984fd98343
Model: fpadovani/ita-latn-10mb-after-ppt-Dp-100mb-ckpt500_seed455 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": 7.321103572845459,
|
|
"epoch": 0.0004962286621675268,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 2e-06,
|
|
"loss": 6.9502,
|
|
"mean_token_accuracy": 0.08894372060894966,
|
|
"num_tokens": 11135.0,
|
|
"step": 5
|
|
},
|
|
{
|
|
"entropy": 7.291898345947265,
|
|
"epoch": 0.0009924573243350536,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 4.5e-06,
|
|
"loss": 6.9889,
|
|
"mean_token_accuracy": 0.08681938499212265,
|
|
"num_tokens": 22299.0,
|
|
"step": 10
|
|
},
|
|
{
|
|
"entropy": 7.309418964385986,
|
|
"epoch": 0.0014886859865025804,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 7e-06,
|
|
"loss": 6.9968,
|
|
"mean_token_accuracy": 0.08861658647656441,
|
|
"num_tokens": 33670.0,
|
|
"step": 15
|
|
},
|
|
{
|
|
"entropy": 7.30535888671875,
|
|
"epoch": 0.001984914648670107,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 9.5e-06,
|
|
"loss": 6.9494,
|
|
"mean_token_accuracy": 0.08504866808652878,
|
|
"num_tokens": 44240.0,
|
|
"step": 20
|
|
},
|
|
{
|
|
"entropy": 7.317498207092285,
|
|
"epoch": 0.002481143310837634,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 1.2e-05,
|
|
"loss": 6.8974,
|
|
"mean_token_accuracy": 0.09154646843671799,
|
|
"num_tokens": 54168.0,
|
|
"step": 25
|
|
},
|
|
{
|
|
"entropy": 7.3441589832305905,
|
|
"epoch": 0.0029773719730051607,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 1.4500000000000002e-05,
|
|
"loss": 6.9,
|
|
"mean_token_accuracy": 0.09077088311314582,
|
|
"num_tokens": 64704.0,
|
|
"step": 30
|
|
},
|
|
{
|
|
"entropy": 7.337980651855469,
|
|
"epoch": 0.0034736006351726877,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 1.7000000000000003e-05,
|
|
"loss": 6.9297,
|
|
"mean_token_accuracy": 0.08911860883235931,
|
|
"num_tokens": 75766.0,
|
|
"step": 35
|
|
},
|
|
{
|
|
"entropy": 7.370907640457153,
|
|
"epoch": 0.003969829297340214,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 1.95e-05,
|
|
"loss": 6.9438,
|
|
"mean_token_accuracy": 0.08970932587981224,
|
|
"num_tokens": 88074.0,
|
|
"step": 40
|
|
},
|
|
{
|
|
"entropy": 7.34942741394043,
|
|
"epoch": 0.004466057959507741,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 2.2e-05,
|
|
"loss": 6.85,
|
|
"mean_token_accuracy": 0.09375255852937699,
|
|
"num_tokens": 99313.0,
|
|
"step": 45
|
|
},
|
|
{
|
|
"entropy": 7.417236328125,
|
|
"epoch": 0.004962286621675268,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 2.4500000000000003e-05,
|
|
"loss": 7.0061,
|
|
"mean_token_accuracy": 0.09381884783506393,
|
|
"num_tokens": 110819.0,
|
|
"step": 50
|
|
},
|
|
{
|
|
"entropy": 7.343614864349365,
|
|
"epoch": 0.0054585152838427945,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 2.7e-05,
|
|
"loss": 6.8035,
|
|
"mean_token_accuracy": 0.09773246571421623,
|
|
"num_tokens": 121156.0,
|
|
"step": 55
|
|
},
|
|
{
|
|
"entropy": 7.392715406417847,
|
|
"epoch": 0.0059547439460103215,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 2.95e-05,
|
|
"loss": 6.9373,
|
|
"mean_token_accuracy": 0.0945754513144493,
|
|
"num_tokens": 131307.0,
|
|
"step": 60
|
|
},
|
|
{
|
|
"entropy": 7.320441150665284,
|
|
"epoch": 0.0064509726081778485,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 3.2e-05,
|
|
"loss": 6.8968,
|
|
"mean_token_accuracy": 0.09729647785425186,
|
|
"num_tokens": 141812.0,
|
|
"step": 65
|
|
},
|
|
{
|
|
"entropy": 7.360306215286255,
|
|
"epoch": 0.0069472012703453755,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 3.4500000000000005e-05,
|
|
"loss": 6.8448,
|
|
"mean_token_accuracy": 0.08999949172139168,
|
|
"num_tokens": 152425.0,
|
|
"step": 70
|
|
},
|
|
{
|
|
"entropy": 7.37144455909729,
|
|
"epoch": 0.007443429932512902,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 3.7e-05,
|
|
"loss": 6.8837,
|
|
"mean_token_accuracy": 0.09427939280867577,
|
|
"num_tokens": 162562.0,
|
|
"step": 75
|
|
},
|
|
{
|
|
"entropy": 7.373857641220093,
|
|
"epoch": 0.007939658594680429,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 3.95e-05,
|
|
"loss": 6.9141,
|
|
"mean_token_accuracy": 0.09801442995667457,
|
|
"num_tokens": 173322.0,
|
|
"step": 80
|
|
},
|
|
{
|
|
"entropy": 7.314117288589477,
|
|
"epoch": 0.008435887256847956,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 4.2000000000000004e-05,
|
|
"loss": 6.857,
|
|
"mean_token_accuracy": 0.09269940182566642,
|
|
"num_tokens": 183169.0,
|
|
"step": 85
|
|
},
|
|
{
|
|
"entropy": 7.3311868667602536,
|
|
"epoch": 0.008932115919015483,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 4.45e-05,
|
|
"loss": 7.0099,
|
|
"mean_token_accuracy": 0.0901446096599102,
|
|
"num_tokens": 194473.0,
|
|
"step": 90
|
|
},
|
|
{
|
|
"entropy": 7.3603380680084225,
|
|
"epoch": 0.00942834458118301,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 4.7000000000000004e-05,
|
|
"loss": 6.8324,
|
|
"mean_token_accuracy": 0.09027603566646576,
|
|
"num_tokens": 206166.0,
|
|
"step": 95
|
|
},
|
|
{
|
|
"entropy": 7.34685206413269,
|
|
"epoch": 0.009924573243350537,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 4.9500000000000004e-05,
|
|
"loss": 6.8455,
|
|
"mean_token_accuracy": 0.09469634592533112,
|
|
"num_tokens": 215923.0,
|
|
"step": 100
|
|
},
|
|
{
|
|
"entropy": 7.320917844772339,
|
|
"epoch": 0.010420801905518062,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 5.2e-05,
|
|
"loss": 6.9275,
|
|
"mean_token_accuracy": 0.09063069075345993,
|
|
"num_tokens": 227139.0,
|
|
"step": 105
|
|
},
|
|
{
|
|
"entropy": 7.346196937561035,
|
|
"epoch": 0.010917030567685589,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 5.45e-05,
|
|
"loss": 6.8558,
|
|
"mean_token_accuracy": 0.09765214547514915,
|
|
"num_tokens": 237770.0,
|
|
"step": 110
|
|
},
|
|
{
|
|
"entropy": 7.377953720092774,
|
|
"epoch": 0.011413259229853116,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 5.7e-05,
|
|
"loss": 6.936,
|
|
"mean_token_accuracy": 0.09508275687694549,
|
|
"num_tokens": 249241.0,
|
|
"step": 115
|
|
},
|
|
{
|
|
"entropy": 7.348550510406494,
|
|
"epoch": 0.011909487892020643,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 5.9499999999999996e-05,
|
|
"loss": 6.8565,
|
|
"mean_token_accuracy": 0.09396146684885025,
|
|
"num_tokens": 258562.0,
|
|
"step": 120
|
|
},
|
|
{
|
|
"entropy": 7.275180292129517,
|
|
"epoch": 0.01240571655418817,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 6.2e-05,
|
|
"loss": 6.902,
|
|
"mean_token_accuracy": 0.09861418008804321,
|
|
"num_tokens": 269548.0,
|
|
"step": 125
|
|
},
|
|
{
|
|
"entropy": 7.438327026367188,
|
|
"epoch": 0.012901945216355697,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 6.450000000000001e-05,
|
|
"loss": 6.9914,
|
|
"mean_token_accuracy": 0.09398091435432435,
|
|
"num_tokens": 280965.0,
|
|
"step": 130
|
|
},
|
|
{
|
|
"entropy": 7.4196254253387455,
|
|
"epoch": 0.013398173878523224,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 6.7e-05,
|
|
"loss": 6.8143,
|
|
"mean_token_accuracy": 0.09857342019677162,
|
|
"num_tokens": 290063.0,
|
|
"step": 135
|
|
},
|
|
{
|
|
"entropy": 7.25293459892273,
|
|
"epoch": 0.013894402540690751,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 6.950000000000001e-05,
|
|
"loss": 6.9046,
|
|
"mean_token_accuracy": 0.09994807839393616,
|
|
"num_tokens": 301013.0,
|
|
"step": 140
|
|
},
|
|
{
|
|
"entropy": 7.350448560714722,
|
|
"epoch": 0.014390631202858276,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 7.2e-05,
|
|
"loss": 6.917,
|
|
"mean_token_accuracy": 0.09355304390192032,
|
|
"num_tokens": 313351.0,
|
|
"step": 145
|
|
},
|
|
{
|
|
"entropy": 7.391125869750977,
|
|
"epoch": 0.014886859865025803,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 7.45e-05,
|
|
"loss": 6.9412,
|
|
"mean_token_accuracy": 0.09017230421304703,
|
|
"num_tokens": 324871.0,
|
|
"step": 150
|
|
},
|
|
{
|
|
"entropy": 7.379152727127075,
|
|
"epoch": 0.01538308852719333,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 7.7e-05,
|
|
"loss": 6.8043,
|
|
"mean_token_accuracy": 0.09457008466124535,
|
|
"num_tokens": 335856.0,
|
|
"step": 155
|
|
},
|
|
{
|
|
"entropy": 7.27963695526123,
|
|
"epoch": 0.015879317189360857,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 7.950000000000001e-05,
|
|
"loss": 6.8058,
|
|
"mean_token_accuracy": 0.08980907499790192,
|
|
"num_tokens": 345410.0,
|
|
"step": 160
|
|
},
|
|
{
|
|
"entropy": 7.367447996139527,
|
|
"epoch": 0.016375545851528384,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 8.2e-05,
|
|
"loss": 6.8948,
|
|
"mean_token_accuracy": 0.09169329479336738,
|
|
"num_tokens": 356370.0,
|
|
"step": 165
|
|
},
|
|
{
|
|
"entropy": 7.369842910766602,
|
|
"epoch": 0.01687177451369591,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 8.450000000000001e-05,
|
|
"loss": 6.9352,
|
|
"mean_token_accuracy": 0.09325620308518409,
|
|
"num_tokens": 368085.0,
|
|
"step": 170
|
|
},
|
|
{
|
|
"entropy": 7.361319303512573,
|
|
"epoch": 0.01736800317586344,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 8.7e-05,
|
|
"loss": 6.8003,
|
|
"mean_token_accuracy": 0.09971174001693725,
|
|
"num_tokens": 378995.0,
|
|
"step": 175
|
|
},
|
|
{
|
|
"entropy": 7.319345235824585,
|
|
"epoch": 0.017864231838030965,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 8.95e-05,
|
|
"loss": 6.909,
|
|
"mean_token_accuracy": 0.09415822923183441,
|
|
"num_tokens": 390727.0,
|
|
"step": 180
|
|
},
|
|
{
|
|
"entropy": 7.4322614669799805,
|
|
"epoch": 0.018360460500198492,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 9.2e-05,
|
|
"loss": 6.849,
|
|
"mean_token_accuracy": 0.09615265130996704,
|
|
"num_tokens": 401875.0,
|
|
"step": 185
|
|
},
|
|
{
|
|
"entropy": 7.230821657180786,
|
|
"epoch": 0.01885668916236602,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 9.45e-05,
|
|
"loss": 6.8835,
|
|
"mean_token_accuracy": 0.0952032633125782,
|
|
"num_tokens": 414959.0,
|
|
"step": 190
|
|
},
|
|
{
|
|
"entropy": 7.3696495532989506,
|
|
"epoch": 0.019352917824533546,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 9.7e-05,
|
|
"loss": 6.8469,
|
|
"mean_token_accuracy": 0.09475988298654556,
|
|
"num_tokens": 425745.0,
|
|
"step": 195
|
|
},
|
|
{
|
|
"entropy": 7.317271423339844,
|
|
"epoch": 0.019849146486701073,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 9.95e-05,
|
|
"loss": 6.7841,
|
|
"mean_token_accuracy": 0.09933056309819221,
|
|
"num_tokens": 435149.0,
|
|
"step": 200
|
|
},
|
|
{
|
|
"entropy": 7.311147165298462,
|
|
"epoch": 0.0203453751488686,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.000102,
|
|
"loss": 6.8521,
|
|
"mean_token_accuracy": 0.09915618151426316,
|
|
"num_tokens": 445706.0,
|
|
"step": 205
|
|
},
|
|
{
|
|
"entropy": 7.283332872390747,
|
|
"epoch": 0.020841603811036124,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00010449999999999999,
|
|
"loss": 6.839,
|
|
"mean_token_accuracy": 0.10072373151779175,
|
|
"num_tokens": 455982.0,
|
|
"step": 210
|
|
},
|
|
{
|
|
"entropy": 7.41149492263794,
|
|
"epoch": 0.02133783247320365,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.000107,
|
|
"loss": 6.8673,
|
|
"mean_token_accuracy": 0.09816423431038857,
|
|
"num_tokens": 465462.0,
|
|
"step": 215
|
|
},
|
|
{
|
|
"entropy": 7.340578031539917,
|
|
"epoch": 0.021834061135371178,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0001095,
|
|
"loss": 6.808,
|
|
"mean_token_accuracy": 0.09429572075605393,
|
|
"num_tokens": 475770.0,
|
|
"step": 220
|
|
},
|
|
{
|
|
"entropy": 7.281261396408081,
|
|
"epoch": 0.022330289797538705,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.000112,
|
|
"loss": 6.766,
|
|
"mean_token_accuracy": 0.09254665300250053,
|
|
"num_tokens": 486345.0,
|
|
"step": 225
|
|
},
|
|
{
|
|
"entropy": 7.2465247631073,
|
|
"epoch": 0.022826518459706232,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0001145,
|
|
"loss": 6.8581,
|
|
"mean_token_accuracy": 0.09497587159276008,
|
|
"num_tokens": 496588.0,
|
|
"step": 230
|
|
},
|
|
{
|
|
"entropy": 7.330821084976196,
|
|
"epoch": 0.02332274712187376,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00011700000000000001,
|
|
"loss": 6.764,
|
|
"mean_token_accuracy": 0.10548505261540413,
|
|
"num_tokens": 506676.0,
|
|
"step": 235
|
|
},
|
|
{
|
|
"entropy": 7.259016704559326,
|
|
"epoch": 0.023818975784041286,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00011949999999999999,
|
|
"loss": 6.7581,
|
|
"mean_token_accuracy": 0.09661711901426315,
|
|
"num_tokens": 516866.0,
|
|
"step": 240
|
|
},
|
|
{
|
|
"entropy": 7.343613529205323,
|
|
"epoch": 0.024315204446208813,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.000122,
|
|
"loss": 6.9088,
|
|
"mean_token_accuracy": 0.09192305207252502,
|
|
"num_tokens": 529349.0,
|
|
"step": 245
|
|
},
|
|
{
|
|
"entropy": 7.2918651580810545,
|
|
"epoch": 0.02481143310837634,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0001245,
|
|
"loss": 6.8356,
|
|
"mean_token_accuracy": 0.0957394741475582,
|
|
"num_tokens": 541310.0,
|
|
"step": 250
|
|
},
|
|
{
|
|
"entropy": 7.347570466995239,
|
|
"epoch": 0.025307661770543867,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.000127,
|
|
"loss": 6.8669,
|
|
"mean_token_accuracy": 0.09501437321305276,
|
|
"num_tokens": 551897.0,
|
|
"step": 255
|
|
},
|
|
{
|
|
"entropy": 7.286837148666382,
|
|
"epoch": 0.025803890432711394,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0001295,
|
|
"loss": 6.8722,
|
|
"mean_token_accuracy": 0.09505478516221047,
|
|
"num_tokens": 564667.0,
|
|
"step": 260
|
|
},
|
|
{
|
|
"entropy": 7.2854108810424805,
|
|
"epoch": 0.02630011909487892,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.000132,
|
|
"loss": 6.7365,
|
|
"mean_token_accuracy": 0.09921214655041695,
|
|
"num_tokens": 575338.0,
|
|
"step": 265
|
|
},
|
|
{
|
|
"entropy": 7.331110572814941,
|
|
"epoch": 0.026796347757046448,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00013450000000000002,
|
|
"loss": 6.8525,
|
|
"mean_token_accuracy": 0.09441650062799453,
|
|
"num_tokens": 586169.0,
|
|
"step": 270
|
|
},
|
|
{
|
|
"entropy": 7.240020895004273,
|
|
"epoch": 0.027292576419213975,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00013700000000000002,
|
|
"loss": 6.8366,
|
|
"mean_token_accuracy": 0.09875859245657921,
|
|
"num_tokens": 596864.0,
|
|
"step": 275
|
|
},
|
|
{
|
|
"entropy": 7.349655055999756,
|
|
"epoch": 0.027788805081381502,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0001395,
|
|
"loss": 6.8323,
|
|
"mean_token_accuracy": 0.09189202263951302,
|
|
"num_tokens": 608894.0,
|
|
"step": 280
|
|
},
|
|
{
|
|
"entropy": 7.330462837219239,
|
|
"epoch": 0.02828503374354903,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00014199999999999998,
|
|
"loss": 6.8435,
|
|
"mean_token_accuracy": 0.09644725024700165,
|
|
"num_tokens": 619863.0,
|
|
"step": 285
|
|
},
|
|
{
|
|
"entropy": 7.33879017829895,
|
|
"epoch": 0.028781262405716553,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0001445,
|
|
"loss": 6.8891,
|
|
"mean_token_accuracy": 0.09643067345023155,
|
|
"num_tokens": 632691.0,
|
|
"step": 290
|
|
},
|
|
{
|
|
"entropy": 7.232556533813477,
|
|
"epoch": 0.02927749106788408,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.000147,
|
|
"loss": 6.7748,
|
|
"mean_token_accuracy": 0.09985843300819397,
|
|
"num_tokens": 643993.0,
|
|
"step": 295
|
|
},
|
|
{
|
|
"entropy": 7.320186996459961,
|
|
"epoch": 0.029773719730051607,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0001495,
|
|
"loss": 6.7693,
|
|
"mean_token_accuracy": 0.09714792221784592,
|
|
"num_tokens": 654275.0,
|
|
"step": 300
|
|
},
|
|
{
|
|
"entropy": 7.211906003952026,
|
|
"epoch": 0.030269948392219134,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000152,
|
|
"loss": 6.7464,
|
|
"mean_token_accuracy": 0.09860079064965248,
|
|
"num_tokens": 664694.0,
|
|
"step": 305
|
|
},
|
|
{
|
|
"entropy": 7.303035020828247,
|
|
"epoch": 0.03076617705438666,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00015450000000000001,
|
|
"loss": 6.7814,
|
|
"mean_token_accuracy": 0.09757039919495583,
|
|
"num_tokens": 674736.0,
|
|
"step": 310
|
|
},
|
|
{
|
|
"entropy": 7.143521499633789,
|
|
"epoch": 0.03126240571655419,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000157,
|
|
"loss": 6.6907,
|
|
"mean_token_accuracy": 0.100661750882864,
|
|
"num_tokens": 687261.0,
|
|
"step": 315
|
|
},
|
|
{
|
|
"entropy": 7.219635915756226,
|
|
"epoch": 0.031758634378721715,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0001595,
|
|
"loss": 6.736,
|
|
"mean_token_accuracy": 0.10075967833399772,
|
|
"num_tokens": 698904.0,
|
|
"step": 320
|
|
},
|
|
{
|
|
"entropy": 7.224134159088135,
|
|
"epoch": 0.032254863040889245,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000162,
|
|
"loss": 6.7152,
|
|
"mean_token_accuracy": 0.10156732127070427,
|
|
"num_tokens": 709035.0,
|
|
"step": 325
|
|
},
|
|
{
|
|
"entropy": 7.154531097412109,
|
|
"epoch": 0.03275109170305677,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00016450000000000001,
|
|
"loss": 6.7922,
|
|
"mean_token_accuracy": 0.10236325189471245,
|
|
"num_tokens": 719565.0,
|
|
"step": 330
|
|
},
|
|
{
|
|
"entropy": 7.312559509277344,
|
|
"epoch": 0.03324732036522429,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00016700000000000002,
|
|
"loss": 6.8179,
|
|
"mean_token_accuracy": 0.0999167263507843,
|
|
"num_tokens": 730329.0,
|
|
"step": 335
|
|
},
|
|
{
|
|
"entropy": 7.277273511886596,
|
|
"epoch": 0.03374354902739182,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00016950000000000003,
|
|
"loss": 6.81,
|
|
"mean_token_accuracy": 0.09728368297219277,
|
|
"num_tokens": 741258.0,
|
|
"step": 340
|
|
},
|
|
{
|
|
"entropy": 7.169039726257324,
|
|
"epoch": 0.034239777689559346,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.00017199999999999998,
|
|
"loss": 6.6991,
|
|
"mean_token_accuracy": 0.09544317200779914,
|
|
"num_tokens": 752636.0,
|
|
"step": 345
|
|
},
|
|
{
|
|
"entropy": 7.274296426773072,
|
|
"epoch": 0.03473600635172688,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00017449999999999999,
|
|
"loss": 6.7879,
|
|
"mean_token_accuracy": 0.09527788013219833,
|
|
"num_tokens": 764113.0,
|
|
"step": 350
|
|
},
|
|
{
|
|
"entropy": 7.15718035697937,
|
|
"epoch": 0.0352322350138944,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000177,
|
|
"loss": 6.6747,
|
|
"mean_token_accuracy": 0.10008381679654121,
|
|
"num_tokens": 772872.0,
|
|
"step": 355
|
|
},
|
|
{
|
|
"entropy": 7.275865650177002,
|
|
"epoch": 0.03572846367606193,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0001795,
|
|
"loss": 6.6976,
|
|
"mean_token_accuracy": 0.10527255833148956,
|
|
"num_tokens": 782788.0,
|
|
"step": 360
|
|
},
|
|
{
|
|
"entropy": 7.130430555343628,
|
|
"epoch": 0.036224692338229454,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000182,
|
|
"loss": 6.7768,
|
|
"mean_token_accuracy": 0.09755202606320382,
|
|
"num_tokens": 793859.0,
|
|
"step": 365
|
|
},
|
|
{
|
|
"entropy": 7.306216430664063,
|
|
"epoch": 0.036720921000396985,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0001845,
|
|
"loss": 6.7439,
|
|
"mean_token_accuracy": 0.09889776185154915,
|
|
"num_tokens": 804906.0,
|
|
"step": 370
|
|
},
|
|
{
|
|
"entropy": 7.191127681732178,
|
|
"epoch": 0.03721714966256451,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.000187,
|
|
"loss": 6.7651,
|
|
"mean_token_accuracy": 0.09736918658018112,
|
|
"num_tokens": 815520.0,
|
|
"step": 375
|
|
},
|
|
{
|
|
"entropy": 7.181806135177612,
|
|
"epoch": 0.03771337832473204,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0001895,
|
|
"loss": 6.7859,
|
|
"mean_token_accuracy": 0.09997142925858497,
|
|
"num_tokens": 826395.0,
|
|
"step": 380
|
|
},
|
|
{
|
|
"entropy": 7.2829760074615475,
