
"step": 14605
|
|
},
|
|
{
|
|
"entropy": 5.65315523147583,
|
|
"epoch": 1.4499801508535133,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000479647390917855,
|
|
"loss": 5.2741,
|
|
"mean_token_accuracy": 0.15630142390727997,
|
|
"num_tokens": 32022674.0,
|
|
"step": 14610
|
|
},
|
|
{
|
|
"entropy": 5.615009021759033,
|
|
"epoch": 1.4504763795156808,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000479632662776836,
|
|
"loss": 5.21,
|
|
"mean_token_accuracy": 0.17004247307777404,
|
|
"num_tokens": 32033383.0,
|
|
"step": 14615
|
|
},
|
|
{
|
|
"entropy": 5.546019887924194,
|
|
"epoch": 1.4509726081778482,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.000479617929561368,
|
|
"loss": 5.1144,
|
|
"mean_token_accuracy": 0.17207654863595961,
|
|
"num_tokens": 32044066.0,
|
|
"step": 14620
|
|
},
|
|
{
|
|
"entropy": 5.54558539390564,
|
|
"epoch": 1.451468836840016,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004796031912718162,
|
|
"loss": 5.2007,
|
|
"mean_token_accuracy": 0.1614237979054451,
|
|
"num_tokens": 32054650.0,
|
|
"step": 14625
|
|
},
|
|
{
|
|
"entropy": 5.634576606750488,
|
|
"epoch": 1.4519650655021834,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00047958844790854606,
|
|
"loss": 5.1818,
|
|
"mean_token_accuracy": 0.16604610979557038,
|
|
"num_tokens": 32065786.0,
|
|
"step": 14630
|
|
},
|
|
{
|
|
"entropy": 5.60061731338501,
|
|
"epoch": 1.4524612941643509,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00047957369947192337,
|
|
"loss": 5.1483,
|
|
"mean_token_accuracy": 0.17453572899103165,
|
|
"num_tokens": 32076326.0,
|
|
"step": 14635
|
|
},
|
|
{
|
|
"entropy": 5.499564456939697,
|
|
"epoch": 1.4529575228265186,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004795589459623136,
|
|
"loss": 5.0875,
|
|
"mean_token_accuracy": 0.16856737136840821,
|
|
"num_tokens": 32086915.0,
|
|
"step": 14640
|
|
},
|
|
{
|
|
"entropy": 5.539043855667114,
|
|
"epoch": 1.453453751488686,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.00047954418738008295,
|
|
"loss": 5.0666,
|
|
"mean_token_accuracy": 0.1736020877957344,
|
|
"num_tokens": 32096614.0,
|
|
"step": 14645
|
|
},
|
|
{
|
|
"entropy": 5.540634393692017,
|
|
"epoch": 1.4539499801508535,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004795294237255971,
|
|
"loss": 5.158,
|
|
"mean_token_accuracy": 0.174413201212883,
|
|
"num_tokens": 32107721.0,
|
|
"step": 14650
|
|
},
|
|
{
|
|
"entropy": 5.539350366592407,
|
|
"epoch": 1.454446208813021,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00047951465499922234,
|
|
"loss": 5.1699,
|
|
"mean_token_accuracy": 0.16659918129444123,
|
|
"num_tokens": 32116621.0,
|
|
"step": 14655
|
|
},
|
|
{
|
|
"entropy": 5.5818687915802006,
|
|
"epoch": 1.4549424374751885,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004794998812013248,
|
|
"loss": 5.1986,
|
|
"mean_token_accuracy": 0.16622278988361358,
|
|
"num_tokens": 32126536.0,
|
|
"step": 14660
|
|
},
|
|
{
|
|
"entropy": 5.593965196609497,
|
|
"epoch": 1.4554386661373562,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.00047948510233227084,
|
|
"loss": 5.2495,
|
|
"mean_token_accuracy": 0.15925149172544478,
|
|
"num_tokens": 32137059.0,
|
|
"step": 14665
|
|
},
|
|
{
|
|
"entropy": 5.510193252563477,
|
|
"epoch": 1.4559348947995236,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004794703183924269,
|
|
"loss": 5.1836,
|
|
"mean_token_accuracy": 0.17112441658973693,
|
|
"num_tokens": 32148186.0,
|
|
"step": 14670
|
|
},
|
|
{
|
|
"entropy": 5.621796751022339,
|
|
"epoch": 1.4564311234616911,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004794555293821597,
|
|
"loss": 5.2336,
|
|
"mean_token_accuracy": 0.15495994687080383,
|
|
"num_tokens": 32158244.0,
|
|
"step": 14675
|
|
},
|
|
{
|
|
"entropy": 5.569933891296387,
|
|
"epoch": 1.4569273521238586,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.000479440735301836,
|
|
"loss": 5.1135,
|
|
"mean_token_accuracy": 0.17377600073814392,
|
|
"num_tokens": 32168404.0,
|
|
"step": 14680
|
|
},
|
|
{
|
|
"entropy": 5.499804401397705,
|
|
"epoch": 1.4574235807860263,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004794259361518226,
|
|
"loss": 5.0805,
|
|
"mean_token_accuracy": 0.17535601258277894,
|
|
"num_tokens": 32178744.0,
|
|
"step": 14685
|
|
},
|
|
{
|
|
"entropy": 5.547453737258911,
|
|
"epoch": 1.4579198094481938,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00047941113193248643,
|
|
"loss": 5.2116,
|
|
"mean_token_accuracy": 0.16683421581983565,
|
|
"num_tokens": 32189948.0,
|
|
"step": 14690
|
|
},
|
|
{
|
|
"entropy": 5.579397249221802,
|
|
"epoch": 1.4584160381103612,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004793963226441947,
|
|
"loss": 5.1889,
|
|
"mean_token_accuracy": 0.16290004551410675,
|
|
"num_tokens": 32200979.0,
|
|
"step": 14695
|
|
},
|
|
{
|
|
"entropy": 5.544812917709351,
|
|
"epoch": 1.4589122667725287,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00047938150828731455,
|
|
"loss": 5.1645,
|
|
"mean_token_accuracy": 0.16926503032445908,
|
|
"num_tokens": 32211569.0,
|
|
"step": 14700
|
|
},
|
|
{
|
|
"entropy": 5.5758302211761475,
|
|
"epoch": 1.4594084954346962,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004793666888622134,
|
|
"loss": 5.1413,
|
|
"mean_token_accuracy": 0.17045687288045883,
|
|
"num_tokens": 32222429.0,
|
|
"step": 14705
|
|
},
|
|
{
|
|
"entropy": 5.553287363052368,
|
|
"epoch": 1.459904724096864,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004793518643692587,
|
|
"loss": 5.199,
|
|
"mean_token_accuracy": 0.1621451273560524,
|
|
"num_tokens": 32234332.0,
|
|
"step": 14710
|
|
},
|
|
{
|
|
"entropy": 5.617584609985352,
|
|
"epoch": 1.4604009527590314,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004793370348088182,
|
|
"loss": 5.251,
|
|
"mean_token_accuracy": 0.16487257480621337,
|
|
"num_tokens": 32244798.0,
|
|
"step": 14715
|
|
},
|
|
{
|
|
"entropy": 5.568008756637573,
|
|
"epoch": 1.4608971814211988,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004793222001812595,
|
|
"loss": 5.1389,
|
|
"mean_token_accuracy": 0.17323154211044312,
|
|
"num_tokens": 32257746.0,
|
|
"step": 14720
|
|
},
|
|
{
|
|
"entropy": 5.593483734130859,
|
|
"epoch": 1.4613934100833665,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00047930736048695045,
|
|
"loss": 5.2366,
|
|
"mean_token_accuracy": 0.16620125472545624,
|
|
"num_tokens": 32270692.0,
|
|
"step": 14725
|
|
},
|
|
{
|
|
"entropy": 5.5526793003082275,
|
|
"epoch": 1.461889638745534,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004792925157262592,
|
|
"loss": 5.1368,
|
|
"mean_token_accuracy": 0.16730573475360871,
|
|
"num_tokens": 32281350.0,
|
|
"step": 14730
|
|
},
|
|
{
|
|
"entropy": 5.5537224292755125,
|
|
"epoch": 1.4623858674077015,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004792776658995537,
|
|
"loss": 5.1645,
|
|
"mean_token_accuracy": 0.16899915635585785,
|
|
"num_tokens": 32293182.0,
|
|
"step": 14735
|
|
},
|
|
{
|
|
"entropy": 5.549123287200928,
|
|
"epoch": 1.462882096069869,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004792628110072023,
|
|
"loss": 5.1452,
|
|
"mean_token_accuracy": 0.16692745238542556,
|
|
"num_tokens": 32304903.0,
|
|
"step": 14740
|
|
},
|
|
{
|
|
"entropy": 5.622548294067383,
|
|
"epoch": 1.4633783247320364,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004792479510495734,
|
|
"loss": 5.3181,
|
|
"mean_token_accuracy": 0.164116707444191,
|
|
"num_tokens": 32316074.0,
|
|
"step": 14745
|
|
},
|
|
{
|
|
"entropy": 5.557573318481445,
|
|
"epoch": 1.463874553394204,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00047923308602703535,
|
|
"loss": 5.1317,
|
|
"mean_token_accuracy": 0.17938311100006105,
|
|
"num_tokens": 32327594.0,
|
|
"step": 14750
|
|
},
|
|
{
|
|
"entropy": 5.528957319259644,
|
|
"epoch": 1.4643707820563716,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00047921821593995684,
|
|
"loss": 5.1812,
|
|
"mean_token_accuracy": 0.17304366379976271,
|
|
"num_tokens": 32339224.0,
|
|
"step": 14755
|
|
},
|
|
{
|
|
"entropy": 5.556363773345947,
|
|
"epoch": 1.464867010718539,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004792033407887066,
|
|
"loss": 5.1505,
|
|
"mean_token_accuracy": 0.17215009927749633,
|
|
"num_tokens": 32349451.0,
|
|
"step": 14760
|
|
},
|
|
{
|
|
"entropy": 5.677080297470093,
|
|
"epoch": 1.4653632393807066,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004791884605736536,
|
|
"loss": 5.227,
|
|
"mean_token_accuracy": 0.16836720257997512,
|
|
"num_tokens": 32361177.0,
|
|
"step": 14765
|
|
},
|
|
{
|
|
"entropy": 5.585278797149658,
|
|
"epoch": 1.4658594680428743,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00047917357529516676,
|
|
"loss": 5.1441,
|
|
"mean_token_accuracy": 0.16627820134162902,
|
|
"num_tokens": 32372031.0,
|
|
"step": 14770
|
|
},
|
|
{
|
|
"entropy": 5.512536144256591,
|
|
"epoch": 1.4663556967050417,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004791586849536152,
|
|
"loss": 5.0603,
|
|
"mean_token_accuracy": 0.17988549321889877,
|
|
"num_tokens": 32383936.0,
|
|
"step": 14775
|
|
},
|
|
{
|
|
"entropy": 5.547338581085205,
|
|
"epoch": 1.4668519253672092,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004791437895493682,
|
|
"loss": 5.2051,
|
|
"mean_token_accuracy": 0.17175210565328597,
|
|
"num_tokens": 32394283.0,
|
|
"step": 14780
|
|
},
|
|
{
|
|
"entropy": 5.55866060256958,
|
|
"epoch": 1.4673481540293767,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.00047912888908279507,
|
|
"loss": 5.1907,
|
|
"mean_token_accuracy": 0.16381733417510985,
|
|
"num_tokens": 32405549.0,
|
|
"step": 14785
|
|
},
|
|
{
|
|
"entropy": 5.535640096664428,
|
|
"epoch": 1.4678443826915442,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004791139835542653,
|
|
"loss": 5.1286,
|
|
"mean_token_accuracy": 0.16895053386688233,
|
|
"num_tokens": 32414896.0,
|
|
"step": 14790
|
|
},
|
|
{
|
|
"entropy": 5.560206079483033,
|
|
"epoch": 1.4683406113537119,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.00047909907296414864,
|
|
"loss": 5.1815,
|
|
"mean_token_accuracy": 0.17300113737583162,
|
|
"num_tokens": 32426863.0,
|
|
"step": 14795
|
|
},
|
|
{
|
|
"entropy": 5.518635702133179,
|
|
"epoch": 1.4688368400158793,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.00047908415731281475,
|
|
"loss": 5.1553,
|
|
"mean_token_accuracy": 0.17030056118965148,
|
|
"num_tokens": 32437703.0,
|
|
"step": 14800
|
|
},
|
|
{
|
|
"entropy": 5.582429456710815,
|
|
"epoch": 1.4693330686780468,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00047906923660063344,
|
|
"loss": 5.2081,
|
|
"mean_token_accuracy": 0.1715475559234619,
|
|
"num_tokens": 32448517.0,
|
|
"step": 14805
|
|
},
|
|
{
|
|
"entropy": 5.537463235855102,
|
|
"epoch": 1.4698292973402145,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000479054310827975,
|
|
"loss": 5.1883,
|
|
"mean_token_accuracy": 0.16616832762956618,
|
|
"num_tokens": 32458782.0,
|
|
"step": 14810
|
|
},
|
|
{
|
|
"entropy": 5.5124444484710695,
|
|
"epoch": 1.470325526002382,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00047903937999520913,
|
|
"loss": 5.0592,
|
|
"mean_token_accuracy": 0.17402507066726686,
|
|
"num_tokens": 32470113.0,
|
|
"step": 14815
|
|
},
|
|
{
|
|
"entropy": 5.562623453140259,
|
|
"epoch": 1.4708217546645495,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004790244441027064,
|
|
"loss": 5.1421,
|
|
"mean_token_accuracy": 0.17384142577648162,
|
|
"num_tokens": 32482455.0,
|
|
"step": 14820
|
|
},
|
|
{
|
|
"entropy": 5.583147239685059,
|
|
"epoch": 1.471317983326717,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004790095031508371,
|
|
"loss": 5.2012,
|
|
"mean_token_accuracy": 0.17069411426782607,
|
|
"num_tokens": 32493536.0,
|
|
"step": 14825
|
|
},
|
|
{
|
|
"entropy": 5.503097295761108,
|
|
"epoch": 1.4718142119888844,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.00047899455713997164,
|
|
"loss": 5.1062,
|
|
"mean_token_accuracy": 0.1720515802502632,
|
|
"num_tokens": 32503991.0,
|
|
"step": 14830
|
|
},
|
|
{
|
|
"entropy": 5.5159343719482425,
|
|
"epoch": 1.4723104406510519,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00047897960607048084,
|
|
"loss": 5.187,
|
|
"mean_token_accuracy": 0.1663205772638321,
|
|
"num_tokens": 32515474.0,
|
|
"step": 14835
|
|
},
|
|
{
|
|
"entropy": 5.499777364730835,
|
|
"epoch": 1.4728066693132196,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.0004789646499427353,
|
|
"loss": 5.0869,
|
|
"mean_token_accuracy": 0.17534635812044144,
|
|
"num_tokens": 32526751.0,
|
|
"step": 14840
|
|
},
|
|
{
|
|
"entropy": 5.633343601226807,
|
|
"epoch": 1.473302897975387,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004789496887571059,
|
|
"loss": 5.2573,
|
|
"mean_token_accuracy": 0.16634935438632964,
|
|
"num_tokens": 32538191.0,
|
|
"step": 14845
|
|
},
|
|
{
|
|
"entropy": 5.56784291267395,
|
|
"epoch": 1.4737991266375545,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00047893472251396373,
|
|
"loss": 5.1872,
|
|
"mean_token_accuracy": 0.17286429852247237,
|
|
"num_tokens": 32548841.0,
|
|
"step": 14850
|
|
},
|
|
{
|
|
"entropy": 5.539698266983033,
|
|
"epoch": 1.4742953552997222,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00047891975121368,
|
|
"loss": 5.13,
|
|
"mean_token_accuracy": 0.16835729628801346,
|
|
"num_tokens": 32558599.0,
|
|
"step": 14855
|
|
},
|
|
{
|
|
"entropy": 5.50932240486145,
|
|
"epoch": 1.4747915839618897,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00047890477485662563,
|
|
"loss": 5.0753,
|
|
"mean_token_accuracy": 0.17769239395856856,
|
|
"num_tokens": 32568641.0,
|
|
"step": 14860
|
|
},
|
|
{
|
|
"entropy": 5.555522441864014,
|
|
"epoch": 1.4752878126240572,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00047888979344317236,
|
|
"loss": 5.187,
|
|
"mean_token_accuracy": 0.16348331421613693,
|
|
"num_tokens": 32578924.0,
|
|
"step": 14865
|
|
},
|
|
{
|
|
"entropy": 5.60650634765625,
|
|
"epoch": 1.4757840412862246,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00047887480697369155,
|
|
"loss": 5.145,
|
|
"mean_token_accuracy": 0.1765582025051117,
|
|
"num_tokens": 32590233.0,
|
|
"step": 14870
|
|
},
|
|
{
|
|
"entropy": 5.589346075057984,
|
|
"epoch": 1.4762802699483921,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00047885981544855475,
|
|
"loss": 5.1782,
|
|
"mean_token_accuracy": 0.1679176941514015,
|
|
"num_tokens": 32600782.0,
|
|
"step": 14875
|
|
},
|
|
{
|
|
"entropy": 5.4977126121521,
|
|
"epoch": 1.4767764986105598,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004788448188681339,
|
|
"loss": 5.1495,
|
|
"mean_token_accuracy": 0.17804412692785263,
|
|
"num_tokens": 32612611.0,
|
|
"step": 14880
|
|
},
|
|
{
|
|
"entropy": 5.602090072631836,
|
|
"epoch": 1.4772727272727273,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004788298172328007,
|
|
"loss": 5.206,
|
|
"mean_token_accuracy": 0.1728799596428871,
|
|
"num_tokens": 32623436.0,
|
|
"step": 14885
|
|
},
|
|
{
|
|
"entropy": 5.582080698013305,
|
|
"epoch": 1.4777689559348948,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00047881481054292736,
|
|
"loss": 5.0999,
|
|
"mean_token_accuracy": 0.1705150306224823,
|
|
"num_tokens": 32633356.0,
|
|
"step": 14890
|
|
},
|
|
{
|
|
"entropy": 5.5104601860046385,
|
|
"epoch": 1.4782651845970625,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00047879979879888584,
|
|
"loss": 5.1367,
|
|
"mean_token_accuracy": 0.1757357746362686,
|
|
"num_tokens": 32643927.0,
|
|
"step": 14895
|
|
},
|
|
{
|
|
"entropy": 5.481229019165039,
|
|
"epoch": 1.47876141325923,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00047878478200104845,
|
|
"loss": 5.11,
|
|
"mean_token_accuracy": 0.17548717707395553,
|
|
"num_tokens": 32655086.0,
|
|
"step": 14900
|
|
},
|
|
{
|
|
"entropy": 5.506432580947876,
|
|
"epoch": 1.4792576419213974,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004787697601497876,
|
|
"loss": 5.0577,
|
|
"mean_token_accuracy": 0.17985972613096238,
|
|
"num_tokens": 32665298.0,
|
|
"step": 14905
|
|
},
|
|
{
|
|
"entropy": 5.551363706588745,
|
|
"epoch": 1.479753870583565,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004787547332454758,
|
|
"loss": 5.1131,
|
|
"mean_token_accuracy": 0.16782129257917405,
|
|
"num_tokens": 32676717.0,
|
|
"step": 14910
|
|
},
|
|
{
|
|
"entropy": 5.5900932312011715,
|
|
"epoch": 1.4802500992457324,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00047873970128848567,
|
|
"loss": 5.191,
|
|
"mean_token_accuracy": 0.1645972102880478,
|
|
"num_tokens": 32686886.0,
|
|
"step": 14915
|
|
},
|
|
{
|
|
"entropy": 5.505083513259888,
|
|
"epoch": 1.4807463279078998,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004787246642791899,
|
|
"loss": 5.1003,
|
|
"mean_token_accuracy": 0.17709156572818757,
|
|
"num_tokens": 32698631.0,
|
|
"step": 14920
|
|
},
|
|
{
|
|
"entropy": 5.498608922958374,
|
|
"epoch": 1.4812425565700675,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.00047870962221796147,
|
|
"loss": 5.1289,
|
|
"mean_token_accuracy": 0.16633621156215667,
|
|
"num_tokens": 32710672.0,
|
|
"step": 14925
|
|
},
|
|
{
|
|
"entropy": 5.553397369384766,
|
|
"epoch": 1.481738785232235,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004786945751051734,
|
|
"loss": 5.1746,
|
|
"mean_token_accuracy": 0.16914642006158828,
|
|
"num_tokens": 32720858.0,
|
|
"step": 14930
|
|
},
|
|
{
|
|
"entropy": 5.509949350357056,
|
|
"epoch": 1.4822350138944025,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004786795229411988,
|
|
"loss": 5.1075,
|
|
"mean_token_accuracy": 0.17026506662368773,
|
|
"num_tokens": 32731592.0,
|
|
"step": 14935
|
|
},
|
|
{
|
|
"entropy": 5.61543083190918,
|
|
"epoch": 1.4827312425565702,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.00047866446572641084,
|
|
"loss": 5.1592,
|
|
"mean_token_accuracy": 0.16700685471296312,
|
|
"num_tokens": 32742777.0,
|
|
"step": 14940
|
|
},
|
|
{
|
|
"entropy": 5.5641392230987545,
|
|
"epoch": 1.4832274712187377,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004786494034611831,
|
|
"loss": 5.0983,
|
|
"mean_token_accuracy": 0.1711895078420639,
|
|
"num_tokens": 32753035.0,
|
|
"step": 14945
|
|
},
|
|
{
|
|
"entropy": 5.546930456161499,
|
|
"epoch": 1.4837236998809051,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000478634336145889,
|
|
"loss": 5.1238,
|
|
"mean_token_accuracy": 0.1683872476220131,
|
|
"num_tokens": 32764318.0,
|
|
"step": 14950
|
|
},
|
|
{
|
|
"entropy": 5.55269865989685,
|
|
"epoch": 1.4842199285430726,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00047861926378090197,
|
|
"loss": 5.1529,
|
|
"mean_token_accuracy": 0.1649496704339981,
|
|
"num_tokens": 32775521.0,
|
|
"step": 14955
|
|
},
|
|
{
|
|
"entropy": 5.6163740158081055,
|
|
"epoch": 1.48471615720524,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004786041863665961,
|
|
"loss": 5.1793,
|
|
"mean_token_accuracy": 0.17126491218805312,
|
|
"num_tokens": 32787101.0,
|
|
"step": 14960
|
|
},
|
|
{
|
|
"entropy": 5.5606588363647464,
|
|
"epoch": 1.4852123858674078,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004785891039033451,
|
|
"loss": 5.1716,
|
|
"mean_token_accuracy": 0.16909338980913163,
|
|
"num_tokens": 32798446.0,
|
|
"step": 14965
|
|
},
|
|
{
|
|
"entropy": 5.550089931488037,
|
|
"epoch": 1.4857086145295753,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.000478574016391523,
|
|
"loss": 5.1777,
|
|
"mean_token_accuracy": 0.1607951730489731,
|
|
"num_tokens": 32809636.0,
|
|
"step": 14970
|
|
},
|
|
{
|
|
"entropy": 5.495729112625122,
|
|
"epoch": 1.4862048431917427,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.000478558923831504,
|
|
"loss": 5.0742,
|
|
"mean_token_accuracy": 0.1702270820736885,
|
|
"num_tokens": 32820132.0,
|
|
"step": 14975
|
|
},
|
|
{
|
|
"entropy": 5.585244655609131,
|
|
"epoch": 1.4867010718539102,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00047854382622366235,
|
|
"loss": 5.1572,
|
|
"mean_token_accuracy": 0.1750050887465477,
|
|
"num_tokens": 32830720.0,
|
|
"step": 14980
|
|
},
|
|
{
|
|
"entropy": 5.525561332702637,
|
|
"epoch": 1.487197300516078,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00047852872356837236,
|
|
"loss": 5.11,
|
|
"mean_token_accuracy": 0.17375846356153488,
|
|
"num_tokens": 32841621.0,
|
|
"step": 14985
|
|
},
|
|
{
|
|
"entropy": 5.604021453857422,
|
|
"epoch": 1.4876935291782454,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004785136158660085,
|
|
"loss": 5.2504,
|
|
"mean_token_accuracy": 0.16192498207092285,
|
|
"num_tokens": 32852074.0,
|
|
"step": 14990
|
|
},
|
|
{
|
|
"entropy": 5.646837186813355,
|
|
"epoch": 1.4881897578404129,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00047849850311694567,
|
|
"loss": 5.1974,
|
|
"mean_token_accuracy": 0.1767324000597,
|
|
"num_tokens": 32862556.0,
|
|
"step": 14995
|
|
},
|
|
{
|
|
"entropy": 5.563993263244629,
|
|
"epoch": 1.4886859865025803,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.00047848338532155833,
|
|
"loss": 5.123,
|
|
"mean_token_accuracy": 0.17461850196123124,
|
|
"num_tokens": 32874407.0,
|
|
"step": 15000
|
|
},
|
|
{
|
|
"epoch": 1.4886859865025803,
|
|
"eval_entropy": 5.35035786092862,
|
|
"eval_loss": 5.255321979522705,
|
|
"eval_mean_token_accuracy": 0.17079043645570158,
|
|
"eval_num_tokens": 32874407.0,
|
|
"eval_runtime": 21.0033,
|
|
"eval_samples_per_second": 1603.034,
|
|
"eval_steps_per_second": 200.397,
|
|
"step": 15000
|
|
},
|
|
{
|
|
"entropy": 5.554626750946045,
|
|
"epoch": 1.4891822151647478,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00047846826248022155,
|
|
"loss": 5.1517,
|
|
"mean_token_accuracy": 0.1650475338101387,
|
|
"num_tokens": 32884986.0,
|
|
"step": 15005
|
|
},
|
|
{
|
|
"entropy": 5.5887526512146,
|
|
"epoch": 1.4896784438269155,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.00047845313459331034,
|
|
"loss": 5.2083,
|
|
"mean_token_accuracy": 0.16810910999774933,
|
|
"num_tokens": 32896016.0,
|
|
"step": 15010
|
|
},
|
|
{
|
|
"entropy": 5.533790540695191,
|
|
"epoch": 1.490174672489083,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.00047843800166119974,
|
|
"loss": 5.1051,
|
|
"mean_token_accuracy": 0.175351320207119,
|
|
"num_tokens": 32905648.0,
|
|
"step": 15015
|
|
},
|
|
{
|
|
"entropy": 5.568153953552246,
|
|
"epoch": 1.4906709011512504,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.000478422863684265,
|
|
"loss": 5.1732,
|
|
"mean_token_accuracy": 0.17154745608568192,
|
|
"num_tokens": 32917103.0,
|
|
"step": 15020
|
|
},
|
|
{
|
|
"entropy": 5.585504627227783,
|
|
"epoch": 1.4911671298134181,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.00047840772066288167,
|
|
"loss": 5.1145,
|
|
"mean_token_accuracy": 0.1708699107170105,
|
|
"num_tokens": 32928741.0,
|
|
"step": 15025
|
|
},
|
|
{
|
|
"entropy": 5.547166776657105,
|
|
"epoch": 1.4916633584755856,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004783925725974252,
|
|
"loss": 5.1752,
|
|
"mean_token_accuracy": 0.16674145460128784,
|
|
"num_tokens": 32939292.0,
|
|
"step": 15030
|
|
},
|
|
{
|
|
"entropy": 5.569071197509766,
|
|
"epoch": 1.492159587137753,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004783774194882712,
|
|
"loss": 5.1652,
|
|
"mean_token_accuracy": 0.16695128083229066,
|
|
"num_tokens": 32949940.0,
|
|
"step": 15035
|
|
},
|
|
{
|
|
"entropy": 5.543909549713135,
|
|
"epoch": 1.4926558157999206,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004783622613357954,
|
|
"loss": 5.1315,
|
|
"mean_token_accuracy": 0.17065854519605636,
|
|
"num_tokens": 32961222.0,
|
|
"step": 15040
|
|
},
|
|
{
|
|
"entropy": 5.492350292205811,
|
|
"epoch": 1.493152044462088,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004783470981403737,
|
|
"loss": 5.1198,
|
|
"mean_token_accuracy": 0.1739916533231735,
|
|
"num_tokens": 32972095.0,
|
|
"step": 15045
|
|
},
|
|
{
|
|
"entropy": 5.572208499908447,
|
|
"epoch": 1.4936482731242555,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004783319299023821,
|
|
"loss": 5.1476,
|
|
"mean_token_accuracy": 0.17626485526561736,
|
|
"num_tokens": 32981834.0,
|
|
"step": 15050
|
|
},
|
|
{
|
|
"entropy": 5.674044942855835,
|
|
"epoch": 1.4941445017864232,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004783167566221969,
|
|
"loss": 5.2388,
|
|
"mean_token_accuracy": 0.16360479593276978,
|
|
"num_tokens": 32994347.0,
|
|
"step": 15055
|
|
},
|
|
{
|
|
"entropy": 5.651814270019531,
|
|
"epoch": 1.4946407304485907,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00047830157830019423,
|
|
"loss": 5.2059,
|
|
"mean_token_accuracy": 0.16891241669654847,
|
|
"num_tokens": 33004780.0,
|
|
"step": 15060
|
|
},
|
|
{
|
|
"entropy": 5.572425079345703,
|
|
"epoch": 1.4951369591107582,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004782863949367505,
|
|
"loss": 5.1599,
|
|
"mean_token_accuracy": 0.16840120255947114,
|
|
"num_tokens": 33015697.0,
|
|
"step": 15065
|
|
},
|
|
{
|
|
"entropy": 5.503729009628296,
|
|
"epoch": 1.4956331877729259,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004782712065322421,
|
|
"loss": 5.1415,
|
|
"mean_token_accuracy": 0.16683482825756074,
|
|
"num_tokens": 33026563.0,
|
|
"step": 15070
|
|
},
|
|
{
|
|
"entropy": 5.588099575042724,
|
|
"epoch": 1.4961294164350933,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004782560130870459,
|
|
"loss": 5.1747,
|
|
"mean_token_accuracy": 0.16130253672599792,
|
|
"num_tokens": 33037290.0,
|
|
"step": 15075
|
|
},
|
|
{
|
|
"entropy": 5.628545093536377,
|
|
"epoch": 1.4966256450972608,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.00047824081460153846,
|
|
"loss": 5.1043,
|
|
"mean_token_accuracy": 0.17105162888765335,
|
|
"num_tokens": 33047199.0,
|
|
"step": 15080
|
|
},
|
|
{
|
|
"entropy": 5.500002098083496,
|
|
"epoch": 1.4971218737594283,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004782256110760969,
|
|
"loss": 5.1172,
|
|
"mean_token_accuracy": 0.1685728833079338,
|
|
"num_tokens": 33057253.0,
|
|
"step": 15085
|
|
},
|
|
{
|
|
"entropy": 5.5785651206970215,
|
|
"epoch": 1.4976181024215958,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000478210402511098,
|
|
"loss": 5.2578,
|
|
"mean_token_accuracy": 0.1641707092523575,
|
|
"num_tokens": 33068228.0,
|
|
"step": 15090
|
|
},
|
|
{
|
|
"entropy": 5.622333240509033,
|
|
"epoch": 1.4981143310837635,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004781951889069189,
|
|
"loss": 5.2197,
|
|
"mean_token_accuracy": 0.17025210857391357,
|
|
"num_tokens": 33079285.0,
|
|
"step": 15095
|
|
},
|
|
{
|
|
"entropy": 5.536925792694092,
|
|
"epoch": 1.498610559745931,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.00047817997026393714,
|
|
"loss": 5.0698,
|
|
"mean_token_accuracy": 0.17296504974365234,
|
|
"num_tokens": 33091253.0,
|
|
"step": 15100
|
|
},
|
|
{
|
|
"entropy": 5.499868535995484,
|
|
"epoch": 1.4991067884080984,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.00047816474658252985,
|
|
"loss": 5.1011,
|
|
"mean_token_accuracy": 0.17394308596849442,
|
|
"num_tokens": 33102492.0,
|
|
"step": 15105
|
|
},
|
|
{
|
|
"entropy": 5.490017223358154,
|
|
"epoch": 1.499603017070266,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00047814951786307467,
|
|
"loss": 5.1278,
|
|
"mean_token_accuracy": 0.16923998445272445,
|
|
"num_tokens": 33115038.0,
|
|
"step": 15110
|
|
},
|
|
{
|
|
"entropy": 5.558667469024658,
|
|
"epoch": 1.5000992457324336,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004781342841059492,
|
|
"loss": 5.1017,
|
|
"mean_token_accuracy": 0.1734825849533081,
|
|
"num_tokens": 33124470.0,
|
|
"step": 15115
|
|
},
|
|
{
|
|
"entropy": 5.541827583312989,
|
|
"epoch": 1.500595474394601,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004781190453115311,
|
|
"loss": 5.1193,
|
|
"mean_token_accuracy": 0.17209340929985045,
|
|
"num_tokens": 33135994.0,
|
|
"step": 15120
|
|
},
|
|
{
|
|
"entropy": 5.510991096496582,
|
|
"epoch": 1.5010917030567685,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00047810380148019847,
|
|
"loss": 5.1294,
|
|
"mean_token_accuracy": 0.17178987711668015,
|
|
"num_tokens": 33145783.0,
|
|
"step": 15125
|
|
},
|
|
{
|
|
"entropy": 5.518322372436524,
|
|
"epoch": 1.501587931718936,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00047808855261232915,
|
|
"loss": 5.2334,
|
|
"mean_token_accuracy": 0.17065344452857972,
|
|
"num_tokens": 33156404.0,
|
|
"step": 15130
|
|
},
|
|
{
|
|
"entropy": 5.563249492645264,
|
|
"epoch": 1.5020841603811035,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.00047807329870830134,
|
|
"loss": 5.2249,
|
|
"mean_token_accuracy": 0.16813631504774093,
|
|
"num_tokens": 33168226.0,
|
|
"step": 15135
|
|
},
|
|
{
|
|
"entropy": 5.559996652603149,
|
|
"epoch": 1.5025803890432712,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004780580397684933,
|
|
"loss": 5.1422,
|
|
"mean_token_accuracy": 0.16867240965366365,
|
|
"num_tokens": 33178265.0,
|
|
"step": 15140
|
|
},
|
|
{
|
|
"entropy": 5.528187274932861,
|
|
"epoch": 1.5030766177054387,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004780427757932835,
|
|
"loss": 5.1002,
|
|
"mean_token_accuracy": 0.17924540638923644,
|
|
"num_tokens": 33188992.0,
|
|
"step": 15145
|
|
},
|
|
{
|
|
"entropy": 5.542638301849365,
|
|
"epoch": 1.5035728463676064,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004780275067830503,
|
|
"loss": 5.1766,
|
|
"mean_token_accuracy": 0.1707996666431427,
|
|
"num_tokens": 33199424.0,
|
|
"step": 15150
|
|
},
|
|
{
|
|
"entropy": 5.531479692459106,
|
|
"epoch": 1.5040690750297738,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004780122327381725,
|
|
"loss": 5.0979,
|
|
"mean_token_accuracy": 0.18169230818748475,
|
|
"num_tokens": 33210900.0,
|
|
"step": 15155
|
|
},
|
|
{
|
|
"entropy": 5.592750024795532,
|
|
"epoch": 1.5045653036919413,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.00047799695365902865,
|
|
"loss": 5.1743,
|
|
"mean_token_accuracy": 0.16534914076328278,
|
|
"num_tokens": 33220796.0,
|
|
"step": 15160
|
|
},
|
|
{
|
|
"entropy": 5.5601893901824955,
|
|
"epoch": 1.5050615323541088,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004779816695459979,
|
|
"loss": 5.1517,
|
|
"mean_token_accuracy": 0.1704527273774147,
|
|
"num_tokens": 33233454.0,
|
|
"step": 15165
|
|
},
|
|
{
|
|
"entropy": 5.566911077499389,
|
|
"epoch": 1.5055577610162763,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004779663803994591,
|
|
"loss": 5.0857,
|
|
"mean_token_accuracy": 0.1749548941850662,
|
|
"num_tokens": 33243574.0,
|
|
"step": 15170
|
|
},
|
|
{
|
|
"entropy": 5.550911569595337,
|
|
"epoch": 1.5060539896784437,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004779510862197914,
|
|
"loss": 5.1286,
|
|
"mean_token_accuracy": 0.16912004500627517,
|
|
"num_tokens": 33256298.0,
|
|
"step": 15175
|
|
},
|
|
{
|
|
"entropy": 5.588207387924195,
|
|
"epoch": 1.5065502183406112,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004779357870073741,
|
|
"loss": 5.2319,
|
|
"mean_token_accuracy": 0.16805994808673858,
|
|
"num_tokens": 33268089.0,
|
|
"step": 15180
|
|
},
|
|
{
|
|
"entropy": 5.528545761108399,
|
|
"epoch": 1.507046447002779,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00047792048276258653,
|
|
"loss": 5.1488,
|
|
"mean_token_accuracy": 0.16780902147293092,
|
|
"num_tokens": 33279955.0,
|
|
"step": 15185
|
|
},
|
|
{
|
|
"entropy": 5.52419638633728,
|
|
"epoch": 1.5075426756649464,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004779051734858083,
|
|
"loss": 5.1292,
|
|
"mean_token_accuracy": 0.16726892441511154,
|
|
"num_tokens": 33291470.0,
|
|
"step": 15190
|
|
},
|
|
{
|
|
"entropy": 5.580616283416748,
|
|
"epoch": 1.508038904327114,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00047788985917741894,
|
|
"loss": 5.1589,
|
|
"mean_token_accuracy": 0.1763240337371826,
|
|
"num_tokens": 33304169.0,
|
|
"step": 15195
|
|
},
|
|
{
|
|
"entropy": 5.479222393035888,
|
|
"epoch": 1.5085351329892815,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00047787453983779826,
|
|
"loss": 5.0122,
|
|
"mean_token_accuracy": 0.17872458398342134,
|
|
"num_tokens": 33314436.0,
|
|
"step": 15200
|
|
},
|
|
{
|
|
"entropy": 5.530719041824341,
|
|
"epoch": 1.509031361651449,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004778592154673262,
|
|
"loss": 5.2258,
|
|
"mean_token_accuracy": 0.16716734170913697,
|
|
"num_tokens": 33325361.0,
|
|
"step": 15205
|
|
},
|
|
{
|
|
"entropy": 5.450767612457275,
|
|
"epoch": 1.5095275903136165,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00047784388606638263,
|
|
"loss": 5.1015,
|
|
"mean_token_accuracy": 0.16731740683317184,
|
|
"num_tokens": 33336644.0,
|
|
"step": 15210
|
|
},
|
|
{
|
|
"entropy": 5.542257261276245,
|
|
"epoch": 1.510023818975784,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004778285516353478,
|
|
"loss": 5.153,
|
|
"mean_token_accuracy": 0.16704134345054628,
|
|
"num_tokens": 33348418.0,
|
|
"step": 15215
|
|
},
|
|
{
|
|
"entropy": 5.546857166290283,
|
|
"epoch": 1.5105200476379514,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.00047781321217460205,
|
|
"loss": 5.1008,
|
|
"mean_token_accuracy": 0.17379361242055893,
|
|
"num_tokens": 33360615.0,
|
|
"step": 15220
|
|
},
|
|
{
|
|
"entropy": 5.5339882373809814,
|
|
"epoch": 1.5110162763001191,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00047779786768452554,
|
|
"loss": 5.1044,
|
|
"mean_token_accuracy": 0.1691182181239128,
|
|
"num_tokens": 33372030.0,
|
|
"step": 15225
|
|
},
|
|
{
|
|
"entropy": 5.537009286880493,
|
|
"epoch": 1.5115125049622866,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00047778251816549895,
|
|
"loss": 5.1229,
|
|
"mean_token_accuracy": 0.16500473916530609,
|
|
"num_tokens": 33382834.0,
|
|
"step": 15230
|
|
},
|
|
{
|
|
"entropy": 5.533806085586548,
|
|
"epoch": 1.512008733624454,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.00047776716361790284,
|
|
"loss": 5.1379,
|
|
"mean_token_accuracy": 0.17281102687120437,
|
|
"num_tokens": 33393250.0,
|
|
"step": 15235
|
|
},
|
|
{
|
|
"entropy": 5.523517274856568,
|
|
"epoch": 1.5125049622866218,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00047775180404211804,
|
|
"loss": 5.0835,
|
|
"mean_token_accuracy": 0.17765696346759796,
|
|
"num_tokens": 33402778.0,
|
|
"step": 15240
|
|
},
|
|
{
|
|
"entropy": 5.5844526290893555,
|
|
"epoch": 1.5130011909487893,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004777364394385254,
|
|
"loss": 5.1716,
|
|
"mean_token_accuracy": 0.1688630297780037,
|
|
"num_tokens": 33413565.0,
|
|
"step": 15245
|
|
},
|
|
{
|
|
"entropy": 5.597110939025879,
|
|
"epoch": 1.5134974196109567,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.00047772106980750593,
|
|
"loss": 5.1123,
|
|
"mean_token_accuracy": 0.17104207575321198,
|
|
"num_tokens": 33424108.0,
|
|
"step": 15250
|
|
},
|
|
{
|
|
"entropy": 5.535395956039428,
|
|
"epoch": 1.5139936482731242,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004777056951494407,
|
|
"loss": 5.1934,
|
|
"mean_token_accuracy": 0.16497849225997924,
|
|
"num_tokens": 33435683.0,
|
|
"step": 15255
|
|
},
|
|
{
|
|
"entropy": 5.522085094451905,
|
|
"epoch": 1.5144898769352917,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000477690315464711,
|
|
"loss": 5.1591,
|
|
"mean_token_accuracy": 0.17248237878084183,
|
|
"num_tokens": 33446267.0,
|
|
"step": 15260
|
|
},
|
|
{
|
|
"entropy": 5.515142154693604,
|
|
"epoch": 1.5149861055974592,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.00047767493075369827,
|
|
"loss": 5.0704,
|
|
"mean_token_accuracy": 0.18734150230884553,
|
|
"num_tokens": 33457901.0,
|
|
"step": 15265
|
|
},
|
|
{
|
|
"entropy": 5.587907075881958,
|
|
"epoch": 1.5154823342596269,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.000477659541016784,
|
|
"loss": 5.2391,
|
|
"mean_token_accuracy": 0.17015222162008287,
|
|
"num_tokens": 33469215.0,
|
|
"step": 15270
|
|
},
|
|
{
|
|
"entropy": 5.560878896713257,
|
|
"epoch": 1.5159785629217943,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00047764414625434983,
|
|
"loss": 5.1081,
|
|
"mean_token_accuracy": 0.17409939616918563,
|
|
"num_tokens": 33480384.0,
|
|
"step": 15275
|
|
},
|
|
{
|
|
"entropy": 5.552048778533935,
|
|
"epoch": 1.516474791583962,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004776287464667774,
|
|
"loss": 5.1014,
|
|
"mean_token_accuracy": 0.17710302174091339,
|
|
"num_tokens": 33491404.0,
|
|
"step": 15280
|
|
},
|
|
{
|
|
"entropy": 5.626476049423218,
|
|
"epoch": 1.5169710202461295,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.00047761334165444876,
|
|
"loss": 5.2384,
|
|
"mean_token_accuracy": 0.1626495823264122,
|
|
"num_tokens": 33501888.0,
|
|
"step": 15285
|
|
},
|
|
{
|
|
"entropy": 5.567591142654419,
|
|
"epoch": 1.517467248908297,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.00047759793181774586,
|
|
"loss": 5.1709,
|
|
"mean_token_accuracy": 0.1713092014193535,
|
|
"num_tokens": 33513274.0,
|
|
"step": 15290
|
|
},
|
|
{
|
|
"entropy": 5.552818870544433,
|
|
"epoch": 1.5179634775704645,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00047758251695705073,
|
|
"loss": 5.1742,
|
|
"mean_token_accuracy": 0.1670441672205925,
|
|
"num_tokens": 33524188.0,
|
|
"step": 15295
|
|
},
|
|
{
|
|
"entropy": 5.563287162780762,
|
|
"epoch": 1.518459706232632,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00047756709707274576,
|
|
"loss": 5.213,
|
|
"mean_token_accuracy": 0.16973214894533156,
|
|
"num_tokens": 33535207.0,
|
|
"step": 15300
|
|
},
|
|
{
|
|
"entropy": 5.610132312774658,
|
|
"epoch": 1.5189559348947994,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004775516721652133,
|
|
"loss": 5.164,
|
|
"mean_token_accuracy": 0.16901655495166779,
|
|
"num_tokens": 33546154.0,
|
|
"step": 15305
|
|
},
|
|
{
|
|
"entropy": 5.547743606567383,
|
|
"epoch": 1.519452163556967,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004775362422348358,
|
|
"loss": 5.0978,
|
|
"mean_token_accuracy": 0.170930977165699,
|
|
"num_tokens": 33555365.0,
|
|
"step": 15310
|
|
},
|
|
{
|
|
"entropy": 5.532332944869995,
|
|
"epoch": 1.5199483922191346,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.00047752080728199586,
|
|
"loss": 5.1431,
|
|
"mean_token_accuracy": 0.16855551451444625,
|
|
"num_tokens": 33566316.0,
|
|
"step": 15315
|
|
},
|
|
{
|
|
"entropy": 5.538038635253907,
|
|
"epoch": 1.520444620881302,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004775053673070764,
|
|
"loss": 5.0765,
|
|
"mean_token_accuracy": 0.1789124056696892,
|
|
"num_tokens": 33576549.0,
|
|
"step": 15320
|
|
},
|
|
{
|
|
"entropy": 5.521228551864624,
|
|
"epoch": 1.5209408495434698,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004774899223104601,
|
|
"loss": 5.1379,
|
|
"mean_token_accuracy": 0.1723025009036064,
|
|
"num_tokens": 33586681.0,
|
|
"step": 15325
|
|
},
|
|
{
|
|
"entropy": 5.6190918445587155,
|
|
"epoch": 1.5214370782056372,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004774744722925301,
|
|
"loss": 5.2631,
|
|
"mean_token_accuracy": 0.1627289354801178,
|
|
"num_tokens": 33599201.0,
|
|
"step": 15330
|
|
},
|
|
{
|
|
"entropy": 5.591014432907104,
|
|
"epoch": 1.5219333068678047,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004774590172536695,
|
|
"loss": 5.1337,
|
|
"mean_token_accuracy": 0.17084709405899048,
|
|
"num_tokens": 33610217.0,
|
|
"step": 15335
|
|
},
|
|
{
|
|
"entropy": 5.544988012313842,
|
|
"epoch": 1.5224295355299722,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00047744355719426146,
|
|
"loss": 5.1609,
|
|
"mean_token_accuracy": 0.17455919235944747,
|
|
"num_tokens": 33620586.0,
|
|
"step": 15340
|
|
},
|
|
{
|
|
"entropy": 5.532115173339844,
|
|
"epoch": 1.5229257641921397,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.00047742809211468953,
|
|
"loss": 5.1381,
|
|
"mean_token_accuracy": 0.17375372499227523,
|
|
"num_tokens": 33630712.0,
|
|
"step": 15345
|
|
},
|
|
{
|
|
"entropy": 5.517926502227783,
|
|
"epoch": 1.5234219928543071,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.000477412622015337,
|
|
"loss": 5.1047,
|
|
"mean_token_accuracy": 0.17157377004623414,
|
|
"num_tokens": 33640367.0,
|
|
"step": 15350
|
|
},
|
|
{
|
|
"entropy": 5.5922643661499025,
|
|
"epoch": 1.5239182215164748,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004773971468965876,
|
|
"loss": 5.1848,
|
|
"mean_token_accuracy": 0.16498054713010787,
|
|
"num_tokens": 33651816.0,
|
|
"step": 15355
|
|
},
|
|
{
|
|
"entropy": 5.550317668914795,
|
|
"epoch": 1.5244144501786423,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00047738166675882516,
|
|
"loss": 5.0736,
|
|
"mean_token_accuracy": 0.1746278539299965,
|
|
"num_tokens": 33663661.0,
|
|
"step": 15360
|
|
},
|
|
{
|
|
"entropy": 5.45186939239502,
|
|
"epoch": 1.52491067884081,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004773661816024335,
|
|
"loss": 5.0022,
|
|
"mean_token_accuracy": 0.1824497327208519,
|
|
"num_tokens": 33673670.0,
|
|
"step": 15365
|
|
},
|
|
{
|
|
"entropy": 5.5002635478973385,
|
|
"epoch": 1.5254069075029775,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004773506914277965,
|
|
"loss": 5.219,
|
|
"mean_token_accuracy": 0.1662943631410599,
|
|
"num_tokens": 33685434.0,
|
|
"step": 15370
|
|
},
|
|
{
|
|
"entropy": 5.582822227478028,
|
|
"epoch": 1.525903136165145,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.00047733519623529853,
|
|
"loss": 5.1726,
|
|
"mean_token_accuracy": 0.17017682194709777,
|
|
"num_tokens": 33696751.0,
|
|
"step": 15375
|
|
},
|
|
{
|
|
"entropy": 5.5826146602630615,
|
|
"epoch": 1.5263993648273124,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004773196960253236,
|
|
"loss": 5.1117,
|
|
"mean_token_accuracy": 0.17130072116851808,
|
|
"num_tokens": 33708141.0,
|
|
"step": 15380
|
|
},
|
|
{
|
|
"entropy": 5.448153877258301,
|
|
"epoch": 1.52689559348948,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004773041907982561,
|
|
"loss": 4.9879,
|
|
"mean_token_accuracy": 0.179925836622715,
|
|
"num_tokens": 33719219.0,
|
|
"step": 15385
|
|
},
|
|
{
|
|
"entropy": 5.546548080444336,
|
|
"epoch": 1.5273918221516474,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.00047728868055448064,
|
|
"loss": 5.1375,
|
|
"mean_token_accuracy": 0.1689855009317398,
|
|
"num_tokens": 33730493.0,
|
|
"step": 15390
|
|
},
|
|
{
|
|
"entropy": 5.592306280136109,
|
|
"epoch": 1.5278880508138148,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004772731652943818,
|
|
"loss": 5.1986,
|
|
"mean_token_accuracy": 0.16408584117889405,
|
|
"num_tokens": 33740273.0,
|
|
"step": 15395
|
|
},
|
|
{
|
|
"entropy": 5.5661030292510985,
|
|
"epoch": 1.5283842794759825,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004772576450183444,
|
|
"loss": 5.1628,
|
|
"mean_token_accuracy": 0.17227281183004378,
|
|
"num_tokens": 33752162.0,
|
|
"step": 15400
|
|
},
|
|
{
|
|
"entropy": 5.559649562835693,
|
|
"epoch": 1.52888050813815,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00047724211972675315,
|
|
"loss": 5.1089,
|
|
"mean_token_accuracy": 0.17103544473648072,
|
|
"num_tokens": 33763139.0,
|
|
"step": 15405
|
|
},
|
|
{
|
|
"entropy": 5.520846557617188,
|
|
"epoch": 1.5293767368003177,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004772265894199931,
|
|
"loss": 5.1577,
|
|
"mean_token_accuracy": 0.1723170757293701,
|
|
"num_tokens": 33774641.0,
|
|
"step": 15410
|
|
},
|
|
{
|
|
"entropy": 5.549260997772217,
|
|
"epoch": 1.5298729654624852,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004772110540984494,
|
|
"loss": 5.1115,
|
|
"mean_token_accuracy": 0.18366141021251678,
|
|
"num_tokens": 33785644.0,
|
|
"step": 15415
|
|
},
|
|
{
|
|
"entropy": 5.618649005889893,
|
|
"epoch": 1.5303691941246527,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004771955137625073,
|
|
"loss": 5.2728,
|
|
"mean_token_accuracy": 0.15961731672286988,
|
|
"num_tokens": 33797880.0,
|
|
"step": 15420
|
|
},
|
|
{
|
|
"entropy": 5.52158145904541,
|
|
"epoch": 1.5308654227868201,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00047717996841255224,
|
|
"loss": 5.0784,
|
|
"mean_token_accuracy": 0.17061331272125244,
|
|
"num_tokens": 33808782.0,
|
|
"step": 15425
|
|
},
|
|
{
|
|
"entropy": 5.501331567764282,
|
|
"epoch": 1.5313616514489876,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00047716441804896955,
|
|
"loss": 5.1086,
|
|
"mean_token_accuracy": 0.17796216160058975,
|
|
"num_tokens": 33818483.0,
|
|
"step": 15430
|
|
},
|
|
{
|
|
"entropy": 5.506070995330811,
|
|
"epoch": 1.531857880111155,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004771488626721449,
|
|
"loss": 5.1309,
|
|
"mean_token_accuracy": 0.1669403940439224,
|
|
"num_tokens": 33828590.0,
|
|
"step": 15435
|
|
},
|
|
{
|
|
"entropy": 5.591064739227295,
|
|
"epoch": 1.5323541087733228,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00047713330228246406,
|
|
"loss": 5.2146,
|
|
"mean_token_accuracy": 0.16426829248666763,
|
|
"num_tokens": 33838978.0,
|
|
"step": 15440
|
|
},
|
|
{
|
|
"entropy": 5.546977138519287,
|
|
"epoch": 1.5328503374354903,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004771177368803129,
|
|
"loss": 5.1452,
|
|
"mean_token_accuracy": 0.16866506189107894,
|
|
"num_tokens": 33851244.0,
|
|
"step": 15445
|
|
},
|
|
{
|
|
"entropy": 5.5352836608886715,
|
|
"epoch": 1.533346566097658,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00047710216646607733,
|
|
"loss": 5.0403,
|
|
"mean_token_accuracy": 0.17950624078512192,
|
|
"num_tokens": 33861666.0,
|
|
"step": 15450
|
|
},
|
|
{
|
|
"entropy": 5.551935148239136,
|
|
"epoch": 1.5338427947598254,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00047708659104014363,
|
|
"loss": 5.1294,
|
|
"mean_token_accuracy": 0.17123485654592513,
|
|
"num_tokens": 33872416.0,
|
|
"step": 15455
|
|
},
|
|
{
|
|
"entropy": 5.51541919708252,
|
|
"epoch": 1.534339023421993,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004770710106028978,
|
|
"loss": 5.1169,
|
|
"mean_token_accuracy": 0.17378889471292497,
|
|
"num_tokens": 33881808.0,
|
|
"step": 15460
|
|
},
|
|
{
|
|
"entropy": 5.589226913452149,
|
|
"epoch": 1.5348352520841604,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00047705542515472647,
|
|
"loss": 5.1926,
|
|
"mean_token_accuracy": 0.17101919651031494,
|
|
"num_tokens": 33892925.0,
|
|
"step": 15465
|
|
},
|
|
{
|
|
"entropy": 5.559091520309448,
|
|
"epoch": 1.5353314807463279,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004770398346960159,
|
|
"loss": 5.1301,
|
|
"mean_token_accuracy": 0.16781868487596513,
|
|
"num_tokens": 33903702.0,
|
|
"step": 15470
|
|
},
|
|
{
|
|
"entropy": 5.591299343109131,
|
|
"epoch": 1.5358277094084953,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00047702423922715284,
|
|
"loss": 5.2128,
|
|
"mean_token_accuracy": 0.17060076594352722,
|
|
"num_tokens": 33917233.0,
|
|
"step": 15475
|
|
},
|
|
{
|
|
"entropy": 5.585413789749145,
|
|
"epoch": 1.5363239380706628,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004770086387485239,
|
|
"loss": 5.1747,
|
|
"mean_token_accuracy": 0.17281627655029297,
|
|
"num_tokens": 33928362.0,
|
|
"step": 15480
|
|
},
|
|
{
|
|
"entropy": 5.62237229347229,
|
|
"epoch": 1.5368201667328305,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.000476993033260516,
|
|
"loss": 5.1919,
|
|
"mean_token_accuracy": 0.1707867667078972,
|
|
"num_tokens": 33938624.0,
|
|
"step": 15485
|
|
},
|
|
{
|
|
"entropy": 5.508676242828369,
|
|
"epoch": 1.537316395394998,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004769774227635162,
|
|
"loss": 5.095,
|
|
"mean_token_accuracy": 0.1748700723052025,
|
|
"num_tokens": 33950058.0,
|
|
"step": 15490
|
|
},
|
|
{
|
|
"entropy": 5.565647745132447,
|
|
"epoch": 1.5378126240571657,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004769618072579115,
|
|
"loss": 5.1887,
|
|
"mean_token_accuracy": 0.16761232614517213,
|
|
"num_tokens": 33962404.0,
|
|
"step": 15495
|
|
},
|
|
{
|
|
"entropy": 5.590378046035767,
|
|
"epoch": 1.5383088527193332,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.00047694618674408917,
|
|
"loss": 5.1466,
|
|
"mean_token_accuracy": 0.16801785230636596,
|
|
"num_tokens": 33973095.0,
|
|
"step": 15500
|
|
},
|
|
{
|
|
"entropy": 5.547408533096314,
|
|
"epoch": 1.5388050813815006,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.00047693056122243655,
|
|
"loss": 5.1556,
|
|
"mean_token_accuracy": 0.16770165860652925,
|
|
"num_tokens": 33984152.0,
|
|
"step": 15505
|
|
},
|
|
{
|
|
"entropy": 5.585107326507568,
|
|
"epoch": 1.539301310043668,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00047691493069334124,
|
|
"loss": 5.1689,
|
|
"mean_token_accuracy": 0.16799376159906387,
|
|
"num_tokens": 33994854.0,
|
|
"step": 15510
|
|
},
|
|
{
|
|
"entropy": 5.5745879173278805,
|
|
"epoch": 1.5397975387058356,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.00047689929515719066,
|
|
"loss": 5.1832,
|
|
"mean_token_accuracy": 0.17225729525089264,
|
|
"num_tokens": 34006573.0,
|
|
"step": 15515
|
|
},
|
|
{
|
|
"entropy": 5.552916860580444,
|
|
"epoch": 1.540293767368003,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00047688365461437263,
|
|
"loss": 5.0989,
|
|
"mean_token_accuracy": 0.16951732635498046,
|
|
"num_tokens": 34016537.0,
|
|
"step": 15520
|
|
},
|
|
{
|
|
"entropy": 5.5335992813110355,
|
|
"epoch": 1.5407899960301707,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00047686800906527493,
|
|
"loss": 5.1269,
|
|
"mean_token_accuracy": 0.178988978266716,
|
|
"num_tokens": 34026825.0,
|
|
"step": 15525
|
|
},
|
|
{
|
|
"entropy": 5.601338958740234,
|
|
"epoch": 1.5412862246923382,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004768523585102856,
|
|
"loss": 5.1285,
|
|
"mean_token_accuracy": 0.17599419206380845,
|
|
"num_tokens": 34036786.0,
|
|
"step": 15530
|
|
},
|
|
{
|
|
"entropy": 5.58551812171936,
|
|
"epoch": 1.541782453354506,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004768367029497928,
|
|
"loss": 5.1232,
|
|
"mean_token_accuracy": 0.1749888151884079,
|
|
"num_tokens": 34046784.0,
|
|
"step": 15535
|
|
},
|
|
{
|
|
"entropy": 5.576945066452026,
|
|
"epoch": 1.5422786820166734,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00047682104238418464,
|
|
"loss": 5.1726,
|
|
"mean_token_accuracy": 0.17262601256370544,
|
|
"num_tokens": 34058250.0,
|
|
"step": 15540
|
|
},
|
|
{
|
|
"entropy": 5.4955487728118895,
|
|
"epoch": 1.5427749106788409,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00047680537681384956,
|
|
"loss": 5.1112,
|
|
"mean_token_accuracy": 0.17404531836509704,
|
|
"num_tokens": 34069969.0,
|
|
"step": 15545
|
|
},
|
|
{
|
|
"entropy": 5.605706977844238,
|
|
"epoch": 1.5432711393410083,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004767897062391759,
|
|
"loss": 5.2115,
|
|
"mean_token_accuracy": 0.1702331081032753,
|
|
"num_tokens": 34080817.0,
|
|
"step": 15550
|
|
},
|
|
{
|
|
"entropy": 5.567223834991455,
|
|
"epoch": 1.5437673680031758,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004767740306605524,
|
|
"loss": 5.1505,
|
|
"mean_token_accuracy": 0.1668059140443802,
|
|
"num_tokens": 34091138.0,
|
|
"step": 15555
|
|
},
|
|
{
|
|
"entropy": 5.545876979827881,
|
|
"epoch": 1.5442635966653433,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004767583500783677,
|
|
"loss": 5.0837,
|
|
"mean_token_accuracy": 0.18054493963718415,
|
|
"num_tokens": 34102035.0,
|
|
"step": 15560
|
|
},
|
|
{
|
|
"entropy": 5.550889921188355,
|
|
"epoch": 1.5447598253275108,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.00047674266449301074,
|
|
"loss": 5.1482,
|
|
"mean_token_accuracy": 0.1734504833817482,
|
|
"num_tokens": 34112533.0,
|
|
"step": 15565
|
|
},
|
|
{
|
|
"entropy": 5.541175174713135,
|
|
"epoch": 1.5452560539896785,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.00047672697390487034,
|
|
"loss": 5.1444,
|
|
"mean_token_accuracy": 0.17447938472032548,
|
|
"num_tokens": 34124196.0,
|
|
"step": 15570
|
|
},
|
|
{
|
|
"entropy": 5.5504638195037845,
|
|
"epoch": 1.545752282651846,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004767112783143357,
|
|
"loss": 5.1229,
|
|
"mean_token_accuracy": 0.17578904777765275,
|
|
"num_tokens": 34135635.0,
|
|
"step": 15575
|
|
},
|
|
{
|
|
"entropy": 5.503779363632202,
|
|
"epoch": 1.5462485113140136,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.000476695577721796,
|
|
"loss": 5.0579,
|
|
"mean_token_accuracy": 0.1799115866422653,
|
|
"num_tokens": 34146202.0,
|
|
"step": 15580
|
|
},
|
|
{
|
|
"entropy": 5.52239408493042,
|
|
"epoch": 1.5467447399761811,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.00047667987212764065,
|
|
"loss": 5.1026,
|
|
"mean_token_accuracy": 0.1759197324514389,
|
|
"num_tokens": 34157354.0,
|
|
"step": 15585
|
|
},
|
|
{
|
|
"entropy": 5.554458808898926,
|
|
"epoch": 1.5472409686383486,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.00047666416153225894,
|
|
"loss": 5.1742,
|
|
"mean_token_accuracy": 0.16596896797418595,
|
|
"num_tokens": 34168563.0,
|
|
"step": 15590
|
|
},
|
|
{
|
|
"entropy": 5.558117198944092,
|
|
"epoch": 1.547737197300516,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004766484459360406,
|
|
"loss": 5.0993,
|
|
"mean_token_accuracy": 0.17693301886320115,
|
|
"num_tokens": 34178604.0,
|
|
"step": 15595
|
|
},
|
|
{
|
|
"entropy": 5.56316556930542,
|
|
"epoch": 1.5482334259626835,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00047663272533937537,
|
|
"loss": 5.1449,
|
|
"mean_token_accuracy": 0.17188220471143723,
|
|
"num_tokens": 34190321.0,
|
|
"step": 15600
|
|
},
|
|
{
|
|
"entropy": 5.5182630062103275,
|
|
"epoch": 1.548729654624851,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.00047661699974265294,
|
|
"loss": 5.1527,
|
|
"mean_token_accuracy": 0.16989970803260804,
|
|
"num_tokens": 34201519.0,
|
|
"step": 15605
|
|
},
|
|
{
|
|
"entropy": 5.506045722961426,
|
|
"epoch": 1.5492258832870187,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.00047660126914626344,
|
|
"loss": 5.0958,
|
|
"mean_token_accuracy": 0.17159055024385453,
|
|
"num_tokens": 34212710.0,
|
|
"step": 15610
|
|
},
|
|
{
|
|
"entropy": 5.592389535903931,
|
|
"epoch": 1.5497221119491862,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004765855335505969,
|
|
"loss": 5.2244,
|
|
"mean_token_accuracy": 0.16767915785312654,
|
|
"num_tokens": 34223187.0,
|
|
"step": 15615
|
|
},
|
|
{
|
|
"entropy": 5.572989273071289,
|
|
"epoch": 1.5502183406113537,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004765697929560434,
|
|
"loss": 5.1657,
|
|
"mean_token_accuracy": 0.1772853121161461,
|
|
"num_tokens": 34234530.0,
|
|
"step": 15620
|
|
},
|
|
{
|
|
"entropy": 5.592358255386353,
|
|
"epoch": 1.5507145692735214,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.00047655404736299354,
|
|
"loss": 5.1705,
|
|
"mean_token_accuracy": 0.16713092476129532,
|
|
"num_tokens": 34245003.0,
|
|
"step": 15625
|
|
},
|
|
{
|
|
"entropy": 5.553425407409668,
|
|
"epoch": 1.5512107979356888,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00047653829677183745,
|
|
"loss": 5.1407,
|
|
"mean_token_accuracy": 0.17425866723060607,
|
|
"num_tokens": 34255630.0,
|
|
"step": 15630
|
|
},
|
|
{
|
|
"entropy": 5.5319568634033205,
|
|
"epoch": 1.5517070265978563,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.00047652254118296596,
|
|
"loss": 5.12,
|
|
"mean_token_accuracy": 0.17600819021463393,
|
|
"num_tokens": 34266716.0,
|
|
"step": 15635
|
|
},
|
|
{
|
|
"entropy": 5.573258018493652,
|
|
"epoch": 1.5522032552600238,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004765067805967697,
|
|
"loss": 5.1533,
|
|
"mean_token_accuracy": 0.16941824555397034,
|
|
"num_tokens": 34278905.0,
|
|
"step": 15640
|
|
},
|
|
{
|
|
"entropy": 5.557124185562134,
|
|
"epoch": 1.5526994839221913,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004764910150136395,
|
|
"loss": 5.1058,
|
|
"mean_token_accuracy": 0.17113475352525712,
|
|
"num_tokens": 34289688.0,
|
|
"step": 15645
|
|
},
|
|
{
|
|
"entropy": 5.540787410736084,
|
|
"epoch": 1.5531957125843587,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00047647524443396625,
|
|
"loss": 5.1364,
|
|
"mean_token_accuracy": 0.1701718896627426,
|
|
"num_tokens": 34300964.0,
|
|
"step": 15650
|
|
},
|
|
{
|
|
"entropy": 5.548469209671021,
|
|
"epoch": 1.5536919412465264,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00047645946885814105,
|
|
"loss": 5.1263,
|
|
"mean_token_accuracy": 0.16975250989198684,
|
|
"num_tokens": 34311435.0,
|
|
"step": 15655
|
|
},
|
|
{
|
|
"entropy": 5.588261842727661,
|
|
"epoch": 1.554188169908694,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004764436882865552,
|
|
"loss": 5.1426,
|
|
"mean_token_accuracy": 0.16890763938426973,
|
|
"num_tokens": 34321742.0,
|
|
"step": 15660
|
|
},
|
|
{
|
|
"entropy": 5.597425842285157,
|
|
"epoch": 1.5546843985708616,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004764279027195999,
|
|
"loss": 5.2113,
|
|
"mean_token_accuracy": 0.16439826041460037,
|
|
"num_tokens": 34333796.0,
|
|
"step": 15665
|
|
},
|
|
{
|
|
"entropy": 5.674645519256591,
|
|
"epoch": 1.555180627233029,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00047641211215766673,
|
|
"loss": 5.2626,
|
|
"mean_token_accuracy": 0.16649988889694214,
|
|
"num_tokens": 34344521.0,
|
|
"step": 15670
|
|
},
|
|
{
|
|
"entropy": 5.524730157852173,
|
|
"epoch": 1.5556768558951966,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004763963166011471,
|
|
"loss": 5.1364,
|
|
"mean_token_accuracy": 0.1763203114271164,
|
|
"num_tokens": 34355629.0,
|
|
"step": 15675
|
|
},
|
|
{
|
|
"entropy": 5.555655670166016,
|
|
"epoch": 1.556173084557364,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004763805160504328,
|
|
"loss": 5.1958,
|
|
"mean_token_accuracy": 0.17040666788816453,
|
|
"num_tokens": 34366935.0,
|
|
"step": 15680
|
|
},
|
|
{
|
|
"entropy": 5.562149286270142,
|
|
"epoch": 1.5566693132195315,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004763647105059157,
|
|
"loss": 5.0966,
|
|
"mean_token_accuracy": 0.16582603752613068,
|
|
"num_tokens": 34378355.0,
|
|
"step": 15685
|
|
},
|
|
{
|
|
"entropy": 5.54614577293396,
|
|
"epoch": 1.557165541881699,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004763488999679877,
|
|
"loss": 5.0498,
|
|
"mean_token_accuracy": 0.17221602499485017,
|
|
"num_tokens": 34388811.0,
|
|
"step": 15690
|
|
},
|
|
{
|
|
"entropy": 5.61201057434082,
|
|
"epoch": 1.5576617705438665,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.00047633308443704076,
|
|
"loss": 5.1823,
|
|
"mean_token_accuracy": 0.1666204437613487,
|
|
"num_tokens": 34399905.0,
|
|
"step": 15695
|
|
},
|
|
{
|
|
"entropy": 5.506280183792114,
|
|
"epoch": 1.5581579992060341,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00047631726391346717,
|
|
"loss": 5.0428,
|
|
"mean_token_accuracy": 0.17504944801330566,
|
|
"num_tokens": 34410338.0,
|
|
"step": 15700
|
|
},
|
|
{
|
|
"entropy": 5.6072704792022705,
|
|
"epoch": 1.5586542278682016,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004763014383976593,
|
|
"loss": 5.2212,
|
|
"mean_token_accuracy": 0.16766735315322875,
|
|
"num_tokens": 34421204.0,
|
|
"step": 15705
|
|
},
|
|
{
|
|
"entropy": 5.510582160949707,
|
|
"epoch": 1.5591504565303693,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00047628560789000945,
|
|
"loss": 5.0326,
|
|
"mean_token_accuracy": 0.18137399554252626,
|
|
"num_tokens": 34431002.0,
|
|
"step": 15710
|
|
},
|
|
{
|
|
"entropy": 5.511729669570923,
|
|
"epoch": 1.5596466851925368,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.00047626977239091027,
|
|
"loss": 5.0854,
|
|
"mean_token_accuracy": 0.17405832856893538,
|
|
"num_tokens": 34442446.0,
|
|
"step": 15715
|
|
},
|
|
{
|
|
"entropy": 5.534721565246582,
|
|
"epoch": 1.5601429138547043,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004762539319007545,
|
|
"loss": 5.0568,
|
|
"mean_token_accuracy": 0.17754935026168822,
|
|
"num_tokens": 34453590.0,
|
|
"step": 15720
|
|
},
|
|
{
|
|
"entropy": 5.586336135864258,
|
|
"epoch": 1.5606391425168717,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004762380864199348,
|
|
"loss": 5.1893,
|
|
"mean_token_accuracy": 0.16865919828414916,
|
|
"num_tokens": 34465614.0,
|
|
"step": 15725
|
|
},
|
|
{
|
|
"entropy": 5.620033407211304,
|
|
"epoch": 1.5611353711790392,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004762222359488443,
|
|
"loss": 5.2927,
|
|
"mean_token_accuracy": 0.1614787682890892,
|
|
"num_tokens": 34476616.0,
|
|
"step": 15730
|
|
},
|
|
{
|
|
"entropy": 5.5874059200286865,
|
|
"epoch": 1.5616315998412067,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004762063804878758,
|
|
"loss": 5.0999,
|
|
"mean_token_accuracy": 0.16776054203510285,
|
|
"num_tokens": 34486260.0,
|
|
"step": 15735
|
|
},
|
|
{
|
|
"entropy": 5.547059774398804,
|
|
"epoch": 1.5621278285033744,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.00047619052003742277,
|
|
"loss": 5.1529,
|
|
"mean_token_accuracy": 0.17356517910957336,
|
|
"num_tokens": 34496392.0,
|
|
"step": 15740
|
|
},
|
|
{
|
|
"entropy": 5.538840103149414,
|
|
"epoch": 1.5626240571655419,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004761746545978782,
|
|
"loss": 5.1381,
|
|
"mean_token_accuracy": 0.17499603182077408,
|
|
"num_tokens": 34507218.0,
|
|
"step": 15745
|
|
},
|
|
{
|
|
"entropy": 5.609614658355713,
|
|
"epoch": 1.5631202858277096,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004761587841696358,
|
|
"loss": 5.1907,
|
|
"mean_token_accuracy": 0.17009020000696182,
|
|
"num_tokens": 34518888.0,
|
|
"step": 15750
|
|
},
|
|
{
|
|
"entropy": 5.563820886611938,
|
|
"epoch": 1.563616514489877,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.000476142908753089,
|
|
"loss": 5.1181,
|
|
"mean_token_accuracy": 0.17389977276325225,
|
|
"num_tokens": 34529865.0,
|
|
"step": 15755
|
|
},
|
|
{
|
|
"entropy": 5.570053434371948,
|
|
"epoch": 1.5641127431520445,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004761270283486314,
|
|
"loss": 5.183,
|
|
"mean_token_accuracy": 0.1677352398633957,
|
|
"num_tokens": 34542541.0,
|
|
"step": 15760
|
|
},
|
|
{
|
|
"entropy": 5.617619466781616,
|
|
"epoch": 1.564608971814212,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.00047611114295665697,
|
|
"loss": 5.181,
|
|
"mean_token_accuracy": 0.1722867727279663,
|
|
"num_tokens": 34553056.0,
|
|
"step": 15765
|
|
},
|
|
{
|
|
"entropy": 5.655702590942383,
|
|
"epoch": 1.5651052004763795,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00047609525257755967,
|
|
"loss": 5.1735,
|
|
"mean_token_accuracy": 0.17132552117109298,
|
|
"num_tokens": 34563344.0,
|
|
"step": 15770
|
|
},
|
|
{
|
|
"entropy": 5.595164585113525,
|
|
"epoch": 1.565601429138547,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004760793572117333,
|
|
"loss": 5.0738,
|
|
"mean_token_accuracy": 0.17740073800086975,
|
|
"num_tokens": 34574320.0,
|
|
"step": 15775
|
|
},
|
|
{
|
|
"entropy": 5.534933137893677,
|
|
