b3267e0a8f
Model: fpadovani/ita-latn-10mb-after-ppt-Dp-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": 7.415488815307617,
|
|
"epoch": 0.0004962286621675268,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 2e-06,
|
|
"loss": 6.9797,
|
|
"mean_token_accuracy": 0.08811815902590751,
|
|
"num_tokens": 11448.0,
|
|
"step": 5
|
|
},
|
|
{
|
|
"entropy": 7.423927688598633,
|
|
"epoch": 0.0009924573243350536,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 4.5e-06,
|
|
"loss": 6.9808,
|
|
"mean_token_accuracy": 0.08794851526618004,
|
|
"num_tokens": 22646.0,
|
|
"step": 10
|
|
},
|
|
{
|
|
"entropy": 7.419756555557251,
|
|
"epoch": 0.0014886859865025804,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 7e-06,
|
|
"loss": 6.9117,
|
|
"mean_token_accuracy": 0.08956757485866547,
|
|
"num_tokens": 34011.0,
|
|
"step": 15
|
|
},
|
|
{
|
|
"entropy": 7.414588403701782,
|
|
"epoch": 0.001984914648670107,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 9.5e-06,
|
|
"loss": 6.9364,
|
|
"mean_token_accuracy": 0.09392186626791954,
|
|
"num_tokens": 44566.0,
|
|
"step": 20
|
|
},
|
|
{
|
|
"entropy": 7.422558164596557,
|
|
"epoch": 0.002481143310837634,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 1.2e-05,
|
|
"loss": 7.0066,
|
|
"mean_token_accuracy": 0.08173666819930077,
|
|
"num_tokens": 56274.0,
|
|
"step": 25
|
|
},
|
|
{
|
|
"entropy": 7.404311037063598,
|
|
"epoch": 0.0029773719730051607,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 1.4500000000000002e-05,
|
|
"loss": 6.9198,
|
|
"mean_token_accuracy": 0.09323365837335587,
|
|
"num_tokens": 66584.0,
|
|
"step": 30
|
|
},
|
|
{
|
|
"entropy": 7.403407335281372,
|
|
"epoch": 0.0034736006351726877,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 1.7000000000000003e-05,
|
|
"loss": 6.9536,
|
|
"mean_token_accuracy": 0.08776896521449089,
|
|
"num_tokens": 76948.0,
|
|
"step": 35
|
|
},
|
|
{
|
|
"entropy": 7.424892377853394,
|
|
"epoch": 0.003969829297340214,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 1.95e-05,
|
|
"loss": 6.9625,
|
|
"mean_token_accuracy": 0.09215026199817658,
|
|
"num_tokens": 87253.0,
|
|
"step": 40
|
|
},
|
|
{
|
|
"entropy": 7.402211713790893,
|
|
"epoch": 0.004466057959507741,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 2.2e-05,
|
|
"loss": 6.9664,
|
|
"mean_token_accuracy": 0.0926709569990635,
|
|
"num_tokens": 98273.0,
|
|
"step": 45
|
|
},
|
|
{
|
|
"entropy": 7.390836954116821,
|
|
"epoch": 0.004962286621675268,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 2.4500000000000003e-05,
|
|
"loss": 6.8805,
|
|
"mean_token_accuracy": 0.09474824145436286,
|
|
"num_tokens": 107788.0,
|
|
"step": 50
|
|
},
|
|
{
|
|
"entropy": 7.361630630493164,
|
|
"epoch": 0.0054585152838427945,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 2.7e-05,
|
|
"loss": 6.9007,
|
|
"mean_token_accuracy": 0.08987915515899658,
|
|
"num_tokens": 118632.0,
|
|
"step": 55
|
|
},
|
|
{
|
|
"entropy": 7.329354906082154,
|
|
"epoch": 0.0059547439460103215,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 2.95e-05,
|
|
"loss": 6.8369,
|
|
"mean_token_accuracy": 0.09355762079358101,
|
|
"num_tokens": 128649.0,
|
|
"step": 60
|
|
},
|
|
{
|
|
"entropy": 7.331360340118408,
|
|
"epoch": 0.0064509726081778485,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 3.2e-05,
|
|
"loss": 6.8725,
|
|
"mean_token_accuracy": 0.09848466441035271,
|
|
"num_tokens": 138958.0,
|
|
"step": 65
|
|
},
|
|
{
|
|
"entropy": 7.316051912307739,
|
|
"epoch": 0.0069472012703453755,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 3.4500000000000005e-05,
|
|
"loss": 6.875,
|
|
"mean_token_accuracy": 0.09506641924381257,
|
|
"num_tokens": 151445.0,
|
|
"step": 70
|
|
},
|
|
{
|
|
"entropy": 7.357440185546875,
|
|
"epoch": 0.007443429932512902,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 3.7e-05,
|
|
"loss": 6.9168,
|
|
"mean_token_accuracy": 0.0950050063431263,
|
|
"num_tokens": 162239.0,
|
|
"step": 75
|
|
},
|
|
{
|
|
"entropy": 7.389816427230835,
|
|
"epoch": 0.007939658594680429,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 3.95e-05,
|
|
"loss": 6.8606,
|
|
"mean_token_accuracy": 0.08998646065592766,
|
|
"num_tokens": 173261.0,
|
|
"step": 80
|
|
},
|
|
{
|
|
"entropy": 7.374487590789795,
|
|
"epoch": 0.008435887256847956,
|
|
"grad_norm": 0.7578125,
|
|
"learning_rate": 4.2000000000000004e-05,
|
|
"loss": 6.8612,
|
|
"mean_token_accuracy": 0.08823171928524971,
|
|
"num_tokens": 183857.0,
|
|
"step": 85
|
|
},
|
|
{
|
|
"entropy": 7.406818819046021,
|
|
"epoch": 0.008932115919015483,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 4.45e-05,
|
|
"loss": 7.0573,
|
|
"mean_token_accuracy": 0.08514732420444489,
|
|
"num_tokens": 196635.0,
|
|
"step": 90
|
|
},
|
|
{
|
|
"entropy": 7.393658542633057,
|
|
"epoch": 0.00942834458118301,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 4.7000000000000004e-05,
|
|
"loss": 7.0168,
|
|
"mean_token_accuracy": 0.09471790939569473,
|
|
"num_tokens": 208700.0,
|
|
"step": 95
|
|
},
|
|
{
|
|
"entropy": 7.416672229766846,
|
|
"epoch": 0.009924573243350537,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 4.9500000000000004e-05,
|
|
"loss": 6.9349,
|
|
"mean_token_accuracy": 0.08931025043129921,
|
|
"num_tokens": 218915.0,
|
|
"step": 100
|
|
},
|
|
{
|
|
"entropy": 7.340483951568603,
|
|
"epoch": 0.010420801905518062,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 5.2e-05,
|
|
"loss": 6.8607,
|
|
"mean_token_accuracy": 0.0964167907834053,
|
|
"num_tokens": 230211.0,
|
|
"step": 105
|
|
},
|
|
{
|
|
"entropy": 7.323957920074463,
|
|
"epoch": 0.010917030567685589,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 5.45e-05,
|
|
"loss": 6.8819,
|
|
"mean_token_accuracy": 0.10094936266541481,
|
|
"num_tokens": 241174.0,
|
|
"step": 110
|
|
},
|
|
{
|
|
"entropy": 7.3142293930053714,
|
|
"epoch": 0.011413259229853116,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 5.7e-05,
|
|
"loss": 6.8898,
|
|
"mean_token_accuracy": 0.09185363873839378,
|
|
"num_tokens": 251708.0,
|
|
"step": 115
|
|
},
|
|
{
|
|
"entropy": 7.415872716903687,
|
|
"epoch": 0.011909487892020643,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 5.9499999999999996e-05,
|
|
"loss": 7.0541,
|
|
"mean_token_accuracy": 0.08325114101171494,
|
|
"num_tokens": 263287.0,
|
|
"step": 120
|
|
},
|
|
{
|
|
"entropy": 7.43096809387207,
|
|
"epoch": 0.01240571655418817,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 6.2e-05,
|
|
"loss": 6.9198,
|
|
"mean_token_accuracy": 0.0861751176416874,
|
|
"num_tokens": 275179.0,
|
|
"step": 125
|
|
},
|
|
{
|
|
"entropy": 7.31543345451355,
|
|
"epoch": 0.012901945216355697,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 6.450000000000001e-05,
|
|
"loss": 6.7886,
|
|
"mean_token_accuracy": 0.09708081930875778,
|
|
"num_tokens": 287223.0,
|
|
"step": 130
|
|
},
|
|
{
|
|
"entropy": 7.303066396713257,
|
|
"epoch": 0.013398173878523224,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 6.7e-05,
|
|
"loss": 6.8086,
|
|
"mean_token_accuracy": 0.09785129725933076,
|
|
"num_tokens": 297868.0,
|
|
"step": 135
|
|
},
|
|
{
|
|
"entropy": 7.2979652881622314,
|
|
"epoch": 0.013894402540690751,
|
|
"grad_norm": 0.78515625,
|
|
"learning_rate": 6.950000000000001e-05,
|
|
"loss": 6.8927,
|
|
"mean_token_accuracy": 0.09260747209191322,
|
|
"num_tokens": 309702.0,
|
|
"step": 140
|
|
},
|
|
{
|
|
"entropy": 7.4375659942626955,
|
|
"epoch": 0.014390631202858276,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 7.2e-05,
|
|
"loss": 6.906,
|
|
"mean_token_accuracy": 0.09100511819124221,
|
|
"num_tokens": 321613.0,
|
|
"step": 145
|
|
},
|
|
{
|
|
"entropy": 7.383455657958985,
|
|
"epoch": 0.014886859865025803,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 7.45e-05,
|
|
"loss": 6.8772,
|
|
"mean_token_accuracy": 0.09483638480305671,
|
|
"num_tokens": 332668.0,
|
|
"step": 150
|
|
},
|
|
{
|
|
"entropy": 7.347703647613526,
|
|
"epoch": 0.01538308852719333,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 7.7e-05,
|
|
"loss": 6.9471,
|
|
"mean_token_accuracy": 0.09541060924530029,
|
|
"num_tokens": 342579.0,
|
|
"step": 155
|
|
},
|
|
{
|
|
"entropy": 7.395112085342407,
|
|
"epoch": 0.015879317189360857,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 7.950000000000001e-05,
|
|
"loss": 6.7956,
|
|
"mean_token_accuracy": 0.09388362988829613,
|
|
"num_tokens": 352271.0,
|
|
"step": 160
|
|
},
|
|
{
|
|
"entropy": 7.331162643432617,
|
|
"epoch": 0.016375545851528384,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 8.2e-05,
|
|
"loss": 6.932,
|
|
"mean_token_accuracy": 0.09907099306583404,
|
|
"num_tokens": 364033.0,
|
|
"step": 165
|
|
},
|
|
{
|
|
"entropy": 7.286223697662353,
|
|
"epoch": 0.01687177451369591,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 8.450000000000001e-05,
|
|
"loss": 6.8812,
|
|
"mean_token_accuracy": 0.09280342161655426,
|
|
"num_tokens": 373788.0,
|
|
"step": 170
|
|
},
|
|
{
|
|
"entropy": 7.398203802108765,
|
|
"epoch": 0.01736800317586344,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 8.7e-05,
|
|
"loss": 6.8526,
|
|
"mean_token_accuracy": 0.09731495082378387,
|
|
"num_tokens": 384883.0,
|
|
"step": 175
|
|
},
|
|
{
|
|
"entropy": 7.3108381748199465,
|
|
"epoch": 0.017864231838030965,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 8.95e-05,
|
|
"loss": 6.7825,
|
|
"mean_token_accuracy": 0.09594601169228553,
|
|
"num_tokens": 396044.0,
|
|
"step": 180
|
|
},
|
|
{
|
|
"entropy": 7.364286279678344,
|
|
"epoch": 0.018360460500198492,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 9.2e-05,
|
|
"loss": 6.9289,
|
|
"mean_token_accuracy": 0.09398710206151009,
|
|
"num_tokens": 406995.0,
|
|
"step": 185
|
|
},
|
|
{
|
|
"entropy": 7.368616962432862,
|
|
"epoch": 0.01885668916236602,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 9.45e-05,
|
|
"loss": 6.8242,
|
|
"mean_token_accuracy": 0.09675540551543235,
|
|
"num_tokens": 417238.0,
|
|
"step": 190
|
|
},
|
|
{
|
|
"entropy": 7.337496566772461,
|
|
"epoch": 0.019352917824533546,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 9.7e-05,
|
|
"loss": 6.869,
|
|
"mean_token_accuracy": 0.09491769820451737,
|
|
"num_tokens": 427263.0,
|
|
"step": 195
|
|
},
|
|
{
|
|
"entropy": 7.282687520980835,
|
|
"epoch": 0.019849146486701073,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 9.95e-05,
|
|
"loss": 6.7887,
|
|
"mean_token_accuracy": 0.1014923520386219,
|
|
"num_tokens": 438357.0,
|
|
"step": 200
|
|
},
|
|
{
|
|
"entropy": 7.343814468383789,
|
|
"epoch": 0.0203453751488686,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000102,
|
|
"loss": 6.8331,
|
|
"mean_token_accuracy": 0.09941279143095016,
|
|
"num_tokens": 448738.0,
|
|
"step": 205
|
|
},
|
|
{
|
|
"entropy": 7.334179782867432,
|
|
"epoch": 0.020841603811036124,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.00010449999999999999,
|
|
"loss": 6.8794,
|
|
"mean_token_accuracy": 0.09967483356595039,
|
|
"num_tokens": 457873.0,
|
|
"step": 210
|
|
},
|
|
{
|
|
"entropy": 7.292327451705932,
|
|
"epoch": 0.02133783247320365,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.000107,
|
|
"loss": 6.8026,
|
|
"mean_token_accuracy": 0.09620003700256348,
|
|
"num_tokens": 468640.0,
|
|
"step": 215
|
|
},
|
|
{
|
|
"entropy": 7.303198051452637,
|
|
"epoch": 0.021834061135371178,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0001095,
|
|
"loss": 6.8446,
|
|
"mean_token_accuracy": 0.09441228732466697,
|
|
"num_tokens": 479922.0,
|
|
"step": 220
|
|
},
|
|
{
|
|
"entropy": 7.285147094726563,
|
|
"epoch": 0.022330289797538705,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.000112,
|
|
"loss": 6.7865,
|
|
"mean_token_accuracy": 0.098848607391119,
|
|
"num_tokens": 491056.0,
|
|
"step": 225
|
|
},
|
|
{
|
|
"entropy": 7.386207151412964,
|
|
"epoch": 0.022826518459706232,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0001145,
|
|
"loss": 6.9114,
|
|
"mean_token_accuracy": 0.09412190616130829,
|
|
"num_tokens": 504365.0,
|
|
"step": 230
|
|
},
|
|
{
|
|
"entropy": 7.306986141204834,
|
|
"epoch": 0.02332274712187376,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00011700000000000001,
|
|
"loss": 6.7885,
|
|
"mean_token_accuracy": 0.09399791210889816,
|
|
"num_tokens": 514347.0,
|
|
"step": 235
|
|
},
|
|
{
|
|
"entropy": 7.284820985794068,
|
|
"epoch": 0.023818975784041286,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.00011949999999999999,
|
|
"loss": 6.8463,
|
|
"mean_token_accuracy": 0.09885015189647675,
|
|
"num_tokens": 525912.0,
|
|
"step": 240
|
|
},
|
|
{
|
|
"entropy": 7.264670991897583,
|
|
"epoch": 0.024315204446208813,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.000122,
|
|
"loss": 6.722,
|
|
"mean_token_accuracy": 0.09802954122424126,
|
|
"num_tokens": 535566.0,
|
|
"step": 245
|
|
},
|
|
{
|
|
"entropy": 7.293220567703247,
|
|
"epoch": 0.02481143310837634,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0001245,
|
|
"loss": 6.7569,
|
|
"mean_token_accuracy": 0.09652359411120415,
|
|
"num_tokens": 546474.0,
|
|
"step": 250
|
|
},
|
|
{
|
|
"entropy": 7.343952226638794,
|
|
"epoch": 0.025307661770543867,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.000127,
|
|
"loss": 6.9085,
|
|
"mean_token_accuracy": 0.09467220306396484,
|
|
"num_tokens": 558132.0,
|
|
"step": 255
|
|
},
|
|
{
|
|
"entropy": 7.391662740707398,
|
|
"epoch": 0.025803890432711394,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0001295,
|
|
"loss": 6.8717,
|
|
"mean_token_accuracy": 0.08968425244092941,
|
|
"num_tokens": 568309.0,
|
|
"step": 260
|
|
},
|
|
{
|
|
"entropy": 7.242248058319092,
|
|
"epoch": 0.02630011909487892,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000132,
|
|
"loss": 6.7985,
|
|
"mean_token_accuracy": 0.09653588980436326,
|
|
"num_tokens": 579701.0,
|
|
"step": 265
|
|
},
|
|
{
|
|
"entropy": 7.3309746265411375,
|
|
"epoch": 0.026796347757046448,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.00013450000000000002,
|
|
"loss": 6.7519,
|
|
"mean_token_accuracy": 0.09935276582837105,
|
|
"num_tokens": 590832.0,
|
|
"step": 270
|
|
},
|
|
{
|
|
"entropy": 7.18915901184082,
|
|
"epoch": 0.027292576419213975,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00013700000000000002,
|
|
"loss": 6.7155,
|
|
"mean_token_accuracy": 0.09612485915422439,
|
|
"num_tokens": 601094.0,
|
|
"step": 275
|
|
},
|
|
{
|
|
"entropy": 7.255670118331909,
|
|
"epoch": 0.027788805081381502,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0001395,
|
|
"loss": 6.7341,
|
|
"mean_token_accuracy": 0.1019403874874115,
|
|
"num_tokens": 612027.0,
|
|
"step": 280
|
|
},
|
|
{
|
|
"entropy": 7.241375875473023,
|
|
"epoch": 0.02828503374354903,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00014199999999999998,
|
|
"loss": 6.7852,
|
|
"mean_token_accuracy": 0.0944296196103096,
|
|
"num_tokens": 623698.0,
|
|
"step": 285
|
|
},
|
|
{
|
|
"entropy": 7.326890134811402,
|
|
"epoch": 0.028781262405716553,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0001445,
|
|
"loss": 6.8125,
|
|
"mean_token_accuracy": 0.09790188670158387,
|
|
"num_tokens": 635631.0,
|
|
"step": 290
|
|
},
|
|
{
|
|
"entropy": 7.2972441673278805,
|
|
"epoch": 0.02927749106788408,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.000147,
|
|
"loss": 6.8098,
|
|
"mean_token_accuracy": 0.09671351835131645,
|
|
"num_tokens": 647663.0,
|
|
"step": 295
|
|
},
|
|
{
|
|
"entropy": 7.226529216766357,
|
|
"epoch": 0.029773719730051607,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0001495,
|
|
"loss": 6.7771,
|
|
"mean_token_accuracy": 0.0953554093837738,
|
|
"num_tokens": 659352.0,
|
|
"step": 300
|
|
},
|
|
{
|
|
"entropy": 7.249944972991943,
|
|
"epoch": 0.030269948392219134,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000152,
|
|
"loss": 6.7277,
|
|
"mean_token_accuracy": 0.10546225905418397,
|
|
"num_tokens": 669379.0,
|
|
"step": 305
|
|
},
|
|
{
|
|
"entropy": 7.287822151184082,
|
|
"epoch": 0.03076617705438666,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00015450000000000001,
|
|
"loss": 6.7385,
|
|
"mean_token_accuracy": 0.10098289772868156,
|
|
"num_tokens": 680144.0,
|
|
"step": 310
|
|
},
|
|
{
|
|
"entropy": 7.2293524742126465,
|
|
"epoch": 0.03126240571655419,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.000157,
|
|
"loss": 6.6844,
|
|
"mean_token_accuracy": 0.09755392372608185,
|
|
"num_tokens": 691165.0,
|
|
"step": 315
|
|
},
|
|
{
|
|
"entropy": 7.23696551322937,
|
|
"epoch": 0.031758634378721715,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0001595,
|
|
"loss": 6.8136,
|
|
"mean_token_accuracy": 0.09727144762873649,
|
|
"num_tokens": 703767.0,
|
|
"step": 320
|
|
},
|
|
{
|
|
"entropy": 7.2687766551971436,
|
|
"epoch": 0.032254863040889245,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000162,
|
|
"loss": 6.7885,
|
|
"mean_token_accuracy": 0.10152007564902306,
|
|
"num_tokens": 714298.0,
|
|
"step": 325
|
|
},
|
|
{
|
|
"entropy": 7.237318611145019,
|
|
"epoch": 0.03275109170305677,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00016450000000000001,
|
|
"loss": 6.7841,
|
|
"mean_token_accuracy": 0.10548736825585366,
|
|
"num_tokens": 724135.0,
|
|
"step": 330
|
|
},
|
|
{
|
|
"entropy": 7.179241037368774,
|
|
"epoch": 0.03324732036522429,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00016700000000000002,
|
|
"loss": 6.8555,
|
|
"mean_token_accuracy": 0.09413279443979264,
|
|
"num_tokens": 735050.0,
|
|
"step": 335
|
|
},
|
|
{
|
|
"entropy": 7.315862798690796,
|
|
"epoch": 0.03374354902739182,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.00016950000000000003,
|
|
"loss": 6.7585,
|
|
"mean_token_accuracy": 0.09567313492298127,
|
|
"num_tokens": 746073.0,
|
|
"step": 340
|
|
},
|
|
{
|
|
"entropy": 7.213669204711914,
|
|
"epoch": 0.034239777689559346,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00017199999999999998,
|
|
"loss": 6.7686,
|
|
"mean_token_accuracy": 0.09640354067087173,
|
|
"num_tokens": 758998.0,
|
|
"step": 345
|
|
},
|
|
{
|
|
"entropy": 7.203896570205688,
|
|
"epoch": 0.03473600635172688,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00017449999999999999,
|
|
"loss": 6.6867,
|
|
"mean_token_accuracy": 0.09490930512547494,
|
|
"num_tokens": 771608.0,
|
|
"step": 350
|
|
},
|
|
{
|
|
"entropy": 7.220716094970703,
|
|
"epoch": 0.0352322350138944,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.000177,
|
|
"loss": 6.7711,
|
|
"mean_token_accuracy": 0.09604462832212449,
|
|
"num_tokens": 782394.0,
|
|
"step": 355
|
|
},
|
|
{
|
|
"entropy": 7.213645648956299,
|
|
"epoch": 0.03572846367606193,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0001795,
|
|
"loss": 6.6827,
|
|
"mean_token_accuracy": 0.10222365930676461,
|
|
"num_tokens": 792389.0,
|
|
"step": 360
|
|
},
|
|
{
|
|
"entropy": 7.195154285430908,
|
|
"epoch": 0.036224692338229454,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.000182,
|
|
"loss": 6.7383,
|
|
"mean_token_accuracy": 0.09877654984593391,
|
|
"num_tokens": 803219.0,
|
|
"step": 365
|
|
},
|
|
{
|
|
"entropy": 7.26901273727417,
|
|
"epoch": 0.036720921000396985,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0001845,
|
|
"loss": 6.8117,
|
|
"mean_token_accuracy": 0.09464164227247238,
|
|
"num_tokens": 814249.0,
|
|
"step": 370
|
|
},
|
|
{
|
|
"entropy": 7.248525381088257,
|
|
"epoch": 0.03721714966256451,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.000187,
|
|
"loss": 6.7002,
|
|
"mean_token_accuracy": 0.10740549117326736,
|
|
"num_tokens": 825138.0,
|
|
"step": 375
|
|
},
|
|
{
|
|
"entropy": 7.151234674453735,
|
|
"epoch": 0.03771337832473204,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0001895,
|
|
"loss": 6.7529,
|
|
"mean_token_accuracy": 0.10170127227902412,
|
|
"num_tokens": 836024.0,
|
|
"step": 380
|
|
},
|
|
{
|
|
"entropy": 7.221024084091186,