|
|
"epoch": 0.03820960698689956,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.000192,
|
|
"loss": 6.732,
|
|
"mean_token_accuracy": 0.09944447204470634,
|
|
"num_tokens": 836627.0,
|
|
"step": 385
|
|
},
|
|
{
|
|
"entropy": 7.153994750976563,
|
|
"epoch": 0.03870583564906709,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0001945,
|
|
"loss": 6.7706,
|
|
"mean_token_accuracy": 0.09017840772867203,
|
|
"num_tokens": 848250.0,
|
|
"step": 390
|
|
},
|
|
{
|
|
"entropy": 7.316059160232544,
|
|
"epoch": 0.039202064311234616,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.00019700000000000002,
|
|
"loss": 6.7703,
|
|
"mean_token_accuracy": 0.09917276129126548,
|
|
"num_tokens": 859195.0,
|
|
"step": 395
|
|
},
|
|
{
|
|
"entropy": 7.160914516448974,
|
|
"epoch": 0.03969829297340215,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00019950000000000002,
|
|
"loss": 6.7453,
|
|
"mean_token_accuracy": 0.10009187385439873,
|
|
"num_tokens": 871955.0,
|
|
"step": 400
|
|
},
|
|
{
|
|
"entropy": 7.1762594223022464,
|
|
"epoch": 0.04019452163556967,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.000202,
|
|
"loss": 6.7606,
|
|
"mean_token_accuracy": 0.09773519337177276,
|
|
"num_tokens": 882729.0,
|
|
"step": 405
|
|
},
|
|
{
|
|
"entropy": 7.1601005554199215,
|
|
"epoch": 0.0406907502977372,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00020449999999999998,
|
|
"loss": 6.6661,
|
|
"mean_token_accuracy": 0.09903571754693985,
|
|
"num_tokens": 893183.0,
|
|
"step": 410
|
|
},
|
|
{
|
|
"entropy": 7.2316563606262205,
|
|
"epoch": 0.041186978959904724,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000207,
|
|
"loss": 6.7912,
|
|
"mean_token_accuracy": 0.10149758830666541,
|
|
"num_tokens": 904988.0,
|
|
"step": 415
|
|
},
|
|
{
|
|
"entropy": 7.237285995483399,
|
|
"epoch": 0.04168320762207225,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0002095,
|
|
"loss": 6.6543,
|
|
"mean_token_accuracy": 0.10472753047943115,
|
|
"num_tokens": 915192.0,
|
|
"step": 420
|
|
},
|
|
{
|
|
"entropy": 7.109501314163208,
|
|
"epoch": 0.04217943628423978,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000212,
|
|
"loss": 6.6954,
|
|
"mean_token_accuracy": 0.10364402532577514,
|
|
"num_tokens": 926494.0,
|
|
"step": 425
|
|
},
|
|
{
|
|
"entropy": 7.216678476333618,
|
|
"epoch": 0.0426756649464073,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0002145,
|
|
"loss": 6.702,
|
|
"mean_token_accuracy": 0.10059248208999634,
|
|
"num_tokens": 938376.0,
|
|
"step": 430
|
|
},
|
|
{
|
|
"entropy": 7.132107162475586,
|
|
"epoch": 0.04317189360857483,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00021700000000000002,
|
|
"loss": 6.6097,
|
|
"mean_token_accuracy": 0.1056530199944973,
|
|
"num_tokens": 948640.0,
|
|
"step": 435
|
|
},
|
|
{
|
|
"entropy": 7.096781969070435,
|
|
"epoch": 0.043668122270742356,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0002195,
|
|
"loss": 6.7184,
|
|
"mean_token_accuracy": 0.09810023754835129,
|
|
"num_tokens": 959759.0,
|
|
"step": 440
|
|
},
|
|
{
|
|
"entropy": 7.138823080062866,
|
|
"epoch": 0.044164350932909886,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.000222,
|
|
"loss": 6.6591,
|
|
"mean_token_accuracy": 0.09683494120836258,
|
|
"num_tokens": 970137.0,
|
|
"step": 445
|
|
},
|
|
{
|
|
"entropy": 7.140137815475464,
|
|
"epoch": 0.04466057959507741,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0002245,
|
|
"loss": 6.6989,
|
|
"mean_token_accuracy": 0.09436362460255623,
|
|
"num_tokens": 979875.0,
|
|
"step": 450
|
|
},
|
|
{
|
|
"entropy": 7.076799058914185,
|
|
"epoch": 0.04515680825724494,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00022700000000000002,
|
|
"loss": 6.6654,
|
|
"mean_token_accuracy": 0.10611343160271644,
|
|
"num_tokens": 990324.0,
|
|
"step": 455
|
|
},
|
|
{
|
|
"entropy": 7.221283626556397,
|
|
"epoch": 0.045653036919412464,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00022950000000000002,
|
|
"loss": 6.6791,
|
|
"mean_token_accuracy": 0.10299149453639984,
|
|
"num_tokens": 1000259.0,
|
|
"step": 460
|
|
},
|
|
{
|
|
"entropy": 7.089738178253174,
|
|
"epoch": 0.046149265581579994,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00023200000000000003,
|
|
"loss": 6.671,
|
|
"mean_token_accuracy": 0.10547975078225136,
|
|
"num_tokens": 1012220.0,
|
|
"step": 465
|
|
},
|
|
{
|
|
"entropy": 7.1531280994415285,
|
|
"epoch": 0.04664549424374752,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00023449999999999998,
|
|
"loss": 6.6543,
|
|
"mean_token_accuracy": 0.10063310712575912,
|
|
"num_tokens": 1022968.0,
|
|
"step": 470
|
|
},
|
|
{
|
|
"entropy": 7.094948148727417,
|
|
"epoch": 0.04714172290591505,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000237,
|
|
"loss": 6.6873,
|
|
"mean_token_accuracy": 0.10046143010258675,
|
|
"num_tokens": 1033415.0,
|
|
"step": 475
|
|
},
|
|
{
|
|
"entropy": 7.113246965408325,
|
|
"epoch": 0.04763795156808257,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0002395,
|
|
"loss": 6.597,
|
|
"mean_token_accuracy": 0.10691144168376923,
|
|
"num_tokens": 1045384.0,
|
|
"step": 480
|
|
},
|
|
{
|
|
"entropy": 7.089356851577759,
|
|
"epoch": 0.0481341802302501,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000242,
|
|
"loss": 6.6934,
|
|
"mean_token_accuracy": 0.10633598864078522,
|
|
"num_tokens": 1054982.0,
|
|
"step": 485
|
|
},
|
|
{
|
|
"entropy": 7.126608800888062,
|
|
"epoch": 0.048630408892417626,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0002445,
|
|
"loss": 6.6344,
|
|
"mean_token_accuracy": 0.10542937964200974,
|
|
"num_tokens": 1065244.0,
|
|
"step": 490
|
|
},
|
|
{
|
|
"entropy": 7.122588300704956,
|
|
"epoch": 0.04912663755458515,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000247,
|
|
"loss": 6.6503,
|
|
"mean_token_accuracy": 0.09597428143024445,
|
|
"num_tokens": 1075236.0,
|
|
"step": 495
|
|
},
|
|
{
|
|
"entropy": 7.064780902862549,
|
|
"epoch": 0.04962286621675268,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0002495,
|
|
"loss": 6.6788,
|
|
"mean_token_accuracy": 0.09427490904927253,
|
|
"num_tokens": 1085397.0,
|
|
"step": 500
|
|
},
|
|
{
|
|
"entropy": 7.108021450042725,
|
|
"epoch": 0.0501190948789202,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.000252,
|
|
"loss": 6.689,
|
|
"mean_token_accuracy": 0.10125237107276916,
|
|
"num_tokens": 1095207.0,
|
|
"step": 505
|
|
},
|
|
{
|
|
"entropy": 7.1391456604003904,
|
|
"epoch": 0.050615323541087734,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0002545,
|
|
"loss": 6.6822,
|
|
"mean_token_accuracy": 0.09262849614024163,
|
|
"num_tokens": 1105834.0,
|
|
"step": 510
|
|
},
|
|
{
|
|
"entropy": 7.115177631378174,
|
|
"epoch": 0.05111155220325526,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000257,
|
|
"loss": 6.6838,
|
|
"mean_token_accuracy": 0.1050037071108818,
|
|
"num_tokens": 1116105.0,
|
|
"step": 515
|
|
},
|
|
{
|
|
"entropy": 7.111266660690307,
|
|
"epoch": 0.05160778086542279,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0002595,
|
|
"loss": 6.6664,
|
|
"mean_token_accuracy": 0.10681836828589439,
|
|
"num_tokens": 1125298.0,
|
|
"step": 520
|
|
},
|
|
{
|
|
"entropy": 7.122176456451416,
|
|
"epoch": 0.05210400952759031,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.000262,
|
|
"loss": 6.6676,
|
|
"mean_token_accuracy": 0.10127982199192047,
|
|
"num_tokens": 1136797.0,
|
|
"step": 525
|
|
},
|
|
{
|
|
"entropy": 6.9743858814239506,
|
|
"epoch": 0.05260023818975784,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00026450000000000003,
|
|
"loss": 6.6766,
|
|
"mean_token_accuracy": 0.10087173655629159,
|
|
"num_tokens": 1148674.0,
|
|
"step": 530
|
|
},
|
|
{
|
|
"entropy": 7.159593200683593,
|
|
"epoch": 0.053096466851925365,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.00026700000000000004,
|
|
"loss": 6.7479,
|
|
"mean_token_accuracy": 0.09798325300216675,
|
|
"num_tokens": 1160329.0,
|
|
"step": 535
|
|
},
|
|
{
|
|
"entropy": 7.162366485595703,
|
|
"epoch": 0.053592695514092896,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00026950000000000005,
|
|
"loss": 6.6908,
|
|
"mean_token_accuracy": 0.09893349334597587,
|
|
"num_tokens": 1170318.0,
|
|
"step": 540
|
|
},
|
|
{
|
|
"entropy": 6.988642835617066,
|
|
"epoch": 0.05408892417626042,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00027200000000000005,
|
|
"loss": 6.5561,
|
|
"mean_token_accuracy": 0.11139835193753242,
|
|
"num_tokens": 1181634.0,
|
|
"step": 545
|
|
},
|
|
{
|
|
"entropy": 7.042670631408692,
|
|
"epoch": 0.05458515283842795,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0002745,
|
|
"loss": 6.6219,
|
|
"mean_token_accuracy": 0.10727389231324196,
|
|
"num_tokens": 1191829.0,
|
|
"step": 550
|
|
},
|
|
{
|
|
"entropy": 6.997174549102783,
|
|
"epoch": 0.055081381500595473,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000277,
|
|
"loss": 6.61,
|
|
"mean_token_accuracy": 0.10348387435078621,
|
|
"num_tokens": 1202265.0,
|
|
"step": 555
|
|
},
|
|
{
|
|
"entropy": 7.030418825149536,
|
|
"epoch": 0.055577610162763004,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0002795,
|
|
"loss": 6.6235,
|
|
"mean_token_accuracy": 0.10154768601059913,
|
|
"num_tokens": 1214173.0,
|
|
"step": 560
|
|
},
|
|
{
|
|
"entropy": 7.092197895050049,
|
|
"epoch": 0.05607383882493053,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00028199999999999997,
|
|
"loss": 6.5238,
|
|
"mean_token_accuracy": 0.10746525302529335,
|
|
"num_tokens": 1224582.0,
|
|
"step": 565
|
|
},
|
|
{
|
|
"entropy": 7.052742052078247,
|
|
"epoch": 0.05657006748709806,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0002845,
|
|
"loss": 6.7535,
|
|
"mean_token_accuracy": 0.09928297400474548,
|
|
"num_tokens": 1235865.0,
|
|
"step": 570
|
|
},
|
|
{
|
|
"entropy": 6.987533903121948,
|
|
"epoch": 0.05706629614926558,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000287,
|
|
"loss": 6.5779,
|
|
"mean_token_accuracy": 0.10504852086305619,
|
|
"num_tokens": 1247194.0,
|
|
"step": 575
|
|
},
|
|
{
|
|
"entropy": 6.921913146972656,
|
|
"epoch": 0.057562524811433105,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0002895,
|
|
"loss": 6.59,
|
|
"mean_token_accuracy": 0.09689045846462249,
|
|
"num_tokens": 1257981.0,
|
|
"step": 580
|
|
},
|
|
{
|
|
"entropy": 7.040601444244385,
|
|
"epoch": 0.058058753473600636,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.000292,
|
|
"loss": 6.553,
|
|
"mean_token_accuracy": 0.10087601393461228,
|
|
"num_tokens": 1268443.0,
|
|
"step": 585
|
|
},
|
|
{
|
|
"entropy": 7.027150583267212,
|
|
"epoch": 0.05855498213576816,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0002945,
|
|
"loss": 6.666,
|
|
"mean_token_accuracy": 0.10131042078137398,
|
|
"num_tokens": 1279134.0,
|
|
"step": 590
|
|
},
|
|
{
|
|
"entropy": 6.966839933395386,
|
|
"epoch": 0.05905121079793569,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000297,
|
|
"loss": 6.6183,
|
|
"mean_token_accuracy": 0.09604747295379638,
|
|
"num_tokens": 1289965.0,
|
|
"step": 595
|
|
},
|
|
{
|
|
"entropy": 7.076975393295288,
|
|
"epoch": 0.05954743946010321,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0002995,
|
|
"loss": 6.5411,
|
|
"mean_token_accuracy": 0.10592939630150795,
|
|
"num_tokens": 1300003.0,
|
|
"step": 600
|
|
},
|
|
{
|
|
"entropy": 6.961626815795898,
|
|
"epoch": 0.060043668122270744,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.000302,
|
|
"loss": 6.608,
|
|
"mean_token_accuracy": 0.10380170494318008,
|
|
"num_tokens": 1311990.0,
|
|
"step": 605
|
|
},
|
|
{
|
|
"entropy": 6.9057409286499025,
|
|
"epoch": 0.06053989678443827,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0003045,
|
|
"loss": 6.6506,
|
|
"mean_token_accuracy": 0.10116632953286171,
|
|
"num_tokens": 1322963.0,
|
|
"step": 610
|
|
},
|
|
{
|
|
"entropy": 7.0877197742462155,
|
|
"epoch": 0.0610361254466058,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.000307,
|
|
"loss": 6.6589,
|
|
"mean_token_accuracy": 0.09740115106105804,
|
|
"num_tokens": 1334580.0,
|
|
"step": 615
|
|
},
|
|
{
|
|
"entropy": 7.017366170883179,
|
|
"epoch": 0.06153235410877332,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0003095,
|
|
"loss": 6.6027,
|
|
"mean_token_accuracy": 0.10138308554887772,
|
|
"num_tokens": 1346545.0,
|
|
"step": 620
|
|
},
|
|
{
|
|
"entropy": 7.022233295440674,
|
|
"epoch": 0.06202858277094085,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.000312,
|
|
"loss": 6.5788,
|
|
"mean_token_accuracy": 0.10256645902991295,
|
|
"num_tokens": 1358375.0,
|
|
"step": 625
|
|
},
|
|
{
|
|
"entropy": 6.930924749374389,
|
|
"epoch": 0.06252481143310838,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0003145,
|
|
"loss": 6.6474,
|
|
"mean_token_accuracy": 0.09666800163686276,
|
|
"num_tokens": 1368376.0,
|
|
"step": 630
|
|
},
|
|
{
|
|
"entropy": 7.004555892944336,
|
|
"epoch": 0.0630210400952759,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000317,
|
|
"loss": 6.539,
|
|
"mean_token_accuracy": 0.1008249580860138,
|
|
"num_tokens": 1377749.0,
|
|
"step": 635
|
|
},
|
|
{
|
|
"entropy": 6.925582361221314,
|
|
"epoch": 0.06351726875744343,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0003195,
|
|
"loss": 6.6182,
|
|
"mean_token_accuracy": 0.1026754193007946,
|
|
"num_tokens": 1389581.0,
|
|
"step": 640
|
|
},
|
|
{
|
|
"entropy": 6.8830712795257565,
|
|
"epoch": 0.06401349741961096,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.000322,
|
|
"loss": 6.5373,
|
|
"mean_token_accuracy": 0.10198206380009651,
|
|
"num_tokens": 1399772.0,
|
|
"step": 645
|
|
},
|
|
{
|
|
"entropy": 6.992895269393921,
|
|
"epoch": 0.06450972608177849,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00032450000000000003,
|
|
"loss": 6.6367,
|
|
"mean_token_accuracy": 0.10756797865033149,
|
|
"num_tokens": 1411158.0,
|
|
"step": 650
|
|
},
|
|
{
|
|
"entropy": 6.994899320602417,
|
|
"epoch": 0.065005954743946,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00032700000000000003,
|
|
"loss": 6.5465,
|
|
"mean_token_accuracy": 0.1033245749771595,
|
|
"num_tokens": 1420651.0,
|
|
"step": 655
|
|
},
|
|
{
|
|
"entropy": 6.84561710357666,
|
|
"epoch": 0.06550218340611354,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00032950000000000004,
|
|
"loss": 6.4921,
|
|
"mean_token_accuracy": 0.10640839785337448,
|
|
"num_tokens": 1431628.0,
|
|
"step": 660
|
|
},
|
|
{
|
|
"entropy": 6.88475866317749,
|
|
"epoch": 0.06599841206828107,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00033200000000000005,
|
|
"loss": 6.5142,
|
|
"mean_token_accuracy": 0.10272238478064537,
|
|
"num_tokens": 1441850.0,
|
|
"step": 665
|
|
},
|
|
{
|
|
"entropy": 7.0489623069763185,
|
|
"epoch": 0.06649464073044858,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00033450000000000005,
|
|
"loss": 6.5969,
|
|
"mean_token_accuracy": 0.10575282126665116,
|
|
"num_tokens": 1452393.0,
|
|
"step": 670
|
|
},
|
|
{
|
|
"entropy": 6.8803466796875,
|
|
"epoch": 0.06699086939261611,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.000337,
|
|
"loss": 6.5199,
|
|
"mean_token_accuracy": 0.10531659424304962,
|
|
"num_tokens": 1463109.0,
|
|
"step": 675
|
|
},
|
|
{
|
|
"entropy": 6.860003042221069,
|
|
"epoch": 0.06748709805478365,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0003395,
|
|
"loss": 6.6383,
|
|
"mean_token_accuracy": 0.1039490133523941,
|
|
"num_tokens": 1475082.0,
|
|
"step": 680
|
|
},
|
|
{
|
|
"entropy": 6.982773113250732,
|
|
"epoch": 0.06798332671695118,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000342,
|
|
"loss": 6.5005,
|
|
"mean_token_accuracy": 0.10786980241537095,
|
|
"num_tokens": 1485477.0,
|
|
"step": 685
|
|
},
|
|
{
|
|
"entropy": 6.865319013595581,
|
|
"epoch": 0.06847955537911869,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00034449999999999997,
|
|
"loss": 6.4864,
|
|
"mean_token_accuracy": 0.10533245354890823,
|
|
"num_tokens": 1495422.0,
|
|
"step": 690
|
|
},
|
|
{
|
|
"entropy": 6.881680583953857,
|
|
"epoch": 0.06897578404128622,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000347,
|
|
"loss": 6.5021,
|
|
"mean_token_accuracy": 0.10336431041359902,
|
|
"num_tokens": 1506368.0,
|
|
"step": 695
|
|
},
|
|
{
|
|
"entropy": 6.89243106842041,
|
|
"epoch": 0.06947201270345375,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0003495,
|
|
"loss": 6.5205,
|
|
"mean_token_accuracy": 0.09701511636376381,
|
|
"num_tokens": 1517437.0,
|
|
"step": 700
|
|
},
|
|
{
|
|
"entropy": 6.802684307098389,
|
|
"epoch": 0.06996824136562128,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000352,
|
|
"loss": 6.4691,
|
|
"mean_token_accuracy": 0.10144305750727653,
|
|
"num_tokens": 1527801.0,
|
|
"step": 705
|
|
},
|
|
{
|
|
"entropy": 6.986940240859985,
|
|
"epoch": 0.0704644700277888,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0003545,
|
|
"loss": 6.5517,
|
|
"mean_token_accuracy": 0.09867026731371879,
|
|
"num_tokens": 1537621.0,
|
|
"step": 710
|
|
},
|
|
{
|
|
"entropy": 6.879312801361084,
|
|
"epoch": 0.07096069868995633,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000357,
|
|
"loss": 6.5558,
|
|
"mean_token_accuracy": 0.10100790783762932,
|
|
"num_tokens": 1549123.0,
|
|
"step": 715
|
|
},
|
|
{
|
|
"entropy": 6.8572304248809814,
|
|
"epoch": 0.07145692735212386,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0003595,
|
|
"loss": 6.5562,
|
|
"mean_token_accuracy": 0.10545549392700196,
|
|
"num_tokens": 1561167.0,
|
|
"step": 720
|
|
},
|
|
{
|
|
"entropy": 6.959098386764526,
|
|
"epoch": 0.07195315601429139,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000362,
|
|
"loss": 6.4677,
|
|
"mean_token_accuracy": 0.11058438867330551,
|
|
"num_tokens": 1571552.0,
|
|
"step": 725
|
|
},
|
|
{
|
|
"entropy": 6.7413163661956785,
|
|
"epoch": 0.07244938467645891,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0003645,
|
|
"loss": 6.4498,
|
|
"mean_token_accuracy": 0.10494914427399635,
|
|
"num_tokens": 1582558.0,
|
|
"step": 730
|
|
},
|
|
{
|
|
"entropy": 6.710915040969849,
|
|
"epoch": 0.07294561333862644,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000367,
|
|
"loss": 6.4301,
|
|
"mean_token_accuracy": 0.10837240293622016,
|
|
"num_tokens": 1595259.0,
|
|
"step": 735
|
|
},
|
|
{
|
|
"entropy": 6.876967239379883,
|
|
"epoch": 0.07344184200079397,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0003695,
|
|
"loss": 6.4578,
|
|
"mean_token_accuracy": 0.108952496945858,
|
|
"num_tokens": 1605585.0,
|
|
"step": 740
|
|
},
|
|
{
|
|
"entropy": 6.710470485687256,
|
|
"epoch": 0.07393807066296149,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.000372,
|
|
"loss": 6.4133,
|
|
"mean_token_accuracy": 0.10763250440359115,
|
|
"num_tokens": 1616529.0,
|
|
"step": 745
|
|
},
|
|
{
|
|
"entropy": 6.689630460739136,
|
|
"epoch": 0.07443429932512902,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0003745,
|
|
"loss": 6.3907,
|
|
"mean_token_accuracy": 0.10895837992429733,
|
|
"num_tokens": 1626223.0,
|
|
"step": 750
|
|
},
|
|
{
|
|
"entropy": 6.887076997756958,
|
|
"epoch": 0.07493052798729655,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.000377,
|
|
"loss": 6.5011,
|
|
"mean_token_accuracy": 0.10325393304228783,
|
|
"num_tokens": 1638173.0,
|
|
"step": 755
|
|
},
|
|
{
|
|
"entropy": 6.611377286911011,
|
|
"epoch": 0.07542675664946408,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0003795,
|
|
"loss": 6.3378,
|
|
"mean_token_accuracy": 0.11054935604333878,
|
|
"num_tokens": 1648919.0,
|
|
"step": 760
|
|
},
|
|
{
|
|
"entropy": 6.933552312850952,
|
|
"epoch": 0.0759229853116316,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.000382,
|
|
"loss": 6.5917,
|
|
"mean_token_accuracy": 0.09958057925105095,
|
|
"num_tokens": 1660704.0,
|
|
"step": 765
|
|
},
|
|
{
|
|
