84189 lines
2.3 MiB
84189 lines
2.3 MiB
{
|
|
"best_global_step": null,
|
|
"best_metric": null,
|
|
"best_model_checkpoint": null,
|
|
"epoch": 4.198330584295497,
|
|
"eval_steps": 3000,
|
|
"global_step": 42000,
|
|
"is_hyper_param_search": false,
|
|
"is_local_process_zero": true,
|
|
"is_world_process_zero": true,
|
|
"log_history": [
|
|
{
|
|
"entropy": 10.691937923431396,
|
|
"epoch": 0.00049982506122857,
|
|
"grad_norm": 12.5625,
|
|
"learning_rate": 2e-06,
|
|
"loss": 10.8222,
|
|
"mean_token_accuracy": 0.0,
|
|
"num_tokens": 9036.0,
|
|
"step": 5
|
|
},
|
|
{
|
|
"entropy": 10.691910362243652,
|
|
"epoch": 0.00099965012245714,
|
|
"grad_norm": 10.5625,
|
|
"learning_rate": 4.5e-06,
|
|
"loss": 10.7866,
|
|
"mean_token_accuracy": 8.539709378965198e-05,
|
|
"num_tokens": 19391.0,
|
|
"step": 10
|
|
},
|
|
{
|
|
"entropy": 10.691011714935303,
|
|
"epoch": 0.00149947518368571,
|
|
"grad_norm": 9.125,
|
|
"learning_rate": 7e-06,
|
|
"loss": 10.5826,
|
|
"mean_token_accuracy": 0.024504283629357814,
|
|
"num_tokens": 27896.0,
|
|
"step": 15
|
|
},
|
|
{
|
|
"entropy": 10.666096115112305,
|
|
"epoch": 0.00199930024491428,
|
|
"grad_norm": 6.03125,
|
|
"learning_rate": 9.5e-06,
|
|
"loss": 10.3675,
|
|
"mean_token_accuracy": 0.04187114499509335,
|
|
"num_tokens": 37280.0,
|
|
"step": 20
|
|
},
|
|
{
|
|
"entropy": 10.540959644317628,
|
|
"epoch": 0.00249912530614285,
|
|
"grad_norm": 4.125,
|
|
"learning_rate": 1.2e-05,
|
|
"loss": 10.1113,
|
|
"mean_token_accuracy": 0.042646989598870276,
|
|
"num_tokens": 46010.0,
|
|
"step": 25
|
|
},
|
|
{
|
|
"entropy": 10.54243049621582,
|
|
"epoch": 0.00299895036737142,
|
|
"grad_norm": 3.359375,
|
|
"learning_rate": 1.4500000000000002e-05,
|
|
"loss": 10.0177,
|
|
"mean_token_accuracy": 0.043468796834349635,
|
|
"num_tokens": 55972.0,
|
|
"step": 30
|
|
},
|
|
{
|
|
"entropy": 10.496186542510987,
|
|
"epoch": 0.00349877542859999,
|
|
"grad_norm": 2.640625,
|
|
"learning_rate": 1.7000000000000003e-05,
|
|
"loss": 9.9866,
|
|
"mean_token_accuracy": 0.0411271832883358,
|
|
"num_tokens": 66142.0,
|
|
"step": 35
|
|
},
|
|
{
|
|
"entropy": 10.507702732086182,
|
|
"epoch": 0.00399860048982856,
|
|
"grad_norm": 2.640625,
|
|
"learning_rate": 1.95e-05,
|
|
"loss": 9.8811,
|
|
"mean_token_accuracy": 0.04595596119761467,
|
|
"num_tokens": 74978.0,
|
|
"step": 40
|
|
},
|
|
{
|
|
"entropy": 10.479924392700195,
|
|
"epoch": 0.00449842555105713,
|
|
"grad_norm": 2.84375,
|
|
"learning_rate": 2.2e-05,
|
|
"loss": 9.832,
|
|
"mean_token_accuracy": 0.04226104132831097,
|
|
"num_tokens": 84153.0,
|
|
"step": 45
|
|
},
|
|
{
|
|
"entropy": 10.43626766204834,
|
|
"epoch": 0.0049982506122857,
|
|
"grad_norm": 2.3125,
|
|
"learning_rate": 2.4500000000000003e-05,
|
|
"loss": 9.8813,
|
|
"mean_token_accuracy": 0.044375188648700714,
|
|
"num_tokens": 94463.0,
|
|
"step": 50
|
|
},
|
|
{
|
|
"entropy": 10.442836666107178,
|
|
"epoch": 0.00549807567351427,
|
|
"grad_norm": 2.328125,
|
|
"learning_rate": 2.7e-05,
|
|
"loss": 9.803,
|
|
"mean_token_accuracy": 0.05454329513013363,
|
|
"num_tokens": 104182.0,
|
|
"step": 55
|
|
},
|
|
{
|
|
"entropy": 10.401250076293945,
|
|
"epoch": 0.00599790073474284,
|
|
"grad_norm": 2.390625,
|
|
"learning_rate": 2.95e-05,
|
|
"loss": 9.6939,
|
|
"mean_token_accuracy": 0.06315181367099285,
|
|
"num_tokens": 114058.0,
|
|
"step": 60
|
|
},
|
|
{
|
|
"entropy": 10.25614423751831,
|
|
"epoch": 0.00649772579597141,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 3.2e-05,
|
|
"loss": 9.71,
|
|
"mean_token_accuracy": 0.05851850733160972,
|
|
"num_tokens": 124154.0,
|
|
"step": 65
|
|
},
|
|
{
|
|
"entropy": 10.31090784072876,
|
|
"epoch": 0.00699755085719998,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 3.4500000000000005e-05,
|
|
"loss": 9.558,
|
|
"mean_token_accuracy": 0.06353861205279827,
|
|
"num_tokens": 132840.0,
|
|
"step": 70
|
|
},
|
|
{
|
|
"entropy": 10.33273687362671,
|
|
"epoch": 0.00749737591842855,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 3.7e-05,
|
|
"loss": 9.5868,
|
|
"mean_token_accuracy": 0.06003404222428799,
|
|
"num_tokens": 143070.0,
|
|
"step": 75
|
|
},
|
|
{
|
|
"entropy": 10.269068050384522,
|
|
"epoch": 0.00799720097965712,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 3.95e-05,
|
|
"loss": 9.5521,
|
|
"mean_token_accuracy": 0.058086647838354113,
|
|
"num_tokens": 153319.0,
|
|
"step": 80
|
|
},
|
|
{
|
|
"entropy": 10.333018684387207,
|
|
"epoch": 0.00849702604088569,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 4.2000000000000004e-05,
|
|
"loss": 9.4889,
|
|
"mean_token_accuracy": 0.056201324239373206,
|
|
"num_tokens": 163152.0,
|
|
"step": 85
|
|
},
|
|
{
|
|
"entropy": 10.19660234451294,
|
|
"epoch": 0.00899685110211426,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 4.45e-05,
|
|
"loss": 9.3242,
|
|
"mean_token_accuracy": 0.061852597072720526,
|
|
"num_tokens": 173321.0,
|
|
"step": 90
|
|
},
|
|
{
|
|
"entropy": 10.18037166595459,
|
|
"epoch": 0.00949667616334283,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 4.7000000000000004e-05,
|
|
"loss": 9.2932,
|
|
"mean_token_accuracy": 0.06662209033966064,
|
|
"num_tokens": 182827.0,
|
|
"step": 95
|
|
},
|
|
{
|
|
"entropy": 10.177055072784423,
|
|
"epoch": 0.0099965012245714,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 4.9500000000000004e-05,
|
|
"loss": 9.2359,
|
|
"mean_token_accuracy": 0.058009016513824466,
|
|
"num_tokens": 191776.0,
|
|
"step": 100
|
|
},
|
|
{
|
|
"entropy": 10.060395526885987,
|
|
"epoch": 0.01049632628579997,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 5.2e-05,
|
|
"loss": 9.1694,
|
|
"mean_token_accuracy": 0.06354880146682262,
|
|
"num_tokens": 201891.0,
|
|
"step": 105
|
|
},
|
|
{
|
|
"entropy": 10.131175804138184,
|
|
"epoch": 0.01099615134702854,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 5.45e-05,
|
|
"loss": 9.0742,
|
|
"mean_token_accuracy": 0.06335793063044548,
|
|
"num_tokens": 210385.0,
|
|
"step": 110
|
|
},
|
|
{
|
|
"entropy": 9.997744750976562,
|
|
"epoch": 0.01149597640825711,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 5.7e-05,
|
|
"loss": 9.0025,
|
|
"mean_token_accuracy": 0.06502830199897289,
|
|
"num_tokens": 220098.0,
|
|
"step": 115
|
|
},
|
|
{
|
|
"entropy": 9.930113220214844,
|
|
"epoch": 0.01199580146948568,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 5.9499999999999996e-05,
|
|
"loss": 8.9257,
|
|
"mean_token_accuracy": 0.06774141155183315,
|
|
"num_tokens": 230703.0,
|
|
"step": 120
|
|
},
|
|
{
|
|
"entropy": 9.789262199401856,
|
|
"epoch": 0.01249562653071425,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 6.2e-05,
|
|
"loss": 8.8116,
|
|
"mean_token_accuracy": 0.06662507690489292,
|
|
"num_tokens": 239545.0,
|
|
"step": 125
|
|
},
|
|
{
|
|
"entropy": 9.746065139770508,
|
|
"epoch": 0.01299545159194282,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 6.450000000000001e-05,
|
|
"loss": 8.75,
|
|
"mean_token_accuracy": 0.06277895718812943,
|
|
"num_tokens": 249726.0,
|
|
"step": 130
|
|
},
|
|
{
|
|
"entropy": 9.624966144561768,
|
|
"epoch": 0.01349527665317139,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 6.7e-05,
|
|
"loss": 8.8151,
|
|
"mean_token_accuracy": 0.06419860571622849,
|
|
"num_tokens": 259491.0,
|
|
"step": 135
|
|
},
|
|
{
|
|
"entropy": 9.605054950714111,
|
|
"epoch": 0.01399510171439996,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 6.950000000000001e-05,
|
|
"loss": 8.7127,
|
|
"mean_token_accuracy": 0.06086057834327221,
|
|
"num_tokens": 268239.0,
|
|
"step": 140
|
|
},
|
|
{
|
|
"entropy": 9.465878677368163,
|
|
"epoch": 0.01449492677562853,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 7.2e-05,
|
|
"loss": 8.6254,
|
|
"mean_token_accuracy": 0.0687973827123642,
|
|
"num_tokens": 276767.0,
|
|
"step": 145
|
|
},
|
|
{
|
|
"entropy": 9.377824974060058,
|
|
"epoch": 0.0149947518368571,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 7.45e-05,
|
|
"loss": 8.5576,
|
|
"mean_token_accuracy": 0.070676776394248,
|
|
"num_tokens": 286072.0,
|
|
"step": 150
|
|
},
|
|
{
|
|
"entropy": 9.257752609252929,
|
|
"epoch": 0.01549457689808567,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 7.7e-05,
|
|
"loss": 8.5675,
|
|
"mean_token_accuracy": 0.06347934491932392,
|
|
"num_tokens": 295178.0,
|
|
"step": 155
|
|
},
|
|
{
|
|
"entropy": 9.222655963897704,
|
|
"epoch": 0.01599440195931424,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 7.950000000000001e-05,
|
|
"loss": 8.6111,
|
|
"mean_token_accuracy": 0.06264784783124924,
|
|
"num_tokens": 305537.0,
|
|
"step": 160
|
|
},
|
|
{
|
|
"entropy": 9.114503574371337,
|
|
"epoch": 0.01649422702054281,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 8.2e-05,
|
|
"loss": 8.4682,
|
|
"mean_token_accuracy": 0.07314668670296669,
|
|
"num_tokens": 315316.0,
|
|
"step": 165
|
|
},
|
|
{
|
|
"entropy": 9.004597473144532,
|
|
"epoch": 0.01699405208177138,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 8.450000000000001e-05,
|
|
"loss": 8.491,
|
|
"mean_token_accuracy": 0.07030753418803215,
|
|
"num_tokens": 325089.0,
|
|
"step": 170
|
|
},
|
|
{
|
|
"entropy": 8.996741676330567,
|
|
"epoch": 0.01749387714299995,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 8.7e-05,
|
|
"loss": 8.4612,
|
|
"mean_token_accuracy": 0.06281476058065891,
|
|
"num_tokens": 334009.0,
|
|
"step": 175
|
|
},
|
|
{
|
|
"entropy": 8.929500389099122,
|
|
"epoch": 0.01799370220422852,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 8.95e-05,
|
|
"loss": 8.397,
|
|
"mean_token_accuracy": 0.06993251703679562,
|
|
"num_tokens": 342535.0,
|
|
"step": 180
|
|
},
|
|
{
|
|
"entropy": 8.847047901153564,
|
|
"epoch": 0.01849352726545709,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 9.2e-05,
|
|
"loss": 8.4064,
|
|
"mean_token_accuracy": 0.06550291888415813,
|
|
"num_tokens": 352324.0,
|
|
"step": 185
|
|
},
|
|
{
|
|
"entropy": 8.74924440383911,
|
|
"epoch": 0.01899335232668566,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 9.45e-05,
|
|
"loss": 8.4174,
|
|
"mean_token_accuracy": 0.0638185866177082,
|
|
"num_tokens": 362824.0,
|
|
"step": 190
|
|
},
|
|
{
|
|
"entropy": 8.884198856353759,
|
|
"epoch": 0.01949317738791423,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 9.7e-05,
|
|
"loss": 8.3963,
|
|
"mean_token_accuracy": 0.06174343600869179,
|
|
"num_tokens": 373056.0,
|
|
"step": 195
|
|
},
|
|
{
|
|
"entropy": 8.75450849533081,
|
|
"epoch": 0.0199930024491428,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 9.95e-05,
|
|
"loss": 8.3509,
|
|
"mean_token_accuracy": 0.07249316610395909,
|
|
"num_tokens": 382448.0,
|
|
"step": 200
|
|
},
|
|
{
|
|
"entropy": 8.695133495330811,
|
|
"epoch": 0.02049282751037137,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.000102,
|
|
"loss": 8.4227,
|
|
"mean_token_accuracy": 0.06916416324675083,
|
|
"num_tokens": 393640.0,
|
|
"step": 205
|
|
},
|
|
{
|
|
"entropy": 8.69532642364502,
|
|
"epoch": 0.02099265257159994,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00010449999999999999,
|
|
"loss": 8.4168,
|
|
"mean_token_accuracy": 0.07142675034701824,
|
|
"num_tokens": 403129.0,
|
|
"step": 210
|
|
},
|
|
{
|
|
"entropy": 8.696801376342773,
|
|
"epoch": 0.02149247763282851,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.000107,
|
|
"loss": 8.3599,
|
|
"mean_token_accuracy": 0.07293656915426254,
|
|
"num_tokens": 412673.0,
|
|
"step": 215
|
|
},
|
|
{
|
|
"entropy": 8.734815216064453,
|
|
"epoch": 0.02199230269405708,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0001095,
|
|
"loss": 8.3822,
|
|
"mean_token_accuracy": 0.07273878008127213,
|
|
"num_tokens": 422960.0,
|
|
"step": 220
|
|
},
|
|
{
|
|
"entropy": 8.641194057464599,
|
|
"epoch": 0.02249212775528565,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000112,
|
|
"loss": 8.3671,
|
|
"mean_token_accuracy": 0.0694367703050375,
|
|
"num_tokens": 433248.0,
|
|
"step": 225
|
|
},
|
|
{
|
|
"entropy": 8.656941223144532,
|
|
"epoch": 0.02299195281651422,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0001145,
|
|
"loss": 8.2924,
|
|
"mean_token_accuracy": 0.07617328315973282,
|
|
"num_tokens": 441738.0,
|
|
"step": 230
|
|
},
|
|
{
|
|
"entropy": 8.517578506469727,
|
|
"epoch": 0.02349177787774279,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00011700000000000001,
|
|
"loss": 8.3911,
|
|
"mean_token_accuracy": 0.07571800649166108,
|
|
"num_tokens": 451894.0,
|
|
"step": 235
|
|
},
|
|
{
|
|
"entropy": 8.691481590270996,
|
|
"epoch": 0.02399160293897136,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00011949999999999999,
|
|
"loss": 8.3454,
|
|
"mean_token_accuracy": 0.078226138651371,
|
|
"num_tokens": 462829.0,
|
|
"step": 240
|
|
},
|
|
{
|
|
"entropy": 8.61854429244995,
|
|
"epoch": 0.02449142800019993,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.000122,
|
|
"loss": 8.3429,
|
|
"mean_token_accuracy": 0.07184191048145294,
|
|
"num_tokens": 472034.0,
|
|
"step": 245
|
|
},
|
|
{
|
|
"entropy": 8.58093318939209,
|
|
"epoch": 0.0249912530614285,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0001245,
|
|
"loss": 8.3983,
|
|
"mean_token_accuracy": 0.06812773868441582,
|
|
"num_tokens": 481963.0,
|
|
"step": 250
|
|
},
|
|
{
|
|
"entropy": 8.630074882507325,
|
|
"epoch": 0.02549107812265707,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000127,
|
|
"loss": 8.2833,
|
|
"mean_token_accuracy": 0.07643958404660225,
|
|
"num_tokens": 491562.0,
|
|
"step": 255
|
|
},
|
|
{
|
|
"entropy": 8.551316165924073,
|
|
"epoch": 0.02599090318388564,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.0001295,
|
|
"loss": 8.226,
|
|
"mean_token_accuracy": 0.08187740184366703,
|
|
"num_tokens": 500884.0,
|
|
"step": 260
|
|
},
|
|
{
|
|
"entropy": 8.544846057891846,
|
|
"epoch": 0.026490728245114212,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.000132,
|
|
"loss": 8.2814,
|
|
"mean_token_accuracy": 0.07459888011217117,
|
|
"num_tokens": 510287.0,
|
|
"step": 265
|
|
},
|
|
{
|
|
"entropy": 8.609485721588134,
|
|
"epoch": 0.02699055330634278,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.00013450000000000002,
|
|
"loss": 8.2357,
|
|
"mean_token_accuracy": 0.0795067872852087,
|
|
"num_tokens": 519633.0,
|
|
"step": 270
|
|
},
|
|
{
|
|
"entropy": 8.487185859680176,
|
|
"epoch": 0.02749037836757135,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00013700000000000002,
|
|
"loss": 8.3194,
|
|
"mean_token_accuracy": 0.07536891847848892,
|
|
"num_tokens": 528999.0,
|
|
"step": 275
|
|
},
|
|
{
|
|
"entropy": 8.59107551574707,
|
|
"epoch": 0.02799020342879992,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0001395,
|
|
"loss": 8.2843,
|
|
"mean_token_accuracy": 0.07671510241925716,
|
|
"num_tokens": 538403.0,
|
|
"step": 280
|
|
},
|
|
{
|
|
"entropy": 8.52663278579712,
|
|
"epoch": 0.02849002849002849,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00014199999999999998,
|
|
"loss": 8.2385,
|
|
"mean_token_accuracy": 0.07777136862277985,
|
|
"num_tokens": 547716.0,
|
|
"step": 285
|
|
},
|
|
{
|
|
"entropy": 8.441480922698975,
|
|
"epoch": 0.02898985355125706,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0001445,
|
|
"loss": 8.2467,
|
|
"mean_token_accuracy": 0.07836432494223118,
|
|
"num_tokens": 557714.0,
|
|
"step": 290
|
|
},
|
|
{
|
|
"entropy": 8.63280029296875,
|
|
"epoch": 0.02948967861248563,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.000147,
|
|
"loss": 8.2838,
|
|
"mean_token_accuracy": 0.07826550751924514,
|
|
"num_tokens": 568591.0,
|
|
"step": 295
|
|
},
|
|
{
|
|
"entropy": 8.439323425292969,
|
|
"epoch": 0.0299895036737142,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0001495,
|
|
"loss": 8.1958,
|
|
"mean_token_accuracy": 0.08220398984849453,
|
|
"num_tokens": 578435.0,
|
|
"step": 300
|
|
},
|
|
{
|
|
"entropy": 8.447675704956055,
|
|
"epoch": 0.03048932873494277,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000152,
|
|
"loss": 8.2599,
|
|
"mean_token_accuracy": 0.07586241215467453,
|
|
"num_tokens": 587461.0,
|
|
"step": 305
|
|
},
|
|
{
|
|
"entropy": 8.497601222991943,
|
|
"epoch": 0.03098915379617134,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00015450000000000001,
|
|
"loss": 8.2869,
|
|
"mean_token_accuracy": 0.073284100741148,
|
|
"num_tokens": 597004.0,
|
|
"step": 310
|
|
},
|
|
{
|
|
"entropy": 8.525490951538085,
|
|
"epoch": 0.03148897885739991,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000157,
|
|
"loss": 8.2464,
|
|
"mean_token_accuracy": 0.07317042723298073,
|
|
"num_tokens": 607831.0,
|
|
"step": 315
|
|
},
|
|
{
|
|
"entropy": 8.550362873077393,
|
|
"epoch": 0.03198880391862848,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0001595,
|
|
"loss": 8.227,
|
|
"mean_token_accuracy": 0.08139617070555687,
|
|
"num_tokens": 618008.0,
|
|
"step": 320
|
|
},
|
|
{
|
|
"entropy": 8.355420207977295,
|
|
"epoch": 0.03248862897985705,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000162,
|
|
"loss": 8.1332,
|
|
"mean_token_accuracy": 0.08453277647495269,
|
|
"num_tokens": 627970.0,
|
|
"step": 325
|
|
},
|
|
{
|
|
"entropy": 8.438968658447266,
|
|
"epoch": 0.03298845404108562,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00016450000000000001,
|
|
"loss": 8.2245,
|
|
"mean_token_accuracy": 0.07926518805325031,
|
|
"num_tokens": 638059.0,
|
|
"step": 330
|
|
},
|
|
{
|
|
"entropy": 8.503382587432862,
|
|
"epoch": 0.03348827910231419,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00016700000000000002,
|
|
"loss": 8.2997,
|
|
"mean_token_accuracy": 0.07444430701434612,
|
|
"num_tokens": 648169.0,
|
|
"step": 335
|
|
},
|
|
{
|
|
"entropy": 8.4659499168396,
|
|
"epoch": 0.03398810416354276,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.00016950000000000003,
|
|
"loss": 8.2816,
|
|
"mean_token_accuracy": 0.07408055253326892,
|
|
"num_tokens": 659351.0,
|
|
"step": 340
|
|
},
|
|
{
|
|
"entropy": 8.479489421844482,
|
|
"epoch": 0.03448792922477133,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00017199999999999998,
|
|
"loss": 8.1133,
|
|
"mean_token_accuracy": 0.081477539986372,
|
|
"num_tokens": 669602.0,
|
|
"step": 345
|
|
},
|
|
{
|
|
"entropy": 8.449872016906738,
|
|
"epoch": 0.0349877542859999,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00017449999999999999,
|
|
"loss": 8.208,
|
|
"mean_token_accuracy": 0.07832706868648528,
|
|
"num_tokens": 679497.0,
|
|
"step": 350
|
|
},
|
|
{
|
|
"entropy": 8.401834392547608,
|
|
"epoch": 0.03548757934722847,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.000177,
|
|
"loss": 8.1508,
|
|
"mean_token_accuracy": 0.08282142281532287,
|
|
"num_tokens": 689020.0,
|
|
"step": 355
|
|
},
|
|
{
|
|
"entropy": 8.419000816345214,
|
|
"epoch": 0.03598740440845704,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0001795,
|
|
"loss": 8.1319,
|
|
"mean_token_accuracy": 0.08381059765815735,
|
|
"num_tokens": 697505.0,
|
|
"step": 360
|
|
},
|
|
{
|
|
"entropy": 8.416812896728516,
|
|
"epoch": 0.03648722946968561,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000182,
|
|
"loss": 8.1197,
|
|
"mean_token_accuracy": 0.07555183880031109,
|
|
"num_tokens": 707646.0,
|
|
"step": 365
|
|
},
|
|
{
|
|
"entropy": 8.340746212005616,
|
|
"epoch": 0.03698705453091418,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0001845,
|
|
"loss": 8.0655,
|
|
"mean_token_accuracy": 0.0808980330824852,
|
|
"num_tokens": 717345.0,
|
|
"step": 370
|
|
},
|
|
{
|
|
"entropy": 8.354646587371827,
|
|
"epoch": 0.03748687959214275,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000187,
|
|
"loss": 8.1434,
|
|
"mean_token_accuracy": 0.08112207651138306,
|
|
"num_tokens": 727785.0,
|
|
"step": 375
|
|
},
|
|
{
|
|
"entropy": 8.41817512512207,
|
|
"epoch": 0.03798670465337132,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0001895,
|
|
"loss": 8.1431,
|
|
"mean_token_accuracy": 0.08172658756375313,
|
|
"num_tokens": 737740.0,
|
|
"step": 380
|
|
},
|
|
{
|
|
"entropy": 8.356461238861083,
|
|
"epoch": 0.03848652971459989,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000192,
|
|
"loss": 8.1072,
|
|
"mean_token_accuracy": 0.07860676273703575,
|
|
"num_tokens": 747026.0,
|
|
"step": 385
|
|
},
|
|
{
|
|
"entropy": 8.281126689910888,
|
|
"epoch": 0.03898635477582846,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0001945,
|
|
"loss": 8.0719,
|
|
"mean_token_accuracy": 0.08162726536393165,
|
|
"num_tokens": 756798.0,
|
|
"step": 390
|
|
},
|
|
{
|
|
"entropy": 8.545885276794433,
|
|
"epoch": 0.03948617983705703,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00019700000000000002,
|
|
"loss": 8.1337,
|
|
"mean_token_accuracy": 0.07723894119262695,
|
|
"num_tokens": 765730.0,
|
|
"step": 395
|
|
},
|
|
{
|
|
"entropy": 8.221963024139404,
|
|
"epoch": 0.0399860048982856,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00019950000000000002,
|
|
"loss": 8.1068,
|
|
"mean_token_accuracy": 0.08807171508669853,
|
|
"num_tokens": 776330.0,
|
|
"step": 400
|
|
},
|
|
{
|
|
"entropy": 8.33034019470215,
|
|
"epoch": 0.04048582995951417,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000202,
|
|
"loss": 8.1773,
|
|
"mean_token_accuracy": 0.0784314177930355,
|
|
"num_tokens": 785840.0,
|
|
"step": 405
|
|
},
|
|
{
|
|
"entropy": 8.340146541595459,
|
|
"epoch": 0.04098565502074274,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00020449999999999998,
|
|
"loss": 8.0226,
|
|
"mean_token_accuracy": 0.08303822055459023,
|
|
"num_tokens": 795126.0,
|
|
"step": 410
|
|
},
|
|
{
|
|
"entropy": 8.34009313583374,
|
|
"epoch": 0.04148548008197131,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000207,
|
|
"loss": 8.1702,
|
|
"mean_token_accuracy": 0.07932347059249878,
|
|
"num_tokens": 805766.0,
|
|
"step": 415
|
|
},
|
|
{
|
|
"entropy": 8.330490493774414,
|
|
"epoch": 0.04198530514319988,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.0002095,
|
|
"loss": 8.1115,
|
|
"mean_token_accuracy": 0.08066079020500183,
|
|
"num_tokens": 815202.0,
|
|
"step": 420
|
|
},
|
|
{
|
|
"entropy": 8.372891998291015,
|
|
"epoch": 0.04248513020442845,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.000212,
|
|
"loss": 8.0709,
|
|
"mean_token_accuracy": 0.08375605717301368,
|
|
"num_tokens": 825065.0,
|
|
"step": 425
|
|
},
|
|
{
|
|
"entropy": 8.171288871765137,
|
|
"epoch": 0.04298495526565702,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0002145,
|
|
"loss": 8.0681,
|
|
"mean_token_accuracy": 0.0807822324335575,
|
|
"num_tokens": 834088.0,
|
|
"step": 430
|
|
},
|
|
{
|
|
"entropy": 8.329067707061768,
|
|
"epoch": 0.04348478032688559,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00021700000000000002,
|
|
"loss": 8.104,
|
|
"mean_token_accuracy": 0.08128277212381363,
|
|
"num_tokens": 843653.0,
|
|
"step": 435
|
|
},
|
|
{
|
|
"entropy": 8.247820854187012,
|
|
"epoch": 0.04398460538811416,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0002195,
|
|
"loss": 7.9929,
|
|
"mean_token_accuracy": 0.08918308317661286,
|
|
"num_tokens": 853248.0,
|
|
"step": 440
|
|
},
|
|
{
|
|
"entropy": 8.318993091583252,
|
|
"epoch": 0.04448443044934273,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.000222,
|
|
"loss": 8.1379,
|
|
"mean_token_accuracy": 0.08139327839016915,
|
|
"num_tokens": 863814.0,
|
|
"step": 445
|
|
},
|
|
{
|
|
"entropy": 8.30269651412964,
|
|
"epoch": 0.0449842555105713,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0002245,
|
|
"loss": 8.0395,
|
|
"mean_token_accuracy": 0.08268025442957878,
|
|
"num_tokens": 874030.0,
|
|
"step": 450
|
|
},
|
|
{
|
|
"entropy": 8.289182376861572,
|
|
"epoch": 0.04548408057179987,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00022700000000000002,
|
|
"loss": 8.0309,
|
|
"mean_token_accuracy": 0.09102015197277069,
|
|
"num_tokens": 883006.0,
|
|
"step": 455
|
|
},
|
|
{
|
|
"entropy": 8.175302314758301,
|
|
"epoch": 0.04598390563302844,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00022950000000000002,
|
|
"loss": 7.9755,
|
|
"mean_token_accuracy": 0.0876532681286335,
|
|
"num_tokens": 892953.0,
|
|
"step": 460
|
|
},
|
|
{
|
|
"entropy": 8.333348941802978,
|
|
"epoch": 0.04648373069425701,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00023200000000000003,
|
|
"loss": 8.1284,
|
|
"mean_token_accuracy": 0.08013307489454746,
|
|
"num_tokens": 904228.0,
|
|
"step": 465
|
|
},
|
|
{
|
|
"entropy": 8.185042667388917,
|
|
"epoch": 0.04698355575548558,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00023449999999999998,
|
|
"loss": 8.0155,
|
|
"mean_token_accuracy": 0.0849261574447155,
|
|
"num_tokens": 915161.0,
|
|
"step": 470
|
|
},
|
|
{
|
|
"entropy": 8.251577377319336,
|
|
"epoch": 0.04748338081671415,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.000237,
|
|
"loss": 8.1226,
|
|
"mean_token_accuracy": 0.07527048066258431,
|
|
"num_tokens": 925167.0,
|
|
"step": 475
|
|
},
|
|
{
|
|
"entropy": 8.203055572509765,
|
|
"epoch": 0.04798320587794272,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0002395,
|
|
"loss": 8.0031,
|
|
"mean_token_accuracy": 0.08475866988301277,
|
|
"num_tokens": 934742.0,
|
|
"step": 480
|
|
},
|
|
{
|
|
"entropy": 8.263946628570556,
|
|
"epoch": 0.04848303093917129,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000242,
|
|
"loss": 8.0565,
|
|
"mean_token_accuracy": 0.08061288818717002,
|
|
"num_tokens": 944549.0,
|
|
"step": 485
|
|
},
|
|
{
|
|
"entropy": 8.130996036529542,
|
|
"epoch": 0.04898285600039986,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0002445,
|
|
"loss": 7.9566,
|
|
"mean_token_accuracy": 0.09062113910913468,
|
|
"num_tokens": 954668.0,
|
|
"step": 490
|
|
},
|
|
{
|
|
"entropy": 8.40848512649536,
|
|
"epoch": 0.04948268106162843,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000247,
|
|
"loss": 8.0619,
|
|
"mean_token_accuracy": 0.07748850770294666,
|
|
"num_tokens": 964953.0,
|
|
"step": 495
|
|
},
|
|
{
|
|
"entropy": 8.065672302246094,
|
|
"epoch": 0.049982506122857,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0002495,
|
|
"loss": 7.9449,
|
|
"mean_token_accuracy": 0.09317015185952186,
|
|
"num_tokens": 974820.0,
|
|
"step": 500
|
|
},
|
|
{
|
|
"entropy": 8.159075212478637,
|
|
"epoch": 0.05048233118408557,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.000252,
|
|
"loss": 7.9396,
|
|
"mean_token_accuracy": 0.0863773450255394,
|
|
"num_tokens": 984888.0,
|
|
"step": 505
|
|
},
|
|
{
|
|
"entropy": 8.047884082794189,
|
|
"epoch": 0.05098215624531414,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0002545,
|
|
"loss": 7.9632,
|
|
"mean_token_accuracy": 0.08658726513385773,
|
|
"num_tokens": 993731.0,
|
|
"step": 510
|
|
},
|
|
{
|
|
"entropy": 8.219942665100097,
|
|
"epoch": 0.05148198130654271,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000257,
|
|
"loss": 7.9006,
|
|
"mean_token_accuracy": 0.08839990794658661,
|
|
"num_tokens": 1003138.0,
|
|
"step": 515
|
|
},
|
|
{
|
|
"entropy": 8.084060764312744,
|
|
"epoch": 0.05198180636777128,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0002595,
|
|
"loss": 7.899,
|
|
"mean_token_accuracy": 0.08839784786105156,
|
|
"num_tokens": 1012058.0,
|
|
"step": 520
|
|
},
|
|
{
|
|
"entropy": 8.172471237182616,
|
|
"epoch": 0.05248163142899985,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.000262,
|
|
"loss": 7.9093,
|
|
"mean_token_accuracy": 0.09066133350133895,
|
|
"num_tokens": 1020804.0,
|
|
"step": 525
|
|
},
|
|
{
|
|
"entropy": 8.197671794891358,
|
|
"epoch": 0.052981456490228424,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00026450000000000003,
|
|
"loss": 7.9273,
|
|
"mean_token_accuracy": 0.08465270027518272,
|
|
"num_tokens": 1030432.0,
|
|
"step": 530
|
|
},
|
|
{
|
|
"entropy": 8.110610485076904,
|
|
"epoch": 0.05348128155145699,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00026700000000000004,
|
|
"loss": 7.8986,
|
|
"mean_token_accuracy": 0.09049126878380775,
|
|
"num_tokens": 1039336.0,
|
|
"step": 535
|
|
},
|
|
{
|
|
"entropy": 8.07482190132141,
|
|
"epoch": 0.05398110661268556,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00026950000000000005,
|
|
"loss": 7.8544,
|
|
"mean_token_accuracy": 0.09336550831794739,
|
|
"num_tokens": 1049314.0,
|
|
"step": 540
|
|
},
|
|
{
|
|
"entropy": 8.168315505981445,
|
|
"epoch": 0.05448093167391413,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00027200000000000005,
|
|
"loss": 7.9191,
|
|
"mean_token_accuracy": 0.0833043985068798,
|
|
"num_tokens": 1059248.0,
|
|
"step": 545
|
|
},
|
|
{
|
|
"entropy": 7.971222257614135,
|
|
"epoch": 0.0549807567351427,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0002745,
|
|
"loss": 7.8734,
|
|
"mean_token_accuracy": 0.09001793414354324,
|
|
"num_tokens": 1069307.0,
|
|
"step": 550
|
|
},
|
|
{
|
|
"entropy": 8.128306674957276,
|
|
"epoch": 0.05548058179637127,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000277,
|
|
"loss": 7.8885,
|
|
"mean_token_accuracy": 0.10013765767216683,
|
|
"num_tokens": 1079603.0,
|
|
"step": 555
|
|
},
|
|
{
|
|
"entropy": 8.082885026931763,
|
|
"epoch": 0.05598040685759984,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0002795,
|
|
"loss": 7.8572,
|
|
"mean_token_accuracy": 0.08783879578113556,
|
|
"num_tokens": 1089386.0,
|
|
"step": 560
|
|
},
|
|
{
|
|
"entropy": 8.03367247581482,
|
|
"epoch": 0.05648023191882841,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00028199999999999997,
|
|
"loss": 7.9334,
|
|
"mean_token_accuracy": 0.09579939767718315,
|
|
"num_tokens": 1099501.0,
|
|
"step": 565
|
|
},
|
|
{
|
|
"entropy": 8.026818656921387,
|
|
"epoch": 0.05698005698005698,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0002845,
|
|
"loss": 7.8401,
|
|
"mean_token_accuracy": 0.08943256586790085,
|
|
"num_tokens": 1108942.0,
|
|
"step": 570
|
|
},
|
|
{
|
|
"entropy": 8.156963968276978,
|
|
"epoch": 0.05747988204128555,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000287,
|
|
"loss": 7.9447,
|
|
"mean_token_accuracy": 0.08371670618653297,
|
|
"num_tokens": 1119484.0,
|
|
"step": 575
|
|
},
|
|
{
|
|
"entropy": 8.109134340286255,
|
|
"epoch": 0.05797970710251412,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0002895,
|
|
"loss": 7.9051,
|
|
"mean_token_accuracy": 0.08559826985001565,
|
|
"num_tokens": 1130426.0,
|
|
"step": 580
|
|
},
|
|
{
|
|
"entropy": 8.004295110702515,
|
|
"epoch": 0.05847953216374269,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000292,
|
|
"loss": 7.8708,
|
|
"mean_token_accuracy": 0.08802263662219048,
|
|
"num_tokens": 1140917.0,
|
|
"step": 585
|
|
},
|
|
{
|
|
"entropy": 8.056009531021118,
|
|
"epoch": 0.05897935722497126,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0002945,
|
|
"loss": 7.8112,
|
|
"mean_token_accuracy": 0.09180943965911866,
|
|
"num_tokens": 1149863.0,
|
|
"step": 590
|
|
},
|
|
{
|
|
"entropy": 8.01901979446411,
|
|
"epoch": 0.05947918228619983,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000297,
|
|
"loss": 7.8604,
|
|
"mean_token_accuracy": 0.08644097074866294,
|
|
"num_tokens": 1158915.0,
|
|
"step": 595
|
|
},
|
|
{
|
|
"entropy": 7.974025106430053,
|
|
"epoch": 0.0599790073474284,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0002995,
|
|
"loss": 7.849,
|
|
"mean_token_accuracy": 0.08794929981231689,
|
|
"num_tokens": 1167886.0,
|
|
"step": 600
|
|
},
|
|
{
|
|
"entropy": 8.07925305366516,
|
|
"epoch": 0.06047883240865697,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.000302,
|
|
"loss": 7.8807,
|
|
"mean_token_accuracy": 0.09158162623643876,
|
|
"num_tokens": 1177878.0,
|
|
"step": 605
|
|
},
|
|
{
|
|
"entropy": 8.07640643119812,
|
|
"epoch": 0.06097865746988554,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0003045,
|
|
"loss": 7.8965,
|
|
"mean_token_accuracy": 0.08518724367022515,
|
|
"num_tokens": 1189511.0,
|
|
"step": 610
|
|
},
|
|
{
|
|
"entropy": 8.041076612472533,
|
|
"epoch": 0.06147848253111411,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000307,
|
|
"loss": 7.8981,
|
|
"mean_token_accuracy": 0.08804430365562439,
|
|
"num_tokens": 1199350.0,
|
|
"step": 615
|
|
},
|
|
{
|
|
"entropy": 7.980624389648438,
|
|
"epoch": 0.06197830759234268,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0003095,
|
|
"loss": 7.8271,
|
|
"mean_token_accuracy": 0.09052536413073539,
|
|
"num_tokens": 1209036.0,
|
|
"step": 620
|
|
},
|
|
{
|
|
"entropy": 7.91511549949646,
|
|
"epoch": 0.06247813265357125,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000312,
|
|
"loss": 7.8584,
|
|
"mean_token_accuracy": 0.08907051086425781,
|
|
"num_tokens": 1218841.0,
|
|
"step": 625
|
|
},
|
|
{
|
|
"entropy": 8.153012752532959,
|
|
"epoch": 0.06297795771479982,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0003145,
|
|
"loss": 7.857,
|
|
"mean_token_accuracy": 0.08877145648002624,
|
|
"num_tokens": 1229700.0,
|
|
"step": 630
|
|
},
|
|
{
|
|
"entropy": 8.000677156448365,
|
|
"epoch": 0.06347778277602839,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000317,
|
|
"loss": 7.8437,
|
|
"mean_token_accuracy": 0.08636783435940742,
|
|
"num_tokens": 1239604.0,
|
|
"step": 635
|
|
},
|
|
{
|
|
"entropy": 7.819658041000366,
|
|
"epoch": 0.06397760783725696,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0003195,
|
|
"loss": 7.7281,
|
|
"mean_token_accuracy": 0.09608968570828438,
|
|
"num_tokens": 1249305.0,
|
|
"step": 640
|
|
},
|
|
{
|
|
"entropy": 8.016890144348144,
|
|
"epoch": 0.06447743289848552,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000322,
|
|
"loss": 7.8545,
|
|
"mean_token_accuracy": 0.09123507961630821,
|
|
"num_tokens": 1261289.0,
|
|
"step": 645
|
|
},
|
|
{
|
|
"entropy": 7.908722877502441,
|
|
"epoch": 0.0649772579597141,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00032450000000000003,
|
|
"loss": 7.8074,
|
|
"mean_token_accuracy": 0.09392313659191132,
|
|
"num_tokens": 1271062.0,
|
|
"step": 650
|
|
},
|
|
{
|
|
"entropy": 7.9713281154632565,
|
|
"epoch": 0.06547708302094267,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00032700000000000003,
|
|
"loss": 7.8102,
|
|
"mean_token_accuracy": 0.08593089655041694,
|
|
"num_tokens": 1280259.0,
|
|
"step": 655
|
|
},
|
|
{
|
|
"entropy": 8.054199171066283,
|
|
"epoch": 0.06597690808217124,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00032950000000000004,
|
|
"loss": 7.7935,
|
|
"mean_token_accuracy": 0.0905226230621338,
|
|
"num_tokens": 1289184.0,
|
|
"step": 660
|
|
},
|
|
{
|
|
"entropy": 7.912717294692993,
|
|
"epoch": 0.06647673314339982,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00033200000000000005,
|
|
"loss": 7.7627,
|
|
"mean_token_accuracy": 0.09990859180688857,
|
|
"num_tokens": 1297916.0,
|
|
"step": 665
|
|
},
|
|
{
|
|
"entropy": 7.934937286376953,
|
|
"epoch": 0.06697655820462838,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00033450000000000005,
|
|
"loss": 7.8034,
|
|
"mean_token_accuracy": 0.09347057268023491,
|
|
"num_tokens": 1307786.0,
|
|
"step": 670
|
|
},
|
|
{
|
|
"entropy": 7.948394060134888,
|
|
"epoch": 0.06747638326585695,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000337,
|
|
"loss": 7.7035,
|
|
"mean_token_accuracy": 0.08821736723184585,
|
|
"num_tokens": 1317528.0,
|
|
"step": 675
|
|
},
|
|
{
|
|
"entropy": 7.898578214645386,
|
|
"epoch": 0.06797620832708552,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0003395,
|
|
"loss": 7.7457,
|
|
"mean_token_accuracy": 0.09229791611433029,
|
|
"num_tokens": 1326170.0,
|
|
"step": 680
|
|
},
|
|
{
|
|
"entropy": 7.833027362823486,
|
|
"epoch": 0.0684760333883141,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000342,
|
|
"loss": 7.7515,
|
|
"mean_token_accuracy": 0.09093709476292133,
|
|
"num_tokens": 1336469.0,
|
|
"step": 685
|
|
},
|
|
{
|
|
"entropy": 7.857772493362427,
|
|
"epoch": 0.06897585844954265,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00034449999999999997,
|
|
"loss": 7.7384,
|
|
"mean_token_accuracy": 0.0885499432682991,
|
|
"num_tokens": 1347449.0,
|
|
"step": 690
|
|
},
|
|
{
|
|
"entropy": 7.819149017333984,
|
|
"epoch": 0.06947568351077123,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000347,
|
|
"loss": 7.7794,
|
|
"mean_token_accuracy": 0.0962777391076088,
|
|
"num_tokens": 1357849.0,
|
|
"step": 695
|
|
},
|
|
{
|
|
"entropy": 7.873389196395874,
|
|
"epoch": 0.0699755085719998,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0003495,
|
|
"loss": 7.7115,
|
|
"mean_token_accuracy": 0.08954642415046692,
|
|
"num_tokens": 1366784.0,
|
|
"step": 700
|
|
},
|
|
{
|
|
"entropy": 7.9029346942901615,
|
|
"epoch": 0.07047533363322837,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000352,
|
|
"loss": 7.6777,
|
|
"mean_token_accuracy": 0.09408788681030274,
|
|
"num_tokens": 1376059.0,
|
|
"step": 705
|
|
},
|
|
{
|
|
"entropy": 7.817119073867798,
|
|
"epoch": 0.07097515869445695,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0003545,
|
|
"loss": 7.6405,
|
|
"mean_token_accuracy": 0.09813722297549247,
|
|
"num_tokens": 1385505.0,
|
|
"step": 710
|
|
},
|
|
{
|
|
"entropy": 7.849679708480835,
|
|
"epoch": 0.0714749837556855,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000357,
|
|
"loss": 7.6998,
|
|
"mean_token_accuracy": 0.10136872977018356,
|
|
"num_tokens": 1395200.0,
|
|
"step": 715
|
|
},
|
|
{
|
|
"entropy": 7.746676015853882,
|
|
"epoch": 0.07197480881691408,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0003595,
|
|
"loss": 7.6351,
|
|
"mean_token_accuracy": 0.09838511943817138,
|
|
"num_tokens": 1404599.0,
|
|
"step": 720
|
|
},
|
|
{
|
|
"entropy": 7.806417465209961,
|
|
"epoch": 0.07247463387814265,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000362,
|
|
"loss": 7.7018,
|
|
"mean_token_accuracy": 0.09462484046816826,
|
|
"num_tokens": 1414761.0,
|
|
"step": 725
|
|
},
|
|
{
|
|
"entropy": 7.835126304626465,
|
|
"epoch": 0.07297445893937123,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0003645,
|
|
"loss": 7.6427,
|
|
"mean_token_accuracy": 0.09922129213809967,
|
|
"num_tokens": 1424296.0,
|
|
"step": 730
|
|
},
|
|
{
|
|
"entropy": 7.799503755569458,
|
|
"epoch": 0.07347428400059978,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000367,
|
|
"loss": 7.7093,
|
|
"mean_token_accuracy": 0.09564783871173858,
|
|
"num_tokens": 1433729.0,
|
|
"step": 735
|
|
},
|
|
{
|
|
"entropy": 7.859089279174805,
|
|
"epoch": 0.07397410906182836,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0003695,
|
|
"loss": 7.7688,
|
|
"mean_token_accuracy": 0.08819435015320778,
|
|
"num_tokens": 1444214.0,
|
|
"step": 740
|
|
},
|
|
{
|
|
"entropy": 7.835516119003296,
|
|
"epoch": 0.07447393412305693,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.000372,
|
|
"loss": 7.7759,
|
|
"mean_token_accuracy": 0.0897902250289917,
|
|
"num_tokens": 1454364.0,
|
|
"step": 745
|
|
},
|
|
{
|
|
"entropy": 7.81394476890564,
|
|
"epoch": 0.0749737591842855,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0003745,
|
|
"loss": 7.6208,
|
|
"mean_token_accuracy": 0.09887422099709511,
|
|
"num_tokens": 1465018.0,
|
|
"step": 750
|
|
},
|
|
{
|
|
"entropy": 7.76133918762207,
|
|
"epoch": 0.07547358424551406,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000377,
|
|
"loss": 7.6162,
|
|
"mean_token_accuracy": 0.09769436419010162,
|
|
"num_tokens": 1474316.0,
|
|
"step": 755
|
|
},
|
|
{
|
|
"entropy": 7.754013442993164,
|
|
"epoch": 0.07597340930674264,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0003795,
|
|
"loss": 7.6798,
|
|
"mean_token_accuracy": 0.09028005488216877,
|
|
"num_tokens": 1483867.0,
|
|
"step": 760
|
|
},
|
|
{
|
|
"entropy": 7.8395530700683596,
|
|
"epoch": 0.07647323436797121,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000382,
|
|
"loss": 7.7473,
|
|
"mean_token_accuracy": 0.09097101353108883,
|
|
"num_tokens": 1493760.0,
|
|
"step": 765
|
|
},
|
|
{
|
|
"entropy": 7.770206785202026,
|
|
"epoch": 0.07697305942919978,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0003845,
|
|
"loss": 7.6632,
|
|
"mean_token_accuracy": 0.09491882026195526,
|
|
"num_tokens": 1503984.0,
|
|
"step": 770
|
|
},
|
|
{
|
|
"entropy": 7.806950092315674,
|
|
"epoch": 0.07747288449042836,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00038700000000000003,
|
|
"loss": 7.7156,
|
|
"mean_token_accuracy": 0.09478980228304863,
|
|
"num_tokens": 1513550.0,
|
|
"step": 775
|
|
},
|
|
{
|
|
"entropy": 7.798428964614868,
|
|
"epoch": 0.07797270955165692,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00038950000000000003,
|
|
"loss": 7.6753,
|
|
"mean_token_accuracy": 0.09549887105822563,
|
|
"num_tokens": 1523543.0,
|
|
"step": 780
|
|
},
|
|
{
|
|
"entropy": 7.81029634475708,
|
|
"epoch": 0.07847253461288549,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00039200000000000004,
|
|
"loss": 7.6472,
|
|
"mean_token_accuracy": 0.08958346769213676,
|
|
"num_tokens": 1533775.0,
|
|
"step": 785
|
|
},
|
|
{
|
|
"entropy": 7.677821111679077,
|
|
"epoch": 0.07897235967411406,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00039450000000000005,
|
|
"loss": 7.645,
|
|
"mean_token_accuracy": 0.09512166753411293,
|
|
"num_tokens": 1545008.0,
|
|
"step": 790
|
|
},
|
|
{
|
|
"entropy": 7.821054697036743,
|
|
"epoch": 0.07947218473534264,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00039700000000000005,
|
|
"loss": 7.6518,
|
|
"mean_token_accuracy": 0.09396766498684883,
|
|
"num_tokens": 1554458.0,
|
|
"step": 795
|
|
},
|
|
{
|
|
"entropy": 7.712546682357788,
|
|
"epoch": 0.0799720097965712,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0003995,
|
|
"loss": 7.6531,
|
|
"mean_token_accuracy": 0.09004195109009742,
|
|
"num_tokens": 1565827.0,
|
|
"step": 800
|
|
},
|
|
{
|
|
"entropy": 7.851324605941772,
|
|
"epoch": 0.08047183485779977,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000402,
|
|
"loss": 7.7369,
|
|
"mean_token_accuracy": 0.08832133710384368,
|
|
"num_tokens": 1577477.0,
|
|
"step": 805
|
|
},
|
|
{
|
|
"entropy": 7.62222638130188,
|
|
"epoch": 0.08097165991902834,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004045,
|
|
"loss": 7.5622,
|
|
"mean_token_accuracy": 0.09800169914960861,
|
|
"num_tokens": 1586622.0,
|
|
"step": 810
|
|
},
|
|
{
|
|
"entropy": 7.73266487121582,
|
|
"epoch": 0.08147148498025691,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00040699999999999997,
|
|
"loss": 7.5753,
|
|
"mean_token_accuracy": 0.09251043051481248,
|
|
"num_tokens": 1596038.0,
|
|
"step": 815
|
|
},
|
|
{
|
|
"entropy": 7.748015069961548,
|
|
"epoch": 0.08197131004148547,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004095,
|
|
"loss": 7.6931,
|
|
"mean_token_accuracy": 0.09194686040282249,
|
|
"num_tokens": 1606419.0,
|
|
"step": 820
|
|
},
|
|
{
|
|
"entropy": 7.690671157836914,
|
|
"epoch": 0.08247113510271405,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000412,
|
|
"loss": 7.6348,
|
|
"mean_token_accuracy": 0.09269572645425797,
|
|
"num_tokens": 1617178.0,
|
|
"step": 825
|
|
},
|
|
{
|
|
"entropy": 7.766012477874756,
|
|
"epoch": 0.08297096016394262,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004145,
|
|
"loss": 7.6793,
|
|
"mean_token_accuracy": 0.09032412022352218,
|
|
"num_tokens": 1628066.0,
|
|
"step": 830
|
|
},
|
|
{
|
|
"entropy": 7.6431036472320555,
|
|
"epoch": 0.08347078522517119,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.000417,
|
|
"loss": 7.6039,
|
|
"mean_token_accuracy": 0.09320124015212058,
|
|
"num_tokens": 1637956.0,
|
|
"step": 835
|
|
},
|
|
{
|
|
"entropy": 7.643291711807251,
|
|
"epoch": 0.08397061028639977,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004195,
|
|
"loss": 7.6418,
|
|
"mean_token_accuracy": 0.09229156970977784,
|
|
"num_tokens": 1647388.0,
|
|
"step": 840
|
|
},
|
|
{
|
|
"entropy": 7.768024444580078,
|
|
"epoch": 0.08447043534762833,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000422,
|
|
"loss": 7.6579,
|
|
"mean_token_accuracy": 0.0924814723432064,
|
|
"num_tokens": 1656983.0,
|
|
"step": 845
|
|
},
|
|
{
|
|
"entropy": 7.680607414245605,
|
|
"epoch": 0.0849702604088569,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004245,
|
|
"loss": 7.6387,
|
|
"mean_token_accuracy": 0.09638504981994629,
|
|
"num_tokens": 1666956.0,
|
|
"step": 850
|
|
},
|
|
{
|
|
"entropy": 7.58338680267334,
|
|
"epoch": 0.08547008547008547,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.000427,
|
|
"loss": 7.4913,
|
|
"mean_token_accuracy": 0.10190274640917778,
|
|
"num_tokens": 1675249.0,
|
|
"step": 855
|
|
},
|
|
{
|
|
"entropy": 7.666333866119385,
|
|
"epoch": 0.08596991053131404,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004295,
|
|
"loss": 7.5701,
|
|
"mean_token_accuracy": 0.09594022110104561,
|
|
"num_tokens": 1684142.0,
|
|
"step": 860
|
|
},
|
|
{
|
|
"entropy": 7.699511909484864,
|
|
"epoch": 0.0864697355925426,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000432,
|
|
"loss": 7.6187,
|
|
"mean_token_accuracy": 0.09947884380817414,
|
|
"num_tokens": 1693512.0,
|
|
"step": 865
|
|
},
|
|
{
|
|
"entropy": 7.624828767776489,
|
|
"epoch": 0.08696956065377118,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004345,
|
|
"loss": 7.6047,
|
|
"mean_token_accuracy": 0.09352649301290512,
|
|
"num_tokens": 1703509.0,
|
|
"step": 870
|
|
},
|
|
{
|
|
"entropy": 7.652335834503174,
|
|
"epoch": 0.08746938571499975,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.000437,
|
|
"loss": 7.5447,
|
|
"mean_token_accuracy": 0.09779571294784546,
|
|
"num_tokens": 1712158.0,
|
|
"step": 875
|
|
},
|
|
{
|
|
"entropy": 7.610031938552856,
|
|
"epoch": 0.08796921077622832,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004395,
|
|
"loss": 7.5735,
|
|
"mean_token_accuracy": 0.09820363372564316,
|
|
"num_tokens": 1721797.0,
|
|
"step": 880
|
|
},
|
|
{
|
|
"entropy": 7.673763847351074,
|
|
"epoch": 0.0884690358374569,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.000442,
|
|
"loss": 7.6141,
|
|
"mean_token_accuracy": 0.08615203425288201,
|
|
"num_tokens": 1732139.0,
|
|
"step": 885
|
|
},
|
|
{
|
|
"entropy": 7.575803756713867,
|
|
"epoch": 0.08896886089868546,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004445,
|
|
"loss": 7.6571,
|
|
"mean_token_accuracy": 0.09244688376784324,
|
|
"num_tokens": 1742419.0,
|
|
"step": 890
|
|
},
|
|
{
|
|
"entropy": 7.63206787109375,
|
|
"epoch": 0.08946868595991403,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000447,
|
|
"loss": 7.6147,
|
|
"mean_token_accuracy": 0.094232327491045,
|
|
"num_tokens": 1752339.0,
|
|
"step": 895
|
|
},
|
|
{
|
|
"entropy": 7.5745398044586185,
|
|
"epoch": 0.0899685110211426,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00044950000000000003,
|
|
"loss": 7.4909,
|
|
"mean_token_accuracy": 0.10000535398721695,
|
|
"num_tokens": 1763014.0,
|
|
"step": 900
|
|
},
|
|
{
|
|
"entropy": 7.5403139114379885,
|
|
"epoch": 0.09046833608237118,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00045200000000000004,
|
|
"loss": 7.4726,
|
|
"mean_token_accuracy": 0.10507719144225121,
|
|
"num_tokens": 1772977.0,
|
|
"step": 905
|
|
},
|
|
{
|
|
"entropy": 7.720607757568359,
|
|
"epoch": 0.09096816114359974,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00045450000000000004,
|
|
"loss": 7.5623,
|
|
"mean_token_accuracy": 0.10015249475836754,
|
|
"num_tokens": 1782085.0,
|
|
"step": 910
|
|
},
|
|
{
|
|
"entropy": 7.486642456054687,
|
|
"epoch": 0.09146798620482831,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00045700000000000005,
|
|
"loss": 7.6137,
|
|
"mean_token_accuracy": 0.09703461900353431,
|
|
"num_tokens": 1791856.0,
|
|
"step": 915
|
|
},
|
|
{
|
|
"entropy": 7.590369796752929,
|
|
"epoch": 0.09196781126605688,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00045950000000000006,
|
|
"loss": 7.4354,
|
|
"mean_token_accuracy": 0.10379491597414017,
|
|
"num_tokens": 1800670.0,
|
|
"step": 920
|
|
},
|
|
{
|
|
"entropy": 7.600048780441284,
|
|
"epoch": 0.09246763632728545,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000462,
|
|
"loss": 7.6196,
|
|
"mean_token_accuracy": 0.09851503968238831,
|
|
"num_tokens": 1811138.0,
|
|
"step": 925
|
|
},
|
|
{
|
|
"entropy": 7.567831325531006,
|
|
"epoch": 0.09296746138851401,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004645,
|
|
"loss": 7.4695,
|
|
"mean_token_accuracy": 0.09572812095284462,
|
|
"num_tokens": 1819771.0,
|
|
"step": 930
|
|
},
|
|
{
|
|
"entropy": 7.476245737075805,
|
|
"epoch": 0.09346728644974259,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000467,
|
|
"loss": 7.5219,
|
|
"mean_token_accuracy": 0.09602356925606728,
|
|
"num_tokens": 1829075.0,
|
|
"step": 935
|
|
},
|
|
{
|
|
"entropy": 7.541802167892456,
|
|
"epoch": 0.09396711151097116,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004695,
|
|
"loss": 7.4949,
|
|
"mean_token_accuracy": 0.10372020304203033,
|
|
"num_tokens": 1837892.0,
|
|
"step": 940
|
|
},
|
|
{
|
|
"entropy": 7.549988889694214,
|
|
"epoch": 0.09446693657219973,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000472,
|
|
"loss": 7.5496,
|
|
"mean_token_accuracy": 0.10090011283755303,
|
|
"num_tokens": 1848359.0,
|
|
"step": 945
|
|
},
|
|
{
|
|
"entropy": 7.562478113174438,
|
|
"epoch": 0.0949667616334283,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004745,
|
|
"loss": 7.5137,
|
|
"mean_token_accuracy": 0.09830754399299621,
|
|
"num_tokens": 1857665.0,
|
|
"step": 950
|
|
},
|
|
{
|
|
"entropy": 7.611538076400757,
|
|
"epoch": 0.09546658669465687,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000477,
|
|
"loss": 7.492,
|
|
"mean_token_accuracy": 0.09751785323023796,
|
|
"num_tokens": 1867313.0,
|
|
"step": 955
|
|
},
|
|
{
|
|
"entropy": 7.502454233169556,
|
|
"epoch": 0.09596641175588544,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004795,
|
|
"loss": 7.5782,
|
|
"mean_token_accuracy": 0.09409020766615868,
|
|
"num_tokens": 1877904.0,
|
|
"step": 960
|
|
},
|
|
{
|
|
"entropy": 7.5820417404174805,
|
|
"epoch": 0.09646623681711401,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000482,
|
|
"loss": 7.5047,
|
|
"mean_token_accuracy": 0.10309838131070137,
|
|
"num_tokens": 1887173.0,
|
|
"step": 965
|
|
},
|
|
{
|
|
"entropy": 7.5440513610839846,
|
|
"epoch": 0.09696606187834259,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004845,
|
|
"loss": 7.5662,
|
|
"mean_token_accuracy": 0.09383099377155305,
|
|
"num_tokens": 1896326.0,
|
|
"step": 970
|
|
},
|
|
{
|
|
"entropy": 7.529570627212524,
|
|
"epoch": 0.09746588693957114,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000487,
|
|
"loss": 7.4731,
|
|
"mean_token_accuracy": 0.09614739716053008,
|
|
"num_tokens": 1905403.0,
|
|
"step": 975
|
|
},
|
|
{
|
|
"entropy": 7.580197811126709,
|
|
"epoch": 0.09796571200079972,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004895,
|
|
"loss": 7.536,
|
|
"mean_token_accuracy": 0.0945430114865303,
|
|
"num_tokens": 1915910.0,
|
|
"step": 980
|
|
},
|
|
{
|
|
"entropy": 7.4563874244689945,
|
|
"epoch": 0.09846553706202829,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.000492,
|
|
"loss": 7.4826,
|
|
"mean_token_accuracy": 0.10040049850940705,
|
|
"num_tokens": 1926538.0,
|
|
"step": 985
|
|
},
|
|
{
|
|
"entropy": 7.50741491317749,
|
|
"epoch": 0.09896536212325686,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004945,
|
|
"loss": 7.528,
|
|
"mean_token_accuracy": 0.09595750495791436,
|
|
"num_tokens": 1936604.0,
|
|
"step": 990
|
|
},
|
|
{
|
|
"entropy": 7.472796154022217,
|
|
"epoch": 0.09946518718448542,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000497,
|
|
"loss": 7.4013,
|
|
"mean_token_accuracy": 0.10520057901740074,
|
|
"num_tokens": 1946509.0,
|
|
"step": 995
|
|
},
|
|
{
|
|
"entropy": 7.56459412574768,
|
|
"epoch": 0.099965012245714,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004995,
|
|
"loss": 7.5791,
|
|
"mean_token_accuracy": 0.09190018028020859,
|
|
"num_tokens": 1955562.0,
|
|
"step": 1000
|
|
},
|
|
{
|
|
"entropy": 7.4920408725738525,
|
|
"epoch": 0.10046483730694257,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999999981884985,
|
|
"loss": 7.4256,
|
|
"mean_token_accuracy": 0.1027059607207775,
|
|
"num_tokens": 1964805.0,
|
|
"step": 1005
|
|
},
|
|
{
|
|
"entropy": 7.523253917694092,
|
|
"epoch": 0.10096466236817114,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999999908292739,
|
|
"loss": 7.5189,
|
|
"mean_token_accuracy": 0.09549521021544934,
|
|
"num_tokens": 1973735.0,
|
|
"step": 1010
|
|
},
|
|
{
|
|
"entropy": 7.478187179565429,
|
|
"epoch": 0.10146448742939972,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999999778091072,
|
|
"loss": 7.4184,
|
|
"mean_token_accuracy": 0.09687747582793235,
|
|
"num_tokens": 1983657.0,
|
|
"step": 1015
|
|
},
|
|
{
|
|
"entropy": 7.534705352783203,
|
|
"epoch": 0.10196431249062828,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004999999591279991,
|
|
"loss": 7.4952,
|
|
"mean_token_accuracy": 0.10017814338207245,
|
|
"num_tokens": 1994767.0,
|
|
"step": 1020
|
|
},
|
|
{
|
|
"entropy": 7.406741523742676,
|
|
"epoch": 0.10246413755185685,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00049999993478595,
|
|
"loss": 7.4923,
|
|
"mean_token_accuracy": 0.09699925854802131,
|
|
"num_tokens": 2004634.0,
|
|
"step": 1025
|
|
},
|
|
{
|
|
"entropy": 7.453082513809204,
|
|
"epoch": 0.10296396261308542,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004999999047829604,
|
|
"loss": 7.4188,
|
|
"mean_token_accuracy": 0.09885356277227401,
|
|
"num_tokens": 2014346.0,
|
|
"step": 1030
|
|
},
|
|
{
|
|
"entropy": 7.5082550048828125,
|
|
"epoch": 0.103463787674314,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000499999869119031,
|
|
"loss": 7.5012,
|
|
"mean_token_accuracy": 0.0958604633808136,
|
|
"num_tokens": 2024132.0,
|
|
"step": 1035
|
|
},
|
|
{
|
|
"entropy": 7.439859199523926,
|
|
"epoch": 0.10396361273554255,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999998277941629,
|
|
"loss": 7.4365,
|
|
"mean_token_accuracy": 0.09600495919585228,
|
|
"num_tokens": 2034230.0,
|
|
"step": 1040
|
|
},
|
|
{
|
|
"entropy": 7.54141902923584,
|
|
"epoch": 0.10446343779677113,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999997808083569,
|
|
"loss": 7.4949,
|
|
"mean_token_accuracy": 0.10028873011469841,
|
|
"num_tokens": 2043936.0,
|
|
"step": 1045
|
|
},
|
|
{
|
|
"entropy": 7.362693738937378,
|
|
"epoch": 0.1049632628579997,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999997281616144,
|
|
"loss": 7.4474,
|
|
"mean_token_accuracy": 0.0918818660080433,
|
|
"num_tokens": 2053386.0,
|
|
"step": 1050
|
|
},
|
|
{
|
|
"entropy": 7.414045619964599,
|
|
"epoch": 0.10546308791922827,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004999996698539366,
|
|
"loss": 7.3857,
|
|
"mean_token_accuracy": 0.10662863552570342,
|
|
"num_tokens": 2063604.0,
|
|
"step": 1055
|
|
},
|
|
{
|
|
"entropy": 7.388621807098389,
|
|
"epoch": 0.10596291298045685,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000499999605885325,
|
|
"loss": 7.4459,
|
|
"mean_token_accuracy": 0.09972845241427422,
|
|
"num_tokens": 2072795.0,
|
|
"step": 1060
|
|
},
|
|
{
|
|
"entropy": 7.523905897140503,
|
|
"epoch": 0.1064627380416854,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004999995362557813,
|
|
"loss": 7.4036,
|
|
"mean_token_accuracy": 0.09751716852188111,
|
|
"num_tokens": 2082113.0,
|
|
"step": 1065
|
|
},
|
|
{
|
|
"entropy": 7.350507736206055,
|
|
"epoch": 0.10696256310291398,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000499999460965307,
|
|
"loss": 7.3091,
|
|
"mean_token_accuracy": 0.10580763667821884,
|
|
"num_tokens": 2090484.0,
|
|
"step": 1070
|
|
},
|
|
{
|
|
"entropy": 7.332064962387085,
|
|
"epoch": 0.10746238816414255,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999993800139043,
|
|
"loss": 7.3631,
|
|
"mean_token_accuracy": 0.10295772925019264,
|
|
"num_tokens": 2100703.0,
|
|
"step": 1075
|
|
},
|
|
{
|
|
"entropy": 7.406967115402222,
|
|
"epoch": 0.10796221322537113,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004999992934015752,
|
|
"loss": 7.4699,
|
|
"mean_token_accuracy": 0.09553133919835091,
|
|
"num_tokens": 2110861.0,
|
|
"step": 1080
|
|
},
|
|
{
|
|
"entropy": 7.458237171173096,
|
|
"epoch": 0.10846203828659969,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004999992011283215,
|
|
"loss": 7.3992,
|
|
"mean_token_accuracy": 0.10053219199180603,
|
|
"num_tokens": 2121414.0,
|
|
"step": 1085
|
|
},
|
|
{
|
|
"entropy": 7.396937417984009,
|
|
"epoch": 0.10896186334782826,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999991031941459,
|
|
"loss": 7.3715,
|
|
"mean_token_accuracy": 0.10346362516283988,
|
|
"num_tokens": 2131201.0,
|
|
"step": 1090
|
|
},
|
|
{
|
|
"entropy": 7.399014854431153,
|
|
"epoch": 0.10946168840905683,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004999989995990509,
|
|
"loss": 7.3818,
|
|
"mean_token_accuracy": 0.09918691813945771,
|
|
"num_tokens": 2142071.0,
|
|
"step": 1095
|
|
},
|
|
{
|
|
"entropy": 7.333117485046387,
|
|
"epoch": 0.1099615134702854,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999988903430389,
|
|
"loss": 7.4204,
|
|
"mean_token_accuracy": 0.10025661289691926,
|
|
"num_tokens": 2151514.0,
|
|
"step": 1100
|
|
},
|
|
{
|
|
"entropy": 7.393906450271606,
|
|
"epoch": 0.11046133853151396,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999987754261126,
|
|
"loss": 7.4106,
|
|
"mean_token_accuracy": 0.10094344615936279,
|
|
"num_tokens": 2160828.0,
|
|
"step": 1105
|
|
},
|
|
{
|
|
"entropy": 7.414836597442627,
|
|
"epoch": 0.11096116359274254,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004999986548482751,
|
|
"loss": 7.4597,
|
|
"mean_token_accuracy": 0.1060835488140583,
|
|
"num_tokens": 2169968.0,
|
|
"step": 1110
|
|
},
|
|
{
|
|
"entropy": 7.483581686019898,
|
|
"epoch": 0.11146098865397111,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004999985286095293,
|
|
"loss": 7.3709,
|
|
"mean_token_accuracy": 0.10352779626846313,
|
|
"num_tokens": 2180434.0,
|
|
"step": 1115
|
|
},
|
|
{
|
|
"entropy": 7.310662508010864,
|
|
"epoch": 0.11196081371519968,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999983967098785,
|
|
"loss": 7.3063,
|
|
"mean_token_accuracy": 0.10279445126652717,
|
|
"num_tokens": 2190024.0,
|
|
"step": 1120
|
|
},
|
|
{
|
|
"entropy": 7.4317279815673825,
|
|
"epoch": 0.11246063877642826,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004999982591493258,
|
|
"loss": 7.3398,
|
|
"mean_token_accuracy": 0.10492815002799034,
|
|
"num_tokens": 2199897.0,
|
|
"step": 1125
|
|
},
|
|
{
|
|
"entropy": 7.252266788482666,
|
|
"epoch": 0.11296046383765682,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999981159278749,
|
|
"loss": 7.3836,
|
|
"mean_token_accuracy": 0.1030288316309452,
|
|
"num_tokens": 2209865.0,
|
|
"step": 1130
|
|
},
|
|
{
|
|
"entropy": 7.442229843139648,
|
|
"epoch": 0.11346028889888539,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004999979670455292,
|
|
"loss": 7.3598,
|
|
"mean_token_accuracy": 0.10323404967784881,
|
|
"num_tokens": 2219960.0,
|
|
"step": 1135
|
|
},
|
|
{
|
|
"entropy": 7.360328197479248,
|
|
"epoch": 0.11396011396011396,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004999978125022926,
|
|
"loss": 7.3618,
|
|
"mean_token_accuracy": 0.10576653704047204,
|
|
"num_tokens": 2230699.0,
|
|
"step": 1140
|
|
},
|
|
{
|
|
"entropy": 7.313149166107178,
|
|
"epoch": 0.11445993902134254,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000499997652298169,
|
|
"loss": 7.36,
|
|
"mean_token_accuracy": 0.10162058845162392,
|
|
"num_tokens": 2239694.0,
|
|
"step": 1145
|
|
},
|
|
{
|
|
"entropy": 7.436854648590088,
|
|
"epoch": 0.1149597640825711,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999974864331624,
|
|
"loss": 7.397,
|
|
"mean_token_accuracy": 0.10627919360995293,
|
|
"num_tokens": 2250624.0,
|
|
"step": 1150
|
|
},
|
|
{
|
|
"entropy": 7.397459411621094,
|
|
"epoch": 0.11545958914379967,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004999973149072768,
|
|
"loss": 7.3916,
|
|
"mean_token_accuracy": 0.1006945587694645,
|
|
"num_tokens": 2260759.0,
|
|
"step": 1155
|
|
},
|
|
{
|
|
"entropy": 7.36720380783081,
|
|
"epoch": 0.11595941420502824,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999971377205167,
|
|
"loss": 7.4208,
|
|
"mean_token_accuracy": 0.09522792771458626,
|
|
"num_tokens": 2271151.0,
|
|
"step": 1160
|
|
},
|
|
{
|
|
"entropy": 7.325729465484619,
|
|
"epoch": 0.11645923926625681,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999969548728864,
|
|
"loss": 7.304,
|
|
"mean_token_accuracy": 0.10690259635448456,
|
|
"num_tokens": 2280014.0,
|
|
"step": 1165
|
|
},
|
|
{
|
|
"entropy": 7.326078319549561,
|
|
"epoch": 0.11695906432748537,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999967663643908,
|
|
"loss": 7.27,
|
|
"mean_token_accuracy": 0.10552891790866852,
|
|
"num_tokens": 2288550.0,
|
|
"step": 1170
|
|
},
|
|
{
|
|
"entropy": 7.31613564491272,
|
|
"epoch": 0.11745888938871395,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004999965721950345,
|
|
"loss": 7.3537,
|
|
"mean_token_accuracy": 0.10183741301298141,
|
|
"num_tokens": 2297899.0,
|
|
"step": 1175
|
|
},
|
|
{
|
|
"entropy": 7.382048177719116,
|
|
"epoch": 0.11795871444994252,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004999963723648222,
|
|
"loss": 7.3137,
|
|
"mean_token_accuracy": 0.1040842704474926,
|
|
"num_tokens": 2308021.0,
|
|
"step": 1180
|
|
},
|
|
{
|
|
"entropy": 7.371705961227417,
|
|
"epoch": 0.1184585395111711,
|
|
"grad_norm": 1.890625,
|
|
"learning_rate": 0.000499996166873759,
|
|
"loss": 7.3646,
|
|
"mean_token_accuracy": 0.10259623602032661,
|
|
"num_tokens": 2319607.0,
|
|
"step": 1185
|
|
},
|
|
{
|
|
"entropy": 7.252321338653564,
|
|
"epoch": 0.11895836457239967,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999959557218502,
|
|
"loss": 7.3417,
|
|
"mean_token_accuracy": 0.1054498240351677,
|
|
"num_tokens": 2329293.0,
|
|
"step": 1190
|
|
},
|
|
{
|
|
"entropy": 7.487326431274414,
|
|
"epoch": 0.11945818963362823,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999957389091012,
|
|
"loss": 7.3749,
|
|
"mean_token_accuracy": 0.10124826729297638,
|
|
"num_tokens": 2339812.0,
|
|
"step": 1195
|
|
},
|
|
{
|
|
"entropy": 7.205873966217041,
|
|
"epoch": 0.1199580146948568,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004999955164355171,
|
|
"loss": 7.3442,
|
|
"mean_token_accuracy": 0.10133651569485665,
|
|
"num_tokens": 2349770.0,
|
|
"step": 1200
|
|
},
|
|
{
|
|
"entropy": 7.392103576660157,
|
|
"epoch": 0.12045783975608537,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.0004999952883011038,
|
|
"loss": 7.2228,
|
|
"mean_token_accuracy": 0.10647637471556663,
|
|
"num_tokens": 2360355.0,
|
|
"step": 1205
|
|
},
|
|
{
|
|
"entropy": 7.279506826400757,
|
|
"epoch": 0.12095766481731395,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000499995054505867,
|
|
"loss": 7.4067,
|
|
"mean_token_accuracy": 0.10051269009709358,
|
|
"num_tokens": 2369444.0,
|
|
"step": 1210
|
|
},
|
|
{
|
|
"entropy": 7.258011054992676,
|
|
"epoch": 0.1214574898785425,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004999948150498124,
|
|
"loss": 7.2901,
|
|
"mean_token_accuracy": 0.10188745036721229,
|
|
"num_tokens": 2380172.0,
|
|
"step": 1215
|
|
},
|
|
{
|
|
"entropy": 7.421121406555176,
|
|
"epoch": 0.12195731493977108,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004999945699329462,
|
|
"loss": 7.4482,
|
|
"mean_token_accuracy": 0.09546739384531974,
|
|
"num_tokens": 2391520.0,
|
|
"step": 1220
|
|
},
|
|
{
|
|
"entropy": 7.376113033294677,
|
|
"epoch": 0.12245714000099965,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999943191552745,
|
|
"loss": 7.3502,
|
|
"mean_token_accuracy": 0.09897809475660324,
|
|
"num_tokens": 2400977.0,
|
|
"step": 1225
|
|
},
|
|
{
|
|
"entropy": 7.440928745269775,
|
|
"epoch": 0.12295696506222822,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999940627168037,
|
|
"loss": 7.3375,
|
|
"mean_token_accuracy": 0.09716171771287918,
|
|
"num_tokens": 2410220.0,
|
|
"step": 1230
|
|
},
|
|
{
|
|
"entropy": 7.268915319442749,
|
|
"epoch": 0.12345679012345678,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00049999380061754,
|
|
"loss": 7.3592,
|
|
"mean_token_accuracy": 0.10169207826256751,
|
|
"num_tokens": 2420000.0,
|
|
"step": 1235
|
|
},
|
|
{
|
|
"entropy": 7.363537454605103,
|
|
"epoch": 0.12395661518468536,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004999935328574903,
|
|
"loss": 7.3006,
|
|
"mean_token_accuracy": 0.10212150141596794,
|
|
"num_tokens": 2429236.0,
|
|
"step": 1240
|
|
},
|
|
{
|
|
"entropy": 7.231467533111572,
|
|
"epoch": 0.12445644024591393,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004999932594366613,
|
|
"loss": 7.2149,
|
|
"mean_token_accuracy": 0.1043446458876133,
|
|
"num_tokens": 2438830.0,
|
|
"step": 1245
|
|
},
|
|
{
|
|
"entropy": 7.279609155654907,
|
|
"epoch": 0.1249562653071425,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999929803550597,
|
|
"loss": 7.226,
|
|
"mean_token_accuracy": 0.11196640729904175,
|
|
"num_tokens": 2448218.0,
|
|
"step": 1250
|
|
},
|
|
{
|
|
"entropy": 7.277344560623169,
|
|
"epoch": 0.12545609036837108,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999926956126927,
|
|
"loss": 7.2902,
|
|
"mean_token_accuracy": 0.10263564661145211,
|
|
"num_tokens": 2458016.0,
|
|
"step": 1255
|
|
},
|
|
{
|
|
"entropy": 7.242998886108398,
|
|
"epoch": 0.12595591542959964,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999924052095672,
|
|
"loss": 7.2023,
|
|
"mean_token_accuracy": 0.10558517500758172,
|
|
"num_tokens": 2467973.0,
|
|
"step": 1260
|
|
},
|
|
{
|
|
"entropy": 7.263315677642822,
|
|
"epoch": 0.12645574049082822,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004999921091456907,
|
|
"loss": 7.2933,
|
|
"mean_token_accuracy": 0.10375840216875076,
|
|
"num_tokens": 2477811.0,
|
|
"step": 1265
|
|
},
|
|
{
|
|
"entropy": 7.332778787612915,
|
|
"epoch": 0.12695556555205678,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004999918074210707,
|
|
"loss": 7.2845,
|
|
"mean_token_accuracy": 0.10562208667397499,
|
|
"num_tokens": 2487477.0,
|
|
"step": 1270
|
|
},
|
|
{
|
|
"entropy": 7.204593849182129,
|
|
"epoch": 0.12745539061328534,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999915000357147,
|
|
"loss": 7.15,
|
|
"mean_token_accuracy": 0.11193068847060203,
|
|
"num_tokens": 2497127.0,
|
|
"step": 1275
|
|
},
|
|
{
|
|
"entropy": 7.1659417152404785,
|
|
"epoch": 0.12795521567451393,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004999911869896305,
|
|
"loss": 7.2694,
|
|
"mean_token_accuracy": 0.10395063161849975,
|
|
"num_tokens": 2506340.0,
|
|
"step": 1280
|
|
},
|
|
{
|
|
"entropy": 7.400280618667603,
|
|
"epoch": 0.1284550407357425,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999908682828258,
|
|
"loss": 7.2879,
|
|
"mean_token_accuracy": 0.1014986701309681,
|
|
"num_tokens": 2515210.0,
|
|
"step": 1285
|
|
},
|
|
{
|
|
"entropy": 7.189401388168335,
|
|
"epoch": 0.12895486579697105,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004999905439153089,
|
|
"loss": 7.1957,
|
|
"mean_token_accuracy": 0.10809917151927947,
|
|
"num_tokens": 2524653.0,
|
|
"step": 1290
|
|
},
|
|
{
|
|
"entropy": 7.1879589557647705,
|
|
"epoch": 0.12945469085819963,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004999902138870878,
|
|
"loss": 7.2331,
|
|
"mean_token_accuracy": 0.10524520874023438,
|
|
"num_tokens": 2534243.0,
|
|
"step": 1295
|
|
},
|
|
{
|
|
"entropy": 7.331889247894287,
|
|
"epoch": 0.1299545159194282,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004999898781981707,
|
|
"loss": 7.2957,
|
|
"mean_token_accuracy": 0.10106250122189522,
|
|
"num_tokens": 2543758.0,
|
|
"step": 1300
|
|
},
|
|
{
|
|
"entropy": 7.328159761428833,
|
|
"epoch": 0.13045434098065678,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999895368485662,
|
|
"loss": 7.3204,
|
|
"mean_token_accuracy": 0.09906842038035393,
|
|
"num_tokens": 2553537.0,
|
|
"step": 1305
|
|
},
|
|
{
|
|
"entropy": 7.208748865127563,
|
|
"epoch": 0.13095416604188534,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000499989189838283,
|
|
"loss": 7.2305,
|
|
"mean_token_accuracy": 0.10748344659805298,
|
|
"num_tokens": 2562812.0,
|
|
"step": 1310
|
|
},
|
|
{
|
|
"entropy": 7.291876220703125,
|
|
"epoch": 0.1314539911031139,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004999888371673295,
|
|
"loss": 7.2098,
|
|
"mean_token_accuracy": 0.1063990943133831,
|
|
"num_tokens": 2571728.0,
|
|
"step": 1315
|
|
},
|
|
{
|
|
"entropy": 7.261162328720093,
|
|
"epoch": 0.13195381616434249,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999884788357147,
|
|
"loss": 7.3045,
|
|
"mean_token_accuracy": 0.10606675744056701,
|
|
"num_tokens": 2582309.0,
|
|
"step": 1320
|
|
},
|
|
{
|
|
"entropy": 7.262210941314697,
|
|
"epoch": 0.13245364122557104,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004999881148434478,
|
|
"loss": 7.215,
|
|
"mean_token_accuracy": 0.10733678117394448,
|
|
"num_tokens": 2591810.0,
|
|
"step": 1325
|
|
},
|
|
{
|
|
"entropy": 7.1788201332092285,
|
|
"epoch": 0.13295346628679963,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999877451905378,
|
|
"loss": 7.195,
|
|
"mean_token_accuracy": 0.1115802325308323,
|
|
"num_tokens": 2602028.0,
|
|
"step": 1330
|
|
},
|
|
{
|
|
"entropy": 7.225124454498291,
|
|
"epoch": 0.1334532913480282,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999873698769941,
|
|
"loss": 7.2008,
|
|
"mean_token_accuracy": 0.1077301986515522,
|
|
"num_tokens": 2610900.0,
|
|
"step": 1335
|
|
},
|
|
{
|
|
"entropy": 7.1687963008880615,
|
|
"epoch": 0.13395311640925675,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000499986988902826,
|
|
"loss": 7.2126,
|
|
"mean_token_accuracy": 0.10684901028871537,
|
|
"num_tokens": 2620918.0,
|
|
"step": 1340
|
|
},
|
|
{
|
|
"entropy": 7.236085271835327,
|
|
"epoch": 0.13445294147048534,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004999866022680431,
|
|
"loss": 7.2222,
|
|
"mean_token_accuracy": 0.10958969220519066,
|
|
"num_tokens": 2631383.0,
|
|
"step": 1345
|
|
},
|
|
{
|
|
"entropy": 7.206014204025268,
|
|
"epoch": 0.1349527665317139,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999862099726552,
|
|
"loss": 7.2001,
|
|
"mean_token_accuracy": 0.1074417658150196,
|
|
"num_tokens": 2640824.0,
|
|
"step": 1350
|
|
},
|
|
{
|
|
"entropy": 7.281944513320923,
|
|
"epoch": 0.13545259159294248,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999858120166721,
|
|
"loss": 7.1667,
|
|
"mean_token_accuracy": 0.10898390486836433,
|
|
"num_tokens": 2649884.0,
|
|
"step": 1355
|
|
},
|
|
{
|
|
"entropy": 7.154571914672852,
|
|
"epoch": 0.13595241665417104,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999854084001039,
|
|
"loss": 7.2461,
|
|
"mean_token_accuracy": 0.10870804488658906,
|
|
"num_tokens": 2659464.0,
|
|
"step": 1360
|
|
},
|
|
{
|
|
"entropy": 7.230677270889283,
|
|
"epoch": 0.1364522417153996,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999849991229608,
|
|
"loss": 7.2445,
|
|
"mean_token_accuracy": 0.10203292071819306,
|
|
"num_tokens": 2668271.0,
|
|
"step": 1365
|
|
},
|
|
{
|
|
"entropy": 7.276260185241699,
|
|
"epoch": 0.1369520667766282,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000499984584185253,
|
|
"loss": 7.2983,
|
|
"mean_token_accuracy": 0.1035520575940609,
|
|
"num_tokens": 2678353.0,
|
|
"step": 1370
|
|
},
|
|
{
|
|
"entropy": 7.259475326538086,
|
|
"epoch": 0.13745189183785675,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004999841635869909,
|
|
"loss": 7.2502,
|
|
"mean_token_accuracy": 0.10212932154536247,
|
|
"num_tokens": 2688082.0,
|
|
"step": 1375
|
|
},
|
|
{
|
|
"entropy": 7.254705953598022,
|
|
"epoch": 0.1379517168990853,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999837373281852,
|
|
"loss": 7.2308,
|
|
"mean_token_accuracy": 0.1053150549530983,
|
|
"num_tokens": 2697780.0,
|
|
"step": 1380
|
|
},
|
|
{
|
|
"entropy": 7.250242757797241,
|
|
"epoch": 0.1384515419603139,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999833054088465,
|
|
"loss": 7.2395,
|
|
"mean_token_accuracy": 0.1104842759668827,
|
|
"num_tokens": 2707851.0,
|
|
"step": 1385
|
|
},
|
|
{
|
|
"entropy": 7.221601819992065,
|
|
"epoch": 0.13895136702154245,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999828678289858,
|
|
"loss": 7.3105,
|
|
"mean_token_accuracy": 0.10258962363004684,
|
|
"num_tokens": 2718041.0,
|
|
"step": 1390
|
|
},
|
|
{
|
|
"entropy": 7.2794324398040775,
|
|
"epoch": 0.13945119208277104,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000499982424588614,
|
|
"loss": 7.1656,
|
|
"mean_token_accuracy": 0.11230125948786736,
|
|
"num_tokens": 2726663.0,
|
|
"step": 1395
|
|
},
|
|
{
|
|
"entropy": 7.231584119796753,
|
|
"epoch": 0.1399510171439996,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999819756877422,
|
|
"loss": 7.161,
|
|
"mean_token_accuracy": 0.10904091596603394,
|
|
"num_tokens": 2734926.0,
|
|
"step": 1400
|
|
},
|
|
{
|
|
"entropy": 7.219024133682251,
|
|
"epoch": 0.14045084220522816,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004999815211263819,
|
|
"loss": 7.2276,
|
|
"mean_token_accuracy": 0.10750553607940674,
|
|
"num_tokens": 2744984.0,
|
|
"step": 1405
|
|
},
|
|
{
|
|
"entropy": 7.246548795700074,
|
|
"epoch": 0.14095066726645675,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999810609045444,
|
|
"loss": 7.1446,
|
|
"mean_token_accuracy": 0.1064922958612442,
|
|
"num_tokens": 2754293.0,
|
|
"step": 1410
|
|
},
|
|
{
|
|
"entropy": 7.148250722885132,
|
|
"epoch": 0.1414504923276853,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004999805950222412,
|
|
"loss": 7.1998,
|
|
"mean_token_accuracy": 0.1090632751584053,
|
|
"num_tokens": 2764602.0,
|
|
"step": 1415
|
|
},
|
|
{
|
|
"entropy": 7.227945852279663,
|
|
"epoch": 0.1419503173889139,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999801234794843,
|
|
"loss": 7.2471,
|
|
"mean_token_accuracy": 0.10523776635527611,
|
|
"num_tokens": 2775171.0,
|
|
"step": 1420
|
|
},
|
|
{
|
|
"entropy": 7.173311996459961,
|
|
"epoch": 0.14245014245014245,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004999796462762853,
|
|
"loss": 7.148,
|
|
"mean_token_accuracy": 0.11108063533902168,
|
|
"num_tokens": 2784739.0,
|
|
"step": 1425
|
|
},
|
|
{
|
|
"entropy": 7.279621887207031,
|
|
"epoch": 0.142949967511371,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004999791634126562,
|
|
"loss": 7.2429,
|
|
"mean_token_accuracy": 0.10983009338378906,
|
|
"num_tokens": 2794549.0,
|
|
"step": 1430
|
|
},
|
|
{
|
|
"entropy": 7.248407173156738,
|
|
"epoch": 0.1434497925725996,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004999786748886094,
|
|
"loss": 7.2142,
|
|
"mean_token_accuracy": 0.11163983568549156,
|
|
"num_tokens": 2803235.0,
|
|
"step": 1435
|
|
},
|
|
{
|
|
"entropy": 7.1812433242797855,
|
|
"epoch": 0.14394961763382816,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004999781807041569,
|
|
"loss": 7.1404,
|
|
"mean_token_accuracy": 0.10748916789889336,
|
|
"num_tokens": 2812367.0,
|
|
"step": 1440
|
|
},
|
|
{
|
|
"entropy": 7.127222061157227,
|
|
"epoch": 0.14444944269505672,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999776808593113,
|
|
"loss": 7.1685,
|
|
"mean_token_accuracy": 0.11234024167060852,
|
|
"num_tokens": 2822173.0,
|
|
"step": 1445
|
|
},
|
|
{
|
|
"entropy": 7.284937810897827,
|
|
"epoch": 0.1449492677562853,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999771753540852,
|
|
"loss": 7.2282,
|
|
"mean_token_accuracy": 0.10868457481265067,
|
|
"num_tokens": 2831498.0,
|
|
"step": 1450
|
|
},
|
|
{
|
|
"entropy": 7.239250993728637,
|
|
"epoch": 0.14544909281751386,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999766641884912,
|
|
"loss": 7.323,
|
|
"mean_token_accuracy": 0.10500293597579002,
|
|
"num_tokens": 2840883.0,
|
|
"step": 1455
|
|
},
|
|
{
|
|
"entropy": 7.220022296905517,
|
|
"epoch": 0.14594891787874245,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999761473625422,
|
|
"loss": 7.1273,
|
|
"mean_token_accuracy": 0.10748794749379158,
|
|
"num_tokens": 2850694.0,
|
|
"step": 1460
|
|
},
|
|
{
|
|
"entropy": 7.092765665054321,
|
|
"epoch": 0.146448742939971,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999756248762513,
|
|
"loss": 7.1412,
|
|
"mean_token_accuracy": 0.10885046645998955,
|
|
"num_tokens": 2861100.0,
|
|
"step": 1465
|
|
},
|
|
{
|
|
"entropy": 7.190248632431031,
|
|
"epoch": 0.14694856800119957,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004999750967296315,
|
|
"loss": 7.0969,
|
|
"mean_token_accuracy": 0.11000208780169488,
|
|
"num_tokens": 2871054.0,
|
|
"step": 1470
|
|
},
|
|
{
|
|
"entropy": 7.077018547058105,
|
|
"epoch": 0.14744839306242816,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999745629226962,
|
|
"loss": 7.0566,
|
|
"mean_token_accuracy": 0.11119223460555076,
|
|
"num_tokens": 2880244.0,
|
|
"step": 1475
|
|
},
|
|
{
|
|
"entropy": 7.110202312469482,
|
|
"epoch": 0.14794821812365672,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004999740234554589,
|
|
"loss": 7.168,
|
|
"mean_token_accuracy": 0.10733421966433525,
|
|
"num_tokens": 2891441.0,
|
|
"step": 1480
|
|
},
|
|
{
|
|
"entropy": 7.2041778564453125,
|
|
"epoch": 0.1484480431848853,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999734783279327,
|
|
"loss": 7.1525,
|
|
"mean_token_accuracy": 0.1034772276878357,
|
|
"num_tokens": 2901784.0,
|
|
"step": 1485
|
|
},
|
|
{
|
|
"entropy": 7.202704334259034,
|
|
"epoch": 0.14894786824611386,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000499972927540132,
|
|
"loss": 7.1767,
|
|
"mean_token_accuracy": 0.1093523621559143,
|
|
"num_tokens": 2912294.0,
|
|
"step": 1490
|
|
},
|
|
{
|
|
"entropy": 7.128389835357666,
|
|
"epoch": 0.14944769330734242,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999723710920703,
|
|
"loss": 7.0937,
|
|
"mean_token_accuracy": 0.10794242620468139,
|
|
"num_tokens": 2921558.0,
|
|
"step": 1495
|
|
},
|
|
{
|
|
"entropy": 7.174574518203736,
|
|
"epoch": 0.149947518368571,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004999718089837616,
|
|
"loss": 7.1091,
|
|
"mean_token_accuracy": 0.10652265399694442,
|
|
"num_tokens": 2930997.0,
|
|
"step": 1500
|
|
},
|
|
{
|
|
"entropy": 7.183879375457764,
|
|
"epoch": 0.15044734342979957,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00049997124121522,
|
|
"loss": 7.0964,
|
|
"mean_token_accuracy": 0.1068081296980381,
|
|
"num_tokens": 2939199.0,
|
|
"step": 1505
|
|
},
|
|
{
|
|
"entropy": 7.077691125869751,
|
|
"epoch": 0.15094716849102813,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999706677864599,
|
|
"loss": 7.1756,
|
|
"mean_token_accuracy": 0.1121082328259945,
|
|
"num_tokens": 2949466.0,
|
|
"step": 1510
|
|
},
|
|
{
|
|
"entropy": 7.178814506530761,
|
|
"epoch": 0.15144699355225671,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999700886974958,
|
|
"loss": 7.095,
|
|
"mean_token_accuracy": 0.1137985847890377,
|
|
"num_tokens": 2959653.0,
|
|
"step": 1515
|
|
},
|
|
{
|
|
"entropy": 7.118761968612671,
|
|
"epoch": 0.15194681861348527,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.000499969503948342,
|
|
"loss": 7.11,
|
|
"mean_token_accuracy": 0.10633486434817314,
|
|
"num_tokens": 2970331.0,
|
|
"step": 1520
|
|
},
|
|
{
|
|
"entropy": 7.120200681686401,
|
|
"epoch": 0.15244664367471386,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999689135390134,
|
|
"loss": 7.0665,
|
|
"mean_token_accuracy": 0.11365851536393165,
|
|
"num_tokens": 2980375.0,
|
|
"step": 1525
|
|
},
|
|
{
|
|
"entropy": 7.091594552993774,
|
|
"epoch": 0.15294646873594242,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004999683174695249,
|
|
"loss": 7.1415,
|
|
"mean_token_accuracy": 0.11111581027507782,
|
|
"num_tokens": 2990562.0,
|
|
"step": 1530
|
|
},
|
|
{
|
|
"entropy": 7.181079769134522,
|
|
"epoch": 0.15344629379717098,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004999677157398914,
|
|
"loss": 7.067,
|
|
"mean_token_accuracy": 0.11519201397895813,
|
|
"num_tokens": 3000797.0,
|
|
"step": 1535
|
|
},
|
|
{
|
|
"entropy": 7.086948585510254,
|
|
"epoch": 0.15394611885839957,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004999671083501281,
|
|
"loss": 7.1387,
|
|
"mean_token_accuracy": 0.11010118499398232,
|
|
"num_tokens": 3010520.0,
|
|
"step": 1540
|
|
},
|
|
{
|
|
"entropy": 7.112814235687256,
|
|
"epoch": 0.15444594391962813,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999664953002502,
|
|
"loss": 7.0513,
|
|
"mean_token_accuracy": 0.10723346099257469,
|
|
"num_tokens": 3020249.0,
|
|
"step": 1545
|
|
},
|
|
{
|
|
"entropy": 7.125877761840821,
|
|
"epoch": 0.1549457689808567,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.000499965876590273,
|
|
"loss": 7.2067,
|
|
"mean_token_accuracy": 0.11246679276227951,
|
|
"num_tokens": 3031721.0,
|
|
"step": 1550
|
|
},
|
|
{
|
|
"entropy": 7.1510156154632565,
|
|
"epoch": 0.15544559404208527,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999652522202125,
|
|
"loss": 7.1458,
|
|
"mean_token_accuracy": 0.10964183732867241,
|
|
"num_tokens": 3041236.0,
|
|
"step": 1555
|
|
},
|
|
{
|
|
"entropy": 7.17815523147583,
|
|
"epoch": 0.15594541910331383,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004999646221900839,
|
|
"loss": 7.1011,
|
|
"mean_token_accuracy": 0.11013681590557098,
|
|
"num_tokens": 3051749.0,
|
|
"step": 1560
|
|
},
|
|
{
|
|
"entropy": 7.200712394714356,
|
|
"epoch": 0.15644524416454242,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004999639864999034,
|
|
"loss": 7.2262,
|
|
"mean_token_accuracy": 0.10536972433328629,
|
|
"num_tokens": 3061928.0,
|
|
"step": 1565
|
|
},
|
|
{
|
|
"entropy": 7.110249471664429,
|
|
"epoch": 0.15694506922577098,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.000499963345149687,
|
|
"loss": 7.0333,
|
|
"mean_token_accuracy": 0.11586274281144142,
|
|
"num_tokens": 3071598.0,
|
|
"step": 1570
|
|
},
|
|
{
|
|
"entropy": 7.061278009414673,
|
|
"epoch": 0.15744489428699954,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004999626981394506,
|
|
"loss": 7.083,
|
|
"mean_token_accuracy": 0.10698318555951118,
|
|
"num_tokens": 3081952.0,
|
|
"step": 1575
|
|
},
|
|
{
|
|
"entropy": 7.216292858123779,
|
|
"epoch": 0.15794471934822812,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999620454692106,
|
|
"loss": 7.1573,
|
|
"mean_token_accuracy": 0.10876896157860756,
|
|
"num_tokens": 3092047.0,
|
|
"step": 1580
|
|
},
|
|
{
|
|
"entropy": 7.157808446884156,
|
|
"epoch": 0.15844454440945668,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999613871389836,
|
|
"loss": 7.1185,
|
|
"mean_token_accuracy": 0.10651418566703796,
|
|
"num_tokens": 3101454.0,
|
|
"step": 1585
|
|
},
|
|
{
|
|
"entropy": 7.061008071899414,
|
|
"epoch": 0.15894436947068527,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999607231487858,
|
|
"loss": 7.0878,
|
|
"mean_token_accuracy": 0.11018021926283836,
|
|
"num_tokens": 3111447.0,
|
|
"step": 1590
|
|
},
|
|
{
|
|
"entropy": 7.0413116931915285,
|
|
"epoch": 0.15944419453191383,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.000499960053498634,
|
|
"loss": 6.9984,
|
|
"mean_token_accuracy": 0.11593033000826836,
|
|
"num_tokens": 3121085.0,
|
|
"step": 1595
|
|
},
|
|
{
|
|
"entropy": 7.061664676666259,
|
|
"epoch": 0.1599440195931424,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999593781885454,
|
|
"loss": 7.0532,
|
|
"mean_token_accuracy": 0.11079274788498879,
|
|
"num_tokens": 3131233.0,
|
|
"step": 1600
|
|
},
|
|
{
|
|
"entropy": 7.104235029220581,
|
|
"epoch": 0.16044384465437098,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999586972185366,
|
|
"loss": 7.1351,
|
|
"mean_token_accuracy": 0.10558126866817474,
|
|
"num_tokens": 3140541.0,
|
|
"step": 1605
|
|
},
|
|
{
|
|
"entropy": 7.144103956222534,
|
|
"epoch": 0.16094366971559954,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999580105886248,
|
|
"loss": 7.1168,
|
|
"mean_token_accuracy": 0.10910270363092422,
|
|
"num_tokens": 3150166.0,
|
|
"step": 1610
|
|
},
|
|
{
|
|
"entropy": 7.1036604881286625,
|
|
"epoch": 0.16144349477682812,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999573182988275,
|
|
"loss": 7.1171,
|
|
"mean_token_accuracy": 0.11519814357161522,
|
|
"num_tokens": 3160259.0,
|
|
"step": 1615
|
|
},
|
|
{
|
|
"entropy": 7.203520393371582,
|
|
"epoch": 0.16194331983805668,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004999566203491619,
|
|
"loss": 7.1016,
|
|
"mean_token_accuracy": 0.10444672331213951,
|
|
"num_tokens": 3168801.0,
|
|
"step": 1620
|
|
},
|
|
{
|
|
"entropy": 7.1718590259552,
|
|
"epoch": 0.16244314489928524,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004999559167396455,
|
|
"loss": 7.2047,
|
|
"mean_token_accuracy": 0.10611712411046029,
|
|
"num_tokens": 3181029.0,
|
|
"step": 1625
|
|
},
|
|
{
|
|
"entropy": 7.069874811172485,
|
|
"epoch": 0.16294296996051383,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004999552074702963,
|
|
"loss": 7.0282,
|
|
"mean_token_accuracy": 0.11574400290846824,
|
|
"num_tokens": 3190963.0,
|
|
"step": 1630
|
|
},
|
|
{
|
|
"entropy": 7.015948343276977,
|
|
"epoch": 0.1634427950217424,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004999544925411318,
|
|
"loss": 7.0127,
|
|
"mean_token_accuracy": 0.11391307860612869,
|
|
"num_tokens": 3200714.0,
|
|
"step": 1635
|
|
},
|
|
{
|
|
"entropy": 7.125380325317383,
|
|
"epoch": 0.16394262008297095,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004999537719521703,
|
|
"loss": 7.0543,
|
|
"mean_token_accuracy": 0.11627331748604774,
|
|
"num_tokens": 3209965.0,
|
|
"step": 1640
|
|
},
|
|
{
|
|
"entropy": 7.081728458404541,
|
|
"epoch": 0.16444244514419953,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004999530457034297,
|
|
"loss": 7.0694,
|
|
"mean_token_accuracy": 0.10980000048875808,
|
|
"num_tokens": 3218849.0,
|
|
"step": 1645
|
|
},
|
|
{
|
|
"entropy": 7.131386089324951,
|
|
"epoch": 0.1649422702054281,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004999523137949283,
|
|
"loss": 7.1137,
|
|
"mean_token_accuracy": 0.10928037911653518,
|
|
"num_tokens": 3229483.0,
|
|
"step": 1650
|
|
},
|
|
{
|
|
"entropy": 7.108076000213623,
|
|
"epoch": 0.16544209526665668,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004999515762266846,
|
|
"loss": 7.107,
|
|
"mean_token_accuracy": 0.10942549929022789,
|
|
"num_tokens": 3239818.0,
|
|
"step": 1655
|
|
},
|
|
{
|
|
"entropy": 7.173019933700561,
|
|
"epoch": 0.16594192032788524,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004999508329987173,
|
|
"loss": 7.1241,
|
|
"mean_token_accuracy": 0.10582287237048149,
|
|
"num_tokens": 3249136.0,
|
|
"step": 1660
|
|
},
|
|
{
|
|
"entropy": 7.111468029022217,
|
|
"epoch": 0.1664417453891138,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999500841110447,
|
|
"loss": 7.0154,
|
|
"mean_token_accuracy": 0.11225976943969726,
|
|
"num_tokens": 3258624.0,
|
|
"step": 1665
|
|
},
|
|
{
|
|
"entropy": 7.112836456298828,
|
|
"epoch": 0.16694157045034239,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.000499949329563686,
|
|
"loss": 7.1247,
|
|
"mean_token_accuracy": 0.10936064794659614,
|
|
"num_tokens": 3269079.0,
|
|
"step": 1670
|
|
},
|
|
{
|
|
"entropy": 7.053909111022949,
|
|
"epoch": 0.16744139551157095,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.00049994856935666,
|
|
"loss": 7.0621,
|
|
"mean_token_accuracy": 0.11304035782814026,
|
|
"num_tokens": 3280069.0,
|
|
"step": 1675
|
|
},
|
|
{
|
|
"entropy": 7.096081161499024,
|
|
"epoch": 0.16794122057279953,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.000499947803489986,
|
|
"loss": 7.0357,
|
|
"mean_token_accuracy": 0.11458788961172103,
|
|
"num_tokens": 3289520.0,
|
|
"step": 1680
|
|
},
|
|
{
|
|
"entropy": 7.1208868503570555,
|
|
"epoch": 0.1684410456340281,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004999470319636829,
|
|
"loss": 7.0512,
|
|
"mean_token_accuracy": 0.11174150407314301,
|
|
"num_tokens": 3299162.0,
|
|
"step": 1685
|
|
},
|
|
{
|
|
"entropy": 6.976963329315185,
|
|
"epoch": 0.16894087069525665,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004999462547777705,
|
|
"loss": 7.0277,
|
|
"mean_token_accuracy": 0.11063397377729416,
|
|
"num_tokens": 3308184.0,
|
|
"step": 1690
|
|
},
|
|
{
|
|
"entropy": 7.206235885620117,
|
|
"epoch": 0.16944069575648524,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999454719322682,
|
|
"loss": 7.0654,
|
|
"mean_token_accuracy": 0.11082289442420006,
|
|
"num_tokens": 3317647.0,
|
|
"step": 1695
|
|
},
|
|
{
|
|
"entropy": 7.0437695503234865,
|
|
"epoch": 0.1699405208177138,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004999446834271958,
|
|
"loss": 7.1133,
|
|
"mean_token_accuracy": 0.10917564556002617,
|
|
"num_tokens": 3329437.0,
|
|
"step": 1700
|
|
},
|
|
{
|
|
"entropy": 7.136263847351074,
|
|
"epoch": 0.17044034587894236,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004999438892625728,
|
|
"loss": 7.056,
|
|
"mean_token_accuracy": 0.11442272663116455,
|
|
"num_tokens": 3340011.0,
|
|
"step": 1705
|
|
},
|
|
{
|
|
"entropy": 7.04804253578186,
|
|
"epoch": 0.17094017094017094,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999430894384198,
|
|
"loss": 7.0522,
|
|
"mean_token_accuracy": 0.11719416975975036,
|
|
"num_tokens": 3348979.0,
|
|
"step": 1710
|
|
},
|
|
{
|
|
"entropy": 7.136094808578491,
|
|
"epoch": 0.1714399960013995,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999422839547564,
|
|
"loss": 7.1209,
|
|
"mean_token_accuracy": 0.10911227688193322,
|
|
"num_tokens": 3359055.0,
|
|
"step": 1715
|
|
},
|
|
{
|
|
"entropy": 7.072116565704346,
|
|
"epoch": 0.1719398210626281,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999414728116029,
|
|
"loss": 7.0214,
|
|
"mean_token_accuracy": 0.1116297036409378,
|
|
"num_tokens": 3368206.0,
|
|
"step": 1720
|
|
},
|
|
{
|
|
"entropy": 7.029803943634033,
|
|
"epoch": 0.17243964612385665,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999406560089798,
|
|
"loss": 7.0601,
|
|
"mean_token_accuracy": 0.11080883666872979,
|
|
"num_tokens": 3378522.0,
|
|
"step": 1725
|
|
},
|
|
{
|
|
"entropy": 7.112205123901367,
|
|
"epoch": 0.1729394711850852,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004999398335469078,
|
|
"loss": 7.0555,
|
|
"mean_token_accuracy": 0.11062405034899711,
|
|
"num_tokens": 3389052.0,
|
|
"step": 1730
|
|
},
|
|
{
|
|
"entropy": 6.981901693344116,
|
|
"epoch": 0.1734392962463138,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999390054254074,
|
|
"loss": 6.9422,
|
|
"mean_token_accuracy": 0.12012189701199531,
|
|
"num_tokens": 3398269.0,
|
|
"step": 1735
|
|
},
|
|
{
|
|
"entropy": 7.079383420944214,
|
|
"epoch": 0.17393912130754235,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999381716444996,
|
|
"loss": 7.009,
|
|
"mean_token_accuracy": 0.11454930454492569,
|
|
"num_tokens": 3408063.0,
|
|
"step": 1740
|
|
},
|
|
{
|
|
"entropy": 7.0896364688873295,
|
|
"epoch": 0.17443894636877094,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004999373322042052,
|
|
"loss": 7.0899,
|
|
"mean_token_accuracy": 0.11016308888792992,
|
|
"num_tokens": 3418903.0,
|
|
"step": 1745
|
|
},
|
|
{
|
|
"entropy": 7.017670631408691,
|
|
"epoch": 0.1749387714299995,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999364871045455,
|
|
"loss": 6.989,
|
|
"mean_token_accuracy": 0.11600941643118859,
|
|
"num_tokens": 3428831.0,
|
|
"step": 1750
|
|
},
|
|
{
|
|
"entropy": 6.994602680206299,
|
|
"epoch": 0.17543859649122806,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004999356363455415,
|
|
"loss": 7.0469,
|
|
"mean_token_accuracy": 0.11205000951886177,
|
|
"num_tokens": 3438314.0,
|
|
"step": 1755
|
|
},
|
|
{
|
|
"entropy": 7.113824510574341,
|
|
"epoch": 0.17593842155245665,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.000499934779927215,
|
|
"loss": 7.0623,
|
|
"mean_token_accuracy": 0.10831346586346627,
|
|
"num_tokens": 3449248.0,
|
|
"step": 1760
|
|
},
|
|
{
|
|
"entropy": 7.026305103302002,
|
|
"epoch": 0.1764382466136852,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999339178495872,
|
|
"loss": 7.0311,
|
|
"mean_token_accuracy": 0.10976018756628036,
|
|
"num_tokens": 3460119.0,
|
|
"step": 1765
|
|
},
|
|
{
|
|
"entropy": 7.039245700836181,
|
|
"epoch": 0.1769380716749138,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999330501126798,
|
|
"loss": 6.9514,
|
|
"mean_token_accuracy": 0.11899356544017792,
|
|
"num_tokens": 3469610.0,
|
|
"step": 1770
|
|
},
|
|
{
|
|
"entropy": 6.961409282684326,
|
|
"epoch": 0.17743789673614235,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004999321767165148,
|
|
"loss": 6.9903,
|
|
"mean_token_accuracy": 0.1108189269900322,
|
|
"num_tokens": 3480219.0,
|
|
"step": 1775
|
|
},
|
|
{
|
|
"entropy": 7.098644351959228,
|
|
"epoch": 0.1779377217973709,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004999312976611142,
|
|
"loss": 6.9401,
|
|
"mean_token_accuracy": 0.11498842909932136,
|
|
"num_tokens": 3489445.0,
|
|
"step": 1780
|
|
},
|
|
{
|
|
"entropy": 7.004860305786133,
|
|
"epoch": 0.1784375468585995,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004999304129465,
|
|
"loss": 6.9697,
|
|
"mean_token_accuracy": 0.11644153371453285,
|
|
"num_tokens": 3499164.0,
|
|
"step": 1785
|
|
},
|
|
{
|
|
"entropy": 7.071631383895874,
|
|
"epoch": 0.17893737191982806,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004999295225726945,
|
|
"loss": 7.0802,
|
|
"mean_token_accuracy": 0.10255986601114273,
|
|
"num_tokens": 3510242.0,
|
|
"step": 1790
|
|
},
|
|
{
|
|
"entropy": 7.021933746337891,
|
|
"epoch": 0.17943719698105662,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00049992862653972,
|
|
"loss": 6.9818,
|
|
"mean_token_accuracy": 0.10971452966332436,
|
|
"num_tokens": 3519481.0,
|
|
"step": 1795
|
|
},
|
|
{
|
|
"entropy": 7.029817724227906,
|
|
"epoch": 0.1799370220422852,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004999277248475992,
|
|
"loss": 7.0064,
|
|
"mean_token_accuracy": 0.11529789119958878,
|
|
"num_tokens": 3529706.0,
|
|
"step": 1800
|
|
},
|
|
{
|
|
"entropy": 6.9250016689300535,
|
|
"epoch": 0.18043684710351376,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999268174963547,
|
|
"loss": 6.974,
|
|
"mean_token_accuracy": 0.11133951023221016,
|
|
"num_tokens": 3539239.0,
|
|
"step": 1805
|
|
},
|
|
{
|
|
"entropy": 7.046410942077637,
|
|
"epoch": 0.18093667216474235,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999259044860093,
|
|
"loss": 6.9372,
|
|
"mean_token_accuracy": 0.11808101162314415,
|
|
"num_tokens": 3548177.0,
|
|
"step": 1810
|
|
},
|
|
{
|
|
"entropy": 7.036075687408447,
|
|
"epoch": 0.1814364972259709,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004999249858165861,
|
|
"loss": 7.0122,
|
|
"mean_token_accuracy": 0.11086658462882042,
|
|
"num_tokens": 3557957.0,
|
|
"step": 1815
|
|
},
|
|
{
|
|
"entropy": 7.026245260238648,
|
|
"epoch": 0.18193632228719947,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004999240614881082,
|
|
"loss": 7.0253,
|
|
"mean_token_accuracy": 0.11065947040915489,
|
|
"num_tokens": 3567701.0,
|
|
"step": 1820
|
|
},
|
|
{
|
|
"entropy": 7.038810110092163,
|
|
"epoch": 0.18243614734842806,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999231315005987,
|
|
"loss": 6.9766,
|
|
"mean_token_accuracy": 0.11399839967489242,
|
|
"num_tokens": 3575830.0,
|
|
"step": 1825
|
|
},
|
|
{
|
|
"entropy": 7.004911994934082,
|
|
"epoch": 0.18293597240965662,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999221958540811,
|
|
"loss": 6.9551,
|
|
"mean_token_accuracy": 0.12019872739911079,
|
|
"num_tokens": 3585453.0,
|
|
"step": 1830
|
|
},
|
|
{
|
|
"entropy": 6.924448537826538,
|
|
"epoch": 0.1834357974708852,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004999212545485789,
|
|
"loss": 6.9666,
|
|
"mean_token_accuracy": 0.11770169287919999,
|
|
"num_tokens": 3595340.0,
|
|
"step": 1835
|
|
},
|
|
{
|
|
"entropy": 7.108413887023926,
|
|
"epoch": 0.18393562253211376,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004999203075841159,
|
|
"loss": 6.9864,
|
|
"mean_token_accuracy": 0.1140538938343525,
|
|
"num_tokens": 3605083.0,
|
|
"step": 1840
|
|
},
|
|
{
|
|
"entropy": 7.03106656074524,
|
|
"epoch": 0.18443544759334232,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999193549607157,
|
|
"loss": 6.9503,
|
|
"mean_token_accuracy": 0.1139814093708992,
|
|
"num_tokens": 3614852.0,
|
|
"step": 1845
|
|
},
|
|
{
|
|
"entropy": 7.015335369110107,
|
|
"epoch": 0.1849352726545709,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999183966784026,
|
|
"loss": 6.9628,
|
|
"mean_token_accuracy": 0.11288752257823945,
|
|
"num_tokens": 3624267.0,
|
|
"step": 1850
|
|
},
|
|
{
|
|
"entropy": 6.954336786270142,
|
|
"epoch": 0.18543509771579947,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004999174327372004,
|
|
"loss": 6.8825,
|
|
"mean_token_accuracy": 0.1168724238872528,
|
|
"num_tokens": 3633826.0,
|
|
"step": 1855
|
|
},
|
|
{
|
|
"entropy": 7.025014400482178,
|
|
"epoch": 0.18593492277702803,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004999164631371335,
|
|
"loss": 7.0058,
|
|
"mean_token_accuracy": 0.10895812138915062,
|
|
"num_tokens": 3643236.0,
|
|
"step": 1860
|
|
},
|
|
{
|
|
"entropy": 6.908126974105835,
|
|
"epoch": 0.18643474783825661,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999154878782262,
|
|
"loss": 6.879,
|
|
"mean_token_accuracy": 0.11762138828635216,
|
|
"num_tokens": 3652859.0,
|
|
"step": 1865
|
|
},
|
|
{
|
|
"entropy": 7.008557558059692,
|
|
"epoch": 0.18693457289948517,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.000499914506960503,
|
|
"loss": 7.0378,
|
|
"mean_token_accuracy": 0.10980783402919769,
|
|
"num_tokens": 3663145.0,
|
|
"step": 1870
|
|
},
|
|
{
|
|
"entropy": 7.017056131362915,
|
|
"epoch": 0.18743439796071376,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004999135203839889,
|
|
"loss": 6.9746,
|
|
"mean_token_accuracy": 0.1128289632499218,
|
|
"num_tokens": 3673492.0,
|
|
"step": 1875
|
|
},
|
|
{
|
|
"entropy": 6.972816038131714,
|
|
"epoch": 0.18793422302194232,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999125281487084,
|
|
"loss": 6.9977,
|
|
"mean_token_accuracy": 0.11690860837697983,
|
|
"num_tokens": 3683582.0,
|
|
"step": 1880
|
|
},
|
|
{
|
|
"entropy": 7.017599773406983,
|
|
"epoch": 0.18843404808317088,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999115302546866,
|
|
"loss": 6.9272,
|
|
"mean_token_accuracy": 0.11678347289562226,
|
|
"num_tokens": 3693075.0,
|
|
"step": 1885
|
|
},
|
|
{
|
|
"entropy": 6.947669601440429,
|
|
"epoch": 0.18893387314439947,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999105267019486,
|
|
"loss": 6.9816,
|
|
"mean_token_accuracy": 0.11278985366225243,
|
|
"num_tokens": 3702290.0,
|
|
"step": 1890
|
|
},
|
|
{
|
|
"entropy": 7.008899068832397,
|
|
"epoch": 0.18943369820562803,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004999095174905195,
|
|
"loss": 6.9368,
|
|
"mean_token_accuracy": 0.11327538117766381,
|
|
"num_tokens": 3711811.0,
|
|
"step": 1895
|
|
},
|
|
{
|
|
"entropy": 6.961658048629761,
|
|
"epoch": 0.1899335232668566,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004999085026204249,
|
|
"loss": 6.925,
|
|
"mean_token_accuracy": 0.11348919793963433,
|
|
"num_tokens": 3720863.0,
|
|
"step": 1900
|
|
},
|
|
{
|
|
"entropy": 7.038826322555542,
|
|
"epoch": 0.19043334832808517,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004999074820916903,
|
|
"loss": 7.1659,
|
|
"mean_token_accuracy": 0.10545966401696205,
|
|
"num_tokens": 3731797.0,
|
|
"step": 1905
|
|
},
|
|
{
|
|
"entropy": 7.0656005859375,
|
|
"epoch": 0.19093317338931373,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999064559043412,
|
|
"loss": 6.7917,
|
|
"mean_token_accuracy": 0.12273367866873741,
|
|
"num_tokens": 3741083.0,
|
|
"step": 1910
|
|
},
|
|
{
|
|
"entropy": 6.850661325454712,
|
|
"epoch": 0.19143299845054232,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004999054240584037,
|
|
"loss": 6.9217,
|
|
"mean_token_accuracy": 0.116951634734869,
|
|
"num_tokens": 3750438.0,
|
|
"step": 1915
|
|
},
|
|
{
|
|
"entropy": 7.075789117813111,
|
|
"epoch": 0.19193282351177088,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004999043865539035,
|
|
"loss": 6.9422,
|
|
"mean_token_accuracy": 0.11572268456220627,
|
|
"num_tokens": 3759763.0,
|
|
"step": 1920
|
|
},
|
|
{
|
|
"entropy": 6.927079534530639,
|
|
"epoch": 0.19243264857299944,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004999033433908667,
|
|
"loss": 6.8813,
|
|
"mean_token_accuracy": 0.12867123857140542,
|
|
"num_tokens": 3769523.0,
|
|
"step": 1925
|
|
},
|
|
{
|
|
"entropy": 6.874381685256958,
|
|
"epoch": 0.19293247363422802,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004999022945693198,
|
|
"loss": 6.9136,
|
|
"mean_token_accuracy": 0.12044937536120415,
|
|
"num_tokens": 3779290.0,
|
|
"step": 1930
|
|
},
|
|
{
|
|
"entropy": 7.032785797119141,
|
|
"epoch": 0.19343229869545658,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000499901240089289,
|
|
"loss": 6.9319,
|
|
"mean_token_accuracy": 0.11947752237319946,
|
|
"num_tokens": 3788582.0,
|
|
"step": 1935
|
|
},
|
|
{
|
|
"entropy": 6.953524160385132,
|
|
"epoch": 0.19393212375668517,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004999001799508009,
|
|
"loss": 6.9225,
|
|
"mean_token_accuracy": 0.11011315360665322,
|
|
"num_tokens": 3798281.0,
|
|
"step": 1940
|
|
},
|
|
{
|
|
"entropy": 6.91785306930542,
|
|
"epoch": 0.19443194881791373,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004998991141538821,
|
|
"loss": 6.9105,
|
|
"mean_token_accuracy": 0.11099191904067993,
|
|
"num_tokens": 3807775.0,
|
|
"step": 1945
|
|
},
|
|
{
|
|
"entropy": 7.051416206359863,
|
|
"epoch": 0.1949317738791423,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004998980426985596,
|
|
"loss": 7.0716,
|
|
"mean_token_accuracy": 0.11268870756030083,
|
|
"num_tokens": 3818852.0,
|
|
"step": 1950
|
|
},
|
|
{
|
|
"entropy": 7.099276971817017,
|
|
"epoch": 0.19543159894037088,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00049989696558486,
|
|
"loss": 6.965,
|
|
"mean_token_accuracy": 0.10571991056203842,
|
|
"num_tokens": 3826924.0,
|
|
"step": 1955
|
|
},
|
|
{
|
|
"entropy": 6.861832475662231,
|
|
"epoch": 0.19593142400159944,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004998958828128108,
|
|
"loss": 6.8775,
|
|
"mean_token_accuracy": 0.12424767538905143,
|
|
"num_tokens": 3835098.0,
|
|
"step": 1960
|
|
},
|
|
{
|
|
"entropy": 7.058041620254516,
|
|
"epoch": 0.19643124906282802,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004998947943824389,
|
|
"loss": 7.0427,
|
|
"mean_token_accuracy": 0.11062902957201004,
|
|
"num_tokens": 3845914.0,
|
|
"step": 1965
|
|
},
|
|
{
|
|
"entropy": 6.971142864227295,
|
|
"epoch": 0.19693107412405658,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004998937002937719,
|
|
"loss": 6.9044,
|
|
"mean_token_accuracy": 0.11801907047629356,
|
|
"num_tokens": 3855791.0,
|
|
"step": 1970
|
|
},
|
|
{
|
|
"entropy": 6.942867279052734,
|
|
"epoch": 0.19743089918528514,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004998926005468373,
|
|
"loss": 6.8828,
|
|
"mean_token_accuracy": 0.12405865415930747,
|
|
"num_tokens": 3865970.0,
|
|
"step": 1975
|
|
},
|
|
{
|
|
"entropy": 6.934929323196411,
|
|
"epoch": 0.19793072424651373,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004998914951416627,
|
|
"loss": 6.9457,
|
|
"mean_token_accuracy": 0.11826047450304031,
|
|
"num_tokens": 3875139.0,
|
|
"step": 1980
|
|
},
|
|
{
|
|
"entropy": 6.993371534347534,
|
|
"epoch": 0.1984305493077423,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000499890384078276,
|
|
"loss": 6.9586,
|
|
"mean_token_accuracy": 0.1164481833577156,
|
|
"num_tokens": 3884075.0,
|
|
"step": 1985
|
|
},
|
|
{
|
|
"entropy": 7.047069311141968,
|
|
"epoch": 0.19893037436897085,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004998892673567051,
|
|
"loss": 6.8696,
|
|
"mean_token_accuracy": 0.11561509147286415,
|
|
"num_tokens": 3894273.0,
|
|
"step": 1990
|
|
},
|
|
{
|
|
"entropy": 6.881417846679687,
|
|
"epoch": 0.19943019943019943,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004998881449769781,
|
|
"loss": 6.919,
|
|
"mean_token_accuracy": 0.11565662696957588,
|
|
"num_tokens": 3904940.0,
|
|
"step": 1995
|
|
},
|
|
{
|
|
"entropy": 7.18874077796936,
|
|
"epoch": 0.199930024491428,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004998870169391232,
|
|
"loss": 7.0733,
|
|
"mean_token_accuracy": 0.1034354567527771,
|
|
"num_tokens": 3916273.0,
|
|
"step": 2000
|
|
},
|
|
{
|
|
"entropy": 6.8554352760314945,
|
|
"epoch": 0.20042984955265658,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.000499885883243169,
|
|
"loss": 6.8612,
|
|
"mean_token_accuracy": 0.11686792820692063,
|
|
"num_tokens": 3926495.0,
|
|
"step": 2005
|
|
},
|
|
{
|
|
"entropy": 6.894193315505982,
|
|
"epoch": 0.20092967461388514,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004998847438891437,
|
|
"loss": 6.9356,
|
|
"mean_token_accuracy": 0.11599919721484184,
|
|
"num_tokens": 3936286.0,
|
|
"step": 2010
|
|
},
|
|
{
|
|
"entropy": 7.00080976486206,
|
|
"epoch": 0.2014294996751137,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004998835988770761,
|
|
"loss": 6.9699,
|
|
"mean_token_accuracy": 0.10990998297929763,
|
|
"num_tokens": 3946924.0,
|
|
"step": 2015
|
|
},
|
|
{
|
|
"entropy": 7.00573239326477,
|
|
"epoch": 0.20192932473634229,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000499882448206995,
|
|
"loss": 6.8975,
|
|
"mean_token_accuracy": 0.11481108143925667,
|
|
"num_tokens": 3956815.0,
|
|
"step": 2020
|
|
},
|
|
{
|
|
"entropy": 6.867879438400268,
|
|
"epoch": 0.20242914979757085,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004998812918789293,
|
|
"loss": 6.8577,
|
|
"mean_token_accuracy": 0.1193717747926712,
|
|
"num_tokens": 3967034.0,
|
|
"step": 2025
|
|
},
|
|
{
|
|
"entropy": 6.9768967628479,
|
|
"epoch": 0.20292897485879943,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004998801298929084,
|
|
"loss": 6.9322,
|
|
"mean_token_accuracy": 0.11179861947894096,
|
|
"num_tokens": 3976800.0,
|
|
"step": 2030
|
|
},
|
|
{
|
|
"entropy": 7.073401927947998,
|
|
"epoch": 0.203428799920028,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004998789622489611,
|
|
"loss": 6.9943,
|
|
"mean_token_accuracy": 0.11428194269537925,
|
|
"num_tokens": 3987279.0,
|
|
"step": 2035
|
|
},
|
|
{
|
|
"entropy": 6.901258516311645,
|
|
"epoch": 0.20392862498125655,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004998777889471171,
|
|
"loss": 6.8761,
|
|
"mean_token_accuracy": 0.11997782960534095,
|
|
"num_tokens": 3998414.0,
|
|
"step": 2040
|
|
},
|
|
{
|
|
"entropy": 6.8927994728088375,
|
|
"epoch": 0.20442845004248514,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004998766099874056,
|
|
"loss": 6.8762,
|
|
"mean_token_accuracy": 0.12286129742860794,
|
|
"num_tokens": 4007994.0,
|
|
"step": 2045
|
|
},
|
|
{
|
|
"entropy": 6.911945915222168,
|
|
"epoch": 0.2049282751037137,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004998754253698566,
|
|
"loss": 6.8832,
|
|
"mean_token_accuracy": 0.11526042371988296,
|
|
"num_tokens": 4018285.0,
|
|
"step": 2050
|
|
},
|
|
{
|
|
"entropy": 7.050160837173462,
|
|
"epoch": 0.20542810016494226,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004998742350944998,
|
|
"loss": 6.9687,
|
|
"mean_token_accuracy": 0.10755550190806389,
|
|
"num_tokens": 4028689.0,
|
|
"step": 2055
|
|
},
|
|
{
|
|
"entropy": 6.887995481491089,
|
|
"epoch": 0.20592792522617084,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004998730391613651,
|
|
"loss": 6.8843,
|
|
"mean_token_accuracy": 0.12264417707920075,
|
|
"num_tokens": 4038944.0,
|
|
"step": 2060
|
|
},
|
|
{
|
|
"entropy": 7.012986135482788,
|
|
"epoch": 0.2064277502873994,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004998718375704825,
|
|
"loss": 6.9971,
|
|
"mean_token_accuracy": 0.11188706979155541,
|
|
"num_tokens": 4049048.0,
|
|
"step": 2065
|
|
},
|
|
{
|
|
"entropy": 6.976608419418335,
|
|
"epoch": 0.206927575348628,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004998706303218825,
|
|
"loss": 6.828,
|
|
"mean_token_accuracy": 0.12201604545116425,
|
|
"num_tokens": 4058710.0,
|
|
"step": 2070
|
|
},
|
|
{
|
|
"entropy": 6.8684539794921875,
|
|
"epoch": 0.20742740040985655,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004998694174155952,
|
|
"loss": 6.8206,
|
|
"mean_token_accuracy": 0.11384685859084129,
|
|
"num_tokens": 4069517.0,
|
|
"step": 2075
|
|
},
|
|
{
|
|
"entropy": 6.8656822681427006,
|
|
"epoch": 0.2079272254710851,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004998681988516512,
|
|
"loss": 6.9341,
|
|
"mean_token_accuracy": 0.11590560525655746,
|
|
"num_tokens": 4080730.0,
|
|
"step": 2080
|
|
},
|
|
{
|
|
"entropy": 6.992557621002197,
|
|
"epoch": 0.2084270505323137,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004998669746300811,
|
|
"loss": 6.8194,
|
|
"mean_token_accuracy": 0.11853130012750626,
|
|
"num_tokens": 4090505.0,
|
|
"step": 2085
|
|
},
|
|
{
|
|
"entropy": 6.830566310882569,
|
|
"epoch": 0.20892687559354226,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004998657447509159,
|
|
"loss": 6.8106,
|
|
"mean_token_accuracy": 0.12010636702179908,
|
|
"num_tokens": 4099963.0,
|
|
"step": 2090
|
|
},
|
|
{
|
|
"entropy": 6.972150182723999,
|
|
"epoch": 0.20942670065477084,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004998645092141864,
|
|
"loss": 6.9136,
|
|
"mean_token_accuracy": 0.11967169344425202,
|
|
"num_tokens": 4109340.0,
|
|
"step": 2095
|
|
},
|
|
{
|
|
"entropy": 7.104512548446655,
|
|
"epoch": 0.2099265257159994,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004998632680199238,
|
|
"loss": 6.9387,
|
|
"mean_token_accuracy": 0.11301500350236893,
|
|
"num_tokens": 4118476.0,
|
|
"step": 2100
|
|
},
|
|
{
|
|
"entropy": 6.826396417617798,
|
|
"epoch": 0.21042635077722796,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004998620211681591,
|
|
"loss": 6.8767,
|
|
"mean_token_accuracy": 0.1197544053196907,
|
|
"num_tokens": 4127922.0,
|
|
"step": 2105
|
|
},
|
|
{
|
|
"entropy": 6.892666673660278,
|
|
"epoch": 0.21092617583845655,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004998607686589239,
|
|
"loss": 6.8679,
|
|
"mean_token_accuracy": 0.12079423889517785,
|
|
"num_tokens": 4137202.0,
|
|
"step": 2110
|
|
},
|
|
{
|
|
"entropy": 6.8921217918396,
|
|
"epoch": 0.2114260008996851,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004998595104922496,
|
|
"loss": 6.8529,
|
|
"mean_token_accuracy": 0.11905877813696861,
|
|
"num_tokens": 4146789.0,
|
|
"step": 2115
|
|
},
|
|
{
|
|
"entropy": 6.8600248336792,
|
|
"epoch": 0.2119258259609137,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004998582466681678,
|
|
"loss": 6.9388,
|
|
"mean_token_accuracy": 0.11638726368546486,
|
|
"num_tokens": 4157628.0,
|
|
"step": 2120
|
|
},
|
|
{
|
|
"entropy": 7.016875600814819,
|
|
"epoch": 0.21242565102214225,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004998569771867105,
|
|
"loss": 6.9026,
|
|
"mean_token_accuracy": 0.1167732298374176,
|
|
"num_tokens": 4168522.0,
|
|
"step": 2125
|
|
},
|
|
{
|
|
"entropy": 6.951946640014649,
|
|
"epoch": 0.2129254760833708,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004998557020479095,
|
|
"loss": 6.9472,
|
|
"mean_token_accuracy": 0.11931234747171401,
|
|
"num_tokens": 4178590.0,
|
|
"step": 2130
|
|
},
|
|
{
|
|
"entropy": 6.875528860092163,
|
|
"epoch": 0.2134253011445994,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004998544212517968,
|
|
"loss": 6.7534,
|
|
"mean_token_accuracy": 0.12599712759256362,
|
|
"num_tokens": 4188004.0,
|
|
"step": 2135
|
|
},
|
|
{
|
|
"entropy": 6.89941816329956,
|
|
"epoch": 0.21392512620582796,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004998531347984047,
|
|
"loss": 6.8609,
|
|
"mean_token_accuracy": 0.1177570328116417,
|
|
"num_tokens": 4197481.0,
|
|
"step": 2140
|
|
},
|
|
{
|
|
"entropy": 6.969382429122925,
|
|
"epoch": 0.21442495126705652,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004998518426877656,
|
|
"loss": 6.9259,
|
|
"mean_token_accuracy": 0.11888409554958343,
|
|
"num_tokens": 4207187.0,
|
|
"step": 2145
|
|
},
|
|
{
|
|
"entropy": 6.892043972015381,
|
|
"epoch": 0.2149247763282851,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004998505449199122,
|
|
"loss": 6.8765,
|
|
"mean_token_accuracy": 0.12126196175813675,
|
|
"num_tokens": 4216485.0,
|
|
"step": 2150
|
|
},
|
|
{
|
|
"entropy": 6.897071361541748,
|
|
"epoch": 0.21542460138951366,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004998492414948768,
|
|
"loss": 6.9547,
|
|
"mean_token_accuracy": 0.11528969705104827,
|
|
"num_tokens": 4228268.0,
|
|
"step": 2155
|
|
},
|
|
{
|
|
"entropy": 6.907302045822144,
|
|
"epoch": 0.21592442645074225,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004998479324126924,
|
|
"loss": 6.7986,
|
|
"mean_token_accuracy": 0.12409409955143928,
|
|
"num_tokens": 4237755.0,
|
|
"step": 2160
|
|
},
|
|
{
|
|
"entropy": 6.982002592086792,
|
|
"epoch": 0.2164242515119708,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004998466176733918,
|
|
"loss": 6.932,
|
|
"mean_token_accuracy": 0.11655529513955117,
|
|
"num_tokens": 4247571.0,
|
|
"step": 2165
|
|
},
|
|
{
|
|
"entropy": 6.855451440811157,
|
|
"epoch": 0.21692407657319937,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004998452972770082,
|
|
"loss": 6.8754,
|
|
"mean_token_accuracy": 0.11860855519771576,
|
|
"num_tokens": 4257003.0,
|
|
"step": 2170
|
|
},
|
|
{
|
|
"entropy": 6.956232166290283,
|
|
"epoch": 0.21742390163442796,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004998439712235747,
|
|
"loss": 6.9122,
|
|
"mean_token_accuracy": 0.11430383697152138,
|
|
"num_tokens": 4266412.0,
|
|
"step": 2175
|
|
},
|
|
{
|
|
"entropy": 6.937617540359497,
|
|
"epoch": 0.21792372669565652,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004998426395131248,
|
|
"loss": 6.8452,
|
|
"mean_token_accuracy": 0.11389510557055474,
|
|
"num_tokens": 4276361.0,
|
|
"step": 2180
|
|
},
|
|
{
|
|
"entropy": 6.936740159988403,
|
|
"epoch": 0.2184235517568851,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004998413021456919,
|
|
"loss": 6.8528,
|
|
"mean_token_accuracy": 0.12202164232730865,
|
|
"num_tokens": 4285815.0,
|
|
"step": 2185
|
|
},
|
|
{
|
|
"entropy": 6.907345581054687,
|
|
"epoch": 0.21892337681811366,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004998399591213098,
|
|
"loss": 6.8365,
|
|
"mean_token_accuracy": 0.11947793588042259,
|
|
"num_tokens": 4296071.0,
|
|
"step": 2190
|
|
},
|
|
{
|
|
"entropy": 6.901845836639405,
|
|
"epoch": 0.21942320187934222,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004998386104400122,
|
|
"loss": 6.8387,
|
|
"mean_token_accuracy": 0.12116138637065887,
|
|
"num_tokens": 4306476.0,
|
|
"step": 2195
|
|
},
|
|
{
|
|
"entropy": 6.931117963790894,
|
|
"epoch": 0.2199230269405708,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004998372561018329,
|
|
"loss": 6.8856,
|
|
"mean_token_accuracy": 0.11641964539885521,
|
|
"num_tokens": 4316312.0,
|
|
"step": 2200
|
|
},
|
|
{
|
|
"entropy": 6.847039604187012,
|
|
"epoch": 0.22042285200179937,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004998358961068062,
|
|
"loss": 6.7863,
|
|
"mean_token_accuracy": 0.12805279418826104,
|
|
"num_tokens": 4325443.0,
|
|
"step": 2205
|
|
},
|
|
{
|
|
"entropy": 6.916587829589844,
|
|
"epoch": 0.22092267706302793,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004998345304549661,
|
|
"loss": 6.8401,
|
|
"mean_token_accuracy": 0.11731385514140129,
|
|
"num_tokens": 4334354.0,
|
|
"step": 2210
|
|
},
|
|
{
|
|
"entropy": 6.8048478126525875,
|
|
"epoch": 0.22142250212425652,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004998331591463471,
|
|
"loss": 6.7509,
|
|
"mean_token_accuracy": 0.12133458405733108,
|
|
"num_tokens": 4344714.0,
|
|
"step": 2215
|
|
},
|
|
{
|
|
"entropy": 6.86434965133667,
|
|
"epoch": 0.22192232718548507,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004998317821809837,
|
|
"loss": 6.7932,
|
|
"mean_token_accuracy": 0.11775240227580071,
|
|
"num_tokens": 4354216.0,
|
|
"step": 2220
|
|
},
|
|
{
|
|
"entropy": 6.932387924194336,
|
|
"epoch": 0.22242215224671366,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004998303995589104,
|
|
"loss": 6.8418,
|
|
"mean_token_accuracy": 0.12000173777341842,
|
|
"num_tokens": 4364764.0,
|
|
"step": 2225
|
|
},
|
|
{
|
|
"entropy": 6.8684345245361325,
|
|
"epoch": 0.22292197730794222,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004998290112801623,
|
|
"loss": 6.9253,
|
|
"mean_token_accuracy": 0.11187315285205841,
|
|
"num_tokens": 4375289.0,
|
|
"step": 2230
|
|
},
|
|
{
|
|
"entropy": 6.82034010887146,
|
|
"epoch": 0.22342180236917078,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000499827617344774,
|
|
"loss": 6.8133,
|
|
"mean_token_accuracy": 0.12498923987150193,
|
|
"num_tokens": 4384984.0,
|
|
"step": 2235
|
|
},
|
|
{
|
|
"entropy": 6.945557641983032,
|
|
"epoch": 0.22392162743039937,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004998262177527807,
|
|
"loss": 6.795,
|
|
"mean_token_accuracy": 0.12080412805080414,
|
|
"num_tokens": 4393321.0,
|
|
"step": 2240
|
|
},
|
|
{
|
|
"entropy": 6.814831018447876,
|
|
"epoch": 0.22442145249162793,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004998248125042177,
|
|
"loss": 6.87,
|
|
"mean_token_accuracy": 0.11272740364074707,
|
|
"num_tokens": 4404908.0,
|
|
"step": 2245
|
|
},
|
|
{
|
|
"entropy": 7.018628549575806,
|
|
"epoch": 0.2249212775528565,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004998234015991202,
|
|
"loss": 6.9487,
|
|
"mean_token_accuracy": 0.1148961141705513,
|
|
"num_tokens": 4415530.0,
|
|
"step": 2250
|
|
},
|
|
{
|
|
"entropy": 6.964756965637207,
|
|
"epoch": 0.22542110261408507,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004998219850375238,
|
|
"loss": 6.8654,
|
|
"mean_token_accuracy": 0.11356062963604927,
|
|
"num_tokens": 4425678.0,
|
|
"step": 2255
|
|
},
|
|
{
|
|
"entropy": 6.778150987625122,
|
|
"epoch": 0.22592092767531363,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004998205628194641,
|
|
"loss": 6.8267,
|
|
"mean_token_accuracy": 0.11817835196852684,
|
|
"num_tokens": 4436890.0,
|
|
"step": 2260
|
|
},
|
|
{
|
|
"entropy": 6.915167760848999,
|
|
"epoch": 0.22642075273654222,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004998191349449768,
|
|
"loss": 6.6857,
|
|
"mean_token_accuracy": 0.12716825529932976,
|
|
"num_tokens": 4446947.0,
|
|
"step": 2265
|
|
},
|
|
{
|
|
"entropy": 6.998455286026001,
|
|
"epoch": 0.22692057779777078,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004998177014140981,
|
|
"loss": 6.8669,
|
|
"mean_token_accuracy": 0.12382732853293418,
|
|
"num_tokens": 4457052.0,
|
|
"step": 2270
|
|
},
|
|
{
|
|
"entropy": 6.763993167877198,
|
|
"epoch": 0.22742040285899934,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004998162622268637,
|
|
"loss": 6.7014,
|
|
"mean_token_accuracy": 0.12646981552243233,
|
|
"num_tokens": 4466171.0,
|
|
"step": 2275
|
|
},
|
|
{
|
|
"entropy": 6.834669017791748,
|
|
"epoch": 0.22792022792022792,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004998148173833101,
|
|
"loss": 6.9205,
|
|
"mean_token_accuracy": 0.11530092284083367,
|
|
"num_tokens": 4476147.0,
|
|
"step": 2280
|
|
},
|
|
{
|
|
"entropy": 6.9172093868255615,
|
|
"epoch": 0.22842005298145648,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004998133668834735,
|
|
"loss": 6.8285,
|
|
"mean_token_accuracy": 0.1202719822525978,
|
|
"num_tokens": 4485786.0,
|
|
"step": 2285
|
|
},
|
|
{
|
|
"entropy": 6.892522478103638,
|
|
"epoch": 0.22891987804268507,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004998119107273905,
|
|
"loss": 6.8783,
|
|
"mean_token_accuracy": 0.12116087898612023,
|
|
"num_tokens": 4495376.0,
|
|
"step": 2290
|
|
},
|
|
{
|
|
"entropy": 6.980706357955933,
|
|
"epoch": 0.22941970310391363,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004998104489150975,
|
|
"loss": 6.8384,
|
|
"mean_token_accuracy": 0.11390652880072594,
|
|
"num_tokens": 4504500.0,
|
|
"step": 2295
|
|
},
|
|
{
|
|
"entropy": 6.80579104423523,
|
|
"epoch": 0.2299195281651422,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004998089814466318,
|
|
"loss": 6.9246,
|
|
"mean_token_accuracy": 0.11344198286533355,
|
|
"num_tokens": 4514842.0,
|
|
"step": 2300
|
|
},
|
|
{
|
|
"entropy": 6.911924409866333,
|
|
"epoch": 0.23041935322637078,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004998075083220295,
|
|
"loss": 6.787,
|
|
"mean_token_accuracy": 0.12299882918596268,
|
|
"num_tokens": 4523794.0,
|
|
"step": 2305
|
|
},
|
|
{
|
|
"entropy": 6.934869241714478,
|
|
"epoch": 0.23091917828759934,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004998060295413286,
|
|
"loss": 6.8514,
|
|
"mean_token_accuracy": 0.11584107503294945,
|
|
"num_tokens": 4533315.0,
|
|
"step": 2310
|
|
},
|
|
{
|
|
"entropy": 6.789450931549072,
|
|
"epoch": 0.23141900334882792,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004998045451045656,
|
|
"loss": 6.7111,
|
|
"mean_token_accuracy": 0.1275709204375744,
|
|
"num_tokens": 4542996.0,
|
|
"step": 2315
|
|
},
|
|
{
|
|
"entropy": 6.862829113006592,
|
|
"epoch": 0.23191882841005648,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004998030550117782,
|
|
"loss": 6.7841,
|
|
"mean_token_accuracy": 0.12046822234988212,
|
|
"num_tokens": 4552719.0,
|
|
"step": 2320
|
|
},
|
|
{
|
|
"entropy": 6.794938373565674,
|
|
"epoch": 0.23241865347128504,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004998015592630037,
|
|
"loss": 6.7181,
|
|
"mean_token_accuracy": 0.12457696348428726,
|
|
"num_tokens": 4562040.0,
|
|
"step": 2325
|
|
},
|
|
{
|
|
"entropy": 6.7735360622406,
|
|
"epoch": 0.23291847853251363,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004998000578582798,
|
|
"loss": 6.7695,
|
|
"mean_token_accuracy": 0.1228984922170639,
|
|
"num_tokens": 4570855.0,
|
|
"step": 2330
|
|
},
|
|
{
|
|
"entropy": 6.912277126312256,
|
|
"epoch": 0.2334183035937422,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004997985507976443,
|
|
"loss": 6.8861,
|
|
"mean_token_accuracy": 0.11459040716290474,
|
|
"num_tokens": 4581814.0,
|
|
"step": 2335
|
|
},
|
|
{
|
|
"entropy": 6.869301176071167,
|
|
"epoch": 0.23391812865497075,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004997970380811351,
|
|
"loss": 6.785,
|
|
"mean_token_accuracy": 0.12393666356801987,
|
|
"num_tokens": 4590731.0,
|
|
"step": 2340
|
|
},
|
|
{
|
|
"entropy": 6.845894432067871,
|
|
"epoch": 0.23441795371619933,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004997955197087904,
|
|
"loss": 6.7703,
|
|
"mean_token_accuracy": 0.11945929154753684,
|
|
"num_tokens": 4600440.0,
|
|
"step": 2345
|
|
},
|
|
{
|
|
"entropy": 6.842683792114258,
|
|
"epoch": 0.2349177787774279,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004997939956806481,
|
|
"loss": 6.774,
|
|
"mean_token_accuracy": 0.12290067374706268,
|
|
"num_tokens": 4609510.0,
|
|
"step": 2350
|
|
},
|
|
{
|
|
"entropy": 6.863666009902954,
|
|
"epoch": 0.23541760383865648,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004997924659967467,
|
|
"loss": 6.8539,
|
|
"mean_token_accuracy": 0.11659590974450111,
|
|
"num_tokens": 4620481.0,
|
|
"step": 2355
|
|
},
|
|
{
|
|
"entropy": 6.893025636672974,
|
|
"epoch": 0.23591742889988504,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004997909306571248,
|
|
"loss": 6.7085,
|
|
"mean_token_accuracy": 0.12738291099667548,
|
|
"num_tokens": 4629388.0,
|
|
"step": 2360
|
|
},
|
|
{
|
|
"entropy": 6.7053995609283445,
|
|
"epoch": 0.2364172539611136,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004997893896618209,
|
|
"loss": 6.7177,
|
|
"mean_token_accuracy": 0.1286756858229637,
|
|
"num_tokens": 4638429.0,
|
|
"step": 2365
|
|
},
|
|
{
|
|
"entropy": 6.883879661560059,
|
|
"epoch": 0.2369170790223422,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004997878430108738,
|
|
"loss": 6.845,
|
|
"mean_token_accuracy": 0.1211053729057312,
|
|
"num_tokens": 4648995.0,
|
|
"step": 2370
|
|
},
|
|
{
|
|
"entropy": 6.898133850097656,
|
|
"epoch": 0.23741690408357075,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004997862907043224,
|
|
"loss": 6.7398,
|
|
"mean_token_accuracy": 0.11961732506752014,
|
|
"num_tokens": 4658584.0,
|
|
"step": 2375
|
|
},
|
|
{
|
|
"entropy": 6.765787029266358,
|
|
"epoch": 0.23791672914479933,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004997847327422059,
|
|
"loss": 6.7737,
|
|
"mean_token_accuracy": 0.12453893274068832,
|
|
"num_tokens": 4668859.0,
|
|
"step": 2380
|
|
},
|
|
{
|
|
"entropy": 6.8678569316864015,
|
|
"epoch": 0.2384165542060279,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004997831691245632,
|
|
"loss": 6.825,
|
|
"mean_token_accuracy": 0.11157805621623992,
|
|
"num_tokens": 4678389.0,
|
|
"step": 2385
|
|
},
|
|
{
|
|
"entropy": 6.839744949340821,
|
|
"epoch": 0.23891637926725645,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004997815998514337,
|
|
"loss": 6.8357,
|
|
"mean_token_accuracy": 0.1212715081870556,
|
|
"num_tokens": 4688763.0,
|
|
"step": 2390
|
|
},
|
|
{
|
|
"entropy": 6.8042905807495115,
|
|
"epoch": 0.23941620432848504,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004997800249228572,
|
|
"loss": 6.7007,
|
|
"mean_token_accuracy": 0.12444251105189323,
|
|
"num_tokens": 4698180.0,
|
|
"step": 2395
|
|
},
|
|
{
|
|
"entropy": 6.778486728668213,
|
|
"epoch": 0.2399160293897136,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004997784443388732,
|
|
"loss": 6.6789,
|
|
"mean_token_accuracy": 0.1236902080476284,
|
|
"num_tokens": 4708111.0,
|
|
"step": 2400
|
|
},
|
|
{
|
|
"entropy": 6.81549825668335,
|
|
"epoch": 0.24041585445094216,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004997768580995212,
|
|
"loss": 6.8155,
|
|
"mean_token_accuracy": 0.1198317751288414,
|
|
"num_tokens": 4717247.0,
|
|
"step": 2405
|
|
},
|
|
{
|
|
"entropy": 6.83826060295105,
|
|
"epoch": 0.24091567951217074,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004997752662048413,
|
|
"loss": 6.7476,
|
|
"mean_token_accuracy": 0.12130436301231384,
|
|
"num_tokens": 4727062.0,
|
|
"step": 2410
|
|
},
|
|
{
|
|
"entropy": 6.770843982696533,
|
|
"epoch": 0.2414155045733993,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004997736686548736,
|
|
"loss": 6.6909,
|
|
"mean_token_accuracy": 0.13135136663913727,
|
|
"num_tokens": 4735806.0,
|
|
"step": 2415
|
|
},
|
|
{
|
|
"entropy": 6.909219455718994,
|
|
"epoch": 0.2419153296346279,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004997720654496582,
|
|
"loss": 6.8409,
|
|
"mean_token_accuracy": 0.11559810191392898,
|
|
"num_tokens": 4745246.0,
|
|
"step": 2420
|
|
},
|
|
{
|
|
"entropy": 6.834303331375122,
|
|
"epoch": 0.24241515469585645,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004997704565892355,
|
|
"loss": 6.7325,
|
|
"mean_token_accuracy": 0.12480264231562614,
|
|
"num_tokens": 4754867.0,
|
|
"step": 2425
|
|
},
|
|
{
|
|
"entropy": 6.803612899780274,
|
|
"epoch": 0.242914979757085,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004997688420736459,
|
|
"loss": 6.8049,
|
|
"mean_token_accuracy": 0.12716324329376222,
|
|
"num_tokens": 4764418.0,
|
|
"step": 2430
|
|
},
|
|
{
|
|
"entropy": 6.777321815490723,
|
|
"epoch": 0.2434148048183136,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004997672219029301,
|
|
"loss": 6.7701,
|
|
"mean_token_accuracy": 0.11963262781500816,
|
|
"num_tokens": 4774137.0,
|
|
"step": 2435
|
|
},
|
|
{
|
|
"entropy": 6.8135435581207275,
|
|
"epoch": 0.24391462987954216,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004997655960771288,
|
|
"loss": 6.8014,
|
|
"mean_token_accuracy": 0.12224104627966881,
|
|
"num_tokens": 4784503.0,
|
|
"step": 2440
|
|
},
|
|
{
|
|
"entropy": 6.83231143951416,
|
|
"epoch": 0.24441445494077074,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.000499763964596283,
|
|
"loss": 6.8487,
|
|
"mean_token_accuracy": 0.11832178011536598,
|
|
"num_tokens": 4795847.0,
|
|
"step": 2445
|
|
},
|
|
{
|
|
"entropy": 6.819264650344849,
|
|
"epoch": 0.2449142800019993,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004997623274604336,
|
|
"loss": 6.7086,
|
|
"mean_token_accuracy": 0.1282437562942505,
|
|
"num_tokens": 4805230.0,
|
|
"step": 2450
|
|
},
|
|
{
|
|
"entropy": 6.745674896240234,
|
|
"epoch": 0.24541410506322786,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.000499760684669622,
|
|
"loss": 6.6627,
|
|
"mean_token_accuracy": 0.1251753568649292,
|
|
"num_tokens": 4815345.0,
|
|
"step": 2455
|
|
},
|
|
{
|
|
"entropy": 6.792028522491455,
|
|
"epoch": 0.24591393012445645,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004997590362238894,
|
|
"loss": 6.7252,
|
|
"mean_token_accuracy": 0.12097799107432365,
|
|
"num_tokens": 4824819.0,
|
|
"step": 2460
|
|
},
|
|
{
|
|
"entropy": 6.798549795150757,
|
|
"epoch": 0.246413755185685,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004997573821232772,
|
|
"loss": 6.7776,
|
|
"mean_token_accuracy": 0.12377737537026405,
|
|
"num_tokens": 4834339.0,
|
|
"step": 2465
|
|
},
|
|
{
|
|
"entropy": 6.775806903839111,
|
|
"epoch": 0.24691358024691357,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004997557223678272,
|
|
"loss": 6.746,
|
|
"mean_token_accuracy": 0.12383496910333633,
|
|
"num_tokens": 4844440.0,
|
|
"step": 2470
|
|
},
|
|
{
|
|
"entropy": 6.874798965454102,
|
|
"epoch": 0.24741340530814215,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004997540569575809,
|
|
"loss": 6.7441,
|
|
"mean_token_accuracy": 0.11938895136117936,
|
|
"num_tokens": 4854688.0,
|
|
"step": 2475
|
|
},
|
|
{
|
|
"entropy": 6.734471464157105,
|
|
"epoch": 0.2479132303693707,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004997523858925805,
|
|
"loss": 6.7423,
|
|
"mean_token_accuracy": 0.1235843650996685,
|
|
"num_tokens": 4864629.0,
|
|
"step": 2480
|
|
},
|
|
{
|
|
"entropy": 6.783338022232056,
|
|
"epoch": 0.2484130554305993,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004997507091728678,
|
|
"loss": 6.7186,
|
|
"mean_token_accuracy": 0.12358858436346054,
|
|
"num_tokens": 4873693.0,
|
|
"step": 2485
|
|
},
|
|
{
|
|
"entropy": 6.776330995559692,
|
|
"epoch": 0.24891288049182786,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004997490267984853,
|
|
"loss": 6.6959,
|
|
"mean_token_accuracy": 0.127644382417202,
|
|
"num_tokens": 4882640.0,
|
|
"step": 2490
|
|
},
|
|
{
|
|
"entropy": 6.767954730987549,
|
|
"epoch": 0.24941270555305642,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004997473387694749,
|
|
"loss": 6.7975,
|
|
"mean_token_accuracy": 0.11814235299825668,
|
|
"num_tokens": 4893452.0,
|
|
"step": 2495
|
|
},
|
|
{
|
|
"entropy": 6.799860954284668,
|
|
"epoch": 0.249912530614285,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004997456450858793,
|
|
"loss": 6.8177,
|
|
"mean_token_accuracy": 0.11675577834248543,
|
|
"num_tokens": 4902949.0,
|
|
"step": 2500
|
|
},
|
|
{
|
|
"entropy": 6.891696548461914,
|
|
"epoch": 0.25041235567551356,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004997439457477412,
|
|
"loss": 6.7823,
|
|
"mean_token_accuracy": 0.11894313916563988,
|
|
"num_tokens": 4912748.0,
|
|
"step": 2505
|
|
},
|
|
{
|
|
"entropy": 6.8100135803222654,
|
|
"epoch": 0.25091218073674215,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004997422407551032,
|
|
"loss": 6.7257,
|
|
"mean_token_accuracy": 0.12602523788809777,
|
|
"num_tokens": 4922405.0,
|
|
"step": 2510
|
|
},
|
|
{
|
|
"entropy": 6.72805871963501,
|
|
"epoch": 0.2514120057979707,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004997405301080082,
|
|
"loss": 6.7064,
|
|
"mean_token_accuracy": 0.12541015595197677,
|
|
"num_tokens": 4931826.0,
|
|
"step": 2515
|
|
},
|
|
{
|
|
"entropy": 6.752864646911621,
|
|
"epoch": 0.25191183085919927,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004997388138064994,
|
|
"loss": 6.773,
|
|
"mean_token_accuracy": 0.12637126743793486,
|
|
"num_tokens": 4942165.0,
|
|
"step": 2520
|
|
},
|
|
{
|
|
"entropy": 6.872462368011474,
|
|
"epoch": 0.25241165592042786,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004997370918506198,
|
|
"loss": 6.7321,
|
|
"mean_token_accuracy": 0.11997186169028282,
|
|
"num_tokens": 4951287.0,
|
|
"step": 2525
|
|
},
|
|
{
|
|
"entropy": 6.76559042930603,
|
|
"epoch": 0.25291148098165644,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004997353642404129,
|
|
"loss": 6.6975,
|
|
"mean_token_accuracy": 0.12422825694084168,
|
|
"num_tokens": 4960452.0,
|
|
"step": 2530
|
|
},
|
|
{
|
|
"entropy": 6.764957475662231,
|
|
"epoch": 0.253411306042885,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004997336309759219,
|
|
"loss": 6.7601,
|
|
"mean_token_accuracy": 0.12294914424419404,
|
|
"num_tokens": 4971310.0,
|
|
"step": 2535
|
|
},
|
|
{
|
|
"entropy": 6.915872573852539,
|
|
"epoch": 0.25391113110411356,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004997318920571907,
|
|
"loss": 6.7266,
|
|
"mean_token_accuracy": 0.12278066650032997,
|
|
"num_tokens": 4980609.0,
|
|
"step": 2540
|
|
},
|
|
{
|
|
"entropy": 6.753065395355224,
|
|
"epoch": 0.25441095616534215,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000499730147484263,
|
|
"loss": 6.7388,
|
|
"mean_token_accuracy": 0.12710461020469666,
|
|
"num_tokens": 4989991.0,
|
|
"step": 2545
|
|
},
|
|
{
|
|
"entropy": 6.74550838470459,
|
|
"epoch": 0.2549107812265707,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004997283972571824,
|
|
"loss": 6.7283,
|
|
"mean_token_accuracy": 0.12032875418663025,
|
|
"num_tokens": 5000493.0,
|
|
"step": 2550
|
|
},
|
|
{
|
|
"entropy": 6.821319437026977,
|
|
"epoch": 0.25541060628779927,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004997266413759934,
|
|
"loss": 6.8219,
|
|
"mean_token_accuracy": 0.12391160577535629,
|
|
"num_tokens": 5010496.0,
|
|
"step": 2555
|
|
},
|
|
{
|
|
"entropy": 6.91074390411377,
|
|
"epoch": 0.25591043134902786,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004997248798407397,
|
|
"loss": 6.8677,
|
|
"mean_token_accuracy": 0.11413910016417503,
|
|
"num_tokens": 5020783.0,
|
|
"step": 2560
|
|
},
|
|
{
|
|
"entropy": 6.725059556961059,
|
|
"epoch": 0.2564102564102564,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004997231126514659,
|
|
"loss": 6.7697,
|
|
"mean_token_accuracy": 0.12141788229346276,
|
|
"num_tokens": 5029939.0,
|
|
"step": 2565
|
|
},
|
|
{
|
|
"entropy": 6.9148595333099365,
|
|
"epoch": 0.256910081471485,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004997213398082165,
|
|
"loss": 6.7619,
|
|
"mean_token_accuracy": 0.12135729119181633,
|
|
"num_tokens": 5039491.0,
|
|
"step": 2570
|
|
},
|
|
{
|
|
"entropy": 6.8569738388061525,
|
|
"epoch": 0.25740990653271356,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.000499719561311036,
|
|
"loss": 6.7675,
|
|
"mean_token_accuracy": 0.12060310840606689,
|
|
"num_tokens": 5049780.0,
|
|
"step": 2575
|
|
},
|
|
{
|
|
"entropy": 6.771124410629272,
|
|
"epoch": 0.2579097315939421,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004997177771599691,
|
|
"loss": 6.7195,
|
|
"mean_token_accuracy": 0.12665437906980515,
|
|
"num_tokens": 5058986.0,
|
|
"step": 2580
|
|
},
|
|
{
|
|
"entropy": 6.762947845458984,
|
|
"epoch": 0.2584095566551707,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004997159873550607,
|
|
"loss": 6.6629,
|
|
"mean_token_accuracy": 0.1242829754948616,
|
|
"num_tokens": 5068269.0,
|
|
"step": 2585
|
|
},
|
|
{
|
|
"entropy": 6.781703472137451,
|
|
"epoch": 0.25890938171639927,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004997141918963561,
|
|
"loss": 6.7982,
|
|
"mean_token_accuracy": 0.11847331300377846,
|
|
"num_tokens": 5078674.0,
|
|
"step": 2590
|
|
},
|
|
{
|
|
"entropy": 6.817697381973266,
|
|
"epoch": 0.25940920677762785,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004997123907839001,
|
|
"loss": 6.7285,
|
|
"mean_token_accuracy": 0.1285196512937546,
|
|
"num_tokens": 5087599.0,
|
|
"step": 2595
|
|
},
|
|
{
|
|
"entropy": 6.75245213508606,
|
|
"epoch": 0.2599090318388564,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004997105840177381,
|
|
"loss": 6.6444,
|
|
"mean_token_accuracy": 0.12771404534578323,
|
|
"num_tokens": 5097418.0,
|
|
"step": 2600
|
|
},
|
|
{
|
|
"entropy": 6.720393276214599,
|
|
"epoch": 0.260408856900085,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004997087715979157,
|
|
"loss": 6.7088,
|
|
"mean_token_accuracy": 0.12440732717514039,
|
|
"num_tokens": 5108248.0,
|
|
"step": 2605
|
|
},
|
|
{
|
|
"entropy": 6.849985408782959,
|
|
"epoch": 0.26090868196131356,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004997069535244785,
|
|
"loss": 6.6605,
|
|
"mean_token_accuracy": 0.12989854514598848,
|
|
"num_tokens": 5118284.0,
|
|
"step": 2610
|
|
},
|
|
{
|
|
"entropy": 6.731876516342163,
|
|
"epoch": 0.2614085070225421,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004997051297974722,
|
|
"loss": 6.8218,
|
|
"mean_token_accuracy": 0.12219112440943718,
|
|
"num_tokens": 5128485.0,
|
|
"step": 2615
|
|
},
|
|
{
|
|
"entropy": 6.833446025848389,
|
|
"epoch": 0.2619083320837707,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004997033004169425,
|
|
"loss": 6.745,
|
|
"mean_token_accuracy": 0.11980004459619523,
|
|
"num_tokens": 5138058.0,
|
|
"step": 2620
|
|
},
|
|
{
|
|
"entropy": 6.705493688583374,
|
|
"epoch": 0.26240815714499927,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004997014653829357,
|
|
"loss": 6.6385,
|
|
"mean_token_accuracy": 0.1275268502533436,
|
|
"num_tokens": 5148555.0,
|
|
"step": 2625
|
|
},
|
|
{
|
|
"entropy": 6.7973309516906735,
|
|
"epoch": 0.2629079822062278,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004996996246954977,
|
|
"loss": 6.8189,
|
|
"mean_token_accuracy": 0.11919309869408608,
|
|
"num_tokens": 5158729.0,
|
|
"step": 2630
|
|
},
|
|
{
|
|
"entropy": 6.896182250976563,
|
|
"epoch": 0.2634078072674564,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004996977783546752,
|
|
"loss": 6.8511,
|
|
"mean_token_accuracy": 0.11748289540410042,
|
|
"num_tokens": 5168900.0,
|
|
"step": 2635
|
|
},
|
|
{
|
|
"entropy": 6.777275085449219,
|
|
"epoch": 0.26390763232868497,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004996959263605143,
|
|
"loss": 6.7687,
|
|
"mean_token_accuracy": 0.11863479912281036,
|
|
"num_tokens": 5179742.0,
|
|
"step": 2640
|
|
},
|
|
{
|
|
"entropy": 6.876881885528564,
|
|
"epoch": 0.2644074573899135,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004996940687130617,
|
|
"loss": 6.7661,
|
|
"mean_token_accuracy": 0.1250888466835022,
|
|
"num_tokens": 5190221.0,
|
|
"step": 2645
|
|
},
|
|
{
|
|
"entropy": 6.781659746170044,
|
|
"epoch": 0.2649072824511421,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004996922054123641,
|
|
"loss": 6.7396,
|
|
"mean_token_accuracy": 0.12349513024091721,
|
|
"num_tokens": 5200252.0,
|
|
"step": 2650
|
|
},
|
|
{
|
|
"entropy": 6.696864986419678,
|
|
"epoch": 0.2654071075123707,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004996903364584685,
|
|
"loss": 6.6989,
|
|
"mean_token_accuracy": 0.1287691190838814,
|
|
"num_tokens": 5209388.0,
|
|
"step": 2655
|
|
},
|
|
{
|
|
"entropy": 6.807218217849732,
|
|
"epoch": 0.26590693257359926,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004996884618514219,
|
|
"loss": 6.6763,
|
|
"mean_token_accuracy": 0.12565898299217224,
|
|
"num_tokens": 5219806.0,
|
|
"step": 2660
|
|
},
|
|
{
|
|
"entropy": 6.739374589920044,
|
|
"epoch": 0.2664067576348278,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004996865815912713,
|
|
"loss": 6.7091,
|
|
"mean_token_accuracy": 0.1312312088906765,
|
|
"num_tokens": 5229485.0,
|
|
"step": 2665
|
|
},
|
|
{
|
|
"entropy": 6.822212362289429,
|
|
"epoch": 0.2669065826960564,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004996846956780642,
|
|
"loss": 6.6959,
|
|
"mean_token_accuracy": 0.12174614071846009,
|
|
"num_tokens": 5238922.0,
|
|
"step": 2670
|
|
},
|
|
{
|
|
"entropy": 6.74418044090271,
|
|
"epoch": 0.26740640775728497,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000499682804111848,
|
|
"loss": 6.6966,
|
|
"mean_token_accuracy": 0.1255224473774433,
|
|
"num_tokens": 5248391.0,
|
|
"step": 2675
|
|
},
|
|
{
|
|
"entropy": 6.749328470230102,
|
|
"epoch": 0.2679062328185135,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004996809068926702,
|
|
"loss": 6.7147,
|
|
"mean_token_accuracy": 0.11848349198698997,
|
|
"num_tokens": 5257605.0,
|
|
"step": 2680
|
|
},
|
|
{
|
|
"entropy": 6.922802114486695,
|
|
"epoch": 0.2684060578797421,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004996790040205786,
|
|
"loss": 6.8072,
|
|
"mean_token_accuracy": 0.12140284031629563,
|
|
"num_tokens": 5266808.0,
|
|
"step": 2685
|
|
},
|
|
{
|
|
"entropy": 6.742965745925903,
|
|
"epoch": 0.2689058829409707,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004996770954956211,
|
|
"loss": 6.6396,
|
|
"mean_token_accuracy": 0.12836444452404977,
|
|
"num_tokens": 5276471.0,
|
|
"step": 2690
|
|
},
|
|
{
|
|
"entropy": 6.656261253356933,
|
|
"epoch": 0.2694057080021992,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004996751813178456,
|
|
"loss": 6.6459,
|
|
"mean_token_accuracy": 0.12415419071912766,
|
|
"num_tokens": 5285312.0,
|
|
"step": 2695
|
|
},
|
|
{
|
|
"entropy": 6.784100151062011,
|
|
"epoch": 0.2699055330634278,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004996732614873005,
|
|
"loss": 6.7723,
|
|
"mean_token_accuracy": 0.11762264221906663,
|
|
"num_tokens": 5295608.0,
|
|
"step": 2700
|
|
},
|
|
{
|
|
"entropy": 6.837291526794433,
|
|
"epoch": 0.2704053581246564,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004996713360040339,
|
|
"loss": 6.7089,
|
|
"mean_token_accuracy": 0.12051343023777009,
|
|
"num_tokens": 5305181.0,
|
|
"step": 2705
|
|
},
|
|
{
|
|
"entropy": 6.760000276565552,
|
|
"epoch": 0.27090518318588497,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004996694048680942,
|
|
"loss": 6.7168,
|
|
"mean_token_accuracy": 0.11832475885748864,
|
|
"num_tokens": 5314706.0,
|
|
"step": 2710
|
|
},
|
|
{
|
|
"entropy": 6.771784496307373,
|
|
"epoch": 0.2714050082471135,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004996674680795302,
|
|
"loss": 6.6436,
|
|
"mean_token_accuracy": 0.12209197878837585,
|
|
"num_tokens": 5324207.0,
|
|
"step": 2715
|
|
},
|
|
{
|
|
"entropy": 6.7553201675415036,
|
|
"epoch": 0.2719048333083421,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004996655256383905,
|
|
"loss": 6.7058,
|
|
"mean_token_accuracy": 0.12452286705374718,
|
|
"num_tokens": 5333554.0,
|
|
"step": 2720
|
|
},
|
|
{
|
|
"entropy": 6.809931802749634,
|
|
"epoch": 0.2724046583695707,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.000499663577544724,
|
|
"loss": 6.7933,
|
|
"mean_token_accuracy": 0.12039531022310257,
|
|
"num_tokens": 5343811.0,
|
|
"step": 2725
|
|
},
|
|
{
|
|
"entropy": 6.77467360496521,
|
|
"epoch": 0.2729044834307992,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004996616237985796,
|
|
"loss": 6.7307,
|
|
"mean_token_accuracy": 0.12147506698966026,
|
|
"num_tokens": 5353980.0,
|
|
"step": 2730
|
|
},
|
|
{
|
|
"entropy": 6.783198595046997,
|
|
"epoch": 0.2734043084920278,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004996596644000066,
|
|
"loss": 6.7045,
|
|
"mean_token_accuracy": 0.12822512909770012,
|
|
"num_tokens": 5363681.0,
|
|
"step": 2735
|
|
},
|
|
{
|
|
"entropy": 6.7205146789550785,
|
|
"epoch": 0.2739041335532564,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004996576993490543,
|
|
"loss": 6.6347,
|
|
"mean_token_accuracy": 0.1307567574083805,
|
|
"num_tokens": 5373855.0,
|
|
"step": 2740
|
|
},
|
|
{
|
|
"entropy": 6.799875783920288,
|
|
"epoch": 0.2744039586144849,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004996557286457721,
|
|
"loss": 6.6961,
|
|
"mean_token_accuracy": 0.12730289548635482,
|
|
"num_tokens": 5383831.0,
|
|
"step": 2745
|
|
},
|
|
{
|
|
"entropy": 6.746462345123291,
|
|
"epoch": 0.2749037836757135,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004996537522902096,
|
|
"loss": 6.7273,
|
|
"mean_token_accuracy": 0.12303572297096252,
|
|
"num_tokens": 5392247.0,
|
|
"step": 2750
|
|
},
|
|
{
|
|
"entropy": 6.783823299407959,
|
|
"epoch": 0.2754036087369421,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004996517702824163,
|
|
"loss": 6.6701,
|
|
"mean_token_accuracy": 0.12064638286828995,
|
|
"num_tokens": 5401091.0,
|
|
"step": 2755
|
|
},
|
|
{
|
|
"entropy": 6.716385412216186,
|
|
"epoch": 0.2759034337981706,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004996497826224425,
|
|
"loss": 6.6708,
|
|
"mean_token_accuracy": 0.12038891389966011,
|
|
"num_tokens": 5409809.0,
|
|
"step": 2760
|
|
},
|
|
{
|
|
"entropy": 6.699102449417114,
|
|
"epoch": 0.2764032588593992,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004996477893103379,
|
|
"loss": 6.6376,
|
|
"mean_token_accuracy": 0.12431047409772873,
|
|
"num_tokens": 5420104.0,
|
|
"step": 2765
|
|
},
|
|
{
|
|
"entropy": 6.762558364868164,
|
|
"epoch": 0.2769030839206278,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004996457903461527,
|
|
"loss": 6.679,
|
|
"mean_token_accuracy": 0.1296892248094082,
|
|
"num_tokens": 5427905.0,
|
|
"step": 2770
|
|
},
|
|
{
|
|
"entropy": 6.644171094894409,
|
|
"epoch": 0.2774029089818564,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004996437857299373,
|
|
"loss": 6.6837,
|
|
"mean_token_accuracy": 0.1241793692111969,
|
|
"num_tokens": 5438537.0,
|
|
"step": 2775
|
|
},
|
|
{
|
|
"entropy": 6.750694274902344,
|
|
"epoch": 0.2779027340430849,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.000499641775461742,
|
|
"loss": 6.7575,
|
|
"mean_token_accuracy": 0.11740487441420555,
|
|
"num_tokens": 5447622.0,
|
|
"step": 2780
|
|
},
|
|
{
|
|
"entropy": 6.782175016403198,
|
|
"epoch": 0.2784025591043135,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004996397595416173,
|
|
"loss": 6.6512,
|
|
"mean_token_accuracy": 0.12953489869832993,
|
|
"num_tokens": 5457407.0,
|
|
"step": 2785
|
|
},
|
|
{
|
|
"entropy": 6.708248949050903,
|
|
"epoch": 0.2789023841655421,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004996377379696143,
|
|
"loss": 6.6579,
|
|
"mean_token_accuracy": 0.1291919894516468,
|
|
"num_tokens": 5467187.0,
|
|
"step": 2790
|
|
},
|
|
{
|
|
"entropy": 6.750952816009521,
|
|
"epoch": 0.2794022092267706,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004996357107457834,
|
|
"loss": 6.7178,
|
|
"mean_token_accuracy": 0.11987345665693283,
|
|
"num_tokens": 5477188.0,
|
|
"step": 2795
|
|
},
|
|
{
|
|
"entropy": 6.771980571746826,
|
|
"epoch": 0.2799020342879992,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.000499633677870176,
|
|
"loss": 6.6586,
|
|
"mean_token_accuracy": 0.12479908540844917,
|
|
"num_tokens": 5485851.0,
|
|
"step": 2800
|
|
},
|
|
{
|
|
"entropy": 6.677957534790039,
|
|
"epoch": 0.2804018593492278,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004996316393428429,
|
|
"loss": 6.7292,
|
|
"mean_token_accuracy": 0.12249960973858834,
|
|
"num_tokens": 5496415.0,
|
|
"step": 2805
|
|
},
|
|
{
|
|
"entropy": 6.791005992889405,
|
|
"epoch": 0.2809016844104563,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004996295951638357,
|
|
"loss": 6.6295,
|
|
"mean_token_accuracy": 0.12775769904255868,
|
|
"num_tokens": 5505538.0,
|
|
"step": 2810
|
|
},
|
|
{
|
|
"entropy": 6.640494632720947,
|
|
"epoch": 0.2814015094716849,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004996275453332057,
|
|
"loss": 6.7225,
|
|
"mean_token_accuracy": 0.12422475144267082,
|
|
"num_tokens": 5514608.0,
|
|
"step": 2815
|
|
},
|
|
{
|
|
"entropy": 6.744523715972901,
|
|
"epoch": 0.2819013345329135,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004996254898510043,
|
|
"loss": 6.6858,
|
|
"mean_token_accuracy": 0.12396883815526963,
|
|
"num_tokens": 5523935.0,
|
|
"step": 2820
|
|
},
|
|
{
|
|
"entropy": 6.709538793563842,
|
|
"epoch": 0.282401159594142,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004996234287172835,
|
|
"loss": 6.6203,
|
|
"mean_token_accuracy": 0.13199909776449203,
|
|
"num_tokens": 5534393.0,
|
|
"step": 2825
|
|
},
|
|
{
|
|
"entropy": 6.747164535522461,
|
|
"epoch": 0.2829009846553706,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000499621361932095,
|
|
"loss": 6.6333,
|
|
"mean_token_accuracy": 0.12683428451418877,
|
|
"num_tokens": 5543414.0,
|
|
"step": 2830
|
|
},
|
|
{
|
|
"entropy": 6.645808696746826,
|
|
"epoch": 0.2834008097165992,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004996192894954909,
|
|
"loss": 6.645,
|
|
"mean_token_accuracy": 0.12200098410248757,
|
|
"num_tokens": 5553742.0,
|
|
"step": 2835
|
|
},
|
|
{
|
|
"entropy": 6.673884487152099,
|
|
"epoch": 0.2839006347778278,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004996172114075232,
|
|
"loss": 6.5438,
|
|
"mean_token_accuracy": 0.14016968458890916,
|
|
"num_tokens": 5562092.0,
|
|
"step": 2840
|
|
},
|
|
{
|
|
"entropy": 6.776102590560913,
|
|
"epoch": 0.2844004598390563,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004996151276682443,
|
|
"loss": 6.7735,
|
|
"mean_token_accuracy": 0.11559542641043663,
|
|
"num_tokens": 5571130.0,
|
|
"step": 2845
|
|
},
|
|
{
|
|
"entropy": 6.898355340957641,
|
|
"epoch": 0.2849002849002849,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004996130382777065,
|
|
"loss": 6.921,
|
|
"mean_token_accuracy": 0.11242175698280335,
|
|
"num_tokens": 5581237.0,
|
|
"step": 2850
|
|
},
|
|
{
|
|
"entropy": 6.831335830688476,
|
|
"epoch": 0.2854001099615135,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004996109432359625,
|
|
"loss": 6.7548,
|
|
"mean_token_accuracy": 0.12118344977498055,
|
|
"num_tokens": 5592488.0,
|
|
"step": 2855
|
|
},
|
|
{
|
|
"entropy": 6.713303327560425,
|
|
"epoch": 0.285899935022742,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004996088425430651,
|
|
"loss": 6.715,
|
|
"mean_token_accuracy": 0.12256577387452125,
|
|
"num_tokens": 5602958.0,
|
|
"step": 2860
|
|
},
|
|
{
|
|
"entropy": 6.751800870895385,
|
|
"epoch": 0.2863997600839706,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004996067361990669,
|
|
"loss": 6.6478,
|
|
"mean_token_accuracy": 0.12125275358557701,
|
|
"num_tokens": 5613247.0,
|
|
"step": 2865
|
|
},
|
|
{
|
|
"entropy": 6.7146094799041744,
|
|
"epoch": 0.2868995851451992,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004996046242040209,
|
|
"loss": 6.6927,
|
|
"mean_token_accuracy": 0.1286645956337452,
|
|
"num_tokens": 5624102.0,
|
|
"step": 2870
|
|
},
|
|
{
|
|
"entropy": 6.78165636062622,
|
|
"epoch": 0.28739941020642773,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004996025065579805,
|
|
"loss": 6.6226,
|
|
"mean_token_accuracy": 0.1292881041765213,
|
|
"num_tokens": 5633147.0,
|
|
"step": 2875
|
|
},
|
|
{
|
|
"entropy": 6.605591201782227,
|
|
"epoch": 0.2878992352676563,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004996003832609988,
|
|
"loss": 6.5787,
|
|
"mean_token_accuracy": 0.12823207154870034,
|
|
"num_tokens": 5643399.0,
|
|
"step": 2880
|
|
},
|
|
{
|
|
"entropy": 6.7568765640258786,
|
|
"epoch": 0.2883990603288849,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004995982543131292,
|
|
"loss": 6.7275,
|
|
"mean_token_accuracy": 0.12245923131704331,
|
|
"num_tokens": 5653129.0,
|
|
"step": 2885
|
|
},
|
|
{
|
|
"entropy": 6.714034366607666,
|
|
"epoch": 0.28889888539011344,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004995961197144254,
|
|
"loss": 6.6475,
|
|
"mean_token_accuracy": 0.12331639975309372,
|
|
"num_tokens": 5662834.0,
|
|
"step": 2890
|
|
},
|
|
{
|
|
"entropy": 6.715389919281006,
|
|
"epoch": 0.289398710451342,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000499593979464941,
|
|
"loss": 6.5933,
|
|
"mean_token_accuracy": 0.13576119020581245,
|
|
"num_tokens": 5672393.0,
|
|
"step": 2895
|
|
},
|
|
{
|
|
"entropy": 6.6997795581817625,
|
|
"epoch": 0.2898985355125706,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004995918335647298,
|
|
"loss": 6.7143,
|
|
"mean_token_accuracy": 0.12798105850815772,
|
|
"num_tokens": 5683189.0,
|
|
"step": 2900
|
|
},
|
|
{
|
|
"entropy": 6.763655710220337,
|
|
"epoch": 0.2903983605737992,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004995896820138459,
|
|
"loss": 6.6676,
|
|
"mean_token_accuracy": 0.12548011690378189,
|
|
"num_tokens": 5692999.0,
|
|
"step": 2905
|
|
},
|
|
{
|
|
"entropy": 6.654674625396728,
|
|
"epoch": 0.29089818563502773,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004995875248123434,
|
|
"loss": 6.6322,
|
|
"mean_token_accuracy": 0.1301705814898014,
|
|
"num_tokens": 5701707.0,
|
|
"step": 2910
|
|
},
|
|
{
|
|
"entropy": 6.656778240203858,
|
|
"epoch": 0.2913980106962563,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004995853619602766,
|
|
"loss": 6.5872,
|
|
"mean_token_accuracy": 0.1278572127223015,
|
|
"num_tokens": 5711824.0,
|
|
"step": 2915
|
|
},
|
|
{
|
|
"entropy": 6.718242835998535,
|
|
"epoch": 0.2918978357574849,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004995831934576998,
|
|
"loss": 6.7023,
|
|
"mean_token_accuracy": 0.12706222161650657,
|
|
"num_tokens": 5722681.0,
|
|
"step": 2920
|
|
},
|
|
{
|
|
"entropy": 6.7669517993927,
|
|
"epoch": 0.29239766081871343,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004995810193046677,
|
|
"loss": 6.6955,
|
|
"mean_token_accuracy": 0.12328885868191719,
|
|
"num_tokens": 5731806.0,
|
|
"step": 2925
|
|
},
|
|
{
|
|
"entropy": 6.707439041137695,
|
|
"epoch": 0.292897485879942,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000499578839501235,
|
|
"loss": 6.6603,
|
|
"mean_token_accuracy": 0.12864745929837226,
|
|
"num_tokens": 5742144.0,
|
|
"step": 2930
|
|
},
|
|
{
|
|
"entropy": 6.705581617355347,
|
|
"epoch": 0.2933973109411706,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004995766540474564,
|
|
"loss": 6.6626,
|
|
"mean_token_accuracy": 0.1203208550810814,
|
|
"num_tokens": 5752752.0,
|
|
"step": 2935
|
|
},
|
|
{
|
|
"entropy": 6.731801557540893,
|
|
"epoch": 0.29389713600239914,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000499574462943387,
|
|
"loss": 6.6124,
|
|
"mean_token_accuracy": 0.12901480495929718,
|
|
"num_tokens": 5762031.0,
|
|
"step": 2940
|
|
},
|
|
{
|
|
"entropy": 6.616041278839111,
|
|
"epoch": 0.2943969610636277,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000499572266189082,
|
|
"loss": 6.5485,
|
|
"mean_token_accuracy": 0.128142399340868,
|
|
"num_tokens": 5772160.0,
|
|
"step": 2945
|
|
},
|
|
{
|
|
"entropy": 6.778317594528199,
|
|
"epoch": 0.2948967861248563,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004995700637845964,
|
|
"loss": 6.6606,
|
|
"mean_token_accuracy": 0.1271796479821205,
|
|
"num_tokens": 5782145.0,
|
|
"step": 2950
|
|
},
|
|
{
|
|
"entropy": 6.600551319122315,
|
|
"epoch": 0.29539661118608485,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004995678557299859,
|
|
"loss": 6.5148,
|
|
"mean_token_accuracy": 0.13630254417657853,
|
|
"num_tokens": 5790889.0,
|
|
"step": 2955
|
|
},
|
|
{
|
|
"entropy": 6.717923641204834,
|
|
"epoch": 0.29589643624731343,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004995656420253058,
|
|
"loss": 6.6642,
|
|
"mean_token_accuracy": 0.1262128658592701,
|
|
"num_tokens": 5801239.0,
|
|
"step": 2960
|
|
},
|
|
{
|
|
"entropy": 6.854567575454712,
|
|
"epoch": 0.296396261308542,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000499563422670612,
|
|
"loss": 6.7637,
|
|
"mean_token_accuracy": 0.12252128720283509,
|
|
"num_tokens": 5811390.0,
|
|
"step": 2965
|
|
},
|
|
{
|
|
"entropy": 6.738302850723267,
|
|
"epoch": 0.2968960863697706,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004995611976659604,
|
|
"loss": 6.7237,
|
|
"mean_token_accuracy": 0.11966272965073585,
|
|
"num_tokens": 5821529.0,
|
|
"step": 2970
|
|
},
|
|
{
|
|
"entropy": 6.708627653121948,
|
|
"epoch": 0.29739591143099914,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004995589670114067,
|
|
"loss": 6.6697,
|
|
"mean_token_accuracy": 0.12530870959162713,
|
|
"num_tokens": 5830551.0,
|
|
"step": 2975
|
|
},
|
|
{
|
|
"entropy": 6.744061517715454,
|
|
"epoch": 0.2978957364922277,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004995567307070072,
|
|
"loss": 6.6927,
|
|
"mean_token_accuracy": 0.1294789083302021,
|
|
"num_tokens": 5840768.0,
|
|
"step": 2980
|
|
},
|
|
{
|
|
"entropy": 6.7781086444854735,
|
|
"epoch": 0.2983955615534563,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004995544887528182,
|
|
"loss": 6.7099,
|
|
"mean_token_accuracy": 0.11977946162223815,
|
|
"num_tokens": 5850515.0,
|
|
"step": 2985
|
|
},
|
|
{
|
|
"entropy": 6.709803867340088,
|
|
"epoch": 0.29889538661468484,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004995522411488959,
|
|
"loss": 6.6054,
|
|
"mean_token_accuracy": 0.13315768986940385,
|
|
"num_tokens": 5859480.0,
|
|
"step": 2990
|
|
},
|
|
{
|
|
"entropy": 6.7460136890411375,
|
|
"epoch": 0.29939521167591343,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004995499878952971,
|
|
"loss": 6.6644,
|
|
"mean_token_accuracy": 0.12363893687725067,
|
|
"num_tokens": 5871255.0,
|
|
"step": 2995
|
|
},
|
|
{
|
|
"entropy": 6.610029220581055,
|
|
"epoch": 0.299895036737142,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004995477289920784,
|
|
"loss": 6.5893,
|
|
"mean_token_accuracy": 0.1339652419090271,
|
|
"num_tokens": 5881306.0,
|
|
"step": 3000
|
|
},
|
|
{
|
|
"epoch": 0.299895036737142,
|
|
"eval_entropy": 6.529951082188823,
|
|
"eval_loss": 6.702248573303223,
|
|
"eval_mean_token_accuracy": 0.1290466456501981,
|
|
"eval_num_tokens": 5881306.0,
|
|
"eval_runtime": 23.7239,
|
|
"eval_samples_per_second": 1308.597,
|
|
"eval_steps_per_second": 163.59,
|
|
"step": 3000
|
|
},
|
|
{
|
|
"entropy": 6.681021976470947,
|
|
"epoch": 0.30039486179837055,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004995454644392967,
|
|
"loss": 6.6686,
|
|
"mean_token_accuracy": 0.1230406939983368,
|
|
"num_tokens": 5891209.0,
|
|
"step": 3005
|
|
},
|
|
{
|
|
"entropy": 6.797600841522216,
|
|
"epoch": 0.30089468685959914,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004995431942370087,
|
|
"loss": 6.7259,
|
|
"mean_token_accuracy": 0.12509791404008866,
|
|
"num_tokens": 5902003.0,
|
|
"step": 3010
|
|
},
|
|
{
|
|
"entropy": 6.776391315460205,
|
|
"epoch": 0.3013945119208277,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004995409183852718,
|
|
"loss": 6.6609,
|
|
"mean_token_accuracy": 0.12573762908577918,
|
|
"num_tokens": 5911327.0,
|
|
"step": 3015
|
|
},
|
|
{
|
|
"entropy": 6.587473058700562,
|
|
"epoch": 0.30189433698205626,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004995386368841432,
|
|
"loss": 6.5949,
|
|
"mean_token_accuracy": 0.13132134079933167,
|
|
"num_tokens": 5920385.0,
|
|
"step": 3020
|
|
},
|
|
{
|
|
"entropy": 6.644120168685913,
|
|
"epoch": 0.30239416204328484,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004995363497336802,
|
|
"loss": 6.5472,
|
|
"mean_token_accuracy": 0.13319996371865273,
|
|
"num_tokens": 5929784.0,
|
|
"step": 3025
|
|
},
|
|
{
|
|
"entropy": 6.675529146194458,
|
|
"epoch": 0.30289398710451343,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004995340569339405,
|
|
"loss": 6.6351,
|
|
"mean_token_accuracy": 0.1254398010671139,
|
|
"num_tokens": 5938766.0,
|
|
"step": 3030
|
|
},
|
|
{
|
|
"entropy": 6.780316305160523,
|
|
"epoch": 0.303393812165742,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004995317584849817,
|
|
"loss": 6.7465,
|
|
"mean_token_accuracy": 0.12507161349058152,
|
|
"num_tokens": 5948869.0,
|
|
"step": 3035
|
|
},
|
|
{
|
|
"entropy": 6.685397911071777,
|
|
"epoch": 0.30389363722697055,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004995294543868615,
|
|
"loss": 6.5529,
|
|
"mean_token_accuracy": 0.12421033307909965,
|
|
"num_tokens": 5959074.0,
|
|
"step": 3040
|
|
},
|
|
{
|
|
"entropy": 6.659611654281616,
|
|
"epoch": 0.30439346228819913,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004995271446396382,
|
|
"loss": 6.6669,
|
|
"mean_token_accuracy": 0.12645429074764253,
|
|
"num_tokens": 5968608.0,
|
|
"step": 3045
|
|
},
|
|
{
|
|
"entropy": 6.73339958190918,
|
|
"epoch": 0.3048932873494277,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004995248292433697,
|
|
"loss": 6.6962,
|
|
"mean_token_accuracy": 0.11696835681796074,
|
|
"num_tokens": 5979756.0,
|
|
"step": 3050
|
|
},
|
|
{
|
|
"entropy": 6.779122972488404,
|
|
"epoch": 0.30539311241065625,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004995225081981142,
|
|
"loss": 6.7665,
|
|
"mean_token_accuracy": 0.11112019196152687,
|
|
"num_tokens": 5990299.0,
|
|
"step": 3055
|
|
},
|
|
{
|
|
"entropy": 6.774257707595825,
|
|
"epoch": 0.30589293747188484,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004995201815039301,
|
|
"loss": 6.6607,
|
|
"mean_token_accuracy": 0.11963343843817711,
|
|
"num_tokens": 6001721.0,
|
|
"step": 3060
|
|
},
|
|
{
|
|
"entropy": 6.6790704250335695,
|
|
"epoch": 0.3063927625331134,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004995178491608762,
|
|
"loss": 6.7327,
|
|
"mean_token_accuracy": 0.12029238194227218,
|
|
"num_tokens": 6012658.0,
|
|
"step": 3065
|
|
},
|
|
{
|
|
"entropy": 6.768873167037964,
|
|
"epoch": 0.30689258759434196,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004995155111690107,
|
|
"loss": 6.6766,
|
|
"mean_token_accuracy": 0.12649752125144004,
|
|
"num_tokens": 6022470.0,
|
|
"step": 3070
|
|
},
|
|
{
|
|
"entropy": 6.687690401077271,
|
|
"epoch": 0.30739241265557055,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.000499513167528393,
|
|
"loss": 6.5548,
|
|
"mean_token_accuracy": 0.1281000018119812,
|
|
"num_tokens": 6034227.0,
|
|
"step": 3075
|
|
},
|
|
{
|
|
"entropy": 6.632200527191162,
|
|
"epoch": 0.30789223771679913,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004995108182390815,
|
|
"loss": 6.5696,
|
|
"mean_token_accuracy": 0.12978074327111244,
|
|
"num_tokens": 6043122.0,
|
|
"step": 3080
|
|
},
|
|
{
|
|
"entropy": 6.67748007774353,
|
|
"epoch": 0.30839206277802766,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004995084633011359,
|
|
"loss": 6.5892,
|
|
"mean_token_accuracy": 0.12593309059739113,
|
|
"num_tokens": 6052988.0,
|
|
"step": 3085
|
|
},
|
|
{
|
|
"entropy": 6.651902532577514,
|
|
"epoch": 0.30889188783925625,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000499506102714615,
|
|
"loss": 6.6284,
|
|
"mean_token_accuracy": 0.12826041579246522,
|
|
"num_tokens": 6062800.0,
|
|
"step": 3090
|
|
},
|
|
{
|
|
"entropy": 6.814677333831787,
|
|
"epoch": 0.30939171290048484,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004995037364795782,
|
|
"loss": 6.7035,
|
|
"mean_token_accuracy": 0.1235254593193531,
|
|
"num_tokens": 6071327.0,
|
|
"step": 3095
|
|
},
|
|
{
|
|
"entropy": 6.7643333911895756,
|
|
"epoch": 0.3098915379617134,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004995013645960853,
|
|
"loss": 6.7053,
|
|
"mean_token_accuracy": 0.12090670987963677,
|
|
"num_tokens": 6080574.0,
|
|
"step": 3100
|
|
},
|
|
{
|
|
"entropy": 6.6897650241851805,
|
|
"epoch": 0.31039136302294196,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004994989870641958,
|
|
"loss": 6.6029,
|
|
"mean_token_accuracy": 0.12805371433496476,
|
|
"num_tokens": 6088081.0,
|
|
"step": 3105
|
|
},
|
|
{
|
|
"entropy": 6.722474527359009,
|
|
"epoch": 0.31089118808417054,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004994966038839695,
|
|
"loss": 6.7177,
|
|
"mean_token_accuracy": 0.12565394565463067,
|
|
"num_tokens": 6097785.0,
|
|
"step": 3110
|
|
},
|
|
{
|
|
"entropy": 6.713695383071899,
|
|
"epoch": 0.31139101314539913,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004994942150554666,
|
|
"loss": 6.6408,
|
|
"mean_token_accuracy": 0.12528237476944923,
|
|
"num_tokens": 6107402.0,
|
|
"step": 3115
|
|
},
|
|
{
|
|
"entropy": 6.668991994857788,
|
|
"epoch": 0.31189083820662766,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004994918205787468,
|
|
"loss": 6.5943,
|
|
"mean_token_accuracy": 0.12502402663230897,
|
|
"num_tokens": 6116439.0,
|
|
"step": 3120
|
|
},
|
|
{
|
|
"entropy": 6.699170875549316,
|
|
"epoch": 0.31239066326785625,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004994894204538706,
|
|
"loss": 6.6482,
|
|
"mean_token_accuracy": 0.13096092343330384,
|
|
"num_tokens": 6126854.0,
|
|
"step": 3125
|
|
},
|
|
{
|
|
"entropy": 6.679208469390869,
|
|
"epoch": 0.31289048832908484,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004994870146808984,
|
|
"loss": 6.5964,
|
|
"mean_token_accuracy": 0.12942466214299203,
|
|
"num_tokens": 6136869.0,
|
|
"step": 3130
|
|
},
|
|
{
|
|
"entropy": 6.625993967056274,
|
|
"epoch": 0.31339031339031337,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004994846032598906,
|
|
"loss": 6.5813,
|
|
"mean_token_accuracy": 0.1329791858792305,
|
|
"num_tokens": 6146772.0,
|
|
"step": 3135
|
|
},
|
|
{
|
|
"entropy": 6.709695720672608,
|
|
"epoch": 0.31389013845154196,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004994821861909082,
|
|
"loss": 6.6718,
|
|
"mean_token_accuracy": 0.12659213691949844,
|
|
"num_tokens": 6156329.0,
|
|
"step": 3140
|
|
},
|
|
{
|
|
"entropy": 6.67364616394043,
|
|
"epoch": 0.31438996351277054,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004994797634740114,
|
|
"loss": 6.5739,
|
|
"mean_token_accuracy": 0.12842462211847305,
|
|
"num_tokens": 6166198.0,
|
|
"step": 3145
|
|
},
|
|
{
|
|
"entropy": 6.628734970092774,
|
|
"epoch": 0.3148897885739991,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004994773351092618,
|
|
"loss": 6.6481,
|
|
"mean_token_accuracy": 0.12540496289730071,
|
|
"num_tokens": 6176180.0,
|
|
"step": 3150
|
|
},
|
|
{
|
|
"entropy": 6.687831735610962,
|
|
"epoch": 0.31538961363522766,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00049947490109672,
|
|
"loss": 6.5962,
|
|
"mean_token_accuracy": 0.1281987413764,
|
|
"num_tokens": 6185776.0,
|
|
"step": 3155
|
|
},
|
|
{
|
|
"entropy": 6.728115272521973,
|
|
"epoch": 0.31588943869645625,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004994724614364476,
|
|
"loss": 6.7325,
|
|
"mean_token_accuracy": 0.12246878519654274,
|
|
"num_tokens": 6196472.0,
|
|
"step": 3160
|
|
},
|
|
{
|
|
"entropy": 6.630450296401977,
|
|
"epoch": 0.31638926375768484,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004994700161285058,
|
|
"loss": 6.5934,
|
|
"mean_token_accuracy": 0.1263155981898308,
|
|
"num_tokens": 6206064.0,
|
|
"step": 3165
|
|
},
|
|
{
|
|
"entropy": 6.755979919433594,
|
|
"epoch": 0.31688908881891337,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000499467565172956,
|
|
"loss": 6.6224,
|
|
"mean_token_accuracy": 0.129413178563118,
|
|
"num_tokens": 6217044.0,
|
|
"step": 3170
|
|
},
|
|
{
|
|
"entropy": 6.671145963668823,
|
|
"epoch": 0.31738891388014195,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004994651085698602,
|
|
"loss": 6.6066,
|
|
"mean_token_accuracy": 0.12426463291049003,
|
|
"num_tokens": 6228294.0,
|
|
"step": 3175
|
|
},
|
|
{
|
|
"entropy": 6.670057916641236,
|
|
"epoch": 0.31788873894137054,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00049946264631928,
|
|
"loss": 6.5465,
|
|
"mean_token_accuracy": 0.1360152244567871,
|
|
"num_tokens": 6238525.0,
|
|
"step": 3180
|
|
},
|
|
{
|
|
"entropy": 6.499093770980835,
|
|
"epoch": 0.3183885640025991,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004994601784212774,
|
|
"loss": 6.4419,
|
|
"mean_token_accuracy": 0.13964417427778245,
|
|
"num_tokens": 6247457.0,
|
|
"step": 3185
|
|
},
|
|
{
|
|
"entropy": 6.5308064937591555,
|
|
"epoch": 0.31888838906382766,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004994577048759144,
|
|
"loss": 6.573,
|
|
"mean_token_accuracy": 0.13198508694767952,
|
|
"num_tokens": 6256414.0,
|
|
"step": 3190
|
|
},
|
|
{
|
|
"entropy": 6.607933044433594,
|
|
"epoch": 0.31938821412505625,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004994552256832533,
|
|
"loss": 6.5048,
|
|
"mean_token_accuracy": 0.13686242029070855,
|
|
"num_tokens": 6266093.0,
|
|
"step": 3195
|
|
},
|
|
{
|
|
"entropy": 6.649296379089355,
|
|
"epoch": 0.3198880391862848,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004994527408433566,
|
|
"loss": 6.5681,
|
|
"mean_token_accuracy": 0.13355113565921783,
|
|
"num_tokens": 6276340.0,
|
|
"step": 3200
|
|
},
|
|
{
|
|
"entropy": 6.617343235015869,
|
|
"epoch": 0.32038786424751337,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004994502503562865,
|
|
"loss": 6.5877,
|
|
"mean_token_accuracy": 0.12834486067295076,
|
|
"num_tokens": 6285044.0,
|
|
"step": 3205
|
|
},
|
|
{
|
|
"entropy": 6.681250047683716,
|
|
"epoch": 0.32088768930874195,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000499447754222106,
|
|
"loss": 6.5154,
|
|
"mean_token_accuracy": 0.1330440990626812,
|
|
"num_tokens": 6294105.0,
|
|
"step": 3210
|
|
},
|
|
{
|
|
"entropy": 6.555824518203735,
|
|
"epoch": 0.3213875143699705,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004994452524408777,
|
|
"loss": 6.5729,
|
|
"mean_token_accuracy": 0.12900223657488824,
|
|
"num_tokens": 6302503.0,
|
|
"step": 3215
|
|
},
|
|
{
|
|
"entropy": 6.677013397216797,
|
|
"epoch": 0.32188733943119907,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004994427450126646,
|
|
"loss": 6.5874,
|
|
"mean_token_accuracy": 0.12441989108920097,
|
|
"num_tokens": 6313068.0,
|
|
"step": 3220
|
|
},
|
|
{
|
|
"entropy": 6.760306739807129,
|
|
"epoch": 0.32238716449242766,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004994402319375298,
|
|
"loss": 6.6682,
|
|
"mean_token_accuracy": 0.12115811482071877,
|
|
"num_tokens": 6322770.0,
|
|
"step": 3225
|
|
},
|
|
{
|
|
"entropy": 6.5807883739471436,
|
|
"epoch": 0.32288698955365625,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004994377132155366,
|
|
"loss": 6.5463,
|
|
"mean_token_accuracy": 0.13018904775381088,
|
|
"num_tokens": 6333055.0,
|
|
"step": 3230
|
|
},
|
|
{
|
|
"entropy": 6.49958643913269,
|
|
"epoch": 0.3233868146148848,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004994351888467482,
|
|
"loss": 6.5625,
|
|
"mean_token_accuracy": 0.13032179921865464,
|
|
"num_tokens": 6342780.0,
|
|
"step": 3235
|
|
},
|
|
{
|
|
"entropy": 6.701545906066895,
|
|
"epoch": 0.32388663967611336,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004994326588312282,
|
|
"loss": 6.5456,
|
|
"mean_token_accuracy": 0.12095091342926026,
|
|
"num_tokens": 6352021.0,
|
|
"step": 3240
|
|
},
|
|
{
|
|
"entropy": 6.605896663665772,
|
|
"epoch": 0.32438646473734195,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004994301231690403,
|
|
"loss": 6.62,
|
|
"mean_token_accuracy": 0.12656017392873764,
|
|
"num_tokens": 6361062.0,
|
|
"step": 3245
|
|
},
|
|
{
|
|
"entropy": 6.672325706481933,
|
|
"epoch": 0.3248862897985705,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004994275818602482,
|
|
"loss": 6.6412,
|
|
"mean_token_accuracy": 0.12171561419963836,
|
|
"num_tokens": 6371318.0,
|
|
"step": 3250
|
|
},
|
|
{
|
|
"entropy": 6.815335893630982,
|
|
"epoch": 0.32538611485979907,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004994250349049159,
|
|
"loss": 6.7133,
|
|
"mean_token_accuracy": 0.12552304565906525,
|
|
"num_tokens": 6381078.0,
|
|
"step": 3255
|
|
},
|
|
{
|
|
"entropy": 6.70945520401001,
|
|
"epoch": 0.32588593992102766,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004994224823031075,
|
|
"loss": 6.5515,
|
|
"mean_token_accuracy": 0.13201567009091378,
|
|
"num_tokens": 6390382.0,
|
|
"step": 3260
|
|
},
|
|
{
|
|
"entropy": 6.613358116149902,
|
|
"epoch": 0.3263857649822562,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004994199240548873,
|
|
"loss": 6.6023,
|
|
"mean_token_accuracy": 0.12341969534754753,
|
|
"num_tokens": 6399849.0,
|
|
"step": 3265
|
|
},
|
|
{
|
|
"entropy": 6.684066915512085,
|
|
"epoch": 0.3268855900434848,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004994173601603194,
|
|
"loss": 6.6252,
|
|
"mean_token_accuracy": 0.12377856075763702,
|
|
"num_tokens": 6409150.0,
|
|
"step": 3270
|
|
},
|
|
{
|
|
"entropy": 6.724408197402954,
|
|
"epoch": 0.32738541510471336,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004994147906194684,
|
|
"loss": 6.6265,
|
|
"mean_token_accuracy": 0.12532238364219667,
|
|
"num_tokens": 6419525.0,
|
|
"step": 3275
|
|
},
|
|
{
|
|
"entropy": 6.663235378265381,
|
|
"epoch": 0.3278852401659419,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004994122154323992,
|
|
"loss": 6.5806,
|
|
"mean_token_accuracy": 0.12679464221000672,
|
|
"num_tokens": 6430185.0,
|
|
"step": 3280
|
|
},
|
|
{
|
|
"entropy": 6.722297477722168,
|
|
"epoch": 0.3283850652271705,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004994096345991763,
|
|
"loss": 6.5563,
|
|
"mean_token_accuracy": 0.12995896786451339,
|
|
"num_tokens": 6440221.0,
|
|
"step": 3285
|
|
},
|
|
{
|
|
"entropy": 6.607683229446411,
|
|
"epoch": 0.32888489028839907,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004994070481198649,
|
|
"loss": 6.6327,
|
|
"mean_token_accuracy": 0.12762965336441995,
|
|
"num_tokens": 6448861.0,
|
|
"step": 3290
|
|
},
|
|
{
|
|
"entropy": 6.682978582382202,
|
|
"epoch": 0.32938471534962765,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004994044559945296,
|
|
"loss": 6.5257,
|
|
"mean_token_accuracy": 0.12889787256717683,
|
|
"num_tokens": 6458782.0,
|
|
"step": 3295
|
|
},
|
|
{
|
|
"entropy": 6.590939092636108,
|
|
"epoch": 0.3298845404108562,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004994018582232361,
|
|
"loss": 6.5764,
|
|
"mean_token_accuracy": 0.1253158003091812,
|
|
"num_tokens": 6470201.0,
|
|
"step": 3300
|
|
},
|
|
{
|
|
"entropy": 6.598582696914673,
|
|
"epoch": 0.3303843654720848,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004993992548060497,
|
|
"loss": 6.6021,
|
|
"mean_token_accuracy": 0.1266971670091152,
|
|
"num_tokens": 6479507.0,
|
|
"step": 3305
|
|
},
|
|
{
|
|
"entropy": 6.683953285217285,
|
|
"epoch": 0.33088419053331336,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004993966457430357,
|
|
"loss": 6.6047,
|
|
"mean_token_accuracy": 0.13037028759717942,
|
|
"num_tokens": 6488902.0,
|
|
"step": 3310
|
|
},
|
|
{
|
|
"entropy": 6.6829265594482425,
|
|
"epoch": 0.3313840155945419,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004993940310342598,
|
|
"loss": 6.5886,
|
|
"mean_token_accuracy": 0.13307278156280516,
|
|
"num_tokens": 6498781.0,
|
|
"step": 3315
|
|
},
|
|
{
|
|
"entropy": 6.58431830406189,
|
|
"epoch": 0.3318838406557705,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004993914106797879,
|
|
"loss": 6.5041,
|
|
"mean_token_accuracy": 0.13261542543768884,
|
|
"num_tokens": 6507358.0,
|
|
"step": 3320
|
|
},
|
|
{
|
|
"entropy": 6.600981760025024,
|
|
"epoch": 0.33238366571699907,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004993887846796858,
|
|
"loss": 6.5627,
|
|
"mean_token_accuracy": 0.1347931757569313,
|
|
"num_tokens": 6517976.0,
|
|
"step": 3325
|
|
},
|
|
{
|
|
"entropy": 6.740728521347046,
|
|
"epoch": 0.3328834907782276,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004993861530340196,
|
|
"loss": 6.6813,
|
|
"mean_token_accuracy": 0.11708623915910721,
|
|
"num_tokens": 6528407.0,
|
|
"step": 3330
|
|
},
|
|
{
|
|
"entropy": 6.799725008010864,
|
|
"epoch": 0.3333833158394562,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004993835157428555,
|
|
"loss": 6.5809,
|
|
"mean_token_accuracy": 0.12460994869470596,
|
|
"num_tokens": 6537619.0,
|
|
"step": 3335
|
|
},
|
|
{
|
|
"entropy": 6.518185138702393,
|
|
"epoch": 0.33388314090068477,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004993808728062599,
|
|
"loss": 6.4912,
|
|
"mean_token_accuracy": 0.1300904169678688,
|
|
"num_tokens": 6548393.0,
|
|
"step": 3340
|
|
},
|
|
{
|
|
"entropy": 6.65168776512146,
|
|
"epoch": 0.3343829659619133,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004993782242242994,
|
|
"loss": 6.5803,
|
|
"mean_token_accuracy": 0.13166460916399955,
|
|
"num_tokens": 6558646.0,
|
|
"step": 3345
|
|
},
|
|
{
|
|
"entropy": 6.66806435585022,
|
|
"epoch": 0.3348827910231419,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004993755699970404,
|
|
"loss": 6.5693,
|
|
"mean_token_accuracy": 0.13037904500961303,
|
|
"num_tokens": 6567534.0,
|
|
"step": 3350
|
|
},
|
|
{
|
|
"entropy": 6.610126113891601,
|
|
"epoch": 0.3353826160843705,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004993729101245498,
|
|
"loss": 6.5987,
|
|
"mean_token_accuracy": 0.13262755200266838,
|
|
"num_tokens": 6577940.0,
|
|
"step": 3355
|
|
},
|
|
{
|
|
"entropy": 6.6294848918914795,
|
|
"epoch": 0.33588244114559906,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004993702446068945,
|
|
"loss": 6.6147,
|
|
"mean_token_accuracy": 0.12785486727952958,
|
|
"num_tokens": 6587421.0,
|
|
"step": 3360
|
|
},
|
|
{
|
|
"entropy": 6.703089475631714,
|
|
"epoch": 0.3363822662068276,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004993675734441416,
|
|
"loss": 6.5881,
|
|
"mean_token_accuracy": 0.12631361037492753,
|
|
"num_tokens": 6597509.0,
|
|
"step": 3365
|
|
},
|
|
{
|
|
"entropy": 6.6260514736175535,
|
|
"epoch": 0.3368820912680562,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004993648966363583,
|
|
"loss": 6.5338,
|
|
"mean_token_accuracy": 0.1388427048921585,
|
|
"num_tokens": 6607003.0,
|
|
"step": 3370
|
|
},
|
|
{
|
|
"entropy": 6.511269807815552,
|
|
"epoch": 0.33738191632928477,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000499362214183612,
|
|
"loss": 6.5903,
|
|
"mean_token_accuracy": 0.13173537701368332,
|
|
"num_tokens": 6617454.0,
|
|
"step": 3375
|
|
},
|
|
{
|
|
"entropy": 6.572839879989624,
|
|
"epoch": 0.3378817413905133,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00049935952608597,
|
|
"loss": 6.5478,
|
|
"mean_token_accuracy": 0.13501427173614503,
|
|
"num_tokens": 6628327.0,
|
|
"step": 3380
|
|
},
|
|
{
|
|
"entropy": 6.63575119972229,
|
|
"epoch": 0.3383815664517419,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004993568323435002,
|
|
"loss": 6.5033,
|
|
"mean_token_accuracy": 0.1291576936841011,
|
|
"num_tokens": 6638282.0,
|
|
"step": 3385
|
|
},
|
|
{
|
|
"entropy": 6.588334560394287,
|
|
"epoch": 0.3388813915129705,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004993541329562702,
|
|
"loss": 6.4992,
|
|
"mean_token_accuracy": 0.134891277551651,
|
|
"num_tokens": 6647138.0,
|
|
"step": 3390
|
|
},
|
|
{
|
|
"entropy": 6.609392261505127,
|
|
"epoch": 0.339381216574199,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004993514279243477,
|
|
"loss": 6.5918,
|
|
"mean_token_accuracy": 0.12653654739260672,
|
|
"num_tokens": 6656129.0,
|
|
"step": 3395
|
|
},
|
|
{
|
|
"entropy": 6.626824617385864,
|
|
"epoch": 0.3398810416354276,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004993487172478012,
|
|
"loss": 6.5766,
|
|
"mean_token_accuracy": 0.13372050300240518,
|
|
"num_tokens": 6666485.0,
|
|
"step": 3400
|
|
},
|
|
{
|
|
"entropy": 6.744373178482055,
|
|
"epoch": 0.3403808666966562,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004993460009266988,
|
|
"loss": 6.6583,
|
|
"mean_token_accuracy": 0.12640992775559426,
|
|
"num_tokens": 6676885.0,
|
|
"step": 3405
|
|
},
|
|
{
|
|
"entropy": 6.656079721450806,
|
|
"epoch": 0.3408806917578847,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004993432789611086,
|
|
"loss": 6.5465,
|
|
"mean_token_accuracy": 0.13199173286557198,
|
|
"num_tokens": 6687309.0,
|
|
"step": 3410
|
|
},
|
|
{
|
|
"entropy": 6.588942384719848,
|
|
"epoch": 0.3413805168191133,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004993405513510992,
|
|
"loss": 6.6823,
|
|
"mean_token_accuracy": 0.1306323938071728,
|
|
"num_tokens": 6696868.0,
|
|
"step": 3415
|
|
},
|
|
{
|
|
"entropy": 6.7879961967468265,
|
|
"epoch": 0.3418803418803419,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004993378180967394,
|
|
"loss": 6.6172,
|
|
"mean_token_accuracy": 0.13136079236865045,
|
|
"num_tokens": 6706526.0,
|
|
"step": 3420
|
|
},
|
|
{
|
|
"entropy": 6.6939380168914795,
|
|
"epoch": 0.3423801669415705,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004993350791980978,
|
|
"loss": 6.6379,
|
|
"mean_token_accuracy": 0.12985037490725518,
|
|
"num_tokens": 6716792.0,
|
|
"step": 3425
|
|
},
|
|
{
|
|
"entropy": 6.478039693832398,
|
|
"epoch": 0.342879992002799,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004993323346552433,
|
|
"loss": 6.4695,
|
|
"mean_token_accuracy": 0.137115740776062,
|
|
"num_tokens": 6726268.0,
|
|
"step": 3430
|
|
},
|
|
{
|
|
"entropy": 6.616924524307251,
|
|
"epoch": 0.3433798170640276,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004993295844682449,
|
|
"loss": 6.563,
|
|
"mean_token_accuracy": 0.1286364048719406,
|
|
"num_tokens": 6735687.0,
|
|
"step": 3435
|
|
},
|
|
{
|
|
"entropy": 6.569231176376343,
|
|
"epoch": 0.3438796421252562,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.000499326828637172,
|
|
"loss": 6.3953,
|
|
"mean_token_accuracy": 0.1459199793636799,
|
|
"num_tokens": 6747055.0,
|
|
"step": 3440
|
|
},
|
|
{
|
|
"entropy": 6.508210897445679,
|
|
"epoch": 0.3443794671864847,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004993240671620938,
|
|
"loss": 6.5133,
|
|
"mean_token_accuracy": 0.1337944194674492,
|
|
"num_tokens": 6756190.0,
|
|
"step": 3445
|
|
},
|
|
{
|
|
"entropy": 6.681909513473511,
|
|
"epoch": 0.3448792922477133,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004993213000430797,
|
|
"loss": 6.6284,
|
|
"mean_token_accuracy": 0.12544018179178237,
|
|
"num_tokens": 6766145.0,
|
|
"step": 3450
|
|
},
|
|
{
|
|
"entropy": 6.676771545410157,
|
|
"epoch": 0.3453791173089419,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004993185272801995,
|
|
"loss": 6.5238,
|
|
"mean_token_accuracy": 0.13093370348215103,
|
|
"num_tokens": 6776294.0,
|
|
"step": 3455
|
|
},
|
|
{
|
|
"entropy": 6.61463098526001,
|
|
"epoch": 0.3458789423701704,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004993157488735228,
|
|
"loss": 6.5721,
|
|
"mean_token_accuracy": 0.1304081656038761,
|
|
"num_tokens": 6785349.0,
|
|
"step": 3460
|
|
},
|
|
{
|
|
"entropy": 6.556643724441528,
|
|
"epoch": 0.346378767431399,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004993129648231197,
|
|
"loss": 6.4718,
|
|
"mean_token_accuracy": 0.1271122671663761,
|
|
"num_tokens": 6794733.0,
|
|
"step": 3465
|
|
},
|
|
{
|
|
"entropy": 6.679942560195923,
|
|
"epoch": 0.3468785924926276,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00049931017512906,
|
|
"loss": 6.5658,
|
|
"mean_token_accuracy": 0.1287422724068165,
|
|
"num_tokens": 6803850.0,
|
|
"step": 3470
|
|
},
|
|
{
|
|
"entropy": 6.58225417137146,
|
|
"epoch": 0.3473784175538562,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004993073797914141,
|
|
"loss": 6.4847,
|
|
"mean_token_accuracy": 0.13215459883213043,
|
|
"num_tokens": 6813201.0,
|
|
"step": 3475
|
|
},
|
|
{
|
|
"entropy": 6.512684631347656,
|
|
"epoch": 0.3478782426150847,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004993045788102522,
|
|
"loss": 6.4682,
|
|
"mean_token_accuracy": 0.13046691417694092,
|
|
"num_tokens": 6822238.0,
|
|
"step": 3480
|
|
},
|
|
{
|
|
"entropy": 6.667408657073975,
|
|
"epoch": 0.3483780676763133,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004993017721856449,
|
|
"loss": 6.5978,
|
|
"mean_token_accuracy": 0.12310194596648216,
|
|
"num_tokens": 6832586.0,
|
|
"step": 3485
|
|
},
|
|
{
|
|
"entropy": 6.626319503784179,
|
|
"epoch": 0.3488778927375419,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004992989599176626,
|
|
"loss": 6.5654,
|
|
"mean_token_accuracy": 0.12846530228853226,
|
|
"num_tokens": 6841699.0,
|
|
"step": 3490
|
|
},
|
|
{
|
|
"entropy": 6.644284200668335,
|
|
"epoch": 0.3493777177987704,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004992961420063763,
|
|
"loss": 6.6131,
|
|
"mean_token_accuracy": 0.12847285494208335,
|
|
"num_tokens": 6851455.0,
|
|
"step": 3495
|
|
},
|
|
{
|
|
"entropy": 6.666490936279297,
|
|
"epoch": 0.349877542859999,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004992933184518567,
|
|
"loss": 6.524,
|
|
"mean_token_accuracy": 0.13283096253871918,
|
|
"num_tokens": 6860646.0,
|
|
"step": 3500
|
|
},
|
|
{
|
|
"entropy": 6.571482467651367,
|
|
"epoch": 0.3503773679212276,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004992904892541749,
|
|
"loss": 6.6076,
|
|
"mean_token_accuracy": 0.1293070636689663,
|
|
"num_tokens": 6870641.0,
|
|
"step": 3505
|
|
},
|
|
{
|
|
"entropy": 6.676307153701782,
|
|
"epoch": 0.3508771929824561,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004992876544134022,
|
|
"loss": 6.6352,
|
|
"mean_token_accuracy": 0.12403724417090416,
|
|
"num_tokens": 6880831.0,
|
|
"step": 3510
|
|
},
|
|
{
|
|
"entropy": 6.666634845733642,
|
|
"epoch": 0.3513770180436847,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004992848139296098,
|
|
"loss": 6.6234,
|
|
"mean_token_accuracy": 0.12937338277697563,
|
|
"num_tokens": 6890305.0,
|
|
"step": 3515
|
|
},
|
|
{
|
|
"entropy": 6.595576810836792,
|
|
"epoch": 0.3518768431049133,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004992819678028692,
|
|
"loss": 6.4999,
|
|
"mean_token_accuracy": 0.1348331443965435,
|
|
"num_tokens": 6900147.0,
|
|
"step": 3520
|
|
},
|
|
{
|
|
"entropy": 6.579501390457153,
|
|
"epoch": 0.3523766681661418,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.000499279116033252,
|
|
"loss": 6.4869,
|
|
"mean_token_accuracy": 0.13790729492902756,
|
|
"num_tokens": 6910367.0,
|
|
"step": 3525
|
|
},
|
|
{
|
|
"entropy": 6.558926105499268,
|
|
"epoch": 0.3528764932273704,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004992762586208299,
|
|
"loss": 6.4736,
|
|
"mean_token_accuracy": 0.13376323729753495,
|
|
"num_tokens": 6919843.0,
|
|
"step": 3530
|
|
},
|
|
{
|
|
"entropy": 6.577578544616699,
|
|
"epoch": 0.353376318288599,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004992733955656749,
|
|
"loss": 6.5312,
|
|
"mean_token_accuracy": 0.130813892185688,
|
|
"num_tokens": 6929912.0,
|
|
"step": 3535
|
|
},
|
|
{
|
|
"entropy": 6.646571493148803,
|
|
"epoch": 0.3538761433498276,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004992705268678589,
|
|
"loss": 6.6069,
|
|
"mean_token_accuracy": 0.1239285834133625,
|
|
"num_tokens": 6940836.0,
|
|
"step": 3540
|
|
},
|
|
{
|
|
"entropy": 6.639316368103027,
|
|
"epoch": 0.3543759684110561,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004992676525274542,
|
|
"loss": 6.5687,
|
|
"mean_token_accuracy": 0.12876028642058374,
|
|
"num_tokens": 6950313.0,
|
|
"step": 3545
|
|
},
|
|
{
|
|
"entropy": 6.594517707824707,
|
|
"epoch": 0.3548757934722847,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004992647725445331,
|
|
"loss": 6.4392,
|
|
"mean_token_accuracy": 0.135837110131979,
|
|
"num_tokens": 6958786.0,
|
|
"step": 3550
|
|
},
|
|
{
|
|
"entropy": 6.62755856513977,
|
|
"epoch": 0.3553756185335133,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000499261886919168,
|
|
"loss": 6.6161,
|
|
"mean_token_accuracy": 0.1281417541205883,
|
|
"num_tokens": 6968453.0,
|
|
"step": 3555
|
|
},
|
|
{
|
|
"entropy": 6.581298780441284,
|
|
"epoch": 0.3558754435947418,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004992589956514316,
|
|
"loss": 6.4422,
|
|
"mean_token_accuracy": 0.13865550979971886,
|
|
"num_tokens": 6978143.0,
|
|
"step": 3560
|
|
},
|
|
{
|
|
"entropy": 6.53548493385315,
|
|
"epoch": 0.3563752686559704,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004992560987413965,
|
|
"loss": 6.4639,
|
|
"mean_token_accuracy": 0.12931203544139863,
|
|
"num_tokens": 6986711.0,
|
|
"step": 3565
|
|
},
|
|
{
|
|
"entropy": 6.544329118728638,
|
|
"epoch": 0.356875093717199,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004992531961891356,
|
|
"loss": 6.5277,
|
|
"mean_token_accuracy": 0.12880890145897866,
|
|
"num_tokens": 6995904.0,
|
|
"step": 3570
|
|
},
|
|
{
|
|
"entropy": 6.643979883193969,
|
|
"epoch": 0.35737491877842753,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004992502879947222,
|
|
"loss": 6.4592,
|
|
"mean_token_accuracy": 0.13585175648331643,
|
|
"num_tokens": 7005479.0,
|
|
"step": 3575
|
|
},
|
|
{
|
|
"entropy": 6.481806850433349,
|
|
"epoch": 0.3578747438396561,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004992473741582291,
|
|
"loss": 6.3796,
|
|
"mean_token_accuracy": 0.13654778599739076,
|
|
"num_tokens": 7015048.0,
|
|
"step": 3580
|
|
},
|
|
{
|
|
"entropy": 6.577729082107544,
|
|
"epoch": 0.3583745689008847,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004992444546797298,
|
|
"loss": 6.5845,
|
|
"mean_token_accuracy": 0.13363236263394357,
|
|
"num_tokens": 7024738.0,
|
|
"step": 3585
|
|
},
|
|
{
|
|
"entropy": 6.586815977096558,
|
|
"epoch": 0.35887439396211324,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004992415295592977,
|
|
"loss": 6.4966,
|
|
"mean_token_accuracy": 0.13316498100757598,
|
|
"num_tokens": 7033972.0,
|
|
"step": 3590
|
|
},
|
|
{
|
|
"entropy": 6.603455924987793,
|
|
"epoch": 0.3593742190233418,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004992385987970064,
|
|
"loss": 6.5519,
|
|
"mean_token_accuracy": 0.1288654737174511,
|
|
"num_tokens": 7043713.0,
|
|
"step": 3595
|
|
},
|
|
{
|
|
"entropy": 6.652811193466187,
|
|
"epoch": 0.3598740440845704,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004992356623929297,
|
|
"loss": 6.519,
|
|
"mean_token_accuracy": 0.1351366400718689,
|
|
"num_tokens": 7053276.0,
|
|
"step": 3600
|
|
},
|
|
{
|
|
"entropy": 6.5362269401550295,
|
|
"epoch": 0.360373869145799,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004992327203471414,
|
|
"loss": 6.5317,
|
|
"mean_token_accuracy": 0.1316842831671238,
|
|
"num_tokens": 7063610.0,
|
|
"step": 3605
|
|
},
|
|
{
|
|
"entropy": 6.559109115600586,
|
|
"epoch": 0.36087369420702753,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004992297726597156,
|
|
"loss": 6.4861,
|
|
"mean_token_accuracy": 0.1344970740377903,
|
|
"num_tokens": 7073497.0,
|
|
"step": 3610
|
|
},
|
|
{
|
|
"entropy": 6.649214267730713,
|
|
"epoch": 0.3613735192682561,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004992268193307264,
|
|
"loss": 6.5818,
|
|
"mean_token_accuracy": 0.12460133656859398,
|
|
"num_tokens": 7084387.0,
|
|
"step": 3615
|
|
},
|
|
{
|
|
"entropy": 6.543021535873413,
|
|
"epoch": 0.3618733443294847,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004992238603602481,
|
|
"loss": 6.437,
|
|
"mean_token_accuracy": 0.13871280774474143,
|
|
"num_tokens": 7093774.0,
|
|
"step": 3620
|
|
},
|
|
{
|
|
"entropy": 6.616115570068359,
|
|
"epoch": 0.36237316939071323,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004992208957483552,
|
|
"loss": 6.5866,
|
|
"mean_token_accuracy": 0.12746953293681146,
|
|
"num_tokens": 7103367.0,
|
|
"step": 3625
|
|
},
|
|
{
|
|
"entropy": 6.621992683410644,
|
|
"epoch": 0.3628729944519418,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004992179254951223,
|
|
"loss": 6.4998,
|
|
"mean_token_accuracy": 0.13220270052552224,
|
|
"num_tokens": 7113261.0,
|
|
"step": 3630
|
|
},
|
|
{
|
|
"entropy": 6.59494800567627,
|
|
"epoch": 0.3633728195131704,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.000499214949600624,
|
|
"loss": 6.4897,
|
|
"mean_token_accuracy": 0.13366419523954393,
|
|
"num_tokens": 7122775.0,
|
|
"step": 3635
|
|
},
|
|
{
|
|
"entropy": 6.53905143737793,
|
|
"epoch": 0.36387264457439894,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004992119680649355,
|
|
"loss": 6.5602,
|
|
"mean_token_accuracy": 0.13340957909822465,
|
|
"num_tokens": 7133369.0,
|
|
"step": 3640
|
|
},
|
|
{
|
|
"entropy": 6.573632335662841,
|
|
"epoch": 0.3643724696356275,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004992089808881313,
|
|
"loss": 6.4246,
|
|
"mean_token_accuracy": 0.13840428218245507,
|
|
"num_tokens": 7142589.0,
|
|
"step": 3645
|
|
},
|
|
{
|
|
"entropy": 6.643885660171509,
|
|
"epoch": 0.3648722946968561,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004992059880702869,
|
|
"loss": 6.6195,
|
|
"mean_token_accuracy": 0.12722167894244193,
|
|
"num_tokens": 7152260.0,
|
|
"step": 3650
|
|
},
|
|
{
|
|
"entropy": 6.599239015579224,
|
|
"epoch": 0.36537211975808465,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004992029896114775,
|
|
"loss": 6.5375,
|
|
"mean_token_accuracy": 0.1395278438925743,
|
|
"num_tokens": 7161297.0,
|
|
"step": 3655
|
|
},
|
|
{
|
|
"entropy": 6.536885595321655,
|
|
"epoch": 0.36587194481931323,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004991999855117787,
|
|
"loss": 6.5857,
|
|
"mean_token_accuracy": 0.13029498904943465,
|
|
"num_tokens": 7172835.0,
|
|
"step": 3660
|
|
},
|
|
{
|
|
"entropy": 6.597273063659668,
|
|
"epoch": 0.3663717698805418,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004991969757712659,
|
|
"loss": 6.5049,
|
|
"mean_token_accuracy": 0.13501314967870712,
|
|
"num_tokens": 7182647.0,
|
|
"step": 3665
|
|
},
|
|
{
|
|
"entropy": 6.534729909896851,
|
|
"epoch": 0.3668715949417704,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.0004991939603900149,
|
|
"loss": 6.5792,
|
|
"mean_token_accuracy": 0.1312929093837738,
|
|
"num_tokens": 7192048.0,
|
|
"step": 3670
|
|
},
|
|
{
|
|
"entropy": 6.60098032951355,
|
|
"epoch": 0.36737142000299894,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004991909393681015,
|
|
"loss": 6.471,
|
|
"mean_token_accuracy": 0.13519922867417336,
|
|
"num_tokens": 7201747.0,
|
|
"step": 3675
|
|
},
|
|
{
|
|
"entropy": 6.591159105300903,
|
|
"epoch": 0.3678712450642275,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004991879127056017,
|
|
"loss": 6.4275,
|
|
"mean_token_accuracy": 0.13343789130449296,
|
|
"num_tokens": 7210660.0,
|
|
"step": 3680
|
|
},
|
|
{
|
|
"entropy": 6.5157793998718265,
|
|
"epoch": 0.3683710701254561,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004991848804025918,
|
|
"loss": 6.4901,
|
|
"mean_token_accuracy": 0.13628655001521112,
|
|
"num_tokens": 7221474.0,
|
|
"step": 3685
|
|
},
|
|
{
|
|
"entropy": 6.5517813205719,
|
|
"epoch": 0.36887089518668464,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.000499181842459148,
|
|
"loss": 6.4418,
|
|
"mean_token_accuracy": 0.13546881526708604,
|
|
"num_tokens": 7231700.0,
|
|
"step": 3690
|
|
},
|
|
{
|
|
"entropy": 6.497189235687256,
|
|
"epoch": 0.36937072024791323,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004991787988753467,
|
|
"loss": 6.4947,
|
|
"mean_token_accuracy": 0.1415654666721821,
|
|
"num_tokens": 7241887.0,
|
|
"step": 3695
|
|
},
|
|
{
|
|
"entropy": 6.602890396118164,
|
|
"epoch": 0.3698705453091418,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004991757496512645,
|
|
"loss": 6.5258,
|
|
"mean_token_accuracy": 0.1301959529519081,
|
|
"num_tokens": 7251399.0,
|
|
"step": 3700
|
|
},
|
|
{
|
|
"entropy": 6.628644800186157,
|
|
"epoch": 0.37037037037037035,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004991726947869782,
|
|
"loss": 6.6282,
|
|
"mean_token_accuracy": 0.1286029815673828,
|
|
"num_tokens": 7260555.0,
|
|
"step": 3705
|
|
},
|
|
{
|
|
"entropy": 6.601524877548218,
|
|
"epoch": 0.37087019543159894,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004991696342825645,
|
|
"loss": 6.5001,
|
|
"mean_token_accuracy": 0.13672052770853044,
|
|
"num_tokens": 7270706.0,
|
|
"step": 3710
|
|
},
|
|
{
|
|
"entropy": 6.555157279968261,
|
|
"epoch": 0.3713700204928275,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004991665681381005,
|
|
"loss": 6.4983,
|
|
"mean_token_accuracy": 0.1283060520887375,
|
|
"num_tokens": 7282491.0,
|
|
"step": 3715
|
|
},
|
|
{
|
|
"entropy": 6.5200635433197025,
|
|
"epoch": 0.37186984555405606,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004991634963536633,
|
|
"loss": 6.4865,
|
|
"mean_token_accuracy": 0.13692417591810227,
|
|
"num_tokens": 7292620.0,
|
|
"step": 3720
|
|
},
|
|
{
|
|
"entropy": 6.602332019805909,
|
|
"epoch": 0.37236967061528464,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004991604189293303,
|
|
"loss": 6.5526,
|
|
"mean_token_accuracy": 0.1268191084265709,
|
|
"num_tokens": 7302383.0,
|
|
"step": 3725
|
|
},
|
|
{
|
|
"entropy": 6.567366886138916,
|
|
"epoch": 0.37286949567651323,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004991573358651787,
|
|
"loss": 6.4428,
|
|
"mean_token_accuracy": 0.14117802530527115,
|
|
"num_tokens": 7312429.0,
|
|
"step": 3730
|
|
},
|
|
{
|
|
"entropy": 6.622728967666626,
|
|
"epoch": 0.3733693207377418,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004991542471612864,
|
|
"loss": 6.6193,
|
|
"mean_token_accuracy": 0.12092858403921128,
|
|
"num_tokens": 7322870.0,
|
|
"step": 3735
|
|
},
|
|
{
|
|
"entropy": 6.623894309997558,
|
|
"epoch": 0.37386914579897035,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004991511528177307,
|
|
"loss": 6.5435,
|
|
"mean_token_accuracy": 0.13075806349515914,
|
|
"num_tokens": 7333931.0,
|
|
"step": 3740
|
|
},
|
|
{
|
|
"entropy": 6.624968338012695,
|
|
"epoch": 0.37436897086019894,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004991480528345898,
|
|
"loss": 6.5639,
|
|
"mean_token_accuracy": 0.12912058010697364,
|
|
"num_tokens": 7344083.0,
|
|
"step": 3745
|
|
},
|
|
{
|
|
"entropy": 6.618381929397583,
|
|
"epoch": 0.3748687959214275,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004991449472119416,
|
|
"loss": 6.5166,
|
|
"mean_token_accuracy": 0.134030569344759,
|
|
"num_tokens": 7353544.0,
|
|
"step": 3750
|
|
},
|
|
{
|
|
"entropy": 6.582413530349731,
|
|
"epoch": 0.37536862098265605,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004991418359498642,
|
|
"loss": 6.4539,
|
|
"mean_token_accuracy": 0.13216032832860947,
|
|
"num_tokens": 7362406.0,
|
|
"step": 3755
|
|
},
|
|
{
|
|
"entropy": 6.570158672332764,
|
|
"epoch": 0.37586844604388464,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004991387190484358,
|
|
"loss": 6.4796,
|
|
"mean_token_accuracy": 0.12776686772704124,
|
|
"num_tokens": 7372056.0,
|
|
"step": 3760
|
|
},
|
|
{
|
|
"entropy": 6.582331991195678,
|
|
"epoch": 0.37636827110511323,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000499135596507735,
|
|
"loss": 6.4762,
|
|
"mean_token_accuracy": 0.13580433204770087,
|
|
"num_tokens": 7381849.0,
|
|
"step": 3765
|
|
},
|
|
{
|
|
"entropy": 6.500207090377808,
|
|
"epoch": 0.37686809616634176,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004991324683278402,
|
|
"loss": 6.4542,
|
|
"mean_token_accuracy": 0.13190585225820542,
|
|
"num_tokens": 7392648.0,
|
|
"step": 3770
|
|
},
|
|
{
|
|
"entropy": 6.490663242340088,
|
|
"epoch": 0.37736792122757035,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004991293345088301,
|
|
"loss": 6.3956,
|
|
"mean_token_accuracy": 0.13850160986185073,
|
|
"num_tokens": 7402121.0,
|
|
"step": 3775
|
|
},
|
|
{
|
|
"entropy": 6.571650695800781,
|
|
"epoch": 0.37786774628879893,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004991261950507837,
|
|
"loss": 6.4674,
|
|
"mean_token_accuracy": 0.13403821289539336,
|
|
"num_tokens": 7412097.0,
|
|
"step": 3780
|
|
},
|
|
{
|
|
"entropy": 6.6062475681304935,
|
|
"epoch": 0.37836757135002747,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00049912304995378,
|
|
"loss": 6.5886,
|
|
"mean_token_accuracy": 0.1247012197971344,
|
|
"num_tokens": 7421945.0,
|
|
"step": 3785
|
|
},
|
|
{
|
|
"entropy": 6.676407146453857,
|
|
"epoch": 0.37886739641125605,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004991198992178979,
|
|
"loss": 6.5542,
|
|
"mean_token_accuracy": 0.1313321188092232,
|
|
"num_tokens": 7432245.0,
|
|
"step": 3790
|
|
},
|
|
{
|
|
"entropy": 6.555547618865967,
|
|
"epoch": 0.37936722147248464,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004991167428432168,
|
|
"loss": 6.4796,
|
|
"mean_token_accuracy": 0.1320396013557911,
|
|
"num_tokens": 7441258.0,
|
|
"step": 3795
|
|
},
|
|
{
|
|
"entropy": 6.578624200820923,
|
|
"epoch": 0.3798670465337132,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004991135808298162,
|
|
"loss": 6.5653,
|
|
"mean_token_accuracy": 0.12515707761049272,
|
|
"num_tokens": 7451141.0,
|
|
"step": 3800
|
|
},
|
|
{
|
|
"entropy": 6.627640056610107,
|
|
"epoch": 0.38036687159494176,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004991104131777755,
|
|
"loss": 6.4685,
|
|
"mean_token_accuracy": 0.13078691586852073,
|
|
"num_tokens": 7461146.0,
|
|
"step": 3805
|
|
},
|
|
{
|
|
"entropy": 6.551756477355957,
|
|
"epoch": 0.38086669665617034,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004991072398871746,
|
|
"loss": 6.4666,
|
|
"mean_token_accuracy": 0.1355071634054184,
|
|
"num_tokens": 7470307.0,
|
|
"step": 3810
|
|
},
|
|
{
|
|
"entropy": 6.52693772315979,
|
|
"epoch": 0.38136652171739893,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004991040609580932,
|
|
"loss": 6.5449,
|
|
"mean_token_accuracy": 0.13105655312538148,
|
|
"num_tokens": 7478944.0,
|
|
"step": 3815
|
|
},
|
|
{
|
|
"entropy": 6.558730554580689,
|
|
"epoch": 0.38186634677862746,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004991008763906112,
|
|
"loss": 6.5259,
|
|
"mean_token_accuracy": 0.12738186717033387,
|
|
"num_tokens": 7488143.0,
|
|
"step": 3820
|
|
},
|
|
{
|
|
"entropy": 6.596171617507935,
|
|
"epoch": 0.38236617183985605,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004990976861848087,
|
|
"loss": 6.5044,
|
|
"mean_token_accuracy": 0.12671239748597146,
|
|
"num_tokens": 7497211.0,
|
|
"step": 3825
|
|
},
|
|
{
|
|
"entropy": 6.578602981567383,
|
|
"epoch": 0.38286599690108464,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004990944903407663,
|
|
"loss": 6.5238,
|
|
"mean_token_accuracy": 0.12751783207058906,
|
|
"num_tokens": 7506299.0,
|
|
"step": 3830
|
|
},
|
|
{
|
|
"entropy": 6.636028146743774,
|
|
"epoch": 0.38336582196231317,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004990912888585641,
|
|
"loss": 6.5582,
|
|
"mean_token_accuracy": 0.12867696061730385,
|
|
"num_tokens": 7516637.0,
|
|
"step": 3835
|
|
},
|
|
{
|
|
"entropy": 6.610043239593506,
|
|
"epoch": 0.38386564702354176,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004990880817382828,
|
|
"loss": 6.4581,
|
|
"mean_token_accuracy": 0.13559791818261147,
|
|
"num_tokens": 7526332.0,
|
|
"step": 3840
|
|
},
|
|
{
|
|
"entropy": 6.48463249206543,
|
|
"epoch": 0.38436547208477034,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.000499084868980003,
|
|
"loss": 6.4213,
|
|
"mean_token_accuracy": 0.14019213169813155,
|
|
"num_tokens": 7535217.0,
|
|
"step": 3845
|
|
},