"epoch": 1.5660976578007144,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004760634568595721,
|
|
"loss": 5.1453,
|
|
"mean_token_accuracy": 0.17128768861293792,
|
|
"num_tokens": 34584728.0,
|
|
"step": 15780
|
|
},
|
|
{
|
|
"entropy": 5.585668087005615,
|
|
"epoch": 1.5665938864628821,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004760475515214704,
|
|
"loss": 5.2388,
|
|
"mean_token_accuracy": 0.1676257148385048,
|
|
"num_tokens": 34596395.0,
|
|
"step": 15785
|
|
},
|
|
{
|
|
"entropy": 5.543160724639892,
|
|
"epoch": 1.5670901151250496,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004760316411978228,
|
|
"loss": 5.141,
|
|
"mean_token_accuracy": 0.16829395294189453,
|
|
"num_tokens": 34607950.0,
|
|
"step": 15790
|
|
},
|
|
{
|
|
"entropy": 5.562315177917481,
|
|
"epoch": 1.5675863437872173,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00047601572588902363,
|
|
"loss": 5.1379,
|
|
"mean_token_accuracy": 0.1778804324567318,
|
|
"num_tokens": 34617640.0,
|
|
"step": 15795
|
|
},
|
|
{
|
|
"entropy": 5.543839597702027,
|
|
"epoch": 1.5680825724493848,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.00047599980559546757,
|
|
"loss": 5.1845,
|
|
"mean_token_accuracy": 0.16260297149419783,
|
|
"num_tokens": 34629475.0,
|
|
"step": 15800
|
|
},
|
|
{
|
|
"entropy": 5.531244897842408,
|
|
"epoch": 1.5685788011115522,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004759838803175495,
|
|
"loss": 5.1135,
|
|
"mean_token_accuracy": 0.16955649703741074,
|
|
"num_tokens": 34641423.0,
|
|
"step": 15805
|
|
},
|
|
{
|
|
"entropy": 5.668246412277222,
|
|
"epoch": 1.5690750297737197,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00047596795005566423,
|
|
"loss": 5.1744,
|
|
"mean_token_accuracy": 0.17198489904403685,
|
|
"num_tokens": 34651894.0,
|
|
"step": 15810
|
|
},
|
|
{
|
|
"entropy": 5.613889122009278,
|
|
"epoch": 1.5695712584358872,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.00047595201481020685,
|
|
"loss": 5.1651,
|
|
"mean_token_accuracy": 0.1670777052640915,
|
|
"num_tokens": 34664177.0,
|
|
"step": 15815
|
|
},
|
|
{
|
|
"entropy": 5.546554803848267,
|
|
"epoch": 1.5700674870980547,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.00047593607458157257,
|
|
"loss": 5.1488,
|
|
"mean_token_accuracy": 0.17135327607393264,
|
|
"num_tokens": 34674850.0,
|
|
"step": 15820
|
|
},
|
|
{
|
|
"entropy": 5.552460622787476,
|
|
"epoch": 1.5705637157602224,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00047592012937015647,
|
|
"loss": 5.1708,
|
|
"mean_token_accuracy": 0.17258865833282472,
|
|
"num_tokens": 34685719.0,
|
|
"step": 15825
|
|
},
|
|
{
|
|
"entropy": 5.622128868103028,
|
|
"epoch": 1.5710599444223898,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00047590417917635423,
|
|
"loss": 5.1587,
|
|
"mean_token_accuracy": 0.16562519967556,
|
|
"num_tokens": 34697261.0,
|
|
"step": 15830
|
|
},
|
|
{
|
|
"entropy": 5.600107097625733,
|
|
"epoch": 1.5715561730845575,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004758882240005613,
|
|
"loss": 5.1666,
|
|
"mean_token_accuracy": 0.17027785032987594,
|
|
"num_tokens": 34708196.0,
|
|
"step": 15835
|
|
},
|
|
{
|
|
"entropy": 5.6132386207580565,
|
|
"epoch": 1.572052401746725,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00047587226384317323,
|
|
"loss": 5.1869,
|
|
"mean_token_accuracy": 0.1689977005124092,
|
|
"num_tokens": 34718855.0,
|
|
"step": 15840
|
|
},
|
|
{
|
|
"entropy": 5.559962892532349,
|
|
"epoch": 1.5725486304088925,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.00047585629870458584,
|
|
"loss": 5.1121,
|
|
"mean_token_accuracy": 0.17602272629737853,
|
|
"num_tokens": 34731137.0,
|
|
"step": 15845
|
|
},
|
|
{
|
|
"entropy": 5.575714015960694,
|
|
"epoch": 1.57304485907106,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004758403285851951,
|
|
"loss": 5.0746,
|
|
"mean_token_accuracy": 0.17832073271274568,
|
|
"num_tokens": 34741628.0,
|
|
"step": 15850
|
|
},
|
|
{
|
|
"entropy": 5.512636184692383,
|
|
"epoch": 1.5735410877332274,
|
|
"grad_norm": 0.796875,
|
|
"learning_rate": 0.00047582435348539695,
|
|
"loss": 5.1501,
|
|
"mean_token_accuracy": 0.17139003723859786,
|
|
"num_tokens": 34752984.0,
|
|
"step": 15855
|
|
},
|
|
{
|
|
"entropy": 5.568330001831055,
|
|
"epoch": 1.574037316395395,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004758083734055875,
|
|
"loss": 5.2216,
|
|
"mean_token_accuracy": 0.16662386804819107,
|
|
"num_tokens": 34764363.0,
|
|
"step": 15860
|
|
},
|
|
{
|
|
"entropy": 5.583333253860474,
|
|
"epoch": 1.5745335450575624,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004757923883461632,
|
|
"loss": 5.1664,
|
|
"mean_token_accuracy": 0.1679494321346283,
|
|
"num_tokens": 34776289.0,
|
|
"step": 15865
|
|
},
|
|
{
|
|
"entropy": 5.623749017715454,
|
|
"epoch": 1.57502977371973,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00047577639830752034,
|
|
"loss": 5.1386,
|
|
"mean_token_accuracy": 0.17214005440473557,
|
|
"num_tokens": 34786760.0,
|
|
"step": 15870
|
|
},
|
|
{
|
|
"entropy": 5.541008472442627,
|
|
"epoch": 1.5755260023818976,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00047576040329005536,
|
|
"loss": 5.1049,
|
|
"mean_token_accuracy": 0.17186620384454726,
|
|
"num_tokens": 34797737.0,
|
|
"step": 15875
|
|
},
|
|
{
|
|
"entropy": 5.526557493209839,
|
|
"epoch": 1.5760222310440652,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.000475744403294165,
|
|
"loss": 5.1657,
|
|
"mean_token_accuracy": 0.17382304221391678,
|
|
"num_tokens": 34809650.0,
|
|
"step": 15880
|
|
},
|
|
{
|
|
"entropy": 5.6612968921661375,
|
|
"epoch": 1.5765184597062327,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00047572839832024606,
|
|
"loss": 5.1888,
|
|
"mean_token_accuracy": 0.1654067099094391,
|
|
"num_tokens": 34820171.0,
|
|
"step": 15885
|
|
},
|
|
{
|
|
"entropy": 5.527270126342773,
|
|
"epoch": 1.5770146883684002,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.00047571238836869537,
|
|
"loss": 5.0427,
|
|
"mean_token_accuracy": 0.17614986151456832,
|
|
"num_tokens": 34831286.0,
|
|
"step": 15890
|
|
},
|
|
{
|
|
"entropy": 5.4632336616516115,
|
|
"epoch": 1.5775109170305677,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004756963734399099,
|
|
"loss": 5.0544,
|
|
"mean_token_accuracy": 0.17737851440906524,
|
|
"num_tokens": 34841767.0,
|
|
"step": 15895
|
|
},
|
|
{
|
|
"entropy": 5.536492156982422,
|
|
"epoch": 1.5780071456927351,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00047568035353428683,
|
|
"loss": 5.1629,
|
|
"mean_token_accuracy": 0.172687329351902,
|
|
"num_tokens": 34852644.0,
|
|
"step": 15900
|
|
},
|
|
{
|
|
"entropy": 5.606753301620484,
|
|
"epoch": 1.5785033743549026,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00047566432865222343,
|
|
"loss": 5.1718,
|
|
"mean_token_accuracy": 0.17330268919467925,
|
|
"num_tokens": 34863605.0,
|
|
"step": 15905
|
|
},
|
|
{
|
|
"entropy": 5.525470924377442,
|
|
"epoch": 1.5789996030170703,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.00047564829879411706,
|
|
"loss": 5.1198,
|
|
"mean_token_accuracy": 0.17635508477687836,
|
|
"num_tokens": 34874594.0,
|
|
"step": 15910
|
|
},
|
|
{
|
|
"entropy": 5.561229991912842,
|
|
"epoch": 1.5794958316792378,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004756322639603653,
|
|
"loss": 5.2146,
|
|
"mean_token_accuracy": 0.167847740650177,
|
|
"num_tokens": 34884627.0,
|
|
"step": 15915
|
|
},
|
|
{
|
|
"entropy": 5.6274457454681395,
|
|
"epoch": 1.5799920603414053,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.00047561622415136565,
|
|
"loss": 5.1755,
|
|
"mean_token_accuracy": 0.1773965761065483,
|
|
"num_tokens": 34895679.0,
|
|
"step": 15920
|
|
},
|
|
{
|
|
"entropy": 5.525401973724366,
|
|
"epoch": 1.580488289003573,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00047560017936751597,
|
|
"loss": 5.105,
|
|
"mean_token_accuracy": 0.17527058273553847,
|
|
"num_tokens": 34906811.0,
|
|
"step": 15925
|
|
},
|
|
{
|
|
"entropy": 5.5443473815917965,
|
|
"epoch": 1.5809845176657404,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004755841296092141,
|
|
"loss": 5.1479,
|
|
"mean_token_accuracy": 0.1667722150683403,
|
|
"num_tokens": 34918655.0,
|
|
"step": 15930
|
|
},
|
|
{
|
|
"entropy": 5.533793354034424,
|
|
"epoch": 1.581480746327908,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00047556807487685797,
|
|
"loss": 5.134,
|
|
"mean_token_accuracy": 0.17009201943874358,
|
|
"num_tokens": 34931034.0,
|
|
"step": 15935
|
|
},
|
|
{
|
|
"entropy": 5.596280765533447,
|
|
"epoch": 1.5819769749900754,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004755520151708458,
|
|
"loss": 5.0867,
|
|
"mean_token_accuracy": 0.17267320454120635,
|
|
"num_tokens": 34939707.0,
|
|
"step": 15940
|
|
},
|
|
{
|
|
"entropy": 5.55272331237793,
|
|
"epoch": 1.5824732036522429,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004755359504915758,
|
|
"loss": 5.1928,
|
|
"mean_token_accuracy": 0.1639191046357155,
|
|
"num_tokens": 34949237.0,
|
|
"step": 15945
|
|
},
|
|
{
|
|
"entropy": 5.605570697784424,
|
|
"epoch": 1.5829694323144103,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004755198808394464,
|
|
"loss": 5.2142,
|
|
"mean_token_accuracy": 0.17125055491924285,
|
|
"num_tokens": 34960380.0,
|
|
"step": 15950
|
|
},
|
|
{
|
|
"entropy": 5.591394853591919,
|
|
"epoch": 1.583465660976578,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.000475503806214856,
|
|
"loss": 5.1725,
|
|
"mean_token_accuracy": 0.16544706821441652,
|
|
"num_tokens": 34971699.0,
|
|
"step": 15955
|
|
},
|
|
{
|
|
"entropy": 5.586516952514648,
|
|
"epoch": 1.5839618896387455,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004754877266182033,
|
|
"loss": 5.1375,
|
|
"mean_token_accuracy": 0.17231732606887817,
|
|
"num_tokens": 34982333.0,
|
|
"step": 15960
|
|
},
|
|
{
|
|
"entropy": 5.564710235595703,
|
|
"epoch": 1.5844581183009132,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000475471642049887,
|
|
"loss": 5.172,
|
|
"mean_token_accuracy": 0.17079628705978395,
|
|
"num_tokens": 34993277.0,
|
|
"step": 15965
|
|
},
|
|
{
|
|
"entropy": 5.522321701049805,
|
|
"epoch": 1.5849543469630807,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004754555525103058,
|
|
"loss": 5.1107,
|
|
"mean_token_accuracy": 0.17557063400745393,
|
|
"num_tokens": 35004252.0,
|
|
"step": 15970
|
|
},
|
|
{
|
|
"entropy": 5.49769139289856,
|
|
"epoch": 1.5854505756252482,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.000475439457999859,
|
|
"loss": 5.0911,
|
|
"mean_token_accuracy": 0.18037165701389313,
|
|
"num_tokens": 35016974.0,
|
|
"step": 15975
|
|
},
|
|
{
|
|
"entropy": 5.575330209732056,
|
|
"epoch": 1.5859468042874156,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.00047542335851894553,
|
|
"loss": 5.1845,
|
|
"mean_token_accuracy": 0.16851292848587035,
|
|
"num_tokens": 35029017.0,
|
|
"step": 15980
|
|
},
|
|
{
|
|
"entropy": 5.620971441268921,
|
|
"epoch": 1.586443032949583,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00047540725406796454,
|
|
"loss": 5.2186,
|
|
"mean_token_accuracy": 0.16834655702114104,
|
|
"num_tokens": 35040239.0,
|
|
"step": 15985
|
|
},
|
|
{
|
|
"entropy": 5.602098846435547,
|
|
"epoch": 1.5869392616117506,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004753911446473156,
|
|
"loss": 5.1213,
|
|
"mean_token_accuracy": 0.16988668143749236,
|
|
"num_tokens": 35051426.0,
|
|
"step": 15990
|
|
},
|
|
{
|
|
"entropy": 5.4708832740783695,
|
|
"epoch": 1.587435490273918,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.000475375030257398,
|
|
"loss": 5.1022,
|
|
"mean_token_accuracy": 0.16767460405826567,
|
|
"num_tokens": 35061777.0,
|
|
"step": 15995
|
|
},
|
|
{
|
|
"entropy": 5.52356915473938,
|
|
"epoch": 1.5879317189360858,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004753589108986114,
|
|
"loss": 5.0498,
|
|
"mean_token_accuracy": 0.18492615222930908,
|
|
"num_tokens": 35071822.0,
|
|
"step": 16000
|
|
},
|
|
{
|
|
"entropy": 5.558615684509277,
|
|
"epoch": 1.5884279475982532,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00047534278657135565,
|
|
"loss": 5.1437,
|
|
"mean_token_accuracy": 0.17297255098819733,
|
|
"num_tokens": 35081900.0,
|
|
"step": 16005
|
|
},
|
|
{
|
|
"entropy": 5.59310302734375,
|
|
"epoch": 1.588924176260421,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004753266572760304,
|
|
"loss": 5.1964,
|
|
"mean_token_accuracy": 0.1688542127609253,
|
|
"num_tokens": 35092866.0,
|
|
"step": 16010
|
|
},
|
|
{
|
|
"entropy": 5.734499120712281,
|
|
"epoch": 1.5894204049225884,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00047531052301303577,
|
|
"loss": 5.281,
|
|
"mean_token_accuracy": 0.16906654834747314,
|
|
"num_tokens": 35103425.0,
|
|
"step": 16015
|
|
},
|
|
{
|
|
"entropy": 5.508281993865967,
|
|
"epoch": 1.5899166335847559,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004752943837827718,
|
|
"loss": 5.0661,
|
|
"mean_token_accuracy": 0.17544660419225694,
|
|
"num_tokens": 35114620.0,
|
|
"step": 16020
|
|
},
|
|
{
|
|
"entropy": 5.600801849365235,
|
|
"epoch": 1.5904128622469234,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004752782395856387,
|
|
"loss": 5.1724,
|
|
"mean_token_accuracy": 0.16886257827281953,
|
|
"num_tokens": 35125199.0,
|
|
"step": 16025
|
|
},
|
|
{
|
|
"entropy": 5.528537178039551,
|
|
"epoch": 1.5909090909090908,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004752620904220368,
|
|
"loss": 5.1347,
|
|
"mean_token_accuracy": 0.17435365915298462,
|
|
"num_tokens": 35135892.0,
|
|
"step": 16030
|
|
},
|
|
{
|
|
"entropy": 5.567734861373902,
|
|
"epoch": 1.5914053195712583,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004752459362923666,
|
|
"loss": 5.1463,
|
|
"mean_token_accuracy": 0.1693684697151184,
|
|
"num_tokens": 35146186.0,
|
|
"step": 16035
|
|
},
|
|
{
|
|
"entropy": 5.577980899810791,
|
|
"epoch": 1.591901548233426,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004752297771970287,
|
|
"loss": 5.1956,
|
|
"mean_token_accuracy": 0.17215658277273177,
|
|
"num_tokens": 35157261.0,
|
|
"step": 16040
|
|
},
|
|
{
|
|
"entropy": 5.606237268447876,
|
|
"epoch": 1.5923977768955935,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.00047521361313642373,
|
|
"loss": 5.1446,
|
|
"mean_token_accuracy": 0.17055224627256393,
|
|
"num_tokens": 35168508.0,
|
|
"step": 16045
|
|
},
|
|
{
|
|
"entropy": 5.533114576339722,
|
|
"epoch": 1.5928940055577612,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004751974441109526,
|
|
"loss": 5.1103,
|
|
"mean_token_accuracy": 0.16907101571559907,
|
|
"num_tokens": 35179444.0,
|
|
"step": 16050
|
|
},
|
|
{
|
|
"entropy": 5.520071268081665,
|
|
"epoch": 1.5933902342199286,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00047518127012101624,
|
|
"loss": 5.1108,
|
|
"mean_token_accuracy": 0.1762010484933853,
|
|
"num_tokens": 35189517.0,
|
|
"step": 16055
|
|
},
|
|
{
|
|
"entropy": 5.5501398086547855,
|
|
"epoch": 1.5938864628820961,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004751650911670157,
|
|
"loss": 5.1529,
|
|
"mean_token_accuracy": 0.16915027648210526,
|
|
"num_tokens": 35200191.0,
|
|
"step": 16060
|
|
},
|
|
{
|
|
"entropy": 5.604111051559448,
|
|
"epoch": 1.5943826915442636,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.00047514890724935236,
|
|
"loss": 5.1661,
|
|
"mean_token_accuracy": 0.16918279230594635,
|
|
"num_tokens": 35211260.0,
|
|
"step": 16065
|
|
},
|
|
{
|
|
"entropy": 5.500099086761475,
|
|
"epoch": 1.594878920206431,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004751327183684272,
|
|
"loss": 5.1447,
|
|
"mean_token_accuracy": 0.1680993989109993,
|
|
"num_tokens": 35222408.0,
|
|
"step": 16070
|
|
},
|
|
{
|
|
"entropy": 5.605546140670777,
|
|
"epoch": 1.5953751488685985,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.00047511652452464196,
|
|
"loss": 5.1854,
|
|
"mean_token_accuracy": 0.16996719986200332,
|
|
"num_tokens": 35232760.0,
|
|
"step": 16075
|
|
},
|
|
{
|
|
"entropy": 5.588399028778076,
|
|
"epoch": 1.595871377530766,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00047510032571839816,
|
|
"loss": 5.1506,
|
|
"mean_token_accuracy": 0.16914570480585098,
|
|
"num_tokens": 35243849.0,
|
|
"step": 16080
|
|
},
|
|
{
|
|
"entropy": 5.588242149353027,
|
|
"epoch": 1.5963676061929337,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004750841219500975,
|
|
"loss": 5.1648,
|
|
"mean_token_accuracy": 0.16913552582263947,
|
|
"num_tokens": 35254962.0,
|
|
"step": 16085
|
|
},
|
|
{
|
|
"entropy": 5.583474016189575,
|
|
"epoch": 1.5968638348551012,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004750679132201416,
|
|
"loss": 5.2403,
|
|
"mean_token_accuracy": 0.1665369153022766,
|
|
"num_tokens": 35265895.0,
|
|
"step": 16090
|
|
},
|
|
{
|
|
"entropy": 5.69076132774353,
|
|
"epoch": 1.597360063517269,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00047505169952893276,
|
|
"loss": 5.2322,
|
|
"mean_token_accuracy": 0.17190774381160737,
|
|
"num_tokens": 35277543.0,
|
|
"step": 16095
|
|
},
|
|
{
|
|
"entropy": 5.587152338027954,
|
|
"epoch": 1.5978562921794364,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00047503548087687267,
|
|
"loss": 5.1317,
|
|
"mean_token_accuracy": 0.17146954238414763,
|
|
"num_tokens": 35289130.0,
|
|
"step": 16100
|
|
},
|
|
{
|
|
"entropy": 5.5185308933258055,
|
|
"epoch": 1.5983525208416038,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00047501925726436376,
|
|
"loss": 5.0779,
|
|
"mean_token_accuracy": 0.17090461403131485,
|
|
"num_tokens": 35298414.0,
|
|
"step": 16105
|
|
},
|
|
{
|
|
"entropy": 5.543598985671997,
|
|
"epoch": 1.5988487495037713,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004750030286918082,
|
|
"loss": 5.1416,
|
|
"mean_token_accuracy": 0.1716749131679535,
|
|
"num_tokens": 35310629.0,
|
|
"step": 16110
|
|
},
|
|
{
|
|
"entropy": 5.6182928562164305,
|
|
"epoch": 1.5993449781659388,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004749867951596086,
|
|
"loss": 5.1818,
|
|
"mean_token_accuracy": 0.16935135573148727,
|
|
"num_tokens": 35321810.0,
|
|
"step": 16115
|
|
},
|
|
{
|
|
"entropy": 5.5639870166778564,
|
|
"epoch": 1.5998412068281063,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00047497055666816736,
|
|
"loss": 5.0998,
|
|
"mean_token_accuracy": 0.1760576844215393,
|
|
"num_tokens": 35333517.0,
|
|
"step": 16120
|
|
},
|
|
{
|
|
"entropy": 5.496850061416626,
|
|
"epoch": 1.600337435490274,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004749543132178873,
|
|
"loss": 5.0415,
|
|
"mean_token_accuracy": 0.17744467705488204,
|
|
"num_tokens": 35344170.0,
|
|
"step": 16125
|
|
},
|
|
{
|
|
"entropy": 5.571909856796265,
|
|
"epoch": 1.6008336641524414,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.000474938064809171,
|
|
"loss": 5.2249,
|
|
"mean_token_accuracy": 0.16783830374479294,
|
|
"num_tokens": 35354963.0,
|
|
"step": 16130
|
|
},
|
|
{
|
|
"entropy": 5.586218929290771,
|
|
"epoch": 1.6013298928146091,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004749218114424216,
|
|
"loss": 5.1861,
|
|
"mean_token_accuracy": 0.17537025958299637,
|
|
"num_tokens": 35365716.0,
|
|
"step": 16135
|
|
},
|
|
{
|
|
"entropy": 5.546600103378296,
|
|
"epoch": 1.6018261214767766,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00047490555311804206,
|
|
"loss": 5.112,
|
|
"mean_token_accuracy": 0.17386993765830994,
|
|
"num_tokens": 35376113.0,
|
|
"step": 16140
|
|
},
|
|
{
|
|
"entropy": 5.51456880569458,
|
|
"epoch": 1.602322350138944,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00047488928983643565,
|
|
"loss": 5.0889,
|
|
"mean_token_accuracy": 0.1700906589627266,
|
|
"num_tokens": 35386178.0,
|
|
"step": 16145
|
|
},
|
|
{
|
|
"entropy": 5.521318960189819,
|
|
"epoch": 1.6028185788011116,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00047487302159800545,
|
|
"loss": 5.0097,
|
|
"mean_token_accuracy": 0.17954554110765458,
|
|
"num_tokens": 35396874.0,
|
|
"step": 16150
|
|
},
|
|
{
|
|
"entropy": 5.54805850982666,
|
|
"epoch": 1.603314807463279,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.000474856748403155,
|
|
"loss": 5.2282,
|
|
"mean_token_accuracy": 0.1678831994533539,
|
|
"num_tokens": 35409405.0,
|
|
"step": 16155
|
|
},
|
|
{
|
|
"entropy": 5.616310119628906,
|
|
"epoch": 1.6038110361254465,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004748404702522879,
|
|
"loss": 5.1762,
|
|
"mean_token_accuracy": 0.1686457484960556,
|
|
"num_tokens": 35421449.0,
|
|
"step": 16160
|
|
},
|
|
{
|
|
"entropy": 5.597290849685669,
|
|
"epoch": 1.604307264787614,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.00047482418714580774,
|
|
"loss": 5.2114,
|
|
"mean_token_accuracy": 0.17077624499797822,
|
|
"num_tokens": 35434612.0,
|
|
"step": 16165
|
|
},
|
|
{
|
|
"entropy": 5.533904409408569,
|
|
"epoch": 1.6048034934497817,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004748078990841183,
|
|
"loss": 5.0961,
|
|
"mean_token_accuracy": 0.17794411033391952,
|
|
"num_tokens": 35446016.0,
|
|
"step": 16170
|
|
},
|
|
{
|
|
"entropy": 5.617804098129272,
|
|
"epoch": 1.6052997221119492,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004747916060676235,
|
|
"loss": 5.1498,
|
|
"mean_token_accuracy": 0.17460282891988754,
|
|
"num_tokens": 35457405.0,
|
|
"step": 16175
|
|
},
|
|
{
|
|
"entropy": 5.593232297897339,
|
|
"epoch": 1.6057959507741169,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.00047477530809672747,
|
|
"loss": 5.2112,
|
|
"mean_token_accuracy": 0.16786461025476457,
|
|
"num_tokens": 35468361.0,
|
|
"step": 16180
|
|
},
|
|
{
|
|
"entropy": 5.540446519851685,
|
|
"epoch": 1.6062921794362843,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004747590051718342,
|
|
"loss": 5.0968,
|
|
"mean_token_accuracy": 0.17383848875761032,
|
|
"num_tokens": 35480092.0,
|
|
"step": 16185
|
|
},
|
|
{
|
|
"entropy": 5.596573686599731,
|
|
"epoch": 1.6067884080984518,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00047474269729334806,
|
|
"loss": 5.2194,
|
|
"mean_token_accuracy": 0.1624014213681221,
|
|
"num_tokens": 35492131.0,
|
|
"step": 16190
|
|
},
|
|
{
|
|
"entropy": 5.619562721252441,
|
|
"epoch": 1.6072846367606193,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.00047472638446167346,
|
|
"loss": 5.169,
|
|
"mean_token_accuracy": 0.1646542578935623,
|
|
"num_tokens": 35503600.0,
|
|
"step": 16195
|
|
},
|
|
{
|
|
"entropy": 5.629235458374024,
|
|
"epoch": 1.6077808654227868,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00047471006667721484,
|
|
"loss": 5.2073,
|
|
"mean_token_accuracy": 0.16861433386802674,
|
|
"num_tokens": 35514716.0,
|
|
"step": 16200
|
|
},
|
|
{
|
|
"entropy": 5.584695434570312,
|
|
"epoch": 1.6082770940849542,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.000474693743940377,
|
|
"loss": 5.1366,
|
|
"mean_token_accuracy": 0.17781931310892105,
|
|
"num_tokens": 35525688.0,
|
|
"step": 16205
|
|
},
|
|
{
|
|
"entropy": 5.554493474960327,
|
|
"epoch": 1.608773322747122,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.00047467741625156453,
|
|
"loss": 5.1422,
|
|
"mean_token_accuracy": 0.17368559837341307,
|
|
"num_tokens": 35536391.0,
|
|
"step": 16210
|
|
},
|
|
{
|
|
"entropy": 5.510008811950684,
|
|
"epoch": 1.6092695514092894,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.00047466108361118235,
|
|
"loss": 5.0776,
|
|
"mean_token_accuracy": 0.17908220440149308,
|
|
"num_tokens": 35547016.0,
|
|
"step": 16215
|
|
},
|
|
{
|
|
"entropy": 5.568167591094971,
|
|
"epoch": 1.6097657800714569,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00047464474601963564,
|
|
"loss": 5.1603,
|
|
"mean_token_accuracy": 0.17011854499578477,
|
|
"num_tokens": 35558402.0,
|
|
"step": 16220
|
|
},
|
|
{
|
|
"entropy": 5.585215377807617,
|
|
"epoch": 1.6102620087336246,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004746284034773294,
|
|
"loss": 5.1485,
|
|
"mean_token_accuracy": 0.1724248558282852,
|
|
"num_tokens": 35569779.0,
|
|
"step": 16225
|
|
},
|
|
{
|
|
"entropy": 5.5655535697937015,
|
|
"epoch": 1.610758237395792,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004746120559846689,
|
|
"loss": 5.1547,
|
|
"mean_token_accuracy": 0.17170076668262482,
|
|
"num_tokens": 35580044.0,
|
|
"step": 16230
|
|
},
|
|
{
|
|
"entropy": 5.600090169906617,
|
|
"epoch": 1.6112544660579595,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.00047459570354205954,
|
|
"loss": 5.2357,
|
|
"mean_token_accuracy": 0.17075808644294738,
|
|
"num_tokens": 35591216.0,
|
|
"step": 16235
|
|
},
|
|
{
|
|
"entropy": 5.508529853820801,
|
|
"epoch": 1.611750694720127,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00047457934614990684,
|
|
"loss": 5.0616,
|
|
"mean_token_accuracy": 0.17528978139162063,
|
|
"num_tokens": 35602376.0,
|
|
"step": 16240
|
|
},
|
|
{
|
|
"entropy": 5.5367542743682865,
|
|
"epoch": 1.6122469233822945,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004745629838086164,
|
|
"loss": 5.0379,
|
|
"mean_token_accuracy": 0.17735781371593476,
|
|
"num_tokens": 35612184.0,
|
|
"step": 16245
|
|
},
|
|
{
|
|
"entropy": 5.579059839248657,
|
|
"epoch": 1.612743152044462,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.00047454661651859394,
|
|
"loss": 5.2048,
|
|
"mean_token_accuracy": 0.17242882996797562,
|
|
"num_tokens": 35624864.0,
|
|
"step": 16250
|
|
},
|
|
{
|
|
"entropy": 5.573807668685913,
|
|
"epoch": 1.6132393807066296,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004745302442802454,
|
|
"loss": 5.1435,
|
|
"mean_token_accuracy": 0.1738520309329033,
|
|
"num_tokens": 35636492.0,
|
|
"step": 16255
|
|
},
|
|
{
|
|
"entropy": 5.512031173706054,
|
|
"epoch": 1.6137356093687971,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004745138670939768,
|
|
"loss": 5.0852,
|
|
"mean_token_accuracy": 0.17595444470643998,
|
|
"num_tokens": 35646831.0,
|
|
"step": 16260
|
|
},
|
|
{
|
|
"entropy": 5.599237966537475,
|
|
"epoch": 1.6142318380309648,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004744974849601941,
|
|
"loss": 5.1966,
|
|
"mean_token_accuracy": 0.17177168279886246,
|
|
"num_tokens": 35657703.0,
|
|
"step": 16265
|
|
},
|
|
{
|
|
"entropy": 5.4731049060821535,
|
|
"epoch": 1.6147280666931323,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004744810978793038,
|
|
"loss": 5.023,
|
|
"mean_token_accuracy": 0.17758560180664062,
|
|
"num_tokens": 35668334.0,
|
|
"step": 16270
|
|
},
|
|
{
|
|
"entropy": 5.526353549957276,
|
|
"epoch": 1.6152242953552998,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00047446470585171206,
|
|
"loss": 5.1726,
|
|
"mean_token_accuracy": 0.16676280796527862,
|
|
"num_tokens": 35679796.0,
|
|
"step": 16275
|
|
},
|
|
{
|
|
"entropy": 5.531010437011719,
|
|
"epoch": 1.6157205240174672,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00047444830887782537,
|
|
"loss": 5.0604,
|
|
"mean_token_accuracy": 0.17524588108062744,
|
|
"num_tokens": 35690825.0,
|
|
"step": 16280
|
|
},
|
|
{
|
|
"entropy": 5.62803020477295,
|
|
"epoch": 1.6162167526796347,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004744319069580504,
|
|
"loss": 5.1849,
|
|
"mean_token_accuracy": 0.17152267098426818,
|
|
"num_tokens": 35701824.0,
|
|
"step": 16285
|
|
},
|
|
{
|
|
"entropy": 5.612047958374023,
|
|
"epoch": 1.6167129813418022,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.00047441550009279395,
|
|
"loss": 5.1012,
|
|
"mean_token_accuracy": 0.17642791122198104,
|
|
"num_tokens": 35713250.0,
|
|
"step": 16290
|
|
},
|
|
{
|
|
"entropy": 5.565155410766602,
|
|
"epoch": 1.6172092100039697,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004743990882824627,
|
|
"loss": 5.1801,
|
|
"mean_token_accuracy": 0.16946621239185333,
|
|
"num_tokens": 35725049.0,
|
|
"step": 16295
|
|
},
|
|
{
|
|
"entropy": 5.494463205337524,
|
|
"epoch": 1.6177054386661374,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00047438267152746376,
|
|
"loss": 5.1189,
|
|
"mean_token_accuracy": 0.16613352298736572,
|
|
"num_tokens": 35734676.0,
|
|
"step": 16300
|
|
},
|
|
{
|
|
"entropy": 5.568187665939331,
|
|
"epoch": 1.6182016673283048,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00047436624982820423,
|
|
"loss": 5.1146,
|
|
"mean_token_accuracy": 0.17054773420095443,
|
|
"num_tokens": 35743953.0,
|
|
"step": 16305
|
|
},
|
|
{
|
|
"entropy": 5.530277061462402,
|
|
"epoch": 1.6186978959904725,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004743498231850913,
|
|
"loss": 5.0523,
|
|
"mean_token_accuracy": 0.18202498704195022,
|
|
"num_tokens": 35753149.0,
|
|
"step": 16310
|
|
},
|
|
{
|
|
"entropy": 5.491792345046997,
|
|
"epoch": 1.61919412465264,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004743333915985323,
|
|
"loss": 5.127,
|
|
"mean_token_accuracy": 0.16944457590579987,
|
|
"num_tokens": 35763783.0,
|
|
"step": 16315
|
|
},
|
|
{
|
|
"entropy": 5.484177207946777,
|
|
"epoch": 1.6196903533148075,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00047431695506893476,
|
|
"loss": 5.0704,
|
|
"mean_token_accuracy": 0.18196655958890914,
|
|
"num_tokens": 35774663.0,
|
|
"step": 16320
|
|
},
|
|
{
|
|
"entropy": 5.574009418487549,
|
|
"epoch": 1.620186581976975,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00047430051359670616,
|
|
"loss": 5.2252,
|
|
"mean_token_accuracy": 0.16487312018871308,
|
|
"num_tokens": 35786990.0,
|
|
"step": 16325
|
|
},
|
|
{
|
|
"entropy": 5.659722185134887,
|
|
"epoch": 1.6206828106391424,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004742840671822542,
|
|
"loss": 5.2263,
|
|
"mean_token_accuracy": 0.1707298368215561,
|
|
"num_tokens": 35798818.0,
|
|
"step": 16330
|
|
},
|
|
{
|
|
"entropy": 5.613869762420654,
|
|
"epoch": 1.62117903930131,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.000474267615825987,
|
|
"loss": 5.1666,
|
|
"mean_token_accuracy": 0.1698811709880829,
|
|
"num_tokens": 35808813.0,
|
|
"step": 16335
|
|
},
|
|
{
|
|
"entropy": 5.531151485443115,
|
|
"epoch": 1.6216752679634776,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00047425115952831213,
|
|
"loss": 5.146,
|
|
"mean_token_accuracy": 0.1767699286341667,
|
|
"num_tokens": 35818664.0,
|
|
"step": 16340
|
|
},
|
|
{
|
|
"entropy": 5.497013330459595,
|
|
"epoch": 1.622171496625645,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.000474234698289638,
|
|
"loss": 5.0933,
|
|
"mean_token_accuracy": 0.17992809414863586,
|
|
"num_tokens": 35828975.0,
|
|
"step": 16345
|
|
},
|
|
{
|
|
"entropy": 5.494010591506958,
|
|
"epoch": 1.6226677252878128,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004742182321103725,
|
|
"loss": 5.1152,
|
|
"mean_token_accuracy": 0.17443787306547165,
|
|
"num_tokens": 35839437.0,
|
|
"step": 16350
|
|
},
|
|
{
|
|
"entropy": 5.543405532836914,
|
|
"epoch": 1.6231639539499803,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004742017609909242,
|
|
"loss": 5.0733,
|
|
"mean_token_accuracy": 0.17784169763326646,
|
|
"num_tokens": 35850413.0,
|
|
"step": 16355
|
|
},
|
|
{
|
|
"entropy": 5.596259117126465,
|
|
"epoch": 1.6236601826121477,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.00047418528493170157,
|
|
"loss": 5.1427,
|
|
"mean_token_accuracy": 0.1686675876379013,
|
|
"num_tokens": 35862745.0,
|
|
"step": 16360
|
|
},
|
|
{
|
|
"entropy": 5.6065216064453125,
|
|
"epoch": 1.6241564112743152,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004741688039331129,
|
|
"loss": 5.13,
|
|
"mean_token_accuracy": 0.1675193652510643,
|
|
"num_tokens": 35873934.0,
|
|
"step": 16365
|
|
},
|
|
{
|
|
"entropy": 5.505111026763916,
|
|
"epoch": 1.6246526399364827,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00047415231799556725,
|
|
"loss": 5.0541,
|
|
"mean_token_accuracy": 0.1791858971118927,
|
|
"num_tokens": 35884279.0,
|
|
"step": 16370
|
|
},
|
|
{
|
|
"entropy": 5.488245153427124,
|
|
"epoch": 1.6251488685986502,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00047413582711947305,
|
|
"loss": 5.1123,
|
|
"mean_token_accuracy": 0.1776946723461151,
|
|
"num_tokens": 35894144.0,
|
|
"step": 16375
|
|
},
|
|
{
|
|
"entropy": 5.5181357860565186,
|
|
"epoch": 1.6256450972608176,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00047411933130523954,
|
|
"loss": 5.1133,
|
|
"mean_token_accuracy": 0.17058235704898833,
|
|
"num_tokens": 35903641.0,
|
|
"step": 16380
|
|
},
|
|
{
|
|
"entropy": 5.511588525772095,
|
|
"epoch": 1.6261413259229853,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004741028305532757,
|
|
"loss": 5.0773,
|
|
"mean_token_accuracy": 0.17215801030397415,
|
|
"num_tokens": 35913634.0,
|
|
"step": 16385
|
|
},
|
|
{
|
|
"entropy": 5.548446798324585,
|
|
"epoch": 1.6266375545851528,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004740863248639907,
|
|
"loss": 5.1221,
|
|
"mean_token_accuracy": 0.17387913465499877,
|
|
"num_tokens": 35923106.0,
|
|
"step": 16390
|
|
},
|
|
{
|
|
"entropy": 5.556178951263428,
|
|
"epoch": 1.6271337832473205,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00047406981423779376,
|
|
"loss": 5.1118,
|
|
"mean_token_accuracy": 0.17499779313802719,
|
|
"num_tokens": 35933709.0,
|
|
"step": 16395
|
|
},
|
|
{
|
|
"entropy": 5.517813062667846,
|
|
"epoch": 1.627630011909488,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00047405329867509447,
|
|
"loss": 5.1352,
|
|
"mean_token_accuracy": 0.16638769805431367,
|
|
"num_tokens": 35944734.0,
|
|
"step": 16400
|
|
},
|
|
{
|
|
"entropy": 5.53065299987793,
|
|
"epoch": 1.6281262405716554,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00047403677817630226,
|
|
"loss": 5.0996,
|
|
"mean_token_accuracy": 0.17241687923669816,
|
|
"num_tokens": 35956513.0,
|
|
"step": 16405
|
|
},
|
|
{
|
|
"entropy": 5.495169544219971,
|
|
"epoch": 1.628622469233823,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004740202527418269,
|
|
"loss": 5.115,
|
|
"mean_token_accuracy": 0.1735220193862915,
|
|
"num_tokens": 35967096.0,
|
|
"step": 16410
|
|
},
|
|
{
|
|
"entropy": 5.566775226593018,
|
|
"epoch": 1.6291186978959904,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.000474003722372078,
|
|
"loss": 5.1936,
|
|
"mean_token_accuracy": 0.17107468843460083,
|
|
"num_tokens": 35979010.0,
|
|
"step": 16415
|
|
},
|
|
{
|
|
"entropy": 5.52549147605896,
|
|
"epoch": 1.6296149265581579,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00047398718706746556,
|
|
"loss": 5.0446,
|
|
"mean_token_accuracy": 0.1739116832613945,
|
|
"num_tokens": 35989253.0,
|
|
"step": 16420
|
|
},
|
|
{
|
|
"entropy": 5.518692302703857,
|
|
"epoch": 1.6301111552203256,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004739706468283998,
|
|
"loss": 5.0663,
|
|
"mean_token_accuracy": 0.17488324493169785,
|
|
"num_tokens": 35999659.0,
|
|
"step": 16425
|
|
},
|
|
{
|
|
"entropy": 5.507155132293701,
|
|
"epoch": 1.630607383882493,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00047395410165529075,
|
|
"loss": 5.1269,
|
|
"mean_token_accuracy": 0.16918691098690034,
|
|
"num_tokens": 36010295.0,
|
|
"step": 16430
|
|
},
|
|
{
|
|
"entropy": 5.563255739212036,
|
|
"epoch": 1.6311036125446607,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00047393755154854855,
|
|
"loss": 5.15,
|
|
"mean_token_accuracy": 0.1705315187573433,
|
|
"num_tokens": 36021575.0,
|
|
"step": 16435
|
|
},
|
|
{
|
|
"entropy": 5.58696722984314,
|
|
"epoch": 1.6315998412068282,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004739209965085839,
|
|
"loss": 5.1411,
|
|
"mean_token_accuracy": 0.16836782693862914,
|
|
"num_tokens": 36032764.0,
|
|
"step": 16440
|
|
},
|
|
{
|
|
"entropy": 5.540527439117431,
|
|
"epoch": 1.6320960698689957,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000473904436535807,
|
|
"loss": 5.0997,
|
|
"mean_token_accuracy": 0.1794095903635025,
|
|
"num_tokens": 36041864.0,
|
|
"step": 16445
|
|
},
|
|
{
|
|
"entropy": 5.476602792739868,
|
|
"epoch": 1.6325922985311632,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004738878716306288,
|
|
"loss": 5.0864,
|
|
"mean_token_accuracy": 0.17238736450672149,
|
|
"num_tokens": 36051321.0,
|
|
"step": 16450
|
|
},
|
|
{
|
|
"entropy": 5.504956436157227,
|
|
"epoch": 1.6330885271933306,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00047387130179345996,
|
|
"loss": 5.0609,
|
|
"mean_token_accuracy": 0.17036915570497513,
|
|
"num_tokens": 36061448.0,
|
|
"step": 16455
|
|
},
|
|
{
|
|
"entropy": 5.558578538894653,
|
|
"epoch": 1.6335847558554981,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00047385472702471133,
|
|
"loss": 5.1948,
|
|
"mean_token_accuracy": 0.17376814037561417,
|
|
"num_tokens": 36071832.0,
|
|
"step": 16460
|
|
},
|
|
{
|
|
"entropy": 5.545031309127808,
|
|
"epoch": 1.6340809845176656,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.000473838147324794,
|
|
"loss": 5.1079,
|
|
"mean_token_accuracy": 0.17153619229793549,
|
|
"num_tokens": 36082103.0,
|
|
"step": 16465
|
|
},
|
|
{
|
|
"entropy": 5.593025016784668,
|
|
"epoch": 1.6345772131798333,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.000473821562694119,
|
|
"loss": 5.1478,
|
|
"mean_token_accuracy": 0.1702588453888893,
|
|
"num_tokens": 36092063.0,
|
|
"step": 16470
|
|
},
|
|
{
|
|
"entropy": 5.569368028640747,
|
|
"epoch": 1.6350734418420008,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004738049731330977,
|
|
"loss": 5.1355,
|
|
"mean_token_accuracy": 0.16376752853393556,
|
|
"num_tokens": 36102573.0,
|
|
"step": 16475
|
|
},
|
|
{
|
|
"entropy": 5.599412155151367,
|
|
"epoch": 1.6355696705041685,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004737883786421414,
|
|
"loss": 5.1153,
|
|
"mean_token_accuracy": 0.17183687835931777,
|
|
"num_tokens": 36112677.0,
|
|
"step": 16480
|
|
},
|
|
{
|
|
"entropy": 5.562631511688233,
|
|
"epoch": 1.636065899166336,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.00047377177922166175,
|
|
"loss": 5.1816,
|
|
"mean_token_accuracy": 0.16841134577989578,
|
|
"num_tokens": 36123337.0,
|
|
"step": 16485
|
|
},
|
|
{
|
|
"entropy": 5.598000764846802,
|
|
"epoch": 1.6365621278285034,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.00047375517487207024,
|
|
"loss": 5.1493,
|
|
"mean_token_accuracy": 0.173994217813015,
|
|
"num_tokens": 36134503.0,
|
|
"step": 16490
|
|
},
|
|
{
|
|
"entropy": 5.64011869430542,
|
|
"epoch": 1.6370583564906709,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.00047373856559377876,
|
|
"loss": 5.2186,
|
|
"mean_token_accuracy": 0.16748932301998137,
|
|
"num_tokens": 36145766.0,
|
|
"step": 16495
|
|
},
|
|
{
|
|
"entropy": 5.591852426528931,
|
|
"epoch": 1.6375545851528384,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004737219513871989,
|
|
"loss": 5.1654,
|
|
"mean_token_accuracy": 0.17032527923583984,
|
|
"num_tokens": 36156584.0,
|
|
"step": 16500
|
|
},
|
|
{
|
|
"entropy": 5.534194231033325,
|
|
"epoch": 1.6380508138150058,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.00047370533225274305,
|
|
"loss": 5.147,
|
|
"mean_token_accuracy": 0.17428812086582185,
|
|
"num_tokens": 36166999.0,
|
|
"step": 16505
|
|
},
|
|
{
|
|
"entropy": 5.56323504447937,
|
|
"epoch": 1.6385470424771735,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004736887081908231,
|
|
"loss": 5.1166,
|
|
"mean_token_accuracy": 0.17571138590574265,
|
|
"num_tokens": 36178724.0,
|
|
"step": 16510
|
|
},
|
|
{
|
|
"entropy": 5.64340615272522,
|
|
"epoch": 1.639043271139341,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004736720792018513,
|
|
"loss": 5.2021,
|
|
"mean_token_accuracy": 0.16817369908094407,
|
|
"num_tokens": 36188912.0,
|
|
"step": 16515
|
|
},
|
|
{
|
|
"entropy": 5.541040754318237,
|
|
"epoch": 1.6395394998015085,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004736554452862399,
|
|
"loss": 5.0997,
|
|
"mean_token_accuracy": 0.17425263971090316,
|
|
"num_tokens": 36198525.0,
|
|
"step": 16520
|
|
},
|
|
{
|
|
"entropy": 5.508972072601319,
|
|
"epoch": 1.6400357284636762,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00047363880644440173,
|
|
"loss": 5.0813,
|
|
"mean_token_accuracy": 0.17363713532686234,
|
|
"num_tokens": 36209384.0,
|
|
"step": 16525
|
|
},
|
|
{
|
|
"entropy": 5.598171281814575,
|
|
"epoch": 1.6405319571258437,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00047362216267674906,
|
|
"loss": 5.1677,
|
|
"mean_token_accuracy": 0.16821869164705278,
|
|
"num_tokens": 36220597.0,
|
|
"step": 16530
|
|
},
|
|
{
|
|
"entropy": 5.626340723037719,
|
|
"epoch": 1.6410281857880111,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004736055139836948,
|
|
"loss": 5.2122,
|
|
"mean_token_accuracy": 0.17054324597120285,
|
|
"num_tokens": 36230317.0,
|
|
"step": 16535
|
|
},
|
|
{
|
|
"entropy": 5.686342430114746,
|
|
"epoch": 1.6415244144501786,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00047358886036565176,
|
|
"loss": 5.2914,
|
|
"mean_token_accuracy": 0.16591713726520538,
|
|
"num_tokens": 36241645.0,
|
|
"step": 16540
|
|
},
|
|
{
|
|
"entropy": 5.599885749816894,
|
|
"epoch": 1.642020643112346,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00047357220182303285,
|
|
"loss": 5.2165,
|
|
"mean_token_accuracy": 0.1655209943652153,
|
|
"num_tokens": 36253098.0,
|
|
"step": 16545
|
|
},
|
|
{
|
|
"entropy": 5.538655519485474,
|
|
"epoch": 1.6425168717745136,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004735555383562513,
|
|
"loss": 5.1113,
|
|
"mean_token_accuracy": 0.17447598278522491,
|
|
"num_tokens": 36264417.0,
|
|
"step": 16550
|
|
},
|
|
{
|
|
"entropy": 5.635347318649292,
|
|
"epoch": 1.6430131004366813,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.00047353886996572014,
|
|
"loss": 5.2061,
|
|
"mean_token_accuracy": 0.16311426609754562,
|
|
"num_tokens": 36276589.0,
|
|
"step": 16555
|
|
},
|
|
{
|
|
"entropy": 5.577414226531983,
|
|
"epoch": 1.6435093290988487,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00047352219665185293,
|
|
"loss": 5.1238,
|
|
"mean_token_accuracy": 0.16760046929121017,
|
|
"num_tokens": 36287308.0,
|
|
"step": 16560
|
|
},
|
|
{
|
|
"entropy": 5.541089010238648,
|
|
"epoch": 1.6440055577610164,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004735055184150629,
|
|
"loss": 5.1248,
|
|
"mean_token_accuracy": 0.17476615756750108,
|
|
"num_tokens": 36298966.0,
|
|
"step": 16565
|
|
},
|
|
{
|
|
"entropy": 5.509775972366333,
|
|
"epoch": 1.644501786423184,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00047348883525576385,
|
|
"loss": 5.1361,
|
|
"mean_token_accuracy": 0.16911161541938782,
|
|
"num_tokens": 36310498.0,
|
|
"step": 16570
|
|
},
|
|
{
|
|
"entropy": 5.5917764663696286,
|
|
"epoch": 1.6449980150853514,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004734721471743694,
|
|
"loss": 5.2006,
|
|
"mean_token_accuracy": 0.1728076919913292,
|
|
"num_tokens": 36321589.0,
|
|
"step": 16575
|
|
},
|
|
{
|
|
"entropy": 5.565700817108154,
|
|
"epoch": 1.6454942437475188,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004734554541712933,
|
|
"loss": 5.1009,
|
|
"mean_token_accuracy": 0.16892541497945784,
|
|
"num_tokens": 36333041.0,
|
|
"step": 16580
|
|
},
|
|
{
|
|
"entropy": 5.602836275100708,
|
|
"epoch": 1.6459904724096863,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004734387562469496,
|
|
"loss": 5.176,
|
|
"mean_token_accuracy": 0.16549454629421234,
|
|
"num_tokens": 36344225.0,
|
|
"step": 16585
|
|
},
|
|
{
|
|
"entropy": 5.569616603851318,
|
|
"epoch": 1.6464867010718538,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00047342205340175235,
|
|
"loss": 5.066,
|
|
"mean_token_accuracy": 0.17604072988033295,
|
|
"num_tokens": 36355524.0,
|
|
"step": 16590
|
|
},
|
|
{
|
|
"entropy": 5.583031368255615,
|
|
"epoch": 1.6469829297340213,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00047340534563611574,
|
|
"loss": 5.1464,
|
|
"mean_token_accuracy": 0.1758979856967926,
|
|
"num_tokens": 36366495.0,
|
|
"step": 16595
|
|
},
|
|
{
|
|
"entropy": 5.566857099533081,
|
|
"epoch": 1.647479158396189,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00047338863295045414,
|
|
"loss": 5.1339,
|
|
"mean_token_accuracy": 0.17026081532239914,
|
|
"num_tokens": 36378316.0,
|
|
"step": 16600
|
|
},
|
|
{
|
|
"entropy": 5.605424594879151,
|
|
"epoch": 1.6479753870583564,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00047337191534518186,
|
|
"loss": 5.2239,
|
|
"mean_token_accuracy": 0.16221691519021988,
|
|
"num_tokens": 36390500.0,
|
|
"step": 16605
|
|
},
|
|
{
|
|
"entropy": 5.609649991989135,
|
|
"epoch": 1.6484716157205241,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004733551928207135,
|
|
"loss": 5.1606,
|
|
"mean_token_accuracy": 0.1712506279349327,
|
|
"num_tokens": 36403831.0,
|
|
"step": 16610
|
|
},
|
|
{
|
|
"entropy": 5.569226312637329,
|
|
"epoch": 1.6489678443826916,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004733384653774639,
|
|
"loss": 5.1242,
|
|
"mean_token_accuracy": 0.17524966299533845,
|
|
"num_tokens": 36414896.0,
|
|
"step": 16615
|
|
},
|
|
{
|
|
"entropy": 5.519056224822998,
|
|
"epoch": 1.649464073044859,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00047332173301584764,
|
|
"loss": 5.0621,
|
|
"mean_token_accuracy": 0.17273387908935547,
|
|
"num_tokens": 36426260.0,
|
|
"step": 16620
|
|
},
|
|
{
|
|
"entropy": 5.48406753540039,
|
|
"epoch": 1.6499603017070266,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00047330499573627975,
|
|
"loss": 5.0224,
|
|
"mean_token_accuracy": 0.18159683048725128,
|
|
"num_tokens": 36437125.0,
|
|
"step": 16625
|
|
},
|
|
{
|
|
"entropy": 5.542082023620606,
|
|
"epoch": 1.650456530369194,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00047328825353917526,
|
|
"loss": 5.0679,
|
|
"mean_token_accuracy": 0.1763029381632805,
|
|
"num_tokens": 36447507.0,
|
|
"step": 16630
|
|
},
|
|
{
|
|
"entropy": 5.6174413681030275,
|
|
"epoch": 1.6509527590313615,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00047327150642494944,
|
|
"loss": 5.2347,
|
|
"mean_token_accuracy": 0.16983219236135483,
|
|
"num_tokens": 36459134.0,
|
|
"step": 16635
|
|
},
|
|
{
|
|
"entropy": 5.606341028213501,
|
|
"epoch": 1.6514489876935292,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004732547543940174,
|
|
"loss": 5.1425,
|
|
"mean_token_accuracy": 0.1669211804866791,
|
|
"num_tokens": 36469594.0,
|
|
"step": 16640
|
|
},
|
|
{
|
|
"entropy": 5.553228759765625,
|
|
"epoch": 1.6519452163556967,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004732379974467947,
|
|
"loss": 5.1445,
|
|
"mean_token_accuracy": 0.17724878042936326,
|
|
"num_tokens": 36480477.0,
|
|
"step": 16645
|
|
},
|
|
{
|
|
"entropy": 5.52822093963623,
|
|
"epoch": 1.6524414450178644,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004732212355836968,
|
|
"loss": 5.1445,
|
|
"mean_token_accuracy": 0.1737054780125618,
|
|
"num_tokens": 36491304.0,
|
|
"step": 16650
|
|
},
|
|
{
|
|
"entropy": 5.6495777606964115,
|
|
"epoch": 1.6529376736800319,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004732044688051395,
|
|
"loss": 5.2132,
|
|
"mean_token_accuracy": 0.1647946760058403,
|
|
"num_tokens": 36502030.0,
|
|
"step": 16655
|
|
},
|
|
{
|
|
"entropy": 5.585239744186401,
|
|
"epoch": 1.6534339023421993,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00047318769711153833,
|
|
"loss": 5.2391,
|
|
"mean_token_accuracy": 0.16840274035930633,
|
|
"num_tokens": 36514405.0,
|
|
"step": 16660
|
|
},
|
|
{
|
|
"entropy": 5.597030115127564,
|
|
"epoch": 1.6539301310043668,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004731709205033094,
|
|
"loss": 5.1104,
|
|
"mean_token_accuracy": 0.17021507918834686,
|
|
"num_tokens": 36524626.0,
|
|
"step": 16665
|
|
},
|
|
{
|
|
"entropy": 5.608535528182983,
|
|
"epoch": 1.6544263596665343,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00047315413898086863,
|
|
"loss": 5.1091,
|
|
"mean_token_accuracy": 0.1769067496061325,
|
|
"num_tokens": 36535340.0,
|
|
"step": 16670
|
|
},
|
|
{
|
|
"entropy": 5.593055534362793,
|
|
"epoch": 1.6549225883287018,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004731373525446322,
|
|
"loss": 5.1108,
|
|
"mean_token_accuracy": 0.17366884648799896,
|
|
"num_tokens": 36547189.0,
|
|
"step": 16675
|
|
},
|
|
{
|
|
"entropy": 5.573965406417846,
|
|
"epoch": 1.6554188169908692,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004731205611950164,
|
|
"loss": 5.1947,
|
|
"mean_token_accuracy": 0.16631772369146347,
|
|
"num_tokens": 36558177.0,
|
|
"step": 16680
|
|
},
|
|
{
|
|
"entropy": 5.528534984588623,
|
|
"epoch": 1.655915045653037,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00047310376493243754,
|
|
"loss": 5.0156,
|
|
"mean_token_accuracy": 0.1760718896985054,
|
|
"num_tokens": 36569559.0,
|
|
"step": 16685
|
|
},
|
|
{
|
|
"entropy": 5.567520809173584,
|
|
"epoch": 1.6564112743152044,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004730869637573122,
|
|
"loss": 5.0827,
|
|
"mean_token_accuracy": 0.1765242785215378,
|
|
"num_tokens": 36579617.0,
|
|
"step": 16690
|
|
},
|
|
{
|
|
"entropy": 5.549475860595703,
|
|
"epoch": 1.656907502977372,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.00047307015767005705,
|
|
"loss": 5.0752,
|
|
"mean_token_accuracy": 0.17589021474123,
|
|
"num_tokens": 36590427.0,
|
|
"step": 16695
|
|
},
|
|
{
|
|
"entropy": 5.52656102180481,
|
|
"epoch": 1.6574037316395396,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004730533466710888,
|
|
"loss": 5.0776,
|
|
"mean_token_accuracy": 0.17531200647354125,
|
|
"num_tokens": 36602313.0,
|
|
"step": 16700
|
|
},
|
|
{
|
|
"entropy": 5.605986881256103,
|
|
"epoch": 1.657899960301707,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004730365307608242,
|
|
"loss": 5.1765,
|
|
"mean_token_accuracy": 0.17297641038894654,
|
|
"num_tokens": 36615191.0,
|
|
"step": 16705
|
|
},
|
|
{
|
|
"entropy": 5.565281629562378,
|
|
"epoch": 1.6583961889638745,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00047301970993968054,
|
|
"loss": 5.1021,
|
|
"mean_token_accuracy": 0.1765014037489891,
|
|
"num_tokens": 36624692.0,
|
|
"step": 16710
|
|
},
|
|
{
|
|
"entropy": 5.580508518218994,
|
|
"epoch": 1.658892417626042,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00047300288420807463,
|
|
"loss": 5.1744,
|
|
"mean_token_accuracy": 0.1661687821149826,
|
|
"num_tokens": 36635961.0,
|
|
"step": 16715
|
|
},
|
|
{
|
|
"entropy": 5.543060684204102,
|
|
"epoch": 1.6593886462882095,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00047298605356642387,
|
|
"loss": 5.1289,
|
|
"mean_token_accuracy": 0.17295888513326646,
|
|
"num_tokens": 36646710.0,
|
|
"step": 16720
|
|
},
|
|
{
|
|
"entropy": 5.577163171768189,
|
|
"epoch": 1.6598848749503772,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00047296921801514565,
|
|
"loss": 5.2162,
|
|
"mean_token_accuracy": 0.16633112877607345,
|
|
"num_tokens": 36657168.0,
|
|
"step": 16725
|
|
},
|
|
{
|
|
"entropy": 5.57464828491211,
|
|
"epoch": 1.6603811036125447,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004729523775546574,
|
|
"loss": 5.1967,
|
|
"mean_token_accuracy": 0.17284595519304274,
|
|
"num_tokens": 36668428.0,
|
|
"step": 16730
|
|
},
|
|
{
|
|
"entropy": 5.5711745262146,
|
|
"epoch": 1.6608773322747123,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004729355321853767,
|
|
"loss": 5.1361,
|
|
"mean_token_accuracy": 0.17802993655204774,
|
|
"num_tokens": 36679361.0,
|
|
"step": 16735
|
|
},
|
|
{
|
|
"entropy": 5.648694181442261,
|
|
"epoch": 1.6613735609368798,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004729186819077214,
|
|
"loss": 5.194,
|
|
"mean_token_accuracy": 0.170845428109169,
|
|
"num_tokens": 36689480.0,
|
|
"step": 16740
|
|
},
|
|
{
|
|
"entropy": 5.64420747756958,
|
|
"epoch": 1.6618697895990473,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004729018267221092,
|
|
"loss": 5.2333,
|
|
"mean_token_accuracy": 0.17059906125068663,
|
|
"num_tokens": 36700420.0,
|
|
"step": 16745
|
|
},
|
|
{
|
|
"entropy": 5.64308443069458,
|
|
"epoch": 1.6623660182612148,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004728849666289581,
|
|
"loss": 5.1824,
|
|
"mean_token_accuracy": 0.17325215488672258,
|
|
"num_tokens": 36710106.0,
|
|
"step": 16750
|
|
},
|
|
{
|
|
"entropy": 5.581542301177978,
|
|
"epoch": 1.6628622469233822,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00047286810162868625,
|
|
"loss": 5.0579,
|
|
"mean_token_accuracy": 0.18079546242952346,
|
|
"num_tokens": 36719630.0,
|
|
"step": 16755
|
|
},
|
|
{
|
|
"entropy": 5.464664649963379,
|
|
"epoch": 1.6633584755855497,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004728512317217119,
|
|
"loss": 5.0399,
|
|
"mean_token_accuracy": 0.17958485782146455,
|
|
"num_tokens": 36729379.0,
|
|
"step": 16760
|
|
},
|
|
{
|
|
"entropy": 5.484744596481323,
|
|
"epoch": 1.6638547042477172,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00047283435690845336,
|
|
"loss": 5.0921,
|
|
"mean_token_accuracy": 0.1769113913178444,
|
|
"num_tokens": 36740103.0,
|
|
"step": 16765
|
|
},
|
|
{
|
|
"entropy": 5.565602731704712,
|
|
"epoch": 1.664350932909885,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00047281747718932906,
|
|
"loss": 5.135,
|
|
"mean_token_accuracy": 0.17403532713651657,
|
|
"num_tokens": 36750928.0,
|
|
"step": 16770
|
|
},
|
|
{
|
|
"entropy": 5.570236349105835,
|
|
"epoch": 1.6648471615720524,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004728005925647575,
|
|
"loss": 5.1433,
|
|
"mean_token_accuracy": 0.17115781158208848,
|
|
"num_tokens": 36761415.0,
|
|
"step": 16775
|
|
},
|
|
{
|
|
"entropy": 5.541550922393799,
|
|
"epoch": 1.66534339023422,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00047278370303515744,
|
|
"loss": 5.1716,
|
|
"mean_token_accuracy": 0.16619772613048553,
|
|
"num_tokens": 36772560.0,
|
|
"step": 16780
|
|
},
|
|
{
|
|
"entropy": 5.570325660705566,
|
|
"epoch": 1.6658396188963875,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004727668086009478,
|
|
"loss": 5.1771,
|
|
"mean_token_accuracy": 0.16833605915307998,
|
|
"num_tokens": 36783597.0,
|
|
"step": 16785
|
|
},
|
|
{
|
|
"entropy": 5.623755311965942,
|
|
"epoch": 1.666335847558555,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00047274990926254753,
|
|
"loss": 5.241,
|
|
"mean_token_accuracy": 0.16613737046718596,
|
|
"num_tokens": 36794219.0,
|
|
"step": 16790
|
|
},
|
|
{
|
|
"entropy": 5.531423044204712,
|
|
"epoch": 1.6668320762207225,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004727330050203755,
|
|
"loss": 5.0706,
|
|
"mean_token_accuracy": 0.17751879394054412,
|
|
"num_tokens": 36804156.0,
|
|
"step": 16795
|
|
},
|
|
{
|
|
"entropy": 5.526420593261719,
|
|
"epoch": 1.66732830488289,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004727160958748511,
|
|
"loss": 5.0992,
|
|
"mean_token_accuracy": 0.17404341101646423,
|
|
"num_tokens": 36814414.0,
|
|
"step": 16800
|
|
},
|
|
{
|
|
"entropy": 5.537476396560669,
|
|
"epoch": 1.6678245335450574,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00047269918182639355,
|
|
"loss": 5.0538,
|
|
"mean_token_accuracy": 0.17120650112628938,
|
|
"num_tokens": 36826173.0,
|
|
"step": 16805
|
|
},
|
|
{
|
|
"entropy": 5.599848461151123,
|
|
"epoch": 1.6683207622072251,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004726822628754222,
|
|
"loss": 5.1583,
|
|
"mean_token_accuracy": 0.17181871086359024,
|
|
"num_tokens": 36837726.0,
|
|
"step": 16810
|
|
},
|
|
{
|
|
"entropy": 5.598222827911377,
|
|
"epoch": 1.6688169908693926,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00047266533902235683,
|
|
"loss": 5.1289,
|
|
"mean_token_accuracy": 0.16565078496932983,
|
|
"num_tokens": 36848605.0,
|
|
"step": 16815
|
|
},
|
|
{
|
|
"entropy": 5.582981300354004,
|
|
"epoch": 1.66931321953156,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004726484102676169,
|
|
"loss": 5.153,
|
|
"mean_token_accuracy": 0.17065990567207337,
|
|
"num_tokens": 36858730.0,
|
|
"step": 16820
|
|
},
|
|
{
|
|
"entropy": 5.526777505874634,
|
|
"epoch": 1.6698094481937278,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004726314766116223,
|
|
"loss": 5.0192,
|
|
"mean_token_accuracy": 0.17582650780677794,
|
|
"num_tokens": 36868239.0,
|
|
"step": 16825
|
|
},
|
|
{
|
|
"entropy": 5.5396997928619385,
|
|
"epoch": 1.6703056768558953,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000472614538054793,
|
|
"loss": 5.105,
|
|
"mean_token_accuracy": 0.17341177314519882,
|
|
"num_tokens": 36878077.0,
|
|
"step": 16830
|
|
},
|
|
{
|
|
"entropy": 5.55140323638916,
|
|
"epoch": 1.6708019055180627,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.00047259759459754893,
|
|
"loss": 5.1533,
|
|
"mean_token_accuracy": 0.16827925592660903,
|
|
"num_tokens": 36888874.0,
|
|
"step": 16835
|
|
},
|
|
{
|
|
"entropy": 5.578630161285401,
|
|
"epoch": 1.6712981341802302,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004725806462403103,
|
|
"loss": 5.1435,
|
|
"mean_token_accuracy": 0.17273767292499542,
|
|
"num_tokens": 36898584.0,
|
|
"step": 16840
|
|
},
|
|
{
|
|
"entropy": 5.573261022567749,
|
|
"epoch": 1.6717943628423977,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00047256369298349736,
|
|
"loss": 5.1368,
|
|
"mean_token_accuracy": 0.17315253764390945,
|
|
"num_tokens": 36908662.0,
|
|
"step": 16845
|
|
},
|
|
{
|
|
"entropy": 5.5238433361053465,
|
|
"epoch": 1.6722905915045652,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00047254673482753065,
|
|
"loss": 5.0781,
|
|
"mean_token_accuracy": 0.17288859486579894,
|
|
"num_tokens": 36919482.0,
|
|
"step": 16850
|
|
},
|
|
{
|
|
"entropy": 5.538987350463867,
|
|
"epoch": 1.6727868201667329,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.00047252977177283045,
|
|
"loss": 5.1121,
|
|
"mean_token_accuracy": 0.16581951528787614,
|
|
"num_tokens": 36930470.0,
|
|
"step": 16855
|
|
},
|
|
{
|
|
"entropy": 5.563366413116455,
|
|
"epoch": 1.6732830488289003,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.00047251280381981764,
|
|
"loss": 5.1026,
|
|
"mean_token_accuracy": 0.1766013354063034,
|
|
"num_tokens": 36942837.0,
|
|
"step": 16860
|
|
},
|
|
{
|
|
"entropy": 5.6174417495727536,
|
|
"epoch": 1.673779277491068,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004724958309689129,
|
|
"loss": 5.1788,
|
|
"mean_token_accuracy": 0.166561958193779,
|
|
"num_tokens": 36952994.0,
|
|
"step": 16865
|
|
},
|
|
{
|
|
"entropy": 5.551107740402221,
|
|
"epoch": 1.6742755061532355,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.00047247885322053705,
|
|
"loss": 5.1597,
|
|
"mean_token_accuracy": 0.16894342005252838,
|
|
"num_tokens": 36963973.0,
|
|
"step": 16870
|
|
},
|
|
{
|
|
"entropy": 5.503463888168335,
|
|
"epoch": 1.674771734815403,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.00047246187057511127,
|
|
"loss": 5.0956,
|
|
"mean_token_accuracy": 0.17601613700389862,
|
|
"num_tokens": 36975897.0,
|
|
"step": 16875
|
|
},
|
|
{
|
|
"entropy": 5.553459167480469,
|
|
"epoch": 1.6752679634775705,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004724448830330565,
|
|
"loss": 5.1027,
|
|
"mean_token_accuracy": 0.1754691183567047,
|
|
"num_tokens": 36986481.0,
|
|
"step": 16880
|
|
},
|
|
{
|
|
"entropy": 5.567030382156372,
|
|
"epoch": 1.675764192139738,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.00047242789059479413,
|
|
"loss": 5.192,
|
|
"mean_token_accuracy": 0.1680533319711685,
|
|
"num_tokens": 36997863.0,
|
|
"step": 16885
|
|
},
|
|
{
|
|
"entropy": 5.620091247558594,
|
|
"epoch": 1.6762604208019054,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00047241089326074547,
|
|
"loss": 5.1383,
|
|
"mean_token_accuracy": 0.1653734490275383,
|
|
"num_tokens": 37009294.0,
|
|
"step": 16890
|
|
},
|
|
{
|
|
"entropy": 5.612838077545166,
|
|
"epoch": 1.6767566494640729,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004723938910313321,
|
|
"loss": 5.1261,
|
|
"mean_token_accuracy": 0.17353014796972274,
|
|
"num_tokens": 37019748.0,
|
|
"step": 16895
|
|
},
|
|
{
|
|
"entropy": 5.588705968856812,
|
|
"epoch": 1.6772528781262406,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00047237688390697555,
|
|
"loss": 5.1778,
|
|
"mean_token_accuracy": 0.17644532546401023,
|
|
"num_tokens": 37030903.0,
|
|
"step": 16900
|
|
},
|
|
{
|
|
"entropy": 5.5499029636383055,
|
|
"epoch": 1.677749106788408,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004723598718880975,
|
|
"loss": 5.1043,
|
|
"mean_token_accuracy": 0.1754912927746773,
|
|
"num_tokens": 37042551.0,
|
|
"step": 16905
|
|
},
|
|
{
|
|
"entropy": 5.577929353713989,
|
|
"epoch": 1.6782453354505757,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00047234285497512005,
|
|
"loss": 5.1709,
|
|
"mean_token_accuracy": 0.16915378719568253,
|
|
"num_tokens": 37053151.0,
|
|
"step": 16910
|
|
},
|
|
{
|
|
"entropy": 5.629922771453858,
|
|
"epoch": 1.6787415641127432,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.00047232583316846494,
|
|
"loss": 5.1829,
|
|
"mean_token_accuracy": 0.166587033867836,
|
|
"num_tokens": 37064421.0,
|
|
"step": 16915
|
|
},
|
|
{
|
|
"entropy": 5.578013801574707,
|
|
"epoch": 1.6792377927749107,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004723088064685544,
|
|
"loss": 5.1295,
|
|
"mean_token_accuracy": 0.17486939132213591,
|
|
"num_tokens": 37074758.0,
|
|
"step": 16920
|
|
},
|
|
{
|
|
"entropy": 5.577193069458008,
|
|
"epoch": 1.6797340214370782,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00047229177487581055,
|
|
"loss": 5.0896,
|
|
"mean_token_accuracy": 0.16904166638851165,
|
|
"num_tokens": 37084898.0,
|
|
"step": 16925
|
|
},
|
|
{
|
|
"entropy": 5.608043193817139,
|
|
"epoch": 1.6802302500992456,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00047227473839065587,
|
|
"loss": 5.1651,
|
|
"mean_token_accuracy": 0.1672091618180275,
|
|
"num_tokens": 37094366.0,
|
|
"step": 16930
|
|
},
|
|
{
|
|
"entropy": 5.676841306686401,
|
|
"epoch": 1.6807264787614131,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00047225769701351284,
|
|
"loss": 5.2253,
|
|
"mean_token_accuracy": 0.1685462027788162,
|
|
"num_tokens": 37104965.0,
|
|
"step": 16935
|
|
},
|
|
{
|
|
"entropy": 5.537209129333496,
|
|
"epoch": 1.6812227074235808,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004722406507448038,
|
|
"loss": 5.0931,
|
|
"mean_token_accuracy": 0.17549068480730057,
|
|
"num_tokens": 37115622.0,
|
|
"step": 16940
|
|
},
|
|
{
|
|
"entropy": 5.609269428253174,
|
|
"epoch": 1.6817189360857483,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.00047222359958495175,
|
|
"loss": 5.1824,
|
|
"mean_token_accuracy": 0.16754831671714782,
|
|
"num_tokens": 37127234.0,
|
|
"step": 16945
|
|
},
|
|
{
|
|
"entropy": 5.570038747787476,
|
|
"epoch": 1.682215164747916,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004722065435343794,
|
|
"loss": 5.0474,
|
|
"mean_token_accuracy": 0.17715921103954316,
|
|
"num_tokens": 37136533.0,
|
|
"step": 16950
|
|
},
|
|
{
|
|
"entropy": 5.583553886413574,
|
|
"epoch": 1.6827113934100835,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004721894825935097,
|
|
"loss": 5.1544,
|
|
"mean_token_accuracy": 0.1715320512652397,
|
|