"entropy": 6.766306972503662,
|
|
"epoch": 0.07641921397379912,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0003845,
|
|
"loss": 6.49,
|
|
"mean_token_accuracy": 0.10253961160778999,
|
|
"num_tokens": 1672080.0,
|
|
"step": 770
|
|
},
|
|
{
|
|
"entropy": 6.803144121170044,
|
|
"epoch": 0.07691544263596665,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00038700000000000003,
|
|
"loss": 6.473,
|
|
"mean_token_accuracy": 0.10405055657029152,
|
|
"num_tokens": 1681930.0,
|
|
"step": 775
|
|
},
|
|
{
|
|
"entropy": 6.825759029388427,
|
|
"epoch": 0.07741167129813419,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00038950000000000003,
|
|
"loss": 6.4713,
|
|
"mean_token_accuracy": 0.10618199408054352,
|
|
"num_tokens": 1693075.0,
|
|
"step": 780
|
|
},
|
|
{
|
|
"entropy": 6.776135778427124,
|
|
"epoch": 0.0779078999603017,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.00039200000000000004,
|
|
"loss": 6.4653,
|
|
"mean_token_accuracy": 0.10373328626155853,
|
|
"num_tokens": 1704163.0,
|
|
"step": 785
|
|
},
|
|
{
|
|
"entropy": 6.840697479248047,
|
|
"epoch": 0.07840412862246923,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00039450000000000005,
|
|
"loss": 6.5917,
|
|
"mean_token_accuracy": 0.09998267292976379,
|
|
"num_tokens": 1714879.0,
|
|
"step": 790
|
|
},
|
|
{
|
|
"entropy": 6.849323797225952,
|
|
"epoch": 0.07890035728463676,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00039700000000000005,
|
|
"loss": 6.5946,
|
|
"mean_token_accuracy": 0.1017768420279026,
|
|
"num_tokens": 1725464.0,
|
|
"step": 795
|
|
},
|
|
{
|
|
"entropy": 6.930966424942016,
|
|
"epoch": 0.0793965859468043,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0003995,
|
|
"loss": 6.5356,
|
|
"mean_token_accuracy": 0.10469997599720955,
|
|
"num_tokens": 1736947.0,
|
|
"step": 800
|
|
},
|
|
{
|
|
"entropy": 6.695473623275757,
|
|
"epoch": 0.07989281460897181,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.000402,
|
|
"loss": 6.3539,
|
|
"mean_token_accuracy": 0.11638421043753625,
|
|
"num_tokens": 1746827.0,
|
|
"step": 805
|
|
},
|
|
{
|
|
"entropy": 6.899624872207641,
|
|
"epoch": 0.08038904327113934,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004045,
|
|
"loss": 6.5774,
|
|
"mean_token_accuracy": 0.10568423792719842,
|
|
"num_tokens": 1757079.0,
|
|
"step": 810
|
|
},
|
|
{
|
|
"entropy": 6.826183795928955,
|
|
"epoch": 0.08088527193330687,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00040699999999999997,
|
|
"loss": 6.5054,
|
|
"mean_token_accuracy": 0.1021289974451065,
|
|
"num_tokens": 1767684.0,
|
|
"step": 815
|
|
},
|
|
{
|
|
"entropy": 6.750361824035645,
|
|
"epoch": 0.0813815005954744,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004095,
|
|
"loss": 6.5018,
|
|
"mean_token_accuracy": 0.10343262404203415,
|
|
"num_tokens": 1778187.0,
|
|
"step": 820
|
|
},
|
|
{
|
|
"entropy": 6.833082675933838,
|
|
"epoch": 0.08187772925764192,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000412,
|
|
"loss": 6.4608,
|
|
"mean_token_accuracy": 0.10938398912549019,
|
|
"num_tokens": 1789139.0,
|
|
"step": 825
|
|
},
|
|
{
|
|
"entropy": 6.733291482925415,
|
|
"epoch": 0.08237395791980945,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004145,
|
|
"loss": 6.3351,
|
|
"mean_token_accuracy": 0.1136176273226738,
|
|
"num_tokens": 1799328.0,
|
|
"step": 830
|
|
},
|
|
{
|
|
"entropy": 6.741356658935547,
|
|
"epoch": 0.08287018658197698,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.000417,
|
|
"loss": 6.496,
|
|
"mean_token_accuracy": 0.10510264784097671,
|
|
"num_tokens": 1811487.0,
|
|
"step": 835
|
|
},
|
|
{
|
|
"entropy": 6.685542392730713,
|
|
"epoch": 0.0833664152441445,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004195,
|
|
"loss": 6.3968,
|
|
"mean_token_accuracy": 0.11166923865675926,
|
|
"num_tokens": 1821923.0,
|
|
"step": 840
|
|
},
|
|
{
|
|
"entropy": 6.720544052124024,
|
|
"epoch": 0.08386264390631203,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000422,
|
|
"loss": 6.402,
|
|
"mean_token_accuracy": 0.10754152461886406,
|
|
"num_tokens": 1833001.0,
|
|
"step": 845
|
|
},
|
|
{
|
|
"entropy": 6.761799335479736,
|
|
"epoch": 0.08435887256847956,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004245,
|
|
"loss": 6.4346,
|
|
"mean_token_accuracy": 0.10533890500664711,
|
|
"num_tokens": 1844473.0,
|
|
"step": 850
|
|
},
|
|
{
|
|
"entropy": 6.626788568496704,
|
|
"epoch": 0.08485510123064709,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.000427,
|
|
"loss": 6.3387,
|
|
"mean_token_accuracy": 0.11210601925849914,
|
|
"num_tokens": 1855851.0,
|
|
"step": 855
|
|
},
|
|
{
|
|
"entropy": 6.650875186920166,
|
|
"epoch": 0.0853513298928146,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004295,
|
|
"loss": 6.3262,
|
|
"mean_token_accuracy": 0.11055968850851058,
|
|
"num_tokens": 1866712.0,
|
|
"step": 860
|
|
},
|
|
{
|
|
"entropy": 6.77458963394165,
|
|
"epoch": 0.08584755855498213,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000432,
|
|
"loss": 6.3713,
|
|
"mean_token_accuracy": 0.10980789661407471,
|
|
"num_tokens": 1876443.0,
|
|
"step": 865
|
|
},
|
|
{
|
|
"entropy": 6.640477132797241,
|
|
"epoch": 0.08634378721714966,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004345,
|
|
"loss": 6.4319,
|
|
"mean_token_accuracy": 0.10897266939282417,
|
|
"num_tokens": 1886239.0,
|
|
"step": 870
|
|
},
|
|
{
|
|
"entropy": 6.729007625579834,
|
|
"epoch": 0.0868400158793172,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.000437,
|
|
"loss": 6.3736,
|
|
"mean_token_accuracy": 0.11199768409132957,
|
|
"num_tokens": 1896457.0,
|
|
"step": 875
|
|
},
|
|
{
|
|
"entropy": 6.60158052444458,
|
|
"epoch": 0.08733624454148471,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004395,
|
|
"loss": 6.3631,
|
|
"mean_token_accuracy": 0.10282145217061042,
|
|
"num_tokens": 1908068.0,
|
|
"step": 880
|
|
},
|
|
{
|
|
"entropy": 6.7822535037994385,
|
|
"epoch": 0.08783247320365224,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.000442,
|
|
"loss": 6.5282,
|
|
"mean_token_accuracy": 0.10227628946304321,
|
|
"num_tokens": 1920093.0,
|
|
"step": 885
|
|
},
|
|
{
|
|
"entropy": 6.631855154037476,
|
|
"epoch": 0.08832870186581977,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004445,
|
|
"loss": 6.312,
|
|
"mean_token_accuracy": 0.11389266178011895,
|
|
"num_tokens": 1930401.0,
|
|
"step": 890
|
|
},
|
|
{
|
|
"entropy": 6.710539054870606,
|
|
"epoch": 0.0888249305279873,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.000447,
|
|
"loss": 6.5031,
|
|
"mean_token_accuracy": 0.10445247143507004,
|
|
"num_tokens": 1940163.0,
|
|
"step": 895
|
|
},
|
|
{
|
|
"entropy": 6.6758523941040036,
|
|
"epoch": 0.08932115919015482,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00044950000000000003,
|
|
"loss": 6.3394,
|
|
"mean_token_accuracy": 0.10623634234070778,
|
|
"num_tokens": 1952455.0,
|
|
"step": 900
|
|
},
|
|
{
|
|
"entropy": 6.620533514022827,
|
|
"epoch": 0.08981738785232235,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00045200000000000004,
|
|
"loss": 6.4614,
|
|
"mean_token_accuracy": 0.1033598780632019,
|
|
"num_tokens": 1965079.0,
|
|
"step": 905
|
|
},
|
|
{
|
|
"entropy": 6.606557559967041,
|
|
"epoch": 0.09031361651448988,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00045450000000000004,
|
|
"loss": 6.3391,
|
|
"mean_token_accuracy": 0.10922778472304344,
|
|
"num_tokens": 1976620.0,
|
|
"step": 910
|
|
},
|
|
{
|
|
"entropy": 6.650234937667847,
|
|
"epoch": 0.0908098451766574,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00045700000000000005,
|
|
"loss": 6.3271,
|
|
"mean_token_accuracy": 0.10684251859784126,
|
|
"num_tokens": 1987626.0,
|
|
"step": 915
|
|
},
|
|
{
|
|
"entropy": 6.633430910110474,
|
|
"epoch": 0.09130607383882493,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.00045950000000000006,
|
|
"loss": 6.3545,
|
|
"mean_token_accuracy": 0.10809084251523018,
|
|
"num_tokens": 1998250.0,
|
|
"step": 920
|
|
},
|
|
{
|
|
"entropy": 6.696629190444947,
|
|
"epoch": 0.09180230250099246,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.000462,
|
|
"loss": 6.3446,
|
|
"mean_token_accuracy": 0.11614455357193947,
|
|
"num_tokens": 2008098.0,
|
|
"step": 925
|
|
},
|
|
{
|
|
"entropy": 6.514123439788818,
|
|
"epoch": 0.09229853116315999,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004645,
|
|
"loss": 6.3045,
|
|
"mean_token_accuracy": 0.10994884520769119,
|
|
"num_tokens": 2020125.0,
|
|
"step": 930
|
|
},
|
|
{
|
|
"entropy": 6.611006355285644,
|
|
"epoch": 0.0927947598253275,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.000467,
|
|
"loss": 6.4379,
|
|
"mean_token_accuracy": 0.11345969960093498,
|
|
"num_tokens": 2030791.0,
|
|
"step": 935
|
|
},
|
|
{
|
|
"entropy": 6.681372880935669,
|
|
"epoch": 0.09329098848749504,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004695,
|
|
"loss": 6.4183,
|
|
"mean_token_accuracy": 0.1092501424252987,
|
|
"num_tokens": 2042358.0,
|
|
"step": 940
|
|
},
|
|
{
|
|
"entropy": 6.599484062194824,
|
|
"epoch": 0.09378721714966257,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.000472,
|
|
"loss": 6.3679,
|
|
"mean_token_accuracy": 0.11037536859512329,
|
|
"num_tokens": 2054549.0,
|
|
"step": 945
|
|
},
|
|
{
|
|
"entropy": 6.597382736206055,
|
|
"epoch": 0.0942834458118301,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004745,
|
|
"loss": 6.3376,
|
|
"mean_token_accuracy": 0.11201154738664627,
|
|
"num_tokens": 2064903.0,
|
|
"step": 950
|
|
},
|
|
{
|
|
"entropy": 6.615338516235352,
|
|
"epoch": 0.09477967447399761,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000477,
|
|
"loss": 6.3146,
|
|
"mean_token_accuracy": 0.10975310951471329,
|
|
"num_tokens": 2075795.0,
|
|
"step": 955
|
|
},
|
|
{
|
|
"entropy": 6.57103590965271,
|
|
"epoch": 0.09527590313616514,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004795,
|
|
"loss": 6.3637,
|
|
"mean_token_accuracy": 0.10602563321590423,
|
|
"num_tokens": 2087249.0,
|
|
"step": 960
|
|
},
|
|
{
|
|
"entropy": 6.655970811843872,
|
|
"epoch": 0.09577213179833267,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000482,
|
|
"loss": 6.3354,
|
|
"mean_token_accuracy": 0.11833583116531372,
|
|
"num_tokens": 2097527.0,
|
|
"step": 965
|
|
},
|
|
{
|
|
"entropy": 6.562977027893067,
|
|
"epoch": 0.0962683604605002,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004845,
|
|
"loss": 6.3478,
|
|
"mean_token_accuracy": 0.11001443713903428,
|
|
"num_tokens": 2108174.0,
|
|
"step": 970
|
|
},
|
|
{
|
|
"entropy": 6.554857492446899,
|
|
"epoch": 0.09676458912266772,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.000487,
|
|
"loss": 6.3492,
|
|
"mean_token_accuracy": 0.1084967702627182,
|
|
"num_tokens": 2120355.0,
|
|
"step": 975
|
|
},
|
|
{
|
|
"entropy": 6.574288702011108,
|
|
"epoch": 0.09726081778483525,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004895,
|
|
"loss": 6.2304,
|
|
"mean_token_accuracy": 0.11568673327565193,
|
|
"num_tokens": 2130861.0,
|
|
"step": 980
|
|
},
|
|
{
|
|
"entropy": 6.584482145309448,
|
|
"epoch": 0.09775704644700278,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000492,
|
|
"loss": 6.3911,
|
|
"mean_token_accuracy": 0.1085393950343132,
|
|
"num_tokens": 2142162.0,
|
|
"step": 985
|
|
},
|
|
{
|
|
"entropy": 6.594986820220948,
|
|
"epoch": 0.0982532751091703,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004945,
|
|
"loss": 6.318,
|
|
"mean_token_accuracy": 0.11034402921795845,
|
|
"num_tokens": 2153374.0,
|
|
"step": 990
|
|
},
|
|
{
|
|
"entropy": 6.524502325057983,
|
|
"epoch": 0.09874950377133783,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000497,
|
|
"loss": 6.2594,
|
|
"mean_token_accuracy": 0.10932201892137527,
|
|
"num_tokens": 2162941.0,
|
|
"step": 995
|
|
},
|
|
{
|
|
"entropy": 6.649286603927612,
|
|
"epoch": 0.09924573243350536,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004995,
|
|
"loss": 6.3437,
|
|
"mean_token_accuracy": 0.09899675399065018,
|
|
"num_tokens": 2172864.0,
|
|
"step": 1000
|
|
},
|
|
{
|
|
"entropy": 6.512604904174805,
|
|
"epoch": 0.09974196109567289,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004999999982145551,
|
|
"loss": 6.3648,
|
|
"mean_token_accuracy": 0.11348994895815849,
|
|
"num_tokens": 2184219.0,
|
|
"step": 1005
|
|
},
|
|
{
|
|
"entropy": 6.696617507934571,
|
|
"epoch": 0.1002381897578404,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999999909611855,
|
|
"loss": 6.3227,
|
|
"mean_token_accuracy": 0.10469643399119377,
|
|
"num_tokens": 2194788.0,
|
|
"step": 1010
|
|
},
|
|
{
|
|
"entropy": 6.4998678207397464,
|
|
"epoch": 0.10073441842000794,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004999999781283008,
|
|
"loss": 6.3441,
|
|
"mean_token_accuracy": 0.10121865943074226,
|
|
"num_tokens": 2205493.0,
|
|
"step": 1015
|
|
},
|
|
{
|
|
"entropy": 6.622814416885376,
|
|
"epoch": 0.10123064708217547,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004999999597159017,
|
|
"loss": 6.3603,
|
|
"mean_token_accuracy": 0.1107247956097126,
|
|
"num_tokens": 2215354.0,
|
|
"step": 1020
|
|
},
|
|
{
|
|
"entropy": 6.516401863098144,
|
|
"epoch": 0.101726875744343,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999999357239882,
|
|
"loss": 6.2838,
|
|
"mean_token_accuracy": 0.11005397066473961,
|
|
"num_tokens": 2225781.0,
|
|
"step": 1025
|
|
},
|
|
{
|
|
"entropy": 6.545648241043091,
|
|
"epoch": 0.10222310440651051,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004999999061525612,
|
|
"loss": 6.3517,
|
|
"mean_token_accuracy": 0.10768992081284523,
|
|
"num_tokens": 2236008.0,
|
|
"step": 1030
|
|
},
|
|
{
|
|
"entropy": 6.544310569763184,
|
|
"epoch": 0.10271933306867805,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004999998710016214,
|
|
"loss": 6.279,
|
|
"mean_token_accuracy": 0.1109216794371605,
|
|
"num_tokens": 2246998.0,
|
|
"step": 1035
|
|
},
|
|
{
|
|
"entropy": 6.540542888641357,
|
|
"epoch": 0.10321556173084558,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004999998302711696,
|
|
"loss": 6.3958,
|
|
"mean_token_accuracy": 0.10798945054411888,
|
|
"num_tokens": 2257451.0,
|
|
"step": 1040
|
|
},
|
|
{
|
|
"entropy": 6.618514966964722,
|
|
"epoch": 0.1037117903930131,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004999997839612069,
|
|
"loss": 6.3545,
|
|
"mean_token_accuracy": 0.1071122370660305,
|
|
"num_tokens": 2268151.0,
|
|
"step": 1045
|
|
},
|
|
{
|
|
"entropy": 6.563951921463013,
|
|
"epoch": 0.10420801905518062,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004999997320717342,
|
|
"loss": 6.3776,
|
|
"mean_token_accuracy": 0.10482034385204315,
|
|
"num_tokens": 2278924.0,
|
|
"step": 1050
|
|
},
|
|
{
|
|
"entropy": 6.501388168334961,
|
|
"epoch": 0.10470424771734815,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004999996746027531,
|
|
"loss": 6.3032,
|
|
"mean_token_accuracy": 0.11530704945325851,
|
|
"num_tokens": 2289229.0,
|
|
"step": 1055
|
|
},
|
|
{
|
|
"entropy": 6.539397239685059,
|
|
"epoch": 0.10520047637951568,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000499999611554265,
|
|
"loss": 6.3215,
|
|
"mean_token_accuracy": 0.1085787646472454,
|
|
"num_tokens": 2300203.0,
|
|
"step": 1060
|
|
},
|
|
{
|
|
"entropy": 6.557326984405518,
|
|
"epoch": 0.10569670504168321,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004999995429262712,
|
|
"loss": 6.3026,
|
|
"mean_token_accuracy": 0.11185992807149887,
|
|
"num_tokens": 2311991.0,
|
|
"step": 1065
|
|
},
|
|
{
|
|
"entropy": 6.499863815307617,
|
|
"epoch": 0.10619293370385073,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004999994687187737,
|
|
"loss": 6.2687,
|
|
"mean_token_accuracy": 0.10764180719852448,
|
|
"num_tokens": 2322110.0,
|
|
"step": 1070
|
|
},
|
|
{
|
|
"entropy": 6.537433528900147,
|
|
"epoch": 0.10668916236601826,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004999993889317742,
|
|
"loss": 6.3196,
|
|
"mean_token_accuracy": 0.1101168490946293,
|
|
"num_tokens": 2332439.0,
|
|
"step": 1075
|
|
},
|
|
{
|
|
"entropy": 6.4248419284820555,
|
|
"epoch": 0.10718539102818579,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999993035652746,
|
|
"loss": 6.1852,
|
|
"mean_token_accuracy": 0.11721493899822236,
|
|
"num_tokens": 2342339.0,
|
|
"step": 1080
|
|
},
|
|
{
|
|
"entropy": 6.510436201095581,
|
|
"epoch": 0.10768161969035331,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004999992126192771,
|
|
"loss": 6.324,
|
|
"mean_token_accuracy": 0.11845446228981019,
|
|
"num_tokens": 2353211.0,
|
|
"step": 1085
|
|
},
|
|
{
|
|
"entropy": 6.59377236366272,
|
|
"epoch": 0.10817784835252084,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.000499999116093784,
|
|
"loss": 6.363,
|
|
"mean_token_accuracy": 0.10857008323073387,
|
|
"num_tokens": 2364709.0,
|
|
"step": 1090
|
|
},
|
|
{
|
|
"entropy": 6.536841201782226,
|
|
"epoch": 0.10867407701468837,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999990139887976,
|
|
"loss": 6.2863,
|
|
"mean_token_accuracy": 0.10694537609815598,
|
|
"num_tokens": 2375095.0,
|
|
"step": 1095
|
|
},
|
|
{
|
|
"entropy": 6.508898782730102,
|
|
"epoch": 0.1091703056768559,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999989063043206,
|
|
"loss": 6.2757,
|
|
"mean_token_accuracy": 0.11252731531858444,
|
|
"num_tokens": 2384206.0,
|
|
"step": 1100
|
|
},
|
|
{
|
|
"entropy": 6.445655059814453,
|
|
"epoch": 0.10966653433902342,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004999987930403555,
|
|
"loss": 6.1962,
|
|
"mean_token_accuracy": 0.11554479971528053,
|
|
"num_tokens": 2395139.0,
|
|
"step": 1105
|
|
},
|
|
{
|
|
"entropy": 6.4702643871307375,
|
|
"epoch": 0.11016276300119095,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999986741969051,
|
|
"loss": 6.3234,
|
|
"mean_token_accuracy": 0.10869933143258095,
|
|
"num_tokens": 2405652.0,
|
|
"step": 1110
|
|
},
|
|
{
|
|
"entropy": 6.626315641403198,
|
|
"epoch": 0.11065899166335848,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004999985497739724,
|
|
"loss": 6.3295,
|
|
"mean_token_accuracy": 0.10884599313139916,
|
|
"num_tokens": 2416386.0,
|
|
"step": 1115
|
|
},
|
|
{
|
|
"entropy": 6.404276943206787,
|
|
"epoch": 0.11115522032552601,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999984197715606,
|
|
"loss": 6.3425,
|
|
"mean_token_accuracy": 0.10958480238914489,
|
|
"num_tokens": 2427807.0,
|
|
"step": 1120
|
|
},
|
|
{
|
|
"entropy": 6.543959474563598,
|
|
"epoch": 0.11165144898769352,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004999982841896728,
|
|
"loss": 6.2502,
|
|
"mean_token_accuracy": 0.11363493949174881,
|
|
"num_tokens": 2439481.0,
|
|
"step": 1125
|
|
},
|
|
{
|
|
"entropy": 6.478694009780884,
|
|
"epoch": 0.11214767764986106,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999981430283123,
|
|
"loss": 6.2981,
|
|
"mean_token_accuracy": 0.11177865490317344,
|
|
"num_tokens": 2449857.0,
|
|
"step": 1130
|
|
},
|
|
{
|
|
"entropy": 6.431196975708008,
|
|
"epoch": 0.11264390631202859,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004999979962874827,
|
|
"loss": 6.2159,
|
|
"mean_token_accuracy": 0.11506233438849449,
|
|
"num_tokens": 2461569.0,
|
|
"step": 1135
|
|
},
|
|
{
|
|
"entropy": 6.506372594833374,
|
|
"epoch": 0.11314013497419612,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004999978439671877,
|
|
"loss": 6.301,
|
|
"mean_token_accuracy": 0.11535706594586373,
|
|
"num_tokens": 2473255.0,
|
|
"step": 1140
|
|
},
|
|
{
|
|
"entropy": 6.511087560653687,
|
|
"epoch": 0.11363636363636363,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999976860674309,
|
|
"loss": 6.2554,
|
|
"mean_token_accuracy": 0.10890059396624566,
|
|
"num_tokens": 2484473.0,
|
|
"step": 1145
|
|
},
|
|
{
|
|
"entropy": 6.409585046768188,
|
|