|
|
{
|
|
"entropy": 6.532036399841308,
|
|
"epoch": 0.3848652971459989,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004990816505838054,
|
|
"loss": 6.5355,
|
|
"mean_token_accuracy": 0.13005966916680337,
|
|
"num_tokens": 7544538.0,
|
|
"step": 3850
|
|
},
|
|
{
|
|
"entropy": 6.659787130355835,
|
|
"epoch": 0.38536512220722746,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004990784265497713,
|
|
"loss": 6.5168,
|
|
"mean_token_accuracy": 0.13391273766756057,
|
|
"num_tokens": 7555302.0,
|
|
"step": 3855
|
|
},
|
|
{
|
|
"entropy": 6.620770120620728,
|
|
"epoch": 0.38586494726845605,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004990751968779817,
|
|
"loss": 6.4618,
|
|
"mean_token_accuracy": 0.13038535714149474,
|
|
"num_tokens": 7564543.0,
|
|
"step": 3860
|
|
},
|
|
{
|
|
"entropy": 6.47852931022644,
|
|
"epoch": 0.38636477232968464,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004990719615685176,
|
|
"loss": 6.5904,
|
|
"mean_token_accuracy": 0.1307446077466011,
|
|
"num_tokens": 7575042.0,
|
|
"step": 3865
|
|
},
|
|
{
|
|
"entropy": 6.63844108581543,
|
|
"epoch": 0.38686459739091317,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004990687206214608,
|
|
"loss": 6.5497,
|
|
"mean_token_accuracy": 0.1223531797528267,
|
|
"num_tokens": 7584467.0,
|
|
"step": 3870
|
|
},
|
|
{
|
|
"entropy": 6.5762358665466305,
|
|
"epoch": 0.38736442245214175,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004990654740368925,
|
|
"loss": 6.5193,
|
|
"mean_token_accuracy": 0.13060501590371132,
|
|
"num_tokens": 7594446.0,
|
|
"step": 3875
|
|
},
|
|
{
|
|
"entropy": 6.498785972595215,
|
|
"epoch": 0.38786424751337034,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004990622218148947,
|
|
"loss": 6.4181,
|
|
"mean_token_accuracy": 0.13888733163475991,
|
|
"num_tokens": 7603200.0,
|
|
"step": 3880
|
|
},
|
|
{
|
|
"entropy": 6.602738571166992,
|
|
"epoch": 0.3883640725745989,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004990589639555489,
|
|
"loss": 6.4854,
|
|
"mean_token_accuracy": 0.1386620283126831,
|
|
"num_tokens": 7613513.0,
|
|
"step": 3885
|
|
},
|
|
{
|
|
"entropy": 6.544764709472656,
|
|
"epoch": 0.38886389763582746,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004990557004589373,
|
|
"loss": 6.4546,
|
|
"mean_token_accuracy": 0.13224028423428535,
|
|
"num_tokens": 7622913.0,
|
|
"step": 3890
|
|
},
|
|
{
|
|
"entropy": 6.551820611953735,
|
|
"epoch": 0.38936372269705605,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004990524313251419,
|
|
"loss": 6.492,
|
|
"mean_token_accuracy": 0.1308333083987236,
|
|
"num_tokens": 7632992.0,
|
|
"step": 3895
|
|
},
|
|
{
|
|
"entropy": 6.6810994148254395,
|
|
"epoch": 0.3898635477582846,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004990491565542449,
|
|
"loss": 6.5105,
|
|
"mean_token_accuracy": 0.13149116560816765,
|
|
"num_tokens": 7642620.0,
|
|
"step": 3900
|
|
},
|
|
{
|
|
"entropy": 6.43835825920105,
|
|
"epoch": 0.39036337281951317,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004990458761463289,
|
|
"loss": 6.4185,
|
|
"mean_token_accuracy": 0.1379806824028492,
|
|
"num_tokens": 7651998.0,
|
|
"step": 3905
|
|
},
|
|
{
|
|
"entropy": 6.525279712677002,
|
|
"epoch": 0.39086319788074175,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004990425901014763,
|
|
"loss": 6.5002,
|
|
"mean_token_accuracy": 0.1255796730518341,
|
|
"num_tokens": 7660084.0,
|
|
"step": 3910
|
|
},
|
|
{
|
|
"entropy": 6.609419631958008,
|
|
"epoch": 0.3913630229419703,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004990392984197697,
|
|
"loss": 6.4169,
|
|
"mean_token_accuracy": 0.14190827161073685,
|
|
"num_tokens": 7668833.0,
|
|
"step": 3915
|
|
},
|
|
{
|
|
"entropy": 6.5328577041625975,
|
|
"epoch": 0.39186284800319887,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004990360011012921,
|
|
"loss": 6.4779,
|
|
"mean_token_accuracy": 0.12975661903619767,
|
|
"num_tokens": 7677617.0,
|
|
"step": 3920
|
|
},
|
|
{
|
|
"entropy": 6.549026203155518,
|
|
"epoch": 0.39236267306442746,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004990326981461264,
|
|
"loss": 6.5655,
|
|
"mean_token_accuracy": 0.12997373789548874,
|
|
"num_tokens": 7687794.0,
|
|
"step": 3925
|
|
},
|
|
{
|
|
"entropy": 6.6215620040893555,
|
|
"epoch": 0.39286249812565605,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004990293895543555,
|
|
"loss": 6.5157,
|
|
"mean_token_accuracy": 0.12998607531189918,
|
|
"num_tokens": 7697608.0,
|
|
"step": 3930
|
|
},
|
|
{
|
|
"entropy": 6.549281597137451,
|
|
"epoch": 0.3933623231868846,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000499026075326063,
|
|
"loss": 6.4323,
|
|
"mean_token_accuracy": 0.13656977489590644,
|
|
"num_tokens": 7707391.0,
|
|
"step": 3935
|
|
},
|
|
{
|
|
"entropy": 6.527210140228272,
|
|
"epoch": 0.39386214824811316,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000499022755461332,
|
|
"loss": 6.4927,
|
|
"mean_token_accuracy": 0.1286533445119858,
|
|
"num_tokens": 7718715.0,
|
|
"step": 3940
|
|
},
|
|
{
|
|
"entropy": 6.575077056884766,
|
|
"epoch": 0.39436197330934175,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.000499019429960246,
|
|
"loss": 6.4977,
|
|
"mean_token_accuracy": 0.129810693860054,
|
|
"num_tokens": 7729481.0,
|
|
"step": 3945
|
|
},
|
|
{
|
|
"entropy": 6.479593324661255,
|
|
"epoch": 0.3948617983705703,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004990160988228888,
|
|
"loss": 6.4501,
|
|
"mean_token_accuracy": 0.13362663462758065,
|
|
"num_tokens": 7739733.0,
|
|
"step": 3950
|
|
},
|
|
{
|
|
"entropy": 6.543328714370728,
|
|
"epoch": 0.39536162343179887,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004990127620493444,
|
|
"loss": 6.4738,
|
|
"mean_token_accuracy": 0.1381253831088543,
|
|
"num_tokens": 7749109.0,
|
|
"step": 3955
|
|
},
|
|
{
|
|
"entropy": 6.560599946975708,
|
|
"epoch": 0.39586144849302746,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004990094196396964,
|
|
"loss": 6.535,
|
|
"mean_token_accuracy": 0.12604611963033677,
|
|
"num_tokens": 7758853.0,
|
|
"step": 3960
|
|
},
|
|
{
|
|
"entropy": 6.605568790435791,
|
|
"epoch": 0.396361273554256,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.000499006071594029,
|
|
"loss": 6.5449,
|
|
"mean_token_accuracy": 0.12700080797076224,
|
|
"num_tokens": 7770831.0,
|
|
"step": 3965
|
|
},
|
|
{
|
|
"entropy": 6.66841197013855,
|
|
"epoch": 0.3968610986154846,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004990027179124266,
|
|
"loss": 6.5871,
|
|
"mean_token_accuracy": 0.12789231762290001,
|
|
"num_tokens": 7781094.0,
|
|
"step": 3970
|
|
},
|
|
{
|
|
"entropy": 6.71191143989563,
|
|
"epoch": 0.39736092367671316,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004989993585949733,
|
|
"loss": 6.5594,
|
|
"mean_token_accuracy": 0.12633242458105087,
|
|
"num_tokens": 7790713.0,
|
|
"step": 3975
|
|
},
|
|
{
|
|
"entropy": 6.474120569229126,
|
|
"epoch": 0.3978607487379417,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004989959936417541,
|
|
"loss": 6.4874,
|
|
"mean_token_accuracy": 0.13250206485390664,
|
|
"num_tokens": 7799425.0,
|
|
"step": 3980
|
|
},
|
|
{
|
|
"entropy": 6.495586729049682,
|
|
"epoch": 0.3983605737991703,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.000498992623052853,
|
|
"loss": 6.4709,
|
|
"mean_token_accuracy": 0.13688051775097848,
|
|
"num_tokens": 7809451.0,
|
|
"step": 3985
|
|
},
|
|
{
|
|
"entropy": 6.643878364562989,
|
|
"epoch": 0.39886039886039887,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004989892468283553,
|
|
"loss": 6.4957,
|
|
"mean_token_accuracy": 0.1341211050748825,
|
|
"num_tokens": 7819707.0,
|
|
"step": 3990
|
|
},
|
|
{
|
|
"entropy": 6.478731727600097,
|
|
"epoch": 0.39936022392162746,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004989858649683457,
|
|
"loss": 6.4211,
|
|
"mean_token_accuracy": 0.13438353165984154,
|
|
"num_tokens": 7828851.0,
|
|
"step": 3995
|
|
},
|
|
{
|
|
"entropy": 6.477199506759644,
|
|
"epoch": 0.399860048982856,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004989824774729094,
|
|
"loss": 6.4987,
|
|
"mean_token_accuracy": 0.13335368856787683,
|
|
"num_tokens": 7837999.0,
|
|
"step": 4000
|
|
},
|
|
{
|
|
"entropy": 6.646010208129883,
|
|
"epoch": 0.4003598740440846,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004989790843421317,
|
|
"loss": 6.586,
|
|
"mean_token_accuracy": 0.1316763199865818,
|
|
"num_tokens": 7847227.0,
|
|
"step": 4005
|
|
},
|
|
{
|
|
"entropy": 6.672080945968628,
|
|
"epoch": 0.40085969910531316,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004989756855760979,
|
|
"loss": 6.5304,
|
|
"mean_token_accuracy": 0.13430671617388726,
|
|
"num_tokens": 7857102.0,
|
|
"step": 4010
|
|
},
|
|
{
|
|
"entropy": 6.524146556854248,
|
|
"epoch": 0.4013595241665417,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004989722811748934,
|
|
"loss": 6.5753,
|
|
"mean_token_accuracy": 0.12646115496754645,
|
|
"num_tokens": 7867395.0,
|
|
"step": 4015
|
|
},
|
|
{
|
|
"entropy": 6.590912961959839,
|
|
"epoch": 0.4018593492277703,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004989688711386039,
|
|
"loss": 6.4217,
|
|
"mean_token_accuracy": 0.13748682290315628,
|
|
"num_tokens": 7876461.0,
|
|
"step": 4020
|
|
},
|
|
{
|
|
"entropy": 6.519725799560547,
|
|
"epoch": 0.40235917428899887,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004989654554673152,
|
|
"loss": 6.5127,
|
|
"mean_token_accuracy": 0.12524235621094704,
|
|
"num_tokens": 7886856.0,
|
|
"step": 4025
|
|
},
|
|
{
|
|
"entropy": 6.491343593597412,
|
|
"epoch": 0.4028589993502274,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004989620341611133,
|
|
"loss": 6.3593,
|
|
"mean_token_accuracy": 0.1446170762181282,
|
|
"num_tokens": 7896255.0,
|
|
"step": 4030
|
|
},
|
|
{
|
|
"entropy": 6.551962852478027,
|
|
"epoch": 0.403358824411456,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004989586072200843,
|
|
"loss": 6.5105,
|
|
"mean_token_accuracy": 0.13109808564186096,
|
|
"num_tokens": 7905827.0,
|
|
"step": 4035
|
|
},
|
|
{
|
|
"entropy": 6.5564357280731205,
|
|
"epoch": 0.40385864947268457,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004989551746443143,
|
|
"loss": 6.4984,
|
|
"mean_token_accuracy": 0.12900145277380942,
|
|
"num_tokens": 7915610.0,
|
|
"step": 4040
|
|
},
|
|
{
|
|
"entropy": 6.583031940460205,
|
|
"epoch": 0.4043584745339131,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004989517364338899,
|
|
"loss": 6.5231,
|
|
"mean_token_accuracy": 0.1292193613946438,
|
|
"num_tokens": 7926209.0,
|
|
"step": 4045
|
|
},
|
|
{
|
|
"entropy": 6.561289119720459,
|
|
"epoch": 0.4048582995951417,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004989482925888974,
|
|
"loss": 6.5025,
|
|
"mean_token_accuracy": 0.13480555191636084,
|
|
"num_tokens": 7936411.0,
|
|
"step": 4050
|
|
},
|
|
{
|
|
"entropy": 6.505609750747681,
|
|
"epoch": 0.4053581246563703,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004989448431094233,
|
|
"loss": 6.4467,
|
|
"mean_token_accuracy": 0.1410248190164566,
|
|
"num_tokens": 7945874.0,
|
|
"step": 4055
|
|
},
|
|
{
|
|
"entropy": 6.591428661346436,
|
|
"epoch": 0.40585794971759886,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004989413879955548,
|
|
"loss": 6.4565,
|
|
"mean_token_accuracy": 0.12914087250828743,
|
|
"num_tokens": 7955303.0,
|
|
"step": 4060
|
|
},
|
|
{
|
|
"entropy": 6.515615463256836,
|
|
"epoch": 0.4063577747788274,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004989379272473785,
|
|
"loss": 6.4364,
|
|
"mean_token_accuracy": 0.13901440128684045,
|
|
"num_tokens": 7964365.0,
|
|
"step": 4065
|
|
},
|
|
{
|
|
"entropy": 6.532591009140015,
|
|
"epoch": 0.406857599840056,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004989344608649815,
|
|
"loss": 6.4414,
|
|
"mean_token_accuracy": 0.13178981989622116,
|
|
"num_tokens": 7973692.0,
|
|
"step": 4070
|
|
},
|
|
{
|
|
"entropy": 6.5347418785095215,
|
|
"epoch": 0.40735742490128457,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004989309888484511,
|
|
"loss": 6.4575,
|
|
"mean_token_accuracy": 0.1335175082087517,
|
|
"num_tokens": 7984003.0,
|
|
"step": 4075
|
|
},
|
|
{
|
|
"entropy": 6.627656030654907,
|
|
"epoch": 0.4078572499625131,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004989275111978748,
|
|
"loss": 6.5465,
|
|
"mean_token_accuracy": 0.1315997950732708,
|
|
"num_tokens": 7994515.0,
|
|
"step": 4080
|
|
},
|
|
{
|
|
"entropy": 6.502608394622802,
|
|
"epoch": 0.4083570750237417,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004989240279133398,
|
|
"loss": 6.433,
|
|
"mean_token_accuracy": 0.1282997891306877,
|
|
"num_tokens": 8004000.0,
|
|
"step": 4085
|
|
},
|
|
{
|
|
"entropy": 6.487736749649048,
|
|
"epoch": 0.4088569000849703,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004989205389949339,
|
|
"loss": 6.4803,
|
|
"mean_token_accuracy": 0.13587168827652932,
|
|
"num_tokens": 8013880.0,
|
|
"step": 4090
|
|
},
|
|
{
|
|
"entropy": 6.555855751037598,
|
|
"epoch": 0.4093567251461988,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004989170444427448,
|
|
"loss": 6.3614,
|
|
"mean_token_accuracy": 0.1401887021958828,
|
|
"num_tokens": 8024395.0,
|
|
"step": 4095
|
|
},
|
|
{
|
|
"entropy": 6.534576511383056,
|
|
"epoch": 0.4098565502074274,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004989135442568606,
|
|
"loss": 6.4302,
|
|
"mean_token_accuracy": 0.13582985028624533,
|
|
"num_tokens": 8033198.0,
|
|
"step": 4100
|
|
},
|
|
{
|
|
"entropy": 6.4525598049163815,
|
|
"epoch": 0.410356375268656,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004989100384373693,
|
|
"loss": 6.3785,
|
|
"mean_token_accuracy": 0.1344170868396759,
|
|
"num_tokens": 8042387.0,
|
|
"step": 4105
|
|
},
|
|
{
|
|
"entropy": 6.509235954284668,
|
|
"epoch": 0.4108562003298845,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004989065269843588,
|
|
"loss": 6.516,
|
|
"mean_token_accuracy": 0.12826233580708504,
|
|
"num_tokens": 8051993.0,
|
|
"step": 4110
|
|
},
|
|
{
|
|
"entropy": 6.524654579162598,
|
|
"epoch": 0.4113560253911131,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000498903009897918,
|
|
"loss": 6.4876,
|
|
"mean_token_accuracy": 0.1279144637286663,
|
|
"num_tokens": 8062122.0,
|
|
"step": 4115
|
|
},
|
|
{
|
|
"entropy": 6.60549750328064,
|
|
"epoch": 0.4118558504523417,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004988994871781349,
|
|
"loss": 6.4879,
|
|
"mean_token_accuracy": 0.13297053351998328,
|
|
"num_tokens": 8071828.0,
|
|
"step": 4120
|
|
},
|
|
{
|
|
"entropy": 6.536817789077759,
|
|
"epoch": 0.4123556755135703,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004988959588250983,
|
|
"loss": 6.445,
|
|
"mean_token_accuracy": 0.1284802883863449,
|
|
"num_tokens": 8081017.0,
|
|
"step": 4125
|
|
},
|
|
{
|
|
"entropy": 6.535213756561279,
|
|
"epoch": 0.4128555005747988,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.000498892424838897,
|
|
"loss": 6.4904,
|
|
"mean_token_accuracy": 0.13281431496143342,
|
|
"num_tokens": 8091706.0,
|
|
"step": 4130
|
|
},
|
|
{
|
|
"entropy": 6.538304424285888,
|
|
"epoch": 0.4133553256360274,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004988888852196199,
|
|
"loss": 6.4655,
|
|
"mean_token_accuracy": 0.1341558001935482,
|
|
"num_tokens": 8100098.0,
|
|
"step": 4135
|
|
},
|
|
{
|
|
"entropy": 6.576635551452637,
|
|
"epoch": 0.413855150697256,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004988853399673562,
|
|
"loss": 6.5215,
|
|
"mean_token_accuracy": 0.1287394106388092,
|
|
"num_tokens": 8110003.0,
|
|
"step": 4140
|
|
},
|
|
{
|
|
"entropy": 6.525849962234497,
|
|
"epoch": 0.4143549757584845,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004988817890821948,
|
|
"loss": 6.4145,
|
|
"mean_token_accuracy": 0.13765130341053008,
|
|
"num_tokens": 8119440.0,
|
|
"step": 4145
|
|
},
|
|
{
|
|
"entropy": 6.53408031463623,
|
|
"epoch": 0.4148548008197131,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004988782325642252,
|
|
"loss": 6.4767,
|
|
"mean_token_accuracy": 0.13233601972460746,
|
|
"num_tokens": 8130347.0,
|
|
"step": 4150
|
|
},
|
|
{
|
|
"entropy": 6.593100214004517,
|
|
"epoch": 0.4153546258809417,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000498874670413537,
|
|
"loss": 6.4934,
|
|
"mean_token_accuracy": 0.1305489718914032,
|
|
"num_tokens": 8139252.0,
|
|
"step": 4155
|
|
},
|
|
{
|
|
"entropy": 6.594889116287232,
|
|
"epoch": 0.4158544509421702,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004988711026302197,
|
|
"loss": 6.5715,
|
|
"mean_token_accuracy": 0.12711631059646605,
|
|
"num_tokens": 8149130.0,
|
|
"step": 4160
|
|
},
|
|
{
|
|
"entropy": 6.5417625427246096,
|
|
"epoch": 0.4163542760033988,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004988675292143629,
|
|
"loss": 6.4799,
|
|
"mean_token_accuracy": 0.13304642513394355,
|
|
"num_tokens": 8158300.0,
|
|
"step": 4165
|
|
},
|
|
{
|
|
"entropy": 6.560239791870117,
|
|
"epoch": 0.4168541010646274,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004988639501660568,
|
|
"loss": 6.4359,
|
|
"mean_token_accuracy": 0.13240988105535506,
|
|
"num_tokens": 8168631.0,
|
|
"step": 4170
|
|
},
|
|
{
|
|
"entropy": 6.556834077835083,
|
|
"epoch": 0.4173539261258559,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004988603654853913,
|
|
"loss": 6.5486,
|
|
"mean_token_accuracy": 0.12870696261525155,
|
|
"num_tokens": 8178942.0,
|
|
"step": 4175
|
|
},
|
|
{
|
|
"entropy": 6.592477560043335,
|
|
"epoch": 0.4178537511870845,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004988567751724565,
|
|
"loss": 6.4592,
|
|
"mean_token_accuracy": 0.1329029843211174,
|
|
"num_tokens": 8188633.0,
|
|
"step": 4180
|
|
},
|
|
{
|
|
"entropy": 6.53848614692688,
|
|
"epoch": 0.4183535762483131,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000498853179227343,
|
|
"loss": 6.4481,
|
|
"mean_token_accuracy": 0.13518220633268357,
|
|
"num_tokens": 8198486.0,
|
|
"step": 4185
|
|
},
|
|
{
|
|
"entropy": 6.5179526805877686,
|
|
"epoch": 0.4188534013095417,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000498849577650141,
|
|
"loss": 6.481,
|
|
"mean_token_accuracy": 0.13624608516693115,
|
|
"num_tokens": 8208369.0,
|
|
"step": 4190
|
|
},
|
|
{
|
|
"entropy": 6.452465963363648,
|
|
"epoch": 0.4193532263707702,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004988459704409413,
|
|
"loss": 6.3423,
|
|
"mean_token_accuracy": 0.14007183760404587,
|
|
"num_tokens": 8217968.0,
|
|
"step": 4195
|
|
},
|
|
{
|
|
"entropy": 6.56020336151123,
|
|
"epoch": 0.4198530514319988,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004988423575998345,
|
|
"loss": 6.4993,
|
|
"mean_token_accuracy": 0.13017036393284798,
|
|
"num_tokens": 8228704.0,
|
|
"step": 4200
|
|
},
|
|
{
|
|
"entropy": 6.545264673233032,
|
|
"epoch": 0.4203528764932274,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004988387391269117,
|
|
"loss": 6.4002,
|
|
"mean_token_accuracy": 0.1359180249273777,
|
|
"num_tokens": 8239185.0,
|
|
"step": 4205
|
|
},
|
|
{
|
|
"entropy": 6.438202905654907,
|
|
"epoch": 0.4208527015544559,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004988351150222638,
|
|
"loss": 6.4721,
|
|
"mean_token_accuracy": 0.13446867540478707,
|
|
"num_tokens": 8248644.0,
|
|
"step": 4210
|
|
},
|
|
{
|
|
"entropy": 6.527329444885254,
|
|
"epoch": 0.4213525266156845,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004988314852859819,
|
|
"loss": 6.5223,
|
|
"mean_token_accuracy": 0.12920535802841188,
|
|
"num_tokens": 8259875.0,
|
|
"step": 4215
|
|
},
|
|
{
|
|
"entropy": 6.443457221984863,
|
|
"epoch": 0.4218523516769131,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004988278499181575,
|
|
"loss": 6.4116,
|
|
"mean_token_accuracy": 0.13716713190078736,
|
|
"num_tokens": 8268894.0,
|
|
"step": 4220
|
|
},
|
|
{
|
|
"entropy": 6.511584758758545,
|
|
"epoch": 0.4223521767381416,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.000498824208918882,
|
|
"loss": 6.4848,
|
|
"mean_token_accuracy": 0.12496452629566193,
|
|
"num_tokens": 8279236.0,
|
|
"step": 4225
|
|
},
|
|
{
|
|
"entropy": 6.498587369918823,
|
|
"epoch": 0.4228520017993702,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000498820562288247,
|
|
"loss": 6.3875,
|
|
"mean_token_accuracy": 0.1388476811349392,
|
|
"num_tokens": 8288464.0,
|
|
"step": 4230
|
|
},
|
|
{
|
|
"entropy": 6.420559930801391,
|
|
"epoch": 0.4233518268605988,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004988169100263442,
|
|
"loss": 6.3736,
|
|
"mean_token_accuracy": 0.13870823681354522,
|
|
"num_tokens": 8298291.0,
|
|
"step": 4235
|
|
},
|
|
{
|
|
"entropy": 6.570061349868775,
|
|
"epoch": 0.4238516519218274,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004988132521332656,
|
|
"loss": 6.5566,
|
|
"mean_token_accuracy": 0.1263101190328598,
|
|
"num_tokens": 8308543.0,
|
|
"step": 4240
|
|
},
|
|
{
|
|
"entropy": 6.634110450744629,
|
|
"epoch": 0.4243514769830559,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004988095886091031,
|
|
"loss": 6.541,
|
|
"mean_token_accuracy": 0.12622241377830506,
|
|
"num_tokens": 8318310.0,
|
|
"step": 4245
|
|
},
|
|
{
|
|
"entropy": 6.533967781066894,
|
|
"epoch": 0.4248513020442845,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004988059194539489,
|
|
"loss": 6.4387,
|
|
"mean_token_accuracy": 0.12934722527861595,
|
|
"num_tokens": 8327853.0,
|
|
"step": 4250
|
|
},
|
|
{
|
|
"entropy": 6.508464908599853,
|
|
"epoch": 0.4253511271055131,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004988022446678954,
|
|
"loss": 6.5343,
|
|
"mean_token_accuracy": 0.1303732469677925,
|
|
"num_tokens": 8337734.0,
|
|
"step": 4255
|
|
},
|
|
{
|
|
"entropy": 6.5576441287994385,
|
|
"epoch": 0.4258509521667416,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004987985642510352,
|
|
"loss": 6.483,
|
|
"mean_token_accuracy": 0.13290337175130845,
|
|
"num_tokens": 8346681.0,
|
|
"step": 4260
|
|
},
|
|
{
|
|
"entropy": 6.561308908462524,
|
|
"epoch": 0.4263507772279702,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004987948782034605,
|
|
"loss": 6.3408,
|
|
"mean_token_accuracy": 0.137284716963768,
|
|
"num_tokens": 8355597.0,
|
|
"step": 4265
|
|
},
|
|
{
|
|
"entropy": 6.51908130645752,
|
|
"epoch": 0.4268506022891988,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004987911865252644,
|
|
"loss": 6.4712,
|
|
"mean_token_accuracy": 0.13078599497675897,
|
|
"num_tokens": 8365529.0,
|
|
"step": 4270
|
|
},
|
|
{
|
|
"entropy": 6.421928787231446,
|
|
"epoch": 0.42735042735042733,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004987874892165395,
|
|
"loss": 6.4018,
|
|
"mean_token_accuracy": 0.1368158020079136,
|
|
"num_tokens": 8374727.0,
|
|
"step": 4275
|
|
},
|
|
{
|
|
"entropy": 6.50489821434021,
|
|
"epoch": 0.4278502524116559,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000498783786277379,
|
|
"loss": 6.4324,
|
|
"mean_token_accuracy": 0.13258315697312356,
|
|
"num_tokens": 8385624.0,
|
|
"step": 4280
|
|
},
|
|
{
|
|
"entropy": 6.5570708274841305,
|
|
"epoch": 0.4283500774728845,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004987800777078759,
|
|
"loss": 6.415,
|
|
"mean_token_accuracy": 0.13189322054386138,
|
|
"num_tokens": 8395242.0,
|
|
"step": 4285
|
|
},
|
|
{
|
|
"entropy": 6.376562833786011,
|
|
"epoch": 0.42884990253411304,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004987763635081238,
|
|
"loss": 6.3413,
|
|
"mean_token_accuracy": 0.13998268991708757,
|
|
"num_tokens": 8404946.0,
|
|
"step": 4290
|
|
},
|
|
{
|
|
"entropy": 6.521537446975708,
|
|
"epoch": 0.4293497275953416,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000498772643678216,
|
|
"loss": 6.6026,
|
|
"mean_token_accuracy": 0.12647197842597963,
|
|
"num_tokens": 8413835.0,
|
|
"step": 4295
|
|
},
|
|
{
|
|
"entropy": 6.618172264099121,
|
|
"epoch": 0.4298495526565702,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004987689182182459,
|
|
"loss": 6.4391,
|
|
"mean_token_accuracy": 0.13389185667037964,
|
|
"num_tokens": 8423338.0,
|
|
"step": 4300
|
|
},
|
|
{
|
|
"entropy": 6.585845947265625,
|
|
"epoch": 0.4303493777177988,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004987651871283075,
|
|
"loss": 6.5685,
|
|
"mean_token_accuracy": 0.12797584161162376,
|
|
"num_tokens": 8434370.0,
|
|
"step": 4305
|
|
},
|
|
{
|
|
"entropy": 6.524690246582031,
|
|
"epoch": 0.43084920277902733,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004987614504084946,
|
|
"loss": 6.4106,
|
|
"mean_token_accuracy": 0.1358144573867321,
|
|
"num_tokens": 8444517.0,
|
|
"step": 4310
|
|
},
|
|
{
|
|
"entropy": 6.499991178512573,
|
|
"epoch": 0.4313490278402559,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004987577080589012,
|
|
"loss": 6.4371,
|
|
"mean_token_accuracy": 0.13471659496426583,
|
|
"num_tokens": 8453269.0,
|
|
"step": 4315
|
|
},
|
|
{
|
|
"entropy": 6.513748502731323,
|
|
"epoch": 0.4318488529014845,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004987539600796213,
|
|
"loss": 6.4578,
|
|
"mean_token_accuracy": 0.13477371484041215,
|
|
"num_tokens": 8462142.0,
|
|
"step": 4320
|
|
},
|
|
{
|
|
"entropy": 6.614743041992187,
|
|
"epoch": 0.43234867796271303,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004987502064707494,
|
|
"loss": 6.4766,
|
|
"mean_token_accuracy": 0.12982487678527832,
|
|
"num_tokens": 8472020.0,
|
|
"step": 4325
|
|
},
|
|
{
|
|
"entropy": 6.492146778106689,
|
|
"epoch": 0.4328485030239416,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004987464472323799,
|
|
"loss": 6.4943,
|
|
"mean_token_accuracy": 0.13149992004036903,
|
|
"num_tokens": 8481985.0,
|
|
"step": 4330
|
|
},
|
|
{
|
|
"entropy": 6.5443164825439455,
|
|
"epoch": 0.4333483280851702,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004987426823646074,
|
|
"loss": 6.4616,
|
|
"mean_token_accuracy": 0.13821166157722473,
|
|
"num_tokens": 8490859.0,
|
|
"step": 4335
|
|
},
|
|
{
|
|
"entropy": 6.5202713966369625,
|
|
"epoch": 0.43384815314639874,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004987389118675266,
|
|
"loss": 6.4504,
|
|
"mean_token_accuracy": 0.13739967420697213,
|
|
"num_tokens": 8500714.0,
|
|
"step": 4340
|
|
},
|
|
{
|
|
"entropy": 6.4656414031982425,
|
|
"epoch": 0.4343479782076273,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004987351357412322,
|
|
"loss": 6.359,
|
|
"mean_token_accuracy": 0.13838136345148086,
|
|
"num_tokens": 8509832.0,
|
|
"step": 4345
|
|
},
|
|
{
|
|
"entropy": 6.387941169738769,
|
|
"epoch": 0.4348478032688559,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004987313539858196,
|
|
"loss": 6.3165,
|
|
"mean_token_accuracy": 0.13517126068472862,
|
|
"num_tokens": 8519455.0,
|
|
"step": 4350
|
|
},
|
|
{
|
|
"entropy": 6.603800630569458,
|
|
"epoch": 0.43534762833008445,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004987275666013836,
|
|
"loss": 6.5333,
|
|
"mean_token_accuracy": 0.12609480768442155,
|
|
"num_tokens": 8529015.0,
|
|
"step": 4355
|
|
},
|
|
{
|
|
"entropy": 6.546134996414184,
|
|
"epoch": 0.43584745339131303,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004987237735880195,
|
|
"loss": 6.4506,
|
|
"mean_token_accuracy": 0.12945613712072374,
|
|
"num_tokens": 8539081.0,
|
|
"step": 4360
|
|
},
|
|
{
|
|
"entropy": 6.472061967849731,
|
|
"epoch": 0.4363472784525416,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004987199749458229,
|
|
"loss": 6.4586,
|
|
"mean_token_accuracy": 0.13243156746029855,
|
|
"num_tokens": 8549889.0,
|
|
"step": 4365
|
|
},
|
|
{
|
|
"entropy": 6.561690330505371,
|
|
"epoch": 0.4368471035137702,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004987161706748893,
|
|
"loss": 6.4557,
|
|
"mean_token_accuracy": 0.1361939549446106,
|
|
"num_tokens": 8560331.0,
|
|
"step": 4370
|
|
},
|
|
{
|
|
"entropy": 6.500359106063843,
|
|
"epoch": 0.43734692857499874,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004987123607753144,
|
|
"loss": 6.406,
|
|
"mean_token_accuracy": 0.13452138230204583,
|
|
"num_tokens": 8570035.0,
|
|
"step": 4375
|
|
},
|
|
{
|
|
"entropy": 6.502156162261963,
|
|
"epoch": 0.4378467536362273,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.000498708545247194,
|
|
"loss": 6.4084,
|
|
"mean_token_accuracy": 0.135636755079031,
|
|
"num_tokens": 8579069.0,
|
|
"step": 4380
|
|
},
|
|
{
|
|
"entropy": 6.543806171417236,
|
|
"epoch": 0.4383465786974559,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004987047240906243,
|
|
"loss": 6.5111,
|
|
"mean_token_accuracy": 0.13440850898623466,
|
|
"num_tokens": 8589542.0,
|
|
"step": 4385
|
|
},
|
|
{
|
|
"entropy": 6.561945962905884,
|
|
"epoch": 0.43884640375868444,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004987008973057012,
|
|
"loss": 6.4396,
|
|
"mean_token_accuracy": 0.13307615146040916,
|
|
"num_tokens": 8600143.0,
|
|
"step": 4390
|
|
},
|
|
{
|
|
"entropy": 6.540645694732666,
|
|
"epoch": 0.43934622881991303,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004986970648925211,
|
|
"loss": 6.4148,
|
|
"mean_token_accuracy": 0.1355074718594551,
|
|
"num_tokens": 8609062.0,
|
|
"step": 4395
|
|
},
|
|
{
|
|
"entropy": 6.533525371551514,
|
|
"epoch": 0.4398460538811416,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004986932268511804,
|
|
"loss": 6.461,
|
|
"mean_token_accuracy": 0.1307988114655018,
|
|
"num_tokens": 8618115.0,
|
|
"step": 4400
|
|
},
|
|
{
|
|
"entropy": 6.419683265686035,
|
|
"epoch": 0.44034587894237015,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004986893831817758,
|
|
"loss": 6.3072,
|
|
"mean_token_accuracy": 0.14577516689896583,
|
|
"num_tokens": 8627091.0,
|
|
"step": 4405
|
|
},
|
|
{
|
|
"entropy": 6.4738565444946286,
|
|
"epoch": 0.44084570400359874,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004986855338844038,
|
|
"loss": 6.381,
|
|
"mean_token_accuracy": 0.1391140937805176,
|
|
"num_tokens": 8637194.0,
|
|
"step": 4410
|
|
},
|
|
{
|
|
"entropy": 6.47957673072815,
|
|
"epoch": 0.4413455290648273,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004986816789591613,
|
|
"loss": 6.4288,
|
|
"mean_token_accuracy": 0.13185917735099792,
|
|
"num_tokens": 8647281.0,
|
|
"step": 4415
|
|
},
|
|
{
|
|
"entropy": 6.6051921367645265,
|
|
"epoch": 0.44184535412605586,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004986778184061453,
|
|
"loss": 6.5441,
|
|
"mean_token_accuracy": 0.13117969557642936,
|
|
"num_tokens": 8658004.0,
|
|
"step": 4420
|
|
},
|
|
{
|
|
"entropy": 6.441143751144409,
|
|
"epoch": 0.44234517918728444,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004986739522254529,
|
|
"loss": 6.3107,
|
|
"mean_token_accuracy": 0.14155919775366782,
|
|
"num_tokens": 8666878.0,
|
|
"step": 4425
|
|
},
|
|
{
|
|
"entropy": 6.481678533554077,
|
|
"epoch": 0.44284500424851303,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004986700804171816,
|
|
"loss": 6.4058,
|
|
"mean_token_accuracy": 0.1369277760386467,
|
|
"num_tokens": 8677695.0,
|
|
"step": 4430
|
|
},
|
|
{
|
|
"entropy": 6.407256317138672,
|
|
"epoch": 0.4433448293097416,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004986662029814285,
|
|
"loss": 6.2354,
|
|
"mean_token_accuracy": 0.14666323587298394,
|
|
"num_tokens": 8686767.0,
|
|
"step": 4435
|
|
},
|
|
{
|
|
"entropy": 6.504606628417969,
|
|
"epoch": 0.44384465437097015,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004986623199182913,
|
|
"loss": 6.4643,
|
|
"mean_token_accuracy": 0.13264728337526321,
|
|
"num_tokens": 8695804.0,
|
|
"step": 4440
|
|
},
|
|
{
|
|
"entropy": 6.438683414459229,
|
|
"epoch": 0.44434447943219874,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004986584312278678,
|
|
"loss": 6.4185,
|
|
"mean_token_accuracy": 0.13090021386742592,
|
|
"num_tokens": 8706079.0,
|
|
"step": 4445
|
|
},
|
|
{
|
|
"entropy": 6.667967414855957,
|
|
"epoch": 0.4448443044934273,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004986545369102556,
|
|
"loss": 6.5395,
|
|
"mean_token_accuracy": 0.13461889550089837,
|
|
"num_tokens": 8715754.0,
|
|
"step": 4450
|
|
},
|
|
{
|
|
"entropy": 6.575337076187134,
|
|
"epoch": 0.44534412955465585,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004986506369655528,
|
|
"loss": 6.4377,
|
|
"mean_token_accuracy": 0.13373658135533334,
|
|
"num_tokens": 8725745.0,
|
|
"step": 4455
|
|
},
|
|
{
|
|
"entropy": 6.422351360321045,
|
|
"epoch": 0.44584395461588444,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004986467313938575,
|
|
"loss": 6.4272,
|
|
"mean_token_accuracy": 0.13778617233037949,
|
|
"num_tokens": 8735043.0,
|
|
"step": 4460
|
|
},
|
|
{
|
|
"entropy": 6.448146152496338,
|
|
"epoch": 0.44634377967711303,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000498642820195268,
|
|
"loss": 6.3667,
|
|
"mean_token_accuracy": 0.13664159774780274,
|
|
"num_tokens": 8744631.0,
|
|
"step": 4465
|
|
},
|
|
{
|
|
"entropy": 6.504123306274414,
|
|
"epoch": 0.44684360473834156,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004986389033698827,
|
|
"loss": 6.4403,
|
|
"mean_token_accuracy": 0.1341246597468853,
|
|
"num_tokens": 8754148.0,
|
|
"step": 4470
|
|
},
|
|
{
|
|
"entropy": 6.534858274459839,
|
|
"epoch": 0.44734342979957015,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004986349809178002,
|
|
"loss": 6.4663,
|
|
"mean_token_accuracy": 0.13697151467204094,
|
|
"num_tokens": 8763230.0,
|
|
"step": 4475
|
|
},
|
|
{
|
|
"entropy": 6.5859139919281,
|
|
"epoch": 0.44784325486079873,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004986310528391192,
|
|
"loss": 6.5168,
|
|
"mean_token_accuracy": 0.1334538169205189,
|
|
"num_tokens": 8772547.0,
|
|
"step": 4480
|
|
},
|
|
{
|
|
"entropy": 6.53432879447937,
|
|
"epoch": 0.44834307992202727,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004986271191339383,
|
|
"loss": 6.36,
|
|
"mean_token_accuracy": 0.13986174315214156,
|
|
"num_tokens": 8782766.0,
|
|
"step": 4485
|
|
},
|
|
{
|
|
"entropy": 6.493881511688232,
|
|
"epoch": 0.44884290498325585,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004986231798023566,
|
|
"loss": 6.4023,
|
|
"mean_token_accuracy": 0.13627419099211693,
|
|
"num_tokens": 8791793.0,
|
|
"step": 4490
|
|
},
|
|
{
|
|
"entropy": 6.477091693878174,
|
|
"epoch": 0.44934273004448444,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004986192348444734,
|
|
"loss": 6.4534,
|
|
"mean_token_accuracy": 0.1348723776638508,
|
|
"num_tokens": 8801888.0,
|
|
"step": 4495
|
|
},
|
|
{
|
|
"entropy": 6.488378667831421,
|
|
"epoch": 0.449842555105713,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004986152842603877,
|
|
"loss": 6.2839,
|
|
"mean_token_accuracy": 0.14627811834216117,
|
|
"num_tokens": 8810629.0,
|
|
"step": 4500
|
|
},
|
|
{
|
|
"entropy": 6.524313354492188,
|
|
"epoch": 0.45034238016694156,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004986113280501989,
|
|
"loss": 6.5078,
|
|
"mean_token_accuracy": 0.1245477132499218,
|
|
"num_tokens": 8820598.0,
|
|
"step": 4505
|
|
},
|
|
{
|
|
"entropy": 6.5409088134765625,
|
|
"epoch": 0.45084220522817015,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004986073662140068,
|
|
"loss": 6.4382,
|
|
"mean_token_accuracy": 0.13651844710111619,
|
|
"num_tokens": 8829814.0,
|
|
"step": 4510
|
|
},
|
|
{
|
|
"entropy": 6.469896697998047,
|
|
"epoch": 0.45134203028939873,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004986033987519109,
|
|
"loss": 6.4126,
|
|
"mean_token_accuracy": 0.12688309997320174,
|
|
"num_tokens": 8839899.0,
|
|
"step": 4515
|
|
},
|
|
{
|
|
"entropy": 6.608504676818848,
|
|
"epoch": 0.45184185535062726,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004985994256640108,
|
|
"loss": 6.4306,
|
|
"mean_token_accuracy": 0.13766766712069511,
|
|
"num_tokens": 8848318.0,
|
|
"step": 4520
|
|
},
|
|
{
|
|
"entropy": 6.532405996322632,
|
|
"epoch": 0.45234168041185585,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004985954469504069,
|
|
"loss": 6.408,
|
|
"mean_token_accuracy": 0.13353217393159866,
|
|
"num_tokens": 8857965.0,
|
|
"step": 4525
|
|
},
|
|
{
|
|
"entropy": 6.439678907394409,
|
|
"epoch": 0.45284150547308444,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004985914626111991,
|
|
"loss": 6.421,
|
|
"mean_token_accuracy": 0.13979350104928018,
|
|
"num_tokens": 8868324.0,
|
|
"step": 4530
|
|
},
|
|
{
|
|
"entropy": 6.4588335990905765,
|
|
"epoch": 0.45334133053431297,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004985874726464875,
|
|
"loss": 6.4175,
|
|
"mean_token_accuracy": 0.13455140441656113,
|
|
"num_tokens": 8877110.0,
|
|
"step": 4535
|
|
},
|
|
{
|
|
"entropy": 6.46298451423645,
|
|
"epoch": 0.45384115559554156,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004985834770563727,
|
|
"loss": 6.3951,
|
|
"mean_token_accuracy": 0.13256110697984697,
|
|
"num_tokens": 8886635.0,
|
|
"step": 4540
|
|
},
|
|
{
|
|
"entropy": 6.49652886390686,
|
|
"epoch": 0.45434098065677014,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004985794758409552,
|
|
"loss": 6.3737,
|
|
"mean_token_accuracy": 0.13694811761379241,
|
|
"num_tokens": 8895184.0,
|
|
"step": 4545
|
|
},
|
|
{
|
|
"entropy": 6.395736885070801,
|
|
"epoch": 0.4548408057179987,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004985754690003354,
|
|
"loss": 6.3589,
|
|
"mean_token_accuracy": 0.14108183607459068,
|
|
"num_tokens": 8905638.0,
|
|
"step": 4550
|
|
},
|
|
{
|
|
"entropy": 6.502994155883789,
|
|
"epoch": 0.45534063077922726,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004985714565346145,
|
|
"loss": 6.4459,
|
|
"mean_token_accuracy": 0.13694894015789033,
|
|
"num_tokens": 8915038.0,
|
|
"step": 4555
|
|
},
|
|
{
|
|
"entropy": 6.537573909759521,
|
|
"epoch": 0.45584045584045585,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004985674384438933,
|
|
"loss": 6.4107,
|
|
"mean_token_accuracy": 0.13412584215402604,
|
|
"num_tokens": 8923745.0,
|
|
"step": 4560
|
|
},
|
|
{
|
|
"entropy": 6.398061323165893,
|
|
"epoch": 0.45634028090168444,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004985634147282729,
|
|
"loss": 6.3852,
|
|
"mean_token_accuracy": 0.1342081107199192,
|
|
"num_tokens": 8934019.0,
|
|
"step": 4565
|
|
},
|
|
{
|
|
"entropy": 6.565010213851929,
|
|
"epoch": 0.45684010596291297,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004985593853878544,
|
|
"loss": 6.4597,
|
|
"mean_token_accuracy": 0.13615109026432037,
|
|
"num_tokens": 8943763.0,
|
|
"step": 4570
|
|
},
|
|
{
|
|
"entropy": 6.4767285823822025,
|
|
"epoch": 0.45733993102414155,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004985553504227394,
|
|
"loss": 6.3688,
|
|
"mean_token_accuracy": 0.13533643633127213,
|
|
"num_tokens": 8953757.0,
|
|
"step": 4575
|
|
},
|
|
{
|
|
"entropy": 6.380968999862671,
|
|
"epoch": 0.45783975608537014,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004985513098330293,
|
|
"loss": 6.3726,
|
|
"mean_token_accuracy": 0.13547075018286706,
|
|
"num_tokens": 8963233.0,
|
|
"step": 4580
|
|
},
|
|
{
|
|
"entropy": 6.429535341262818,
|
|
"epoch": 0.4583395811465987,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004985472636188257,
|
|
"loss": 6.334,
|
|
"mean_token_accuracy": 0.14010989367961885,
|
|
"num_tokens": 8972210.0,
|
|
"step": 4585
|
|
},
|
|
{
|
|
"entropy": 6.4599534034729,
|
|
"epoch": 0.45883940620782726,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004985432117802305,
|
|
"loss": 6.2878,
|
|
"mean_token_accuracy": 0.14164225086569787,
|
|
"num_tokens": 8982818.0,
|
|
"step": 4590
|
|
},
|
|
{
|
|
"entropy": 6.512010669708252,
|
|
"epoch": 0.45933923126905585,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004985391543173456,
|
|
"loss": 6.4562,
|
|
"mean_token_accuracy": 0.13241320922970773,
|
|
"num_tokens": 8992019.0,
|
|
"step": 4595
|
|
},
|
|
{
|
|
"entropy": 6.457628440856934,
|
|
"epoch": 0.4598390563302844,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.000498535091230273,
|
|
"loss": 6.3613,
|
|
"mean_token_accuracy": 0.1401025503873825,
|
|
"num_tokens": 9000891.0,
|
|
"step": 4600
|
|
},
|
|
{
|
|
"entropy": 6.527205944061279,
|
|
"epoch": 0.46033888139151297,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004985310225191152,
|
|
"loss": 6.412,
|
|
"mean_token_accuracy": 0.1276500105857849,
|
|
"num_tokens": 9010660.0,
|
|
"step": 4605
|
|
},
|
|
{
|
|
"entropy": 6.482425165176392,
|
|
"epoch": 0.46083870645274155,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004985269481839744,
|
|
"loss": 6.4576,
|
|
"mean_token_accuracy": 0.13516637980937957,
|
|
"num_tokens": 9020078.0,
|
|
"step": 4610
|
|
},
|
|
{
|
|
"entropy": 6.481579303741455,
|
|
"epoch": 0.4613385315139701,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004985228682249529,
|
|
"loss": 6.3964,
|
|
"mean_token_accuracy": 0.1379421815276146,
|
|
"num_tokens": 9030728.0,
|
|
"step": 4615
|
|
},
|
|
{
|
|
"entropy": 6.526381587982177,
|
|
"epoch": 0.46183835657519867,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004985187826421538,
|
|
"loss": 6.3237,
|
|
"mean_token_accuracy": 0.13987818658351897,
|
|
"num_tokens": 9041271.0,
|
|
"step": 4620
|
|
},
|
|
{
|
|
"entropy": 6.385977172851563,
|
|
"epoch": 0.46233818163642726,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004985146914356795,
|
|
"loss": 6.4432,
|
|
"mean_token_accuracy": 0.13601470440626146,
|
|
"num_tokens": 9050135.0,
|
|
"step": 4625
|
|
},
|
|
{
|
|
"entropy": 6.5035289287567135,
|
|
"epoch": 0.46283800669765585,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000498510594605633,
|
|
"loss": 6.4235,
|
|
"mean_token_accuracy": 0.13525536954402922,
|
|
"num_tokens": 9059374.0,
|
|
"step": 4630
|
|
},
|
|
{
|
|
"entropy": 6.548880481719971,
|
|
"epoch": 0.4633378317588844,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004985064921521177,
|
|
"loss": 6.4377,
|
|
"mean_token_accuracy": 0.13258222863078117,
|
|
"num_tokens": 9069568.0,
|
|
"step": 4635
|
|
},
|
|
{
|
|
"entropy": 6.504767894744873,
|
|
"epoch": 0.46383765682011296,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004985023840752364,
|
|
"loss": 6.3755,
|
|
"mean_token_accuracy": 0.14026534408330918,
|
|
"num_tokens": 9079952.0,
|
|
"step": 4640
|
|
},
|
|
{
|
|
"entropy": 6.401940536499024,
|
|
"epoch": 0.46433748188134155,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004984982703750926,
|
|
"loss": 6.3212,
|
|
"mean_token_accuracy": 0.149515238404274,
|
|
"num_tokens": 9088968.0,
|
|
"step": 4645
|
|
},
|
|
{
|
|
"entropy": 6.44706449508667,
|
|
"epoch": 0.4648373069425701,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004984941510517899,
|
|
"loss": 6.4427,
|
|
"mean_token_accuracy": 0.13683839961886407,
|
|
"num_tokens": 9099736.0,
|
|
"step": 4650
|
|
},
|
|
{
|
|
"entropy": 6.4781208515167235,
|
|
"epoch": 0.46533713200379867,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004984900261054319,
|
|
"loss": 6.4369,
|
|
"mean_token_accuracy": 0.13208477199077606,
|
|
"num_tokens": 9109200.0,
|
|
"step": 4655
|
|
},
|
|
{
|
|
"entropy": 6.534184360504151,
|
|
"epoch": 0.46583695706502726,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004984858955361224,
|
|
"loss": 6.5517,
|
|
"mean_token_accuracy": 0.12318905889987945,
|
|
"num_tokens": 9118283.0,
|
|
"step": 4660
|
|
},
|
|
{
|
|
"entropy": 6.538456726074219,
|
|
"epoch": 0.4663367821262558,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004984817593439651,
|
|
"loss": 6.3773,
|
|
"mean_token_accuracy": 0.13581222742795945,
|
|
"num_tokens": 9126765.0,
|
|
"step": 4665
|
|
},
|
|
{
|
|
"entropy": 6.465129613876343,
|
|
"epoch": 0.4668366071874844,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004984776175290643,
|
|
"loss": 6.4294,
|
|
"mean_token_accuracy": 0.13170129358768462,
|
|
"num_tokens": 9137210.0,
|
|
"step": 4670
|
|
},
|
|
{
|
|
"entropy": 6.479430150985718,
|
|
"epoch": 0.46733643224871296,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004984734700915242,
|
|
"loss": 6.3411,
|
|
"mean_token_accuracy": 0.14183183684945105,
|
|
"num_tokens": 9147811.0,
|
|
"step": 4675
|
|
},
|
|
{
|
|
"entropy": 6.435356187820434,
|
|
"epoch": 0.4678362573099415,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.000498469317031449,
|
|
"loss": 6.3485,
|
|
"mean_token_accuracy": 0.137740558385849,
|
|
"num_tokens": 9159080.0,
|
|
"step": 4680
|
|
},
|
|
{
|
|
"entropy": 6.416247367858887,
|
|
"epoch": 0.4683360823711701,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004984651583489434,
|
|
"loss": 6.3671,
|
|
"mean_token_accuracy": 0.13596429228782653,
|
|
"num_tokens": 9168959.0,
|
|
"step": 4685
|
|
},
|
|
{
|
|
"entropy": 6.447586631774902,
|
|
"epoch": 0.46883590743239867,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004984609940441119,
|
|
"loss": 6.4147,
|
|
"mean_token_accuracy": 0.1337486557662487,
|
|
"num_tokens": 9178873.0,
|
|
"step": 4690
|
|
},
|
|
{
|
|
"entropy": 6.451929187774658,
|
|
"epoch": 0.46933573249362726,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004984568241170593,
|
|
"loss": 6.2733,
|
|
"mean_token_accuracy": 0.1413310095667839,
|
|
"num_tokens": 9188056.0,
|
|
"step": 4695
|
|
},
|
|
{
|
|
"entropy": 6.450091743469239,
|
|
"epoch": 0.4698355575548558,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004984526485678905,
|
|
"loss": 6.4999,
|
|
"mean_token_accuracy": 0.1394587591290474,
|
|
"num_tokens": 9197993.0,
|
|
"step": 4700
|
|
},
|
|
{
|
|
"entropy": 6.562577104568481,
|
|
"epoch": 0.4703353826160844,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004984484673967105,
|
|
"loss": 6.4733,
|
|
"mean_token_accuracy": 0.13233150988817216,
|
|
"num_tokens": 9207719.0,
|
|
"step": 4705
|
|
},
|
|
{
|
|
"entropy": 6.489262342453003,
|
|
"epoch": 0.47083520767731296,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004984442806036246,
|
|
"loss": 6.3661,
|
|
"mean_token_accuracy": 0.1441465824842453,
|
|
"num_tokens": 9217036.0,
|
|
"step": 4710
|
|
},
|
|
{
|
|
"entropy": 6.422714519500732,
|
|
"epoch": 0.4713350327385415,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004984400881887381,
|
|
"loss": 6.3662,
|
|
"mean_token_accuracy": 0.1343640834093094,
|
|
"num_tokens": 9226132.0,
|
|
"step": 4715
|
|
},
|
|
{
|
|
"entropy": 6.536276626586914,
|
|
"epoch": 0.4718348577997701,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004984358901521565,
|
|
"loss": 6.4179,
|
|
"mean_token_accuracy": 0.13391911014914512,
|
|
"num_tokens": 9235914.0,
|
|
"step": 4720
|
|
},
|
|
{
|
|
"entropy": 6.55507378578186,
|
|
"epoch": 0.47233468286099867,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004984316864939853,
|
|
"loss": 6.4239,
|
|
"mean_token_accuracy": 0.1325272463262081,
|
|
"num_tokens": 9245269.0,
|
|
"step": 4725
|
|
},
|
|
{
|
|
"entropy": 6.311108779907227,
|
|
"epoch": 0.4728345079222272,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004984274772143304,
|
|
"loss": 6.2979,
|
|
"mean_token_accuracy": 0.1423199161887169,
|
|
"num_tokens": 9254107.0,
|
|
"step": 4730
|
|
},
|
|
{
|
|
"entropy": 6.557476949691773,
|
|
"epoch": 0.4733343329834558,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004984232623132977,
|
|
"loss": 6.4943,
|
|
"mean_token_accuracy": 0.12752621173858641,
|
|
"num_tokens": 9265219.0,
|
|
"step": 4735
|
|
},
|
|
{
|
|
"entropy": 6.538834142684936,
|
|
"epoch": 0.4738341580446844,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004984190417909932,
|
|
"loss": 6.4225,
|
|
"mean_token_accuracy": 0.13008161038160324,
|
|
"num_tokens": 9274610.0,
|
|
"step": 4740
|
|
},
|
|
{
|
|
"entropy": 6.45155897140503,
|
|
"epoch": 0.4743339831059129,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004984148156475231,
|
|
"loss": 6.436,
|
|
"mean_token_accuracy": 0.13551058396697044,
|
|
"num_tokens": 9283576.0,
|
|
"step": 4745
|
|
},
|
|
{
|
|
"entropy": 6.529959487915039,
|
|
"epoch": 0.4748338081671415,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004984105838829937,
|
|
"loss": 6.4436,
|
|
"mean_token_accuracy": 0.13864721208810807,
|
|
"num_tokens": 9293377.0,
|
|
"step": 4750
|
|
},
|
|
{
|
|
"entropy": 6.529016351699829,
|
|
"epoch": 0.4753336332283701,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004984063464975116,
|
|
"loss": 6.5055,
|
|
"mean_token_accuracy": 0.1282574638724327,
|
|
"num_tokens": 9302647.0,
|
|
"step": 4755
|
|
},
|
|
{
|
|
"entropy": 6.542206239700318,
|
|
"epoch": 0.47583345828959867,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004984021034911833,
|
|
"loss": 6.4795,
|
|
"mean_token_accuracy": 0.12635858356952667,
|
|
"num_tokens": 9312153.0,
|
|
"step": 4760
|
|
},
|
|
{
|
|
"entropy": 6.540885162353516,
|
|
"epoch": 0.4763332833508272,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004983978548641154,
|
|
"loss": 6.3736,
|
|
"mean_token_accuracy": 0.1392926350235939,
|
|
"num_tokens": 9320537.0,
|
|
"step": 4765
|
|
},
|
|
{
|
|
"entropy": 6.387734365463257,
|
|
"epoch": 0.4768331084120558,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004983936006164151,
|
|
"loss": 6.2867,
|
|
"mean_token_accuracy": 0.1454198345541954,
|
|
"num_tokens": 9330193.0,
|
|
"step": 4770
|
|
},
|
|
{
|
|
"entropy": 6.492685031890869,
|
|
"epoch": 0.47733293347328437,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004983893407481892,
|
|
"loss": 6.4815,
|
|
"mean_token_accuracy": 0.13175106048583984,
|
|
"num_tokens": 9340377.0,
|
|
"step": 4775
|
|
},
|
|
{
|
|
"entropy": 6.528011465072632,
|
|
"epoch": 0.4778327585345129,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004983850752595451,
|
|
"loss": 6.4333,
|
|
"mean_token_accuracy": 0.13777383416891098,
|
|
"num_tokens": 9349773.0,
|
|
"step": 4780
|
|
},
|
|
{
|
|
"entropy": 6.4005608558654785,
|
|
"epoch": 0.4783325835957415,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004983808041505898,
|
|
"loss": 6.3544,
|
|
"mean_token_accuracy": 0.13698267564177513,
|
|
"num_tokens": 9359844.0,
|
|
"step": 4785
|
|
},
|
|
{
|
|
"entropy": 6.4836437702178955,
|
|
"epoch": 0.4788324086569701,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004983765274214311,
|
|
"loss": 6.4306,
|
|
"mean_token_accuracy": 0.1377669893205166,
|
|
"num_tokens": 9369744.0,
|
|
"step": 4790
|
|
},
|
|
{
|
|
"entropy": 6.507730484008789,
|
|
"epoch": 0.4793322337181986,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004983722450721764,
|
|
"loss": 6.3844,
|
|
"mean_token_accuracy": 0.13529214337468148,
|
|
"num_tokens": 9378489.0,
|
|
"step": 4795
|
|
},
|
|
{
|
|
"entropy": 6.529411745071411,
|
|
"epoch": 0.4798320587794272,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004983679571029336,
|
|
"loss": 6.4549,
|
|
"mean_token_accuracy": 0.13523728400468826,
|
|
"num_tokens": 9388833.0,
|
|
"step": 4800
|
|
},
|
|
{
|
|
"entropy": 6.493711948394775,
|
|
"epoch": 0.4803318838406558,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004983636635138103,
|
|
"loss": 6.3591,
|
|
"mean_token_accuracy": 0.13547564148902894,
|
|
"num_tokens": 9398010.0,
|
|
"step": 4805
|
|
},
|
|
{
|
|
"entropy": 6.490125274658203,
|
|
"epoch": 0.4808317089018843,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004983593643049148,
|
|
"loss": 6.4615,
|
|
"mean_token_accuracy": 0.13016107976436614,
|
|
"num_tokens": 9407847.0,
|
|
"step": 4810
|
|
},
|
|
{
|
|
"entropy": 6.425223159790039,
|
|
"epoch": 0.4813315339631129,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004983550594763552,
|
|
"loss": 6.3871,
|
|
"mean_token_accuracy": 0.13814985528588294,
|
|
"num_tokens": 9416965.0,
|
|
"step": 4815
|
|
},
|
|
{
|
|
"entropy": 6.485588502883911,
|
|
"epoch": 0.4818313590243415,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004983507490282397,
|
|
"loss": 6.3954,
|
|
"mean_token_accuracy": 0.1414204254746437,
|
|
"num_tokens": 9426646.0,
|
|
"step": 4820
|
|
},
|
|
{
|
|
"entropy": 6.435629606246948,
|
|
"epoch": 0.4823311840855701,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004983464329606768,
|
|
"loss": 6.3709,
|
|
"mean_token_accuracy": 0.13402513712644576,
|
|
"num_tokens": 9435961.0,
|
|
"step": 4825
|
|
},
|
|
{
|
|
"entropy": 6.4540657043457035,
|
|
"epoch": 0.4828310091467986,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004983421112737752,
|
|
"loss": 6.3523,
|
|
"mean_token_accuracy": 0.1387752465903759,
|
|
"num_tokens": 9446369.0,
|
|
"step": 4830
|
|
},
|
|
{
|
|
"entropy": 6.523642683029175,
|
|
"epoch": 0.4833308342080272,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004983377839676435,
|
|
"loss": 6.347,
|
|
"mean_token_accuracy": 0.1420137882232666,
|
|
"num_tokens": 9456315.0,
|
|
"step": 4835
|
|
},
|
|
{
|
|
"entropy": 6.528051900863647,
|
|
"epoch": 0.4838306592692558,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004983334510423906,
|
|
"loss": 6.5053,
|
|
"mean_token_accuracy": 0.12767389342188834,
|
|
"num_tokens": 9465500.0,
|
|
"step": 4840
|
|
},
|
|
{
|
|
"entropy": 6.427554559707642,
|
|
"epoch": 0.4843304843304843,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004983291124981257,
|
|
"loss": 6.4475,
|
|
"mean_token_accuracy": 0.13194834515452386,
|
|
"num_tokens": 9475437.0,
|
|
"step": 4845
|
|
},
|
|
{
|
|
"entropy": 6.48316764831543,
|
|
"epoch": 0.4848303093917129,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004983247683349576,
|
|
"loss": 6.3722,
|
|
"mean_token_accuracy": 0.1303052343428135,
|
|
"num_tokens": 9485178.0,
|
|
"step": 4850
|
|
},
|
|
{
|
|
"entropy": 6.5141924858093265,
|
|
"epoch": 0.4853301344529415,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004983204185529959,
|
|
"loss": 6.3816,
|
|
"mean_token_accuracy": 0.13886707350611688,
|
|
"num_tokens": 9494666.0,
|
|
"step": 4855
|
|
},
|
|
{
|
|
"entropy": 6.416102647781372,
|
|
"epoch": 0.48582995951417,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004983160631523499,
|
|
"loss": 6.4427,
|
|
"mean_token_accuracy": 0.14189637899398805,
|
|
"num_tokens": 9504538.0,
|
|
"step": 4860
|
|
},
|
|
{
|
|
"entropy": 6.554702472686768,
|
|
"epoch": 0.4863297845753986,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004983117021331293,
|
|
"loss": 6.4054,
|
|
"mean_token_accuracy": 0.13481321856379508,
|
|
"num_tokens": 9514660.0,
|
|
"step": 4865
|
|
},
|
|
{
|
|
"entropy": 6.397809267044067,
|
|
"epoch": 0.4868296096366272,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004983073354954436,
|
|
"loss": 6.3722,
|
|
"mean_token_accuracy": 0.1399870201945305,
|
|
"num_tokens": 9524734.0,
|
|
"step": 4870
|
|
},
|
|
{
|
|
"entropy": 6.486401319503784,
|
|
"epoch": 0.4873294346978557,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004983029632394029,
|
|
"loss": 6.3394,
|
|
"mean_token_accuracy": 0.13598363772034644,
|
|
"num_tokens": 9533469.0,
|
|
"step": 4875
|
|
},
|
|
{
|
|
"entropy": 6.479533624649048,
|
|
"epoch": 0.4878292597590843,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000498298585365117,
|
|
"loss": 6.3949,
|
|
"mean_token_accuracy": 0.1376280166208744,
|
|
"num_tokens": 9543916.0,
|
|
"step": 4880
|
|
},
|
|
{
|
|
"entropy": 6.520917797088623,
|
|
"epoch": 0.4883290848203129,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004982942018726963,
|
|
"loss": 6.3099,
|
|
"mean_token_accuracy": 0.140919092297554,
|
|
"num_tokens": 9553767.0,
|
|
"step": 4885
|
|
},
|
|
{
|
|
"entropy": 6.464224529266358,
|
|
"epoch": 0.4888289098815415,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004982898127622508,
|
|
"loss": 6.4237,
|
|
"mean_token_accuracy": 0.1348918780684471,
|
|
"num_tokens": 9564713.0,
|
|
"step": 4890
|
|
},
|
|
{
|
|
"entropy": 6.415190839767456,
|
|
"epoch": 0.48932873494277,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004982854180338911,
|
|
"loss": 6.4848,
|
|
"mean_token_accuracy": 0.1310221068561077,
|
|
"num_tokens": 9576216.0,
|
|
"step": 4895
|
|
},
|
|
{
|
|
"entropy": 6.580247640609741,
|
|
"epoch": 0.4898285600039986,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004982810176877279,
|
|
"loss": 6.4432,
|
|
"mean_token_accuracy": 0.13468685895204544,
|
|
"num_tokens": 9586428.0,
|
|
"step": 4900
|
|
},
|
|
{
|
|
"entropy": 6.5749287605285645,
|
|
"epoch": 0.4903283850652272,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004982766117238716,
|
|
"loss": 6.4563,
|
|
"mean_token_accuracy": 0.13091298565268517,
|
|
"num_tokens": 9596548.0,
|
|
"step": 4905
|
|
},
|
|
{
|
|
"entropy": 6.4557301044464115,
|
|
"epoch": 0.4908282101264557,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004982722001424331,
|
|
"loss": 6.3512,
|
|
"mean_token_accuracy": 0.13645192086696625,
|
|
"num_tokens": 9605190.0,
|
|
"step": 4910
|
|
},
|
|
{
|
|
"entropy": 6.470714426040649,
|
|
"epoch": 0.4913280351876843,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004982677829435236,
|
|
"loss": 6.3487,
|
|
"mean_token_accuracy": 0.13710420876741408,
|
|
"num_tokens": 9614682.0,
|
|
"step": 4915
|
|
},
|
|
{
|
|
"entropy": 6.482896995544434,
|
|
"epoch": 0.4918278602489129,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004982633601272543,
|
|
"loss": 6.3889,
|
|
"mean_token_accuracy": 0.1296637199819088,
|
|
"num_tokens": 9625026.0,
|
|
"step": 4920
|
|
},
|
|
{
|
|
"entropy": 6.420542049407959,
|
|
"epoch": 0.4923276853101414,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004982589316937361,
|
|
"loss": 6.3716,
|
|
"mean_token_accuracy": 0.13665490970015526,
|
|
"num_tokens": 9634301.0,
|
|
"step": 4925
|
|
},
|
|
{
|
|
"entropy": 6.427209806442261,
|
|
"epoch": 0.49282751037137,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004982544976430808,
|
|
"loss": 6.3837,
|
|
"mean_token_accuracy": 0.1369131959974766,
|
|
"num_tokens": 9645025.0,
|
|
"step": 4930
|
|
},
|
|
{
|
|
"entropy": 6.456084489822388,
|
|
"epoch": 0.4933273354325986,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004982500579753995,
|
|
"loss": 6.3413,
|
|
"mean_token_accuracy": 0.14008644819259644,
|
|
"num_tokens": 9655595.0,
|
|
"step": 4935
|
|
},
|
|
{
|
|
"entropy": 6.4558305740356445,
|
|
"epoch": 0.49382716049382713,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004982456126908044,
|
|
"loss": 6.3777,
|
|
"mean_token_accuracy": 0.13302047550678253,
|
|
"num_tokens": 9664770.0,
|
|
"step": 4940
|
|
},
|
|
{
|
|
"entropy": 6.510966777801514,
|
|
"epoch": 0.4943269855550557,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004982411617894071,
|
|
"loss": 6.3645,
|
|
"mean_token_accuracy": 0.13752162009477614,
|
|
"num_tokens": 9673820.0,
|
|
"step": 4945
|
|
},
|
|
{
|
|
"entropy": 6.418698024749756,
|
|
"epoch": 0.4948268106162843,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004982367052713196,
|
|
"loss": 6.3652,
|
|
"mean_token_accuracy": 0.14175712838768958,
|
|
"num_tokens": 9683087.0,
|
|
"step": 4950
|
|
},
|
|
{
|
|
"entropy": 6.533307361602783,
|
|
"epoch": 0.4953266356775129,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004982322431366541,
|
|
"loss": 6.4969,
|
|
"mean_token_accuracy": 0.13403859436511995,
|
|
"num_tokens": 9692798.0,
|
|
"step": 4955
|
|
},
|
|
{
|
|
"entropy": 6.5089301586151125,
|
|
"epoch": 0.4958264607387414,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004982277753855227,
|
|
"loss": 6.291,
|
|
"mean_token_accuracy": 0.1398764967918396,
|
|
"num_tokens": 9703062.0,
|
|
"step": 4960
|
|
},
|
|
{
|
|
"entropy": 6.411831426620483,
|
|
"epoch": 0.49632628579997,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.000498223302018038,
|
|
"loss": 6.2841,
|
|
"mean_token_accuracy": 0.1449793666601181,
|
|
"num_tokens": 9713223.0,
|
|
"step": 4965
|
|
},
|
|
{
|
|
"entropy": 6.429420089721679,
|
|
"epoch": 0.4968261108611986,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004982188230343124,
|
|
"loss": 6.3939,
|
|
"mean_token_accuracy": 0.13417016491293907,
|
|
"num_tokens": 9722483.0,
|
|
"step": 4970
|
|
},
|
|
{
|
|
"entropy": 6.4690508365631105,
|
|
"epoch": 0.49732593592242713,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004982143384344587,
|
|
"loss": 6.3529,
|
|
"mean_token_accuracy": 0.13833339735865594,
|
|
"num_tokens": 9732350.0,
|
|
"step": 4975
|
|
},
|
|
{
|
|
"entropy": 6.46622486114502,
|
|
"epoch": 0.4978257609836557,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004982098482185897,
|
|
"loss": 6.3785,
|
|
"mean_token_accuracy": 0.13927287757396697,
|
|
"num_tokens": 9741824.0,
|
|
"step": 4980
|
|
},
|
|
{
|
|
"entropy": 6.43610634803772,
|
|
"epoch": 0.4983255860448843,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004982053523868182,
|
|
"loss": 6.332,
|
|
"mean_token_accuracy": 0.13948794230818748,
|
|
"num_tokens": 9751428.0,
|
|
"step": 4985
|
|
},
|
|
{
|
|
"entropy": 6.389789247512818,
|
|
"epoch": 0.49882541110611284,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004982008509392576,
|
|
"loss": 6.2551,
|
|
"mean_token_accuracy": 0.1467537611722946,
|
|
"num_tokens": 9761430.0,
|
|
"step": 4990
|
|
},
|
|
{
|
|
"entropy": 6.504963636398315,
|
|
"epoch": 0.4993252361673414,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.000498196343876021,
|
|
"loss": 6.4839,
|
|
"mean_token_accuracy": 0.13137512877583504,
|
|
"num_tokens": 9771540.0,
|
|
"step": 4995
|
|
},
|
|
{
|
|
"entropy": 6.538363409042359,
|
|
"epoch": 0.49982506122857,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004981918311972219,
|
|
"loss": 6.4581,
|
|
"mean_token_accuracy": 0.1347872421145439,
|
|
"num_tokens": 9781342.0,
|
|
"step": 5000
|
|
},
|
|
{
|
|
"entropy": 6.491554594039917,
|
|
"epoch": 0.5003248862897985,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004981873129029737,
|
|
"loss": 6.4406,
|
|
"mean_token_accuracy": 0.13302661776542662,
|
|
"num_tokens": 9790313.0,
|
|
"step": 5005
|
|
},
|
|
{
|
|
"entropy": 6.572258710861206,
|
|
"epoch": 0.5008247113510271,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00049818278899339,
|
|
"loss": 6.3802,
|
|
"mean_token_accuracy": 0.1342344142496586,
|
|
"num_tokens": 9799656.0,
|
|
"step": 5010
|
|
},
|
|
{
|
|
"entropy": 6.428929805755615,
|
|
"epoch": 0.5013245364122557,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.000498178259468585,
|
|
"loss": 6.3472,
|
|
"mean_token_accuracy": 0.14534548670053482,
|
|
"num_tokens": 9808971.0,
|
|
"step": 5015
|
|
},
|
|
{
|
|
"entropy": 6.464481258392334,
|
|
"epoch": 0.5018243614734843,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004981737243286722,
|
|
"loss": 6.4189,
|
|
"mean_token_accuracy": 0.13541440293192863,
|
|
"num_tokens": 9820397.0,
|
|
"step": 5020
|
|
},
|
|
{
|
|
"entropy": 6.518436908721924,
|
|
"epoch": 0.5023241865347129,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004981691835737661,
|
|
"loss": 6.3917,
|
|
"mean_token_accuracy": 0.13676153644919395,
|
|
"num_tokens": 9829309.0,
|
|
"step": 5025
|
|
},
|
|
{
|
|
"entropy": 6.472116947174072,
|
|
"epoch": 0.5028240115959414,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004981646372039807,
|
|
"loss": 6.3974,
|
|
"mean_token_accuracy": 0.13122374638915063,
|
|
"num_tokens": 9838950.0,
|
|
"step": 5030
|
|
},
|
|
{
|
|
"entropy": 6.494530963897705,
|
|
"epoch": 0.50332383665717,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004981600852194305,
|
|
"loss": 6.3491,
|
|
"mean_token_accuracy": 0.14054525196552276,
|
|
"num_tokens": 9849613.0,
|
|
"step": 5035
|
|
},
|
|
{
|
|
"entropy": 6.537146854400635,
|
|
"epoch": 0.5038236617183985,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00049815552762023,
|
|
"loss": 6.5049,
|
|
"mean_token_accuracy": 0.12978233993053437,
|
|
"num_tokens": 9860842.0,
|
|
"step": 5040
|
|
},
|
|
{
|
|
"entropy": 6.366571950912475,
|
|
"epoch": 0.5043234867796271,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004981509644064937,
|
|
"loss": 6.3503,
|
|
"mean_token_accuracy": 0.14064454808831214,
|
|
"num_tokens": 9871936.0,
|
|
"step": 5045
|
|
},
|
|
{
|
|
"entropy": 6.407763433456421,
|
|
"epoch": 0.5048233118408557,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004981463955783367,
|
|
"loss": 6.2417,
|
|
"mean_token_accuracy": 0.14102230221033096,
|
|
"num_tokens": 9882142.0,
|
|
"step": 5050
|
|
},
|
|
{
|
|
"entropy": 6.455689096450806,
|
|
"epoch": 0.5053231369020843,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004981418211358736,
|
|
"loss": 6.3604,
|
|
"mean_token_accuracy": 0.13463332876563072,
|
|
"num_tokens": 9892713.0,
|
|
"step": 5055
|
|
},
|
|
{
|
|
"entropy": 6.457704782485962,
|
|
"epoch": 0.5058229619633129,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004981372410792199,
|
|
"loss": 6.4166,
|
|
"mean_token_accuracy": 0.13474635332822799,
|
|
"num_tokens": 9901706.0,
|
|
"step": 5060
|
|
},
|
|
{
|
|
"entropy": 6.381054067611695,
|
|
"epoch": 0.5063227870245414,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004981326554084906,
|
|
"loss": 6.3465,
|
|
"mean_token_accuracy": 0.1387743279337883,
|
|
"num_tokens": 9912444.0,
|
|
"step": 5065
|
|
},
|
|
{
|
|
"entropy": 6.56711049079895,
|
|
"epoch": 0.50682261208577,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004981280641238011,
|
|
"loss": 6.3506,
|
|
"mean_token_accuracy": 0.13491351827979087,
|
|
"num_tokens": 9921593.0,
|
|
"step": 5070
|
|
},
|
|
{
|
|
"entropy": 6.379525375366211,
|
|
"epoch": 0.5073224371469985,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004981234672252669,
|
|
"loss": 6.2987,
|
|
"mean_token_accuracy": 0.14403324723243713,
|
|
"num_tokens": 9931362.0,
|
|
"step": 5075
|
|
},
|
|
{
|
|
"entropy": 6.52586612701416,
|
|
"epoch": 0.5078222622082271,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004981188647130037,
|
|
"loss": 6.4528,
|
|
"mean_token_accuracy": 0.13757158145308496,
|
|
"num_tokens": 9941877.0,
|
|
"step": 5080
|
|
},
|
|
{
|
|
"entropy": 6.583056926727295,
|
|
"epoch": 0.5083220872694557,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004981142565871272,
|
|
"loss": 6.5055,
|
|
"mean_token_accuracy": 0.12831874638795854,
|
|
"num_tokens": 9952516.0,
|
|
"step": 5085
|
|
},
|
|
{
|
|
"entropy": 6.603437805175782,
|
|
"epoch": 0.5088219123306843,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004981096428477535,
|
|
"loss": 6.5572,
|
|
"mean_token_accuracy": 0.12907882556319236,
|
|
"num_tokens": 9963078.0,
|
|
"step": 5090
|
|
},
|
|
{
|
|
"entropy": 6.561179685592651,
|
|
"epoch": 0.5093217373919128,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004981050234949986,
|
|
"loss": 6.4342,
|
|
"mean_token_accuracy": 0.1301390290260315,
|
|
"num_tokens": 9972816.0,
|
|
"step": 5095
|
|
},
|
|
{
|
|
"entropy": 6.472829532623291,
|
|
"epoch": 0.5098215624531414,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004981003985289786,
|
|
"loss": 6.3965,
|
|
"mean_token_accuracy": 0.1327144332230091,
|
|
"num_tokens": 9982773.0,
|
|
"step": 5100
|
|
},
|
|
{
|
|
"entropy": 6.4751060009002686,
|
|
"epoch": 0.51032138751437,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004980957679498101,
|
|
"loss": 6.3835,
|
|
"mean_token_accuracy": 0.14121959432959558,
|
|
"num_tokens": 9992602.0,
|
|
"step": 5105
|
|
},
|
|
{
|
|
"entropy": 6.479527425765991,
|
|
"epoch": 0.5108212125755985,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004980911317576095,
|
|
"loss": 6.3428,
|
|
"mean_token_accuracy": 0.13944500610232352,
|
|
"num_tokens": 10002185.0,
|
|
"step": 5110
|
|
},
|
|
{
|
|
"entropy": 6.4052345752716064,
|
|
"epoch": 0.5113210376368271,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004980864899524933,
|
|
"loss": 6.3415,
|
|
"mean_token_accuracy": 0.13430991321802138,
|
|
"num_tokens": 10012028.0,
|
|
"step": 5115
|
|
},
|
|
{
|
|
"entropy": 6.437929916381836,
|
|
"epoch": 0.5118208626980557,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004980818425345786,
|
|
"loss": 6.4286,
|
|
"mean_token_accuracy": 0.13085610717535018,
|
|
"num_tokens": 10021914.0,
|
|
"step": 5120
|
|
},
|
|
{
|
|
"entropy": 6.511262130737305,
|
|
"epoch": 0.5123206877592843,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000498077189503982,
|
|
"loss": 6.3966,
|
|
"mean_token_accuracy": 0.13715369179844855,
|
|
"num_tokens": 10031246.0,
|
|
"step": 5125
|
|
},
|
|
{
|
|
"entropy": 6.553551101684571,
|
|
"epoch": 0.5128205128205128,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004980725308608208,
|
|
"loss": 6.402,
|
|
"mean_token_accuracy": 0.13357761651277542,
|
|
"num_tokens": 10042064.0,
|
|
"step": 5130
|
|
},
|
|
{
|
|
"entropy": 6.362481212615966,
|
|
"epoch": 0.5133203378817414,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.0004980678666052121,
|
|
"loss": 6.19,
|
|
"mean_token_accuracy": 0.14961197972297668,
|
|
"num_tokens": 10052943.0,
|
|
"step": 5135
|
|
},
|
|
{
|
|
"entropy": 6.404932165145874,
|
|
"epoch": 0.51382016294297,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004980631967372733,
|
|
"loss": 6.3697,
|
|
"mean_token_accuracy": 0.13727065026760102,
|
|
"num_tokens": 10062497.0,
|
|
"step": 5140
|
|
},
|
|
{
|
|
"entropy": 6.464839744567871,
|
|
"epoch": 0.5143199880041985,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004980585212571218,
|
|
"loss": 6.3645,
|
|
"mean_token_accuracy": 0.1414380431175232,
|
|
"num_tokens": 10072819.0,
|
|
"step": 5145
|
|
},
|
|
{
|
|
"entropy": 6.358304023742676,
|
|
"epoch": 0.5148198130654271,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004980538401648753,
|
|
"loss": 6.2407,
|
|
"mean_token_accuracy": 0.14484174624085427,
|
|
"num_tokens": 10081834.0,
|
|
"step": 5150
|
|
},
|
|
{
|
|
"entropy": 6.44873366355896,
|
|
"epoch": 0.5153196381266557,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004980491534606517,
|
|
"loss": 6.3624,
|
|
"mean_token_accuracy": 0.14508387371897696,
|
|
"num_tokens": 10090746.0,
|
|
"step": 5155
|
|
},
|
|
{
|
|
"entropy": 6.4216272830963135,
|
|
"epoch": 0.5158194631878842,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004980444611445686,
|
|
"loss": 6.3656,
|
|
"mean_token_accuracy": 0.13868543729186059,
|
|
"num_tokens": 10101728.0,
|
|
"step": 5160
|
|
},
|
|
{
|
|
"entropy": 6.4501988887786865,
|
|
"epoch": 0.5163192882491128,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004980397632167444,
|
|
"loss": 6.3363,
|
|
"mean_token_accuracy": 0.14399878904223443,
|
|
"num_tokens": 10111641.0,
|
|
"step": 5165
|
|
},
|
|
{
|
|
"entropy": 6.4942793369293215,
|
|
"epoch": 0.5168191133103414,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004980350596772971,
|
|
"loss": 6.3046,
|
|
"mean_token_accuracy": 0.13481297269463538,
|
|
"num_tokens": 10120708.0,
|
|
"step": 5170
|
|
},
|
|
{
|
|
"entropy": 6.419431209564209,
|
|
"epoch": 0.51731893837157,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004980303505263451,
|
|
"loss": 6.3311,
|
|
"mean_token_accuracy": 0.1368158668279648,
|
|
"num_tokens": 10131279.0,
|
|
"step": 5175
|
|
},
|
|
{
|
|
"entropy": 6.412103843688965,
|
|
"epoch": 0.5178187634327985,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004980256357640069,
|
|
"loss": 6.2256,
|
|
"mean_token_accuracy": 0.14284660071134567,
|
|
"num_tokens": 10140329.0,
|
|
"step": 5180
|
|
},
|
|
{
|
|
"entropy": 6.509219026565551,
|
|
"epoch": 0.5183185884940271,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004980209153904011,
|
|
"loss": 6.4162,
|
|
"mean_token_accuracy": 0.13610876351594925,
|
|
"num_tokens": 10149658.0,
|
|
"step": 5185
|
|
},
|
|
{
|
|
"entropy": 6.340816640853882,
|
|
"epoch": 0.5188184135552557,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004980161894056464,
|
|
"loss": 6.2127,
|
|
"mean_token_accuracy": 0.14570229947566987,
|
|
"num_tokens": 10159131.0,
|
|
"step": 5190
|
|
},
|
|
{
|
|
"entropy": 6.353019285202026,
|
|
"epoch": 0.5193182386164842,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004980114578098618,
|
|
"loss": 6.3856,
|
|
"mean_token_accuracy": 0.13546337187290192,
|
|
"num_tokens": 10169094.0,
|
|
"step": 5195
|
|
},
|
|
{
|
|
"entropy": 6.487119054794311,
|
|
"epoch": 0.5198180636777128,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004980067206031663,
|
|
"loss": 6.2793,
|
|
"mean_token_accuracy": 0.14671253859996797,
|
|
"num_tokens": 10177910.0,
|
|
"step": 5200
|
|
},
|
|
{
|
|
"entropy": 6.437972784042358,
|
|
"epoch": 0.5203178887389414,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004980019777856791,
|
|
"loss": 6.328,
|
|
"mean_token_accuracy": 0.14403121471405028,
|
|
"num_tokens": 10186801.0,
|
|
"step": 5205
|
|
},
|
|
{
|
|
"entropy": 6.483811330795288,
|
|
"epoch": 0.52081771380017,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004979972293575195,
|
|
"loss": 6.4062,
|
|
"mean_token_accuracy": 0.1334290087223053,
|
|
"num_tokens": 10196841.0,
|
|
"step": 5210
|
|
},
|
|
{
|
|
"entropy": 6.502076721191406,
|
|
"epoch": 0.5213175388613985,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004979924753188069,
|
|
"loss": 6.4635,
|
|
"mean_token_accuracy": 0.12991615235805512,
|
|
"num_tokens": 10207829.0,
|
|
"step": 5215
|
|
},
|
|
{
|
|
"entropy": 6.441777324676513,
|
|
"epoch": 0.5218173639226271,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004979877156696612,
|
|
"loss": 6.4525,
|
|
"mean_token_accuracy": 0.13123227879405022,
|
|
"num_tokens": 10217029.0,
|
|
"step": 5220
|
|
},
|
|
{
|
|
"entropy": 6.426708173751831,
|
|
"epoch": 0.5223171889838556,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004979829504102018,
|
|
"loss": 6.3068,
|
|
"mean_token_accuracy": 0.14138131588697433,
|
|
"num_tokens": 10227602.0,
|
|
"step": 5225
|
|
},
|
|
{
|
|
"entropy": 6.425765800476074,
|
|
"epoch": 0.5228170140450842,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004979781795405488,
|
|
"loss": 6.3371,
|
|
"mean_token_accuracy": 0.13900671154260635,
|
|
"num_tokens": 10237990.0,
|
|
"step": 5230
|
|
},
|
|
{
|
|
"entropy": 6.462211942672729,
|
|
"epoch": 0.5233168391063128,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004979734030608222,
|
|
"loss": 6.3787,
|
|
"mean_token_accuracy": 0.1397375248372555,
|
|
"num_tokens": 10247381.0,
|
|
"step": 5235
|
|
},
|
|
{
|
|
"entropy": 6.40122652053833,
|
|
"epoch": 0.5238166641675414,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004979686209711422,
|
|
"loss": 6.1952,
|
|
"mean_token_accuracy": 0.15425493717193603,
|
|
"num_tokens": 10256444.0,
|
|
"step": 5240
|
|
},
|
|
{
|
|
"entropy": 6.466607666015625,
|
|
"epoch": 0.5243164892287699,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.000497963833271629,
|
|
"loss": 6.3641,
|
|
"mean_token_accuracy": 0.13539370372891427,
|
|
"num_tokens": 10266965.0,
|
|
"step": 5245
|
|
},
|
|
{
|
|
"entropy": 6.396874952316284,
|
|
"epoch": 0.5248163142899985,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004979590399624031,
|
|
"loss": 6.2913,
|
|
"mean_token_accuracy": 0.14410683065652846,
|
|
"num_tokens": 10276520.0,
|
|
"step": 5250
|
|
},
|
|
{
|
|
"entropy": 6.452992725372314,
|
|
"epoch": 0.5253161393512271,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004979542410435852,
|
|
"loss": 6.3688,
|
|
"mean_token_accuracy": 0.13349135145545005,
|
|
"num_tokens": 10285676.0,
|
|
"step": 5255
|
|
},
|
|
{
|
|
"entropy": 6.369792509078979,
|
|
"epoch": 0.5258159644124556,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004979494365152959,
|
|
"loss": 6.2599,
|
|
"mean_token_accuracy": 0.1452934131026268,
|
|
"num_tokens": 10295643.0,
|
|
"step": 5260
|
|
},
|
|
{
|
|
"entropy": 6.447965335845947,
|
|
"epoch": 0.5263157894736842,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004979446263776562,
|
|
"loss": 6.3667,
|
|
"mean_token_accuracy": 0.13000320717692376,
|
|
"num_tokens": 10305555.0,
|
|
"step": 5265
|
|
},
|
|
{
|
|
"entropy": 6.454273414611817,
|
|
"epoch": 0.5268156145349128,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.000497939810630787,
|
|
"loss": 6.3263,
|
|
"mean_token_accuracy": 0.14252042546868324,
|
|
"num_tokens": 10315399.0,
|
|
"step": 5270
|
|
},
|
|
{
|
|
"entropy": 6.36467227935791,
|
|
"epoch": 0.5273154395961414,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004979349892748096,
|
|
"loss": 6.3697,
|
|
"mean_token_accuracy": 0.14212508723139763,
|
|
"num_tokens": 10325414.0,
|
|
"step": 5275
|
|
},
|
|
{
|
|
"entropy": 6.4512800693511965,
|
|
"epoch": 0.5278152646573699,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004979301623098452,
|
|
"loss": 6.3436,
|
|
"mean_token_accuracy": 0.1363958165049553,
|
|
"num_tokens": 10334701.0,
|
|
"step": 5280
|
|
},
|
|
{
|
|
"entropy": 6.416783666610717,
|
|
"epoch": 0.5283150897185985,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004979253297360153,
|
|
"loss": 6.4277,
|
|
"mean_token_accuracy": 0.1374026782810688,
|
|
"num_tokens": 10343951.0,
|
|
"step": 5285
|
|
},
|
|
{
|
|
"entropy": 6.408209896087646,
|
|
"epoch": 0.528814914779827,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004979204915534415,
|
|
"loss": 6.2931,
|
|
"mean_token_accuracy": 0.14456386864185333,
|
|
"num_tokens": 10352990.0,
|
|
"step": 5290
|
|
},
|
|
{
|
|
"entropy": 6.448209238052368,
|
|
"epoch": 0.5293147398410556,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004979156477622454,
|
|
"loss": 6.3515,
|
|
"mean_token_accuracy": 0.14031895026564598,
|
|
"num_tokens": 10363059.0,
|
|
"step": 5295
|
|
},
|
|
{
|
|
"entropy": 6.498208045959473,
|
|
"epoch": 0.5298145649022842,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004979107983625491,
|
|
"loss": 6.341,
|
|
"mean_token_accuracy": 0.14113035723567008,
|
|
"num_tokens": 10373237.0,
|
|
"step": 5300
|
|
},
|
|
{
|
|
"entropy": 6.5129311084747314,
|
|
"epoch": 0.5303143899635128,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004979059433544744,
|
|
"loss": 6.44,
|
|
"mean_token_accuracy": 0.13211785033345222,
|
|
"num_tokens": 10383373.0,
|
|
"step": 5305
|
|
},
|
|
{
|
|
"entropy": 6.4633525848388675,
|
|
"epoch": 0.5308142150247414,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004979010827381435,
|
|
"loss": 6.3274,
|
|
"mean_token_accuracy": 0.12966383323073388,
|
|
"num_tokens": 10392612.0,
|
|
"step": 5310
|
|
},
|
|
{
|
|
"entropy": 6.362445640563965,
|
|
"epoch": 0.5313140400859699,
|
|
"grad_norm": 3.609375,
|
|
"learning_rate": 0.0004978962165136787,
|
|
"loss": 6.272,
|
|
"mean_token_accuracy": 0.13932389095425607,
|
|
"num_tokens": 10402201.0,
|
|
"step": 5315
|
|
},
|
|
{
|
|
"entropy": 6.4546863555908205,
|
|
"epoch": 0.5318138651471985,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004978913446812025,
|
|
"loss": 6.3025,
|
|
"mean_token_accuracy": 0.14247895479202272,
|
|
"num_tokens": 10411847.0,
|
|
"step": 5320
|
|
},
|
|
{
|
|
"entropy": 6.419976806640625,
|
|
"epoch": 0.532313690208427,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004978864672408374,
|
|
"loss": 6.3926,
|
|
"mean_token_accuracy": 0.13130954205989837,
|
|
"num_tokens": 10422035.0,
|
|
"step": 5325
|
|
},
|
|
{
|
|
"entropy": 6.40062460899353,
|
|
"epoch": 0.5328135152696556,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004978815841927061,
|
|
"loss": 6.3389,
|
|
"mean_token_accuracy": 0.1398831605911255,
|
|
"num_tokens": 10432097.0,
|
|
"step": 5330
|
|
},
|
|
{
|
|
"entropy": 6.454918003082275,
|
|
"epoch": 0.5333133403308842,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004978766955369315,
|
|
"loss": 6.3387,
|
|
"mean_token_accuracy": 0.14079173132777215,
|
|
"num_tokens": 10442357.0,
|
|
"step": 5335
|
|
},
|
|
{
|
|
"entropy": 6.311182165145874,
|
|
"epoch": 0.5338131653921128,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004978718012736367,
|
|
"loss": 6.275,
|
|
"mean_token_accuracy": 0.1485537901520729,
|
|
"num_tokens": 10453491.0,
|
|
"step": 5340
|
|
},
|
|
{
|
|
"entropy": 6.431671237945556,
|
|
"epoch": 0.5343129904533414,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004978669014029446,
|
|
"loss": 6.3142,
|
|
"mean_token_accuracy": 0.14028706550598144,
|
|
"num_tokens": 10464016.0,
|
|
"step": 5345
|
|
},
|
|
{
|
|
"entropy": 6.473352241516113,
|
|
"epoch": 0.5348128155145699,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004978619959249787,
|
|
"loss": 6.311,
|
|
"mean_token_accuracy": 0.13191917762160302,
|
|
"num_tokens": 10473471.0,
|
|
"step": 5350
|
|
},
|
|
{
|
|
"entropy": 6.363288736343383,
|
|
"epoch": 0.5353126405757984,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004978570848398623,
|
|
"loss": 6.3153,
|
|
"mean_token_accuracy": 0.13890534415841102,
|
|
"num_tokens": 10482329.0,
|
|
"step": 5355
|
|
},
|
|
{
|
|
"entropy": 6.4296393394470215,
|
|
"epoch": 0.535812465637027,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.000497852168147719,
|
|
"loss": 6.418,
|
|
"mean_token_accuracy": 0.13311819806694986,
|
|
"num_tokens": 10491731.0,
|
|
"step": 5360
|
|
},
|
|
{
|
|
"entropy": 6.529134321212768,
|
|
"epoch": 0.5363122906982556,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004978472458486724,
|
|
"loss": 6.4002,
|
|
"mean_token_accuracy": 0.13935512900352479,
|
|
"num_tokens": 10501317.0,
|
|
"step": 5365
|
|
},
|
|
{
|
|
"entropy": 6.475551557540894,
|
|
"epoch": 0.5368121157594842,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004978423179428466,
|
|
"loss": 6.2984,
|
|
"mean_token_accuracy": 0.13850174099206924,
|
|
"num_tokens": 10509849.0,
|
|
"step": 5370
|
|
},
|
|
{
|
|
"entropy": 6.3376429080963135,
|
|
"epoch": 0.5373119408207128,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004978373844303653,
|
|
"loss": 6.3189,
|
|
"mean_token_accuracy": 0.13514501750469207,
|
|
"num_tokens": 10518714.0,
|
|
"step": 5375
|
|
},
|
|
{
|
|
"entropy": 6.466615438461304,
|
|
"epoch": 0.5378117658819414,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004978324453113528,
|
|
"loss": 6.357,
|
|
"mean_token_accuracy": 0.13815916925668717,
|
|
"num_tokens": 10529128.0,
|
|
"step": 5380
|
|
},
|
|
{
|
|
"entropy": 6.475117874145508,
|
|
"epoch": 0.5383115909431699,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004978275005859333,
|
|
"loss": 6.2947,
|
|
"mean_token_accuracy": 0.1379874348640442,
|
|
"num_tokens": 10538748.0,
|
|
"step": 5385
|
|
},
|
|
{
|
|
"entropy": 6.381226968765259,
|
|
"epoch": 0.5388114160043984,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004978225502542313,
|
|
"loss": 6.3256,
|
|
"mean_token_accuracy": 0.13793647438287734,
|
|
"num_tokens": 10549273.0,
|
|
"step": 5390
|
|
},
|
|
{
|
|
"entropy": 6.4153244972229,
|
|
"epoch": 0.539311241065627,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004978175943163712,
|
|
"loss": 6.2757,
|
|
"mean_token_accuracy": 0.14547774568200111,
|
|
"num_tokens": 10559332.0,
|
|
"step": 5395
|
|
},
|
|
{
|
|
"entropy": 6.370609998703003,
|
|
"epoch": 0.5398110661268556,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004978126327724777,
|
|
"loss": 6.2962,
|
|
"mean_token_accuracy": 0.1446087673306465,
|
|
"num_tokens": 10568699.0,
|
|
"step": 5400
|
|
},
|
|
{
|
|
"entropy": 6.355083084106445,
|
|
"epoch": 0.5403108911880842,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004978076656226758,
|
|
"loss": 6.2665,
|
|
"mean_token_accuracy": 0.14076985865831376,
|
|
"num_tokens": 10579129.0,
|
|
"step": 5405
|
|
},
|
|
{
|
|
"entropy": 6.394743204116821,
|
|
"epoch": 0.5408107162493128,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004978026928670902,
|
|
"loss": 6.3442,
|
|
"mean_token_accuracy": 0.13657924234867097,
|
|
"num_tokens": 10589093.0,
|
|
"step": 5410
|
|
},
|
|
{
|
|
"entropy": 6.347167110443115,
|
|
"epoch": 0.5413105413105413,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004977977145058463,
|
|
"loss": 6.359,
|
|
"mean_token_accuracy": 0.1375754989683628,
|
|
"num_tokens": 10598766.0,
|
|
"step": 5415
|
|
},
|
|
{
|
|
"entropy": 6.3665509700775145,
|
|
"epoch": 0.5418103663717699,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004977927305390693,
|
|
"loss": 6.2774,
|
|
"mean_token_accuracy": 0.14815937578678132,
|
|
"num_tokens": 10609148.0,
|
|
"step": 5420
|
|
},
|
|
{
|
|
"entropy": 6.5036862850189205,
|
|
"epoch": 0.5423101914329984,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004977877409668845,
|
|
"loss": 6.4375,
|
|
"mean_token_accuracy": 0.12969812080264093,
|
|
"num_tokens": 10618160.0,
|
|
"step": 5425
|
|
},
|
|
{
|
|
"entropy": 6.421460199356079,
|
|
"epoch": 0.542810016494227,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.0004977827457894174,
|
|
"loss": 6.3537,
|
|
"mean_token_accuracy": 0.13131480067968368,
|
|
"num_tokens": 10628839.0,
|
|
"step": 5430
|
|
},
|
|
{
|
|
"entropy": 6.460460519790649,
|
|
"epoch": 0.5433098415554556,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004977777450067937,
|
|
"loss": 6.3418,
|
|
"mean_token_accuracy": 0.1394140265882015,
|
|
"num_tokens": 10638312.0,
|
|
"step": 5435
|
|
},
|
|
{
|
|
"entropy": 6.474530363082886,
|
|
"epoch": 0.5438096666166842,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004977727386191393,
|
|
"loss": 6.34,
|
|
"mean_token_accuracy": 0.13660069406032563,
|
|
"num_tokens": 10647128.0,
|
|
"step": 5440
|
|
},
|
|
{
|
|
"entropy": 6.42323112487793,
|
|
"epoch": 0.5443094916779128,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.0004977677266265802,
|
|
"loss": 6.4833,
|
|
"mean_token_accuracy": 0.13081137612462043,
|
|
"num_tokens": 10657574.0,
|
|
"step": 5445
|
|
},
|
|
{
|
|
"entropy": 6.390897369384765,
|
|
"epoch": 0.5448093167391413,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004977627090292424,
|
|
"loss": 6.3382,
|
|
"mean_token_accuracy": 0.13386189714074134,
|
|
"num_tokens": 10668497.0,
|
|
"step": 5450
|
|
},
|
|
{
|
|
"entropy": 6.447263383865357,
|
|
"epoch": 0.5453091418003698,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004977576858272521,
|
|
"loss": 6.3542,
|
|
"mean_token_accuracy": 0.13918982222676277,
|
|
"num_tokens": 10678728.0,
|
|
"step": 5455
|
|
},
|
|
{
|
|
"entropy": 6.445428705215454,
|
|
"epoch": 0.5458089668615984,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004977526570207358,
|
|
"loss": 6.3574,
|
|
"mean_token_accuracy": 0.1380918189883232,
|
|
"num_tokens": 10688953.0,
|
|
"step": 5460
|
|
},
|
|
{
|
|
"entropy": 6.358369588851929,
|
|
"epoch": 0.546308791922827,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004977476226098199,
|
|
"loss": 6.3195,
|
|
"mean_token_accuracy": 0.1424561321735382,
|
|
"num_tokens": 10698570.0,
|
|
"step": 5465
|
|
},
|
|
{
|
|
"entropy": 6.385986232757569,
|
|
"epoch": 0.5468086169840556,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004977425825946312,
|
|
"loss": 6.2164,
|
|
"mean_token_accuracy": 0.15032757222652435,
|
|
"num_tokens": 10708438.0,
|
|
"step": 5470
|
|
},
|
|
{
|
|
"entropy": 6.409063243865967,
|
|
"epoch": 0.5473084420452842,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004977375369752964,
|
|
"loss": 6.2968,
|
|
"mean_token_accuracy": 0.1432842992246151,
|
|
"num_tokens": 10718559.0,
|
|
"step": 5475
|
|
},
|
|
{
|
|
"entropy": 6.278464078903198,
|
|
"epoch": 0.5478082671065128,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004977324857519425,
|
|
"loss": 6.4167,
|
|
"mean_token_accuracy": 0.13704861402511598,
|
|
"num_tokens": 10729348.0,
|
|
"step": 5480
|
|
},
|
|
{
|
|
"entropy": 6.529194259643555,
|
|
"epoch": 0.5483080921677413,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004977274289246967,
|
|
"loss": 6.3946,
|
|
"mean_token_accuracy": 0.1368100695312023,
|
|
"num_tokens": 10739139.0,
|
|
"step": 5485
|
|
},
|
|
{
|
|
"entropy": 6.433472776412964,
|
|
"epoch": 0.5488079172289698,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004977223664936859,
|
|
"loss": 6.4331,
|
|
"mean_token_accuracy": 0.1324752040207386,
|
|
"num_tokens": 10749451.0,
|
|
"step": 5490
|
|
},
|
|
{
|
|
"entropy": 6.420543003082275,
|
|
"epoch": 0.5493077422901984,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004977172984590378,
|
|
"loss": 6.2767,
|
|
"mean_token_accuracy": 0.14483995437622071,
|
|
"num_tokens": 10757990.0,
|
|
"step": 5495
|
|
},
|
|
{
|
|
"entropy": 6.463605546951294,
|
|
"epoch": 0.549807567351427,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004977122248208798,
|
|
"loss": 6.2347,
|
|
"mean_token_accuracy": 0.14013865888118743,
|
|
"num_tokens": 10766825.0,
|
|
"step": 5500
|
|
},
|
|
{
|
|
"entropy": 6.337217140197754,
|
|
"epoch": 0.5503073924126556,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004977071455793394,
|
|
"loss": 6.3059,
|
|
"mean_token_accuracy": 0.13765543773770333,
|
|
"num_tokens": 10776670.0,
|
|
"step": 5505
|
|
},
|
|
{
|
|
"entropy": 6.328641700744629,
|
|
"epoch": 0.5508072174738842,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004977020607345445,
|
|
"loss": 6.2604,
|
|
"mean_token_accuracy": 0.14444502145051957,
|
|
"num_tokens": 10787152.0,
|
|
"step": 5510
|
|
},
|
|
{
|
|
"entropy": 6.4152027606964115,
|
|
"epoch": 0.5513070425351128,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004976969702866231,
|
|
"loss": 6.3943,
|
|
"mean_token_accuracy": 0.1340176969766617,
|
|
"num_tokens": 10796903.0,
|
|
"step": 5515
|
|
},
|
|
{
|
|
"entropy": 6.4490638256073,
|
|
"epoch": 0.5518068675963412,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004976918742357033,
|
|
"loss": 6.3518,
|
|
"mean_token_accuracy": 0.1396077059209347,
|
|
"num_tokens": 10806549.0,
|
|
"step": 5520
|
|
},
|
|
{
|
|
"entropy": 6.55826325416565,
|
|
"epoch": 0.5523066926575698,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004976867725819133,
|
|
"loss": 6.4667,
|
|
"mean_token_accuracy": 0.12954409047961235,
|
|
"num_tokens": 10816755.0,
|
|
"step": 5525
|
|
},
|
|
{
|
|
"entropy": 6.432829999923706,
|
|
"epoch": 0.5528065177187984,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004976816653253813,
|
|
"loss": 6.3043,
|
|
"mean_token_accuracy": 0.13626608103513718,
|
|
"num_tokens": 10827171.0,
|
|
"step": 5530
|
|
},
|
|
{
|
|
"entropy": 6.405724048614502,
|
|
"epoch": 0.553306342780027,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004976765524662359,
|
|
"loss": 6.3277,
|
|
"mean_token_accuracy": 0.13775218650698662,
|
|
"num_tokens": 10837048.0,
|
|
"step": 5535
|
|
},
|
|
{
|
|
"entropy": 6.480524730682373,
|
|
"epoch": 0.5538061678412556,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004976714340046058,
|
|
"loss": 6.3299,
|
|
"mean_token_accuracy": 0.13683032765984535,
|
|
"num_tokens": 10846775.0,
|
|
"step": 5540
|
|
},
|
|
{
|
|
"entropy": 6.393848705291748,
|
|
"epoch": 0.5543059929024842,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004976663099406196,
|
|
"loss": 6.3462,
|
|
"mean_token_accuracy": 0.13975223451852797,
|
|
"num_tokens": 10856234.0,
|
|
"step": 5545
|
|
},
|
|
{
|
|
"entropy": 6.385819816589356,
|
|
"epoch": 0.5548058179637128,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004976611802744066,
|
|
"loss": 6.3697,
|
|
"mean_token_accuracy": 0.13305724635720254,
|
|
"num_tokens": 10865943.0,
|
|
"step": 5550
|
|
},
|
|
{
|
|
"entropy": 6.4838074207305905,
|
|
"epoch": 0.5553056430249412,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004976560450060954,
|
|
"loss": 6.2818,
|
|
"mean_token_accuracy": 0.1389782540500164,
|
|
"num_tokens": 10875286.0,
|
|
"step": 5555
|
|
},
|
|
{
|
|
"entropy": 6.499625110626221,
|
|
"epoch": 0.5558054680861698,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004976509041358154,
|
|
"loss": 6.3717,
|
|
"mean_token_accuracy": 0.1385914698243141,
|
|
"num_tokens": 10884491.0,
|
|
"step": 5560
|
|
},
|
|
{
|
|
"entropy": 6.310593986511231,
|
|
"epoch": 0.5563052931473984,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000497645757663696,
|
|
"loss": 6.2337,
|
|
"mean_token_accuracy": 0.1463724382221699,
|
|
"num_tokens": 10892773.0,
|
|
"step": 5565
|
|
},
|
|
{
|
|
"entropy": 6.375320720672607,
|
|
"epoch": 0.556805118208627,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004976406055898665,
|
|
"loss": 6.3869,
|
|
"mean_token_accuracy": 0.13724598586559295,
|
|
"num_tokens": 10903517.0,
|
|
"step": 5570
|
|
},
|
|
{
|
|
"entropy": 6.4880389213562015,
|
|
"epoch": 0.5573049432698556,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004976354479144568,
|
|
"loss": 6.3472,
|
|
"mean_token_accuracy": 0.14230165705084802,
|
|
"num_tokens": 10913075.0,
|
|
"step": 5575
|
|
},
|
|
{
|
|
"entropy": 6.462172603607177,
|
|
"epoch": 0.5578047683310842,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004976302846375965,
|
|
"loss": 6.3483,
|
|
"mean_token_accuracy": 0.14335301369428635,
|
|
"num_tokens": 10922962.0,
|
|
"step": 5580
|
|
},
|
|
{
|
|
"entropy": 6.373585605621338,
|
|
"epoch": 0.5583045933923126,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004976251157594155,
|
|
"loss": 6.2853,
|
|
"mean_token_accuracy": 0.13618385270237923,
|
|
"num_tokens": 10932192.0,
|
|
"step": 5585
|
|
},
|
|
{
|
|
"entropy": 6.384717607498169,
|
|
"epoch": 0.5588044184535412,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004976199412800437,
|
|
"loss": 6.2727,
|
|
"mean_token_accuracy": 0.14798521846532822,
|
|
"num_tokens": 10941748.0,
|
|
"step": 5590
|
|
},
|
|
{
|
|
"entropy": 6.47556438446045,
|
|
"epoch": 0.5593042435147698,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004976147611996118,
|
|
"loss": 6.442,
|
|
"mean_token_accuracy": 0.13446364551782608,
|
|
"num_tokens": 10951467.0,
|
|
"step": 5595
|
|
},
|
|
{
|
|
"entropy": 6.48672456741333,
|
|
"epoch": 0.5598040685759984,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004976095755182496,
|
|
"loss": 6.3428,
|
|
"mean_token_accuracy": 0.1381102494895458,
|
|
"num_tokens": 10962598.0,
|
|
"step": 5600
|
|
},
|
|
{
|
|
"entropy": 6.37509593963623,
|
|
"epoch": 0.560303893637227,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004976043842360877,
|
|
"loss": 6.2609,
|
|
"mean_token_accuracy": 0.13521101251244544,
|
|
"num_tokens": 10971206.0,
|
|
"step": 5605
|
|
},
|
|
{
|
|
"entropy": 6.305227756500244,
|
|
"epoch": 0.5608037186984556,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.000497599187353257,
|
|
"loss": 6.2494,
|
|
"mean_token_accuracy": 0.13938769847154617,
|
|
"num_tokens": 10979922.0,
|
|
"step": 5610
|
|
},
|
|
{
|
|
"entropy": 6.3692711353302,
|
|
"epoch": 0.5613035437596842,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004975939848698879,
|
|
"loss": 6.2814,
|
|
"mean_token_accuracy": 0.14390315264463424,
|
|
"num_tokens": 10988886.0,
|
|
"step": 5615
|
|
},
|
|
{
|
|
"entropy": 6.265742683410645,
|
|
"epoch": 0.5618033688209126,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004975887767861113,
|
|
"loss": 6.2927,
|
|
"mean_token_accuracy": 0.14396480172872544,
|
|
"num_tokens": 10998570.0,
|
|
"step": 5620
|
|
},
|
|
{
|
|
"entropy": 6.376459693908691,
|
|
"epoch": 0.5623031938821412,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004975835631020585,
|
|
"loss": 6.2357,
|
|
"mean_token_accuracy": 0.14439999610185622,
|
|
"num_tokens": 11009549.0,
|
|
"step": 5625
|
|
},
|
|
{
|
|
"entropy": 6.293685102462769,
|
|
"epoch": 0.5628030189433698,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004975783438178605,
|
|
"loss": 6.127,
|
|
"mean_token_accuracy": 0.16214562952518463,
|
|
"num_tokens": 11019382.0,
|
|
"step": 5630
|
|
},
|
|
{
|
|
"entropy": 6.418667936325074,
|
|
"epoch": 0.5633028440045984,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004975731189336487,
|
|
"loss": 6.3599,
|
|
"mean_token_accuracy": 0.13114651739597322,
|
|
"num_tokens": 11028205.0,
|
|
"step": 5635
|
|
},
|
|
{
|
|
"entropy": 6.422270679473877,
|
|
"epoch": 0.563802669065827,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004975678884495544,
|
|
"loss": 6.2863,
|
|
"mean_token_accuracy": 0.14224059656262397,
|
|
"num_tokens": 11037684.0,
|
|
"step": 5640
|
|
},
|
|
{
|
|
"entropy": 6.349951314926147,
|
|
"epoch": 0.5643024941270556,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004975626523657093,
|
|
"loss": 6.2584,
|
|
"mean_token_accuracy": 0.1368769459426403,
|
|
"num_tokens": 11047119.0,
|
|
"step": 5645
|
|
},
|
|
{
|
|
"entropy": 6.251744365692138,
|
|
"epoch": 0.564802319188284,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004975574106822451,
|
|
"loss": 6.2619,
|
|
"mean_token_accuracy": 0.14665021300315856,
|
|
"num_tokens": 11057362.0,
|
|
"step": 5650
|
|
},
|
|
{
|
|
"entropy": 6.3798047542572025,
|
|
"epoch": 0.5653021442495126,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004975521633992938,
|
|
"loss": 6.216,
|
|
"mean_token_accuracy": 0.14489733055233955,
|
|
"num_tokens": 11067685.0,
|
|
"step": 5655
|
|
},
|
|
{
|
|
"entropy": 6.39489893913269,
|
|
"epoch": 0.5658019693107412,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004975469105169873,
|
|
"loss": 6.2072,
|
|
"mean_token_accuracy": 0.14295902103185654,
|
|
"num_tokens": 11077468.0,
|
|
"step": 5660
|
|
},
|
|
{
|
|
"entropy": 6.413747930526734,
|
|
"epoch": 0.5663017943719698,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004975416520354579,
|
|
"loss": 6.404,
|
|
"mean_token_accuracy": 0.1398212917149067,
|
|
"num_tokens": 11087266.0,
|
|
"step": 5665
|
|
},
|
|
{
|
|
"entropy": 6.374395275115967,
|
|
"epoch": 0.5668016194331984,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004975363879548377,
|
|
"loss": 6.2982,
|
|
"mean_token_accuracy": 0.13866044878959655,
|
|
"num_tokens": 11098053.0,
|
|
"step": 5670
|
|
},
|
|
{
|
|
"entropy": 6.532749032974243,
|
|
"epoch": 0.567301444494427,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004975311182752592,
|
|
"loss": 6.3584,
|
|
"mean_token_accuracy": 0.14000722095370294,
|
|
"num_tokens": 11107341.0,
|
|
"step": 5675
|
|
},
|
|
{
|
|
"entropy": 6.361231470108033,
|
|
"epoch": 0.5678012695556556,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004975258429968551,
|
|
"loss": 6.278,
|
|
"mean_token_accuracy": 0.13990237116813659,
|
|
"num_tokens": 11116356.0,
|
|
"step": 5680
|
|
},
|
|
{
|
|
"entropy": 6.34175477027893,
|
|
"epoch": 0.568301094616884,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004975205621197581,
|
|
"loss": 6.3034,
|
|
"mean_token_accuracy": 0.1467010609805584,
|
|
"num_tokens": 11126504.0,
|
|
"step": 5685
|
|
},
|
|
{
|
|
"entropy": 6.370285272598267,
|
|
"epoch": 0.5688009196781126,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004975152756441009,
|
|
"loss": 6.2407,
|
|
"mean_token_accuracy": 0.14483981877565383,
|
|
"num_tokens": 11136473.0,
|
|
"step": 5690
|
|
},
|
|
{
|
|
"entropy": 6.404270839691162,
|
|
"epoch": 0.5693007447393412,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004975099835700166,
|
|
"loss": 6.3122,
|
|
"mean_token_accuracy": 0.13850560039281845,
|
|
"num_tokens": 11146798.0,
|
|
"step": 5695
|
|
},
|
|
{
|
|
"entropy": 6.444261980056763,
|
|
"epoch": 0.5698005698005698,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004975046858976386,
|
|
"loss": 6.3302,
|
|
"mean_token_accuracy": 0.13601220175623893,
|
|
"num_tokens": 11156833.0,
|
|
"step": 5700
|
|
},
|
|
{
|
|
"entropy": 6.441240215301514,
|
|
"epoch": 0.5703003948617984,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004974993826270997,
|
|
"loss": 6.3672,
|
|
"mean_token_accuracy": 0.1342060700058937,
|
|
"num_tokens": 11165229.0,
|
|
"step": 5705
|
|
},
|
|
{
|
|
"entropy": 6.3729188442230225,
|
|
"epoch": 0.570800219923027,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004974940737585337,
|
|
"loss": 6.2005,
|
|
"mean_token_accuracy": 0.1447728879749775,
|
|
"num_tokens": 11174126.0,
|
|
"step": 5710
|
|
},
|
|
{
|
|
"entropy": 6.333694076538086,
|
|
"epoch": 0.5713000449842555,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.000497488759292074,
|
|
"loss": 6.2725,
|
|
"mean_token_accuracy": 0.14456492960453032,
|
|
"num_tokens": 11183558.0,
|
|
"step": 5715
|
|
},
|
|
{
|
|
"entropy": 6.397473096847534,
|
|
"epoch": 0.571799870045484,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004974834392278545,
|
|
"loss": 6.3665,
|
|
"mean_token_accuracy": 0.13695593401789666,
|
|
"num_tokens": 11193449.0,
|
|
"step": 5720
|
|
},
|
|
{
|
|
"entropy": 6.510390138626098,
|
|
"epoch": 0.5722996951067126,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004974781135660088,
|
|
"loss": 6.3552,
|
|
"mean_token_accuracy": 0.1336575262248516,
|
|
"num_tokens": 11203805.0,
|
|
"step": 5725
|
|
},
|
|
{
|
|
"entropy": 6.2931036949157715,
|
|
"epoch": 0.5727995201679412,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004974727823066709,
|
|
"loss": 6.2007,
|
|
"mean_token_accuracy": 0.1508660152554512,
|
|
"num_tokens": 11213578.0,
|
|
"step": 5730
|
|
},
|
|
{
|
|
"entropy": 6.409654521942139,
|
|
"epoch": 0.5732993452291698,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004974674454499753,
|
|
"loss": 6.4052,
|
|
"mean_token_accuracy": 0.13590671718120576,
|
|
"num_tokens": 11223398.0,
|
|
"step": 5735
|
|
},
|
|
{
|
|
"entropy": 6.534228086471558,
|
|
"epoch": 0.5737991702903984,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004974621029960559,
|
|
"loss": 6.4722,
|
|
"mean_token_accuracy": 0.1311562441289425,
|
|
"num_tokens": 11232947.0,
|
|
"step": 5740
|
|
},
|
|
{
|
|
"entropy": 6.430829477310181,
|
|
"epoch": 0.574298995351627,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004974567549450472,
|
|
"loss": 6.2514,
|
|
"mean_token_accuracy": 0.14314207136631013,
|
|
"num_tokens": 11242992.0,
|
|
"step": 5745
|
|
},
|
|
{
|
|
"entropy": 6.474722623825073,
|
|
"epoch": 0.5747988204128555,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004974514012970839,
|
|
"loss": 6.4338,
|
|
"mean_token_accuracy": 0.12969737872481346,
|
|
"num_tokens": 11252825.0,
|
|
"step": 5750
|
|
},
|
|
{
|
|
"entropy": 6.461831951141358,
|
|
"epoch": 0.575298645474084,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004974460420523005,
|
|
"loss": 6.2943,
|
|
"mean_token_accuracy": 0.13857915103435517,
|
|
"num_tokens": 11262777.0,
|
|
"step": 5755
|
|
},
|
|
{
|
|
"entropy": 6.393844127655029,
|
|
"epoch": 0.5757984705353126,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004974406772108319,
|
|
"loss": 6.3349,
|
|
"mean_token_accuracy": 0.1352956660091877,
|
|
"num_tokens": 11272828.0,
|
|
"step": 5760
|
|
},
|
|
{
|
|
"entropy": 6.438638210296631,
|
|
"epoch": 0.5762982955965412,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004974353067728132,
|
|
"loss": 6.3349,
|
|
"mean_token_accuracy": 0.13701027631759644,
|
|
"num_tokens": 11282290.0,
|
|
"step": 5765
|
|
},
|
|
{
|
|
"entropy": 6.486875677108765,
|
|
"epoch": 0.5767981206577698,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004974299307383794,
|
|
"loss": 6.3594,
|
|
"mean_token_accuracy": 0.13259207010269164,
|
|
"num_tokens": 11290844.0,
|
|
"step": 5770
|
|
},
|
|
{
|
|
"entropy": 6.417836284637451,
|
|
"epoch": 0.5772979457189984,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004974245491076656,
|
|
"loss": 6.2733,
|
|
"mean_token_accuracy": 0.1455862581729889,
|
|
"num_tokens": 11299243.0,
|
|
"step": 5775
|
|
},
|
|
{
|
|
"entropy": 6.392756128311158,
|
|
"epoch": 0.5777977707802269,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004974191618808075,
|
|
"loss": 6.3121,
|
|
"mean_token_accuracy": 0.14002888053655624,
|
|
"num_tokens": 11308556.0,
|
|
"step": 5780
|
|
},
|
|
{
|
|
"entropy": 6.4467826843261715,
|
|
"epoch": 0.5782975958414555,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004974137690579405,
|
|
"loss": 6.4027,
|
|
"mean_token_accuracy": 0.13739326298236848,
|
|
"num_tokens": 11318172.0,
|
|
"step": 5785
|
|
},
|
|
{
|
|
"entropy": 6.481961727142334,
|
|
"epoch": 0.578797420902684,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004974083706392004,
|
|
"loss": 6.37,
|
|
"mean_token_accuracy": 0.1334846369922161,
|
|
"num_tokens": 11328967.0,
|
|
"step": 5790
|
|
},
|
|
{
|
|
"entropy": 6.410213136672974,
|
|
"epoch": 0.5792972459639126,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004974029666247228,
|
|
"loss": 6.3549,
|
|
"mean_token_accuracy": 0.13774811178445817,
|
|
"num_tokens": 11339234.0,
|
|
"step": 5795
|
|
},
|
|
{
|
|
"entropy": 6.555100679397583,
|
|
"epoch": 0.5797970710251412,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004973975570146438,
|
|
"loss": 6.3383,
|
|
"mean_token_accuracy": 0.13209013119339943,
|
|
"num_tokens": 11349934.0,
|
|
"step": 5800
|
|
},
|
|
{
|
|
"entropy": 6.487929391860962,
|
|
"epoch": 0.5802968960863698,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004973921418090997,
|
|
"loss": 6.4426,
|
|
"mean_token_accuracy": 0.1348351262509823,
|
|
"num_tokens": 11359817.0,
|
|
"step": 5805
|
|
},
|
|
{
|
|
"entropy": 6.3201491355896,
|
|
"epoch": 0.5807967211475984,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004973867210082263,
|
|
"loss": 6.231,
|
|
"mean_token_accuracy": 0.1433400556445122,
|
|
"num_tokens": 11369565.0,
|
|
"step": 5810
|
|
},
|
|
{
|
|
"entropy": 6.4635889530181885,
|
|
"epoch": 0.5812965462088269,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004973812946121603,
|
|
"loss": 6.3417,
|
|
"mean_token_accuracy": 0.13727482929825782,
|
|
"num_tokens": 11379543.0,
|
|
"step": 5815
|
|
},
|
|
{
|
|
"entropy": 6.470111989974976,
|
|
"epoch": 0.5817963712700555,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004973758626210382,
|
|
"loss": 6.3705,
|
|
"mean_token_accuracy": 0.13818111643195152,
|
|
"num_tokens": 11388909.0,
|
|
"step": 5820
|
|
},
|
|
{
|
|
"entropy": 6.4237206935882565,
|
|
"epoch": 0.582296196331284,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004973704250349965,
|
|
"loss": 6.408,
|
|
"mean_token_accuracy": 0.13562145829200745,
|
|
"num_tokens": 11399774.0,
|
|
"step": 5825
|
|
},
|
|
{
|
|
"entropy": 6.384641695022583,
|
|
"epoch": 0.5827960213925126,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004973649818541722,
|
|
"loss": 6.2902,
|
|
"mean_token_accuracy": 0.13921330794692038,
|
|
"num_tokens": 11408701.0,
|
|
"step": 5830
|
|
},
|
|
{
|
|
"entropy": 6.441925477981568,
|
|
"epoch": 0.5832958464537412,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004973595330787022,
|
|
"loss": 6.278,
|
|
"mean_token_accuracy": 0.13829041719436647,
|
|
"num_tokens": 11418582.0,
|
|
"step": 5835
|
|
},
|
|
{
|
|
"entropy": 6.426104784011841,
|
|
"epoch": 0.5837956715149698,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004973540787087235,
|
|
"loss": 6.3553,
|
|
"mean_token_accuracy": 0.13323938548564912,
|
|
"num_tokens": 11429155.0,
|
|
"step": 5840
|
|
},
|
|
{
|
|
"entropy": 6.451894903182984,
|
|
"epoch": 0.5842954965761983,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004973486187443734,
|
|
"loss": 6.1996,
|
|
"mean_token_accuracy": 0.14416561275720596,
|
|
"num_tokens": 11438798.0,
|
|
"step": 5845
|
|
},
|
|
{
|
|
"entropy": 6.370334959030151,
|
|
"epoch": 0.5847953216374269,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004973431531857893,
|
|
"loss": 6.3668,
|
|
"mean_token_accuracy": 0.1347464457154274,
|
|
"num_tokens": 11449862.0,
|
|
"step": 5850
|
|
},
|
|
{
|
|
"entropy": 6.389704418182373,
|
|
"epoch": 0.5852951466986555,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004973376820331087,
|
|
"loss": 6.3353,
|
|
"mean_token_accuracy": 0.13906349390745162,
|
|
"num_tokens": 11459697.0,
|
|
"step": 5855
|
|
},
|
|
{
|
|
"entropy": 6.568944025039673,
|
|
"epoch": 0.585794971759884,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004973322052864692,
|
|
"loss": 6.4479,
|
|
"mean_token_accuracy": 0.13794757351279258,
|
|
"num_tokens": 11468973.0,
|
|
"step": 5860
|
|
},
|
|
{
|
|
"entropy": 6.350123071670533,
|
|
"epoch": 0.5862947968211126,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.0004973267229460087,
|
|
"loss": 6.2825,
|
|
"mean_token_accuracy": 0.14003330916166307,
|
|
"num_tokens": 11479453.0,
|
|
"step": 5865
|
|
},
|
|
{
|
|
"entropy": 6.348764133453369,
|
|
"epoch": 0.5867946218823412,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.000497321235011865,
|
|
"loss": 6.3255,
|
|
"mean_token_accuracy": 0.1448430150747299,
|
|
"num_tokens": 11488642.0,
|
|
"step": 5870
|
|
},
|
|
{
|
|
"entropy": 6.46609206199646,
|
|
"epoch": 0.5872944469435698,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004973157414841763,
|
|
"loss": 6.2234,
|
|
"mean_token_accuracy": 0.1438489742577076,
|
|
"num_tokens": 11497898.0,
|
|
"step": 5875
|
|
},
|
|
{
|
|
"entropy": 6.345861911773682,
|
|
"epoch": 0.5877942720047983,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004973102423630806,
|
|
"loss": 6.3128,
|
|
"mean_token_accuracy": 0.1439259171485901,
|
|
"num_tokens": 11508337.0,
|
|
"step": 5880
|
|
},
|
|
{
|
|
"entropy": 6.454480886459351,
|
|
"epoch": 0.5882940970660269,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004973047376487166,
|
|
"loss": 6.3716,
|
|
"mean_token_accuracy": 0.1348287396132946,
|
|
"num_tokens": 11518045.0,
|
|
"step": 5885
|
|
},
|
|
{
|
|
"entropy": 6.3810920238494875,
|
|
"epoch": 0.5887939221272555,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004972992273412224,
|
|
"loss": 6.2677,
|
|
"mean_token_accuracy": 0.1362629845738411,
|
|
"num_tokens": 11527297.0,
|
|
"step": 5890
|
|
},
|
|
{
|
|
"entropy": 6.40717921257019,
|
|
"epoch": 0.589293747188484,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004972937114407369,
|
|
"loss": 6.2796,
|
|
"mean_token_accuracy": 0.1401158943772316,
|
|
"num_tokens": 11537674.0,
|
|
"step": 5895
|
|
},
|
|
{
|
|
"entropy": 6.4201148509979244,
|
|
"epoch": 0.5897935722497126,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000497288189947399,
|
|
"loss": 6.3198,
|
|
"mean_token_accuracy": 0.13654682859778405,
|
|
"num_tokens": 11548046.0,
|
|
"step": 5900
|
|
},
|
|
{
|
|
"entropy": 6.358149099349975,
|
|
"epoch": 0.5902933973109412,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004972826628613472,
|
|
"loss": 6.3285,
|
|
"mean_token_accuracy": 0.1363440714776516,
|
|
"num_tokens": 11558075.0,
|
|
"step": 5905
|
|
},
|
|
{
|
|
"entropy": 6.422307348251342,
|
|
"epoch": 0.5907932223721697,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004972771301827209,
|
|
"loss": 6.3127,
|
|
"mean_token_accuracy": 0.14183902814984323,
|
|
"num_tokens": 11567983.0,
|
|
"step": 5910
|
|
},
|
|
{
|
|
"entropy": 6.358101272583008,
|
|
"epoch": 0.5912930474333983,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004972715919116592,
|
|
"loss": 6.2968,
|
|
"mean_token_accuracy": 0.13985158875584602,
|
|
"num_tokens": 11577438.0,
|
|
"step": 5915
|
|
},
|
|
{
|
|
"entropy": 6.39671106338501,
|
|
"epoch": 0.5917928724946269,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004972660480483015,
|
|
"loss": 6.209,
|
|
"mean_token_accuracy": 0.14532208442687988,
|
|
"num_tokens": 11586579.0,
|
|
"step": 5920
|
|
},
|
|
{
|
|
"entropy": 6.3205595970153805,
|
|
"epoch": 0.5922926975558555,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004972604985927871,
|
|
"loss": 6.3116,
|
|
"mean_token_accuracy": 0.14388131871819496,
|
|
"num_tokens": 11595380.0,
|
|
"step": 5925
|
|
},
|
|
{
|
|
"entropy": 6.387597513198853,
|
|
"epoch": 0.592792522617084,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004972549435452558,
|
|
"loss": 6.2972,
|
|
"mean_token_accuracy": 0.13740020841360093,
|
|
"num_tokens": 11605383.0,
|
|
"step": 5930
|
|
},
|
|
{
|
|
"entropy": 6.463783597946167,
|
|
"epoch": 0.5932923476783126,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004972493829058474,
|
|
"loss": 6.359,
|
|
"mean_token_accuracy": 0.14069342389702796,
|
|
"num_tokens": 11614783.0,
|
|
"step": 5935
|
|
},
|
|
{
|
|
"entropy": 6.466608619689941,
|
|
"epoch": 0.5937921727395412,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004972438166747016,
|
|
"loss": 6.3119,
|
|
"mean_token_accuracy": 0.13708549216389657,
|
|
"num_tokens": 11624524.0,
|
|
"step": 5940
|
|
},
|
|
{
|
|
"entropy": 6.298400211334228,
|
|
"epoch": 0.5942919978007697,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004972382448519586,
|
|
"loss": 6.1874,
|
|
"mean_token_accuracy": 0.1489984482526779,
|
|
"num_tokens": 11633908.0,
|
|
"step": 5945
|
|
},
|
|
{
|
|
"entropy": 6.313541412353516,
|
|
"epoch": 0.5947918228619983,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004972326674377586,
|
|
"loss": 6.2471,
|
|
"mean_token_accuracy": 0.14342263489961624,
|
|
"num_tokens": 11644076.0,
|
|
"step": 5950
|
|
},
|
|
{
|
|
"entropy": 6.478358364105224,
|
|
"epoch": 0.5952916479232269,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004972270844322418,
|
|
"loss": 6.3154,
|
|
"mean_token_accuracy": 0.1340063951909542,
|
|
"num_tokens": 11652754.0,
|
|
"step": 5955
|
|
},
|
|
{
|
|
"entropy": 6.3840117931365965,
|
|
"epoch": 0.5957914729844555,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004972214958355488,
|
|
"loss": 6.2413,
|
|
"mean_token_accuracy": 0.14417502284049988,
|
|
"num_tokens": 11663468.0,
|
|
"step": 5960
|
|
},
|
|
{
|
|
"entropy": 6.2802550315856935,
|
|
"epoch": 0.596291298045684,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004972159016478201,
|
|
"loss": 6.3219,
|
|
"mean_token_accuracy": 0.1371239349246025,
|
|
"num_tokens": 11672711.0,
|
|
"step": 5965
|
|
},
|
|
{
|
|
"entropy": 6.364471530914306,
|
|
"epoch": 0.5967911231069126,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004972103018691965,
|
|
"loss": 6.2571,
|
|
"mean_token_accuracy": 0.14432041645050048,
|
|
"num_tokens": 11681800.0,
|
|
"step": 5970
|
|
},
|
|
{
|
|
"entropy": 6.402378940582276,
|
|
"epoch": 0.5972909481681411,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004972046964998189,
|
|
"loss": 6.2579,
|
|
"mean_token_accuracy": 0.15038390457630157,
|
|
"num_tokens": 11691229.0,
|
|
"step": 5975
|
|
},
|
|
{
|
|
"entropy": 6.344723320007324,
|
|
"epoch": 0.5977907732293697,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004971990855398283,
|
|
"loss": 6.2803,
|
|
"mean_token_accuracy": 0.1394992120563984,
|
|
"num_tokens": 11700027.0,
|
|
"step": 5980
|
|
},
|
|
{
|
|
"entropy": 6.363552808761597,
|
|
"epoch": 0.5982905982905983,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004971934689893658,
|
|
"loss": 6.2544,
|
|
"mean_token_accuracy": 0.14758194386959075,
|
|
"num_tokens": 11708899.0,
|
|
"step": 5985
|
|
},
|
|
{
|
|
"entropy": 6.332235479354859,
|
|
"epoch": 0.5987904233518269,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004971878468485729,
|
|
"loss": 6.2442,
|
|
"mean_token_accuracy": 0.1447736620903015,
|
|
"num_tokens": 11719325.0,
|
|
"step": 5990
|
|
},
|
|
{
|
|
"entropy": 6.4186420917510985,
|
|
"epoch": 0.5992902484130554,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000497182219117591,
|
|
"loss": 6.3036,
|
|
"mean_token_accuracy": 0.14428125098347663,
|
|
"num_tokens": 11728835.0,
|
|
"step": 5995
|
|
},
|
|
{
|
|
"entropy": 6.458810138702392,
|
|
"epoch": 0.599790073474284,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004971765857965615,
|
|
"loss": 6.3674,
|
|
"mean_token_accuracy": 0.1335064485669136,
|
|
"num_tokens": 11738252.0,
|
|
"step": 6000
|
|
},
|
|
{
|
|
"epoch": 0.599790073474284,
|
|
"eval_entropy": 6.222119353106882,
|
|
"eval_loss": 6.3355512619018555,
|
|
"eval_mean_token_accuracy": 0.14418950053812593,
|
|
"eval_num_tokens": 11738252.0,
|
|
"eval_runtime": 23.5717,
|
|
"eval_samples_per_second": 1317.044,
|
|
"eval_steps_per_second": 164.646,
|
|
"step": 6000
|
|
},
|
|
{
|
|
"entropy": 6.325327777862549,
|
|
"epoch": 0.6002898985355126,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004971709468856263,
|
|
"loss": 6.2236,
|
|
"mean_token_accuracy": 0.14892019629478453,
|
|
"num_tokens": 11748448.0,
|
|
"step": 6005
|
|
},
|
|
{
|
|
"entropy": 6.398207139968872,
|
|
"epoch": 0.6007897235967411,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004971653023849274,
|
|
"loss": 6.3865,
|
|
"mean_token_accuracy": 0.13725630715489387,
|
|
"num_tokens": 11757835.0,
|
|
"step": 6010
|
|
},
|
|
{
|
|
"entropy": 6.421339845657348,
|
|
"epoch": 0.6012895486579697,
|
|
"grad_norm": 2.375,
|
|
"learning_rate": 0.0004971596522946065,
|
|
"loss": 6.3902,
|
|
"mean_token_accuracy": 0.13375852182507514,
|
|
"num_tokens": 11767792.0,
|
|
"step": 6015
|
|
},
|
|
{
|
|
"entropy": 6.409697961807251,
|
|
"epoch": 0.6017893737191983,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004971539966148059,
|
|
"loss": 6.2522,
|
|
"mean_token_accuracy": 0.1491508424282074,
|
|
"num_tokens": 11777329.0,
|
|
"step": 6020
|
|
},
|
|
{
|
|
"entropy": 6.45603346824646,
|
|
"epoch": 0.6022891987804269,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004971483353456681,
|
|
"loss": 6.3417,
|
|
"mean_token_accuracy": 0.13632039725780487,
|
|
"num_tokens": 11786776.0,
|
|
"step": 6025
|
|
},
|
|
{
|
|
"entropy": 6.340818881988525,
|
|
"epoch": 0.6027890238416554,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004971426684873352,
|
|
"loss": 6.2798,
|
|
"mean_token_accuracy": 0.14493238925933838,
|
|
"num_tokens": 11797669.0,
|
|
"step": 6030
|
|
},
|
|
{
|
|
"entropy": 6.345732593536377,
|
|
"epoch": 0.603288848902884,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004971369960399499,
|
|
"loss": 6.2366,
|
|
"mean_token_accuracy": 0.14206422567367555,
|
|
"num_tokens": 11807661.0,
|
|
"step": 6035
|
|
},
|
|
{
|
|
"entropy": 6.460015678405762,
|
|
"epoch": 0.6037886739641125,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.000497131318003655,
|
|
"loss": 6.3393,
|
|
"mean_token_accuracy": 0.13968021869659425,
|
|
"num_tokens": 11817943.0,
|
|
"step": 6040
|
|
},
|
|
{
|
|
"entropy": 6.445551586151123,
|
|
"epoch": 0.6042884990253411,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004971256343785932,
|
|
"loss": 6.2836,
|
|
"mean_token_accuracy": 0.13863051161170006,
|
|
"num_tokens": 11826896.0,
|
|
"step": 6045
|
|
},
|
|
{
|
|
"entropy": 6.375212240219116,
|
|
"epoch": 0.6047883240865697,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004971199451649078,
|
|
"loss": 6.2311,
|
|
"mean_token_accuracy": 0.14266153275966645,
|
|
"num_tokens": 11836306.0,
|
|
"step": 6050
|
|
},
|
|
{
|
|
"entropy": 6.270658349990844,
|
|
"epoch": 0.6052881491477983,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004971142503627415,
|
|
"loss": 6.3285,
|
|
"mean_token_accuracy": 0.14062388837337494,
|
|
"num_tokens": 11845998.0,
|
|
"step": 6055
|
|
},
|
|
{
|
|
"entropy": 6.43452296257019,
|
|
"epoch": 0.6057879742090269,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.000497108549972238,
|
|
"loss": 6.3235,
|
|
"mean_token_accuracy": 0.13975783661007882,
|
|
"num_tokens": 11855009.0,
|
|
"step": 6060
|
|
},
|
|
{
|
|
"entropy": 6.4450713157653805,
|
|
"epoch": 0.6062877992702554,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004971028439935404,
|
|
"loss": 6.1624,
|
|
"mean_token_accuracy": 0.14758953154087068,
|
|
"num_tokens": 11865163.0,
|
|
"step": 6065
|
|
},
|
|
{
|
|
"entropy": 6.294251155853272,
|
|
"epoch": 0.606787624331484,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004970971324267925,
|
|
"loss": 6.4501,
|
|
"mean_token_accuracy": 0.13839514106512069,
|
|
"num_tokens": 11875720.0,
|
|
"step": 6070
|
|
},
|
|
{
|
|
"entropy": 6.459564876556397,
|
|
"epoch": 0.6072874493927125,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004970914152721378,
|
|
"loss": 6.3616,
|
|
"mean_token_accuracy": 0.140549136698246,
|
|
"num_tokens": 11884247.0,
|
|
"step": 6075
|
|
},
|
|
{
|
|
"entropy": 6.385787153244019,
|
|
"epoch": 0.6077872744539411,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004970856925297204,
|
|
"loss": 6.2151,
|
|
"mean_token_accuracy": 0.1424304224550724,
|
|
"num_tokens": 11894978.0,
|
|
"step": 6080
|
|
},
|
|
{
|
|
"entropy": 6.377972269058228,
|
|
"epoch": 0.6082870995151697,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000497079964199684,
|
|
"loss": 6.3207,
|
|
"mean_token_accuracy": 0.13819993436336517,
|
|
"num_tokens": 11904904.0,
|
|
"step": 6085
|
|
},
|
|
{
|
|
"entropy": 6.467128086090088,
|
|
"epoch": 0.6087869245763983,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004970742302821729,
|
|
"loss": 6.3632,
|
|
"mean_token_accuracy": 0.13567261695861815,
|
|
"num_tokens": 11915339.0,
|
|
"step": 6090
|
|
},
|
|
{
|
|
"entropy": 6.372006750106811,
|
|
"epoch": 0.6092867496376269,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004970684907773312,
|
|
"loss": 6.2845,
|
|
"mean_token_accuracy": 0.13606042191386222,
|
|
"num_tokens": 11925451.0,
|
|
"step": 6095
|
|
},
|
|
{
|
|
"entropy": 6.32097544670105,
|
|
"epoch": 0.6097865746988554,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004970627456853036,
|
|
"loss": 6.2565,
|
|
"mean_token_accuracy": 0.1369823195040226,
|
|
"num_tokens": 11934931.0,
|
|
"step": 6100
|
|
},
|
|
{
|
|
"entropy": 6.380632066726685,
|
|
"epoch": 0.6102863997600839,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004970569950062343,
|
|
"loss": 6.1756,
|
|
"mean_token_accuracy": 0.15396128892898558,
|
|
"num_tokens": 11943492.0,
|
|
"step": 6105
|
|
},
|
|
{
|
|
"entropy": 6.380721664428711,
|
|
"epoch": 0.6107862248213125,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004970512387402682,
|
|
"loss": 6.3263,
|
|
"mean_token_accuracy": 0.13436108753085135,
|
|
"num_tokens": 11952880.0,
|
|
"step": 6110
|
|
},
|
|
{
|
|
"entropy": 6.472577905654907,
|
|
"epoch": 0.6112860498825411,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004970454768875501,
|
|
"loss": 6.2861,
|
|
"mean_token_accuracy": 0.14190733432769775,
|
|
"num_tokens": 11961840.0,
|
|
"step": 6115
|
|
},
|
|
{
|
|
"entropy": 6.404052686691284,
|
|
"epoch": 0.6117858749437697,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004970397094482249,
|
|
"loss": 6.3363,
|
|
"mean_token_accuracy": 0.14052857607603073,
|
|
"num_tokens": 11970833.0,
|
|
"step": 6120
|
|
},
|
|
{
|
|
"entropy": 6.338464975357056,
|
|
"epoch": 0.6122857000049983,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004970339364224378,
|
|
"loss": 6.3224,
|
|
"mean_token_accuracy": 0.13694415241479874,
|
|
"num_tokens": 11980497.0,
|
|
"step": 6125
|
|
},
|
|
{
|
|
"entropy": 6.460524559020996,
|
|
"epoch": 0.6127855250662269,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004970281578103339,
|
|
"loss": 6.2292,
|
|
"mean_token_accuracy": 0.1439013287425041,
|
|
"num_tokens": 11989505.0,
|
|
"step": 6130
|
|
},
|
|
{
|
|
"entropy": 6.408053779602051,
|
|
"epoch": 0.6132853501274554,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004970223736120587,
|
|
"loss": 6.341,
|
|
"mean_token_accuracy": 0.13839608207345008,
|
|
"num_tokens": 11998952.0,
|
|
"step": 6135
|
|
},
|
|
{
|
|
"entropy": 6.287954950332642,
|
|
"epoch": 0.6137851751886839,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004970165838277578,
|
|
"loss": 6.1233,
|
|
"mean_token_accuracy": 0.1451805427670479,
|
|
"num_tokens": 12009249.0,
|
|
"step": 6140
|
|
},
|
|
{
|
|
"entropy": 6.353747034072876,
|
|
"epoch": 0.6142850002499125,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004970107884575767,
|
|
"loss": 6.2299,
|
|
"mean_token_accuracy": 0.14374330639839172,
|
|
"num_tokens": 12018345.0,
|
|
"step": 6145
|
|
},
|
|
{
|
|
"entropy": 6.419749116897583,
|
|
"epoch": 0.6147848253111411,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004970049875016613,
|
|
"loss": 6.2872,
|
|
"mean_token_accuracy": 0.14101603254675865,
|
|
"num_tokens": 12026530.0,
|
|
"step": 6150
|
|
},
|
|
{
|
|
"entropy": 6.288591432571411,
|
|
"epoch": 0.6152846503723697,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004969991809601576,
|
|
"loss": 6.2292,
|
|
"mean_token_accuracy": 0.14639043360948562,
|
|
"num_tokens": 12036232.0,
|
|
"step": 6155
|
|
},
|
|
{
|
|
"entropy": 6.28270525932312,
|
|
"epoch": 0.6157844754335983,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004969933688332115,
|
|
"loss": 6.1509,
|
|
"mean_token_accuracy": 0.15005660951137542,
|
|
"num_tokens": 12045668.0,
|
|
"step": 6160
|
|
},
|
|
{
|
|
"entropy": 6.331249141693116,
|
|
"epoch": 0.6162843004948269,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004969875511209694,
|
|
"loss": 6.1846,
|
|
"mean_token_accuracy": 0.151524630934,
|
|
"num_tokens": 12055544.0,
|
|
"step": 6165
|
|
},
|
|
{
|
|
"entropy": 6.4789731979370115,
|
|
"epoch": 0.6167841255560553,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004969817278235777,
|
|
"loss": 6.3812,
|
|
"mean_token_accuracy": 0.13332609012722968,
|
|
"num_tokens": 12065076.0,
|
|
"step": 6170
|
|
},
|
|
{
|
|
"entropy": 6.428238248825073,
|
|
"epoch": 0.6172839506172839,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004969758989411829,
|
|
"loss": 6.3562,
|
|
"mean_token_accuracy": 0.1403255730867386,
|
|
"num_tokens": 12074623.0,
|
|
"step": 6175
|
|
},
|
|
{
|
|
"entropy": 6.40726146697998,
|
|
"epoch": 0.6177837756785125,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004969700644739315,
|
|
"loss": 6.2462,
|
|
"mean_token_accuracy": 0.14269398003816605,
|
|
"num_tokens": 12085040.0,
|
|
"step": 6180
|
|
},
|
|
{
|
|
"entropy": 6.3842200756073,
|
|
"epoch": 0.6182836007397411,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004969642244219705,
|
|
"loss": 6.2858,
|
|
"mean_token_accuracy": 0.1406437113881111,
|
|
"num_tokens": 12094699.0,
|
|
"step": 6185
|
|
},
|
|
{
|
|
"entropy": 6.470867395401001,
|
|
"epoch": 0.6187834258009697,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004969583787854467,
|
|
"loss": 6.2961,
|
|
"mean_token_accuracy": 0.1383143611252308,
|
|
"num_tokens": 12104256.0,
|
|
"step": 6190
|
|
},
|
|
{
|
|
"entropy": 6.342094802856446,
|
|
"epoch": 0.6192832508621983,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004969525275645071,
|
|
"loss": 6.2767,
|
|
"mean_token_accuracy": 0.1414248526096344,
|
|
"num_tokens": 12114058.0,
|
|
"step": 6195
|
|
},
|
|
{
|
|
"entropy": 6.2767980098724365,
|
|
"epoch": 0.6197830759234269,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004969466707592991,
|
|
"loss": 6.3137,
|
|
"mean_token_accuracy": 0.14230649843811988,
|
|
"num_tokens": 12124483.0,
|
|
"step": 6200
|
|
},
|
|
{
|
|
"entropy": 6.425835084915161,
|
|
"epoch": 0.6202829009846553,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00049694080836997,
|
|
"loss": 6.3082,
|
|
"mean_token_accuracy": 0.14319800660014154,
|
|
"num_tokens": 12134700.0,
|
|
"step": 6205
|
|
},
|
|
{
|
|
"entropy": 6.489741659164428,
|
|
"epoch": 0.6207827260458839,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004969349403966672,
|
|
"loss": 6.3279,
|
|
"mean_token_accuracy": 0.13634368106722833,
|
|
"num_tokens": 12144688.0,
|
|
"step": 6210
|
|
},
|
|
{
|
|
"entropy": 6.350111293792724,
|
|
"epoch": 0.6212825511071125,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004969290668395385,
|
|
"loss": 6.1983,
|
|
"mean_token_accuracy": 0.14928776174783706,
|
|
"num_tokens": 12154597.0,
|
|
"step": 6215
|
|
},
|
|
{
|
|
"entropy": 6.39958701133728,
|
|
"epoch": 0.6217823761683411,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004969231876987315,
|
|
"loss": 6.366,
|
|
"mean_token_accuracy": 0.13354292288422584,
|
|
"num_tokens": 12164730.0,
|
|
"step": 6220
|
|
},
|
|
{
|
|
"entropy": 6.458413171768188,
|
|
"epoch": 0.6222822012295697,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004969173029743942,
|
|
"loss": 6.416,
|
|
"mean_token_accuracy": 0.1325943648815155,
|
|
"num_tokens": 12174238.0,
|
|
"step": 6225
|
|
},
|
|
{
|
|
"entropy": 6.3747138500213625,
|
|
"epoch": 0.6227820262907983,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004969114126666746,
|
|
"loss": 6.261,
|
|
"mean_token_accuracy": 0.13903287425637245,
|
|
"num_tokens": 12183124.0,
|
|
"step": 6230
|
|
},
|
|
{
|
|
"entropy": 6.434756898880005,
|
|
"epoch": 0.6232818513520267,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004969055167757211,
|
|
"loss": 6.2724,
|
|
"mean_token_accuracy": 0.1443145103752613,
|
|
"num_tokens": 12192076.0,
|
|
"step": 6235
|
|
},
|
|
{
|
|
"entropy": 6.368928384780884,
|
|
"epoch": 0.6237816764132553,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004968996153016819,
|
|
"loss": 6.244,
|
|
"mean_token_accuracy": 0.14949045404791833,
|
|
"num_tokens": 12201244.0,
|
|
"step": 6240
|
|
},
|
|
{
|
|
"entropy": 6.376616477966309,
|
|
"epoch": 0.6242815014744839,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004968937082447054,
|
|
"loss": 6.3194,
|
|
"mean_token_accuracy": 0.13708976432681083,
|
|
"num_tokens": 12211349.0,
|
|
"step": 6245
|
|
},
|
|
{
|
|
"entropy": 6.39571590423584,
|
|
"epoch": 0.6247813265357125,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004968877956049403,
|
|
"loss": 6.2638,
|
|
"mean_token_accuracy": 0.13884067833423613,
|
|
"num_tokens": 12220880.0,
|
|
"step": 6250
|
|
},
|
|
{
|
|
"entropy": 6.406757259368897,
|
|
"epoch": 0.6252811515969411,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004968818773825355,
|
|
"loss": 6.3422,
|
|
"mean_token_accuracy": 0.13541234284639359,
|
|
"num_tokens": 12231398.0,
|
|
"step": 6255
|
|
},
|
|
{
|
|
"entropy": 6.470320844650269,
|
|
"epoch": 0.6257809766581697,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004968759535776396,
|
|
"loss": 6.3211,
|
|
"mean_token_accuracy": 0.13639183416962625,
|
|
"num_tokens": 12239487.0,
|
|
"step": 6260
|
|
},
|
|
{
|
|
"entropy": 6.464857482910157,
|
|
"epoch": 0.6262808017193983,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004968700241904018,
|
|
"loss": 6.4451,
|
|
"mean_token_accuracy": 0.13263344913721084,
|
|
"num_tokens": 12249984.0,
|
|
"step": 6265
|
|
},
|
|
{
|
|
"entropy": 6.422102642059326,
|
|
"epoch": 0.6267806267806267,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004968640892209714,
|
|
"loss": 6.2522,
|
|
"mean_token_accuracy": 0.1418606497347355,
|
|
"num_tokens": 12259876.0,
|
|
"step": 6270
|
|
},
|
|
{
|
|
"entropy": 6.341937017440796,
|
|
"epoch": 0.6272804518418553,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004968581486694975,
|
|
"loss": 6.2422,
|
|
"mean_token_accuracy": 0.14051881656050683,
|
|
"num_tokens": 12270262.0,
|
|
"step": 6275
|
|
},
|
|
{
|
|
"entropy": 6.332383489608764,
|
|
"epoch": 0.6277802769030839,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004968522025361297,
|
|
"loss": 6.2613,
|
|
"mean_token_accuracy": 0.1410231687128544,
|
|
"num_tokens": 12280432.0,
|
|
"step": 6280
|
|
},
|
|
{
|
|
"entropy": 6.426399374008179,
|
|
"epoch": 0.6282801019643125,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004968462508210176,
|
|
"loss": 6.2601,
|
|
"mean_token_accuracy": 0.14495118483901023,
|
|
"num_tokens": 12290518.0,
|
|
"step": 6285
|
|
},
|
|
{
|
|
"entropy": 6.441583204269409,
|
|
"epoch": 0.6287799270255411,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004968402935243109,
|
|
"loss": 6.3392,
|
|
"mean_token_accuracy": 0.13528941050171853,
|
|
"num_tokens": 12300305.0,
|
|
"step": 6290
|
|
},
|
|
{
|
|
"entropy": 6.272086238861084,
|
|
"epoch": 0.6292797520867697,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004968343306461595,
|
|
"loss": 6.2696,
|
|
"mean_token_accuracy": 0.14362943097949027,
|
|
"num_tokens": 12309079.0,
|
|
"step": 6295
|
|
},
|
|
{
|
|
"entropy": 6.456324338912964,
|
|
"epoch": 0.6297795771479981,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004968283621867134,
|
|
"loss": 6.3645,
|
|
"mean_token_accuracy": 0.13107775077223777,
|
|
"num_tokens": 12319502.0,
|
|
"step": 6300
|
|
},
|
|
{
|
|
"entropy": 6.49516339302063,
|
|
"epoch": 0.6302794022092267,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004968223881461227,
|
|
"loss": 6.238,
|
|
"mean_token_accuracy": 0.1446000263094902,
|
|
"num_tokens": 12329025.0,
|
|
"step": 6305
|
|
},
|
|
{
|
|
"entropy": 6.355226039886475,
|
|
"epoch": 0.6307792272704553,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.000496816408524538,
|
|
"loss": 6.3026,
|
|
"mean_token_accuracy": 0.1373799405992031,
|
|
"num_tokens": 12338822.0,
|
|
"step": 6310
|
|
},
|
|
{
|
|
"entropy": 6.361549615859985,
|
|
"epoch": 0.6312790523316839,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004968104233221094,
|
|
"loss": 6.3376,
|
|
"mean_token_accuracy": 0.14064089059829712,
|
|
"num_tokens": 12348592.0,
|
|
"step": 6315
|
|
},
|
|
{
|
|
"entropy": 6.360891723632813,
|
|
"epoch": 0.6317788773929125,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004968044325389877,
|
|
"loss": 6.237,
|
|
"mean_token_accuracy": 0.14268747121095657,
|
|
"num_tokens": 12357673.0,
|
|
"step": 6320
|
|
},
|
|
{
|
|
"entropy": 6.414012718200683,
|
|
"epoch": 0.6322787024541411,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004967984361753235,
|
|
"loss": 6.2885,
|
|
"mean_token_accuracy": 0.14190788641572,
|
|
"num_tokens": 12367603.0,
|
|
"step": 6325
|
|
},
|
|
{
|
|
"entropy": 6.426939821243286,
|
|
"epoch": 0.6327785275153697,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004967924342312677,
|
|
"loss": 6.2996,
|
|
"mean_token_accuracy": 0.14523561894893647,
|
|
"num_tokens": 12376532.0,
|
|
"step": 6330
|
|
},
|
|
{
|
|
"entropy": 6.366886568069458,
|
|
"epoch": 0.6332783525765981,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004967864267069713,
|
|
"loss": 6.2622,
|
|
"mean_token_accuracy": 0.14098296463489532,
|
|
"num_tokens": 12386553.0,
|
|
"step": 6335
|
|
},
|
|
{
|
|
"entropy": 6.382465600967407,
|
|
"epoch": 0.6337781776378267,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004967804136025856,
|
|
"loss": 6.291,
|
|
"mean_token_accuracy": 0.14418137967586517,
|
|
"num_tokens": 12396274.0,
|
|
"step": 6340
|
|
},
|
|
{
|
|
"entropy": 6.338514947891236,
|
|
"epoch": 0.6342780026990553,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004967743949182617,
|
|
"loss": 6.2284,
|
|
"mean_token_accuracy": 0.14256718009710312,
|
|
"num_tokens": 12405993.0,
|
|
"step": 6345
|
|
},
|
|
{
|
|
"entropy": 6.320691299438477,
|
|
"epoch": 0.6347778277602839,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004967683706541511,
|
|
"loss": 6.2761,
|
|
"mean_token_accuracy": 0.1457001529633999,
|
|
"num_tokens": 12417309.0,
|
|
"step": 6350
|
|
},
|
|
{
|
|
"entropy": 6.32744460105896,
|
|
"epoch": 0.6352776528215125,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004967623408104054,
|
|
"loss": 6.1474,
|
|
"mean_token_accuracy": 0.14919132813811303,
|
|
"num_tokens": 12425981.0,
|
|
"step": 6355
|
|
},
|
|
{
|
|
"entropy": 6.4638735294342045,
|
|
"epoch": 0.6357774778827411,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004967563053871762,
|
|
"loss": 6.2484,
|
|
"mean_token_accuracy": 0.14249523878097534,
|
|
"num_tokens": 12435197.0,
|
|
"step": 6360
|
|
},
|
|
{
|
|
"entropy": 6.355536365509034,
|
|
"epoch": 0.6362773029439696,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004967502643846155,
|
|
"loss": 6.2285,
|
|
"mean_token_accuracy": 0.14414375722408296,
|
|
"num_tokens": 12444697.0,
|
|
"step": 6365
|
|
},
|
|
{
|
|
"entropy": 6.346193933486939,
|
|
"epoch": 0.6367771280051981,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.000496744217802875,
|
|
"loss": 6.2236,
|
|
"mean_token_accuracy": 0.1432081863284111,
|
|
"num_tokens": 12454490.0,
|
|
"step": 6370
|
|
},
|
|
{
|
|
"entropy": 6.429242277145386,
|
|
"epoch": 0.6372769530664267,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004967381656421073,
|
|
"loss": 6.2565,
|
|
"mean_token_accuracy": 0.13868944570422173,
|
|
"num_tokens": 12463440.0,
|
|
"step": 6375
|
|
},
|
|
{
|
|
"entropy": 6.363940620422364,
|
|
"epoch": 0.6377767781276553,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004967321079024643,
|
|
"loss": 6.3476,
|
|
"mean_token_accuracy": 0.140744711458683,
|
|
"num_tokens": 12473285.0,
|
|
"step": 6380
|
|
},
|
|
{
|
|
"entropy": 6.408857345581055,
|
|
"epoch": 0.6382766031888839,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004967260445840985,
|
|
"loss": 6.2048,
|
|
"mean_token_accuracy": 0.14893916323781015,
|
|
"num_tokens": 12481975.0,
|
|
"step": 6385
|
|
},
|
|
{
|
|
"entropy": 6.345850801467895,
|
|
"epoch": 0.6387764282501125,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004967199756871624,
|
|
"loss": 6.2573,
|
|
"mean_token_accuracy": 0.14267202094197273,
|
|
"num_tokens": 12491736.0,
|
|
"step": 6390
|
|
},
|
|
{
|
|
"entropy": 6.292747259140015,
|
|
"epoch": 0.6392762533113411,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004967139012118088,
|
|
"loss": 6.3098,
|
|
"mean_token_accuracy": 0.13867436423897744,
|
|
"num_tokens": 12502369.0,
|
|
"step": 6395
|
|
},
|
|
{
|
|
"entropy": 6.410211420059204,
|
|
"epoch": 0.6397760783725696,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004967078211581907,
|
|
"loss": 6.2699,
|
|
"mean_token_accuracy": 0.1411287911236286,
|
|
"num_tokens": 12512906.0,
|
|
"step": 6400
|
|
},
|
|
{
|
|
"entropy": 6.413819694519043,
|
|
"epoch": 0.6402759034337981,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004967017355264606,
|
|
"loss": 6.226,
|
|
"mean_token_accuracy": 0.14184003695845604,
|
|
"num_tokens": 12523454.0,
|
|
"step": 6405
|
|
},
|
|
{
|
|
"entropy": 6.363322067260742,
|
|
"epoch": 0.6407757284950267,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.000496695644316772,
|
|
"loss": 6.3898,
|
|
"mean_token_accuracy": 0.1342937633395195,
|
|
"num_tokens": 12533228.0,
|
|
"step": 6410
|
|
},
|
|
{
|
|
"entropy": 6.439122819900513,
|
|
"epoch": 0.6412755535562553,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004966895475292781,
|
|
"loss": 6.3724,
|
|
"mean_token_accuracy": 0.13641492798924446,
|
|
"num_tokens": 12543188.0,
|
|
"step": 6415
|
|
},
|
|
{
|
|
"entropy": 6.3917735576629635,
|
|
"epoch": 0.6417753786174839,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004966834451641322,
|
|
"loss": 6.3076,
|
|
"mean_token_accuracy": 0.1359946012496948,
|
|
"num_tokens": 12553844.0,
|
|
"step": 6420
|
|
},
|
|
{
|
|
"entropy": 6.37999997138977,
|
|
"epoch": 0.6422752036787125,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004966773372214878,
|
|
"loss": 6.1957,
|
|
"mean_token_accuracy": 0.1438866063952446,
|
|
"num_tokens": 12563544.0,
|
|
"step": 6425
|
|
},
|
|
{
|
|
"entropy": 6.335693407058716,
|
|
"epoch": 0.642775028739941,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004966712237014987,
|
|
"loss": 6.2323,
|
|
"mean_token_accuracy": 0.1441716805100441,
|
|
"num_tokens": 12572894.0,
|
|
"step": 6430
|
|
},
|
|
{
|
|
"entropy": 6.394088935852051,
|
|
"epoch": 0.6432748538011696,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004966651046043186,
|
|
"loss": 6.368,
|
|
"mean_token_accuracy": 0.1325935512781143,
|
|
"num_tokens": 12583533.0,
|
|
"step": 6435
|
|
},
|
|
{
|
|
"entropy": 6.432648086547852,
|
|
"epoch": 0.6437746788623981,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004966589799301016,
|
|
"loss": 6.2497,
|
|
"mean_token_accuracy": 0.14007219299674034,
|
|
"num_tokens": 12593160.0,
|
|
"step": 6440
|
|
},
|
|
{
|
|
"entropy": 6.490913581848145,
|
|
"epoch": 0.6442745039236267,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004966528496790015,
|
|
"loss": 6.3399,
|
|
"mean_token_accuracy": 0.1376480370759964,
|
|
"num_tokens": 12604010.0,
|
|
"step": 6445
|
|
},
|
|
{
|
|
"entropy": 6.316685390472412,
|
|
"epoch": 0.6447743289848553,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004966467138511729,
|
|
"loss": 6.2561,
|
|
"mean_token_accuracy": 0.14571298211812972,
|
|
"num_tokens": 12614256.0,
|
|
"step": 6450
|
|
},
|
|
{
|
|
"entropy": 6.35328164100647,
|
|
"epoch": 0.6452741540460839,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00049664057244677,
|
|
"loss": 6.3535,
|
|
"mean_token_accuracy": 0.13842764869332314,
|
|
"num_tokens": 12624228.0,
|
|
"step": 6455
|
|
},
|
|
{
|
|
"entropy": 6.425360584259034,
|
|
"epoch": 0.6457739791073125,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004966344254659473,
|
|
"loss": 6.2052,
|
|
"mean_token_accuracy": 0.14232587143778802,
|
|
"num_tokens": 12634611.0,
|
|
"step": 6460
|
|
},
|
|
{
|
|
"entropy": 6.3840900421142575,
|
|
"epoch": 0.646273804168541,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004966282729088595,
|
|
"loss": 6.234,
|
|
"mean_token_accuracy": 0.13821083605289458,
|
|
"num_tokens": 12645309.0,
|
|
"step": 6465
|
|
},
|
|
{
|
|
"entropy": 6.39522705078125,
|
|
"epoch": 0.6467736292297696,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004966221147756615,
|
|
"loss": 6.2236,
|
|
"mean_token_accuracy": 0.14299412965774536,
|
|
"num_tokens": 12655283.0,
|
|
"step": 6470
|
|
},
|
|
{
|
|
"entropy": 6.333930921554566,
|
|
"epoch": 0.6472734542909981,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004966159510665079,
|
|
"loss": 6.2429,
|
|
"mean_token_accuracy": 0.14506687670946122,
|
|
"num_tokens": 12664531.0,
|
|
"step": 6475
|
|
},
|
|
{
|
|
"entropy": 6.336265420913696,
|
|
"epoch": 0.6477732793522267,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004966097817815542,
|
|
"loss": 6.2894,
|
|
"mean_token_accuracy": 0.1429209031164646,
|
|
"num_tokens": 12674791.0,
|
|
"step": 6480
|
|
},
|
|
{
|
|
"entropy": 6.372271251678467,
|
|
"epoch": 0.6482731044134553,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004966036069209552,
|
|
"loss": 6.275,
|
|
"mean_token_accuracy": 0.1434067502617836,
|
|
"num_tokens": 12685359.0,
|
|
"step": 6485
|
|
},
|
|
{
|
|
"entropy": 6.332733774185181,
|
|
"epoch": 0.6487729294746839,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004965974264848666,
|
|
"loss": 6.2598,
|
|
"mean_token_accuracy": 0.14337700605392456,
|
|
"num_tokens": 12694719.0,
|
|
"step": 6490
|
|
},
|
|
{
|
|
"entropy": 6.415884351730346,
|
|
"epoch": 0.6492727545359124,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004965912404734438,
|
|
"loss": 6.281,
|
|
"mean_token_accuracy": 0.1463285878300667,
|
|
"num_tokens": 12704032.0,
|
|
"step": 6495
|
|
},
|
|
{
|
|
"entropy": 6.384467601776123,
|
|
"epoch": 0.649772579597141,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004965850488868424,
|
|
"loss": 6.2595,
|
|
"mean_token_accuracy": 0.14304308742284774,
|
|
"num_tokens": 12713785.0,
|
|
"step": 6500
|
|
},
|
|
{
|
|
"entropy": 6.264138174057007,
|
|
"epoch": 0.6502724046583696,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004965788517252181,
|
|
"loss": 6.1968,
|
|
"mean_token_accuracy": 0.14354190677404405,
|
|
"num_tokens": 12724718.0,
|
|
"step": 6505
|
|
},
|
|
{
|
|
"entropy": 6.4190146923065186,
|
|
"epoch": 0.6507722297195981,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.000496572648988727,
|
|
"loss": 6.3057,
|
|
"mean_token_accuracy": 0.143632373213768,
|
|
"num_tokens": 12733518.0,
|
|
"step": 6510
|
|
},
|
|
{
|
|
"entropy": 6.426302146911621,
|
|
"epoch": 0.6512720547808267,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.000496566440677525,
|
|
"loss": 6.2295,
|
|
"mean_token_accuracy": 0.14380089417099953,
|
|
"num_tokens": 12743453.0,
|
|
"step": 6515
|
|
},
|
|
{
|
|
"entropy": 6.307664966583252,
|
|
"epoch": 0.6517718798420553,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004965602267917685,
|
|
"loss": 6.3183,
|
|
"mean_token_accuracy": 0.14244844019412994,
|
|
"num_tokens": 12753717.0,
|
|
"step": 6520
|
|
},
|
|
{
|
|
"entropy": 6.2848169803619385,
|
|
"epoch": 0.6522717049032839,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004965540073316136,
|
|
"loss": 6.2033,
|
|
"mean_token_accuracy": 0.14699351489543916,
|
|
"num_tokens": 12763240.0,
|
|
"step": 6525
|
|
},
|
|
{
|
|
"entropy": 6.396650123596191,
|
|
"epoch": 0.6527715299645124,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004965477822972169,
|
|
"loss": 6.2913,
|
|
"mean_token_accuracy": 0.1478447750210762,
|
|
"num_tokens": 12773284.0,
|
|
"step": 6530
|
|
},
|
|
{
|
|
"entropy": 6.4042840003967285,
|
|
"epoch": 0.653271355025741,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004965415516887349,
|
|
"loss": 6.2819,
|
|
"mean_token_accuracy": 0.13938205316662788,
|
|
"num_tokens": 12782189.0,
|
|
"step": 6535
|
|
},
|
|
{
|
|
"entropy": 6.255416440963745,
|
|
"epoch": 0.6537711800869695,
|
|
"grad_norm": 1.9921875,
|
|
"learning_rate": 0.0004965353155063246,
|
|
"loss": 6.2102,
|
|
"mean_token_accuracy": 0.14704835787415504,
|
|
"num_tokens": 12792790.0,
|
|
"step": 6540
|
|
},
|
|
{
|
|
"entropy": 6.35142970085144,
|
|
"epoch": 0.6542710051481981,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004965290737501427,
|
|
"loss": 6.1764,
|
|
"mean_token_accuracy": 0.14953116625547408,
|
|
"num_tokens": 12802368.0,
|
|
"step": 6545
|
|
},
|
|
{
|
|
"entropy": 6.385757875442505,
|
|
"epoch": 0.6547708302094267,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004965228264203464,
|
|
"loss": 6.2031,
|
|
"mean_token_accuracy": 0.14364102780818938,
|
|
"num_tokens": 12812226.0,
|
|
"step": 6550
|
|
},
|
|
{
|
|
"entropy": 6.329181432723999,
|
|
"epoch": 0.6552706552706553,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004965165735170928,
|
|
"loss": 6.2396,
|
|
"mean_token_accuracy": 0.14335149079561232,
|
|
"num_tokens": 12820986.0,
|
|
"step": 6555
|
|
},
|
|
{
|
|
"entropy": 6.272090101242066,
|
|
"epoch": 0.6557704803318838,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.000496510315040539,
|
|
"loss": 6.2643,
|
|
"mean_token_accuracy": 0.14013660252094268,
|
|
"num_tokens": 12830690.0,
|
|
"step": 6560
|
|
},
|
|
{
|
|
"entropy": 6.421197843551636,
|
|
"epoch": 0.6562703053931124,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004965040509908429,
|
|
"loss": 6.302,
|
|
"mean_token_accuracy": 0.14080157801508902,
|
|
"num_tokens": 12841780.0,
|
|
"step": 6565
|
|
},
|
|
{
|
|
"entropy": 6.420072317123413,
|
|
"epoch": 0.656770130454341,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004964977813681618,
|
|
"loss": 6.2329,
|
|
"mean_token_accuracy": 0.14666478782892228,
|
|
"num_tokens": 12850713.0,
|
|
"step": 6570
|
|
},
|
|
{
|
|
"entropy": 6.315571737289429,
|
|
"epoch": 0.6572699555155695,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004964915061726534,
|
|
"loss": 6.2867,
|
|
"mean_token_accuracy": 0.14022428989410402,
|
|
"num_tokens": 12862211.0,
|
|
"step": 6575
|
|
},
|
|
{
|
|
"entropy": 6.335816144943237,
|
|
"epoch": 0.6577697805767981,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004964852254044759,
|
|
"loss": 6.3364,
|
|
"mean_token_accuracy": 0.13908637017011644,
|
|
"num_tokens": 12871171.0,
|
|
"step": 6580
|
|
},
|
|
{
|
|
"entropy": 6.371293926239014,
|
|
"epoch": 0.6582696056380267,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004964789390637871,
|
|
"loss": 6.1955,
|
|
"mean_token_accuracy": 0.14533864110708236,
|
|
"num_tokens": 12880601.0,
|
|
"step": 6585
|
|
},
|
|
{
|
|
"entropy": 6.34336256980896,
|
|
"epoch": 0.6587694306992553,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004964726471507451,
|
|
"loss": 6.1693,
|
|
"mean_token_accuracy": 0.14412349313497544,
|
|
"num_tokens": 12890702.0,
|
|
"step": 6590
|
|
},
|
|
{
|
|
"entropy": 6.350169134140015,
|
|
"epoch": 0.6592692557604838,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004964663496655083,
|
|
"loss": 6.2731,
|
|
"mean_token_accuracy": 0.13806238025426865,
|
|
"num_tokens": 12901156.0,
|
|
"step": 6595
|
|
},
|
|
{
|
|
"entropy": 6.4678342819213865,
|
|
"epoch": 0.6597690808217124,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004964600466082351,
|
|
"loss": 6.2836,
|
|
"mean_token_accuracy": 0.13456722125411033,
|
|
"num_tokens": 12912183.0,
|
|
"step": 6600
|
|
},
|
|
{
|
|
"entropy": 6.349811172485351,
|
|
"epoch": 0.660268905882941,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004964537379790842,
|
|
"loss": 6.2579,
|
|
"mean_token_accuracy": 0.14334989637136458,
|
|
"num_tokens": 12922200.0,
|
|
"step": 6605
|
|
},
|
|
{
|
|
"entropy": 6.2914872646331785,
|
|
"epoch": 0.6607687309441695,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004964474237782141,
|
|
"loss": 6.146,
|
|
"mean_token_accuracy": 0.14655178785324097,
|
|
"num_tokens": 12931201.0,
|
|
"step": 6610
|
|
},
|
|
{
|
|
"entropy": 6.24609341621399,
|
|
"epoch": 0.6612685560053981,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004964411040057839,
|
|
"loss": 6.1381,
|
|
"mean_token_accuracy": 0.1485193267464638,
|
|
"num_tokens": 12941290.0,
|
|
"step": 6615
|
|
},
|
|
{
|
|
"entropy": 6.218661212921143,
|
|
"epoch": 0.6617683810666267,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004964347786619524,
|
|
"loss": 6.1749,
|
|
"mean_token_accuracy": 0.14614703878760338,
|
|
"num_tokens": 12953458.0,
|
|
"step": 6620
|
|
},
|
|
{
|
|
"entropy": 6.239731502532959,
|
|
"epoch": 0.6622682061278552,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004964284477468791,
|
|
"loss": 6.0361,
|
|
"mean_token_accuracy": 0.1567079909145832,
|
|
"num_tokens": 12964072.0,
|
|
"step": 6625
|
|
},
|
|
{
|
|
"entropy": 6.469099521636963,
|
|
"epoch": 0.6627680311890838,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004964221112607228,
|
|
"loss": 6.2393,
|
|
"mean_token_accuracy": 0.1375857874751091,
|
|
"num_tokens": 12974092.0,
|
|
"step": 6630
|
|
},
|
|
{
|
|
"entropy": 6.321001815795898,
|
|
"epoch": 0.6632678562503124,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004964157692036432,
|
|
"loss": 6.154,
|
|
"mean_token_accuracy": 0.14844254329800605,
|
|
"num_tokens": 12983546.0,
|
|
"step": 6635
|
|
},
|
|
{
|
|
"entropy": 6.345171070098877,
|
|
"epoch": 0.663767681311541,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004964094215757998,
|
|
"loss": 6.2617,
|
|
"mean_token_accuracy": 0.13610675185918808,
|
|
"num_tokens": 12993690.0,
|
|
"step": 6640
|
|
},
|
|
{
|
|
"entropy": 6.352869176864624,
|
|
"epoch": 0.6642675063727695,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004964030683773525,
|
|
"loss": 6.1906,
|
|
"mean_token_accuracy": 0.14434328600764273,
|
|
"num_tokens": 13003248.0,
|
|
"step": 6645
|
|
},
|
|
{
|
|
"entropy": 6.354497718811035,
|
|
"epoch": 0.6647673314339981,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004963967096084608,
|
|
"loss": 6.191,
|
|
"mean_token_accuracy": 0.14685217142105103,
|
|
"num_tokens": 13013182.0,
|
|
"step": 6650
|
|
},
|
|
{
|
|
"entropy": 6.293743562698364,
|
|
"epoch": 0.6652671564952267,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004963903452692849,
|
|
"loss": 6.1996,
|
|
"mean_token_accuracy": 0.14745060428977014,
|
|
"num_tokens": 13022726.0,
|
|
"step": 6655
|
|
},
|
|
{
|
|
"entropy": 6.244716358184815,
|
|
"epoch": 0.6657669815564552,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004963839753599848,
|
|
"loss": 6.1575,
|
|
"mean_token_accuracy": 0.14454718828201293,
|
|
"num_tokens": 13031811.0,
|
|
"step": 6660
|
|
},
|
|
{
|
|
"entropy": 6.376889085769653,
|
|
"epoch": 0.6662668066176838,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.000496377599880721,
|
|
"loss": 6.1934,
|
|
"mean_token_accuracy": 0.14934000223875046,
|
|
"num_tokens": 13040884.0,
|
|
"step": 6665
|
|
},
|
|
{
|
|
"entropy": 6.3811346054077145,
|
|
"epoch": 0.6667666316789124,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004963712188316537,
|
|
"loss": 6.3223,
|
|
"mean_token_accuracy": 0.1370953120291233,
|
|
"num_tokens": 13049937.0,
|
|
"step": 6670
|
|
},
|
|
{
|
|
"entropy": 6.324701452255249,
|
|
"epoch": 0.667266456740141,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004963648322129435,
|
|
"loss": 6.1589,
|
|
"mean_token_accuracy": 0.1480522409081459,
|
|
"num_tokens": 13059307.0,
|
|
"step": 6675
|
|
},
|
|
{
|
|
"entropy": 6.3423168659210205,
|
|
"epoch": 0.6677662818013695,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.000496358440024751,
|
|
"loss": 6.2881,
|
|
"mean_token_accuracy": 0.13714971542358398,
|
|
"num_tokens": 13069400.0,
|
|
"step": 6680
|
|
},
|
|
{
|
|
"entropy": 6.373897504806519,
|
|
"epoch": 0.6682661068625981,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004963520422672372,
|
|
"loss": 6.1803,
|
|
"mean_token_accuracy": 0.14665843173861504,
|
|
"num_tokens": 13079965.0,
|
|
"step": 6685
|
|
},
|
|
{
|
|
"entropy": 6.381875228881836,
|
|
"epoch": 0.6687659319238266,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000496345638940563,
|
|
"loss": 6.3575,
|
|
"mean_token_accuracy": 0.13467492684721946,
|
|
"num_tokens": 13090144.0,
|
|
"step": 6690
|
|
},
|
|
{
|
|
"entropy": 6.363946866989136,
|
|
"epoch": 0.6692657569850552,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004963392300448894,
|
|
"loss": 6.1517,
|
|
"mean_token_accuracy": 0.14645947366952897,
|
|
"num_tokens": 13100217.0,
|
|
"step": 6695
|
|
},
|
|
{
|
|
"entropy": 6.30076265335083,
|
|
"epoch": 0.6697655820462838,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004963328155803778,
|
|
"loss": 6.224,
|
|
"mean_token_accuracy": 0.14600871056318282,
|
|
"num_tokens": 13109031.0,
|
|
"step": 6700
|
|
},
|
|
{
|
|
"entropy": 6.380642557144165,
|
|
"epoch": 0.6702654071075124,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004963263955471895,
|
|
"loss": 6.3368,
|
|
"mean_token_accuracy": 0.13109761849045753,
|
|
"num_tokens": 13119073.0,
|
|
"step": 6705
|
|
},
|
|
{
|
|
"entropy": 6.366076898574829,
|
|
"epoch": 0.670765232168741,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.000496319969945486,
|
|
"loss": 6.2847,
|
|
"mean_token_accuracy": 0.14624615982174874,
|
|
"num_tokens": 13129208.0,
|
|
"step": 6710
|
|
},
|
|
{
|
|
"entropy": 6.332978916168213,
|
|
"epoch": 0.6712650572299695,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.000496313538775429,
|
|
"loss": 6.2159,
|
|
"mean_token_accuracy": 0.14699893817305565,
|
|
"num_tokens": 13138559.0,
|
|
"step": 6715
|
|
},
|
|
{
|
|
"entropy": 6.361584281921386,
|
|
"epoch": 0.6717648822911981,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004963071020371803,
|
|
"loss": 6.3321,
|
|
"mean_token_accuracy": 0.14095332175493241,
|
|
"num_tokens": 13148456.0,
|
|
"step": 6720
|
|
},
|
|
{
|
|
"entropy": 6.360890054702759,
|
|
"epoch": 0.6722647073524266,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004963006597309019,
|
|
"loss": 6.2481,
|
|
"mean_token_accuracy": 0.14297167286276818,
|
|
"num_tokens": 13158245.0,
|
|
"step": 6725
|
|
},
|
|
{
|
|
"entropy": 6.439178943634033,
|
|
"epoch": 0.6727645324136552,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004962942118567559,
|
|
"loss": 6.2805,
|
|
"mean_token_accuracy": 0.15162380859255792,
|
|
"num_tokens": 13166269.0,
|
|
"step": 6730
|
|
},
|
|
{
|
|
"entropy": 6.339335823059082,
|
|
"epoch": 0.6732643574748838,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004962877584149043,
|
|
"loss": 6.2415,
|
|
"mean_token_accuracy": 0.14097519665956498,
|
|
"num_tokens": 13176763.0,
|
|
"step": 6735
|
|
},
|
|
{
|
|
"entropy": 6.280173015594483,
|
|
"epoch": 0.6737641825361124,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004962812994055098,
|
|
"loss": 6.2024,
|
|
"mean_token_accuracy": 0.14538279920816422,
|
|
"num_tokens": 13185945.0,
|
|
"step": 6740
|
|
},
|
|
{
|
|
"entropy": 6.405073738098144,
|
|
"epoch": 0.674264007597341,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004962748348287347,
|
|
"loss": 6.2836,
|
|
"mean_token_accuracy": 0.14246615618467331,
|
|
"num_tokens": 13197205.0,
|
|
"step": 6745
|
|
},
|
|
{
|
|
"entropy": 6.296693897247314,
|
|
"epoch": 0.6747638326585695,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004962683646847416,
|
|
"loss": 6.2635,
|
|
"mean_token_accuracy": 0.13742260485887528,
|
|
"num_tokens": 13206939.0,
|
|
"step": 6750
|
|
},
|
|
{
|
|
"entropy": 6.308182954788208,
|
|
"epoch": 0.675263657719798,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004962618889736936,
|
|
"loss": 6.2009,
|
|
"mean_token_accuracy": 0.14284489750862123,
|
|
"num_tokens": 13216317.0,
|
|
"step": 6755
|
|
},
|
|
{
|
|
"entropy": 6.358166742324829,
|
|
"epoch": 0.6757634827810266,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004962554076957533,
|
|
"loss": 6.2331,
|
|
"mean_token_accuracy": 0.1492699772119522,
|
|
"num_tokens": 13226594.0,
|
|
"step": 6760
|
|
},
|
|
{
|
|
"entropy": 6.428493928909302,
|
|
"epoch": 0.6762633078422552,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004962489208510838,
|
|
"loss": 6.3811,
|
|
"mean_token_accuracy": 0.13592161610722542,
|
|
"num_tokens": 13237477.0,
|
|
"step": 6765
|
|
},
|
|
{
|
|
"entropy": 6.396593189239502,
|
|
"epoch": 0.6767631329034838,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004962424284398484,
|
|
"loss": 6.1747,
|
|
"mean_token_accuracy": 0.1454145684838295,
|
|
"num_tokens": 13247041.0,
|
|
"step": 6770
|
|
},
|
|
{
|
|
"entropy": 6.282503604888916,
|
|
"epoch": 0.6772629579647124,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004962359304622105,
|
|
"loss": 6.1662,
|
|
"mean_token_accuracy": 0.14722471535205842,
|
|
"num_tokens": 13257223.0,
|
|
"step": 6775
|
|
},
|
|
{
|
|
"entropy": 6.334440422058106,
|
|
"epoch": 0.677762783025941,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004962294269183335,
|
|
"loss": 6.2123,
|
|
"mean_token_accuracy": 0.14640141129493714,
|
|
"num_tokens": 13267457.0,
|
|
"step": 6780
|
|
},
|
|
{
|
|
"entropy": 6.386912631988525,
|
|
"epoch": 0.6782626080871695,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000496222917808381,
|
|
"loss": 6.2375,
|
|
"mean_token_accuracy": 0.1386418327689171,
|
|
"num_tokens": 13277656.0,
|
|
"step": 6785
|
|
},
|
|
{
|
|
"entropy": 6.325541257858276,
|
|
"epoch": 0.678762433148398,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004962164031325169,
|
|
"loss": 6.2273,
|
|
"mean_token_accuracy": 0.14622305184602738,
|
|
"num_tokens": 13288483.0,
|
|
"step": 6790
|
|
},
|
|
{
|
|
"entropy": 6.298862409591675,
|
|
"epoch": 0.6792622582096266,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.000496209882890905,
|
|
"loss": 6.1493,
|
|
"mean_token_accuracy": 0.15328536182641983,
|
|
"num_tokens": 13298312.0,
|
|
"step": 6795
|
|
},
|
|
{
|
|
"entropy": 6.229435968399048,
|
|
"epoch": 0.6797620832708552,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004962033570837094,
|
|
"loss": 6.0584,
|
|
"mean_token_accuracy": 0.14531668201088904,
|
|
"num_tokens": 13308038.0,
|
|
"step": 6800
|
|
},
|
|
{
|
|
"entropy": 6.285090208053589,
|
|
"epoch": 0.6802619083320838,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004961968257110941,
|
|
"loss": 6.1565,
|
|
"mean_token_accuracy": 0.14741025865077972,
|
|
"num_tokens": 13317963.0,
|
|
"step": 6805
|
|
},
|
|
{
|
|
"entropy": 6.300033330917358,
|
|
"epoch": 0.6807617333933124,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004961902887732236,
|
|
"loss": 6.2292,
|
|
"mean_token_accuracy": 0.14750295728445054,
|
|
"num_tokens": 13328210.0,
|
|
"step": 6810
|
|
},
|
|
{
|
|
"entropy": 6.311105060577392,
|
|
"epoch": 0.681261558454541,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004961837462702626,
|
|
"loss": 6.1991,
|
|
"mean_token_accuracy": 0.1448679596185684,
|
|
"num_tokens": 13337778.0,
|
|
"step": 6815
|
|
},
|
|
{
|
|
"entropy": 6.301775026321411,
|
|
"epoch": 0.6817613835157694,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004961771982023752,
|
|
"loss": 6.1802,
|
|
"mean_token_accuracy": 0.14408588409423828,
|
|
"num_tokens": 13348117.0,
|
|
"step": 6820
|
|
},
|
|
{
|
|
"entropy": 6.342627429962159,
|
|
"epoch": 0.682261208576998,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004961706445697265,
|
|
"loss": 6.1443,
|
|
"mean_token_accuracy": 0.14329586327075958,
|
|
"num_tokens": 13356379.0,
|
|
"step": 6825
|
|
},
|
|
{
|
|
"entropy": 6.260994005203247,
|
|
"epoch": 0.6827610336382266,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004961640853724813,
|
|
"loss": 6.1644,
|
|
"mean_token_accuracy": 0.14717764109373094,
|
|
"num_tokens": 13366621.0,
|
|
"step": 6830
|
|
},
|
|
{
|
|
"entropy": 6.316004228591919,
|
|
"epoch": 0.6832608586994552,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004961575206108046,
|
|
"loss": 6.3077,
|
|
"mean_token_accuracy": 0.13996322378516196,
|
|
"num_tokens": 13375596.0,
|
|
"step": 6835
|
|
},
|
|
{
|
|
"entropy": 6.387084531784057,
|
|
"epoch": 0.6837606837606838,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004961509502848616,
|
|
"loss": 6.2583,
|
|
"mean_token_accuracy": 0.14108679220080375,
|
|
"num_tokens": 13385871.0,
|
|
"step": 6840
|
|
},
|
|
{
|
|
"entropy": 6.380372047424316,
|
|
"epoch": 0.6842605088219124,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004961443743948177,
|
|
"loss": 6.2637,
|
|
"mean_token_accuracy": 0.14109894260764122,
|
|
"num_tokens": 13395277.0,
|
|
"step": 6845
|
|
},
|
|
{
|
|
"entropy": 6.296953868865967,
|
|
"epoch": 0.684760333883141,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000496137792940838,
|
|
"loss": 6.2915,
|
|
"mean_token_accuracy": 0.13900421634316446,
|
|
"num_tokens": 13405064.0,
|
|
"step": 6850
|
|
},
|
|
{
|
|
"entropy": 6.381401443481446,
|
|
"epoch": 0.6852601589443694,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004961312059230885,
|
|
"loss": 6.2604,
|
|
"mean_token_accuracy": 0.1429591543972492,
|
|
"num_tokens": 13414399.0,
|
|
"step": 6855
|
|
},
|
|
{
|
|
"entropy": 6.348307752609253,
|
|
"epoch": 0.685759984005598,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004961246133417348,
|
|
"loss": 6.3415,
|
|
"mean_token_accuracy": 0.1393718972802162,
|
|
"num_tokens": 13424343.0,
|
|
"step": 6860
|
|
},
|
|
{
|
|
"entropy": 6.346564483642578,
|
|
"epoch": 0.6862598090668266,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004961180151969427,
|
|
"loss": 6.2204,
|
|
"mean_token_accuracy": 0.14897054955363273,
|
|
"num_tokens": 13434362.0,
|
|
"step": 6865
|
|
},
|
|
{
|
|
"entropy": 6.379272031784057,
|
|
"epoch": 0.6867596341280552,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004961114114888782,
|
|
"loss": 6.223,
|
|
"mean_token_accuracy": 0.14392918422818185,
|
|
"num_tokens": 13444578.0,
|
|
"step": 6870
|
|
},
|
|
{
|
|
"entropy": 6.2164021015167235,
|
|
"epoch": 0.6872594591892838,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004961048022177074,
|
|
"loss": 6.1051,
|
|
"mean_token_accuracy": 0.14629753604531287,
|
|
"num_tokens": 13454184.0,
|
|
"step": 6875
|
|
},
|
|
{
|
|
"entropy": 6.307594108581543,
|
|
"epoch": 0.6877592842505124,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004960981873835968,
|
|
"loss": 6.2097,
|
|
"mean_token_accuracy": 0.14229094237089157,
|
|
"num_tokens": 13464269.0,
|
|
"step": 6880
|
|
},
|
|
{
|
|
"entropy": 6.40620789527893,
|
|
"epoch": 0.6882591093117408,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004960915669867126,
|
|
"loss": 6.2728,
|
|
"mean_token_accuracy": 0.13971073776483536,
|
|
"num_tokens": 13472747.0,
|
|
"step": 6885
|
|
},
|
|
{
|
|
"entropy": 6.281014919281006,
|
|
"epoch": 0.6887589343729694,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004960849410272216,
|
|
"loss": 6.2331,
|
|
"mean_token_accuracy": 0.14719310104846955,
|
|
"num_tokens": 13481670.0,
|
|
"step": 6890
|
|
},
|
|
{
|
|
"entropy": 6.250548791885376,
|
|
"epoch": 0.689258759434198,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004960783095052903,
|
|
"loss": 6.1379,
|
|
"mean_token_accuracy": 0.15078865438699723,
|
|
"num_tokens": 13490428.0,
|
|
"step": 6895
|
|
},
|
|
{
|
|
"entropy": 6.264186763763428,
|
|
"epoch": 0.6897585844954266,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004960716724210856,
|
|
"loss": 6.1004,
|
|
"mean_token_accuracy": 0.14907412976026535,
|
|
"num_tokens": 13499549.0,
|
|
"step": 6900
|
|
},
|
|
{
|
|
"entropy": 6.317903137207031,
|
|
"epoch": 0.6902584095566552,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004960650297747746,
|
|
"loss": 6.2773,
|
|
"mean_token_accuracy": 0.14041923731565475,
|
|
"num_tokens": 13508930.0,
|
|
"step": 6905
|
|
},
|
|
{
|
|
"entropy": 6.352906656265259,
|
|
"epoch": 0.6907582346178838,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004960583815665242,
|
|
"loss": 6.2872,
|
|
"mean_token_accuracy": 0.1401541970670223,
|
|
"num_tokens": 13518858.0,
|
|
"step": 6910
|
|
},
|
|
{
|
|
"entropy": 6.3616118907928465,
|
|
"epoch": 0.6912580596791124,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004960517277965018,
|
|
"loss": 6.2321,
|
|
"mean_token_accuracy": 0.13450878858566284,
|
|
"num_tokens": 13529346.0,
|
|
"step": 6915
|
|
},
|
|
{
|
|
"entropy": 6.332385587692261,
|
|
"epoch": 0.6917578847403408,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004960450684648749,
|
|
"loss": 6.2224,
|
|
"mean_token_accuracy": 0.13784221857786177,
|
|
"num_tokens": 13539096.0,
|
|
"step": 6920
|
|
},
|
|
{
|
|
"entropy": 6.3196052551269535,
|
|
"epoch": 0.6922577098015694,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.000496038403571811,
|
|
"loss": 6.2533,
|
|
"mean_token_accuracy": 0.14087265878915786,
|
|
"num_tokens": 13548698.0,
|
|
"step": 6925
|
|
},
|
|
{
|
|
"entropy": 6.305506658554077,
|
|
"epoch": 0.692757534862798,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004960317331174777,
|
|
"loss": 6.2405,
|
|
"mean_token_accuracy": 0.14463794156908988,
|
|
"num_tokens": 13559550.0,
|
|
"step": 6930
|
|
},
|
|
{
|
|
"entropy": 6.391615772247315,
|
|
"epoch": 0.6932573599240266,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004960250571020428,
|
|
"loss": 6.3138,
|
|
"mean_token_accuracy": 0.13640302568674087,
|
|
"num_tokens": 13569248.0,
|
|
"step": 6935
|
|
},
|
|
{
|
|
"entropy": 6.390089273452759,
|
|
"epoch": 0.6937571849852552,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004960183755256744,
|
|
"loss": 6.1873,
|
|
"mean_token_accuracy": 0.14286122098565102,
|
|
"num_tokens": 13578957.0,
|
|
"step": 6940
|
|
},
|
|
{
|
|
"entropy": 6.385510396957398,
|
|
"epoch": 0.6942570100464838,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004960116883885406,
|
|
"loss": 6.2871,
|
|
"mean_token_accuracy": 0.13741213977336883,
|
|
"num_tokens": 13589630.0,
|
|
"step": 6945
|
|
},
|
|
{
|
|
"entropy": 6.340646982192993,
|
|
"epoch": 0.6947568351077124,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004960049956908095,
|
|
"loss": 6.1921,
|
|
"mean_token_accuracy": 0.14678001776337624,
|
|
"num_tokens": 13599067.0,
|
|
"step": 6950
|
|
},
|
|
{
|
|
"entropy": 6.34862060546875,
|
|
"epoch": 0.6952566601689408,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004959982974326496,
|
|
"loss": 6.2588,
|
|
"mean_token_accuracy": 0.1393041916191578,
|
|
"num_tokens": 13609068.0,
|
|
"step": 6955
|
|
},
|
|
{
|
|
"entropy": 6.370382833480835,
|
|
"epoch": 0.6957564852301694,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004959915936142294,
|
|
"loss": 6.3076,
|
|
"mean_token_accuracy": 0.1441367633640766,
|
|
"num_tokens": 13619112.0,
|
|
"step": 6960
|
|
},
|
|
{
|
|
"entropy": 6.406302356719971,
|
|
"epoch": 0.696256310291398,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004959848842357175,
|
|
"loss": 6.3195,
|
|
"mean_token_accuracy": 0.14691561609506607,
|
|
"num_tokens": 13629518.0,
|
|
"step": 6965
|
|
},
|
|
{
|
|
"entropy": 6.4604637145996096,
|
|
"epoch": 0.6967561353526266,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004959781692972829,
|
|
"loss": 6.332,
|
|
"mean_token_accuracy": 0.14065197557210923,
|
|
"num_tokens": 13639796.0,
|
|
"step": 6970
|
|
},
|
|
{
|
|
"entropy": 6.385721206665039,
|
|
"epoch": 0.6972559604138552,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004959714487990943,
|
|
"loss": 6.2734,
|
|
"mean_token_accuracy": 0.1430683322250843,
|
|
"num_tokens": 13649876.0,
|
|
"step": 6975
|
|
},
|
|
{
|
|
"entropy": 6.388269281387329,
|
|
"epoch": 0.6977557854750838,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.000495964722741321,
|
|
"loss": 6.2511,
|
|
"mean_token_accuracy": 0.14366811960935594,
|
|
"num_tokens": 13660670.0,
|
|
"step": 6980
|
|
},
|
|
{
|
|
"entropy": 6.321117496490478,
|
|
"epoch": 0.6982556105363122,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004959579911241322,
|
|
"loss": 6.1838,
|
|
"mean_token_accuracy": 0.14604139775037767,
|
|
"num_tokens": 13669958.0,
|
|
"step": 6985
|
|
},
|
|
{
|
|
"entropy": 6.266972541809082,
|
|
"epoch": 0.6987554355975408,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004959512539476971,
|
|
"loss": 6.1279,
|
|
"mean_token_accuracy": 0.1502666801214218,
|
|
"num_tokens": 13678414.0,
|
|
"step": 6990
|
|
},
|
|
{
|
|
"entropy": 6.276806116104126,
|
|
"epoch": 0.6992552606587694,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004959445112121853,
|
|
"loss": 6.1646,
|
|
"mean_token_accuracy": 0.1487281210720539,
|
|
"num_tokens": 13687424.0,
|
|
"step": 6995
|
|
},
|
|
{
|
|
"entropy": 6.331806278228759,
|
|
"epoch": 0.699755085719998,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004959377629177665,
|
|
"loss": 6.3056,
|
|
"mean_token_accuracy": 0.13894835487008095,
|
|
"num_tokens": 13697249.0,
|
|
"step": 7000
|
|
},
|
|
{
|
|
"entropy": 6.304219770431518,
|
|
"epoch": 0.7002549107812266,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004959310090646104,
|
|
"loss": 6.1942,
|
|
"mean_token_accuracy": 0.145977284014225,
|
|
"num_tokens": 13707059.0,
|
|
"step": 7005
|
|
},
|
|
{
|
|
"entropy": 6.3667525291442875,
|
|
"epoch": 0.7007547358424552,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004959242496528869,
|
|
"loss": 6.1456,
|
|
"mean_token_accuracy": 0.1492059513926506,
|
|
"num_tokens": 13715899.0,
|
|
"step": 7010
|
|
},
|
|
{
|
|
"entropy": 6.317831707000733,
|
|
"epoch": 0.7012545609036838,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004959174846827663,
|
|
"loss": 6.2824,
|
|
"mean_token_accuracy": 0.13746010214090348,
|
|
"num_tokens": 13725318.0,
|
|
"step": 7015
|
|
},
|
|
{
|
|
"entropy": 6.337517499923706,
|
|
"epoch": 0.7017543859649122,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004959107141544186,
|
|
"loss": 6.2518,
|
|
"mean_token_accuracy": 0.1441350281238556,
|
|
"num_tokens": 13734816.0,
|
|
"step": 7020
|
|
},
|
|
{
|
|
"entropy": 6.415861749649048,
|
|
"epoch": 0.7022542110261408,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.000495903938068014,
|
|
"loss": 6.278,
|
|
"mean_token_accuracy": 0.13754311501979827,
|
|
"num_tokens": 13744323.0,
|
|
"step": 7025
|
|
},
|
|
{
|
|
"entropy": 6.501106691360474,
|
|
"epoch": 0.7027540360873694,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004958971564237233,
|
|
"loss": 6.4612,
|
|
"mean_token_accuracy": 0.12470668181777,
|
|
"num_tokens": 13754301.0,
|
|
"step": 7030
|
|
},
|
|
{
|
|
"entropy": 6.422401475906372,
|
|
"epoch": 0.703253861148598,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.000495890369221717,
|
|
"loss": 6.319,
|
|
"mean_token_accuracy": 0.13458661139011383,
|
|
"num_tokens": 13763561.0,
|
|
"step": 7035
|
|
},
|
|
{
|
|
"entropy": 6.3136241912841795,
|
|
"epoch": 0.7037536862098266,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004958835764621657,
|
|
"loss": 6.2031,
|
|
"mean_token_accuracy": 0.14579539373517036,
|
|
"num_tokens": 13773500.0,
|
|
"step": 7040
|
|
},
|
|
{
|
|
"entropy": 6.417852783203125,
|
|
"epoch": 0.7042535112710552,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004958767781452406,
|
|
"loss": 6.2024,
|
|
"mean_token_accuracy": 0.14278700202703476,
|
|
"num_tokens": 13782390.0,
|
|
"step": 7045
|
|
},
|
|
{
|
|
"entropy": 6.33878607749939,
|
|
"epoch": 0.7047533363322837,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004958699742711126,
|
|
"loss": 6.1845,
|
|
"mean_token_accuracy": 0.1478372909128666,
|
|
"num_tokens": 13791790.0,
|
|
"step": 7050
|
|
},
|
|
{
|
|
"entropy": 6.353102159500122,
|
|
"epoch": 0.7052531613935122,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004958631648399528,
|
|
"loss": 6.2748,
|
|
"mean_token_accuracy": 0.1372276224195957,
|
|
"num_tokens": 13802352.0,
|
|
"step": 7055
|
|
},
|
|
{
|
|
"entropy": 6.361660957336426,
|
|
"epoch": 0.7057529864547408,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004958563498519327,
|
|
"loss": 6.2238,
|
|
"mean_token_accuracy": 0.14929865226149558,
|
|
"num_tokens": 13812905.0,
|
|
"step": 7060
|
|
},
|
|
{
|
|
"entropy": 6.359763526916504,
|
|
"epoch": 0.7062528115159694,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004958495293072235,
|
|
"loss": 6.3244,
|
|
"mean_token_accuracy": 0.13780978322029114,
|
|
"num_tokens": 13823456.0,
|
|
"step": 7065
|
|
},
|
|
{
|
|
"entropy": 6.3433257102966305,
|
|
"epoch": 0.706752636577198,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004958427032059971,
|
|
"loss": 6.1683,
|
|
"mean_token_accuracy": 0.15489820539951324,
|
|
"num_tokens": 13832110.0,
|
|
"step": 7070
|
|
},
|
|
{
|
|
"entropy": 6.2405171394348145,
|
|
"epoch": 0.7072524616384266,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004958358715484251,
|
|
"loss": 6.188,
|
|
"mean_token_accuracy": 0.14749221354722977,
|
|
"num_tokens": 13841637.0,
|
|
"step": 7075
|
|
},
|
|
{
|
|
"entropy": 6.304652833938599,
|
|
"epoch": 0.7077522866996552,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004958290343346795,
|
|
"loss": 6.1774,
|
|
"mean_token_accuracy": 0.14241352155804635,
|
|
"num_tokens": 13852185.0,
|
|
"step": 7080
|
|
},
|
|
{
|
|
"entropy": 6.319034194946289,
|
|
"epoch": 0.7082521117608837,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.000495822191564932,
|
|
"loss": 6.1181,
|
|
"mean_token_accuracy": 0.15449463427066804,
|
|
"num_tokens": 13862469.0,
|
|
"step": 7085
|
|
},
|
|
{
|
|
"entropy": 6.327530145645142,
|
|
"epoch": 0.7087519368221122,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004958153432393553,
|
|
"loss": 6.208,
|
|
"mean_token_accuracy": 0.14218529164791108,
|
|
"num_tokens": 13872472.0,
|
|
"step": 7090
|
|
},
|
|
{
|
|
"entropy": 6.312508249282837,
|
|
"epoch": 0.7092517618833408,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000495808489358121,
|
|
"loss": 6.2414,
|
|
"mean_token_accuracy": 0.13936603292822838,
|
|
"num_tokens": 13882622.0,
|
|
"step": 7095
|
|
},
|
|
{
|
|
"entropy": 6.330296850204467,
|
|
"epoch": 0.7097515869445694,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004958016299214022,
|
|
"loss": 6.2367,
|
|
"mean_token_accuracy": 0.1445574387907982,
|
|
"num_tokens": 13891836.0,
|
|
"step": 7100
|
|
},
|
|
{
|
|
"entropy": 6.404167985916137,
|
|
"epoch": 0.710251412005798,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004957947649293712,
|
|
"loss": 6.1339,
|
|
"mean_token_accuracy": 0.14620952308177948,
|
|
"num_tokens": 13901555.0,
|
|
"step": 7105
|
|
},
|
|
{
|
|
"entropy": 6.3054383277893065,
|
|
"epoch": 0.7107512370670266,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004957878943822006,
|
|
"loss": 6.2362,
|
|
"mean_token_accuracy": 0.1425202839076519,
|
|
"num_tokens": 13911145.0,
|
|
"step": 7110
|
|
},
|
|
{
|
|
"entropy": 6.234632587432861,
|
|
"epoch": 0.7112510621282551,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004957810182800634,
|
|
"loss": 6.1371,
|
|
"mean_token_accuracy": 0.15011852607131004,
|
|
"num_tokens": 13920375.0,
|
|
"step": 7115
|
|
},
|
|
{
|
|
"entropy": 6.272734117507935,
|
|
"epoch": 0.7117508871894836,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004957741366231327,
|
|
"loss": 6.1423,
|
|
"mean_token_accuracy": 0.15246715471148492,
|
|
"num_tokens": 13930175.0,
|
|
"step": 7120
|
|
},
|
|
{
|
|
"entropy": 6.287425947189331,
|
|
"epoch": 0.7122507122507122,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004957672494115815,
|
|
"loss": 6.222,
|
|
"mean_token_accuracy": 0.15177012532949447,
|
|
"num_tokens": 13939935.0,
|
|
"step": 7125
|
|
},
|
|
{
|
|
"entropy": 6.3001793384552,
|
|
"epoch": 0.7127505373119408,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.000495760356645583,
|
|
"loss": 6.1919,
|
|
"mean_token_accuracy": 0.1353710785508156,
|
|
"num_tokens": 13950356.0,
|
|
"step": 7130
|
|
},
|
|
{
|
|
"entropy": 6.36169319152832,
|
|
"epoch": 0.7132503623731694,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004957534583253108,
|
|
"loss": 6.2097,
|
|
"mean_token_accuracy": 0.14495083540678025,
|
|
"num_tokens": 13960661.0,
|
|
"step": 7135
|
|
},
|
|
{
|
|
"entropy": 6.388730478286743,
|
|
"epoch": 0.713750187434398,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004957465544509384,
|
|
"loss": 6.2234,
|
|
"mean_token_accuracy": 0.14034337550401688,
|
|
"num_tokens": 13970629.0,
|
|
"step": 7140
|
|
},
|
|
{
|
|
"entropy": 6.263514757156372,
|
|
"epoch": 0.7142500124956266,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004957396450226395,
|
|
"loss": 6.1301,
|
|
"mean_token_accuracy": 0.15107150077819825,
|
|
"num_tokens": 13979801.0,
|
|
"step": 7145
|
|
},
|
|
{
|
|
"entropy": 6.31006269454956,
|
|
"epoch": 0.7147498375568551,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004957327300405879,
|
|
"loss": 6.3376,
|
|
"mean_token_accuracy": 0.14776059985160828,
|
|
"num_tokens": 13989749.0,
|
|
"step": 7150
|
|
},
|
|
{
|
|
"entropy": 6.3592592716217045,
|
|
"epoch": 0.7152496626180836,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004957258095049577,
|
|
"loss": 6.2236,
|
|
"mean_token_accuracy": 0.14252349361777306,
|
|
"num_tokens": 13999483.0,
|
|
"step": 7155
|
|
},
|
|
{
|
|
"entropy": 6.30907096862793,
|
|
"epoch": 0.7157494876793122,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004957188834159229,
|
|
"loss": 6.1988,
|
|
"mean_token_accuracy": 0.15286268293857574,
|
|
"num_tokens": 14009243.0,
|
|
"step": 7160
|
|
},
|
|
{
|
|
"entropy": 6.210056018829346,
|
|
"epoch": 0.7162493127405408,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004957119517736577,
|
|
"loss": 6.1664,
|
|
"mean_token_accuracy": 0.1418146498501301,
|
|
"num_tokens": 14020452.0,
|
|
"step": 7165
|
|
},
|
|
{
|
|
"entropy": 6.310309791564942,
|
|
"epoch": 0.7167491378017694,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004957050145783366,
|
|
"loss": 6.1662,
|
|
"mean_token_accuracy": 0.13924267292022705,
|
|
"num_tokens": 14030446.0,
|
|
"step": 7170
|
|
},
|
|
{
|
|
"entropy": 6.401497268676758,
|
|
"epoch": 0.717248962862998,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004956980718301342,
|
|
"loss": 6.3636,
|
|
"mean_token_accuracy": 0.13962490484118462,
|
|
"num_tokens": 14040742.0,
|
|
"step": 7175
|
|
},
|
|
{
|
|
"entropy": 6.335114574432373,
|
|
"epoch": 0.7177487879242265,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004956911235292251,
|
|
"loss": 6.175,
|
|
"mean_token_accuracy": 0.14628776982426644,
|
|
"num_tokens": 14050255.0,
|
|
"step": 7180
|
|
},
|
|
{
|
|
"entropy": 6.326679706573486,
|
|
"epoch": 0.7182486129854551,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004956841696757841,
|
|
"loss": 6.128,
|
|
"mean_token_accuracy": 0.15696224793791771,
|
|
"num_tokens": 14059745.0,
|
|
"step": 7185
|
|
},
|
|
{
|
|
"entropy": 6.26316556930542,
|
|
"epoch": 0.7187484380466836,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004956772102699862,
|
|
"loss": 6.1602,
|
|
"mean_token_accuracy": 0.14652982652187346,
|
|
"num_tokens": 14069741.0,
|
|
"step": 7190
|
|
},
|
|
{
|
|
"entropy": 6.308904933929443,
|
|
"epoch": 0.7192482631079122,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004956702453120064,
|
|
"loss": 6.2324,
|
|
"mean_token_accuracy": 0.14142434820532798,
|
|
"num_tokens": 14078758.0,
|
|
"step": 7195
|
|
},
|
|
{
|
|
"entropy": 6.391016483306885,
|
|
"epoch": 0.7197480881691408,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004956632748020201,
|
|
"loss": 6.2724,
|
|
"mean_token_accuracy": 0.14334044381976127,
|
|
"num_tokens": 14087770.0,
|
|
"step": 7200
|
|
},
|
|
{
|
|
"entropy": 6.332693386077881,
|
|
"epoch": 0.7202479132303694,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004956562987402026,
|
|
"loss": 6.256,
|
|
"mean_token_accuracy": 0.13745878636837006,
|
|
"num_tokens": 14097139.0,
|
|
"step": 7205
|
|
},
|
|
{
|
|
"entropy": 6.224049139022827,
|
|
"epoch": 0.720747738291598,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004956493171267293,
|
|
"loss": 6.1086,
|
|
"mean_token_accuracy": 0.15160176977515222,
|
|
"num_tokens": 14107040.0,
|
|
"step": 7210
|
|
},
|
|
{
|
|
"entropy": 6.383421754837036,
|
|
"epoch": 0.7212475633528265,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.000495642329961776,
|
|
"loss": 6.2514,
|
|
"mean_token_accuracy": 0.14360006675124168,
|
|
"num_tokens": 14117103.0,
|
|
"step": 7215
|
|
},
|
|
{
|
|
"entropy": 6.401718473434448,
|
|
"epoch": 0.7217473884140551,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004956353372455185,
|
|
"loss": 6.2504,
|
|
"mean_token_accuracy": 0.14321641996502876,
|
|
"num_tokens": 14127608.0,
|
|
"step": 7220
|
|
},
|
|
{
|
|
"entropy": 6.27881383895874,
|
|
"epoch": 0.7222472134752836,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004956283389781327,
|
|
"loss": 6.1753,
|
|
"mean_token_accuracy": 0.14906150475144386,
|
|
"num_tokens": 14137618.0,
|
|
"step": 7225
|
|
},
|
|
{
|
|
"entropy": 6.2777174949646,
|
|
"epoch": 0.7227470385365122,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004956213351597946,
|
|
"loss": 6.2148,
|
|
"mean_token_accuracy": 0.14890653192996978,
|
|
"num_tokens": 14147285.0,
|
|
"step": 7230
|
|
},
|
|
{
|
|
"entropy": 6.284318304061889,
|
|
"epoch": 0.7232468635977408,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004956143257906805,
|
|
"loss": 6.1478,
|
|
"mean_token_accuracy": 0.14911566078662872,
|
|
"num_tokens": 14156398.0,
|
|
"step": 7235
|
|
},
|
|
{
|
|
"entropy": 6.239259529113769,
|
|
"epoch": 0.7237466886589694,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004956073108709667,
|
|
"loss": 6.2226,
|
|
"mean_token_accuracy": 0.13758197352290152,
|
|
"num_tokens": 14166562.0,
|
|
"step": 7240
|
|
},
|
|
{
|
|
"entropy": 6.265067005157471,
|
|
"epoch": 0.7242465137201979,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004956002904008298,
|
|
"loss": 6.0888,
|
|
"mean_token_accuracy": 0.1526718482375145,
|
|
"num_tokens": 14175824.0,
|
|
"step": 7245
|
|
},
|
|
{
|
|
"entropy": 6.3486902713775635,
|
|
"epoch": 0.7247463387814265,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004955932643804463,
|
|
"loss": 6.1528,
|
|
"mean_token_accuracy": 0.1450277164578438,
|
|
"num_tokens": 14185181.0,
|
|
"step": 7250
|
|
},
|
|
{
|
|
"entropy": 6.3490941524505615,
|
|
"epoch": 0.7252461638426551,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.000495586232809993,
|
|
"loss": 6.2731,
|
|
"mean_token_accuracy": 0.14282962530851365,
|
|
"num_tokens": 14194622.0,
|
|
"step": 7255
|
|
},
|
|
{
|
|
"entropy": 6.366567850112915,
|
|
"epoch": 0.7257459889038836,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004955791956896469,
|
|
"loss": 6.2137,
|
|
"mean_token_accuracy": 0.14499950930476188,
|
|
"num_tokens": 14204758.0,
|
|
"step": 7260
|
|
},
|
|
{
|
|
"entropy": 6.292021656036377,
|
|
"epoch": 0.7262458139651122,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000495572153019585,
|
|
"loss": 6.1878,
|
|
"mean_token_accuracy": 0.14332186356186866,
|
|
"num_tokens": 14214926.0,
|
|
"step": 7265
|
|
},
|
|
{
|
|
"entropy": 6.323084688186645,
|
|
"epoch": 0.7267456390263408,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004955651047999844,
|
|
"loss": 6.2134,
|
|
"mean_token_accuracy": 0.14154637306928636,
|
|
"num_tokens": 14225372.0,
|
|
"step": 7270
|
|
},
|
|
{
|
|
"entropy": 6.328884792327881,
|
|
"epoch": 0.7272454640875694,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004955580510310226,
|
|
"loss": 6.1521,
|
|
"mean_token_accuracy": 0.1474081188440323,
|
|
"num_tokens": 14235676.0,
|
|
"step": 7275
|
|
},
|
|
{
|
|
"entropy": 6.300685214996338,
|
|
"epoch": 0.7277452891487979,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004955509917128771,
|
|
"loss": 6.2624,
|
|
"mean_token_accuracy": 0.13789445906877518,
|
|
"num_tokens": 14244196.0,
|
|
"step": 7280
|
|
},
|
|
{
|
|
"entropy": 6.312507438659668,
|
|
"epoch": 0.7282451142100265,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004955439268457252,
|
|
"loss": 6.2368,
|
|
"mean_token_accuracy": 0.1401965029537678,
|
|
"num_tokens": 14253648.0,
|
|
"step": 7285
|
|
},
|
|
{
|
|
"entropy": 6.46242733001709,
|
|
"epoch": 0.728744939271255,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004955368564297449,
|
|
"loss": 6.3592,
|
|
"mean_token_accuracy": 0.13597094565629958,
|
|
"num_tokens": 14264373.0,
|
|
"step": 7290
|
|
},
|
|
{
|
|
"entropy": 6.311672306060791,
|
|
"epoch": 0.7292447643324836,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004955297804651142,
|
|
"loss": 6.128,
|
|
"mean_token_accuracy": 0.1502915844321251,
|
|
"num_tokens": 14274544.0,
|
|
"step": 7295
|
|
},
|
|
{
|
|
"entropy": 6.363030481338501,
|
|
"epoch": 0.7297445893937122,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004955226989520107,
|
|
"loss": 6.2276,
|
|
"mean_token_accuracy": 0.13519150614738465,
|
|
"num_tokens": 14284648.0,
|
|
"step": 7300
|
|
},
|
|
{
|
|
"entropy": 6.253767395019532,
|
|
"epoch": 0.7302444144549408,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000495515611890613,
|
|
"loss": 6.1655,
|
|
"mean_token_accuracy": 0.14713185355067254,
|
|
"num_tokens": 14294308.0,
|
|
"step": 7305
|
|
},
|
|
{
|
|
"entropy": 6.295068836212158,
|
|
"epoch": 0.7307442395161693,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004955085192810993,
|
|
"loss": 6.2184,
|
|
"mean_token_accuracy": 0.1475299045443535,
|
|
"num_tokens": 14304965.0,
|
|
"step": 7310
|
|
},
|
|
{
|
|
"entropy": 6.299453830718994,
|
|
"epoch": 0.7312440645773979,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004955014211236479,
|
|
"loss": 6.1768,
|
|
"mean_token_accuracy": 0.14760952666401864,
|
|
"num_tokens": 14315880.0,
|
|
"step": 7315
|
|
},
|
|
{
|
|
"entropy": 6.2900251865386965,
|
|
"epoch": 0.7317438896386265,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004954943174184375,
|
|
"loss": 6.2375,
|
|
"mean_token_accuracy": 0.14287684857845306,
|
|
"num_tokens": 14326316.0,
|
|
"step": 7320
|
|
},
|
|
{
|
|
"entropy": 6.290630865097046,
|
|
"epoch": 0.732243714699855,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004954872081656469,
|
|
"loss": 6.1776,
|
|
"mean_token_accuracy": 0.15054567158222198,
|
|
"num_tokens": 14335802.0,
|
|
"step": 7325
|
|
},
|
|
{
|
|
"entropy": 6.2418053150177,
|
|
"epoch": 0.7327435397610836,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004954800933654548,
|
|
"loss": 6.1637,
|
|
"mean_token_accuracy": 0.15217621996998787,
|
|
"num_tokens": 14346050.0,
|
|
"step": 7330
|
|
},
|
|
{
|
|
"entropy": 6.333403587341309,
|
|
"epoch": 0.7332433648223122,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004954729730180403,
|
|
"loss": 6.1368,
|
|
"mean_token_accuracy": 0.15035522133111953,
|
|
"num_tokens": 14355483.0,
|
|
"step": 7335
|
|
},
|
|
{
|
|
"entropy": 6.31912317276001,
|
|
"epoch": 0.7337431898835408,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004954658471235825,
|
|
"loss": 6.0991,
|
|
"mean_token_accuracy": 0.1499519780278206,
|
|
"num_tokens": 14364649.0,
|
|
"step": 7340
|
|
},
|
|
{
|
|
"entropy": 6.217097806930542,
|
|
"epoch": 0.7342430149447693,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004954587156822607,
|
|
"loss": 6.1188,
|
|
"mean_token_accuracy": 0.1522404246032238,
|
|
"num_tokens": 14374495.0,
|
|
"step": 7345
|
|
},
|
|
{
|
|
"entropy": 6.310339021682739,
|
|
"epoch": 0.7347428400059979,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004954515786942544,
|
|
"loss": 6.2123,
|
|
"mean_token_accuracy": 0.1365861713886261,
|
|
"num_tokens": 14384247.0,
|
|
"step": 7350
|
|
},
|
|
{
|
|
"entropy": 6.312385892868042,
|
|
"epoch": 0.7352426650672265,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.000495444436159743,
|
|
"loss": 6.2561,
|
|
"mean_token_accuracy": 0.1367305785417557,
|
|
"num_tokens": 14393675.0,
|
|
"step": 7355
|
|
},
|
|
{
|
|
"entropy": 6.292232418060303,
|
|
"epoch": 0.735742490128455,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004954372880789064,
|
|
"loss": 6.1558,
|
|
"mean_token_accuracy": 0.14200675413012503,
|
|
"num_tokens": 14403579.0,
|
|
"step": 7360
|
|
},
|
|
{
|
|
"entropy": 6.392525148391724,
|
|
"epoch": 0.7362423151896836,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004954301344519244,
|
|
"loss": 6.1461,
|
|
"mean_token_accuracy": 0.14907317757606506,
|
|
"num_tokens": 14413506.0,
|
|
"step": 7365
|
|
},
|
|
{
|
|
"entropy": 6.4459082126617435,
|
|
"epoch": 0.7367421402509122,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004954229752789769,
|
|
"loss": 6.3216,
|
|
"mean_token_accuracy": 0.14311579316854478,
|
|
"num_tokens": 14422960.0,
|
|
"step": 7370
|
|
},
|
|
{
|
|
"entropy": 6.364059925079346,
|
|
"epoch": 0.7372419653121407,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004954158105602441,
|
|
"loss": 6.3018,
|
|
"mean_token_accuracy": 0.14146305993199348,
|
|
"num_tokens": 14432207.0,
|
|
"step": 7375
|
|
},
|
|
{
|
|
"entropy": 6.295948457717896,
|
|
"epoch": 0.7377417903733693,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004954086402959061,
|
|
"loss": 6.2681,
|
|
"mean_token_accuracy": 0.13732415065169334,
|
|
"num_tokens": 14441785.0,
|
|
"step": 7380
|
|
},
|
|
{
|
|
"entropy": 6.390121078491211,
|
|
"epoch": 0.7382416154345979,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004954014644861435,
|
|
"loss": 6.2016,
|
|
"mean_token_accuracy": 0.14674563556909562,
|
|
"num_tokens": 14451320.0,
|
|
"step": 7385
|
|
},
|
|
{
|
|
"entropy": 6.33625340461731,
|
|
"epoch": 0.7387414404958265,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004953942831311367,
|
|
"loss": 6.3319,
|
|
"mean_token_accuracy": 0.1442642666399479,
|
|
"num_tokens": 14460777.0,
|
|
"step": 7390
|
|
},
|
|
{
|
|
"entropy": 6.3263829231262205,
|
|
"epoch": 0.739241265557055,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004953870962310666,
|
|
"loss": 6.2129,
|
|
"mean_token_accuracy": 0.14810526967048646,
|
|
"num_tokens": 14469729.0,
|
|
"step": 7395
|
|
},
|
|
{
|
|
"entropy": 6.303956747055054,
|
|
"epoch": 0.7397410906182836,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004953799037861138,
|
|
"loss": 6.1468,
|
|
"mean_token_accuracy": 0.15309115573763848,
|
|
"num_tokens": 14480559.0,
|
|
"step": 7400
|
|
},
|
|
{
|
|
"entropy": 6.348096942901611,
|
|
"epoch": 0.7402409156795122,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004953727057964594,
|
|
"loss": 6.1687,
|
|
"mean_token_accuracy": 0.1470792919397354,
|
|
"num_tokens": 14489631.0,
|
|
"step": 7405
|
|
},
|
|
{
|
|
"entropy": 6.414287137985229,
|
|
"epoch": 0.7407407407407407,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004953655022622843,
|
|
"loss": 6.3846,
|
|
"mean_token_accuracy": 0.13241870626807212,
|
|
"num_tokens": 14498994.0,
|
|
"step": 7410
|
|
},
|
|
{
|
|
"entropy": 6.377609348297119,
|
|
"epoch": 0.7412405658019693,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004953582931837699,
|
|
"loss": 6.2013,
|
|
"mean_token_accuracy": 0.14467180967330934,
|
|
"num_tokens": 14508456.0,
|
|
"step": 7415
|
|
},
|
|
{
|
|
"entropy": 6.278591775894165,
|
|
"epoch": 0.7417403908631979,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004953510785610976,
|
|
"loss": 6.1901,
|
|
"mean_token_accuracy": 0.1473128877580166,
|
|
"num_tokens": 14517388.0,
|
|
"step": 7420
|
|
},
|
|
{
|
|
"entropy": 6.390936088562012,
|
|
"epoch": 0.7422402159244265,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004953438583944487,
|
|
"loss": 6.2798,
|
|
"mean_token_accuracy": 0.14066454768180847,
|
|
"num_tokens": 14526889.0,
|
|
"step": 7425
|
|
},
|
|
{
|
|
"entropy": 6.32545428276062,
|
|
"epoch": 0.742740040985655,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004953366326840052,
|
|
"loss": 6.2261,
|
|
"mean_token_accuracy": 0.1506802536547184,
|
|
"num_tokens": 14537115.0,
|
|
"step": 7430
|
|
},
|
|
{
|
|
"entropy": 6.290111494064331,
|
|
"epoch": 0.7432398660468836,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004953294014299486,
|
|
"loss": 6.1758,
|
|
"mean_token_accuracy": 0.1470622569322586,
|
|
"num_tokens": 14547354.0,
|
|
"step": 7435
|
|
},
|
|
{
|
|
"entropy": 6.395859909057617,
|
|
"epoch": 0.7437396911081121,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004953221646324611,
|
|
"loss": 6.3802,
|
|
"mean_token_accuracy": 0.1334720805287361,
|
|
"num_tokens": 14557689.0,
|
|
"step": 7440
|
|
},
|
|
{
|
|
"entropy": 6.3484086990356445,
|
|
"epoch": 0.7442395161693407,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004953149222917245,
|
|
"loss": 6.2089,
|
|
"mean_token_accuracy": 0.14387989565730094,
|
|
"num_tokens": 14567687.0,
|
|
"step": 7445
|
|
},
|
|
{
|
|
"entropy": 6.309614610671997,
|
|
"epoch": 0.7447393412305693,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004953076744079213,
|
|
"loss": 6.2618,
|
|
"mean_token_accuracy": 0.14552861154079438,
|
|
"num_tokens": 14577800.0,
|
|
"step": 7450
|
|
},
|
|
{
|
|
"entropy": 6.416631507873535,
|
|
"epoch": 0.7452391662917979,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004953004209812335,
|
|
"loss": 6.1934,
|
|
"mean_token_accuracy": 0.14524638801813125,
|
|
"num_tokens": 14587467.0,
|
|
"step": 7455
|
|
},
|
|
{
|
|
"entropy": 6.330381250381469,
|
|
"epoch": 0.7457389913530265,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004952931620118439,
|
|
"loss": 6.1681,
|
|
"mean_token_accuracy": 0.15144518688321112,
|
|
"num_tokens": 14597710.0,
|
|
"step": 7460
|
|
},
|
|
{
|
|
"entropy": 6.295101499557495,
|
|
"epoch": 0.746238816414255,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004952858974999351,
|
|
"loss": 6.1211,
|
|
"mean_token_accuracy": 0.14862216413021087,
|
|
"num_tokens": 14607212.0,
|
|
"step": 7465
|
|
},
|
|
{
|
|
"entropy": 6.357637023925781,
|
|
"epoch": 0.7467386414754836,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004952786274456896,
|
|
"loss": 6.1922,
|
|
"mean_token_accuracy": 0.1411703571677208,
|
|
"num_tokens": 14616237.0,
|
|
"step": 7470
|
|
},
|
|
{
|
|
"entropy": 6.238756418228149,
|
|
"epoch": 0.7472384665367121,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004952713518492907,
|
|
"loss": 6.1136,
|
|
"mean_token_accuracy": 0.14785224124789237,
|
|
"num_tokens": 14625645.0,
|
|
"step": 7475
|
|
},
|
|
{
|
|
"entropy": 6.261566305160523,
|
|
"epoch": 0.7477382915979407,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004952640707109213,
|
|
"loss": 6.0904,
|
|
"mean_token_accuracy": 0.15164580941200256,
|
|
"num_tokens": 14634897.0,
|
|
"step": 7480
|
|
},
|
|
{
|
|
"entropy": 6.231878280639648,
|
|
"epoch": 0.7482381166591693,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004952567840307644,
|
|
"loss": 6.2032,
|
|
"mean_token_accuracy": 0.14593568965792655,
|
|
"num_tokens": 14645310.0,
|
|
"step": 7485
|
|
},
|
|
{
|
|
"entropy": 6.349256467819214,
|
|
"epoch": 0.7487379417203979,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004952494918090036,
|
|
"loss": 6.3066,
|
|
"mean_token_accuracy": 0.13680757507681846,
|
|
"num_tokens": 14654983.0,
|
|
"step": 7490
|
|
},
|
|
{
|
|
"entropy": 6.37339506149292,
|
|
"epoch": 0.7492377667816265,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004952421940458222,
|
|
"loss": 6.2013,
|
|
"mean_token_accuracy": 0.14576212391257287,
|
|
"num_tokens": 14664384.0,
|
|
"step": 7495
|
|
},
|
|
{
|
|
"entropy": 6.368697166442871,
|
|
"epoch": 0.749737591842855,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004952348907414039,
|
|
"loss": 6.2379,
|
|
"mean_token_accuracy": 0.13812749087810516,
|
|
"num_tokens": 14674375.0,
|
|
"step": 7500
|
|
},
|
|
{
|
|
"entropy": 6.311900806427002,
|
|
"epoch": 0.7502374169040835,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004952275818959325,
|
|
"loss": 6.1687,
|
|
"mean_token_accuracy": 0.15201991945505142,
|
|
"num_tokens": 14683212.0,
|
|
"step": 7505
|
|
},
|
|
{
|
|
"entropy": 6.248887443542481,
|
|
"epoch": 0.7507372419653121,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004952202675095916,
|
|
"loss": 6.1631,
|
|
"mean_token_accuracy": 0.14759597778320313,
|
|
"num_tokens": 14693267.0,
|
|
"step": 7510
|
|
},
|
|
{
|
|
"entropy": 6.29571270942688,
|
|
"epoch": 0.7512370670265407,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004952129475825657,
|
|
"loss": 6.1575,
|
|
"mean_token_accuracy": 0.14932916387915612,
|
|
"num_tokens": 14702835.0,
|
|
"step": 7515
|
|
},
|
|
{
|
|
"entropy": 6.290961742401123,
|
|
"epoch": 0.7517368920877693,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004952056221150385,
|
|
"loss": 6.1967,
|
|
"mean_token_accuracy": 0.14851897954940796,
|
|
"num_tokens": 14713243.0,
|
|
"step": 7520
|
|
},
|
|
{
|
|
"entropy": 6.385180330276489,
|
|
"epoch": 0.7522367171489979,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004951982911071945,
|
|
"loss": 6.2558,
|
|
"mean_token_accuracy": 0.1477909989655018,
|
|
"num_tokens": 14724943.0,
|
|
"step": 7525
|
|
},
|
|
{
|
|
"entropy": 6.343636846542358,
|
|
"epoch": 0.7527365422102265,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004951909545592183,
|
|
"loss": 6.162,
|
|
"mean_token_accuracy": 0.14616925567388533,
|
|
"num_tokens": 14734812.0,
|
|
"step": 7530
|
|
},
|
|
{
|
|
"entropy": 6.261893796920776,
|
|
"epoch": 0.753236367271455,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004951836124712942,
|
|
"loss": 6.2621,
|
|
"mean_token_accuracy": 0.14915494248270988,
|
|
"num_tokens": 14745465.0,
|
|
"step": 7535
|
|
},
|
|
{
|
|
"entropy": 6.3355108261108395,
|
|
"epoch": 0.7537361923326835,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004951762648436073,
|
|
"loss": 6.2271,
|
|
"mean_token_accuracy": 0.1380041189491749,
|
|
"num_tokens": 14755088.0,
|
|
"step": 7540
|
|
},
|
|
{
|
|
"entropy": 6.450184440612793,
|
|
"epoch": 0.7542360173939121,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004951689116763419,
|
|
"loss": 6.2808,
|
|
"mean_token_accuracy": 0.14245418682694436,
|
|
"num_tokens": 14764866.0,
|
|
"step": 7545
|
|
},
|
|
{
|
|
"entropy": 6.356716775894165,
|
|
"epoch": 0.7547358424551407,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004951615529696835,
|
|
"loss": 6.189,
|
|
"mean_token_accuracy": 0.14138278663158416,
|
|
"num_tokens": 14775528.0,
|
|
"step": 7550
|
|
},
|
|
{
|
|
"entropy": 6.25912070274353,
|
|
"epoch": 0.7552356675163693,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004951541887238172,
|
|
"loss": 6.1638,
|
|
"mean_token_accuracy": 0.14905866235494614,
|
|
"num_tokens": 14785698.0,
|
|
"step": 7555
|
|
},
|
|
{
|
|
"entropy": 6.253559494018555,
|
|
"epoch": 0.7557354925775979,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004951468189389281,
|
|
"loss": 6.1715,
|
|
"mean_token_accuracy": 0.14896537810564042,
|
|
"num_tokens": 14794765.0,
|
|
"step": 7560
|
|
},
|
|
{
|
|
"entropy": 6.468278932571411,
|
|
"epoch": 0.7562353176388265,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004951394436152016,
|
|
"loss": 6.3354,
|
|
"mean_token_accuracy": 0.1366427555680275,
|
|
"num_tokens": 14804185.0,
|
|
"step": 7565
|
|
},
|
|
{
|
|
"entropy": 6.339979600906372,
|
|
"epoch": 0.7567351427000549,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004951320627528234,
|
|
"loss": 6.1077,
|
|
"mean_token_accuracy": 0.1485820382833481,
|
|
"num_tokens": 14814270.0,
|
|
"step": 7570
|
|
},
|
|
{
|
|
"entropy": 6.174428033828735,
|
|
"epoch": 0.7572349677612835,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004951246763519791,
|
|
"loss": 6.1613,
|
|
"mean_token_accuracy": 0.15507109686732293,
|
|
"num_tokens": 14824879.0,
|
|
"step": 7575
|
|
},
|
|
{
|
|
"entropy": 6.349507474899292,
|
|
"epoch": 0.7577347928225121,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004951172844128546,
|
|
"loss": 6.2203,
|
|
"mean_token_accuracy": 0.14171002209186553,
|
|
"num_tokens": 14834882.0,
|
|
"step": 7580
|
|
},
|
|
{
|
|
"entropy": 6.302507305145264,
|
|
"epoch": 0.7582346178837407,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004951098869356358,
|
|
"loss": 6.1612,
|
|
"mean_token_accuracy": 0.14080809876322747,
|
|
"num_tokens": 14845518.0,
|
|
"step": 7585
|
|
},
|
|
{
|
|
"entropy": 6.331415033340454,
|
|
"epoch": 0.7587344429449693,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000495102483920509,
|
|
"loss": 6.2704,
|
|
"mean_token_accuracy": 0.13857753649353982,
|
|
"num_tokens": 14856046.0,
|
|
"step": 7590
|
|
},
|
|
{
|
|
"entropy": 6.437483024597168,
|
|
"epoch": 0.7592342680061979,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004950950753676603,
|
|
"loss": 6.3698,
|
|
"mean_token_accuracy": 0.13390636444091797,
|
|
"num_tokens": 14865214.0,
|
|
"step": 7595
|
|
},
|
|
{
|
|
"entropy": 6.334856748580933,
|
|
"epoch": 0.7597340930674265,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004950876612772763,
|
|
"loss": 6.1715,
|
|
"mean_token_accuracy": 0.14836979806423187,
|
|
"num_tokens": 14875708.0,
|
|
"step": 7600
|
|
},
|
|
{
|
|
"entropy": 6.258086204528809,
|
|
"epoch": 0.7602339181286549,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004950802416495431,
|
|
"loss": 6.2071,
|
|
"mean_token_accuracy": 0.13905663117766381,
|
|
"num_tokens": 14886041.0,
|
|
"step": 7605
|
|
},
|
|
{
|
|
"entropy": 6.249067163467407,
|
|
"epoch": 0.7607337431898835,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004950728164846478,
|
|
"loss": 6.089,
|
|
"mean_token_accuracy": 0.14997563660144805,
|
|
"num_tokens": 14895824.0,
|
|
"step": 7610
|
|
},
|
|
{
|
|
"entropy": 6.280237627029419,
|
|
"epoch": 0.7612335682511121,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004950653857827771,
|
|
"loss": 6.1205,
|
|
"mean_token_accuracy": 0.14796930998563768,
|
|
"num_tokens": 14904946.0,
|
|
"step": 7615
|
|
},
|
|
{
|
|
"entropy": 6.315958070755005,
|
|
"epoch": 0.7617333933123407,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004950579495441177,
|
|
"loss": 6.0885,
|
|
"mean_token_accuracy": 0.14441069811582566,
|
|
"num_tokens": 14914088.0,
|
|
"step": 7620
|
|
},
|
|
{
|
|
"entropy": 6.2729331970214846,
|
|
"epoch": 0.7622332183735693,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004950505077688572,
|
|
"loss": 6.2955,
|
|
"mean_token_accuracy": 0.1413036197423935,
|
|
"num_tokens": 14924780.0,
|
|
"step": 7625
|
|
},
|
|
{
|
|
"entropy": 6.262010478973389,
|
|
"epoch": 0.7627330434347979,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004950430604571824,
|
|
"loss": 6.1122,
|
|
"mean_token_accuracy": 0.14823548048734664,
|
|
"num_tokens": 14933857.0,
|
|
"step": 7630
|
|
},
|
|
{
|
|
"entropy": 6.290208959579468,
|
|
"epoch": 0.7632328684960263,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004950356076092808,
|
|
"loss": 6.1411,
|
|
"mean_token_accuracy": 0.14823199659585953,
|
|
"num_tokens": 14944223.0,
|
|
"step": 7635
|
|
},
|
|
{
|
|
"entropy": 6.408723020553589,
|
|
"epoch": 0.7637326935572549,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00049502814922534,
|
|
"loss": 6.3959,
|
|
"mean_token_accuracy": 0.13327127322554588,
|
|
"num_tokens": 14953677.0,
|
|
"step": 7640
|
|
},
|
|
{
|
|
"entropy": 6.331975746154785,
|
|
"epoch": 0.7642325186184835,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004950206853055475,
|
|
"loss": 6.1984,
|
|
"mean_token_accuracy": 0.14544573724269866,
|
|
"num_tokens": 14963883.0,
|
|
"step": 7645
|
|
},
|
|
{
|
|
"entropy": 6.28794298171997,
|
|
"epoch": 0.7647323436797121,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004950132158500913,
|
|
"loss": 6.1373,
|
|
"mean_token_accuracy": 0.14800980389118196,
|
|
"num_tokens": 14973680.0,
|
|
"step": 7650
|
|
},
|
|
{
|
|
"entropy": 6.302719020843506,
|
|
"epoch": 0.7652321687409407,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004950057408591591,
|
|
"loss": 6.1147,
|
|
"mean_token_accuracy": 0.15342116802930833,
|
|
"num_tokens": 14982492.0,
|
|
"step": 7655
|
|
},
|
|
{
|
|
"entropy": 6.254760456085205,
|
|
