0e207e3c54
Model: fpadovani/ita-latn-10mb-after-ppt-shuff-dyck-100mb-ckpt500_seed3407 Source: Original Platform
6046 lines
164 KiB
JSON
6046 lines
164 KiB
JSON
{
|
|
"best_global_step": null,
|
|
"best_metric": null,
|
|
"best_model_checkpoint": null,
|
|
"epoch": 0.29773719730051607,
|
|
"eval_steps": 3000,
|
|
"global_step": 3000,
|
|
"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
|
|
}
|
|
],
|
|
"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": 1645030401638400.0,
|
|
"train_batch_size": 16,
|
|
"trial_name": null,
|
|
"trial_params": null
|
|
}
|