"epoch": 0.11413259229853116,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999975225882164,
|
|
"loss": 6.2632,
|
|
"mean_token_accuracy": 0.11080945432186126,
|
|
"num_tokens": 2495652.0,
|
|
"step": 1150
|
|
},
|
|
{
|
|
"entropy": 6.538078832626343,
|
|
"epoch": 0.1146288209606987,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.000499997353529548,
|
|
"loss": 6.3189,
|
|
"mean_token_accuracy": 0.10957048162817955,
|
|
"num_tokens": 2507137.0,
|
|
"step": 1155
|
|
},
|
|
{
|
|
"entropy": 6.4585597038269045,
|
|
"epoch": 0.11512504962286621,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999971788914303,
|
|
"loss": 6.2365,
|
|
"mean_token_accuracy": 0.11182398498058319,
|
|
"num_tokens": 2517896.0,
|
|
"step": 1160
|
|
},
|
|
{
|
|
"entropy": 6.409658336639405,
|
|
"epoch": 0.11562127828503374,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004999969986738672,
|
|
"loss": 6.2389,
|
|
"mean_token_accuracy": 0.11219030469655991,
|
|
"num_tokens": 2529976.0,
|
|
"step": 1165
|
|
},
|
|
{
|
|
"entropy": 6.589641475677491,
|
|
"epoch": 0.11611750694720127,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999968128768634,
|
|
"loss": 6.2993,
|
|
"mean_token_accuracy": 0.10817597731947899,
|
|
"num_tokens": 2540872.0,
|
|
"step": 1170
|
|
},
|
|
{
|
|
"entropy": 6.4878946304321286,
|
|
"epoch": 0.1166137356093688,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999966215004236,
|
|
"loss": 6.3182,
|
|
"mean_token_accuracy": 0.10902737304568291,
|
|
"num_tokens": 2551178.0,
|
|
"step": 1175
|
|
},
|
|
{
|
|
"entropy": 6.421410703659058,
|
|
"epoch": 0.11710996427153632,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004999964245445522,
|
|
"loss": 6.2131,
|
|
"mean_token_accuracy": 0.11171767115592957,
|
|
"num_tokens": 2561472.0,
|
|
"step": 1180
|
|
},
|
|
{
|
|
"entropy": 6.479715394973755,
|
|
"epoch": 0.11760619293370385,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999962220092545,
|
|
"loss": 6.2229,
|
|
"mean_token_accuracy": 0.10870179533958435,
|
|
"num_tokens": 2572717.0,
|
|
"step": 1185
|
|
},
|
|
{
|
|
"entropy": 6.373128843307495,
|
|
"epoch": 0.11810242159587138,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004999960138945351,
|
|
"loss": 6.1331,
|
|
"mean_token_accuracy": 0.1215246357023716,
|
|
"num_tokens": 2582991.0,
|
|
"step": 1190
|
|
},
|
|
{
|
|
"entropy": 6.388510036468506,
|
|
"epoch": 0.11859865025803891,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999958002003996,
|
|
"loss": 6.2167,
|
|
"mean_token_accuracy": 0.11683873906731605,
|
|
"num_tokens": 2594872.0,
|
|
"step": 1195
|
|
},
|
|
{
|
|
"entropy": 6.415997266769409,
|
|
"epoch": 0.11909487892020643,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004999955809268529,
|
|
"loss": 6.2267,
|
|
"mean_token_accuracy": 0.11254609376192093,
|
|
"num_tokens": 2605991.0,
|
|
"step": 1200
|
|
},
|
|
{
|
|
"entropy": 6.393628072738648,
|
|
"epoch": 0.11959110758237396,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004999953560739008,
|
|
"loss": 6.247,
|
|
"mean_token_accuracy": 0.11305257230997086,
|
|
"num_tokens": 2617613.0,
|
|
"step": 1205
|
|
},
|
|
{
|
|
"entropy": 6.516189765930176,
|
|
"epoch": 0.12008733624454149,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004999951256415485,
|
|
"loss": 6.3355,
|
|
"mean_token_accuracy": 0.1064811147749424,
|
|
"num_tokens": 2627724.0,
|
|
"step": 1210
|
|
},
|
|
{
|
|
"entropy": 6.452616119384766,
|
|
"epoch": 0.12058356490670902,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.000499994889629802,
|
|
"loss": 6.2306,
|
|
"mean_token_accuracy": 0.1097794696688652,
|
|
"num_tokens": 2638944.0,
|
|
"step": 1215
|
|
},
|
|
{
|
|
"entropy": 6.364139032363892,
|
|
"epoch": 0.12107979356887653,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000499994648038667,
|
|
"loss": 6.0846,
|
|
"mean_token_accuracy": 0.12294464185833931,
|
|
"num_tokens": 2649132.0,
|
|
"step": 1220
|
|
},
|
|
{
|
|
"entropy": 6.4025427341461185,
|
|
"epoch": 0.12157602223104406,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004999944008681496,
|
|
"loss": 6.2173,
|
|
"mean_token_accuracy": 0.10822719931602479,
|
|
"num_tokens": 2660482.0,
|
|
"step": 1225
|
|
},
|
|
{
|
|
"entropy": 6.506667852401733,
|
|
"epoch": 0.1220722508932116,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004999941481182559,
|
|
"loss": 6.2818,
|
|
"mean_token_accuracy": 0.10780982449650764,
|
|
"num_tokens": 2672953.0,
|
|
"step": 1230
|
|
},
|
|
{
|
|
"entropy": 6.3546521186828615,
|
|
"epoch": 0.12256847955537911,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004999938897889921,
|
|
"loss": 6.1948,
|
|
"mean_token_accuracy": 0.11872131600975991,
|
|
"num_tokens": 2684958.0,
|
|
"step": 1235
|
|
},
|
|
{
|
|
"entropy": 6.4603499412536625,
|
|
"epoch": 0.12306470821754664,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999936258803647,
|
|
"loss": 6.2033,
|
|
"mean_token_accuracy": 0.1136890321969986,
|
|
"num_tokens": 2695375.0,
|
|
"step": 1240
|
|
},
|
|
{
|
|
"entropy": 6.467173624038696,
|
|
"epoch": 0.12356093687971417,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004999933563923802,
|
|
"loss": 6.373,
|
|
"mean_token_accuracy": 0.10880970358848571,
|
|
"num_tokens": 2707762.0,
|
|
"step": 1245
|
|
},
|
|
{
|
|
"entropy": 6.37615966796875,
|
|
"epoch": 0.1240571655418817,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004999930813250451,
|
|
"loss": 6.1962,
|
|
"mean_token_accuracy": 0.11519552767276764,
|
|
"num_tokens": 2718237.0,
|
|
"step": 1250
|
|
},
|
|
{
|
|
"entropy": 6.407051467895508,
|
|
"epoch": 0.12455339420404922,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004999928006783667,
|
|
"loss": 6.1689,
|
|
"mean_token_accuracy": 0.1186670869588852,
|
|
"num_tokens": 2728746.0,
|
|
"step": 1255
|
|
},
|
|
{
|
|
"entropy": 6.4216368198394775,
|
|
"epoch": 0.12504962286621676,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999925144523515,
|
|
"loss": 6.1714,
|
|
"mean_token_accuracy": 0.11274236291646958,
|
|
"num_tokens": 2739030.0,
|
|
"step": 1260
|
|
},
|
|
{
|
|
"entropy": 6.250958776473999,
|
|
"epoch": 0.12554585152838427,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004999922226470066,
|
|
"loss": 6.1324,
|
|
"mean_token_accuracy": 0.12048356831073762,
|
|
"num_tokens": 2750233.0,
|
|
"step": 1265
|
|
},
|
|
{
|
|
"entropy": 6.451997470855713,
|
|
"epoch": 0.1260420801905518,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004999919252623397,
|
|
"loss": 6.2138,
|
|
"mean_token_accuracy": 0.10769852250814438,
|
|
"num_tokens": 2761298.0,
|
|
"step": 1270
|
|
},
|
|
{
|
|
"entropy": 6.400608777999878,
|
|
"epoch": 0.12653830885271933,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004999916222983577,
|
|
"loss": 6.2612,
|
|
"mean_token_accuracy": 0.11032301038503647,
|
|
"num_tokens": 2771493.0,
|
|
"step": 1275
|
|
},
|
|
{
|
|
"entropy": 6.354720497131348,
|
|
"epoch": 0.12703453751488686,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004999913137550682,
|
|
"loss": 6.1673,
|
|
"mean_token_accuracy": 0.11023365557193757,
|
|
"num_tokens": 2782969.0,
|
|
"step": 1280
|
|
},
|
|
{
|
|
"entropy": 6.468644714355468,
|
|
"epoch": 0.1275307661770544,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999909996324791,
|
|
"loss": 6.1993,
|
|
"mean_token_accuracy": 0.11823943629860878,
|
|
"num_tokens": 2793355.0,
|
|
"step": 1285
|
|
},
|
|
{
|
|
"entropy": 6.278990459442139,
|
|
"epoch": 0.12802699483922192,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.000499990679930598,
|
|
"loss": 6.1114,
|
|
"mean_token_accuracy": 0.11726746633648873,
|
|
"num_tokens": 2804473.0,
|
|
"step": 1290
|
|
},
|
|
{
|
|
"entropy": 6.389729928970337,
|
|
"epoch": 0.12852322350138945,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004999903546494327,
|
|
"loss": 6.1831,
|
|
"mean_token_accuracy": 0.11785808727145194,
|
|
"num_tokens": 2814899.0,
|
|
"step": 1295
|
|
},
|
|
{
|
|
"entropy": 6.435607671737671,
|
|
"epoch": 0.12901945216355698,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004999900237889916,
|
|
"loss": 6.2205,
|
|
"mean_token_accuracy": 0.11157539635896682,
|
|
"num_tokens": 2825592.0,
|
|
"step": 1300
|
|
},
|
|
{
|
|
"entropy": 6.323909330368042,
|
|
"epoch": 0.12951568082572448,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999896873492827,
|
|
"loss": 6.2083,
|
|
"mean_token_accuracy": 0.11462137624621391,
|
|
"num_tokens": 2837444.0,
|
|
"step": 1305
|
|
},
|
|
{
|
|
"entropy": 6.432302522659302,
|
|
"epoch": 0.130011909487892,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004999893453303143,
|
|
"loss": 6.2024,
|
|
"mean_token_accuracy": 0.11139100939035415,
|
|
"num_tokens": 2849256.0,
|
|
"step": 1310
|
|
},
|
|
{
|
|
"entropy": 6.387406969070435,
|
|
"epoch": 0.13050813815005954,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999889977320949,
|
|
"loss": 6.2585,
|
|
"mean_token_accuracy": 0.11350850909948348,
|
|
"num_tokens": 2860606.0,
|
|
"step": 1315
|
|
},
|
|
{
|
|
"entropy": 6.396147966384888,
|
|
"epoch": 0.13100436681222707,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004999886445546332,
|
|
"loss": 6.1914,
|
|
"mean_token_accuracy": 0.12097390070557594,
|
|
"num_tokens": 2871825.0,
|
|
"step": 1320
|
|
},
|
|
{
|
|
"entropy": 6.425122690200806,
|
|
"epoch": 0.1315005954743946,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.000499988285797938,
|
|
"loss": 6.2041,
|
|
"mean_token_accuracy": 0.12094095051288604,
|
|
"num_tokens": 2883408.0,
|
|
"step": 1325
|
|
},
|
|
{
|
|
"entropy": 6.322391223907471,
|
|
"epoch": 0.13199682413656214,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.000499987921462018,
|
|
"loss": 6.1787,
|
|
"mean_token_accuracy": 0.12214997559785842,
|
|
"num_tokens": 2895786.0,
|
|
"step": 1330
|
|
},
|
|
{
|
|
"entropy": 6.381843423843383,
|
|
"epoch": 0.13249305279872967,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999875515468825,
|
|
"loss": 6.178,
|
|
"mean_token_accuracy": 0.11670075803995132,
|
|
"num_tokens": 2905273.0,
|
|
"step": 1335
|
|
},
|
|
{
|
|
"entropy": 6.471662425994873,
|
|
"epoch": 0.13298928146089717,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004999871760525403,
|
|
"loss": 6.2786,
|
|
"mean_token_accuracy": 0.10916746258735657,
|
|
"num_tokens": 2917546.0,
|
|
"step": 1340
|
|
},
|
|
{
|
|
"entropy": 6.495834398269653,
|
|
"epoch": 0.1334855101230647,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999867949790011,
|
|
"loss": 6.2294,
|
|
"mean_token_accuracy": 0.11407745182514191,
|
|
"num_tokens": 2928715.0,
|
|
"step": 1345
|
|
},
|
|
{
|
|
"entropy": 6.333612298965454,
|
|
"epoch": 0.13398173878523223,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004999864083262743,
|
|
"loss": 6.17,
|
|
"mean_token_accuracy": 0.11962553858757019,
|
|
"num_tokens": 2940260.0,
|
|
"step": 1350
|
|
},
|
|
{
|
|
"entropy": 6.396699094772339,
|
|
"epoch": 0.13447796744739976,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004999860160943691,
|
|
"loss": 6.1696,
|
|
"mean_token_accuracy": 0.1181778758764267,
|
|
"num_tokens": 2951543.0,
|
|
"step": 1355
|
|
},
|
|
{
|
|
"entropy": 6.358440589904785,
|
|
"epoch": 0.1349741961095673,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004999856182832958,
|
|
"loss": 6.2075,
|
|
"mean_token_accuracy": 0.11538006886839866,
|
|
"num_tokens": 2962504.0,
|
|
"step": 1360
|
|
},
|
|
{
|
|
"entropy": 6.349350261688232,
|
|
"epoch": 0.13547042477173482,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004999852148930637,
|
|
"loss": 6.1291,
|
|
"mean_token_accuracy": 0.12085686475038529,
|
|
"num_tokens": 2973784.0,
|
|
"step": 1365
|
|
},
|
|
{
|
|
"entropy": 6.387005567550659,
|
|
"epoch": 0.13596665343390235,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999848059236832,
|
|
"loss": 6.2569,
|
|
"mean_token_accuracy": 0.10802673473954201,
|
|
"num_tokens": 2985281.0,
|
|
"step": 1370
|
|
},
|
|
{
|
|
"entropy": 6.308599185943604,
|
|
"epoch": 0.13646288209606988,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004999843913751643,
|
|
"loss": 6.1018,
|
|
"mean_token_accuracy": 0.12057043686509132,
|
|
"num_tokens": 2996090.0,
|
|
"step": 1375
|
|
},
|
|
{
|
|
"entropy": 6.370522308349609,
|
|
"epoch": 0.13695911075823738,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004999839712475174,
|
|
"loss": 6.1337,
|
|
"mean_token_accuracy": 0.11793153062462806,
|
|
"num_tokens": 3006235.0,
|
|
"step": 1380
|
|
},
|
|
{
|
|
"entropy": 6.298479413986206,
|
|
"epoch": 0.13745533942040492,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004999835455407526,
|
|
"loss": 6.1056,
|
|
"mean_token_accuracy": 0.1146063707768917,
|
|
"num_tokens": 3016481.0,
|
|
"step": 1385
|
|
},
|
|
{
|
|
"entropy": 6.411545610427856,
|
|
"epoch": 0.13795156808257245,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999831142548808,
|
|
"loss": 6.162,
|
|
"mean_token_accuracy": 0.12275284230709076,
|
|
"num_tokens": 3026382.0,
|
|
"step": 1390
|
|
},
|
|
{
|
|
"entropy": 6.287210941314697,
|
|
"epoch": 0.13844779674473998,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999826773899124,
|
|
"loss": 6.1672,
|
|
"mean_token_accuracy": 0.10925834402441978,
|
|
"num_tokens": 3036637.0,
|
|
"step": 1395
|
|
},
|
|
{
|
|
"entropy": 6.356094312667847,
|
|
"epoch": 0.1389440254069075,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004999822349458586,
|
|
"loss": 6.2199,
|
|
"mean_token_accuracy": 0.11081714704632759,
|
|
"num_tokens": 3047115.0,
|
|
"step": 1400
|
|
},
|
|
{
|
|
"entropy": 6.465851879119873,
|
|
"epoch": 0.13944025406907504,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004999817869227301,
|
|
"loss": 6.2426,
|
|
"mean_token_accuracy": 0.11556067392230034,
|
|
"num_tokens": 3057499.0,
|
|
"step": 1405
|
|
},
|
|
{
|
|
"entropy": 6.309928035736084,
|
|
"epoch": 0.13993648273124257,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999813333205381,
|
|
"loss": 6.1574,
|
|
"mean_token_accuracy": 0.11418915838003159,
|
|
"num_tokens": 3068503.0,
|
|
"step": 1410
|
|
},
|
|
{
|
|
"entropy": 6.382554817199707,
|
|
"epoch": 0.14043271139341007,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004999808741392937,
|
|
"loss": 6.1352,
|
|
"mean_token_accuracy": 0.1202838383615017,
|
|
"num_tokens": 3079220.0,
|
|
"step": 1415
|
|
},
|
|
{
|
|
"entropy": 6.248684358596802,
|
|
"epoch": 0.1409289400555776,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004999804093790086,
|
|
"loss": 6.129,
|
|
"mean_token_accuracy": 0.12194435819983482,
|
|
"num_tokens": 3091621.0,
|
|
"step": 1420
|
|
},
|
|
{
|
|
"entropy": 6.3224715232849125,
|
|
"epoch": 0.14142516871774513,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000499979939039694,
|
|
"loss": 6.1108,
|
|
"mean_token_accuracy": 0.12159208208322525,
|
|
"num_tokens": 3101378.0,
|
|
"step": 1425
|
|
},
|
|
{
|
|
"entropy": 6.2528337955474855,
|
|
"epoch": 0.14192139737991266,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004999794631213618,
|
|
"loss": 6.1223,
|
|
"mean_token_accuracy": 0.11627830192446709,
|
|
"num_tokens": 3112996.0,
|
|
"step": 1430
|
|
},
|
|
{
|
|
"entropy": 6.345195579528808,
|
|
"epoch": 0.1424176260420802,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004999789816240236,
|
|
"loss": 6.1233,
|
|
"mean_token_accuracy": 0.11082257777452469,
|
|
"num_tokens": 3124262.0,
|
|
"step": 1435
|
|
},
|
|
{
|
|
"entropy": 6.282847118377686,
|
|
"epoch": 0.14291385470424772,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999784945476915,
|
|
"loss": 6.1378,
|
|
"mean_token_accuracy": 0.11149395331740379,
|
|
"num_tokens": 3135785.0,
|
|
"step": 1440
|
|
},
|
|
{
|
|
"entropy": 6.278212022781372,
|
|
"epoch": 0.14341008336641525,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004999780018923775,
|
|
"loss": 6.0202,
|
|
"mean_token_accuracy": 0.12852933034300804,
|
|
"num_tokens": 3146841.0,
|
|
"step": 1445
|
|
},
|
|
{
|
|
"entropy": 6.276055955886841,
|
|
"epoch": 0.14390631202858278,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004999775036580939,
|
|
"loss": 6.1744,
|
|
"mean_token_accuracy": 0.11450461819767951,
|
|
"num_tokens": 3158931.0,
|
|
"step": 1450
|
|
},
|
|
{
|
|
"entropy": 6.341690492630005,
|
|
"epoch": 0.1444025406907503,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999769998448529,
|
|
"loss": 6.1153,
|
|
"mean_token_accuracy": 0.11504201218485832,
|
|
"num_tokens": 3169320.0,
|
|
"step": 1455
|
|
},
|
|
{
|
|
"entropy": 6.3100001335144045,
|
|
"epoch": 0.14489876935291782,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999764904526672,
|
|
"loss": 6.1483,
|
|
"mean_token_accuracy": 0.11918737143278121,
|
|
"num_tokens": 3179163.0,
|
|
"step": 1460
|
|
},
|
|
{
|
|
"entropy": 6.281153011322021,
|
|
"epoch": 0.14539499801508535,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999759754815492,
|
|
"loss": 6.083,
|
|
"mean_token_accuracy": 0.11143830195069312,
|
|
"num_tokens": 3187987.0,
|
|
"step": 1465
|
|
},
|
|
{
|
|
"entropy": 6.255558013916016,
|
|
"epoch": 0.14589122667725288,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004999754549315118,
|
|
"loss": 6.0775,
|
|
"mean_token_accuracy": 0.12257000356912613,
|
|
"num_tokens": 3198052.0,
|
|
"step": 1470
|
|
},
|
|
{
|
|
"entropy": 6.222886371612549,
|
|
"epoch": 0.1463874553394204,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.000499974928802568,
|
|
"loss": 6.0643,
|
|
"mean_token_accuracy": 0.11924131661653518,
|
|
"num_tokens": 3209019.0,
|
|
"step": 1475
|
|
},
|
|
{
|
|
"entropy": 6.209675025939942,
|
|
"epoch": 0.14688368400158794,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999743970947306,
|
|
"loss": 6.0273,
|
|
"mean_token_accuracy": 0.12434762641787529,
|
|
"num_tokens": 3219130.0,
|
|
"step": 1480
|
|
},
|
|
{
|
|
"entropy": 6.21720700263977,
|
|
"epoch": 0.14737991266375547,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.000499973859808013,
|
|
"loss": 6.0421,
|
|
"mean_token_accuracy": 0.12010939195752143,
|
|
"num_tokens": 3230882.0,
|
|
"step": 1485
|
|
},
|
|
{
|
|
"entropy": 6.222798299789429,
|
|
"epoch": 0.14787614132592297,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004999733169424284,
|
|
"loss": 6.1729,
|
|
"mean_token_accuracy": 0.11634461581707001,
|
|
"num_tokens": 3241752.0,
|
|
"step": 1490
|
|
},
|
|
{
|
|
"entropy": 6.488711023330689,
|
|
"epoch": 0.1483723699880905,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004999727684979904,
|
|
"loss": 6.1832,
|
|
"mean_token_accuracy": 0.11442616507411003,
|
|
"num_tokens": 3252291.0,
|
|
"step": 1495
|
|
},
|
|
{
|
|
"entropy": 6.317147922515869,
|
|
"epoch": 0.14886859865025803,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004999722144747125,
|
|
"loss": 6.0964,
|
|
"mean_token_accuracy": 0.11958790943026543,
|
|
"num_tokens": 3263525.0,
|
|
"step": 1500
|
|
},
|
|
{
|
|
"entropy": 6.26204400062561,
|
|
"epoch": 0.14936482731242556,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004999716548726085,
|
|
"loss": 6.0651,
|
|
"mean_token_accuracy": 0.12191420197486877,
|
|
"num_tokens": 3274164.0,
|
|
"step": 1505
|
|
},
|
|
{
|
|
"entropy": 6.1559864521026615,
|
|
"epoch": 0.1498610559745931,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004999710896916921,
|
|
"loss": 6.0561,
|
|
"mean_token_accuracy": 0.12110427170991897,
|
|
"num_tokens": 3286244.0,
|
|
"step": 1510
|
|
},
|
|
{
|
|
"entropy": 6.305137777328492,
|
|
"epoch": 0.15035728463676062,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004999705189319774,
|
|
"loss": 6.1474,
|
|
"mean_token_accuracy": 0.11220626085996628,
|
|
"num_tokens": 3296569.0,
|
|
"step": 1515
|
|
},
|
|
{
|
|
"entropy": 6.250655698776245,
|
|
"epoch": 0.15085351329892815,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004999699425934788,
|
|
"loss": 6.1675,
|
|
"mean_token_accuracy": 0.12036664485931396,