"epoch": 0.7657319938021693,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004949982603329391,
|
|
"loss": 6.0667,
|
|
"mean_token_accuracy": 0.15364200472831727,
|
|
"num_tokens": 14991555.0,
|
|
"step": 7660
|
|
},
|
|
{
|
|
"entropy": 6.404291868209839,
|
|
"epoch": 0.7662318188633979,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004949907742716195,
|
|
"loss": 6.2873,
|
|
"mean_token_accuracy": 0.13565628826618195,
|
|
"num_tokens": 15000678.0,
|
|
"step": 7665
|
|
},
|
|
{
|
|
"entropy": 6.234206485748291,
|
|
"epoch": 0.7667316439246263,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004949832826753886,
|
|
"loss": 6.1604,
|
|
"mean_token_accuracy": 0.14629355669021607,
|
|
"num_tokens": 15010418.0,
|
|
"step": 7670
|
|
},
|
|
{
|
|
"entropy": 6.300794219970703,
|
|
"epoch": 0.7672314689858549,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000494975785544435,
|
|
"loss": 6.2963,
|
|
"mean_token_accuracy": 0.13721828237175943,
|
|
"num_tokens": 15020829.0,
|
|
"step": 7675
|
|
},
|
|
{
|
|
"entropy": 6.392731952667236,
|
|
"epoch": 0.7677312940470835,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004949682828789472,
|
|
"loss": 6.1841,
|
|
"mean_token_accuracy": 0.13928207382559776,
|
|
"num_tokens": 15030055.0,
|
|
"step": 7680
|
|
},
|
|
{
|
|
"entropy": 6.297975635528564,
|
|
"epoch": 0.7682311191083121,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.000494960774679114,
|
|
"loss": 6.1291,
|
|
"mean_token_accuracy": 0.14844092950224877,
|
|
"num_tokens": 15039620.0,
|
|
"step": 7685
|
|
},
|
|
{
|
|
"entropy": 6.240979719161987,
|
|
"epoch": 0.7687309441695407,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004949532609451242,
|
|
"loss": 6.2057,
|
|
"mean_token_accuracy": 0.14623843207955362,
|
|
"num_tokens": 15049299.0,
|
|
"step": 7690
|
|
},
|
|
{
|
|
"entropy": 6.267113161087036,
|
|
"epoch": 0.7692307692307693,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004949457416771671,
|
|
"loss": 6.1522,
|
|
"mean_token_accuracy": 0.14873508661985396,
|
|
"num_tokens": 15059554.0,
|
|
"step": 7695
|
|
},
|
|
{
|
|
"entropy": 6.189442825317383,
|
|
"epoch": 0.7697305942919977,
|
|
"grad_norm": 2.234375,
|
|
"learning_rate": 0.0004949382168754316,
|
|
"loss": 6.0736,
|
|
"mean_token_accuracy": 0.14874422699213027,
|
|
"num_tokens": 15069651.0,
|
|
"step": 7700
|
|
},
|
|
{
|
|
"entropy": 6.325786161422729,
|
|
"epoch": 0.7702304193532263,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004949306865401073,
|
|
"loss": 6.201,
|
|
"mean_token_accuracy": 0.14223990142345427,
|
|
"num_tokens": 15080000.0,
|
|
"step": 7705
|
|
},
|
|
{
|
|
"entropy": 6.334896802902222,
|
|
"epoch": 0.7707302444144549,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004949231506713833,
|
|
"loss": 6.1585,
|
|
"mean_token_accuracy": 0.14810031652450562,
|
|
"num_tokens": 15089237.0,
|
|
"step": 7710
|
|
},
|
|
{
|
|
"entropy": 6.212333106994629,
|
|
"epoch": 0.7712300694756835,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004949156092694496,
|
|
"loss": 6.0421,
|
|
"mean_token_accuracy": 0.15409350246191025,
|
|
"num_tokens": 15097829.0,
|
|
"step": 7715
|
|
},
|
|
{
|
|
"entropy": 6.285293436050415,
|
|
"epoch": 0.7717298945369121,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004949080623344958,
|
|
"loss": 6.1972,
|
|
"mean_token_accuracy": 0.14618782103061675,
|
|
"num_tokens": 15106697.0,
|
|
"step": 7720
|
|
},
|
|
{
|
|
"entropy": 6.244736862182617,
|
|
"epoch": 0.7722297195981407,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004949005098667117,
|
|
"loss": 6.0343,
|
|
"mean_token_accuracy": 0.15691149085760117,
|
|
"num_tokens": 15115003.0,
|
|
"step": 7725
|
|
},
|
|
{
|
|
"entropy": 6.2918518543243405,
|
|
"epoch": 0.7727295446593693,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004948929518662873,
|
|
"loss": 6.2722,
|
|
"mean_token_accuracy": 0.1464829236268997,
|
|
"num_tokens": 15125281.0,
|
|
"step": 7730
|
|
},
|
|
{
|
|
"entropy": 6.303362321853638,
|
|
"epoch": 0.7732293697205977,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004948853883334129,
|
|
"loss": 6.1208,
|
|
"mean_token_accuracy": 0.1569477140903473,
|
|
"num_tokens": 15134609.0,
|
|
"step": 7735
|
|
},
|
|
{
|
|
"entropy": 6.3459583759307865,
|
|
"epoch": 0.7737291947818263,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004948778192682787,
|
|
"loss": 6.2618,
|
|
"mean_token_accuracy": 0.13910077661275863,
|
|
"num_tokens": 15143922.0,
|
|
"step": 7740
|
|
},
|
|
{
|
|
"entropy": 6.350108957290649,
|
|
"epoch": 0.7742290198430549,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.000494870244671075,
|
|
"loss": 6.1995,
|
|
"mean_token_accuracy": 0.14947025924921037,
|
|
"num_tokens": 15153490.0,
|
|
"step": 7745
|
|
},
|
|
{
|
|
"entropy": 6.323730897903443,
|
|
"epoch": 0.7747288449042835,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004948626645419926,
|
|
"loss": 6.195,
|
|
"mean_token_accuracy": 0.14370884448289872,
|
|
"num_tokens": 15162422.0,
|
|
"step": 7750
|
|
},
|
|
{
|
|
"entropy": 6.229171800613403,
|
|
"epoch": 0.7752286699655121,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004948550788812222,
|
|
"loss": 6.1359,
|
|
"mean_token_accuracy": 0.14826637655496597,
|
|
"num_tokens": 15171016.0,
|
|
"step": 7755
|
|
},
|
|
{
|
|
"entropy": 6.280304574966431,
|
|
"epoch": 0.7757284950267407,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004948474876889545,
|
|
"loss": 6.1154,
|
|
"mean_token_accuracy": 0.15118646621704102,
|
|
"num_tokens": 15179880.0,
|
|
"step": 7760
|
|
},
|
|
{
|
|
"entropy": 6.314484405517578,
|
|
"epoch": 0.7762283200879692,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004948398909653806,
|
|
"loss": 6.2287,
|
|
"mean_token_accuracy": 0.14712076783180236,
|
|
"num_tokens": 15190412.0,
|
|
"step": 7765
|
|
},
|
|
{
|
|
"entropy": 6.374810361862183,
|
|
"epoch": 0.7767281451491977,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004948322887106917,
|
|
"loss": 6.3399,
|
|
"mean_token_accuracy": 0.1330977775156498,
|
|
"num_tokens": 15201311.0,
|
|
"step": 7770
|
|
},
|
|
{
|
|
"entropy": 6.433690595626831,
|
|
"epoch": 0.7772279702104263,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004948246809250788,
|
|
"loss": 6.2174,
|
|
"mean_token_accuracy": 0.14403920024633407,
|
|
"num_tokens": 15210058.0,
|
|
"step": 7775
|
|
},
|
|
{
|
|
"entropy": 6.407169008255005,
|
|
"epoch": 0.7777277952716549,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004948170676087338,
|
|
"loss": 6.2546,
|
|
"mean_token_accuracy": 0.13774337321519853,
|
|
"num_tokens": 15220023.0,
|
|
"step": 7780
|
|
},
|
|
{
|
|
"entropy": 6.252200317382813,
|
|
"epoch": 0.7782276203328835,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004948094487618476,
|
|
"loss": 6.1277,
|
|
"mean_token_accuracy": 0.15259376019239426,
|
|
"num_tokens": 15229757.0,
|
|
"step": 7785
|
|
},
|
|
{
|
|
"entropy": 6.3349220752716064,
|
|
"epoch": 0.7787274453941121,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004948018243846126,
|
|
"loss": 6.2034,
|
|
"mean_token_accuracy": 0.14446027725934982,
|
|
"num_tokens": 15238928.0,
|
|
"step": 7790
|
|
},
|
|
{
|
|
"entropy": 6.24542465209961,
|
|
"epoch": 0.7792272704553407,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004947941944772199,
|
|
"loss": 6.1897,
|
|
"mean_token_accuracy": 0.1440369591116905,
|
|
"num_tokens": 15248864.0,
|
|
"step": 7795
|
|
},
|
|
{
|
|
"entropy": 6.351641511917114,
|
|
"epoch": 0.7797270955165692,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.000494786559039862,
|
|
"loss": 6.2759,
|
|
"mean_token_accuracy": 0.14626755490899085,
|
|
"num_tokens": 15259135.0,
|
|
"step": 7800
|
|
},
|
|
{
|
|
"entropy": 6.331418418884278,
|
|
"epoch": 0.7802269205777977,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004947789180727308,
|
|
"loss": 6.0978,
|
|
"mean_token_accuracy": 0.1545046254992485,
|
|
"num_tokens": 15268410.0,
|
|
"step": 7805
|
|
},
|
|
{
|
|
"entropy": 6.27475380897522,
|
|
"epoch": 0.7807267456390263,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004947712715760186,
|
|
"loss": 6.1379,
|
|
"mean_token_accuracy": 0.14849400520324707,
|
|
"num_tokens": 15277863.0,
|
|
"step": 7810
|
|
},
|
|
{
|
|
"entropy": 6.279900646209716,
|
|
"epoch": 0.7812265707002549,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004947636195499177,
|
|
"loss": 6.1926,
|
|
"mean_token_accuracy": 0.14714178889989854,
|
|
"num_tokens": 15286638.0,
|
|
"step": 7815
|
|
},
|
|
{
|
|
"entropy": 6.27982382774353,
|
|
"epoch": 0.7817263957614835,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004947559619946207,
|
|
"loss": 6.1257,
|
|
"mean_token_accuracy": 0.14487288370728493,
|
|
"num_tokens": 15296395.0,
|
|
"step": 7820
|
|
},
|
|
{
|
|
"entropy": 6.279161071777343,
|
|
"epoch": 0.7822262208227121,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004947482989103203,
|
|
"loss": 6.2005,
|
|
"mean_token_accuracy": 0.15035826414823533,
|
|
"num_tokens": 15305940.0,
|
|
"step": 7825
|
|
},
|
|
{
|
|
"entropy": 6.27035756111145,
|
|
"epoch": 0.7827260458839406,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004947406302972092,
|
|
"loss": 6.2127,
|
|
"mean_token_accuracy": 0.1441306971013546,
|
|
"num_tokens": 15315803.0,
|
|
"step": 7830
|
|
},
|
|
{
|
|
"entropy": 6.343496179580688,
|
|
"epoch": 0.7832258709451692,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004947329561554804,
|
|
"loss": 6.2409,
|
|
"mean_token_accuracy": 0.14269353970885276,
|
|
"num_tokens": 15325742.0,
|
|
"step": 7835
|
|
},
|
|
{
|
|
"entropy": 6.29396653175354,
|
|
"epoch": 0.7837256960063977,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004947252764853269,
|
|
"loss": 6.1228,
|
|
"mean_token_accuracy": 0.1486676186323166,
|
|
"num_tokens": 15336366.0,
|
|
"step": 7840
|
|
},
|
|
{
|
|
"entropy": 6.298370313644409,
|
|
"epoch": 0.7842255210676263,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004947175912869421,
|
|
"loss": 6.1952,
|
|
"mean_token_accuracy": 0.14569169357419015,
|
|
"num_tokens": 15347044.0,
|
|
"step": 7845
|
|
},
|
|
{
|
|
"entropy": 6.263945770263672,
|
|
"epoch": 0.7847253461288549,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004947099005605191,
|
|
"loss": 6.0748,
|
|
"mean_token_accuracy": 0.14707342982292176,
|
|
"num_tokens": 15356397.0,
|
|
"step": 7850
|
|
},
|
|
{
|
|
"entropy": 6.227381467819214,
|
|
"epoch": 0.7852251711900835,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004947022043062517,
|
|
"loss": 6.1692,
|
|
"mean_token_accuracy": 0.1494780331850052,
|
|
"num_tokens": 15366105.0,
|
|
"step": 7855
|
|
},
|
|
{
|
|
"entropy": 6.302454137802124,
|
|
"epoch": 0.7857249962513121,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004946945025243333,
|
|
"loss": 6.2518,
|
|
"mean_token_accuracy": 0.14066690802574158,
|
|
"num_tokens": 15375377.0,
|
|
"step": 7860
|
|
},
|
|
{
|
|
"entropy": 6.33960919380188,
|
|
"epoch": 0.7862248213125406,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004946867952149577,
|
|
"loss": 6.2359,
|
|
"mean_token_accuracy": 0.14246560111641884,
|
|
"num_tokens": 15385718.0,
|
|
"step": 7865
|
|
},
|
|
{
|
|
"entropy": 6.358570384979248,
|
|
"epoch": 0.7867246463737692,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004946790823783189,
|
|
"loss": 6.244,
|
|
"mean_token_accuracy": 0.13942286223173142,
|
|
"num_tokens": 15395032.0,
|
|
"step": 7870
|
|
},
|
|
{
|
|
"entropy": 6.308583784103393,
|
|
"epoch": 0.7872244714349977,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.000494671364014611,
|
|
"loss": 6.2348,
|
|
"mean_token_accuracy": 0.1442372642457485,
|
|
"num_tokens": 15405023.0,
|
|
"step": 7875
|
|
},
|
|
{
|
|
"entropy": 6.24981164932251,
|
|
"epoch": 0.7877242964962263,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000494663640124028,
|
|
"loss": 6.115,
|
|
"mean_token_accuracy": 0.15042841732501983,
|
|
"num_tokens": 15414174.0,
|
|
"step": 7880
|
|
},
|
|
{
|
|
"entropy": 6.247652196884156,
|
|
"epoch": 0.7882241215574549,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004946559107067643,
|
|
"loss": 6.1461,
|
|
"mean_token_accuracy": 0.14153414517641066,
|
|
"num_tokens": 15423622.0,
|
|
"step": 7885
|
|
},
|
|
{
|
|
"entropy": 6.322947835922241,
|
|
"epoch": 0.7887239466186835,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004946481757630146,
|
|
"loss": 6.1988,
|
|
"mean_token_accuracy": 0.145340296626091,
|
|
"num_tokens": 15433873.0,
|
|
"step": 7890
|
|
},
|
|
{
|
|
"entropy": 6.275658893585205,
|
|
"epoch": 0.789223771679912,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004946404352929732,
|
|
"loss": 6.0666,
|
|
"mean_token_accuracy": 0.15388471707701684,
|
|
"num_tokens": 15443600.0,
|
|
"step": 7895
|
|
},
|
|
{
|
|
"entropy": 6.2278729438781735,
|
|
"epoch": 0.7897235967411406,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.000494632689296835,
|
|
"loss": 6.19,
|
|
"mean_token_accuracy": 0.14828322902321817,
|
|
"num_tokens": 15454531.0,
|
|
"step": 7900
|
|
},
|
|
{
|
|
"entropy": 6.2535449981689455,
|
|
"epoch": 0.7902234218023692,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004946249377747947,
|
|
"loss": 6.0927,
|
|
"mean_token_accuracy": 0.16011133044958115,
|
|
"num_tokens": 15464313.0,
|
|
"step": 7905
|
|
},
|
|
{
|
|
"entropy": 6.257008361816406,
|
|
"epoch": 0.7907232468635977,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004946171807270476,
|
|
"loss": 6.1771,
|
|
"mean_token_accuracy": 0.14582148790359498,
|
|
"num_tokens": 15473363.0,
|
|
"step": 7910
|
|
},
|
|
{
|
|
"entropy": 6.287841749191284,
|
|
"epoch": 0.7912230719248263,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004946094181537887,
|
|
"loss": 6.2153,
|
|
"mean_token_accuracy": 0.14719806015491485,
|
|
"num_tokens": 15483296.0,
|
|
"step": 7915
|
|
},
|
|
{
|
|
"entropy": 6.246859884262085,
|
|
"epoch": 0.7917228969860549,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004946016500552134,
|
|
"loss": 6.2386,
|
|
"mean_token_accuracy": 0.14390528574585915,
|
|
"num_tokens": 15493579.0,
|
|
"step": 7920
|
|
},
|
|
{
|
|
"entropy": 6.356759929656983,
|
|
"epoch": 0.7922227220472835,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004945938764315171,
|
|
"loss": 6.1395,
|
|
"mean_token_accuracy": 0.14601777642965316,
|
|
"num_tokens": 15502105.0,
|
|
"step": 7925
|
|
},
|
|
{
|
|
"entropy": 6.340047168731689,
|
|
"epoch": 0.792722547108512,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004945860972828954,
|
|
"loss": 6.1239,
|
|
"mean_token_accuracy": 0.1426735945045948,
|
|
"num_tokens": 15511888.0,
|
|
"step": 7930
|
|
},
|
|
{
|
|
"entropy": 6.251442003250122,
|
|
"epoch": 0.7932223721697406,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004945783126095439,
|
|
"loss": 6.1639,
|
|
"mean_token_accuracy": 0.1460930399596691,
|
|
"num_tokens": 15522469.0,
|
|
"step": 7935
|
|
},
|
|
{
|
|
"entropy": 6.211803579330445,
|
|
"epoch": 0.7937221972309692,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004945705224116586,
|
|
"loss": 6.2522,
|
|
"mean_token_accuracy": 0.1411016419529915,
|
|
"num_tokens": 15533332.0,
|
|
"step": 7940
|
|
},
|
|
{
|
|
"entropy": 6.373286342620849,
|
|
"epoch": 0.7942220222921977,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004945627266894354,
|
|
"loss": 6.1511,
|
|
"mean_token_accuracy": 0.1492772251367569,
|
|
"num_tokens": 15542861.0,
|
|
"step": 7945
|
|
},
|
|
{
|
|
"entropy": 6.275880813598633,
|
|
"epoch": 0.7947218473534263,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004945549254430707,
|
|
"loss": 6.1326,
|
|
"mean_token_accuracy": 0.1411457486450672,
|
|
"num_tokens": 15552503.0,
|
|
"step": 7950
|
|
},
|
|
{
|
|
"entropy": 6.191089248657226,
|
|
"epoch": 0.7952216724146549,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004945471186727603,
|
|
"loss": 6.1315,
|
|
"mean_token_accuracy": 0.15307629704475403,
|
|
"num_tokens": 15562397.0,
|
|
"step": 7955
|
|
},
|
|
{
|
|
"entropy": 6.374970006942749,
|
|
"epoch": 0.7957214974758834,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004945393063787011,
|
|
"loss": 6.1719,
|
|
"mean_token_accuracy": 0.13816557079553604,
|
|
"num_tokens": 15570956.0,
|
|
"step": 7960
|
|
},
|
|
{
|
|
"entropy": 6.2921782493591305,
|
|
"epoch": 0.796221322537112,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004945314885610894,
|
|
"loss": 6.0866,
|
|
"mean_token_accuracy": 0.15081177949905394,
|
|
"num_tokens": 15579938.0,
|
|
"step": 7965
|
|
},
|
|
{
|
|
"entropy": 6.2503406524658205,
|
|
"epoch": 0.7967211475983406,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004945236652201219,
|
|
"loss": 6.1551,
|
|
"mean_token_accuracy": 0.1501242384314537,
|
|
"num_tokens": 15589906.0,
|
|
"step": 7970
|
|
},
|
|
{
|
|
"entropy": 6.34084849357605,
|
|
"epoch": 0.7972209726595691,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004945158363559955,
|
|
"loss": 6.2331,
|
|
"mean_token_accuracy": 0.14189469441771507,
|
|
"num_tokens": 15599891.0,
|
|
"step": 7975
|
|
},
|
|
{
|
|
"entropy": 6.373281097412109,
|
|
"epoch": 0.7977207977207977,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004945080019689071,
|
|
"loss": 6.336,
|
|
"mean_token_accuracy": 0.13428587540984155,
|
|
"num_tokens": 15609669.0,
|
|
"step": 7980
|
|
},
|
|
{
|
|
"entropy": 6.389525651931763,
|
|
"epoch": 0.7982206227820263,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004945001620590538,
|
|
"loss": 6.2552,
|
|
"mean_token_accuracy": 0.14018792957067489,
|
|
"num_tokens": 15619899.0,
|
|
"step": 7985
|
|
},
|
|
{
|
|
"entropy": 6.377849531173706,
|
|
"epoch": 0.7987204478432549,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.000494492316626633,
|
|
"loss": 6.2389,
|
|
"mean_token_accuracy": 0.1450905069708824,
|
|
"num_tokens": 15629822.0,
|
|
"step": 7990
|
|
},
|
|
{
|
|
"entropy": 6.282259845733643,
|
|
"epoch": 0.7992202729044834,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004944844656718419,
|
|
"loss": 6.1636,
|
|
"mean_token_accuracy": 0.1422221541404724,
|
|
"num_tokens": 15639810.0,
|
|
"step": 7995
|
|
},
|
|
{
|
|
"entropy": 6.291674280166626,
|
|
"epoch": 0.799720097965712,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004944766091948783,
|
|
"loss": 6.1564,
|
|
"mean_token_accuracy": 0.1462959423661232,
|
|
"num_tokens": 15649701.0,
|
|
"step": 8000
|
|
},
|
|
{
|
|
"entropy": 6.413050603866577,
|
|
"epoch": 0.8002199230269406,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004944687471959395,
|
|
"loss": 6.2271,
|
|
"mean_token_accuracy": 0.147781403362751,
|
|
"num_tokens": 15659969.0,
|
|
"step": 8005
|
|
},
|
|
{
|
|
"entropy": 6.317382669448852,
|
|
"epoch": 0.8007197480881691,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004944608796752237,
|
|
"loss": 6.1593,
|
|
"mean_token_accuracy": 0.14672942608594894,
|
|
"num_tokens": 15669947.0,
|
|
"step": 8010
|
|
},
|
|
{
|
|
"entropy": 6.271909618377686,
|
|
"epoch": 0.8012195731493977,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004944530066329284,
|
|
"loss": 6.2251,
|
|
"mean_token_accuracy": 0.14509136080741883,
|
|
"num_tokens": 15678799.0,
|
|
"step": 8015
|
|
},
|
|
{
|
|
"entropy": 6.385493469238281,
|
|
"epoch": 0.8017193982106263,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004944451280692521,
|
|
"loss": 6.1579,
|
|
"mean_token_accuracy": 0.1431487664580345,
|
|
"num_tokens": 15688859.0,
|
|
"step": 8020
|
|
},
|
|
{
|
|
"entropy": 6.231485366821289,
|
|
"epoch": 0.8022192232718548,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004944372439843927,
|
|
"loss": 6.1033,
|
|
"mean_token_accuracy": 0.14942432045936585,
|
|
"num_tokens": 15697121.0,
|
|
"step": 8025
|
|
},
|
|
{
|
|
"entropy": 6.251531600952148,
|
|
"epoch": 0.8027190483330834,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004944293543785489,
|
|
"loss": 6.2614,
|
|
"mean_token_accuracy": 0.14371100664138795,
|
|
"num_tokens": 15707918.0,
|
|
"step": 8030
|
|
},
|
|
{
|
|
"entropy": 6.3498780727386475,
|
|
"epoch": 0.803218873394312,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004944214592519188,
|
|
"loss": 6.1619,
|
|
"mean_token_accuracy": 0.1502821072936058,
|
|
"num_tokens": 15717342.0,
|
|
"step": 8035
|
|
},
|
|
{
|
|
"entropy": 6.317608880996704,
|
|
"epoch": 0.8037186984555406,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004944135586047014,
|
|
"loss": 6.1718,
|
|
"mean_token_accuracy": 0.1466163255274296,
|
|
"num_tokens": 15727767.0,
|
|
"step": 8040
|
|
},
|
|
{
|
|
"entropy": 6.276845550537109,
|
|
"epoch": 0.8042185235167691,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004944056524370953,
|
|
"loss": 6.1787,
|
|
"mean_token_accuracy": 0.14879640713334083,
|
|
"num_tokens": 15737049.0,
|
|
"step": 8045
|
|
},
|
|
{
|
|
"entropy": 6.244410133361816,
|
|
"epoch": 0.8047183485779977,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004943977407492994,
|
|
"loss": 6.1089,
|
|
"mean_token_accuracy": 0.1464175522327423,
|
|
"num_tokens": 15746640.0,
|
|
"step": 8050
|
|
},
|
|
{
|
|
"entropy": 6.334406089782715,
|
|
"epoch": 0.8052181736392263,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004943898235415128,
|
|
"loss": 6.1206,
|
|
"mean_token_accuracy": 0.15196825116872786,
|
|
"num_tokens": 15756151.0,
|
|
"step": 8055
|
|
},
|
|
{
|
|
"entropy": 6.2099662780761715,
|
|
"epoch": 0.8057179987004548,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004943819008139347,
|
|
"loss": 6.066,
|
|
"mean_token_accuracy": 0.15285230278968812,
|
|
"num_tokens": 15765226.0,
|
|
"step": 8060
|
|
},
|
|
{
|
|
"entropy": 6.149449968338013,
|
|
"epoch": 0.8062178237616834,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004943739725667644,
|
|
"loss": 6.1187,
|
|
"mean_token_accuracy": 0.1511198878288269,
|
|
"num_tokens": 15775916.0,
|
|
"step": 8065
|
|
},
|
|
{
|
|
"entropy": 6.32827205657959,
|
|
"epoch": 0.806717648822912,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004943660388002014,
|
|
"loss": 6.2377,
|
|
"mean_token_accuracy": 0.14484416469931602,
|
|
"num_tokens": 15785660.0,
|
|
"step": 8070
|
|
},
|
|
{
|
|
"entropy": 6.28638973236084,
|
|
"epoch": 0.8072174738841406,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004943580995144454,
|
|
"loss": 6.2019,
|
|
"mean_token_accuracy": 0.15317482724785805,
|
|
"num_tokens": 15794995.0,
|
|
"step": 8075
|
|
},
|
|
{
|
|
"entropy": 6.3401306629180905,
|
|
"epoch": 0.8077172989453691,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004943501547096961,
|
|
"loss": 6.1806,
|
|
"mean_token_accuracy": 0.14184014201164247,
|
|
"num_tokens": 15804370.0,
|
|
"step": 8080
|
|
},
|
|
{
|
|
"entropy": 6.218646812438965,
|
|
"epoch": 0.8082171240065977,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004943422043861531,
|
|
"loss": 6.1134,
|
|
"mean_token_accuracy": 0.15055215433239938,
|
|
"num_tokens": 15814759.0,
|
|
"step": 8085
|
|
},
|
|
{
|
|
"entropy": 6.297994947433471,
|
|
"epoch": 0.8087169490678262,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004943342485440169,
|
|
"loss": 6.1938,
|
|
"mean_token_accuracy": 0.15205567330121994,
|
|
"num_tokens": 15823385.0,
|
|
"step": 8090
|
|
},
|
|
{
|
|
"entropy": 6.244811487197876,
|
|
"epoch": 0.8092167741290548,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004943262871834874,
|
|
"loss": 6.1738,
|
|
"mean_token_accuracy": 0.1462759181857109,
|
|
"num_tokens": 15833226.0,
|
|
"step": 8095
|
|
},
|
|
{
|
|
"entropy": 6.390608835220337,
|
|
"epoch": 0.8097165991902834,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004943183203047649,
|
|
"loss": 6.2845,
|
|
"mean_token_accuracy": 0.14520051181316376,
|
|
"num_tokens": 15842565.0,
|
|
"step": 8100
|
|
},
|
|
{
|
|
"entropy": 6.274631977081299,
|
|
"epoch": 0.810216424251512,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004943103479080499,
|
|
"loss": 6.1271,
|
|
"mean_token_accuracy": 0.1518069326877594,
|
|
"num_tokens": 15851816.0,
|
|
"step": 8105
|
|
},
|
|
{
|
|
"entropy": 6.209253740310669,
|
|
"epoch": 0.8107162493127406,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.000494302369993543,
|
|
"loss": 6.0968,
|
|
"mean_token_accuracy": 0.14296378046274186,
|
|
"num_tokens": 15861830.0,
|
|
"step": 8110
|
|
},
|
|
{
|
|
"entropy": 6.260493326187134,
|
|
"epoch": 0.8112160743739691,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004942943865614449,
|
|
"loss": 6.2279,
|
|
"mean_token_accuracy": 0.13823597356677056,
|
|
"num_tokens": 15871118.0,
|
|
"step": 8115
|
|
},
|
|
{
|
|
"entropy": 6.336203908920288,
|
|
"epoch": 0.8117158994351977,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004942863976119565,
|
|
"loss": 6.2283,
|
|
"mean_token_accuracy": 0.13980461284518242,
|
|
"num_tokens": 15880935.0,
|
|
"step": 8120
|
|
},
|
|
{
|
|
"entropy": 6.367153692245483,
|
|
"epoch": 0.8122157244964262,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004942784031452788,
|
|
"loss": 6.1417,
|
|
"mean_token_accuracy": 0.14696732461452483,
|
|
"num_tokens": 15890458.0,
|
|
"step": 8125
|
|
},
|
|
{
|
|
"entropy": 6.203979349136352,
|
|
"epoch": 0.8127155495576548,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004942704031616127,
|
|
"loss": 6.0586,
|
|
"mean_token_accuracy": 0.14927561432123185,
|
|
"num_tokens": 15899194.0,
|
|
"step": 8130
|
|
},
|
|
{
|
|
"entropy": 6.208375549316406,
|
|
"epoch": 0.8132153746188834,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004942623976611598,
|
|
"loss": 6.1639,
|
|
"mean_token_accuracy": 0.15308842584490776,
|
|
"num_tokens": 15909529.0,
|
|
"step": 8135
|
|
},
|
|
{
|
|
"entropy": 6.291259622573852,
|
|
"epoch": 0.813715199680112,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004942543866441215,
|
|
"loss": 6.2505,
|
|
"mean_token_accuracy": 0.1476470075547695,
|
|
"num_tokens": 15919370.0,
|
|
"step": 8140
|
|
},
|
|
{
|
|
"entropy": 6.343314504623413,
|
|
"epoch": 0.8142150247413406,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004942463701106992,
|
|
"loss": 6.1068,
|
|
"mean_token_accuracy": 0.15364054441452027,
|
|
"num_tokens": 15928651.0,
|
|
"step": 8145
|
|
},
|
|
{
|
|
"entropy": 6.287114906311035,
|
|
"epoch": 0.8147148498025691,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004942383480610946,
|
|
"loss": 6.1388,
|
|
"mean_token_accuracy": 0.14867808893322945,
|
|
"num_tokens": 15937738.0,
|
|
"step": 8150
|
|
},
|
|
{
|
|
"entropy": 6.345033597946167,
|
|
"epoch": 0.8152146748637976,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004942303204955096,
|
|
"loss": 6.2771,
|
|
"mean_token_accuracy": 0.13467902988195418,
|
|
"num_tokens": 15947167.0,
|
|
"step": 8155
|
|
},
|
|
{
|
|
"entropy": 6.300409889221191,
|
|
"epoch": 0.8157144999250262,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004942222874141461,
|
|
"loss": 6.2211,
|
|
"mean_token_accuracy": 0.14762133210897446,
|
|
"num_tokens": 15956611.0,
|
|
"step": 8160
|
|
},
|
|
{
|
|
"entropy": 6.292691469192505,
|
|
"epoch": 0.8162143249862548,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004942142488172063,
|
|
"loss": 6.1801,
|
|
"mean_token_accuracy": 0.14196729362010957,
|
|
"num_tokens": 15967085.0,
|
|
"step": 8165
|
|
},
|
|
{
|
|
"entropy": 6.2443643569946286,
|
|
"epoch": 0.8167141500474834,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004942062047048924,
|
|
"loss": 6.2016,
|
|
"mean_token_accuracy": 0.1424353078007698,
|
|
"num_tokens": 15978008.0,
|
|
"step": 8170
|
|
},
|
|
{
|
|
"entropy": 6.329860973358154,
|
|
"epoch": 0.817213975108712,
|
|
"grad_norm": 2.921875,
|
|
"learning_rate": 0.0004941981550774068,
|
|
"loss": 6.35,
|
|
"mean_token_accuracy": 0.13919807672500611,
|
|
"num_tokens": 15986975.0,
|
|
"step": 8175
|
|
},
|
|
{
|
|
"entropy": 6.230203342437744,
|
|
"epoch": 0.8177138001699406,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004941900999349521,
|
|
"loss": 6.0889,
|
|
"mean_token_accuracy": 0.1468741074204445,
|
|
"num_tokens": 15997334.0,
|
|
"step": 8180
|
|
},
|
|
{
|
|
"entropy": 6.1699385166168215,
|
|
"epoch": 0.8182136252311691,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004941820392777307,
|
|
"loss": 6.0674,
|
|
"mean_token_accuracy": 0.15493642836809157,
|
|
"num_tokens": 16007485.0,
|
|
"step": 8185
|
|
},
|
|
{
|
|
"entropy": 6.325546979904175,
|
|
"epoch": 0.8187134502923976,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004941739731059457,
|
|
"loss": 6.233,
|
|
"mean_token_accuracy": 0.14546746611595154,
|
|
"num_tokens": 16017874.0,
|
|
"step": 8190
|
|
},
|
|
{
|
|
"entropy": 6.322471952438354,
|
|
"epoch": 0.8192132753536262,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004941659014198,
|
|
"loss": 6.2657,
|
|
"mean_token_accuracy": 0.14471103101968766,
|
|
"num_tokens": 16027778.0,
|
|
"step": 8195
|
|
},
|
|
{
|
|
"entropy": 6.2709838390350345,
|
|
"epoch": 0.8197131004148548,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004941578242194965,
|
|
"loss": 6.1732,
|
|
"mean_token_accuracy": 0.15058131366968155,
|
|
"num_tokens": 16037116.0,
|
|
"step": 8200
|
|
},
|
|
{
|
|
"entropy": 6.369179821014404,
|
|
"epoch": 0.8202129254760834,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004941497415052387,
|
|
"loss": 6.2796,
|
|
"mean_token_accuracy": 0.14499787837266923,
|
|
"num_tokens": 16046890.0,
|
|
"step": 8205
|
|
},
|
|
{
|
|
"entropy": 6.347852897644043,
|
|
"epoch": 0.820712750537312,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004941416532772296,
|
|
"loss": 6.1714,
|
|
"mean_token_accuracy": 0.14729817807674409,
|
|
"num_tokens": 16057870.0,
|
|
"step": 8210
|
|
},
|
|
{
|
|
"entropy": 6.401031064987182,
|
|
"epoch": 0.8212125755985406,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.000494133559535673,
|
|
"loss": 6.2138,
|
|
"mean_token_accuracy": 0.14139816612005235,
|
|
"num_tokens": 16067578.0,
|
|
"step": 8215
|
|
},
|
|
{
|
|
"entropy": 6.268149089813233,
|
|
"epoch": 0.821712400659769,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004941254602807724,
|
|
"loss": 6.1671,
|
|
"mean_token_accuracy": 0.14500691890716552,
|
|
"num_tokens": 16077108.0,
|
|
"step": 8220
|
|
},
|
|
{
|
|
"entropy": 6.294595336914062,
|
|
"epoch": 0.8222122257209976,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004941173555127315,
|
|
"loss": 6.1241,
|
|
"mean_token_accuracy": 0.14990601688623428,
|
|
"num_tokens": 16087864.0,
|
|
"step": 8225
|
|
},
|
|
{
|
|
"entropy": 6.2137383937835695,
|
|
"epoch": 0.8227120507822262,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004941092452317546,
|
|
"loss": 6.0478,
|
|
"mean_token_accuracy": 0.15572260990738868,
|
|
"num_tokens": 16096853.0,
|
|
"step": 8230
|
|
},
|
|
{
|
|
"entropy": 6.235782194137573,
|
|
"epoch": 0.8232118758434548,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004941011294380452,
|
|
"loss": 6.0889,
|
|
"mean_token_accuracy": 0.1527320623397827,
|
|
"num_tokens": 16106012.0,
|
|
"step": 8235
|
|
},
|
|
{
|
|
"entropy": 6.210958337783813,
|
|
"epoch": 0.8237117009046834,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004940930081318079,
|
|
"loss": 6.1215,
|
|
"mean_token_accuracy": 0.1504502296447754,
|
|
"num_tokens": 16115764.0,
|
|
"step": 8240
|
|
},
|
|
{
|
|
"entropy": 6.3026824474334715,
|
|
"epoch": 0.824211525965912,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004940848813132469,
|
|
"loss": 6.1893,
|
|
"mean_token_accuracy": 0.14391789063811303,
|
|
"num_tokens": 16127211.0,
|
|
"step": 8245
|
|
},
|
|
{
|
|
"entropy": 6.3200828552246096,
|
|
"epoch": 0.8247113510271405,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004940767489825666,
|
|
"loss": 6.1577,
|
|
"mean_token_accuracy": 0.14688317924737931,
|
|
"num_tokens": 16136204.0,
|
|
"step": 8250
|
|
},
|
|
{
|
|
"entropy": 6.283053302764893,
|
|
"epoch": 0.825211176088369,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004940686111399716,
|
|
"loss": 6.0914,
|
|
"mean_token_accuracy": 0.15165790915489197,
|
|
"num_tokens": 16145411.0,
|
|
"step": 8255
|
|
},
|
|
{
|
|
"entropy": 6.258586645126343,
|
|
"epoch": 0.8257110011495976,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004940604677856669,
|
|
"loss": 6.2159,
|
|
"mean_token_accuracy": 0.1371447592973709,
|
|
"num_tokens": 16156575.0,
|
|
"step": 8260
|
|
},
|
|
{
|
|
"entropy": 6.276592111587524,
|
|
"epoch": 0.8262108262108262,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.000494052318919857,
|
|
"loss": 6.1344,
|
|
"mean_token_accuracy": 0.14887368381023408,
|
|
"num_tokens": 16167387.0,
|
|
"step": 8265
|
|
},
|
|
{
|
|
"entropy": 6.294545316696167,
|
|
"epoch": 0.8267106512720548,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004940441645427473,
|
|
"loss": 6.1382,
|
|
"mean_token_accuracy": 0.14058304578065872,
|
|
"num_tokens": 16177302.0,
|
|
"step": 8270
|
|
},
|
|
{
|
|
"entropy": 6.307913827896118,
|
|
"epoch": 0.8272104763332834,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004940360046545427,
|
|
"loss": 6.2619,
|
|
"mean_token_accuracy": 0.13909060433506965,
|
|
"num_tokens": 16186830.0,
|
|
"step": 8275
|
|
},
|
|
{
|
|
"entropy": 6.350049018859863,
|
|
"epoch": 0.827710301394512,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004940278392554486,
|
|
"loss": 6.1848,
|
|
"mean_token_accuracy": 0.14652676433324813,
|
|
"num_tokens": 16197424.0,
|
|
"step": 8280
|
|
},
|
|
{
|
|
"entropy": 6.299580240249634,
|
|
"epoch": 0.8282101264557404,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004940196683456704,
|
|
"loss": 6.1634,
|
|
"mean_token_accuracy": 0.14599313586950302,
|
|
"num_tokens": 16207209.0,
|
|
"step": 8285
|
|
},
|
|
{
|
|
"entropy": 6.320684099197388,
|
|
"epoch": 0.828709951516969,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004940114919254137,
|
|
"loss": 6.1622,
|
|
"mean_token_accuracy": 0.14545141607522966,
|
|
"num_tokens": 16217952.0,
|
|
"step": 8290
|
|
},
|
|
{
|
|
"entropy": 6.238395404815674,
|
|
"epoch": 0.8292097765781976,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004940033099948843,
|
|
"loss": 6.2038,
|
|
"mean_token_accuracy": 0.14643324688076972,
|
|
"num_tokens": 16227749.0,
|
|
"step": 8295
|
|
},
|
|
{
|
|
"entropy": 6.255685615539551,
|
|
"epoch": 0.8297096016394262,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004939951225542879,
|
|
"loss": 6.1628,
|
|
"mean_token_accuracy": 0.14679743573069573,
|
|
"num_tokens": 16236716.0,
|
|
"step": 8300
|
|
},
|
|
{
|
|
"entropy": 6.295976638793945,
|
|
"epoch": 0.8302094267006548,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004939869296038306,
|
|
"loss": 6.1365,
|
|
"mean_token_accuracy": 0.15375211387872695,
|
|
"num_tokens": 16246471.0,
|
|
"step": 8305
|
|
},
|
|
{
|
|
"entropy": 6.325051164627075,
|
|
"epoch": 0.8307092517618834,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004939787311437185,
|
|
"loss": 6.2404,
|
|
"mean_token_accuracy": 0.13944485038518906,
|
|
"num_tokens": 16256694.0,
|
|
"step": 8310
|
|
},
|
|
{
|
|
"entropy": 6.252741193771362,
|
|
"epoch": 0.831209076823112,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004939705271741579,
|
|
"loss": 6.0911,
|
|
"mean_token_accuracy": 0.15199627876281738,
|
|
"num_tokens": 16266073.0,
|
|
"step": 8315
|
|
},
|
|
{
|
|
"entropy": 6.314142036437988,
|
|
"epoch": 0.8317089018843404,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004939623176953551,
|
|
"loss": 6.1238,
|
|
"mean_token_accuracy": 0.14674125984311104,
|
|
"num_tokens": 16274608.0,
|
|
"step": 8320
|
|
},
|
|
{
|
|
"entropy": 6.229287338256836,
|
|
"epoch": 0.832208726945569,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004939541027075168,
|
|
"loss": 6.0944,
|
|
"mean_token_accuracy": 0.14839435517787933,
|
|
"num_tokens": 16284311.0,
|
|
"step": 8325
|
|
},
|
|
{
|
|
"entropy": 6.165537977218628,
|
|
"epoch": 0.8327085520067976,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004939458822108496,
|
|
"loss": 6.151,
|
|
"mean_token_accuracy": 0.1514931321144104,
|
|
"num_tokens": 16293829.0,
|
|
"step": 8330
|
|
},
|
|
{
|
|
"entropy": 6.2559449672698975,
|
|
"epoch": 0.8332083770680262,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004939376562055602,
|
|
"loss": 6.2531,
|
|
"mean_token_accuracy": 0.1485627844929695,
|
|
"num_tokens": 16303876.0,
|
|
"step": 8335
|
|
},
|
|
{
|
|
"entropy": 6.3408948421478275,
|
|
"epoch": 0.8337082021292548,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004939294246918558,
|
|
"loss": 6.1175,
|
|
"mean_token_accuracy": 0.1488794781267643,
|
|
"num_tokens": 16313781.0,
|
|
"step": 8340
|
|
},
|
|
{
|
|
"entropy": 6.197822999954224,
|
|
"epoch": 0.8342080271904834,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004939211876699435,
|
|
"loss": 6.0491,
|
|
"mean_token_accuracy": 0.16324939131736754,
|
|
"num_tokens": 16325214.0,
|
|
"step": 8345
|
|
},
|
|
{
|
|
"entropy": 6.286114311218261,
|
|
"epoch": 0.8347078522517118,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004939129451400305,
|
|
"loss": 6.0656,
|
|
"mean_token_accuracy": 0.1533803328871727,
|
|
"num_tokens": 16335635.0,
|
|
"step": 8350
|
|
},
|
|
{
|
|
"entropy": 6.336215257644653,
|
|
"epoch": 0.8352076773129404,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.000493904697102324,
|
|
"loss": 6.1886,
|
|
"mean_token_accuracy": 0.14563629031181335,
|
|
"num_tokens": 16345459.0,
|
|
"step": 8355
|
|
},
|
|
{
|
|
"entropy": 6.193558835983277,
|
|
"epoch": 0.835707502374169,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004938964435570317,
|
|
"loss": 6.0571,
|
|
"mean_token_accuracy": 0.15347934812307357,
|
|
"num_tokens": 16354972.0,
|
|
"step": 8360
|
|
},
|
|
{
|
|
"entropy": 6.225519466400146,
|
|
"epoch": 0.8362073274353976,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004938881845043612,
|
|
"loss": 6.0837,
|
|
"mean_token_accuracy": 0.15230301022529602,
|
|
"num_tokens": 16363257.0,
|
|
"step": 8365
|
|
},
|
|
{
|
|
"entropy": 6.145082473754883,
|
|
"epoch": 0.8367071524966262,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004938799199445202,
|
|
"loss": 6.1078,
|
|
"mean_token_accuracy": 0.16600719094276428,
|
|
"num_tokens": 16374102.0,
|
|
"step": 8370
|
|
},
|
|
{
|
|
"entropy": 6.240188789367676,
|
|
"epoch": 0.8372069775578548,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004938716498777169,
|
|
"loss": 6.1285,
|
|
"mean_token_accuracy": 0.15080219507217407,
|
|
"num_tokens": 16383809.0,
|
|
"step": 8375
|
|
},
|
|
{
|
|
"entropy": 6.250911235809326,
|
|
"epoch": 0.8377068026190834,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004938633743041592,
|
|
"loss": 6.2034,
|
|
"mean_token_accuracy": 0.14554041400551795,
|
|
"num_tokens": 16393743.0,
|
|
"step": 8380
|
|
},
|
|
{
|
|
"entropy": 6.239728212356567,
|
|
"epoch": 0.8382066276803118,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004938550932240552,
|
|
"loss": 6.0823,
|
|
"mean_token_accuracy": 0.15832468420267104,
|
|
"num_tokens": 16403225.0,
|
|
"step": 8385
|
|
},
|
|
{
|
|
"entropy": 6.365964031219482,
|
|
"epoch": 0.8387064527415404,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004938468066376134,
|
|
"loss": 6.1324,
|
|
"mean_token_accuracy": 0.15150270536541938,
|
|
"num_tokens": 16413104.0,
|
|
"step": 8390
|
|
},
|
|
{
|
|
"entropy": 6.239263105392456,
|
|
"epoch": 0.839206277802769,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004938385145450423,
|
|
"loss": 6.1778,
|
|
"mean_token_accuracy": 0.14437811747193335,
|
|
"num_tokens": 16422831.0,
|
|
"step": 8395
|
|
},
|
|
{
|
|
"entropy": 6.247150516510009,
|
|
"epoch": 0.8397061028639976,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004938302169465505,
|
|
"loss": 6.1406,
|
|
"mean_token_accuracy": 0.1472749799489975,
|
|
"num_tokens": 16431955.0,
|
|
"step": 8400
|
|
},
|
|
{
|
|
"entropy": 6.376676082611084,
|
|
"epoch": 0.8402059279252262,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004938219138423467,
|
|
"loss": 6.2567,
|
|
"mean_token_accuracy": 0.13974295556545258,
|
|
"num_tokens": 16443266.0,
|
|
"step": 8405
|
|
},
|
|
{
|
|
"entropy": 6.307219123840332,
|
|
"epoch": 0.8407057529864548,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004938136052326399,
|
|
"loss": 6.1413,
|
|
"mean_token_accuracy": 0.1493738502264023,
|
|
"num_tokens": 16454264.0,
|
|
"step": 8410
|
|
},
|
|
{
|
|
"entropy": 6.160571050643921,
|
|
"epoch": 0.8412055780476833,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004938052911176392,
|
|
"loss": 6.0445,
|
|
"mean_token_accuracy": 0.15207744389772415,
|
|
"num_tokens": 16463613.0,
|
|
"step": 8415
|
|
},
|
|
{
|
|
"entropy": 6.239917182922364,
|
|
"epoch": 0.8417054031089118,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004937969714975534,
|
|
"loss": 6.0886,
|
|
"mean_token_accuracy": 0.14654372185468673,
|
|
"num_tokens": 16472517.0,
|
|
"step": 8420
|
|
},
|
|
{
|
|
"entropy": 6.329404306411743,
|
|
"epoch": 0.8422052281701404,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004937886463725923,
|
|
"loss": 6.1709,
|
|
"mean_token_accuracy": 0.14707983881235123,
|
|
"num_tokens": 16482328.0,
|
|
"step": 8425
|
|
},
|
|
{
|
|
"entropy": 6.246041631698608,
|
|
"epoch": 0.842705053231369,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004937803157429651,
|
|
"loss": 6.1793,
|
|
"mean_token_accuracy": 0.14606166630983353,
|
|
"num_tokens": 16492152.0,
|
|
"step": 8430
|
|
},
|
|
{
|
|
"entropy": 6.281878995895386,
|
|
"epoch": 0.8432048782925976,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004937719796088815,
|
|
"loss": 6.1332,
|
|
"mean_token_accuracy": 0.1467640444636345,
|
|
"num_tokens": 16501740.0,
|
|
"step": 8435
|
|
},
|
|
{
|
|
"entropy": 6.295157194137573,
|
|
"epoch": 0.8437047033538262,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004937636379705511,
|
|
"loss": 6.1495,
|
|
"mean_token_accuracy": 0.14300159215927125,
|
|
"num_tokens": 16512048.0,
|
|
"step": 8440
|
|
},
|
|
{
|
|
"entropy": 6.245462656021118,
|
|
"epoch": 0.8442045284150548,
|
|
"grad_norm": 1.9140625,
|
|
"learning_rate": 0.0004937552908281839,
|
|
"loss": 6.1474,
|
|
"mean_token_accuracy": 0.1498699739575386,
|
|
"num_tokens": 16521935.0,
|
|
"step": 8445
|
|
},
|
|
{
|
|
"entropy": 6.266146326065064,
|
|
"epoch": 0.8447043534762833,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004937469381819899,
|
|
"loss": 6.1776,
|
|
"mean_token_accuracy": 0.1444061204791069,
|
|
"num_tokens": 16531953.0,
|
|
"step": 8450
|
|
},
|
|
{
|
|
"entropy": 6.266036653518677,
|
|
"epoch": 0.8452041785375118,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004937385800321792,
|
|
"loss": 6.0846,
|
|
"mean_token_accuracy": 0.1474167063832283,
|
|
"num_tokens": 16541196.0,
|
|
"step": 8455
|
|
},
|
|
{
|
|
"entropy": 6.223774814605713,
|
|
"epoch": 0.8457040035987404,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004937302163789621,
|
|
"loss": 5.9902,
|
|
"mean_token_accuracy": 0.15602245628833772,
|
|
"num_tokens": 16550453.0,
|
|
"step": 8460
|
|
},
|
|
{
|
|
"entropy": 6.284070110321045,
|
|
"epoch": 0.846203828659969,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004937218472225491,
|
|
"loss": 6.1619,
|
|
"mean_token_accuracy": 0.14609891474246978,
|
|
"num_tokens": 16560125.0,
|
|
"step": 8465
|
|
},
|
|
{
|
|
"entropy": 6.225284671783447,
|
|
"epoch": 0.8467036537211976,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004937134725631506,
|
|
"loss": 6.1037,
|
|
"mean_token_accuracy": 0.14829656332731248,
|
|
"num_tokens": 16569097.0,
|
|
"step": 8470
|
|
},
|
|
{
|
|
"entropy": 6.32614483833313,
|
|
"epoch": 0.8472034787824262,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004937050924009775,
|
|
"loss": 6.2555,
|
|
"mean_token_accuracy": 0.14651484340429305,
|
|
"num_tokens": 16579032.0,
|
|
"step": 8475
|
|
},
|
|
{
|
|
"entropy": 6.333699655532837,
|
|
"epoch": 0.8477033038436548,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004936967067362406,
|
|
"loss": 6.1513,
|
|
"mean_token_accuracy": 0.14502770006656646,
|
|
"num_tokens": 16588868.0,
|
|
"step": 8480
|
|
},
|
|
{
|
|
"entropy": 6.25390133857727,
|
|
"epoch": 0.8482031289048833,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004936883155691507,
|
|
"loss": 6.0918,
|
|
"mean_token_accuracy": 0.15236334428191184,
|
|
"num_tokens": 16598043.0,
|
|
"step": 8485
|
|
},
|
|
{
|
|
"entropy": 6.176337385177613,
|
|
"epoch": 0.8487029539661118,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004936799188999192,
|
|
"loss": 6.0935,
|
|
"mean_token_accuracy": 0.1534414619207382,
|
|
"num_tokens": 16607145.0,
|
|
"step": 8490
|
|
},
|
|
{
|
|
"entropy": 6.229042625427246,
|
|
"epoch": 0.8492027790273404,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004936715167287571,
|
|
"loss": 6.1205,
|
|
"mean_token_accuracy": 0.1504385069012642,
|
|
"num_tokens": 16616930.0,
|
|
"step": 8495
|
|
},
|
|
{
|
|
"entropy": 6.247959089279175,
|
|
"epoch": 0.849702604088569,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.000493663109055876,
|
|
"loss": 6.1233,
|
|
"mean_token_accuracy": 0.14941577315330506,
|
|
"num_tokens": 16628175.0,
|
|
"step": 8500
|
|
},
|
|
{
|
|
"entropy": 6.283598709106445,
|
|
"epoch": 0.8502024291497976,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004936546958814873,
|
|
"loss": 6.1722,
|
|
"mean_token_accuracy": 0.1443457432091236,
|
|
"num_tokens": 16638914.0,
|
|
"step": 8505
|
|
},
|
|
{
|
|
"entropy": 6.25822491645813,
|
|
"epoch": 0.8507022542110262,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 0.0004936462772058026,
|
|
"loss": 6.1616,
|
|
"mean_token_accuracy": 0.14130658209323882,
|
|
"num_tokens": 16648299.0,
|
|
"step": 8510
|
|
},
|
|
{
|
|
"entropy": 6.251192188262939,
|
|
"epoch": 0.8512020792722547,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004936378530290339,
|
|
"loss": 6.1581,
|
|
"mean_token_accuracy": 0.1452266737818718,
|
|
"num_tokens": 16658088.0,
|
|
"step": 8515
|
|
},
|
|
{
|
|
"entropy": 6.284399557113647,
|
|
"epoch": 0.8517019043334833,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004936294233513931,
|
|
"loss": 6.2275,
|
|
"mean_token_accuracy": 0.1381968230009079,
|
|
"num_tokens": 16669324.0,
|
|
"step": 8520
|
|
},
|
|
{
|
|
"entropy": 6.276660060882568,
|
|
"epoch": 0.8522017293947118,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004936209881730922,
|
|
"loss": 6.1025,
|
|
"mean_token_accuracy": 0.14990838542580603,
|
|
"num_tokens": 16679118.0,
|
|
"step": 8525
|
|
},
|
|
{
|
|
"entropy": 6.315235900878906,
|
|
"epoch": 0.8527015544559404,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004936125474943436,
|
|
"loss": 6.1766,
|
|
"mean_token_accuracy": 0.1414633259177208,
|
|
"num_tokens": 16689245.0,
|
|
"step": 8530
|
|
},
|
|
{
|
|
"entropy": 6.2860133171081545,
|
|
"epoch": 0.853201379517169,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004936041013153596,
|
|
"loss": 6.1596,
|
|
"mean_token_accuracy": 0.1472108855843544,
|
|
"num_tokens": 16698364.0,
|
|
"step": 8535
|
|
},
|
|
{
|
|
"entropy": 6.240392827987671,
|
|
"epoch": 0.8537012045783976,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004935956496363525,
|
|
"loss": 6.1159,
|
|
"mean_token_accuracy": 0.15300555378198624,
|
|
"num_tokens": 16708059.0,
|
|
"step": 8540
|
|
},
|
|
{
|
|
"entropy": 6.319275665283203,
|
|
"epoch": 0.8542010296396262,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004935871924575352,
|
|
"loss": 6.1122,
|
|
"mean_token_accuracy": 0.1480521686375141,
|
|
"num_tokens": 16717206.0,
|
|
"step": 8545
|
|
},
|
|
{
|
|
"entropy": 6.212071132659912,
|
|
"epoch": 0.8547008547008547,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004935787297791204,
|
|
"loss": 6.0694,
|
|
"mean_token_accuracy": 0.14809702038764955,
|
|
"num_tokens": 16726889.0,
|
|
"step": 8550
|
|
},
|
|
{
|
|
"entropy": 6.264035415649414,
|
|
"epoch": 0.8552006797620832,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004935702616013209,
|
|
"loss": 6.1998,
|
|
"mean_token_accuracy": 0.14563535302877426,
|
|
"num_tokens": 16737232.0,
|
|
"step": 8555
|
|
},
|
|
{
|
|
"entropy": 6.258747243881226,
|
|
"epoch": 0.8557005048233118,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.00049356178792435,
|
|
"loss": 6.0702,
|
|
"mean_token_accuracy": 0.1547325909137726,
|
|
"num_tokens": 16747213.0,
|
|
"step": 8560
|
|
},
|
|
{
|
|
"entropy": 6.283885812759399,
|
|
"epoch": 0.8562003298845404,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.0004935533087484207,
|
|
"loss": 6.1025,
|
|
"mean_token_accuracy": 0.1454384870827198,
|
|
"num_tokens": 16756412.0,
|
|
"step": 8565
|
|
},
|
|
{
|
|
"entropy": 6.245044755935669,
|
|
"epoch": 0.856700154945769,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004935448240737464,
|
|
"loss": 6.133,
|
|
"mean_token_accuracy": 0.14659983813762664,
|
|
"num_tokens": 16766475.0,
|
|
"step": 8570
|
|
},
|
|
{
|
|
"entropy": 6.245946741104126,
|
|
"epoch": 0.8571999800069976,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004935363339005405,
|
|
"loss": 6.1232,
|
|
"mean_token_accuracy": 0.14707613587379456,
|
|
"num_tokens": 16775903.0,
|
|
"step": 8575
|
|
},
|
|
{
|
|
"entropy": 6.349631881713867,
|
|
"epoch": 0.8576998050682261,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004935278382290168,
|
|
"loss": 6.2153,
|
|
"mean_token_accuracy": 0.14394367411732673,
|
|
"num_tokens": 16785347.0,
|
|
"step": 8580
|
|
},
|
|
{
|
|
"entropy": 6.274719715118408,
|
|
"epoch": 0.8581996301294547,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004935193370593887,
|
|
"loss": 6.1482,
|
|
"mean_token_accuracy": 0.15185702890157698,
|
|
"num_tokens": 16794704.0,
|
|
"step": 8585
|
|
},
|
|
{
|
|
"entropy": 6.280138826370239,
|
|
"epoch": 0.8586994551906832,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004935108303918705,
|
|
"loss": 6.0957,
|
|
"mean_token_accuracy": 0.15252209901809693,
|
|
"num_tokens": 16804711.0,
|
|
"step": 8590
|
|
},
|
|
{
|
|
"entropy": 6.243320417404175,
|
|
"epoch": 0.8591992802519118,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004935023182266761,
|
|
"loss": 6.1518,
|
|
"mean_token_accuracy": 0.14576567336916924,
|
|
"num_tokens": 16814217.0,
|
|
"step": 8595
|
|
},
|
|
{
|
|
"entropy": 6.274166011810303,
|
|
"epoch": 0.8596991053131404,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004934938005640194,
|
|
"loss": 6.1158,
|
|
"mean_token_accuracy": 0.15240332633256912,
|
|
"num_tokens": 16823652.0,
|
|
"step": 8600
|
|
},
|
|
{
|
|
"entropy": 6.298847579956055,
|
|
"epoch": 0.860198930374369,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.000493485277404115,
|
|
"loss": 6.1401,
|
|
"mean_token_accuracy": 0.14576715901494025,
|
|
"num_tokens": 16832293.0,
|
|
"step": 8605
|
|
},
|
|
{
|
|
"entropy": 6.276272249221802,
|
|
"epoch": 0.8606987554355976,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004934767487471772,
|
|
"loss": 6.1681,
|
|
"mean_token_accuracy": 0.1488754317164421,
|
|
"num_tokens": 16840877.0,
|
|
"step": 8610
|
|
},
|
|
{
|
|
"entropy": 6.2254273891448975,
|
|
"epoch": 0.8611985804968261,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004934682145934207,
|
|
"loss": 6.175,
|
|
"mean_token_accuracy": 0.1431325152516365,
|
|
"num_tokens": 16851245.0,
|
|
"step": 8615
|
|
},
|
|
{
|
|
"entropy": 6.28835620880127,
|
|
"epoch": 0.8616984055580547,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00049345967494306,
|
|
"loss": 6.1557,
|
|
"mean_token_accuracy": 0.14635056629776955,
|
|
"num_tokens": 16862023.0,
|
|
"step": 8620
|
|
},
|
|
{
|
|
"entropy": 6.266018295288086,
|
|
"epoch": 0.8621982306192832,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004934511297963102,
|
|
"loss": 6.1371,
|
|
"mean_token_accuracy": 0.15106738954782487,
|
|
"num_tokens": 16871262.0,
|
|
"step": 8625
|
|
},
|
|
{
|
|
"entropy": 6.350247859954834,
|
|
"epoch": 0.8626980556805118,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004934425791533861,
|
|
"loss": 6.253,
|
|
"mean_token_accuracy": 0.14286625608801842,
|
|
"num_tokens": 16881513.0,
|
|
"step": 8630
|
|
},
|
|
{
|
|
"entropy": 6.161167764663697,
|
|
"epoch": 0.8631978807417404,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004934340230145031,
|
|
"loss": 6.0221,
|
|
"mean_token_accuracy": 0.15355553328990937,
|
|
"num_tokens": 16891516.0,
|
|
"step": 8635
|
|
},
|
|
{
|
|
"entropy": 6.260900688171387,
|
|
"epoch": 0.863697705802969,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004934254613798761,
|
|
"loss": 6.1814,
|
|
"mean_token_accuracy": 0.1463272601366043,
|
|
"num_tokens": 16901405.0,
|
|
"step": 8640
|
|
},
|
|
{
|
|
"entropy": 6.237873315811157,
|
|
"epoch": 0.8641975308641975,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004934168942497207,
|
|
"loss": 6.0945,
|
|
"mean_token_accuracy": 0.15495193153619766,
|
|
"num_tokens": 16911404.0,
|
|
"step": 8645
|
|
},
|
|
{
|
|
"entropy": 6.266516017913818,
|
|
"epoch": 0.8646973559254261,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004934083216242526,
|
|
"loss": 6.0834,
|
|
"mean_token_accuracy": 0.14429578334093093,
|
|
"num_tokens": 16920837.0,
|
|
"step": 8650
|
|
},
|
|
{
|
|
"entropy": 6.308184576034546,
|
|
"epoch": 0.8651971809866547,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004933997435036873,
|
|
"loss": 6.2177,
|
|
"mean_token_accuracy": 0.13706560134887696,
|
|
"num_tokens": 16930255.0,
|
|
"step": 8655
|
|
},
|
|
{
|
|
"entropy": 6.246794843673706,
|
|
"epoch": 0.8656970060478832,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004933911598882405,
|
|
"loss": 6.1557,
|
|
"mean_token_accuracy": 0.139996225386858,
|
|
"num_tokens": 16940188.0,
|
|
"step": 8660
|
|
},
|
|
{
|
|
"entropy": 6.337051057815552,
|
|
"epoch": 0.8661968311091118,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004933825707781284,
|
|
"loss": 6.2342,
|
|
"mean_token_accuracy": 0.14369843080639838,
|
|
"num_tokens": 16950260.0,
|
|
"step": 8665
|
|
},
|
|
{
|
|
"entropy": 6.298245859146118,
|
|
"epoch": 0.8666966561703404,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004933739761735671,
|
|
"loss": 6.1377,
|
|
"mean_token_accuracy": 0.1453426033258438,
|
|
"num_tokens": 16959299.0,
|
|
"step": 8670
|
|
},
|
|
{
|
|
"entropy": 6.285887098312378,
|
|
"epoch": 0.867196481231569,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004933653760747726,
|
|
"loss": 6.3056,
|
|
"mean_token_accuracy": 0.14031370133161544,
|
|
"num_tokens": 16969541.0,
|
|
"step": 8675
|
|
},
|
|
{
|
|
"entropy": 6.270383405685425,
|
|
"epoch": 0.8676963062927975,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004933567704819615,
|
|
"loss": 6.1201,
|
|
"mean_token_accuracy": 0.1441718354821205,
|
|
"num_tokens": 16978754.0,
|
|
"step": 8680
|
|
},
|
|
{
|
|
"entropy": 6.34366021156311,
|
|
"epoch": 0.8681961313540261,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004933481593953502,
|
|
"loss": 6.2036,
|
|
"mean_token_accuracy": 0.1441444545984268,
|
|
"num_tokens": 16989188.0,
|
|
"step": 8685
|
|
},
|
|
{
|
|
"entropy": 6.252267456054687,
|
|
"epoch": 0.8686959564152547,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004933395428151554,
|
|
"loss": 6.1265,
|
|
"mean_token_accuracy": 0.14513652995228768,
|
|
"num_tokens": 16999295.0,
|
|
"step": 8690
|
|
},
|
|
{
|
|
"entropy": 6.338964605331421,
|
|
"epoch": 0.8691957814764832,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.000493330920741594,
|
|
"loss": 6.1758,
|
|
"mean_token_accuracy": 0.1430986523628235,
|
|
"num_tokens": 17009080.0,
|
|
"step": 8695
|
|
},
|
|
{
|
|
"entropy": 6.277364492416382,
|
|
"epoch": 0.8696956065377118,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004933222931748827,
|
|
"loss": 6.1703,
|
|
"mean_token_accuracy": 0.1485441356897354,
|
|
"num_tokens": 17018201.0,
|
|
"step": 8700
|
|
},
|
|
{
|
|
"entropy": 6.307969236373902,
|
|
"epoch": 0.8701954315989404,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004933136601152387,
|
|
"loss": 6.2214,
|
|
"mean_token_accuracy": 0.14555304497480392,
|
|
"num_tokens": 17027896.0,
|
|
"step": 8705
|
|
},
|
|
{
|
|
"entropy": 6.21087236404419,
|
|
"epoch": 0.8706952566601689,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004933050215628793,
|
|
"loss": 6.0449,
|
|
"mean_token_accuracy": 0.1521621271967888,
|
|
"num_tokens": 17038846.0,
|
|
"step": 8710
|
|
},
|
|
{
|
|
"entropy": 6.279975843429566,
|
|
"epoch": 0.8711950817213975,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004932963775180216,
|
|
"loss": 6.1021,
|
|
"mean_token_accuracy": 0.15255472660064698,
|
|
"num_tokens": 17048021.0,
|
|
"step": 8715
|
|
},
|
|
{
|
|
"entropy": 6.260575914382935,
|
|
"epoch": 0.8716949067826261,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004932877279808833,
|
|
"loss": 6.1888,
|
|
"mean_token_accuracy": 0.14471224546432496,
|
|
"num_tokens": 17058076.0,
|
|
"step": 8720
|
|
},
|
|
{
|
|
"entropy": 6.268863773345947,
|
|
"epoch": 0.8721947318438547,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004932790729516818,
|
|
"loss": 6.1404,
|
|
"mean_token_accuracy": 0.1452201411128044,
|
|
"num_tokens": 17068988.0,
|
|
"step": 8725
|
|
},
|
|
{
|
|
"entropy": 6.273371410369873,
|
|
"epoch": 0.8726945569050832,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004932704124306352,
|
|
"loss": 6.2403,
|
|
"mean_token_accuracy": 0.14546009749174119,
|
|
"num_tokens": 17079423.0,
|
|
"step": 8730
|
|
},
|
|
{
|
|
"entropy": 6.329331016540527,
|
|
"epoch": 0.8731943819663118,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.000493261746417961,
|
|
"loss": 6.166,
|
|
"mean_token_accuracy": 0.15287376195192337,
|
|
"num_tokens": 17089675.0,
|
|
"step": 8735
|
|
},
|
|
{
|
|
"entropy": 6.220649480819702,
|
|
"epoch": 0.8736942070275404,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004932530749138775,
|
|
"loss": 6.0656,
|
|
"mean_token_accuracy": 0.1565648451447487,
|
|
"num_tokens": 17099234.0,
|
|
"step": 8740
|
|
},
|
|
{
|
|
"entropy": 6.265024137496948,
|
|
"epoch": 0.8741940320887689,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004932443979186028,
|
|
"loss": 6.1024,
|
|
"mean_token_accuracy": 0.14622531980276107,
|
|
"num_tokens": 17108966.0,
|
|
"step": 8745
|
|
},
|
|
{
|
|
"entropy": 6.226924848556519,
|
|
"epoch": 0.8746938571499975,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004932357154323552,
|
|
"loss": 6.1551,
|
|
"mean_token_accuracy": 0.1478735774755478,
|
|
"num_tokens": 17117941.0,
|
|
"step": 8750
|
|
},
|
|
{
|
|
"entropy": 6.210325908660889,
|
|
"epoch": 0.8751936822112261,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004932270274553531,
|
|
"loss": 6.0586,
|
|
"mean_token_accuracy": 0.15065574496984482,
|
|
"num_tokens": 17127561.0,
|
|
"step": 8755
|
|
},
|
|
{
|
|
"entropy": 6.23476209640503,
|
|
"epoch": 0.8756935072724547,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004932183339878153,
|
|
"loss": 6.1267,
|
|
"mean_token_accuracy": 0.14655791670084,
|
|
"num_tokens": 17137645.0,
|
|
"step": 8760
|
|
},
|
|
{
|
|
"entropy": 6.286288213729859,
|
|
"epoch": 0.8761933323336832,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004932096350299602,
|
|
"loss": 6.1751,
|
|
"mean_token_accuracy": 0.14319735318422316,
|
|
"num_tokens": 17146955.0,
|
|
"step": 8765
|
|
},
|
|
{
|
|
"entropy": 6.35867862701416,
|
|
"epoch": 0.8766931573949118,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004932009305820069,
|
|
"loss": 6.1974,
|
|
"mean_token_accuracy": 0.13611237928271294,
|
|
"num_tokens": 17158287.0,
|
|
"step": 8770
|
|
},
|
|
{
|
|
"entropy": 6.406553649902344,
|
|
"epoch": 0.8771929824561403,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004931922206441743,
|
|
"loss": 6.1839,
|
|
"mean_token_accuracy": 0.13917835652828217,
|
|
"num_tokens": 17168646.0,
|
|
"step": 8775
|
|
},
|
|
{
|
|
"entropy": 6.299132919311523,
|
|
"epoch": 0.8776928075173689,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004931835052166817,
|
|
"loss": 6.1734,
|
|
"mean_token_accuracy": 0.1393842414021492,
|
|
"num_tokens": 17178533.0,
|
|
"step": 8780
|
|
},
|
|
{
|
|
"entropy": 6.2566431045532225,
|
|
"epoch": 0.8781926325785975,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004931747842997481,
|
|
"loss": 6.1973,
|
|
"mean_token_accuracy": 0.145637845993042,
|
|
"num_tokens": 17189584.0,
|
|
"step": 8785
|
|
},
|
|
{
|
|
"entropy": 6.196907377243042,
|
|
"epoch": 0.8786924576398261,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004931660578935931,
|
|
"loss": 6.0891,
|
|
"mean_token_accuracy": 0.1511687532067299,
|
|
"num_tokens": 17199521.0,
|
|
"step": 8790
|
|
},
|
|
{
|
|
"entropy": 6.29045090675354,
|
|
"epoch": 0.8791922827010547,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004931573259984363,
|
|
"loss": 6.137,
|
|
"mean_token_accuracy": 0.15247608572244645,
|
|
"num_tokens": 17209812.0,
|
|
"step": 8795
|
|
},
|
|
{
|
|
"entropy": 6.373798274993897,
|
|
"epoch": 0.8796921077622832,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004931485886144972,
|
|
"loss": 6.1929,
|
|
"mean_token_accuracy": 0.14428210705518724,
|
|
"num_tokens": 17220119.0,
|
|
"step": 8800
|
|
},
|
|
{
|
|
"entropy": 6.2596338272094725,
|
|
"epoch": 0.8801919328235118,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004931398457419959,
|
|
"loss": 6.1045,
|
|
"mean_token_accuracy": 0.15475255697965623,
|
|
"num_tokens": 17229777.0,
|
|
"step": 8805
|
|
},
|
|
{
|
|
"entropy": 6.2191637516021725,
|
|
"epoch": 0.8806917578847403,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004931310973811521,
|
|
"loss": 6.0956,
|
|
"mean_token_accuracy": 0.15246562510728837,
|
|
"num_tokens": 17239039.0,
|
|
"step": 8810
|
|
},
|
|
{
|
|
"entropy": 6.198563814163208,
|
|
"epoch": 0.8811915829459689,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000493122343532186,
|
|
"loss": 6.0504,
|
|
"mean_token_accuracy": 0.14824269264936446,
|
|
"num_tokens": 17248202.0,
|
|
"step": 8815
|
|
},
|
|
{
|
|
"entropy": 6.252795553207397,
|
|
"epoch": 0.8816914080071975,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.000493113584195318,
|
|
"loss": 6.1398,
|
|
"mean_token_accuracy": 0.15230997055768966,
|
|
"num_tokens": 17258253.0,
|
|
"step": 8820
|
|
},
|
|
{
|
|
"entropy": 6.24111795425415,
|
|
"epoch": 0.8821912330684261,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004931048193707681,
|
|
"loss": 6.109,
|
|
"mean_token_accuracy": 0.15066774785518647,
|
|
"num_tokens": 17268381.0,
|
|
"step": 8825
|
|
},
|
|
{
|
|
"entropy": 6.338550710678101,
|
|
"epoch": 0.8826910581296546,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004930960490587573,
|
|
"loss": 6.1959,
|
|
"mean_token_accuracy": 0.14700786992907525,
|
|
"num_tokens": 17278220.0,
|
|
"step": 8830
|
|
},
|
|
{
|
|
"entropy": 6.355367136001587,
|
|
"epoch": 0.8831908831908832,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.000493087273259506,
|
|
"loss": 6.2674,
|
|
"mean_token_accuracy": 0.1471392810344696,
|
|
"num_tokens": 17288388.0,
|
|
"step": 8835
|
|
},
|
|
{
|
|
"entropy": 6.366063785552979,
|
|
"epoch": 0.8836907082521117,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004930784919732349,
|
|
"loss": 6.2666,
|
|
"mean_token_accuracy": 0.14705021008849145,
|
|
"num_tokens": 17297308.0,
|
|
"step": 8840
|
|
},
|
|
{
|
|
"entropy": 6.149344253540039,
|
|
"epoch": 0.8841905333133403,
|
|
"grad_norm": 1.90625,
|
|
"learning_rate": 0.0004930697052001651,
|
|
"loss": 6.0487,
|
|
"mean_token_accuracy": 0.1563984841108322,
|
|
"num_tokens": 17307586.0,
|
|
"step": 8845
|
|
},
|
|
{
|
|
"entropy": 6.247825813293457,
|
|
"epoch": 0.8846903583745689,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004930609129405177,
|
|
"loss": 6.1605,
|
|
"mean_token_accuracy": 0.14380409121513366,
|
|
"num_tokens": 17317342.0,
|
|
"step": 8850
|
|
},
|
|
{
|
|
"entropy": 6.260551643371582,
|
|
"epoch": 0.8851901834357975,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004930521151945138,
|
|
"loss": 6.0982,
|
|
"mean_token_accuracy": 0.15146129280328752,
|
|
"num_tokens": 17326586.0,
|
|
"step": 8855
|
|
},
|
|
{
|
|
"entropy": 6.301983737945557,
|
|
"epoch": 0.8856900084970261,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004930433119623749,
|
|
"loss": 6.2406,
|
|
"mean_token_accuracy": 0.13693952932953835,
|
|
"num_tokens": 17337551.0,
|
|
"step": 8860
|
|
},
|
|
{
|
|
"entropy": 6.342548179626465,
|
|
"epoch": 0.8861898335582546,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004930345032443221,
|
|
"loss": 6.1657,
|
|
"mean_token_accuracy": 0.13816626965999604,
|
|
"num_tokens": 17346702.0,
|
|
"step": 8865
|
|
},
|
|
{
|
|
"entropy": 6.235070276260376,
|
|
"epoch": 0.8866896586194832,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004930256890405777,
|
|
"loss": 6.1318,
|
|
"mean_token_accuracy": 0.15403689593076705,
|
|
"num_tokens": 17356595.0,
|
|
"step": 8870
|
|
},
|
|
{
|
|
"entropy": 6.319204950332642,
|
|
"epoch": 0.8871894836807117,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004930168693513627,
|
|
"loss": 6.1846,
|
|
"mean_token_accuracy": 0.149034284055233,
|
|
"num_tokens": 17366264.0,
|
|
"step": 8875
|
|
},
|
|
{
|
|
"entropy": 6.317347145080566,
|
|
"epoch": 0.8876893087419403,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004930080441768995,
|
|
"loss": 6.184,
|
|
"mean_token_accuracy": 0.14377377703785896,
|
|
"num_tokens": 17376324.0,
|
|
"step": 8880
|
|
},
|
|
{
|
|
"entropy": 6.286531019210815,
|
|
"epoch": 0.8881891338031689,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00049299921351741,
|
|
"loss": 6.1255,
|
|
"mean_token_accuracy": 0.14417110681533812,
|
|
"num_tokens": 17386436.0,
|
|
"step": 8885
|
|
},
|
|
{
|
|
"entropy": 6.24146785736084,
|
|
"epoch": 0.8886889588643975,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004929903773731164,
|
|
"loss": 6.1036,
|
|
"mean_token_accuracy": 0.15214107781648636,
|
|
"num_tokens": 17395511.0,
|
|
"step": 8890
|
|
},
|
|
{
|
|
"entropy": 6.212081861495972,
|
|
"epoch": 0.8891887839256261,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004929815357442409,
|
|
"loss": 6.1006,
|
|
"mean_token_accuracy": 0.15339987799525262,
|
|
"num_tokens": 17404887.0,
|
|
"step": 8895
|
|
},
|
|
{
|
|
"entropy": 6.261399555206299,
|
|
"epoch": 0.8896886089868546,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004929726886310062,
|
|
"loss": 6.0859,
|
|
"mean_token_accuracy": 0.14992300420999527,
|
|
"num_tokens": 17413936.0,
|
|
"step": 8900
|
|
},
|
|
{
|
|
"entropy": 6.2568460464477536,
|
|
"epoch": 0.8901884340480831,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004929638360336348,
|
|
"loss": 6.1673,
|
|
"mean_token_accuracy": 0.14320943355560303,
|
|
"num_tokens": 17425011.0,
|
|
"step": 8905
|
|
},
|
|
{
|
|
"entropy": 6.276605701446533,
|
|
"epoch": 0.8906882591093117,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004929549779523492,
|
|
"loss": 6.109,
|
|
"mean_token_accuracy": 0.14854919016361237,
|
|
"num_tokens": 17434508.0,
|
|
"step": 8910
|
|
},
|
|
{
|
|
"entropy": 6.292928075790405,
|
|
"epoch": 0.8911880841705403,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004929461143873725,
|
|
"loss": 6.128,
|
|
"mean_token_accuracy": 0.1482929363846779,
|
|
"num_tokens": 17444155.0,
|
|
"step": 8915
|
|
},
|
|
{
|
|
"entropy": 6.3267906665802,
|
|
"epoch": 0.8916879092317689,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004929372453389277,
|
|
"loss": 6.2345,
|
|
"mean_token_accuracy": 0.13820834085345268,
|
|
"num_tokens": 17453834.0,
|
|
"step": 8920
|
|
},
|
|
{
|
|
"entropy": 6.204963541030883,
|
|
"epoch": 0.8921877342929975,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004929283708072378,
|
|
"loss": 6.0846,
|
|
"mean_token_accuracy": 0.15507842898368834,
|
|
"num_tokens": 17463491.0,
|
|
"step": 8925
|
|
},
|
|
{
|
|
"entropy": 6.149940347671508,
|
|
"epoch": 0.8926875593542261,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004929194907925262,
|
|
"loss": 6.0434,
|
|
"mean_token_accuracy": 0.15164035111665725,
|
|
"num_tokens": 17472882.0,
|
|
"step": 8930
|
|
},
|
|
{
|
|
"entropy": 6.264197540283203,
|
|
"epoch": 0.8931873844154546,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004929106052950163,
|
|
"loss": 6.1573,
|
|
"mean_token_accuracy": 0.1497704066336155,
|
|
"num_tokens": 17483318.0,
|
|
"step": 8935
|
|
},
|
|
{
|
|
"entropy": 6.20780839920044,
|
|
"epoch": 0.8936872094766831,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004929017143149317,
|
|
"loss": 6.0778,
|
|
"mean_token_accuracy": 0.15200841426849365,
|
|
"num_tokens": 17493212.0,
|
|
"step": 8940
|
|
},
|
|
{
|
|
"entropy": 6.2409679889678955,
|
|
"epoch": 0.8941870345379117,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.000492892817852496,
|
|
"loss": 6.08,
|
|
"mean_token_accuracy": 0.14508683681488038,
|
|
"num_tokens": 17502782.0,
|
|
"step": 8945
|
|
},
|
|
{
|
|
"entropy": 6.2060588836669925,
|
|
"epoch": 0.8946868595991403,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.000492883915907933,
|
|
"loss": 6.2528,
|
|
"mean_token_accuracy": 0.1420326016843319,
|
|
"num_tokens": 17514321.0,
|
|
"step": 8950
|
|
},
|
|
{
|
|
"entropy": 6.278987550735474,
|
|
"epoch": 0.8951866846603689,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004928750084814668,
|
|
"loss": 6.0974,
|
|
"mean_token_accuracy": 0.15245210826396943,
|
|
"num_tokens": 17522910.0,
|
|
"step": 8955
|
|
},
|
|
{
|
|
"entropy": 6.29258918762207,
|
|
"epoch": 0.8956865097215975,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004928660955733214,
|
|
"loss": 6.133,
|
|
"mean_token_accuracy": 0.1421135902404785,
|
|
"num_tokens": 17532747.0,
|
|
"step": 8960
|
|
},
|
|
{
|
|
"entropy": 6.244504737854004,
|
|
"epoch": 0.896186334782826,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004928571771837211,
|
|
"loss": 6.1204,
|
|
"mean_token_accuracy": 0.14728728979825972,
|
|
"num_tokens": 17542956.0,
|
|
"step": 8965
|
|
},
|
|
{
|
|
"entropy": 6.259652090072632,
|
|
"epoch": 0.8966861598440545,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004928482533128902,
|
|
"loss": 6.2129,
|
|
"mean_token_accuracy": 0.14703244119882583,
|
|
"num_tokens": 17552462.0,
|
|
"step": 8970
|
|
},
|
|
{
|
|
"entropy": 6.317249488830567,
|
|
"epoch": 0.8971859849052831,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004928393239610535,
|
|
"loss": 6.144,
|
|
"mean_token_accuracy": 0.14515073150396346,
|
|
"num_tokens": 17561413.0,
|
|
"step": 8975
|
|
},
|
|
{
|
|
"entropy": 6.286448812484741,
|
|
"epoch": 0.8976858099665117,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004928303891284354,
|
|
"loss": 6.1159,
|
|
"mean_token_accuracy": 0.15042459070682526,
|
|
"num_tokens": 17571157.0,
|
|
"step": 8980
|
|
},
|
|
{
|
|
"entropy": 6.341135454177857,
|
|
"epoch": 0.8981856350277403,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004928214488152607,
|
|
"loss": 6.1778,
|
|
"mean_token_accuracy": 0.14475326165556907,
|
|
"num_tokens": 17581645.0,
|
|
"step": 8985
|
|
},
|
|
{
|
|
"entropy": 6.242169046401978,
|
|
"epoch": 0.8986854600889689,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004928125030217545,
|
|
"loss": 6.1383,
|
|
"mean_token_accuracy": 0.15014248639345168,
|
|
"num_tokens": 17591990.0,
|
|
"step": 8990
|
|
},
|
|
{
|
|
"entropy": 6.308021068572998,
|
|
"epoch": 0.8991852851501975,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004928035517481416,
|
|
"loss": 6.1545,
|
|
"mean_token_accuracy": 0.15807769894599916,
|
|
"num_tokens": 17602063.0,
|
|
"step": 8995
|
|
},
|
|
{
|
|
"entropy": 6.250316143035889,
|
|
"epoch": 0.899685110211426,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004927945949946476,
|
|
"loss": 6.1708,
|
|
"mean_token_accuracy": 0.14406087920069693,
|
|
"num_tokens": 17612258.0,
|
|
"step": 9000
|
|
},
|
|
{
|
|
"epoch": 0.899685110211426,
|
|
"eval_entropy": 6.139723458814731,
|
|
"eval_loss": 6.176752090454102,
|
|
"eval_mean_token_accuracy": 0.15213278615816034,
|
|
"eval_num_tokens": 17612258.0,
|
|
"eval_runtime": 23.5839,
|
|
"eval_samples_per_second": 1316.365,
|
|
"eval_steps_per_second": 164.562,
|
|
"step": 9000
|
|
},
|
|
{
|
|
"entropy": 6.2707662105560305,
|
|
"epoch": 0.9001849352726545,
|
|
"grad_norm": 2.390625,
|
|
"learning_rate": 0.0004927856327614975,
|
|
"loss": 6.0846,
|
|
"mean_token_accuracy": 0.15197736918926238,
|
|
"num_tokens": 17621901.0,
|
|
"step": 9005
|
|
},
|
|
{
|
|
"entropy": 6.253821086883545,
|
|
"epoch": 0.9006847603338831,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.000492776665048917,
|
|
"loss": 6.0862,
|
|
"mean_token_accuracy": 0.14120185673236846,
|
|
"num_tokens": 17630854.0,
|
|
"step": 9010
|
|
},
|
|
{
|
|
"entropy": 6.353455495834351,
|
|
"epoch": 0.9011845853951117,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004927676918571316,
|
|
"loss": 6.2257,
|
|
"mean_token_accuracy": 0.1396675944328308,
|
|
"num_tokens": 17640758.0,
|
|
"step": 9015
|
|
},
|
|
{
|
|
"entropy": 6.273074388504028,
|
|
"epoch": 0.9016844104563403,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004927587131863671,
|
|
"loss": 6.0932,
|
|
"mean_token_accuracy": 0.15239740163087845,
|
|
"num_tokens": 17650171.0,
|
|
"step": 9020
|
|
},
|
|
{
|
|
"entropy": 6.249118423461914,
|
|
"epoch": 0.9021842355175689,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004927497290368493,
|
|
"loss": 6.2324,
|
|
"mean_token_accuracy": 0.1458345539867878,
|
|
"num_tokens": 17660403.0,
|
|
"step": 9025
|
|
},
|
|
{
|
|
"entropy": 6.338074636459351,
|
|
"epoch": 0.9026840605787975,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004927407394088046,
|
|
"loss": 6.2377,
|
|
"mean_token_accuracy": 0.14179567918181418,
|
|
"num_tokens": 17670764.0,
|
|
"step": 9030
|
|
},
|
|
{
|
|
"entropy": 6.211802864074707,
|
|
"epoch": 0.9031838856400259,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004927317443024587,
|
|
"loss": 6.1339,
|
|
"mean_token_accuracy": 0.14813459068536758,
|
|
"num_tokens": 17679804.0,
|
|
"step": 9035
|
|
},
|
|
{
|
|
"entropy": 6.350583171844482,
|
|
"epoch": 0.9036837107012545,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004927227437180382,
|
|
"loss": 6.1886,
|
|
"mean_token_accuracy": 0.14003006517887115,
|
|
"num_tokens": 17689819.0,
|
|
"step": 9040
|
|
},
|
|
{
|
|
"entropy": 6.320320272445679,
|
|
"epoch": 0.9041835357624831,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.0004927137376557696,
|
|
"loss": 6.2241,
|
|
"mean_token_accuracy": 0.14652050137519837,
|
|
"num_tokens": 17699716.0,
|
|
"step": 9045
|
|
},
|
|
{
|
|
"entropy": 6.284196043014527,
|
|
"epoch": 0.9046833608237117,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004927047261158793,
|
|
"loss": 6.0889,
|
|
"mean_token_accuracy": 0.1529783457517624,
|
|
"num_tokens": 17709988.0,
|
|
"step": 9050
|
|
},
|
|
{
|
|
"entropy": 6.215233230590821,
|
|
"epoch": 0.9051831858849403,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004926957090985942,
|
|
"loss": 6.0651,
|
|
"mean_token_accuracy": 0.1509389117360115,
|
|
"num_tokens": 17719821.0,
|
|
"step": 9055
|
|
},
|
|
{
|
|
"entropy": 6.356567287445069,
|
|
"epoch": 0.9056830109461689,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004926866866041409,
|
|
"loss": 6.2254,
|
|
"mean_token_accuracy": 0.13990216851234435,
|
|
"num_tokens": 17728813.0,
|
|
"step": 9060
|
|
},
|
|
{
|
|
"entropy": 6.25905179977417,
|
|
"epoch": 0.9061828360073975,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004926776586327467,
|
|
"loss": 6.1044,
|
|
"mean_token_accuracy": 0.14727877229452133,
|
|
"num_tokens": 17738906.0,
|
|
"step": 9065
|
|
},
|
|
{
|
|
"entropy": 6.2407087802886965,
|
|
"epoch": 0.9066826610686259,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004926686251846386,
|
|
"loss": 6.0907,
|
|
"mean_token_accuracy": 0.15298380106687545,
|
|
"num_tokens": 17748869.0,
|
|
"step": 9070
|
|
},
|
|
{
|
|
"entropy": 6.310334300994873,
|
|
"epoch": 0.9071824861298545,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004926595862600439,
|
|
"loss": 6.2291,
|
|
"mean_token_accuracy": 0.14141777753829957,
|
|
"num_tokens": 17758772.0,
|
|
"step": 9075
|
|
},
|
|
{
|
|
"entropy": 6.275823593139648,
|
|
"epoch": 0.9076823111910831,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004926505418591901,
|
|
"loss": 6.2106,
|
|
"mean_token_accuracy": 0.14034887477755548,
|
|
"num_tokens": 17768575.0,
|
|
"step": 9080
|
|
},
|
|
{
|
|
"entropy": 6.290746831893921,
|
|
"epoch": 0.9081821362523117,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004926414919823045,
|
|
"loss": 6.2528,
|
|
"mean_token_accuracy": 0.13516096472740174,
|
|
"num_tokens": 17777445.0,
|
|
"step": 9085
|
|
},
|
|
{
|
|
"entropy": 6.245418357849121,
|
|
"epoch": 0.9086819613135403,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004926324366296151,
|
|
"loss": 6.0626,
|
|
"mean_token_accuracy": 0.1501642346382141,
|
|
"num_tokens": 17787995.0,
|
|
"step": 9090
|
|
},
|
|
{
|
|
"entropy": 6.252548456192017,
|
|
"epoch": 0.9091817863747689,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004926233758013494,
|
|
"loss": 6.0509,
|
|
"mean_token_accuracy": 0.15676427111029625,
|
|
"num_tokens": 17797899.0,
|
|
"step": 9095
|
|
},
|
|
{
|
|
"entropy": 6.309170579910278,
|
|
"epoch": 0.9096816114359974,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004926143094977359,
|
|
"loss": 6.1063,
|
|
"mean_token_accuracy": 0.14765240550041198,
|
|
"num_tokens": 17807640.0,
|
|
"step": 9100
|
|
},
|
|
{
|
|
"entropy": 6.227313899993897,
|
|
"epoch": 0.9101814364972259,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004926052377190022,
|
|
"loss": 6.126,
|
|
"mean_token_accuracy": 0.14825500398874283,
|
|
"num_tokens": 17817997.0,
|
|
"step": 9105
|
|
},
|
|
{
|
|
"entropy": 6.280065679550171,
|
|
"epoch": 0.9106812615584545,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004925961604653765,
|
|
"loss": 6.1605,
|
|
"mean_token_accuracy": 0.1422814592719078,
|
|
"num_tokens": 17828145.0,
|
|
"step": 9110
|
|
},
|
|
{
|
|
"entropy": 6.333649015426635,
|
|
"epoch": 0.9111810866196831,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004925870777370877,
|
|
"loss": 6.061,
|
|
"mean_token_accuracy": 0.15739258974790574,
|
|
"num_tokens": 17837403.0,
|
|
"step": 9115
|
|
},
|
|
{
|
|
"entropy": 6.26377911567688,
|
|
"epoch": 0.9116809116809117,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004925779895343639,
|
|
"loss": 6.1299,
|
|
"mean_token_accuracy": 0.15004582032561303,
|
|
"num_tokens": 17846745.0,
|
|
"step": 9120
|
|
},
|
|
{
|
|
"entropy": 6.284781503677368,
|
|
"epoch": 0.9121807367421403,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004925688958574339,
|
|
"loss": 6.1596,
|
|
"mean_token_accuracy": 0.14793580621480942,
|
|
"num_tokens": 17857422.0,
|
|
"step": 9125
|
|
},
|
|
{
|
|
"entropy": 6.243457460403443,
|
|
"epoch": 0.9126805618033689,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004925597967065264,
|
|
"loss": 6.0508,
|
|
"mean_token_accuracy": 0.15382441878318787,
|
|
"num_tokens": 17867004.0,
|
|
"step": 9130
|
|
},
|
|
{
|
|
"entropy": 6.3056535720825195,
|
|
"epoch": 0.9131803868645973,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004925506920818705,
|
|
"loss": 6.1942,
|
|
"mean_token_accuracy": 0.14008287340402603,
|
|
"num_tokens": 17876933.0,
|
|
"step": 9135
|
|
},
|
|
{
|
|
"entropy": 6.278475189208985,
|
|
"epoch": 0.9136802119258259,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004925415819836951,
|
|
"loss": 6.147,
|
|
"mean_token_accuracy": 0.14869310557842255,
|
|
"num_tokens": 17887639.0,
|
|
"step": 9140
|
|
},
|
|
{
|
|
"entropy": 6.264593410491943,
|
|
"epoch": 0.9141800369870545,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004925324664122294,
|
|
"loss": 6.0287,
|
|
"mean_token_accuracy": 0.16113806515932083,
|
|
"num_tokens": 17897125.0,
|
|
"step": 9145
|
|
},
|
|
{
|
|
"entropy": 6.203950595855713,
|
|
"epoch": 0.9146798620482831,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004925233453677029,
|
|
"loss": 6.1733,
|
|
"mean_token_accuracy": 0.1448161281645298,
|
|
"num_tokens": 17907580.0,
|
|
"step": 9150
|
|
},
|
|
{
|
|
"entropy": 6.204181718826294,
|
|
"epoch": 0.9151796871095117,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004925142188503451,
|
|
"loss": 6.0453,
|
|
"mean_token_accuracy": 0.16035950779914857,
|
|
"num_tokens": 17915937.0,
|
|
"step": 9155
|
|
},
|
|
{
|
|
"entropy": 6.19406476020813,
|
|
"epoch": 0.9156795121707403,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004925050868603854,
|
|
"loss": 6.0208,
|
|
"mean_token_accuracy": 0.15496256798505784,
|
|
"num_tokens": 17926337.0,
|
|
"step": 9160
|
|
},
|
|
{
|
|
"entropy": 6.271029281616211,
|
|
"epoch": 0.9161793372319688,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004924959493980537,
|
|
"loss": 6.2103,
|
|
"mean_token_accuracy": 0.13686318099498748,
|
|
"num_tokens": 17936123.0,
|
|
"step": 9165
|
|
},
|
|
{
|
|
"entropy": 6.252589225769043,
|
|
"epoch": 0.9166791622931973,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004924868064635798,
|
|
"loss": 6.0696,
|
|
"mean_token_accuracy": 0.15073217675089837,
|
|
"num_tokens": 17946143.0,
|
|
"step": 9170
|
|
},
|
|
{
|
|
"entropy": 6.3810343742370605,
|
|
"epoch": 0.9171789873544259,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.000492477658057194,
|
|
"loss": 6.2246,
|
|
"mean_token_accuracy": 0.14059614315629004,
|
|
"num_tokens": 17956034.0,
|
|
"step": 9175
|
|
},
|
|
{
|
|
"entropy": 6.257679653167725,
|
|
"epoch": 0.9176788124156545,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004924685041791262,
|
|
"loss": 6.0979,
|
|
"mean_token_accuracy": 0.1443646177649498,
|
|
"num_tokens": 17965455.0,
|
|
"step": 9180
|
|
},
|
|
{
|
|
"entropy": 6.234354829788208,
|
|
"epoch": 0.9181786374768831,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004924593448296068,
|
|
"loss": 6.126,
|
|
"mean_token_accuracy": 0.1433185011148453,
|
|
"num_tokens": 17974506.0,
|
|
"step": 9185
|
|
},
|
|
{
|
|
"entropy": 6.228525876998901,
|
|
"epoch": 0.9186784625381117,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004924501800088662,
|
|
"loss": 6.1433,
|
|
"mean_token_accuracy": 0.14215124770998955,
|
|
"num_tokens": 17984750.0,
|
|
"step": 9190
|
|
},
|
|
{
|
|
"entropy": 6.241401338577271,
|
|
"epoch": 0.9191782875993403,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004924410097171351,
|
|
"loss": 6.1377,
|
|
"mean_token_accuracy": 0.15220036059617997,
|
|
"num_tokens": 17993871.0,
|
|
"step": 9195
|
|
},
|
|
{
|
|
"entropy": 6.244402694702148,
|
|
"epoch": 0.9196781126605688,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.000492431833954644,
|
|
"loss": 6.1068,
|
|
"mean_token_accuracy": 0.1497140794992447,
|
|
"num_tokens": 18003686.0,
|
|
"step": 9200
|
|
},
|
|
{
|
|
"entropy": 6.2604717254638675,
|
|
"epoch": 0.9201779377217973,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004924226527216241,
|
|
"loss": 6.1346,
|
|
"mean_token_accuracy": 0.15008196532726287,
|
|
"num_tokens": 18013024.0,
|
|
"step": 9205
|
|
},
|
|
{
|
|
"entropy": 6.263730907440186,
|
|
"epoch": 0.9206777627830259,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004924134660183061,
|
|
"loss": 6.099,
|
|
"mean_token_accuracy": 0.14889158681035042,
|
|
"num_tokens": 18022718.0,
|
|
"step": 9210
|
|
},
|
|
{
|
|
"entropy": 6.1407952308654785,
|
|
"epoch": 0.9211775878442545,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004924042738449212,
|
|
"loss": 5.9555,
|
|
"mean_token_accuracy": 0.1525575503706932,
|
|
"num_tokens": 18032185.0,
|
|
"step": 9215
|
|
},
|
|
{
|
|
"entropy": 6.300953340530396,
|
|
"epoch": 0.9216774129054831,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004923950762017008,
|
|
"loss": 6.153,
|
|
"mean_token_accuracy": 0.15161130726337432,
|
|
"num_tokens": 18041864.0,
|
|
"step": 9220
|
|
},
|
|
{
|
|
"entropy": 6.154758739471435,
|
|
"epoch": 0.9221772379667117,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004923858730888762,
|
|
"loss": 5.9918,
|
|
"mean_token_accuracy": 0.16416605710983276,
|
|
"num_tokens": 18050797.0,
|
|
"step": 9225
|
|
},
|
|
{
|
|
"entropy": 6.179091119766236,
|
|
"epoch": 0.9226770630279402,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000492376664506679,
|
|
"loss": 6.0166,
|
|
"mean_token_accuracy": 0.15271463394165039,
|
|
"num_tokens": 18060414.0,
|
|
"step": 9230
|
|
},
|
|
{
|
|
"entropy": 6.22623610496521,
|
|
"epoch": 0.9231768880891688,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004923674504553408,
|
|
"loss": 6.1484,
|
|
"mean_token_accuracy": 0.14723171293735504,
|
|
"num_tokens": 18070832.0,
|
|
"step": 9235
|
|
},
|
|
{
|
|
"entropy": 6.272461795806885,
|
|
"epoch": 0.9236767131503973,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004923582309350935,
|
|
"loss": 6.0973,
|
|
"mean_token_accuracy": 0.1501172050833702,
|
|
"num_tokens": 18078918.0,
|
|
"step": 9240
|
|
},
|
|
{
|
|
"entropy": 6.294412660598755,
|
|
"epoch": 0.9241765382116259,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.000492349005946169,
|
|
"loss": 6.154,
|
|
"mean_token_accuracy": 0.15143943578004837,
|
|
"num_tokens": 18087896.0,
|
|
"step": 9245
|
|
},
|
|
{
|
|
"entropy": 6.333119869232178,
|
|
"epoch": 0.9246763632728545,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004923397754887994,
|
|
"loss": 6.2102,
|
|
"mean_token_accuracy": 0.1431832417845726,
|
|
"num_tokens": 18097535.0,
|
|
"step": 9250
|
|
},
|
|
{
|
|
"entropy": 6.176212930679322,
|
|
"epoch": 0.9251761883340831,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004923305395632172,
|
|
"loss": 6.0806,
|
|
"mean_token_accuracy": 0.1512439213693142,
|
|
"num_tokens": 18107503.0,
|
|
"step": 9255
|
|
},
|
|
{
|
|
"entropy": 6.24899845123291,
|
|
"epoch": 0.9256760133953117,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004923212981696543,
|
|
"loss": 6.0854,
|
|
"mean_token_accuracy": 0.14923255667090415,
|
|
"num_tokens": 18117188.0,
|
|
"step": 9260
|
|
},
|
|
{
|
|
"entropy": 6.343647813796997,
|
|
"epoch": 0.9261758384565402,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004923120513083436,
|
|
"loss": 6.2589,
|
|
"mean_token_accuracy": 0.1378469757735729,
|
|
"num_tokens": 18127965.0,
|
|
"step": 9265
|
|
},
|
|
{
|
|
"entropy": 6.249783658981324,
|
|
"epoch": 0.9266756635177688,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004923027989795175,
|
|
"loss": 6.1178,
|
|
"mean_token_accuracy": 0.1457314074039459,
|
|
"num_tokens": 18136861.0,
|
|
"step": 9270
|
|
},
|
|
{
|
|
"entropy": 6.21954026222229,
|
|
"epoch": 0.9271754885789973,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.000492293541183409,
|
|
"loss": 6.0943,
|
|
"mean_token_accuracy": 0.14869869351387024,
|
|
"num_tokens": 18145702.0,
|
|
"step": 9275
|
|
},
|
|
{
|
|
"entropy": 6.291553354263305,
|
|
"epoch": 0.9276753136402259,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004922842779202509,
|
|
"loss": 6.1743,
|
|
"mean_token_accuracy": 0.14882912039756774,
|
|
"num_tokens": 18155177.0,
|
|
"step": 9280
|
|
},
|
|
{
|
|
"entropy": 6.2452467918396,
|
|
"epoch": 0.9281751387014545,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004922750091902763,
|
|
"loss": 6.051,
|
|
"mean_token_accuracy": 0.15065366998314858,
|
|
"num_tokens": 18165361.0,
|
|
"step": 9285
|
|
},
|
|
{
|
|
"entropy": 6.2458032131195065,
|
|
"epoch": 0.9286749637626831,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004922657349937183,
|
|
"loss": 6.1009,
|
|
"mean_token_accuracy": 0.14763772413134574,
|
|
"num_tokens": 18175300.0,
|
|
"step": 9290
|
|
},
|
|
{
|
|
"entropy": 6.337135219573975,
|
|
"epoch": 0.9291747888239116,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004922564553308103,
|
|
"loss": 6.0998,
|
|
"mean_token_accuracy": 0.15319805443286896,
|
|
"num_tokens": 18183985.0,
|
|
"step": 9295
|
|
},
|
|
{
|
|
"entropy": 6.3126795291900635,
|
|
"epoch": 0.9296746138851402,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.000492247170201786,
|
|
"loss": 6.2181,
|
|
"mean_token_accuracy": 0.1427415542304516,
|
|
"num_tokens": 18193251.0,
|
|
"step": 9300
|
|
},
|
|
{
|
|
"entropy": 6.283484363555909,
|
|
"epoch": 0.9301744389463688,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004922378796068785,
|
|
"loss": 6.0612,
|
|
"mean_token_accuracy": 0.1548401892185211,
|
|
"num_tokens": 18202081.0,
|
|
"step": 9305
|
|
},
|
|
{
|
|
"entropy": 6.229377031326294,
|
|
"epoch": 0.9306742640075973,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.000492228583546322,
|
|
"loss": 6.0642,
|
|
"mean_token_accuracy": 0.14648374244570733,
|
|
"num_tokens": 18211499.0,
|
|
"step": 9310
|
|
},
|
|
{
|
|
"entropy": 6.197189092636108,
|
|
"epoch": 0.9311740890688259,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004922192820203502,
|
|
"loss": 6.0649,
|
|
"mean_token_accuracy": 0.15283203125,
|
|
"num_tokens": 18220764.0,
|
|
"step": 9315
|
|
},
|
|
{
|
|
"entropy": 6.174600744247437,
|
|
"epoch": 0.9316739141300545,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004922099750291972,
|
|
"loss": 6.0707,
|
|
"mean_token_accuracy": 0.15849846601486206,
|
|
"num_tokens": 18230126.0,
|
|
"step": 9320
|
|
},
|
|
{
|
|
"entropy": 6.16498441696167,
|
|
"epoch": 0.9321737391912831,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004922006625730971,
|
|
"loss": 6.07,
|
|
"mean_token_accuracy": 0.15209577828645707,
|
|
"num_tokens": 18238426.0,
|
|
"step": 9325
|
|
},
|
|
{
|
|
"entropy": 6.267601490020752,
|
|
"epoch": 0.9326735642525116,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004921913446522843,
|
|
"loss": 6.1628,
|
|
"mean_token_accuracy": 0.14164744094014167,
|
|
"num_tokens": 18248215.0,
|
|
"step": 9330
|
|
},
|
|
{
|
|
"entropy": 6.257072877883911,
|
|
"epoch": 0.9331733893137402,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.000492182021266993,
|
|
"loss": 6.1171,
|
|
"mean_token_accuracy": 0.14654496014118196,
|
|
"num_tokens": 18258967.0,
|
|
"step": 9335
|
|
},
|
|
{
|
|
"entropy": 6.314351749420166,
|
|
"epoch": 0.9336732143749688,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.000492172692417458,
|
|
"loss": 6.1712,
|
|
"mean_token_accuracy": 0.14318839460611343,
|
|
"num_tokens": 18268901.0,
|
|
"step": 9340
|
|
},
|
|
{
|
|
"entropy": 6.377855396270752,
|
|
"epoch": 0.9341730394361973,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.000492163358103914,
|
|
"loss": 6.1883,
|
|
"mean_token_accuracy": 0.14365150183439254,
|
|
"num_tokens": 18279615.0,
|
|
"step": 9345
|
|
},
|
|
{
|
|
"entropy": 6.18309850692749,
|
|
"epoch": 0.9346728644974259,
|
|
"grad_norm": 1.84375,
|
|
"learning_rate": 0.0004921540183265957,
|
|
"loss": 6.0974,
|
|
"mean_token_accuracy": 0.15152767300605774,
|
|
"num_tokens": 18289630.0,
|
|
"step": 9350
|
|
},
|
|
{
|
|
"entropy": 6.195323753356933,
|
|
"epoch": 0.9351726895586545,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004921446730857383,
|
|
"loss": 6.146,
|
|
"mean_token_accuracy": 0.1466882348060608,
|
|
"num_tokens": 18299764.0,
|
|
"step": 9355
|
|
},
|
|
{
|
|
"entropy": 6.234064388275146,
|
|
"epoch": 0.935672514619883,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004921353223815767,
|
|
"loss": 6.0384,
|
|
"mean_token_accuracy": 0.1607164114713669,
|
|
"num_tokens": 18310252.0,
|
|
"step": 9360
|
|
},
|
|
{
|
|
"entropy": 6.3009199619293215,
|
|
"epoch": 0.9361723396811116,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004921259662143463,
|
|
"loss": 6.1126,
|
|
"mean_token_accuracy": 0.15220096856355667,
|
|
"num_tokens": 18319753.0,
|
|
"step": 9365
|
|
},
|
|
{
|
|
"entropy": 6.259305334091186,
|
|
"epoch": 0.9366721647423402,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004921166045842825,
|
|
"loss": 6.1351,
|
|
"mean_token_accuracy": 0.14800689816474916,
|
|
"num_tokens": 18330307.0,
|
|
"step": 9370
|
|
},
|
|
{
|
|
"entropy": 6.269847869873047,
|
|
"epoch": 0.9371719898035688,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004921072374916208,
|
|
"loss": 6.1744,
|
|
"mean_token_accuracy": 0.14757596403360368,
|
|
"num_tokens": 18340867.0,
|
|
"step": 9375
|
|
},
|
|
{
|
|
"entropy": 6.221883916854859,
|
|
"epoch": 0.9376718148647973,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004920978649365968,
|
|
"loss": 6.0099,
|
|
"mean_token_accuracy": 0.16141703575849534,
|
|
"num_tokens": 18350852.0,
|
|
"step": 9380
|
|
},
|
|
{
|
|
"entropy": 6.1437976360321045,
|
|
"epoch": 0.9381716399260259,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004920884869194463,
|
|
"loss": 6.017,
|
|
"mean_token_accuracy": 0.1564452603459358,
|
|
"num_tokens": 18361821.0,
|
|
"step": 9385
|
|
},
|
|
{
|
|
"entropy": 6.2910590171813965,
|
|
"epoch": 0.9386714649872545,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004920791034404054,
|
|
"loss": 6.1575,
|
|
"mean_token_accuracy": 0.1417326919734478,
|
|
"num_tokens": 18371391.0,
|
|
"step": 9390
|
|
},
|
|
{
|
|
"entropy": 6.321835088729858,
|
|
"epoch": 0.939171290048483,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004920697144997102,
|
|
"loss": 6.1515,
|
|
"mean_token_accuracy": 0.14812880083918573,
|
|
"num_tokens": 18380661.0,
|
|
"step": 9395
|
|
},
|
|
{
|
|
"entropy": 6.218744850158691,
|
|
"epoch": 0.9396711151097116,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004920603200975968,
|
|
"loss": 6.0963,
|
|
"mean_token_accuracy": 0.15220969915390015,
|
|
"num_tokens": 18390365.0,
|
|
"step": 9400
|
|
},
|
|
{
|
|
"entropy": 6.159506130218506,
|
|
"epoch": 0.9401709401709402,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004920509202343016,
|
|
"loss": 6.0546,
|
|
"mean_token_accuracy": 0.15513156801462175,
|
|
"num_tokens": 18399536.0,
|
|
"step": 9405
|
|
},
|
|
{
|
|
"entropy": 6.252153158187866,
|
|
"epoch": 0.9406707652321687,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.000492041514910061,
|
|
"loss": 6.1117,
|
|
"mean_token_accuracy": 0.15268371999263763,
|
|
"num_tokens": 18408769.0,
|
|
"step": 9410
|
|
},
|
|
{
|
|
"entropy": 6.232716798782349,
|
|
"epoch": 0.9411705902933973,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.0004920321041251118,
|
|
"loss": 6.1341,
|
|
"mean_token_accuracy": 0.14862325713038443,
|
|
"num_tokens": 18418554.0,
|
|
"step": 9415
|
|
},
|
|
{
|
|
"entropy": 6.1887129783630375,
|
|
"epoch": 0.9416704153546259,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004920226878796908,
|
|
"loss": 6.1078,
|
|
"mean_token_accuracy": 0.1459977775812149,
|
|
"num_tokens": 18429670.0,
|
|
"step": 9420
|
|
},
|
|
{
|
|
"entropy": 6.301774692535401,
|
|
"epoch": 0.9421702404158544,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004920132661740348,
|
|
"loss": 6.2093,
|
|
"mean_token_accuracy": 0.14631576389074324,
|
|
"num_tokens": 18438747.0,
|
|
"step": 9425
|
|
},
|
|
{
|
|
"entropy": 6.320364332199096,
|
|
"epoch": 0.942670065477083,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004920038390083808,
|
|
"loss": 6.159,
|
|
"mean_token_accuracy": 0.14723806083202362,
|
|
"num_tokens": 18449350.0,
|
|
"step": 9430
|
|
},
|
|
{
|
|
"entropy": 6.248285722732544,
|
|
"epoch": 0.9431698905383116,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.000491994406382966,
|
|
"loss": 6.0732,
|
|
"mean_token_accuracy": 0.15016899704933168,
|
|
"num_tokens": 18459052.0,
|
|
"step": 9435
|
|
},
|
|
{
|
|
"entropy": 6.2822265625,
|
|
"epoch": 0.9436697155995402,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004919849682980278,
|
|
"loss": 6.1799,
|
|
"mean_token_accuracy": 0.1491839364171028,
|
|
"num_tokens": 18469266.0,
|
|
"step": 9440
|
|
},
|
|
{
|
|
"entropy": 6.316525650024414,
|
|
"epoch": 0.9441695406607687,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004919755247538037,
|
|
"loss": 6.1667,
|
|
"mean_token_accuracy": 0.14303553029894828,
|
|
"num_tokens": 18479381.0,
|
|
"step": 9445
|
|
},
|
|
{
|
|
"entropy": 6.2104589462280275,
|
|
"epoch": 0.9446693657219973,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004919660757505312,
|
|
"loss": 6.017,
|
|
"mean_token_accuracy": 0.15580771639943122,
|
|
"num_tokens": 18488973.0,
|
|
"step": 9450
|
|
},
|
|
{
|
|
"entropy": 6.113431310653686,
|
|
"epoch": 0.9451691907832259,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004919566212884481,
|
|
"loss": 6.0157,
|
|
"mean_token_accuracy": 0.15505917519330978,
|
|
"num_tokens": 18497907.0,
|
|
"step": 9455
|
|
},
|
|
{
|
|
"entropy": 6.197196292877197,
|
|
"epoch": 0.9456690158444544,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004919471613677921,
|
|
"loss": 6.0762,
|
|
"mean_token_accuracy": 0.15334462970495225,
|
|
"num_tokens": 18507628.0,
|
|
"step": 9460
|
|
},
|
|
{
|
|
"entropy": 6.27160120010376,
|
|
"epoch": 0.946168840905683,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004919376959888015,
|
|
"loss": 6.2124,
|
|
"mean_token_accuracy": 0.14611563980579376,
|
|
"num_tokens": 18516346.0,
|
|
"step": 9465
|
|
},
|
|
{
|
|
"entropy": 6.3423604488372805,
|
|
"epoch": 0.9466686659669116,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004919282251517142,
|
|
"loss": 6.0291,
|
|
"mean_token_accuracy": 0.15277713537216187,
|
|
"num_tokens": 18525568.0,
|
|
"step": 9470
|
|
},
|
|
{
|
|
"entropy": 6.232535314559937,
|
|
"epoch": 0.9471684910281402,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004919187488567686,
|
|
"loss": 6.1486,
|
|
"mean_token_accuracy": 0.1497054398059845,
|
|
"num_tokens": 18536715.0,
|
|
"step": 9475
|
|
},
|
|
{
|
|
"entropy": 6.240742635726929,
|
|
"epoch": 0.9476683160893687,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0004919092671042031,
|
|
"loss": 6.1723,
|
|
"mean_token_accuracy": 0.14626911133527756,
|
|
"num_tokens": 18546405.0,
|
|
"step": 9480
|
|
},
|
|
{
|
|
"entropy": 6.326673173904419,
|
|
"epoch": 0.9481681411505973,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004918997798942562,
|
|
"loss": 6.2309,
|
|
"mean_token_accuracy": 0.14294743835926055,
|
|
"num_tokens": 18556721.0,
|
|
"step": 9485
|
|
},
|
|
{
|
|
"entropy": 6.348190832138061,
|
|
"epoch": 0.9486679662118258,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004918902872271668,
|
|
"loss": 6.2329,
|
|
"mean_token_accuracy": 0.14100321829319,
|
|
"num_tokens": 18567875.0,
|
|
"step": 9490
|
|
},
|
|
{
|
|
"entropy": 6.213951063156128,
|
|
"epoch": 0.9491677912730544,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004918807891031734,
|
|
"loss": 6.1294,
|
|
"mean_token_accuracy": 0.14599598199129105,
|
|
"num_tokens": 18578185.0,
|
|
"step": 9495
|
|
},
|
|
{
|
|
"entropy": 6.215129137039185,
|
|
"epoch": 0.949667616334283,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004918712855225154,
|
|
"loss": 6.0844,
|
|
"mean_token_accuracy": 0.14716582745313644,
|
|
"num_tokens": 18587503.0,
|
|
"step": 9500
|
|
},
|
|
{
|
|
"entropy": 6.264170551300049,
|
|
"epoch": 0.9501674413955116,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004918617764854314,
|
|
"loss": 6.1256,
|
|
"mean_token_accuracy": 0.14867414385080338,
|
|
"num_tokens": 18597018.0,
|
|
"step": 9505
|
|
},
|
|
{
|
|
"entropy": 6.31040391921997,
|
|
"epoch": 0.9506672664567402,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.000491852261992161,
|
|
"loss": 6.1152,
|
|
"mean_token_accuracy": 0.1543574959039688,
|
|
"num_tokens": 18606262.0,
|
|
"step": 9510
|
|
},
|
|
{
|
|
"entropy": 6.339242839813233,
|
|
"epoch": 0.9511670915179687,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004918427420429435,
|
|
"loss": 6.1806,
|
|
"mean_token_accuracy": 0.14710851907730102,
|
|
"num_tokens": 18616070.0,
|
|
"step": 9515
|
|
},
|
|
{
|
|
"entropy": 6.186763763427734,
|
|
"epoch": 0.9516669165791973,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004918332166380185,
|
|
"loss": 6.1427,
|
|
"mean_token_accuracy": 0.14604226350784302,
|
|
"num_tokens": 18625882.0,
|
|
"step": 9520
|
|
},
|
|
{
|
|
"entropy": 6.2373744487762455,
|
|
"epoch": 0.9521667416404258,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004918236857776254,
|
|
"loss": 6.2148,
|
|
"mean_token_accuracy": 0.14268339425325394,
|
|
"num_tokens": 18635997.0,
|
|
"step": 9525
|
|
},
|
|
{
|
|
"entropy": 6.240341567993164,
|
|
"epoch": 0.9526665667016544,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004918141494620042,
|
|
"loss": 6.0507,
|
|
"mean_token_accuracy": 0.1521468661725521,
|
|
"num_tokens": 18646234.0,
|
|
"step": 9530
|
|
},
|
|
{
|
|
"entropy": 6.223635721206665,
|
|
"epoch": 0.953166391762883,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004918046076913949,
|
|
"loss": 6.0991,
|
|
"mean_token_accuracy": 0.1467491492629051,
|
|
"num_tokens": 18655407.0,
|
|
"step": 9535
|
|
},
|
|
{
|
|
"entropy": 6.190256214141845,
|
|
"epoch": 0.9536662168241116,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004917950604660374,
|
|
"loss": 6.0453,
|
|
"mean_token_accuracy": 0.16087137907743454,
|
|
"num_tokens": 18664695.0,
|
|
"step": 9540
|
|
},
|
|
{
|
|
"entropy": 6.259846878051758,
|
|
"epoch": 0.9541660418853402,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.000491785507786172,
|
|
"loss": 6.0172,
|
|
"mean_token_accuracy": 0.15543370842933654,
|
|
"num_tokens": 18675170.0,
|
|
"step": 9545
|
|
},
|
|
{
|
|
"entropy": 6.145201396942139,
|
|
"epoch": 0.9546658669465687,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004917759496520388,
|
|
"loss": 5.9989,
|
|
"mean_token_accuracy": 0.15719758570194245,
|
|
"num_tokens": 18684619.0,
|
|
"step": 9550
|
|
},
|
|
{
|
|
"entropy": 6.1628499031066895,
|
|
"epoch": 0.9551656920077972,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004917663860638787,
|
|
"loss": 6.1726,
|
|
"mean_token_accuracy": 0.14980884343385698,
|
|
"num_tokens": 18694133.0,
|
|
"step": 9555
|
|
},
|
|
{
|
|
"entropy": 6.261532545089722,
|
|
"epoch": 0.9556655170690258,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004917568170219321,
|
|
"loss": 6.1228,
|
|
"mean_token_accuracy": 0.14827767312526702,
|
|
"num_tokens": 18705084.0,
|
|
"step": 9560
|
|
},
|
|
{
|
|
"entropy": 6.208607912063599,
|
|
"epoch": 0.9561653421302544,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004917472425264397,
|
|
"loss": 6.0517,
|
|
"mean_token_accuracy": 0.15078692212700845,
|
|
"num_tokens": 18714822.0,
|
|
"step": 9565
|
|
},
|
|
{
|
|
"entropy": 6.269644165039063,
|
|
"epoch": 0.956665167191483,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004917376625776425,
|
|
"loss": 6.1685,
|
|
"mean_token_accuracy": 0.14474971145391463,
|
|
"num_tokens": 18725471.0,
|
|
"step": 9570
|
|
},
|
|
{
|
|
"entropy": 6.276574611663818,
|
|
"epoch": 0.9571649922527116,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004917280771757814,
|
|
"loss": 6.1427,
|
|
"mean_token_accuracy": 0.14567931443452836,
|
|
"num_tokens": 18734884.0,
|
|
"step": 9575
|
|
},
|
|
{
|
|
"entropy": 6.122213411331177,
|
|
"epoch": 0.9576648173139402,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004917184863210977,
|
|
"loss": 5.8731,
|
|
"mean_token_accuracy": 0.1681960791349411,
|
|
"num_tokens": 18744720.0,
|
|
"step": 9580
|
|
},
|
|
{
|
|
"entropy": 6.229800128936768,
|
|
"epoch": 0.9581646423751687,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004917088900138326,
|
|
"loss": 6.1122,
|
|
"mean_token_accuracy": 0.15004415959119796,
|
|
"num_tokens": 18753636.0,
|
|
"step": 9585
|
|
},
|
|
{
|
|
"entropy": 6.322670745849609,
|
|
"epoch": 0.9586644674363972,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004916992882542276,
|
|
"loss": 6.1006,
|
|
"mean_token_accuracy": 0.14908642694354057,
|
|
"num_tokens": 18763750.0,
|
|
"step": 9590
|
|
},
|
|
{
|
|
"entropy": 6.207269859313965,
|
|
"epoch": 0.9591642924976258,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004916896810425244,
|
|
"loss": 6.0546,
|
|
"mean_token_accuracy": 0.15118743479251862,
|
|
"num_tokens": 18773626.0,
|
|
"step": 9595
|
|
},
|
|
{
|
|
"entropy": 6.219454288482666,
|
|
"epoch": 0.9596641175588544,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004916800683789645,
|
|
"loss": 6.063,
|
|
"mean_token_accuracy": 0.1522775650024414,
|
|
"num_tokens": 18782898.0,
|
|
"step": 9600
|
|
},
|
|
{
|
|
"entropy": 6.327855587005615,
|
|
"epoch": 0.960163942620083,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004916704502637897,
|
|
"loss": 6.1931,
|
|
"mean_token_accuracy": 0.14349066764116286,
|
|
"num_tokens": 18792894.0,
|
|
"step": 9605
|
|
},
|
|
{
|
|
"entropy": 6.2121885299682615,
|
|
"epoch": 0.9606637676813116,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004916608266972422,
|
|
"loss": 6.0935,
|
|
"mean_token_accuracy": 0.15067237615585327,
|
|
"num_tokens": 18802030.0,
|
|
"step": 9610
|
|
},
|
|
{
|
|
"entropy": 6.207405042648316,
|
|
"epoch": 0.9611635927425402,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004916511976795642,
|
|
"loss": 6.1992,
|
|
"mean_token_accuracy": 0.14298802688717843,
|
|
"num_tokens": 18812011.0,
|
|
"step": 9615
|
|
},
|
|
{
|
|
"entropy": 6.286406755447388,
|
|
"epoch": 0.9616634178037686,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004916415632109977,
|
|
"loss": 6.0969,
|
|
"mean_token_accuracy": 0.15050239562988282,
|
|
"num_tokens": 18821217.0,
|
|
"step": 9620
|
|
},
|
|
{
|
|
"entropy": 6.3407751560211185,
|
|
"epoch": 0.9621632428649972,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004916319232917852,
|
|
"loss": 6.1646,
|
|
"mean_token_accuracy": 0.1435486912727356,
|
|
"num_tokens": 18831597.0,
|
|
"step": 9625
|
|
},
|
|
{
|
|
"entropy": 6.311895704269409,
|
|
"epoch": 0.9626630679262258,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004916222779221694,
|
|
"loss": 6.1218,
|
|
"mean_token_accuracy": 0.15257727950811387,
|
|
"num_tokens": 18840925.0,
|
|
"step": 9630
|
|
},
|
|
{
|
|
"entropy": 6.224952697753906,
|
|
"epoch": 0.9631628929874544,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004916126271023926,
|
|
"loss": 6.1388,
|
|
"mean_token_accuracy": 0.1492209255695343,
|
|
"num_tokens": 18850838.0,
|
|
"step": 9635
|
|
},
|
|
{
|
|
"entropy": 6.3141227722167965,
|
|
"epoch": 0.963662718048683,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.000491602970832698,
|
|
"loss": 6.1396,
|
|
"mean_token_accuracy": 0.1446845680475235,
|
|
"num_tokens": 18860527.0,
|
|
"step": 9640
|
|
},
|
|
{
|
|
"entropy": 6.239820194244385,
|
|
"epoch": 0.9641625431099116,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004915933091133284,
|
|
"loss": 6.0754,
|
|
"mean_token_accuracy": 0.15459849685430527,
|
|
"num_tokens": 18870971.0,
|
|
"step": 9645
|
|
},
|
|
{
|
|
"entropy": 6.197712230682373,
|
|
"epoch": 0.9646623681711401,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004915836419445268,
|
|
"loss": 6.0609,
|
|
"mean_token_accuracy": 0.15507566183805466,
|
|
"num_tokens": 18879985.0,
|
|
"step": 9650
|
|
},
|
|
{
|
|
"entropy": 6.272829675674439,
|
|
"epoch": 0.9651621932323686,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004915739693265365,
|
|
"loss": 6.0868,
|
|
"mean_token_accuracy": 0.14531096816062927,
|
|
"num_tokens": 18889583.0,
|
|
"step": 9655
|
|
},
|
|
{
|
|
"entropy": 6.2158444881439205,
|
|
"epoch": 0.9656620182935972,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004915642912596009,
|
|
"loss": 6.0941,
|
|
"mean_token_accuracy": 0.1546364977955818,
|
|
"num_tokens": 18900520.0,
|
|
"step": 9660
|
|
},
|
|
{
|
|
"entropy": 6.277464723587036,
|
|
"epoch": 0.9661618433548258,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004915546077439634,
|
|
"loss": 6.1368,
|
|
"mean_token_accuracy": 0.14698187932372092,
|
|
"num_tokens": 18910924.0,
|
|
"step": 9665
|
|
},
|
|
{
|
|
"entropy": 6.326194810867309,
|
|
"epoch": 0.9666616684160544,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004915449187798677,
|
|
"loss": 6.0649,
|
|
"mean_token_accuracy": 0.15707309246063234,
|
|
"num_tokens": 18919628.0,
|
|
"step": 9670
|
|
},
|
|
{
|
|
"entropy": 6.27040205001831,
|
|
"epoch": 0.967161493477283,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004915352243675576,
|
|
"loss": 6.1672,
|
|
"mean_token_accuracy": 0.14706978052854539,
|
|
"num_tokens": 18929779.0,
|
|
"step": 9675
|
|
},
|
|
{
|
|
"entropy": 6.212332487106323,
|
|
"epoch": 0.9676613185385116,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.000491525524507277,
|
|
"loss": 6.0862,
|
|
"mean_token_accuracy": 0.15082838758826256,
|
|
"num_tokens": 18939791.0,
|
|
"step": 9680
|
|
},
|
|
{
|
|
"entropy": 6.168014717102051,
|
|
"epoch": 0.96816114359974,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004915158191992699,
|
|
"loss": 6.0265,
|
|
"mean_token_accuracy": 0.15056950077414513,
|
|
"num_tokens": 18949611.0,
|
|
"step": 9685
|
|
},
|
|
{
|
|
"entropy": 6.259332752227783,
|
|
"epoch": 0.9686609686609686,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004915061084437805,
|
|
"loss": 6.0868,
|
|
"mean_token_accuracy": 0.15144484788179396,
|
|
"num_tokens": 18959018.0,
|
|
"step": 9690
|
|
},
|
|
{
|
|
"entropy": 6.279534196853637,
|
|
"epoch": 0.9691607937221972,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004914963922410531,
|
|
"loss": 6.0371,
|
|
"mean_token_accuracy": 0.15167754665017127,
|
|
"num_tokens": 18967460.0,
|
|
"step": 9695
|
|
},
|
|
{
|
|
"entropy": 6.227499103546142,
|
|
"epoch": 0.9696606187834258,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004914866705913322,
|
|
"loss": 6.1346,
|
|
"mean_token_accuracy": 0.14630355685949326,
|
|
"num_tokens": 18977545.0,
|
|
"step": 9700
|
|
},
|
|
{
|
|
"entropy": 6.212757682800293,
|
|
"epoch": 0.9701604438446544,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004914769434948623,
|
|
"loss": 6.1159,
|
|
"mean_token_accuracy": 0.15726826936006547,
|
|
"num_tokens": 18987304.0,
|
|
"step": 9705
|
|
},
|
|
{
|
|
"entropy": 6.2686597347259525,
|
|
"epoch": 0.970660268905883,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004914672109518883,
|
|
"loss": 6.1898,
|
|
"mean_token_accuracy": 0.14999598041176795,
|
|
"num_tokens": 18996571.0,
|
|
"step": 9710
|
|
},
|
|
{
|
|
"entropy": 6.367182636260987,
|
|
"epoch": 0.9711600939671116,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.000491457472962655,
|
|
"loss": 6.1262,
|
|
"mean_token_accuracy": 0.1426181748509407,
|
|
"num_tokens": 19007345.0,
|
|
"step": 9715
|
|
},
|
|
{
|
|
"entropy": 6.298504829406738,
|
|
"epoch": 0.97165991902834,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004914477295274073,
|
|
"loss": 6.1449,
|
|
"mean_token_accuracy": 0.14534396007657052,
|
|
"num_tokens": 19018202.0,
|
|
"step": 9720
|
|
},
|
|
{
|
|
"entropy": 6.232018566131591,
|
|
"epoch": 0.9721597440895686,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004914379806463905,
|
|
"loss": 6.099,
|
|
"mean_token_accuracy": 0.15088520646095277,
|
|
"num_tokens": 19027642.0,
|
|
"step": 9725
|
|
},
|
|
{
|
|
"entropy": 6.28934063911438,
|
|
"epoch": 0.9726595691507972,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004914282263198498,
|
|
"loss": 6.121,
|
|
"mean_token_accuracy": 0.14836250022053718,
|
|
"num_tokens": 19037433.0,
|
|
"step": 9730
|
|
},
|
|
{
|
|
"entropy": 6.295781850814819,
|
|
"epoch": 0.9731593942120258,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004914184665480305,
|
|
"loss": 6.1348,
|
|
"mean_token_accuracy": 0.15056052729487418,
|
|
"num_tokens": 19046835.0,
|
|
"step": 9735
|
|
},
|
|
{
|
|
"entropy": 6.308745050430298,
|
|
"epoch": 0.9736592192732544,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004914087013311784,
|
|
"loss": 6.2008,
|
|
"mean_token_accuracy": 0.14433033019304276,
|
|
"num_tokens": 19057109.0,
|
|
"step": 9740
|
|
},
|
|
{
|
|
"entropy": 6.199694108963013,
|
|
"epoch": 0.974159044334483,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004913989306695389,
|
|
"loss": 6.0974,
|
|
"mean_token_accuracy": 0.14893966019153596,
|
|
"num_tokens": 19067688.0,
|
|
"step": 9745
|
|
},
|
|
{
|
|
"entropy": 6.2316741943359375,
|
|
"epoch": 0.9746588693957114,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.0004913891545633582,
|
|
"loss": 6.0769,
|
|
"mean_token_accuracy": 0.15238936841487885,
|
|
"num_tokens": 19077127.0,
|
|
"step": 9750
|
|
},
|
|
{
|
|
"entropy": 6.235041713714599,
|
|
"epoch": 0.97515869445694,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.000491379373012882,
|
|
"loss": 6.1371,
|
|
"mean_token_accuracy": 0.15783379822969437,
|
|
"num_tokens": 19088797.0,
|
|
"step": 9755
|
|
},
|
|
{
|
|
"entropy": 6.2633801937103275,
|
|
"epoch": 0.9756585195181686,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004913695860183563,
|
|
"loss": 6.0675,
|
|
"mean_token_accuracy": 0.15472119748592378,
|
|
"num_tokens": 19098647.0,
|
|
"step": 9760
|
|
},
|
|
{
|
|
"entropy": 6.1970987796783445,
|
|
"epoch": 0.9761583445793972,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004913597935800276,
|
|
"loss": 6.0359,
|
|
"mean_token_accuracy": 0.15427698493003844,
|
|
"num_tokens": 19108385.0,
|
|
"step": 9765
|
|
},
|
|
{
|
|
"entropy": 6.281727409362793,
|
|
"epoch": 0.9766581696406258,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004913499956981422,
|
|
"loss": 6.153,
|
|
"mean_token_accuracy": 0.1440155953168869,
|
|
"num_tokens": 19117593.0,
|
|
"step": 9770
|
|
},
|
|
{
|
|
"entropy": 6.268272018432617,
|
|
"epoch": 0.9771579947018544,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004913401923729465,
|
|
"loss": 6.0627,
|
|
"mean_token_accuracy": 0.14705411940813065,
|
|
"num_tokens": 19127440.0,
|
|
"step": 9775
|
|
},
|
|
{
|
|
"entropy": 6.287357664108276,
|
|
"epoch": 0.977657819763083,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004913303836046873,
|
|
"loss": 6.0704,
|
|
"mean_token_accuracy": 0.14986386001110077,
|
|
"num_tokens": 19136649.0,
|
|
"step": 9780
|
|
},
|
|
{
|
|
"entropy": 6.1856701374053955,
|
|
"epoch": 0.9781576448243114,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004913205693936112,
|
|
"loss": 6.1414,
|
|
"mean_token_accuracy": 0.15199240893125535,
|
|
"num_tokens": 19147702.0,
|
|
"step": 9785
|
|
},
|
|
{
|
|
"entropy": 6.18320255279541,
|
|
"epoch": 0.97865746988554,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004913107497399653,
|
|
"loss": 6.0955,
|
|
"mean_token_accuracy": 0.15147413164377213,
|
|
"num_tokens": 19157146.0,
|
|
"step": 9790
|
|
},
|
|
{
|
|
"entropy": 6.292190265655518,
|
|
"epoch": 0.9791572949467686,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004913009246439966,
|
|
"loss": 6.201,
|
|
"mean_token_accuracy": 0.1434192307293415,
|
|
"num_tokens": 19167157.0,
|
|
"step": 9795
|
|
},
|
|
{
|
|
"entropy": 6.403326797485351,
|
|
"epoch": 0.9796571200079972,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004912910941059525,
|
|
"loss": 6.1692,
|
|
"mean_token_accuracy": 0.13740362450480462,
|
|
"num_tokens": 19177188.0,
|
|
"step": 9800
|
|
},
|
|
{
|
|
"entropy": 6.1945184707641605,
|
|
"epoch": 0.9801569450692258,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004912812581260799,
|
|
"loss": 5.9667,
|
|
"mean_token_accuracy": 0.15585940182209015,
|
|
"num_tokens": 19185940.0,
|
|
"step": 9805
|
|
},
|
|
{
|
|
"entropy": 6.1670811653137205,
|
|
"epoch": 0.9806567701304544,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004912714167046265,
|
|
"loss": 6.0547,
|
|
"mean_token_accuracy": 0.14437031447887422,
|
|
"num_tokens": 19194634.0,
|
|
"step": 9810
|
|
},
|
|
{
|
|
"entropy": 6.2410194873809814,
|
|
"epoch": 0.9811565951916829,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004912615698418399,
|
|
"loss": 6.0531,
|
|
"mean_token_accuracy": 0.1570142239332199,
|
|
"num_tokens": 19203835.0,
|
|
"step": 9815
|
|
},
|
|
{
|
|
"entropy": 6.244063186645508,
|
|
"epoch": 0.9816564202529114,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004912517175379679,
|
|
"loss": 6.0751,
|
|
"mean_token_accuracy": 0.15095652863383294,
|
|
"num_tokens": 19213458.0,
|
|
"step": 9820
|
|
},
|
|
{
|
|
"entropy": 6.275372648239136,
|
|
"epoch": 0.98215624531414,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004912418597932584,
|
|
"loss": 6.1628,
|
|
"mean_token_accuracy": 0.14198298379778862,
|
|
"num_tokens": 19222494.0,
|
|
"step": 9825
|
|
},
|
|
{
|
|
"entropy": 6.239107131958008,
|
|
"epoch": 0.9826560703753686,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004912319966079592,
|
|
"loss": 6.0586,
|
|
"mean_token_accuracy": 0.1510770469903946,
|
|
"num_tokens": 19232153.0,
|
|
"step": 9830
|
|
},
|
|
{
|
|
"entropy": 6.232474040985108,
|
|
"epoch": 0.9831558954365972,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004912221279823187,
|
|
"loss": 6.1188,
|
|
"mean_token_accuracy": 0.1450786381959915,
|
|
"num_tokens": 19241673.0,
|
|
"step": 9835
|
|
},
|
|
{
|
|
"entropy": 6.318443775177002,
|
|
"epoch": 0.9836557204978258,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004912122539165851,
|
|
"loss": 6.0878,
|
|
"mean_token_accuracy": 0.14770561456680298,
|
|
"num_tokens": 19250146.0,
|
|
"step": 9840
|
|
},
|
|
{
|
|
"entropy": 6.358970689773559,
|
|
"epoch": 0.9841555455590544,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004912023744110068,
|
|
"loss": 6.1973,
|
|
"mean_token_accuracy": 0.14836482256650924,
|
|
"num_tokens": 19259969.0,
|
|
"step": 9845
|
|
},
|
|
{
|
|
"entropy": 6.210375022888184,
|
|
"epoch": 0.9846553706202829,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004911924894658324,
|
|
"loss": 6.1255,
|
|
"mean_token_accuracy": 0.13817757442593576,
|
|
"num_tokens": 19269502.0,
|
|
"step": 9850
|
|
},
|
|
{
|
|
"entropy": 6.180826568603516,
|
|
"epoch": 0.9851551956815114,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004911825990813107,
|
|
"loss": 6.0081,
|
|
"mean_token_accuracy": 0.15917390957474709,
|
|
"num_tokens": 19277965.0,
|
|
"step": 9855
|
|
},
|
|
{
|
|
"entropy": 6.2200109481811525,
|
|
"epoch": 0.98565502074274,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004911727032576903,
|
|
"loss": 6.0717,
|
|
"mean_token_accuracy": 0.15084305107593537,
|
|
"num_tokens": 19287618.0,
|
|
"step": 9860
|
|
},
|
|
{
|
|
"entropy": 6.27437047958374,
|
|
"epoch": 0.9861548458039686,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004911628019952203,
|
|
"loss": 6.0694,
|
|
"mean_token_accuracy": 0.15520483776926994,
|
|
"num_tokens": 19297865.0,
|
|
"step": 9865
|
|
},
|
|
{
|
|
"entropy": 6.219357442855835,
|
|
"epoch": 0.9866546708651972,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004911528952941499,
|
|
"loss": 6.057,
|
|
"mean_token_accuracy": 0.14999715387821197,
|
|
"num_tokens": 19308957.0,
|
|
"step": 9870
|
|
},
|
|
{
|
|
"entropy": 6.273249578475952,
|
|
"epoch": 0.9871544959264258,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004911429831547283,
|
|
"loss": 6.1398,
|
|
"mean_token_accuracy": 0.14897414892911912,
|
|
"num_tokens": 19319310.0,
|
|
"step": 9875
|
|
},
|
|
{
|
|
"entropy": 6.235526418685913,
|
|
"epoch": 0.9876543209876543,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004911330655772047,
|
|
"loss": 6.1229,
|
|
"mean_token_accuracy": 0.15258189737796785,
|
|
"num_tokens": 19329854.0,
|
|
"step": 9880
|
|
},
|
|
{
|
|
"entropy": 6.254607200622559,
|
|
"epoch": 0.9881541460488829,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.000491123142561829,
|
|
"loss": 6.0935,
|
|
"mean_token_accuracy": 0.14468444660305976,
|
|
"num_tokens": 19340327.0,
|
|
"step": 9885
|
|
},
|
|
{
|
|
"entropy": 6.221146154403686,
|
|
"epoch": 0.9886539711101114,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004911132141088505,
|
|
"loss": 6.0007,
|
|
"mean_token_accuracy": 0.15526287406682968,
|
|
"num_tokens": 19349577.0,
|
|
"step": 9890
|
|
},
|
|
{
|
|
"entropy": 6.247826623916626,
|
|
"epoch": 0.98915379617134,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004911032802185192,
|
|
"loss": 6.1243,
|
|
"mean_token_accuracy": 0.14174894317984582,
|
|
"num_tokens": 19359601.0,
|
|
"step": 9895
|
|
},
|
|
{
|
|
"entropy": 6.249024820327759,
|
|
"epoch": 0.9896536212325686,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.000491093340891085,
|
|
"loss": 6.1376,
|
|
"mean_token_accuracy": 0.14840798303484917,
|
|
"num_tokens": 19368592.0,
|
|
"step": 9900
|
|
},
|
|
{
|
|
"entropy": 6.295890235900879,
|
|
"epoch": 0.9901534462937972,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004910833961267979,
|
|
"loss": 6.1158,
|
|
"mean_token_accuracy": 0.14280205890536307,
|
|
"num_tokens": 19379220.0,
|
|
"step": 9905
|
|
},
|
|
{
|
|
"entropy": 6.18821439743042,
|
|
"epoch": 0.9906532713550258,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004910734459259081,
|
|
"loss": 6.0108,
|
|
"mean_token_accuracy": 0.15101381316781043,
|
|
"num_tokens": 19388339.0,
|
|
"step": 9910
|
|
},
|
|
{
|
|
"entropy": 6.186379432678223,
|
|
"epoch": 0.9911530964162543,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004910634902886662,
|
|
"loss": 6.0671,
|
|
"mean_token_accuracy": 0.154706159979105,
|
|
"num_tokens": 19396873.0,
|
|
"step": 9915
|
|
},
|
|
{
|
|
"entropy": 6.24030294418335,
|
|
"epoch": 0.9916529214774829,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004910535292153224,
|
|
"loss": 6.0602,
|
|
"mean_token_accuracy": 0.15034509524703027,
|
|
"num_tokens": 19406268.0,
|
|
"step": 9920
|
|
},
|
|
{
|
|
"entropy": 6.338252305984497,
|
|
"epoch": 0.9921527465387114,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004910435627061273,
|
|
"loss": 6.1289,
|
|
"mean_token_accuracy": 0.15386831238865853,
|
|
"num_tokens": 19415478.0,
|
|
"step": 9925
|
|
},
|
|
{
|
|
"entropy": 6.196127462387085,
|
|
"epoch": 0.99265257159994,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004910335907613318,
|
|
"loss": 6.0463,
|
|
"mean_token_accuracy": 0.15231262072920798,
|
|
"num_tokens": 19424835.0,
|
|
"step": 9930
|
|
},
|
|
{
|
|
"entropy": 6.209330606460571,
|
|
"epoch": 0.9931523966611686,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004910236133811867,
|
|
"loss": 6.0792,
|
|
"mean_token_accuracy": 0.1524357818067074,
|
|
"num_tokens": 19434147.0,
|
|
"step": 9935
|
|
},
|
|
{
|
|
"entropy": 6.321203422546387,
|
|
"epoch": 0.9936522217223972,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004910136305659432,
|
|
"loss": 6.1433,
|
|
"mean_token_accuracy": 0.1473076358437538,
|
|
"num_tokens": 19444157.0,
|
|
"step": 9940
|
|
},
|
|
{
|
|
"entropy": 6.218345499038696,
|
|
"epoch": 0.9941520467836257,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004910036423158523,
|
|
"loss": 6.0778,
|
|
"mean_token_accuracy": 0.154684891551733,
|
|
"num_tokens": 19453859.0,
|
|
"step": 9945
|
|
},
|
|
{
|
|
"entropy": 6.220662307739258,
|
|
"epoch": 0.9946518718448543,
|
|
"grad_norm": 2.3125,
|
|
"learning_rate": 0.0004909936486311653,
|
|
"loss": 6.1279,
|
|
"mean_token_accuracy": 0.1507511630654335,
|
|
"num_tokens": 19464191.0,
|
|
"step": 9950
|
|
},
|
|
{
|
|
"entropy": 6.216753435134888,
|
|
"epoch": 0.9951516969060828,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004909836495121336,
|
|
"loss": 6.0838,
|
|
"mean_token_accuracy": 0.15288073271512986,
|
|
"num_tokens": 19473025.0,
|
|
"step": 9955
|
|
},
|
|
{
|
|
"entropy": 6.311555194854736,
|
|
"epoch": 0.9956515219673114,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004909736449590091,
|
|
"loss": 6.2291,
|
|
"mean_token_accuracy": 0.14836422055959703,
|
|
"num_tokens": 19483329.0,
|
|
"step": 9960
|
|
},
|
|
{
|
|
"entropy": 6.265091037750244,
|
|
"epoch": 0.99615134702854,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.000490963634972043,
|
|
"loss": 6.1194,
|
|
"mean_token_accuracy": 0.14428912550210954,
|
|
"num_tokens": 19492756.0,
|
|
"step": 9965
|
|
},
|
|
{
|
|
"entropy": 6.248616743087768,
|
|
"epoch": 0.9966511720897686,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004909536195514875,
|
|
"loss": 6.1577,
|
|
"mean_token_accuracy": 0.14273637533187866,
|
|
"num_tokens": 19502363.0,
|
|
"step": 9970
|
|
},
|
|
{
|
|
"entropy": 6.30375599861145,
|
|
"epoch": 0.9971509971509972,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004909435986975946,
|
|
"loss": 6.1818,
|
|
"mean_token_accuracy": 0.14637240916490554,
|
|
"num_tokens": 19512180.0,
|
|
"step": 9975
|
|
},
|
|
{
|
|
"entropy": 6.343056917190552,
|
|
"epoch": 0.9976508222122257,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004909335724106162,
|
|
"loss": 6.1829,
|
|
"mean_token_accuracy": 0.1457211971282959,
|
|
"num_tokens": 19521819.0,
|
|
"step": 9980
|
|
},
|
|
{
|
|
"entropy": 6.246092462539673,
|
|
"epoch": 0.9981506472734543,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004909235406908047,
|
|
"loss": 6.1158,
|
|
"mean_token_accuracy": 0.14938534647226334,
|
|
"num_tokens": 19531960.0,
|
|
"step": 9985
|
|
},
|
|
{
|
|
"entropy": 6.198645114898682,
|
|
"epoch": 0.9986504723346828,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004909135035384126,
|
|
"loss": 6.0848,
|
|
"mean_token_accuracy": 0.15256978422403336,
|
|
"num_tokens": 19542278.0,
|
|
"step": 9990
|
|
},
|
|
{
|
|
"entropy": 6.292979001998901,
|
|
"epoch": 0.9991502973959114,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004909034609536922,
|
|
"loss": 6.1316,
|
|
"mean_token_accuracy": 0.14888818711042404,
|
|
"num_tokens": 19552740.0,
|
|
"step": 9995
|
|
},
|
|
{
|
|
"entropy": 6.264652347564697,
|
|
"epoch": 0.99965012245714,
|
|
"grad_norm": 2.65625,
|
|
"learning_rate": 0.0004908934129368963,
|
|
"loss": 6.0738,
|
|
"mean_token_accuracy": 0.15019856691360473,
|
|
"num_tokens": 19563174.0,
|
|
"step": 10000
|
|
},
|
|
{
|
|
"entropy": 6.2063873079088,
|
|
"epoch": 1.0000999650122457,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004908833594882777,
|
|
"loss": 6.0633,
|
|
"mean_token_accuracy": 0.15104605505863825,
|
|
"num_tokens": 19571268.0,
|
|
"step": 10005
|
|
},
|
|
{
|
|
"entropy": 6.232393836975097,
|
|
"epoch": 1.0005997900734742,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004908733006080893,
|
|
"loss": 5.9542,
|
|
"mean_token_accuracy": 0.15942276418209075,
|
|
"num_tokens": 19580615.0,
|
|
"step": 10010
|
|
},
|
|
{
|
|
"entropy": 6.238720989227295,
|
|
"epoch": 1.001099615134703,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004908632362965842,
|
|
"loss": 6.0111,
|
|
"mean_token_accuracy": 0.15403904542326927,
|
|
"num_tokens": 19590983.0,
|
|
"step": 10015
|
|
},
|
|
{
|
|
"entropy": 6.223530387878418,
|
|
"epoch": 1.0015994401959314,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004908531665540158,
|
|
"loss": 5.9916,
|
|
"mean_token_accuracy": 0.15515465661883354,
|
|
"num_tokens": 19600440.0,
|
|
"step": 10020
|
|
},
|
|
{
|
|
"entropy": 6.174214029312134,
|
|
"epoch": 1.00209926525716,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.000490843091380637,
|
|
"loss": 6.027,
|
|
"mean_token_accuracy": 0.15265021175146104,
|
|
"num_tokens": 19610779.0,
|
|
"step": 10025
|
|
},
|
|
{
|
|
"entropy": 6.2175719261169435,
|
|
"epoch": 1.0025990903183886,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004908330107767018,
|
|
"loss": 6.0422,
|
|
"mean_token_accuracy": 0.14577231854200362,
|
|
"num_tokens": 19620729.0,
|
|
"step": 10030
|
|
},
|
|
{
|
|
"entropy": 6.2749419689178465,
|
|
"epoch": 1.003098915379617,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004908229247424633,
|
|
"loss": 6.017,
|
|
"mean_token_accuracy": 0.15350845009088515,
|
|
"num_tokens": 19630493.0,
|
|
"step": 10035
|
|
},
|
|
{
|
|
"entropy": 6.247971391677856,
|
|
"epoch": 1.0035987404408457,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004908128332781758,
|
|
"loss": 6.0068,
|
|
"mean_token_accuracy": 0.15064608454704284,
|
|
"num_tokens": 19640672.0,
|
|
"step": 10040
|
|
},
|
|
{
|
|
"entropy": 6.244055938720703,
|
|
"epoch": 1.0040985655020742,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004908027363840928,
|
|
"loss": 6.0266,
|
|
"mean_token_accuracy": 0.15170393139123917,
|
|
"num_tokens": 19651009.0,
|
|
"step": 10045
|
|
},
|
|
{
|
|
"entropy": 6.238856267929077,
|
|
"epoch": 1.004598390563303,
|
|
"grad_norm": 3.78125,
|
|
"learning_rate": 0.0004907926340604686,
|
|
"loss": 6.0609,
|
|
"mean_token_accuracy": 0.1516696944832802,
|
|
"num_tokens": 19661422.0,
|
|
"step": 10050
|
|
},
|
|
{
|
|
"entropy": 6.234027481079101,
|
|
"epoch": 1.0050982156245314,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.0004907825263075573,
|
|
"loss": 6.0173,
|
|
"mean_token_accuracy": 0.14826187938451768,
|
|
"num_tokens": 19671039.0,
|
|
"step": 10055
|
|
},
|
|
{
|
|
"entropy": 6.220024871826172,
|
|
"epoch": 1.00559804068576,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004907724131256129,
|
|
"loss": 6.0105,
|
|
"mean_token_accuracy": 0.14830300211906433,
|
|
"num_tokens": 19680385.0,
|
|
"step": 10060
|
|
},
|
|
{
|
|
"entropy": 6.250578784942627,
|
|
"epoch": 1.0060978657469886,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004907622945148903,
|
|
"loss": 6.0703,
|
|
"mean_token_accuracy": 0.14842513725161552,
|
|
"num_tokens": 19690626.0,
|
|
"step": 10065
|
|
},
|
|
{
|
|
"entropy": 6.26675443649292,
|
|
"epoch": 1.006597690808217,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004907521704756438,
|
|
"loss": 6.0142,
|
|
"mean_token_accuracy": 0.14238255470991135,
|
|
"num_tokens": 19700234.0,
|
|
"step": 10070
|
|
},
|
|
{
|
|
"entropy": 6.253324270248413,
|
|
"epoch": 1.0070975158694457,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004907420410081284,
|
|
"loss": 6.012,
|
|
"mean_token_accuracy": 0.15270191207528114,
|
|
"num_tokens": 19708986.0,
|
|
"step": 10075
|
|
},
|
|
{
|
|
"entropy": 6.190138483047486,
|
|
"epoch": 1.0075973409306742,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.0004907319061125986,
|
|
"loss": 6.0593,
|
|
"mean_token_accuracy": 0.14822639375925065,
|
|
"num_tokens": 19718292.0,
|
|
"step": 10080
|
|
},
|
|
{
|
|
"entropy": 6.131137800216675,
|
|
"epoch": 1.008097165991903,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004907217657893096,
|
|
"loss": 5.9624,
|
|
"mean_token_accuracy": 0.15677581131458282,
|
|
"num_tokens": 19727563.0,
|
|
"step": 10085
|
|
},
|
|
{
|
|
"entropy": 6.2391736030578615,
|
|
"epoch": 1.0085969910531314,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004907116200385165,
|
|
"loss": 6.0164,
|
|
"mean_token_accuracy": 0.14878358393907548,
|
|
"num_tokens": 19737649.0,
|
|
"step": 10090
|
|
},
|
|
{
|
|
"entropy": 6.274553918838501,
|
|
"epoch": 1.00909681611436,
|
|
"grad_norm": 2.453125,
|
|
"learning_rate": 0.0004907014688604745,
|
|
"loss": 6.0487,
|
|
"mean_token_accuracy": 0.14974594712257386,
|
|
"num_tokens": 19746911.0,
|
|
"step": 10095
|
|
},
|
|
{
|
|
"entropy": 6.12417688369751,
|
|
"epoch": 1.0095966411755886,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004906913122554391,
|
|
"loss": 6.0357,
|
|
"mean_token_accuracy": 0.1512255534529686,
|
|
"num_tokens": 19757144.0,
|
|
"step": 10100
|
|
},
|
|
{
|
|
"entropy": 6.188208818435669,
|
|
"epoch": 1.010096466236817,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004906811502236657,
|
|
"loss": 5.9563,
|
|
"mean_token_accuracy": 0.15488606095314025,
|
|
"num_tokens": 19766422.0,
|
|
"step": 10105
|
|
},
|
|
{
|
|
"entropy": 6.288571739196778,
|
|
"epoch": 1.0105962912980457,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004906709827654101,
|
|
"loss": 6.0183,
|
|
"mean_token_accuracy": 0.15200354978442193,
|
|
"num_tokens": 19774711.0,
|
|
"step": 10110
|
|
},
|
|
{
|
|
"entropy": 6.228627681732178,
|
|
"epoch": 1.0110961163592742,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004906608098809281,
|
|
"loss": 6.0166,
|
|
"mean_token_accuracy": 0.15119887739419938,
|
|
"num_tokens": 19784347.0,
|
|
"step": 10115
|
|
},
|
|
{
|
|
"entropy": 6.216867923736572,
|
|
"epoch": 1.011595941420503,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004906506315704756,
|
|
"loss": 6.1396,
|
|
"mean_token_accuracy": 0.1457881286740303,
|
|
"num_tokens": 19796100.0,
|
|
"step": 10120
|
|
},
|
|
{
|
|
"entropy": 6.213804864883423,
|
|
"epoch": 1.0120957664817314,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004906404478343087,
|
|
"loss": 5.9726,
|
|
"mean_token_accuracy": 0.1545696146786213,
|
|
"num_tokens": 19805942.0,
|
|
"step": 10125
|
|
},
|
|
{
|
|
"entropy": 6.2151491165161135,
|
|
"epoch": 1.0125955915429599,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004906302586726837,
|
|
"loss": 5.9497,
|
|
"mean_token_accuracy": 0.1608385443687439,
|
|
"num_tokens": 19814707.0,
|
|
"step": 10130
|
|
},
|
|
{
|
|
"entropy": 6.171500635147095,
|
|
"epoch": 1.0130954166041886,
|
|
"grad_norm": 1.90625,
|
|
"learning_rate": 0.0004906200640858567,
|
|
"loss": 6.0763,
|
|
"mean_token_accuracy": 0.1448494404554367,
|
|
"num_tokens": 19825061.0,
|
|
"step": 10135
|
|
},
|
|
{
|
|
"entropy": 6.216320323944092,
|
|
"epoch": 1.013595241665417,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004906098640740846,
|
|
"loss": 6.0204,
|
|
"mean_token_accuracy": 0.15389695912599563,
|
|
"num_tokens": 19834572.0,
|
|
"step": 10140
|
|
},
|
|
{
|
|
"entropy": 6.281344985961914,
|
|
"epoch": 1.0140950667266457,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004905996586376236,
|
|
"loss": 6.0519,
|
|
"mean_token_accuracy": 0.1448914423584938,
|
|
"num_tokens": 19844691.0,
|
|
"step": 10145
|
|
},
|
|
{
|
|
"entropy": 6.169038724899292,
|
|
"epoch": 1.0145948917878742,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004905894477767308,
|
|
"loss": 5.9251,
|
|
"mean_token_accuracy": 0.157583612203598,
|
|
"num_tokens": 19854806.0,
|
|
"step": 10150
|
|
},
|
|
{
|
|
"entropy": 6.229771947860717,
|
|
"epoch": 1.015094716849103,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004905792314916629,
|
|
"loss": 6.0357,
|
|
"mean_token_accuracy": 0.15063023269176484,
|
|
"num_tokens": 19863943.0,
|
|
"step": 10155
|
|
},
|
|
{
|
|
"entropy": 6.25595064163208,
|
|
"epoch": 1.0155945419103314,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004905690097826769,
|
|
"loss": 6.0342,
|
|
"mean_token_accuracy": 0.1471012368798256,
|
|
"num_tokens": 19873417.0,
|
|
"step": 10160
|
|
},
|
|
{
|
|
"entropy": 6.181386232376099,
|
|
"epoch": 1.0160943669715599,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004905587826500303,
|
|
"loss": 5.9824,
|
|
"mean_token_accuracy": 0.1477060340344906,
|
|
"num_tokens": 19883088.0,
|
|
"step": 10165
|
|
},
|
|
{
|
|
"entropy": 6.240792942047119,
|
|
"epoch": 1.0165941920327886,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004905485500939801,
|
|
"loss": 6.017,
|
|
"mean_token_accuracy": 0.15172144919633865,
|
|
"num_tokens": 19893851.0,
|
|
"step": 10170
|
|
},
|
|
{
|
|
"entropy": 6.1961061477661135,
|
|
"epoch": 1.017094017094017,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004905383121147838,
|
|
"loss": 5.975,
|
|
"mean_token_accuracy": 0.14715945199131966,
|
|
"num_tokens": 19904243.0,
|
|
"step": 10175
|
|
},
|
|
{
|
|
"entropy": 6.211069011688233,
|
|
"epoch": 1.0175938421552457,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004905280687126991,
|
|
"loss": 6.1422,
|
|
"mean_token_accuracy": 0.14917925298213958,
|
|
"num_tokens": 19914825.0,
|
|
"step": 10180
|
|
},
|
|
{
|
|
"entropy": 6.208258771896363,
|
|
"epoch": 1.0180936672164742,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004905178198879837,
|
|
"loss": 6.0314,
|
|
"mean_token_accuracy": 0.1490439787507057,
|
|
"num_tokens": 19925455.0,
|
|
"step": 10185
|
|
},
|
|
{
|
|
"entropy": 6.183230209350586,
|
|
"epoch": 1.018593492277703,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004905075656408953,
|
|
"loss": 6.0414,
|
|
"mean_token_accuracy": 0.1503809280693531,
|
|
"num_tokens": 19935810.0,
|
|
"step": 10190
|
|
},
|
|
{
|
|
"entropy": 6.2322876930236815,
|
|
"epoch": 1.0190933173389314,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.000490497305971692,
|
|
"loss": 6.0094,
|
|
"mean_token_accuracy": 0.1514083370566368,
|
|
"num_tokens": 19945508.0,
|
|
"step": 10195
|
|
},
|
|
{
|
|
"entropy": 6.1991111755371096,
|
|
"epoch": 1.0195931424001599,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.000490487040880632,
|
|
"loss": 5.9498,
|
|
"mean_token_accuracy": 0.14916113317012786,
|
|
"num_tokens": 19955148.0,
|
|
"step": 10200
|
|
},
|
|
{
|
|
"entropy": 6.083432722091675,
|
|
"epoch": 1.0200929674613886,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004904767703679735,
|
|
"loss": 5.9694,
|
|
"mean_token_accuracy": 0.1529839128255844,
|
|
"num_tokens": 19965607.0,
|
|
"step": 10205
|
|
},
|
|
{
|
|
"entropy": 6.199935722351074,
|
|
"epoch": 1.020592792522617,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004904664944339748,
|
|
"loss": 6.0094,
|
|
"mean_token_accuracy": 0.15225431248545646,
|
|
"num_tokens": 19976598.0,
|
|
"step": 10210
|
|
},
|
|
{
|
|
"entropy": 6.219248676300049,
|
|
"epoch": 1.0210926175838457,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004904562130788947,
|
|
"loss": 5.9254,
|
|
"mean_token_accuracy": 0.15705513060092927,
|
|
"num_tokens": 19986183.0,
|
|
"step": 10215
|
|
},
|
|
{
|
|
"entropy": 6.234408330917359,
|
|
"epoch": 1.0215924426450742,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004904459263029916,
|
|
"loss": 6.0236,
|
|
"mean_token_accuracy": 0.15483262985944748,
|
|
"num_tokens": 19995930.0,
|
|
"step": 10220
|
|
},
|
|
{
|
|
"entropy": 6.254371213912964,
|
|
"epoch": 1.0220922677063027,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004904356341065245,
|
|
"loss": 6.114,
|
|
"mean_token_accuracy": 0.14660026878118515,
|
|
"num_tokens": 20005826.0,
|
|
"step": 10225
|
|
},
|
|
{
|
|
"entropy": 6.203324651718139,
|
|
"epoch": 1.0225920927675314,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004904253364897521,
|
|
"loss": 6.0415,
|
|
"mean_token_accuracy": 0.15484552532434465,
|
|
"num_tokens": 20015057.0,
|
|
"step": 10230
|
|
},
|
|
{
|
|
"entropy": 6.275355815887451,
|
|
"epoch": 1.0230919178287599,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004904150334529339,
|
|
"loss": 6.0039,
|
|
"mean_token_accuracy": 0.14145815819501878,
|
|
"num_tokens": 20024181.0,
|
|
"step": 10235
|
|
},
|
|
{
|
|
"entropy": 6.20418791770935,
|
|
"epoch": 1.0235917428899886,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004904047249963289,
|
|
"loss": 6.0136,
|
|
"mean_token_accuracy": 0.15010612159967424,
|
|
"num_tokens": 20033453.0,
|
|
"step": 10240
|
|
},
|
|
{
|
|
"entropy": 6.191885232925415,
|
|
"epoch": 1.024091567951217,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004903944111201964,
|
|
"loss": 6.0341,
|
|
"mean_token_accuracy": 0.14934864044189453,
|
|
"num_tokens": 20043324.0,
|
|
"step": 10245
|
|
},
|
|
{
|
|
"entropy": 6.186628770828247,
|
|
"epoch": 1.0245913930124457,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004903840918247958,
|
|
"loss": 6.0387,
|
|
"mean_token_accuracy": 0.15226204469799995,
|
|
"num_tokens": 20053010.0,
|
|
"step": 10250
|
|
},
|
|
{
|
|
"entropy": 6.261638259887695,
|
|
"epoch": 1.0250912180736742,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.000490373767110387,
|
|
"loss": 5.998,
|
|
"mean_token_accuracy": 0.1554411008954048,
|
|
"num_tokens": 20063457.0,
|
|
"step": 10255
|
|
},
|
|
{
|
|
"entropy": 6.268414926528931,
|
|
"epoch": 1.0255910431349027,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004903634369772296,
|
|
"loss": 6.027,
|
|
"mean_token_accuracy": 0.15048531740903853,
|
|
"num_tokens": 20073479.0,
|
|
"step": 10260
|
|
},
|
|
{
|
|
"entropy": 6.209446239471435,
|
|
"epoch": 1.0260908681961314,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004903531014255835,
|
|
"loss": 6.0275,
|
|
"mean_token_accuracy": 0.14842105507850648,
|
|
"num_tokens": 20082711.0,
|
|
"step": 10265
|
|
},
|
|
{
|
|
"entropy": 6.161308097839355,
|
|
"epoch": 1.0265906932573599,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004903427604557089,
|
|
"loss": 5.9931,
|
|
"mean_token_accuracy": 0.1566895477473736,
|
|
"num_tokens": 20092535.0,
|
|
"step": 10270
|
|
},
|
|
{
|
|
"entropy": 6.219944286346435,
|
|
"epoch": 1.0270905183185886,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004903324140678658,
|
|
"loss": 5.969,
|
|
"mean_token_accuracy": 0.15915192663669586,
|
|
"num_tokens": 20101564.0,
|
|
"step": 10275
|
|
},
|
|
{
|
|
"entropy": 6.080531597137451,
|
|
"epoch": 1.027590343379817,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004903220622623146,
|
|
"loss": 5.8839,
|
|
"mean_token_accuracy": 0.16180048733949662,
|
|
"num_tokens": 20110361.0,
|
|
"step": 10280
|
|
},
|
|
{
|
|
"entropy": 6.205290794372559,
|
|
"epoch": 1.0280901684410457,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004903117050393157,
|
|
"loss": 5.9714,
|
|
"mean_token_accuracy": 0.1575970396399498,
|
|
"num_tokens": 20119816.0,
|
|
"step": 10285
|
|
},
|
|
{
|
|
"entropy": 6.224004745483398,
|
|
"epoch": 1.0285899935022742,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004903013423991296,
|
|
"loss": 6.0305,
|
|
"mean_token_accuracy": 0.15508941411972046,
|
|
"num_tokens": 20129246.0,
|
|
"step": 10290
|
|
},
|
|
{
|
|
"entropy": 6.230030488967896,
|
|
"epoch": 1.0290898185635027,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004902909743420173,
|
|
"loss": 6.0114,
|
|
"mean_token_accuracy": 0.15104206651449203,
|
|
"num_tokens": 20140029.0,
|
|
"step": 10295
|
|
},
|
|
{
|
|
"entropy": 6.171510219573975,
|
|
"epoch": 1.0295896436247314,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004902806008682394,
|
|
"loss": 5.9213,
|
|
"mean_token_accuracy": 0.1589931681752205,
|
|
"num_tokens": 20150684.0,
|
|
"step": 10300
|
|
},
|
|
{
|
|
"entropy": 6.208301639556884,
|
|
"epoch": 1.0300894686859599,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.000490270221978057,
|
|
"loss": 6.0154,
|
|
"mean_token_accuracy": 0.15298869758844375,
|
|
"num_tokens": 20160007.0,
|
|
"step": 10305
|
|
},
|
|
{
|
|
"entropy": 6.283911991119385,
|
|
"epoch": 1.0305892937471886,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004902598376717312,
|
|
"loss": 6.0973,
|
|
"mean_token_accuracy": 0.14645808115601539,
|
|
"num_tokens": 20170512.0,
|
|
"step": 10310
|
|
},
|
|
{
|
|
"entropy": 6.1785553932189945,
|
|
"epoch": 1.031089118808417,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004902494479495233,
|
|
"loss": 5.9764,
|
|
"mean_token_accuracy": 0.1595336154103279,
|
|
"num_tokens": 20181954.0,
|
|
"step": 10315
|
|
},
|
|
{
|
|
"entropy": 6.168446111679077,
|
|
"epoch": 1.0315889438696457,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004902390528116946,
|
|
"loss": 5.9889,
|
|
"mean_token_accuracy": 0.15001600831747056,
|
|
"num_tokens": 20191780.0,
|
|
"step": 10320
|
|
},
|
|
{
|
|
"entropy": 6.200594520568847,
|
|
"epoch": 1.0320887689308742,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004902286522585068,
|
|
"loss": 6.0616,
|
|
"mean_token_accuracy": 0.14833675771951677,
|
|
"num_tokens": 20201646.0,
|
|
"step": 10325
|
|
},
|
|
{
|
|
"entropy": 6.217910385131836,
|
|
"epoch": 1.0325885939921027,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004902182462902215,
|
|
"loss": 6.0482,
|
|
"mean_token_accuracy": 0.15123704597353935,
|
|
"num_tokens": 20210943.0,
|
|
"step": 10330
|
|
},
|
|
{
|
|
"entropy": 6.263118553161621,
|
|
"epoch": 1.0330884190533314,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004902078349071004,
|
|
"loss": 6.0208,
|
|
"mean_token_accuracy": 0.1466373957693577,
|
|
"num_tokens": 20219901.0,
|
|
"step": 10335
|
|
},
|
|
{
|
|
"entropy": 6.228824520111084,
|
|
"epoch": 1.0335882441145599,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004901974181094057,
|
|
"loss": 6.0035,
|
|
"mean_token_accuracy": 0.14916652366518973,
|
|
"num_tokens": 20229630.0,
|
|
"step": 10340
|
|
},
|
|
{
|
|
"entropy": 6.251888084411621,
|
|
"epoch": 1.0340880691757885,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004901869958973991,
|
|
"loss": 6.0552,
|
|
"mean_token_accuracy": 0.14913733750581742,
|
|
"num_tokens": 20239932.0,
|
|
"step": 10345
|
|
},
|
|
{
|
|
"entropy": 6.268005466461181,
|
|
"epoch": 1.034587894237017,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004901765682713432,
|
|
"loss": 5.9677,
|
|
"mean_token_accuracy": 0.151399664580822,
|
|
"num_tokens": 20248863.0,
|
|
"step": 10350
|
|
},
|
|
{
|
|
"entropy": 6.136422920227051,
|
|
"epoch": 1.0350877192982457,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004901661352315003,
|
|
"loss": 5.8774,
|
|
"mean_token_accuracy": 0.15820712298154832,
|
|
"num_tokens": 20257916.0,
|
|
"step": 10355
|
|
},
|
|
{
|
|
"entropy": 6.166300964355469,
|
|
"epoch": 1.0355875443594742,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004901556967781327,
|
|
"loss": 6.0053,
|
|
"mean_token_accuracy": 0.15192359387874604,
|
|
"num_tokens": 20267579.0,
|
|
"step": 10360
|
|
},
|
|
{
|
|
"entropy": 6.221320056915284,
|
|
"epoch": 1.0360873694207027,
|
|
"grad_norm": 1.8515625,
|
|
"learning_rate": 0.0004901452529115031,
|
|
"loss": 6.053,
|
|
"mean_token_accuracy": 0.1449980169534683,
|
|
"num_tokens": 20278909.0,
|
|
"step": 10365
|
|
},
|
|
{
|
|
"entropy": 6.228009033203125,
|
|
"epoch": 1.0365871944819314,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004901348036318743,
|
|
"loss": 6.0021,
|
|
"mean_token_accuracy": 0.1474953457713127,
|
|
"num_tokens": 20288933.0,
|
|
"step": 10370
|
|
},
|
|
{
|
|
"entropy": 6.25818452835083,
|
|
"epoch": 1.0370870195431598,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004901243489395093,
|
|
"loss": 6.0188,
|
|
"mean_token_accuracy": 0.142359459400177,
|
|
"num_tokens": 20298329.0,
|
|
"step": 10375
|
|
},
|
|
{
|
|
"entropy": 6.209525299072266,
|
|
"epoch": 1.0375868446043885,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.000490113888834671,
|
|
"loss": 6.0595,
|
|
"mean_token_accuracy": 0.15545681565999986,
|
|
"num_tokens": 20308742.0,
|
|
"step": 10380
|
|
},
|
|
{
|
|
"entropy": 6.078628826141357,
|
|
"epoch": 1.038086669665617,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004901034233176227,
|
|
"loss": 5.8697,
|
|
"mean_token_accuracy": 0.16828331351280212,
|
|
"num_tokens": 20318379.0,
|
|
"step": 10385
|
|
},
|
|
{
|
|
"entropy": 6.185838270187378,
|
|
"epoch": 1.0385864947268455,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004900929523886274,
|
|
"loss": 5.9431,
|
|
"mean_token_accuracy": 0.1534660667181015,
|
|
"num_tokens": 20328127.0,
|
|
"step": 10390
|
|
},
|
|
{
|
|
"entropy": 6.208504390716553,
|
|
"epoch": 1.0390863197880742,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.000490082476047949,
|
|
"loss": 6.0128,
|
|
"mean_token_accuracy": 0.15713909715414048,
|
|
"num_tokens": 20338562.0,
|
|
"step": 10395
|
|
},
|
|
{
|
|
"entropy": 6.223556089401245,
|
|
"epoch": 1.0395861448493027,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004900719942958506,
|
|
"loss": 5.9656,
|
|
"mean_token_accuracy": 0.15980771481990813,
|
|
"num_tokens": 20346984.0,
|
|
"step": 10400
|
|
},
|
|
{
|
|
"entropy": 6.175549173355103,
|
|
"epoch": 1.0400859699105314,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004900615071325963,
|
|
"loss": 5.9839,
|
|
"mean_token_accuracy": 0.15786415189504624,
|
|
"num_tokens": 20356666.0,
|
|
"step": 10405
|
|
},
|
|
{
|
|
"entropy": 6.2009861946105955,
|
|
"epoch": 1.0405857949717598,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.00049005101455845,
|
|
"loss": 5.9634,
|
|
"mean_token_accuracy": 0.15166688710451126,
|
|
"num_tokens": 20365834.0,
|
|
"step": 10410
|
|
},
|
|
{
|
|
"entropy": 6.219707012176514,
|
|
"epoch": 1.0410856200329885,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004900405165736753,
|
|
"loss": 6.0495,
|
|
"mean_token_accuracy": 0.1460423782467842,
|
|
"num_tokens": 20377184.0,
|
|
"step": 10415
|
|
},
|
|
{
|
|
"entropy": 6.1475263118743895,
|
|
"epoch": 1.041585445094217,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004900300131785365,
|
|
"loss": 5.9767,
|
|
"mean_token_accuracy": 0.15538606345653533,
|
|
"num_tokens": 20387059.0,
|
|
"step": 10420
|
|
},
|
|
{
|
|
"entropy": 6.238153600692749,
|
|
"epoch": 1.0420852701554455,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.000490019504373298,
|
|
"loss": 6.0851,
|
|
"mean_token_accuracy": 0.1474063776433468,
|
|
"num_tokens": 20397162.0,
|
|
"step": 10425
|
|
},
|
|
{
|
|
"entropy": 6.14004487991333,
|
|
"epoch": 1.0425850952166742,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004900089901582241,
|
|
"loss": 5.9125,
|
|
"mean_token_accuracy": 0.15710821002721786,
|
|
"num_tokens": 20407755.0,
|
|
"step": 10430
|
|
},
|
|
{
|
|
"entropy": 6.217952919006348,
|
|
"epoch": 1.0430849202779027,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004899984705335792,
|
|
"loss": 6.0208,
|
|
"mean_token_accuracy": 0.15002369731664658,
|
|
"num_tokens": 20417729.0,
|
|
"step": 10435
|
|
},
|
|
{
|
|
"entropy": 6.2227928161621096,
|
|
"epoch": 1.0435847453391314,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004899879454996282,
|
|
"loss": 6.018,
|
|
"mean_token_accuracy": 0.15074368119239806,
|
|
"num_tokens": 20428523.0,
|
|
"step": 10440
|
|
},
|
|
{
|
|
"entropy": 6.113245487213135,
|
|
"epoch": 1.0440845704003598,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004899774150566358,
|
|
"loss": 5.9576,
|
|
"mean_token_accuracy": 0.1617699906229973,
|
|
"num_tokens": 20438667.0,
|
|
"step": 10445
|
|
},
|
|
{
|
|
"entropy": 6.2017255306243895,
|
|
"epoch": 1.0445843954615885,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.000489966879204867,
|
|
"loss": 6.0098,
|
|
"mean_token_accuracy": 0.14654252529144288,
|
|
"num_tokens": 20449568.0,
|
|
"step": 10450
|
|
},
|
|
{
|
|
"entropy": 6.210640621185303,
|
|
"epoch": 1.045084220522817,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004899563379445869,
|
|
"loss": 5.9826,
|
|
"mean_token_accuracy": 0.15381477624177933,
|
|
"num_tokens": 20458665.0,
|
|
"step": 10455
|
|
},
|
|
{
|
|
"entropy": 6.176488447189331,
|
|
"epoch": 1.0455840455840455,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004899457912760605,
|
|
"loss": 5.9248,
|
|
"mean_token_accuracy": 0.1588617593050003,
|
|
"num_tokens": 20468587.0,
|
|
"step": 10460
|
|
},
|
|
{
|
|
"entropy": 6.173476934432983,
|
|
"epoch": 1.0460838706452742,
|
|
"grad_norm": 2.546875,
|
|
"learning_rate": 0.0004899352391995533,
|
|
"loss": 5.951,
|
|
"mean_token_accuracy": 0.15408904403448104,
|
|
"num_tokens": 20479186.0,
|
|
"step": 10465
|
|
},
|
|
{
|
|
"entropy": 6.28180079460144,
|
|
"epoch": 1.0465836957065027,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004899246817153309,
|
|
"loss": 6.054,
|
|
"mean_token_accuracy": 0.14951284378767013,
|
|
"num_tokens": 20488035.0,
|
|
"step": 10470
|
|
},
|
|
{
|
|
"entropy": 6.236543655395508,
|
|
"epoch": 1.0470835207677314,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004899141188236587,
|
|
"loss": 6.0141,
|
|
"mean_token_accuracy": 0.14833798184990882,
|
|
"num_tokens": 20498189.0,
|
|
"step": 10475
|
|
},
|
|
{
|
|
"entropy": 6.244407272338867,
|
|
"epoch": 1.0475833458289598,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004899035505248027,
|
|
"loss": 5.9661,
|
|
"mean_token_accuracy": 0.15517472326755524,
|
|
"num_tokens": 20508199.0,
|
|
"step": 10480
|
|
},
|
|
{
|
|
"entropy": 6.223096179962158,
|
|
"epoch": 1.0480831708901883,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004898929768190286,
|
|
"loss": 6.1192,
|
|
"mean_token_accuracy": 0.14485445469617844,
|
|
"num_tokens": 20517155.0,
|
|
"step": 10485
|
|
},
|
|
{
|
|
"entropy": 6.180911302566528,
|
|
"epoch": 1.048582995951417,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004898823977066024,
|
|
"loss": 5.9759,
|
|
"mean_token_accuracy": 0.155949904024601,
|
|
"num_tokens": 20526559.0,
|
|
"step": 10490
|
|
},
|
|
{
|
|
"entropy": 6.211443281173706,
|
|
"epoch": 1.0490828210126455,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004898718131877906,
|
|
"loss": 6.059,
|
|
"mean_token_accuracy": 0.14521945565938948,
|
|
"num_tokens": 20536299.0,
|
|
"step": 10495
|
|
},
|
|
{
|
|
"entropy": 6.166639709472657,
|
|
"epoch": 1.0495826460738742,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004898612232628591,
|
|
"loss": 5.8651,
|
|
"mean_token_accuracy": 0.1686046227812767,
|
|
"num_tokens": 20545290.0,
|
|
"step": 10500
|
|
},
|
|
{
|
|
"entropy": 6.227097749710083,
|
|
"epoch": 1.0500824711351027,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004898506279320745,
|
|
"loss": 5.9984,
|
|
"mean_token_accuracy": 0.15078563019633293,
|
|
"num_tokens": 20554691.0,
|
|
"step": 10505
|
|
},
|
|
{
|
|
"entropy": 6.168217563629151,
|
|
"epoch": 1.0505822961963314,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004898400271957034,
|
|
"loss": 6.0044,
|
|
"mean_token_accuracy": 0.1502242401242256,
|
|
"num_tokens": 20564595.0,
|
|
"step": 10510
|
|
},
|
|
{
|
|
"entropy": 6.148492622375488,
|
|
"epoch": 1.0510821212575598,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004898294210540126,
|
|
"loss": 5.9346,
|
|
"mean_token_accuracy": 0.15621903389692307,
|
|
"num_tokens": 20574174.0,
|
|
"step": 10515
|
|
},
|
|
{
|
|
"entropy": 6.212651681900025,
|
|
"epoch": 1.0515819463187883,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004898188095072688,
|
|
"loss": 5.9515,
|
|
"mean_token_accuracy": 0.16079924553632735,
|
|
"num_tokens": 20583666.0,
|
|
"step": 10520
|
|
},
|
|
{
|
|
"entropy": 6.260073328018189,
|
|
"epoch": 1.052081771380017,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.000489808192555739,
|
|
"loss": 6.0718,
|
|
"mean_token_accuracy": 0.14773667305707933,
|
|
"num_tokens": 20594040.0,
|
|
"step": 10525
|
|
},
|
|
{
|
|
"entropy": 6.239969968795776,
|
|
"epoch": 1.0525815964412455,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004897975701996903,
|
|
"loss": 6.0859,
|
|
"mean_token_accuracy": 0.1449655145406723,
|
|
"num_tokens": 20605329.0,
|
|
"step": 10530
|
|
},
|
|
{
|
|
"entropy": 6.113816165924073,
|
|
"epoch": 1.0530814215024742,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004897869424393902,
|
|
"loss": 5.9011,
|
|
"mean_token_accuracy": 0.15849124789237976,
|
|
"num_tokens": 20615107.0,
|
|
"step": 10535
|
|
},
|
|
{
|
|
"entropy": 6.148946714401245,
|
|
"epoch": 1.0535812465637027,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004897763092751057,
|
|
"loss": 5.943,
|
|
"mean_token_accuracy": 0.15736338645219802,
|
|
"num_tokens": 20624636.0,
|
|
"step": 10540
|
|
},
|
|
{
|
|
"entropy": 6.224472904205323,
|
|
"epoch": 1.0540810716249314,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004897656707071045,
|
|
"loss": 5.9333,
|
|
"mean_token_accuracy": 0.15725087225437165,
|
|
"num_tokens": 20634541.0,
|
|
"step": 10545
|
|
},
|
|
{
|
|
"entropy": 6.167675495147705,
|
|
"epoch": 1.0545808966861598,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004897550267356545,
|
|
"loss": 6.0043,
|
|
"mean_token_accuracy": 0.15720853358507156,
|
|
"num_tokens": 20644941.0,
|
|
"step": 10550
|
|
},
|
|
{
|
|
"entropy": 6.206024074554444,
|
|
"epoch": 1.0550807217473883,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004897443773610231,
|
|
"loss": 5.9177,
|
|
"mean_token_accuracy": 0.16083155423402787,
|
|
"num_tokens": 20653609.0,
|
|
"step": 10555
|
|
},
|
|
{
|
|
"entropy": 6.173372459411621,
|
|
"epoch": 1.055580546808617,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004897337225834785,
|
|
"loss": 5.9299,
|
|
"mean_token_accuracy": 0.15974637418985366,
|
|
"num_tokens": 20663302.0,
|
|
"step": 10560
|
|
},
|
|
{
|
|
"entropy": 6.085679197311402,
|
|
"epoch": 1.0560803718698455,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.0004897230624032888,
|
|
"loss": 5.8477,
|
|
"mean_token_accuracy": 0.16446128487586975,
|
|
"num_tokens": 20673785.0,
|
|
"step": 10565
|
|
},
|
|
{
|
|
"entropy": 6.16916971206665,
|
|
"epoch": 1.0565801969310742,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004897123968207219,
|
|
"loss": 5.9182,
|
|
"mean_token_accuracy": 0.15650865957140922,
|
|
"num_tokens": 20683156.0,
|
|
"step": 10570
|
|
},
|
|
{
|
|
"entropy": 6.206054067611694,
|
|
"epoch": 1.0570800219923027,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004897017258360465,
|
|
"loss": 6.0008,
|
|
"mean_token_accuracy": 0.15478356480598449,
|
|
"num_tokens": 20692153.0,
|
|
"step": 10575
|
|
},
|
|
{
|
|
"entropy": 6.216446590423584,
|
|
"epoch": 1.0575798470535314,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004896910494495308,
|
|
"loss": 6.0069,
|
|
"mean_token_accuracy": 0.154074514657259,
|
|
"num_tokens": 20702343.0,
|
|
"step": 10580
|
|
},
|
|
{
|
|
"entropy": 6.090823841094971,
|
|
"epoch": 1.0580796721147598,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004896803676614436,
|
|
"loss": 5.836,
|
|
"mean_token_accuracy": 0.17420537769794464,
|
|
"num_tokens": 20712866.0,
|
|
"step": 10585
|
|
},
|
|
{
|
|
"entropy": 6.191429710388183,
|
|
"epoch": 1.0585794971759883,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 0.0004896696804720536,
|
|
"loss": 6.1025,
|
|
"mean_token_accuracy": 0.14527041912078859,
|
|
"num_tokens": 20722679.0,
|
|
"step": 10590
|
|
},
|
|
{
|
|
"entropy": 6.277051115036011,
|
|
"epoch": 1.059079322237217,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004896589878816297,
|
|
"loss": 6.0793,
|
|
"mean_token_accuracy": 0.15211109071969986,
|
|
"num_tokens": 20732177.0,
|
|
"step": 10595
|
|
},
|
|
{
|
|
"entropy": 6.262920618057251,
|
|
"epoch": 1.0595791472984455,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004896482898904409,
|
|
"loss": 6.0768,
|
|
"mean_token_accuracy": 0.14589622914791106,
|
|
"num_tokens": 20742900.0,
|
|
"step": 10600
|
|
},
|
|
{
|
|
"entropy": 6.156751203536987,
|
|
"epoch": 1.0600789723596742,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004896375864987563,
|
|
"loss": 5.8896,
|
|
"mean_token_accuracy": 0.1574319362640381,
|
|
"num_tokens": 20752039.0,
|
|
"step": 10605
|
|
},
|
|
{
|
|
"entropy": 6.14383716583252,
|
|
"epoch": 1.0605787974209027,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004896268777068453,
|
|
"loss": 5.9322,
|
|
"mean_token_accuracy": 0.15913830548524857,
|
|
"num_tokens": 20760352.0,
|
|
"step": 10610
|
|
},
|
|
{
|
|
"entropy": 6.313779878616333,
|
|
"epoch": 1.0610786224821314,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004896161635149773,
|
|
"loss": 6.136,
|
|
"mean_token_accuracy": 0.1449337162077427,
|
|
"num_tokens": 20770038.0,
|
|
"step": 10615
|
|
},
|
|
{
|
|
"entropy": 6.149812698364258,
|
|
"epoch": 1.0615784475433598,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004896054439234217,
|
|
"loss": 5.899,
|
|
"mean_token_accuracy": 0.16779386401176452,
|
|
"num_tokens": 20779076.0,
|
|
"step": 10620
|
|
},
|
|
{
|
|
"entropy": 6.205066680908203,
|
|
"epoch": 1.0620782726045883,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004895947189324486,
|
|
"loss": 6.0226,
|
|
"mean_token_accuracy": 0.14764627516269685,
|
|
"num_tokens": 20789272.0,
|
|
"step": 10625
|
|
},
|
|
{
|
|
"entropy": 6.167108345031738,
|
|
"epoch": 1.062578097665817,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004895839885423273,
|
|
"loss": 5.994,
|
|
"mean_token_accuracy": 0.15537745207548143,
|
|
"num_tokens": 20799381.0,
|
|
"step": 10630
|
|
},
|
|
{
|
|
"entropy": 6.137248277664185,
|
|
"epoch": 1.0630779227270455,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004895732527533283,
|
|
"loss": 5.9129,
|
|
"mean_token_accuracy": 0.15839783921837808,
|
|
"num_tokens": 20809886.0,
|
|
"step": 10635
|
|
},
|
|
{
|
|
"entropy": 6.237708711624146,
|
|
"epoch": 1.0635777477882742,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004895625115657215,
|
|
"loss": 6.0272,
|
|
"mean_token_accuracy": 0.15324915051460267,
|
|
"num_tokens": 20819625.0,
|
|
"step": 10640
|
|
},
|
|
{
|
|
"entropy": 6.201759195327758,
|
|
"epoch": 1.0640775728495027,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.000489551764979777,
|
|
"loss": 5.979,
|
|
"mean_token_accuracy": 0.15168224275112152,
|
|
"num_tokens": 20829481.0,
|
|
"step": 10645
|
|
},
|
|
{
|
|
"entropy": 6.16482400894165,
|
|
"epoch": 1.0645773979107314,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004895410129957653,
|
|
"loss": 6.0045,
|
|
"mean_token_accuracy": 0.15040917173027993,
|
|
"num_tokens": 20840715.0,
|
|
"step": 10650
|
|
},
|
|
{
|
|
"entropy": 6.099859571456909,
|
|
"epoch": 1.0650772229719598,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004895302556139569,
|
|
"loss": 5.9922,
|
|
"mean_token_accuracy": 0.156874181330204,
|
|
"num_tokens": 20851334.0,
|
|
"step": 10655
|
|
},
|
|
{
|
|
"entropy": 6.211218166351318,
|
|
"epoch": 1.0655770480331883,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004895194928346226,
|
|
"loss": 5.9463,
|
|
"mean_token_accuracy": 0.1544322907924652,
|
|
"num_tokens": 20860357.0,
|
|
"step": 10660
|
|
},
|
|
{
|
|
"entropy": 6.198316669464111,
|
|
"epoch": 1.066076873094417,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.000489508724658033,
|
|
"loss": 6.0777,
|
|
"mean_token_accuracy": 0.14833938628435134,
|
|
"num_tokens": 20870360.0,
|
|
"step": 10665
|
|
},
|
|
{
|
|
"entropy": 6.25762619972229,
|
|
"epoch": 1.0665766981556455,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.000489497951084459,
|
|
"loss": 6.0167,
|
|
"mean_token_accuracy": 0.15636848658323288,
|
|
"num_tokens": 20880640.0,
|
|
"step": 10670
|
|
},
|
|
{
|
|
"entropy": 6.207287073135376,
|
|
"epoch": 1.0670765232168742,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004894871721141718,
|
|
"loss": 5.984,
|
|
"mean_token_accuracy": 0.15058879926800728,
|
|
"num_tokens": 20890524.0,
|
|
"step": 10675
|
|
},
|
|
{
|
|
"entropy": 6.165485954284668,
|
|
"epoch": 1.0675763482781027,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004894763877474426,
|
|
"loss": 5.9886,
|
|
"mean_token_accuracy": 0.1526798278093338,
|
|
"num_tokens": 20901469.0,
|
|
"step": 10680
|
|
},
|
|
{
|
|
"entropy": 6.1404252529144285,
|
|
"epoch": 1.0680761733393311,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004894655979845427,
|
|
"loss": 6.0336,
|
|
"mean_token_accuracy": 0.15069067627191543,
|
|
"num_tokens": 20910703.0,
|
|
"step": 10685
|
|
},
|
|
{
|
|
"entropy": 6.189463376998901,
|
|
"epoch": 1.0685759984005598,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004894548028257434,
|
|
"loss": 5.9625,
|
|
"mean_token_accuracy": 0.15357812792062758,
|
|
"num_tokens": 20920241.0,
|
|
"step": 10690
|
|
},
|
|
{
|
|
"entropy": 6.175825881958008,
|
|
"epoch": 1.0690758234617883,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004894440022713165,
|
|
"loss": 5.9953,
|
|
"mean_token_accuracy": 0.15783682316541672,
|
|
"num_tokens": 20930138.0,
|
|
"step": 10695
|
|
},
|
|
{
|
|
"entropy": 6.208317995071411,
|
|
"epoch": 1.069575648523017,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004894331963215337,
|
|
"loss": 5.9661,
|
|
"mean_token_accuracy": 0.15733662694692613,
|
|
"num_tokens": 20939592.0,
|
|
"step": 10700
|
|
},
|
|
{
|
|
"entropy": 6.177032327651977,
|
|
"epoch": 1.0700754735842455,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.000489422384976667,
|
|
"loss": 5.9618,
|
|
"mean_token_accuracy": 0.16215263307094574,
|
|
"num_tokens": 20948208.0,
|
|
"step": 10705
|
|
},
|
|
{
|
|
"entropy": 6.152873229980469,
|
|
"epoch": 1.0705752986454742,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004894115682369881,
|
|
"loss": 5.965,
|
|
"mean_token_accuracy": 0.155369308590889,
|
|
"num_tokens": 20958323.0,
|
|
"step": 10710
|
|
},
|
|
{
|
|
"entropy": 6.165218877792358,
|
|
"epoch": 1.0710751237067027,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004894007461027693,
|
|
"loss": 5.9414,
|
|
"mean_token_accuracy": 0.15968192964792252,
|
|
"num_tokens": 20967593.0,
|
|
"step": 10715
|
|
},
|
|
{
|
|
"entropy": 6.1513505458831785,
|
|
"epoch": 1.0715749487679311,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004893899185742828,
|
|
"loss": 5.9382,
|
|
"mean_token_accuracy": 0.15624755024909973,
|
|
"num_tokens": 20977236.0,
|
|
"step": 10720
|
|
},
|
|
{
|
|
"entropy": 6.1235023021698,
|
|
"epoch": 1.0720747738291598,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004893790856518014,
|
|
"loss": 6.0122,
|
|
"mean_token_accuracy": 0.15551438182592392,
|
|
"num_tokens": 20986346.0,
|
|
"step": 10725
|
|
},
|
|
{
|
|
"entropy": 6.096535158157349,
|
|
"epoch": 1.0725745988903883,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004893682473355972,
|
|
"loss": 5.8771,
|
|
"mean_token_accuracy": 0.164378722012043,
|
|
"num_tokens": 20995794.0,
|
|
"step": 10730
|
|
},
|
|
{
|
|
"entropy": 6.129690170288086,
|
|
"epoch": 1.073074423951617,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004893574036259432,
|
|
"loss": 5.8848,
|
|
"mean_token_accuracy": 0.15969372540712357,
|
|
"num_tokens": 21005133.0,
|
|
"step": 10735
|
|
},
|
|
{
|
|
"entropy": 6.183308029174805,
|
|
"epoch": 1.0735742490128455,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004893465545231119,
|
|
"loss": 6.0091,
|
|
"mean_token_accuracy": 0.15558296740055083,
|
|
"num_tokens": 21014445.0,
|
|
"step": 10740
|
|
},
|
|
{
|
|
"entropy": 6.107181167602539,
|
|
"epoch": 1.074074074074074,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004893357000273765,
|
|
"loss": 5.8958,
|
|
"mean_token_accuracy": 0.15392211303114892,
|
|
"num_tokens": 21023093.0,
|
|
"step": 10745
|
|
},
|
|
{
|
|
"entropy": 6.131949329376221,
|
|
"epoch": 1.0745738991353027,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00048932484013901,
|
|
"loss": 5.9758,
|
|
"mean_token_accuracy": 0.15346091389656066,
|
|
"num_tokens": 21031445.0,
|
|
"step": 10750
|
|
},
|
|
{
|
|
"entropy": 6.152755403518677,
|
|
"epoch": 1.0750737241965311,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004893139748582857,
|
|
"loss": 5.9546,
|
|
"mean_token_accuracy": 0.15513472855091096,
|
|
"num_tokens": 21041026.0,
|
|
"step": 10755
|
|
},
|
|
{
|
|
"entropy": 6.191868543624878,
|
|
"epoch": 1.0755735492577598,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.000489303104185477,
|
|
"loss": 5.9994,
|
|
"mean_token_accuracy": 0.15582500100135804,
|
|
"num_tokens": 21050665.0,
|
|
"step": 10760
|
|
},
|
|
{
|
|
"entropy": 6.122053718566894,
|
|
"epoch": 1.0760733743189883,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004892922281208573,
|
|
"loss": 5.9622,
|
|
"mean_token_accuracy": 0.1509912982583046,
|
|
"num_tokens": 21060470.0,
|
|
"step": 10765
|
|
},
|
|
{
|
|
"entropy": 6.257739162445068,
|
|
"epoch": 1.076573199380217,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004892813466647002,
|
|
"loss": 6.0881,
|
|
"mean_token_accuracy": 0.14919286593794823,
|
|
"num_tokens": 21070174.0,
|
|
"step": 10770
|
|
},
|
|
{
|
|
"entropy": 6.286755180358886,
|
|
"epoch": 1.0770730244414455,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004892704598172797,
|
|
"loss": 6.0849,
|
|
"mean_token_accuracy": 0.147285782545805,
|
|
"num_tokens": 21079686.0,
|
|
"step": 10775
|
|
},
|
|
{
|
|
"entropy": 6.276339292526245,
|
|
"epoch": 1.077572849502674,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004892595675788696,
|
|
"loss": 6.0283,
|
|
"mean_token_accuracy": 0.1505945973098278,
|
|
"num_tokens": 21089509.0,
|
|
"step": 10780
|
|
},
|
|
{
|
|
"entropy": 6.2047687530517575,
|
|
"epoch": 1.0780726745639027,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004892486699497439,
|
|
"loss": 6.0629,
|
|
"mean_token_accuracy": 0.14613900184631348,
|
|
"num_tokens": 21099992.0,
|
|
"step": 10785
|
|
},
|
|
{
|
|
"entropy": 6.196640062332153,
|
|
"epoch": 1.0785724996251311,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004892377669301766,
|
|
"loss": 5.9806,
|
|
"mean_token_accuracy": 0.1502140372991562,
|
|
"num_tokens": 21109593.0,
|
|
"step": 10790
|
|
},
|
|
{
|
|
"entropy": 6.214747905731201,
|
|
"epoch": 1.0790723246863598,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004892268585204423,
|
|
"loss": 5.9555,
|
|
"mean_token_accuracy": 0.15461448580026627,
|
|
"num_tokens": 21119837.0,
|
|
"step": 10795
|
|
},
|
|
{
|
|
"entropy": 6.230557203292847,
|
|
"epoch": 1.0795721497475883,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004892159447208154,
|
|
"loss": 6.0314,
|
|
"mean_token_accuracy": 0.1533092364668846,
|
|
"num_tokens": 21129908.0,
|
|
"step": 10800
|
|
},
|
|
{
|
|
"entropy": 6.182940101623535,
|
|
"epoch": 1.080071974808817,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004892050255315705,
|
|
"loss": 6.0394,
|
|
"mean_token_accuracy": 0.1535039946436882,
|
|
"num_tokens": 21140362.0,
|
|
"step": 10805
|
|
},
|
|
{
|
|
"entropy": 6.176079416275025,
|
|
"epoch": 1.0805717998700455,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004891941009529822,
|
|
"loss": 6.0191,
|
|
"mean_token_accuracy": 0.15578728914260864,
|
|
"num_tokens": 21151617.0,
|
|
"step": 10810
|
|
},
|
|
{
|
|
"entropy": 6.207557916641235,
|
|
"epoch": 1.081071624931274,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004891831709853255,
|
|
"loss": 5.9982,
|
|
"mean_token_accuracy": 0.1497117042541504,
|
|
"num_tokens": 21160736.0,
|
|
"step": 10815
|
|
},
|
|
{
|
|
"entropy": 6.051417636871338,
|
|
"epoch": 1.0815714499925027,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004891722356288752,
|
|
"loss": 5.9356,
|
|
"mean_token_accuracy": 0.15966171622276307,
|
|
"num_tokens": 21170311.0,
|
|
"step": 10820
|
|
},
|
|
{
|
|
"entropy": 6.105764865875244,
|
|
"epoch": 1.0820712750537311,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004891612948839068,
|
|
"loss": 5.9166,
|
|
"mean_token_accuracy": 0.1541769325733185,
|
|
"num_tokens": 21179732.0,
|
|
"step": 10825
|
|
},
|
|
{
|
|
"entropy": 6.186644411087036,
|
|
"epoch": 1.0825711001149598,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004891503487506951,
|
|
"loss": 5.9288,
|
|
"mean_token_accuracy": 0.1542472004890442,
|
|
"num_tokens": 21189600.0,
|
|
"step": 10830
|
|
},
|
|
{
|
|
"entropy": 6.243680143356324,
|
|
"epoch": 1.0830709251761883,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004891393972295159,
|
|
"loss": 5.9761,
|
|
"mean_token_accuracy": 0.1528242439031601,
|
|
"num_tokens": 21199016.0,
|
|
"step": 10835
|
|
},
|
|
{
|
|
"entropy": 6.146160650253296,
|
|
"epoch": 1.083570750237417,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004891284403206444,
|
|
"loss": 5.9792,
|
|
"mean_token_accuracy": 0.1563607394695282,
|
|
"num_tokens": 21208176.0,
|
|
"step": 10840
|
|
},
|
|
{
|
|
"entropy": 6.114896821975708,
|
|
"epoch": 1.0840705752986455,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004891174780243566,
|
|
"loss": 5.9194,
|
|
"mean_token_accuracy": 0.1608621172606945,
|
|
"num_tokens": 21217948.0,
|
|
"step": 10845
|
|
},
|
|
{
|
|
"entropy": 6.113623762130738,
|
|
"epoch": 1.084570400359874,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.000489106510340928,
|
|
"loss": 5.9065,
|
|
"mean_token_accuracy": 0.17097460627555847,
|
|
"num_tokens": 21227994.0,
|
|
"step": 10850
|
|
},
|
|
{
|
|
"entropy": 6.159657001495361,
|
|
"epoch": 1.0850702254211027,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004890955372706348,
|
|
"loss": 5.9294,
|
|
"mean_token_accuracy": 0.1630495309829712,
|
|
"num_tokens": 21237676.0,
|
|
"step": 10855
|
|
},
|
|
{
|
|
"entropy": 6.129100227355957,
|
|
"epoch": 1.0855700504823311,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004890845588137531,
|
|
"loss": 5.9007,
|
|
"mean_token_accuracy": 0.15763380229473115,
|
|
"num_tokens": 21248992.0,
|
|
"step": 10860
|
|
},
|
|
{
|
|
"entropy": 6.144695234298706,
|
|
"epoch": 1.0860698755435598,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004890735749705587,
|
|
"loss": 5.9705,
|
|
"mean_token_accuracy": 0.15795147344470023,
|
|
"num_tokens": 21258414.0,
|
|
"step": 10865
|
|
},
|
|
{
|
|
"entropy": 6.172103929519653,
|
|
"epoch": 1.0865697006047883,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004890625857413283,
|
|
"loss": 5.953,
|
|
"mean_token_accuracy": 0.1554660201072693,
|
|
"num_tokens": 21267687.0,
|
|
"step": 10870
|
|
},
|
|
{
|
|
"entropy": 6.184333848953247,
|
|
"epoch": 1.087069525666017,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004890515911263385,
|
|
"loss": 6.0041,
|
|
"mean_token_accuracy": 0.15596673488616944,
|
|
"num_tokens": 21277623.0,
|
|
"step": 10875
|
|
},
|
|
{
|
|
"entropy": 6.214262580871582,
|
|
"epoch": 1.0875693507272455,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004890405911258656,
|
|
"loss": 6.0632,
|
|
"mean_token_accuracy": 0.14790254086256027,
|
|
"num_tokens": 21288178.0,
|
|
"step": 10880
|
|
},
|
|
{
|
|
"entropy": 6.226759958267212,
|
|
"epoch": 1.088069175788474,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004890295857401866,
|
|
"loss": 5.988,
|
|
"mean_token_accuracy": 0.15190412253141403,
|
|
"num_tokens": 21298367.0,
|
|
"step": 10885
|
|
},
|
|
{
|
|
"entropy": 6.179524707794189,
|
|
"epoch": 1.0885690008497027,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.0004890185749695783,
|
|
"loss": 6.018,
|
|
"mean_token_accuracy": 0.15185327380895614,
|
|
"num_tokens": 21307475.0,
|
|
"step": 10890
|
|
},
|
|
{
|
|
"entropy": 6.194209814071655,
|
|
"epoch": 1.0890688259109311,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004890075588143176,
|
|
"loss": 6.0038,
|
|
"mean_token_accuracy": 0.14982156902551652,
|
|
"num_tokens": 21317715.0,
|
|
"step": 10895
|
|
},
|
|
{
|
|
"entropy": 6.171987915039063,
|
|
"epoch": 1.0895686509721598,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004889965372746819,
|
|
"loss": 6.046,
|
|
"mean_token_accuracy": 0.1440729543566704,
|
|
"num_tokens": 21327487.0,
|
|
"step": 10900
|
|
},
|
|
{
|
|
"entropy": 6.138454103469849,
|
|
"epoch": 1.0900684760333883,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004889855103509484,
|
|
"loss": 5.9496,
|
|
"mean_token_accuracy": 0.15668963491916657,
|
|
"num_tokens": 21337588.0,
|
|
"step": 10905
|
|
},
|
|
{
|
|
"entropy": 6.114659214019776,
|
|
"epoch": 1.090568301094617,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004889744780433944,
|
|
"loss": 5.8373,
|
|
"mean_token_accuracy": 0.16587060540914536,
|
|
"num_tokens": 21347037.0,
|
|
"step": 10910
|
|
},
|
|
{
|
|
"entropy": 6.092364358901977,
|
|
"epoch": 1.0910681261558455,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004889634403522976,
|
|
"loss": 6.0346,
|
|
"mean_token_accuracy": 0.15080819725990297,
|
|
"num_tokens": 21358784.0,
|
|
"step": 10915
|
|
},
|
|
{
|
|
"entropy": 6.179441833496094,
|
|
"epoch": 1.091567951217074,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004889523972779359,
|
|
"loss": 6.0012,
|
|
"mean_token_accuracy": 0.1521432429552078,
|
|
"num_tokens": 21368245.0,
|
|
"step": 10920
|
|
},
|
|
{
|
|
"entropy": 6.164575147628784,
|
|
"epoch": 1.0920677762783026,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004889413488205868,
|
|
"loss": 5.9383,
|
|
"mean_token_accuracy": 0.1602636493742466,
|
|
"num_tokens": 21377409.0,
|
|
"step": 10925
|
|
},
|
|
{
|
|
"entropy": 6.211748313903809,
|
|
"epoch": 1.0925676013395311,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004889302949805283,
|
|
"loss": 5.9395,
|
|
"mean_token_accuracy": 0.1582891032099724,
|
|
"num_tokens": 21388109.0,
|
|
"step": 10930
|
|
},
|
|
{
|
|
"entropy": 6.133979177474975,
|
|
"epoch": 1.0930674264007598,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004889192357580388,
|
|
"loss": 5.8426,
|
|
"mean_token_accuracy": 0.1629247024655342,
|
|
"num_tokens": 21396645.0,
|
|
"step": 10935
|
|
},
|
|
{
|
|
"entropy": 6.202014446258545,
|
|
"epoch": 1.0935672514619883,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004889081711533964,
|
|
"loss": 6.0632,
|
|
"mean_token_accuracy": 0.14829194620251657,
|
|
"num_tokens": 21407398.0,
|
|
"step": 10940
|
|
},
|
|
{
|
|
"entropy": 6.129686546325684,
|
|
"epoch": 1.0940670765232168,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004888971011668793,
|
|
"loss": 5.8757,
|
|
"mean_token_accuracy": 0.15977948531508446,
|
|
"num_tokens": 21417185.0,
|
|
"step": 10945
|
|
},
|
|
{
|
|
"entropy": 6.200656366348267,
|
|
"epoch": 1.0945669015844455,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004888860257987662,
|
|
"loss": 6.067,
|
|
"mean_token_accuracy": 0.14702474176883698,
|
|
"num_tokens": 21426743.0,
|
|
"step": 10950
|
|
},
|
|
{
|
|
"entropy": 6.163834047317505,
|
|
"epoch": 1.095066726645674,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004888749450493358,
|
|
"loss": 5.9904,
|
|
"mean_token_accuracy": 0.153190453350544,
|
|
"num_tokens": 21436528.0,
|
|
"step": 10955
|
|
},
|
|
{
|
|
"entropy": 6.124946546554566,
|
|
"epoch": 1.0955665517069026,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.0004888638589188669,
|
|
"loss": 5.9688,
|
|
"mean_token_accuracy": 0.1614849388599396,
|
|
"num_tokens": 21445286.0,
|
|
"step": 10960
|
|
},
|
|
{
|
|
"entropy": 6.249599027633667,
|
|
"epoch": 1.0960663767681311,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004888527674076382,
|
|
"loss": 6.1074,
|
|
"mean_token_accuracy": 0.15115003436803817,
|
|
"num_tokens": 21455695.0,
|
|
"step": 10965
|
|
},
|
|
{
|
|
"entropy": 6.2146913528442385,
|
|
"epoch": 1.0965662018293598,
|
|
"grad_norm": 6.0625,
|
|
"learning_rate": 0.000488841670515929,
|
|
"loss": 5.9652,
|
|
"mean_token_accuracy": 0.15328542068600653,
|
|
"num_tokens": 21465305.0,
|
|
"step": 10970
|
|
},
|
|
{
|
|
"entropy": 6.111506605148316,
|
|
"epoch": 1.0970660268905883,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004888305682440183,
|
|
"loss": 5.8667,
|
|
"mean_token_accuracy": 0.1672878496348858,
|
|
"num_tokens": 21475101.0,
|
|
"step": 10975
|
|
},
|
|
{
|
|
"entropy": 6.141602325439453,
|
|
"epoch": 1.0975658519518168,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004888194605921855,
|
|
"loss": 5.9257,
|
|
"mean_token_accuracy": 0.1610399529337883,
|
|
"num_tokens": 21484240.0,
|
|
"step": 10980
|
|
},
|
|
{
|
|
"entropy": 6.239077758789063,
|
|
"epoch": 1.0980656770130455,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004888083475607102,
|
|
"loss": 6.0302,
|
|
"mean_token_accuracy": 0.151107993721962,
|
|
"num_tokens": 21494700.0,
|
|
"step": 10985
|
|
},
|
|
{
|
|
"entropy": 6.094038200378418,
|
|
"epoch": 1.098565502074274,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004887972291498718,
|
|
"loss": 5.919,
|
|
"mean_token_accuracy": 0.15702562481164933,
|
|
"num_tokens": 21504418.0,
|
|
"step": 10990
|
|
},
|
|
{
|
|
"entropy": 6.207502317428589,
|
|
"epoch": 1.0990653271355026,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004887861053599503,
|
|
"loss": 5.9236,
|
|
"mean_token_accuracy": 0.15595513731241226,
|
|
"num_tokens": 21514019.0,
|
|
"step": 10995
|
|
},
|
|
{
|
|
"entropy": 6.174081325531006,
|
|
"epoch": 1.0995651521967311,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004887749761912252,
|
|
"loss": 5.9453,
|
|
"mean_token_accuracy": 0.15641257166862488,
|
|
"num_tokens": 21524279.0,
|
|
"step": 11000
|
|
},
|
|
{
|
|
"entropy": 6.2020337104797365,
|
|
"epoch": 1.1000649772579596,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004887638416439768,
|
|
"loss": 5.9632,
|
|
"mean_token_accuracy": 0.15037081837654115,
|
|
"num_tokens": 21533851.0,
|
|
"step": 11005
|
|
},
|
|
{
|
|
"entropy": 6.16806993484497,
|
|
"epoch": 1.1005648023191883,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004887527017184851,
|
|
"loss": 5.924,
|
|
"mean_token_accuracy": 0.1546926960349083,
|
|
"num_tokens": 21542589.0,
|
|
"step": 11010
|
|
},
|
|
{
|
|
"entropy": 6.166245985031128,
|
|
"epoch": 1.1010646273804168,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004887415564150305,
|
|
"loss": 5.9927,
|
|
"mean_token_accuracy": 0.15054001212120055,
|
|
"num_tokens": 21553018.0,
|
|
"step": 11015
|
|
},
|
|
{
|
|
"entropy": 6.267609882354736,
|
|
"epoch": 1.1015644524416455,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004887304057338934,
|
|
"loss": 6.1011,
|
|
"mean_token_accuracy": 0.14651739820837975,
|
|
"num_tokens": 21561830.0,
|
|
"step": 11020
|
|
},
|
|
{
|
|
"entropy": 6.239610910415649,
|
|
"epoch": 1.102064277502874,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.000488719249675354,
|
|
"loss": 5.9536,
|
|
"mean_token_accuracy": 0.1536804363131523,
|
|
"num_tokens": 21571126.0,
|
|
"step": 11025
|
|
},
|
|
{
|
|
"entropy": 6.110537815093994,
|
|
"epoch": 1.1025641025641026,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004887080882396936,
|
|
"loss": 5.9592,
|
|
"mean_token_accuracy": 0.16280061453580857,
|
|
"num_tokens": 21580771.0,
|
|
"step": 11030
|
|
},
|
|
{
|
|
"entropy": 6.194991540908814,
|
|
"epoch": 1.1030639276253311,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004886969214271925,
|
|
"loss": 6.0825,
|
|
"mean_token_accuracy": 0.1497802786529064,
|
|
"num_tokens": 21591687.0,
|
|
"step": 11035
|
|
},
|
|
{
|
|
"entropy": 6.169806623458863,
|
|
"epoch": 1.1035637526865596,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004886857492381319,
|
|
"loss": 5.9685,
|
|
"mean_token_accuracy": 0.15749285072088243,
|
|
"num_tokens": 21601056.0,
|
|
"step": 11040
|
|
},
|
|
{
|
|
"entropy": 6.153095388412476,
|
|
"epoch": 1.1040635777477883,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004886745716727928,
|
|
"loss": 5.948,
|
|
"mean_token_accuracy": 0.15879009515047074,
|
|
"num_tokens": 21610846.0,
|
|
"step": 11045
|
|
},
|
|
{
|
|
"entropy": 6.152535533905029,
|
|
"epoch": 1.1045634028090168,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004886633887314565,
|
|
"loss": 5.929,
|
|
"mean_token_accuracy": 0.1538671150803566,
|
|
"num_tokens": 21621504.0,
|
|
"step": 11050
|
|
},
|
|
{
|
|
"entropy": 6.1460926055908205,
|
|
"epoch": 1.1050632278702455,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004886522004144044,
|
|
"loss": 5.8941,
|
|
"mean_token_accuracy": 0.1651014119386673,
|
|
"num_tokens": 21631566.0,
|
|
"step": 11055
|
|
},
|
|
{
|
|
"entropy": 6.207142639160156,
|
|
"epoch": 1.105563052931474,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004886410067219178,
|
|
"loss": 5.9515,
|
|
"mean_token_accuracy": 0.1587765023112297,
|
|
"num_tokens": 21641392.0,
|
|
"step": 11060
|
|
},
|
|
{
|
|
"entropy": 6.1335869312286375,
|
|
"epoch": 1.1060628779927026,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004886298076542785,
|
|
"loss": 5.909,
|
|
"mean_token_accuracy": 0.16362943798303603,
|
|
"num_tokens": 21650356.0,
|
|
"step": 11065
|
|
},
|
|
{
|
|
"entropy": 6.18138017654419,
|
|
"epoch": 1.1065627030539311,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004886186032117682,
|
|
"loss": 6.0298,
|
|
"mean_token_accuracy": 0.1514166846871376,
|
|
"num_tokens": 21660704.0,
|
|
"step": 11070
|
|
},
|
|
{
|
|
"entropy": 6.198483610153199,
|
|
"epoch": 1.1070625281151596,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004886073933946688,
|
|
"loss": 5.9551,
|
|
"mean_token_accuracy": 0.15121551752090454,
|
|
"num_tokens": 21671002.0,
|
|
"step": 11075
|
|
},
|
|
{
|
|
"entropy": 6.121125268936157,
|
|
"epoch": 1.1075623531763883,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004885961782032624,
|
|
"loss": 5.9094,
|
|
"mean_token_accuracy": 0.16212226897478105,
|
|
"num_tokens": 21680802.0,
|
|
"step": 11080
|
|
},
|
|
{
|
|
"entropy": 6.103603553771973,
|
|
"epoch": 1.1080621782376168,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.000488584957637831,
|
|
"loss": 5.9135,
|
|
"mean_token_accuracy": 0.16017423272132875,
|
|
"num_tokens": 21690535.0,
|
|
"step": 11085
|
|
},
|
|
{
|
|
"entropy": 6.161426162719726,
|
|
"epoch": 1.1085620032988455,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004885737316986571,
|
|
"loss": 6.0137,
|
|
"mean_token_accuracy": 0.15026820525527002,
|
|
"num_tokens": 21700283.0,
|
|
"step": 11090
|
|
},
|
|
{
|
|
"entropy": 6.263440227508545,
|
|
"epoch": 1.109061828360074,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.000488562500386023,
|
|
"loss": 5.9578,
|
|
"mean_token_accuracy": 0.1532932013273239,
|
|
"num_tokens": 21709927.0,
|
|
"step": 11095
|
|
},
|
|
{
|
|
"entropy": 6.171089220046997,
|
|
"epoch": 1.1095616534213026,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004885512637002115,
|
|
"loss": 5.892,
|
|
"mean_token_accuracy": 0.16278183534741403,
|
|
"num_tokens": 21720011.0,
|
|
"step": 11100
|
|
},
|
|
{
|
|
"entropy": 6.138248157501221,
|
|
"epoch": 1.1100614784825311,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004885400216415051,
|
|
"loss": 6.0124,
|
|
"mean_token_accuracy": 0.1482589364051819,
|
|
"num_tokens": 21729456.0,
|
|
"step": 11105
|
|
},
|
|
{
|
|
"entropy": 6.25309476852417,
|
|
"epoch": 1.1105613035437596,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004885287742101865,
|
|
"loss": 6.0614,
|
|
"mean_token_accuracy": 0.15060478895902635,
|
|
"num_tokens": 21739341.0,
|
|
"step": 11110
|
|
},
|
|
{
|
|
"entropy": 6.265266466140747,
|
|
"epoch": 1.1110611286049883,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004885175214065392,
|
|
"loss": 6.0519,
|
|
"mean_token_accuracy": 0.1445502944290638,
|
|
"num_tokens": 21749549.0,
|
|
"step": 11115
|
|
},
|
|
{
|
|
"entropy": 6.207500743865967,
|
|
"epoch": 1.1115609536662168,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004885062632308457,
|
|
"loss": 5.938,
|
|
"mean_token_accuracy": 0.15182265043258666,
|
|
"num_tokens": 21760030.0,
|
|
"step": 11120
|
|
},
|
|
{
|
|
"entropy": 6.202724313735962,
|
|
"epoch": 1.1120607787274455,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004884949996833898,
|
|
"loss": 6.0307,
|
|
"mean_token_accuracy": 0.15140736252069473,
|
|
"num_tokens": 21769754.0,
|
|
"step": 11125
|
|
},
|
|
{
|
|
"entropy": 6.169153642654419,
|
|
"epoch": 1.112560603788674,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004884837307644545,
|
|
"loss": 6.0096,
|
|
"mean_token_accuracy": 0.1515662595629692,
|
|
"num_tokens": 21780248.0,
|
|
"step": 11130
|
|
},
|
|
{
|
|
"entropy": 6.148779201507568,
|
|
"epoch": 1.1130604288499026,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004884724564743236,
|
|
"loss": 5.9073,
|
|
"mean_token_accuracy": 0.16309308856725693,
|
|
"num_tokens": 21789014.0,
|
|
"step": 11135
|
|
},
|
|
{
|
|
"entropy": 6.12496509552002,
|
|
"epoch": 1.1135602539111311,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004884611768132805,
|
|
"loss": 5.9201,
|
|
"mean_token_accuracy": 0.15609773248434067,
|
|
"num_tokens": 21798210.0,
|
|
"step": 11140
|
|
},
|
|
{
|
|
"entropy": 6.127873659133911,
|
|
"epoch": 1.1140600789723596,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004884498917816092,
|
|
"loss": 5.9496,
|
|
"mean_token_accuracy": 0.15685731619596482,
|
|
"num_tokens": 21807947.0,
|
|
"step": 11145
|
|
},
|
|
{
|
|
"entropy": 6.15563588142395,
|
|
"epoch": 1.1145599040335883,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004884386013795935,
|
|
"loss": 5.995,
|
|
"mean_token_accuracy": 0.15536333695054055,
|
|
"num_tokens": 21816685.0,
|
|
"step": 11150
|
|
},
|
|
{
|
|
"entropy": 6.236415004730224,
|
|
"epoch": 1.1150597290948168,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004884273056075175,
|
|
"loss": 5.9608,
|
|
"mean_token_accuracy": 0.15593728125095369,
|
|
"num_tokens": 21826479.0,
|
|
"step": 11155
|
|
},
|
|
{
|
|
"entropy": 6.109762191772461,
|
|
"epoch": 1.1155595541560455,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004884160044656654,
|
|
"loss": 5.9672,
|
|
"mean_token_accuracy": 0.15251924693584443,
|
|
"num_tokens": 21837518.0,
|
|
"step": 11160
|
|
},
|
|
{
|
|
"entropy": 6.139361047744751,
|
|
"epoch": 1.116059379217274,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004884046979543217,
|
|
"loss": 5.8871,
|
|
"mean_token_accuracy": 0.15499355643987656,
|
|
"num_tokens": 21846069.0,
|
|
"step": 11165
|
|
},
|
|
{
|
|
"entropy": 6.2051229000091555,
|
|
"epoch": 1.1165592042785026,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004883933860737706,
|
|
"loss": 6.0897,
|
|
"mean_token_accuracy": 0.15541018843650817,
|
|
"num_tokens": 21855594.0,
|
|
"step": 11170
|
|
},
|
|
{
|
|
"entropy": 6.150937128067016,
|
|
"epoch": 1.1170590293397311,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004883820688242968,
|
|
"loss": 5.9701,
|
|
"mean_token_accuracy": 0.15113090425729753,
|
|
"num_tokens": 21864648.0,
|
|
"step": 11175
|
|
},
|
|
{
|
|
"entropy": 6.250085353851318,
|
|
"epoch": 1.1175588544009596,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004883707462061851,
|
|
"loss": 5.9985,
|
|
"mean_token_accuracy": 0.14634210839867592,
|
|
"num_tokens": 21875516.0,
|
|
"step": 11180
|
|
},
|
|
{
|
|
"entropy": 6.170653057098389,
|
|
"epoch": 1.1180586794621883,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004883594182197203,
|
|
"loss": 6.0051,
|
|
"mean_token_accuracy": 0.15406120121479033,
|
|
"num_tokens": 21885232.0,
|
|
"step": 11185
|
|
},
|
|
{
|
|
"entropy": 6.151582145690918,
|
|
"epoch": 1.1185585045234168,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004883480848651875,
|
|
"loss": 5.9497,
|
|
"mean_token_accuracy": 0.1579062432050705,
|
|
"num_tokens": 21895913.0,
|
|
"step": 11190
|
|
},
|
|
{
|
|
"entropy": 6.206772232055664,
|
|
"epoch": 1.1190583295846455,
|
|
"grad_norm": 1.9296875,
|
|
"learning_rate": 0.0004883367461428716,
|
|
"loss": 6.0344,
|
|
"mean_token_accuracy": 0.15026285350322724,
|
|
"num_tokens": 21906160.0,
|
|
"step": 11195
|
|
},
|
|
{
|
|
"entropy": 6.1354296684265135,
|
|
"epoch": 1.119558154645874,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004883254020530582,
|
|
"loss": 5.9039,
|
|
"mean_token_accuracy": 0.16246647089719773,
|
|
"num_tokens": 21915326.0,
|
|
"step": 11200
|
|
},
|
|
{
|
|
"entropy": 6.1779218196868895,
|
|
"epoch": 1.1200579797071024,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004883140525960327,
|
|
"loss": 5.9831,
|
|
"mean_token_accuracy": 0.15215202867984773,
|
|
"num_tokens": 21925804.0,
|
|
"step": 11205
|
|
},
|
|
{
|
|
"entropy": 6.193980550765991,
|
|
"epoch": 1.1205578047683311,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004883026977720803,
|
|
"loss": 5.8979,
|
|
"mean_token_accuracy": 0.1616089776158333,
|
|
"num_tokens": 21934226.0,
|
|
"step": 11210
|
|
},
|
|
{
|
|
"entropy": 6.047083520889283,
|
|
"epoch": 1.1210576298295596,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.000488291337581487,
|
|
"loss": 5.786,
|
|
"mean_token_accuracy": 0.17675856202840806,
|
|
"num_tokens": 21944068.0,
|
|
"step": 11215
|
|
},
|
|
{
|
|
"entropy": 6.168870306015014,
|
|
"epoch": 1.1215574548907883,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004882799720245385,
|
|
"loss": 6.0231,
|
|
"mean_token_accuracy": 0.15611078590154648,
|
|
"num_tokens": 21954509.0,
|
|
"step": 11220
|
|
},
|
|
{
|
|
"entropy": 6.177779817581177,
|
|
"epoch": 1.1220572799520168,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004882686011015208,
|
|
"loss": 6.0283,
|
|
"mean_token_accuracy": 0.14786954671144487,
|
|
"num_tokens": 21963753.0,
|
|
"step": 11225
|
|
},
|
|
{
|
|
"entropy": 6.165050840377807,
|
|
"epoch": 1.1225571050132455,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.00048825722481272006,
|
|
"loss": 5.97,
|
|
"mean_token_accuracy": 0.15491714999079703,
|
|
"num_tokens": 21973634.0,
|
|
"step": 11230
|
|
},
|
|
{
|
|
"entropy": 6.187585163116455,
|
|
"epoch": 1.123056930074474,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004882458431584223,
|
|
"loss": 6.0091,
|
|
"mean_token_accuracy": 0.15739966481924056,
|
|
"num_tokens": 21984029.0,
|
|
"step": 11235
|
|
},
|
|
{
|
|
"entropy": 6.16133942604065,
|
|
"epoch": 1.1235567551357024,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.0004882344561389141,
|
|
"loss": 6.0509,
|
|
"mean_token_accuracy": 0.15195800587534905,
|
|
"num_tokens": 21994270.0,
|
|
"step": 11240
|
|
},
|
|
{
|
|
"entropy": 6.318618488311768,
|
|
"epoch": 1.124056580196931,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.00048822306375448176,
|
|
"loss": 6.0697,
|
|
"mean_token_accuracy": 0.14534596353769302,
|
|
"num_tokens": 22002911.0,
|
|
"step": 11245
|
|
},
|
|
{
|
|
"entropy": 6.152344369888306,
|
|
"epoch": 1.1245564052581596,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004882116660054121,
|
|
"loss": 6.0296,
|
|
"mean_token_accuracy": 0.15108929127454757,
|
|
"num_tokens": 22012615.0,
|
|
"step": 11250
|
|
},
|
|
{
|
|
"entropy": 6.1539805889129635,
|
|
"epoch": 1.1250562303193883,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004882002628919917,
|
|
"loss": 6.0056,
|
|
"mean_token_accuracy": 0.15410257130861282,
|
|
"num_tokens": 22022274.0,
|
|
"step": 11255
|
|
},
|
|
{
|
|
"entropy": 6.140741014480591,
|
|
"epoch": 1.1255560553806168,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004881888544145076,
|
|
"loss": 5.8754,
|
|
"mean_token_accuracy": 0.15651678293943405,
|
|
"num_tokens": 22031238.0,
|
|
"step": 11260
|
|
},
|
|
{
|
|
"entropy": 6.146964836120605,
|
|
"epoch": 1.1260558804418452,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.00048817744057324673,
|
|
"loss": 5.9355,
|
|
"mean_token_accuracy": 0.15283789336681367,
|
|
"num_tokens": 22041003.0,
|
|
"step": 11265
|
|
},
|
|
{
|
|
"entropy": 6.0776032447814945,
|
|
"epoch": 1.126555705503074,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00048816602136849644,
|
|
"loss": 5.9292,
|
|
"mean_token_accuracy": 0.15870113000273706,
|
|
"num_tokens": 22050621.0,
|
|
"step": 11270
|
|
},
|
|
{
|
|
"entropy": 6.154777145385742,
|
|
"epoch": 1.1270555305643024,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.00048815459680054375,
|
|
"loss": 6.0131,
|
|
"mean_token_accuracy": 0.14526955634355546,
|
|
"num_tokens": 22060382.0,
|
|
"step": 11275
|
|
},
|
|
{
|
|
"entropy": 6.177711439132691,
|
|
"epoch": 1.127555355625531,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00048814316686967635,
|
|
"loss": 5.9604,
|
|
"mean_token_accuracy": 0.1567354157567024,
|
|
"num_tokens": 22069896.0,
|
|
"step": 11280
|
|
},
|
|
{
|
|
"entropy": 6.198789834976196,
|
|
"epoch": 1.1280551806867596,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004881317315761817,
|
|
"loss": 5.8908,
|
|
"mean_token_accuracy": 0.16615169793367385,
|
|
"num_tokens": 22080234.0,
|
|
"step": 11285
|
|
},
|
|
{
|
|
"entropy": 6.133270645141602,
|
|
"epoch": 1.1285550057479883,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00048812029092034747,
|
|
"loss": 6.0069,
|
|
"mean_token_accuracy": 0.15555982068181037,
|
|
"num_tokens": 22089866.0,
|
|
"step": 11290
|
|
},
|
|
{
|
|
"entropy": 6.116809701919555,
|
|
"epoch": 1.1290548308092168,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00048810884490246164,
|
|
"loss": 5.9464,
|
|
"mean_token_accuracy": 0.15819924473762512,
|
|
"num_tokens": 22100740.0,
|
|
"step": 11295
|
|
},
|
|
{
|
|
"entropy": 6.212266063690185,
|
|
"epoch": 1.1295546558704452,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.000488097393522812,
|
|
"loss": 5.9596,
|
|
"mean_token_accuracy": 0.15572836399078369,
|
|
"num_tokens": 22110519.0,
|
|
"step": 11300
|
|
},
|
|
{
|
|
"entropy": 6.074816608428955,
|
|
"epoch": 1.130054480931674,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004880859367816868,
|
|
"loss": 5.8915,
|
|
"mean_token_accuracy": 0.16337006241083146,
|
|
"num_tokens": 22119671.0,
|
|
"step": 11305
|
|
},
|
|
{
|
|
"entropy": 6.168532609939575,
|
|
"epoch": 1.1305543059929024,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004880744746793744,
|
|
"loss": 5.9533,
|
|
"mean_token_accuracy": 0.14340534657239914,
|
|
"num_tokens": 22130022.0,
|
|
"step": 11310
|
|
},
|
|
{
|
|
"entropy": 6.2538656234741214,
|
|
"epoch": 1.131054131054131,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00048806300721616295,
|
|
"loss": 6.0265,
|
|
"mean_token_accuracy": 0.1557791382074356,
|
|
"num_tokens": 22140875.0,
|
|
"step": 11315
|
|
},
|
|
{
|
|
"entropy": 6.235920095443726,
|
|
"epoch": 1.1315539561153596,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.00048805153439234107,
|
|
"loss": 5.9836,
|
|
"mean_token_accuracy": 0.1580161690711975,
|
|
"num_tokens": 22150144.0,
|
|
"step": 11320
|
|
},
|
|
{
|
|
"entropy": 6.10329122543335,
|
|
"epoch": 1.1320537811765883,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004880400562081974,
|
|
"loss": 5.9325,
|
|
"mean_token_accuracy": 0.16385404765605927,
|
|
"num_tokens": 22158951.0,
|
|
"step": 11325
|
|
},
|
|
{
|
|
"entropy": 6.061306476593018,
|
|
"epoch": 1.1325536062378168,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.00048802857266402075,
|
|
"loss": 5.9391,
|
|
"mean_token_accuracy": 0.15585393458604813,
|
|
"num_tokens": 22167458.0,
|
|
"step": 11330
|
|
},
|
|
{
|
|
"entropy": 6.118793392181397,
|
|
"epoch": 1.1330534312990452,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004880170837601,
|
|
"loss": 5.9046,
|
|
"mean_token_accuracy": 0.15917653292417527,
|
|
"num_tokens": 22176760.0,
|
|
"step": 11335
|
|
},
|
|
{
|
|
"entropy": 6.180065250396728,
|
|
"epoch": 1.133553256360274,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004880055894967242,
|
|
"loss": 5.9567,
|
|
"mean_token_accuracy": 0.15223372280597686,
|
|
"num_tokens": 22186476.0,
|
|
"step": 11340
|
|
},
|
|
{
|
|
"entropy": 6.086314868927002,
|
|
"epoch": 1.1340530814215024,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00048799408987418264,
|
|
"loss": 5.948,
|
|
"mean_token_accuracy": 0.1579450786113739,
|
|
"num_tokens": 22196420.0,
|
|
"step": 11345
|
|
},
|
|
{
|
|
"entropy": 6.120630168914795,
|
|
"epoch": 1.134552906482731,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.00048798258489276457,
|
|
"loss": 5.9755,
|
|
"mean_token_accuracy": 0.1537513867020607,
|
|
"num_tokens": 22204989.0,
|
|
"step": 11350
|
|
},
|
|
{
|
|
"entropy": 6.121804285049438,
|
|
"epoch": 1.1350527315439596,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004879710745527595,
|
|
"loss": 5.934,
|
|
"mean_token_accuracy": 0.15794263705611228,
|
|
"num_tokens": 22214831.0,
|
|
"step": 11355
|
|
},
|
|
{
|
|
"entropy": 6.270429039001465,
|
|
"epoch": 1.1355525566051883,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.00048795955885445696,
|
|
"loss": 6.0159,
|
|
"mean_token_accuracy": 0.15609221607446672,
|
|
"num_tokens": 22223772.0,
|
|
"step": 11360
|
|
},
|
|
{
|
|
"entropy": 6.1366418361663815,
|
|
"epoch": 1.1360523816664168,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004879480377981467,
|
|
"loss": 5.8898,
|
|
"mean_token_accuracy": 0.1610545590519905,
|
|
"num_tokens": 22231989.0,
|
|
"step": 11365
|
|
},
|
|
{
|
|
"entropy": 6.1556631565094,
|
|
"epoch": 1.1365522067276452,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.00048793651138411866,
|
|
"loss": 5.9214,
|
|
"mean_token_accuracy": 0.15981796383857727,
|
|
"num_tokens": 22241018.0,
|
|
"step": 11370
|
|
},
|
|
{
|
|
"entropy": 6.0874158382415775,
|
|
"epoch": 1.137052031788874,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00048792497961266273,
|
|
"loss": 5.9029,
|
|
"mean_token_accuracy": 0.15424375087022782,
|
|
"num_tokens": 22250575.0,
|
|
"step": 11375
|
|
},
|
|
{
|
|
"entropy": 6.121708822250366,
|
|
"epoch": 1.1375518568501024,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00048791344248406916,
|
|
"loss": 5.9929,
|
|
"mean_token_accuracy": 0.15789100676774978,
|
|
"num_tokens": 22259471.0,
|
|
"step": 11380
|
|
},
|
|
{
|
|
"entropy": 6.217072534561157,
|
|
"epoch": 1.138051681911331,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.00048790189999862814,
|
|
"loss": 5.9681,
|
|
"mean_token_accuracy": 0.1552117332816124,
|
|
"num_tokens": 22269402.0,
|
|
"step": 11385
|
|
},
|
|
{
|
|
"entropy": 6.152390098571777,
|
|
"epoch": 1.1385515069725596,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.00048789035215663013,
|
|
"loss": 6.0122,
|
|
"mean_token_accuracy": 0.151630799472332,
|
|
"num_tokens": 22279685.0,
|
|
"step": 11390
|
|
},
|
|
{
|
|
"entropy": 6.170343494415283,
|
|
"epoch": 1.1390513320337883,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.00048787879895836563,
|
|
"loss": 5.9357,
|
|
"mean_token_accuracy": 0.15431418418884277,
|
|
"num_tokens": 22288628.0,
|
|
"step": 11395
|
|
},
|
|
{
|
|
"entropy": 6.229870986938477,
|
|
"epoch": 1.1395511570950168,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004878672404041253,
|
|
"loss": 5.9597,
|
|
"mean_token_accuracy": 0.15678505897521972,
|
|
"num_tokens": 22297762.0,
|
|
"step": 11400
|
|
},
|
|
{
|
|
"entropy": 6.208660221099853,
|
|
"epoch": 1.1400509821562452,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00048785567649419994,
|
|
"loss": 6.1304,
|
|
"mean_token_accuracy": 0.14967557042837143,
|
|
"num_tokens": 22307838.0,
|
|
"step": 11405
|
|
},
|
|
{
|
|
"entropy": 6.124197578430175,
|
|
"epoch": 1.140550807217474,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004878441072288806,
|
|
"loss": 5.9103,
|
|
"mean_token_accuracy": 0.1615430399775505,
|
|
"num_tokens": 22317553.0,
|
|
"step": 11410
|
|
},
|
|
{
|
|
"entropy": 6.112193632125854,
|
|
"epoch": 1.1410506322787024,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00048783253260845826,
|
|
"loss": 5.8345,
|
|
"mean_token_accuracy": 0.16616780012845994,
|
|
"num_tokens": 22327892.0,
|
|
"step": 11415
|
|
},
|
|
{
|
|
"entropy": 6.13757734298706,
|
|
"epoch": 1.141550457339931,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004878209526332242,
|
|
"loss": 5.922,
|
|
"mean_token_accuracy": 0.16156515702605248,
|
|
"num_tokens": 22338363.0,
|
|
"step": 11420
|
|
},
|
|
{
|
|
"entropy": 6.150075817108155,
|
|
"epoch": 1.1420502824011596,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.00048780936730346967,
|
|
"loss": 5.915,
|
|
"mean_token_accuracy": 0.15303796753287316,
|
|
"num_tokens": 22347645.0,
|
|
"step": 11425
|
|
},
|
|
{
|
|
"entropy": 6.15480899810791,
|
|
"epoch": 1.1425501074623883,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00048779777661948627,
|
|
"loss": 5.9766,
|
|
"mean_token_accuracy": 0.15863730162382125,
|
|
"num_tokens": 22356906.0,
|
|
"step": 11430
|
|
},
|
|
{
|
|
"entropy": 6.122133827209472,
|
|
"epoch": 1.1430499325236168,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004877861805815655,
|
|
"loss": 5.9222,
|
|
"mean_token_accuracy": 0.1561330460011959,
|
|
"num_tokens": 22365806.0,
|
|
"step": 11435
|
|
},
|
|
{
|
|
"entropy": 6.0671271800994875,
|
|
"epoch": 1.1435497575848452,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004877745791899993,
|
|
"loss": 5.8228,
|
|
"mean_token_accuracy": 0.16571658253669738,
|
|
"num_tokens": 22374752.0,
|
|
"step": 11440
|
|
},
|
|
{
|
|
"entropy": 6.1428862571716305,
|
|
"epoch": 1.144049582646074,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00048776297244507936,
|
|
"loss": 5.8945,
|
|
"mean_token_accuracy": 0.15657515674829484,
|
|
"num_tokens": 22383280.0,
|
|
"step": 11445
|
|
},
|
|
{
|
|
"entropy": 6.165312623977661,
|
|
"epoch": 1.1445494077073024,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.00048775136034709784,
|
|
"loss": 5.9955,
|
|
"mean_token_accuracy": 0.15749927014112472,
|
|
"num_tokens": 22393873.0,
|
|
"step": 11450
|
|
},
|
|
{
|
|
"entropy": 6.163510656356811,
|
|
"epoch": 1.145049232768531,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.00048773974289634676,
|
|
"loss": 5.9035,
|
|
"mean_token_accuracy": 0.158704175055027,
|
|
"num_tokens": 22404880.0,
|
|
"step": 11455
|
|
},
|
|
{
|
|
"entropy": 6.19859766960144,
|
|
"epoch": 1.1455490578297596,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004877281200931185,
|
|
"loss": 6.0206,
|
|