"num_tokens": 37147821.0,
|
|
"step": 16955
|
|
},
|
|
{
|
|
"entropy": 5.5517964363098145,
|
|
"epoch": 1.683207622072251,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004721724167627657,
|
|
"loss": 5.1583,
|
|
"mean_token_accuracy": 0.17215365469455718,
|
|
"num_tokens": 37158929.0,
|
|
"step": 16960
|
|
},
|
|
{
|
|
"entropy": 5.596142292022705,
|
|
"epoch": 1.6837038507344184,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004721553460425708,
|
|
"loss": 5.1548,
|
|
"mean_token_accuracy": 0.17849822491407394,
|
|
"num_tokens": 37169817.0,
|
|
"step": 16965
|
|
},
|
|
{
|
|
"entropy": 5.5814528465271,
|
|
"epoch": 1.684200079396586,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000472138270433348,
|
|
"loss": 5.2621,
|
|
"mean_token_accuracy": 0.16471544280648232,
|
|
"num_tokens": 37181009.0,
|
|
"step": 16970
|
|
},
|
|
{
|
|
"entropy": 5.552694463729859,
|
|
"epoch": 1.6846963080587534,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00047212118993552097,
|
|
"loss": 5.089,
|
|
"mean_token_accuracy": 0.1761760577559471,
|
|
"num_tokens": 37192110.0,
|
|
"step": 16975
|
|
},
|
|
{
|
|
"entropy": 5.575069570541382,
|
|
"epoch": 1.6851925367209208,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004721041045495131,
|
|
"loss": 5.136,
|
|
"mean_token_accuracy": 0.17346104234457016,
|
|
"num_tokens": 37203426.0,
|
|
"step": 16980
|
|
},
|
|
{
|
|
"entropy": 5.619303369522095,
|
|
"epoch": 1.6856887653830885,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00047208701427574817,
|
|
"loss": 5.2176,
|
|
"mean_token_accuracy": 0.16681872457265853,
|
|
"num_tokens": 37215025.0,
|
|
"step": 16985
|
|
},
|
|
{
|
|
"entropy": 5.6421293258667,
|
|
"epoch": 1.686184994045256,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00047206991911465,
|
|
"loss": 5.1477,
|
|
"mean_token_accuracy": 0.17911407649517058,
|
|
"num_tokens": 37225653.0,
|
|
"step": 16990
|
|
},
|
|
{
|
|
"entropy": 5.562642669677734,
|
|
"epoch": 1.6866812227074237,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004720528190666425,
|
|
"loss": 5.1179,
|
|
"mean_token_accuracy": 0.17100996524095535,
|
|
"num_tokens": 37237282.0,
|
|
"step": 16995
|
|
},
|
|
{
|
|
"entropy": 5.496473217010498,
|
|
"epoch": 1.6871774513695912,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00047203571413214967,
|
|
"loss": 5.0817,
|
|
"mean_token_accuracy": 0.18428921550512314,
|
|
"num_tokens": 37248476.0,
|
|
"step": 17000
|
|
},
|
|
{
|
|
"entropy": 5.570226001739502,
|
|
"epoch": 1.6876736800317587,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004720186043115957,
|
|
"loss": 5.0737,
|
|
"mean_token_accuracy": 0.1730433762073517,
|
|
"num_tokens": 37259354.0,
|
|
"step": 17005
|
|
},
|
|
{
|
|
"entropy": 5.569587993621826,
|
|
"epoch": 1.6881699086939261,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004720014896054048,
|
|
"loss": 5.1428,
|
|
"mean_token_accuracy": 0.16817787587642669,
|
|
"num_tokens": 37269895.0,
|
|
"step": 17010
|
|
},
|
|
{
|
|
"entropy": 5.536753702163696,
|
|
"epoch": 1.6886661373560936,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004719843700140017,
|
|
"loss": 5.1154,
|
|
"mean_token_accuracy": 0.17986234724521638,
|
|
"num_tokens": 37281201.0,
|
|
"step": 17015
|
|
},
|
|
{
|
|
"entropy": 5.558519506454468,
|
|
"epoch": 1.689162366018261,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004719672455378105,
|
|
"loss": 5.1291,
|
|
"mean_token_accuracy": 0.1699021965265274,
|
|
"num_tokens": 37293362.0,
|
|
"step": 17020
|
|
},
|
|
{
|
|
"entropy": 5.637897920608521,
|
|
"epoch": 1.6896585946804288,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.000471950116177256,
|
|
"loss": 5.1611,
|
|
"mean_token_accuracy": 0.1686394229531288,
|
|
"num_tokens": 37304291.0,
|
|
"step": 17025
|
|
},
|
|
{
|
|
"entropy": 5.596599674224853,
|
|
"epoch": 1.6901548233425963,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004719329819327631,
|
|
"loss": 5.1438,
|
|
"mean_token_accuracy": 0.1711001694202423,
|
|
"num_tokens": 37315608.0,
|
|
"step": 17030
|
|
},
|
|
{
|
|
"entropy": 5.569362735748291,
|
|
"epoch": 1.690651052004764,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004719158428047566,
|
|
"loss": 5.0943,
|
|
"mean_token_accuracy": 0.168352709710598,
|
|
"num_tokens": 37327559.0,
|
|
"step": 17035
|
|
},
|
|
{
|
|
"entropy": 5.5401458740234375,
|
|
"epoch": 1.6911472806669314,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004718986987936615,
|
|
"loss": 5.1212,
|
|
"mean_token_accuracy": 0.17786616533994676,
|
|
"num_tokens": 37338101.0,
|
|
"step": 17040
|
|
},
|
|
{
|
|
"entropy": 5.581073331832886,
|
|
"epoch": 1.691643509329099,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.00047188154989990296,
|
|
"loss": 5.2042,
|
|
"mean_token_accuracy": 0.17016657441854477,
|
|
"num_tokens": 37349124.0,
|
|
"step": 17045
|
|
},
|
|
{
|
|
"entropy": 5.540998935699463,
|
|
"epoch": 1.6921397379912664,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004718643961239062,
|
|
"loss": 5.0752,
|
|
"mean_token_accuracy": 0.17614357471466063,
|
|
"num_tokens": 37360061.0,
|
|
"step": 17050
|
|
},
|
|
{
|
|
"entropy": 5.579684495925903,
|
|
"epoch": 1.6926359666534339,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.00047184723746609666,
|
|
"loss": 5.1343,
|
|
"mean_token_accuracy": 0.17226943820714952,
|
|
"num_tokens": 37371210.0,
|
|
"step": 17055
|
|
},
|
|
{
|
|
"entropy": 5.542012166976929,
|
|
"epoch": 1.6931321953156013,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00047183007392689977,
|
|
"loss": 5.0946,
|
|
"mean_token_accuracy": 0.17004089504480363,
|
|
"num_tokens": 37382547.0,
|
|
"step": 17060
|
|
},
|
|
{
|
|
"entropy": 5.546593952178955,
|
|
"epoch": 1.6936284239777688,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00047181290550674115,
|
|
"loss": 5.1562,
|
|
"mean_token_accuracy": 0.17347490042448044,
|
|
"num_tokens": 37392311.0,
|
|
"step": 17065
|
|
},
|
|
{
|
|
"entropy": 5.5597306251525875,
|
|
"epoch": 1.6941246526399365,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004717957322060466,
|
|
"loss": 5.0964,
|
|
"mean_token_accuracy": 0.17364707738161086,
|
|
"num_tokens": 37402626.0,
|
|
"step": 17070
|
|
},
|
|
{
|
|
"entropy": 5.561833381652832,
|
|
"epoch": 1.694620881302104,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004717785540252419,
|
|
"loss": 5.1036,
|
|
"mean_token_accuracy": 0.17350115478038788,
|
|
"num_tokens": 37412100.0,
|
|
"step": 17075
|
|
},
|
|
{
|
|
"entropy": 5.498662233352661,
|
|
"epoch": 1.6951171099642717,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004717613709647532,
|
|
"loss": 5.0116,
|
|
"mean_token_accuracy": 0.17816671580076218,
|
|
"num_tokens": 37421735.0,
|
|
"step": 17080
|
|
},
|
|
{
|
|
"entropy": 5.607385110855103,
|
|
"epoch": 1.6956133386264391,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00047174418302500635,
|
|
"loss": 5.2093,
|
|
"mean_token_accuracy": 0.16542862951755524,
|
|
"num_tokens": 37432179.0,
|
|
"step": 17085
|
|
},
|
|
{
|
|
"entropy": 5.561559677124023,
|
|
"epoch": 1.6961095672886066,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004717269902064278,
|
|
"loss": 5.0763,
|
|
"mean_token_accuracy": 0.18370807766914368,
|
|
"num_tokens": 37443276.0,
|
|
"step": 17090
|
|
},
|
|
{
|
|
"entropy": 5.583922719955444,
|
|
"epoch": 1.696605795950774,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004717097925094438,
|
|
"loss": 5.1894,
|
|
"mean_token_accuracy": 0.1680811569094658,
|
|
"num_tokens": 37454537.0,
|
|
"step": 17095
|
|
},
|
|
{
|
|
"entropy": 5.591526508331299,
|
|
"epoch": 1.6971020246129416,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004716925899344808,
|
|
"loss": 5.1049,
|
|
"mean_token_accuracy": 0.1662537544965744,
|
|
"num_tokens": 37465493.0,
|
|
"step": 17100
|
|
},
|
|
{
|
|
"entropy": 5.507003307342529,
|
|
"epoch": 1.697598253275109,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004716753824819654,
|
|
"loss": 5.0996,
|
|
"mean_token_accuracy": 0.17380036562681198,
|
|
"num_tokens": 37475511.0,
|
|
"step": 17105
|
|
},
|
|
{
|
|
"entropy": 5.503319501876831,
|
|
"epoch": 1.6980944819372767,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004716581701523243,
|
|
"loss": 5.0102,
|
|
"mean_token_accuracy": 0.17425770163536072,
|
|
"num_tokens": 37487046.0,
|
|
"step": 17110
|
|
},
|
|
{
|
|
"entropy": 5.565830039978027,
|
|
"epoch": 1.6985907105994442,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.00047164095294598433,
|
|
"loss": 5.1641,
|
|
"mean_token_accuracy": 0.16879702657461165,
|
|
"num_tokens": 37498398.0,
|
|
"step": 17115
|
|
},
|
|
{
|
|
"entropy": 5.57945761680603,
|
|
"epoch": 1.699086939261612,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.00047162373086337243,
|
|
"loss": 5.1716,
|
|
"mean_token_accuracy": 0.16734508275985718,
|
|
"num_tokens": 37509397.0,
|
|
"step": 17120
|
|
},
|
|
{
|
|
"entropy": 5.572624397277832,
|
|
"epoch": 1.6995831679237794,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00047160650390491574,
|
|
"loss": 5.0499,
|
|
"mean_token_accuracy": 0.18090201318264007,
|
|
"num_tokens": 37519284.0,
|
|
"step": 17125
|
|
},
|
|
{
|
|
"entropy": 5.5761829853057865,
|
|
"epoch": 1.7000793965859469,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004715892720710414,
|
|
"loss": 5.1518,
|
|
"mean_token_accuracy": 0.17086864560842513,
|
|
"num_tokens": 37529699.0,
|
|
"step": 17130
|
|
},
|
|
{
|
|
"entropy": 5.636133861541748,
|
|
"epoch": 1.7005756252481143,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004715720353621767,
|
|
"loss": 5.2017,
|
|
"mean_token_accuracy": 0.16297321021556854,
|
|
"num_tokens": 37541756.0,
|
|
"step": 17135
|
|
},
|
|
{
|
|
"entropy": 5.502932071685791,
|
|
"epoch": 1.7010718539102818,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00047155479377874917,
|
|
"loss": 5.0829,
|
|
"mean_token_accuracy": 0.17542338222265244,
|
|
"num_tokens": 37552693.0,
|
|
"step": 17140
|
|
},
|
|
{
|
|
"entropy": 5.546161079406739,
|
|
"epoch": 1.7015680825724493,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00047153754732118616,
|
|
"loss": 5.062,
|
|
"mean_token_accuracy": 0.1763912707567215,
|
|
"num_tokens": 37563826.0,
|
|
"step": 17145
|
|
},
|
|
{
|
|
"entropy": 5.5860276222229,
|
|
"epoch": 1.7020643112346168,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004715202959899156,
|
|
"loss": 5.1042,
|
|
"mean_token_accuracy": 0.17517814189195632,
|
|
"num_tokens": 37576645.0,
|
|
"step": 17150
|
|
},
|
|
{
|
|
"entropy": 5.4545149326324465,
|
|
"epoch": 1.7025605398967845,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004715030397853651,
|
|
"loss": 4.9822,
|
|
"mean_token_accuracy": 0.1835605651140213,
|
|
"num_tokens": 37587467.0,
|
|
"step": 17155
|
|
},
|
|
{
|
|
"entropy": 5.592034387588501,
|
|
"epoch": 1.703056768558952,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00047148577870796264,
|
|
"loss": 5.1635,
|
|
"mean_token_accuracy": 0.1691695600748062,
|
|
"num_tokens": 37598475.0,
|
|
"step": 17160
|
|
},
|
|
{
|
|
"entropy": 5.627919244766235,
|
|
"epoch": 1.7035529972211196,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004714685127581363,
|
|
"loss": 5.2541,
|
|
"mean_token_accuracy": 0.16691816747188568,
|
|
"num_tokens": 37610260.0,
|
|
"step": 17165
|
|
},
|
|
{
|
|
"entropy": 5.5737567901611325,
|
|
"epoch": 1.704049225883287,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00047145124193631415,
|
|
"loss": 5.1827,
|
|
"mean_token_accuracy": 0.16948528289794923,
|
|
"num_tokens": 37621129.0,
|
|
"step": 17170
|
|
},
|
|
{
|
|
"entropy": 5.548666667938233,
|
|
"epoch": 1.7045454545454546,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.00047143396624292454,
|
|
"loss": 5.0774,
|
|
"mean_token_accuracy": 0.17280406951904298,
|
|
"num_tokens": 37633130.0,
|
|
"step": 17175
|
|
},
|
|
{
|
|
"entropy": 5.599744749069214,
|
|
"epoch": 1.705041683207622,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.00047141668567839584,
|
|
"loss": 5.2022,
|
|
"mean_token_accuracy": 0.1700626716017723,
|
|
"num_tokens": 37644247.0,
|
|
"step": 17180
|
|
},
|
|
{
|
|
"entropy": 5.616266393661499,
|
|
"epoch": 1.7055379118697895,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004713994002431566,
|
|
"loss": 5.1247,
|
|
"mean_token_accuracy": 0.17535771131515504,
|
|
"num_tokens": 37655602.0,
|
|
"step": 17185
|
|
},
|
|
{
|
|
"entropy": 5.5037469387054445,
|
|
"epoch": 1.706034140531957,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.00047138210993763534,
|
|
"loss": 5.0519,
|
|
"mean_token_accuracy": 0.18014779239892958,
|
|
"num_tokens": 37667150.0,
|
|
"step": 17190
|
|
},
|
|
{
|
|
"entropy": 5.492997026443481,
|
|
"epoch": 1.7065303691941247,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.000471364814762261,
|
|
"loss": 5.0593,
|
|
"mean_token_accuracy": 0.1819021925330162,
|
|
"num_tokens": 37677626.0,
|
|
"step": 17195
|
|
},
|
|
{
|
|
"entropy": 5.625694274902344,
|
|
"epoch": 1.7070265978562922,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004713475147174624,
|
|
"loss": 5.2086,
|
|
"mean_token_accuracy": 0.16772229075431824,
|
|
"num_tokens": 37689050.0,
|
|
"step": 17200
|
|
},
|
|
{
|
|
"entropy": 5.645072174072266,
|
|
"epoch": 1.7075228265184597,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004713302098036685,
|
|
"loss": 5.0943,
|
|
"mean_token_accuracy": 0.18364367932081221,
|
|
"num_tokens": 37699190.0,
|
|
"step": 17205
|
|
},
|
|
{
|
|
"entropy": 5.486385536193848,
|
|
"epoch": 1.7080190551806274,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004713129000213085,
|
|
"loss": 5.0834,
|
|
"mean_token_accuracy": 0.17613888382911683,
|
|
"num_tokens": 37710465.0,
|
|
"step": 17210
|
|
},
|
|
{
|
|
"entropy": 5.506699085235596,
|
|
"epoch": 1.7085152838427948,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004712955853708115,
|
|
"loss": 5.1841,
|
|
"mean_token_accuracy": 0.17233196049928665,
|
|
"num_tokens": 37722426.0,
|
|
"step": 17215
|
|
},
|
|
{
|
|
"entropy": 5.529746675491333,
|
|
"epoch": 1.7090115125049623,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.000471278265852607,
|
|
"loss": 5.079,
|
|
"mean_token_accuracy": 0.17865019738674165,
|
|
"num_tokens": 37733104.0,
|
|
"step": 17220
|
|
},
|
|
{
|
|
"entropy": 5.527663230895996,
|
|
"epoch": 1.7095077411671298,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004712609414671245,
|
|
"loss": 5.0179,
|
|
"mean_token_accuracy": 0.1805179536342621,
|
|
"num_tokens": 37742747.0,
|
|
"step": 17225
|
|
},
|
|
{
|
|
"entropy": 5.536157608032227,
|
|
"epoch": 1.7100039698292973,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004712436122147935,
|
|
"loss": 5.0757,
|
|
"mean_token_accuracy": 0.17503509670495987,
|
|
"num_tokens": 37753338.0,
|
|
"step": 17230
|
|
},
|
|
{
|
|
"entropy": 5.518141984939575,
|
|
"epoch": 1.7105001984914647,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004712262780960438,
|
|
"loss": 5.0722,
|
|
"mean_token_accuracy": 0.17581305652856827,
|
|
"num_tokens": 37763122.0,
|
|
"step": 17235
|
|
},
|
|
{
|
|
"entropy": 5.539923191070557,
|
|
"epoch": 1.7109964271536324,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00047120893911130525,
|
|
"loss": 5.0676,
|
|
"mean_token_accuracy": 0.17038348764181138,
|
|
"num_tokens": 37774677.0,
|
|
"step": 17240
|
|
},
|
|
{
|
|
"entropy": 5.534102201461792,
|
|
"epoch": 1.7114926558158,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.00047119159526100773,
|
|
"loss": 5.0839,
|
|
"mean_token_accuracy": 0.16821239292621612,
|
|
"num_tokens": 37786186.0,
|
|
"step": 17245
|
|
},
|
|
{
|
|
"entropy": 5.517325782775879,
|
|
"epoch": 1.7119888844779676,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.00047117424654558146,
|
|
"loss": 5.1005,
|
|
"mean_token_accuracy": 0.1793801948428154,
|
|
"num_tokens": 37796837.0,
|
|
"step": 17250
|
|
},
|
|
{
|
|
"entropy": 5.575711917877197,
|
|
"epoch": 1.712485113140135,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004711568929654566,
|
|
"loss": 5.1631,
|
|
"mean_token_accuracy": 0.17081210911273956,
|
|
"num_tokens": 37808813.0,
|
|
"step": 17255
|
|
},
|
|
{
|
|
"entropy": 5.549413204193115,
|
|
"epoch": 1.7129813418023025,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004711395345210635,
|
|
"loss": 5.026,
|
|
"mean_token_accuracy": 0.17955968677997589,
|
|
"num_tokens": 37819770.0,
|
|
"step": 17260
|
|
},
|
|
{
|
|
"entropy": 5.550781917572022,
|
|
"epoch": 1.71347757046447,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004711221712128325,
|
|
"loss": 5.1137,
|
|
"mean_token_accuracy": 0.17487804740667343,
|
|
"num_tokens": 37831831.0,
|
|
"step": 17265
|
|
},
|
|
{
|
|
"entropy": 5.555217266082764,
|
|
"epoch": 1.7139737991266375,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004711048030411943,
|
|
"loss": 5.1576,
|
|
"mean_token_accuracy": 0.17047970294952391,
|
|
"num_tokens": 37843092.0,
|
|
"step": 17270
|
|
},
|
|
{
|
|
"entropy": 5.58795166015625,
|
|
"epoch": 1.714470027788805,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.00047108743000657963,
|
|
"loss": 5.1244,
|
|
"mean_token_accuracy": 0.1759021446108818,
|
|
"num_tokens": 37853192.0,
|
|
"step": 17275
|
|
},
|
|
{
|
|
"entropy": 5.647727727890015,
|
|
"epoch": 1.7149662564509724,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004710700521094192,
|
|
"loss": 5.1529,
|
|
"mean_token_accuracy": 0.17165095061063768,
|
|
"num_tokens": 37863510.0,
|
|
"step": 17280
|
|
},
|
|
{
|
|
"entropy": 5.532742357254028,
|
|
"epoch": 1.7154624851131401,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.00047105266935014385,
|
|
"loss": 5.0631,
|
|
"mean_token_accuracy": 0.18225870579481124,
|
|
"num_tokens": 37876156.0,
|
|
"step": 17285
|
|
},
|
|
{
|
|
"entropy": 5.518691778182983,
|
|
"epoch": 1.7159587137753076,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00047103528172918487,
|
|
"loss": 5.1169,
|
|
"mean_token_accuracy": 0.17749424576759337,
|
|
"num_tokens": 37887153.0,
|
|
"step": 17290
|
|
},
|
|
{
|
|
"entropy": 5.5618085861206055,
|
|
"epoch": 1.7164549424374753,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004710178892469733,
|
|
"loss": 5.0978,
|
|
"mean_token_accuracy": 0.1794215679168701,
|
|
"num_tokens": 37898820.0,
|
|
"step": 17295
|
|
},
|
|
{
|
|
"entropy": 5.578125381469727,
|
|
"epoch": 1.7169511710996428,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.00047100049190394044,
|
|
"loss": 5.0888,
|
|
"mean_token_accuracy": 0.17426283210515975,
|
|
"num_tokens": 37910257.0,
|
|
"step": 17300
|
|
},
|
|
{
|
|
"entropy": 5.544584131240844,
|
|
"epoch": 1.7174473997618103,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004709830897005178,
|
|
"loss": 5.1771,
|
|
"mean_token_accuracy": 0.17154236435890197,
|
|
"num_tokens": 37921574.0,
|
|
"step": 17305
|
|
},
|
|
{
|
|
"entropy": 5.616960573196411,
|
|
"epoch": 1.7179436284239777,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004709656826371367,
|
|
"loss": 5.1606,
|
|
"mean_token_accuracy": 0.17311425507068634,
|
|
"num_tokens": 37932741.0,
|
|
"step": 17310
|
|
},
|
|
{
|
|
"entropy": 5.556202793121338,
|
|
"epoch": 1.7184398570861452,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004709482707142291,
|
|
"loss": 5.1318,
|
|
"mean_token_accuracy": 0.17382349967956542,
|
|
"num_tokens": 37944592.0,
|
|
"step": 17315
|
|
},
|
|
{
|
|
"entropy": 5.557074880599975,
|
|
"epoch": 1.7189360857483127,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00047093085393222646,
|
|
"loss": 5.0809,
|
|
"mean_token_accuracy": 0.17793885618448257,
|
|
"num_tokens": 37954983.0,
|
|
"step": 17320
|
|
},
|
|
{
|
|
"entropy": 5.562156009674072,
|
|
"epoch": 1.7194323144104804,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00047091343229156094,
|
|
"loss": 5.1546,
|
|
"mean_token_accuracy": 0.17035369724035263,
|
|
"num_tokens": 37964491.0,
|
|
"step": 17325
|
|
},
|
|
{
|
|
"entropy": 5.5098920345306395,
|
|
"epoch": 1.7199285430726479,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004708960057926644,
|
|
"loss": 5.0451,
|
|
"mean_token_accuracy": 0.1774196907877922,
|
|
"num_tokens": 37976140.0,
|
|
"step": 17330
|
|
},
|
|
{
|
|
"entropy": 5.549550008773804,
|
|
"epoch": 1.7204247717348156,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00047087857443596905,
|
|
"loss": 5.0867,
|
|
"mean_token_accuracy": 0.1775013253092766,
|
|
"num_tokens": 37987776.0,
|
|
"step": 17335
|
|
},
|
|
{
|
|
"entropy": 5.560797166824341,
|
|
"epoch": 1.720921000396983,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00047086113822190716,
|
|
"loss": 5.1484,
|
|
"mean_token_accuracy": 0.16919077336788177,
|
|
"num_tokens": 37998088.0,
|
|
"step": 17340
|
|
},
|
|
{
|
|
"entropy": 5.53006944656372,
|
|
"epoch": 1.7214172290591505,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.00047084369715091103,
|
|
"loss": 5.1337,
|
|
"mean_token_accuracy": 0.16951314210891724,
|
|
"num_tokens": 38009802.0,
|
|
"step": 17345
|
|
},
|
|
{
|
|
"entropy": 5.5932230949401855,
|
|
"epoch": 1.721913457721318,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004708262512234133,
|
|
"loss": 5.1716,
|
|
"mean_token_accuracy": 0.17263431549072267,
|
|
"num_tokens": 38020797.0,
|
|
"step": 17350
|
|
},
|
|
{
|
|
"entropy": 5.6425275802612305,
|
|
"epoch": 1.7224096863834855,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004708088004398464,
|
|
"loss": 5.1624,
|
|
"mean_token_accuracy": 0.17210831940174104,
|
|
"num_tokens": 38031816.0,
|
|
"step": 17355
|
|
},
|
|
{
|
|
"entropy": 5.545508813858032,
|
|
"epoch": 1.722905915045653,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004707913448006433,
|
|
"loss": 5.1609,
|
|
"mean_token_accuracy": 0.16241195946931838,
|
|
"num_tokens": 38043953.0,
|
|
"step": 17360
|
|
},
|
|
{
|
|
"entropy": 5.514689874649048,
|
|
"epoch": 1.7234021437078204,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004707738843062367,
|
|
"loss": 5.0318,
|
|
"mean_token_accuracy": 0.1831573724746704,
|
|
"num_tokens": 38053929.0,
|
|
"step": 17365
|
|
},
|
|
{
|
|
"entropy": 5.626897382736206,
|
|
"epoch": 1.723898372369988,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004707564189570596,
|
|
"loss": 5.2587,
|
|
"mean_token_accuracy": 0.17311705201864241,
|
|
"num_tokens": 38067091.0,
|
|
"step": 17370
|
|
},
|
|
{
|
|
"entropy": 5.591850090026855,
|
|
"epoch": 1.7243946010321556,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004707389487535451,
|
|
"loss": 5.0969,
|
|
"mean_token_accuracy": 0.17243184596300126,
|
|
"num_tokens": 38079002.0,
|
|
"step": 17375
|
|
},
|
|
{
|
|
"entropy": 5.5826293468475345,
|
|
"epoch": 1.7248908296943233,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004707214736961265,
|
|
"loss": 5.1032,
|
|
"mean_token_accuracy": 0.1832143947482109,
|
|
"num_tokens": 38089526.0,
|
|
"step": 17380
|
|
},
|
|
{
|
|
"entropy": 5.559901714324951,
|
|
"epoch": 1.7253870583564908,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004707039937852371,
|
|
"loss": 5.1073,
|
|
"mean_token_accuracy": 0.1793068215250969,
|
|
"num_tokens": 38099902.0,
|
|
"step": 17385
|
|
},
|
|
{
|
|
"entropy": 5.523968744277954,
|
|
"epoch": 1.7258832870186582,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.00047068650902131034,
|
|
"loss": 5.0738,
|
|
"mean_token_accuracy": 0.17942894697189332,
|
|
"num_tokens": 38111725.0,
|
|
"step": 17390
|
|
},
|
|
{
|
|
"entropy": 5.558438062667847,
|
|
"epoch": 1.7263795156808257,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004706690194047798,
|
|
"loss": 5.0404,
|
|
"mean_token_accuracy": 0.17444614320993423,
|
|
"num_tokens": 38123522.0,
|
|
"step": 17395
|
|
},
|
|
{
|
|
"entropy": 5.573927783966065,
|
|
"epoch": 1.7268757443429932,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004706515249360792,
|
|
"loss": 5.1705,
|
|
"mean_token_accuracy": 0.17031463235616684,
|
|
"num_tokens": 38133968.0,
|
|
"step": 17400
|
|
},
|
|
{
|
|
"entropy": 5.529282188415527,
|
|
"epoch": 1.7273719730051607,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004706340256156425,
|
|
"loss": 5.221,
|
|
"mean_token_accuracy": 0.16289281845092773,
|
|
"num_tokens": 38145288.0,
|
|
"step": 17405
|
|
},
|
|
{
|
|
"entropy": 5.58859338760376,
|
|
"epoch": 1.7278682016673284,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004706165214439034,
|
|
"loss": 5.1151,
|
|
"mean_token_accuracy": 0.17147918045520782,
|
|
"num_tokens": 38156141.0,
|
|
"step": 17410
|
|
},
|
|
{
|
|
"entropy": 5.618618202209473,
|
|
"epoch": 1.7283644303294958,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004705990124212961,
|
|
"loss": 5.0777,
|
|
"mean_token_accuracy": 0.18603018969297408,
|
|
"num_tokens": 38167211.0,
|
|
"step": 17415
|
|
},
|
|
{
|
|
"entropy": 5.545669031143189,
|
|
"epoch": 1.7288606589916635,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004705814985482548,
|
|
"loss": 5.1414,
|
|
"mean_token_accuracy": 0.17378313094377518,
|
|
"num_tokens": 38177360.0,
|
|
"step": 17420
|
|
},
|
|
{
|
|
"entropy": 5.508595895767212,
|
|
"epoch": 1.729356887653831,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00047056397982521366,
|
|
"loss": 5.0437,
|
|
"mean_token_accuracy": 0.17996789664030075,
|
|
"num_tokens": 38187857.0,
|
|
"step": 17425
|
|
},
|
|
{
|
|
"entropy": 5.590577268600464,
|
|
"epoch": 1.7298531163159985,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004705464562526074,
|
|
"loss": 5.1715,
|
|
"mean_token_accuracy": 0.16224278807640075,
|
|
"num_tokens": 38198161.0,
|
|
"step": 17430
|
|
},
|
|
{
|
|
"entropy": 5.585971641540527,
|
|
"epoch": 1.730349344978166,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004705289278308703,
|
|
"loss": 5.1016,
|
|
"mean_token_accuracy": 0.17599351853132247,
|
|
"num_tokens": 38208612.0,
|
|
"step": 17435
|
|
},
|
|
{
|
|
"entropy": 5.5811385154724125,
|
|
"epoch": 1.7308455736403334,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.00047051139456043707,
|
|
"loss": 5.135,
|
|
"mean_token_accuracy": 0.17004906982183457,
|
|
"num_tokens": 38220153.0,
|
|
"step": 17440
|
|
},
|
|
{
|
|
"entropy": 5.555471706390381,
|
|
"epoch": 1.731341802302501,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004704938564417427,
|
|
"loss": 5.1011,
|
|
"mean_token_accuracy": 0.17772171795368194,
|
|
"num_tokens": 38230790.0,
|
|
"step": 17445
|
|
},
|
|
{
|
|
"entropy": 5.55522928237915,
|
|
"epoch": 1.7318380309646684,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00047047631347522175,
|
|
"loss": 5.049,
|
|
"mean_token_accuracy": 0.18061629682779312,
|
|
"num_tokens": 38242585.0,
|
|
"step": 17450
|
|
},
|
|
{
|
|
"entropy": 5.5654490947723385,
|
|
"epoch": 1.732334259626836,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.00047045876566130957,
|
|
"loss": 5.1042,
|
|
"mean_token_accuracy": 0.1754191666841507,
|
|
"num_tokens": 38253316.0,
|
|
"step": 17455
|
|
},
|
|
{
|
|
"entropy": 5.488184547424316,
|
|
"epoch": 1.7328304882890035,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004704412130004411,
|
|
"loss": 5.0802,
|
|
"mean_token_accuracy": 0.17691100835800172,
|
|
"num_tokens": 38263230.0,
|
|
"step": 17460
|
|
},
|
|
{
|
|
"entropy": 5.581308841705322,
|
|
"epoch": 1.7333267169511712,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00047042365549305174,
|
|
"loss": 5.1468,
|
|
"mean_token_accuracy": 0.17157044857740403,
|
|
"num_tokens": 38273416.0,
|
|
"step": 17465
|
|
},
|
|
{
|
|
"entropy": 5.53314242362976,
|
|
"epoch": 1.7338229456133387,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004704060931395768,
|
|
"loss": 5.0769,
|
|
"mean_token_accuracy": 0.18006590902805328,
|
|
"num_tokens": 38285764.0,
|
|
"step": 17470
|
|
},
|
|
{
|
|
"entropy": 5.591202259063721,
|
|
"epoch": 1.7343191742755062,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00047038852594045186,
|
|
"loss": 5.1833,
|
|
"mean_token_accuracy": 0.17256945371627808,
|
|
"num_tokens": 38296899.0,
|
|
"step": 17475
|
|
},
|
|
{
|
|
"entropy": 5.616226673126221,
|
|
"epoch": 1.7348154029376737,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00047037095389611245,
|
|
"loss": 5.1743,
|
|
"mean_token_accuracy": 0.17670390009880066,
|
|
"num_tokens": 38309050.0,
|
|
"step": 17480
|
|
},
|
|
{
|
|
"entropy": 5.5264490127563475,
|
|
"epoch": 1.7353116315998411,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004703533770069944,
|
|
"loss": 5.1091,
|
|
"mean_token_accuracy": 0.1777672663331032,
|
|
"num_tokens": 38320831.0,
|
|
"step": 17485
|
|
},
|
|
{
|
|
"entropy": 5.567055511474609,
|
|
"epoch": 1.7358078602620086,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.00047033579527353355,
|
|
"loss": 5.135,
|
|
"mean_token_accuracy": 0.17228993624448777,
|
|
"num_tokens": 38332096.0,
|
|
"step": 17490
|
|
},
|
|
{
|
|
"entropy": 5.595486259460449,
|
|
"epoch": 1.7363040889241763,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004703182086961659,
|
|
"loss": 5.1546,
|
|
"mean_token_accuracy": 0.1682416930794716,
|
|
"num_tokens": 38343110.0,
|
|
"step": 17495
|
|
},
|
|
{
|
|
"entropy": 5.6186693668365475,
|
|
"epoch": 1.7368003175863438,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004703006172753274,
|
|
"loss": 5.1382,
|
|
"mean_token_accuracy": 0.17911583930253983,
|
|
"num_tokens": 38353971.0,
|
|
"step": 17500
|
|
},
|
|
{
|
|
"entropy": 5.522997951507568,
|
|
"epoch": 1.7372965462485113,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00047028302101145467,
|
|
"loss": 5.0693,
|
|
"mean_token_accuracy": 0.178188294172287,
|
|
"num_tokens": 38365114.0,
|
|
"step": 17505
|
|
},
|
|
{
|
|
"entropy": 5.573307800292969,
|
|
"epoch": 1.737792774910679,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004702654199049836,
|
|
"loss": 5.0953,
|
|
"mean_token_accuracy": 0.17266631126403809,
|
|
"num_tokens": 38375784.0,
|
|
"step": 17510
|
|
},
|
|
{
|
|
"entropy": 5.538006830215454,
|
|
"epoch": 1.7382890035728464,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.000470247813956351,
|
|
"loss": 5.0821,
|
|
"mean_token_accuracy": 0.17605000883340835,
|
|
"num_tokens": 38386053.0,
|
|
"step": 17515
|
|
},
|
|
{
|
|
"entropy": 5.484797859191895,
|
|
"epoch": 1.738785232235014,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00047023020316599334,
|
|
"loss": 5.0833,
|
|
"mean_token_accuracy": 0.17451546639204024,
|
|
"num_tokens": 38396545.0,
|
|
"step": 17520
|
|
},
|
|
{
|
|
"entropy": 5.551498031616211,
|
|
"epoch": 1.7392814608971814,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.00047021258753434725,
|
|
"loss": 5.0629,
|
|
"mean_token_accuracy": 0.17322328239679335,
|
|
"num_tokens": 38406344.0,
|
|
"step": 17525
|
|
},
|
|
{
|
|
"entropy": 5.5825286388397215,
|
|
"epoch": 1.7397776895593489,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00047019496706184966,
|
|
"loss": 5.0563,
|
|
"mean_token_accuracy": 0.17969710230827332,
|
|
"num_tokens": 38416388.0,
|
|
"step": 17530
|
|
},
|
|
{
|
|
"entropy": 5.5995628356933596,
|
|
"epoch": 1.7402739182215163,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004701773417489375,
|
|
"loss": 5.1858,
|
|
"mean_token_accuracy": 0.16599820107221602,
|
|
"num_tokens": 38427608.0,
|
|
"step": 17535
|
|
},
|
|
{
|
|
"entropy": 5.542110347747803,
|
|
"epoch": 1.740770146883684,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.00047015971159604787,
|
|
"loss": 5.1031,
|
|
"mean_token_accuracy": 0.17624692171812056,
|
|
"num_tokens": 38437921.0,
|
|
"step": 17540
|
|
},
|
|
{
|
|
"entropy": 5.555644750595093,
|
|
"epoch": 1.7412663755458515,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.000470142076603618,
|
|
"loss": 5.1605,
|
|
"mean_token_accuracy": 0.16873769760131835,
|
|
"num_tokens": 38448767.0,
|
|
"step": 17545
|
|
},
|
|
{
|
|
"entropy": 5.589807844161987,
|
|
"epoch": 1.7417626042080192,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.00047012443677208496,
|
|
"loss": 5.2283,
|
|
"mean_token_accuracy": 0.16700267493724824,
|
|
"num_tokens": 38460052.0,
|
|
"step": 17550
|
|
},
|
|
{
|
|
"entropy": 5.576025199890137,
|
|
"epoch": 1.7422588328701867,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004701067921018864,
|
|
"loss": 5.0786,
|
|
"mean_token_accuracy": 0.17620374113321305,
|
|
"num_tokens": 38470177.0,
|
|
"step": 17555
|
|
},
|
|
{
|
|
"entropy": 5.590360116958618,
|
|
"epoch": 1.7427550615323542,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00047008914259345986,
|
|
"loss": 5.0911,
|
|
"mean_token_accuracy": 0.1702023595571518,
|
|
"num_tokens": 38481608.0,
|
|
"step": 17560
|
|
},
|
|
{
|
|
"entropy": 5.55975661277771,
|
|
"epoch": 1.7432512901945216,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.00047007148824724295,
|
|
"loss": 5.1581,
|
|
"mean_token_accuracy": 0.16911829859018326,
|
|
"num_tokens": 38492534.0,
|
|
"step": 17565
|
|
},
|
|
{
|
|
"entropy": 5.557606792449951,
|
|
"epoch": 1.743747518856689,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004700538290636734,
|
|
"loss": 5.1581,
|
|
"mean_token_accuracy": 0.17308571338653564,
|
|
"num_tokens": 38503629.0,
|
|
"step": 17570
|
|
},
|
|
{
|
|
"entropy": 5.496676015853882,
|
|
"epoch": 1.7442437475188566,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00047003616504318925,
|
|
"loss": 5.0418,
|
|
"mean_token_accuracy": 0.17432612031698227,
|
|
"num_tokens": 38514428.0,
|
|
"step": 17575
|
|
},
|
|
{
|
|
"entropy": 5.581231307983399,
|
|
"epoch": 1.744739976181024,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00047001849618622844,
|
|
"loss": 5.1344,
|
|
"mean_token_accuracy": 0.1703056275844574,
|
|
"num_tokens": 38525468.0,
|
|
"step": 17580
|
|
},
|
|
{
|
|
"entropy": 5.517770147323608,
|
|
"epoch": 1.7452362048431918,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00047000082249322916,
|
|
"loss": 5.1007,
|
|
"mean_token_accuracy": 0.17329324334859847,
|
|
"num_tokens": 38535095.0,
|
|
"step": 17585
|
|
},
|
|
{
|
|
"entropy": 5.579011344909668,
|
|
"epoch": 1.7457324335053592,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004699831439646297,
|
|
"loss": 5.0906,
|
|
"mean_token_accuracy": 0.17359646409749985,
|
|
"num_tokens": 38546867.0,
|
|
"step": 17590
|
|
},
|
|
{
|
|
"entropy": 5.495063209533692,
|
|
"epoch": 1.746228662167527,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004699654606008684,
|
|
"loss": 5.0017,
|
|
"mean_token_accuracy": 0.1814451649785042,
|
|
"num_tokens": 38557231.0,
|
|
"step": 17595
|
|
},
|
|
{
|
|
"entropy": 5.537030839920044,
|
|
"epoch": 1.7467248908296944,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004699477724023838,
|
|
"loss": 5.1224,
|
|
"mean_token_accuracy": 0.17315296828746796,
|
|
"num_tokens": 38568857.0,
|
|
"step": 17600
|
|
},
|
|
{
|
|
"entropy": 5.599961471557617,
|
|
"epoch": 1.7472211194918619,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004699300793696145,
|
|
"loss": 5.0976,
|
|
"mean_token_accuracy": 0.17201314270496368,
|
|
"num_tokens": 38579177.0,
|
|
"step": 17605
|
|
},
|
|
{
|
|
"entropy": 5.570987796783447,
|
|
"epoch": 1.7477173481540293,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004699123815029993,
|
|
"loss": 5.0079,
|
|
"mean_token_accuracy": 0.1800644278526306,
|
|
"num_tokens": 38588683.0,
|
|
"step": 17610
|
|
},
|
|
{
|
|
"entropy": 5.527664422988892,
|
|
"epoch": 1.7482135768161968,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00046989467880297704,
|
|
"loss": 5.0854,
|
|
"mean_token_accuracy": 0.1740689605474472,
|
|
"num_tokens": 38599636.0,
|
|
"step": 17615
|
|
},
|
|
{
|
|
"entropy": 5.626832914352417,
|
|
"epoch": 1.7487098054783643,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00046987697126998673,
|
|
"loss": 5.1991,
|
|
"mean_token_accuracy": 0.16754450649023056,
|
|
"num_tokens": 38609360.0,
|
|
"step": 17620
|
|
},
|
|
{
|
|
"entropy": 5.58344874382019,
|
|
"epoch": 1.749206034140532,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004698592589044674,
|
|
"loss": 5.1239,
|
|
"mean_token_accuracy": 0.17207718640565872,
|
|
"num_tokens": 38620996.0,
|
|
"step": 17625
|
|
},
|
|
{
|
|
"entropy": 5.572943210601807,
|
|
"epoch": 1.7497022628026995,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00046984154170685833,
|
|
"loss": 5.2215,
|
|
"mean_token_accuracy": 0.1728046104311943,
|
|
"num_tokens": 38632935.0,
|
|
"step": 17630
|
|
},
|
|
{
|
|
"entropy": 5.658014822006225,
|
|
"epoch": 1.7501984914648672,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004698238196775989,
|
|
"loss": 5.211,
|
|
"mean_token_accuracy": 0.16946618705987931,
|
|
"num_tokens": 38644299.0,
|
|
"step": 17635
|
|
},
|
|
{
|
|
"entropy": 5.589119291305542,
|
|
"epoch": 1.7506947201270346,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.00046980609281712857,
|
|
"loss": 5.1507,
|
|
"mean_token_accuracy": 0.1749320074915886,
|
|
"num_tokens": 38654970.0,
|
|
"step": 17640
|
|
},
|
|
{
|
|
"entropy": 5.580189180374146,
|
|
"epoch": 1.7511909487892021,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004697883611258868,
|
|
"loss": 5.1893,
|
|
"mean_token_accuracy": 0.1741221010684967,
|
|
"num_tokens": 38666302.0,
|
|
"step": 17645
|
|
},
|
|
{
|
|
"entropy": 5.562500905990601,
|
|
"epoch": 1.7516871774513696,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004697706246043136,
|
|
"loss": 5.1081,
|
|
"mean_token_accuracy": 0.17513372302055358,
|
|
"num_tokens": 38678346.0,
|
|
"step": 17650
|
|
},
|
|
{
|
|
"entropy": 5.5413085460662845,
|
|
"epoch": 1.752183406113537,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00046975288325284845,
|
|
"loss": 5.0493,
|
|
"mean_token_accuracy": 0.17577243149280547,
|
|
"num_tokens": 38688242.0,
|
|
"step": 17655
|
|
},
|
|
{
|
|
"entropy": 5.630189752578735,
|
|
"epoch": 1.7526796347757045,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004697351370719315,
|
|
"loss": 5.2204,
|
|
"mean_token_accuracy": 0.16486080139875411,
|
|
"num_tokens": 38698756.0,
|
|
"step": 17660
|
|
},
|
|
{
|
|
"entropy": 5.596133756637573,
|
|
"epoch": 1.753175863437872,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004697173860620027,
|
|
"loss": 5.19,
|
|
"mean_token_accuracy": 0.1659785345196724,
|
|
"num_tokens": 38710410.0,
|
|
"step": 17665
|
|
},
|
|
{
|
|
"entropy": 5.63321442604065,
|
|
"epoch": 1.7536720921000397,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004696996302235024,
|
|
"loss": 5.136,
|
|
"mean_token_accuracy": 0.16877845376729966,
|
|
"num_tokens": 38721917.0,
|
|
"step": 17670
|
|
},
|
|
{
|
|
"entropy": 5.595292472839356,
|
|
"epoch": 1.7541683207622072,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.00046968186955687074,
|
|
"loss": 5.1582,
|
|
"mean_token_accuracy": 0.17791620194911956,
|
|
"num_tokens": 38733085.0,
|
|
"step": 17675
|
|
},
|
|
{
|
|
"entropy": 5.528179788589478,
|
|
"epoch": 1.7546645494243749,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004696641040625483,
|
|
"loss": 5.18,
|
|
"mean_token_accuracy": 0.16956325024366378,
|
|
"num_tokens": 38744785.0,
|
|
"step": 17680
|
|
},
|
|
{
|
|
"entropy": 5.569801473617554,
|
|
"epoch": 1.7551607780865424,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.00046964633374097544,
|
|
"loss": 5.1533,
|
|
"mean_token_accuracy": 0.1736989811062813,
|
|
"num_tokens": 38755626.0,
|
|
"step": 17685
|
|
},
|
|
{
|
|
"entropy": 5.615735197067261,
|
|
"epoch": 1.7556570067487098,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00046962855859259306,
|
|
"loss": 5.0364,
|
|
"mean_token_accuracy": 0.1725809618830681,
|
|
"num_tokens": 38766360.0,
|
|
"step": 17690
|
|
},
|
|
{
|
|
"entropy": 5.581758260726929,
|
|
"epoch": 1.7561532354108773,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00046961077861784167,
|
|
"loss": 5.1084,
|
|
"mean_token_accuracy": 0.1726755529642105,
|
|
"num_tokens": 38776763.0,
|
|
"step": 17695
|
|
},
|
|
{
|
|
"entropy": 5.521144676208496,
|
|
"epoch": 1.7566494640730448,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004695929938171624,
|
|
"loss": 5.1758,
|
|
"mean_token_accuracy": 0.17600510865449906,
|
|
"num_tokens": 38787664.0,
|
|
"step": 17700
|
|
},
|
|
{
|
|
"entropy": 5.577087640762329,
|
|
"epoch": 1.7571456927352123,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004695752041909962,
|
|
"loss": 5.1017,
|
|
"mean_token_accuracy": 0.1711129814386368,
|
|
"num_tokens": 38798018.0,
|
|
"step": 17705
|
|
},
|
|
{
|
|
"entropy": 5.573191833496094,
|
|
"epoch": 1.75764192139738,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004695574097397842,
|
|
"loss": 5.0615,
|
|
"mean_token_accuracy": 0.17492159307003022,
|
|
"num_tokens": 38810381.0,
|
|
"step": 17710
|
|
},
|
|
{
|
|
"entropy": 5.499499940872193,
|
|
"epoch": 1.7581381500595474,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00046953961046396767,
|
|
"loss": 5.0662,
|
|
"mean_token_accuracy": 0.18041797429323198,
|
|
"num_tokens": 38821042.0,
|
|
"step": 17715
|
|
},
|
|
{
|
|
"entropy": 5.508300542831421,
|
|
"epoch": 1.7586343787217151,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00046952180636398793,
|
|
"loss": 5.0218,
|
|
"mean_token_accuracy": 0.17752404361963273,
|
|
"num_tokens": 38830890.0,
|
|
"step": 17720
|
|
},
|
|
{
|
|
"entropy": 5.5899986743927,
|
|
"epoch": 1.7591306073838826,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004695039974402866,
|
|
"loss": 5.066,
|
|
"mean_token_accuracy": 0.1826263725757599,
|
|
"num_tokens": 38842648.0,
|
|
"step": 17725
|
|
},
|
|
{
|
|
"entropy": 5.554860401153564,
|
|
"epoch": 1.75962683604605,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.00046948618369330533,
|
|
"loss": 5.0192,
|
|
"mean_token_accuracy": 0.1832275778055191,
|
|
"num_tokens": 38852740.0,
|
|
"step": 17730
|
|
},
|
|
{
|
|
"entropy": 5.5347191333770756,
|
|
"epoch": 1.7601230647082176,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00046946836512348566,
|
|
"loss": 5.144,
|
|
"mean_token_accuracy": 0.1655426040291786,
|
|
"num_tokens": 38863371.0,
|
|
"step": 17735
|
|
},
|
|
{
|
|
"entropy": 5.598482465744018,
|
|
"epoch": 1.760619293370385,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00046945054173126965,
|
|
"loss": 5.1268,
|
|
"mean_token_accuracy": 0.1708410531282425,
|
|
"num_tokens": 38873893.0,
|
|
"step": 17740
|
|
},
|
|
{
|
|
"entropy": 5.578781270980835,
|
|
"epoch": 1.7611155220325525,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00046943271351709923,
|
|
"loss": 5.1665,
|
|
"mean_token_accuracy": 0.1677718788385391,
|
|
"num_tokens": 38884778.0,
|
|
"step": 17745
|
|
},
|
|
{
|
|
"entropy": 5.510950374603271,
|
|
"epoch": 1.76161175069472,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004694148804814164,
|
|
"loss": 5.1125,
|
|
"mean_token_accuracy": 0.16857096701860427,
|
|
"num_tokens": 38896011.0,
|
|
"step": 17750
|
|
},
|
|
{
|
|
"entropy": 5.59821457862854,
|
|
"epoch": 1.7621079793568877,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004693970426246635,
|
|
"loss": 5.1468,
|
|
"mean_token_accuracy": 0.16961099356412887,
|
|
"num_tokens": 38907686.0,
|
|
"step": 17755
|
|
},
|
|
{
|
|
"entropy": 5.5256627082824705,
|
|
"epoch": 1.7626042080190552,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.00046937919994728287,
|
|
"loss": 5.1085,
|
|
"mean_token_accuracy": 0.1772584065794945,
|
|
"num_tokens": 38919180.0,
|
|
"step": 17760
|
|
},
|
|
{
|
|
"entropy": 5.549013710021972,
|
|
"epoch": 1.7631004366812228,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004693613524497168,
|
|
"loss": 5.09,
|
|
"mean_token_accuracy": 0.17301513105630875,
|
|
"num_tokens": 38929600.0,
|
|
"step": 17765
|
|
},
|
|
{
|
|
"entropy": 5.5715728282928465,
|
|
"epoch": 1.7635966653433903,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00046934350013240814,
|
|
"loss": 5.0393,
|
|
"mean_token_accuracy": 0.18329585194587708,
|
|
"num_tokens": 38940404.0,
|
|
"step": 17770
|
|
},
|
|
{
|
|
"entropy": 5.54627799987793,
|
|
"epoch": 1.7640928940055578,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004693256429957994,
|
|
"loss": 5.095,
|
|
"mean_token_accuracy": 0.17642540484666824,
|
|
"num_tokens": 38951929.0,
|
|
"step": 17775
|
|
},
|
|
{
|
|
"entropy": 5.516851282119751,
|
|
"epoch": 1.7645891226677253,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004693077810403335,
|
|
"loss": 5.0842,
|
|
"mean_token_accuracy": 0.175152924656868,
|
|
"num_tokens": 38961954.0,
|
|
"step": 17780
|
|
},
|
|
{
|
|
"entropy": 5.495822095870972,
|
|
"epoch": 1.7650853513298927,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00046928991426645325,
|
|
"loss": 5.0658,
|
|
"mean_token_accuracy": 0.17466057687997819,
|
|
"num_tokens": 38970974.0,
|
|
"step": 17785
|
|
},
|
|
{
|
|
"entropy": 5.581322765350341,
|
|
"epoch": 1.7655815799920602,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00046927204267460177,
|
|
"loss": 5.1415,
|
|
"mean_token_accuracy": 0.17215966135263444,
|
|
"num_tokens": 38982481.0,
|
|
"step": 17790
|
|
},
|
|
{
|
|
"entropy": 5.634880399703979,
|
|
"epoch": 1.766077808654228,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00046925416626522235,
|
|
"loss": 5.1025,
|
|
"mean_token_accuracy": 0.17899129390716553,
|
|
"num_tokens": 38993279.0,
|
|
"step": 17795
|
|
},
|
|
{
|
|
"entropy": 5.540242004394531,
|
|
"epoch": 1.7665740373163954,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004692362850387581,
|
|
"loss": 5.0784,
|
|
"mean_token_accuracy": 0.18178649246692657,
|
|
"num_tokens": 39003748.0,
|
|
"step": 17800
|
|
},
|
|
{
|
|
"entropy": 5.497012138366699,
|
|
"epoch": 1.7670702659785629,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00046921839899565263,
|
|
"loss": 5.1051,
|
|
"mean_token_accuracy": 0.16572619527578353,
|
|
"num_tokens": 39014902.0,
|
|
"step": 17805
|
|
},
|
|
{
|
|
"entropy": 5.602819156646729,
|
|
"epoch": 1.7675664946407306,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004692005081363493,
|
|
"loss": 5.1662,
|
|
"mean_token_accuracy": 0.1694572687149048,
|
|
"num_tokens": 39026484.0,
|
|
"step": 17810
|
|
},
|
|
{
|
|
"entropy": 5.564551830291748,
|
|
"epoch": 1.768062723302898,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.00046918261246129176,
|
|
"loss": 5.1538,
|
|
"mean_token_accuracy": 0.17185938358306885,
|
|
"num_tokens": 39036268.0,
|
|
"step": 17815
|
|
},
|
|
{
|
|
"entropy": 5.598098278045654,
|
|
"epoch": 1.7685589519650655,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.000469164711970924,
|
|
"loss": 5.2003,
|
|
"mean_token_accuracy": 0.17065991163253785,
|
|
"num_tokens": 39049092.0,
|
|
"step": 17820
|
|
},
|
|
{
|
|
"entropy": 5.625868272781372,
|
|
"epoch": 1.769055180627233,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004691468066656896,
|
|
"loss": 5.1554,
|
|
"mean_token_accuracy": 0.17015611827373506,
|
|
"num_tokens": 39059255.0,
|
|
"step": 17825
|
|
},
|
|
{
|
|
"entropy": 5.516210508346558,
|
|
"epoch": 1.7695514092894005,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.00046912889654603286,
|
|
"loss": 5.053,
|
|
"mean_token_accuracy": 0.1774064302444458,
|
|
"num_tokens": 39069913.0,
|
|
"step": 17830
|
|
},
|
|
{
|
|
"entropy": 5.541619348526001,
|
|
"epoch": 1.770047637951568,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004691109816123977,
|
|
"loss": 5.0727,
|
|
"mean_token_accuracy": 0.17889440953731536,
|
|
"num_tokens": 39080666.0,
|
|
"step": 17835
|
|
},
|
|
{
|
|
"entropy": 5.591982507705689,
|
|
"epoch": 1.7705438666137356,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004690930618652286,
|
|
"loss": 5.1424,
|
|
"mean_token_accuracy": 0.17367461025714875,
|
|
"num_tokens": 39091562.0,
|
|
"step": 17840
|
|
},
|
|
{
|
|
"entropy": 5.603212833404541,
|
|
"epoch": 1.7710400952759031,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00046907513730496975,
|
|
"loss": 5.2189,
|
|
"mean_token_accuracy": 0.16420638412237168,
|
|
"num_tokens": 39102567.0,
|
|
"step": 17845
|
|
},
|
|
{
|
|
"entropy": 5.631757402420044,
|
|
"epoch": 1.7715363239380708,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004690572079320657,
|
|
"loss": 5.105,
|
|
"mean_token_accuracy": 0.17596133500337602,
|
|
"num_tokens": 39113260.0,
|
|
"step": 17850
|
|
},
|
|
{
|
|
"entropy": 5.5827446460723875,
|
|
"epoch": 1.7720325526002383,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00046903927374696106,
|
|
"loss": 5.1448,
|
|
"mean_token_accuracy": 0.1742891326546669,
|
|
"num_tokens": 39125790.0,
|
|
"step": 17855
|
|
},
|
|
{
|
|
"entropy": 5.5558558940887455,
|
|
"epoch": 1.7725287812624058,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004690213347501005,
|
|
"loss": 5.1849,
|
|
"mean_token_accuracy": 0.1703210711479187,
|
|
"num_tokens": 39137220.0,
|
|
"step": 17860
|
|
},
|
|
{
|
|
"entropy": 5.560394239425659,
|
|
"epoch": 1.7730250099245732,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004690033909419289,
|
|
"loss": 5.0677,
|
|
"mean_token_accuracy": 0.17490962743759156,
|
|
"num_tokens": 39146362.0,
|
|
"step": 17865
|
|
},
|
|
{
|
|
"entropy": 5.616075277328491,
|
|
"epoch": 1.7735212385867407,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00046898544232289126,
|
|
"loss": 5.1466,
|
|
"mean_token_accuracy": 0.16869162917137145,
|
|
"num_tokens": 39156822.0,
|
|
"step": 17870
|
|
},
|
|
{
|
|
"entropy": 5.626028823852539,
|
|
"epoch": 1.7740174672489082,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.00046896748889343267,
|
|
"loss": 5.1299,
|
|
"mean_token_accuracy": 0.16527492702007293,
|
|
"num_tokens": 39166693.0,
|
|
"step": 17875
|
|
},
|
|
{
|
|
"entropy": 5.496959972381592,
|
|
"epoch": 1.7745136959110757,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00046894953065399836,
|
|
"loss": 5.0989,
|
|
"mean_token_accuracy": 0.17684730589389802,
|
|
"num_tokens": 39176889.0,
|
|
"step": 17880
|
|
},
|
|
{
|
|
"entropy": 5.560200452804565,
|
|
"epoch": 1.7750099245732434,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00046893156760503357,
|
|
"loss": 5.099,
|
|
"mean_token_accuracy": 0.18187216073274612,
|
|
"num_tokens": 39188077.0,
|
|
"step": 17885
|
|
},
|
|
{
|
|
"entropy": 5.536591482162476,
|
|
"epoch": 1.7755061532354108,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004689135997469838,
|
|
"loss": 5.0894,
|
|
"mean_token_accuracy": 0.16988267600536347,
|
|
"num_tokens": 39198182.0,
|
|
"step": 17890
|
|
},
|
|
{
|
|
"entropy": 5.625663089752197,
|
|
"epoch": 1.7760023818975785,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004688956270802945,
|
|
"loss": 5.0667,
|
|
"mean_token_accuracy": 0.1798384740948677,
|
|
"num_tokens": 39208801.0,
|
|
"step": 17895
|
|
},
|
|
{
|
|
"entropy": 5.457943677902222,
|
|
"epoch": 1.776498610559746,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004688776496054117,
|
|
"loss": 4.9411,
|
|
"mean_token_accuracy": 0.18785025030374528,
|
|
"num_tokens": 39220658.0,
|
|
"step": 17900
|
|
},
|
|
{
|
|
"entropy": 5.540046167373657,
|
|
"epoch": 1.7769948392219135,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00046885966732278077,
|
|
"loss": 5.1807,
|
|
"mean_token_accuracy": 0.16862889379262924,
|
|
"num_tokens": 39231987.0,
|
|
"step": 17905
|
|
},
|
|
{
|
|
"entropy": 5.576083469390869,
|
|
"epoch": 1.777491067884081,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00046884168023284787,
|
|
"loss": 5.066,
|
|
"mean_token_accuracy": 0.1771724745631218,
|
|
"num_tokens": 39242797.0,
|
|
"step": 17910
|
|
},
|
|
{
|
|
"entropy": 5.576232814788819,
|
|
"epoch": 1.7779872965462484,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00046882368833605894,
|
|
"loss": 5.1202,
|
|
"mean_token_accuracy": 0.17469854950904845,
|
|
"num_tokens": 39253621.0,
|
|
"step": 17915
|
|
},
|
|
{
|
|
"entropy": 5.52582483291626,
|
|
"epoch": 1.778483525208416,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00046880569163286023,
|
|
"loss": 5.1398,
|
|
"mean_token_accuracy": 0.16921603828668594,
|
|
"num_tokens": 39264126.0,
|
|
"step": 17920
|
|
},
|
|
{
|
|
"entropy": 5.563271617889404,
|
|
"epoch": 1.7789797538705836,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00046878769012369807,
|
|
"loss": 5.0743,
|
|
"mean_token_accuracy": 0.180909962952137,
|
|
"num_tokens": 39275118.0,
|
|
"step": 17925
|
|
},
|
|
{
|
|
"entropy": 5.562721061706543,
|
|
"epoch": 1.779475982532751,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00046876968380901864,
|
|
"loss": 5.0942,
|
|
"mean_token_accuracy": 0.17614645957946778,
|
|
"num_tokens": 39287237.0,
|
|
"step": 17930
|
|
},
|
|
{
|
|
"entropy": 5.624432182312011,
|
|
"epoch": 1.7799722111949188,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00046875167268926865,
|
|
"loss": 5.1524,
|
|
"mean_token_accuracy": 0.17139471918344498,
|
|
"num_tokens": 39296995.0,
|
|
"step": 17935
|
|
},
|
|
{
|
|
"entropy": 5.53447003364563,
|
|
"epoch": 1.7804684398570862,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004687336567648947,
|
|
"loss": 5.0538,
|
|
"mean_token_accuracy": 0.17358405739068986,
|
|
"num_tokens": 39305980.0,
|
|
"step": 17940
|
|
},
|
|
{
|
|
"entropy": 5.584849643707275,
|
|
"epoch": 1.7809646685192537,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00046871563603634347,
|
|
"loss": 5.1741,
|
|
"mean_token_accuracy": 0.16430944502353667,
|
|
"num_tokens": 39316494.0,
|
|
"step": 17945
|
|
},
|
|
{
|
|
"entropy": 5.581762599945068,
|
|
"epoch": 1.7814608971814212,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004686976105040619,
|
|
"loss": 5.147,
|
|
"mean_token_accuracy": 0.17480543851852418,
|
|
"num_tokens": 39327699.0,
|
|
"step": 17950
|
|
},
|
|
{
|
|
"entropy": 5.584734869003296,
|
|
"epoch": 1.7819571258435887,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004686795801684969,
|
|
"loss": 5.1629,
|
|
"mean_token_accuracy": 0.16990833282470702,
|
|
"num_tokens": 39338749.0,
|
|
"step": 17955
|
|
},
|
|
{
|
|
"entropy": 5.569218683242798,
|
|
"epoch": 1.7824533545057561,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004686615450300958,
|
|
"loss": 5.1362,
|
|
"mean_token_accuracy": 0.17690266221761702,
|
|
"num_tokens": 39349747.0,
|
|
"step": 17960
|
|
},
|
|
{
|
|
"entropy": 5.508942604064941,
|
|
"epoch": 1.7829495831679236,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004686435050893056,
|
|
"loss": 4.9987,
|
|
"mean_token_accuracy": 0.18178412765264512,
|
|
"num_tokens": 39360068.0,
|
|
"step": 17965
|
|
},
|
|
{
|
|
"entropy": 5.502421951293945,
|
|
"epoch": 1.7834458118300913,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00046862546034657376,
|
|
"loss": 5.0282,
|
|
"mean_token_accuracy": 0.1788963109254837,
|
|
"num_tokens": 39369651.0,
|
|
"step": 17970
|
|
},
|
|
{
|
|
"entropy": 5.586280727386475,
|
|
"epoch": 1.7839420404922588,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004686074108023477,
|
|
"loss": 5.2313,
|
|
"mean_token_accuracy": 0.1694331258535385,
|
|
"num_tokens": 39381354.0,
|
|
"step": 17975
|
|
},
|
|
{
|
|
"entropy": 5.585847520828247,
|
|
"epoch": 1.7844382691544265,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00046858935645707506,
|
|
"loss": 5.083,
|
|
"mean_token_accuracy": 0.17145538777112962,
|
|
"num_tokens": 39391793.0,
|
|
"step": 17980
|
|
},
|
|
{
|
|
"entropy": 5.527411937713623,
|
|
"epoch": 1.784934497816594,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004685712973112035,
|
|
"loss": 5.0998,
|
|
"mean_token_accuracy": 0.17774528712034227,
|
|
"num_tokens": 39402194.0,
|
|
"step": 17985
|
|
},
|
|
{
|
|
"entropy": 5.532209873199463,
|
|
"epoch": 1.7854307264787614,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004685532333651809,
|
|
"loss": 5.1059,
|
|
"mean_token_accuracy": 0.17310286313295364,
|
|
"num_tokens": 39413193.0,
|
|
"step": 17990
|
|
},
|
|
{
|
|
"entropy": 5.549567317962646,
|
|
"epoch": 1.785926955140929,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00046853516461945523,
|
|
"loss": 5.0774,
|
|
"mean_token_accuracy": 0.18055932968854904,
|
|
"num_tokens": 39423072.0,
|
|
"step": 17995
|
|
},
|
|
{
|
|
"entropy": 5.604977178573608,
|
|
"epoch": 1.7864231838030964,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00046851709107447446,
|
|
"loss": 5.1968,
|
|
"mean_token_accuracy": 0.1684126600623131,
|
|
"num_tokens": 39435088.0,
|
|
"step": 18000
|
|
},
|
|
{
|
|
"epoch": 1.7864231838030964,
|
|
"eval_entropy": 5.376621442555985,
|
|
"eval_loss": 5.217236042022705,
|
|
"eval_mean_token_accuracy": 0.17458677464106157,
|
|
"eval_num_tokens": 39435088.0,
|
|
"eval_runtime": 20.473,
|
|
"eval_samples_per_second": 1644.557,
|
|
"eval_steps_per_second": 205.588,
|
|
"step": 18000
|
|
},
|
|
{
|
|
"entropy": 5.516323137283325,
|
|
"epoch": 1.7869194124652639,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004684990127306868,
|
|
"loss": 5.0587,
|
|
"mean_token_accuracy": 0.1767568454146385,
|
|
"num_tokens": 39446129.0,
|
|
"step": 18005
|
|
},
|
|
{
|
|
"entropy": 5.520525789260864,
|
|
"epoch": 1.7874156411274316,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00046848092958854065,
|
|
"loss": 5.011,
|
|
"mean_token_accuracy": 0.189851376414299,
|
|
"num_tokens": 39458127.0,
|
|
"step": 18010
|
|
},
|
|
{
|
|
"entropy": 5.557810926437378,
|
|
"epoch": 1.787911869789599,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004684628416484843,
|
|
"loss": 5.0693,
|
|
"mean_token_accuracy": 0.17873586267232894,
|
|
"num_tokens": 39468204.0,
|
|
"step": 18015
|
|
},
|
|
{
|
|
"entropy": 5.5416114807128904,
|
|
"epoch": 1.7884080984517667,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004684447489109663,
|
|
"loss": 5.1392,
|
|
"mean_token_accuracy": 0.17283686697483064,
|
|
"num_tokens": 39479114.0,
|
|
"step": 18020
|
|
},
|
|
{
|
|
"entropy": 5.547650241851807,
|
|
"epoch": 1.7889043271139342,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00046842665137643546,
|
|
"loss": 5.1128,
|
|
"mean_token_accuracy": 0.1774169459939003,
|
|
"num_tokens": 39489691.0,
|
|
"step": 18025
|
|
},
|
|
{
|
|
"entropy": 5.612976789474487,
|
|
"epoch": 1.7894005557761017,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00046840854904534046,
|
|
"loss": 5.2269,
|
|
"mean_token_accuracy": 0.16386041939258575,
|
|
"num_tokens": 39501879.0,
|
|
"step": 18030
|
|
},
|
|
{
|
|
"entropy": 5.608426809310913,
|
|
"epoch": 1.7898967844382692,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004683904419181302,
|
|
"loss": 5.1345,
|
|
"mean_token_accuracy": 0.17699406296014786,
|
|
"num_tokens": 39513413.0,
|
|
"step": 18035
|
|
},
|
|
{
|
|
"entropy": 5.554781579971314,
|
|
"epoch": 1.7903930131004366,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00046837232999525366,
|
|
"loss": 5.0795,
|
|
"mean_token_accuracy": 0.17090435475111007,
|
|
"num_tokens": 39522719.0,
|
|
"step": 18040
|
|
},
|
|
{
|
|
"entropy": 5.556888055801392,
|
|
"epoch": 1.7908892417626041,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00046835421327716,
|
|
"loss": 5.1405,
|
|
"mean_token_accuracy": 0.1730068013072014,
|
|
"num_tokens": 39532463.0,
|
|
"step": 18045
|
|
},
|
|
{
|
|
"entropy": 5.5412859439849855,
|
|
"epoch": 1.7913854704247716,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004683360917642986,
|
|
"loss": 5.0943,
|
|
"mean_token_accuracy": 0.17171480357646943,
|
|
"num_tokens": 39543005.0,
|
|
"step": 18050
|
|
},
|
|
{
|
|
"entropy": 5.601563215255737,
|
|
"epoch": 1.7918816990869393,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00046831796545711865,
|
|
"loss": 5.164,
|
|
"mean_token_accuracy": 0.16778888255357743,
|
|
"num_tokens": 39553468.0,
|
|
"step": 18055
|
|
},
|
|
{
|
|
"entropy": 5.67397928237915,
|
|
"epoch": 1.7923779277491068,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00046829983435606973,
|
|
"loss": 5.2231,
|
|
"mean_token_accuracy": 0.17129427939653397,
|
|
"num_tokens": 39563539.0,
|
|
"step": 18060
|
|
},
|
|
{
|
|
"entropy": 5.592680835723877,
|
|
"epoch": 1.7928741564112745,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004682816984616014,
|
|
"loss": 5.1576,
|
|
"mean_token_accuracy": 0.17221810519695283,
|
|
"num_tokens": 39574835.0,
|
|
"step": 18065
|
|
},
|
|
{
|
|
"entropy": 5.569009590148926,
|
|
"epoch": 1.793370385073442,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.00046826355777416346,
|
|
"loss": 5.1046,
|
|
"mean_token_accuracy": 0.17700168639421462,
|
|
"num_tokens": 39586021.0,
|
|
"step": 18070
|
|
},
|
|
{
|
|
"entropy": 5.585173940658569,
|
|
"epoch": 1.7938666137356094,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00046824541229420583,
|
|
"loss": 5.044,
|
|
"mean_token_accuracy": 0.17448382079601288,
|
|
"num_tokens": 39596333.0,
|
|
"step": 18075
|
|
},
|
|
{
|
|
"entropy": 5.534476661682129,
|
|
"epoch": 1.7943628423977769,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00046822726202217825,
|
|
"loss": 5.0682,
|
|
"mean_token_accuracy": 0.17738160490989685,
|
|
"num_tokens": 39607553.0,
|
|
"step": 18080
|
|
},
|
|
{
|
|
"entropy": 5.530224609375,
|
|
"epoch": 1.7948590710599444,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.000468209106958531,
|
|
"loss": 5.1664,
|
|
"mean_token_accuracy": 0.16989864856004716,
|
|
"num_tokens": 39619700.0,
|
|
"step": 18085
|
|
},
|
|
{
|
|
"entropy": 5.542677688598633,
|
|
"epoch": 1.7953552997221118,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004681909471037142,
|
|
"loss": 5.0765,
|
|
"mean_token_accuracy": 0.18002297282218932,
|
|
"num_tokens": 39630623.0,
|
|
"step": 18090
|
|
},
|
|
{
|
|
"entropy": 5.554100227355957,
|
|
"epoch": 1.7958515283842795,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00046817278245817815,
|
|
"loss": 5.0711,
|
|
"mean_token_accuracy": 0.18067716807127,
|
|
"num_tokens": 39641089.0,
|
|
"step": 18095
|
|
},
|
|
{
|
|
"entropy": 5.530361700057983,
|
|
"epoch": 1.796347757046447,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004681546130223735,
|
|
"loss": 5.1262,
|
|
"mean_token_accuracy": 0.1715655505657196,
|
|
"num_tokens": 39652381.0,
|
|
"step": 18100
|
|
},
|
|
{
|
|
"entropy": 5.532079219818115,
|
|
"epoch": 1.7968439857086145,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004681364387967505,
|
|
"loss": 5.0607,
|
|
"mean_token_accuracy": 0.1748769223690033,
|
|
"num_tokens": 39662536.0,
|
|
"step": 18105
|
|
},
|
|
{
|
|
"entropy": 5.543280553817749,
|
|
"epoch": 1.7973402143707822,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004681182597817601,
|
|
"loss": 5.1066,
|
|
"mean_token_accuracy": 0.17961354702711105,
|
|
"num_tokens": 39673140.0,
|
|
"step": 18110
|
|
},
|
|
{
|
|
"entropy": 5.520239210128784,
|
|
"epoch": 1.7978364430329496,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004681000759778529,
|
|
"loss": 5.0997,
|
|
"mean_token_accuracy": 0.1677226424217224,
|
|
"num_tokens": 39683843.0,
|
|
"step": 18115
|
|
},
|
|
{
|
|
"entropy": 5.520877456665039,
|
|
"epoch": 1.7983326716951171,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004680818873854799,
|
|
"loss": 5.0518,
|
|
"mean_token_accuracy": 0.17436048984527588,
|
|
"num_tokens": 39694178.0,
|
|
"step": 18120
|
|
},
|
|
{
|
|
"entropy": 5.472235441207886,
|
|
"epoch": 1.7988289003572846,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004680636940050922,
|
|
"loss": 5.0536,
|
|
"mean_token_accuracy": 0.17695568650960922,
|
|
"num_tokens": 39704818.0,
|
|
"step": 18125
|
|
},
|
|
{
|
|
"entropy": 5.556345510482788,
|
|