|
|
"epoch": 0.03820960698689956,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.000192,
|
|
"loss": 6.7426,
|
|
"mean_token_accuracy": 0.0970191240310669,
|
|
"num_tokens": 847765.0,
|
|
"step": 385
|
|
},
|
|
{
|
|
"entropy": 7.190954208374023,
|
|
"epoch": 0.03870583564906709,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0001945,
|
|
"loss": 6.7344,
|
|
"mean_token_accuracy": 0.0974167302250862,
|
|
"num_tokens": 859980.0,
|
|
"step": 390
|
|
},
|
|
{
|
|
"entropy": 7.299342060089112,
|
|
"epoch": 0.039202064311234616,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00019700000000000002,
|
|
"loss": 6.7494,
|
|
"mean_token_accuracy": 0.09645001664757728,
|
|
"num_tokens": 871514.0,
|
|
"step": 395
|
|
},
|
|
{
|
|
"entropy": 7.188382196426391,
|
|
"epoch": 0.03969829297340215,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00019950000000000002,
|
|
"loss": 6.7508,
|
|
"mean_token_accuracy": 0.09433658048510551,
|
|
"num_tokens": 881984.0,
|
|
"step": 400
|
|
},
|
|
{
|
|
"entropy": 7.196045541763306,
|
|
"epoch": 0.04019452163556967,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000202,
|
|
"loss": 6.7063,
|
|
"mean_token_accuracy": 0.10188237726688384,
|
|
"num_tokens": 894198.0,
|
|
"step": 405
|
|
},
|
|
{
|
|
"entropy": 7.18197021484375,
|
|
"epoch": 0.0406907502977372,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00020449999999999998,
|
|
"loss": 6.719,
|
|
"mean_token_accuracy": 0.09976514428853989,
|
|
"num_tokens": 905394.0,
|
|
"step": 410
|
|
},
|
|
{
|
|
"entropy": 7.248855495452881,
|
|
"epoch": 0.041186978959904724,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.000207,
|
|
"loss": 6.7958,
|
|
"mean_token_accuracy": 0.09452574029564857,
|
|
"num_tokens": 917010.0,
|
|
"step": 415
|
|
},
|
|
{
|
|
"entropy": 7.155883693695069,
|
|
"epoch": 0.04168320762207225,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0002095,
|
|
"loss": 6.6121,
|
|
"mean_token_accuracy": 0.10424820482730865,
|
|
"num_tokens": 926761.0,
|
|
"step": 420
|
|
},
|
|
{
|
|
"entropy": 7.060562229156494,
|
|
"epoch": 0.04217943628423978,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000212,
|
|
"loss": 6.6519,
|
|
"mean_token_accuracy": 0.10032859295606614,
|
|
"num_tokens": 938385.0,
|
|
"step": 425
|
|
},
|
|
{
|
|
"entropy": 7.134511184692383,
|
|
"epoch": 0.0426756649464073,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0002145,
|
|
"loss": 6.6897,
|
|
"mean_token_accuracy": 0.0993834190070629,
|
|
"num_tokens": 949709.0,
|
|
"step": 430
|
|
},
|
|
{
|
|
"entropy": 7.11284236907959,
|
|
"epoch": 0.04317189360857483,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00021700000000000002,
|
|
"loss": 6.7173,
|
|
"mean_token_accuracy": 0.09899322465062141,
|
|
"num_tokens": 960837.0,
|
|
"step": 435
|
|
},
|
|
{
|
|
"entropy": 7.13794903755188,
|
|
"epoch": 0.043668122270742356,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0002195,
|
|
"loss": 6.5545,
|
|
"mean_token_accuracy": 0.10581014305353165,
|
|
"num_tokens": 971036.0,
|
|
"step": 440
|
|
},
|
|
{
|
|
"entropy": 7.189764070510864,
|
|
"epoch": 0.044164350932909886,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000222,
|
|
"loss": 6.6988,
|
|
"mean_token_accuracy": 0.09889093339443207,
|
|
"num_tokens": 983057.0,
|
|
"step": 445
|
|
},
|
|
{
|
|
"entropy": 7.109373235702515,
|
|
"epoch": 0.04466057959507741,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0002245,
|
|
"loss": 6.657,
|
|
"mean_token_accuracy": 0.10294226482510567,
|
|
"num_tokens": 994303.0,
|
|
"step": 450
|
|
},
|
|
{
|
|
"entropy": 7.106617975234985,
|
|
"epoch": 0.04515680825724494,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00022700000000000002,
|
|
"loss": 6.6683,
|
|
"mean_token_accuracy": 0.1027058370411396,
|
|
"num_tokens": 1005033.0,
|
|
"step": 455
|
|
},
|
|
{
|
|
"entropy": 7.166249561309814,
|
|
"epoch": 0.045653036919412464,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.00022950000000000002,
|
|
"loss": 6.7313,
|
|
"mean_token_accuracy": 0.10222981199622154,
|
|
"num_tokens": 1015940.0,
|
|
"step": 460
|
|
},
|
|
{
|
|
"entropy": 7.1316859245300295,
|
|
"epoch": 0.046149265581579994,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00023200000000000003,
|
|
"loss": 6.6994,
|
|
"mean_token_accuracy": 0.1031339094042778,
|
|
"num_tokens": 1027582.0,
|
|
"step": 465
|
|
},
|
|
{
|
|
"entropy": 7.089751434326172,
|
|
"epoch": 0.04664549424374752,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00023449999999999998,
|
|
"loss": 6.6675,
|
|
"mean_token_accuracy": 0.10097738355398178,
|
|
"num_tokens": 1040046.0,
|
|
"step": 470
|
|
},
|
|
{
|
|
"entropy": 7.186102390289307,
|
|
"epoch": 0.04714172290591505,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.000237,
|
|
"loss": 6.7444,
|
|
"mean_token_accuracy": 0.09288590252399445,
|
|
"num_tokens": 1050636.0,
|
|
"step": 475
|
|
},
|
|
{
|
|
"entropy": 7.142090320587158,
|
|
"epoch": 0.04763795156808257,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0002395,
|
|
"loss": 6.6294,
|
|
"mean_token_accuracy": 0.10634742677211761,
|
|
"num_tokens": 1060748.0,
|
|
"step": 480
|
|
},
|
|
{
|
|
"entropy": 7.175977611541748,
|
|
"epoch": 0.0481341802302501,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.000242,
|
|
"loss": 6.6716,
|
|
"mean_token_accuracy": 0.09640654549002647,
|
|
"num_tokens": 1071940.0,
|
|
"step": 485
|
|
},
|
|
{
|
|
"entropy": 7.124125528335571,
|
|
"epoch": 0.048630408892417626,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0002445,
|
|
"loss": 6.701,
|
|
"mean_token_accuracy": 0.10127488672733306,
|
|
"num_tokens": 1082962.0,
|
|
"step": 490
|
|
},
|
|
{
|
|
"entropy": 7.0944671630859375,
|
|
"epoch": 0.04912663755458515,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.000247,
|
|
"loss": 6.6792,
|
|
"mean_token_accuracy": 0.1065860316157341,
|
|
"num_tokens": 1093082.0,
|
|
"step": 495
|
|
},
|
|
{
|
|
"entropy": 7.197715377807617,
|
|
"epoch": 0.04962286621675268,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0002495,
|
|
"loss": 6.7682,
|
|
"mean_token_accuracy": 0.10142254531383514,
|
|
"num_tokens": 1103528.0,
|
|
"step": 500
|
|
},
|
|
{
|
|
"entropy": 7.073600006103516,
|
|
"epoch": 0.0501190948789202,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000252,
|
|
"loss": 6.6416,
|
|
"mean_token_accuracy": 0.0960576593875885,
|
|
"num_tokens": 1114813.0,
|
|
"step": 505
|
|
},
|
|
{
|
|
"entropy": 7.003829717636108,
|
|
"epoch": 0.050615323541087734,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0002545,
|
|
"loss": 6.6403,
|
|
"mean_token_accuracy": 0.09825952127575874,
|
|
"num_tokens": 1125345.0,
|
|
"step": 510
|
|
},
|
|
{
|
|
"entropy": 7.108769464492798,
|
|
"epoch": 0.05111155220325526,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000257,
|
|
"loss": 6.6572,
|
|
"mean_token_accuracy": 0.09955623000860214,
|
|
"num_tokens": 1134985.0,
|
|
"step": 515
|
|
},
|
|
{
|
|
"entropy": 7.135790109634399,
|
|
"epoch": 0.05160778086542279,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0002595,
|
|
"loss": 6.6783,
|
|
"mean_token_accuracy": 0.10150780752301217,
|
|
"num_tokens": 1145796.0,
|
|
"step": 520
|
|
},
|
|
{
|
|
"entropy": 7.187171220779419,
|
|
"epoch": 0.05210400952759031,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000262,
|
|
"loss": 6.8131,
|
|
"mean_token_accuracy": 0.09044179245829582,
|
|
"num_tokens": 1156936.0,
|
|
"step": 525
|
|
},
|
|
{
|
|
"entropy": 7.090089416503906,
|
|
"epoch": 0.05260023818975784,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00026450000000000003,
|
|
"loss": 6.6959,
|
|
"mean_token_accuracy": 0.10054284557700158,
|
|
"num_tokens": 1167526.0,
|
|
"step": 530
|
|
},
|
|
{
|
|
"entropy": 7.1854321479797365,
|
|
"epoch": 0.053096466851925365,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00026700000000000004,
|
|
"loss": 6.7306,
|
|
"mean_token_accuracy": 0.09534744620323181,
|
|
"num_tokens": 1177647.0,
|
|
"step": 535
|
|
},
|
|
{
|
|
"entropy": 7.077204322814941,
|
|
"epoch": 0.053592695514092896,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00026950000000000005,
|
|
"loss": 6.6923,
|
|
"mean_token_accuracy": 0.1065493330359459,
|
|
"num_tokens": 1188255.0,
|
|
"step": 540
|
|
},
|
|
{
|
|
"entropy": 7.047231197357178,
|
|
"epoch": 0.05408892417626042,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00027200000000000005,
|
|
"loss": 6.6221,
|
|
"mean_token_accuracy": 0.11043694391846656,
|
|
"num_tokens": 1199433.0,
|
|
"step": 545
|
|
},
|
|
{
|
|
"entropy": 7.008746385574341,
|
|
"epoch": 0.05458515283842795,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0002745,
|
|
"loss": 6.7064,
|
|
"mean_token_accuracy": 0.09511427283287048,
|
|
"num_tokens": 1210067.0,
|
|
"step": 550
|
|
},
|
|
{
|
|
"entropy": 7.019316959381103,
|
|
"epoch": 0.055081381500595473,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000277,
|
|
"loss": 6.5836,
|
|
"mean_token_accuracy": 0.1026071272790432,
|
|
"num_tokens": 1220639.0,
|
|
"step": 555
|
|
},
|
|
{
|
|
"entropy": 7.124681997299194,
|
|
"epoch": 0.055577610162763004,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0002795,
|
|
"loss": 6.6339,
|
|
"mean_token_accuracy": 0.10223110392689705,
|
|
"num_tokens": 1233158.0,
|
|
"step": 560
|
|
},
|
|
{
|
|
"entropy": 7.022218942642212,
|
|
"epoch": 0.05607383882493053,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00028199999999999997,
|
|
"loss": 6.6128,
|
|
"mean_token_accuracy": 0.10005637407302856,
|
|
"num_tokens": 1244552.0,
|
|
"step": 565
|
|
},
|
|
{
|
|
"entropy": 7.1609320640563965,
|
|
"epoch": 0.05657006748709806,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0002845,
|
|
"loss": 6.7327,
|
|
"mean_token_accuracy": 0.09698689877986907,
|
|
"num_tokens": 1255478.0,
|
|
"step": 570
|
|
},
|
|
{
|
|
"entropy": 6.899557256698609,
|
|
"epoch": 0.05706629614926558,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000287,
|
|
"loss": 6.5604,
|
|
"mean_token_accuracy": 0.10638210996985435,
|
|
"num_tokens": 1267507.0,
|
|
"step": 575
|
|
},
|
|
{
|
|
"entropy": 7.014608669281006,
|
|
"epoch": 0.057562524811433105,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0002895,
|
|
"loss": 6.5649,
|
|
"mean_token_accuracy": 0.09933194518089294,
|
|
"num_tokens": 1279377.0,
|
|
"step": 580
|
|
},
|
|
{
|
|
"entropy": 7.112942886352539,
|
|
"epoch": 0.058058753473600636,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.000292,
|
|
"loss": 6.6557,
|
|
"mean_token_accuracy": 0.10565379559993744,
|
|
"num_tokens": 1290671.0,
|
|
"step": 585
|
|
},
|
|
{
|
|
"entropy": 6.903086757659912,
|
|
"epoch": 0.05855498213576816,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0002945,
|
|
"loss": 6.6323,
|
|
"mean_token_accuracy": 0.10672209039330482,
|
|
"num_tokens": 1302792.0,
|
|
"step": 590
|
|
},
|
|
{
|
|
"entropy": 7.101827001571655,
|
|
"epoch": 0.05905121079793569,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.000297,
|
|
"loss": 6.5868,
|
|
"mean_token_accuracy": 0.09854365140199661,
|
|
"num_tokens": 1313315.0,
|
|
"step": 595
|
|
},
|
|
{
|
|
"entropy": 6.9200047016143795,
|
|
"epoch": 0.05954743946010321,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0002995,
|
|
"loss": 6.6504,
|
|
"mean_token_accuracy": 0.09922990500926972,
|
|
"num_tokens": 1326358.0,
|
|
"step": 600
|
|
},
|
|
{
|
|
"entropy": 7.008511209487915,
|
|
"epoch": 0.060043668122270744,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000302,
|
|
"loss": 6.5085,
|
|
"mean_token_accuracy": 0.1003392606973648,
|
|
"num_tokens": 1336266.0,
|
|
"step": 605
|
|
},
|
|
{
|
|
"entropy": 6.907269525527954,
|
|
"epoch": 0.06053989678443827,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0003045,
|
|
"loss": 6.4734,
|
|
"mean_token_accuracy": 0.10566542968153954,
|
|
"num_tokens": 1347610.0,
|
|
"step": 610
|
|
},
|
|
{
|
|
"entropy": 6.930313205718994,
|
|
"epoch": 0.0610361254466058,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000307,
|
|
"loss": 6.4398,
|
|
"mean_token_accuracy": 0.10840422213077545,
|
|
"num_tokens": 1358317.0,
|
|
"step": 615
|
|
},
|
|
{
|
|
"entropy": 6.901958322525024,
|
|
"epoch": 0.06153235410877332,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0003095,
|
|
"loss": 6.5551,
|
|
"mean_token_accuracy": 0.1008565068244934,
|
|
"num_tokens": 1370126.0,
|
|
"step": 620
|
|
},
|
|
{
|
|
"entropy": 6.962115097045898,
|
|
"epoch": 0.06202858277094085,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.000312,
|
|
"loss": 6.5148,
|
|
"mean_token_accuracy": 0.10650759786367417,
|
|
"num_tokens": 1381571.0,
|
|
"step": 625
|
|
},
|
|
{
|
|
"entropy": 6.91578860282898,
|
|
"epoch": 0.06252481143310838,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0003145,
|
|
"loss": 6.5516,
|
|
"mean_token_accuracy": 0.10437883734703064,
|
|
"num_tokens": 1392486.0,
|
|
"step": 630
|
|
},
|
|
{
|
|
"entropy": 6.933821678161621,
|
|
"epoch": 0.0630210400952759,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.000317,
|
|
"loss": 6.5571,
|
|
"mean_token_accuracy": 0.10577636584639549,
|
|
"num_tokens": 1403086.0,
|
|
"step": 635
|
|
},
|
|
{
|
|
"entropy": 6.9292055606842045,
|
|
"epoch": 0.06351726875744343,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0003195,
|
|
"loss": 6.5243,
|
|
"mean_token_accuracy": 0.10535438284277916,
|
|
"num_tokens": 1414537.0,
|
|
"step": 640
|
|
},
|
|
{
|
|
"entropy": 6.871757984161377,
|
|
"epoch": 0.06401349741961096,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.000322,
|
|
"loss": 6.5485,
|
|
"mean_token_accuracy": 0.10128815025091172,
|
|
"num_tokens": 1426998.0,
|
|
"step": 645
|
|
},
|
|
{
|
|
"entropy": 6.936267471313476,
|
|
"epoch": 0.06450972608177849,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00032450000000000003,
|
|
"loss": 6.5753,
|
|
"mean_token_accuracy": 0.10118880569934845,
|
|
"num_tokens": 1437667.0,
|
|
"step": 650
|
|
},
|
|
{
|
|
"entropy": 6.886267423629761,
|
|
"epoch": 0.065005954743946,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00032700000000000003,
|
|
"loss": 6.4528,
|
|
"mean_token_accuracy": 0.10906932204961776,
|
|
"num_tokens": 1448280.0,
|
|
"step": 655
|
|
},
|
|
{
|
|
"entropy": 6.921428108215332,
|
|
"epoch": 0.06550218340611354,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00032950000000000004,
|
|
"loss": 6.5105,
|
|
"mean_token_accuracy": 0.10349921584129333,
|
|
"num_tokens": 1458608.0,
|
|
"step": 660
|
|
},
|
|
{
|
|
"entropy": 6.980496501922607,
|
|
"epoch": 0.06599841206828107,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00033200000000000005,
|
|
"loss": 6.695,
|
|
"mean_token_accuracy": 0.09470629766583442,
|
|
"num_tokens": 1470435.0,
|
|
"step": 665
|
|
},
|
|
{
|
|
"entropy": 6.830832529067993,
|
|
"epoch": 0.06649464073044858,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00033450000000000005,
|
|
"loss": 6.5469,
|
|
"mean_token_accuracy": 0.10282312780618667,
|
|
"num_tokens": 1481959.0,
|
|
"step": 670
|
|
},
|
|
{
|
|
"entropy": 6.974913597106934,
|
|
"epoch": 0.06699086939261611,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000337,
|
|
"loss": 6.5976,
|
|
"mean_token_accuracy": 0.09841747283935547,
|
|
"num_tokens": 1493798.0,
|
|
"step": 675
|
|
},
|
|
{
|
|
"entropy": 6.887060308456421,
|
|
"epoch": 0.06748709805478365,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0003395,
|
|
"loss": 6.403,
|
|
"mean_token_accuracy": 0.10493207052350044,
|
|
"num_tokens": 1502969.0,
|
|
"step": 680
|
|
},
|
|
{
|
|
"entropy": 6.897101402282715,
|
|
"epoch": 0.06798332671695118,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.000342,
|
|
"loss": 6.5595,
|
|
"mean_token_accuracy": 0.10253233015537262,
|
|
"num_tokens": 1513825.0,
|
|
"step": 685
|
|
},
|
|
{
|
|
"entropy": 6.822127819061279,
|
|
"epoch": 0.06847955537911869,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00034449999999999997,
|
|
"loss": 6.4575,
|
|
"mean_token_accuracy": 0.10815273150801659,
|
|
"num_tokens": 1525328.0,
|
|
"step": 690
|
|
},
|
|
{
|
|
"entropy": 6.891428852081299,
|
|
"epoch": 0.06897578404128622,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.000347,
|
|
"loss": 6.4859,
|
|
"mean_token_accuracy": 0.10564783737063407,
|
|
"num_tokens": 1537383.0,
|
|
"step": 695
|
|
},
|
|
{
|
|
"entropy": 6.913006925582886,
|
|
"epoch": 0.06947201270345375,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0003495,
|
|
"loss": 6.5826,
|
|
"mean_token_accuracy": 0.10424128845334053,
|
|
"num_tokens": 1549671.0,
|
|
"step": 700
|
|
},
|
|
{
|
|
"entropy": 6.7738439559936525,
|
|
"epoch": 0.06996824136562128,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000352,
|
|
"loss": 6.4562,
|
|
"mean_token_accuracy": 0.1023649513721466,
|
|
"num_tokens": 1559974.0,
|
|
"step": 705
|
|
},
|
|
{
|
|
"entropy": 6.948292827606201,
|
|
"epoch": 0.0704644700277888,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0003545,
|
|
"loss": 6.5642,
|
|
"mean_token_accuracy": 0.09899581745266914,
|
|
"num_tokens": 1570890.0,
|
|
"step": 710
|
|
},
|
|
{
|
|
"entropy": 6.786388778686524,
|
|
"epoch": 0.07096069868995633,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000357,
|
|
"loss": 6.473,
|
|
"mean_token_accuracy": 0.11216894015669823,
|
|
"num_tokens": 1581434.0,
|
|
"step": 715
|
|
},
|
|
{
|
|
"entropy": 6.885098886489868,
|
|
"epoch": 0.07145692735212386,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0003595,
|
|
"loss": 6.5411,
|
|
"mean_token_accuracy": 0.1010577216744423,
|
|
"num_tokens": 1593710.0,
|
|
"step": 720
|
|
},
|
|
{
|
|
"entropy": 6.914775133132935,
|
|
"epoch": 0.07195315601429139,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000362,
|
|
"loss": 6.5039,
|
|
"mean_token_accuracy": 0.10822037607431412,
|
|
"num_tokens": 1604635.0,
|
|
"step": 725
|
|
},
|
|
{
|
|
"entropy": 6.96195125579834,
|
|
"epoch": 0.07244938467645891,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0003645,
|
|
"loss": 6.5621,
|
|
"mean_token_accuracy": 0.10865710079669952,
|
|
"num_tokens": 1615258.0,
|
|
"step": 730
|
|
},
|
|
{
|
|
"entropy": 6.818844604492187,
|
|
"epoch": 0.07294561333862644,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000367,
|
|
"loss": 6.4657,
|
|
"mean_token_accuracy": 0.1062205784022808,
|
|
"num_tokens": 1625942.0,
|
|
"step": 735
|
|
},
|
|
{
|
|
"entropy": 6.773487854003906,
|
|
"epoch": 0.07344184200079397,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0003695,
|
|
"loss": 6.4609,
|
|
"mean_token_accuracy": 0.11281525269150734,
|
|
"num_tokens": 1636270.0,
|
|
"step": 740
|
|
},
|
|
{
|
|
"entropy": 6.791012191772461,
|
|
"epoch": 0.07393807066296149,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.000372,
|
|
"loss": 6.442,
|
|
"mean_token_accuracy": 0.10923936069011689,
|
|
"num_tokens": 1647029.0,
|
|
"step": 745
|
|
},
|
|
{
|
|
"entropy": 6.894232225418091,
|
|
"epoch": 0.07443429932512902,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0003745,
|
|
"loss": 6.6043,
|
|
"mean_token_accuracy": 0.10349742248654366,
|
|
"num_tokens": 1659483.0,
|
|
"step": 750
|
|
},
|
|
{
|
|
"entropy": 6.763030767440796,
|
|
"epoch": 0.07493052798729655,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.000377,
|
|
"loss": 6.4626,
|
|
"mean_token_accuracy": 0.10359987020492553,
|
|
"num_tokens": 1669425.0,
|
|
"step": 755
|
|
},
|
|
{
|
|
"entropy": 6.839314746856689,
|
|
"epoch": 0.07542675664946408,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0003795,
|
|
"loss": 6.4669,
|
|
"mean_token_accuracy": 0.10515316724777221,
|
|
"num_tokens": 1680426.0,
|
|
"step": 760
|
|
},
|
|
{
|
|
"entropy": 6.7409745216369625,
|
|
"epoch": 0.0759229853116316,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.000382,
|
|
"loss": 6.49,
|
|
"mean_token_accuracy": 0.1022932469844818,
|
|
"num_tokens": 1692803.0,
|
|
"step": 765
|
|
},
|