"mean_token_accuracy": 0.14970198422670364,
|
|
"num_tokens": 22414848.0,
|
|
"step": 11460
|
|
},
|
|
{
|
|
"entropy": 6.160959148406983,
|
|
"epoch": 1.1460488828909883,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00048771649193770554,
|
|
"loss": 5.9725,
|
|
"mean_token_accuracy": 0.15001334100961686,
|
|
"num_tokens": 22425377.0,
|
|
"step": 11465
|
|
},
|
|
{
|
|
"entropy": 6.2000030994415285,
|
|
"epoch": 1.1465487079522168,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004877048584304004,
|
|
"loss": 5.9616,
|
|
"mean_token_accuracy": 0.15394231602549552,
|
|
"num_tokens": 22435787.0,
|
|
"step": 11470
|
|
},
|
|
{
|
|
"entropy": 6.257690572738648,
|
|
"epoch": 1.1470485330134452,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00048769321957149557,
|
|
"loss": 6.1308,
|
|
"mean_token_accuracy": 0.1421785295009613,
|
|
"num_tokens": 22446540.0,
|
|
"step": 11475
|
|
},
|
|
{
|
|
"entropy": 6.150134801864624,
|
|
"epoch": 1.147548358074674,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004876815753612843,
|
|
"loss": 5.946,
|
|
"mean_token_accuracy": 0.15582237839698793,
|
|
"num_tokens": 22456170.0,
|
|
"step": 11480
|
|
},
|
|
{
|
|
"entropy": 6.17533507347107,
|
|
"epoch": 1.1480481831359024,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004876699258000592,
|
|
"loss": 5.9736,
|
|
"mean_token_accuracy": 0.1515693411231041,
|
|
"num_tokens": 22464502.0,
|
|
"step": 11485
|
|
},
|
|
{
|
|
"entropy": 6.2002216339111325,
|
|
"epoch": 1.148548008197131,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004876582708881135,
|
|
"loss": 6.0029,
|
|
"mean_token_accuracy": 0.1539310559630394,
|
|
"num_tokens": 22475093.0,
|
|
"step": 11490
|
|
},
|
|
{
|
|
"entropy": 6.204256629943847,
|
|
"epoch": 1.1490478332583596,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004876466106257404,
|
|
"loss": 6.019,
|
|
"mean_token_accuracy": 0.1511889174580574,
|
|
"num_tokens": 22484229.0,
|
|
"step": 11495
|
|
},
|
|
{
|
|
"entropy": 6.256861829757691,
|
|
"epoch": 1.149547658319588,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.00048763494501323333,
|
|
"loss": 6.0411,
|
|
"mean_token_accuracy": 0.15025287568569184,
|
|
"num_tokens": 22493979.0,
|
|
"step": 11500
|
|
},
|
|
{
|
|
"entropy": 6.237468004226685,
|
|
"epoch": 1.1500474833808167,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00048762327405088573,
|
|
"loss": 5.989,
|
|
"mean_token_accuracy": 0.15696250796318054,
|
|
"num_tokens": 22504675.0,
|
|
"step": 11505
|
|
},
|
|
{
|
|
"entropy": 6.1411888122558596,
|
|
"epoch": 1.1505473084420452,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004876115977389913,
|
|
"loss": 5.937,
|
|
"mean_token_accuracy": 0.16081333607435228,
|
|
"num_tokens": 22514407.0,
|
|
"step": 11510
|
|
},
|
|
{
|
|
"entropy": 6.194857406616211,
|
|
"epoch": 1.151047133503274,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00048759991607784375,
|
|
"loss": 6.0247,
|
|
"mean_token_accuracy": 0.15047699809074402,
|
|
"num_tokens": 22524234.0,
|
|
"step": 11515
|
|
},
|
|
{
|
|
"entropy": 6.11414155960083,
|
|
"epoch": 1.1515469585645024,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00048758822906773706,
|
|
"loss": 5.8637,
|
|
"mean_token_accuracy": 0.16002584546804427,
|
|
"num_tokens": 22534004.0,
|
|
"step": 11520
|
|
},
|
|
{
|
|
"entropy": 6.186272096633911,
|
|
"epoch": 1.1520467836257309,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.00048757653670896523,
|
|
"loss": 6.0321,
|
|
"mean_token_accuracy": 0.16344474107027054,
|
|
"num_tokens": 22543926.0,
|
|
"step": 11525
|
|
},
|
|
{
|
|
"entropy": 6.203880691528321,
|
|
"epoch": 1.1525466086869596,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004875648390018224,
|
|
"loss": 5.9611,
|
|
"mean_token_accuracy": 0.16035965383052825,
|
|
"num_tokens": 22553671.0,
|
|
"step": 11530
|
|
},
|
|
{
|
|
"entropy": 6.146420812606811,
|
|
"epoch": 1.153046433748188,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.000487553135946603,
|
|
"loss": 5.9182,
|
|
"mean_token_accuracy": 0.1558047965168953,
|
|
"num_tokens": 22562503.0,
|
|
"step": 11535
|
|
},
|
|
{
|
|
"entropy": 6.2046802043914795,
|
|
"epoch": 1.1535462588094167,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00048754142754360135,
|
|
"loss": 5.9458,
|
|
"mean_token_accuracy": 0.1544528529047966,
|
|
"num_tokens": 22572555.0,
|
|
"step": 11540
|
|
},
|
|
{
|
|
"entropy": 6.2499706745147705,
|
|
"epoch": 1.1540460838706452,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004875297137931121,
|
|
"loss": 6.0325,
|
|
"mean_token_accuracy": 0.1516187831759453,
|
|
"num_tokens": 22583720.0,
|
|
"step": 11545
|
|
},
|
|
{
|
|
"entropy": 6.164298677444458,
|
|
"epoch": 1.154545908931874,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004875179946954298,
|
|
"loss": 5.9787,
|
|
"mean_token_accuracy": 0.1521018013358116,
|
|
"num_tokens": 22593373.0,
|
|
"step": 11550
|
|
},
|
|
{
|
|
"entropy": 6.18038420677185,
|
|
"epoch": 1.1550457339931024,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00048750627025084955,
|
|
"loss": 5.9081,
|
|
"mean_token_accuracy": 0.1573541522026062,
|
|
"num_tokens": 22604229.0,
|
|
"step": 11555
|
|
},
|
|
{
|
|
"entropy": 6.172487592697143,
|
|
"epoch": 1.1555455590543309,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004874945404596662,
|
|
"loss": 5.8722,
|
|
"mean_token_accuracy": 0.16478561013936996,
|
|
"num_tokens": 22613451.0,
|
|
"step": 11560
|
|
},
|
|
{
|
|
"entropy": 6.132219648361206,
|
|
"epoch": 1.1560453841155596,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00048748280532217485,
|
|
"loss": 6.0671,
|
|
"mean_token_accuracy": 0.14978796392679214,
|
|
"num_tokens": 22622809.0,
|
|
"step": 11565
|
|
},
|
|
{
|
|
"entropy": 6.21790566444397,
|
|
"epoch": 1.156545209176788,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004874710648386709,
|
|
"loss": 6.0349,
|
|
"mean_token_accuracy": 0.14883778393268585,
|
|
"num_tokens": 22633121.0,
|
|
"step": 11570
|
|
},
|
|
{
|
|
"entropy": 6.207902908325195,
|
|
"epoch": 1.1570450342380167,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004874593190094496,
|
|
"loss": 5.977,
|
|
"mean_token_accuracy": 0.1548261061310768,
|
|
"num_tokens": 22642346.0,
|
|
"step": 11575
|
|
},
|
|
{
|
|
"entropy": 6.162228155136108,
|
|
"epoch": 1.1575448592992452,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004874475678348065,
|
|
"loss": 5.9194,
|
|
"mean_token_accuracy": 0.1591774970293045,
|
|
"num_tokens": 22653157.0,
|
|
"step": 11580
|
|
},
|
|
{
|
|
"entropy": 6.172361612319946,
|
|
"epoch": 1.158044684360474,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.00048743581131503716,
|
|
"loss": 5.9909,
|
|
"mean_token_accuracy": 0.15582970380783082,
|
|
"num_tokens": 22663841.0,
|
|
"step": 11585
|
|
},
|
|
{
|
|
"entropy": 6.320128440856934,
|
|
"epoch": 1.1585445094217024,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004874240494504376,
|
|
"loss": 6.0651,
|
|
"mean_token_accuracy": 0.15741583704948425,
|
|
"num_tokens": 22674242.0,
|
|
"step": 11590
|
|
},
|
|
{
|
|
"entropy": 6.120945310592651,
|
|
"epoch": 1.1590443344829309,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00048741228224130357,
|
|
"loss": 5.891,
|
|
"mean_token_accuracy": 0.16382880061864852,
|
|
"num_tokens": 22683371.0,
|
|
"step": 11595
|
|
},
|
|
{
|
|
"entropy": 6.130554676055908,
|
|
"epoch": 1.1595441595441596,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00048740050968793116,
|
|
"loss": 5.9234,
|
|
"mean_token_accuracy": 0.15389275550842285,
|
|
"num_tokens": 22693767.0,
|
|
"step": 11600
|
|
},
|
|
{
|
|
"entropy": 6.157484483718872,
|
|
"epoch": 1.160043984605388,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004873887317906166,
|
|
"loss": 5.9831,
|
|
"mean_token_accuracy": 0.15227321088314055,
|
|
"num_tokens": 22705108.0,
|
|
"step": 11605
|
|
},
|
|
{
|
|
"entropy": 6.204415512084961,
|
|
"epoch": 1.1605438096666167,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00048737694854965617,
|
|
"loss": 5.8975,
|
|
"mean_token_accuracy": 0.1590589240193367,
|
|
"num_tokens": 22715244.0,
|
|
"step": 11610
|
|
},
|
|
{
|
|
"entropy": 6.136318302154541,
|
|
"epoch": 1.1610436347278452,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00048736515996534644,
|
|
"loss": 5.8802,
|
|
"mean_token_accuracy": 0.1690744325518608,
|
|
"num_tokens": 22724519.0,
|
|
"step": 11615
|
|
},
|
|
{
|
|
"entropy": 6.034622764587402,
|
|
"epoch": 1.161543459789074,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004873533660379839,
|
|
"loss": 5.8388,
|
|
"mean_token_accuracy": 0.16576862186193467,
|
|
"num_tokens": 22733847.0,
|
|
"step": 11620
|
|
},
|
|
{
|
|
"entropy": 6.082125616073609,
|
|
"epoch": 1.1620432848503024,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.00048734156676786525,
|
|
"loss": 5.9044,
|
|
"mean_token_accuracy": 0.15905808061361312,
|
|
"num_tokens": 22743023.0,
|
|
"step": 11625
|
|
},
|
|
{
|
|
"entropy": 6.155583667755127,
|
|
"epoch": 1.1625431099115309,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004873297621552875,
|
|
"loss": 5.9702,
|
|
"mean_token_accuracy": 0.15693069845438004,
|
|
"num_tokens": 22754101.0,
|
|
"step": 11630
|
|
},
|
|
{
|
|
"entropy": 6.153883361816407,
|
|
"epoch": 1.1630429349727596,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00048731795220054755,
|
|
"loss": 5.9143,
|
|
"mean_token_accuracy": 0.15300537794828414,
|
|
"num_tokens": 22763815.0,
|
|
"step": 11635
|
|
},
|
|
{
|
|
"entropy": 6.141056251525879,
|
|
"epoch": 1.163542760033988,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004873061369039425,
|
|
"loss": 6.0335,
|
|
"mean_token_accuracy": 0.1516496606171131,
|
|
"num_tokens": 22774041.0,
|
|
"step": 11640
|
|
},
|
|
{
|
|
"entropy": 6.204327249526978,
|
|
"epoch": 1.1640425850952167,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004872943162657697,
|
|
"loss": 6.0123,
|
|
"mean_token_accuracy": 0.16086317598819733,
|
|
"num_tokens": 22784046.0,
|
|
"step": 11645
|
|
},
|
|
{
|
|
"entropy": 6.249092435836792,
|
|
"epoch": 1.1645424101564452,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004872824902863265,
|
|
"loss": 6.0314,
|
|
"mean_token_accuracy": 0.1481860026717186,
|
|
"num_tokens": 22794316.0,
|
|
"step": 11650
|
|
},
|
|
{
|
|
"entropy": 6.1565898895263675,
|
|
"epoch": 1.165042235217674,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004872706589659106,
|
|
"loss": 5.9171,
|
|
"mean_token_accuracy": 0.16067816466093063,
|
|
"num_tokens": 22805185.0,
|
|
"step": 11655
|
|
},
|
|
{
|
|
"entropy": 6.132637405395508,
|
|
"epoch": 1.1655420602789024,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00048725882230481947,
|
|
"loss": 6.0076,
|
|
"mean_token_accuracy": 0.1558746039867401,
|
|
"num_tokens": 22815336.0,
|
|
"step": 11660
|
|
},
|
|
{
|
|
"entropy": 6.207607316970825,
|
|
"epoch": 1.1660418853401309,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.00048724698030335096,
|
|
"loss": 6.0496,
|
|
"mean_token_accuracy": 0.15027876570820808,
|
|
"num_tokens": 22825530.0,
|
|
"step": 11665
|
|
},
|
|
{
|
|
"entropy": 6.167031574249267,
|
|
"epoch": 1.1665417104013596,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004872351329618031,
|
|
"loss": 5.8551,
|
|
"mean_token_accuracy": 0.1735166698694229,
|
|
"num_tokens": 22834194.0,
|
|
"step": 11670
|
|
},
|
|
{
|
|
"entropy": 6.179953861236572,
|
|
"epoch": 1.167041535462588,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00048722328028047386,
|
|
"loss": 6.0446,
|
|
"mean_token_accuracy": 0.14853890910744666,
|
|
"num_tokens": 22844688.0,
|
|
"step": 11675
|
|
},
|
|
{
|
|
"entropy": 6.223675060272217,
|
|
"epoch": 1.1675413605238167,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.00048721142225966146,
|
|
"loss": 6.0334,
|
|
"mean_token_accuracy": 0.1501857616007328,
|
|
"num_tokens": 22855239.0,
|
|
"step": 11680
|
|
},
|
|
{
|
|
"entropy": 6.091694021224976,
|
|
"epoch": 1.1680411855850452,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004871995588996644,
|
|
"loss": 5.8221,
|
|
"mean_token_accuracy": 0.16536771059036254,
|
|
"num_tokens": 22866248.0,
|
|
"step": 11685
|
|
},
|
|
{
|
|
"entropy": 6.125625944137573,
|
|
"epoch": 1.168541010646274,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004871876902007809,
|
|
"loss": 5.9786,
|
|
"mean_token_accuracy": 0.15631398260593415,
|
|
"num_tokens": 22876119.0,
|
|
"step": 11690
|
|
},
|
|
{
|
|
"entropy": 6.1542541027069095,
|
|
"epoch": 1.1690408357075024,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00048717581616330985,
|
|
"loss": 5.8895,
|
|
"mean_token_accuracy": 0.1662924036383629,
|
|
"num_tokens": 22885854.0,
|
|
"step": 11695
|
|
},
|
|
{
|
|
"entropy": 6.202460718154907,
|
|
"epoch": 1.1695406607687309,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00048716393678754975,
|
|
"loss": 6.0112,
|
|
"mean_token_accuracy": 0.1531591981649399,
|
|
"num_tokens": 22895544.0,
|
|
"step": 11700
|
|
},
|
|
{
|
|
"entropy": 6.215129756927491,
|
|
"epoch": 1.1700404858299596,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004871520520737996,
|
|
"loss": 6.0203,
|
|
"mean_token_accuracy": 0.1494310110807419,
|
|
"num_tokens": 22904608.0,
|
|
"step": 11705
|
|
},
|
|
{
|
|
"entropy": 6.18988265991211,
|
|
"epoch": 1.170540310891188,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004871401620223585,
|
|
"loss": 6.0019,
|
|
"mean_token_accuracy": 0.16044313013553618,
|
|
"num_tokens": 22914716.0,
|
|
"step": 11710
|
|
},
|
|
{
|
|
"entropy": 6.247105264663697,
|
|
"epoch": 1.1710401359524167,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004871282666335255,
|
|
"loss": 6.0721,
|
|
"mean_token_accuracy": 0.14879173710942267,
|
|
"num_tokens": 22925466.0,
|
|
"step": 11715
|
|
},
|
|
{
|
|
"entropy": 6.110837841033936,
|
|
"epoch": 1.1715399610136452,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00048711636590759985,
|
|
"loss": 5.9501,
|
|
"mean_token_accuracy": 0.15398866906762124,
|
|
"num_tokens": 22934499.0,
|
|
"step": 11720
|
|
},
|
|
{
|
|
"entropy": 6.146024322509765,
|
|
"epoch": 1.172039786074874,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00048710445984488106,
|
|
"loss": 5.9468,
|
|
"mean_token_accuracy": 0.15472581833600998,
|
|
"num_tokens": 22943822.0,
|
|
"step": 11725
|
|
},
|
|
{
|
|
"entropy": 6.102200269699097,
|
|
"epoch": 1.1725396111361024,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004870925484456686,
|
|
"loss": 5.9651,
|
|
"mean_token_accuracy": 0.15842757895588874,
|
|
"num_tokens": 22952375.0,
|
|
"step": 11730
|
|
},
|
|
{
|
|
"entropy": 6.163388967514038,
|
|
"epoch": 1.1730394361973309,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004870806317102622,
|
|
"loss": 5.9631,
|
|
"mean_token_accuracy": 0.15419413149356842,
|
|
"num_tokens": 22961945.0,
|
|
"step": 11735
|
|
},
|
|
{
|
|
"entropy": 6.23486738204956,
|
|
"epoch": 1.1735392612585596,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004870687096389617,
|
|
"loss": 6.0773,
|
|
"mean_token_accuracy": 0.15317733585834503,
|
|
"num_tokens": 22972029.0,
|
|
"step": 11740
|
|
},
|
|
{
|
|
"entropy": 6.223558568954468,
|
|
"epoch": 1.174039086319788,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.000487056782232067,
|
|
"loss": 5.9731,
|
|
"mean_token_accuracy": 0.15458502024412155,
|
|
"num_tokens": 22980954.0,
|
|
"step": 11745
|
|
},
|
|
{
|
|
"entropy": 6.1261388778686525,
|
|
"epoch": 1.1745389113810167,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00048704484948987824,
|
|
"loss": 5.9165,
|
|
"mean_token_accuracy": 0.1554683819413185,
|
|
"num_tokens": 22991213.0,
|
|
"step": 11750
|
|
},
|
|
{
|
|
"entropy": 6.160103368759155,
|
|
"epoch": 1.1750387364422452,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004870329114126956,
|
|
"loss": 5.9331,
|
|
"mean_token_accuracy": 0.15347087979316712,
|
|
"num_tokens": 23000833.0,
|
|
"step": 11755
|
|
},
|
|
{
|
|
"entropy": 6.233826971054077,
|
|
"epoch": 1.1755385615034737,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004870209680008196,
|
|
"loss": 6.0181,
|
|
"mean_token_accuracy": 0.15664072781801225,
|
|
"num_tokens": 23010598.0,
|
|
"step": 11760
|
|
},
|
|
{
|
|
"entropy": 6.191549396514892,
|
|
"epoch": 1.1760383865647024,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004870090192545505,
|
|
"loss": 5.9955,
|
|
"mean_token_accuracy": 0.14790518060326577,
|
|
"num_tokens": 23019929.0,
|
|
"step": 11765
|
|
},
|
|
{
|
|
"entropy": 6.118762683868408,
|
|
"epoch": 1.1765382116259309,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.000486997065174189,
|
|
"loss": 5.9078,
|
|
"mean_token_accuracy": 0.15689281672239302,
|
|
"num_tokens": 23029880.0,
|
|
"step": 11770
|
|
},
|
|
{
|
|
"entropy": 6.16850528717041,
|
|
"epoch": 1.1770380366871596,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00048698510576003593,
|
|
"loss": 6.0333,
|
|
"mean_token_accuracy": 0.15020066350698472,
|
|
"num_tokens": 23039153.0,
|
|
"step": 11775
|
|
},
|
|
{
|
|
"entropy": 6.257021236419678,
|
|
"epoch": 1.177537861748388,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00048697314101239217,
|
|
"loss": 5.9915,
|
|
"mean_token_accuracy": 0.15751764327287673,
|
|
"num_tokens": 23049578.0,
|
|
"step": 11780
|
|
},
|
|
{
|
|
"entropy": 6.064672136306763,
|
|
"epoch": 1.1780376868096165,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004869611709315587,
|
|
"loss": 5.8522,
|
|
"mean_token_accuracy": 0.16184662729501725,
|
|
"num_tokens": 23058882.0,
|
|
"step": 11785
|
|
},
|
|
{
|
|
"entropy": 6.1092462062835695,
|
|
"epoch": 1.1785375118708452,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00048694919551783665,
|
|
"loss": 5.9683,
|
|
"mean_token_accuracy": 0.15907809883356094,
|
|
"num_tokens": 23069056.0,
|
|
"step": 11790
|
|
},
|
|
{
|
|
"entropy": 6.162931632995606,
|
|
"epoch": 1.1790373369320737,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00048693721477152755,
|
|
"loss": 5.9839,
|
|
"mean_token_accuracy": 0.15467517226934432,
|
|
"num_tokens": 23079155.0,
|
|
"step": 11795
|
|
},
|
|
{
|
|
"entropy": 6.288737630844116,
|
|
"epoch": 1.1795371619933024,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00048692522869293246,
|
|
"loss": 6.1071,
|
|
"mean_token_accuracy": 0.14290804862976075,
|
|
"num_tokens": 23089001.0,
|
|
"step": 11800
|
|
},
|
|
{
|
|
"entropy": 6.1644086837768555,
|
|
"epoch": 1.1800369870545309,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004869132372823533,
|
|
"loss": 5.918,
|
|
"mean_token_accuracy": 0.15994679033756257,
|
|
"num_tokens": 23098824.0,
|
|
"step": 11805
|
|
},
|
|
{
|
|
"entropy": 6.192744874954224,
|
|
"epoch": 1.1805368121157596,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00048690124054009157,
|
|
"loss": 5.9361,
|
|
"mean_token_accuracy": 0.15142097622156142,
|
|
"num_tokens": 23107752.0,
|
|
"step": 11810
|
|
},
|
|
{
|
|
"entropy": 6.046417665481568,
|
|
"epoch": 1.181036637176988,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004868892384664491,
|
|
"loss": 5.883,
|
|
"mean_token_accuracy": 0.1543777108192444,
|
|
"num_tokens": 23116815.0,
|
|
"step": 11815
|
|
},
|
|
{
|
|
"entropy": 6.0947174549102785,
|
|
"epoch": 1.1815364622382165,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00048687723106172805,
|
|
"loss": 5.8626,
|
|
"mean_token_accuracy": 0.15405744910240174,
|
|
"num_tokens": 23126093.0,
|
|
"step": 11820
|
|
},
|
|
{
|
|
"entropy": 6.251590585708618,
|
|
"epoch": 1.1820362872994452,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.00048686521832623026,
|
|
"loss": 5.9645,
|
|
"mean_token_accuracy": 0.15875712484121324,
|
|
"num_tokens": 23135928.0,
|
|
"step": 11825
|
|
},
|
|
{
|
|
"entropy": 6.261361694335937,
|
|
"epoch": 1.1825361123606737,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004868532002602581,
|
|
"loss": 6.063,
|
|
"mean_token_accuracy": 0.1460098072886467,
|
|
"num_tokens": 23145345.0,
|
|
"step": 11830
|
|
},
|
|
{
|
|
"entropy": 6.178055095672607,
|
|
"epoch": 1.1830359374219024,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.000486841176864114,
|
|
"loss": 5.9866,
|
|
"mean_token_accuracy": 0.1543113648891449,
|
|
"num_tokens": 23155184.0,
|
|
"step": 11835
|
|
},
|
|
{
|
|
"entropy": 6.189496088027954,
|
|
"epoch": 1.1835357624831309,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00048682914813810035,
|
|
"loss": 6.0306,
|
|
"mean_token_accuracy": 0.15057751089334487,
|
|
"num_tokens": 23166297.0,
|
|
"step": 11840
|
|
},
|
|
{
|
|
"entropy": 6.14486174583435,
|
|
"epoch": 1.1840355875443596,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00048681711408251986,
|
|
"loss": 5.9121,
|
|
"mean_token_accuracy": 0.1537284106016159,
|
|
"num_tokens": 23175268.0,
|
|
"step": 11845
|
|
},
|
|
{
|
|
"entropy": 6.2232283592224125,
|
|
"epoch": 1.184535412605588,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00048680507469767533,
|
|
"loss": 5.9371,
|
|
"mean_token_accuracy": 0.15343511030077933,
|
|
"num_tokens": 23185400.0,
|
|
"step": 11850
|
|
},
|
|
{
|
|
"entropy": 6.2029297828674315,
|
|
"epoch": 1.1850352376668165,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004867930299838696,
|
|
"loss": 6.0237,
|
|
"mean_token_accuracy": 0.1510491192340851,
|
|
"num_tokens": 23194540.0,
|
|
"step": 11855
|
|
},
|
|
{
|
|
"entropy": 6.162105989456177,
|
|
"epoch": 1.1855350627280452,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00048678097994140566,
|
|
"loss": 6.084,
|
|
"mean_token_accuracy": 0.15456485450267793,
|
|
"num_tokens": 23205049.0,
|
|
"step": 11860
|
|
},
|
|
{
|
|
"entropy": 6.232222080230713,
|
|
"epoch": 1.1860348877892737,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00048676892457058687,
|
|
"loss": 5.9848,
|
|
"mean_token_accuracy": 0.15396279692649842,
|
|
"num_tokens": 23214369.0,
|
|
"step": 11865
|
|
},
|
|
{
|
|
"entropy": 6.1500202178955075,
|
|
"epoch": 1.1865347128505024,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004867568638717164,
|
|
"loss": 5.9202,
|
|
"mean_token_accuracy": 0.16146257519721985,
|
|
"num_tokens": 23223806.0,
|
|
"step": 11870
|
|
},
|
|
{
|
|
"entropy": 6.195460510253906,
|
|
"epoch": 1.1870345379117309,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00048674479784509766,
|
|
"loss": 6.0084,
|
|
"mean_token_accuracy": 0.15282646864652633,
|
|
"num_tokens": 23233086.0,
|
|
"step": 11875
|
|
},
|
|
{
|
|
"entropy": 6.130538272857666,
|
|
"epoch": 1.1875343629729596,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00048673272649103435,
|
|
"loss": 5.9486,
|
|
"mean_token_accuracy": 0.16294859498739242,
|
|
"num_tokens": 23242564.0,
|
|
"step": 11880
|
|
},
|
|
{
|
|
"entropy": 6.101591396331787,
|
|
"epoch": 1.188034188034188,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00048672064980983013,
|
|
"loss": 5.8707,
|
|
"mean_token_accuracy": 0.1602120578289032,
|
|
"num_tokens": 23252396.0,
|
|
"step": 11885
|
|
},
|
|
{
|
|
"entropy": 6.161205863952636,
|
|
"epoch": 1.1885340130954165,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.00048670856780178874,
|
|
"loss": 5.9889,
|
|
"mean_token_accuracy": 0.15480765253305434,
|
|
"num_tokens": 23261528.0,
|
|
"step": 11890
|
|
},
|
|
{
|
|
"entropy": 6.225141286849976,
|
|
"epoch": 1.1890338381566452,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00048669648046721436,
|
|
"loss": 6.0448,
|
|
"mean_token_accuracy": 0.15721153765916823,
|
|
"num_tokens": 23271794.0,
|
|
"step": 11895
|
|
},
|
|
{
|
|
"entropy": 6.222901725769043,
|
|
"epoch": 1.1895336632178737,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.000486684387806411,
|
|
"loss": 5.9754,
|
|
"mean_token_accuracy": 0.1520319923758507,
|
|
"num_tokens": 23281340.0,
|
|
"step": 11900
|
|
},
|
|
{
|
|
"entropy": 6.202496194839478,
|
|
"epoch": 1.1900334882791024,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.00048667228981968285,
|
|
"loss": 6.0075,
|
|
"mean_token_accuracy": 0.15111462846398355,
|
|
"num_tokens": 23290579.0,
|
|
"step": 11905
|
|
},
|
|
{
|
|
"entropy": 6.069172430038452,
|
|
"epoch": 1.1905333133403309,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00048666018650733446,
|
|
"loss": 5.898,
|
|
"mean_token_accuracy": 0.16001971513032914,
|
|
"num_tokens": 23300762.0,
|
|
"step": 11910
|
|
},
|
|
{
|
|
"entropy": 6.121626710891723,
|
|
"epoch": 1.1910331384015596,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004866480778696702,
|
|
"loss": 5.9547,
|
|
"mean_token_accuracy": 0.15563222020864487,
|
|
"num_tokens": 23310793.0,
|
|
"step": 11915
|
|
},
|
|
{
|
|
"entropy": 6.1300910949707035,
|
|
"epoch": 1.191532963462788,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00048663596390699477,
|
|
"loss": 5.8641,
|
|
"mean_token_accuracy": 0.1581147477030754,
|
|
"num_tokens": 23321289.0,
|
|
"step": 11920
|
|
},
|
|
{
|
|
"entropy": 6.159178113937378,
|
|
"epoch": 1.1920327885240165,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004866238446196129,
|
|
"loss": 6.0433,
|
|
"mean_token_accuracy": 0.1495481550693512,
|
|
"num_tokens": 23331173.0,
|
|
"step": 11925
|
|
},
|
|
{
|
|
"entropy": 6.2463466167449955,
|
|
"epoch": 1.1925326135852452,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004866117200078296,
|
|
"loss": 6.1323,
|
|
"mean_token_accuracy": 0.14346483647823333,
|
|
"num_tokens": 23341905.0,
|
|
"step": 11930
|
|
},
|
|
{
|
|
"entropy": 6.230529260635376,
|
|
"epoch": 1.1930324386464737,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00048659959007194985,
|
|
"loss": 5.9735,
|
|
"mean_token_accuracy": 0.15860424935817719,
|
|
"num_tokens": 23351840.0,
|
|
"step": 11935
|
|
},
|
|
{
|
|
"entropy": 6.271266174316406,
|
|
"epoch": 1.1935322637077024,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.00048658745481227884,
|
|
"loss": 6.066,
|
|
"mean_token_accuracy": 0.1421751447021961,
|
|
"num_tokens": 23362269.0,
|
|
"step": 11940
|
|
},
|
|
{
|
|
"entropy": 6.297079181671142,
|
|
"epoch": 1.1940320887689309,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.000486575314229122,
|
|
"loss": 6.1371,
|
|
"mean_token_accuracy": 0.1469311907887459,
|
|
"num_tokens": 23372431.0,
|
|
"step": 11945
|
|
},
|
|
{
|
|
"entropy": 6.239289236068726,
|
|
"epoch": 1.1945319138301596,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.0004865631683227846,
|
|
"loss": 5.8938,
|
|
"mean_token_accuracy": 0.15750027745962142,
|
|
"num_tokens": 23381650.0,
|
|
"step": 11950
|
|
},
|
|
{
|
|
"entropy": 6.064280414581299,
|
|
"epoch": 1.195031738891388,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.00048655101709357243,
|
|
"loss": 5.8974,
|
|
"mean_token_accuracy": 0.1651660308241844,
|
|
"num_tokens": 23390842.0,
|
|
"step": 11955
|
|
},
|
|
{
|
|
"entropy": 6.111900806427002,
|
|
"epoch": 1.1955315639526165,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.000486538860541791,
|
|
"loss": 5.9164,
|
|
"mean_token_accuracy": 0.1615041524171829,
|
|
"num_tokens": 23400109.0,
|
|
"step": 11960
|
|
},
|
|
{
|
|
"entropy": 6.099809074401856,
|
|
"epoch": 1.1960313890138452,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00048652669866774636,
|
|
"loss": 5.8022,
|
|
"mean_token_accuracy": 0.1601795196533203,
|
|
"num_tokens": 23409234.0,
|
|
"step": 11965
|
|
},
|
|
{
|
|
"entropy": 6.120146942138672,
|
|
"epoch": 1.1965312140750737,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004865145314717443,
|
|
"loss": 5.9488,
|
|
"mean_token_accuracy": 0.1562504068017006,
|
|
"num_tokens": 23419094.0,
|
|
"step": 11970
|
|
},
|
|
{
|
|
"entropy": 6.233087396621704,
|
|
"epoch": 1.1970310391363024,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.00048650235895409115,
|
|
"loss": 5.9267,
|
|
"mean_token_accuracy": 0.15422954261302949,
|
|
"num_tokens": 23428185.0,
|
|
"step": 11975
|
|
},
|
|
{
|
|
"entropy": 6.166892004013062,
|
|
"epoch": 1.1975308641975309,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004864901811150931,
|
|
"loss": 5.9913,
|
|
"mean_token_accuracy": 0.1541443184018135,
|
|
"num_tokens": 23438224.0,
|
|
"step": 11980
|
|
},
|
|
{
|
|
"entropy": 6.116296577453613,
|
|
"epoch": 1.1980306892587596,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004864779979550564,
|
|
"loss": 5.9018,
|
|
"mean_token_accuracy": 0.16291505396366118,
|
|
"num_tokens": 23447982.0,
|
|
"step": 11985
|
|
},
|
|
{
|
|
"entropy": 6.156915616989136,
|
|
"epoch": 1.198530514319988,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004864658094742878,
|
|
"loss": 5.9539,
|
|
"mean_token_accuracy": 0.1563790649175644,
|
|
"num_tokens": 23458237.0,
|
|
"step": 11990
|
|
},
|
|
{
|
|
"entropy": 6.213999795913696,
|
|
"epoch": 1.1990303393812165,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.00048645361567309375,
|
|
"loss": 6.0088,
|
|
"mean_token_accuracy": 0.15272126346826553,
|
|
"num_tokens": 23467570.0,
|
|
"step": 11995
|
|
},
|
|
{
|
|
"entropy": 6.265379762649536,
|
|
"epoch": 1.1995301644424452,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004864414165517812,
|
|
"loss": 6.0025,
|
|
"mean_token_accuracy": 0.15862176865339278,
|
|
"num_tokens": 23478192.0,
|
|
"step": 12000
|
|
},
|
|
{
|
|
"epoch": 1.1995301644424452,
|
|
"eval_entropy": 6.050195842267189,
|
|
"eval_loss": 6.077088832855225,
|
|
"eval_mean_token_accuracy": 0.15807910671246955,
|
|
"eval_num_tokens": 23478192.0,
|
|
"eval_runtime": 23.8568,
|
|
"eval_samples_per_second": 1301.308,
|
|
"eval_steps_per_second": 162.679,
|
|
"step": 12000
|
|
},
|
|
{
|
|
"entropy": 6.199899435043335,
|
|
"epoch": 1.2000299895036737,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.000486429212110657,
|
|
"loss": 6.0296,
|
|
"mean_token_accuracy": 0.15094629377126695,
|
|
"num_tokens": 23488128.0,
|
|
"step": 12005
|
|
},
|
|
{
|
|
"entropy": 6.191727209091186,
|
|
"epoch": 1.2005298145649024,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004864170023500282,
|
|
"loss": 6.0276,
|
|
"mean_token_accuracy": 0.15196529328823088,
|
|
"num_tokens": 23496740.0,
|
|
"step": 12010
|
|
},
|
|
{
|
|
"entropy": 6.14084210395813,
|
|
"epoch": 1.2010296396261309,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004864047872702021,
|
|
"loss": 5.8915,
|
|
"mean_token_accuracy": 0.16810173839330672,
|
|
"num_tokens": 23505606.0,
|
|
"step": 12015
|
|
},
|
|
{
|
|
"entropy": 6.147327947616577,
|
|
"epoch": 1.2015294646873593,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004863925668714859,
|
|
"loss": 5.8945,
|
|
"mean_token_accuracy": 0.15749603807926177,
|
|
"num_tokens": 23515001.0,
|
|
"step": 12020
|
|
},
|
|
{
|
|
"entropy": 6.156831550598144,
|
|
"epoch": 1.202029289748588,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004863803411541871,
|
|
"loss": 6.0392,
|
|
"mean_token_accuracy": 0.14907794296741486,
|
|
"num_tokens": 23526353.0,
|
|
"step": 12025
|
|
},
|
|
{
|
|
"entropy": 6.105481481552124,
|
|
"epoch": 1.2025291148098165,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004863681101186134,
|
|
"loss": 5.8411,
|
|
"mean_token_accuracy": 0.1668488249182701,
|
|
"num_tokens": 23535571.0,
|
|
"step": 12030
|
|
},
|
|
{
|
|
"entropy": 6.064318418502808,
|
|
"epoch": 1.2030289398710452,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004863558737650723,
|
|
"loss": 5.9277,
|
|
"mean_token_accuracy": 0.16584953665733337,
|
|
"num_tokens": 23545495.0,
|
|
"step": 12035
|
|
},
|
|
{
|
|
"entropy": 6.168333911895752,
|
|
"epoch": 1.2035287649322737,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004863436320938719,
|
|
"loss": 5.9089,
|
|
"mean_token_accuracy": 0.15826427340507507,
|
|
"num_tokens": 23554942.0,
|
|
"step": 12040
|
|
},
|
|
{
|
|
"entropy": 6.180454730987549,
|
|
"epoch": 1.2040285899935022,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00048633138510532003,
|
|
"loss": 5.992,
|
|
"mean_token_accuracy": 0.15368711203336716,
|
|
"num_tokens": 23564297.0,
|
|
"step": 12045
|
|
},
|
|
{
|
|
"entropy": 6.16219687461853,
|
|
"epoch": 1.2045284150547308,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00048631913279972497,
|
|
"loss": 5.9947,
|
|
"mean_token_accuracy": 0.15627450197935105,
|
|
"num_tokens": 23574899.0,
|
|
"step": 12050
|
|
},
|
|
{
|
|
"entropy": 6.201348829269409,
|
|
"epoch": 1.2050282401159593,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00048630687517739484,
|
|
"loss": 6.0546,
|
|
"mean_token_accuracy": 0.15214102044701577,
|
|
"num_tokens": 23585309.0,
|
|
"step": 12055
|
|
},
|
|
{
|
|
"entropy": 6.10280933380127,
|
|
"epoch": 1.205528065177188,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004862946122386381,
|
|
"loss": 5.9048,
|
|
"mean_token_accuracy": 0.15918524265289308,
|
|
"num_tokens": 23595270.0,
|
|
"step": 12060
|
|
},
|
|
{
|
|
"entropy": 6.186801624298096,
|
|
"epoch": 1.2060278902384165,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00048628234398376334,
|
|
"loss": 5.9816,
|
|
"mean_token_accuracy": 0.1590077519416809,
|
|
"num_tokens": 23604698.0,
|
|
"step": 12065
|
|
},
|
|
{
|
|
"entropy": 6.159816026687622,
|
|
"epoch": 1.2065277152996452,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00048627007041307914,
|
|
"loss": 6.0137,
|
|
"mean_token_accuracy": 0.15074703842401505,
|
|
"num_tokens": 23614588.0,
|
|
"step": 12070
|
|
},
|
|
{
|
|
"entropy": 6.098800802230835,
|
|
"epoch": 1.2070275403608737,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00048625779152689435,
|
|
"loss": 5.8602,
|
|
"mean_token_accuracy": 0.16643391102552413,
|
|
"num_tokens": 23624394.0,
|
|
"step": 12075
|
|
},
|
|
{
|
|
"entropy": 6.200442790985107,
|
|
"epoch": 1.2075273654221022,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004862455073255179,
|
|
"loss": 5.9267,
|
|
"mean_token_accuracy": 0.15674215704202651,
|
|
"num_tokens": 23633558.0,
|
|
"step": 12080
|
|
},
|
|
{
|
|
"entropy": 6.185452604293824,
|
|
"epoch": 1.2080271904833308,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00048623321780925883,
|
|
"loss": 5.9803,
|
|
"mean_token_accuracy": 0.15276988968253136,
|
|
"num_tokens": 23643320.0,
|
|
"step": 12085
|
|
},
|
|
{
|
|
"entropy": 6.156462574005127,
|
|
"epoch": 1.2085270155445593,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.00048622092297842637,
|
|
"loss": 6.0712,
|
|
"mean_token_accuracy": 0.1507236272096634,
|
|
"num_tokens": 23653660.0,
|
|
"step": 12090
|
|
},
|
|
{
|
|
"entropy": 6.167096185684204,
|
|
"epoch": 1.209026840605788,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004862086228333298,
|
|
"loss": 5.9342,
|
|
"mean_token_accuracy": 0.15746346414089202,
|
|
"num_tokens": 23662556.0,
|
|
"step": 12095
|
|
},
|
|
{
|
|
"entropy": 6.117544746398925,
|
|
"epoch": 1.2095266656670165,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00048619631737427865,
|
|
"loss": 5.9434,
|
|
"mean_token_accuracy": 0.15573475062847136,
|
|
"num_tokens": 23672628.0,
|
|
"step": 12100
|
|
},
|
|
{
|
|
"entropy": 6.06883692741394,
|
|
"epoch": 1.2100264907282452,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004861840066015825,
|
|
"loss": 5.8632,
|
|
"mean_token_accuracy": 0.165093731880188,
|
|
"num_tokens": 23682574.0,
|
|
"step": 12105
|
|
},
|
|
{
|
|
"entropy": 6.154279470443726,
|
|
"epoch": 1.2105263157894737,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00048617169051555113,
|
|
"loss": 6.0038,
|
|
"mean_token_accuracy": 0.1495068795979023,
|
|
"num_tokens": 23691870.0,
|
|
"step": 12110
|
|
},
|
|
{
|
|
"entropy": 6.16855206489563,
|
|
"epoch": 1.2110261408507021,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004861593691164942,
|
|
"loss": 5.8913,
|
|
"mean_token_accuracy": 0.15467180982232093,
|
|
"num_tokens": 23701896.0,
|
|
"step": 12115
|
|
},
|
|
{
|
|
"entropy": 6.114151191711426,
|
|
"epoch": 1.2115259659119308,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004861470424047221,
|
|
"loss": 5.9388,
|
|
"mean_token_accuracy": 0.15587804466485977,
|
|
"num_tokens": 23711960.0,
|
|
"step": 12120
|
|
},
|
|
{
|
|
"entropy": 6.098422956466675,
|
|
"epoch": 1.2120257909731593,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004861347103805446,
|
|
"loss": 6.002,
|
|
"mean_token_accuracy": 0.15374198853969573,
|
|
"num_tokens": 23721090.0,
|
|
"step": 12125
|
|
},
|
|
{
|
|
"entropy": 6.2354999542236325,
|
|
"epoch": 1.212525616034388,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004861223730442722,
|
|
"loss": 6.1465,
|
|
"mean_token_accuracy": 0.14846143424510955,
|
|
"num_tokens": 23731245.0,
|
|
"step": 12130
|
|
},
|
|
{
|
|
"entropy": 6.1624328136444095,
|
|
"epoch": 1.2130254410956165,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.00048611003039621516,
|
|
"loss": 5.9823,
|
|
"mean_token_accuracy": 0.15259638279676438,
|
|
"num_tokens": 23740891.0,
|
|
"step": 12135
|
|
},
|
|
{
|
|
"entropy": 6.225450754165649,
|
|
"epoch": 1.2135252661568452,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004860976824366841,
|
|
"loss": 6.0508,
|
|
"mean_token_accuracy": 0.14930666536092757,
|
|
"num_tokens": 23751275.0,
|
|
"step": 12140
|
|
},
|
|
{
|
|
"entropy": 6.281868028640747,
|
|
"epoch": 1.2140250912180737,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00048608532916598964,
|
|
"loss": 6.1028,
|
|
"mean_token_accuracy": 0.14672356620430946,
|
|
"num_tokens": 23760994.0,
|
|
"step": 12145
|
|
},
|
|
{
|
|
"entropy": 6.182911920547485,
|
|
"epoch": 1.2145249162793021,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00048607297058444267,
|
|
"loss": 5.8982,
|
|
"mean_token_accuracy": 0.15400320142507554,
|
|
"num_tokens": 23770084.0,
|
|
"step": 12150
|
|
},
|
|
{
|
|
"entropy": 6.094257545471192,
|
|
"epoch": 1.2150247413405308,
|
|
"grad_norm": 1.8515625,
|
|
"learning_rate": 0.0004860606066923541,
|
|
"loss": 5.9288,
|
|
"mean_token_accuracy": 0.15634187757968904,
|
|
"num_tokens": 23780241.0,
|
|
"step": 12155
|
|
},
|
|
{
|
|
"entropy": 6.069482231140137,
|
|
"epoch": 1.2155245664017593,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00048604823749003485,
|
|
"loss": 5.8901,
|
|
"mean_token_accuracy": 0.1635168671607971,
|
|
"num_tokens": 23789970.0,
|
|
"step": 12160
|
|
},
|
|
{
|
|
"entropy": 6.228507232666016,
|
|
"epoch": 1.216024391462988,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004860358629777963,
|
|
"loss": 6.0117,
|
|
"mean_token_accuracy": 0.15150651335716248,
|
|
"num_tokens": 23799924.0,
|
|
"step": 12165
|
|
},
|
|
{
|
|
"entropy": 6.214637088775635,
|
|
"epoch": 1.2165242165242165,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004860234831559498,
|
|
"loss": 5.8825,
|
|
"mean_token_accuracy": 0.16508516669273376,
|
|
"num_tokens": 23809258.0,
|
|
"step": 12170
|
|
},
|
|
{
|
|
"entropy": 6.018302488327026,
|
|
"epoch": 1.2170240415854452,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00048601109802480676,
|
|
"loss": 5.8768,
|
|
"mean_token_accuracy": 0.15989995300769805,
|
|
"num_tokens": 23817979.0,
|
|
"step": 12175
|
|
},
|
|
{
|
|
"entropy": 6.096931123733521,
|
|
"epoch": 1.2175238666466737,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.00048599870758467875,
|
|
"loss": 5.8733,
|
|
"mean_token_accuracy": 0.16377185583114623,
|
|
"num_tokens": 23828182.0,
|
|
"step": 12180
|
|
},
|
|
{
|
|
"entropy": 6.195300340652466,
|
|
"epoch": 1.2180236917079021,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.00048598631183587753,
|
|
"loss": 5.8914,
|
|
"mean_token_accuracy": 0.16429374366998672,
|
|
"num_tokens": 23838135.0,
|
|
"step": 12185
|
|
},
|
|
{
|
|
"entropy": 6.103349924087524,
|
|
"epoch": 1.2185235167691308,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00048597391077871504,
|
|
"loss": 5.8454,
|
|
"mean_token_accuracy": 0.1595311015844345,
|
|
"num_tokens": 23847586.0,
|
|
"step": 12190
|
|
},
|
|
{
|
|
"entropy": 6.0575824737548825,
|
|
"epoch": 1.2190233418303593,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00048596150441350324,
|
|
"loss": 5.9005,
|
|
"mean_token_accuracy": 0.15736396312713624,
|
|
"num_tokens": 23857112.0,
|
|
"step": 12195
|
|
},
|
|
{
|
|
"entropy": 6.156764078140259,
|
|
"epoch": 1.219523166891588,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004859490927405543,
|
|
"loss": 6.1165,
|
|
"mean_token_accuracy": 0.14905385971069335,
|
|
"num_tokens": 23866990.0,
|
|
"step": 12200
|
|
},
|
|
{
|
|
"entropy": 6.300009441375733,
|
|
"epoch": 1.2200229919528165,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004859366757601804,
|
|
"loss": 6.122,
|
|
"mean_token_accuracy": 0.14187795519828797,
|
|
"num_tokens": 23877037.0,
|
|
"step": 12205
|
|
},
|
|
{
|
|
"entropy": 6.2392415523529055,
|
|
"epoch": 1.2205228170140452,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00048592425347269405,
|
|
"loss": 6.0376,
|
|
"mean_token_accuracy": 0.14966610074043274,
|
|
"num_tokens": 23886341.0,
|
|
"step": 12210
|
|
},
|
|
{
|
|
"entropy": 6.250817728042603,
|
|
"epoch": 1.2210226420752737,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 0.00048591182587840777,
|
|
"loss": 6.0122,
|
|
"mean_token_accuracy": 0.15051086097955704,
|
|
"num_tokens": 23896143.0,
|
|
"step": 12215
|
|
},
|
|
{
|
|
"entropy": 6.28934531211853,
|
|
"epoch": 1.2215224671365021,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004858993929776342,
|
|
"loss": 6.0249,
|
|
"mean_token_accuracy": 0.15044788718223573,
|
|
"num_tokens": 23906086.0,
|
|
"step": 12220
|
|
},
|
|
{
|
|
"entropy": 6.184673690795899,
|
|
"epoch": 1.2220222921977308,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00048588695477068617,
|
|
"loss": 5.9468,
|
|
"mean_token_accuracy": 0.1532865807414055,
|
|
"num_tokens": 23914669.0,
|
|
"step": 12225
|
|
},
|
|
{
|
|
"entropy": 6.153165292739868,
|
|
"epoch": 1.2225221172589593,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00048587451125787665,
|
|
"loss": 5.9387,
|
|
"mean_token_accuracy": 0.15872783213853836,
|
|
"num_tokens": 23925461.0,
|
|
"step": 12230
|
|
},
|
|
{
|
|
"entropy": 6.092390632629394,
|
|
"epoch": 1.223021942320188,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004858620624395187,
|
|
"loss": 5.9922,
|
|
"mean_token_accuracy": 0.1596124455332756,
|
|
"num_tokens": 23934436.0,
|
|
"step": 12235
|
|
},
|
|
{
|
|
"entropy": 6.150168800354004,
|
|
"epoch": 1.2235217673814165,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00048584960831592547,
|
|
"loss": 6.0182,
|
|
"mean_token_accuracy": 0.15344582572579385,
|
|
"num_tokens": 23944894.0,
|
|
"step": 12240
|
|
},
|
|
{
|
|
"entropy": 6.237721967697143,
|
|
"epoch": 1.2240215924426452,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00048583714888741035,
|
|
"loss": 5.9093,
|
|
"mean_token_accuracy": 0.164944389462471,
|
|
"num_tokens": 23954621.0,
|
|
"step": 12245
|
|
},
|
|
{
|
|
"entropy": 6.11160798072815,
|
|
"epoch": 1.2245214175038737,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00048582468415428687,
|
|
"loss": 5.8995,
|
|
"mean_token_accuracy": 0.15842829570174216,
|
|
"num_tokens": 23964379.0,
|
|
"step": 12250
|
|
},
|
|
{
|
|
"entropy": 6.087403869628906,
|
|
"epoch": 1.2250212425651021,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00048581221411686857,
|
|
"loss": 5.8854,
|
|
"mean_token_accuracy": 0.1606437861919403,
|
|
"num_tokens": 23973414.0,
|
|
"step": 12255
|
|
},
|
|
{
|
|
"entropy": 6.1575233936309814,
|
|
"epoch": 1.2255210676263308,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00048579973877546916,
|
|
"loss": 5.9403,
|
|
"mean_token_accuracy": 0.15637090131640435,
|
|
"num_tokens": 23982912.0,
|
|
"step": 12260
|
|
},
|
|
{
|
|
"entropy": 6.299131298065186,
|
|
"epoch": 1.2260208926875593,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00048578725813040263,
|
|
"loss": 6.076,
|
|
"mean_token_accuracy": 0.14022471606731415,
|
|
"num_tokens": 23993927.0,
|
|
"step": 12265
|
|
},
|
|
{
|
|
"entropy": 6.163681840896606,
|
|
"epoch": 1.226520717748788,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004857747721819829,
|
|
"loss": 5.8892,
|
|
"mean_token_accuracy": 0.1539958342909813,
|
|
"num_tokens": 24003518.0,
|
|
"step": 12270
|
|
},
|
|
{
|
|
"entropy": 6.11926851272583,
|
|
"epoch": 1.2270205428100165,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004857622809305241,
|
|
"loss": 5.9938,
|
|
"mean_token_accuracy": 0.16001538932323456,
|
|
"num_tokens": 24013013.0,
|
|
"step": 12275
|
|
},
|
|
{
|
|
"entropy": 6.231849479675293,
|
|
"epoch": 1.2275203678712452,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00048574978437634057,
|
|
"loss": 6.0715,
|
|
"mean_token_accuracy": 0.1545599564909935,
|
|
"num_tokens": 24022276.0,
|
|
"step": 12280
|
|
},
|
|
{
|
|
"entropy": 6.086420345306396,
|
|
"epoch": 1.2280201929324737,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004857372825197468,
|
|
"loss": 5.8851,
|
|
"mean_token_accuracy": 0.16119584143161775,
|
|
"num_tokens": 24032165.0,
|
|
"step": 12285
|
|
},
|
|
{
|
|
"entropy": 6.201887893676758,
|
|
"epoch": 1.2285200179937021,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004857247753610571,
|
|
"loss": 5.9491,
|
|
"mean_token_accuracy": 0.15815795063972474,
|
|
"num_tokens": 24041313.0,
|
|
"step": 12290
|
|
},
|
|
{
|
|
"entropy": 6.220150566101074,
|
|
"epoch": 1.2290198430549308,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00048571226290058635,
|
|
"loss": 6.0064,
|
|
"mean_token_accuracy": 0.1566406197845936,
|
|
"num_tokens": 24050810.0,
|
|
"step": 12295
|
|
},
|
|
{
|
|
"entropy": 6.1585455417633055,
|
|
"epoch": 1.2295196681161593,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004856997451386492,
|
|
"loss": 5.9369,
|
|
"mean_token_accuracy": 0.16096862852573396,
|
|
"num_tokens": 24060582.0,
|
|
"step": 12300
|
|
},
|
|
{
|
|
"entropy": 6.1547523021698,
|
|
"epoch": 1.2300194931773878,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004856872220755607,
|
|
"loss": 6.0176,
|
|
"mean_token_accuracy": 0.15021227300167084,
|
|
"num_tokens": 24070208.0,
|
|
"step": 12305
|
|
},
|
|
{
|
|
"entropy": 6.055608701705933,
|
|
"epoch": 1.2305193182386165,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.000485674693711636,
|
|
"loss": 5.9667,
|
|
"mean_token_accuracy": 0.15747600495815278,
|
|
"num_tokens": 24080837.0,
|
|
"step": 12310
|
|
},
|
|
{
|
|
"entropy": 6.156947278976441,
|
|
"epoch": 1.231019143299845,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004856621600471901,
|
|
"loss": 5.9748,
|
|
"mean_token_accuracy": 0.15534792095422745,
|
|
"num_tokens": 24090696.0,
|
|
"step": 12315
|
|
},
|
|
{
|
|
"entropy": 6.246610927581787,
|
|
"epoch": 1.2315189683610737,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00048564962108253853,
|
|
"loss": 6.0324,
|
|
"mean_token_accuracy": 0.1530123807489872,
|
|
"num_tokens": 24100957.0,
|
|
"step": 12320
|
|
},
|
|
{
|
|
"entropy": 6.222395229339599,
|
|
"epoch": 1.2320187934223021,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004856370768179967,
|
|
"loss": 5.9551,
|
|
"mean_token_accuracy": 0.16419268846511842,
|
|
"num_tokens": 24109177.0,
|
|
"step": 12325
|
|
},
|
|
{
|
|
"entropy": 6.098350715637207,
|
|
"epoch": 1.2325186184835308,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00048562452725388024,
|
|
"loss": 5.9636,
|
|
"mean_token_accuracy": 0.15708701759576799,
|
|
"num_tokens": 24118918.0,
|
|
"step": 12330
|
|
},
|
|
{
|
|
"entropy": 6.128720283508301,
|
|
"epoch": 1.2330184435447593,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004856119723905048,
|
|
"loss": 5.8923,
|
|
"mean_token_accuracy": 0.15524128675460816,
|
|
"num_tokens": 24128255.0,
|
|
"step": 12335
|
|
},
|
|
{
|
|
"entropy": 6.211879444122315,
|
|
"epoch": 1.2335182686059878,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004855994122281864,
|
|
"loss": 5.9818,
|
|
"mean_token_accuracy": 0.15366657227277755,
|
|
"num_tokens": 24137670.0,
|
|
"step": 12340
|
|
},
|
|
{
|
|
"entropy": 6.130569410324097,
|
|
"epoch": 1.2340180936672165,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00048558684676724083,
|
|
"loss": 5.9443,
|
|
"mean_token_accuracy": 0.15951559990644454,
|
|
"num_tokens": 24147417.0,
|
|
"step": 12345
|
|
},
|
|
{
|
|
"entropy": 6.1573724269866945,
|
|
"epoch": 1.234517918728445,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00048557427600798454,
|
|
"loss": 5.9636,
|
|
"mean_token_accuracy": 0.15548376441001893,
|
|
"num_tokens": 24158019.0,
|
|
"step": 12350
|
|
},
|
|
{
|
|
"entropy": 6.195652484893799,
|
|
"epoch": 1.2350177437896737,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004855616999507336,
|
|
"loss": 5.9889,
|
|
"mean_token_accuracy": 0.15028104186058044,
|
|
"num_tokens": 24168118.0,
|
|
"step": 12355
|
|
},
|
|
{
|
|
"entropy": 6.213690233230591,
|
|
"epoch": 1.2355175688509021,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00048554911859580445,
|
|
"loss": 6.0358,
|
|
"mean_token_accuracy": 0.1507461652159691,
|
|
"num_tokens": 24177700.0,
|
|
"step": 12360
|
|
},
|
|
{
|
|
"entropy": 6.143312883377075,
|
|
"epoch": 1.2360173939121308,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004855365319435137,
|
|
"loss": 5.9379,
|
|
"mean_token_accuracy": 0.16281663924455642,
|
|
"num_tokens": 24187701.0,
|
|
"step": 12365
|
|
},
|
|
{
|
|
"entropy": 6.149842309951782,
|
|
"epoch": 1.2365172189733593,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.000485523939994178,
|
|
"loss": 5.9403,
|
|
"mean_token_accuracy": 0.15686926245689392,
|
|
"num_tokens": 24197364.0,
|
|
"step": 12370
|
|
},
|
|
{
|
|
"entropy": 6.153480577468872,
|
|
"epoch": 1.2370170440345878,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004855113427481141,
|
|
"loss": 6.0088,
|
|
"mean_token_accuracy": 0.15855405032634734,
|
|
"num_tokens": 24208015.0,
|
|
"step": 12375
|
|
},
|
|
{
|
|
"entropy": 6.149875164031982,
|
|
"epoch": 1.2375168690958165,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.000485498740205639,
|
|
"loss": 5.9812,
|
|
"mean_token_accuracy": 0.15330363661050797,
|
|
"num_tokens": 24218576.0,
|
|
"step": 12380
|
|
},
|
|
{
|
|
"entropy": 6.2113172054290775,
|
|
"epoch": 1.238016694157045,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.00048548613236706976,
|
|
"loss": 6.0093,
|
|
"mean_token_accuracy": 0.151277507096529,
|
|
"num_tokens": 24228727.0,
|
|
"step": 12385
|
|
},
|
|
{
|
|
"entropy": 6.156699705123901,
|
|
"epoch": 1.2385165192182737,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004854735192327236,
|
|
"loss": 5.9657,
|
|
"mean_token_accuracy": 0.16014844924211502,
|
|
"num_tokens": 24238580.0,
|
|
"step": 12390
|
|
},
|
|
{
|
|
"entropy": 6.17481050491333,
|
|
"epoch": 1.2390163442795021,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00048546090080291783,
|
|
"loss": 5.9352,
|
|
"mean_token_accuracy": 0.15282906144857406,
|
|
"num_tokens": 24249543.0,
|
|
"step": 12395
|
|
},
|
|
{
|
|
"entropy": 6.122203302383423,
|
|
"epoch": 1.2395161693407308,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.00048544827707797,
|
|
"loss": 5.9602,
|
|
"mean_token_accuracy": 0.15565237849950792,
|
|
"num_tokens": 24259346.0,
|
|
"step": 12400
|
|
},
|
|
{
|
|
"entropy": 6.183234977722168,
|
|
"epoch": 1.2400159944019593,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00048543564805819764,
|
|
"loss": 5.8678,
|
|
"mean_token_accuracy": 0.1634332776069641,
|
|
"num_tokens": 24267987.0,
|
|
"step": 12405
|
|
},
|
|
{
|
|
"entropy": 6.0854127407073975,
|
|
"epoch": 1.2405158194631878,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004854230137439185,
|
|
"loss": 5.8558,
|
|
"mean_token_accuracy": 0.16354030668735503,
|
|
"num_tokens": 24278398.0,
|
|
"step": 12410
|
|
},
|
|
{
|
|
"entropy": 6.27455358505249,
|
|
"epoch": 1.2410156445244165,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.00048541037413545046,
|
|
"loss": 6.1808,
|
|
"mean_token_accuracy": 0.14410172551870346,
|
|
"num_tokens": 24289425.0,
|
|
"step": 12415
|
|
},
|
|
{
|
|
"entropy": 6.233187484741211,
|
|
"epoch": 1.241515469585645,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004853977292331116,
|
|
"loss": 6.004,
|
|
"mean_token_accuracy": 0.15627337321639062,
|
|
"num_tokens": 24298866.0,
|
|
"step": 12420
|
|
},
|
|
{
|
|
"entropy": 6.216458940505982,
|
|
"epoch": 1.2420152946468737,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004853850790372201,
|
|
"loss": 5.9109,
|
|
"mean_token_accuracy": 0.16707831248641014,
|
|
"num_tokens": 24309237.0,
|
|
"step": 12425
|
|
},
|
|
{
|
|
"entropy": 6.127988386154175,
|
|
"epoch": 1.2425151197081021,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00048537242354809403,
|
|
"loss": 5.9041,
|
|
"mean_token_accuracy": 0.15482162311673164,
|
|
"num_tokens": 24320175.0,
|
|
"step": 12430
|
|
},
|
|
{
|
|
"entropy": 6.0925554752349855,
|
|
"epoch": 1.2430149447693308,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.00048535976276605186,
|
|
"loss": 5.94,
|
|
"mean_token_accuracy": 0.15460563749074935,
|
|
"num_tokens": 24328896.0,
|
|
"step": 12435
|
|
},
|
|
{
|
|
"entropy": 6.20690884590149,
|
|
"epoch": 1.2435147698305593,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004853470966914123,
|
|
"loss": 5.9924,
|
|
"mean_token_accuracy": 0.15424013435840606,
|
|
"num_tokens": 24337988.0,
|
|
"step": 12440
|
|
},
|
|
{
|
|
"entropy": 6.194861936569214,
|
|
"epoch": 1.2440145948917878,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004853344253244939,
|
|
"loss": 5.8915,
|
|
"mean_token_accuracy": 0.16522590070962906,
|
|
"num_tokens": 24347154.0,
|
|
"step": 12445
|
|
},
|
|
{
|
|
"entropy": 6.172908687591553,
|
|
"epoch": 1.2445144199530165,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.00048532174866561543,
|
|
"loss": 6.0144,
|
|
"mean_token_accuracy": 0.1485647216439247,
|
|
"num_tokens": 24357564.0,
|
|
"step": 12450
|
|
},
|
|
{
|
|
"entropy": 6.1157862663269045,
|
|
"epoch": 1.245014245014245,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.00048530906671509597,
|
|
"loss": 5.9035,
|
|
"mean_token_accuracy": 0.15980457365512848,
|
|
"num_tokens": 24366413.0,
|
|
"step": 12455
|
|
},
|
|
{
|
|
"entropy": 6.128127717971802,
|
|
"epoch": 1.2455140700754737,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00048529637947325444,
|
|
"loss": 5.8593,
|
|
"mean_token_accuracy": 0.16693251430988312,
|
|
"num_tokens": 24374950.0,
|
|
"step": 12460
|
|
},
|
|
{
|
|
"entropy": 5.98353590965271,
|
|
"epoch": 1.2460138951367021,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004852836869404101,
|
|
"loss": 5.6992,
|
|
"mean_token_accuracy": 0.17168040797114373,
|
|
"num_tokens": 24384354.0,
|
|
"step": 12465
|
|
},
|
|
{
|
|
"entropy": 6.108272361755371,
|
|
"epoch": 1.2465137201979308,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004852709891168823,
|
|
"loss": 5.9202,
|
|
"mean_token_accuracy": 0.15317668169736862,
|
|
"num_tokens": 24395671.0,
|
|
"step": 12470
|
|
},
|
|
{
|
|
"entropy": 6.210268545150757,
|
|
"epoch": 1.2470135452591593,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004852582860029906,
|
|
"loss": 5.9122,
|
|
"mean_token_accuracy": 0.15453821420669556,
|
|
"num_tokens": 24404497.0,
|
|
"step": 12475
|
|
},
|
|
{
|
|
"entropy": 6.07373571395874,
|
|
"epoch": 1.2475133703203878,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.00048524557759905445,
|
|
"loss": 5.9138,
|
|
"mean_token_accuracy": 0.15981688350439072,
|
|
"num_tokens": 24413651.0,
|
|
"step": 12480
|
|
},
|
|
{
|
|
"entropy": 6.109033870697021,
|
|
"epoch": 1.2480131953816165,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004852328639053937,
|
|
"loss": 5.9806,
|
|
"mean_token_accuracy": 0.15506304055452347,
|
|
"num_tokens": 24424037.0,
|
|
"step": 12485
|
|
},
|
|
{
|
|
"entropy": 6.166393852233886,
|
|
"epoch": 1.248513020442845,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004852201449223282,
|
|
"loss": 5.8688,
|
|
"mean_token_accuracy": 0.16324560344219208,
|
|
"num_tokens": 24433005.0,
|
|
"step": 12490
|
|
},
|
|
{
|
|
"entropy": 6.181481122970581,
|
|
"epoch": 1.2490128455040737,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.000485207420650178,
|
|
"loss": 6.0455,
|
|
"mean_token_accuracy": 0.14739421606063843,
|
|
"num_tokens": 24443241.0,
|
|
"step": 12495
|
|
},
|
|
{
|
|
"entropy": 6.192589807510376,
|
|
"epoch": 1.2495126705653021,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004851946910892631,
|
|
"loss": 5.9055,
|
|
"mean_token_accuracy": 0.1573794886469841,
|
|
"num_tokens": 24452676.0,
|
|
"step": 12500
|
|
},
|
|
{
|
|
"entropy": 6.198310089111328,
|
|
"epoch": 1.2500124956265308,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004851819562399039,
|
|
"loss": 5.9903,
|
|
"mean_token_accuracy": 0.1519806668162346,
|
|
"num_tokens": 24462287.0,
|
|
"step": 12505
|
|
},
|
|
{
|
|
"entropy": 6.2249424934387205,
|
|
"epoch": 1.2505123206877593,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004851692161024207,
|
|
"loss": 6.0557,
|
|
"mean_token_accuracy": 0.1481504112482071,
|
|
"num_tokens": 24471707.0,
|
|
"step": 12510
|
|
},
|
|
{
|
|
"entropy": 6.179369068145752,
|
|
"epoch": 1.2510121457489878,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.00048515647067713425,
|
|
"loss": 5.9241,
|
|
"mean_token_accuracy": 0.15510827153921128,
|
|
"num_tokens": 24481920.0,
|
|
"step": 12515
|
|
},
|
|
{
|
|
"entropy": 6.094916772842407,
|
|
"epoch": 1.2515119708102165,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.000485143719964365,
|
|
"loss": 5.8493,
|
|
"mean_token_accuracy": 0.16588624864816665,
|
|
"num_tokens": 24491890.0,
|
|
"step": 12520
|
|
},
|
|
{
|
|
"entropy": 6.112090253829956,
|
|
"epoch": 1.252011795871445,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004851309639644338,
|
|
"loss": 5.94,
|
|
"mean_token_accuracy": 0.15722692161798477,
|
|
"num_tokens": 24501563.0,
|
|
"step": 12525
|
|
},
|
|
{
|
|
"entropy": 6.155604076385498,
|
|
"epoch": 1.2525116209326734,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004851182026776616,
|
|
"loss": 5.8743,
|
|
"mean_token_accuracy": 0.16577624678611755,
|
|
"num_tokens": 24511828.0,
|
|
"step": 12530
|
|
},
|
|
{
|
|
"entropy": 6.203512382507324,
|
|
"epoch": 1.2530114459939021,
|
|
"grad_norm": 1.8984375,
|
|
"learning_rate": 0.0004851054361043696,
|
|
"loss": 5.9352,
|
|
"mean_token_accuracy": 0.1568019226193428,
|
|
"num_tokens": 24521695.0,
|
|
"step": 12535
|
|
},
|
|
{
|
|
"entropy": 6.209982252120971,
|
|
"epoch": 1.2535112710551308,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00048509266424487873,
|
|
"loss": 6.0153,
|
|
"mean_token_accuracy": 0.1475982442498207,
|
|
"num_tokens": 24531755.0,
|
|
"step": 12540
|
|
},
|
|
{
|
|
"entropy": 6.174740266799927,
|
|
"epoch": 1.2540110961163593,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004850798870995106,
|
|
"loss": 5.9125,
|
|
"mean_token_accuracy": 0.1610000878572464,
|
|
"num_tokens": 24540221.0,
|
|
"step": 12545
|
|
},
|
|
{
|
|
"entropy": 6.198403358459473,
|
|
"epoch": 1.2545109211775878,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.00048506710466858657,
|
|
"loss": 5.9395,
|
|
"mean_token_accuracy": 0.15496189147233963,
|
|
"num_tokens": 24549749.0,
|
|
"step": 12550
|
|
},
|
|
{
|
|
"entropy": 6.190253353118896,
|
|
"epoch": 1.2550107462388165,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00048505431695242823,
|
|
"loss": 5.9745,
|
|
"mean_token_accuracy": 0.15337319523096085,
|
|
"num_tokens": 24559318.0,
|
|
"step": 12555
|
|
},
|
|
{
|
|
"entropy": 6.205845022201538,
|
|
"epoch": 1.255510571300045,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00048504152395135726,
|
|
"loss": 5.9933,
|
|
"mean_token_accuracy": 0.1553647756576538,
|
|
"num_tokens": 24568779.0,
|
|
"step": 12560
|
|
},
|
|
{
|
|
"entropy": 6.143230152130127,
|
|
"epoch": 1.2560103963612734,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.00048502872566569564,
|
|
"loss": 5.9804,
|
|
"mean_token_accuracy": 0.14577547758817672,
|
|
"num_tokens": 24578258.0,
|
|
"step": 12565
|
|
},
|
|
{
|
|
"entropy": 6.197085571289063,
|
|
"epoch": 1.2565102214225021,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00048501592209576535,
|
|
"loss": 5.9536,
|
|
"mean_token_accuracy": 0.15800777673721314,
|
|
"num_tokens": 24587485.0,
|
|
"step": 12570
|
|
},
|
|
{
|
|
"entropy": 6.163204336166382,
|
|
"epoch": 1.2570100464837308,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004850031132418885,
|
|
"loss": 5.9331,
|
|
"mean_token_accuracy": 0.1545553222298622,
|
|
"num_tokens": 24597656.0,
|
|
"step": 12575
|
|
},
|
|
{
|
|
"entropy": 6.150587320327759,
|
|
"epoch": 1.2575098715449593,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00048499029910438734,
|
|
"loss": 5.8624,
|
|
"mean_token_accuracy": 0.15785117894411088,
|
|
"num_tokens": 24606986.0,
|
|
"step": 12580
|
|
},
|
|
{
|
|
"entropy": 6.122126674652099,
|
|
"epoch": 1.2580096966061878,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00048497747968358424,
|
|
"loss": 5.8975,
|
|
"mean_token_accuracy": 0.1607358291745186,
|
|
"num_tokens": 24617091.0,
|
|
"step": 12585
|
|
},
|
|
{
|
|
"entropy": 6.156837511062622,
|
|
"epoch": 1.2585095216674165,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004849646549798019,
|
|
"loss": 5.9413,
|
|
"mean_token_accuracy": 0.15593989938497543,
|
|
"num_tokens": 24627139.0,
|
|
"step": 12590
|
|
},
|
|
{
|
|
"entropy": 6.296873998641968,
|
|
"epoch": 1.259009346728645,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00048495182499336275,
|
|
"loss": 6.0213,
|
|
"mean_token_accuracy": 0.14943011328577996,
|
|
"num_tokens": 24635632.0,
|
|
"step": 12595
|
|
},
|
|
{
|
|
"entropy": 6.174128866195678,
|
|
"epoch": 1.2595091717898734,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 0.00048493898972458985,
|
|
"loss": 5.9751,
|
|
"mean_token_accuracy": 0.15206774920225144,
|
|
"num_tokens": 24646590.0,
|
|
"step": 12600
|
|
},
|
|
{
|
|
"entropy": 6.177919530868531,
|
|
"epoch": 1.2600089968511021,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004849261491738059,
|
|
"loss": 6.046,
|
|
"mean_token_accuracy": 0.14794811233878136,
|
|
"num_tokens": 24656865.0,
|
|
"step": 12605
|
|
},
|
|
{
|
|
"entropy": 6.223530673980713,
|
|
"epoch": 1.2605088219123306,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00048491330334133405,
|
|
"loss": 6.0435,
|
|
"mean_token_accuracy": 0.14721440821886062,
|
|
"num_tokens": 24666438.0,
|
|
"step": 12610
|
|
},
|
|
{
|
|
"entropy": 6.234167051315308,
|
|
"epoch": 1.2610086469735593,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00048490045222749744,
|
|
"loss": 5.9879,
|
|
"mean_token_accuracy": 0.15502232760190965,
|
|
"num_tokens": 24675935.0,
|
|
"step": 12615
|
|
},
|
|
{
|
|
"entropy": 6.115681171417236,
|
|
"epoch": 1.2615084720347878,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00048488759583261955,
|
|
"loss": 5.8836,
|
|
"mean_token_accuracy": 0.16638837456703187,
|
|
"num_tokens": 24686165.0,
|
|
"step": 12620
|
|
},
|
|
{
|
|
"entropy": 6.1963643550872805,
|
|
"epoch": 1.2620082970960165,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004848747341570238,
|
|
"loss": 5.9733,
|
|
"mean_token_accuracy": 0.1505975231528282,
|
|
"num_tokens": 24696564.0,
|
|
"step": 12625
|
|
},
|
|
{
|
|
"entropy": 6.18072543144226,
|
|
"epoch": 1.262508122157245,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00048486186720103364,
|
|
"loss": 5.9166,
|
|
"mean_token_accuracy": 0.15619558095932007,
|
|
"num_tokens": 24706462.0,
|
|
"step": 12630
|
|
},
|
|
{
|
|
"entropy": 6.1127362728118895,
|
|
"epoch": 1.2630079472184734,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.000484848994964973,
|
|
"loss": 5.9055,
|
|
"mean_token_accuracy": 0.15823880210518837,
|
|
"num_tokens": 24715153.0,
|
|
"step": 12635
|
|
},
|
|
{
|
|
"entropy": 6.076861619949341,
|
|
"epoch": 1.2635077722797021,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.00048483611744916556,
|
|
"loss": 5.9402,
|
|
"mean_token_accuracy": 0.15647810325026512,
|
|
"num_tokens": 24725215.0,
|
|
"step": 12640
|
|
},
|
|
{
|
|
"entropy": 6.097990655899048,
|
|
"epoch": 1.2640075973409306,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.00048482323465393545,
|
|
"loss": 5.9287,
|
|
"mean_token_accuracy": 0.16446128636598586,
|
|
"num_tokens": 24735081.0,
|
|
"step": 12645
|
|
},
|
|
{
|
|
"entropy": 6.158984375,
|
|
"epoch": 1.2645074224021593,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004848103465796067,
|
|
"loss": 5.9042,
|
|
"mean_token_accuracy": 0.16131824851036072,
|
|
"num_tokens": 24744948.0,
|
|
"step": 12650
|
|
},
|
|
{
|
|
"entropy": 6.104265594482422,
|
|
"epoch": 1.2650072474633878,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004847974532265037,
|
|
"loss": 5.9158,
|
|
"mean_token_accuracy": 0.15820914506912231,
|
|
"num_tokens": 24754123.0,
|
|
"step": 12655
|
|
},
|
|
{
|
|
"entropy": 6.1608141422271725,
|
|
"epoch": 1.2655070725246165,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004847845545949507,
|
|
"loss": 6.0207,
|
|
"mean_token_accuracy": 0.14851216673851014,
|
|
"num_tokens": 24763864.0,
|
|
"step": 12660
|
|
},
|
|
{
|
|
"entropy": 6.2003148078918455,
|
|
"epoch": 1.266006897585845,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00048477165068527237,
|
|
"loss": 6.0028,
|
|
"mean_token_accuracy": 0.15384961515665055,
|
|
"num_tokens": 24774088.0,
|
|
"step": 12665
|
|
},
|
|
{
|
|
"entropy": 6.185011291503907,
|
|
"epoch": 1.2665067226470734,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.00048475874149779313,
|
|
"loss": 5.9237,
|
|
"mean_token_accuracy": 0.16217005923390387,
|
|
"num_tokens": 24782485.0,
|
|
"step": 12670
|
|
},
|
|
{
|
|
"entropy": 6.165617418289185,
|
|
"epoch": 1.2670065477083021,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.000484745827032838,
|
|
"loss": 5.927,
|
|
"mean_token_accuracy": 0.15649309605360032,
|
|
"num_tokens": 24791776.0,
|
|
"step": 12675
|
|
},
|
|
{
|
|
"entropy": 6.19484167098999,
|
|
"epoch": 1.2675063727695306,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.00048473290729073194,
|
|
"loss": 5.9892,
|
|
"mean_token_accuracy": 0.1556473195552826,
|
|
"num_tokens": 24802053.0,
|
|
"step": 12680
|
|
},
|
|
{
|
|
"entropy": 6.1477924346923825,
|
|
"epoch": 1.2680061978307593,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004847199822717998,
|
|
"loss": 5.9218,
|
|
"mean_token_accuracy": 0.15525194704532624,
|
|
"num_tokens": 24811235.0,
|
|
"step": 12685
|
|
},
|
|
{
|
|
"entropy": 6.190126228332519,
|
|
"epoch": 1.2685060228919878,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004847070519763668,
|
|
"loss": 6.0308,
|
|
"mean_token_accuracy": 0.14525450244545937,
|
|
"num_tokens": 24821904.0,
|
|
"step": 12690
|
|
},
|
|
{
|
|
"entropy": 6.148566150665284,
|
|
"epoch": 1.2690058479532165,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004846941164047585,
|
|
"loss": 5.9223,
|
|
"mean_token_accuracy": 0.15534555315971374,
|
|
"num_tokens": 24831555.0,
|
|
"step": 12695
|
|
},
|
|
{
|
|
"entropy": 6.306117582321167,
|
|
"epoch": 1.269505673014445,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00048468117555730013,
|
|
"loss": 6.0668,
|
|
"mean_token_accuracy": 0.15397983714938163,
|
|
"num_tokens": 24841840.0,
|
|
"step": 12700
|
|
},
|
|
{
|
|
"entropy": 6.118523263931275,
|
|
"epoch": 1.2700054980756734,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004846682294343173,
|
|
"loss": 5.9343,
|
|
"mean_token_accuracy": 0.15664737299084663,
|
|
"num_tokens": 24850172.0,
|
|
"step": 12705
|
|
},
|
|
{
|
|
"entropy": 6.175709772109985,
|
|
"epoch": 1.2705053231369021,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004846552780361358,
|
|
"loss": 5.9189,
|
|
"mean_token_accuracy": 0.15455542802810668,
|
|
"num_tokens": 24860433.0,
|
|
"step": 12710
|
|
},
|
|
{
|
|
"entropy": 6.2268554210662845,
|
|
"epoch": 1.2710051481981306,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00048464232136308146,
|
|
"loss": 5.9968,
|
|
"mean_token_accuracy": 0.15506697446107864,
|
|
"num_tokens": 24870677.0,
|
|
"step": 12715
|
|
},
|
|
{
|
|
"entropy": 6.203292798995972,
|
|
"epoch": 1.2715049732593593,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004846293594154802,
|
|
"loss": 5.9956,
|
|
"mean_token_accuracy": 0.15151088386774064,
|
|
"num_tokens": 24881804.0,
|
|
"step": 12720
|
|
},
|
|
{
|
|
"entropy": 6.167476034164428,
|
|
"epoch": 1.2720047983205878,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004846163921936583,
|
|
"loss": 5.9184,
|
|
"mean_token_accuracy": 0.1620791420340538,
|
|
"num_tokens": 24892632.0,
|
|
"step": 12725
|
|
},
|
|
{
|
|
"entropy": 6.171008062362671,
|
|
"epoch": 1.2725046233818165,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00048460341969794183,
|
|
"loss": 5.9572,
|
|
"mean_token_accuracy": 0.15405600816011428,
|
|
"num_tokens": 24902055.0,
|
|
"step": 12730
|
|
},
|
|
{
|
|
"entropy": 6.235155916213989,
|
|
"epoch": 1.273004448443045,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00048459044192865726,
|
|
"loss": 6.081,
|
|
"mean_token_accuracy": 0.14752552807331085,
|
|
"num_tokens": 24912450.0,
|
|
"step": 12735
|
|
},
|
|
{
|
|
"entropy": 6.225162410736084,
|
|
"epoch": 1.2735042735042734,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004845774588861311,
|
|
"loss": 5.9905,
|
|
"mean_token_accuracy": 0.15358151495456696,
|
|
"num_tokens": 24922206.0,
|
|
"step": 12740
|
|
},
|
|
{
|
|
"entropy": 6.1136133670806885,
|
|
"epoch": 1.2740040985655021,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00048456447057069004,
|
|
"loss": 5.7777,
|
|
"mean_token_accuracy": 0.16790566295385362,
|
|
"num_tokens": 24931295.0,
|
|
"step": 12745
|
|
},
|
|
{
|
|
"entropy": 6.075013589859009,
|
|
"epoch": 1.2745039236267306,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00048455147698266084,
|
|
"loss": 5.8873,
|
|
"mean_token_accuracy": 0.16287400871515273,
|
|
"num_tokens": 24940979.0,
|
|
"step": 12750
|
|
},
|
|
{
|
|
"entropy": 6.0834370136260985,
|
|
"epoch": 1.2750037486879593,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004845384781223703,
|
|
"loss": 5.9452,
|
|
"mean_token_accuracy": 0.15070963203907012,
|
|
"num_tokens": 24950704.0,
|
|
"step": 12755
|
|
},
|
|
{
|
|
"entropy": 6.237839412689209,
|
|
"epoch": 1.2755035737491878,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00048452547399014566,
|
|
"loss": 6.032,
|
|
"mean_token_accuracy": 0.15142979919910432,
|
|
"num_tokens": 24961667.0,
|
|
"step": 12760
|
|
},
|
|
{
|
|
"entropy": 6.181571531295776,
|
|
"epoch": 1.2760033988104165,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.000484512464586314,
|
|
"loss": 5.982,
|
|
"mean_token_accuracy": 0.15340655744075776,
|
|
"num_tokens": 24971531.0,
|
|
"step": 12765
|
|
},
|
|
{
|
|
"entropy": 6.122630310058594,
|
|
"epoch": 1.276503223871645,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00048449944991120264,
|
|
"loss": 5.8567,
|
|
"mean_token_accuracy": 0.1574491396546364,
|
|
"num_tokens": 24981002.0,
|
|
"step": 12770
|
|
},
|
|
{
|
|
"entropy": 6.146213483810425,
|
|
"epoch": 1.2770030489328734,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004844864299651391,
|
|
"loss": 5.945,
|
|
"mean_token_accuracy": 0.1571796491742134,
|
|
"num_tokens": 24990402.0,
|
|
"step": 12775
|
|
},
|
|
{
|
|
"entropy": 6.0939295291900635,
|
|
"epoch": 1.2775028739941021,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00048447340474845076,
|
|
"loss": 5.8885,
|
|
"mean_token_accuracy": 0.1661619082093239,
|
|
"num_tokens": 24999399.0,
|
|
"step": 12780
|
|
},
|
|
{
|
|
"entropy": 6.019286012649536,
|
|
"epoch": 1.2780026990553306,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00048446037426146555,
|
|
"loss": 5.7372,
|
|
"mean_token_accuracy": 0.1805116832256317,
|
|
"num_tokens": 25010411.0,
|
|
"step": 12785
|
|
},
|
|
{
|
|
"entropy": 6.23597149848938,
|
|
"epoch": 1.278502524116559,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004844473385045112,
|
|
"loss": 6.0329,
|
|
"mean_token_accuracy": 0.1500043675303459,
|
|
"num_tokens": 25019834.0,
|
|
"step": 12790
|
|
},
|
|
{
|
|
"entropy": 6.212685489654541,
|
|
"epoch": 1.2790023491777878,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004844342974779157,
|
|
"loss": 6.0253,
|
|
"mean_token_accuracy": 0.15458481535315513,
|
|
"num_tokens": 25030331.0,
|
|
"step": 12795
|
|
},
|
|
{
|
|
"entropy": 6.175279235839843,
|
|
"epoch": 1.2795021742390165,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00048442125118200707,
|
|
"loss": 5.9306,
|
|
"mean_token_accuracy": 0.15867668390274048,
|
|
"num_tokens": 25040369.0,
|
|
"step": 12800
|
|
},
|
|
{
|
|
"entropy": 6.125909233093262,
|
|
"epoch": 1.280001999300245,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004844081996171137,
|
|
"loss": 5.8994,
|
|
"mean_token_accuracy": 0.16179734468460083,
|
|
"num_tokens": 25049798.0,
|
|
"step": 12805
|
|
},
|
|
{
|
|
"entropy": 6.233055496215821,
|
|
"epoch": 1.2805018243614734,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.000484395142783564,
|
|
"loss": 5.9719,
|
|
"mean_token_accuracy": 0.15110021233558654,
|
|
"num_tokens": 25060982.0,
|
|
"step": 12810
|
|
},
|
|
{
|
|
"entropy": 6.181978225708008,
|
|
"epoch": 1.2810016494227021,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004843820806816863,
|
|
"loss": 6.0458,
|
|
"mean_token_accuracy": 0.1447092741727829,
|
|
"num_tokens": 25070532.0,
|
|
"step": 12815
|
|
},
|
|
{
|
|
"entropy": 6.149425745010376,
|
|
"epoch": 1.2815014744839306,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004843690133118094,
|
|
"loss": 5.9561,
|
|
"mean_token_accuracy": 0.16143618375062943,
|
|
"num_tokens": 25080146.0,
|
|
"step": 12820
|
|
},
|
|
{
|
|
"entropy": 6.084601259231567,
|
|
"epoch": 1.282001299545159,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.000484355940674262,
|
|
"loss": 5.9208,
|
|
"mean_token_accuracy": 0.15589116215705873,
|
|
"num_tokens": 25090758.0,
|
|
"step": 12825
|
|
},
|
|
{
|
|
"entropy": 6.106634092330933,
|
|
"epoch": 1.2825011246063878,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00048434286276937294,
|
|
"loss": 5.9725,
|
|
"mean_token_accuracy": 0.1615099087357521,
|
|
"num_tokens": 25100735.0,
|
|
"step": 12830
|
|
},
|
|
{
|
|
"entropy": 6.157269430160523,
|
|
"epoch": 1.2830009496676165,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004843297795974713,
|
|
"loss": 5.9329,
|
|
"mean_token_accuracy": 0.1614208459854126,
|
|
"num_tokens": 25110996.0,
|
|
"step": 12835
|
|
},
|
|
{
|
|
"entropy": 6.243693494796753,
|
|
"epoch": 1.283500774728845,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004843166911588864,
|
|
"loss": 5.8845,
|
|
"mean_token_accuracy": 0.1576448991894722,
|
|
"num_tokens": 25119720.0,
|
|
"step": 12840
|
|
},
|
|
{
|
|
"entropy": 6.1188921451568605,
|
|
"epoch": 1.2840005997900734,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004843035974539473,
|
|
"loss": 5.984,
|
|
"mean_token_accuracy": 0.15494607985019684,
|
|
"num_tokens": 25129916.0,
|
|
"step": 12845
|
|
},
|
|
{
|
|
"entropy": 6.175960302352905,
|
|
"epoch": 1.2845004248513021,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00048429049848298364,
|
|
"loss": 6.0163,
|
|
"mean_token_accuracy": 0.15332424342632295,
|
|
"num_tokens": 25138647.0,
|
|
"step": 12850
|
|
},
|
|
{
|
|
"entropy": 6.221134233474731,
|
|
"epoch": 1.2850002499125306,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.00048427739424632485,
|
|
"loss": 5.8836,
|
|
"mean_token_accuracy": 0.1586208239197731,
|
|
"num_tokens": 25146621.0,
|
|
"step": 12855
|
|
},
|
|
{
|
|
"entropy": 6.157750034332276,
|
|
"epoch": 1.285500074973759,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00048426428474430055,
|
|
"loss": 6.0018,
|
|
"mean_token_accuracy": 0.15330712497234344,
|
|
"num_tokens": 25158600.0,
|
|
"step": 12860
|
|
},
|
|
{
|
|
"entropy": 6.158607864379883,
|
|
"epoch": 1.2859999000349878,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00048425116997724083,
|
|
"loss": 5.9212,
|
|
"mean_token_accuracy": 0.156647789478302,
|
|
"num_tokens": 25169051.0,
|
|
"step": 12865
|
|
},
|
|
{
|
|
"entropy": 6.1217035293579105,
|
|
"epoch": 1.2864997250962165,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.00048423804994547555,
|
|
"loss": 5.8521,
|
|
"mean_token_accuracy": 0.1661289304494858,
|
|
"num_tokens": 25177866.0,
|
|
"step": 12870
|
|
},
|
|
{
|
|
"entropy": 6.149631309509277,
|
|
"epoch": 1.286999550157445,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00048422492464933464,
|
|
"loss": 5.9288,
|
|
"mean_token_accuracy": 0.15456630736589433,
|
|
"num_tokens": 25186868.0,
|
|
"step": 12875
|
|
},
|
|
{
|
|
"entropy": 6.131720781326294,
|
|
"epoch": 1.2874993752186734,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00048421179408914857,
|
|
"loss": 6.028,
|
|
"mean_token_accuracy": 0.15176038071513176,
|
|
"num_tokens": 25196682.0,
|
|
"step": 12880
|
|
},
|
|
{
|
|
"entropy": 6.200189828872681,
|
|
"epoch": 1.2879992002799021,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.00048419865826524757,
|
|
"loss": 6.0082,
|
|
"mean_token_accuracy": 0.15438259541988372,
|
|
"num_tokens": 25206326.0,
|
|
"step": 12885
|
|
},
|
|
{
|
|
"entropy": 6.207353925704956,
|
|
"epoch": 1.2884990253411306,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00048418551717796217,
|
|
"loss": 6.0186,
|
|
"mean_token_accuracy": 0.14796894490718843,
|
|
"num_tokens": 25216499.0,
|
|
"step": 12890
|
|
},
|
|
{
|
|
"entropy": 6.174864959716797,
|
|
"epoch": 1.288998850402359,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00048417237082762295,
|
|
"loss": 5.8844,
|
|
"mean_token_accuracy": 0.161013862490654,
|
|
"num_tokens": 25226854.0,
|
|
"step": 12895
|
|
},
|
|
{
|
|
"entropy": 6.243460988998413,
|
|
"epoch": 1.2894986754635878,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.00048415921921456074,
|
|
"loss": 6.1354,
|
|
"mean_token_accuracy": 0.14885302856564522,
|
|
"num_tokens": 25237536.0,
|
|
"step": 12900
|
|
},
|
|
{
|
|
"entropy": 6.129333019256592,
|
|
"epoch": 1.2899985005248162,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.00048414606233910634,
|
|
"loss": 5.8832,
|
|
"mean_token_accuracy": 0.15784451216459275,
|
|
"num_tokens": 25246536.0,
|
|
"step": 12905
|
|
},
|
|
{
|
|
"entropy": 6.130053901672364,
|
|
"epoch": 1.290498325586045,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004841329002015909,
|
|
"loss": 5.9771,
|
|
"mean_token_accuracy": 0.15738071799278258,
|
|
"num_tokens": 25256305.0,
|
|
"step": 12910
|
|
},
|
|
{
|
|
"entropy": 6.176922941207886,
|
|
"epoch": 1.2909981506472734,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00048411973280234553,
|
|
"loss": 5.8917,
|
|
"mean_token_accuracy": 0.16168347746133804,
|
|
"num_tokens": 25265691.0,
|
|
"step": 12915
|
|
},
|
|
{
|
|
"entropy": 6.237619161605835,
|
|
"epoch": 1.291497975708502,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.00048410656014170135,
|
|
"loss": 6.0088,
|
|
"mean_token_accuracy": 0.15427018851041793,
|
|
"num_tokens": 25275963.0,
|
|
"step": 12920
|
|
},
|
|
{
|
|
"entropy": 6.160730504989624,
|
|
"epoch": 1.2919978007697306,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00048409338221999,
|
|
"loss": 5.9387,
|
|
"mean_token_accuracy": 0.1586361676454544,
|
|
"num_tokens": 25286646.0,
|
|
"step": 12925
|
|
},
|
|
{
|
|
"entropy": 6.117222499847412,
|
|
"epoch": 1.292497625830959,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00048408019903754297,
|
|
"loss": 5.9795,
|
|
"mean_token_accuracy": 0.15848901569843293,
|
|
"num_tokens": 25296144.0,
|
|
"step": 12930
|
|
},
|
|
{
|
|
"entropy": 6.15462851524353,
|
|
"epoch": 1.2929974508921878,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.000484067010594692,
|
|
"loss": 5.9774,
|
|
"mean_token_accuracy": 0.14803930819034578,
|
|
"num_tokens": 25306802.0,
|
|
"step": 12935
|
|
},
|
|
{
|
|
"entropy": 6.1699628829956055,
|
|
"epoch": 1.2934972759534162,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00048405381689176877,
|
|
"loss": 5.9325,
|
|
"mean_token_accuracy": 0.15921355336904525,
|
|
"num_tokens": 25316021.0,
|
|
"step": 12940
|
|
},
|
|
{
|
|
"entropy": 6.156700944900512,
|
|
"epoch": 1.293997101014645,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00048404061792910527,
|
|
"loss": 5.9056,
|
|
"mean_token_accuracy": 0.15876879990100862,
|
|
"num_tokens": 25325583.0,
|
|
"step": 12945
|
|
},
|
|
{
|
|
"entropy": 6.0968907356262205,
|
|
"epoch": 1.2944969260758734,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.00048402741370703363,
|
|
"loss": 5.9253,
|
|
"mean_token_accuracy": 0.15834522992372513,
|
|
"num_tokens": 25335046.0,
|
|
"step": 12950
|
|
},
|
|
{
|
|
"entropy": 6.183151912689209,
|
|
"epoch": 1.294996751137102,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004840142042258861,
|
|
"loss": 5.9926,
|
|
"mean_token_accuracy": 0.146283096075058,
|
|
"num_tokens": 25344180.0,
|
|
"step": 12955
|
|
},
|
|
{
|
|
"entropy": 6.1754312992095945,
|
|
"epoch": 1.2954965761983306,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.000484000989485995,
|
|
"loss": 5.9001,
|
|
"mean_token_accuracy": 0.15345722287893296,
|
|
"num_tokens": 25353131.0,
|
|
"step": 12960
|
|
},
|
|
{
|
|
"entropy": 6.173001050949097,
|
|
"epoch": 1.295996401259559,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00048398776948769265,
|
|
"loss": 5.9602,
|
|
"mean_token_accuracy": 0.1508757397532463,
|
|
"num_tokens": 25362546.0,
|
|
"step": 12965
|
|
},
|
|
{
|
|
"entropy": 6.095330095291137,
|
|
"epoch": 1.2964962263207878,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004839745442313119,
|
|
"loss": 5.8368,
|
|
"mean_token_accuracy": 0.1665271058678627,
|
|
"num_tokens": 25372773.0,
|
|
"step": 12970
|
|
},
|
|
{
|
|
"entropy": 6.1797911643981935,
|
|
"epoch": 1.2969960513820162,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.00048396131371718535,
|
|
"loss": 5.909,
|
|
"mean_token_accuracy": 0.15641495883464812,
|
|
"num_tokens": 25382459.0,
|
|
"step": 12975
|
|
},
|
|
{
|
|
"entropy": 6.12809796333313,
|
|
"epoch": 1.297495876443245,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.00048394807794564586,
|
|
"loss": 5.9063,
|
|
"mean_token_accuracy": 0.15339850038290023,
|
|
"num_tokens": 25392561.0,
|
|
"step": 12980
|
|
},
|
|
{
|
|
"entropy": 6.064737224578858,
|
|
"epoch": 1.2979957015044734,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004839348369170266,
|
|
"loss": 5.841,
|
|
"mean_token_accuracy": 0.1741722121834755,
|
|
"num_tokens": 25402250.0,
|
|
"step": 12985
|
|
},
|
|
{
|
|
"entropy": 6.094322633743286,
|
|
"epoch": 1.298495526565702,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00048392159063166055,
|
|
"loss": 5.8954,
|
|
"mean_token_accuracy": 0.15702453404664993,
|
|
"num_tokens": 25411813.0,
|
|
"step": 12990
|
|
},
|
|
{
|
|
"entropy": 6.075023031234741,
|
|
"epoch": 1.2989953516269306,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004839083390898811,
|
|
"loss": 5.8913,
|
|
"mean_token_accuracy": 0.16241199374198914,
|
|
"num_tokens": 25421232.0,
|
|
"step": 12995
|
|
},
|
|
{
|
|
"entropy": 6.129521274566651,
|
|
"epoch": 1.299495176688159,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004838950822920215,
|
|
"loss": 5.9502,
|
|
"mean_token_accuracy": 0.15682778358459473,
|
|
"num_tokens": 25430617.0,
|
|
"step": 13000
|
|
},
|
|
{
|
|
"entropy": 6.118180274963379,
|
|
"epoch": 1.2999950017493878,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0004838818202384155,
|
|
"loss": 5.8628,
|
|
"mean_token_accuracy": 0.16855358183383942,
|
|
"num_tokens": 25440514.0,
|
|
"step": 13005
|
|
},
|
|
{
|
|
"entropy": 6.249346446990967,
|
|
"epoch": 1.3004948268106162,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.00048386855292939664,
|
|
"loss": 6.0214,
|
|
"mean_token_accuracy": 0.15124907046556474,
|
|
"num_tokens": 25450058.0,
|
|
"step": 13010
|
|
},
|
|
{
|
|
"entropy": 6.165060186386109,
|
|
"epoch": 1.300994651871845,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004838552803652986,
|
|
"loss": 5.923,
|
|
"mean_token_accuracy": 0.15582990944385527,
|
|
"num_tokens": 25459418.0,
|
|
"step": 13015
|
|
},
|
|
{
|
|
"entropy": 6.1334309577941895,
|
|
"epoch": 1.3014944769330734,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00048384200254645557,
|
|
"loss": 6.019,
|
|
"mean_token_accuracy": 0.1524246908724308,
|
|
"num_tokens": 25468944.0,
|
|
"step": 13020
|
|
},
|
|
{
|
|
"entropy": 6.103222942352295,
|
|
"epoch": 1.301994301994302,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00048382871947320145,
|
|
"loss": 5.8882,
|
|
"mean_token_accuracy": 0.16581465154886246,
|
|
"num_tokens": 25478072.0,
|
|
"step": 13025
|
|
},
|
|
{
|
|
"entropy": 6.1755729675292965,
|
|
"epoch": 1.3024941270555306,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004838154311458705,
|
|
"loss": 6.004,
|
|
"mean_token_accuracy": 0.1543924868106842,
|
|
"num_tokens": 25488301.0,
|
|
"step": 13030
|
|
},
|
|
{
|
|
"entropy": 6.201048851013184,
|
|
"epoch": 1.302993952116759,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.00048380213756479704,
|
|
"loss": 5.9731,
|
|
"mean_token_accuracy": 0.14989329874515533,
|
|
"num_tokens": 25498343.0,
|
|
"step": 13035
|
|
},
|
|
{
|
|
"entropy": 6.233013343811035,
|
|
"epoch": 1.3034937771779878,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00048378883873031553,
|
|
"loss": 6.0593,
|
|
"mean_token_accuracy": 0.15224601328372955,
|
|
"num_tokens": 25509302.0,
|
|
"step": 13040
|
|
},
|
|
{
|
|
"entropy": 6.189176416397094,
|
|
"epoch": 1.3039936022392162,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004837755346427605,
|
|
"loss": 5.9774,
|
|
"mean_token_accuracy": 0.15510757267475128,
|
|
"num_tokens": 25520246.0,
|
|
"step": 13045
|
|
},
|
|
{
|
|
"entropy": 6.155944013595581,
|
|
"epoch": 1.3044934273004447,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00048376222530246684,
|
|
"loss": 5.9385,
|
|
"mean_token_accuracy": 0.156169556081295,
|
|
"num_tokens": 25528879.0,
|
|
"step": 13050
|
|
},
|
|
{
|
|
"entropy": 6.1424487113952635,
|
|
"epoch": 1.3049932523616734,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00048374891070976925,
|
|
"loss": 5.9378,
|
|
"mean_token_accuracy": 0.1628851920366287,
|
|
"num_tokens": 25538029.0,
|
|
"step": 13055
|
|
},
|
|
{
|
|
"entropy": 6.1625477313995365,
|
|
"epoch": 1.305493077422902,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004837355908650028,
|
|
"loss": 5.9768,
|
|
"mean_token_accuracy": 0.15717717111110688,
|
|
"num_tokens": 25547752.0,
|
|
"step": 13060
|
|
},
|
|
{
|
|
"entropy": 6.176790523529053,
|
|
"epoch": 1.3059929024841306,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004837222657685026,
|
|
"loss": 5.9496,
|
|
"mean_token_accuracy": 0.16078850328922273,
|
|
"num_tokens": 25558197.0,
|
|
"step": 13065
|
|
},
|
|
{
|
|
"entropy": 6.185945749282837,
|
|
"epoch": 1.306492727545359,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00048370893542060383,
|
|
"loss": 5.9793,
|
|
"mean_token_accuracy": 0.15298392549157142,
|
|
"num_tokens": 25569910.0,
|
|
"step": 13070
|
|
},
|
|
{
|
|
"entropy": 6.212973117828369,
|
|
"epoch": 1.3069925526065878,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004836955998216421,
|
|
"loss": 5.9926,
|
|
"mean_token_accuracy": 0.15732813775539398,
|
|
"num_tokens": 25579069.0,
|
|
"step": 13075
|
|
},
|
|
{
|
|
"entropy": 6.192774963378906,
|
|
"epoch": 1.3074923776678162,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00048368225897195264,
|
|
"loss": 5.9684,
|
|
"mean_token_accuracy": 0.15628271400928498,
|
|
"num_tokens": 25588164.0,
|
|
"step": 13080
|
|
},
|
|
{
|
|
"entropy": 6.116890621185303,
|
|
"epoch": 1.3079922027290447,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00048366891287187133,
|
|
"loss": 6.0194,
|
|
"mean_token_accuracy": 0.1481206849217415,
|
|
"num_tokens": 25598741.0,
|
|
"step": 13085
|
|
},
|
|
{
|
|
"entropy": 6.0692455768585205,
|
|
"epoch": 1.3084920277902734,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004836555615217337,
|
|
"loss": 5.8395,
|
|
"mean_token_accuracy": 0.16094954013824464,
|
|
"num_tokens": 25608572.0,
|
|
"step": 13090
|
|
},
|
|
{
|
|
"entropy": 6.135541534423828,
|
|
"epoch": 1.308991852851502,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.0004836422049218761,
|
|
"loss": 5.8578,
|
|
"mean_token_accuracy": 0.16072544902563096,
|
|
"num_tokens": 25617686.0,
|
|
"step": 13095
|
|
},
|
|
{
|
|
"entropy": 6.057381725311279,
|
|
"epoch": 1.3094916779127306,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00048362884307263416,
|
|
"loss": 5.8695,
|
|
"mean_token_accuracy": 0.15520852208137512,
|
|
"num_tokens": 25627268.0,
|
|
"step": 13100
|
|
},
|
|
{
|
|
"entropy": 6.121604585647583,
|
|
"epoch": 1.309991502973959,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.00048361547597434426,
|
|
"loss": 5.8561,
|
|
"mean_token_accuracy": 0.15929325371980668,
|
|
"num_tokens": 25636341.0,
|
|
"step": 13105
|
|
},
|
|
{
|
|
"entropy": 6.212964248657227,
|
|
"epoch": 1.3104913280351878,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.00048360210362734257,
|
|
"loss": 6.0031,
|
|
"mean_token_accuracy": 0.15165067762136458,
|
|
"num_tokens": 25645403.0,
|
|
"step": 13110
|
|
},
|
|
{
|
|
"entropy": 6.137271213531494,
|
|
"epoch": 1.3109911530964162,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004835887260319657,
|
|
"loss": 5.9577,
|
|
"mean_token_accuracy": 0.16124185621738435,
|
|
"num_tokens": 25656062.0,
|
|
"step": 13115
|
|
},
|
|
{
|
|
"entropy": 6.097936201095581,
|
|
"epoch": 1.3114909781576447,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004835753431885502,
|
|
"loss": 5.8483,
|
|
"mean_token_accuracy": 0.1620157927274704,
|
|
"num_tokens": 25665449.0,
|
|
"step": 13120
|
|
},
|
|
{
|
|
"entropy": 6.081419849395752,
|
|
"epoch": 1.3119908032188734,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00048356195509743265,
|
|
"loss": 5.9227,
|
|
"mean_token_accuracy": 0.15958764851093293,
|
|
"num_tokens": 25674844.0,
|
|
"step": 13125
|
|
},
|
|
{
|
|
"entropy": 6.166410684585571,
|
|
"epoch": 1.312490628280102,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.00048354856175895,
|
|
"loss": 6.0375,
|
|
"mean_token_accuracy": 0.14873254373669625,
|
|
"num_tokens": 25686058.0,
|
|
"step": 13130
|
|
},
|
|
{
|
|
"entropy": 6.212475347518921,
|
|
"epoch": 1.3129904533413306,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004835351631734392,
|
|
"loss": 5.9679,
|
|
"mean_token_accuracy": 0.15593373030424118,
|
|
"num_tokens": 25696000.0,
|
|
"step": 13135
|
|
},
|
|
{
|
|
"entropy": 6.1812999725341795,
|
|
"epoch": 1.313490278402559,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004835217593412374,
|
|
"loss": 5.8802,
|
|
"mean_token_accuracy": 0.1658456340432167,
|
|
"num_tokens": 25705912.0,
|
|
"step": 13140
|
|
},
|
|
{
|
|
"entropy": 6.050013256072998,
|
|
"epoch": 1.3139901034637878,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004835083502626818,
|
|
"loss": 5.8605,
|
|
"mean_token_accuracy": 0.159502974152565,
|
|
"num_tokens": 25716288.0,
|
|
"step": 13145
|
|
},
|
|
{
|
|
"entropy": 6.171238851547241,
|
|
"epoch": 1.3144899285250162,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00048349493593810973,
|
|
"loss": 5.9794,
|
|
"mean_token_accuracy": 0.15527609884738922,
|
|
"num_tokens": 25726235.0,
|
|
"step": 13150
|
|
},
|
|
{
|
|
"entropy": 6.15140290260315,
|
|
"epoch": 1.3149897535862447,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004834815163678587,
|
|
"loss": 5.969,
|
|
"mean_token_accuracy": 0.15463163778185846,
|
|
"num_tokens": 25735740.0,
|
|
"step": 13155
|
|
},
|
|
{
|
|
"entropy": 6.101669502258301,
|
|
"epoch": 1.3154895786474734,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004834680915522664,
|
|
"loss": 5.8612,
|
|
"mean_token_accuracy": 0.16768842488527297,
|
|
"num_tokens": 25744500.0,
|
|
"step": 13160
|
|
},
|
|
{
|
|
"entropy": 6.164356136322022,
|
|
"epoch": 1.3159894037087019,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004834546614916705,
|
|
"loss": 5.9321,
|
|
"mean_token_accuracy": 0.16489131450653077,
|
|
"num_tokens": 25754798.0,
|
|
"step": 13165
|
|
},
|
|
{
|
|
"entropy": 6.170533752441406,
|
|
"epoch": 1.3164892287699306,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00048344122618640905,
|
|
"loss": 5.9023,
|
|
"mean_token_accuracy": 0.16477506160736083,
|
|
"num_tokens": 25764985.0,
|
|
"step": 13170
|
|
},
|
|
{
|
|
"entropy": 6.177911233901978,
|
|
"epoch": 1.316989053831159,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004834277856368199,
|
|
"loss": 5.9171,
|
|
"mean_token_accuracy": 0.1580347090959549,
|
|
"num_tokens": 25775929.0,
|
|
"step": 13175
|
|
},
|
|
{
|
|
"entropy": 6.243767786026001,
|
|
"epoch": 1.3174888788923877,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.00048341433984324127,
|
|
"loss": 6.1217,
|
|
"mean_token_accuracy": 0.1444265626370907,
|
|
"num_tokens": 25786319.0,
|
|
"step": 13180
|
|
},
|
|
{
|
|
"entropy": 6.097338485717773,
|
|
"epoch": 1.3179887039536162,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00048340088880601163,
|
|
"loss": 5.9411,
|
|
"mean_token_accuracy": 0.15827794075012208,
|
|
"num_tokens": 25796394.0,
|
|
"step": 13185
|
|
},
|
|
{
|
|
"entropy": 6.164988040924072,
|
|
"epoch": 1.3184885290148447,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004833874325254691,
|
|
"loss": 5.8826,
|
|
"mean_token_accuracy": 0.15987986475229263,
|
|
"num_tokens": 25805965.0,
|
|
"step": 13190
|
|
},
|
|
{
|
|
"entropy": 6.20246057510376,
|
|
"epoch": 1.3189883540760734,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00048337397100195245,
|
|
"loss": 5.9191,
|
|
"mean_token_accuracy": 0.15538064688444136,
|
|
"num_tokens": 25816219.0,
|
|
"step": 13195
|
|
},
|
|
{
|
|
"entropy": 6.187918090820313,
|
|
"epoch": 1.3194881791373019,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004833605042358003,
|
|
"loss": 5.9871,
|
|
"mean_token_accuracy": 0.1588281899690628,
|
|
"num_tokens": 25826263.0,
|
|
"step": 13200
|
|
},
|
|
{
|
|
"entropy": 6.1791199207305905,
|
|
"epoch": 1.3199880041985306,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004833470322273515,
|
|
"loss": 5.9675,
|
|
"mean_token_accuracy": 0.15493707805871965,
|
|
"num_tokens": 25836262.0,
|
|
"step": 13205
|
|
},
|
|
{
|
|
"entropy": 6.1938573837280275,
|
|
"epoch": 1.320487829259759,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00048333355497694506,
|
|
"loss": 5.8877,
|
|
"mean_token_accuracy": 0.1619814544916153,
|
|
"num_tokens": 25845906.0,
|
|
"step": 13210
|
|
},
|
|
{
|
|
"entropy": 6.092811155319214,
|
|
"epoch": 1.3209876543209877,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004833200724849199,
|
|
"loss": 5.8757,
|
|
"mean_token_accuracy": 0.16639862358570098,
|
|
"num_tokens": 25856251.0,
|
|
"step": 13215
|
|
},
|
|
{
|
|
"entropy": 6.079971075057983,
|
|
"epoch": 1.3214874793822162,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00048330658475161526,
|
|
"loss": 5.9503,
|
|
"mean_token_accuracy": 0.16594918742775916,
|
|
"num_tokens": 25866695.0,
|
|
"step": 13220
|
|
},
|
|
{
|
|
"entropy": 6.146766662597656,
|
|
"epoch": 1.3219873044434447,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004832930917773706,
|
|
"loss": 6.0106,
|
|
"mean_token_accuracy": 0.15031296908855438,
|
|
"num_tokens": 25877208.0,
|
|
"step": 13225
|
|
},
|
|
{
|
|
"entropy": 6.221292495727539,
|
|
"epoch": 1.3224871295046734,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.00048327959356252544,
|
|
"loss": 5.889,
|
|
"mean_token_accuracy": 0.162984199821949,
|
|
"num_tokens": 25887062.0,
|
|
"step": 13230
|
|
},
|
|
{
|
|
"entropy": 6.237447357177734,
|
|
"epoch": 1.3229869545659019,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004832660901074192,
|
|
"loss": 5.9903,
|
|
"mean_token_accuracy": 0.15430379658937454,
|
|
"num_tokens": 25896410.0,
|
|
"step": 13235
|
|
},
|
|
{
|
|
"entropy": 6.095164155960083,
|
|
"epoch": 1.3234867796271306,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.00048325258141239174,
|
|
"loss": 5.8512,
|
|
"mean_token_accuracy": 0.16410801857709884,
|
|
"num_tokens": 25905085.0,
|
|
"step": 13240
|
|
},
|
|
{
|
|
"entropy": 6.1868115901947025,
|
|
"epoch": 1.323986604688359,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004832390674777829,
|
|
"loss": 5.9324,
|
|
"mean_token_accuracy": 0.15469116270542144,
|
|
"num_tokens": 25914334.0,
|
|
"step": 13245
|
|
},
|
|
{
|
|
"entropy": 6.152792739868164,
|
|
"epoch": 1.3244864297495877,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.00048322554830393274,
|
|
"loss": 5.9387,
|
|
"mean_token_accuracy": 0.15107419788837434,
|
|
"num_tokens": 25922676.0,
|
|
"step": 13250
|
|
},
|
|
{
|
|
"entropy": 6.171576642990113,
|
|
"epoch": 1.3249862548108162,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004832120238911813,
|
|
"loss": 5.9645,
|
|
"mean_token_accuracy": 0.16050836443901062,
|
|
"num_tokens": 25931910.0,
|
|
"step": 13255
|
|
},
|
|
{
|
|
"entropy": 6.096503114700317,
|
|
"epoch": 1.3254860798720447,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.000483198494239869,
|
|
"loss": 5.8261,
|
|
"mean_token_accuracy": 0.16611166894435883,
|
|
"num_tokens": 25942713.0,
|
|
"step": 13260
|
|
},
|
|
{
|
|
"entropy": 6.09018497467041,
|
|
"epoch": 1.3259859049332734,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00048318495935033615,
|
|
"loss": 5.8314,
|
|
"mean_token_accuracy": 0.16736013144254686,
|
|
"num_tokens": 25951462.0,
|
|
"step": 13265
|
|
},
|
|
{
|
|
"entropy": 6.180334424972534,
|
|
"epoch": 1.3264857299945019,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.00048317141922292326,
|
|
"loss": 5.8896,
|
|
"mean_token_accuracy": 0.1599945217370987,
|
|
"num_tokens": 25961172.0,
|
|
"step": 13270
|
|
},
|
|
{
|
|
"entropy": 6.131149339675903,
|
|
"epoch": 1.3269855550557306,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004831578738579711,
|
|
"loss": 5.9066,
|
|
"mean_token_accuracy": 0.15385794788599014,
|
|
"num_tokens": 25971119.0,
|
|
"step": 13275
|
|
},
|
|
{
|
|
"entropy": 6.218445539474487,
|
|
"epoch": 1.327485380116959,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004831443232558203,
|
|
"loss": 6.0542,
|
|
"mean_token_accuracy": 0.1535279430449009,
|
|
"num_tokens": 25981758.0,
|
|
"step": 13280
|
|
},
|
|
{
|
|
"entropy": 6.24181718826294,
|
|
"epoch": 1.3279852051781877,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00048313076741681186,
|
|
"loss": 6.0046,
|
|
"mean_token_accuracy": 0.1506742499768734,
|
|
"num_tokens": 25991033.0,
|
|
"step": 13285
|
|
},
|
|
{
|
|
"entropy": 6.132058572769165,
|
|
"epoch": 1.3284850302394162,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.00048311720634128697,
|
|
"loss": 6.0269,
|
|
"mean_token_accuracy": 0.15611413046717643,
|
|
"num_tokens": 26001547.0,
|
|
"step": 13290
|
|
},
|
|
{
|
|
"entropy": 6.234566068649292,
|
|
"epoch": 1.3289848553006447,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004831036400295867,
|
|
"loss": 6.0596,
|
|
"mean_token_accuracy": 0.14754553139209747,
|
|
"num_tokens": 26012140.0,
|
|
"step": 13295
|
|
},
|
|
{
|
|
"entropy": 6.2622216701507565,
|
|
"epoch": 1.3294846803618734,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00048309006848205237,
|
|
"loss": 5.9631,
|
|
"mean_token_accuracy": 0.15471525192260743,
|
|
"num_tokens": 26022068.0,
|
|
"step": 13300
|
|
},
|
|
{
|
|
"entropy": 6.217406511306763,
|
|
"epoch": 1.3299845054231019,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004830764916990255,
|
|
"loss": 5.8982,
|
|
"mean_token_accuracy": 0.15676374733448029,
|
|
"num_tokens": 26031313.0,
|
|
"step": 13305
|
|
},
|
|
{
|
|
"entropy": 6.141649770736694,
|
|
"epoch": 1.3304843304843303,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004830629096808476,
|
|
"loss": 5.8818,
|
|
"mean_token_accuracy": 0.16377949118614196,
|
|
"num_tokens": 26040937.0,
|
|
"step": 13310
|
|
},
|
|
{
|
|
"entropy": 6.07700514793396,
|
|
"epoch": 1.330984155545559,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004830493224278605,
|
|
"loss": 5.7635,
|
|
"mean_token_accuracy": 0.1744140073657036,
|
|
"num_tokens": 26049719.0,
|
|
"step": 13315
|
|
},
|
|
{
|
|
"entropy": 6.250267505645752,
|
|
"epoch": 1.3314839806067877,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004830357299404059,
|
|
"loss": 6.0062,
|
|
"mean_token_accuracy": 0.15176339596509933,
|
|
"num_tokens": 26060064.0,
|
|
"step": 13320
|
|
},
|
|
{
|
|
"entropy": 6.137303686141967,
|
|
"epoch": 1.3319838056680162,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004830221322188259,
|
|
"loss": 5.8916,
|
|
"mean_token_accuracy": 0.1669079393148422,
|
|
"num_tokens": 26069605.0,
|
|
"step": 13325
|
|
},
|
|
{
|
|
"entropy": 6.189572334289551,
|
|
"epoch": 1.3324836307292447,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004830085292634626,
|
|
"loss": 5.9857,
|
|
"mean_token_accuracy": 0.14881925731897355,
|
|
"num_tokens": 26079075.0,
|
|
"step": 13330
|
|
},
|
|
{
|
|
"entropy": 6.1138369083404545,
|
|
"epoch": 1.3329834557904734,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00048299492107465816,
|
|
"loss": 5.9362,
|
|
"mean_token_accuracy": 0.15054402500391006,
|
|
"num_tokens": 26089003.0,
|
|
"step": 13335
|
|
},
|
|
{
|
|
"entropy": 6.184536027908325,
|
|
"epoch": 1.3334832808517019,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004829813076527551,
|
|
"loss": 5.9585,
|
|
"mean_token_accuracy": 0.153141750395298,
|
|
"num_tokens": 26099044.0,
|
|
"step": 13340
|
|
},
|
|
{
|
|
"entropy": 6.142232131958008,
|
|
"epoch": 1.3339831059129303,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00048296768899809577,
|
|
"loss": 5.9226,
|
|
"mean_token_accuracy": 0.15283889323472977,
|
|
"num_tokens": 26109044.0,
|
|
"step": 13345
|
|
},
|
|
{
|
|
"entropy": 6.120077228546142,
|
|
"epoch": 1.334482930974159,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.00048295406511102303,
|
|
"loss": 5.9936,
|
|
"mean_token_accuracy": 0.14861363768577576,
|
|
"num_tokens": 26118593.0,
|
|
"step": 13350
|
|
},
|
|
{
|
|
"entropy": 6.192146635055542,
|
|
"epoch": 1.3349827560353877,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004829404359918795,
|
|
"loss": 6.0032,
|
|
"mean_token_accuracy": 0.15580553114414214,
|
|
"num_tokens": 26128885.0,
|
|
"step": 13355
|
|
},
|
|
{
|
|
"entropy": 6.209059143066407,
|
|
"epoch": 1.3354825810966162,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.000482926801641008,
|
|
"loss": 5.9842,
|
|
"mean_token_accuracy": 0.15600850507616998,
|
|
"num_tokens": 26138173.0,
|
|
"step": 13360
|
|
},
|
|
{
|
|
"entropy": 6.214423942565918,
|
|
"epoch": 1.3359824061578447,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00048291316205875174,
|
|
"loss": 5.9321,
|
|
"mean_token_accuracy": 0.15535638630390167,
|
|
"num_tokens": 26147724.0,
|
|
"step": 13365
|
|
},
|
|
{
|
|
"entropy": 6.0966239929199215,
|
|
"epoch": 1.3364822312190734,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00048289951724545384,
|
|
"loss": 5.8791,
|
|
"mean_token_accuracy": 0.16094851940870286,
|
|
"num_tokens": 26156970.0,
|
|
"step": 13370
|
|
},
|
|
{
|
|
"entropy": 6.055920505523682,
|
|
"epoch": 1.3369820562803019,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00048288586720145757,
|
|
"loss": 5.8449,
|
|
"mean_token_accuracy": 0.15795587003231049,
|
|
"num_tokens": 26166757.0,
|
|
"step": 13375
|
|
},
|
|
{
|
|
"entropy": 6.142801761627197,
|
|
"epoch": 1.3374818813415303,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004828722119271064,
|
|
"loss": 5.9961,
|
|
"mean_token_accuracy": 0.14875075742602348,
|
|
"num_tokens": 26176944.0,
|
|
"step": 13380
|
|
},
|
|
{
|
|
"entropy": 6.157301044464111,
|
|
"epoch": 1.337981706402759,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00048285855142274375,
|
|
"loss": 5.8436,
|
|
"mean_token_accuracy": 0.16563331186771393,
|
|
"num_tokens": 26185380.0,
|
|
"step": 13385
|
|
},
|
|
{
|
|
"entropy": 6.157561635971069,
|
|
"epoch": 1.3384815314639877,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004828448856887135,
|
|
"loss": 5.9464,
|
|
"mean_token_accuracy": 0.15706296488642693,
|
|
"num_tokens": 26194936.0,
|
|
"step": 13390
|
|
},
|
|
{
|
|
"entropy": 6.081349611282349,
|
|
"epoch": 1.3389813565252162,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004828312147253595,
|
|
"loss": 5.8551,
|
|
"mean_token_accuracy": 0.15932156890630722,
|
|
"num_tokens": 26205825.0,
|
|
"step": 13395
|
|
},
|
|
{
|
|
"entropy": 6.249830484390259,
|
|
"epoch": 1.3394811815864447,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004828175385330255,
|
|
"loss": 6.0098,
|
|
"mean_token_accuracy": 0.1462766632437706,
|
|
"num_tokens": 26215977.0,
|
|
"step": 13400
|
|
},
|
|
{
|
|
"entropy": 6.216329956054688,
|
|
"epoch": 1.3399810066476734,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004828038571120558,
|
|
"loss": 5.9591,
|
|
"mean_token_accuracy": 0.15963440835475923,
|
|
"num_tokens": 26225424.0,
|
|
"step": 13405
|
|
},
|
|
{
|
|
"entropy": 6.17230806350708,
|
|
"epoch": 1.3404808317089019,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00048279017046279446,
|
|
"loss": 5.9815,
|
|
"mean_token_accuracy": 0.1597868949174881,
|
|
"num_tokens": 26235491.0,
|
|
"step": 13410
|
|
},
|
|
{
|
|
"entropy": 6.165284824371338,
|
|
"epoch": 1.3409806567701303,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00048277647858558596,
|
|
"loss": 6.0194,
|
|
"mean_token_accuracy": 0.1536007598042488,
|
|
"num_tokens": 26246030.0,
|
|
"step": 13415
|
|
},
|
|
{
|
|
"entropy": 6.244114065170288,
|
|
"epoch": 1.341480481831359,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00048276278148077465,
|
|
"loss": 6.0436,
|
|
"mean_token_accuracy": 0.1454267144203186,
|
|
"num_tokens": 26255008.0,
|
|
"step": 13420
|
|
},
|
|
{
|
|
"entropy": 6.08438401222229,
|
|
"epoch": 1.3419803068925875,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.00048274907914870526,
|
|
"loss": 5.7393,
|
|
"mean_token_accuracy": 0.17554350942373276,
|
|
"num_tokens": 26263319.0,
|
|
"step": 13425
|
|
},
|
|
{
|
|
"entropy": 6.084990358352661,
|
|
"epoch": 1.3424801319538162,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00048273537158972246,
|
|
"loss": 5.8583,
|
|
"mean_token_accuracy": 0.1612003803253174,
|
|
"num_tokens": 26272555.0,
|
|
"step": 13430
|
|
},
|
|
{
|
|
"entropy": 6.139375782012939,
|
|
"epoch": 1.3429799570150447,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.00048272165880417124,
|
|
"loss": 5.946,
|
|
"mean_token_accuracy": 0.15595633089542388,
|
|
"num_tokens": 26282915.0,
|
|
"step": 13435
|
|
},
|
|
{
|
|
"entropy": 6.167522716522217,
|
|
"epoch": 1.3434797820762734,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00048270794079239643,
|
|
"loss": 5.8949,
|
|
"mean_token_accuracy": 0.16371387541294097,
|
|
"num_tokens": 26292705.0,
|
|
"step": 13440
|
|
},
|
|
{
|
|
"entropy": 6.268767404556274,
|
|
"epoch": 1.3439796071375019,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00048269421755474336,
|
|
"loss": 6.0126,
|
|
"mean_token_accuracy": 0.14959271177649497,
|
|
"num_tokens": 26303678.0,
|
|
"step": 13445
|
|
},
|
|
{
|
|
"entropy": 6.164479064941406,
|
|
"epoch": 1.3444794321987303,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004826804890915572,
|
|
"loss": 5.9351,
|
|
"mean_token_accuracy": 0.15266655683517455,
|
|
"num_tokens": 26312844.0,
|
|
"step": 13450
|
|
},
|
|
{
|
|
"entropy": 6.218075942993164,
|
|
"epoch": 1.344979257259959,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004826667554031834,
|
|
"loss": 6.0046,
|
|
"mean_token_accuracy": 0.149177997559309,
|
|
"num_tokens": 26322763.0,
|
|
"step": 13455
|
|
},
|
|
{
|
|
"entropy": 6.127144145965576,
|
|
"epoch": 1.3454790823211875,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004826530164899674,
|
|
"loss": 5.9154,
|
|
"mean_token_accuracy": 0.15740453824400902,
|
|
"num_tokens": 26331381.0,
|
|
"step": 13460
|
|
},
|
|
{
|
|
"entropy": 6.029008865356445,
|
|
"epoch": 1.3459789073824162,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00048263927235225505,
|
|
"loss": 5.684,
|
|
"mean_token_accuracy": 0.17971582114696502,
|
|
"num_tokens": 26340637.0,
|
|
"step": 13465
|
|
},
|
|
{
|
|
"entropy": 6.17818512916565,
|
|
"epoch": 1.3464787324436447,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004826255229903919,
|
|
"loss": 5.894,
|
|
"mean_token_accuracy": 0.15740025490522386,
|
|
"num_tokens": 26350508.0,
|
|
"step": 13470
|
|
},
|
|
{
|
|
"entropy": 6.170793628692627,
|
|
"epoch": 1.3469785575048734,
|
|
"grad_norm": 2.328125,
|
|
"learning_rate": 0.00048261176840472416,
|
|
"loss": 6.0833,
|
|
"mean_token_accuracy": 0.15282572209835052,
|
|
"num_tokens": 26360419.0,
|
|
"step": 13475
|
|
},
|
|
{
|
|
"entropy": 6.1905053615570065,
|
|
"epoch": 1.3474783825661019,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.00048259800859559764,
|
|
"loss": 5.9293,
|
|
"mean_token_accuracy": 0.1533403255045414,
|
|
"num_tokens": 26370355.0,
|
|
"step": 13480
|
|
},
|
|
{
|
|
"entropy": 6.086648464202881,
|
|
"epoch": 1.3479782076273303,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004825842435633587,
|
|
"loss": 5.8828,
|
|
"mean_token_accuracy": 0.16225536167621613,
|
|
"num_tokens": 26380085.0,
|
|
"step": 13485
|
|
},
|
|
{
|
|
"entropy": 6.131977605819702,
|
|
"epoch": 1.348478032688559,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00048257047330835354,
|
|
"loss": 5.9217,
|
|
"mean_token_accuracy": 0.16104235649108886,
|
|
"num_tokens": 26389571.0,
|
|
"step": 13490
|
|
},
|
|
{
|
|
"entropy": 6.093983221054077,
|
|
"epoch": 1.3489778577497875,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00048255669783092876,
|
|
"loss": 5.9047,
|
|
"mean_token_accuracy": 0.15970612764358522,
|
|
"num_tokens": 26399560.0,
|
|
"step": 13495
|
|
},
|
|
{
|
|
"entropy": 6.131382846832276,
|
|
"epoch": 1.3494776828110162,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00048254291713143083,
|
|
"loss": 5.9108,
|
|
"mean_token_accuracy": 0.15783733278512954,
|
|
"num_tokens": 26409290.0,
|
|
"step": 13500
|
|
},
|
|
{
|
|
"entropy": 6.1973714351654055,
|
|
"epoch": 1.3499775078722447,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.0004825291312102066,
|
|
"loss": 5.9663,
|
|
"mean_token_accuracy": 0.15795569270849227,
|
|
"num_tokens": 26419458.0,
|
|
"step": 13505
|
|
},
|
|
{
|
|
"entropy": 6.170440435409546,
|
|
"epoch": 1.3504773329334734,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004825153400676027,
|
|
"loss": 5.8587,
|
|
"mean_token_accuracy": 0.16096708923578262,
|
|
"num_tokens": 26428947.0,
|
|
"step": 13510
|
|
},
|
|
{
|
|
"entropy": 5.949077510833741,
|
|
"epoch": 1.3509771579947019,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004825015437039663,
|
|
"loss": 5.7805,
|
|
"mean_token_accuracy": 0.1663256913423538,
|
|
"num_tokens": 26438874.0,
|
|
"step": 13515
|
|
},
|
|
{
|
|
"entropy": 6.128787851333618,
|
|
"epoch": 1.3514769830559303,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004824877421196444,
|
|
"loss": 5.8647,
|
|
"mean_token_accuracy": 0.16112425327301025,
|
|
"num_tokens": 26448510.0,
|
|
"step": 13520
|
|
},
|
|
{
|
|
"entropy": 6.032810020446777,
|
|
"epoch": 1.351976808117159,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004824739353149844,
|
|
"loss": 5.8352,
|
|
"mean_token_accuracy": 0.1590333729982376,
|
|
"num_tokens": 26458552.0,
|
|
"step": 13525
|
|
},
|
|
{
|
|
"entropy": 6.099111604690552,
|
|
"epoch": 1.3524766331783875,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.00048246012329033355,
|
|
"loss": 5.9426,
|
|
"mean_token_accuracy": 0.1562192842364311,
|
|
"num_tokens": 26467900.0,
|
|
"step": 13530
|
|
},
|
|
{
|
|
"entropy": 6.199307489395141,
|
|
"epoch": 1.3529764582396162,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.00048244630604603935,
|
|
"loss": 5.923,
|
|
"mean_token_accuracy": 0.15992572978138925,
|
|
"num_tokens": 26477229.0,
|
|
"step": 13535
|
|
},
|
|
{
|
|
"entropy": 6.192346858978271,
|
|
"epoch": 1.3534762833008447,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00048243248358244945,
|
|
"loss": 5.9574,
|
|
"mean_token_accuracy": 0.15444340258836747,
|
|
"num_tokens": 26487358.0,
|
|
"step": 13540
|
|
},
|
|
{
|
|
"entropy": 6.096559619903564,
|
|
"epoch": 1.3539761083620734,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004824186558999117,
|
|
"loss": 5.8243,
|
|
"mean_token_accuracy": 0.16178459376096727,
|
|
"num_tokens": 26496399.0,
|
|
"step": 13545
|
|
},
|
|
{
|
|
"entropy": 6.083345174789429,
|
|
"epoch": 1.3544759334233019,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00048240482299877386,
|
|
"loss": 5.9252,
|
|
"mean_token_accuracy": 0.15940019339323044,
|
|
"num_tokens": 26506170.0,
|
|
"step": 13550
|
|
},
|
|
{
|
|
"entropy": 6.1777738571167,
|
|
"epoch": 1.3549757584845303,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004823909848793841,
|
|
"loss": 5.9536,
|
|
"mean_token_accuracy": 0.15433786511421205,
|
|
"num_tokens": 26516414.0,
|
|
"step": 13555
|
|
},
|
|
{
|
|
"entropy": 6.080035829544068,
|
|
"epoch": 1.355475583545759,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00048237714154209053,
|
|
"loss": 5.8576,
|
|
"mean_token_accuracy": 0.1628124311566353,
|
|
"num_tokens": 26526345.0,
|
|
"step": 13560
|
|
},
|
|
{
|
|
"entropy": 6.209974861145019,
|
|
"epoch": 1.3559754086069875,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004823632929872415,
|
|
"loss": 5.9555,
|
|
"mean_token_accuracy": 0.15523934960365296,
|
|
"num_tokens": 26535768.0,
|
|
"step": 13565
|
|
},
|
|
{
|
|
"entropy": 6.157249307632446,
|
|
"epoch": 1.3564752336682162,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00048234943921518524,
|
|
"loss": 5.9434,
|
|
"mean_token_accuracy": 0.15802091956138611,
|
|
"num_tokens": 26546181.0,
|
|
"step": 13570
|
|
},
|
|
{
|
|
"entropy": 6.106801319122314,
|
|
"epoch": 1.3569750587294447,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004823355802262705,
|
|
"loss": 5.8975,
|
|
"mean_token_accuracy": 0.16192759722471237,
|
|
"num_tokens": 26555664.0,
|
|
"step": 13575
|
|
},
|
|
{
|
|
"entropy": 6.200563859939575,
|
|
"epoch": 1.3574748837906734,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004823217160208459,
|
|
"loss": 5.99,
|
|
"mean_token_accuracy": 0.153380536288023,
|
|
"num_tokens": 26564801.0,
|
|
"step": 13580
|
|
},
|
|
{
|
|
"entropy": 6.2960512161254885,
|
|
"epoch": 1.3579747088519019,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004823078465992604,
|
|
"loss": 6.0684,
|
|
"mean_token_accuracy": 0.15203940719366074,
|
|
"num_tokens": 26575397.0,
|
|
"step": 13585
|
|
},
|
|
{
|
|
"entropy": 6.129009580612182,
|
|
"epoch": 1.3584745339131303,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004822939719618627,
|
|
"loss": 5.9131,
|
|
"mean_token_accuracy": 0.16364746242761613,
|
|
"num_tokens": 26584533.0,
|
|
"step": 13590
|
|
},
|
|
{
|
|
"entropy": 6.188502454757691,
|
|
"epoch": 1.358974358974359,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.000482280092109002,
|
|
"loss": 5.9201,
|
|
"mean_token_accuracy": 0.16066576838493346,
|
|
"num_tokens": 26594176.0,
|
|
"step": 13595
|
|
},
|
|
{
|
|
"entropy": 6.15440788269043,
|
|
"epoch": 1.3594741840355875,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00048226620704102757,
|
|
"loss": 5.9469,
|
|
"mean_token_accuracy": 0.14897557497024536,
|
|
"num_tokens": 26603033.0,
|
|
"step": 13600
|
|
},
|
|
{
|
|
"entropy": 6.2116961002349855,
|
|
"epoch": 1.359974009096816,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004822523167582886,
|
|
"loss": 5.919,
|
|
"mean_token_accuracy": 0.1595153883099556,
|
|
"num_tokens": 26612327.0,
|
|
"step": 13605
|
|
},
|
|
{
|
|
"entropy": 6.123779916763306,
|
|
"epoch": 1.3604738341580447,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004822384212611348,
|
|
"loss": 5.8976,
|
|
"mean_token_accuracy": 0.15832812935113907,
|
|
"num_tokens": 26622180.0,
|
|
"step": 13610
|
|
},
|
|
{
|
|
"entropy": 6.139707946777344,
|
|
"epoch": 1.3609736592192734,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00048222452054991563,
|
|
"loss": 6.0204,
|
|
"mean_token_accuracy": 0.14583451449871063,
|
|
"num_tokens": 26633137.0,
|
|
"step": 13615
|
|
},
|
|
{
|
|
"entropy": 6.097583818435669,
|
|
"epoch": 1.3614734842805019,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004822106146249808,
|
|
"loss": 5.8025,
|
|
"mean_token_accuracy": 0.16549130752682686,
|
|
"num_tokens": 26642642.0,
|
|
"step": 13620
|
|
},
|
|
{
|
|
"entropy": 6.235262680053711,
|
|
"epoch": 1.3619733093417303,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.00048219670348668026,
|
|
"loss": 6.0105,
|
|
"mean_token_accuracy": 0.1557586185634136,
|
|
"num_tokens": 26652465.0,
|
|
"step": 13625
|
|
},
|
|
{
|
|
"entropy": 6.191774463653564,
|
|
"epoch": 1.362473134402959,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.00048218278713536394,
|
|
"loss": 5.9482,
|
|
"mean_token_accuracy": 0.1562319315969944,
|
|
"num_tokens": 26662971.0,
|
|
"step": 13630
|
|
},
|
|
{
|
|
"entropy": 6.023241281509399,
|
|
"epoch": 1.3629729594641875,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004821688655713821,
|
|
"loss": 5.8445,
|
|
"mean_token_accuracy": 0.16247360557317733,
|
|
"num_tokens": 26672373.0,
|
|
"step": 13635
|
|
},
|
|
{
|
|
"entropy": 6.081688356399536,
|
|
"epoch": 1.363472784525416,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.00048215493879508474,
|
|
"loss": 5.8556,
|
|
"mean_token_accuracy": 0.164544714987278,
|
|
"num_tokens": 26681491.0,
|
|
"step": 13640
|
|
},
|
|
{
|
|
"entropy": 6.191488742828369,
|
|
"epoch": 1.3639726095866447,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004821410068068226,
|
|
"loss": 5.9481,
|
|
"mean_token_accuracy": 0.15922945141792297,
|
|
"num_tokens": 26690094.0,
|
|
"step": 13645
|
|
},
|
|
{
|
|
"entropy": 6.2064262390136715,
|
|
"epoch": 1.3644724346478734,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004821270696069459,
|
|
"loss": 5.9424,
|
|
"mean_token_accuracy": 0.15093102306127548,
|
|
"num_tokens": 26699525.0,
|
|
"step": 13650
|
|
},
|
|
{
|
|
"entropy": 6.106315755844117,
|
|
"epoch": 1.3649722597091019,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00048211312719580553,
|
|
"loss": 5.8567,
|
|
"mean_token_accuracy": 0.1582114189863205,
|
|
"num_tokens": 26709943.0,
|
|
"step": 13655
|
|
},
|
|
{
|
|
"entropy": 6.122861862182617,
|
|
"epoch": 1.3654720847703303,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004820991795737521,
|
|
"loss": 5.9131,
|
|
"mean_token_accuracy": 0.1552156075835228,
|
|
"num_tokens": 26719517.0,
|
|
"step": 13660
|
|
},
|
|
{
|
|
"entropy": 6.157819366455078,
|
|
"epoch": 1.365971909831559,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00048208522674113665,
|
|
"loss": 5.9672,
|
|
"mean_token_accuracy": 0.1622170627117157,
|
|
"num_tokens": 26728753.0,
|
|
"step": 13665
|
|
},
|
|
{
|
|
"entropy": 6.166556692123413,
|
|
"epoch": 1.3664717348927875,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004820712686983101,
|
|
"loss": 5.9249,
|
|
"mean_token_accuracy": 0.15511706247925758,
|
|
"num_tokens": 26737662.0,
|
|
"step": 13670
|
|
},
|
|
{
|
|
"entropy": 6.080324792861939,
|
|
"epoch": 1.366971559954016,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00048205730544562385,
|
|
"loss": 5.8745,
|
|
"mean_token_accuracy": 0.16297486126422883,
|
|
"num_tokens": 26748167.0,
|
|
"step": 13675
|
|
},
|
|
{
|
|
"entropy": 6.179111576080322,
|
|
"epoch": 1.3674713850152447,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.000482043336983429,
|
|
"loss": 5.9859,
|
|
"mean_token_accuracy": 0.15291956067085266,
|
|
"num_tokens": 26756692.0,
|
|
"step": 13680
|
|
},
|
|
{
|
|
"entropy": 6.096879625320435,
|
|
"epoch": 1.3679712100764732,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00048202936331207707,
|
|
"loss": 5.8964,
|
|
"mean_token_accuracy": 0.16100419610738753,
|
|
"num_tokens": 26766201.0,
|
|
"step": 13685
|
|
},
|
|
{
|
|
"entropy": 6.075778579711914,
|
|
"epoch": 1.3684710351377019,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004820153844319196,
|
|
"loss": 5.9083,
|
|
"mean_token_accuracy": 0.16028712838888168,
|
|
"num_tokens": 26774911.0,
|
|
"step": 13690
|
|
},
|
|
{
|
|
"entropy": 6.144129991531372,
|
|
"epoch": 1.3689708601989303,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00048200140034330844,
|
|
"loss": 5.8822,
|
|
"mean_token_accuracy": 0.16373094469308852,
|
|
"num_tokens": 26784271.0,
|
|
"step": 13695
|
|
},
|
|
{
|
|
"entropy": 6.252957534790039,
|
|
"epoch": 1.369470685260159,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00048198741104659516,
|
|
"loss": 5.9744,
|
|
"mean_token_accuracy": 0.1594805970788002,
|
|
"num_tokens": 26794975.0,
|
|
"step": 13700
|
|
},
|
|
{
|
|
"entropy": 6.199783849716186,
|
|
"epoch": 1.3699705103213875,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.000481973416542132,
|
|
"loss": 6.0297,
|
|
"mean_token_accuracy": 0.15491671115159988,
|
|
"num_tokens": 26805989.0,
|
|
"step": 13705
|
|
},
|
|
{
|
|
"entropy": 6.174100160598755,
|
|
"epoch": 1.370470335382616,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004819594168302709,
|
|
"loss": 5.9731,
|
|
"mean_token_accuracy": 0.1575739249587059,
|
|
"num_tokens": 26815961.0,
|
|
"step": 13710
|
|
},
|
|
{
|
|
"entropy": 6.104086780548096,
|
|
"epoch": 1.3709701604438447,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004819454119113641,
|
|
"loss": 5.8171,
|
|
"mean_token_accuracy": 0.16839422136545182,
|
|
"num_tokens": 26825697.0,
|
|
"step": 13715
|
|
},
|
|
{
|
|
"entropy": 6.154540872573852,
|
|
"epoch": 1.3714699855050732,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.000481931401785764,
|
|
"loss": 5.8792,
|
|
"mean_token_accuracy": 0.15832828879356384,
|
|
"num_tokens": 26834965.0,
|
|
"step": 13720
|
|
},
|
|
{
|
|
"entropy": 6.115646839141846,
|
|
"epoch": 1.3719698105663019,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004819173864538231,
|
|
"loss": 5.9075,
|
|
"mean_token_accuracy": 0.16441078633069992,
|
|
"num_tokens": 26845621.0,
|
|
"step": 13725
|
|
},
|
|
{
|
|
"entropy": 6.222882461547852,
|
|
"epoch": 1.3724696356275303,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00048190336591589394,
|
|
"loss": 6.0035,
|
|
"mean_token_accuracy": 0.1523177832365036,
|
|
"num_tokens": 26855176.0,
|
|
"step": 13730
|
|
},
|
|
{
|
|
"entropy": 6.239377069473266,
|
|
"epoch": 1.372969460688759,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004818893401723294,
|
|
"loss": 5.9625,
|
|
"mean_token_accuracy": 0.15688011199235916,
|
|
"num_tokens": 26864197.0,
|
|
"step": 13735
|
|
},
|
|
{
|
|
"entropy": 6.157269763946533,
|
|
"epoch": 1.3734692857499875,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.00048187530922348226,
|
|
"loss": 5.9229,
|
|
"mean_token_accuracy": 0.15628610253334047,
|
|
"num_tokens": 26873895.0,
|
|
"step": 13740
|
|
},
|
|
{
|
|
"entropy": 6.144111204147339,
|
|
"epoch": 1.373969110811216,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004818612730697056,
|
|
"loss": 6.0457,
|
|
"mean_token_accuracy": 0.15030306577682495,
|
|
"num_tokens": 26883685.0,
|
|
"step": 13745
|
|
},
|
|
{
|
|
"entropy": 6.193239688873291,
|
|
"epoch": 1.3744689358724447,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00048184723171135256,
|
|
"loss": 5.8024,
|
|
"mean_token_accuracy": 0.1606294184923172,
|
|
"num_tokens": 26893939.0,
|
|
"step": 13750
|
|
},
|
|
{
|
|
"entropy": 6.116706037521363,
|
|
"epoch": 1.3749687609336732,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.00048183318514877634,
|
|
"loss": 5.8972,
|
|
"mean_token_accuracy": 0.16470476984977722,
|
|
"num_tokens": 26903588.0,
|
|
"step": 13755
|
|
},
|
|
{
|
|
"entropy": 6.174177885055542,
|
|
"epoch": 1.3754685859949018,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004818191333823305,
|
|
"loss": 6.0456,
|
|
"mean_token_accuracy": 0.1523826986551285,
|
|
"num_tokens": 26914068.0,
|
|
"step": 13760
|
|
},
|
|
{
|
|
"entropy": 6.15484848022461,
|
|
"epoch": 1.3759684110561303,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004818050764123684,
|
|
"loss": 5.9254,
|
|
"mean_token_accuracy": 0.15486986190080643,
|
|
"num_tokens": 26923928.0,
|
|
"step": 13765
|
|
},
|
|
{
|
|
"entropy": 6.119842624664306,
|
|
"epoch": 1.376468236117359,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004817910142392438,
|
|
"loss": 5.8632,
|
|
"mean_token_accuracy": 0.16237968504428862,
|
|
"num_tokens": 26933202.0,
|
|
"step": 13770
|
|
},
|
|
{
|
|
"entropy": 6.031164121627808,
|
|
"epoch": 1.3769680611785875,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.00048177694686331047,
|
|
"loss": 5.7526,
|
|
"mean_token_accuracy": 0.1667496904730797,
|
|
"num_tokens": 26943466.0,
|
|
"step": 13775
|
|
},
|
|
{
|
|
"entropy": 6.09368371963501,
|
|
"epoch": 1.377467886239816,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004817628742849224,
|
|
"loss": 5.8706,
|
|
"mean_token_accuracy": 0.15734305381774902,
|
|
"num_tokens": 26953996.0,
|
|
"step": 13780
|
|
},
|
|
{
|
|
"entropy": 6.108762311935425,
|
|
"epoch": 1.3779677113010447,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00048174879650443364,
|
|
"loss": 5.923,
|
|
"mean_token_accuracy": 0.1599729061126709,
|
|
"num_tokens": 26963238.0,
|
|
"step": 13785
|
|
},
|
|
{
|
|
"entropy": 6.127309894561767,
|
|
"epoch": 1.3784675363622731,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00048173471352219835,
|
|
"loss": 5.9181,
|
|
"mean_token_accuracy": 0.14826206415891646,
|
|
"num_tokens": 26973124.0,
|
|
"step": 13790
|
|
},
|
|
{
|
|
"entropy": 6.117661237716675,
|
|
"epoch": 1.3789673614235018,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004817206253385708,
|
|
"loss": 5.8523,
|
|
"mean_token_accuracy": 0.16209922283887862,
|
|
"num_tokens": 26981698.0,
|
|
"step": 13795
|
|
},
|
|
{
|
|
"entropy": 6.140020227432251,
|
|
"epoch": 1.3794671864847303,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00048170653195390555,
|
|
"loss": 5.9609,
|
|
"mean_token_accuracy": 0.15860718116164207,
|
|
"num_tokens": 26991263.0,
|
|
"step": 13800
|
|
},
|
|
{
|
|
"entropy": 6.058004236221313,
|
|
"epoch": 1.379967011545959,
|
|
"grad_norm": 1.953125,
|
|
"learning_rate": 0.0004816924333685572,
|
|
"loss": 5.8667,
|
|
"mean_token_accuracy": 0.16487080976366997,
|
|
"num_tokens": 27001835.0,
|
|
"step": 13805
|
|
},
|
|
{
|
|
"entropy": 6.117015027999878,
|
|
"epoch": 1.3804668366071875,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004816783295828804,
|
|
"loss": 5.9002,
|
|
"mean_token_accuracy": 0.15816379338502884,
|
|
"num_tokens": 27011306.0,
|
|
"step": 13810
|
|
},
|
|
{
|
|
"entropy": 6.315247869491577,
|
|
"epoch": 1.380966661668416,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.00048166422059722996,
|
|
"loss": 6.074,
|
|
"mean_token_accuracy": 0.14898498728871346,
|
|
"num_tokens": 27022038.0,
|
|
"step": 13815
|
|
},
|
|
{
|
|
"entropy": 6.229460144042969,
|
|
"epoch": 1.3814664867296447,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004816501064119609,
|
|
"loss": 5.9649,
|
|
"mean_token_accuracy": 0.15633662045001984,
|
|
"num_tokens": 27032225.0,
|
|
"step": 13820
|
|
},
|
|
{
|
|
"entropy": 6.187652444839477,
|
|
"epoch": 1.3819663117908731,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004816359870274284,
|
|
"loss": 5.9128,
|
|
"mean_token_accuracy": 0.1568162754178047,
|
|
"num_tokens": 27042770.0,
|
|
"step": 13825
|
|
},
|
|
{
|
|
"entropy": 6.149801206588745,
|
|
"epoch": 1.3824661368521018,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004816218624439876,
|
|
"loss": 5.9497,
|
|
"mean_token_accuracy": 0.15984033346176146,
|
|
"num_tokens": 27052543.0,
|
|
"step": 13830
|
|
},
|
|
{
|
|
"entropy": 6.182939243316651,
|
|
"epoch": 1.3829659619133303,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.00048160773266199384,
|
|
"loss": 5.9568,
|
|
"mean_token_accuracy": 0.15122343301773072,
|
|
"num_tokens": 27061955.0,
|
|
"step": 13835
|
|
},
|
|
{
|
|
"entropy": 6.109112977981567,
|
|
"epoch": 1.383465786974559,
|
|
"grad_norm": 1.8515625,
|
|
"learning_rate": 0.0004815935976818028,
|
|
"loss": 5.8423,
|
|
"mean_token_accuracy": 0.1650175616145134,
|
|
"num_tokens": 27071458.0,
|
|
"step": 13840
|
|
},
|
|
{
|
|
"entropy": 6.146598291397095,
|
|
"epoch": 1.3839656120357875,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00048157945750377005,
|
|
"loss": 5.8852,
|
|
"mean_token_accuracy": 0.1602638304233551,
|
|
"num_tokens": 27081331.0,
|
|
"step": 13845
|
|
},
|
|
{
|
|
"entropy": 6.077832221984863,
|
|
"epoch": 1.384465437097016,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004815653121282512,
|
|
"loss": 5.8383,
|
|
"mean_token_accuracy": 0.16466595232486725,
|
|
"num_tokens": 27090159.0,
|
|
"step": 13850
|
|
},
|
|
{
|
|
"entropy": 6.130023956298828,
|
|
"epoch": 1.3849652621582447,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00048155116155560227,
|
|
"loss": 5.9213,
|
|
"mean_token_accuracy": 0.1590987116098404,
|
|
"num_tokens": 27099389.0,
|
|
"step": 13855
|
|
},
|
|
{
|
|
"entropy": 6.192239904403687,
|
|
"epoch": 1.3854650872194731,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00048153700578617924,
|
|
"loss": 5.9934,
|
|
"mean_token_accuracy": 0.15302683860063554,
|
|
"num_tokens": 27109878.0,
|
|
"step": 13860
|
|
},
|
|
{
|
|
"entropy": 6.180838537216187,
|
|
"epoch": 1.3859649122807016,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004815228448203384,
|
|
"loss": 5.9757,
|
|
"mean_token_accuracy": 0.15419846177101135,
|
|
"num_tokens": 27119556.0,
|
|
"step": 13865
|
|
},
|
|
{
|
|
"entropy": 6.160820960998535,
|
|
"epoch": 1.3864647373419303,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004815086786584358,
|
|
"loss": 5.8969,
|
|
"mean_token_accuracy": 0.1629953607916832,
|
|
"num_tokens": 27129086.0,
|
|
"step": 13870
|
|
},
|
|
{
|
|
"entropy": 6.154081535339356,
|
|
"epoch": 1.386964562403159,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.000481494507300828,
|
|
"loss": 5.9865,
|
|
"mean_token_accuracy": 0.1620579943060875,
|
|
"num_tokens": 27138908.0,
|
|
"step": 13875
|
|
},
|
|
{
|
|
"entropy": 6.091911125183105,
|
|
"epoch": 1.3874643874643875,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004814803307478716,
|
|
"loss": 5.8943,
|
|
"mean_token_accuracy": 0.1623252347111702,
|
|
"num_tokens": 27149306.0,
|
|
"step": 13880
|
|
},
|
|
{
|
|
"entropy": 6.052503061294556,
|
|
"epoch": 1.387964212525616,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.00048146614899992313,
|
|
"loss": 5.762,
|
|
"mean_token_accuracy": 0.1719990998506546,
|
|
"num_tokens": 27159293.0,
|
|
"step": 13885
|
|
},
|
|
{
|
|
"entropy": 6.099456691741944,
|
|
"epoch": 1.3884640375868447,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00048145196205733954,
|
|
"loss": 5.8659,
|
|
"mean_token_accuracy": 0.1618460476398468,
|
|
"num_tokens": 27168450.0,
|
|
"step": 13890
|
|
},
|
|
{
|
|
"entropy": 6.111635971069336,
|
|
"epoch": 1.3889638626480731,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00048143776992047767,
|
|
"loss": 5.8654,
|
|
"mean_token_accuracy": 0.16381198912858963,
|
|
"num_tokens": 27177548.0,
|
|
"step": 13895
|
|
},
|
|
{
|
|
"entropy": 6.11266860961914,
|
|
"epoch": 1.3894636877093016,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00048142357258969465,
|
|
"loss": 5.9278,
|
|
"mean_token_accuracy": 0.1604678899049759,
|
|
"num_tokens": 27186826.0,
|
|
"step": 13900
|
|
},
|
|
{
|
|
"entropy": 6.155711841583252,
|
|
"epoch": 1.3899635127705303,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004814093700653477,
|
|
"loss": 5.8989,
|
|
"mean_token_accuracy": 0.15810148566961288,
|
|
"num_tokens": 27196363.0,
|
|
"step": 13905
|
|
},
|
|
{
|
|
"entropy": 6.2352190017700195,
|
|
"epoch": 1.390463337831759,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00048139516234779403,
|
|
"loss": 5.9631,
|
|
"mean_token_accuracy": 0.15756095051765442,
|
|
"num_tokens": 27205461.0,
|
|
"step": 13910
|
|
},
|
|
{
|
|
"entropy": 6.246933841705323,
|
|
"epoch": 1.3909631628929875,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00048138094943739123,
|
|
"loss": 6.0993,
|
|
"mean_token_accuracy": 0.1442100629210472,
|
|
"num_tokens": 27214490.0,
|
|
"step": 13915
|
|
},
|
|
{
|
|
"entropy": 6.0951512336730955,
|
|
"epoch": 1.391462987954216,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00048136673133449687,
|
|
"loss": 5.8902,
|
|
"mean_token_accuracy": 0.16283289194107056,
|
|
"num_tokens": 27224020.0,
|
|
"step": 13920
|
|
},
|
|
{
|
|
"entropy": 6.012313508987427,
|
|
"epoch": 1.3919628130154447,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.0004813525080394686,
|
|
"loss": 5.8459,
|
|
"mean_token_accuracy": 0.16710145846009256,
|
|
"num_tokens": 27234591.0,
|
|
"step": 13925
|
|
},
|
|
{
|
|
"entropy": 6.158491230010986,
|
|
"epoch": 1.3924626380766731,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004813382795526644,
|
|
"loss": 5.9062,
|
|
"mean_token_accuracy": 0.160186704993248,
|
|
"num_tokens": 27244991.0,
|
|
"step": 13930
|
|
},
|
|
{
|
|
"entropy": 6.103867387771606,
|
|
"epoch": 1.3929624631379016,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004813240458744421,
|
|
"loss": 5.8801,
|
|
"mean_token_accuracy": 0.16120165437459946,
|
|
"num_tokens": 27254663.0,
|
|
"step": 13935
|
|
},
|
|
{
|
|
"entropy": 6.190715217590332,
|
|
"epoch": 1.3934622881991303,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.00048130980700516,
|
|
"loss": 5.9864,
|
|
"mean_token_accuracy": 0.15098951309919356,
|
|
"num_tokens": 27265238.0,
|
|
"step": 13940
|
|
},
|
|
{
|
|
"entropy": 6.164424037933349,
|
|
"epoch": 1.3939621132603588,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004812955629451761,
|
|
"loss": 5.9311,
|
|
"mean_token_accuracy": 0.16472459733486175,
|
|
"num_tokens": 27273844.0,
|
|
"step": 13945
|
|
},
|
|
{
|
|
"entropy": 6.096916246414184,
|
|
"epoch": 1.3944619383215875,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004812813136948491,
|
|
"loss": 5.8643,
|
|
"mean_token_accuracy": 0.1559591919183731,
|
|
"num_tokens": 27283356.0,
|
|
"step": 13950
|
|
},
|
|
{
|
|
"entropy": 5.921930265426636,
|
|
"epoch": 1.394961763382816,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00048126705925453716,
|
|
"loss": 5.6979,
|
|
"mean_token_accuracy": 0.18205879777669906,
|
|
"num_tokens": 27292685.0,
|
|
"step": 13955
|
|
},
|
|
{
|
|
"entropy": 6.094734048843383,
|
|
"epoch": 1.3954615884440447,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004812527996245992,
|
|
"loss": 5.8533,
|
|
"mean_token_accuracy": 0.15713960379362107,
|
|
"num_tokens": 27302347.0,
|
|
"step": 13960
|
|
},
|
|
{
|
|
"entropy": 6.21630449295044,
|
|
"epoch": 1.3959614135052731,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004812385348053938,
|
|
"loss": 5.9887,
|
|
"mean_token_accuracy": 0.15596369206905364,
|
|
"num_tokens": 27311807.0,
|
|
"step": 13965
|
|
},
|
|
{
|
|
"entropy": 6.153706693649292,
|
|
"epoch": 1.3964612385665016,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00048122426479728,
|
|
"loss": 5.9693,
|
|
"mean_token_accuracy": 0.15437859743833543,
|
|
"num_tokens": 27322561.0,
|
|
"step": 13970
|
|
},
|
|
{
|
|
"entropy": 6.141304397583008,
|
|
"epoch": 1.3969610636277303,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004812099896006167,
|
|
"loss": 5.8954,
|
|
"mean_token_accuracy": 0.16642517298460008,
|
|
"num_tokens": 27332105.0,
|
|
"step": 13975
|
|
},
|
|
{
|
|
"entropy": 6.061940670013428,
|
|
"epoch": 1.3974608886889588,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004811957092157631,
|
|
"loss": 5.8869,
|
|
"mean_token_accuracy": 0.1639922022819519,
|
|
"num_tokens": 27341900.0,
|
|
"step": 13980
|
|
},
|
|
{
|
|
"entropy": 6.04265947341919,
|
|
"epoch": 1.3979607137501875,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00048118142364307864,
|
|
"loss": 5.8196,
|
|
"mean_token_accuracy": 0.166228486597538,
|
|
"num_tokens": 27351991.0,
|
|
"step": 13985
|
|
},
|
|
{
|
|
"entropy": 6.142511034011841,
|
|
"epoch": 1.398460538811416,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004811671328829225,
|
|
"loss": 5.8908,
|
|
"mean_token_accuracy": 0.16402522325515748,
|
|
"num_tokens": 27361634.0,
|
|
"step": 13990
|
|
},
|
|
{
|
|
"entropy": 6.180378198623657,
|
|
"epoch": 1.3989603638726447,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00048115283693565445,
|
|
"loss": 5.9159,
|
|
"mean_token_accuracy": 0.15981507897377015,
|
|
"num_tokens": 27373528.0,
|
|
"step": 13995
|
|
},
|
|
{
|
|
"entropy": 6.148707723617553,
|
|
"epoch": 1.3994601889338731,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.000481138535801634,
|
|
"loss": 5.9146,
|
|
"mean_token_accuracy": 0.1565297707915306,
|
|
"num_tokens": 27382123.0,
|
|
"step": 14000
|
|
},
|
|
{
|
|
"entropy": 6.144369220733642,
|
|
"epoch": 1.3999600139951016,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.000481124229481221,
|
|
"loss": 5.8873,
|
|
"mean_token_accuracy": 0.16118423491716385,
|
|
"num_tokens": 27392486.0,
|
|
"step": 14005
|
|
},
|
|
{
|
|
"entropy": 6.159963512420655,
|
|
"epoch": 1.4004598390563303,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004811099179747755,
|
|
"loss": 5.8903,
|
|
"mean_token_accuracy": 0.16086832582950591,
|
|
"num_tokens": 27402018.0,
|
|
"step": 14010
|
|
},
|
|
{
|
|
"entropy": 6.145850753784179,
|
|
"epoch": 1.4009596641175588,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.00048109560128265747,
|
|
"loss": 5.8914,
|
|
"mean_token_accuracy": 0.1591351494193077,
|
|
"num_tokens": 27411404.0,
|
|
"step": 14015
|
|
},
|
|
{
|
|
"entropy": 6.185385370254517,
|
|
"epoch": 1.4014594891787875,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004810812794052271,
|
|
"loss": 6.0506,
|
|
"mean_token_accuracy": 0.14900418370962143,
|
|
"num_tokens": 27420968.0,
|
|
"step": 14020
|
|
},
|
|
{
|
|
"entropy": 6.172234344482422,
|
|
"epoch": 1.401959314240016,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004810669523428449,
|
|
"loss": 5.8959,
|
|
"mean_token_accuracy": 0.15800752714276314,
|
|
"num_tokens": 27430964.0,
|
|
"step": 14025
|
|
},
|
|
{
|
|
"entropy": 6.123978996276856,
|
|
"epoch": 1.4024591393012447,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.000481052620095871,
|
|
"loss": 5.9186,
|
|
"mean_token_accuracy": 0.15444019436836243,
|
|
"num_tokens": 27440517.0,
|
|
"step": 14030
|
|
},
|
|
{
|
|
"entropy": 6.056941080093384,
|
|
"epoch": 1.4029589643624731,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004810382826646664,
|
|
"loss": 5.9343,
|
|
"mean_token_accuracy": 0.15636221468448638,
|
|
"num_tokens": 27449085.0,
|
|
"step": 14035
|
|
},
|
|
{
|
|
"entropy": 6.069472932815552,
|
|
"epoch": 1.4034587894237016,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004810239400495915,
|
|
"loss": 5.8326,
|
|
"mean_token_accuracy": 0.1678320050239563,
|
|
"num_tokens": 27457637.0,
|
|
"step": 14040
|
|
},
|
|
{
|
|
"entropy": 6.157347393035889,
|
|
"epoch": 1.4039586144849303,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004810095922510073,
|
|
"loss": 5.9574,
|
|
"mean_token_accuracy": 0.15599428713321686,
|
|
"num_tokens": 27467967.0,
|
|
"step": 14045
|
|
},
|
|
{
|
|
"entropy": 6.114198541641235,
|
|
"epoch": 1.4044584395461588,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.00048099523926927487,
|
|
"loss": 5.9249,
|
|
"mean_token_accuracy": 0.15783270448446274,
|
|
"num_tokens": 27477386.0,
|
|
"step": 14050
|
|
},
|
|
{
|
|
"entropy": 6.108553791046143,
|
|
"epoch": 1.4049582646073875,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004809808811047552,
|
|
"loss": 5.83,
|
|
"mean_token_accuracy": 0.16031135469675065,
|
|
"num_tokens": 27487289.0,
|
|
"step": 14055
|
|
},
|
|
{
|
|
"entropy": 6.147035026550293,
|
|
"epoch": 1.405458089668616,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00048096651775780943,
|
|
"loss": 5.8258,
|
|
"mean_token_accuracy": 0.1638666421175003,
|
|
"num_tokens": 27496687.0,
|
|
"step": 14060
|
|
},
|
|
{
|
|
"entropy": 6.085003137588501,
|
|
"epoch": 1.4059579147298447,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004809521492287992,
|
|
"loss": 5.8524,
|
|
"mean_token_accuracy": 0.16258841902017593,
|
|
"num_tokens": 27507040.0,
|
|
"step": 14065
|
|
},
|
|
{
|
|
"entropy": 6.180186653137207,
|
|
"epoch": 1.4064577397910731,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004809377755180858,
|
|
"loss": 5.9704,
|
|
"mean_token_accuracy": 0.14970656707882882,
|
|
"num_tokens": 27516861.0,
|
|
"step": 14070
|
|
},
|
|
{
|
|
"entropy": 6.1892537593841555,
|
|
"epoch": 1.4069575648523016,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004809233966260311,
|
|
"loss": 5.8383,
|
|
"mean_token_accuracy": 0.17061182111501694,
|
|
"num_tokens": 27526816.0,
|
|
"step": 14075
|
|
},
|
|
{
|
|
"entropy": 6.134786653518677,
|
|
"epoch": 1.4074573899135303,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004809090125529966,
|
|
"loss": 5.9106,
|
|
"mean_token_accuracy": 0.16102984845638274,
|
|
"num_tokens": 27535984.0,
|
|
"step": 14080
|
|
},
|
|
{
|
|
"entropy": 6.131832313537598,
|
|
"epoch": 1.4079572149747588,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00048089462329934437,
|
|
"loss": 5.9056,
|
|
"mean_token_accuracy": 0.15271441340446473,
|
|
"num_tokens": 27545515.0,
|
|
"step": 14085
|
|
},
|
|
{
|
|
"entropy": 6.107638025283814,
|
|
"epoch": 1.4084570400359875,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.00048088022886543636,
|
|
"loss": 5.8664,
|
|
"mean_token_accuracy": 0.1622526004910469,
|
|
"num_tokens": 27554673.0,
|
|
"step": 14090
|
|
},
|
|
{
|
|
"entropy": 6.18196816444397,
|
|
"epoch": 1.408956865097216,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004808658292516348,
|
|
"loss": 5.8817,
|
|
"mean_token_accuracy": 0.15931390970945358,
|
|
"num_tokens": 27564282.0,
|
|
"step": 14095
|
|
},
|
|
{
|
|
"entropy": 6.1313880443572994,
|
|
"epoch": 1.4094566901584447,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00048085142445830197,
|
|
"loss": 5.9656,
|
|
"mean_token_accuracy": 0.14879624396562577,
|
|
"num_tokens": 27574205.0,
|
|
"step": 14100
|
|
},
|
|
{
|
|
"entropy": 6.183283472061158,
|
|
"epoch": 1.4099565152196731,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00048083701448580027,
|
|
"loss": 5.9254,
|
|
"mean_token_accuracy": 0.1590803638100624,
|
|
"num_tokens": 27584283.0,
|
|
"step": 14105
|
|
},
|
|
{
|
|
"entropy": 6.182303047180175,
|
|
"epoch": 1.4104563402809016,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.00048082259933449224,
|
|
"loss": 5.8782,
|
|
"mean_token_accuracy": 0.156558820605278,
|
|
"num_tokens": 27592828.0,
|
|
"step": 14110
|
|
},
|
|
{
|
|
"entropy": 6.088471984863281,
|
|
"epoch": 1.4109561653421303,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004808081790047406,
|
|
"loss": 5.9015,
|
|
"mean_token_accuracy": 0.16590752750635146,
|
|
"num_tokens": 27602412.0,
|
|
"step": 14115
|
|
},
|
|
{
|
|
"entropy": 6.125770807266235,
|
|
"epoch": 1.4114559904033588,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00048079375349690807,
|
|
"loss": 5.8844,
|
|
"mean_token_accuracy": 0.15807032883167266,
|
|
"num_tokens": 27611685.0,
|
|
"step": 14120
|
|
},
|
|
{
|
|
"entropy": 6.174746751785278,
|
|
"epoch": 1.4119558154645873,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00048077932281135775,
|
|
"loss": 5.927,
|
|
"mean_token_accuracy": 0.15109578222036363,
|
|
"num_tokens": 27621108.0,
|
|
"step": 14125
|
|
},
|
|
{
|
|
"entropy": 6.211177730560303,
|
|
"epoch": 1.412455640525816,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00048076488694845257,
|
|
"loss": 5.8653,
|
|
"mean_token_accuracy": 0.16404128521680833,
|
|
"num_tokens": 27631212.0,
|
|
"step": 14130
|
|
},
|
|
{
|
|
"entropy": 6.160654544830322,
|
|
"epoch": 1.4129554655870447,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00048075044590855574,
|
|
"loss": 6.0095,
|
|
"mean_token_accuracy": 0.15512877851724624,
|
|
"num_tokens": 27641071.0,
|
|
"step": 14135
|
|
},
|
|
{
|
|
"entropy": 6.164603757858276,
|
|
"epoch": 1.4134552906482731,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00048073599969203064,
|
|
"loss": 6.0095,
|
|
"mean_token_accuracy": 0.14836524203419685,
|
|
"num_tokens": 27650903.0,
|
|
"step": 14140
|
|
},
|
|
{
|
|
"entropy": 6.162520170211792,
|
|
"epoch": 1.4139551157095016,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004807215482992408,
|
|
"loss": 5.9085,
|
|
"mean_token_accuracy": 0.15974087715148927,
|
|
"num_tokens": 27661272.0,
|
|
"step": 14145
|
|
},
|
|
{
|
|
"entropy": 6.146009397506714,
|
|
"epoch": 1.4144549407707303,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004807070917305497,
|
|
"loss": 5.9002,
|
|
"mean_token_accuracy": 0.15626959800720214,
|
|
"num_tokens": 27671042.0,
|
|
"step": 14150
|
|
},
|
|
{
|
|
"entropy": 6.132666158676147,
|
|
"epoch": 1.4149547658319588,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00048069262998632115,
|
|
"loss": 5.9089,
|
|
"mean_token_accuracy": 0.15504830479621887,
|
|
"num_tokens": 27680876.0,
|
|
"step": 14155
|
|
},
|
|
{
|
|
"entropy": 6.178604316711426,
|
|
"epoch": 1.4154545908931873,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004806781630669189,
|
|
"loss": 5.8828,
|
|
"mean_token_accuracy": 0.15710073336958885,
|
|
"num_tokens": 27690193.0,
|
|
"step": 14160
|
|
},
|
|
{
|
|
"entropy": 6.142898654937744,
|
|
"epoch": 1.415954415954416,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00048066369097270694,
|
|
"loss": 5.8739,
|
|
"mean_token_accuracy": 0.1657583996653557,
|
|
"num_tokens": 27700095.0,
|
|
"step": 14165
|
|
},
|
|
{
|
|
"entropy": 6.082460927963257,
|
|
"epoch": 1.4164542410156447,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004806492137040495,
|
|
"loss": 5.9274,
|
|
"mean_token_accuracy": 0.15387239009141923,
|
|
"num_tokens": 27710172.0,
|
|
"step": 14170
|
|
},
|
|
{
|
|
"entropy": 6.121841382980347,
|
|
"epoch": 1.4169540660768731,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00048063473126131086,
|
|
"loss": 5.8603,
|
|
"mean_token_accuracy": 0.16136195212602616,
|
|
"num_tokens": 27720241.0,
|
|
"step": 14175
|
|
},
|
|
{
|
|
"entropy": 6.166153240203857,
|
|
"epoch": 1.4174538911381016,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004806202436448551,
|
|
"loss": 5.9291,
|
|
"mean_token_accuracy": 0.16084531098604202,
|
|
"num_tokens": 27730959.0,
|
|
"step": 14180
|
|
},
|
|
{
|
|
"entropy": 6.100432586669922,
|
|
"epoch": 1.4179537161993303,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004806057508550471,
|
|
"loss": 5.9178,
|
|
"mean_token_accuracy": 0.16295157372951508,
|
|
"num_tokens": 27740690.0,
|
|
"step": 14185
|
|
},
|
|
{
|
|
"entropy": 6.111538982391357,
|
|
"epoch": 1.4184535412605588,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004805912528922512,
|
|
"loss": 5.803,
|
|
"mean_token_accuracy": 0.16402893662452697,
|
|
"num_tokens": 27749538.0,
|
|
"step": 14190
|
|
},
|
|
{
|
|
"entropy": 6.147728681564331,
|
|
"epoch": 1.4189533663217873,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004805767497568323,
|
|
"loss": 5.8972,
|
|
"mean_token_accuracy": 0.1583215981721878,
|
|
"num_tokens": 27759150.0,
|
|
"step": 14195
|
|
},
|
|
{
|
|
"entropy": 6.15982346534729,
|
|
"epoch": 1.419453191383016,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00048056224144915534,
|
|
"loss": 5.892,
|
|
"mean_token_accuracy": 0.15838515907526016,
|
|
"num_tokens": 27767150.0,
|
|
"step": 14200
|
|
},
|
|
{
|
|
"entropy": 6.155028247833252,
|
|
"epoch": 1.4199530164442444,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.00048054772796958517,
|
|
"loss": 5.9291,
|
|
"mean_token_accuracy": 0.1578789696097374,
|
|
"num_tokens": 27776866.0,
|
|
"step": 14205
|
|
},
|
|
{
|
|
"entropy": 6.101190519332886,
|
|
"epoch": 1.4204528415054731,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00048053320931848713,
|
|
"loss": 5.7892,
|
|
"mean_token_accuracy": 0.16822739839553832,
|
|
"num_tokens": 27786941.0,
|
|
"step": 14210
|
|
},
|
|
{
|
|
"entropy": 6.2098836421966555,
|
|
"epoch": 1.4209526665667016,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00048051868549622644,
|
|
"loss": 6.0136,
|
|
"mean_token_accuracy": 0.15156687945127487,
|
|
"num_tokens": 27796962.0,
|
|
"step": 14215
|
|
},
|
|
{
|
|
"entropy": 6.102784156799316,
|
|
"epoch": 1.4214524916279303,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00048050415650316853,
|
|
"loss": 5.901,
|
|
"mean_token_accuracy": 0.15864731073379518,
|
|
"num_tokens": 27806609.0,
|
|
"step": 14220
|
|
},
|
|
{
|
|
"entropy": 6.164079999923706,
|
|
"epoch": 1.4219523166891588,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004804896223396789,
|
|
"loss": 5.9177,
|
|
"mean_token_accuracy": 0.1578953206539154,
|
|
"num_tokens": 27816734.0,
|
|
"step": 14225
|
|
},
|
|
{
|
|
"entropy": 6.1364082336425785,
|
|
"epoch": 1.4224521417503873,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004804750830061232,
|
|
"loss": 5.9716,
|
|
"mean_token_accuracy": 0.14960987567901612,
|
|
"num_tokens": 27826686.0,
|
|
"step": 14230
|
|
},
|
|
{
|
|
"entropy": 6.16151762008667,
|
|
"epoch": 1.422951966811616,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004804605385028673,
|
|
"loss": 5.897,
|
|
"mean_token_accuracy": 0.1558688461780548,
|
|
"num_tokens": 27836193.0,
|
|
"step": 14235
|
|
},
|
|
{
|
|
"entropy": 6.100816249847412,
|
|
"epoch": 1.4234517918728444,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004804459888302772,
|
|
"loss": 5.8565,
|
|
"mean_token_accuracy": 0.1650846168398857,
|
|
"num_tokens": 27845175.0,
|
|
"step": 14240
|
|
},
|
|
{
|
|
"entropy": 6.120284366607666,
|
|
"epoch": 1.4239516169340731,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.00048043143398871874,
|
|
"loss": 5.8821,
|
|
"mean_token_accuracy": 0.163255175948143,
|
|
"num_tokens": 27853829.0,
|
|
"step": 14245
|
|
},
|
|
{
|
|
"entropy": 6.17583818435669,
|
|
"epoch": 1.4244514419953016,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004804168739785583,
|
|
"loss": 5.948,
|
|
"mean_token_accuracy": 0.15891079008579254,
|
|
"num_tokens": 27863468.0,
|
|
"step": 14250
|
|
},
|
|
{
|
|
"entropy": 6.164515542984009,
|
|
"epoch": 1.4249512670565303,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004804023088001623,
|
|
"loss": 5.9232,
|
|
"mean_token_accuracy": 0.1552080787718296,
|
|
"num_tokens": 27873565.0,
|
|
"step": 14255
|
|
},
|
|
{
|
|
"entropy": 6.255309820175171,
|
|
"epoch": 1.4254510921177588,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004803877384538969,
|
|
"loss": 6.0268,
|
|
"mean_token_accuracy": 0.15062852203845978,
|
|
"num_tokens": 27883687.0,
|
|
"step": 14260
|
|
},
|
|
{
|
|
"entropy": 6.171930599212646,
|
|
"epoch": 1.4259509171789873,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.000480373162940129,
|
|
"loss": 6.0408,
|
|
"mean_token_accuracy": 0.15009994357824324,
|
|
"num_tokens": 27893702.0,
|
|
"step": 14265
|
|
},
|
|
{
|
|
"entropy": 6.186646318435669,
|
|
"epoch": 1.426450742240216,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00048035858225922506,
|
|
"loss": 5.8781,
|
|
"mean_token_accuracy": 0.1635551504790783,
|
|
"num_tokens": 27902809.0,
|
|
"step": 14270
|
|
},
|
|
{
|
|
"entropy": 6.294264078140259,
|
|
"epoch": 1.4269505673014444,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.00048034399641155206,
|
|
"loss": 5.9893,
|
|
"mean_token_accuracy": 0.15167927071452142,
|
|
"num_tokens": 27912810.0,
|
|
"step": 14275
|
|
},
|
|
{
|
|
"entropy": 6.174759387969971,
|
|
"epoch": 1.4274503923626731,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00048032940539747697,
|
|
"loss": 5.9558,
|
|
"mean_token_accuracy": 0.15171603709459305,
|
|
"num_tokens": 27922402.0,
|
|
"step": 14280
|
|
},
|
|
{
|
|
"entropy": 6.11567645072937,
|
|
"epoch": 1.4279502174239016,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00048031480921736686,
|
|
"loss": 5.9448,
|
|
"mean_token_accuracy": 0.16087897419929503,
|
|
"num_tokens": 27932379.0,
|
|
"step": 14285
|
|
},
|
|
{
|
|
"entropy": 6.228717374801636,
|
|
"epoch": 1.4284500424851303,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.000480300207871589,
|
|
"loss": 6.1143,
|
|
"mean_token_accuracy": 0.1481747403740883,
|
|
"num_tokens": 27942994.0,
|
|
"step": 14290
|
|
},
|
|
{
|
|
"entropy": 6.218153476715088,
|
|
"epoch": 1.4289498675463588,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00048028560136051076,
|
|
"loss": 5.9136,
|
|
"mean_token_accuracy": 0.15851071774959563,
|
|
"num_tokens": 27952860.0,
|
|
"step": 14295
|
|
},
|
|
{
|
|
"entropy": 6.164930152893066,
|
|
"epoch": 1.4294496926075873,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00048027098968449954,
|
|
"loss": 5.9422,
|
|
"mean_token_accuracy": 0.15416307449340821,
|
|
"num_tokens": 27962435.0,
|
|
"step": 14300
|
|
},
|
|
{
|
|
"entropy": 6.149840688705444,
|
|
"epoch": 1.429949517668816,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004802563728439231,
|
|
"loss": 5.8957,
|
|
"mean_token_accuracy": 0.15777752697467803,
|
|
"num_tokens": 27971889.0,
|
|
"step": 14305
|
|
},
|
|
{
|
|
"entropy": 6.174994277954101,
|
|
"epoch": 1.4304493427300444,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004802417508391491,
|
|
"loss": 5.9658,
|
|
"mean_token_accuracy": 0.1528554804623127,
|
|
"num_tokens": 27982683.0,
|
|
"step": 14310
|
|
},
|
|
{
|
|
"entropy": 6.132606363296508,
|
|
"epoch": 1.4309491677912731,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004802271236705455,
|
|
"loss": 5.8754,
|
|
"mean_token_accuracy": 0.1624034583568573,
|
|
"num_tokens": 27992408.0,
|
|
"step": 14315
|
|
},
|
|
{
|
|
"entropy": 6.265625905990601,
|
|
"epoch": 1.4314489928525016,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00048021249133848025,
|
|
"loss": 5.9676,
|
|
"mean_token_accuracy": 0.15260375365614892,
|
|
"num_tokens": 28002592.0,
|
|
"step": 14320
|
|
},
|
|
{
|
|
"entropy": 6.198496913909912,
|
|
"epoch": 1.4319488179137303,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00048019785384332154,
|
|
"loss": 5.9437,
|
|
"mean_token_accuracy": 0.1547225907444954,
|
|
"num_tokens": 28012148.0,
|
|
"step": 14325
|
|
},
|
|
{
|
|
"entropy": 6.150672912597656,
|
|
"epoch": 1.4324486429749588,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004801832111854376,
|
|
"loss": 5.9591,
|
|
"mean_token_accuracy": 0.15324863344430922,
|
|
"num_tokens": 28021341.0,
|
|
"step": 14330
|
|
},
|
|
{
|
|
"entropy": 6.132143592834472,
|
|
"epoch": 1.4329484680361873,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004801685633651969,
|
|
"loss": 5.9021,
|
|
"mean_token_accuracy": 0.16061148047447205,
|
|
"num_tokens": 28030721.0,
|
|
"step": 14335
|
|
},
|
|
{
|
|
"entropy": 6.072684812545776,
|
|
"epoch": 1.433448293097416,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004801539103829679,
|
|
"loss": 5.7969,
|
|
"mean_token_accuracy": 0.1627567395567894,
|
|
"num_tokens": 28040665.0,
|
|
"step": 14340
|
|
},
|
|
{
|
|
"entropy": 6.255423450469971,
|
|
"epoch": 1.4339481181586444,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004801392522391193,
|
|
"loss": 6.0391,
|
|
"mean_token_accuracy": 0.144136743247509,
|
|
"num_tokens": 28052307.0,
|
|
"step": 14345
|
|
},
|
|
{
|
|
"entropy": 6.175729131698608,
|
|
"epoch": 1.4344479432198731,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00048012458893401995,
|
|
"loss": 5.8851,
|
|
"mean_token_accuracy": 0.16727278977632523,
|
|
"num_tokens": 28061347.0,
|
|
"step": 14350
|
|
},
|
|
{
|
|
"entropy": 6.2000020980834964,
|
|
"epoch": 1.4349477682811016,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004801099204680387,
|
|
"loss": 5.9354,
|
|
"mean_token_accuracy": 0.1569803312420845,
|
|
"num_tokens": 28072088.0,
|
|
"step": 14355
|
|
},
|
|
{
|
|
"entropy": 6.2106773853302,
|
|
"epoch": 1.4354475933423303,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00048009524684154464,
|
|
"loss": 5.9715,
|
|
"mean_token_accuracy": 0.1545247182250023,
|
|
"num_tokens": 28081674.0,
|
|
"step": 14360
|
|
},
|
|
{
|
|
"entropy": 6.08840503692627,
|
|
"epoch": 1.4359474184035588,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004800805680549069,
|
|
"loss": 5.8681,
|
|
"mean_token_accuracy": 0.16416578441858293,
|
|
"num_tokens": 28091530.0,
|
|
"step": 14365
|
|
},
|
|
{
|
|
"entropy": 6.087087249755859,
|
|
"epoch": 1.4364472434647872,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00048006588410849497,
|
|
"loss": 5.8791,
|
|
"mean_token_accuracy": 0.1558594673871994,
|
|
"num_tokens": 28102322.0,
|
|
"step": 14370
|
|
},
|
|
{
|
|
"entropy": 6.188942718505859,
|
|
"epoch": 1.436947068526016,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.000480051195002678,
|
|
"loss": 5.879,
|
|
"mean_token_accuracy": 0.15761257112026214,
|
|
"num_tokens": 28112041.0,
|
|
"step": 14375
|
|
},
|
|
{
|
|
"entropy": 6.199165105819702,
|
|
"epoch": 1.4374468935872444,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00048003650073782586,
|
|
"loss": 5.9557,
|
|
"mean_token_accuracy": 0.15307693034410477,
|
|
"num_tokens": 28122451.0,
|
|
"step": 14380
|
|
},
|
|
{
|
|
"entropy": 6.120172691345215,
|
|
"epoch": 1.437946718648473,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.000480021801314308,
|
|
"loss": 5.8822,
|
|
"mean_token_accuracy": 0.1597979858517647,
|
|
"num_tokens": 28131949.0,
|
|
"step": 14385
|
|
},
|
|
{
|
|
"entropy": 6.114171886444092,
|
|
"epoch": 1.4384465437097016,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004800070967324944,
|
|
"loss": 5.9239,
|
|
"mean_token_accuracy": 0.1504079930484295,
|
|
"num_tokens": 28141905.0,
|
|
"step": 14390
|
|
},
|
|
{
|
|
"entropy": 6.076116371154785,
|
|
"epoch": 1.4389463687709303,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00047999238699275506,
|
|
"loss": 5.8984,
|
|
"mean_token_accuracy": 0.15590541511774064,
|
|
"num_tokens": 28150735.0,
|
|
"step": 14395
|
|
},
|
|
{
|
|
"entropy": 6.157782649993896,
|
|
"epoch": 1.4394461938321588,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00047997767209546,
|
|
"loss": 5.8771,
|
|
"mean_token_accuracy": 0.16161351650953293,
|
|
"num_tokens": 28160872.0,
|
|
"step": 14400
|
|
},
|
|
{
|
|
"entropy": 6.1595374584198,
|
|
"epoch": 1.4399460188933872,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004799629520409795,
|
|
"loss": 5.9406,
|
|
"mean_token_accuracy": 0.15811784267425538,
|
|
"num_tokens": 28170873.0,
|
|
"step": 14405
|
|
},
|
|
{
|
|
"entropy": 6.179621076583862,
|
|
"epoch": 1.440445843954616,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00047994822682968373,
|
|
"loss": 5.9148,
|
|
"mean_token_accuracy": 0.15638519823551178,
|
|
"num_tokens": 28180637.0,
|
|
"step": 14410
|
|
},
|
|
{
|
|
"entropy": 6.154677009582519,
|
|
"epoch": 1.4409456690158444,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00047993349646194343,
|
|
"loss": 5.9394,
|
|
"mean_token_accuracy": 0.15639625787734984,
|
|
"num_tokens": 28189326.0,
|
|
"step": 14415
|
|
},
|
|
{
|
|
"entropy": 6.110971260070801,
|
|
"epoch": 1.441445494077073,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00047991876093812904,
|
|
"loss": 5.8613,
|
|
"mean_token_accuracy": 0.1570332944393158,
|
|
"num_tokens": 28198729.0,
|
|
"step": 14420
|
|
},
|
|
{
|
|
"entropy": 6.109112930297852,
|
|
"epoch": 1.4419453191383016,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00047990402025861143,
|
|
"loss": 5.8232,
|
|
"mean_token_accuracy": 0.16734228283166885,
|
|
"num_tokens": 28207525.0,
|
|
"step": 14425
|
|
},
|
|
{
|
|
"entropy": 6.187689876556396,
|
|
"epoch": 1.4424451441995303,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004798892744237613,
|
|
"loss": 6.0315,
|
|
"mean_token_accuracy": 0.15251780599355697,
|
|
"num_tokens": 28218176.0,
|
|
"step": 14430
|
|
},
|
|
{
|
|
"entropy": 6.219600582122803,
|
|
"epoch": 1.4429449692607588,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00047987452343394976,
|
|
"loss": 5.9204,
|
|
"mean_token_accuracy": 0.1582502841949463,
|
|
"num_tokens": 28229207.0,
|
|
"step": 14435
|
|
},
|
|
{
|
|
"entropy": 6.203507614135742,
|
|
"epoch": 1.4434447943219872,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00047985976728954794,
|
|
"loss": 5.8668,
|
|
"mean_token_accuracy": 0.1604503870010376,
|
|
"num_tokens": 28238124.0,
|
|
"step": 14440
|
|
},
|
|
{
|
|
"entropy": 6.094093132019043,
|
|
"epoch": 1.443944619383216,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004798450059909271,
|
|
"loss": 5.9807,
|
|
"mean_token_accuracy": 0.14802010506391525,
|
|
"num_tokens": 28248359.0,
|
|
"step": 14445
|
|
},
|
|
{
|
|
"entropy": 6.220690679550171,
|
|
"epoch": 1.4444444444444444,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004798302395384586,
|
|
"loss": 5.9605,
|
|
"mean_token_accuracy": 0.14771072342991828,
|
|
"num_tokens": 28258200.0,
|
|
"step": 14450
|
|
},
|
|
{
|
|
"entropy": 6.238508176803589,
|
|
"epoch": 1.444944269505673,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00047981546793251405,
|
|
"loss": 5.9454,
|
|
"mean_token_accuracy": 0.14885313659906388,
|
|
"num_tokens": 28268512.0,
|
|
"step": 14455
|
|
},
|
|
{
|
|
"entropy": 6.106968545913697,
|
|
"epoch": 1.4454440945669016,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000479800691173465,
|
|
"loss": 5.8972,
|
|
"mean_token_accuracy": 0.16408976316452026,
|
|
"num_tokens": 28278657.0,
|
|
"step": 14460
|
|
},
|
|
{
|
|
"entropy": 6.078235340118408,
|
|
"epoch": 1.4459439196281303,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004797859092616832,
|
|
"loss": 5.9617,
|
|
"mean_token_accuracy": 0.15647161602973939,
|
|
"num_tokens": 28289104.0,
|
|
"step": 14465
|
|
},
|
|
{
|
|
"entropy": 6.134978723526001,
|
|
"epoch": 1.4464437446893588,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.00047977112219754064,
|
|
"loss": 5.8255,
|
|
"mean_token_accuracy": 0.16141843646764756,
|
|
"num_tokens": 28299110.0,
|
|
"step": 14470
|
|
},
|
|
{
|
|
"entropy": 6.124222946166992,
|
|
"epoch": 1.4469435697505872,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004797563299814094,
|
|
"loss": 5.886,
|
|
"mean_token_accuracy": 0.16420616954565048,
|
|
"num_tokens": 28309350.0,
|
|
"step": 14475
|
|
},
|
|
{
|
|
"entropy": 6.062426996231079,
|
|
"epoch": 1.447443394811816,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00047974153261366156,
|
|
"loss": 5.7562,
|
|
"mean_token_accuracy": 0.166972354054451,
|
|
"num_tokens": 28319080.0,
|
|
"step": 14480
|
|
},
|
|
{
|
|
"entropy": 6.159498071670532,
|
|
"epoch": 1.4479432198730444,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004797267300946694,
|
|
"loss": 5.8977,
|
|
"mean_token_accuracy": 0.15600424483418465,
|
|
"num_tokens": 28328853.0,
|
|
"step": 14485
|
|
},
|
|
{
|
|
"entropy": 6.172773122787476,
|
|
"epoch": 1.448443044934273,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00047971192242480544,
|
|
"loss": 5.9304,
|
|
"mean_token_accuracy": 0.15610072016716003,
|
|
"num_tokens": 28339499.0,
|
|
"step": 14490
|
|
},
|
|
{
|
|
"entropy": 6.153044986724853,
|
|
"epoch": 1.4489428699955016,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004796971096044422,
|
|
"loss": 5.9281,
|
|
"mean_token_accuracy": 0.15699478089809418,
|
|
"num_tokens": 28350068.0,
|
|
"step": 14495
|
|
},
|
|
{
|
|
"entropy": 6.1847161769866945,
|
|
"epoch": 1.44944269505673,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004796822916339523,
|
|
"loss": 5.9728,
|
|
"mean_token_accuracy": 0.15529006868600845,
|
|
"num_tokens": 28360912.0,
|
|
"step": 14500
|
|
},
|
|
{
|
|
"entropy": 6.166716623306274,
|
|
"epoch": 1.4499425201179588,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00047966746851370865,
|
|
"loss": 5.9246,
|
|
"mean_token_accuracy": 0.15355965495109558,
|
|
"num_tokens": 28370094.0,
|
|
"step": 14505
|
|
},
|
|
{
|
|
"entropy": 6.098060274124146,
|
|
"epoch": 1.4504423451791872,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004796526402440841,
|
|
"loss": 5.9046,
|
|
"mean_token_accuracy": 0.15746061354875565,
|
|
"num_tokens": 28380520.0,
|
|
"step": 14510
|
|
},
|
|
{
|
|
"entropy": 6.1130444526672365,
|
|
"epoch": 1.450942170240416,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004796378068254518,
|
|
"loss": 5.9872,
|
|
"mean_token_accuracy": 0.16089940965175628,
|
|
"num_tokens": 28390406.0,
|
|
"step": 14515
|
|
},
|
|
{
|
|
"entropy": 6.181748247146606,
|
|
"epoch": 1.4514419953016444,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.000479622968258185,
|
|
"loss": 5.9006,
|
|
"mean_token_accuracy": 0.16395324021577834,
|
|
"num_tokens": 28399935.0,
|
|
"step": 14520
|
|
},
|
|
{
|
|
"entropy": 6.119853925704956,
|
|
"epoch": 1.451941820362873,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004796081245426569,
|
|
"loss": 5.8947,
|
|
"mean_token_accuracy": 0.16107099056243895,
|
|
"num_tokens": 28409167.0,
|
|
"step": 14525
|
|
},
|
|
{
|
|
"entropy": 6.158179473876953,
|
|
"epoch": 1.4524416454241016,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00047959327567924115,
|
|
"loss": 5.9649,
|
|
"mean_token_accuracy": 0.15481597036123276,
|
|
"num_tokens": 28419093.0,
|
|
"step": 14530
|
|
},
|
|
{
|
|
"entropy": 6.101051378250122,
|
|
"epoch": 1.45294147048533,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00047957842166831103,
|
|
"loss": 5.8876,
|
|
"mean_token_accuracy": 0.15812289863824844,
|
|
"num_tokens": 28428803.0,
|
|
"step": 14535
|
|
},
|
|
{
|
|
"entropy": 6.112209796905518,
|
|
"epoch": 1.4534412955465588,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00047956356251024066,
|
|
"loss": 5.8754,
|
|
"mean_token_accuracy": 0.16673296988010405,
|
|
"num_tokens": 28439724.0,
|
|
"step": 14540
|
|
},
|
|
{
|
|
"entropy": 6.178677320480347,
|
|
"epoch": 1.4539411206077872,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004795486982054036,
|
|
"loss": 5.8549,
|
|
"mean_token_accuracy": 0.17007712721824647,
|
|
"num_tokens": 28448450.0,
|
|
"step": 14545
|
|
},
|
|
{
|
|
"entropy": 6.129712057113648,
|
|
"epoch": 1.454440945669016,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.000479533828754174,
|
|
"loss": 5.9913,
|
|
"mean_token_accuracy": 0.15599589496850969,
|
|
"num_tokens": 28458862.0,
|
|
"step": 14550
|
|
},
|
|
{
|
|
"entropy": 6.170761585235596,
|
|
"epoch": 1.4549407707302444,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004795189541569258,
|
|
"loss": 6.0435,
|
|
"mean_token_accuracy": 0.1463349536061287,
|
|
"num_tokens": 28469602.0,
|
|
"step": 14555
|
|
},
|
|
{
|
|
"entropy": 6.193738985061645,
|
|
"epoch": 1.455440595791473,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00047950407441403343,
|
|
"loss": 5.8647,
|
|
"mean_token_accuracy": 0.1647908315062523,
|
|
"num_tokens": 28480635.0,
|
|
"step": 14560
|
|
},
|
|
{
|
|
"entropy": 6.165647554397583,
|
|
"epoch": 1.4559404208527016,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004794891895258711,
|
|
"loss": 5.8913,
|
|
"mean_token_accuracy": 0.16056907474994658,
|
|
"num_tokens": 28490471.0,
|
|
"step": 14565
|
|
},
|
|
{
|
|
"entropy": 6.049009561538696,
|
|
"epoch": 1.45644024591393,
|
|
"grad_norm": 1.9296875,
|
|
"learning_rate": 0.0004794742994928134,
|
|
"loss": 5.7871,
|
|
"mean_token_accuracy": 0.17293789088726044,
|
|
"num_tokens": 28499595.0,
|
|
"step": 14570
|
|
},
|
|
{
|
|
"entropy": 6.1181245803833,
|
|
"epoch": 1.4569400709751588,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.000479459404315235,
|
|
"loss": 5.8931,
|
|
"mean_token_accuracy": 0.1584995061159134,
|
|
"num_tokens": 28508278.0,
|
|
"step": 14575
|
|
},
|
|
{
|
|
"entropy": 6.099142074584961,
|
|
"epoch": 1.4574398960363872,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00047944450399351054,
|
|
"loss": 5.9302,
|
|
"mean_token_accuracy": 0.15288180559873582,
|
|
"num_tokens": 28518286.0,
|
|
"step": 14580
|
|
},
|
|
{
|
|
"entropy": 6.181583833694458,
|
|
"epoch": 1.457939721097616,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.000479429598528015,
|
|
"loss": 5.9513,
|
|
"mean_token_accuracy": 0.15104594081640244,
|
|
"num_tokens": 28527517.0,
|
|
"step": 14585
|
|
},
|
|
{
|
|
"entropy": 6.354275846481324,
|
|
"epoch": 1.4584395461588444,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004794146879191233,
|
|
"loss": 6.1493,
|
|
"mean_token_accuracy": 0.1467358313500881,
|
|
"num_tokens": 28538521.0,
|
|
"step": 14590
|
|
},
|
|
{
|
|
"entropy": 6.191965818405151,
|
|
"epoch": 1.458939371220073,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004793997721672107,
|
|
"loss": 5.9166,
|
|
"mean_token_accuracy": 0.15522282123565673,
|
|
"num_tokens": 28547696.0,
|
|
"step": 14595
|
|
},
|
|
{
|
|
"entropy": 6.075242757797241,
|
|
"epoch": 1.4594391962813016,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00047938485127265243,
|
|
"loss": 5.9063,
|
|
"mean_token_accuracy": 0.16249443590641022,
|
|
"num_tokens": 28558083.0,
|
|
"step": 14600
|
|
},
|
|
{
|
|
"entropy": 6.138222694396973,
|
|
"epoch": 1.45993902134253,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004793699252358239,
|
|
"loss": 5.8731,
|
|
"mean_token_accuracy": 0.1642042025923729,
|
|
"num_tokens": 28568453.0,
|
|
"step": 14605
|
|
},
|
|
{
|
|
"entropy": 6.110101270675659,
|
|
"epoch": 1.4604388464037588,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004793549940571006,
|
|
"loss": 5.9006,
|
|
"mean_token_accuracy": 0.15804723501205445,
|
|
"num_tokens": 28578401.0,
|
|
"step": 14610
|
|
},
|
|
{
|
|
"entropy": 6.17487645149231,
|
|
"epoch": 1.4609386714649872,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00047934005773685824,
|
|
"loss": 5.917,
|
|
"mean_token_accuracy": 0.16274190843105316,
|
|
"num_tokens": 28587717.0,
|
|
"step": 14615
|
|
},
|
|
{
|
|
"entropy": 6.189158391952515,
|
|
"epoch": 1.461438496526216,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.00047932511627547266,
|
|
"loss": 5.9197,
|
|
"mean_token_accuracy": 0.15721644163131715,
|
|
"num_tokens": 28597609.0,
|
|
"step": 14620
|
|
},
|
|
{
|
|
"entropy": 6.116632652282715,
|
|
"epoch": 1.4619383215874444,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004793101696733197,
|
|
"loss": 5.854,
|
|
"mean_token_accuracy": 0.1576530657708645,
|
|
"num_tokens": 28606742.0,
|
|
"step": 14625
|
|
},
|
|
{
|
|
"entropy": 6.090998029708862,
|
|
"epoch": 1.4624381466486729,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00047929521793077545,
|
|
"loss": 5.8662,
|
|
"mean_token_accuracy": 0.1610901713371277,
|
|
"num_tokens": 28615822.0,
|
|
"step": 14630
|
|
},
|
|
{
|
|
"entropy": 6.1250653743743895,
|
|
"epoch": 1.4629379717099016,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004792802610482161,
|
|
"loss": 5.9559,
|
|
"mean_token_accuracy": 0.15274227187037467,
|
|
"num_tokens": 28625372.0,
|
|
"step": 14635
|
|
},
|
|
{
|
|
"entropy": 6.178671932220459,
|
|
"epoch": 1.46343779677113,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004792652990260179,
|
|
"loss": 5.9443,
|
|
"mean_token_accuracy": 0.15415917783975602,
|
|
"num_tokens": 28635329.0,
|
|
"step": 14640
|
|
},
|
|
{
|
|
"entropy": 6.18708987236023,
|
|
"epoch": 1.4639376218323585,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004792503318645574,
|
|
"loss": 5.94,
|
|
"mean_token_accuracy": 0.15805829763412477,
|
|
"num_tokens": 28645534.0,
|
|
"step": 14645
|
|
},
|
|
{
|
|
"entropy": 6.17720046043396,
|
|
"epoch": 1.4644374468935872,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00047923535956421104,
|
|
"loss": 6.0049,
|
|
"mean_token_accuracy": 0.15069349855184555,
|
|
"num_tokens": 28657207.0,
|
|
"step": 14650
|
|
},
|
|
{
|
|
"entropy": 6.156323862075806,
|
|
"epoch": 1.464937271954816,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00047922038212535565,
|
|
"loss": 5.9406,
|
|
"mean_token_accuracy": 0.15996264815330505,
|
|
"num_tokens": 28667260.0,
|
|
"step": 14655
|
|
},
|
|
{
|
|
"entropy": 6.135656547546387,
|
|
"epoch": 1.4654370970160444,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00047920539954836793,
|
|
"loss": 5.8258,
|
|
"mean_token_accuracy": 0.15990129858255386,
|
|
"num_tokens": 28677255.0,
|
|
"step": 14660
|
|
},
|
|
{
|
|
"entropy": 6.133906602859497,
|
|
"epoch": 1.4659369220772729,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.000479190411833625,
|
|
"loss": 5.8922,
|
|
"mean_token_accuracy": 0.16863906234502793,
|
|
"num_tokens": 28687136.0,
|
|
"step": 14665
|
|
},
|
|
{
|
|
"entropy": 6.1888512134552,
|
|
"epoch": 1.4664367471385016,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.00047917541898150377,
|
|
"loss": 5.9443,
|
|
"mean_token_accuracy": 0.15653647035360335,
|
|
"num_tokens": 28697499.0,
|
|
"step": 14670
|
|
},
|
|
{
|
|
"entropy": 6.215901803970337,
|
|
"epoch": 1.46693657219973,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00047916042099238154,
|
|
"loss": 6.143,
|
|
"mean_token_accuracy": 0.1443213030695915,
|
|
"num_tokens": 28706843.0,
|
|
"step": 14675
|
|
},
|
|
{
|
|
"entropy": 6.159741306304932,
|
|
"epoch": 1.4674363972609585,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00047914541786663566,
|
|
"loss": 5.9218,
|
|
"mean_token_accuracy": 0.15912147015333175,
|
|
"num_tokens": 28715676.0,
|
|
"step": 14680
|
|
},
|
|
{
|
|
"entropy": 6.040154075622558,
|
|
"epoch": 1.4679362223221872,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00047913040960464363,
|
|
"loss": 5.8458,
|
|
"mean_token_accuracy": 0.16045166850090026,
|
|
"num_tokens": 28725714.0,
|
|
"step": 14685
|
|
},
|
|
{
|
|
"entropy": 6.109461879730224,
|
|
"epoch": 1.468436047383416,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00047911539620678305,
|
|
"loss": 5.8981,
|
|
"mean_token_accuracy": 0.1575067088007927,
|
|
"num_tokens": 28734928.0,
|
|
"step": 14690
|
|
},
|
|
{
|
|
"entropy": 6.214490652084351,
|
|
"epoch": 1.4689358724446444,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004791003776734316,
|
|
"loss": 5.8827,
|
|
"mean_token_accuracy": 0.16021695584058762,
|
|
"num_tokens": 28743999.0,
|
|
"step": 14695
|
|
},
|
|
{
|
|
"entropy": 6.110587310791016,
|
|
"epoch": 1.4694356975058729,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00047908535400496713,
|
|
"loss": 5.8697,
|
|
"mean_token_accuracy": 0.16157838702201843,
|
|
"num_tokens": 28753220.0,
|
|
"step": 14700
|
|
},
|
|
{
|
|
"entropy": 6.102980613708496,
|
|
"epoch": 1.4699355225671016,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.00047907032520176765,
|
|
"loss": 5.9195,
|
|
"mean_token_accuracy": 0.15651477873325348,
|
|
"num_tokens": 28762525.0,
|
|
"step": 14705
|
|
},
|
|
{
|
|
"entropy": 6.119652509689331,
|
|
"epoch": 1.47043534762833,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004790552912642113,
|
|
"loss": 5.8493,
|
|
"mean_token_accuracy": 0.16263106763362883,
|
|
"num_tokens": 28772749.0,
|
|
"step": 14710
|
|
},
|
|
{
|
|
"entropy": 6.09613618850708,
|
|
"epoch": 1.4709351726895585,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00047904025219267643,
|
|
"loss": 5.8545,
|
|
"mean_token_accuracy": 0.16698092073202134,
|
|
"num_tokens": 28782685.0,
|
|
"step": 14715
|
|
},
|
|
{
|
|
"entropy": 6.1994640827178955,
|
|
"epoch": 1.4714349977507872,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.00047902520798754125,
|
|
"loss": 6.0044,
|
|
"mean_token_accuracy": 0.1522551216185093,
|
|
"num_tokens": 28794172.0,
|
|
"step": 14720
|
|
},
|
|
{
|
|
"entropy": 6.172838163375855,
|
|
"epoch": 1.471934822812016,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004790101586491843,
|
|
"loss": 5.9801,
|
|
"mean_token_accuracy": 0.1458091601729393,
|
|
"num_tokens": 28805513.0,
|
|
"step": 14725
|
|
},
|
|
{
|
|
"entropy": 6.186948156356811,
|
|
"epoch": 1.4724346478732444,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004789951041779843,
|
|
"loss": 5.9139,
|
|
"mean_token_accuracy": 0.16275637447834015,
|
|
"num_tokens": 28815737.0,
|
|
"step": 14730
|
|
},
|
|
{
|
|
"entropy": 6.125944757461548,
|
|
"epoch": 1.4729344729344729,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00047898004457432,
|
|
"loss": 5.8995,
|
|
"mean_token_accuracy": 0.1576883852481842,
|
|
"num_tokens": 28824901.0,
|
|
"step": 14735
|
|
},
|
|
{
|
|
"entropy": 6.105707836151123,
|
|
"epoch": 1.4734342979957016,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004789649798385702,
|
|
"loss": 5.8519,
|
|
"mean_token_accuracy": 0.1626073956489563,
|
|
"num_tokens": 28833625.0,
|
|
"step": 14740
|
|
},
|
|
{
|
|
"entropy": 6.000137519836426,
|
|
"epoch": 1.47393412305693,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00047894990997111403,
|
|
"loss": 5.788,
|
|
"mean_token_accuracy": 0.17254174053668975,
|
|
"num_tokens": 28843084.0,
|
|
"step": 14745
|
|
},
|
|
{
|
|
"entropy": 6.099820137023926,
|
|
"epoch": 1.4744339481181585,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00047893483497233057,
|
|
"loss": 5.8222,
|
|
"mean_token_accuracy": 0.16964966654777527,
|
|
"num_tokens": 28852320.0,
|
|
"step": 14750
|
|
},
|
|
{
|
|
"entropy": 6.124870920181275,
|
|
"epoch": 1.4749337731793872,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004789197548425992,
|
|
"loss": 5.8601,
|
|
"mean_token_accuracy": 0.16351866126060485,
|
|
"num_tokens": 28861379.0,
|
|
"step": 14755
|
|
},
|
|
{
|
|
"entropy": 6.057726812362671,
|
|
"epoch": 1.4754335982406157,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004789046695822992,
|
|
"loss": 5.8656,
|
|
"mean_token_accuracy": 0.1662130355834961,
|
|
"num_tokens": 28871181.0,
|
|
"step": 14760
|
|
},
|
|
{
|
|
"entropy": 6.161553573608399,
|
|
"epoch": 1.4759334233018444,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00047888957919181026,
|
|
"loss": 5.9235,
|
|
"mean_token_accuracy": 0.16569416970014572,
|
|
"num_tokens": 28880763.0,
|
|
"step": 14765
|
|
},
|
|
{
|
|
"entropy": 6.042367172241211,
|
|
"epoch": 1.4764332483630729,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004788744836715119,
|
|
"loss": 5.8459,
|
|
"mean_token_accuracy": 0.16730682253837587,
|
|
"num_tokens": 28889876.0,
|
|
"step": 14770
|
|
},
|
|
{
|
|
"entropy": 6.173138570785523,
|
|
"epoch": 1.4769330734243016,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004788593830217841,
|
|
"loss": 5.8908,
|
|
"mean_token_accuracy": 0.1583087906241417,
|
|
"num_tokens": 28899765.0,
|
|
"step": 14775
|
|
},
|
|
{
|
|
"entropy": 6.176129913330078,
|
|
"epoch": 1.47743289848553,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00047884427724300657,
|
|
"loss": 5.9449,
|
|
"mean_token_accuracy": 0.15468351691961288,
|
|
"num_tokens": 28909755.0,
|
|
"step": 14780
|
|
},
|
|
{
|
|
"entropy": 6.149960899353028,
|
|
"epoch": 1.4779327235467585,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004788291663355595,
|
|
"loss": 5.894,
|
|
"mean_token_accuracy": 0.1665000408887863,
|
|
"num_tokens": 28919368.0,
|
|
"step": 14785
|
|
},
|
|
{
|
|
"entropy": 6.165680408477783,
|
|
"epoch": 1.4784325486079872,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004788140502998231,
|
|
"loss": 5.9294,
|
|
"mean_token_accuracy": 0.15894270688295364,
|
|
"num_tokens": 28930076.0,
|
|
"step": 14790
|
|
},
|
|
{
|
|
"entropy": 6.140274333953857,
|
|
"epoch": 1.4789323736692157,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004787989291361776,
|
|
"loss": 5.9205,
|
|
"mean_token_accuracy": 0.1603965252637863,
|
|
"num_tokens": 28939555.0,
|
|
"step": 14795
|
|
},
|
|
{
|
|
"entropy": 6.148188877105713,
|
|
"epoch": 1.4794321987304444,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004787838028450035,
|
|
"loss": 5.9848,
|
|
"mean_token_accuracy": 0.14777956530451775,
|
|
"num_tokens": 28951084.0,
|
|
"step": 14800
|
|
},
|
|
{
|
|
"entropy": 6.226462173461914,
|
|
"epoch": 1.4799320237916729,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00047876867142668136,
|
|
"loss": 5.9414,
|
|
"mean_token_accuracy": 0.1543032169342041,
|
|
"num_tokens": 28960798.0,
|
|
"step": 14805
|
|
},
|
|
{
|
|
"entropy": 6.1780486583709715,
|
|
"epoch": 1.4804318488529016,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0004787535348815918,
|
|
"loss": 5.864,
|
|
"mean_token_accuracy": 0.16375095248222352,
|
|
"num_tokens": 28970543.0,
|
|
"step": 14810
|
|
},
|
|
{
|
|
"entropy": 6.194151735305786,
|
|
"epoch": 1.48093167391413,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00047873839321011587,
|
|
"loss": 6.012,
|
|
"mean_token_accuracy": 0.14943614453077317,
|
|
"num_tokens": 28979863.0,
|
|
"step": 14815
|
|
},
|
|
{
|
|
"entropy": 6.129429864883423,
|
|
"epoch": 1.4814314989753585,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004787232464126343,
|
|
"loss": 5.8644,
|
|
"mean_token_accuracy": 0.16435156166553497,
|
|
"num_tokens": 28989774.0,
|
|
"step": 14820
|
|
},
|
|
{
|
|
"entropy": 6.19352879524231,
|
|
"epoch": 1.4819313240365872,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004787080944895283,
|
|
"loss": 5.996,
|
|
"mean_token_accuracy": 0.1473240524530411,
|
|
"num_tokens": 29000608.0,
|
|
"step": 14825
|
|
},
|
|
{
|
|
"entropy": 6.1841965675354,
|
|
"epoch": 1.4824311490978157,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00047869293744117906,
|
|
"loss": 6.0098,
|
|
"mean_token_accuracy": 0.15313551798462868,
|
|
"num_tokens": 29010977.0,
|
|
"step": 14830
|
|
},
|
|
{
|
|
"entropy": 6.220831680297851,
|
|
"epoch": 1.4829309741590444,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00047867777526796793,
|
|
"loss": 5.856,
|
|
"mean_token_accuracy": 0.15731898695230484,
|
|
"num_tokens": 29021868.0,
|
|
"step": 14835
|
|
},
|
|
{
|
|
"entropy": 6.115712213516235,
|
|
"epoch": 1.4834307992202729,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004786626079702764,
|
|
"loss": 5.9075,
|
|
"mean_token_accuracy": 0.15869607031345367,
|
|
"num_tokens": 29031878.0,
|
|
"step": 14840
|
|
},
|
|
{
|
|
"entropy": 6.217625761032105,
|
|
"epoch": 1.4839306242815016,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004786474355484861,
|
|
"loss": 6.0335,
|
|
"mean_token_accuracy": 0.15758893713355066,
|
|
"num_tokens": 29041862.0,
|
|
"step": 14845
|
|
},
|
|
{
|
|
"entropy": 6.116294860839844,
|
|
"epoch": 1.48443044934273,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004786322580029786,
|
|
"loss": 5.949,
|
|
"mean_token_accuracy": 0.1577303647994995,
|
|
"num_tokens": 29052534.0,
|
|
"step": 14850
|
|
},
|
|
{
|
|
"entropy": 6.123795652389527,
|
|
"epoch": 1.4849302744039585,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00047861707533413593,
|
|
"loss": 5.8547,
|
|
"mean_token_accuracy": 0.16392020434141158,
|
|
"num_tokens": 29061958.0,
|
|
"step": 14855
|
|
},
|
|
{
|
|
"entropy": 6.063033246994019,
|
|
"epoch": 1.4854300994651872,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004786018875423401,
|
|
"loss": 5.7618,
|
|
"mean_token_accuracy": 0.166125600785017,
|
|
"num_tokens": 29071816.0,
|
|
"step": 14860
|
|
},
|
|
{
|
|
"entropy": 6.1030198097229,
|
|
"epoch": 1.4859299245264157,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00047858669462797317,
|
|
"loss": 5.8596,
|
|
"mean_token_accuracy": 0.1690874069929123,
|
|
"num_tokens": 29081198.0,
|
|
"step": 14865
|
|
},
|
|
{
|
|
"entropy": 6.134812068939209,
|
|
"epoch": 1.4864297495876444,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00047857149659141736,
|
|
"loss": 5.9842,
|
|
"mean_token_accuracy": 0.1529584437608719,
|
|
"num_tokens": 29091197.0,
|
|
"step": 14870
|
|
},
|
|
{
|
|
"entropy": 6.141243028640747,
|
|
"epoch": 1.4869295746488729,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004785562934330551,
|
|
"loss": 5.9408,
|
|
"mean_token_accuracy": 0.15979982614517213,
|
|
"num_tokens": 29100386.0,
|
|
"step": 14875
|
|
},
|
|
{
|
|
"entropy": 6.164915895462036,
|
|
"epoch": 1.4874293997101016,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.00047854108515326885,
|
|
"loss": 5.9109,
|
|
"mean_token_accuracy": 0.15709883868694305,
|
|
"num_tokens": 29110056.0,
|
|
"step": 14880
|
|
},
|
|
{
|
|
"entropy": 6.093268585205078,
|
|
"epoch": 1.48792922477133,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004785258717524412,
|
|
"loss": 5.7527,
|
|
"mean_token_accuracy": 0.17023885250091553,
|
|
"num_tokens": 29119157.0,
|
|
"step": 14885
|
|
},
|
|
{
|
|
"entropy": 6.172559642791748,
|
|
"epoch": 1.4884290498325585,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00047851065323095514,
|
|
"loss": 5.8884,
|
|
"mean_token_accuracy": 0.15377486795186995,
|
|
"num_tokens": 29129075.0,
|
|
"step": 14890
|
|
},
|
|
{
|
|
"entropy": 6.14768352508545,
|
|
"epoch": 1.4889288748937872,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004784954295891933,
|
|
"loss": 5.9267,
|
|
"mean_token_accuracy": 0.1599687159061432,
|
|
"num_tokens": 29139026.0,
|
|
"step": 14895
|
|
},
|
|
{
|
|
"entropy": 6.131284952163696,
|
|
"epoch": 1.4894286999550157,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00047848020082753883,
|
|
"loss": 5.8344,
|
|
"mean_token_accuracy": 0.16366566866636276,
|
|
"num_tokens": 29149315.0,
|
|
"step": 14900
|
|
},
|
|
{
|
|
"entropy": 6.11028904914856,
|
|
"epoch": 1.4899285250162442,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004784649669463749,
|
|
"loss": 5.901,
|
|
"mean_token_accuracy": 0.1520991563796997,
|
|
"num_tokens": 29158916.0,
|
|
"step": 14905
|
|
},
|
|
{
|
|
"entropy": 6.122009515762329,
|
|
"epoch": 1.4904283500774729,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00047844972794608474,
|
|
"loss": 5.887,
|
|
"mean_token_accuracy": 0.15574095398187637,
|
|
"num_tokens": 29166844.0,
|
|
"step": 14910
|
|
},
|
|
{
|
|
"entropy": 6.097465562820434,
|
|
"epoch": 1.4909281751387016,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00047843448382705185,
|
|
"loss": 5.8494,
|
|
"mean_token_accuracy": 0.17061115056276321,
|
|
"num_tokens": 29176057.0,
|
|
"step": 14915
|
|
},
|
|
{
|
|
"entropy": 6.091483068466187,
|
|
"epoch": 1.49142800019993,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00047841923458965966,
|
|
"loss": 5.893,
|
|
"mean_token_accuracy": 0.16030517518520354,
|
|
"num_tokens": 29186212.0,
|
|
"step": 14920
|
|
},
|
|
{
|
|
"entropy": 6.044935894012451,
|
|
"epoch": 1.4919278252611585,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00047840398023429176,
|
|
"loss": 5.83,
|
|
"mean_token_accuracy": 0.16389580219984054,
|
|
"num_tokens": 29196138.0,
|
|
"step": 14925
|
|
},
|
|
{
|
|
"entropy": 6.248041582107544,
|
|
"epoch": 1.4924276503223872,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.00047838872076133213,
|
|
"loss": 5.9521,
|
|
"mean_token_accuracy": 0.15093939006328583,
|
|
"num_tokens": 29205979.0,
|
|
"step": 14930
|
|
},
|
|
{
|
|
"entropy": 6.1723264217376705,
|
|
"epoch": 1.4929274753836157,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004783734561711647,
|
|
"loss": 5.9478,
|
|
"mean_token_accuracy": 0.15050376653671266,
|
|
"num_tokens": 29214776.0,
|
|
"step": 14935
|
|
},
|
|
{
|
|
"entropy": 6.058135271072388,
|
|
"epoch": 1.4934273004448442,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00047835818646417333,
|
|
"loss": 5.8007,
|
|
"mean_token_accuracy": 0.16314827799797058,
|
|
"num_tokens": 29223823.0,
|
|
"step": 14940
|
|
},
|
|
{
|
|
"entropy": 6.123723745346069,
|
|
"epoch": 1.4939271255060729,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004783429116407423,
|
|
"loss": 5.883,
|
|
"mean_token_accuracy": 0.16150118112564088,
|
|
"num_tokens": 29232974.0,
|
|
"step": 14945
|
|
},
|
|
{
|
|
"entropy": 6.146603631973266,
|
|
"epoch": 1.4944269505673016,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00047832763170125605,
|
|
"loss": 5.8555,
|
|
"mean_token_accuracy": 0.1592354506254196,
|
|
"num_tokens": 29241773.0,
|
|
"step": 14950
|
|
},
|
|
{
|
|
"entropy": 6.093553876876831,
|
|
"epoch": 1.49492677562853,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00047831234664609887,
|
|
"loss": 5.8239,
|
|
"mean_token_accuracy": 0.1623486638069153,
|
|
"num_tokens": 29251490.0,
|
|
"step": 14955
|
|
},
|
|
{
|
|
"entropy": 6.033182525634766,
|
|
"epoch": 1.4954266006897585,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00047829705647565535,
|
|
"loss": 5.8263,
|
|
"mean_token_accuracy": 0.17424614429473878,
|
|
"num_tokens": 29260338.0,
|
|
"step": 14960
|
|
},
|
|
{
|
|
"entropy": 6.075300455093384,
|
|
"epoch": 1.4959264257509872,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004782817611903102,
|
|
"loss": 5.8884,
|
|
"mean_token_accuracy": 0.16413553506135942,
|
|
"num_tokens": 29270192.0,
|
|
"step": 14965
|
|
},
|
|
{
|
|
"entropy": 6.177013301849366,
|
|
"epoch": 1.4964262508122157,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00047826646079044826,
|
|
"loss": 5.9925,
|
|
"mean_token_accuracy": 0.15769227743148803,
|
|
"num_tokens": 29281413.0,
|
|
"step": 14970
|
|
},
|
|
{
|
|
"entropy": 6.214835739135742,
|
|
"epoch": 1.4969260758734442,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00047825115527645447,
|
|
"loss": 5.9375,
|
|
"mean_token_accuracy": 0.16006978526711463,
|
|
"num_tokens": 29291959.0,
|
|
"step": 14975
|
|
},
|
|
{
|
|
"entropy": 6.159595537185669,
|
|
"epoch": 1.4974259009346729,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004782358446487139,
|
|
"loss": 5.9376,
|
|
"mean_token_accuracy": 0.1653369426727295,
|
|
"num_tokens": 29302577.0,
|
|
"step": 14980
|
|
},
|
|
{
|
|
"entropy": 6.090263938903808,
|
|
"epoch": 1.4979257259959016,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00047822052890761173,
|
|
"loss": 5.8455,
|
|
"mean_token_accuracy": 0.16826079934835433,
|
|
"num_tokens": 29312437.0,
|
|
"step": 14985
|
|
},
|
|
{
|
|
"entropy": 6.018375253677368,
|
|
"epoch": 1.49842555105713,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004782052080535334,
|
|
"loss": 5.8087,
|
|
"mean_token_accuracy": 0.16640501022338866,
|
|
"num_tokens": 29321777.0,
|
|
"step": 14990
|
|
},
|
|
{
|
|
"entropy": 6.174808120727539,
|
|
"epoch": 1.4989253761183585,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004781898820868644,
|
|
"loss": 5.8705,
|
|
"mean_token_accuracy": 0.16114144772291183,
|
|
"num_tokens": 29330551.0,
|
|
"step": 14995
|
|
},
|
|
{
|
|
"entropy": 6.155779838562012,
|
|
"epoch": 1.4994252011795872,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004781745510079901,
|
|
"loss": 5.8858,
|
|
"mean_token_accuracy": 0.15882690846920014,
|
|
"num_tokens": 29340110.0,
|
|
"step": 15000
|
|
},
|
|
{
|
|
"epoch": 1.4994252011795872,
|
|
"eval_entropy": 5.969068961916311,
|
|
"eval_loss": 5.9901204109191895,
|
|
"eval_mean_token_accuracy": 0.16268406624655476,
|
|
"eval_num_tokens": 29340110.0,
|
|
"eval_runtime": 23.8708,
|
|
"eval_samples_per_second": 1300.543,
|
|
"eval_steps_per_second": 162.584,
|
|
"step": 15000
|
|
},
|
|
{
|
|
"entropy": 6.136759567260742,
|
|
"epoch": 1.4999250262408157,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00047815921481729647,
|
|
"loss": 5.9589,
|
|
"mean_token_accuracy": 0.1545475646853447,
|
|
"num_tokens": 29348935.0,
|
|
"step": 15005
|
|
},
|
|
{
|
|
"entropy": 6.1694427013397215,
|
|
"epoch": 1.5004248513020442,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004781438735151693,
|
|
"loss": 5.9873,
|
|
"mean_token_accuracy": 0.1474507212638855,
|
|
"num_tokens": 29359108.0,
|
|
"step": 15010
|
|
},
|
|
{
|
|
"entropy": 6.155844497680664,
|
|
"epoch": 1.5009246763632729,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.00047812852710199446,
|
|
"loss": 5.8629,
|
|
"mean_token_accuracy": 0.17175030708312988,
|
|
"num_tokens": 29369074.0,
|
|
"step": 15015
|
|
},
|
|
{
|
|
"entropy": 6.116925764083862,
|
|
"epoch": 1.5014245014245016,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004781131755781582,
|
|
"loss": 5.9026,
|
|
"mean_token_accuracy": 0.14713370203971862,
|
|
"num_tokens": 29379138.0,
|
|
"step": 15020
|
|
},
|
|
{
|
|
"entropy": 6.125406885147095,
|
|
"epoch": 1.50192432648573,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004780978189440467,
|
|
"loss": 5.9195,
|
|
"mean_token_accuracy": 0.15533546209335328,
|
|
"num_tokens": 29389124.0,
|
|
"step": 15025
|
|
},
|
|
{
|
|
"entropy": 6.08275671005249,
|
|
"epoch": 1.5024241515469585,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00047808245720004633,
|
|
"loss": 5.791,
|
|
"mean_token_accuracy": 0.17125678062438965,
|
|
"num_tokens": 29398179.0,
|
|
"step": 15030
|
|
},
|
|
{
|
|
"entropy": 6.158256149291992,
|
|
"epoch": 1.5029239766081872,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00047806709034654355,
|
|
"loss": 5.8612,
|
|
"mean_token_accuracy": 0.15952516198158265,
|
|
"num_tokens": 29408177.0,
|
|
"step": 15035
|
|
},
|
|
{
|
|
"entropy": 6.1401965618133545,
|
|
"epoch": 1.5034238016694157,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004780517183839251,
|
|
"loss": 5.9062,
|
|
"mean_token_accuracy": 0.15829854160547258,
|
|
"num_tokens": 29418699.0,
|
|
"step": 15040
|
|
},
|
|
{
|
|
"entropy": 6.11042857170105,
|
|
"epoch": 1.5039236267306442,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004780363413125777,
|
|
"loss": 5.9532,
|
|
"mean_token_accuracy": 0.16332702040672303,
|
|
"num_tokens": 29429271.0,
|
|
"step": 15045
|
|
},
|
|
{
|
|
"entropy": 6.222468280792237,
|
|
"epoch": 1.5044234517918729,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00047802095913288814,
|
|
"loss": 6.0609,
|
|
"mean_token_accuracy": 0.15482898354530333,
|
|
"num_tokens": 29439004.0,
|
|
"step": 15050
|
|
},
|
|
{
|
|
"entropy": 6.212536144256592,
|
|
"epoch": 1.5049232768531016,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00047800557184524345,
|
|
"loss": 6.0066,
|
|
"mean_token_accuracy": 0.1551068164408207,
|
|
"num_tokens": 29449359.0,
|
|
"step": 15055
|
|
},
|
|
{
|
|
"entropy": 6.163725566864014,
|
|
"epoch": 1.5054231019143298,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004779901794500308,
|
|
"loss": 5.9846,
|
|
"mean_token_accuracy": 0.1515995517373085,
|
|
"num_tokens": 29459277.0,
|
|
"step": 15060
|
|
},
|
|
{
|
|
"entropy": 6.151822710037232,
|
|
"epoch": 1.5059229269755585,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00047797478194763754,
|
|
"loss": 5.9079,
|
|
"mean_token_accuracy": 0.15930714681744576,
|
|
"num_tokens": 29468676.0,
|
|
"step": 15065
|
|
},
|
|
{
|
|
"entropy": 6.190333271026612,
|
|
"epoch": 1.5064227520367872,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.00047795937933845103,
|
|
"loss": 5.9837,
|
|
"mean_token_accuracy": 0.15031797289848328,
|
|
"num_tokens": 29478343.0,
|
|
"step": 15070
|
|
},
|
|
{
|
|
"entropy": 6.194295978546142,
|
|
"epoch": 1.5069225770980157,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004779439716228587,
|
|
"loss": 5.8796,
|
|
"mean_token_accuracy": 0.15300556197762488,
|
|
"num_tokens": 29488434.0,
|
|
"step": 15075
|
|
},
|
|
{
|
|
"entropy": 6.120421552658081,
|
|
"epoch": 1.5074224021592442,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004779285588012482,
|
|
"loss": 5.8355,
|
|
"mean_token_accuracy": 0.16310104876756668,
|
|
"num_tokens": 29498303.0,
|
|
"step": 15080
|
|
},
|
|
{
|
|
"entropy": 6.135522127151489,
|
|
"epoch": 1.5079222272204729,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00047791314087400745,
|
|
"loss": 5.9743,
|
|
"mean_token_accuracy": 0.15061080157756807,
|
|
"num_tokens": 29508597.0,
|
|
"step": 15085
|
|
},
|
|
{
|
|
"entropy": 6.112280464172363,
|
|
"epoch": 1.5084220522817016,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004778977178415243,
|
|
"loss": 5.859,
|
|
"mean_token_accuracy": 0.169554241001606,
|
|
"num_tokens": 29517640.0,
|
|
"step": 15090
|
|
},
|
|
{
|
|
"entropy": 6.188988971710205,
|
|
"epoch": 1.5089218773429298,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004778822897041868,
|
|
"loss": 5.9274,
|
|
"mean_token_accuracy": 0.15721369832754134,
|
|
"num_tokens": 29527415.0,
|
|
"step": 15095
|
|
},
|
|
{
|
|
"entropy": 6.209465456008911,
|
|
"epoch": 1.5094217024041585,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.000477866856462383,
|
|
"loss": 5.8605,
|
|
"mean_token_accuracy": 0.15844809412956237,
|
|
"num_tokens": 29537296.0,
|
|
"step": 15100
|
|
},
|
|
{
|
|
"entropy": 6.197969102859497,
|
|
"epoch": 1.5099215274653872,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004778514181165014,
|
|
"loss": 5.9588,
|
|
"mean_token_accuracy": 0.15580889582633972,
|
|
"num_tokens": 29546709.0,
|
|
"step": 15105
|
|
},
|
|
{
|
|
"entropy": 6.186705923080444,
|
|
"epoch": 1.5104213525266157,
|
|
"grad_norm": 1.8984375,
|
|
"learning_rate": 0.00047783597466693025,
|
|
"loss": 5.9633,
|
|
"mean_token_accuracy": 0.14912043362855912,
|
|
"num_tokens": 29556627.0,
|
|
"step": 15110
|
|
},
|
|
{
|
|
"entropy": 6.220252609252929,
|
|
"epoch": 1.5109211775878442,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004778205261140582,
|
|
"loss": 5.926,
|
|
"mean_token_accuracy": 0.15555409342050552,
|
|
"num_tokens": 29566381.0,
|
|
"step": 15115
|
|
},
|
|
{
|
|
"entropy": 6.15552773475647,
|
|
"epoch": 1.5114210026490729,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004778050724582739,
|
|
"loss": 5.9514,
|
|
"mean_token_accuracy": 0.15807626098394395,
|
|
"num_tokens": 29575634.0,
|
|
"step": 15120
|
|
},
|
|
{
|
|
"entropy": 6.0975908756256105,
|
|
"epoch": 1.5119208277103013,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.00047778961369996623,
|
|
"loss": 5.8829,
|
|
"mean_token_accuracy": 0.16284081786870958,
|
|
"num_tokens": 29586103.0,
|
|
"step": 15125
|
|
},
|
|
{
|
|
"entropy": 6.158964395523071,
|
|
"epoch": 1.5124206527715298,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000477774149839524,
|
|
"loss": 5.8585,
|
|
"mean_token_accuracy": 0.16471410542726517,
|
|
"num_tokens": 29596764.0,
|
|
"step": 15130
|
|
},
|
|
{
|
|
"entropy": 6.153457593917847,
|
|
"epoch": 1.5129204778327585,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00047775868087733634,
|
|
"loss": 5.8687,
|
|
"mean_token_accuracy": 0.15700220316648483,
|
|
"num_tokens": 29606642.0,
|
|
"step": 15135
|
|
},
|
|
{
|
|
"entropy": 6.119776487350464,
|
|
"epoch": 1.5134203028939872,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00047774320681379237,
|
|
"loss": 5.9441,
|
|
"mean_token_accuracy": 0.15507982820272445,
|
|
"num_tokens": 29616583.0,
|
|
"step": 15140
|
|
},
|
|
{
|
|
"entropy": 6.067386531829834,
|
|
"epoch": 1.5139201279552157,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004777277276492816,
|
|
"loss": 5.8794,
|
|
"mean_token_accuracy": 0.1614138051867485,
|
|
"num_tokens": 29625961.0,
|
|
"step": 15145
|
|
},
|
|
{
|
|
"entropy": 6.19804801940918,
|
|
"epoch": 1.5144199530164442,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00047771224338419326,
|
|
"loss": 5.8563,
|
|
"mean_token_accuracy": 0.1565035417675972,
|
|
"num_tokens": 29636089.0,
|
|
"step": 15150
|
|
},
|
|
{
|
|
"entropy": 6.150305318832397,
|
|
"epoch": 1.5149197780776729,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004776967540189171,
|
|
"loss": 5.8817,
|
|
"mean_token_accuracy": 0.16364790499210358,
|
|
"num_tokens": 29646068.0,
|
|
"step": 15155
|
|
},
|
|
{
|
|
"entropy": 6.071046972274781,
|
|
"epoch": 1.5154196031389013,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004776812595538428,
|
|
"loss": 5.838,
|
|
"mean_token_accuracy": 0.16742997318506242,
|
|
"num_tokens": 29655248.0,
|
|
"step": 15160
|
|
},
|
|
{
|
|
"entropy": 6.117970705032349,
|
|
"epoch": 1.5159194282001298,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00047766575998936013,
|
|
"loss": 5.9373,
|
|
"mean_token_accuracy": 0.15023559853434562,
|
|
"num_tokens": 29665073.0,
|
|
"step": 15165
|
|
},
|
|
{
|
|
"entropy": 6.197440958023071,
|
|
"epoch": 1.5164192532613585,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00047765025532585907,
|
|
"loss": 5.948,
|
|
"mean_token_accuracy": 0.15950971692800522,
|
|
"num_tokens": 29674714.0,
|
|
"step": 15170
|
|
},
|
|
{
|
|
"entropy": 6.190606117248535,
|
|
"epoch": 1.5169190783225872,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004776347455637298,
|
|
"loss": 5.9363,
|
|
"mean_token_accuracy": 0.16096141040325165,
|
|
"num_tokens": 29683658.0,
|
|
"step": 15175
|
|
},
|
|
{
|
|
"entropy": 6.089086961746216,
|
|
"epoch": 1.5174189033838157,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004776192307033624,
|
|
"loss": 5.8169,
|
|
"mean_token_accuracy": 0.1700205460190773,
|
|
"num_tokens": 29693089.0,
|
|
"step": 15180
|
|
},
|
|
{
|
|
"entropy": 6.169860601425171,
|
|
"epoch": 1.5179187284450442,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004776037107451473,
|
|
"loss": 5.8853,
|
|
"mean_token_accuracy": 0.16439483165740967,
|
|
"num_tokens": 29702727.0,
|
|
"step": 15185
|
|
},
|
|
{
|
|
"entropy": 6.1305726051330565,
|
|
"epoch": 1.5184185535062729,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.000477588185689475,
|
|
"loss": 5.9308,
|
|
"mean_token_accuracy": 0.16092125773429872,
|
|
"num_tokens": 29713882.0,
|
|
"step": 15190
|
|
},
|
|
{
|
|
"entropy": 6.0984578132629395,
|
|
"epoch": 1.5189183785675013,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00047757265553673606,
|
|
"loss": 5.7868,
|
|
"mean_token_accuracy": 0.17264163494110107,
|
|
"num_tokens": 29722792.0,
|
|
"step": 15195
|
|
},
|
|
{
|
|
"entropy": 6.127743816375732,
|
|
"epoch": 1.5194182036287298,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00047755712028732126,
|
|
"loss": 5.9729,
|
|
"mean_token_accuracy": 0.1568317450582981,
|
|
"num_tokens": 29734246.0,
|
|
"step": 15200
|
|
},
|
|
{
|
|
"entropy": 6.293207502365112,
|
|
"epoch": 1.5199180286899585,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004775415799416214,
|
|
"loss": 5.9807,
|
|
"mean_token_accuracy": 0.15994197130203247,
|
|
"num_tokens": 29743747.0,
|
|
"step": 15205
|
|
},
|
|
{
|
|
"entropy": 6.1655213832855225,
|
|
"epoch": 1.5204178537511872,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004775260345000275,
|
|
"loss": 5.8287,
|
|
"mean_token_accuracy": 0.1625361904501915,
|
|
"num_tokens": 29754136.0,
|
|
"step": 15210
|
|
},
|
|
{
|
|
"entropy": 6.06421685218811,
|
|
"epoch": 1.5209176788124157,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00047751048396293077,
|
|
"loss": 5.7872,
|
|
"mean_token_accuracy": 0.16893598884344102,
|
|
"num_tokens": 29763802.0,
|
|
"step": 15215
|
|
},
|
|
{
|
|
"entropy": 6.041688394546509,
|
|
"epoch": 1.5214175038736442,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00047749492833072226,
|
|
"loss": 5.8142,
|
|
"mean_token_accuracy": 0.157342828810215,
|
|
"num_tokens": 29773376.0,
|
|
"step": 15220
|
|
},
|
|
{
|
|
"entropy": 6.132526111602783,
|
|
"epoch": 1.5219173289348729,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00047747936760379354,
|
|
"loss": 5.8995,
|
|
"mean_token_accuracy": 0.16234552711248398,
|
|
"num_tokens": 29784407.0,
|
|
"step": 15225
|
|
},
|
|
{
|
|
"entropy": 6.145341539382935,
|
|
"epoch": 1.5224171539961013,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.000477463801782536,
|
|
"loss": 5.8678,
|
|
"mean_token_accuracy": 0.15537516698241233,
|
|
"num_tokens": 29794745.0,
|
|
"step": 15230
|
|
},
|
|
{
|
|
"entropy": 6.1384529113769535,
|
|
"epoch": 1.5229169790573298,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00047744823086734136,
|