|
|
"num_tokens": 3307259.0,
|
|
"step": 1520
|
|
},
|
|
{
|
|
"entropy": 6.2826783657073975,
|
|
"epoch": 0.15134974196109569,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004999693606762103,
|
|
"loss": 5.9762,
|
|
"mean_token_accuracy": 0.12630216851830484,
|
|
"num_tokens": 3317473.0,
|
|
"step": 1525
|
|
},
|
|
{
|
|
"entropy": 6.221875429153442,
|
|
"epoch": 0.1518459706232632,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004999687731801865,
|
|
"loss": 6.0801,
|
|
"mean_token_accuracy": 0.11735879704356193,
|
|
"num_tokens": 3328783.0,
|
|
"step": 1530
|
|
},
|
|
{
|
|
"entropy": 6.221706104278565,
|
|
"epoch": 0.15234219928543072,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004999681801054217,
|
|
"loss": 6.1161,
|
|
"mean_token_accuracy": 0.11810076832771302,
|
|
"num_tokens": 3338308.0,
|
|
"step": 1535
|
|
},
|
|
{
|
|
"entropy": 6.273039722442627,
|
|
"epoch": 0.15283842794759825,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.000499967581451931,
|
|
"loss": 6.0367,
|
|
"mean_token_accuracy": 0.12085681930184364,
|
|
"num_tokens": 3348802.0,
|
|
"step": 1540
|
|
},
|
|
{
|
|
"entropy": 6.250692558288574,
|
|
"epoch": 0.15333465660976578,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000499966977219729,
|
|
"loss": 6.0505,
|
|
"mean_token_accuracy": 0.122286207228899,
|
|
"num_tokens": 3358781.0,
|
|
"step": 1545
|
|
},
|
|
{
|
|
"entropy": 6.182136583328247,
|
|
"epoch": 0.1538308852719333,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999663674088306,
|
|
"loss": 6.004,
|
|
"mean_token_accuracy": 0.12099720686674117,
|
|
"num_tokens": 3369360.0,
|
|
"step": 1550
|
|
},
|
|
{
|
|
"entropy": 6.30761604309082,
|
|
"epoch": 0.15432711393410084,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004999657520192511,
|
|
"loss": 6.1196,
|
|
"mean_token_accuracy": 0.11720000579953194,
|
|
"num_tokens": 3380111.0,
|
|
"step": 1555
|
|
},
|
|
{
|
|
"entropy": 6.182616472244263,
|
|
"epoch": 0.15482334259626837,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004999651310510058,
|
|
"loss": 6.0476,
|
|
"mean_token_accuracy": 0.12010963633656502,
|
|
"num_tokens": 3391932.0,
|
|
"step": 1560
|
|
},
|
|
{
|
|
"entropy": 6.286138010025025,
|
|
"epoch": 0.15531957125843587,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004999645045041099,
|
|
"loss": 6.0978,
|
|
"mean_token_accuracy": 0.11951644867658615,
|
|
"num_tokens": 3402192.0,
|
|
"step": 1565
|
|
},
|
|
{
|
|
"entropy": 6.25222749710083,
|
|
"epoch": 0.1558157999206034,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999638723785791,
|
|
"loss": 5.9897,
|
|
"mean_token_accuracy": 0.12218942567706108,
|
|
"num_tokens": 3412382.0,
|
|
"step": 1570
|
|
},
|
|
{
|
|
"entropy": 6.230171489715576,
|
|
"epoch": 0.15631202858277093,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.000499963234674429,
|
|
"loss": 6.0516,
|
|
"mean_token_accuracy": 0.11803107783198356,
|
|
"num_tokens": 3422471.0,
|
|
"step": 1575
|
|
},
|
|
{
|
|
"entropy": 6.2233234405517575,
|
|
"epoch": 0.15680825724493846,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004999625913916754,
|
|
"loss": 6.0301,
|
|
"mean_token_accuracy": 0.12271839007735252,
|
|
"num_tokens": 3432348.0,
|
|
"step": 1580
|
|
},
|
|
{
|
|
"entropy": 6.185507822036743,
|
|
"epoch": 0.157304485907106,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004999619425303343,
|
|
"loss": 6.0307,
|
|
"mean_token_accuracy": 0.11823347955942154,
|
|
"num_tokens": 3442549.0,
|
|
"step": 1585
|
|
},
|
|
{
|
|
"entropy": 6.245360565185547,
|
|
"epoch": 0.15780071456927353,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999612880904219,
|
|
"loss": 6.1235,
|
|
"mean_token_accuracy": 0.11440040320158004,
|
|
"num_tokens": 3452317.0,
|
|
"step": 1590
|
|
},
|
|
{
|
|
"entropy": 6.224632358551025,
|
|
"epoch": 0.15829694323144106,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004999606280719542,
|
|
"loss": 6.0532,
|
|
"mean_token_accuracy": 0.11879203096032143,
|
|
"num_tokens": 3463432.0,
|
|
"step": 1595
|
|
},
|
|
{
|
|
"entropy": 6.308253622055053,
|
|
"epoch": 0.1587931718936086,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004999599624749475,
|
|
"loss": 6.1023,
|
|
"mean_token_accuracy": 0.11679881960153579,
|
|
"num_tokens": 3473800.0,
|
|
"step": 1600
|
|
},
|
|
{
|
|
"entropy": 6.227562952041626,
|
|
"epoch": 0.1592894005557761,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999592912994187,
|
|
"loss": 6.0823,
|
|
"mean_token_accuracy": 0.11684635356068611,
|
|
"num_tokens": 3484803.0,
|
|
"step": 1605
|
|
},
|
|
{
|
|
"entropy": 6.235965061187744,
|
|
"epoch": 0.15978562921794362,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004999586145453842,
|
|
"loss": 6.0284,
|
|
"mean_token_accuracy": 0.12258547395467759,
|
|
"num_tokens": 3494687.0,
|
|
"step": 1610
|
|
},
|
|
{
|
|
"entropy": 6.244058561325073,
|
|
"epoch": 0.16028185788011115,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004999579322128608,
|
|
"loss": 6.0741,
|
|
"mean_token_accuracy": 0.11799983456730842,
|
|
"num_tokens": 3505586.0,
|
|
"step": 1615
|
|
},
|
|
{
|
|
"entropy": 6.10240535736084,
|
|
"epoch": 0.16077808654227868,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004999572443018654,
|
|
"loss": 5.9235,
|
|
"mean_token_accuracy": 0.13439927846193314,
|
|
"num_tokens": 3516702.0,
|
|
"step": 1620
|
|
},
|
|
{
|
|
"entropy": 6.232553434371948,
|
|
"epoch": 0.1612743152044462,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999565508124151,
|
|
"loss": 6.0416,
|
|
"mean_token_accuracy": 0.12300089374184608,
|
|
"num_tokens": 3527240.0,
|
|
"step": 1625
|
|
},
|
|
{
|
|
"entropy": 6.2715003490448,
|
|
"epoch": 0.16177054386661374,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.000499955851744527,
|
|
"loss": 6.1539,
|
|
"mean_token_accuracy": 0.11600246727466583,
|
|
"num_tokens": 3539368.0,
|
|
"step": 1630
|
|
},
|
|
{
|
|
"entropy": 6.200672674179077,
|
|
"epoch": 0.16226677252878127,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004999551470982185,
|
|
"loss": 6.0307,
|
|
"mean_token_accuracy": 0.12346499860286712,
|
|
"num_tokens": 3551128.0,
|
|
"step": 1635
|
|
},
|
|
{
|
|
"entropy": 6.121882009506225,
|
|
"epoch": 0.1627630011909488,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999544368735073,
|
|
"loss": 6.0322,
|
|
"mean_token_accuracy": 0.12636793553829193,
|
|
"num_tokens": 3562385.0,
|
|
"step": 1640
|
|
},
|
|
{
|
|
"entropy": 6.254643726348877,
|
|
"epoch": 0.1632592298531163,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004999537210704106,
|
|
"loss": 6.0262,
|
|
"mean_token_accuracy": 0.1224179670214653,
|
|
"num_tokens": 3572737.0,
|
|
"step": 1645
|
|
},
|
|
{
|
|
"entropy": 6.137145900726319,
|
|
"epoch": 0.16375545851528384,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999529996889463,
|
|
"loss": 6.0462,
|
|
"mean_token_accuracy": 0.11289570853114128,
|
|
"num_tokens": 3583872.0,
|
|
"step": 1650
|
|
},
|
|
{
|
|
"entropy": 6.286539888381958,
|
|
"epoch": 0.16425168717745137,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999522727291325,
|
|
"loss": 6.0236,
|
|
"mean_token_accuracy": 0.11809901297092437,
|
|
"num_tokens": 3595012.0,
|
|
"step": 1655
|
|
},
|
|
{
|
|
"entropy": 6.250521469116211,
|
|
"epoch": 0.1647479158396189,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000499951540190987,
|
|
"loss": 6.14,
|
|
"mean_token_accuracy": 0.11284013092517853,
|
|
"num_tokens": 3605733.0,
|
|
"step": 1660
|
|
},
|
|
{
|
|
"entropy": 6.2044517517089846,
|
|
"epoch": 0.16524414450178643,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999508020745281,
|
|
"loss": 6.0625,
|
|
"mean_token_accuracy": 0.12692697569727898,
|
|
"num_tokens": 3615997.0,
|
|
"step": 1665
|
|
},
|
|
{
|
|
"entropy": 6.166298866271973,
|
|
"epoch": 0.16574037316395396,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004999500583797739,
|
|
"loss": 6.0486,
|
|
"mean_token_accuracy": 0.12888892963528634,
|
|
"num_tokens": 3628742.0,
|
|
"step": 1670
|
|
},
|
|
{
|
|
"entropy": 6.150118827819824,
|
|
"epoch": 0.1662366018261215,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999493091067431,
|
|
"loss": 6.0301,
|
|
"mean_token_accuracy": 0.1232452742755413,
|
|
"num_tokens": 3639702.0,
|
|
"step": 1675
|
|
},
|
|
{
|
|
"entropy": 6.249062776565552,
|
|
"epoch": 0.166732830488289,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004999485542554541,
|
|
"loss": 6.0093,
|
|
"mean_token_accuracy": 0.12544036880135537,
|
|
"num_tokens": 3650414.0,
|
|
"step": 1680
|
|
},
|
|
{
|
|
"entropy": 6.117237901687622,
|
|
"epoch": 0.16722905915045652,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004999477938259256,
|
|
"loss": 5.9927,
|
|
"mean_token_accuracy": 0.11784988194704056,
|
|
"num_tokens": 3660739.0,
|
|
"step": 1685
|
|
},
|
|
{
|
|
"entropy": 6.2560646533966064,
|
|
"epoch": 0.16772528781262405,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004999470278181766,
|
|
"loss": 6.075,
|
|
"mean_token_accuracy": 0.12103780433535576,
|
|
"num_tokens": 3673109.0,
|
|
"step": 1690
|
|
},
|
|
{
|
|
"entropy": 6.2072841167449955,
|
|
"epoch": 0.16822151647479158,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999462562322261,
|
|
"loss": 6.0392,
|
|
"mean_token_accuracy": 0.123382568359375,
|
|
"num_tokens": 3683168.0,
|
|
"step": 1695
|
|
},
|
|
{
|
|
"entropy": 6.17884316444397,
|
|
"epoch": 0.1687177451369591,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.000499945479068093,
|
|
"loss": 6.0407,
|
|
"mean_token_accuracy": 0.12351762875914574,
|
|
"num_tokens": 3694309.0,
|
|
"step": 1700
|
|
},
|
|
{
|
|
"entropy": 6.194273328781128,
|
|
"epoch": 0.16921397379912664,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999446963257969,
|
|
"loss": 6.1322,
|
|
"mean_token_accuracy": 0.11986947655677796,
|
|
"num_tokens": 3706165.0,
|
|
"step": 1705
|
|
},
|
|
{
|
|
"entropy": 6.218581247329712,
|
|
"epoch": 0.16971020246129417,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004999439080053571,
|
|
"loss": 6.1305,
|
|
"mean_token_accuracy": 0.12079597637057304,
|
|
"num_tokens": 3717818.0,
|
|
"step": 1710
|
|
},
|
|
{
|
|
"entropy": 6.240843820571899,
|
|
"epoch": 0.1702064311234617,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999431141067928,
|
|
"loss": 5.9971,
|
|
"mean_token_accuracy": 0.1241668090224266,
|
|
"num_tokens": 3727837.0,
|
|
"step": 1715
|
|
},
|
|
{
|
|
"entropy": 6.140651416778565,
|
|
"epoch": 0.1707026597856292,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004999423146301242,
|
|
"loss": 5.9883,
|
|
"mean_token_accuracy": 0.11822554692626,
|
|
"num_tokens": 3738827.0,
|
|
"step": 1720
|
|
},
|
|
{
|
|
"entropy": 6.252899122238159,
|
|
"epoch": 0.17119888844779674,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004999415095753709,
|
|
"loss": 6.0,
|
|
"mean_token_accuracy": 0.12453790381550789,
|
|
"num_tokens": 3749859.0,
|
|
"step": 1725
|
|
},
|
|
{
|
|
"entropy": 6.116316032409668,
|
|
"epoch": 0.17169511710996427,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004999406989425527,
|
|
"loss": 5.999,
|
|
"mean_token_accuracy": 0.1228027805685997,
|
|
"num_tokens": 3760999.0,
|
|
"step": 1730
|
|
},
|
|
{
|
|
"entropy": 6.207907724380493,
|
|
"epoch": 0.1721913457721318,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999398827316901,
|
|
"loss": 6.025,
|
|
"mean_token_accuracy": 0.12453913390636444,
|
|
"num_tokens": 3771541.0,
|
|
"step": 1735
|
|
},
|
|
{
|
|
"entropy": 6.126678371429444,
|
|
"epoch": 0.17268757443429933,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.000499939060942803,
|
|
"loss": 5.983,
|
|
"mean_token_accuracy": 0.1210265539586544,
|
|
"num_tokens": 3781503.0,
|
|
"step": 1740
|
|
},
|
|
{
|
|
"entropy": 6.190077447891236,
|
|
"epoch": 0.17318380309646686,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999382335759119,
|
|
"loss": 6.0486,
|
|
"mean_token_accuracy": 0.11707601249217987,
|
|
"num_tokens": 3791278.0,
|
|
"step": 1745
|
|
},
|
|
{
|
|
"entropy": 6.263814401626587,
|
|
"epoch": 0.1736800317586344,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004999374006310372,
|
|
"loss": 6.0787,
|
|
"mean_token_accuracy": 0.12131959795951844,
|
|
"num_tokens": 3802995.0,
|
|
"step": 1750
|
|
},
|
|
{
|
|
"entropy": 6.144543790817261,
|
|
"epoch": 0.1741762604208019,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004999365621081999,
|
|
"loss": 6.0164,
|
|
"mean_token_accuracy": 0.12310748770833016,
|
|
"num_tokens": 3813912.0,
|
|
"step": 1755
|
|
},
|
|
{
|
|
"entropy": 6.259069395065308,
|
|
"epoch": 0.17467248908296942,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004999357180074204,
|
|
"loss": 5.9649,
|
|
"mean_token_accuracy": 0.1212263897061348,
|
|
"num_tokens": 3823513.0,
|
|
"step": 1760
|
|
},
|
|
{
|
|
"entropy": 6.128121471405029,
|
|
"epoch": 0.17516871774513695,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004999348683287199,
|
|
"loss": 6.0029,
|
|
"mean_token_accuracy": 0.1258741870522499,
|
|
"num_tokens": 3835602.0,
|
|
"step": 1765
|
|
},
|
|
{
|
|
"entropy": 6.148974323272705,
|
|
"epoch": 0.17566494640730448,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004999340130721192,
|
|
"loss": 6.0626,
|
|
"mean_token_accuracy": 0.11835796162486076,
|
|
"num_tokens": 3847031.0,
|
|
"step": 1770
|
|
},
|
|
{
|
|
"entropy": 6.139218711853028,
|
|
"epoch": 0.17616117506947201,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999331522376396,
|
|
"loss": 5.9138,
|
|
"mean_token_accuracy": 0.1234263926744461,
|
|
"num_tokens": 3857714.0,
|
|
"step": 1775
|
|
},
|
|
{
|
|
"entropy": 6.157423210144043,
|
|
"epoch": 0.17665740373163955,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004999322858253027,
|
|
"loss": 6.0043,
|
|
"mean_token_accuracy": 0.1264146938920021,
|
|
"num_tokens": 3868818.0,
|
|
"step": 1780
|
|
},
|
|
{
|
|
"entropy": 6.190987920761108,
|
|
"epoch": 0.17715363239380708,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999314138351297,
|
|
"loss": 6.0497,
|
|
"mean_token_accuracy": 0.12253930419683456,
|
|
"num_tokens": 3878802.0,
|
|
"step": 1785
|
|
},
|
|
{
|
|
"entropy": 6.232629203796387,
|
|
"epoch": 0.1776498610559746,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004999305362671424,
|
|
"loss": 6.0532,
|
|
"mean_token_accuracy": 0.12156687378883362,
|
|
"num_tokens": 3890045.0,
|
|
"step": 1790
|
|
},
|
|
{
|
|
"entropy": 6.123168706893921,
|
|
"epoch": 0.1781460897181421,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004999296531213624,
|
|
"loss": 5.9338,
|
|
"mean_token_accuracy": 0.12736912518739701,
|
|
"num_tokens": 3901429.0,
|
|
"step": 1795
|
|
},
|
|
{
|
|
"entropy": 6.106752252578735,
|
|
"epoch": 0.17864231838030964,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004999287643978117,
|
|
"loss": 5.9172,
|
|
"mean_token_accuracy": 0.12626976445317267,
|
|
"num_tokens": 3912201.0,
|
|
"step": 1800
|
|
},
|
|
{
|
|
"entropy": 6.071602916717529,
|
|
"epoch": 0.17913854704247717,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004999278700965124,
|
|
"loss": 5.9402,
|
|
"mean_token_accuracy": 0.12588722854852677,
|
|
"num_tokens": 3922338.0,
|
|
"step": 1805
|
|
},
|
|
{
|
|
"entropy": 6.153251314163208,
|
|
"epoch": 0.1796347757046447,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004999269702174866,
|
|
"loss": 5.9837,
|
|
"mean_token_accuracy": 0.12280823290348053,
|
|
"num_tokens": 3934469.0,
|
|
"step": 1810
|
|
},
|
|
{
|
|
"entropy": 6.121962928771973,
|
|
"epoch": 0.18013100436681223,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004999260647607565,
|
|
"loss": 5.9517,
|
|
"mean_token_accuracy": 0.12701089158654214,
|
|
"num_tokens": 3946136.0,
|
|
"step": 1815
|
|
},
|
|
{
|
|
"entropy": 6.157146072387695,
|
|
"epoch": 0.18062723302897976,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999251537263448,
|
|
"loss": 6.0053,
|
|
"mean_token_accuracy": 0.12121656090021134,
|
|
"num_tokens": 3956976.0,
|
|
"step": 1820
|
|
},
|
|
{
|
|
"entropy": 6.189162302017212,
|
|
"epoch": 0.1811234616911473,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004999242371142739,
|
|
"loss": 6.0184,
|
|
"mean_token_accuracy": 0.12531510293483733,
|
|
"num_tokens": 3967929.0,
|
|
"step": 1825
|
|
},
|
|
{
|
|
"entropy": 6.028120803833008,
|
|
"epoch": 0.1816196903533148,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004999233149245665,
|
|
"loss": 5.9661,
|
|
"mean_token_accuracy": 0.13040608540177345,
|
|
"num_tokens": 3979585.0,
|
|
"step": 1830
|
|
},
|
|
{
|
|
"entropy": 6.194211387634278,
|
|
"epoch": 0.18211591901548232,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004999223871572456,
|
|
"loss": 5.9483,
|
|
"mean_token_accuracy": 0.12807398438453674,
|
|
"num_tokens": 3990097.0,
|
|
"step": 1835
|
|
},
|
|
{
|
|
"entropy": 6.195305252075196,
|
|
"epoch": 0.18261214767764986,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999214538123342,
|
|
"loss": 6.0159,
|
|
"mean_token_accuracy": 0.11925126612186432,
|
|
"num_tokens": 3999864.0,
|
|
"step": 1840
|
|
},
|
|
{
|
|
"entropy": 6.140563869476319,
|
|
"epoch": 0.18310837633981739,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999205148898554,
|
|
"loss": 6.0352,
|
|
"mean_token_accuracy": 0.12029140070080757,
|
|
"num_tokens": 4012986.0,
|
|
"step": 1845
|
|
},
|
|
{
|
|
"entropy": 6.133894157409668,
|
|
"epoch": 0.18360460500198492,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004999195703898325,
|
|
"loss": 6.014,
|
|
"mean_token_accuracy": 0.12564092352986336,
|
|
"num_tokens": 4024231.0,
|
|
"step": 1850
|
|
},
|
|
{
|
|
"entropy": 6.100856161117553,
|
|
"epoch": 0.18410083366415245,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004999186203122889,
|
|
"loss": 6.014,
|
|
"mean_token_accuracy": 0.1193986639380455,
|
|
"num_tokens": 4035709.0,
|
|
"step": 1855
|
|
},
|
|
{
|
|
"entropy": 6.097147274017334,
|
|
"epoch": 0.18459706232631998,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004999176646572482,
|
|
"loss": 5.8987,
|
|
"mean_token_accuracy": 0.12348575592041015,
|
|
"num_tokens": 4046504.0,
|
|
"step": 1860
|
|
},
|
|
{
|
|
"entropy": 6.13851490020752,
|
|
"epoch": 0.1850932909884875,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000499916703424734,
|
|
"loss": 5.9443,
|
|
"mean_token_accuracy": 0.11826654374599457,
|
|
"num_tokens": 4056864.0,
|
|
"step": 1865
|
|
},
|
|
{
|
|
"entropy": 6.073440790176392,
|
|
"epoch": 0.185589519650655,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004999157366147702,
|
|
"loss": 5.962,
|
|
"mean_token_accuracy": 0.12339324504137039,
|
|
"num_tokens": 4067682.0,
|
|
"step": 1870
|
|
},
|
|
{
|
|
"entropy": 6.170620965957641,
|
|
"epoch": 0.18608574831282254,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004999147642273809,
|
|
"loss": 5.9651,
|
|
"mean_token_accuracy": 0.12521442025899887,
|
|
"num_tokens": 4078623.0,
|
|
"step": 1875
|
|
},
|
|
{
|
|
"entropy": 6.154106092453003,
|
|
"epoch": 0.18658197697499007,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00049991378626259,
|
|
"loss": 6.0492,
|
|
"mean_token_accuracy": 0.12163211032748222,
|
|
"num_tokens": 4090479.0,
|
|
"step": 1880
|
|
},
|
|
{
|
|
"entropy": 6.190439748764038,
|
|
"epoch": 0.1870782056371576,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004999128027204219,
|
|
"loss": 5.9575,
|
|
"mean_token_accuracy": 0.1205236978828907,
|
|
"num_tokens": 4100379.0,
|
|
"step": 1885
|
|
},
|
|
{
|
|
"entropy": 6.100738382339477,
|
|
"epoch": 0.18757443429932513,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.000499911813600901,
|
|
"loss": 6.102,
|
|
"mean_token_accuracy": 0.11705014109611511,
|
|
"num_tokens": 4111738.0,
|
|
"step": 1890
|
|
},
|
|
{
|
|
"entropy": 6.248137140274048,
|
|
"epoch": 0.18807066296149266,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004999108189040516,