|
{
|
|
"entropy": 6.86904993057251,
|
|
"epoch": 0.07641921397379912,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0003845,
|
|
"loss": 6.5127,
|
|
"mean_token_accuracy": 0.10286033898591995,
|
|
"num_tokens": 1703919.0,
|
|
"step": 770
|
|
},
|
|
{
|
|
"entropy": 6.803786706924439,
|
|
"epoch": 0.07691544263596665,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.00038700000000000003,
|
|
"loss": 6.4902,
|
|
"mean_token_accuracy": 0.11186280027031899,
|
|
"num_tokens": 1714487.0,
|
|
"step": 775
|
|
},
|
|
{
|
|
"entropy": 6.829148006439209,
|
|
"epoch": 0.07741167129813419,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00038950000000000003,
|
|
"loss": 6.5375,
|
|
"mean_token_accuracy": 0.103410904109478,
|
|
"num_tokens": 1726601.0,
|
|
"step": 780
|
|
},
|
|
{
|
|
"entropy": 6.77627649307251,
|
|
"epoch": 0.0779078999603017,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00039200000000000004,
|
|
"loss": 6.4293,
|
|
"mean_token_accuracy": 0.10090705007314682,
|
|
"num_tokens": 1738743.0,
|
|
"step": 785
|
|
},
|
|
{
|
|
"entropy": 6.75617151260376,
|
|
"epoch": 0.07840412862246923,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00039450000000000005,
|
|
"loss": 6.509,
|
|
"mean_token_accuracy": 0.10762425512075424,
|
|
"num_tokens": 1748286.0,
|
|
"step": 790
|
|
},
|
|
{
|
|
"entropy": 6.78504114151001,
|
|
"epoch": 0.07890035728463676,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00039700000000000005,
|
|
"loss": 6.5497,
|
|
"mean_token_accuracy": 0.10279078707098961,
|
|
"num_tokens": 1758917.0,
|
|
"step": 795
|
|
},
|
|
{
|
|
"entropy": 6.834147977828979,
|
|
"epoch": 0.0793965859468043,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0003995,
|
|
"loss": 6.3768,
|
|
"mean_token_accuracy": 0.11014361456036567,
|
|
"num_tokens": 1769179.0,
|
|
"step": 800
|
|
},
|
|
{
|
|
"entropy": 6.686023187637329,
|
|
"epoch": 0.07989281460897181,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.000402,
|
|
"loss": 6.5004,
|
|
"mean_token_accuracy": 0.09990919530391693,
|
|
"num_tokens": 1782369.0,
|
|
"step": 805
|
|
},
|
|
{
|
|
"entropy": 6.789707326889038,
|
|
"epoch": 0.08038904327113934,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004045,
|
|
"loss": 6.5087,
|
|
"mean_token_accuracy": 0.11087186112999917,
|
|
"num_tokens": 1795992.0,
|
|
"step": 810
|
|
},
|
|
{
|
|
"entropy": 6.767456674575806,
|
|
"epoch": 0.08088527193330687,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.00040699999999999997,
|
|
"loss": 6.4063,
|
|
"mean_token_accuracy": 0.11133067905902863,
|
|
"num_tokens": 1806938.0,
|
|
"step": 815
|
|
},
|
|
{
|
|
"entropy": 6.6453076839447025,
|
|
"epoch": 0.0813815005954744,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004095,
|
|
"loss": 6.3335,
|
|
"mean_token_accuracy": 0.1083066463470459,
|
|
"num_tokens": 1817663.0,
|
|
"step": 820
|
|
},
|
|
{
|
|
"entropy": 6.804880285263062,
|
|
"epoch": 0.08187772925764192,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.000412,
|
|
"loss": 6.4937,
|
|
"mean_token_accuracy": 0.10573754906654358,
|
|
"num_tokens": 1828254.0,
|
|
"step": 825
|
|
},
|
|
{
|
|
"entropy": 6.744491100311279,
|
|
"epoch": 0.08237395791980945,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004145,
|
|
"loss": 6.4121,
|
|
"mean_token_accuracy": 0.10808726996183396,
|
|
"num_tokens": 1839001.0,
|
|
"step": 830
|
|
},
|
|
{
|
|
"entropy": 6.780965948104859,
|
|
"epoch": 0.08287018658197698,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.000417,
|
|
"loss": 6.5072,
|
|
"mean_token_accuracy": 0.1064543254673481,
|
|
"num_tokens": 1849906.0,
|
|
"step": 835
|
|
},
|
|
{
|
|
"entropy": 6.638266897201538,
|
|
"epoch": 0.0833664152441445,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004195,
|
|
"loss": 6.4146,
|
|
"mean_token_accuracy": 0.10410640761256218,
|
|
"num_tokens": 1860982.0,
|
|
"step": 840
|
|
},
|
|
{
|
|
"entropy": 6.7845916748046875,
|
|
"epoch": 0.08386264390631203,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.000422,
|
|
"loss": 6.3668,
|
|
"mean_token_accuracy": 0.10832294374704361,
|
|
"num_tokens": 1872177.0,
|
|
"step": 845
|
|
},
|
|
{
|
|
"entropy": 6.6455484390258786,
|
|
"epoch": 0.08435887256847956,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004245,
|
|
"loss": 6.345,
|
|
"mean_token_accuracy": 0.10717036500573159,
|
|
"num_tokens": 1882783.0,
|
|
"step": 850
|
|
},
|
|
{
|
|
"entropy": 6.82792387008667,
|
|
"epoch": 0.08485510123064709,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000427,
|
|
"loss": 6.521,
|
|
"mean_token_accuracy": 0.0995104432106018,
|
|
"num_tokens": 1893706.0,
|
|
"step": 855
|
|
},
|
|
{
|
|
"entropy": 6.6573139190673825,
|
|
"epoch": 0.0853513298928146,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004295,
|
|
"loss": 6.399,
|
|
"mean_token_accuracy": 0.10572489872574806,
|
|
"num_tokens": 1903852.0,
|
|
"step": 860
|
|
},
|
|
{
|
|
"entropy": 6.720736408233643,
|
|
"epoch": 0.08584755855498213,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000432,
|
|
"loss": 6.4272,
|
|
"mean_token_accuracy": 0.10979009121656418,
|
|
"num_tokens": 1914157.0,
|
|
"step": 865
|
|
},
|
|
{
|
|
"entropy": 6.719715213775634,
|
|
"epoch": 0.08634378721714966,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004345,
|
|
"loss": 6.3646,
|
|
"mean_token_accuracy": 0.10477298423647881,
|
|
"num_tokens": 1924684.0,
|
|
"step": 870
|
|
},
|
|
{
|
|
"entropy": 6.765842390060425,
|
|
"epoch": 0.0868400158793172,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.000437,
|
|
"loss": 6.5126,
|
|
"mean_token_accuracy": 0.1022205650806427,
|
|
"num_tokens": 1935657.0,
|
|
"step": 875
|
|
},
|
|
{
|
|
"entropy": 6.674496650695801,
|
|
"epoch": 0.08733624454148471,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004395,
|
|
"loss": 6.3866,
|
|
"mean_token_accuracy": 0.10951956436038017,
|
|
"num_tokens": 1946735.0,
|
|
"step": 880
|
|
},
|
|
{
|
|
"entropy": 6.771207475662232,
|
|
"epoch": 0.08783247320365224,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000442,
|
|
"loss": 6.558,
|
|
"mean_token_accuracy": 0.10081006437540055,
|
|
"num_tokens": 1957871.0,
|
|
"step": 885
|
|
},
|
|
{
|
|
"entropy": 6.6469238758087155,
|
|
"epoch": 0.08832870186581977,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004445,
|
|
"loss": 6.4001,
|
|
"mean_token_accuracy": 0.10841071009635925,
|
|
"num_tokens": 1969032.0,
|
|
"step": 890
|
|
},
|
|
{
|
|
"entropy": 6.773042964935303,
|
|
"epoch": 0.0888249305279873,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000447,
|
|
"loss": 6.4253,
|
|
"mean_token_accuracy": 0.10482999682426453,
|
|
"num_tokens": 1980212.0,
|
|
"step": 895
|
|
},
|
|
{
|
|
"entropy": 6.5782490253448485,
|
|
"epoch": 0.08932115919015482,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.00044950000000000003,
|
|
"loss": 6.3457,
|
|
"mean_token_accuracy": 0.1083353117108345,
|
|
"num_tokens": 1990333.0,
|
|
"step": 900
|
|
},
|
|
{
|
|
"entropy": 6.723943090438842,
|
|
"epoch": 0.08981738785232235,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00045200000000000004,
|
|
"loss": 6.4208,
|
|
"mean_token_accuracy": 0.11527454107999802,
|
|
"num_tokens": 2001486.0,
|
|
"step": 905
|
|
},
|
|
{
|
|
"entropy": 6.647228240966797,
|
|
"epoch": 0.09031361651448988,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00045450000000000004,
|
|
"loss": 6.4152,
|
|
"mean_token_accuracy": 0.10908102542161942,
|
|
"num_tokens": 2012535.0,
|
|
"step": 910
|
|
},
|
|
{
|
|
"entropy": 6.65789384841919,
|
|
"epoch": 0.0908098451766574,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.00045700000000000005,
|
|
"loss": 6.3697,
|
|
"mean_token_accuracy": 0.11192298531532288,
|
|
"num_tokens": 2024116.0,
|
|
"step": 915
|
|
},
|
|
{
|
|
"entropy": 6.552388858795166,
|
|
"epoch": 0.09130607383882493,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.00045950000000000006,
|
|
"loss": 6.4129,
|
|
"mean_token_accuracy": 0.10573532730340958,
|
|
"num_tokens": 2036341.0,
|
|
"step": 920
|
|
},
|
|
{
|
|
"entropy": 6.772451591491699,
|
|
"epoch": 0.09180230250099246,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.000462,
|
|
"loss": 6.3831,
|
|
"mean_token_accuracy": 0.11066723242402077,
|
|
"num_tokens": 2046768.0,
|
|
"step": 925
|
|
},
|
|
{
|
|
"entropy": 6.601136875152588,
|
|
"epoch": 0.09229853116315999,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004645,
|
|
"loss": 6.3447,
|
|
"mean_token_accuracy": 0.10959907621145248,
|
|
"num_tokens": 2057315.0,
|
|
"step": 930
|
|
},
|
|
{
|
|
"entropy": 6.595295667648315,
|
|
"epoch": 0.0927947598253275,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.000467,
|
|
"loss": 6.3258,
|
|
"mean_token_accuracy": 0.1111043132841587,
|
|
"num_tokens": 2068267.0,
|
|
"step": 935
|
|
},
|
|
{
|
|
"entropy": 6.6356977939605715,
|
|
"epoch": 0.09329098848749504,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004695,
|
|
"loss": 6.4018,
|
|
"mean_token_accuracy": 0.10635230094194412,
|
|
"num_tokens": 2078271.0,
|
|
"step": 940
|
|
},
|
|
{
|
|
"entropy": 6.570490837097168,
|
|
"epoch": 0.09378721714966257,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000472,
|
|
"loss": 6.3186,
|
|
"mean_token_accuracy": 0.10399494022130966,
|
|
"num_tokens": 2088381.0,
|
|
"step": 945
|
|
},
|
|
{
|
|
"entropy": 6.635789442062378,
|
|
"epoch": 0.0942834458118301,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004745,
|
|
"loss": 6.2807,
|
|
"mean_token_accuracy": 0.10803479552268982,
|
|
"num_tokens": 2098899.0,
|
|
"step": 950
|
|
},
|
|
{
|
|
"entropy": 6.580207061767578,
|
|
"epoch": 0.09477967447399761,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000477,
|
|
"loss": 6.4469,
|
|
"mean_token_accuracy": 0.1090017631649971,
|
|
"num_tokens": 2110057.0,
|
|
"step": 955
|
|
},
|
|
{
|
|
"entropy": 6.590322017669678,
|
|
"epoch": 0.09527590313616514,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004795,
|
|
"loss": 6.3534,
|
|
"mean_token_accuracy": 0.10890609472990036,
|
|
"num_tokens": 2121758.0,
|
|
"step": 960
|
|
},
|
|
{
|
|
"entropy": 6.626723718643189,
|
|
"epoch": 0.09577213179833267,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.000482,
|
|
"loss": 6.3606,
|
|
"mean_token_accuracy": 0.11137763261795045,
|
|
"num_tokens": 2131840.0,
|
|
"step": 965
|
|
},
|
|
{
|
|
"entropy": 6.4795605659484865,
|
|
"epoch": 0.0962683604605002,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004845,
|
|
"loss": 6.3243,
|
|
"mean_token_accuracy": 0.11041747704148293,
|
|
"num_tokens": 2142084.0,
|
|
"step": 970
|
|
},
|
|
{
|
|
"entropy": 6.671319103240966,
|
|
"epoch": 0.09676458912266772,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000487,
|
|
"loss": 6.3937,
|
|
"mean_token_accuracy": 0.10798183381557465,
|
|
"num_tokens": 2152785.0,
|
|
"step": 975
|
|
},
|
|
{
|
|
"entropy": 6.661399173736572,
|
|
"epoch": 0.09726081778483525,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004895,
|
|
"loss": 6.3784,
|
|
"mean_token_accuracy": 0.109221463650465,
|
|
"num_tokens": 2163774.0,
|
|
"step": 980
|
|
},
|
|
{
|
|
"entropy": 6.505852460861206,
|
|
"epoch": 0.09775704644700278,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.000492,
|
|
"loss": 6.2916,
|
|
"mean_token_accuracy": 0.1088893674314022,
|
|
"num_tokens": 2175378.0,
|
|
"step": 985
|
|
},
|
|
{
|
|
"entropy": 6.755297660827637,
|
|
"epoch": 0.0982532751091703,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004945,
|
|
"loss": 6.5117,
|
|
"mean_token_accuracy": 0.1058343231678009,
|
|
"num_tokens": 2186510.0,
|
|
"step": 990
|
|
},
|
|
{
|
|
"entropy": 6.522902965545654,
|
|
"epoch": 0.09874950377133783,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.000497,
|
|
"loss": 6.2971,
|
|
"mean_token_accuracy": 0.11370693743228913,
|
|
"num_tokens": 2197482.0,
|
|
"step": 995
|
|
},
|
|
{
|
|
"entropy": 6.5511187553405765,
|
|
"epoch": 0.09924573243350536,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004995,
|
|
"loss": 6.3049,
|
|
"mean_token_accuracy": 0.10995083898305893,
|
|
"num_tokens": 2208329.0,
|
|
"step": 1000
|
|
},
|
|
{
|
|
"entropy": 6.5022056102752686,
|
|
"epoch": 0.09974196109567289,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004999999982145551,
|
|
"loss": 6.2196,
|
|
"mean_token_accuracy": 0.10750824585556984,
|
|
"num_tokens": 2218632.0,
|
|
"step": 1005
|
|
},
|
|
{
|
|
"entropy": 6.522266244888305,
|
|
"epoch": 0.1002381897578404,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004999999909611855,
|
|
"loss": 6.3288,
|
|
"mean_token_accuracy": 0.10453014001250267,
|
|
"num_tokens": 2231335.0,
|
|
"step": 1010
|
|
},
|
|
{
|
|
"entropy": 6.613006448745727,
|
|
"epoch": 0.10073441842000794,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999999781283008,
|
|
"loss": 6.3162,
|
|
"mean_token_accuracy": 0.11068271622061729,
|
|
"num_tokens": 2241704.0,
|
|
"step": 1015
|
|
},
|
|
{
|
|
"entropy": 6.541505002975464,
|
|
"epoch": 0.10123064708217547,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004999999597159017,
|
|
"loss": 6.3683,
|
|
"mean_token_accuracy": 0.10505040511488914,
|
|
"num_tokens": 2252310.0,
|
|
"step": 1020
|
|
},
|
|
{
|
|
"entropy": 6.5655745506286625,
|
|
"epoch": 0.101726875744343,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004999999357239882,
|
|
"loss": 6.289,
|
|
"mean_token_accuracy": 0.10687798410654067,
|
|
"num_tokens": 2262270.0,
|
|
"step": 1025
|
|
},
|
|
{
|
|
"entropy": 6.599134349822998,
|
|
"epoch": 0.10222310440651051,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004999999061525612,
|
|
"loss": 6.4258,
|
|
"mean_token_accuracy": 0.10728801861405372,
|
|
"num_tokens": 2273986.0,
|
|
"step": 1030
|
|
},
|
|
{
|
|
"entropy": 6.644435930252075,
|
|
"epoch": 0.10271933306867805,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999998710016214,
|
|
"loss": 6.3152,
|
|
"mean_token_accuracy": 0.10951637625694274,
|
|
"num_tokens": 2283430.0,
|
|
"step": 1035
|
|
},
|
|
{
|
|
"entropy": 6.572604465484619,
|
|
"epoch": 0.10321556173084558,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004999998302711696,
|
|
"loss": 6.3347,
|
|
"mean_token_accuracy": 0.10473796129226684,
|
|
"num_tokens": 2294201.0,
|
|
"step": 1040
|
|
},
|
|
{
|
|
"entropy": 6.451688957214356,
|
|
"epoch": 0.1037117903930131,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004999997839612069,
|
|
"loss": 6.2316,
|
|
"mean_token_accuracy": 0.10967583358287811,
|
|
"num_tokens": 2303876.0,
|
|
"step": 1045
|
|
},
|
|
{
|
|
"entropy": 6.53422532081604,
|
|
"epoch": 0.10420801905518062,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004999997320717342,
|
|
"loss": 6.2748,
|
|
"mean_token_accuracy": 0.11531499549746513,
|
|
"num_tokens": 2313713.0,
|
|
"step": 1050
|
|
},
|
|
{
|
|
"entropy": 6.462176990509033,
|
|
"epoch": 0.10470424771734815,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004999996746027531,
|
|
"loss": 6.281,
|
|
"mean_token_accuracy": 0.1057841993868351,
|
|
"num_tokens": 2324862.0,
|
|
"step": 1055
|
|
},
|
|
{
|
|
"entropy": 6.63836817741394,
|
|
"epoch": 0.10520047637951568,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000499999611554265,
|
|
"loss": 6.342,
|
|
"mean_token_accuracy": 0.11243951395153999,
|
|
"num_tokens": 2334974.0,
|
|
"step": 1060
|
|
},
|
|
{
|
|
"entropy": 6.527207708358764,
|
|
"epoch": 0.10569670504168321,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004999995429262712,
|
|
"loss": 6.3814,
|
|
"mean_token_accuracy": 0.11008421406149864,
|
|
"num_tokens": 2345945.0,
|
|
"step": 1065
|
|
},
|
|
{
|
|
"entropy": 6.573855066299439,
|
|
"epoch": 0.10619293370385073,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999994687187737,
|
|
"loss": 6.3162,
|
|
"mean_token_accuracy": 0.10868648067116737,
|
|
"num_tokens": 2356749.0,
|
|
"step": 1070
|
|
},
|
|
{
|
|
"entropy": 6.601923894882202,
|
|
"epoch": 0.10668916236601826,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004999993889317742,
|
|
"loss": 6.3894,
|
|
"mean_token_accuracy": 0.10912014171481133,
|
|
"num_tokens": 2368181.0,
|
|
"step": 1075
|
|
},
|
|
{
|
|
"entropy": 6.519433784484863,
|
|
"epoch": 0.10718539102818579,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999993035652746,
|
|
"loss": 6.2988,
|
|
"mean_token_accuracy": 0.10856023505330085,
|
|
"num_tokens": 2377737.0,
|
|
"step": 1080
|
|
},
|
|
{
|
|
"entropy": 6.498434209823609,
|
|
"epoch": 0.10768161969035331,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004999992126192771,
|
|
"loss": 6.2253,
|
|
"mean_token_accuracy": 0.11343928501009941,
|
|
"num_tokens": 2388944.0,
|
|
"step": 1085
|
|
},
|
|
{
|
|
"entropy": 6.506166744232178,
|
|
"epoch": 0.10817784835252084,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000499999116093784,
|
|
"loss": 6.3021,
|
|
"mean_token_accuracy": 0.11269065588712693,
|
|
"num_tokens": 2400758.0,
|
|
"step": 1090
|
|
},
|
|
{
|
|
"entropy": 6.475096273422241,
|
|
"epoch": 0.10867407701468837,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004999990139887976,
|
|
"loss": 6.2988,
|
|
"mean_token_accuracy": 0.11071598455309868,
|
|
"num_tokens": 2411916.0,
|
|
"step": 1095
|
|
},
|
|
{
|
|
"entropy": 6.6090761661529545,
|
|
"epoch": 0.1091703056768559,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999989063043206,
|
|
"loss": 6.3162,
|
|
"mean_token_accuracy": 0.10899331420660019,
|
|
"num_tokens": 2423310.0,
|
|
"step": 1100
|
|
},
|
|
{
|
|
"entropy": 6.4430852890014645,
|
|
"epoch": 0.10966653433902342,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004999987930403555,
|
|
"loss": 6.255,
|
|
"mean_token_accuracy": 0.11132511496543884,
|
|
"num_tokens": 2432100.0,
|
|
"step": 1105
|
|
},
|
|
{
|
|
"entropy": 6.497279357910156,
|
|
"epoch": 0.11016276300119095,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004999986741969051,
|
|
"loss": 6.3283,
|
|
"mean_token_accuracy": 0.10885677859187126,
|
|
"num_tokens": 2443563.0,
|
|
"step": 1110
|
|
},
|
|
{
|
|
"entropy": 6.568647575378418,
|
|
"epoch": 0.11065899166335848,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999985497739724,
|
|
"loss": 6.3328,
|
|
"mean_token_accuracy": 0.10904523879289627,
|
|
"num_tokens": 2455435.0,
|
|
"step": 1115
|
|
},
|
|
{
|
|
"entropy": 6.526462554931641,
|
|
"epoch": 0.11115522032552601,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004999984197715606,
|
|
"loss": 6.2693,
|
|
"mean_token_accuracy": 0.11513903066515922,
|
|
"num_tokens": 2466173.0,
|
|
"step": 1120
|
|
},
|
|
{
|
|
"entropy": 6.406380701065063,
|
|
"epoch": 0.11165144898769352,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004999982841896728,
|
|
"loss": 6.2217,
|
|
"mean_token_accuracy": 0.11128725931048393,
|
|
"num_tokens": 2476349.0,
|
|
"step": 1125
|
|
},
|
|
{
|
|
"entropy": 6.5459887981414795,
|
|
"epoch": 0.11214767764986106,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004999981430283123,
|
|
"loss": 6.3545,
|
|
"mean_token_accuracy": 0.11260213553905488,
|
|
"num_tokens": 2487864.0,
|
|
"step": 1130
|
|
},
|
|
{
|
|
"entropy": 6.459234380722046,
|
|
"epoch": 0.11264390631202859,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004999979962874827,
|
|
"loss": 6.2778,
|
|
"mean_token_accuracy": 0.11224315464496612,
|
|
"num_tokens": 2499188.0,
|
|
"step": 1135
|
|
},
|
|
{
|
|
"entropy": 6.541913795471191,
|
|
"epoch": 0.11314013497419612,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999978439671877,
|
|
"loss": 6.2679,
|
|
"mean_token_accuracy": 0.11238265410065651,
|
|
"num_tokens": 2509813.0,
|
|
"step": 1140
|
|
},
|
|
{
|
|
"entropy": 6.452944564819336,
|
|
"epoch": 0.11363636363636363,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004999976860674309,
|
|
"loss": 6.2954,
|
|
"mean_token_accuracy": 0.1079881377518177,
|
|
"num_tokens": 2520813.0,
|
|
"step": 1145
|
|
},
|
|
{
|
|