|
"loss": 5.8573,
|
|
"mean_token_accuracy": 0.15867346078157424,
|
|
"num_tokens": 29804393.0,
|
|
"step": 15235
|
|
},
|
|
{
|
|
"entropy": 6.1012818813323975,
|
|
"epoch": 1.5234168041185585,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00047743265485860123,
|
|
"loss": 5.8416,
|
|
"mean_token_accuracy": 0.1608274683356285,
|
|
"num_tokens": 29814306.0,
|
|
"step": 15240
|
|
},
|
|
{
|
|
"entropy": 6.17518720626831,
|
|
"epoch": 1.5239166291797872,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00047741707375670766,
|
|
"loss": 5.8899,
|
|
"mean_token_accuracy": 0.1588516876101494,
|
|
"num_tokens": 29823730.0,
|
|
"step": 15245
|
|
},
|
|
{
|
|
"entropy": 6.14407172203064,
|
|
"epoch": 1.5244164542410157,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004774014875620526,
|
|
"loss": 5.8686,
|
|
"mean_token_accuracy": 0.15934555977582932,
|
|
"num_tokens": 29833901.0,
|
|
"step": 15250
|
|
},
|
|
{
|
|
"entropy": 6.098142433166504,
|
|
"epoch": 1.5249162793022442,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00047738589627502814,
|
|
"loss": 5.8196,
|
|
"mean_token_accuracy": 0.17014452815055847,
|
|
"num_tokens": 29843874.0,
|
|
"step": 15255
|
|
},
|
|
{
|
|
"entropy": 6.143678855895996,
|
|
"epoch": 1.5254161043634729,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.00047737029989602665,
|
|
"loss": 5.8578,
|
|
"mean_token_accuracy": 0.1587330222129822,
|
|
"num_tokens": 29853031.0,
|
|
"step": 15260
|
|
},
|
|
{
|
|
"entropy": 6.098814392089844,
|
|
"epoch": 1.5259159294247013,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004773546984254405,
|
|
"loss": 5.9006,
|
|
"mean_token_accuracy": 0.1571081519126892,
|
|
"num_tokens": 29862437.0,
|
|
"step": 15265
|
|
},
|
|
{
|
|
"entropy": 6.051092958450317,
|
|
"epoch": 1.5264157544859298,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004773390918636622,
|
|
"loss": 5.8133,
|
|
"mean_token_accuracy": 0.1645175188779831,
|
|
"num_tokens": 29870914.0,
|
|
"step": 15270
|
|
},
|
|
{
|
|
"entropy": 6.107993698120117,
|
|
"epoch": 1.5269155795471585,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004773234802110844,
|
|
"loss": 5.8412,
|
|
"mean_token_accuracy": 0.16391278356313704,
|
|
"num_tokens": 29880745.0,
|
|
"step": 15275
|
|
},
|
|
{
|
|
"entropy": 6.195461988449097,
|
|
"epoch": 1.5274154046083872,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004773078634681,
|
|
"loss": 6.0267,
|
|
"mean_token_accuracy": 0.15176126584410668,
|
|
"num_tokens": 29890049.0,
|
|
"step": 15280
|
|
},
|
|
{
|
|
"entropy": 6.271877479553223,
|
|
"epoch": 1.5279152296696157,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00047729224163510167,
|
|
"loss": 6.0177,
|
|
"mean_token_accuracy": 0.15353228598833085,
|
|
"num_tokens": 29899664.0,
|
|
"step": 15285
|
|
},
|
|
{
|
|
"entropy": 6.16676082611084,
|
|
"epoch": 1.5284150547308442,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.00047727661471248263,
|
|
"loss": 5.8847,
|
|
"mean_token_accuracy": 0.16869666203856468,
|
|
"num_tokens": 29909261.0,
|
|
"step": 15290
|
|
},
|
|
{
|
|
"entropy": 6.118931674957276,
|
|
"epoch": 1.5289148797920729,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.000477260982700636,
|
|
"loss": 5.7521,
|
|
"mean_token_accuracy": 0.16772303879261016,
|
|
"num_tokens": 29920137.0,
|
|
"step": 15295
|
|
},
|
|
{
|
|
"entropy": 6.131432580947876,
|
|
"epoch": 1.5294147048533013,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004772453455999552,
|
|
"loss": 5.9367,
|
|
"mean_token_accuracy": 0.15772649943828582,
|
|
"num_tokens": 29930708.0,
|
|
"step": 15300
|
|
},
|
|
{
|
|
"entropy": 6.138315057754516,
|
|
"epoch": 1.5299145299145298,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004772297034108334,
|
|
"loss": 6.0102,
|
|
"mean_token_accuracy": 0.15555102229118348,
|
|
"num_tokens": 29940804.0,
|
|
"step": 15305
|
|
},
|
|
{
|
|
"entropy": 6.088601922988891,
|
|
"epoch": 1.5304143549757585,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00047721405613366434,
|
|
"loss": 5.8207,
|
|
"mean_token_accuracy": 0.16179277896881103,
|
|
"num_tokens": 29951609.0,
|
|
"step": 15310
|
|
},
|
|
{
|
|
"entropy": 6.227131271362305,
|
|
"epoch": 1.5309141800369872,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00047719840376884173,
|
|
"loss": 5.9768,
|
|
"mean_token_accuracy": 0.16435107588768005,
|
|
"num_tokens": 29961764.0,
|
|
"step": 15315
|
|
},
|
|
{
|
|
"entropy": 6.128134107589721,
|
|
"epoch": 1.5314140050982155,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004771827463167593,
|
|
"loss": 5.8996,
|
|
"mean_token_accuracy": 0.1534770041704178,
|
|
"num_tokens": 29972160.0,
|
|
"step": 15320
|
|
},
|
|
{
|
|
"entropy": 6.084901809692383,
|
|
"epoch": 1.5319138301594442,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004771670837778109,
|
|
"loss": 5.8095,
|
|
"mean_token_accuracy": 0.16341745853424072,
|
|
"num_tokens": 29982190.0,
|
|
"step": 15325
|
|
},
|
|
{
|
|
"entropy": 6.184044551849365,
|
|
"epoch": 1.5324136552206729,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.00047715141615239075,
|
|
"loss": 5.9234,
|
|
"mean_token_accuracy": 0.16050842702388762,
|
|
"num_tokens": 29992020.0,
|
|
"step": 15330
|
|
},
|
|
{
|
|
"entropy": 6.1740881443023685,
|
|
"epoch": 1.5329134802819013,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00047713574344089305,
|
|
"loss": 5.9493,
|
|
"mean_token_accuracy": 0.15685709416866303,
|
|
"num_tokens": 30002585.0,
|
|
"step": 15335
|
|
},
|
|
{
|
|
"entropy": 6.136387157440185,
|
|
"epoch": 1.5334133053431298,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.000477120065643712,
|
|
"loss": 5.9106,
|
|
"mean_token_accuracy": 0.15703713297843933,
|
|
"num_tokens": 30012210.0,
|
|
"step": 15340
|
|
},
|
|
{
|
|
"entropy": 6.179438781738281,
|
|
"epoch": 1.5339131304043585,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004771043827612421,
|
|
"loss": 5.9805,
|
|
"mean_token_accuracy": 0.15978062599897386,
|
|
"num_tokens": 30022339.0,
|
|
"step": 15345
|
|
},
|
|
{
|
|
"entropy": 6.106447029113769,
|
|
"epoch": 1.5344129554655872,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00047708869479387795,
|
|
"loss": 5.8581,
|
|
"mean_token_accuracy": 0.16432844549417497,
|
|
"num_tokens": 30032313.0,
|
|
"step": 15350
|
|
},
|
|
{
|
|
"entropy": 6.11654314994812,
|
|
"epoch": 1.5349127805268155,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004770730017420143,
|
|
"loss": 5.8515,
|
|
"mean_token_accuracy": 0.16480098515748978,
|
|
"num_tokens": 30041840.0,
|
|
"step": 15355
|
|
},
|
|
{
|
|
"entropy": 6.078329801559448,
|
|
"epoch": 1.5354126055880442,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004770573036060458,
|
|
"loss": 5.8162,
|
|
"mean_token_accuracy": 0.16789164394140244,
|
|
"num_tokens": 30052118.0,
|
|
"step": 15360
|
|
},
|
|
{
|
|
"entropy": 6.194440507888794,
|
|
"epoch": 1.5359124306492729,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004770416003863676,
|
|
"loss": 5.9919,
|
|
"mean_token_accuracy": 0.15537165254354476,
|
|
"num_tokens": 30062352.0,
|
|
"step": 15365
|
|
},
|
|
{
|
|
"entropy": 6.16536955833435,
|
|
"epoch": 1.5364122557105013,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004770258920833748,
|
|
"loss": 5.9621,
|
|
"mean_token_accuracy": 0.15180836692452432,
|
|
"num_tokens": 30072657.0,
|
|
"step": 15370
|
|
},
|
|
{
|
|
"entropy": 6.133648920059204,
|
|
"epoch": 1.5369120807717298,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.00047701017869746236,
|
|
"loss": 5.9192,
|
|
"mean_token_accuracy": 0.15897963792085648,
|
|
"num_tokens": 30082759.0,
|
|
"step": 15375
|
|
},
|
|
{
|
|
"entropy": 6.172386121749878,
|
|
"epoch": 1.5374119058329585,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00047699446022902596,
|
|
"loss": 6.0099,
|
|
"mean_token_accuracy": 0.15272779539227485,
|
|
"num_tokens": 30092762.0,
|
|
"step": 15380
|
|
},
|
|
{
|
|
"entropy": 6.164754009246826,
|
|
"epoch": 1.537911730894187,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.00047697873667846094,
|
|
"loss": 5.8878,
|
|
"mean_token_accuracy": 0.15395362675189972,
|
|
"num_tokens": 30101492.0,
|
|
"step": 15385
|
|
},
|
|
{
|
|
"entropy": 6.2284934520721436,
|
|
"epoch": 1.5384115559554155,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00047696300804616276,
|
|
"loss": 5.9068,
|
|
"mean_token_accuracy": 0.1619730770587921,
|
|
"num_tokens": 30111136.0,
|
|
"step": 15390
|
|
},
|
|
{
|
|
"entropy": 6.153344678878784,
|
|
"epoch": 1.5389113810166442,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004769472743325273,
|
|
"loss": 5.9322,
|
|
"mean_token_accuracy": 0.16065984070301056,
|
|
"num_tokens": 30120804.0,
|
|
"step": 15395
|
|
},
|
|
{
|
|
"entropy": 6.20813512802124,
|
|
"epoch": 1.5394112060778729,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00047693153553795046,
|
|
"loss": 5.9483,
|
|
"mean_token_accuracy": 0.1560834527015686,
|
|
"num_tokens": 30130976.0,
|
|
"step": 15400
|
|
},
|
|
{
|
|
"entropy": 6.137753343582153,
|
|
"epoch": 1.5399110311391013,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004769157916628281,
|
|
"loss": 5.8742,
|
|
"mean_token_accuracy": 0.1624482661485672,
|
|
"num_tokens": 30140060.0,
|
|
"step": 15405
|
|
},
|
|
{
|
|
"entropy": 6.1509441375732425,
|
|
"epoch": 1.5404108562003298,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00047690004270755634,
|
|
"loss": 5.9368,
|
|
"mean_token_accuracy": 0.1568168044090271,
|
|
"num_tokens": 30150474.0,
|
|
"step": 15410
|
|
},
|
|
{
|
|
"entropy": 6.185036277770996,
|
|
"epoch": 1.5409106812615585,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004768842886725314,
|
|
"loss": 5.9424,
|
|
"mean_token_accuracy": 0.15672353953123092,
|
|
"num_tokens": 30159529.0,
|
|
"step": 15415
|
|
},
|
|
{
|
|
"entropy": 6.158765602111816,
|
|
"epoch": 1.541410506322787,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00047686852955814986,
|
|
"loss": 6.0631,
|
|
"mean_token_accuracy": 0.1555615782737732,
|
|
"num_tokens": 30169352.0,
|
|
"step": 15420
|
|
},
|
|
{
|
|
"entropy": 6.135985565185547,
|
|
"epoch": 1.5419103313840155,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.000476852765364808,
|
|
"loss": 5.8281,
|
|
"mean_token_accuracy": 0.16499021351337434,
|
|
"num_tokens": 30178190.0,
|
|
"step": 15425
|
|
},
|
|
{
|
|
"entropy": 6.070001888275146,
|
|
"epoch": 1.5424101564452442,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004768369960929025,
|
|
"loss": 5.8128,
|
|
"mean_token_accuracy": 0.16403407156467437,
|
|
"num_tokens": 30187878.0,
|
|
"step": 15430
|
|
},
|
|
{
|
|
"entropy": 6.108920955657959,
|
|
"epoch": 1.5429099815064728,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004768212217428301,
|
|
"loss": 5.9128,
|
|
"mean_token_accuracy": 0.15988751947879792,
|
|
"num_tokens": 30197786.0,
|
|
"step": 15435
|
|
},
|
|
{
|
|
"entropy": 6.189189434051514,
|
|
"epoch": 1.5434098065677013,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00047680544231498766,
|
|
"loss": 5.9148,
|
|
"mean_token_accuracy": 0.16264031529426576,
|
|
"num_tokens": 30207837.0,
|
|
"step": 15440
|
|
},
|
|
{
|
|
"entropy": 6.080624198913574,
|
|
"epoch": 1.5439096316289298,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004767896578097723,
|
|
"loss": 5.8654,
|
|
"mean_token_accuracy": 0.16577401608228684,
|
|
"num_tokens": 30217135.0,
|
|
"step": 15445
|
|
},
|
|
{
|
|
"entropy": 6.026799154281616,
|
|
"epoch": 1.5444094566901585,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004767738682275811,
|
|
"loss": 5.848,
|
|
"mean_token_accuracy": 0.1592901200056076,
|
|
"num_tokens": 30227339.0,
|
|
"step": 15450
|
|
},
|
|
{
|
|
"entropy": 6.217907476425171,
|
|
"epoch": 1.544909281751387,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004767580735688112,
|
|
"loss": 6.0234,
|
|
"mean_token_accuracy": 0.15032312870025635,
|
|
"num_tokens": 30235735.0,
|
|
"step": 15455
|
|
},
|
|
{
|
|
"entropy": 6.148895120620727,
|
|
"epoch": 1.5454091068126155,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004767422738338601,
|
|
"loss": 5.8368,
|
|
"mean_token_accuracy": 0.16673685014247894,
|
|
"num_tokens": 30245921.0,
|
|
"step": 15460
|
|
},
|
|
{
|
|
"entropy": 6.0757598876953125,
|
|
"epoch": 1.5459089318738441,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004767264690231253,
|
|
"loss": 5.8337,
|
|
"mean_token_accuracy": 0.16876982003450394,
|
|
"num_tokens": 30256047.0,
|
|
"step": 15465
|
|
},
|
|
{
|
|
"entropy": 6.08550910949707,
|
|
"epoch": 1.5464087569350728,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004767106591370045,
|
|
"loss": 5.8694,
|
|
"mean_token_accuracy": 0.16294163167476655,
|
|
"num_tokens": 30266460.0,
|
|
"step": 15470
|
|
},
|
|
{
|
|
"entropy": 6.144644641876221,
|
|
"epoch": 1.5469085819963013,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.00047669484417589537,
|
|
"loss": 5.873,
|
|
"mean_token_accuracy": 0.16082055121660233,
|
|
"num_tokens": 30275937.0,
|
|
"step": 15475
|
|
},
|
|
{
|
|
"entropy": 6.184883975982666,
|
|
"epoch": 1.5474084070575298,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00047667902414019585,
|
|
"loss": 5.8217,
|
|
"mean_token_accuracy": 0.16800087243318557,
|
|
"num_tokens": 30285608.0,
|
|
"step": 15480
|
|
},
|
|
{
|
|
"entropy": 6.037270259857178,
|
|
"epoch": 1.5479082321187585,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.000476663199030304,
|
|
"loss": 5.853,
|
|
"mean_token_accuracy": 0.16526937931776048,
|
|
"num_tokens": 30295071.0,
|
|
"step": 15485
|
|
},
|
|
{
|
|
"entropy": 5.952275800704956,
|
|
"epoch": 1.548408057179987,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00047664736884661804,
|
|
"loss": 5.8508,
|
|
"mean_token_accuracy": 0.16396021693944932,
|
|
"num_tokens": 30305878.0,
|
|
"step": 15490
|
|
},
|
|
{
|
|
"entropy": 6.212483263015747,
|
|
"epoch": 1.5489078822412155,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00047663153358953604,
|
|
"loss": 5.9522,
|
|
"mean_token_accuracy": 0.16168071031570436,
|
|
"num_tokens": 30316544.0,
|
|
"step": 15495
|
|
},
|
|
{
|
|
"entropy": 6.234240531921387,
|
|
"epoch": 1.5494077073024441,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004766156932594566,
|
|
"loss": 5.8539,
|
|
"mean_token_accuracy": 0.1589973583817482,
|
|
"num_tokens": 30325819.0,
|
|
"step": 15500
|
|
},
|
|
{
|
|
"entropy": 6.113700723648071,
|
|
"epoch": 1.5499075323636728,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00047659984785677824,
|
|
"loss": 5.8208,
|
|
"mean_token_accuracy": 0.16180218607187272,
|
|
"num_tokens": 30335160.0,
|
|
"step": 15505
|
|
},
|
|
{
|
|
"entropy": 6.088001012802124,
|
|
"epoch": 1.5504073574249013,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00047658399738189955,
|
|
"loss": 5.9021,
|
|
"mean_token_accuracy": 0.1632031410932541,
|
|
"num_tokens": 30343412.0,
|
|
"step": 15510
|
|
},
|
|
{
|
|
"entropy": 6.024244260787964,
|
|
"epoch": 1.5509071824861298,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00047656814183521937,
|
|
"loss": 5.8259,
|
|
"mean_token_accuracy": 0.16587333977222443,
|
|
"num_tokens": 30352336.0,
|
|
"step": 15515
|
|
},
|
|
{
|
|
"entropy": 6.163676357269287,
|
|
"epoch": 1.5514070075473585,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004765522812171366,
|
|
"loss": 5.8262,
|
|
"mean_token_accuracy": 0.1605166971683502,
|
|
"num_tokens": 30362476.0,
|
|
"step": 15520
|
|
},
|
|
{
|
|
"entropy": 6.151455879211426,
|
|
"epoch": 1.551906832608587,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00047653641552805023,
|
|
"loss": 5.8935,
|
|
"mean_token_accuracy": 0.16111961305141448,
|
|
"num_tokens": 30372639.0,
|
|
"step": 15525
|
|
},
|
|
{
|
|
"entropy": 6.098763465881348,
|
|
"epoch": 1.5524066576698154,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004765205447683595,
|
|
"loss": 5.7604,
|
|
"mean_token_accuracy": 0.16646797209978104,
|
|
"num_tokens": 30382443.0,
|
|
"step": 15530
|
|
},
|
|
{
|
|
"entropy": 6.097776317596436,
|
|
"epoch": 1.5529064827310441,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004765046689384638,
|
|
"loss": 5.8165,
|
|
"mean_token_accuracy": 0.15879101008176805,
|
|
"num_tokens": 30390969.0,
|
|
"step": 15535
|
|
},
|
|
{
|
|
"entropy": 6.078667497634887,
|
|
"epoch": 1.5534063077922728,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004764887880387625,
|
|
"loss": 5.9042,
|
|
"mean_token_accuracy": 0.15626829117536545,
|
|
"num_tokens": 30401773.0,
|
|
"step": 15540
|
|
},
|
|
{
|
|
"entropy": 6.202826499938965,
|
|
"epoch": 1.5539061328535013,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00047647290206965506,
|
|
"loss": 5.973,
|
|
"mean_token_accuracy": 0.15267098024487497,
|
|
"num_tokens": 30412393.0,
|
|
"step": 15545
|
|
},
|
|
{
|
|
"entropy": 6.16403603553772,
|
|
"epoch": 1.5544059579147298,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00047645701103154125,
|
|
"loss": 5.8849,
|
|
"mean_token_accuracy": 0.157875719666481,
|
|
"num_tokens": 30422274.0,
|
|
"step": 15550
|
|
},
|
|
{
|
|
"entropy": 6.173828411102295,
|
|
"epoch": 1.5549057829759585,
|
|
"grad_norm": 2.8125,
|
|
"learning_rate": 0.00047644111492482094,
|
|
"loss": 5.9209,
|
|
"mean_token_accuracy": 0.15894222855567933,
|
|
"num_tokens": 30432345.0,
|
|
"step": 15555
|
|
},
|
|
{
|
|
"entropy": 6.1405264377594,
|
|
"epoch": 1.555405608037187,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000476425213749894,
|
|
"loss": 5.78,
|
|
"mean_token_accuracy": 0.16812246292829514,
|
|
"num_tokens": 30443016.0,
|
|
"step": 15560
|
|
},
|
|
{
|
|
"entropy": 6.041651058197021,
|
|
"epoch": 1.5559054330984154,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004764093075071605,
|
|
"loss": 5.741,
|
|
"mean_token_accuracy": 0.16955182254314421,
|
|
"num_tokens": 30452392.0,
|
|
"step": 15565
|
|
},
|
|
{
|
|
"entropy": 6.04131064414978,
|
|
"epoch": 1.5564052581596441,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004763933961970206,
|
|
"loss": 5.8578,
|
|
"mean_token_accuracy": 0.16227657049894334,
|
|
"num_tokens": 30461178.0,
|
|
"step": 15570
|
|
},
|
|
{
|
|
"entropy": 6.1343790054321286,
|
|
"epoch": 1.5569050832208728,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004763774798198748,
|
|
"loss": 5.8603,
|
|
"mean_token_accuracy": 0.16114207208156586,
|
|
"num_tokens": 30470616.0,
|
|
"step": 15575
|
|
},
|
|
{
|
|
"entropy": 6.142730283737182,
|
|
"epoch": 1.5574049082821013,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004763615583761234,
|
|
"loss": 5.8334,
|
|
"mean_token_accuracy": 0.1626288890838623,
|
|
"num_tokens": 30479393.0,
|
|
"step": 15580
|
|
},
|
|
{
|
|
"entropy": 6.148135185241699,
|
|
"epoch": 1.5579047333433298,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004763456318661669,
|
|
"loss": 5.8416,
|
|
"mean_token_accuracy": 0.16323017328977585,
|
|
"num_tokens": 30488927.0,
|
|
"step": 15585
|
|
},
|
|
{
|
|
"entropy": 6.054379034042358,
|
|
"epoch": 1.5584045584045585,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004763297002904062,
|
|
"loss": 5.9169,
|
|
"mean_token_accuracy": 0.15800921767950057,
|
|
"num_tokens": 30498973.0,
|
|
"step": 15590
|
|
},
|
|
{
|
|
"entropy": 6.112800741195679,
|
|
"epoch": 1.558904383465787,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00047631376364924195,
|
|
"loss": 5.8338,
|
|
"mean_token_accuracy": 0.16736518889665603,
|
|
"num_tokens": 30508643.0,
|
|
"step": 15595
|
|
},
|
|
{
|
|
"entropy": 6.055330610275268,
|
|
"epoch": 1.5594042085270154,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004762978219430753,
|
|
"loss": 5.7908,
|
|
"mean_token_accuracy": 0.16724276542663574,
|
|
"num_tokens": 30518321.0,
|
|
"step": 15600
|
|
},
|
|
{
|
|
"entropy": 6.119699239730835,
|
|
"epoch": 1.5599040335882441,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004762818751723072,
|
|
"loss": 5.8016,
|
|
"mean_token_accuracy": 0.16162988543510437,
|
|
"num_tokens": 30528127.0,
|
|
"step": 15605
|
|
},
|
|
{
|
|
"entropy": 6.1009547233581545,
|
|
"epoch": 1.5604038586494728,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.00047626592333733895,
|
|
"loss": 5.7484,
|
|
"mean_token_accuracy": 0.17222401052713393,
|
|
"num_tokens": 30538411.0,
|
|
"step": 15610
|
|
},
|
|
{
|
|
"entropy": 6.053055095672607,
|
|
"epoch": 1.560903683710701,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004762499664385719,
|
|
"loss": 5.8894,
|
|
"mean_token_accuracy": 0.1579878196120262,
|
|
"num_tokens": 30548118.0,
|
|
"step": 15615
|
|
},
|
|
{
|
|
"entropy": 6.124635314941406,
|
|
"epoch": 1.5614035087719298,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00047623400447640733,
|
|
"loss": 5.9133,
|
|
"mean_token_accuracy": 0.15761272609233856,
|
|
"num_tokens": 30557920.0,
|
|
"step": 15620
|
|
},
|
|
{
|
|
"entropy": 6.263584756851197,
|
|
"epoch": 1.5619033338331585,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00047621803745124717,
|
|
"loss": 5.9315,
|
|
"mean_token_accuracy": 0.15884170085191726,
|
|
"num_tokens": 30567189.0,
|
|
"step": 15625
|
|
},
|
|
{
|
|
"entropy": 6.151346254348755,
|
|
"epoch": 1.562403158894387,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00047620206536349294,
|
|
"loss": 5.9317,
|
|
"mean_token_accuracy": 0.16056433767080308,
|
|
"num_tokens": 30578208.0,
|
|
"step": 15630
|
|
},
|
|
{
|
|
"entropy": 6.093531799316406,
|
|
"epoch": 1.5629029839556154,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00047618608821354636,
|
|
"loss": 5.8628,
|
|
"mean_token_accuracy": 0.15800632536411285,
|
|
"num_tokens": 30587845.0,
|
|
"step": 15635
|
|
},
|
|
{
|
|
"entropy": 6.148631000518799,
|
|
"epoch": 1.5634028090168441,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004761701060018097,
|
|
"loss": 5.9025,
|
|
"mean_token_accuracy": 0.1599184937775135,
|
|
"num_tokens": 30596601.0,
|
|
"step": 15640
|
|
},
|
|
{
|
|
"entropy": 6.20504412651062,
|
|
"epoch": 1.5639026340780728,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.000476154118728685,
|
|
"loss": 5.9598,
|
|
"mean_token_accuracy": 0.15227677077054977,
|
|
"num_tokens": 30606860.0,
|
|
"step": 15645
|
|
},
|
|
{
|
|
"entropy": 6.106543731689453,
|
|
"epoch": 1.564402459139301,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00047613812639457425,
|
|
"loss": 5.8481,
|
|
"mean_token_accuracy": 0.16099748760461807,
|
|
"num_tokens": 30614980.0,
|
|
"step": 15650
|
|
},
|
|
{
|
|
"entropy": 6.078296041488647,
|
|
"epoch": 1.5649022842005298,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004761221289998801,
|
|
"loss": 5.9434,
|
|
"mean_token_accuracy": 0.16075193881988525,
|
|
"num_tokens": 30625833.0,
|
|
"step": 15655
|
|
},
|
|
{
|
|
"entropy": 6.1446483612060545,
|
|
"epoch": 1.5654021092617585,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004761061265450049,
|
|
"loss": 5.8947,
|
|
"mean_token_accuracy": 0.16505882367491723,
|
|
"num_tokens": 30636052.0,
|
|
"step": 15660
|
|
},
|
|
{
|
|
"entropy": 6.211981582641601,
|
|
"epoch": 1.565901934322987,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00047609011903035136,
|
|
"loss": 5.9089,
|
|
"mean_token_accuracy": 0.1541065126657486,
|
|
"num_tokens": 30646421.0,
|
|
"step": 15665
|
|
},
|
|
{
|
|
"entropy": 6.129273843765259,
|
|
"epoch": 1.5664017593842154,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00047607410645632216,
|
|
"loss": 5.9708,
|
|
"mean_token_accuracy": 0.1589779920876026,
|
|
"num_tokens": 30655903.0,
|
|
"step": 15670
|
|
},
|
|
{
|
|
"entropy": 6.048210716247558,
|
|
"epoch": 1.5669015844454441,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00047605808882332013,
|
|
"loss": 5.7702,
|
|
"mean_token_accuracy": 0.16247298270463945,
|
|
"num_tokens": 30664963.0,
|
|
"step": 15675
|
|
},
|
|
{
|
|
"entropy": 6.169276094436645,
|
|
"epoch": 1.5674014095066726,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004760420661317484,
|
|
"loss": 5.8704,
|
|
"mean_token_accuracy": 0.16183864176273347,
|
|
"num_tokens": 30675182.0,
|
|
"step": 15680
|
|
},
|
|
{
|
|
"entropy": 6.185893154144287,
|
|
"epoch": 1.567901234567901,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004760260383820099,
|
|
"loss": 5.9885,
|
|
"mean_token_accuracy": 0.15695508122444152,
|
|
"num_tokens": 30685267.0,
|
|
"step": 15685
|
|
},
|
|
{
|
|
"entropy": 6.223132753372193,
|
|
"epoch": 1.5684010596291298,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00047601000557450816,
|
|
"loss": 5.9883,
|
|
"mean_token_accuracy": 0.15326895266771318,
|
|
"num_tokens": 30697462.0,
|
|
"step": 15690
|
|
},
|
|
{
|
|
"entropy": 6.1554662704467775,
|
|
"epoch": 1.5689008846903585,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004759939677096463,
|
|
"loss": 5.8151,
|
|
"mean_token_accuracy": 0.16152628064155578,
|
|
"num_tokens": 30706754.0,
|
|
"step": 15695
|
|
},
|
|
{
|
|
"entropy": 6.048240995407104,
|
|
"epoch": 1.569400709751587,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004759779247878279,
|
|
"loss": 5.9025,
|
|
"mean_token_accuracy": 0.15399678349494933,
|
|
"num_tokens": 30717136.0,
|
|
"step": 15700
|
|
},
|
|
{
|
|
"entropy": 6.086741828918457,
|
|
"epoch": 1.5699005348128154,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00047596187680945675,
|
|
"loss": 5.803,
|
|
"mean_token_accuracy": 0.1613622322678566,
|
|
"num_tokens": 30725830.0,
|
|
"step": 15705
|
|
},
|
|
{
|
|
"entropy": 6.226022577285766,
|
|
"epoch": 1.5704003598740441,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004759458237749364,
|
|
"loss": 5.9127,
|
|
"mean_token_accuracy": 0.16303760260343553,
|
|
"num_tokens": 30736494.0,
|
|
"step": 15710
|
|
},
|
|
{
|
|
"entropy": 6.220048999786377,
|
|
"epoch": 1.5709001849352726,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004759297656846708,
|
|
"loss": 5.9,
|
|
"mean_token_accuracy": 0.15465883985161782,
|
|
"num_tokens": 30746006.0,
|
|
"step": 15715
|
|
},
|
|
{
|
|
"entropy": 6.118537044525146,
|
|
"epoch": 1.571400009996501,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.00047591370253906415,
|
|
"loss": 5.8604,
|
|
"mean_token_accuracy": 0.15504343062639236,
|
|
"num_tokens": 30754776.0,
|
|
"step": 15720
|
|
},
|
|
{
|
|
"entropy": 6.003805160522461,
|
|
"epoch": 1.5718998350577298,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00047589763433852027,
|
|
"loss": 5.8477,
|
|
"mean_token_accuracy": 0.16667582839727402,
|
|
"num_tokens": 30764342.0,
|
|
"step": 15725
|
|
},
|
|
{
|
|
"entropy": 6.147149705886841,
|
|
"epoch": 1.5723996601189585,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004758815610834437,
|
|
"loss": 5.8582,
|
|
"mean_token_accuracy": 0.1581901341676712,
|
|
"num_tokens": 30773282.0,
|
|
"step": 15730
|
|
},
|
|
{
|
|
"entropy": 6.177919006347656,
|
|
"epoch": 1.572899485180187,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00047586548277423873,
|
|
"loss": 5.8269,
|
|
"mean_token_accuracy": 0.1640584349632263,
|
|
"num_tokens": 30783407.0,
|
|
"step": 15735
|
|
},
|
|
{
|
|
"entropy": 6.092030048370361,
|
|
"epoch": 1.5733993102414154,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00047584939941130994,
|
|
"loss": 5.8534,
|
|
"mean_token_accuracy": 0.16158094704151155,
|
|
"num_tokens": 30793922.0,
|
|
"step": 15740
|
|
},
|
|
{
|
|
"entropy": 6.072525882720948,
|
|
"epoch": 1.5738991353026441,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004758333109950619,
|
|
"loss": 5.8144,
|
|
"mean_token_accuracy": 0.1618849106132984,
|
|
"num_tokens": 30802721.0,
|
|
"step": 15745
|
|
},
|
|
{
|
|
"entropy": 6.1073509693145756,
|
|
"epoch": 1.5743989603638726,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00047581721752589943,
|
|
"loss": 5.9691,
|
|
"mean_token_accuracy": 0.15507132261991502,
|
|
"num_tokens": 30813229.0,
|
|
"step": 15750
|
|
},
|
|
{
|
|
"entropy": 6.1787354946136475,
|
|
"epoch": 1.574898785425101,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004758011190042274,
|
|
"loss": 5.9205,
|
|
"mean_token_accuracy": 0.1574215590953827,
|
|
"num_tokens": 30822989.0,
|
|
"step": 15755
|
|
},
|
|
{
|
|
"entropy": 6.143587398529053,
|
|
"epoch": 1.5753986104863298,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004757850154304509,
|
|
"loss": 5.9364,
|
|
"mean_token_accuracy": 0.15265523567795752,
|
|
"num_tokens": 30832134.0,
|
|
"step": 15760
|
|
},
|
|
{
|
|
"entropy": 6.169547080993652,
|
|
"epoch": 1.5758984355475585,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004757689068049752,
|
|
"loss": 5.9403,
|
|
"mean_token_accuracy": 0.16043658852577208,
|
|
"num_tokens": 30841528.0,
|
|
"step": 15765
|
|
},
|
|
{
|
|
"entropy": 6.081172370910645,
|
|
"epoch": 1.576398260608787,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.00047575279312820533,
|
|
"loss": 5.8693,
|
|
"mean_token_accuracy": 0.15912111699581147,
|
|
"num_tokens": 30852166.0,
|
|
"step": 15770
|
|
},
|
|
{
|
|
"entropy": 6.171766042709351,
|
|
"epoch": 1.5768980856700154,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004757366744005469,
|
|
"loss": 5.9244,
|
|
"mean_token_accuracy": 0.1573824778199196,
|
|
"num_tokens": 30862188.0,
|
|
"step": 15775
|
|
},
|
|
{
|
|
"entropy": 6.1935049533844,
|
|
"epoch": 1.5773979107312441,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00047572055062240537,
|
|
"loss": 5.9349,
|
|
"mean_token_accuracy": 0.15564235746860505,
|
|
"num_tokens": 30871057.0,
|
|
"step": 15780
|
|
},
|
|
{
|
|
"entropy": 6.16683783531189,
|
|
"epoch": 1.5778977357924726,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004757044217941865,
|
|
"loss": 5.7699,
|
|
"mean_token_accuracy": 0.16504726111888884,
|
|
"num_tokens": 30880884.0,
|
|
"step": 15785
|
|
},
|
|
{
|
|
"entropy": 6.06003041267395,
|
|
"epoch": 1.578397560853701,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00047568828791629605,
|
|
"loss": 5.8574,
|
|
"mean_token_accuracy": 0.15600989162921905,
|
|
"num_tokens": 30891017.0,
|
|
"step": 15790
|
|
},
|
|
{
|
|
"entropy": 6.108499908447266,
|
|
"epoch": 1.5788973859149298,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004756721489891398,
|
|
"loss": 5.8672,
|
|
"mean_token_accuracy": 0.1605653703212738,
|
|
"num_tokens": 30901008.0,
|
|
"step": 15795
|
|
},
|
|
{
|
|
"entropy": 6.17630786895752,
|
|
"epoch": 1.5793972109761585,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004756560050131239,
|
|
"loss": 5.9588,
|
|
"mean_token_accuracy": 0.15656841844320296,
|
|
"num_tokens": 30911266.0,
|
|
"step": 15800
|
|
},
|
|
{
|
|
"entropy": 6.103103733062744,
|
|
"epoch": 1.579897036037387,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00047563985598865466,
|
|
"loss": 5.8463,
|
|
"mean_token_accuracy": 0.16243888288736344,
|
|
"num_tokens": 30921758.0,
|
|
"step": 15805
|
|
},
|
|
{
|
|
"entropy": 6.126082801818848,
|
|
"epoch": 1.5803968610986154,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00047562370191613816,
|
|
"loss": 5.9081,
|
|
"mean_token_accuracy": 0.1579236790537834,
|
|
"num_tokens": 30931446.0,
|
|
"step": 15810
|
|
},
|
|
{
|
|
"entropy": 6.157434463500977,
|
|
"epoch": 1.5808966861598441,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004756075427959811,
|
|
"loss": 6.0207,
|
|
"mean_token_accuracy": 0.15780184268951417,
|
|
"num_tokens": 30942651.0,
|
|
"step": 15815
|
|
},
|
|
{
|
|
"entropy": 6.074296760559082,
|
|
"epoch": 1.5813965112210726,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004755913786285898,
|
|
"loss": 5.7637,
|
|
"mean_token_accuracy": 0.16211674511432647,
|
|
"num_tokens": 30952039.0,
|
|
"step": 15820
|
|
},
|
|
{
|
|
"entropy": 6.101223182678223,
|
|
"epoch": 1.581896336282301,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00047557520941437093,
|
|
"loss": 5.8412,
|
|
"mean_token_accuracy": 0.1625264972448349,
|
|
"num_tokens": 30961834.0,
|
|
"step": 15825
|
|
},
|
|
{
|
|
"entropy": 6.15417103767395,
|
|
"epoch": 1.5823961613435298,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00047555903515373156,
|
|
"loss": 5.9197,
|
|
"mean_token_accuracy": 0.15694278180599214,
|
|
"num_tokens": 30972015.0,
|
|
"step": 15830
|
|
},
|
|
{
|
|
"entropy": 6.078415966033935,
|
|
"epoch": 1.5828959864047585,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00047554285584707834,
|
|
"loss": 5.7942,
|
|
"mean_token_accuracy": 0.16642882525920868,
|
|
"num_tokens": 30982082.0,
|
|
"step": 15835
|
|
},
|
|
{
|
|
"entropy": 6.105426454544068,
|
|
"epoch": 1.583395811465987,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004755266714948186,
|
|
"loss": 5.796,
|
|
"mean_token_accuracy": 0.16809799373149872,
|
|
"num_tokens": 30991273.0,
|
|
"step": 15840
|
|
},
|
|
{
|
|
"entropy": 6.09671630859375,
|
|
"epoch": 1.5838956365272154,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004755104820973593,
|
|
"loss": 5.835,
|
|
"mean_token_accuracy": 0.16358477622270584,
|
|
"num_tokens": 31001062.0,
|
|
"step": 15845
|
|
},
|
|
{
|
|
"entropy": 6.0429517269134525,
|
|
"epoch": 1.5843954615884441,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00047549428765510793,
|
|
"loss": 5.796,
|
|
"mean_token_accuracy": 0.16111780256032943,
|
|
"num_tokens": 31009905.0,
|
|
"step": 15850
|
|
},
|
|
{
|
|
"entropy": 6.0670185565948485,
|
|
"epoch": 1.5848952866496726,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00047547808816847186,
|
|
"loss": 5.9045,
|
|
"mean_token_accuracy": 0.15322913378477096,
|
|
"num_tokens": 31020517.0,
|
|
"step": 15855
|
|
},
|
|
{
|
|
"entropy": 6.170886516571045,
|
|
"epoch": 1.585395111710901,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004754618836378587,
|
|
"loss": 5.8911,
|
|
"mean_token_accuracy": 0.1553575351834297,
|
|
"num_tokens": 31030789.0,
|
|
"step": 15860
|
|
},
|
|
{
|
|
"entropy": 6.155055236816406,
|
|
"epoch": 1.5858949367721298,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004754456740636761,
|
|
"loss": 5.8445,
|
|
"mean_token_accuracy": 0.17112063765525817,
|
|
"num_tokens": 31040459.0,
|
|
"step": 15865
|
|
},
|
|
{
|
|
"entropy": 6.093184232711792,
|
|
"epoch": 1.5863947618333585,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00047542945944633187,
|
|
"loss": 5.8616,
|
|
"mean_token_accuracy": 0.1651126265525818,
|
|
"num_tokens": 31050049.0,
|
|
"step": 15870
|
|
},
|
|
{
|
|
"entropy": 6.040435934066773,
|
|
"epoch": 1.5868945868945867,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00047541323978623405,
|
|
"loss": 5.8639,
|
|
"mean_token_accuracy": 0.16348167955875398,
|
|
"num_tokens": 31058678.0,
|
|
"step": 15875
|
|
},
|
|
{
|
|
"entropy": 6.128684711456299,
|
|
"epoch": 1.5873944119558154,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00047539701508379073,
|
|
"loss": 5.9129,
|
|
"mean_token_accuracy": 0.15773721784353256,
|
|
"num_tokens": 31067878.0,
|
|
"step": 15880
|
|
},
|
|
{
|
|
"entropy": 6.1564939498901365,
|
|
"epoch": 1.5878942370170441,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004753807853394101,
|
|
"loss": 5.8961,
|
|
"mean_token_accuracy": 0.15775365829467775,
|
|
"num_tokens": 31077632.0,
|
|
"step": 15885
|
|
},
|
|
{
|
|
"entropy": 6.138030004501343,
|
|
"epoch": 1.5883940620782726,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00047536455055350034,
|
|
"loss": 5.9488,
|
|
"mean_token_accuracy": 0.15829872861504554,
|
|
"num_tokens": 31087576.0,
|
|
"step": 15890
|
|
},
|
|
{
|
|
"entropy": 6.062282609939575,
|
|
"epoch": 1.588893887139501,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00047534831072647016,
|
|
"loss": 5.8406,
|
|
"mean_token_accuracy": 0.1625261053442955,
|
|
"num_tokens": 31097053.0,
|
|
"step": 15895
|
|
},
|
|
{
|
|
"entropy": 6.08411226272583,
|
|
"epoch": 1.5893937122007298,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00047533206585872805,
|
|
"loss": 5.8588,
|
|
"mean_token_accuracy": 0.1598147064447403,
|
|
"num_tokens": 31106426.0,
|
|
"step": 15900
|
|
},
|
|
{
|
|
"entropy": 6.1566907405853275,
|
|
"epoch": 1.5898935372619585,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004753158159506827,
|
|
"loss": 5.841,
|
|
"mean_token_accuracy": 0.16317206919193267,
|
|
"num_tokens": 31115645.0,
|
|
"step": 15905
|
|
},
|
|
{
|
|
"entropy": 6.097361135482788,
|
|
"epoch": 1.5903933623231867,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004752995610027429,
|
|
"loss": 5.8717,
|
|
"mean_token_accuracy": 0.1649112105369568,
|
|
"num_tokens": 31125275.0,
|
|
"step": 15910
|
|
},
|
|
{
|
|
"entropy": 6.083859014511108,
|
|
"epoch": 1.5908931873844154,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00047528330101531777,
|
|
"loss": 5.8439,
|
|
"mean_token_accuracy": 0.1593996524810791,
|
|
"num_tokens": 31136444.0,
|
|
"step": 15915
|
|
},
|
|
{
|
|
"entropy": 6.06806526184082,
|
|
"epoch": 1.5913930124456441,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00047526703598881623,
|
|
"loss": 5.8507,
|
|
"mean_token_accuracy": 0.16740842461585997,
|
|
"num_tokens": 31145489.0,
|
|
"step": 15920
|
|
},
|
|
{
|
|
"entropy": 6.189351177215576,
|
|
"epoch": 1.5918928375068726,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004752507659236476,
|
|
"loss": 5.9385,
|
|
"mean_token_accuracy": 0.15564728975296022,
|
|
"num_tokens": 31154239.0,
|
|
"step": 15925
|
|
},
|
|
{
|
|
"entropy": 6.137935066223145,
|
|
"epoch": 1.592392662568101,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004752344908202213,
|
|
"loss": 5.8527,
|
|
"mean_token_accuracy": 0.16458972841501235,
|
|
"num_tokens": 31163401.0,
|
|
"step": 15930
|
|
},
|
|
{
|
|
"entropy": 6.052607440948487,
|
|
"epoch": 1.5928924876293298,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004752182106789467,
|
|
"loss": 5.836,
|
|
"mean_token_accuracy": 0.16648358553647996,
|
|
"num_tokens": 31173567.0,
|
|
"step": 15935
|
|
},
|
|
{
|
|
"entropy": 6.1300661087036135,
|
|
"epoch": 1.5933923126905583,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00047520192550023344,
|
|
"loss": 5.8845,
|
|
"mean_token_accuracy": 0.16116737425327302,
|
|
"num_tokens": 31183654.0,
|
|
"step": 15940
|
|
},
|
|
{
|
|
"entropy": 6.1397350311279295,
|
|
"epoch": 1.5938921377517867,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004751856352844913,
|
|
"loss": 5.9,
|
|
"mean_token_accuracy": 0.16272855252027513,
|
|
"num_tokens": 31193814.0,
|
|
"step": 15945
|
|
},
|
|
{
|
|
"entropy": 6.131307697296142,
|
|
"epoch": 1.5943919628130154,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00047516934003213,
|
|
"loss": 5.8681,
|
|
"mean_token_accuracy": 0.1593376249074936,
|
|
"num_tokens": 31203834.0,
|
|
"step": 15950
|
|
},
|
|
{
|
|
"entropy": 6.133946943283081,
|
|
"epoch": 1.5948917878742441,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00047515303974355965,
|
|
"loss": 5.9983,
|
|
"mean_token_accuracy": 0.14716990143060685,
|
|
"num_tokens": 31214625.0,
|
|
"step": 15955
|
|
},
|
|
{
|
|
"entropy": 6.21510944366455,
|
|
"epoch": 1.5953916129354726,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.00047513673441919036,
|
|
"loss": 5.9219,
|
|
"mean_token_accuracy": 0.16002627462148666,
|
|
"num_tokens": 31224125.0,
|
|
"step": 15960
|
|
},
|
|
{
|
|
"entropy": 6.148350191116333,
|
|
"epoch": 1.595891437996701,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004751204240594323,
|
|
"loss": 5.9072,
|
|
"mean_token_accuracy": 0.16153207868337632,
|
|
"num_tokens": 31233869.0,
|
|
"step": 15965
|
|
},
|
|
{
|
|
"entropy": 6.195877027511597,
|
|
"epoch": 1.5963912630579298,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004751041086646959,
|
|
"loss": 6.0079,
|
|
"mean_token_accuracy": 0.15301622301340104,
|
|
"num_tokens": 31244652.0,
|
|
"step": 15970
|
|
},
|
|
{
|
|
"entropy": 6.205608224868774,
|
|
"epoch": 1.5968910881191583,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004750877882353915,
|
|
"loss": 5.9491,
|
|
"mean_token_accuracy": 0.16067053526639938,
|
|
"num_tokens": 31254754.0,
|
|
"step": 15975
|
|
},
|
|
{
|
|
"entropy": 6.168276071548462,
|
|
"epoch": 1.5973909131803867,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.00047507146277192997,
|
|
"loss": 5.963,
|
|
"mean_token_accuracy": 0.16296229660511016,
|
|
"num_tokens": 31263768.0,
|
|
"step": 15980
|
|
},
|
|
{
|
|
"entropy": 6.070095729827881,
|
|
"epoch": 1.5978907382416154,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004750551322747219,
|
|
"loss": 5.8897,
|
|
"mean_token_accuracy": 0.15907872021198272,
|
|
"num_tokens": 31273295.0,
|
|
"step": 15985
|
|
},
|
|
{
|
|
"entropy": 6.19075231552124,
|
|
"epoch": 1.5983905633028441,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004750387967441781,
|
|
"loss": 5.9596,
|
|
"mean_token_accuracy": 0.1528765633702278,
|
|
"num_tokens": 31284996.0,
|
|
"step": 15990
|
|
},
|
|
{
|
|
"entropy": 6.20226035118103,
|
|
"epoch": 1.5988903883640726,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00047502245618070976,
|
|
"loss": 5.8844,
|
|
"mean_token_accuracy": 0.15611421167850495,
|
|
"num_tokens": 31294496.0,
|
|
"step": 15995
|
|
},
|
|
{
|
|
"entropy": 6.091341161727906,
|
|
"epoch": 1.599390213425301,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00047500611058472783,
|
|
"loss": 5.7908,
|
|
"mean_token_accuracy": 0.16094809025526047,
|
|
"num_tokens": 31303655.0,
|
|
"step": 16000
|
|
},
|
|
{
|
|
"entropy": 6.095734119415283,
|
|
"epoch": 1.5998900384865298,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00047498975995664356,
|
|
"loss": 5.8331,
|
|
"mean_token_accuracy": 0.16860375851392745,
|
|
"num_tokens": 31313058.0,
|
|
"step": 16005
|
|
},
|
|
{
|
|
"entropy": 6.084413719177246,
|
|
"epoch": 1.6003898635477583,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004749734042968685,
|
|
"loss": 5.8257,
|
|
"mean_token_accuracy": 0.16647930145263673,
|
|
"num_tokens": 31323214.0,
|
|
"step": 16010
|
|
},
|
|
{
|
|
"entropy": 6.179101800918579,
|
|
"epoch": 1.6008896886089867,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.000474957043605814,
|
|
"loss": 5.9745,
|
|
"mean_token_accuracy": 0.15763366222381592,
|
|
"num_tokens": 31333691.0,
|
|
"step": 16015
|
|
},
|
|
{
|
|
"entropy": 6.25221815109253,
|
|
"epoch": 1.6013895136702154,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00047494067788389174,
|
|
"loss": 5.9245,
|
|
"mean_token_accuracy": 0.15439243465662003,
|
|
"num_tokens": 31342240.0,
|
|
"step": 16020
|
|
},
|
|
{
|
|
"entropy": 6.129102373123169,
|
|
"epoch": 1.6018893387314441,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00047492430713151347,
|
|
"loss": 5.825,
|
|
"mean_token_accuracy": 0.16748217195272447,
|
|
"num_tokens": 31351955.0,
|
|
"step": 16025
|
|
},
|
|
{
|
|
"entropy": 6.040925645828247,
|
|
"epoch": 1.6023891637926726,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004749079313490911,
|
|
"loss": 5.8032,
|
|
"mean_token_accuracy": 0.16716589778661728,
|
|
"num_tokens": 31361583.0,
|
|
"step": 16030
|
|
},
|
|
{
|
|
"entropy": 6.088488483428955,
|
|
"epoch": 1.602888988853901,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00047489155053703655,
|
|
"loss": 5.8741,
|
|
"mean_token_accuracy": 0.16249251663684844,
|
|
"num_tokens": 31371219.0,
|
|
"step": 16035
|
|
},
|
|
{
|
|
"entropy": 6.178510999679565,
|
|
"epoch": 1.6033888139151298,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004748751646957621,
|
|
"loss": 5.883,
|
|
"mean_token_accuracy": 0.1556862361729145,
|
|
"num_tokens": 31381561.0,
|
|
"step": 16040
|
|
},
|
|
{
|
|
"entropy": 6.168209981918335,
|
|
"epoch": 1.6038886389763582,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004748587738256799,
|
|
"loss": 5.8484,
|
|
"mean_token_accuracy": 0.1638987123966217,
|
|
"num_tokens": 31391385.0,
|
|
"step": 16045
|
|
},
|
|
{
|
|
"entropy": 6.168503475189209,
|
|
"epoch": 1.6043884640375867,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004748423779272024,
|
|
"loss": 5.8815,
|
|
"mean_token_accuracy": 0.1574132263660431,
|
|
"num_tokens": 31400817.0,
|
|
"step": 16050
|
|
},
|
|
{
|
|
"entropy": 6.146331691741944,
|
|
"epoch": 1.6048882890988154,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00047482597700074204,
|
|
"loss": 5.9494,
|
|
"mean_token_accuracy": 0.15307085812091828,
|
|
"num_tokens": 31411460.0,
|
|
"step": 16055
|
|
},
|
|
{
|
|
"entropy": 6.0337268829345705,
|
|
"epoch": 1.6053881141600441,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00047480957104671157,
|
|
"loss": 5.8128,
|
|
"mean_token_accuracy": 0.1718428060412407,
|
|
"num_tokens": 31420407.0,
|
|
"step": 16060
|
|
},
|
|
{
|
|
"entropy": 6.137241649627685,
|
|
"epoch": 1.6058879392212726,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004747931600655237,
|
|
"loss": 5.9577,
|
|
"mean_token_accuracy": 0.15480193942785264,
|
|
"num_tokens": 31430964.0,
|
|
"step": 16065
|
|
},
|
|
{
|
|
"entropy": 6.097628402709961,
|
|
"epoch": 1.606387764282501,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.00047477674405759136,
|
|
"loss": 5.7798,
|
|
"mean_token_accuracy": 0.1686554506421089,
|
|
"num_tokens": 31440143.0,
|
|
"step": 16070
|
|
},
|
|
{
|
|
"entropy": 6.0729447364807125,
|
|
"epoch": 1.6068875893437298,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004747603230233275,
|
|
"loss": 5.8731,
|
|
"mean_token_accuracy": 0.1646135799586773,
|
|
"num_tokens": 31449615.0,
|
|
"step": 16075
|
|
},
|
|
{
|
|
"entropy": 6.146064043045044,
|
|
"epoch": 1.6073874144049582,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004747438969631453,
|
|
"loss": 5.9572,
|
|
"mean_token_accuracy": 0.14821103364229202,
|
|
"num_tokens": 31459238.0,
|
|
"step": 16080
|
|
},
|
|
{
|
|
"entropy": 6.139043998718262,
|
|
"epoch": 1.6078872394661867,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004747274658774581,
|
|
"loss": 5.8567,
|
|
"mean_token_accuracy": 0.1695764794945717,
|
|
"num_tokens": 31468540.0,
|
|
"step": 16085
|
|
},
|
|
{
|
|
"entropy": 6.126196479797363,
|
|
"epoch": 1.6083870645274154,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004747110297666793,
|
|
"loss": 5.84,
|
|
"mean_token_accuracy": 0.16754427701234817,
|
|
"num_tokens": 31478999.0,
|
|
"step": 16090
|
|
},
|
|
{
|
|
"entropy": 6.078820896148682,
|
|
"epoch": 1.6088868895886441,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004746945886312223,
|
|
"loss": 5.8786,
|
|
"mean_token_accuracy": 0.16174889951944352,
|
|
"num_tokens": 31490237.0,
|
|
"step": 16095
|
|
},
|
|
{
|
|
"entropy": 6.116386222839355,
|
|
"epoch": 1.6093867146498726,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004746781424715009,
|
|
"loss": 5.9263,
|
|
"mean_token_accuracy": 0.15998089611530303,
|
|
"num_tokens": 31500250.0,
|
|
"step": 16100
|
|
},
|
|
{
|
|
"entropy": 6.196410226821899,
|
|
"epoch": 1.609886539711101,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00047466169128792873,
|
|
"loss": 5.9695,
|
|
"mean_token_accuracy": 0.1575181305408478,
|
|
"num_tokens": 31511559.0,
|
|
"step": 16105
|
|
},
|
|
{
|
|
"entropy": 6.218584299087524,
|
|
"epoch": 1.6103863647723298,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004746452350809198,
|
|
"loss": 5.9225,
|
|
"mean_token_accuracy": 0.15792882591485977,
|
|
"num_tokens": 31520189.0,
|
|
"step": 16110
|
|
},
|
|
{
|
|
"entropy": 6.028193855285645,
|
|
"epoch": 1.6108861898335582,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00047462877385088815,
|
|
"loss": 5.7647,
|
|
"mean_token_accuracy": 0.16634624153375627,
|
|
"num_tokens": 31529361.0,
|
|
"step": 16115
|
|
},
|
|
{
|
|
"entropy": 6.022070646286011,
|
|
"epoch": 1.6113860148947867,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00047461230759824794,
|
|
"loss": 5.92,
|
|
"mean_token_accuracy": 0.1547860860824585,
|
|
"num_tokens": 31539530.0,
|
|
"step": 16120
|
|
},
|
|
{
|
|
"entropy": 6.248088026046753,
|
|
"epoch": 1.6118858399560154,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00047459583632341343,
|
|
"loss": 5.9867,
|
|
"mean_token_accuracy": 0.15121661722660065,
|
|
"num_tokens": 31549166.0,
|
|
"step": 16125
|
|
},
|
|
{
|
|
"entropy": 6.1368013381958,
|
|
"epoch": 1.6123856650172441,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00047457936002679905,
|
|
"loss": 5.8656,
|
|
"mean_token_accuracy": 0.16321052461862565,
|
|
"num_tokens": 31558643.0,
|
|
"step": 16130
|
|
},
|
|
{
|
|
"entropy": 6.143841314315796,
|
|
"epoch": 1.6128854900784724,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00047456287870881924,
|
|
"loss": 5.8547,
|
|
"mean_token_accuracy": 0.16555679887533187,
|
|
"num_tokens": 31568752.0,
|
|
"step": 16135
|
|
},
|
|
{
|
|
"entropy": 6.145507764816284,
|
|
"epoch": 1.613385315139701,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004745463923698888,
|
|
"loss": 5.9352,
|
|
"mean_token_accuracy": 0.15683097392320633,
|
|
"num_tokens": 31577894.0,
|
|
"step": 16140
|
|
},
|
|
{
|
|
"entropy": 6.069931840896606,
|
|
"epoch": 1.6138851402009298,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004745299010104226,
|
|
"loss": 5.8693,
|
|
"mean_token_accuracy": 0.16115620732307434,
|
|
"num_tokens": 31586348.0,
|
|
"step": 16145
|
|
},
|
|
{
|
|
"entropy": 6.1560405731201175,
|
|
"epoch": 1.6143849652621582,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00047451340463083527,
|
|
"loss": 5.9046,
|
|
"mean_token_accuracy": 0.16242365390062333,
|
|
"num_tokens": 31596472.0,
|
|
"step": 16150
|
|
},
|
|
{
|
|
"entropy": 6.214483404159546,
|
|
"epoch": 1.6148847903233867,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00047449690323154206,
|
|
"loss": 5.8725,
|
|
"mean_token_accuracy": 0.16163890585303306,
|
|
"num_tokens": 31606342.0,
|
|
"step": 16155
|
|
},
|
|
{
|
|
"entropy": 6.145944595336914,
|
|
"epoch": 1.6153846153846154,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00047448039681295814,
|
|
"loss": 5.9283,
|
|
"mean_token_accuracy": 0.15377518832683562,
|
|
"num_tokens": 31615548.0,
|
|
"step": 16160
|
|
},
|
|
{
|
|
"entropy": 6.060011482238769,
|
|
"epoch": 1.6158844404458441,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00047446388537549867,
|
|
"loss": 5.9148,
|
|
"mean_token_accuracy": 0.15456662774086,
|
|
"num_tokens": 31626290.0,
|
|
"step": 16165
|
|
},
|
|
{
|
|
"entropy": 6.147197103500366,
|
|
"epoch": 1.6163842655070724,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004744473689195793,
|
|
"loss": 5.8867,
|
|
"mean_token_accuracy": 0.1610730528831482,
|
|
"num_tokens": 31635620.0,
|
|
"step": 16170
|
|
},
|
|
{
|
|
"entropy": 6.148130989074707,
|
|
"epoch": 1.616884090568301,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004744308474456154,
|
|
"loss": 5.9225,
|
|
"mean_token_accuracy": 0.16163863986730576,
|
|
"num_tokens": 31647168.0,
|
|
"step": 16175
|
|
},
|
|
{
|
|
"entropy": 6.145283603668213,
|
|
"epoch": 1.6173839156295298,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004744143209540227,
|
|
"loss": 5.8004,
|
|
"mean_token_accuracy": 0.16176878809928893,
|
|
"num_tokens": 31656173.0,
|
|
"step": 16180
|
|
},
|
|
{
|
|
"entropy": 6.074552154541015,
|
|
"epoch": 1.6178837406907582,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004743977894452169,
|
|
"loss": 5.8816,
|
|
"mean_token_accuracy": 0.15985965430736543,
|
|
"num_tokens": 31665224.0,
|
|
"step": 16185
|
|
},
|
|
{
|
|
"entropy": 6.0285186767578125,
|
|
"epoch": 1.6183835657519867,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004743812529196142,
|
|
"loss": 5.8347,
|
|
"mean_token_accuracy": 0.1609862968325615,
|
|
"num_tokens": 31674623.0,
|
|
"step": 16190
|
|
},
|
|
{
|
|
"entropy": 6.153869533538819,
|
|
"epoch": 1.6188833908132154,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004743647113776304,
|
|
"loss": 5.8802,
|
|
"mean_token_accuracy": 0.16540788412094115,
|
|
"num_tokens": 31684565.0,
|
|
"step": 16195
|
|
},
|
|
{
|
|
"entropy": 6.143793249130249,
|
|
"epoch": 1.619383215874444,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.00047434816481968175,
|
|
"loss": 5.9153,
|
|
"mean_token_accuracy": 0.1597794361412525,
|
|
"num_tokens": 31694885.0,
|
|
"step": 16200
|
|
},
|
|
{
|
|
"entropy": 6.162732028961182,
|
|
"epoch": 1.6198830409356724,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00047433161324618456,
|
|
"loss": 5.9115,
|
|
"mean_token_accuracy": 0.15935486555099487,
|
|
"num_tokens": 31704077.0,
|
|
"step": 16205
|
|
},
|
|
{
|
|
"entropy": 6.241324710845947,
|
|
"epoch": 1.620382865996901,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004743150566575553,
|
|
"loss": 5.9493,
|
|
"mean_token_accuracy": 0.15140072554349898,
|
|
"num_tokens": 31713773.0,
|
|
"step": 16210
|
|
},
|
|
{
|
|
"entropy": 6.164005899429322,
|
|
"epoch": 1.6208826910581298,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004742984950542105,
|
|
"loss": 5.9592,
|
|
"mean_token_accuracy": 0.16007295548915862,
|
|
"num_tokens": 31724020.0,
|
|
"step": 16215
|
|
},
|
|
{
|
|
"entropy": 6.136595821380615,
|
|
"epoch": 1.6213825161193582,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00047428192843656684,
|
|
"loss": 5.8983,
|
|
"mean_token_accuracy": 0.15775277614593505,
|
|
"num_tokens": 31733992.0,
|
|
"step": 16220
|
|
},
|
|
{
|
|
"entropy": 6.211799573898316,
|
|
"epoch": 1.6218823411805867,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.00047426535680504105,
|
|
"loss": 5.9286,
|
|
"mean_token_accuracy": 0.15749860554933548,
|
|
"num_tokens": 31745153.0,
|
|
"step": 16225
|
|
},
|
|
{
|
|
"entropy": 6.176314926147461,
|
|
"epoch": 1.6223821662418154,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00047424878016005036,
|
|
"loss": 5.8505,
|
|
"mean_token_accuracy": 0.1599099263548851,
|
|
"num_tokens": 31755110.0,
|
|
"step": 16230
|
|
},
|
|
{
|
|
"entropy": 6.119541597366333,
|
|
"epoch": 1.622881991303044,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004742321985020115,
|
|
"loss": 5.8757,
|
|
"mean_token_accuracy": 0.1598087340593338,
|
|
"num_tokens": 31764219.0,
|
|
"step": 16235
|
|
},
|
|
{
|
|
"entropy": 6.0570111751556395,
|
|
"epoch": 1.6233818163642724,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004742156118313418,
|
|
"loss": 5.7731,
|
|
"mean_token_accuracy": 0.15940103381872178,
|
|
"num_tokens": 31773597.0,
|
|
"step": 16240
|
|
},
|
|
{
|
|
"entropy": 6.146574544906616,
|
|
"epoch": 1.623881641425501,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00047419902014845855,
|
|
"loss": 5.884,
|
|
"mean_token_accuracy": 0.15996838510036468,
|
|
"num_tokens": 31783302.0,
|
|
"step": 16245
|
|
},
|
|
{
|
|
"entropy": 6.081358146667481,
|
|
"epoch": 1.6243814664867298,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004741824234537793,
|
|
"loss": 5.9193,
|
|
"mean_token_accuracy": 0.1561587020754814,
|
|
"num_tokens": 31793127.0,
|
|
"step": 16250
|
|
},
|
|
{
|
|
"entropy": 6.108809566497802,
|
|
"epoch": 1.6248812915479582,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00047416582174772143,
|
|
"loss": 5.8956,
|
|
"mean_token_accuracy": 0.1611502155661583,
|
|
"num_tokens": 31802756.0,
|
|
"step": 16255
|
|
},
|
|
{
|
|
"entropy": 6.164645338058472,
|
|
"epoch": 1.6253811166091867,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.00047414921503070276,
|
|
"loss": 5.9376,
|
|
"mean_token_accuracy": 0.15861285477876663,
|
|
"num_tokens": 31813390.0,
|
|
"step": 16260
|
|
},
|
|
{
|
|
"entropy": 6.150406217575073,
|
|
"epoch": 1.6258809416704154,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00047413260330314116,
|
|
"loss": 5.9144,
|
|
"mean_token_accuracy": 0.16733056157827378,
|
|
"num_tokens": 31823304.0,
|
|
"step": 16265
|
|
},
|
|
{
|
|
"entropy": 6.1531651496887205,
|
|
"epoch": 1.626380766731644,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004741159865654544,
|
|
"loss": 5.8864,
|
|
"mean_token_accuracy": 0.16533361673355101,
|
|
"num_tokens": 31832878.0,
|
|
"step": 16270
|
|
},
|
|
{
|
|
"entropy": 6.140581941604614,
|
|
"epoch": 1.6268805917928724,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.00047409936481806076,
|
|
"loss": 5.8978,
|
|
"mean_token_accuracy": 0.16217795461416246,
|
|
"num_tokens": 31841753.0,
|
|
"step": 16275
|
|
},
|
|
{
|
|
"entropy": 6.006665754318237,
|
|
"epoch": 1.627380416854101,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004740827380613782,
|
|
"loss": 5.727,
|
|
"mean_token_accuracy": 0.1673479810357094,
|
|
"num_tokens": 31851451.0,
|
|
"step": 16280
|
|
},
|
|
{
|
|
"entropy": 6.1131706714630125,
|
|
"epoch": 1.6278802419153298,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00047406610629582526,
|
|
"loss": 5.8488,
|
|
"mean_token_accuracy": 0.16459959745407104,
|
|
"num_tokens": 31860885.0,
|
|
"step": 16285
|
|
},
|
|
{
|
|
"entropy": 6.07653431892395,
|
|
"epoch": 1.6283800669765582,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00047404946952182034,
|
|
"loss": 5.806,
|
|
"mean_token_accuracy": 0.1725273311138153,
|
|
"num_tokens": 31870056.0,
|
|
"step": 16290
|
|
},
|
|
{
|
|
"entropy": 6.099943494796753,
|
|
"epoch": 1.6288798920377867,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004740328277397819,
|
|
"loss": 5.8739,
|
|
"mean_token_accuracy": 0.16686343550682067,
|
|
"num_tokens": 31879513.0,
|
|
"step": 16295
|
|
},
|
|
{
|
|
"entropy": 6.134911966323853,
|
|
"epoch": 1.6293797170990154,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004740161809501288,
|
|
"loss": 5.8439,
|
|
"mean_token_accuracy": 0.16484363973140717,
|
|
"num_tokens": 31890288.0,
|
|
"step": 16300
|
|
},
|
|
{
|
|
"entropy": 6.157239961624145,
|
|
"epoch": 1.6298795421602439,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00047399952915327975,
|
|
"loss": 5.8498,
|
|
"mean_token_accuracy": 0.15603400096297265,
|
|
"num_tokens": 31900168.0,
|
|
"step": 16305
|
|
},
|
|
{
|
|
"entropy": 6.126083183288574,
|
|
"epoch": 1.6303793672214724,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004739828723496538,
|
|
"loss": 5.8298,
|
|
"mean_token_accuracy": 0.15930139273405075,
|
|
"num_tokens": 31908788.0,
|
|
"step": 16310
|
|
},
|
|
{
|
|
"entropy": 6.072530746459961,
|
|
"epoch": 1.630879192282701,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00047396621053967,
|
|
"loss": 5.843,
|
|
"mean_token_accuracy": 0.16678276360034944,
|
|
"num_tokens": 31916968.0,
|
|
"step": 16315
|
|
},
|
|
{
|
|
"entropy": 6.175118923187256,
|
|
"epoch": 1.6313790173439298,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00047394954372374743,
|
|
"loss": 5.9,
|
|
"mean_token_accuracy": 0.1551012173295021,
|
|
"num_tokens": 31927205.0,
|
|
"step": 16320
|
|
},
|
|
{
|
|
"entropy": 6.165901947021484,
|
|
"epoch": 1.6318788424051582,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00047393287190230566,
|
|
"loss": 5.8356,
|
|
"mean_token_accuracy": 0.1604092925786972,
|
|
"num_tokens": 31937001.0,
|
|
"step": 16325
|
|
},
|
|
{
|
|
"entropy": 6.110785913467407,
|
|
"epoch": 1.6323786674663867,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004739161950757639,
|
|
"loss": 5.8767,
|
|
"mean_token_accuracy": 0.15767664611339569,
|
|
"num_tokens": 31946915.0,
|
|
"step": 16330
|
|
},
|
|
{
|
|
"entropy": 6.145122861862182,
|
|
"epoch": 1.6328784925276154,
|
|
"grad_norm": 1.984375,
|
|
"learning_rate": 0.000473899513244542,
|
|
"loss": 5.8431,
|
|
"mean_token_accuracy": 0.1618260011076927,
|
|
"num_tokens": 31956615.0,
|
|
"step": 16335
|
|
},
|
|
{
|
|
"entropy": 6.118664646148682,
|
|
"epoch": 1.6333783175888439,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004738828264090594,
|
|
"loss": 5.9207,
|
|
"mean_token_accuracy": 0.15699604600667955,
|
|
"num_tokens": 31967203.0,
|
|
"step": 16340
|
|
},
|
|
{
|
|
"entropy": 6.106103754043579,
|
|
"epoch": 1.6338781426500724,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00047386613456973614,
|
|
"loss": 5.7884,
|
|
"mean_token_accuracy": 0.167632058262825,
|
|
"num_tokens": 31976736.0,
|
|
"step": 16345
|
|
},
|
|
{
|
|
"entropy": 6.065636396408081,
|
|
"epoch": 1.634377967711301,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004738494377269921,
|
|
"loss": 5.8112,
|
|
"mean_token_accuracy": 0.16667845398187636,
|
|
"num_tokens": 31987000.0,
|
|
"step": 16350
|
|
},
|
|
{
|
|
"entropy": 6.174714660644531,
|
|
"epoch": 1.6348777927725298,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.00047383273588124736,
|
|
"loss": 6.0091,
|
|
"mean_token_accuracy": 0.15545531809329988,
|
|
"num_tokens": 31996238.0,
|
|
"step": 16355
|
|
},
|
|
{
|
|
"entropy": 6.193500614166259,
|
|
"epoch": 1.6353776178337582,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004738160290329222,
|
|
"loss": 5.9092,
|
|
"mean_token_accuracy": 0.15937088429927826,
|
|
"num_tokens": 32005785.0,
|
|
"step": 16360
|
|
},
|
|
{
|
|
"entropy": 6.130488872528076,
|
|
"epoch": 1.6358774428949867,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00047379931718243684,
|
|
"loss": 5.9608,
|
|
"mean_token_accuracy": 0.1601053312420845,
|
|
"num_tokens": 32017140.0,
|
|
"step": 16365
|
|
},
|
|
{
|
|
"entropy": 6.065225601196289,
|
|
"epoch": 1.6363772679562154,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004737826003302118,
|
|
"loss": 5.7485,
|
|
"mean_token_accuracy": 0.1746237576007843,
|
|
"num_tokens": 32026431.0,
|
|
"step": 16370
|
|
},
|
|
{
|
|
"entropy": 6.193103456497193,
|
|
"epoch": 1.6368770930174439,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00047376587847666767,
|
|
"loss": 6.0052,
|
|
"mean_token_accuracy": 0.15909340977668762,
|
|
"num_tokens": 32036211.0,
|
|
"step": 16375
|
|
},
|
|
{
|
|
"entropy": 6.1763709545135494,
|
|
"epoch": 1.6373769180786724,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004737491516222253,
|
|
"loss": 5.9123,
|
|
"mean_token_accuracy": 0.15526963174343109,
|
|
"num_tokens": 32047231.0,
|
|
"step": 16380
|
|
},
|
|
{
|
|
"entropy": 6.128999280929565,
|
|
"epoch": 1.637876743139901,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00047373241976730537,
|
|
"loss": 5.8866,
|
|
"mean_token_accuracy": 0.1579688683152199,
|
|
"num_tokens": 32057649.0,
|
|
"step": 16385
|
|
},
|
|
{
|
|
"entropy": 6.175368356704712,
|
|
"epoch": 1.6383765682011298,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004737156829123289,
|
|
"loss": 5.8511,
|
|
"mean_token_accuracy": 0.16340236961841584,
|
|
"num_tokens": 32066208.0,
|
|
"step": 16390
|
|
},
|
|
{
|
|
"entropy": 6.16707181930542,
|
|
"epoch": 1.638876393262358,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00047369894105771693,
|
|
"loss": 5.9053,
|
|
"mean_token_accuracy": 0.17434269040822983,
|
|
"num_tokens": 32076451.0,
|
|
"step": 16395
|
|
},
|
|
{
|
|
"entropy": 6.19351601600647,
|
|
"epoch": 1.6393762183235867,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00047368219420389077,
|
|
"loss": 5.9459,
|
|
"mean_token_accuracy": 0.15300357192754746,
|
|
"num_tokens": 32085642.0,
|
|
"step": 16400
|
|
},
|
|
{
|
|
"entropy": 6.162382745742798,
|
|
"epoch": 1.6398760433848154,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004736654423512717,
|
|
"loss": 5.9166,
|
|
"mean_token_accuracy": 0.15671353936195373,
|
|
"num_tokens": 32094350.0,
|
|
"step": 16405
|
|
},
|
|
{
|
|
"entropy": 6.108351421356201,
|
|
"epoch": 1.6403758684460439,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004736486855002813,
|
|
"loss": 5.8847,
|
|
"mean_token_accuracy": 0.16184229105710984,
|
|
"num_tokens": 32104981.0,
|
|
"step": 16410
|
|
},
|
|
{
|
|
"entropy": 6.111570596694946,
|
|
"epoch": 1.6408756935072724,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.000473631923651341,
|
|
"loss": 5.8661,
|
|
"mean_token_accuracy": 0.16245781034231185,
|
|
"num_tokens": 32114198.0,
|
|
"step": 16415
|
|
},
|
|
{
|
|
"entropy": 6.144701957702637,
|
|
"epoch": 1.641375518568501,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004736151568048726,
|
|
"loss": 5.861,
|
|
"mean_token_accuracy": 0.16171735972166063,
|
|
"num_tokens": 32124622.0,
|
|
"step": 16420
|
|
},
|
|
{
|
|
"entropy": 6.130097484588623,
|
|
"epoch": 1.6418753436297298,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.000473598384961298,
|
|
"loss": 5.9076,
|
|
"mean_token_accuracy": 0.15210689455270768,
|
|
"num_tokens": 32134466.0,
|
|
"step": 16425
|
|
},
|
|
{
|
|
"entropy": 6.20010085105896,
|
|
"epoch": 1.642375168690958,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00047358160812103925,
|
|
"loss": 5.9369,
|
|
"mean_token_accuracy": 0.15536476522684098,
|
|
"num_tokens": 32144104.0,
|
|
"step": 16430
|
|
},
|
|
{
|
|
"entropy": 6.103492689132691,
|
|
"epoch": 1.6428749937521867,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004735648262845182,
|
|
"loss": 5.8178,
|
|
"mean_token_accuracy": 0.16161573380231858,
|
|
"num_tokens": 32156432.0,
|
|
"step": 16435
|
|
},
|
|
{
|
|
"entropy": 6.173177719116211,
|
|
"epoch": 1.6433748188134154,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.00047354803945215727,
|
|
"loss": 5.9117,
|
|
"mean_token_accuracy": 0.16193071156740188,
|
|
"num_tokens": 32166853.0,
|
|
"step": 16440
|
|
},
|
|
{
|
|
"entropy": 6.119800758361817,
|
|
"epoch": 1.6438746438746439,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00047353124762437865,
|
|
"loss": 5.784,
|
|
"mean_token_accuracy": 0.17476997822523116,
|
|
"num_tokens": 32175604.0,
|
|
"step": 16445
|
|
},
|
|
{
|
|
"entropy": 6.078823232650757,
|
|
"epoch": 1.6443744689358724,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004735144508016051,
|
|
"loss": 5.8635,
|
|
"mean_token_accuracy": 0.16064816415309907,
|
|
"num_tokens": 32185878.0,
|
|
"step": 16450
|
|
},
|
|
{
|
|
"entropy": 6.157793188095093,
|
|
"epoch": 1.644874293997101,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004734976489842589,
|
|
"loss": 5.9683,
|
|
"mean_token_accuracy": 0.15036503970623016,
|
|
"num_tokens": 32196061.0,
|
|
"step": 16455
|
|
},
|
|
{
|
|
"entropy": 6.153126049041748,
|
|
"epoch": 1.6453741190583295,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.000473480842172763,
|
|
"loss": 5.8624,
|
|
"mean_token_accuracy": 0.16707222908735275,
|
|
"num_tokens": 32207470.0,
|
|
"step": 16460
|
|
},
|
|
{
|
|
"entropy": 6.203348827362061,
|
|
"epoch": 1.645873944119558,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.00047346403036754023,
|
|
"loss": 5.9734,
|
|
"mean_token_accuracy": 0.15738432258367538,
|
|
"num_tokens": 32216660.0,
|
|
"step": 16465
|
|
},
|
|
{
|
|
"entropy": 6.18003659248352,
|
|
"epoch": 1.6463737691807867,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00047344721356901344,
|
|
"loss": 5.8517,
|
|
"mean_token_accuracy": 0.16395285129547119,
|
|
"num_tokens": 32226472.0,
|
|
"step": 16470
|
|
},
|
|
{
|
|
"entropy": 6.1828264713287355,
|
|
"epoch": 1.6468735942420154,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004734303917776059,
|
|
"loss": 5.9556,
|
|
"mean_token_accuracy": 0.15418880432844162,
|
|
"num_tokens": 32235841.0,
|
|
"step": 16475
|
|
},
|
|
{
|
|
"entropy": 6.0212301254272464,
|
|
"epoch": 1.6473734193032439,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00047341356499374065,
|
|
"loss": 5.7304,
|
|
"mean_token_accuracy": 0.17145554572343827,
|
|
"num_tokens": 32245388.0,
|
|
"step": 16480
|
|
},
|
|
{
|
|
"entropy": 6.1301007747650145,
|
|
"epoch": 1.6478732443644724,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004733967332178412,
|
|
"loss": 5.9145,
|
|
"mean_token_accuracy": 0.16238226294517516,
|
|
"num_tokens": 32255089.0,
|
|
"step": 16485
|
|
},
|
|
{
|
|
"entropy": 6.080270481109619,
|
|
"epoch": 1.648373069425701,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004733798964503311,
|
|
"loss": 5.7587,
|
|
"mean_token_accuracy": 0.16990573704242706,
|
|
"num_tokens": 32265196.0,
|
|
"step": 16490
|
|
},
|
|
{
|
|
"entropy": 6.046630907058716,
|
|
"epoch": 1.6488728944869295,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004733630546916338,
|
|
"loss": 5.7531,
|
|
"mean_token_accuracy": 0.16512000411748887,
|
|
"num_tokens": 32276734.0,
|
|
"step": 16495
|
|
},
|
|
{
|
|
"entropy": 6.11317777633667,
|
|
"epoch": 1.649372719548158,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.00047334620794217306,
|
|
"loss": 5.9064,
|
|
"mean_token_accuracy": 0.15816880017518997,
|
|
"num_tokens": 32286098.0,
|
|
"step": 16500
|
|
},
|
|
{
|
|
"entropy": 6.127501678466797,
|
|
"epoch": 1.6498725446093867,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004733293562023727,
|
|
"loss": 5.9403,
|
|
"mean_token_accuracy": 0.1565721280872822,
|
|
"num_tokens": 32295123.0,
|
|
"step": 16505
|
|
},
|
|
{
|
|
"entropy": 6.124748039245605,
|
|
"epoch": 1.6503723696706154,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.00047331249947265685,
|
|
"loss": 5.845,
|
|
"mean_token_accuracy": 0.1652669683098793,
|
|
"num_tokens": 32304016.0,
|
|
"step": 16510
|
|
},
|
|
{
|
|
"entropy": 6.107478523254395,
|
|
"epoch": 1.6508721947318439,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004732956377534496,
|
|
"loss": 5.8196,
|
|
"mean_token_accuracy": 0.15800952166318893,
|
|
"num_tokens": 32313437.0,
|
|
"step": 16515
|
|
},
|
|
{
|
|
"entropy": 6.141150999069214,
|
|
"epoch": 1.6513720197930724,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.000473278771045175,
|
|
"loss": 5.8973,
|
|
"mean_token_accuracy": 0.1629784122109413,
|
|
"num_tokens": 32322966.0,
|
|
"step": 16520
|
|
},
|
|
{
|
|
"entropy": 6.077485466003418,
|
|
"epoch": 1.651871844854301,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00047326189934825764,
|
|
"loss": 5.9097,
|
|
"mean_token_accuracy": 0.15579638332128526,
|
|
"num_tokens": 32333555.0,
|
|
"step": 16525
|
|
},
|
|
{
|
|
"entropy": 6.10307354927063,
|
|
"epoch": 1.6523716699155295,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004732450226631219,
|
|
"loss": 5.8092,
|
|
"mean_token_accuracy": 0.16455169171094894,
|
|
"num_tokens": 32343946.0,
|
|
"step": 16530
|
|
},
|
|
{
|
|
"entropy": 6.163082599639893,
|
|
"epoch": 1.652871494976758,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.00047322814099019236,
|
|
"loss": 5.8632,
|
|
"mean_token_accuracy": 0.16236407831311225,
|
|
"num_tokens": 32353932.0,
|
|
"step": 16535
|
|
},
|
|
{
|
|
"entropy": 6.035224771499633,
|
|
"epoch": 1.6533713200379867,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004732112543298938,
|
|
"loss": 5.7755,
|
|
"mean_token_accuracy": 0.16848057508468628,
|
|
"num_tokens": 32363156.0,
|
|
"step": 16540
|
|
},
|
|
{
|
|
"entropy": 6.034097576141358,
|
|
"epoch": 1.6538711450992154,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004731943626826511,
|
|
"loss": 5.8133,
|
|
"mean_token_accuracy": 0.16707777976989746,
|
|
"num_tokens": 32371987.0,
|
|
"step": 16545
|
|
},
|
|
{
|
|
"entropy": 6.182418441772461,
|
|
"epoch": 1.6543709701604439,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00047317746604888923,
|
|
"loss": 5.8935,
|
|
"mean_token_accuracy": 0.15517692565917968,
|
|
"num_tokens": 32381391.0,
|
|
"step": 16550
|
|
},
|
|
{
|
|
"entropy": 6.1798159122467045,
|
|
"epoch": 1.6548707952216724,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.00047316056442903333,
|
|
"loss": 5.9185,
|
|
"mean_token_accuracy": 0.16136854588985444,
|
|
"num_tokens": 32390980.0,
|
|
"step": 16555
|
|
},
|
|
{
|
|
"entropy": 6.067631721496582,
|
|
"epoch": 1.655370620282901,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004731436578235086,
|
|
"loss": 5.8164,
|
|
"mean_token_accuracy": 0.16624444723129272,
|
|
"num_tokens": 32399240.0,
|
|
"step": 16560
|
|
},
|
|
{
|
|
"entropy": 6.116207933425903,
|
|
"epoch": 1.6558704453441295,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00047312674623274046,
|
|
"loss": 5.8597,
|
|
"mean_token_accuracy": 0.1602943480014801,
|
|
"num_tokens": 32409793.0,
|
|
"step": 16565
|
|
},
|
|
{
|
|
"entropy": 6.194666862487793,
|
|
"epoch": 1.656370270405358,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004731098296571543,
|
|
"loss": 5.8586,
|
|
"mean_token_accuracy": 0.1631217524409294,
|
|
"num_tokens": 32420658.0,
|
|
"step": 16570
|
|
},
|
|
{
|
|
"entropy": 6.318262434005737,
|
|
"epoch": 1.6568700954665867,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00047309290809717584,
|
|
"loss": 6.0513,
|
|
"mean_token_accuracy": 0.15152612403035165,
|
|
"num_tokens": 32430044.0,
|
|
"step": 16575
|
|
},
|
|
{
|
|
"entropy": 6.099453020095825,
|
|
"epoch": 1.6573699205278154,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.00047307598155323083,
|
|
"loss": 5.8998,
|
|
"mean_token_accuracy": 0.16494379788637162,
|
|
"num_tokens": 32439913.0,
|
|
"step": 16580
|
|
},
|
|
{
|
|
"entropy": 6.084395694732666,
|
|
"epoch": 1.6578697455890439,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.000473059050025745,
|
|
"loss": 5.8404,
|
|
"mean_token_accuracy": 0.1604056864976883,
|
|
"num_tokens": 32449125.0,
|
|
"step": 16585
|
|
},
|
|
{
|
|
"entropy": 6.10713758468628,
|
|
"epoch": 1.6583695706502724,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004730421135151445,
|
|
"loss": 5.8632,
|
|
"mean_token_accuracy": 0.16448641568422318,
|
|
"num_tokens": 32458549.0,
|
|
"step": 16590
|
|
},
|
|
{
|
|
"entropy": 6.142619562149048,
|
|
"epoch": 1.658869395711501,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004730251720218554,
|
|
"loss": 5.8393,
|
|
"mean_token_accuracy": 0.16367946565151215,
|
|
"num_tokens": 32468860.0,
|
|
"step": 16595
|
|
},
|
|
{
|
|
"entropy": 6.1834149837493895,
|
|
"epoch": 1.6593692207727295,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00047300822554630393,
|
|
"loss": 5.8339,
|
|
"mean_token_accuracy": 0.16432933509349823,
|
|
"num_tokens": 32479090.0,
|
|
"step": 16600
|
|
},
|
|
{
|
|
"entropy": 6.109146976470948,
|
|
"epoch": 1.659869045833958,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004729912740889164,
|
|
"loss": 5.7733,
|
|
"mean_token_accuracy": 0.16865911483764648,
|
|
"num_tokens": 32488611.0,
|
|
"step": 16605
|
|
},
|
|
{
|
|
"entropy": 6.086883115768432,
|
|
"epoch": 1.6603688708951867,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00047297431765011945,
|
|
"loss": 5.814,
|
|
"mean_token_accuracy": 0.16205232739448547,
|
|
"num_tokens": 32497821.0,
|
|
"step": 16610
|
|
},
|
|
{
|
|
"entropy": 6.013880825042724,
|
|
"epoch": 1.6608686959564154,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00047295735623033953,
|
|
"loss": 5.8043,
|
|
"mean_token_accuracy": 0.17166174501180648,
|
|
"num_tokens": 32507324.0,
|
|
"step": 16615
|
|
},
|
|
{
|
|
"entropy": 6.066670036315918,
|
|
"epoch": 1.6613685210176439,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004729403898300035,
|
|
"loss": 5.7885,
|
|
"mean_token_accuracy": 0.17106807976961136,
|
|
"num_tokens": 32517498.0,
|
|
"step": 16620
|
|
},
|
|
{
|
|
"entropy": 6.088050174713135,
|
|
"epoch": 1.6618683460788723,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00047292341844953813,
|
|
"loss": 5.8529,
|
|
"mean_token_accuracy": 0.16081804931163787,
|
|
"num_tokens": 32526527.0,
|
|
"step": 16625
|
|
},
|
|
{
|
|
"entropy": 6.113596391677857,
|
|
"epoch": 1.662368171140101,
|
|
"grad_norm": 2.265625,
|
|
"learning_rate": 0.0004729064420893706,
|
|
"loss": 5.8285,
|
|
"mean_token_accuracy": 0.16891932040452956,
|
|
"num_tokens": 32535017.0,
|
|
"step": 16630
|
|
},
|
|
{
|
|
"entropy": 5.991485214233398,
|
|
"epoch": 1.6628679962013295,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004728894607499278,
|
|
"loss": 5.7041,
|
|
"mean_token_accuracy": 0.1837837055325508,
|
|
"num_tokens": 32545687.0,
|
|
"step": 16635
|
|
},
|
|
{
|
|
"entropy": 6.100140953063965,
|
|
"epoch": 1.663367821262558,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004728724744316371,
|
|
"loss": 5.8612,
|
|
"mean_token_accuracy": 0.15739219039678573,
|
|
"num_tokens": 32554876.0,
|
|
"step": 16640
|
|
},
|
|
{
|
|
"entropy": 6.177180624008178,
|
|
"epoch": 1.6638676463237867,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00047285548313492594,
|
|
"loss": 5.948,
|
|
"mean_token_accuracy": 0.15829978436231612,
|
|
"num_tokens": 32565453.0,
|
|
"step": 16645
|
|
},
|
|
{
|
|
"entropy": 6.180706882476807,
|
|
"epoch": 1.6643674713850154,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004728384868602217,
|
|
"loss": 5.8384,
|
|
"mean_token_accuracy": 0.16195722222328185,
|
|
"num_tokens": 32573882.0,
|
|
"step": 16650
|
|
},
|
|
{
|
|
"entropy": 6.189860057830811,
|
|
"epoch": 1.6648672964462436,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.000472821485607952,
|
|
"loss": 5.9748,
|
|
"mean_token_accuracy": 0.15073680728673935,
|
|
"num_tokens": 32583182.0,
|
|
"step": 16655
|
|
},
|
|
{
|
|
"entropy": 6.18095760345459,
|
|
"epoch": 1.6653671215074723,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004728044793785446,
|
|
"loss": 5.9228,
|
|
"mean_token_accuracy": 0.15684778541326522,
|
|
"num_tokens": 32593405.0,
|
|
"step": 16660
|
|
},
|
|
{
|
|
"entropy": 6.112678146362304,
|
|
"epoch": 1.665866946568701,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00047278746817242754,
|
|
"loss": 5.872,
|
|
"mean_token_accuracy": 0.1557893767952919,
|
|
"num_tokens": 32603451.0,
|
|
"step": 16665
|
|
},
|
|
{
|
|
"entropy": 6.163123989105225,
|
|
"epoch": 1.6663667716299295,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004727704519900286,
|
|
"loss": 5.9932,
|
|
"mean_token_accuracy": 0.1594257779419422,
|
|
"num_tokens": 32614054.0,
|
|
"step": 16670
|
|
},
|
|
{
|
|
"entropy": 6.124230480194091,
|
|
"epoch": 1.666866596691158,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.000472753430831776,
|
|
"loss": 5.8322,
|
|
"mean_token_accuracy": 0.16533894389867781,
|
|
"num_tokens": 32623154.0,
|
|
"step": 16675
|
|
},
|
|
{
|
|
"entropy": 6.162586402893067,
|
|
"epoch": 1.6673664217523867,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00047273640469809786,
|
|
"loss": 5.9991,
|
|
"mean_token_accuracy": 0.15644034147262573,
|
|
"num_tokens": 32633252.0,
|
|
"step": 16680
|
|
},
|
|
{
|
|
"entropy": 6.048516654968262,
|
|
"epoch": 1.6678662468136154,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004727193735894227,
|
|
"loss": 5.7968,
|
|
"mean_token_accuracy": 0.16567823737859727,
|
|
"num_tokens": 32643681.0,
|
|
"step": 16685
|
|
},
|
|
{
|
|
"entropy": 6.042785692214966,
|
|
"epoch": 1.6683660718748436,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.00047270233750617907,
|
|
"loss": 5.7137,
|
|
"mean_token_accuracy": 0.17545314282178878,
|
|
"num_tokens": 32653094.0,
|
|
"step": 16690
|
|
},
|
|
{
|
|
"entropy": 6.086886024475097,
|
|
"epoch": 1.6688658969360723,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00047268529644879545,
|
|
"loss": 5.7412,
|
|
"mean_token_accuracy": 0.16168431490659713,
|
|
"num_tokens": 32663795.0,
|
|
"step": 16695
|
|
},
|
|
{
|
|
"entropy": 6.142530536651611,
|
|
"epoch": 1.669365721997301,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.00047266825041770066,
|
|
"loss": 5.8382,
|
|
"mean_token_accuracy": 0.16479238569736482,
|
|
"num_tokens": 32673763.0,
|
|
"step": 16700
|
|
},
|
|
{
|
|
"entropy": 6.070951318740844,
|
|
"epoch": 1.6698655470585295,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004726511994133235,
|
|
"loss": 5.8007,
|
|
"mean_token_accuracy": 0.16941775232553483,
|
|
"num_tokens": 32683436.0,
|
|
"step": 16705
|
|
},
|
|
{
|
|
"entropy": 6.112431144714355,
|
|
"epoch": 1.670365372119758,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00047263414343609307,
|
|
"loss": 5.774,
|
|
"mean_token_accuracy": 0.1645307183265686,
|
|
"num_tokens": 32692563.0,
|
|
"step": 16710
|
|
},
|
|
{
|
|
"entropy": 6.102208232879638,
|
|
"epoch": 1.6708651971809867,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00047261708248643846,
|
|
"loss": 5.861,
|
|
"mean_token_accuracy": 0.1599726803600788,
|
|
"num_tokens": 32700973.0,
|
|
"step": 16715
|
|
},
|
|
{
|
|
"entropy": 6.050986337661743,
|
|
"epoch": 1.6713650222422152,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004726000165647888,
|
|
"loss": 5.8013,
|
|
"mean_token_accuracy": 0.1739999383687973,
|
|
"num_tokens": 32710299.0,
|
|
"step": 16720
|
|
},
|
|
{
|
|
"entropy": 6.157758140563965,
|
|
"epoch": 1.6718648473034436,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004725829456715737,
|
|
"loss": 5.9079,
|
|
"mean_token_accuracy": 0.1563047409057617,
|
|
"num_tokens": 32719421.0,
|
|
"step": 16725
|
|
},
|
|
{
|
|
"entropy": 6.127217483520508,
|
|
"epoch": 1.6723646723646723,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004725658698072225,
|
|
"loss": 5.873,
|
|
"mean_token_accuracy": 0.16384452134370803,
|
|
"num_tokens": 32729052.0,
|
|
"step": 16730
|
|
},
|
|
{
|
|
"entropy": 6.01908049583435,
|
|
"epoch": 1.672864497425901,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004725487889721648,
|
|
"loss": 5.7503,
|
|
"mean_token_accuracy": 0.17131175249814987,
|
|
"num_tokens": 32738953.0,
|
|
"step": 16735
|
|
},
|
|
{
|
|
"entropy": 6.111048650741577,
|
|
"epoch": 1.6733643224871295,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004725317031668304,
|
|
"loss": 5.8915,
|
|
"mean_token_accuracy": 0.16039555221796037,
|
|
"num_tokens": 32748728.0,
|
|
"step": 16740
|
|
},
|
|
{
|
|
"entropy": 6.138377523422241,
|
|
"epoch": 1.673864147548358,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00047251461239164916,
|
|
"loss": 5.8508,
|
|
"mean_token_accuracy": 0.15747175067663194,
|
|
"num_tokens": 32758305.0,
|
|
"step": 16745
|
|
},
|
|
{
|
|
"entropy": 6.1284078598022464,
|
|
"epoch": 1.6743639726095867,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004724975166470512,
|
|
"loss": 5.8942,
|
|
"mean_token_accuracy": 0.16370432302355767,
|
|
"num_tokens": 32768398.0,
|
|
"step": 16750
|
|
},
|
|
{
|
|
"entropy": 6.089828729629517,
|
|
"epoch": 1.6748637976708152,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004724804159334665,
|
|
"loss": 5.8553,
|
|
"mean_token_accuracy": 0.16417628079652785,
|
|
"num_tokens": 32778970.0,
|
|
"step": 16755
|
|
},
|
|
{
|
|
"entropy": 6.106259679794311,
|
|
"epoch": 1.6753636227320436,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0004724633102513253,
|
|
"loss": 5.7687,
|
|
"mean_token_accuracy": 0.16122331470251083,
|
|
"num_tokens": 32789815.0,
|
|
"step": 16760
|
|
},
|
|
{
|
|
"entropy": 6.133359098434449,
|
|
"epoch": 1.6758634477932723,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004724461996010581,
|
|
"loss": 5.8858,
|
|
"mean_token_accuracy": 0.16086881905794143,
|
|
"num_tokens": 32799378.0,
|
|
"step": 16765
|
|
},
|
|
{
|
|
"entropy": 6.072362184524536,
|
|
"epoch": 1.676363272854501,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004724290839830953,
|
|
"loss": 5.7782,
|
|
"mean_token_accuracy": 0.17221519201993943,
|
|
"num_tokens": 32809380.0,
|
|
"step": 16770
|
|
},
|
|
{
|
|
"entropy": 6.047758960723877,
|
|
"epoch": 1.6768630979157295,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004724119633978675,
|
|
"loss": 5.7789,
|
|
"mean_token_accuracy": 0.169873508810997,
|
|
"num_tokens": 32818645.0,
|
|
"step": 16775
|
|
},
|
|
{
|
|
"entropy": 6.0860795974731445,
|
|
"epoch": 1.677362922976958,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00047239483784580554,
|
|
"loss": 5.8306,
|
|
"mean_token_accuracy": 0.16674723625183105,
|
|
"num_tokens": 32827832.0,
|
|
"step": 16780
|
|
},
|
|
{
|
|
"entropy": 6.174402141571045,
|
|
"epoch": 1.6778627480381867,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004723777073273403,
|
|
"loss": 5.9242,
|
|
"mean_token_accuracy": 0.15221443623304368,
|
|
"num_tokens": 32839312.0,
|
|
"step": 16785
|
|
},
|
|
{
|
|
"entropy": 6.08099331855774,
|
|
"epoch": 1.6783625730994152,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004723605718429026,
|
|
"loss": 5.8051,
|
|
"mean_token_accuracy": 0.16935500651597976,
|
|
"num_tokens": 32849065.0,
|
|
"step": 16790
|
|
},
|
|
{
|
|
"entropy": 6.119829845428467,
|
|
"epoch": 1.6788623981606436,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004723434313929238,
|
|
"loss": 5.8112,
|
|
"mean_token_accuracy": 0.16109203770756722,
|
|
"num_tokens": 32858469.0,
|
|
"step": 16795
|
|
},
|
|
{
|
|
"entropy": 6.135422849655152,
|
|
"epoch": 1.6793622232218723,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00047232628597783507,
|
|
"loss": 5.9151,
|
|
"mean_token_accuracy": 0.15433017909526825,
|
|
"num_tokens": 32868700.0,
|
|
"step": 16800
|
|
},
|
|
{
|
|
"entropy": 6.1444700241088865,
|
|
"epoch": 1.679862048283101,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00047230913559806773,
|
|
"loss": 5.8086,
|
|
"mean_token_accuracy": 0.16680509299039842,
|
|
"num_tokens": 32878403.0,
|
|
"step": 16805
|
|
},
|
|
{
|
|
"entropy": 6.147442960739136,
|
|
"epoch": 1.6803618733443295,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004722919802540533,
|
|
"loss": 5.8986,
|
|
"mean_token_accuracy": 0.15698599070310593,
|
|
"num_tokens": 32888322.0,
|
|
"step": 16810
|
|
},
|
|
{
|
|
"entropy": 6.12728066444397,
|
|
"epoch": 1.680861698405558,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004722748199462234,
|
|
"loss": 5.8635,
|
|
"mean_token_accuracy": 0.159330415725708,
|
|
"num_tokens": 32897170.0,
|
|
"step": 16815
|
|
},
|
|
{
|
|
"entropy": 6.052549552917481,
|
|
"epoch": 1.6813615234667867,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004722576546750098,
|
|
"loss": 5.7042,
|
|
"mean_token_accuracy": 0.17216254025697708,
|
|
"num_tokens": 32906503.0,
|
|
"step": 16820
|
|
},
|
|
{
|
|
"entropy": 6.075279998779297,
|
|
"epoch": 1.6818613485280152,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00047224048444084434,
|
|
"loss": 5.8336,
|
|
"mean_token_accuracy": 0.16550259590148925,
|
|
"num_tokens": 32915723.0,
|
|
"step": 16825
|
|
},
|
|
{
|
|
"entropy": 6.093961572647094,
|
|
"epoch": 1.6823611735892436,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00047222330924415906,
|
|
"loss": 5.9038,
|
|
"mean_token_accuracy": 0.16662451177835463,
|
|
"num_tokens": 32925589.0,
|
|
"step": 16830
|
|
},
|
|
{
|
|
"entropy": 6.1602335453033445,
|
|
"epoch": 1.6828609986504723,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004722061290853862,
|
|
"loss": 5.9084,
|
|
"mean_token_accuracy": 0.1639178767800331,
|
|
"num_tokens": 32935727.0,
|
|
"step": 16835
|
|
},
|
|
{
|
|
"entropy": 6.090109395980835,
|
|
"epoch": 1.683360823711701,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00047218894396495765,
|
|
"loss": 5.8112,
|
|
"mean_token_accuracy": 0.16744061261415483,
|
|
"num_tokens": 32944257.0,
|
|
"step": 16840
|
|
},
|
|
{
|
|
"entropy": 6.109005117416382,
|
|
"epoch": 1.6838606487729295,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004721717538833061,
|
|
"loss": 5.8888,
|
|
"mean_token_accuracy": 0.15798853188753129,
|
|
"num_tokens": 32954341.0,
|
|
"step": 16845
|
|
},
|
|
{
|
|
"entropy": 6.121562433242798,
|
|
"epoch": 1.684360473834158,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.000472154558840864,
|
|
"loss": 5.8541,
|
|
"mean_token_accuracy": 0.16148653477430344,
|
|
"num_tokens": 32963997.0,
|
|
"step": 16850
|
|
},
|
|
{
|
|
"entropy": 6.036176681518555,
|
|
"epoch": 1.6848602988953867,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.000472137358838064,
|
|
"loss": 5.8285,
|
|
"mean_token_accuracy": 0.16132424920797347,
|
|
"num_tokens": 32974301.0,
|
|
"step": 16855
|
|
},
|
|
{
|
|
"entropy": 6.174757575988769,
|
|
"epoch": 1.6853601239566152,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004721201538753387,
|
|
"loss": 5.8774,
|
|
"mean_token_accuracy": 0.15793148055672646,
|
|
"num_tokens": 32983535.0,
|
|
"step": 16860
|
|
},
|
|
{
|
|
"entropy": 6.117872428894043,
|
|
"epoch": 1.6858599490178436,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00047210294395312103,
|
|
"loss": 5.8647,
|
|
"mean_token_accuracy": 0.16725480556488037,
|
|
"num_tokens": 32993392.0,
|
|
"step": 16865
|
|
},
|
|
{
|
|
"entropy": 5.919343948364258,
|
|
"epoch": 1.6863597740790723,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.000472085729071844,
|
|
"loss": 5.592,
|
|
"mean_token_accuracy": 0.18676192611455916,
|
|
"num_tokens": 33002103.0,
|
|
"step": 16870
|
|
},
|
|
{
|
|
"entropy": 6.057176160812378,
|
|
"epoch": 1.686859599140301,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00047206850923194076,
|
|
"loss": 5.8691,
|
|
"mean_token_accuracy": 0.16298008114099502,
|
|
"num_tokens": 33011557.0,
|
|
"step": 16875
|
|
},
|
|
{
|
|
"entropy": 6.165191173553467,
|
|
"epoch": 1.6873594242015295,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00047205128443384456,
|
|
"loss": 5.8753,
|
|
"mean_token_accuracy": 0.16192150712013245,
|
|
"num_tokens": 33021015.0,
|
|
"step": 16880
|
|
},
|
|
{
|
|
"entropy": 6.145686149597168,
|
|
"epoch": 1.687859249262758,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004720340546779887,
|
|
"loss": 5.8274,
|
|
"mean_token_accuracy": 0.16373817920684813,
|
|
"num_tokens": 33029719.0,
|
|
"step": 16885
|
|
},
|
|
{
|
|
"entropy": 6.161823558807373,
|
|
"epoch": 1.6883590743239867,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.0004720168199648068,
|
|
"loss": 5.8898,
|
|
"mean_token_accuracy": 0.15919446796178818,
|
|
"num_tokens": 33039424.0,
|
|
"step": 16890
|
|
},
|
|
{
|
|
"entropy": 6.141677713394165,
|
|
"epoch": 1.6888588993852152,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00047199958029473237,
|
|
"loss": 5.8612,
|
|
"mean_token_accuracy": 0.16170452684164047,
|
|
"num_tokens": 33050175.0,
|
|
"step": 16895
|
|
},
|
|
{
|
|
"entropy": 6.117555856704712,
|
|
"epoch": 1.6893587244464436,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00047198233566819915,
|
|
"loss": 5.8715,
|
|
"mean_token_accuracy": 0.16236645728349686,
|
|
"num_tokens": 33061352.0,
|
|
"step": 16900
|
|
},
|
|
{
|
|
"entropy": 6.137941217422485,
|
|
"epoch": 1.6898585495076723,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004719650860856411,
|
|
"loss": 5.8369,
|
|
"mean_token_accuracy": 0.16249137073755265,
|
|
"num_tokens": 33069946.0,
|
|
"step": 16905
|
|
},
|
|
{
|
|
"entropy": 6.082652997970581,
|
|
"epoch": 1.690358374568901,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00047194783154749217,
|
|
"loss": 5.8216,
|
|
"mean_token_accuracy": 0.16467711627483367,
|
|
"num_tokens": 33078478.0,
|
|
"step": 16910
|
|
},
|
|
{
|
|
"entropy": 6.099985027313233,
|
|
"epoch": 1.6908581996301293,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004719305720541865,
|
|
"loss": 5.7986,
|
|
"mean_token_accuracy": 0.17374778538942337,
|
|
"num_tokens": 33088073.0,
|
|
"step": 16915
|
|
},
|
|
{
|
|
"entropy": 6.059681463241577,
|
|
"epoch": 1.691358024691358,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00047191330760615823,
|
|
"loss": 5.7897,
|
|
"mean_token_accuracy": 0.16655015647411348,
|
|
"num_tokens": 33097127.0,
|
|
"step": 16920
|
|
},
|
|
{
|
|
"entropy": 6.0413487434387205,
|
|
"epoch": 1.6918578497525867,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00047189603820384186,
|
|
"loss": 5.8092,
|
|
"mean_token_accuracy": 0.16877787411212922,
|
|
"num_tokens": 33107250.0,
|
|
"step": 16925
|
|
},
|
|
{
|
|
"entropy": 6.064757776260376,
|
|
"epoch": 1.6923576748138152,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00047187876384767187,
|
|
"loss": 5.815,
|
|
"mean_token_accuracy": 0.1657470151782036,
|
|
"num_tokens": 33117585.0,
|
|
"step": 16930
|
|
},
|
|
{
|
|
"entropy": 6.1313450813293455,
|
|
"epoch": 1.6928574998750436,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00047186148453808274,
|
|
"loss": 5.8251,
|
|
"mean_token_accuracy": 0.16052726805210113,
|
|
"num_tokens": 33127077.0,
|
|
"step": 16935
|
|
},
|
|
{
|
|
"entropy": 6.121941375732422,
|
|
"epoch": 1.6933573249362723,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004718442002755094,
|
|
"loss": 5.8585,
|
|
"mean_token_accuracy": 0.15812154561281205,
|
|
"num_tokens": 33136327.0,
|
|
"step": 16940
|
|
},
|
|
{
|
|
"entropy": 6.081155061721802,
|
|
"epoch": 1.693857149997501,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004718269110603866,
|
|
"loss": 5.7339,
|
|
"mean_token_accuracy": 0.1690545752644539,
|
|
"num_tokens": 33145528.0,
|
|
"step": 16945
|
|
},
|
|
{
|
|
"entropy": 6.0176373481750485,
|
|
"epoch": 1.6943569750587293,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00047180961689314937,
|
|
"loss": 5.8284,
|
|
"mean_token_accuracy": 0.17070186585187913,
|
|
"num_tokens": 33154651.0,
|
|
"step": 16950
|
|
},
|
|
{
|
|
"entropy": 6.047551774978638,
|
|
"epoch": 1.694856800119958,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004717923177742329,
|
|
"loss": 5.8313,
|
|
"mean_token_accuracy": 0.16603592932224273,
|
|
"num_tokens": 33164602.0,
|
|
"step": 16955
|
|
},
|
|
{
|
|
"entropy": 6.192107629776001,
|
|
"epoch": 1.6953566251811867,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00047177501370407223,
|
|
"loss": 5.937,
|
|
"mean_token_accuracy": 0.15762703120708466,
|
|
"num_tokens": 33173534.0,
|
|
"step": 16960
|
|
},
|
|
{
|
|
"entropy": 6.0753912925720215,
|
|
"epoch": 1.6958564502424152,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00047175770468310294,
|
|
"loss": 5.909,
|
|
"mean_token_accuracy": 0.16273582577705384,
|
|
"num_tokens": 33183528.0,
|
|
"step": 16965
|
|
},
|
|
{
|
|
"entropy": 6.213628101348877,
|
|
"epoch": 1.6963562753036436,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00047174039071176037,
|
|
"loss": 5.9708,
|
|
"mean_token_accuracy": 0.14892186373472213,
|
|
"num_tokens": 33193762.0,
|
|
"step": 16970
|
|
},
|
|
{
|
|
"entropy": 6.129265022277832,
|
|
"epoch": 1.6968561003648723,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.00047172307179048025,
|
|
"loss": 5.8195,
|
|
"mean_token_accuracy": 0.16547536998987197,
|
|
"num_tokens": 33203050.0,
|
|
"step": 16975
|
|
},
|
|
{
|
|
"entropy": 6.2035455226898195,
|
|
"epoch": 1.697355925426101,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004717057479196982,
|
|
"loss": 5.9411,
|
|
"mean_token_accuracy": 0.1654243603348732,
|
|
"num_tokens": 33212975.0,
|
|
"step": 16980
|
|
},
|
|
{
|
|
"entropy": 6.145605564117432,
|
|
"epoch": 1.6978557504873293,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004716884190998502,
|
|
"loss": 5.883,
|
|
"mean_token_accuracy": 0.16100297421216964,
|
|
"num_tokens": 33222967.0,
|
|
"step": 16985
|
|
},
|
|
{
|
|
"entropy": 6.132839488983154,
|
|
"epoch": 1.698355575548558,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004716710853313721,
|
|
"loss": 5.8576,
|
|
"mean_token_accuracy": 0.15872777104377747,
|
|
"num_tokens": 33233000.0,
|
|
"step": 16990
|
|
},
|
|
{
|
|
"entropy": 6.2149194240570065,
|
|
"epoch": 1.6988554006097867,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00047165374661470023,
|
|
"loss": 5.9507,
|
|
"mean_token_accuracy": 0.15825337469577788,
|
|
"num_tokens": 33242429.0,
|
|
"step": 16995
|
|
},
|
|
{
|
|
"entropy": 6.135564470291138,
|
|
"epoch": 1.6993552256710152,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00047163640295027064,
|
|
"loss": 5.8569,
|
|
"mean_token_accuracy": 0.1600394919514656,
|
|
"num_tokens": 33252474.0,
|
|
"step": 17000
|
|
},
|
|
{
|
|
"entropy": 6.1082510471344,
|
|
"epoch": 1.6998550507322436,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00047161905433851974,
|
|
"loss": 5.9147,
|
|
"mean_token_accuracy": 0.15451256185770035,
|
|
"num_tokens": 33261296.0,
|
|
"step": 17005
|
|
},
|
|
{
|
|
"entropy": 6.079780912399292,
|
|
"epoch": 1.7003548757934723,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00047160170077988403,
|
|
"loss": 5.7617,
|
|
"mean_token_accuracy": 0.17053687274456025,
|
|
"num_tokens": 33271382.0,
|
|
"step": 17010
|
|
},
|
|
{
|
|
"entropy": 6.172500991821289,
|
|
"epoch": 1.7008547008547008,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004715843422748001,
|
|
"loss": 5.9072,
|
|
"mean_token_accuracy": 0.1569389060139656,
|
|
"num_tokens": 33281512.0,
|
|
"step": 17015
|
|
},
|
|
{
|
|
"entropy": 6.165734052658081,
|
|
"epoch": 1.7013545259159293,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00047156697882370474,
|
|
"loss": 5.8705,
|
|
"mean_token_accuracy": 0.1596240818500519,
|
|
"num_tokens": 33290974.0,
|
|
"step": 17020
|
|
},
|
|
{
|
|
"entropy": 6.131651496887207,
|
|
"epoch": 1.701854350977158,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004715496104270348,
|
|
"loss": 5.9188,
|
|
"mean_token_accuracy": 0.15352497845888138,
|
|
"num_tokens": 33301576.0,
|
|
"step": 17025
|
|
},
|
|
{
|
|
"entropy": 6.056046438217163,
|
|
"epoch": 1.7023541760383867,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004715322370852272,
|
|
"loss": 5.7189,
|
|
"mean_token_accuracy": 0.17549443989992142,
|
|
"num_tokens": 33311277.0,
|
|
"step": 17030
|
|
},
|
|
{
|
|
"entropy": 6.042885684967041,
|
|
"epoch": 1.7028540010996152,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00047151485879871907,
|
|
"loss": 5.8076,
|
|
"mean_token_accuracy": 0.1702376827597618,
|
|
"num_tokens": 33322018.0,
|
|
"step": 17035
|
|
},
|
|
{
|
|
"entropy": 6.114020824432373,
|
|
"epoch": 1.7033538261608436,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00047149747556794763,
|
|
"loss": 5.8814,
|
|
"mean_token_accuracy": 0.16093982458114625,
|
|
"num_tokens": 33331804.0,
|
|
"step": 17040
|
|
},
|
|
{
|
|
"entropy": 6.181418514251709,
|
|
"epoch": 1.7038536512220723,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00047148008739335035,
|
|
"loss": 5.8834,
|
|
"mean_token_accuracy": 0.15723083913326263,
|
|
"num_tokens": 33342014.0,
|
|
"step": 17045
|
|
},
|
|
{
|
|
"entropy": 6.140880680084228,
|
|
"epoch": 1.7043534762833008,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004714626942753646,
|
|
"loss": 5.8291,
|
|
"mean_token_accuracy": 0.1655607968568802,
|
|
"num_tokens": 33352086.0,
|
|
"step": 17050
|
|
},
|
|
{
|
|
"entropy": 6.136274671554565,
|
|
"epoch": 1.7048533013445293,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.000471445296214428,
|
|
"loss": 5.8128,
|
|
"mean_token_accuracy": 0.17023831605911255,
|
|
"num_tokens": 33362067.0,
|
|
"step": 17055
|
|
},
|
|
{
|
|
"entropy": 6.094441556930542,
|
|
"epoch": 1.705353126405758,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00047142789321097834,
|
|
"loss": 5.8324,
|
|
"mean_token_accuracy": 0.16534274369478225,
|
|
"num_tokens": 33371803.0,
|
|
"step": 17060
|
|
},
|
|
{
|
|
"entropy": 6.163855123519897,
|
|
"epoch": 1.7058529514669867,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004714104852654534,
|
|
"loss": 5.8558,
|
|
"mean_token_accuracy": 0.16327501237392425,
|
|
"num_tokens": 33381258.0,
|
|
"step": 17065
|
|
},
|
|
{
|
|
"entropy": 6.136796236038208,
|
|
"epoch": 1.7063527765282152,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004713930723782912,
|
|
"loss": 5.8642,
|
|
"mean_token_accuracy": 0.16078613847494125,
|
|
"num_tokens": 33390709.0,
|
|
"step": 17070
|
|
},
|
|
{
|
|
"entropy": 6.161985063552857,
|
|
"epoch": 1.7068526015894436,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00047137565454992983,
|
|
"loss": 5.8769,
|
|
"mean_token_accuracy": 0.16147163063287734,
|
|
"num_tokens": 33400831.0,
|
|
"step": 17075
|
|
},
|
|
{
|
|
"entropy": 6.119814395904541,
|
|
"epoch": 1.7073524266506723,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00047135823178080745,
|
|
"loss": 5.8329,
|
|
"mean_token_accuracy": 0.1637144520878792,
|
|
"num_tokens": 33410974.0,
|
|
"step": 17080
|
|
},
|
|
{
|
|
"entropy": 6.188448238372803,
|
|
"epoch": 1.7078522517119008,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004713408040713626,
|
|
"loss": 5.9522,
|
|
"mean_token_accuracy": 0.15507494658231735,
|
|
"num_tokens": 33420555.0,
|
|
"step": 17085
|
|
},
|
|
{
|
|
"entropy": 6.145060443878174,
|
|
"epoch": 1.7083520767731293,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00047132337142203365,
|
|
"loss": 5.961,
|
|
"mean_token_accuracy": 0.15563779324293137,
|
|
"num_tokens": 33431064.0,
|
|
"step": 17090
|
|
},
|
|
{
|
|
"entropy": 6.130756139755249,
|
|
"epoch": 1.708851901834358,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004713059338332591,
|
|
"loss": 5.8181,
|
|
"mean_token_accuracy": 0.16710542887449265,
|
|
"num_tokens": 33441223.0,
|
|
"step": 17095
|
|
},
|
|
{
|
|
"entropy": 6.143070459365845,
|
|
"epoch": 1.7093517268955867,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00047128849130547774,
|
|
"loss": 5.8613,
|
|
"mean_token_accuracy": 0.1648654267191887,
|
|
"num_tokens": 33451520.0,
|
|
"step": 17100
|
|
},
|
|
{
|
|
"entropy": 6.07532811164856,
|
|
"epoch": 1.7098515519568152,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00047127104383912856,
|
|
"loss": 5.7956,
|
|
"mean_token_accuracy": 0.16675146520137787,
|
|
"num_tokens": 33461310.0,
|
|
"step": 17105
|
|
},
|
|
{
|
|
"entropy": 6.168755340576172,
|
|
"epoch": 1.7103513770180436,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004712535914346504,
|
|
"loss": 5.9052,
|
|
"mean_token_accuracy": 0.16413626670837403,
|
|
"num_tokens": 33471250.0,
|
|
"step": 17110
|
|
},
|
|
{
|
|
"entropy": 6.093137121200561,
|
|
"epoch": 1.7108512020792723,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00047123613409248233,
|
|
"loss": 5.7793,
|
|
"mean_token_accuracy": 0.16176048517227173,
|
|
"num_tokens": 33480950.0,
|
|
"step": 17115
|
|
},
|
|
{
|
|
"entropy": 6.0771674633026125,
|
|
"epoch": 1.7113510271405008,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00047121867181306365,
|
|
"loss": 5.7401,
|
|
"mean_token_accuracy": 0.16837601065635682,
|
|
"num_tokens": 33490394.0,
|
|
"step": 17120
|
|
},
|
|
{
|
|
"entropy": 6.03310546875,
|
|
"epoch": 1.7118508522017293,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004712012045968337,
|
|
"loss": 5.8518,
|
|
"mean_token_accuracy": 0.15960967242717744,
|
|
"num_tokens": 33500130.0,
|
|
"step": 17125
|
|
},
|
|
{
|
|
"entropy": 6.122752285003662,
|
|
"epoch": 1.712350677262958,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.00047118373244423197,
|
|
"loss": 5.9186,
|
|
"mean_token_accuracy": 0.1663791298866272,
|
|
"num_tokens": 33510698.0,
|
|
"step": 17130
|
|
},
|
|
{
|
|
"entropy": 6.13548903465271,
|
|
"epoch": 1.7128505023241867,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00047116625535569787,
|
|
"loss": 5.8228,
|
|
"mean_token_accuracy": 0.16140831857919694,
|
|
"num_tokens": 33520161.0,
|
|
"step": 17135
|
|
},
|
|
{
|
|
"entropy": 6.0874275207519535,
|
|
"epoch": 1.7133503273854152,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00047114877333167133,
|
|
"loss": 5.8708,
|
|
"mean_token_accuracy": 0.16802819073200226,
|
|
"num_tokens": 33530190.0,
|
|
"step": 17140
|
|
},
|
|
{
|
|
"entropy": 6.1481077671051025,
|
|
"epoch": 1.7138501524466436,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.00047113128637259216,
|
|
"loss": 5.8432,
|
|
"mean_token_accuracy": 0.1689216434955597,
|
|
"num_tokens": 33539376.0,
|
|
"step": 17145
|
|
},
|
|
{
|
|
"entropy": 6.160684633255005,
|
|
"epoch": 1.7143499775078723,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004711137944789003,
|
|
"loss": 5.8371,
|
|
"mean_token_accuracy": 0.16129862517118454,
|
|
"num_tokens": 33549290.0,
|
|
"step": 17150
|
|
},
|
|
{
|
|
"entropy": 6.116025495529175,
|
|
"epoch": 1.7148498025691008,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00047109629765103577,
|
|
"loss": 5.9134,
|
|
"mean_token_accuracy": 0.15745049417018891,
|
|
"num_tokens": 33559483.0,
|
|
"step": 17155
|
|
},
|
|
{
|
|
"entropy": 6.128926372528076,
|
|
"epoch": 1.7153496276303293,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00047107879588943887,
|
|
"loss": 5.8878,
|
|
"mean_token_accuracy": 0.16217012107372283,
|
|
"num_tokens": 33569464.0,
|
|
"step": 17160
|
|
},
|
|
{
|
|
"entropy": 6.2021440982818605,
|
|
"epoch": 1.715849452691558,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00047106128919455,
|
|
"loss": 5.9805,
|
|
"mean_token_accuracy": 0.1558922439813614,
|
|
"num_tokens": 33579759.0,
|
|
"step": 17165
|
|
},
|
|
{
|
|
"entropy": 6.134302759170533,
|
|
"epoch": 1.7163492777527867,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004710437775668094,
|
|
"loss": 5.817,
|
|
"mean_token_accuracy": 0.16416923701763153,
|
|
"num_tokens": 33590054.0,
|
|
"step": 17170
|
|
},
|
|
{
|
|
"entropy": 6.088890266418457,
|
|
"epoch": 1.7168491028140151,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004710262610066579,
|
|
"loss": 5.8138,
|
|
"mean_token_accuracy": 0.16810918152332305,
|
|
"num_tokens": 33600014.0,
|
|
"step": 17175
|
|
},
|
|
{
|
|
"entropy": 6.166955947875977,
|
|
"epoch": 1.7173489278752436,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00047100873951453617,
|
|
"loss": 5.8297,
|
|
"mean_token_accuracy": 0.16101797074079513,
|
|
"num_tokens": 33609579.0,
|
|
"step": 17180
|
|
},
|
|
{
|
|
"entropy": 6.159162187576294,
|
|
"epoch": 1.7178487529364723,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00047099121309088487,
|
|
"loss": 5.8983,
|
|
"mean_token_accuracy": 0.15850197076797484,
|
|
"num_tokens": 33618082.0,
|
|
"step": 17185
|
|
},
|
|
{
|
|
"entropy": 6.064070224761963,
|
|
"epoch": 1.7183485779977008,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.00047097368173614515,
|
|
"loss": 5.8657,
|
|
"mean_token_accuracy": 0.16142818331718445,
|
|
"num_tokens": 33627835.0,
|
|
"step": 17190
|
|
},
|
|
{
|
|
"entropy": 6.100105476379395,
|
|
"epoch": 1.7188484030589293,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00047095614545075807,
|
|
"loss": 5.8664,
|
|
"mean_token_accuracy": 0.1596950702369213,
|
|
"num_tokens": 33638187.0,
|
|
"step": 17195
|
|
},
|
|
{
|
|
"entropy": 6.195778179168701,
|
|
"epoch": 1.719348228120158,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004709386042351647,
|
|
"loss": 5.8594,
|
|
"mean_token_accuracy": 0.15646356642246245,
|
|
"num_tokens": 33647805.0,
|
|
"step": 17200
|
|
},
|
|
{
|
|
"entropy": 6.154709768295288,
|
|
"epoch": 1.7198480531813867,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004709210580898065,
|
|
"loss": 5.8642,
|
|
"mean_token_accuracy": 0.16096559017896653,
|
|
"num_tokens": 33656657.0,
|
|
"step": 17205
|
|
},
|
|
{
|
|
"entropy": 6.091437816619873,
|
|
"epoch": 1.720347878242615,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004709035070151249,
|
|
"loss": 5.8149,
|
|
"mean_token_accuracy": 0.16366640329360962,
|
|
"num_tokens": 33666025.0,
|
|
"step": 17210
|
|
},
|
|
{
|
|
"entropy": 6.074840974807739,
|
|
"epoch": 1.7208477033038436,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004708859510115614,
|
|
"loss": 5.7601,
|
|
"mean_token_accuracy": 0.16853323727846145,
|
|
"num_tokens": 33676378.0,
|
|
"step": 17215
|
|
},
|
|
{
|
|
"entropy": 6.252654695510865,
|
|
"epoch": 1.7213475283650723,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004708683900795579,
|
|
"loss": 5.9689,
|
|
"mean_token_accuracy": 0.15362064391374589,
|
|
"num_tokens": 33685899.0,
|
|
"step": 17220
|
|
},
|
|
{
|
|
"entropy": 6.159629917144775,
|
|
"epoch": 1.7218473534263008,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00047085082421955603,
|
|
"loss": 5.8592,
|
|
"mean_token_accuracy": 0.16372107863426208,
|
|
"num_tokens": 33696155.0,
|
|
"step": 17225
|
|
},
|
|
{
|
|
"entropy": 6.165194272994995,
|
|
"epoch": 1.7223471784875293,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00047083325343199786,
|
|
"loss": 5.8627,
|
|
"mean_token_accuracy": 0.16175238341093062,
|
|
"num_tokens": 33704685.0,
|
|
"step": 17230
|
|
},
|
|
{
|
|
"entropy": 6.229802894592285,
|
|
"epoch": 1.722847003548758,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004708156777173254,
|
|
"loss": 5.9696,
|
|
"mean_token_accuracy": 0.15388983786106109,
|
|
"num_tokens": 33715189.0,
|
|
"step": 17235
|
|
},
|
|
{
|
|
"entropy": 6.135674381256104,
|
|
"epoch": 1.7233468286099867,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004707980970759809,
|
|
"loss": 5.8647,
|
|
"mean_token_accuracy": 0.16149176359176637,
|
|
"num_tokens": 33724619.0,
|
|
"step": 17240
|
|
},
|
|
{
|
|
"entropy": 6.1062451839447025,
|
|
"epoch": 1.723846653671215,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.00047078051150840666,
|
|
"loss": 5.8523,
|
|
"mean_token_accuracy": 0.1665616363286972,
|
|
"num_tokens": 33734371.0,
|
|
"step": 17245
|
|
},
|
|
{
|
|
"entropy": 6.038412284851074,
|
|
"epoch": 1.7243464787324436,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004707629210150451,
|
|
"loss": 5.7953,
|
|
"mean_token_accuracy": 0.1671959176659584,
|
|
"num_tokens": 33743592.0,
|
|
"step": 17250
|
|
},
|
|
{
|
|
"entropy": 6.1577225685119625,
|
|
"epoch": 1.7248463037936723,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.0004707453255963388,
|
|
"loss": 5.8399,
|
|
"mean_token_accuracy": 0.1666915476322174,
|
|
"num_tokens": 33753686.0,
|
|
"step": 17255
|
|
},
|
|
{
|
|
"entropy": 6.1662595748901365,
|
|
"epoch": 1.7253461288549008,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00047072772525273053,
|
|
"loss": 5.912,
|
|
"mean_token_accuracy": 0.16065869629383087,
|
|
"num_tokens": 33763076.0,
|
|
"step": 17260
|
|
},
|
|
{
|
|
"entropy": 6.032483291625977,
|
|
"epoch": 1.7258459539161293,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.00047071011998466304,
|
|
"loss": 5.6985,
|
|
"mean_token_accuracy": 0.1735437273979187,
|
|
"num_tokens": 33772283.0,
|
|
"step": 17265
|
|
},
|
|
{
|
|
"entropy": 6.096075439453125,
|
|
"epoch": 1.726345778977358,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.00047069250979257934,
|
|
"loss": 5.7943,
|
|
"mean_token_accuracy": 0.16639554053544997,
|
|
"num_tokens": 33782208.0,
|
|
"step": 17270
|
|
},
|
|
{
|
|
"entropy": 6.039402055740356,
|
|
"epoch": 1.7268456040385864,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.00047067489467692236,
|
|
"loss": 5.7735,
|
|
"mean_token_accuracy": 0.17472267523407936,
|
|
"num_tokens": 33792048.0,
|
|
"step": 17275
|
|
},
|
|
{
|
|
"entropy": 6.017827701568604,
|
|
"epoch": 1.727345429099815,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004706572746381354,
|
|
"loss": 5.8265,
|
|
"mean_token_accuracy": 0.1701744467020035,
|
|
"num_tokens": 33800903.0,
|
|
"step": 17280
|
|
},
|
|
{
|
|
"entropy": 6.10653657913208,
|
|
"epoch": 1.7278452541610436,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00047063964967666177,
|
|
"loss": 5.8701,
|
|
"mean_token_accuracy": 0.1601317122578621,
|
|
"num_tokens": 33810575.0,
|
|
"step": 17285
|
|
},
|
|
{
|
|
"entropy": 6.050252437591553,
|
|
"epoch": 1.7283450792222723,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004706220197929449,
|
|
"loss": 5.7935,
|
|
"mean_token_accuracy": 0.16602483093738557,
|
|
"num_tokens": 33819365.0,
|
|
"step": 17290
|
|
},
|
|
{
|
|
"entropy": 6.167187690734863,
|
|
"epoch": 1.7288449042835008,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004706043849874284,
|
|
"loss": 5.9259,
|
|
"mean_token_accuracy": 0.1592279002070427,
|
|
"num_tokens": 33828941.0,
|
|
"step": 17295
|
|
},
|
|
{
|
|
"entropy": 6.104386949539185,
|
|
"epoch": 1.7293447293447293,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.00047058674526055585,
|
|
"loss": 5.8333,
|
|
"mean_token_accuracy": 0.16255820840597152,
|
|
"num_tokens": 33838700.0,
|
|
"step": 17300
|
|
},
|
|
{
|
|
"entropy": 6.183803081512451,
|
|
"epoch": 1.729844554405958,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00047056910061277115,
|
|
"loss": 5.8674,
|
|
"mean_token_accuracy": 0.1564794175326824,
|
|
"num_tokens": 33848592.0,
|
|
"step": 17305
|
|
},
|
|
{
|
|
"entropy": 6.124628639221191,
|
|
"epoch": 1.7303443794671864,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004705514510445182,
|
|
"loss": 5.8451,
|
|
"mean_token_accuracy": 0.16737015545368195,
|
|
"num_tokens": 33858037.0,
|
|
"step": 17310
|
|
},
|
|
{
|
|
"entropy": 6.119843816757202,
|
|
"epoch": 1.730844204528415,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.000470533796556241,
|
|
"loss": 5.9123,
|
|
"mean_token_accuracy": 0.1630480632185936,
|
|
"num_tokens": 33867284.0,
|
|
"step": 17315
|
|
},
|
|
{
|
|
"entropy": 6.113216209411621,
|
|
"epoch": 1.7313440295896436,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004705161371483839,
|
|
"loss": 5.7946,
|
|
"mean_token_accuracy": 0.16674706041812898,
|
|
"num_tokens": 33876006.0,
|
|
"step": 17320
|
|
},
|
|
{
|
|
"entropy": 6.061402988433838,
|
|
"epoch": 1.7318438546508723,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00047049847282139095,
|
|
"loss": 5.6878,
|
|
"mean_token_accuracy": 0.17149617969989778,
|
|
"num_tokens": 33885273.0,
|
|
"step": 17325
|
|
},
|
|
{
|
|
"entropy": 6.191039419174194,
|
|
"epoch": 1.7323436797121008,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00047048080357570685,
|
|
"loss": 5.9288,
|
|
"mean_token_accuracy": 0.15592167973518373,
|
|
"num_tokens": 33894332.0,
|
|
"step": 17330
|
|
},
|
|
{
|
|
"entropy": 6.11606183052063,
|
|
"epoch": 1.7328435047733293,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.000470463129411776,
|
|
"loss": 5.8082,
|
|
"mean_token_accuracy": 0.1665389597415924,
|
|
"num_tokens": 33903556.0,
|
|
"step": 17335
|
|
},
|
|
{
|
|
"entropy": 6.209295797348022,
|
|
"epoch": 1.733343329834558,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004704454503300431,
|
|
"loss": 5.991,
|
|
"mean_token_accuracy": 0.14674981981515883,
|
|
"num_tokens": 33913129.0,
|
|
"step": 17340
|
|
},
|
|
{
|
|
"entropy": 6.107484531402588,
|
|
"epoch": 1.7338431548957864,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.000470427766330953,
|
|
"loss": 5.8705,
|
|
"mean_token_accuracy": 0.1660257324576378,
|
|
"num_tokens": 33923016.0,
|
|
"step": 17345
|
|
},
|
|
{
|
|
"entropy": 6.169083833694458,
|
|
"epoch": 1.734342979957015,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004704100774149506,
|
|
"loss": 5.8279,
|
|
"mean_token_accuracy": 0.16138252019882202,
|
|
"num_tokens": 33932336.0,
|
|
"step": 17350
|
|
},
|
|
{
|
|
"entropy": 6.20218300819397,
|
|
"epoch": 1.7348428050182436,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00047039238358248086,
|
|
"loss": 5.8502,
|
|
"mean_token_accuracy": 0.1620868667960167,
|
|
"num_tokens": 33941488.0,
|
|
"step": 17355
|
|
},
|
|
{
|
|
"entropy": 6.077953147888183,
|
|
"epoch": 1.7353426300794723,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.000470374684833989,
|
|
"loss": 5.6988,
|
|
"mean_token_accuracy": 0.17255197316408158,
|
|
"num_tokens": 33950919.0,
|
|
"step": 17360
|
|
},
|
|
{
|
|
"entropy": 6.028074169158936,
|
|
"epoch": 1.7358424551407008,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004703569811699205,
|
|
"loss": 5.7531,
|
|
"mean_token_accuracy": 0.17374650835990907,
|
|
"num_tokens": 33960609.0,
|
|
"step": 17365
|
|
},
|
|
{
|
|
"entropy": 6.146865749359131,
|
|
"epoch": 1.7363422802019293,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00047033927259072046,
|
|
"loss": 5.8988,
|
|
"mean_token_accuracy": 0.15924923568964006,
|
|
"num_tokens": 33970454.0,
|
|
"step": 17370
|
|
},
|
|
{
|
|
"entropy": 6.0890239715576175,
|
|
"epoch": 1.736842105263158,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.00047032155909683464,
|
|
"loss": 5.7684,
|
|
"mean_token_accuracy": 0.16922948509454727,
|
|
"num_tokens": 33979029.0,
|
|
"step": 17375
|
|
},
|
|
{
|
|
"entropy": 6.236788368225097,
|
|
"epoch": 1.7373419303243864,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004703038406887087,
|
|
"loss": 5.9959,
|
|
"mean_token_accuracy": 0.150369743257761,
|
|
"num_tokens": 33990525.0,
|
|
"step": 17380
|
|
},
|
|
{
|
|
"entropy": 6.100458240509033,
|
|
"epoch": 1.737841755385615,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00047028611736678837,
|
|
"loss": 5.792,
|
|
"mean_token_accuracy": 0.17331325113773347,
|
|
"num_tokens": 34000022.0,
|
|
"step": 17385
|
|
},
|
|
{
|
|
"entropy": 6.091656732559204,
|
|
"epoch": 1.7383415804468436,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004702683891315196,
|
|
"loss": 5.8964,
|
|
"mean_token_accuracy": 0.15669012516736985,
|
|
"num_tokens": 34010082.0,
|
|
"step": 17390
|
|
},
|
|
{
|
|
"entropy": 6.137772130966186,
|
|
"epoch": 1.7388414055080723,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00047025065598334834,
|
|
"loss": 5.8516,
|
|
"mean_token_accuracy": 0.15300845205783845,
|
|
"num_tokens": 34020245.0,
|
|
"step": 17395
|
|
},
|
|
{
|
|
"entropy": 6.127038383483887,
|
|
"epoch": 1.7393412305693008,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004702329179227208,
|
|
"loss": 5.8408,
|
|
"mean_token_accuracy": 0.15858988016843795,
|
|
"num_tokens": 34029359.0,
|
|
"step": 17400
|
|
},
|
|
{
|
|
"entropy": 6.2134583473205565,
|
|
"epoch": 1.7398410556305293,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00047021517495008335,
|
|
"loss": 5.8837,
|
|
"mean_token_accuracy": 0.15703776627779006,
|
|
"num_tokens": 34039778.0,
|
|
"step": 17405
|
|
},
|
|
{
|
|
"entropy": 6.170652770996094,
|
|
"epoch": 1.740340880691758,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00047019742706588233,
|
|
"loss": 5.932,
|
|
"mean_token_accuracy": 0.15969896763563157,
|
|
"num_tokens": 34050102.0,
|
|
"step": 17410
|
|
},
|
|
{
|
|
"entropy": 6.129020404815674,
|
|
"epoch": 1.7408407057529864,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004701796742705642,
|
|
"loss": 5.7895,
|
|
"mean_token_accuracy": 0.1681482821702957,
|
|
"num_tokens": 34059292.0,
|
|
"step": 17415
|
|
},
|
|
{
|
|
"entropy": 6.115680456161499,
|
|
"epoch": 1.741340530814215,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00047016191656457573,
|
|
"loss": 5.8766,
|
|
"mean_token_accuracy": 0.1602344885468483,
|
|
"num_tokens": 34068547.0,
|
|
"step": 17420
|
|
},
|
|
{
|
|
"entropy": 6.0543890476226805,
|
|
"epoch": 1.7418403558754436,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00047014415394836374,
|
|
"loss": 5.7789,
|
|
"mean_token_accuracy": 0.16812487691640854,
|
|
"num_tokens": 34078142.0,
|
|
"step": 17425
|
|
},
|
|
{
|
|
"entropy": 6.086417865753174,
|
|
"epoch": 1.7423401809366723,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004701263864223749,
|
|
"loss": 5.8535,
|
|
"mean_token_accuracy": 0.15521161556243895,
|
|
"num_tokens": 34087780.0,
|
|
"step": 17430
|
|
},
|
|
{
|
|
"entropy": 6.19147801399231,
|
|
"epoch": 1.7428400059979008,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004701086139870565,
|
|
"loss": 5.9054,
|
|
"mean_token_accuracy": 0.1536896988749504,
|
|
"num_tokens": 34097988.0,
|
|
"step": 17435
|
|
},
|
|
{
|
|
"entropy": 6.155747938156128,
|
|
"epoch": 1.7433398310591293,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004700908366428556,
|
|
"loss": 5.8751,
|
|
"mean_token_accuracy": 0.15489028245210648,
|
|
"num_tokens": 34107310.0,
|
|
"step": 17440
|
|
},
|
|
{
|
|
"entropy": 6.193790340423584,
|
|
"epoch": 1.743839656120358,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004700730543902194,
|
|
"loss": 5.957,
|
|
"mean_token_accuracy": 0.15726105570793153,
|
|
"num_tokens": 34117063.0,
|
|
"step": 17445
|
|
},
|
|
{
|
|
"entropy": 6.057797145843506,
|
|
"epoch": 1.7443394811815864,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00047005526722959537,
|
|
"loss": 5.8048,
|
|
"mean_token_accuracy": 0.16806154251098632,
|
|
"num_tokens": 34125391.0,
|
|
"step": 17450
|
|
},
|
|
{
|
|
"entropy": 6.066979503631591,
|
|
"epoch": 1.744839306242815,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00047003747516143095,
|
|
"loss": 5.902,
|
|
"mean_token_accuracy": 0.15875881314277648,
|
|
"num_tokens": 34135816.0,
|
|
"step": 17455
|
|
},
|
|
{
|
|
"entropy": 6.14509015083313,
|
|
"epoch": 1.7453391313040436,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00047001967818617385,
|
|
"loss": 5.9288,
|
|
"mean_token_accuracy": 0.15735705941915512,
|
|
"num_tokens": 34146366.0,
|
|
"step": 17460
|
|
},
|
|
{
|
|
"entropy": 6.194706964492798,
|
|
"epoch": 1.7458389563652723,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004700018763042719,
|
|
"loss": 5.8572,
|
|
"mean_token_accuracy": 0.15940831750631332,
|
|
"num_tokens": 34155982.0,
|
|
"step": 17465
|
|
},
|
|
{
|
|
"entropy": 6.154786539077759,
|
|
"epoch": 1.7463387814265006,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004699840695161728,
|
|
"loss": 5.8951,
|
|
"mean_token_accuracy": 0.16209059804677964,
|
|
"num_tokens": 34164808.0,
|
|
"step": 17470
|
|
},
|
|
{
|
|
"entropy": 6.059711742401123,
|
|
"epoch": 1.7468386064877293,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004699662578223248,
|
|
"loss": 5.7937,
|
|
"mean_token_accuracy": 0.1725698485970497,
|
|
"num_tokens": 34174010.0,
|
|
"step": 17475
|
|
},
|
|
{
|
|
"entropy": 6.110303211212158,
|
|
"epoch": 1.747338431548958,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00046994844122317587,
|
|
"loss": 5.779,
|
|
"mean_token_accuracy": 0.16369424313306807,
|
|
"num_tokens": 34183116.0,
|
|
"step": 17480
|
|
},
|
|
{
|
|
"entropy": 6.11467752456665,
|
|
"epoch": 1.7478382566101864,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00046993061971917433,
|
|
"loss": 5.8482,
|
|
"mean_token_accuracy": 0.1702541619539261,
|
|
"num_tokens": 34191976.0,
|
|
"step": 17485
|
|
},
|
|
{
|
|
"entropy": 6.120127725601196,
|
|
"epoch": 1.748338081671415,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00046991279331076865,
|
|
"loss": 5.8731,
|
|
"mean_token_accuracy": 0.16079101860523223,
|
|
"num_tokens": 34200211.0,
|
|
"step": 17490
|
|
},
|
|
{
|
|
"entropy": 6.126020050048828,
|
|
"epoch": 1.7488379067326436,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004698949619984071,
|
|
"loss": 5.8616,
|
|
"mean_token_accuracy": 0.1645189106464386,
|
|
"num_tokens": 34210392.0,
|
|
"step": 17495
|
|
},
|
|
{
|
|
"entropy": 6.108590126037598,
|
|
"epoch": 1.7493377317938723,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004698771257825385,
|
|
"loss": 5.8566,
|
|
"mean_token_accuracy": 0.1622546821832657,
|
|
"num_tokens": 34220139.0,
|
|
"step": 17500
|
|
},
|
|
{
|
|
"entropy": 6.118734216690063,
|
|
"epoch": 1.7498375568551006,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004698592846636116,
|
|
"loss": 5.8708,
|
|
"mean_token_accuracy": 0.16140561252832414,
|
|
"num_tokens": 34230413.0,
|
|
"step": 17505
|
|
},
|
|
{
|
|
"entropy": 6.045577764511108,
|
|
"epoch": 1.7503373819163293,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004698414386420752,
|
|
"loss": 5.885,
|
|
"mean_token_accuracy": 0.1680714726448059,
|
|
"num_tokens": 34240312.0,
|
|
"step": 17510
|
|
},
|
|
{
|
|
"entropy": 6.120620679855347,
|
|
"epoch": 1.750837206977558,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004698235877183784,
|
|
"loss": 5.8959,
|
|
"mean_token_accuracy": 0.15875301361083985,
|
|
"num_tokens": 34250043.0,
|
|
"step": 17515
|
|
},
|
|
{
|
|
"entropy": 6.173157119750977,
|
|
"epoch": 1.7513370320387864,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00046980573189297017,
|
|
"loss": 5.8513,
|
|
"mean_token_accuracy": 0.1642141193151474,
|
|
"num_tokens": 34259424.0,
|
|
"step": 17520
|
|
},
|
|
{
|
|
"entropy": 6.1149389266967775,
|
|
"epoch": 1.751836857100015,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004697878711662999,
|
|
"loss": 5.8156,
|
|
"mean_token_accuracy": 0.16539095640182494,
|
|
"num_tokens": 34268133.0,
|
|
"step": 17525
|
|
},
|
|
{
|
|
"entropy": 6.071035623550415,
|
|
"epoch": 1.7523366821612436,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00046977000553881696,
|
|
"loss": 5.8432,
|
|
"mean_token_accuracy": 0.1641629531979561,
|
|
"num_tokens": 34277090.0,
|
|
"step": 17530
|
|
},
|
|
{
|
|
"entropy": 6.099884843826294,
|
|
"epoch": 1.752836507222472,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00046975213501097076,
|
|
"loss": 5.8367,
|
|
"mean_token_accuracy": 0.1652570128440857,
|
|
"num_tokens": 34285684.0,
|
|
"step": 17535
|
|
},
|
|
{
|
|
"entropy": 6.064550256729126,
|
|
"epoch": 1.7533363322837006,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004697342595832109,
|
|
"loss": 5.7157,
|
|
"mean_token_accuracy": 0.17021902054548263,
|
|
"num_tokens": 34294483.0,
|
|
"step": 17540
|
|
},
|
|
{
|
|
"entropy": 6.109165382385254,
|
|
"epoch": 1.7538361573449293,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00046971637925598725,
|
|
"loss": 5.8277,
|
|
"mean_token_accuracy": 0.16380289644002916,
|
|
"num_tokens": 34303027.0,
|
|
"step": 17545
|
|
},
|
|
{
|
|
"entropy": 6.145949840545654,
|
|
"epoch": 1.754335982406158,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004696984940297496,
|
|
"loss": 5.8676,
|
|
"mean_token_accuracy": 0.15415992587804794,
|
|
"num_tokens": 34313034.0,
|
|
"step": 17550
|
|
},
|
|
{
|
|
"entropy": 6.063510322570801,
|
|
"epoch": 1.7548358074673864,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.000469680603904948,
|
|
"loss": 5.8161,
|
|
"mean_token_accuracy": 0.16809021830558776,
|
|
"num_tokens": 34323345.0,
|
|
"step": 17555
|
|
},
|
|
{
|
|
"entropy": 6.073070096969604,
|
|
"epoch": 1.755335632528615,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00046966270888203237,
|
|
"loss": 5.8427,
|
|
"mean_token_accuracy": 0.16222451031208038,
|
|
"num_tokens": 34332273.0,
|
|
"step": 17560
|
|
},
|
|
{
|
|
"entropy": 6.20688157081604,
|
|
"epoch": 1.7558354575898436,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004696448089614532,
|
|
"loss": 5.924,
|
|
"mean_token_accuracy": 0.16014135926961898,
|
|
"num_tokens": 34342071.0,
|
|
"step": 17565
|
|
},
|
|
{
|
|
"entropy": 6.10514817237854,
|
|
"epoch": 1.756335282651072,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004696269041436606,
|
|
"loss": 5.7223,
|
|
"mean_token_accuracy": 0.1719916433095932,
|
|
"num_tokens": 34352204.0,
|
|
"step": 17570
|
|
},
|
|
{
|
|
"entropy": 6.034449434280395,
|
|
"epoch": 1.7568351077123006,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004696089944291052,
|
|
"loss": 5.7745,
|
|
"mean_token_accuracy": 0.1708928555250168,
|
|
"num_tokens": 34362033.0,
|
|
"step": 17575
|
|
},
|
|
{
|
|
"entropy": 6.141708326339722,
|
|
"epoch": 1.7573349327735293,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004695910798182377,
|
|
"loss": 5.8597,
|
|
"mean_token_accuracy": 0.1637091413140297,
|
|
"num_tokens": 34371770.0,
|
|
"step": 17580
|
|
},
|
|
{
|
|
"entropy": 6.117165613174438,
|
|
"epoch": 1.757834757834758,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004695731603115086,
|
|
"loss": 5.8811,
|
|
"mean_token_accuracy": 0.16035598814487456,
|
|
"num_tokens": 34381755.0,
|
|
"step": 17585
|
|
},
|
|
{
|
|
"entropy": 6.059657001495362,
|
|
"epoch": 1.7583345828959864,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.00046955523590936884,
|
|
"loss": 5.7773,
|
|
"mean_token_accuracy": 0.1669861450791359,
|
|
"num_tokens": 34390909.0,
|
|
"step": 17590
|
|
},
|
|
{
|
|
"entropy": 6.1609423637390135,
|
|
"epoch": 1.758834407957215,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004695373066122694,
|
|
"loss": 5.8754,
|
|
"mean_token_accuracy": 0.16121077090501784,
|
|
"num_tokens": 34401051.0,
|
|
"step": 17595
|
|
},
|
|
{
|
|
"entropy": 6.174912166595459,
|
|
"epoch": 1.7593342330184436,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004695193724206615,
|
|
"loss": 5.8877,
|
|
"mean_token_accuracy": 0.16476171165704728,
|
|
"num_tokens": 34410099.0,
|
|
"step": 17600
|
|
},
|
|
{
|
|
"entropy": 6.091646194458008,
|
|
"epoch": 1.759834058079672,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00046950143333499613,
|
|
"loss": 5.7982,
|
|
"mean_token_accuracy": 0.15888398587703706,
|
|
"num_tokens": 34418895.0,
|
|
"step": 17605
|
|
},
|
|
{
|
|
"entropy": 6.0000206470489506,
|
|
"epoch": 1.7603338831409006,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00046948348935572476,
|
|
"loss": 5.8475,
|
|
"mean_token_accuracy": 0.16446249485015868,
|
|
"num_tokens": 34429369.0,
|
|
"step": 17610
|
|
},
|
|
{
|
|
"entropy": 6.119893503189087,
|
|
"epoch": 1.7608337082021293,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004694655404832988,
|
|
"loss": 5.8955,
|
|
"mean_token_accuracy": 0.16525406241416932,
|
|
"num_tokens": 34439773.0,
|
|
"step": 17615
|
|
},
|
|
{
|
|
"entropy": 6.2512036800384525,
|
|
"epoch": 1.761333533263358,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00046944758671817,
|
|
"loss": 5.9273,
|
|
"mean_token_accuracy": 0.15854718908667564,
|
|
"num_tokens": 34450613.0,
|
|
"step": 17620
|
|
},
|
|
{
|
|
"entropy": 6.173658990859986,
|
|
"epoch": 1.7618333583245864,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004694296280607899,
|
|
"loss": 5.9216,
|
|
"mean_token_accuracy": 0.16239755749702453,
|
|
"num_tokens": 34460785.0,
|
|
"step": 17625
|
|
},
|
|
{
|
|
"entropy": 6.247310495376587,
|
|
"epoch": 1.762333183385815,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004694116645116104,
|
|
"loss": 5.9591,
|
|
"mean_token_accuracy": 0.1549449719488621,
|
|
"num_tokens": 34471152.0,
|
|
"step": 17630
|
|
},
|
|
{
|
|
"entropy": 6.099266815185547,
|
|
"epoch": 1.7628330084470436,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004693936960710834,
|
|
"loss": 5.7747,
|
|
"mean_token_accuracy": 0.1703835666179657,
|
|
"num_tokens": 34481511.0,
|
|
"step": 17635
|
|
},
|
|
{
|
|
"entropy": 6.078824377059936,
|
|
"epoch": 1.763332833508272,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00046937572273966104,
|
|
"loss": 5.8402,
|
|
"mean_token_accuracy": 0.1673873782157898,
|
|
"num_tokens": 34490556.0,
|
|
"step": 17640
|
|
},
|
|
{
|
|
"entropy": 6.092703866958618,
|
|
"epoch": 1.7638326585695006,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00046935774451779556,
|
|
"loss": 5.8343,
|
|
"mean_token_accuracy": 0.1668176457285881,
|
|
"num_tokens": 34500363.0,
|
|
"step": 17645
|
|
},
|
|
{
|
|
"entropy": 6.059854030609131,
|
|
"epoch": 1.7643324836307293,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004693397614059392,
|
|
"loss": 5.8336,
|
|
"mean_token_accuracy": 0.16878130286931992,
|
|
"num_tokens": 34511009.0,
|
|
"step": 17650
|
|
},
|
|
{
|
|
"entropy": 6.228938055038452,
|
|
"epoch": 1.764832308691958,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004693217734045445,
|
|
"loss": 5.8986,
|
|
"mean_token_accuracy": 0.1588161088526249,
|
|
"num_tokens": 34520806.0,
|
|
"step": 17655
|
|
},
|
|
{
|
|
"entropy": 6.191421699523926,
|
|
"epoch": 1.7653321337531864,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00046930378051406393,
|
|
"loss": 5.8236,
|
|
"mean_token_accuracy": 0.16540293842554094,
|
|
"num_tokens": 34531266.0,
|
|
"step": 17660
|
|
},
|
|
{
|
|
"entropy": 6.235346078872681,
|
|
"epoch": 1.765831958814415,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00046928578273495026,
|
|
"loss": 5.9887,
|
|
"mean_token_accuracy": 0.15136819034814836,
|
|
"num_tokens": 34542503.0,
|
|
"step": 17665
|
|
},
|
|
{
|
|
"entropy": 6.144253969192505,
|
|
"epoch": 1.7663317838756436,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004692677800676563,
|
|
"loss": 5.8656,
|
|
"mean_token_accuracy": 0.1645709827542305,
|
|
"num_tokens": 34552639.0,
|
|
"step": 17670
|
|
},
|
|
{
|
|
"entropy": 6.04638147354126,
|
|
"epoch": 1.766831608936872,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00046924977251263495,
|
|
"loss": 5.7821,
|
|
"mean_token_accuracy": 0.16980100274086,
|
|
"num_tokens": 34562411.0,
|
|
"step": 17675
|
|
},
|
|
{
|
|
"entropy": 6.083621311187744,
|
|
"epoch": 1.7673314339981006,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.00046923176007033937,
|
|
"loss": 5.8471,
|
|
"mean_token_accuracy": 0.16053920984268188,
|
|
"num_tokens": 34571532.0,
|
|
"step": 17680
|
|
},
|
|
{
|
|
"entropy": 6.131117677688598,
|
|
"epoch": 1.7678312590593293,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00046921374274122265,
|
|
"loss": 5.7707,
|
|
"mean_token_accuracy": 0.16452214270830154,
|
|
"num_tokens": 34580338.0,
|
|
"step": 17685
|
|
},
|
|
{
|
|
"entropy": 6.041928291320801,
|
|
"epoch": 1.768331084120558,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00046919572052573814,
|
|
"loss": 5.7905,
|
|
"mean_token_accuracy": 0.16990778148174285,
|
|
"num_tokens": 34589353.0,
|
|
"step": 17690
|
|
},
|
|
{
|
|
"entropy": 6.162481212615967,
|
|
"epoch": 1.7688309091817864,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.00046917769342433925,
|
|
"loss": 5.9723,
|
|
"mean_token_accuracy": 0.16018515080213547,
|
|
"num_tokens": 34599981.0,
|
|
"step": 17695
|
|
},
|
|
{
|
|
"entropy": 6.068850708007813,
|
|
"epoch": 1.769330734243015,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004691596614374796,
|
|
"loss": 5.6985,
|
|
"mean_token_accuracy": 0.1741074427962303,
|
|
"num_tokens": 34608927.0,
|
|
"step": 17700
|
|
},
|
|
{
|
|
"entropy": 6.127185678482055,
|
|
"epoch": 1.7698305593042436,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004691416245656128,
|
|
"loss": 5.8698,
|
|
"mean_token_accuracy": 0.15983858406543733,
|
|
"num_tokens": 34619455.0,
|
|
"step": 17705
|
|
},
|
|
{
|
|
"entropy": 6.1132001876831055,
|
|
"epoch": 1.770330384365472,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00046912358280919267,
|
|
"loss": 5.7504,
|
|
"mean_token_accuracy": 0.1665702134370804,
|
|
"num_tokens": 34628761.0,
|
|
"step": 17710
|
|
},
|
|
{
|
|
"entropy": 6.102512407302856,
|
|
"epoch": 1.7708302094267006,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00046910553616867314,
|
|
"loss": 5.8856,
|
|
"mean_token_accuracy": 0.15870064944028855,
|
|
"num_tokens": 34638859.0,
|
|
"step": 17715
|
|
},
|
|
{
|
|
"entropy": 6.043902397155762,
|
|
"epoch": 1.7713300344879293,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004690874846445083,
|
|
"loss": 5.7589,
|
|
"mean_token_accuracy": 0.1702035993337631,
|
|
"num_tokens": 34648466.0,
|
|
"step": 17720
|
|
},
|
|
{
|
|
"entropy": 6.045576906204223,
|
|
"epoch": 1.771829859549158,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004690694282371523,
|
|
"loss": 5.7575,
|
|
"mean_token_accuracy": 0.16930388659238815,
|
|
"num_tokens": 34658567.0,
|
|
"step": 17725
|
|
},
|
|
{
|
|
"entropy": 6.026725578308105,
|
|
"epoch": 1.7723296846103862,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004690513669470594,
|
|
"loss": 5.6783,
|
|
"mean_token_accuracy": 0.17870956510305405,
|
|
"num_tokens": 34667555.0,
|
|
"step": 17730
|
|
},
|
|
{
|
|
"entropy": 6.167243146896363,
|
|
"epoch": 1.772829509671615,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.000469033300774684,
|
|
"loss": 5.8563,
|
|
"mean_token_accuracy": 0.159641832113266,
|
|
"num_tokens": 34678002.0,
|
|
"step": 17735
|
|
},
|
|
{
|
|
"entropy": 6.114215898513794,
|
|
"epoch": 1.7733293347328436,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004690152297204808,
|
|
"loss": 5.7973,
|
|
"mean_token_accuracy": 0.17122994512319564,
|
|
"num_tokens": 34688112.0,
|
|
"step": 17740
|
|
},
|
|
{
|
|
"entropy": 6.091564083099366,
|
|
"epoch": 1.773829159794072,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00046899715378490427,
|
|
"loss": 5.8783,
|
|
"mean_token_accuracy": 0.16099835634231568,
|
|
"num_tokens": 34697960.0,
|
|
"step": 17745
|
|
},
|
|
{
|
|
"entropy": 6.072007417678833,
|
|
"epoch": 1.7743289848553006,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.00046897907296840927,
|
|
"loss": 5.7114,
|
|
"mean_token_accuracy": 0.17345488518476487,
|
|
"num_tokens": 34708072.0,
|
|
"step": 17750
|
|
},
|
|
{
|
|
"entropy": 6.037260723114014,
|
|
"epoch": 1.7748288099165292,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004689609872714507,
|
|
"loss": 5.7423,
|
|
"mean_token_accuracy": 0.1698773831129074,
|
|
"num_tokens": 34717723.0,
|
|
"step": 17755
|
|
},
|
|
{
|
|
"entropy": 6.125628423690796,
|
|
"epoch": 1.775328634977758,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00046894289669448366,
|
|
"loss": 5.8725,
|
|
"mean_token_accuracy": 0.16127837896347047,
|
|
"num_tokens": 34727326.0,
|
|
"step": 17760
|
|
},
|
|
{
|
|
"entropy": 6.1628705024719235,
|
|
"epoch": 1.7758284600389862,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00046892480123796314,
|
|
"loss": 5.8302,
|
|
"mean_token_accuracy": 0.16487298905849457,
|
|
"num_tokens": 34737203.0,
|
|
"step": 17765
|
|
},
|
|
{
|
|
"entropy": 6.091555118560791,
|
|
"epoch": 1.776328285100215,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004689067009023446,
|
|
"loss": 5.8387,
|
|
"mean_token_accuracy": 0.16337076127529143,
|
|
"num_tokens": 34746287.0,
|
|
"step": 17770
|
|
},
|
|
{
|
|
"entropy": 6.071529531478882,
|
|
"epoch": 1.7768281101614436,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004688885956880834,
|
|
"loss": 5.7809,
|
|
"mean_token_accuracy": 0.16863114833831788,
|
|
"num_tokens": 34757478.0,
|
|
"step": 17775
|
|
},
|
|
{
|
|
"entropy": 6.119533681869507,
|
|
"epoch": 1.777327935222672,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004688704855956349,
|
|
"loss": 5.7676,
|
|
"mean_token_accuracy": 0.17045095413923264,
|
|
"num_tokens": 34766474.0,
|
|
"step": 17780
|
|
},
|
|
{
|
|
"entropy": 6.12436990737915,
|
|
"epoch": 1.7778277602839005,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.00046885237062545493,
|
|
"loss": 5.7611,
|
|
"mean_token_accuracy": 0.16922566145658494,
|
|
"num_tokens": 34775500.0,
|
|
"step": 17785
|
|
},
|
|
{
|
|
"entropy": 6.067885780334473,
|
|
"epoch": 1.7783275853451292,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00046883425077799923,
|
|
"loss": 5.8745,
|
|
"mean_token_accuracy": 0.1645024374127388,
|
|
"num_tokens": 34785290.0,
|
|
"step": 17790
|
|
},
|
|
{
|
|
"entropy": 6.242372035980225,
|
|
"epoch": 1.7788274104063577,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004688161260537236,
|
|
"loss": 6.0462,
|
|
"mean_token_accuracy": 0.14957467913627626,
|
|
"num_tokens": 34794485.0,
|
|
"step": 17795
|
|
},
|
|
{
|
|
"entropy": 6.182308959960937,
|
|
"epoch": 1.7793272354675862,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004687979964530842,
|
|
"loss": 5.8002,
|
|
"mean_token_accuracy": 0.1666768506169319,
|
|
"num_tokens": 34803825.0,
|
|
"step": 17800
|
|
},
|
|
{
|
|
"entropy": 6.172938537597656,
|
|
"epoch": 1.779827060528815,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.000468779861976537,
|
|
"loss": 5.9273,
|
|
"mean_token_accuracy": 0.15534346997737886,
|
|
"num_tokens": 34812553.0,
|
|
"step": 17805
|
|
},
|
|
{
|
|
"entropy": 6.076042222976684,
|
|
"epoch": 1.7803268855900436,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00046876172262453843,
|
|
"loss": 5.883,
|
|
"mean_token_accuracy": 0.1644313305616379,
|
|
"num_tokens": 34822427.0,
|
|
"step": 17810
|
|
},
|
|
{
|
|
"entropy": 6.14277982711792,
|
|
"epoch": 1.780826710651272,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00046874357839754463,
|
|
"loss": 6.0362,
|
|
"mean_token_accuracy": 0.15067177414894103,
|
|
"num_tokens": 34831918.0,
|
|
"step": 17815
|
|
},
|
|
{
|
|
"entropy": 6.1720499992370605,
|
|
"epoch": 1.7813265357125005,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00046872542929601234,
|
|
"loss": 5.8057,
|
|
"mean_token_accuracy": 0.16108608543872832,
|
|
"num_tokens": 34840429.0,
|
|
"step": 17820
|
|
},
|
|
{
|
|
"entropy": 6.1331264019012455,
|
|
"epoch": 1.7818263607737292,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00046870727532039816,
|
|
"loss": 5.7996,
|
|
"mean_token_accuracy": 0.16690599620342256,
|
|
"num_tokens": 34850455.0,
|
|
"step": 17825
|
|
},
|
|
{
|
|
"entropy": 6.082704067230225,
|
|
"epoch": 1.7823261858349577,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004686891164711586,
|
|
"loss": 5.7976,
|
|
"mean_token_accuracy": 0.1670275777578354,
|
|
"num_tokens": 34860062.0,
|
|
"step": 17830
|
|
},
|
|
{
|
|
"entropy": 6.118826055526734,
|
|
"epoch": 1.7828260108961862,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00046867095274875085,
|
|
"loss": 5.8153,
|
|
"mean_token_accuracy": 0.17085691392421723,
|
|
"num_tokens": 34869987.0,
|
|
"step": 17835
|
|
},
|
|
{
|
|
"entropy": 6.142798042297363,
|
|
"epoch": 1.783325835957415,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00046865278415363174,
|
|
"loss": 5.927,
|
|
"mean_token_accuracy": 0.15881933867931367,
|
|
"num_tokens": 34881593.0,
|
|
"step": 17840
|
|
},
|
|
{
|
|
"entropy": 6.159872531890869,
|
|
"epoch": 1.7838256610186436,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004686346106862584,
|
|
"loss": 5.8703,
|
|
"mean_token_accuracy": 0.16152282953262329,
|
|
"num_tokens": 34891468.0,
|
|
"step": 17845
|
|
},
|
|
{
|
|
"entropy": 6.11032280921936,
|
|
"epoch": 1.784325486079872,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004686164323470881,
|
|
"loss": 5.7565,
|
|
"mean_token_accuracy": 0.16973702907562255,
|
|
"num_tokens": 34900591.0,
|
|
"step": 17850
|
|
},
|
|
{
|
|
"entropy": 6.101046991348267,
|
|
"epoch": 1.7848253111411005,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004685982491365781,
|
|
"loss": 5.7677,
|
|
"mean_token_accuracy": 0.17229566723108292,
|
|
"num_tokens": 34909514.0,
|
|
"step": 17855
|
|
},
|
|
{
|
|
"entropy": 6.15239634513855,
|
|
"epoch": 1.7853251362023292,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00046858006105518615,
|
|
"loss": 5.7741,
|
|
"mean_token_accuracy": 0.16635277271270751,
|
|
"num_tokens": 34918836.0,
|
|
"step": 17860
|
|
},
|
|
{
|
|
"entropy": 6.0001977443695065,
|
|
"epoch": 1.7858249612635577,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004685618681033695,
|
|
"loss": 5.7128,
|
|
"mean_token_accuracy": 0.1717883124947548,
|
|
"num_tokens": 34928040.0,
|
|
"step": 17865
|
|
},
|
|
{
|
|
"entropy": 6.057123851776123,
|
|
"epoch": 1.7863247863247862,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004685436702815861,
|
|
"loss": 5.7675,
|
|
"mean_token_accuracy": 0.17020978927612304,
|
|
"num_tokens": 34936879.0,
|
|
"step": 17870
|
|
},
|
|
{
|
|
"entropy": 6.085494613647461,
|
|
"epoch": 1.786824611386015,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004685254675902938,
|
|
"loss": 5.8067,
|
|
"mean_token_accuracy": 0.16087810844182968,
|
|
"num_tokens": 34946986.0,
|
|
"step": 17875
|
|
},
|
|
{
|
|
"entropy": 6.081479024887085,
|
|
"epoch": 1.7873244364472436,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004685072600299505,
|
|
"loss": 5.8054,
|
|
"mean_token_accuracy": 0.16483895629644393,
|
|
"num_tokens": 34956848.0,
|
|
"step": 17880
|
|
},
|
|
{
|
|
"entropy": 6.176258754730225,
|
|
"epoch": 1.787824261508472,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004684890476010144,
|
|
"loss": 5.8546,
|
|
"mean_token_accuracy": 0.1653517633676529,
|
|
"num_tokens": 34966656.0,
|
|
"step": 17885
|
|
},
|
|
{
|
|
"entropy": 6.13749852180481,
|
|
"epoch": 1.7883240865697005,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004684708303039435,
|
|
"loss": 5.7726,
|
|
"mean_token_accuracy": 0.17276311218738555,
|
|
"num_tokens": 34975672.0,
|
|
"step": 17890
|
|
},
|
|
{
|
|
"entropy": 5.996784400939942,
|
|
"epoch": 1.7888239116309292,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00046845260813919645,
|
|
"loss": 5.7867,
|
|
"mean_token_accuracy": 0.1718239188194275,
|
|
"num_tokens": 34985253.0,
|
|
"step": 17895
|
|
},
|
|
{
|
|
"entropy": 6.0682902336120605,
|
|
"epoch": 1.7893237366921577,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00046843438110723143,
|
|
"loss": 5.7723,
|
|
"mean_token_accuracy": 0.17010565996170043,
|
|
"num_tokens": 34995115.0,
|
|
"step": 17900
|
|
},
|
|
{
|
|
"entropy": 6.1444720268249515,
|
|
"epoch": 1.7898235617533862,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00046841614920850724,
|
|
"loss": 5.834,
|
|
"mean_token_accuracy": 0.16808309853076936,
|
|
"num_tokens": 35005317.0,
|
|
"step": 17905
|
|
},
|
|
{
|
|
"entropy": 6.154652833938599,
|
|
"epoch": 1.790323386814615,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00046839791244348243,
|
|
"loss": 5.8445,
|
|
"mean_token_accuracy": 0.16633743196725845,
|
|
"num_tokens": 35015296.0,
|
|
"step": 17910
|
|
},
|
|
{
|
|
"entropy": 6.009828329086304,
|
|
"epoch": 1.7908232118758436,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00046837967081261606,
|
|
"loss": 5.6048,
|
|
"mean_token_accuracy": 0.1857542872428894,
|
|
"num_tokens": 35023575.0,
|
|
"step": 17915
|
|
},
|
|
{
|
|
"entropy": 6.110335016250611,
|
|
"epoch": 1.791323036937072,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004683614243163668,
|
|
"loss": 5.9133,
|
|
"mean_token_accuracy": 0.16155678406357765,
|
|
"num_tokens": 35034350.0,
|
|
"step": 17920
|
|
},
|
|
{
|
|
"entropy": 6.073188447952271,
|
|
"epoch": 1.7918228619983005,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004683431729551939,
|
|
"loss": 5.8271,
|
|
"mean_token_accuracy": 0.1652176186442375,
|
|
"num_tokens": 35045125.0,
|
|
"step": 17925
|
|
},
|
|
{
|
|
"entropy": 6.0837592601776125,
|
|
"epoch": 1.7923226870595292,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004683249167295565,
|
|
"loss": 5.7568,
|
|
"mean_token_accuracy": 0.1712494522333145,
|
|
"num_tokens": 35055160.0,
|
|
"step": 17930
|
|
},
|
|
{
|
|
"entropy": 6.133599519729614,
|
|
"epoch": 1.7928225121207577,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.000468306655639914,
|
|
"loss": 5.9088,
|
|
"mean_token_accuracy": 0.15774717032909394,
|
|
"num_tokens": 35065626.0,
|
|
"step": 17935
|
|
},
|
|
{
|
|
"entropy": 6.177978944778443,
|
|
"epoch": 1.7933223371819862,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004682883896867257,
|
|
"loss": 5.8963,
|
|
"mean_token_accuracy": 0.16228712052106858,
|
|
"num_tokens": 35077294.0,
|
|
"step": 17940
|
|
},
|
|
{
|
|
"entropy": 6.085515022277832,
|
|
"epoch": 1.793822162243215,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004682701188704513,
|
|
"loss": 5.7614,
|
|
"mean_token_accuracy": 0.1748046860098839,
|
|
"num_tokens": 35086022.0,
|
|
"step": 17945
|
|
},
|
|
{
|
|
"entropy": 6.114905548095703,
|
|
"epoch": 1.7943219873044436,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004682518431915505,
|
|
"loss": 5.9613,
|
|
"mean_token_accuracy": 0.1619322381913662,
|
|
"num_tokens": 35095966.0,
|
|
"step": 17950
|
|
},
|
|
{
|
|
"entropy": 6.117956733703613,
|
|
"epoch": 1.794821812365672,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00046823356265048293,
|
|
"loss": 5.7815,
|
|
"mean_token_accuracy": 0.1601074978709221,
|
|
"num_tokens": 35105554.0,
|
|
"step": 17955
|
|
},
|
|
{
|
|
"entropy": 6.063162517547608,
|
|
"epoch": 1.7953216374269005,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004682152772477087,
|
|
"loss": 5.749,
|
|
"mean_token_accuracy": 0.16868563890457153,
|
|
"num_tokens": 35114485.0,
|
|
"step": 17960
|
|
},
|
|
{
|
|
"entropy": 6.07885217666626,
|
|
"epoch": 1.7958214624881292,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00046819698698368785,
|
|
"loss": 5.8404,
|
|
"mean_token_accuracy": 0.16081240624189377,
|
|
"num_tokens": 35124765.0,
|
|
"step": 17965
|
|
},
|
|
{
|
|
"entropy": 6.12259087562561,
|
|
"epoch": 1.7963212875493577,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00046817869185888044,
|
|
"loss": 5.8664,
|
|
"mean_token_accuracy": 0.16100157648324967,
|
|
"num_tokens": 35134474.0,
|
|
"step": 17970
|
|
},
|
|
{
|
|
"entropy": 6.116328001022339,
|
|
"epoch": 1.7968211126105862,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004681603918737469,
|
|
"loss": 5.8284,
|
|
"mean_token_accuracy": 0.16755760163068772,
|
|
"num_tokens": 35144717.0,
|
|
"step": 17975
|
|
},
|
|
{
|
|
"entropy": 6.176896286010742,
|
|
"epoch": 1.7973209376718149,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.00046814208702874766,
|
|
"loss": 5.8264,
|
|
"mean_token_accuracy": 0.17200229167938233,
|
|
"num_tokens": 35153889.0,
|
|
"step": 17980
|
|
},
|
|
{
|
|
"entropy": 6.051694250106811,
|
|
"epoch": 1.7978207627330436,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.00046812377732434316,
|
|
"loss": 5.7729,
|
|
"mean_token_accuracy": 0.16642460376024246,
|
|
"num_tokens": 35163909.0,
|
|
"step": 17985
|
|
},
|
|
{
|
|
"entropy": 6.11577000617981,
|
|
"epoch": 1.7983205877942718,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.00046810546276099415,
|
|
"loss": 5.8648,
|
|
"mean_token_accuracy": 0.15462714284658433,
|
|
"num_tokens": 35174614.0,
|
|
"step": 17990
|
|
},
|
|
{
|
|
"entropy": 6.104050779342652,
|
|
"epoch": 1.7988204128555005,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004680871433391613,
|
|
"loss": 5.8538,
|
|
"mean_token_accuracy": 0.16439516097307205,
|
|
"num_tokens": 35184568.0,
|
|
"step": 17995
|
|
},
|
|
{
|
|
"entropy": 6.0546222686767575,
|
|
"epoch": 1.7993202379167292,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00046806881905930565,
|
|
"loss": 5.8015,
|
|
"mean_token_accuracy": 0.16840032786130904,
|
|
"num_tokens": 35194594.0,
|
|
"step": 18000
|
|
},
|
|
{
|
|
"epoch": 1.7993202379167292,
|
|
"eval_entropy": 5.8954797842796856,
|
|
"eval_loss": 5.926145553588867,
|
|
"eval_mean_token_accuracy": 0.16697430877983033,
|
|
"eval_num_tokens": 35194594.0,
|
|
"eval_runtime": 23.8527,
|
|
"eval_samples_per_second": 1301.53,
|
|
"eval_steps_per_second": 162.707,
|
|
"step": 18000
|
|
},
|
|
{
|
|
"entropy": 6.078249263763428,
|
|
"epoch": 1.7998200629779577,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00046805048992188823,
|
|
"loss": 5.7783,
|
|
"mean_token_accuracy": 0.17200014740228653,
|
|
"num_tokens": 35204710.0,
|
|
"step": 18005
|
|
},
|
|
{
|
|
"entropy": 6.220006036758423,
|
|
"epoch": 1.8003198880391862,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00046803215592737014,
|
|
"loss": 5.9704,
|
|
"mean_token_accuracy": 0.15174682885408403,
|
|
"num_tokens": 35215531.0,
|
|
"step": 18010
|
|
},
|
|
{
|
|
"entropy": 6.167250299453736,
|
|
"epoch": 1.8008197131004149,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00046801381707621266,
|
|
"loss": 5.8432,
|
|
"mean_token_accuracy": 0.16612268537282943,
|
|
"num_tokens": 35224274.0,
|
|
"step": 18015
|
|
},
|
|
{
|
|
"entropy": 6.078136253356933,
|
|
"epoch": 1.8013195381616436,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00046799547336887727,
|
|
"loss": 5.7775,
|
|
"mean_token_accuracy": 0.17055410146713257,
|
|
"num_tokens": 35234341.0,
|
|
"step": 18020
|
|
},
|
|
{
|
|
"entropy": 6.0823297023773195,
|
|
"epoch": 1.8018193632228718,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004679771248058254,
|
|
"loss": 5.8022,
|
|
"mean_token_accuracy": 0.158466337621212,
|
|
"num_tokens": 35244841.0,
|
|
"step": 18025
|
|
},
|
|
{
|
|
"entropy": 6.115656995773316,
|
|
"epoch": 1.8023191882841005,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004679587713875187,
|
|
"loss": 5.9019,
|
|
"mean_token_accuracy": 0.15566385686397552,
|
|
"num_tokens": 35254770.0,
|
|
"step": 18030
|
|
},
|
|
{
|
|
"entropy": 6.170646810531617,
|
|
"epoch": 1.8028190133453292,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.000467940413114419,
|
|
"loss": 5.8277,
|
|
"mean_token_accuracy": 0.16630408614873887,
|
|
"num_tokens": 35263676.0,
|
|
"step": 18035
|
|
},
|
|
{
|
|
"entropy": 6.087178802490234,
|
|
"epoch": 1.8033188384065577,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004679220499869881,
|
|
"loss": 5.8273,
|
|
"mean_token_accuracy": 0.1595147058367729,
|
|
"num_tokens": 35273845.0,
|
|
"step": 18040
|
|
},
|
|
{
|
|
"entropy": 6.14619140625,
|
|
"epoch": 1.8038186634677862,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004679036820056881,
|
|
"loss": 5.9701,
|
|
"mean_token_accuracy": 0.15394546389579772,
|
|
"num_tokens": 35285121.0,
|
|
"step": 18045
|
|
},
|
|
{
|
|
"entropy": 6.1649271011352536,
|
|
"epoch": 1.8043184885290149,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00046788530917098105,
|
|
"loss": 5.8684,
|
|
"mean_token_accuracy": 0.16195056438446045,
|
|
"num_tokens": 35294601.0,
|
|
"step": 18050
|
|
},
|
|
{
|
|
"entropy": 6.148553323745728,
|
|
"epoch": 1.8048183135902434,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004678669314833293,
|
|
"loss": 5.8581,
|
|
"mean_token_accuracy": 0.16080692410469055,
|
|
"num_tokens": 35304456.0,
|
|
"step": 18055
|
|
},
|
|
{
|
|
"entropy": 6.065420722961425,
|
|
"epoch": 1.8053181386514718,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00046784854894319525,
|
|
"loss": 5.8579,
|
|
"mean_token_accuracy": 0.16767567545175552,
|
|
"num_tokens": 35314333.0,
|
|
"step": 18060
|
|
},
|
|
{
|
|
"entropy": 6.143421745300293,
|
|
"epoch": 1.8058179637127005,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00046783016155104123,
|
|
"loss": 5.8328,
|
|
"mean_token_accuracy": 0.16367872357368468,
|
|
"num_tokens": 35325267.0,
|
|
"step": 18065
|
|
},
|
|
{
|
|
"entropy": 6.173601245880127,
|
|
"epoch": 1.8063177887739292,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00046781176930732997,
|
|
"loss": 5.8204,
|
|
"mean_token_accuracy": 0.16156936287879944,
|
|
"num_tokens": 35334232.0,
|
|
"step": 18070
|
|
},
|
|
{
|
|
"entropy": 6.1294056415557865,
|
|
"epoch": 1.8068176138351577,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004677933722125243,
|
|
"loss": 5.861,
|
|
"mean_token_accuracy": 0.16071026772260666,
|
|
"num_tokens": 35344961.0,
|
|
"step": 18075
|
|
},
|
|
{
|
|
"entropy": 6.1243926048278805,
|
|
"epoch": 1.8073174388963862,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004677749702670869,
|
|
"loss": 5.9089,
|
|
"mean_token_accuracy": 0.1635565310716629,
|
|
"num_tokens": 35354719.0,
|
|
"step": 18080
|
|
},
|
|
{
|
|
"entropy": 6.058001327514648,
|
|
"epoch": 1.8078172639576149,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004677565634714809,
|
|
"loss": 5.7607,
|
|
"mean_token_accuracy": 0.17138111144304274,
|
|
"num_tokens": 35365301.0,
|
|
"step": 18085
|
|
},
|
|
{
|
|
"entropy": 6.073010206222534,
|
|
"epoch": 1.8083170890188434,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004677381518261693,
|
|
"loss": 5.8274,
|
|
"mean_token_accuracy": 0.15901716500520707,
|
|
"num_tokens": 35375586.0,
|
|
"step": 18090
|
|
},
|
|
{
|
|
"entropy": 6.099800395965576,
|
|
"epoch": 1.8088169140800718,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00046771973533161543,
|
|
"loss": 5.8568,
|
|
"mean_token_accuracy": 0.1632835328578949,
|
|
"num_tokens": 35385226.0,
|
|
"step": 18095
|
|
},
|
|
{
|
|
"entropy": 6.080997705459595,
|
|
"epoch": 1.8093167391413005,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00046770131398828264,
|
|
"loss": 5.7748,
|
|
"mean_token_accuracy": 0.1704069346189499,
|
|
"num_tokens": 35394872.0,
|
|
"step": 18100
|
|
},
|
|
{
|
|
"entropy": 6.002931070327759,
|
|
"epoch": 1.8098165642025292,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00046768288779663436,
|
|
"loss": 5.7321,
|
|
"mean_token_accuracy": 0.16783900409936905,
|
|
"num_tokens": 35403790.0,
|
|
"step": 18105
|
|
},
|
|
{
|
|
"entropy": 6.145980262756348,
|
|
"epoch": 1.8103163892637577,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004676644567571342,
|
|
"loss": 5.8825,
|
|
"mean_token_accuracy": 0.1623958617448807,
|
|
"num_tokens": 35414042.0,
|
|
"step": 18110
|
|
},
|
|
{
|
|
"entropy": 6.0651270866394045,
|
|
"epoch": 1.8108162143249862,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00046764602087024596,
|
|
"loss": 5.7209,
|
|
"mean_token_accuracy": 0.1722832903265953,
|
|
"num_tokens": 35423345.0,
|
|
"step": 18115
|
|
},
|
|
{
|
|
"entropy": 6.073203992843628,
|
|
"epoch": 1.8113160393862149,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004676275801364332,
|
|
"loss": 5.8578,
|
|
"mean_token_accuracy": 0.15892522037029266,
|
|
"num_tokens": 35433284.0,
|
|
"step": 18120
|
|
},
|
|
{
|
|
"entropy": 6.1246538162231445,
|
|
"epoch": 1.8118158644474434,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004676091345561603,
|
|
"loss": 5.8485,
|
|
"mean_token_accuracy": 0.15982912331819535,
|
|
"num_tokens": 35443258.0,
|
|
"step": 18125
|
|
},
|
|
{
|
|
"entropy": 6.128575181961059,
|
|
"epoch": 1.8123156895086718,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000467590684129891,
|
|
"loss": 5.8771,
|
|
"mean_token_accuracy": 0.1615601174533367,
|
|
"num_tokens": 35453214.0,
|
|
"step": 18130
|
|
},
|
|
{
|
|
"entropy": 6.186525917053222,
|
|
"epoch": 1.8128155145699005,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00046757222885808973,
|
|
"loss": 5.8036,
|
|
"mean_token_accuracy": 0.1683404639363289,
|
|
"num_tokens": 35462802.0,
|
|
"step": 18135
|
|
},
|
|
{
|
|
"entropy": 6.022737646102906,
|
|
"epoch": 1.8133153396311292,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00046755376874122075,
|
|
"loss": 5.7094,
|
|
"mean_token_accuracy": 0.1764661967754364,
|
|
"num_tokens": 35472423.0,
|
|
"step": 18140
|
|
},
|
|
{
|
|
"entropy": 6.108632040023804,
|
|
"epoch": 1.8138151646923577,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004675353037797485,
|
|
"loss": 5.8364,
|
|
"mean_token_accuracy": 0.1647487089037895,
|
|
"num_tokens": 35481835.0,
|
|
"step": 18145
|
|
},
|
|
{
|
|
"entropy": 6.068162488937378,
|
|
"epoch": 1.8143149897535862,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004675168339741375,
|
|
"loss": 5.847,
|
|
"mean_token_accuracy": 0.16579292714595795,
|
|
"num_tokens": 35491834.0,
|
|
"step": 18150
|
|
},
|
|
{
|
|
"entropy": 6.081631851196289,
|
|
"epoch": 1.8148148148148149,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004674983593248525,
|
|
"loss": 5.839,
|
|
"mean_token_accuracy": 0.16161713153123855,
|
|
"num_tokens": 35501591.0,
|
|
"step": 18155
|
|
},
|
|
{
|
|
"entropy": 6.032625198364258,
|
|
"epoch": 1.8153146398760434,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00046747987983235836,
|
|
"loss": 5.7772,
|
|
"mean_token_accuracy": 0.16795562207698822,
|
|
"num_tokens": 35511720.0,
|
|
"step": 18160
|
|
},
|
|
{
|
|
"entropy": 6.182640314102173,
|
|
"epoch": 1.8158144649372718,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00046746139549711993,
|
|
"loss": 5.8774,
|
|
"mean_token_accuracy": 0.1630174547433853,
|
|
"num_tokens": 35521040.0,
|
|
"step": 18165
|
|
},
|
|
{
|
|
"entropy": 6.078531122207641,
|
|
"epoch": 1.8163142899985005,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004674429063196023,
|
|
"loss": 5.7498,
|
|
"mean_token_accuracy": 0.1715579152107239,
|
|
"num_tokens": 35530919.0,
|
|
"step": 18170
|
|
},
|
|
{
|
|
"entropy": 6.039144277572632,
|
|
"epoch": 1.8168141150597292,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00046742441230027067,
|
|
"loss": 5.7269,
|
|
"mean_token_accuracy": 0.17383552193641663,
|
|
"num_tokens": 35539964.0,
|
|
"step": 18175
|
|
},
|
|
{
|
|
"entropy": 6.081282758712769,
|
|
"epoch": 1.8173139401209577,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004674059134395904,
|
|
"loss": 5.83,
|
|
"mean_token_accuracy": 0.16368343979120253,
|
|
"num_tokens": 35549679.0,
|
|
"step": 18180
|
|
},
|
|
{
|
|
"entropy": 6.193099880218506,
|
|
"epoch": 1.8178137651821862,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0004673874097380268,
|
|
"loss": 5.9134,
|
|
"mean_token_accuracy": 0.15814111679792403,
|
|
"num_tokens": 35560159.0,
|
|
"step": 18185
|
|
},
|
|
{
|
|
"entropy": 6.202969694137574,
|
|
"epoch": 1.8183135902434149,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004673689011960455,
|
|
"loss": 5.9492,
|
|
"mean_token_accuracy": 0.1587182305753231,
|
|
"num_tokens": 35571591.0,
|
|
"step": 18190
|
|
},
|
|
{
|
|
"entropy": 6.143823480606079,
|
|
"epoch": 1.8188134153046434,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00046735038781411204,
|
|
"loss": 5.754,
|
|
"mean_token_accuracy": 0.16738696545362472,
|
|
"num_tokens": 35581641.0,
|
|
"step": 18195
|
|
},
|
|
{
|
|
"entropy": 6.1670613288879395,
|
|
"epoch": 1.8193132403658718,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004673318695926925,
|
|
"loss": 5.944,
|
|
"mean_token_accuracy": 0.15887511223554612,
|
|
"num_tokens": 35591738.0,
|
|
"step": 18200
|
|
},
|
|
{
|
|
"entropy": 6.197928190231323,
|
|
"epoch": 1.8198130654271005,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004673133465322525,
|
|
"loss": 5.9545,
|
|
"mean_token_accuracy": 0.15996465235948562,
|
|
"num_tokens": 35600818.0,
|
|
"step": 18205
|
|
},
|
|
{
|
|
"entropy": 6.154720306396484,
|
|
"epoch": 1.8203128904883292,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004672948186332582,
|
|
"loss": 5.8159,
|
|
"mean_token_accuracy": 0.16589495688676834,
|
|
"num_tokens": 35610180.0,
|
|
"step": 18210
|
|
},
|
|
{
|
|
"entropy": 6.094410037994384,
|
|
"epoch": 1.8208127155495577,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00046727628589617574,
|
|
"loss": 5.7983,
|
|
"mean_token_accuracy": 0.16678022146224974,
|
|
"num_tokens": 35620894.0,
|
|
"step": 18215
|
|
},
|
|
{
|
|
"entropy": 6.161709117889404,
|
|
"epoch": 1.8213125406107862,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00046725774832147147,
|
|
"loss": 5.9135,
|
|
"mean_token_accuracy": 0.15960183888673782,
|
|
"num_tokens": 35630976.0,
|
|
"step": 18220
|
|
},
|
|
{
|
|
"entropy": 6.164668703079224,
|
|
"epoch": 1.8218123656720149,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00046723920590961167,
|
|
"loss": 5.903,
|
|
"mean_token_accuracy": 0.16202606558799743,
|
|
"num_tokens": 35640436.0,
|
|
"step": 18225
|
|
},
|
|
{
|
|
"entropy": 6.160171175003052,
|
|
"epoch": 1.8223121907332434,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004672206586610629,
|
|
"loss": 5.8381,
|
|
"mean_token_accuracy": 0.1650242619216442,
|
|
"num_tokens": 35650533.0,
|
|
"step": 18230
|
|
},
|
|
{
|
|
"entropy": 6.075879764556885,
|
|
"epoch": 1.8228120157944718,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00046720210657629185,
|
|
"loss": 5.7612,
|
|
"mean_token_accuracy": 0.1697671204805374,
|
|
"num_tokens": 35660748.0,
|
|
"step": 18235
|
|
},
|
|
{
|
|
"entropy": 6.073791265487671,
|
|
"epoch": 1.8233118408557005,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00046718354965576527,
|
|
"loss": 5.8722,
|
|
"mean_token_accuracy": 0.16792336106300354,
|
|
"num_tokens": 35671186.0,
|
|
"step": 18240
|
|
},
|
|
{
|
|
"entropy": 6.107644844055176,
|
|
"epoch": 1.8238116659169292,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00046716498789995,
|
|
"loss": 5.7638,
|
|
"mean_token_accuracy": 0.17541894912719727,
|
|
"num_tokens": 35681784.0,
|
|
"step": 18245
|
|
},
|
|
{
|
|
"entropy": 6.12407956123352,
|
|
"epoch": 1.8243114909781575,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00046714642130931306,
|
|
"loss": 5.8206,
|
|
"mean_token_accuracy": 0.16501579582691192,
|
|
"num_tokens": 35692110.0,
|
|
"step": 18250
|
|
},
|
|
{
|
|
"entropy": 6.061975049972534,
|
|
"epoch": 1.8248113160393862,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00046712784988432173,
|
|
"loss": 5.7894,
|
|
"mean_token_accuracy": 0.16509875804185867,
|
|
"num_tokens": 35702051.0,
|
|
"step": 18255
|
|
},
|
|
{
|
|
"entropy": 6.075981712341308,
|
|
"epoch": 1.8253111411006149,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.000467109273625443,
|
|
"loss": 5.8174,
|
|
"mean_token_accuracy": 0.16709185093641282,
|
|
"num_tokens": 35711368.0,
|
|
"step": 18260
|
|
},
|
|
{
|
|
"entropy": 6.131850242614746,
|
|
"epoch": 1.8258109661618434,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004670906925331444,
|
|
"loss": 5.91,
|
|
"mean_token_accuracy": 0.16010029017925262,
|
|
"num_tokens": 35720868.0,
|
|
"step": 18265
|
|
},
|
|
{
|
|
"entropy": 6.101100015640259,
|
|
"epoch": 1.8263107912230718,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00046707210660789343,
|
|
"loss": 5.8298,
|
|
"mean_token_accuracy": 0.1651126652956009,
|
|
"num_tokens": 35730697.0,
|
|
"step": 18270
|
|
},
|
|
{
|
|
"entropy": 6.08077826499939,
|
|
"epoch": 1.8268106162843005,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004670535158501577,
|
|
"loss": 5.7733,
|
|
"mean_token_accuracy": 0.1683964490890503,
|
|
"num_tokens": 35740341.0,
|
|
"step": 18275
|
|
},
|
|
{
|
|
"entropy": 6.006336498260498,
|
|
"epoch": 1.8273104413455292,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00046703492026040495,
|
|
"loss": 5.7221,
|
|
"mean_token_accuracy": 0.1796570062637329,
|
|
"num_tokens": 35749324.0,
|
|
"step": 18280
|
|
},
|
|
{
|
|
"entropy": 6.155780696868897,
|
|
"epoch": 1.8278102664067575,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00046701631983910296,
|
|
"loss": 5.845,
|
|
"mean_token_accuracy": 0.1597383961081505,
|
|
"num_tokens": 35759650.0,
|
|
"step": 18285
|
|
},
|
|
{
|
|
"entropy": 6.088052034378052,
|
|
"epoch": 1.8283100914679862,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00046699771458671974,
|
|
"loss": 5.759,
|
|
"mean_token_accuracy": 0.1667125090956688,
|
|
"num_tokens": 35770586.0,
|
|
"step": 18290
|
|
},
|
|
{
|
|
"entropy": 6.142336988449097,
|
|
"epoch": 1.8288099165292149,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.00046697910450372356,
|
|
"loss": 5.8609,
|
|
"mean_token_accuracy": 0.15939129739999772,
|
|
"num_tokens": 35780204.0,
|
|
"step": 18295
|
|
},
|
|
{
|
|
"entropy": 6.105853080749512,
|
|
"epoch": 1.8293097415904434,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00046696048959058236,
|
|
"loss": 5.7822,
|
|
"mean_token_accuracy": 0.15699482709169388,
|
|
"num_tokens": 35790008.0,
|
|
"step": 18300
|
|
},
|
|
{
|
|
"entropy": 6.031469297409058,
|
|
"epoch": 1.8298095666516718,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004669418698477647,
|
|
"loss": 5.7844,
|
|
"mean_token_accuracy": 0.1694465696811676,
|
|
"num_tokens": 35799752.0,
|
|
"step": 18305
|
|
},
|
|
{
|
|
"entropy": 6.148848152160644,
|
|
"epoch": 1.8303093917129005,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00046692324527573907,
|
|
"loss": 5.8749,
|
|
"mean_token_accuracy": 0.16282531172037124,
|
|
"num_tokens": 35809779.0,
|
|
"step": 18310
|
|
},
|
|
{
|
|
"entropy": 6.134984159469605,
|
|
"epoch": 1.830809216774129,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004669046158749738,
|
|
"loss": 5.833,
|
|
"mean_token_accuracy": 0.16105546802282333,
|
|
"num_tokens": 35819461.0,
|
|
"step": 18315
|
|
},
|
|
{
|
|
"entropy": 6.164929485321045,
|
|
"epoch": 1.8313090418353575,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00046688598164593793,
|
|
"loss": 5.8776,
|
|
"mean_token_accuracy": 0.1626274600625038,
|
|
"num_tokens": 35828868.0,
|
|
"step": 18320
|
|
},
|
|
{
|
|
"entropy": 6.0923460006713865,
|
|
"epoch": 1.8318088668965862,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004668673425891001,
|
|
"loss": 5.8515,
|
|
"mean_token_accuracy": 0.1647162526845932,
|
|
"num_tokens": 35839102.0,
|
|
"step": 18325
|
|
},
|
|
{
|
|
"entropy": 6.034536838531494,
|
|
"epoch": 1.8323086919578149,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00046684869870492927,
|
|
"loss": 5.7065,
|
|
"mean_token_accuracy": 0.17015066593885422,
|
|
"num_tokens": 35848884.0,
|
|
"step": 18330
|
|
},
|
|
{
|
|
"entropy": 6.044521427154541,
|
|
"epoch": 1.8328085170190433,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00046683004999389455,
|
|
"loss": 5.8025,
|
|
"mean_token_accuracy": 0.17272736132144928,
|
|
"num_tokens": 35858820.0,
|
|
"step": 18335
|
|
},
|
|
{
|
|
"entropy": 6.213045930862426,
|
|
"epoch": 1.8333083420802718,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004668113964564651,
|
|
"loss": 5.8388,
|
|
"mean_token_accuracy": 0.15675497204065322,
|
|
"num_tokens": 35868167.0,
|
|
"step": 18340
|
|
},
|
|
{
|
|
"entropy": 6.120562887191772,
|
|
"epoch": 1.8338081671415005,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004667927380931104,
|
|
"loss": 5.8779,
|
|
"mean_token_accuracy": 0.15835225880146026,
|
|
"num_tokens": 35877544.0,
|
|
"step": 18345
|
|
},
|
|
{
|
|
"entropy": 6.0497642993927006,
|
|
"epoch": 1.834307992202729,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004667740749042997,
|
|
"loss": 5.786,
|
|
"mean_token_accuracy": 0.17030153572559356,
|
|
"num_tokens": 35887263.0,
|
|
"step": 18350
|
|
},
|
|
{
|
|
"entropy": 6.154393720626831,
|
|
"epoch": 1.8348078172639575,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00046675540689050253,
|
|
"loss": 5.8653,
|
|
"mean_token_accuracy": 0.1577667087316513,
|
|
"num_tokens": 35896833.0,
|
|
"step": 18355
|
|
},
|
|
{
|
|
"entropy": 6.070201778411866,
|
|
"epoch": 1.8353076423251862,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00046673673405218876,
|
|
"loss": 5.743,
|
|
"mean_token_accuracy": 0.1702558860182762,
|
|
"num_tokens": 35905477.0,
|
|
"step": 18360
|
|
},
|
|
{
|
|
"entropy": 6.141659832000732,
|
|
"epoch": 1.8358074673864149,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0004667180563898281,
|
|
"loss": 5.9153,
|
|
"mean_token_accuracy": 0.15629589110612868,
|
|
"num_tokens": 35916261.0,
|
|
"step": 18365
|
|
},
|
|
{
|
|
"entropy": 6.073173666000367,
|
|
"epoch": 1.8363072924476433,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.00046669937390389043,
|
|
"loss": 5.7491,
|
|
"mean_token_accuracy": 0.17001239508390426,
|
|
"num_tokens": 35926188.0,
|
|
"step": 18370
|
|
},
|
|
{
|
|
"entropy": 5.987343120574951,
|
|
"epoch": 1.8368071175088718,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00046668068659484584,
|
|
"loss": 5.6948,
|
|
"mean_token_accuracy": 0.17104713022708892,
|
|
"num_tokens": 35935970.0,
|
|
"step": 18375
|
|
},
|
|
{
|
|
"entropy": 6.107727479934693,
|
|
"epoch": 1.8373069425701005,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00046666199446316454,
|
|
"loss": 5.8742,
|
|
"mean_token_accuracy": 0.1631246328353882,
|
|
"num_tokens": 35946220.0,
|
|
"step": 18380
|
|
},
|
|
{
|
|
"entropy": 6.069183015823365,
|
|
"epoch": 1.837806767631329,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00046664329750931675,
|
|
"loss": 5.7027,
|
|
"mean_token_accuracy": 0.1738334596157074,
|
|
"num_tokens": 35955918.0,
|
|
"step": 18385
|
|
},
|
|
{
|
|
"entropy": 6.2323326587677,
|
|
"epoch": 1.8383065926925575,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.000466624595733773,
|
|
"loss": 5.9743,
|
|
"mean_token_accuracy": 0.15412475615739823,
|
|
"num_tokens": 35966136.0,
|
|
"step": 18390
|
|
},
|
|
{
|
|
"entropy": 6.119294548034668,
|
|
"epoch": 1.8388064177537862,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004666058891370036,
|
|
"loss": 5.7705,
|
|
"mean_token_accuracy": 0.16715034693479539,
|
|
"num_tokens": 35975775.0,
|
|
"step": 18395
|
|
},
|
|
{
|
|
"entropy": 6.097045755386352,
|
|
"epoch": 1.8393062428150149,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004665871777194794,
|
|
"loss": 5.7821,
|
|
"mean_token_accuracy": 0.1693917080760002,
|
|
"num_tokens": 35984637.0,
|
|
"step": 18400
|
|
},
|
|
{
|
|
"entropy": 6.121038484573364,
|
|
"epoch": 1.8398060678762433,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.00046656846148167107,
|
|
"loss": 5.8192,
|
|
"mean_token_accuracy": 0.16481139212846757,
|
|
"num_tokens": 35993944.0,
|
|
"step": 18405
|
|
},
|
|
{
|
|
"entropy": 6.115529108047485,
|
|
"epoch": 1.8403058929374718,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00046654974042404957,
|
|
"loss": 5.8265,
|
|
"mean_token_accuracy": 0.16711724549531937,
|
|
"num_tokens": 36003442.0,
|
|
"step": 18410
|
|
},
|
|
{
|
|
"entropy": 6.08825364112854,
|
|
"epoch": 1.8408057179987005,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00046653101454708593,
|
|
"loss": 5.7924,
|
|
"mean_token_accuracy": 0.16753575056791306,
|
|
"num_tokens": 36014354.0,
|
|
"step": 18415
|
|
},
|
|
{
|
|
"entropy": 6.231806850433349,
|
|
"epoch": 1.841305543059929,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004665122838512512,
|
|
"loss": 5.9682,
|
|
"mean_token_accuracy": 0.1566050320863724,
|
|
"num_tokens": 36025499.0,
|
|
"step": 18420
|
|
},
|
|
{
|
|
"entropy": 6.222250366210938,
|
|
"epoch": 1.8418053681211575,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004664935483370167,
|
|
"loss": 5.8905,
|
|
"mean_token_accuracy": 0.16325618624687194,
|
|
"num_tokens": 36036261.0,
|
|
"step": 18425
|
|
},
|
|
{
|
|
"entropy": 6.12715892791748,
|
|
"epoch": 1.8423051931823862,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004664748080048537,
|
|
"loss": 5.8396,
|
|
"mean_token_accuracy": 0.16512970328330995,
|
|
"num_tokens": 36045663.0,
|
|
"step": 18430
|
|
},
|
|
{
|
|
"entropy": 6.041265249252319,
|
|
"epoch": 1.8428050182436149,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.00046645606285523395,
|
|
"loss": 5.7578,
|
|
"mean_token_accuracy": 0.17349298894405366,
|
|
"num_tokens": 36055491.0,
|
|
"step": 18435
|
|
},
|
|
{
|
|
"entropy": 6.168734550476074,
|
|
"epoch": 1.8433048433048433,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00046643731288862884,
|
|
"loss": 5.9138,
|
|
"mean_token_accuracy": 0.15904866605997087,
|
|
"num_tokens": 36066379.0,
|
|
"step": 18440
|
|
},
|
|
{
|
|
"entropy": 6.160578107833862,
|
|
"epoch": 1.8438046683660718,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.0004664185581055103,
|
|
"loss": 5.8967,
|
|
"mean_token_accuracy": 0.16368016600608826,
|
|
"num_tokens": 36075160.0,
|
|
"step": 18445
|
|
},
|
|
{
|
|
"entropy": 6.126960420608521,
|
|
"epoch": 1.8443044934273005,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00046639979850634995,
|
|
"loss": 5.8106,
|
|
"mean_token_accuracy": 0.16318074688315393,
|
|
"num_tokens": 36084620.0,
|
|
"step": 18450
|
|
},
|
|
{
|
|
"entropy": 6.1096326351165775,
|
|
"epoch": 1.844804318488529,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00046638103409162,
|
|
"loss": 5.9039,
|
|
"mean_token_accuracy": 0.15610924810171128,
|
|
"num_tokens": 36095289.0,
|
|
"step": 18455
|
|
},
|
|
{
|
|
"entropy": 6.102383136749268,
|
|
"epoch": 1.8453041435497575,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00046636226486179244,
|
|
"loss": 5.8626,
|
|
"mean_token_accuracy": 0.16394977420568466,
|
|
"num_tokens": 36105352.0,
|
|
"step": 18460
|
|
},
|
|
{
|
|
"entropy": 6.043758916854858,
|
|
"epoch": 1.8458039686109862,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004663434908173396,
|
|
"loss": 5.6845,
|
|
"mean_token_accuracy": 0.17155448198318482,
|
|
"num_tokens": 36114722.0,
|
|
"step": 18465
|
|
},
|
|
{
|
|
"entropy": 6.08569598197937,
|
|
"epoch": 1.8463037936722149,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004663247119587338,
|
|
"loss": 5.8406,
|
|
"mean_token_accuracy": 0.16170215904712676,
|
|
"num_tokens": 36123745.0,
|
|
"step": 18470
|
|
},
|
|
{
|
|
"entropy": 6.091285610198975,
|
|
"epoch": 1.8468036187334433,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004663059282864474,
|
|
"loss": 5.8104,
|
|
"mean_token_accuracy": 0.16093951910734178,
|
|
"num_tokens": 36133315.0,
|
|
"step": 18475
|
|
},
|
|
{
|
|
"entropy": 6.174090051651001,
|
|
"epoch": 1.8473034437946718,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004662871398009531,
|
|
"loss": 5.7932,
|
|
"mean_token_accuracy": 0.16357087194919587,
|
|
"num_tokens": 36142990.0,
|
|
"step": 18480
|
|
},
|
|
{
|
|
"entropy": 6.197640752792358,
|
|
"epoch": 1.8478032688559005,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004662683465027235,
|
|
"loss": 5.8141,
|
|
"mean_token_accuracy": 0.16369594931602477,
|
|
"num_tokens": 36152804.0,
|
|
"step": 18485
|
|
},
|
|
{
|
|
"entropy": 6.128863048553467,
|
|
"epoch": 1.848303093917129,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00046624954839223165,
|
|
"loss": 5.9022,
|
|
"mean_token_accuracy": 0.15755719542503357,
|
|
"num_tokens": 36161772.0,
|
|
"step": 18490
|
|
},
|
|
{
|
|
"entropy": 6.011888074874878,
|
|
"epoch": 1.8488029189783575,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00046623074546995024,
|
|
"loss": 5.8003,
|
|
"mean_token_accuracy": 0.1698562130331993,
|
|
"num_tokens": 36170726.0,
|
|
"step": 18495
|
|
},
|
|
{
|
|
"entropy": 6.1152318000793455,
|
|
"epoch": 1.8493027440395862,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00046621193773635256,
|
|
"loss": 5.8544,
|
|
"mean_token_accuracy": 0.15419517382979392,
|
|
"num_tokens": 36181972.0,
|
|
"step": 18500
|
|
},
|
|
{
|
|
"entropy": 6.173034191131592,
|
|
"epoch": 1.8498025691008149,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004661931251919118,
|
|
"loss": 5.8101,
|
|
"mean_token_accuracy": 0.16247158497571945,
|
|
"num_tokens": 36191527.0,
|
|
"step": 18505
|
|
},
|
|
{
|
|
"entropy": 6.186601781845093,
|
|
"epoch": 1.8503023941620433,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00046617430783710105,
|
|
"loss": 5.9723,
|
|
"mean_token_accuracy": 0.15619270578026773,
|
|
"num_tokens": 36201591.0,
|
|
"step": 18510
|
|
},
|
|
{
|
|
"entropy": 6.099596643447876,
|
|
"epoch": 1.8508022192232718,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.000466155485672394,
|
|
"loss": 5.8443,
|
|
"mean_token_accuracy": 0.16353820115327836,
|
|
"num_tokens": 36211893.0,
|
|
"step": 18515
|
|
},
|
|
{
|
|
"entropy": 6.117953205108643,
|
|
"epoch": 1.8513020442845005,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004661366586982641,
|
|
"loss": 5.8251,
|
|
"mean_token_accuracy": 0.16689545959234237,
|
|
"num_tokens": 36221520.0,
|
|
"step": 18520
|
|
},
|
|
{
|
|
"entropy": 6.10032811164856,
|
|
"epoch": 1.851801869345729,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004661178269151851,
|
|
"loss": 5.8424,
|
|
"mean_token_accuracy": 0.1690305143594742,
|
|
"num_tokens": 36231633.0,
|
|
"step": 18525
|
|
},
|
|
{
|
|
"entropy": 6.170127868652344,
|
|
"epoch": 1.8523016944069575,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00046609899032363074,
|
|
"loss": 5.9008,
|
|
"mean_token_accuracy": 0.16522443890571595,
|
|
"num_tokens": 36242514.0,
|
|
"step": 18530
|
|
},
|
|
{
|
|
"entropy": 6.158346891403198,
|
|
"epoch": 1.8528015194681862,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004660801489240749,
|
|
"loss": 5.8648,
|
|
"mean_token_accuracy": 0.16433299332857132,
|
|
"num_tokens": 36252631.0,
|
|
"step": 18535
|
|
},
|
|
{
|
|
"entropy": 6.1376546859741214,
|
|
"epoch": 1.8533013445294149,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00046606130271699175,
|
|
"loss": 5.7707,
|
|
"mean_token_accuracy": 0.16446590721607207,
|
|
"num_tokens": 36261894.0,
|
|
"step": 18540
|
|
},
|
|
{
|
|
"entropy": 6.090643215179443,
|
|
"epoch": 1.8538011695906431,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004660424517028553,
|
|
"loss": 5.9269,
|
|
"mean_token_accuracy": 0.15943244099617004,
|
|
"num_tokens": 36271483.0,
|
|
"step": 18545
|
|
},
|
|
{
|
|
"entropy": 6.147729921340942,
|
|
"epoch": 1.8543009946518718,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00046602359588214,
|
|
"loss": 5.871,
|
|
"mean_token_accuracy": 0.15964867621660234,
|
|
"num_tokens": 36281038.0,
|
|
"step": 18550
|
|
},
|
|
{
|
|
"entropy": 6.037668180465698,
|
|
"epoch": 1.8548008197131005,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004660047352553202,
|
|
"loss": 5.6551,
|
|
"mean_token_accuracy": 0.17949103116989135,
|
|
"num_tokens": 36289718.0,
|
|
"step": 18555
|
|
},
|
|
{
|
|
"entropy": 6.109107208251953,
|
|
"epoch": 1.855300644774329,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00046598586982287034,
|
|
"loss": 5.7986,
|
|
"mean_token_accuracy": 0.16417734920978547,
|
|
"num_tokens": 36299912.0,
|
|
"step": 18560
|
|
},
|
|
{
|
|
"entropy": 6.09499888420105,
|
|
"epoch": 1.8558004698355575,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00046596699958526515,
|
|
"loss": 5.8508,
|
|
"mean_token_accuracy": 0.16241896152496338,
|
|
"num_tokens": 36309686.0,
|
|
"step": 18565
|
|
},
|
|
{
|
|
"entropy": 6.123609399795532,
|
|
"epoch": 1.8563002948967862,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00046594812454297944,
|
|
"loss": 5.8265,
|
|
"mean_token_accuracy": 0.16783982515335083,
|
|
"num_tokens": 36319247.0,
|
|
"step": 18570
|
|
},
|
|
{
|
|
"entropy": 6.036340618133545,
|
|
"epoch": 1.8568001199580149,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.000465929244696488,
|
|
"loss": 5.7813,
|
|
"mean_token_accuracy": 0.16871864944696427,
|
|
"num_tokens": 36329149.0,
|
|
"step": 18575
|
|
},
|
|
{
|
|
"entropy": 6.05415358543396,
|
|
"epoch": 1.8572999450192431,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004659103600462659,
|
|
"loss": 5.8282,
|
|
"mean_token_accuracy": 0.16690582633018494,
|
|
"num_tokens": 36338857.0,
|
|
"step": 18580
|
|
},
|
|
{
|
|
"entropy": 6.12278184890747,
|
|
"epoch": 1.8577997700804718,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004658914705927883,
|
|
"loss": 5.8596,
|
|
"mean_token_accuracy": 0.16016734540462493,
|
|
"num_tokens": 36349415.0,
|
|
"step": 18585
|
|
},
|
|
{
|
|
"entropy": 6.134076023101807,
|
|
"epoch": 1.8582995951417005,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004658725763365304,
|
|
"loss": 5.8283,
|
|
"mean_token_accuracy": 0.16324102580547334,
|
|
"num_tokens": 36359597.0,
|
|
"step": 18590
|
|
},
|
|
{
|
|
"entropy": 6.0458275318145756,
|
|
"epoch": 1.858799420202929,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004658536772779676,
|
|
"loss": 5.8085,
|
|
"mean_token_accuracy": 0.16813635528087617,
|
|
"num_tokens": 36369816.0,
|
|
"step": 18595
|
|
},
|
|
{
|
|
"entropy": 6.119785785675049,
|
|
"epoch": 1.8592992452641575,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004658347734175754,
|
|
"loss": 5.8741,
|
|
"mean_token_accuracy": 0.16267246454954148,
|
|
"num_tokens": 36380624.0,
|
|
"step": 18600
|
|
},
|
|
{
|
|
"entropy": 6.145242595672608,
|
|
"epoch": 1.8597990703253862,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00046581586475582946,
|
|
"loss": 5.7962,
|
|
"mean_token_accuracy": 0.16772578060626983,
|
|
"num_tokens": 36390597.0,
|
|
"step": 18605
|
|
},
|
|
{
|
|
"entropy": 6.173731803894043,
|
|
"epoch": 1.8602988953866146,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004657969512932054,
|
|
"loss": 5.8022,
|
|
"mean_token_accuracy": 0.15890775471925736,
|
|
"num_tokens": 36400404.0,
|
|
"step": 18610
|
|
},
|
|
{
|
|
"entropy": 6.059240627288818,
|
|
"epoch": 1.8607987204478431,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004657780330301791,
|
|
"loss": 5.8141,
|
|
"mean_token_accuracy": 0.16577143967151642,
|
|
"num_tokens": 36409599.0,
|
|
"step": 18615
|
|
},
|
|
{
|
|
"entropy": 6.00146484375,
|
|
"epoch": 1.8612985455090718,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00046575910996722657,
|
|
"loss": 5.7381,
|
|
"mean_token_accuracy": 0.17199854105710982,
|
|
"num_tokens": 36419217.0,
|
|
"step": 18620
|
|
},
|
|
{
|
|
"entropy": 6.13303575515747,
|
|
"epoch": 1.8617983705703005,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000465740182104824,
|
|
"loss": 5.8287,
|
|
"mean_token_accuracy": 0.16241230443120003,
|
|
"num_tokens": 36429097.0,
|
|
"step": 18625
|
|
},
|
|
{
|
|
"entropy": 6.1495208740234375,
|
|
"epoch": 1.862298195631529,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00046572124944344745,
|
|
"loss": 5.8112,
|
|
"mean_token_accuracy": 0.16782474666833877,
|
|
"num_tokens": 36439260.0,
|
|
"step": 18630
|
|
},
|
|
{
|
|
"entropy": 6.048889017105102,
|
|
"epoch": 1.8627980206927575,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00046570231198357344,
|
|
"loss": 5.7118,
|
|
"mean_token_accuracy": 0.168332302570343,
|
|
"num_tokens": 36449083.0,
|
|
"step": 18635
|
|
},
|
|
{
|
|
"entropy": 6.086647653579712,
|
|
"epoch": 1.8632978457539862,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004656833697256783,
|
|
"loss": 5.7904,
|
|
"mean_token_accuracy": 0.16602717638015746,
|
|
"num_tokens": 36459337.0,
|
|
"step": 18640
|
|
},
|
|
{
|
|
"entropy": 6.119024324417114,
|
|
"epoch": 1.8637976708152146,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004656644226702386,
|
|
"loss": 5.8718,
|
|
"mean_token_accuracy": 0.160018590092659,
|
|
"num_tokens": 36469132.0,
|
|
"step": 18645
|
|
},
|
|
{
|
|
"entropy": 6.1324108123779295,
|
|
"epoch": 1.8642974958764431,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00046564547081773115,
|
|
"loss": 5.8473,
|
|
"mean_token_accuracy": 0.16205427944660186,
|
|
"num_tokens": 36479111.0,
|
|
"step": 18650
|
|
},
|
|
{
|
|
"entropy": 6.137992858886719,
|
|
"epoch": 1.8647973209376718,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004656265141686326,
|
|
"loss": 5.764,
|
|
"mean_token_accuracy": 0.1681882843375206,
|
|
"num_tokens": 36488553.0,
|
|
"step": 18655
|
|
},
|
|
{
|
|
"entropy": 6.099249982833863,
|
|
"epoch": 1.8652971459989005,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00046560755272342014,
|
|
"loss": 5.8662,
|
|
"mean_token_accuracy": 0.1644662693142891,
|
|
"num_tokens": 36498719.0,
|
|
"step": 18660
|
|
},
|
|
{
|
|
"entropy": 6.14863862991333,
|
|
"epoch": 1.865796971060129,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004655885864825706,
|
|
"loss": 5.827,
|
|
"mean_token_accuracy": 0.16804136633872985,
|
|
"num_tokens": 36508332.0,
|
|
"step": 18665
|
|
},
|
|
{
|
|
"entropy": 6.058225774765015,
|
|
"epoch": 1.8662967961213575,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004655696154465613,
|
|
"loss": 5.8167,
|
|
"mean_token_accuracy": 0.16824888586997985,
|
|
"num_tokens": 36517867.0,
|
|
"step": 18670
|
|
},
|
|
{
|
|
"entropy": 6.1393426895141605,
|
|
"epoch": 1.8667966211825862,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00046555063961586956,
|
|
"loss": 5.8062,
|
|
"mean_token_accuracy": 0.1644602447748184,
|
|
"num_tokens": 36526734.0,
|
|
"step": 18675
|
|
},
|
|
{
|
|
"entropy": 6.075457143783569,
|
|
"epoch": 1.8672964462438146,
|
|
"grad_norm": 2.5,
|
|
"learning_rate": 0.0004655316589909727,
|
|
"loss": 5.8004,
|
|
"mean_token_accuracy": 0.16335614323616027,
|
|
"num_tokens": 36536381.0,
|
|
"step": 18680
|
|
},
|
|
{
|
|
"entropy": 6.091069602966309,
|
|
"epoch": 1.867796271305043,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004655126735723484,
|
|
"loss": 5.8244,
|
|
"mean_token_accuracy": 0.1625499665737152,
|
|
"num_tokens": 36545708.0,
|
|
"step": 18685
|
|
},
|
|
{
|
|
"entropy": 6.140816736221313,
|
|
"epoch": 1.8682960963662718,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00046549368336047415,
|
|
"loss": 5.8768,
|
|
"mean_token_accuracy": 0.15949410051107407,
|
|
"num_tokens": 36555616.0,
|
|
"step": 18690
|
|
},
|
|
{
|
|
"entropy": 6.18088436126709,
|
|
"epoch": 1.8687959214275005,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004654746883558279,
|
|
"loss": 5.9266,
|
|
"mean_token_accuracy": 0.1555531933903694,
|
|
"num_tokens": 36565394.0,
|
|
"step": 18695
|
|
},
|
|
{
|
|
"entropy": 6.096475648880005,
|
|
"epoch": 1.869295746488729,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004654556885588875,
|
|
"loss": 5.7468,
|
|
"mean_token_accuracy": 0.1720901310443878,
|
|
"num_tokens": 36576329.0,
|
|
"step": 18700
|
|
},
|
|
{
|
|
"entropy": 6.0128092765808105,
|
|
"epoch": 1.8697955715499575,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00046543668397013103,
|
|
"loss": 5.7644,
|
|
"mean_token_accuracy": 0.17060289084911345,
|
|
"num_tokens": 36585402.0,
|
|
"step": 18705
|
|
},
|
|
{
|
|
"entropy": 6.1823255062103275,
|
|
"epoch": 1.8702953966111862,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004654176745900365,
|
|
"loss": 5.9135,
|
|
"mean_token_accuracy": 0.1589534893631935,
|
|
"num_tokens": 36594318.0,
|
|
"step": 18710
|
|
},
|
|
{
|
|
"entropy": 6.135144996643066,
|
|
"epoch": 1.8707952216724146,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00046539866041908233,
|
|
"loss": 5.7948,
|
|
"mean_token_accuracy": 0.1630299687385559,
|
|
"num_tokens": 36605377.0,
|
|
"step": 18715
|
|
},
|
|
{
|
|
"entropy": 5.982225036621093,
|
|
"epoch": 1.871295046733643,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.00046537964145774687,
|
|
"loss": 5.6861,
|
|
"mean_token_accuracy": 0.17728904634714127,
|
|
"num_tokens": 36614860.0,
|
|
"step": 18720
|
|
},
|
|
{
|
|
"entropy": 5.915312910079956,
|
|
"epoch": 1.8717948717948718,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004653606177065086,
|
|
"loss": 5.6725,
|
|
"mean_token_accuracy": 0.17899990528821946,
|
|
"num_tokens": 36625968.0,
|
|
"step": 18725
|
|
},
|
|
{
|
|
"entropy": 6.111940240859985,
|
|
"epoch": 1.8722946968561005,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004653415891658462,
|
|
"loss": 5.809,
|
|
"mean_token_accuracy": 0.1674633502960205,
|
|
"num_tokens": 36633966.0,
|
|
"step": 18730
|
|
},
|
|
{
|
|
"entropy": 6.1302131652832035,
|
|
"epoch": 1.872794521917329,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00046532255583623837,
|
|
"loss": 5.837,
|
|
"mean_token_accuracy": 0.16682206392288207,
|
|
"num_tokens": 36644409.0,
|
|
"step": 18735
|
|
},
|
|
{
|
|
"entropy": 6.1166441440582275,
|
|
"epoch": 1.8732943469785575,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000465303517718164,
|
|
"loss": 5.8565,
|
|
"mean_token_accuracy": 0.1648477628827095,
|
|
"num_tokens": 36653660.0,
|
|
"step": 18740
|
|
},
|
|
{
|
|
"entropy": 6.113664865493774,
|
|
"epoch": 1.8737941720397862,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004652844748121021,
|
|
"loss": 5.7852,
|
|
"mean_token_accuracy": 0.16692061722278595,
|
|
"num_tokens": 36663590.0,
|
|
"step": 18745
|
|
},
|
|
{
|
|
"entropy": 6.224225616455078,
|
|
"epoch": 1.8742939971010146,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004652654271185318,
|
|
"loss": 5.8534,
|
|
"mean_token_accuracy": 0.16188222765922547,
|
|
"num_tokens": 36672448.0,
|
|
"step": 18750
|
|
},
|
|
{
|
|
"entropy": 6.175465631484985,
|
|
"epoch": 1.874793822162243,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00046524637463793233,
|
|
"loss": 5.9519,
|
|
"mean_token_accuracy": 0.15808349400758742,
|
|
"num_tokens": 36682901.0,
|
|
"step": 18755
|
|
},
|
|
{
|
|
"entropy": 6.111906719207764,
|
|
"epoch": 1.8752936472234718,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.000465227317370783,
|
|
"loss": 5.8205,
|
|
"mean_token_accuracy": 0.15902247428894042,
|
|
"num_tokens": 36693768.0,
|
|
"step": 18760
|
|
},
|
|
{
|
|
"entropy": 6.165689945220947,
|
|
"epoch": 1.8757934722847005,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00046520825531756326,
|
|
"loss": 5.9015,
|
|
"mean_token_accuracy": 0.16123343408107757,
|
|
"num_tokens": 36704005.0,
|
|
"step": 18765
|
|
},
|
|
{
|
|
"entropy": 6.118316316604615,
|
|
"epoch": 1.876293297345929,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004651891884787528,
|
|
"loss": 5.8204,
|
|
"mean_token_accuracy": 0.16417828798294068,
|
|
"num_tokens": 36712966.0,
|
|
"step": 18770
|
|
},
|
|
{
|
|
"entropy": 6.05847659111023,
|
|
"epoch": 1.8767931224071575,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00046517011685483136,
|
|
"loss": 5.7608,
|
|
"mean_token_accuracy": 0.17238716930150985,
|
|
"num_tokens": 36722160.0,
|
|
"step": 18775
|
|
},
|
|
{
|
|
"entropy": 6.089846897125244,
|
|
"epoch": 1.8772929474683862,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00046515104044627867,
|
|
"loss": 5.7706,
|
|
"mean_token_accuracy": 0.1676633507013321,
|
|
"num_tokens": 36731810.0,
|
|
"step": 18780
|
|
},
|
|
{
|
|
"entropy": 6.091346740722656,
|
|
"epoch": 1.8777927725296146,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004651319592535747,
|
|
"loss": 5.8547,
|
|
"mean_token_accuracy": 0.16267334520816804,
|
|
"num_tokens": 36741772.0,
|
|
"step": 18785
|
|
},
|
|
{
|
|
"entropy": 6.151124668121338,
|
|
"epoch": 1.878292597590843,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004651128732771996,
|
|
"loss": 5.8887,
|
|
"mean_token_accuracy": 0.1524428591132164,
|
|
"num_tokens": 36752060.0,
|
|
"step": 18790
|
|
},
|
|
{
|
|
"entropy": 6.1060394763946535,
|
|
"epoch": 1.8787924226520718,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00046509378251763346,
|
|
"loss": 5.8204,
|
|
"mean_token_accuracy": 0.16107624620199204,
|
|
"num_tokens": 36760590.0,
|
|
"step": 18795
|
|
},
|
|
{
|
|
"entropy": 6.020538806915283,
|
|
"epoch": 1.8792922477133005,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004650746869753567,
|
|
"loss": 5.7513,
|
|
"mean_token_accuracy": 0.16726432293653487,
|
|
"num_tokens": 36769628.0,
|
|
"step": 18800
|
|
},
|
|
{
|
|
"entropy": 6.063245010375977,
|
|
"epoch": 1.8797920727745288,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004650555866508498,
|
|
"loss": 5.7009,
|
|
"mean_token_accuracy": 0.17532316595315933,
|
|
"num_tokens": 36779498.0,
|
|
"step": 18805
|
|
},
|
|
{
|
|
"entropy": 6.064249420166016,
|
|
"epoch": 1.8802918978357575,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00046503648154459315,
|
|
"loss": 5.827,
|
|
"mean_token_accuracy": 0.16045496761798858,
|
|
"num_tokens": 36789789.0,
|
|
"step": 18810
|
|
},
|
|
{
|
|
"entropy": 6.0851274013519285,
|
|
"epoch": 1.8807917228969862,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004650173716570676,
|
|
"loss": 5.7245,
|
|
"mean_token_accuracy": 0.16367260962724686,
|
|
"num_tokens": 36800316.0,
|
|
"step": 18815
|
|
},
|
|
{
|
|
"entropy": 6.0716430187225345,
|
|
"epoch": 1.8812915479582146,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00046499825698875384,
|
|
"loss": 5.81,
|
|
"mean_token_accuracy": 0.16587711870670319,
|
|
"num_tokens": 36810811.0,
|
|
"step": 18820
|
|
},
|
|
{
|
|
"entropy": 6.076467037200928,
|
|
"epoch": 1.881791373019443,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00046497913754013284,
|
|
"loss": 5.7912,
|
|
"mean_token_accuracy": 0.16599448174238204,
|
|
"num_tokens": 36820439.0,
|
|
"step": 18825
|
|
},
|
|
{
|
|
"entropy": 6.0745596408844,
|
|
"epoch": 1.8822911980806718,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004649600133116856,
|
|
"loss": 5.7517,
|
|
"mean_token_accuracy": 0.16613928824663163,
|
|
"num_tokens": 36830363.0,
|
|
"step": 18830
|
|
},
|
|
{
|
|
"entropy": 6.062951469421387,
|
|
"epoch": 1.8827910231419005,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00046494088430389335,
|
|
"loss": 5.7607,
|
|
"mean_token_accuracy": 0.16686485707759857,
|
|
"num_tokens": 36840854.0,
|
|
"step": 18835
|
|
},
|
|
{
|
|
"entropy": 6.068666458129883,
|
|
"epoch": 1.8832908482031288,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004649217505172373,
|
|
"loss": 5.7497,
|
|
"mean_token_accuracy": 0.16259421557188034,
|
|
"num_tokens": 36850719.0,
|
|
"step": 18840
|
|
},
|
|
{
|
|
"entropy": 6.026221895217896,
|
|
"epoch": 1.8837906732643575,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004649026119521989,
|
|
"loss": 5.8325,
|
|
"mean_token_accuracy": 0.1626471608877182,
|
|
"num_tokens": 36861074.0,
|
|
"step": 18845
|
|
},
|
|
{
|
|
"entropy": 6.103958559036255,
|
|
"epoch": 1.8842904983255861,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00046488346860925955,
|
|
"loss": 5.829,
|
|
"mean_token_accuracy": 0.16128266006708145,
|
|
"num_tokens": 36870432.0,
|
|
"step": 18850
|
|
},
|
|
{
|
|
"entropy": 6.101656675338745,
|
|
"epoch": 1.8847903233868146,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00046486432048890104,
|
|
"loss": 5.7891,
|
|
"mean_token_accuracy": 0.16330398470163346,
|
|
"num_tokens": 36880213.0,
|
|
"step": 18855
|
|
},
|
|
{
|
|
"entropy": 6.060547304153443,
|
|
"epoch": 1.885290148448043,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004648451675916051,
|
|
"loss": 5.7903,
|
|
"mean_token_accuracy": 0.1623082637786865,
|
|
"num_tokens": 36889948.0,
|
|
"step": 18860
|
|
},
|
|
{
|
|
"entropy": 6.113190031051635,
|
|
"epoch": 1.8857899735092718,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00046482600991785365,
|
|
"loss": 5.8565,
|
|
"mean_token_accuracy": 0.16046745032072068,
|
|
"num_tokens": 36900211.0,
|
|
"step": 18865
|
|
},
|
|
{
|
|
"entropy": 6.101048135757447,
|
|
"epoch": 1.8862897985705003,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00046480684746812856,
|
|
"loss": 5.8452,
|
|
"mean_token_accuracy": 0.1693171039223671,
|
|
"num_tokens": 36909515.0,
|
|
"step": 18870
|
|
},
|
|
{
|
|
"entropy": 6.02421555519104,
|
|
"epoch": 1.8867896236317288,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00046478768024291205,
|
|
"loss": 5.7483,
|
|
"mean_token_accuracy": 0.17352455705404282,
|
|
"num_tokens": 36918057.0,
|
|
"step": 18875
|
|
},
|
|
{
|
|
"entropy": 6.087971305847168,
|
|
"epoch": 1.8872894486929574,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00046476850824268633,
|
|
"loss": 5.8362,
|
|
"mean_token_accuracy": 0.1680491015315056,
|
|
"num_tokens": 36926960.0,
|
|
"step": 18880
|
|
},
|
|
{
|
|
"entropy": 6.137731838226318,
|
|
"epoch": 1.8877892737541861,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004647493314679338,
|
|
"loss": 5.8423,
|
|
"mean_token_accuracy": 0.1665145441889763,
|
|
"num_tokens": 36936542.0,
|
|
"step": 18885
|
|
},
|
|
{
|
|
"entropy": 6.044464063644409,
|
|
"epoch": 1.8882890988154146,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.000464730149919137,
|
|
"loss": 5.679,
|
|
"mean_token_accuracy": 0.1785890817642212,
|
|
"num_tokens": 36946621.0,
|
|
"step": 18890
|
|
},
|
|
{
|
|
"entropy": 6.108857011795044,
|
|
"epoch": 1.888788923876643,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004647109635967783,
|
|
"loss": 5.7725,
|
|
"mean_token_accuracy": 0.16634008586406707,
|
|
"num_tokens": 36955813.0,
|
|
"step": 18895
|
|
},
|
|
{
|
|
"entropy": 6.015109014511109,
|
|
"epoch": 1.8892887489378718,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004646917725013406,
|
|
"loss": 5.7868,
|
|
"mean_token_accuracy": 0.16994795054197312,
|
|
"num_tokens": 36965924.0,
|
|
"step": 18900
|
|
},
|
|
{
|
|
"entropy": 6.1092418193817135,
|
|
"epoch": 1.8897885739991003,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004646725766333068,
|
|
"loss": 5.8463,
|
|
"mean_token_accuracy": 0.16430750787258147,
|
|
"num_tokens": 36975471.0,
|
|
"step": 18905
|
|
},
|
|
{
|
|
"entropy": 6.041192436218262,
|
|
"epoch": 1.8902883990603288,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00046465337599315966,
|
|
"loss": 5.725,
|
|
"mean_token_accuracy": 0.16990944743156433,
|
|
"num_tokens": 36985979.0,
|
|
"step": 18910
|
|
},
|
|
{
|
|
"entropy": 6.117856454849243,
|
|
"epoch": 1.8907882241215574,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00046463417058138247,
|
|
"loss": 5.9469,
|
|
"mean_token_accuracy": 0.1584871880710125,
|
|
"num_tokens": 36996357.0,
|
|
"step": 18915
|
|
},
|
|
{
|
|
"entropy": 6.092455005645752,
|
|
"epoch": 1.8912880491827861,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004646149603984583,
|
|
"loss": 5.7582,
|
|
"mean_token_accuracy": 0.1701499789953232,
|
|
"num_tokens": 37006193.0,
|
|
"step": 18920
|
|
},
|
|
{
|
|
"entropy": 6.146443319320679,
|
|
"epoch": 1.8917878742440146,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004645957454448706,
|
|
"loss": 5.9162,
|
|
"mean_token_accuracy": 0.15966390073299408,
|
|
"num_tokens": 37015887.0,
|
|
"step": 18925
|
|
},
|
|
{
|
|
"entropy": 6.225219345092773,
|
|
"epoch": 1.892287699305243,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004645765257211026,
|
|
"loss": 5.8925,
|
|
"mean_token_accuracy": 0.15528341382741928,
|
|
"num_tokens": 37026869.0,
|
|
"step": 18930
|
|
},
|
|
{
|
|
"entropy": 6.171398591995239,
|
|
"epoch": 1.8927875243664718,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00046455730122763804,
|
|
"loss": 5.8659,
|
|
"mean_token_accuracy": 0.1599810615181923,
|
|
"num_tokens": 37036170.0,
|
|
"step": 18935
|
|
},
|
|
{
|
|
"entropy": 6.107275915145874,
|
|
"epoch": 1.8932873494277003,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004645380719649606,
|
|
"loss": 5.837,
|
|
"mean_token_accuracy": 0.16070839166641235,
|
|
"num_tokens": 37046843.0,
|
|
"step": 18940
|
|
},
|
|
{
|
|
"entropy": 6.101402759552002,
|
|
"epoch": 1.8937871744889287,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00046451883793355406,
|
|
"loss": 5.8273,
|
|
"mean_token_accuracy": 0.16346073895692825,
|
|
"num_tokens": 37056948.0,
|
|
"step": 18945
|
|
},
|
|
{
|
|
"entropy": 6.049373292922974,
|
|
"epoch": 1.8942869995501574,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00046449959913390227,
|
|
"loss": 5.7238,
|
|
"mean_token_accuracy": 0.17013953775167465,
|
|
"num_tokens": 37066600.0,
|
|
"step": 18950
|
|
},
|
|
{
|
|
"entropy": 6.088477706909179,
|
|
"epoch": 1.8947868246113861,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00046448035556648936,
|
|
"loss": 5.7939,
|
|
"mean_token_accuracy": 0.1678351119160652,
|
|
"num_tokens": 37076192.0,
|
|
"step": 18955
|
|
},
|
|
{
|
|
"entropy": 6.070483446121216,
|
|
"epoch": 1.8952866496726146,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00046446110723179945,
|
|
"loss": 5.814,
|
|
"mean_token_accuracy": 0.17091581523418425,
|
|
"num_tokens": 37087403.0,
|
|
"step": 18960
|
|
},
|
|
{
|
|
"entropy": 6.191273880004883,
|
|
"epoch": 1.895786474733843,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004644418541303169,
|
|
"loss": 5.9261,
|
|
"mean_token_accuracy": 0.16047690361738204,
|
|
"num_tokens": 37096643.0,
|
|
"step": 18965
|
|
},
|
|
{
|
|
"entropy": 6.148874282836914,
|
|
"epoch": 1.8962862997950718,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00046442259626252593,
|
|
"loss": 5.8006,
|
|
"mean_token_accuracy": 0.17177630066871644,
|
|
"num_tokens": 37106088.0,
|
|
"step": 18970
|
|
},
|
|
{
|
|
"entropy": 6.111350345611572,
|
|
"epoch": 1.8967861248563003,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00046440333362891123,
|
|
"loss": 5.7977,
|
|
"mean_token_accuracy": 0.165407395362854,
|
|
"num_tokens": 37115830.0,
|
|
"step": 18975
|
|
},
|
|
{
|
|
"entropy": 6.044348859786988,
|
|
"epoch": 1.8972859499175287,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004643840662299574,
|
|
"loss": 5.803,
|
|
"mean_token_accuracy": 0.1653302490711212,
|
|
"num_tokens": 37125311.0,
|
|
"step": 18980
|
|
},
|
|
{
|
|
"entropy": 6.056293296813965,
|
|
"epoch": 1.8977857749787574,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004643647940661492,
|
|
"loss": 5.7217,
|
|
"mean_token_accuracy": 0.1769422858953476,
|
|
"num_tokens": 37135716.0,
|
|
"step": 18985
|
|
},
|
|
{
|
|
"entropy": 6.067849445343017,
|
|
"epoch": 1.8982856000399861,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00046434551713797146,
|
|
"loss": 5.6988,
|
|
"mean_token_accuracy": 0.17255447953939437,
|
|
"num_tokens": 37145112.0,
|
|
"step": 18990
|
|
},
|
|
{
|
|
"entropy": 6.082761764526367,
|
|
"epoch": 1.8987854251012146,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004643262354459093,
|
|
"loss": 5.8607,
|
|
"mean_token_accuracy": 0.15101508647203446,
|
|
"num_tokens": 37155081.0,
|
|
"step": 18995
|
|
},
|
|
{
|
|
"entropy": 6.015715885162353,
|
|
"epoch": 1.899285250162443,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.00046430694899044774,
|
|
"loss": 5.7981,
|
|
"mean_token_accuracy": 0.17128389179706574,
|
|
"num_tokens": 37165633.0,
|
|
"step": 19000
|
|
},
|
|
{
|
|
"entropy": 6.1866593837738035,
|
|
"epoch": 1.8997850752236718,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000464287657772072,
|
|
"loss": 5.7622,
|
|
"mean_token_accuracy": 0.160648849606514,
|
|
"num_tokens": 37175842.0,
|
|
"step": 19005
|
|
},
|
|
{
|
|
"entropy": 6.1480621814727785,
|
|
"epoch": 1.9002849002849003,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004642683617912676,
|
|
"loss": 5.893,
|
|
"mean_token_accuracy": 0.1568323254585266,
|
|
"num_tokens": 37185076.0,
|
|
"step": 19010
|
|
},
|
|
{
|
|
"entropy": 6.084721040725708,
|
|
"epoch": 1.9007847253461287,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00046424906104851994,
|
|
"loss": 5.7735,
|
|
"mean_token_accuracy": 0.16792121678590774,
|
|
"num_tokens": 37195088.0,