"epoch": 1.799325129019452,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.000468045495837141,
|
|
"loss": 5.0663,
|
|
"mean_token_accuracy": 0.1716505452990532,
|
|
"num_tokens": 39715599.0,
|
|
"step": 18130
|
|
},
|
|
{
|
|
"entropy": 5.579806804656982,
|
|
"epoch": 1.7998213576816195,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00046802729288207735,
|
|
"loss": 5.0814,
|
|
"mean_token_accuracy": 0.17834774702787398,
|
|
"num_tokens": 39725736.0,
|
|
"step": 18135
|
|
},
|
|
{
|
|
"entropy": 5.5522219181060795,
|
|
"epoch": 1.8003175863437872,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00046800908514035285,
|
|
"loss": 5.1251,
|
|
"mean_token_accuracy": 0.17335045337677002,
|
|
"num_tokens": 39735736.0,
|
|
"step": 18140
|
|
},
|
|
{
|
|
"entropy": 5.561379528045654,
|
|
"epoch": 1.8008138150059547,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00046799087261241884,
|
|
"loss": 5.1614,
|
|
"mean_token_accuracy": 0.16988508850336076,
|
|
"num_tokens": 39747443.0,
|
|
"step": 18145
|
|
},
|
|
{
|
|
"entropy": 5.578796148300171,
|
|
"epoch": 1.8013100436681224,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004679726552987271,
|
|
"loss": 5.0945,
|
|
"mean_token_accuracy": 0.17009207457304001,
|
|
"num_tokens": 39758128.0,
|
|
"step": 18150
|
|
},
|
|
{
|
|
"entropy": 5.557246732711792,
|
|
"epoch": 1.80180627233029,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004679544331997294,
|
|
"loss": 5.0297,
|
|
"mean_token_accuracy": 0.18322060257196426,
|
|
"num_tokens": 39769153.0,
|
|
"step": 18155
|
|
},
|
|
{
|
|
"entropy": 5.56773009300232,
|
|
"epoch": 1.8023025009924574,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00046793620631587743,
|
|
"loss": 5.1124,
|
|
"mean_token_accuracy": 0.16667832881212236,
|
|
"num_tokens": 39779666.0,
|
|
"step": 18160
|
|
},
|
|
{
|
|
"entropy": 5.566453886032105,
|
|
"epoch": 1.8027987296546248,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00046791797464762334,
|
|
"loss": 5.1462,
|
|
"mean_token_accuracy": 0.16968514919281005,
|
|
"num_tokens": 39790329.0,
|
|
"step": 18165
|
|
},
|
|
{
|
|
"entropy": 5.615738344192505,
|
|
"epoch": 1.8032949583167923,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.00046789973819541915,
|
|
"loss": 5.1297,
|
|
"mean_token_accuracy": 0.17371605485677719,
|
|
"num_tokens": 39801996.0,
|
|
"step": 18170
|
|
},
|
|
{
|
|
"entropy": 5.625317525863648,
|
|
"epoch": 1.8037911869789598,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004678814969597171,
|
|
"loss": 5.1072,
|
|
"mean_token_accuracy": 0.17198027819395065,
|
|
"num_tokens": 39814064.0,
|
|
"step": 18175
|
|
},
|
|
{
|
|
"entropy": 5.553517389297485,
|
|
"epoch": 1.8042874156411273,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004678632509409696,
|
|
"loss": 5.0665,
|
|
"mean_token_accuracy": 0.1776961162686348,
|
|
"num_tokens": 39825369.0,
|
|
"step": 18180
|
|
},
|
|
{
|
|
"entropy": 5.510013246536255,
|
|
"epoch": 1.804783644303295,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000467845000139629,
|
|
"loss": 5.149,
|
|
"mean_token_accuracy": 0.17642490863800048,
|
|
"num_tokens": 39835218.0,
|
|
"step": 18185
|
|
},
|
|
{
|
|
"entropy": 5.5924444675445555,
|
|
"epoch": 1.8052798729654624,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000467826744556148,
|
|
"loss": 5.1726,
|
|
"mean_token_accuracy": 0.16996136754751207,
|
|
"num_tokens": 39844706.0,
|
|
"step": 18190
|
|
},
|
|
{
|
|
"entropy": 5.506793737411499,
|
|
"epoch": 1.8057761016276301,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004678084841909792,
|
|
"loss": 5.0975,
|
|
"mean_token_accuracy": 0.17927393168210984,
|
|
"num_tokens": 39856348.0,
|
|
"step": 18195
|
|
},
|
|
{
|
|
"entropy": 5.550699615478516,
|
|
"epoch": 1.8062723302897976,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00046779021904457555,
|
|
"loss": 5.1446,
|
|
"mean_token_accuracy": 0.1717533841729164,
|
|
"num_tokens": 39866850.0,
|
|
"step": 18200
|
|
},
|
|
{
|
|
"entropy": 5.590773010253907,
|
|
"epoch": 1.806768558951965,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004677719491173898,
|
|
"loss": 5.1677,
|
|
"mean_token_accuracy": 0.1759544476866722,
|
|
"num_tokens": 39877647.0,
|
|
"step": 18205
|
|
},
|
|
{
|
|
"entropy": 5.584692096710205,
|
|
"epoch": 1.8072647876141326,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.00046775367440987506,
|
|
"loss": 5.1894,
|
|
"mean_token_accuracy": 0.17400931119918822,
|
|
"num_tokens": 39889172.0,
|
|
"step": 18210
|
|
},
|
|
{
|
|
"entropy": 5.597168016433716,
|
|
"epoch": 1.8077610162763,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004677353949224846,
|
|
"loss": 5.1029,
|
|
"mean_token_accuracy": 0.17396012246608733,
|
|
"num_tokens": 39900445.0,
|
|
"step": 18215
|
|
},
|
|
{
|
|
"entropy": 5.571915483474731,
|
|
"epoch": 1.8082572449384675,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00046771711065567167,
|
|
"loss": 5.1331,
|
|
"mean_token_accuracy": 0.17335934489965438,
|
|
"num_tokens": 39912825.0,
|
|
"step": 18220
|
|
},
|
|
{
|
|
"entropy": 5.494789886474609,
|
|
"epoch": 1.8087534736006352,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004676988216098896,
|
|
"loss": 5.0799,
|
|
"mean_token_accuracy": 0.17813094556331635,
|
|
"num_tokens": 39923370.0,
|
|
"step": 18225
|
|
},
|
|
{
|
|
"entropy": 5.617679738998413,
|
|
"epoch": 1.8092497022628027,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004676805277855921,
|
|
"loss": 5.1446,
|
|
"mean_token_accuracy": 0.17175042629241943,
|
|
"num_tokens": 39934724.0,
|
|
"step": 18230
|
|
},
|
|
{
|
|
"entropy": 5.565017414093018,
|
|
"epoch": 1.8097459309249704,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004676622291832326,
|
|
"loss": 5.0718,
|
|
"mean_token_accuracy": 0.16928407102823256,
|
|
"num_tokens": 39947064.0,
|
|
"step": 18235
|
|
},
|
|
{
|
|
"entropy": 5.548071336746216,
|
|
"epoch": 1.8102421595871379,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00046764392580326506,
|
|
"loss": 5.0727,
|
|
"mean_token_accuracy": 0.17396903783082962,
|
|
"num_tokens": 39957649.0,
|
|
"step": 18240
|
|
},
|
|
{
|
|
"entropy": 5.533809518814087,
|
|
"epoch": 1.8107383882493053,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00046762561764614316,
|
|
"loss": 5.1187,
|
|
"mean_token_accuracy": 0.1732972890138626,
|
|
"num_tokens": 39968086.0,
|
|
"step": 18245
|
|
},
|
|
{
|
|
"entropy": 5.532074880599976,
|
|
"epoch": 1.8112346169114728,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.000467607304712321,
|
|
"loss": 5.0719,
|
|
"mean_token_accuracy": 0.1758315846323967,
|
|
"num_tokens": 39978794.0,
|
|
"step": 18250
|
|
},
|
|
{
|
|
"entropy": 5.588777637481689,
|
|
"epoch": 1.8117308455736403,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00046758898700225283,
|
|
"loss": 5.0938,
|
|
"mean_token_accuracy": 0.1740478590130806,
|
|
"num_tokens": 39990383.0,
|
|
"step": 18255
|
|
},
|
|
{
|
|
"entropy": 5.586848640441895,
|
|
"epoch": 1.8122270742358078,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004675706645163927,
|
|
"loss": 5.1662,
|
|
"mean_token_accuracy": 0.17162053436040878,
|
|
"num_tokens": 40001900.0,
|
|
"step": 18260
|
|
},
|
|
{
|
|
"entropy": 5.588620519638061,
|
|
"epoch": 1.8127233028979752,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.000467552337255195,
|
|
"loss": 5.0829,
|
|
"mean_token_accuracy": 0.17045395374298095,
|
|
"num_tokens": 40012482.0,
|
|
"step": 18265
|
|
},
|
|
{
|
|
"entropy": 5.531330394744873,
|
|
"epoch": 1.813219531560143,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004675340052191144,
|
|
"loss": 5.1015,
|
|
"mean_token_accuracy": 0.1747794896364212,
|
|
"num_tokens": 40023264.0,
|
|
"step": 18270
|
|
},
|
|
{
|
|
"entropy": 5.606415128707885,
|
|
"epoch": 1.8137157602223104,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004675156684086052,
|
|
"loss": 5.1628,
|
|
"mean_token_accuracy": 0.1697589173913002,
|
|
"num_tokens": 40034754.0,
|
|
"step": 18275
|
|
},
|
|
{
|
|
"entropy": 5.5492490291595455,
|
|
"epoch": 1.814211988884478,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004674973268241224,
|
|
"loss": 5.0722,
|
|
"mean_token_accuracy": 0.17935317307710646,
|
|
"num_tokens": 40045781.0,
|
|
"step": 18280
|
|
},
|
|
{
|
|
"entropy": 5.591843318939209,
|
|
"epoch": 1.8147082175466456,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004674789804661205,
|
|
"loss": 5.1598,
|
|
"mean_token_accuracy": 0.17444380968809128,
|
|
"num_tokens": 40055700.0,
|
|
"step": 18285
|
|
},
|
|
{
|
|
"entropy": 5.605121040344239,
|
|
"epoch": 1.815204446208813,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00046746062933505477,
|
|
"loss": 5.1735,
|
|
"mean_token_accuracy": 0.17266058176755905,
|
|
"num_tokens": 40066702.0,
|
|
"step": 18290
|
|
},
|
|
{
|
|
"entropy": 5.588819313049316,
|
|
"epoch": 1.8157006748709805,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004674422734313801,
|
|
"loss": 5.1766,
|
|
"mean_token_accuracy": 0.17474929690361024,
|
|
"num_tokens": 40077856.0,
|
|
"step": 18295
|
|
},
|
|
{
|
|
"entropy": 5.500308036804199,
|
|
"epoch": 1.816196903533148,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00046742391275555176,
|
|
"loss": 5.064,
|
|
"mean_token_accuracy": 0.17913249582052232,
|
|
"num_tokens": 40089205.0,
|
|
"step": 18300
|
|
},
|
|
{
|
|
"entropy": 5.607101631164551,
|
|
"epoch": 1.8166931321953155,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.000467405547308025,
|
|
"loss": 5.1133,
|
|
"mean_token_accuracy": 0.17143297642469407,
|
|
"num_tokens": 40100028.0,
|
|
"step": 18305
|
|
},
|
|
{
|
|
"entropy": 5.647699689865112,
|
|
"epoch": 1.8171893608574832,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004673871770892553,
|
|
"loss": 5.1331,
|
|
"mean_token_accuracy": 0.17165503948926925,
|
|
"num_tokens": 40109635.0,
|
|
"step": 18310
|
|
},
|
|
{
|
|
"entropy": 5.551734590530396,
|
|
"epoch": 1.8176855895196506,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00046736880209969814,
|
|
"loss": 5.0925,
|
|
"mean_token_accuracy": 0.17392676770687104,
|
|
"num_tokens": 40120539.0,
|
|
"step": 18315
|
|
},
|
|
{
|
|
"entropy": 5.57048544883728,
|
|
"epoch": 1.8181818181818183,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00046735042233980923,
|
|
"loss": 5.1512,
|
|
"mean_token_accuracy": 0.16403615176677705,
|
|
"num_tokens": 40131738.0,
|
|
"step": 18320
|
|
},
|
|
{
|
|
"entropy": 5.663658237457275,
|
|
"epoch": 1.8186780468439858,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00046733203781004426,
|
|
"loss": 5.2196,
|
|
"mean_token_accuracy": 0.17271289974451065,
|
|
"num_tokens": 40142800.0,
|
|
"step": 18325
|
|
},
|
|
{
|
|
"entropy": 5.660841226577759,
|
|
"epoch": 1.8191742755061533,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.00046731364851085923,
|
|
"loss": 5.1706,
|
|
"mean_token_accuracy": 0.16808565855026245,
|
|
"num_tokens": 40153992.0,
|
|
"step": 18330
|
|
},
|
|
{
|
|
"entropy": 5.589001703262329,
|
|
"epoch": 1.8196705041683208,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004672952544427101,
|
|
"loss": 5.1184,
|
|
"mean_token_accuracy": 0.17254485189914703,
|
|
"num_tokens": 40165213.0,
|
|
"step": 18335
|
|
},
|
|
{
|
|
"entropy": 5.560780811309814,
|
|
"epoch": 1.8201667328304882,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00046727685560605305,
|
|
"loss": 5.1788,
|
|
"mean_token_accuracy": 0.16840216815471648,
|
|
"num_tokens": 40176763.0,
|
|
"step": 18340
|
|
},
|
|
{
|
|
"entropy": 5.56354169845581,
|
|
"epoch": 1.8206629614926557,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004672584520013443,
|
|
"loss": 5.0568,
|
|
"mean_token_accuracy": 0.17163143754005433,
|
|
"num_tokens": 40187958.0,
|
|
"step": 18345
|
|
},
|
|
{
|
|
"entropy": 5.533384513854981,
|
|
"epoch": 1.8211591901548232,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004672400436290402,
|
|
"loss": 5.0706,
|
|
"mean_token_accuracy": 0.17672607004642488,
|
|
"num_tokens": 40197881.0,
|
|
"step": 18350
|
|
},
|
|
{
|
|
"entropy": 5.583889198303223,
|
|
"epoch": 1.821655418816991,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00046722163048959725,
|
|
"loss": 5.0538,
|
|
"mean_token_accuracy": 0.18200553208589554,
|
|
"num_tokens": 40209322.0,
|
|
"step": 18355
|
|
},
|
|
{
|
|
"entropy": 5.565239143371582,
|
|
"epoch": 1.8221516474791584,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004672032125834721,
|
|
"loss": 5.1173,
|
|
"mean_token_accuracy": 0.17447513192892075,
|
|
"num_tokens": 40222186.0,
|
|
"step": 18360
|
|
},
|
|
{
|
|
"entropy": 5.58490309715271,
|
|
"epoch": 1.822647876141326,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004671847899111214,
|
|
"loss": 5.1384,
|
|
"mean_token_accuracy": 0.17238964587450029,
|
|
"num_tokens": 40232136.0,
|
|
"step": 18365
|
|
},
|
|
{
|
|
"entropy": 5.6306617736816404,
|
|
"epoch": 1.8231441048034935,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00046716636247300206,
|
|
"loss": 5.1782,
|
|
"mean_token_accuracy": 0.16945978850126267,
|
|
"num_tokens": 40244468.0,
|
|
"step": 18370
|
|
},
|
|
{
|
|
"entropy": 5.599199819564819,
|
|
"epoch": 1.823640333465661,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00046714793026957096,
|
|
"loss": 5.1356,
|
|
"mean_token_accuracy": 0.17083004713058472,
|
|
"num_tokens": 40255441.0,
|
|
"step": 18375
|
|
},
|
|
{
|
|
"entropy": 5.516262674331665,
|
|
"epoch": 1.8241365621278285,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004671294933012853,
|
|
"loss": 5.045,
|
|
"mean_token_accuracy": 0.1725158527493477,
|
|
"num_tokens": 40266109.0,
|
|
"step": 18380
|
|
},
|
|
{
|
|
"entropy": 5.526769495010376,
|
|
"epoch": 1.824632790789996,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00046711105156860223,
|
|
"loss": 5.0707,
|
|
"mean_token_accuracy": 0.17202406227588654,
|
|
"num_tokens": 40277635.0,
|
|
"step": 18385
|
|
},
|
|
{
|
|
"entropy": 5.570279455184936,
|
|
"epoch": 1.8251290194521634,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00046709260507197896,
|
|
"loss": 5.2046,
|
|
"mean_token_accuracy": 0.17353739440441132,
|
|
"num_tokens": 40288668.0,
|
|
"step": 18390
|
|
},
|
|
{
|
|
"entropy": 5.53749303817749,
|
|
"epoch": 1.8256252481143311,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00046707415381187306,
|
|
"loss": 5.0698,
|
|
"mean_token_accuracy": 0.17616031616926192,
|
|
"num_tokens": 40300262.0,
|
|
"step": 18395
|
|
},
|
|
{
|
|
"entropy": 5.5743152618408205,
|
|
"epoch": 1.8261214767764986,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.000467055697788742,
|
|
"loss": 5.1363,
|
|
"mean_token_accuracy": 0.1635638028383255,
|
|
"num_tokens": 40310931.0,
|
|
"step": 18400
|
|
},
|
|
{
|
|
"entropy": 5.546328544616699,
|
|
"epoch": 1.826617705438666,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.00046703723700304345,
|
|
"loss": 5.0857,
|
|
"mean_token_accuracy": 0.17368315309286117,
|
|
"num_tokens": 40321623.0,
|
|
"step": 18405
|
|
},
|
|
{
|
|
"entropy": 5.523750495910645,
|
|
"epoch": 1.8271139341008338,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004670187714552353,
|
|
"loss": 5.0479,
|
|
"mean_token_accuracy": 0.175416561961174,
|
|
"num_tokens": 40330951.0,
|
|
"step": 18410
|
|
},
|
|
{
|
|
"entropy": 5.586254405975342,
|
|
"epoch": 1.8276101627630013,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.00046700030114577533,
|
|
"loss": 5.1344,
|
|
"mean_token_accuracy": 0.17705303132534028,
|
|
"num_tokens": 40342971.0,
|
|
"step": 18415
|
|
},
|
|
{
|
|
"entropy": 5.542151260375976,
|
|
"epoch": 1.8281063914251687,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004669818260751217,
|
|
"loss": 5.0877,
|
|
"mean_token_accuracy": 0.18032497316598892,
|
|
"num_tokens": 40353837.0,
|
|
"step": 18420
|
|
},
|
|
{
|
|
"entropy": 5.543359470367432,
|
|
"epoch": 1.8286026200873362,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004669633462437324,
|
|
"loss": 5.1785,
|
|
"mean_token_accuracy": 0.17377234101295472,
|
|
"num_tokens": 40367389.0,
|
|
"step": 18425
|
|
},
|
|
{
|
|
"entropy": 5.562901163101197,
|
|
"epoch": 1.8290988487495037,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00046694486165206573,
|
|
"loss": 5.0014,
|
|
"mean_token_accuracy": 0.1825328454375267,
|
|
"num_tokens": 40376793.0,
|
|
"step": 18430
|
|
},
|
|
{
|
|
"entropy": 5.574186515808106,
|
|
"epoch": 1.8295950774116712,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004669263723005801,
|
|
"loss": 5.0984,
|
|
"mean_token_accuracy": 0.17968219071626662,
|
|
"num_tokens": 40388025.0,
|
|
"step": 18435
|
|
},
|
|
{
|
|
"entropy": 5.554730749130249,
|
|
"epoch": 1.8300913060738389,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00046690787818973406,
|
|
"loss": 5.181,
|
|
"mean_token_accuracy": 0.17453974038362502,
|
|
"num_tokens": 40399731.0,
|
|
"step": 18440
|
|
},
|
|
{
|
|
"entropy": 5.575783920288086,
|
|
"epoch": 1.8305875347360063,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.00046688937931998613,
|
|
"loss": 5.2303,
|
|
"mean_token_accuracy": 0.1716172441840172,
|
|
"num_tokens": 40411078.0,
|
|
"step": 18445
|
|
},
|
|
{
|
|
"entropy": 5.63482928276062,
|
|
"epoch": 1.831083763398174,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004668708756917951,
|
|
"loss": 5.1847,
|
|
"mean_token_accuracy": 0.16972215175628663,
|
|
"num_tokens": 40422806.0,
|
|
"step": 18450
|
|
},
|
|
{
|
|
"entropy": 5.704753303527832,
|
|
"epoch": 1.8315799920603415,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00046685236730561975,
|
|
"loss": 5.2332,
|
|
"mean_token_accuracy": 0.16531258299946786,
|
|
"num_tokens": 40434041.0,
|
|
"step": 18455
|
|
},
|
|
{
|
|
"entropy": 5.601125764846802,
|
|
"epoch": 1.832076220722509,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.00046683385416191914,
|
|
"loss": 5.0761,
|
|
"mean_token_accuracy": 0.18101150542497635,
|
|
"num_tokens": 40444658.0,
|
|
"step": 18460
|
|
},
|
|
{
|
|
"entropy": 5.5495442867279055,
|
|
"epoch": 1.8325724493846764,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00046681533626115226,
|
|
"loss": 5.0834,
|
|
"mean_token_accuracy": 0.17381613701581955,
|
|
"num_tokens": 40455745.0,
|
|
"step": 18465
|
|
},
|
|
{
|
|
"entropy": 5.513105678558349,
|
|
"epoch": 1.833068678046844,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004667968136037784,
|
|
"loss": 5.1744,
|
|
"mean_token_accuracy": 0.17271911799907685,
|
|
"num_tokens": 40468829.0,
|
|
"step": 18470
|
|
},
|
|
{
|
|
"entropy": 5.526120615005493,
|
|
"epoch": 1.8335649067090114,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00046677828619025687,
|
|
"loss": 5.0861,
|
|
"mean_token_accuracy": 0.17547255456447602,
|
|
"num_tokens": 40479817.0,
|
|
"step": 18475
|
|
},
|
|
{
|
|
"entropy": 5.669960689544678,
|
|
"epoch": 1.8340611353711789,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00046675975402104706,
|
|
"loss": 5.191,
|
|
"mean_token_accuracy": 0.1685073569417,
|
|
"num_tokens": 40490398.0,
|
|
"step": 18480
|
|
},
|
|
{
|
|
"entropy": 5.539244556427002,
|
|
"epoch": 1.8345573640333466,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00046674121709660855,
|
|
"loss": 5.0237,
|
|
"mean_token_accuracy": 0.1787686377763748,
|
|
"num_tokens": 40500483.0,
|
|
"step": 18485
|
|
},
|
|
{
|
|
"entropy": 5.5947342872619625,
|
|
"epoch": 1.835053592695514,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.000466722675417401,
|
|
"loss": 5.1497,
|
|
"mean_token_accuracy": 0.17010664641857148,
|
|
"num_tokens": 40511494.0,
|
|
"step": 18490
|
|
},
|
|
{
|
|
"entropy": 5.575565528869629,
|
|
"epoch": 1.8355498213576817,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00046670412898388425,
|
|
"loss": 5.0914,
|
|
"mean_token_accuracy": 0.18553085327148439,
|
|
"num_tokens": 40523573.0,
|
|
"step": 18495
|
|
},
|
|
{
|
|
"entropy": 5.555435085296631,
|
|
"epoch": 1.8360460500198492,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.00046668557779651825,
|
|
"loss": 5.1492,
|
|
"mean_token_accuracy": 0.17197633981704713,
|
|
"num_tokens": 40534904.0,
|
|
"step": 18500
|
|
},
|
|
{
|
|
"entropy": 5.5364326477050785,
|
|
"epoch": 1.8365422786820167,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00046666702185576295,
|
|
"loss": 5.1073,
|
|
"mean_token_accuracy": 0.17526595890522004,
|
|
"num_tokens": 40545053.0,
|
|
"step": 18505
|
|
},
|
|
{
|
|
"entropy": 5.5635459423065186,
|
|
"epoch": 1.8370385073441842,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004666484611620785,
|
|
"loss": 5.0389,
|
|
"mean_token_accuracy": 0.18085704743862152,
|
|
"num_tokens": 40555305.0,
|
|
"step": 18510
|
|
},
|
|
{
|
|
"entropy": 5.541917037963867,
|
|
"epoch": 1.8375347360063516,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004666298957159251,
|
|
"loss": 5.0736,
|
|
"mean_token_accuracy": 0.17188790440559387,
|
|
"num_tokens": 40565611.0,
|
|
"step": 18515
|
|
},
|
|
{
|
|
"entropy": 5.573732471466064,
|
|
"epoch": 1.8380309646685191,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00046661132551776327,
|
|
"loss": 5.1574,
|
|
"mean_token_accuracy": 0.17759806364774705,
|
|
"num_tokens": 40578321.0,
|
|
"step": 18520
|
|
},
|
|
{
|
|
"entropy": 5.617476129531861,
|
|
"epoch": 1.8385271933306868,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004665927505680535,
|
|
"loss": 5.1566,
|
|
"mean_token_accuracy": 0.1810738116502762,
|
|
"num_tokens": 40588696.0,
|
|
"step": 18525
|
|
},
|
|
{
|
|
"entropy": 5.58264422416687,
|
|
"epoch": 1.8390234219928543,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00046657417086725625,
|
|
"loss": 5.1116,
|
|
"mean_token_accuracy": 0.1716594085097313,
|
|
"num_tokens": 40599699.0,
|
|
"step": 18530
|
|
},
|
|
{
|
|
"entropy": 5.552099990844726,
|
|
"epoch": 1.839519650655022,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004665555864158324,
|
|
"loss": 5.1198,
|
|
"mean_token_accuracy": 0.1748165175318718,
|
|
"num_tokens": 40609706.0,
|
|
"step": 18535
|
|
},
|
|
{
|
|
"entropy": 5.559789562225342,
|
|
"epoch": 1.8400158793171895,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004665369972142428,
|
|
"loss": 5.1505,
|
|
"mean_token_accuracy": 0.17779080122709273,
|
|
"num_tokens": 40619431.0,
|
|
"step": 18540
|
|
},
|
|
{
|
|
"entropy": 5.611735916137695,
|
|
"epoch": 1.840512107979357,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00046651840326294845,
|
|
"loss": 5.1182,
|
|
"mean_token_accuracy": 0.17686475366353988,
|
|
"num_tokens": 40629904.0,
|
|
"step": 18545
|
|
},
|
|
{
|
|
"entropy": 5.561684465408325,
|
|
"epoch": 1.8410083366415244,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004664998045624104,
|
|
"loss": 5.154,
|
|
"mean_token_accuracy": 0.17088982909917833,
|
|
"num_tokens": 40641266.0,
|
|
"step": 18550
|
|
},
|
|
{
|
|
"entropy": 5.518081474304199,
|
|
"epoch": 1.8415045653036919,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004664812011130897,
|
|
"loss": 5.0953,
|
|
"mean_token_accuracy": 0.17238613218069077,
|
|
"num_tokens": 40652454.0,
|
|
"step": 18555
|
|
},
|
|
{
|
|
"entropy": 5.577287769317627,
|
|
"epoch": 1.8420007939658594,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00046646259291544787,
|
|
"loss": 5.0842,
|
|
"mean_token_accuracy": 0.17364238500595092,
|
|
"num_tokens": 40664311.0,
|
|
"step": 18560
|
|
},
|
|
{
|
|
"entropy": 5.50480432510376,
|
|
"epoch": 1.8424970226280268,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004664439799699463,
|
|
"loss": 5.012,
|
|
"mean_token_accuracy": 0.17981128692626952,
|
|
"num_tokens": 40675241.0,
|
|
"step": 18565
|
|
},
|
|
{
|
|
"entropy": 5.547020816802979,
|
|
"epoch": 1.8429932512901945,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.00046642536227704665,
|
|
"loss": 5.0885,
|
|
"mean_token_accuracy": 0.17679386138916015,
|
|
"num_tokens": 40685972.0,
|
|
"step": 18570
|
|
},
|
|
{
|
|
"entropy": 5.533656358718872,
|
|
"epoch": 1.843489479952362,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00046640673983721037,
|
|
"loss": 5.1091,
|
|
"mean_token_accuracy": 0.17504760921001433,
|
|
"num_tokens": 40696967.0,
|
|
"step": 18575
|
|
},
|
|
{
|
|
"entropy": 5.583533382415771,
|
|
"epoch": 1.8439857086145297,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.00046638811265089944,
|
|
"loss": 5.1032,
|
|
"mean_token_accuracy": 0.17084284424781798,
|
|
"num_tokens": 40707710.0,
|
|
"step": 18580
|
|
},
|
|
{
|
|
"entropy": 5.6240739822387695,
|
|
"epoch": 1.8444819372766972,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004663694807185758,
|
|
"loss": 5.239,
|
|
"mean_token_accuracy": 0.16960958391427994,
|
|
"num_tokens": 40718586.0,
|
|
"step": 18585
|
|
},
|
|
{
|
|
"entropy": 5.6136102199554445,
|
|
"epoch": 1.8449781659388647,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00046635084404070135,
|
|
"loss": 5.1142,
|
|
"mean_token_accuracy": 0.1783537745475769,
|
|
"num_tokens": 40729792.0,
|
|
"step": 18590
|
|
},
|
|
{
|
|
"entropy": 5.712875890731811,
|
|
"epoch": 1.8454743946010321,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004663322026177382,
|
|
"loss": 5.171,
|
|
"mean_token_accuracy": 0.16736815646290779,
|
|
"num_tokens": 40740974.0,
|
|
"step": 18595
|
|
},
|
|
{
|
|
"entropy": 5.526970338821411,
|
|
"epoch": 1.8459706232631996,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00046631355645014875,
|
|
"loss": 4.9854,
|
|
"mean_token_accuracy": 0.18436610251665114,
|
|
"num_tokens": 40750208.0,
|
|
"step": 18600
|
|
},
|
|
{
|
|
"entropy": 5.544992113113404,
|
|
"epoch": 1.846466851925367,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00046629490553839537,
|
|
"loss": 5.0853,
|
|
"mean_token_accuracy": 0.1767660841345787,
|
|
"num_tokens": 40762163.0,
|
|
"step": 18605
|
|
},
|
|
{
|
|
"entropy": 5.58039116859436,
|
|
"epoch": 1.8469630805875348,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004662762498829405,
|
|
"loss": 5.1792,
|
|
"mean_token_accuracy": 0.17419902086257935,
|
|
"num_tokens": 40773028.0,
|
|
"step": 18610
|
|
},
|
|
{
|
|
"entropy": 5.637732410430909,
|
|
"epoch": 1.8474593092497023,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004662575894842469,
|
|
"loss": 5.1514,
|
|
"mean_token_accuracy": 0.16426871418952943,
|
|
"num_tokens": 40784939.0,
|
|
"step": 18615
|
|
},
|
|
{
|
|
"entropy": 5.591274976730347,
|
|
"epoch": 1.84795553791187,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.00046623892434277713,
|
|
"loss": 5.1387,
|
|
"mean_token_accuracy": 0.17336395382881165,
|
|
"num_tokens": 40796170.0,
|
|
"step": 18620
|
|
},
|
|
{
|
|
"entropy": 5.578694629669189,
|
|
"epoch": 1.8484517665740374,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004662202544589941,
|
|
"loss": 5.0881,
|
|
"mean_token_accuracy": 0.17862146049737931,
|
|
"num_tokens": 40807184.0,
|
|
"step": 18625
|
|
},
|
|
{
|
|
"entropy": 5.542214488983154,
|
|
"epoch": 1.848947995236205,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.00046620157983336087,
|
|
"loss": 5.0602,
|
|
"mean_token_accuracy": 0.1744668588042259,
|
|
"num_tokens": 40818474.0,
|
|
"step": 18630
|
|
},
|
|
{
|
|
"entropy": 5.55736722946167,
|
|
"epoch": 1.8494442238983724,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004661829004663404,
|
|
"loss": 5.1175,
|
|
"mean_token_accuracy": 0.17546663284301758,
|
|
"num_tokens": 40828789.0,
|
|
"step": 18635
|
|
},
|
|
{
|
|
"entropy": 5.568894910812378,
|
|
"epoch": 1.8499404525605398,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004661642163583961,
|
|
"loss": 5.0705,
|
|
"mean_token_accuracy": 0.18279811441898347,
|
|
"num_tokens": 40840564.0,
|
|
"step": 18640
|
|
},
|
|
{
|
|
"entropy": 5.534308624267578,
|
|
"epoch": 1.8504366812227073,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.00046614552750999093,
|
|
"loss": 5.062,
|
|
"mean_token_accuracy": 0.17633196860551834,
|
|
"num_tokens": 40852528.0,
|
|
"step": 18645
|
|
},
|
|
{
|
|
"entropy": 5.551772880554199,
|
|
"epoch": 1.8509329098848748,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004661268339215887,
|
|
"loss": 5.1048,
|
|
"mean_token_accuracy": 0.17363428324460983,
|
|
"num_tokens": 40863242.0,
|
|
"step": 18650
|
|
},
|
|
{
|
|
"entropy": 5.53049521446228,
|
|
"epoch": 1.8514291385470425,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004661081355936528,
|
|
"loss": 5.0643,
|
|
"mean_token_accuracy": 0.18281110972166062,
|
|
"num_tokens": 40873721.0,
|
|
"step": 18655
|
|
},
|
|
{
|
|
"entropy": 5.599796867370605,
|
|
"epoch": 1.85192536720921,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000466089432526647,
|
|
"loss": 5.1475,
|
|
"mean_token_accuracy": 0.17103291004896165,
|
|
"num_tokens": 40884921.0,
|
|
"step": 18660
|
|
},
|
|
{
|
|
"entropy": 5.590263605117798,
|
|
"epoch": 1.8524215958713777,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00046607072472103493,
|
|
"loss": 5.0436,
|
|
"mean_token_accuracy": 0.17644645273685455,
|
|
"num_tokens": 40896243.0,
|
|
"step": 18665
|
|
},
|
|
{
|
|
"entropy": 5.554067230224609,
|
|
"epoch": 1.8529178245335451,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.00046605201217728067,
|
|
"loss": 5.1731,
|
|
"mean_token_accuracy": 0.16817651987075805,
|
|
"num_tokens": 40907191.0,
|
|
"step": 18670
|
|
},
|
|
{
|
|
"entropy": 5.596529293060303,
|
|
"epoch": 1.8534140531957126,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.00046603329489584817,
|
|
"loss": 5.1277,
|
|
"mean_token_accuracy": 0.18083939254283904,
|
|
"num_tokens": 40918737.0,
|
|
"step": 18675
|
|
},
|
|
{
|
|
"entropy": 5.6284534454345705,
|
|
"epoch": 1.85391028185788,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004660145728772016,
|
|
"loss": 5.1377,
|
|
"mean_token_accuracy": 0.17307621091604233,
|
|
"num_tokens": 40930184.0,
|
|
"step": 18680
|
|
},
|
|
{
|
|
"entropy": 5.540746450424194,
|
|
"epoch": 1.8544065105200476,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004659958461218052,
|
|
"loss": 5.0406,
|
|
"mean_token_accuracy": 0.18058212399482726,
|
|
"num_tokens": 40941483.0,
|
|
"step": 18685
|
|
},
|
|
{
|
|
"entropy": 5.5579094886779785,
|
|
"epoch": 1.854902739182215,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.00046597711463012344,
|
|
"loss": 5.1316,
|
|
"mean_token_accuracy": 0.17433445304632186,
|
|
"num_tokens": 40952392.0,
|
|
"step": 18690
|
|
},
|
|
{
|
|
"entropy": 5.528490924835205,
|
|
"epoch": 1.8553989678443827,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004659583784026207,
|
|
"loss": 5.0566,
|
|
"mean_token_accuracy": 0.1776428610086441,
|
|
"num_tokens": 40962539.0,
|
|
"step": 18695
|
|
},
|
|
{
|
|
"entropy": 5.543492603302002,
|
|
"epoch": 1.8558951965065502,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00046593963743976163,
|
|
"loss": 4.9924,
|
|
"mean_token_accuracy": 0.18435071557760238,
|
|
"num_tokens": 40972594.0,
|
|
"step": 18700
|
|
},
|
|
{
|
|
"entropy": 5.5710138320922855,
|
|
"epoch": 1.8563914251687177,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.000465920891742011,
|
|
"loss": 5.1198,
|
|
"mean_token_accuracy": 0.17292593121528627,
|
|
"num_tokens": 40983460.0,
|
|
"step": 18705
|
|
},
|
|
{
|
|
"entropy": 5.540741014480591,
|
|
"epoch": 1.8568876538308854,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004659021413098337,
|
|
"loss": 5.1035,
|
|
"mean_token_accuracy": 0.1728368043899536,
|
|
"num_tokens": 40993945.0,
|
|
"step": 18710
|
|
},
|
|
{
|
|
"entropy": 5.4902032852172855,
|
|
"epoch": 1.8573838824930529,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00046588338614369465,
|
|
"loss": 5.0951,
|
|
"mean_token_accuracy": 0.17472022622823716,
|
|
"num_tokens": 41005781.0,
|
|
"step": 18715
|
|
},
|
|
{
|
|
"entropy": 5.621731233596802,
|
|
"epoch": 1.8578801111552203,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.00046586462624405897,
|
|
"loss": 5.1968,
|
|
"mean_token_accuracy": 0.16917262822389603,
|
|
"num_tokens": 41017650.0,
|
|
"step": 18720
|
|
},
|
|
{
|
|
"entropy": 5.581646299362182,
|
|
"epoch": 1.8583763398173878,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004658458616113918,
|
|
"loss": 5.0719,
|
|
"mean_token_accuracy": 0.17837297469377517,
|
|
"num_tokens": 41029196.0,
|
|
"step": 18725
|
|
},
|
|
{
|
|
"entropy": 5.583410120010376,
|
|
"epoch": 1.8588725684795553,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004658270922461585,
|
|
"loss": 5.1414,
|
|
"mean_token_accuracy": 0.1769915610551834,
|
|
"num_tokens": 41040204.0,
|
|
"step": 18730
|
|
},
|
|
{
|
|
"entropy": 5.585629796981811,
|
|
"epoch": 1.8593687971417228,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00046580831814882446,
|
|
"loss": 5.123,
|
|
"mean_token_accuracy": 0.17069858312606812,
|
|
"num_tokens": 41050507.0,
|
|
"step": 18735
|
|
},
|
|
{
|
|
"entropy": 5.527240896224976,
|
|
"epoch": 1.8598650258038905,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00046578953931985536,
|
|
"loss": 5.092,
|
|
"mean_token_accuracy": 0.17268568873405457,
|
|
"num_tokens": 41062001.0,
|
|
"step": 18740
|
|
},
|
|
{
|
|
"entropy": 5.580925846099854,
|
|
"epoch": 1.860361254466058,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004657707557597167,
|
|
"loss": 5.0962,
|
|
"mean_token_accuracy": 0.17323880940675734,
|
|
"num_tokens": 41073097.0,
|
|
"step": 18745
|
|
},
|
|
{
|
|
"entropy": 5.583203363418579,
|
|
"epoch": 1.8608574831282256,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00046575196746887447,
|
|
"loss": 5.1209,
|
|
"mean_token_accuracy": 0.1713651418685913,
|
|
"num_tokens": 41083883.0,
|
|
"step": 18750
|
|
},
|
|
{
|
|
"entropy": 5.489950323104859,
|
|
"epoch": 1.861353711790393,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00046573317444779445,
|
|
"loss": 5.0949,
|
|
"mean_token_accuracy": 0.18363923728466033,
|
|
"num_tokens": 41095506.0,
|
|
"step": 18755
|
|
},
|
|
{
|
|
"entropy": 5.579948759078979,
|
|
"epoch": 1.8618499404525606,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004657143766969427,
|
|
"loss": 5.1232,
|
|
"mean_token_accuracy": 0.17421770989894866,
|
|
"num_tokens": 41106568.0,
|
|
"step": 18760
|
|
},
|
|
{
|
|
"entropy": 5.578218603134156,
|
|
"epoch": 1.862346169114728,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004656955742167853,
|
|
"loss": 5.015,
|
|
"mean_token_accuracy": 0.17773817032575606,
|
|
"num_tokens": 41117661.0,
|
|
"step": 18765
|
|
},
|
|
{
|
|
"entropy": 5.559988880157471,
|
|
"epoch": 1.8628423977768955,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.00046567676700778865,
|
|
"loss": 5.1031,
|
|
"mean_token_accuracy": 0.17744435220956803,
|
|
"num_tokens": 41129209.0,
|
|
"step": 18770
|
|
},
|
|
{
|
|
"entropy": 5.564537715911865,
|
|
"epoch": 1.863338626439063,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.00046565795507041904,
|
|
"loss": 5.1725,
|
|
"mean_token_accuracy": 0.17351065427064896,
|
|
"num_tokens": 41140715.0,
|
|
"step": 18775
|
|
},
|
|
{
|
|
"entropy": 5.572348117828369,
|
|
"epoch": 1.8638348551012305,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.000465639138405143,
|
|
"loss": 5.1359,
|
|
"mean_token_accuracy": 0.17433889359235763,
|
|
"num_tokens": 41151080.0,
|
|
"step": 18780
|
|
},
|
|
{
|
|
"entropy": 5.595568132400513,
|
|
"epoch": 1.8643310837633982,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00046562031701242703,
|
|
"loss": 5.1464,
|
|
"mean_token_accuracy": 0.1780318945646286,
|
|
"num_tokens": 41162816.0,
|
|
"step": 18785
|
|
},
|
|
{
|
|
"entropy": 5.568077230453492,
|
|
"epoch": 1.8648273124255657,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00046560149089273803,
|
|
"loss": 5.0409,
|
|
"mean_token_accuracy": 0.1847884625196457,
|
|
"num_tokens": 41173456.0,
|
|
"step": 18790
|
|
},
|
|
{
|
|
"entropy": 5.5413374423980715,
|
|
"epoch": 1.8653235410877333,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004655826600465427,
|
|
"loss": 5.0037,
|
|
"mean_token_accuracy": 0.1799089252948761,
|
|
"num_tokens": 41184436.0,
|
|
"step": 18795
|
|
},
|
|
{
|
|
"entropy": 5.512774038314819,
|
|
"epoch": 1.8658197697499008,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00046556382447430816,
|
|
"loss": 5.0765,
|
|
"mean_token_accuracy": 0.17751057744026183,
|
|
"num_tokens": 41196417.0,
|
|
"step": 18800
|
|
},
|
|
{
|
|
"entropy": 5.5446936130523685,
|
|
"epoch": 1.8663159984120683,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00046554498417650134,
|
|
"loss": 5.0831,
|
|
"mean_token_accuracy": 0.17722584307193756,
|
|
"num_tokens": 41206054.0,
|
|
"step": 18805
|
|
},
|
|
{
|
|
"entropy": 5.537550544738769,
|
|
"epoch": 1.8668122270742358,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004655261391535895,
|
|
"loss": 5.0938,
|
|
"mean_token_accuracy": 0.17636859863996507,
|
|
"num_tokens": 41217002.0,
|
|
"step": 18810
|
|
},
|
|
{
|
|
"entropy": 5.706327629089356,
|
|
"epoch": 1.8673084557364032,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004655072894060399,
|
|
"loss": 5.2437,
|
|
"mean_token_accuracy": 0.16572582125663757,
|
|
"num_tokens": 41228485.0,
|
|
"step": 18815
|
|
},
|
|
{
|
|
"entropy": 5.609031391143799,
|
|
"epoch": 1.8678046843985707,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004654884349343201,
|
|
"loss": 5.1189,
|
|
"mean_token_accuracy": 0.17708613574504853,
|
|
"num_tokens": 41240600.0,
|
|
"step": 18820
|
|
},
|
|
{
|
|
"entropy": 5.643232965469361,
|
|
"epoch": 1.8683009130607384,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00046546957573889757,
|
|
"loss": 5.211,
|
|
"mean_token_accuracy": 0.1694723054766655,
|
|
"num_tokens": 41251870.0,
|
|
"step": 18825
|
|
},
|
|
{
|
|
"entropy": 5.54521598815918,
|
|
"epoch": 1.868797141722906,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00046545071182024,
|
|
"loss": 5.1097,
|
|
"mean_token_accuracy": 0.16906451284885407,
|
|
"num_tokens": 41264679.0,
|
|
"step": 18830
|
|
},
|
|
{
|
|
"entropy": 5.6929511547088625,
|
|
"epoch": 1.8692933703850736,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00046543184317881516,
|
|
"loss": 5.1976,
|
|
"mean_token_accuracy": 0.16911463141441346,
|
|
"num_tokens": 41275690.0,
|
|
"step": 18835
|
|
},
|
|
{
|
|
"entropy": 5.554496812820434,
|
|
"epoch": 1.869789599047241,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000465412969815091,
|
|
"loss": 5.0817,
|
|
"mean_token_accuracy": 0.17793331444263458,
|
|
"num_tokens": 41285118.0,
|
|
"step": 18840
|
|
},
|
|
{
|
|
"entropy": 5.5289019584655765,
|
|
"epoch": 1.8702858277094085,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004653940917295354,
|
|
"loss": 5.0799,
|
|
"mean_token_accuracy": 0.1762320175766945,
|
|
"num_tokens": 41296330.0,
|
|
"step": 18845
|
|
},
|
|
{
|
|
"entropy": 5.521486616134643,
|
|
"epoch": 1.870782056371576,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004653752089226166,
|
|
"loss": 5.1071,
|
|
"mean_token_accuracy": 0.17323946654796601,
|
|
"num_tokens": 41307051.0,
|
|
"step": 18850
|
|
},
|
|
{
|
|
"entropy": 5.562676906585693,
|
|
"epoch": 1.8712782850337435,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004653563213948029,
|
|
"loss": 5.0459,
|
|
"mean_token_accuracy": 0.18045729994773865,
|
|
"num_tokens": 41317111.0,
|
|
"step": 18855
|
|
},
|
|
{
|
|
"entropy": 5.500308227539063,
|
|
"epoch": 1.871774513695911,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00046533742914656254,
|
|
"loss": 5.0317,
|
|
"mean_token_accuracy": 0.17823178917169571,
|
|
"num_tokens": 41327509.0,
|
|
"step": 18860
|
|
},
|
|
{
|
|
"entropy": 5.558806753158569,
|
|
"epoch": 1.8722707423580784,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00046531853217836414,
|
|
"loss": 5.1217,
|
|
"mean_token_accuracy": 0.1714998885989189,
|
|
"num_tokens": 41338721.0,
|
|
"step": 18865
|
|
},
|
|
{
|
|
"entropy": 5.633945941925049,
|
|
"epoch": 1.8727669710202461,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00046529963049067623,
|
|
"loss": 5.1667,
|
|
"mean_token_accuracy": 0.1708723098039627,
|
|
"num_tokens": 41349767.0,
|
|
"step": 18870
|
|
},
|
|
{
|
|
"entropy": 5.686631917953491,
|
|
"epoch": 1.8732631996824136,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00046528072408396747,
|
|
"loss": 5.2718,
|
|
"mean_token_accuracy": 0.1667434275150299,
|
|
"num_tokens": 41361151.0,
|
|
"step": 18875
|
|
},
|
|
{
|
|
"entropy": 5.5772655487060545,
|
|
"epoch": 1.8737594283445813,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004652618129587069,
|
|
"loss": 5.0664,
|
|
"mean_token_accuracy": 0.17504362016916275,
|
|
"num_tokens": 41372875.0,
|
|
"step": 18880
|
|
},
|
|
{
|
|
"entropy": 5.622480297088623,
|
|
"epoch": 1.8742556570067488,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00046524289711536327,
|
|
"loss": 5.1375,
|
|
"mean_token_accuracy": 0.17084690034389496,
|
|
"num_tokens": 41383284.0,
|
|
"step": 18885
|
|
},
|
|
{
|
|
"entropy": 5.5345375537872314,
|
|
"epoch": 1.8747518856689163,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004652239765544057,
|
|
"loss": 5.0917,
|
|
"mean_token_accuracy": 0.17910555750131607,
|
|
"num_tokens": 41395389.0,
|
|
"step": 18890
|
|
},
|
|
{
|
|
"entropy": 5.506894922256469,
|
|
"epoch": 1.8752481143310837,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00046520505127630346,
|
|
"loss": 5.0512,
|
|
"mean_token_accuracy": 0.17614742517471313,
|
|
"num_tokens": 41406740.0,
|
|
"step": 18895
|
|
},
|
|
{
|
|
"entropy": 5.541567993164063,
|
|
"epoch": 1.8757443429932512,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00046518612128152576,
|
|
"loss": 5.0679,
|
|
"mean_token_accuracy": 0.17749993801116942,
|
|
"num_tokens": 41417279.0,
|
|
"step": 18900
|
|
},
|
|
{
|
|
"entropy": 5.512280082702636,
|
|
"epoch": 1.8762405716554187,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004651671865705421,
|
|
"loss": 5.0373,
|
|
"mean_token_accuracy": 0.17643697261810304,
|
|
"num_tokens": 41428574.0,
|
|
"step": 18905
|
|
},
|
|
{
|
|
"entropy": 5.560574626922607,
|
|
"epoch": 1.8767368003175864,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00046514824714382204,
|
|
"loss": 5.0315,
|
|
"mean_token_accuracy": 0.17742726802825928,
|
|
"num_tokens": 41438784.0,
|
|
"step": 18910
|
|
},
|
|
{
|
|
"entropy": 5.559384393692016,
|
|
"epoch": 1.8772330289797539,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004651293030018351,
|
|
"loss": 5.0711,
|
|
"mean_token_accuracy": 0.1744977653026581,
|
|
"num_tokens": 41448481.0,
|
|
"step": 18915
|
|
},
|
|
{
|
|
"entropy": 5.5868010997772215,
|
|
"epoch": 1.8777292576419216,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00046511035414505115,
|
|
"loss": 5.1155,
|
|
"mean_token_accuracy": 0.1788717344403267,
|
|
"num_tokens": 41459097.0,
|
|
"step": 18920
|
|
},
|
|
{
|
|
"entropy": 5.60605640411377,
|
|
"epoch": 1.878225486304089,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004650914005739401,
|
|
"loss": 5.1579,
|
|
"mean_token_accuracy": 0.17140321284532548,
|
|
"num_tokens": 41469647.0,
|
|
"step": 18925
|
|
},
|
|
{
|
|
"entropy": 5.562855243682861,
|
|
"epoch": 1.8787217149662565,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004650724422889719,
|
|
"loss": 5.1008,
|
|
"mean_token_accuracy": 0.16781231462955476,
|
|
"num_tokens": 41479826.0,
|
|
"step": 18930
|
|
},
|
|
{
|
|
"entropy": 5.600466108322143,
|
|
"epoch": 1.879217943628424,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004650534792906167,
|
|
"loss": 5.0571,
|
|
"mean_token_accuracy": 0.17631438374519348,
|
|
"num_tokens": 41490551.0,
|
|
"step": 18935
|
|
},
|
|
{
|
|
"entropy": 5.556157064437866,
|
|
"epoch": 1.8797141722905915,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004650345115793447,
|
|
"loss": 5.0914,
|
|
"mean_token_accuracy": 0.179885895550251,
|
|
"num_tokens": 41500908.0,
|
|
"step": 18940
|
|
},
|
|
{
|
|
"entropy": 5.537628269195556,
|
|
"epoch": 1.880210400952759,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00046501553915562644,
|
|
"loss": 5.064,
|
|
"mean_token_accuracy": 0.1736200124025345,
|
|
"num_tokens": 41511311.0,
|
|
"step": 18945
|
|
},
|
|
{
|
|
"entropy": 5.530085325241089,
|
|
"epoch": 1.8807066296149264,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00046499656201993213,
|
|
"loss": 5.093,
|
|
"mean_token_accuracy": 0.17708706259727477,
|
|
"num_tokens": 41522068.0,
|
|
"step": 18950
|
|
},
|
|
{
|
|
"entropy": 5.543504238128662,
|
|
"epoch": 1.881202858277094,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00046497758017273255,
|
|
"loss": 5.0983,
|
|
"mean_token_accuracy": 0.17089073359966278,
|
|
"num_tokens": 41534099.0,
|
|
"step": 18955
|
|
},
|
|
{
|
|
"entropy": 5.606848621368409,
|
|
"epoch": 1.8816990869392616,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.00046495859361449834,
|
|
"loss": 5.1634,
|
|
"mean_token_accuracy": 0.16555947065353394,
|
|
"num_tokens": 41545870.0,
|
|
"step": 18960
|
|
},
|
|
{
|
|
"entropy": 5.581093740463257,
|
|
"epoch": 1.8821953156014293,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004649396023457003,
|
|
"loss": 5.1551,
|
|
"mean_token_accuracy": 0.17180070132017136,
|
|
"num_tokens": 41558175.0,
|
|
"step": 18965
|
|
},
|
|
{
|
|
"entropy": 5.548663139343262,
|
|
"epoch": 1.8826915442635968,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004649206063668094,
|
|
"loss": 5.1078,
|
|
"mean_token_accuracy": 0.18083097487688066,
|
|
"num_tokens": 41569326.0,
|
|
"step": 18970
|
|
},
|
|
{
|
|
"entropy": 5.562871885299683,
|
|
"epoch": 1.8831877729257642,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004649016056782968,
|
|
"loss": 5.0559,
|
|
"mean_token_accuracy": 0.18182073831558226,
|
|
"num_tokens": 41580065.0,
|
|
"step": 18975
|
|
},
|
|
{
|
|
"entropy": 5.634759473800659,
|
|
"epoch": 1.8836840015879317,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004648826002806334,
|
|
"loss": 5.1979,
|
|
"mean_token_accuracy": 0.1764739543199539,
|
|
"num_tokens": 41590915.0,
|
|
"step": 18980
|
|
},
|
|
{
|
|
"entropy": 5.533243465423584,
|
|
"epoch": 1.8841802302500992,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004648635901742909,
|
|
"loss": 5.0467,
|
|
"mean_token_accuracy": 0.18027180135250093,
|
|
"num_tokens": 41602096.0,
|
|
"step": 18985
|
|
},
|
|
{
|
|
"entropy": 5.566839551925659,
|
|
"epoch": 1.8846764589122667,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004648445753597403,
|
|
"loss": 5.1614,
|
|
"mean_token_accuracy": 0.17083170861005784,
|
|
"num_tokens": 41612589.0,
|
|
"step": 18990
|
|
},
|
|
{
|
|
"entropy": 5.540729522705078,
|
|
"epoch": 1.8851726875744343,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.00046482555583745336,
|
|
"loss": 5.0539,
|
|
"mean_token_accuracy": 0.1739143282175064,
|
|
"num_tokens": 41624163.0,
|
|
"step": 18995
|
|
},
|
|
{
|
|
"entropy": 5.574202299118042,
|
|
"epoch": 1.8856689162366018,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004648065316079017,
|
|
"loss": 5.055,
|
|
"mean_token_accuracy": 0.17677053064107895,
|
|
"num_tokens": 41635919.0,
|
|
"step": 19000
|
|
},
|
|
{
|
|
"entropy": 5.536738491058349,
|
|
"epoch": 1.8861651448987695,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00046478750267155703,
|
|
"loss": 5.0786,
|
|
"mean_token_accuracy": 0.17330556958913804,
|
|
"num_tokens": 41644723.0,
|
|
"step": 19005
|
|
},
|
|
{
|
|
"entropy": 5.548032522201538,
|
|
"epoch": 1.886661373560937,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.00046476846902889125,
|
|
"loss": 5.1432,
|
|
"mean_token_accuracy": 0.17674286663532257,
|
|
"num_tokens": 41657137.0,
|
|
"step": 19010
|
|
},
|
|
{
|
|
"entropy": 5.599433040618896,
|
|
"epoch": 1.8871576022231045,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004647494306803764,
|
|
"loss": 5.1179,
|
|
"mean_token_accuracy": 0.17483253180980682,
|
|
"num_tokens": 41667773.0,
|
|
"step": 19015
|
|
},
|
|
{
|
|
"entropy": 5.624449348449707,
|
|
"epoch": 1.887653830885272,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.00046473038762648446,
|
|
"loss": 5.1877,
|
|
"mean_token_accuracy": 0.17361018806695938,
|
|
"num_tokens": 41680549.0,
|
|
"step": 19020
|
|
},
|
|
{
|
|
"entropy": 5.569558334350586,
|
|
"epoch": 1.8881500595474394,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00046471133986768784,
|
|
"loss": 5.0835,
|
|
"mean_token_accuracy": 0.17772890329360963,
|
|
"num_tokens": 41689700.0,
|
|
"step": 19025
|
|
},
|
|
{
|
|
"entropy": 5.63198037147522,
|
|
"epoch": 1.888646288209607,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00046469228740445874,
|
|
"loss": 5.1248,
|
|
"mean_token_accuracy": 0.17821198403835298,
|
|
"num_tokens": 41699734.0,
|
|
"step": 19030
|
|
},
|
|
{
|
|
"entropy": 5.5688129425048825,
|
|
"epoch": 1.8891425168717744,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00046467323023726965,
|
|
"loss": 5.1243,
|
|
"mean_token_accuracy": 0.17509949058294297,
|
|
"num_tokens": 41710644.0,
|
|
"step": 19035
|
|
},
|
|
{
|
|
"entropy": 5.499895334243774,
|
|
"epoch": 1.889638745533942,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00046465416836659313,
|
|
"loss": 5.0394,
|
|
"mean_token_accuracy": 0.1806145504117012,
|
|
"num_tokens": 41721416.0,
|
|
"step": 19040
|
|
},
|
|
{
|
|
"entropy": 5.582535171508789,
|
|
"epoch": 1.8901349741961095,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.000464635101792902,
|
|
"loss": 5.0517,
|
|
"mean_token_accuracy": 0.17709997147321702,
|
|
"num_tokens": 41732139.0,
|
|
"step": 19045
|
|
},
|
|
{
|
|
"entropy": 5.561202049255371,
|
|
"epoch": 1.8906312028582772,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00046461603051666883,
|
|
"loss": 5.1488,
|
|
"mean_token_accuracy": 0.17352749407291412,
|
|
"num_tokens": 41744233.0,
|
|
"step": 19050
|
|
},
|
|
{
|
|
"entropy": 5.561340999603272,
|
|
"epoch": 1.8911274315204447,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00046459695453836676,
|
|
"loss": 5.0699,
|
|
"mean_token_accuracy": 0.1834057793021202,
|
|
"num_tokens": 41755514.0,
|
|
"step": 19055
|
|
},
|
|
{
|
|
"entropy": 5.596374559402466,
|
|
"epoch": 1.8916236601826122,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004645778738584688,
|
|
"loss": 5.1034,
|
|
"mean_token_accuracy": 0.17541026175022126,
|
|
"num_tokens": 41765613.0,
|
|
"step": 19060
|
|
},
|
|
{
|
|
"entropy": 5.609683656692505,
|
|
"epoch": 1.8921198888447797,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004645587884774481,
|
|
"loss": 5.1388,
|
|
"mean_token_accuracy": 0.1724128544330597,
|
|
"num_tokens": 41777294.0,
|
|
"step": 19065
|
|
},
|
|
{
|
|
"entropy": 5.5225907325744625,
|
|
"epoch": 1.8926161175069471,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004645396983957778,
|
|
"loss": 5.0444,
|
|
"mean_token_accuracy": 0.18220995217561722,
|
|
"num_tokens": 41788278.0,
|
|
"step": 19070
|
|
},
|
|
{
|
|
"entropy": 5.578003025054931,
|
|
"epoch": 1.8931123461691146,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00046452060361393147,
|
|
"loss": 5.1093,
|
|
"mean_token_accuracy": 0.1702814817428589,
|
|
"num_tokens": 41798663.0,
|
|
"step": 19075
|
|
},
|
|
{
|
|
"entropy": 5.584049367904663,
|
|
"epoch": 1.8936085748312823,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004645015041323825,
|
|
"loss": 5.0664,
|
|
"mean_token_accuracy": 0.1794762507081032,
|
|
"num_tokens": 41808711.0,
|
|
"step": 19080
|
|
},
|
|
{
|
|
"entropy": 5.580535745620727,
|
|
"epoch": 1.8941048034934498,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00046448239995160455,
|
|
"loss": 5.1147,
|
|
"mean_token_accuracy": 0.1716906785964966,
|
|
"num_tokens": 41819679.0,
|
|
"step": 19085
|
|
},
|
|
{
|
|
"entropy": 5.611795473098755,
|
|
"epoch": 1.8946010321556173,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004644632910720715,
|
|
"loss": 5.0996,
|
|
"mean_token_accuracy": 0.17616001665592193,
|
|
"num_tokens": 41829649.0,
|
|
"step": 19090
|
|
},
|
|
{
|
|
"entropy": 5.5847875595092775,
|
|
"epoch": 1.895097260817785,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.000464444177494257,
|
|
"loss": 5.1472,
|
|
"mean_token_accuracy": 0.17002528309822082,
|
|
"num_tokens": 41842523.0,
|
|
"step": 19095
|
|
},
|
|
{
|
|
"entropy": 5.566792058944702,
|
|
"epoch": 1.8955934894799524,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004644250592186351,
|
|
"loss": 5.1119,
|
|
"mean_token_accuracy": 0.17423339039087296,
|
|
"num_tokens": 41854514.0,
|
|
"step": 19100
|
|
},
|
|
{
|
|
"entropy": 5.598566293716431,
|
|
"epoch": 1.89608971814212,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.00046440593624568,
|
|
"loss": 5.0832,
|
|
"mean_token_accuracy": 0.17401032745838166,
|
|
"num_tokens": 41865166.0,
|
|
"step": 19105
|
|
},
|
|
{
|
|
"entropy": 5.559074068069458,
|
|
"epoch": 1.8965859468042874,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004643868085758657,
|
|
"loss": 5.0405,
|
|
"mean_token_accuracy": 0.18056625127792358,
|
|
"num_tokens": 41877264.0,
|
|
"step": 19110
|
|
},
|
|
{
|
|
"entropy": 5.581889581680298,
|
|
"epoch": 1.8970821754664549,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00046436767620966675,
|
|
"loss": 5.0646,
|
|
"mean_token_accuracy": 0.17500241994857788,
|
|
"num_tokens": 41887345.0,
|
|
"step": 19115
|
|
},
|
|
{
|
|
"entropy": 5.5845636367797855,
|
|
"epoch": 1.8975784041286223,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00046434853914755744,
|
|
"loss": 5.1214,
|
|
"mean_token_accuracy": 0.17222516536712645,
|
|
"num_tokens": 41898877.0,
|
|
"step": 19120
|
|
},
|
|
{
|
|
"entropy": 5.510692548751831,
|
|
"epoch": 1.89807463279079,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.00046432939739001237,
|
|
"loss": 5.0427,
|
|
"mean_token_accuracy": 0.17791842073202133,
|
|
"num_tokens": 41910593.0,
|
|
"step": 19125
|
|
},
|
|
{
|
|
"entropy": 5.540350389480591,
|
|
"epoch": 1.8985708614529575,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00046431025093750613,
|
|
"loss": 5.0833,
|
|
"mean_token_accuracy": 0.18365292400121688,
|
|
"num_tokens": 41920719.0,
|
|
"step": 19130
|
|
},
|
|
{
|
|
"entropy": 5.597641515731811,
|
|
"epoch": 1.8990670901151252,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.00046429109979051367,
|
|
"loss": 5.1212,
|
|
"mean_token_accuracy": 0.16393977999687195,
|
|
"num_tokens": 41931630.0,
|
|
"step": 19135
|
|
},
|
|
{
|
|
"entropy": 5.574547672271729,
|
|
"epoch": 1.8995633187772927,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00046427194394950985,
|
|
"loss": 5.1501,
|
|
"mean_token_accuracy": 0.1732749342918396,
|
|
"num_tokens": 41943076.0,
|
|
"step": 19140
|
|
},
|
|
{
|
|
"entropy": 5.592162847518921,
|
|
"epoch": 1.9000595474394602,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004642527834149696,
|
|
"loss": 5.0451,
|
|
"mean_token_accuracy": 0.17585303485393525,
|
|
"num_tokens": 41954294.0,
|
|
"step": 19145
|
|
},
|
|
{
|
|
"entropy": 5.541206645965576,
|
|
"epoch": 1.9005557761016276,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00046423361818736814,
|
|
"loss": 5.0446,
|
|
"mean_token_accuracy": 0.17360924184322357,
|
|
"num_tokens": 41964943.0,
|
|
"step": 19150
|
|
},
|
|
{
|
|
"entropy": 5.504830980300904,
|
|
"epoch": 1.901052004763795,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004642144482671807,
|
|
"loss": 5.0784,
|
|
"mean_token_accuracy": 0.17577015608549118,
|
|
"num_tokens": 41975211.0,
|
|
"step": 19155
|
|
},
|
|
{
|
|
"entropy": 5.558339405059814,
|
|
"epoch": 1.9015482334259626,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.00046419527365488275,
|
|
"loss": 5.0883,
|
|
"mean_token_accuracy": 0.17465862333774568,
|
|
"num_tokens": 41986492.0,
|
|
"step": 19160
|
|
},
|
|
{
|
|
"entropy": 5.530906438827515,
|
|
"epoch": 1.90204446208813,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004641760943509496,
|
|
"loss": 5.0697,
|
|
"mean_token_accuracy": 0.17716875225305556,
|
|
"num_tokens": 41997613.0,
|
|
"step": 19165
|
|
},
|
|
{
|
|
"entropy": 5.547230434417725,
|
|
"epoch": 1.9025406907502977,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.000464156910355857,
|
|
"loss": 5.1404,
|
|
"mean_token_accuracy": 0.16788488924503325,
|
|
"num_tokens": 42008597.0,
|
|
"step": 19170
|
|
},
|
|
{
|
|
"entropy": 5.544430875778199,
|
|
"epoch": 1.9030369194124652,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.00046413772167008057,
|
|
"loss": 5.1206,
|
|
"mean_token_accuracy": 0.17881128191947937,
|
|
"num_tokens": 42019698.0,
|
|
"step": 19175
|
|
},
|
|
{
|
|
"entropy": 5.563129472732544,
|
|
"epoch": 1.903533148074633,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00046411852829409626,
|
|
"loss": 5.0122,
|
|
"mean_token_accuracy": 0.17747138440608978,
|
|
"num_tokens": 42029473.0,
|
|
"step": 19180
|
|
},
|
|
{
|
|
"entropy": 5.5570985794067385,
|
|
"epoch": 1.9040293767368004,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00046409933022837984,
|
|
"loss": 5.1532,
|
|
"mean_token_accuracy": 0.17229220420122146,
|
|
"num_tokens": 42041494.0,
|
|
"step": 19185
|
|
},
|
|
{
|
|
"entropy": 5.57109317779541,
|
|
"epoch": 1.9045256053989679,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004640801274734076,
|
|
"loss": 5.1121,
|
|
"mean_token_accuracy": 0.17497511059045792,
|
|
"num_tokens": 42051798.0,
|
|
"step": 19190
|
|
},
|
|
{
|
|
"entropy": 5.569985723495483,
|
|
"epoch": 1.9050218340611353,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004640609200296557,
|
|
"loss": 5.0381,
|
|
"mean_token_accuracy": 0.17674174457788466,
|
|
"num_tokens": 42061802.0,
|
|
"step": 19195
|
|
},
|
|
{
|
|
"entropy": 5.5907776832580565,
|
|
"epoch": 1.9055180627233028,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004640417078976003,
|
|
"loss": 5.1602,
|
|
"mean_token_accuracy": 0.16748594790697097,
|
|
"num_tokens": 42071503.0,
|
|
"step": 19200
|
|
},
|
|
{
|
|
"entropy": 5.445274019241333,
|
|
"epoch": 1.9060142913854703,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004640224910777179,
|
|
"loss": 5.0066,
|
|
"mean_token_accuracy": 0.1784880205988884,
|
|
"num_tokens": 42082104.0,
|
|
"step": 19205
|
|
},
|
|
{
|
|
"entropy": 5.5312236785888675,
|
|
"epoch": 1.906510520047638,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.000464003269570485,
|
|
"loss": 5.0701,
|
|
"mean_token_accuracy": 0.17583508640527726,
|
|
"num_tokens": 42092798.0,
|
|
"step": 19210
|
|
},
|
|
{
|
|
"entropy": 5.574150419235229,
|
|
"epoch": 1.9070067487098055,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004639840433763783,
|
|
"loss": 5.1179,
|
|
"mean_token_accuracy": 0.1736740291118622,
|
|
"num_tokens": 42103062.0,
|
|
"step": 19215
|
|
},
|
|
{
|
|
"entropy": 5.599778842926026,
|
|
"epoch": 1.9075029773719732,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00046396481249587454,
|
|
"loss": 5.1575,
|
|
"mean_token_accuracy": 0.17718523293733596,
|
|
"num_tokens": 42115062.0,
|
|
"step": 19220
|
|
},
|
|
{
|
|
"entropy": 5.651457977294922,
|
|
"epoch": 1.9079992060341406,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004639455769294506,
|
|
"loss": 5.1511,
|
|
"mean_token_accuracy": 0.17218709439039231,
|
|
"num_tokens": 42125937.0,
|
|
"step": 19225
|
|
},
|
|
{
|
|
"entropy": 5.579854249954224,
|
|
"epoch": 1.9084954346963081,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004639263366775835,
|
|
"loss": 5.0857,
|
|
"mean_token_accuracy": 0.17947132289409637,
|
|
"num_tokens": 42136916.0,
|
|
"step": 19230
|
|
},
|
|
{
|
|
"entropy": 5.60452446937561,
|
|
"epoch": 1.9089916633584756,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00046390709174075036,
|
|
"loss": 5.1483,
|
|
"mean_token_accuracy": 0.16964043527841569,
|
|
"num_tokens": 42148348.0,
|
|
"step": 19235
|
|
},
|
|
{
|
|
"entropy": 5.621536302566528,
|
|
"epoch": 1.909487892020643,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004638878421194284,
|
|
"loss": 5.0551,
|
|
"mean_token_accuracy": 0.1832812622189522,
|
|
"num_tokens": 42157586.0,
|
|
"step": 19240
|
|
},
|
|
{
|
|
"entropy": 5.566982412338257,
|
|
"epoch": 1.9099841206828105,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.000463868587814095,
|
|
"loss": 5.1245,
|
|
"mean_token_accuracy": 0.16906868666410446,
|
|
"num_tokens": 42169536.0,
|
|
"step": 19245
|
|
},
|
|
{
|
|
"entropy": 5.4944923400878904,
|
|
"epoch": 1.910480349344978,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004638493288252276,
|
|
"loss": 5.0521,
|
|
"mean_token_accuracy": 0.1763198718428612,
|
|
"num_tokens": 42180024.0,
|
|
"step": 19250
|
|
},
|
|
{
|
|
"entropy": 5.565520906448365,
|
|
"epoch": 1.9109765780071457,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00046383006515330374,
|
|
"loss": 5.0623,
|
|
"mean_token_accuracy": 0.1832951694726944,
|
|
"num_tokens": 42191070.0,
|
|
"step": 19255
|
|
},
|
|
{
|
|
"entropy": 5.570163774490356,
|
|
"epoch": 1.9114728066693132,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004638107967988012,
|
|
"loss": 5.115,
|
|
"mean_token_accuracy": 0.17710933834314346,
|
|
"num_tokens": 42203643.0,
|
|
"step": 19260
|
|
},
|
|
{
|
|
"entropy": 5.5978234767913815,
|
|
"epoch": 1.9119690353314809,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00046379152376219775,
|
|
"loss": 5.1622,
|
|
"mean_token_accuracy": 0.17120399177074433,
|
|
"num_tokens": 42214979.0,
|
|
"step": 19265
|
|
},
|
|
{
|
|
"entropy": 5.677051115036011,
|
|
"epoch": 1.9124652639936484,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00046377224604397127,
|
|
"loss": 5.1499,
|
|
"mean_token_accuracy": 0.17099551260471343,
|
|
"num_tokens": 42225152.0,
|
|
"step": 19270
|
|
},
|
|
{
|
|
"entropy": 5.624697017669678,
|
|
"epoch": 1.9129614926558158,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004637529636445998,
|
|
"loss": 5.0693,
|
|
"mean_token_accuracy": 0.1809826523065567,
|
|
"num_tokens": 42235151.0,
|
|
"step": 19275
|
|
},
|
|
{
|
|
"entropy": 5.546418952941894,
|
|
"epoch": 1.9134577213179833,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004637336765645617,
|
|
"loss": 5.0656,
|
|
"mean_token_accuracy": 0.1829977810382843,
|
|
"num_tokens": 42245419.0,
|
|
"step": 19280
|
|
},
|
|
{
|
|
"entropy": 5.508101892471314,
|
|
"epoch": 1.9139539499801508,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00046371438480433504,
|
|
"loss": 5.0482,
|
|
"mean_token_accuracy": 0.17987146526575087,
|
|
"num_tokens": 42255836.0,
|
|
"step": 19285
|
|
},
|
|
{
|
|
"entropy": 5.5303544998168945,
|
|
"epoch": 1.9144501786423183,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004636950883643983,
|
|
"loss": 5.1416,
|
|
"mean_token_accuracy": 0.17315745651721953,
|
|
"num_tokens": 42267490.0,
|
|
"step": 19290
|
|
},
|
|
{
|
|
"entropy": 5.603589725494385,
|
|
"epoch": 1.914946407304486,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00046367578724523,
|
|
"loss": 5.0997,
|
|
"mean_token_accuracy": 0.17101542502641678,
|
|
"num_tokens": 42276957.0,
|
|
"step": 19295
|
|
},
|
|
{
|
|
"entropy": 5.602015352249145,
|
|
"epoch": 1.9154426359666534,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004636564814473087,
|
|
"loss": 4.979,
|
|
"mean_token_accuracy": 0.18534846901893615,
|
|
"num_tokens": 42288469.0,
|
|
"step": 19300
|
|
},
|
|
{
|
|
"entropy": 5.541460561752319,
|
|
"epoch": 1.9159388646288211,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004636371709711131,
|
|
"loss": 5.0443,
|
|
"mean_token_accuracy": 0.18952454775571823,