"entropy": 6.451686000823974,
|
|
"epoch": 0.11413259229853116,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999975225882164,
|
|
"loss": 6.2857,
|
|
"mean_token_accuracy": 0.11005399227142335,
|
|
"num_tokens": 2531802.0,
|
|
"step": 1150
|
|
},
|
|
{
|
|
"entropy": 6.419873952865601,
|
|
"epoch": 0.1146288209606987,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000499997353529548,
|
|
"loss": 6.0989,
|
|
"mean_token_accuracy": 0.12534342482686042,
|
|
"num_tokens": 2541935.0,
|
|
"step": 1155
|
|
},
|
|
{
|
|
"entropy": 6.41290922164917,
|
|
"epoch": 0.11512504962286621,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999971788914303,
|
|
"loss": 6.209,
|
|
"mean_token_accuracy": 0.11427329108119011,
|
|
"num_tokens": 2553224.0,
|
|
"step": 1160
|
|
},
|
|
{
|
|
"entropy": 6.4005992889404295,
|
|
"epoch": 0.11562127828503374,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004999969986738672,
|
|
"loss": 6.2408,
|
|
"mean_token_accuracy": 0.1071538008749485,
|
|
"num_tokens": 2565355.0,
|
|
"step": 1165
|
|
},
|
|
{
|
|
"entropy": 6.517459058761597,
|
|
"epoch": 0.11611750694720127,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999968128768634,
|
|
"loss": 6.3245,
|
|
"mean_token_accuracy": 0.1080057941377163,
|
|
"num_tokens": 2575962.0,
|
|
"step": 1170
|
|
},
|
|
{
|
|
"entropy": 6.512309551239014,
|
|
"epoch": 0.1166137356093688,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004999966215004236,
|
|
"loss": 6.3356,
|
|
"mean_token_accuracy": 0.11455044671893119,
|
|
"num_tokens": 2588136.0,
|
|
"step": 1175
|
|
},
|
|
{
|
|
"entropy": 6.473892450332642,
|
|
"epoch": 0.11710996427153632,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004999964245445522,
|
|
"loss": 6.2264,
|
|
"mean_token_accuracy": 0.11278848052024841,
|
|
"num_tokens": 2597785.0,
|
|
"step": 1180
|
|
},
|
|
{
|
|
"entropy": 6.45322551727295,
|
|
"epoch": 0.11760619293370385,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004999962220092545,
|
|
"loss": 6.2625,
|
|
"mean_token_accuracy": 0.12006586417555809,
|
|
"num_tokens": 2609738.0,
|
|
"step": 1185
|
|
},
|
|
{
|
|
"entropy": 6.329366683959961,
|
|
"epoch": 0.11810242159587138,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004999960138945351,
|
|
"loss": 6.1518,
|
|
"mean_token_accuracy": 0.12184964567422867,
|
|
"num_tokens": 2620179.0,
|
|
"step": 1190
|
|
},
|
|
{
|
|
"entropy": 6.402722692489624,
|
|
"epoch": 0.11859865025803891,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999958002003996,
|
|
"loss": 6.1977,
|
|
"mean_token_accuracy": 0.1172001026570797,
|
|
"num_tokens": 2631550.0,
|
|
"step": 1195
|
|
},
|
|
{
|
|
"entropy": 6.43868670463562,
|
|
"epoch": 0.11909487892020643,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004999955809268529,
|
|
"loss": 6.2334,
|
|
"mean_token_accuracy": 0.1126227967441082,
|
|
"num_tokens": 2642467.0,
|
|
"step": 1200
|
|
},
|
|
{
|
|
"entropy": 6.404077625274658,
|
|
"epoch": 0.11959110758237396,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999953560739008,
|
|
"loss": 6.2134,
|
|
"mean_token_accuracy": 0.11190939992666245,
|
|
"num_tokens": 2652132.0,
|
|
"step": 1205
|
|
},
|
|
{
|
|
"entropy": 6.447581481933594,
|
|
"epoch": 0.12008733624454149,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004999951256415485,
|
|
"loss": 6.2707,
|
|
"mean_token_accuracy": 0.11127389594912529,
|
|
"num_tokens": 2663336.0,
|
|
"step": 1210
|
|
},
|
|
{
|
|
"entropy": 6.5261087894439695,
|
|
"epoch": 0.12058356490670902,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000499994889629802,
|
|
"loss": 6.3448,
|
|
"mean_token_accuracy": 0.10134708434343338,
|
|
"num_tokens": 2674201.0,
|
|
"step": 1215
|
|
},
|
|
{
|
|
"entropy": 6.487839126586914,
|
|
"epoch": 0.12107979356887653,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.000499994648038667,
|
|
"loss": 6.2708,
|
|
"mean_token_accuracy": 0.11672815084457397,
|
|
"num_tokens": 2685073.0,
|
|
"step": 1220
|
|
},
|
|
{
|
|
"entropy": 6.450255823135376,
|
|
"epoch": 0.12157602223104406,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999944008681496,
|
|
"loss": 6.1999,
|
|
"mean_token_accuracy": 0.11382194608449936,
|
|
"num_tokens": 2695024.0,
|
|
"step": 1225
|
|
},
|
|
{
|
|
"entropy": 6.476427698135376,
|
|
"epoch": 0.1220722508932116,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004999941481182559,
|
|
"loss": 6.2898,
|
|
"mean_token_accuracy": 0.10765945836901665,
|
|
"num_tokens": 2706232.0,
|
|
"step": 1230
|
|
},
|
|
{
|
|
"entropy": 6.459441423416138,
|
|
"epoch": 0.12256847955537911,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999938897889921,
|
|
"loss": 6.2763,
|
|
"mean_token_accuracy": 0.11456048339605332,
|
|
"num_tokens": 2715874.0,
|
|
"step": 1235
|
|
},
|
|
{
|
|
"entropy": 6.38568229675293,
|
|
"epoch": 0.12306470821754664,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004999936258803647,
|
|
"loss": 6.2288,
|
|
"mean_token_accuracy": 0.11625665873289108,
|
|
"num_tokens": 2727409.0,
|
|
"step": 1240
|
|
},
|
|
{
|
|
"entropy": 6.370026016235352,
|
|
"epoch": 0.12356093687971417,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999933563923802,
|
|
"loss": 6.1212,
|
|
"mean_token_accuracy": 0.11923045217990876,
|
|
"num_tokens": 2737259.0,
|
|
"step": 1245
|
|
},
|
|
{
|
|
"entropy": 6.439346504211426,
|
|
"epoch": 0.1240571655418817,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004999930813250451,
|
|
"loss": 6.2589,
|
|
"mean_token_accuracy": 0.11177127435803413,
|
|
"num_tokens": 2748416.0,
|
|
"step": 1250
|
|
},
|
|
{
|
|
"entropy": 6.4149510860443115,
|
|
"epoch": 0.12455339420404922,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999928006783667,
|
|
"loss": 6.234,
|
|
"mean_token_accuracy": 0.11361540555953979,
|
|
"num_tokens": 2760470.0,
|
|
"step": 1255
|
|
},
|
|
{
|
|
"entropy": 6.43356351852417,
|
|
"epoch": 0.12504962286621676,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999925144523515,
|
|
"loss": 6.2615,
|
|
"mean_token_accuracy": 0.11003044992685318,
|
|
"num_tokens": 2770222.0,
|
|
"step": 1260
|
|
},
|
|
{
|
|
"entropy": 6.444881439208984,
|
|
"epoch": 0.12554585152838427,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999922226470066,
|
|
"loss": 6.1815,
|
|
"mean_token_accuracy": 0.1138396754860878,
|
|
"num_tokens": 2780212.0,
|
|
"step": 1265
|
|
},
|
|
{
|
|
"entropy": 6.312497234344482,
|
|
"epoch": 0.1260420801905518,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004999919252623397,
|
|
"loss": 6.1511,
|
|
"mean_token_accuracy": 0.11787962689995765,
|
|
"num_tokens": 2790239.0,
|
|
"step": 1270
|
|
},
|
|
{
|
|
"entropy": 6.418433570861817,
|
|
"epoch": 0.12653830885271933,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999916222983577,
|
|
"loss": 6.1859,
|
|
"mean_token_accuracy": 0.11903090998530388,
|
|
"num_tokens": 2801902.0,
|
|
"step": 1275
|
|
},
|
|
{
|
|
"entropy": 6.350197839736938,
|
|
"epoch": 0.12703453751488686,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004999913137550682,
|
|
"loss": 6.1833,
|
|
"mean_token_accuracy": 0.11472797095775604,
|
|
"num_tokens": 2813268.0,
|
|
"step": 1280
|
|
},
|
|
{
|
|
"entropy": 6.413725900650024,
|
|
"epoch": 0.1275307661770544,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004999909996324791,
|
|
"loss": 6.2532,
|
|
"mean_token_accuracy": 0.11241401582956315,
|
|
"num_tokens": 2824506.0,
|
|
"step": 1285
|
|
},
|
|
{
|
|
"entropy": 6.40827522277832,
|
|
"epoch": 0.12802699483922192,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.000499990679930598,
|
|
"loss": 6.1575,
|
|
"mean_token_accuracy": 0.11616934686899186,
|
|
"num_tokens": 2835144.0,
|
|
"step": 1290
|
|
},
|
|
{
|
|
"entropy": 6.333975553512573,
|
|
"epoch": 0.12852322350138945,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004999903546494327,
|
|
"loss": 6.1793,
|
|
"mean_token_accuracy": 0.11346072256565094,
|
|
"num_tokens": 2845382.0,
|
|
"step": 1295
|
|
},
|
|
{
|
|
"entropy": 6.406157112121582,
|
|
"epoch": 0.12901945216355698,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999900237889916,
|
|
"loss": 6.1977,
|
|
"mean_token_accuracy": 0.11914140731096268,
|
|
"num_tokens": 2854697.0,
|
|
"step": 1300
|
|
},
|
|
{
|
|
"entropy": 6.399594116210937,
|
|
"epoch": 0.12951568082572448,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999896873492827,
|
|
"loss": 6.1988,
|
|
"mean_token_accuracy": 0.11011647656559945,
|
|
"num_tokens": 2866216.0,
|
|
"step": 1305
|
|
},
|
|
{
|
|
"entropy": 6.361563110351563,
|
|
"epoch": 0.130011909487892,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004999893453303143,
|
|
"loss": 6.1669,
|
|
"mean_token_accuracy": 0.11769109070301056,
|
|
"num_tokens": 2877734.0,
|
|
"step": 1310
|
|
},
|
|
{
|
|
"entropy": 6.433618021011353,
|
|
"epoch": 0.13050813815005954,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999889977320949,
|
|
"loss": 6.2305,
|
|
"mean_token_accuracy": 0.11750640273094178,
|
|
"num_tokens": 2889445.0,
|
|
"step": 1315
|
|
},
|
|
{
|
|
"entropy": 6.24367208480835,
|
|
"epoch": 0.13100436681222707,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004999886445546332,
|
|
"loss": 6.1673,
|
|
"mean_token_accuracy": 0.1189102478325367,
|
|
"num_tokens": 2900485.0,
|
|
"step": 1320
|
|
},
|
|
{
|
|
"entropy": 6.488619422912597,
|
|
"epoch": 0.1315005954743946,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.000499988285797938,
|
|
"loss": 6.1406,
|
|
"mean_token_accuracy": 0.12021579965949059,
|
|
"num_tokens": 2909795.0,
|
|
"step": 1325
|
|
},
|
|
{
|
|
"entropy": 6.218992137908936,
|
|
"epoch": 0.13199682413656214,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.000499987921462018,
|
|
"loss": 6.1739,
|
|
"mean_token_accuracy": 0.12471199110150337,
|
|
"num_tokens": 2920153.0,
|
|
"step": 1330
|
|
},
|
|
{
|
|
"entropy": 6.459899282455444,
|
|
"epoch": 0.13249305279872967,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004999875515468825,
|
|
"loss": 6.162,
|
|
"mean_token_accuracy": 0.11742881909012795,
|
|
"num_tokens": 2930457.0,
|
|
"step": 1335
|
|
},
|
|
{
|
|
"entropy": 6.303973865509033,
|
|
"epoch": 0.13298928146089717,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004999871760525403,
|
|
"loss": 6.2265,
|
|
"mean_token_accuracy": 0.11418904587626458,
|
|
"num_tokens": 2941305.0,
|
|
"step": 1340
|
|
},
|
|
{
|
|
"entropy": 6.43122968673706,
|
|
"epoch": 0.1334855101230647,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999867949790011,
|
|
"loss": 6.1693,
|
|
"mean_token_accuracy": 0.11784612089395523,
|
|
"num_tokens": 2951798.0,
|
|
"step": 1345
|
|
},
|
|
{
|
|
"entropy": 6.290275287628174,
|
|
"epoch": 0.13398173878523223,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004999864083262743,
|
|
"loss": 6.067,
|
|
"mean_token_accuracy": 0.12247526496648789,
|
|
"num_tokens": 2962486.0,
|
|
"step": 1350
|
|
},
|
|
{
|
|
"entropy": 6.344256925582886,
|
|
"epoch": 0.13447796744739976,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004999860160943691,
|
|
"loss": 6.1817,
|
|
"mean_token_accuracy": 0.11753400415182114,
|
|
"num_tokens": 2974317.0,
|
|
"step": 1355
|
|
},
|
|
{
|
|
"entropy": 6.320338010787964,
|
|
"epoch": 0.1349741961095673,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004999856182832958,
|
|
"loss": 6.0902,
|
|
"mean_token_accuracy": 0.12005901709198952,
|
|
"num_tokens": 2985440.0,
|
|
"step": 1360
|
|
},
|
|
{
|
|
"entropy": 6.327242660522461,
|
|
"epoch": 0.13547042477173482,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004999852148930637,
|
|
"loss": 6.1637,
|
|
"mean_token_accuracy": 0.11592641919851303,
|
|
"num_tokens": 2997044.0,
|
|
"step": 1365
|
|
},
|
|
{
|
|
"entropy": 6.361653184890747,
|
|
"epoch": 0.13596665343390235,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004999848059236832,
|
|
"loss": 6.1792,
|
|
"mean_token_accuracy": 0.11417617872357369,
|
|
"num_tokens": 3005965.0,
|
|
"step": 1370
|
|
},
|
|
{
|
|
"entropy": 6.298781776428223,
|
|
"epoch": 0.13646288209606988,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004999843913751643,
|
|
"loss": 6.0483,
|
|
"mean_token_accuracy": 0.11773452535271645,
|
|
"num_tokens": 3015031.0,
|
|
"step": 1375
|
|
},
|
|
{
|
|
"entropy": 6.287301540374756,
|
|
"epoch": 0.13695911075823738,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004999839712475174,
|
|
"loss": 6.1151,
|
|
"mean_token_accuracy": 0.1147402547299862,
|
|
"num_tokens": 3026275.0,
|
|
"step": 1380
|
|
},
|
|
{
|
|
"entropy": 6.302942562103271,
|
|
"epoch": 0.13745533942040492,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004999835455407526,
|
|
"loss": 6.1485,
|
|
"mean_token_accuracy": 0.11648812666535377,
|
|
"num_tokens": 3036778.0,
|
|
"step": 1385
|
|
},
|
|
{
|
|
"entropy": 6.41059980392456,
|
|
"epoch": 0.13795156808257245,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999831142548808,
|
|
"loss": 6.2536,
|
|
"mean_token_accuracy": 0.11463667005300522,
|
|
"num_tokens": 3048149.0,
|
|
"step": 1390
|
|
},
|
|
{
|
|
"entropy": 6.343495893478393,
|
|
"epoch": 0.13844779674473998,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999826773899124,
|
|
"loss": 6.1206,
|
|
"mean_token_accuracy": 0.11659936383366584,
|
|
"num_tokens": 3059149.0,
|
|
"step": 1395
|
|
},
|
|
{
|
|
"entropy": 6.2959178447723385,
|
|
"epoch": 0.1389440254069075,
|
|
"grad_norm": 0.78515625,
|
|
"learning_rate": 0.0004999822349458586,
|
|
"loss": 6.1424,
|
|
"mean_token_accuracy": 0.12055872678756714,
|
|
"num_tokens": 3071613.0,
|
|
"step": 1400
|
|
},
|
|
{
|
|
"entropy": 6.433216142654419,
|
|
"epoch": 0.13944025406907504,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004999817869227301,
|
|
"loss": 6.2831,
|
|
"mean_token_accuracy": 0.11233281642198563,
|
|
"num_tokens": 3084742.0,
|
|
"step": 1405
|
|
},
|
|
{
|
|
"entropy": 6.355742263793945,
|
|
"epoch": 0.13993648273124257,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004999813333205381,
|
|
"loss": 6.1927,
|
|
"mean_token_accuracy": 0.11989191100001335,
|
|
"num_tokens": 3095356.0,
|
|
"step": 1410
|
|
},
|
|
{
|
|
"entropy": 6.345205307006836,
|
|
"epoch": 0.14043271139341007,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004999808741392937,
|
|
"loss": 6.1828,
|
|
"mean_token_accuracy": 0.11414567157626151,
|
|
"num_tokens": 3107717.0,
|
|
"step": 1415
|
|
},
|
|
{
|
|
"entropy": 6.309127426147461,
|
|
"epoch": 0.1409289400555776,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004999804093790086,
|
|
"loss": 6.1671,
|
|
"mean_token_accuracy": 0.11339711248874665,
|
|
"num_tokens": 3119205.0,
|
|
"step": 1420
|
|
},
|
|
{
|
|
"entropy": 6.414076328277588,
|
|
"epoch": 0.14142516871774513,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.000499979939039694,
|
|
"loss": 6.2164,
|
|
"mean_token_accuracy": 0.11629738509655,
|
|
"num_tokens": 3130564.0,
|
|
"step": 1425
|
|
},
|
|
{
|
|
"entropy": 6.257117033004761,
|
|
"epoch": 0.14192139737991266,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004999794631213618,
|
|
"loss": 6.1496,
|
|
"mean_token_accuracy": 0.11587404683232308,
|
|
"num_tokens": 3141883.0,
|
|
"step": 1430
|
|
},
|
|
{
|
|
"entropy": 6.4088245868682865,
|
|
"epoch": 0.1424176260420802,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004999789816240236,
|
|
"loss": 6.1524,
|
|
"mean_token_accuracy": 0.11169286966323852,
|
|
"num_tokens": 3152817.0,
|
|
"step": 1435
|
|
},
|
|
{
|
|
"entropy": 6.226463317871094,
|
|
"epoch": 0.14291385470424772,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999784945476915,
|
|
"loss": 6.0639,
|
|
"mean_token_accuracy": 0.12211388051509857,
|
|
"num_tokens": 3163546.0,
|
|
"step": 1440
|
|
},
|
|
{
|
|
"entropy": 6.368065643310547,
|
|
"epoch": 0.14341008336641525,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999780018923775,
|
|
"loss": 6.1194,
|
|
"mean_token_accuracy": 0.11407855600118637,
|
|
"num_tokens": 3173899.0,
|
|
"step": 1445
|
|
},
|
|
{
|
|
"entropy": 6.161925745010376,
|
|
"epoch": 0.14390631202858278,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004999775036580939,
|
|
"loss": 6.0337,
|
|
"mean_token_accuracy": 0.11928667798638344,
|
|
"num_tokens": 3184433.0,
|
|
"step": 1450
|
|
},
|
|
{
|
|
"entropy": 6.412479734420776,
|
|
"epoch": 0.1444025406907503,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999769998448529,
|
|
"loss": 6.1516,
|
|
"mean_token_accuracy": 0.11415581554174423,
|
|
"num_tokens": 3196077.0,
|
|
"step": 1455
|
|
},
|
|
{
|
|
"entropy": 6.141682243347168,
|
|
"epoch": 0.14489876935291782,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999764904526672,
|
|
"loss": 6.0621,
|
|
"mean_token_accuracy": 0.12485457435250283,
|
|
"num_tokens": 3206645.0,
|
|
"step": 1460
|
|
},
|
|
{
|
|
"entropy": 6.4062056064605715,
|
|
"epoch": 0.14539499801508535,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999759754815492,
|
|
"loss": 6.185,
|
|
"mean_token_accuracy": 0.12362410277128219,
|
|
"num_tokens": 3216786.0,
|
|
"step": 1465
|
|
},
|
|
{
|
|
"entropy": 6.270987462997437,
|
|
"epoch": 0.14589122667725288,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004999754549315118,
|
|
"loss": 6.1125,
|
|
"mean_token_accuracy": 0.1173293948173523,
|
|
"num_tokens": 3227384.0,
|
|
"step": 1470
|
|
},
|
|
{
|
|
"entropy": 6.215911531448365,
|
|
"epoch": 0.1463874553394204,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.000499974928802568,
|
|
"loss": 5.9691,
|
|
"mean_token_accuracy": 0.12435413226485252,
|
|
"num_tokens": 3238800.0,
|
|
"step": 1475
|
|
},
|
|
{
|
|
"entropy": 6.228160572052002,
|
|
"epoch": 0.14688368400158794,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999743970947306,
|
|
"loss": 6.1209,
|
|
"mean_token_accuracy": 0.11474767550826073,
|
|
"num_tokens": 3248627.0,
|
|
"step": 1480
|
|
},
|
|
{
|
|
"entropy": 6.310603427886963,
|
|
"epoch": 0.14737991266375547,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.000499973859808013,
|
|
"loss": 6.1474,
|
|
"mean_token_accuracy": 0.11879593282938003,
|
|
"num_tokens": 3258989.0,
|
|
"step": 1485
|
|
},
|
|
{
|
|
"entropy": 6.224552726745605,
|
|
"epoch": 0.14787614132592297,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999733169424284,
|
|
"loss": 6.1196,
|
|
"mean_token_accuracy": 0.12131216377019882,
|
|
"num_tokens": 3269474.0,
|
|
"step": 1490
|
|
},
|
|
{
|
|
"entropy": 6.298264455795288,
|
|
"epoch": 0.1483723699880905,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004999727684979904,
|
|
"loss": 6.1048,
|
|
"mean_token_accuracy": 0.11965034380555153,
|
|
"num_tokens": 3280453.0,
|
|
"step": 1495
|
|
},
|
|
{
|
|
"entropy": 6.228455209732056,
|
|
"epoch": 0.14886859865025803,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004999722144747125,
|
|
"loss": 6.0331,
|
|
"mean_token_accuracy": 0.11981930211186409,
|
|
"num_tokens": 3290234.0,
|
|
"step": 1500
|
|
},
|
|
{
|
|
"entropy": 6.207645463943481,
|
|
"epoch": 0.14936482731242556,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999716548726085,
|
|
"loss": 6.0146,
|
|
"mean_token_accuracy": 0.12176985815167427,
|
|
"num_tokens": 3300943.0,
|
|
"step": 1505
|
|
},
|
|
{
|
|
"entropy": 6.184590911865234,
|
|
"epoch": 0.1498610559745931,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999710896916921,
|
|
"loss": 5.9902,
|
|
"mean_token_accuracy": 0.12336606532335281,
|
|
"num_tokens": 3311296.0,
|
|
"step": 1510
|
|
},
|
|
{
|
|
"entropy": 6.256126356124878,
|
|
"epoch": 0.15035728463676062,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999705189319774,
|
|
"loss": 6.1279,
|
|
"mean_token_accuracy": 0.11304511949419975,
|
|
"num_tokens": 3322310.0,
|
|
"step": 1515
|
|
},
|
|
{
|
|
"entropy": 6.240859413146973,
|
|
"epoch": 0.15085351329892815,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004999699425934788,
|
|
"loss": 6.1363,
|
|