|
|
"step": 19015
|
|
},
|
|
{
|
|
"entropy": 6.099788093566895,
|
|
"epoch": 1.9012845504073574,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00046422975554431453,
|
|
"loss": 5.8417,
|
|
"mean_token_accuracy": 0.15713683962821962,
|
|
"num_tokens": 37205082.0,
|
|
"step": 19020
|
|
},
|
|
{
|
|
"entropy": 6.069739151000976,
|
|
"epoch": 1.9017843754685861,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00046421044527913713,
|
|
"loss": 5.7479,
|
|
"mean_token_accuracy": 0.16574580520391463,
|
|
"num_tokens": 37215097.0,
|
|
"step": 19025
|
|
},
|
|
{
|
|
"entropy": 6.145927429199219,
|
|
"epoch": 1.9022842005298146,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004641911302534737,
|
|
"loss": 5.8628,
|
|
"mean_token_accuracy": 0.16157404631376265,
|
|
"num_tokens": 37225461.0,
|
|
"step": 19030
|
|
},
|
|
{
|
|
"entropy": 6.147272396087646,
|
|
"epoch": 1.902784025591043,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.00046417181046781004,
|
|
"loss": 5.9328,
|
|
"mean_token_accuracy": 0.1602594330906868,
|
|
"num_tokens": 37235033.0,
|
|
"step": 19035
|
|
},
|
|
{
|
|
"entropy": 6.157132816314697,
|
|
"epoch": 1.9032838506522718,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004641524859226324,
|
|
"loss": 5.8731,
|
|
"mean_token_accuracy": 0.16238587200641633,
|
|
"num_tokens": 37245407.0,
|
|
"step": 19040
|
|
},
|
|
{
|
|
"entropy": 6.1859447956085205,
|
|
"epoch": 1.9037836757135003,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00046413315661842676,
|
|
"loss": 5.9497,
|
|
"mean_token_accuracy": 0.15690101087093353,
|
|
"num_tokens": 37255654.0,
|
|
"step": 19045
|
|
},
|
|
{
|
|
"entropy": 6.165120697021484,
|
|
"epoch": 1.9042835007747287,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004641138225556797,
|
|
"loss": 5.8542,
|
|
"mean_token_accuracy": 0.16876156479120255,
|
|
"num_tokens": 37264461.0,
|
|
"step": 19050
|
|
},
|
|
{
|
|
"entropy": 6.015301036834717,
|
|
"epoch": 1.9047833258359574,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004640944837348774,
|
|
"loss": 5.7112,
|
|
"mean_token_accuracy": 0.17316190749406815,
|
|
"num_tokens": 37273893.0,
|
|
"step": 19055
|
|
},
|
|
{
|
|
"entropy": 6.104934787750244,
|
|
"epoch": 1.9052831508971861,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.00046407514015650667,
|
|
"loss": 5.8678,
|
|
"mean_token_accuracy": 0.1565048411488533,
|
|
"num_tokens": 37282784.0,
|
|
"step": 19060
|
|
},
|
|
{
|
|
"entropy": 6.09890398979187,
|
|
"epoch": 1.9057829759584144,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00046405579182105393,
|
|
"loss": 5.8589,
|
|
"mean_token_accuracy": 0.15970478504896163,
|
|
"num_tokens": 37291990.0,
|
|
"step": 19065
|
|
},
|
|
{
|
|
"entropy": 6.112426328659057,
|
|
"epoch": 1.906282801019643,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004640364387290062,
|
|
"loss": 5.7578,
|
|
"mean_token_accuracy": 0.16788182854652406,
|
|
"num_tokens": 37302451.0,
|
|
"step": 19070
|
|
},
|
|
{
|
|
"entropy": 6.141508674621582,
|
|
"epoch": 1.9067826260808718,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00046401708088085036,
|
|
"loss": 5.8364,
|
|
"mean_token_accuracy": 0.16574998944997787,
|
|
"num_tokens": 37313035.0,
|
|
"step": 19075
|
|
},
|
|
{
|
|
"entropy": 6.058089303970337,
|
|
"epoch": 1.9072824511421003,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00046399771827707335,
|
|
"loss": 5.8061,
|
|
"mean_token_accuracy": 0.1655999407172203,
|
|
"num_tokens": 37323107.0,
|
|
"step": 19080
|
|
},
|
|
{
|
|
"entropy": 6.074736595153809,
|
|
"epoch": 1.9077822762033287,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.00046397835091816235,
|
|
"loss": 5.8272,
|
|
"mean_token_accuracy": 0.16684531718492507,
|
|
"num_tokens": 37332180.0,
|
|
"step": 19085
|
|
},
|
|
{
|
|
"entropy": 5.990530920028687,
|
|
"epoch": 1.9082821012645574,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00046395897880460474,
|
|
"loss": 5.7515,
|
|
"mean_token_accuracy": 0.18249568194150925,
|
|
"num_tokens": 37341588.0,
|
|
"step": 19090
|
|
},
|
|
{
|
|
"entropy": 5.98441596031189,
|
|
"epoch": 1.9087819263257861,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00046393960193688783,
|
|
"loss": 5.7245,
|
|
"mean_token_accuracy": 0.1684180900454521,
|
|
"num_tokens": 37350969.0,
|
|
"step": 19095
|
|
},
|
|
{
|
|
"entropy": 6.191913652420044,
|
|
"epoch": 1.9092817513870144,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00046392022031549907,
|
|
"loss": 5.8839,
|
|
"mean_token_accuracy": 0.1639529585838318,
|
|
"num_tokens": 37360387.0,
|
|
"step": 19100
|
|
},
|
|
{
|
|
"entropy": 6.091094255447388,
|
|
"epoch": 1.909781576448243,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004639008339409263,
|
|
"loss": 5.8227,
|
|
"mean_token_accuracy": 0.17135983407497407,
|
|
"num_tokens": 37369443.0,
|
|
"step": 19105
|
|
},
|
|
{
|
|
"entropy": 6.079126071929932,
|
|
"epoch": 1.9102814015094718,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004638814428136571,
|
|
"loss": 5.7769,
|
|
"mean_token_accuracy": 0.1699872389435768,
|
|
"num_tokens": 37379111.0,
|
|
"step": 19110
|
|
},
|
|
{
|
|
"entropy": 6.105374145507812,
|
|
"epoch": 1.9107812265707003,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004638620469341794,
|
|
"loss": 5.8077,
|
|
"mean_token_accuracy": 0.17102467268705368,
|
|
"num_tokens": 37389880.0,
|
|
"step": 19115
|
|
},
|
|
{
|
|
"entropy": 6.031556272506714,
|
|
"epoch": 1.9112810516319287,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004638426463029812,
|
|
"loss": 5.7066,
|
|
"mean_token_accuracy": 0.16917487978935242,
|
|
"num_tokens": 37400055.0,
|
|
"step": 19120
|
|
},
|
|
{
|
|
"entropy": 6.153701877593994,
|
|
"epoch": 1.9117808766931574,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004638232409205506,
|
|
"loss": 5.8544,
|
|
"mean_token_accuracy": 0.16253732442855834,
|
|
"num_tokens": 37409223.0,
|
|
"step": 19125
|
|
},
|
|
{
|
|
"entropy": 6.132917881011963,
|
|
"epoch": 1.912280701754386,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00046380383078737584,
|
|
"loss": 5.8684,
|
|
"mean_token_accuracy": 0.16904034316539765,
|
|
"num_tokens": 37418480.0,
|
|
"step": 19130
|
|
},
|
|
{
|
|
"entropy": 6.077174139022827,
|
|
"epoch": 1.9127805268156144,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00046378441590394525,
|
|
"loss": 5.8051,
|
|
"mean_token_accuracy": 0.164736245572567,
|
|
"num_tokens": 37428578.0,
|
|
"step": 19135
|
|
},
|
|
{
|
|
"entropy": 6.104228973388672,
|
|
"epoch": 1.913280351876843,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004637649962707474,
|
|
"loss": 5.7656,
|
|
"mean_token_accuracy": 0.164133220911026,
|
|
"num_tokens": 37438847.0,
|
|
"step": 19140
|
|
},
|
|
{
|
|
"entropy": 6.087374877929688,
|
|
"epoch": 1.9137801769380718,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00046374557188827084,
|
|
"loss": 5.7777,
|
|
"mean_token_accuracy": 0.16641025096178055,
|
|
"num_tokens": 37448369.0,
|
|
"step": 19145
|
|
},
|
|
{
|
|
"entropy": 6.112240743637085,
|
|
"epoch": 1.9142800019993003,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004637261427570042,
|
|
"loss": 5.9298,
|
|
"mean_token_accuracy": 0.16082784086465834,
|
|
"num_tokens": 37457899.0,
|
|
"step": 19150
|
|
},
|
|
{
|
|
"entropy": 6.090391683578491,
|
|
"epoch": 1.9147798270605287,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004637067088774364,
|
|
"loss": 5.7699,
|
|
"mean_token_accuracy": 0.16978160440921783,
|
|
"num_tokens": 37468429.0,
|
|
"step": 19155
|
|
},
|
|
{
|
|
"entropy": 6.178743839263916,
|
|
"epoch": 1.9152796521217574,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00046368727025005634,
|
|
"loss": 5.9284,
|
|
"mean_token_accuracy": 0.1607283264398575,
|
|
"num_tokens": 37479009.0,
|
|
"step": 19160
|
|
},
|
|
{
|
|
"entropy": 6.069395732879639,
|
|
"epoch": 1.915779477182986,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00046366782687535315,
|
|
"loss": 5.7768,
|
|
"mean_token_accuracy": 0.16641553193330766,
|
|
"num_tokens": 37488114.0,
|
|
"step": 19165
|
|
},
|
|
{
|
|
"entropy": 6.119457006454468,
|
|
"epoch": 1.9162793022442144,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000463648378753816,
|
|
"loss": 5.7636,
|
|
"mean_token_accuracy": 0.16729666590690612,
|
|
"num_tokens": 37497477.0,
|
|
"step": 19170
|
|
},
|
|
{
|
|
"entropy": 6.191433572769165,
|
|
"epoch": 1.916779127305443,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00046362892588593406,
|
|
"loss": 5.8444,
|
|
"mean_token_accuracy": 0.1632758781313896,
|
|
"num_tokens": 37507126.0,
|
|
"step": 19175
|
|
},
|
|
{
|
|
"entropy": 6.165030574798584,
|
|
"epoch": 1.9172789523666718,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00046360946827219703,
|
|
"loss": 5.921,
|
|
"mean_token_accuracy": 0.15919571593403817,
|
|
"num_tokens": 37517625.0,
|
|
"step": 19180
|
|
},
|
|
{
|
|
"entropy": 6.207913064956665,
|
|
"epoch": 1.9177787774279003,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004635900059130942,
|
|
"loss": 5.931,
|
|
"mean_token_accuracy": 0.1563483089208603,
|
|
"num_tokens": 37528761.0,
|
|
"step": 19185
|
|
},
|
|
{
|
|
"entropy": 6.138037633895874,
|
|
"epoch": 1.9182786024891287,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004635705388091154,
|
|
"loss": 5.8433,
|
|
"mean_token_accuracy": 0.16442470699548722,
|
|
"num_tokens": 37538513.0,
|
|
"step": 19190
|
|
},
|
|
{
|
|
"entropy": 6.045541048049927,
|
|
"epoch": 1.9187784275503574,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004635510669607504,
|
|
"loss": 5.8271,
|
|
"mean_token_accuracy": 0.16678439527750016,
|
|
"num_tokens": 37548266.0,
|
|
"step": 19195
|
|
},
|
|
{
|
|
"entropy": 6.094783115386963,
|
|
"epoch": 1.919278252611586,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000463531590368489,
|
|
"loss": 5.7605,
|
|
"mean_token_accuracy": 0.17043652534484863,
|
|
"num_tokens": 37558544.0,
|
|
"step": 19200
|
|
},
|
|
{
|
|
"entropy": 6.125850105285645,
|
|
"epoch": 1.9197780776728144,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00046351210903282136,
|
|
"loss": 5.8217,
|
|
"mean_token_accuracy": 0.1598704695701599,
|
|
"num_tokens": 37568430.0,
|
|
"step": 19205
|
|
},
|
|
{
|
|
"entropy": 6.108664894104004,
|
|
"epoch": 1.920277902734043,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00046349262295423754,
|
|
"loss": 5.8672,
|
|
"mean_token_accuracy": 0.15483100712299347,
|
|
"num_tokens": 37579286.0,
|
|
"step": 19210
|
|
},
|
|
{
|
|
"entropy": 6.1108033657073975,
|
|
"epoch": 1.9207777277952718,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00046347313213322786,
|
|
"loss": 5.824,
|
|
"mean_token_accuracy": 0.1595865234732628,
|
|
"num_tokens": 37590142.0,
|
|
"step": 19215
|
|
},
|
|
{
|
|
"entropy": 6.184304428100586,
|
|
"epoch": 1.9212775528565003,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004634536365702826,
|
|
"loss": 5.9867,
|
|
"mean_token_accuracy": 0.1512823536992073,
|
|
"num_tokens": 37600498.0,
|
|
"step": 19220
|
|
},
|
|
{
|
|
"entropy": 6.100282382965088,
|
|
"epoch": 1.9217773779177287,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00046343413626589243,
|
|
"loss": 5.8672,
|
|
"mean_token_accuracy": 0.16209751814603807,
|
|
"num_tokens": 37610530.0,
|
|
"step": 19225
|
|
},
|
|
{
|
|
"entropy": 6.043549346923828,
|
|
"epoch": 1.9222772029789574,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004634146312205478,
|
|
"loss": 5.7819,
|
|
"mean_token_accuracy": 0.1725287675857544,
|
|
"num_tokens": 37621267.0,
|
|
"step": 19230
|
|
},
|
|
{
|
|
"entropy": 6.183690786361694,
|
|
"epoch": 1.922777028040186,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00046339512143473956,
|
|
"loss": 5.9282,
|
|
"mean_token_accuracy": 0.15366215333342553,
|
|
"num_tokens": 37632609.0,
|
|
"step": 19235
|
|
},
|
|
{
|
|
"entropy": 6.119522523880005,
|
|
"epoch": 1.9232768531014144,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00046337560690895856,
|
|
"loss": 5.7131,
|
|
"mean_token_accuracy": 0.17188965678215026,
|
|
"num_tokens": 37641757.0,
|
|
"step": 19240
|
|
},
|
|
{
|
|
"entropy": 6.140407419204712,
|
|
"epoch": 1.923776678162643,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00046335608764369574,
|
|
"loss": 5.8901,
|
|
"mean_token_accuracy": 0.15826768726110457,
|
|
"num_tokens": 37651021.0,
|
|
"step": 19245
|
|
},
|
|
{
|
|
"entropy": 6.144965267181396,
|
|
"epoch": 1.9242765032238718,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.00046333656363944226,
|
|
"loss": 5.8144,
|
|
"mean_token_accuracy": 0.16150998175144196,
|
|
"num_tokens": 37659965.0,
|
|
"step": 19250
|
|
},
|
|
{
|
|
"entropy": 6.065109968185425,
|
|
"epoch": 1.9247763282851003,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00046331703489668925,
|
|
"loss": 5.805,
|
|
"mean_token_accuracy": 0.18027915209531784,
|
|
"num_tokens": 37669957.0,
|
|
"step": 19255
|
|
},
|
|
{
|
|
"entropy": 6.108649587631225,
|
|
"epoch": 1.9252761533463287,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00046329750141592814,
|
|
"loss": 5.7256,
|
|
"mean_token_accuracy": 0.16809334903955458,
|
|
"num_tokens": 37678585.0,
|
|
"step": 19260
|
|
},
|
|
{
|
|
"entropy": 6.091938924789429,
|
|
"epoch": 1.9257759784075574,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004632779631976503,
|
|
"loss": 5.8313,
|
|
"mean_token_accuracy": 0.16486683189868928,
|
|
"num_tokens": 37688315.0,
|
|
"step": 19265
|
|
},
|
|
{
|
|
"entropy": 6.137817859649658,
|
|
"epoch": 1.926275803468786,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.00046325842024234735,
|
|
"loss": 5.9211,
|
|
"mean_token_accuracy": 0.15983497798442842,
|
|
"num_tokens": 37699042.0,
|
|
"step": 19270
|
|
},
|
|
{
|
|
"entropy": 6.122247648239136,
|
|
"epoch": 1.9267756285300144,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00046323887255051105,
|
|
"loss": 5.7963,
|
|
"mean_token_accuracy": 0.16680215299129486,
|
|
"num_tokens": 37709607.0,
|
|
"step": 19275
|
|
},
|
|
{
|
|
"entropy": 6.1294698238372805,
|
|
"epoch": 1.927275453591243,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00046321932012263317,
|
|
"loss": 5.7602,
|
|
"mean_token_accuracy": 0.16599445715546607,
|
|
"num_tokens": 37718893.0,
|
|
"step": 19280
|
|
},
|
|
{
|
|
"entropy": 6.077314281463623,
|
|
"epoch": 1.9277752786524718,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004631997629592055,
|
|
"loss": 5.817,
|
|
"mean_token_accuracy": 0.1607205592095852,
|
|
"num_tokens": 37730786.0,
|
|
"step": 19285
|
|
},
|
|
{
|
|
"entropy": 6.131097602844238,
|
|
"epoch": 1.9282751037137003,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.0004631802010607204,
|
|
"loss": 5.8882,
|
|
"mean_token_accuracy": 0.1540803477168083,
|
|
"num_tokens": 37740801.0,
|
|
"step": 19290
|
|
},
|
|
{
|
|
"entropy": 6.083081865310669,
|
|
"epoch": 1.9287749287749287,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00046316063442766975,
|
|
"loss": 5.7199,
|
|
"mean_token_accuracy": 0.1697300598025322,
|
|
"num_tokens": 37750580.0,
|
|
"step": 19295
|
|
},
|
|
{
|
|
"entropy": 5.982817125320435,
|
|
"epoch": 1.9292747538361574,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00046314106306054596,
|
|
"loss": 5.6672,
|
|
"mean_token_accuracy": 0.17828288823366165,
|
|
"num_tokens": 37759915.0,
|
|
"step": 19300
|
|
},
|
|
{
|
|
"entropy": 6.211821222305298,
|
|
"epoch": 1.929774578897386,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00046312148695984147,
|
|
"loss": 5.9687,
|
|
"mean_token_accuracy": 0.15266973823308944,
|
|
"num_tokens": 37770648.0,
|
|
"step": 19305
|
|
},
|
|
{
|
|
"entropy": 6.160683059692383,
|
|
"epoch": 1.9302744039586144,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004631019061260488,
|
|
"loss": 5.7058,
|
|
"mean_token_accuracy": 0.17261725217103957,
|
|
"num_tokens": 37779612.0,
|
|
"step": 19310
|
|
},
|
|
{
|
|
"entropy": 6.059337568283081,
|
|
"epoch": 1.930774229019843,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004630823205596605,
|
|
"loss": 5.8047,
|
|
"mean_token_accuracy": 0.16667267084121704,
|
|
"num_tokens": 37789813.0,
|
|
"step": 19315
|
|
},
|
|
{
|
|
"entropy": 6.105976343154907,
|
|
"epoch": 1.9312740540810718,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00046306273026116944,
|
|
"loss": 5.8207,
|
|
"mean_token_accuracy": 0.1636005625128746,
|
|
"num_tokens": 37799706.0,
|
|
"step": 19320
|
|
},
|
|
{
|
|
"entropy": 6.167033576965332,
|
|
"epoch": 1.9317738791423,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004630431352310685,
|
|
"loss": 5.8797,
|
|
"mean_token_accuracy": 0.1581083968281746,
|
|
"num_tokens": 37809787.0,
|
|
"step": 19325
|
|
},
|
|
{
|
|
"entropy": 6.103306293487549,
|
|
"epoch": 1.9322737042035287,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00046302353546985066,
|
|
"loss": 5.84,
|
|
"mean_token_accuracy": 0.16325974762439727,
|
|
"num_tokens": 37821091.0,
|
|
"step": 19330
|
|
},
|
|
{
|
|
"entropy": 6.077139663696289,
|
|
"epoch": 1.9327735292647574,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.000463003930978009,
|
|
"loss": 5.7498,
|
|
"mean_token_accuracy": 0.1634071111679077,
|
|
"num_tokens": 37830467.0,
|
|
"step": 19335
|
|
},
|
|
{
|
|
"entropy": 6.086410856246948,
|
|
"epoch": 1.933273354325986,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004629843217560369,
|
|
"loss": 5.8007,
|
|
"mean_token_accuracy": 0.16258842945098878,
|
|
"num_tokens": 37839666.0,
|
|
"step": 19340
|
|
},
|
|
{
|
|
"entropy": 6.11778039932251,
|
|
"epoch": 1.9337731793872144,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004629647078044276,
|
|
"loss": 5.8849,
|
|
"mean_token_accuracy": 0.16179901510477065,
|
|
"num_tokens": 37848255.0,
|
|
"step": 19345
|
|
},
|
|
{
|
|
"entropy": 5.956648206710815,
|
|
"epoch": 1.934273004448443,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004629450891236746,
|
|
"loss": 5.6493,
|
|
"mean_token_accuracy": 0.1779637709259987,
|
|
"num_tokens": 37858077.0,
|
|
"step": 19350
|
|
},
|
|
{
|
|
"entropy": 6.086611270904541,
|
|
"epoch": 1.9347728295096718,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004629254657142715,
|
|
"loss": 5.8537,
|
|
"mean_token_accuracy": 0.16635037511587142,
|
|
"num_tokens": 37868027.0,
|
|
"step": 19355
|
|
},
|
|
{
|
|
"entropy": 6.134270286560058,
|
|
"epoch": 1.9352726545709,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004629058375767121,
|
|
"loss": 5.8106,
|
|
"mean_token_accuracy": 0.1716615378856659,
|
|
"num_tokens": 37877952.0,
|
|
"step": 19360
|
|
},
|
|
{
|
|
"entropy": 6.102794408798218,
|
|
"epoch": 1.9357724796321287,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00046288620471149014,
|
|
"loss": 5.8323,
|
|
"mean_token_accuracy": 0.16419207751750947,
|
|
"num_tokens": 37888873.0,
|
|
"step": 19365
|
|
},
|
|
{
|
|
"entropy": 6.065708494186401,
|
|
"epoch": 1.9362723046933574,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00046286656711909966,
|
|
"loss": 5.7078,
|
|
"mean_token_accuracy": 0.17006196975708007,
|
|
"num_tokens": 37898360.0,
|
|
"step": 19370
|
|
},
|
|
{
|
|
"entropy": 5.998361444473266,
|
|
"epoch": 1.936772129754586,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00046284692480003467,
|
|
"loss": 5.8257,
|
|
"mean_token_accuracy": 0.16465667635202408,
|
|
"num_tokens": 37908620.0,
|
|
"step": 19375
|
|
},
|
|
{
|
|
"entropy": 6.103675651550293,
|
|
"epoch": 1.9372719548158144,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00046282727775478935,
|
|
"loss": 5.8878,
|
|
"mean_token_accuracy": 0.16391040235757828,
|
|
"num_tokens": 37917939.0,
|
|
"step": 19380
|
|
},
|
|
{
|
|
"entropy": 6.149976396560669,
|
|
"epoch": 1.937771779877043,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004628076259838581,
|
|
"loss": 5.8044,
|
|
"mean_token_accuracy": 0.1676780566573143,
|
|
"num_tokens": 37928044.0,
|
|
"step": 19385
|
|
},
|
|
{
|
|
"entropy": 6.136116647720337,
|
|
"epoch": 1.9382716049382716,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00046278796948773525,
|
|
"loss": 5.7677,
|
|
"mean_token_accuracy": 0.16710995137691498,
|
|
"num_tokens": 37937853.0,
|
|
"step": 19390
|
|
},
|
|
{
|
|
"entropy": 6.064478778839112,
|
|
"epoch": 1.9387714299995,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.00046276830826691553,
|
|
"loss": 5.8268,
|
|
"mean_token_accuracy": 0.16343286037445068,
|
|
"num_tokens": 37946949.0,
|
|
"step": 19395
|
|
},
|
|
{
|
|
"entropy": 6.115055322647095,
|
|
"epoch": 1.9392712550607287,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00046274864232189334,
|
|
"loss": 5.8834,
|
|
"mean_token_accuracy": 0.15669015869498254,
|
|
"num_tokens": 37958038.0,
|
|
"step": 19400
|
|
},
|
|
{
|
|
"entropy": 6.193453741073609,
|
|
"epoch": 1.9397710801219574,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00046272897165316367,
|
|
"loss": 5.848,
|
|
"mean_token_accuracy": 0.16533450037240982,
|
|
"num_tokens": 37968751.0,
|
|
"step": 19405
|
|
},
|
|
{
|
|
"entropy": 6.055865669250489,
|
|
"epoch": 1.940270905183186,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004627092962612215,
|
|
"loss": 5.7772,
|
|
"mean_token_accuracy": 0.16406439542770385,
|
|
"num_tokens": 37979758.0,
|
|
"step": 19410
|
|
},
|
|
{
|
|
"entropy": 6.120651292800903,
|
|
"epoch": 1.9407707302444144,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004626896161465616,
|
|
"loss": 5.8806,
|
|
"mean_token_accuracy": 0.1569210797548294,
|
|
"num_tokens": 37989776.0,
|
|
"step": 19415
|
|
},
|
|
{
|
|
"entropy": 6.079971694946289,
|
|
"epoch": 1.941270555305643,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00046266993130967925,
|
|
"loss": 5.7539,
|
|
"mean_token_accuracy": 0.16824226528406144,
|
|
"num_tokens": 37999715.0,
|
|
"step": 19420
|
|
},
|
|
{
|
|
"entropy": 6.087408065795898,
|
|
"epoch": 1.9417703803668716,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004626502417510698,
|
|
"loss": 5.8135,
|
|
"mean_token_accuracy": 0.167626566439867,
|
|
"num_tokens": 38010161.0,
|
|
"step": 19425
|
|
},
|
|
{
|
|
"entropy": 6.08631854057312,
|
|
"epoch": 1.9422702054281,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00046263054747122857,
|
|
"loss": 5.7972,
|
|
"mean_token_accuracy": 0.17314853072166442,
|
|
"num_tokens": 38019569.0,
|
|
"step": 19430
|
|
},
|
|
{
|
|
"entropy": 6.131941175460815,
|
|
"epoch": 1.9427700304893287,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004626108484706509,
|
|
"loss": 5.8303,
|
|
"mean_token_accuracy": 0.16236521899700165,
|
|
"num_tokens": 38029366.0,
|
|
"step": 19435
|
|
},
|
|
{
|
|
"entropy": 6.051262950897216,
|
|
"epoch": 1.9432698555505574,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00046259114474983266,
|
|
"loss": 5.7911,
|
|
"mean_token_accuracy": 0.16705298125743867,
|
|
"num_tokens": 38038606.0,
|
|
"step": 19440
|
|
},
|
|
{
|
|
"entropy": 6.027880239486694,
|
|
"epoch": 1.943769680611786,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00046257143630926953,
|
|
"loss": 5.6813,
|
|
"mean_token_accuracy": 0.17403662651777269,
|
|
"num_tokens": 38049045.0,
|
|
"step": 19445
|
|
},
|
|
{
|
|
"entropy": 6.156255626678467,
|
|
"epoch": 1.9442695056730144,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004625517231494573,
|
|
"loss": 5.9197,
|
|
"mean_token_accuracy": 0.16079616993665696,
|
|
"num_tokens": 38059052.0,
|
|
"step": 19450
|
|
},
|
|
{
|
|
"entropy": 6.093530988693237,
|
|
"epoch": 1.944769330734243,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004625320052708919,
|
|
"loss": 5.7092,
|
|
"mean_token_accuracy": 0.1713375762104988,
|
|
"num_tokens": 38069316.0,
|
|
"step": 19455
|
|
},
|
|
{
|
|
"entropy": 6.108533430099487,
|
|
"epoch": 1.9452691557954715,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004625122826740696,
|
|
"loss": 5.8347,
|
|
"mean_token_accuracy": 0.169109570980072,
|
|
"num_tokens": 38079175.0,
|
|
"step": 19460
|
|
},
|
|
{
|
|
"entropy": 6.085714101791382,
|
|
"epoch": 1.9457689808567,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004624925553594865,
|
|
"loss": 5.7736,
|
|
"mean_token_accuracy": 0.16978764086961745,
|
|
"num_tokens": 38089701.0,
|
|
"step": 19465
|
|
},
|
|
{
|
|
"entropy": 6.226853847503662,
|
|
"epoch": 1.9462688059179287,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004624728233276389,
|
|
"loss": 5.8945,
|
|
"mean_token_accuracy": 0.15676886588335037,
|
|
"num_tokens": 38099948.0,
|
|
"step": 19470
|
|
},
|
|
{
|
|
"entropy": 6.091783618927002,
|
|
"epoch": 1.9467686309791574,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00046245308657902334,
|
|
"loss": 5.8388,
|
|
"mean_token_accuracy": 0.16855625212192535,
|
|
"num_tokens": 38110195.0,
|
|
"step": 19475
|
|
},
|
|
{
|
|
"entropy": 6.059541797637939,
|
|
"epoch": 1.947268456040386,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004624333451141364,
|
|
"loss": 5.8556,
|
|
"mean_token_accuracy": 0.16224491894245147,
|
|
"num_tokens": 38121027.0,
|
|
"step": 19480
|
|
},
|
|
{
|
|
"entropy": 6.104718399047852,
|
|
"epoch": 1.9477682811016144,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004624135989334746,
|
|
"loss": 5.7734,
|
|
"mean_token_accuracy": 0.16050538867712022,
|
|
"num_tokens": 38130684.0,
|
|
"step": 19485
|
|
},
|
|
{
|
|
"entropy": 6.1137488842010494,
|
|
"epoch": 1.948268106162843,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00046239384803753496,
|
|
"loss": 5.7059,
|
|
"mean_token_accuracy": 0.17503903508186341,
|
|
"num_tokens": 38140376.0,
|
|
"step": 19490
|
|
},
|
|
{
|
|
"entropy": 6.122917652130127,
|
|
"epoch": 1.9487679312240715,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00046237409242681435,
|
|
"loss": 5.9304,
|
|
"mean_token_accuracy": 0.15479682385921478,
|
|
"num_tokens": 38150687.0,
|
|
"step": 19495
|
|
},
|
|
{
|
|
"entropy": 6.078304147720337,
|
|
"epoch": 1.9492677562853,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004623543321018097,
|
|
"loss": 5.7658,
|
|
"mean_token_accuracy": 0.16431433707475662,
|
|
"num_tokens": 38160853.0,
|
|
"step": 19500
|
|
},
|
|
{
|
|
"entropy": 6.089649391174317,
|
|
"epoch": 1.9497675813465287,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004623345670630184,
|
|
"loss": 5.7971,
|
|
"mean_token_accuracy": 0.16292511075735092,
|
|
"num_tokens": 38170702.0,
|
|
"step": 19505
|
|
},
|
|
{
|
|
"entropy": 6.106585741043091,
|
|
"epoch": 1.9502674064077574,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004623147973109375,
|
|
"loss": 5.7957,
|
|
"mean_token_accuracy": 0.1737288787961006,
|
|
"num_tokens": 38179425.0,
|
|
"step": 19510
|
|
},
|
|
{
|
|
"entropy": 6.046446752548218,
|
|
"epoch": 1.950767231468986,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00046229502284606455,
|
|
"loss": 5.8297,
|
|
"mean_token_accuracy": 0.16614948213100433,
|
|
"num_tokens": 38189700.0,
|
|
"step": 19515
|
|
},
|
|
{
|
|
"entropy": 6.1252100467681885,
|
|
"epoch": 1.9512670565302144,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.000462275243668897,
|
|
"loss": 5.8447,
|
|
"mean_token_accuracy": 0.16332716643810272,
|
|
"num_tokens": 38198944.0,
|
|
"step": 19520
|
|
},
|
|
{
|
|
"entropy": 6.075853395462036,
|
|
"epoch": 1.951766881591443,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00046225545977993245,
|
|
"loss": 5.7441,
|
|
"mean_token_accuracy": 0.1680539384484291,
|
|
"num_tokens": 38207237.0,
|
|
"step": 19525
|
|
},
|
|
{
|
|
"entropy": 6.10767183303833,
|
|
"epoch": 1.9522667066526715,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004622356711796688,
|
|
"loss": 5.8275,
|
|
"mean_token_accuracy": 0.16118751615285873,
|
|
"num_tokens": 38217234.0,
|
|
"step": 19530
|
|
},
|
|
{
|
|
"entropy": 6.048633432388305,
|
|
"epoch": 1.9527665317139,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004622158778686038,
|
|
"loss": 5.7228,
|
|
"mean_token_accuracy": 0.1711645945906639,
|
|
"num_tokens": 38226463.0,
|
|
"step": 19535
|
|
},
|
|
{
|
|
"entropy": 5.976444292068481,
|
|
"epoch": 1.9532663567751287,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00046219607984723554,
|
|
"loss": 5.7328,
|
|
"mean_token_accuracy": 0.17218034118413925,
|
|
"num_tokens": 38235313.0,
|
|
"step": 19540
|
|
},
|
|
{
|
|
"entropy": 6.162175273895263,
|
|
"epoch": 1.9537661818363574,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00046217627711606205,
|
|
"loss": 5.7321,
|
|
"mean_token_accuracy": 0.1632661171257496,
|
|
"num_tokens": 38243769.0,
|
|
"step": 19545
|
|
},
|
|
{
|
|
"entropy": 6.204343652725219,
|
|
"epoch": 1.954266006897586,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00046215646967558155,
|
|
"loss": 5.9052,
|
|
"mean_token_accuracy": 0.1632521480321884,
|
|
"num_tokens": 38253522.0,
|
|
"step": 19550
|
|
},
|
|
{
|
|
"entropy": 6.104289150238037,
|
|
"epoch": 1.9547658319588144,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00046213665752629246,
|
|
"loss": 5.8189,
|
|
"mean_token_accuracy": 0.16310772448778152,
|
|
"num_tokens": 38263816.0,
|
|
"step": 19555
|
|
},
|
|
{
|
|
"entropy": 6.017949151992798,
|
|
"epoch": 1.955265657020043,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004621168406686933,
|
|
"loss": 5.7526,
|
|
"mean_token_accuracy": 0.16611257791519166,
|
|
"num_tokens": 38273139.0,
|
|
"step": 19560
|
|
},
|
|
{
|
|
"entropy": 6.025910520553589,
|
|
"epoch": 1.9557654820812715,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00046209701910328245,
|
|
"loss": 5.7991,
|
|
"mean_token_accuracy": 0.1631425142288208,
|
|
"num_tokens": 38282355.0,
|
|
"step": 19565
|
|
},
|
|
{
|
|
"entropy": 6.12298994064331,
|
|
"epoch": 1.9562653071425,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004620771928305588,
|
|
"loss": 5.8098,
|
|
"mean_token_accuracy": 0.16179344803094864,
|
|
"num_tokens": 38291140.0,
|
|
"step": 19570
|
|
},
|
|
{
|
|
"entropy": 6.064161014556885,
|
|
"epoch": 1.9567651322037287,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004620573618510211,
|
|
"loss": 5.6989,
|
|
"mean_token_accuracy": 0.17847869396209717,
|
|
"num_tokens": 38300117.0,
|
|
"step": 19575
|
|
},
|
|
{
|
|
"entropy": 6.110593605041504,
|
|
"epoch": 1.9572649572649574,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.00046203752616516834,
|
|
"loss": 5.7755,
|
|
"mean_token_accuracy": 0.17068348973989486,
|
|
"num_tokens": 38309978.0,
|
|
"step": 19580
|
|
},
|
|
{
|
|
"entropy": 6.042370700836182,
|
|
"epoch": 1.9577647823261857,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00046201768577349957,
|
|
"loss": 5.8012,
|
|
"mean_token_accuracy": 0.1705411233007908,
|
|
"num_tokens": 38318875.0,
|
|
"step": 19585
|
|
},
|
|
{
|
|
"entropy": 6.130873823165894,
|
|
"epoch": 1.9582646073874144,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004619978406765139,
|
|
"loss": 5.9259,
|
|
"mean_token_accuracy": 0.16291563361883163,
|
|
"num_tokens": 38328354.0,
|
|
"step": 19590
|
|
},
|
|
{
|
|
"entropy": 6.165820932388305,
|
|
"epoch": 1.958764432448643,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004619779908747107,
|
|
"loss": 5.8605,
|
|
"mean_token_accuracy": 0.1657483994960785,
|
|
"num_tokens": 38338196.0,
|
|
"step": 19595
|
|
},
|
|
{
|
|
"entropy": 6.100707006454468,
|
|
"epoch": 1.9592642575098715,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004619581363685893,
|
|
"loss": 5.8349,
|
|
"mean_token_accuracy": 0.16379522681236267,
|
|
"num_tokens": 38349077.0,
|
|
"step": 19600
|
|
},
|
|
{
|
|
"entropy": 6.067377519607544,
|
|
"epoch": 1.9597640825711,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004619382771586494,
|
|
"loss": 5.7953,
|
|
"mean_token_accuracy": 0.16899383142590524,
|
|
"num_tokens": 38359507.0,
|
|
"step": 19605
|
|
},
|
|
{
|
|
"entropy": 6.208382987976075,
|
|
"epoch": 1.9602639076323287,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004619184132453905,
|
|
"loss": 5.9832,
|
|
"mean_token_accuracy": 0.15701862499117852,
|
|
"num_tokens": 38370452.0,
|
|
"step": 19610
|
|
},
|
|
{
|
|
"entropy": 6.177937602996826,
|
|
"epoch": 1.9607637326935574,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004618985446293125,
|
|
"loss": 5.7734,
|
|
"mean_token_accuracy": 0.1696055516600609,
|
|
"num_tokens": 38379734.0,
|
|
"step": 19615
|
|
},
|
|
{
|
|
"entropy": 6.011740207672119,
|
|
"epoch": 1.9612635577547857,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00046187867131091504,
|
|
"loss": 5.6333,
|
|
"mean_token_accuracy": 0.17886392921209335,
|
|
"num_tokens": 38388589.0,
|
|
"step": 19620
|
|
},
|
|
{
|
|
"entropy": 6.067960023880005,
|
|
"epoch": 1.9617633828160144,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004618587932906984,
|
|
"loss": 5.8461,
|
|
"mean_token_accuracy": 0.15866232067346572,
|
|
"num_tokens": 38399158.0,
|
|
"step": 19625
|
|
},
|
|
{
|
|
"entropy": 6.123591423034668,
|
|
"epoch": 1.962263207877243,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00046183891056916256,
|
|
"loss": 5.7734,
|
|
"mean_token_accuracy": 0.16849352717399596,
|
|
"num_tokens": 38409254.0,
|
|
"step": 19630
|
|
},
|
|
{
|
|
"entropy": 6.1354718685150145,
|
|
"epoch": 1.9627630329384715,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004618190231468079,
|
|
"loss": 5.8223,
|
|
"mean_token_accuracy": 0.16601746678352355,
|
|
"num_tokens": 38419308.0,
|
|
"step": 19635
|
|
},
|
|
{
|
|
"entropy": 6.047301292419434,
|
|
"epoch": 1.9632628579997,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00046179913102413456,
|
|
"loss": 5.782,
|
|
"mean_token_accuracy": 0.17066773846745492,
|
|
"num_tokens": 38428245.0,
|
|
"step": 19640
|
|
},
|
|
{
|
|
"entropy": 6.080204153060913,
|
|
"epoch": 1.9637626830609287,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004617792342016433,
|
|
"loss": 5.8602,
|
|
"mean_token_accuracy": 0.1626323238015175,
|
|
"num_tokens": 38438675.0,
|
|
"step": 19645
|
|
},
|
|
{
|
|
"entropy": 6.158809804916382,
|
|
"epoch": 1.9642625081221572,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004617593326798344,
|
|
"loss": 5.7781,
|
|
"mean_token_accuracy": 0.16689076870679856,
|
|
"num_tokens": 38447592.0,
|
|
"step": 19650
|
|
},
|
|
{
|
|
"entropy": 6.099963903427124,
|
|
"epoch": 1.9647623331833857,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004617394264592089,
|
|
"loss": 5.7963,
|
|
"mean_token_accuracy": 0.17078716456890106,
|
|
"num_tokens": 38456290.0,
|
|
"step": 19655
|
|
},
|
|
{
|
|
"entropy": 6.0547867774963375,
|
|
"epoch": 1.9652621582446144,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004617195155402674,
|
|
"loss": 5.7436,
|
|
"mean_token_accuracy": 0.16579633504152297,
|
|
"num_tokens": 38465995.0,
|
|
"step": 19660
|
|
},
|
|
{
|
|
"entropy": 6.2091124057769775,
|
|
"epoch": 1.965761983305843,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00046169959992351103,
|
|
"loss": 5.8986,
|
|
"mean_token_accuracy": 0.155789502710104,
|
|
"num_tokens": 38475181.0,
|
|
"step": 19665
|
|
},
|
|
{
|
|
"entropy": 6.17203106880188,
|
|
"epoch": 1.9662618083670715,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00046167967960944066,
|
|
"loss": 5.7975,
|
|
"mean_token_accuracy": 0.1637072205543518,
|
|
"num_tokens": 38484325.0,
|
|
"step": 19670
|
|
},
|
|
{
|
|
"entropy": 6.148690843582154,
|
|
"epoch": 1.9667616334283,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004616597545985577,
|
|
"loss": 5.8796,
|
|
"mean_token_accuracy": 0.16432542949914933,
|
|
"num_tokens": 38492908.0,
|
|
"step": 19675
|
|
},
|
|
{
|
|
"entropy": 6.079439401626587,
|
|
"epoch": 1.9672614584895287,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004616398248913632,
|
|
"loss": 5.8334,
|
|
"mean_token_accuracy": 0.1646043598651886,
|
|
"num_tokens": 38501295.0,
|
|
"step": 19680
|
|
},
|
|
{
|
|
"entropy": 6.126398229598999,
|
|
"epoch": 1.9677612835507572,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00046161989048835886,
|
|
"loss": 5.8137,
|
|
"mean_token_accuracy": 0.1629142627120018,
|
|
"num_tokens": 38511267.0,
|
|
"step": 19685
|
|
},
|
|
{
|
|
"entropy": 6.158321666717529,
|
|
"epoch": 1.9682611086119857,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00046159995139004594,
|
|
"loss": 5.7978,
|
|
"mean_token_accuracy": 0.16925691664218903,
|
|
"num_tokens": 38521476.0,
|
|
"step": 19690
|
|
},
|
|
{
|
|
"entropy": 6.087535047531128,
|
|
"epoch": 1.9687609336732144,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004615800075969264,
|
|
"loss": 5.6864,
|
|
"mean_token_accuracy": 0.17811733484268188,
|
|
"num_tokens": 38531731.0,
|
|
"step": 19695
|
|
},
|
|
{
|
|
"entropy": 6.014466905593872,
|
|
"epoch": 1.969260758734443,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.00046156005910950187,
|
|
"loss": 5.8075,
|
|
"mean_token_accuracy": 0.16416847854852676,
|
|
"num_tokens": 38541428.0,
|
|
"step": 19700
|
|
},
|
|
{
|
|
"entropy": 6.136988592147827,
|
|
"epoch": 1.9697605837956715,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004615401059282742,
|
|
"loss": 5.9219,
|
|
"mean_token_accuracy": 0.157976034283638,
|
|
"num_tokens": 38550947.0,
|
|
"step": 19705
|
|
},
|
|
{
|
|
"entropy": 6.194087076187134,
|
|
"epoch": 1.9702604088569,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.00046152014805374546,
|
|
"loss": 5.8448,
|
|
"mean_token_accuracy": 0.16423358023166656,
|
|
"num_tokens": 38561090.0,
|
|
"step": 19710
|
|
},
|
|
{
|
|
"entropy": 6.166461324691772,
|
|
"epoch": 1.9707602339181287,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004615001854864179,
|
|
"loss": 5.8711,
|
|
"mean_token_accuracy": 0.1595260977745056,
|
|
"num_tokens": 38570555.0,
|
|
"step": 19715
|
|
},
|
|
{
|
|
"entropy": 6.1442700862884525,
|
|
"epoch": 1.9712600589793572,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00046148021822679347,
|
|
"loss": 5.8318,
|
|
"mean_token_accuracy": 0.16878003180027007,
|
|
"num_tokens": 38579392.0,
|
|
"step": 19720
|
|
},
|
|
{
|
|
"entropy": 6.076017189025879,
|
|
"epoch": 1.9717598840405857,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004614602462753749,
|
|
"loss": 5.7651,
|
|
"mean_token_accuracy": 0.16869430541992186,
|
|
"num_tokens": 38590352.0,
|
|
"step": 19725
|
|
},
|
|
{
|
|
"entropy": 6.119795608520508,
|
|
"epoch": 1.9722597091018144,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004614402696326645,
|
|
"loss": 5.8047,
|
|
"mean_token_accuracy": 0.16274723410606384,
|
|
"num_tokens": 38600261.0,
|
|
"step": 19730
|
|
},
|
|
{
|
|
"entropy": 6.095158529281616,
|
|
"epoch": 1.972759534163043,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00046142028829916485,
|
|
"loss": 5.8069,
|
|
"mean_token_accuracy": 0.1650327429175377,
|
|
"num_tokens": 38610409.0,
|
|
"step": 19735
|
|
},
|
|
{
|
|
"entropy": 6.145334482192993,
|
|
"epoch": 1.9732593592242715,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004614003022753787,
|
|
"loss": 5.8931,
|
|
"mean_token_accuracy": 0.15911152511835097,
|
|
"num_tokens": 38619737.0,
|
|
"step": 19740
|
|
},
|
|
{
|
|
"entropy": 6.136614799499512,
|
|
"epoch": 1.9737591842855,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004613803115618089,
|
|
"loss": 5.8311,
|
|
"mean_token_accuracy": 0.17109839171171187,
|
|
"num_tokens": 38628994.0,
|
|
"step": 19745
|
|
},
|
|
{
|
|
"entropy": 6.048517751693725,
|
|
"epoch": 1.9742590093467287,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00046136031615895846,
|
|
"loss": 5.7129,
|
|
"mean_token_accuracy": 0.17802256792783738,
|
|
"num_tokens": 38638598.0,
|
|
"step": 19750
|
|
},
|
|
{
|
|
"entropy": 6.170714664459228,
|
|
"epoch": 1.9747588344079572,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004613403160673305,
|
|
"loss": 5.8253,
|
|
"mean_token_accuracy": 0.16334739327430725,
|
|
"num_tokens": 38649956.0,
|
|
"step": 19755
|
|
},
|
|
{
|
|
"entropy": 6.086538696289063,
|
|
"epoch": 1.9752586594691857,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.000461320311287428,
|
|
"loss": 5.8168,
|
|
"mean_token_accuracy": 0.16781125515699385,
|
|
"num_tokens": 38660006.0,
|
|
"step": 19760
|
|
},
|
|
{
|
|
"entropy": 6.089510679244995,
|
|
"epoch": 1.9757584845304144,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00046130030181975446,
|
|
"loss": 5.8522,
|
|
"mean_token_accuracy": 0.16312528401613235,
|
|
"num_tokens": 38669714.0,
|
|
"step": 19765
|
|
},
|
|
{
|
|
"entropy": 6.116232872009277,
|
|
"epoch": 1.976258309591643,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004612802876648133,
|
|
"loss": 5.8921,
|
|
"mean_token_accuracy": 0.1656282812356949,
|
|
"num_tokens": 38679766.0,
|
|
"step": 19770
|
|
},
|
|
{
|
|
"entropy": 6.120855712890625,
|
|
"epoch": 1.9767581346528715,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.000461260268823108,
|
|
"loss": 5.7918,
|
|
"mean_token_accuracy": 0.16839701533317566,
|
|
"num_tokens": 38689440.0,
|
|
"step": 19775
|
|
},
|
|
{
|
|
"entropy": 6.136609601974487,
|
|
"epoch": 1.9772579597141,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00046124024529514224,
|
|
"loss": 5.8322,
|
|
"mean_token_accuracy": 0.16595556139945983,
|
|
"num_tokens": 38700105.0,
|
|
"step": 19780
|
|
},
|
|
{
|
|
"entropy": 6.129881906509399,
|
|
"epoch": 1.9777577847753287,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004612202170814198,
|
|
"loss": 5.8165,
|
|
"mean_token_accuracy": 0.15978501364588737,
|
|
"num_tokens": 38709876.0,
|
|
"step": 19785
|
|
},
|
|
{
|
|
"entropy": 6.1609796524047855,
|
|
"epoch": 1.9782576098365572,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004612001841824447,
|
|
"loss": 5.8458,
|
|
"mean_token_accuracy": 0.16340383887290955,
|
|
"num_tokens": 38718857.0,
|
|
"step": 19790
|
|
},
|
|
{
|
|
"entropy": 6.077872943878174,
|
|
"epoch": 1.9787574348977857,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00046118014659872085,
|
|
"loss": 5.7857,
|
|
"mean_token_accuracy": 0.17308118641376496,
|
|
"num_tokens": 38729353.0,
|
|
"step": 19795
|
|
},
|
|
{
|
|
"entropy": 6.055468511581421,
|
|
"epoch": 1.9792572599590144,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004611601043307525,
|
|
"loss": 5.7422,
|
|
"mean_token_accuracy": 0.1721504047513008,
|
|
"num_tokens": 38738641.0,
|
|
"step": 19800
|
|
},
|
|
{
|
|
"entropy": 6.065119981765747,
|
|
"epoch": 1.979757085020243,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00046114005737904376,
|
|
"loss": 5.8567,
|
|
"mean_token_accuracy": 0.16776637732982635,
|
|
"num_tokens": 38748423.0,
|
|
"step": 19805
|
|
},
|
|
{
|
|
"entropy": 6.129310894012451,
|
|
"epoch": 1.9802569100814715,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.000461120005744099,
|
|
"loss": 5.8072,
|
|
"mean_token_accuracy": 0.164868001639843,
|
|
"num_tokens": 38758063.0,
|
|
"step": 19810
|
|
},
|
|
{
|
|
"entropy": 6.160581064224243,
|
|
"epoch": 1.9807567351427,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00046109994942642287,
|
|
"loss": 5.8107,
|
|
"mean_token_accuracy": 0.16499156057834624,
|
|
"num_tokens": 38766769.0,
|
|
"step": 19815
|
|
},
|
|
{
|
|
"entropy": 6.0576629638671875,
|
|
"epoch": 1.9812565602039287,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004610798884265199,
|
|
"loss": 5.7368,
|
|
"mean_token_accuracy": 0.17440543025732042,
|
|
"num_tokens": 38775665.0,
|
|
"step": 19820
|
|
},
|
|
{
|
|
"entropy": 6.038535165786743,
|
|
"epoch": 1.9817563852651572,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00046105982274489483,
|
|
"loss": 5.6845,
|
|
"mean_token_accuracy": 0.1772536188364029,
|
|
"num_tokens": 38784044.0,
|
|
"step": 19825
|
|
},
|
|
{
|
|
"entropy": 6.112452459335327,
|
|
"epoch": 1.9822562103263857,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00046103975238205244,
|
|
"loss": 5.8128,
|
|
"mean_token_accuracy": 0.1697612628340721,
|
|
"num_tokens": 38793666.0,
|
|
"step": 19830
|
|
},
|
|
{
|
|
"entropy": 6.17901840209961,
|
|
"epoch": 1.9827560353876144,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004610196773384978,
|
|
"loss": 5.9204,
|
|
"mean_token_accuracy": 0.1566963568329811,
|
|
"num_tokens": 38804193.0,
|
|
"step": 19835
|
|
},
|
|
{
|
|
"entropy": 6.202119636535644,
|
|
"epoch": 1.983255860448843,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00046099959761473593,
|
|
"loss": 5.8603,
|
|
"mean_token_accuracy": 0.16010444462299347,
|
|
"num_tokens": 38814200.0,
|
|
"step": 19840
|
|
},
|
|
{
|
|
"entropy": 6.200698614120483,
|
|
"epoch": 1.9837556855100713,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00046097951321127207,
|
|
"loss": 5.8538,
|
|
"mean_token_accuracy": 0.16653407365083694,
|
|
"num_tokens": 38824390.0,
|
|
"step": 19845
|
|
},
|
|
{
|
|
"entropy": 6.005752420425415,
|
|
"epoch": 1.9842555105713,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00046095942412861145,
|
|
"loss": 5.6915,
|
|
"mean_token_accuracy": 0.17823731154203415,
|
|
"num_tokens": 38832733.0,
|
|
"step": 19850
|
|
},
|
|
{
|
|
"entropy": 6.057382202148437,
|
|
"epoch": 1.9847553356325287,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004609393303672596,
|
|
"loss": 5.8171,
|
|
"mean_token_accuracy": 0.16692613065242767,
|
|
"num_tokens": 38843368.0,
|
|
"step": 19855
|
|
},
|
|
{
|
|
"entropy": 6.0607102394104,
|
|
"epoch": 1.9852551606937572,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00046091923192772205,
|
|
"loss": 5.6937,
|
|
"mean_token_accuracy": 0.1800062671303749,
|
|
"num_tokens": 38854066.0,
|
|
"step": 19860
|
|
},
|
|
{
|
|
"entropy": 6.174441766738892,
|
|
"epoch": 1.9857549857549857,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004608991288105045,
|
|
"loss": 5.8583,
|
|
"mean_token_accuracy": 0.1619427978992462,
|
|
"num_tokens": 38864509.0,
|
|
"step": 19865
|
|
},
|
|
{
|
|
"entropy": 6.141784763336181,
|
|
"epoch": 1.9862548108162144,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.00046087902101611265,
|
|
"loss": 5.7699,
|
|
"mean_token_accuracy": 0.17204521000385284,
|
|
"num_tokens": 38874287.0,
|
|
"step": 19870
|
|
},
|
|
{
|
|
"entropy": 6.001802110671997,
|
|
"epoch": 1.986754635877443,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004608589085450525,
|
|
"loss": 5.6653,
|
|
"mean_token_accuracy": 0.17388948500156404,
|
|
"num_tokens": 38884517.0,
|
|
"step": 19875
|
|
},
|
|
{
|
|
"entropy": 5.995101881027222,
|
|
"epoch": 1.9872544609386713,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00046083879139783,
|
|
"loss": 5.6821,
|
|
"mean_token_accuracy": 0.1719906136393547,
|
|
"num_tokens": 38894440.0,
|
|
"step": 19880
|
|
},
|
|
{
|
|
"entropy": 6.065050268173218,
|
|
"epoch": 1.9877542859999,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004608186695749514,
|
|
"loss": 5.8555,
|
|
"mean_token_accuracy": 0.1645030602812767,
|
|
"num_tokens": 38904500.0,
|
|
"step": 19885
|
|
},
|
|
{
|
|
"entropy": 6.147082328796387,
|
|
"epoch": 1.9882541110611287,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004607985430769228,
|
|
"loss": 5.8089,
|
|
"mean_token_accuracy": 0.16835977137088776,
|
|
"num_tokens": 38913695.0,
|
|
"step": 19890
|
|
},
|
|
{
|
|
"entropy": 6.0498627662658695,
|
|
"epoch": 1.9887539361223572,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004607784119042507,
|
|
"loss": 5.7735,
|
|
"mean_token_accuracy": 0.1637938365340233,
|
|
"num_tokens": 38923071.0,
|
|
"step": 19895
|
|
},
|
|
{
|
|
"entropy": 6.04052038192749,
|
|
"epoch": 1.9892537611835857,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004607582760574416,
|
|
"loss": 5.6936,
|
|
"mean_token_accuracy": 0.17396079003810883,
|
|
"num_tokens": 38932663.0,
|
|
"step": 19900
|
|
},
|
|
{
|
|
"entropy": 6.124537658691406,
|
|
"epoch": 1.9897535862448144,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.000460738135537002,
|
|
"loss": 5.7689,
|
|
"mean_token_accuracy": 0.16239200681447982,
|
|
"num_tokens": 38941230.0,
|
|
"step": 19905
|
|
},
|
|
{
|
|
"entropy": 6.139766788482666,
|
|
"epoch": 1.9902534113060428,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00046071799034343874,
|
|
"loss": 5.8074,
|
|
"mean_token_accuracy": 0.1620147556066513,
|
|
"num_tokens": 38951004.0,
|
|
"step": 19910
|
|
},
|
|
{
|
|
"entropy": 6.0331658840179445,
|
|
"epoch": 1.9907532363672713,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004606978404772587,
|
|
"loss": 5.7738,
|
|
"mean_token_accuracy": 0.16747061014175416,
|
|
"num_tokens": 38960440.0,
|
|
"step": 19915
|
|
},
|
|
{
|
|
"entropy": 6.068949556350708,
|
|
"epoch": 1.9912530614285,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00046067768593896865,
|
|
"loss": 5.753,
|
|
"mean_token_accuracy": 0.1705079898238182,
|
|
"num_tokens": 38970012.0,
|
|
"step": 19920
|
|
},
|
|
{
|
|
"entropy": 6.105887937545776,
|
|
"epoch": 1.9917528864897287,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004606575267290759,
|
|
"loss": 5.8534,
|
|
"mean_token_accuracy": 0.16632786616683007,
|
|
"num_tokens": 38979842.0,
|
|
"step": 19925
|
|
},
|
|
{
|
|
"entropy": 5.905295991897583,
|
|
"epoch": 1.9922527115509572,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004606373628480875,
|
|
"loss": 5.5852,
|
|
"mean_token_accuracy": 0.20125603079795837,
|
|
"num_tokens": 38990123.0,
|
|
"step": 19930
|
|
},
|
|
{
|
|
"entropy": 6.076378870010376,
|
|
"epoch": 1.9927525366121857,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004606171942965108,
|
|
"loss": 5.8042,
|
|
"mean_token_accuracy": 0.17139284163713456,
|
|
"num_tokens": 39000500.0,
|
|
"step": 19935
|
|
},
|
|
{
|
|
"entropy": 6.159777355194092,
|
|
"epoch": 1.9932523616734144,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004605970210748533,
|
|
"loss": 5.8276,
|
|
"mean_token_accuracy": 0.16886540949344636,
|
|
"num_tokens": 39009795.0,
|
|
"step": 19940
|
|
},
|
|
{
|
|
"entropy": 6.103161382675171,
|
|
"epoch": 1.9937521867346428,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004605768431836225,
|
|
"loss": 5.7459,
|
|
"mean_token_accuracy": 0.16944815069437028,
|
|
"num_tokens": 39018969.0,
|
|
"step": 19945
|
|
},
|
|
{
|
|
"entropy": 6.056585311889648,
|
|
"epoch": 1.9942520117958713,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00046055666062332605,
|
|
"loss": 5.6526,
|
|
"mean_token_accuracy": 0.17090588212013244,
|
|
"num_tokens": 39028167.0,
|
|
"step": 19950
|
|
},
|
|
{
|
|
"entropy": 6.0148681640625,
|
|
"epoch": 1.9947518368571,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00046053647339447184,
|
|
"loss": 5.6939,
|
|
"mean_token_accuracy": 0.1775069773197174,
|
|
"num_tokens": 39037513.0,
|
|
"step": 19955
|
|
},
|
|
{
|
|
"entropy": 6.087954902648926,
|
|
"epoch": 1.9952516619183287,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00046051628149756767,
|
|
"loss": 5.7606,
|
|
"mean_token_accuracy": 0.167257422208786,
|
|
"num_tokens": 39046258.0,
|
|
"step": 19960
|
|
},
|
|
{
|
|
"entropy": 5.947696256637573,
|
|
"epoch": 1.9957514869795572,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004604960849331216,
|
|
"loss": 5.6863,
|
|
"mean_token_accuracy": 0.17423568069934844,
|
|
"num_tokens": 39056778.0,
|
|
"step": 19965
|
|
},
|
|
{
|
|
"entropy": 6.080803728103637,
|
|
"epoch": 1.9962513120407857,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004604758837016417,
|
|
"loss": 5.701,
|
|
"mean_token_accuracy": 0.17148376107215882,
|
|
"num_tokens": 39066091.0,
|
|
"step": 19970
|
|
},
|
|
{
|
|
"entropy": 6.1148841381073,
|
|
"epoch": 1.9967511371020144,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004604556778036363,
|
|
"loss": 5.7847,
|
|
"mean_token_accuracy": 0.16667204350233078,
|
|
"num_tokens": 39075769.0,
|
|
"step": 19975
|
|
},
|
|
{
|
|
"entropy": 6.112657594680786,
|
|
"epoch": 1.9972509621632428,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00046043546723961384,
|
|
"loss": 5.8551,
|
|
"mean_token_accuracy": 0.16555734425783158,
|
|
"num_tokens": 39085690.0,
|
|
"step": 19980
|
|
},
|
|
{
|
|
"entropy": 6.062629222869873,
|
|
"epoch": 1.9977507872244713,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00046041525201008266,
|
|
"loss": 5.7118,
|
|
"mean_token_accuracy": 0.17518312782049178,
|
|
"num_tokens": 39094143.0,
|
|
"step": 19985
|
|
},
|
|
{
|
|
"entropy": 6.114654874801635,
|
|
"epoch": 1.9982506122857,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00046039503211555154,
|
|
"loss": 5.8572,
|
|
"mean_token_accuracy": 0.16116896122694016,
|
|
"num_tokens": 39104980.0,
|
|
"step": 19990
|
|
},
|
|
{
|
|
"entropy": 6.176002836227417,
|
|
"epoch": 1.9987504373469287,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00046037480755652913,
|
|
"loss": 5.8641,
|
|
"mean_token_accuracy": 0.16270339488983154,
|
|
"num_tokens": 39115093.0,
|
|
"step": 19995
|
|
},
|
|
{
|
|
"entropy": 6.191942548751831,
|
|
"epoch": 1.9992502624081572,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00046035457833352414,
|
|
"loss": 5.7767,
|
|
"mean_token_accuracy": 0.1595386251807213,
|
|
"num_tokens": 39124482.0,
|
|
"step": 20000
|
|
},
|
|
{
|
|
"entropy": 6.121924781799317,
|
|
"epoch": 1.9997500874693857,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00046033434444704577,
|
|
"loss": 5.7588,
|
|
"mean_token_accuracy": 0.16482550352811814,
|
|
"num_tokens": 39135029.0,
|
|
"step": 20005
|
|
},
|
|
{
|
|
"entropy": 6.083685927920872,
|
|
"epoch": 2.0001999300244915,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00046031410589760294,
|
|
"loss": 5.6924,
|
|
"mean_token_accuracy": 0.17169252865844303,
|
|
"num_tokens": 39142785.0,
|
|
"step": 20010
|
|
},
|
|
{
|
|
"entropy": 6.106768321990967,
|
|
"epoch": 2.00069975508572,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00046029386268570485,
|
|
"loss": 5.7245,
|
|
"mean_token_accuracy": 0.1662154033780098,
|
|
"num_tokens": 39151917.0,
|
|
"step": 20015
|
|
},
|
|
{
|
|
"entropy": 6.044861125946045,
|
|
"epoch": 2.0011995801469484,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004602736148118609,
|
|
"loss": 5.6012,
|
|
"mean_token_accuracy": 0.18739093244075775,
|
|
"num_tokens": 39161782.0,
|
|
"step": 20020
|
|
},
|
|
{
|
|
"entropy": 6.077157831192016,
|
|
"epoch": 2.001699405208177,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00046025336227658047,
|
|
"loss": 5.6577,
|
|
"mean_token_accuracy": 0.17822888344526291,
|
|
"num_tokens": 39170954.0,
|
|
"step": 20025
|
|
},
|
|
{
|
|
"entropy": 6.012733364105225,
|
|
"epoch": 2.002199230269406,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00046023310508037316,
|
|
"loss": 5.6646,
|
|
"mean_token_accuracy": 0.17571278512477875,
|
|
"num_tokens": 39179405.0,
|
|
"step": 20030
|
|
},
|
|
{
|
|
"entropy": 6.037385034561157,
|
|
"epoch": 2.002699055330634,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00046021284322374847,
|
|
"loss": 5.7242,
|
|
"mean_token_accuracy": 0.16785858720541,
|
|
"num_tokens": 39188837.0,
|
|
"step": 20035
|
|
},
|
|
{
|
|
"entropy": 6.0926103591918945,
|
|
"epoch": 2.003198880391863,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004601925767072164,
|
|
"loss": 5.7172,
|
|
"mean_token_accuracy": 0.17756464183330536,
|
|
"num_tokens": 39198562.0,
|
|
"step": 20040
|
|
},
|
|
{
|
|
"entropy": 6.1095113277435305,
|
|
"epoch": 2.0036987054530915,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00046017230553128675,
|
|
"loss": 5.6691,
|
|
"mean_token_accuracy": 0.16734883710741996,
|
|
"num_tokens": 39207503.0,
|
|
"step": 20045
|
|
},
|
|
{
|
|
"entropy": 6.0906792163848875,
|
|
"epoch": 2.00419853051432,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00046015202969646953,
|
|
"loss": 5.7216,
|
|
"mean_token_accuracy": 0.1699637606739998,
|
|
"num_tokens": 39216992.0,
|
|
"step": 20050
|
|
},
|
|
{
|
|
"entropy": 6.110006189346313,
|
|
"epoch": 2.0046983555755484,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004601317492032749,
|
|
"loss": 5.7367,
|
|
"mean_token_accuracy": 0.16723355799913406,
|
|
"num_tokens": 39227202.0,
|
|
"step": 20055
|
|
},
|
|
{
|
|
"entropy": 6.0607953548431395,
|
|
"epoch": 2.005198180636777,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.000460111464052213,
|
|
"loss": 5.7348,
|
|
"mean_token_accuracy": 0.16627422571182252,
|
|
"num_tokens": 39236843.0,
|
|
"step": 20060
|
|
},
|
|
{
|
|
"entropy": 6.0740007877349855,
|
|
"epoch": 2.005698005698006,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00046009117424379445,
|
|
"loss": 5.6913,
|
|
"mean_token_accuracy": 0.17805316150188447,
|
|
"num_tokens": 39246162.0,
|
|
"step": 20065
|
|
},
|
|
{
|
|
"entropy": 6.179464817047119,
|
|
"epoch": 2.006197830759234,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00046007087977852947,
|
|
"loss": 5.7961,
|
|
"mean_token_accuracy": 0.16502643525600433,
|
|
"num_tokens": 39256295.0,
|
|
"step": 20070
|
|
},
|
|
{
|
|
"entropy": 6.207182931900024,
|
|
"epoch": 2.0066976558204628,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00046005058065692883,
|
|
"loss": 5.7719,
|
|
"mean_token_accuracy": 0.16940322369337082,
|
|
"num_tokens": 39266704.0,
|
|
"step": 20075
|
|
},
|
|
{
|
|
"entropy": 6.129868745803833,
|
|
"epoch": 2.0071974808816915,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00046003027687950316,
|
|
"loss": 5.7191,
|
|
"mean_token_accuracy": 0.16438053846359252,
|
|
"num_tokens": 39276308.0,
|
|
"step": 20080
|
|
},
|
|
{
|
|
"entropy": 6.036658763885498,
|
|
"epoch": 2.00769730594292,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004600099684467634,
|
|
"loss": 5.6899,
|
|
"mean_token_accuracy": 0.16371146142482756,
|
|
"num_tokens": 39287357.0,
|
|
"step": 20085
|
|
},
|
|
{
|
|
"entropy": 6.015314245223999,
|
|
"epoch": 2.0081971310041484,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004599896553592204,
|
|
"loss": 5.6666,
|
|
"mean_token_accuracy": 0.17392464876174926,
|
|
"num_tokens": 39297209.0,
|
|
"step": 20090
|
|
},
|
|
{
|
|
"entropy": 6.118293285369873,
|
|
"epoch": 2.008696956065377,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004599693376173853,
|
|
"loss": 5.8059,
|
|
"mean_token_accuracy": 0.16168147474527358,
|
|
"num_tokens": 39305884.0,
|
|
"step": 20095
|
|
},
|
|
{
|
|
"entropy": 6.068700361251831,
|
|
"epoch": 2.009196781126606,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004599490152217692,
|
|
"loss": 5.7348,
|
|
"mean_token_accuracy": 0.16623416990041734,
|
|
"num_tokens": 39314761.0,
|
|
"step": 20100
|
|
},
|
|
{
|
|
"entropy": 6.146401119232178,
|
|
"epoch": 2.009696606187834,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.00045992868817288355,
|
|
"loss": 5.7709,
|
|
"mean_token_accuracy": 0.16815247237682343,
|
|
"num_tokens": 39323752.0,
|
|
"step": 20105
|
|
},
|
|
{
|
|
"entropy": 6.1432431697845455,
|
|
"epoch": 2.0101964312490628,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004599083564712396,
|
|
"loss": 5.7627,
|
|
"mean_token_accuracy": 0.1682730108499527,
|
|
"num_tokens": 39333296.0,
|
|
"step": 20110
|
|
},
|
|
{
|
|
"entropy": 6.127297973632812,
|
|
"epoch": 2.0106962563102915,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00045988802011734896,
|
|
"loss": 5.8143,
|
|
"mean_token_accuracy": 0.16513504534959794,
|
|
"num_tokens": 39343693.0,
|
|
"step": 20115
|
|
},
|
|
{
|
|
"entropy": 6.0841999530792235,
|
|
"epoch": 2.01119608137152,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00045986767911172343,
|
|
"loss": 5.6957,
|
|
"mean_token_accuracy": 0.16824744641780853,
|
|
"num_tokens": 39353443.0,
|
|
"step": 20120
|
|
},
|
|
{
|
|
"entropy": 6.104141426086426,
|
|
"epoch": 2.0116959064327484,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00045984733345487465,
|
|
"loss": 5.6785,
|
|
"mean_token_accuracy": 0.17374279201030732,
|
|
"num_tokens": 39363236.0,
|
|
"step": 20125
|
|
},
|
|
{
|
|
"entropy": 6.107530355453491,
|
|
"epoch": 2.012195731493977,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00045982698314731447,
|
|
"loss": 5.693,
|
|
"mean_token_accuracy": 0.16687774658203125,
|
|
"num_tokens": 39372764.0,
|
|
"step": 20130
|
|
},
|
|
{
|
|
"entropy": 6.181967449188233,
|
|
"epoch": 2.012695556555206,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00045980662818955495,
|
|
"loss": 5.7352,
|
|
"mean_token_accuracy": 0.1671268969774246,
|
|
"num_tokens": 39383087.0,
|
|
"step": 20135
|
|
},
|
|
{
|
|
"entropy": 6.070302486419678,
|
|
"epoch": 2.013195381616434,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00045978626858210833,
|
|
"loss": 5.657,
|
|
"mean_token_accuracy": 0.17466090768575668,
|
|
"num_tokens": 39392356.0,
|
|
"step": 20140
|
|
},
|
|
{
|
|
"entropy": 6.07214388847351,
|
|
"epoch": 2.0136952066776628,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004597659043254866,
|
|
"loss": 5.7699,
|
|
"mean_token_accuracy": 0.16743133962154388,
|
|
"num_tokens": 39401782.0,
|
|
"step": 20145
|
|
},
|
|
{
|
|
"entropy": 6.116475296020508,
|
|
"epoch": 2.0141950317388915,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004597455354202023,
|
|
"loss": 5.6861,
|
|
"mean_token_accuracy": 0.16985016018152238,
|
|
"num_tokens": 39410819.0,
|
|
"step": 20150
|
|
},
|
|
{
|
|
"entropy": 5.974573993682862,
|
|
"epoch": 2.01469485680012,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004597251618667679,
|
|
"loss": 5.6428,
|
|
"mean_token_accuracy": 0.177241051197052,
|
|
"num_tokens": 39419902.0,
|
|
"step": 20155
|
|
},
|
|
{
|
|
"entropy": 6.1492242336273195,
|
|
"epoch": 2.0151946818613484,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00045970478366569594,
|
|
"loss": 5.7667,
|
|
"mean_token_accuracy": 0.17055751234292985,
|
|
"num_tokens": 39429265.0,
|
|
"step": 20160
|
|
},
|
|
{
|
|
"entropy": 6.065391588211059,
|
|
"epoch": 2.015694506922577,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00045968440081749917,
|
|
"loss": 5.7056,
|
|
"mean_token_accuracy": 0.1661935567855835,
|
|
"num_tokens": 39439515.0,
|
|
"step": 20165
|
|
},
|
|
{
|
|
"entropy": 6.045851039886474,
|
|
"epoch": 2.016194331983806,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004596640133226904,
|
|
"loss": 5.6926,
|
|
"mean_token_accuracy": 0.1715142086148262,
|
|
"num_tokens": 39448970.0,
|
|
"step": 20170
|
|
},
|
|
{
|
|
"entropy": 6.0784502029418945,
|
|
"epoch": 2.016694157045034,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00045964362118178253,
|
|
"loss": 5.6629,
|
|
"mean_token_accuracy": 0.17594827860593795,
|
|
"num_tokens": 39460359.0,
|
|
"step": 20175
|
|
},
|
|
{
|
|
"entropy": 6.173139572143555,
|
|
"epoch": 2.0171939821062628,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004596232243952887,
|
|
"loss": 5.8556,
|
|
"mean_token_accuracy": 0.16308331340551377,
|
|
"num_tokens": 39470175.0,
|
|
"step": 20180
|
|
},
|
|
{
|
|
"entropy": 5.97087836265564,
|
|
"epoch": 2.0176938071674915,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.000459602822963722,
|
|
"loss": 5.6283,
|
|
"mean_token_accuracy": 0.17922350764274597,
|
|
"num_tokens": 39479834.0,
|
|
"step": 20185
|
|
},
|
|
{
|
|
"entropy": 6.0713588237762455,
|
|
"epoch": 2.01819363222872,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00045958241688759583,
|
|
"loss": 5.689,
|
|
"mean_token_accuracy": 0.1683349296450615,
|
|
"num_tokens": 39489108.0,
|
|
"step": 20190
|
|
},
|
|
{
|
|
"entropy": 6.0943268775939945,
|
|
"epoch": 2.0186934572899484,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00045956200616742356,
|
|
"loss": 5.7525,
|
|
"mean_token_accuracy": 0.17224438041448592,
|
|
"num_tokens": 39499098.0,
|
|
"step": 20195
|
|
},
|
|
{
|
|
"entropy": 6.132609558105469,
|
|
"epoch": 2.019193282351177,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004595415908037187,
|
|
"loss": 5.7419,
|
|
"mean_token_accuracy": 0.1713191419839859,
|
|
"num_tokens": 39508470.0,
|
|
"step": 20200
|
|
},
|
|
{
|
|
"entropy": 6.1556305408477785,
|
|
"epoch": 2.019693107412406,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004595211707969948,
|
|
"loss": 5.7762,
|
|
"mean_token_accuracy": 0.161455699801445,
|
|
"num_tokens": 39518941.0,
|
|
"step": 20205
|
|
},
|
|
{
|
|
"entropy": 6.087546443939209,
|
|
"epoch": 2.020192932473634,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004595007461477658,
|
|
"loss": 5.6721,
|
|
"mean_token_accuracy": 0.16480484902858733,
|
|
"num_tokens": 39528613.0,
|
|
"step": 20210
|
|
},
|
|
{
|
|
"entropy": 6.055966854095459,
|
|
"epoch": 2.0206927575348628,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00045948031685654557,
|
|
"loss": 5.6963,
|
|
"mean_token_accuracy": 0.16808133870363234,
|
|
"num_tokens": 39537831.0,
|
|
"step": 20215
|
|
},
|
|
{
|
|
"entropy": 6.092569303512573,
|
|
"epoch": 2.0211925825960915,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004594598829238479,
|
|
"loss": 5.6362,
|
|
"mean_token_accuracy": 0.17592521160840988,
|
|
"num_tokens": 39547439.0,
|
|
"step": 20220
|
|
},
|
|
{
|
|
"entropy": 6.0488207817077635,
|
|
"epoch": 2.0216924076573197,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004594394443501872,
|
|
"loss": 5.6554,
|
|
"mean_token_accuracy": 0.1685817211866379,
|
|
"num_tokens": 39556898.0,
|
|
"step": 20225
|
|
},
|
|
{
|
|
"entropy": 6.092200088500976,
|
|
"epoch": 2.0221922327185484,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004594190011360775,
|
|
"loss": 5.6887,
|
|
"mean_token_accuracy": 0.16622617095708847,
|
|
"num_tokens": 39565882.0,
|
|
"step": 20230
|
|
},
|
|
{
|
|
"entropy": 6.095596170425415,
|
|
"epoch": 2.022692057779777,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004593985532820331,
|
|
"loss": 5.7752,
|
|
"mean_token_accuracy": 0.16855795234441756,
|
|
"num_tokens": 39575903.0,
|
|
"step": 20235
|
|
},
|
|
{
|
|
"entropy": 6.0357880115509035,
|
|
"epoch": 2.023191882841006,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004593781007885686,
|
|
"loss": 5.6668,
|
|
"mean_token_accuracy": 0.1746720477938652,
|
|
"num_tokens": 39586058.0,
|
|
"step": 20240
|
|
},
|
|
{
|
|
"entropy": 6.1744921684265135,
|
|
"epoch": 2.023691707902234,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004593576436561985,
|
|
"loss": 5.7518,
|
|
"mean_token_accuracy": 0.1676945447921753,
|
|
"num_tokens": 39596241.0,
|
|
"step": 20245
|
|
},
|
|
{
|
|
"entropy": 6.2097412109375,
|
|
"epoch": 2.0241915329634628,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00045933718188543763,
|
|
"loss": 5.8298,
|
|
"mean_token_accuracy": 0.16299255788326264,
|
|
"num_tokens": 39605359.0,
|
|
"step": 20250
|
|
},
|
|
{
|
|
"entropy": 6.120931196212768,
|
|
"epoch": 2.0246913580246915,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004593167154768006,
|
|
"loss": 5.7342,
|
|
"mean_token_accuracy": 0.17650927901268004,
|
|
"num_tokens": 39615168.0,
|
|
"step": 20255
|
|
},
|
|
{
|
|
"entropy": 6.050666093826294,
|
|
"epoch": 2.0251911830859197,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004592962444308024,
|
|
"loss": 5.685,
|
|
"mean_token_accuracy": 0.1698768749833107,
|
|
"num_tokens": 39624308.0,
|
|
"step": 20260
|
|
},
|
|
{
|
|
"entropy": 6.091116666793823,
|
|
"epoch": 2.0256910081471484,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004592757687479582,
|
|
"loss": 5.744,
|
|
"mean_token_accuracy": 0.17317683547735213,
|
|
"num_tokens": 39633422.0,
|
|
"step": 20265
|
|
},
|
|
{
|
|
"entropy": 6.078937244415283,
|
|
"epoch": 2.026190833208377,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.000459255288428783,
|
|
"loss": 5.6978,
|
|
"mean_token_accuracy": 0.17335078120231628,
|
|
"num_tokens": 39642725.0,
|
|
"step": 20270
|
|
},
|
|
{
|
|
"entropy": 6.098373794555664,
|
|
"epoch": 2.026690658269606,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004592348034737922,
|
|
"loss": 5.7495,
|
|
"mean_token_accuracy": 0.1668761819601059,
|
|
"num_tokens": 39652974.0,
|
|
"step": 20275
|
|
},
|
|
{
|
|
"entropy": 6.1447690486907955,
|
|
"epoch": 2.027190483330834,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004592143138835012,
|
|
"loss": 5.8385,
|
|
"mean_token_accuracy": 0.1613427370786667,
|
|
"num_tokens": 39661947.0,
|
|
"step": 20280
|
|
},
|
|
{
|
|
"entropy": 6.0060781955719,
|
|
"epoch": 2.0276903083920628,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004591938196584254,
|
|
"loss": 5.5575,
|
|
"mean_token_accuracy": 0.19005701094865798,
|
|
"num_tokens": 39671179.0,
|
|
"step": 20285
|
|
},
|
|
{
|
|
"entropy": 6.095835161209107,
|
|
"epoch": 2.0281901334532915,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00045917332079908055,
|
|
"loss": 5.7617,
|
|
"mean_token_accuracy": 0.17008300870656967,
|
|
"num_tokens": 39681874.0,
|
|
"step": 20290
|
|
},
|
|
{
|
|
"entropy": 6.126419448852539,
|
|
"epoch": 2.0286899585145197,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004591528173059823,
|
|
"loss": 5.7006,
|
|
"mean_token_accuracy": 0.170759853720665,
|
|
"num_tokens": 39691351.0,
|
|
"step": 20295
|
|
},
|
|
{
|
|
"entropy": 6.128867435455322,
|
|
"epoch": 2.0291897835757484,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004591323091796465,
|
|
"loss": 5.7199,
|
|
"mean_token_accuracy": 0.17366330772638322,
|
|
"num_tokens": 39702315.0,
|
|
"step": 20300
|
|
},
|
|
{
|
|
"entropy": 6.110440349578857,
|
|
"epoch": 2.029689608636977,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004591117964205893,
|
|
"loss": 5.7496,
|
|
"mean_token_accuracy": 0.16904657781124116,
|
|
"num_tokens": 39712048.0,
|
|
"step": 20305
|
|
},
|
|
{
|
|
"entropy": 6.0440699577331545,
|
|
"epoch": 2.030189433698206,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00045909127902932657,
|
|
"loss": 5.75,
|
|
"mean_token_accuracy": 0.1712127447128296,
|
|
"num_tokens": 39722013.0,
|
|
"step": 20310
|
|
},
|
|
{
|
|
"entropy": 6.118055820465088,
|
|
"epoch": 2.030689258759434,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004590707570063747,
|
|
"loss": 5.6964,
|
|
"mean_token_accuracy": 0.16847662776708602,
|
|
"num_tokens": 39730867.0,
|
|
"step": 20315
|
|
},
|
|
{
|
|
"entropy": 6.036715459823609,
|
|
"epoch": 2.0311890838206628,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00045905023035224993,
|
|
"loss": 5.6666,
|
|
"mean_token_accuracy": 0.17527082860469817,
|
|
"num_tokens": 39740451.0,
|
|
"step": 20320
|
|
},
|
|
{
|
|
"entropy": 6.030253648757935,
|
|
"epoch": 2.0316889088818915,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00045902969906746875,
|
|
"loss": 5.6984,
|
|
"mean_token_accuracy": 0.17504477202892305,
|
|
"num_tokens": 39750580.0,
|
|
"step": 20325
|
|
},
|
|
{
|
|
"entropy": 6.016846132278443,
|
|
"epoch": 2.0321887339431197,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00045900916315254765,
|
|
"loss": 5.5927,
|
|
"mean_token_accuracy": 0.18047329038381577,
|
|
"num_tokens": 39760943.0,
|
|
"step": 20330
|
|
},
|
|
{
|
|
"entropy": 6.041616916656494,
|
|
"epoch": 2.0326885590043484,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00045898862260800337,
|
|
"loss": 5.6998,
|
|
"mean_token_accuracy": 0.17553142607212066,
|
|
"num_tokens": 39770686.0,
|
|
"step": 20335
|
|
},
|
|
{
|
|
"entropy": 6.100028467178345,
|
|
"epoch": 2.033188384065577,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00045896807743435263,
|
|
"loss": 5.7762,
|
|
"mean_token_accuracy": 0.1603745073080063,
|
|
"num_tokens": 39781121.0,
|
|
"step": 20340
|
|
},
|
|
{
|
|
"entropy": 6.090352296829224,
|
|
"epoch": 2.033688209126806,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004589475276321125,
|
|
"loss": 5.6845,
|
|
"mean_token_accuracy": 0.1729837417602539,
|
|
"num_tokens": 39791284.0,
|
|
"step": 20345
|
|
},
|
|
{
|
|
"entropy": 6.037026834487915,
|
|
"epoch": 2.034188034188034,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00045892697320179987,
|
|
"loss": 5.6413,
|
|
"mean_token_accuracy": 0.1684225991368294,
|
|
"num_tokens": 39800475.0,
|
|
"step": 20350
|
|
},
|
|
{
|
|
"entropy": 6.094515562057495,
|
|
"epoch": 2.0346878592492628,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004589064141439319,
|
|
"loss": 5.7492,
|
|
"mean_token_accuracy": 0.16735653728246688,
|
|
"num_tokens": 39809077.0,
|
|
"step": 20355
|
|
},
|
|
{
|
|
"entropy": 6.029647731781006,
|
|
"epoch": 2.0351876843104915,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004588858504590259,
|
|
"loss": 5.6053,
|
|
"mean_token_accuracy": 0.18237573206424712,
|
|
"num_tokens": 39819201.0,
|
|
"step": 20360
|
|
},
|
|
{
|
|
"entropy": 6.0466022968292235,
|
|
"epoch": 2.0356875093717197,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004588652821475992,
|
|
"loss": 5.6621,
|
|
"mean_token_accuracy": 0.1677258148789406,
|
|
"num_tokens": 39829067.0,
|
|
"step": 20365
|
|
},
|
|
{
|
|
"entropy": 6.041173839569092,
|
|
"epoch": 2.0361873344329484,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00045884470921016935,
|
|
"loss": 5.6721,
|
|
"mean_token_accuracy": 0.17131635993719102,
|
|
"num_tokens": 39838766.0,
|
|
"step": 20370
|
|
},
|
|
{
|
|
"entropy": 6.016316366195679,
|
|
"epoch": 2.036687159494177,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.00045882413164725395,
|
|
"loss": 5.6293,
|
|
"mean_token_accuracy": 0.1742175117135048,
|
|
"num_tokens": 39849108.0,
|
|
"step": 20375
|
|
},
|
|
{
|
|
"entropy": 6.0351948738098145,
|
|
"epoch": 2.037186984555406,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00045880354945937056,
|
|
"loss": 5.6886,
|
|
"mean_token_accuracy": 0.1741631880402565,
|
|
"num_tokens": 39857556.0,
|
|
"step": 20380
|
|
},
|
|
{
|
|
"entropy": 6.01390061378479,
|
|
"epoch": 2.037686809616634,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004587829626470373,
|
|
"loss": 5.6366,
|
|
"mean_token_accuracy": 0.17801076024770737,
|
|
"num_tokens": 39868729.0,
|
|
"step": 20385
|
|
},
|
|
{
|
|
"entropy": 6.035105180740357,
|
|
"epoch": 2.0381866346778628,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00045876237121077196,
|
|
"loss": 5.6647,
|
|
"mean_token_accuracy": 0.17323270440101624,
|
|
"num_tokens": 39878463.0,
|
|
"step": 20390
|
|
},
|
|
{
|
|
"entropy": 6.022845268249512,
|
|
"epoch": 2.0386864597390915,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004587417751510926,
|
|
"loss": 5.6368,
|
|
"mean_token_accuracy": 0.17397841960191726,
|
|
"num_tokens": 39888836.0,
|
|
"step": 20395
|
|
},
|
|
{
|
|
"entropy": 6.044895505905151,
|
|
"epoch": 2.0391862848003197,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00045872117446851753,
|
|
"loss": 5.6865,
|
|
"mean_token_accuracy": 0.17629272639751434,
|
|
"num_tokens": 39899567.0,
|
|
"step": 20400
|
|
},
|
|
{
|
|
"entropy": 6.065983057022095,
|
|
"epoch": 2.0396861098615484,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004587005691635649,
|
|
"loss": 5.6963,
|
|
"mean_token_accuracy": 0.16311922073364257,
|
|
"num_tokens": 39908324.0,
|
|
"step": 20405
|
|
},
|
|
{
|
|
"entropy": 6.102595090866089,
|
|
"epoch": 2.040185934922777,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00045867995923675326,
|
|
"loss": 5.7634,
|
|
"mean_token_accuracy": 0.16344040930271148,
|
|
"num_tokens": 39918725.0,
|
|
"step": 20410
|
|
},
|
|
{
|
|
"entropy": 6.0857421398162845,
|
|
"epoch": 2.040685759984006,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004586593446886011,
|
|
"loss": 5.6628,
|
|
"mean_token_accuracy": 0.17012247145175935,
|
|
"num_tokens": 39928317.0,
|
|
"step": 20415
|
|
},
|
|
{
|
|
"entropy": 6.050543355941772,
|
|
"epoch": 2.041185585045234,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004586387255196271,
|
|
"loss": 5.7068,
|
|
"mean_token_accuracy": 0.17428743243217468,
|
|
"num_tokens": 39937314.0,
|
|
"step": 20420
|
|
},
|
|
{
|
|
"entropy": 6.087438488006592,
|
|
"epoch": 2.0416854101064628,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00045861810173035,
|
|
"loss": 5.736,
|
|
"mean_token_accuracy": 0.16432462483644486,
|
|
"num_tokens": 39947323.0,
|
|
"step": 20425
|
|
},
|
|
{
|
|
"entropy": 6.083712434768676,
|
|
"epoch": 2.0421852351676915,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00045859747332128883,
|
|
"loss": 5.7614,
|
|
"mean_token_accuracy": 0.16546907126903534,
|
|
"num_tokens": 39956982.0,
|
|
"step": 20430
|
|
},
|
|
{
|
|
"entropy": 6.097852182388306,
|
|
"epoch": 2.0426850602289197,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004585768402929623,
|
|
"loss": 5.7285,
|
|
"mean_token_accuracy": 0.16703149825334548,
|
|
"num_tokens": 39967619.0,
|
|
"step": 20435
|
|
},
|
|
{
|
|
"entropy": 6.071418380737304,
|
|
"epoch": 2.0431848852901484,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004585562026458898,
|
|
"loss": 5.6754,
|
|
"mean_token_accuracy": 0.1675551176071167,
|
|
"num_tokens": 39977916.0,
|
|
"step": 20440
|
|
},
|
|
{
|
|
"entropy": 6.00427393913269,
|
|
"epoch": 2.043684710351377,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00045853556038059044,
|
|
"loss": 5.6977,
|
|
"mean_token_accuracy": 0.1733304738998413,
|
|
"num_tokens": 39986918.0,
|
|
"step": 20445
|
|
},
|
|
{
|
|
"entropy": 6.041682577133178,
|
|
"epoch": 2.0441845354126054,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.00045851491349758366,
|
|
"loss": 5.6714,
|
|
"mean_token_accuracy": 0.1675277069211006,
|
|
"num_tokens": 39995641.0,
|
|
"step": 20450
|
|
},
|
|
{
|
|
"entropy": 6.065790796279908,
|
|
"epoch": 2.044684360473834,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00045849426199738884,
|
|
"loss": 5.7077,
|
|
"mean_token_accuracy": 0.1623551368713379,
|
|
"num_tokens": 40005525.0,
|
|
"step": 20455
|
|
},
|
|
{
|
|
"entropy": 6.080822467803955,
|
|
"epoch": 2.0451841855350628,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004584736058805256,
|
|
"loss": 5.8055,
|
|
"mean_token_accuracy": 0.1632790520787239,
|
|
"num_tokens": 40014474.0,
|
|
"step": 20460
|
|
},
|
|
{
|
|
"entropy": 6.083623218536377,
|
|
"epoch": 2.0456840105962915,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004584529451475137,
|
|
"loss": 5.7672,
|
|
"mean_token_accuracy": 0.17109280079603195,
|
|
"num_tokens": 40024231.0,
|
|
"step": 20465
|
|
},
|
|
{
|
|
"entropy": 6.007787656784058,
|
|
"epoch": 2.0461838356575197,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00045843227979887286,
|
|
"loss": 5.6348,
|
|
"mean_token_accuracy": 0.17987486869096755,
|
|
"num_tokens": 40033947.0,
|
|
"step": 20470
|
|
},
|
|
{
|
|
"entropy": 6.05950698852539,
|
|
"epoch": 2.0466836607187484,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00045841160983512303,
|
|
"loss": 5.7295,
|
|
"mean_token_accuracy": 0.1659873127937317,
|
|
"num_tokens": 40044800.0,
|
|
"step": 20475
|
|
},
|
|
{
|
|
"entropy": 6.033528470993042,
|
|
"epoch": 2.047183485779977,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004583909352567843,
|
|
"loss": 5.6289,
|
|
"mean_token_accuracy": 0.1673227995634079,
|
|
"num_tokens": 40053629.0,
|
|
"step": 20480
|
|
},
|
|
{
|
|
"entropy": 6.055481433868408,
|
|
"epoch": 2.0476833108412054,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004583702560643769,
|
|
"loss": 5.778,
|
|
"mean_token_accuracy": 0.1679072543978691,
|
|
"num_tokens": 40063014.0,
|
|
"step": 20485
|
|
},
|
|
{
|
|
"entropy": 6.076848030090332,
|
|
"epoch": 2.048183135902434,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000458349572258421,
|
|
"loss": 5.7496,
|
|
"mean_token_accuracy": 0.1660551443696022,
|
|
"num_tokens": 40072332.0,
|
|
"step": 20490
|
|
},
|
|
{
|
|
"entropy": 6.103006792068482,
|
|
"epoch": 2.0486829609636628,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00045832888383943706,
|
|
"loss": 5.8258,
|
|
"mean_token_accuracy": 0.16620447039604186,
|
|
"num_tokens": 40083144.0,
|
|
"step": 20495
|
|
},
|
|
{
|
|
"entropy": 6.078356742858887,
|
|
"epoch": 2.0491827860248915,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004583081908079455,
|
|
"loss": 5.5888,
|
|
"mean_token_accuracy": 0.18454822301864623,
|
|
"num_tokens": 40092035.0,
|
|
"step": 20500
|
|
},
|
|
{
|
|
"entropy": 6.152366876602173,
|
|
"epoch": 2.0496826110861197,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004582874931644671,
|
|
"loss": 5.7255,
|
|
"mean_token_accuracy": 0.1696801468729973,
|
|
"num_tokens": 40101518.0,
|
|
"step": 20505
|
|
},
|
|
{
|
|
"entropy": 6.112811613082886,
|
|
"epoch": 2.0501824361473484,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00045826679090952253,
|
|
"loss": 5.7158,
|
|
"mean_token_accuracy": 0.17249889373779298,
|
|
"num_tokens": 40110856.0,
|
|
"step": 20510
|
|
},
|
|
{
|
|
"entropy": 6.049323463439942,
|
|
"epoch": 2.050682261208577,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00045824608404363267,
|
|
"loss": 5.7775,
|
|
"mean_token_accuracy": 0.1623607411980629,
|
|
"num_tokens": 40120977.0,
|
|
"step": 20515
|
|
},
|
|
{
|
|
"entropy": 6.175363063812256,
|
|
"epoch": 2.0511820862698054,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004582253725673184,
|
|
"loss": 5.7736,
|
|
"mean_token_accuracy": 0.16010714396834375,
|
|
"num_tokens": 40130358.0,
|
|
"step": 20520
|
|
},
|
|
{
|
|
"entropy": 6.085140228271484,
|
|
"epoch": 2.051681911331034,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.000458204656481101,
|
|
"loss": 5.6451,
|
|
"mean_token_accuracy": 0.17719546258449553,
|
|
"num_tokens": 40139889.0,
|
|
"step": 20525
|
|
},
|
|
{
|
|
"entropy": 6.094038820266723,
|
|
"epoch": 2.0521817363922628,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004581839357855015,
|
|
"loss": 5.7837,
|
|
"mean_token_accuracy": 0.1658376485109329,
|
|
"num_tokens": 40150262.0,
|
|
"step": 20530
|
|
},
|
|
{
|
|
"entropy": 6.105523872375488,
|
|
"epoch": 2.0526815614534915,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00045816321048104143,
|
|
"loss": 5.7062,
|
|
"mean_token_accuracy": 0.17075145989656448,
|
|
"num_tokens": 40159256.0,
|
|
"step": 20535
|
|
},
|
|
{
|
|
"entropy": 6.108629179000855,
|
|
"epoch": 2.0531813865147197,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004581424805682421,
|
|
"loss": 5.8738,
|
|
"mean_token_accuracy": 0.16702414005994798,
|
|
"num_tokens": 40169283.0,
|
|
"step": 20540
|
|
},
|
|
{
|
|
"entropy": 6.037505197525024,
|
|
"epoch": 2.0536812115759484,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.000458121746047625,
|
|
"loss": 5.6312,
|
|
"mean_token_accuracy": 0.17663238644599916,
|
|
"num_tokens": 40180621.0,
|
|
"step": 20545
|
|
},
|
|
{
|
|
"entropy": 6.162702989578247,
|
|
"epoch": 2.054181036637177,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004581010069197119,
|
|
"loss": 5.7995,
|
|
"mean_token_accuracy": 0.1626599207520485,
|
|
"num_tokens": 40189601.0,
|
|
"step": 20550
|
|
},
|
|
{
|
|
"entropy": 6.134081602096558,
|
|
"epoch": 2.0546808616984054,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00045808026318502464,
|
|
"loss": 5.7718,
|
|
"mean_token_accuracy": 0.16204890310764314,
|
|
"num_tokens": 40200762.0,
|
|
"step": 20555
|
|
},
|
|
{
|
|
"entropy": 6.209389066696167,
|
|
"epoch": 2.055180686759634,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004580595148440851,
|
|
"loss": 5.7776,
|
|
"mean_token_accuracy": 0.16888571083545684,
|
|
"num_tokens": 40210667.0,
|
|
"step": 20560
|
|
},
|
|
{
|
|
"entropy": 6.036061811447143,
|
|
"epoch": 2.0556805118208628,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004580387618974152,
|
|
"loss": 5.5802,
|
|
"mean_token_accuracy": 0.18033019453287125,
|
|
"num_tokens": 40220239.0,
|
|
"step": 20565
|
|
},
|
|
{
|
|
"entropy": 6.0802146911621096,
|
|
"epoch": 2.0561803368820915,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.00045801800434553715,
|
|
"loss": 5.7637,
|
|
"mean_token_accuracy": 0.16433104276657104,
|
|
"num_tokens": 40231099.0,
|
|
"step": 20570
|
|
},
|
|
{
|
|
"entropy": 6.152751731872558,
|
|
"epoch": 2.0566801619433197,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004579972421889732,
|
|
"loss": 5.7479,
|
|
"mean_token_accuracy": 0.17514243423938752,
|
|
"num_tokens": 40240372.0,
|
|
"step": 20575
|
|
},
|
|
{
|
|
"entropy": 6.11155424118042,
|
|
"epoch": 2.0571799870045484,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004579764754282458,
|
|
"loss": 5.7585,
|
|
"mean_token_accuracy": 0.1633845552802086,
|
|
"num_tokens": 40250819.0,
|
|
"step": 20580
|
|
},
|
|
{
|
|
"entropy": 6.0221182346344,
|
|
"epoch": 2.057679812065777,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00045795570406387726,
|
|
"loss": 5.6745,
|
|
"mean_token_accuracy": 0.17497652173042297,
|
|
"num_tokens": 40260306.0,
|
|
"step": 20585
|
|
},
|
|
{
|
|
"entropy": 5.927273559570312,
|
|
"epoch": 2.0581796371270054,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004579349280963904,
|
|
"loss": 5.6022,
|
|
"mean_token_accuracy": 0.18202160596847533,
|
|
"num_tokens": 40269828.0,
|
|
"step": 20590
|
|
},
|
|
{
|
|
"entropy": 6.171006298065185,
|
|
"epoch": 2.058679462188234,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00045791414752630765,
|
|
"loss": 5.8189,
|
|
"mean_token_accuracy": 0.16496391147375106,
|
|
"num_tokens": 40279947.0,
|
|
"step": 20595
|
|
},
|
|
{
|
|
"entropy": 6.099703407287597,
|
|
"epoch": 2.0591792872494628,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004578933623541522,
|
|
"loss": 5.7591,
|
|
"mean_token_accuracy": 0.1717797949910164,
|
|
"num_tokens": 40289170.0,
|
|
"step": 20600
|
|
},
|
|
{
|
|
"entropy": 6.052335405349732,
|
|
"epoch": 2.0596791123106915,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00045787257258044666,
|
|
"loss": 5.7479,
|
|
"mean_token_accuracy": 0.16569513753056525,
|
|
"num_tokens": 40299561.0,
|
|
"step": 20605
|
|
},
|
|
{
|
|
"entropy": 6.129467296600342,
|
|
"epoch": 2.0601789373719197,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00045785177820571434,
|
|
"loss": 5.7116,
|
|
"mean_token_accuracy": 0.16631195694208145,
|
|
"num_tokens": 40309222.0,
|
|
"step": 20610
|
|
},
|
|
{
|
|
"entropy": 6.189896821975708,
|
|
"epoch": 2.0606787624331484,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00045783097923047833,
|
|
"loss": 5.766,
|
|
"mean_token_accuracy": 0.1683766722679138,
|
|
"num_tokens": 40318868.0,
|
|
"step": 20615
|
|
},
|
|
{
|
|
"entropy": 6.089294910430908,
|
|
"epoch": 2.061178587494377,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00045781017565526194,
|
|
"loss": 5.7256,
|
|
"mean_token_accuracy": 0.1665828362107277,
|
|
"num_tokens": 40328184.0,
|
|
"step": 20620
|
|
},
|
|
{
|
|
"entropy": 6.040116453170777,
|
|
"epoch": 2.0616784125556054,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00045778936748058855,
|
|
"loss": 5.7589,
|
|
"mean_token_accuracy": 0.1783750280737877,
|
|
"num_tokens": 40338927.0,
|
|
"step": 20625
|
|
},
|
|
{
|
|
"entropy": 6.143514156341553,
|
|
"epoch": 2.062178237616834,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00045776855470698163,
|
|
"loss": 5.8025,
|
|
"mean_token_accuracy": 0.16603197306394576,
|
|
"num_tokens": 40349174.0,
|
|
"step": 20630
|
|
},
|
|
{
|
|
"entropy": 6.01706371307373,
|
|
"epoch": 2.0626780626780628,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00045774773733496505,
|
|
"loss": 5.6383,
|
|
"mean_token_accuracy": 0.1774222657084465,
|
|
"num_tokens": 40359460.0,
|
|
"step": 20635
|
|
},
|
|
{
|
|
"entropy": 6.06631326675415,
|
|
"epoch": 2.0631778877392914,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004577269153650624,
|
|
"loss": 5.6392,
|
|
"mean_token_accuracy": 0.17573363780975343,
|
|
"num_tokens": 40368943.0,
|
|
"step": 20640
|
|
},
|
|
{
|
|
"entropy": 6.085320997238159,
|
|
"epoch": 2.0636777128005197,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004577060887977975,
|
|
"loss": 5.6064,
|
|
"mean_token_accuracy": 0.1723095014691353,
|
|
"num_tokens": 40378285.0,
|
|
"step": 20645
|
|
},
|
|
{
|
|
"entropy": 6.012967777252197,
|
|
"epoch": 2.0641775378617484,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00045768525763369443,
|
|
"loss": 5.7105,
|
|
"mean_token_accuracy": 0.17837089002132417,
|
|
"num_tokens": 40386638.0,
|
|
"step": 20650
|
|
},
|
|
{
|
|
"entropy": 6.046308279037476,
|
|
"epoch": 2.064677362922977,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00045766442187327735,
|
|
"loss": 5.7669,
|
|
"mean_token_accuracy": 0.1689102455973625,
|
|
"num_tokens": 40396149.0,
|
|
"step": 20655
|
|
},
|
|
{
|
|
"entropy": 6.055954265594482,
|
|
"epoch": 2.0651771879842054,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00045764358151707043,
|
|
"loss": 5.6608,
|
|
"mean_token_accuracy": 0.17346668541431426,
|
|
"num_tokens": 40405915.0,
|
|
"step": 20660
|
|
},
|
|
{
|
|
"entropy": 6.120338487625122,
|
|
"epoch": 2.065677013045434,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004576227365655979,
|
|
"loss": 5.7011,
|
|
"mean_token_accuracy": 0.17719444036483764,
|
|
"num_tokens": 40415292.0,
|
|
"step": 20665
|
|
},
|
|
{
|
|
"entropy": 6.071564245223999,
|
|
"epoch": 2.0661768381066627,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004576018870193844,
|
|
"loss": 5.7934,
|
|
"mean_token_accuracy": 0.16503249257802963,
|
|
"num_tokens": 40426729.0,
|
|
"step": 20670
|
|
},
|
|
{
|
|
"entropy": 6.064353513717651,
|
|
"epoch": 2.0666766631678914,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004575810328789543,
|
|
"loss": 5.6723,
|
|
"mean_token_accuracy": 0.173725163936615,
|
|
"num_tokens": 40436016.0,
|
|
"step": 20675
|
|
},
|
|
{
|
|
"entropy": 6.1096233367919925,
|
|
"epoch": 2.0671764882291197,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004575601741448325,
|
|
"loss": 5.7654,
|
|
"mean_token_accuracy": 0.1664750784635544,
|
|
"num_tokens": 40444894.0,
|
|
"step": 20680
|
|
},
|
|
{
|
|
"entropy": 6.106636428833008,
|
|
"epoch": 2.0676763132903484,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00045753931081754366,
|
|
"loss": 5.7395,
|
|
"mean_token_accuracy": 0.1720089688897133,
|
|
"num_tokens": 40454650.0,
|
|
"step": 20685
|
|
},
|
|
{
|
|
"entropy": 6.121022367477417,
|
|
"epoch": 2.068176138351577,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004575184428976127,
|
|
"loss": 5.7419,
|
|
"mean_token_accuracy": 0.1644274890422821,
|
|
"num_tokens": 40463809.0,
|
|
"step": 20690
|
|
},
|
|
{
|
|
"entropy": 6.069043684005737,
|
|
"epoch": 2.0686759634128054,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004574975703855647,
|
|
"loss": 5.7181,
|
|
"mean_token_accuracy": 0.17042400389909745,
|
|
"num_tokens": 40474497.0,
|
|
"step": 20695
|
|
},
|
|
{
|
|
"entropy": 6.052027082443237,
|
|
"epoch": 2.069175788474034,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00045747669328192477,
|
|
"loss": 5.7025,
|
|
"mean_token_accuracy": 0.1716521054506302,
|
|
"num_tokens": 40484617.0,
|
|
"step": 20700
|
|
},
|
|
{
|
|
"entropy": 6.055066347122192,
|
|
"epoch": 2.0696756135352627,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004574558115872183,
|
|
"loss": 5.653,
|
|
"mean_token_accuracy": 0.16988637149333954,
|
|
"num_tokens": 40494620.0,
|
|
"step": 20705
|
|
},
|
|
{
|
|
"entropy": 6.021566486358642,
|
|
"epoch": 2.0701754385964914,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00045743492530197046,
|
|
"loss": 5.631,
|
|
"mean_token_accuracy": 0.18368634283542634,
|
|
"num_tokens": 40503546.0,
|
|
"step": 20710
|
|
},
|
|
{
|
|
"entropy": 6.078079319000244,
|
|
"epoch": 2.0706752636577197,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004574140344267069,
|
|
"loss": 5.7092,
|
|
"mean_token_accuracy": 0.17252736538648605,
|
|
"num_tokens": 40513373.0,
|
|
"step": 20715
|
|
},
|
|
{
|
|
"entropy": 6.11840238571167,
|
|
"epoch": 2.0711750887189484,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004573931389619531,
|
|
"loss": 5.7229,
|
|
"mean_token_accuracy": 0.16894706785678865,
|
|
"num_tokens": 40523468.0,
|
|
"step": 20720
|
|
},
|
|
{
|
|
"entropy": 6.087650966644287,
|
|
"epoch": 2.071674913780177,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00045737223890823494,
|
|
"loss": 5.7329,
|
|
"mean_token_accuracy": 0.1600095123052597,
|
|
"num_tokens": 40533570.0,
|
|
"step": 20725
|
|
},
|
|
{
|
|
"entropy": 6.0618328094482425,
|
|
"epoch": 2.0721747388414054,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00045735133426607813,
|
|
"loss": 5.7504,
|
|
"mean_token_accuracy": 0.16909938603639602,
|
|
"num_tokens": 40544223.0,
|
|
"step": 20730
|
|
},
|
|
{
|
|
"entropy": 6.084108066558838,
|
|
"epoch": 2.072674563902634,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00045733042503600865,
|
|
"loss": 5.6651,
|
|
"mean_token_accuracy": 0.17410363852977753,
|
|
"num_tokens": 40554201.0,
|
|
"step": 20735
|
|
},
|
|
{
|
|
"entropy": 6.00155553817749,
|
|
"epoch": 2.0731743889638627,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00045730951121855255,
|
|
"loss": 5.6146,
|
|
"mean_token_accuracy": 0.17838177382946013,
|
|
"num_tokens": 40564134.0,
|
|
"step": 20740
|
|
},
|
|
{
|
|
"entropy": 6.119166421890259,
|
|
"epoch": 2.0736742140250914,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004572885928142362,
|
|
"loss": 5.8386,
|
|
"mean_token_accuracy": 0.15989660173654557,
|
|
"num_tokens": 40575466.0,
|
|
"step": 20745
|
|
},
|
|
{
|
|
"entropy": 6.14246883392334,
|
|
"epoch": 2.0741740390863197,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004572676698235857,
|
|
"loss": 5.8,
|
|
"mean_token_accuracy": 0.1700843408703804,
|
|
"num_tokens": 40586296.0,
|
|
"step": 20750
|
|
},
|
|
{
|
|
"entropy": 6.076147508621216,
|
|
"epoch": 2.0746738641475484,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004572467422471275,
|
|
"loss": 5.7298,
|
|
"mean_token_accuracy": 0.17166358679533006,
|
|
"num_tokens": 40597721.0,
|
|
"step": 20755
|
|
},
|
|
{
|
|
"entropy": 6.090233564376831,
|
|
"epoch": 2.075173689208777,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00045722581008538816,
|
|
"loss": 5.7271,
|
|
"mean_token_accuracy": 0.16843950599431992,
|
|
"num_tokens": 40607804.0,
|
|
"step": 20760
|
|
},
|
|
{
|
|
"entropy": 6.045340061187744,
|
|
"epoch": 2.0756735142700053,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004572048733388944,
|
|
"loss": 5.7249,
|
|
"mean_token_accuracy": 0.16996003091335296,
|
|
"num_tokens": 40617652.0,
|
|
"step": 20765
|
|
},
|
|
{
|
|
"entropy": 6.063038349151611,
|
|
"epoch": 2.076173339331234,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00045718393200817284,
|
|
"loss": 5.7317,
|
|
"mean_token_accuracy": 0.1708322137594223,
|
|
"num_tokens": 40626949.0,
|
|
"step": 20770
|
|
},
|
|
{
|
|
"entropy": 6.056390857696533,
|
|
"epoch": 2.0766731643924627,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00045716298609375044,
|
|
"loss": 5.7755,
|
|
"mean_token_accuracy": 0.1719658210873604,
|
|
"num_tokens": 40636176.0,
|
|
"step": 20775
|
|
},
|
|
{
|
|
"entropy": 6.168983840942383,
|
|
"epoch": 2.077172989453691,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00045714203559615423,
|
|
"loss": 5.7884,
|
|
"mean_token_accuracy": 0.1702670156955719,
|
|
"num_tokens": 40646268.0,
|
|
"step": 20780
|
|
},
|
|
{
|
|
"entropy": 6.115704441070557,
|
|
"epoch": 2.0776728145149197,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004571210805159112,
|
|
"loss": 5.8076,
|
|
"mean_token_accuracy": 0.1621360197663307,
|
|
"num_tokens": 40655352.0,
|
|
"step": 20785
|
|
},
|
|
{
|
|
"entropy": 6.062943172454834,
|
|
"epoch": 2.0781726395761484,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004571001208535487,
|
|
"loss": 5.7254,
|
|
"mean_token_accuracy": 0.16816433370113373,
|
|
"num_tokens": 40665166.0,
|
|
"step": 20790
|
|
},
|
|
{
|
|
"entropy": 6.037515926361084,
|
|
"epoch": 2.078672464637377,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000457079156609594,
|
|
"loss": 5.5971,
|
|
"mean_token_accuracy": 0.18152587711811066,
|
|
"num_tokens": 40675149.0,
|
|
"step": 20795
|
|
},
|
|
{
|
|
"entropy": 6.1098902225494385,
|
|
"epoch": 2.0791722896986053,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004570581877845746,
|
|
"loss": 5.678,
|
|
"mean_token_accuracy": 0.16915171593427658,
|
|
"num_tokens": 40685116.0,
|
|
"step": 20800
|
|
},
|
|
{
|
|
"entropy": 5.996523427963257,
|
|
"epoch": 2.079672114759834,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.000457037214379018,
|
|
"loss": 5.595,
|
|
"mean_token_accuracy": 0.17817540019750594,
|
|
"num_tokens": 40694834.0,
|
|
"step": 20805
|
|
},
|
|
{
|
|
"entropy": 6.143706321716309,
|
|
"epoch": 2.0801719398210627,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00045701623639345204,
|
|
"loss": 5.8455,
|
|
"mean_token_accuracy": 0.16176264435052873,
|
|
"num_tokens": 40704294.0,
|
|
"step": 20810
|
|
},
|
|
{
|
|
"entropy": 6.034538793563843,
|
|
"epoch": 2.080671764882291,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00045699525382840423,
|
|
"loss": 5.7223,
|
|
"mean_token_accuracy": 0.17081956714391708,
|
|
"num_tokens": 40714269.0,
|
|
"step": 20815
|
|
},
|
|
{
|
|
"entropy": 6.20108118057251,
|
|
"epoch": 2.0811715899435197,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00045697426668440277,
|
|
"loss": 5.7772,
|
|
"mean_token_accuracy": 0.1597936272621155,
|
|
"num_tokens": 40723795.0,
|
|
"step": 20820
|
|
},
|
|
{
|
|
"entropy": 6.0939079284667965,
|
|
"epoch": 2.0816714150047484,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00045695327496197557,
|
|
"loss": 5.8033,
|
|
"mean_token_accuracy": 0.16345560550689697,
|
|
"num_tokens": 40734702.0,
|
|
"step": 20825
|
|
},
|
|
{
|
|
"entropy": 6.041447448730469,
|
|
"epoch": 2.082171240065977,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004569322786616508,
|
|
"loss": 5.6251,
|
|
"mean_token_accuracy": 0.17766495645046235,
|
|
"num_tokens": 40744174.0,
|
|
"step": 20830
|
|
},
|
|
{
|
|
"entropy": 6.081759071350097,
|
|
"epoch": 2.0826710651272053,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004569112777839567,
|
|
"loss": 5.783,
|
|
"mean_token_accuracy": 0.16471962183713912,
|
|
"num_tokens": 40754474.0,
|
|
"step": 20835
|
|
},
|
|
{
|
|
"entropy": 6.075573348999024,
|
|
"epoch": 2.083170890188434,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00045689027232942165,
|
|
"loss": 5.6993,
|
|
"mean_token_accuracy": 0.1742400899529457,
|
|
"num_tokens": 40764051.0,
|
|
"step": 20840
|
|
},
|
|
{
|
|
"entropy": 6.16472749710083,
|
|
"epoch": 2.0836707152496627,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 0.0004568692622985742,
|
|
"loss": 5.7488,
|
|
"mean_token_accuracy": 0.16523120552301407,
|
|
"num_tokens": 40774518.0,
|
|
"step": 20845
|
|
},
|
|
{
|
|
"entropy": 6.05124340057373,
|
|
"epoch": 2.084170540310891,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00045684824769194284,
|
|
"loss": 5.7588,
|
|
"mean_token_accuracy": 0.1737546965479851,
|
|
"num_tokens": 40783887.0,
|
|
"step": 20850
|
|
},
|
|
{
|
|
"entropy": 6.102864408493042,
|
|
"epoch": 2.0846703653721197,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004568272285100564,
|
|
"loss": 5.7968,
|
|
"mean_token_accuracy": 0.1613840103149414,
|
|
"num_tokens": 40793607.0,
|
|
"step": 20855
|
|
},
|
|
{
|
|
"entropy": 6.081948280334473,
|
|
"epoch": 2.0851701904333484,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004568062047534437,
|
|
"loss": 5.7341,
|
|
"mean_token_accuracy": 0.16621689945459367,
|
|
"num_tokens": 40802948.0,
|
|
"step": 20860
|
|
},
|
|
{
|
|
"entropy": 6.012741231918335,
|
|
"epoch": 2.085670015494577,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004567851764226337,
|
|
"loss": 5.7097,
|
|
"mean_token_accuracy": 0.17045191377401353,
|
|
"num_tokens": 40812733.0,
|
|
"step": 20865
|
|
},
|
|
{
|
|
"entropy": 6.098845624923706,
|
|
"epoch": 2.0861698405558053,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00045676414351815533,
|
|
"loss": 5.7011,
|
|
"mean_token_accuracy": 0.16915300041437148,
|
|
"num_tokens": 40821074.0,
|
|
"step": 20870
|
|
},
|
|
{
|
|
"entropy": 6.14929723739624,
|
|
"epoch": 2.086669665617034,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004567431060405379,
|
|
"loss": 5.757,
|
|
"mean_token_accuracy": 0.1727476492524147,
|
|
"num_tokens": 40831427.0,
|
|
"step": 20875
|
|
},
|
|
{
|
|
"entropy": 6.113503313064575,
|
|
"epoch": 2.0871694906782627,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004567220639903108,
|
|
"loss": 5.7253,
|
|
"mean_token_accuracy": 0.17133447378873826,
|
|
"num_tokens": 40841433.0,
|
|
"step": 20880
|
|
},
|
|
{
|
|
"entropy": 6.1086982727050785,
|
|
"epoch": 2.087669315739491,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00045670101736800325,
|
|
"loss": 5.7369,
|
|
"mean_token_accuracy": 0.16475818753242494,
|
|
"num_tokens": 40851176.0,
|
|
"step": 20885
|
|
},
|
|
{
|
|
"entropy": 6.184404516220093,
|
|
"epoch": 2.0881691408007197,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00045667996617414485,
|
|
"loss": 5.7833,
|
|
"mean_token_accuracy": 0.1623788982629776,
|
|
"num_tokens": 40860436.0,
|
|
"step": 20890
|
|
},
|
|
{
|
|
"entropy": 6.197712326049805,
|
|
"epoch": 2.0886689658619484,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004566589104092653,
|
|
"loss": 5.8329,
|
|
"mean_token_accuracy": 0.16236623972654343,
|
|
"num_tokens": 40870650.0,
|
|
"step": 20895
|
|
},
|
|
{
|
|
"entropy": 6.069238901138306,
|
|
"epoch": 2.089168790923177,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004566378500738943,
|
|
"loss": 5.7304,
|
|
"mean_token_accuracy": 0.17164090722799302,
|
|
"num_tokens": 40879967.0,
|
|
"step": 20900
|
|
},
|
|
{
|
|
"entropy": 6.053676319122315,
|
|
"epoch": 2.0896686159844053,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00045661678516856164,
|
|
"loss": 5.6299,
|
|
"mean_token_accuracy": 0.17872551828622818,
|
|
"num_tokens": 40889299.0,
|
|
"step": 20905
|
|
},
|
|
{
|
|
"entropy": 5.993607664108277,
|
|
"epoch": 2.090168441045634,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004565957156937975,
|
|
"loss": 5.5668,
|
|
"mean_token_accuracy": 0.18496748358011245,
|
|
"num_tokens": 40899165.0,
|
|
"step": 20910
|
|
},
|
|
{
|
|
"entropy": 6.062177562713623,
|
|
"epoch": 2.0906682661068627,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004565746416501318,
|
|
"loss": 5.7798,
|
|
"mean_token_accuracy": 0.16814637184143066,
|
|
"num_tokens": 40908834.0,
|
|
"step": 20915
|
|
},
|
|
{
|
|
"entropy": 6.094614458084107,
|
|
"epoch": 2.091168091168091,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00045655356303809494,
|
|
"loss": 5.7577,
|
|
"mean_token_accuracy": 0.1639866054058075,
|
|
"num_tokens": 40918132.0,
|
|
"step": 20920
|
|
},
|
|
{
|
|
"entropy": 6.087294483184815,
|
|
"epoch": 2.0916679162293197,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00045653247985821707,
|
|
"loss": 5.7045,
|
|
"mean_token_accuracy": 0.16785240322351455,
|
|
"num_tokens": 40929050.0,
|
|
"step": 20925
|
|
},
|
|
{
|
|
"entropy": 6.128788423538208,
|
|
"epoch": 2.0921677412905484,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00045651139211102875,
|
|
"loss": 5.8017,
|
|
"mean_token_accuracy": 0.16144311279058457,
|
|
"num_tokens": 40938876.0,
|
|
"step": 20930
|
|
},
|
|
{
|
|
"entropy": 6.116076993942261,
|
|
"epoch": 2.092667566351777,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00045649029979706054,
|
|
"loss": 5.7639,
|
|
"mean_token_accuracy": 0.16797665655612945,
|
|
"num_tokens": 40948639.0,
|
|
"step": 20935
|
|
},
|
|
{
|
|
"entropy": 6.103848075866699,
|
|
"epoch": 2.0931673914130053,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00045646920291684303,
|
|
"loss": 5.7266,
|
|
"mean_token_accuracy": 0.1643073447048664,
|
|
"num_tokens": 40958718.0,
|
|
"step": 20940
|
|
},
|
|
{
|
|
"entropy": 6.084023761749267,
|
|
"epoch": 2.093667216474234,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004564481014709072,
|
|
"loss": 5.7081,
|
|
"mean_token_accuracy": 0.16380864530801773,
|
|
"num_tokens": 40967962.0,
|
|
"step": 20945
|
|
},
|
|
{
|
|
"entropy": 6.085675668716431,
|
|
"epoch": 2.0941670415354627,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004564269954597836,
|
|
"loss": 5.6877,
|
|
"mean_token_accuracy": 0.16963281780481337,
|
|
"num_tokens": 40978566.0,
|
|
"step": 20950
|
|
},
|
|
{
|
|
"entropy": 6.048718881607056,
|
|
"epoch": 2.094666866596691,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00045640588488400364,
|
|
"loss": 5.6614,
|
|
"mean_token_accuracy": 0.18051191419363022,
|
|
"num_tokens": 40989439.0,
|
|
"step": 20955
|
|
},
|
|
{
|
|
"entropy": 6.054898118972778,
|
|
"epoch": 2.0951666916579197,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004563847697440983,
|
|
"loss": 5.687,
|
|
"mean_token_accuracy": 0.17219069451093674,
|
|
"num_tokens": 40998934.0,
|
|
"step": 20960
|
|
},
|
|
{
|
|
"entropy": 6.070707178115844,
|
|
"epoch": 2.0956665167191484,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00045636365004059876,
|
|
"loss": 5.6462,
|
|
"mean_token_accuracy": 0.1778530955314636,
|
|
"num_tokens": 41007965.0,
|
|
"step": 20965
|
|
},
|
|
{
|
|
"entropy": 6.140841436386109,
|
|
"epoch": 2.0961663417803766,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00045634252577403644,
|
|
"loss": 5.7736,
|
|
"mean_token_accuracy": 0.15720486491918564,
|
|
"num_tokens": 41018572.0,
|
|
"step": 20970
|
|
},
|
|
{
|
|
"entropy": 6.098780679702759,
|
|
"epoch": 2.0966661668416053,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00045632139694494294,
|
|
"loss": 5.6542,
|
|
"mean_token_accuracy": 0.1742400720715523,
|
|
"num_tokens": 41028272.0,
|
|
"step": 20975
|
|
},
|
|
{
|
|
"entropy": 5.970915842056274,
|
|
"epoch": 2.097165991902834,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004563002635538496,
|
|
"loss": 5.6385,
|
|
"mean_token_accuracy": 0.18230925798416137,
|
|
"num_tokens": 41037282.0,
|
|
"step": 20980
|
|
},
|
|
{
|
|
"entropy": 6.105281496047974,
|
|
"epoch": 2.0976658169640627,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004562791256012884,
|
|
"loss": 5.7064,
|
|
"mean_token_accuracy": 0.1806460827589035,
|
|
"num_tokens": 41046590.0,
|
|
"step": 20985
|
|
},
|
|
{
|
|
"entropy": 5.946405220031738,
|
|
"epoch": 2.098165642025291,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004562579830877911,
|
|
"loss": 5.5433,
|
|
"mean_token_accuracy": 0.1897762030363083,
|
|
"num_tokens": 41057014.0,
|
|
"step": 20990
|
|
},
|
|
{
|
|
"entropy": 6.0902985572814945,
|
|
"epoch": 2.0986654670865197,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004562368360138894,
|
|
"loss": 5.7179,
|
|
"mean_token_accuracy": 0.16748330891132354,
|
|
"num_tokens": 41065882.0,
|
|
"step": 20995
|
|
},
|
|
{
|
|
"entropy": 6.040648460388184,
|
|
"epoch": 2.0991652921477484,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004562156843801157,
|
|
"loss": 5.7117,
|
|
"mean_token_accuracy": 0.1717856392264366,
|
|
"num_tokens": 41075971.0,
|
|
"step": 21000
|
|
},
|
|
{
|
|
"epoch": 2.0991652921477484,
|
|
"eval_entropy": 5.87447228354297,
|
|
"eval_loss": 5.860039710998535,
|
|
"eval_mean_token_accuracy": 0.17255805956506445,
|
|
"eval_num_tokens": 41075971.0,
|
|
"eval_runtime": 23.7112,
|
|
"eval_samples_per_second": 1309.294,
|
|
"eval_steps_per_second": 163.678,
|
|
"step": 21000
|
|
},
|
|
{
|
|
"entropy": 6.043226432800293,
|
|
"epoch": 2.0996651172089766,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00045619452818700194,
|
|
"loss": 5.6037,
|
|
"mean_token_accuracy": 0.18117007613182068,
|
|
"num_tokens": 41085305.0,
|
|
"step": 21005
|
|
},
|
|
{
|
|
"entropy": 6.160520792007446,
|
|
"epoch": 2.1001649422702053,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00045617336743508056,
|
|
"loss": 5.8051,
|
|
"mean_token_accuracy": 0.16229568421840668,
|
|
"num_tokens": 41094995.0,
|
|
"step": 21010
|
|
},
|
|
{
|
|
"entropy": 6.10351939201355,
|
|
"epoch": 2.100664767331434,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004561522021248837,
|
|
"loss": 5.7217,
|
|
"mean_token_accuracy": 0.172009240090847,
|
|
"num_tokens": 41104809.0,
|
|
"step": 21015
|
|
},
|
|
{
|
|
"entropy": 6.132609558105469,
|
|
"epoch": 2.1011645923926627,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004561310322569442,
|
|
"loss": 5.826,
|
|
"mean_token_accuracy": 0.1606111392378807,
|
|
"num_tokens": 41116002.0,
|
|
"step": 21020
|
|
},
|
|
{
|
|
"entropy": 6.085776615142822,
|
|
"epoch": 2.101664417453891,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00045610985783179454,
|
|
"loss": 5.6881,
|
|
"mean_token_accuracy": 0.17196666300296784,
|
|
"num_tokens": 41127657.0,
|
|
"step": 21025
|
|
},
|
|
{
|
|
"entropy": 6.079985809326172,
|
|
"epoch": 2.1021642425151197,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004560886788499674,
|
|
"loss": 5.7157,
|
|
"mean_token_accuracy": 0.1727018654346466,
|
|
"num_tokens": 41137151.0,
|
|
"step": 21030
|
|
},
|
|
{
|
|
"entropy": 6.0521493434906,
|
|
"epoch": 2.1026640675763484,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00045606749531199573,
|
|
"loss": 5.7006,
|
|
"mean_token_accuracy": 0.17193552255630493,
|
|
"num_tokens": 41146365.0,
|
|
"step": 21035
|
|
},
|
|
{
|
|
"entropy": 6.10101056098938,
|
|
"epoch": 2.1031638926375766,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00045604630721841243,
|
|
"loss": 5.7288,
|
|
"mean_token_accuracy": 0.162210114300251,
|
|
"num_tokens": 41155506.0,
|
|
"step": 21040
|
|
},
|
|
{
|
|
"entropy": 6.063256788253784,
|
|
"epoch": 2.1036637176988053,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00045602511456975064,
|
|
"loss": 5.6839,
|
|
"mean_token_accuracy": 0.16659491509199142,
|
|
"num_tokens": 41166382.0,
|
|
"step": 21045
|
|
},
|
|
{
|
|
"entropy": 6.035562944412232,
|
|
"epoch": 2.104163542760034,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004560039173665436,
|
|
"loss": 5.692,
|
|
"mean_token_accuracy": 0.1692475512623787,
|
|
"num_tokens": 41176658.0,
|
|
"step": 21050
|
|
},
|
|
{
|
|
"entropy": 5.951170969009399,
|
|
"epoch": 2.1046633678212627,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004559827156093245,
|
|
"loss": 5.5207,
|
|
"mean_token_accuracy": 0.18840957731008529,
|
|
"num_tokens": 41187528.0,
|
|
"step": 21055
|
|
},
|
|
{
|
|
"entropy": 6.098663806915283,
|
|
"epoch": 2.105163192882491,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004559615092986268,
|
|
"loss": 5.7313,
|
|
"mean_token_accuracy": 0.17364161610603332,
|
|
"num_tokens": 41197923.0,
|
|
"step": 21060
|
|
},
|
|
{
|
|
"entropy": 5.994360160827637,
|
|
"epoch": 2.1056630179437197,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00045594029843498425,
|
|
"loss": 5.6636,
|
|
"mean_token_accuracy": 0.17617646902799605,
|
|
"num_tokens": 41207358.0,
|
|
"step": 21065
|
|
},
|
|
{
|
|
"entropy": 6.070820236206055,
|
|
"epoch": 2.1061628430049484,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00045591908301893027,
|
|
"loss": 5.7662,
|
|
"mean_token_accuracy": 0.16704825758934022,
|
|
"num_tokens": 41217733.0,
|
|
"step": 21070
|
|
},
|
|
{
|
|
"entropy": 6.170948219299317,
|
|
"epoch": 2.1066626680661766,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00045589786305099875,
|
|
"loss": 5.8555,
|
|
"mean_token_accuracy": 0.1630786567926407,
|
|
"num_tokens": 41228065.0,
|
|
"step": 21075
|
|
},
|
|
{
|
|
"entropy": 6.160651159286499,
|
|
"epoch": 2.1071624931274053,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004558766385317235,
|
|
"loss": 5.773,
|
|
"mean_token_accuracy": 0.16907128393650056,
|
|
"num_tokens": 41237192.0,
|
|
"step": 21080
|
|
},
|
|
{
|
|
"entropy": 5.932946300506591,
|
|
"epoch": 2.107662318188634,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00045585540946163855,
|
|
"loss": 5.5338,
|
|
"mean_token_accuracy": 0.18920145630836488,
|
|
"num_tokens": 41247583.0,
|
|
"step": 21085
|
|
},
|
|
{
|
|
"entropy": 6.0579766750335695,
|
|
"epoch": 2.1081621432498627,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004558341758412781,
|
|
"loss": 5.7115,
|
|
"mean_token_accuracy": 0.16862494945526124,
|
|
"num_tokens": 41257179.0,
|
|
"step": 21090
|
|
},
|
|
{
|
|
"entropy": 6.1462202072143555,
|
|
"epoch": 2.108661968311091,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004558129376711763,
|
|
"loss": 5.7625,
|
|
"mean_token_accuracy": 0.16506483405828476,
|
|
"num_tokens": 41266737.0,
|
|
"step": 21095
|
|
},
|
|
{
|
|
"entropy": 6.039091682434082,
|
|
"epoch": 2.1091617933723197,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004557916949518675,
|
|
"loss": 5.6611,
|
|
"mean_token_accuracy": 0.1725896954536438,
|
|
"num_tokens": 41275449.0,
|
|
"step": 21100
|
|
},
|
|
{
|
|
"entropy": 6.045521593093872,
|
|
"epoch": 2.1096616184335484,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004557704476838862,
|
|
"loss": 5.7653,
|
|
"mean_token_accuracy": 0.17068218439817429,
|
|
"num_tokens": 41285555.0,
|
|
"step": 21105
|
|
},
|
|
{
|
|
"entropy": 6.002806758880615,
|
|
"epoch": 2.1101614434947766,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00045574919586776686,
|
|
"loss": 5.5847,
|
|
"mean_token_accuracy": 0.18043577820062637,
|
|
"num_tokens": 41295649.0,
|
|
"step": 21110
|
|
},
|
|
{
|
|
"entropy": 6.0682353496551515,
|
|
"epoch": 2.1106612685560053,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00045572793950404434,
|
|
"loss": 5.7383,
|
|
"mean_token_accuracy": 0.16983322501182557,
|
|
"num_tokens": 41304762.0,
|
|
"step": 21115
|
|
},
|
|
{
|
|
"entropy": 6.024362516403198,
|
|
"epoch": 2.111161093617234,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00045570667859325337,
|
|
"loss": 5.7003,
|
|
"mean_token_accuracy": 0.17224484235048293,
|
|
"num_tokens": 41314840.0,
|
|
"step": 21120
|
|
},
|
|
{
|
|
"entropy": 6.102211236953735,
|
|
"epoch": 2.1116609186784627,
|
|
"grad_norm": 3.0,
|
|
"learning_rate": 0.00045568541313592884,
|
|
"loss": 5.735,
|
|
"mean_token_accuracy": 0.17248350605368615,
|
|
"num_tokens": 41326056.0,
|
|
"step": 21125
|
|
},
|
|
{
|
|
"entropy": 6.093270969390869,
|
|
"epoch": 2.112160743739691,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00045566414313260586,
|
|
"loss": 5.6732,
|
|
"mean_token_accuracy": 0.1714185133576393,
|
|
"num_tokens": 41336348.0,
|
|
"step": 21130
|
|
},
|
|
{
|
|
"entropy": 6.067757320404053,
|
|
"epoch": 2.1126605688009197,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004556428685838194,
|
|
"loss": 5.7449,
|
|
"mean_token_accuracy": 0.16485064774751662,
|
|
"num_tokens": 41347112.0,
|
|
"step": 21135
|
|
},
|
|
{
|
|
"entropy": 6.060745525360107,
|
|
"epoch": 2.1131603938621484,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.000455621589490105,
|
|
"loss": 5.7041,
|
|
"mean_token_accuracy": 0.16742128431797026,
|
|
"num_tokens": 41356872.0,
|
|
"step": 21140
|
|
},
|
|
{
|
|
"entropy": 6.107937622070312,
|
|
"epoch": 2.1136602189233766,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004556003058519979,
|
|
"loss": 5.6866,
|
|
"mean_token_accuracy": 0.17049000561237335,
|
|
"num_tokens": 41365710.0,
|
|
"step": 21145
|
|
},
|
|
{
|
|
"entropy": 5.9956748485565186,
|
|
"epoch": 2.1141600439846053,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00045557901767003347,
|
|
"loss": 5.6592,
|
|
"mean_token_accuracy": 0.1711634263396263,
|
|
"num_tokens": 41375676.0,
|
|
"step": 21150
|
|
},
|
|
{
|
|
"entropy": 6.0281473159790036,
|
|
"epoch": 2.114659869045834,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00045555772494474745,
|
|
"loss": 5.7357,
|
|
"mean_token_accuracy": 0.1719532147049904,
|
|
"num_tokens": 41386134.0,
|
|
"step": 21155
|
|
},
|
|
{
|
|
"entropy": 6.08924126625061,
|
|
"epoch": 2.1151596941070627,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004555364276766756,
|
|
"loss": 5.6713,
|
|
"mean_token_accuracy": 0.17020233422517778,
|
|
"num_tokens": 41396318.0,
|
|
"step": 21160
|
|
},
|
|
{
|
|
"entropy": 6.018682813644409,
|
|
"epoch": 2.115659519168291,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004555151258663535,
|
|
"loss": 5.663,
|
|
"mean_token_accuracy": 0.17581064254045486,
|
|
"num_tokens": 41405921.0,
|
|
"step": 21165
|
|
},
|
|
{
|
|
"entropy": 6.001601266860962,
|
|
"epoch": 2.1161593442295197,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004554938195143175,
|
|
"loss": 5.6751,
|
|
"mean_token_accuracy": 0.1715221509337425,
|
|
"num_tokens": 41415868.0,
|
|
"step": 21170
|
|
},
|
|
{
|
|
"entropy": 6.030138444900513,
|
|
"epoch": 2.1166591692907484,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004554725086211033,
|
|
"loss": 5.7196,
|
|
"mean_token_accuracy": 0.17403461486101152,
|
|
"num_tokens": 41425585.0,
|
|
"step": 21175
|
|
},
|
|
{
|
|
"entropy": 6.039669847488403,
|
|
"epoch": 2.1171589943519766,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00045545119318724734,
|
|
"loss": 5.6975,
|
|
"mean_token_accuracy": 0.17588476836681366,
|
|
"num_tokens": 41434675.0,
|
|
"step": 21180
|
|
},
|
|
{
|
|
"entropy": 6.195851802825928,
|
|
"epoch": 2.1176588194132053,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004554298732132857,
|
|
"loss": 5.8552,
|
|
"mean_token_accuracy": 0.16021475195884705,
|
|
"num_tokens": 41445644.0,
|
|
"step": 21185
|
|
},
|
|
{
|
|
"entropy": 5.985871315002441,
|
|
"epoch": 2.118158644474434,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004554085486997549,
|
|
"loss": 5.6439,
|
|
"mean_token_accuracy": 0.17601146101951598,
|
|
"num_tokens": 41455416.0,
|
|
"step": 21190
|
|
},
|
|
{
|
|
"entropy": 6.062557649612427,
|
|
"epoch": 2.1186584695356627,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004553872196471914,
|
|
"loss": 5.7485,
|
|
"mean_token_accuracy": 0.1738804593682289,
|
|
"num_tokens": 41465988.0,
|
|
"step": 21195
|
|
},
|
|
{
|
|
"entropy": 6.034213399887085,
|
|
"epoch": 2.119158294596891,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00045536588605613195,
|
|
"loss": 5.6742,
|
|
"mean_token_accuracy": 0.17805061638355255,
|
|
"num_tokens": 41475704.0,
|
|
"step": 21200
|
|
},
|
|
{
|
|
"entropy": 6.0915168762207035,
|
|
"epoch": 2.1196581196581197,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00045534454792711324,
|
|
"loss": 5.8168,
|
|
"mean_token_accuracy": 0.16398298144340515,
|
|
"num_tokens": 41485723.0,
|
|
"step": 21205
|
|
},
|
|
{
|
|
"entropy": 6.164515638351441,
|
|
"epoch": 2.1201579447193484,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00045532320526067206,
|
|
"loss": 5.7595,
|
|
"mean_token_accuracy": 0.16495111510157584,
|
|
"num_tokens": 41495610.0,
|
|
"step": 21210
|
|
},
|
|
{
|
|
"entropy": 6.0976286888122555,
|
|
"epoch": 2.1206577697805766,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004553018580573454,
|
|
"loss": 5.72,
|
|
"mean_token_accuracy": 0.16745613813400267,
|
|
"num_tokens": 41504799.0,
|
|
"step": 21215
|
|
},
|
|
{
|
|
"entropy": 6.054748630523681,
|
|
"epoch": 2.1211575948418053,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.00045528050631767037,
|
|
"loss": 5.7132,
|
|
"mean_token_accuracy": 0.16490430980920792,
|
|
"num_tokens": 41514335.0,
|
|
"step": 21220
|
|
},
|
|
{
|
|
"entropy": 6.043227291107177,
|
|
"epoch": 2.121657419903034,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00045525915004218426,
|
|
"loss": 5.7142,
|
|
"mean_token_accuracy": 0.1681663990020752,
|
|
"num_tokens": 41523955.0,
|
|
"step": 21225
|
|
},
|
|
{
|
|
"entropy": 6.082354354858398,
|
|
"epoch": 2.1221572449642627,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00045523778923142435,
|
|
"loss": 5.702,
|
|
"mean_token_accuracy": 0.17357385009527207,
|
|
"num_tokens": 41532647.0,
|
|
"step": 21230
|
|
},
|
|
{
|
|
"entropy": 6.089354848861694,
|
|
"epoch": 2.122657070025491,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004552164238859279,
|
|
"loss": 5.7251,
|
|
"mean_token_accuracy": 0.16607663333415984,
|
|
"num_tokens": 41542885.0,
|
|
"step": 21235
|
|
},
|
|
{
|
|
"entropy": 6.049063348770142,
|
|
"epoch": 2.1231568950867197,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00045519505400623274,
|
|
"loss": 5.8339,
|
|
"mean_token_accuracy": 0.17342146039009093,
|
|
"num_tokens": 41553381.0,
|
|
"step": 21240
|
|
},
|
|
{
|
|
"entropy": 6.124532699584961,
|
|
"epoch": 2.1236567201479484,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00045517367959287635,
|
|
"loss": 5.7686,
|
|
"mean_token_accuracy": 0.1632281720638275,
|
|
"num_tokens": 41563740.0,
|
|
"step": 21245
|
|
},
|
|
{
|
|
"entropy": 6.126098346710205,
|
|
"epoch": 2.1241565452091766,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00045515230064639657,
|
|
"loss": 5.6395,
|
|
"mean_token_accuracy": 0.17482392191886903,
|
|
"num_tokens": 41574404.0,
|
|
"step": 21250
|
|
},
|
|
{
|
|
"entropy": 6.091603803634643,
|
|
"epoch": 2.1246563702704053,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00045513091716733117,
|
|
"loss": 5.6843,
|
|
"mean_token_accuracy": 0.1696012757718563,
|
|
"num_tokens": 41583532.0,
|
|
"step": 21255
|
|
},
|
|
{
|
|
"entropy": 6.01133131980896,
|
|
"epoch": 2.125156195331634,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.00045510952915621834,
|
|
"loss": 5.6574,
|
|
"mean_token_accuracy": 0.17414176613092422,
|
|
"num_tokens": 41594003.0,
|
|
"step": 21260
|
|
},
|
|
{
|
|
"entropy": 6.0694318294525145,
|
|
"epoch": 2.1256560203928627,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004550881366135961,
|
|
"loss": 5.6877,
|
|
"mean_token_accuracy": 0.16863466054201126,
|
|
"num_tokens": 41603779.0,
|
|
"step": 21265
|
|
},
|
|
{
|
|
"entropy": 5.972971963882446,
|
|
"epoch": 2.126155845454091,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.00045506673954000265,
|
|
"loss": 5.5111,
|
|
"mean_token_accuracy": 0.19240949004888536,
|
|
"num_tokens": 41613666.0,
|
|
"step": 21270
|
|
},
|
|
{
|
|
"entropy": 6.129001760482788,
|
|
"epoch": 2.1266556705153197,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004550453379359763,
|
|
"loss": 5.7239,
|
|
"mean_token_accuracy": 0.16624608933925628,
|
|
"num_tokens": 41622312.0,
|
|
"step": 21275
|
|
},
|
|
{
|
|
"entropy": 6.148170137405396,
|
|
"epoch": 2.1271554955765484,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00045502393180205564,
|
|
"loss": 5.8242,
|
|
"mean_token_accuracy": 0.15741970390081406,
|
|
"num_tokens": 41632798.0,
|
|
"step": 21280
|
|
},
|
|
{
|
|
"entropy": 6.055782651901245,
|
|
"epoch": 2.1276553206377766,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004550025211387792,
|
|
"loss": 5.7291,
|
|
"mean_token_accuracy": 0.17047278583049774,
|
|
"num_tokens": 41641396.0,
|
|
"step": 21285
|
|
},
|
|
{
|
|
"entropy": 6.1286908149719235,
|
|
"epoch": 2.1281551456990053,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004549811059466857,
|
|
"loss": 5.761,
|
|
"mean_token_accuracy": 0.16923148930072784,
|
|
"num_tokens": 41650136.0,
|
|
"step": 21290
|
|
},
|
|
{
|
|
"entropy": 6.114555501937867,
|
|
"epoch": 2.128654970760234,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004549596862263138,
|
|
"loss": 5.7606,
|
|
"mean_token_accuracy": 0.16160599142313004,
|
|
"num_tokens": 41660001.0,
|
|
"step": 21295
|
|
},
|
|
{
|
|
"entropy": 6.038178396224976,
|
|
"epoch": 2.1291547958214627,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004549382619782025,
|
|
"loss": 5.7293,
|
|
"mean_token_accuracy": 0.17326404005289078,
|
|
"num_tokens": 41669846.0,
|
|
"step": 21300
|
|
},
|
|
{
|
|
"entropy": 6.0749164581298825,
|
|
"epoch": 2.129654620882691,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004549168332028908,
|
|
"loss": 5.659,
|
|
"mean_token_accuracy": 0.17638987600803374,
|
|
"num_tokens": 41678684.0,
|
|
"step": 21305
|
|
},
|
|
{
|
|
"entropy": 6.025007486343384,
|
|
"epoch": 2.1301544459439197,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00045489539990091796,
|
|
"loss": 5.6916,
|
|
"mean_token_accuracy": 0.17100845277309418,
|
|
"num_tokens": 41688475.0,
|
|
"step": 21310
|
|
},
|
|
{
|
|
"entropy": 6.114686679840088,
|
|
"epoch": 2.1306542710051484,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00045487396207282316,
|
|
"loss": 5.6544,
|
|
"mean_token_accuracy": 0.1791937157511711,
|
|
"num_tokens": 41698541.0,
|
|
"step": 21315
|
|
},
|
|
{
|
|
"entropy": 6.059953498840332,
|
|
"epoch": 2.1311540960663766,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00045485251971914565,
|
|
"loss": 5.6958,
|
|
"mean_token_accuracy": 0.17249010801315307,
|
|
"num_tokens": 41707138.0,
|
|
"step": 21320
|
|
},
|
|
{
|
|
"entropy": 6.062049818038941,
|
|
"epoch": 2.1316539211276053,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004548310728404251,
|
|
"loss": 5.7461,
|
|
"mean_token_accuracy": 0.1677121952176094,
|
|
"num_tokens": 41718103.0,
|
|
"step": 21325
|
|
},
|
|
{
|
|
"entropy": 6.116953611373901,
|
|
"epoch": 2.132153746188834,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000454809621437201,
|
|
"loss": 5.6974,
|
|
"mean_token_accuracy": 0.16968277245759963,
|
|
"num_tokens": 41727889.0,
|
|
"step": 21330
|
|
},
|
|
{
|
|
"entropy": 6.134177303314209,
|
|
"epoch": 2.1326535712500623,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004547881655100131,
|
|
"loss": 5.786,
|
|
"mean_token_accuracy": 0.16637807488441467,
|
|
"num_tokens": 41738421.0,
|
|
"step": 21335
|
|
},
|
|
{
|
|
"entropy": 6.023992967605591,
|
|
"epoch": 2.133153396311291,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004547667050594013,
|
|
"loss": 5.6273,
|
|
"mean_token_accuracy": 0.1806188002228737,
|
|
"num_tokens": 41748192.0,
|
|
"step": 21340
|
|
},
|
|
{
|
|
"entropy": 6.020236396789551,
|
|
"epoch": 2.1336532213725197,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00045474524008590536,
|
|
"loss": 5.6851,
|
|
"mean_token_accuracy": 0.17579428851604462,
|
|
"num_tokens": 41757000.0,
|
|
"step": 21345
|
|
},
|
|
{
|
|
"entropy": 6.044516706466675,
|
|
"epoch": 2.1341530464337484,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004547237705900655,
|
|
"loss": 5.6557,
|
|
"mean_token_accuracy": 0.17962298542261124,
|
|
"num_tokens": 41766163.0,
|
|
"step": 21350
|
|
},
|
|
{
|
|
"entropy": 6.039214134216309,
|
|
"epoch": 2.1346528714949766,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00045470229657242176,
|
|
"loss": 5.6377,
|
|
"mean_token_accuracy": 0.17309304922819138,
|
|
"num_tokens": 41775600.0,
|
|
"step": 21355
|
|
},
|
|
{
|
|
"entropy": 6.0780627727508545,
|
|
"epoch": 2.1351526965562053,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00045468081803351447,
|
|
"loss": 5.8226,
|
|
"mean_token_accuracy": 0.15759820640087127,
|
|
"num_tokens": 41784535.0,
|
|
"step": 21360
|
|
},
|
|
{
|
|
"entropy": 6.097094392776489,
|
|
"epoch": 2.135652521617434,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004546593349738841,
|
|
"loss": 5.7192,
|
|
"mean_token_accuracy": 0.1675022155046463,
|
|
"num_tokens": 41794534.0,
|
|
"step": 21365
|
|
},
|
|
{
|
|
"entropy": 6.023589134216309,
|
|
"epoch": 2.1361523466786623,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.000454637847394071,
|
|
"loss": 5.6491,
|
|
"mean_token_accuracy": 0.17722269296646118,
|
|
"num_tokens": 41804155.0,
|
|
"step": 21370
|
|
},
|
|
{
|
|
"entropy": 6.004642486572266,
|
|
"epoch": 2.136652171739891,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00045461635529461597,
|
|
"loss": 5.6494,
|
|
"mean_token_accuracy": 0.17501810938119888,
|
|
"num_tokens": 41814813.0,
|
|
"step": 21375
|
|
},
|
|
{
|
|
"entropy": 6.041778421401977,
|
|
"epoch": 2.1371519968011197,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004545948586760596,
|
|
"loss": 5.668,
|
|
"mean_token_accuracy": 0.1744779422879219,
|
|
"num_tokens": 41824660.0,
|
|
"step": 21380
|
|
},
|
|
{
|
|
"entropy": 6.105130338668824,
|
|
"epoch": 2.1376518218623484,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004545733575389428,
|
|
"loss": 5.6617,
|
|
"mean_token_accuracy": 0.18492425084114075,
|
|
"num_tokens": 41834139.0,
|
|
"step": 21385
|
|
},
|
|
{
|
|
"entropy": 6.016358137130737,
|
|
"epoch": 2.1381516469235766,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004545518518838066,
|
|
"loss": 5.75,
|
|
"mean_token_accuracy": 0.1672527238726616,
|
|
"num_tokens": 41845183.0,
|
|
"step": 21390
|
|
},
|
|
{
|
|
"entropy": 5.982950162887573,
|
|
"epoch": 2.1386514719848053,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.000454530341711192,
|
|
"loss": 5.6561,
|
|
"mean_token_accuracy": 0.17340595424175262,
|
|
"num_tokens": 41854569.0,
|
|
"step": 21395
|
|
},
|
|
{
|
|
"entropy": 6.093788576126099,
|
|
"epoch": 2.139151297046034,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004545088270216401,
|
|
"loss": 5.6418,
|
|
"mean_token_accuracy": 0.1796325996518135,
|
|
"num_tokens": 41863469.0,
|
|
"step": 21400
|
|
},
|
|
{
|
|
"entropy": 6.085266733169556,
|
|
"epoch": 2.1396511221072623,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004544873078156924,
|
|
"loss": 5.7345,
|
|
"mean_token_accuracy": 0.17282312661409377,
|
|
"num_tokens": 41873172.0,
|
|
"step": 21405
|
|
},
|
|
{
|
|
"entropy": 6.001015901565552,
|
|
"epoch": 2.140150947168491,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00045446578409389016,
|
|
"loss": 5.6473,
|
|
"mean_token_accuracy": 0.17034633308649064,
|
|
"num_tokens": 41882276.0,
|
|
"step": 21410
|
|
},
|
|
{
|
|
"entropy": 6.065458917617798,
|
|
"epoch": 2.1406507722297197,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00045444425585677503,
|
|
"loss": 5.8051,
|
|
"mean_token_accuracy": 0.1652781695127487,
|
|
"num_tokens": 41893240.0,
|
|
"step": 21415
|
|
},
|
|
{
|
|
"entropy": 6.161846733093261,
|
|
"epoch": 2.1411505972909484,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004544227231048886,
|
|
"loss": 5.7109,
|
|
"mean_token_accuracy": 0.1721098780632019,
|
|
"num_tokens": 41902889.0,
|
|
"step": 21420
|
|
},
|
|
{
|
|
"entropy": 6.086296558380127,
|
|
"epoch": 2.1416504223521766,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004544011858387726,
|
|
"loss": 5.737,
|
|
"mean_token_accuracy": 0.16884352564811705,
|
|
"num_tokens": 41911887.0,
|
|
"step": 21425
|
|
},
|
|
{
|
|
"entropy": 5.983133268356323,
|
|
"epoch": 2.1421502474134053,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00045437964405896895,
|
|
"loss": 5.6236,
|
|
"mean_token_accuracy": 0.18292977064847946,
|
|
"num_tokens": 41921563.0,
|
|
"step": 21430
|
|
},
|
|
{
|
|
"entropy": 6.027721357345581,
|
|
"epoch": 2.142650072474634,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00045435809776601954,
|
|
"loss": 5.6339,
|
|
"mean_token_accuracy": 0.17524924725294114,
|
|
"num_tokens": 41930454.0,
|
|
"step": 21435
|
|
},
|
|
{
|
|
"entropy": 6.100055313110351,
|
|
"epoch": 2.1431498975358623,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004543365469604666,
|
|
"loss": 5.767,
|
|
"mean_token_accuracy": 0.16218314319849014,
|
|
"num_tokens": 41939289.0,
|
|
"step": 21440
|
|
},
|
|
{
|
|
"entropy": 6.004695987701416,
|
|
"epoch": 2.143649722597091,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004543149916428523,
|
|
"loss": 5.6604,
|
|
"mean_token_accuracy": 0.1730983465909958,
|
|
"num_tokens": 41949569.0,
|
|
"step": 21445
|
|
},
|
|
{
|
|
"entropy": 6.068342113494873,
|
|
"epoch": 2.1441495476583197,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004542934318137189,
|
|
"loss": 5.7237,
|
|
"mean_token_accuracy": 0.16991955786943436,
|
|
"num_tokens": 41960767.0,
|
|
"step": 21450
|
|
},
|
|
{
|
|
"entropy": 6.099776744842529,
|
|
"epoch": 2.1446493727195484,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004542718674736089,
|
|
"loss": 5.6954,
|
|
"mean_token_accuracy": 0.16931515485048293,
|
|
"num_tokens": 41969985.0,
|
|
"step": 21455
|
|
},
|
|
{
|
|
"entropy": 6.121584463119507,
|
|
"epoch": 2.1451491977807766,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004542502986230649,
|
|
"loss": 5.6832,
|
|
"mean_token_accuracy": 0.16683722138404847,
|
|
"num_tokens": 41980156.0,
|
|
"step": 21460
|
|
},
|
|
{
|
|
"entropy": 6.092706251144409,
|
|
"epoch": 2.1456490228420053,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004542287252626295,
|
|
"loss": 5.7803,
|
|
"mean_token_accuracy": 0.17042239159345626,
|
|
"num_tokens": 41990416.0,
|
|
"step": 21465
|
|
},
|
|
{
|
|
"entropy": 6.117132520675659,
|
|
"epoch": 2.146148847903234,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004542071473928455,
|
|
"loss": 5.7763,
|
|
"mean_token_accuracy": 0.16583269834518433,
|
|
"num_tokens": 42000065.0,
|
|
"step": 21470
|
|
},
|
|
{
|
|
"entropy": 6.129070281982422,
|
|
"epoch": 2.1466486729644623,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004541855650142557,
|
|
"loss": 5.6503,
|
|
"mean_token_accuracy": 0.17246291786432266,
|
|
"num_tokens": 42010683.0,
|
|
"step": 21475
|
|
},
|
|
{
|
|
"entropy": 6.055108737945557,
|
|
"epoch": 2.147148498025691,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00045416397812740323,
|
|
"loss": 5.7037,
|
|
"mean_token_accuracy": 0.16960131525993347,
|
|
"num_tokens": 42020191.0,
|
|
"step": 21480
|
|
},
|
|
{
|
|
"entropy": 6.048486137390137,
|
|
"epoch": 2.1476483230869197,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004541423867328312,
|
|
"loss": 5.7244,
|
|
"mean_token_accuracy": 0.16880512088537217,
|
|
"num_tokens": 42029875.0,
|
|
"step": 21485
|
|
},
|
|
{
|
|
"entropy": 6.0366312026977536,
|
|
"epoch": 2.148148148148148,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004541207908310829,
|
|
"loss": 5.6767,
|
|
"mean_token_accuracy": 0.18016607463359832,
|
|
"num_tokens": 42040265.0,
|
|
"step": 21490
|
|
},
|
|
{
|
|
"entropy": 6.027802801132202,
|
|
"epoch": 2.1486479732093766,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004540991904227015,
|
|
"loss": 5.5862,
|
|
"mean_token_accuracy": 0.18507321625947953,
|
|
"num_tokens": 42050370.0,
|
|
"step": 21495
|
|
},
|
|
{
|
|
"entropy": 6.0744054317474365,
|
|
"epoch": 2.1491477982706053,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00045407758550823055,
|
|
"loss": 5.7133,
|
|
"mean_token_accuracy": 0.17345928400754929,
|
|
"num_tokens": 42059865.0,
|
|
"step": 21500
|
|
},
|
|
{
|
|
"entropy": 6.036302137374878,
|
|
"epoch": 2.149647623331834,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.00045405597608821365,
|
|
"loss": 5.7093,
|
|
"mean_token_accuracy": 0.17578438818454742,
|
|
"num_tokens": 42071973.0,
|
|
"step": 21505
|
|
},
|
|
{
|
|
"entropy": 6.077007818222046,
|
|
"epoch": 2.1501474483930623,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004540343621631944,
|
|
"loss": 5.7179,
|
|
"mean_token_accuracy": 0.17094098329544066,
|
|
"num_tokens": 42082810.0,
|
|
"step": 21510
|
|
},
|
|
{
|
|
"entropy": 6.126628828048706,
|
|
"epoch": 2.150647273454291,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004540127437337167,
|
|
"loss": 5.6865,
|
|
"mean_token_accuracy": 0.17274952977895736,
|
|
"num_tokens": 42092644.0,
|
|
"step": 21515
|
|
},
|
|
{
|
|
"entropy": 5.9760274410247805,
|
|
"epoch": 2.1511470985155197,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004539911208003245,
|
|
"loss": 5.6598,
|
|
"mean_token_accuracy": 0.1770198091864586,
|
|
"num_tokens": 42103393.0,
|
|
"step": 21520
|
|
},
|
|
{
|
|
"entropy": 5.947650814056397,
|
|
"epoch": 2.151646923576748,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004539694933635617,
|
|
"loss": 5.6298,
|
|
"mean_token_accuracy": 0.16835854947566986,
|
|
"num_tokens": 42113759.0,
|
|
"step": 21525
|
|
},
|
|
{
|
|
"entropy": 6.046452856063842,
|
|
"epoch": 2.1521467486379766,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00045394786142397253,
|
|
"loss": 5.7199,
|
|
"mean_token_accuracy": 0.16721190363168717,
|
|
"num_tokens": 42124092.0,
|
|
"step": 21530
|
|
},
|
|
{
|
|
"entropy": 5.97120418548584,
|
|
"epoch": 2.1526465736992053,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004539262249821012,
|
|
"loss": 5.5491,
|
|
"mean_token_accuracy": 0.18015631884336472,
|
|
"num_tokens": 42132750.0,
|
|
"step": 21535
|
|
},
|
|
{
|
|
"entropy": 6.041675662994384,
|
|
"epoch": 2.153146398760434,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00045390458403849203,
|
|
"loss": 5.7058,
|
|
"mean_token_accuracy": 0.17255569547414779,
|
|
"num_tokens": 42141766.0,
|
|
"step": 21540
|
|
},
|
|
{
|
|
"entropy": 6.123242902755737,
|
|
"epoch": 2.1536462238216623,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004538829385936896,
|
|
"loss": 5.8249,
|
|
"mean_token_accuracy": 0.16010879427194596,
|
|
"num_tokens": 42152057.0,
|
|
"step": 21545
|
|
},
|
|
{
|
|
"entropy": 6.045621776580811,
|
|
"epoch": 2.154146048882891,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004538612886482385,
|
|
"loss": 5.7152,
|
|
"mean_token_accuracy": 0.1721815809607506,
|
|
"num_tokens": 42162414.0,
|
|
"step": 21550
|
|
},
|
|
{
|
|
"entropy": 6.068025875091553,
|
|
"epoch": 2.1546458739441197,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004538396342026834,
|
|
"loss": 5.6755,
|
|
"mean_token_accuracy": 0.1701608270406723,
|
|
"num_tokens": 42172217.0,
|
|
"step": 21555
|
|
},
|
|
{
|
|
"entropy": 6.056132459640503,
|
|
"epoch": 2.155145699005348,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004538179752575691,
|
|
"loss": 5.7036,
|
|
"mean_token_accuracy": 0.16893795132637024,
|
|
"num_tokens": 42182267.0,
|
|
"step": 21560
|
|
},
|
|
{
|
|
"entropy": 6.040149927139282,
|
|
"epoch": 2.1556455240665766,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004537963118134406,
|
|
"loss": 5.7735,
|
|
"mean_token_accuracy": 0.1747739404439926,
|
|
"num_tokens": 42192279.0,
|
|
"step": 21565
|
|
},
|
|
{
|
|
"entropy": 6.196079730987549,
|
|
"epoch": 2.1561453491278053,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00045377464387084287,
|
|
"loss": 5.8357,
|
|
"mean_token_accuracy": 0.1622178390622139,
|
|
"num_tokens": 42202209.0,
|
|
"step": 21570
|
|
},
|
|
{
|
|
"entropy": 6.14599118232727,
|
|
"epoch": 2.156645174189034,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004537529714303211,
|
|
"loss": 5.8039,
|
|
"mean_token_accuracy": 0.16185471042990685,
|
|
"num_tokens": 42212378.0,
|
|
"step": 21575
|
|
},
|
|
{
|
|
"entropy": 6.0584348201751705,
|
|
"epoch": 2.1571449992502623,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00045373129449242054,
|
|
"loss": 5.7116,
|
|
"mean_token_accuracy": 0.17030760943889617,
|
|
"num_tokens": 42222725.0,
|
|
"step": 21580
|
|
},
|
|
{
|
|
"entropy": 6.027674913406372,
|
|
"epoch": 2.157644824311491,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004537096130576866,
|
|
"loss": 5.7242,
|
|
"mean_token_accuracy": 0.17197906821966172,
|
|
"num_tokens": 42233510.0,
|
|
"step": 21585
|
|
},
|
|
{
|
|
"entropy": 6.116976737976074,
|
|
"epoch": 2.1581446493727197,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00045368792712666486,
|
|
"loss": 5.7758,
|
|
"mean_token_accuracy": 0.17189740836620332,
|
|
"num_tokens": 42242589.0,
|
|
"step": 21590
|
|
},
|
|
{
|
|
"entropy": 6.104128646850586,
|
|
"epoch": 2.158644474433948,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004536662366999008,
|
|
"loss": 5.6425,
|
|
"mean_token_accuracy": 0.16967471539974213,
|
|
"num_tokens": 42251663.0,
|
|
"step": 21595
|
|
},
|
|
{
|
|
"entropy": 6.039616537094116,
|
|
"epoch": 2.1591442994951766,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004536445417779402,
|
|
"loss": 5.6211,
|
|
"mean_token_accuracy": 0.17749060690402985,
|
|
"num_tokens": 42260507.0,
|
|
"step": 21600
|
|
},
|
|
{
|
|
"entropy": 6.036412048339844,
|
|
"epoch": 2.1596441245564053,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00045362284236132895,
|
|
"loss": 5.7126,
|
|
"mean_token_accuracy": 0.17100178450345993,
|
|
"num_tokens": 42270967.0,
|
|
"step": 21605
|
|
},
|
|
{
|
|
"entropy": 6.009857511520385,
|
|
"epoch": 2.160143949617634,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00045360113845061283,
|
|
"loss": 5.6605,
|
|
"mean_token_accuracy": 0.17458752691745758,
|
|
"num_tokens": 42280418.0,
|
|
"step": 21610
|
|
},
|
|
{
|
|
"entropy": 6.042594003677368,
|
|
"epoch": 2.1606437746788623,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00045357943004633813,
|
|
"loss": 5.7066,
|
|
"mean_token_accuracy": 0.16786503195762634,
|
|
"num_tokens": 42290371.0,
|
|
"step": 21615
|
|
},
|
|
{
|
|
"entropy": 6.020025062561035,
|
|
"epoch": 2.161143599740091,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00045355771714905086,
|
|
"loss": 5.6609,
|
|
"mean_token_accuracy": 0.1783612012863159,
|
|
"num_tokens": 42300259.0,
|
|
"step": 21620
|
|
},
|
|
{
|
|
"entropy": 6.072748231887817,
|
|
"epoch": 2.1616434248013197,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00045353599975929746,
|
|
"loss": 5.6989,
|
|
"mean_token_accuracy": 0.1744714632630348,
|
|
"num_tokens": 42309817.0,
|
|
"step": 21625
|
|
},
|
|
{
|
|
"entropy": 6.112416839599609,
|
|
"epoch": 2.162143249862548,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004535142778776241,
|
|
"loss": 5.7692,
|
|
"mean_token_accuracy": 0.17227453589439393,
|
|
"num_tokens": 42319231.0,
|
|
"step": 21630
|
|
},
|
|
{
|
|
"entropy": 6.017733955383301,
|
|
"epoch": 2.1626430749237766,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004534925515045776,
|
|
"loss": 5.6577,
|
|
"mean_token_accuracy": 0.17567150741815568,
|
|
"num_tokens": 42328943.0,
|
|
"step": 21635
|
|
},
|
|
{
|
|
"entropy": 6.051760959625244,
|
|
"epoch": 2.1631428999850053,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00045347082064070435,
|
|
"loss": 5.6466,
|
|
"mean_token_accuracy": 0.17246305495500563,
|
|
"num_tokens": 42337938.0,
|
|
"step": 21640
|
|
},
|
|
{
|
|
"entropy": 6.057065629959107,
|
|
"epoch": 2.163642725046234,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004534490852865512,
|
|
"loss": 5.7722,
|
|
"mean_token_accuracy": 0.1701118066906929,
|
|
"num_tokens": 42348906.0,
|
|
"step": 21645
|
|
},
|
|
{
|
|
"entropy": 6.093236064910888,
|
|
"epoch": 2.1641425501074623,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00045342734544266493,
|
|
"loss": 5.6879,
|
|
"mean_token_accuracy": 0.17302015274763108,
|
|
"num_tokens": 42359026.0,
|
|
"step": 21650
|
|
},
|
|
{
|
|
"entropy": 6.104183292388916,
|
|
"epoch": 2.164642375168691,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004534056011095926,
|
|
"loss": 5.785,
|
|
"mean_token_accuracy": 0.1635444536805153,
|
|
"num_tokens": 42368697.0,
|
|
"step": 21655
|
|
},
|
|
{
|
|
"entropy": 6.036143493652344,
|
|
"epoch": 2.1651422002299197,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00045338385228788124,
|
|
"loss": 5.6361,
|
|
"mean_token_accuracy": 0.17682795971632004,
|
|
"num_tokens": 42377961.0,
|
|
"step": 21660
|
|
},
|
|
{
|
|
"entropy": 6.046940469741822,
|
|
"epoch": 2.165642025291148,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00045336209897807813,
|
|
"loss": 5.684,
|
|
"mean_token_accuracy": 0.17093176245689393,
|
|
"num_tokens": 42388219.0,
|
|
"step": 21665
|
|
},
|
|
{
|
|
"entropy": 6.084421300888062,
|
|
"epoch": 2.1661418503523766,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00045334034118073047,
|
|
"loss": 5.7337,
|
|
"mean_token_accuracy": 0.1742533951997757,
|
|
"num_tokens": 42397626.0,
|
|
"step": 21670
|
|
},
|
|
{
|
|
"entropy": 6.165010213851929,
|
|
"epoch": 2.1666416754136053,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00045331857889638566,
|
|
"loss": 5.738,
|
|
"mean_token_accuracy": 0.16476799547672272,
|
|
"num_tokens": 42406806.0,
|
|
"step": 21675
|
|
},
|
|
{
|
|
"entropy": 5.945415306091308,
|
|
"epoch": 2.167141500474834,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004532968121255914,
|
|
"loss": 5.5404,
|
|
"mean_token_accuracy": 0.18813517540693284,
|
|
"num_tokens": 42416544.0,
|
|
"step": 21680
|
|
},
|
|
{
|
|
"entropy": 5.994277286529541,
|
|
"epoch": 2.1676413255360623,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.00045327504086889513,
|
|
"loss": 5.6808,
|
|
"mean_token_accuracy": 0.17097365856170654,
|
|
"num_tokens": 42426447.0,
|
|
"step": 21685
|
|
},
|
|
{
|
|
"entropy": 6.093823194503784,
|
|
"epoch": 2.168141150597291,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00045325326512684466,
|
|
"loss": 5.71,
|
|
"mean_token_accuracy": 0.16786229163408278,
|
|
"num_tokens": 42435411.0,
|
|
"step": 21690
|
|
},
|
|
{
|
|
"entropy": 6.098823118209839,
|
|
"epoch": 2.1686409756585197,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00045323148489998807,
|
|
"loss": 5.7348,
|
|
"mean_token_accuracy": 0.16074257344007492,
|
|
"num_tokens": 42445280.0,
|
|
"step": 21695
|
|
},
|
|
{
|
|
"entropy": 6.043877458572387,
|
|
"epoch": 2.169140800719748,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.000453209700188873,
|
|
"loss": 5.6501,
|
|
"mean_token_accuracy": 0.17573040276765822,
|
|
"num_tokens": 42455182.0,
|
|
"step": 21700
|
|
},
|
|
{
|
|
"entropy": 6.07042555809021,
|
|
"epoch": 2.1696406257809766,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00045318791099404785,
|
|
"loss": 5.773,
|
|
"mean_token_accuracy": 0.16733378618955613,
|
|
"num_tokens": 42464492.0,
|
|
"step": 21705
|
|
},
|
|
{
|
|
"entropy": 6.107957267761231,
|
|
"epoch": 2.1701404508422053,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00045316611731606075,
|
|
"loss": 5.7839,
|
|
"mean_token_accuracy": 0.16839563846588135,
|
|
"num_tokens": 42475461.0,
|
|
"step": 21710
|
|
},
|
|
{
|
|
"entropy": 6.100037908554077,
|
|
"epoch": 2.170640275903434,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004531443191554598,
|
|
"loss": 5.7165,
|
|
"mean_token_accuracy": 0.17387815713882446,
|
|
"num_tokens": 42484383.0,
|
|
"step": 21715
|
|
},
|
|
{
|
|
"entropy": 6.065162992477417,
|
|
"epoch": 2.1711401009646623,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004531225165127938,
|
|
"loss": 5.7419,
|
|
"mean_token_accuracy": 0.17556357383728027,
|
|
"num_tokens": 42494268.0,
|
|
"step": 21720
|
|
},
|
|
{
|
|
"entropy": 6.09242811203003,
|
|
"epoch": 2.171639926025891,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00045310070938861107,
|
|
"loss": 5.735,
|
|
"mean_token_accuracy": 0.1678965672850609,
|
|
"num_tokens": 42503035.0,
|
|
"step": 21725
|
|
},
|
|
{
|
|
"entropy": 5.981829881668091,
|
|
"epoch": 2.1721397510871197,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00045307889778346035,
|
|
"loss": 5.6053,
|
|
"mean_token_accuracy": 0.18369434624910355,
|
|
"num_tokens": 42512205.0,
|
|
"step": 21730
|
|
},
|
|
{
|
|
"entropy": 6.116300010681153,
|
|
"epoch": 2.172639576148348,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004530570816978903,
|
|
"loss": 5.7685,
|
|
"mean_token_accuracy": 0.16400405764579773,
|
|
"num_tokens": 42523153.0,
|
|
"step": 21735
|
|
},
|
|
{
|
|
"entropy": 6.153788280487061,
|
|
"epoch": 2.1731394012095766,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00045303526113245,
|
|
"loss": 5.7575,
|
|
"mean_token_accuracy": 0.16937157660722732,
|
|
"num_tokens": 42532457.0,
|
|
"step": 21740
|
|
},
|
|
{
|
|
"entropy": 6.050369739532471,
|
|
"epoch": 2.1736392262708053,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004530134360876882,
|
|
"loss": 5.6832,
|
|
"mean_token_accuracy": 0.1751691445708275,
|
|
"num_tokens": 42542179.0,
|
|
"step": 21745
|
|
},
|
|
{
|
|
"entropy": 6.036983633041382,
|
|
"epoch": 2.174139051332034,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004529916065641543,
|
|
"loss": 5.6754,
|
|
"mean_token_accuracy": 0.17341640442609788,
|
|
"num_tokens": 42552441.0,
|
|
"step": 21750
|
|
},
|
|
{
|
|
"entropy": 6.03537883758545,
|
|
"epoch": 2.1746388763932623,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004529697725623973,
|
|
"loss": 5.5852,
|
|
"mean_token_accuracy": 0.17875811606645584,
|
|
"num_tokens": 42562600.0,
|
|
"step": 21755
|
|
},
|
|
{
|
|
"entropy": 6.1070770740509035,
|
|
"epoch": 2.175138701454491,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00045294793408296656,
|
|
"loss": 5.6761,
|
|
"mean_token_accuracy": 0.17265091687440873,
|
|
"num_tokens": 42571790.0,
|
|
"step": 21760
|
|
},
|
|
{
|
|
"entropy": 6.079111385345459,
|
|
"epoch": 2.1756385265157197,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004529260911264117,
|
|
"loss": 5.6842,
|
|
"mean_token_accuracy": 0.18278567790985106,
|
|
"num_tokens": 42581816.0,
|
|
"step": 21765
|
|
},
|
|
{
|
|
"entropy": 6.0499114990234375,
|
|
"epoch": 2.176138351576948,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004529042436932822,
|
|
"loss": 5.6759,
|
|
"mean_token_accuracy": 0.17517668455839158,
|
|
"num_tokens": 42591501.0,
|
|
"step": 21770
|
|
},
|
|
{
|
|
"entropy": 6.108690071105957,
|
|
"epoch": 2.1766381766381766,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00045288239178412754,
|
|
"loss": 5.6341,
|
|
"mean_token_accuracy": 0.1777725711464882,
|
|
"num_tokens": 42601237.0,
|
|
"step": 21775
|
|
},
|
|
{
|
|
"entropy": 6.014836072921753,
|
|
"epoch": 2.1771380016994053,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004528605353994978,
|
|
"loss": 5.662,
|
|
"mean_token_accuracy": 0.1758300244808197,
|
|
"num_tokens": 42611239.0,
|
|
"step": 21780
|
|
},
|
|
{
|
|
"entropy": 6.089399433135986,
|
|
"epoch": 2.177637826760634,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004528386745399428,
|
|
"loss": 5.6891,
|
|
"mean_token_accuracy": 0.18117855340242386,
|
|
"num_tokens": 42621153.0,
|
|
"step": 21785
|
|
},
|
|
{
|
|
"entropy": 6.1035804271698,
|
|
"epoch": 2.1781376518218623,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00045281680920601235,
|
|
"loss": 5.7005,
|
|
"mean_token_accuracy": 0.1754380375146866,
|
|
"num_tokens": 42631508.0,
|
|
"step": 21790
|
|
},
|
|
{
|
|
"entropy": 6.086840343475342,
|
|
"epoch": 2.178637476883091,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004527949393982569,
|
|
"loss": 5.7094,
|
|
"mean_token_accuracy": 0.166280996799469,
|
|
"num_tokens": 42641401.0,
|
|
"step": 21795
|
|
},
|
|
{
|
|
"entropy": 6.122628164291382,
|
|
"epoch": 2.1791373019443196,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00045277306511722645,
|
|
"loss": 5.7232,
|
|
"mean_token_accuracy": 0.16528749614953994,
|
|
"num_tokens": 42651631.0,
|
|
"step": 21800
|
|
},
|
|
{
|
|
"entropy": 6.082775735855103,
|
|
"epoch": 2.179637127005548,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004527511863634714,
|
|
"loss": 5.6578,
|
|
"mean_token_accuracy": 0.17593708336353303,
|
|
"num_tokens": 42661506.0,
|
|
"step": 21805
|
|
},
|
|
{
|
|
"entropy": 6.03814206123352,
|
|
"epoch": 2.1801369520667766,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004527293031375422,
|
|
"loss": 5.6506,
|
|
"mean_token_accuracy": 0.17550643980503083,
|
|
"num_tokens": 42671403.0,
|
|
"step": 21810
|
|
},
|
|
{
|
|
"entropy": 6.089567708969116,
|
|
"epoch": 2.1806367771280053,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004527074154399896,
|
|
"loss": 5.8104,
|
|
"mean_token_accuracy": 0.17373067438602446,
|
|
"num_tokens": 42681360.0,
|
|
"step": 21815
|
|
},
|
|
{
|
|
"entropy": 6.101115417480469,
|
|
"epoch": 2.181136602189234,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00045268552327136415,
|
|
"loss": 5.6691,
|
|
"mean_token_accuracy": 0.174757918715477,
|
|
"num_tokens": 42691381.0,
|
|
"step": 21820
|
|
},
|
|
{
|
|
"entropy": 6.0949294090271,
|
|
"epoch": 2.1816364272504623,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00045266362663221656,
|
|
"loss": 5.7347,
|
|
"mean_token_accuracy": 0.17581699043512344,
|
|
"num_tokens": 42701857.0,
|
|
"step": 21825
|
|
},
|
|
{
|
|
"entropy": 6.1496683120727536,
|
|
"epoch": 2.182136252311691,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00045264172552309786,
|
|
"loss": 5.7511,
|
|
"mean_token_accuracy": 0.16550771296024322,
|
|
"num_tokens": 42711526.0,
|
|
"step": 21830
|
|
},
|
|
{
|
|
"entropy": 6.080040359497071,
|
|
"epoch": 2.1826360773729196,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004526198199445591,
|
|
"loss": 5.6844,
|
|
"mean_token_accuracy": 0.17005229145288467,
|
|
"num_tokens": 42721552.0,
|
|
"step": 21835
|
|
},
|
|
{
|
|
"entropy": 6.035427093505859,
|
|
"epoch": 2.183135902434148,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00045259790989715133,
|
|
"loss": 5.6629,
|
|
"mean_token_accuracy": 0.17736527621746062,
|
|
"num_tokens": 42732161.0,
|
|
"step": 21840
|
|
},
|
|
{
|
|
"entropy": 6.046205854415893,
|
|
"epoch": 2.1836357274953766,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00045257599538142587,
|
|
"loss": 5.7369,
|
|
"mean_token_accuracy": 0.17128790467977523,
|
|
"num_tokens": 42741140.0,
|
|
"step": 21845
|
|
},
|
|
{
|
|
"entropy": 6.0618761539459225,
|
|
"epoch": 2.1841355525566053,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00045255407639793407,
|
|
"loss": 5.6622,
|
|
"mean_token_accuracy": 0.17412643283605575,
|
|
"num_tokens": 42750000.0,
|
|
"step": 21850
|
|
},
|
|
{
|
|
"entropy": 6.094034433364868,
|
|
"epoch": 2.1846353776178336,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004525321529472274,
|
|
"loss": 5.6676,
|
|
"mean_token_accuracy": 0.1686531975865364,
|
|
"num_tokens": 42760430.0,
|
|
"step": 21855
|
|
},
|
|
{
|
|
"entropy": 6.091526079177856,
|
|
"epoch": 2.1851352026790622,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00045251022502985737,
|
|
"loss": 5.7042,
|
|
"mean_token_accuracy": 0.17025245130062103,
|
|
"num_tokens": 42770904.0,
|
|
"step": 21860
|
|
},
|
|
{
|
|
"entropy": 6.1004563331604,
|
|
"epoch": 2.185635027740291,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004524882926463758,
|
|
"loss": 5.7416,
|
|
"mean_token_accuracy": 0.16467310339212418,
|
|
"num_tokens": 42781297.0,
|
|
"step": 21865
|
|
},
|
|
{
|
|
"entropy": 6.046659708023071,
|
|
"epoch": 2.1861348528015196,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004524663557973345,
|
|
"loss": 5.7318,
|
|
"mean_token_accuracy": 0.17264027148485184,
|
|
"num_tokens": 42790781.0,
|
|
"step": 21870
|
|
},
|
|
{
|
|
"entropy": 6.056605625152588,
|
|
"epoch": 2.186634677862748,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00045244441448328535,
|
|
"loss": 5.7263,
|
|
"mean_token_accuracy": 0.1676354631781578,
|
|
"num_tokens": 42800387.0,
|
|
"step": 21875
|
|
},
|
|
{
|
|
"entropy": 6.164255571365357,
|
|
"epoch": 2.1871345029239766,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00045242246870478035,
|
|
"loss": 5.7701,
|
|
"mean_token_accuracy": 0.16379728317260742,
|
|
"num_tokens": 42809204.0,
|
|
"step": 21880
|
|
},
|
|
{
|
|
"entropy": 6.131562328338623,
|
|
"epoch": 2.1876343279852053,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004524005184623717,
|
|
"loss": 5.7749,
|
|
"mean_token_accuracy": 0.17022548615932465,
|
|
"num_tokens": 42819431.0,
|
|
"step": 21885
|
|
},
|
|
{
|
|
"entropy": 5.970657253265381,
|
|
"epoch": 2.1881341530464335,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004523785637566117,
|
|
"loss": 5.579,
|
|
"mean_token_accuracy": 0.18089306205511094,
|
|
"num_tokens": 42830072.0,
|
|
"step": 21890
|
|
},
|
|
{
|
|
"entropy": 5.999266052246094,
|
|
"epoch": 2.1886339781076622,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004523566045880527,
|
|
"loss": 5.6893,
|
|
"mean_token_accuracy": 0.1720039203763008,
|
|
"num_tokens": 42840201.0,
|
|
"step": 21895
|
|
},
|
|
{
|
|
"entropy": 6.027826929092408,
|
|
"epoch": 2.189133803168891,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.00045233464095724706,
|
|
"loss": 5.6476,
|
|
"mean_token_accuracy": 0.1743355706334114,
|
|
"num_tokens": 42849695.0,
|
|
"step": 21900
|
|
},
|
|
{
|
|
"entropy": 6.167458486557007,
|
|
"epoch": 2.1896336282301196,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00045231267286474755,
|
|
"loss": 5.7851,
|
|
"mean_token_accuracy": 0.17084471136331558,
|
|
"num_tokens": 42858674.0,
|
|
"step": 21905
|
|
},
|
|
{
|
|
"entropy": 6.124717903137207,
|
|
"epoch": 2.190133453291348,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004522907003111068,
|
|
"loss": 5.7015,
|
|
"mean_token_accuracy": 0.1769531898200512,
|
|
"num_tokens": 42869879.0,
|
|
"step": 21910
|
|
},
|
|
{
|
|
"entropy": 6.086302614212036,
|
|
"epoch": 2.1906332783525766,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004522687232968776,
|
|
"loss": 5.7129,
|
|
"mean_token_accuracy": 0.16798786520957948,
|
|
"num_tokens": 42879652.0,
|
|
"step": 21915
|
|
},
|
|
{
|
|
"entropy": 6.044944334030151,
|
|
"epoch": 2.1911331034138053,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00045224674182261306,
|
|
"loss": 5.6763,
|
|
"mean_token_accuracy": 0.17941535711288453,
|
|
"num_tokens": 42889081.0,
|
|
"step": 21920
|
|
},
|
|
{
|
|
"entropy": 6.105813980102539,
|
|
"epoch": 2.1916329284750335,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00045222475588886597,
|
|
"loss": 5.6895,
|
|
"mean_token_accuracy": 0.17403754889965056,
|
|
"num_tokens": 42899621.0,
|
|
"step": 21925
|
|
},
|
|
{
|
|
"entropy": 6.114725589752197,
|
|
"epoch": 2.1921327535362622,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00045220276549618973,
|
|
"loss": 5.7858,
|
|
"mean_token_accuracy": 0.17173759192228316,
|
|
"num_tokens": 42910722.0,
|
|
"step": 21930
|
|
},
|
|
{
|
|
"entropy": 6.150332736968994,
|
|
"epoch": 2.192632578597491,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00045218077064513744,
|
|
"loss": 5.7775,
|
|
"mean_token_accuracy": 0.17002077847719194,
|
|
"num_tokens": 42920788.0,
|
|
"step": 21935
|
|
},
|
|
{
|
|
"entropy": 6.060717296600342,
|
|
"epoch": 2.1931324036587196,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004521587713362626,
|
|
"loss": 5.7201,
|
|
"mean_token_accuracy": 0.17568450570106506,
|
|
"num_tokens": 42930183.0,
|
|
"step": 21940
|
|
},
|
|
{
|
|
"entropy": 6.056248950958252,
|
|
"epoch": 2.193632228719948,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004521367675701187,
|
|
"loss": 5.6704,
|
|
"mean_token_accuracy": 0.1770023822784424,
|
|
"num_tokens": 42939886.0,
|
|
"step": 21945
|
|
},
|
|
{
|
|
"entropy": 6.14858865737915,
|
|
"epoch": 2.1941320537811766,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004521147593472592,
|
|
"loss": 5.7141,
|
|
"mean_token_accuracy": 0.1699317365884781,
|
|
"num_tokens": 42948756.0,
|
|
"step": 21950
|
|
},
|
|
{
|
|
"entropy": 6.053235006332398,
|
|
"epoch": 2.1946318788424053,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00045209274666823795,
|
|
"loss": 5.7451,
|
|
"mean_token_accuracy": 0.17296187877655028,
|
|
"num_tokens": 42957540.0,
|
|
"step": 21955
|
|
},
|
|
{
|
|
"entropy": 6.095971536636353,
|
|
"epoch": 2.1951317039036335,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004520707295336088,
|
|
"loss": 5.7528,
|
|
"mean_token_accuracy": 0.1711742699146271,
|
|
"num_tokens": 42967628.0,
|
|
"step": 21960
|
|
},
|
|
{
|
|
"entropy": 6.133524656295776,
|
|
"epoch": 2.1956315289648622,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00045204870794392574,
|
|
"loss": 5.7447,
|
|
"mean_token_accuracy": 0.16891617327928543,
|
|
"num_tokens": 42975850.0,
|
|
"step": 21965
|
|
},
|
|
{
|
|
"entropy": 6.080046272277832,
|
|
"epoch": 2.196131354026091,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00045202668189974263,
|
|
"loss": 5.7859,
|
|
"mean_token_accuracy": 0.1680530607700348,
|
|
"num_tokens": 42986640.0,
|
|
"step": 21970
|
|
},
|
|
{
|
|
"entropy": 6.073560380935669,
|
|
"epoch": 2.1966311790873196,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004520046514016138,
|
|
"loss": 5.5886,
|
|
"mean_token_accuracy": 0.1813989534974098,
|
|
"num_tokens": 42995876.0,
|
|
"step": 21975
|
|
},
|
|
{
|
|
"entropy": 6.044579696655274,
|
|
"epoch": 2.197131004148548,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00045198261645009347,
|
|
"loss": 5.6655,
|
|
"mean_token_accuracy": 0.1735708937048912,
|
|
"num_tokens": 43005843.0,
|
|
"step": 21980
|
|
},
|
|
{
|
|
"entropy": 6.081101751327514,
|
|
"epoch": 2.1976308292097766,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.000451960577045736,
|
|
"loss": 5.731,
|
|
"mean_token_accuracy": 0.16621703952550887,
|
|
"num_tokens": 43015866.0,
|
|
"step": 21985
|
|
},
|
|
{
|
|
"entropy": 6.054759836196899,
|
|
"epoch": 2.1981306542710053,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.000451938533189096,
|
|
"loss": 5.7131,
|
|
"mean_token_accuracy": 0.16945298463106157,
|
|
"num_tokens": 43025669.0,
|
|
"step": 21990
|
|
},
|
|
{
|
|
"entropy": 6.113602209091186,
|
|
"epoch": 2.1986304793322335,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004519164848807281,
|
|
"loss": 5.7529,
|
|
"mean_token_accuracy": 0.1707417368888855,
|
|
"num_tokens": 43036120.0,
|
|
"step": 21995
|
|
},
|
|
{
|
|
"entropy": 6.150713872909546,
|
|
"epoch": 2.1991303043934622,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00045189443212118686,
|
|
"loss": 5.7886,
|
|
"mean_token_accuracy": 0.16887526959180832,
|
|
"num_tokens": 43045799.0,
|
|
"step": 22000
|
|
},
|
|
{
|
|
"entropy": 6.04130744934082,
|
|
"epoch": 2.199630129454691,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00045187237491102727,
|
|
"loss": 5.651,
|
|
"mean_token_accuracy": 0.17854729145765305,
|
|
"num_tokens": 43055341.0,
|
|
"step": 22005
|
|
},
|
|
{
|
|
"entropy": 6.075776195526123,
|
|
"epoch": 2.200129954515919,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.00045185031325080426,
|
|
"loss": 5.7604,
|
|
"mean_token_accuracy": 0.17157328575849534,
|
|
"num_tokens": 43064899.0,
|
|
"step": 22010
|
|
},
|
|
{
|
|
"entropy": 6.050348281860352,
|
|
"epoch": 2.200629779577148,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00045182824714107284,
|
|
"loss": 5.6364,
|
|
"mean_token_accuracy": 0.17845782041549682,
|
|
"num_tokens": 43074789.0,
|
|
"step": 22015
|
|
},
|
|
{
|
|
"entropy": 6.168544578552246,
|
|
"epoch": 2.2011296046383766,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00045180617658238827,
|
|
"loss": 5.7481,
|
|
"mean_token_accuracy": 0.1722235381603241,
|
|
"num_tokens": 43084107.0,
|
|
"step": 22020
|
|
},
|
|
{
|
|
"entropy": 6.116107082366943,
|
|
"epoch": 2.2016294296996053,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004517841015753057,
|
|
"loss": 5.6705,
|
|
"mean_token_accuracy": 0.17389950305223464,
|
|
"num_tokens": 43093120.0,
|
|
"step": 22025
|
|
},
|
|
{
|
|
"entropy": 6.04542555809021,
|
|
"epoch": 2.2021292547608335,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004517620221203807,
|
|
"loss": 5.7393,
|
|
"mean_token_accuracy": 0.1685160666704178,
|
|
"num_tokens": 43103251.0,
|
|
"step": 22030
|
|
},
|
|
{
|
|
"entropy": 6.112654304504394,
|
|
"epoch": 2.2026290798220622,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00045173993821816873,
|
|
"loss": 5.7089,
|
|
"mean_token_accuracy": 0.1671309217810631,
|
|
"num_tokens": 43113162.0,
|
|
"step": 22035
|
|
},
|
|
{
|
|
"entropy": 6.107520675659179,
|
|
"epoch": 2.203128904883291,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004517178498692253,
|
|
"loss": 5.7224,
|
|
"mean_token_accuracy": 0.17434252947568893,
|
|
"num_tokens": 43122170.0,
|
|
"step": 22040
|
|
},
|
|
{
|
|
"entropy": 6.144588661193848,
|
|
"epoch": 2.203628729944519,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00045169575707410637,
|
|
"loss": 5.7262,
|
|
"mean_token_accuracy": 0.16727375835180283,
|
|
"num_tokens": 43132271.0,
|
|
"step": 22045
|
|
},
|
|
{
|
|
"entropy": 6.093336486816407,
|
|
"epoch": 2.204128555005748,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00045167365983336756,
|
|
"loss": 5.6523,
|
|
"mean_token_accuracy": 0.17635588943958283,
|
|
"num_tokens": 43141593.0,
|
|
"step": 22050
|
|
},
|
|
{
|
|
"entropy": 6.023672485351563,
|
|
"epoch": 2.2046283800669766,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00045165155814756497,
|
|
"loss": 5.6891,
|
|
"mean_token_accuracy": 0.17123606353998183,
|
|
"num_tokens": 43150659.0,
|
|
"step": 22055
|
|
},
|
|
{
|
|
"entropy": 6.067949724197388,
|
|
"epoch": 2.2051282051282053,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00045162945201725457,
|
|
"loss": 5.7328,
|
|
"mean_token_accuracy": 0.17505012899637223,
|
|
"num_tokens": 43160575.0,
|
|
"step": 22060
|
|
},
|
|
{
|
|
"entropy": 6.15854320526123,
|
|
"epoch": 2.2056280301894335,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004516073414429927,
|
|
"loss": 5.7054,
|
|
"mean_token_accuracy": 0.16997485905885695,
|
|
"num_tokens": 43169703.0,
|
|
"step": 22065
|
|
},
|
|
{
|
|
"entropy": 6.2100423812866214,
|
|
"epoch": 2.2061278552506622,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004515852264253356,
|
|
"loss": 5.8136,
|
|
"mean_token_accuracy": 0.16357283145189286,
|
|
"num_tokens": 43180685.0,
|
|
"step": 22070
|
|
},
|
|
{
|
|
"entropy": 6.008137321472168,
|
|
"epoch": 2.206627680311891,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00045156310696483953,
|
|
"loss": 5.6173,
|
|
"mean_token_accuracy": 0.1802598476409912,
|
|
"num_tokens": 43190398.0,
|
|
"step": 22075
|
|
},
|
|
{
|
|
"entropy": 6.112729835510254,
|
|
"epoch": 2.207127505373119,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004515409830620612,
|
|
"loss": 5.8071,
|
|
"mean_token_accuracy": 0.16447489261627196,
|
|
"num_tokens": 43200867.0,
|
|
"step": 22080
|
|
},
|
|
{
|
|
"entropy": 6.1454020023345945,
|
|
"epoch": 2.207627330434348,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004515188547175571,
|
|
"loss": 5.7945,
|
|
"mean_token_accuracy": 0.16274551749229432,
|
|
"num_tokens": 43211236.0,
|
|
"step": 22085
|
|
},
|
|
{
|
|
"entropy": 6.163127517700195,
|
|
"epoch": 2.2081271554955766,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000451496721931884,
|
|
"loss": 5.8585,
|
|
"mean_token_accuracy": 0.1642795741558075,
|
|
"num_tokens": 43220713.0,
|
|
"step": 22090
|
|
},
|
|
{
|
|
"entropy": 6.091136169433594,
|
|
"epoch": 2.2086269805568053,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004514745847055989,
|
|
"loss": 5.7195,
|
|
"mean_token_accuracy": 0.17003757506608963,
|
|
"num_tokens": 43231258.0,
|
|
"step": 22095
|
|
},
|
|
{
|
|
"entropy": 6.098960924148559,
|
|
"epoch": 2.2091268056180335,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004514524430392586,
|
|
"loss": 5.6667,
|
|
"mean_token_accuracy": 0.1715839684009552,
|
|
"num_tokens": 43240523.0,
|
|
"step": 22100
|
|
},
|
|
{
|
|
"entropy": 6.065347623825073,
|
|
"epoch": 2.2096266306792622,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004514302969334202,
|
|
"loss": 5.8145,
|
|
"mean_token_accuracy": 0.16702722311019896,
|
|
"num_tokens": 43250044.0,
|
|
"step": 22105
|
|
},
|
|
{
|
|
"entropy": 6.10836877822876,
|
|
"epoch": 2.210126455740491,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00045140814638864105,
|
|
"loss": 5.7261,
|
|
"mean_token_accuracy": 0.1710817411541939,
|
|
"num_tokens": 43260393.0,
|
|
"step": 22110
|
|
},
|
|
{
|
|
"entropy": 6.074278259277344,
|
|
"epoch": 2.210626280801719,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004513859914054782,
|
|
"loss": 5.6541,
|
|
"mean_token_accuracy": 0.17921528816223145,
|
|
"num_tokens": 43270554.0,
|
|
"step": 22115
|
|
},
|
|
{
|
|
"entropy": 5.996972322463989,
|
|
"epoch": 2.211126105862948,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00045136383198448926,
|
|
"loss": 5.6014,
|
|
"mean_token_accuracy": 0.17406702786684036,
|
|
"num_tokens": 43280256.0,
|
|
"step": 22120
|
|
},
|
|
{
|
|
"entropy": 6.045521306991577,
|
|
"epoch": 2.2116259309241766,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004513416681262317,
|
|
"loss": 5.7388,
|
|
"mean_token_accuracy": 0.17443681210279466,
|
|
"num_tokens": 43289399.0,
|
|
"step": 22125
|
|
},
|
|
{
|
|
"entropy": 6.127220487594604,
|
|
"epoch": 2.2121257559854053,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004513194998312631,
|
|
"loss": 5.7594,
|
|
"mean_token_accuracy": 0.1687379226088524,
|
|
"num_tokens": 43299349.0,
|
|
"step": 22130
|
|
},
|
|
{
|
|
"entropy": 6.057160949707031,
|
|
"epoch": 2.2126255810466335,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004512973271001413,
|
|
"loss": 5.6957,
|
|
"mean_token_accuracy": 0.17812313586473466,
|
|
"num_tokens": 43309199.0,
|
|
"step": 22135
|
|
},
|
|
{
|
|
"entropy": 6.03382134437561,
|
|
"epoch": 2.2131254061078622,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00045127514993342413,
|
|
"loss": 5.7047,
|
|
"mean_token_accuracy": 0.1788108080625534,
|
|
"num_tokens": 43319637.0,
|
|
"step": 22140
|
|
},
|
|
{
|
|
"entropy": 6.026248836517334,
|
|
"epoch": 2.213625231169091,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004512529683316695,
|
|
"loss": 5.6693,
|
|
"mean_token_accuracy": 0.17255899608135222,
|
|
"num_tokens": 43329005.0,
|
|
"step": 22145
|
|
},
|
|
{
|
|
"entropy": 6.0027953624725345,
|
|
"epoch": 2.214125056230319,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00045123078229543557,
|
|
"loss": 5.5985,
|
|
"mean_token_accuracy": 0.1859506294131279,
|
|
"num_tokens": 43339299.0,
|
|
"step": 22150
|
|
},
|
|
{
|
|
"entropy": 6.040128755569458,
|
|
"epoch": 2.214624881291548,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004512085918252805,
|
|
"loss": 5.7326,
|
|
"mean_token_accuracy": 0.17156766802072526,
|
|
"num_tokens": 43350317.0,
|
|
"step": 22155
|
|
},
|
|
{
|
|
"entropy": 6.105335474014282,
|
|
"epoch": 2.2151247063527766,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004511863969217625,
|
|
"loss": 5.7131,
|
|
"mean_token_accuracy": 0.17465749084949495,
|
|
"num_tokens": 43360607.0,
|
|
"step": 22160
|
|
},
|
|
{
|
|
"entropy": 6.118352365493775,
|
|
"epoch": 2.2156245314140053,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00045116419758544024,
|
|
"loss": 5.7308,
|
|
"mean_token_accuracy": 0.16824308335781096,
|
|
"num_tokens": 43370622.0,
|
|
"step": 22165
|
|
},
|
|
{
|
|
"entropy": 6.037186527252198,
|
|
"epoch": 2.2161243564752335,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00045114199381687207,
|
|
"loss": 5.6858,
|
|
"mean_token_accuracy": 0.1755439192056656,
|
|
"num_tokens": 43379841.0,
|
|
"step": 22170
|
|
},
|
|
{
|
|
"entropy": 5.979604959487915,
|
|
"epoch": 2.2166241815364622,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004511197856166166,
|
|
"loss": 5.6201,
|
|
"mean_token_accuracy": 0.17547230273485184,
|
|
"num_tokens": 43389575.0,
|
|
"step": 22175
|
|
},
|
|
{
|
|
"entropy": 6.112716770172119,
|
|
"epoch": 2.217124006597691,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004510975729852327,
|
|
"loss": 5.6804,
|
|
"mean_token_accuracy": 0.179116128385067,
|
|
"num_tokens": 43399686.0,
|
|
"step": 22180
|
|
},
|
|
{
|
|
"entropy": 6.137652063369751,
|
|
"epoch": 2.217623831658919,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004510753559232792,
|
|
"loss": 5.7828,
|
|
"mean_token_accuracy": 0.1633241891860962,
|
|
"num_tokens": 43408918.0,
|
|
"step": 22185
|
|
},
|
|
{
|
|
"entropy": 6.138072919845581,
|
|
"epoch": 2.218123656720148,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00045105313443131496,
|
|
"loss": 5.7918,
|
|
"mean_token_accuracy": 0.16612424403429032,
|
|
"num_tokens": 43419285.0,
|
|
"step": 22190
|
|
},
|
|
{
|
|
"entropy": 6.072656679153442,
|
|
"epoch": 2.2186234817813766,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004510309085098992,
|
|
"loss": 5.6445,
|
|
"mean_token_accuracy": 0.1769646644592285,
|
|
"num_tokens": 43428909.0,
|
|
"step": 22195
|
|
},
|
|
{
|
|
"entropy": 6.089702367782593,
|
|
"epoch": 2.2191233068426053,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00045100867815959107,
|
|
"loss": 5.7024,
|
|
"mean_token_accuracy": 0.16772138178348542,
|
|
"num_tokens": 43438092.0,
|
|
"step": 22200
|
|
},
|
|
{
|
|
"entropy": 5.981192684173584,
|
|
"epoch": 2.2196231319038335,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004509864433809499,
|
|
"loss": 5.5447,
|
|
"mean_token_accuracy": 0.1852123558521271,
|
|
"num_tokens": 43447566.0,
|
|
"step": 22205
|
|
},
|
|
{
|
|
"entropy": 6.068679761886597,
|
|
"epoch": 2.2201229569650622,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004509642041745351,
|
|
"loss": 5.6979,
|
|
"mean_token_accuracy": 0.17621578574180602,
|
|
"num_tokens": 43457765.0,
|
|
"step": 22210
|
|
},
|
|
{
|
|
"entropy": 6.063366365432739,
|
|
"epoch": 2.220622782026291,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004509419605409062,
|
|
"loss": 5.5662,
|
|
"mean_token_accuracy": 0.18236087560653685,
|
|
"num_tokens": 43467664.0,
|
|
"step": 22215
|
|
},
|
|
{
|
|
"entropy": 6.0992515087127686,
|
|
"epoch": 2.221122607087519,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004509197124806229,
|
|
"loss": 5.7654,
|
|
"mean_token_accuracy": 0.170225790143013,
|
|
"num_tokens": 43477732.0,
|
|
"step": 22220
|
|
},
|
|
{
|
|
"entropy": 5.997075319290161,
|
|
"epoch": 2.221622432148748,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00045089745999424486,
|
|
"loss": 5.6967,
|
|
"mean_token_accuracy": 0.1765386566519737,
|
|
"num_tokens": 43487005.0,
|
|
"step": 22225
|
|
},
|
|
{
|
|
"entropy": 6.0542994976043705,
|
|
"epoch": 2.2221222572099766,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000450875203082332,
|
|
"loss": 5.6873,
|
|
"mean_token_accuracy": 0.1735798478126526,
|
|
"num_tokens": 43496167.0,
|
|
"step": 22230
|
|
},
|
|
{
|
|
"entropy": 6.12067141532898,
|
|
"epoch": 2.2226220822712053,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004508529417454442,
|
|
"loss": 5.7034,
|
|
"mean_token_accuracy": 0.17338578402996063,
|
|
"num_tokens": 43506464.0,
|
|
"step": 22235
|
|
},
|
|
{
|
|
"entropy": 6.076030015945435,
|
|
"epoch": 2.2231219073324335,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00045083067598414176,
|
|
"loss": 5.6783,
|
|
"mean_token_accuracy": 0.1710233435034752,
|
|
"num_tokens": 43516554.0,
|
|
"step": 22240
|
|
},
|
|
{
|
|
"entropy": 6.045764017105102,
|
|
"epoch": 2.2236217323936622,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00045080840579898466,
|
|
"loss": 5.6226,
|
|
"mean_token_accuracy": 0.17854979932308196,
|
|
"num_tokens": 43525233.0,
|
|
"step": 22245
|
|
},
|
|
{
|
|
"entropy": 6.1606964588165285,
|
|
"epoch": 2.224121557454891,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004507861311905334,
|
|
"loss": 5.839,
|
|
"mean_token_accuracy": 0.1545635551214218,
|
|
"num_tokens": 43536075.0,
|
|
"step": 22250
|
|
},
|
|
{
|
|
"entropy": 6.038920068740845,
|
|
"epoch": 2.224621382516119,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004507638521593482,
|
|
"loss": 5.579,
|
|
"mean_token_accuracy": 0.18030722737312316,
|
|
"num_tokens": 43545478.0,
|
|
"step": 22255
|
|
},
|
|
{
|
|
"entropy": 6.1011394500732425,
|
|
"epoch": 2.225121207577348,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004507415687059898,
|
|
"loss": 5.7209,
|
|
"mean_token_accuracy": 0.15826830714941026,
|
|
"num_tokens": 43554261.0,
|
|
"step": 22260
|
|
},
|
|
{
|
|
"entropy": 6.017924118041992,
|
|
"epoch": 2.2256210326385766,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00045071928083101874,
|
|
"loss": 5.6356,
|
|
"mean_token_accuracy": 0.173980276286602,
|
|
"num_tokens": 43563235.0,
|
|
"step": 22265
|
|
},
|
|
{
|
|
"entropy": 6.088432025909424,
|
|
"epoch": 2.2261208576998053,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004506969885349957,
|
|
"loss": 5.7369,
|
|
"mean_token_accuracy": 0.16527409553527833,
|
|
"num_tokens": 43572385.0,
|
|
"step": 22270
|
|
},
|
|
{
|
|
"entropy": 6.03280086517334,
|
|
"epoch": 2.2266206827610335,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004506746918184818,
|
|
"loss": 5.6574,
|
|
"mean_token_accuracy": 0.17163578420877457,
|
|
"num_tokens": 43580843.0,
|
|
"step": 22275
|
|
},
|
|
{
|
|
"entropy": 6.059504985809326,
|
|
"epoch": 2.2271205078222622,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004506523906820378,
|
|
"loss": 5.7302,
|
|
"mean_token_accuracy": 0.1763191893696785,
|
|
"num_tokens": 43590500.0,
|
|
"step": 22280
|
|
},
|
|
{
|
|
"entropy": 6.049973344802856,
|
|
"epoch": 2.227620332883491,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004506300851262248,
|
|
"loss": 5.6348,
|
|
"mean_token_accuracy": 0.18171750456094743,
|
|
"num_tokens": 43601306.0,
|
|
"step": 22285
|
|
},
|
|
{
|
|
"entropy": 6.006799840927124,
|
|
"epoch": 2.228120157944719,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00045060777515160404,
|
|
"loss": 5.5716,
|
|
"mean_token_accuracy": 0.18149776011705399,
|
|
"num_tokens": 43612728.0,
|
|
"step": 22290
|
|
},
|
|
{
|
|
"entropy": 6.094565105438233,
|
|
"epoch": 2.228619983005948,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004505854607587369,
|
|
"loss": 5.7093,
|
|
"mean_token_accuracy": 0.17174057587981223,
|
|
"num_tokens": 43622178.0,
|
|
"step": 22295
|
|
},
|
|
{
|
|
"entropy": 6.1501000881195065,
|
|
"epoch": 2.2291198080671766,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004505631419481847,
|
|
"loss": 5.8051,
|
|
"mean_token_accuracy": 0.15781422108411788,
|
|
"num_tokens": 43632622.0,
|
|
"step": 22300
|
|
},
|
|
{
|
|
"entropy": 6.16510853767395,
|
|
"epoch": 2.2296196331284053,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004505408187205091,
|
|
"loss": 5.8346,
|
|
"mean_token_accuracy": 0.15950777381658554,
|
|
"num_tokens": 43642703.0,
|
|
"step": 22305
|
|
},
|
|
{
|
|
"entropy": 6.04364161491394,
|
|
"epoch": 2.2301194581896335,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004505184910762716,
|
|
"loss": 5.7052,
|
|
"mean_token_accuracy": 0.17500858008861542,
|
|
"num_tokens": 43652075.0,
|
|
"step": 22310
|
|
},
|
|
{
|
|
"entropy": 6.0636241912841795,
|
|
"epoch": 2.2306192832508622,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00045049615901603406,
|
|
"loss": 5.722,
|
|
"mean_token_accuracy": 0.17225242853164674,
|
|
"num_tokens": 43660459.0,
|
|
"step": 22315
|
|
},
|
|
{
|
|
"entropy": 6.045185899734497,
|
|
"epoch": 2.231119108312091,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004504738225403583,
|
|
"loss": 5.5683,
|
|
"mean_token_accuracy": 0.18658003360033035,
|
|
"num_tokens": 43670528.0,
|
|
"step": 22320
|
|
},
|
|
{
|
|
"entropy": 6.001858901977539,
|
|
"epoch": 2.231618933373319,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004504514816498064,
|
|
"loss": 5.6435,
|
|
"mean_token_accuracy": 0.1781071588397026,
|
|
"num_tokens": 43680383.0,
|
|
"step": 22325
|
|
},
|
|
{
|
|
"entropy": 6.075688123703003,
|
|
"epoch": 2.232118758434548,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00045042913634494024,
|
|
"loss": 5.6638,
|
|
"mean_token_accuracy": 0.17948515564203263,
|
|
"num_tokens": 43690922.0,
|
|
"step": 22330
|
|
},
|
|
{
|
|
"entropy": 6.1135241985321045,
|
|
"epoch": 2.2326185834957766,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004504067866263222,
|
|
"loss": 5.7623,
|
|
"mean_token_accuracy": 0.1664172738790512,
|
|
"num_tokens": 43700444.0,
|
|
"step": 22335
|
|
},
|
|
{
|
|
"entropy": 6.144137954711914,
|
|
"epoch": 2.2331184085570053,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0004503844324945146,
|
|
"loss": 5.7009,
|
|
"mean_token_accuracy": 0.1743481397628784,
|
|
"num_tokens": 43711946.0,
|
|
"step": 22340
|
|
},
|
|
{
|
|
"entropy": 6.0831914901733395,
|
|
"epoch": 2.2336182336182335,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004503620739500797,
|
|
"loss": 5.6901,
|
|
"mean_token_accuracy": 0.17074926793575287,
|
|
"num_tokens": 43722368.0,
|
|
"step": 22345
|
|
},
|
|
{
|
|
"entropy": 5.945222282409668,
|
|
"epoch": 2.2341180586794622,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004503397109935802,
|
|
"loss": 5.55,
|
|
"mean_token_accuracy": 0.18232066333293914,
|
|
"num_tokens": 43731035.0,
|
|
"step": 22350
|
|
},
|
|
{
|
|
"entropy": 6.0373206615448,
|
|
"epoch": 2.234617883740691,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004503173436255787,
|
|
"loss": 5.6925,
|
|
"mean_token_accuracy": 0.16928586214780808,
|
|
"num_tokens": 43740737.0,
|
|
"step": 22355
|
|
},
|
|
{
|
|
"entropy": 6.062059116363526,
|
|
"epoch": 2.235117708801919,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000450294971846638,
|
|
"loss": 5.7381,
|
|
"mean_token_accuracy": 0.17443309873342513,
|
|
"num_tokens": 43750184.0,
|
|
"step": 22360
|
|
},
|
|
{
|
|
"entropy": 6.05583176612854,
|
|
"epoch": 2.235617533863148,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004502725956573208,
|
|
"loss": 5.6989,
|
|
"mean_token_accuracy": 0.17304016500711442,
|
|
"num_tokens": 43759573.0,
|
|
"step": 22365
|
|
},
|
|
{
|
|
"entropy": 6.0556807041168215,
|
|
"epoch": 2.2361173589243766,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004502502150581903,
|
|
"loss": 5.6457,
|
|
"mean_token_accuracy": 0.17462544590234758,
|
|
"num_tokens": 43769065.0,
|
|
"step": 22370
|
|
},
|
|
{
|
|
"entropy": 6.089718675613403,
|
|
"epoch": 2.2366171839856053,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004502278300498094,
|
|
"loss": 5.7268,
|
|
"mean_token_accuracy": 0.1686737984418869,
|
|
"num_tokens": 43779279.0,
|
|
"step": 22375
|
|
},
|
|
{
|
|
"entropy": 6.071601152420044,
|
|
"epoch": 2.2371170090468335,
|
|
"grad_norm": 1.9609375,
|
|
"learning_rate": 0.00045020544063274147,
|
|
"loss": 5.7485,
|
|
"mean_token_accuracy": 0.16475741267204286,
|
|
"num_tokens": 43789606.0,
|
|
"step": 22380
|
|
},
|
|
{
|
|
"entropy": 6.118506526947021,
|
|
"epoch": 2.2376168341080622,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00045018304680754975,
|
|
"loss": 5.7163,
|
|
"mean_token_accuracy": 0.17317909151315689,
|
|
"num_tokens": 43798309.0,
|
|
"step": 22385
|
|
},
|
|
{
|
|
"entropy": 6.0838634967803955,
|
|
"epoch": 2.238116659169291,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004501606485747975,
|
|
"loss": 5.6893,
|
|
"mean_token_accuracy": 0.17899496704339982,
|
|
"num_tokens": 43809378.0,
|
|
"step": 22390
|
|
},
|
|
{
|
|
"entropy": 6.0497664451599125,
|
|
"epoch": 2.238616484230519,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004501382459350485,
|
|
"loss": 5.6579,
|
|
"mean_token_accuracy": 0.1698521852493286,
|
|
"num_tokens": 43819258.0,
|
|
"step": 22395
|
|
},
|
|
{
|
|
"entropy": 6.014442682266235,
|
|
"epoch": 2.239116309291748,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004501158388888663,
|
|
"loss": 5.6767,
|
|
"mean_token_accuracy": 0.17557064741849898,
|
|
"num_tokens": 43829015.0,
|
|
"step": 22400
|
|
},
|
|
{
|
|
"entropy": 6.13017578125,
|
|
"epoch": 2.2396161343529766,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004500934274368147,
|
|
"loss": 5.7629,
|
|
"mean_token_accuracy": 0.16892049759626387,
|
|
"num_tokens": 43838347.0,
|
|
"step": 22405
|
|
},
|
|
{
|
|
"entropy": 6.22054762840271,
|
|
"epoch": 2.240115959414205,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00045007101157945747,
|
|
"loss": 5.8013,
|
|
"mean_token_accuracy": 0.16326963603496553,
|
|
"num_tokens": 43847302.0,
|
|
"step": 22410
|
|
},
|
|
{
|
|
"entropy": 6.049062252044678,
|
|
"epoch": 2.2406157844754335,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00045004859131735867,
|
|
"loss": 5.6762,
|
|
"mean_token_accuracy": 0.1720476418733597,
|
|
"num_tokens": 43857803.0,
|
|
"step": 22415
|
|
},
|
|
{
|
|
"entropy": 6.040486288070679,
|
|
"epoch": 2.2411156095366622,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00045002616665108233,
|
|
"loss": 5.7567,
|
|
"mean_token_accuracy": 0.16557680070400238,
|
|
"num_tokens": 43867682.0,
|
|
"step": 22420
|
|
},
|
|
{
|
|
"entropy": 6.064830923080445,
|
|
"epoch": 2.241615434597891,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004500037375811926,
|
|
"loss": 5.7742,
|
|
"mean_token_accuracy": 0.1608240433037281,
|
|
"num_tokens": 43878699.0,
|
|
"step": 22425
|
|
},
|
|
{
|
|
"entropy": 6.158652496337891,
|
|
"epoch": 2.242115259659119,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00044998130410825395,
|
|
"loss": 5.7921,
|
|
"mean_token_accuracy": 0.1647699773311615,
|
|
"num_tokens": 43887752.0,
|
|
"step": 22430
|
|
},
|
|
{
|
|
"entropy": 6.132038736343384,
|
|
"epoch": 2.242615084720348,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004499588662328307,
|
|
"loss": 5.7545,
|
|
"mean_token_accuracy": 0.16406787186861038,
|
|
"num_tokens": 43897518.0,
|
|
"step": 22435
|
|
},
|
|
{
|
|
"entropy": 6.118708992004395,
|
|
"epoch": 2.2431149097815766,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004499364239554874,
|
|
"loss": 5.6769,
|
|
"mean_token_accuracy": 0.17522989958524704,
|
|
"num_tokens": 43907054.0,
|
|
"step": 22440
|
|
},
|
|
{
|
|
"entropy": 6.12865891456604,
|
|
"epoch": 2.243614734842805,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004499139772767887,
|
|
"loss": 5.7738,
|
|
"mean_token_accuracy": 0.1673462361097336,
|
|
"num_tokens": 43916926.0,
|
|
"step": 22445
|
|
},
|
|
{
|
|
"entropy": 6.080125713348389,
|
|
"epoch": 2.2441145599040335,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004498915261972993,
|
|
"loss": 5.7212,
|
|
"mean_token_accuracy": 0.17239292412996293,
|
|
"num_tokens": 43926615.0,
|
|
"step": 22450
|
|
},
|
|
{
|
|
"entropy": 6.045749664306641,
|
|
"epoch": 2.244614384965262,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00044986907071758417,
|
|
"loss": 5.5909,
|
|
"mean_token_accuracy": 0.17482556998729706,
|
|
"num_tokens": 43936768.0,
|
|
"step": 22455
|
|
},
|
|
{
|
|
"entropy": 6.029107236862183,
|
|
"epoch": 2.245114210026491,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004498466108382082,
|
|
"loss": 5.5948,
|
|
"mean_token_accuracy": 0.17914859503507613,
|
|
"num_tokens": 43945812.0,
|
|
"step": 22460
|
|
},
|
|
{
|
|
"entropy": 6.152380657196045,
|
|
"epoch": 2.245614035087719,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004498241465597365,
|
|
"loss": 5.8416,
|
|
"mean_token_accuracy": 0.16236548572778703,
|
|
"num_tokens": 43955848.0,
|
|
"step": 22465
|
|
},
|
|
{
|
|
"entropy": 6.108153676986694,
|
|
"epoch": 2.246113860148948,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004498016778827342,
|
|
"loss": 5.7088,
|
|
"mean_token_accuracy": 0.16845007687807084,
|
|
"num_tokens": 43964375.0,
|
|
"step": 22470
|
|
},
|
|
{
|
|
"entropy": 6.101273822784424,
|
|
"epoch": 2.2466136852101766,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004497792048077667,
|
|
"loss": 5.7672,
|
|
"mean_token_accuracy": 0.1604781448841095,
|
|
"num_tokens": 43973992.0,
|
|
"step": 22475
|
|
},
|
|
{
|
|
"entropy": 6.103909158706665,
|
|
"epoch": 2.247113510271405,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004497567273353994,
|
|
"loss": 5.7683,
|
|
"mean_token_accuracy": 0.16776231676340103,
|
|
"num_tokens": 43983283.0,
|
|
"step": 22480
|
|
},
|
|
{
|
|
"entropy": 6.03523440361023,
|
|
"epoch": 2.2476133353326335,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00044973424546619774,
|
|
"loss": 5.5737,
|
|
"mean_token_accuracy": 0.18317320346832275,
|
|
"num_tokens": 43992175.0,
|
|
"step": 22485
|
|
},
|
|
{
|
|
"entropy": 6.105590534210205,
|
|
"epoch": 2.248113160393862,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004497117592007275,
|
|
"loss": 5.6633,
|
|
"mean_token_accuracy": 0.17633543461561202,
|
|
"num_tokens": 44001684.0,
|
|
"step": 22490
|
|
},
|
|
{
|
|
"entropy": 6.077815818786621,
|
|
"epoch": 2.248612985455091,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004496892685395543,
|
|
"loss": 5.726,
|
|
"mean_token_accuracy": 0.17177759110927582,
|
|
"num_tokens": 44011381.0,
|
|
"step": 22495
|
|
},
|
|
{
|
|
"entropy": 6.10280213356018,
|
|
"epoch": 2.249112810516319,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004496667734832441,
|
|
"loss": 5.6991,
|
|
"mean_token_accuracy": 0.17066423445940018,
|
|
"num_tokens": 44020702.0,
|
|
"step": 22500
|
|
},
|
|
{
|
|
"entropy": 6.05187349319458,
|
|
"epoch": 2.249612635577548,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00044964427403236274,
|
|
"loss": 5.6396,
|
|
"mean_token_accuracy": 0.1759045422077179,
|
|
"num_tokens": 44030123.0,
|
|
"step": 22505
|
|
},
|
|
{
|
|
"entropy": 5.998813962936401,
|
|
"epoch": 2.2501124606387766,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004496217701874765,
|
|
"loss": 5.6329,
|
|
"mean_token_accuracy": 0.17409106343984604,
|
|
"num_tokens": 44039673.0,
|
|
"step": 22510
|
|
},
|
|
{
|
|
"entropy": 6.0017376899719235,
|
|
"epoch": 2.250612285700005,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004495992619491514,
|
|
"loss": 5.556,
|
|
"mean_token_accuracy": 0.1805314302444458,
|
|
"num_tokens": 44050446.0,
|
|
"step": 22515
|
|
},
|
|
{
|
|
"entropy": 6.022802639007568,
|
|
"epoch": 2.2511121107612335,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004495767493179538,
|
|
"loss": 5.6505,
|
|
"mean_token_accuracy": 0.17238283455371856,
|
|
"num_tokens": 44059711.0,
|
|
"step": 22520
|
|
},
|
|
{
|
|
"entropy": 6.141827821731567,
|
|
"epoch": 2.251611935822462,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004495542322944501,
|
|
"loss": 5.7399,
|
|
"mean_token_accuracy": 0.1633409306406975,
|
|
"num_tokens": 44069573.0,
|
|
"step": 22525
|
|
},
|
|
{
|
|
"entropy": 6.085900354385376,
|
|
"epoch": 2.2521117608836905,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00044953171087920693,
|
|
"loss": 5.7224,
|
|
"mean_token_accuracy": 0.17461846470832826,
|
|
"num_tokens": 44078834.0,
|
|
"step": 22530
|
|
},
|
|
{
|
|
"entropy": 6.037906074523926,
|
|
"epoch": 2.252611585944919,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004495091850727907,
|
|
"loss": 5.6802,
|
|
"mean_token_accuracy": 0.17405156493186952,
|
|
"num_tokens": 44089007.0,
|
|
"step": 22535
|
|
},
|
|
{
|
|
"entropy": 6.058475208282471,
|
|
"epoch": 2.253111411006148,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00044948665487576833,
|
|
"loss": 5.6517,
|
|
"mean_token_accuracy": 0.17297311574220658,
|
|
"num_tokens": 44099482.0,
|
|
"step": 22540
|
|
},
|
|
{
|
|
"entropy": 6.067983388900757,
|
|
"epoch": 2.2536112360673766,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00044946412028870657,
|
|
"loss": 5.7672,
|
|
"mean_token_accuracy": 0.16797101944684983,
|
|
"num_tokens": 44108767.0,
|
|
"step": 22545
|
|
},
|
|
{
|
|
"entropy": 6.071152448654175,
|
|
"epoch": 2.254111061128605,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004494415813121725,
|
|
"loss": 5.5474,
|
|
"mean_token_accuracy": 0.1873765617609024,
|
|
"num_tokens": 44119086.0,
|
|
"step": 22550
|
|
},
|
|
{
|
|
"entropy": 6.098179149627685,
|
|
"epoch": 2.2546108861898335,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004494190379467331,
|
|
"loss": 5.7496,
|
|
"mean_token_accuracy": 0.17480560392141342,
|
|
"num_tokens": 44129392.0,
|
|
"step": 22555
|
|
},
|
|
{
|
|
"entropy": 6.175434112548828,
|
|
"epoch": 2.255110711251062,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00044939649019295564,
|
|
"loss": 5.8673,
|
|
"mean_token_accuracy": 0.16290825828909875,
|
|
"num_tokens": 44141226.0,
|
|
"step": 22560
|
|
},
|
|
{
|
|
"entropy": 6.079759836196899,
|
|
"epoch": 2.2556105363122905,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004493739380514073,
|
|
"loss": 5.645,
|
|
"mean_token_accuracy": 0.1798301786184311,
|
|
"num_tokens": 44151142.0,
|
|
"step": 22565
|
|
},
|
|
{
|
|
"entropy": 6.024267387390137,
|
|
"epoch": 2.256110361373519,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004493513815226556,
|
|
"loss": 5.627,
|
|
"mean_token_accuracy": 0.17689021080732345,
|
|
"num_tokens": 44161431.0,
|
|
"step": 22570
|
|
},
|
|
{
|
|
"entropy": 6.036727571487427,
|
|
"epoch": 2.256610186434748,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000449328820607268,
|
|
"loss": 5.6518,
|
|
"mean_token_accuracy": 0.18133107870817183,
|
|
"num_tokens": 44171220.0,
|
|
"step": 22575
|
|
},
|
|
{
|
|
"entropy": 6.10524697303772,
|
|
"epoch": 2.2571100114959766,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004493062553058121,
|
|
"loss": 5.7673,
|
|
"mean_token_accuracy": 0.16912038773298263,
|
|
"num_tokens": 44181314.0,
|
|
"step": 22580
|
|
},
|
|
{
|
|
"entropy": 6.055276346206665,
|
|
"epoch": 2.257609836557205,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00044928368561885566,
|
|
"loss": 5.669,
|
|
"mean_token_accuracy": 0.17193051278591157,
|
|
"num_tokens": 44190575.0,
|
|
"step": 22585
|
|
},
|
|
{
|
|
"entropy": 6.073415660858155,
|
|
"epoch": 2.2581096616184335,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00044926111154696655,
|
|
"loss": 5.7202,
|
|
"mean_token_accuracy": 0.16916196793317795,
|
|
"num_tokens": 44199769.0,
|
|
"step": 22590
|
|
},
|
|
{
|
|
"entropy": 6.037960815429687,
|
|
"epoch": 2.258609486679662,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004492385330907127,
|
|
"loss": 5.6098,
|
|
"mean_token_accuracy": 0.17935370802879333,
|
|
"num_tokens": 44209255.0,
|
|
"step": 22595
|
|
},
|
|
{
|
|
"entropy": 6.1065253734588625,
|
|
"epoch": 2.2591093117408905,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004492159502506622,
|
|
"loss": 5.7691,
|
|
"mean_token_accuracy": 0.1743679702281952,
|
|
"num_tokens": 44217742.0,
|
|
"step": 22600
|
|
},
|
|
{
|
|
"entropy": 6.001553106307983,
|
|
"epoch": 2.259609136802119,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00044919336302738324,
|
|
"loss": 5.6755,
|
|
"mean_token_accuracy": 0.1741026371717453,
|
|
"num_tokens": 44227277.0,
|
|
"step": 22605
|
|
},
|
|
{
|
|
"entropy": 6.0866011619567875,
|
|
"epoch": 2.260108961863348,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00044917077142144407,
|
|
"loss": 5.6764,
|
|
"mean_token_accuracy": 0.17597934156656264,
|
|
"num_tokens": 44236460.0,
|
|
"step": 22610
|
|
},
|
|
{
|
|
"entropy": 5.990848112106323,
|
|
"epoch": 2.2606087869245766,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00044914817543341315,
|
|
"loss": 5.638,
|
|
"mean_token_accuracy": 0.1809018388390541,
|
|
"num_tokens": 44246840.0,
|
|
"step": 22615
|
|
},
|
|
{
|
|
"entropy": 6.154830265045166,
|
|
"epoch": 2.261108611985805,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004491255750638589,
|
|
"loss": 5.8253,
|
|
"mean_token_accuracy": 0.16505912691354752,
|
|
"num_tokens": 44257258.0,
|
|
"step": 22620
|
|
},
|
|
{
|
|
"entropy": 6.160608577728271,
|
|
"epoch": 2.2616084370470335,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00044910297031335006,
|
|
"loss": 5.7736,
|
|
"mean_token_accuracy": 0.17136289775371552,
|
|
"num_tokens": 44267155.0,
|
|
"step": 22625
|
|
},
|
|
{
|
|
"entropy": 5.931515264511108,
|
|
"epoch": 2.262108262108262,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00044908036118245523,
|
|
"loss": 5.5232,
|
|
"mean_token_accuracy": 0.1858709365129471,
|
|
"num_tokens": 44276432.0,
|
|
"step": 22630
|
|
},
|
|
{
|
|
"entropy": 6.027887439727783,
|
|
"epoch": 2.2626080871694905,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004490577476717433,
|
|
"loss": 5.6282,
|
|
"mean_token_accuracy": 0.18570034354925155,
|
|
"num_tokens": 44287340.0,
|
|
"step": 22635
|
|
},
|
|
{
|
|
"entropy": 6.0464120388031,
|
|
"epoch": 2.263107912230719,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004490351297817832,
|
|
"loss": 5.6795,
|
|
"mean_token_accuracy": 0.17527788132429123,
|
|
"num_tokens": 44296252.0,
|
|
"step": 22640
|
|
},
|
|
{
|
|
"entropy": 6.074407434463501,
|
|
"epoch": 2.263607737291948,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000449012507513144,
|
|
"loss": 5.7039,
|
|
"mean_token_accuracy": 0.1777969032526016,
|
|
"num_tokens": 44305779.0,
|
|
"step": 22645
|
|
},
|
|
{
|
|
"entropy": 6.074302911758423,
|
|
"epoch": 2.2641075623531766,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00044898988086639497,
|
|
"loss": 5.6809,
|
|
"mean_token_accuracy": 0.17364162504673003,
|
|
"num_tokens": 44315729.0,
|
|
"step": 22650
|
|
},
|
|
{
|
|
"entropy": 6.025763416290284,
|
|
"epoch": 2.264607387414405,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004489672498421053,
|
|
"loss": 5.6675,
|
|
"mean_token_accuracy": 0.17220954298973085,
|
|
"num_tokens": 44325525.0,
|
|
"step": 22655
|
|
},
|
|
{
|
|
"entropy": 6.020935726165772,
|
|
"epoch": 2.2651072124756335,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004489446144408444,
|
|
"loss": 5.5922,
|
|
"mean_token_accuracy": 0.18891848176717757,
|
|
"num_tokens": 44335860.0,
|
|
"step": 22660
|
|
},
|
|
{
|
|
"entropy": 5.974157524108887,
|
|
"epoch": 2.265607037536862,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004489219746631817,
|
|
"loss": 5.5692,
|
|
"mean_token_accuracy": 0.1855461522936821,
|
|
"num_tokens": 44344944.0,
|
|
"step": 22665
|
|
},
|
|
{
|
|
"entropy": 6.063340902328491,
|
|
"epoch": 2.2661068625980905,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00044889933050968695,
|
|
"loss": 5.6924,
|
|
"mean_token_accuracy": 0.17405368983745576,
|
|
"num_tokens": 44355293.0,
|
|
"step": 22670
|
|
},
|
|
{
|
|
"entropy": 6.076911497116089,
|
|
"epoch": 2.266606687659319,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00044887668198092975,
|
|
"loss": 5.6065,
|
|
"mean_token_accuracy": 0.18404664248228073,
|
|
"num_tokens": 44364252.0,
|
|
"step": 22675
|
|
},
|
|
{
|
|
"entropy": 6.078535270690918,
|
|
"epoch": 2.267106512720548,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00044885402907748,
|
|
"loss": 5.7165,
|
|
"mean_token_accuracy": 0.17250694930553437,
|
|
"num_tokens": 44374483.0,
|
|
"step": 22680
|
|
},
|
|
{
|
|
"entropy": 6.0822412967681885,
|
|
"epoch": 2.2676063377817766,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00044883137179990755,
|
|
"loss": 5.7209,
|
|
"mean_token_accuracy": 0.1703102022409439,
|
|
"num_tokens": 44385163.0,
|
|
"step": 22685
|
|
},
|
|
{
|
|
"entropy": 6.0564045906066895,
|
|
"epoch": 2.268106162843005,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00044880871014878253,
|
|
"loss": 5.6964,
|
|
"mean_token_accuracy": 0.17723734378814698,
|
|
"num_tokens": 44394993.0,
|
|
"step": 22690
|
|
},
|
|
{
|
|
"entropy": 6.062743997573852,
|
|
"epoch": 2.2686059879042335,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00044878604412467517,
|
|
"loss": 5.7311,
|
|
"mean_token_accuracy": 0.17119051665067672,
|
|
"num_tokens": 44404954.0,
|
|
"step": 22695
|
|
},
|
|
{
|
|
"entropy": 6.125878190994262,
|
|
"epoch": 2.269105812965462,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00044876337372815555,
|
|
"loss": 5.7226,
|
|
"mean_token_accuracy": 0.16412465125322342,
|
|
"num_tokens": 44413911.0,
|
|
"step": 22700
|
|
},
|
|
{
|
|
"entropy": 6.1398561000823975,
|
|
"epoch": 2.2696056380266905,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.00044874069895979417,
|
|
"loss": 5.8162,
|
|
"mean_token_accuracy": 0.16147057861089706,
|
|
"num_tokens": 44423156.0,
|
|
"step": 22705
|
|
},
|
|
{
|
|
"entropy": 6.0345676898956295,
|
|
"epoch": 2.270105463087919,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004487180198201616,
|
|
"loss": 5.7226,
|
|
"mean_token_accuracy": 0.16698667407035828,
|
|
"num_tokens": 44432303.0,
|
|
"step": 22710
|
|
},
|
|
{
|
|
"entropy": 5.976342821121216,
|
|
"epoch": 2.270605288149148,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00044869533630982833,
|
|
"loss": 5.5508,
|
|
"mean_token_accuracy": 0.1814276784658432,
|
|
"num_tokens": 44442097.0,
|
|
"step": 22715
|
|
},
|
|
{
|
|
"entropy": 6.003163766860962,
|
|
"epoch": 2.2711051132103766,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000448672648429365,
|
|
"loss": 5.6424,
|
|
"mean_token_accuracy": 0.18064063042402267,
|
|
"num_tokens": 44452168.0,
|
|
"step": 22720
|
|
},
|
|
{
|
|
"entropy": 6.038792419433594,
|
|
"epoch": 2.271604938271605,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00044864995617934265,
|
|
"loss": 5.6524,
|
|
"mean_token_accuracy": 0.17429352253675462,
|
|
"num_tokens": 44461612.0,
|
|
"step": 22725
|
|
},
|
|
{
|
|
"entropy": 6.069672679901123,
|
|
"epoch": 2.2721047633328335,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.000448627259560332,
|
|
"loss": 5.7345,
|
|
"mean_token_accuracy": 0.1678517058491707,
|
|
"num_tokens": 44473397.0,
|
|
"step": 22730
|
|
},
|
|
{
|
|
"entropy": 6.0537004470825195,
|
|
"epoch": 2.272604588394062,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00044860455857290415,
|
|
"loss": 5.6284,
|
|
"mean_token_accuracy": 0.1773111492395401,
|
|
"num_tokens": 44482677.0,
|
|
"step": 22735
|
|
},
|
|
{
|
|
"entropy": 6.098512935638428,
|
|
"epoch": 2.2731044134552905,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004485818532176304,
|
|
"loss": 5.7478,
|
|
"mean_token_accuracy": 0.1688385307788849,
|
|
"num_tokens": 44492918.0,
|
|
"step": 22740
|
|
},
|
|
{
|
|
"entropy": 6.118225908279419,
|
|
"epoch": 2.273604238516519,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004485591434950818,
|
|
"loss": 5.7265,
|
|
"mean_token_accuracy": 0.1637028157711029,
|
|
"num_tokens": 44502514.0,
|
|
"step": 22745
|
|
},
|
|
{
|
|
"entropy": 6.0268059253692625,
|
|
"epoch": 2.274104063577748,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004485364294058298,
|
|
"loss": 5.5906,
|
|
"mean_token_accuracy": 0.18165698349475862,
|
|
"num_tokens": 44513078.0,
|
|
"step": 22750
|
|
},
|
|
{
|
|
"entropy": 5.9715500831604,
|
|
"epoch": 2.2746038886389766,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00044851371095044597,
|
|
"loss": 5.671,
|
|
"mean_token_accuracy": 0.17125180065631868,
|
|
"num_tokens": 44523318.0,
|
|
"step": 22755
|
|
},
|
|
{
|
|
"entropy": 6.047052049636841,
|
|
"epoch": 2.275103713700205,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00044849098812950174,
|
|
"loss": 5.7429,
|
|
"mean_token_accuracy": 0.173597514629364,
|
|
"num_tokens": 44533910.0,
|
|
"step": 22760
|
|
},
|
|
{
|
|
"entropy": 6.084307241439819,
|
|
"epoch": 2.2756035387614335,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.000448468260943569,
|
|
"loss": 5.6435,
|
|
"mean_token_accuracy": 0.1787631943821907,
|
|
"num_tokens": 44543733.0,
|
|
"step": 22765
|
|
},
|
|
{
|
|
"entropy": 6.049649286270141,
|
|
"epoch": 2.276103363822662,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00044844552939321937,
|
|
"loss": 5.7325,
|
|
"mean_token_accuracy": 0.1701285570859909,
|
|
"num_tokens": 44554041.0,
|
|
"step": 22770
|
|
},
|
|
{
|
|
"entropy": 6.053313541412353,
|
|
"epoch": 2.2766031888838905,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004484227934790248,
|
|
"loss": 5.685,
|
|
"mean_token_accuracy": 0.17547703832387923,
|
|
"num_tokens": 44564136.0,
|
|
"step": 22775
|
|
},
|
|
{
|
|
"entropy": 6.00047345161438,
|
|
"epoch": 2.277103013945119,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004484000532015575,
|
|
"loss": 5.6201,
|
|
"mean_token_accuracy": 0.1776821196079254,
|
|
"num_tokens": 44572706.0,
|
|
"step": 22780
|
|
},
|
|
{
|
|
"entropy": 6.062019920349121,
|
|
"epoch": 2.277602839006348,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00044837730856138935,
|
|
"loss": 5.7006,
|
|
"mean_token_accuracy": 0.16909769028425217,
|
|
"num_tokens": 44581748.0,
|
|
"step": 22785
|
|
},
|
|
{
|
|
"entropy": 6.039270877838135,
|
|
"epoch": 2.2781026640675766,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004483545595590928,
|
|
"loss": 5.6363,
|
|
"mean_token_accuracy": 0.1778234988451004,
|
|
"num_tokens": 44591107.0,
|
|
"step": 22790
|
|
},
|
|
{
|
|
"entropy": 6.185616493225098,
|
|
"epoch": 2.278602489128805,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004483318061952401,
|
|
"loss": 5.764,
|
|
"mean_token_accuracy": 0.16588449627161025,
|
|
"num_tokens": 44600718.0,
|
|
"step": 22795
|
|
},
|
|
{
|
|
"entropy": 6.026822090148926,
|
|
"epoch": 2.2791023141900335,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004483090484704038,
|
|
"loss": 5.6138,
|
|
"mean_token_accuracy": 0.18309806287288666,
|
|
"num_tokens": 44610702.0,
|
|
"step": 22800
|
|
},
|
|
{
|
|
"entropy": 6.034923839569092,
|
|