|
|
"loss": 6.0623,
|
|
"mean_token_accuracy": 0.11439691036939621,
|
|
"num_tokens": 4123602.0,
|
|
"step": 1895
|
|
},
|
|
{
|
|
"entropy": 6.1028767108917235,
|
|
"epoch": 0.1885668916236602,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004999098186298986,
|
|
"loss": 6.007,
|
|
"mean_token_accuracy": 0.12231771126389504,
|
|
"num_tokens": 4133558.0,
|
|
"step": 1900
|
|
},
|
|
{
|
|
"entropy": 6.093136978149414,
|
|
"epoch": 0.1890631202858277,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004999088127784667,
|
|
"loss": 5.9219,
|
|
"mean_token_accuracy": 0.12927619069814683,
|
|
"num_tokens": 4143901.0,
|
|
"step": 1905
|
|
},
|
|
{
|
|
"entropy": 6.120997333526612,
|
|
"epoch": 0.18955934894799523,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.000499907801349781,
|
|
"loss": 5.9625,
|
|
"mean_token_accuracy": 0.11881752163171769,
|
|
"num_tokens": 4154180.0,
|
|
"step": 1910
|
|
},
|
|
{
|
|
"entropy": 6.1055737972259525,
|
|
"epoch": 0.19005557761016276,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004999067843438664,
|
|
"loss": 5.9002,
|
|
"mean_token_accuracy": 0.12527662962675096,
|
|
"num_tokens": 4163540.0,
|
|
"step": 1915
|
|
},
|
|
{
|
|
"entropy": 6.11438364982605,
|
|
"epoch": 0.1905518062723303,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999057617607482,
|
|
"loss": 5.9836,
|
|
"mean_token_accuracy": 0.12190114930272103,
|
|
"num_tokens": 4173723.0,
|
|
"step": 1920
|
|
},
|
|
{
|
|
"entropy": 6.151767587661743,
|
|
"epoch": 0.19104803493449782,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004999047336004517,
|
|
"loss": 5.9828,
|
|
"mean_token_accuracy": 0.12671934813261032,
|
|
"num_tokens": 4184771.0,
|
|
"step": 1925
|
|
},
|
|
{
|
|
"entropy": 6.133954286575317,
|
|
"epoch": 0.19154426359666535,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004999036998630024,
|
|
"loss": 5.9683,
|
|
"mean_token_accuracy": 0.12368112206459045,
|
|
"num_tokens": 4195791.0,
|
|
"step": 1930
|
|
},
|
|
{
|
|
"entropy": 6.083200073242187,
|
|
"epoch": 0.19204049225883288,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.000499902660548426,
|
|
"loss": 6.0029,
|
|
"mean_token_accuracy": 0.12152576521039009,
|
|
"num_tokens": 4207393.0,
|
|
"step": 1935
|
|
},
|
|
{
|
|
"entropy": 6.179332113265991,
|
|
"epoch": 0.1925367209210004,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004999016156567482,
|
|
"loss": 5.9361,
|
|
"mean_token_accuracy": 0.1270752251148224,
|
|
"num_tokens": 4218278.0,
|
|
"step": 1940
|
|
},
|
|
{
|
|
"entropy": 6.1392213821411135,
|
|
"epoch": 0.1930329495831679,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000499900565187995,
|
|
"loss": 6.0965,
|
|
"mean_token_accuracy": 0.11639922857284546,
|
|
"num_tokens": 4229448.0,
|
|
"step": 1945
|
|
},
|
|
{
|
|
"entropy": 6.2056193351745605,
|
|
"epoch": 0.19352917824533544,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004998995091421924,
|
|
"loss": 6.0121,
|
|
"mean_token_accuracy": 0.12356942817568779,
|
|
"num_tokens": 4240750.0,
|
|
"step": 1950
|
|
},
|
|
{
|
|
"entropy": 6.125873804092407,
|
|
"epoch": 0.19402540690750297,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004998984475193665,
|
|
"loss": 5.9919,
|
|
"mean_token_accuracy": 0.1261401057243347,
|
|
"num_tokens": 4252086.0,
|
|
"step": 1955
|
|
},
|
|
{
|
|
"entropy": 6.123996639251709,
|
|
"epoch": 0.1945216355696705,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004998973803195439,
|
|
"loss": 5.9428,
|
|
"mean_token_accuracy": 0.1254188634455204,
|
|
"num_tokens": 4262756.0,
|
|
"step": 1960
|
|
},
|
|
{
|
|
"entropy": 6.069361400604248,
|
|
"epoch": 0.19501786423183803,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004998963075427508,
|
|
"loss": 5.999,
|
|
"mean_token_accuracy": 0.12879851460456848,
|
|
"num_tokens": 4272965.0,
|
|
"step": 1965
|
|
},
|
|
{
|
|
"entropy": 6.210020208358765,
|
|
"epoch": 0.19551409289400556,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004998952291890138,
|
|
"loss": 6.052,
|
|
"mean_token_accuracy": 0.12350022047758102,
|
|
"num_tokens": 4284465.0,
|
|
"step": 1970
|
|
},
|
|
{
|
|
"entropy": 6.133313083648682,
|
|
"epoch": 0.1960103215561731,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004998941452583599,
|
|
"loss": 5.9768,
|
|
"mean_token_accuracy": 0.12168458700180054,
|
|
"num_tokens": 4295266.0,
|
|
"step": 1975
|
|
},
|
|
{
|
|
"entropy": 6.1962378978729244,
|
|
"epoch": 0.1965065502183406,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004998930557508156,
|
|
"loss": 6.017,
|
|
"mean_token_accuracy": 0.11654685959219932,
|
|
"num_tokens": 4306477.0,
|
|
"step": 1980
|
|
},
|
|
{
|
|
"entropy": 6.12655668258667,
|
|
"epoch": 0.19700277888050813,
|
|
"grad_norm": 0.7578125,
|
|
"learning_rate": 0.0004998919606664082,
|
|
"loss": 6.0534,
|
|
"mean_token_accuracy": 0.11759311258792877,
|
|
"num_tokens": 4319150.0,
|
|
"step": 1985
|
|
},
|
|
{
|
|
"entropy": 6.129172420501709,
|
|
"epoch": 0.19749900754267566,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004998908600051648,
|
|
"loss": 6.0234,
|
|
"mean_token_accuracy": 0.12395478188991546,
|
|
"num_tokens": 4330679.0,
|
|
"step": 1990
|
|
},
|
|
{
|
|
"entropy": 6.184890651702881,
|
|
"epoch": 0.1979952362048432,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004998897537671126,
|
|
"loss": 5.9498,
|
|
"mean_token_accuracy": 0.1217629611492157,
|
|
"num_tokens": 4340597.0,
|
|
"step": 1995
|
|
},
|
|
{
|
|
"entropy": 6.026102209091187,
|
|
"epoch": 0.19849146486701072,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004998886419522792,
|
|
"loss": 5.951,
|
|
"mean_token_accuracy": 0.12472691535949706,
|
|
"num_tokens": 4351814.0,
|
|
"step": 2000
|
|
},
|
|
{
|
|
"entropy": 6.186213159561158,
|
|
"epoch": 0.19898769352917825,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.0004998875245606919,
|
|
"loss": 6.0405,
|
|
"mean_token_accuracy": 0.1263307310640812,
|
|
"num_tokens": 4363930.0,
|
|
"step": 2005
|
|
},
|
|
{
|
|
"entropy": 6.186520051956177,
|
|
"epoch": 0.19948392219134578,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004998864015923788,
|
|
"loss": 5.9422,
|
|
"mean_token_accuracy": 0.12555222287774087,
|
|
"num_tokens": 4376127.0,
|
|
"step": 2010
|
|
},
|
|
{
|
|
"entropy": 6.03753776550293,
|
|
"epoch": 0.1999801508535133,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004998852730473674,
|
|
"loss": 5.9369,
|
|
"mean_token_accuracy": 0.12351071462035179,
|
|
"num_tokens": 4386095.0,
|
|
"step": 2015
|
|
},
|
|
{
|
|
"entropy": 6.076215410232544,
|
|
"epoch": 0.2004763795156808,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004998841389256859,
|
|
"loss": 5.8703,
|
|
"mean_token_accuracy": 0.12462282553315163,
|
|
"num_tokens": 4397441.0,
|
|
"step": 2020
|
|
},
|
|
{
|
|
"entropy": 6.071394205093384,
|
|
"epoch": 0.20097260817784834,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004998829992273622,
|
|
"loss": 5.9734,
|
|
"mean_token_accuracy": 0.12160781174898147,
|
|
"num_tokens": 4408295.0,
|
|
"step": 2025
|
|
},
|
|
{
|
|
"entropy": 6.043331718444824,
|
|
"epoch": 0.20146883684001587,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004998818539524248,
|
|
"loss": 5.9636,
|
|
"mean_token_accuracy": 0.12636535987257957,
|
|
"num_tokens": 4419307.0,
|
|
"step": 2030
|
|
},
|
|
{
|
|
"entropy": 6.137074136734009,
|
|
"epoch": 0.2019650655021834,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.000499880703100902,
|
|
"loss": 5.9539,
|
|
"mean_token_accuracy": 0.12338273897767067,
|
|
"num_tokens": 4431908.0,
|
|
"step": 2035
|
|
},
|
|
{
|
|
"entropy": 6.1705132007598875,
|
|
"epoch": 0.20246129416435094,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004998795466728223,
|
|
"loss": 5.9858,
|
|
"mean_token_accuracy": 0.12354729771614074,
|
|
"num_tokens": 4443417.0,
|
|
"step": 2040
|
|
},
|
|
{
|
|
"entropy": 6.078726291656494,
|
|
"epoch": 0.20295752282651847,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004998783846682144,
|
|
"loss": 6.0307,
|
|
"mean_token_accuracy": 0.1215967983007431,
|
|
"num_tokens": 4453224.0,
|
|
"step": 2045
|
|
},
|
|
{
|
|
"entropy": 6.076732397079468,
|
|
"epoch": 0.203453751488686,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004998772170871072,
|
|
"loss": 5.8468,
|
|
"mean_token_accuracy": 0.12905316129326821,
|
|
"num_tokens": 4463231.0,
|
|
"step": 2050
|
|
},
|
|
{
|
|
"entropy": 6.058457279205323,
|
|
"epoch": 0.20394998015085353,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004998760439295295,
|
|
"loss": 5.9344,
|
|
"mean_token_accuracy": 0.12181595787405967,
|
|
"num_tokens": 4474397.0,
|
|
"step": 2055
|
|
},
|
|
{
|
|
"entropy": 6.075131225585937,
|
|
"epoch": 0.20444620881302103,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004998748651955105,
|
|
"loss": 5.9376,
|
|
"mean_token_accuracy": 0.12992871999740602,
|
|
"num_tokens": 4485623.0,
|
|
"step": 2060
|
|
},
|
|
{
|
|
"entropy": 6.1033796787261965,
|
|
"epoch": 0.20494243747518856,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004998736808850795,
|
|
"loss": 5.9249,
|
|
"mean_token_accuracy": 0.12822652086615563,
|
|
"num_tokens": 4495247.0,
|
|
"step": 2065
|
|
},
|
|
{
|
|
"entropy": 6.0438454151153564,
|
|
"epoch": 0.2054386661373561,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004998724909982656,
|
|
"loss": 5.9906,
|
|
"mean_token_accuracy": 0.12130568027496338,
|
|
"num_tokens": 4506490.0,
|
|
"step": 2070
|
|
},
|
|
{
|
|
"entropy": 6.184813690185547,
|
|
"epoch": 0.20593489479952362,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004998712955350986,
|
|
"loss": 6.0001,
|
|
"mean_token_accuracy": 0.12409835308790207,
|
|
"num_tokens": 4517511.0,
|
|
"step": 2075
|
|
},
|
|
{
|
|
"entropy": 6.033582639694214,
|
|
"epoch": 0.20643112346169115,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004998700944956081,
|
|
"loss": 5.9458,
|
|
"mean_token_accuracy": 0.13070451766252517,
|
|
"num_tokens": 4528655.0,
|
|
"step": 2080
|
|
},
|
|
{
|
|
"entropy": 6.07148003578186,
|
|
"epoch": 0.20692735212385868,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004998688878798237,
|
|
"loss": 5.9863,
|
|
"mean_token_accuracy": 0.12557874843478203,
|
|
"num_tokens": 4539369.0,
|
|
"step": 2085
|
|
},
|
|
{
|
|
"entropy": 6.109499120712281,
|
|
"epoch": 0.2074235807860262,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004998676756877753,
|
|
"loss": 5.8801,
|
|
"mean_token_accuracy": 0.12313915863633156,
|
|
"num_tokens": 4548747.0,
|
|
"step": 2090
|
|
},
|
|
{
|
|
"entropy": 5.956798696517945,
|
|
"epoch": 0.20791980944819372,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004998664579194934,
|
|
"loss": 5.8747,
|
|
"mean_token_accuracy": 0.12651906609535218,
|
|
"num_tokens": 4561283.0,
|
|
"step": 2095
|
|
},
|
|
{
|
|
"entropy": 6.101844596862793,
|
|
"epoch": 0.20841603811036125,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004998652345750077,
|
|
"loss": 6.0087,
|
|
"mean_token_accuracy": 0.12195251435041428,
|
|
"num_tokens": 4571929.0,
|
|
"step": 2100
|
|
},
|
|
{
|
|
"entropy": 6.0962621688842775,
|
|
"epoch": 0.20891226677252878,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004998640056543487,
|
|
"loss": 5.9936,
|
|
"mean_token_accuracy": 0.12055393010377884,
|
|
"num_tokens": 4583105.0,
|
|
"step": 2105
|
|
},
|
|
{
|
|
"entropy": 6.128101778030396,
|
|
"epoch": 0.2094084954346963,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004998627711575469,
|
|
"loss": 6.0601,
|
|
"mean_token_accuracy": 0.11935122683644295,
|
|
"num_tokens": 4595360.0,
|
|
"step": 2110
|
|
},
|
|
{
|
|
"entropy": 6.121275186538696,
|
|
"epoch": 0.20990472409686384,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.000499861531084633,
|
|
"loss": 6.0214,
|
|
"mean_token_accuracy": 0.12107700780034066,
|
|
"num_tokens": 4607621.0,
|
|
"step": 2115
|
|
},
|
|
{
|
|
"entropy": 6.0780713081359865,
|
|
"epoch": 0.21040095275903137,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004998602854356376,
|
|
"loss": 5.8639,
|
|
"mean_token_accuracy": 0.1276746354997158,
|
|
"num_tokens": 4618286.0,
|
|
"step": 2120
|
|
},
|
|
{
|
|
"entropy": 6.060158061981201,
|
|
"epoch": 0.2108971814211989,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004998590342105917,
|
|
"loss": 5.9454,
|
|
"mean_token_accuracy": 0.1269027128815651,
|
|
"num_tokens": 4628345.0,
|
|
"step": 2125
|
|
},
|
|
{
|
|
"entropy": 6.151575517654419,
|
|
"epoch": 0.21139341008336643,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004998577774095262,
|
|
"loss": 5.9933,
|
|
"mean_token_accuracy": 0.12428949922323226,
|
|
"num_tokens": 4639074.0,
|
|
"step": 2130
|
|
},
|
|
{
|
|
"entropy": 6.060426807403564,
|
|
"epoch": 0.21188963874553393,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004998565150324724,
|
|
"loss": 6.0473,
|
|
"mean_token_accuracy": 0.12472090199589729,
|
|
"num_tokens": 4652698.0,
|
|
"step": 2135
|
|
},
|
|
{
|
|
"entropy": 6.079493188858033,
|
|
"epoch": 0.21238586740770146,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004998552470794616,
|
|
"loss": 5.8508,
|
|
"mean_token_accuracy": 0.13163320422172547,
|
|
"num_tokens": 4663924.0,
|
|
"step": 2140
|
|
},
|
|
{
|
|
"entropy": 6.1048369884490965,
|
|
"epoch": 0.212882096069869,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004998539735505251,
|
|
"loss": 5.965,
|
|
"mean_token_accuracy": 0.1236407183110714,
|
|
"num_tokens": 4673821.0,
|
|
"step": 2145
|
|
},
|
|
{
|
|
"entropy": 6.084499216079712,
|
|
"epoch": 0.21337832473203652,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004998526944456946,
|
|
"loss": 5.9017,
|
|
"mean_token_accuracy": 0.12818676382303237,
|
|
"num_tokens": 4686646.0,
|
|
"step": 2150
|
|
},
|
|
{
|
|
"entropy": 6.096099758148194,
|
|
"epoch": 0.21387455339420405,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004998514097650018,
|
|
"loss": 5.9023,
|
|
"mean_token_accuracy": 0.1319211333990097,
|
|
"num_tokens": 4698118.0,
|
|
"step": 2155
|
|
},
|
|
{
|
|
"entropy": 6.026635837554932,
|
|
"epoch": 0.21437078205637158,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004998501195084786,
|
|
"loss": 5.9088,
|
|
"mean_token_accuracy": 0.12052568271756173,
|
|
"num_tokens": 4708869.0,
|
|
"step": 2160
|
|
},
|
|
{
|
|
"entropy": 6.034014320373535,
|
|
"epoch": 0.21486701071853911,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004998488236761569,
|
|
"loss": 5.9338,
|
|
"mean_token_accuracy": 0.1213805504143238,
|
|
"num_tokens": 4720172.0,
|
|
"step": 2165
|
|
},
|
|
{
|
|
"entropy": 6.08177638053894,
|
|
"epoch": 0.21536323938070662,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004998475222680688,
|
|
"loss": 5.9905,
|
|
"mean_token_accuracy": 0.12283061891794204,
|
|
"num_tokens": 4731886.0,
|
|
"step": 2170
|
|
},
|
|
{
|
|
"entropy": 6.061129188537597,
|
|
"epoch": 0.21585946804287415,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004998462152842468,
|
|
"loss": 5.8735,
|
|
"mean_token_accuracy": 0.1260004922747612,
|
|
"num_tokens": 4742381.0,
|
|
"step": 2175
|
|
},
|
|
{
|
|
"entropy": 6.03049898147583,
|
|
"epoch": 0.21635569670504168,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.000499844902724723,
|
|
"loss": 5.8151,
|
|
"mean_token_accuracy": 0.13139328137040138,
|
|
"num_tokens": 4752851.0,
|
|
"step": 2180
|
|
},
|
|
{
|
|
"entropy": 6.024123573303223,
|
|
"epoch": 0.2168519253672092,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004998435845895302,
|
|
"loss": 5.9025,
|
|
"mean_token_accuracy": 0.12522170394659043,
|
|
"num_tokens": 4764271.0,
|
|
"step": 2185
|
|
},
|
|
{
|
|
"entropy": 6.008631229400635,
|
|
"epoch": 0.21734815402937674,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000499842260878701,
|
|
"loss": 5.9643,
|
|
"mean_token_accuracy": 0.12548010498285295,
|
|
"num_tokens": 4776216.0,
|
|
"step": 2190
|
|
},
|
|
{
|
|
"entropy": 6.02488341331482,
|
|
"epoch": 0.21784438269154427,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004998409315922683,
|
|
"loss": 5.9141,
|
|
"mean_token_accuracy": 0.1233865849673748,
|
|
"num_tokens": 4786666.0,
|
|
"step": 2195
|
|
},
|
|
{
|
|
"entropy": 6.102518749237061,
|
|
"epoch": 0.2183406113537118,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004998395967302649,
|
|
"loss": 5.9867,
|
|
"mean_token_accuracy": 0.11829503029584884,
|
|
"num_tokens": 4798062.0,
|
|
"step": 2200
|
|
},
|
|
{
|
|
"entropy": 6.052379560470581,
|
|
"epoch": 0.21883684001587933,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000499838256292724,
|
|
"loss": 5.9647,
|
|
"mean_token_accuracy": 0.12422867640852928,
|
|
"num_tokens": 4808837.0,
|
|
"step": 2205
|
|
},
|
|
{
|
|
"entropy": 6.059252071380615,
|
|
"epoch": 0.21933306867804683,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004998369102796787,
|
|
"loss": 5.8906,
|
|
"mean_token_accuracy": 0.13139605671167373,
|
|
"num_tokens": 4819894.0,
|
|
"step": 2210
|
|
},
|
|
{
|
|
"entropy": 5.953090047836303,
|
|
"epoch": 0.21982929734021436,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004998355586911627,
|
|
"loss": 5.8606,
|
|
"mean_token_accuracy": 0.12828084975481033,
|
|
"num_tokens": 4830976.0,
|
|
"step": 2215
|
|
},
|
|
{
|
|
"entropy": 6.128897476196289,
|
|
"epoch": 0.2203255260023819,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004998342015272093,
|
|
"loss": 6.0499,
|
|
"mean_token_accuracy": 0.12443847954273224,
|
|
"num_tokens": 4844292.0,
|
|
"step": 2220
|
|
},
|
|
{
|
|
"entropy": 6.087233448028565,
|
|
"epoch": 0.22082175466454942,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.0004998328387878521,
|
|
"loss": 5.8356,
|
|
"mean_token_accuracy": 0.13550032079219818,
|
|
"num_tokens": 4855284.0,
|
|
"step": 2225
|
|
},
|
|
{
|
|
"entropy": 6.04253740310669,
|
|
"epoch": 0.22131798332671695,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004998314704731249,
|
|
"loss": 5.9686,
|
|
"mean_token_accuracy": 0.12750899493694307,
|
|
"num_tokens": 4867801.0,
|
|
"step": 2230
|
|
},
|
|
{
|
|
"entropy": 6.014859342575074,
|
|
"epoch": 0.22181421198888449,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004998300965830618,
|
|
"loss": 5.7639,
|
|
"mean_token_accuracy": 0.12936904281377792,
|
|
"num_tokens": 4877392.0,
|
|
"step": 2235
|
|
},
|
|
{
|
|
"entropy": 5.9705253601074215,
|
|
"epoch": 0.22231044065105202,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004998287171176968,
|
|
"loss": 5.8695,
|
|
"mean_token_accuracy": 0.12599683701992034,
|
|
"num_tokens": 4888772.0,
|
|
"step": 2240
|
|
},
|
|
{
|
|
"entropy": 6.065585517883301,
|
|
"epoch": 0.22280666931321952,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004998273320770641,
|
|
"loss": 5.9199,
|
|
"mean_token_accuracy": 0.12483752593398094,
|
|
"num_tokens": 4899739.0,
|
|
"step": 2245
|
|
},
|
|
{
|
|
"entropy": 6.090867757797241,
|
|
"epoch": 0.22330289797538705,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000499825941461198,
|
|
"loss": 5.8943,
|
|
"mean_token_accuracy": 0.1287125341594219,
|
|
"num_tokens": 4910455.0,
|
|
"step": 2250
|
|
},
|
|
{
|
|
"entropy": 6.070242071151734,
|
|
"epoch": 0.22379912663755458,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004998245452701329,
|
|
"loss": 5.8417,
|
|
"mean_token_accuracy": 0.12609231770038604,
|
|
"num_tokens": 4921156.0,
|
|
"step": 2255
|
|
},
|
|
{
|
|
"entropy": 6.000742483139038,
|
|
"epoch": 0.2242953552997221,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004998231435039036,
|
|
"loss": 5.8579,
|
|
"mean_token_accuracy": 0.1287795290350914,
|
|
"num_tokens": 4931771.0,
|
|
"step": 2260
|
|
},
|
|
{
|
|
"entropy": 5.991134738922119,
|
|
"epoch": 0.22479158396188964,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004998217361625449,
|
|
"loss": 5.8663,
|
|
"mean_token_accuracy": 0.12458878979086876,
|
|