|
|
"num_tokens": 42299141.0,
|
|
"step": 19305
|
|
},
|
|
{
|
|
"entropy": 5.529378271102905,
|
|
"epoch": 1.9164350932909886,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00046361785581712224,
|
|
"loss": 5.1296,
|
|
"mean_token_accuracy": 0.17912334352731704,
|
|
"num_tokens": 42310651.0,
|
|
"step": 19310
|
|
},
|
|
{
|
|
"entropy": 5.513909864425659,
|
|
"epoch": 1.916931321953156,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000463598535985815,
|
|
"loss": 4.9541,
|
|
"mean_token_accuracy": 0.19018761366605758,
|
|
"num_tokens": 42320529.0,
|
|
"step": 19315
|
|
},
|
|
{
|
|
"entropy": 5.556969070434571,
|
|
"epoch": 1.9174275506153236,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004635792114776704,
|
|
"loss": 5.0079,
|
|
"mean_token_accuracy": 0.18231214135885238,
|
|
"num_tokens": 42331216.0,
|
|
"step": 19320
|
|
},
|
|
{
|
|
"entropy": 5.490019845962524,
|
|
"epoch": 1.917923779277491,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004635598822931677,
|
|
"loss": 5.0202,
|
|
"mean_token_accuracy": 0.18094714879989623,
|
|
"num_tokens": 42341730.0,
|
|
"step": 19325
|
|
},
|
|
{
|
|
"entropy": 5.572424507141113,
|
|
"epoch": 1.9184200079396585,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00046354054843278624,
|
|
"loss": 5.1173,
|
|
"mean_token_accuracy": 0.1721300482749939,
|
|
"num_tokens": 42352643.0,
|
|
"step": 19330
|
|
},
|
|
{
|
|
"entropy": 5.626467752456665,
|
|
"epoch": 1.918916236601826,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00046352120989700553,
|
|
"loss": 5.1645,
|
|
"mean_token_accuracy": 0.16845486909151078,
|
|
"num_tokens": 42363979.0,
|
|
"step": 19335
|
|
},
|
|
{
|
|
"entropy": 5.629286670684815,
|
|
"epoch": 1.9194124652639937,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000463501866686305,
|
|
"loss": 5.105,
|
|
"mean_token_accuracy": 0.1746789187192917,
|
|
"num_tokens": 42374104.0,
|
|
"step": 19340
|
|
},
|
|
{
|
|
"entropy": 5.61504340171814,
|
|
"epoch": 1.9199086939261611,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00046348251880116433,
|
|
"loss": 5.0956,
|
|
"mean_token_accuracy": 0.17424288243055344,
|
|
"num_tokens": 42383576.0,
|
|
"step": 19345
|
|
},
|
|
{
|
|
"entropy": 5.573254346847534,
|
|
"epoch": 1.9204049225883288,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00046346316624206325,
|
|
"loss": 5.1033,
|
|
"mean_token_accuracy": 0.1774061381816864,
|
|
"num_tokens": 42394625.0,
|
|
"step": 19350
|
|
},
|
|
{
|
|
"entropy": 5.543413782119751,
|
|
"epoch": 1.9209011512504963,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004634438090094819,
|
|
"loss": 5.0496,
|
|
"mean_token_accuracy": 0.17962605953216554,
|
|
"num_tokens": 42404764.0,
|
|
"step": 19355
|
|
},
|
|
{
|
|
"entropy": 5.584619140625,
|
|
"epoch": 1.9213973799126638,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00046342444710390006,
|
|
"loss": 5.0269,
|
|
"mean_token_accuracy": 0.17842495441436768,
|
|
"num_tokens": 42414386.0,
|
|
"step": 19360
|
|
},
|
|
{
|
|
"entropy": 5.570868921279907,
|
|
"epoch": 1.9218936085748313,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.000463405080525798,
|
|
"loss": 5.1242,
|
|
"mean_token_accuracy": 0.17460551410913466,
|
|
"num_tokens": 42425671.0,
|
|
"step": 19365
|
|
},
|
|
{
|
|
"entropy": 5.583004426956177,
|
|
"epoch": 1.9223898372369987,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004633857092756559,
|
|
"loss": 5.1392,
|
|
"mean_token_accuracy": 0.16956614702939987,
|
|
"num_tokens": 42436365.0,
|
|
"step": 19370
|
|
},
|
|
{
|
|
"entropy": 5.547567653656006,
|
|
"epoch": 1.9228860658991662,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004633663333539542,
|
|
"loss": 5.0038,
|
|
"mean_token_accuracy": 0.1752679243683815,
|
|
"num_tokens": 42447624.0,
|
|
"step": 19375
|
|
},
|
|
{
|
|
"entropy": 5.629079103469849,
|
|
"epoch": 1.923382294561334,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00046334695276117324,
|
|
"loss": 5.1018,
|
|
"mean_token_accuracy": 0.1740894228219986,
|
|
"num_tokens": 42458013.0,
|
|
"step": 19380
|
|
},
|
|
{
|
|
"entropy": 5.59863395690918,
|
|
"epoch": 1.9238785232235014,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004633275674977937,
|
|
"loss": 5.1276,
|
|
"mean_token_accuracy": 0.16924300342798232,
|
|
"num_tokens": 42469807.0,
|
|
"step": 19385
|
|
},
|
|
{
|
|
"entropy": 5.503483772277832,
|
|
"epoch": 1.9243747518856689,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004633081775642964,
|
|
"loss": 5.0564,
|
|
"mean_token_accuracy": 0.17505667060613633,
|
|
"num_tokens": 42479240.0,
|
|
"step": 19390
|
|
},
|
|
{
|
|
"entropy": 5.5568524360656735,
|
|
"epoch": 1.9248709805478366,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00046328878296116196,
|
|
"loss": 5.118,
|
|
"mean_token_accuracy": 0.17725289314985276,
|
|
"num_tokens": 42489558.0,
|
|
"step": 19395
|
|
},
|
|
{
|
|
"entropy": 5.608658218383789,
|
|
"epoch": 1.925367209210004,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00046326938368887146,
|
|
"loss": 5.1321,
|
|
"mean_token_accuracy": 0.17715611010789872,
|
|
"num_tokens": 42501252.0,
|
|
"step": 19400
|
|
},
|
|
{
|
|
"entropy": 5.625342082977295,
|
|
"epoch": 1.9258634378721715,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.00046324997974790596,
|
|
"loss": 5.1558,
|
|
"mean_token_accuracy": 0.1770201161503792,
|
|
"num_tokens": 42512330.0,
|
|
"step": 19405
|
|
},
|
|
{
|
|
"entropy": 5.582589769363404,
|
|
"epoch": 1.926359666534339,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004632305711387466,
|
|
"loss": 5.1488,
|
|
"mean_token_accuracy": 0.17336562871932984,
|
|
"num_tokens": 42525216.0,
|
|
"step": 19410
|
|
},
|
|
{
|
|
"entropy": 5.603672742843628,
|
|
"epoch": 1.9268558951965065,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00046321115786187466,
|
|
"loss": 5.0941,
|
|
"mean_token_accuracy": 0.17508437484502792,
|
|
"num_tokens": 42537047.0,
|
|
"step": 19415
|
|
},
|
|
{
|
|
"entropy": 5.593495798110962,
|
|
"epoch": 1.927352123858674,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00046319173991777153,
|
|
"loss": 5.0749,
|
|
"mean_token_accuracy": 0.17257878929376602,
|
|
"num_tokens": 42549784.0,
|
|
"step": 19420
|
|
},
|
|
{
|
|
"entropy": 5.562648630142212,
|
|
"epoch": 1.9278483525208416,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004631723173069188,
|
|
"loss": 5.0714,
|
|
"mean_token_accuracy": 0.17260258197784423,
|
|
"num_tokens": 42561079.0,
|
|
"step": 19425
|
|
},
|
|
{
|
|
"entropy": 5.558985090255737,
|
|
"epoch": 1.928344581183009,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004631528900297981,
|
|
"loss": 5.1354,
|
|
"mean_token_accuracy": 0.17199122309684753,
|
|
"num_tokens": 42572531.0,
|
|
"step": 19430
|
|
},
|
|
{
|
|
"entropy": 5.562539577484131,
|
|
"epoch": 1.9288408098451768,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00046313345808689113,
|
|
"loss": 5.0504,
|
|
"mean_token_accuracy": 0.1781085506081581,
|
|
"num_tokens": 42583836.0,
|
|
"step": 19435
|
|
},
|
|
{
|
|
"entropy": 5.622388315200806,
|
|
"epoch": 1.9293370385073443,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004631140214786798,
|
|
"loss": 5.1592,
|
|
"mean_token_accuracy": 0.17296061366796495,
|
|
"num_tokens": 42595338.0,
|
|
"step": 19440
|
|
},
|
|
{
|
|
"entropy": 5.5818993091583256,
|
|
"epoch": 1.9298332671695118,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00046309458020564606,
|
|
"loss": 5.0962,
|
|
"mean_token_accuracy": 0.17329725325107576,
|
|
"num_tokens": 42606804.0,
|
|
"step": 19445
|
|
},
|
|
{
|
|
"entropy": 5.544586896896362,
|
|
"epoch": 1.9303294958316792,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00046307513426827214,
|
|
"loss": 5.0295,
|
|
"mean_token_accuracy": 0.18118116408586502,
|
|
"num_tokens": 42616987.0,
|
|
"step": 19450
|
|
},
|
|
{
|
|
"entropy": 5.569060659408569,
|
|
"epoch": 1.9308257244938467,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00046305568366704006,
|
|
"loss": 5.1048,
|
|
"mean_token_accuracy": 0.1745738834142685,
|
|
"num_tokens": 42627633.0,
|
|
"step": 19455
|
|
},
|
|
{
|
|
"entropy": 5.592783117294312,
|
|
"epoch": 1.9313219531560142,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004630362284024322,
|
|
"loss": 5.0653,
|
|
"mean_token_accuracy": 0.1722562924027443,
|
|
"num_tokens": 42638802.0,
|
|
"step": 19460
|
|
},
|
|
{
|
|
"entropy": 5.5772136688232425,
|
|
"epoch": 1.9318181818181817,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00046301676847493116,
|
|
"loss": 5.061,
|
|
"mean_token_accuracy": 0.1808040753006935,
|
|
"num_tokens": 42650802.0,
|
|
"step": 19465
|
|
},
|
|
{
|
|
"entropy": 5.551653146743774,
|
|
"epoch": 1.9323144104803494,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00046299730388501935,
|
|
"loss": 5.032,
|
|
"mean_token_accuracy": 0.1813851073384285,
|
|
"num_tokens": 42660290.0,
|
|
"step": 19470
|
|
},
|
|
{
|
|
"entropy": 5.590027475357056,
|
|
"epoch": 1.9328106391425168,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.00046297783463317957,
|
|
"loss": 5.1203,
|
|
"mean_token_accuracy": 0.17696295827627181,
|
|
"num_tokens": 42671182.0,
|
|
"step": 19475
|
|
},
|
|
{
|
|
"entropy": 5.60194354057312,
|
|
"epoch": 1.9333068678046845,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004629583607198945,
|
|
"loss": 5.1239,
|
|
"mean_token_accuracy": 0.17695219218730926,
|
|
"num_tokens": 42682499.0,
|
|
"step": 19480
|
|
},
|
|
{
|
|
"entropy": 5.540981197357178,
|
|
"epoch": 1.933803096466852,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00046293888214564704,
|
|
"loss": 5.1313,
|
|
"mean_token_accuracy": 0.17261911928653717,
|
|
"num_tokens": 42693728.0,
|
|
"step": 19485
|
|
},
|
|
{
|
|
"entropy": 5.573365783691406,
|
|
"epoch": 1.9342993251290195,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00046291939891092036,
|
|
"loss": 5.1155,
|
|
"mean_token_accuracy": 0.1752532184123993,
|
|
"num_tokens": 42704877.0,
|
|
"step": 19490
|
|
},
|
|
{
|
|
"entropy": 5.617432928085327,
|
|
"epoch": 1.934795553791187,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004628999110161975,
|
|
"loss": 5.1425,
|
|
"mean_token_accuracy": 0.16973139494657516,
|
|
"num_tokens": 42715787.0,
|
|
"step": 19495
|
|
},
|
|
{
|
|
"entropy": 5.596118021011352,
|
|
"epoch": 1.9352917824533544,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00046288041846196174,
|
|
"loss": 5.1041,
|
|
"mean_token_accuracy": 0.1750999927520752,
|
|
"num_tokens": 42727557.0,
|
|
"step": 19500
|
|
},
|
|
{
|
|
"entropy": 5.606228828430176,
|
|
"epoch": 1.935788011115522,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00046286092124869647,
|
|
"loss": 5.1045,
|
|
"mean_token_accuracy": 0.17468319982290267,
|
|
"num_tokens": 42737540.0,
|
|
"step": 19505
|
|
},
|
|
{
|
|
"entropy": 5.637428569793701,
|
|
"epoch": 1.9362842397776896,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00046284141937688513,
|
|
"loss": 5.1319,
|
|
"mean_token_accuracy": 0.1786578565835953,
|
|
"num_tokens": 42748716.0,
|
|
"step": 19510
|
|
},
|
|
{
|
|
"entropy": 5.673902893066407,
|
|
"epoch": 1.936780468439857,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00046282191284701123,
|
|
"loss": 5.1662,
|
|
"mean_token_accuracy": 0.17017856389284133,
|
|
"num_tokens": 42758991.0,
|
|
"step": 19515
|
|
},
|
|
{
|
|
"entropy": 5.653537130355835,
|
|
"epoch": 1.9372766971020248,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004628024016595587,
|
|
"loss": 5.1422,
|
|
"mean_token_accuracy": 0.1710558831691742,
|
|
"num_tokens": 42771105.0,
|
|
"step": 19520
|
|
},
|
|
{
|
|
"entropy": 5.55591344833374,
|
|
"epoch": 1.9377729257641922,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.00046278288581501136,
|
|
"loss": 5.103,
|
|
"mean_token_accuracy": 0.17486774027347565,
|
|
"num_tokens": 42783317.0,
|
|
"step": 19525
|
|
},
|
|
{
|
|
"entropy": 5.652013731002808,
|
|
"epoch": 1.9382691544263597,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.00046276336531385305,
|
|
"loss": 5.2283,
|
|
"mean_token_accuracy": 0.1676255762577057,
|
|
"num_tokens": 42794998.0,
|
|
"step": 19530
|
|
},
|
|
{
|
|
"entropy": 5.6051544666290285,
|
|
"epoch": 1.9387653830885272,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00046274384015656785,
|
|
"loss": 5.1016,
|
|
"mean_token_accuracy": 0.18168456107378006,
|
|
"num_tokens": 42806197.0,
|
|
"step": 19535
|
|
},
|
|
{
|
|
"entropy": 5.53239369392395,
|
|
"epoch": 1.9392616117506947,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00046272431034363997,
|
|
"loss": 5.002,
|
|
"mean_token_accuracy": 0.17452119886875153,
|
|
"num_tokens": 42816522.0,
|
|
"step": 19540
|
|
},
|
|
{
|
|
"entropy": 5.553054761886597,
|
|
"epoch": 1.9397578404128621,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004627047758755538,
|
|
"loss": 5.0123,
|
|
"mean_token_accuracy": 0.18434111177921295,
|
|
"num_tokens": 42826003.0,
|
|
"step": 19545
|
|
},
|
|
{
|
|
"entropy": 5.59314866065979,
|
|
"epoch": 1.9402540690750296,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004626852367527935,
|
|
"loss": 5.1002,
|
|
"mean_token_accuracy": 0.17019644677639006,
|
|
"num_tokens": 42836346.0,
|
|
"step": 19550
|
|
},
|
|
{
|
|
"entropy": 5.5753350257873535,
|
|
"epoch": 1.9407502977371973,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004626656929758438,
|
|
"loss": 5.1586,
|
|
"mean_token_accuracy": 0.17343145310878755,
|
|
"num_tokens": 42846296.0,
|
|
"step": 19555
|
|
},
|
|
{
|
|
"entropy": 5.672791290283203,
|
|
"epoch": 1.9412465263993648,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004626461445451894,
|
|
"loss": 5.1485,
|
|
"mean_token_accuracy": 0.17419494092464446,
|
|
"num_tokens": 42856323.0,
|
|
"step": 19560
|
|
},
|
|
{
|
|
"entropy": 5.6711437702178955,
|
|
"epoch": 1.9417427550615325,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004626265914613149,
|
|
"loss": 5.1654,
|
|
"mean_token_accuracy": 0.1695869415998459,
|
|
"num_tokens": 42866937.0,
|
|
"step": 19565
|
|
},
|
|
{
|
|
"entropy": 5.593677425384522,
|
|
"epoch": 1.9422389837237,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004626070337247052,
|
|
"loss": 5.1287,
|
|
"mean_token_accuracy": 0.1693687006831169,
|
|
"num_tokens": 42877194.0,
|
|
"step": 19570
|
|
},
|
|
{
|
|
"entropy": 5.594156122207641,
|
|
"epoch": 1.9427352123858674,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004625874713358453,
|
|
"loss": 5.129,
|
|
"mean_token_accuracy": 0.17129995226860045,
|
|
"num_tokens": 42887741.0,
|
|
"step": 19575
|
|
},
|
|
{
|
|
"entropy": 5.572790956497192,
|
|
"epoch": 1.943231441048035,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00046256790429522035,
|
|
"loss": 5.1079,
|
|
"mean_token_accuracy": 0.18464816659688948,
|
|
"num_tokens": 42898195.0,
|
|
"step": 19580
|
|
},
|
|
{
|
|
"entropy": 5.655848360061645,
|
|
"epoch": 1.9437276697102024,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004625483326033155,
|
|
"loss": 5.149,
|
|
"mean_token_accuracy": 0.17260519415140152,
|
|
"num_tokens": 42908852.0,
|
|
"step": 19585
|
|
},
|
|
{
|
|
"entropy": 5.556072950363159,
|
|
"epoch": 1.9442238983723699,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004625287562606162,
|
|
"loss": 5.0419,
|
|
"mean_token_accuracy": 0.1763271987438202,
|
|
"num_tokens": 42920166.0,
|
|
"step": 19590
|
|
},
|
|
{
|
|
"entropy": 5.607384920120239,
|
|
"epoch": 1.9447201270345376,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004625091752676078,
|
|
"loss": 5.1226,
|
|
"mean_token_accuracy": 0.1745381087064743,
|
|
"num_tokens": 42931677.0,
|
|
"step": 19595
|
|
},
|
|
{
|
|
"entropy": 5.584395074844361,
|
|
"epoch": 1.945216355696705,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000462489589624776,
|
|
"loss": 5.107,
|
|
"mean_token_accuracy": 0.17392319291830063,
|
|
"num_tokens": 42942346.0,
|
|
"step": 19600
|
|
},
|
|
{
|
|
"entropy": 5.475983476638794,
|
|
"epoch": 1.9457125843588727,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004624699993326063,
|
|
"loss": 5.0702,
|
|
"mean_token_accuracy": 0.1802891030907631,
|
|
"num_tokens": 42953821.0,
|
|
"step": 19605
|
|
},
|
|
{
|
|
"entropy": 5.543852710723877,
|
|
"epoch": 1.9462088130210402,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00046245040439158456,
|
|
"loss": 5.0678,
|
|
"mean_token_accuracy": 0.17612649202346803,
|
|
"num_tokens": 42964358.0,
|
|
"step": 19610
|
|
},
|
|
{
|
|
"entropy": 5.573706245422363,
|
|
"epoch": 1.9467050416832077,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.00046243080480219673,
|
|
"loss": 5.0572,
|
|
"mean_token_accuracy": 0.17840345799922944,
|
|
"num_tokens": 42976459.0,
|
|
"step": 19615
|
|
},
|
|
{
|
|
"entropy": 5.641165781021118,
|
|
"epoch": 1.9472012703453752,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004624112005649288,
|
|
"loss": 5.2039,
|
|
"mean_token_accuracy": 0.16884401738643645,
|
|
"num_tokens": 42988603.0,
|
|
"step": 19620
|
|
},
|
|
{
|
|
"entropy": 5.568244600296021,
|
|
"epoch": 1.9476974990075426,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00046239159168026694,
|
|
"loss": 5.1193,
|
|
"mean_token_accuracy": 0.1738400474190712,
|
|
"num_tokens": 43000262.0,
|
|
"step": 19625
|
|
},
|
|
{
|
|
"entropy": 5.521918392181396,
|
|
"epoch": 1.94819372766971,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0004623719781486974,
|
|
"loss": 5.0561,
|
|
"mean_token_accuracy": 0.1762985348701477,
|
|
"num_tokens": 43009363.0,
|
|
"step": 19630
|
|
},
|
|
{
|
|
"entropy": 5.628265619277954,
|
|
"epoch": 1.9486899563318776,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00046235235997070664,
|
|
"loss": 5.1252,
|
|
"mean_token_accuracy": 0.17919848263263702,
|
|
"num_tokens": 43019893.0,
|
|
"step": 19635
|
|
},
|
|
{
|
|
"entropy": 5.5354039669036865,
|
|
"epoch": 1.9491861849940453,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.000462332737146781,
|
|
"loss": 5.0287,
|
|
"mean_token_accuracy": 0.18238697797060013,
|
|
"num_tokens": 43031152.0,
|
|
"step": 19640
|
|
},
|
|
{
|
|
"entropy": 5.574510145187378,
|
|
"epoch": 1.9496824136562128,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004623131096774071,
|
|
"loss": 5.1669,
|
|
"mean_token_accuracy": 0.170855288207531,
|
|
"num_tokens": 43041247.0,
|
|
"step": 19645
|
|
},
|
|
{
|
|
"entropy": 5.628740358352661,
|
|
"epoch": 1.9501786423183805,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004622934775630717,
|
|
"loss": 5.0827,
|
|
"mean_token_accuracy": 0.17058514654636384,
|
|
"num_tokens": 43052065.0,
|
|
"step": 19650
|
|
},
|
|
{
|
|
"entropy": 5.5691609382629395,
|
|
"epoch": 1.950674870980548,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.00046227384080426163,
|
|
"loss": 5.12,
|
|
"mean_token_accuracy": 0.17122100442647933,
|
|
"num_tokens": 43063217.0,
|
|
"step": 19655
|
|
},
|
|
{
|
|
"entropy": 5.553304052352905,
|
|
"epoch": 1.9511710996427154,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004622541994014639,
|
|
"loss": 5.1243,
|
|
"mean_token_accuracy": 0.1771386981010437,
|
|
"num_tokens": 43074463.0,
|
|
"step": 19660
|
|
},
|
|
{
|
|
"entropy": 5.691059684753418,
|
|
"epoch": 1.9516673283048829,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004622345533551655,
|
|
"loss": 5.1616,
|
|
"mean_token_accuracy": 0.16897969990968703,
|
|
"num_tokens": 43086004.0,
|
|
"step": 19665
|
|
},
|
|
{
|
|
"entropy": 5.620903253555298,
|
|
"epoch": 1.9521635569670504,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004622149026658537,
|
|
"loss": 5.0595,
|
|
"mean_token_accuracy": 0.18073871582746506,
|
|
"num_tokens": 43096973.0,
|
|
"step": 19670
|
|
},
|
|
{
|
|
"entropy": 5.6457103252410885,
|
|
"epoch": 1.9526597856292178,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004621952473340156,
|
|
"loss": 5.1584,
|
|
"mean_token_accuracy": 0.1755485862493515,
|
|
"num_tokens": 43107337.0,
|
|
"step": 19675
|
|
},
|
|
{
|
|
"entropy": 5.611739778518677,
|
|
"epoch": 1.9531560142913855,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004621755873601388,
|
|
"loss": 5.0806,
|
|
"mean_token_accuracy": 0.18096780627965928,
|
|
"num_tokens": 43118668.0,
|
|
"step": 19680
|
|
},
|
|
{
|
|
"entropy": 5.654886245727539,
|
|
"epoch": 1.953652242953553,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004621559227447108,
|
|
"loss": 5.1876,
|
|
"mean_token_accuracy": 0.1683372363448143,
|
|
"num_tokens": 43129030.0,
|
|
"step": 19685
|
|
},
|
|
{
|
|
"entropy": 5.520848894119263,
|
|
"epoch": 1.9541484716157205,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004621362534882192,
|
|
"loss": 5.0365,
|
|
"mean_token_accuracy": 0.1843307673931122,
|
|
"num_tokens": 43139120.0,
|
|
"step": 19690
|
|
},
|
|
{
|
|
"entropy": 5.572016954421997,
|
|
"epoch": 1.9546447002778882,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004621165795911517,
|
|
"loss": 5.122,
|
|
"mean_token_accuracy": 0.17558340430259706,
|
|
"num_tokens": 43152390.0,
|
|
"step": 19695
|
|
},
|
|
{
|
|
"entropy": 5.554745244979858,
|
|
"epoch": 1.9551409289400556,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00046209690105399623,
|
|
"loss": 4.9344,
|
|
"mean_token_accuracy": 0.18695660680532455,
|
|
"num_tokens": 43162230.0,
|
|
"step": 19700
|
|
},
|
|
{
|
|
"entropy": 5.505560779571534,
|
|
"epoch": 1.9556371576022231,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00046207721787724085,
|
|
"loss": 5.0673,
|
|
"mean_token_accuracy": 0.17772364467382432,
|
|
"num_tokens": 43172751.0,
|
|
"step": 19705
|
|
},
|
|
{
|
|
"entropy": 5.642329216003418,
|
|
"epoch": 1.9561333862643906,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00046205753006137347,
|
|
"loss": 5.152,
|
|
"mean_token_accuracy": 0.1744347706437111,
|
|
"num_tokens": 43183835.0,
|
|
"step": 19710
|
|
},
|
|
{
|
|
"entropy": 5.65907917022705,
|
|
"epoch": 1.956629614926558,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00046203783760688245,
|
|
"loss": 5.0485,
|
|
"mean_token_accuracy": 0.1729263558983803,
|
|
"num_tokens": 43193178.0,
|
|
"step": 19715
|
|
},
|
|
{
|
|
"entropy": 5.583413743972779,
|
|
"epoch": 1.9571258435887255,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004620181405142561,
|
|
"loss": 5.1988,
|
|
"mean_token_accuracy": 0.1671207293868065,
|
|
"num_tokens": 43204968.0,
|
|
"step": 19720
|
|
},
|
|
{
|
|
"entropy": 5.561521339416504,
|
|
"epoch": 1.9576220722508932,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004619984387839829,
|
|
"loss": 5.2202,
|
|
"mean_token_accuracy": 0.16834264099597931,
|
|
"num_tokens": 43214916.0,
|
|
"step": 19725
|
|
},
|
|
{
|
|
"entropy": 5.711319255828857,
|
|
"epoch": 1.9581183009130607,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.00046197873241655133,
|
|
"loss": 5.2134,
|
|
"mean_token_accuracy": 0.16977116018533706,
|
|
"num_tokens": 43226374.0,
|
|
"step": 19730
|
|
},
|
|
{
|
|
"entropy": 5.58314266204834,
|
|
"epoch": 1.9586145295752284,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004619590214124501,
|
|
"loss": 5.0853,
|
|
"mean_token_accuracy": 0.1738823115825653,
|
|
"num_tokens": 43237296.0,
|
|
"step": 19735
|
|
},
|
|
{
|
|
"entropy": 5.66984281539917,
|
|
"epoch": 1.9591107582373959,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00046193930577216797,
|
|
"loss": 5.2423,
|
|
"mean_token_accuracy": 0.1598547577857971,
|
|
"num_tokens": 43248220.0,
|
|
"step": 19740
|
|
},
|
|
{
|
|
"entropy": 5.560368251800537,
|
|
"epoch": 1.9596069868995634,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004619195854961939,
|
|
"loss": 5.0149,
|
|
"mean_token_accuracy": 0.18297584503889083,
|
|
"num_tokens": 43259913.0,
|
|
"step": 19745
|
|
},
|
|
{
|
|
"entropy": 5.622790813446045,
|
|
"epoch": 1.9601032155617308,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.00046189986058501687,
|
|
"loss": 5.1485,
|
|
"mean_token_accuracy": 0.17128514349460602,
|
|
"num_tokens": 43272317.0,
|
|
"step": 19750
|
|
},
|
|
{
|
|
"entropy": 5.491859865188599,
|
|
"epoch": 1.9605994442238983,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000461880131039126,
|
|
"loss": 5.0153,
|
|
"mean_token_accuracy": 0.18247572034597398,
|
|
"num_tokens": 43283170.0,
|
|
"step": 19755
|
|
},
|
|
{
|
|
"entropy": 5.536263084411621,
|
|
"epoch": 1.9610956728860658,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004618603968590107,
|
|
"loss": 5.1072,
|
|
"mean_token_accuracy": 0.17903425693511962,
|
|
"num_tokens": 43293899.0,
|
|
"step": 19760
|
|
},
|
|
{
|
|
"entropy": 5.605640316009522,
|
|
"epoch": 1.9615919015482333,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00046184065804516007,
|
|
"loss": 5.1354,
|
|
"mean_token_accuracy": 0.17757341265678406,
|
|
"num_tokens": 43305638.0,
|
|
"step": 19765
|
|
},
|
|
{
|
|
"entropy": 5.64197883605957,
|
|
"epoch": 1.962088130210401,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004618209145980638,
|
|
"loss": 5.2056,
|
|
"mean_token_accuracy": 0.16710670292377472,
|
|
"num_tokens": 43315900.0,
|
|
"step": 19770
|
|
},
|
|
{
|
|
"entropy": 5.67323489189148,
|
|
"epoch": 1.9625843588725684,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004618011665182114,
|
|
"loss": 5.272,
|
|
"mean_token_accuracy": 0.1656080037355423,
|
|
"num_tokens": 43328464.0,
|
|
"step": 19775
|
|
},
|
|
{
|
|
"entropy": 5.53949465751648,
|
|
"epoch": 1.9630805875347361,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004617814138060926,
|
|
"loss": 4.9582,
|
|
"mean_token_accuracy": 0.18672350347042083,
|
|
"num_tokens": 43339303.0,
|
|
"step": 19780
|
|
},
|
|
{
|
|
"entropy": 5.621024036407471,
|
|
"epoch": 1.9635768161969036,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004617616564621972,
|
|
"loss": 5.1992,
|
|
"mean_token_accuracy": 0.17171578705310822,
|
|
"num_tokens": 43349269.0,
|
|
"step": 19785
|
|
},
|
|
{
|
|
"entropy": 5.5267102241516115,
|
|
"epoch": 1.964073044859071,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.00046174189448701516,
|
|
"loss": 5.0495,
|
|
"mean_token_accuracy": 0.17921780347824096,
|
|
"num_tokens": 43361090.0,
|
|
"step": 19790
|
|
},
|
|
{
|
|
"entropy": 5.556002187728882,
|
|
"epoch": 1.9645692735212386,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004617221278810365,
|
|
"loss": 5.0389,
|
|
"mean_token_accuracy": 0.174630868434906,
|
|
"num_tokens": 43373448.0,
|
|
"step": 19795
|
|
},
|
|
{
|
|
"entropy": 5.671497583389282,
|
|
"epoch": 1.965065502183406,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00046170235664475147,
|
|
"loss": 5.1783,
|
|
"mean_token_accuracy": 0.17180072665214538,
|
|
"num_tokens": 43386202.0,
|
|
"step": 19800
|
|
},
|
|
{
|
|
"entropy": 5.580495452880859,
|
|
"epoch": 1.9655617308455735,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00046168258077865026,
|
|
"loss": 5.09,
|
|
"mean_token_accuracy": 0.1797773450613022,
|
|
"num_tokens": 43396363.0,
|
|
"step": 19805
|
|
},
|
|
{
|
|
"entropy": 5.556813192367554,
|
|
"epoch": 1.9660579595077412,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004616628002832233,
|
|
"loss": 5.0049,
|
|
"mean_token_accuracy": 0.18110644817352295,
|
|
"num_tokens": 43406076.0,
|
|
"step": 19810
|
|
},
|
|
{
|
|
"entropy": 5.587572956085205,
|
|
"epoch": 1.9665541881699087,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00046164301515896124,
|
|
"loss": 5.1448,
|
|
"mean_token_accuracy": 0.17329322695732116,
|
|
"num_tokens": 43416226.0,
|
|
"step": 19815
|
|
},
|
|
{
|
|
"entropy": 5.553575944900513,
|
|
"epoch": 1.9670504168320764,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004616232254063544,
|
|
"loss": 4.9986,
|
|
"mean_token_accuracy": 0.18101046234369278,
|
|
"num_tokens": 43427364.0,
|
|
"step": 19820
|
|
},
|
|
{
|
|
"entropy": 5.598277282714844,
|
|
"epoch": 1.9675466454942439,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00046160343102589384,
|
|
"loss": 5.1203,
|
|
"mean_token_accuracy": 0.17934240251779557,
|
|
"num_tokens": 43437854.0,
|
|
"step": 19825
|
|
},
|
|
{
|
|
"entropy": 5.573452568054199,
|
|
"epoch": 1.9680428741564113,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004615836320180702,
|
|
"loss": 5.1511,
|
|
"mean_token_accuracy": 0.17664049863815307,
|
|
"num_tokens": 43449370.0,
|
|
"step": 19830
|
|
},
|
|
{
|
|
"entropy": 5.559548044204712,
|
|
"epoch": 1.9685391028185788,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00046156382838337455,
|
|
"loss": 5.0941,
|
|
"mean_token_accuracy": 0.1821209594607353,
|
|
"num_tokens": 43461631.0,
|
|
"step": 19835
|
|
},
|
|
{
|
|
"entropy": 5.607298088073731,
|
|
"epoch": 1.9690353314807463,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00046154402012229807,
|
|
"loss": 5.0927,
|
|
"mean_token_accuracy": 0.17239862084388732,
|
|
"num_tokens": 43472357.0,
|
|
"step": 19840
|
|
},
|
|
{
|
|
"entropy": 5.5414710521698,
|
|
"epoch": 1.9695315601429138,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00046152420723533175,
|
|
"loss": 5.054,
|
|
"mean_token_accuracy": 0.17707743346691132,
|
|
"num_tokens": 43483642.0,
|
|
"step": 19845
|
|
},
|
|
{
|
|
"entropy": 5.6295366287231445,
|
|
"epoch": 1.9700277888050812,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00046150438972296706,
|
|
"loss": 5.1349,
|
|
"mean_token_accuracy": 0.17591917067766188,
|
|
"num_tokens": 43495136.0,
|
|
"step": 19850
|
|
},
|
|
{
|
|
"entropy": 5.552084064483642,
|
|
"epoch": 1.970524017467249,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00046148456758569536,
|
|
"loss": 5.1124,
|
|
"mean_token_accuracy": 0.17267705798149108,
|
|
"num_tokens": 43506376.0,
|
|
"step": 19855
|
|
},
|
|
{
|
|
"entropy": 5.558958959579468,
|
|
"epoch": 1.9710202461294164,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00046146474082400823,
|
|
"loss": 5.0698,
|
|
"mean_token_accuracy": 0.176774001121521,
|
|
"num_tokens": 43516658.0,
|
|
"step": 19860
|
|
},
|
|
{
|
|
"entropy": 5.571771097183228,
|
|
"epoch": 1.971516474791584,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00046144490943839735,
|
|
"loss": 5.0464,
|
|
"mean_token_accuracy": 0.1817093849182129,
|
|
"num_tokens": 43526907.0,
|
|
"step": 19865
|
|
},
|
|
{
|
|
"entropy": 5.655218315124512,
|
|
"epoch": 1.9720127034537516,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004614250734293544,
|
|
"loss": 5.1376,
|
|
"mean_token_accuracy": 0.1728274032473564,
|
|
"num_tokens": 43537739.0,
|
|
"step": 19870
|
|
},
|
|
{
|
|
"entropy": 5.522761249542237,
|
|
"epoch": 1.972508932115919,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00046140523279737146,
|
|
"loss": 5.0943,
|
|
"mean_token_accuracy": 0.17799045890569687,
|
|
"num_tokens": 43549240.0,
|
|
"step": 19875
|
|
},
|
|
{
|
|
"entropy": 5.570582914352417,
|
|
"epoch": 1.9730051607780865,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004613853875429403,
|
|
"loss": 5.0538,
|
|
"mean_token_accuracy": 0.17478798627853392,
|
|
"num_tokens": 43559857.0,
|
|
"step": 19880
|
|
},
|
|
{
|
|
"entropy": 5.538764190673828,
|
|
"epoch": 1.973501389440254,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004613655376665532,
|
|
"loss": 5.042,
|
|
"mean_token_accuracy": 0.1760262057185173,
|
|
"num_tokens": 43570262.0,
|
|
"step": 19885
|
|
},
|
|
{
|
|
"entropy": 5.63384780883789,
|
|
"epoch": 1.9739976181024215,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004613456831687024,
|
|
"loss": 5.1151,
|
|
"mean_token_accuracy": 0.17173005193471907,
|
|
"num_tokens": 43581965.0,
|
|
"step": 19890
|
|
},
|
|
{
|
|
"entropy": 5.562789487838745,
|
|
"epoch": 1.9744938467645892,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00046132582404988004,
|
|
"loss": 5.0769,
|
|
"mean_token_accuracy": 0.17880486696958542,
|
|
"num_tokens": 43592728.0,
|
|
"step": 19895
|
|
},
|
|
{
|
|
"entropy": 5.594052314758301,
|
|
"epoch": 1.9749900754267566,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00046130596031057885,
|
|
"loss": 5.0441,
|
|
"mean_token_accuracy": 0.1728651061654091,
|
|
"num_tokens": 43602437.0,
|
|
"step": 19900
|
|
},
|
|
{
|
|
"entropy": 5.598533630371094,
|
|
"epoch": 1.9754863040889243,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00046128609195129135,
|
|
"loss": 5.1628,
|
|
"mean_token_accuracy": 0.17248115986585616,
|
|
"num_tokens": 43613115.0,
|
|
"step": 19905
|
|
},
|
|
{
|
|
"entropy": 5.6184135437011715,
|
|
"epoch": 1.9759825327510918,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004612662189725101,
|
|
"loss": 5.1459,
|
|
"mean_token_accuracy": 0.1716393396258354,
|
|
"num_tokens": 43623700.0,
|
|
"step": 19910
|
|
},
|
|
{
|
|
"entropy": 5.6604790687561035,
|
|
"epoch": 1.9764787614132593,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.000461246341374728,
|
|
"loss": 5.1604,
|
|
"mean_token_accuracy": 0.1706886038184166,
|
|
"num_tokens": 43633712.0,
|
|
"step": 19915
|
|
},
|
|
{
|
|
"entropy": 5.624731063842773,
|
|
"epoch": 1.9769749900754268,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00046122645915843796,
|
|
"loss": 5.1894,
|
|
"mean_token_accuracy": 0.17017436772584915,
|
|
"num_tokens": 43643705.0,
|
|
"step": 19920
|
|
},
|
|
{
|
|
"entropy": 5.598883104324341,
|
|
"epoch": 1.9774712187375942,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00046120657232413305,
|
|
"loss": 5.1417,
|
|
"mean_token_accuracy": 0.1766065239906311,
|
|
"num_tokens": 43655376.0,
|
|
"step": 19925
|
|
},
|
|
{
|
|
"entropy": 5.557476997375488,
|
|
"epoch": 1.9779674473997617,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004611866808723064,
|
|
"loss": 5.0388,
|
|
"mean_token_accuracy": 0.1845523163676262,
|
|
"num_tokens": 43666329.0,
|
|
"step": 19930
|
|
},
|
|
{
|
|
"entropy": 5.524384498596191,
|
|
"epoch": 1.9784636760619292,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.00046116678480345117,
|
|
"loss": 5.0521,
|
|
"mean_token_accuracy": 0.17806633710861205,
|
|
"num_tokens": 43676415.0,
|
|
"step": 19935
|
|
},
|
|
{
|
|
"entropy": 5.523144102096557,
|
|
"epoch": 1.9789599047240969,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.00046114688411806083,
|
|
"loss": 5.0676,
|
|
"mean_token_accuracy": 0.18042845875024796,
|
|
"num_tokens": 43686997.0,
|
|
"step": 19940
|
|
},
|
|
{
|
|
"entropy": 5.540007734298706,
|
|
"epoch": 1.9794561333862644,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.00046112697881662895,
|
|
"loss": 5.0385,
|
|
"mean_token_accuracy": 0.1834940642118454,
|
|
"num_tokens": 43697342.0,
|
|
"step": 19945
|
|
},
|
|
{
|
|
"entropy": 5.652699279785156,
|
|
"epoch": 1.979952362048432,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00046110706889964905,
|
|
"loss": 5.1437,
|
|
"mean_token_accuracy": 0.17826791256666183,
|
|
"num_tokens": 43707876.0,
|
|
"step": 19950
|
|
},
|
|
{
|
|
"entropy": 5.57138090133667,
|
|
"epoch": 1.9804485907105995,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004610871543676149,
|
|
"loss": 4.9955,
|
|
"mean_token_accuracy": 0.1790217474102974,
|
|
"num_tokens": 43718268.0,
|
|
"step": 19955
|
|
},
|
|
{
|
|
"entropy": 5.569626045227051,
|
|
"epoch": 1.980944819372767,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.00046106723522102024,
|
|
"loss": 5.1533,
|
|
"mean_token_accuracy": 0.16895215064287186,
|
|
"num_tokens": 43729853.0,
|
|
"step": 19960
|
|
},
|
|
{
|
|
"entropy": 5.580903387069702,
|
|
"epoch": 1.9814410480349345,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00046104731146035904,
|
|
"loss": 5.1382,
|
|
"mean_token_accuracy": 0.17228945195674897,
|
|
"num_tokens": 43739886.0,
|
|
"step": 19965
|
|
},
|
|
{
|
|
"entropy": 5.628433465957642,
|
|
"epoch": 1.981937276697102,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004610273830861255,
|
|
"loss": 5.1118,
|
|
"mean_token_accuracy": 0.17257425785064698,
|
|
"num_tokens": 43750536.0,
|
|
"step": 19970
|
|
},
|
|
{
|
|
"entropy": 5.616104650497436,
|
|
"epoch": 1.9824335053592694,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004610074500988137,
|
|
"loss": 5.0988,
|
|
"mean_token_accuracy": 0.17899229228496552,
|
|
"num_tokens": 43763192.0,
|
|
"step": 19975
|
|
},
|
|
{
|
|
"entropy": 5.618440294265747,
|
|
"epoch": 1.9829297340214371,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004609875124989179,
|
|
"loss": 5.1365,
|
|
"mean_token_accuracy": 0.1766981303691864,
|
|
"num_tokens": 43774117.0,
|
|
"step": 19980
|
|
},
|
|
{
|
|
"entropy": 5.533320808410645,
|
|
"epoch": 1.9834259626836046,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004609675702869326,
|
|
"loss": 5.0666,
|
|
"mean_token_accuracy": 0.1747085228562355,
|
|
"num_tokens": 43784708.0,
|
|
"step": 19985
|
|
},
|
|
{
|
|
"entropy": 5.573682260513306,
|
|
"epoch": 1.983922191345772,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004609476234633523,
|
|
"loss": 5.1013,
|
|
"mean_token_accuracy": 0.1803373023867607,
|
|
"num_tokens": 43796767.0,
|
|
"step": 19990
|
|
},
|
|
{
|
|
"entropy": 5.636098623275757,
|
|
"epoch": 1.9844184200079398,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00046092767202867156,
|
|
"loss": 5.2144,
|
|
"mean_token_accuracy": 0.1675091952085495,
|
|
"num_tokens": 43807203.0,
|
|
"step": 19995
|
|
},
|
|
{
|
|
"entropy": 5.572779273986816,
|
|
"epoch": 1.9849146486701073,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00046090771598338525,
|
|
"loss": 5.1121,
|
|
"mean_token_accuracy": 0.1792059138417244,
|
|
"num_tokens": 43817123.0,
|
|
"step": 20000
|
|
},
|
|
{
|
|
"entropy": 5.598117160797119,
|
|
"epoch": 1.9854108773322747,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004608877553279881,
|
|
"loss": 5.089,
|
|
"mean_token_accuracy": 0.18206135779619217,
|
|
"num_tokens": 43828625.0,
|
|
"step": 20005
|
|
},
|
|
{
|
|
"entropy": 5.574577045440674,
|
|
"epoch": 1.9859071059944422,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004608677900629753,
|
|
"loss": 5.0506,
|
|
"mean_token_accuracy": 0.17934031486511232,
|
|
"num_tokens": 43840012.0,
|
|
"step": 20010
|
|
},
|
|
{
|
|
"entropy": 5.488186693191528,
|
|
"epoch": 1.9864033346566097,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00046084782018884177,
|
|
"loss": 5.0489,
|
|
"mean_token_accuracy": 0.17638782858848573,
|
|
"num_tokens": 43851253.0,
|
|
"step": 20015
|
|
},
|
|
{
|
|
"entropy": 5.643233299255371,
|
|
"epoch": 1.9868995633187772,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.00046082784570608266,
|
|
"loss": 5.1645,
|
|
"mean_token_accuracy": 0.17455788254737853,
|
|
"num_tokens": 43864389.0,
|
|
"step": 20020
|
|
},
|
|
{
|
|
"entropy": 5.639037036895752,
|
|
"epoch": 1.9873957919809448,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00046080786661519354,
|
|
"loss": 5.1562,
|
|
"mean_token_accuracy": 0.17175842076539993,
|
|
"num_tokens": 43876446.0,
|
|
"step": 20025
|
|
},
|
|
{
|
|
"entropy": 5.603530979156494,
|
|
"epoch": 1.9878920206431123,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004607878829166696,
|
|
"loss": 5.1104,
|
|
"mean_token_accuracy": 0.16865846365690232,
|
|
"num_tokens": 43888318.0,
|
|
"step": 20030
|
|
},
|
|
{
|
|
"entropy": 5.520271158218383,
|
|
"epoch": 1.98838824930528,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00046076789461100653,
|
|
"loss": 5.05,
|
|
"mean_token_accuracy": 0.18364468663930894,
|
|
"num_tokens": 43898358.0,
|
|
"step": 20035
|
|
},
|
|
{
|
|
"entropy": 5.591721105575561,
|
|
"epoch": 1.9888844779674475,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004607479016987001,
|
|
"loss": 5.0984,
|
|
"mean_token_accuracy": 0.1757814645767212,
|
|
"num_tokens": 43909831.0,
|
|
"step": 20040
|
|
},
|
|
{
|
|
"entropy": 5.597817754745483,
|
|
"epoch": 1.989380706629615,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004607279041802458,
|
|
"loss": 5.0673,
|
|
"mean_token_accuracy": 0.17361391335725784,
|
|
"num_tokens": 43919648.0,
|
|
"step": 20045
|
|
},
|
|
{
|
|
"entropy": 5.569124174118042,
|
|
"epoch": 1.9898769352917824,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.00046070790205613967,
|
|
"loss": 5.12,
|
|
"mean_token_accuracy": 0.17306884825229646,
|
|
"num_tokens": 43930563.0,
|
|
"step": 20050
|
|
},
|
|
{
|
|
"entropy": 5.63607497215271,
|
|
"epoch": 1.99037316395395,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.00046068789532687784,
|
|
"loss": 5.1932,
|
|
"mean_token_accuracy": 0.17143940329551696,
|
|
"num_tokens": 43942490.0,
|
|
"step": 20055
|
|
},
|
|
{
|
|
"entropy": 5.561767673492431,
|
|
"epoch": 1.9908693926161174,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004606678839929563,
|
|
"loss": 4.9763,
|
|
"mean_token_accuracy": 0.18970065861940383,
|
|
"num_tokens": 43952187.0,
|
|
"step": 20060
|
|
},
|
|
{
|
|
"entropy": 5.522125291824341,
|
|
"epoch": 1.9913656212782849,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004606478680548713,
|
|
"loss": 5.0381,
|
|
"mean_token_accuracy": 0.1813553750514984,
|
|
"num_tokens": 43964203.0,
|
|
"step": 20065
|
|
},
|
|
{
|
|
"entropy": 5.547319936752319,
|
|
"epoch": 1.9918618499404526,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00046062784751311917,
|
|
"loss": 5.1192,
|
|
"mean_token_accuracy": 0.17629277259111403,
|
|
"num_tokens": 43974048.0,
|
|
"step": 20070
|
|
},
|
|
{
|
|
"entropy": 5.6360697746276855,
|
|
"epoch": 1.99235807860262,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00046060782236819647,
|
|
"loss": 5.1016,
|
|
"mean_token_accuracy": 0.17606257796287536,
|
|
"num_tokens": 43984469.0,
|
|
"step": 20075
|
|
},
|
|
{
|
|
"entropy": 5.588944911956787,
|
|
"epoch": 1.9928543072647877,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004605877926205996,
|
|
"loss": 5.122,
|
|
"mean_token_accuracy": 0.1758631095290184,
|
|
"num_tokens": 43995494.0,
|
|
"step": 20080
|
|
},
|
|
{
|
|
"entropy": 5.58999457359314,
|
|
"epoch": 1.9933505359269552,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004605677582708256,
|
|
"loss": 5.0483,
|
|
"mean_token_accuracy": 0.1770133838057518,
|
|
"num_tokens": 44005869.0,
|
|
"step": 20085
|
|
},
|
|
{
|
|
"entropy": 5.629586315155029,
|
|
"epoch": 1.9938467645891227,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004605477193193709,
|
|
"loss": 5.1065,
|
|
"mean_token_accuracy": 0.172397281229496,
|
|
"num_tokens": 44016956.0,
|
|
"step": 20090
|
|
},
|
|
{
|
|
"entropy": 5.6551614761352536,
|
|
"epoch": 1.9943429932512902,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004605276757667326,
|
|
"loss": 5.1784,
|
|
"mean_token_accuracy": 0.16540496796369553,
|
|
"num_tokens": 44029524.0,
|
|
"step": 20095
|
|
},
|
|
{
|
|
"entropy": 5.574221801757813,
|
|
"epoch": 1.9948392219134576,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004605076276134078,
|
|
"loss": 5.0624,
|
|
"mean_token_accuracy": 0.17908160239458085,
|
|
"num_tokens": 44039523.0,
|
|
"step": 20100
|
|
},
|
|
{
|
|
"entropy": 5.659173631668091,
|
|
"epoch": 1.9953354505756251,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00046048757485989345,
|
|
"loss": 5.1743,
|
|
"mean_token_accuracy": 0.16826657056808472,
|
|
"num_tokens": 44050538.0,
|
|
"step": 20105
|
|
},
|
|
{
|
|
"entropy": 5.641814517974853,
|
|
"epoch": 1.9958316792377928,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.000460467517506687,
|
|
"loss": 5.1578,
|
|
"mean_token_accuracy": 0.16938179433345796,
|
|
"num_tokens": 44061108.0,
|
|
"step": 20110
|
|
},
|
|
{
|
|
"entropy": 5.551302719116211,
|
|
"epoch": 1.9963279078999603,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004604474555542858,
|
|
"loss": 5.0942,
|
|
"mean_token_accuracy": 0.17868563234806062,
|
|
"num_tokens": 44072706.0,
|
|
"step": 20115
|
|
},
|
|
{
|
|
"entropy": 5.610600852966309,
|
|
"epoch": 1.996824136562128,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004604273890031872,
|
|
"loss": 5.0865,
|
|
"mean_token_accuracy": 0.17227104306221008,
|
|
"num_tokens": 44082697.0,
|
|
"step": 20120
|
|
},
|
|
{
|
|
"entropy": 5.5398736000061035,
|
|
"epoch": 1.9973203652242955,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.000460407317853889,
|
|
"loss": 5.0696,
|
|
"mean_token_accuracy": 0.17819233387708663,
|
|
"num_tokens": 44093265.0,
|
|
"step": 20125
|
|
},
|
|
{
|
|
"entropy": 5.562592697143555,
|
|
"epoch": 1.997816593886463,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004603872421068888,
|
|
"loss": 5.0619,
|
|
"mean_token_accuracy": 0.1732928767800331,
|
|
"num_tokens": 44103535.0,
|
|
"step": 20130
|
|
},
|
|
{
|
|
"entropy": 5.568638801574707,
|
|
"epoch": 1.9983128225486304,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004603671617626845,
|
|
"loss": 5.0523,
|
|
"mean_token_accuracy": 0.18068394511938096,
|
|
"num_tokens": 44113903.0,
|
|
"step": 20135
|
|
},
|
|
{
|
|
"entropy": 5.587209272384643,
|
|
"epoch": 1.9988090512107979,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00046034707682177393,
|
|
"loss": 5.088,
|
|
"mean_token_accuracy": 0.1831910565495491,
|
|
"num_tokens": 44125148.0,
|
|
"step": 20140
|
|
},
|
|
{
|
|
"entropy": 5.674484491348267,
|
|
"epoch": 1.9993052798729654,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004603269872846554,
|
|
"loss": 5.1869,
|
|
"mean_token_accuracy": 0.16739544719457627,
|
|
"num_tokens": 44136563.0,
|
|
"step": 20145
|
|
},
|
|
{
|
|
"entropy": 5.7027617454528805,
|
|
"epoch": 1.9998015085351328,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.00046030689315182676,
|
|
"loss": 5.1505,
|
|
"mean_token_accuracy": 0.17384083867073058,
|
|
"num_tokens": 44147521.0,
|
|
"step": 20150
|
|
},
|
|
{
|
|
"entropy": 5.645961761474609,
|
|
"epoch": 2.0002977371973003,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004602867944237866,
|
|
"loss": 5.1377,
|
|
"mean_token_accuracy": 0.1753172382712364,
|
|
"num_tokens": 44158977.0,
|
|
"step": 20155
|
|
},
|
|
{
|
|
"entropy": 5.613375520706176,
|
|
"epoch": 2.0007939658594682,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00046026669110103315,
|
|
"loss": 5.099,
|
|
"mean_token_accuracy": 0.17865435928106307,
|
|
"num_tokens": 44170986.0,
|
|
"step": 20160
|
|
},
|
|
{
|
|
"entropy": 5.684283685684204,
|
|
"epoch": 2.0012901945216357,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00046024658318406493,
|
|
"loss": 5.1495,
|
|
"mean_token_accuracy": 0.17643476128578187,
|
|
"num_tokens": 44180936.0,
|
|
"step": 20165
|
|
},
|
|
{
|
|
"entropy": 5.6822834491729735,
|
|
"epoch": 2.001786423183803,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004602264706733807,
|
|
"loss": 5.146,
|
|
"mean_token_accuracy": 0.17399806380271912,
|
|
"num_tokens": 44191741.0,
|
|
"step": 20170
|
|
},
|
|
{
|
|
"entropy": 5.602428531646728,
|
|
"epoch": 2.0022826518459707,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004602063535694791,
|
|
"loss": 5.0262,
|
|
"mean_token_accuracy": 0.17787106484174728,
|
|
"num_tokens": 44202310.0,
|
|
"step": 20175
|
|
},
|
|
{
|
|
"entropy": 5.586825752258301,
|
|
"epoch": 2.002778880508138,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.000460186231872859,
|
|
"loss": 5.0745,
|
|
"mean_token_accuracy": 0.18134640008211136,
|
|
"num_tokens": 44213514.0,
|
|
"step": 20180
|
|
},
|
|
{
|
|
"entropy": 5.65569920539856,
|
|
"epoch": 2.0032751091703056,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.00046016610558401936,
|
|
"loss": 5.1083,
|
|
"mean_token_accuracy": 0.17185890674591064,
|
|
"num_tokens": 44224718.0,
|
|
"step": 20185
|
|
},
|
|
{
|
|
"entropy": 5.617652320861817,
|
|
"epoch": 2.003771337832473,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00046014597470345935,
|
|
"loss": 5.1229,
|
|
"mean_token_accuracy": 0.17804794311523436,
|
|
"num_tokens": 44235999.0,
|
|
"step": 20190
|
|
},
|
|
{
|
|
"entropy": 5.578877592086792,
|
|
"epoch": 2.0042675664946406,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004601258392316781,
|
|
"loss": 4.98,
|
|
"mean_token_accuracy": 0.18120295703411102,
|
|
"num_tokens": 44246323.0,
|
|
"step": 20195
|
|
},
|
|
{
|
|
"entropy": 5.559261894226074,
|
|
"epoch": 2.0047637951568085,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00046010569916917496,
|
|
"loss": 5.0216,
|
|
"mean_token_accuracy": 0.17838912308216096,
|
|
"num_tokens": 44256323.0,
|
|
"step": 20200
|
|
},
|
|
{
|
|
"entropy": 5.588315057754516,
|
|
"epoch": 2.005260023818976,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004600855545164493,
|
|
"loss": 5.0067,
|
|
"mean_token_accuracy": 0.18068246096372603,
|
|
"num_tokens": 44266845.0,
|
|
"step": 20205
|
|
},
|
|
{
|
|
"entropy": 5.624822759628296,
|
|
"epoch": 2.0057562524811434,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004600654052740008,
|
|
"loss": 5.1023,
|
|
"mean_token_accuracy": 0.1778157964348793,
|
|
"num_tokens": 44277861.0,
|
|
"step": 20210
|
|
},
|
|
{
|
|
"entropy": 5.593832492828369,
|
|
"epoch": 2.006252481143311,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004600452514423289,
|
|
"loss": 5.0396,
|
|
"mean_token_accuracy": 0.18204380422830582,
|
|
"num_tokens": 44288511.0,
|
|
"step": 20215
|
|
},
|
|
{
|
|
"entropy": 5.5884888648986815,
|
|
"epoch": 2.0067487098054784,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004600250930219336,
|
|
"loss": 5.1547,
|
|
"mean_token_accuracy": 0.1687192514538765,
|
|
"num_tokens": 44299752.0,
|
|
"step": 20220
|
|
},
|
|
{
|
|
"entropy": 5.593734645843506,
|
|
"epoch": 2.007244938467646,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00046000493001331465,
|
|
"loss": 5.0004,
|
|
"mean_token_accuracy": 0.18091526478528977,
|
|
"num_tokens": 44309443.0,
|
|
"step": 20225
|
|
},
|
|
{
|
|
"entropy": 5.633876085281372,
|
|
"epoch": 2.0077411671298133,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00045998476241697214,
|
|
"loss": 5.0247,
|
|
"mean_token_accuracy": 0.18577445447444915,
|
|
"num_tokens": 44320030.0,
|
|
"step": 20230
|
|
},
|
|
{
|
|
"entropy": 5.532174825668335,
|
|
"epoch": 2.008237395791981,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004599645902334061,
|
|
"loss": 4.935,
|
|
"mean_token_accuracy": 0.18527044951915742,
|
|
"num_tokens": 44330077.0,
|
|
"step": 20235
|
|
},
|
|
{
|
|
"entropy": 5.458415699005127,
|
|
"epoch": 2.0087336244541483,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00045994441346311677,
|
|
"loss": 5.0192,
|
|
"mean_token_accuracy": 0.1848942831158638,
|
|
"num_tokens": 44340336.0,
|
|
"step": 20240
|
|
},
|
|
{
|
|
"entropy": 5.585581874847412,
|
|
"epoch": 2.009229853116316,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004599242321066045,
|
|
"loss": 5.009,
|
|
"mean_token_accuracy": 0.18270372301340104,
|
|
"num_tokens": 44350704.0,
|
|
"step": 20245
|
|
},
|
|
{
|
|
"entropy": 5.635739755630493,
|
|
"epoch": 2.0097260817784837,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00045990404616436976,
|
|
"loss": 5.0452,
|
|
"mean_token_accuracy": 0.18373702913522721,
|
|
"num_tokens": 44360541.0,
|
|
"step": 20250
|
|
},
|
|
{
|
|
"entropy": 5.4952953338623045,
|
|
"epoch": 2.010222310440651,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004598838556369131,
|
|
"loss": 4.9566,
|
|
"mean_token_accuracy": 0.18585868179798126,
|
|
"num_tokens": 44372132.0,
|
|
"step": 20255
|
|
},
|
|
{
|
|
"entropy": 5.505873441696167,
|
|
"epoch": 2.0107185391028186,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.00045986366052473525,
|
|
"loss": 4.9553,
|
|
"mean_token_accuracy": 0.1907545283436775,
|
|
"num_tokens": 44383594.0,
|
|
"step": 20260
|
|
},
|
|
{
|
|
"entropy": 5.52165994644165,
|
|
"epoch": 2.011214767764986,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004598434608283369,
|
|
"loss": 4.98,
|
|
"mean_token_accuracy": 0.18184978663921356,
|
|
"num_tokens": 44394101.0,
|
|
"step": 20265
|
|
},
|
|
{
|
|
"entropy": 5.632853412628174,
|
|
"epoch": 2.0117109964271536,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004598232565482191,
|
|
"loss": 5.0892,
|
|
"mean_token_accuracy": 0.1794629603624344,
|
|
"num_tokens": 44405670.0,
|
|
"step": 20270
|
|
},
|
|
{
|
|
"entropy": 5.620148849487305,
|
|
"epoch": 2.012207225089321,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00045980304768488274,
|
|
"loss": 5.0422,
|
|
"mean_token_accuracy": 0.1825747773051262,
|
|
"num_tokens": 44417748.0,
|
|
"step": 20275
|
|
},
|
|
{
|
|
"entropy": 5.638302278518677,
|
|
"epoch": 2.0127034537514885,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00045978283423882906,
|
|
"loss": 5.0334,
|
|
"mean_token_accuracy": 0.17779522985219956,
|
|
"num_tokens": 44429648.0,
|
|
"step": 20280
|
|
},
|
|
{
|
|
"entropy": 5.541291809082031,
|
|
"epoch": 2.0131996824136564,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00045976261621055915,
|
|
"loss": 5.0155,
|
|
"mean_token_accuracy": 0.1786918967962265,
|
|
"num_tokens": 44440867.0,
|
|
"step": 20285
|
|
},
|
|
{
|
|
"entropy": 5.561808490753174,
|
|
"epoch": 2.013695911075824,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00045974239360057457,
|
|
"loss": 5.0633,
|
|
"mean_token_accuracy": 0.1781747654080391,
|
|
"num_tokens": 44452981.0,
|
|
"step": 20290
|
|
},
|
|
{
|
|
"entropy": 5.58002667427063,
|
|
"epoch": 2.0141921397379914,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00045972216640937676,
|
|
"loss": 4.9991,
|
|
"mean_token_accuracy": 0.1874930053949356,
|
|
"num_tokens": 44464243.0,
|
|
"step": 20295
|
|
},
|
|
{
|
|
"entropy": 5.6033953666687015,
|
|
"epoch": 2.014688368400159,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004597019346374672,
|
|
"loss": 5.0875,
|
|
"mean_token_accuracy": 0.1769336000084877,
|
|
"num_tokens": 44474376.0,
|
|
"step": 20300
|
|
},
|
|
{
|
|
"entropy": 5.548331308364868,
|
|
"epoch": 2.0151845970623263,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004596816982853477,
|
|
"loss": 4.9697,
|
|
"mean_token_accuracy": 0.1939048945903778,
|
|
"num_tokens": 44485686.0,
|
|
"step": 20305
|
|
},
|
|
{
|
|
"entropy": 5.498635196685791,
|
|
"epoch": 2.015680825724494,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00045966145735352,
|
|
"loss": 4.9881,
|
|
"mean_token_accuracy": 0.18503205478191376,
|
|
"num_tokens": 44496096.0,
|
|
"step": 20310
|
|
},
|
|
{
|
|
"entropy": 5.633474683761596,
|
|
"epoch": 2.0161770543866613,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00045964121184248604,
|
|
"loss": 5.0861,
|
|
"mean_token_accuracy": 0.17507048845291137,
|
|
"num_tokens": 44507555.0,
|
|
"step": 20315
|
|
},
|
|
{
|
|
"entropy": 5.5817920684814455,
|
|
"epoch": 2.0166732830488288,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004596209617527479,
|
|
"loss": 5.0544,
|
|
"mean_token_accuracy": 0.177122001349926,
|
|
"num_tokens": 44519288.0,
|
|
"step": 20320
|
|
},
|
|
{
|
|
"entropy": 5.625044870376587,
|
|
"epoch": 2.0171695117109962,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004596007070848078,
|
|
"loss": 5.0913,
|
|
"mean_token_accuracy": 0.1673508882522583,
|
|
"num_tokens": 44530146.0,
|
|
"step": 20325
|
|
},
|
|
{
|
|
"entropy": 5.62387170791626,
|
|
"epoch": 2.017665740373164,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00045958044783916795,
|
|
"loss": 5.0636,
|
|
"mean_token_accuracy": 0.18019708693027497,
|
|
"num_tokens": 44541411.0,
|
|
"step": 20330
|
|
},
|
|
{
|
|
"entropy": 5.5671141147613525,
|
|
"epoch": 2.0181619690353316,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004595601840163306,
|
|
"loss": 5.033,
|
|
"mean_token_accuracy": 0.1766697272658348,
|
|
"num_tokens": 44552556.0,
|
|
"step": 20335
|
|
},
|
|
{
|
|
"entropy": 5.537384510040283,
|
|
"epoch": 2.018658197697499,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00045953991561679855,
|
|
"loss": 5.042,
|
|
"mean_token_accuracy": 0.18193720579147338,
|
|
"num_tokens": 44563052.0,
|
|
"step": 20340
|
|
},
|
|
{
|
|
"entropy": 5.534431600570679,
|
|
"epoch": 2.0191544263596666,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004595196426410742,
|
|
"loss": 5.0239,
|
|
"mean_token_accuracy": 0.18166431784629822,
|
|
"num_tokens": 44574020.0,
|
|
"step": 20345
|
|
},
|
|
{
|
|
"entropy": 5.5410583972930905,
|
|
"epoch": 2.019650655021834,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00045949936508966015,
|
|
"loss": 4.9769,
|
|
"mean_token_accuracy": 0.1821667656302452,
|
|
"num_tokens": 44586261.0,
|
|
"step": 20350
|
|
},
|
|
{
|
|
"entropy": 5.594756269454956,
|
|
"epoch": 2.0201468836840015,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004594790829630596,
|
|
"loss": 5.0251,
|
|
"mean_token_accuracy": 0.17324368953704833,
|
|
"num_tokens": 44596391.0,
|
|
"step": 20355
|
|
},
|
|
{
|
|
"entropy": 5.5267126083374025,
|
|
"epoch": 2.020643112346169,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004594587962617752,
|
|
"loss": 4.9813,
|
|
"mean_token_accuracy": 0.18209591507911682,
|
|
"num_tokens": 44606263.0,
|
|
"step": 20360
|
|
},
|
|
{
|
|
"entropy": 5.571532487869263,
|
|
"epoch": 2.0211393410083365,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004594385049863102,
|
|
"loss": 5.0498,
|
|
"mean_token_accuracy": 0.17598610371351242,
|
|
"num_tokens": 44617332.0,
|
|
"step": 20365
|
|
},
|
|
{
|
|
"entropy": 5.571857976913452,
|
|
"epoch": 2.021635569670504,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.00045941820913716766,
|
|
"loss": 5.0423,
|
|
"mean_token_accuracy": 0.19036736637353896,
|
|
"num_tokens": 44629784.0,
|
|
"step": 20370
|
|
},
|
|
{
|
|
"entropy": 5.672733354568481,
|
|
"epoch": 2.022131798332672,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00045939790871485093,
|
|
"loss": 5.1552,
|
|
"mean_token_accuracy": 0.16935770064592362,
|
|
"num_tokens": 44641398.0,
|
|
"step": 20375
|
|
},
|
|
{
|
|
"entropy": 5.507920789718628,
|
|
"epoch": 2.0226280269948393,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00045937760371986334,
|
|
"loss": 4.9055,
|
|
"mean_token_accuracy": 0.1905221089720726,
|
|
"num_tokens": 44652592.0,
|
|
"step": 20380
|
|
},
|
|
{
|
|
"entropy": 5.561168527603149,
|
|
"epoch": 2.023124255657007,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00045935729415270857,
|
|
"loss": 4.9746,
|
|
"mean_token_accuracy": 0.19756082445383072,
|
|
"num_tokens": 44663896.0,
|
|
"step": 20385
|
|
},
|
|
{
|
|
"entropy": 5.667262077331543,
|
|
"epoch": 2.0236204843191743,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004593369800138901,
|
|
"loss": 5.1233,
|
|
"mean_token_accuracy": 0.17189263701438903,
|
|
"num_tokens": 44675004.0,
|
|
"step": 20390
|
|
},
|
|
{
|
|
"entropy": 5.621305751800537,
|
|
"epoch": 2.0241167129813418,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004593166613039118,
|
|
"loss": 5.0913,
|
|
"mean_token_accuracy": 0.17793205380439758,
|
|
"num_tokens": 44686778.0,
|
|
"step": 20395
|
|
},
|
|
{
|
|
"entropy": 5.559695434570313,
|
|
"epoch": 2.0246129416435092,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00045929633802327743,
|
|
"loss": 5.0152,
|
|
"mean_token_accuracy": 0.18322455286979675,
|
|
"num_tokens": 44697600.0,
|
|
"step": 20400
|
|
},
|
|
{
|
|
"entropy": 5.547638893127441,
|
|
"epoch": 2.0251091703056767,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000459276010172491,
|
|
"loss": 5.0716,
|
|
"mean_token_accuracy": 0.17049810588359832,
|
|
"num_tokens": 44707453.0,
|
|
"step": 20405
|
|
},
|
|
{
|
|
"entropy": 5.590932893753052,
|
|
"epoch": 2.025605398967844,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00045925567775205656,
|
|
"loss": 5.1391,
|
|
"mean_token_accuracy": 0.1736005961894989,
|
|
"num_tokens": 44718351.0,
|
|
"step": 20410
|
|
},
|
|
{
|
|
"entropy": 5.60587887763977,
|
|
"epoch": 2.026101627630012,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00045923534076247846,
|
|
"loss": 5.0128,
|
|
"mean_token_accuracy": 0.18642785400152206,
|
|
"num_tokens": 44728884.0,
|
|
"step": 20415
|
|
},
|
|
{
|
|
"entropy": 5.600027799606323,
|
|
"epoch": 2.0265978562921796,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.00045921499920426083,
|
|
"loss": 5.0263,
|
|
"mean_token_accuracy": 0.1786925658583641,
|
|
"num_tokens": 44740769.0,
|
|
"step": 20420
|
|
},
|
|
{
|
|
"entropy": 5.599120426177978,
|
|
"epoch": 2.027094084954347,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00045919465307790817,
|
|
"loss": 5.1447,
|
|
"mean_token_accuracy": 0.17507598847150802,
|
|
"num_tokens": 44753094.0,
|
|
"step": 20425
|
|
},
|
|
{
|
|
"entropy": 5.5000285625457765,
|
|
"epoch": 2.0275903136165145,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00045917430238392505,
|
|
"loss": 4.8942,
|
|
"mean_token_accuracy": 0.19176001399755477,
|
|
"num_tokens": 44762996.0,
|
|
"step": 20430
|
|
},
|
|
{
|
|
"entropy": 5.528482675552368,
|
|
"epoch": 2.028086542278682,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.000459153947122816,
|
|
"loss": 5.0858,
|
|
"mean_token_accuracy": 0.18000393211841584,
|
|
"num_tokens": 44775343.0,
|
|
"step": 20435
|
|
},
|
|
{
|
|
"entropy": 5.519376182556153,
|
|
"epoch": 2.0285827709408495,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004591335872950859,
|
|
"loss": 4.9389,
|
|
"mean_token_accuracy": 0.18735790699720384,
|
|
"num_tokens": 44785383.0,
|
|
"step": 20440
|
|
},
|
|
{
|
|
"entropy": 5.554380083084107,
|
|
"epoch": 2.029078999603017,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004591132229012397,
|
|
"loss": 5.0015,
|
|
"mean_token_accuracy": 0.18096659630537032,
|
|
"num_tokens": 44796805.0,
|
|
"step": 20445
|
|
},
|
|
{
|
|
"entropy": 5.569212436676025,
|
|
"epoch": 2.0295752282651844,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00045909285394178217,
|
|
"loss": 5.0113,
|
|
"mean_token_accuracy": 0.18607627898454665,
|
|
"num_tokens": 44806800.0,
|
|
"step": 20450
|
|
},
|
|
{
|
|
"entropy": 5.605460548400879,
|
|
"epoch": 2.030071456927352,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004590724804172187,
|
|
"loss": 5.1266,
|
|
"mean_token_accuracy": 0.16906161308288575,
|
|
"num_tokens": 44818745.0,
|
|
"step": 20455
|
|
},
|
|
{
|
|
"entropy": 5.524948310852051,
|
|
"epoch": 2.03056768558952,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004590521023280543,
|
|
"loss": 4.9927,
|
|
"mean_token_accuracy": 0.18356360048055648,
|
|
"num_tokens": 44829825.0,
|
|
"step": 20460
|
|
},
|
|
{
|
|
"entropy": 5.536785507202149,
|
|
"epoch": 2.0310639142516873,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00045903171967479425,
|
|
"loss": 5.0033,
|
|
"mean_token_accuracy": 0.18167675882577897,
|
|
"num_tokens": 44841742.0,
|
|
"step": 20465
|
|
},
|
|
{
|
|
"entropy": 5.5943561553955075,
|
|
"epoch": 2.031560142913855,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00045901133245794426,
|
|
"loss": 5.129,
|
|
"mean_token_accuracy": 0.18166817724704742,
|
|
"num_tokens": 44853019.0,
|
|
"step": 20470
|
|
},
|
|
{
|
|
"entropy": 5.555161666870117,
|
|
"epoch": 2.0320563715760223,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004589909406780096,
|
|
"loss": 4.9651,
|
|
"mean_token_accuracy": 0.18661444634199142,
|
|
"num_tokens": 44863147.0,
|
|
"step": 20475
|
|
},
|
|
{
|
|
"entropy": 5.630882787704468,
|
|
"epoch": 2.0325526002381897,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00045897054433549617,
|
|
"loss": 5.0364,
|
|
"mean_token_accuracy": 0.1834707573056221,
|
|
"num_tokens": 44873638.0,
|
|
"step": 20480
|
|
},
|
|
{
|
|
"entropy": 5.5578453540802,
|
|
"epoch": 2.033048828900357,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00045895014343090963,