"epoch": 2.279602139251262,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00044828628638515647,
|
|
"loss": 5.6898,
|
|
"mean_token_accuracy": 0.17448866218328477,
|
|
"num_tokens": 44621060.0,
|
|
"step": 22805
|
|
},
|
|
{
|
|
"entropy": 6.021358299255371,
|
|
"epoch": 2.2801019643124905,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004482635199400707,
|
|
"loss": 5.6038,
|
|
"mean_token_accuracy": 0.17894552648067474,
|
|
"num_tokens": 44631060.0,
|
|
"step": 22810
|
|
},
|
|
{
|
|
"entropy": 6.074204301834106,
|
|
"epoch": 2.280601789373719,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00044824074913571936,
|
|
"loss": 5.6466,
|
|
"mean_token_accuracy": 0.17481619268655776,
|
|
"num_tokens": 44640025.0,
|
|
"step": 22815
|
|
},
|
|
{
|
|
"entropy": 6.00816912651062,
|
|
"epoch": 2.281101614434948,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00044821797397267535,
|
|
"loss": 5.7403,
|
|
"mean_token_accuracy": 0.17396088391542436,
|
|
"num_tokens": 44650168.0,
|
|
"step": 22820
|
|
},
|
|
{
|
|
"entropy": 6.096772146224976,
|
|
"epoch": 2.2816014394961766,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004481951944515117,
|
|
"loss": 5.7308,
|
|
"mean_token_accuracy": 0.1617944598197937,
|
|
"num_tokens": 44660370.0,
|
|
"step": 22825
|
|
},
|
|
{
|
|
"entropy": 6.034852981567383,
|
|
"epoch": 2.282101264557405,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00044817241057280155,
|
|
"loss": 5.6909,
|
|
"mean_token_accuracy": 0.17266330122947693,
|
|
"num_tokens": 44669776.0,
|
|
"step": 22830
|
|
},
|
|
{
|
|
"entropy": 6.028156423568726,
|
|
"epoch": 2.2826010896186335,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004481496223371181,
|
|
"loss": 5.6587,
|
|
"mean_token_accuracy": 0.17077943980693816,
|
|
"num_tokens": 44678891.0,
|
|
"step": 22835
|
|
},
|
|
{
|
|
"entropy": 6.0406496047973635,
|
|
"epoch": 2.283100914679862,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00044812682974503464,
|
|
"loss": 5.6106,
|
|
"mean_token_accuracy": 0.18087831288576126,
|
|
"num_tokens": 44688750.0,
|
|
"step": 22840
|
|
},
|
|
{
|
|
"entropy": 6.014291477203369,
|
|
"epoch": 2.2836007397410905,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004481040327971248,
|
|
"loss": 5.6748,
|
|
"mean_token_accuracy": 0.1712581068277359,
|
|
"num_tokens": 44698570.0,
|
|
"step": 22845
|
|
},
|
|
{
|
|
"entropy": 6.098011064529419,
|
|
"epoch": 2.284100564802319,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00044808123149396193,
|
|
"loss": 5.6939,
|
|
"mean_token_accuracy": 0.1748856395483017,
|
|
"num_tokens": 44707423.0,
|
|
"step": 22850
|
|
},
|
|
{
|
|
"entropy": 6.0897071838378904,
|
|
"epoch": 2.284600389863548,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00044805842583611993,
|
|
"loss": 5.7196,
|
|
"mean_token_accuracy": 0.1637044757604599,
|
|
"num_tokens": 44717526.0,
|
|
"step": 22855
|
|
},
|
|
{
|
|
"entropy": 5.996752548217773,
|
|
"epoch": 2.2851002149247766,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00044803561582417237,
|
|
"loss": 5.5871,
|
|
"mean_token_accuracy": 0.18193459063768386,
|
|
"num_tokens": 44726713.0,
|
|
"step": 22860
|
|
},
|
|
{
|
|
"entropy": 6.094383287429809,
|
|
"epoch": 2.285600039986005,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00044801280145869327,
|
|
"loss": 5.781,
|
|
"mean_token_accuracy": 0.16567677557468413,
|
|
"num_tokens": 44736399.0,
|
|
"step": 22865
|
|
},
|
|
{
|
|
"entropy": 6.131544065475464,
|
|
"epoch": 2.2860998650472335,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004479899827402566,
|
|
"loss": 5.7496,
|
|
"mean_token_accuracy": 0.1661750078201294,
|
|
"num_tokens": 44746291.0,
|
|
"step": 22870
|
|
},
|
|
{
|
|
"entropy": 6.077876949310303,
|
|
"epoch": 2.286599690108462,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00044796715966943654,
|
|
"loss": 5.731,
|
|
"mean_token_accuracy": 0.17105165421962737,
|
|
"num_tokens": 44755937.0,
|
|
"step": 22875
|
|
},
|
|
{
|
|
"entropy": 6.023032522201538,
|
|
"epoch": 2.2870995151696905,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004479443322468072,
|
|
"loss": 5.6941,
|
|
"mean_token_accuracy": 0.17422498315572738,
|
|
"num_tokens": 44765764.0,
|
|
"step": 22880
|
|
},
|
|
{
|
|
"entropy": 6.04978346824646,
|
|
"epoch": 2.287599340230919,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004479215004729429,
|
|
"loss": 5.7715,
|
|
"mean_token_accuracy": 0.16991278678178787,
|
|
"num_tokens": 44776134.0,
|
|
"step": 22885
|
|
},
|
|
{
|
|
"entropy": 6.065638875961303,
|
|
"epoch": 2.288099165292148,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004478986643484183,
|
|
"loss": 5.7123,
|
|
"mean_token_accuracy": 0.17587504386901856,
|
|
"num_tokens": 44786356.0,
|
|
"step": 22890
|
|
},
|
|
{
|
|
"entropy": 6.0670092582702635,
|
|
"epoch": 2.2885989903533765,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00044787582387380764,
|
|
"loss": 5.5999,
|
|
"mean_token_accuracy": 0.17938142716884614,
|
|
"num_tokens": 44795838.0,
|
|
"step": 22895
|
|
},
|
|
{
|
|
"entropy": 6.036712551116944,
|
|
"epoch": 2.289098815414605,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004478529790496858,
|
|
"loss": 5.6894,
|
|
"mean_token_accuracy": 0.17197711914777755,
|
|
"num_tokens": 44804571.0,
|
|
"step": 22900
|
|
},
|
|
{
|
|
"entropy": 6.05548129081726,
|
|
"epoch": 2.2895986404758335,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00044783012987662755,
|
|
"loss": 5.7308,
|
|
"mean_token_accuracy": 0.1708865150809288,
|
|
"num_tokens": 44814546.0,
|
|
"step": 22905
|
|
},
|
|
{
|
|
"entropy": 6.026643133163452,
|
|
"epoch": 2.290098465537062,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004478072763552076,
|
|
"loss": 5.5892,
|
|
"mean_token_accuracy": 0.17970643043518067,
|
|
"num_tokens": 44825196.0,
|
|
"step": 22910
|
|
},
|
|
{
|
|
"entropy": 6.050881814956665,
|
|
"epoch": 2.2905982905982905,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004477844184860011,
|
|
"loss": 5.6468,
|
|
"mean_token_accuracy": 0.17391785830259324,
|
|
"num_tokens": 44835502.0,
|
|
"step": 22915
|
|
},
|
|
{
|
|
"entropy": 5.981116676330567,
|
|
"epoch": 2.291098115659519,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00044776155626958305,
|
|
"loss": 5.6877,
|
|
"mean_token_accuracy": 0.1742405503988266,
|
|
"num_tokens": 44845574.0,
|
|
"step": 22920
|
|
},
|
|
{
|
|
"entropy": 5.932076120376587,
|
|
"epoch": 2.291597940720748,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00044773868970652875,
|
|
"loss": 5.5554,
|
|
"mean_token_accuracy": 0.18696845769882203,
|
|
"num_tokens": 44855946.0,
|
|
"step": 22925
|
|
},
|
|
{
|
|
"entropy": 6.112062740325928,
|
|
"epoch": 2.2920977657819765,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00044771581879741334,
|
|
"loss": 5.7571,
|
|
"mean_token_accuracy": 0.1660885915160179,
|
|
"num_tokens": 44865753.0,
|
|
"step": 22930
|
|
},
|
|
{
|
|
"entropy": 6.026565504074097,
|
|
"epoch": 2.292597590843205,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.00044769294354281253,
|
|
"loss": 5.6568,
|
|
"mean_token_accuracy": 0.17344452142715455,
|
|
"num_tokens": 44876296.0,
|
|
"step": 22935
|
|
},
|
|
{
|
|
"entropy": 6.168589925765991,
|
|
"epoch": 2.2930974159044335,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00044767006394330166,
|
|
"loss": 5.7836,
|
|
"mean_token_accuracy": 0.16381236165761948,
|
|
"num_tokens": 44886207.0,
|
|
"step": 22940
|
|
},
|
|
{
|
|
"entropy": 6.023128652572632,
|
|
"epoch": 2.293597240965662,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00044764717999945644,
|
|
"loss": 5.6552,
|
|
"mean_token_accuracy": 0.1833658054471016,
|
|
"num_tokens": 44894911.0,
|
|
"step": 22945
|
|
},
|
|
{
|
|
"entropy": 6.006473970413208,
|
|
"epoch": 2.2940970660268905,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00044762429171185246,
|
|
"loss": 5.6695,
|
|
"mean_token_accuracy": 0.17943334579467773,
|
|
"num_tokens": 44904513.0,
|
|
"step": 22950
|
|
},
|
|
{
|
|
"entropy": 6.002195835113525,
|
|
"epoch": 2.294596891088119,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00044760139908106583,
|
|
"loss": 5.6024,
|
|
"mean_token_accuracy": 0.17614807784557343,
|
|
"num_tokens": 44914039.0,
|
|
"step": 22955
|
|
},
|
|
{
|
|
"entropy": 6.004284524917603,
|
|
"epoch": 2.295096716149348,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004475785021076724,
|
|
"loss": 5.6956,
|
|
"mean_token_accuracy": 0.17493657618761063,
|
|
"num_tokens": 44924149.0,
|
|
"step": 22960
|
|
},
|
|
{
|
|
"entropy": 5.979197978973389,
|
|
"epoch": 2.2955965412105765,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00044755560079224834,
|
|
"loss": 5.5896,
|
|
"mean_token_accuracy": 0.18606843203306198,
|
|
"num_tokens": 44933929.0,
|
|
"step": 22965
|
|
},
|
|
{
|
|
"entropy": 6.0707744598388675,
|
|
"epoch": 2.296096366271805,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004475326951353697,
|
|
"loss": 5.6184,
|
|
"mean_token_accuracy": 0.1814635694026947,
|
|
"num_tokens": 44943199.0,
|
|
"step": 22970
|
|
},
|
|
{
|
|
"entropy": 6.0610123634338375,
|
|
"epoch": 2.2965961913330335,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00044750978513761276,
|
|
"loss": 5.7242,
|
|
"mean_token_accuracy": 0.1695463202893734,
|
|
"num_tokens": 44952660.0,
|
|
"step": 22975
|
|
},
|
|
{
|
|
"entropy": 5.940778112411499,
|
|
"epoch": 2.297096016394262,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004474868707995541,
|
|
"loss": 5.5597,
|
|
"mean_token_accuracy": 0.17953137457370758,
|
|
"num_tokens": 44962907.0,
|
|
"step": 22980
|
|
},
|
|
{
|
|
"entropy": 6.084239435195923,
|
|
"epoch": 2.2975958414554905,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00044746395212177015,
|
|
"loss": 5.6985,
|
|
"mean_token_accuracy": 0.1741614505648613,
|
|
"num_tokens": 44973319.0,
|
|
"step": 22985
|
|
},
|
|
{
|
|
"entropy": 6.0896735191345215,
|
|
"epoch": 2.298095666516719,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00044744102910483755,
|
|
"loss": 5.6275,
|
|
"mean_token_accuracy": 0.17671078741550444,
|
|
"num_tokens": 44982818.0,
|
|
"step": 22990
|
|
},
|
|
{
|
|
"entropy": 5.967837524414063,
|
|
"epoch": 2.298595491577948,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000447418101749333,
|
|
"loss": 5.5146,
|
|
"mean_token_accuracy": 0.19110410511493683,
|
|
"num_tokens": 44992189.0,
|
|
"step": 22995
|
|
},
|
|
{
|
|
"entropy": 5.952633428573608,
|
|
"epoch": 2.299095316639176,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004473951700558334,
|
|
"loss": 5.6795,
|
|
"mean_token_accuracy": 0.1809281513094902,
|
|
"num_tokens": 45002296.0,
|
|
"step": 23000
|
|
},
|
|
{
|
|
"entropy": 6.11917519569397,
|
|
"epoch": 2.299595141700405,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00044737223402491574,
|
|
"loss": 5.7202,
|
|
"mean_token_accuracy": 0.17027538567781447,
|
|
"num_tokens": 45011500.0,
|
|
"step": 23005
|
|
},
|
|
{
|
|
"entropy": 6.151496934890747,
|
|
"epoch": 2.3000949667616335,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00044734929365715685,
|
|
"loss": 5.7959,
|
|
"mean_token_accuracy": 0.16129543781280517,
|
|
"num_tokens": 45021816.0,
|
|
"step": 23010
|
|
},
|
|
{
|
|
"entropy": 6.13515157699585,
|
|
"epoch": 2.3005947918228618,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00044732634895313424,
|
|
"loss": 5.78,
|
|
"mean_token_accuracy": 0.16375336050987244,
|
|
"num_tokens": 45031227.0,
|
|
"step": 23015
|
|
},
|
|
{
|
|
"entropy": 5.991793060302735,
|
|
"epoch": 2.3010946168840904,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.000447303399913425,
|
|
"loss": 5.6174,
|
|
"mean_token_accuracy": 0.1853421464562416,
|
|
"num_tokens": 45040076.0,
|
|
"step": 23020
|
|
},
|
|
{
|
|
"entropy": 6.120551538467407,
|
|
"epoch": 2.301594441945319,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00044728044653860653,
|
|
"loss": 5.7962,
|
|
"mean_token_accuracy": 0.17112789750099183,
|
|
"num_tokens": 45049905.0,
|
|
"step": 23025
|
|
},
|
|
{
|
|
"entropy": 6.153276062011718,
|
|
"epoch": 2.302094267006548,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004472574888292564,
|
|
"loss": 5.8447,
|
|
"mean_token_accuracy": 0.15745872855186463,
|
|
"num_tokens": 45059722.0,
|
|
"step": 23030
|
|
},
|
|
{
|
|
"entropy": 6.067645788192749,
|
|
"epoch": 2.302594092067776,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004472345267859521,
|
|
"loss": 5.6567,
|
|
"mean_token_accuracy": 0.17563721984624864,
|
|
"num_tokens": 45068734.0,
|
|
"step": 23035
|
|
},
|
|
{
|
|
"entropy": 6.05361270904541,
|
|
"epoch": 2.303093917129005,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004472115604092715,
|
|
"loss": 5.6641,
|
|
"mean_token_accuracy": 0.17222387939691544,
|
|
"num_tokens": 45078774.0,
|
|
"step": 23040
|
|
},
|
|
{
|
|
"entropy": 6.019655084609985,
|
|
"epoch": 2.3035937421902335,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00044718858969979236,
|
|
"loss": 5.6587,
|
|
"mean_token_accuracy": 0.17077835351228715,
|
|
"num_tokens": 45088351.0,
|
|
"step": 23045
|
|
},
|
|
{
|
|
"entropy": 6.195325803756714,
|
|
"epoch": 2.3040935672514617,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00044716561465809256,
|
|
"loss": 5.8431,
|
|
"mean_token_accuracy": 0.16386722326278685,
|
|
"num_tokens": 45098530.0,
|
|
"step": 23050
|
|
},
|
|
{
|
|
"entropy": 6.043189287185669,
|
|
"epoch": 2.3045933923126904,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00044714263528475024,
|
|
"loss": 5.6848,
|
|
"mean_token_accuracy": 0.1743500843644142,
|
|
"num_tokens": 45108950.0,
|
|
"step": 23055
|
|
},
|
|
{
|
|
"entropy": 6.024399137496948,
|
|
"epoch": 2.305093217373919,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00044711965158034345,
|
|
"loss": 5.7146,
|
|
"mean_token_accuracy": 0.17396614998579024,
|
|
"num_tokens": 45117548.0,
|
|
"step": 23060
|
|
},
|
|
{
|
|
"entropy": 6.050306987762451,
|
|
"epoch": 2.305593042435148,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004470966635454506,
|
|
"loss": 5.6739,
|
|
"mean_token_accuracy": 0.1671048656105995,
|
|
"num_tokens": 45126882.0,
|
|
"step": 23065
|
|
},
|
|
{
|
|
"entropy": 6.144672060012818,
|
|
"epoch": 2.306092867496376,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004470736711806499,
|
|
"loss": 5.7213,
|
|
"mean_token_accuracy": 0.16810256391763687,
|
|
"num_tokens": 45137751.0,
|
|
"step": 23070
|
|
},
|
|
{
|
|
"entropy": 5.9754722118377686,
|
|
"epoch": 2.306592692557605,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00044705067448651996,
|
|
"loss": 5.528,
|
|
"mean_token_accuracy": 0.18646798580884932,
|
|
"num_tokens": 45147051.0,
|
|
"step": 23075
|
|
},
|
|
{
|
|
"entropy": 6.048721742630005,
|
|
"epoch": 2.3070925176188335,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004470276734636393,
|
|
"loss": 5.6786,
|
|
"mean_token_accuracy": 0.17359419614076615,
|
|
"num_tokens": 45156859.0,
|
|
"step": 23080
|
|
},
|
|
{
|
|
"entropy": 6.031953382492065,
|
|
"epoch": 2.3075923426800617,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00044700466811258666,
|
|
"loss": 5.6687,
|
|
"mean_token_accuracy": 0.17621501684188842,
|
|
"num_tokens": 45167555.0,
|
|
"step": 23085
|
|
},
|
|
{
|
|
"entropy": 6.062075853347778,
|
|
"epoch": 2.3080921677412904,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004469816584339408,
|
|
"loss": 5.6637,
|
|
"mean_token_accuracy": 0.1802670791745186,
|
|
"num_tokens": 45177777.0,
|
|
"step": 23090
|
|
},
|
|
{
|
|
"entropy": 6.0298925876617435,
|
|
"epoch": 2.308591992802519,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00044695864442828066,
|
|
"loss": 5.6439,
|
|
"mean_token_accuracy": 0.17584583759307862,
|
|
"num_tokens": 45187902.0,
|
|
"step": 23095
|
|
},
|
|
{
|
|
"entropy": 6.0856081485748295,
|
|
"epoch": 2.309091817863748,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00044693562609618534,
|
|
"loss": 5.6991,
|
|
"mean_token_accuracy": 0.169344562292099,
|
|
"num_tokens": 45198012.0,
|
|
"step": 23100
|
|
},
|
|
{
|
|
"entropy": 6.052190494537354,
|
|
"epoch": 2.309591642924976,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004469126034382339,
|
|
"loss": 5.6263,
|
|
"mean_token_accuracy": 0.18515117317438126,
|
|
"num_tokens": 45208327.0,
|
|
"step": 23105
|
|
},
|
|
{
|
|
"entropy": 6.054539728164673,
|
|
"epoch": 2.310091467986205,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004468895764550055,
|
|
"loss": 5.794,
|
|
"mean_token_accuracy": 0.1638451635837555,
|
|
"num_tokens": 45218748.0,
|
|
"step": 23110
|
|
},
|
|
{
|
|
"entropy": 6.062408685684204,
|
|
"epoch": 2.3105912930474335,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004468665451470797,
|
|
"loss": 5.7069,
|
|
"mean_token_accuracy": 0.17328882366418838,
|
|
"num_tokens": 45228803.0,
|
|
"step": 23115
|
|
},
|
|
{
|
|
"entropy": 6.095842027664185,
|
|
"epoch": 2.3110911181086617,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004468435095150358,
|
|
"loss": 5.6829,
|
|
"mean_token_accuracy": 0.17272025495767593,
|
|
"num_tokens": 45238855.0,
|
|
"step": 23120
|
|
},
|
|
{
|
|
"entropy": 6.051634883880615,
|
|
"epoch": 2.3115909431698904,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00044682046955945345,
|
|
"loss": 5.6639,
|
|
"mean_token_accuracy": 0.17625488042831422,
|
|
"num_tokens": 45248848.0,
|
|
"step": 23125
|
|
},
|
|
{
|
|
"entropy": 6.070901346206665,
|
|
"epoch": 2.312090768231119,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004467974252809123,
|
|
"loss": 5.7019,
|
|
"mean_token_accuracy": 0.1660928562283516,
|
|
"num_tokens": 45258170.0,
|
|
"step": 23130
|
|
},
|
|
{
|
|
"entropy": 6.003852081298828,
|
|
"epoch": 2.312590593292348,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00044677437667999204,
|
|
"loss": 5.654,
|
|
"mean_token_accuracy": 0.17704127877950668,
|
|
"num_tokens": 45268033.0,
|
|
"step": 23135
|
|
},
|
|
{
|
|
"entropy": 6.0391716957092285,
|
|
"epoch": 2.313090418353576,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00044675132375727273,
|
|
"loss": 5.6564,
|
|
"mean_token_accuracy": 0.17797177284955978,
|
|
"num_tokens": 45277318.0,
|
|
"step": 23140
|
|
},
|
|
{
|
|
"entropy": 6.0634603023529055,
|
|
"epoch": 2.313590243414805,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004467282665133343,
|
|
"loss": 5.7026,
|
|
"mean_token_accuracy": 0.17240968942642212,
|
|
"num_tokens": 45286810.0,
|
|
"step": 23145
|
|
},
|
|
{
|
|
"entropy": 6.024183988571167,
|
|
"epoch": 2.3140900684760335,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004467052049487569,
|
|
"loss": 5.5894,
|
|
"mean_token_accuracy": 0.1803989976644516,
|
|
"num_tokens": 45296292.0,
|
|
"step": 23150
|
|
},
|
|
{
|
|
"entropy": 6.090055513381958,
|
|
"epoch": 2.3145898935372617,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00044668213906412074,
|
|
"loss": 5.7019,
|
|
"mean_token_accuracy": 0.16899942606687546,
|
|
"num_tokens": 45305580.0,
|
|
"step": 23155
|
|
},
|
|
{
|
|
"entropy": 5.899357843399048,
|
|
"epoch": 2.3150897185984904,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.00044665906886000604,
|
|
"loss": 5.5285,
|
|
"mean_token_accuracy": 0.19135591983795167,
|
|
"num_tokens": 45314831.0,
|
|
"step": 23160
|
|
},
|
|
{
|
|
"entropy": 5.9663163185119625,
|
|
"epoch": 2.315589543659719,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00044663599433699346,
|
|
"loss": 5.6483,
|
|
"mean_token_accuracy": 0.17848593592643738,
|
|
"num_tokens": 45324503.0,
|
|
"step": 23165
|
|
},
|
|
{
|
|
"entropy": 6.1573591232299805,
|
|
"epoch": 2.316089368720948,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00044661291549566337,
|
|
"loss": 5.7659,
|
|
"mean_token_accuracy": 0.17141859084367753,
|
|
"num_tokens": 45335459.0,
|
|
"step": 23170
|
|
},
|
|
{
|
|
"entropy": 6.090490913391113,
|
|
"epoch": 2.316589193782176,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004465898323365965,
|
|
"loss": 5.7307,
|
|
"mean_token_accuracy": 0.17112892121076584,
|
|
"num_tokens": 45344951.0,
|
|
"step": 23175
|
|
},
|
|
{
|
|
"entropy": 6.088250207901001,
|
|
"epoch": 2.317089018843405,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004465667448603736,
|
|
"loss": 5.8682,
|
|
"mean_token_accuracy": 0.1588994175195694,
|
|
"num_tokens": 45354953.0,
|
|
"step": 23180
|
|
},
|
|
{
|
|
"entropy": 6.094873714447021,
|
|
"epoch": 2.3175888439046335,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00044654365306757553,
|
|
"loss": 5.7208,
|
|
"mean_token_accuracy": 0.17284342050552368,
|
|
"num_tokens": 45364567.0,
|
|
"step": 23185
|
|
},
|
|
{
|
|
"entropy": 6.123171091079712,
|
|
"epoch": 2.3180886689658617,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00044652055695878335,
|
|
"loss": 5.7101,
|
|
"mean_token_accuracy": 0.16931606084108353,
|
|
"num_tokens": 45374147.0,
|
|
"step": 23190
|
|
},
|
|
{
|
|
"entropy": 6.0637603282928465,
|
|
"epoch": 2.3185884940270904,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00044649745653457806,
|
|
"loss": 5.6506,
|
|
"mean_token_accuracy": 0.17552071064710617,
|
|
"num_tokens": 45383304.0,
|
|
"step": 23195
|
|
},
|
|
{
|
|
"entropy": 5.713884735107422,
|
|
"epoch": 2.319088319088319,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00044647435179554087,
|
|
"loss": 5.4095,
|
|
"mean_token_accuracy": 0.20528105199337005,
|
|
"num_tokens": 45392508.0,
|
|
"step": 23200
|
|
},
|
|
{
|
|
"entropy": 6.07532844543457,
|
|
"epoch": 2.319588144149548,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004464512427422531,
|
|
"loss": 5.7478,
|
|
"mean_token_accuracy": 0.1714147910475731,
|
|
"num_tokens": 45402584.0,
|
|
"step": 23205
|
|
},
|
|
{
|
|
"entropy": 6.101289844512939,
|
|
"epoch": 2.320087969210776,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00044642812937529624,
|
|
"loss": 5.783,
|
|
"mean_token_accuracy": 0.16129010021686555,
|
|
"num_tokens": 45413270.0,
|
|
"step": 23210
|
|
},
|
|
{
|
|
"entropy": 6.110234498977661,
|
|
"epoch": 2.320587794272005,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004464050116952517,
|
|
"loss": 5.7228,
|
|
"mean_token_accuracy": 0.18021120727062226,
|
|
"num_tokens": 45423444.0,
|
|
"step": 23215
|
|
},
|
|
{
|
|
"entropy": 6.1082111358642575,
|
|
"epoch": 2.3210876193332335,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00044638188970270114,
|
|
"loss": 5.7799,
|
|
"mean_token_accuracy": 0.16662174463272095,
|
|
"num_tokens": 45433737.0,
|
|
"step": 23220
|
|
},
|
|
{
|
|
"entropy": 6.107088184356689,
|
|
"epoch": 2.3215874443944617,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00044635876339822647,
|
|
"loss": 5.7109,
|
|
"mean_token_accuracy": 0.16726793944835663,
|
|
"num_tokens": 45442948.0,
|
|
"step": 23225
|
|
},
|
|
{
|
|
"entropy": 6.057793807983399,
|
|
"epoch": 2.3220872694556904,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00044633563278240933,
|
|
"loss": 5.6369,
|
|
"mean_token_accuracy": 0.17158055752515794,
|
|
"num_tokens": 45453181.0,
|
|
"step": 23230
|
|
},
|
|
{
|
|
"entropy": 6.048984003067017,
|
|
"epoch": 2.322587094516919,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00044631249785583173,
|
|
"loss": 5.7118,
|
|
"mean_token_accuracy": 0.16995309740304948,
|
|
"num_tokens": 45462888.0,
|
|
"step": 23235
|
|
},
|
|
{
|
|
"entropy": 6.054628944396972,
|
|
"epoch": 2.323086919578148,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004462893586190758,
|
|
"loss": 5.7008,
|
|
"mean_token_accuracy": 0.1687774956226349,
|
|
"num_tokens": 45471269.0,
|
|
"step": 23240
|
|
},
|
|
{
|
|
"entropy": 6.0467465877532955,
|
|
"epoch": 2.323586744639376,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00044626621507272364,
|
|
"loss": 5.6897,
|
|
"mean_token_accuracy": 0.17471655309200287,
|
|
"num_tokens": 45480799.0,
|
|
"step": 23245
|
|
},
|
|
{
|
|
"entropy": 5.9789234638214115,
|
|
"epoch": 2.324086569700605,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00044624306721735763,
|
|
"loss": 5.6737,
|
|
"mean_token_accuracy": 0.17141595631837844,
|
|
"num_tokens": 45490729.0,
|
|
"step": 23250
|
|
},
|
|
{
|
|
"entropy": 6.090534639358521,
|
|
"epoch": 2.3245863947618335,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00044621991505356014,
|
|
"loss": 5.7589,
|
|
"mean_token_accuracy": 0.16209158152341843,
|
|
"num_tokens": 45500020.0,
|
|
"step": 23255
|
|
},
|
|
{
|
|
"entropy": 6.123114776611328,
|
|
"epoch": 2.3250862198230617,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00044619675858191353,
|
|
"loss": 5.7248,
|
|
"mean_token_accuracy": 0.17071440070867538,
|
|
"num_tokens": 45509175.0,
|
|
"step": 23260
|
|
},
|
|
{
|
|
"entropy": 6.121223068237304,
|
|
"epoch": 2.3255860448842904,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004461735978030006,
|
|
"loss": 5.7116,
|
|
"mean_token_accuracy": 0.16990227103233338,
|
|
"num_tokens": 45519089.0,
|
|
"step": 23265
|
|
},
|
|
{
|
|
"entropy": 5.93277678489685,
|
|
"epoch": 2.326085869945519,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00044615043271740404,
|
|
"loss": 5.5178,
|
|
"mean_token_accuracy": 0.19543037116527556,
|
|
"num_tokens": 45528623.0,
|
|
"step": 23270
|
|
},
|
|
{
|
|
"entropy": 6.0297605991363525,
|
|
"epoch": 2.326585695006748,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004461272633257065,
|
|
"loss": 5.6618,
|
|
"mean_token_accuracy": 0.1732642188668251,
|
|
"num_tokens": 45538260.0,
|
|
"step": 23275
|
|
},
|
|
{
|
|
"entropy": 6.084908199310303,
|
|
"epoch": 2.327085520067976,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004461040896284912,
|
|
"loss": 5.7024,
|
|
"mean_token_accuracy": 0.17064151912927628,
|
|
"num_tokens": 45547874.0,
|
|
"step": 23280
|
|
},
|
|
{
|
|
"entropy": 6.146101665496826,
|
|
"epoch": 2.327585345129205,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000446080911626341,
|
|
"loss": 5.665,
|
|
"mean_token_accuracy": 0.17788902521133423,
|
|
"num_tokens": 45557229.0,
|
|
"step": 23285
|
|
},
|
|
{
|
|
"entropy": 6.088607740402222,
|
|
"epoch": 2.3280851701904335,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004460577293198391,
|
|
"loss": 5.8136,
|
|
"mean_token_accuracy": 0.1630767524242401,
|
|
"num_tokens": 45567803.0,
|
|
"step": 23290
|
|
},
|
|
{
|
|
"entropy": 5.958169889450073,
|
|
"epoch": 2.3285849952516617,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00044603454270956863,
|
|
"loss": 5.5236,
|
|
"mean_token_accuracy": 0.1840052366256714,
|
|
"num_tokens": 45576412.0,
|
|
"step": 23295
|
|
},
|
|
{
|
|
"entropy": 6.019798469543457,
|
|
"epoch": 2.3290848203128904,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004460113517961132,
|
|
"loss": 5.6692,
|
|
"mean_token_accuracy": 0.17680879384279252,
|
|
"num_tokens": 45584951.0,
|
|
"step": 23300
|
|
},
|
|
{
|
|
"entropy": 6.052875661849976,
|
|
"epoch": 2.329584645374119,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004459881565800561,
|
|
"loss": 5.6766,
|
|
"mean_token_accuracy": 0.17113007307052613,
|
|
"num_tokens": 45594520.0,
|
|
"step": 23305
|
|
},
|
|
{
|
|
"entropy": 6.004458713531494,
|
|
"epoch": 2.330084470435348,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004459649570619809,
|
|
"loss": 5.5748,
|
|
"mean_token_accuracy": 0.18470701873302459,
|
|
"num_tokens": 45604438.0,
|
|
"step": 23310
|
|
},
|
|
{
|
|
"entropy": 6.012117910385132,
|
|
"epoch": 2.330584295496576,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004459417532424715,
|
|
"loss": 5.7041,
|
|
"mean_token_accuracy": 0.1795194923877716,
|
|
"num_tokens": 45614898.0,
|
|
"step": 23315
|
|
},
|
|
{
|
|
"entropy": 6.125318288803101,
|
|
"epoch": 2.331084120557805,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004459185451221116,
|
|
"loss": 5.7842,
|
|
"mean_token_accuracy": 0.16594187170267105,
|
|
"num_tokens": 45624812.0,
|
|
"step": 23320
|
|
},
|
|
{
|
|
"entropy": 5.970911741256714,
|
|
"epoch": 2.3315839456190335,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.000445895332701485,
|
|
"loss": 5.5974,
|
|
"mean_token_accuracy": 0.17535770684480667,
|
|
"num_tokens": 45635238.0,
|
|
"step": 23325
|
|
},
|
|
{
|
|
"entropy": 6.046926116943359,
|
|
"epoch": 2.3320837706802617,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00044587211598117577,
|
|
"loss": 5.6864,
|
|
"mean_token_accuracy": 0.17960671186447144,
|
|
"num_tokens": 45644928.0,
|
|
"step": 23330
|
|
},
|
|
{
|
|
"entropy": 6.145384883880615,
|
|
"epoch": 2.3325835957414904,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00044584889496176815,
|
|
"loss": 5.7697,
|
|
"mean_token_accuracy": 0.16578260511159898,
|
|
"num_tokens": 45654708.0,
|
|
"step": 23335
|
|
},
|
|
{
|
|
"entropy": 6.048732852935791,
|
|
"epoch": 2.333083420802719,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004458256696438463,
|
|
"loss": 5.7139,
|
|
"mean_token_accuracy": 0.17417414337396622,
|
|
"num_tokens": 45664000.0,
|
|
"step": 23340
|
|
},
|
|
{
|
|
"entropy": 6.056825351715088,
|
|
"epoch": 2.333583245863948,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00044580244002799454,
|
|
"loss": 5.7024,
|
|
"mean_token_accuracy": 0.17080347537994384,
|
|
"num_tokens": 45674563.0,
|
|
"step": 23345
|
|
},
|
|
{
|
|
"entropy": 6.060544633865357,
|
|
"epoch": 2.334083070925176,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004457792061147973,
|
|
"loss": 5.6546,
|
|
"mean_token_accuracy": 0.18095923811197281,
|
|
"num_tokens": 45683525.0,
|
|
"step": 23350
|
|
},
|
|
{
|
|
"entropy": 6.08147554397583,
|
|
"epoch": 2.334582895986405,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004457559679048392,
|
|
"loss": 5.7746,
|
|
"mean_token_accuracy": 0.16932618916034697,
|
|
"num_tokens": 45693767.0,
|
|
"step": 23355
|
|
},
|
|
{
|
|
"entropy": 6.1195008754730225,
|
|
"epoch": 2.3350827210476335,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.000445732725398705,
|
|
"loss": 5.7522,
|
|
"mean_token_accuracy": 0.16770072132349015,
|
|
"num_tokens": 45702999.0,
|
|
"step": 23360
|
|
},
|
|
{
|
|
"entropy": 6.042944431304932,
|
|
"epoch": 2.3355825461088617,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004457094785969792,
|
|
"loss": 5.6454,
|
|
"mean_token_accuracy": 0.17746188268065452,
|
|
"num_tokens": 45712370.0,
|
|
"step": 23365
|
|
},
|
|
{
|
|
"entropy": 6.011191654205322,
|
|
"epoch": 2.3360823711700904,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00044568622750024693,
|
|
"loss": 5.6518,
|
|
"mean_token_accuracy": 0.17531405836343766,
|
|
"num_tokens": 45721321.0,
|
|
"step": 23370
|
|
},
|
|
{
|
|
"entropy": 6.018875455856323,
|
|
"epoch": 2.336582196231319,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004456629721090931,
|
|
"loss": 5.6858,
|
|
"mean_token_accuracy": 0.17115638107061387,
|
|
"num_tokens": 45731043.0,
|
|
"step": 23375
|
|
},
|
|
{
|
|
"entropy": 6.017781591415405,
|
|
"epoch": 2.337082021292548,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004456397124241028,
|
|
"loss": 5.6621,
|
|
"mean_token_accuracy": 0.17862430959939957,
|
|
"num_tokens": 45739916.0,
|
|
"step": 23380
|
|
},
|
|
{
|
|
"entropy": 6.077720308303833,
|
|
"epoch": 2.337581846353776,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004456164484458612,
|
|
"loss": 5.6551,
|
|
"mean_token_accuracy": 0.17950366884469987,
|
|
"num_tokens": 45749680.0,
|
|
"step": 23385
|
|
},
|
|
{
|
|
"entropy": 6.050723457336426,
|
|
"epoch": 2.338081671415005,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004455931801749537,
|
|
"loss": 5.7498,
|
|
"mean_token_accuracy": 0.1622303918004036,
|
|
"num_tokens": 45758457.0,
|
|
"step": 23390
|
|
},
|
|
{
|
|
"entropy": 6.200327587127686,
|
|
"epoch": 2.3385814964762335,
|
|
"grad_norm": 1.9296875,
|
|
"learning_rate": 0.00044556990761196566,
|
|
"loss": 5.7946,
|
|
"mean_token_accuracy": 0.16091436445713042,
|
|
"num_tokens": 45768793.0,
|
|
"step": 23395
|
|
},
|
|
{
|
|
"entropy": 6.168738555908203,
|
|
"epoch": 2.3390813215374617,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00044554663075748266,
|
|
"loss": 5.7659,
|
|
"mean_token_accuracy": 0.17001837790012359,
|
|
"num_tokens": 45778724.0,
|
|
"step": 23400
|
|
},
|
|
{
|
|
"entropy": 6.074654769897461,
|
|
"epoch": 2.3395811465986904,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004455233496120903,
|
|
"loss": 5.753,
|
|
"mean_token_accuracy": 0.1735953778028488,
|
|
"num_tokens": 45788186.0,
|
|
"step": 23405
|
|
},
|
|
{
|
|
"entropy": 6.02429575920105,
|
|
"epoch": 2.340080971659919,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004455000641763743,
|
|
"loss": 5.6731,
|
|
"mean_token_accuracy": 0.17448950111865996,
|
|
"num_tokens": 45797496.0,
|
|
"step": 23410
|
|
},
|
|
{
|
|
"entropy": 6.091831493377685,
|
|
"epoch": 2.340580796721148,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00044547677445092064,
|
|
"loss": 5.6703,
|
|
"mean_token_accuracy": 0.17529186606407166,
|
|
"num_tokens": 45807450.0,
|
|
"step": 23415
|
|
},
|
|
{
|
|
"entropy": 6.040422248840332,
|
|
"epoch": 2.341080621782376,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00044545348043631525,
|
|
"loss": 5.6436,
|
|
"mean_token_accuracy": 0.18007360249757767,
|
|
"num_tokens": 45817149.0,
|
|
"step": 23420
|
|
},
|
|
{
|
|
"entropy": 6.038127994537353,
|
|
"epoch": 2.341580446843605,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00044543018213314404,
|
|
"loss": 5.7428,
|
|
"mean_token_accuracy": 0.17474524229764937,
|
|
"num_tokens": 45828102.0,
|
|
"step": 23425
|
|
},
|
|
{
|
|
"entropy": 6.039235830307007,
|
|
"epoch": 2.3420802719048335,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00044540687954199335,
|
|
"loss": 5.6953,
|
|
"mean_token_accuracy": 0.1755706861615181,
|
|
"num_tokens": 45837961.0,
|
|
"step": 23430
|
|
},
|
|
{
|
|
"entropy": 5.934189081192017,
|
|
"epoch": 2.3425800969660617,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00044538357266344936,
|
|
"loss": 5.49,
|
|
"mean_token_accuracy": 0.18789185881614684,
|
|
"num_tokens": 45848190.0,
|
|
"step": 23435
|
|
},
|
|
{
|
|
"entropy": 6.0456188201904295,
|
|
"epoch": 2.3430799220272904,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004453602614980986,
|
|
"loss": 5.6779,
|
|
"mean_token_accuracy": 0.17161813527345657,
|
|
"num_tokens": 45857019.0,
|
|
"step": 23440
|
|
},
|
|
{
|
|
"entropy": 6.07444658279419,
|
|
"epoch": 2.343579747088519,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004453369460465274,
|
|
"loss": 5.6883,
|
|
"mean_token_accuracy": 0.17213812470436096,
|
|
"num_tokens": 45865835.0,
|
|
"step": 23445
|
|
},
|
|
{
|
|
"entropy": 6.065567064285278,
|
|
"epoch": 2.344079572149748,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004453136263093225,
|
|
"loss": 5.7704,
|
|
"mean_token_accuracy": 0.16590767204761506,
|
|
"num_tokens": 45876027.0,
|
|
"step": 23450
|
|
},
|
|
{
|
|
"entropy": 6.092840623855591,
|
|
"epoch": 2.344579397210976,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004452903022870707,
|
|
"loss": 5.7401,
|
|
"mean_token_accuracy": 0.16479096114635466,
|
|
"num_tokens": 45886270.0,
|
|
"step": 23455
|
|
},
|
|
{
|
|
"entropy": 6.0032727241516115,
|
|
"epoch": 2.3450792222722048,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004452669739803586,
|
|
"loss": 5.642,
|
|
"mean_token_accuracy": 0.18016216456890105,
|
|
"num_tokens": 45895741.0,
|
|
"step": 23460
|
|
},
|
|
{
|
|
"entropy": 5.997713899612426,
|
|
"epoch": 2.3455790473334335,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004452436413897733,
|
|
"loss": 5.5905,
|
|
"mean_token_accuracy": 0.18777657598257064,
|
|
"num_tokens": 45905119.0,
|
|
"step": 23465
|
|
},
|
|
{
|
|
"entropy": 6.03373122215271,
|
|
"epoch": 2.3460788723946617,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004452203045159018,
|
|
"loss": 5.7061,
|
|
"mean_token_accuracy": 0.1686856120824814,
|
|
"num_tokens": 45915677.0,
|
|
"step": 23470
|
|
},
|
|
{
|
|
"entropy": 6.041910219192505,
|
|
"epoch": 2.3465786974558904,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004451969633593312,
|
|
"loss": 5.7184,
|
|
"mean_token_accuracy": 0.17431120872497557,
|
|
"num_tokens": 45925256.0,
|
|
"step": 23475
|
|
},
|
|
{
|
|
"entropy": 6.034491348266601,
|
|
"epoch": 2.347078522517119,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00044517361792064883,
|
|
"loss": 5.6532,
|
|
"mean_token_accuracy": 0.17496244758367538,
|
|
"num_tokens": 45933623.0,
|
|
"step": 23480
|
|
},
|
|
{
|
|
"entropy": 6.066129684448242,
|
|
"epoch": 2.347578347578348,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00044515026820044195,
|
|
"loss": 5.7698,
|
|
"mean_token_accuracy": 0.1670339435338974,
|
|
"num_tokens": 45945226.0,
|
|
"step": 23485
|
|
},
|
|
{
|
|
"entropy": 6.109652519226074,
|
|
"epoch": 2.348078172639576,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004451269141992982,
|
|
"loss": 5.6989,
|
|
"mean_token_accuracy": 0.16821766197681426,
|
|
"num_tokens": 45954744.0,
|
|
"step": 23490
|
|
},
|
|
{
|
|
"entropy": 6.0283934593200685,
|
|
"epoch": 2.3485779977008048,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00044510355591780503,
|
|
"loss": 5.6792,
|
|
"mean_token_accuracy": 0.17504030764102935,
|
|
"num_tokens": 45964216.0,
|
|
"step": 23495
|
|
},
|
|
{
|
|
"entropy": 6.0447594165802006,
|
|
"epoch": 2.3490778227620335,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004450801933565502,
|
|
"loss": 5.7224,
|
|
"mean_token_accuracy": 0.16860841512680053,
|
|
"num_tokens": 45974342.0,
|
|
"step": 23500
|
|
},
|
|
{
|
|
"entropy": 6.038186979293823,
|
|
"epoch": 2.3495776478232617,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004450568265161214,
|
|
"loss": 5.6316,
|
|
"mean_token_accuracy": 0.17850009799003602,
|
|
"num_tokens": 45983392.0,
|
|
"step": 23505
|
|
},
|
|
{
|
|
"entropy": 6.113355016708374,
|
|
"epoch": 2.3500774728844904,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00044503345539710664,
|
|
"loss": 5.7037,
|
|
"mean_token_accuracy": 0.17384907007217407,
|
|
"num_tokens": 45993717.0,
|
|
"step": 23510
|
|
},
|
|
{
|
|
"entropy": 6.066995525360108,
|
|
"epoch": 2.350577297945719,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004450100800000939,
|
|
"loss": 5.6695,
|
|
"mean_token_accuracy": 0.18020149171352387,
|
|
"num_tokens": 46003780.0,
|
|
"step": 23515
|
|
},
|
|
{
|
|
"entropy": 6.04229507446289,
|
|
"epoch": 2.3510771230069474,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004449867003256713,
|
|
"loss": 5.7702,
|
|
"mean_token_accuracy": 0.1663312390446663,
|
|
"num_tokens": 46015003.0,
|
|
"step": 23520
|
|
},
|
|
{
|
|
"entropy": 6.025079727172852,
|
|
"epoch": 2.351576948068176,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00044496331637442697,
|
|
"loss": 5.6961,
|
|
"mean_token_accuracy": 0.1659468024969101,
|
|
"num_tokens": 46025425.0,
|
|
"step": 23525
|
|
},
|
|
{
|
|
"entropy": 6.097351598739624,
|
|
"epoch": 2.3520767731294048,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004449399281469495,
|
|
"loss": 5.7259,
|
|
"mean_token_accuracy": 0.17280982583761215,
|
|
"num_tokens": 46035978.0,
|
|
"step": 23530
|
|
},
|
|
{
|
|
"entropy": 6.057266044616699,
|
|
"epoch": 2.3525765981906335,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00044491653564382704,
|
|
"loss": 5.6666,
|
|
"mean_token_accuracy": 0.176117505133152,
|
|
"num_tokens": 46046184.0,
|
|
"step": 23535
|
|
},
|
|
{
|
|
"entropy": 6.104152584075928,
|
|
"epoch": 2.3530764232518617,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004448931388656483,
|
|
"loss": 5.6173,
|
|
"mean_token_accuracy": 0.17758571058511735,
|
|
"num_tokens": 46057274.0,
|
|
"step": 23540
|
|
},
|
|
{
|
|
"entropy": 6.133448839187622,
|
|
"epoch": 2.3535762483130904,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00044486973781300196,
|
|
"loss": 5.7883,
|
|
"mean_token_accuracy": 0.1669346995651722,
|
|
"num_tokens": 46067302.0,
|
|
"step": 23545
|
|
},
|
|
{
|
|
"entropy": 6.031261825561524,
|
|
"epoch": 2.354076073374319,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00044484633248647665,
|
|
"loss": 5.6992,
|
|
"mean_token_accuracy": 0.17010157108306884,
|
|
"num_tokens": 46078076.0,
|
|
"step": 23550
|
|
},
|
|
{
|
|
"entropy": 5.998898696899414,
|
|
"epoch": 2.3545758984355474,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00044482292288666134,
|
|
"loss": 5.6537,
|
|
"mean_token_accuracy": 0.17712720781564711,
|
|
"num_tokens": 46088008.0,
|
|
"step": 23555
|
|
},
|
|
{
|
|
"entropy": 6.061924266815185,
|
|
"epoch": 2.355075723496776,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.000444799509014145,
|
|
"loss": 5.7034,
|
|
"mean_token_accuracy": 0.17203725576400758,
|
|
"num_tokens": 46097418.0,
|
|
"step": 23560
|
|
},
|
|
{
|
|
"entropy": 6.038363218307495,
|
|
"epoch": 2.3555755485580048,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004447760908695167,
|
|
"loss": 5.631,
|
|
"mean_token_accuracy": 0.1787923663854599,
|
|
"num_tokens": 46106906.0,
|
|
"step": 23565
|
|
},
|
|
{
|
|
"entropy": 6.000717401504517,
|
|
"epoch": 2.356075373619233,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00044475266845336566,
|
|
"loss": 5.6693,
|
|
"mean_token_accuracy": 0.17650959640741348,
|
|
"num_tokens": 46116859.0,
|
|
"step": 23570
|
|
},
|
|
{
|
|
"entropy": 5.991524744033813,
|
|
"epoch": 2.3565751986804617,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004447292417662811,
|
|
"loss": 5.7154,
|
|
"mean_token_accuracy": 0.17436835914850235,
|
|
"num_tokens": 46127633.0,
|
|
"step": 23575
|
|
},
|
|
{
|
|
"entropy": 6.0992655754089355,
|
|
"epoch": 2.3570750237416904,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004447058108088525,
|
|
"loss": 5.6496,
|
|
"mean_token_accuracy": 0.17433698624372482,
|
|
"num_tokens": 46136539.0,
|
|
"step": 23580
|
|
},
|
|
{
|
|
"entropy": 6.02979793548584,
|
|
"epoch": 2.357574848802919,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00044468237558166945,
|
|
"loss": 5.7107,
|
|
"mean_token_accuracy": 0.1700812593102455,
|
|
"num_tokens": 46147204.0,
|
|
"step": 23585
|
|
},
|
|
{
|
|
"entropy": 6.023034191131591,
|
|
"epoch": 2.3580746738641474,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00044465893608532146,
|
|
"loss": 5.6431,
|
|
"mean_token_accuracy": 0.1795258030295372,
|
|
"num_tokens": 46157638.0,
|
|
"step": 23590
|
|
},
|
|
{
|
|
"entropy": 6.099021911621094,
|
|
"epoch": 2.358574498925376,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00044463549232039824,
|
|
"loss": 5.6949,
|
|
"mean_token_accuracy": 0.17190442085266114,
|
|
"num_tokens": 46167820.0,
|
|
"step": 23595
|
|
},
|
|
{
|
|
"entropy": 6.089278221130371,
|
|
"epoch": 2.3590743239866048,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004446120442874898,
|
|
"loss": 5.702,
|
|
"mean_token_accuracy": 0.17310182005167007,
|
|
"num_tokens": 46177964.0,
|
|
"step": 23600
|
|
},
|
|
{
|
|
"entropy": 6.052863264083863,
|
|
"epoch": 2.359574149047833,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004445885919871859,
|
|
"loss": 5.6941,
|
|
"mean_token_accuracy": 0.16999887377023698,
|
|
"num_tokens": 46187265.0,
|
|
"step": 23605
|
|
},
|
|
{
|
|
"entropy": 6.0177226066589355,
|
|
"epoch": 2.3600739741090617,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004445651354200766,
|
|
"loss": 5.6827,
|
|
"mean_token_accuracy": 0.17305982261896133,
|
|
"num_tokens": 46196683.0,
|
|
"step": 23610
|
|
},
|
|
{
|
|
"entropy": 5.934831714630127,
|
|
"epoch": 2.3605737991702904,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00044454167458675225,
|
|
"loss": 5.5672,
|
|
"mean_token_accuracy": 0.18332260549068452,
|
|
"num_tokens": 46205619.0,
|
|
"step": 23615
|
|
},
|
|
{
|
|
"entropy": 5.96635217666626,
|
|
"epoch": 2.361073624231519,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00044451820948780295,
|
|
"loss": 5.6323,
|
|
"mean_token_accuracy": 0.18017166703939438,
|
|
"num_tokens": 46215121.0,
|
|
"step": 23620
|
|
},
|
|
{
|
|
"entropy": 6.000116539001465,
|
|
"epoch": 2.3615734492927474,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00044449474012381903,
|
|
"loss": 5.6086,
|
|
"mean_token_accuracy": 0.17708858847618103,
|
|
"num_tokens": 46224773.0,
|
|
"step": 23625
|
|
},
|
|
{
|
|
"entropy": 6.078643131256103,
|
|
"epoch": 2.362073274353976,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00044447126649539123,
|
|
"loss": 5.7058,
|
|
"mean_token_accuracy": 0.17485607266426087,
|
|
"num_tokens": 46234297.0,
|
|
"step": 23630
|
|
},
|
|
{
|
|
"entropy": 6.006612110137939,
|
|
"epoch": 2.3625730994152048,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004444477886031098,
|
|
"loss": 5.6341,
|
|
"mean_token_accuracy": 0.17884102314710618,
|
|
"num_tokens": 46243947.0,
|
|
"step": 23635
|
|
},
|
|
{
|
|
"entropy": 6.007134294509887,
|
|
"epoch": 2.363072924476433,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004444243064475657,
|
|
"loss": 5.6191,
|
|
"mean_token_accuracy": 0.17475195750594139,
|
|
"num_tokens": 46253604.0,
|
|
"step": 23640
|
|
},
|
|
{
|
|
"entropy": 6.033260536193848,
|
|
"epoch": 2.3635727495376617,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004444008200293496,
|
|
"loss": 5.6687,
|
|
"mean_token_accuracy": 0.18412374705076218,
|
|
"num_tokens": 46263460.0,
|
|
"step": 23645
|
|
},
|
|
{
|
|
"entropy": 6.137081336975098,
|
|
"epoch": 2.3640725745988904,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00044437732934905256,
|
|
"loss": 5.7609,
|
|
"mean_token_accuracy": 0.1703055202960968,
|
|
"num_tokens": 46272780.0,
|
|
"step": 23650
|
|
},
|
|
{
|
|
"entropy": 5.99548830986023,
|
|
"epoch": 2.364572399660119,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004443538344072654,
|
|
"loss": 5.595,
|
|
"mean_token_accuracy": 0.180925589799881,
|
|
"num_tokens": 46283278.0,
|
|
"step": 23655
|
|
},
|
|
{
|
|
"entropy": 5.963144969940186,
|
|
"epoch": 2.3650722247213474,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00044433033520457937,
|
|
"loss": 5.6524,
|
|
"mean_token_accuracy": 0.17539941519498825,
|
|
"num_tokens": 46291900.0,
|
|
"step": 23660
|
|
},
|
|
{
|
|
"entropy": 6.001904726028442,
|
|
"epoch": 2.365572049782576,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004443068317415857,
|
|
"loss": 5.6489,
|
|
"mean_token_accuracy": 0.17170209735631942,
|
|
"num_tokens": 46301517.0,
|
|
"step": 23665
|
|
},
|
|
{
|
|
"entropy": 6.076879167556763,
|
|
"epoch": 2.3660718748438048,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00044428332401887566,
|
|
"loss": 5.7146,
|
|
"mean_token_accuracy": 0.17133090645074844,
|
|
"num_tokens": 46311267.0,
|
|
"step": 23670
|
|
},
|
|
{
|
|
"entropy": 6.087161445617676,
|
|
"epoch": 2.366571699905033,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004442598120370408,
|
|
"loss": 5.7616,
|
|
"mean_token_accuracy": 0.16878858655691148,
|
|
"num_tokens": 46320280.0,
|
|
"step": 23675
|
|
},
|
|
{
|
|
"entropy": 6.012307453155517,
|
|
"epoch": 2.3670715249662617,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004442362957966726,
|
|
"loss": 5.6319,
|
|
"mean_token_accuracy": 0.17712644785642623,
|
|
"num_tokens": 46328566.0,
|
|
"step": 23680
|
|
},
|
|
{
|
|
"entropy": 6.055805492401123,
|
|
"epoch": 2.3675713500274904,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00044421277529836276,
|
|
"loss": 5.765,
|
|
"mean_token_accuracy": 0.17249911576509475,
|
|
"num_tokens": 46337586.0,
|
|
"step": 23685
|
|
},
|
|
{
|
|
"entropy": 6.048549509048462,
|
|
"epoch": 2.368071175088719,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004441892505427031,
|
|
"loss": 5.6125,
|
|
"mean_token_accuracy": 0.17580168545246125,
|
|
"num_tokens": 46346505.0,
|
|
"step": 23690
|
|
},
|
|
{
|
|
"entropy": 5.974664545059204,
|
|
"epoch": 2.3685710001499474,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004441657215302853,
|
|
"loss": 5.5319,
|
|
"mean_token_accuracy": 0.18268718421459199,
|
|
"num_tokens": 46355809.0,
|
|
"step": 23695
|
|
},
|
|
{
|
|
"entropy": 6.018911600112915,
|
|
"epoch": 2.369070825211176,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00044414218826170155,
|
|
"loss": 5.6478,
|
|
"mean_token_accuracy": 0.17639799416065216,
|
|
"num_tokens": 46366844.0,
|
|
"step": 23700
|
|
},
|
|
{
|
|
"entropy": 6.0825430393219,
|
|
"epoch": 2.3695706502724048,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004441186507375439,
|
|
"loss": 5.796,
|
|
"mean_token_accuracy": 0.16267869472503663,
|
|
"num_tokens": 46376762.0,
|
|
"step": 23705
|
|
},
|
|
{
|
|
"entropy": 6.044733715057373,
|
|
"epoch": 2.370070475333633,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00044409510895840446,
|
|
"loss": 5.6455,
|
|
"mean_token_accuracy": 0.1756926327943802,
|
|
"num_tokens": 46385716.0,
|
|
"step": 23710
|
|
},
|
|
{
|
|
"entropy": 5.9898608207702635,
|
|
"epoch": 2.3705703003948617,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.00044407156292487553,
|
|
"loss": 5.622,
|
|
"mean_token_accuracy": 0.1741563931107521,
|
|
"num_tokens": 46394442.0,
|
|
"step": 23715
|
|
},
|
|
{
|
|
"entropy": 5.929108047485352,
|
|
"epoch": 2.3710701254560904,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004440480126375497,
|
|
"loss": 5.6609,
|
|
"mean_token_accuracy": 0.177002664655447,
|
|
"num_tokens": 46405380.0,
|
|
"step": 23720
|
|
},
|
|
{
|
|
"entropy": 5.999854326248169,
|
|
"epoch": 2.371569950517319,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004440244580970193,
|
|
"loss": 5.6673,
|
|
"mean_token_accuracy": 0.1786164879798889,
|
|
"num_tokens": 46416134.0,
|
|
"step": 23725
|
|
},
|
|
{
|
|
"entropy": 6.125939226150512,
|
|
"epoch": 2.3720697755785474,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00044400089930387703,
|
|
"loss": 5.7232,
|
|
"mean_token_accuracy": 0.1754659816622734,
|
|
"num_tokens": 46425793.0,
|
|
"step": 23730
|
|
},
|
|
{
|
|
"entropy": 6.049745750427246,
|
|
"epoch": 2.372569600639776,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00044397733625871566,
|
|
"loss": 5.6545,
|
|
"mean_token_accuracy": 0.17505585253238679,
|
|
"num_tokens": 46435548.0,
|
|
"step": 23735
|
|
},
|
|
{
|
|
"entropy": 6.031286573410034,
|
|
"epoch": 2.3730694257010048,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00044395376896212805,
|
|
"loss": 5.7061,
|
|
"mean_token_accuracy": 0.1697102501988411,
|
|
"num_tokens": 46445674.0,
|
|
"step": 23740
|
|
},
|
|
{
|
|
"entropy": 6.075003719329834,
|
|
"epoch": 2.373569250762233,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00044393019741470696,
|
|
"loss": 5.6192,
|
|
"mean_token_accuracy": 0.17938391417264937,
|
|
"num_tokens": 46455711.0,
|
|
"step": 23745
|
|
},
|
|
{
|
|
"entropy": 6.018052196502685,
|
|
"epoch": 2.3740690758234617,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.0004439066216170456,
|
|
"loss": 5.6405,
|
|
"mean_token_accuracy": 0.18103395402431488,
|
|
"num_tokens": 46466998.0,
|
|
"step": 23750
|
|
},
|
|
{
|
|
"entropy": 6.077763938903809,
|
|
"epoch": 2.3745689008846904,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00044388304156973713,
|
|
"loss": 5.5931,
|
|
"mean_token_accuracy": 0.18131269812583922,
|
|
"num_tokens": 46475802.0,
|
|
"step": 23755
|
|
},
|
|
{
|
|
"entropy": 6.054673719406128,
|
|
"epoch": 2.375068725945919,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00044385945727337477,
|
|
"loss": 5.723,
|
|
"mean_token_accuracy": 0.1777203917503357,
|
|
"num_tokens": 46485678.0,
|
|
"step": 23760
|
|
},
|
|
{
|
|
"entropy": 5.980311632156372,
|
|
"epoch": 2.3755685510071474,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.000443835868728552,
|
|
"loss": 5.5539,
|
|
"mean_token_accuracy": 0.1848280817270279,
|
|
"num_tokens": 46495062.0,
|
|
"step": 23765
|
|
},
|
|
{
|
|
"entropy": 6.06671175956726,
|
|
"epoch": 2.376068376068376,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004438122759358621,
|
|
"loss": 5.7024,
|
|
"mean_token_accuracy": 0.17229639291763305,
|
|
"num_tokens": 46503588.0,
|
|
"step": 23770
|
|
},
|
|
{
|
|
"entropy": 6.085389804840088,
|
|
"epoch": 2.3765682011296048,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00044378867889589884,
|
|
"loss": 5.7229,
|
|
"mean_token_accuracy": 0.1678300067782402,
|
|
"num_tokens": 46512855.0,
|
|
"step": 23775
|
|
},
|
|
{
|
|
"entropy": 6.115764570236206,
|
|
"epoch": 2.377068026190833,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004437650776092558,
|
|
"loss": 5.8521,
|
|
"mean_token_accuracy": 0.15855634957551956,
|
|
"num_tokens": 46525243.0,
|
|
"step": 23780
|
|
},
|
|
{
|
|
"entropy": 6.079003190994262,
|
|
"epoch": 2.3775678512520617,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00044374147207652695,
|
|
"loss": 5.6793,
|
|
"mean_token_accuracy": 0.17502610236406327,
|
|
"num_tokens": 46535308.0,
|
|
"step": 23785
|
|
},
|
|
{
|
|
"entropy": 6.116574764251709,
|
|
"epoch": 2.3780676763132904,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000443717862298306,
|
|
"loss": 5.7383,
|
|
"mean_token_accuracy": 0.16660940945148467,
|
|
"num_tokens": 46544434.0,
|
|
"step": 23790
|
|
},
|
|
{
|
|
"entropy": 6.126009798049926,
|
|
"epoch": 2.378567501374519,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00044369424827518704,
|
|
"loss": 5.7189,
|
|
"mean_token_accuracy": 0.17413312643766404,
|
|
"num_tokens": 46553588.0,
|
|
"step": 23795
|
|
},
|
|
{
|
|
"entropy": 6.046082258224487,
|
|
"epoch": 2.3790673264357474,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00044367063000776423,
|
|
"loss": 5.7259,
|
|
"mean_token_accuracy": 0.16701387166976928,
|
|
"num_tokens": 46563383.0,
|
|
"step": 23800
|
|
},
|
|
{
|
|
"entropy": 6.009003973007202,
|
|
"epoch": 2.379567151496976,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004436470074966317,
|
|
"loss": 5.7193,
|
|
"mean_token_accuracy": 0.18064373433589936,
|
|
"num_tokens": 46572837.0,
|
|
"step": 23805
|
|
},
|
|
{
|
|
"entropy": 6.07470326423645,
|
|
"epoch": 2.3800669765582048,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000443623380742384,
|
|
"loss": 5.6774,
|
|
"mean_token_accuracy": 0.1786559745669365,
|
|
"num_tokens": 46582040.0,
|
|
"step": 23810
|
|
},
|
|
{
|
|
"entropy": 6.0902016162872314,
|
|
"epoch": 2.380566801619433,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004435997497456153,
|
|
"loss": 5.6924,
|
|
"mean_token_accuracy": 0.18146701753139496,
|
|
"num_tokens": 46592785.0,
|
|
"step": 23815
|
|
},
|
|
{
|
|
"entropy": 6.09073576927185,
|
|
"epoch": 2.3810666266806617,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004435761145069203,
|
|
"loss": 5.656,
|
|
"mean_token_accuracy": 0.17041588425636292,
|
|
"num_tokens": 46603625.0,
|
|
"step": 23820
|
|
},
|
|
{
|
|
"entropy": 6.075634574890136,
|
|
"epoch": 2.3815664517418904,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00044355247502689374,
|
|
"loss": 5.7005,
|
|
"mean_token_accuracy": 0.17069990783929825,
|
|
"num_tokens": 46612705.0,
|
|
"step": 23825
|
|
},
|
|
{
|
|
"entropy": 6.027826404571533,
|
|
"epoch": 2.382066276803119,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004435288313061302,
|
|
"loss": 5.6659,
|
|
"mean_token_accuracy": 0.1774760216474533,
|
|
"num_tokens": 46623178.0,
|
|
"step": 23830
|
|
},
|
|
{
|
|
"entropy": 5.995530366897583,
|
|
"epoch": 2.3825661018643474,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004435051833452246,
|
|
"loss": 5.5912,
|
|
"mean_token_accuracy": 0.17797075361013412,
|
|
"num_tokens": 46633063.0,
|
|
"step": 23835
|
|
},
|
|
{
|
|
"entropy": 6.06159930229187,
|
|
"epoch": 2.383065926925576,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000443481531144772,
|
|
"loss": 5.6711,
|
|
"mean_token_accuracy": 0.17781369537115096,
|
|
"num_tokens": 46641830.0,
|
|
"step": 23840
|
|
},
|
|
{
|
|
"entropy": 6.03528618812561,
|
|
"epoch": 2.3835657519868048,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004434578747053674,
|
|
"loss": 5.6618,
|
|
"mean_token_accuracy": 0.16510488390922545,
|
|
"num_tokens": 46651421.0,
|
|
"step": 23845
|
|
},
|
|
{
|
|
"entropy": 5.918494796752929,
|
|
"epoch": 2.384065577048033,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00044343421402760606,
|
|
"loss": 5.5471,
|
|
"mean_token_accuracy": 0.18119206875562668,
|
|
"num_tokens": 46661453.0,
|
|
"step": 23850
|
|
},
|
|
{
|
|
"entropy": 6.102961778640747,
|
|
"epoch": 2.3845654021092617,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004434105491120832,
|
|
"loss": 5.6988,
|
|
"mean_token_accuracy": 0.1718964971601963,
|
|
"num_tokens": 46671355.0,
|
|
"step": 23855
|
|
},
|
|
{
|
|
"entropy": 6.124168014526367,
|
|
"epoch": 2.3850652271704904,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00044338687995939424,
|
|
"loss": 5.7365,
|
|
"mean_token_accuracy": 0.17182641476392746,
|
|
"num_tokens": 46680966.0,
|
|
"step": 23860
|
|
},
|
|
{
|
|
"entropy": 6.059729671478271,
|
|
"epoch": 2.385565052231719,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004433632065701348,
|
|
"loss": 5.7181,
|
|
"mean_token_accuracy": 0.17304592877626418,
|
|
"num_tokens": 46691350.0,
|
|
"step": 23865
|
|
},
|
|
{
|
|
"entropy": 6.028903532028198,
|
|
"epoch": 2.3860648772929474,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004433395289449003,
|
|
"loss": 5.6989,
|
|
"mean_token_accuracy": 0.16809470653533937,
|
|
"num_tokens": 46701324.0,
|
|
"step": 23870
|
|
},
|
|
{
|
|
"entropy": 6.019116735458374,
|
|
"epoch": 2.386564702354176,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004433158470842867,
|
|
"loss": 5.6615,
|
|
"mean_token_accuracy": 0.1746137946844101,
|
|
"num_tokens": 46710713.0,
|
|
"step": 23875
|
|
},
|
|
{
|
|
"entropy": 5.878491306304932,
|
|
"epoch": 2.3870645274154048,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004432921609888896,
|
|
"loss": 5.5192,
|
|
"mean_token_accuracy": 0.19046257436275482,
|
|
"num_tokens": 46720798.0,
|
|
"step": 23880
|
|
},
|
|
{
|
|
"entropy": 6.084499025344849,
|
|
"epoch": 2.387564352476633,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00044326847065930507,
|
|
"loss": 5.7484,
|
|
"mean_token_accuracy": 0.17644204646348954,
|
|
"num_tokens": 46730337.0,
|
|
"step": 23885
|
|
},
|
|
{
|
|
"entropy": 6.0731781959533695,
|
|
"epoch": 2.3880641775378617,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00044324477609612907,
|
|
"loss": 5.7573,
|
|
"mean_token_accuracy": 0.16333687901496888,
|
|
"num_tokens": 46740457.0,
|
|
"step": 23890
|
|
},
|
|
{
|
|
"entropy": 6.022536277770996,
|
|
"epoch": 2.3885640025990904,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004432210772999578,
|
|
"loss": 5.6699,
|
|
"mean_token_accuracy": 0.17032699435949325,
|
|
"num_tokens": 46749764.0,
|
|
"step": 23895
|
|
},
|
|
{
|
|
"entropy": 6.010875034332275,
|
|
"epoch": 2.389063827660319,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004431973742713876,
|
|
"loss": 5.7441,
|
|
"mean_token_accuracy": 0.17667725384235383,
|
|
"num_tokens": 46760343.0,
|
|
"step": 23900
|
|
},
|
|
{
|
|
"entropy": 6.096673250198364,
|
|
"epoch": 2.3895636527215474,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004431736670110146,
|
|
"loss": 5.7187,
|
|
"mean_token_accuracy": 0.16860295087099075,
|
|
"num_tokens": 46770187.0,
|
|
"step": 23905
|
|
},
|
|
{
|
|
"entropy": 6.071474981307984,
|
|
"epoch": 2.390063477782776,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00044314995551943554,
|
|
"loss": 5.6641,
|
|
"mean_token_accuracy": 0.18196818977594376,
|
|
"num_tokens": 46779984.0,
|
|
"step": 23910
|
|
},
|
|
{
|
|
"entropy": 6.003053045272827,
|
|
"epoch": 2.3905633028440048,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004431262397972468,
|
|
"loss": 5.5806,
|
|
"mean_token_accuracy": 0.18028392195701598,
|
|
"num_tokens": 46788940.0,
|
|
"step": 23915
|
|
},
|
|
{
|
|
"entropy": 6.069033193588257,
|
|
"epoch": 2.391063127905233,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00044310251984504517,
|
|
"loss": 5.6229,
|
|
"mean_token_accuracy": 0.17787495702505113,
|
|
"num_tokens": 46798606.0,
|
|
"step": 23920
|
|
},
|
|
{
|
|
"entropy": 6.063167333602905,
|
|
"epoch": 2.3915629529664617,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00044307879566342736,
|
|
"loss": 5.7406,
|
|
"mean_token_accuracy": 0.16935207843780517,
|
|
"num_tokens": 46809366.0,
|
|
"step": 23925
|
|
},
|
|
{
|
|
"entropy": 6.071451616287232,
|
|
"epoch": 2.3920627780276904,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004430550672529903,
|
|
"loss": 5.6949,
|
|
"mean_token_accuracy": 0.16897144615650178,
|
|
"num_tokens": 46819174.0,
|
|
"step": 23930
|
|
},
|
|
{
|
|
"entropy": 5.9475030422210695,
|
|
"epoch": 2.392562603088919,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.000443031334614331,
|
|
"loss": 5.5635,
|
|
"mean_token_accuracy": 0.18901590406894683,
|
|
"num_tokens": 46828194.0,
|
|
"step": 23935
|
|
},
|
|
{
|
|
"entropy": 5.964138746261597,
|
|
"epoch": 2.3930624281501474,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004430075977480466,
|
|
"loss": 5.6319,
|
|
"mean_token_accuracy": 0.18702857494354247,
|
|
"num_tokens": 46838038.0,
|
|
"step": 23940
|
|
},
|
|
{
|
|
"entropy": 5.9489351272583,
|
|
"epoch": 2.393562253211376,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004429838566547343,
|
|
"loss": 5.6212,
|
|
"mean_token_accuracy": 0.17616167068481445,
|
|
"num_tokens": 46847495.0,
|
|
"step": 23945
|
|
},
|
|
{
|
|
"entropy": 5.995094919204712,
|
|
"epoch": 2.3940620782726048,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004429601113349913,
|
|
"loss": 5.7014,
|
|
"mean_token_accuracy": 0.1772020563483238,
|
|
"num_tokens": 46857759.0,
|
|
"step": 23950
|
|
},
|
|
{
|
|
"entropy": 6.0518479347229,
|
|
"epoch": 2.394561903333833,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00044293636178941516,
|
|
"loss": 5.7124,
|
|
"mean_token_accuracy": 0.1696982815861702,
|
|
"num_tokens": 46868147.0,
|
|
"step": 23955
|
|
},
|
|
{
|
|
"entropy": 6.050582456588745,
|
|
"epoch": 2.3950617283950617,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004429126080186034,
|
|
"loss": 5.7037,
|
|
"mean_token_accuracy": 0.17265557050704955,
|
|
"num_tokens": 46877863.0,
|
|
"step": 23960
|
|
},
|
|
{
|
|
"entropy": 6.093220329284668,
|
|
"epoch": 2.3955615534562904,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00044288885002315354,
|
|
"loss": 5.7239,
|
|
"mean_token_accuracy": 0.1658271700143814,
|
|
"num_tokens": 46887542.0,
|
|
"step": 23965
|
|
},
|
|
{
|
|
"entropy": 6.142875385284424,
|
|
"epoch": 2.396061378517519,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00044286508780366345,
|
|
"loss": 5.6877,
|
|
"mean_token_accuracy": 0.17284282743930818,
|
|
"num_tokens": 46897194.0,
|
|
"step": 23970
|
|
},
|
|
{
|
|
"entropy": 6.1012372970581055,
|
|
"epoch": 2.3965612035787474,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00044284132136073097,
|
|
"loss": 5.6245,
|
|
"mean_token_accuracy": 0.17259487211704255,
|
|
"num_tokens": 46905800.0,
|
|
"step": 23975
|
|
},
|
|
{
|
|
"entropy": 5.982861614227295,
|
|
"epoch": 2.397061028639976,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004428175506949541,
|
|
"loss": 5.6541,
|
|
"mean_token_accuracy": 0.17373547703027725,
|
|
"num_tokens": 46915587.0,
|
|
"step": 23980
|
|
},
|
|
{
|
|
"entropy": 6.101286745071411,
|
|
"epoch": 2.3975608537012048,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00044279377580693077,
|
|
"loss": 5.7482,
|
|
"mean_token_accuracy": 0.1680064842104912,
|
|
"num_tokens": 46925886.0,
|
|
"step": 23985
|
|
},
|
|
{
|
|
"entropy": 6.065193367004395,
|
|
"epoch": 2.398060678762433,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004427699966972592,
|
|
"loss": 5.6749,
|
|
"mean_token_accuracy": 0.17407783567905427,
|
|
"num_tokens": 46936640.0,
|
|
"step": 23990
|
|
},
|
|
{
|
|
"entropy": 6.075407457351685,
|
|
"epoch": 2.3985605038236617,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00044274621336653765,
|
|
"loss": 5.7103,
|
|
"mean_token_accuracy": 0.1724499061703682,
|
|
"num_tokens": 46947699.0,
|
|
"step": 23995
|
|
},
|
|
{
|
|
"entropy": 6.036323213577271,
|
|
"epoch": 2.3990603288848904,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00044272242581536457,
|
|
"loss": 5.6662,
|
|
"mean_token_accuracy": 0.17423981577157974,
|
|
"num_tokens": 46956723.0,
|
|
"step": 24000
|
|
},
|
|
{
|
|
"epoch": 2.3990603288848904,
|
|
"eval_entropy": 5.881733407558961,
|
|
"eval_loss": 5.798177242279053,
|
|
"eval_mean_token_accuracy": 0.17727648249220923,
|
|
"eval_num_tokens": 46956723.0,
|
|
"eval_runtime": 23.9274,
|
|
"eval_samples_per_second": 1297.468,
|
|
"eval_steps_per_second": 162.199,
|
|
"step": 24000
|
|
},
|
|
{
|
|
"entropy": 6.0886071681976315,
|
|
"epoch": 2.399560153946119,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00044269863404433846,
|
|
"loss": 5.6744,
|
|
"mean_token_accuracy": 0.17327133417129517,
|
|
"num_tokens": 46966528.0,
|
|
"step": 24005
|
|
},
|
|
{
|
|
"entropy": 6.17800669670105,
|
|
"epoch": 2.4000599790073474,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004426748380540578,
|
|
"loss": 5.7519,
|
|
"mean_token_accuracy": 0.16836042702198029,
|
|
"num_tokens": 46975249.0,
|
|
"step": 24010
|
|
},
|
|
{
|
|
"entropy": 6.030256891250611,
|
|
"epoch": 2.400559804068576,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004426510378451215,
|
|
"loss": 5.708,
|
|
"mean_token_accuracy": 0.17200195789337158,
|
|
"num_tokens": 46985351.0,
|
|
"step": 24015
|
|
},
|
|
{
|
|
"entropy": 6.059681701660156,
|
|
"epoch": 2.4010596291298048,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00044262723341812805,
|
|
"loss": 5.7119,
|
|
"mean_token_accuracy": 0.16935346871614457,
|
|
"num_tokens": 46995529.0,
|
|
"step": 24020
|
|
},
|
|
{
|
|
"entropy": 5.986124515533447,
|
|
"epoch": 2.401559454191033,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004426034247736766,
|
|
"loss": 5.5888,
|
|
"mean_token_accuracy": 0.18175187408924104,
|
|
"num_tokens": 47005058.0,
|
|
"step": 24025
|
|
},
|
|
{
|
|
"entropy": 6.005021429061889,
|
|
"epoch": 2.4020592792522617,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004425796119123662,
|
|
"loss": 5.6559,
|
|
"mean_token_accuracy": 0.17159512490034104,
|
|
"num_tokens": 47015389.0,
|
|
"step": 24030
|
|
},
|
|
{
|
|
"entropy": 6.127612209320068,
|
|
"epoch": 2.4025591043134904,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00044255579483479577,
|
|
"loss": 5.7114,
|
|
"mean_token_accuracy": 0.16607104241847992,
|
|
"num_tokens": 47024918.0,
|
|
"step": 24035
|
|
},
|
|
{
|
|
"entropy": 6.084712314605713,
|
|
"epoch": 2.4030589293747187,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004425319735415647,
|
|
"loss": 5.7793,
|
|
"mean_token_accuracy": 0.16543229371309282,
|
|
"num_tokens": 47035078.0,
|
|
"step": 24040
|
|
},
|
|
{
|
|
"entropy": 6.05713038444519,
|
|
"epoch": 2.4035587544359474,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004425081480332723,
|
|
"loss": 5.7085,
|
|
"mean_token_accuracy": 0.17588661313056947,
|
|
"num_tokens": 47045004.0,
|
|
"step": 24045
|
|
},
|
|
{
|
|
"entropy": 5.99917950630188,
|
|
"epoch": 2.404058579497176,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.000442484318310518,
|
|
"loss": 5.6037,
|
|
"mean_token_accuracy": 0.177299103140831,
|
|
"num_tokens": 47053996.0,
|
|
"step": 24050
|
|
},
|
|
{
|
|
"entropy": 6.015354108810425,
|
|
"epoch": 2.4045584045584047,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00044246048437390133,
|
|
"loss": 5.6805,
|
|
"mean_token_accuracy": 0.1727102130651474,
|
|
"num_tokens": 47063668.0,
|
|
"step": 24055
|
|
},
|
|
{
|
|
"entropy": 6.069788122177124,
|
|
"epoch": 2.405058229619633,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000442436646224022,
|
|
"loss": 5.6962,
|
|
"mean_token_accuracy": 0.17423110455274582,
|
|
"num_tokens": 47073125.0,
|
|
"step": 24060
|
|
},
|
|
{
|
|
"entropy": 6.097348976135254,
|
|
"epoch": 2.4055580546808617,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00044241280386147965,
|
|
"loss": 5.7678,
|
|
"mean_token_accuracy": 0.1661932423710823,
|
|
"num_tokens": 47083502.0,
|
|
"step": 24065
|
|
},
|
|
{
|
|
"entropy": 6.081894588470459,
|
|
"epoch": 2.4060578797420904,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00044238895728687433,
|
|
"loss": 5.6715,
|
|
"mean_token_accuracy": 0.17339230477809905,
|
|
"num_tokens": 47093474.0,
|
|
"step": 24070
|
|
},
|
|
{
|
|
"entropy": 5.969157934188843,
|
|
"epoch": 2.4065577048033187,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004423651065008059,
|
|
"loss": 5.5425,
|
|
"mean_token_accuracy": 0.18471816778182984,
|
|
"num_tokens": 47103349.0,
|
|
"step": 24075
|
|
},
|
|
{
|
|
"entropy": 5.977228307723999,
|
|
"epoch": 2.4070575298645474,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004423412515038744,
|
|
"loss": 5.6301,
|
|
"mean_token_accuracy": 0.17878925204277038,
|
|
"num_tokens": 47112746.0,
|
|
"step": 24080
|
|
},
|
|
{
|
|
"entropy": 6.071626043319702,
|
|
"epoch": 2.407557354925776,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004423173922966802,
|
|
"loss": 5.7192,
|
|
"mean_token_accuracy": 0.17840429544448852,
|
|
"num_tokens": 47122622.0,
|
|
"step": 24085
|
|
},
|
|
{
|
|
"entropy": 6.066196441650391,
|
|
"epoch": 2.4080571799870043,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00044229352887982325,
|
|
"loss": 5.6615,
|
|
"mean_token_accuracy": 0.1730986073613167,
|
|
"num_tokens": 47131529.0,
|
|
"step": 24090
|
|
},
|
|
{
|
|
"entropy": 6.073369455337525,
|
|
"epoch": 2.408557005048233,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00044226966125390435,
|
|
"loss": 5.7627,
|
|
"mean_token_accuracy": 0.17213647812604904,
|
|
"num_tokens": 47141173.0,
|
|
"step": 24095
|
|
},
|
|
{
|
|
"entropy": 6.113953161239624,
|
|
"epoch": 2.4090568301094617,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004422457894195237,
|
|
"loss": 5.833,
|
|
"mean_token_accuracy": 0.16715992242097855,
|
|
"num_tokens": 47150276.0,
|
|
"step": 24100
|
|
},
|
|
{
|
|
"entropy": 6.055497694015503,
|
|
"epoch": 2.4095566551706904,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004422219133772821,
|
|
"loss": 5.6731,
|
|
"mean_token_accuracy": 0.18030701875686644,
|
|
"num_tokens": 47159614.0,
|
|
"step": 24105
|
|
},
|
|
{
|
|
"entropy": 6.137231874465942,
|
|
"epoch": 2.4100564802319187,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004421980331277802,
|
|
"loss": 5.6832,
|
|
"mean_token_accuracy": 0.1692778304219246,
|
|
"num_tokens": 47169082.0,
|
|
"step": 24110
|
|
},
|
|
{
|
|
"entropy": 5.944161748886108,
|
|
"epoch": 2.4105563052931473,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00044217414867161873,
|
|
"loss": 5.5834,
|
|
"mean_token_accuracy": 0.18985380232334137,
|
|
"num_tokens": 47178457.0,
|
|
"step": 24115
|
|
},
|
|
{
|
|
"entropy": 6.016427087783813,
|
|
"epoch": 2.411056130354376,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004421502600093987,
|
|
"loss": 5.6368,
|
|
"mean_token_accuracy": 0.17715291678905487,
|
|
"num_tokens": 47187580.0,
|
|
"step": 24120
|
|
},
|
|
{
|
|
"entropy": 6.063990640640259,
|
|
"epoch": 2.4115559554156043,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00044212636714172115,
|
|
"loss": 5.6248,
|
|
"mean_token_accuracy": 0.1794080287218094,
|
|
"num_tokens": 47197709.0,
|
|
"step": 24125
|
|
},
|
|
{
|
|
"entropy": 6.1067859649658205,
|
|
"epoch": 2.412055780476833,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004421024700691873,
|
|
"loss": 5.7594,
|
|
"mean_token_accuracy": 0.16809295117855072,
|
|
"num_tokens": 47207816.0,
|
|
"step": 24130
|
|
},
|
|
{
|
|
"entropy": 6.077155303955078,
|
|
"epoch": 2.4125556055380617,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004420785687923982,
|
|
"loss": 5.7077,
|
|
"mean_token_accuracy": 0.16664121001958848,
|
|
"num_tokens": 47217434.0,
|
|
"step": 24135
|
|
},
|
|
{
|
|
"entropy": 6.047197389602661,
|
|
"epoch": 2.4130554305992904,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004420546633119554,
|
|
"loss": 5.7096,
|
|
"mean_token_accuracy": 0.17023658007383347,
|
|
"num_tokens": 47227102.0,
|
|
"step": 24140
|
|
},
|
|
{
|
|
"entropy": 6.012833786010742,
|
|
"epoch": 2.4135552556605187,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004420307536284602,
|
|
"loss": 5.576,
|
|
"mean_token_accuracy": 0.1841287985444069,
|
|
"num_tokens": 47235826.0,
|
|
"step": 24145
|
|
},
|
|
{
|
|
"entropy": 6.02816686630249,
|
|
"epoch": 2.4140550807217473,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00044200683974251424,
|
|
"loss": 5.6783,
|
|
"mean_token_accuracy": 0.1801210969686508,
|
|
"num_tokens": 47244168.0,
|
|
"step": 24150
|
|
},
|
|
{
|
|
"entropy": 6.010729503631592,
|
|
"epoch": 2.414554905782976,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004419829216547191,
|
|
"loss": 5.6883,
|
|
"mean_token_accuracy": 0.16944559514522553,
|
|
"num_tokens": 47253437.0,
|
|
"step": 24155
|
|
},
|
|
{
|
|
"entropy": 6.048952674865722,
|
|
"epoch": 2.4150547308442043,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004419589993656767,
|
|
"loss": 5.7062,
|
|
"mean_token_accuracy": 0.17214177250862123,
|
|
"num_tokens": 47263137.0,
|
|
"step": 24160
|
|
},
|
|
{
|
|
"entropy": 6.211365652084351,
|
|
"epoch": 2.415554555905433,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004419350728759888,
|
|
"loss": 5.8338,
|
|
"mean_token_accuracy": 0.16126581355929376,
|
|
"num_tokens": 47273081.0,
|
|
"step": 24165
|
|
},
|
|
{
|
|
"entropy": 6.041406869888306,
|
|
"epoch": 2.4160543809666617,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00044191114218625736,
|
|
"loss": 5.6498,
|
|
"mean_token_accuracy": 0.17959222495555877,
|
|
"num_tokens": 47282500.0,
|
|
"step": 24170
|
|
},
|
|
{
|
|
"entropy": 6.027213096618652,
|
|
"epoch": 2.4165542060278904,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004418872072970846,
|
|
"loss": 5.6105,
|
|
"mean_token_accuracy": 0.18202471733093262,
|
|
"num_tokens": 47291467.0,
|
|
"step": 24175
|
|
},
|
|
{
|
|
"entropy": 6.017886066436768,
|
|
"epoch": 2.4170540310891186,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004418632682090727,
|
|
"loss": 5.654,
|
|
"mean_token_accuracy": 0.17569231390953063,
|
|
"num_tokens": 47302286.0,
|
|
"step": 24180
|
|
},
|
|
{
|
|
"entropy": 6.006929206848144,
|
|
"epoch": 2.4175538561503473,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004418393249228238,
|
|
"loss": 5.5835,
|
|
"mean_token_accuracy": 0.18166396617889405,
|
|
"num_tokens": 47311271.0,
|
|
"step": 24185
|
|
},
|
|
{
|
|
"entropy": 5.954036283493042,
|
|
"epoch": 2.418053681211576,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004418153774389405,
|
|
"loss": 5.5993,
|
|
"mean_token_accuracy": 0.18557493388652802,
|
|
"num_tokens": 47319909.0,
|
|
"step": 24190
|
|
},
|
|
{
|
|
"entropy": 6.005117177963257,
|
|
"epoch": 2.4185535062728043,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004417914257580252,
|
|
"loss": 5.6154,
|
|
"mean_token_accuracy": 0.17638318687677385,
|
|
"num_tokens": 47329422.0,
|
|
"step": 24195
|
|
},
|
|
{
|
|
"entropy": 6.041919708251953,
|
|
"epoch": 2.419053331334033,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004417674698806805,
|
|
"loss": 5.6804,
|
|
"mean_token_accuracy": 0.1688791587948799,
|
|
"num_tokens": 47341287.0,
|
|
"step": 24200
|
|
},
|
|
{
|
|
"entropy": 5.994577550888062,
|
|
"epoch": 2.4195531563952617,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004417435098075093,
|
|
"loss": 5.6237,
|
|
"mean_token_accuracy": 0.17764231860637664,
|
|
"num_tokens": 47350550.0,
|
|
"step": 24205
|
|
},
|
|
{
|
|
"entropy": 6.088534355163574,
|
|
"epoch": 2.4200529814564904,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004417195455391142,
|
|
"loss": 5.7008,
|
|
"mean_token_accuracy": 0.17339558899402618,
|
|
"num_tokens": 47359867.0,
|
|
"step": 24210
|
|
},
|
|
{
|
|
"entropy": 6.051791763305664,
|
|
"epoch": 2.4205528065177186,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00044169557707609826,
|
|
"loss": 5.7001,
|
|
"mean_token_accuracy": 0.16870047003030778,
|
|
"num_tokens": 47368713.0,
|
|
"step": 24215
|
|
},
|
|
{
|
|
"entropy": 5.9937583923339846,
|
|
"epoch": 2.4210526315789473,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004416716044190644,
|
|
"loss": 5.6818,
|
|
"mean_token_accuracy": 0.17313681691884994,
|
|
"num_tokens": 47378404.0,
|
|
"step": 24220
|
|
},
|
|
{
|
|
"entropy": 6.1274638175964355,
|
|
"epoch": 2.421552456640176,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000441647627568616,
|
|
"loss": 5.6739,
|
|
"mean_token_accuracy": 0.17543043792247773,
|
|
"num_tokens": 47387403.0,
|
|
"step": 24225
|
|
},
|
|
{
|
|
"entropy": 6.074211597442627,
|
|
"epoch": 2.4220522817014043,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00044162364652535613,
|
|
"loss": 5.6591,
|
|
"mean_token_accuracy": 0.1743313893675804,
|
|
"num_tokens": 47397322.0,
|
|
"step": 24230
|
|
},
|
|
{
|
|
"entropy": 6.04805850982666,
|
|
"epoch": 2.422552106762633,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004415996612898882,
|
|
"loss": 5.6506,
|
|
"mean_token_accuracy": 0.18012515008449553,
|
|
"num_tokens": 47407827.0,
|
|
"step": 24235
|
|
},
|
|
{
|
|
"entropy": 6.050482702255249,
|
|
"epoch": 2.4230519318238617,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00044157567186281553,
|
|
"loss": 5.7297,
|
|
"mean_token_accuracy": 0.1736801430583,
|
|
"num_tokens": 47418664.0,
|
|
"step": 24240
|
|
},
|
|
{
|
|
"entropy": 5.987440395355224,
|
|
"epoch": 2.4235517568850904,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.000441551678244742,
|
|
"loss": 5.6615,
|
|
"mean_token_accuracy": 0.1768203929066658,
|
|
"num_tokens": 47428399.0,
|
|
"step": 24245
|
|
},
|
|
{
|
|
"entropy": 6.039525270462036,
|
|
"epoch": 2.4240515819463186,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.000441527680436271,
|
|
"loss": 5.6571,
|
|
"mean_token_accuracy": 0.17661914974451065,
|
|
"num_tokens": 47438608.0,
|
|
"step": 24250
|
|
},
|
|
{
|
|
"entropy": 6.026753664016724,
|
|
"epoch": 2.4245514070075473,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00044150367843800645,
|
|
"loss": 5.7134,
|
|
"mean_token_accuracy": 0.17205592840909958,
|
|
"num_tokens": 47447551.0,
|
|
"step": 24255
|
|
},
|
|
{
|
|
"entropy": 5.947839069366455,
|
|
"epoch": 2.425051232068776,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004414796722505522,
|
|
"loss": 5.5513,
|
|
"mean_token_accuracy": 0.18055694103240966,
|
|
"num_tokens": 47456886.0,
|
|
"step": 24260
|
|
},
|
|
{
|
|
"entropy": 6.032843589782715,
|
|
"epoch": 2.4255510571300043,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004414556618745122,
|
|
"loss": 5.6052,
|
|
"mean_token_accuracy": 0.1779559001326561,
|
|
"num_tokens": 47466452.0,
|
|
"step": 24265
|
|
},
|
|
{
|
|
"entropy": 5.951350831985474,
|
|
"epoch": 2.426050882191233,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00044143164731049063,
|
|
"loss": 5.6257,
|
|
"mean_token_accuracy": 0.18754031062126159,
|
|
"num_tokens": 47477390.0,
|
|
"step": 24270
|
|
},
|
|
{
|
|
"entropy": 6.028798532485962,
|
|
"epoch": 2.4265507072524617,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004414076285590916,
|
|
"loss": 5.5864,
|
|
"mean_token_accuracy": 0.18135980367660523,
|
|
"num_tokens": 47487198.0,
|
|
"step": 24275
|
|
},
|
|
{
|
|
"entropy": 6.011521816253662,
|
|
"epoch": 2.4270505323136904,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004413836056209195,
|
|
"loss": 5.5809,
|
|
"mean_token_accuracy": 0.18193985074758529,
|
|
"num_tokens": 47496597.0,
|
|
"step": 24280
|
|
},
|
|
{
|
|
"entropy": 5.9097918510437015,
|
|
"epoch": 2.4275503573749186,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00044135957849657866,
|
|
"loss": 5.5627,
|
|
"mean_token_accuracy": 0.18257229328155516,
|
|
"num_tokens": 47506658.0,
|
|
"step": 24285
|
|
},
|
|
{
|
|
"entropy": 6.0747428894042965,
|
|
"epoch": 2.4280501824361473,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00044133554718667363,
|
|
"loss": 5.6814,
|
|
"mean_token_accuracy": 0.17123400568962097,
|
|
"num_tokens": 47516830.0,
|
|
"step": 24290
|
|
},
|
|
{
|
|
"entropy": 5.9841173648834225,
|
|
"epoch": 2.428550007497376,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00044131151169180905,
|
|
"loss": 5.5814,
|
|
"mean_token_accuracy": 0.1746261328458786,
|
|
"num_tokens": 47526051.0,
|
|
"step": 24295
|
|
},
|
|
{
|
|
"entropy": 5.9733785629272464,
|
|
"epoch": 2.4290498325586043,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00044128747201258956,
|
|
"loss": 5.6949,
|
|
"mean_token_accuracy": 0.17413696944713591,
|
|
"num_tokens": 47535958.0,
|
|
"step": 24300
|
|
},
|
|
{
|
|
"entropy": 6.153683376312256,
|
|
"epoch": 2.429549657619833,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00044126342814962015,
|
|
"loss": 5.6965,
|
|
"mean_token_accuracy": 0.17116239070892333,
|
|
"num_tokens": 47545596.0,
|
|
"step": 24305
|
|
},
|
|
{
|
|
"entropy": 6.1253008365631105,
|
|
"epoch": 2.4300494826810617,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00044123938010350575,
|
|
"loss": 5.7518,
|
|
"mean_token_accuracy": 0.17051671743392943,
|
|
"num_tokens": 47555143.0,
|
|
"step": 24310
|
|
},
|
|
{
|
|
"entropy": 6.041749334335327,
|
|
"epoch": 2.4305493077422904,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00044121532787485114,
|
|
"loss": 5.6419,
|
|
"mean_token_accuracy": 0.17944339364767076,
|
|
"num_tokens": 47564676.0,
|
|
"step": 24315
|
|
},
|
|
{
|
|
"entropy": 6.010359191894532,
|
|
"epoch": 2.4310491328035186,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00044119127146426167,
|
|
"loss": 5.6556,
|
|
"mean_token_accuracy": 0.18615644574165344,
|
|
"num_tokens": 47574082.0,
|
|
"step": 24320
|
|
},
|
|
{
|
|
"entropy": 6.003118181228638,
|
|
"epoch": 2.4315489578647473,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00044116721087234266,
|
|
"loss": 5.6444,
|
|
"mean_token_accuracy": 0.18569766730070114,
|
|
"num_tokens": 47583886.0,
|
|
"step": 24325
|
|
},
|
|
{
|
|
"entropy": 6.141997480392456,
|
|
"epoch": 2.432048782925976,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004411431460996994,
|
|
"loss": 5.7879,
|
|
"mean_token_accuracy": 0.16647899895906448,
|
|
"num_tokens": 47593428.0,
|
|
"step": 24330
|
|
},
|
|
{
|
|
"entropy": 6.072964096069336,
|
|
"epoch": 2.4325486079872043,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004411190771469373,
|
|
"loss": 5.6526,
|
|
"mean_token_accuracy": 0.18052538633346557,
|
|
"num_tokens": 47602321.0,
|
|
"step": 24335
|
|
},
|
|
{
|
|
"entropy": 6.079082345962524,
|
|
"epoch": 2.433048433048433,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00044109500401466194,
|
|
"loss": 5.6469,
|
|
"mean_token_accuracy": 0.17233314961194993,
|
|
"num_tokens": 47611231.0,
|
|
"step": 24340
|
|
},
|
|
{
|
|
"entropy": 6.19488410949707,
|
|
"epoch": 2.4335482581096617,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004410709267034791,
|
|
"loss": 5.7768,
|
|
"mean_token_accuracy": 0.16895080357789993,
|
|
"num_tokens": 47622606.0,
|
|
"step": 24345
|
|
},
|
|
{
|
|
"entropy": 6.030557298660279,
|
|
"epoch": 2.4340480831708904,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00044104684521399434,
|
|
"loss": 5.6469,
|
|
"mean_token_accuracy": 0.1787317380309105,
|
|
"num_tokens": 47632054.0,
|
|
"step": 24350
|
|
},
|
|
{
|
|
"entropy": 6.151304769515991,
|
|
"epoch": 2.4345479082321186,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004410227595468138,
|
|
"loss": 5.8506,
|
|
"mean_token_accuracy": 0.16087090596556664,
|
|
"num_tokens": 47642318.0,
|
|
"step": 24355
|
|
},
|
|
{
|
|
"entropy": 6.148514986038208,
|
|
"epoch": 2.4350477332933473,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00044099866970254327,
|
|
"loss": 5.702,
|
|
"mean_token_accuracy": 0.1726711332798004,
|
|
"num_tokens": 47652467.0,
|
|
"step": 24360
|
|
},
|
|
{
|
|
"entropy": 6.127427101135254,
|
|
"epoch": 2.435547558354576,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00044097457568178903,
|
|
"loss": 5.7168,
|
|
"mean_token_accuracy": 0.1655310273170471,
|
|
"num_tokens": 47661729.0,
|
|
"step": 24365
|
|
},
|
|
{
|
|
"entropy": 5.84200701713562,
|
|
"epoch": 2.4360473834158043,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00044095047748515706,
|
|
"loss": 5.4127,
|
|
"mean_token_accuracy": 0.1986510843038559,
|
|
"num_tokens": 47670937.0,
|
|
"step": 24370
|
|
},
|
|
{
|
|
"entropy": 5.985865211486816,
|
|
"epoch": 2.436547208477033,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00044092637511325384,
|
|
"loss": 5.6527,
|
|
"mean_token_accuracy": 0.17977405488491058,
|
|
"num_tokens": 47680414.0,
|
|
"step": 24375
|
|
},
|
|
{
|
|
"entropy": 6.04291410446167,
|
|
"epoch": 2.4370470335382617,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004409022685666857,
|
|
"loss": 5.6431,
|
|
"mean_token_accuracy": 0.17743666619062423,
|
|
"num_tokens": 47689381.0,
|
|
"step": 24380
|
|
},
|
|
{
|
|
"entropy": 6.079780244827271,
|
|
"epoch": 2.4375468585994904,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004408781578460592,
|
|
"loss": 5.6674,
|
|
"mean_token_accuracy": 0.17873741686344147,
|
|
"num_tokens": 47698810.0,
|
|
"step": 24385
|
|
},
|
|
{
|
|
"entropy": 5.9976438045501705,
|
|
"epoch": 2.4380466836607186,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00044085404295198097,
|
|
"loss": 5.6172,
|
|
"mean_token_accuracy": 0.17635117173194886,
|
|
"num_tokens": 47708396.0,
|
|
"step": 24390
|
|
},
|
|
{
|
|
"entropy": 6.026316118240357,
|
|
"epoch": 2.4385465087219473,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004408299238850576,
|
|
"loss": 5.6091,
|
|
"mean_token_accuracy": 0.16951944679021835,
|
|
"num_tokens": 47717487.0,
|
|
"step": 24395
|
|
},
|
|
{
|
|
"entropy": 6.033814191818237,
|
|
"epoch": 2.439046333783176,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004408058006458961,
|
|
"loss": 5.7216,
|
|
"mean_token_accuracy": 0.17142244130373002,
|
|
"num_tokens": 47727717.0,
|
|
"step": 24400
|
|
},
|
|
{
|
|
"entropy": 5.893590641021729,
|
|
"epoch": 2.4395461588444043,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004407816732351032,
|
|
"loss": 5.4761,
|
|
"mean_token_accuracy": 0.18963074386119844,
|
|
"num_tokens": 47738129.0,
|
|
"step": 24405
|
|
},
|
|
{
|
|
"entropy": 5.992917156219482,
|
|
"epoch": 2.440045983905633,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00044075754165328614,
|
|
"loss": 5.6649,
|
|
"mean_token_accuracy": 0.1790579304099083,
|
|
"num_tokens": 47748130.0,
|
|
"step": 24410
|
|
},
|
|
{
|
|
"entropy": 6.043490314483643,
|
|
"epoch": 2.4405458089668617,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.000440733405901052,
|
|
"loss": 5.6757,
|
|
"mean_token_accuracy": 0.17485827803611756,
|
|
"num_tokens": 47758066.0,
|
|
"step": 24415
|
|
},
|
|
{
|
|
"entropy": 6.028379344940186,
|
|
"epoch": 2.4410456340280904,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00044070926597900804,
|
|
"loss": 5.5763,
|
|
"mean_token_accuracy": 0.18727675527334214,
|
|
"num_tokens": 47767771.0,
|
|
"step": 24420
|
|
},
|
|
{
|
|
"entropy": 6.070698976516724,
|
|
"epoch": 2.4415454590893186,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004406851218877615,
|
|
"loss": 5.6683,
|
|
"mean_token_accuracy": 0.1743554800748825,
|
|
"num_tokens": 47777893.0,
|
|
"step": 24425
|
|
},
|
|
{
|
|
"entropy": 6.001916027069091,
|
|
"epoch": 2.4420452841505473,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00044066097362792,
|
|
"loss": 5.5633,
|
|
"mean_token_accuracy": 0.1817164570093155,
|
|
"num_tokens": 47787804.0,
|
|
"step": 24430
|
|
},
|
|
{
|
|
"entropy": 6.0067119121551515,
|
|
"epoch": 2.442545109211776,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.000440636821200091,
|
|
"loss": 5.6154,
|
|
"mean_token_accuracy": 0.18519625514745713,
|
|
"num_tokens": 47796644.0,
|
|
"step": 24435
|
|
},
|
|
{
|
|
"entropy": 6.0042695045471195,
|
|
"epoch": 2.4430449342730043,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004406126646048822,
|
|
"loss": 5.5761,
|
|
"mean_token_accuracy": 0.18504342138767244,
|
|
"num_tokens": 47806918.0,
|
|
"step": 24440
|
|
},
|
|
{
|
|
"entropy": 6.072028303146363,
|
|
"epoch": 2.443544759334233,
|
|
"grad_norm": 2.328125,
|
|
"learning_rate": 0.0004405885038429014,
|
|
"loss": 5.5367,
|
|
"mean_token_accuracy": 0.19558241665363313,
|
|
"num_tokens": 47817167.0,
|
|
"step": 24445
|
|
},
|
|
{
|
|
"entropy": 6.075762987136841,
|
|
"epoch": 2.4440445843954617,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00044056433891475645,
|
|
"loss": 5.6998,
|
|
"mean_token_accuracy": 0.17425734251737596,
|
|
"num_tokens": 47826363.0,
|
|
"step": 24450
|
|
},
|
|
{
|
|
"entropy": 5.977590084075928,
|
|
"epoch": 2.4445444094566904,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004405401698210553,
|
|
"loss": 5.6086,
|
|
"mean_token_accuracy": 0.16660034731030465,
|
|
"num_tokens": 47837427.0,
|
|
"step": 24455
|
|
},
|
|
{
|
|
"entropy": 6.066119718551636,
|
|
"epoch": 2.4450442345179186,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004405159965624061,
|
|
"loss": 5.7299,
|
|
"mean_token_accuracy": 0.1705239325761795,
|
|
"num_tokens": 47846619.0,
|
|
"step": 24460
|
|
},
|
|
{
|
|
"entropy": 6.122731924057007,
|
|
"epoch": 2.4455440595791473,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.000440491819139417,
|
|
"loss": 5.6977,
|
|
"mean_token_accuracy": 0.16786837428808213,
|
|
"num_tokens": 47856577.0,
|
|
"step": 24465
|
|
},
|
|
{
|
|
"entropy": 6.016014146804809,
|
|
"epoch": 2.446043884640376,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004404676375526963,
|
|
"loss": 5.6132,
|
|
"mean_token_accuracy": 0.18026182651519776,
|
|
"num_tokens": 47865855.0,
|
|
"step": 24470
|
|
},
|
|
{
|
|
"entropy": 6.003352880477905,
|
|
"epoch": 2.4465437097016043,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00044044345180285245,
|
|
"loss": 5.6481,
|
|
"mean_token_accuracy": 0.18003834784030914,
|
|
"num_tokens": 47875074.0,
|
|
"step": 24475
|
|
},
|
|
{
|
|
"entropy": 6.069564294815064,
|
|
"epoch": 2.447043534762833,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.000440419261890494,
|
|
"loss": 5.7447,
|
|
"mean_token_accuracy": 0.1670381799340248,
|
|
"num_tokens": 47885159.0,
|
|
"step": 24480
|
|
},
|
|
{
|
|
"entropy": 6.025638580322266,
|
|
"epoch": 2.4475433598240617,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00044039506781622936,
|
|
"loss": 5.664,
|
|
"mean_token_accuracy": 0.18072758615016937,
|
|
"num_tokens": 47895082.0,
|
|
"step": 24485
|
|
},
|
|
{
|
|
"entropy": 5.983976984024048,
|
|
"epoch": 2.4480431848852904,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004403708695806674,
|
|
"loss": 5.6192,
|
|
"mean_token_accuracy": 0.18566812574863434,
|
|
"num_tokens": 47905428.0,
|
|
"step": 24490
|
|
},
|
|
{
|
|
"entropy": 5.996654272079468,
|
|
"epoch": 2.4485430099465186,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004403466671844169,
|
|
"loss": 5.4818,
|
|
"mean_token_accuracy": 0.19790310859680177,
|
|
"num_tokens": 47914803.0,
|
|
"step": 24495
|
|
},
|
|
{
|
|
"entropy": 6.015547800064087,
|
|
"epoch": 2.4490428350077473,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004403224606280869,
|
|
"loss": 5.6354,
|
|
"mean_token_accuracy": 0.17807949483394622,
|
|
"num_tokens": 47924276.0,
|
|
"step": 24500
|
|
},
|
|
{
|
|
"entropy": 6.077470159530639,
|
|
"epoch": 2.449542660068976,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004402982499122862,
|
|
"loss": 5.7176,
|
|
"mean_token_accuracy": 0.17317877113819122,
|
|
"num_tokens": 47934980.0,
|
|
"step": 24505
|
|
},
|
|
{
|
|
"entropy": 6.128697633743286,
|
|
"epoch": 2.4500424851302043,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00044027403503762416,
|
|
"loss": 5.6989,
|
|
"mean_token_accuracy": 0.17180401533842088,
|
|
"num_tokens": 47944925.0,
|
|
"step": 24510
|
|
},
|
|
{
|
|
"entropy": 6.117228984832764,
|
|
"epoch": 2.450542310191433,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004402498160047099,
|
|
"loss": 5.6837,
|
|
"mean_token_accuracy": 0.1713176652789116,
|
|
"num_tokens": 47954324.0,
|
|
"step": 24515
|
|
},
|
|
{
|
|
"entropy": 6.012296199798584,
|
|
"epoch": 2.4510421352526617,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004402255928141528,
|
|
"loss": 5.6256,
|
|
"mean_token_accuracy": 0.17892444431781768,
|
|
"num_tokens": 47964333.0,
|
|
"step": 24520
|
|
},
|
|
{
|
|
"entropy": 6.100943613052368,
|
|
"epoch": 2.4515419603138904,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004402013654665623,
|
|
"loss": 5.7474,
|
|
"mean_token_accuracy": 0.1625466004014015,
|
|
"num_tokens": 47973790.0,
|
|
"step": 24525
|
|
},
|
|
{
|
|
"entropy": 6.041972970962524,
|
|
"epoch": 2.4520417853751186,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00044017713396254796,
|
|
"loss": 5.7081,
|
|
"mean_token_accuracy": 0.17599491775035858,
|
|
"num_tokens": 47983756.0,
|
|
"step": 24530
|
|
},
|
|
{
|
|
"entropy": 6.058880472183228,
|
|
"epoch": 2.4525416104363473,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00044015289830271945,
|
|
"loss": 5.6809,
|
|
"mean_token_accuracy": 0.17530606985092162,
|
|
"num_tokens": 47993605.0,
|
|
"step": 24535
|
|
},
|
|
{
|
|
"entropy": 6.024312162399292,
|
|
"epoch": 2.453041435497576,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00044012865848768644,
|
|
"loss": 5.6575,
|
|
"mean_token_accuracy": 0.17828157246112825,
|
|
"num_tokens": 48003553.0,
|
|
"step": 24540
|
|
},
|
|
{
|
|
"entropy": 6.111248302459717,
|
|
"epoch": 2.4535412605588043,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00044010441451805896,
|
|
"loss": 5.7564,
|
|
"mean_token_accuracy": 0.16948112696409226,
|
|
"num_tokens": 48015074.0,
|
|
"step": 24545
|
|
},
|
|
{
|
|
"entropy": 6.113588857650757,
|
|
"epoch": 2.454041085620033,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004400801663944468,
|
|
"loss": 5.6935,
|
|
"mean_token_accuracy": 0.17283657640218736,
|
|
"num_tokens": 48024392.0,
|
|
"step": 24550
|
|
},
|
|
{
|
|
"entropy": 6.026064777374268,
|
|
"epoch": 2.4545409106812617,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00044005591411746023,
|
|
"loss": 5.6229,
|
|
"mean_token_accuracy": 0.17521522790193558,
|
|
"num_tokens": 48034626.0,
|
|
"step": 24555
|
|
},
|
|
{
|
|
"entropy": 5.985178852081299,
|
|
"epoch": 2.4550407357424904,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00044003165768770927,
|
|
"loss": 5.5468,
|
|
"mean_token_accuracy": 0.18266777992248534,
|
|
"num_tokens": 48044542.0,
|
|
"step": 24560
|
|
},
|
|
{
|
|
"entropy": 6.0234438419342045,
|
|
"epoch": 2.4555405608037186,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004400073971058043,
|
|
"loss": 5.6395,
|
|
"mean_token_accuracy": 0.17600957602262496,
|
|
"num_tokens": 48053951.0,
|
|
"step": 24565
|
|
},
|
|
{
|
|
"entropy": 6.157665824890136,
|
|
"epoch": 2.4560403858649473,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00043998313237235566,
|
|
"loss": 5.7571,
|
|
"mean_token_accuracy": 0.16373063921928405,
|
|
"num_tokens": 48064587.0,
|
|
"step": 24570
|
|
},
|
|
{
|
|
"entropy": 6.069653081893921,
|
|
"epoch": 2.456540210926176,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004399588634879739,
|
|
"loss": 5.6738,
|
|
"mean_token_accuracy": 0.1764748603105545,
|
|
"num_tokens": 48074204.0,
|
|
"step": 24575
|
|
},
|
|
{
|
|
"entropy": 6.06509485244751,
|
|
"epoch": 2.4570400359874043,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004399345904532695,
|
|
"loss": 5.6491,
|
|
"mean_token_accuracy": 0.17649355083703994,
|
|
"num_tokens": 48084617.0,
|
|
"step": 24580
|
|
},
|
|
{
|
|
"entropy": 6.087675523757935,
|
|
"epoch": 2.457539861048633,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004399103132688533,
|
|
"loss": 5.6632,
|
|
"mean_token_accuracy": 0.179979407787323,
|
|
"num_tokens": 48094333.0,
|
|
"step": 24585
|
|
},
|
|
{
|
|
"entropy": 6.011349201202393,
|
|
"epoch": 2.4580396861098617,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00043988603193533606,
|
|
"loss": 5.7011,
|
|
"mean_token_accuracy": 0.17612486630678176,
|
|
"num_tokens": 48104639.0,
|
|
"step": 24590
|
|
},
|
|
{
|
|
"entropy": 5.986402559280395,
|
|
"epoch": 2.45853951117109,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004398617464533287,
|
|
"loss": 5.6403,
|
|
"mean_token_accuracy": 0.18223071247339248,
|
|
"num_tokens": 48115291.0,
|
|
"step": 24595
|
|
},
|
|
{
|
|
"entropy": 6.088130044937134,
|
|
"epoch": 2.4590393362323186,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004398374568234422,
|
|
"loss": 5.7347,
|
|
"mean_token_accuracy": 0.1727553963661194,
|
|
"num_tokens": 48124351.0,
|
|
"step": 24600
|
|
},
|
|
{
|
|
"entropy": 6.078551959991455,
|
|
"epoch": 2.4595391612935473,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004398131630462877,
|
|
"loss": 5.6585,
|
|
"mean_token_accuracy": 0.17796149402856826,
|
|
"num_tokens": 48134236.0,
|
|
"step": 24605
|
|
},
|
|
{
|
|
"entropy": 6.029651117324829,
|
|
"epoch": 2.4600389863547756,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00043978886512247646,
|
|
"loss": 5.6685,
|
|
"mean_token_accuracy": 0.17485146969556808,
|
|
"num_tokens": 48143569.0,
|
|
"step": 24610
|
|
},
|
|
{
|
|
"entropy": 6.037168312072754,
|
|
"epoch": 2.4605388114160043,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004397645630526197,
|
|
"loss": 5.6777,
|
|
"mean_token_accuracy": 0.17613199800252916,
|
|
"num_tokens": 48153856.0,
|
|
"step": 24615
|
|
},
|
|
{
|
|
"entropy": 6.018367290496826,
|
|
"epoch": 2.461038636477233,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000439740256837329,
|
|
"loss": 5.6497,
|
|
"mean_token_accuracy": 0.1798037827014923,
|
|
"num_tokens": 48163131.0,
|
|
"step": 24620
|
|
},
|
|
{
|
|
"entropy": 6.088261842727661,
|
|
"epoch": 2.4615384615384617,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004397159464772158,
|
|
"loss": 5.7282,
|
|
"mean_token_accuracy": 0.1652219533920288,
|
|
"num_tokens": 48174717.0,
|
|
"step": 24625
|
|
},
|
|
{
|
|
"entropy": 6.031934356689453,
|
|
"epoch": 2.46203828659969,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00043969163197289174,
|
|
"loss": 5.6115,
|
|
"mean_token_accuracy": 0.1743137001991272,
|
|
"num_tokens": 48186207.0,
|
|
"step": 24630
|
|
},
|
|
{
|
|
"entropy": 6.020684719085693,
|
|
"epoch": 2.4625381116609186,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004396673133249687,
|
|
"loss": 5.6611,
|
|
"mean_token_accuracy": 0.16944748759269715,
|
|
"num_tokens": 48196939.0,
|
|
"step": 24635
|
|
},
|
|
{
|
|
"entropy": 5.9944745063781735,
|
|
"epoch": 2.4630379367221473,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004396429905340584,
|
|
"loss": 5.6614,
|
|
"mean_token_accuracy": 0.17896944880485535,
|
|
"num_tokens": 48208388.0,
|
|
"step": 24640
|
|
},
|
|
{
|
|
"entropy": 6.106299829483032,
|
|
"epoch": 2.4635377617833756,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00043961866360077266,
|
|
"loss": 5.6711,
|
|
"mean_token_accuracy": 0.17626942694187164,
|
|
"num_tokens": 48218272.0,
|
|
"step": 24645
|
|
},
|
|
{
|
|
"entropy": 6.058535385131836,
|
|
"epoch": 2.4640375868446043,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004395943325257239,
|
|
"loss": 5.6801,
|
|
"mean_token_accuracy": 0.18019117861986161,
|
|
"num_tokens": 48227526.0,
|
|
"step": 24650
|
|
},
|
|
{
|
|
"entropy": 5.991103553771973,
|
|
"epoch": 2.464537411905833,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00043956999730952403,
|
|
"loss": 5.6277,
|
|
"mean_token_accuracy": 0.1811704531311989,
|
|
"num_tokens": 48237181.0,
|
|
"step": 24655
|
|
},
|
|
{
|
|
"entropy": 6.001305103302002,
|
|
"epoch": 2.4650372369670617,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00043954565795278536,
|
|
"loss": 5.5765,
|
|
"mean_token_accuracy": 0.18929771482944488,
|
|
"num_tokens": 48245338.0,
|
|
"step": 24660
|
|
},
|
|
{
|
|
"entropy": 6.025060939788818,
|
|
"epoch": 2.46553706202829,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004395213144561203,
|
|
"loss": 5.699,
|
|
"mean_token_accuracy": 0.17592445015907288,
|
|
"num_tokens": 48254927.0,
|
|
"step": 24665
|
|
},
|
|
{
|
|
"entropy": 6.056041479110718,
|
|
"epoch": 2.4660368870895186,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004394969668201413,
|
|
"loss": 5.7245,
|
|
"mean_token_accuracy": 0.18004821985960007,
|
|
"num_tokens": 48266170.0,
|
|
"step": 24670
|
|
},
|
|
{
|
|
"entropy": 6.0218846797943115,
|
|
"epoch": 2.4665367121507473,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004394726150454609,
|
|
"loss": 5.6163,
|
|
"mean_token_accuracy": 0.18188352435827254,
|
|
"num_tokens": 48276216.0,
|
|
"step": 24675
|
|
},
|
|
{
|
|
"entropy": 6.033428764343261,
|
|
"epoch": 2.4670365372119756,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004394482591326918,
|
|
"loss": 5.7168,
|
|
"mean_token_accuracy": 0.17433317452669145,
|
|
"num_tokens": 48285677.0,
|
|
"step": 24680
|
|
},
|
|
{
|
|
"entropy": 6.1054717063903805,
|
|
"epoch": 2.4675363622732043,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00043942389908244693,
|
|
"loss": 5.6901,
|
|
"mean_token_accuracy": 0.17648373544216156,
|
|
"num_tokens": 48297252.0,
|
|
"step": 24685
|
|
},
|
|
{
|
|
"entropy": 5.9974500179290775,
|
|
"epoch": 2.468036187334433,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000439399534895339,
|
|
"loss": 5.5591,
|
|
"mean_token_accuracy": 0.17997117340564728,
|
|
"num_tokens": 48306507.0,
|
|
"step": 24690
|
|
},
|
|
{
|
|
"entropy": 5.989813899993896,
|
|
"epoch": 2.4685360123956617,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004393751665719811,
|
|
"loss": 5.6335,
|
|
"mean_token_accuracy": 0.17677572816610337,
|
|
"num_tokens": 48316323.0,
|
|
"step": 24695
|
|
},
|
|
{
|
|
"entropy": 6.054601764678955,
|
|
"epoch": 2.46903583745689,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004393507941129863,
|
|
"loss": 5.6545,
|
|
"mean_token_accuracy": 0.1707194611430168,
|
|
"num_tokens": 48326007.0,
|
|
"step": 24700
|
|
},
|
|
{
|
|
"entropy": 6.01278076171875,
|
|
"epoch": 2.4695356625181186,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004393264175189678,
|
|
"loss": 5.6586,
|
|
"mean_token_accuracy": 0.17540258914232254,
|
|
"num_tokens": 48335291.0,
|
|
"step": 24705
|
|
},
|
|
{
|
|
"entropy": 6.126325702667236,
|
|
"epoch": 2.4700354875793473,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00043930203679053885,
|
|
"loss": 5.6903,
|
|
"mean_token_accuracy": 0.17212548702955247,
|
|
"num_tokens": 48345078.0,
|
|
"step": 24710
|
|
},
|
|
{
|
|
"entropy": 6.065726852416992,
|
|
"epoch": 2.4705353126405756,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00043927765192831305,
|
|
"loss": 5.7214,
|
|
"mean_token_accuracy": 0.17699576020240784,
|
|
"num_tokens": 48354329.0,
|
|
"step": 24715
|
|
},
|
|
{
|
|
"entropy": 6.021416091918946,
|
|
"epoch": 2.4710351377018043,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004392532629329038,
|
|
"loss": 5.6941,
|
|
"mean_token_accuracy": 0.1763074889779091,
|
|
"num_tokens": 48363261.0,
|
|
"step": 24720
|
|
},
|
|
{
|
|
"entropy": 6.064648628234863,
|
|
"epoch": 2.471534962763033,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00043922886980492465,
|
|
"loss": 5.6894,
|
|
"mean_token_accuracy": 0.1752315416932106,
|
|
"num_tokens": 48372389.0,
|
|
"step": 24725
|
|
},
|
|
{
|
|
"entropy": 6.183157205581665,
|
|
"epoch": 2.4720347878242617,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00043920447254498947,
|
|
"loss": 5.7876,
|
|
"mean_token_accuracy": 0.16744272857904435,
|
|
"num_tokens": 48381553.0,
|
|
"step": 24730
|
|
},
|
|
{
|
|
"entropy": 6.1046816349029545,
|
|
"epoch": 2.47253461288549,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004391800711537119,
|
|
"loss": 5.6574,
|
|
"mean_token_accuracy": 0.17658925354480742,
|
|
"num_tokens": 48391356.0,
|
|
"step": 24735
|
|
},
|
|
{
|
|
"entropy": 6.075534057617188,
|
|
"epoch": 2.4730344379467186,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.00043915566563170605,
|
|
"loss": 5.7266,
|
|
"mean_token_accuracy": 0.17053902596235276,
|
|
"num_tokens": 48401092.0,
|
|
"step": 24740
|
|
},
|
|
{
|
|
"entropy": 6.0742968082427975,
|
|
"epoch": 2.4735342630079473,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00043913125597958594,
|
|
"loss": 5.7813,
|
|
"mean_token_accuracy": 0.1680430732667446,
|
|
"num_tokens": 48411891.0,
|
|
"step": 24745
|
|
},
|
|
{
|
|
"entropy": 6.072730207443238,
|
|
"epoch": 2.4740340880691756,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00043910684219796564,
|
|
"loss": 5.7049,
|
|
"mean_token_accuracy": 0.17399029284715653,
|
|
"num_tokens": 48421393.0,
|
|
"step": 24750
|
|
},
|
|
{
|
|
"entropy": 6.061235666275024,
|
|
"epoch": 2.4745339131304043,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00043908242428745937,
|
|
"loss": 5.6601,
|
|
"mean_token_accuracy": 0.1732328101992607,
|
|
"num_tokens": 48431485.0,
|
|
"step": 24755
|
|
},
|
|
{
|
|
"entropy": 6.070634222030639,
|
|
"epoch": 2.475033738191633,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00043905800224868153,
|
|
"loss": 5.6788,
|
|
"mean_token_accuracy": 0.17557214796543122,
|
|
"num_tokens": 48440997.0,
|
|
"step": 24760
|
|
},
|
|
{
|
|
"entropy": 6.013326120376587,
|
|
"epoch": 2.4755335632528617,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004390335760822466,
|
|
"loss": 5.68,
|
|
"mean_token_accuracy": 0.17213184982538224,
|
|
"num_tokens": 48451043.0,
|
|
"step": 24765
|
|
},
|
|
{
|
|
"entropy": 5.978026485443115,
|
|
"epoch": 2.47603338831409,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004390091457887691,
|
|
"loss": 5.6092,
|
|
"mean_token_accuracy": 0.17387280464172364,
|
|
"num_tokens": 48460776.0,
|
|
"step": 24770
|
|
},
|
|
{
|
|
"entropy": 6.028924131393433,
|
|
"epoch": 2.4765332133753186,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004389847113688637,
|
|
"loss": 5.6483,
|
|
"mean_token_accuracy": 0.1689825102686882,
|
|
"num_tokens": 48470095.0,
|
|
"step": 24775
|
|
},
|
|
{
|
|
"entropy": 6.037907648086548,
|
|
"epoch": 2.4770330384365473,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00043896027282314516,
|
|
"loss": 5.6858,
|
|
"mean_token_accuracy": 0.17004235684871674,
|
|
"num_tokens": 48480977.0,
|
|
"step": 24780
|
|
},
|
|
{
|
|
"entropy": 5.98356671333313,
|
|
"epoch": 2.4775328634977756,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004389358301522283,
|
|
"loss": 5.6445,
|
|
"mean_token_accuracy": 0.17499774396419526,
|
|
"num_tokens": 48490547.0,
|
|
"step": 24785
|
|
},
|
|
{
|
|
"entropy": 6.084045362472534,
|
|
"epoch": 2.4780326885590043,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00043891138335672825,
|
|
"loss": 5.6789,
|
|
"mean_token_accuracy": 0.16913772523403167,
|
|
"num_tokens": 48500358.0,
|
|
"step": 24790
|
|
},
|
|
{
|
|
"entropy": 6.056918811798096,
|
|
"epoch": 2.478532513620233,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004388869324372599,
|
|
"loss": 5.755,
|
|
"mean_token_accuracy": 0.1702621877193451,
|
|
"num_tokens": 48509175.0,
|
|
"step": 24795
|
|
},
|
|
{
|
|
"entropy": 6.056420946121216,
|
|
"epoch": 2.4790323386814617,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004388624773944385,
|
|
"loss": 5.7021,
|
|
"mean_token_accuracy": 0.17036577314138412,
|
|
"num_tokens": 48518620.0,
|
|
"step": 24800
|
|
},
|
|
{
|
|
"entropy": 6.053989601135254,
|
|
"epoch": 2.47953216374269,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00043883801822887933,
|
|
"loss": 5.6493,
|
|
"mean_token_accuracy": 0.18541426211595535,
|
|
"num_tokens": 48527609.0,
|
|
"step": 24805
|
|
},
|
|
{
|
|
"entropy": 6.05877652168274,
|
|
"epoch": 2.4800319888039186,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00043881355494119773,
|
|
"loss": 5.6559,
|
|
"mean_token_accuracy": 0.17418801188468933,
|
|
"num_tokens": 48538002.0,
|
|
"step": 24810
|
|
},
|
|
{
|
|
"entropy": 6.017501783370972,
|
|
"epoch": 2.4805318138651473,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004387890875320093,
|
|
"loss": 5.6206,
|
|
"mean_token_accuracy": 0.17705588638782502,
|
|
"num_tokens": 48546939.0,
|
|
"step": 24815
|
|
},
|
|
{
|
|
"entropy": 6.030125284194947,
|
|
"epoch": 2.4810316389263756,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00043876461600192955,
|
|
"loss": 5.6179,
|
|
"mean_token_accuracy": 0.18173117339611053,
|
|
"num_tokens": 48556431.0,
|
|
"step": 24820
|
|
},
|
|
{
|
|
"entropy": 5.995352077484131,
|
|
"epoch": 2.4815314639876043,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004387401403515743,
|
|
"loss": 5.6367,
|
|
"mean_token_accuracy": 0.18165358006954194,
|
|
"num_tokens": 48565993.0,
|
|
"step": 24825
|
|
},
|
|
{
|
|
"entropy": 6.000512981414795,
|
|
"epoch": 2.482031289048833,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00043871566058155913,
|
|
"loss": 5.6332,
|
|
"mean_token_accuracy": 0.18515712171792983,
|
|
"num_tokens": 48575324.0,
|
|
"step": 24830
|
|
},
|
|
{
|
|
"entropy": 6.080173826217651,
|
|
"epoch": 2.4825311141100617,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00043869117669250015,
|
|
"loss": 5.687,
|
|
"mean_token_accuracy": 0.17079694718122482,
|
|
"num_tokens": 48584432.0,
|
|
"step": 24835
|
|
},
|
|
{
|
|
"entropy": 6.041371250152588,
|
|
"epoch": 2.48303093917129,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004386666886850132,
|
|
"loss": 5.7027,
|
|
"mean_token_accuracy": 0.17087610214948654,
|
|
"num_tokens": 48595459.0,
|
|
"step": 24840
|
|
},
|
|
{
|
|
"entropy": 6.061032485961914,
|
|
"epoch": 2.4835307642325186,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00043864219655971457,
|
|
"loss": 5.669,
|
|
"mean_token_accuracy": 0.17133895605802535,
|
|
"num_tokens": 48605505.0,
|
|
"step": 24845
|
|
},
|
|
{
|
|
"entropy": 6.0473291873931885,
|
|
"epoch": 2.4840305892937473,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004386177003172203,
|
|
"loss": 5.5914,
|
|
"mean_token_accuracy": 0.18423412442207338,
|
|
"num_tokens": 48615237.0,
|
|
"step": 24850
|
|
},
|
|
{
|
|
"entropy": 6.1022240161895756,
|
|
"epoch": 2.4845304143549756,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00043859319995814686,
|
|
"loss": 5.7029,
|
|
"mean_token_accuracy": 0.17156235724687577,
|
|
"num_tokens": 48625711.0,
|
|
"step": 24855
|
|
},
|
|
{
|
|
"entropy": 6.099638366699219,
|
|
"epoch": 2.4850302394162043,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004385686954831105,
|
|
"loss": 5.6492,
|
|
"mean_token_accuracy": 0.17525752633810043,
|
|
"num_tokens": 48636091.0,
|
|
"step": 24860
|
|
},
|
|
{
|
|
"entropy": 5.932737588882446,
|
|
"epoch": 2.485530064477433,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00043854418689272793,
|
|
"loss": 5.53,
|
|
"mean_token_accuracy": 0.1806458741426468,
|
|
"num_tokens": 48645891.0,
|
|
"step": 24865
|
|
},
|
|
{
|
|
"entropy": 5.9988641262054445,
|
|
"epoch": 2.4860298895386617,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00043851967418761574,
|
|
"loss": 5.6744,
|
|
"mean_token_accuracy": 0.17858005166053773,
|
|
"num_tokens": 48657197.0,
|
|
"step": 24870
|
|
},
|
|
{
|
|
"entropy": 6.018079137802124,
|
|
"epoch": 2.48652971459989,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00043849515736839057,
|
|
"loss": 5.6472,
|
|
"mean_token_accuracy": 0.18111660778522493,
|
|
"num_tokens": 48666325.0,
|
|
"step": 24875
|
|
},
|
|
{
|
|
"entropy": 6.083094835281372,
|
|
"epoch": 2.4870295396611186,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00043847063643566935,
|
|
"loss": 5.6706,
|
|
"mean_token_accuracy": 0.1727414146065712,
|
|
"num_tokens": 48676208.0,
|
|
"step": 24880
|
|
},
|
|
{
|
|
"entropy": 6.071585369110108,
|
|
"epoch": 2.4875293647223473,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00043844611139006893,
|
|
"loss": 5.7281,
|
|
"mean_token_accuracy": 0.175820954144001,
|
|
"num_tokens": 48685809.0,
|
|
"step": 24885
|
|
},
|
|
{
|
|
"entropy": 6.103422212600708,
|
|
"epoch": 2.4880291897835756,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00043842158223220644,
|
|
"loss": 5.7449,
|
|
"mean_token_accuracy": 0.16867251992225646,
|
|
"num_tokens": 48696029.0,
|
|
"step": 24890
|
|
},
|
|
{
|
|
"entropy": 6.019418478012085,
|
|
"epoch": 2.4885290148448043,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.000438397048962699,
|
|
"loss": 5.592,
|
|
"mean_token_accuracy": 0.18222148418426515,
|
|
"num_tokens": 48704858.0,
|
|
"step": 24895
|
|
},
|
|
{
|
|
"entropy": 6.032077503204346,
|
|
"epoch": 2.489028839906033,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00043837251158216386,
|
|
"loss": 5.729,
|
|
"mean_token_accuracy": 0.17725322842597963,
|
|
"num_tokens": 48715120.0,
|
|
"step": 24900
|
|
},
|
|
{
|
|
"entropy": 6.081197690963745,
|
|
"epoch": 2.4895286649672617,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00043834797009121836,
|
|
"loss": 5.6785,
|
|
"mean_token_accuracy": 0.17532220035791396,
|
|
"num_tokens": 48725156.0,
|
|
"step": 24905
|
|
},
|
|
{
|
|
"entropy": 6.015300512313843,
|
|
"epoch": 2.49002849002849,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00043832342449047994,
|
|
"loss": 5.633,
|
|
"mean_token_accuracy": 0.17894736230373381,
|
|
"num_tokens": 48734799.0,
|
|
"step": 24910
|
|
},
|
|
{
|
|
"entropy": 6.01845645904541,
|
|
"epoch": 2.4905283150897186,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004382988747805661,
|
|
"loss": 5.6684,
|
|
"mean_token_accuracy": 0.17747225761413574,
|
|
"num_tokens": 48744414.0,
|
|
"step": 24915
|
|
},
|
|
{
|
|
"entropy": 6.057831811904907,
|
|
"epoch": 2.4910281401509473,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004382743209620948,
|
|
"loss": 5.7647,
|
|
"mean_token_accuracy": 0.17230988293886185,
|
|
"num_tokens": 48754390.0,
|
|
"step": 24920
|
|
},
|
|
{
|
|
"entropy": 6.093270587921142,
|
|
"epoch": 2.4915279652121756,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004382497630356835,
|
|
"loss": 5.6438,
|
|
"mean_token_accuracy": 0.17218891978263856,
|
|
"num_tokens": 48764517.0,
|
|
"step": 24925
|
|
},
|
|
{
|
|
"entropy": 6.088988590240478,
|
|
"epoch": 2.4920277902734043,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00043822520100195015,
|
|
"loss": 5.676,
|
|
"mean_token_accuracy": 0.17241186052560806,
|
|
"num_tokens": 48774767.0,
|
|
"step": 24930
|
|
},
|
|
{
|
|
"entropy": 6.081583642959595,
|
|
"epoch": 2.492527615334633,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00043820063486151267,
|
|
"loss": 5.6931,
|
|
"mean_token_accuracy": 0.17162569761276245,
|
|
"num_tokens": 48784279.0,
|
|
"step": 24935
|
|
},
|
|
{
|
|
"entropy": 6.07888822555542,
|
|
"epoch": 2.4930274403958617,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00043817606461498933,
|
|
"loss": 5.5979,
|
|
"mean_token_accuracy": 0.18594349771738053,
|
|
"num_tokens": 48794179.0,
|
|
"step": 24940
|
|
},
|
|
{
|
|
"entropy": 5.994911336898804,
|
|
"epoch": 2.49352726545709,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00043815149026299823,
|
|
"loss": 5.6069,
|
|
"mean_token_accuracy": 0.17567966282367706,
|
|
"num_tokens": 48804593.0,
|
|
"step": 24945
|
|
},
|
|
{
|
|
"entropy": 5.969489431381225,
|
|
"epoch": 2.4940270905183186,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004381269118061575,
|
|
"loss": 5.5932,
|
|
"mean_token_accuracy": 0.18388954252004625,
|
|
"num_tokens": 48813280.0,
|
|
"step": 24950
|
|
},
|
|
{
|
|
"entropy": 6.002853441238403,
|
|
"epoch": 2.4945269155795473,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004381023292450857,
|
|
"loss": 5.6071,
|
|
"mean_token_accuracy": 0.1815829947590828,
|
|
"num_tokens": 48823830.0,
|
|
"step": 24955
|
|
},
|
|
{
|
|
"entropy": 5.961542177200317,
|
|
"epoch": 2.4950267406407756,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004380777425804012,
|
|
"loss": 5.5549,
|
|
"mean_token_accuracy": 0.1831890657544136,
|
|
"num_tokens": 48833277.0,
|
|
"step": 24960
|
|
},
|
|
{
|
|
"entropy": 6.014238357543945,
|
|
"epoch": 2.4955265657020043,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00043805315181272275,
|
|
"loss": 5.6319,
|
|
"mean_token_accuracy": 0.17295539677143096,
|
|
"num_tokens": 48842718.0,
|
|
"step": 24965
|
|
},
|
|
{
|
|
"entropy": 6.0162327766418455,
|
|
"epoch": 2.496026390763233,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004380285569426689,
|
|
"loss": 5.7473,
|
|
"mean_token_accuracy": 0.16822484284639358,
|
|
"num_tokens": 48852831.0,
|
|
"step": 24970
|
|
},
|
|
{
|
|
"entropy": 5.953922939300537,
|
|
"epoch": 2.4965262158244617,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004380039579708586,
|
|
"loss": 5.6079,
|
|
"mean_token_accuracy": 0.18049888908863068,
|
|
"num_tokens": 48862188.0,
|
|
"step": 24975
|
|
},
|
|
{
|
|
"entropy": 6.068013763427734,
|
|
"epoch": 2.49702604088569,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004379793548979105,
|
|
"loss": 5.5995,
|
|
"mean_token_accuracy": 0.1796725019812584,
|
|
"num_tokens": 48872817.0,
|
|
"step": 24980
|
|
},
|
|
{
|
|
"entropy": 6.0064770698547365,
|
|
"epoch": 2.4975258659469186,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004379547477244439,
|
|
"loss": 5.6005,
|
|
"mean_token_accuracy": 0.18310548961162568,
|
|
"num_tokens": 48882233.0,
|
|
"step": 24985
|
|
},
|
|
{
|
|
"entropy": 6.026395034790039,
|
|
"epoch": 2.4980256910081473,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004379301364510777,
|
|
"loss": 5.696,
|
|
"mean_token_accuracy": 0.17601963579654695,
|
|
"num_tokens": 48893534.0,
|
|
"step": 24990
|
|
},
|
|
{
|
|
"entropy": 6.0045738697052,
|
|
"epoch": 2.4985255160693756,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004379055210784313,
|
|
"loss": 5.5665,
|
|
"mean_token_accuracy": 0.18510853946208955,
|
|
"num_tokens": 48903067.0,
|
|
"step": 24995
|
|
},
|
|
{
|
|
"entropy": 5.986723136901856,
|
|
"epoch": 2.4990253411306043,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004378809016071238,
|
|
"loss": 5.5657,
|
|
"mean_token_accuracy": 0.18432186543941498,
|
|
"num_tokens": 48911966.0,
|
|
"step": 25000
|
|
},
|
|
{
|
|
"entropy": 5.934085321426392,
|
|
"epoch": 2.499525166191833,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004378562780377748,
|
|
"loss": 5.476,
|
|
"mean_token_accuracy": 0.1967385709285736,
|
|
"num_tokens": 48921600.0,
|
|
"step": 25005
|
|
},
|
|
{
|
|
"entropy": 6.0269914150238035,
|
|
"epoch": 2.5000249912530617,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004378316503710037,
|
|
"loss": 5.6471,
|
|
"mean_token_accuracy": 0.17436469197273255,
|
|
"num_tokens": 48931071.0,
|
|
"step": 25010
|
|
},
|
|
{
|
|
"entropy": 5.984958934783935,
|
|
"epoch": 2.50052481631429,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004378070186074302,
|
|
"loss": 5.6461,
|
|
"mean_token_accuracy": 0.1813439577817917,
|
|
"num_tokens": 48941957.0,
|
|
"step": 25015
|
|
},
|
|
{
|
|
"entropy": 6.025920104980469,
|
|
"epoch": 2.5010246413755186,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00043778238274767395,
|
|
"loss": 5.6187,
|
|
"mean_token_accuracy": 0.18453295528888702,
|
|
"num_tokens": 48951466.0,
|
|
"step": 25020
|
|
},
|
|
{
|
|
"entropy": 6.103551721572876,
|
|
"epoch": 2.501524466436747,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004377577427923549,
|
|
"loss": 5.6832,
|
|
"mean_token_accuracy": 0.17495481073856353,
|
|
"num_tokens": 48961967.0,
|
|
"step": 25025
|
|
},
|
|
{
|
|
"entropy": 6.070560121536255,
|
|
"epoch": 2.5020242914979756,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00043773309874209294,
|
|
"loss": 5.6813,
|
|
"mean_token_accuracy": 0.18002144396305084,
|
|
"num_tokens": 48973391.0,
|
|
"step": 25030
|
|
},
|
|
{
|
|
"entropy": 5.974062442779541,
|
|
"epoch": 2.5025241165592043,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00043770845059750807,
|
|
"loss": 5.6205,
|
|
"mean_token_accuracy": 0.17556519210338592,
|
|
"num_tokens": 48983047.0,
|
|
"step": 25035
|
|
},
|
|
{
|
|
"entropy": 6.0337811470031735,
|
|
"epoch": 2.503023941620433,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00043768379835922044,
|
|
"loss": 5.6994,
|
|
"mean_token_accuracy": 0.16851172745227813,
|
|
"num_tokens": 48992140.0,
|
|
"step": 25040
|
|
},
|
|
{
|
|
"entropy": 5.991536712646484,
|
|
"epoch": 2.5035237666816617,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004376591420278503,
|
|
"loss": 5.515,
|
|
"mean_token_accuracy": 0.19107802212238312,
|
|
"num_tokens": 49002323.0,
|
|
"step": 25045
|
|
},
|
|
{
|
|
"entropy": 6.012349605560303,
|
|
"epoch": 2.50402359174289,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000437634481604018,
|
|
"loss": 5.6546,
|
|
"mean_token_accuracy": 0.17753661125898362,
|
|
"num_tokens": 49011727.0,
|
|
"step": 25050
|
|
},
|
|
{
|
|
"entropy": 6.0378875732421875,
|
|
"epoch": 2.5045234168041186,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.000437609817088344,
|
|
"loss": 5.5656,
|
|
"mean_token_accuracy": 0.18015332221984864,
|
|
"num_tokens": 49020723.0,
|
|
"step": 25055
|
|
},
|
|
{
|
|
"entropy": 5.990635395050049,
|
|
"epoch": 2.505023241865347,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00043758514848144886,
|
|
"loss": 5.7093,
|
|
"mean_token_accuracy": 0.17189764529466628,
|
|
"num_tokens": 49030270.0,
|
|
"step": 25060
|
|
},
|
|
{
|
|
"entropy": 5.958374881744385,
|
|
"epoch": 2.5055230669265756,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004375604757839532,
|
|
"loss": 5.5405,
|
|
"mean_token_accuracy": 0.18953807204961776,
|
|
"num_tokens": 49039726.0,
|
|
"step": 25065
|
|
},
|
|
{
|
|
"entropy": 6.043044567108154,
|
|
"epoch": 2.5060228919878043,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00043753579899647783,
|
|
"loss": 5.6442,
|
|
"mean_token_accuracy": 0.16693153828382493,
|
|
"num_tokens": 49050191.0,
|
|
"step": 25070
|
|
},
|
|
{
|
|
"entropy": 6.12791633605957,
|
|
"epoch": 2.506522717049033,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00043751111811964353,
|
|
"loss": 5.7386,
|
|
"mean_token_accuracy": 0.16669244021177293,
|
|
"num_tokens": 49060748.0,
|
|
"step": 25075
|
|
},
|
|
{
|
|
"entropy": 6.033016538619995,
|
|
"epoch": 2.5070225421102617,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004374864331540713,
|
|
"loss": 5.6697,
|
|
"mean_token_accuracy": 0.17873067110776902,
|
|
"num_tokens": 49070582.0,
|
|
"step": 25080
|
|
},
|
|
{
|
|
"entropy": 5.9604823112487795,
|
|
"epoch": 2.50752236717149,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004374617441003823,
|
|
"loss": 5.6136,
|
|
"mean_token_accuracy": 0.18610099703073502,
|
|
"num_tokens": 49080729.0,
|
|
"step": 25085
|
|
},
|
|
{
|
|
"entropy": 6.069977188110352,
|
|
"epoch": 2.5080221922327186,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004374370509591976,
|
|
"loss": 5.7305,
|
|
"mean_token_accuracy": 0.1715638294816017,
|
|
"num_tokens": 49090814.0,
|
|
"step": 25090
|
|
},
|
|
{
|
|
"entropy": 6.044988775253296,
|
|
"epoch": 2.508522017293947,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00043741235373113854,
|
|
"loss": 5.6391,
|
|
"mean_token_accuracy": 0.17529194355010985,
|
|
"num_tokens": 49100236.0,
|
|
"step": 25095
|
|
},
|
|
{
|
|
"entropy": 6.033241939544678,
|
|
"epoch": 2.5090218423551756,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00043738765241682637,
|
|
"loss": 5.6283,
|
|
"mean_token_accuracy": 0.17719219177961348,
|
|
"num_tokens": 49111403.0,
|
|
"step": 25100
|
|
},
|
|
{
|
|
"entropy": 6.021692180633545,
|
|
"epoch": 2.5095216674164043,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004373629470168826,
|
|
"loss": 5.6782,
|
|
"mean_token_accuracy": 0.1779496967792511,
|
|
"num_tokens": 49121678.0,
|
|
"step": 25105
|
|
},
|
|
{
|
|
"entropy": 5.97016716003418,
|
|
"epoch": 2.510021492477633,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.000437338237531929,
|
|
"loss": 5.5288,
|
|
"mean_token_accuracy": 0.19637700021266938,
|
|
"num_tokens": 49131171.0,
|
|
"step": 25110
|
|
},
|
|
{
|
|
"entropy": 5.971565866470337,
|
|
"epoch": 2.5105213175388617,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004373135239625871,
|
|
"loss": 5.5288,
|
|
"mean_token_accuracy": 0.1882092535495758,
|
|
"num_tokens": 49140300.0,
|
|
"step": 25115
|
|
},
|
|
{
|
|
"entropy": 5.938932275772094,
|
|
"epoch": 2.51102114260009,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00043728880630947864,
|
|
"loss": 5.5935,
|
|
"mean_token_accuracy": 0.18020131289958954,
|
|
"num_tokens": 49150028.0,
|
|
"step": 25120
|
|
},
|
|
{
|
|
"entropy": 6.056129264831543,
|
|
"epoch": 2.5115209676613186,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00043726408457322557,
|
|
"loss": 5.6813,
|
|
"mean_token_accuracy": 0.17163184136152268,
|
|
"num_tokens": 49160971.0,
|
|
"step": 25125
|
|
},
|
|
{
|
|
"entropy": 6.139138841629029,
|
|
"epoch": 2.512020792722547,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00043723935875445,
|
|
"loss": 5.6843,
|
|
"mean_token_accuracy": 0.1733221724629402,
|
|
"num_tokens": 49170834.0,
|
|
"step": 25130
|
|
},
|
|
{
|
|
"entropy": 6.004573726654053,
|
|
"epoch": 2.5125206177837756,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004372146288537738,
|
|
"loss": 5.5498,
|
|
"mean_token_accuracy": 0.18523871898651123,
|
|
"num_tokens": 49180459.0,
|
|
"step": 25135
|
|
},
|
|
{
|
|
"entropy": 6.006904411315918,
|
|
"epoch": 2.5130204428450043,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.00043718989487181927,
|
|
"loss": 5.5866,
|
|
"mean_token_accuracy": 0.17719856649637222,
|
|
"num_tokens": 49190767.0,
|
|
"step": 25140
|
|
},
|
|
{
|
|
"entropy": 6.087732315063477,
|
|
"epoch": 2.513520267906233,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004371651568092088,
|
|
"loss": 5.6516,
|
|
"mean_token_accuracy": 0.1719252124428749,
|
|
"num_tokens": 49200368.0,
|
|
"step": 25145
|
|
},
|
|
{
|
|
"entropy": 6.044086027145386,
|
|
"epoch": 2.5140200929674617,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004371404146665647,
|
|
"loss": 5.6525,
|
|
"mean_token_accuracy": 0.1809021756052971,
|
|
"num_tokens": 49210731.0,
|
|
"step": 25150
|
|
},
|
|
{
|
|
"entropy": 5.979925537109375,
|
|
"epoch": 2.51451991802869,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00043711566844450934,
|
|
"loss": 5.6116,
|
|
"mean_token_accuracy": 0.17959929406642913,
|
|
"num_tokens": 49222783.0,
|
|
"step": 25155
|
|
},
|
|
{
|
|
"entropy": 5.96338963508606,
|
|
"epoch": 2.5150197430899186,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00043709091814366565,
|
|
"loss": 5.6108,
|
|
"mean_token_accuracy": 0.18098832219839095,
|
|
"num_tokens": 49232738.0,
|
|
"step": 25160
|
|
},
|
|
{
|
|
"entropy": 6.076579236984253,
|
|
"epoch": 2.515519568151147,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00043706616376465614,
|
|
"loss": 5.7107,
|
|
"mean_token_accuracy": 0.17034954130649566,
|
|
"num_tokens": 49242666.0,
|
|
"step": 25165
|
|
},
|
|
{
|
|
"entropy": 5.994010782241821,
|
|
"epoch": 2.5160193932123756,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004370414053081036,
|
|
"loss": 5.61,
|
|
"mean_token_accuracy": 0.17916163057088852,
|
|
"num_tokens": 49253227.0,
|
|
"step": 25170
|
|
},
|
|
{
|
|
"entropy": 5.992199039459228,
|
|
"epoch": 2.5165192182736043,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.000437016642774631,
|
|
"loss": 5.534,
|
|
"mean_token_accuracy": 0.19166046231985093,
|
|
"num_tokens": 49262635.0,
|
|
"step": 25175
|
|
},
|
|
{
|
|
"entropy": 6.022533130645752,
|
|
"epoch": 2.517019043334833,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00043699187616486144,
|
|
"loss": 5.6526,
|
|
"mean_token_accuracy": 0.1752773180603981,
|
|
"num_tokens": 49271952.0,
|
|
"step": 25180
|
|
},
|
|
{
|
|
"entropy": 6.0855365753173825,
|
|
"epoch": 2.5175188683960616,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004369671054794178,
|
|
"loss": 5.7486,
|
|
"mean_token_accuracy": 0.16756757944822312,
|
|
"num_tokens": 49281282.0,
|
|
"step": 25185
|
|
},
|
|
{
|
|
"entropy": 5.975560235977173,
|
|
"epoch": 2.51801869345729,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00043694233071892366,
|
|
"loss": 5.6464,
|
|
"mean_token_accuracy": 0.18164808601140975,
|
|
"num_tokens": 49290892.0,
|
|
"step": 25190
|
|
},
|
|
{
|
|
"entropy": 6.115087032318115,
|
|
"epoch": 2.5185185185185186,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00043691755188400203,
|
|
"loss": 5.6942,
|
|
"mean_token_accuracy": 0.17579671889543533,
|
|
"num_tokens": 49300816.0,
|
|
"step": 25195
|
|
},
|
|
{
|
|
"entropy": 6.080513048171997,
|
|
"epoch": 2.519018343579747,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004368927689752765,
|
|
"loss": 5.7066,
|
|
"mean_token_accuracy": 0.1697137862443924,
|
|
"num_tokens": 49309849.0,
|
|
"step": 25200
|
|
},
|
|
{
|
|
"entropy": 6.023027515411377,
|
|
"epoch": 2.5195181686409756,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00043686798199337053,
|
|
"loss": 5.5622,
|
|
"mean_token_accuracy": 0.17706016451120377,
|
|
"num_tokens": 49319785.0,
|
|
"step": 25205
|
|
},
|
|
{
|
|
"entropy": 6.005905961990356,
|
|
"epoch": 2.5200179937022043,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00043684319093890777,
|
|
"loss": 5.6152,
|
|
"mean_token_accuracy": 0.18302474319934844,
|
|
"num_tokens": 49329117.0,
|
|
"step": 25210
|
|
},
|
|
{
|
|
"entropy": 6.082866621017456,
|
|
"epoch": 2.520517818763433,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00043681839581251206,
|
|
"loss": 5.7069,
|
|
"mean_token_accuracy": 0.17205699980258943,
|
|
"num_tokens": 49338527.0,
|
|
"step": 25215
|
|
},
|
|
{
|
|
"entropy": 6.123406457901001,
|
|
"epoch": 2.521017643824661,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00043679359661480703,
|
|
"loss": 5.8298,
|
|
"mean_token_accuracy": 0.16375347524881362,
|
|
"num_tokens": 49348976.0,
|
|
"step": 25220
|
|
},
|
|
{
|
|
"entropy": 6.001164150238037,
|
|
"epoch": 2.52151746888589,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00043676879334641686,
|
|
"loss": 5.6612,
|
|
"mean_token_accuracy": 0.182169771194458,
|
|
"num_tokens": 49358817.0,
|
|
"step": 25225
|
|
},
|
|
{
|
|
"entropy": 5.98209547996521,
|
|
"epoch": 2.5220172939471186,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004367439860079654,
|
|
"loss": 5.6239,
|
|
"mean_token_accuracy": 0.180136476457119,
|
|
"num_tokens": 49369463.0,
|
|
"step": 25230
|
|
},
|
|
{
|
|
"entropy": 6.122039461135865,
|
|
"epoch": 2.522517119008347,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00043671917460007693,
|
|
"loss": 5.7058,
|
|
"mean_token_accuracy": 0.1787787452340126,
|
|
"num_tokens": 49379198.0,
|
|
"step": 25235
|
|
},
|
|
{
|
|
"entropy": 5.998304033279419,
|
|
"epoch": 2.5230169440695756,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00043669435912337557,
|
|
"loss": 5.5925,
|
|
"mean_token_accuracy": 0.18115227818489074,
|
|
"num_tokens": 49388018.0,
|
|
"step": 25240
|
|
},
|
|
{
|
|
"entropy": 5.988892459869385,
|
|
"epoch": 2.5235167691308042,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004366695395784858,
|
|
"loss": 5.6768,
|
|
"mean_token_accuracy": 0.17549901604652404,
|
|
"num_tokens": 49397082.0,
|
|
"step": 25245
|
|
},
|
|
{
|
|
"entropy": 5.965608549118042,
|
|
"epoch": 2.524016594192033,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.000436644715966032,
|
|
"loss": 5.5629,
|
|
"mean_token_accuracy": 0.181040520966053,
|
|
"num_tokens": 49405763.0,
|
|
"step": 25250
|
|
},
|
|
{
|
|
"entropy": 5.927306747436523,
|
|
"epoch": 2.524516419253261,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004366198882866387,
|
|
"loss": 5.5248,
|
|
"mean_token_accuracy": 0.19131924211978912,
|
|
"num_tokens": 49415296.0,
|
|
"step": 25255
|
|
},
|
|
{
|
|
"entropy": 6.083302450180054,
|
|
"epoch": 2.52501624431449,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00043659505654093065,
|
|
"loss": 5.7281,
|
|
"mean_token_accuracy": 0.17288426160812378,
|
|
"num_tokens": 49425066.0,
|
|
"step": 25260
|
|
},
|
|
{
|
|
"entropy": 6.001824378967285,
|
|
"epoch": 2.5255160693757186,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00043657022072953253,
|
|
"loss": 5.6161,
|
|
"mean_token_accuracy": 0.18186036199331285,
|
|
"num_tokens": 49434056.0,
|
|
"step": 25265
|
|
},
|
|
{
|
|
"entropy": 6.14989333152771,
|
|
"epoch": 2.526015894436947,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004365453808530693,
|
|
"loss": 5.7318,
|
|
"mean_token_accuracy": 0.17436858862638474,
|
|
"num_tokens": 49443822.0,
|
|
"step": 25270
|
|
},
|
|
{
|
|
"entropy": 6.011353635787964,
|
|
"epoch": 2.5265157194981755,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00043652053691216574,
|
|
"loss": 5.5732,
|
|
"mean_token_accuracy": 0.1822014033794403,
|
|
"num_tokens": 49453455.0,
|
|
"step": 25275
|
|
},
|
|
{
|
|
"entropy": 6.000114393234253,
|
|
"epoch": 2.5270155445594042,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004364956889074471,
|
|
"loss": 5.6026,
|
|
"mean_token_accuracy": 0.18483332246541978,
|
|
"num_tokens": 49462069.0,
|
|
"step": 25280
|
|
},
|
|
{
|
|
"entropy": 6.037860870361328,
|
|
"epoch": 2.527515369620633,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004364708368395385,
|
|
"loss": 5.6621,
|
|
"mean_token_accuracy": 0.1768892765045166,
|
|
"num_tokens": 49471802.0,
|
|
"step": 25285
|
|
},
|
|
{
|
|
"entropy": 5.985757875442505,
|
|
"epoch": 2.528015194681861,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00043644598070906516,
|
|
"loss": 5.6251,
|
|
"mean_token_accuracy": 0.1838405281305313,
|
|
"num_tokens": 49481181.0,
|
|
"step": 25290
|
|
},
|
|
{
|
|
"entropy": 6.043817949295044,
|
|
"epoch": 2.52851501974309,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004364211205166525,
|
|
"loss": 5.6644,
|
|
"mean_token_accuracy": 0.1747914358973503,
|
|
"num_tokens": 49491769.0,
|
|
"step": 25295
|
|
},
|
|
{
|
|
"entropy": 6.07287712097168,
|
|
"epoch": 2.5290148448043186,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00043639625626292595,
|
|
"loss": 5.7178,
|
|
"mean_token_accuracy": 0.17464480847120284,
|
|
"num_tokens": 49501711.0,
|
|
"step": 25300
|
|
},
|
|
{
|
|
"entropy": 6.027508497238159,
|
|
"epoch": 2.529514669865547,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004363713879485112,
|
|
"loss": 5.6834,
|
|
"mean_token_accuracy": 0.17240516543388368,
|
|
"num_tokens": 49511248.0,
|
|
"step": 25305
|
|
},
|
|
{
|
|
"entropy": 5.928113508224487,
|
|
"epoch": 2.5300144949267755,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004363465155740338,
|
|
"loss": 5.529,
|
|
"mean_token_accuracy": 0.18732579946517944,
|
|
"num_tokens": 49520349.0,
|
|
"step": 25310
|
|
},
|
|
{
|
|
"entropy": 6.091530179977417,
|
|
"epoch": 2.5305143199880042,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004363216391401196,
|
|
"loss": 5.7223,
|
|
"mean_token_accuracy": 0.17917766720056533,
|
|
"num_tokens": 49530233.0,
|
|
"step": 25315
|
|
},
|
|
{
|
|
"entropy": 5.986883068084717,
|
|
"epoch": 2.531014145049233,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004362967586473945,
|
|
"loss": 5.5605,
|
|
"mean_token_accuracy": 0.18934595882892608,
|
|
"num_tokens": 49540059.0,
|
|
"step": 25320
|
|
},
|
|
{
|
|
"entropy": 6.066008424758911,
|
|
"epoch": 2.531513970110461,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004362718740964844,
|
|
"loss": 5.6201,
|
|
"mean_token_accuracy": 0.18114217221736909,
|
|
"num_tokens": 49549113.0,
|
|
"step": 25325
|
|
},
|
|
{
|
|
"entropy": 6.117833185195923,
|
|
"epoch": 2.53201379517169,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004362469854880155,
|
|
"loss": 5.7232,
|
|
"mean_token_accuracy": 0.1731607049703598,
|
|
"num_tokens": 49558954.0,
|
|
"step": 25330
|
|
},
|
|
{
|
|
"entropy": 5.934583616256714,
|
|
"epoch": 2.5325136202329186,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004362220928226139,
|
|
"loss": 5.5431,
|
|
"mean_token_accuracy": 0.18601454198360443,
|
|
"num_tokens": 49568905.0,
|
|
"step": 25335
|
|
},
|
|
{
|
|
"entropy": 6.0418288230896,
|
|
"epoch": 2.533013445294147,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00043619719610090595,
|
|
"loss": 5.5716,
|
|
"mean_token_accuracy": 0.18347230404615403,
|
|
"num_tokens": 49579581.0,
|
|
"step": 25340
|
|
},
|
|
{
|
|
"entropy": 6.065149450302124,
|
|
"epoch": 2.5335132703553755,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.000436172295323518,
|
|
"loss": 5.6625,
|
|
"mean_token_accuracy": 0.1783336192369461,
|
|
"num_tokens": 49589169.0,
|
|
"step": 25345
|
|
},
|
|
{
|
|
"entropy": 6.067013216018677,
|
|
"epoch": 2.5340130954166042,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00043614739049107666,
|
|
"loss": 5.7425,
|
|
"mean_token_accuracy": 0.17634260058403015,
|
|
"num_tokens": 49598910.0,
|
|
"step": 25350
|
|
},
|
|
{
|
|
"entropy": 6.053786039352417,
|
|
"epoch": 2.534512920477833,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.00043612248160420833,
|
|
"loss": 5.6867,
|
|
"mean_token_accuracy": 0.17588303089141846,
|
|
"num_tokens": 49608570.0,
|
|
"step": 25355
|
|
},
|
|
{
|
|
"entropy": 6.08862452507019,
|
|
"epoch": 2.535012745539061,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00043609756866353985,
|
|
"loss": 5.6896,
|
|
"mean_token_accuracy": 0.17077322155237198,
|
|
"num_tokens": 49618034.0,
|
|
"step": 25360
|
|
},
|
|
{
|
|
"entropy": 6.082648515701294,
|
|
"epoch": 2.53551257060029,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.000436072651669698,
|
|
"loss": 5.7189,
|
|
"mean_token_accuracy": 0.17332539856433868,
|
|
"num_tokens": 49628297.0,
|
|
"step": 25365
|
|
},
|
|
{
|
|
"entropy": 6.029137420654297,
|
|
"epoch": 2.5360123956615186,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004360477306233097,
|
|
"loss": 5.7213,
|
|
"mean_token_accuracy": 0.17499091178178788,
|
|
"num_tokens": 49638504.0,
|
|
"step": 25370
|
|
},
|
|
{
|
|
"entropy": 6.0393774032592775,
|
|
"epoch": 2.536512220722747,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00043602280552500195,
|
|
"loss": 5.6927,
|
|
"mean_token_accuracy": 0.17489517331123353,
|
|
"num_tokens": 49648597.0,
|
|
"step": 25375
|
|
},
|
|
{
|
|
"entropy": 5.989431428909302,
|
|
"epoch": 2.5370120457839755,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00043599787637540186,
|
|
"loss": 5.6704,
|
|
"mean_token_accuracy": 0.1798797905445099,
|
|
"num_tokens": 49657767.0,
|
|
"step": 25380
|
|
},
|
|
{
|
|
"entropy": 5.993502140045166,
|
|
"epoch": 2.5375118708452042,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00043597294317513654,
|
|
"loss": 5.587,
|
|
"mean_token_accuracy": 0.18755653202533723,
|
|
"num_tokens": 49667739.0,
|
|
"step": 25385
|
|
},
|
|
{
|
|
"entropy": 6.028469753265381,
|
|
"epoch": 2.538011695906433,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00043594800592483345,
|
|
"loss": 5.5554,
|
|
"mean_token_accuracy": 0.18139148205518724,
|
|
"num_tokens": 49676350.0,
|
|
"step": 25390
|
|
},
|
|
{
|
|
"entropy": 6.0405021667480465,
|
|
"epoch": 2.538511520967661,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00043592306462511993,
|
|
"loss": 5.6764,
|
|
"mean_token_accuracy": 0.18260296434164047,
|
|
"num_tokens": 49684654.0,
|
|
"step": 25395
|
|
},
|
|
{
|
|
"entropy": 6.029631090164185,
|
|
"epoch": 2.53901134602889,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00043589811927662356,
|
|
"loss": 5.6623,
|
|
"mean_token_accuracy": 0.17412343621253967,
|
|
"num_tokens": 49695138.0,
|
|
"step": 25400
|
|
},
|
|
{
|
|
"entropy": 6.060790395736694,
|
|
"epoch": 2.5395111710901186,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00043587316987997183,
|
|
"loss": 5.6234,
|
|
"mean_token_accuracy": 0.18197770714759826,
|
|
"num_tokens": 49704671.0,
|
|
"step": 25405
|
|
},
|
|
{
|
|
"entropy": 6.023987770080566,
|
|
"epoch": 2.540010996151347,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00043584821643579265,
|
|
"loss": 5.6818,
|
|
"mean_token_accuracy": 0.1795186698436737,
|
|
"num_tokens": 49714998.0,
|
|
"step": 25410
|
|
},
|
|
{
|
|
"entropy": 5.968161582946777,
|
|
"epoch": 2.5405108212125755,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00043582325894471366,
|
|
"loss": 5.477,
|
|
"mean_token_accuracy": 0.19019569158554078,
|
|
"num_tokens": 49725333.0,
|
|
"step": 25415
|
|
},
|
|
{
|
|
"entropy": 6.0756937026977536,
|
|
"epoch": 2.5410106462738042,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004357982974073629,
|
|
"loss": 5.6916,
|
|
"mean_token_accuracy": 0.17384756207466126,
|
|
"num_tokens": 49735919.0,
|
|
"step": 25420
|
|
},
|
|
{
|
|
"entropy": 6.049579238891601,
|
|
"epoch": 2.541510471335033,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004357733318243683,
|
|
"loss": 5.6789,
|
|
"mean_token_accuracy": 0.17713318169116973,
|
|
"num_tokens": 49746631.0,
|
|
"step": 25425
|
|
},
|
|
{
|
|
"entropy": 6.048529577255249,
|
|
"epoch": 2.542010296396261,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00043574836219635805,
|
|
"loss": 5.6545,
|
|
"mean_token_accuracy": 0.17964892089366913,
|
|
"num_tokens": 49756241.0,
|
|
"step": 25430
|
|
},
|
|
{
|
|
"entropy": 6.050957679748535,
|
|
"epoch": 2.54251012145749,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00043572338852396035,
|
|
"loss": 5.6317,
|
|
"mean_token_accuracy": 0.18482844680547714,
|
|
"num_tokens": 49766761.0,
|
|
"step": 25435
|
|
},
|
|
{
|
|
"entropy": 5.987704420089722,
|
|
"epoch": 2.5430099465187186,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00043569841080780367,
|
|
"loss": 5.6139,
|
|
"mean_token_accuracy": 0.18301165401935576,
|
|
"num_tokens": 49775442.0,
|
|
"step": 25440
|
|
},
|
|
{
|
|
"entropy": 6.030871915817261,
|
|
"epoch": 2.543509771579947,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00043567342904851625,
|
|
"loss": 5.6644,
|
|
"mean_token_accuracy": 0.1696798488497734,
|
|
"num_tokens": 49784071.0,
|
|
"step": 25445
|
|
},
|
|
{
|
|
"entropy": 6.01219630241394,
|
|
"epoch": 2.5440095966411755,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004356484432467267,
|
|
"loss": 5.6736,
|
|
"mean_token_accuracy": 0.17060493379831315,
|
|
"num_tokens": 49793649.0,
|
|
"step": 25450
|
|
},
|
|
{
|
|
"entropy": 6.030922794342041,
|
|
"epoch": 2.5445094217024042,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00043562345340306363,
|
|
"loss": 5.694,
|
|
"mean_token_accuracy": 0.17723112255334855,
|
|
"num_tokens": 49802940.0,
|
|
"step": 25455
|
|
},
|
|
{
|
|
"entropy": 5.959990072250366,
|
|
"epoch": 2.545009246763633,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004355984595181559,
|
|
"loss": 5.5919,
|
|
"mean_token_accuracy": 0.18125167936086656,
|
|
"num_tokens": 49813035.0,
|
|
"step": 25460
|
|
},
|
|
{
|
|
"entropy": 6.081461000442505,
|
|
"epoch": 2.545509071824861,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004355734615926321,
|
|
"loss": 5.7259,
|
|
"mean_token_accuracy": 0.1730189085006714,
|
|
"num_tokens": 49823154.0,
|
|
"step": 25465
|
|
},
|
|
{
|
|
"entropy": 5.993745899200439,
|
|
"epoch": 2.54600889688609,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004355484596271214,
|
|
"loss": 5.5795,
|
|
"mean_token_accuracy": 0.17502461969852448,
|
|
"num_tokens": 49833662.0,
|
|
"step": 25470
|
|
},
|
|
{
|
|
"entropy": 5.93044490814209,
|
|
"epoch": 2.5465087219473186,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004355234536222528,
|
|
"loss": 5.5263,
|
|
"mean_token_accuracy": 0.18485236763954163,
|
|
"num_tokens": 49843322.0,
|
|
"step": 25475
|
|
},
|
|
{
|
|
"entropy": 5.9748846054077145,
|
|
"epoch": 2.547008547008547,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004354984435786554,
|
|
"loss": 5.6071,
|
|
"mean_token_accuracy": 0.18742865175008774,
|
|
"num_tokens": 49853360.0,
|
|
"step": 25480
|
|
},
|
|
{
|
|
"entropy": 5.941626167297363,
|
|
"epoch": 2.5475083720697755,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004354734294969585,
|
|
"loss": 5.6553,
|
|
"mean_token_accuracy": 0.1777411252260208,
|
|
"num_tokens": 49864205.0,
|
|
"step": 25485
|
|
},
|
|
{
|
|
"entropy": 6.0369030952453615,
|
|
"epoch": 2.5480081971310042,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00043544841137779127,
|
|
"loss": 5.626,
|
|
"mean_token_accuracy": 0.17408559918403627,
|
|
"num_tokens": 49873629.0,
|
|
"step": 25490
|
|
},
|
|
{
|
|
"entropy": 6.032674407958984,
|
|
"epoch": 2.548508022192233,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00043542338922178343,
|
|
"loss": 5.5667,
|
|
"mean_token_accuracy": 0.18038753867149354,
|
|
"num_tokens": 49883877.0,
|
|
"step": 25495
|
|
},
|
|
{
|
|
"entropy": 6.069333171844482,
|
|
"epoch": 2.549007847253461,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00043539836302956434,
|
|
"loss": 5.7178,
|
|
"mean_token_accuracy": 0.1738424614071846,
|
|
"num_tokens": 49893664.0,
|
|
"step": 25500
|
|
},
|
|
{
|
|
"entropy": 5.935047388076782,
|
|
"epoch": 2.54950767231469,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004353733328017637,
|
|
"loss": 5.5914,
|
|
"mean_token_accuracy": 0.1840689957141876,
|
|
"num_tokens": 49903356.0,
|
|
"step": 25505
|
|
},
|
|
{
|
|
"entropy": 6.00285587310791,
|
|
"epoch": 2.5500074973759186,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004353482985390113,
|
|
"loss": 5.5655,
|
|
"mean_token_accuracy": 0.18071367889642714,
|
|
"num_tokens": 49912579.0,
|
|
"step": 25510
|
|
},
|
|
{
|
|
"entropy": 6.0152099609375,
|
|
"epoch": 2.550507322437147,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000435323260241937,
|
|
"loss": 5.5697,
|
|
"mean_token_accuracy": 0.18971913456916809,
|
|
"num_tokens": 49922123.0,
|
|
"step": 25515
|
|
},
|
|
{
|
|
"entropy": 6.109286975860596,
|
|
"epoch": 2.5510071474983755,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00043529821791117064,
|
|
"loss": 5.713,
|
|
"mean_token_accuracy": 0.17385945916175843,
|
|
"num_tokens": 49931340.0,
|
|
"step": 25520
|
|
},
|
|
{
|
|
"entropy": 6.087798833847046,
|
|
"epoch": 2.5515069725596042,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004352731715473425,
|
|
"loss": 5.7042,
|
|
"mean_token_accuracy": 0.17285197228193283,
|
|
"num_tokens": 49940449.0,
|
|
"step": 25525
|
|
},
|
|
{
|
|
"entropy": 6.069275045394898,
|
|
"epoch": 2.552006797620833,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00043524812115108244,
|
|
"loss": 5.702,
|
|
"mean_token_accuracy": 0.17393108308315278,
|
|
"num_tokens": 49949914.0,
|
|
"step": 25530
|
|
},
|
|
{
|
|
"entropy": 5.993856716156006,
|
|
"epoch": 2.552506622682061,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00043522306672302103,
|
|
"loss": 5.6351,
|
|
"mean_token_accuracy": 0.18057361394166946,
|
|
"num_tokens": 49960877.0,
|
|
"step": 25535
|
|
},
|
|
{
|
|
"entropy": 6.052314567565918,
|
|
"epoch": 2.55300644774329,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004351980082637884,
|
|
"loss": 5.6068,
|
|
"mean_token_accuracy": 0.18206802010536194,
|
|
"num_tokens": 49969272.0,
|
|
"step": 25540
|
|
},
|
|
{
|
|
"entropy": 6.060594701766968,
|
|
"epoch": 2.5535062728045186,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00043517294577401504,
|
|
"loss": 5.66,
|
|
"mean_token_accuracy": 0.17717259824275972,
|
|
"num_tokens": 49978600.0,
|
|
"step": 25545
|
|
},
|
|
{
|
|
"entropy": 5.899148273468017,
|
|
"epoch": 2.554006097865747,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00043514787925433176,
|
|
"loss": 5.5248,
|
|
"mean_token_accuracy": 0.19379835873842238,
|
|
"num_tokens": 49987772.0,
|
|
"step": 25550
|
|
},
|
|
{
|
|
"entropy": 5.974797916412354,
|
|
"epoch": 2.5545059229269755,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004351228087053689,
|
|
"loss": 5.7034,
|
|
"mean_token_accuracy": 0.17646191269159317,
|
|
"num_tokens": 49996826.0,
|
|
"step": 25555
|
|
},
|
|
{
|
|
"entropy": 6.085300350189209,
|
|
"epoch": 2.5550057479882042,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.00043509773412775746,
|
|
"loss": 5.6325,
|
|
"mean_token_accuracy": 0.17706382870674134,
|
|
"num_tokens": 50006619.0,
|
|
"step": 25560
|
|
},
|
|
{
|
|
"entropy": 6.028863859176636,
|
|
"epoch": 2.555505573049433,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004350726555221282,
|
|
"loss": 5.5741,
|
|
"mean_token_accuracy": 0.18439312577247619,
|
|
"num_tokens": 50017050.0,
|
|
"step": 25565
|
|
},
|
|
{
|
|
"entropy": 6.01319637298584,
|
|
"epoch": 2.556005398110661,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004350475728891121,
|
|
"loss": 5.6204,
|
|
"mean_token_accuracy": 0.1813817024230957,
|
|
"num_tokens": 50026558.0,
|
|
"step": 25570
|
|
},
|
|
{
|
|
"entropy": 5.997391700744629,
|
|
"epoch": 2.55650522317189,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004350224862293403,
|
|
"loss": 5.6071,
|
|
"mean_token_accuracy": 0.17808909863233566,
|
|
"num_tokens": 50035540.0,
|
|
"step": 25575
|
|
},
|
|
{
|
|
"entropy": 6.011634349822998,
|
|
"epoch": 2.557005048233118,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00043499739554344393,
|
|
"loss": 5.6387,
|
|
"mean_token_accuracy": 0.17594165951013566,
|
|
"num_tokens": 50045780.0,
|
|
"step": 25580
|
|
},
|
|
{
|
|
"entropy": 5.99439263343811,
|
|
"epoch": 2.557504873294347,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00043497230083205425,
|
|
"loss": 5.5375,
|
|
"mean_token_accuracy": 0.1865432307124138,
|
|
"num_tokens": 50055977.0,
|
|
"step": 25585
|
|
},
|
|
{
|
|
"entropy": 6.009659671783448,
|
|
"epoch": 2.5580046983555755,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004349472020958026,
|
|
"loss": 5.6489,
|
|
"mean_token_accuracy": 0.17497324645519258,
|
|
"num_tokens": 50065974.0,
|
|
"step": 25590
|
|
},
|
|
{
|
|
"entropy": 5.910415506362915,
|
|
"epoch": 2.5585045234168042,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00043492209933532054,
|
|
"loss": 5.5545,
|
|
"mean_token_accuracy": 0.18836472928524017,
|
|
"num_tokens": 50075969.0,
|
|
"step": 25595
|
|
},
|
|
{
|
|
"entropy": 6.079482126235962,
|
|
"epoch": 2.559004348478033,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00043489699255123954,
|
|
"loss": 5.6257,
|
|
"mean_token_accuracy": 0.18215664923191072,
|
|
"num_tokens": 50085304.0,
|
|
"step": 25600
|
|
},
|
|
{
|
|
"entropy": 6.044822025299072,
|
|
"epoch": 2.559504173539261,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004348718817441914,
|
|
"loss": 5.6993,
|
|
"mean_token_accuracy": 0.1750642791390419,
|
|
"num_tokens": 50094903.0,
|
|
"step": 25605
|
|
},
|
|
{
|
|
"entropy": 6.070815753936768,
|
|
"epoch": 2.56000399860049,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004348467669148078,
|
|
"loss": 5.6035,
|
|
"mean_token_accuracy": 0.18061578124761582,
|
|
"num_tokens": 50106990.0,
|
|
"step": 25610
|
|
},
|
|
{
|
|
"entropy": 6.141482782363892,
|
|
"epoch": 2.560503823661718,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00043482164806372075,
|
|
"loss": 5.7231,
|
|
"mean_token_accuracy": 0.16639111191034317,
|
|
"num_tokens": 50117655.0,
|
|
"step": 25615
|
|
},
|
|
{
|
|
"entropy": 6.09886794090271,
|
|
"epoch": 2.561003648722947,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004347965251915622,
|
|
"loss": 5.7169,
|
|
"mean_token_accuracy": 0.17497677057981492,
|
|
"num_tokens": 50127024.0,
|
|
"step": 25620
|
|
},
|
|
{
|
|
"entropy": 5.999304723739624,
|
|
"epoch": 2.5615034737841755,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00043477139829896415,
|
|
"loss": 5.6304,
|
|
"mean_token_accuracy": 0.18559712171554565,
|
|
"num_tokens": 50136524.0,
|
|
"step": 25625
|
|
},
|
|
{
|
|
"entropy": 6.053003263473511,
|
|
"epoch": 2.5620032988454042,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00043474626738655876,
|
|
"loss": 5.6877,
|
|
"mean_token_accuracy": 0.1735115349292755,
|
|
"num_tokens": 50146242.0,
|
|
"step": 25630
|
|
},
|
|
{
|
|
"entropy": 5.992054033279419,
|
|
"epoch": 2.562503123906633,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004347211324549785,
|
|
"loss": 5.6172,
|
|
"mean_token_accuracy": 0.17987524569034577,
|
|
"num_tokens": 50156486.0,
|
|
"step": 25635
|
|
},
|
|
{
|
|
"entropy": 6.035290670394898,
|
|
"epoch": 2.563002948967861,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00043469599350485556,
|
|
"loss": 5.6486,
|
|
"mean_token_accuracy": 0.17782288491725923,
|
|
"num_tokens": 50166479.0,
|
|
"step": 25640
|
|
},
|
|
{
|
|
"entropy": 6.011074542999268,
|
|
"epoch": 2.56350277402909,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004346708505368225,
|
|
"loss": 5.6258,
|
|
"mean_token_accuracy": 0.17688858956098558,
|
|
"num_tokens": 50176207.0,
|
|
"step": 25645
|
|
},
|
|
{
|
|
"entropy": 6.001205825805664,
|
|
"epoch": 2.564002599090318,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004346457035515121,
|
|
"loss": 5.6369,
|
|
"mean_token_accuracy": 0.1781435489654541,
|
|
"num_tokens": 50185577.0,
|
|
"step": 25650
|
|
},
|
|
{
|
|
"entropy": 6.081278944015503,
|
|
"epoch": 2.564502424151547,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00043462055254955666,
|
|
"loss": 5.6378,
|
|
"mean_token_accuracy": 0.1757716029882431,
|
|
"num_tokens": 50195473.0,
|
|
"step": 25655
|
|
},
|
|
{
|
|
"entropy": 6.01756443977356,
|
|
"epoch": 2.5650022492127755,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004345953975315893,
|
|
"loss": 5.5812,
|
|
"mean_token_accuracy": 0.1800333023071289,
|
|
"num_tokens": 50205684.0,
|
|
"step": 25660
|
|
},
|
|
{
|
|
"entropy": 6.050907564163208,
|
|
"epoch": 2.5655020742740042,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004345702384982429,
|
|
"loss": 5.7269,
|
|
"mean_token_accuracy": 0.1723924070596695,
|
|
"num_tokens": 50215716.0,
|
|
"step": 25665
|
|
},
|
|
{
|
|
"entropy": 6.129036569595337,
|
|
"epoch": 2.566001899335233,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004345450754501502,
|
|
"loss": 5.7683,
|
|
"mean_token_accuracy": 0.16857461482286454,
|
|
"num_tokens": 50226240.0,
|
|
"step": 25670
|
|
},
|
|
{
|
|
"entropy": 6.054889869689942,
|
|
"epoch": 2.566501724396461,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00043451990838794453,
|
|
"loss": 5.7231,
|
|
"mean_token_accuracy": 0.17086989283561707,
|
|
"num_tokens": 50234886.0,
|
|
"step": 25675
|
|
},
|
|
{
|
|
"entropy": 6.081551027297974,
|
|
"epoch": 2.56700154945769,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000434494737312259,
|
|
"loss": 5.6918,
|
|
"mean_token_accuracy": 0.17294537872076035,
|
|
"num_tokens": 50244594.0,
|
|
"step": 25680
|
|
},
|
|
{
|
|
"entropy": 6.016102743148804,
|
|
"epoch": 2.567501374518918,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00043446956222372693,
|
|
"loss": 5.644,
|
|
"mean_token_accuracy": 0.1801856204867363,
|
|
"num_tokens": 50254423.0,
|
|
"step": 25685
|
|
},
|
|
{
|
|
"entropy": 6.011240673065186,
|
|
"epoch": 2.568001199580147,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004344443831229816,
|
|
"loss": 5.6506,
|
|
"mean_token_accuracy": 0.1761116564273834,
|
|
"num_tokens": 50263280.0,
|
|
"step": 25690
|
|
},
|
|
{
|
|
"entropy": 6.0311342716217045,
|
|
"epoch": 2.5685010246413755,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00043441920001065676,
|
|
"loss": 5.6244,
|
|
"mean_token_accuracy": 0.17974747717380524,
|
|
"num_tokens": 50272802.0,
|
|
"step": 25695
|
|
},
|
|
{
|
|
"entropy": 6.048868083953858,
|
|
"epoch": 2.5690008497026042,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004343940128873858,
|
|
"loss": 5.6817,
|
|
"mean_token_accuracy": 0.17612839862704277,
|
|
"num_tokens": 50282066.0,
|
|
"step": 25700
|
|
},
|
|
{
|
|
"entropy": 6.02129054069519,
|
|
"epoch": 2.569500674763833,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00043436882175380256,
|
|
"loss": 5.5533,
|
|
"mean_token_accuracy": 0.1830284357070923,
|
|
"num_tokens": 50292333.0,
|
|
"step": 25705
|
|
},
|
|
{
|
|
"entropy": 5.868991994857788,
|
|
"epoch": 2.570000499825061,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004343436266105407,
|
|
"loss": 5.456,
|
|
"mean_token_accuracy": 0.19455483853816985,
|
|
"num_tokens": 50302001.0,
|
|
"step": 25710
|
|
},
|
|
{
|
|
"entropy": 6.080248689651489,
|
|
"epoch": 2.57050032488629,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004343184274582343,
|
|
"loss": 5.7613,
|
|
"mean_token_accuracy": 0.16460890620946883,
|
|
"num_tokens": 50312447.0,
|
|
"step": 25715
|
|
},
|
|
{
|
|
"entropy": 5.98896336555481,
|
|
"epoch": 2.571000149947518,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004342932242975172,
|
|
"loss": 5.5943,
|
|
"mean_token_accuracy": 0.17810958176851271,
|
|
"num_tokens": 50321534.0,
|
|
"step": 25720
|
|
},
|
|
{
|
|
"entropy": 6.046103763580322,
|
|
"epoch": 2.571499975008747,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004342680171290235,
|
|
"loss": 5.6158,
|
|
"mean_token_accuracy": 0.17620407193899154,
|
|
"num_tokens": 50331354.0,
|
|
"step": 25725
|
|
},
|
|
{
|
|
"entropy": 6.142542219161987,
|
|
"epoch": 2.5719998000699755,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004342428059533875,
|
|
"loss": 5.805,
|
|
"mean_token_accuracy": 0.16450287252664567,
|
|
"num_tokens": 50341463.0,
|
|
"step": 25730
|
|
},
|
|
{
|
|
"entropy": 6.066467142105102,
|
|
"epoch": 2.5724996251312042,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004342175907712435,
|
|
"loss": 5.5901,
|
|
"mean_token_accuracy": 0.17551926970481874,
|
|
"num_tokens": 50350374.0,
|
|
"step": 25735
|
|
},
|
|
{
|
|
"entropy": 5.988846349716186,
|
|
"epoch": 2.572999450192433,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00043419237158322596,
|
|
"loss": 5.6296,
|
|
"mean_token_accuracy": 0.17565218657255172,
|
|
"num_tokens": 50359749.0,
|
|
"step": 25740
|
|
},
|
|
{
|
|
"entropy": 6.069468545913696,
|
|
"epoch": 2.573499275253661,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00043416714838996915,
|
|
"loss": 5.698,
|
|
"mean_token_accuracy": 0.17542275339365004,
|
|
"num_tokens": 50369910.0,
|
|
"step": 25745
|
|
},
|
|
{
|
|
"entropy": 6.145536613464356,
|
|
"epoch": 2.57399910031489,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.000434141921192108,
|
|
"loss": 5.698,
|
|
"mean_token_accuracy": 0.17012307196855544,
|
|
"num_tokens": 50380840.0,
|
|
"step": 25750
|
|
},
|
|
{
|
|
"entropy": 6.023998403549195,
|
|
"epoch": 2.574498925376118,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000434116689990277,
|
|
"loss": 5.6604,
|
|
"mean_token_accuracy": 0.17894080877304078,
|
|
"num_tokens": 50389310.0,
|
|
"step": 25755
|
|
},
|
|
{
|
|
"entropy": 6.013774824142456,
|
|
"epoch": 2.574998750437347,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00043409145478511105,
|
|
"loss": 5.7295,
|
|
"mean_token_accuracy": 0.17402278035879135,
|
|
"num_tokens": 50398412.0,
|
|
"step": 25760
|
|
},
|
|
{
|
|
"entropy": 5.97282862663269,
|
|
"epoch": 2.5754985754985755,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00043406621557724495,
|
|
"loss": 5.6004,
|
|
"mean_token_accuracy": 0.1773402988910675,
|
|
"num_tokens": 50408525.0,
|
|
"step": 25765
|
|
},
|
|
{
|
|
"entropy": 6.083196401596069,
|
|
"epoch": 2.5759984005598042,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00043404097236731396,
|
|
"loss": 5.7829,
|
|
"mean_token_accuracy": 0.16902088820934297,
|
|
"num_tokens": 50419578.0,
|
|
"step": 25770
|
|
},
|
|
{
|
|
"entropy": 6.051550054550171,
|
|
"epoch": 2.5764982256210325,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004340157251559529,
|
|
"loss": 5.669,
|
|
"mean_token_accuracy": 0.17869922071695327,
|
|
"num_tokens": 50428925.0,
|
|
"step": 25775
|
|
},
|
|
{
|
|
"entropy": 5.980451774597168,
|
|
"epoch": 2.576998050682261,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00043399047394379717,
|
|
"loss": 5.5873,
|
|
"mean_token_accuracy": 0.18410459011793137,
|
|
"num_tokens": 50438769.0,
|
|
"step": 25780
|
|
},
|
|
{
|
|
"entropy": 6.049971342086792,
|
|
"epoch": 2.57749787574349,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00043396521873148195,
|
|
"loss": 5.7392,
|
|
"mean_token_accuracy": 0.17281908094882964,
|
|
"num_tokens": 50449210.0,
|
|
"step": 25785
|
|
},
|
|
{
|
|
"entropy": 6.034308862686157,
|
|
"epoch": 2.577997700804718,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00043393995951964277,
|
|
"loss": 5.6609,
|
|
"mean_token_accuracy": 0.1724180608987808,
|
|
"num_tokens": 50458703.0,
|
|
"step": 25790
|
|
},
|
|
{
|
|
"entropy": 5.97446026802063,
|
|
"epoch": 2.578497525865947,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00043391469630891513,
|
|
"loss": 5.628,
|
|
"mean_token_accuracy": 0.17995593696832657,
|
|
"num_tokens": 50468210.0,
|
|
"step": 25795
|
|
},
|
|
{
|
|
"entropy": 5.999925565719605,
|
|
"epoch": 2.5789973509271755,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004338894290999346,
|
|
"loss": 5.6305,
|
|
"mean_token_accuracy": 0.18315281867980956,
|
|
"num_tokens": 50477726.0,
|
|
"step": 25800
|
|
},
|
|
{
|
|
"entropy": 6.030463743209839,
|
|
"epoch": 2.5794971759884042,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00043386415789333687,
|
|
"loss": 5.6102,
|
|
"mean_token_accuracy": 0.1794360101222992,
|
|
"num_tokens": 50488637.0,
|
|
"step": 25805
|
|
},
|
|
{
|
|
"entropy": 6.03476128578186,
|
|
"epoch": 2.5799970010496325,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004338388826897579,
|
|
"loss": 5.5814,
|
|
"mean_token_accuracy": 0.18444014340639114,
|
|
"num_tokens": 50498544.0,
|
|
"step": 25810
|
|
},
|
|
{
|
|
"entropy": 6.003820562362671,
|
|
"epoch": 2.580496826110861,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004338136034898335,
|
|
"loss": 5.7576,
|
|
"mean_token_accuracy": 0.16064487397670746,
|
|
"num_tokens": 50508482.0,
|
|
"step": 25815
|
|
},
|
|
{
|
|
"entropy": 6.016677474975586,
|
|
"epoch": 2.58099665117209,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004337883202941997,
|
|
"loss": 5.6135,
|
|
"mean_token_accuracy": 0.17907737642526628,
|
|
"num_tokens": 50518294.0,
|
|
"step": 25820
|
|
},
|
|
{
|
|
"entropy": 5.997594499588013,
|
|
"epoch": 2.581496476233318,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004337630331034926,
|
|
"loss": 5.6447,
|
|
"mean_token_accuracy": 0.17974233627319336,
|
|
"num_tokens": 50528403.0,
|
|
"step": 25825
|
|
},
|
|
{
|
|
"entropy": 6.024012088775635,
|
|
"epoch": 2.581996301294547,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00043373774191834844,
|
|
"loss": 5.6176,
|
|
"mean_token_accuracy": 0.17740169316530227,
|
|
"num_tokens": 50538103.0,
|
|
"step": 25830
|
|
},
|
|
{
|
|
"entropy": 5.988544702529907,
|
|
"epoch": 2.5824961263557755,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00043371244673940355,
|
|
"loss": 5.5863,
|
|
"mean_token_accuracy": 0.1862240821123123,
|
|
"num_tokens": 50548020.0,
|
|
"step": 25835
|
|
},
|
|
{
|
|
"entropy": 6.052499151229858,
|
|
"epoch": 2.582995951417004,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004336871475672943,
|
|
"loss": 5.6406,
|
|
"mean_token_accuracy": 0.1755969449877739,
|
|
"num_tokens": 50557843.0,
|
|
"step": 25840
|
|
},
|
|
{
|
|
"entropy": 6.060406160354614,
|
|
"epoch": 2.5834957764782325,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004336618444026573,
|
|
"loss": 5.7041,
|
|
"mean_token_accuracy": 0.17192864716053008,
|
|
"num_tokens": 50567377.0,
|
|
"step": 25845
|
|
},
|
|
{
|
|
"entropy": 6.033933162689209,
|
|
"epoch": 2.583995601539461,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00043363653724612903,
|
|
"loss": 5.5939,
|
|
"mean_token_accuracy": 0.18272983133792878,
|
|
"num_tokens": 50577184.0,
|
|
"step": 25850
|
|
},
|
|
{
|
|
"entropy": 6.03616099357605,
|
|
"epoch": 2.58449542660069,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00043361122609834646,
|
|
"loss": 5.6482,
|
|
"mean_token_accuracy": 0.17902942895889282,
|
|
"num_tokens": 50585859.0,
|
|
"step": 25855
|
|
},
|
|
{
|
|
"entropy": 6.016443204879761,
|
|
"epoch": 2.584995251661918,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004335859109599462,
|
|
"loss": 5.628,
|
|
"mean_token_accuracy": 0.18032461404800415,
|
|
"num_tokens": 50595627.0,
|
|
"step": 25860
|
|
},
|
|
{
|
|
"entropy": 5.959928035736084,
|
|
"epoch": 2.585495076723147,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00043356059183156514,
|
|
"loss": 5.5926,
|
|
"mean_token_accuracy": 0.18326856791973115,
|
|
"num_tokens": 50605733.0,
|
|
"step": 25865
|
|
},
|
|
{
|
|
"entropy": 6.032998323440552,
|
|
"epoch": 2.5859949017843755,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00043353526871384054,
|
|
"loss": 5.6983,
|
|
"mean_token_accuracy": 0.1707962080836296,
|
|
"num_tokens": 50615341.0,
|
|
"step": 25870
|
|
},
|
|
{
|
|
"entropy": 6.0366082191467285,
|
|
"epoch": 2.586494726845604,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004335099416074092,
|
|
"loss": 5.6097,
|
|
"mean_token_accuracy": 0.1762554630637169,
|
|
"num_tokens": 50625545.0,
|
|
"step": 25875
|
|
},
|
|
{
|
|
"entropy": 6.045047807693481,
|
|
"epoch": 2.5869945519068325,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004334846105129086,
|
|
"loss": 5.7074,
|
|
"mean_token_accuracy": 0.17274340093135834,
|
|
"num_tokens": 50635518.0,
|
|
"step": 25880
|
|
},
|
|
{
|
|
"entropy": 5.954197740554809,
|
|
"epoch": 2.587494376968061,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.000433459275430976,
|
|
"loss": 5.5419,
|
|
"mean_token_accuracy": 0.18524603992700578,
|
|
"num_tokens": 50644353.0,
|
|
"step": 25885
|
|
},
|
|
{
|
|
"entropy": 6.077037763595581,
|
|
"epoch": 2.58799420202929,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004334339363622488,
|
|
"loss": 5.7385,
|
|
"mean_token_accuracy": 0.1710638016462326,
|
|
"num_tokens": 50653911.0,
|
|
"step": 25890
|
|
},
|
|
{
|
|
"entropy": 6.062735843658447,
|
|
"epoch": 2.588494027090518,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00043340859330736454,
|
|
"loss": 5.6518,
|
|
"mean_token_accuracy": 0.1730289191007614,
|
|
"num_tokens": 50664476.0,
|
|
"step": 25895
|
|
},
|
|
{
|
|
"entropy": 6.0556127548217775,
|
|
"epoch": 2.588993852151747,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00043338324626696084,
|
|
"loss": 5.6036,
|
|
"mean_token_accuracy": 0.17683175355195999,
|
|
"num_tokens": 50673779.0,
|
|
"step": 25900
|
|
},
|
|
{
|
|
"entropy": 6.053953027725219,
|
|
"epoch": 2.5894936772129755,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004333578952416753,
|
|
"loss": 5.6062,
|
|
"mean_token_accuracy": 0.18162054866552352,
|
|
"num_tokens": 50682572.0,
|
|
"step": 25905
|
|
},
|
|
{
|
|
"entropy": 5.916374731063843,
|
|
"epoch": 2.589993502274204,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000433332540232146,
|
|
"loss": 5.5512,
|
|
"mean_token_accuracy": 0.18397713750600814,
|
|
"num_tokens": 50691553.0,
|
|
"step": 25910
|
|
},
|
|
{
|
|
"entropy": 6.014012193679809,
|
|
"epoch": 2.5904933273354325,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00043330718123901074,
|
|
"loss": 5.582,
|
|
"mean_token_accuracy": 0.18506468385457991,
|
|
"num_tokens": 50701348.0,
|
|
"step": 25915
|
|
},
|
|
{
|
|
"entropy": 5.964022874832153,
|
|
"epoch": 2.590993152396661,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00043328181826290745,
|
|
"loss": 5.6113,
|
|
"mean_token_accuracy": 0.17891876250505448,
|
|
"num_tokens": 50710586.0,
|
|
"step": 25920
|
|
},
|
|
{
|
|
"entropy": 5.982455205917359,
|
|
"epoch": 2.59149297745789,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004332564513044744,
|
|
"loss": 5.6201,
|
|
"mean_token_accuracy": 0.17991709113121032,
|
|
"num_tokens": 50720224.0,
|
|
"step": 25925
|
|
},
|
|
{
|
|
"entropy": 6.029573822021485,
|
|
"epoch": 2.591992802519118,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00043323108036434974,
|
|
"loss": 5.5858,
|
|
"mean_token_accuracy": 0.1843689888715744,
|
|
"num_tokens": 50730295.0,
|
|
"step": 25930
|
|
},
|
|
{
|
|
"entropy": 6.068397521972656,
|
|
"epoch": 2.592492627580347,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004332057054431718,
|
|
"loss": 5.6654,
|
|
"mean_token_accuracy": 0.17365404218435287,
|
|
"num_tokens": 50739516.0,
|
|
"step": 25935
|
|
},
|
|
{
|
|
"entropy": 5.982893753051758,
|
|
"epoch": 2.5929924526415755,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000433180326541579,
|
|
"loss": 5.5655,
|
|
"mean_token_accuracy": 0.1866952434182167,
|
|
"num_tokens": 50748506.0,
|
|
"step": 25940
|
|
},
|
|
{
|
|
"entropy": 6.029824876785279,
|
|
"epoch": 2.593492277702804,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004331549436602099,
|
|
"loss": 5.6783,
|
|
"mean_token_accuracy": 0.17194873988628387,
|
|
"num_tokens": 50758804.0,
|
|
"step": 25945
|
|
},
|
|
{
|
|
"entropy": 5.912535047531128,
|
|
"epoch": 2.5939921027640325,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00043312955679970317,
|
|
"loss": 5.5415,
|
|
"mean_token_accuracy": 0.1851236954331398,
|
|
"num_tokens": 50768898.0,
|
|
"step": 25950
|
|
},
|
|
{
|
|
"entropy": 6.029923439025879,
|
|
"epoch": 2.594491927825261,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00043310416596069746,
|
|
"loss": 5.6809,
|
|
"mean_token_accuracy": 0.1798834979534149,
|
|
"num_tokens": 50778625.0,
|
|
"step": 25955
|
|
},
|
|
{
|
|
"entropy": 5.992418956756592,
|
|
"epoch": 2.59499175288649,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00043307877114383167,
|
|
"loss": 5.55,
|
|
"mean_token_accuracy": 0.18468205630779266,
|
|
"num_tokens": 50787162.0,
|
|
"step": 25960
|
|
},
|
|
{
|
|
"entropy": 5.933291339874268,
|
|
"epoch": 2.595491577947718,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004330533723497445,
|
|
"loss": 5.5724,
|
|
"mean_token_accuracy": 0.18291742205619813,
|
|
"num_tokens": 50796615.0,
|
|
"step": 25965
|
|
},
|
|
{
|
|
"entropy": 6.059269523620605,
|
|
"epoch": 2.595991403008947,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00043302796957907523,
|
|
"loss": 5.7017,
|
|
"mean_token_accuracy": 0.1733262225985527,
|
|
"num_tokens": 50807381.0,
|
|
"step": 25970
|
|
},
|
|
{
|
|
"entropy": 6.105675268173218,
|
|
"epoch": 2.5964912280701755,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00043300256283246297,
|
|
"loss": 5.641,
|
|
"mean_token_accuracy": 0.17599131166934967,
|
|
"num_tokens": 50818348.0,
|
|
"step": 25975
|
|
},
|
|
{
|
|
"entropy": 6.058058404922486,
|
|
"epoch": 2.596991053131404,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00043297715211054684,
|
|
"loss": 5.6687,
|
|
"mean_token_accuracy": 0.17565441727638245,
|
|
"num_tokens": 50828688.0,
|
|
"step": 25980
|
|
},
|
|
{
|
|
"entropy": 6.038634967803955,
|
|
"epoch": 2.5974908781926325,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00043295173741396626,
|
|
"loss": 5.6468,
|
|
"mean_token_accuracy": 0.17726025730371475,
|
|
"num_tokens": 50837831.0,
|
|
"step": 25985
|
|
},
|
|
{
|
|
"entropy": 6.091867589950562,
|
|
"epoch": 2.597990703253861,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004329263187433605,
|
|
"loss": 5.6006,
|
|
"mean_token_accuracy": 0.17769330739974976,
|
|
"num_tokens": 50846998.0,
|
|
"step": 25990
|
|
},
|
|
{
|
|
"entropy": 5.931419420242309,
|
|
"epoch": 2.59849052831509,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004329008960993694,
|
|
"loss": 5.5119,
|
|
"mean_token_accuracy": 0.18563360422849656,
|
|
"num_tokens": 50856310.0,
|
|
"step": 25995
|
|
},
|
|
{
|
|
"entropy": 5.852314424514771,
|
|
"epoch": 2.598990353376318,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004328754694826322,
|
|
"loss": 5.552,
|
|
"mean_token_accuracy": 0.18880294710397721,
|
|
"num_tokens": 50867376.0,
|
|
"step": 26000
|
|
},
|
|
{
|
|
"entropy": 6.023526239395141,
|
|
"epoch": 2.599490178437547,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004328500388937889,
|
|
"loss": 5.5777,
|
|
"mean_token_accuracy": 0.19128865003585815,
|
|
"num_tokens": 50877007.0,
|
|
"step": 26005
|
|
},
|
|
{
|
|
"entropy": 6.098875188827515,
|
|
"epoch": 2.5999900034987755,
|
|
"grad_norm": 2.421875,
|
|
"learning_rate": 0.00043282460433347926,
|
|
"loss": 5.5936,
|
|
"mean_token_accuracy": 0.18624731451272963,
|
|
"num_tokens": 50886221.0,
|
|
"step": 26010
|
|
},
|
|
{
|
|
"entropy": 6.018326759338379,
|
|
"epoch": 2.600489828560004,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004327991658023431,
|
|
"loss": 5.6653,
|
|
"mean_token_accuracy": 0.17452152520418168,
|
|
"num_tokens": 50895534.0,
|
|
"step": 26015
|
|
},
|
|
{
|
|
"entropy": 5.99275689125061,
|
|
"epoch": 2.6009896536212325,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004327737233010205,
|
|
"loss": 5.6034,
|
|
"mean_token_accuracy": 0.1805785819888115,
|
|
"num_tokens": 50905987.0,
|
|
"step": 26020
|
|
},
|
|
{
|
|
"entropy": 6.039106178283691,
|
|
"epoch": 2.601489478682461,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00043274827683015174,
|
|
"loss": 5.7184,
|
|
"mean_token_accuracy": 0.1673829063773155,
|
|
"num_tokens": 50914810.0,
|
|
"step": 26025
|
|
},
|
|
{
|
|
"entropy": 6.087317276000976,
|
|
"epoch": 2.60198930374369,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00043272282639037683,
|
|
"loss": 5.6815,
|
|
"mean_token_accuracy": 0.1771216332912445,
|
|
"num_tokens": 50925115.0,
|
|
"step": 26030
|
|
},
|
|
{
|
|
"entropy": 6.142575931549072,
|
|
"epoch": 2.602489128804918,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00043269737198233627,
|
|
"loss": 5.7232,
|
|
"mean_token_accuracy": 0.17593874782323837,
|
|
"num_tokens": 50934511.0,
|
|
"step": 26035
|
|
},
|
|
{
|
|
"entropy": 5.989528512954712,
|
|
"epoch": 2.602988953866147,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004326719136066704,
|
|
"loss": 5.5963,
|
|
"mean_token_accuracy": 0.17939829230308532,
|
|
"num_tokens": 50943937.0,
|
|
"step": 26040
|
|
},
|
|
{
|
|
"entropy": 6.089645147323608,
|
|
"epoch": 2.6034887789273755,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00043264645126401977,
|
|
"loss": 5.718,
|
|
"mean_token_accuracy": 0.1659764289855957,
|
|
"num_tokens": 50952952.0,
|
|
"step": 26045
|
|
},
|
|
{
|
|
"entropy": 6.013368272781372,
|
|
"epoch": 2.603988603988604,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00043262098495502497,
|
|
"loss": 5.5694,
|
|
"mean_token_accuracy": 0.18240151554346085,
|
|
"num_tokens": 50962569.0,
|
|
"step": 26050
|
|
},
|
|
{
|
|
"entropy": 6.072065162658691,
|
|
"epoch": 2.6044884290498325,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004325955146803267,
|
|
"loss": 5.6987,
|
|
"mean_token_accuracy": 0.17338844984769822,
|
|
"num_tokens": 50971520.0,
|
|
"step": 26055
|
|
},
|
|
{
|
|
"entropy": 6.008082675933838,
|
|
"epoch": 2.604988254111061,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004325700404405659,
|
|
"loss": 5.68,
|
|
"mean_token_accuracy": 0.17574826627969742,
|
|
"num_tokens": 50981209.0,
|
|
"step": 26060
|
|
},
|
|
{
|
|
"entropy": 6.026397323608398,
|
|
"epoch": 2.60548807917229,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004325445622363834,
|
|
"loss": 5.6551,
|
|
"mean_token_accuracy": 0.17098330035805703,
|
|
"num_tokens": 50991245.0,
|
|
"step": 26065
|
|
},
|
|
{
|
|
"entropy": 6.083217144012451,
|
|
"epoch": 2.605987904233518,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004325190800684203,
|
|
"loss": 5.6634,
|
|
"mean_token_accuracy": 0.17734452784061433,
|
|
"num_tokens": 51000341.0,
|
|
"step": 26070
|
|
},
|
|
{
|
|
"entropy": 6.215442132949829,
|
|
"epoch": 2.606487729294747,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004324935939373176,
|
|
"loss": 5.789,
|
|
"mean_token_accuracy": 0.16515380293130874,
|
|
"num_tokens": 51010136.0,
|
|
"step": 26075
|
|
},
|
|
{
|
|
"entropy": 6.060026931762695,
|
|
"epoch": 2.6069875543559755,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004324681038437166,
|
|
"loss": 5.7261,
|
|
"mean_token_accuracy": 0.16916718780994416,
|
|
"num_tokens": 51020751.0,
|
|
"step": 26080
|
|
},
|
|
{
|
|
"entropy": 6.108510303497314,
|
|
"epoch": 2.607487379417204,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004324426097882587,
|
|
"loss": 5.773,
|
|
"mean_token_accuracy": 0.170938341319561,
|
|
"num_tokens": 51031546.0,
|
|
"step": 26085
|
|
},
|
|
{
|
|
"entropy": 6.0652822971344,
|
|
"epoch": 2.6079872044784325,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004324171117715852,
|
|
"loss": 5.6063,
|
|
"mean_token_accuracy": 0.18524561524391175,
|
|
"num_tokens": 51041351.0,
|
|
"step": 26090
|
|
},
|
|
{
|
|
"entropy": 6.001061630249024,
|
|
"epoch": 2.608487029539661,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00043239160979433765,
|
|
"loss": 5.6126,
|
|
"mean_token_accuracy": 0.17446594834327697,
|
|
"num_tokens": 51050450.0,
|
|
"step": 26095
|
|
},
|
|
{
|
|
"entropy": 5.9778162956237795,
|
|
"epoch": 2.6089868546008894,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004323661038571578,
|
|
"loss": 5.5631,
|
|
"mean_token_accuracy": 0.18259495347738267,
|
|
"num_tokens": 51059895.0,
|
|
"step": 26100
|
|
},
|
|
{
|
|
"entropy": 5.997101640701294,
|
|
"epoch": 2.609486679662118,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00043234059396068725,
|
|
"loss": 5.6703,
|
|
"mean_token_accuracy": 0.17905840873718262,
|
|
"num_tokens": 51068984.0,
|
|
"step": 26105
|
|
},
|
|
{
|
|
"entropy": 5.944442272186279,
|
|
"epoch": 2.609986504723347,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004323150801055677,
|
|
"loss": 5.6198,
|
|
"mean_token_accuracy": 0.18191674947738648,
|
|
"num_tokens": 51079087.0,
|
|
"step": 26110
|
|
},
|
|
{
|
|
"entropy": 6.059824657440186,
|
|
"epoch": 2.6104863297845755,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004322895622924414,
|
|
"loss": 5.641,
|
|
"mean_token_accuracy": 0.17652402967214584,
|
|
"num_tokens": 51089306.0,
|
|
"step": 26115
|
|
},
|
|
{
|
|
"entropy": 6.043988418579102,
|
|
"epoch": 2.610986154845804,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004322640405219501,
|
|
"loss": 5.6421,
|
|
"mean_token_accuracy": 0.17675406038761138,
|
|
"num_tokens": 51098998.0,
|
|
"step": 26120
|
|
},
|
|
{
|
|
"entropy": 5.986744832992554,
|
|
"epoch": 2.6114859799070325,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00043223851479473596,
|
|
"loss": 5.5453,
|
|
"mean_token_accuracy": 0.19311549961566926,
|
|
"num_tokens": 51108995.0,
|
|
"step": 26125
|
|
},
|
|
{
|
|
"entropy": 5.990160131454468,
|
|
"epoch": 2.611985804968261,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00043221298511144133,
|
|
"loss": 5.507,
|
|
"mean_token_accuracy": 0.1844029188156128,
|
|
"num_tokens": 51118574.0,
|
|
"step": 26130
|
|
},
|
|
{
|
|
"entropy": 5.905547428131103,
|
|
"epoch": 2.6124856300294894,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00043218745147270845,
|
|
"loss": 5.5479,
|
|
"mean_token_accuracy": 0.1870749443769455,
|
|
"num_tokens": 51128438.0,
|
|
"step": 26135
|
|
},
|
|
{
|
|
"entropy": 6.090448236465454,
|
|
"epoch": 2.612985455090718,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00043216191387917966,
|
|
"loss": 5.6646,
|
|
"mean_token_accuracy": 0.17306902259588242,
|
|
"num_tokens": 51137223.0,
|
|
"step": 26140
|
|
},
|
|
{
|
|
"entropy": 6.078333473205566,
|
|
"epoch": 2.613485280151947,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004321363723314976,
|
|
"loss": 5.7113,
|
|
"mean_token_accuracy": 0.17297292798757552,
|
|
"num_tokens": 51147299.0,
|
|
"step": 26145
|
|
},
|
|
{
|
|
"entropy": 6.028052806854248,
|
|
"epoch": 2.6139851052131755,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00043211082683030483,
|
|
"loss": 5.7467,
|
|
"mean_token_accuracy": 0.16447574347257615,
|
|
"num_tokens": 51157782.0,
|
|
"step": 26150
|
|
},
|
|
{
|
|
"entropy": 6.002382564544678,
|
|
"epoch": 2.614484930274404,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00043208527737624406,
|
|
"loss": 5.6277,
|
|
"mean_token_accuracy": 0.17985670417547225,
|
|
"num_tokens": 51168328.0,
|
|
"step": 26155
|
|
},
|
|
{
|
|
"entropy": 6.021002912521363,
|
|
"epoch": 2.6149847553356325,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00043205972396995825,
|
|
"loss": 5.6486,
|
|
"mean_token_accuracy": 0.1786860778927803,
|
|
"num_tokens": 51177619.0,
|
|
"step": 26160
|
|
},
|
|
{
|
|
"entropy": 6.06429533958435,
|
|
"epoch": 2.615484580396861,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004320341666120901,
|
|
"loss": 5.5944,
|
|
"mean_token_accuracy": 0.18410515636205674,
|
|
"num_tokens": 51186039.0,
|
|
"step": 26165
|
|
},
|
|
{
|
|
"entropy": 5.984625768661499,
|
|
"epoch": 2.6159844054580894,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00043200860530328287,
|
|
"loss": 5.5296,
|
|
"mean_token_accuracy": 0.1933184579014778,
|
|
"num_tokens": 51195798.0,
|
|
"step": 26170
|
|
},
|
|
{
|
|
"entropy": 6.02772798538208,
|
|
"epoch": 2.616484230519318,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00043198304004417933,
|
|
"loss": 5.6997,
|
|
"mean_token_accuracy": 0.17509601265192032,
|
|
"num_tokens": 51206020.0,
|
|
"step": 26175
|
|
},
|
|
{
|
|
"entropy": 6.0427577018737795,
|
|
"epoch": 2.616984055580547,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00043195747083542296,
|
|
"loss": 5.62,
|
|
"mean_token_accuracy": 0.1766590729355812,
|
|
"num_tokens": 51216376.0,
|
|
"step": 26180
|
|
},
|
|
{
|
|
"entropy": 5.912385511398315,
|
|
"epoch": 2.6174838806417755,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000431931897677657,
|
|
"loss": 5.5312,
|
|
"mean_token_accuracy": 0.17912169247865678,
|
|
"num_tokens": 51225542.0,
|
|
"step": 26185
|
|
},
|
|
{
|
|
"entropy": 6.043753147125244,
|
|
"epoch": 2.617983705703004,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00043190632057152497,
|
|
"loss": 5.7056,
|
|
"mean_token_accuracy": 0.1704210862517357,
|
|
"num_tokens": 51235649.0,
|
|
"step": 26190
|
|
},
|
|
{
|
|
"entropy": 6.028866958618164,
|
|
"epoch": 2.6184835307642325,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004318807395176702,
|
|
"loss": 5.6685,
|
|
"mean_token_accuracy": 0.1760180577635765,
|
|
"num_tokens": 51245665.0,
|
|
"step": 26195
|
|
},
|
|
{
|
|
"entropy": 6.007025623321534,
|
|
"epoch": 2.618983355825461,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004318551545167364,
|
|
"loss": 5.6472,
|
|
"mean_token_accuracy": 0.17228757292032243,
|
|
"num_tokens": 51255213.0,
|
|
"step": 26200
|
|
},
|
|
{
|
|
"entropy": 5.972498369216919,
|
|
"epoch": 2.6194831808866894,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004318295655693674,
|
|
"loss": 5.5479,
|
|
"mean_token_accuracy": 0.19134253710508348,
|
|
"num_tokens": 51264742.0,
|
|
"step": 26205
|
|
},
|
|
{
|
|
"entropy": 5.975474691390991,
|
|
"epoch": 2.619983005947918,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00043180397267620675,
|
|
"loss": 5.6678,
|
|
"mean_token_accuracy": 0.17780322432518006,
|
|
"num_tokens": 51275135.0,
|
|
"step": 26210
|
|
},
|
|
{
|
|
"entropy": 6.00389461517334,
|
|
"epoch": 2.620482831009147,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004317783758378985,
|
|
"loss": 5.5832,
|
|
"mean_token_accuracy": 0.18354176431894303,
|
|
"num_tokens": 51285285.0,
|
|
"step": 26215
|
|
},
|
|
{
|
|
"entropy": 6.032405614852905,
|
|
"epoch": 2.6209826560703755,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00043175277505508677,
|
|
"loss": 5.6967,
|
|
"mean_token_accuracy": 0.18026851266622543,
|
|
"num_tokens": 51294880.0,
|
|
"step": 26220
|
|
},
|
|
{
|
|
"entropy": 6.067369413375855,
|
|
"epoch": 2.621482481131604,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004317271703284154,
|
|
"loss": 5.728,
|
|
"mean_token_accuracy": 0.17132726609706878,
|
|
"num_tokens": 51305585.0,
|
|
"step": 26225
|
|
},
|
|
{
|
|
"entropy": 6.07272777557373,
|
|
"epoch": 2.6219823061928325,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00043170156165852887,
|
|
"loss": 5.6776,
|
|
"mean_token_accuracy": 0.1797110840678215,
|
|
"num_tokens": 51315377.0,
|
|
"step": 26230
|
|
},
|
|
{
|
|
"entropy": 6.030005741119385,
|
|
"epoch": 2.622482131254061,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004316759490460713,
|
|
"loss": 5.6085,
|
|
"mean_token_accuracy": 0.18254674226045609,
|
|
"num_tokens": 51325800.0,
|
|
"step": 26235
|
|
},
|
|
{
|
|
"entropy": 5.914257431030274,
|
|
"epoch": 2.6229819563152894,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.00043165033249168723,
|
|
"loss": 5.5129,
|
|
"mean_token_accuracy": 0.18513756543397902,
|
|
"num_tokens": 51335138.0,
|
|
"step": 26240
|
|
},
|
|
{
|
|
"entropy": 6.013012886047363,
|
|
"epoch": 2.623481781376518,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00043162471199602103,
|
|
"loss": 5.6314,
|
|
"mean_token_accuracy": 0.1799275115132332,
|
|
"num_tokens": 51345871.0,
|
|
"step": 26245
|
|
},
|
|
{
|
|
"entropy": 6.022783899307251,
|
|
"epoch": 2.623981606437747,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00043159908755971746,
|
|
"loss": 5.6458,
|
|
"mean_token_accuracy": 0.17640068084001542,
|
|
"num_tokens": 51354774.0,
|
|
"step": 26250
|
|
},
|
|
{
|
|
"entropy": 5.961348628997802,
|
|
"epoch": 2.6244814314989755,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00043157345918342103,
|
|
"loss": 5.6086,
|
|
"mean_token_accuracy": 0.18057195246219634,
|
|
"num_tokens": 51364641.0,
|
|
"step": 26255
|
|
},
|
|
{
|
|
"entropy": 5.992480850219726,
|
|
"epoch": 2.624981256560204,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004315478268677768,
|
|
"loss": 5.6531,
|
|
"mean_token_accuracy": 0.17706194072961806,
|
|
"num_tokens": 51373821.0,
|
|
"step": 26260
|
|
},
|
|
{
|
|
"entropy": 6.087594795227051,
|
|
"epoch": 2.6254810816214325,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004315221906134294,
|
|
"loss": 5.7157,
|
|
"mean_token_accuracy": 0.1761400133371353,
|
|
"num_tokens": 51383926.0,
|
|
"step": 26265
|
|
},
|
|
{
|
|
"entropy": 5.9421913623809814,
|
|
"epoch": 2.625980906682661,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00043149655042102404,
|
|
"loss": 5.4729,
|
|
"mean_token_accuracy": 0.19075075387954712,
|
|
"num_tokens": 51393254.0,
|
|
"step": 26270
|
|
},
|
|
{
|
|
"entropy": 5.961695146560669,
|
|
"epoch": 2.6264807317438894,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00043147090629120575,
|
|
"loss": 5.6447,
|
|
"mean_token_accuracy": 0.1773478463292122,
|
|
"num_tokens": 51403890.0,
|
|
"step": 26275
|
|
},
|
|
{
|
|
"entropy": 6.010869741439819,
|
|
"epoch": 2.626980556805118,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.0004314452582246197,
|
|
"loss": 5.6434,
|
|
"mean_token_accuracy": 0.18271817564964293,
|
|
"num_tokens": 51413309.0,
|
|
"step": 26280
|
|
},
|
|
{
|
|
"entropy": 6.0121783256530765,
|
|
"epoch": 2.627480381866347,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00043141960622191116,
|
|
"loss": 5.6388,
|
|
"mean_token_accuracy": 0.17735054343938828,
|
|
"num_tokens": 51423364.0,
|
|
"step": 26285
|
|
},
|
|
{
|
|
"entropy": 5.972802972793579,
|
|
"epoch": 2.6279802069275755,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00043139395028372565,
|
|
"loss": 5.561,
|
|
"mean_token_accuracy": 0.18370341658592224,
|
|
"num_tokens": 51434105.0,
|
|
"step": 26290
|
|
},
|
|
{
|
|
"entropy": 5.965019083023071,
|
|
"epoch": 2.6284800319888038,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00043136829041070856,
|
|
"loss": 5.6409,
|
|
"mean_token_accuracy": 0.17419401109218596,
|
|
"num_tokens": 51442980.0,
|
|
"step": 26295
|
|
},
|
|
{
|
|
"entropy": 6.008703804016113,
|
|
"epoch": 2.6289798570500325,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00043134262660350555,
|
|
"loss": 5.6282,
|
|
"mean_token_accuracy": 0.1835736706852913,
|
|
"num_tokens": 51452659.0,
|
|
"step": 26300
|
|
},
|
|
{
|
|
"entropy": 5.9968503475189205,
|
|
"epoch": 2.629479682111261,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004313169588627622,
|
|
"loss": 5.57,
|
|
"mean_token_accuracy": 0.1790195032954216,
|
|
"num_tokens": 51462212.0,
|
|
"step": 26305
|
|
},
|
|
{
|
|
"entropy": 5.987971639633178,
|
|
"epoch": 2.6299795071724894,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004312912871891245,
|
|
"loss": 5.6853,
|
|
"mean_token_accuracy": 0.17035162597894668,
|
|
"num_tokens": 51472066.0,
|
|
"step": 26310
|
|
},
|
|
{
|
|
"entropy": 5.978605699539185,
|
|
"epoch": 2.630479332233718,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004312656115832381,
|
|
"loss": 5.6299,
|
|
"mean_token_accuracy": 0.1791704073548317,
|
|
"num_tokens": 51482345.0,
|
|
"step": 26315
|
|
},
|
|
{
|
|
"entropy": 6.108958625793457,
|
|
"epoch": 2.630979157294947,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00043123993204574926,
|
|
"loss": 5.6796,
|
|
"mean_token_accuracy": 0.17657088488340378,
|
|
"num_tokens": 51493259.0,
|
|
"step": 26320
|
|
},
|
|
{
|
|
"entropy": 6.03445029258728,
|
|
"epoch": 2.6314789823561755,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00043121424857730384,
|
|
"loss": 5.6662,
|
|
"mean_token_accuracy": 0.17479225397109985,
|
|
"num_tokens": 51503105.0,
|
|
"step": 26325
|
|
},
|
|
{
|
|
"entropy": 5.966983509063721,
|
|
"epoch": 2.6319788074174038,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004311885611785482,
|
|
"loss": 5.583,
|
|
"mean_token_accuracy": 0.18534208685159684,
|
|
"num_tokens": 51512650.0,
|
|
"step": 26330
|
|
},
|
|
{
|
|
"entropy": 5.9500244140625,
|
|
"epoch": 2.6324786324786325,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00043116286985012847,
|
|
"loss": 5.5653,
|
|
"mean_token_accuracy": 0.18240073472261428,
|
|
"num_tokens": 51521457.0,
|
|
"step": 26335
|
|
},
|
|
{
|
|
"entropy": 6.018056774139405,
|
|
"epoch": 2.632978457539861,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00043113717459269116,
|
|
"loss": 5.6596,
|
|
"mean_token_accuracy": 0.18261127322912216,
|
|
"num_tokens": 51530715.0,
|
|
"step": 26340
|
|
},
|
|
{
|
|
"entropy": 6.019969701766968,
|
|
"epoch": 2.6334782826010894,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004311114754068827,
|
|
"loss": 5.6377,
|
|
"mean_token_accuracy": 0.18167367726564407,
|
|
"num_tokens": 51540243.0,
|
|
"step": 26345
|
|
},
|
|
{
|
|
"entropy": 6.002894926071167,
|
|
"epoch": 2.633978107662318,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004310857722933497,
|
|
"loss": 5.5886,
|
|
"mean_token_accuracy": 0.18404884934425353,
|
|
"num_tokens": 51550191.0,
|
|
"step": 26350
|
|
},
|
|
{
|
|
"entropy": 6.0483723163604735,
|
|
"epoch": 2.634477932723547,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00043106006525273896,
|
|
"loss": 5.6798,
|
|
"mean_token_accuracy": 0.17778917253017426,
|
|
"num_tokens": 51559707.0,
|
|
"step": 26355
|
|
},
|
|
{
|
|
"entropy": 5.939345216751098,
|
|
"epoch": 2.6349777577847755,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004310343542856969,
|
|
"loss": 5.6018,
|
|
"mean_token_accuracy": 0.18620568811893462,
|
|
"num_tokens": 51569146.0,
|
|
"step": 26360
|
|
},
|
|
{
|
|
"entropy": 6.060904169082642,
|
|
"epoch": 2.6354775828460038,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00043100863939287077,
|
|
"loss": 5.6893,
|
|
"mean_token_accuracy": 0.1733599364757538,
|
|
"num_tokens": 51578301.0,
|
|
"step": 26365
|
|
},
|
|
{
|
|
"entropy": 6.121021032333374,
|
|
"epoch": 2.6359774079072325,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004309829205749074,
|
|
"loss": 5.7248,
|
|
"mean_token_accuracy": 0.16951099783182144,
|
|
"num_tokens": 51587474.0,
|
|
"step": 26370
|
|
},
|
|
{
|
|
"entropy": 6.000983715057373,
|
|
"epoch": 2.636477232968461,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00043095719783245386,
|
|
"loss": 5.6717,
|
|
"mean_token_accuracy": 0.17985575199127196,
|
|
"num_tokens": 51597166.0,
|
|
"step": 26375
|
|
},
|
|
{
|
|
"entropy": 5.944950246810913,
|
|
"epoch": 2.6369770580296894,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00043093147116615737,
|
|
"loss": 5.5841,
|
|
"mean_token_accuracy": 0.18208354264497756,
|
|
"num_tokens": 51606448.0,
|
|
"step": 26380
|
|
},
|
|
{
|
|
"entropy": 5.990692043304444,
|
|
"epoch": 2.637476883090918,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004309057405766652,
|
|
"loss": 5.6255,
|
|
"mean_token_accuracy": 0.18297402411699296,
|
|
"num_tokens": 51615901.0,
|
|
"step": 26385
|
|
},
|
|
{
|
|
"entropy": 6.070221900939941,
|
|
"epoch": 2.637976708152147,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00043088000606462474,
|
|
"loss": 5.6228,
|
|
"mean_token_accuracy": 0.18099315017461776,
|
|
"num_tokens": 51624798.0,
|
|
"step": 26390
|
|
},
|
|
{
|
|
"entropy": 5.994387006759643,
|
|
"epoch": 2.6384765332133755,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00043085426763068334,
|
|
"loss": 5.6032,
|
|
"mean_token_accuracy": 0.17655272483825685,
|
|
"num_tokens": 51634359.0,
|
|
"step": 26395
|
|
},
|
|
{
|
|
"entropy": 6.026086139678955,
|
|
"epoch": 2.6389763582746038,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00043082852527548876,
|
|
"loss": 5.6764,
|
|
"mean_token_accuracy": 0.17749617695808412,
|
|
"num_tokens": 51644251.0,
|
|
"step": 26400
|
|
},
|
|
{
|
|
"entropy": 6.09981861114502,
|
|
"epoch": 2.6394761833358324,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004308027789996886,
|
|
"loss": 5.6858,
|
|
"mean_token_accuracy": 0.17415545582771302,
|
|
"num_tokens": 51653741.0,
|
|
"step": 26405
|
|
},
|
|
{
|
|
"entropy": 6.02845458984375,
|
|
"epoch": 2.639976008397061,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004307770288039306,
|
|
"loss": 5.6604,
|
|
"mean_token_accuracy": 0.17651582956314088,
|
|
"num_tokens": 51663174.0,
|
|
"step": 26410
|
|
},
|
|
{
|
|
"entropy": 6.061994791030884,
|
|
"epoch": 2.6404758334582894,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00043075127468886264,
|
|
"loss": 5.7578,
|
|
"mean_token_accuracy": 0.16715817749500275,
|
|
"num_tokens": 51673194.0,
|
|
"step": 26415
|
|
},
|
|
{
|
|
"entropy": 6.029434156417847,
|
|
"epoch": 2.640975658519518,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00043072551665513265,
|
|
"loss": 5.6082,
|
|
"mean_token_accuracy": 0.17869900166988373,
|
|
"num_tokens": 51682211.0,
|
|
"step": 26420
|
|
},
|
|
{
|
|
"entropy": 6.012693309783936,
|
|
"epoch": 2.641475483580747,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00043069975470338875,
|
|
"loss": 5.6337,
|
|
"mean_token_accuracy": 0.1813640460371971,
|
|
"num_tokens": 51692005.0,
|
|
"step": 26425
|
|
},
|
|
{
|
|
"entropy": 6.110755062103271,
|
|
"epoch": 2.6419753086419755,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00043067398883427907,
|
|
"loss": 5.6516,
|
|
"mean_token_accuracy": 0.18432620465755462,
|
|
"num_tokens": 51701451.0,
|
|
"step": 26430
|
|
},
|
|
{
|
|
"entropy": 5.976279783248901,
|
|
"epoch": 2.6424751337032037,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00043064821904845185,
|
|
"loss": 5.5349,
|
|
"mean_token_accuracy": 0.18334961980581282,
|
|
"num_tokens": 51710894.0,
|
|
"step": 26435
|
|
},
|
|
{
|
|
"entropy": 6.05038537979126,
|
|
"epoch": 2.6429749587644324,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004306224453465556,
|
|
"loss": 5.6921,
|
|
"mean_token_accuracy": 0.17572889626026153,
|
|
"num_tokens": 51721984.0,
|
|
"step": 26440
|
|
},
|
|
{
|
|
"entropy": 5.943293523788452,
|
|
"epoch": 2.643474783825661,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00043059666772923854,
|
|
"loss": 5.5555,
|
|
"mean_token_accuracy": 0.18691188246011733,
|
|
"num_tokens": 51731816.0,
|
|
"step": 26445
|
|
},
|
|
{
|
|
"entropy": 6.050026798248291,
|
|
"epoch": 2.6439746088868894,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004305708861971495,
|
|
"loss": 5.7265,
|
|
"mean_token_accuracy": 0.18147789388895036,
|
|
"num_tokens": 51743661.0,
|
|
"step": 26450
|
|
},
|
|
{
|
|
"entropy": 6.024900197982788,
|
|
"epoch": 2.644474433948118,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004305451007509369,
|
|
"loss": 5.6857,
|
|
"mean_token_accuracy": 0.16884540766477585,
|
|
"num_tokens": 51753468.0,
|
|
"step": 26455
|
|
},
|
|
{
|
|
"entropy": 6.034595632553101,
|
|
"epoch": 2.644974259009347,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004305193113912496,
|
|
"loss": 5.6535,
|
|
"mean_token_accuracy": 0.17917366474866867,
|
|
"num_tokens": 51763125.0,
|
|
"step": 26460
|
|
},
|
|
{
|
|
"entropy": 6.034744453430176,
|
|
"epoch": 2.6454740840705755,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00043049351811873645,
|
|
"loss": 5.6502,
|
|
"mean_token_accuracy": 0.18027815371751785,
|
|
"num_tokens": 51773229.0,
|
|
"step": 26465
|
|
},
|
|
{
|
|
"entropy": 5.988840198516845,
|
|
"epoch": 2.6459739091318037,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004304677209340464,
|
|
"loss": 5.5941,
|
|
"mean_token_accuracy": 0.18184377253055573,
|
|
"num_tokens": 51783296.0,
|
|
"step": 26470
|
|
},
|
|
{
|
|
"entropy": 5.9701926708221436,
|
|
"epoch": 2.6464737341930324,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00043044191983782846,
|
|
"loss": 5.5768,
|
|
"mean_token_accuracy": 0.17987361848354338,
|
|
"num_tokens": 51792083.0,
|
|
"step": 26475
|
|
},
|
|
{
|
|
"entropy": 6.0462440013885494,
|
|
"epoch": 2.646973559254261,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00043041611483073187,
|
|
"loss": 5.7463,
|
|
"mean_token_accuracy": 0.17709808498620988,
|
|
"num_tokens": 51802269.0,
|
|
"step": 26480
|
|
},
|
|
{
|
|
"entropy": 6.046507167816162,
|
|
"epoch": 2.6474733843154894,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004303903059134059,
|
|
"loss": 5.6225,
|
|
"mean_token_accuracy": 0.18260800391435622,
|
|
"num_tokens": 51812192.0,
|
|
"step": 26485
|
|
},
|
|
{
|
|
"entropy": 6.019453763961792,
|
|
"epoch": 2.647973209376718,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00043036449308649967,
|
|
"loss": 5.644,
|
|
"mean_token_accuracy": 0.17620814442634583,
|
|
"num_tokens": 51822065.0,
|
|
"step": 26490
|
|
},
|
|
{
|
|
"entropy": 6.067802286148071,
|
|
"epoch": 2.648473034437947,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00043033867635066287,
|
|
"loss": 5.6623,
|
|
"mean_token_accuracy": 0.1760426416993141,
|
|
"num_tokens": 51831470.0,
|
|
"step": 26495
|
|
},
|
|
{
|
|
"entropy": 6.05645866394043,
|
|
"epoch": 2.6489728594991755,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004303128557065448,
|
|
"loss": 5.6663,
|
|
"mean_token_accuracy": 0.1735011026263237,
|
|
"num_tokens": 51841969.0,
|
|
"step": 26500
|
|
},
|
|
{
|
|
"entropy": 6.033924770355225,
|
|
"epoch": 2.6494726845604037,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004302870311547954,
|
|
"loss": 5.6674,
|
|
"mean_token_accuracy": 0.1727770373225212,
|
|
"num_tokens": 51851513.0,
|
|
"step": 26505
|
|
},
|
|
{
|
|
"entropy": 6.09293270111084,
|
|
"epoch": 2.6499725096216324,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00043026120269606423,
|
|
"loss": 5.634,
|
|
"mean_token_accuracy": 0.1796199917793274,
|
|
"num_tokens": 51860791.0,
|
|
"step": 26510
|
|
},
|
|
{
|
|
"entropy": 6.042760992050171,
|
|
"epoch": 2.650472334682861,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00043023537033100106,
|
|
"loss": 5.6567,
|
|
"mean_token_accuracy": 0.17709647864103317,
|
|
"num_tokens": 51871124.0,
|
|
"step": 26515
|
|
},
|
|
{
|
|
"entropy": 5.974906921386719,
|
|
"epoch": 2.6509721597440894,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00043020953406025606,
|
|
"loss": 5.5733,
|
|
"mean_token_accuracy": 0.18850859999656677,
|
|
"num_tokens": 51879183.0,
|
|
"step": 26520
|
|
},
|
|
{
|
|
"entropy": 5.922607946395874,
|
|
"epoch": 2.651471984805318,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000430183693884479,
|
|
"loss": 5.5882,
|
|
"mean_token_accuracy": 0.18533850014209746,
|
|
"num_tokens": 51889824.0,
|
|
"step": 26525
|
|
},
|
|
{
|
|
"entropy": 5.899206209182739,
|
|
"epoch": 2.651971809866547,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004301578498043202,
|
|
"loss": 5.536,
|
|
"mean_token_accuracy": 0.19576661735773088,
|
|
"num_tokens": 51899561.0,
|
|
"step": 26530
|
|
},
|
|
{
|
|
"entropy": 5.983383321762085,
|
|
"epoch": 2.6524716349277755,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00043013200182042983,
|
|
"loss": 5.6601,
|
|
"mean_token_accuracy": 0.17595523595809937,
|
|
"num_tokens": 51908359.0,
|
|
"step": 26535
|
|
},
|
|
{
|
|
"entropy": 5.98090558052063,
|
|
"epoch": 2.6529714599890037,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00043010614993345815,
|
|
"loss": 5.5415,
|
|
"mean_token_accuracy": 0.18224378377199174,
|
|
"num_tokens": 51917782.0,
|
|
"step": 26540
|
|
},
|
|
{
|
|
"entropy": 5.974357748031617,
|
|
"epoch": 2.6534712850502324,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004300802941440557,
|
|
"loss": 5.5933,
|
|
"mean_token_accuracy": 0.17967232167720795,
|
|
"num_tokens": 51926218.0,
|
|
"step": 26545
|
|
},
|
|
{
|
|
"entropy": 5.908923768997193,
|
|
"epoch": 2.653971110111461,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004300544344528729,
|
|
"loss": 5.4857,
|
|
"mean_token_accuracy": 0.18951882421970367,
|
|
"num_tokens": 51936541.0,
|
|
"step": 26550
|
|
},
|
|
{
|
|
"entropy": 6.097597217559814,
|
|
"epoch": 2.6544709351726894,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00043002857086056053,
|
|
"loss": 5.7362,
|
|
"mean_token_accuracy": 0.17154934108257294,
|
|
"num_tokens": 51945158.0,
|
|
"step": 26555
|
|
},
|
|
{
|
|
"entropy": 6.034967613220215,
|
|
"epoch": 2.654970760233918,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004300027033677691,
|
|
"loss": 5.6705,
|
|
"mean_token_accuracy": 0.17571485191583633,
|
|
"num_tokens": 51955402.0,
|
|
"step": 26560
|
|
},
|
|
{
|
|
"entropy": 5.99038610458374,
|
|
"epoch": 2.655470585295147,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004299768319751496,
|
|
"loss": 5.6091,
|
|
"mean_token_accuracy": 0.18567289412021637,
|
|
"num_tokens": 51965038.0,
|
|
"step": 26565
|
|
},
|
|
{
|
|
"entropy": 6.062204074859619,
|
|
"epoch": 2.6559704103563755,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004299509566833529,
|
|
"loss": 5.6627,
|
|
"mean_token_accuracy": 0.17254490703344344,
|
|
"num_tokens": 51974967.0,
|
|
"step": 26570
|
|
},
|
|
{
|
|
"entropy": 5.995502233505249,
|
|
"epoch": 2.6564702354176037,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00042992507749302995,
|
|
"loss": 5.6665,
|
|
"mean_token_accuracy": 0.17881798446178437,
|
|
"num_tokens": 51985010.0,
|
|
"step": 26575
|
|
},
|
|
{
|
|
"entropy": 6.042936658859253,
|
|
"epoch": 2.6569700604788324,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00042989919440483194,
|
|
"loss": 5.5925,
|
|
"mean_token_accuracy": 0.18506261557340623,
|
|
"num_tokens": 51994620.0,
|
|
"step": 26580
|
|
},
|
|
{
|
|
"entropy": 6.046794033050537,
|
|
"epoch": 2.657469885540061,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004298733074194101,
|
|
"loss": 5.5716,
|
|
"mean_token_accuracy": 0.18231419324874878,
|
|
"num_tokens": 52003475.0,
|
|
"step": 26585
|
|
},
|
|
{
|
|
"entropy": 6.020167684555053,
|
|
"epoch": 2.6579697106012894,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004298474165374156,