"mean_token_accuracy": 0.11859385669231415,
|
|
"num_tokens": 3334176.0,
|
|
"step": 1520
|
|
},
|
|
{
|
|
"entropy": 6.342157602310181,
|
|
"epoch": 0.15134974196109569,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004999693606762103,
|
|
"loss": 6.1278,
|
|
"mean_token_accuracy": 0.11730345636606217,
|
|
"num_tokens": 3344839.0,
|
|
"step": 1525
|
|
},
|
|
{
|
|
"entropy": 6.24994010925293,
|
|
"epoch": 0.1518459706232632,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004999687731801865,
|
|
"loss": 6.1041,
|
|
"mean_token_accuracy": 0.11314293071627617,
|
|
"num_tokens": 3357046.0,
|
|
"step": 1530
|
|
},
|
|
{
|
|
"entropy": 6.32585072517395,
|
|
"epoch": 0.15234219928543072,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999681801054217,
|
|
"loss": 6.1754,
|
|
"mean_token_accuracy": 0.11708802953362465,
|
|
"num_tokens": 3367783.0,
|
|
"step": 1535
|
|
},
|
|
{
|
|
"entropy": 6.213843870162964,
|
|
"epoch": 0.15283842794759825,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000499967581451931,
|
|
"loss": 6.0432,
|
|
"mean_token_accuracy": 0.11833713948726654,
|
|
"num_tokens": 3378529.0,
|
|
"step": 1540
|
|
},
|
|
{
|
|
"entropy": 6.292020654678344,
|
|
"epoch": 0.15333465660976578,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000499966977219729,
|
|
"loss": 6.2356,
|
|
"mean_token_accuracy": 0.11526345536112785,
|
|
"num_tokens": 3389318.0,
|
|
"step": 1545
|
|
},
|
|
{
|
|
"entropy": 6.392855215072632,
|
|
"epoch": 0.1538308852719333,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004999663674088306,
|
|
"loss": 6.2284,
|
|
"mean_token_accuracy": 0.11469097509980201,
|
|
"num_tokens": 3400603.0,
|
|
"step": 1550
|
|
},
|
|
{
|
|
"entropy": 6.286278486251831,
|
|
"epoch": 0.15432711393410084,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999657520192511,
|
|
"loss": 6.1222,
|
|
"mean_token_accuracy": 0.11655379831790924,
|
|
"num_tokens": 3410316.0,
|
|
"step": 1555
|
|
},
|
|
{
|
|
"entropy": 6.2597517490386965,
|
|
"epoch": 0.15482334259626837,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004999651310510058,
|
|
"loss": 6.0634,
|
|
"mean_token_accuracy": 0.12244669795036316,
|
|
"num_tokens": 3422155.0,
|
|
"step": 1560
|
|
},
|
|
{
|
|
"entropy": 6.282853603363037,
|
|
"epoch": 0.15531957125843587,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004999645045041099,
|
|
"loss": 6.0028,
|
|
"mean_token_accuracy": 0.1191568560898304,
|
|
"num_tokens": 3432892.0,
|
|
"step": 1565
|
|
},
|
|
{
|
|
"entropy": 6.221517276763916,
|
|
"epoch": 0.1558157999206034,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004999638723785791,
|
|
"loss": 6.1304,
|
|
"mean_token_accuracy": 0.12089115679264069,
|
|
"num_tokens": 3443967.0,
|
|
"step": 1570
|
|
},
|
|
{
|
|
"entropy": 6.202426433563232,
|
|
"epoch": 0.15631202858277093,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.000499963234674429,
|
|
"loss": 6.0213,
|
|
"mean_token_accuracy": 0.12375078648328781,
|
|
"num_tokens": 3454354.0,
|
|
"step": 1575
|
|
},
|
|
{
|
|
"entropy": 6.131307458877563,
|
|
"epoch": 0.15680825724493846,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004999625913916754,
|
|
"loss": 6.0405,
|
|
"mean_token_accuracy": 0.11991182640194893,
|
|
"num_tokens": 3465232.0,
|
|
"step": 1580
|
|
},
|
|
{
|
|
"entropy": 6.1873551368713375,
|
|
"epoch": 0.157304485907106,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999619425303343,
|
|
"loss": 6.0184,
|
|
"mean_token_accuracy": 0.12445951774716377,
|
|
"num_tokens": 3475443.0,
|
|
"step": 1585
|
|
},
|
|
{
|
|
"entropy": 6.2718860626220705,
|
|
"epoch": 0.15780071456927353,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004999612880904219,
|
|
"loss": 6.0401,
|
|
"mean_token_accuracy": 0.12001754567027093,
|
|
"num_tokens": 3486643.0,
|
|
"step": 1590
|
|
},
|
|
{
|
|
"entropy": 6.218065166473389,
|
|
"epoch": 0.15829694323144106,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004999606280719542,
|
|
"loss": 6.1047,
|
|
"mean_token_accuracy": 0.1197525791823864,
|
|
"num_tokens": 3497557.0,
|
|
"step": 1595
|
|
},
|
|
{
|
|
"entropy": 6.363813638687134,
|
|
"epoch": 0.1587931718936086,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999599624749475,
|
|
"loss": 6.1079,
|
|
"mean_token_accuracy": 0.1160752110183239,
|
|
"num_tokens": 3509790.0,
|
|
"step": 1600
|
|
},
|
|
{
|
|
"entropy": 6.141760301589966,
|
|
"epoch": 0.1592894005557761,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004999592912994187,
|
|
"loss": 6.0233,
|
|
"mean_token_accuracy": 0.11927468180656434,
|
|
"num_tokens": 3521577.0,
|
|
"step": 1605
|
|
},
|
|
{
|
|
"entropy": 6.263496160507202,
|
|
"epoch": 0.15978562921794362,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004999586145453842,
|
|
"loss": 6.0717,
|
|
"mean_token_accuracy": 0.11626604050397873,
|
|
"num_tokens": 3532126.0,
|
|
"step": 1610
|
|
},
|
|
{
|
|
"entropy": 6.084614086151123,
|
|
"epoch": 0.16028185788011115,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999579322128608,
|
|
"loss": 5.9055,
|
|
"mean_token_accuracy": 0.12044439241290092,
|
|
"num_tokens": 3542560.0,
|
|
"step": 1615
|
|
},
|
|
{
|
|
"entropy": 6.201308965682983,
|
|
"epoch": 0.16077808654227868,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004999572443018654,
|
|
"loss": 6.065,
|
|
"mean_token_accuracy": 0.11997904106974602,
|
|
"num_tokens": 3553863.0,
|
|
"step": 1620
|
|
},
|
|
{
|
|
"entropy": 6.1602541446685795,
|
|
"epoch": 0.1612743152044462,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004999565508124151,
|
|
"loss": 6.0874,
|
|
"mean_token_accuracy": 0.12250801846385002,
|
|
"num_tokens": 3564953.0,
|
|
"step": 1625
|
|
},
|
|
{
|
|
"entropy": 6.266576147079467,
|
|
"epoch": 0.16177054386661374,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.000499955851744527,
|
|
"loss": 6.0789,
|
|
"mean_token_accuracy": 0.12218151539564133,
|
|
"num_tokens": 3576247.0,
|
|
"step": 1630
|
|
},
|
|
{
|
|
"entropy": 6.306499862670899,
|
|
"epoch": 0.16226677252878127,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004999551470982185,
|
|
"loss": 6.1101,
|
|
"mean_token_accuracy": 0.11723152995109558,
|
|
"num_tokens": 3587600.0,
|
|
"step": 1635
|
|
},
|
|
{
|
|
"entropy": 6.263530349731445,
|
|
"epoch": 0.1627630011909488,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999544368735073,
|
|
"loss": 6.0821,
|
|
"mean_token_accuracy": 0.12516205981373787,
|
|
"num_tokens": 3597727.0,
|
|
"step": 1640
|
|
},
|
|
{
|
|
"entropy": 6.230346632003784,
|
|
"epoch": 0.1632592298531163,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004999537210704106,
|
|
"loss": 6.0679,
|
|
"mean_token_accuracy": 0.12371558174490929,
|
|
"num_tokens": 3608066.0,
|
|
"step": 1645
|
|
},
|
|
{
|
|
"entropy": 6.272209596633911,
|
|
"epoch": 0.16375545851528384,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004999529996889463,
|
|
"loss": 6.1215,
|
|
"mean_token_accuracy": 0.11630801856517792,
|
|
"num_tokens": 3618263.0,
|
|
"step": 1650
|
|
},
|
|
{
|
|
"entropy": 6.252897644042969,
|
|
"epoch": 0.16425168717745137,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999522727291325,
|
|
"loss": 6.07,
|
|
"mean_token_accuracy": 0.12269503250718117,
|
|
"num_tokens": 3629465.0,
|
|
"step": 1655
|
|
},
|
|
{
|
|
"entropy": 6.205037641525268,
|
|
"epoch": 0.1647479158396189,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000499951540190987,
|
|
"loss": 6.0946,
|
|
"mean_token_accuracy": 0.11775854378938674,
|
|
"num_tokens": 3639657.0,
|
|
"step": 1660
|
|
},
|
|
{
|
|
"entropy": 6.27462944984436,
|
|
"epoch": 0.16524414450178643,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004999508020745281,
|
|
"loss": 6.0516,
|
|
"mean_token_accuracy": 0.11680529490113259,
|
|
"num_tokens": 3652374.0,
|
|
"step": 1665
|
|
},
|
|
{
|
|
"entropy": 6.219149589538574,
|
|
"epoch": 0.16574037316395396,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004999500583797739,
|
|
"loss": 6.0272,
|
|
"mean_token_accuracy": 0.12123104184865952,
|
|
"num_tokens": 3664083.0,
|
|
"step": 1670
|
|
},
|
|
{
|
|
"entropy": 6.1698380470275875,
|
|
"epoch": 0.1662366018261215,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004999493091067431,
|
|
"loss": 6.0679,
|
|
"mean_token_accuracy": 0.12645655497908592,
|
|
"num_tokens": 3675314.0,
|
|
"step": 1675
|
|
},
|
|
{
|
|
"entropy": 6.184545946121216,
|
|
"epoch": 0.166732830488289,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004999485542554541,
|
|
"loss": 6.0337,
|
|
"mean_token_accuracy": 0.11284921467304229,
|
|
"num_tokens": 3686019.0,
|
|
"step": 1680
|
|
},
|
|
{
|
|
"entropy": 6.288911151885986,
|
|
"epoch": 0.16722905915045652,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004999477938259256,
|
|
"loss": 6.1241,
|
|
"mean_token_accuracy": 0.1167833961546421,
|
|
"num_tokens": 3698170.0,
|
|
"step": 1685
|
|
},
|
|
{
|
|
"entropy": 6.210192346572876,
|
|
"epoch": 0.16772528781262405,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004999470278181766,
|
|
"loss": 6.1146,
|
|
"mean_token_accuracy": 0.11569419503211975,
|
|
"num_tokens": 3709243.0,
|
|
"step": 1690
|
|
},
|
|
{
|
|
"entropy": 6.2869891166687015,
|
|
"epoch": 0.16822151647479158,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004999462562322261,
|
|
"loss": 6.0797,
|
|
"mean_token_accuracy": 0.12025846838951111,
|
|
"num_tokens": 3720196.0,
|
|
"step": 1695
|
|
},
|
|
{
|
|
"entropy": 6.290680551528931,
|
|
"epoch": 0.1687177451369591,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.000499945479068093,
|
|
"loss": 6.1355,
|
|
"mean_token_accuracy": 0.12103915438055993,
|
|
"num_tokens": 3732714.0,
|
|
"step": 1700
|
|
},
|
|
{
|
|
"entropy": 6.222851324081421,
|
|
"epoch": 0.16921397379912664,
|
|
"grad_norm": 0.7890625,
|
|
"learning_rate": 0.0004999446963257969,
|
|
"loss": 6.0964,
|
|
"mean_token_accuracy": 0.11665565371513367,
|
|
"num_tokens": 3746474.0,
|
|
"step": 1705
|
|
},
|
|
{
|
|
"entropy": 6.142470836639404,
|
|
"epoch": 0.16971020246129417,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004999439080053571,
|
|
"loss": 5.9737,
|
|
"mean_token_accuracy": 0.12647735849022865,
|
|
"num_tokens": 3757528.0,
|
|
"step": 1710
|
|
},
|
|
{
|
|
"entropy": 6.312270736694336,
|
|
"epoch": 0.1702064311234617,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004999431141067928,
|
|
"loss": 6.1028,
|
|
"mean_token_accuracy": 0.1200647495687008,
|
|
"num_tokens": 3768360.0,
|
|
"step": 1715
|
|
},
|
|
{
|
|
"entropy": 6.174591398239135,
|
|
"epoch": 0.1707026597856292,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004999423146301242,
|
|
"loss": 5.9725,
|
|
"mean_token_accuracy": 0.1192103810608387,
|
|
"num_tokens": 3779809.0,
|
|
"step": 1720
|
|
},
|
|
{
|
|
"entropy": 6.11200361251831,
|
|
"epoch": 0.17119888844779674,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004999415095753709,
|
|
"loss": 5.9783,
|
|
"mean_token_accuracy": 0.12067282646894455,
|
|
"num_tokens": 3791455.0,
|
|
"step": 1725
|
|
},
|
|
{
|
|
"entropy": 6.143737411499023,
|
|
"epoch": 0.17169511710996427,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004999406989425527,
|
|
"loss": 5.9996,
|
|
"mean_token_accuracy": 0.12016435712575912,
|
|
"num_tokens": 3803209.0,
|
|
"step": 1730
|
|
},
|
|
{
|
|
"entropy": 6.139561700820923,
|
|
"epoch": 0.1721913457721318,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999398827316901,
|
|
"loss": 6.0474,
|
|
"mean_token_accuracy": 0.12039401978254319,
|
|
"num_tokens": 3813553.0,
|
|
"step": 1735
|
|
},
|
|
{
|
|
"entropy": 6.202684926986694,
|
|
"epoch": 0.17268757443429933,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.000499939060942803,
|
|
"loss": 6.0878,
|
|
"mean_token_accuracy": 0.11598005071282387,
|
|
"num_tokens": 3824856.0,
|
|
"step": 1740
|
|
},
|
|
{
|
|
"entropy": 6.242949295043945,
|
|
"epoch": 0.17318380309646686,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999382335759119,
|
|
"loss": 6.1542,
|
|
"mean_token_accuracy": 0.11370768472552299,
|
|
"num_tokens": 3835489.0,
|
|
"step": 1745
|
|
},
|
|
{
|
|
"entropy": 6.265321969985962,
|
|
"epoch": 0.1736800317586344,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999374006310372,
|
|
"loss": 6.0015,
|
|
"mean_token_accuracy": 0.12164871916174888,
|
|
"num_tokens": 3844838.0,
|
|
"step": 1750
|
|
},
|
|
{
|
|
"entropy": 6.10846905708313,
|
|
"epoch": 0.1741762604208019,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004999365621081999,
|
|
"loss": 5.9625,
|
|
"mean_token_accuracy": 0.11757483780384063,
|
|
"num_tokens": 3855288.0,
|
|
"step": 1755
|
|
},
|
|
{
|
|
"entropy": 6.1842241287231445,
|
|
"epoch": 0.17467248908296942,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999357180074204,
|
|
"loss": 6.0165,
|
|
"mean_token_accuracy": 0.12564777955412865,
|
|
"num_tokens": 3865585.0,
|
|
"step": 1760
|
|
},
|
|
{
|
|
"entropy": 6.159081268310547,
|
|
"epoch": 0.17516871774513695,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004999348683287199,
|
|
"loss": 5.9979,
|
|
"mean_token_accuracy": 0.11737576574087143,
|
|
"num_tokens": 3877694.0,
|
|
"step": 1765
|
|
},
|
|
{
|
|
"entropy": 6.146845006942749,
|
|
"epoch": 0.17566494640730448,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004999340130721192,
|
|
"loss": 5.9587,
|
|
"mean_token_accuracy": 0.13080541640520096,
|
|
"num_tokens": 3888802.0,
|
|
"step": 1770
|
|
},
|
|
{
|
|
"entropy": 6.100156831741333,
|
|
"epoch": 0.17616117506947201,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004999331522376396,
|
|
"loss": 5.9332,
|
|
"mean_token_accuracy": 0.12021833211183548,
|
|
"num_tokens": 3900294.0,
|
|
"step": 1775
|
|
},
|
|
{
|
|
"entropy": 6.149476766586304,
|
|
"epoch": 0.17665740373163955,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999322858253027,
|
|
"loss": 5.9754,
|
|
"mean_token_accuracy": 0.12123704552650452,
|
|
"num_tokens": 3910865.0,
|
|
"step": 1780
|
|
},
|
|
{
|
|
"entropy": 6.165459203720093,
|
|
"epoch": 0.17715363239380708,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999314138351297,
|
|
"loss": 6.0263,
|
|
"mean_token_accuracy": 0.12229800149798394,
|
|
"num_tokens": 3921960.0,
|
|
"step": 1785
|
|
},
|
|
{
|
|
"entropy": 6.191252756118774,
|
|
"epoch": 0.1776498610559746,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999305362671424,
|
|
"loss": 6.0387,
|
|
"mean_token_accuracy": 0.11913010105490685,
|
|
"num_tokens": 3934085.0,
|
|
"step": 1790
|
|
},
|
|
{
|
|
"entropy": 6.127382612228393,
|
|
"epoch": 0.1781460897181421,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004999296531213624,
|
|
"loss": 5.8928,
|
|
"mean_token_accuracy": 0.13389062657952308,
|
|
"num_tokens": 3944532.0,
|
|
"step": 1795
|
|
},
|
|
{
|
|
"entropy": 6.108739185333252,
|
|
"epoch": 0.17864231838030964,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999287643978117,
|
|
"loss": 5.9284,
|
|
"mean_token_accuracy": 0.1266961745917797,
|
|
"num_tokens": 3954995.0,
|
|
"step": 1800
|
|
},
|
|
{
|
|
"entropy": 6.063549137115478,
|
|
"epoch": 0.17913854704247717,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004999278700965124,
|
|
"loss": 5.99,
|
|
"mean_token_accuracy": 0.1248068444430828,
|
|
"num_tokens": 3966621.0,
|
|
"step": 1805
|
|
},
|
|
{
|
|
"entropy": 6.155789041519165,
|
|
"epoch": 0.1796347757046447,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004999269702174866,
|
|
"loss": 6.0518,
|
|
"mean_token_accuracy": 0.12221262827515603,
|
|
"num_tokens": 3977568.0,
|
|
"step": 1810
|
|
},
|
|
{
|
|
"entropy": 6.161475467681885,
|
|
"epoch": 0.18013100436681223,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999260647607565,
|
|
"loss": 6.0683,
|
|
"mean_token_accuracy": 0.11906974241137505,
|
|
"num_tokens": 3988571.0,
|
|
"step": 1815
|
|
},
|
|
{
|
|
"entropy": 6.180405378341675,
|
|
"epoch": 0.18062723302897976,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999251537263448,
|
|
"loss": 5.8891,
|
|
"mean_token_accuracy": 0.12807116732001306,
|
|
"num_tokens": 3998380.0,
|
|
"step": 1820
|
|
},
|
|
{
|
|
"entropy": 6.073153924942017,
|
|
"epoch": 0.1811234616911473,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004999242371142739,
|
|
"loss": 6.0713,
|
|
"mean_token_accuracy": 0.12228276878595352,
|
|
"num_tokens": 4010017.0,
|
|
"step": 1825
|
|
},
|
|
{
|
|
"entropy": 6.301033782958984,
|
|
"epoch": 0.1816196903533148,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004999233149245665,
|
|
"loss": 6.0383,
|
|
"mean_token_accuracy": 0.12104798778891564,
|
|
"num_tokens": 4020922.0,
|
|
"step": 1830
|
|
},
|
|
{
|
|
"entropy": 6.202951669692993,
|
|
"epoch": 0.18211591901548232,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004999223871572456,
|
|
"loss": 6.0035,
|
|
"mean_token_accuracy": 0.12094608992338181,
|
|
"num_tokens": 4030927.0,
|
|
"step": 1835
|
|
},
|
|
{
|
|
"entropy": 6.1489091396331785,
|
|
"epoch": 0.18261214767764986,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999214538123342,
|
|
"loss": 6.0733,
|
|
"mean_token_accuracy": 0.11611957773566246,
|
|
"num_tokens": 4041375.0,
|
|
"step": 1840
|
|
},
|
|
{
|
|
"entropy": 6.178863096237182,
|
|
"epoch": 0.18310837633981739,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004999205148898554,
|
|
"loss": 6.0746,
|
|
"mean_token_accuracy": 0.11968084275722504,
|
|
"num_tokens": 4053213.0,
|
|
"step": 1845
|
|
},
|
|
{
|
|
"entropy": 6.172112369537354,
|
|
"epoch": 0.18360460500198492,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999195703898325,
|
|
"loss": 5.9206,
|
|
"mean_token_accuracy": 0.12607544884085656,
|
|
"num_tokens": 4064536.0,
|
|
"step": 1850
|
|
},
|
|
{
|
|
"entropy": 6.156340265274048,
|
|
"epoch": 0.18410083366415245,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999186203122889,
|
|
"loss": 5.9853,
|
|
"mean_token_accuracy": 0.12510076612234117,
|
|
"num_tokens": 4075282.0,
|
|
"step": 1855
|
|
},
|
|
{
|
|
"entropy": 6.041736364364624,
|
|
"epoch": 0.18459706232631998,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999176646572482,
|
|
"loss": 5.9996,
|
|
"mean_token_accuracy": 0.12671509012579918,
|
|
"num_tokens": 4085501.0,
|
|
"step": 1860
|
|
},
|
|
{
|
|
"entropy": 6.163187837600708,
|
|
"epoch": 0.1850932909884875,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000499916703424734,
|
|
"loss": 5.9386,
|
|
"mean_token_accuracy": 0.11762271374464035,
|
|
"num_tokens": 4095697.0,
|
|
"step": 1865
|
|
},
|
|
{
|
|
"entropy": 6.143773317337036,
|
|
"epoch": 0.185589519650655,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004999157366147702,
|
|
"loss": 6.0013,
|
|
"mean_token_accuracy": 0.12127534747123718,
|
|
"num_tokens": 4106459.0,
|
|
"step": 1870
|
|
},
|
|
{
|
|
"entropy": 6.127069616317749,
|
|
"epoch": 0.18608574831282254,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004999147642273809,
|
|
"loss": 5.9328,
|
|
"mean_token_accuracy": 0.12429732158780098,
|
|
"num_tokens": 4118320.0,
|
|
"step": 1875
|
|
},
|
|
{
|
|
"entropy": 6.075209379196167,
|
|
"epoch": 0.18658197697499007,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00049991378626259,
|
|
"loss": 5.9491,
|
|
"mean_token_accuracy": 0.13264545872807504,
|
|
"num_tokens": 4131249.0,
|
|
"step": 1880
|
|
},
|
|
{
|
|
"entropy": 6.168709850311279,
|
|
"epoch": 0.1870782056371576,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999128027204219,
|
|
"loss": 6.0205,
|
|
"mean_token_accuracy": 0.1249746061861515,
|
|
"num_tokens": 4141480.0,
|
|
"step": 1885
|
|
},
|
|
{
|
|
"entropy": 6.181358861923218,
|
|
"epoch": 0.18757443429932513,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000499911813600901,
|
|
"loss": 6.0712,
|
|
"mean_token_accuracy": 0.12171259969472885,
|
|
"num_tokens": 4152344.0,
|
|
"step": 1890
|
|
},
|
|
{
|
|
"entropy": 6.18400239944458,
|
|