|
|
"loss": 5.0343,
|
|
"mean_token_accuracy": 0.18064282238483428,
|
|
"num_tokens": 44885752.0,
|
|
"step": 20485
|
|
},
|
|
{
|
|
"entropy": 5.511915683746338,
|
|
"epoch": 2.0335450575625247,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.00045892973796475594,
|
|
"loss": 4.9878,
|
|
"mean_token_accuracy": 0.17926738709211348,
|
|
"num_tokens": 44897471.0,
|
|
"step": 20490
|
|
},
|
|
{
|
|
"entropy": 5.641724109649658,
|
|
"epoch": 2.034041286224692,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000458909327937541,
|
|
"loss": 5.0801,
|
|
"mean_token_accuracy": 0.17359787672758104,
|
|
"num_tokens": 44907236.0,
|
|
"step": 20495
|
|
},
|
|
{
|
|
"entropy": 5.594384717941284,
|
|
"epoch": 2.03453751488686,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00045888891334977105,
|
|
"loss": 4.9902,
|
|
"mean_token_accuracy": 0.18277155011892318,
|
|
"num_tokens": 44918103.0,
|
|
"step": 20500
|
|
},
|
|
{
|
|
"entropy": 5.546513462066651,
|
|
"epoch": 2.0350337435490276,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004588684942019524,
|
|
"loss": 5.0475,
|
|
"mean_token_accuracy": 0.17986328303813934,
|
|
"num_tokens": 44928263.0,
|
|
"step": 20505
|
|
},
|
|
{
|
|
"entropy": 5.5183717727661135,
|
|
"epoch": 2.035529972211195,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00045884807049459116,
|
|
"loss": 5.0121,
|
|
"mean_token_accuracy": 0.1820213943719864,
|
|
"num_tokens": 44939487.0,
|
|
"step": 20510
|
|
},
|
|
{
|
|
"entropy": 5.574971866607666,
|
|
"epoch": 2.0360262008733625,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000458827642228194,
|
|
"loss": 5.1081,
|
|
"mean_token_accuracy": 0.17568829357624055,
|
|
"num_tokens": 44949749.0,
|
|
"step": 20515
|
|
},
|
|
{
|
|
"entropy": 5.58670449256897,
|
|
"epoch": 2.03652242953553,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00045880720940326744,
|
|
"loss": 5.0346,
|
|
"mean_token_accuracy": 0.17874034345149994,
|
|
"num_tokens": 44960347.0,
|
|
"step": 20520
|
|
},
|
|
{
|
|
"entropy": 5.665294504165649,
|
|
"epoch": 2.0370186581976975,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00045878677202031804,
|
|
"loss": 5.1019,
|
|
"mean_token_accuracy": 0.17289525419473648,
|
|
"num_tokens": 44970420.0,
|
|
"step": 20525
|
|
},
|
|
{
|
|
"entropy": 5.560429620742798,
|
|
"epoch": 2.037514886859865,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004587663300798529,
|
|
"loss": 5.0347,
|
|
"mean_token_accuracy": 0.17720650285482406,
|
|
"num_tokens": 44980888.0,
|
|
"step": 20530
|
|
},
|
|
{
|
|
"entropy": 5.5810709476470945,
|
|
"epoch": 2.0380111155220324,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004587458835823786,
|
|
"loss": 5.0337,
|
|
"mean_token_accuracy": 0.17814827263355254,
|
|
"num_tokens": 44992721.0,
|
|
"step": 20535
|
|
},
|
|
{
|
|
"entropy": 5.580349922180176,
|
|
"epoch": 2.0385073441842,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00045872543252840236,
|
|
"loss": 5.0041,
|
|
"mean_token_accuracy": 0.18439416140317916,
|
|
"num_tokens": 45003603.0,
|
|
"step": 20540
|
|
},
|
|
{
|
|
"entropy": 5.557141971588135,
|
|
"epoch": 2.039003572846368,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00045870497691843134,
|
|
"loss": 5.0339,
|
|
"mean_token_accuracy": 0.18700573444366456,
|
|
"num_tokens": 45014864.0,
|
|
"step": 20545
|
|
},
|
|
{
|
|
"entropy": 5.586525249481201,
|
|
"epoch": 2.0394998015085353,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004586845167529727,
|
|
"loss": 5.0793,
|
|
"mean_token_accuracy": 0.1750664606690407,
|
|
"num_tokens": 45027766.0,
|
|
"step": 20550
|
|
},
|
|
{
|
|
"entropy": 5.557331609725952,
|
|
"epoch": 2.0399960301707027,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.00045866405203253384,
|
|
"loss": 5.0372,
|
|
"mean_token_accuracy": 0.17988807559013367,
|
|
"num_tokens": 45039524.0,
|
|
"step": 20555
|
|
},
|
|
{
|
|
"entropy": 5.582472419738769,
|
|
"epoch": 2.04049225883287,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004586435827576223,
|
|
"loss": 5.0617,
|
|
"mean_token_accuracy": 0.17601825445890426,
|
|
"num_tokens": 45050848.0,
|
|
"step": 20560
|
|
},
|
|
{
|
|
"entropy": 5.564962100982666,
|
|
"epoch": 2.0409884874950377,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004586231089287456,
|
|
"loss": 5.0089,
|
|
"mean_token_accuracy": 0.178389011323452,
|
|
"num_tokens": 45061229.0,
|
|
"step": 20565
|
|
},
|
|
{
|
|
"entropy": 5.525482606887818,
|
|
"epoch": 2.041484716157205,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004586026305464115,
|
|
"loss": 4.9572,
|
|
"mean_token_accuracy": 0.18500153720378876,
|
|
"num_tokens": 45070466.0,
|
|
"step": 20570
|
|
},
|
|
{
|
|
"entropy": 5.589316558837891,
|
|
"epoch": 2.0419809448193726,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00045858214761112777,
|
|
"loss": 5.0467,
|
|
"mean_token_accuracy": 0.17747531831264496,
|
|
"num_tokens": 45081839.0,
|
|
"step": 20575
|
|
},
|
|
{
|
|
"entropy": 5.652382278442383,
|
|
"epoch": 2.04247717348154,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00045856166012340235,
|
|
"loss": 5.1038,
|
|
"mean_token_accuracy": 0.17503010034561156,
|
|
"num_tokens": 45092458.0,
|
|
"step": 20580
|
|
},
|
|
{
|
|
"entropy": 5.643860960006714,
|
|
"epoch": 2.0429734021437076,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004585411680837433,
|
|
"loss": 5.0836,
|
|
"mean_token_accuracy": 0.17511983811855317,
|
|
"num_tokens": 45104629.0,
|
|
"step": 20585
|
|
},
|
|
{
|
|
"entropy": 5.581271648406982,
|
|
"epoch": 2.0434696308058755,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00045852067149265875,
|
|
"loss": 4.9434,
|
|
"mean_token_accuracy": 0.1826970860362053,
|
|
"num_tokens": 45115556.0,
|
|
"step": 20590
|
|
},
|
|
{
|
|
"entropy": 5.5476508140563965,
|
|
"epoch": 2.043965859468043,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.000458500170350657,
|
|
"loss": 5.0175,
|
|
"mean_token_accuracy": 0.1785544604063034,
|
|
"num_tokens": 45126489.0,
|
|
"step": 20595
|
|
},
|
|
{
|
|
"entropy": 5.579299736022949,
|
|
"epoch": 2.0444620881302105,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00045847966465824654,
|
|
"loss": 5.1267,
|
|
"mean_token_accuracy": 0.17368541061878204,
|
|
"num_tokens": 45138882.0,
|
|
"step": 20600
|
|
},
|
|
{
|
|
"entropy": 5.636334228515625,
|
|
"epoch": 2.044958316792378,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004584591544159356,
|
|
"loss": 5.0553,
|
|
"mean_token_accuracy": 0.18055800050497056,
|
|
"num_tokens": 45149941.0,
|
|
"step": 20605
|
|
},
|
|
{
|
|
"entropy": 5.667939281463623,
|
|
"epoch": 2.0454545454545454,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004584386396242331,
|
|
"loss": 5.0874,
|
|
"mean_token_accuracy": 0.17820067554712296,
|
|
"num_tokens": 45162267.0,
|
|
"step": 20610
|
|
},
|
|
{
|
|
"entropy": 5.63246488571167,
|
|
"epoch": 2.045950774116713,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00045841812028364756,
|
|
"loss": 5.1739,
|
|
"mean_token_accuracy": 0.17613014876842498,
|
|
"num_tokens": 45174444.0,
|
|
"step": 20615
|
|
},
|
|
{
|
|
"entropy": 5.559367942810058,
|
|
"epoch": 2.0464470027788804,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00045839759639468774,
|
|
"loss": 5.0265,
|
|
"mean_token_accuracy": 0.18383753448724746,
|
|
"num_tokens": 45183957.0,
|
|
"step": 20620
|
|
},
|
|
{
|
|
"entropy": 5.605564212799072,
|
|
"epoch": 2.046943231441048,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004583770679578628,
|
|
"loss": 5.1133,
|
|
"mean_token_accuracy": 0.1812033087015152,
|
|
"num_tokens": 45195607.0,
|
|
"step": 20625
|
|
},
|
|
{
|
|
"entropy": 5.54872465133667,
|
|
"epoch": 2.0474394601032158,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004583565349736818,
|
|
"loss": 5.0028,
|
|
"mean_token_accuracy": 0.1790957823395729,
|
|
"num_tokens": 45205627.0,
|
|
"step": 20630
|
|
},
|
|
{
|
|
"entropy": 5.530519294738769,
|
|
"epoch": 2.0479356887653832,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004583359974426538,
|
|
"loss": 5.0661,
|
|
"mean_token_accuracy": 0.1742791309952736,
|
|
"num_tokens": 45216331.0,
|
|
"step": 20635
|
|
},
|
|
{
|
|
"entropy": 5.567686986923218,
|
|
"epoch": 2.0484319174275507,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00045831545536528806,
|
|
"loss": 5.0862,
|
|
"mean_token_accuracy": 0.16973341405391693,
|
|
"num_tokens": 45227826.0,
|
|
"step": 20640
|
|
},
|
|
{
|
|
"entropy": 5.595687961578369,
|
|
"epoch": 2.048928146089718,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00045829490874209404,
|
|
"loss": 5.0147,
|
|
"mean_token_accuracy": 0.18066619485616683,
|
|
"num_tokens": 45238093.0,
|
|
"step": 20645
|
|
},
|
|
{
|
|
"entropy": 5.571276521682739,
|
|
"epoch": 2.0494243747518857,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00045827435757358136,
|
|
"loss": 5.0443,
|
|
"mean_token_accuracy": 0.18174657374620437,
|
|
"num_tokens": 45248660.0,
|
|
"step": 20650
|
|
},
|
|
{
|
|
"entropy": 5.636414813995361,
|
|
"epoch": 2.049920603414053,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004582538018602594,
|
|
"loss": 5.1127,
|
|
"mean_token_accuracy": 0.1737897887825966,
|
|
"num_tokens": 45261059.0,
|
|
"step": 20655
|
|
},
|
|
{
|
|
"entropy": 5.557131910324097,
|
|
"epoch": 2.0504168320762206,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004582332416026381,
|
|
"loss": 5.0132,
|
|
"mean_token_accuracy": 0.1771009922027588,
|
|
"num_tokens": 45272210.0,
|
|
"step": 20660
|
|
},
|
|
{
|
|
"entropy": 5.6142806053161625,
|
|
"epoch": 2.050913060738388,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00045821267680122725,
|
|
"loss": 5.1071,
|
|
"mean_token_accuracy": 0.1789221405982971,
|
|
"num_tokens": 45283488.0,
|
|
"step": 20665
|
|
},
|
|
{
|
|
"entropy": 5.565041828155517,
|
|
"epoch": 2.0514092894005556,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004581921074565368,
|
|
"loss": 4.9556,
|
|
"mean_token_accuracy": 0.186887463927269,
|
|
"num_tokens": 45292824.0,
|
|
"step": 20670
|
|
},
|
|
{
|
|
"entropy": 5.557746458053589,
|
|
"epoch": 2.0519055180627235,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004581715335690768,
|
|
"loss": 5.0468,
|
|
"mean_token_accuracy": 0.17812294661998748,
|
|
"num_tokens": 45303102.0,
|
|
"step": 20675
|
|
},
|
|
{
|
|
"entropy": 5.580737829208374,
|
|
"epoch": 2.052401746724891,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00045815095513935747,
|
|
"loss": 4.9565,
|
|
"mean_token_accuracy": 0.17806898355484008,
|
|
"num_tokens": 45313825.0,
|
|
"step": 20680
|
|
},
|
|
{
|
|
"entropy": 5.549282169342041,
|
|
"epoch": 2.0528979753870584,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004581303721678891,
|
|
"loss": 5.0033,
|
|
"mean_token_accuracy": 0.1876699820160866,
|
|
"num_tokens": 45325789.0,
|
|
"step": 20685
|
|
},
|
|
{
|
|
"entropy": 5.570593595504761,
|
|
"epoch": 2.053394204049226,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004581097846551821,
|
|
"loss": 5.0795,
|
|
"mean_token_accuracy": 0.1743321478366852,
|
|
"num_tokens": 45337630.0,
|
|
"step": 20690
|
|
},
|
|
{
|
|
"entropy": 5.640217065811157,
|
|
"epoch": 2.0538904327113934,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.000458089192601747,
|
|
"loss": 5.0978,
|
|
"mean_token_accuracy": 0.17524106204509735,
|
|
"num_tokens": 45349815.0,
|
|
"step": 20695
|
|
},
|
|
{
|
|
"entropy": 5.586354780197143,
|
|
"epoch": 2.054386661373561,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00045806859600809455,
|
|
"loss": 5.0368,
|
|
"mean_token_accuracy": 0.17634499669075013,
|
|
"num_tokens": 45360741.0,
|
|
"step": 20700
|
|
},
|
|
{
|
|
"entropy": 5.476849508285523,
|
|
"epoch": 2.0548828900357283,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004580479948747353,
|
|
"loss": 4.9155,
|
|
"mean_token_accuracy": 0.18714760094881058,
|
|
"num_tokens": 45371258.0,
|
|
"step": 20705
|
|
},
|
|
{
|
|
"entropy": 5.587560987472534,
|
|
"epoch": 2.055379118697896,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00045802738920218015,
|
|
"loss": 5.045,
|
|
"mean_token_accuracy": 0.17742789685726165,
|
|
"num_tokens": 45381914.0,
|
|
"step": 20710
|
|
},
|
|
{
|
|
"entropy": 5.555529451370239,
|
|
"epoch": 2.0558753473600637,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004580067789909403,
|
|
"loss": 5.0516,
|
|
"mean_token_accuracy": 0.1820403218269348,
|
|
"num_tokens": 45393159.0,
|
|
"step": 20715
|
|
},
|
|
{
|
|
"entropy": 5.545459651947022,
|
|
"epoch": 2.056371576022231,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00045798616424152654,
|
|
"loss": 4.9319,
|
|
"mean_token_accuracy": 0.18739939481019974,
|
|
"num_tokens": 45403076.0,
|
|
"step": 20720
|
|
},
|
|
{
|
|
"entropy": 5.561541271209717,
|
|
"epoch": 2.0568678046843987,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00045796554495445023,
|
|
"loss": 5.0797,
|
|
"mean_token_accuracy": 0.1781062051653862,
|
|
"num_tokens": 45412962.0,
|
|
"step": 20725
|
|
},
|
|
{
|
|
"entropy": 5.5583171367645265,
|
|
"epoch": 2.057364033346566,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004579449211302228,
|
|
"loss": 4.9967,
|
|
"mean_token_accuracy": 0.1842828556895256,
|
|
"num_tokens": 45423620.0,
|
|
"step": 20730
|
|
},
|
|
{
|
|
"entropy": 5.584582662582397,
|
|
"epoch": 2.0578602620087336,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004579242927693554,
|
|
"loss": 5.037,
|
|
"mean_token_accuracy": 0.17163565903902053,
|
|
"num_tokens": 45435901.0,
|
|
"step": 20735
|
|
},
|
|
{
|
|
"entropy": 5.574634218215943,
|
|
"epoch": 2.058356490670901,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004579036598723598,
|
|
"loss": 4.9683,
|
|
"mean_token_accuracy": 0.19019347727298735,
|
|
"num_tokens": 45445409.0,
|
|
"step": 20740
|
|
},
|
|
{
|
|
"entropy": 5.6521838188171385,
|
|
"epoch": 2.0588527193330686,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00045788302243974745,
|
|
"loss": 5.1238,
|
|
"mean_token_accuracy": 0.1788850173354149,
|
|
"num_tokens": 45455794.0,
|
|
"step": 20745
|
|
},
|
|
{
|
|
"entropy": 5.595630216598511,
|
|
"epoch": 2.059348947995236,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004578623804720302,
|
|
"loss": 4.9991,
|
|
"mean_token_accuracy": 0.18362150490283966,
|
|
"num_tokens": 45465922.0,
|
|
"step": 20750
|
|
},
|
|
{
|
|
"entropy": 5.556346273422241,
|
|
"epoch": 2.0598451766574035,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004578417339697201,
|
|
"loss": 5.1042,
|
|
"mean_token_accuracy": 0.1750722348690033,
|
|
"num_tokens": 45476314.0,
|
|
"step": 20755
|
|
},
|
|
{
|
|
"entropy": 5.588579797744751,
|
|
"epoch": 2.0603414053195714,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00045782108293332884,
|
|
"loss": 5.0197,
|
|
"mean_token_accuracy": 0.1753836527466774,
|
|
"num_tokens": 45487232.0,
|
|
"step": 20760
|
|
},
|
|
{
|
|
"entropy": 5.664383506774902,
|
|
"epoch": 2.060837633981739,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004578004273633687,
|
|
"loss": 5.0885,
|
|
"mean_token_accuracy": 0.18001712560653688,
|
|
"num_tokens": 45498368.0,
|
|
"step": 20765
|
|
},
|
|
{
|
|
"entropy": 5.57822003364563,
|
|
"epoch": 2.0613338626439064,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00045777976726035194,
|
|
"loss": 5.0287,
|
|
"mean_token_accuracy": 0.17257740795612336,
|
|
"num_tokens": 45507600.0,
|
|
"step": 20770
|
|
},
|
|
{
|
|
"entropy": 5.590188694000244,
|
|
"epoch": 2.061830091306074,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004577591026247907,
|
|
"loss": 5.1225,
|
|
"mean_token_accuracy": 0.16889785826206208,
|
|
"num_tokens": 45518594.0,
|
|
"step": 20775
|
|
},
|
|
{
|
|
"entropy": 5.566431140899658,
|
|
"epoch": 2.0623263199682413,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004577384334571976,
|
|
"loss": 4.9925,
|
|
"mean_token_accuracy": 0.17890307307243347,
|
|
"num_tokens": 45529929.0,
|
|
"step": 20780
|
|
},
|
|
{
|
|
"entropy": 5.577402019500733,
|
|
"epoch": 2.062822548630409,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004577177597580851,
|
|
"loss": 5.0013,
|
|
"mean_token_accuracy": 0.18637326806783677,
|
|
"num_tokens": 45540228.0,
|
|
"step": 20785
|
|
},
|
|
{
|
|
"entropy": 5.521492528915405,
|
|
"epoch": 2.0633187772925763,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00045769708152796593,
|
|
"loss": 4.9699,
|
|
"mean_token_accuracy": 0.18163398802280425,
|
|
"num_tokens": 45552026.0,
|
|
"step": 20790
|
|
},
|
|
{
|
|
"entropy": 5.519711446762085,
|
|
"epoch": 2.0638150059547438,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00045767639876735276,
|
|
"loss": 5.0472,
|
|
"mean_token_accuracy": 0.1865169957280159,
|
|
"num_tokens": 45563579.0,
|
|
"step": 20795
|
|
},
|
|
{
|
|
"entropy": 5.650913572311401,
|
|
"epoch": 2.0643112346169117,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004576557114767585,
|
|
"loss": 5.1299,
|
|
"mean_token_accuracy": 0.17230444103479386,
|
|
"num_tokens": 45573800.0,
|
|
"step": 20800
|
|
},
|
|
{
|
|
"entropy": 5.556518840789795,
|
|
"epoch": 2.064807463279079,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00045763501965669627,
|
|
"loss": 5.0027,
|
|
"mean_token_accuracy": 0.17949966043233873,
|
|
"num_tokens": 45583758.0,
|
|
"step": 20805
|
|
},
|
|
{
|
|
"entropy": 5.580332851409912,
|
|
"epoch": 2.0653036919412466,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.000457614323307679,
|
|
"loss": 5.0007,
|
|
"mean_token_accuracy": 0.18121497631072997,
|
|
"num_tokens": 45595154.0,
|
|
"step": 20810
|
|
},
|
|
{
|
|
"entropy": 5.621364593505859,
|
|
"epoch": 2.065799920603414,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00045759362243022,
|
|
"loss": 5.1041,
|
|
"mean_token_accuracy": 0.17656422704458236,
|
|
"num_tokens": 45606557.0,
|
|
"step": 20815
|
|
},
|
|
{
|
|
"entropy": 5.539298009872437,
|
|
"epoch": 2.0662961492655816,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004575729170248327,
|
|
"loss": 4.9654,
|
|
"mean_token_accuracy": 0.18942419141530992,
|
|
"num_tokens": 45615531.0,
|
|
"step": 20820
|
|
},
|
|
{
|
|
"entropy": 5.498677349090576,
|
|
"epoch": 2.066792377927749,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004575522070920305,
|
|
"loss": 4.9728,
|
|
"mean_token_accuracy": 0.1830257222056389,
|
|
"num_tokens": 45626512.0,
|
|
"step": 20825
|
|
},
|
|
{
|
|
"entropy": 5.6015135765075685,
|
|
"epoch": 2.0672886065899165,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00045753149263232687,
|
|
"loss": 5.0803,
|
|
"mean_token_accuracy": 0.17098679393529892,
|
|
"num_tokens": 45638005.0,
|
|
"step": 20830
|
|
},
|
|
{
|
|
"entropy": 5.598339986801148,
|
|
"epoch": 2.067784835252084,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004575107736462355,
|
|
"loss": 5.0812,
|
|
"mean_token_accuracy": 0.17462422102689742,
|
|
"num_tokens": 45647740.0,
|
|
"step": 20835
|
|
},
|
|
{
|
|
"entropy": 5.544892501831055,
|
|
"epoch": 2.0682810639142515,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004574900501342703,
|
|
"loss": 5.0056,
|
|
"mean_token_accuracy": 0.18812091648578644,
|
|
"num_tokens": 45659021.0,
|
|
"step": 20840
|
|
},
|
|
{
|
|
"entropy": 5.579664802551269,
|
|
"epoch": 2.0687772925764194,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004574693220969451,
|
|
"loss": 5.0811,
|
|
"mean_token_accuracy": 0.17835566401481628,
|
|
"num_tokens": 45669413.0,
|
|
"step": 20845
|
|
},
|
|
{
|
|
"entropy": 5.667920875549316,
|
|
"epoch": 2.069273521238587,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004574485895347738,
|
|
"loss": 5.1388,
|
|
"mean_token_accuracy": 0.17369325011968612,
|
|
"num_tokens": 45680719.0,
|
|
"step": 20850
|
|
},
|
|
{
|
|
"entropy": 5.518199396133423,
|
|
"epoch": 2.0697697499007544,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00045742785244827066,
|
|
"loss": 4.9628,
|
|
"mean_token_accuracy": 0.18290352523326875,
|
|
"num_tokens": 45690393.0,
|
|
"step": 20855
|
|
},
|
|
{
|
|
"entropy": 5.548664474487305,
|
|
"epoch": 2.070265978562922,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004574071108379499,
|
|
"loss": 5.0783,
|
|
"mean_token_accuracy": 0.17684251368045806,
|
|
"num_tokens": 45701304.0,
|
|
"step": 20860
|
|
},
|
|
{
|
|
"entropy": 5.5731456756591795,
|
|
"epoch": 2.0707622072250893,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004573863647043259,
|
|
"loss": 4.9414,
|
|
"mean_token_accuracy": 0.18446728438138962,
|
|
"num_tokens": 45711892.0,
|
|
"step": 20865
|
|
},
|
|
{
|
|
"entropy": 5.581446313858033,
|
|
"epoch": 2.0712584358872568,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004573656140479129,
|
|
"loss": 5.0151,
|
|
"mean_token_accuracy": 0.1787782147526741,
|
|
"num_tokens": 45723693.0,
|
|
"step": 20870
|
|
},
|
|
{
|
|
"entropy": 5.5282111167907715,
|
|
"epoch": 2.0717546645494243,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004573448588692258,
|
|
"loss": 5.0033,
|
|
"mean_token_accuracy": 0.17832859605550766,
|
|
"num_tokens": 45734392.0,
|
|
"step": 20875
|
|
},
|
|
{
|
|
"entropy": 5.464937925338745,
|
|
"epoch": 2.0722508932115917,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000457324099168779,
|
|
"loss": 4.9329,
|
|
"mean_token_accuracy": 0.19012268781661987,
|
|
"num_tokens": 45745732.0,
|
|
"step": 20880
|
|
},
|
|
{
|
|
"entropy": 5.52878246307373,
|
|
"epoch": 2.0727471218737596,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004573033349470874,
|
|
"loss": 4.99,
|
|
"mean_token_accuracy": 0.18597166687250138,
|
|
"num_tokens": 45756671.0,
|
|
"step": 20885
|
|
},
|
|
{
|
|
"entropy": 5.636493492126465,
|
|
"epoch": 2.073243350535927,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004572825662046661,
|
|
"loss": 5.1048,
|
|
"mean_token_accuracy": 0.17231640368700027,
|
|
"num_tokens": 45767685.0,
|
|
"step": 20890
|
|
},
|
|
{
|
|
"entropy": 5.59394941329956,
|
|
"epoch": 2.0737395791980946,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004572617929420298,
|
|
"loss": 5.01,
|
|
"mean_token_accuracy": 0.18423440754413606,
|
|
"num_tokens": 45777251.0,
|
|
"step": 20895
|
|
},
|
|
{
|
|
"entropy": 5.6230322360992435,
|
|
"epoch": 2.074235807860262,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00045724101515969375,
|
|
"loss": 5.0783,
|
|
"mean_token_accuracy": 0.18082635700702668,
|
|
"num_tokens": 45790037.0,
|
|
"step": 20900
|
|
},
|
|
{
|
|
"entropy": 5.601011610031128,
|
|
"epoch": 2.0747320365224295,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00045722023285817327,
|
|
"loss": 5.1267,
|
|
"mean_token_accuracy": 0.17161785960197448,
|
|
"num_tokens": 45800803.0,
|
|
"step": 20905
|
|
},
|
|
{
|
|
"entropy": 5.622574949264527,
|
|
"epoch": 2.075228265184597,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004571994460379837,
|
|
"loss": 5.0605,
|
|
"mean_token_accuracy": 0.17137459367513658,
|
|
"num_tokens": 45812447.0,
|
|
"step": 20910
|
|
},
|
|
{
|
|
"entropy": 5.591508960723877,
|
|
"epoch": 2.0757244938467645,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00045717865469964045,
|
|
"loss": 5.0135,
|
|
"mean_token_accuracy": 0.18045831173658372,
|
|
"num_tokens": 45822172.0,
|
|
"step": 20915
|
|
},
|
|
{
|
|
"entropy": 5.6481201171875,
|
|
"epoch": 2.076220722508932,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00045715785884365914,
|
|
"loss": 5.1355,
|
|
"mean_token_accuracy": 0.1753174141049385,
|
|
"num_tokens": 45832583.0,
|
|
"step": 20920
|
|
},
|
|
{
|
|
"entropy": 5.630967044830323,
|
|
"epoch": 2.0767169511710994,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00045713705847055537,
|
|
"loss": 5.1425,
|
|
"mean_token_accuracy": 0.17449038326740265,
|
|
"num_tokens": 45842640.0,
|
|
"step": 20925
|
|
},
|
|
{
|
|
"entropy": 5.637538766860962,
|
|
"epoch": 2.0772131798332674,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004571162535808451,
|
|
"loss": 5.1388,
|
|
"mean_token_accuracy": 0.17166436910629274,
|
|
"num_tokens": 45854618.0,
|
|
"step": 20930
|
|
},
|
|
{
|
|
"entropy": 5.60342173576355,
|
|
"epoch": 2.077709408495435,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004570954441750441,
|
|
"loss": 5.0317,
|
|
"mean_token_accuracy": 0.18146111220121383,
|
|
"num_tokens": 45866130.0,
|
|
"step": 20935
|
|
},
|
|
{
|
|
"entropy": 5.628126239776611,
|
|
"epoch": 2.0782056371576023,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004570746302536685,
|
|
"loss": 5.057,
|
|
"mean_token_accuracy": 0.17616796046495437,
|
|
"num_tokens": 45877187.0,
|
|
"step": 20940
|
|
},
|
|
{
|
|
"entropy": 5.549054765701294,
|
|
"epoch": 2.07870186581977,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00045705381181723444,
|
|
"loss": 5.0679,
|
|
"mean_token_accuracy": 0.17600455582141877,
|
|
"num_tokens": 45889557.0,
|
|
"step": 20945
|
|
},
|
|
{
|
|
"entropy": 5.573263311386109,
|
|
"epoch": 2.0791980944819373,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00045703298886625804,
|
|
"loss": 5.0654,
|
|
"mean_token_accuracy": 0.1764945477247238,
|
|
"num_tokens": 45900860.0,
|
|
"step": 20950
|
|
},
|
|
{
|
|
"entropy": 5.593493032455444,
|
|
"epoch": 2.0796943231441047,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004570121614012558,
|
|
"loss": 5.0869,
|
|
"mean_token_accuracy": 0.1741206780076027,
|
|
"num_tokens": 45912231.0,
|
|
"step": 20955
|
|
},
|
|
{
|
|
"entropy": 5.642436122894287,
|
|
"epoch": 2.080190551806272,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00045699132942274425,
|
|
"loss": 5.1233,
|
|
"mean_token_accuracy": 0.17317160815000535,
|
|
"num_tokens": 45922722.0,
|
|
"step": 20960
|
|
},
|
|
{
|
|
"entropy": 5.580073833465576,
|
|
"epoch": 2.0806867804684397,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00045697049293123984,
|
|
"loss": 5.0352,
|
|
"mean_token_accuracy": 0.18277282565832137,
|
|
"num_tokens": 45932444.0,
|
|
"step": 20965
|
|
},
|
|
{
|
|
"entropy": 5.633468198776245,
|
|
"epoch": 2.0811830091306076,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004569496519272593,
|
|
"loss": 5.0605,
|
|
"mean_token_accuracy": 0.18099953830242158,
|
|
"num_tokens": 45942826.0,
|
|
"step": 20970
|
|
},
|
|
{
|
|
"entropy": 5.600572204589843,
|
|
"epoch": 2.081679237792775,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00045692880641131945,
|
|
"loss": 5.055,
|
|
"mean_token_accuracy": 0.18229408115148543,
|
|
"num_tokens": 45953935.0,
|
|
"step": 20975
|
|
},
|
|
{
|
|
"entropy": 5.627800035476684,
|
|
"epoch": 2.0821754664549426,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004569079563839372,
|
|
"loss": 5.1464,
|
|
"mean_token_accuracy": 0.17057626247406005,
|
|
"num_tokens": 45964693.0,
|
|
"step": 20980
|
|
},
|
|
{
|
|
"entropy": 5.63632116317749,
|
|
"epoch": 2.08267169511711,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00045688710184562965,
|
|
"loss": 5.0366,
|
|
"mean_token_accuracy": 0.174713633954525,
|
|
"num_tokens": 45976481.0,
|
|
"step": 20985
|
|
},
|
|
{
|
|
"entropy": 5.652490949630737,
|
|
"epoch": 2.0831679237792775,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00045686624279691387,
|
|
"loss": 5.1148,
|
|
"mean_token_accuracy": 0.18101923912763596,
|
|
"num_tokens": 45988879.0,
|
|
"step": 20990
|
|
},
|
|
{
|
|
"entropy": 5.561849355697632,
|
|
"epoch": 2.083664152441445,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004568453792383072,
|
|
"loss": 5.0078,
|
|
"mean_token_accuracy": 0.18511599600315093,
|
|
"num_tokens": 45999332.0,
|
|
"step": 20995
|
|
},
|
|
{
|
|
"entropy": 5.597072505950928,
|
|
"epoch": 2.0841603811036125,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000456824511170327,
|
|
"loss": 5.046,
|
|
"mean_token_accuracy": 0.17673124521970748,
|
|
"num_tokens": 46009841.0,
|
|
"step": 21000
|
|
},
|
|
{
|
|
"epoch": 2.0841603811036125,
|
|
"eval_entropy": 5.378207194037606,
|
|
"eval_loss": 5.182725429534912,
|
|
"eval_mean_token_accuracy": 0.17813740089008206,
|
|
"eval_num_tokens": 46009841.0,
|
|
"eval_runtime": 20.5344,
|
|
"eval_samples_per_second": 1639.64,
|
|
"eval_steps_per_second": 204.973,
|
|
"step": 21000
|
|
},
|
|
{
|
|
"entropy": 5.549616813659668,
|
|
"epoch": 2.08465660976578,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004568036385934906,
|
|
"loss": 4.9721,
|
|
"mean_token_accuracy": 0.18178554326295854,
|
|
"num_tokens": 46020678.0,
|
|
"step": 21005
|
|
},
|
|
{
|
|
"entropy": 5.596362352371216,
|
|
"epoch": 2.0851528384279474,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00045678276150831586,
|
|
"loss": 5.0583,
|
|
"mean_token_accuracy": 0.176519213616848,
|
|
"num_tokens": 46032036.0,
|
|
"step": 21010
|
|
},
|
|
{
|
|
"entropy": 5.606713151931762,
|
|
"epoch": 2.0856490670901153,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004567618799153202,
|
|
"loss": 5.0492,
|
|
"mean_token_accuracy": 0.17937204688787461,
|
|
"num_tokens": 46042675.0,
|
|
"step": 21015
|
|
},
|
|
{
|
|
"entropy": 5.5188436031341555,
|
|
"epoch": 2.086145295752283,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00045674099381502167,
|
|
"loss": 5.064,
|
|
"mean_token_accuracy": 0.1755911096930504,
|
|
"num_tokens": 46053616.0,
|
|
"step": 21020
|
|
},
|
|
{
|
|
"entropy": 5.60694580078125,
|
|
"epoch": 2.0866415244144503,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004567201032079381,
|
|
"loss": 5.0804,
|
|
"mean_token_accuracy": 0.1770681068301201,
|
|
"num_tokens": 46063755.0,
|
|
"step": 21025
|
|
},
|
|
{
|
|
"entropy": 5.634601068496704,
|
|
"epoch": 2.0871377530766178,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00045669920809458754,
|
|
"loss": 5.0601,
|
|
"mean_token_accuracy": 0.18070498555898667,
|
|
"num_tokens": 46074459.0,
|
|
"step": 21030
|
|
},
|
|
{
|
|
"entropy": 5.676368474960327,
|
|
"epoch": 2.0876339817387852,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004566783084754881,
|
|
"loss": 5.1244,
|
|
"mean_token_accuracy": 0.17696245908737182,
|
|
"num_tokens": 46085053.0,
|
|
"step": 21035
|
|
},
|
|
{
|
|
"entropy": 5.5432586669921875,
|
|
"epoch": 2.0881302104009527,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00045665740435115815,
|
|
"loss": 4.9672,
|
|
"mean_token_accuracy": 0.18689364790916443,
|
|
"num_tokens": 46094697.0,
|
|
"step": 21040
|
|
},
|
|
{
|
|
"entropy": 5.554885816574097,
|
|
"epoch": 2.08862643906312,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000456636495722116,
|
|
"loss": 5.0853,
|
|
"mean_token_accuracy": 0.17936250269412995,
|
|
"num_tokens": 46105617.0,
|
|
"step": 21045
|
|
},
|
|
{
|
|
"entropy": 5.668656253814698,
|
|
"epoch": 2.0891226677252877,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004566155825888801,
|
|
"loss": 5.0325,
|
|
"mean_token_accuracy": 0.18122997283935546,
|
|
"num_tokens": 46115450.0,
|
|
"step": 21050
|
|
},
|
|
{
|
|
"entropy": 5.590940666198731,
|
|
"epoch": 2.089618896387455,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004565946649519691,
|
|
"loss": 5.1039,
|
|
"mean_token_accuracy": 0.17471627295017242,
|
|
"num_tokens": 46126511.0,
|
|
"step": 21055
|
|
},
|
|
{
|
|
"entropy": 5.581959390640259,
|
|
"epoch": 2.090115125049623,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00045657374281190177,
|
|
"loss": 5.0017,
|
|
"mean_token_accuracy": 0.18319119811058043,
|
|
"num_tokens": 46136294.0,
|
|
"step": 21060
|
|
},
|
|
{
|
|
"entropy": 5.576907157897949,
|
|
"epoch": 2.0906113537117905,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004565528161691969,
|
|
"loss": 5.0833,
|
|
"mean_token_accuracy": 0.17087069451808928,
|
|
"num_tokens": 46148926.0,
|
|
"step": 21065
|
|
},
|
|
{
|
|
"entropy": 5.626527452468872,
|
|
"epoch": 2.091107582373958,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004565318850243733,
|
|
"loss": 5.0837,
|
|
"mean_token_accuracy": 0.18009043782949447,
|
|
"num_tokens": 46160130.0,
|
|
"step": 21070
|
|
},
|
|
{
|
|
"entropy": 5.5552350044250485,
|
|
"epoch": 2.0916038110361255,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004565109493779502,
|
|
"loss": 4.9911,
|
|
"mean_token_accuracy": 0.1845992088317871,
|
|
"num_tokens": 46169919.0,
|
|
"step": 21075
|
|
},
|
|
{
|
|
"entropy": 5.603697395324707,
|
|
"epoch": 2.092100039698293,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00045649000923044664,
|
|
"loss": 5.0767,
|
|
"mean_token_accuracy": 0.1763385906815529,
|
|
"num_tokens": 46181186.0,
|
|
"step": 21080
|
|
},
|
|
{
|
|
"entropy": 5.597004985809326,
|
|
"epoch": 2.0925962683604604,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00045646906458238196,
|
|
"loss": 5.077,
|
|
"mean_token_accuracy": 0.17143227756023408,
|
|
"num_tokens": 46192172.0,
|
|
"step": 21085
|
|
},
|
|
{
|
|
"entropy": 5.579356384277344,
|
|
"epoch": 2.093092497022628,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004564481154342754,
|
|
"loss": 5.0511,
|
|
"mean_token_accuracy": 0.17318841218948364,
|
|
"num_tokens": 46202678.0,
|
|
"step": 21090
|
|
},
|
|
{
|
|
"entropy": 5.604232311248779,
|
|
"epoch": 2.0935887256847954,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004564271617866467,
|
|
"loss": 5.0585,
|
|
"mean_token_accuracy": 0.17549093961715698,
|
|
"num_tokens": 46212213.0,
|
|
"step": 21095
|
|
},
|
|
{
|
|
"entropy": 5.658325958251953,
|
|
"epoch": 2.0940849543469633,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00045640620364001524,
|
|
"loss": 5.0877,
|
|
"mean_token_accuracy": 0.17705549746751786,
|
|
"num_tokens": 46223044.0,
|
|
"step": 21100
|
|
},
|
|
{
|
|
"entropy": 5.64846773147583,
|
|
"epoch": 2.0945811830091308,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00045638524099490086,
|
|
"loss": 5.0949,
|
|
"mean_token_accuracy": 0.18088916093111038,
|
|
"num_tokens": 46236008.0,
|
|
"step": 21105
|
|
},
|
|
{
|
|
"entropy": 5.559442663192749,
|
|
"epoch": 2.0950774116712982,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00045636427385182334,
|
|
"loss": 5.0494,
|
|
"mean_token_accuracy": 0.1757390931248665,
|
|
"num_tokens": 46247631.0,
|
|
"step": 21110
|
|
},
|
|
{
|
|
"entropy": 5.583029460906983,
|
|
"epoch": 2.0955736403334657,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00045634330221130265,
|
|
"loss": 5.0186,
|
|
"mean_token_accuracy": 0.17828223407268523,
|
|
"num_tokens": 46258294.0,
|
|
"step": 21115
|
|
},
|
|
{
|
|
"entropy": 5.602357721328735,
|
|
"epoch": 2.096069868995633,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004563223260738589,
|
|
"loss": 5.0279,
|
|
"mean_token_accuracy": 0.1764216259121895,
|
|
"num_tokens": 46269611.0,
|
|
"step": 21120
|
|
},
|
|
{
|
|
"entropy": 5.579091024398804,
|
|
"epoch": 2.0965660976578007,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000456301345440012,
|
|
"loss": 5.1014,
|
|
"mean_token_accuracy": 0.1849465474486351,
|
|
"num_tokens": 46280731.0,
|
|
"step": 21125
|
|
},
|
|
{
|
|
"entropy": 5.563394832611084,
|
|
"epoch": 2.097062326319968,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004562803603102825,
|
|
"loss": 5.0249,
|
|
"mean_token_accuracy": 0.1745460405945778,
|
|
"num_tokens": 46290226.0,
|
|
"step": 21130
|
|
},
|
|
{
|
|
"entropy": 5.623651313781738,
|
|
"epoch": 2.0975585549821356,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00045625937068519075,
|
|
"loss": 5.0362,
|
|
"mean_token_accuracy": 0.17938980907201768,
|
|
"num_tokens": 46300388.0,
|
|
"step": 21135
|
|
},
|
|
{
|
|
"entropy": 5.58364429473877,
|
|
"epoch": 2.098054783644303,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004562383765652571,
|
|
"loss": 5.0781,
|
|
"mean_token_accuracy": 0.18040805459022521,
|
|
"num_tokens": 46312214.0,
|
|
"step": 21140
|
|
},
|
|
{
|
|
"entropy": 5.605428457260132,
|
|
"epoch": 2.098551012306471,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004562173779510023,
|
|
"loss": 5.0853,
|
|
"mean_token_accuracy": 0.16679899394512177,
|
|
"num_tokens": 46322728.0,
|
|
"step": 21145
|
|
},
|
|
{
|
|
"entropy": 5.55753345489502,
|
|
"epoch": 2.0990472409686385,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.000456196374842947,
|
|
"loss": 5.0137,
|
|
"mean_token_accuracy": 0.18286693692207337,
|
|
"num_tokens": 46334169.0,
|
|
"step": 21150
|
|
},
|
|
{
|
|
"entropy": 5.59223051071167,
|
|
"epoch": 2.099543469630806,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00045617536724161203,
|
|
"loss": 4.9982,
|
|
"mean_token_accuracy": 0.17731491923332215,
|
|
"num_tokens": 46344601.0,
|
|
"step": 21155
|
|
},
|
|
{
|
|
"entropy": 5.576746559143066,
|
|
"epoch": 2.1000396982929734,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00045615435514751834,
|
|
"loss": 5.0743,
|
|
"mean_token_accuracy": 0.17338691800832748,
|
|
"num_tokens": 46355633.0,
|
|
"step": 21160
|
|
},
|
|
{
|
|
"entropy": 5.609165668487549,
|
|
"epoch": 2.100535926955141,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.000456133338561187,
|
|
"loss": 5.1392,
|
|
"mean_token_accuracy": 0.16641507893800736,
|
|
"num_tokens": 46365981.0,
|
|
"step": 21165
|
|
},
|
|
{
|
|
"entropy": 5.617049264907837,
|
|
"epoch": 2.1010321556173084,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004561123174831391,
|
|
"loss": 5.0966,
|
|
"mean_token_accuracy": 0.18057404905557634,
|
|
"num_tokens": 46376664.0,
|
|
"step": 21170
|
|
},
|
|
{
|
|
"entropy": 5.558592653274536,
|
|
"epoch": 2.101528384279476,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004560912919138962,
|
|
"loss": 5.005,
|
|
"mean_token_accuracy": 0.1823573961853981,
|
|
"num_tokens": 46387918.0,
|
|
"step": 21175
|
|
},
|
|
{
|
|
"entropy": 5.637909650802612,
|
|
"epoch": 2.1020246129416433,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00045607026185397924,
|
|
"loss": 5.0274,
|
|
"mean_token_accuracy": 0.1830432340502739,
|
|
"num_tokens": 46398660.0,
|
|
"step": 21180
|
|
},
|
|
{
|
|
"entropy": 5.574792861938477,
|
|
"epoch": 2.102520841603811,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004560492273039101,
|
|
"loss": 4.9803,
|
|
"mean_token_accuracy": 0.18094398230314254,
|
|
"num_tokens": 46409365.0,
|
|
"step": 21185
|
|
},
|
|
{
|
|
"entropy": 5.567476844787597,
|
|
"epoch": 2.1030170702659787,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00045602818826421024,
|
|
"loss": 4.9945,
|
|
"mean_token_accuracy": 0.18630912601947786,
|
|
"num_tokens": 46419457.0,
|
|
"step": 21190
|
|
},
|
|
{
|
|
"entropy": 5.569611120223999,
|
|
"epoch": 2.103513298928146,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004560071447354013,
|
|
"loss": 5.0868,
|
|
"mean_token_accuracy": 0.17638052105903626,
|
|
"num_tokens": 46430189.0,
|
|
"step": 21195
|
|
},
|
|
{
|
|
"entropy": 5.5185614109039305,
|
|
"epoch": 2.1040095275903137,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004559860967180053,
|
|
"loss": 5.0292,
|
|
"mean_token_accuracy": 0.18278742134571074,
|
|
"num_tokens": 46440555.0,
|
|
"step": 21200
|
|
},
|
|
{
|
|
"entropy": 5.65135498046875,
|
|
"epoch": 2.104505756252481,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004559650442125441,
|
|
"loss": 5.0524,
|
|
"mean_token_accuracy": 0.1734270229935646,
|
|
"num_tokens": 46451582.0,
|
|
"step": 21205
|
|
},
|
|
{
|
|
"entropy": 5.700384044647217,
|
|
"epoch": 2.1050019849146486,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004559439872195397,
|
|
"loss": 5.0824,
|
|
"mean_token_accuracy": 0.17643293291330336,
|
|
"num_tokens": 46463614.0,
|
|
"step": 21210
|
|
},
|
|
{
|
|
"entropy": 5.634904289245606,
|
|
"epoch": 2.105498213576816,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004559229257395144,
|
|
"loss": 5.0733,
|
|
"mean_token_accuracy": 0.17539695501327515,
|
|
"num_tokens": 46474279.0,
|
|
"step": 21215
|
|
},
|
|
{
|
|
"entropy": 5.630218744277954,
|
|
"epoch": 2.1059944422389836,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00045590185977299025,
|
|
"loss": 5.1763,
|
|
"mean_token_accuracy": 0.17436592876911164,
|
|
"num_tokens": 46485531.0,
|
|
"step": 21220
|
|
},
|
|
{
|
|
"entropy": 5.5639465808868405,
|
|
"epoch": 2.106490670901151,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004558807893204899,
|
|
"loss": 4.9858,
|
|
"mean_token_accuracy": 0.18145814687013626,
|
|
"num_tokens": 46496197.0,
|
|
"step": 21225
|
|
},
|
|
{
|
|
"entropy": 5.614350986480713,
|
|
"epoch": 2.106986899563319,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004558597143825357,
|
|
"loss": 5.0644,
|
|
"mean_token_accuracy": 0.17861939668655397,
|
|
"num_tokens": 46506759.0,
|
|
"step": 21230
|
|
},
|
|
{
|
|
"entropy": 5.568059349060059,
|
|
"epoch": 2.1074831282254864,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004558386349596503,
|
|
"loss": 5.0681,
|
|
"mean_token_accuracy": 0.17717475593090057,
|
|
"num_tokens": 46518956.0,
|
|
"step": 21235
|
|
},
|
|
{
|
|
"entropy": 5.684637022018433,
|
|
"epoch": 2.107979356887654,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004558175510523564,
|
|
"loss": 5.1443,
|
|
"mean_token_accuracy": 0.1723005011677742,
|
|
"num_tokens": 46530109.0,
|
|
"step": 21240
|
|
},
|
|
{
|
|
"entropy": 5.635321807861328,
|
|
"epoch": 2.1084755855498214,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00045579646266117696,
|
|
"loss": 5.0007,
|
|
"mean_token_accuracy": 0.17881372272968293,
|
|
"num_tokens": 46542206.0,
|
|
"step": 21245
|
|
},
|
|
{
|
|
"entropy": 5.608251285552979,
|
|
"epoch": 2.108971814211989,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00045577536978663475,
|
|
"loss": 5.1574,
|
|
"mean_token_accuracy": 0.18266464322805404,
|
|
"num_tokens": 46554143.0,
|
|
"step": 21250
|
|
},
|
|
{
|
|
"entropy": 5.552614355087281,
|
|
"epoch": 2.1094680428741563,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004557542724292529,
|
|
"loss": 4.9873,
|
|
"mean_token_accuracy": 0.18234004825353622,
|
|
"num_tokens": 46565697.0,
|
|
"step": 21255
|
|
},
|
|
{
|
|
"entropy": 5.617684650421142,
|
|
"epoch": 2.109964271536324,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004557331705895545,
|
|
"loss": 5.0454,
|
|
"mean_token_accuracy": 0.17975567728281022,
|
|
"num_tokens": 46576358.0,
|
|
"step": 21260
|
|
},
|
|
{
|
|
"entropy": 5.618617820739746,
|
|
"epoch": 2.1104605001984913,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004557120642680631,
|
|
"loss": 5.0854,
|
|
"mean_token_accuracy": 0.17682051062583923,
|
|
"num_tokens": 46589422.0,
|
|
"step": 21265
|
|
},
|
|
{
|
|
"entropy": 5.582330846786499,
|
|
"epoch": 2.1109567288606588,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004556909534653018,
|
|
"loss": 5.0578,
|
|
"mean_token_accuracy": 0.18285891860723497,
|
|
"num_tokens": 46599623.0,
|
|
"step": 21270
|
|
},
|
|
{
|
|
"entropy": 5.584320545196533,
|
|
"epoch": 2.1114529575228267,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004556698381817942,
|
|
"loss": 4.9968,
|
|
"mean_token_accuracy": 0.1861279621720314,
|
|
"num_tokens": 46609321.0,
|
|
"step": 21275
|
|
},
|
|
{
|
|
"entropy": 5.525045394897461,
|
|
"epoch": 2.111949186184994,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000455648718418064,
|
|
"loss": 5.0684,
|
|
"mean_token_accuracy": 0.17370790094137192,
|
|
"num_tokens": 46620265.0,
|
|
"step": 21280
|
|
},
|
|
{
|
|
"entropy": 5.595817279815674,
|
|
"epoch": 2.1124454148471616,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004556275941746348,
|
|
"loss": 5.0825,
|
|
"mean_token_accuracy": 0.18267000168561937,
|
|
"num_tokens": 46630776.0,
|
|
"step": 21285
|
|
},
|
|
{
|
|
"entropy": 5.549660873413086,
|
|
"epoch": 2.112941643509329,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.00045560646545203044,
|
|
"loss": 4.9673,
|
|
"mean_token_accuracy": 0.18396178781986236,
|
|
"num_tokens": 46641382.0,
|
|
"step": 21290
|
|
},
|
|
{
|
|
"entropy": 5.523974895477295,
|
|
"epoch": 2.1134378721714966,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.00045558533225077496,
|
|
"loss": 4.9798,
|
|
"mean_token_accuracy": 0.18110697567462922,
|
|
"num_tokens": 46653589.0,
|
|
"step": 21295
|
|
},
|
|
{
|
|
"entropy": 5.54365119934082,
|
|
"epoch": 2.113934100833664,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.00045556419457139235,
|
|
"loss": 5.0228,
|
|
"mean_token_accuracy": 0.1827416092157364,
|
|
"num_tokens": 46664595.0,
|
|
"step": 21300
|
|
},
|
|
{
|
|
"entropy": 5.598300743103027,
|
|
"epoch": 2.1144303294958315,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00045554305241440684,
|
|
"loss": 5.0444,
|
|
"mean_token_accuracy": 0.1780799373984337,
|
|
"num_tokens": 46675453.0,
|
|
"step": 21305
|
|
},
|
|
{
|
|
"entropy": 5.557474088668823,
|
|
"epoch": 2.114926558157999,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004555219057803426,
|
|
"loss": 4.9611,
|
|
"mean_token_accuracy": 0.18098766803741456,
|
|
"num_tokens": 46685668.0,
|
|
"step": 21310
|
|
},
|
|
{
|
|
"entropy": 5.576448583602906,
|
|
"epoch": 2.115422786820167,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004555007546697242,
|
|
"loss": 5.0626,
|
|
"mean_token_accuracy": 0.1745098739862442,
|
|
"num_tokens": 46696144.0,
|
|
"step": 21315
|
|
},
|
|
{
|
|
"entropy": 5.593879127502442,
|
|
"epoch": 2.1159190154823344,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00045547959908307585,
|
|
"loss": 5.0453,
|
|
"mean_token_accuracy": 0.17621316462755204,
|
|
"num_tokens": 46707892.0,
|
|
"step": 21320
|
|
},
|
|
{
|
|
"entropy": 5.609086227416992,
|
|
"epoch": 2.116415244144502,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004554584390209225,
|
|
"loss": 5.0646,
|
|
"mean_token_accuracy": 0.18206441402435303,
|
|
"num_tokens": 46721099.0,
|
|
"step": 21325
|
|
},
|
|
{
|
|
"entropy": 5.61162543296814,
|
|
"epoch": 2.1169114728066694,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004554372744837886,
|
|
"loss": 5.0917,
|
|
"mean_token_accuracy": 0.1766042962670326,
|
|
"num_tokens": 46732974.0,
|
|
"step": 21330
|
|
},
|
|
{
|
|
"entropy": 5.6034228801727295,
|
|
"epoch": 2.117407701468837,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004554161054721992,
|
|
"loss": 5.1137,
|
|
"mean_token_accuracy": 0.1791682094335556,
|
|
"num_tokens": 46743148.0,
|
|
"step": 21335
|
|
},
|
|
{
|
|
"entropy": 5.563817501068115,
|
|
"epoch": 2.1179039301310043,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004553949319866791,
|
|
"loss": 5.0163,
|
|
"mean_token_accuracy": 0.18600744605064393,
|
|
"num_tokens": 46754214.0,
|
|
"step": 21340
|
|
},
|
|
{
|
|
"entropy": 5.593805646896362,
|
|
"epoch": 2.118400158793172,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00045537375402775334,
|
|
"loss": 5.0441,
|
|
"mean_token_accuracy": 0.17925716787576676,
|
|
"num_tokens": 46764112.0,
|
|
"step": 21345
|
|
},
|
|
{
|
|
"entropy": 5.554880094528198,
|
|
"epoch": 2.1188963874553393,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00045535257159594724,
|
|
"loss": 5.0067,
|
|
"mean_token_accuracy": 0.18660915940999984,
|
|
"num_tokens": 46775202.0,
|
|
"step": 21350
|
|
},
|
|
{
|
|
"entropy": 5.699235200881958,
|
|
"epoch": 2.1193926161175067,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000455331384691786,
|
|
"loss": 5.0569,
|
|
"mean_token_accuracy": 0.17765737175941468,
|
|
"num_tokens": 46786557.0,
|
|
"step": 21355
|
|
},
|
|
{
|
|
"entropy": 5.577398157119751,
|
|
"epoch": 2.1198888447796747,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004553101933157949,
|
|
"loss": 5.0301,
|
|
"mean_token_accuracy": 0.16968678534030915,
|
|
"num_tokens": 46797082.0,
|
|
"step": 21360
|
|
},
|
|
{
|
|
"entropy": 5.548353099822998,
|
|
"epoch": 2.120385073441842,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00045528899746849965,
|
|
"loss": 5.0615,
|
|
"mean_token_accuracy": 0.17988609224557878,
|
|
"num_tokens": 46806679.0,
|
|
"step": 21365
|
|
},
|
|
{
|
|
"entropy": 5.666635942459107,
|
|
"epoch": 2.1208813021040096,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004552677971504257,
|
|
"loss": 5.1856,
|
|
"mean_token_accuracy": 0.16439101248979568,
|
|
"num_tokens": 46818169.0,
|
|
"step": 21370
|
|
},
|
|
{
|
|
"entropy": 5.750371599197388,
|
|
"epoch": 2.121377530766177,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.0004552465923620988,
|
|
"loss": 5.2345,
|
|
"mean_token_accuracy": 0.1687205970287323,
|
|
"num_tokens": 46829552.0,
|
|
"step": 21375
|
|
},
|
|
{
|
|
"entropy": 5.646593999862671,
|
|
"epoch": 2.1218737594283446,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004552253831040448,
|
|
"loss": 5.1341,
|
|
"mean_token_accuracy": 0.1758819043636322,
|
|
"num_tokens": 46840808.0,
|
|
"step": 21380
|
|
},
|
|
{
|
|
"entropy": 5.631982135772705,
|
|
"epoch": 2.122369988090512,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00045520416937678973,
|
|
"loss": 5.0601,
|
|
"mean_token_accuracy": 0.1720468893647194,
|
|
"num_tokens": 46852066.0,
|
|
"step": 21385
|
|
},
|
|
{
|
|
"entropy": 5.577331781387329,
|
|
"epoch": 2.1228662167526795,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00045518295118085955,
|
|
"loss": 4.9917,
|
|
"mean_token_accuracy": 0.18183973878622056,
|
|
"num_tokens": 46863163.0,
|
|
"step": 21390
|
|
},
|
|
{
|
|
"entropy": 5.616700220108032,
|
|
"epoch": 2.123362445414847,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00045516172851678036,
|
|
"loss": 5.0539,
|
|
"mean_token_accuracy": 0.17280440777540207,
|
|
"num_tokens": 46873246.0,
|
|
"step": 21395
|
|
},
|
|
{
|
|
"entropy": 5.569489622116089,
|
|
"epoch": 2.123858674077015,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00045514050138507857,
|
|
"loss": 5.0692,
|
|
"mean_token_accuracy": 0.17490116208791734,
|
|
"num_tokens": 46883881.0,
|
|
"step": 21400
|
|
},
|
|
{
|
|
"entropy": 5.6027342796325685,
|
|
"epoch": 2.1243549027391824,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004551192697862805,
|
|
"loss": 5.1019,
|
|
"mean_token_accuracy": 0.1771396741271019,
|
|
"num_tokens": 46894907.0,
|
|
"step": 21405
|
|
},
|
|
{
|
|
"entropy": 5.57938060760498,
|
|
"epoch": 2.12485113140135,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004550980337209127,
|
|
"loss": 5.0046,
|
|
"mean_token_accuracy": 0.1740194231271744,
|
|
"num_tokens": 46905220.0,
|
|
"step": 21410
|
|
},
|
|
{
|
|
"entropy": 5.564579582214355,
|
|
"epoch": 2.1253473600635173,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00045507679318950166,
|
|
"loss": 5.0103,
|
|
"mean_token_accuracy": 0.1850699871778488,
|
|
"num_tokens": 46916328.0,
|
|
"step": 21415
|
|
},
|
|
{
|
|
"entropy": 5.766316890716553,
|
|
"epoch": 2.125843588725685,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004550555481925743,
|
|
"loss": 5.2208,
|
|
"mean_token_accuracy": 0.16631329655647278,
|
|
"num_tokens": 46927450.0,
|
|
"step": 21420
|
|
},
|
|
{
|
|
"entropy": 5.5532958984375,
|
|
"epoch": 2.1263398173878523,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00045503429873065723,
|
|
"loss": 4.9692,
|
|
"mean_token_accuracy": 0.18178583979606627,
|
|
"num_tokens": 46936758.0,
|
|
"step": 21425
|
|
},
|
|
{
|
|
"entropy": 5.501639175415039,
|
|
"epoch": 2.1268360460500197,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004550130448042775,
|
|
"loss": 4.9285,
|
|
"mean_token_accuracy": 0.18358418792486192,
|
|
"num_tokens": 46945776.0,
|
|
"step": 21430
|
|
},
|
|
{
|
|
"entropy": 5.5447389602661135,
|
|
"epoch": 2.127332274712187,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004549917864139622,
|
|
"loss": 5.0362,
|
|
"mean_token_accuracy": 0.18409579396247863,
|
|
"num_tokens": 46955621.0,
|
|
"step": 21435
|
|
},
|
|
{
|
|
"entropy": 5.7072838306427,
|
|
"epoch": 2.1278285033743547,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004549705235602384,
|
|
"loss": 5.1466,
|
|
"mean_token_accuracy": 0.17853861302137375,
|
|
"num_tokens": 46966890.0,
|
|
"step": 21440
|
|
},
|
|
{
|
|
"entropy": 5.624867057800293,
|
|
"epoch": 2.1283247320365226,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004549492562436334,
|
|
"loss": 5.1556,
|
|
"mean_token_accuracy": 0.17566467076539993,
|
|
"num_tokens": 46978380.0,
|
|
"step": 21445
|
|
},
|
|
{
|
|
"entropy": 5.585629653930664,
|
|
"epoch": 2.12882096069869,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00045492798446467465,
|
|
"loss": 4.971,
|
|
"mean_token_accuracy": 0.18519706428050994,
|
|
"num_tokens": 46988286.0,
|
|
"step": 21450
|
|
},
|
|
{
|
|
"entropy": 5.5865966796875,
|
|
"epoch": 2.1293171893608576,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00045490670822388957,
|
|
"loss": 4.991,
|
|
"mean_token_accuracy": 0.1812462627887726,
|
|
"num_tokens": 46997795.0,
|
|
"step": 21455
|
|
},
|
|
{
|
|
"entropy": 5.516621398925781,
|
|
"epoch": 2.129813418023025,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004548854275218059,
|
|
"loss": 4.8902,
|
|
"mean_token_accuracy": 0.19194891452789306,
|
|
"num_tokens": 47007970.0,
|
|
"step": 21460
|
|
},
|
|
{
|
|
"entropy": 5.539976692199707,
|
|
"epoch": 2.1303096466851925,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00045486414235895115,
|
|
"loss": 5.0138,
|
|
"mean_token_accuracy": 0.18090228438377381,
|
|
"num_tokens": 47019548.0,
|
|
"step": 21465
|
|
},
|
|
{
|
|
"entropy": 5.584608554840088,
|
|
"epoch": 2.13080587534736,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004548428527358532,
|
|
"loss": 5.1162,
|
|
"mean_token_accuracy": 0.1752985894680023,
|
|
"num_tokens": 47029568.0,
|
|
"step": 21470
|
|
},
|
|
{
|
|
"entropy": 5.660408687591553,
|
|
"epoch": 2.1313021040095275,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004548215586530401,
|
|
"loss": 5.1133,
|
|
"mean_token_accuracy": 0.17004141807556153,
|
|
"num_tokens": 47042048.0,
|
|
"step": 21475
|
|
},
|
|
{
|
|
"entropy": 5.582299661636353,
|
|
"epoch": 2.131798332671695,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00045480026011103975,
|
|
"loss": 4.9804,
|
|
"mean_token_accuracy": 0.17573142796754837,
|
|
"num_tokens": 47052099.0,
|
|
"step": 21480
|
|
},
|
|
{
|
|
"entropy": 5.592738914489746,
|
|
"epoch": 2.132294561333863,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.00045477895711038045,
|
|
"loss": 5.015,
|
|
"mean_token_accuracy": 0.18177002668380737,
|
|
"num_tokens": 47063310.0,
|
|
"step": 21485
|
|
},
|
|
{
|
|
"entropy": 5.58268518447876,
|
|
"epoch": 2.1327907899960303,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004547576496515904,
|
|
"loss": 5.044,
|
|
"mean_token_accuracy": 0.17684397399425505,
|
|
"num_tokens": 47073545.0,
|
|
"step": 21490
|
|
},
|
|
{
|
|
"entropy": 5.565859699249268,
|
|
"epoch": 2.133287018658198,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00045473633773519795,
|
|
"loss": 5.0895,
|
|
"mean_token_accuracy": 0.17818187475204467,
|
|
"num_tokens": 47085456.0,
|
|
"step": 21495
|
|
},
|
|
{
|
|
"entropy": 5.6535240650177006,
|
|
"epoch": 2.1337832473203653,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00045471502136173173,
|
|
"loss": 5.0619,
|
|
"mean_token_accuracy": 0.17919227927923204,
|
|
"num_tokens": 47096590.0,
|
|
"step": 21500
|
|
},
|
|
{
|
|
"entropy": 5.678283214569092,
|
|
"epoch": 2.1342794759825328,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004546937005317201,
|
|
"loss": 5.0062,
|
|
"mean_token_accuracy": 0.18891891837120056,
|
|
"num_tokens": 47107876.0,
|
|
"step": 21505
|
|
},
|
|
{
|
|
"entropy": 5.577515172958374,
|
|
"epoch": 2.1347757046447002,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00045467237524569193,
|
|
"loss": 5.0449,
|
|
"mean_token_accuracy": 0.17991174459457399,
|
|
"num_tokens": 47117662.0,
|
|
"step": 21510
|
|
},
|
|
{
|
|
"entropy": 5.562215518951416,
|
|
"epoch": 2.1352719333068677,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00045465104550417604,
|
|
"loss": 5.0753,
|
|
"mean_token_accuracy": 0.17737892866134644,
|
|
"num_tokens": 47129283.0,
|
|
"step": 21515
|
|
},
|
|
{
|
|
"entropy": 5.664295816421509,
|
|
"epoch": 2.135768161969035,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00045462971130770123,
|
|
"loss": 5.1532,
|
|
"mean_token_accuracy": 0.17320260852575303,
|
|
"num_tokens": 47140824.0,
|
|
"step": 21520
|
|
},
|
|
{
|
|
"entropy": 5.575448846817016,
|
|
"epoch": 2.1362643906312027,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004546083726567968,
|
|
"loss": 5.0058,
|
|
"mean_token_accuracy": 0.18087561279535294,
|
|
"num_tokens": 47151733.0,
|
|
"step": 21525
|
|
},
|
|
{
|
|
"entropy": 5.583763504028321,
|
|
"epoch": 2.1367606192933706,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004545870295519917,
|
|
"loss": 5.1205,
|
|
"mean_token_accuracy": 0.16902925968170165,
|
|
"num_tokens": 47162846.0,
|
|
"step": 21530
|
|
},
|
|
{
|
|
"entropy": 5.631829500198364,
|
|
"epoch": 2.137256847955538,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00045456568199381524,
|
|
"loss": 5.0145,
|
|
"mean_token_accuracy": 0.1806974560022354,
|
|
"num_tokens": 47174969.0,
|
|
"step": 21535
|
|
},
|
|
{
|
|
"entropy": 5.666506385803222,
|
|
"epoch": 2.1377530766177055,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00045454432998279676,
|
|
"loss": 5.1054,
|
|
"mean_token_accuracy": 0.17508367747068404,
|
|
"num_tokens": 47186903.0,
|
|
"step": 21540
|
|
},
|
|
{
|
|
"entropy": 5.617109107971191,
|
|
"epoch": 2.138249305279873,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004545229735194658,
|
|
"loss": 5.0834,
|
|
"mean_token_accuracy": 0.1783437430858612,
|
|
"num_tokens": 47197716.0,
|
|
"step": 21545
|
|
},
|
|
{
|
|
"entropy": 5.604199981689453,
|
|
"epoch": 2.1387455339420405,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00045450161260435196,
|
|
"loss": 5.0092,
|
|
"mean_token_accuracy": 0.1813771605491638,
|
|
"num_tokens": 47208623.0,
|
|
"step": 21550
|
|
},
|
|
{
|
|
"entropy": 5.547342920303345,
|
|
"epoch": 2.139241762604208,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004544802472379849,
|
|
"loss": 5.0182,
|
|
"mean_token_accuracy": 0.18133753836154937,
|
|
"num_tokens": 47218248.0,
|
|
"step": 21555
|
|
},
|
|
{
|
|
"entropy": 5.6151481628417965,
|
|
"epoch": 2.1397379912663754,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004544588774208945,
|
|
"loss": 5.1487,
|
|
"mean_token_accuracy": 0.17479496449232101,
|
|
"num_tokens": 47232028.0,
|
|
"step": 21560
|
|
},
|
|
{
|
|
"entropy": 5.662732410430908,
|
|
"epoch": 2.140234219928543,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00045443750315361055,
|
|
"loss": 5.015,
|
|
"mean_token_accuracy": 0.18409377932548524,
|
|
"num_tokens": 47241976.0,
|
|
"step": 21565
|
|
},
|
|
{
|
|
"entropy": 5.601552867889405,
|
|
"epoch": 2.140730448590711,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004544161244366632,
|
|
"loss": 5.0221,
|
|
"mean_token_accuracy": 0.1823471352458,
|
|
"num_tokens": 47253228.0,
|
|
"step": 21570
|
|
},
|
|
{
|
|
"entropy": 5.578529977798462,
|
|
"epoch": 2.1412266772528783,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004543947412705826,
|
|
"loss": 5.0402,
|
|
"mean_token_accuracy": 0.1810141086578369,
|
|
"num_tokens": 47265210.0,
|
|
"step": 21575
|
|
},
|
|
{
|
|
"entropy": 5.560053873062134,
|
|
"epoch": 2.1417229059150458,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00045437335365589905,
|
|
"loss": 5.0548,
|
|
"mean_token_accuracy": 0.17746611684560776,
|
|
"num_tokens": 47275723.0,
|
|
"step": 21580
|
|
},
|
|
{
|
|
"entropy": 5.6039714336395265,
|
|
"epoch": 2.1422191345772132,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00045435196159314276,
|
|
"loss": 5.0951,
|
|
"mean_token_accuracy": 0.17851237952709198,
|
|
"num_tokens": 47286469.0,
|
|
"step": 21585
|
|
},
|
|
{
|
|
"entropy": 5.668009424209595,
|
|
"epoch": 2.1427153632393807,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00045433056508284425,
|
|
"loss": 5.1128,
|
|
"mean_token_accuracy": 0.17833200544118882,
|
|
"num_tokens": 47296461.0,
|
|
"step": 21590
|
|
},
|
|
{
|
|
"entropy": 5.643115234375,
|
|
"epoch": 2.143211591901548,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004543091641255342,
|
|
"loss": 5.0124,
|
|
"mean_token_accuracy": 0.18718140125274657,
|
|
"num_tokens": 47307217.0,
|
|
"step": 21595
|
|
},
|
|
{
|
|
"entropy": 5.6398458003997805,
|
|
"epoch": 2.1437078205637157,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004542877587217432,
|
|
"loss": 5.1423,
|
|
"mean_token_accuracy": 0.17120454907417298,
|
|
"num_tokens": 47317041.0,
|
|
"step": 21600
|
|
},
|
|
{
|
|
"entropy": 5.5971814632415775,
|
|
"epoch": 2.144204049225883,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00045426634887200224,
|
|
"loss": 5.05,
|
|
"mean_token_accuracy": 0.17875636965036393,
|
|
"num_tokens": 47328185.0,
|
|
"step": 21605
|
|
},
|
|
{
|
|
"entropy": 5.639533615112304,
|
|
"epoch": 2.1447002778880506,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.000454244934576842,
|
|
"loss": 5.0975,
|
|
"mean_token_accuracy": 0.17185043394565583,
|
|
"num_tokens": 47339984.0,
|
|
"step": 21610
|
|
},
|
|
{
|
|
"entropy": 5.609605741500855,
|
|
"epoch": 2.1451965065502185,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00045422351583679365,
|
|
"loss": 5.0474,
|
|
"mean_token_accuracy": 0.18795174956321717,
|
|
"num_tokens": 47350911.0,
|
|
"step": 21615
|
|
},
|
|
{
|
|
"entropy": 5.610928535461426,
|
|
"epoch": 2.145692735212386,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004542020926523883,
|
|
"loss": 5.0395,
|
|
"mean_token_accuracy": 0.1735944226384163,
|
|
"num_tokens": 47361703.0,
|
|
"step": 21620
|
|
},
|
|
{
|
|
"entropy": 5.568384313583374,
|
|
"epoch": 2.1461889638745535,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004541806650241572,
|
|
"loss": 5.0093,
|
|
"mean_token_accuracy": 0.17709755897521973,
|
|
"num_tokens": 47372878.0,
|
|
"step": 21625
|
|
},
|
|
{
|
|
"entropy": 5.575262784957886,
|
|
"epoch": 2.146685192536721,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004541592329526317,
|
|
"loss": 5.0408,
|
|
"mean_token_accuracy": 0.17615410089492797,
|
|
"num_tokens": 47383056.0,
|
|
"step": 21630
|
|
},
|
|
{
|
|
"entropy": 5.559898614883423,
|
|
"epoch": 2.1471814211988884,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004541377964383434,
|
|
"loss": 5.0717,
|
|
"mean_token_accuracy": 0.1783818393945694,
|
|
"num_tokens": 47394160.0,
|
|
"step": 21635
|
|
},
|
|
{
|
|
"entropy": 5.630073499679566,
|
|
"epoch": 2.147677649861056,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004541163554818237,
|
|
"loss": 5.0163,
|
|
"mean_token_accuracy": 0.17626212686300277,
|
|
"num_tokens": 47404861.0,
|
|
"step": 21640
|
|
},
|
|
{
|
|
"entropy": 5.636077785491944,
|
|
"epoch": 2.1481738785232234,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00045409491008360423,
|
|
"loss": 5.0962,
|
|
"mean_token_accuracy": 0.17747374922037124,
|
|
"num_tokens": 47415236.0,
|
|
"step": 21645
|
|
},
|
|
{
|
|
"entropy": 5.627088594436645,
|
|
"epoch": 2.148670107185391,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004540734602442169,
|
|
"loss": 5.0511,
|
|
"mean_token_accuracy": 0.17763217240571977,
|
|
"num_tokens": 47425789.0,
|
|
"step": 21650
|
|
},
|
|
{
|
|
"entropy": 5.551941680908203,
|
|
"epoch": 2.149166335847559,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004540520059641937,
|
|
"loss": 4.9286,
|
|
"mean_token_accuracy": 0.18573008775711058,
|
|
"num_tokens": 47436236.0,
|
|
"step": 21655
|
|
},
|
|
{
|
|
"entropy": 5.515349864959717,
|
|