"num_tokens": 4942790.0,
|
|
"step": 2265
|
|
},
|
|
{
|
|
"entropy": 5.995892524719238,
|
|
"epoch": 0.22528781262405717,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004998203232460915,
|
|
"loss": 5.874,
|
|
"mean_token_accuracy": 0.12552486434578897,
|
|
"num_tokens": 4952752.0,
|
|
"step": 2270
|
|
},
|
|
{
|
|
"entropy": 6.009762763977051,
|
|
"epoch": 0.2257840412862247,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004998189047545785,
|
|
"loss": 5.9124,
|
|
"mean_token_accuracy": 0.12559892162680625,
|
|
"num_tokens": 4963659.0,
|
|
"step": 2275
|
|
},
|
|
{
|
|
"entropy": 6.0851356983184814,
|
|
"epoch": 0.22628026994839223,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004998174806880411,
|
|
"loss": 5.8793,
|
|
"mean_token_accuracy": 0.12859429866075517,
|
|
"num_tokens": 4976121.0,
|
|
"step": 2280
|
|
},
|
|
{
|
|
"entropy": 6.003554630279541,
|
|
"epoch": 0.22677649861055973,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004998160510465146,
|
|
"loss": 5.9175,
|
|
"mean_token_accuracy": 0.12735827937722205,
|
|
"num_tokens": 4986515.0,
|
|
"step": 2285
|
|
},
|
|
{
|
|
"entropy": 5.9042627811431885,
|
|
"epoch": 0.22727272727272727,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004998146158300345,
|
|
"loss": 5.7962,
|
|
"mean_token_accuracy": 0.13313199654221536,
|
|
"num_tokens": 4998231.0,
|
|
"step": 2290
|
|
},
|
|
{
|
|
"entropy": 6.041743040084839,
|
|
"epoch": 0.2277689559348948,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004998131750386364,
|
|
"loss": 5.8249,
|
|
"mean_token_accuracy": 0.1294488824903965,
|
|
"num_tokens": 5010309.0,
|
|
"step": 2295
|
|
},
|
|
{
|
|
"entropy": 5.973780727386474,
|
|
"epoch": 0.22826518459706233,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004998117286723559,
|
|
"loss": 5.9081,
|
|
"mean_token_accuracy": 0.1309161476790905,
|
|
"num_tokens": 5020864.0,
|
|
"step": 2300
|
|
},
|
|
{
|
|
"entropy": 6.018421363830567,
|
|
"epoch": 0.22876141325922986,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000499810276731229,
|
|
"loss": 5.9005,
|
|
"mean_token_accuracy": 0.13277044668793678,
|
|
"num_tokens": 5032224.0,
|
|
"step": 2305
|
|
},
|
|
{
|
|
"entropy": 6.084892845153808,
|
|
"epoch": 0.2292576419213974,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004998088192152918,
|
|
"loss": 5.8614,
|
|
"mean_token_accuracy": 0.1324816547334194,
|
|
"num_tokens": 5044318.0,
|
|
"step": 2310
|
|
},
|
|
{
|
|
"entropy": 5.994323968887329,
|
|
"epoch": 0.22975387058356492,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004998073561245801,
|
|
"loss": 5.9598,
|
|
"mean_token_accuracy": 0.12364556863904,
|
|
"num_tokens": 5055270.0,
|
|
"step": 2315
|
|
},
|
|
{
|
|
"entropy": 6.087515926361084,
|
|
"epoch": 0.23025009924573242,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004998058874591305,
|
|
"loss": 5.8998,
|
|
"mean_token_accuracy": 0.13236292973160743,
|
|
"num_tokens": 5064771.0,
|
|
"step": 2320
|
|
},
|
|
{
|
|
"entropy": 6.012254524230957,
|
|
"epoch": 0.23074632790789995,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004998044132189793,
|
|
"loss": 5.9151,
|
|
"mean_token_accuracy": 0.12145323902368546,
|
|
"num_tokens": 5075509.0,
|
|
"step": 2325
|
|
},
|
|
{
|
|
"entropy": 5.989501953125,
|
|
"epoch": 0.23124255657006748,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.000499802933404163,
|
|
"loss": 5.8608,
|
|
"mean_token_accuracy": 0.12346896156668663,
|
|
"num_tokens": 5086270.0,
|
|
"step": 2330
|
|
},
|
|
{
|
|
"entropy": 5.993625497817993,
|
|
"epoch": 0.231738785232235,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004998014480147183,
|
|
"loss": 5.8026,
|
|
"mean_token_accuracy": 0.134233608096838,
|
|
"num_tokens": 5096695.0,
|
|
"step": 2335
|
|
},
|
|
{
|
|
"entropy": 6.032075071334839,
|
|
"epoch": 0.23223501389440254,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004997999570506823,
|
|
"loss": 5.8928,
|
|
"mean_token_accuracy": 0.1275573804974556,
|
|
"num_tokens": 5107775.0,
|
|
"step": 2340
|
|
},
|
|
{
|
|
"entropy": 5.994977617263794,
|
|
"epoch": 0.23273124255657007,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004997984605120917,
|
|
"loss": 5.8537,
|
|
"mean_token_accuracy": 0.1317949816584587,
|
|
"num_tokens": 5118215.0,
|
|
"step": 2345
|
|
},
|
|
{
|
|
"entropy": 6.086479043960571,
|
|
"epoch": 0.2332274712187376,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004997969583989835,
|
|
"loss": 5.8716,
|
|
"mean_token_accuracy": 0.1287857286632061,
|
|
"num_tokens": 5129509.0,
|
|
"step": 2350
|
|
},
|
|
{
|
|
"entropy": 5.943372297286987,
|
|
"epoch": 0.23372369988090513,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004997954507113952,
|
|
"loss": 5.8281,
|
|
"mean_token_accuracy": 0.12884464114904404,
|
|
"num_tokens": 5140689.0,
|
|
"step": 2355
|
|
},
|
|
{
|
|
"entropy": 5.984193468093872,
|
|
"epoch": 0.23421992854307264,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004997939374493642,
|
|
"loss": 5.818,
|
|
"mean_token_accuracy": 0.1295442223548889,
|
|
"num_tokens": 5151060.0,
|
|
"step": 2360
|
|
},
|
|
{
|
|
"entropy": 5.96844630241394,
|
|
"epoch": 0.23471615720524017,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.000499792418612928,
|
|
"loss": 5.7961,
|
|
"mean_token_accuracy": 0.12893855795264245,
|
|
"num_tokens": 5161481.0,
|
|
"step": 2365
|
|
},
|
|
{
|
|
"entropy": 5.9971160888671875,
|
|
"epoch": 0.2352123858674077,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004997908942021241,
|
|
"loss": 5.9171,
|
|
"mean_token_accuracy": 0.12333358600735664,
|
|
"num_tokens": 5171961.0,
|
|
"step": 2370
|
|
},
|
|
{
|
|
"entropy": 6.144476413726807,
|
|
"epoch": 0.23570861452957523,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004997893642169904,
|
|
"loss": 5.9614,
|
|
"mean_token_accuracy": 0.12242959663271905,
|
|
"num_tokens": 5184158.0,
|
|
"step": 2375
|
|
},
|
|
{
|
|
"entropy": 5.974719429016114,
|
|
"epoch": 0.23620484319174276,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004997878286575648,
|
|
"loss": 5.9808,
|
|
"mean_token_accuracy": 0.12806885838508605,
|
|
"num_tokens": 5195942.0,
|
|
"step": 2380
|
|
},
|
|
{
|
|
"entropy": 6.029640007019043,
|
|
"epoch": 0.2367010718539103,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004997862875238855,
|
|
"loss": 5.8598,
|
|
"mean_token_accuracy": 0.12884648367762566,
|
|
"num_tokens": 5208063.0,
|
|
"step": 2385
|
|
},
|
|
{
|
|
"entropy": 6.0588702201843265,
|
|
"epoch": 0.23719730051607782,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004997847408159907,
|
|
"loss": 5.9084,
|
|
"mean_token_accuracy": 0.13252404928207398,
|
|
"num_tokens": 5219424.0,
|
|
"step": 2390
|
|
},
|
|
{
|
|
"entropy": 6.0522301197052,
|
|
"epoch": 0.23769352917824532,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004997831885339186,
|
|
"loss": 5.9037,
|
|
"mean_token_accuracy": 0.12284734547138214,
|
|
"num_tokens": 5230351.0,
|
|
"step": 2395
|
|
},
|
|
{
|
|
"entropy": 5.945491743087769,
|
|
"epoch": 0.23818975784041285,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004997816306777077,
|
|
"loss": 5.79,
|
|
"mean_token_accuracy": 0.12974425926804542,
|
|
"num_tokens": 5242906.0,
|
|
"step": 2400
|
|
},
|
|
{
|
|
"entropy": 5.940090894699097,
|
|
"epoch": 0.23868598650258038,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004997800672473969,
|
|
"loss": 5.8165,
|
|
"mean_token_accuracy": 0.13514286726713182,
|
|
"num_tokens": 5253689.0,
|
|
"step": 2405
|
|
},
|
|
{
|
|
"entropy": 6.0798712253570555,
|
|
"epoch": 0.2391822151647479,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004997784982430247,
|
|
"loss": 5.9217,
|
|
"mean_token_accuracy": 0.13028180822730065,
|
|
"num_tokens": 5265896.0,
|
|
"step": 2410
|
|
},
|
|
{
|
|
"entropy": 5.999238395690918,
|
|
"epoch": 0.23967844382691544,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004997769236646301,
|
|
"loss": 5.832,
|
|
"mean_token_accuracy": 0.12702908590435982,
|
|
"num_tokens": 5276800.0,
|
|
"step": 2415
|
|
},
|
|
{
|
|
"entropy": 5.974053955078125,
|
|
"epoch": 0.24017467248908297,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004997753435122522,
|
|
"loss": 5.8315,
|
|
"mean_token_accuracy": 0.13149850741028785,
|
|
"num_tokens": 5289113.0,
|
|
"step": 2420
|
|
},
|
|
{
|
|
"entropy": 5.999874496459961,
|
|
"epoch": 0.2406709011512505,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00049977375778593,
|
|
"loss": 5.7911,
|
|
"mean_token_accuracy": 0.12800634130835534,
|
|
"num_tokens": 5298825.0,
|
|
"step": 2425
|
|
},
|
|
{
|
|
"entropy": 5.885820531845093,
|
|
"epoch": 0.24116712981341804,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004997721664857032,
|
|
"loss": 5.8154,
|
|
"mean_token_accuracy": 0.1327855445444584,
|
|
"num_tokens": 5310376.0,
|
|
"step": 2430
|
|
},
|
|
{
|
|
"entropy": 5.9202381610870365,
|
|
"epoch": 0.24166335847558554,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004997705696116108,
|
|
"loss": 5.8319,
|
|
"mean_token_accuracy": 0.12816173657774926,
|
|
"num_tokens": 5320483.0,
|
|
"step": 2435
|
|
},
|
|
{
|
|
"entropy": 6.028395891189575,
|
|
"epoch": 0.24215958713775307,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004997689671636926,
|
|
"loss": 5.7414,
|
|
"mean_token_accuracy": 0.13838978856801987,
|
|
"num_tokens": 5330995.0,
|
|
"step": 2440
|
|
},
|
|
{
|
|
"entropy": 5.933304786682129,
|
|
"epoch": 0.2426558157999206,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004997673591419884,
|
|
"loss": 5.8568,
|
|
"mean_token_accuracy": 0.1328567832708359,
|
|
"num_tokens": 5341208.0,
|
|
"step": 2445
|
|
},
|
|
{
|
|
"entropy": 5.9697181224823,
|
|
"epoch": 0.24315204446208813,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004997657455465381,
|
|
"loss": 5.9195,
|
|
"mean_token_accuracy": 0.13485939353704451,
|
|
"num_tokens": 5351769.0,
|
|
"step": 2450
|
|
},
|
|
{
|
|
"entropy": 5.988297748565674,
|
|
"epoch": 0.24364827312425566,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004997641263773815,
|
|
"loss": 5.7017,
|
|
"mean_token_accuracy": 0.13556905314326287,
|
|
"num_tokens": 5361033.0,
|
|
"step": 2455
|
|
},
|
|
{
|
|
"entropy": 5.82569694519043,
|
|
"epoch": 0.2441445017864232,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.000499762501634559,
|
|
"loss": 5.7772,
|
|
"mean_token_accuracy": 0.1308267556130886,
|
|
"num_tokens": 5372381.0,
|
|
"step": 2460
|
|
},
|
|
{
|
|
"entropy": 6.007634067535401,
|
|
"epoch": 0.24464073044859072,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004997608713181108,
|
|
"loss": 5.838,
|
|
"mean_token_accuracy": 0.13373954892158507,
|
|
"num_tokens": 5383101.0,
|
|
"step": 2465
|
|
},
|
|
{
|
|
"entropy": 5.999208927154541,
|
|
"epoch": 0.24513695911075822,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004997592354280772,
|
|
"loss": 5.866,
|
|
"mean_token_accuracy": 0.12492905780673028,
|
|
"num_tokens": 5393661.0,
|
|
"step": 2470
|
|
},
|
|
{
|
|
"entropy": 6.018182182312012,
|
|
"epoch": 0.24563318777292575,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.000499757593964499,
|
|
"loss": 5.8775,
|
|
"mean_token_accuracy": 0.1348043665289879,
|
|
"num_tokens": 5405377.0,
|
|
"step": 2475
|
|
},
|
|
{
|
|
"entropy": 5.926452541351319,
|
|
"epoch": 0.24612941643509328,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004997559469274166,
|
|
"loss": 5.7918,
|
|
"mean_token_accuracy": 0.12829321920871734,
|
|
"num_tokens": 5417172.0,
|
|
"step": 2480
|
|
},
|
|
{
|
|
"entropy": 5.959072780609131,
|
|
"epoch": 0.24662564509726081,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004997542943168712,
|
|
"loss": 5.9262,
|
|
"mean_token_accuracy": 0.12317180931568146,
|
|
"num_tokens": 5428053.0,
|
|
"step": 2485
|
|
},
|
|
{
|
|
"entropy": 6.076896238327026,
|
|
"epoch": 0.24712187375942835,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004997526361329035,
|
|
"loss": 5.8564,
|
|
"mean_token_accuracy": 0.12735359892249107,
|
|
"num_tokens": 5438282.0,
|
|
"step": 2490
|
|
},
|
|
{
|
|
"entropy": 5.928952550888061,
|
|
"epoch": 0.24761810242159588,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004997509723755547,
|
|
"loss": 5.8189,
|
|
"mean_token_accuracy": 0.13142750561237335,
|
|
"num_tokens": 5448940.0,
|
|
"step": 2495
|
|
},
|
|
{
|
|
"entropy": 5.812957143783569,
|
|
"epoch": 0.2481143310837634,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004997493030448662,
|
|
"loss": 5.6781,
|
|
"mean_token_accuracy": 0.13580155298113822,
|
|
"num_tokens": 5458471.0,
|
|
"step": 2500
|
|
},
|
|
{
|
|
"entropy": 5.949634838104248,
|
|
"epoch": 0.24861055974593094,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004997476281408793,
|
|
"loss": 5.7861,
|
|
"mean_token_accuracy": 0.13658471554517745,
|
|
"num_tokens": 5467979.0,
|
|
"step": 2505
|
|
},
|
|
{
|
|
"entropy": 6.00718846321106,
|
|
"epoch": 0.24910678840809844,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004997459476636354,
|
|
"loss": 5.9151,
|
|
"mean_token_accuracy": 0.11804315224289894,
|
|
"num_tokens": 5479852.0,
|
|
"step": 2510
|
|
},
|
|
{
|
|
"entropy": 5.938953304290772,
|
|
"epoch": 0.24960301707026597,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004997442616131763,
|
|
"loss": 5.7642,
|
|
"mean_token_accuracy": 0.12964859008789062,
|
|
"num_tokens": 5491827.0,
|
|
"step": 2515
|
|
},
|
|
{
|
|
"entropy": 5.895040082931518,
|
|
"epoch": 0.25009924573243353,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004997425699895438,
|
|
"loss": 5.7411,
|
|
"mean_token_accuracy": 0.13389707282185553,
|
|
"num_tokens": 5502206.0,
|
|
"step": 2520
|
|
},
|
|
{
|
|
"entropy": 5.923152685165405,
|
|
"epoch": 0.25059547439460106,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004997408727927798,
|
|
"loss": 5.779,
|
|
"mean_token_accuracy": 0.12976060807704926,
|
|
"num_tokens": 5514352.0,
|
|
"step": 2525
|
|
},
|
|
{
|
|
"entropy": 5.96109037399292,
|
|
"epoch": 0.25109170305676853,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004997391700229264,
|
|
"loss": 5.7926,
|
|
"mean_token_accuracy": 0.1397273398935795,
|
|
"num_tokens": 5524413.0,
|
|
"step": 2530
|
|
},
|
|
{
|
|
"entropy": 5.91346435546875,
|
|
"epoch": 0.25158793171893606,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.000499737461680026,
|
|
"loss": 5.7945,
|
|
"mean_token_accuracy": 0.12549405321478843,
|
|
"num_tokens": 5533692.0,
|
|
"step": 2535
|
|
},
|
|
{
|
|
"entropy": 6.0045164108276365,
|
|
"epoch": 0.2520841603811036,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004997357477641207,
|
|
"loss": 5.9264,
|
|
"mean_token_accuracy": 0.13241172581911087,
|
|
"num_tokens": 5545955.0,
|
|
"step": 2540
|
|
},
|
|
{
|
|
"entropy": 5.92925500869751,
|
|
"epoch": 0.2525803890432711,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004997340282752532,
|
|
"loss": 5.8668,
|
|
"mean_token_accuracy": 0.13234830275177956,
|
|
"num_tokens": 5557667.0,
|
|
"step": 2545
|
|
},
|
|
{
|
|
"entropy": 5.862270545959473,
|
|
"epoch": 0.25307661770543866,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000499732303213466,
|
|
"loss": 5.7624,
|
|
"mean_token_accuracy": 0.12981996908783913,
|
|
"num_tokens": 5567635.0,
|
|
"step": 2550
|
|
},
|
|
{
|
|
"entropy": 5.9047070980072025,
|
|
"epoch": 0.2535728463676062,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004997305725788019,
|
|
"loss": 5.7698,
|
|
"mean_token_accuracy": 0.13442888036370276,
|
|
"num_tokens": 5578584.0,
|
|
"step": 2555
|
|
},
|
|
{
|
|
"entropy": 6.005180597305298,
|
|
"epoch": 0.2540690750297737,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000499728836371304,
|
|
"loss": 5.8818,
|
|
"mean_token_accuracy": 0.12881023287773133,
|
|
"num_tokens": 5589679.0,
|
|
"step": 2560
|
|
},
|
|
{
|
|
"entropy": 5.980772924423218,
|
|
"epoch": 0.25456530369194125,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004997270945910151,
|
|
"loss": 5.8516,
|
|
"mean_token_accuracy": 0.12968761026859282,
|
|
"num_tokens": 5601550.0,
|
|
"step": 2565
|
|
},
|
|
{
|
|
"entropy": 5.974395275115967,
|
|
"epoch": 0.2550615323541088,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004997253472379785,
|
|
"loss": 5.8688,
|
|
"mean_token_accuracy": 0.1274749144911766,
|
|
"num_tokens": 5611777.0,
|
|
"step": 2570
|
|
},
|
|
{
|
|
"entropy": 5.999769496917724,
|
|
"epoch": 0.2555577610162763,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004997235943122375,
|
|
"loss": 5.8864,
|
|
"mean_token_accuracy": 0.13235417976975442,
|
|
"num_tokens": 5623792.0,
|
|
"step": 2575
|
|
},
|
|
{
|
|
"entropy": 5.866275358200073,
|
|
"epoch": 0.25605398967844384,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004997218358138356,
|
|
"loss": 5.6778,
|
|
"mean_token_accuracy": 0.13726607859134674,
|
|
"num_tokens": 5634072.0,
|
|
"step": 2580
|
|
},
|
|
{
|
|
"entropy": 5.999044752120971,
|
|
"epoch": 0.25655021834061137,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004997200717428165,
|
|
"loss": 5.9544,
|
|
"mean_token_accuracy": 0.12634836062788962,
|
|
"num_tokens": 5645046.0,
|
|
"step": 2585
|
|
},
|
|
{
|
|
"entropy": 5.904431629180908,
|
|
"epoch": 0.2570464470027789,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004997183020992237,
|
|
"loss": 5.809,
|
|
"mean_token_accuracy": 0.1285477615892887,
|
|
"num_tokens": 5655156.0,
|
|
"step": 2590
|
|
},
|
|
{
|
|
"entropy": 5.938637113571167,
|
|
"epoch": 0.25754267566494643,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004997165268831014,
|
|
"loss": 5.7818,
|
|
"mean_token_accuracy": 0.13181826770305632,
|
|
"num_tokens": 5665621.0,
|
|
"step": 2595
|
|
},
|
|
{
|
|
"entropy": 5.93091344833374,
|
|
"epoch": 0.25803890432711396,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004997147460944933,
|
|
"loss": 5.8289,
|
|
"mean_token_accuracy": 0.12735895141959191,
|
|
"num_tokens": 5677072.0,
|
|
"step": 2600
|
|
},
|
|
{
|
|
"entropy": 6.021169185638428,
|
|
"epoch": 0.25853513298928144,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004997129597334438,
|
|
"loss": 5.7873,
|
|
"mean_token_accuracy": 0.1364290252327919,
|
|
"num_tokens": 5687926.0,
|
|
"step": 2605
|
|
},
|
|
{
|
|
"entropy": 5.8465227603912355,
|
|
"epoch": 0.25903136165144897,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004997111677999971,
|
|
"loss": 5.7934,
|
|
"mean_token_accuracy": 0.13265275880694388,
|
|
"num_tokens": 5698923.0,
|
|
"step": 2610
|
|
},
|
|
{
|
|
"entropy": 5.994477939605713,
|
|
"epoch": 0.2595275903136165,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004997093702941976,
|
|
"loss": 5.9077,
|
|
"mean_token_accuracy": 0.12608013227581977,
|
|
"num_tokens": 5709879.0,
|
|
"step": 2615
|
|
},
|
|
{
|
|
"entropy": 6.012147760391235,
|
|
"epoch": 0.260023818975784,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00049970756721609,
|
|
"loss": 5.849,
|
|
"mean_token_accuracy": 0.13115165755152702,
|
|
"num_tokens": 5720698.0,
|
|
"step": 2620
|
|
},
|
|
{
|
|
"entropy": 5.843365859985352,
|
|
"epoch": 0.26052004763795156,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.000499705758565719,
|
|
"loss": 5.8038,
|
|
"mean_token_accuracy": 0.13133684992790223,
|
|
"num_tokens": 5732890.0,
|
|
"step": 2625
|
|
},
|
|
{
|
|
"entropy": 5.973391675949097,
|
|
"epoch": 0.2610162763001191,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004997039443431292,
|
|
"loss": 5.7878,
|
|
"mean_token_accuracy": 0.12773183211684228,
|
|
"num_tokens": 5743741.0,
|
|
"step": 2630
|
|
},
|
|
{
|
|
"entropy": 5.905499076843261,
|
|
"epoch": 0.2615125049622866,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004997021245483659,
|
|
"loss": 5.7137,
|
|
"mean_token_accuracy": 0.13542912974953653,
|
|
"num_tokens": 5754730.0,
|
|
"step": 2635
|
|
},
|
|
{
|
|
"entropy": 5.871477842330933,
|
|