"epoch": 0.18807066296149266,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004999108189040516,
|
|
"loss": 6.0532,
|
|
"mean_token_accuracy": 0.1188795156776905,
|
|
"num_tokens": 4164772.0,
|
|
"step": 1895
|
|
},
|
|
{
|
|
"entropy": 6.120943212509156,
|
|
"epoch": 0.1885668916236602,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004999098186298986,
|
|
"loss": 5.9959,
|
|
"mean_token_accuracy": 0.11978129372000694,
|
|
"num_tokens": 4175511.0,
|
|
"step": 1900
|
|
},
|
|
{
|
|
"entropy": 6.083007574081421,
|
|
"epoch": 0.1890631202858277,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004999088127784667,
|
|
"loss": 5.9597,
|
|
"mean_token_accuracy": 0.1269135594367981,
|
|
"num_tokens": 4187445.0,
|
|
"step": 1905
|
|
},
|
|
{
|
|
"entropy": 6.157655334472656,
|
|
"epoch": 0.18955934894799523,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.000499907801349781,
|
|
"loss": 5.9288,
|
|
"mean_token_accuracy": 0.1249204121530056,
|
|
"num_tokens": 4198124.0,
|
|
"step": 1910
|
|
},
|
|
{
|
|
"entropy": 6.117712736129761,
|
|
"epoch": 0.19005557761016276,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004999067843438664,
|
|
"loss": 5.9642,
|
|
"mean_token_accuracy": 0.12320106327533722,
|
|
"num_tokens": 4208954.0,
|
|
"step": 1915
|
|
},
|
|
{
|
|
"entropy": 6.1655356884002686,
|
|
"epoch": 0.1905518062723303,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004999057617607482,
|
|
"loss": 6.036,
|
|
"mean_token_accuracy": 0.12222218587994575,
|
|
"num_tokens": 4218896.0,
|
|
"step": 1920
|
|
},
|
|
{
|
|
"entropy": 6.073115491867066,
|
|
"epoch": 0.19104803493449782,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004999047336004517,
|
|
"loss": 5.9545,
|
|
"mean_token_accuracy": 0.11575927585363388,
|
|
"num_tokens": 4228851.0,
|
|
"step": 1925
|
|
},
|
|
{
|
|
"entropy": 6.062970113754273,
|
|
"epoch": 0.19154426359666535,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999036998630024,
|
|
"loss": 5.9034,
|
|
"mean_token_accuracy": 0.12176035344600677,
|
|
"num_tokens": 4240377.0,
|
|
"step": 1930
|
|
},
|
|
{
|
|
"entropy": 6.1012085437774655,
|
|
"epoch": 0.19204049225883288,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.000499902660548426,
|
|
"loss": 5.9005,
|
|
"mean_token_accuracy": 0.12233036682009697,
|
|
"num_tokens": 4251341.0,
|
|
"step": 1935
|
|
},
|
|
{
|
|
"entropy": 6.09600863456726,
|
|
"epoch": 0.1925367209210004,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999016156567482,
|
|
"loss": 5.9999,
|
|
"mean_token_accuracy": 0.12348600029945374,
|
|
"num_tokens": 4261206.0,
|
|
"step": 1940
|
|
},
|
|
{
|
|
"entropy": 6.171257972717285,
|
|
"epoch": 0.1930329495831679,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.000499900565187995,
|
|
"loss": 6.0095,
|
|
"mean_token_accuracy": 0.11739006116986275,
|
|
"num_tokens": 4272662.0,
|
|
"step": 1945
|
|
},
|
|
{
|
|
"entropy": 6.155332422256469,
|
|
"epoch": 0.19352917824533544,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004998995091421924,
|
|
"loss": 5.9894,
|
|
"mean_token_accuracy": 0.12250523716211319,
|
|
"num_tokens": 4283302.0,
|
|
"step": 1950
|
|
},
|
|
{
|
|
"entropy": 6.102492046356201,
|
|
"epoch": 0.19402540690750297,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004998984475193665,
|
|
"loss": 5.9331,
|
|
"mean_token_accuracy": 0.1246795579791069,
|
|
"num_tokens": 4296087.0,
|
|
"step": 1955
|
|
},
|
|
{
|
|
"entropy": 6.071946620941162,
|
|
"epoch": 0.1945216355696705,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004998973803195439,
|
|
"loss": 5.9506,
|
|
"mean_token_accuracy": 0.12343922182917595,
|
|
"num_tokens": 4305918.0,
|
|
"step": 1960
|
|
},
|
|
{
|
|
"entropy": 6.098349571228027,
|
|
"epoch": 0.19501786423183803,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004998963075427508,
|
|
"loss": 6.0056,
|
|
"mean_token_accuracy": 0.12570720240473748,
|
|
"num_tokens": 4316507.0,
|
|
"step": 1965
|
|
},
|
|
{
|
|
"entropy": 6.172418403625488,
|
|
"epoch": 0.19551409289400556,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004998952291890138,
|
|
"loss": 5.9377,
|
|
"mean_token_accuracy": 0.12697042599320413,
|
|
"num_tokens": 4329091.0,
|
|
"step": 1970
|
|
},
|
|
{
|
|
"entropy": 6.116201543807984,
|
|
"epoch": 0.1960103215561731,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004998941452583599,
|
|
"loss": 6.0005,
|
|
"mean_token_accuracy": 0.12526401430368422,
|
|
"num_tokens": 4339266.0,
|
|
"step": 1975
|
|
},
|
|
{
|
|
"entropy": 6.060456848144531,
|
|
"epoch": 0.1965065502183406,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004998930557508156,
|
|
"loss": 5.9315,
|
|
"mean_token_accuracy": 0.12996648699045182,
|
|
"num_tokens": 4349300.0,
|
|
"step": 1980
|
|
},
|
|
{
|
|
"entropy": 6.031670236587525,
|
|
"epoch": 0.19700277888050813,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004998919606664082,
|
|
"loss": 5.8523,
|
|
"mean_token_accuracy": 0.1329902485013008,
|
|
"num_tokens": 4360314.0,
|
|
"step": 1985
|
|
},
|
|
{
|
|
"entropy": 6.06371750831604,
|
|
"epoch": 0.19749900754267566,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004998908600051648,
|
|
"loss": 5.9022,
|
|
"mean_token_accuracy": 0.12996097579598426,
|
|
"num_tokens": 4370077.0,
|
|
"step": 1990
|
|
},
|
|
{
|
|
"entropy": 6.041788816452026,
|
|
"epoch": 0.1979952362048432,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004998897537671126,
|
|
"loss": 5.9163,
|
|
"mean_token_accuracy": 0.12319361120462417,
|
|
"num_tokens": 4381000.0,
|
|
"step": 1995
|
|
},
|
|
{
|
|
"entropy": 6.162951469421387,
|
|
"epoch": 0.19849146486701072,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004998886419522792,
|
|
"loss": 6.1233,
|
|
"mean_token_accuracy": 0.11464894115924835,
|
|
"num_tokens": 4393485.0,
|
|
"step": 2000
|
|
},
|
|
{
|
|
"entropy": 6.207508325576782,
|
|
"epoch": 0.19898769352917825,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004998875245606919,
|
|
"loss": 5.9466,
|
|
"mean_token_accuracy": 0.1263269901275635,
|
|
"num_tokens": 4404354.0,
|
|
"step": 2005
|
|
},
|
|
{
|
|
"entropy": 6.115656423568725,
|
|
"epoch": 0.19948392219134578,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004998864015923788,
|
|
"loss": 6.0848,
|
|
"mean_token_accuracy": 0.12513597384095193,
|
|
"num_tokens": 4414818.0,
|
|
"step": 2010
|
|
},
|
|
{
|
|
"entropy": 6.1054645538330075,
|
|
"epoch": 0.1999801508535133,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004998852730473674,
|
|
"loss": 5.9732,
|
|
"mean_token_accuracy": 0.1186623029410839,
|
|
"num_tokens": 4426271.0,
|
|
"step": 2015
|
|
},
|
|
{
|
|
"entropy": 6.113159704208374,
|
|
"epoch": 0.2004763795156808,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004998841389256859,
|
|
"loss": 6.0201,
|
|
"mean_token_accuracy": 0.12535962387919425,
|
|
"num_tokens": 4436981.0,
|
|
"step": 2020
|
|
},
|
|
{
|
|
"entropy": 6.088190221786499,
|
|
"epoch": 0.20097260817784834,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004998829992273622,
|
|
"loss": 5.8457,
|
|
"mean_token_accuracy": 0.12926107719540597,
|
|
"num_tokens": 4446494.0,
|
|
"step": 2025
|
|
},
|
|
{
|
|
"entropy": 6.0542316913604735,
|
|
"epoch": 0.20146883684001587,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004998818539524248,
|
|
"loss": 5.941,
|
|
"mean_token_accuracy": 0.12792145758867263,
|
|
"num_tokens": 4458535.0,
|
|
"step": 2030
|
|
},
|
|
{
|
|
"entropy": 6.076647806167602,
|
|
"epoch": 0.2019650655021834,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.000499880703100902,
|
|
"loss": 5.9109,
|
|
"mean_token_accuracy": 0.12890672460198402,
|
|
"num_tokens": 4469025.0,
|
|
"step": 2035
|
|
},
|
|
{
|
|
"entropy": 6.119675874710083,
|
|
"epoch": 0.20246129416435094,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004998795466728223,
|
|
"loss": 5.9311,
|
|
"mean_token_accuracy": 0.12614311054348945,
|
|
"num_tokens": 4478431.0,
|
|
"step": 2040
|
|
},
|
|
{
|
|
"entropy": 6.100471878051758,
|
|
"epoch": 0.20295752282651847,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004998783846682144,
|
|
"loss": 6.0565,
|
|
"mean_token_accuracy": 0.12169205471873283,
|
|
"num_tokens": 4490215.0,
|
|
"step": 2045
|
|
},
|
|
{
|
|
"entropy": 6.08721661567688,
|
|
"epoch": 0.203453751488686,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.0004998772170871072,
|
|
"loss": 5.9323,
|
|
"mean_token_accuracy": 0.12300658226013184,
|
|
"num_tokens": 4502895.0,
|
|
"step": 2050
|
|
},
|
|
{
|
|
"entropy": 6.049704933166504,
|
|
"epoch": 0.20394998015085353,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004998760439295295,
|
|
"loss": 5.9527,
|
|
"mean_token_accuracy": 0.12245631441473961,
|
|
"num_tokens": 4514468.0,
|
|
"step": 2055
|
|
},
|
|
{
|
|
"entropy": 6.120728397369385,
|
|
"epoch": 0.20444620881302103,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004998748651955105,
|
|
"loss": 5.9697,
|
|
"mean_token_accuracy": 0.12270477414131165,
|
|
"num_tokens": 4525787.0,
|
|
"step": 2060
|
|
},
|
|
{
|
|
"entropy": 6.1617701053619385,
|
|
"epoch": 0.20494243747518856,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004998736808850795,
|
|
"loss": 6.0537,
|
|
"mean_token_accuracy": 0.1189173199236393,
|
|
"num_tokens": 4537536.0,
|
|
"step": 2065
|
|
},
|
|
{
|
|
"entropy": 6.137720203399658,
|
|
"epoch": 0.2054386661373561,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004998724909982656,
|
|
"loss": 5.9957,
|
|
"mean_token_accuracy": 0.1230063110589981,
|
|
"num_tokens": 4549619.0,
|
|
"step": 2070
|
|
},
|
|
{
|
|
"entropy": 6.054072999954224,
|
|
"epoch": 0.20593489479952362,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004998712955350986,
|
|
"loss": 5.9127,
|
|
"mean_token_accuracy": 0.12620335072278976,
|
|
"num_tokens": 4560248.0,
|
|
"step": 2075
|
|
},
|
|
{
|
|
"entropy": 6.133942365646362,
|
|
"epoch": 0.20643112346169115,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004998700944956081,
|
|
"loss": 6.0258,
|
|
"mean_token_accuracy": 0.12564925700426102,
|
|
"num_tokens": 4571888.0,
|
|
"step": 2080
|
|
},
|
|
{
|
|
"entropy": 6.092451715469361,
|
|
"epoch": 0.20692735212385868,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004998688878798237,
|
|
"loss": 5.8719,
|
|
"mean_token_accuracy": 0.13250108286738396,
|
|
"num_tokens": 4583234.0,
|
|
"step": 2085
|
|
},
|
|
{
|
|
"entropy": 6.129697036743164,
|
|
"epoch": 0.2074235807860262,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004998676756877753,
|
|
"loss": 6.0849,
|
|
"mean_token_accuracy": 0.1196140132844448,
|
|
"num_tokens": 4595252.0,
|
|
"step": 2090
|
|
},
|
|
{
|
|
"entropy": 6.055380916595459,
|
|
"epoch": 0.20791980944819372,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004998664579194934,
|
|
"loss": 5.8636,
|
|
"mean_token_accuracy": 0.12891709432005882,
|
|
"num_tokens": 4607091.0,
|
|
"step": 2095
|
|
},
|
|
{
|
|
"entropy": 6.060617876052857,
|
|
"epoch": 0.20841603811036125,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004998652345750077,
|
|
"loss": 5.8251,
|
|
"mean_token_accuracy": 0.13188225999474526,
|
|
"num_tokens": 4618003.0,
|
|
"step": 2100
|
|
},
|
|
{
|
|
"entropy": 6.004556941986084,
|
|
"epoch": 0.20891226677252878,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004998640056543487,
|
|
"loss": 5.8382,
|
|
"mean_token_accuracy": 0.12877558246254922,
|
|
"num_tokens": 4628429.0,
|
|
"step": 2105
|
|
},
|
|
{
|
|
"entropy": 6.042101526260376,
|
|
"epoch": 0.2094084954346963,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004998627711575469,
|
|
"loss": 5.9003,
|
|
"mean_token_accuracy": 0.1301546387374401,
|
|
"num_tokens": 4639414.0,
|
|
"step": 2110
|
|
},
|
|
{
|
|
"entropy": 6.125416374206543,
|
|
"epoch": 0.20990472409686384,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.000499861531084633,
|
|
"loss": 5.9868,
|
|
"mean_token_accuracy": 0.12510028034448623,
|
|
"num_tokens": 4652594.0,
|
|
"step": 2115
|
|
},
|
|
{
|
|
"entropy": 5.983136796951294,
|
|
"epoch": 0.21040095275903137,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004998602854356376,
|
|
"loss": 5.8353,
|
|
"mean_token_accuracy": 0.13099646791815758,
|
|
"num_tokens": 4662981.0,
|
|
"step": 2120
|
|
},
|
|
{
|
|
"entropy": 6.04475212097168,
|
|
"epoch": 0.2108971814211989,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004998590342105917,
|
|
"loss": 5.929,
|
|
"mean_token_accuracy": 0.12667660117149354,
|
|
"num_tokens": 4672469.0,
|
|
"step": 2125
|
|
},
|
|
{
|
|
"entropy": 6.043806028366089,
|
|
"epoch": 0.21139341008336643,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004998577774095262,
|
|
"loss": 5.9052,
|
|
"mean_token_accuracy": 0.12564729601144792,
|
|
"num_tokens": 4683640.0,
|
|
"step": 2130
|
|
},
|
|
{
|
|
"entropy": 6.0359203815460205,
|
|
"epoch": 0.21188963874553393,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004998565150324724,
|
|
"loss": 5.8664,
|
|
"mean_token_accuracy": 0.12986178547143937,
|
|
"num_tokens": 4694032.0,
|
|
"step": 2135
|
|
},
|
|
{
|
|
"entropy": 5.933635091781616,
|
|
"epoch": 0.21238586740770146,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004998552470794616,
|
|
"loss": 5.7421,
|
|
"mean_token_accuracy": 0.13141876757144927,
|
|
"num_tokens": 4704253.0,
|
|
"step": 2140
|
|
},
|
|
{
|
|
"entropy": 6.008824586868286,
|
|
"epoch": 0.212882096069869,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004998539735505251,
|
|
"loss": 5.8993,
|
|
"mean_token_accuracy": 0.1256441943347454,
|
|
"num_tokens": 4715327.0,
|
|
"step": 2145
|
|
},
|
|
{
|
|
"entropy": 6.166449022293091,
|
|
"epoch": 0.21337832473203652,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004998526944456946,
|
|
"loss": 5.9113,
|
|
"mean_token_accuracy": 0.12448364496231079,
|
|
"num_tokens": 4726450.0,
|
|
"step": 2150
|
|
},
|
|
{
|
|
"entropy": 6.0194117546081545,
|
|
"epoch": 0.21387455339420405,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004998514097650018,
|
|
"loss": 5.9441,
|
|
"mean_token_accuracy": 0.12404742538928985,
|
|
"num_tokens": 4736630.0,
|
|
"step": 2155
|
|
},
|
|
{
|
|
"entropy": 6.021891641616821,
|
|
"epoch": 0.21437078205637158,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004998501195084786,
|
|
"loss": 5.8261,
|
|
"mean_token_accuracy": 0.13041977211833,
|
|
"num_tokens": 4746592.0,
|
|
"step": 2160
|
|
},
|
|
{
|
|
"entropy": 6.075963544845581,
|
|
"epoch": 0.21486701071853911,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004998488236761569,
|
|
"loss": 5.9943,
|
|
"mean_token_accuracy": 0.12953520566225052,
|
|
"num_tokens": 4757824.0,
|
|
"step": 2165
|
|
},
|
|
{
|
|
"entropy": 6.078512859344483,
|
|
"epoch": 0.21536323938070662,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004998475222680688,
|
|
"loss": 5.9418,
|
|
"mean_token_accuracy": 0.12912883386015891,
|
|
"num_tokens": 4768453.0,
|
|
"step": 2170
|
|
},
|
|
{
|
|
"entropy": 5.984212827682495,
|
|
"epoch": 0.21585946804287415,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004998462152842468,
|
|
"loss": 5.9138,
|
|
"mean_token_accuracy": 0.1260770782828331,
|
|
"num_tokens": 4779664.0,
|
|
"step": 2175
|
|
},
|
|
{
|
|
"entropy": 6.1202507495880125,
|
|
"epoch": 0.21635569670504168,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.000499844902724723,
|
|
"loss": 5.9297,
|
|
"mean_token_accuracy": 0.1291131466627121,
|
|
"num_tokens": 4791012.0,
|
|
"step": 2180
|
|
},
|
|
{
|
|
"entropy": 6.0246453285217285,
|
|
"epoch": 0.2168519253672092,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004998435845895302,
|
|
"loss": 5.804,
|
|
"mean_token_accuracy": 0.1243359960615635,
|
|
"num_tokens": 4800578.0,
|
|
"step": 2185
|
|
},
|
|
{
|
|
"entropy": 5.987508344650268,
|
|
"epoch": 0.21734815402937674,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.000499842260878701,
|
|
"loss": 5.8239,
|
|
"mean_token_accuracy": 0.12554812505841256,
|
|
"num_tokens": 4810940.0,
|
|
"step": 2190
|
|
},
|
|
{
|
|
"entropy": 6.046344041824341,
|
|
"epoch": 0.21784438269154427,
|
|
"grad_norm": 0.796875,
|
|
"learning_rate": 0.0004998409315922683,
|
|
"loss": 5.9594,
|
|
"mean_token_accuracy": 0.12463009878993034,
|
|
"num_tokens": 4822696.0,
|
|
"step": 2195
|
|
},
|
|
{
|
|
"entropy": 6.06123194694519,
|
|
"epoch": 0.2183406113537118,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004998395967302649,
|
|
"loss": 5.8424,
|
|
"mean_token_accuracy": 0.1316361606121063,
|
|
"num_tokens": 4833669.0,
|
|
"step": 2200
|
|
},
|
|
{
|
|
"entropy": 6.1397562503814695,
|
|
"epoch": 0.21883684001587933,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.000499838256292724,
|
|
"loss": 6.0156,
|
|
"mean_token_accuracy": 0.12383595556020736,
|
|
"num_tokens": 4844021.0,
|
|
"step": 2205
|
|
},
|
|
{
|
|
"entropy": 5.95759687423706,
|
|
"epoch": 0.21933306867804683,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004998369102796787,
|
|
"loss": 5.8932,
|
|
"mean_token_accuracy": 0.12637994140386583,
|
|
"num_tokens": 4855336.0,
|
|
"step": 2210
|
|
},
|
|
{
|
|
"entropy": 6.048965978622436,
|
|
"epoch": 0.21982929734021436,
|
|
"grad_norm": 0.796875,
|
|
"learning_rate": 0.0004998355586911627,
|
|
"loss": 5.9059,
|
|
"mean_token_accuracy": 0.12790409997105598,
|
|
"num_tokens": 4867713.0,
|
|
"step": 2215
|
|
},
|
|
{
|
|
"entropy": 5.9969117641448975,
|
|
"epoch": 0.2203255260023819,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004998342015272093,
|
|
"loss": 5.8694,
|
|
"mean_token_accuracy": 0.12453557699918746,
|
|
"num_tokens": 4879134.0,
|
|
"step": 2220
|
|
},
|
|
{
|
|
"entropy": 6.086967134475708,
|
|
"epoch": 0.22082175466454942,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004998328387878521,
|
|
"loss": 6.0274,
|
|
"mean_token_accuracy": 0.12505436688661575,
|
|
"num_tokens": 4891755.0,
|
|
"step": 2225
|
|
},
|
|
{
|
|
"entropy": 6.152056741714477,
|
|
"epoch": 0.22131798332671695,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004998314704731249,
|
|
"loss": 6.0155,
|
|
"mean_token_accuracy": 0.12360429838299751,
|
|
"num_tokens": 4903264.0,
|
|
"step": 2230
|
|
},
|
|
{
|
|
"entropy": 6.021547603607178,
|
|
"epoch": 0.22181421198888449,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004998300965830618,
|
|
"loss": 5.8482,
|
|
"mean_token_accuracy": 0.1265365608036518,
|
|
"num_tokens": 4912533.0,
|
|
"step": 2235
|
|
},
|
|
{
|
|
"entropy": 5.9325371265411375,
|
|
"epoch": 0.22231044065105202,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004998287171176968,
|
|
"loss": 5.8439,
|
|
"mean_token_accuracy": 0.13453373461961746,
|
|
"num_tokens": 4923288.0,
|
|
"step": 2240
|
|
},
|
|
{
|
|
"entropy": 6.013333702087403,
|
|
"epoch": 0.22280666931321952,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004998273320770641,
|
|
"loss": 5.861,
|
|
"mean_token_accuracy": 0.1291363902390003,
|
|
"num_tokens": 4934759.0,
|
|
"step": 2245
|
|
},
|
|
{
|
|
"entropy": 6.0565742492675785,
|
|
"epoch": 0.22330289797538705,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000499825941461198,
|
|
"loss": 5.9108,
|
|
"mean_token_accuracy": 0.12829016521573067,
|
|
"num_tokens": 4947024.0,
|
|
"step": 2250
|
|
},
|
|
{
|
|
"entropy": 5.990304183959961,
|
|
"epoch": 0.22379912663755458,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004998245452701329,
|
|
"loss": 5.8611,
|
|
"mean_token_accuracy": 0.12755537852644921,
|
|
"num_tokens": 4959281.0,
|
|
"step": 2255
|
|
},
|
|
{
|
|
"entropy": 6.069461011886597,
|
|
"epoch": 0.2242953552997221,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004998231435039036,
|
|
"loss": 5.9047,
|
|
"mean_token_accuracy": 0.12395669743418694,
|
|
"num_tokens": 4970466.0,
|
|
"step": 2260
|
|
},
|
|
{
|
|
"entropy": 6.021377325057983,
|
|
"epoch": 0.22479158396188964,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004998217361625449,
|
|
"loss": 5.8562,