"epoch": 2.1496625645097263,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004540305472440666,
|
|
"loss": 4.9507,
|
|
"mean_token_accuracy": 0.18640548586845399,
|
|
"num_tokens": 47447041.0,
|
|
"step": 21660
|
|
},
|
|
{
|
|
"entropy": 5.571415376663208,
|
|
"epoch": 2.1501587931718937,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004540090840843677,
|
|
"loss": 5.0967,
|
|
"mean_token_accuracy": 0.17228649109601973,
|
|
"num_tokens": 47458001.0,
|
|
"step": 21665
|
|
},
|
|
{
|
|
"entropy": 5.560210418701172,
|
|
"epoch": 2.150655021834061,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004539876164856292,
|
|
"loss": 4.9613,
|
|
"mean_token_accuracy": 0.18584735095500945,
|
|
"num_tokens": 47468621.0,
|
|
"step": 21670
|
|
},
|
|
{
|
|
"entropy": 5.553755044937134,
|
|
"epoch": 2.1511512504962287,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004539661444483835,
|
|
"loss": 5.0842,
|
|
"mean_token_accuracy": 0.17947480976581573,
|
|
"num_tokens": 47478957.0,
|
|
"step": 21675
|
|
},
|
|
{
|
|
"entropy": 5.559771156311035,
|
|
"epoch": 2.151647479158396,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004539446679731631,
|
|
"loss": 5.0215,
|
|
"mean_token_accuracy": 0.18373374491930008,
|
|
"num_tokens": 47489640.0,
|
|
"step": 21680
|
|
},
|
|
{
|
|
"entropy": 5.651854991912842,
|
|
"epoch": 2.1521437078205636,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004539231870605005,
|
|
"loss": 5.1519,
|
|
"mean_token_accuracy": 0.17401155084371567,
|
|
"num_tokens": 47501581.0,
|
|
"step": 21685
|
|
},
|
|
{
|
|
"entropy": 5.6084897994995115,
|
|
"epoch": 2.152639936482731,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.00045390170171092845,
|
|
"loss": 5.0834,
|
|
"mean_token_accuracy": 0.17708443850278854,
|
|
"num_tokens": 47513605.0,
|
|
"step": 21690
|
|
},
|
|
{
|
|
"entropy": 5.658263921737671,
|
|
"epoch": 2.1531361651448986,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00045388021192497956,
|
|
"loss": 5.0849,
|
|
"mean_token_accuracy": 0.1809326931834221,
|
|
"num_tokens": 47523784.0,
|
|
"step": 21695
|
|
},
|
|
{
|
|
"entropy": 5.575326347351075,
|
|
"epoch": 2.1536323938070665,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.000453858717703187,
|
|
"loss": 4.9834,
|
|
"mean_token_accuracy": 0.17962647080421448,
|
|
"num_tokens": 47534643.0,
|
|
"step": 21700
|
|
},
|
|
{
|
|
"entropy": 5.583701038360596,
|
|
"epoch": 2.154128622469234,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004538372190460836,
|
|
"loss": 5.0903,
|
|
"mean_token_accuracy": 0.17195199579000472,
|
|
"num_tokens": 47545920.0,
|
|
"step": 21705
|
|
},
|
|
{
|
|
"entropy": 5.5628283500671385,
|
|
"epoch": 2.1546248511314015,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004538157159542025,
|
|
"loss": 5.0381,
|
|
"mean_token_accuracy": 0.17441756576299666,
|
|
"num_tokens": 47557024.0,
|
|
"step": 21710
|
|
},
|
|
{
|
|
"entropy": 5.595124387741089,
|
|
"epoch": 2.155121079793569,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004537942084280771,
|
|
"loss": 5.0093,
|
|
"mean_token_accuracy": 0.18362217545509338,
|
|
"num_tokens": 47567531.0,
|
|
"step": 21715
|
|
},
|
|
{
|
|
"entropy": 5.585353660583496,
|
|
"epoch": 2.1556173084557364,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.00045377269646824036,
|
|
"loss": 5.1367,
|
|
"mean_token_accuracy": 0.17484066337347032,
|
|
"num_tokens": 47578642.0,
|
|
"step": 21720
|
|
},
|
|
{
|
|
"entropy": 5.6135828495025635,
|
|
"epoch": 2.156113537117904,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00045375118007522607,
|
|
"loss": 5.1837,
|
|
"mean_token_accuracy": 0.1732584223151207,
|
|
"num_tokens": 47589346.0,
|
|
"step": 21725
|
|
},
|
|
{
|
|
"entropy": 5.559467029571533,
|
|
"epoch": 2.1566097657800714,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004537296592495678,
|
|
"loss": 4.9829,
|
|
"mean_token_accuracy": 0.18416567593812944,
|
|
"num_tokens": 47599689.0,
|
|
"step": 21730
|
|
},
|
|
{
|
|
"entropy": 5.640780639648438,
|
|
"epoch": 2.157105994442239,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000453708133991799,
|
|
"loss": 5.0802,
|
|
"mean_token_accuracy": 0.17734809070825577,
|
|
"num_tokens": 47609214.0,
|
|
"step": 21735
|
|
},
|
|
{
|
|
"entropy": 5.633480453491211,
|
|
"epoch": 2.1576022231044063,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00045368660430245364,
|
|
"loss": 5.0252,
|
|
"mean_token_accuracy": 0.17884812653064727,
|
|
"num_tokens": 47620119.0,
|
|
"step": 21740
|
|
},
|
|
{
|
|
"entropy": 5.592954492568969,
|
|
"epoch": 2.158098451766574,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004536650701820654,
|
|
"loss": 4.9973,
|
|
"mean_token_accuracy": 0.17908246219158172,
|
|
"num_tokens": 47630085.0,
|
|
"step": 21745
|
|
},
|
|
{
|
|
"entropy": 5.571291160583496,
|
|
"epoch": 2.1585946804287417,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004536435316311685,
|
|
"loss": 4.9873,
|
|
"mean_token_accuracy": 0.18062832802534104,
|
|
"num_tokens": 47641457.0,
|
|
"step": 21750
|
|
},
|
|
{
|
|
"entropy": 5.591070032119751,
|
|
"epoch": 2.159090909090909,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00045362198865029696,
|
|
"loss": 5.012,
|
|
"mean_token_accuracy": 0.17439776957035064,
|
|
"num_tokens": 47652269.0,
|
|
"step": 21755
|
|
},
|
|
{
|
|
"entropy": 5.578510570526123,
|
|
"epoch": 2.1595871377530766,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00045360044123998495,
|
|
"loss": 5.0399,
|
|
"mean_token_accuracy": 0.17895068377256393,
|
|
"num_tokens": 47664601.0,
|
|
"step": 21760
|
|
},
|
|
{
|
|
"entropy": 5.627600049972534,
|
|
"epoch": 2.160083366415244,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00045357888940076685,
|
|
"loss": 5.1446,
|
|
"mean_token_accuracy": 0.1762605682015419,
|
|
"num_tokens": 47676187.0,
|
|
"step": 21765
|
|
},
|
|
{
|
|
"entropy": 5.554150152206421,
|
|
"epoch": 2.1605795950774116,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004535573331331771,
|
|
"loss": 4.9491,
|
|
"mean_token_accuracy": 0.1862216755747795,
|
|
"num_tokens": 47687057.0,
|
|
"step": 21770
|
|
},
|
|
{
|
|
"entropy": 5.589615774154663,
|
|
"epoch": 2.161075823739579,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.00045353577243775035,
|
|
"loss": 5.001,
|
|
"mean_token_accuracy": 0.18201490342617035,
|
|
"num_tokens": 47699074.0,
|
|
"step": 21775
|
|
},
|
|
{
|
|
"entropy": 5.601614141464234,
|
|
"epoch": 2.1615720524017465,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004535142073150211,
|
|
"loss": 5.0044,
|
|
"mean_token_accuracy": 0.18161804229021072,
|
|
"num_tokens": 47710400.0,
|
|
"step": 21780
|
|
},
|
|
{
|
|
"entropy": 5.571734857559204,
|
|
"epoch": 2.162068281063914,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004534926377655241,
|
|
"loss": 4.8857,
|
|
"mean_token_accuracy": 0.19429706782102585,
|
|
"num_tokens": 47720900.0,
|
|
"step": 21785
|
|
},
|
|
{
|
|
"entropy": 5.532523965835571,
|
|
"epoch": 2.162564509726082,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00045347106378979435,
|
|
"loss": 4.9175,
|
|
"mean_token_accuracy": 0.18466942608356476,
|
|
"num_tokens": 47730702.0,
|
|
"step": 21790
|
|
},
|
|
{
|
|
"entropy": 5.5342902660369875,
|
|
"epoch": 2.1630607383882494,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00045344948538836674,
|
|
"loss": 4.994,
|
|
"mean_token_accuracy": 0.18384909480810166,
|
|
"num_tokens": 47740451.0,
|
|
"step": 21795
|
|
},
|
|
{
|
|
"entropy": 5.598954153060913,
|
|
"epoch": 2.163556967050417,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00045342790256177646,
|
|
"loss": 5.0729,
|
|
"mean_token_accuracy": 0.18085743933916093,
|
|
"num_tokens": 47752285.0,
|
|
"step": 21800
|
|
},
|
|
{
|
|
"entropy": 5.642742872238159,
|
|
"epoch": 2.1640531957125844,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004534063153105587,
|
|
"loss": 5.0656,
|
|
"mean_token_accuracy": 0.17590310126543046,
|
|
"num_tokens": 47761895.0,
|
|
"step": 21805
|
|
},
|
|
{
|
|
"entropy": 5.5979901313781735,
|
|
"epoch": 2.164549424374752,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004533847236352487,
|
|
"loss": 4.9629,
|
|
"mean_token_accuracy": 0.18740931749343873,
|
|
"num_tokens": 47771718.0,
|
|
"step": 21810
|
|
},
|
|
{
|
|
"entropy": 5.511568021774292,
|
|
"epoch": 2.1650456530369193,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.000453363127536382,
|
|
"loss": 5.0046,
|
|
"mean_token_accuracy": 0.18217131346464158,
|
|
"num_tokens": 47782183.0,
|
|
"step": 21815
|
|
},
|
|
{
|
|
"entropy": 5.48533787727356,
|
|
"epoch": 2.165541881699087,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00045334152701449407,
|
|
"loss": 4.9516,
|
|
"mean_token_accuracy": 0.1853344812989235,
|
|
"num_tokens": 47792190.0,
|
|
"step": 21820
|
|
},
|
|
{
|
|
"entropy": 5.67718653678894,
|
|
"epoch": 2.1660381103612543,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004533199220701205,
|
|
"loss": 5.1564,
|
|
"mean_token_accuracy": 0.17121699452400208,
|
|
"num_tokens": 47803245.0,
|
|
"step": 21825
|
|
},
|
|
{
|
|
"entropy": 5.64677996635437,
|
|
"epoch": 2.166534339023422,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00045329831270379714,
|
|
"loss": 5.0933,
|
|
"mean_token_accuracy": 0.1739192485809326,
|
|
"num_tokens": 47814605.0,
|
|
"step": 21830
|
|
},
|
|
{
|
|
"entropy": 5.582768774032592,
|
|
"epoch": 2.1670305676855897,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.00045327669891605975,
|
|
"loss": 5.0682,
|
|
"mean_token_accuracy": 0.18000198155641556,
|
|
"num_tokens": 47825945.0,
|
|
"step": 21835
|
|
},
|
|
{
|
|
"entropy": 5.546384859085083,
|
|
"epoch": 2.167526796347757,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004532550807074445,
|
|
"loss": 5.066,
|
|
"mean_token_accuracy": 0.1756667673587799,
|
|
"num_tokens": 47838119.0,
|
|
"step": 21840
|
|
},
|
|
{
|
|
"entropy": 5.613620281219482,
|
|
"epoch": 2.1680230250099246,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004532334580784873,
|
|
"loss": 5.0584,
|
|
"mean_token_accuracy": 0.18069804608821868,
|
|
"num_tokens": 47849560.0,
|
|
"step": 21845
|
|
},
|
|
{
|
|
"entropy": 5.650173473358154,
|
|
"epoch": 2.168519253672092,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004532118310297244,
|
|
"loss": 5.0721,
|
|
"mean_token_accuracy": 0.1677744470536709,
|
|
"num_tokens": 47860036.0,
|
|
"step": 21850
|
|
},
|
|
{
|
|
"entropy": 5.518974924087525,
|
|
"epoch": 2.1690154823342596,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004531901995616921,
|
|
"loss": 4.9548,
|
|
"mean_token_accuracy": 0.18143303841352462,
|
|
"num_tokens": 47870826.0,
|
|
"step": 21855
|
|
},
|
|
{
|
|
"entropy": 5.575003433227539,
|
|
"epoch": 2.169511710996427,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004531685636749268,
|
|
"loss": 5.0753,
|
|
"mean_token_accuracy": 0.1716070294380188,
|
|
"num_tokens": 47881415.0,
|
|
"step": 21860
|
|
},
|
|
{
|
|
"entropy": 5.651249122619629,
|
|
"epoch": 2.1700079396585945,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004531469233699651,
|
|
"loss": 5.0786,
|
|
"mean_token_accuracy": 0.17890810072422028,
|
|
"num_tokens": 47893343.0,
|
|
"step": 21865
|
|
},
|
|
{
|
|
"entropy": 5.5685631275177006,
|
|
"epoch": 2.170504168320762,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004531252786473436,
|
|
"loss": 5.0631,
|
|
"mean_token_accuracy": 0.1751348689198494,
|
|
"num_tokens": 47904871.0,
|
|
"step": 21870
|
|
},
|
|
{
|
|
"entropy": 5.562549304962158,
|
|
"epoch": 2.17100039698293,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004531036295075989,
|
|
"loss": 4.9804,
|
|
"mean_token_accuracy": 0.18189692348241807,
|
|
"num_tokens": 47915367.0,
|
|
"step": 21875
|
|
},
|
|
{
|
|
"entropy": 5.5944239616394045,
|
|
"epoch": 2.1714966256450974,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00045308197595126797,
|
|
"loss": 4.9977,
|
|
"mean_token_accuracy": 0.1846961185336113,
|
|
"num_tokens": 47925987.0,
|
|
"step": 21880
|
|
},
|
|
{
|
|
"entropy": 5.604113674163818,
|
|
"epoch": 2.171992854307265,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004530603179788879,
|
|
"loss": 5.0887,
|
|
"mean_token_accuracy": 0.18021042346954347,
|
|
"num_tokens": 47937688.0,
|
|
"step": 21885
|
|
},
|
|
{
|
|
"entropy": 5.566831064224243,
|
|
"epoch": 2.1724890829694323,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004530386555909955,
|
|
"loss": 5.041,
|
|
"mean_token_accuracy": 0.18573734015226365,
|
|
"num_tokens": 47948550.0,
|
|
"step": 21890
|
|
},
|
|
{
|
|
"entropy": 5.604857778549194,
|
|
"epoch": 2.1729853116316,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00045301698878812813,
|
|
"loss": 5.0379,
|
|
"mean_token_accuracy": 0.1845029205083847,
|
|
"num_tokens": 47957982.0,
|
|
"step": 21895
|
|
},
|
|
{
|
|
"entropy": 5.624063301086426,
|
|
"epoch": 2.1734815402937673,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004529953175708231,
|
|
"loss": 5.0848,
|
|
"mean_token_accuracy": 0.17916077822446824,
|
|
"num_tokens": 47969562.0,
|
|
"step": 21900
|
|
},
|
|
{
|
|
"entropy": 5.604766082763672,
|
|
"epoch": 2.1739777689559348,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00045297364193961763,
|
|
"loss": 5.1039,
|
|
"mean_token_accuracy": 0.17346563190221786,
|
|
"num_tokens": 47981323.0,
|
|
"step": 21905
|
|
},
|
|
{
|
|
"entropy": 5.609239768981934,
|
|
"epoch": 2.1744739976181022,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00045295196189504934,
|
|
"loss": 5.0263,
|
|
"mean_token_accuracy": 0.17552904635667801,
|
|
"num_tokens": 47991454.0,
|
|
"step": 21910
|
|
},
|
|
{
|
|
"entropy": 5.564348745346069,
|
|
"epoch": 2.17497022628027,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00045293027743765595,
|
|
"loss": 4.9135,
|
|
"mean_token_accuracy": 0.1843430742621422,
|
|
"num_tokens": 48001300.0,
|
|
"step": 21915
|
|
},
|
|
{
|
|
"entropy": 5.591091442108154,
|
|
"epoch": 2.1754664549424376,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00045290858856797503,
|
|
"loss": 5.0179,
|
|
"mean_token_accuracy": 0.18275899440050125,
|
|
"num_tokens": 48012608.0,
|
|
"step": 21920
|
|
},
|
|
{
|
|
"entropy": 5.616801643371582,
|
|
"epoch": 2.175962683604605,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00045288689528654444,
|
|
"loss": 5.0416,
|
|
"mean_token_accuracy": 0.18189008086919783,
|
|
"num_tokens": 48022120.0,
|
|
"step": 21925
|
|
},
|
|
{
|
|
"entropy": 5.600833606719971,
|
|
"epoch": 2.1764589122667726,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00045286519759390217,
|
|
"loss": 5.0471,
|
|
"mean_token_accuracy": 0.1793038547039032,
|
|
"num_tokens": 48032629.0,
|
|
"step": 21930
|
|
},
|
|
{
|
|
"entropy": 5.564683151245117,
|
|
"epoch": 2.17695514092894,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004528434954905863,
|
|
"loss": 4.9657,
|
|
"mean_token_accuracy": 0.18391641229391098,
|
|
"num_tokens": 48042934.0,
|
|
"step": 21935
|
|
},
|
|
{
|
|
"entropy": 5.576721429824829,
|
|
"epoch": 2.1774513695911075,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004528217889771349,
|
|
"loss": 5.0524,
|
|
"mean_token_accuracy": 0.1794678181409836,
|
|
"num_tokens": 48052825.0,
|
|
"step": 21940
|
|
},
|
|
{
|
|
"entropy": 5.639779329299927,
|
|
"epoch": 2.177947598253275,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00045280007805408636,
|
|
"loss": 5.1136,
|
|
"mean_token_accuracy": 0.1706728979945183,
|
|
"num_tokens": 48064565.0,
|
|
"step": 21945
|
|
},
|
|
{
|
|
"entropy": 5.648127508163452,
|
|
"epoch": 2.1784438269154425,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00045277836272197895,
|
|
"loss": 5.0776,
|
|
"mean_token_accuracy": 0.18024928718805314,
|
|
"num_tokens": 48076006.0,
|
|
"step": 21950
|
|
},
|
|
{
|
|
"entropy": 5.675761795043945,
|
|
"epoch": 2.17894005557761,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00045275664298135134,
|
|
"loss": 5.182,
|
|
"mean_token_accuracy": 0.17125353962183,
|
|
"num_tokens": 48087110.0,
|
|
"step": 21955
|
|
},
|
|
{
|
|
"entropy": 5.618146514892578,
|
|
"epoch": 2.179436284239778,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004527349188327419,
|
|
"loss": 5.0635,
|
|
"mean_token_accuracy": 0.1855880782008171,
|
|
"num_tokens": 48098894.0,
|
|
"step": 21960
|
|
},
|
|
{
|
|
"entropy": 5.6330725193023685,
|
|
"epoch": 2.1799325129019453,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004527131902766895,
|
|
"loss": 5.0785,
|
|
"mean_token_accuracy": 0.17861806303262712,
|
|
"num_tokens": 48109729.0,
|
|
"step": 21965
|
|
},
|
|
{
|
|
"entropy": 5.625303792953491,
|
|
"epoch": 2.180428741564113,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004526914573137329,
|
|
"loss": 5.071,
|
|
"mean_token_accuracy": 0.17511035948991777,
|
|
"num_tokens": 48120345.0,
|
|
"step": 21970
|
|
},
|
|
{
|
|
"entropy": 5.609857416152954,
|
|
"epoch": 2.1809249702262803,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00045266971994441116,
|
|
"loss": 5.0109,
|
|
"mean_token_accuracy": 0.1806703433394432,
|
|
"num_tokens": 48130185.0,
|
|
"step": 21975
|
|
},
|
|
{
|
|
"entropy": 5.555281162261963,
|
|
"epoch": 2.1814211988884478,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.000452647978169263,
|
|
"loss": 4.9787,
|
|
"mean_token_accuracy": 0.18263042122125625,
|
|
"num_tokens": 48141020.0,
|
|
"step": 21980
|
|
},
|
|
{
|
|
"entropy": 5.572640323638916,
|
|
"epoch": 2.1819174275506152,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00045262623198882797,
|
|
"loss": 5.064,
|
|
"mean_token_accuracy": 0.18618489056825638,
|
|
"num_tokens": 48153361.0,
|
|
"step": 21985
|
|
},
|
|
{
|
|
"entropy": 5.6059380054473875,
|
|
"epoch": 2.1824136562127827,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004526044814036451,
|
|
"loss": 5.0251,
|
|
"mean_token_accuracy": 0.17799050956964493,
|
|
"num_tokens": 48163604.0,
|
|
"step": 21990
|
|
},
|
|
{
|
|
"entropy": 5.58221960067749,
|
|
"epoch": 2.18290988487495,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00045258272641425377,
|
|
"loss": 5.0414,
|
|
"mean_token_accuracy": 0.17689698189496994,
|
|
"num_tokens": 48174732.0,
|
|
"step": 21995
|
|
},
|
|
{
|
|
"entropy": 5.618593025207519,
|
|
"epoch": 2.183406113537118,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004525609670211934,
|
|
"loss": 5.0081,
|
|
"mean_token_accuracy": 0.1845436543226242,
|
|
"num_tokens": 48187082.0,
|
|
"step": 22000
|
|
},
|
|
{
|
|
"entropy": 5.605060577392578,
|
|
"epoch": 2.1839023421992856,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00045253920322500373,
|
|
"loss": 5.0222,
|
|
"mean_token_accuracy": 0.18025557845830917,
|
|
"num_tokens": 48196547.0,
|
|
"step": 22005
|
|
},
|
|
{
|
|
"entropy": 5.580152559280395,
|
|
"epoch": 2.184398570861453,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00045251743502622445,
|
|
"loss": 5.0699,
|
|
"mean_token_accuracy": 0.1801171272993088,
|
|
"num_tokens": 48207404.0,
|
|
"step": 22010
|
|
},
|
|
{
|
|
"entropy": 5.547487783432007,
|
|
"epoch": 2.1848947995236205,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004524956624253952,
|
|
"loss": 5.0439,
|
|
"mean_token_accuracy": 0.18376276940107344,
|
|
"num_tokens": 48217093.0,
|
|
"step": 22015
|
|
},
|
|
{
|
|
"entropy": 5.603080797195434,
|
|
"epoch": 2.185391028185788,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00045247388542305595,
|
|
"loss": 5.0678,
|
|
"mean_token_accuracy": 0.17807838767766954,
|
|
"num_tokens": 48228093.0,
|
|
"step": 22020
|
|
},
|
|
{
|
|
"entropy": 5.561899852752686,
|
|
"epoch": 2.1858872568479555,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004524521040197469,
|
|
"loss": 5.033,
|
|
"mean_token_accuracy": 0.18567698299884797,
|
|
"num_tokens": 48238834.0,
|
|
"step": 22025
|
|
},
|
|
{
|
|
"entropy": 5.645340538024902,
|
|
"epoch": 2.186383485510123,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00045243031821600794,
|
|
"loss": 5.0757,
|
|
"mean_token_accuracy": 0.18889536261558532,
|
|
"num_tokens": 48250782.0,
|
|
"step": 22030
|
|
},
|
|
{
|
|
"entropy": 5.500328874588012,
|
|
"epoch": 2.1868797141722904,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004524085280123795,
|
|
"loss": 4.9717,
|
|
"mean_token_accuracy": 0.1805126041173935,
|
|
"num_tokens": 48261711.0,
|
|
"step": 22035
|
|
},
|
|
{
|
|
"entropy": 5.574241590499878,
|
|
"epoch": 2.187375942834458,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004523867334094018,
|
|
"loss": 5.0873,
|
|
"mean_token_accuracy": 0.17435535192489623,
|
|
"num_tokens": 48273505.0,
|
|
"step": 22040
|
|
},
|
|
{
|
|
"entropy": 5.560463953018188,
|
|
"epoch": 2.187872171496626,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004523649344076154,
|
|
"loss": 4.9822,
|
|
"mean_token_accuracy": 0.18139338344335557,
|
|
"num_tokens": 48284639.0,
|
|
"step": 22045
|
|
},
|
|
{
|
|
"entropy": 5.596578931808471,
|
|
"epoch": 2.1883684001587933,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00045234313100756077,
|
|
"loss": 5.0647,
|
|
"mean_token_accuracy": 0.1765772208571434,
|
|
"num_tokens": 48296275.0,
|
|
"step": 22050
|
|
},
|
|
{
|
|
"entropy": 5.557593774795532,
|
|
"epoch": 2.188864628820961,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00045232132320977854,
|
|
"loss": 4.9709,
|
|
"mean_token_accuracy": 0.18602284938097,
|
|
"num_tokens": 48306859.0,
|
|
"step": 22055
|
|
},
|
|
{
|
|
"entropy": 5.609091567993164,
|
|
"epoch": 2.1893608574831283,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004522995110148097,
|
|
"loss": 5.1127,
|
|
"mean_token_accuracy": 0.18117768466472625,
|
|
"num_tokens": 48317561.0,
|
|
"step": 22060
|
|
},
|
|
{
|
|
"entropy": 5.5942830562591555,
|
|
"epoch": 2.1898570861452957,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.000452277694423195,
|
|
"loss": 5.1209,
|
|
"mean_token_accuracy": 0.16993902176618575,
|
|
"num_tokens": 48327814.0,
|
|
"step": 22065
|
|
},
|
|
{
|
|
"entropy": 5.586060476303101,
|
|
"epoch": 2.190353314807463,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004522558734354755,
|
|
"loss": 4.9752,
|
|
"mean_token_accuracy": 0.18480440974235535,
|
|
"num_tokens": 48339658.0,
|
|
"step": 22070
|
|
},
|
|
{
|
|
"entropy": 5.6134397983551025,
|
|
"epoch": 2.1908495434696307,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00045223404805219225,
|
|
"loss": 5.0883,
|
|
"mean_token_accuracy": 0.17792799770832063,
|
|
"num_tokens": 48352115.0,
|
|
"step": 22075
|
|
},
|
|
{
|
|
"entropy": 5.6445409774780275,
|
|
"epoch": 2.191345772131798,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00045221221827388655,
|
|
"loss": 5.0387,
|
|
"mean_token_accuracy": 0.18001949936151504,
|
|
"num_tokens": 48362378.0,
|
|
"step": 22080
|
|
},
|
|
{
|
|
"entropy": 5.578653192520141,
|
|
"epoch": 2.191842000793966,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004521903841010997,
|
|
"loss": 4.9759,
|
|
"mean_token_accuracy": 0.1877150759100914,
|
|
"num_tokens": 48373035.0,
|
|
"step": 22085
|
|
},
|
|
{
|
|
"entropy": 5.534437036514282,
|
|
"epoch": 2.1923382294561335,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004521685455343731,
|
|
"loss": 5.0309,
|
|
"mean_token_accuracy": 0.18416130542755127,
|
|
"num_tokens": 48383737.0,
|
|
"step": 22090
|
|
},
|
|
{
|
|
"entropy": 5.56206693649292,
|
|
"epoch": 2.192834458118301,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00045214670257424835,
|
|
"loss": 5.0225,
|
|
"mean_token_accuracy": 0.17904094606637955,
|
|
"num_tokens": 48394547.0,
|
|
"step": 22095
|
|
},
|
|
{
|
|
"entropy": 5.609930038452148,
|
|
"epoch": 2.1933306867804685,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004521248552212671,
|
|
"loss": 5.0893,
|
|
"mean_token_accuracy": 0.17812312692403792,
|
|
"num_tokens": 48404906.0,
|
|
"step": 22100
|
|
},
|
|
{
|
|
"entropy": 5.57509446144104,
|
|
"epoch": 2.193826915442636,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004521030034759711,
|
|
"loss": 5.0235,
|
|
"mean_token_accuracy": 0.18149878233671188,
|
|
"num_tokens": 48416425.0,
|
|
"step": 22105
|
|
},
|
|
{
|
|
"entropy": 5.598795938491821,
|
|
"epoch": 2.1943231441048034,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004520811473389023,
|
|
"loss": 4.9865,
|
|
"mean_token_accuracy": 0.1817646488547325,
|
|
"num_tokens": 48426967.0,
|
|
"step": 22110
|
|
},
|
|
{
|
|
"entropy": 5.612984704971313,
|
|
"epoch": 2.194819372766971,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00045205928681060255,
|
|
"loss": 5.1058,
|
|
"mean_token_accuracy": 0.18466767072677612,
|
|
"num_tokens": 48439720.0,
|
|
"step": 22115
|
|
},
|
|
{
|
|
"entropy": 5.585451602935791,
|
|
"epoch": 2.1953156014291384,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000452037421891614,
|
|
"loss": 5.0926,
|
|
"mean_token_accuracy": 0.18281929045915604,
|
|
"num_tokens": 48449949.0,
|
|
"step": 22120
|
|
},
|
|
{
|
|
"entropy": 5.5391075134277346,
|
|
"epoch": 2.195811830091306,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00045201555258247896,
|
|
"loss": 4.98,
|
|
"mean_token_accuracy": 0.18449413776397705,
|
|
"num_tokens": 48462515.0,
|
|
"step": 22125
|
|
},
|
|
{
|
|
"entropy": 5.56147837638855,
|
|
"epoch": 2.196308058753474,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004519936788837396,
|
|
"loss": 5.0111,
|
|
"mean_token_accuracy": 0.18165423572063447,
|
|
"num_tokens": 48471984.0,
|
|
"step": 22130
|
|
},
|
|
{
|
|
"entropy": 5.6573656558990475,
|
|
"epoch": 2.1968042874156413,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00045197180079593836,
|
|
"loss": 5.1004,
|
|
"mean_token_accuracy": 0.17616873532533645,
|
|
"num_tokens": 48482814.0,
|
|
"step": 22135
|
|
},
|
|
{
|
|
"entropy": 5.655974102020264,
|
|
"epoch": 2.1973005160778087,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00045194991831961777,
|
|
"loss": 5.0457,
|
|
"mean_token_accuracy": 0.18555772602558135,
|
|
"num_tokens": 48493670.0,
|
|
"step": 22140
|
|
},
|
|
{
|
|
"entropy": 5.546384620666504,
|
|
"epoch": 2.197796744739976,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004519280314553206,
|
|
"loss": 5.0243,
|
|
"mean_token_accuracy": 0.17614435255527497,
|
|
"num_tokens": 48504758.0,
|
|
"step": 22145
|
|
},
|
|
{
|
|
"entropy": 5.6040102481842045,
|
|
"epoch": 2.1982929734021437,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004519061402035894,
|
|
"loss": 5.0543,
|
|
"mean_token_accuracy": 0.1704815298318863,
|
|
"num_tokens": 48515846.0,
|
|
"step": 22150
|
|
},
|
|
{
|
|
"entropy": 5.612509298324585,
|
|
"epoch": 2.198789202064311,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00045188424456496723,
|
|
"loss": 5.0394,
|
|
"mean_token_accuracy": 0.18775732070207596,
|
|
"num_tokens": 48526136.0,
|
|
"step": 22155
|
|
},
|
|
{
|
|
"entropy": 5.641967296600342,
|
|
"epoch": 2.1992854307264786,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00045186234453999693,
|
|
"loss": 5.1534,
|
|
"mean_token_accuracy": 0.17862827479839324,
|
|
"num_tokens": 48536031.0,
|
|
"step": 22160
|
|
},
|
|
{
|
|
"entropy": 5.487728214263916,
|
|
"epoch": 2.199781659388646,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00045184044012922154,
|
|
"loss": 4.9683,
|
|
"mean_token_accuracy": 0.18186060041189195,
|
|
"num_tokens": 48546965.0,
|
|
"step": 22165
|
|
},
|
|
{
|
|
"entropy": 5.60263466835022,
|
|
"epoch": 2.200277888050814,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00045181853133318425,
|
|
"loss": 5.0504,
|
|
"mean_token_accuracy": 0.17720620930194855,
|
|
"num_tokens": 48557637.0,
|
|
"step": 22170
|
|
},
|
|
{
|
|
"entropy": 5.631606817245483,
|
|
"epoch": 2.2007741167129815,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004517966181524285,
|
|
"loss": 5.0938,
|
|
"mean_token_accuracy": 0.18279265016317367,
|
|
"num_tokens": 48568578.0,
|
|
"step": 22175
|
|
},
|
|
{
|
|
"entropy": 5.659185266494751,
|
|
"epoch": 2.201270345375149,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004517747005874975,
|
|
"loss": 5.1313,
|
|
"mean_token_accuracy": 0.17839040607213974,
|
|
"num_tokens": 48581782.0,
|
|
"step": 22180
|
|
},
|
|
{
|
|
"entropy": 5.524752521514893,
|
|
"epoch": 2.2017665740373165,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004517527786389349,
|
|
"loss": 4.9938,
|
|
"mean_token_accuracy": 0.1855344757437706,
|
|
"num_tokens": 48592432.0,
|
|
"step": 22185
|
|
},
|
|
{
|
|
"entropy": 5.538179397583008,
|
|
"epoch": 2.202262802699484,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00045173085230728417,
|
|
"loss": 5.0282,
|
|
"mean_token_accuracy": 0.18091219216585158,
|
|
"num_tokens": 48603251.0,
|
|
"step": 22190
|
|
},
|
|
{
|
|
"entropy": 5.633578586578369,
|
|
"epoch": 2.2027590313616514,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004517089215930892,
|
|
"loss": 5.1247,
|
|
"mean_token_accuracy": 0.1747087761759758,
|
|
"num_tokens": 48616118.0,
|
|
"step": 22195
|
|
},
|
|
{
|
|
"entropy": 5.640906906127929,
|
|
"epoch": 2.203255260023819,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00045168698649689375,
|
|
"loss": 5.0896,
|
|
"mean_token_accuracy": 0.17727308422327043,
|
|
"num_tokens": 48626903.0,
|
|
"step": 22200
|
|
},
|
|
{
|
|
"entropy": 5.558699989318848,
|
|
"epoch": 2.2037514886859864,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00045166504701924176,
|
|
"loss": 4.9701,
|
|
"mean_token_accuracy": 0.18535945266485215,
|
|
"num_tokens": 48638186.0,
|
|
"step": 22205
|
|
},
|
|
{
|
|
"entropy": 5.613149642944336,
|
|
"epoch": 2.204247717348154,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.00045164310316067727,
|
|
"loss": 5.0943,
|
|
"mean_token_accuracy": 0.1711938574910164,
|
|
"num_tokens": 48649948.0,
|
|
"step": 22210
|
|
},
|
|
{
|
|
"entropy": 5.587204265594482,
|
|
"epoch": 2.2047439460103218,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004516211549217444,
|
|
"loss": 4.9992,
|
|
"mean_token_accuracy": 0.18400440067052842,
|
|
"num_tokens": 48660869.0,
|
|
"step": 22215
|
|
},
|
|
{
|
|
"entropy": 5.526603412628174,
|
|
"epoch": 2.2052401746724892,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004515992023029875,
|
|
"loss": 5.0232,
|
|
"mean_token_accuracy": 0.17694871872663498,
|
|
"num_tokens": 48673383.0,
|
|
"step": 22220
|
|
},
|
|
{
|
|
"entropy": 5.513467025756836,
|
|
"epoch": 2.2057364033346567,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000451577245304951,
|
|
"loss": 4.9807,
|
|
"mean_token_accuracy": 0.18683461397886275,
|
|
"num_tokens": 48684071.0,
|
|
"step": 22225
|
|
},
|
|
{
|
|
"entropy": 5.580668544769287,
|
|
"epoch": 2.206232631996824,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004515552839281792,
|
|
"loss": 5.0145,
|
|
"mean_token_accuracy": 0.17973570823669432,
|
|
"num_tokens": 48695432.0,
|
|
"step": 22230
|
|
},
|
|
{
|
|
"entropy": 5.58124189376831,
|
|
"epoch": 2.2067288606589917,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004515333181732169,
|
|
"loss": 5.0237,
|
|
"mean_token_accuracy": 0.18465565145015717,
|
|
"num_tokens": 48706102.0,
|
|
"step": 22235
|
|
},
|
|
{
|
|
"entropy": 5.547732591629028,
|
|
"epoch": 2.207225089321159,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00045151134804060863,
|
|
"loss": 5.077,
|
|
"mean_token_accuracy": 0.17627473622560502,
|
|
"num_tokens": 48717748.0,
|
|
"step": 22240
|
|
},
|
|
{
|
|
"entropy": 5.588041067123413,
|
|
"epoch": 2.2077213179833266,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004514893735308993,
|
|
"loss": 4.9801,
|
|
"mean_token_accuracy": 0.1840432822704315,
|
|
"num_tokens": 48728941.0,
|
|
"step": 22245
|
|
},
|
|
{
|
|
"entropy": 5.569143676757813,
|
|
"epoch": 2.208217546645494,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004514673946446338,
|
|
"loss": 5.0443,
|
|
"mean_token_accuracy": 0.1831594243645668,
|
|
"num_tokens": 48738565.0,
|
|
"step": 22250
|
|
},
|
|
{
|
|
"entropy": 5.562809848785401,
|
|
"epoch": 2.208713775307662,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004514454113823572,
|
|
"loss": 5.019,
|
|
"mean_token_accuracy": 0.1765393540263176,
|
|
"num_tokens": 48749537.0,
|
|
"step": 22255
|
|
},
|
|
{
|
|
"entropy": 5.545636415481567,
|
|
"epoch": 2.2092100039698295,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004514234237446146,
|
|
"loss": 5.0205,
|
|
"mean_token_accuracy": 0.17443419694900514,
|
|
"num_tokens": 48760388.0,
|
|
"step": 22260
|
|
},
|
|
{
|
|
"entropy": 5.5714531421661375,
|
|
"epoch": 2.209706232631997,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00045140143173195117,
|
|
"loss": 5.0509,
|
|
"mean_token_accuracy": 0.1768399953842163,
|
|
"num_tokens": 48770551.0,
|
|
"step": 22265
|
|
},
|
|
{
|
|
"entropy": 5.548145580291748,
|
|
"epoch": 2.2102024612941644,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004513794353449124,
|
|
"loss": 4.9972,
|
|
"mean_token_accuracy": 0.17944179028272628,
|
|
"num_tokens": 48780739.0,
|
|
"step": 22270
|
|
},
|
|
{
|
|
"entropy": 5.593333292007446,
|
|
"epoch": 2.210698689956332,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004513574345840437,
|
|
"loss": 5.1188,
|
|
"mean_token_accuracy": 0.17226570546627046,
|
|
"num_tokens": 48791478.0,
|
|
"step": 22275
|
|
},
|
|
{
|
|
"entropy": 5.6152276515960695,
|
|
"epoch": 2.2111949186184994,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004513354294498907,
|
|
"loss": 5.0739,
|
|
"mean_token_accuracy": 0.17670032978057862,
|
|
"num_tokens": 48802202.0,
|
|
"step": 22280
|
|
},
|
|
{
|
|
"entropy": 5.589963054656982,
|
|
"epoch": 2.211691147280667,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00045131341994299895,
|
|
"loss": 5.0476,
|
|
"mean_token_accuracy": 0.18130356073379517,
|
|
"num_tokens": 48813619.0,
|
|
"step": 22285
|
|
},
|
|
{
|
|
"entropy": 5.607101535797119,
|
|
"epoch": 2.2121873759428343,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004512914060639143,
|
|
"loss": 5.0065,
|
|
"mean_token_accuracy": 0.18936029970645904,
|
|
"num_tokens": 48824951.0,
|
|
"step": 22290
|
|
},
|
|
{
|
|
"entropy": 5.5926981449127195,
|
|
"epoch": 2.212683604605002,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004512693878131827,
|
|
"loss": 5.0194,
|
|
"mean_token_accuracy": 0.18406404107809066,
|
|
"num_tokens": 48834328.0,
|
|
"step": 22295
|
|
},
|
|
{
|
|
"entropy": 5.57903528213501,
|
|
"epoch": 2.2131798332671697,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00045124736519135003,
|
|
"loss": 5.0581,
|
|
"mean_token_accuracy": 0.17980943322181703,
|
|
"num_tokens": 48843880.0,
|
|
"step": 22300
|
|
},
|
|
{
|
|
"entropy": 5.5731042385101315,
|
|
"epoch": 2.213676061929337,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00045122533819896257,
|
|
"loss": 5.0582,
|
|
"mean_token_accuracy": 0.18477343320846557,
|
|
"num_tokens": 48854893.0,
|
|
"step": 22305
|
|
},
|
|
{
|
|
"entropy": 5.580644655227661,
|
|
"epoch": 2.2141722905915047,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004512033068365664,
|
|
"loss": 5.1188,
|
|
"mean_token_accuracy": 0.17615607529878616,
|
|
"num_tokens": 48867308.0,
|
|
"step": 22310
|
|
},
|
|
{
|
|
"entropy": 5.627501344680786,
|
|
"epoch": 2.214668519253672,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004511812711047079,
|
|
"loss": 5.1042,
|
|
"mean_token_accuracy": 0.17725855112075806,
|
|
"num_tokens": 48880222.0,
|
|
"step": 22315
|
|
},
|
|
{
|
|
"entropy": 5.652177000045777,
|
|
"epoch": 2.2151647479158396,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00045115923100393356,
|
|
"loss": 5.0476,
|
|
"mean_token_accuracy": 0.1829438477754593,
|
|
"num_tokens": 48890345.0,
|
|
"step": 22320
|
|
},
|
|
{
|
|
"entropy": 5.583768510818482,
|
|
"epoch": 2.215660976578007,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00045113718653478984,
|
|
"loss": 4.9856,
|
|
"mean_token_accuracy": 0.18363598585128785,
|
|
"num_tokens": 48901267.0,
|
|
"step": 22325
|
|
},
|
|
{
|
|
"entropy": 5.604900121688843,
|
|
"epoch": 2.2161572052401746,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004511151376978234,
|
|
"loss": 5.0508,
|
|
"mean_token_accuracy": 0.18134261071681976,
|
|
"num_tokens": 48911739.0,
|
|
"step": 22330
|
|
},
|
|
{
|
|
"entropy": 5.607231092453003,
|
|
"epoch": 2.216653433902342,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00045109308449358114,
|
|
"loss": 4.9937,
|
|
"mean_token_accuracy": 0.1829239159822464,
|
|
"num_tokens": 48922376.0,
|
|
"step": 22335
|
|
},
|
|
{
|
|
"entropy": 5.58563380241394,
|
|
"epoch": 2.21714966256451,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004510710269226098,
|
|
"loss": 4.933,
|
|
"mean_token_accuracy": 0.18203675746917725,
|
|
"num_tokens": 48934101.0,
|
|
"step": 22340
|
|
},
|
|
{
|
|
"entropy": 5.537929487228394,
|
|
"epoch": 2.2176458912266774,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004510489649854564,
|
|
"loss": 5.0186,
|
|
"mean_token_accuracy": 0.18465807884931565,
|
|
"num_tokens": 48944684.0,
|
|
"step": 22345
|
|
},
|
|
{
|
|
"entropy": 5.565070056915284,
|
|
"epoch": 2.218142119888845,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000451026898682668,
|
|
"loss": 5.0212,
|
|
"mean_token_accuracy": 0.1741677850484848,
|
|
"num_tokens": 48955255.0,
|
|
"step": 22350
|
|
},
|
|
{
|
|
"entropy": 5.5622382164001465,
|
|
"epoch": 2.2186383485510124,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004510048280147918,
|
|
"loss": 5.0449,
|
|
"mean_token_accuracy": 0.18326972424983978,
|
|
"num_tokens": 48967034.0,
|
|
"step": 22355
|
|
},
|
|
{
|
|
"entropy": 5.620797395706177,
|
|
"epoch": 2.21913457721318,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004509827529823751,
|
|
"loss": 5.1404,
|
|
"mean_token_accuracy": 0.17184707522392273,
|
|
"num_tokens": 48977903.0,
|
|
"step": 22360
|
|
},
|
|
{
|
|
"entropy": 5.613242053985596,
|
|
"epoch": 2.2196308058753473,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00045096067358596536,
|
|
"loss": 5.0165,
|
|
"mean_token_accuracy": 0.18206143230199814,
|
|
"num_tokens": 48988889.0,
|
|
"step": 22365
|
|
},
|
|
{
|
|
"entropy": 5.6383514404296875,
|
|
"epoch": 2.220127034537515,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00045093858982611006,
|
|
"loss": 5.12,
|
|
"mean_token_accuracy": 0.16795546412467957,
|
|
"num_tokens": 48998946.0,
|
|
"step": 22370
|
|
},
|
|
{
|
|
"entropy": 5.592536306381225,
|
|
"epoch": 2.2206232631996823,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004509165017033569,
|
|
"loss": 5.0197,
|
|
"mean_token_accuracy": 0.18399660438299179,
|
|
"num_tokens": 49008141.0,
|
|
"step": 22375
|
|
},
|
|
{
|
|
"entropy": 5.547129583358765,
|
|
"epoch": 2.2211194918618498,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00045089440921825354,
|
|
"loss": 4.9411,
|
|
"mean_token_accuracy": 0.19075675904750825,
|
|
"num_tokens": 49019387.0,
|
|
"step": 22380
|
|
},
|
|
{
|
|
"entropy": 5.526688098907471,
|
|
"epoch": 2.2216157205240172,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00045087231237134787,
|
|
"loss": 4.9956,
|
|
"mean_token_accuracy": 0.18144616335630417,
|
|
"num_tokens": 49030280.0,
|
|
"step": 22385
|
|
},
|
|
{
|
|
"entropy": 5.620566320419312,
|
|
"epoch": 2.222111949186185,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00045085021116318783,
|
|
"loss": 4.9849,
|
|
"mean_token_accuracy": 0.18748746067285538,
|
|
"num_tokens": 49041766.0,
|
|
"step": 22390
|
|
},
|
|
{
|
|
"entropy": 5.714295768737793,
|
|
"epoch": 2.2226081778483526,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004508281055943214,
|
|
"loss": 5.221,
|
|
"mean_token_accuracy": 0.1705726847052574,
|
|
"num_tokens": 49052931.0,
|
|
"step": 22395
|
|
},
|
|
{
|
|
"entropy": 5.563606691360474,
|
|
"epoch": 2.22310440651052,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004508059956652969,
|
|
"loss": 5.0187,
|
|
"mean_token_accuracy": 0.1782955199480057,
|
|
"num_tokens": 49064153.0,
|
|
"step": 22400
|
|
},
|
|
{
|
|
"entropy": 5.556827735900879,
|
|
"epoch": 2.2236006351726876,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004507838813766625,
|
|
"loss": 5.0361,
|
|
"mean_token_accuracy": 0.18064209669828415,
|
|
"num_tokens": 49075857.0,
|
|
"step": 22405
|
|
},
|
|
{
|
|
"entropy": 5.678604650497436,
|
|
"epoch": 2.224096863834855,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004507617627289666,
|
|
"loss": 5.0593,
|
|
"mean_token_accuracy": 0.1782527133822441,
|
|
"num_tokens": 49086632.0,
|
|
"step": 22410
|
|
},
|
|
{
|
|
"entropy": 5.607068967819214,
|
|
"epoch": 2.2245930924970225,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004507396397227577,
|
|
"loss": 5.0279,
|
|
"mean_token_accuracy": 0.1786979392170906,
|
|
"num_tokens": 49098086.0,
|
|
"step": 22415
|
|
},
|
|
{
|
|
"entropy": 5.527521991729737,
|
|
"epoch": 2.22508932115919,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00045071751235858454,
|
|
"loss": 4.9404,
|
|
"mean_token_accuracy": 0.18760869055986404,
|
|
"num_tokens": 49108857.0,
|
|
"step": 22420
|
|
},
|
|
{
|
|
"entropy": 5.549077796936035,
|
|
"epoch": 2.2255855498213575,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004506953806369956,
|
|
"loss": 4.9754,
|
|
"mean_token_accuracy": 0.1857747495174408,
|
|
"num_tokens": 49119609.0,
|
|
"step": 22425
|
|
},
|
|
{
|
|
"entropy": 5.608169221878052,
|
|
"epoch": 2.2260817784835254,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004506732445585399,
|
|
"loss": 5.074,
|
|
"mean_token_accuracy": 0.1825532153248787,
|
|
"num_tokens": 49130047.0,
|
|
"step": 22430
|
|
},
|
|
{
|
|
"entropy": 5.572369861602783,
|
|
"epoch": 2.226578007145693,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004506511041237662,
|
|
"loss": 5.0245,
|
|
"mean_token_accuracy": 0.18269540518522262,
|
|
"num_tokens": 49140517.0,
|
|
"step": 22435
|
|
},
|
|
{
|
|
"entropy": 5.601465511322021,
|
|
"epoch": 2.2270742358078603,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00045062895933322366,
|
|
"loss": 5.0356,
|
|
"mean_token_accuracy": 0.1782595306634903,
|
|
"num_tokens": 49151497.0,
|
|
"step": 22440
|
|
},
|
|
{
|
|
"entropy": 5.482938241958618,
|
|
"epoch": 2.227570464470028,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004506068101874614,
|
|
"loss": 4.9599,
|
|
"mean_token_accuracy": 0.17888348251581193,
|
|
"num_tokens": 49161568.0,
|
|
"step": 22445
|
|
},
|
|
{
|
|
"entropy": 5.6057229995727536,
|
|
"epoch": 2.2280666931321953,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00045058465668702856,
|
|
"loss": 5.0732,
|
|
"mean_token_accuracy": 0.1794983848929405,
|
|
"num_tokens": 49173554.0,
|
|
"step": 22450
|
|
},
|
|
{
|
|
"entropy": 5.671862602233887,
|
|
"epoch": 2.2285629217943628,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00045056249883247457,
|
|
"loss": 5.0718,
|
|
"mean_token_accuracy": 0.1773956760764122,
|
|
"num_tokens": 49185399.0,
|
|
"step": 22455
|
|
},
|
|
{
|
|
"entropy": 5.608171844482422,
|
|
"epoch": 2.2290591504565302,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00045054033662434903,
|
|
"loss": 4.9957,
|
|
"mean_token_accuracy": 0.18290940374135972,
|
|
"num_tokens": 49195489.0,
|
|
"step": 22460
|
|
},
|
|
{
|
|
"entropy": 5.496192836761475,
|
|
"epoch": 2.2295553791186977,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00045051817006320127,
|
|
"loss": 4.9601,
|
|
"mean_token_accuracy": 0.1836245521903038,
|
|
"num_tokens": 49204652.0,
|
|
"step": 22465
|
|
},
|
|
{
|
|
"entropy": 5.54185004234314,
|
|
"epoch": 2.230051607780865,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00045049599914958124,
|
|
"loss": 5.0546,
|
|
"mean_token_accuracy": 0.17424410134553908,
|
|
"num_tokens": 49215420.0,
|
|
"step": 22470
|
|
},
|
|
{
|
|
"entropy": 5.594494771957398,
|
|
"epoch": 2.230547836443033,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004504738238840385,
|
|
"loss": 5.0139,
|
|
"mean_token_accuracy": 0.18304983228445054,
|
|
"num_tokens": 49225375.0,
|
|
"step": 22475
|
|
},
|
|
{
|
|
"entropy": 5.633879947662353,
|
|
"epoch": 2.2310440651052006,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004504516442671231,
|
|
"loss": 5.0182,
|
|
"mean_token_accuracy": 0.17765786349773408,
|
|
"num_tokens": 49238399.0,
|
|
"step": 22480
|
|
},
|
|
{
|
|
"entropy": 5.5827446460723875,
|
|
"epoch": 2.231540293767368,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.00045042946029938495,
|
|
"loss": 4.9979,
|
|
"mean_token_accuracy": 0.17983777970075607,
|
|
"num_tokens": 49251069.0,
|
|
"step": 22485
|
|
},
|
|
{
|
|
"entropy": 5.5566212177276615,
|
|
"epoch": 2.2320365224295355,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00045040727198137416,
|
|
"loss": 5.0305,
|
|
"mean_token_accuracy": 0.1777949184179306,
|
|
"num_tokens": 49263859.0,
|
|
"step": 22490
|
|
},
|
|
{
|
|
"entropy": 5.604022073745727,
|
|
"epoch": 2.232532751091703,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00045038507931364103,
|
|
"loss": 5.0295,
|
|
"mean_token_accuracy": 0.1811242073774338,
|
|
"num_tokens": 49274846.0,
|
|
"step": 22495
|
|
},
|
|
{
|
|
"entropy": 5.56999454498291,
|
|
"epoch": 2.2330289797538705,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00045036288229673583,
|
|
"loss": 4.9791,
|
|
"mean_token_accuracy": 0.18691035509109497,
|
|
"num_tokens": 49285197.0,
|
|
"step": 22500
|
|
},
|
|
{
|
|
"entropy": 5.534236335754395,
|
|
"epoch": 2.233525208416038,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00045034068093120907,
|
|
"loss": 4.9766,
|
|
"mean_token_accuracy": 0.17641551047563553,
|
|
"num_tokens": 49296238.0,
|
|
"step": 22505
|
|
},
|
|
{
|
|
"entropy": 5.677579641342163,
|
|
"epoch": 2.2340214370782054,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004503184752176112,
|
|
"loss": 5.2035,
|
|
"mean_token_accuracy": 0.1695760115981102,
|
|
"num_tokens": 49308262.0,
|
|
"step": 22510
|
|
},
|
|
{
|
|
"entropy": 5.586322879791259,
|
|
"epoch": 2.2345176657403734,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000450296265156493,
|
|
"loss": 4.9835,
|
|
"mean_token_accuracy": 0.18736137598752975,
|
|
"num_tokens": 49318881.0,
|
|
"step": 22515
|
|
},
|
|
{
|
|
"entropy": 5.651030826568603,
|
|
"epoch": 2.235013894402541,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00045027405074840506,
|
|
"loss": 5.1322,
|
|
"mean_token_accuracy": 0.17456569522619247,
|
|
"num_tokens": 49329470.0,
|
|
"step": 22520
|
|
},
|
|
{
|
|
"entropy": 5.595328664779663,
|
|
"epoch": 2.2355101230647083,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004502518319938984,
|
|
"loss": 5.0198,
|
|
"mean_token_accuracy": 0.18555116206407546,
|
|
"num_tokens": 49339806.0,
|
|
"step": 22525
|
|
},
|
|
{
|
|
"entropy": 5.701306343078613,
|
|
"epoch": 2.236006351726876,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00045022960889352394,
|
|
"loss": 5.1294,
|
|
"mean_token_accuracy": 0.17799793034791947,
|
|
"num_tokens": 49350295.0,
|
|
"step": 22530
|
|
},
|
|
{
|
|
"entropy": 5.607735109329224,
|
|
"epoch": 2.2365025803890433,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00045020738144783273,
|
|
"loss": 5.0372,
|
|
"mean_token_accuracy": 0.17820966094732285,
|
|
"num_tokens": 49360735.0,
|
|
"step": 22535
|
|
},
|
|
{
|
|
"entropy": 5.548648738861084,
|
|
"epoch": 2.2369988090512107,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004501851496573761,
|
|
"loss": 4.9877,
|
|
"mean_token_accuracy": 0.18256026655435562,
|
|
"num_tokens": 49372278.0,
|
|
"step": 22540
|
|
},
|
|
{
|
|
"entropy": 5.572845602035523,
|
|
"epoch": 2.237495037713378,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004501629135227051,
|
|
"loss": 5.0928,
|
|
"mean_token_accuracy": 0.17433278560638427,
|
|
"num_tokens": 49382842.0,
|
|
"step": 22545
|
|
},
|
|
{
|
|
"entropy": 5.617898464202881,
|
|
"epoch": 2.2379912663755457,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004501406730443714,
|
|
"loss": 5.0912,
|
|
"mean_token_accuracy": 0.17576729357242585,
|
|
"num_tokens": 49394633.0,
|
|
"step": 22550
|
|
},
|
|
{
|
|
"entropy": 5.668472146987915,
|
|
"epoch": 2.238487495037713,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00045011842822292636,
|
|
"loss": 5.0675,
|
|
"mean_token_accuracy": 0.17675844132900237,
|
|
"num_tokens": 49404731.0,
|
|
"step": 22555
|
|
},
|
|
{
|
|
"entropy": 5.641077184677124,
|
|
"epoch": 2.238983723699881,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004500961790589216,
|
|
"loss": 5.0544,
|
|
"mean_token_accuracy": 0.17910027354955674,
|
|
"num_tokens": 49415918.0,
|
|
"step": 22560
|
|
},
|
|
{
|
|
"entropy": 5.553595685958863,
|
|
"epoch": 2.2394799523620486,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000450073925552909,
|
|
"loss": 4.9969,
|
|
"mean_token_accuracy": 0.17839334011077881,
|
|
"num_tokens": 49427458.0,
|
|
"step": 22565
|
|
},
|
|
{
|
|
"entropy": 5.584511375427246,
|
|
"epoch": 2.239976181024216,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004500516677054403,
|
|
"loss": 5.0178,
|
|
"mean_token_accuracy": 0.18439576029777527,
|
|
"num_tokens": 49437696.0,
|
|
"step": 22570
|
|
},
|
|
{
|
|
"entropy": 5.65137825012207,
|
|
"epoch": 2.2404724096863835,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00045002940551706726,
|
|
"loss": 5.2217,
|
|
"mean_token_accuracy": 0.1747758075594902,
|
|
"num_tokens": 49449220.0,
|
|
"step": 22575
|
|
},
|
|
{
|
|
"entropy": 5.620813655853271,
|
|
"epoch": 2.240968638348551,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00045000713898834225,
|
|
"loss": 5.0493,
|
|
"mean_token_accuracy": 0.17836696058511733,
|
|
"num_tokens": 49459624.0,
|
|
"step": 22580
|
|
},
|
|
{
|
|
"entropy": 5.617305517196655,
|
|
"epoch": 2.2414648670107185,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004499848681198173,
|
|
"loss": 4.9687,
|
|
"mean_token_accuracy": 0.18799397051334382,
|
|
"num_tokens": 49471813.0,
|
|
"step": 22585
|
|
},
|
|
{
|
|
"entropy": 5.5926868438720705,
|
|
"epoch": 2.241961095672886,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004499625929120447,
|
|
"loss": 5.0383,
|
|
"mean_token_accuracy": 0.18021085262298583,
|
|
"num_tokens": 49482624.0,
|
|
"step": 22590
|
|
},
|
|
{
|
|
"entropy": 5.596084833145142,
|
|
"epoch": 2.2424573243350534,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004499403133655768,
|
|
"loss": 5.0643,
|
|
"mean_token_accuracy": 0.1739892914891243,
|
|
"num_tokens": 49493791.0,
|
|
"step": 22595
|
|
},
|
|
{
|
|
"entropy": 5.6493675231933596,
|
|
"epoch": 2.2429535529972213,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004499180294809661,
|
|
"loss": 5.096,
|
|
"mean_token_accuracy": 0.17527344971895217,
|
|
"num_tokens": 49504060.0,
|
|
"step": 22600
|
|
},
|
|
{
|
|
"entropy": 5.548713541030883,
|
|
"epoch": 2.243449781659389,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00044989574125876516,
|
|
"loss": 4.9347,
|
|
"mean_token_accuracy": 0.18660158216953276,
|
|
"num_tokens": 49515962.0,
|
|
"step": 22605
|
|
},
|
|
{
|
|
"entropy": 5.6037561893463135,
|
|
"epoch": 2.2439460103215563,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004498734486995267,
|
|
"loss": 5.0652,
|
|
"mean_token_accuracy": 0.17424511015415192,
|
|
"num_tokens": 49526676.0,
|
|
"step": 22610
|
|
},
|
|
{
|
|
"entropy": 5.607731294631958,
|
|
"epoch": 2.2444422389837237,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00044985115180380355,
|
|
"loss": 5.0577,
|
|
"mean_token_accuracy": 0.17544593513011933,
|
|
"num_tokens": 49537347.0,
|
|
"step": 22615
|
|
},
|
|
{
|
|
"entropy": 5.624332332611084,
|
|
"epoch": 2.2449384676458912,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00044982885057214857,
|
|
"loss": 5.0639,
|
|
"mean_token_accuracy": 0.17598291337490082,
|
|
"num_tokens": 49547422.0,
|
|
"step": 22620
|
|
},
|
|
{
|
|
"entropy": 5.583463382720947,
|
|
"epoch": 2.2454346963080587,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00044980654500511485,
|
|
"loss": 4.9204,
|
|
"mean_token_accuracy": 0.18898916244506836,
|
|
"num_tokens": 49557250.0,
|
|
"step": 22625
|
|
},
|
|
{
|
|
"entropy": 5.654331064224243,
|
|
"epoch": 2.245930924970226,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00044978423510325544,
|
|
"loss": 5.117,
|
|
"mean_token_accuracy": 0.17775555253028869,
|
|
"num_tokens": 49567106.0,
|
|
"step": 22630
|
|
},
|
|
{
|
|
"entropy": 5.620014476776123,
|
|
"epoch": 2.2464271536323936,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004497619208671237,
|
|
"loss": 5.0672,
|
|
"mean_token_accuracy": 0.17509078681468965,
|
|
"num_tokens": 49578978.0,
|
|
"step": 22635
|
|
},
|
|
{
|
|
"entropy": 5.686333179473877,
|
|
"epoch": 2.246923382294561,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004497396022972728,
|
|
"loss": 5.1064,
|
|
"mean_token_accuracy": 0.1785639524459839,
|
|
"num_tokens": 49589730.0,
|
|
"step": 22640
|
|
},
|
|
{
|
|
"entropy": 5.603769016265869,
|
|
"epoch": 2.247419610956729,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004497172793942564,
|
|
"loss": 5.0191,
|
|
"mean_token_accuracy": 0.18040618747472764,
|
|
"num_tokens": 49600881.0,
|
|
"step": 22645
|
|
},
|
|
{
|
|
"entropy": 5.599695825576783,
|
|
"epoch": 2.2479158396188965,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004496949521586279,
|
|
"loss": 5.0659,
|
|
"mean_token_accuracy": 0.1783287286758423,
|
|
"num_tokens": 49611120.0,
|
|
"step": 22650
|
|
},
|
|
{
|
|
"entropy": 5.618778085708618,
|
|
"epoch": 2.248412068281064,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00044967262059094097,
|
|
"loss": 5.0855,
|
|
"mean_token_accuracy": 0.17207848131656647,
|
|
"num_tokens": 49622978.0,
|
|
"step": 22655
|
|
},
|
|
{
|
|
"entropy": 5.601924800872803,
|
|
"epoch": 2.2489082969432315,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00044965028469174956,
|
|
"loss": 5.0726,
|
|
"mean_token_accuracy": 0.17792664468288422,
|
|
"num_tokens": 49633678.0,
|
|
"step": 22660
|
|
},
|
|
{
|
|
"entropy": 5.610531854629516,
|
|
"epoch": 2.249404525605399,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00044962794446160736,
|
|
"loss": 5.0619,
|
|
"mean_token_accuracy": 0.17468793988227843,
|
|
"num_tokens": 49644886.0,
|
|
"step": 22665
|
|
},
|
|
{
|
|
"entropy": 5.597045993804931,
|
|
"epoch": 2.2499007542675664,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00044960559990106844,
|
|
"loss": 4.9987,
|
|
"mean_token_accuracy": 0.1867280676960945,
|
|
"num_tokens": 49656790.0,
|
|
"step": 22670
|
|
},
|
|
{
|
|
"entropy": 5.632965612411499,
|
|
"epoch": 2.250396982929734,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004495832510106869,
|
|
"loss": 5.0479,
|
|
"mean_token_accuracy": 0.17537580132484437,
|
|
"num_tokens": 49667943.0,
|
|
"step": 22675
|
|
},
|
|
{
|
|
"entropy": 5.569033288955689,
|
|
"epoch": 2.2508932115919014,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004495608977910169,
|
|
"loss": 5.0299,
|
|
"mean_token_accuracy": 0.17802347838878632,
|
|
"num_tokens": 49678652.0,
|
|
"step": 22680
|
|
},
|
|
{
|
|
"entropy": 5.57305941581726,
|
|
"epoch": 2.2513894402540693,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004495385402426128,
|
|
"loss": 4.9958,
|
|
"mean_token_accuracy": 0.18683501034975053,
|
|
"num_tokens": 49688951.0,
|
|
"step": 22685
|
|
},
|
|
{
|
|
"entropy": 5.588244962692261,
|
|
"epoch": 2.2518856689162368,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000449516178366029,
|
|
"loss": 5.0565,
|
|
"mean_token_accuracy": 0.1780592381954193,
|
|
"num_tokens": 49698750.0,
|
|
"step": 22690
|
|
},
|
|
{
|
|
"entropy": 5.625252962112427,
|
|
"epoch": 2.2523818975784042,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00044949381216182,
|
|
"loss": 5.1349,
|
|
"mean_token_accuracy": 0.171563021838665,
|
|
"num_tokens": 49709442.0,
|
|
"step": 22695
|
|
},
|
|
{
|
|
"entropy": 5.6081953048706055,
|
|
"epoch": 2.2528781262405717,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00044947144163054036,
|
|
"loss": 5.029,
|
|
"mean_token_accuracy": 0.18069500029087066,
|
|
"num_tokens": 49720517.0,
|
|
"step": 22700
|
|
},
|
|
{
|
|
"entropy": 5.608110952377319,
|
|
"epoch": 2.253374354902739,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004494490667727451,
|
|
"loss": 5.0241,
|
|
"mean_token_accuracy": 0.17928366959095002,
|
|
"num_tokens": 49731413.0,
|
|
"step": 22705
|
|
},
|
|
{
|
|
"entropy": 5.653209590911866,
|
|
"epoch": 2.2538705835649067,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00044942668758898873,
|
|
"loss": 5.1929,
|
|
"mean_token_accuracy": 0.16980450451374055,
|
|
"num_tokens": 49742492.0,
|
|
"step": 22710
|
|
},
|
|
{
|
|
"entropy": 5.644893836975098,
|
|
"epoch": 2.254366812227074,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004494043040798265,
|
|
"loss": 5.0306,
|
|
"mean_token_accuracy": 0.1753566488623619,
|
|
"num_tokens": 49753981.0,
|
|
"step": 22715
|
|
},
|
|
{
|
|
"entropy": 5.615680742263794,
|
|
"epoch": 2.2548630408892416,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004493819162458133,
|
|
"loss": 5.0769,
|
|
"mean_token_accuracy": 0.17856322079896927,
|
|
"num_tokens": 49764718.0,
|
|
"step": 22720
|
|
},
|
|
{
|
|
"entropy": 5.599643993377685,
|
|
"epoch": 2.255359269551409,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004493595240875043,
|
|
"loss": 5.0248,
|
|
"mean_token_accuracy": 0.18065377324819565,
|
|
"num_tokens": 49775361.0,
|
|
"step": 22725
|
|
},
|
|
{
|
|
"entropy": 5.544538784027099,
|
|
"epoch": 2.255855498213577,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00044933712760545486,
|
|
"loss": 5.0098,
|
|
"mean_token_accuracy": 0.18104665130376815,
|
|
"num_tokens": 49786670.0,
|
|
"step": 22730
|
|
},
|
|
{
|
|
"entropy": 5.645787715911865,
|
|
"epoch": 2.2563517268757445,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004493147268002203,
|
|
"loss": 5.1408,
|
|
"mean_token_accuracy": 0.17564889937639236,
|
|
"num_tokens": 49796514.0,
|
|
"step": 22735
|
|
},
|
|
{
|
|
"entropy": 5.540385770797729,
|
|
"epoch": 2.256847955537912,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00044929232167235613,
|
|
"loss": 4.9953,
|
|
"mean_token_accuracy": 0.1855500653386116,
|
|
"num_tokens": 49807042.0,
|
|
"step": 22740
|
|
},
|
|
{
|
|
"entropy": 5.565149736404419,
|
|
"epoch": 2.2573441842000794,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004492699122224179,
|
|
"loss": 5.0739,
|
|
"mean_token_accuracy": 0.17502318024635316,
|
|
"num_tokens": 49818779.0,
|
|
"step": 22745
|
|
},
|
|
{
|
|
"entropy": 5.616581821441651,
|
|
"epoch": 2.257840412862247,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00044924749845096144,
|
|
"loss": 5.0671,
|
|
"mean_token_accuracy": 0.17724036574363708,
|
|
"num_tokens": 49829901.0,
|
|
"step": 22750
|
|
},
|
|
{
|
|
"entropy": 5.604426765441895,
|
|
"epoch": 2.2583366415244144,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004492250803585425,
|
|
"loss": 5.0507,
|
|
"mean_token_accuracy": 0.18493872433900832,
|
|
"num_tokens": 49840837.0,
|
|
"step": 22755
|
|
},
|
|
{
|
|
"entropy": 5.614662170410156,
|
|
"epoch": 2.258832870186582,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004492026579457169,
|
|
"loss": 5.0105,
|
|
"mean_token_accuracy": 0.1774394094944,
|
|
"num_tokens": 49853052.0,
|
|
"step": 22760
|
|
},
|
|
{
|
|
"entropy": 5.581817293167115,
|
|
"epoch": 2.2593290988487493,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004491802312130408,
|
|
"loss": 5.0243,
|
|
"mean_token_accuracy": 0.17834030240774154,
|
|
"num_tokens": 49864210.0,
|
|
"step": 22765
|
|
},
|
|
{
|
|
"entropy": 5.563812208175659,
|
|
"epoch": 2.2598253275109172,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004491578001610703,
|
|
"loss": 4.9886,
|
|
"mean_token_accuracy": 0.186432908475399,
|
|
"num_tokens": 49874995.0,
|
|
"step": 22770
|
|
},
|
|
{
|
|
"entropy": 5.50725531578064,
|
|
"epoch": 2.2603215561730847,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00044913536479036163,
|
|
"loss": 5.0049,
|
|
"mean_token_accuracy": 0.1801043227314949,
|
|
"num_tokens": 49886240.0,
|
|
"step": 22775
|
|
},
|
|
{
|
|
"entropy": 5.56751651763916,
|
|
"epoch": 2.260817784835252,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.00044911292510147117,
|
|
"loss": 5.0153,
|
|
"mean_token_accuracy": 0.18055537790060044,
|
|
"num_tokens": 49897580.0,
|
|
"step": 22780
|
|
},
|
|
{
|
|
"entropy": 5.583517980575562,
|
|
"epoch": 2.2613140134974197,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004490904810949553,
|
|
"loss": 5.0583,
|
|
"mean_token_accuracy": 0.1789379447698593,
|
|
"num_tokens": 49907280.0,
|
|
"step": 22785
|
|
},
|
|
{
|
|
"entropy": 5.611277866363525,
|
|
"epoch": 2.261810242159587,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00044906803277137064,
|
|
"loss": 5.0761,
|
|
"mean_token_accuracy": 0.1817319795489311,
|
|
"num_tokens": 49917552.0,
|
|
"step": 22790
|
|
},
|
|
{
|
|
"entropy": 5.586445045471192,
|
|
"epoch": 2.2623064708217546,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004490455801312738,
|
|
"loss": 5.0481,
|
|
"mean_token_accuracy": 0.1772630751132965,
|
|
"num_tokens": 49930610.0,
|
|
"step": 22795
|
|
},
|
|
{
|
|
"entropy": 5.599416589736938,
|
|
"epoch": 2.262802699483922,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004490231231752217,
|
|
"loss": 5.0794,
|
|
"mean_token_accuracy": 0.17749821841716767,
|
|
"num_tokens": 49941054.0,
|
|
"step": 22800
|
|
},
|
|
{
|
|
"entropy": 5.500024700164795,
|
|
"epoch": 2.2632989281460896,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004490006619037711,
|
|
"loss": 4.9263,
|
|
"mean_token_accuracy": 0.19124432057142257,
|
|
"num_tokens": 49950885.0,
|
|
"step": 22805
|
|
},
|
|
{
|
|
"entropy": 5.5474159717559814,
|
|
"epoch": 2.263795156808257,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00044897819631747903,
|
|
"loss": 5.0357,
|
|
"mean_token_accuracy": 0.17892571538686752,
|
|
"num_tokens": 49961723.0,
|
|
"step": 22810
|
|
},
|
|
{
|
|
"entropy": 5.54910945892334,
|
|
"epoch": 2.2642913854704245,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00044895572641690256,
|
|
"loss": 5.0085,
|
|
"mean_token_accuracy": 0.18188804090023042,
|
|
"num_tokens": 49974124.0,
|
|
"step": 22815
|
|
},
|
|
{
|
|
"entropy": 5.572559213638305,
|
|
"epoch": 2.2647876141325924,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.000448933252202599,
|
|
"loss": 5.0346,
|
|
"mean_token_accuracy": 0.18043317794799804,
|
|
"num_tokens": 49985792.0,
|
|
"step": 22820
|
|
},
|
|
{
|
|
"entropy": 5.541806745529175,
|
|
"epoch": 2.26528384279476,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00044891077367512544,
|
|
"loss": 4.9758,
|
|
"mean_token_accuracy": 0.1844248056411743,
|
|
"num_tokens": 49996935.0,
|
|
"step": 22825
|
|
},
|
|
{
|
|
"entropy": 5.653744173049927,
|
|
"epoch": 2.2657800714569274,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004488882908350396,
|
|
"loss": 5.1389,
|
|
"mean_token_accuracy": 0.17303285300731658,
|
|
"num_tokens": 50007545.0,
|
|
"step": 22830
|
|
},
|
|
{
|
|
"entropy": 5.632570362091064,
|
|
"epoch": 2.266276300119095,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004488658036828987,
|
|
"loss": 5.0448,
|
|
"mean_token_accuracy": 0.18197034299373627,
|
|
"num_tokens": 50018797.0,
|
|
"step": 22835
|
|
},
|
|
{
|
|
"entropy": 5.581188726425171,
|
|