"epoch": 0.26200873362445415,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.000499700299181474,
|
|
"loss": 5.7528,
|
|
"mean_token_accuracy": 0.13477372154593467,
|
|
"num_tokens": 5764705.0,
|
|
"step": 2640
|
|
},
|
|
{
|
|
"entropy": 5.9722490310668945,
|
|
"epoch": 0.2625049622866217,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004996984682424989,
|
|
"loss": 5.865,
|
|
"mean_token_accuracy": 0.12664012461900712,
|
|
"num_tokens": 5776803.0,
|
|
"step": 2645
|
|
},
|
|
{
|
|
"entropy": 6.041519641876221,
|
|
"epoch": 0.2630011909487892,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000499696631731486,
|
|
"loss": 5.8975,
|
|
"mean_token_accuracy": 0.1250507615506649,
|
|
"num_tokens": 5788203.0,
|
|
"step": 2650
|
|
},
|
|
{
|
|
"entropy": 6.021883153915406,
|
|
"epoch": 0.26349741961095674,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.0004996947896484809,
|
|
"loss": 5.8195,
|
|
"mean_token_accuracy": 0.12791492864489556,
|
|
"num_tokens": 5800476.0,
|
|
"step": 2655
|
|
},
|
|
{
|
|
"entropy": 5.887351179122925,
|
|
"epoch": 0.26399364827312427,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.000499692941993529,
|
|
"loss": 5.8694,
|
|
"mean_token_accuracy": 0.12800540328025817,
|
|
"num_tokens": 5811652.0,
|
|
"step": 2660
|
|
},
|
|
{
|
|
"entropy": 5.990099906921387,
|
|
"epoch": 0.2644898769352918,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004996910887666765,
|
|
"loss": 5.7816,
|
|
"mean_token_accuracy": 0.1410517655313015,
|
|
"num_tokens": 5823036.0,
|
|
"step": 2665
|
|
},
|
|
{
|
|
"entropy": 5.909138345718384,
|
|
"epoch": 0.26498610559745933,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000499689229967969,
|
|
"loss": 5.7264,
|
|
"mean_token_accuracy": 0.13503767773509026,
|
|
"num_tokens": 5833220.0,
|
|
"step": 2670
|
|
},
|
|
{
|
|
"entropy": 5.86794605255127,
|
|
"epoch": 0.26548233425962686,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004996873655974529,
|
|
"loss": 5.8144,
|
|
"mean_token_accuracy": 0.12698522582650185,
|
|
"num_tokens": 5843777.0,
|
|
"step": 2675
|
|
},
|
|
{
|
|
"entropy": 5.916513824462891,
|
|
"epoch": 0.26597856292179434,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004996854956551743,
|
|
"loss": 5.8224,
|
|
"mean_token_accuracy": 0.1307629682123661,
|
|
"num_tokens": 5854942.0,
|
|
"step": 2680
|
|
},
|
|
{
|
|
"entropy": 5.988381481170654,
|
|
"epoch": 0.26647479158396187,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004996836201411794,
|
|
"loss": 5.8396,
|
|
"mean_token_accuracy": 0.1324163593351841,
|
|
"num_tokens": 5866536.0,
|
|
"step": 2685
|
|
},
|
|
{
|
|
"entropy": 5.9175981998443605,
|
|
"epoch": 0.2669710202461294,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.000499681739055515,
|
|
"loss": 5.7219,
|
|
"mean_token_accuracy": 0.1395683117210865,
|
|
"num_tokens": 5876653.0,
|
|
"step": 2690
|
|
},
|
|
{
|
|
"entropy": 5.919457578659058,
|
|
"epoch": 0.26746724890829693,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004996798523982276,
|
|
"loss": 5.7461,
|
|
"mean_token_accuracy": 0.12860351651906968,
|
|
"num_tokens": 5887092.0,
|
|
"step": 2695
|
|
},
|
|
{
|
|
"entropy": 5.938131856918335,
|
|
"epoch": 0.26796347757046446,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.000499677960169364,
|
|
"loss": 5.8721,
|
|
"mean_token_accuracy": 0.1272119738161564,
|
|
"num_tokens": 5898224.0,
|
|
"step": 2700
|
|
},
|
|
{
|
|
"entropy": 5.945243692398071,
|
|
"epoch": 0.268459706232632,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004996760623689711,
|
|
"loss": 5.7136,
|
|
"mean_token_accuracy": 0.13979979678988458,
|
|
"num_tokens": 5909235.0,
|
|
"step": 2705
|
|
},
|
|
{
|
|
"entropy": 5.943400955200195,
|
|
"epoch": 0.2689559348947995,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.000499674158997096,
|
|
"loss": 5.8699,
|
|
"mean_token_accuracy": 0.13342854082584382,
|
|
"num_tokens": 5921299.0,
|
|
"step": 2710
|
|
},
|
|
{
|
|
"entropy": 5.9730690002441404,
|
|
"epoch": 0.26945216355696705,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004996722500537859,
|
|
"loss": 5.8334,
|
|
"mean_token_accuracy": 0.12727866619825362,
|
|
"num_tokens": 5933249.0,
|
|
"step": 2715
|
|
},
|
|
{
|
|
"entropy": 5.9161705493927,
|
|
"epoch": 0.2699483922191346,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004996703355390881,
|
|
"loss": 5.8614,
|
|
"mean_token_accuracy": 0.12605185210704803,
|
|
"num_tokens": 5945942.0,
|
|
"step": 2720
|
|
},
|
|
{
|
|
"entropy": 5.93488187789917,
|
|
"epoch": 0.2704446208813021,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00049966841545305,
|
|
"loss": 5.7666,
|
|
"mean_token_accuracy": 0.1335825651884079,
|
|
"num_tokens": 5956315.0,
|
|
"step": 2725
|
|
},
|
|
{
|
|
"entropy": 5.966945314407349,
|
|
"epoch": 0.27094084954346964,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004996664897957195,
|
|
"loss": 5.854,
|
|
"mean_token_accuracy": 0.12438153848052025,
|
|
"num_tokens": 5966566.0,
|
|
"step": 2730
|
|
},
|
|
{
|
|
"entropy": 5.866949892044067,
|
|
"epoch": 0.2714370782056372,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004996645585671441,
|
|
"loss": 5.7093,
|
|
"mean_token_accuracy": 0.13864025473594666,
|
|
"num_tokens": 5977137.0,
|
|
"step": 2735
|
|
},
|
|
{
|
|
"entropy": 5.936009550094605,
|
|
"epoch": 0.2719333068678047,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004996626217673717,
|
|
"loss": 5.8313,
|
|
"mean_token_accuracy": 0.1317468449473381,
|
|
"num_tokens": 5987653.0,
|
|
"step": 2740
|
|
},
|
|
{
|
|
"entropy": 5.963485193252564,
|
|
"epoch": 0.27242953552997223,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004996606793964504,
|
|
"loss": 5.887,
|
|
"mean_token_accuracy": 0.1295153670012951,
|
|
"num_tokens": 5998530.0,
|
|
"step": 2745
|
|
},
|
|
{
|
|
"entropy": 5.893201017379761,
|
|
"epoch": 0.27292576419213976,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004996587314544284,
|
|
"loss": 5.7099,
|
|
"mean_token_accuracy": 0.13821978718042374,
|
|
"num_tokens": 6009550.0,
|
|
"step": 2750
|
|
},
|
|
{
|
|
"entropy": 5.940571975708008,
|
|
"epoch": 0.27342199285430724,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004996567779413539,
|
|
"loss": 5.9101,
|
|
"mean_token_accuracy": 0.12932207062840462,
|
|
"num_tokens": 6021522.0,
|
|
"step": 2755
|
|
},
|
|
{
|
|
"entropy": 5.959524393081665,
|
|
"epoch": 0.27391822151647477,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004996548188572755,
|
|
"loss": 5.7807,
|
|
"mean_token_accuracy": 0.13457212075591088,
|
|
"num_tokens": 6033993.0,
|
|
"step": 2760
|
|
},
|
|
{
|
|
"entropy": 5.988877677917481,
|
|
"epoch": 0.2744144501786423,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004996528542022416,
|
|
"loss": 5.9458,
|
|
"mean_token_accuracy": 0.1262620911002159,
|
|
"num_tokens": 6044804.0,
|
|
"step": 2765
|
|
},
|
|
{
|
|
"entropy": 5.921116924285888,
|
|
"epoch": 0.27491067884080983,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.000499650883976301,
|
|
"loss": 5.7866,
|
|
"mean_token_accuracy": 0.1267233669757843,
|
|
"num_tokens": 6054878.0,
|
|
"step": 2770
|
|
},
|
|
{
|
|
"entropy": 5.956991338729859,
|
|
"epoch": 0.27540690750297736,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004996489081795026,
|
|
"loss": 5.7891,
|
|
"mean_token_accuracy": 0.13266447335481643,
|
|
"num_tokens": 6065492.0,
|
|
"step": 2775
|
|
},
|
|
{
|
|
"entropy": 5.925124549865723,
|
|
"epoch": 0.2759031361651449,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004996469268118953,
|
|
"loss": 5.811,
|
|
"mean_token_accuracy": 0.12755917012691498,
|
|
"num_tokens": 6077360.0,
|
|
"step": 2780
|
|
},
|
|
{
|
|
"entropy": 5.918424940109253,
|
|
"epoch": 0.2763993648273124,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004996449398735283,
|
|
"loss": 5.7938,
|
|
"mean_token_accuracy": 0.12594451755285263,
|
|
"num_tokens": 6087530.0,
|
|
"step": 2785
|
|
},
|
|
{
|
|
"entropy": 5.934395456314087,
|
|
"epoch": 0.27689559348947995,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004996429473644509,
|
|
"loss": 5.7659,
|
|
"mean_token_accuracy": 0.13185836747288704,
|
|
"num_tokens": 6098064.0,
|
|
"step": 2790
|
|
},
|
|
{
|
|
"entropy": 5.828168869018555,
|
|
"epoch": 0.2773918221516475,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004996409492847124,
|
|
"loss": 5.701,
|
|
"mean_token_accuracy": 0.13495547845959663,
|
|
"num_tokens": 6108446.0,
|
|
"step": 2795
|
|
},
|
|
{
|
|
"entropy": 5.9052245140075685,
|
|
"epoch": 0.277888050813815,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004996389456343624,
|
|
"loss": 5.7486,
|
|
"mean_token_accuracy": 0.13034897968173026,
|
|
"num_tokens": 6118923.0,
|
|
"step": 2800
|
|
},
|
|
{
|
|
"entropy": 5.881168937683105,
|
|
"epoch": 0.27838427947598254,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004996369364134507,
|
|
"loss": 5.6589,
|
|
"mean_token_accuracy": 0.1399786502122879,
|
|
"num_tokens": 6130583.0,
|
|
"step": 2805
|
|
},
|
|
{
|
|
"entropy": 5.936345386505127,
|
|
"epoch": 0.2788805081381501,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.000499634921622027,
|
|
"loss": 5.8739,
|
|
"mean_token_accuracy": 0.12864407300949096,
|
|
"num_tokens": 6142351.0,
|
|
"step": 2810
|
|
},
|
|
{
|
|
"entropy": 5.869996118545532,
|
|
"epoch": 0.2793767368003176,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004996329012601413,
|
|
"loss": 5.69,
|
|
"mean_token_accuracy": 0.135867390781641,
|
|
"num_tokens": 6152964.0,
|
|
"step": 2815
|
|
},
|
|
{
|
|
"entropy": 5.823973894119263,
|
|
"epoch": 0.27987296546248513,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004996308753278437,
|
|
"loss": 5.7623,
|
|
"mean_token_accuracy": 0.1387517362833023,
|
|
"num_tokens": 6163522.0,
|
|
"step": 2820
|
|
},
|
|
{
|
|
"entropy": 5.948193883895874,
|
|
"epoch": 0.28036919412465267,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004996288438251843,
|
|
"loss": 5.7879,
|
|
"mean_token_accuracy": 0.12974680438637734,
|
|
"num_tokens": 6174060.0,
|
|
"step": 2825
|
|
},
|
|
{
|
|
"entropy": 5.917904472351074,
|
|
"epoch": 0.28086542278682014,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004996268067522137,
|
|
"loss": 5.701,
|
|
"mean_token_accuracy": 0.13888110667467118,
|
|
"num_tokens": 6183850.0,
|
|
"step": 2830
|
|
},
|
|
{
|
|
"entropy": 5.905739784240723,
|
|
"epoch": 0.28136165144898767,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004996247641089823,
|
|
"loss": 5.7671,
|
|
"mean_token_accuracy": 0.12889229655265808,
|
|
"num_tokens": 6195073.0,
|
|
"step": 2835
|
|
},
|
|
{
|
|
"entropy": 5.953272962570191,
|
|
"epoch": 0.2818578801111552,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004996227158955409,
|
|
"loss": 5.8007,
|
|
"mean_token_accuracy": 0.12981446608901023,
|
|
"num_tokens": 6206658.0,
|
|
"step": 2840
|
|
},
|
|
{
|
|
"entropy": 5.779361295700073,
|
|
"epoch": 0.28235410877332273,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.00049962066211194,
|
|
"loss": 5.6868,
|
|
"mean_token_accuracy": 0.13519837632775306,
|
|
"num_tokens": 6217183.0,
|
|
"step": 2845
|
|
},
|
|
{
|
|
"entropy": 5.8369691371917725,
|
|
"epoch": 0.28285033743549026,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004996186027582308,
|
|
"loss": 5.7279,
|
|
"mean_token_accuracy": 0.13328900784254075,
|
|
"num_tokens": 6227575.0,
|
|
"step": 2850
|
|
},
|
|
{
|
|
"entropy": 5.891994619369507,
|
|
"epoch": 0.2833465660976578,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004996165378344642,
|
|
"loss": 5.7363,
|
|
"mean_token_accuracy": 0.13181785643100738,
|
|
"num_tokens": 6239698.0,
|
|
"step": 2855
|
|
},
|
|
{
|
|
"entropy": 5.858404922485351,
|
|
"epoch": 0.2838427947598253,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004996144673406914,
|
|
"loss": 5.7423,
|
|
"mean_token_accuracy": 0.1368052139878273,
|
|
"num_tokens": 6249730.0,
|
|
"step": 2860
|
|
},
|
|
{
|
|
"entropy": 5.834589242935181,
|
|
"epoch": 0.28433902342199285,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004996123912769639,
|
|
"loss": 5.7313,
|
|
"mean_token_accuracy": 0.13907284140586854,
|
|
"num_tokens": 6259493.0,
|
|
"step": 2865
|
|
},
|
|
{
|
|
"entropy": 5.90723762512207,
|
|
"epoch": 0.2848352520841604,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004996103096433332,
|
|
"loss": 5.74,
|
|
"mean_token_accuracy": 0.13290882706642151,
|
|
"num_tokens": 6269568.0,
|
|
"step": 2870
|
|
},
|
|
{
|
|
"entropy": 5.922413015365601,
|
|
"epoch": 0.2853314807463279,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004996082224398506,
|
|
"loss": 5.7645,
|
|
"mean_token_accuracy": 0.1388328976929188,
|
|
"num_tokens": 6280028.0,
|
|
"step": 2875
|
|
},
|
|
{
|
|
"entropy": 5.826960611343384,
|
|
"epoch": 0.28582770940849545,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004996061296665682,
|
|
"loss": 5.7286,
|
|
"mean_token_accuracy": 0.1314896821975708,
|
|
"num_tokens": 6290321.0,
|
|
"step": 2880
|
|
},
|
|
{
|
|
"entropy": 5.862280654907226,
|
|
"epoch": 0.286323938070663,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004996040313235377,
|
|
"loss": 5.728,
|
|
"mean_token_accuracy": 0.1321492835879326,
|
|
"num_tokens": 6300729.0,
|
|
"step": 2885
|
|
},
|
|
{
|
|
"entropy": 5.939273405075073,
|
|
"epoch": 0.2868201667328305,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004996019274108112,
|
|
"loss": 5.7601,
|
|
"mean_token_accuracy": 0.1290019102394581,
|
|
"num_tokens": 6311051.0,
|
|
"step": 2890
|
|
},
|
|
{
|
|
"entropy": 5.802321290969848,
|
|
"epoch": 0.28731639539499804,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.000499599817928441,
|
|
"loss": 5.6792,
|
|
"mean_token_accuracy": 0.1415045864880085,
|
|
"num_tokens": 6322201.0,
|
|
"step": 2895
|
|
},
|
|
{
|
|
"entropy": 5.875109529495239,
|
|
"epoch": 0.28781262405716557,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004995977028764792,
|
|
"loss": 5.7885,
|
|
"mean_token_accuracy": 0.133917373418808,
|
|
"num_tokens": 6332372.0,
|
|
"step": 2900
|
|
},
|
|
{
|
|
"entropy": 5.954572486877441,
|
|
"epoch": 0.28830885271933304,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004995955822549783,
|
|
"loss": 5.899,
|
|
"mean_token_accuracy": 0.13203557208180428,
|
|
"num_tokens": 6344070.0,
|
|
"step": 2905
|
|
},
|
|
{
|
|
"entropy": 5.788153886795044,
|
|
"epoch": 0.2888050813815006,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004995934560639909,
|
|
"loss": 5.7194,
|
|
"mean_token_accuracy": 0.13280046507716178,
|
|
"num_tokens": 6355118.0,
|
|
"step": 2910
|
|
},
|
|
{
|
|
"entropy": 5.910306978225708,
|
|
"epoch": 0.2893013100436681,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004995913243035699,
|
|
"loss": 5.7816,
|
|
"mean_token_accuracy": 0.13115150183439256,
|
|
"num_tokens": 6366722.0,
|
|
"step": 2915
|
|
},
|
|
{
|
|
"entropy": 5.846759939193726,
|
|
"epoch": 0.28979753870583563,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004995891869737678,
|
|
"loss": 5.7226,
|
|
"mean_token_accuracy": 0.13123665228486062,
|
|
"num_tokens": 6376190.0,
|
|
"step": 2920
|
|
},
|
|
{
|
|
"entropy": 5.852357482910156,
|
|
"epoch": 0.29029376736800316,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004995870440746379,
|
|
"loss": 5.8527,
|
|
"mean_token_accuracy": 0.1258479841053486,
|
|
"num_tokens": 6385883.0,
|
|
"step": 2925
|
|
},
|
|
{
|
|
"entropy": 5.875295686721802,
|
|
"epoch": 0.2907899960301707,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004995848956062333,
|
|
"loss": 5.7043,
|
|
"mean_token_accuracy": 0.1373466357588768,
|
|
"num_tokens": 6397762.0,
|
|
"step": 2930
|
|
},
|
|
{
|
|
"entropy": 5.876016473770141,
|
|
"epoch": 0.2912862246923382,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004995827415686071,
|
|
"loss": 5.8161,
|
|
"mean_token_accuracy": 0.12998180985450744,
|
|
"num_tokens": 6408972.0,
|
|
"step": 2935
|
|
},
|
|
{
|
|
"entropy": 5.8990397453308105,
|
|
"epoch": 0.29178245335450576,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.000499580581961813,
|
|
"loss": 5.6794,
|
|
"mean_token_accuracy": 0.13430978432297708,
|
|
"num_tokens": 6418998.0,
|
|
"step": 2940
|
|
},
|
|
{
|
|
"entropy": 5.945958471298217,
|
|
"epoch": 0.2922786820166733,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004995784167859043,
|
|
"loss": 5.7651,
|
|
"mean_token_accuracy": 0.13749361261725426,
|
|
"num_tokens": 6430046.0,
|
|
"step": 2945
|
|
},
|
|
{
|
|
"entropy": 5.919869470596313,
|
|
"epoch": 0.2927749106788408,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004995762460409349,
|
|
"loss": 5.7428,
|
|
"mean_token_accuracy": 0.13194330036640167,
|
|
"num_tokens": 6441351.0,
|
|
"step": 2950
|
|
},
|
|
{
|
|
"entropy": 5.815007972717285,
|
|
"epoch": 0.29327113934100835,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004995740697269584,
|
|
"loss": 5.7621,
|
|
"mean_token_accuracy": 0.1333144061267376,
|
|
"num_tokens": 6453259.0,
|
|
"step": 2955
|
|
},
|
|
{
|
|
"entropy": 5.883697414398194,
|
|
"epoch": 0.2937673680031759,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004995718878440289,
|
|
"loss": 5.7516,
|
|
"mean_token_accuracy": 0.1323343835771084,
|
|
"num_tokens": 6464819.0,
|
|
"step": 2960
|
|
},
|
|
{
|
|
"entropy": 5.958118867874146,
|
|
"epoch": 0.2942635966653434,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004995697003922006,
|
|
"loss": 5.8363,
|
|
"mean_token_accuracy": 0.13035116493701934,
|
|
"num_tokens": 6477315.0,
|
|
"step": 2965
|
|
},
|
|
{
|
|
"entropy": 5.872132253646851,
|
|
"epoch": 0.29475982532751094,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004995675073715274,
|
|
"loss": 5.7451,
|
|
"mean_token_accuracy": 0.13140062168240546,
|
|
"num_tokens": 6488461.0,
|
|
"step": 2970
|
|
},
|
|
{
|
|
"entropy": 5.804051685333252,
|
|
"epoch": 0.29525605398967847,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004995653087820641,
|
|
"loss": 5.7166,
|
|
"mean_token_accuracy": 0.13911211416125296,
|
|
"num_tokens": 6499486.0,
|
|
"step": 2975
|
|
},
|
|
{
|
|
"entropy": 5.947262525558472,
|
|
"epoch": 0.29575228265184594,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.000499563104623865,
|
|
"loss": 5.8091,
|
|
"mean_token_accuracy": 0.13345877602696418,
|
|
"num_tokens": 6511337.0,
|
|
"step": 2980
|
|
},
|
|
{
|
|
"entropy": 5.84906907081604,
|
|
"epoch": 0.2962485113140135,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004995608948969849,
|
|
"loss": 5.6918,
|
|
"mean_token_accuracy": 0.13708140105009078,
|
|
"num_tokens": 6521066.0,
|
|
"step": 2985
|
|
},
|
|
{
|
|
"entropy": 5.782366609573364,
|
|
"epoch": 0.296744739976181,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004995586796014784,
|
|
"loss": 5.7117,
|
|
"mean_token_accuracy": 0.13593292757868766,
|
|
"num_tokens": 6531267.0,
|
|
"step": 2990
|
|
},
|
|
{
|
|
"entropy": 5.831585788726807,
|
|
"epoch": 0.29724096863834853,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004995564587374005,
|
|
"loss": 5.7673,
|
|
"mean_token_accuracy": 0.12948553413152694,
|
|
"num_tokens": 6541891.0,
|
|
"step": 2995
|
|
},
|
|
{
|
|
"entropy": 5.903474807739258,
|
|
"epoch": 0.29773719730051607,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004995542323048063,
|
|
"loss": 5.7197,
|
|
"mean_token_accuracy": 0.13689327314496041,
|
|
"num_tokens": 6551974.0,
|
|
"step": 3000
|
|
},
|
|
{
|
|
"epoch": 0.29773719730051607,
|
|
"eval_entropy": 5.687596190596,
|
|
"eval_loss": 5.815427303314209,
|
|
"eval_mean_token_accuracy": 0.13528745296530922,
|
|
"eval_num_tokens": 6551974.0,
|
|
"eval_runtime": 20.4138,
|
|
"eval_samples_per_second": 1649.324,
|
|
"eval_steps_per_second": 206.184,
|
|
"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": 1631120449536000.0,
|
|
"train_batch_size": 16,
|
|
"trial_name": null,
|
|
"trial_params": null
|
|
}
|