|
|
"mean_token_accuracy": 0.12923893854022026,
|
|
"num_tokens": 4981135.0,
|
|
"step": 2265
|
|
},
|
|
{
|
|
"entropy": 6.048352479934692,
|
|
"epoch": 0.22528781262405717,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004998203232460915,
|
|
"loss": 5.9167,
|
|
"mean_token_accuracy": 0.1324473612010479,
|
|
"num_tokens": 4991292.0,
|
|
"step": 2270
|
|
},
|
|
{
|
|
"entropy": 5.9737649917602536,
|
|
"epoch": 0.2257840412862247,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004998189047545785,
|
|
"loss": 5.8825,
|
|
"mean_token_accuracy": 0.13191651031374932,
|
|
"num_tokens": 5002806.0,
|
|
"step": 2275
|
|
},
|
|
{
|
|
"entropy": 5.993149375915527,
|
|
"epoch": 0.22628026994839223,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004998174806880411,
|
|
"loss": 5.8179,
|
|
"mean_token_accuracy": 0.13567918241024018,
|
|
"num_tokens": 5013474.0,
|
|
"step": 2280
|
|
},
|
|
{
|
|
"entropy": 6.056148862838745,
|
|
"epoch": 0.22677649861055973,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004998160510465146,
|
|
"loss": 5.8642,
|
|
"mean_token_accuracy": 0.13143307566642762,
|
|
"num_tokens": 5025151.0,
|
|
"step": 2285
|
|
},
|
|
{
|
|
"entropy": 5.92156720161438,
|
|
"epoch": 0.22727272727272727,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004998146158300345,
|
|
"loss": 5.8638,
|
|
"mean_token_accuracy": 0.13245996236801147,
|
|
"num_tokens": 5037166.0,
|
|
"step": 2290
|
|
},
|
|
{
|
|
"entropy": 6.050130987167359,
|
|
"epoch": 0.2277689559348948,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004998131750386364,
|
|
"loss": 5.9076,
|
|
"mean_token_accuracy": 0.1297108441591263,
|
|
"num_tokens": 5047452.0,
|
|
"step": 2295
|
|
},
|
|
{
|
|
"entropy": 6.028859281539917,
|
|
"epoch": 0.22826518459706233,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004998117286723559,
|
|
"loss": 5.9272,
|
|
"mean_token_accuracy": 0.11998689249157905,
|
|
"num_tokens": 5058501.0,
|
|
"step": 2300
|
|
},
|
|
{
|
|
"entropy": 6.028175163269043,
|
|
"epoch": 0.22876141325922986,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.000499810276731229,
|
|
"loss": 5.9102,
|
|
"mean_token_accuracy": 0.12801963984966278,
|
|
"num_tokens": 5069716.0,
|
|
"step": 2305
|
|
},
|
|
{
|
|
"entropy": 6.123485803604126,
|
|
"epoch": 0.2292576419213974,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004998088192152918,
|
|
"loss": 5.8893,
|
|
"mean_token_accuracy": 0.1252819001674652,
|
|
"num_tokens": 5078509.0,
|
|
"step": 2310
|
|
},
|
|
{
|
|
"entropy": 6.000077247619629,
|
|
"epoch": 0.22975387058356492,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004998073561245801,
|
|
"loss": 5.9347,
|
|
"mean_token_accuracy": 0.12345504015684128,
|
|
"num_tokens": 5090355.0,
|
|
"step": 2315
|
|
},
|
|
{
|
|
"entropy": 6.051438713073731,
|
|
"epoch": 0.23025009924573242,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004998058874591305,
|
|
"loss": 5.8242,
|
|
"mean_token_accuracy": 0.1337508350610733,
|
|
"num_tokens": 5100582.0,
|
|
"step": 2320
|
|
},
|
|
{
|
|
"entropy": 6.000838756561279,
|
|
"epoch": 0.23074632790789995,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004998044132189793,
|
|
"loss": 5.8887,
|
|
"mean_token_accuracy": 0.12203488871455193,
|
|
"num_tokens": 5112176.0,
|
|
"step": 2325
|
|
},
|
|
{
|
|
"entropy": 6.021178150177002,
|
|
"epoch": 0.23124255657006748,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.000499802933404163,
|
|
"loss": 5.8335,
|
|
"mean_token_accuracy": 0.1279439650475979,
|
|
"num_tokens": 5122840.0,
|
|
"step": 2330
|
|
},
|
|
{
|
|
"entropy": 6.0098320007324215,
|
|
"epoch": 0.231738785232235,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004998014480147183,
|
|
"loss": 5.8047,
|
|
"mean_token_accuracy": 0.13865086659789086,
|
|
"num_tokens": 5132926.0,
|
|
"step": 2335
|
|
},
|
|
{
|
|
"entropy": 5.934864521026611,
|
|
"epoch": 0.23223501389440254,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004997999570506823,
|
|
"loss": 5.7806,
|
|
"mean_token_accuracy": 0.13042209595441817,
|
|
"num_tokens": 5143394.0,
|
|
"step": 2340
|
|
},
|
|
{
|
|
"entropy": 5.982978010177613,
|
|
"epoch": 0.23273124255657007,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0004997984605120917,
|
|
"loss": 5.8147,
|
|
"mean_token_accuracy": 0.12575569450855256,
|
|
"num_tokens": 5155710.0,
|
|
"step": 2345
|
|
},
|
|
{
|
|
"entropy": 5.841717767715454,
|
|
"epoch": 0.2332274712187376,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004997969583989835,
|
|
"loss": 5.751,
|
|
"mean_token_accuracy": 0.12713968753814697,
|
|
"num_tokens": 5167065.0,
|
|
"step": 2350
|
|
},
|
|
{
|
|
"entropy": 5.989433431625367,
|
|
"epoch": 0.23372369988090513,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004997954507113952,
|
|
"loss": 5.8495,
|
|
"mean_token_accuracy": 0.12923550233244896,
|
|
"num_tokens": 5177535.0,
|
|
"step": 2355
|
|
},
|
|
{
|
|
"entropy": 6.037681818008423,
|
|
"epoch": 0.23421992854307264,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004997939374493642,
|
|
"loss": 5.7806,
|
|
"mean_token_accuracy": 0.13312982767820358,
|
|
"num_tokens": 5188324.0,
|
|
"step": 2360
|
|
},
|
|
{
|
|
"entropy": 5.901477909088134,
|
|
"epoch": 0.23471615720524017,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.000499792418612928,
|
|
"loss": 5.86,
|
|
"mean_token_accuracy": 0.1304488480091095,
|
|
"num_tokens": 5199223.0,
|
|
"step": 2365
|
|
},
|
|
{
|
|
"entropy": 5.945672512054443,
|
|
"epoch": 0.2352123858674077,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004997908942021241,
|
|
"loss": 5.8299,
|
|
"mean_token_accuracy": 0.13325254768133163,
|
|
"num_tokens": 5210080.0,
|
|
"step": 2370
|
|
},
|
|
{
|
|
"entropy": 6.099682092666626,
|
|
"epoch": 0.23570861452957523,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004997893642169904,
|
|
"loss": 5.9558,
|
|
"mean_token_accuracy": 0.12958926782011987,
|
|
"num_tokens": 5220867.0,
|
|
"step": 2375
|
|
},
|
|
{
|
|
"entropy": 6.014858865737915,
|
|
"epoch": 0.23620484319174276,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004997878286575648,
|
|
"loss": 5.7952,
|
|
"mean_token_accuracy": 0.12957458645105363,
|
|
"num_tokens": 5231451.0,
|
|
"step": 2380
|
|
},
|
|
{
|
|
"entropy": 5.938134288787841,
|
|
"epoch": 0.2367010718539103,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004997862875238855,
|
|
"loss": 5.9034,
|
|
"mean_token_accuracy": 0.12620984017848969,
|
|
"num_tokens": 5244643.0,
|
|
"step": 2385
|
|
},
|
|
{
|
|
"entropy": 6.035072565078735,
|
|
"epoch": 0.23719730051607782,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004997847408159907,
|
|
"loss": 5.9145,
|
|
"mean_token_accuracy": 0.12331874147057534,
|
|
"num_tokens": 5256279.0,
|
|
"step": 2390
|
|
},
|
|
{
|
|
"entropy": 6.0572350978851315,
|
|
"epoch": 0.23769352917824532,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004997831885339186,
|
|
"loss": 5.8955,
|
|
"mean_token_accuracy": 0.13024576678872107,
|
|
"num_tokens": 5268498.0,
|
|
"step": 2395
|
|
},
|
|
{
|
|
"entropy": 5.939180183410644,
|
|
"epoch": 0.23818975784041285,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004997816306777077,
|
|
"loss": 5.8567,
|
|
"mean_token_accuracy": 0.13194234371185304,
|
|
"num_tokens": 5280869.0,
|
|
"step": 2400
|
|
},
|
|
{
|
|
"entropy": 6.102878284454346,
|
|
"epoch": 0.23868598650258038,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004997800672473969,
|
|
"loss": 5.9558,
|
|
"mean_token_accuracy": 0.12405509725213051,
|
|
"num_tokens": 5293082.0,
|
|
"step": 2405
|
|
},
|
|
{
|
|
"entropy": 5.935460233688355,
|
|
"epoch": 0.2391822151647479,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004997784982430247,
|
|
"loss": 5.7407,
|
|
"mean_token_accuracy": 0.14041346311569214,
|
|
"num_tokens": 5304039.0,
|
|
"step": 2410
|
|
},
|
|
{
|
|
"entropy": 5.937913465499878,
|
|
"epoch": 0.23967844382691544,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004997769236646301,
|
|
"loss": 5.8253,
|
|
"mean_token_accuracy": 0.13146729916334152,
|
|
"num_tokens": 5315016.0,
|
|
"step": 2415
|
|
},
|
|
{
|
|
"entropy": 6.090373134613037,
|
|
"epoch": 0.24017467248908297,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004997753435122522,
|
|
"loss": 5.9481,
|
|
"mean_token_accuracy": 0.12890507653355598,
|
|
"num_tokens": 5326090.0,
|
|
"step": 2420
|
|
},
|
|
{
|
|
"entropy": 5.9364526748657225,
|
|
"epoch": 0.2406709011512505,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00049977375778593,
|
|
"loss": 5.7381,
|
|
"mean_token_accuracy": 0.13036757260560988,
|
|
"num_tokens": 5336423.0,
|
|
"step": 2425
|
|
},
|
|
{
|
|
"entropy": 5.988410186767578,
|
|
"epoch": 0.24116712981341804,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004997721664857032,
|
|
"loss": 5.9064,
|
|
"mean_token_accuracy": 0.13083979934453965,
|
|
"num_tokens": 5346982.0,
|
|
"step": 2430
|
|
},
|
|
{
|
|
"entropy": 5.9514707088470455,
|
|
"epoch": 0.24166335847558554,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004997705696116108,
|
|
"loss": 5.8041,
|
|
"mean_token_accuracy": 0.13514370396733283,
|
|
"num_tokens": 5359210.0,
|
|
"step": 2435
|
|
},
|
|
{
|
|
"entropy": 5.958845949172973,
|
|
"epoch": 0.24215958713775307,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004997689671636926,
|
|
"loss": 5.8358,
|
|
"mean_token_accuracy": 0.12565323561429978,
|
|
"num_tokens": 5369891.0,
|
|
"step": 2440
|
|
},
|
|
{
|
|
"entropy": 5.962273597717285,
|
|
"epoch": 0.2426558157999206,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004997673591419884,
|
|
"loss": 5.8116,
|
|
"mean_token_accuracy": 0.1305241070687771,
|
|
"num_tokens": 5380850.0,
|
|
"step": 2445
|
|
},
|
|
{
|
|
"entropy": 5.970908737182617,
|
|
"epoch": 0.24315204446208813,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004997657455465381,
|
|
"loss": 5.8724,
|
|
"mean_token_accuracy": 0.13438860848546028,
|
|
"num_tokens": 5391903.0,
|
|
"step": 2450
|
|
},
|
|
{
|
|
"entropy": 6.027713441848755,
|
|
"epoch": 0.24364827312425566,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004997641263773815,
|
|
"loss": 5.9209,
|
|
"mean_token_accuracy": 0.1283269263803959,
|
|
"num_tokens": 5402517.0,
|
|
"step": 2455
|
|
},
|
|
{
|
|
"entropy": 5.9370378971099855,
|
|
"epoch": 0.2441445017864232,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.000499762501634559,
|
|
"loss": 5.8357,
|
|
"mean_token_accuracy": 0.12951843738555907,
|
|
"num_tokens": 5414110.0,
|
|
"step": 2460
|
|
},
|
|
{
|
|
"entropy": 6.02907428741455,
|
|
"epoch": 0.24464073044859072,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004997608713181108,
|
|
"loss": 5.8403,
|
|
"mean_token_accuracy": 0.13202603831887244,
|
|
"num_tokens": 5424466.0,
|
|
"step": 2465
|
|
},
|
|
{
|
|
"entropy": 5.915480756759644,
|
|
"epoch": 0.24513695911075822,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004997592354280772,
|
|
"loss": 5.8526,
|
|
"mean_token_accuracy": 0.1366075359284878,
|
|
"num_tokens": 5434461.0,
|
|
"step": 2470
|
|
},
|
|
{
|
|
"entropy": 5.940920686721801,
|
|
"epoch": 0.24563318777292575,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.000499757593964499,
|
|
"loss": 5.8263,
|
|
"mean_token_accuracy": 0.12434638366103172,
|
|
"num_tokens": 5445921.0,
|
|
"step": 2475
|
|
},
|
|
{
|
|
"entropy": 5.955485916137695,
|
|
"epoch": 0.24612941643509328,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004997559469274166,
|
|
"loss": 5.8127,
|
|
"mean_token_accuracy": 0.12727661803364754,
|
|
"num_tokens": 5456283.0,
|
|
"step": 2480
|
|
},
|
|
{
|
|
"entropy": 5.970708322525025,
|
|
"epoch": 0.24662564509726081,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004997542943168712,
|
|
"loss": 5.8501,
|
|
"mean_token_accuracy": 0.1340114578604698,
|
|
"num_tokens": 5467616.0,
|
|
"step": 2485
|
|
},
|
|
{
|
|
"entropy": 5.974401187896729,
|
|
"epoch": 0.24712187375942835,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004997526361329035,
|
|
"loss": 5.8048,
|
|
"mean_token_accuracy": 0.13320422694087028,
|
|
"num_tokens": 5478050.0,
|
|
"step": 2490
|
|
},
|
|
{
|
|
"entropy": 6.017988967895508,
|
|
"epoch": 0.24761810242159588,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004997509723755547,
|
|
"loss": 5.8205,
|
|
"mean_token_accuracy": 0.13056738600134848,
|
|
"num_tokens": 5487185.0,
|
|
"step": 2495
|
|
},
|
|
{
|
|
"entropy": 5.945784282684326,
|
|
"epoch": 0.2481143310837634,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004997493030448662,
|
|
"loss": 5.8411,
|
|
"mean_token_accuracy": 0.1261320762336254,
|
|
"num_tokens": 5498802.0,
|
|
"step": 2500
|
|
},
|
|
{
|
|
"entropy": 5.9388504981994625,
|
|
"epoch": 0.24861055974593094,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004997476281408793,
|
|
"loss": 5.855,
|
|
"mean_token_accuracy": 0.12759978100657463,
|
|
"num_tokens": 5510285.0,
|
|
"step": 2505
|
|
},
|
|
{
|
|
"entropy": 6.00165810585022,
|
|
"epoch": 0.24910678840809844,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004997459476636354,
|
|
"loss": 5.7335,
|
|
"mean_token_accuracy": 0.13755400031805037,
|
|
"num_tokens": 5520028.0,
|
|
"step": 2510
|
|
},
|
|
{
|
|
"entropy": 5.905316925048828,
|
|
"epoch": 0.24960301707026597,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004997442616131763,
|
|
"loss": 5.85,
|
|
"mean_token_accuracy": 0.12924634143710137,
|
|
"num_tokens": 5529271.0,
|
|
"step": 2515
|
|
},
|
|
{
|
|
"entropy": 5.97735447883606,
|
|
"epoch": 0.25009924573243353,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004997425699895438,
|
|
"loss": 5.7753,
|
|
"mean_token_accuracy": 0.12766662314534188,
|
|
"num_tokens": 5539396.0,
|
|
"step": 2520
|
|
},
|
|
{
|
|
"entropy": 6.006867456436157,
|
|
"epoch": 0.25059547439460106,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004997408727927798,
|
|
"loss": 5.9196,
|
|
"mean_token_accuracy": 0.13126150593161584,
|
|
"num_tokens": 5551674.0,
|
|
"step": 2525
|
|
},
|
|
{
|
|
"entropy": 5.974583911895752,
|
|
"epoch": 0.25109170305676853,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004997391700229264,
|
|
"loss": 5.8413,
|
|
"mean_token_accuracy": 0.1326450914144516,
|
|
"num_tokens": 5562749.0,
|
|
"step": 2530
|
|
},
|
|
{
|
|
"entropy": 5.960433483123779,
|
|
"epoch": 0.25158793171893606,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.000499737461680026,
|
|
"loss": 5.854,
|
|
"mean_token_accuracy": 0.134577427059412,
|
|
"num_tokens": 5573478.0,
|
|
"step": 2535
|
|
},
|
|
{
|
|
"entropy": 5.884474802017212,
|
|
"epoch": 0.2520841603811036,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004997357477641207,
|
|
"loss": 5.8349,
|
|
"mean_token_accuracy": 0.1368376225233078,
|
|
"num_tokens": 5584546.0,
|
|
"step": 2540
|
|
},
|
|
{
|
|
"entropy": 5.904690790176391,
|
|
"epoch": 0.2525803890432711,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004997340282752532,
|
|
"loss": 5.7177,
|
|
"mean_token_accuracy": 0.13633103296160698,
|
|
"num_tokens": 5594004.0,
|
|
"step": 2545
|
|
},
|
|
{
|
|
"entropy": 5.9720470905303955,
|
|
"epoch": 0.25307661770543866,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.000499732303213466,
|
|
"loss": 5.7943,
|
|
"mean_token_accuracy": 0.125521769374609,
|
|
"num_tokens": 5606095.0,
|
|
"step": 2550
|
|
},
|
|
{
|
|
"entropy": 5.999422073364258,
|
|
"epoch": 0.2535728463676062,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004997305725788019,
|
|
"loss": 5.813,
|
|
"mean_token_accuracy": 0.12604894265532493,
|
|
"num_tokens": 5615596.0,
|
|
"step": 2555
|
|
},
|
|
{
|
|
"entropy": 5.867432165145874,
|
|
"epoch": 0.2540690750297737,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.000499728836371304,
|
|
"loss": 5.771,
|
|
"mean_token_accuracy": 0.13205990493297576,
|
|
"num_tokens": 5626753.0,
|
|
"step": 2560
|
|
},
|
|
{
|
|
"entropy": 5.866491079330444,
|
|
"epoch": 0.25456530369194125,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004997270945910151,
|
|
"loss": 5.7828,
|
|
"mean_token_accuracy": 0.12868185043334962,
|
|
"num_tokens": 5636135.0,
|
|
"step": 2565
|
|
},
|
|
{
|
|
"entropy": 6.046658754348755,
|
|
"epoch": 0.2550615323541088,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004997253472379785,
|
|
"loss": 5.8504,
|
|
"mean_token_accuracy": 0.1282991424202919,
|
|
"num_tokens": 5647074.0,
|
|
"step": 2570
|
|
},
|
|
{
|
|
"entropy": 5.9704625606536865,
|
|
"epoch": 0.2555577610162763,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004997235943122375,
|
|
"loss": 5.8703,
|
|
"mean_token_accuracy": 0.12940976694226264,
|
|
"num_tokens": 5658600.0,
|
|
"step": 2575
|
|
},
|
|
{
|
|
"entropy": 5.924697065353394,
|
|
"epoch": 0.25605398967844384,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004997218358138356,
|
|
"loss": 5.7866,
|
|
"mean_token_accuracy": 0.13074240386486052,
|
|
"num_tokens": 5668453.0,
|
|
"step": 2580
|
|
},
|
|
{
|
|
"entropy": 5.984611177444458,
|
|
"epoch": 0.25655021834061137,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004997200717428165,
|
|
"loss": 5.8295,
|
|
"mean_token_accuracy": 0.12661149725317955,
|
|
"num_tokens": 5678855.0,
|
|
"step": 2585
|
|
},
|
|
{
|
|
"entropy": 5.916502237319946,
|
|
"epoch": 0.2570464470027789,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004997183020992237,
|
|
"loss": 5.8903,
|
|
"mean_token_accuracy": 0.12172176912426949,
|
|
"num_tokens": 5690063.0,
|
|
"step": 2590
|
|
},
|
|
{
|
|
"entropy": 5.936478853225708,
|
|
"epoch": 0.25754267566494643,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004997165268831014,
|
|
"loss": 5.7896,
|
|
"mean_token_accuracy": 0.13551302403211593,
|
|
"num_tokens": 5701487.0,
|
|
"step": 2595
|
|
},
|
|
{
|
|
"entropy": 5.903074455261231,
|
|
"epoch": 0.25803890432711396,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004997147460944933,
|
|
"loss": 5.7725,
|
|
"mean_token_accuracy": 0.1349751755595207,
|
|
"num_tokens": 5713034.0,
|
|
"step": 2600
|
|
},
|
|
{
|
|
"entropy": 6.014874839782715,
|
|
"epoch": 0.25853513298928144,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004997129597334438,
|
|
"loss": 5.8224,
|
|
"mean_token_accuracy": 0.13061220347881317,
|
|
"num_tokens": 5725469.0,
|
|
"step": 2605
|
|
},
|
|
{
|
|
"entropy": 5.862464809417725,
|
|
"epoch": 0.25903136165144897,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004997111677999971,
|
|
"loss": 5.812,
|
|
"mean_token_accuracy": 0.12882769852876663,
|
|
"num_tokens": 5737099.0,
|
|
"step": 2610
|
|
},
|
|
{
|
|
"entropy": 5.97240686416626,
|
|
"epoch": 0.2595275903136165,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004997093702941976,
|
|
"loss": 5.8214,
|
|
"mean_token_accuracy": 0.12686606049537658,
|
|
"num_tokens": 5748756.0,
|
|
"step": 2615
|
|
},
|
|
{
|
|
"entropy": 5.980477237701416,
|
|
"epoch": 0.260023818975784,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00049970756721609,
|
|
"loss": 5.8099,
|
|
"mean_token_accuracy": 0.12726252228021623,
|
|
"num_tokens": 5759598.0,
|
|
"step": 2620
|
|
},
|
|
{
|
|
"entropy": 5.953548765182495,
|
|
"epoch": 0.26052004763795156,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.000499705758565719,
|
|
"loss": 5.854,
|
|
"mean_token_accuracy": 0.12930647283792496,
|
|
"num_tokens": 5770397.0,
|
|
"step": 2625
|
|
},
|
|
{
|
|
"entropy": 6.005121231079102,
|
|
"epoch": 0.2610162763001191,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004997039443431292,
|
|
"loss": 5.9263,
|
|
"mean_token_accuracy": 0.12437670230865479,
|
|
"num_tokens": 5780935.0,
|
|
"step": 2630
|
|
},
|
|
{
|
|
"entropy": 6.0060749530792235,
|
|
"epoch": 0.2615125049622866,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004997021245483659,
|
|
"loss": 5.7808,
|
|
"mean_token_accuracy": 0.13181432709097862,
|
|
"num_tokens": 5791557.0,
|
|
"step": 2635