"epoch": 2.2667725287812623,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004488433122192606,
|
|
"loss": 5.0106,
|
|
"mean_token_accuracy": 0.18376223891973495,
|
|
"num_tokens": 50030884.0,
|
|
"step": 22840
|
|
},
|
|
{
|
|
"entropy": 5.642255640029907,
|
|
"epoch": 2.26726875744343,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00044882081644468286,
|
|
"loss": 5.1477,
|
|
"mean_token_accuracy": 0.17101453244686127,
|
|
"num_tokens": 50042327.0,
|
|
"step": 22845
|
|
},
|
|
{
|
|
"entropy": 5.608316659927368,
|
|
"epoch": 2.2677649861055973,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00044879831635972345,
|
|
"loss": 5.0854,
|
|
"mean_token_accuracy": 0.18410026282072067,
|
|
"num_tokens": 50053733.0,
|
|
"step": 22850
|
|
},
|
|
{
|
|
"entropy": 5.595193719863891,
|
|
"epoch": 2.268261214767765,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004487758119649403,
|
|
"loss": 5.0191,
|
|
"mean_token_accuracy": 0.18390018343925477,
|
|
"num_tokens": 50064153.0,
|
|
"step": 22855
|
|
},
|
|
{
|
|
"entropy": 5.519360589981079,
|
|
"epoch": 2.2687574434299327,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00044875330326089153,
|
|
"loss": 4.9702,
|
|
"mean_token_accuracy": 0.19200130850076674,
|
|
"num_tokens": 50074397.0,
|
|
"step": 22860
|
|
},
|
|
{
|
|
"entropy": 5.520435428619384,
|
|
"epoch": 2.2692536720921,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004487307902481352,
|
|
"loss": 4.9746,
|
|
"mean_token_accuracy": 0.18198251873254775,
|
|
"num_tokens": 50084074.0,
|
|
"step": 22865
|
|
},
|
|
{
|
|
"entropy": 5.581186103820801,
|
|
"epoch": 2.2697499007542676,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00044870827292722967,
|
|
"loss": 5.0013,
|
|
"mean_token_accuracy": 0.17841627299785615,
|
|
"num_tokens": 50094535.0,
|
|
"step": 22870
|
|
},
|
|
{
|
|
"entropy": 5.589366722106933,
|
|
"epoch": 2.270246129416435,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004486857512987333,
|
|
"loss": 5.0679,
|
|
"mean_token_accuracy": 0.17727411836385726,
|
|
"num_tokens": 50105907.0,
|
|
"step": 22875
|
|
},
|
|
{
|
|
"entropy": 5.544551610946655,
|
|
"epoch": 2.2707423580786026,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00044866322536320447,
|
|
"loss": 5.0399,
|
|
"mean_token_accuracy": 0.18140538930892944,
|
|
"num_tokens": 50117361.0,
|
|
"step": 22880
|
|
},
|
|
{
|
|
"entropy": 5.611779260635376,
|
|
"epoch": 2.27123858674077,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00044864069512120185,
|
|
"loss": 5.0599,
|
|
"mean_token_accuracy": 0.18520863503217697,
|
|
"num_tokens": 50128598.0,
|
|
"step": 22885
|
|
},
|
|
{
|
|
"entropy": 5.591342782974243,
|
|
"epoch": 2.2717348154029375,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00044861816057328424,
|
|
"loss": 5.0369,
|
|
"mean_token_accuracy": 0.17884714901447296,
|
|
"num_tokens": 50140470.0,
|
|
"step": 22890
|
|
},
|
|
{
|
|
"entropy": 5.624648380279541,
|
|
"epoch": 2.272231044065105,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00044859562172001036,
|
|
"loss": 5.0997,
|
|
"mean_token_accuracy": 0.17759020030498504,
|
|
"num_tokens": 50150950.0,
|
|
"step": 22895
|
|
},
|
|
{
|
|
"entropy": 5.535177564620971,
|
|
"epoch": 2.2727272727272725,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004485730785619391,
|
|
"loss": 4.9409,
|
|
"mean_token_accuracy": 0.18485622704029084,
|
|
"num_tokens": 50161173.0,
|
|
"step": 22900
|
|
},
|
|
{
|
|
"entropy": 5.609437751770019,
|
|
"epoch": 2.2732235013894404,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004485505310996295,
|
|
"loss": 5.1723,
|
|
"mean_token_accuracy": 0.17111800909042357,
|
|
"num_tokens": 50173874.0,
|
|
"step": 22905
|
|
},
|
|
{
|
|
"entropy": 5.715093755722046,
|
|
"epoch": 2.273719730051608,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004485279793336406,
|
|
"loss": 5.1213,
|
|
"mean_token_accuracy": 0.17077192962169646,
|
|
"num_tokens": 50185123.0,
|
|
"step": 22910
|
|
},
|
|
{
|
|
"entropy": 5.612595701217652,
|
|
"epoch": 2.2742159587137754,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004485054232645319,
|
|
"loss": 5.0728,
|
|
"mean_token_accuracy": 0.18398701399564743,
|
|
"num_tokens": 50195699.0,
|
|
"step": 22915
|
|
},
|
|
{
|
|
"entropy": 5.651986026763916,
|
|
"epoch": 2.274712187375943,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004484828628928625,
|
|
"loss": 5.0851,
|
|
"mean_token_accuracy": 0.18250927031040193,
|
|
"num_tokens": 50206623.0,
|
|
"step": 22920
|
|
},
|
|
{
|
|
"entropy": 5.673154497146607,
|
|
"epoch": 2.2752084160381103,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00044846029821919193,
|
|
"loss": 5.149,
|
|
"mean_token_accuracy": 0.17489539235830306,
|
|
"num_tokens": 50216086.0,
|
|
"step": 22925
|
|
},
|
|
{
|
|
"entropy": 5.536364316940308,
|
|
"epoch": 2.275704644700278,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004484377292440797,
|
|
"loss": 5.0339,
|
|
"mean_token_accuracy": 0.1776548519730568,
|
|
"num_tokens": 50228472.0,
|
|
"step": 22930
|
|
},
|
|
{
|
|
"entropy": 5.597187137603759,
|
|
"epoch": 2.2762008733624453,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00044841515596808553,
|
|
"loss": 5.0654,
|
|
"mean_token_accuracy": 0.1734164297580719,
|
|
"num_tokens": 50238607.0,
|
|
"step": 22935
|
|
},
|
|
{
|
|
"entropy": 5.606688213348389,
|
|
"epoch": 2.276697102024613,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00044839257839176914,
|
|
"loss": 5.0168,
|
|
"mean_token_accuracy": 0.18222397267818452,
|
|
"num_tokens": 50249890.0,
|
|
"step": 22940
|
|
},
|
|
{
|
|
"entropy": 5.586983013153076,
|
|
"epoch": 2.2771933306867806,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00044836999651569055,
|
|
"loss": 5.013,
|
|
"mean_token_accuracy": 0.18418598771095276,
|
|
"num_tokens": 50260234.0,
|
|
"step": 22945
|
|
},
|
|
{
|
|
"entropy": 5.57249608039856,
|
|
"epoch": 2.277689559348948,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004483474103404095,
|
|
"loss": 5.0647,
|
|
"mean_token_accuracy": 0.18492246121168138,
|
|
"num_tokens": 50271605.0,
|
|
"step": 22950
|
|
},
|
|
{
|
|
"entropy": 5.596893405914306,
|
|
"epoch": 2.2781857880111156,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00044832481986648633,
|
|
"loss": 4.9435,
|
|
"mean_token_accuracy": 0.18492139875888824,
|
|
"num_tokens": 50281837.0,
|
|
"step": 22955
|
|
},
|
|
{
|
|
"entropy": 5.549652242660523,
|
|
"epoch": 2.278682016673283,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000448302225094481,
|
|
"loss": 4.9834,
|
|
"mean_token_accuracy": 0.18546690791845322,
|
|
"num_tokens": 50292524.0,
|
|
"step": 22960
|
|
},
|
|
{
|
|
"entropy": 5.5931768894195555,
|
|
"epoch": 2.2791782453354505,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00044827962602495393,
|
|
"loss": 5.0043,
|
|
"mean_token_accuracy": 0.17987931817770003,
|
|
"num_tokens": 50304009.0,
|
|
"step": 22965
|
|
},
|
|
{
|
|
"entropy": 5.624735116958618,
|
|
"epoch": 2.279674473997618,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00044825702265846557,
|
|
"loss": 5.0764,
|
|
"mean_token_accuracy": 0.17724401950836183,
|
|
"num_tokens": 50316103.0,
|
|
"step": 22970
|
|
},
|
|
{
|
|
"entropy": 5.602565097808838,
|
|
"epoch": 2.2801707026597855,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004482344149955763,
|
|
"loss": 5.0832,
|
|
"mean_token_accuracy": 0.18215854465961456,
|
|
"num_tokens": 50326127.0,
|
|
"step": 22975
|
|
},
|
|
{
|
|
"entropy": 5.533067321777343,
|
|
"epoch": 2.280666931321953,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004482118030368469,
|
|
"loss": 4.9872,
|
|
"mean_token_accuracy": 0.18493663221597673,
|
|
"num_tokens": 50337044.0,
|
|
"step": 22980
|
|
},
|
|
{
|
|
"entropy": 5.619342613220215,
|
|
"epoch": 2.2811631599841204,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.000448189186782838,
|
|
"loss": 5.1865,
|
|
"mean_token_accuracy": 0.17090394496917724,
|
|
"num_tokens": 50347796.0,
|
|
"step": 22985
|
|
},
|
|
{
|
|
"entropy": 5.5643086433410645,
|
|
"epoch": 2.2816593886462884,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00044816656623411044,
|
|
"loss": 5.0543,
|
|
"mean_token_accuracy": 0.17792009562253952,
|
|
"num_tokens": 50358454.0,
|
|
"step": 22990
|
|
},
|
|
{
|
|
"entropy": 5.565145683288574,
|
|
"epoch": 2.282155617308456,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004481439413912252,
|
|
"loss": 4.9573,
|
|
"mean_token_accuracy": 0.1811808779835701,
|
|
"num_tokens": 50369415.0,
|
|
"step": 22995
|
|
},
|
|
{
|
|
"entropy": 5.566468095779419,
|
|
"epoch": 2.2826518459706233,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00044812131225474333,
|
|
"loss": 5.0594,
|
|
"mean_token_accuracy": 0.17492768466472625,
|
|
"num_tokens": 50379977.0,
|
|
"step": 23000
|
|
},
|
|
{
|
|
"entropy": 5.638420152664184,
|
|
"epoch": 2.283148074632791,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004480986788252259,
|
|
"loss": 5.0548,
|
|
"mean_token_accuracy": 0.18053642213344573,
|
|
"num_tokens": 50390465.0,
|
|
"step": 23005
|
|
},
|
|
{
|
|
"entropy": 5.644487953186035,
|
|
"epoch": 2.2836443032949583,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004480760411032343,
|
|
"loss": 5.0818,
|
|
"mean_token_accuracy": 0.1787111684679985,
|
|
"num_tokens": 50402230.0,
|
|
"step": 23010
|
|
},
|
|
{
|
|
"entropy": 5.537339544296264,
|
|
"epoch": 2.2841405319571257,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004480533990893298,
|
|
"loss": 4.9694,
|
|
"mean_token_accuracy": 0.18669238835573196,
|
|
"num_tokens": 50413819.0,
|
|
"step": 23015
|
|
},
|
|
{
|
|
"entropy": 5.743681001663208,
|
|
"epoch": 2.284636760619293,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004480307527840739,
|
|
"loss": 5.2497,
|
|
"mean_token_accuracy": 0.1648907855153084,
|
|
"num_tokens": 50424977.0,
|
|
"step": 23020
|
|
},
|
|
{
|
|
"entropy": 5.656344699859619,
|
|
"epoch": 2.285132989281461,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004480081021880282,
|
|
"loss": 5.0544,
|
|
"mean_token_accuracy": 0.17721066027879714,
|
|
"num_tokens": 50438357.0,
|
|
"step": 23025
|
|
},
|
|
{
|
|
"entropy": 5.6191794872283936,
|
|
"epoch": 2.2856292179436286,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004479854473017543,
|
|
"loss": 5.0492,
|
|
"mean_token_accuracy": 0.1796061411499977,
|
|
"num_tokens": 50449081.0,
|
|
"step": 23030
|
|
},
|
|
{
|
|
"entropy": 5.515747547149658,
|
|
"epoch": 2.286125446605796,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00044796278812581417,
|
|
"loss": 4.9475,
|
|
"mean_token_accuracy": 0.18713658303022385,
|
|
"num_tokens": 50460358.0,
|
|
"step": 23035
|
|
},
|
|
{
|
|
"entropy": 5.592691373825073,
|
|
"epoch": 2.2866216752679636,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004479401246607695,
|
|
"loss": 5.0327,
|
|
"mean_token_accuracy": 0.1791094422340393,
|
|
"num_tokens": 50470955.0,
|
|
"step": 23040
|
|
},
|
|
{
|
|
"entropy": 5.631878757476807,
|
|
"epoch": 2.287117903930131,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004479174569071823,
|
|
"loss": 5.0057,
|
|
"mean_token_accuracy": 0.1853179767727852,
|
|
"num_tokens": 50482250.0,
|
|
"step": 23045
|
|
},
|
|
{
|
|
"entropy": 5.584647178649902,
|
|
"epoch": 2.2876141325922985,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004478947848656149,
|
|
"loss": 5.0378,
|
|
"mean_token_accuracy": 0.18050197064876555,
|
|
"num_tokens": 50493868.0,
|
|
"step": 23050
|
|
},
|
|
{
|
|
"entropy": 5.5868284702301025,
|
|
"epoch": 2.288110361254466,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00044787210853662943,
|
|
"loss": 5.0855,
|
|
"mean_token_accuracy": 0.18069671839475632,
|
|
"num_tokens": 50504012.0,
|
|
"step": 23055
|
|
},
|
|
{
|
|
"entropy": 5.620962047576905,
|
|
"epoch": 2.2886065899166335,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004478494279207881,
|
|
"loss": 5.0049,
|
|
"mean_token_accuracy": 0.18260658979415895,
|
|
"num_tokens": 50515503.0,
|
|
"step": 23060
|
|
},
|
|
{
|
|
"entropy": 5.589963817596436,
|
|
"epoch": 2.289102818578801,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00044782674301865346,
|
|
"loss": 5.0503,
|
|
"mean_token_accuracy": 0.1753444865345955,
|
|
"num_tokens": 50526180.0,
|
|
"step": 23065
|
|
},
|
|
{
|
|
"entropy": 5.607716512680054,
|
|
"epoch": 2.2895990472409684,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004478040538307879,
|
|
"loss": 5.0687,
|
|
"mean_token_accuracy": 0.17163751274347305,
|
|
"num_tokens": 50536711.0,
|
|
"step": 23070
|
|
},
|
|
{
|
|
"entropy": 5.6650806903839115,
|
|
"epoch": 2.2900952759031363,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004477813603577543,
|
|
"loss": 5.1253,
|
|
"mean_token_accuracy": 0.1744353875517845,
|
|
"num_tokens": 50547736.0,
|
|
"step": 23075
|
|
},
|
|
{
|
|
"entropy": 5.620262527465821,
|
|
"epoch": 2.290591504565304,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00044775866260011516,
|
|
"loss": 5.0212,
|
|
"mean_token_accuracy": 0.18726903200149536,
|
|
"num_tokens": 50558173.0,
|
|
"step": 23080
|
|
},
|
|
{
|
|
"entropy": 5.599652814865112,
|
|
"epoch": 2.2910877332274713,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004477359605584335,
|
|
"loss": 5.0489,
|
|
"mean_token_accuracy": 0.18064558058977126,
|
|
"num_tokens": 50568421.0,
|
|
"step": 23085
|
|
},
|
|
{
|
|
"entropy": 5.595942878723145,
|
|
"epoch": 2.2915839618896388,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00044771325423327227,
|
|
"loss": 5.0119,
|
|
"mean_token_accuracy": 0.18216795921325685,
|
|
"num_tokens": 50579182.0,
|
|
"step": 23090
|
|
},
|
|
{
|
|
"entropy": 5.6086602210998535,
|
|
"epoch": 2.2920801905518062,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004476905436251945,
|
|
"loss": 5.0363,
|
|
"mean_token_accuracy": 0.1848099038004875,
|
|
"num_tokens": 50590916.0,
|
|
"step": 23095
|
|
},
|
|
{
|
|
"entropy": 5.505478191375732,
|
|
"epoch": 2.2925764192139737,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00044766782873476333,
|
|
"loss": 4.92,
|
|
"mean_token_accuracy": 0.19027017056941986,
|
|
"num_tokens": 50600682.0,
|
|
"step": 23100
|
|
},
|
|
{
|
|
"entropy": 5.664739608764648,
|
|
"epoch": 2.293072647876141,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.000447645109562542,
|
|
"loss": 5.1874,
|
|
"mean_token_accuracy": 0.16733266711235045,
|
|
"num_tokens": 50612103.0,
|
|
"step": 23105
|
|
},
|
|
{
|
|
"entropy": 5.674100589752197,
|
|
"epoch": 2.293568876538309,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00044762238610909414,
|
|
"loss": 5.1153,
|
|
"mean_token_accuracy": 0.17316448390483857,
|
|
"num_tokens": 50623894.0,
|
|
"step": 23110
|
|
},
|
|
{
|
|
"entropy": 5.6742846965789795,
|
|
"epoch": 2.2940651052004766,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004475996583749829,
|
|
"loss": 5.0839,
|
|
"mean_token_accuracy": 0.17228189408779143,
|
|
"num_tokens": 50634495.0,
|
|
"step": 23115
|
|
},
|
|
{
|
|
"entropy": 5.66628680229187,
|
|
"epoch": 2.294561333862644,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00044757692636077215,
|
|
"loss": 5.215,
|
|
"mean_token_accuracy": 0.17369554191827774,
|
|
"num_tokens": 50645921.0,
|
|
"step": 23120
|
|
},
|
|
{
|
|
"entropy": 5.66722297668457,
|
|
"epoch": 2.2950575625248115,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00044755419006702545,
|
|
"loss": 5.0582,
|
|
"mean_token_accuracy": 0.17647605389356613,
|
|
"num_tokens": 50657047.0,
|
|
"step": 23125
|
|
},
|
|
{
|
|
"entropy": 5.639464855194092,
|
|
"epoch": 2.295553791186979,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00044753144949430667,
|
|
"loss": 5.0339,
|
|
"mean_token_accuracy": 0.17725845724344252,
|
|
"num_tokens": 50668271.0,
|
|
"step": 23130
|
|
},
|
|
{
|
|
"entropy": 5.5653282642364506,
|
|
"epoch": 2.2960500198491465,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004475087046431798,
|
|
"loss": 4.9852,
|
|
"mean_token_accuracy": 0.1874163419008255,
|
|
"num_tokens": 50678870.0,
|
|
"step": 23135
|
|
},
|
|
{
|
|
"entropy": 5.573322582244873,
|
|
"epoch": 2.296546248511314,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004474859555142087,
|
|
"loss": 5.0394,
|
|
"mean_token_accuracy": 0.18124370872974396,
|
|
"num_tokens": 50690322.0,
|
|
"step": 23140
|
|
},
|
|
{
|
|
"entropy": 5.5733558177948,
|
|
"epoch": 2.2970424771734814,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00044746320210795753,
|
|
"loss": 4.9793,
|
|
"mean_token_accuracy": 0.1834281638264656,
|
|
"num_tokens": 50701958.0,
|
|
"step": 23145
|
|
},
|
|
{
|
|
"entropy": 5.583808469772339,
|
|
"epoch": 2.297538705835649,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004474404444249906,
|
|
"loss": 5.0474,
|
|
"mean_token_accuracy": 0.18413593173027037,
|
|
"num_tokens": 50712962.0,
|
|
"step": 23150
|
|
},
|
|
{
|
|
"entropy": 5.574769163131714,
|
|
"epoch": 2.2980349344978164,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00044741768246587226,
|
|
"loss": 5.079,
|
|
"mean_token_accuracy": 0.18358581215143205,
|
|
"num_tokens": 50723442.0,
|
|
"step": 23155
|
|
},
|
|
{
|
|
"entropy": 5.599833822250366,
|
|
"epoch": 2.2985311631599843,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004473949162311669,
|
|
"loss": 4.957,
|
|
"mean_token_accuracy": 0.181428362429142,
|
|
"num_tokens": 50733188.0,
|
|
"step": 23160
|
|
},
|
|
{
|
|
"entropy": 5.619607734680176,
|
|
"epoch": 2.2990273918221518,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004473721457214391,
|
|
"loss": 5.0967,
|
|
"mean_token_accuracy": 0.1729112982749939,
|
|
"num_tokens": 50744023.0,
|
|
"step": 23165
|
|
},
|
|
{
|
|
"entropy": 5.695945358276367,
|
|
"epoch": 2.2995236204843192,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004473493709372535,
|
|
"loss": 5.2631,
|
|
"mean_token_accuracy": 0.17567385882139205,
|
|
"num_tokens": 50756807.0,
|
|
"step": 23170
|
|
},
|
|
{
|
|
"entropy": 5.663753366470337,
|
|
"epoch": 2.3000198491464867,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004473265918791749,
|
|
"loss": 5.1487,
|
|
"mean_token_accuracy": 0.17493315190076827,
|
|
"num_tokens": 50768981.0,
|
|
"step": 23175
|
|
},
|
|
{
|
|
"entropy": 5.654820537567138,
|
|
"epoch": 2.300516077808654,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004473038085477682,
|
|
"loss": 5.0518,
|
|
"mean_token_accuracy": 0.1841997131705284,
|
|
"num_tokens": 50780111.0,
|
|
"step": 23180
|
|
},
|
|
{
|
|
"entropy": 5.6414525508880615,
|
|
"epoch": 2.3010123064708217,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00044728102094359826,
|
|
"loss": 5.0876,
|
|
"mean_token_accuracy": 0.1773157000541687,
|
|
"num_tokens": 50790318.0,
|
|
"step": 23185
|
|
},
|
|
{
|
|
"entropy": 5.627245235443115,
|
|
"epoch": 2.301508535132989,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004472582290672303,
|
|
"loss": 5.1141,
|
|
"mean_token_accuracy": 0.1752907156944275,
|
|
"num_tokens": 50800734.0,
|
|
"step": 23190
|
|
},
|
|
{
|
|
"entropy": 5.528088760375977,
|
|
"epoch": 2.3020047637951566,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00044723543291922936,
|
|
"loss": 5.0149,
|
|
"mean_token_accuracy": 0.18594680428504945,
|
|
"num_tokens": 50811236.0,
|
|
"step": 23195
|
|
},
|
|
{
|
|
"entropy": 5.569911146163941,
|
|
"epoch": 2.3025009924573245,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00044721263250016086,
|
|
"loss": 5.0118,
|
|
"mean_token_accuracy": 0.18104765713214874,
|
|
"num_tokens": 50821776.0,
|
|
"step": 23200
|
|
},
|
|
{
|
|
"entropy": 5.65333776473999,
|
|
"epoch": 2.302997221119492,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00044718982781059017,
|
|
"loss": 5.1511,
|
|
"mean_token_accuracy": 0.17451186925172807,
|
|
"num_tokens": 50834156.0,
|
|
"step": 23205
|
|
},
|
|
{
|
|
"entropy": 5.58366847038269,
|
|
"epoch": 2.3034934497816595,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00044716701885108275,
|
|
"loss": 5.0241,
|
|
"mean_token_accuracy": 0.1829358920454979,
|
|
"num_tokens": 50845086.0,
|
|
"step": 23210
|
|
},
|
|
{
|
|
"entropy": 5.618365049362183,
|
|
"epoch": 2.303989678443827,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00044714420562220423,
|
|
"loss": 5.0307,
|
|
"mean_token_accuracy": 0.18179574459791184,
|
|
"num_tokens": 50858637.0,
|
|
"step": 23215
|
|
},
|
|
{
|
|
"entropy": 5.644404697418213,
|
|
"epoch": 2.3044859071059944,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004471213881245204,
|
|
"loss": 5.1558,
|
|
"mean_token_accuracy": 0.1749633491039276,
|
|
"num_tokens": 50871159.0,
|
|
"step": 23220
|
|
},
|
|
{
|
|
"entropy": 5.5893453598022464,
|
|
"epoch": 2.304982135768162,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.000447098566358597,
|
|
"loss": 5.0408,
|
|
"mean_token_accuracy": 0.17604662775993346,
|
|
"num_tokens": 50884072.0,
|
|
"step": 23225
|
|
},
|
|
{
|
|
"entropy": 5.557044172286988,
|
|
"epoch": 2.3054783644303294,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.00044707574032500005,
|
|
"loss": 5.0443,
|
|
"mean_token_accuracy": 0.18032577335834504,
|
|
"num_tokens": 50896627.0,
|
|
"step": 23230
|
|
},
|
|
{
|
|
"entropy": 5.555281066894532,
|
|
"epoch": 2.305974593092497,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004470529100242955,
|
|
"loss": 4.9643,
|
|
"mean_token_accuracy": 0.1855953097343445,
|
|
"num_tokens": 50907476.0,
|
|
"step": 23235
|
|
},
|
|
{
|
|
"entropy": 5.589204359054565,
|
|
"epoch": 2.3064708217546643,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004470300754570495,
|
|
"loss": 5.0463,
|
|
"mean_token_accuracy": 0.17860807180404664,
|
|
"num_tokens": 50918104.0,
|
|
"step": 23240
|
|
},
|
|
{
|
|
"entropy": 5.560319232940674,
|
|
"epoch": 2.3069670504168323,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004470072366238284,
|
|
"loss": 5.0121,
|
|
"mean_token_accuracy": 0.17882056087255477,
|
|
"num_tokens": 50930575.0,
|
|
"step": 23245
|
|
},
|
|
{
|
|
"entropy": 5.568819761276245,
|
|
"epoch": 2.3074632790789997,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00044698439352519836,
|
|
"loss": 4.97,
|
|
"mean_token_accuracy": 0.18190665692090988,
|
|
"num_tokens": 50940592.0,
|
|
"step": 23250
|
|
},
|
|
{
|
|
"entropy": 5.57731990814209,
|
|
"epoch": 2.307959507741167,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00044696154616172604,
|
|
"loss": 5.0411,
|
|
"mean_token_accuracy": 0.17612005770206451,
|
|
"num_tokens": 50952134.0,
|
|
"step": 23255
|
|
},
|
|
{
|
|
"entropy": 5.5701545715332035,
|
|
"epoch": 2.3084557364033347,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004469386945339779,
|
|
"loss": 5.0846,
|
|
"mean_token_accuracy": 0.1784474566578865,
|
|
"num_tokens": 50962721.0,
|
|
"step": 23260
|
|
},
|
|
{
|
|
"entropy": 5.57421989440918,
|
|
"epoch": 2.308951965065502,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004469158386425206,
|
|
"loss": 5.0229,
|
|
"mean_token_accuracy": 0.18003182262182235,
|
|
"num_tokens": 50974893.0,
|
|
"step": 23265
|
|
},
|
|
{
|
|
"entropy": 5.594786310195923,
|
|
"epoch": 2.3094481937276696,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.000446892978487921,
|
|
"loss": 4.9969,
|
|
"mean_token_accuracy": 0.1797194093465805,
|
|
"num_tokens": 50986225.0,
|
|
"step": 23270
|
|
},
|
|
{
|
|
"entropy": 5.5979804515838625,
|
|
"epoch": 2.309944422389837,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00044687011407074583,
|
|
"loss": 5.1009,
|
|
"mean_token_accuracy": 0.1689686268568039,
|
|
"num_tokens": 50997924.0,
|
|
"step": 23275
|
|
},
|
|
{
|
|
"entropy": 5.584272670745849,
|
|
"epoch": 2.3104406510520046,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004468472453915623,
|
|
"loss": 4.9806,
|
|
"mean_token_accuracy": 0.18198306262493133,
|
|
"num_tokens": 51008179.0,
|
|
"step": 23280
|
|
},
|
|
{
|
|
"entropy": 5.544312620162964,
|
|
"epoch": 2.3109368797141725,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004468243724509373,
|
|
"loss": 4.9953,
|
|
"mean_token_accuracy": 0.18630722910165787,
|
|
"num_tokens": 51018462.0,
|
|
"step": 23285
|
|
},
|
|
{
|
|
"entropy": 5.618963098526001,
|
|
"epoch": 2.31143310837634,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004468014952494382,
|
|
"loss": 5.0724,
|
|
"mean_token_accuracy": 0.17896728962659836,
|
|
"num_tokens": 51029769.0,
|
|
"step": 23290
|
|
},
|
|
{
|
|
"entropy": 5.616843557357788,
|
|
"epoch": 2.3119293370385074,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00044677861378763205,
|
|
"loss": 5.0759,
|
|
"mean_token_accuracy": 0.1816832974553108,
|
|
"num_tokens": 51041058.0,
|
|
"step": 23295
|
|
},
|
|
{
|
|
"entropy": 5.587506484985352,
|
|
"epoch": 2.312425565700675,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00044675572806608655,
|
|
"loss": 5.0129,
|
|
"mean_token_accuracy": 0.18079742789268494,
|
|
"num_tokens": 51050958.0,
|
|
"step": 23300
|
|
},
|
|
{
|
|
"entropy": 5.618343257904053,
|
|
"epoch": 2.3129217943628424,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00044673283808536915,
|
|
"loss": 5.0231,
|
|
"mean_token_accuracy": 0.18827854543924333,
|
|
"num_tokens": 51062459.0,
|
|
"step": 23305
|
|
},
|
|
{
|
|
"entropy": 5.688998031616211,
|
|
"epoch": 2.31341802302501,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004467099438460474,
|
|
"loss": 5.211,
|
|
"mean_token_accuracy": 0.1744321808218956,
|
|
"num_tokens": 51074596.0,
|
|
"step": 23310
|
|
},
|
|
{
|
|
"entropy": 5.66031699180603,
|
|
"epoch": 2.3139142516871773,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00044668704534868886,
|
|
"loss": 5.0712,
|
|
"mean_token_accuracy": 0.17126382291316986,
|
|
"num_tokens": 51085265.0,
|
|
"step": 23315
|
|
},
|
|
{
|
|
"entropy": 5.60770001411438,
|
|
"epoch": 2.314410480349345,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00044666414259386173,
|
|
"loss": 5.0168,
|
|
"mean_token_accuracy": 0.17705831974744796,
|
|
"num_tokens": 51095986.0,
|
|
"step": 23320
|
|
},
|
|
{
|
|
"entropy": 5.623257780075074,
|
|
"epoch": 2.3149067090115123,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00044664123558213367,
|
|
"loss": 5.016,
|
|
"mean_token_accuracy": 0.17910957038402558,
|
|
"num_tokens": 51107518.0,
|
|
"step": 23325
|
|
},
|
|
{
|
|
"entropy": 5.569105386734009,
|
|
"epoch": 2.31540293767368,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004466183243140729,
|
|
"loss": 4.9738,
|
|
"mean_token_accuracy": 0.18646175414323807,
|
|
"num_tokens": 51119715.0,
|
|
"step": 23330
|
|
},
|
|
{
|
|
"entropy": 5.548243427276612,
|
|
"epoch": 2.3158991663358477,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00044659540879024746,
|
|
"loss": 4.9943,
|
|
"mean_token_accuracy": 0.18227538615465164,
|
|
"num_tokens": 51130801.0,
|
|
"step": 23335
|
|
},
|
|
{
|
|
"entropy": 5.555860805511474,
|
|
"epoch": 2.316395394998015,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004465724890112256,
|
|
"loss": 5.042,
|
|
"mean_token_accuracy": 0.17628263980150222,
|
|
"num_tokens": 51142509.0,
|
|
"step": 23340
|
|
},
|
|
{
|
|
"entropy": 5.6402171611785885,
|
|
"epoch": 2.3168916236601826,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00044654956497757576,
|
|
"loss": 5.0763,
|
|
"mean_token_accuracy": 0.17936841696500777,
|
|
"num_tokens": 51154839.0,
|
|
"step": 23345
|
|
},
|
|
{
|
|
"entropy": 5.57779016494751,
|
|
"epoch": 2.31738785232235,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00044652663668986634,
|
|
"loss": 5.0225,
|
|
"mean_token_accuracy": 0.18539883345365524,
|
|
"num_tokens": 51165293.0,
|
|
"step": 23350
|
|
},
|
|
{
|
|
"entropy": 5.556305551528931,
|
|
"epoch": 2.3178840809845176,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.000446503704148666,
|
|
"loss": 5.0857,
|
|
"mean_token_accuracy": 0.1782493069767952,
|
|
"num_tokens": 51176371.0,
|
|
"step": 23355
|
|
},
|
|
{
|
|
"entropy": 5.564503955841064,
|
|
"epoch": 2.318380309646685,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004464807673545433,
|
|
"loss": 5.0106,
|
|
"mean_token_accuracy": 0.18717833757400512,
|
|
"num_tokens": 51187240.0,
|
|
"step": 23360
|
|
},
|
|
{
|
|
"entropy": 5.670996856689453,
|
|
"epoch": 2.3188765383088525,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004464578263080671,
|
|
"loss": 5.0991,
|
|
"mean_token_accuracy": 0.17741835564374925,
|
|
"num_tokens": 51199084.0,
|
|
"step": 23365
|
|
},
|
|
{
|
|
"entropy": 5.589241361618042,
|
|
"epoch": 2.3193727669710205,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00044643488100980623,
|
|
"loss": 4.9714,
|
|
"mean_token_accuracy": 0.1834746092557907,
|
|
"num_tokens": 51209885.0,
|
|
"step": 23370
|
|
},
|
|
{
|
|
"entropy": 5.594709682464599,
|
|
"epoch": 2.319868995633188,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004464119314603298,
|
|
"loss": 5.0283,
|
|
"mean_token_accuracy": 0.18390836268663407,
|
|
"num_tokens": 51220644.0,
|
|
"step": 23375
|
|
},
|
|
{
|
|
"entropy": 5.58029088973999,
|
|
"epoch": 2.3203652242953554,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00044638897766020673,
|
|
"loss": 5.0103,
|
|
"mean_token_accuracy": 0.1815899059176445,
|
|
"num_tokens": 51231342.0,
|
|
"step": 23380
|
|
},
|
|
{
|
|
"entropy": 5.5645177364349365,
|
|
"epoch": 2.320861452957523,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004463660196100064,
|
|
"loss": 4.9299,
|
|
"mean_token_accuracy": 0.1838017001748085,
|
|
"num_tokens": 51241368.0,
|
|
"step": 23385
|
|
},
|
|
{
|
|
"entropy": 5.547626113891601,
|
|
"epoch": 2.3213576816196904,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00044634305731029803,
|
|
"loss": 5.1229,
|
|
"mean_token_accuracy": 0.1810004472732544,
|
|
"num_tokens": 51252784.0,
|
|
"step": 23390
|
|
},
|
|
{
|
|
"entropy": 5.5737354278564455,
|
|
"epoch": 2.321853910281858,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00044632009076165096,
|
|
"loss": 5.0087,
|
|
"mean_token_accuracy": 0.1803363710641861,
|
|
"num_tokens": 51264246.0,
|
|
"step": 23395
|
|
},
|
|
{
|
|
"entropy": 5.581436586380005,
|
|
"epoch": 2.3223501389440253,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000446297119964635,
|
|
"loss": 4.9831,
|
|
"mean_token_accuracy": 0.18832659125328063,
|
|
"num_tokens": 51274575.0,
|
|
"step": 23400
|
|
},
|
|
{
|
|
"entropy": 5.611540079116821,
|
|
"epoch": 2.322846367606193,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004462741449198194,
|
|
"loss": 4.9903,
|
|
"mean_token_accuracy": 0.18128154873847963,
|
|
"num_tokens": 51285384.0,
|
|
"step": 23405
|
|
},
|
|
{
|
|
"entropy": 5.653060007095337,
|
|
"epoch": 2.3233425962683603,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00044625116562777413,
|
|
"loss": 5.08,
|
|
"mean_token_accuracy": 0.18511968553066255,
|
|
"num_tokens": 51297983.0,
|
|
"step": 23410
|
|
},
|
|
{
|
|
"entropy": 5.511483383178711,
|
|
"epoch": 2.323838824930528,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004462281820890689,
|
|
"loss": 4.9822,
|
|
"mean_token_accuracy": 0.18765173256397247,
|
|
"num_tokens": 51308795.0,
|
|
"step": 23415
|
|
},
|
|
{
|
|
"entropy": 5.547490835189819,
|
|
"epoch": 2.3243350535926957,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00044620519430427376,
|
|
"loss": 5.0025,
|
|
"mean_token_accuracy": 0.18458894938230513,
|
|
"num_tokens": 51318597.0,
|
|
"step": 23420
|
|
},
|
|
{
|
|
"entropy": 5.550917911529541,
|
|
"epoch": 2.324831282254863,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004461822022739588,
|
|
"loss": 4.9494,
|
|
"mean_token_accuracy": 0.18288534581661225,
|
|
"num_tokens": 51329238.0,
|
|
"step": 23425
|
|
},
|
|
{
|
|
"entropy": 5.615041065216064,
|
|
"epoch": 2.3253275109170306,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000446159205998694,
|
|
"loss": 5.0423,
|
|
"mean_token_accuracy": 0.18075837790966034,
|
|
"num_tokens": 51340295.0,
|
|
"step": 23430
|
|
},
|
|
{
|
|
"entropy": 5.564624977111817,
|
|
"epoch": 2.325823739579198,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004461362054790497,
|
|
"loss": 5.015,
|
|
"mean_token_accuracy": 0.1820700079202652,
|
|
"num_tokens": 51350702.0,
|
|
"step": 23435
|
|
},
|
|
{
|
|
"entropy": 5.612828254699707,
|
|
"epoch": 2.3263199682413656,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00044611320071559637,
|
|
"loss": 5.0318,
|
|
"mean_token_accuracy": 0.18055972903966905,
|
|
"num_tokens": 51359794.0,
|
|
"step": 23440
|
|
},
|
|
{
|
|
"entropy": 5.606128787994384,
|
|
"epoch": 2.326816196903533,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00044609019170890424,
|
|
"loss": 5.0004,
|
|
"mean_token_accuracy": 0.18530600368976594,
|
|
"num_tokens": 51368932.0,
|
|
"step": 23445
|
|
},
|
|
{
|
|
"entropy": 5.617540693283081,
|
|
"epoch": 2.3273124255657005,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00044606717845954415,
|
|
"loss": 5.0662,
|
|
"mean_token_accuracy": 0.18132403939962388,
|
|
"num_tokens": 51381111.0,
|
|
"step": 23450
|
|
},
|
|
{
|
|
"entropy": 5.534998655319214,
|
|
"epoch": 2.3278086542278684,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00044604416096808656,
|
|
"loss": 4.9757,
|
|
"mean_token_accuracy": 0.19520024508237838,
|
|
"num_tokens": 51392976.0,
|
|
"step": 23455
|
|
},
|
|
{
|
|
"entropy": 5.614948272705078,
|
|
"epoch": 2.328304882890036,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00044602113923510235,
|
|
"loss": 5.0058,
|
|
"mean_token_accuracy": 0.17893098592758178,
|
|
"num_tokens": 51403586.0,
|
|
"step": 23460
|
|
},
|
|
{
|
|
"entropy": 5.6019322872161865,
|
|
"epoch": 2.3288011115522034,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00044599811326116246,
|
|
"loss": 5.0636,
|
|
"mean_token_accuracy": 0.17843217104673387,
|
|
"num_tokens": 51414035.0,
|
|
"step": 23465
|
|
},
|
|
{
|
|
"entropy": 5.590606069564819,
|
|
"epoch": 2.329297340214371,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00044597508304683784,
|
|
"loss": 5.0662,
|
|
"mean_token_accuracy": 0.17720458209514617,
|
|
"num_tokens": 51424111.0,
|
|
"step": 23470
|
|
},
|
|
{
|
|
"entropy": 5.5653258800506595,
|
|
"epoch": 2.3297935688765383,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004459520485926995,
|
|
"loss": 4.9697,
|
|
"mean_token_accuracy": 0.1882004588842392,
|
|
"num_tokens": 51434566.0,
|
|
"step": 23475
|
|
},
|
|
{
|
|
"entropy": 5.644761228561402,
|
|
"epoch": 2.330289797538706,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004459290098993188,
|
|
"loss": 5.0334,
|
|
"mean_token_accuracy": 0.18696822673082353,
|
|
"num_tokens": 51445568.0,
|
|
"step": 23480
|
|
},
|
|
{
|
|
"entropy": 5.636776876449585,
|
|
"epoch": 2.3307860262008733,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00044590596696726686,
|
|
"loss": 5.0246,
|
|
"mean_token_accuracy": 0.18721263408660888,
|
|
"num_tokens": 51456482.0,
|
|
"step": 23485
|
|
},
|
|
{
|
|
"entropy": 5.620083570480347,
|
|
"epoch": 2.3312822548630407,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004458829197971153,
|
|
"loss": 5.1081,
|
|
"mean_token_accuracy": 0.17495281994342804,
|
|
"num_tokens": 51467809.0,
|
|
"step": 23490
|
|
},
|
|
{
|
|
"entropy": 5.63603720664978,
|
|
"epoch": 2.3317784835252082,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00044585986838943556,
|
|
"loss": 5.0175,
|
|
"mean_token_accuracy": 0.17824462950229644,
|
|
"num_tokens": 51477927.0,
|
|
"step": 23495
|
|
},
|
|
{
|
|
"entropy": 5.593960237503052,
|
|
"epoch": 2.3322747121873757,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00044583681274479927,
|
|
"loss": 5.071,
|
|
"mean_token_accuracy": 0.18142592459917067,
|
|
"num_tokens": 51488432.0,
|
|
"step": 23500
|
|
},
|
|
{
|
|
"entropy": 5.617846202850342,
|
|
"epoch": 2.3327709408495436,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004458137528637781,
|
|
"loss": 5.0394,
|
|
"mean_token_accuracy": 0.18071080446243287,
|
|
"num_tokens": 51499149.0,
|
|
"step": 23505
|
|
},
|
|
{
|
|
"entropy": 5.666125011444092,
|
|
"epoch": 2.333267169511711,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00044579068874694386,
|
|
"loss": 5.071,
|
|
"mean_token_accuracy": 0.17561647146940232,
|
|
"num_tokens": 51510672.0,
|
|
"step": 23510
|
|
},
|
|
{
|
|
"entropy": 5.641594696044922,
|
|
"epoch": 2.3337633981738786,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004457676203948687,
|
|
"loss": 5.0617,
|
|
"mean_token_accuracy": 0.17588749378919602,
|
|
"num_tokens": 51521855.0,
|
|
"step": 23515
|
|
},
|
|
{
|
|
"entropy": 5.645274972915649,
|
|
"epoch": 2.334259626836046,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004457445478081244,
|
|
"loss": 5.0383,
|
|
"mean_token_accuracy": 0.18006182760000228,
|
|
"num_tokens": 51531970.0,
|
|
"step": 23520
|
|
},
|
|
{
|
|
"entropy": 5.60600733757019,
|
|
"epoch": 2.3347558554982135,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00044572147098728335,
|
|
"loss": 5.1153,
|
|
"mean_token_accuracy": 0.17813000679016114,
|
|
"num_tokens": 51543110.0,
|
|
"step": 23525
|
|
},
|
|
{
|
|
"entropy": 5.5759031772613525,
|
|
"epoch": 2.335252084160381,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00044569838993291757,
|
|
"loss": 5.0453,
|
|
"mean_token_accuracy": 0.17850546538829803,
|
|
"num_tokens": 51552991.0,
|
|
"step": 23530
|
|
},
|
|
{
|
|
"entropy": 5.639141035079956,
|
|
"epoch": 2.3357483128225485,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00044567530464559963,
|
|
"loss": 5.0638,
|
|
"mean_token_accuracy": 0.18162497878074646,
|
|
"num_tokens": 51564472.0,
|
|
"step": 23535
|
|
},
|
|
{
|
|
"entropy": 5.589152526855469,
|
|
"epoch": 2.3362445414847164,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004456522151259019,
|
|
"loss": 5.0814,
|
|
"mean_token_accuracy": 0.18080969154834747,
|
|
"num_tokens": 51576051.0,
|
|
"step": 23540
|
|
},
|
|
{
|
|
"entropy": 5.670563268661499,
|
|
"epoch": 2.336740770146884,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.000445629121374397,
|
|
"loss": 5.0722,
|
|
"mean_token_accuracy": 0.17418465614318848,
|
|
"num_tokens": 51586658.0,
|
|
"step": 23545
|
|
},
|
|
{
|
|
"entropy": 5.614601182937622,
|
|
"epoch": 2.3372369988090513,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00044560602339165746,
|
|
"loss": 5.0389,
|
|
"mean_token_accuracy": 0.1779758632183075,
|
|
"num_tokens": 51596614.0,
|
|
"step": 23550
|
|
},
|
|
{
|
|
"entropy": 5.590232896804809,
|
|
"epoch": 2.337733227471219,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004455829211782562,
|
|
"loss": 5.0717,
|
|
"mean_token_accuracy": 0.17915811985731125,
|
|
"num_tokens": 51607102.0,
|
|
"step": 23555
|
|
},
|
|
{
|
|
"entropy": 5.675381803512574,
|
|
"epoch": 2.3382294561333863,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004455598147347661,
|
|
"loss": 5.1025,
|
|
"mean_token_accuracy": 0.1766846612095833,
|
|
"num_tokens": 51619079.0,
|
|
"step": 23560
|
|
},
|
|
{
|
|
"entropy": 5.6101583480834964,
|
|
"epoch": 2.3387256847955538,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004455367040617601,
|
|
"loss": 4.9859,
|
|
"mean_token_accuracy": 0.18753135502338408,
|
|
"num_tokens": 51630273.0,
|
|
"step": 23565
|
|
},
|
|
{
|
|
"entropy": 5.56528606414795,
|
|
"epoch": 2.3392219134577212,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00044551358915981135,
|
|
"loss": 5.0409,
|
|
"mean_token_accuracy": 0.1820089712738991,
|
|
"num_tokens": 51640480.0,
|
|
"step": 23570
|
|
},
|
|
{
|
|
"entropy": 5.593130826950073,
|
|
"epoch": 2.3397181421198887,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004454904700294929,
|
|
"loss": 5.0766,
|
|
"mean_token_accuracy": 0.1786801502108574,
|
|
"num_tokens": 51651831.0,
|
|
"step": 23575
|
|
},
|
|
{
|
|
"entropy": 5.60858006477356,
|
|
"epoch": 2.340214370782056,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004454673466713783,
|
|
"loss": 5.0751,
|
|
"mean_token_accuracy": 0.17778751105070115,
|
|
"num_tokens": 51664061.0,
|
|
"step": 23580
|
|
},
|
|
{
|
|
"entropy": 5.590447902679443,
|
|
"epoch": 2.3407105994442237,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00044544421908604073,
|
|
"loss": 5.026,
|
|
"mean_token_accuracy": 0.1818692833185196,
|
|
"num_tokens": 51675081.0,
|
|
"step": 23585
|
|
},
|
|
{
|
|
"entropy": 5.575238418579102,
|
|
"epoch": 2.3412068281063916,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00044542108727405386,
|
|
"loss": 4.9373,
|
|
"mean_token_accuracy": 0.1871587172150612,
|
|
"num_tokens": 51684477.0,
|
|
"step": 23590
|
|
},
|
|
{
|
|
"entropy": 5.702288722991943,
|
|
"epoch": 2.341703056768559,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00044539795123599117,
|
|
"loss": 5.0957,
|
|
"mean_token_accuracy": 0.18402961492538453,
|
|
"num_tokens": 51694420.0,
|
|
"step": 23595
|
|
},
|
|
{
|
|
"entropy": 5.474022626876831,
|
|
"epoch": 2.3421992854307265,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00044537481097242654,
|
|
"loss": 4.9272,
|
|
"mean_token_accuracy": 0.1897786557674408,
|
|
"num_tokens": 51704635.0,
|
|
"step": 23600
|
|
},
|
|
{
|
|
"entropy": 5.610105323791504,
|
|
"epoch": 2.342695514092894,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00044535166648393377,
|
|
"loss": 5.1388,
|
|
"mean_token_accuracy": 0.17504112869501115,
|
|
"num_tokens": 51716149.0,
|
|
"step": 23605
|
|
},
|
|
{
|
|
"entropy": 5.548909664154053,
|
|
"epoch": 2.3431917427550615,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00044532851777108663,
|
|
"loss": 4.9788,
|
|
"mean_token_accuracy": 0.18450577110052108,
|
|
"num_tokens": 51726861.0,
|
|
"step": 23610
|
|
},
|
|
{
|
|
"entropy": 5.648274898529053,
|
|
"epoch": 2.343687971417229,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004453053648344593,
|
|
"loss": 5.2094,
|
|
"mean_token_accuracy": 0.17432949244976043,
|
|
"num_tokens": 51738111.0,
|
|
"step": 23615
|
|
},
|
|
{
|
|
"entropy": 5.565129804611206,
|
|
"epoch": 2.3441842000793964,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00044528220767462595,
|
|
"loss": 5.0422,
|
|
"mean_token_accuracy": 0.18279070258140565,
|
|
"num_tokens": 51749004.0,
|
|
"step": 23620
|
|
},
|
|
{
|
|
"entropy": 5.580155849456787,
|
|
"epoch": 2.3446804287415643,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004452590462921607,
|
|
"loss": 5.022,
|
|
"mean_token_accuracy": 0.17733656764030456,
|
|
"num_tokens": 51759557.0,
|
|
"step": 23625
|
|
},
|
|
{
|
|
"entropy": 5.626314878463745,
|
|
"epoch": 2.345176657403732,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00044523588068763804,
|
|
"loss": 5.0883,
|
|
"mean_token_accuracy": 0.17816792726516723,
|
|
"num_tokens": 51769921.0,
|
|
"step": 23630
|
|
},
|
|
{
|
|
"entropy": 5.572683095932007,
|
|
"epoch": 2.3456728860658993,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004452127108616324,
|
|
"loss": 4.9548,
|
|
"mean_token_accuracy": 0.19134241491556167,
|
|
"num_tokens": 51780158.0,
|
|
"step": 23635
|
|
},
|
|
{
|
|
"entropy": 5.638480758666992,
|
|
"epoch": 2.3461691147280668,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00044518953681471824,
|
|
"loss": 5.0588,
|
|
"mean_token_accuracy": 0.17901730984449388,
|
|
"num_tokens": 51790502.0,
|
|
"step": 23640
|
|
},
|
|
{
|
|
"entropy": 5.5948234558105465,
|
|
"epoch": 2.3466653433902342,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004451663585474703,
|
|
"loss": 5.0759,
|
|
"mean_token_accuracy": 0.17232829928398133,
|
|
"num_tokens": 51801420.0,
|
|
"step": 23645
|
|
},
|
|
{
|
|
"entropy": 5.60740098953247,
|
|
"epoch": 2.3471615720524017,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00044514317606046336,
|
|
"loss": 5.0742,
|
|
"mean_token_accuracy": 0.18954353034496307,
|
|
"num_tokens": 51812399.0,
|
|
"step": 23650
|
|
},
|
|
{
|
|
"entropy": 5.660820198059082,
|
|
"epoch": 2.347657800714569,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004451199893542723,
|
|
"loss": 5.1183,
|
|
"mean_token_accuracy": 0.17228747755289078,
|
|
"num_tokens": 51824268.0,
|
|
"step": 23655
|
|
},
|
|
{
|
|
"entropy": 5.561337614059449,
|
|
"epoch": 2.3481540293767367,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004450967984294721,
|
|
"loss": 5.0448,
|
|
"mean_token_accuracy": 0.17698400169610978,
|
|
"num_tokens": 51835842.0,
|
|
"step": 23660
|
|
},
|
|
{
|
|
"entropy": 5.583753490447998,
|
|
"epoch": 2.348650258038904,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004450736032866377,
|
|
"loss": 4.9846,
|
|
"mean_token_accuracy": 0.1826761394739151,
|
|
"num_tokens": 51847501.0,
|
|
"step": 23665
|
|
},
|
|
{
|
|
"entropy": 5.595281982421875,
|
|
"epoch": 2.3491464867010716,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00044505040392634447,
|
|
"loss": 5.0305,
|
|
"mean_token_accuracy": 0.1872783422470093,
|
|
"num_tokens": 51858056.0,
|
|
"step": 23670
|
|
},
|
|
{
|
|
"entropy": 5.636955642700196,
|
|
"epoch": 2.3496427153632395,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004450272003491677,
|
|
"loss": 4.9967,
|
|
"mean_token_accuracy": 0.1887053519487381,
|
|
"num_tokens": 51869248.0,
|
|
"step": 23675
|
|
},
|
|
{
|
|
"entropy": 5.593786430358887,
|
|
"epoch": 2.350138944025407,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00044500399255568274,
|
|
"loss": 5.0904,
|
|
"mean_token_accuracy": 0.1746561273932457,
|
|
"num_tokens": 51881496.0,
|
|
"step": 23680
|
|
},
|
|
{
|
|
"entropy": 5.569082164764405,
|
|
"epoch": 2.3506351726875745,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00044498078054646507,
|
|
"loss": 5.0407,
|
|
"mean_token_accuracy": 0.17979726344347,
|
|
"num_tokens": 51891851.0,
|
|
"step": 23685
|
|
},
|
|
{
|
|
"entropy": 5.6511420726776125,
|
|
"epoch": 2.351131401349742,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00044495756432209025,
|
|
"loss": 5.1273,
|
|
"mean_token_accuracy": 0.1777437835931778,
|
|
"num_tokens": 51903581.0,
|
|
"step": 23690
|
|
},
|
|
{
|
|
"entropy": 5.58378381729126,
|
|
"epoch": 2.3516276300119094,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00044493434388313423,
|
|
"loss": 4.9651,
|
|
"mean_token_accuracy": 0.18419304937124253,
|
|
"num_tokens": 51913650.0,
|
|
"step": 23695
|
|
},
|
|
{
|
|
"entropy": 5.526974248886108,
|
|
"epoch": 2.352123858674077,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00044491111923017254,
|
|
"loss": 4.9804,
|
|
"mean_token_accuracy": 0.18517538905143738,
|
|
"num_tokens": 51924704.0,
|
|
"step": 23700
|
|
},
|
|
{
|
|
"entropy": 5.654710197448731,
|
|
"epoch": 2.3526200873362444,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00044488789036378117,
|
|
"loss": 5.1115,
|
|
"mean_token_accuracy": 0.177008980512619,
|
|
"num_tokens": 51937576.0,
|
|
"step": 23705
|
|
},
|
|
{
|
|
"entropy": 5.613334655761719,
|
|
"epoch": 2.3531163159984123,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004448646572845363,
|
|
"loss": 4.9575,
|
|
"mean_token_accuracy": 0.1870013654232025,
|
|
"num_tokens": 51947359.0,
|
|
"step": 23710
|
|
},
|
|
{
|
|
"entropy": 5.598943471908569,
|
|
"epoch": 2.35361254466058,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004448414199930139,
|
|
"loss": 5.1005,
|
|
"mean_token_accuracy": 0.1712775155901909,
|
|
"num_tokens": 51958016.0,
|
|
"step": 23715
|
|
},
|
|
{
|
|
"entropy": 5.67420072555542,
|
|
"epoch": 2.3541087733227473,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00044481817848979026,
|
|
"loss": 5.0988,
|
|
"mean_token_accuracy": 0.1787247657775879,
|
|
"num_tokens": 51968770.0,
|
|
"step": 23720
|
|
},
|
|
{
|
|
"entropy": 5.59364686012268,
|
|
"epoch": 2.3546050019849147,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004447949327754418,
|
|
"loss": 4.9672,
|
|
"mean_token_accuracy": 0.1912851944565773,
|
|
"num_tokens": 51980052.0,
|
|
"step": 23725
|
|
},
|
|
{
|
|
"entropy": 5.6142831325531,
|
|
"epoch": 2.355101230647082,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004447716828505447,
|
|
"loss": 5.1244,
|
|
"mean_token_accuracy": 0.17506493330001832,
|
|
"num_tokens": 51992080.0,
|
|
"step": 23730
|
|
},
|
|
{
|
|
"entropy": 5.582031965255737,
|
|
"epoch": 2.3555974593092497,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004447484287156758,
|
|
"loss": 5.0468,
|
|
"mean_token_accuracy": 0.18303615152835845,
|
|
"num_tokens": 52004313.0,
|
|
"step": 23735
|
|
},
|
|
{
|
|
"entropy": 5.650063705444336,
|
|
"epoch": 2.356093687971417,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004447251703714117,
|
|
"loss": 5.0334,
|
|
"mean_token_accuracy": 0.18002406358718873,
|
|
"num_tokens": 52015207.0,
|
|
"step": 23740
|
|
},
|
|
{
|
|
"entropy": 5.6015260219573975,
|
|
"epoch": 2.3565899166335846,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000444701907818329,
|
|
"loss": 5.0347,
|
|
"mean_token_accuracy": 0.17736193239688874,
|
|
"num_tokens": 52026565.0,
|
|
"step": 23745
|
|
},
|
|
{
|
|
"entropy": 5.635419511795044,
|
|
"epoch": 2.357086145295752,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004446786410570048,
|
|
"loss": 5.0646,
|
|
"mean_token_accuracy": 0.17616048753261565,
|
|
"num_tokens": 52037654.0,
|
|
"step": 23750
|
|
},
|
|
{
|
|
"entropy": 5.558535528182984,
|
|
"epoch": 2.3575823739579196,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00044465537008801575,
|
|
"loss": 4.961,
|
|
"mean_token_accuracy": 0.1841454967856407,
|
|
"num_tokens": 52049772.0,
|
|
"step": 23755
|
|
},
|
|
{
|
|
"entropy": 5.580855417251587,
|
|
"epoch": 2.3580786026200875,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004446320949119392,
|
|
"loss": 5.105,
|
|
"mean_token_accuracy": 0.17487892657518386,
|
|
"num_tokens": 52061363.0,
|
|
"step": 23760
|
|
},
|
|
{
|
|
"entropy": 5.607885313034058,
|
|
"epoch": 2.358574831282255,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00044460881552935215,
|
|
"loss": 4.9709,
|
|
"mean_token_accuracy": 0.18495057225227357,
|
|
"num_tokens": 52073153.0,
|
|
"step": 23765
|
|
},
|
|
{
|
|
"entropy": 5.561751937866211,
|
|
"epoch": 2.3590710599444225,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00044458553194083204,
|
|
"loss": 5.0096,
|
|
"mean_token_accuracy": 0.18456631302833557,
|
|
"num_tokens": 52083369.0,
|
|
"step": 23770
|
|
},
|
|
{
|
|
"entropy": 5.523240756988526,
|
|
"epoch": 2.35956728860659,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004445622441469562,
|
|
"loss": 4.9656,
|
|
"mean_token_accuracy": 0.18823008239269257,
|
|
"num_tokens": 52093701.0,
|
|
"step": 23775
|
|
},
|
|
{
|
|
"entropy": 5.569080257415772,
|
|
"epoch": 2.3600635172687574,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00044453895214830195,
|
|
"loss": 5.0255,
|
|
"mean_token_accuracy": 0.1830786868929863,
|
|
"num_tokens": 52105863.0,
|
|
"step": 23780
|
|
},
|
|
{
|
|
"entropy": 5.543252277374267,
|
|
"epoch": 2.360559745930925,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004445156559454471,
|
|
"loss": 5.017,
|
|
"mean_token_accuracy": 0.1818300813436508,
|
|
"num_tokens": 52116476.0,
|
|
"step": 23785
|
|
},
|
|
{
|
|
"entropy": 5.666142463684082,
|
|
"epoch": 2.3610559745930924,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00044449235553896914,
|
|
"loss": 5.1165,
|
|
"mean_token_accuracy": 0.1691933959722519,
|
|
"num_tokens": 52127262.0,
|
|
"step": 23790
|
|
},
|
|
{
|
|
"entropy": 5.686756420135498,
|
|
"epoch": 2.36155220325526,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004444690509294461,
|
|
"loss": 5.0729,
|
|
"mean_token_accuracy": 0.17669105380773545,
|
|
"num_tokens": 52138575.0,
|
|
"step": 23795
|
|
},
|
|
{
|
|
"entropy": 5.585786199569702,
|
|
"epoch": 2.3620484319174277,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004444457421174558,
|
|
"loss": 5.0278,
|
|
"mean_token_accuracy": 0.18147281259298326,
|
|
"num_tokens": 52149620.0,
|
|
"step": 23800
|
|
},
|
|
{
|
|
"entropy": 5.639217281341553,
|
|
"epoch": 2.3625446605795952,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004444224291035761,
|
|
"loss": 5.0612,
|
|
"mean_token_accuracy": 0.1762116014957428,
|
|
"num_tokens": 52161929.0,
|
|
"step": 23805
|
|
},
|
|
{
|
|
"entropy": 5.512679529190064,
|
|
"epoch": 2.3630408892417627,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00044439911188838533,
|
|
"loss": 4.9882,
|
|
"mean_token_accuracy": 0.18888108134269715,
|
|
"num_tokens": 52172283.0,
|
|
"step": 23810
|
|
},
|
|
{
|
|
"entropy": 5.584146881103516,
|
|
"epoch": 2.36353711790393,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004443757904724615,
|
|
"loss": 5.0783,
|
|
"mean_token_accuracy": 0.1781835824251175,
|
|
"num_tokens": 52184130.0,
|
|
"step": 23815
|
|
},
|
|
{
|
|
"entropy": 5.588577032089233,
|
|
"epoch": 2.3640333465660976,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.00044435246485638317,
|
|
"loss": 5.0846,
|
|
"mean_token_accuracy": 0.18076565861701965,
|
|
"num_tokens": 52195358.0,
|
|
"step": 23820
|
|
},
|
|
{
|
|
"entropy": 5.568464565277099,
|
|
"epoch": 2.364529575228265,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004443291350407285,
|
|
"loss": 4.979,
|
|
"mean_token_accuracy": 0.18197174072265626,
|
|
"num_tokens": 52207070.0,
|
|
"step": 23825
|
|
},
|
|
{
|
|
"entropy": 5.605605506896973,
|
|
"epoch": 2.3650258038904326,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004443058010260762,
|
|
"loss": 5.1006,
|
|
"mean_token_accuracy": 0.17477748095989226,
|
|
"num_tokens": 52217658.0,
|
|
"step": 23830
|
|
},
|
|
{
|
|
"entropy": 5.577688264846802,
|
|
"epoch": 2.3655220325526,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00044428246281300493,
|
|
"loss": 5.0051,
|
|
"mean_token_accuracy": 0.18622718900442123,
|
|
"num_tokens": 52229350.0,
|
|
"step": 23835
|
|
},
|
|
{
|
|
"entropy": 5.656297874450684,
|
|
"epoch": 2.3660182612147675,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00044425912040209326,
|
|
"loss": 5.1592,
|
|
"mean_token_accuracy": 0.1753564551472664,
|
|
"num_tokens": 52241260.0,
|
|
"step": 23840
|
|
},
|
|
{
|
|
"entropy": 5.675198030471802,
|
|
"epoch": 2.3665144898769355,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00044423577379392023,
|
|
"loss": 5.061,
|
|
"mean_token_accuracy": 0.18123331516981125,
|
|
"num_tokens": 52253049.0,
|
|
"step": 23845
|
|
},
|
|
{
|
|
"entropy": 5.585350799560547,
|
|
"epoch": 2.367010718539103,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004442124229890646,
|
|
"loss": 5.0358,
|
|
"mean_token_accuracy": 0.18232847154140472,
|
|
"num_tokens": 52263405.0,
|
|
"step": 23850
|
|
},
|
|
{
|
|
"entropy": 5.5854637145996096,
|
|
"epoch": 2.3675069472012704,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00044418906798810554,
|
|
"loss": 5.0412,
|
|
"mean_token_accuracy": 0.18200973719358443,
|
|
"num_tokens": 52273075.0,
|
|
"step": 23855
|
|
},
|
|
{
|
|
"entropy": 5.7175764560699465,
|
|
"epoch": 2.368003175863438,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.00044416570879162213,
|
|
"loss": 5.2322,
|
|
"mean_token_accuracy": 0.17419291734695436,
|
|
"num_tokens": 52284275.0,
|
|
"step": 23860
|
|
},
|
|
{
|
|
"entropy": 5.59305853843689,
|
|
"epoch": 2.3684994045256054,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004441423454001936,
|
|
"loss": 5.034,
|
|
"mean_token_accuracy": 0.17180906534194945,
|
|
"num_tokens": 52295084.0,
|
|
"step": 23865
|
|
},
|
|
{
|
|
"entropy": 5.586873531341553,
|
|
"epoch": 2.368995633187773,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00044411897781439946,
|
|
"loss": 5.0266,
|
|
"mean_token_accuracy": 0.18246820122003554,
|
|
"num_tokens": 52304172.0,
|
|
"step": 23870
|
|
},
|
|
{
|
|
"entropy": 5.498567056655884,
|
|
"epoch": 2.3694918618499403,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004440956060348191,
|
|
"loss": 4.9748,
|
|
"mean_token_accuracy": 0.18676338642835616,
|
|
"num_tokens": 52315370.0,
|
|
"step": 23875
|
|
},
|
|
{
|
|
"entropy": 5.597283029556275,
|
|
"epoch": 2.369988090512108,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004440722300620321,
|
|
"loss": 5.0375,
|
|
"mean_token_accuracy": 0.18130150586366653,
|
|
"num_tokens": 52326517.0,
|
|
"step": 23880
|
|
},
|
|
{
|
|
"entropy": 5.662319087982178,
|
|
"epoch": 2.3704843191742757,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00044404884989661804,
|
|
"loss": 5.0865,
|
|
"mean_token_accuracy": 0.18310338705778123,
|
|
"num_tokens": 52337110.0,
|
|
"step": 23885
|
|
},
|
|
{
|
|
"entropy": 5.592140817642212,
|
|
"epoch": 2.370980547836443,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004440254655391568,
|
|
"loss": 5.0039,
|
|
"mean_token_accuracy": 0.1850810244679451,
|
|
"num_tokens": 52347509.0,
|
|
"step": 23890
|
|
},
|
|
{
|
|
"entropy": 5.670315742492676,
|
|
"epoch": 2.3714767764986107,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004440020769902282,
|
|
"loss": 5.1361,
|
|
"mean_token_accuracy": 0.17586909085512162,
|
|
"num_tokens": 52357920.0,
|
|
"step": 23895
|
|
},
|
|
{
|
|
"entropy": 5.63978009223938,
|
|
"epoch": 2.371973005160778,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00044397868425041234,
|
|
"loss": 5.0995,
|
|
"mean_token_accuracy": 0.1759955793619156,
|
|
"num_tokens": 52368138.0,
|
|
"step": 23900
|
|
},
|
|
{
|
|
"entropy": 5.667237234115601,
|
|
"epoch": 2.3724692338229456,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004439552873202891,
|
|
"loss": 5.0594,
|
|
"mean_token_accuracy": 0.1795011579990387,
|
|
"num_tokens": 52380503.0,
|
|
"step": 23905
|
|
},
|
|
{
|
|
"entropy": 5.6044487953186035,
|
|
"epoch": 2.372965462485113,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00044393188620043893,
|
|
"loss": 5.0472,
|
|
"mean_token_accuracy": 0.18059685826301575,
|
|
"num_tokens": 52390850.0,
|
|
"step": 23910
|
|
},
|
|
{
|
|
"entropy": 5.542678165435791,
|
|
"epoch": 2.3734616911472806,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004439084808914419,
|
|
"loss": 4.985,
|
|
"mean_token_accuracy": 0.18484220504760743,
|
|
"num_tokens": 52400829.0,
|
|
"step": 23915
|
|
},
|
|
{
|
|
"entropy": 5.641800737380981,
|
|
"epoch": 2.373957919809448,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00044388507139387864,
|
|
"loss": 5.0681,
|
|
"mean_token_accuracy": 0.18003148436546326,
|
|
"num_tokens": 52412892.0,
|
|
"step": 23920
|
|
},
|
|
{
|
|
"entropy": 5.581310033798218,
|
|
"epoch": 2.3744541484716155,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004438616577083293,
|
|
"loss": 5.0116,
|
|
"mean_token_accuracy": 0.18533659875392913,
|
|
"num_tokens": 52423662.0,
|
|
"step": 23925
|
|
},
|
|
{
|
|
"entropy": 5.600772953033447,
|
|
"epoch": 2.3749503771337834,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000443838239835375,
|
|
"loss": 5.0575,
|
|
"mean_token_accuracy": 0.18391835391521455,
|
|
"num_tokens": 52433541.0,
|
|
"step": 23930
|
|
},
|
|
{
|
|
"entropy": 5.622206354141236,
|
|
"epoch": 2.375446605795951,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004438148177755959,
|
|
"loss": 5.0949,
|
|
"mean_token_accuracy": 0.17893042415380478,
|
|
"num_tokens": 52445504.0,
|
|
"step": 23935
|
|
},
|
|
{
|
|
"entropy": 5.650042963027954,
|
|
"epoch": 2.3759428344581184,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00044379139152957327,
|
|
"loss": 5.057,
|
|
"mean_token_accuracy": 0.1753670021891594,
|
|
"num_tokens": 52456116.0,
|
|
"step": 23940
|
|
},
|
|
{
|
|
"entropy": 5.59142107963562,
|
|
"epoch": 2.376439063120286,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00044376796109788777,
|
|
"loss": 4.9383,
|
|
"mean_token_accuracy": 0.18848557472229005,
|
|
"num_tokens": 52465462.0,
|
|
"step": 23945
|
|
},
|
|
{
|
|
"entropy": 5.570306777954102,
|
|
"epoch": 2.3769352917824533,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00044374452648112046,
|
|
"loss": 5.0982,
|
|
"mean_token_accuracy": 0.17667741924524308,
|
|
"num_tokens": 52477213.0,
|
|
"step": 23950
|
|
},
|
|
{
|
|
"entropy": 5.641315078735351,
|
|
"epoch": 2.377431520444621,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00044372108767985253,
|
|
"loss": 5.1004,
|
|
"mean_token_accuracy": 0.17777794152498244,
|
|
"num_tokens": 52488095.0,
|
|
"step": 23955
|
|
},
|
|
{
|
|
"entropy": 5.674362277984619,
|
|
"epoch": 2.3779277491067883,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004436976446946652,
|
|
"loss": 5.1435,
|
|
"mean_token_accuracy": 0.17102427035570145,
|
|
"num_tokens": 52499078.0,
|
|
"step": 23960
|
|
},
|
|
{
|
|
"entropy": 5.617254734039307,
|
|
"epoch": 2.3784239777689558,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00044367419752613983,
|
|
"loss": 5.0295,
|
|
"mean_token_accuracy": 0.17971991002559662,
|
|
"num_tokens": 52510829.0,
|
|
"step": 23965
|
|
},
|
|
{
|
|
"entropy": 5.6331230163574215,
|
|
"epoch": 2.3789202064311237,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004436507461748577,
|
|
"loss": 5.0403,
|
|
"mean_token_accuracy": 0.17940446585416794,
|
|
"num_tokens": 52521466.0,
|
|
"step": 23970
|
|
},
|
|
{
|
|
"entropy": 5.6306994438171385,
|
|
"epoch": 2.379416435093291,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004436272906414007,
|
|
"loss": 4.961,
|
|
"mean_token_accuracy": 0.1843634158372879,
|
|
"num_tokens": 52532617.0,
|
|
"step": 23975
|
|
},
|
|
{
|
|
"entropy": 5.515544366836548,
|
|
"epoch": 2.3799126637554586,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004436038309263501,
|
|
"loss": 5.0202,
|
|
"mean_token_accuracy": 0.17911292910575866,
|
|
"num_tokens": 52543826.0,
|
|
"step": 23980
|
|
},
|
|
{
|
|
"entropy": 5.560767602920532,
|
|
"epoch": 2.380408892417626,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00044358036703028773,
|
|
"loss": 5.0595,
|
|
"mean_token_accuracy": 0.18059613108634948,
|
|
"num_tokens": 52556752.0,
|
|
"step": 23985
|
|
},
|
|
{
|
|
"entropy": 5.628003120422363,
|
|
"epoch": 2.3809051210797936,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00044355689895379563,
|
|
"loss": 5.1201,
|
|
"mean_token_accuracy": 0.17333704084157944,
|
|
"num_tokens": 52567268.0,
|
|
"step": 23990
|
|
},
|
|
{
|
|
"entropy": 5.613879251480102,
|
|
"epoch": 2.381401349741961,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00044353342669745566,
|
|
"loss": 5.0479,
|
|
"mean_token_accuracy": 0.18038588464260102,
|
|
"num_tokens": 52576894.0,
|
|
"step": 23995
|
|
},
|
|
{
|
|
"entropy": 5.578713655471802,
|
|
"epoch": 2.3818975784041285,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00044350995026184976,
|
|
"loss": 5.0341,
|
|
"mean_token_accuracy": 0.18142016530036925,
|
|
"num_tokens": 52587434.0,
|
|
"step": 24000
|
|
},
|
|
{
|
|
"epoch": 2.3818975784041285,
|
|
"eval_entropy": 5.412793871738418,
|
|
"eval_loss": 5.156675815582275,
|
|
"eval_mean_token_accuracy": 0.18144856775336607,
|
|
"eval_num_tokens": 52587434.0,
|
|
"eval_runtime": 20.6019,
|
|
"eval_samples_per_second": 1634.269,
|
|
"eval_steps_per_second": 204.302,
|
|
"step": 24000
|
|
}
|
|
],
|
|
"logging_steps": 5,
|
|
"max_steps": 100750,
|
|
"num_input_tokens_seen": 0,
|
|
"num_train_epochs": 10,
|
|
"save_steps": 3000,
|
|
"stateful_callbacks": {
|
|
"TrainerControl": {
|
|
"args": {
|
|
"should_epoch_stop": false,
|
|
"should_evaluate": false,
|
|
"should_log": false,
|
|
"should_save": true,
|
|
"should_training_stop": false
|
|
},
|
|
"attributes": {}
|
|
}
|
|
},
|
|
"total_flos": 1.307768601305088e+16,
|
|
"train_batch_size": 16,
|
|
"trial_name": null,
|
|
"trial_params": null
|
|
}
|