|
|
},
|
|
{
|
|
"entropy": 5.898467540740967,
|
|
"epoch": 0.26200873362445415,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.000499700299181474,
|
|
"loss": 5.8199,
|
|
"mean_token_accuracy": 0.1286296509206295,
|
|
"num_tokens": 5802233.0,
|
|
"step": 2640
|
|
},
|
|
{
|
|
"entropy": 5.9045013904571535,
|
|
"epoch": 0.2625049622866217,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004996984682424989,
|
|
"loss": 5.7429,
|
|
"mean_token_accuracy": 0.13722301945090293,
|
|
"num_tokens": 5813424.0,
|
|
"step": 2645
|
|
},
|
|
{
|
|
"entropy": 5.888933420181274,
|
|
"epoch": 0.2630011909487892,
|
|
"grad_norm": 0.7890625,
|
|
"learning_rate": 0.000499696631731486,
|
|
"loss": 5.7238,
|
|
"mean_token_accuracy": 0.13307972252368927,
|
|
"num_tokens": 5825652.0,
|
|
"step": 2650
|
|
},
|
|
{
|
|
"entropy": 5.953473615646362,
|
|
"epoch": 0.26349741961095674,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004996947896484809,
|
|
"loss": 5.8126,
|
|
"mean_token_accuracy": 0.13535162359476088,
|
|
"num_tokens": 5836603.0,
|
|
"step": 2655
|
|
},
|
|
{
|
|
"entropy": 5.948557996749878,
|
|
"epoch": 0.26399364827312427,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.000499692941993529,
|
|
"loss": 5.8636,
|
|
"mean_token_accuracy": 0.1336210548877716,
|
|
"num_tokens": 5849365.0,
|
|
"step": 2660
|
|
},
|
|
{
|
|
"entropy": 5.975414085388183,
|
|
"epoch": 0.2644898769352918,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004996910887666765,
|
|
"loss": 5.7797,
|
|
"mean_token_accuracy": 0.1360326051712036,
|
|
"num_tokens": 5860305.0,
|
|
"step": 2665
|
|
},
|
|
{
|
|
"entropy": 5.86191725730896,
|
|
"epoch": 0.26498610559745933,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.000499689229967969,
|
|
"loss": 5.7249,
|
|
"mean_token_accuracy": 0.1364116244018078,
|
|
"num_tokens": 5872272.0,
|
|
"step": 2670
|
|
},
|
|
{
|
|
"entropy": 5.931841802597046,
|
|
"epoch": 0.26548233425962686,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004996873655974529,
|
|
"loss": 5.7536,
|
|
"mean_token_accuracy": 0.13195567727088928,
|
|
"num_tokens": 5884107.0,
|
|
"step": 2675
|
|
},
|
|
{
|
|
"entropy": 5.839572381973267,
|
|
"epoch": 0.26597856292179434,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004996854956551743,
|
|
"loss": 5.7433,
|
|
"mean_token_accuracy": 0.13461884558200837,
|
|
"num_tokens": 5894060.0,
|
|
"step": 2680
|
|
},
|
|
{
|
|
"entropy": 5.867028617858887,
|
|
"epoch": 0.26647479158396187,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004996836201411794,
|
|
"loss": 5.7661,
|
|
"mean_token_accuracy": 0.13390844464302062,
|
|
"num_tokens": 5904804.0,
|
|
"step": 2685
|
|
},
|
|
{
|
|
"entropy": 6.046043062210083,
|
|
"epoch": 0.2669710202461294,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000499681739055515,
|
|
"loss": 5.8361,
|
|
"mean_token_accuracy": 0.12845558002591134,
|
|
"num_tokens": 5916496.0,
|
|
"step": 2690
|
|
},
|
|
{
|
|
"entropy": 5.9300178527832035,
|
|
"epoch": 0.26746724890829693,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004996798523982276,
|
|
"loss": 5.7818,
|
|
"mean_token_accuracy": 0.1285025343298912,
|
|
"num_tokens": 5926920.0,
|
|
"step": 2695
|
|
},
|
|
{
|
|
"entropy": 5.965683031082153,
|
|
"epoch": 0.26796347757046446,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.000499677960169364,
|
|
"loss": 5.8865,
|
|
"mean_token_accuracy": 0.12686679884791374,
|
|
"num_tokens": 5940098.0,
|
|
"step": 2700
|
|
},
|
|
{
|
|
"entropy": 5.910781335830689,
|
|
"epoch": 0.268459706232632,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004996760623689711,
|
|
"loss": 5.7374,
|
|
"mean_token_accuracy": 0.13134501054883002,
|
|
"num_tokens": 5949687.0,
|
|
"step": 2705
|
|
},
|
|
{
|
|
"entropy": 5.929884958267212,
|
|
"epoch": 0.2689559348947995,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.000499674158997096,
|
|
"loss": 5.8442,
|
|
"mean_token_accuracy": 0.12607498317956925,
|
|
"num_tokens": 5960777.0,
|
|
"step": 2710
|
|
},
|
|
{
|
|
"entropy": 5.978472423553467,
|
|
"epoch": 0.26945216355696705,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004996722500537859,
|
|
"loss": 5.7503,
|
|
"mean_token_accuracy": 0.13114108070731162,
|
|
"num_tokens": 5972298.0,
|
|
"step": 2715
|
|
},
|
|
{
|
|
"entropy": 5.902798414230347,
|
|
"epoch": 0.2699483922191346,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004996703355390881,
|
|
"loss": 5.8696,
|
|
"mean_token_accuracy": 0.12787102088332175,
|
|
"num_tokens": 5985613.0,
|
|
"step": 2720
|
|
},
|
|
{
|
|
"entropy": 5.998373651504517,
|
|
"epoch": 0.2704446208813021,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00049966841545305,
|
|
"loss": 5.9368,
|
|
"mean_token_accuracy": 0.1289162516593933,
|
|
"num_tokens": 5997530.0,
|
|
"step": 2725
|
|
},
|
|
{
|
|
"entropy": 5.979059410095215,
|
|
"epoch": 0.27094084954346964,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004996664897957195,
|
|
"loss": 5.7906,
|
|
"mean_token_accuracy": 0.12967565059661865,
|
|
"num_tokens": 6008123.0,
|
|
"step": 2730
|
|
},
|
|
{
|
|
"entropy": 5.898594331741333,
|
|
"epoch": 0.2714370782056372,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004996645585671441,
|
|
"loss": 5.8159,
|
|
"mean_token_accuracy": 0.13189680576324464,
|
|
"num_tokens": 6020578.0,
|
|
"step": 2735
|
|
},
|
|
{
|
|
"entropy": 5.885920572280884,
|
|
"epoch": 0.2719333068678047,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004996626217673717,
|
|
"loss": 5.7329,
|
|
"mean_token_accuracy": 0.13771061301231385,
|
|
"num_tokens": 6031625.0,
|
|
"step": 2740
|
|
},
|
|
{
|
|
"entropy": 5.859991264343262,
|
|
"epoch": 0.27242953552997223,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004996606793964504,
|
|
"loss": 5.771,
|
|
"mean_token_accuracy": 0.13899061530828477,
|
|
"num_tokens": 6041320.0,
|
|
"step": 2745
|
|
},
|
|
{
|
|
"entropy": 5.95008225440979,
|
|
"epoch": 0.27292576419213976,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004996587314544284,
|
|
"loss": 5.793,
|
|
"mean_token_accuracy": 0.13212788924574853,
|
|
"num_tokens": 6052627.0,
|
|
"step": 2750
|
|
},
|
|
{
|
|
"entropy": 5.905590677261353,
|
|
"epoch": 0.27342199285430724,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004996567779413539,
|
|
"loss": 5.7442,
|
|
"mean_token_accuracy": 0.13712375462055207,
|
|
"num_tokens": 6063468.0,
|
|
"step": 2755
|
|
},
|
|
{
|
|
"entropy": 5.918176126480103,
|
|
"epoch": 0.27391822151647477,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004996548188572755,
|
|
"loss": 5.7254,
|
|
"mean_token_accuracy": 0.13772219493985177,
|
|
"num_tokens": 6074208.0,
|
|
"step": 2760
|
|
},
|
|
{
|
|
"entropy": 5.93715763092041,
|
|
"epoch": 0.2744144501786423,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004996528542022416,
|
|
"loss": 5.7761,
|
|
"mean_token_accuracy": 0.1317790240049362,
|
|
"num_tokens": 6085068.0,
|
|
"step": 2765
|
|
},
|
|
{
|
|
"entropy": 5.8894490718841555,
|
|
"epoch": 0.27491067884080983,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.000499650883976301,
|
|
"loss": 5.7723,
|
|
"mean_token_accuracy": 0.13286536261439325,
|
|
"num_tokens": 6096445.0,
|
|
"step": 2770
|
|
},
|
|
{
|
|
"entropy": 5.8424560070037845,
|
|
"epoch": 0.27540690750297736,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004996489081795026,
|
|
"loss": 5.6885,
|
|
"mean_token_accuracy": 0.137538892775774,
|
|
"num_tokens": 6106527.0,
|
|
"step": 2775
|
|
},
|
|
{
|
|
"entropy": 5.817946577072144,
|
|
"epoch": 0.2759031361651449,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004996469268118953,
|
|
"loss": 5.7127,
|
|
"mean_token_accuracy": 0.14144881442189217,
|
|
"num_tokens": 6115923.0,
|
|
"step": 2780
|
|
},
|
|
{
|
|
"entropy": 5.838368940353393,
|
|
"epoch": 0.2763993648273124,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004996449398735283,
|
|
"loss": 5.6099,
|
|
"mean_token_accuracy": 0.14129377156496048,
|
|
"num_tokens": 6125861.0,
|
|
"step": 2785
|
|
},
|
|
{
|
|
"entropy": 5.945985269546509,
|
|
"epoch": 0.27689559348947995,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004996429473644509,
|
|
"loss": 5.8072,
|
|
"mean_token_accuracy": 0.13425228521227836,
|
|
"num_tokens": 6137189.0,
|
|
"step": 2790
|
|
},
|
|
{
|
|
"entropy": 5.8859100341796875,
|
|
"epoch": 0.2773918221516475,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004996409492847124,
|
|
"loss": 5.7305,
|
|
"mean_token_accuracy": 0.13389328271150588,
|
|
"num_tokens": 6147920.0,
|
|
"step": 2795
|
|
},
|
|
{
|
|
"entropy": 5.892881202697754,
|
|
"epoch": 0.277888050813815,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004996389456343624,
|
|
"loss": 5.7287,
|
|
"mean_token_accuracy": 0.14077215641736984,
|
|
"num_tokens": 6159371.0,
|
|
"step": 2800
|
|
},
|
|
{
|
|
"entropy": 6.015835094451904,
|
|
"epoch": 0.27838427947598254,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004996369364134507,
|
|
"loss": 5.9235,
|
|
"mean_token_accuracy": 0.12242046073079109,
|
|
"num_tokens": 6172679.0,
|
|
"step": 2805
|
|
},
|
|
{
|
|
"entropy": 5.894385576248169,
|
|
"epoch": 0.2788805081381501,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.000499634921622027,
|
|
"loss": 5.7718,
|
|
"mean_token_accuracy": 0.12801498249173165,
|
|
"num_tokens": 6184244.0,
|
|
"step": 2810
|
|
},
|
|
{
|
|
"entropy": 5.8594602108001705,
|
|
"epoch": 0.2793767368003176,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004996329012601413,
|
|
"loss": 5.6501,
|
|
"mean_token_accuracy": 0.1308717854321003,
|
|
"num_tokens": 6194826.0,
|
|
"step": 2815
|
|
},
|
|
{
|
|
"entropy": 5.934268379211426,
|
|
"epoch": 0.27987296546248513,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004996308753278437,
|
|
"loss": 5.7955,
|
|
"mean_token_accuracy": 0.13045783266425132,
|
|
"num_tokens": 6206808.0,
|
|
"step": 2820
|
|
},
|
|
{
|
|
"entropy": 5.903773975372315,
|
|
"epoch": 0.28036919412465267,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004996288438251843,
|
|
"loss": 5.8036,
|
|
"mean_token_accuracy": 0.1288069613277912,
|
|
"num_tokens": 6217303.0,
|
|
"step": 2825
|
|
},
|
|
{
|
|
"entropy": 5.918454885482788,
|
|
"epoch": 0.28086542278682014,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004996268067522137,
|
|
"loss": 5.7907,
|
|
"mean_token_accuracy": 0.13076610937714578,
|
|
"num_tokens": 6227965.0,
|
|
"step": 2830
|
|
},
|
|
{
|
|
"entropy": 6.045854377746582,
|
|
"epoch": 0.28136165144898767,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004996247641089823,
|
|
"loss": 5.8534,
|
|
"mean_token_accuracy": 0.12538014501333236,
|
|
"num_tokens": 6239011.0,
|
|
"step": 2835
|
|
},
|
|
{
|
|
"entropy": 5.820587921142578,
|
|
"epoch": 0.2818578801111552,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004996227158955409,
|
|
"loss": 5.7089,
|
|
"mean_token_accuracy": 0.13381239399313927,
|
|
"num_tokens": 6249084.0,
|
|
"step": 2840
|
|
},
|
|
{
|
|
"entropy": 5.854635334014892,
|
|
"epoch": 0.28235410877332273,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00049962066211194,
|
|
"loss": 5.7811,
|
|
"mean_token_accuracy": 0.12858823388814927,
|
|
"num_tokens": 6260706.0,
|
|
"step": 2845
|
|
},
|
|
{
|
|
"entropy": 5.910700273513794,
|
|
"epoch": 0.28285033743549026,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004996186027582308,
|
|
"loss": 5.719,
|
|
"mean_token_accuracy": 0.13755066841840743,
|
|
"num_tokens": 6272848.0,
|
|
"step": 2850
|
|
},
|
|
{
|
|
"entropy": 5.831938123703003,
|
|
"epoch": 0.2833465660976578,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004996165378344642,
|
|
"loss": 5.7198,
|
|
"mean_token_accuracy": 0.1345575749874115,
|
|
"num_tokens": 6283820.0,
|
|
"step": 2855
|
|
},
|
|
{
|
|
"entropy": 5.887689590454102,
|
|
"epoch": 0.2838427947598253,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004996144673406914,
|
|
"loss": 5.8847,
|
|
"mean_token_accuracy": 0.1203585371375084,
|
|
"num_tokens": 6294193.0,
|
|
"step": 2860
|
|
},
|
|
{
|
|
"entropy": 5.846189975738525,
|
|
"epoch": 0.28433902342199285,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004996123912769639,
|
|
"loss": 5.7111,
|
|
"mean_token_accuracy": 0.14153243526816367,
|
|
"num_tokens": 6304407.0,
|
|
"step": 2865
|
|
},
|
|
{
|
|
"entropy": 5.857138013839721,
|
|
"epoch": 0.2848352520841604,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004996103096433332,
|
|
"loss": 5.7866,
|
|
"mean_token_accuracy": 0.13395510241389275,
|
|
"num_tokens": 6316311.0,
|
|
"step": 2870
|
|
},
|
|
{
|
|
"entropy": 5.944645738601684,
|
|
"epoch": 0.2853314807463279,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004996082224398506,
|
|
"loss": 5.7471,
|
|
"mean_token_accuracy": 0.13548968210816384,
|
|
"num_tokens": 6327248.0,
|
|
"step": 2875
|
|
},
|
|
{
|
|
"entropy": 5.888983535766601,
|
|
"epoch": 0.28582770940849545,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004996061296665682,
|
|
"loss": 5.7629,
|
|
"mean_token_accuracy": 0.13373192697763442,
|
|
"num_tokens": 6338494.0,
|
|
"step": 2880
|
|
},
|
|
{
|
|
"entropy": 5.86532621383667,
|
|
"epoch": 0.286323938070663,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004996040313235377,
|
|
"loss": 5.6606,
|
|
"mean_token_accuracy": 0.1401577278971672,
|
|
"num_tokens": 6349038.0,
|
|
"step": 2885
|
|
},
|
|
{
|
|
"entropy": 5.888543939590454,
|
|
"epoch": 0.2868201667328305,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004996019274108112,
|
|
"loss": 5.7737,
|
|
"mean_token_accuracy": 0.12937842831015586,
|
|
"num_tokens": 6360180.0,
|
|
"step": 2890
|
|
},
|
|
{
|
|
"entropy": 5.789392042160034,
|
|
"epoch": 0.28731639539499804,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.000499599817928441,
|
|
"loss": 5.7128,
|
|
"mean_token_accuracy": 0.13721143081784248,
|
|
"num_tokens": 6370931.0,
|
|
"step": 2895
|
|
},
|
|
{
|
|
"entropy": 5.796161222457886,
|
|
"epoch": 0.28781262405716557,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004995977028764792,
|
|
"loss": 5.7034,
|
|
"mean_token_accuracy": 0.14205339923501015,
|
|
"num_tokens": 6381810.0,
|
|
"step": 2900
|
|
},
|
|
{
|
|
"entropy": 5.8964122295379635,
|
|
"epoch": 0.28830885271933304,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004995955822549783,
|
|
"loss": 5.7075,
|
|
"mean_token_accuracy": 0.1379415936768055,
|
|
"num_tokens": 6392268.0,
|
|
"step": 2905
|
|
},
|
|
{
|
|
"entropy": 5.881337690353393,
|
|
"epoch": 0.2888050813815006,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004995934560639909,
|
|
"loss": 5.7543,
|
|
"mean_token_accuracy": 0.132367368042469,
|
|
"num_tokens": 6403650.0,
|
|
"step": 2910
|
|
},
|
|
{
|
|
"entropy": 5.904406881332397,
|
|
"epoch": 0.2893013100436681,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004995913243035699,
|
|
"loss": 5.7468,
|
|
"mean_token_accuracy": 0.13186144679784775,
|
|
"num_tokens": 6414672.0,
|
|
"step": 2915
|
|
},
|
|
{
|
|
"entropy": 5.880802202224731,
|
|
"epoch": 0.28979753870583563,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004995891869737678,
|
|
"loss": 5.8088,
|
|
"mean_token_accuracy": 0.1321220226585865,
|
|
"num_tokens": 6424916.0,
|
|
"step": 2920
|
|
},
|
|
{
|
|
"entropy": 5.9205621719360355,
|
|
"epoch": 0.29029376736800316,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004995870440746379,
|
|
"loss": 5.7555,
|
|
"mean_token_accuracy": 0.13907312899827956,
|
|
"num_tokens": 6435950.0,
|
|
"step": 2925
|
|
},
|
|
{
|
|
"entropy": 5.813934850692749,
|
|
"epoch": 0.2907899960301707,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004995848956062333,
|
|
"loss": 5.7223,
|
|
"mean_token_accuracy": 0.1334433563053608,
|
|
"num_tokens": 6446336.0,
|
|
"step": 2930
|
|
},
|
|
{
|
|
"entropy": 5.862525606155396,
|
|
"epoch": 0.2912862246923382,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004995827415686071,
|
|
"loss": 5.7939,
|
|
"mean_token_accuracy": 0.1313887841999531,
|
|
"num_tokens": 6457655.0,
|
|
"step": 2935
|
|
},
|
|
{
|
|
"entropy": 5.933152437210083,
|
|
"epoch": 0.29178245335450576,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000499580581961813,
|
|
"loss": 5.6738,
|
|
"mean_token_accuracy": 0.1359466515481472,
|
|
"num_tokens": 6469627.0,
|
|
"step": 2940
|
|
},
|
|
{
|
|
"entropy": 5.85411057472229,
|
|
"epoch": 0.2922786820166733,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004995784167859043,
|
|
"loss": 5.7708,
|
|
"mean_token_accuracy": 0.1325305663049221,
|
|
"num_tokens": 6480351.0,
|
|
"step": 2945
|
|
},
|
|
{
|
|
"entropy": 5.930560064315796,
|
|
"epoch": 0.2927749106788408,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004995762460409349,
|
|
"loss": 5.7976,
|
|
"mean_token_accuracy": 0.1347188226878643,
|
|
"num_tokens": 6491651.0,
|
|
"step": 2950
|
|
},
|
|
{
|
|
"entropy": 5.843895006179809,
|
|
"epoch": 0.29327113934100835,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004995740697269584,
|
|
"loss": 5.6555,
|
|
"mean_token_accuracy": 0.13501327559351922,
|
|
"num_tokens": 6502531.0,
|
|
"step": 2955
|
|
},
|
|
{
|
|
"entropy": 5.776656246185302,
|
|
"epoch": 0.2937673680031759,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004995718878440289,
|
|
"loss": 5.6508,
|
|
"mean_token_accuracy": 0.13918386697769164,
|
|
"num_tokens": 6511938.0,
|
|
"step": 2960
|
|
},
|
|
{
|
|
"entropy": 5.909338426589966,
|
|
"epoch": 0.2942635966653434,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004995697003922006,
|
|
"loss": 5.8071,
|
|
"mean_token_accuracy": 0.1281385228037834,
|
|
"num_tokens": 6522775.0,
|
|
"step": 2965
|
|
},
|
|
{
|
|
"entropy": 5.889328289031982,
|
|
"epoch": 0.29475982532751094,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004995675073715274,
|
|
"loss": 5.6384,
|
|
"mean_token_accuracy": 0.1326303191483021,
|
|
"num_tokens": 6534660.0,
|
|
"step": 2970
|
|
},
|
|
{
|
|
"entropy": 5.867802667617798,
|
|
"epoch": 0.29525605398967847,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004995653087820641,
|
|
"loss": 5.7662,
|
|
"mean_token_accuracy": 0.1363363467156887,
|
|
"num_tokens": 6545673.0,
|
|
"step": 2975
|
|
},
|
|
{
|
|
"entropy": 5.872935438156128,
|
|
"epoch": 0.29575228265184594,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000499563104623865,
|
|
"loss": 5.7364,
|
|
"mean_token_accuracy": 0.13667785823345185,
|
|
"num_tokens": 6556912.0,
|
|
"step": 2980
|
|
},
|
|
{
|
|
"entropy": 5.885501098632813,
|
|
"epoch": 0.2962485113140135,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004995608948969849,
|
|
"loss": 5.8271,
|
|
"mean_token_accuracy": 0.13097959756851196,
|
|
"num_tokens": 6567532.0,
|
|
"step": 2985
|
|
},
|
|
{
|
|
"entropy": 5.90928168296814,
|
|
"epoch": 0.296744739976181,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004995586796014784,
|
|
"loss": 5.796,
|
|
"mean_token_accuracy": 0.13155989721417427,
|
|
"num_tokens": 6577830.0,
|
|
"step": 2990
|
|
},
|
|
{
|
|
"entropy": 5.823900842666626,
|
|
"epoch": 0.29724096863834853,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004995564587374005,
|
|
"loss": 5.6926,
|
|
"mean_token_accuracy": 0.13435450717806816,
|
|
"num_tokens": 6587254.0,
|
|
"step": 2995
|
|
},
|
|
{
|
|
"entropy": 5.902713966369629,
|
|
"epoch": 0.29773719730051607,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004995542323048063,
|
|
"loss": 5.8848,
|
|
"mean_token_accuracy": 0.12699431478977202,
|
|
"num_tokens": 6598294.0,
|
|
"step": 3000
|
|
},
|
|
{
|
|
"epoch": 0.29773719730051607,
|
|
"eval_entropy": 5.728751434966033,
|
|
"eval_loss": 5.813499450683594,
|
|
"eval_mean_token_accuracy": 0.1359337329577737,
|
|
"eval_num_tokens": 6598294.0,
|
|
"eval_runtime": 20.8245,
|
|
"eval_samples_per_second": 1616.798,
|
|
"eval_steps_per_second": 202.118,
|
|
"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
|
|
}
|