|
|
"loss": 5.5985,
|
|
"mean_token_accuracy": 0.1824175998568535,
|
|
"num_tokens": 52013303.0,
|
|
"step": 26590
|
|
},
|
|
{
|
|
"entropy": 5.932922744750977,
|
|
"epoch": 2.658469535662518,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004298215217595,
|
|
"loss": 5.558,
|
|
"mean_token_accuracy": 0.18501343727111816,
|
|
"num_tokens": 52021944.0,
|
|
"step": 26595
|
|
},
|
|
{
|
|
"entropy": 6.029012393951416,
|
|
"epoch": 2.658969360723747,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00042979562308631476,
|
|
"loss": 5.6703,
|
|
"mean_token_accuracy": 0.17665086984634398,
|
|
"num_tokens": 52030590.0,
|
|
"step": 26600
|
|
},
|
|
{
|
|
"entropy": 6.01625394821167,
|
|
"epoch": 2.6594691857849755,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004297697205185115,
|
|
"loss": 5.6311,
|
|
"mean_token_accuracy": 0.177615986764431,
|
|
"num_tokens": 52039861.0,
|
|
"step": 26605
|
|
},
|
|
{
|
|
"entropy": 6.099452066421509,
|
|
"epoch": 2.6599690108462037,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004297438140567419,
|
|
"loss": 5.7137,
|
|
"mean_token_accuracy": 0.17134196907281876,
|
|
"num_tokens": 52051598.0,
|
|
"step": 26610
|
|
},
|
|
{
|
|
"entropy": 6.094136476516724,
|
|
"epoch": 2.6604688359074324,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004297179037016577,
|
|
"loss": 5.7187,
|
|
"mean_token_accuracy": 0.17662692666053773,
|
|
"num_tokens": 52060662.0,
|
|
"step": 26615
|
|
},
|
|
{
|
|
"entropy": 6.023752450942993,
|
|
"epoch": 2.6609686609686607,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00042969198945391084,
|
|
"loss": 5.6688,
|
|
"mean_token_accuracy": 0.17526323795318605,
|
|
"num_tokens": 52070166.0,
|
|
"step": 26620
|
|
},
|
|
{
|
|
"entropy": 5.9543163776397705,
|
|
"epoch": 2.6614684860298894,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004296660713141534,
|
|
"loss": 5.5678,
|
|
"mean_token_accuracy": 0.18376553803682327,
|
|
"num_tokens": 52079409.0,
|
|
"step": 26625
|
|
},
|
|
{
|
|
"entropy": 6.0083435535430905,
|
|
"epoch": 2.661968311091118,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00042964014928303733,
|
|
"loss": 5.6837,
|
|
"mean_token_accuracy": 0.1830224171280861,
|
|
"num_tokens": 52090419.0,
|
|
"step": 26630
|
|
},
|
|
{
|
|
"entropy": 6.091170883178711,
|
|
"epoch": 2.662468136152347,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.000429614223361215,
|
|
"loss": 5.6813,
|
|
"mean_token_accuracy": 0.1827877417206764,
|
|
"num_tokens": 52100681.0,
|
|
"step": 26635
|
|
},
|
|
{
|
|
"entropy": 6.025186395645141,
|
|
"epoch": 2.6629679612135755,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004295882935493385,
|
|
"loss": 5.6032,
|
|
"mean_token_accuracy": 0.18265023827552795,
|
|
"num_tokens": 52109852.0,
|
|
"step": 26640
|
|
},
|
|
{
|
|
"entropy": 6.005277538299561,
|
|
"epoch": 2.6634677862748037,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00042956235984806034,
|
|
"loss": 5.6105,
|
|
"mean_token_accuracy": 0.17915076315402984,
|
|
"num_tokens": 52118967.0,
|
|
"step": 26645
|
|
},
|
|
{
|
|
"entropy": 6.096801042556763,
|
|
"epoch": 2.6639676113360324,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00042953642225803296,
|
|
"loss": 5.6761,
|
|
"mean_token_accuracy": 0.17867792546749114,
|
|
"num_tokens": 52128570.0,
|
|
"step": 26650
|
|
},
|
|
{
|
|
"entropy": 5.918860340118409,
|
|
"epoch": 2.6644674363972607,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000429510480779909,
|
|
"loss": 5.6299,
|
|
"mean_token_accuracy": 0.17958634346723557,
|
|
"num_tokens": 52139683.0,
|
|
"step": 26655
|
|
},
|
|
{
|
|
"entropy": 6.010262298583984,
|
|
"epoch": 2.6649672614584894,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004294845354143411,
|
|
"loss": 5.6038,
|
|
"mean_token_accuracy": 0.1795576572418213,
|
|
"num_tokens": 52150139.0,
|
|
"step": 26660
|
|
},
|
|
{
|
|
"entropy": 6.04895396232605,
|
|
"epoch": 2.665467086519718,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004294585861619821,
|
|
"loss": 5.6828,
|
|
"mean_token_accuracy": 0.17800093740224837,
|
|
"num_tokens": 52159211.0,
|
|
"step": 26665
|
|
},
|
|
{
|
|
"entropy": 6.114756345748901,
|
|
"epoch": 2.665966911580947,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00042943263302348475,
|
|
"loss": 5.7261,
|
|
"mean_token_accuracy": 0.1715156078338623,
|
|
"num_tokens": 52169100.0,
|
|
"step": 26670
|
|
},
|
|
{
|
|
"entropy": 5.970224523544312,
|
|
"epoch": 2.6664667366421755,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00042940667599950205,
|
|
"loss": 5.5388,
|
|
"mean_token_accuracy": 0.1860246866941452,
|
|
"num_tokens": 52178336.0,
|
|
"step": 26675
|
|
},
|
|
{
|
|
"entropy": 5.98388934135437,
|
|
"epoch": 2.6669665617034037,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00042938071509068717,
|
|
"loss": 5.618,
|
|
"mean_token_accuracy": 0.1833014205098152,
|
|
"num_tokens": 52188579.0,
|
|
"step": 26680
|
|
},
|
|
{
|
|
"entropy": 6.045494318008423,
|
|
"epoch": 2.6674663867646324,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.00042935475029769323,
|
|
"loss": 5.6714,
|
|
"mean_token_accuracy": 0.1724283665418625,
|
|
"num_tokens": 52197706.0,
|
|
"step": 26685
|
|
},
|
|
{
|
|
"entropy": 6.111980867385864,
|
|
"epoch": 2.6679662118258607,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00042932878162117347,
|
|
"loss": 5.7033,
|
|
"mean_token_accuracy": 0.17491311877965926,
|
|
"num_tokens": 52207881.0,
|
|
"step": 26690
|
|
},
|
|
{
|
|
"entropy": 6.017416620254517,
|
|
"epoch": 2.6684660368870894,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004293028090617813,
|
|
"loss": 5.6346,
|
|
"mean_token_accuracy": 0.18108907341957092,
|
|
"num_tokens": 52217842.0,
|
|
"step": 26695
|
|
},
|
|
{
|
|
"entropy": 6.043239641189575,
|
|
"epoch": 2.668965861948318,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00042927683262017016,
|
|
"loss": 5.6992,
|
|
"mean_token_accuracy": 0.17526763826608657,
|
|
"num_tokens": 52228198.0,
|
|
"step": 26700
|
|
},
|
|
{
|
|
"entropy": 6.066903734207154,
|
|
"epoch": 2.669465687009547,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004292508522969935,
|
|
"loss": 5.6241,
|
|
"mean_token_accuracy": 0.17603110820055007,
|
|
"num_tokens": 52238658.0,
|
|
"step": 26705
|
|
},
|
|
{
|
|
"entropy": 6.0198160171508786,
|
|
"epoch": 2.6699655120707755,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004292248680929052,
|
|
"loss": 5.6108,
|
|
"mean_token_accuracy": 0.1852746680378914,
|
|
"num_tokens": 52247767.0,
|
|
"step": 26710
|
|
},
|
|
{
|
|
"entropy": 6.09090142250061,
|
|
"epoch": 2.6704653371320037,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00042919888000855885,
|
|
"loss": 5.6835,
|
|
"mean_token_accuracy": 0.1774326890707016,
|
|
"num_tokens": 52257536.0,
|
|
"step": 26715
|
|
},
|
|
{
|
|
"entropy": 6.027754545211792,
|
|
"epoch": 2.6709651621932324,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00042917288804460835,
|
|
"loss": 5.665,
|
|
"mean_token_accuracy": 0.18488256335258485,
|
|
"num_tokens": 52269002.0,
|
|
"step": 26720
|
|
},
|
|
{
|
|
"entropy": 5.99418625831604,
|
|
"epoch": 2.6714649872544607,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004291468922017078,
|
|
"loss": 5.6843,
|
|
"mean_token_accuracy": 0.1708453744649887,
|
|
"num_tokens": 52279065.0,
|
|
"step": 26725
|
|
},
|
|
{
|
|
"entropy": 5.929057168960571,
|
|
"epoch": 2.6719648123156894,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000429120892480511,
|
|
"loss": 5.5748,
|
|
"mean_token_accuracy": 0.18444027602672577,
|
|
"num_tokens": 52289077.0,
|
|
"step": 26730
|
|
},
|
|
{
|
|
"entropy": 6.011571407318115,
|
|
"epoch": 2.672464637376918,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004290948888816722,
|
|
"loss": 5.578,
|
|
"mean_token_accuracy": 0.17749013900756835,
|
|
"num_tokens": 52298147.0,
|
|
"step": 26735
|
|
},
|
|
{
|
|
"entropy": 6.000582027435303,
|
|
"epoch": 2.672964462438147,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004290688814058456,
|
|
"loss": 5.6444,
|
|
"mean_token_accuracy": 0.18364610373973847,
|
|
"num_tokens": 52308131.0,
|
|
"step": 26740
|
|
},
|
|
{
|
|
"entropy": 5.958431625366211,
|
|
"epoch": 2.6734642874993755,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004290428700536857,
|
|
"loss": 5.5527,
|
|
"mean_token_accuracy": 0.1883833348751068,
|
|
"num_tokens": 52317211.0,
|
|
"step": 26745
|
|
},
|
|
{
|
|
"entropy": 6.0800501823425295,
|
|
"epoch": 2.6739641125606037,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004290168548258467,
|
|
"loss": 5.7566,
|
|
"mean_token_accuracy": 0.17581503987312316,
|
|
"num_tokens": 52326640.0,
|
|
"step": 26750
|
|
},
|
|
{
|
|
"entropy": 6.056253862380982,
|
|
"epoch": 2.6744639376218324,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00042899083572298335,
|
|
"loss": 5.6212,
|
|
"mean_token_accuracy": 0.18132370412349702,
|
|
"num_tokens": 52335084.0,
|
|
"step": 26755
|
|
},
|
|
{
|
|
"entropy": 6.005887889862061,
|
|
"epoch": 2.6749637626830607,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00042896481274575014,
|
|
"loss": 5.5419,
|
|
"mean_token_accuracy": 0.19188250601291656,
|
|
"num_tokens": 52344982.0,
|
|
"step": 26760
|
|
},
|
|
{
|
|
"entropy": 5.992859315872193,
|
|
"epoch": 2.6754635877442894,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00042893878589480195,
|
|
"loss": 5.6075,
|
|
"mean_token_accuracy": 0.1815670982003212,
|
|
"num_tokens": 52353976.0,
|
|
"step": 26765
|
|
},
|
|
{
|
|
"entropy": 6.067263412475586,
|
|
"epoch": 2.675963412805518,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00042891275517079345,
|
|
"loss": 5.7232,
|
|
"mean_token_accuracy": 0.1716982066631317,
|
|
"num_tokens": 52363917.0,
|
|
"step": 26770
|
|
},
|
|
{
|
|
"entropy": 5.981343746185303,
|
|
"epoch": 2.676463237866747,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00042888672057437964,
|
|
"loss": 5.5332,
|
|
"mean_token_accuracy": 0.1920326754450798,
|
|
"num_tokens": 52373008.0,
|
|
"step": 26775
|
|
},
|
|
{
|
|
"entropy": 5.993420362472534,
|
|
"epoch": 2.6769630629279755,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00042886068210621557,
|
|
"loss": 5.5801,
|
|
"mean_token_accuracy": 0.17762986868619918,
|
|
"num_tokens": 52383872.0,
|
|
"step": 26780
|
|
},
|
|
{
|
|
"entropy": 6.066840362548828,
|
|
"epoch": 2.6774628879892037,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004288346397669563,
|
|
"loss": 5.6795,
|
|
"mean_token_accuracy": 0.1754004642367363,
|
|
"num_tokens": 52393484.0,
|
|
"step": 26785
|
|
},
|
|
{
|
|
"entropy": 6.029188585281372,
|
|
"epoch": 2.6779627130504324,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004288085935572571,
|
|
"loss": 5.6795,
|
|
"mean_token_accuracy": 0.1726717859506607,
|
|
"num_tokens": 52403350.0,
|
|
"step": 26790
|
|
},
|
|
{
|
|
"entropy": 5.996001958847046,
|
|
"epoch": 2.6784625381116607,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004287825434777733,
|
|
"loss": 5.591,
|
|
"mean_token_accuracy": 0.1828855335712433,
|
|
"num_tokens": 52412270.0,
|
|
"step": 26795
|
|
},
|
|
{
|
|
"entropy": 6.082120704650879,
|
|
"epoch": 2.6789623631728894,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00042875648952916024,
|
|
"loss": 5.6332,
|
|
"mean_token_accuracy": 0.18276962637901306,
|
|
"num_tokens": 52422855.0,
|
|
"step": 26800
|
|
},
|
|
{
|
|
"entropy": 5.98437728881836,
|
|
"epoch": 2.679462188234118,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004287304317120734,
|
|
"loss": 5.5817,
|
|
"mean_token_accuracy": 0.182672818005085,
|
|
"num_tokens": 52432254.0,
|
|
"step": 26805
|
|
},
|
|
{
|
|
"entropy": 5.919236946105957,
|
|
"epoch": 2.679962013295347,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00042870437002716854,
|
|
"loss": 5.5999,
|
|
"mean_token_accuracy": 0.17688648253679276,
|
|
"num_tokens": 52441830.0,
|
|
"step": 26810
|
|
},
|
|
{
|
|
"entropy": 6.0564171314239506,
|
|
"epoch": 2.680461838356575,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004286783044751013,
|
|
"loss": 5.6929,
|
|
"mean_token_accuracy": 0.17017603516578675,
|
|
"num_tokens": 52451913.0,
|
|
"step": 26815
|
|
},
|
|
{
|
|
"entropy": 6.130397176742553,
|
|
"epoch": 2.6809616634178037,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004286522350565274,
|
|
"loss": 5.5323,
|
|
"mean_token_accuracy": 0.19468679130077363,
|
|
"num_tokens": 52460737.0,
|
|
"step": 26820
|
|
},
|
|
{
|
|
"entropy": 5.972865009307862,
|
|
"epoch": 2.6814614884790324,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00042862616177210286,
|
|
"loss": 5.5733,
|
|
"mean_token_accuracy": 0.1800844483077526,
|
|
"num_tokens": 52470398.0,
|
|
"step": 26825
|
|
},
|
|
{
|
|
"entropy": 5.952329397201538,
|
|
"epoch": 2.6819613135402607,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004286000846224836,
|
|
"loss": 5.6376,
|
|
"mean_token_accuracy": 0.17872157841920852,
|
|
"num_tokens": 52481362.0,
|
|
"step": 26830
|
|
},
|
|
{
|
|
"entropy": 6.029623413085938,
|
|
"epoch": 2.6824611386014894,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00042857400360832575,
|
|
"loss": 5.5779,
|
|
"mean_token_accuracy": 0.18853707015514373,
|
|
"num_tokens": 52490724.0,
|
|
"step": 26835
|
|
},
|
|
{
|
|
"entropy": 6.0657988548278805,
|
|
"epoch": 2.682960963662718,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004285479187302854,
|
|
"loss": 5.6438,
|
|
"mean_token_accuracy": 0.17526229470968246,
|
|
"num_tokens": 52500038.0,
|
|
"step": 26840
|
|
},
|
|
{
|
|
"entropy": 6.071943473815918,
|
|
"epoch": 2.6834607887239468,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000428521829989019,
|
|
"loss": 5.605,
|
|
"mean_token_accuracy": 0.18456125110387803,
|
|
"num_tokens": 52509796.0,
|
|
"step": 26845
|
|
},
|
|
{
|
|
"entropy": 5.964777898788452,
|
|
"epoch": 2.683960613785175,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004284957373851829,
|
|
"loss": 5.6042,
|
|
"mean_token_accuracy": 0.18320257663726808,
|
|
"num_tokens": 52519373.0,
|
|
"step": 26850
|
|
},
|
|
{
|
|
"entropy": 5.993216848373413,
|
|
"epoch": 2.6844604388464037,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00042846964091943347,
|
|
"loss": 5.6183,
|
|
"mean_token_accuracy": 0.18314651250839234,
|
|
"num_tokens": 52530073.0,
|
|
"step": 26855
|
|
},
|
|
{
|
|
"entropy": 6.058871507644653,
|
|
"epoch": 2.6849602639076324,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00042844354059242735,
|
|
"loss": 5.7136,
|
|
"mean_token_accuracy": 0.1755130410194397,
|
|
"num_tokens": 52538995.0,
|
|
"step": 26860
|
|
},
|
|
{
|
|
"entropy": 6.021759176254273,
|
|
"epoch": 2.6854600889688607,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004284174364048213,
|
|
"loss": 5.6019,
|
|
"mean_token_accuracy": 0.1827116459608078,
|
|
"num_tokens": 52547824.0,
|
|
"step": 26865
|
|
},
|
|
{
|
|
"entropy": 5.993349218368531,
|
|
"epoch": 2.6859599140300894,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.000428391328357272,
|
|
"loss": 5.6013,
|
|
"mean_token_accuracy": 0.18218588680028916,
|
|
"num_tokens": 52557215.0,
|
|
"step": 26870
|
|
},
|
|
{
|
|
"entropy": 6.009469413757325,
|
|
"epoch": 2.686459739091318,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004283652164504364,
|
|
"loss": 5.6827,
|
|
"mean_token_accuracy": 0.17287533730268478,
|
|
"num_tokens": 52567557.0,
|
|
"step": 26875
|
|
},
|
|
{
|
|
"entropy": 6.113264656066894,
|
|
"epoch": 2.6869595641525468,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00042833910068497134,
|
|
"loss": 5.6939,
|
|
"mean_token_accuracy": 0.17550454288721085,
|
|
"num_tokens": 52577597.0,
|
|
"step": 26880
|
|
},
|
|
{
|
|
"entropy": 6.076932191848755,
|
|
"epoch": 2.687459389213775,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.000428312981061534,
|
|
"loss": 5.6533,
|
|
"mean_token_accuracy": 0.17612115740776063,
|
|
"num_tokens": 52589183.0,
|
|
"step": 26885
|
|
},
|
|
{
|
|
"entropy": 5.967991304397583,
|
|
"epoch": 2.6879592142750037,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004282868575807815,
|
|
"loss": 5.5776,
|
|
"mean_token_accuracy": 0.18200986981391906,
|
|
"num_tokens": 52598846.0,
|
|
"step": 26890
|
|
},
|
|
{
|
|
"entropy": 6.036656713485717,
|
|
"epoch": 2.6884590393362324,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00042826073024337117,
|
|
"loss": 5.6519,
|
|
"mean_token_accuracy": 0.17153763324022292,
|
|
"num_tokens": 52609072.0,
|
|
"step": 26895
|
|
},
|
|
{
|
|
"entropy": 6.095133590698242,
|
|
"epoch": 2.6889588643974607,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004282345990499602,
|
|
"loss": 5.7531,
|
|
"mean_token_accuracy": 0.16989525258541108,
|
|
"num_tokens": 52619648.0,
|
|
"step": 26900
|
|
},
|
|
{
|
|
"entropy": 6.106661081314087,
|
|
"epoch": 2.6894586894586894,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004282084640012062,
|
|
"loss": 5.6431,
|
|
"mean_token_accuracy": 0.17735883295536042,
|
|
"num_tokens": 52629992.0,
|
|
"step": 26905
|
|
},
|
|
{
|
|
"entropy": 6.055054140090943,
|
|
"epoch": 2.689958514519918,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004281823250977667,
|
|
"loss": 5.5911,
|
|
"mean_token_accuracy": 0.18123097494244575,
|
|
"num_tokens": 52639174.0,
|
|
"step": 26910
|
|
},
|
|
{
|
|
"entropy": 5.885088491439819,
|
|
"epoch": 2.6904583395811468,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00042815618234029923,
|
|
"loss": 5.4132,
|
|
"mean_token_accuracy": 0.1964778333902359,
|
|
"num_tokens": 52648254.0,
|
|
"step": 26915
|
|
},
|
|
{
|
|
"entropy": 5.9144734859466555,
|
|
"epoch": 2.690958164642375,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00042813003572946163,
|
|
"loss": 5.5905,
|
|
"mean_token_accuracy": 0.18147398680448532,
|
|
"num_tokens": 52658072.0,
|
|
"step": 26920
|
|
},
|
|
{
|
|
"entropy": 6.008952331542969,
|
|
"epoch": 2.6914579897036037,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00042810388526591184,
|
|
"loss": 5.6821,
|
|
"mean_token_accuracy": 0.1818379804491997,
|
|
"num_tokens": 52668868.0,
|
|
"step": 26925
|
|
},
|
|
{
|
|
"entropy": 6.084114027023316,
|
|
"epoch": 2.6919578147648324,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00042807773095030757,
|
|
"loss": 5.7028,
|
|
"mean_token_accuracy": 0.17761926501989364,
|
|
"num_tokens": 52678848.0,
|
|
"step": 26930
|
|
},
|
|
{
|
|
"entropy": 5.899989032745362,
|
|
"epoch": 2.6924576398260607,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004280515727833071,
|
|
"loss": 5.4406,
|
|
"mean_token_accuracy": 0.19748872071504592,
|
|
"num_tokens": 52689690.0,
|
|
"step": 26935
|
|
},
|
|
{
|
|
"entropy": 5.94414873123169,
|
|
"epoch": 2.6929574648872894,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004280254107655684,
|
|
"loss": 5.5875,
|
|
"mean_token_accuracy": 0.18441541939973832,
|
|
"num_tokens": 52699284.0,
|
|
"step": 26940
|
|
},
|
|
{
|
|
"entropy": 6.037202072143555,
|
|
"epoch": 2.693457289948518,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004279992448977497,
|
|
"loss": 5.7237,
|
|
"mean_token_accuracy": 0.1748224288225174,
|
|
"num_tokens": 52709961.0,
|
|
"step": 26945
|
|
},
|
|
{
|
|
"entropy": 5.960940599441528,
|
|
"epoch": 2.6939571150097468,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004279730751805094,
|
|
"loss": 5.5514,
|
|
"mean_token_accuracy": 0.1832769349217415,
|
|
"num_tokens": 52720655.0,
|
|
"step": 26950
|
|
},
|
|
{
|
|
"entropy": 6.02155499458313,
|
|
"epoch": 2.694456940070975,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00042794690161450583,
|
|
"loss": 5.5919,
|
|
"mean_token_accuracy": 0.18550732880830764,
|
|
"num_tokens": 52729628.0,
|
|
"step": 26955
|
|
},
|
|
{
|
|
"entropy": 5.883202409744262,
|
|
"epoch": 2.6949567651322037,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004279207242003976,
|
|
"loss": 5.463,
|
|
"mean_token_accuracy": 0.1891649156808853,
|
|
"num_tokens": 52738685.0,
|
|
"step": 26960
|
|
},
|
|
{
|
|
"entropy": 5.93750638961792,
|
|
"epoch": 2.6954565901934324,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00042789454293884336,
|
|
"loss": 5.5824,
|
|
"mean_token_accuracy": 0.18444643318653106,
|
|
"num_tokens": 52748249.0,
|
|
"step": 26965
|
|
},
|
|
{
|
|
"entropy": 6.071706914901734,
|
|
"epoch": 2.6959564152546607,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004278683578305017,
|
|
"loss": 5.7353,
|
|
"mean_token_accuracy": 0.1768995225429535,
|
|
"num_tokens": 52758447.0,
|
|
"step": 26970
|
|
},
|
|
{
|
|
"entropy": 6.1087360858917235,
|
|
"epoch": 2.6964562403158894,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00042784216887603154,
|
|
"loss": 5.6913,
|
|
"mean_token_accuracy": 0.1760014921426773,
|
|
"num_tokens": 52768448.0,
|
|
"step": 26975
|
|
},
|
|
{
|
|
"entropy": 6.06812219619751,
|
|
"epoch": 2.696956065377118,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004278159760760917,
|
|
"loss": 5.6141,
|
|
"mean_token_accuracy": 0.17823555171489716,
|
|
"num_tokens": 52778831.0,
|
|
"step": 26980
|
|
},
|
|
{
|
|
"entropy": 6.004651784896851,
|
|
"epoch": 2.6974558904383468,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004277897794313412,
|
|
"loss": 5.5908,
|
|
"mean_token_accuracy": 0.17905790656805037,
|
|
"num_tokens": 52788915.0,
|
|
"step": 26985
|
|
},
|
|
{
|
|
"entropy": 5.995166683197022,
|
|
"epoch": 2.697955715499575,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004277635789424393,
|
|
"loss": 5.6278,
|
|
"mean_token_accuracy": 0.18027897030115128,
|
|
"num_tokens": 52798670.0,
|
|
"step": 26990
|
|
},
|
|
{
|
|
"entropy": 6.058378744125366,
|
|
"epoch": 2.6984555405608037,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004277373746100449,
|
|
"loss": 5.6389,
|
|
"mean_token_accuracy": 0.17969059348106384,
|
|
"num_tokens": 52807783.0,
|
|
"step": 26995
|
|
},
|
|
{
|
|
"entropy": 6.06757869720459,
|
|
"epoch": 2.6989553656220324,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00042771116643481753,
|
|
"loss": 5.6772,
|
|
"mean_token_accuracy": 0.1677168771624565,
|
|
"num_tokens": 52816664.0,
|
|
"step": 27000
|
|
},
|
|
{
|
|
"epoch": 2.6989553656220324,
|
|
"eval_entropy": 5.845460138932788,
|
|
"eval_loss": 5.732309818267822,
|
|
"eval_mean_token_accuracy": 0.18311976011735942,
|
|
"eval_num_tokens": 52816664.0,
|
|
"eval_runtime": 23.7006,
|
|
"eval_samples_per_second": 1309.882,
|
|
"eval_steps_per_second": 163.751,
|
|
"step": 27000
|
|
},
|
|
{
|
|
"entropy": 6.047358465194702,
|
|
"epoch": 2.6994551906832607,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004276849544174166,
|
|
"loss": 5.6704,
|
|
"mean_token_accuracy": 0.17477551996707916,
|
|
"num_tokens": 52826241.0,
|
|
"step": 27005
|
|
},
|
|
{
|
|
"entropy": 6.084078311920166,
|
|
"epoch": 2.6999550157444894,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00042765873855850133,
|
|
"loss": 5.6135,
|
|
"mean_token_accuracy": 0.18264936208724974,
|
|
"num_tokens": 52836138.0,
|
|
"step": 27010
|
|
},
|
|
{
|
|
"entropy": 6.042387390136719,
|
|
"epoch": 2.700454840805718,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004276325188587316,
|
|
"loss": 5.582,
|
|
"mean_token_accuracy": 0.18230862766504288,
|
|
"num_tokens": 52845679.0,
|
|
"step": 27015
|
|
},
|
|
{
|
|
"entropy": 5.967452049255371,
|
|
"epoch": 2.7009546658669468,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004276062953187669,
|
|
"loss": 5.5626,
|
|
"mean_token_accuracy": 0.18361443281173706,
|
|
"num_tokens": 52855455.0,
|
|
"step": 27020
|
|
},
|
|
{
|
|
"entropy": 6.050507354736328,
|
|
"epoch": 2.701454490928175,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004275800679392671,
|
|
"loss": 5.6338,
|
|
"mean_token_accuracy": 0.18233570605516433,
|
|
"num_tokens": 52865589.0,
|
|
"step": 27025
|
|
},
|
|
{
|
|
"entropy": 6.023155546188354,
|
|
"epoch": 2.7019543159894037,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004275538367208921,
|
|
"loss": 5.6635,
|
|
"mean_token_accuracy": 0.17949198335409164,
|
|
"num_tokens": 52877087.0,
|
|
"step": 27030
|
|
},
|
|
{
|
|
"entropy": 6.153647804260254,
|
|
"epoch": 2.7024541410506324,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00042752760166430185,
|
|
"loss": 5.7462,
|
|
"mean_token_accuracy": 0.16712506115436554,
|
|
"num_tokens": 52887370.0,
|
|
"step": 27035
|
|
},
|
|
{
|
|
"entropy": 6.069916439056397,
|
|
"epoch": 2.7029539661118607,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00042750136277015625,
|
|
"loss": 5.654,
|
|
"mean_token_accuracy": 0.16938242465257644,
|
|
"num_tokens": 52897744.0,
|
|
"step": 27040
|
|
},
|
|
{
|
|
"entropy": 6.0535095691680905,
|
|
"epoch": 2.7034537911730894,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00042747512003911577,
|
|
"loss": 5.6123,
|
|
"mean_token_accuracy": 0.17943339943885803,
|
|
"num_tokens": 52907008.0,
|
|
"step": 27045
|
|
},
|
|
{
|
|
"entropy": 6.0049456596374515,
|
|
"epoch": 2.703953616234318,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00042744887347184035,
|
|
"loss": 5.6229,
|
|
"mean_token_accuracy": 0.17705328911542892,
|
|
"num_tokens": 52916941.0,
|
|
"step": 27050
|
|
},
|
|
{
|
|
"entropy": 6.009659481048584,
|
|
"epoch": 2.7044534412955468,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004274226230689906,
|
|
"loss": 5.6309,
|
|
"mean_token_accuracy": 0.1825429767370224,
|
|
"num_tokens": 52927381.0,
|
|
"step": 27055
|
|
},
|
|
{
|
|
"entropy": 6.008446264266968,
|
|
"epoch": 2.704953266356775,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00042739636883122687,
|
|
"loss": 5.6106,
|
|
"mean_token_accuracy": 0.18240844011306762,
|
|
"num_tokens": 52937462.0,
|
|
"step": 27060
|
|
},
|
|
{
|
|
"entropy": 6.003031873703003,
|
|
"epoch": 2.7054530914180037,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00042737011075920974,
|
|
"loss": 5.6153,
|
|
"mean_token_accuracy": 0.18011519461870193,
|
|
"num_tokens": 52946612.0,
|
|
"step": 27065
|
|
},
|
|
{
|
|
"entropy": 6.015258359909057,
|
|
"epoch": 2.7059529164792324,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004273438488535997,
|
|
"loss": 5.6043,
|
|
"mean_token_accuracy": 0.1829233095049858,
|
|
"num_tokens": 52955814.0,
|
|
"step": 27070
|
|
},
|
|
{
|
|
"entropy": 5.9697277545928955,
|
|
"epoch": 2.7064527415404607,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00042731758311505773,
|
|
"loss": 5.5778,
|
|
"mean_token_accuracy": 0.1846031054854393,
|
|
"num_tokens": 52965586.0,
|
|
"step": 27075
|
|
},
|
|
{
|
|
"entropy": 5.981623268127441,
|
|
"epoch": 2.7069525666016894,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00042729131354424455,
|
|
"loss": 5.5311,
|
|
"mean_token_accuracy": 0.18993192166090012,
|
|
"num_tokens": 52975805.0,
|
|
"step": 27080
|
|
},
|
|
{
|
|
"entropy": 6.070930480957031,
|
|
"epoch": 2.707452391662918,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004272650401418211,
|
|
"loss": 5.684,
|
|
"mean_token_accuracy": 0.1755255326628685,
|
|
"num_tokens": 52986040.0,
|
|
"step": 27085
|
|
},
|
|
{
|
|
"entropy": 5.964757633209229,
|
|
"epoch": 2.7079522167241468,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004272387629084484,
|
|
"loss": 5.6076,
|
|
"mean_token_accuracy": 0.1810666188597679,
|
|
"num_tokens": 52995660.0,
|
|
"step": 27090
|
|
},
|
|
{
|
|
"entropy": 6.044379758834839,
|
|
"epoch": 2.708452041785375,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00042721248184478765,
|
|
"loss": 5.7345,
|
|
"mean_token_accuracy": 0.1750588372349739,
|
|
"num_tokens": 53005193.0,
|
|
"step": 27095
|
|
},
|
|
{
|
|
"entropy": 6.096976709365845,
|
|
"epoch": 2.7089518668466037,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004271861969515,
|
|
"loss": 5.6869,
|
|
"mean_token_accuracy": 0.1803567200899124,
|
|
"num_tokens": 53015624.0,
|
|
"step": 27100
|
|
},
|
|
{
|
|
"entropy": 6.001797342300415,
|
|
"epoch": 2.7094516919078324,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00042715990822924673,
|
|
"loss": 5.5932,
|
|
"mean_token_accuracy": 0.18028765618801118,
|
|
"num_tokens": 53026673.0,
|
|
"step": 27105
|
|
},
|
|
{
|
|
"entropy": 6.053807640075684,
|
|
"epoch": 2.7099515169690607,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00042713361567868946,
|
|
"loss": 5.6464,
|
|
"mean_token_accuracy": 0.17793587744235992,
|
|
"num_tokens": 53035421.0,
|
|
"step": 27110
|
|
},
|
|
{
|
|
"entropy": 6.065346765518188,
|
|
"epoch": 2.7104513420302894,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00042710731930048945,
|
|
"loss": 5.6718,
|
|
"mean_token_accuracy": 0.1760808303952217,
|
|
"num_tokens": 53045132.0,
|
|
"step": 27115
|
|
},
|
|
{
|
|
"entropy": 6.014540719985962,
|
|
"epoch": 2.710951167091518,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004270810190953085,
|
|
"loss": 5.5764,
|
|
"mean_token_accuracy": 0.18279560655355453,
|
|
"num_tokens": 53055176.0,
|
|
"step": 27120
|
|
},
|
|
{
|
|
"entropy": 5.953253507614136,
|
|
"epoch": 2.7114509921527468,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004270547150638082,
|
|
"loss": 5.5937,
|
|
"mean_token_accuracy": 0.1864369422197342,
|
|
"num_tokens": 53064846.0,
|
|
"step": 27125
|
|
},
|
|
{
|
|
"entropy": 5.972094440460205,
|
|
"epoch": 2.711950817213975,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00042702840720665043,
|
|
"loss": 5.6111,
|
|
"mean_token_accuracy": 0.1838383898139,
|
|
"num_tokens": 53074669.0,
|
|
"step": 27130
|
|
},
|
|
{
|
|
"entropy": 6.10482702255249,
|
|
"epoch": 2.7124506422752037,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00042700209552449706,
|
|
"loss": 5.6408,
|
|
"mean_token_accuracy": 0.1771107628941536,
|
|
"num_tokens": 53084196.0,
|
|
"step": 27135
|
|
},
|
|
{
|
|
"entropy": 5.961599540710449,
|
|
"epoch": 2.7129504673364324,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00042697578001801,
|
|
"loss": 5.6201,
|
|
"mean_token_accuracy": 0.18013228178024293,
|
|
"num_tokens": 53094435.0,
|
|
"step": 27140
|
|
},
|
|
{
|
|
"entropy": 5.938086366653442,
|
|
"epoch": 2.7134502923976607,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004269494606878515,
|
|
"loss": 5.5618,
|
|
"mean_token_accuracy": 0.18767464458942412,
|
|
"num_tokens": 53104221.0,
|
|
"step": 27145
|
|
},
|
|
{
|
|
"entropy": 6.049519491195679,
|
|
"epoch": 2.7139501174588894,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004269231375346836,
|
|
"loss": 5.6463,
|
|
"mean_token_accuracy": 0.17938455790281296,
|
|
"num_tokens": 53113685.0,
|
|
"step": 27150
|
|
},
|
|
{
|
|
"entropy": 6.108600521087647,
|
|
"epoch": 2.714449942520118,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004268968105591687,
|
|
"loss": 5.708,
|
|
"mean_token_accuracy": 0.16800982356071473,
|
|
"num_tokens": 53125353.0,
|
|
"step": 27155
|
|
},
|
|
{
|
|
"entropy": 5.976388835906983,
|
|
"epoch": 2.7149497675813468,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004268704797619692,
|
|
"loss": 5.6197,
|
|
"mean_token_accuracy": 0.18054789006710054,
|
|
"num_tokens": 53133860.0,
|
|
"step": 27160
|
|
},
|
|
{
|
|
"entropy": 5.935795164108276,
|
|
"epoch": 2.715449592642575,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00042684414514374734,
|
|
"loss": 5.5246,
|
|
"mean_token_accuracy": 0.18924008160829545,
|
|
"num_tokens": 53142700.0,
|
|
"step": 27165
|
|
},
|
|
{
|
|
"entropy": 6.0286609649658205,
|
|
"epoch": 2.7159494177038037,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.00042681780670516595,
|
|
"loss": 5.584,
|
|
"mean_token_accuracy": 0.1759762331843376,
|
|
"num_tokens": 53152517.0,
|
|
"step": 27170
|
|
},
|
|
{
|
|
"entropy": 5.970217514038086,
|
|
"epoch": 2.716449242765032,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004267914644468877,
|
|
"loss": 5.4891,
|
|
"mean_token_accuracy": 0.18827113807201384,
|
|
"num_tokens": 53162270.0,
|
|
"step": 27175
|
|
},
|
|
{
|
|
"entropy": 6.016447734832764,
|
|
"epoch": 2.7169490678262607,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004267651183695752,
|
|
"loss": 5.7581,
|
|
"mean_token_accuracy": 0.17014363408088684,
|
|
"num_tokens": 53173664.0,
|
|
"step": 27180
|
|
},
|
|
{
|
|
"entropy": 6.017502212524414,
|
|
"epoch": 2.7174488928874894,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004267387684738913,
|
|
"loss": 5.6306,
|
|
"mean_token_accuracy": 0.178409181535244,
|
|
"num_tokens": 53184668.0,
|
|
"step": 27185
|
|
},
|
|
{
|
|
"entropy": 5.999864959716797,
|
|
"epoch": 2.717948717948718,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004267124147604991,
|
|
"loss": 5.5635,
|
|
"mean_token_accuracy": 0.1824850931763649,
|
|
"num_tokens": 53194107.0,
|
|
"step": 27190
|
|
},
|
|
{
|
|
"entropy": 5.972761249542236,
|
|
"epoch": 2.7184485430099468,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004266860572300615,
|
|
"loss": 5.5777,
|
|
"mean_token_accuracy": 0.18802892565727233,
|
|
"num_tokens": 53204248.0,
|
|
"step": 27195
|
|
},
|
|
{
|
|
"entropy": 6.068559455871582,
|
|
"epoch": 2.718948368071175,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004266596958832419,
|
|
"loss": 5.6922,
|
|
"mean_token_accuracy": 0.17133635133504868,
|
|
"num_tokens": 53213415.0,
|
|
"step": 27200
|
|
},
|
|
{
|
|
"entropy": 6.149484586715698,
|
|
"epoch": 2.7194481931324037,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004266333307207032,
|
|
"loss": 5.7945,
|
|
"mean_token_accuracy": 0.1720515549182892,
|
|
"num_tokens": 53224403.0,
|
|
"step": 27205
|
|
},
|
|
{
|
|
"entropy": 6.062715196609497,
|
|
"epoch": 2.719948018193632,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.00042660696174310904,
|
|
"loss": 5.643,
|
|
"mean_token_accuracy": 0.17875972539186477,
|
|
"num_tokens": 53233890.0,
|
|
"step": 27210
|
|
},
|
|
{
|
|
"entropy": 6.000703287124634,
|
|
"epoch": 2.7204478432548607,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004265805889511227,
|
|
"loss": 5.6658,
|
|
"mean_token_accuracy": 0.17122752964496613,
|
|
"num_tokens": 53243783.0,
|
|
"step": 27215
|
|
},
|
|
{
|
|
"entropy": 6.034943675994873,
|
|
"epoch": 2.7209476683160894,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004265542123454077,
|
|
"loss": 5.6596,
|
|
"mean_token_accuracy": 0.17743945121765137,
|
|
"num_tokens": 53252941.0,
|
|
"step": 27220
|
|
},
|
|
{
|
|
"entropy": 6.056026840209961,
|
|
"epoch": 2.721447493377318,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00042652783192662774,
|
|
"loss": 5.6497,
|
|
"mean_token_accuracy": 0.1773553729057312,
|
|
"num_tokens": 53262846.0,
|
|
"step": 27225
|
|
},
|
|
{
|
|
"entropy": 6.072891759872436,
|
|
"epoch": 2.7219473184385468,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004265014476954465,
|
|
"loss": 5.7048,
|
|
"mean_token_accuracy": 0.17340670824050902,
|
|
"num_tokens": 53273416.0,
|
|
"step": 27230
|
|
},
|
|
{
|
|
"entropy": 6.075435638427734,
|
|
"epoch": 2.722447143499775,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004264750596525279,
|
|
"loss": 5.6626,
|
|
"mean_token_accuracy": 0.182249316573143,
|
|
"num_tokens": 53282815.0,
|
|
"step": 27235
|
|
},
|
|
{
|
|
"entropy": 6.015643310546875,
|
|
"epoch": 2.7229469685610037,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00042644866779853577,
|
|
"loss": 5.6242,
|
|
"mean_token_accuracy": 0.178840009868145,
|
|
"num_tokens": 53292355.0,
|
|
"step": 27240
|
|
},
|
|
{
|
|
"entropy": 5.971475839614868,
|
|
"epoch": 2.723446793622232,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00042642227213413405,
|
|
"loss": 5.6505,
|
|
"mean_token_accuracy": 0.1814847096800804,
|
|
"num_tokens": 53301947.0,
|
|
"step": 27245
|
|
},
|
|
{
|
|
"entropy": 6.050347375869751,
|
|
"epoch": 2.7239466186834607,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00042639587265998696,
|
|
"loss": 5.664,
|
|
"mean_token_accuracy": 0.18199941664934158,
|
|
"num_tokens": 53311753.0,
|
|
"step": 27250
|
|
},
|
|
{
|
|
"entropy": 6.101753664016724,
|
|
"epoch": 2.7244464437446894,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004263694693767587,
|
|
"loss": 5.6573,
|
|
"mean_token_accuracy": 0.17655176371335984,
|
|
"num_tokens": 53321447.0,
|
|
"step": 27255
|
|
},
|
|
{
|
|
"entropy": 5.991778898239136,
|
|
"epoch": 2.724946268805918,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004263430622851135,
|
|
"loss": 5.5689,
|
|
"mean_token_accuracy": 0.18355932235717773,
|
|
"num_tokens": 53331809.0,
|
|
"step": 27260
|
|
},
|
|
{
|
|
"entropy": 6.040099239349365,
|
|
"epoch": 2.7254460938671468,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004263166513857158,
|
|
"loss": 5.6881,
|
|
"mean_token_accuracy": 0.18072952777147294,
|
|
"num_tokens": 53341674.0,
|
|
"step": 27265
|
|
},
|
|
{
|
|
"entropy": 5.954408645629883,
|
|
"epoch": 2.725945918928375,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00042629023667923016,
|
|
"loss": 5.5123,
|
|
"mean_token_accuracy": 0.19037096947431564,
|
|
"num_tokens": 53350689.0,
|
|
"step": 27270
|
|
},
|
|
{
|
|
"entropy": 5.996921730041504,
|
|
"epoch": 2.7264457439896037,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00042626381816632096,
|
|
"loss": 5.6723,
|
|
"mean_token_accuracy": 0.177163228392601,
|
|
"num_tokens": 53360596.0,
|
|
"step": 27275
|
|
},
|
|
{
|
|
"entropy": 6.044889736175537,
|
|
"epoch": 2.726945569050832,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00042623739584765315,
|
|
"loss": 5.6319,
|
|
"mean_token_accuracy": 0.17574717849493027,
|
|
"num_tokens": 53370277.0,
|
|
"step": 27280
|
|
},
|
|
{
|
|
"entropy": 5.98068904876709,
|
|
"epoch": 2.7274453941120607,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00042621096972389136,
|
|
"loss": 5.5928,
|
|
"mean_token_accuracy": 0.178391033411026,
|
|
"num_tokens": 53379479.0,
|
|
"step": 27285
|
|
},
|
|
{
|
|
"entropy": 6.069110488891601,
|
|
"epoch": 2.7279452191732894,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00042618453979570035,
|
|
"loss": 5.6221,
|
|
"mean_token_accuracy": 0.17684302031993865,
|
|
"num_tokens": 53389175.0,
|
|
"step": 27290
|
|
},
|
|
{
|
|
"entropy": 5.949979162216186,
|
|
"epoch": 2.728445044234518,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00042615810606374535,
|
|
"loss": 5.4822,
|
|
"mean_token_accuracy": 0.18929586410522461,
|
|
"num_tokens": 53398941.0,
|
|
"step": 27295
|
|
},
|
|
{
|
|
"entropy": 5.972408580780029,
|
|
"epoch": 2.7289448692957468,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004261316685286913,
|
|
"loss": 5.5435,
|
|
"mean_token_accuracy": 0.189031919836998,
|
|
"num_tokens": 53408501.0,
|
|
"step": 27300
|
|
},
|
|
{
|
|
"entropy": 6.032048606872559,
|
|
"epoch": 2.729444694356975,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004261052271912033,
|
|
"loss": 5.603,
|
|
"mean_token_accuracy": 0.1809762477874756,
|
|
"num_tokens": 53418272.0,
|
|
"step": 27305
|
|
},
|
|
{
|
|
"entropy": 6.0440935611724855,
|
|
"epoch": 2.7299445194182037,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004260787820519467,
|
|
"loss": 5.6555,
|
|
"mean_token_accuracy": 0.17959091514348985,
|
|
"num_tokens": 53428433.0,
|
|
"step": 27310
|
|
},
|
|
{
|
|
"entropy": 6.078962612152099,
|
|
"epoch": 2.730444344479432,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004260523331115868,
|
|
"loss": 5.7219,
|
|
"mean_token_accuracy": 0.17228589951992035,
|
|
"num_tokens": 53438023.0,
|
|
"step": 27315
|
|
},
|
|
{
|
|
"entropy": 6.057709169387818,
|
|
"epoch": 2.7309441695406607,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00042602588037078903,
|
|
"loss": 5.5757,
|
|
"mean_token_accuracy": 0.19111323058605195,
|
|
"num_tokens": 53447492.0,
|
|
"step": 27320
|
|
},
|
|
{
|
|
"entropy": 6.030286502838135,
|
|
"epoch": 2.7314439946018894,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00042599942383021906,
|
|
"loss": 5.6718,
|
|
"mean_token_accuracy": 0.17849143147468566,
|
|
"num_tokens": 53457563.0,
|
|
"step": 27325
|
|
},
|
|
{
|
|
"entropy": 5.959152603149414,
|
|
"epoch": 2.731943819663118,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004259729634905424,
|
|
"loss": 5.6206,
|
|
"mean_token_accuracy": 0.17932230085134507,
|
|
"num_tokens": 53466616.0,
|
|
"step": 27330
|
|
},
|
|
{
|
|
"entropy": 6.039875030517578,
|
|
"epoch": 2.7324436447243468,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00042594649935242493,
|
|
"loss": 5.6491,
|
|
"mean_token_accuracy": 0.1764938160777092,
|
|
"num_tokens": 53476365.0,
|
|
"step": 27335
|
|
},
|
|
{
|
|
"entropy": 5.985813617706299,
|
|
"epoch": 2.732943469785575,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004259200314165322,
|
|
"loss": 5.5153,
|
|
"mean_token_accuracy": 0.18737920373678207,
|
|
"num_tokens": 53485581.0,
|
|
"step": 27340
|
|
},
|
|
{
|
|
"entropy": 5.917011785507202,
|
|
"epoch": 2.7334432948468037,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004258935596835303,
|
|
"loss": 5.5747,
|
|
"mean_token_accuracy": 0.1808233767747879,
|
|
"num_tokens": 53495533.0,
|
|
"step": 27345
|
|
},
|
|
{
|
|
"entropy": 6.009725904464721,
|
|
"epoch": 2.733943119908032,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00042586708415408547,
|
|
"loss": 5.6043,
|
|
"mean_token_accuracy": 0.17776651084423065,
|
|
"num_tokens": 53505530.0,
|
|
"step": 27350
|
|
},
|
|
{
|
|
"entropy": 6.056218910217285,
|
|
"epoch": 2.7344429449692607,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004258406048288635,
|
|
"loss": 5.6937,
|
|
"mean_token_accuracy": 0.17589082717895507,
|
|
"num_tokens": 53515276.0,
|
|
"step": 27355
|
|
},
|
|
{
|
|
"entropy": 6.077590417861939,
|
|
"epoch": 2.7349427700304894,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.00042581412170853073,
|
|
"loss": 5.6553,
|
|
"mean_token_accuracy": 0.1891116604208946,
|
|
"num_tokens": 53525213.0,
|
|
"step": 27360
|
|
},
|
|
{
|
|
"entropy": 5.998879909515381,
|
|
"epoch": 2.735442595091718,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004257876347937535,
|
|
"loss": 5.6372,
|
|
"mean_token_accuracy": 0.18548209518194197,
|
|
"num_tokens": 53534691.0,
|
|
"step": 27365
|
|
},
|
|
{
|
|
"entropy": 5.8964488983154295,
|
|
"epoch": 2.7359424201529463,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004257611440851981,
|
|
"loss": 5.4597,
|
|
"mean_token_accuracy": 0.20103965997695922,
|
|
"num_tokens": 53545878.0,
|
|
"step": 27370
|
|
},
|
|
{
|
|
"entropy": 6.0163044929504395,
|
|
"epoch": 2.736442245214175,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00042573464958353116,
|
|
"loss": 5.5912,
|
|
"mean_token_accuracy": 0.1857845053076744,
|
|
"num_tokens": 53555757.0,
|
|
"step": 27375
|
|
},
|
|
{
|
|
"entropy": 6.027343082427978,
|
|
"epoch": 2.7369420702754037,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004257081512894192,
|
|
"loss": 5.6508,
|
|
"mean_token_accuracy": 0.1738528326153755,
|
|
"num_tokens": 53565494.0,
|
|
"step": 27380
|
|
},
|
|
{
|
|
"entropy": 6.038026571273804,
|
|
"epoch": 2.737441895336632,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00042568164920352895,
|
|
"loss": 5.655,
|
|
"mean_token_accuracy": 0.17633592635393142,
|
|
"num_tokens": 53574302.0,
|
|
"step": 27385
|
|
},
|
|
{
|
|
"entropy": 5.958465099334717,
|
|
"epoch": 2.7379417203978607,
|
|
"grad_norm": 1.9140625,
|
|
"learning_rate": 0.0004256551433265273,
|
|
"loss": 5.6506,
|
|
"mean_token_accuracy": 0.1776180684566498,
|
|
"num_tokens": 53585447.0,
|
|
"step": 27390
|
|
},
|
|
{
|
|
"entropy": 6.070897388458252,
|
|
"epoch": 2.7384415454590894,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004256286336590808,
|
|
"loss": 5.6287,
|
|
"mean_token_accuracy": 0.1741023078560829,
|
|
"num_tokens": 53594728.0,
|
|
"step": 27395
|
|
},
|
|
{
|
|
"entropy": 5.875654458999634,
|
|
"epoch": 2.738941370520318,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004256021202018568,
|
|
"loss": 5.4692,
|
|
"mean_token_accuracy": 0.18729083985090256,
|
|
"num_tokens": 53604961.0,
|
|
"step": 27400
|
|
},
|
|
{
|
|
"entropy": 5.917499780654907,
|
|
"epoch": 2.7394411955815463,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004255756029555222,
|
|
"loss": 5.5776,
|
|
"mean_token_accuracy": 0.1867365449666977,
|
|
"num_tokens": 53614736.0,
|
|
"step": 27405
|
|
},
|
|
{
|
|
"entropy": 5.876136398315429,
|
|
"epoch": 2.739941020642775,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00042554908192074406,
|
|
"loss": 5.4369,
|
|
"mean_token_accuracy": 0.2027800440788269,
|
|
"num_tokens": 53623740.0,
|
|
"step": 27410
|
|
},
|
|
{
|
|
"entropy": 5.905259513854981,
|
|
"epoch": 2.7404408457040037,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00042552255709818975,
|
|
"loss": 5.5755,
|
|
"mean_token_accuracy": 0.18385056555271148,
|
|
"num_tokens": 53633901.0,
|
|
"step": 27415
|
|
},
|
|
{
|
|
"entropy": 6.1463724136352536,
|
|
"epoch": 2.740940670765232,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00042549602848852673,
|
|
"loss": 5.7934,
|
|
"mean_token_accuracy": 0.17233910262584687,
|
|
"num_tokens": 53644242.0,
|
|
"step": 27420
|
|
},
|
|
{
|
|
"entropy": 5.9953430652618405,
|
|
"epoch": 2.7414404958264607,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004254694960924224,
|
|
"loss": 5.5681,
|
|
"mean_token_accuracy": 0.1854543536901474,
|
|
"num_tokens": 53654764.0,
|
|
"step": 27425
|
|
},
|
|
{
|
|
"entropy": 5.857956504821777,
|
|
"epoch": 2.7419403208876894,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004254429599105442,
|
|
"loss": 5.4526,
|
|
"mean_token_accuracy": 0.19148709923028945,
|
|
"num_tokens": 53664746.0,
|
|
"step": 27430
|
|
},
|
|
{
|
|
"entropy": 6.0241364479064945,
|
|
"epoch": 2.742440145948918,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004254164199435598,
|
|
"loss": 5.6785,
|
|
"mean_token_accuracy": 0.17797570079565048,
|
|
"num_tokens": 53673586.0,
|
|
"step": 27435
|
|
},
|
|
{
|
|
"entropy": 6.016499137878418,
|
|
"epoch": 2.7429399710101463,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004253898761921371,
|
|
"loss": 5.5761,
|
|
"mean_token_accuracy": 0.1796272650361061,
|
|
"num_tokens": 53683907.0,
|
|
"step": 27440
|
|
},
|
|
{
|
|
"entropy": 6.009234762191772,
|
|
"epoch": 2.743439796071375,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004253633286569437,
|
|
"loss": 5.6155,
|
|
"mean_token_accuracy": 0.18076304942369462,
|
|
"num_tokens": 53694018.0,
|
|
"step": 27445
|
|
},
|
|
{
|
|
"entropy": 6.144090986251831,
|
|
"epoch": 2.7439396211326037,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004253367773386476,
|
|
"loss": 5.818,
|
|
"mean_token_accuracy": 0.16531736701726912,
|
|
"num_tokens": 53705057.0,
|
|
"step": 27450
|
|
},
|
|
{
|
|
"entropy": 6.033056640625,
|
|
"epoch": 2.744439446193832,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.000425310222237917,
|
|
"loss": 5.5556,
|
|
"mean_token_accuracy": 0.18388477861881256,
|
|
"num_tokens": 53713848.0,
|
|
"step": 27455
|
|
},
|
|
{
|
|
"entropy": 6.003184032440186,
|
|
"epoch": 2.7449392712550607,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00042528366335541984,
|
|
"loss": 5.6478,
|
|
"mean_token_accuracy": 0.17341329604387284,
|
|
"num_tokens": 53722716.0,
|
|
"step": 27460
|
|
},
|
|
{
|
|
"entropy": 5.956453084945679,
|
|
"epoch": 2.7454390963162894,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004252571006918243,
|
|
"loss": 5.497,
|
|
"mean_token_accuracy": 0.18539465218782425,
|
|
"num_tokens": 53732450.0,
|
|
"step": 27465
|
|
},
|
|
{
|
|
"entropy": 6.009842014312744,
|
|
"epoch": 2.745938921377518,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004252305342477989,
|
|
"loss": 5.6231,
|
|
"mean_token_accuracy": 0.1842624768614769,
|
|
"num_tokens": 53742050.0,
|
|
"step": 27470
|
|
},
|
|
{
|
|
"entropy": 6.043869352340698,
|
|
"epoch": 2.7464387464387463,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00042520396402401185,
|
|
"loss": 5.6455,
|
|
"mean_token_accuracy": 0.17679871767759323,
|
|
"num_tokens": 53751392.0,
|
|
"step": 27475
|
|
},
|
|
{
|
|
"entropy": 6.087569236755371,
|
|
"epoch": 2.746938571499975,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004251773900211317,
|
|
"loss": 5.7188,
|
|
"mean_token_accuracy": 0.1733258455991745,
|
|
"num_tokens": 53761477.0,
|
|
"step": 27480
|
|
},
|
|
{
|
|
"entropy": 6.081698322296143,
|
|
"epoch": 2.7474383965612037,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00042515081223982716,
|
|
"loss": 5.6087,
|
|
"mean_token_accuracy": 0.1791086256504059,
|
|
"num_tokens": 53771046.0,
|
|
"step": 27485
|
|
},
|
|
{
|
|
"entropy": 5.989876699447632,
|
|
"epoch": 2.747938221622432,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00042512423068076673,
|
|
"loss": 5.6415,
|
|
"mean_token_accuracy": 0.17935156673192978,
|
|
"num_tokens": 53781259.0,
|
|
"step": 27490
|
|
},
|
|
{
|
|
"entropy": 6.039244365692139,
|
|
"epoch": 2.7484380466836607,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004250976453446193,
|
|
"loss": 5.6192,
|
|
"mean_token_accuracy": 0.1821155697107315,
|
|
"num_tokens": 53790895.0,
|
|
"step": 27495
|
|
},
|
|
{
|
|
"entropy": 6.047803592681885,
|
|
"epoch": 2.7489378717448893,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004250710562320538,
|
|
"loss": 5.6169,
|
|
"mean_token_accuracy": 0.17995046377182006,
|
|
"num_tokens": 53800120.0,
|
|
"step": 27500
|
|
},
|
|
{
|
|
"entropy": 6.024582624435425,
|
|
"epoch": 2.749437696806118,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00042504446334373905,
|
|
"loss": 5.613,
|
|
"mean_token_accuracy": 0.18142711222171784,
|
|
"num_tokens": 53809960.0,
|
|
"step": 27505
|
|
},
|
|
{
|
|
"entropy": 5.990838813781738,
|
|
"epoch": 2.7499375218673463,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004250178666803442,
|
|
"loss": 5.5675,
|
|
"mean_token_accuracy": 0.1834932327270508,
|
|
"num_tokens": 53819356.0,
|
|
"step": 27510
|
|
},
|
|
{
|
|
"entropy": 5.956617069244385,
|
|
"epoch": 2.750437346928575,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004249912662425385,
|
|
"loss": 5.4984,
|
|
"mean_token_accuracy": 0.19156447798013687,
|
|
"num_tokens": 53830026.0,
|
|
"step": 27515
|
|
},
|
|
{
|
|
"entropy": 6.036260938644409,
|
|
"epoch": 2.7509371719898037,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00042496466203099107,
|
|
"loss": 5.6397,
|
|
"mean_token_accuracy": 0.17922402322292327,
|
|
"num_tokens": 53840040.0,
|
|
"step": 27520
|
|
},
|
|
{
|
|
"entropy": 6.052906322479248,
|
|
"epoch": 2.751436997051032,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00042493805404637136,
|
|
"loss": 5.6541,
|
|
"mean_token_accuracy": 0.17657300531864167,
|
|
"num_tokens": 53850106.0,
|
|
"step": 27525
|
|
},
|
|
{
|
|
"entropy": 6.033842420578003,
|
|
"epoch": 2.7519368221122606,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00042491144228934885,
|
|
"loss": 5.6291,
|
|
"mean_token_accuracy": 0.1847486600279808,
|
|
"num_tokens": 53861312.0,
|
|
"step": 27530
|
|
},
|
|
{
|
|
"entropy": 6.0748215675354,
|
|
"epoch": 2.7524366471734893,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000424884826760593,
|
|
"loss": 5.7329,
|
|
"mean_token_accuracy": 0.17697833180427552,
|
|
"num_tokens": 53871914.0,
|
|
"step": 27535
|
|
},
|
|
{
|
|
"entropy": 6.049887084960938,
|
|
"epoch": 2.752936472234718,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00042485820746077346,
|
|
"loss": 5.6448,
|
|
"mean_token_accuracy": 0.17929272055625917,
|
|
"num_tokens": 53881241.0,
|
|
"step": 27540
|
|
},
|
|
{
|
|
"entropy": 6.02434983253479,
|
|
"epoch": 2.7534362972959463,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00042483158439055995,
|
|
"loss": 5.6578,
|
|
"mean_token_accuracy": 0.1739363968372345,
|
|
"num_tokens": 53891002.0,
|
|
"step": 27545
|
|
},
|
|
{
|
|
"entropy": 6.043816232681275,
|
|
"epoch": 2.753936122357175,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004248049575506224,
|
|
"loss": 5.6567,
|
|
"mean_token_accuracy": 0.1759311318397522,
|
|
"num_tokens": 53900998.0,
|
|
"step": 27550
|
|
},
|
|
{
|
|
"entropy": 5.984628295898437,
|
|
"epoch": 2.7544359474184037,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004247783269416306,
|
|
"loss": 5.6112,
|
|
"mean_token_accuracy": 0.17506305128335953,
|
|
"num_tokens": 53910577.0,
|
|
"step": 27555
|
|
},
|
|
{
|
|
"entropy": 6.064738702774048,
|
|
"epoch": 2.754935772479632,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00042475169256425466,
|
|
"loss": 5.7389,
|
|
"mean_token_accuracy": 0.17451515644788743,
|
|
"num_tokens": 53919757.0,
|
|
"step": 27560
|
|
},
|
|
{
|
|
"entropy": 6.067226839065552,
|
|
"epoch": 2.7554355975408606,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004247250544191647,
|
|
"loss": 5.6318,
|
|
"mean_token_accuracy": 0.17141604274511338,
|
|
"num_tokens": 53928521.0,
|
|
"step": 27565
|
|
},
|
|
{
|
|
"entropy": 6.094553661346436,
|
|
"epoch": 2.7559354226020893,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00042469841250703086,
|
|
"loss": 5.7264,
|
|
"mean_token_accuracy": 0.1693292424082756,
|
|
"num_tokens": 53939127.0,
|
|
"step": 27570
|
|
},
|
|
{
|
|
"entropy": 5.996855974197388,
|
|
"epoch": 2.756435247663318,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004246717668285235,
|
|
"loss": 5.5199,
|
|
"mean_token_accuracy": 0.18679230362176896,
|
|
"num_tokens": 53948572.0,
|
|
"step": 27575
|
|
},
|
|
{
|
|
"entropy": 6.08230242729187,
|
|
"epoch": 2.7569350727245463,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00042464511738431296,
|
|
"loss": 5.6358,
|
|
"mean_token_accuracy": 0.18156180828809737,
|
|
"num_tokens": 53958332.0,
|
|
"step": 27580
|
|
},
|
|
{
|
|
"entropy": 6.039926195144654,
|
|
"epoch": 2.757434897785775,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00042461846417506983,
|
|
"loss": 5.6018,
|
|
"mean_token_accuracy": 0.184420670568943,
|
|
"num_tokens": 53968771.0,
|
|
"step": 27585
|
|
},
|
|
{
|
|
"entropy": 5.9971031665802,
|
|
"epoch": 2.7579347228470037,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004245918072014646,
|
|
"loss": 5.6357,
|
|
"mean_token_accuracy": 0.18151891082525254,
|
|
"num_tokens": 53979134.0,
|
|
"step": 27590
|
|
},
|
|
{
|
|
"entropy": 6.029516124725342,
|
|
"epoch": 2.758434547908232,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.000424565146464168,
|
|
"loss": 5.6629,
|
|
"mean_token_accuracy": 0.1756909191608429,
|
|
"num_tokens": 53990668.0,
|
|
"step": 27595
|
|
},
|
|
{
|
|
"entropy": 6.065501976013183,
|
|
"epoch": 2.7589343729694606,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00042453848196385085,
|
|
"loss": 5.7279,
|
|
"mean_token_accuracy": 0.17488906979560853,
|
|
"num_tokens": 54001559.0,
|
|
"step": 27600
|
|
},
|
|
{
|
|
"entropy": 6.005951547622681,
|
|
"epoch": 2.7594341980306893,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00042451181370118394,
|
|
"loss": 5.5725,
|
|
"mean_token_accuracy": 0.1816001832485199,
|
|
"num_tokens": 54010893.0,
|
|
"step": 27605
|
|
},
|
|
{
|
|
"entropy": 6.0518919944763185,
|
|
"epoch": 2.759934023091918,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004244851416768383,
|
|
"loss": 5.5948,
|
|
"mean_token_accuracy": 0.17763546854257584,
|
|
"num_tokens": 54019592.0,
|
|
"step": 27610
|
|
},
|
|
{
|
|
"entropy": 6.059850692749023,
|
|
"epoch": 2.7604338481531463,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004244584658914849,
|
|
"loss": 5.6902,
|
|
"mean_token_accuracy": 0.17630219459533691,
|
|
"num_tokens": 54029915.0,
|
|
"step": 27615
|
|
},
|
|
{
|
|
"entropy": 6.05860276222229,
|
|
"epoch": 2.760933673214375,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00042443178634579497,
|
|
"loss": 5.6793,
|
|
"mean_token_accuracy": 0.17579298019409179,
|
|
"num_tokens": 54039554.0,
|
|
"step": 27620
|
|
},
|
|
{
|
|
"entropy": 5.9232306480407715,
|
|
"epoch": 2.7614334982756037,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004244051030404398,
|
|
"loss": 5.4153,
|
|
"mean_token_accuracy": 0.2010583057999611,
|
|
"num_tokens": 54050184.0,
|
|
"step": 27625
|
|
},
|
|
{
|
|
"entropy": 5.935444259643555,
|
|
"epoch": 2.761933323336832,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.00042437841597609054,
|
|
"loss": 5.5445,
|
|
"mean_token_accuracy": 0.18731414675712585,
|
|
"num_tokens": 54058895.0,
|
|
"step": 27630
|
|
},
|
|
{
|
|
"entropy": 6.068425989151001,
|
|
"epoch": 2.7624331483980606,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004243517251534189,
|
|
"loss": 5.6421,
|
|
"mean_token_accuracy": 0.17791600227355958,
|
|
"num_tokens": 54068032.0,
|
|
"step": 27635
|
|
},
|
|
{
|
|
"entropy": 6.047348546981811,
|
|
"epoch": 2.7629329734592893,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004243250305730963,
|
|
"loss": 5.6912,
|
|
"mean_token_accuracy": 0.1749239444732666,
|
|
"num_tokens": 54076435.0,
|
|
"step": 27640
|
|
},
|
|
{
|
|
"entropy": 5.989130020141602,
|
|
"epoch": 2.763432798520518,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00042429833223579436,
|
|
"loss": 5.6106,
|
|
"mean_token_accuracy": 0.1813209906220436,
|
|
"num_tokens": 54086274.0,
|
|
"step": 27645
|
|
},
|
|
{
|
|
"entropy": 5.995919179916382,
|
|
"epoch": 2.7639326235817463,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00042427163014218473,
|
|
"loss": 5.6337,
|
|
"mean_token_accuracy": 0.17775212973356247,
|
|
"num_tokens": 54095699.0,
|
|
"step": 27650
|
|
},
|
|
{
|
|
"entropy": 5.989639377593994,
|
|
"epoch": 2.764432448642975,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00042424492429293933,
|
|
"loss": 5.5557,
|
|
"mean_token_accuracy": 0.19160015732049943,
|
|
"num_tokens": 54106424.0,
|
|
"step": 27655
|
|
},
|
|
{
|
|
"entropy": 6.015076780319214,
|
|
"epoch": 2.7649322737042037,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00042421821468873003,
|
|
"loss": 5.6181,
|
|
"mean_token_accuracy": 0.18182581216096877,
|
|
"num_tokens": 54115226.0,
|
|
"step": 27660
|
|
},
|
|
{
|
|
"entropy": 6.005518531799316,
|
|
"epoch": 2.765432098765432,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00042419150133022883,
|
|
"loss": 5.5575,
|
|
"mean_token_accuracy": 0.18699107468128204,
|
|
"num_tokens": 54124018.0,
|
|
"step": 27665
|
|
},
|
|
{
|
|
"entropy": 6.086720132827759,
|
|
"epoch": 2.7659319238266606,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004241647842181078,
|
|
"loss": 5.684,
|
|
"mean_token_accuracy": 0.17524344772100447,
|
|
"num_tokens": 54134096.0,
|
|
"step": 27670
|
|
},
|
|
{
|
|
"entropy": 6.067239093780517,
|
|
"epoch": 2.7664317488878893,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00042413806335303935,
|
|
"loss": 5.6926,
|
|
"mean_token_accuracy": 0.17154513746500016,
|
|
"num_tokens": 54143207.0,
|
|
"step": 27675
|
|
},
|
|
{
|
|
"entropy": 5.896594524383545,
|
|
"epoch": 2.766931573949118,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00042411133873569544,
|
|
"loss": 5.4725,
|
|
"mean_token_accuracy": 0.20239548534154891,
|
|
"num_tokens": 54153647.0,
|
|
"step": 27680
|
|
},
|
|
{
|
|
"entropy": 6.099235677719117,
|
|
"epoch": 2.7674313990103463,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004240846103667487,
|
|
"loss": 5.6291,
|
|
"mean_token_accuracy": 0.17519983947277068,
|
|
"num_tokens": 54163695.0,
|
|
"step": 27685
|
|
},
|
|
{
|
|
"entropy": 5.978342580795288,
|
|
"epoch": 2.767931224071575,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00042405787824687153,
|
|
"loss": 5.5716,
|
|
"mean_token_accuracy": 0.18243311643600463,
|
|
"num_tokens": 54174450.0,
|
|
"step": 27690
|
|
},
|
|
{
|
|
"entropy": 5.9343119144439695,
|
|
"epoch": 2.7684310491328032,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004240311423767364,
|
|
"loss": 5.5585,
|
|
"mean_token_accuracy": 0.19229740649461746,
|
|
"num_tokens": 54184328.0,
|
|
"step": 27695
|
|
},
|
|
{
|
|
"entropy": 5.99854736328125,
|
|
"epoch": 2.768930874194032,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004240044027570162,
|
|
"loss": 5.6011,
|
|
"mean_token_accuracy": 0.1869821533560753,
|
|
"num_tokens": 54193385.0,
|
|
"step": 27700
|
|
},
|
|
{
|
|
"entropy": 5.999873208999634,
|
|
"epoch": 2.7694306992552606,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004239776593883835,
|
|
"loss": 5.5587,
|
|
"mean_token_accuracy": 0.17899419963359833,
|
|
"num_tokens": 54203320.0,
|
|
"step": 27705
|
|
},
|
|
{
|
|
"entropy": 6.040283107757569,
|
|
"epoch": 2.7699305243164893,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00042395091227151124,
|
|
"loss": 5.6645,
|
|
"mean_token_accuracy": 0.18220154494047164,
|
|
"num_tokens": 54213395.0,
|
|
"step": 27710
|
|
},
|
|
{
|
|
"entropy": 6.0294169902801515,
|
|
"epoch": 2.770430349377718,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00042392416140707233,
|
|
"loss": 5.6473,
|
|
"mean_token_accuracy": 0.1815662771463394,
|
|
"num_tokens": 54222093.0,
|
|
"step": 27715
|
|
},
|
|
{
|
|
"entropy": 6.025890350341797,
|
|
"epoch": 2.7709301744389463,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004238974067957399,
|
|
"loss": 5.6228,
|
|
"mean_token_accuracy": 0.18027707934379578,
|
|
"num_tokens": 54231950.0,
|
|
"step": 27720
|
|
},
|
|
{
|
|
"entropy": 5.995367622375488,
|
|
"epoch": 2.771429999500175,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.000423870648438187,
|
|
"loss": 5.5474,
|
|
"mean_token_accuracy": 0.1846894085407257,
|
|
"num_tokens": 54241585.0,
|
|
"step": 27725
|
|
},
|
|
{
|
|
"entropy": 6.054909086227417,
|
|
"epoch": 2.7719298245614032,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004238438863350869,
|
|
"loss": 5.7056,
|
|
"mean_token_accuracy": 0.17887565344572068,
|
|
"num_tokens": 54251525.0,
|
|
"step": 27730
|
|
},
|
|
{
|
|
"entropy": 5.9493152618408205,
|
|
"epoch": 2.772429649622632,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004238171204871129,
|
|
"loss": 5.5652,
|
|
"mean_token_accuracy": 0.1839079886674881,
|
|
"num_tokens": 54260777.0,
|
|
"step": 27735
|
|
},
|
|
{
|
|
"entropy": 6.023270606994629,
|
|
"epoch": 2.7729294746838606,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00042379035089493844,
|
|
"loss": 5.651,
|
|
"mean_token_accuracy": 0.1747887536883354,
|
|
"num_tokens": 54270651.0,
|
|
"step": 27740
|
|
},
|
|
{
|
|
"entropy": 5.912592267990112,
|
|
"epoch": 2.7734292997450893,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004237635775592371,
|
|
"loss": 5.4547,
|
|
"mean_token_accuracy": 0.19226004779338837,
|
|
"num_tokens": 54280241.0,
|
|
"step": 27745
|
|
},
|
|
{
|
|
"entropy": 6.06895751953125,
|
|
"epoch": 2.773929124806318,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004237368004806823,
|
|
"loss": 5.6584,
|
|
"mean_token_accuracy": 0.17545924037694932,
|
|
"num_tokens": 54290075.0,
|
|
"step": 27750
|
|
},
|
|
{
|
|
"entropy": 6.000563907623291,
|
|
"epoch": 2.7744289498675463,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.000423710019659948,
|
|
"loss": 5.5726,
|
|
"mean_token_accuracy": 0.18461386263370513,
|
|
"num_tokens": 54298452.0,
|
|
"step": 27755
|
|
},
|
|
{
|
|
"entropy": 5.984912157058716,
|
|
"epoch": 2.774928774928775,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00042368323509770785,
|
|
"loss": 5.5362,
|
|
"mean_token_accuracy": 0.18808608502149582,
|
|
"num_tokens": 54308516.0,
|
|
"step": 27760
|
|
},
|
|
{
|
|
"entropy": 5.923238134384155,
|
|
"epoch": 2.7754285999900032,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004236564467946357,
|
|
"loss": 5.5318,
|
|
"mean_token_accuracy": 0.18420441597700118,
|
|
"num_tokens": 54317921.0,
|
|
"step": 27765
|
|
},
|
|
{
|
|
"entropy": 5.894258785247803,
|
|
"epoch": 2.775928425051232,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004236296547514056,
|
|
"loss": 5.506,
|
|
"mean_token_accuracy": 0.18776869177818298,
|
|
"num_tokens": 54327558.0,
|
|
"step": 27770
|
|
},
|
|
{
|
|
"entropy": 6.053262090682983,
|
|
"epoch": 2.7764282501124606,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004236028589686917,
|
|
"loss": 5.6536,
|
|
"mean_token_accuracy": 0.18385602831840514,
|
|
"num_tokens": 54337638.0,
|
|
"step": 27775
|
|
},
|
|
{
|
|
"entropy": 5.9901039600372314,
|
|
"epoch": 2.7769280751736893,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00042357605944716816,
|
|
"loss": 5.5454,
|
|
"mean_token_accuracy": 0.18917048573493958,
|
|
"num_tokens": 54345607.0,
|
|
"step": 27780
|
|
},
|
|
{
|
|
"entropy": 5.894578886032105,
|
|
"epoch": 2.777427900234918,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00042354925618750904,
|
|
"loss": 5.4703,
|
|
"mean_token_accuracy": 0.19210363924503326,
|
|
"num_tokens": 54355230.0,
|
|
"step": 27785
|
|
},
|
|
{
|
|
"entropy": 6.00942096710205,
|
|
"epoch": 2.7779277252961463,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00042352244919038895,
|
|
"loss": 5.6706,
|
|
"mean_token_accuracy": 0.1785041183233261,
|
|
"num_tokens": 54365449.0,
|
|
"step": 27790
|
|
},
|
|
{
|
|
"entropy": 6.021489810943604,
|
|
"epoch": 2.778427550357375,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00042349563845648226,
|
|
"loss": 5.573,
|
|
"mean_token_accuracy": 0.17892964482307433,
|
|
"num_tokens": 54375822.0,
|
|
"step": 27795
|
|
},
|
|
{
|
|
"entropy": 6.0785231590271,
|
|
"epoch": 2.7789273754186032,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004234688239864634,
|
|
"loss": 5.683,
|
|
"mean_token_accuracy": 0.17587544098496438,
|
|
"num_tokens": 54385365.0,
|
|
"step": 27800
|
|
},
|
|
{
|
|
"entropy": 6.003191566467285,
|
|
"epoch": 2.779427200479832,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004234420057810073,
|
|
"loss": 5.5537,
|
|
"mean_token_accuracy": 0.18722043335437774,
|
|
"num_tokens": 54394466.0,
|
|
"step": 27805
|
|
},
|
|
{
|
|
"entropy": 5.976953506469727,
|
|
"epoch": 2.7799270255410606,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00042341518384078847,
|
|
"loss": 5.5489,
|
|
"mean_token_accuracy": 0.18701144754886628,
|
|
"num_tokens": 54404011.0,
|
|
"step": 27810
|
|
},
|
|
{
|
|
"entropy": 5.9955237865447994,
|
|
"epoch": 2.7804268506022893,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004233883581664818,
|
|
"loss": 5.5821,
|
|
"mean_token_accuracy": 0.18463050276041032,
|
|
"num_tokens": 54413527.0,
|
|
"step": 27815
|
|
},
|
|
{
|
|
"entropy": 6.023649835586548,
|
|
"epoch": 2.780926675663518,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004233615287587622,
|
|
"loss": 5.6478,
|
|
"mean_token_accuracy": 0.18586431443691254,
|
|
"num_tokens": 54423301.0,
|
|
"step": 27820
|
|
},
|
|
{
|
|
"entropy": 6.065954971313476,
|
|
"epoch": 2.7814265007247463,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00042333469561830475,
|
|
"loss": 5.6463,
|
|
"mean_token_accuracy": 0.1780619964003563,
|
|
"num_tokens": 54433132.0,
|
|
"step": 27825
|
|
},
|
|
{
|
|
"entropy": 6.03499846458435,
|
|
"epoch": 2.781926325785975,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004233078587457845,
|
|
"loss": 5.645,
|
|
"mean_token_accuracy": 0.17746975570917128,
|
|
"num_tokens": 54442926.0,
|
|
"step": 27830
|
|
},
|
|
{
|
|
"entropy": 6.0900554180145265,
|
|
"epoch": 2.7824261508472032,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004232810181418767,
|
|
"loss": 5.6522,
|
|
"mean_token_accuracy": 0.16986499726772308,
|
|
"num_tokens": 54452325.0,
|
|
"step": 27835
|
|
},
|
|
{
|
|
"entropy": 5.970729160308838,
|
|
"epoch": 2.782925975908432,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004232541738072566,
|
|
"loss": 5.5616,
|
|
"mean_token_accuracy": 0.18229442089796066,
|
|
"num_tokens": 54462340.0,
|
|
"step": 27840
|
|
},
|
|
{
|
|
"entropy": 5.96690936088562,
|
|
"epoch": 2.7834258009696606,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00042322732574259976,
|
|
"loss": 5.4782,
|
|
"mean_token_accuracy": 0.19984378814697265,
|
|
"num_tokens": 54471752.0,
|
|
"step": 27845
|
|
},
|
|
{
|
|
"entropy": 6.0474255084991455,
|
|
"epoch": 2.7839256260308893,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00042320047394858143,
|
|
"loss": 5.6738,
|
|
"mean_token_accuracy": 0.17581633627414703,
|
|
"num_tokens": 54482712.0,
|
|
"step": 27850
|
|
},
|
|
{
|
|
"entropy": 6.076085710525513,
|
|
"epoch": 2.784425451092118,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004231736184258773,
|
|
"loss": 5.5892,
|
|
"mean_token_accuracy": 0.18659006655216218,
|
|
"num_tokens": 54492804.0,
|
|
"step": 27855
|
|
},
|
|
{
|
|
"entropy": 6.052265930175781,
|
|
"epoch": 2.7849252761533463,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004231467591751631,
|
|
"loss": 5.6705,
|
|
"mean_token_accuracy": 0.17916675209999083,
|
|
"num_tokens": 54502869.0,
|
|
"step": 27860
|
|
},
|
|
{
|
|
"entropy": 6.001364707946777,
|
|
"epoch": 2.785425101214575,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004231198961971145,
|
|
"loss": 5.6001,
|
|
"mean_token_accuracy": 0.18082303553819656,
|
|
"num_tokens": 54513089.0,
|
|
"step": 27865
|
|
},
|
|
{
|
|
"entropy": 6.038150310516357,
|
|
"epoch": 2.7859249262758032,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004230930294924075,
|
|
"loss": 5.6632,
|
|
"mean_token_accuracy": 0.17959298193454742,
|
|
"num_tokens": 54524312.0,
|
|
"step": 27870
|
|
},
|
|
{
|
|
"entropy": 5.9751868724823,
|
|
"epoch": 2.786424751337032,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00042306615906171794,
|
|
"loss": 5.6354,
|
|
"mean_token_accuracy": 0.18390797525644303,
|
|
"num_tokens": 54534258.0,
|
|
"step": 27875
|
|
},
|
|
{
|
|
"entropy": 6.071157312393188,
|
|
"epoch": 2.7869245763982606,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000423039284905722,
|
|
"loss": 5.6099,
|
|
"mean_token_accuracy": 0.17580223083496094,
|
|
"num_tokens": 54544411.0,
|
|
"step": 27880
|
|
},
|
|
{
|
|
"entropy": 6.070682191848755,
|
|
"epoch": 2.7874244014594893,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00042301240702509576,
|
|
"loss": 5.5711,
|
|
"mean_token_accuracy": 0.18581733107566833,
|
|
"num_tokens": 54553253.0,
|
|
"step": 27885
|
|
},
|
|
{
|
|
"entropy": 5.968079566955566,
|
|
"epoch": 2.7879242265207176,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004229855254205154,
|
|
"loss": 5.6094,
|
|
"mean_token_accuracy": 0.17641311138868332,
|
|
"num_tokens": 54563095.0,
|
|
"step": 27890
|
|
},
|
|
{
|
|
"entropy": 5.961511945724487,
|
|
"epoch": 2.7884240515819463,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00042295864009265723,
|
|
"loss": 5.5504,
|
|
"mean_token_accuracy": 0.1820025086402893,
|
|
"num_tokens": 54573969.0,
|
|
"step": 27895
|
|
},
|
|
{
|
|
"entropy": 6.068711662292481,
|
|
"epoch": 2.788923876643175,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00042293175104219776,
|
|
"loss": 5.6719,
|
|
"mean_token_accuracy": 0.17364476770162582,
|
|
"num_tokens": 54583864.0,
|
|
"step": 27900
|
|
},
|
|
{
|
|
"entropy": 6.096372270584107,
|
|
"epoch": 2.7894237017044032,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00042290485826981355,
|
|
"loss": 5.6904,
|
|
"mean_token_accuracy": 0.17532456815242767,
|
|
"num_tokens": 54594463.0,
|
|
"step": 27905
|
|
},
|
|
{
|
|
"entropy": 5.996795892715454,
|
|
"epoch": 2.789923526765632,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00042287796177618115,
|
|
"loss": 5.6125,
|
|
"mean_token_accuracy": 0.17855604737997055,
|
|
"num_tokens": 54603940.0,
|
|
"step": 27910
|
|
},
|
|
{
|
|
"entropy": 5.9317704200744625,
|
|
"epoch": 2.7904233518268606,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00042285106156197727,
|
|
"loss": 5.5724,
|
|
"mean_token_accuracy": 0.18209253251552582,
|
|
"num_tokens": 54613936.0,
|
|
"step": 27915
|
|
},
|
|
{
|
|
"entropy": 6.010437488555908,
|
|
"epoch": 2.7909231768880893,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004228241576278787,
|
|
"loss": 5.5903,
|
|
"mean_token_accuracy": 0.1866847813129425,
|
|
"num_tokens": 54622584.0,
|
|
"step": 27920
|
|
},
|
|
{
|
|
"entropy": 6.059363985061646,
|
|
"epoch": 2.7914230019493176,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00042279724997456246,
|
|
"loss": 5.6766,
|
|
"mean_token_accuracy": 0.17884342670440673,
|
|
"num_tokens": 54632899.0,
|
|
"step": 27925
|
|
},
|
|
{
|
|
"entropy": 6.146766281127929,
|
|
"epoch": 2.7919228270105463,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00042277033860270544,
|
|
"loss": 5.7792,
|
|
"mean_token_accuracy": 0.1684461787343025,
|
|
"num_tokens": 54644025.0,
|
|
"step": 27930
|
|
},
|
|
{
|
|
"entropy": 6.067764234542847,
|
|
"epoch": 2.792422652071775,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00042274342351298467,
|
|
"loss": 5.5865,
|
|
"mean_token_accuracy": 0.1783630758523941,
|
|
"num_tokens": 54652916.0,
|
|
"step": 27935
|
|
},
|
|
{
|
|
"entropy": 6.084703207015991,
|
|
"epoch": 2.7929224771330032,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004227165047060773,
|
|
"loss": 5.7695,
|
|
"mean_token_accuracy": 0.16561242192983627,
|
|
"num_tokens": 54662888.0,
|
|
"step": 27940
|
|
},
|
|
{
|
|
"entropy": 6.03842339515686,
|
|
"epoch": 2.793422302194232,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004226895821826608,
|
|
"loss": 5.6198,
|
|
"mean_token_accuracy": 0.1792700931429863,
|
|
"num_tokens": 54672597.0,
|
|
"step": 27945
|
|
},
|
|
{
|
|
"entropy": 5.983539009094239,
|
|
"epoch": 2.7939221272554606,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004226626559434124,
|
|
"loss": 5.6136,
|
|
"mean_token_accuracy": 0.18732032179832458,
|
|
"num_tokens": 54683284.0,
|
|
"step": 27950
|
|
},
|
|
{
|
|
"entropy": 6.0441666603088375,
|
|
"epoch": 2.7944219523166893,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00042263572598900956,
|
|
"loss": 5.6503,
|
|
"mean_token_accuracy": 0.1788380667567253,
|
|
"num_tokens": 54693207.0,
|
|
"step": 27955
|
|
},
|
|
{
|
|
"entropy": 5.986917114257812,
|
|
"epoch": 2.7949217773779176,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00042260879232012985,
|
|
"loss": 5.5343,
|
|
"mean_token_accuracy": 0.19085340201854706,
|
|
"num_tokens": 54703122.0,
|
|
"step": 27960
|
|
},
|
|
{
|
|
"entropy": 5.909074497222901,
|
|
"epoch": 2.7954216024391463,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00042258185493745086,
|
|
"loss": 5.5981,
|
|
"mean_token_accuracy": 0.18272251337766648,
|
|
"num_tokens": 54713034.0,
|
|
"step": 27965
|
|
},
|
|
{
|
|
"entropy": 6.08094539642334,
|
|
"epoch": 2.795921427500375,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004225549138416504,
|
|
"loss": 5.7873,
|
|
"mean_token_accuracy": 0.16631658375263214,
|
|
"num_tokens": 54722342.0,
|
|
"step": 27970
|
|
},
|
|
{
|
|
"entropy": 6.080085802078247,
|
|
"epoch": 2.7964212525616032,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004225279690334063,
|
|
"loss": 5.6558,
|
|
"mean_token_accuracy": 0.1741357773542404,
|
|
"num_tokens": 54732346.0,
|
|
"step": 27975
|
|
},
|
|
{
|
|
"entropy": 6.032880020141602,
|
|
"epoch": 2.796921077622832,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00042250102051339647,
|
|
"loss": 5.6345,
|
|
"mean_token_accuracy": 0.17384740710258484,
|
|
"num_tokens": 54742859.0,
|
|
"step": 27980
|
|
},
|
|
{
|
|
"entropy": 6.033864450454712,
|
|
"epoch": 2.7974209026840606,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00042247406828229897,
|
|
"loss": 5.5197,
|
|
"mean_token_accuracy": 0.18904136270284652,
|
|
"num_tokens": 54752782.0,
|
|
"step": 27985
|
|
},
|
|
{
|
|
"entropy": 5.994531154632568,
|
|
"epoch": 2.7979207277452893,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004224471123407917,
|
|
"loss": 5.6129,
|
|
"mean_token_accuracy": 0.18046984821558,
|
|
"num_tokens": 54762415.0,
|
|
"step": 27990
|
|
},
|
|
{
|
|
"entropy": 5.938282871246338,
|
|
"epoch": 2.7984205528065176,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004224201526895531,
|
|
"loss": 5.5678,
|
|
"mean_token_accuracy": 0.1816193178296089,
|
|
"num_tokens": 54773709.0,
|
|
"step": 27995
|
|
},
|
|
{
|
|
"entropy": 5.934268665313721,
|
|
"epoch": 2.7989203778677463,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00042239318932926144,
|
|
"loss": 5.5511,
|
|
"mean_token_accuracy": 0.19170697182416915,
|
|
"num_tokens": 54782895.0,
|
|
"step": 28000
|
|
},
|
|
{
|
|
"entropy": 5.999650526046753,
|
|
"epoch": 2.799420202928975,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000422366222260595,
|
|
"loss": 5.6092,
|
|
"mean_token_accuracy": 0.17792854607105255,
|
|
"num_tokens": 54793032.0,
|
|
"step": 28005
|
|
},
|
|
{
|
|
"entropy": 6.051441383361817,
|
|
"epoch": 2.7999200279902032,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00042233925148423235,
|
|
"loss": 5.6703,
|
|
"mean_token_accuracy": 0.1752370297908783,
|
|
"num_tokens": 54803325.0,
|
|
"step": 28010
|
|
},
|
|
{
|
|
"entropy": 6.042774343490601,
|
|
"epoch": 2.800419853051432,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004223122770008521,
|
|
"loss": 5.6726,
|
|
"mean_token_accuracy": 0.17492060214281083,
|
|
"num_tokens": 54813630.0,
|
|
"step": 28015
|
|
},
|
|
{
|
|
"entropy": 6.0391627788543705,
|
|
"epoch": 2.8009196781126606,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00042228529881113285,
|
|
"loss": 5.611,
|
|
"mean_token_accuracy": 0.17794201523065567,
|
|
"num_tokens": 54822916.0,
|
|
"step": 28020
|
|
},
|
|
{
|
|
"entropy": 5.955593395233154,
|
|
"epoch": 2.8014195031738893,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00042225831691575336,
|
|
"loss": 5.5319,
|
|
"mean_token_accuracy": 0.18843859434127808,
|
|
"num_tokens": 54834650.0,
|
|
"step": 28025
|
|
},
|
|
{
|
|
"entropy": 6.014127397537232,
|
|
"epoch": 2.8019193282351176,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004222313313153925,
|
|
"loss": 5.6129,
|
|
"mean_token_accuracy": 0.17973574995994568,
|
|
"num_tokens": 54843347.0,
|
|
"step": 28030
|
|
},
|
|
{
|
|
"entropy": 5.855348682403564,
|
|
"epoch": 2.8024191532963463,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.00042220434201072917,
|
|
"loss": 5.4451,
|
|
"mean_token_accuracy": 0.19564231634140014,
|
|
"num_tokens": 54853625.0,
|
|
"step": 28035
|
|
},
|
|
{
|
|
"entropy": 6.076178455352784,
|
|
"epoch": 2.802918978357575,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004221773490024426,
|
|
"loss": 5.74,
|
|
"mean_token_accuracy": 0.18092188537120818,
|
|
"num_tokens": 54863796.0,
|
|
"step": 28040
|
|
},
|
|
{
|
|
"entropy": 6.080136251449585,
|
|
"epoch": 2.8034188034188032,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004221503522912117,
|
|
"loss": 5.6093,
|
|
"mean_token_accuracy": 0.18051760494709015,
|
|
"num_tokens": 54872766.0,
|
|
"step": 28045
|
|
},
|
|
{
|
|
"entropy": 5.945446443557739,
|
|
"epoch": 2.803918628480032,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00042212335187771587,
|
|
"loss": 5.5372,
|
|
"mean_token_accuracy": 0.18604232370853424,
|
|
"num_tokens": 54881234.0,
|
|
"step": 28050
|
|
},
|
|
{
|
|
"entropy": 5.9987424373626705,
|
|
"epoch": 2.8044184535412606,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00042209634776263434,
|
|
"loss": 5.6051,
|
|
"mean_token_accuracy": 0.17928128689527512,
|
|
"num_tokens": 54890830.0,
|
|
"step": 28055
|
|
},
|
|
{
|
|
"entropy": 6.074267292022705,
|
|
"epoch": 2.8049182786024893,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004220693399466466,
|
|
"loss": 5.7166,
|
|
"mean_token_accuracy": 0.17546866983175277,
|
|
"num_tokens": 54900496.0,
|
|
"step": 28060
|
|
},
|
|
{
|
|
"entropy": 6.1133912086486815,
|
|
"epoch": 2.8054181036637176,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00042204232843043207,
|
|
"loss": 5.6698,
|
|
"mean_token_accuracy": 0.17304071933031082,
|
|
"num_tokens": 54911190.0,
|
|
"step": 28065
|
|
},
|
|
{
|
|
"entropy": 5.9979980945587155,
|
|
"epoch": 2.8059179287249463,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00042201531321467027,
|
|
"loss": 5.5487,
|
|
"mean_token_accuracy": 0.18804462403059005,
|
|
"num_tokens": 54919817.0,
|
|
"step": 28070
|
|
},
|
|
{
|
|
"entropy": 5.987304782867431,
|
|
"epoch": 2.806417753786175,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00042198829430004114,
|
|
"loss": 5.6074,
|
|
"mean_token_accuracy": 0.1779014825820923,
|
|
"num_tokens": 54930549.0,
|
|
"step": 28075
|
|
},
|
|
{
|
|
"entropy": 5.959118747711182,
|
|
"epoch": 2.8069175788474032,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00042196127168722436,
|
|
"loss": 5.6355,
|
|
"mean_token_accuracy": 0.18764781206846237,
|
|
"num_tokens": 54940016.0,
|
|
"step": 28080
|
|
},
|
|
{
|
|
"entropy": 6.0029503345489506,
|
|
"epoch": 2.807417403908632,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004219342453768998,
|
|
"loss": 5.673,
|
|
"mean_token_accuracy": 0.17937340438365937,
|
|
"num_tokens": 54949664.0,
|
|
"step": 28085
|
|
},
|
|
{
|
|
"entropy": 6.026821851730347,
|
|
"epoch": 2.8079172289698606,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004219072153697474,
|
|
"loss": 5.662,
|
|
"mean_token_accuracy": 0.1752329647541046,
|
|
"num_tokens": 54959931.0,
|
|
"step": 28090
|
|
},
|
|
{
|
|
"entropy": 5.945647859573365,
|
|
"epoch": 2.8084170540310893,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004218801816664473,
|
|
"loss": 5.4948,
|
|
"mean_token_accuracy": 0.18873592913150788,
|
|
"num_tokens": 54969902.0,
|
|
"step": 28095
|
|
},
|
|
{
|
|
"entropy": 5.942046594619751,
|
|
"epoch": 2.8089168790923176,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004218531442676796,
|
|
"loss": 5.5991,
|
|
"mean_token_accuracy": 0.17489945888519287,
|
|
"num_tokens": 54978865.0,
|
|
"step": 28100
|
|
},
|
|
{
|
|
"entropy": 6.005749177932739,
|
|
"epoch": 2.8094167041535463,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004218261031741246,
|
|
"loss": 5.5478,
|
|
"mean_token_accuracy": 0.1830482542514801,
|
|
"num_tokens": 54987895.0,
|
|
"step": 28105
|
|
},
|
|
{
|
|
"entropy": 6.0160480499267575,
|
|
"epoch": 2.809916529214775,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00042179905838646254,
|
|
"loss": 5.5731,
|
|
"mean_token_accuracy": 0.17957282215356826,
|
|
"num_tokens": 54997703.0,
|
|
"step": 28110
|
|
},
|
|
{
|
|
"entropy": 5.967171716690063,
|
|
"epoch": 2.8104163542760032,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000421772009905374,
|
|
"loss": 5.5345,
|
|
"mean_token_accuracy": 0.1867477133870125,
|
|
"num_tokens": 55007591.0,
|
|
"step": 28115
|
|
},
|
|
{
|
|
"entropy": 5.955159997940063,
|
|
"epoch": 2.810916179337232,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004217449577315395,
|
|
"loss": 5.6039,
|
|
"mean_token_accuracy": 0.18318414241075515,
|
|
"num_tokens": 55017784.0,
|
|
"step": 28120
|
|
},
|
|
{
|
|
"entropy": 5.955984687805175,
|
|
"epoch": 2.8114160043984606,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004217179018656396,
|
|
"loss": 5.5367,
|
|
"mean_token_accuracy": 0.1905265048146248,
|
|
"num_tokens": 55027336.0,
|
|
"step": 28125
|
|
},
|
|
{
|
|
"entropy": 6.033627605438232,
|
|
"epoch": 2.8119158294596893,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000421690842308355,
|
|
"loss": 5.6164,
|
|
"mean_token_accuracy": 0.17633572965860367,
|
|
"num_tokens": 55037102.0,
|
|
"step": 28130
|
|
},
|
|
{
|
|
"entropy": 5.991381216049194,
|
|
"epoch": 2.8124156545209176,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004216637790603667,
|
|
"loss": 5.6844,
|
|
"mean_token_accuracy": 0.1774497076869011,
|
|
"num_tokens": 55046528.0,
|
|
"step": 28135
|
|
},
|
|
{
|
|
"entropy": 5.989004135131836,
|
|
"epoch": 2.8129154795821463,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004216367121223553,
|
|
"loss": 5.6322,
|
|
"mean_token_accuracy": 0.17868288308382035,
|
|
"num_tokens": 55057175.0,
|
|
"step": 28140
|
|
},
|
|
{
|
|
"entropy": 6.059020566940307,
|
|
"epoch": 2.813415304643375,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000421609641495002,
|
|
"loss": 5.6934,
|
|
"mean_token_accuracy": 0.17114609181880952,
|
|
"num_tokens": 55067345.0,
|
|
"step": 28145
|
|
},
|
|
{
|
|
"entropy": 6.039589691162109,
|
|
"epoch": 2.8139151297046032,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00042158256717898785,
|
|
"loss": 5.548,
|
|
"mean_token_accuracy": 0.1870230421423912,
|
|
"num_tokens": 55076728.0,
|
|
"step": 28150
|
|
},
|
|
{
|
|
"entropy": 5.997413206100464,
|
|
"epoch": 2.814414954765832,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000421555489174994,
|
|
"loss": 5.6443,
|
|
"mean_token_accuracy": 0.18347059935331345,
|
|
"num_tokens": 55086262.0,
|
|
"step": 28155
|
|
},
|
|
{
|
|
"entropy": 5.89373369216919,
|
|
"epoch": 2.8149147798270606,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00042152840748370184,
|
|
"loss": 5.4622,
|
|
"mean_token_accuracy": 0.19442293792963028,
|
|
"num_tokens": 55095096.0,
|
|
"step": 28160
|
|
},
|
|
{
|
|
"entropy": 5.932889413833618,
|
|
"epoch": 2.8154146048882893,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004215013221057926,
|
|
"loss": 5.5493,
|
|
"mean_token_accuracy": 0.1874716266989708,
|
|
"num_tokens": 55104961.0,
|
|
"step": 28165
|
|
},
|
|
{
|
|
"entropy": 5.994808149337769,
|
|
"epoch": 2.8159144299495176,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004214742330419478,
|
|
"loss": 5.5757,
|
|
"mean_token_accuracy": 0.18671636432409286,
|
|
"num_tokens": 55114069.0,
|
|
"step": 28170
|
|
},
|
|
{
|
|
"entropy": 5.983975172042847,
|
|
"epoch": 2.8164142550107463,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00042144714029284893,
|
|
"loss": 5.5429,
|
|
"mean_token_accuracy": 0.1892799913883209,
|
|
"num_tokens": 55124775.0,
|
|
"step": 28175
|
|
},
|
|
{
|
|
"entropy": 6.114463901519775,
|
|
"epoch": 2.816914080071975,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00042142004385917783,
|
|
"loss": 5.7535,
|
|
"mean_token_accuracy": 0.1713150754570961,
|
|
"num_tokens": 55134245.0,
|
|
"step": 28180
|
|
},
|
|
{
|
|
"entropy": 6.020087194442749,
|
|
"epoch": 2.8174139051332032,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.000421392943741616,
|
|
"loss": 5.6807,
|
|
"mean_token_accuracy": 0.17656381279230118,
|
|
"num_tokens": 55145770.0,
|
|
"step": 28185
|
|
},
|
|
{
|
|
"entropy": 6.043983316421508,
|
|
"epoch": 2.817913730194432,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004213658399408454,
|
|
"loss": 5.5911,
|
|
"mean_token_accuracy": 0.17982300072908403,
|
|
"num_tokens": 55156618.0,
|
|
"step": 28190
|
|
},
|
|
{
|
|
"entropy": 6.010182046890259,
|
|
"epoch": 2.8184135552556606,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004213387324575479,
|
|
"loss": 5.5541,
|
|
"mean_token_accuracy": 0.18692696839571,
|
|
"num_tokens": 55166323.0,
|
|
"step": 28195
|
|
},
|
|
{
|
|
"entropy": 6.061015892028808,
|
|
"epoch": 2.8189133803168893,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004213116212924056,
|
|
"loss": 5.8094,
|
|
"mean_token_accuracy": 0.17035490572452544,
|
|
"num_tokens": 55176037.0,
|
|
"step": 28200
|
|
},
|
|
{
|
|
"entropy": 6.09406476020813,
|
|
"epoch": 2.8194132053781176,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00042128450644610046,
|
|
"loss": 5.629,
|
|
"mean_token_accuracy": 0.17959488481283187,
|
|
"num_tokens": 55185861.0,
|
|
"step": 28205
|
|
},
|
|
{
|
|
"entropy": 6.001201152801514,
|
|
"epoch": 2.8199130304393463,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00042125738791931486,
|
|
"loss": 5.6246,
|
|
"mean_token_accuracy": 0.18030940592288972,
|
|
"num_tokens": 55196126.0,
|
|
"step": 28210
|
|
},
|
|
{
|
|
"entropy": 5.952488803863526,
|
|
"epoch": 2.8204128555005745,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.000421230265712731,
|
|
"loss": 5.5529,
|
|
"mean_token_accuracy": 0.18962854146957397,
|
|
"num_tokens": 55205108.0,
|
|
"step": 28215
|
|
},
|
|
{
|
|
"entropy": 6.001776838302613,
|
|
"epoch": 2.820912680561803,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004212031398270313,
|
|
"loss": 5.6662,
|
|
"mean_token_accuracy": 0.17667269557714463,
|
|
"num_tokens": 55215351.0,
|
|
"step": 28220
|
|
},
|
|
{
|
|
"entropy": 5.982744932174683,
|
|
"epoch": 2.821412505623032,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00042117601026289827,
|
|
"loss": 5.5452,
|
|
"mean_token_accuracy": 0.18609317690134047,
|
|
"num_tokens": 55224594.0,
|
|
"step": 28225
|
|
},
|
|
{
|
|
"entropy": 6.039327096939087,
|
|
"epoch": 2.8219123306842606,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00042114887702101434,
|
|
"loss": 5.6174,
|
|
"mean_token_accuracy": 0.176704303920269,
|
|
"num_tokens": 55234600.0,
|
|
"step": 28230
|
|
},
|
|
{
|
|
"entropy": 6.002168655395508,
|
|
"epoch": 2.8224121557454893,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00042112174010206226,
|
|
"loss": 5.5387,
|
|
"mean_token_accuracy": 0.18555715084075927,
|
|
"num_tokens": 55243377.0,
|
|
"step": 28235
|
|
},
|
|
{
|
|
"entropy": 5.981421852111817,
|
|
"epoch": 2.8229119808067176,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00042109459950672487,
|
|
"loss": 5.559,
|
|
"mean_token_accuracy": 0.18348946869373323,
|
|
"num_tokens": 55252245.0,
|
|
"step": 28240
|
|
},
|
|
{
|
|
"entropy": 5.999243974685669,
|
|
"epoch": 2.8234118058679463,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00042106745523568494,
|
|
"loss": 5.6414,
|
|
"mean_token_accuracy": 0.17561950981616975,
|
|
"num_tokens": 55261784.0,
|
|
"step": 28245
|
|
},
|
|
{
|
|
"entropy": 6.010159492492676,
|
|
"epoch": 2.8239116309291745,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00042104030728962535,
|
|
"loss": 5.6009,
|
|
"mean_token_accuracy": 0.1822350576519966,
|
|
"num_tokens": 55272151.0,
|
|
"step": 28250
|
|
},
|
|
{
|
|
"entropy": 6.070586919784546,
|
|
"epoch": 2.824411455990403,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00042101315566922927,
|
|
"loss": 5.6099,
|
|
"mean_token_accuracy": 0.1749724805355072,
|
|
"num_tokens": 55281800.0,
|
|
"step": 28255
|
|
},
|
|
{
|
|
"entropy": 6.049679279327393,
|
|
"epoch": 2.824911281051632,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00042098600037517985,
|
|
"loss": 5.6316,
|
|
"mean_token_accuracy": 0.17606378197669983,
|
|
"num_tokens": 55291297.0,
|
|
"step": 28260
|
|
},
|
|
{
|
|
"entropy": 5.934825468063354,
|
|
"epoch": 2.8254111061128606,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004209588414081601,
|
|
"loss": 5.5439,
|
|
"mean_token_accuracy": 0.1925976261496544,
|
|
"num_tokens": 55300265.0,
|
|
"step": 28265
|
|
},
|
|
{
|
|
"entropy": 5.960999870300293,
|
|
"epoch": 2.8259109311740893,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00042093167876885345,
|
|
"loss": 5.5411,
|
|
"mean_token_accuracy": 0.18488650321960448,
|
|
"num_tokens": 55310802.0,
|
|
"step": 28270
|
|
},
|
|
{
|
|
"entropy": 6.01676836013794,
|
|
"epoch": 2.8264107562353176,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004209045124579434,
|
|
"loss": 5.6341,
|
|
"mean_token_accuracy": 0.1857464075088501,
|
|
"num_tokens": 55320871.0,
|
|
"step": 28275
|
|
},
|
|
{
|
|
"entropy": 6.063550853729248,
|
|
"epoch": 2.8269105812965463,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00042087734247611333,
|
|
"loss": 5.6755,
|
|
"mean_token_accuracy": 0.17270337641239167,
|
|
"num_tokens": 55330419.0,
|
|
"step": 28280
|
|
},
|
|
{
|
|
"entropy": 6.056761121749878,
|
|
"epoch": 2.8274104063577745,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004208501688240468,
|
|
"loss": 5.661,
|
|
"mean_token_accuracy": 0.182366219162941,
|
|
"num_tokens": 55339930.0,
|
|
"step": 28285
|
|
},
|
|
{
|
|
"entropy": 6.055887126922608,
|
|
"epoch": 2.827910231419003,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00042082299150242764,
|
|
"loss": 5.6187,
|
|
"mean_token_accuracy": 0.1859167367219925,
|
|
"num_tokens": 55349871.0,
|
|
"step": 28290
|
|
},
|
|
{
|
|
"entropy": 6.050034999847412,
|
|
"epoch": 2.828410056480232,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004207958105119395,
|
|
"loss": 5.6394,
|
|
"mean_token_accuracy": 0.1731743633747101,
|
|
"num_tokens": 55360046.0,
|
|
"step": 28295
|
|
},
|
|
{
|
|
"entropy": 5.980698442459106,
|
|
"epoch": 2.8289098815414606,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00042076862585326626,
|
|
"loss": 5.5387,
|
|
"mean_token_accuracy": 0.18994793742895127,
|
|
"num_tokens": 55370173.0,
|
|
"step": 28300
|
|
},
|
|
{
|
|
"entropy": 5.991707134246826,
|
|
"epoch": 2.8294097066026893,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00042074143752709195,
|
|
"loss": 5.6199,
|
|
"mean_token_accuracy": 0.18183928728103638,
|
|
"num_tokens": 55380947.0,
|
|
"step": 28305
|
|
},
|
|
{
|
|
"entropy": 6.072722482681274,
|
|
"epoch": 2.8299095316639176,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004207142455341005,
|
|
"loss": 5.6797,
|
|
"mean_token_accuracy": 0.1775285616517067,
|
|
"num_tokens": 55390317.0,
|
|
"step": 28310
|
|
},
|
|
{
|
|
"entropy": 5.996292352676392,
|
|
"epoch": 2.8304093567251463,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00042068704987497627,
|
|
"loss": 5.4908,
|
|
"mean_token_accuracy": 0.18484881222248079,
|
|
"num_tokens": 55400729.0,
|
|
"step": 28315
|
|
},
|
|
{
|
|
"entropy": 5.957330846786499,
|
|
"epoch": 2.8309091817863745,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00042065985055040326,
|
|
"loss": 5.5756,
|
|
"mean_token_accuracy": 0.1845529109239578,
|
|
"num_tokens": 55409770.0,
|
|
"step": 28320
|
|
},
|
|
{
|
|
"entropy": 5.970203256607055,
|
|
"epoch": 2.831409006847603,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004206326475610658,
|
|
"loss": 5.643,
|
|
"mean_token_accuracy": 0.18059325069189072,
|
|
"num_tokens": 55419521.0,
|
|
"step": 28325
|
|
},
|
|
{
|
|
"entropy": 6.034972715377807,
|
|
"epoch": 2.831908831908832,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00042060544090764856,
|
|
"loss": 5.7008,
|
|
"mean_token_accuracy": 0.18023770600557326,
|
|
"num_tokens": 55429496.0,
|
|
"step": 28330
|
|
},
|
|
{
|
|
"entropy": 6.000565004348755,
|
|
"epoch": 2.8324086569700606,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004205782305908358,
|
|
"loss": 5.6063,
|
|
"mean_token_accuracy": 0.18216612040996552,
|
|
"num_tokens": 55438465.0,
|
|
"step": 28335
|
|
},
|
|
{
|
|
"entropy": 6.016143941879273,
|
|
"epoch": 2.8329084820312893,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004205510166113122,
|
|
"loss": 5.5837,
|
|
"mean_token_accuracy": 0.18668380081653596,
|
|
"num_tokens": 55448061.0,
|
|
"step": 28340
|
|
},
|
|
{
|
|
"entropy": 5.869404888153076,
|
|
"epoch": 2.8334083070925176,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00042052379896976254,
|
|
"loss": 5.5063,
|
|
"mean_token_accuracy": 0.1924541860818863,
|
|
"num_tokens": 55456363.0,
|
|
"step": 28345
|
|
},
|
|
{
|
|
"entropy": 5.944651556015015,
|
|
"epoch": 2.8339081321537463,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004204965776668716,
|
|
"loss": 5.5532,
|
|
"mean_token_accuracy": 0.18084517270326614,
|
|
"num_tokens": 55466507.0,
|
|
"step": 28350
|
|
},
|
|
{
|
|
"entropy": 6.097656202316284,
|
|
"epoch": 2.8344079572149745,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004204693527033241,
|
|
"loss": 5.6486,
|
|
"mean_token_accuracy": 0.18026620298624038,
|
|
"num_tokens": 55476723.0,
|
|
"step": 28355
|
|
},
|
|
{
|
|
"entropy": 6.0265357971191404,
|
|
"epoch": 2.834907782276203,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00042044212407980517,
|
|
"loss": 5.6431,
|
|
"mean_token_accuracy": 0.17976395636796952,
|
|
"num_tokens": 55486227.0,
|
|
"step": 28360
|
|
},
|
|
{
|
|
"entropy": 6.026445055007935,
|
|
"epoch": 2.835407607337432,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00042041489179699983,
|
|
"loss": 5.6301,
|
|
"mean_token_accuracy": 0.18020037710666656,
|
|
"num_tokens": 55495899.0,
|
|
"step": 28365
|
|
},
|
|
{
|
|
"entropy": 5.937975120544434,
|
|
"epoch": 2.8359074323986606,
|
|
"grad_norm": 1.921875,
|
|
"learning_rate": 0.0004203876558555932,
|
|
"loss": 5.608,
|
|
"mean_token_accuracy": 0.1920860931277275,
|
|
"num_tokens": 55506164.0,
|
|
"step": 28370
|
|
},
|
|
{
|
|
"entropy": 6.003772926330567,
|
|
"epoch": 2.8364072574598893,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00042036041625627055,
|
|
"loss": 5.6377,
|
|
"mean_token_accuracy": 0.17785289883613586,
|
|
"num_tokens": 55515159.0,
|
|
"step": 28375
|
|
},
|
|
{
|
|
"entropy": 5.991685914993286,
|
|
"epoch": 2.8369070825211176,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00042033317299971726,
|
|
"loss": 5.656,
|
|
"mean_token_accuracy": 0.17803092747926713,
|
|
"num_tokens": 55524728.0,
|
|
"step": 28380
|
|
},
|
|
{
|
|
"entropy": 6.037967872619629,
|
|
"epoch": 2.8374069075823463,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004203059260866187,
|
|
"loss": 5.6331,
|
|
"mean_token_accuracy": 0.17850785553455353,
|
|
"num_tokens": 55534555.0,
|
|
"step": 28385
|
|
},
|
|
{
|
|
"entropy": 6.020828342437744,
|
|
"epoch": 2.8379067326435745,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004202786755176604,
|
|
"loss": 5.6606,
|
|
"mean_token_accuracy": 0.18856139332056046,
|
|
"num_tokens": 55544156.0,
|
|
"step": 28390
|
|
},
|
|
{
|
|
"entropy": 6.041080141067505,
|
|
"epoch": 2.838406557704803,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004202514212935281,
|
|
"loss": 5.614,
|
|
"mean_token_accuracy": 0.1849908247590065,
|
|
"num_tokens": 55553912.0,
|
|
"step": 28395
|
|
},
|
|
{
|
|
"entropy": 5.997678184509278,
|
|
"epoch": 2.838906382766032,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004202241634149074,
|
|
"loss": 5.5994,
|
|
"mean_token_accuracy": 0.1821608677506447,
|
|
"num_tokens": 55564052.0,
|
|
"step": 28400
|
|
},
|
|
{
|
|
"entropy": 5.854486656188965,
|
|
"epoch": 2.8394062078272606,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.00042019690188248407,
|
|
"loss": 5.3776,
|
|
"mean_token_accuracy": 0.2148037001490593,
|
|
"num_tokens": 55574098.0,
|
|
"step": 28405
|
|
},
|
|
{
|
|
"entropy": 5.97832932472229,
|
|
"epoch": 2.839906032888489,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004201696366969441,
|
|
"loss": 5.5179,
|
|
"mean_token_accuracy": 0.19205449074506759,
|
|
"num_tokens": 55584429.0,
|
|
"step": 28410
|
|
},
|
|
{
|
|
"entropy": 6.088295221328735,
|
|
"epoch": 2.8404058579497176,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004201423678589734,
|
|
"loss": 5.6528,
|
|
"mean_token_accuracy": 0.17858751714229584,
|
|
"num_tokens": 55595990.0,
|
|
"step": 28415
|
|
},
|
|
{
|
|
"entropy": 5.995885801315308,
|
|
"epoch": 2.8409056830109463,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000420115095369258,
|
|
"loss": 5.6689,
|
|
"mean_token_accuracy": 0.1810540609061718,
|
|
"num_tokens": 55606208.0,
|
|
"step": 28420
|
|
},
|
|
{
|
|
"entropy": 5.939640378952026,
|
|
"epoch": 2.8414055080721745,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004200878192284843,
|
|
"loss": 5.5107,
|
|
"mean_token_accuracy": 0.1906447008252144,
|
|
"num_tokens": 55615790.0,
|
|
"step": 28425
|
|
},
|
|
{
|
|
"entropy": 6.060921621322632,
|
|
"epoch": 2.841905333133403,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004200605394373383,
|
|
"loss": 5.611,
|
|
"mean_token_accuracy": 0.18299693167209624,
|
|
"num_tokens": 55625914.0,
|
|
"step": 28430
|
|
},
|
|
{
|
|
"entropy": 5.983905220031739,
|
|
"epoch": 2.842405158194632,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004200332559965065,
|
|
"loss": 5.5711,
|
|
"mean_token_accuracy": 0.19117571115493776,
|
|
"num_tokens": 55636019.0,
|
|
"step": 28435
|
|
},
|
|
{
|
|
"entropy": 5.9941291332244875,
|
|
"epoch": 2.8429049832558606,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004200059689066752,
|
|
"loss": 5.6597,
|
|
"mean_token_accuracy": 0.17870039641857147,
|
|
"num_tokens": 55645713.0,
|
|
"step": 28440
|
|
},
|
|
{
|
|
"entropy": 6.041415977478027,
|
|
"epoch": 2.843404808317089,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00041997867816853115,
|
|
"loss": 5.6795,
|
|
"mean_token_accuracy": 0.17631586343050004,
|
|
"num_tokens": 55655773.0,
|
|
"step": 28445
|
|
},
|
|
{
|
|
"entropy": 6.039073753356933,
|
|
"epoch": 2.8439046333783176,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00041995138378276084,
|
|
"loss": 5.5877,
|
|
"mean_token_accuracy": 0.18685323148965835,
|
|
"num_tokens": 55664647.0,
|
|
"step": 28450
|
|
},
|
|
{
|
|
"entropy": 6.0694043159484865,
|
|
"epoch": 2.8444044584395463,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00041992408575005095,
|
|
"loss": 5.7106,
|
|
"mean_token_accuracy": 0.17319973558187485,
|
|
"num_tokens": 55674610.0,
|
|
"step": 28455
|
|
},
|
|
{
|
|
"entropy": 5.9723268985748295,
|
|
"epoch": 2.8449042835007745,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004198967840710884,
|
|
"loss": 5.5916,
|
|
"mean_token_accuracy": 0.1780230313539505,
|
|
"num_tokens": 55684260.0,
|
|
"step": 28460
|
|
},
|
|
{
|
|
"entropy": 5.979046630859375,
|
|
"epoch": 2.845404108562003,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00041986947874656,
|
|
"loss": 5.5726,
|
|
"mean_token_accuracy": 0.1867212638258934,
|
|
"num_tokens": 55693546.0,
|
|
"step": 28465
|
|
},
|
|
{
|
|
"entropy": 6.011122035980224,
|
|
"epoch": 2.845903933623232,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004198421697771529,
|
|
"loss": 5.5749,
|
|
"mean_token_accuracy": 0.1885392040014267,
|
|
"num_tokens": 55702824.0,
|
|
"step": 28470
|
|
},
|
|
{
|
|
"entropy": 6.045650482177734,
|
|
"epoch": 2.8464037586844606,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000419814857163554,
|
|
"loss": 5.6598,
|
|
"mean_token_accuracy": 0.1745161607861519,
|
|
"num_tokens": 55712522.0,
|
|
"step": 28475
|
|
},
|
|
{
|
|
"entropy": 5.984211874008179,
|
|
"epoch": 2.846903583745689,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004197875409064506,
|
|
"loss": 5.6295,
|
|
"mean_token_accuracy": 0.18120575398206712,
|
|
"num_tokens": 55723093.0,
|
|
"step": 28480
|
|
},
|
|
{
|
|
"entropy": 5.853728485107422,
|
|
"epoch": 2.8474034088069176,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004197602210065299,
|
|
"loss": 5.3936,
|
|
"mean_token_accuracy": 0.21124559491872788,
|
|
"num_tokens": 55732583.0,
|
|
"step": 28485
|
|
},
|
|
{
|
|
"entropy": 6.042953109741211,
|
|
"epoch": 2.8479032338681463,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004197328974644793,
|
|
"loss": 5.6851,
|
|
"mean_token_accuracy": 0.1783396080136299,
|
|
"num_tokens": 55742777.0,
|
|
"step": 28490
|
|
},
|
|
{
|
|
"entropy": 6.069170808792114,
|
|
"epoch": 2.8484030589293745,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004197055702809862,
|
|
"loss": 5.6246,
|
|
"mean_token_accuracy": 0.17879858762025833,
|
|
"num_tokens": 55751587.0,
|
|
"step": 28495
|
|
},
|
|
{
|
|
"entropy": 6.052051782608032,
|
|
"epoch": 2.848902883990603,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004196782394567382,
|
|
"loss": 5.6845,
|
|
"mean_token_accuracy": 0.17519346326589585,
|
|
"num_tokens": 55761959.0,
|
|
"step": 28500
|
|
},
|
|
{
|
|
"entropy": 6.058198881149292,
|
|
"epoch": 2.849402709051832,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000419650904992423,
|
|
"loss": 5.6247,
|
|
"mean_token_accuracy": 0.17760857343673705,
|
|
"num_tokens": 55771055.0,
|
|
"step": 28505
|
|
},
|
|
{
|
|
"entropy": 6.088492012023925,
|
|
"epoch": 2.8499025341130606,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00041962356688872817,
|
|
"loss": 5.6324,
|
|
"mean_token_accuracy": 0.1801241621375084,
|
|
"num_tokens": 55780625.0,
|
|
"step": 28510
|
|
},
|
|
{
|
|
"entropy": 6.000034141540527,
|
|
"epoch": 2.850402359174289,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004195962251463417,
|
|
"loss": 5.6223,
|
|
"mean_token_accuracy": 0.18289237469434738,
|
|
"num_tokens": 55790290.0,
|
|
"step": 28515
|
|
},
|
|
{
|
|
"entropy": 6.016279697418213,
|
|
"epoch": 2.8509021842355176,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004195688797659513,
|
|
"loss": 5.6452,
|
|
"mean_token_accuracy": 0.18004991710186005,
|
|
"num_tokens": 55800407.0,
|
|
"step": 28520
|
|
},
|
|
{
|
|
"entropy": 6.070173120498657,
|
|
"epoch": 2.8514020092967463,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00041954153074824516,
|
|
"loss": 5.7231,
|
|
"mean_token_accuracy": 0.17359387874603271,
|
|
"num_tokens": 55810205.0,
|
|
"step": 28525
|
|
},
|
|
{
|
|
"entropy": 5.987732934951782,
|
|
"epoch": 2.8519018343579745,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004195141780939113,
|
|
"loss": 5.5645,
|
|
"mean_token_accuracy": 0.1840199589729309,
|
|
"num_tokens": 55820115.0,
|
|
"step": 28530
|
|
},
|
|
{
|
|
"entropy": 5.977353143692016,
|
|
"epoch": 2.852401659419203,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00041948682180363784,
|
|
"loss": 5.58,
|
|
"mean_token_accuracy": 0.18548913896083832,
|
|
"num_tokens": 55829620.0,
|
|
"step": 28535
|
|
},
|
|
{
|
|
"entropy": 5.989503622055054,
|
|
"epoch": 2.852901484480432,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004194594618781132,
|
|
"loss": 5.5688,
|
|
"mean_token_accuracy": 0.17937367558479309,
|
|
"num_tokens": 55839945.0,
|
|
"step": 28540
|
|
},
|
|
{
|
|
"entropy": 5.895614194869995,
|
|
"epoch": 2.8534013095416606,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.00041943209831802567,
|
|
"loss": 5.4569,
|
|
"mean_token_accuracy": 0.18974122703075408,
|
|
"num_tokens": 55850276.0,
|
|
"step": 28545
|
|
},
|
|
{
|
|
"entropy": 6.101979207992554,
|
|
"epoch": 2.853901134602889,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00041940473112406365,
|
|
"loss": 5.5569,
|
|
"mean_token_accuracy": 0.1878917396068573,
|
|
"num_tokens": 55859898.0,
|
|
"step": 28550
|
|
},
|
|
{
|
|
"entropy": 6.001931190490723,
|
|
"epoch": 2.8544009596641176,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00041937736029691575,
|
|
"loss": 5.5161,
|
|
"mean_token_accuracy": 0.18712717294692993,
|
|
"num_tokens": 55869339.0,
|
|
"step": 28555
|
|
},
|
|
{
|
|
"entropy": 5.9607631206512455,
|
|
"epoch": 2.8549007847253463,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004193499858372706,
|
|
"loss": 5.62,
|
|
"mean_token_accuracy": 0.18316590934991836,
|
|
"num_tokens": 55880161.0,
|
|
"step": 28560
|
|
},
|
|
{
|
|
"entropy": 6.030162382125854,
|
|
"epoch": 2.8554006097865745,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000419322607745817,
|
|
"loss": 5.6397,
|
|
"mean_token_accuracy": 0.18233606666326524,
|
|
"num_tokens": 55889522.0,
|
|
"step": 28565
|
|
},
|
|
{
|
|
"entropy": 6.071934413909912,
|
|
"epoch": 2.855900434847803,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00041929522602324377,
|
|
"loss": 5.683,
|
|
"mean_token_accuracy": 0.17448124885559083,
|
|
"num_tokens": 55899253.0,
|
|
"step": 28570
|
|
},
|
|
{
|
|
"entropy": 5.999889850616455,
|
|
"epoch": 2.856400259909032,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004192678406702398,
|
|
"loss": 5.5272,
|
|
"mean_token_accuracy": 0.18697894662618636,
|
|
"num_tokens": 55908385.0,
|
|
"step": 28575
|
|
},
|
|
{
|
|
"entropy": 5.984980201721191,
|
|
"epoch": 2.8569000849702606,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.000419240451687494,
|
|
"loss": 5.5806,
|
|
"mean_token_accuracy": 0.18568631261587143,
|
|
"num_tokens": 55917171.0,
|
|
"step": 28580
|
|
},
|
|
{
|
|
"entropy": 6.010468339920044,
|
|
"epoch": 2.857399910031489,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00041921305907569555,
|
|
"loss": 5.636,
|
|
"mean_token_accuracy": 0.18143174946308135,
|
|
"num_tokens": 55926839.0,
|
|
"step": 28585
|
|
},
|
|
{
|
|
"entropy": 6.025142669677734,
|
|
"epoch": 2.8578997350927176,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004191856628355337,
|
|
"loss": 5.6651,
|
|
"mean_token_accuracy": 0.17897681295871734,
|
|
"num_tokens": 55936850.0,
|
|
"step": 28590
|
|
},
|
|
{
|
|
"entropy": 6.040089273452759,
|
|
"epoch": 2.8583995601539463,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004191582629676977,
|
|
"loss": 5.7122,
|
|
"mean_token_accuracy": 0.16876224428415298,
|
|
"num_tokens": 55947242.0,
|
|
"step": 28595
|
|
},
|
|
{
|
|
"entropy": 6.129884147644043,
|
|
"epoch": 2.8588993852151745,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00041913085947287675,
|
|
"loss": 5.6383,
|
|
"mean_token_accuracy": 0.17821415960788728,
|
|
"num_tokens": 55957150.0,
|
|
"step": 28600
|
|
},
|
|
{
|
|
"entropy": 6.007491874694824,
|
|
"epoch": 2.859399210276403,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004191034523517606,
|
|
"loss": 5.6261,
|
|
"mean_token_accuracy": 0.17924347072839736,
|
|
"num_tokens": 55966769.0,
|
|
"step": 28605
|
|
},
|
|
{
|
|
"entropy": 5.966547679901123,
|
|
"epoch": 2.859899035337632,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00041907604160503864,
|
|
"loss": 5.5182,
|
|
"mean_token_accuracy": 0.19396236538887024,
|
|
"num_tokens": 55976536.0,
|
|
"step": 28610
|
|
},
|
|
{
|
|
"entropy": 5.927217960357666,
|
|
"epoch": 2.8603988603988606,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00041904862723340046,
|
|
"loss": 5.4805,
|
|
"mean_token_accuracy": 0.1882716566324234,
|
|
"num_tokens": 55986607.0,
|
|
"step": 28615
|
|
},
|
|
{
|
|
"entropy": 6.040523529052734,
|
|
"epoch": 2.860898685460089,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00041902120923753593,
|
|
"loss": 5.6509,
|
|
"mean_token_accuracy": 0.18247703909873964,
|
|
"num_tokens": 55995767.0,
|
|
"step": 28620
|
|
},
|
|
{
|
|
"entropy": 6.079926919937134,
|
|
"epoch": 2.8613985105213176,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004189937876181349,
|
|
"loss": 5.7165,
|
|
"mean_token_accuracy": 0.17383841276168824,
|
|
"num_tokens": 56005602.0,
|
|
"step": 28625
|
|
},
|
|
{
|
|
"entropy": 6.017708158493042,
|
|
"epoch": 2.8618983355825462,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004189663623758872,
|
|
"loss": 5.5931,
|
|
"mean_token_accuracy": 0.18587300032377244,
|
|
"num_tokens": 56014991.0,
|
|
"step": 28630
|
|
},
|
|
{
|
|
"entropy": 6.102934885025024,
|
|
"epoch": 2.8623981606437745,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00041893893351148284,
|
|
"loss": 5.6652,
|
|
"mean_token_accuracy": 0.17641374617815017,
|
|
"num_tokens": 56023486.0,
|
|
"step": 28635
|
|
},
|
|
{
|
|
"entropy": 6.022071695327758,
|
|
"epoch": 2.862897985705003,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000418911501025612,
|
|
"loss": 5.7109,
|
|
"mean_token_accuracy": 0.17827905863523483,
|
|
"num_tokens": 56034017.0,
|
|
"step": 28640
|
|
},
|
|
{
|
|
"entropy": 6.0576972484588625,
|
|
"epoch": 2.863397810766232,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004188840649189648,
|
|
"loss": 5.6677,
|
|
"mean_token_accuracy": 0.17528716176748277,
|
|
"num_tokens": 56043433.0,
|
|
"step": 28645
|
|
},
|
|
{
|
|
"entropy": 6.023940753936768,
|
|
"epoch": 2.8638976358274606,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00041885662519223154,
|
|
"loss": 5.5713,
|
|
"mean_token_accuracy": 0.1844679057598114,
|
|
"num_tokens": 56053116.0,
|
|
"step": 28650
|
|
},
|
|
{
|
|
"entropy": 5.972518539428711,
|
|
"epoch": 2.864397460888689,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004188291818461026,
|
|
"loss": 5.559,
|
|
"mean_token_accuracy": 0.18608012795448303,
|
|
"num_tokens": 56063728.0,
|
|
"step": 28655
|
|
},
|
|
{
|
|
"entropy": 5.982802009582519,
|
|
"epoch": 2.8648972859499175,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00041880173488126847,
|
|
"loss": 5.5738,
|
|
"mean_token_accuracy": 0.18519942760467528,
|
|
"num_tokens": 56072987.0,
|
|
"step": 28660
|
|
},
|
|
{
|
|
"entropy": 6.014527654647827,
|
|
"epoch": 2.8653971110111462,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00041877428429841967,
|
|
"loss": 5.5599,
|
|
"mean_token_accuracy": 0.18826552033424376,
|
|
"num_tokens": 56082819.0,
|
|
"step": 28665
|
|
},
|
|
{
|
|
"entropy": 6.056998252868652,
|
|
"epoch": 2.8658969360723745,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004187468300982469,
|
|
"loss": 5.7528,
|
|
"mean_token_accuracy": 0.1725439116358757,
|
|
"num_tokens": 56094104.0,
|
|
"step": 28670
|
|
},
|
|
{
|
|
"entropy": 5.985310840606689,
|
|
"epoch": 2.866396761133603,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004187193722814409,
|
|
"loss": 5.5841,
|
|
"mean_token_accuracy": 0.1871058985590935,
|
|
"num_tokens": 56103595.0,
|
|
"step": 28675
|
|
},
|
|
{
|
|
"entropy": 6.0340879440307615,
|
|
"epoch": 2.866896586194832,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004186919108486925,
|
|
"loss": 5.6638,
|
|
"mean_token_accuracy": 0.17626270800828933,
|
|
"num_tokens": 56113458.0,
|
|
"step": 28680
|
|
},
|
|
{
|
|
"entropy": 6.036566591262817,
|
|
"epoch": 2.8673964112560606,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004186644458006925,
|
|
"loss": 5.6348,
|
|
"mean_token_accuracy": 0.1797400787472725,
|
|
"num_tokens": 56123694.0,
|
|
"step": 28685
|
|
},
|
|
{
|
|
"entropy": 5.972597694396972,
|
|
"epoch": 2.867896236317289,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.000418636977138132,
|
|
"loss": 5.5448,
|
|
"mean_token_accuracy": 0.19198350608348846,
|
|
"num_tokens": 56132392.0,
|
|
"step": 28690
|
|
},
|
|
{
|
|
"entropy": 5.982212352752685,
|
|
"epoch": 2.8683960613785175,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00041860950486170227,
|
|
"loss": 5.6176,
|
|
"mean_token_accuracy": 0.179642890393734,
|
|
"num_tokens": 56141175.0,
|
|
"step": 28695
|
|
},
|
|
{
|
|
"entropy": 5.99999098777771,
|
|
"epoch": 2.8688958864397462,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004185820289720942,
|
|
"loss": 5.6379,
|
|
"mean_token_accuracy": 0.17354786098003389,
|
|
"num_tokens": 56151089.0,
|
|
"step": 28700
|
|
},
|
|
{
|
|
"entropy": 5.967705821990966,
|
|
"epoch": 2.8693957115009745,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00041855454946999925,
|
|
"loss": 5.5124,
|
|
"mean_token_accuracy": 0.19272801876068116,
|
|
"num_tokens": 56160800.0,
|
|
"step": 28705
|
|
},
|
|
{
|
|
"entropy": 5.974580335617065,
|
|
"epoch": 2.869895536562203,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00041852706635610884,
|
|
"loss": 5.5804,
|
|
"mean_token_accuracy": 0.18620118051767348,
|
|
"num_tokens": 56171385.0,
|
|
"step": 28710
|
|
},
|
|
{
|
|
"entropy": 5.9280797958374025,
|
|
"epoch": 2.870395361623432,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00041849957963111434,
|
|
"loss": 5.5236,
|
|
"mean_token_accuracy": 0.1911383807659149,
|
|
"num_tokens": 56181187.0,
|
|
"step": 28715
|
|
},
|
|
{
|
|
"entropy": 5.9684844493865965,
|
|
"epoch": 2.8708951866846606,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004184720892957073,
|
|
"loss": 5.5264,
|
|
"mean_token_accuracy": 0.1917385384440422,
|
|
"num_tokens": 56189478.0,
|
|
"step": 28720
|
|
},
|
|
{
|
|
"entropy": 6.008992290496826,
|
|
"epoch": 2.871395011745889,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004184445953505795,
|
|
"loss": 5.6396,
|
|
"mean_token_accuracy": 0.18223694413900376,
|
|
"num_tokens": 56198809.0,
|
|
"step": 28725
|
|
},
|
|
{
|
|
"entropy": 5.954725074768066,
|
|
"epoch": 2.8718948368071175,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004184170977964225,
|
|
"loss": 5.558,
|
|
"mean_token_accuracy": 0.18457405865192414,
|
|
"num_tokens": 56208826.0,
|
|
"step": 28730
|
|
},
|
|
{
|
|
"entropy": 6.033171796798706,
|
|
"epoch": 2.8723946618683462,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00041838959663392827,
|
|
"loss": 5.5953,
|
|
"mean_token_accuracy": 0.18147780150175094,
|
|
"num_tokens": 56217811.0,
|
|
"step": 28735
|
|
},
|
|
{
|
|
"entropy": 5.990016984939575,
|
|
"epoch": 2.8728944869295745,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004183620918637887,
|
|
"loss": 5.563,
|
|
"mean_token_accuracy": 0.18483150154352188,
|
|
"num_tokens": 56226624.0,
|
|
"step": 28740
|
|
},
|
|
{
|
|
"entropy": 5.9216875553131105,
|
|
"epoch": 2.873394311990803,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004183345834866957,
|
|
"loss": 5.5192,
|
|
"mean_token_accuracy": 0.1887126848101616,
|
|
"num_tokens": 56235829.0,
|
|
"step": 28745
|
|
},
|
|
{
|
|
"entropy": 5.97251148223877,
|
|
"epoch": 2.873894137052032,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00041830707150334164,
|
|
"loss": 5.5795,
|
|
"mean_token_accuracy": 0.18436657637357712,
|
|
"num_tokens": 56245387.0,
|
|
"step": 28750
|
|
},
|
|
{
|
|
"entropy": 6.002174997329712,
|
|
"epoch": 2.8743939621132606,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004182795559144184,
|
|
"loss": 5.631,
|
|
"mean_token_accuracy": 0.1804027184844017,
|
|
"num_tokens": 56254936.0,
|
|
"step": 28755
|
|
},
|
|
{
|
|
"entropy": 6.11781153678894,
|
|
"epoch": 2.874893787174489,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004182520367206184,
|
|
"loss": 5.7323,
|
|
"mean_token_accuracy": 0.17619536370038985,
|
|
"num_tokens": 56265070.0,
|
|
"step": 28760
|
|
},
|
|
{
|
|
"entropy": 5.963392877578736,
|
|
"epoch": 2.8753936122357175,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00041822451392263413,
|
|
"loss": 5.5197,
|
|
"mean_token_accuracy": 0.19000029414892197,
|
|
"num_tokens": 56274602.0,
|
|
"step": 28765
|
|
},
|
|
{
|
|
"entropy": 5.966036128997803,
|
|
"epoch": 2.875893437296946,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004181969875211578,
|
|
"loss": 5.6056,
|
|
"mean_token_accuracy": 0.18173538893461227,
|
|
"num_tokens": 56284078.0,
|
|
"step": 28770
|
|
},
|
|
{
|
|
"entropy": 5.957304668426514,
|
|
"epoch": 2.8763932623581745,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00041816945751688215,
|
|
"loss": 5.5598,
|
|
"mean_token_accuracy": 0.18457468152046203,
|
|
"num_tokens": 56295132.0,
|
|
"step": 28775
|
|
},
|
|
{
|
|
"entropy": 5.9564306259155275,
|
|
"epoch": 2.876893087419403,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00041814192391049983,
|
|
"loss": 5.5391,
|
|
"mean_token_accuracy": 0.20150987505912782,
|
|
"num_tokens": 56305156.0,
|
|
"step": 28780
|
|
},
|
|
{
|
|
"entropy": 6.050829458236694,
|
|
"epoch": 2.877392912480632,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004181143867027036,
|
|
"loss": 5.7111,
|
|
"mean_token_accuracy": 0.17604059725999832,
|
|
"num_tokens": 56314272.0,
|
|
"step": 28785
|
|
},
|
|
{
|
|
"entropy": 5.9643134593963625,
|
|
"epoch": 2.8778927375418606,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00041808684589418615,
|
|
"loss": 5.6359,
|
|
"mean_token_accuracy": 0.18246766030788422,
|
|
"num_tokens": 56325184.0,
|
|
"step": 28790
|
|
},
|
|
{
|
|
"entropy": 5.9738422393798825,
|
|
"epoch": 2.878392562603089,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004180593014856404,
|
|
"loss": 5.5498,
|
|
"mean_token_accuracy": 0.18286344408988953,
|
|
"num_tokens": 56335288.0,
|
|
"step": 28795
|
|
},
|
|
{
|
|
"entropy": 5.937062692642212,
|
|
"epoch": 2.8788923876643175,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004180317534777596,
|
|
"loss": 5.5413,
|
|
"mean_token_accuracy": 0.18790563493967055,
|
|
"num_tokens": 56344038.0,
|
|
"step": 28800
|
|
},
|
|
{
|
|
"entropy": 6.010318326950073,
|
|
"epoch": 2.879392212725546,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00041800420187123656,
|
|
"loss": 5.7334,
|
|
"mean_token_accuracy": 0.17603045105934143,
|
|
"num_tokens": 56355120.0,
|
|
"step": 28805
|
|
},
|
|
{
|
|
"entropy": 6.016832590103149,
|
|
"epoch": 2.8798920377867745,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004179766466667646,
|
|
"loss": 5.5614,
|
|
"mean_token_accuracy": 0.1855492353439331,
|
|
"num_tokens": 56364398.0,
|
|
"step": 28810
|
|
},
|
|
{
|
|
"entropy": 5.958179759979248,
|
|
"epoch": 2.880391862848003,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004179490878650371,
|
|
"loss": 5.5192,
|
|
"mean_token_accuracy": 0.19540375769138335,
|
|
"num_tokens": 56373988.0,
|
|
"step": 28815
|
|
},
|
|
{
|
|
"entropy": 6.008880996704102,
|
|
"epoch": 2.880891687909232,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004179215254667473,
|
|
"loss": 5.664,
|
|
"mean_token_accuracy": 0.17421995401382445,
|
|
"num_tokens": 56383398.0,
|
|
"step": 28820
|
|
},
|
|
{
|
|
"entropy": 6.081080341339112,
|
|
"epoch": 2.8813915129704606,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004178939594725887,
|
|
"loss": 5.6845,
|
|
"mean_token_accuracy": 0.1712057486176491,
|
|
"num_tokens": 56392679.0,
|
|
"step": 28825
|
|
},
|
|
{
|
|
"entropy": 6.0435058116912845,
|
|
"epoch": 2.881891338031689,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004178663898832548,
|
|
"loss": 5.6311,
|
|
"mean_token_accuracy": 0.17528256326913833,
|
|
"num_tokens": 56402812.0,
|
|
"step": 28830
|
|
},
|
|
{
|
|
"entropy": 5.998792886734009,
|
|
"epoch": 2.8823911630929175,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004178388166994392,
|
|
"loss": 5.6125,
|
|
"mean_token_accuracy": 0.17749225795269014,
|
|
"num_tokens": 56412799.0,
|
|
"step": 28835
|
|
},
|
|
{
|
|
"entropy": 6.004590654373169,
|
|
"epoch": 2.882890988154146,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004178112399218359,
|
|
"loss": 5.5424,
|
|
"mean_token_accuracy": 0.18602584749460221,
|
|
"num_tokens": 56422200.0,
|
|
"step": 28840
|
|
},
|
|
{
|
|
"entropy": 6.003469371795655,
|
|
"epoch": 2.8833908132153745,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00041778365955113844,
|
|
"loss": 5.4954,
|
|
"mean_token_accuracy": 0.18976576030254363,
|
|
"num_tokens": 56432466.0,
|
|
"step": 28845
|
|
},
|
|
{
|
|
"entropy": 5.964813470840454,
|
|
"epoch": 2.883890638276603,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004177560755880409,
|
|
"loss": 5.5449,
|
|
"mean_token_accuracy": 0.1820091724395752,
|
|
"num_tokens": 56442139.0,
|
|
"step": 28850
|
|
},
|
|
{
|
|
"entropy": 5.824852991104126,
|
|
"epoch": 2.884390463337832,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004177284880332373,
|
|
"loss": 5.5064,
|
|
"mean_token_accuracy": 0.18769243657588958,
|
|
"num_tokens": 56452509.0,
|
|
"step": 28855
|
|
},
|
|
{
|
|
"entropy": 5.945426607131958,
|
|
"epoch": 2.8848902883990606,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00041770089688742155,
|
|
"loss": 5.51,
|
|
"mean_token_accuracy": 0.1844404697418213,
|
|
"num_tokens": 56462135.0,
|
|
"step": 28860
|
|
},
|
|
{
|
|
"entropy": 5.957814121246338,
|
|
"epoch": 2.885390113460289,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.000417673302151288,
|
|
"loss": 5.4752,
|
|
"mean_token_accuracy": 0.19335409253835678,
|
|
"num_tokens": 56471544.0,
|
|
"step": 28865
|
|
},
|
|
{
|
|
"entropy": 6.06758484840393,
|
|
"epoch": 2.8858899385215175,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004176457038255309,
|
|
"loss": 5.6542,
|
|
"mean_token_accuracy": 0.1839800387620926,
|
|
"num_tokens": 56481293.0,
|
|
"step": 28870
|
|
},
|
|
{
|
|
"entropy": 5.9632213592529295,
|
|
"epoch": 2.886389763582746,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004176181019108446,
|
|
"loss": 5.5731,
|
|
"mean_token_accuracy": 0.18092337399721145,
|
|
"num_tokens": 56490265.0,
|
|
"step": 28875
|
|
},
|
|
{
|
|
"entropy": 5.934902667999268,
|
|
"epoch": 2.8868895886439745,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004175904964079236,
|
|
"loss": 5.4881,
|
|
"mean_token_accuracy": 0.18967539668083191,
|
|
"num_tokens": 56499617.0,
|
|
"step": 28880
|
|
},
|
|
{
|
|
"entropy": 5.95713062286377,
|
|
"epoch": 2.887389413705203,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004175628873174623,
|
|
"loss": 5.543,
|
|
"mean_token_accuracy": 0.19042887389659882,
|
|
"num_tokens": 56509962.0,
|
|
"step": 28885
|
|
},
|
|
{
|
|
"entropy": 6.009275817871094,
|
|
"epoch": 2.887889238766432,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00041753527464015547,
|
|
"loss": 5.6304,
|
|
"mean_token_accuracy": 0.17678735107183458,
|
|
"num_tokens": 56519786.0,
|
|
"step": 28890
|
|
},
|
|
{
|
|
"entropy": 5.965920877456665,
|
|
"epoch": 2.8883890638276606,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004175076583766978,
|
|
"loss": 5.5998,
|
|
"mean_token_accuracy": 0.1770608127117157,
|
|
"num_tokens": 56528675.0,
|
|
"step": 28895
|
|
},
|
|
{
|
|
"entropy": 6.074101066589355,
|
|
"epoch": 2.888888888888889,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004174800385277842,
|
|
"loss": 5.6667,
|
|
"mean_token_accuracy": 0.17467039376497268,
|
|
"num_tokens": 56538783.0,
|
|
"step": 28900
|
|
},
|
|
{
|
|
"entropy": 6.053297758102417,
|
|
"epoch": 2.8893887139501175,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004174524150941094,
|
|
"loss": 5.7057,
|
|
"mean_token_accuracy": 0.17468495965003966,
|
|
"num_tokens": 56549063.0,
|
|
"step": 28905
|
|
},
|
|
{
|
|
"entropy": 6.0137248039245605,
|
|
"epoch": 2.889888539011346,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004174247880763685,
|
|
"loss": 5.5775,
|
|
"mean_token_accuracy": 0.18393174409866334,
|
|
"num_tokens": 56558414.0,
|
|
"step": 28910
|
|
},
|
|
{
|
|
"entropy": 5.9983659267425535,
|
|
"epoch": 2.8903883640725745,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004173971574752566,
|
|
"loss": 5.6393,
|
|
"mean_token_accuracy": 0.18259720802307128,
|
|
"num_tokens": 56568493.0,
|
|
"step": 28915
|
|
},
|
|
{
|
|
"entropy": 6.020189237594605,
|
|
"epoch": 2.890888189133803,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004173695232914688,
|
|
"loss": 5.6548,
|
|
"mean_token_accuracy": 0.1697910338640213,
|
|
"num_tokens": 56578832.0,
|
|
"step": 28920
|
|
},
|
|
{
|
|
"entropy": 6.034400796890258,
|
|
"epoch": 2.891388014195032,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004173418855257005,
|
|
"loss": 5.6085,
|
|
"mean_token_accuracy": 0.18130335807800294,
|
|
"num_tokens": 56587707.0,
|
|
"step": 28925
|
|
},
|
|
{
|
|
"entropy": 5.961549425125122,
|
|
"epoch": 2.8918878392562606,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000417314244178647,
|
|
"loss": 5.5543,
|
|
"mean_token_accuracy": 0.18679014295339585,
|
|
"num_tokens": 56597145.0,
|
|
"step": 28930
|
|
},
|
|
{
|
|
"entropy": 5.95048770904541,
|
|
"epoch": 2.892387664317489,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004172865992510037,
|
|
"loss": 5.5691,
|
|
"mean_token_accuracy": 0.18465525060892105,
|
|
"num_tokens": 56607148.0,
|
|
"step": 28935
|
|
},
|
|
{
|
|
"entropy": 5.944522762298584,
|
|
"epoch": 2.8928874893787175,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.00041725895074346615,
|
|
"loss": 5.5554,
|
|
"mean_token_accuracy": 0.18466101288795472,
|
|
"num_tokens": 56616574.0,
|
|
"step": 28940
|
|
},
|
|
{
|
|
"entropy": 6.009114980697632,
|
|
"epoch": 2.893387314439946,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004172312986567301,
|
|
"loss": 5.5951,
|
|
"mean_token_accuracy": 0.1854513943195343,
|
|
"num_tokens": 56625986.0,
|
|
"step": 28945
|
|
},
|
|
{
|
|
"entropy": 5.944673538208008,
|
|
"epoch": 2.8938871395011745,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004172036429914911,
|
|
"loss": 5.5743,
|
|
"mean_token_accuracy": 0.1856213852763176,
|
|
"num_tokens": 56634524.0,
|
|
"step": 28950
|
|
},
|
|
{
|
|
"entropy": 6.017916822433472,
|
|
"epoch": 2.894386964562403,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00041717598374844505,
|
|
"loss": 5.5913,
|
|
"mean_token_accuracy": 0.17742492407560348,
|
|
"num_tokens": 56643770.0,
|
|
"step": 28955
|
|
},
|
|
{
|
|
"entropy": 5.9466320991516115,
|
|
"epoch": 2.894886789623632,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00041714832092828785,
|
|
"loss": 5.5451,
|
|
"mean_token_accuracy": 0.19413947761058808,
|
|
"num_tokens": 56654339.0,
|
|
"step": 28960
|
|
},
|
|
{
|
|
"entropy": 5.960594511032104,
|
|
"epoch": 2.89538661468486,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00041712065453171544,
|
|
"loss": 5.5117,
|
|
"mean_token_accuracy": 0.18419922292232513,
|
|
"num_tokens": 56664814.0,
|
|
"step": 28965
|
|
},
|
|
{
|
|
"entropy": 5.999015045166016,
|
|
"epoch": 2.895886439746089,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00041709298455942394,
|
|
"loss": 5.6497,
|
|
"mean_token_accuracy": 0.18097376227378845,
|
|
"num_tokens": 56674602.0,
|
|
"step": 28970
|
|
},
|
|
{
|
|
"entropy": 5.907823610305786,
|
|
"epoch": 2.8963862648073175,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00041706531101210956,
|
|
"loss": 5.5811,
|
|
"mean_token_accuracy": 0.19052610248327256,
|
|
"num_tokens": 56684294.0,
|
|
"step": 28975
|
|
},
|
|
{
|
|
"entropy": 6.011510944366455,
|
|
"epoch": 2.896886089868546,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00041703763389046853,
|
|
"loss": 5.6724,
|
|
"mean_token_accuracy": 0.18081312328577043,
|
|
"num_tokens": 56693626.0,
|
|
"step": 28980
|
|
},
|
|
{
|
|
"entropy": 6.071752452850342,
|
|
"epoch": 2.8973859149297745,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00041700995319519707,
|
|
"loss": 5.6259,
|
|
"mean_token_accuracy": 0.1762305423617363,
|
|
"num_tokens": 56704574.0,
|
|
"step": 28985
|
|
},
|
|
{
|
|
"entropy": 5.959652280807495,
|
|
"epoch": 2.897885739991003,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004169822689269918,
|
|
"loss": 5.5392,
|
|
"mean_token_accuracy": 0.19037200659513473,
|
|
"num_tokens": 56714990.0,
|
|
"step": 28990
|
|
},
|
|
{
|
|
"entropy": 5.979641723632812,
|
|
"epoch": 2.898385565052232,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00041695458108654914,
|
|
"loss": 5.6292,
|
|
"mean_token_accuracy": 0.18183283358812333,
|
|
"num_tokens": 56724651.0,
|
|
"step": 28995
|
|
},
|
|
{
|
|
"entropy": 5.964604187011719,
|
|
"epoch": 2.89888539011346,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00041692688967456576,
|
|
"loss": 5.5348,
|
|
"mean_token_accuracy": 0.18678184896707534,
|
|
"num_tokens": 56733500.0,
|
|
"step": 29000
|
|
},
|
|
{
|
|
"entropy": 6.030916500091553,
|
|
"epoch": 2.899385215174689,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00041689919469173835,
|
|
"loss": 5.6992,
|
|
"mean_token_accuracy": 0.18174281418323518,
|
|
"num_tokens": 56743010.0,
|
|
"step": 29005
|
|
},
|
|
{
|
|
"entropy": 6.036991167068481,
|
|
"epoch": 2.8998850402359175,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004168714961387637,
|
|
"loss": 5.6469,
|
|
"mean_token_accuracy": 0.18197005689144136,
|
|
"num_tokens": 56753441.0,
|
|
"step": 29010
|
|
},
|
|
{
|
|
"entropy": 6.04302749633789,
|
|
"epoch": 2.900384865297146,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004168437940163388,
|
|
"loss": 5.6625,
|
|
"mean_token_accuracy": 0.18107815086841583,
|
|
"num_tokens": 56762767.0,
|
|
"step": 29015
|
|
},
|
|
{
|
|
"entropy": 6.055582714080811,
|
|
"epoch": 2.9008846903583745,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004168160883251605,
|
|
"loss": 5.6598,
|
|
"mean_token_accuracy": 0.18369342237710953,
|
|
"num_tokens": 56772354.0,
|
|
"step": 29020
|
|
},
|
|
{
|
|
"entropy": 6.047346544265747,
|
|
"epoch": 2.901384515419603,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00041678837906592586,
|
|
"loss": 5.5775,
|
|
"mean_token_accuracy": 0.1803925096988678,
|
|
"num_tokens": 56782453.0,
|
|
"step": 29025
|
|
},
|
|
{
|
|
"entropy": 5.986154937744141,
|
|
"epoch": 2.901884340480832,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00041676066623933216,
|
|
"loss": 5.6722,
|
|
"mean_token_accuracy": 0.17766814380884172,
|
|
"num_tokens": 56792762.0,
|
|
"step": 29030
|
|
},
|
|
{
|
|
"entropy": 5.980810880661011,
|
|
"epoch": 2.90238416554206,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004167329498460766,
|
|
"loss": 5.5671,
|
|
"mean_token_accuracy": 0.18698561936616898,
|
|
"num_tokens": 56802160.0,
|
|
"step": 29035
|
|
},
|
|
{
|
|
"entropy": 5.981358575820923,
|
|
"epoch": 2.902883990603289,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00041670522988685637,
|
|
"loss": 5.5518,
|
|
"mean_token_accuracy": 0.1824916645884514,
|
|
"num_tokens": 56811691.0,
|
|
"step": 29040
|
|
},
|
|
{
|
|
"entropy": 6.01159815788269,
|
|
"epoch": 2.9033838156645175,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00041667750636236914,
|
|
"loss": 5.5684,
|
|
"mean_token_accuracy": 0.1876875638961792,
|
|
"num_tokens": 56821721.0,
|
|
"step": 29045
|
|
},
|
|
{
|
|
"entropy": 5.814236879348755,
|
|
"epoch": 2.903883640725746,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004166497792733122,
|
|
"loss": 5.3528,
|
|
"mean_token_accuracy": 0.21039293110370635,
|
|
"num_tokens": 56832463.0,
|
|
"step": 29050
|
|
},
|
|
{
|
|
"entropy": 6.014954423904419,
|
|
"epoch": 2.9043834657869745,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004166220486203834,
|
|
"loss": 5.6844,
|
|
"mean_token_accuracy": 0.17224069833755493,
|
|
"num_tokens": 56842814.0,
|
|
"step": 29055
|
|
},
|
|
{
|
|
"entropy": 6.104810476303101,
|
|
"epoch": 2.904883290848203,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004165943144042802,
|
|
"loss": 5.7037,
|
|
"mean_token_accuracy": 0.17190056294202805,
|
|
"num_tokens": 56853410.0,
|
|
"step": 29060
|
|
},
|
|
{
|
|
"entropy": 6.0175739288330075,
|
|
"epoch": 2.905383115909432,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00041656657662570047,
|
|
"loss": 5.5929,
|
|
"mean_token_accuracy": 0.1842205673456192,
|
|
"num_tokens": 56864264.0,
|
|
"step": 29065
|
|
},
|
|
{
|
|
"entropy": 6.038772630691528,
|
|
"epoch": 2.90588294097066,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004165388352853421,
|
|
"loss": 5.6216,
|
|
"mean_token_accuracy": 0.18193963617086412,
|
|
"num_tokens": 56873275.0,
|
|
"step": 29070
|
|
},
|
|
{
|
|
"entropy": 6.006763362884522,
|
|
"epoch": 2.906382766031889,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00041651109038390305,
|
|
"loss": 5.5362,
|
|
"mean_token_accuracy": 0.19775369465351106,
|
|
"num_tokens": 56882700.0,
|
|
"step": 29075
|
|
},
|
|
{
|
|
"entropy": 6.053705453872681,
|
|
"epoch": 2.9068825910931175,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00041648334192208146,
|
|
"loss": 5.6515,
|
|
"mean_token_accuracy": 0.17018372118473052,
|
|
"num_tokens": 56892836.0,
|
|
"step": 29080
|
|
},
|
|
{
|
|
"entropy": 5.983827114105225,
|
|
"epoch": 2.907382416154346,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00041645558990057536,
|
|
"loss": 5.5762,
|
|
"mean_token_accuracy": 0.19066125005483628,
|
|
"num_tokens": 56904337.0,
|
|
"step": 29085
|
|
},
|
|
{
|
|
"entropy": 5.933207368850708,
|
|
"epoch": 2.9078822412155745,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.00041642783432008294,
|
|
"loss": 5.5303,
|
|
"mean_token_accuracy": 0.18336802423000337,
|
|
"num_tokens": 56914296.0,
|
|
"step": 29090
|
|
},
|
|
{
|
|
"entropy": 5.998925304412841,
|
|
"epoch": 2.908382066276803,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00041640007518130274,
|
|
"loss": 5.5788,
|
|
"mean_token_accuracy": 0.18004709035158156,
|
|
"num_tokens": 56924528.0,
|
|
"step": 29095
|
|
},
|
|
{
|
|
"entropy": 6.04989767074585,
|
|
"epoch": 2.908881891338032,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000416372312484933,
|
|
"loss": 5.5832,
|
|
"mean_token_accuracy": 0.19144247174263002,
|
|
"num_tokens": 56934585.0,
|
|
"step": 29100
|
|
},
|
|
{
|
|
"entropy": 6.009792137145996,
|
|
"epoch": 2.90938171639926,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00041634454623167217,
|
|
"loss": 5.6316,
|
|
"mean_token_accuracy": 0.18979420214891435,
|
|
"num_tokens": 56944551.0,
|
|
"step": 29105
|
|
},
|
|
{
|
|
"entropy": 5.989292764663697,
|
|
"epoch": 2.909881541460489,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00041631677642221896,
|
|
"loss": 5.6124,
|
|
"mean_token_accuracy": 0.17896495014429092,
|
|
"num_tokens": 56953120.0,
|
|
"step": 29110
|
|
},
|
|
{
|
|
"entropy": 6.01397123336792,
|
|
"epoch": 2.9103813665217175,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000416289003057272,
|
|
"loss": 5.5835,
|
|
"mean_token_accuracy": 0.1853387326002121,
|
|
"num_tokens": 56963747.0,
|
|
"step": 29115
|
|
},
|
|
{
|
|
"entropy": 5.984549713134766,
|
|
"epoch": 2.910881191582946,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004162612261375302,
|
|
"loss": 5.6066,
|
|
"mean_token_accuracy": 0.18629638999700546,
|
|
"num_tokens": 56974192.0,
|
|
"step": 29120
|
|
},
|
|
{
|
|
"entropy": 6.060419750213623,
|
|
"epoch": 2.9113810166441745,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00041623344566369216,
|
|
"loss": 5.6979,
|
|
"mean_token_accuracy": 0.17154345214366912,
|
|
"num_tokens": 56984672.0,
|
|
"step": 29125
|
|
},
|
|
{
|
|
"entropy": 6.011792087554932,
|
|
"epoch": 2.911880841705403,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.000416205661636457,
|
|
"loss": 5.5821,
|
|
"mean_token_accuracy": 0.1789775714278221,
|
|
"num_tokens": 56993737.0,
|
|
"step": 29130
|
|
},
|
|
{
|
|
"entropy": 6.054802274703979,
|
|
"epoch": 2.912380666766632,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004161778740565238,
|
|
"loss": 5.6518,
|
|
"mean_token_accuracy": 0.17910155653953552,
|
|
"num_tokens": 57004253.0,
|
|
"step": 29135
|
|
},
|
|
{
|
|
"entropy": 6.005196380615234,
|
|
"epoch": 2.91288049182786,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00041615008292459157,
|
|
"loss": 5.5565,
|
|
"mean_token_accuracy": 0.18514811098575593,
|
|
"num_tokens": 57013690.0,
|
|
"step": 29140
|
|
},
|
|
{
|
|
"entropy": 5.946212720870972,
|
|
"epoch": 2.913380316889089,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00041612228824135954,
|
|
"loss": 5.4669,
|
|
"mean_token_accuracy": 0.19473315328359603,
|
|
"num_tokens": 57022702.0,
|
|
"step": 29145
|
|
},
|
|
{
|
|
"entropy": 6.020378065109253,
|
|
"epoch": 2.9138801419503175,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00041609449000752706,
|
|
"loss": 5.6506,
|
|
"mean_token_accuracy": 0.18173354119062424,
|
|
"num_tokens": 57032442.0,
|
|
"step": 29150
|
|
},
|
|
{
|
|
"entropy": 6.044873142242432,
|
|
"epoch": 2.914379967011546,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004160666882237936,
|
|
"loss": 5.5661,
|
|
"mean_token_accuracy": 0.1862018808722496,
|
|
"num_tokens": 57042284.0,
|
|
"step": 29155
|
|
},
|
|
{
|
|
"entropy": 5.957995653152466,
|
|
"epoch": 2.9148797920727745,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004160388828908585,
|
|
"loss": 5.5226,
|
|
"mean_token_accuracy": 0.18590052276849747,
|
|
"num_tokens": 57051504.0,
|
|
"step": 29160
|
|
},
|
|
{
|
|
"entropy": 5.978785514831543,
|
|
"epoch": 2.915379617134003,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00041601107400942146,
|
|
"loss": 5.5972,
|
|
"mean_token_accuracy": 0.18638526648283005,
|
|
"num_tokens": 57060717.0,
|
|
"step": 29165
|
|
},
|
|
{
|
|
"entropy": 5.951480531692505,
|
|
"epoch": 2.915879442195232,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00041598326158018197,
|
|
"loss": 5.6025,
|
|
"mean_token_accuracy": 0.18353753834962844,
|
|
"num_tokens": 57070767.0,
|
|
"step": 29170
|
|
},
|
|
{
|
|
"entropy": 5.993894100189209,
|
|
"epoch": 2.91637926725646,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00041595544560384004,
|
|
"loss": 5.5512,
|
|
"mean_token_accuracy": 0.18755939602851868,
|
|
"num_tokens": 57080922.0,
|
|
"step": 29175
|
|
},
|
|
{
|
|
"entropy": 5.916297721862793,
|
|
"epoch": 2.916879092317689,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004159276260810952,
|
|
"loss": 5.5001,
|
|
"mean_token_accuracy": 0.1891560047864914,
|
|
"num_tokens": 57090703.0,
|
|
"step": 29180
|
|
},
|
|
{
|
|
"entropy": 5.941477298736572,
|
|
"epoch": 2.9173789173789175,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00041589980301264765,
|
|
"loss": 5.584,
|
|
"mean_token_accuracy": 0.18580522239208222,
|
|
"num_tokens": 57100468.0,
|
|
"step": 29185
|
|
},
|
|
{
|
|
"entropy": 6.022137832641602,
|
|
"epoch": 2.917878742440146,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004158719763991973,
|
|
"loss": 5.5596,
|
|
"mean_token_accuracy": 0.18136871010065078,
|
|
"num_tokens": 57110281.0,
|
|
"step": 29190
|
|
},
|
|
{
|
|
"entropy": 5.986542892456055,
|
|
"epoch": 2.9183785675013745,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00041584414624144426,
|
|
"loss": 5.583,
|
|
"mean_token_accuracy": 0.18388703018426894,
|
|
"num_tokens": 57120280.0,
|
|
"step": 29195
|
|
},
|
|
{
|
|
"entropy": 5.943633270263672,
|
|
"epoch": 2.918878392562603,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004158163125400887,
|
|
"loss": 5.6066,
|
|
"mean_token_accuracy": 0.18231650590896606,
|
|
"num_tokens": 57129577.0,
|
|
"step": 29200
|
|
},
|
|
{
|
|
"entropy": 5.993096113204956,
|
|
"epoch": 2.919378217623832,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00041578847529583106,
|
|
"loss": 5.6331,
|
|
"mean_token_accuracy": 0.1776512920856476,
|
|
"num_tokens": 57139327.0,
|
|
"step": 29205
|
|
},
|
|
{
|
|
"entropy": 6.015553283691406,
|
|
"epoch": 2.91987804268506,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004157606345093715,
|
|
"loss": 5.5956,
|
|
"mean_token_accuracy": 0.1821601063013077,
|
|
"num_tokens": 57149288.0,
|
|
"step": 29210
|
|
},
|
|
{
|
|
"entropy": 6.008014583587647,
|
|
"epoch": 2.920377867746289,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004157327901814107,
|
|
"loss": 5.591,
|
|
"mean_token_accuracy": 0.17854555696249008,
|
|
"num_tokens": 57158308.0,
|
|
"step": 29215
|
|
},
|
|
{
|
|
"entropy": 5.98085126876831,
|
|
"epoch": 2.9208776928075175,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00041570494231264906,
|
|
"loss": 5.5421,
|
|
"mean_token_accuracy": 0.18362233340740203,
|
|
"num_tokens": 57167893.0,
|
|
"step": 29220
|
|
},
|
|
{
|
|
"entropy": 5.954479360580445,
|
|
"epoch": 2.9213775178687458,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00041567709090378725,
|
|
"loss": 5.5382,
|
|
"mean_token_accuracy": 0.19199252873659134,
|
|
"num_tokens": 57178489.0,
|
|
"step": 29225
|
|
},
|
|
{
|
|
"entropy": 6.028810453414917,
|
|
"epoch": 2.9218773429299745,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00041564923595552604,
|
|
"loss": 5.6024,
|
|
"mean_token_accuracy": 0.17599327713251114,
|
|
"num_tokens": 57187713.0,
|
|
"step": 29230
|
|
},
|
|
{
|
|
"entropy": 6.0018964290618895,
|
|
"epoch": 2.922377167991203,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00041562137746856625,
|
|
"loss": 5.5418,
|
|
"mean_token_accuracy": 0.17918623387813568,
|
|
"num_tokens": 57197914.0,
|
|
"step": 29235
|
|
},
|
|
{
|
|
"entropy": 5.934159803390503,
|
|
"epoch": 2.922876993052432,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00041559351544360893,
|
|
"loss": 5.565,
|
|
"mean_token_accuracy": 0.19043684601783753,
|
|
"num_tokens": 57207902.0,
|
|
"step": 29240
|
|
},
|
|
{
|
|
"entropy": 6.057322406768799,
|
|
"epoch": 2.92337681811366,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00041556564988135474,
|
|
"loss": 5.64,
|
|
"mean_token_accuracy": 0.18184490948915483,
|
|
"num_tokens": 57219000.0,
|
|
"step": 29245
|
|
},
|
|
{
|
|
"entropy": 6.018290042877197,
|
|
"epoch": 2.923876643174889,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004155377807825051,
|
|
"loss": 5.6283,
|
|
"mean_token_accuracy": 0.18322395533323288,
|
|
"num_tokens": 57228333.0,
|
|
"step": 29250
|
|
},
|
|
{
|
|
"entropy": 5.982365942001342,
|
|
"epoch": 2.9243764682361175,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000415509908147761,
|
|
"loss": 5.6187,
|
|
"mean_token_accuracy": 0.18521764129400253,
|
|
"num_tokens": 57237595.0,
|
|
"step": 29255
|
|
},
|
|
{
|
|
"entropy": 5.980288982391357,
|
|
"epoch": 2.9248762932973458,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00041548203197782377,
|
|
"loss": 5.53,
|
|
"mean_token_accuracy": 0.18970726579427719,
|
|
"num_tokens": 57246797.0,
|
|
"step": 29260
|
|
},
|
|
{
|
|
"entropy": 6.016009950637818,
|
|
"epoch": 2.9253761183585745,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00041545415227339474,
|
|
"loss": 5.6261,
|
|
"mean_token_accuracy": 0.18555885106325148,
|
|
"num_tokens": 57258685.0,
|
|
"step": 29265
|
|
},
|
|
{
|
|
"entropy": 6.0547933101654055,
|
|
"epoch": 2.925875943419803,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004154262690351754,
|
|
"loss": 5.6124,
|
|
"mean_token_accuracy": 0.18064164072275163,
|
|
"num_tokens": 57269103.0,
|
|
"step": 29270
|
|
},
|
|
{
|
|
"entropy": 6.036549663543701,
|
|
"epoch": 2.926375768481032,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004153983822638673,
|
|
"loss": 5.6788,
|
|
"mean_token_accuracy": 0.17837551832199097,
|
|
"num_tokens": 57279346.0,
|
|
"step": 29275
|
|
},
|
|
{
|
|
"entropy": 6.059149599075317,
|
|
"epoch": 2.92687559354226,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00041537049196017196,
|
|
"loss": 5.6376,
|
|
"mean_token_accuracy": 0.17875242084264756,
|
|
"num_tokens": 57289438.0,
|
|
"step": 29280
|
|
},
|
|
{
|
|
"entropy": 5.954437971115112,
|
|
"epoch": 2.927375418603489,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00041534259812479125,
|
|
"loss": 5.6405,
|
|
"mean_token_accuracy": 0.1832588031888008,
|
|
"num_tokens": 57299621.0,
|
|
"step": 29285
|
|
},
|
|
{
|
|
"entropy": 6.028519868850708,
|
|
"epoch": 2.927875243664717,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004153147007584269,
|
|
"loss": 5.5687,
|
|
"mean_token_accuracy": 0.18326803296804428,
|
|
"num_tokens": 57309043.0,
|
|
"step": 29290
|
|
},
|
|
{
|
|
"entropy": 6.032455539703369,
|
|
"epoch": 2.9283750687259458,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00041528679986178066,
|
|
"loss": 5.571,
|
|
"mean_token_accuracy": 0.1889626994729042,
|
|
"num_tokens": 57318554.0,
|
|
"step": 29295
|
|
},
|
|
{
|
|
"entropy": 5.973637485504151,
|
|
"epoch": 2.9288748937871745,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00041525889543555475,
|
|
"loss": 5.5757,
|
|
"mean_token_accuracy": 0.1905403509736061,
|
|
"num_tokens": 57327798.0,
|
|
"step": 29300
|
|
},
|
|
{
|
|
"entropy": 5.963986587524414,
|
|
"epoch": 2.929374718848403,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000415230987480451,
|
|
"loss": 5.6175,
|
|
"mean_token_accuracy": 0.18534624129533767,
|
|
"num_tokens": 57337395.0,
|
|
"step": 29305
|
|
},
|
|
{
|
|
"entropy": 6.001691389083862,
|
|
"epoch": 2.929874543909632,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004152030759971718,
|
|
"loss": 5.5773,
|
|
"mean_token_accuracy": 0.18597228676080704,
|
|
"num_tokens": 57347025.0,
|
|
"step": 29310
|
|
},
|
|
{
|
|
"entropy": 5.917685604095459,
|
|
"epoch": 2.93037436897086,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004151751609864193,
|
|
"loss": 5.432,
|
|
"mean_token_accuracy": 0.19883350133895875,
|
|
"num_tokens": 57356093.0,
|
|
"step": 29315
|
|
},
|
|
{
|
|
"entropy": 6.007935476303101,
|
|
"epoch": 2.930874194032089,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004151472424488957,
|
|
"loss": 5.5961,
|
|
"mean_token_accuracy": 0.18647719770669938,
|
|
"num_tokens": 57365852.0,
|
|
"step": 29320
|
|
},
|
|
{
|
|
"entropy": 6.0171526908874515,
|
|
"epoch": 2.931374019093317,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004151193203853036,
|
|
"loss": 5.657,
|
|
"mean_token_accuracy": 0.1745600089430809,
|
|
"num_tokens": 57375598.0,
|
|
"step": 29325
|
|
},
|
|
{
|
|
"entropy": 5.952260828018188,
|
|
"epoch": 2.9318738441545458,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00041509139479634544,
|
|
"loss": 5.5187,
|
|
"mean_token_accuracy": 0.1901157021522522,
|
|
"num_tokens": 57385533.0,
|
|
"step": 29330
|
|
},
|
|
{
|
|
"entropy": 5.988120460510254,
|
|
"epoch": 2.9323736692157745,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00041506346568272385,
|
|
"loss": 5.5796,
|
|
"mean_token_accuracy": 0.1859850123524666,
|
|
"num_tokens": 57396109.0,
|
|
"step": 29335
|
|
},
|
|
{
|
|
"entropy": 6.1073356628417965,
|
|
"epoch": 2.932873494277003,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00041503553304514157,
|
|
"loss": 5.6666,
|
|
"mean_token_accuracy": 0.17788280993700029,
|
|
"num_tokens": 57407186.0,
|
|
"step": 29340
|
|
},
|
|
{
|
|
"entropy": 6.051157093048095,
|
|
"epoch": 2.933373319338232,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004150075968843012,
|
|
"loss": 5.5753,
|
|
"mean_token_accuracy": 0.18575214892625808,
|
|
"num_tokens": 57415934.0,
|
|
"step": 29345
|
|
},
|
|
{
|
|
"entropy": 5.967261409759521,
|
|
"epoch": 2.93387314439946,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00041497965720090573,
|
|
"loss": 5.5896,
|
|
"mean_token_accuracy": 0.18771781772375107,
|
|
"num_tokens": 57425650.0,
|
|
"step": 29350
|
|
},
|
|
{
|
|
"entropy": 5.89099383354187,
|
|
"epoch": 2.934372969460689,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00041495171399565816,
|
|
"loss": 5.5348,
|
|
"mean_token_accuracy": 0.19041796177625656,
|
|
"num_tokens": 57436070.0,
|
|
"step": 29355
|
|
},
|
|
{
|
|
"entropy": 6.016760063171387,
|
|
"epoch": 2.934872794521917,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004149237672692615,
|
|
"loss": 5.6004,
|
|
"mean_token_accuracy": 0.17961885184049606,
|
|
"num_tokens": 57446050.0,
|
|
"step": 29360
|
|
},
|
|
{
|
|
"entropy": 6.006008815765381,
|
|
"epoch": 2.9353726195831458,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004148958170224188,
|
|
"loss": 5.542,
|
|
"mean_token_accuracy": 0.18703186511993408,
|
|
"num_tokens": 57455898.0,
|
|
"step": 29365
|
|
},
|
|
{
|
|
"entropy": 5.914278888702393,
|
|
"epoch": 2.9358724446443745,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00041486786325583343,
|
|
"loss": 5.5475,
|
|
"mean_token_accuracy": 0.19101609140634537,
|
|
"num_tokens": 57464754.0,
|
|
"step": 29370
|
|
},
|
|
{
|
|
"entropy": 5.9505949974060055,
|
|
"epoch": 2.936372269705603,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00041483990597020854,
|
|
"loss": 5.6218,
|
|
"mean_token_accuracy": 0.1792048081755638,
|
|
"num_tokens": 57474267.0,
|
|
"step": 29375
|
|
},
|
|
{
|
|
"entropy": 5.928002882003784,
|
|
"epoch": 2.936872094766832,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00041481194516624763,
|
|
"loss": 5.5044,
|
|
"mean_token_accuracy": 0.1828790307044983,
|
|
"num_tokens": 57484193.0,
|
|
"step": 29380
|
|
},
|
|
{
|
|
"entropy": 5.995638179779053,
|
|
"epoch": 2.93737191982806,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004147839808446541,
|
|
"loss": 5.4918,
|
|
"mean_token_accuracy": 0.18640368282794953,
|
|
"num_tokens": 57493004.0,
|
|
"step": 29385
|
|
},
|
|
{
|
|
"entropy": 5.943348550796509,
|
|
"epoch": 2.937871744889289,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00041475601300613166,
|
|
"loss": 5.5152,
|
|
"mean_token_accuracy": 0.19617605358362197,
|
|
"num_tokens": 57502509.0,
|
|
"step": 29390
|
|
},
|
|
{
|
|
"entropy": 6.008260679244995,
|
|
"epoch": 2.938371569950517,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00041472804165138384,
|
|
"loss": 5.5708,
|
|
"mean_token_accuracy": 0.1780075654387474,
|
|
"num_tokens": 57511770.0,
|
|
"step": 29395
|
|
},
|
|
{
|
|
"entropy": 5.970231580734253,
|
|
"epoch": 2.9388713950117458,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004147000667811145,
|
|
"loss": 5.6048,
|
|
"mean_token_accuracy": 0.18422103822231292,
|
|
"num_tokens": 57521724.0,
|
|
"step": 29400
|
|
},
|
|
{
|
|
"entropy": 5.97248649597168,
|
|
"epoch": 2.9393712200729745,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004146720883960273,
|
|
"loss": 5.5809,
|
|
"mean_token_accuracy": 0.1881623685359955,
|
|
"num_tokens": 57531393.0,
|
|
"step": 29405
|
|
},
|
|
{
|
|
"entropy": 5.971164321899414,
|
|
"epoch": 2.939871045134203,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004146441064968264,
|
|
"loss": 5.5788,
|
|
"mean_token_accuracy": 0.18255227208137512,
|
|
"num_tokens": 57539793.0,
|
|
"step": 29410
|
|
},
|
|
{
|
|
"entropy": 6.082666301727295,
|
|
"epoch": 2.940370870195432,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00041461612108421576,
|
|
"loss": 5.7275,
|
|
"mean_token_accuracy": 0.1774870976805687,
|
|
"num_tokens": 57549099.0,
|
|
"step": 29415
|
|
},
|
|
{
|
|
"entropy": 6.041388893127442,
|
|
"epoch": 2.94087069525666,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00041458813215889935,
|
|
"loss": 5.5759,
|
|
"mean_token_accuracy": 0.18507146835327148,
|
|
"num_tokens": 57558146.0,
|
|
"step": 29420
|
|
},
|
|
{
|
|
"entropy": 6.0041967868804935,
|
|
"epoch": 2.941370520317889,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004145601397215815,
|
|
"loss": 5.5489,
|
|
"mean_token_accuracy": 0.18484702408313752,
|
|
"num_tokens": 57567448.0,
|
|
"step": 29425
|
|
},
|
|
{
|
|
"entropy": 6.007260370254516,
|
|
"epoch": 2.941870345379117,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00041453214377296636,
|
|
"loss": 5.6109,
|
|
"mean_token_accuracy": 0.17665203362703324,
|
|
"num_tokens": 57577286.0,
|
|
"step": 29430
|
|
},
|
|
{
|
|
"entropy": 5.933387374877929,
|
|
"epoch": 2.9423701704403458,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004145041443137585,
|
|
"loss": 5.5398,
|
|
"mean_token_accuracy": 0.1852570578455925,
|
|
"num_tokens": 57587926.0,
|
|
"step": 29435
|
|
},
|
|
{
|
|
"entropy": 5.918116712570191,
|
|
"epoch": 2.9428699955015745,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004144761413446622,
|
|
"loss": 5.4696,
|
|
"mean_token_accuracy": 0.20122869908809662,
|
|
"num_tokens": 57598533.0,
|
|
"step": 29440
|
|
},
|
|
{
|
|
"entropy": 5.988051700592041,
|
|
"epoch": 2.943369820562803,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00041444813486638215,
|
|
"loss": 5.5271,
|
|
"mean_token_accuracy": 0.20064109116792678,
|
|
"num_tokens": 57607410.0,
|
|
"step": 29445
|
|
},
|
|
{
|
|
"entropy": 5.977674388885498,
|
|
"epoch": 2.943869645624032,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00041442012487962284,
|
|
"loss": 5.6739,
|
|
"mean_token_accuracy": 0.17619151026010513,
|
|
"num_tokens": 57617787.0,
|
|
"step": 29450
|
|
},
|
|
{
|
|
"entropy": 6.010932779312133,
|
|
"epoch": 2.94436947068526,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004143921113850891,
|
|
"loss": 5.5932,
|
|
"mean_token_accuracy": 0.18506048768758773,
|
|
"num_tokens": 57627537.0,
|
|
"step": 29455
|
|
},
|
|
{
|
|
"entropy": 6.037269163131714,
|
|
"epoch": 2.944869295746489,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00041436409438348564,
|
|
"loss": 5.5647,
|
|
"mean_token_accuracy": 0.18959832340478897,
|
|
"num_tokens": 57637281.0,
|
|
"step": 29460
|
|
},
|
|
{
|
|
"entropy": 5.944535636901856,
|
|
"epoch": 2.945369120807717,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004143360738755175,
|
|
"loss": 5.5356,
|
|
"mean_token_accuracy": 0.18658024072647095,
|
|
"num_tokens": 57646889.0,
|
|
"step": 29465
|
|
},
|
|
{
|
|
"entropy": 5.957968521118164,
|
|
"epoch": 2.9458689458689458,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004143080498618895,
|
|
"loss": 5.5142,
|
|
"mean_token_accuracy": 0.19338694512844085,
|
|
"num_tokens": 57655583.0,
|
|
"step": 29470
|
|
},
|
|
{
|
|
"entropy": 5.985981798171997,
|
|
"epoch": 2.9463687709301745,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00041428002234330694,
|
|
"loss": 5.5531,
|
|
"mean_token_accuracy": 0.18382490426301956,
|
|
"num_tokens": 57664778.0,
|
|
"step": 29475
|
|
},
|
|
{
|
|
"entropy": 5.920751953125,
|
|
"epoch": 2.946868595991403,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004142519913204748,
|
|
"loss": 5.549,
|
|
"mean_token_accuracy": 0.18953129053115844,
|
|
"num_tokens": 57674663.0,
|
|
"step": 29480
|
|
},
|
|
{
|
|
"entropy": 5.9899050235748295,
|
|
"epoch": 2.9473684210526314,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00041422395679409834,
|
|
"loss": 5.6141,
|
|
"mean_token_accuracy": 0.18713163137435912,
|
|
"num_tokens": 57684267.0,
|
|
"step": 29485
|
|
},
|
|
{
|
|
"entropy": 6.086307334899902,
|
|
"epoch": 2.94786824611386,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00041419591876488304,
|
|
"loss": 5.5701,
|
|
"mean_token_accuracy": 0.1861496388912201,
|
|
"num_tokens": 57694513.0,
|
|
"step": 29490
|
|
},
|
|
{
|
|
"entropy": 6.039879512786865,
|
|
"epoch": 2.948368071175089,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004141678772335342,
|
|
"loss": 5.5079,
|
|
"mean_token_accuracy": 0.18835990130901337,
|
|
"num_tokens": 57703474.0,
|
|
"step": 29495
|
|
},
|
|
{
|
|
"entropy": 5.935766363143921,
|
|
"epoch": 2.948867896236317,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00041413983220075736,
|
|
"loss": 5.533,
|
|
"mean_token_accuracy": 0.18969237804412842,
|
|
"num_tokens": 57714371.0,
|
|
"step": 29500
|
|
},
|
|
{
|
|
"entropy": 6.092406797409057,
|
|
"epoch": 2.9493677212975458,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00041411178366725814,
|
|
"loss": 5.6479,
|
|
"mean_token_accuracy": 0.1820398434996605,
|
|
"num_tokens": 57724403.0,
|
|
"step": 29505
|
|
},
|
|
{
|
|
"entropy": 6.010732173919678,
|
|
"epoch": 2.9498675463587745,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004140837316337423,
|
|
"loss": 5.5972,
|
|
"mean_token_accuracy": 0.1833369791507721,
|
|
"num_tokens": 57733705.0,
|
|
"step": 29510
|
|
},
|
|
{
|
|
"entropy": 5.987784147262573,
|
|
"epoch": 2.950367371420003,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004140556761009155,
|
|
"loss": 5.5038,
|
|
"mean_token_accuracy": 0.18902122229337692,
|
|
"num_tokens": 57743597.0,
|
|
"step": 29515
|
|
},
|
|
{
|
|
"entropy": 5.96956057548523,
|
|
"epoch": 2.9508671964812314,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004140276170694837,
|
|
"loss": 5.6164,
|
|
"mean_token_accuracy": 0.18442288041114807,
|
|
"num_tokens": 57754085.0,
|
|
"step": 29520
|
|
},
|
|
{
|
|
"entropy": 6.074036598205566,
|
|
"epoch": 2.95136702154246,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00041399955454015286,
|
|
"loss": 5.6564,
|
|
"mean_token_accuracy": 0.18200306445360184,
|
|
"num_tokens": 57764140.0,
|
|
"step": 29525
|
|
},
|
|
{
|
|
"entropy": 6.123690843582153,
|
|
"epoch": 2.951866846603689,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00041397148851362903,
|
|
"loss": 5.5858,
|
|
"mean_token_accuracy": 0.18754535615444184,
|
|
"num_tokens": 57772537.0,
|
|
"step": 29530
|
|
},
|
|
{
|
|
"entropy": 6.085543537139893,
|
|
"epoch": 2.952366671664917,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00041394341899061814,
|
|
"loss": 5.7289,
|
|
"mean_token_accuracy": 0.17172711789608003,
|
|
"num_tokens": 57782758.0,
|
|
"step": 29535
|
|
},
|
|
{
|
|
"entropy": 6.054210519790649,
|
|
"epoch": 2.9528664967261458,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004139153459718267,
|
|
"loss": 5.6967,
|
|
"mean_token_accuracy": 0.1795722484588623,
|
|
"num_tokens": 57791315.0,
|
|
"step": 29540
|
|
},
|
|
{
|
|
"entropy": 6.102345371246338,
|
|
"epoch": 2.9533663217873745,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.000413887269457961,
|
|
"loss": 5.6444,
|
|
"mean_token_accuracy": 0.1790851965546608,
|
|
"num_tokens": 57800225.0,
|
|
"step": 29545
|
|
},
|
|
{
|
|
"entropy": 6.012195348739624,
|
|
"epoch": 2.953866146848603,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00041385918944972716,
|
|
"loss": 5.5143,
|
|
"mean_token_accuracy": 0.1949934720993042,
|
|
"num_tokens": 57810319.0,
|
|
"step": 29550
|
|
},
|
|
{
|
|
"entropy": 5.914375638961792,
|
|
"epoch": 2.9543659719098314,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00041383110594783197,
|
|
"loss": 5.4557,
|
|
"mean_token_accuracy": 0.19468313902616502,
|
|
"num_tokens": 57819506.0,
|
|
"step": 29555
|
|
},
|
|
{
|
|
"entropy": 5.972245407104492,
|
|
"epoch": 2.95486579697106,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00041380301895298173,
|
|
"loss": 5.6751,
|
|
"mean_token_accuracy": 0.18416894674301149,
|
|
"num_tokens": 57829047.0,
|
|
"step": 29560
|
|
},
|
|
{
|
|
"entropy": 6.036110258102417,
|
|
"epoch": 2.955365622032289,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00041377492846588333,
|
|
"loss": 5.6723,
|
|
"mean_token_accuracy": 0.17585377991199494,
|
|
"num_tokens": 57839155.0,
|
|
"step": 29565
|
|
},
|
|
{
|
|
"entropy": 5.970257568359375,
|
|
"epoch": 2.955865447093517,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00041374683448724346,
|
|
"loss": 5.508,
|
|
"mean_token_accuracy": 0.19415581077337266,
|
|
"num_tokens": 57848705.0,
|
|
"step": 29570
|
|
},
|
|
{
|
|
"entropy": 5.955063962936402,
|
|
"epoch": 2.9563652721547458,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004137187370177689,
|
|
"loss": 5.5132,
|
|
"mean_token_accuracy": 0.18901387155056,
|
|
"num_tokens": 57858231.0,
|
|
"step": 29575
|
|
},
|
|
{
|
|
"entropy": 6.0264686107635494,
|
|
"epoch": 2.9568650972159745,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00041369063605816667,
|
|
"loss": 5.5922,
|
|
"mean_token_accuracy": 0.18809752017259598,
|
|
"num_tokens": 57868931.0,
|
|
"step": 29580
|
|
},
|
|
{
|
|
"entropy": 5.875388193130493,
|
|
"epoch": 2.957364922277203,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004136625316091437,
|
|
"loss": 5.4815,
|
|
"mean_token_accuracy": 0.19369305670261383,
|
|
"num_tokens": 57879075.0,
|
|
"step": 29585
|
|
},
|
|
{
|
|
"entropy": 5.9991600036621096,
|
|
"epoch": 2.9578647473384314,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004136344236714071,
|
|
"loss": 5.5543,
|
|
"mean_token_accuracy": 0.19072927087545394,
|
|
"num_tokens": 57889730.0,
|
|
"step": 29590
|
|
},
|
|
{
|
|
"entropy": 6.071002006530762,
|
|
"epoch": 2.95836457239966,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00041360631224566407,
|
|
"loss": 5.6438,
|
|
"mean_token_accuracy": 0.17589961886405944,
|
|
"num_tokens": 57900269.0,
|
|
"step": 29595
|
|
},
|
|
{
|
|
"entropy": 6.025560808181763,
|
|
"epoch": 2.958864397460889,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004135781973326219,
|
|
"loss": 5.5519,
|
|
"mean_token_accuracy": 0.18503678888082503,
|
|
"num_tokens": 57909269.0,
|
|
"step": 29600
|
|
},
|
|
{
|
|
"entropy": 5.890185117721558,
|
|
"epoch": 2.959364222522117,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00041355007893298796,
|
|
"loss": 5.4781,
|
|
"mean_token_accuracy": 0.19270889908075334,
|
|
"num_tokens": 57918408.0,
|
|
"step": 29605
|
|
},
|
|
{
|
|
"entropy": 5.947587394714356,
|
|
"epoch": 2.9598640475833458,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004135219570474697,
|
|
"loss": 5.552,
|
|
"mean_token_accuracy": 0.18688424527645112,
|
|
"num_tokens": 57928864.0,
|
|
"step": 29610
|
|
},
|
|
{
|
|
"entropy": 6.037745380401612,
|
|
"epoch": 2.9603638726445745,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00041349383167677456,
|
|
"loss": 5.6351,
|
|
"mean_token_accuracy": 0.17712004780769347,
|
|
"num_tokens": 57937998.0,
|
|
"step": 29615
|
|
},
|
|
{
|
|
"entropy": 5.983285903930664,
|
|
"epoch": 2.960863697705803,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00041346570282161033,
|
|
"loss": 5.5358,
|
|
"mean_token_accuracy": 0.18882708698511125,
|
|
"num_tokens": 57947630.0,
|
|
"step": 29620
|
|
},
|
|
{
|
|
"entropy": 6.019979476928711,
|
|
"epoch": 2.9613635227670314,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00041343757048268464,
|
|
"loss": 5.5876,
|
|
"mean_token_accuracy": 0.18818099200725555,
|
|
"num_tokens": 57957013.0,
|
|
"step": 29625
|
|
},
|
|
{
|
|
"entropy": 6.033219718933106,
|
|
"epoch": 2.96186334782826,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004134094346607053,
|
|
"loss": 5.6322,
|
|
"mean_token_accuracy": 0.17752128541469575,
|
|
"num_tokens": 57967445.0,
|
|
"step": 29630
|
|
},
|
|
{
|
|
"entropy": 6.031663608551026,
|
|
"epoch": 2.962363172889489,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004133812953563802,
|
|
"loss": 5.6671,
|
|
"mean_token_accuracy": 0.17648613601922988,
|
|
"num_tokens": 57976761.0,
|
|
"step": 29635
|
|
},
|
|
{
|
|
"entropy": 5.972355890274048,
|
|
"epoch": 2.962862997950717,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00041335315257041733,
|
|
"loss": 5.5226,
|
|
"mean_token_accuracy": 0.1871005266904831,
|
|
"num_tokens": 57986743.0,
|
|
"step": 29640
|
|
},
|
|
{
|
|
"entropy": 5.991907596588135,
|
|
"epoch": 2.9633628230119458,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00041332500630352463,
|
|
"loss": 5.613,
|
|
"mean_token_accuracy": 0.1770298570394516,
|
|
"num_tokens": 57996606.0,
|
|
"step": 29645
|
|
},
|
|
{
|
|
"entropy": 6.004441499710083,
|
|
"epoch": 2.9638626480731745,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004132968565564105,
|
|
"loss": 5.5671,
|
|
"mean_token_accuracy": 0.1891460970044136,
|
|
"num_tokens": 58005348.0,
|
|
"step": 29650
|
|
},
|
|
{
|
|
"entropy": 6.026729011535645,
|
|
"epoch": 2.964362473134403,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000413268703329783,
|
|
"loss": 5.5639,
|
|
"mean_token_accuracy": 0.18550854921340942,
|
|
"num_tokens": 58015034.0,
|
|
"step": 29655
|
|
},
|
|
{
|
|
"entropy": 5.971669244766235,
|
|
"epoch": 2.9648622981956314,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004132405466243505,
|
|
"loss": 5.5136,
|
|
"mean_token_accuracy": 0.191532763838768,
|
|
"num_tokens": 58023813.0,
|
|
"step": 29660
|
|
},
|
|
{
|
|
"entropy": 5.942009019851684,
|
|
"epoch": 2.96536212325686,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00041321238644082144,
|
|
"loss": 5.5677,
|
|
"mean_token_accuracy": 0.19031236171722413,
|
|
"num_tokens": 58033567.0,
|
|
"step": 29665
|
|
},
|
|
{
|
|
"entropy": 6.005946159362793,
|
|
"epoch": 2.965861948318089,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00041318422277990426,
|
|
"loss": 5.5463,
|
|
"mean_token_accuracy": 0.18779894709587097,
|
|
"num_tokens": 58043633.0,
|
|
"step": 29670
|
|
},
|
|
{
|
|
"entropy": 5.939936113357544,
|
|
"epoch": 2.966361773379317,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004131560556423076,
|
|
"loss": 5.4928,
|
|
"mean_token_accuracy": 0.19405934661626817,
|
|
"num_tokens": 58053932.0,
|
|
"step": 29675
|
|
},
|
|
{
|
|
"entropy": 5.987191295623779,
|
|
"epoch": 2.9668615984405458,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004131278850287401,
|
|
"loss": 5.5481,
|
|
"mean_token_accuracy": 0.18647626489400865,
|
|
"num_tokens": 58064168.0,
|
|
"step": 29680
|
|
},
|
|
{
|
|
"entropy": 5.930380582809448,
|
|
"epoch": 2.9673614235017745,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00041309971093991067,
|
|
"loss": 5.5758,
|
|
"mean_token_accuracy": 0.18455904871225357,
|
|
"num_tokens": 58074389.0,
|
|
"step": 29685
|
|
},
|
|
{
|
|
"entropy": 5.933172655105591,
|
|
"epoch": 2.967861248563003,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00041307153337652805,
|
|
"loss": 5.4531,
|
|
"mean_token_accuracy": 0.19025654941797257,
|
|
"num_tokens": 58084028.0,
|
|
"step": 29690
|
|
},
|
|
{
|
|
"entropy": 6.000842046737671,
|
|
"epoch": 2.9683610736242314,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000413043352339301,
|
|
"loss": 5.6296,
|
|
"mean_token_accuracy": 0.18021471202373504,
|
|
"num_tokens": 58093842.0,
|
|
"step": 29695
|
|
},
|
|
{
|
|
"entropy": 6.096247243881225,
|
|
"epoch": 2.96886089868546,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004130151678289388,
|
|
"loss": 5.5801,
|
|
"mean_token_accuracy": 0.1903948500752449,
|
|
"num_tokens": 58103775.0,
|
|
"step": 29700
|
|
},
|
|
{
|
|
"entropy": 5.986282062530518,
|
|
"epoch": 2.969360723746689,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004129869798461506,
|
|
"loss": 5.5461,
|
|
"mean_token_accuracy": 0.1870393320918083,
|
|
"num_tokens": 58113710.0,
|
|
"step": 29705
|
|
},
|
|
{
|
|
"entropy": 5.967748689651489,
|
|
"epoch": 2.969860548807917,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004129587883916454,
|
|
"loss": 5.619,
|
|
"mean_token_accuracy": 0.17500205636024474,
|
|
"num_tokens": 58123408.0,
|
|
"step": 29710
|
|
},
|
|
{
|
|
"entropy": 6.096813440322876,
|
|
"epoch": 2.9703603738691458,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004129305934661326,
|
|
"loss": 5.6512,
|
|
"mean_token_accuracy": 0.18134722113609314,
|
|
"num_tokens": 58132305.0,
|
|
"step": 29715
|
|
},
|
|
{
|
|
"entropy": 6.0071702003479,
|
|
"epoch": 2.9708601989303745,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00041290239507032155,
|
|
"loss": 5.5459,
|
|
"mean_token_accuracy": 0.18525767028331758,
|
|
"num_tokens": 58141655.0,
|
|
"step": 29720
|
|
},
|
|
{
|
|
"entropy": 5.93862247467041,
|
|
"epoch": 2.971360023991603,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004128741932049218,
|
|
"loss": 5.4753,
|
|
"mean_token_accuracy": 0.194343464076519,
|
|
"num_tokens": 58151495.0,
|
|
"step": 29725
|
|
},
|
|
{
|
|
"entropy": 5.916690158843994,
|
|
"epoch": 2.9718598490528314,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004128459878706428,
|
|
"loss": 5.5637,
|
|
"mean_token_accuracy": 0.1798371911048889,
|
|
"num_tokens": 58161388.0,
|
|
"step": 29730
|
|
},
|
|
{
|
|
"entropy": 5.883533239364624,
|
|
"epoch": 2.97235967411406,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004128177790681942,
|
|
"loss": 5.4398,
|
|
"mean_token_accuracy": 0.20649030208587646,
|
|
"num_tokens": 58171563.0,
|
|
"step": 29735
|
|
},
|
|
{
|
|
"entropy": 6.008903074264526,
|
|
"epoch": 2.972859499175289,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00041278956679828566,
|
|
"loss": 5.5775,
|
|
"mean_token_accuracy": 0.18937459588050842,
|
|
"num_tokens": 58181943.0,
|
|
"step": 29740
|
|
},
|
|
{
|
|
"entropy": 6.076177072525025,
|
|
"epoch": 2.973359324236517,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00041276135106162713,
|
|
"loss": 5.6801,
|
|
"mean_token_accuracy": 0.18036435395479203,
|
|
"num_tokens": 58192199.0,
|
|
"step": 29745
|
|
},
|
|
{
|
|
"entropy": 5.9944230079650875,
|
|
"epoch": 2.9738591492977458,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004127331318589285,
|
|
"loss": 5.654,
|
|
"mean_token_accuracy": 0.17867959290742874,
|
|
"num_tokens": 58201612.0,
|
|
"step": 29750
|
|
},
|
|
{
|
|
"entropy": 6.000206708908081,
|
|
"epoch": 2.9743589743589745,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00041270490919089966,
|
|
"loss": 5.6117,
|
|
"mean_token_accuracy": 0.183893184363842,
|
|
"num_tokens": 58211567.0,
|
|
"step": 29755
|
|
},
|
|
{
|
|
"entropy": 6.042569541931153,
|
|
"epoch": 2.974858799420203,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004126766830582508,
|
|
"loss": 5.6071,
|
|
"mean_token_accuracy": 0.18244485557079315,
|
|
"num_tokens": 58222739.0,
|
|
"step": 29760
|
|
},
|
|
{
|
|
"entropy": 6.020136213302612,
|
|
"epoch": 2.9753586244814314,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000412648453461692,
|
|
"loss": 5.5656,
|
|
"mean_token_accuracy": 0.18214865624904633,
|
|
"num_tokens": 58232269.0,
|
|
"step": 29765
|
|
},
|
|
{
|
|
"entropy": 6.021013689041138,
|
|
"epoch": 2.97585844954266,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00041262022040193346,
|
|
"loss": 5.7009,
|
|
"mean_token_accuracy": 0.1756475530564785,
|
|
"num_tokens": 58242451.0,
|
|
"step": 29770
|
|
},
|
|
{
|
|
"entropy": 6.057576990127563,
|
|
"epoch": 2.976358274603889,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00041259198387968564,
|
|
"loss": 5.7401,
|
|
"mean_token_accuracy": 0.17012189328670502,
|
|
"num_tokens": 58252202.0,
|
|
"step": 29775
|
|
},
|
|
{
|
|
"entropy": 6.008184337615967,
|
|
"epoch": 2.976858099665117,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00041256374389565895,
|
|
"loss": 5.5451,
|
|
"mean_token_accuracy": 0.18782974183559417,
|
|
"num_tokens": 58260864.0,
|
|
"step": 29780
|
|
},
|
|
{
|
|
"entropy": 5.993956470489502,
|
|
"epoch": 2.9773579247263458,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00041253550045056375,
|
|
"loss": 5.5592,
|
|
"mean_token_accuracy": 0.1877695620059967,
|
|
"num_tokens": 58271636.0,
|
|
"step": 29785
|
|
},
|
|
{
|
|
"entropy": 6.008885192871094,
|
|
"epoch": 2.9778577497875744,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00041250725354511085,
|
|
"loss": 5.4909,
|
|
"mean_token_accuracy": 0.1945252001285553,
|
|
"num_tokens": 58281792.0,
|
|
"step": 29790
|
|
},
|
|
{
|
|
"entropy": 6.035029649734497,
|
|
"epoch": 2.978357574848803,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004124790031800109,
|
|
"loss": 5.6484,
|
|
"mean_token_accuracy": 0.18232512921094896,
|
|
"num_tokens": 58291528.0,
|
|
"step": 29795
|
|
},
|
|
{
|
|
"entropy": 5.953736305236816,
|
|
"epoch": 2.9788573999100314,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004124507493559745,
|
|
"loss": 5.5926,
|
|
"mean_token_accuracy": 0.18682167530059815,
|
|
"num_tokens": 58302159.0,
|
|
"step": 29800
|
|
},
|
|
{
|
|
"entropy": 5.915394449234009,
|
|
"epoch": 2.97935722497126,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004124224920737126,
|
|
"loss": 5.5849,
|
|
"mean_token_accuracy": 0.1900637298822403,
|
|
"num_tokens": 58311621.0,
|
|
"step": 29805
|
|
},
|
|
{
|
|
"entropy": 5.9513983726501465,
|
|
"epoch": 2.9798570500324884,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004123942313339361,
|
|
"loss": 5.5939,
|
|
"mean_token_accuracy": 0.18912981003522872,
|
|
"num_tokens": 58320968.0,
|
|
"step": 29810
|
|
},
|
|
{
|
|
"entropy": 5.984130239486694,
|
|
"epoch": 2.980356875093717,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00041236596713735624,
|
|
"loss": 5.5909,
|
|
"mean_token_accuracy": 0.18133622854948045,
|
|
"num_tokens": 58330092.0,
|
|
"step": 29815
|
|
},
|
|
{
|
|
"entropy": 5.98772087097168,
|
|
"epoch": 2.9808567001549457,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004123376994846839,
|
|
"loss": 5.6637,
|
|
"mean_token_accuracy": 0.1775856137275696,
|
|
"num_tokens": 58339976.0,
|
|
"step": 29820
|
|
},
|
|
{
|
|
"entropy": 5.981420564651489,
|
|
"epoch": 2.9813565252161744,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004123094283766304,
|
|
"loss": 5.4979,
|
|
"mean_token_accuracy": 0.18868456929922103,
|
|
"num_tokens": 58349343.0,
|
|
"step": 29825
|
|
},
|
|
{
|
|
"entropy": 6.021856689453125,
|
|
"epoch": 2.981856350277403,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00041228115381390705,
|
|
"loss": 5.5736,
|
|
"mean_token_accuracy": 0.1817847728729248,
|
|
"num_tokens": 58358858.0,
|
|
"step": 29830
|
|
},
|
|
{
|
|
"entropy": 6.059363603591919,
|
|
"epoch": 2.9823561753386314,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00041225287579722526,
|
|
"loss": 5.6473,
|
|
"mean_token_accuracy": 0.1737842008471489,
|
|
"num_tokens": 58368532.0,
|
|
"step": 29835
|
|
},
|
|
{
|
|
"entropy": 5.937616920471191,
|
|
"epoch": 2.98285600039986,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004122245943272963,
|
|
"loss": 5.441,
|
|
"mean_token_accuracy": 0.19547626227140427,
|
|
"num_tokens": 58377997.0,
|
|
"step": 29840
|
|
},
|
|
{
|
|
"entropy": 5.953769540786743,
|
|
"epoch": 2.9833558254610884,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00041219630940483187,
|
|
"loss": 5.5338,
|
|
"mean_token_accuracy": 0.19324521720409393,
|
|
"num_tokens": 58387136.0,
|
|
"step": 29845
|
|
},
|
|
{
|
|
"entropy": 6.041741418838501,
|
|
"epoch": 2.983855650522317,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004121680210305436,
|
|
"loss": 5.5647,
|
|
"mean_token_accuracy": 0.18197683990001678,
|
|
"num_tokens": 58396110.0,
|
|
"step": 29850
|
|
},
|
|
{
|
|
"entropy": 6.103499984741211,
|
|
"epoch": 2.9843554755835457,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004121397292051433,
|
|
"loss": 5.7122,
|
|
"mean_token_accuracy": 0.17030903995037078,
|
|
"num_tokens": 58406411.0,
|
|
"step": 29855
|
|
},
|
|
{
|
|
"entropy": 6.004285669326782,
|
|
"epoch": 2.9848553006447744,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004121114339293427,
|
|
"loss": 5.5664,
|
|
"mean_token_accuracy": 0.18154270201921463,
|
|
"num_tokens": 58416172.0,
|
|
"step": 29860
|
|
},
|
|
{
|
|
"entropy": 5.927602338790893,
|
|
"epoch": 2.985355125706003,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004120831352038537,
|
|
"loss": 5.4921,
|
|
"mean_token_accuracy": 0.19115181565284728,
|
|
"num_tokens": 58426245.0,
|
|
"step": 29865
|
|
},
|
|
{
|
|
"entropy": 6.001721715927124,
|
|
"epoch": 2.9858549507672314,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004120548330293882,
|
|
"loss": 5.5737,
|
|
"mean_token_accuracy": 0.1832054913043976,
|
|
"num_tokens": 58435796.0,
|
|
"step": 29870
|
|
},
|
|
{
|
|
"entropy": 6.024183320999145,
|
|
"epoch": 2.98635477582846,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00041202652740665845,
|
|
"loss": 5.6378,
|
|
"mean_token_accuracy": 0.17415812909603118,
|
|
"num_tokens": 58445360.0,
|
|
"step": 29875
|
|
},
|
|
{
|
|
"entropy": 6.020950365066528,
|
|
"epoch": 2.9868546008896883,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004119982183363765,
|
|
"loss": 5.6157,
|
|
"mean_token_accuracy": 0.18344443440437316,
|
|
"num_tokens": 58453665.0,
|
|
"step": 29880
|
|
},
|
|
{
|
|
"entropy": 5.995265865325928,
|
|
"epoch": 2.987354425950917,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00041196990581925466,
|
|
"loss": 5.6035,
|
|
"mean_token_accuracy": 0.17674384415149688,
|
|
"num_tokens": 58462121.0,
|
|
"step": 29885
|
|
},
|
|
{
|
|
"entropy": 5.954890871047974,
|
|
"epoch": 2.9878542510121457,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004119415898560052,
|
|
"loss": 5.5904,
|
|
"mean_token_accuracy": 0.17816223353147506,
|
|
"num_tokens": 58471678.0,
|
|
"step": 29890
|
|
},
|
|
{
|
|
"entropy": 6.084583568572998,
|
|
"epoch": 2.9883540760733744,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004119132704473405,
|
|
"loss": 5.6472,
|
|
"mean_token_accuracy": 0.1784023940563202,
|
|
"num_tokens": 58481140.0,
|
|
"step": 29895
|
|
},
|
|
{
|
|
"entropy": 6.091830921173096,
|
|
"epoch": 2.988853901134603,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004118849475939733,
|
|
"loss": 5.6318,
|
|
"mean_token_accuracy": 0.1801155537366867,
|
|
"num_tokens": 58491163.0,
|
|
"step": 29900
|
|
},
|
|
{
|
|
"entropy": 5.976254987716675,
|
|
"epoch": 2.9893537261958314,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00041185662129661593,
|
|
"loss": 5.5855,
|
|
"mean_token_accuracy": 0.1814818263053894,
|
|
"num_tokens": 58500433.0,
|
|
"step": 29905
|
|
},
|
|
{
|
|
"entropy": 6.052849149703979,
|
|
"epoch": 2.98985355125706,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004118282915559813,
|
|
"loss": 5.6037,
|
|
"mean_token_accuracy": 0.17492140978574752,
|
|
"num_tokens": 58510618.0,
|
|
"step": 29910
|
|
},
|
|
{
|
|
"entropy": 5.9793905258178714,
|
|
"epoch": 2.9903533763182883,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004117999583727819,
|
|
"loss": 5.5199,
|
|
"mean_token_accuracy": 0.1876463621854782,
|
|
"num_tokens": 58519658.0,
|
|
"step": 29915
|
|
},
|
|
{
|
|
"entropy": 5.942109632492065,
|
|
"epoch": 2.990853201379517,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00041177162174773084,
|
|
"loss": 5.4746,
|
|
"mean_token_accuracy": 0.19160480797290802,
|
|
"num_tokens": 58530102.0,
|
|
"step": 29920
|
|
},
|
|
{
|
|
"entropy": 6.0246720790863035,
|
|
"epoch": 2.9913530264407457,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00041174328168154094,
|
|
"loss": 5.5978,
|
|
"mean_token_accuracy": 0.17909146398305892,
|
|
"num_tokens": 58539300.0,
|
|
"step": 29925
|
|
},
|
|
{
|
|
"entropy": 5.968430471420288,
|
|
"epoch": 2.9918528515019744,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004117149381749253,
|
|
"loss": 5.581,
|
|
"mean_token_accuracy": 0.1781037673354149,
|
|
"num_tokens": 58548592.0,
|
|
"step": 29930
|
|
},
|
|
{
|
|
"entropy": 5.984486103057861,
|
|
"epoch": 2.992352676563203,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004116865912285971,
|
|
"loss": 5.5873,
|
|
"mean_token_accuracy": 0.18286624699831008,
|
|
"num_tokens": 58559335.0,
|
|
"step": 29935
|
|
},
|
|
{
|
|
"entropy": 6.004906177520752,
|
|
"epoch": 2.9928525016244314,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00041165824084326923,
|
|
"loss": 5.5151,
|
|
"mean_token_accuracy": 0.18839209377765656,
|
|
"num_tokens": 58568470.0,
|
|
"step": 29940
|
|
},
|
|
{
|
|
"entropy": 5.927399682998657,
|
|
"epoch": 2.99335232668566,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004116298870196553,
|
|
"loss": 5.4447,
|
|
"mean_token_accuracy": 0.19750769734382628,
|
|
"num_tokens": 58577514.0,
|
|
"step": 29945
|
|
},
|
|
{
|
|
"entropy": 6.001390361785889,
|
|
"epoch": 2.9938521517468883,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00041160152975846853,
|
|
"loss": 5.5233,
|
|
"mean_token_accuracy": 0.1876409649848938,
|
|
"num_tokens": 58587241.0,
|
|
"step": 29950
|
|
},
|
|
{
|
|
"entropy": 6.0297328472137455,
|
|
"epoch": 2.994351976808117,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004115731690604225,
|
|
"loss": 5.7184,
|
|
"mean_token_accuracy": 0.18013422340154647,
|
|
"num_tokens": 58596923.0,
|
|
"step": 29955
|
|
},
|
|
{
|
|
"entropy": 5.989173936843872,
|
|
"epoch": 2.9948518018693457,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004115448049262306,
|
|
"loss": 5.5337,
|
|
"mean_token_accuracy": 0.19029093831777572,
|
|
"num_tokens": 58607316.0,
|
|
"step": 29960
|
|
},
|
|
{
|
|
"entropy": 5.920219850540161,
|
|
"epoch": 2.9953516269305744,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004115164373566065,
|
|
"loss": 5.5009,
|
|
"mean_token_accuracy": 0.19654790312051773,
|
|
"num_tokens": 58616601.0,
|
|
"step": 29965
|
|
},
|
|
{
|
|
"entropy": 6.001998996734619,
|
|
"epoch": 2.995851451991803,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00041148806635226407,
|
|
"loss": 5.6605,
|
|
"mean_token_accuracy": 0.1817271277308464,
|
|
"num_tokens": 58628094.0,
|
|
"step": 29970
|
|
},
|
|
{
|
|
"entropy": 6.03379545211792,
|
|
"epoch": 2.9963512770530314,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000411459691913917,
|
|
"loss": 5.5937,
|
|
"mean_token_accuracy": 0.18316017091274261,
|
|
"num_tokens": 58638005.0,
|
|
"step": 29975
|
|
},
|
|
{
|
|
"entropy": 6.010437440872193,
|
|
"epoch": 2.99685110211426,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00041143131404227913,
|
|
"loss": 5.609,
|
|
"mean_token_accuracy": 0.17691365778446197,
|
|
"num_tokens": 58648552.0,
|
|
"step": 29980
|
|
},
|
|
{
|
|
"entropy": 5.965445184707642,
|
|
"epoch": 2.9973509271754883,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004114029327380645,
|
|
"loss": 5.4928,
|
|
"mean_token_accuracy": 0.1979580655694008,
|
|
"num_tokens": 58657661.0,
|
|
"step": 29985
|
|
},
|
|
{
|
|
"entropy": 6.030761241912842,
|
|
"epoch": 2.997850752236717,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004113745480019872,
|
|
"loss": 5.6653,
|
|
"mean_token_accuracy": 0.18104513734579086,
|
|
"num_tokens": 58667553.0,
|
|
"step": 29990
|
|
},
|
|
{
|
|
"entropy": 6.090502548217773,
|
|
"epoch": 2.9983505772979457,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004113461598347614,
|
|
"loss": 5.6948,
|
|
"mean_token_accuracy": 0.17791249006986617,
|
|
"num_tokens": 58677641.0,
|
|
"step": 29995
|
|
},
|
|
{
|
|
"entropy": 5.988465785980225,
|
|
"epoch": 2.9988504023591744,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.00041131776823710134,
|
|
"loss": 5.5489,
|
|
"mean_token_accuracy": 0.18734422475099563,
|
|
"num_tokens": 58687729.0,
|
|
"step": 30000
|
|
},
|
|
{
|
|
"epoch": 2.9988504023591744,
|
|
"eval_entropy": 5.809750569846575,
|
|
"eval_loss": 5.673617839813232,
|
|
"eval_mean_token_accuracy": 0.18867066250986828,
|
|
"eval_num_tokens": 58687729.0,
|
|
"eval_runtime": 23.6124,
|
|
"eval_samples_per_second": 1314.775,
|
|
"eval_steps_per_second": 164.363,
|
|
"step": 30000
|
|
},
|
|
{
|
|
"entropy": 5.972734689712524,
|
|
"epoch": 2.9993502274204027,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004112893732097213,
|
|
"loss": 5.5196,
|
|
"mean_token_accuracy": 0.1937110185623169,
|
|
"num_tokens": 58697164.0,
|
|
"step": 30005
|
|
},
|
|
{
|
|
"entropy": 5.904154205322266,
|
|
"epoch": 2.9998500524816314,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004112609747533356,
|
|
"loss": 5.4788,
|
|
"mean_token_accuracy": 0.19820438772439958,
|
|
"num_tokens": 58705702.0,
|
|
"step": 30010
|
|
},
|
|
{
|
|
"entropy": 6.009302457173665,
|
|
"epoch": 3.000299895036737,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004112325728686589,
|
|
"loss": 5.5745,
|
|
"mean_token_accuracy": 0.18993012441529167,
|
|
"num_tokens": 58714408.0,
|
|
"step": 30015
|
|
},
|
|
{
|
|
"entropy": 5.992026281356812,
|
|
"epoch": 3.000799720097966,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00041120416755640574,
|
|
"loss": 5.5063,
|
|
"mean_token_accuracy": 0.1890733227133751,
|
|
"num_tokens": 58724185.0,
|
|
"step": 30020
|
|
},
|
|
{
|
|
"entropy": 5.922540140151978,
|
|
"epoch": 3.001299545159194,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00041117575881729075,
|
|
"loss": 5.3927,
|
|
"mean_token_accuracy": 0.1969762235879898,
|
|
"num_tokens": 58733998.0,
|
|
"step": 30025
|
|
},
|
|
{
|
|
"entropy": 5.963575220108032,
|
|
"epoch": 3.001799370220423,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00041114734665202875,
|
|
"loss": 5.5062,
|
|
"mean_token_accuracy": 0.18798189759254455,
|
|
"num_tokens": 58743881.0,
|
|
"step": 30030
|
|
},
|
|
{
|
|
"entropy": 6.023996305465698,
|
|
"epoch": 3.0022991952816516,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004111189310613344,
|
|
"loss": 5.5542,
|
|
"mean_token_accuracy": 0.184088097512722,
|
|
"num_tokens": 58754106.0,
|
|
"step": 30035
|
|
},
|
|
{
|
|
"entropy": 6.060251140594483,
|
|
"epoch": 3.00279902034288,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00041109051204592294,
|
|
"loss": 5.5126,
|
|
"mean_token_accuracy": 0.19028006941080094,
|
|
"num_tokens": 58763830.0,
|
|
"step": 30040
|
|
},
|
|
{
|
|
"entropy": 5.96569299697876,
|
|
"epoch": 3.0032988454041085,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00041106208960650913,
|
|
"loss": 5.4706,
|
|
"mean_token_accuracy": 0.19964258819818498,
|
|
"num_tokens": 58773478.0,
|
|
"step": 30045
|
|
},
|
|
{
|
|
"entropy": 5.924048709869385,
|
|
"epoch": 3.003798670465337,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00041103366374380817,
|
|
"loss": 5.508,
|
|
"mean_token_accuracy": 0.19726539254188538,
|
|
"num_tokens": 58784529.0,
|
|
"step": 30050
|
|
},
|
|
{
|
|
"entropy": 6.062330865859986,
|
|
"epoch": 3.004298495526566,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00041100523445853525,
|
|
"loss": 5.6088,
|
|
"mean_token_accuracy": 0.18701052069664,
|
|
"num_tokens": 58794087.0,
|
|
"step": 30055
|
|
},
|
|
{
|
|
"entropy": 5.832253789901733,
|
|
"epoch": 3.004798320587794,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004109768017514056,
|
|
"loss": 5.3089,
|
|
"mean_token_accuracy": 0.20859542042016982,
|
|
"num_tokens": 58804350.0,
|
|
"step": 30060
|
|
},
|
|
{
|
|
"entropy": 5.9562952518463135,
|
|
"epoch": 3.005298145649023,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004109483656231346,
|
|
"loss": 5.5711,
|
|
"mean_token_accuracy": 0.18432366102933884,
|
|
"num_tokens": 58814560.0,
|
|
"step": 30065
|
|
},
|
|
{
|
|
"entropy": 5.973737668991089,
|
|
"epoch": 3.0057979707102516,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00041091992607443777,
|
|
"loss": 5.5748,
|
|
"mean_token_accuracy": 0.17975105941295624,
|
|
"num_tokens": 58825016.0,
|
|
"step": 30070
|
|
},
|
|
{
|
|
"entropy": 5.906259298324585,
|
|
"epoch": 3.00629779577148,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00041089148310603053,
|
|
"loss": 5.3634,
|
|
"mean_token_accuracy": 0.20064887255430222,
|
|
"num_tokens": 58834673.0,
|
|
"step": 30075
|
|
},
|
|
{
|
|
"entropy": 5.966768598556518,
|
|
"epoch": 3.0067976208327085,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004108630367186285,
|
|
"loss": 5.3848,
|
|
"mean_token_accuracy": 0.20140929967164994,
|
|
"num_tokens": 58843461.0,
|
|
"step": 30080
|
|
},
|
|
{
|
|
"entropy": 5.943648004531861,
|
|
"epoch": 3.007297445893937,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00041083458691294755,
|
|
"loss": 5.5033,
|
|
"mean_token_accuracy": 0.191776342689991,
|
|
"num_tokens": 58853048.0,
|
|
"step": 30085
|
|
},
|
|
{
|
|
"entropy": 5.912047052383423,
|
|
"epoch": 3.007797270955166,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004108061336897032,
|
|
"loss": 5.4782,
|
|
"mean_token_accuracy": 0.18673345148563386,
|
|
"num_tokens": 58863234.0,
|
|
"step": 30090
|
|
},
|
|
{
|
|
"entropy": 5.992109584808349,
|
|
"epoch": 3.008297096016394,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004107776770496116,
|
|
"loss": 5.5052,
|
|
"mean_token_accuracy": 0.19199325144290924,
|
|
"num_tokens": 58871503.0,
|
|
"step": 30095
|
|
},
|
|
{
|
|
"entropy": 5.951854276657104,
|
|
"epoch": 3.008796921077623,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004107492169933885,
|
|
"loss": 5.4524,
|
|
"mean_token_accuracy": 0.19773415625095367,
|
|
"num_tokens": 58880660.0,
|
|
"step": 30100
|
|
},
|
|
{
|
|
"entropy": 5.947471666336059,
|
|
"epoch": 3.0092967461388516,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00041072075352175004,
|
|
"loss": 5.4714,
|
|
"mean_token_accuracy": 0.19419908076524733,
|
|
"num_tokens": 58889563.0,
|
|
"step": 30105
|
|
},
|
|
{
|
|
"entropy": 5.910320806503296,
|
|
"epoch": 3.00979657120008,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00041069228663541234,
|
|
"loss": 5.4095,
|
|
"mean_token_accuracy": 0.19973219335079193,
|
|
"num_tokens": 58900139.0,
|
|
"step": 30110
|
|
},
|
|
{
|
|
"entropy": 5.849691724777221,
|
|
"epoch": 3.0102963962613085,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004106638163350917,
|
|
"loss": 5.359,
|
|
"mean_token_accuracy": 0.20565673261880874,
|
|
"num_tokens": 58909644.0,
|
|
"step": 30115
|
|
},
|
|
{
|
|
"entropy": 5.923143720626831,
|
|
"epoch": 3.010796221322537,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004106353426215043,
|
|
"loss": 5.5089,
|
|
"mean_token_accuracy": 0.1825881153345108,
|
|
"num_tokens": 58919998.0,
|
|
"step": 30120
|
|
},
|
|
{
|
|
"entropy": 5.998043870925903,
|
|
"epoch": 3.0112960463837655,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00041060686549536656,
|
|
"loss": 5.485,
|
|
"mean_token_accuracy": 0.18956365585327148,
|
|
"num_tokens": 58928447.0,
|
|
"step": 30125
|
|
},
|
|
{
|
|
"entropy": 6.038575935363769,
|
|
"epoch": 3.011795871444994,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000410578384957395,
|
|
"loss": 5.557,
|
|
"mean_token_accuracy": 0.17637839764356614,
|
|
"num_tokens": 58939410.0,
|
|
"step": 30130
|
|
},
|
|
{
|
|
"entropy": 5.985652494430542,
|
|
"epoch": 3.012295696506223,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004105499010083062,
|
|
"loss": 5.5332,
|
|
"mean_token_accuracy": 0.1851104289293289,
|
|
"num_tokens": 58949672.0,
|
|
"step": 30135
|
|
},
|
|
{
|
|
"entropy": 5.898100900650024,
|
|
"epoch": 3.0127955215674516,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00041052141364881665,
|
|
"loss": 5.3335,
|
|
"mean_token_accuracy": 0.21060683578252792,
|
|
"num_tokens": 58960034.0,
|
|
"step": 30140
|
|
},
|
|
{
|
|
"entropy": 6.001464700698852,
|
|
"epoch": 3.01329534662868,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00041049292287964335,
|
|
"loss": 5.4194,
|
|
"mean_token_accuracy": 0.19259812980890273,
|
|
"num_tokens": 58969770.0,
|
|
"step": 30145
|
|
},
|
|
{
|
|
"entropy": 5.942034959793091,
|
|
"epoch": 3.0137951716899085,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00041046442870150293,
|
|
"loss": 5.4233,
|
|
"mean_token_accuracy": 0.19729091078042985,
|
|
"num_tokens": 58979638.0,
|
|
"step": 30150
|
|
},
|
|
{
|
|
"entropy": 5.934301567077637,
|
|
"epoch": 3.014294996751137,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00041043593111511227,
|
|
"loss": 5.401,
|
|
"mean_token_accuracy": 0.19385458379983903,
|
|
"num_tokens": 58988566.0,
|
|
"step": 30155
|
|
},
|
|
{
|
|
"entropy": 5.943822383880615,
|
|
"epoch": 3.0147948218123655,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004104074301211885,
|
|
"loss": 5.4928,
|
|
"mean_token_accuracy": 0.18733034729957582,
|
|
"num_tokens": 58998354.0,
|
|
"step": 30160
|
|
},
|
|
{
|
|
"entropy": 6.022428131103515,
|
|
"epoch": 3.015294646873594,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00041037892572044863,
|
|
"loss": 5.5008,
|
|
"mean_token_accuracy": 0.1842317432165146,
|
|
"num_tokens": 59007310.0,
|
|
"step": 30165
|
|
},
|
|
{
|
|
"entropy": 6.018810033798218,
|
|
"epoch": 3.015794471934823,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00041035041791360983,
|
|
"loss": 5.5716,
|
|
"mean_token_accuracy": 0.18652478158473967,
|
|
"num_tokens": 59017145.0,
|
|
"step": 30170
|
|
},
|
|
{
|
|
"entropy": 5.993401765823364,
|
|
"epoch": 3.0162942969960516,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004103219067013893,
|
|
"loss": 5.4695,
|
|
"mean_token_accuracy": 0.1912190854549408,
|
|
"num_tokens": 59026941.0,
|
|
"step": 30175
|
|
},
|
|
{
|
|
"entropy": 5.906410169601441,
|
|
"epoch": 3.01679412205728,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00041029339208450445,
|
|
"loss": 5.4303,
|
|
"mean_token_accuracy": 0.20169650614261628,
|
|
"num_tokens": 59036343.0,
|
|
"step": 30180
|
|
},
|
|
{
|
|
"entropy": 5.9200256824493405,
|
|
"epoch": 3.0172939471185085,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004102648740636727,
|
|
"loss": 5.443,
|
|
"mean_token_accuracy": 0.19315614998340608,
|
|
"num_tokens": 59046601.0,
|
|
"step": 30185
|
|
},
|
|
{
|
|
"entropy": 5.982809162139892,
|
|
"epoch": 3.017793772179737,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004102363526396115,
|
|
"loss": 5.5531,
|
|
"mean_token_accuracy": 0.17977938205003738,
|
|
"num_tokens": 59055819.0,
|
|
"step": 30190
|
|
},
|
|
{
|
|
"entropy": 5.929302835464478,
|
|
"epoch": 3.0182935972409655,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004102078278130384,
|
|
"loss": 5.4744,
|
|
"mean_token_accuracy": 0.19594795256853104,
|
|
"num_tokens": 59064956.0,
|
|
"step": 30195
|
|
},
|
|
{
|
|
"entropy": 5.899699783325195,
|
|
"epoch": 3.018793422302194,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00041017929958467113,
|
|
"loss": 5.3354,
|
|
"mean_token_accuracy": 0.1960517004132271,
|
|
"num_tokens": 59073842.0,
|
|
"step": 30200
|
|
},
|
|
{
|
|
"entropy": 5.977841997146607,
|
|
"epoch": 3.019293247363423,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004101507679552276,
|
|
"loss": 5.5098,
|
|
"mean_token_accuracy": 0.18770071119070053,
|
|
"num_tokens": 59084946.0,
|
|
"step": 30205
|
|
},
|
|
{
|
|
"entropy": 6.02443561553955,
|
|
"epoch": 3.0197930724246516,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004101222329254255,
|
|
"loss": 5.5288,
|
|
"mean_token_accuracy": 0.19283157885074614,
|
|
"num_tokens": 59095142.0,
|
|
"step": 30210
|
|
},
|
|
{
|
|
"entropy": 5.961938905715942,
|
|
"epoch": 3.02029289748588,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004100936944959828,
|
|
"loss": 5.4856,
|
|
"mean_token_accuracy": 0.19183343797922134,
|
|
"num_tokens": 59104618.0,
|
|
"step": 30215
|
|
},
|
|
{
|
|
"entropy": 5.94179630279541,
|
|
"epoch": 3.0207927225471085,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004100651526676174,
|
|
"loss": 5.5253,
|
|
"mean_token_accuracy": 0.18822157084941865,
|
|
"num_tokens": 59114485.0,
|
|
"step": 30220
|
|
},
|
|
{
|
|
"entropy": 6.025289058685303,
|
|
"epoch": 3.021292547608337,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004100366074410476,
|
|
"loss": 5.5873,
|
|
"mean_token_accuracy": 0.17934390902519226,
|
|
"num_tokens": 59124866.0,
|
|
"step": 30225
|
|
},
|
|
{
|
|
"entropy": 5.916163730621338,
|
|
"epoch": 3.0217923726695655,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00041000805881699143,
|
|
"loss": 5.3757,
|
|
"mean_token_accuracy": 0.19935044795274734,
|
|
"num_tokens": 59134123.0,
|
|
"step": 30230
|
|
},
|
|
{
|
|
"entropy": 5.9965245723724365,
|
|
"epoch": 3.022292197730794,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004099795067961673,
|
|
"loss": 5.5191,
|
|
"mean_token_accuracy": 0.18997085392475127,
|
|
"num_tokens": 59144375.0,
|
|
"step": 30235
|
|
},
|
|
{
|
|
"entropy": 5.995415735244751,
|
|
"epoch": 3.022792022792023,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004099509513792935,
|
|
"loss": 5.4889,
|
|
"mean_token_accuracy": 0.1910456523299217,
|
|
"num_tokens": 59154185.0,
|
|
"step": 30240
|
|
},
|
|
{
|
|
"entropy": 6.026722860336304,
|
|
"epoch": 3.0232918478532516,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00040992239256708844,
|
|
"loss": 5.5688,
|
|
"mean_token_accuracy": 0.18509793132543564,
|
|
"num_tokens": 59164501.0,
|
|
"step": 30245
|
|
},
|
|
{
|
|
"entropy": 5.984708261489868,
|
|
"epoch": 3.02379167291448,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004098938303602708,
|
|
"loss": 5.46,
|
|
"mean_token_accuracy": 0.1974733829498291,
|
|
"num_tokens": 59174349.0,
|
|
"step": 30250
|
|
},
|
|
{
|
|
"entropy": 5.985975503921509,
|
|
"epoch": 3.0242914979757085,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00040986526475955904,
|
|
"loss": 5.5043,
|
|
"mean_token_accuracy": 0.20181758403778077,
|
|
"num_tokens": 59183532.0,
|
|
"step": 30255
|
|
},
|
|
{
|
|
"entropy": 5.9418610572814945,
|
|
"epoch": 3.024791323036937,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.000409836695765672,
|
|
"loss": 5.4608,
|
|
"mean_token_accuracy": 0.18835237473249436,
|
|
"num_tokens": 59192492.0,
|
|
"step": 30260
|
|
},
|
|
{
|
|
"entropy": 5.966141319274902,
|
|
"epoch": 3.0252911480981655,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00040980812337932835,
|
|
"loss": 5.4878,
|
|
"mean_token_accuracy": 0.18752565160393714,
|
|
"num_tokens": 59203237.0,
|
|
"step": 30265
|
|
},
|
|
{
|
|
"entropy": 5.891648483276367,
|
|
"epoch": 3.025790973159394,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00040977954760124693,
|
|
"loss": 5.4265,
|
|
"mean_token_accuracy": 0.18839163035154344,
|
|
"num_tokens": 59213286.0,
|
|
"step": 30270
|
|
},
|
|
{
|
|
"entropy": 6.0151620388031,
|
|
"epoch": 3.026290798220623,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00040975096843214677,
|
|
"loss": 5.5233,
|
|
"mean_token_accuracy": 0.18088602274656296,
|
|
"num_tokens": 59223211.0,
|
|
"step": 30275
|
|
},
|
|
{
|
|
"entropy": 5.980376052856445,
|
|
"epoch": 3.0267906232818516,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00040972238587274695,
|
|
"loss": 5.5201,
|
|
"mean_token_accuracy": 0.19045343846082688,
|
|
"num_tokens": 59232702.0,
|
|
"step": 30280
|
|
},
|
|
{
|
|
"entropy": 5.990558910369873,
|
|
"epoch": 3.02729044834308,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00040969379992376664,
|
|
"loss": 5.5814,
|
|
"mean_token_accuracy": 0.1888894885778427,
|
|
"num_tokens": 59242357.0,
|
|
"step": 30285
|
|
},
|
|
{
|
|
"entropy": 6.032013320922852,
|
|
"epoch": 3.0277902734043085,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004096652105859249,
|
|
"loss": 5.4847,
|
|
"mean_token_accuracy": 0.18653424382209777,
|
|
"num_tokens": 59250785.0,
|
|
"step": 30290
|
|
},
|
|
{
|
|
"entropy": 6.057624578475952,
|
|
"epoch": 3.028290098465537,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004096366178599412,
|
|
"loss": 5.5202,
|
|
"mean_token_accuracy": 0.1874241814017296,
|
|
"num_tokens": 59260264.0,
|
|
"step": 30295
|
|
},
|
|
{
|
|
"entropy": 5.9676737785339355,
|
|
"epoch": 3.0287899235267655,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004096080217465347,
|
|
"loss": 5.4945,
|
|
"mean_token_accuracy": 0.19450927525758743,
|
|
"num_tokens": 59269603.0,
|
|
"step": 30300
|
|
},
|
|
{
|
|
"entropy": 5.995889329910279,
|
|
"epoch": 3.029289748587994,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004095794222464252,
|
|
"loss": 5.5203,
|
|
"mean_token_accuracy": 0.19375595450401306,
|
|
"num_tokens": 59279255.0,
|
|
"step": 30305
|
|
},
|
|
{
|
|
"entropy": 6.025269365310669,
|
|
"epoch": 3.029789573649223,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004095508193603319,
|
|
"loss": 5.5708,
|
|
"mean_token_accuracy": 0.1806512087583542,
|
|
"num_tokens": 59288650.0,
|
|
"step": 30310
|
|
},
|
|
{
|
|
"entropy": 5.899461269378662,
|
|
"epoch": 3.0302893987104516,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004095222130889747,
|
|
"loss": 5.4976,
|
|
"mean_token_accuracy": 0.18942508548498155,
|
|
"num_tokens": 59298032.0,
|
|
"step": 30315
|
|
},
|
|
{
|
|
"entropy": 6.044114446640014,
|
|
"epoch": 3.03078922377168,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00040949360343307324,
|
|
"loss": 5.5148,
|
|
"mean_token_accuracy": 0.1872825428843498,
|
|
"num_tokens": 59307147.0,
|
|
"step": 30320
|
|
},
|
|
{
|
|
"entropy": 6.114926052093506,
|
|
"epoch": 3.0312890488329085,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004094649903933472,
|
|
"loss": 5.5271,
|
|
"mean_token_accuracy": 0.1825868681073189,
|
|
"num_tokens": 59316602.0,
|
|
"step": 30325
|
|
},
|
|
{
|
|
"entropy": 5.881718730926513,
|
|
"epoch": 3.031788873894137,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00040943637397051683,
|
|
"loss": 5.4596,
|
|
"mean_token_accuracy": 0.19543141275644302,
|
|
"num_tokens": 59326176.0,
|
|
"step": 30330
|
|
},
|
|
{
|
|
"entropy": 5.946799898147583,
|
|
"epoch": 3.0322886989553655,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00040940775416530164,
|
|
"loss": 5.5473,
|
|
"mean_token_accuracy": 0.18204125612974167,
|
|
"num_tokens": 59335676.0,
|
|
"step": 30335
|
|
},
|
|
{
|
|
"entropy": 5.9502636909484865,
|
|
"epoch": 3.032788524016594,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00040937913097842204,
|
|
"loss": 5.3702,
|
|
"mean_token_accuracy": 0.21406832039356233,
|
|
"num_tokens": 59345807.0,
|
|
"step": 30340
|
|
},
|
|
{
|
|
"entropy": 5.969470643997193,
|
|
"epoch": 3.033288349077823,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004093505044105982,
|
|
"loss": 5.4188,
|
|
"mean_token_accuracy": 0.1951259657740593,
|
|
"num_tokens": 59355197.0,
|
|
"step": 30345
|
|
},
|
|
{
|
|
"entropy": 5.990471744537354,
|
|
"epoch": 3.033788174139051,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00040932187446255004,
|
|
"loss": 5.5744,
|
|
"mean_token_accuracy": 0.18898524791002275,
|
|
"num_tokens": 59364498.0,
|
|
"step": 30350
|
|
},
|
|
{
|
|
"entropy": 5.9131382465362545,
|
|
"epoch": 3.03428799920028,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004092932411349982,
|
|
"loss": 5.4286,
|
|
"mean_token_accuracy": 0.19842628836631776,
|
|
"num_tokens": 59373541.0,
|
|
"step": 30355
|
|
},
|
|
{
|
|
"entropy": 6.0507423877716064,
|
|
"epoch": 3.0347878242615085,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.000409264604428663,
|
|
"loss": 5.5949,
|
|
"mean_token_accuracy": 0.18196279406547547,
|
|
"num_tokens": 59384743.0,
|
|
"step": 30360
|
|
},
|
|
{
|
|
"entropy": 5.97858772277832,
|
|
"epoch": 3.035287649322737,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004092359643442648,
|
|
"loss": 5.5027,
|
|
"mean_token_accuracy": 0.1917838156223297,
|
|
"num_tokens": 59394173.0,
|
|
"step": 30365
|
|
},
|
|
{
|
|
"entropy": 5.927977180480957,
|
|
"epoch": 3.0357874743839655,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004092073208825243,
|
|
"loss": 5.542,
|
|
"mean_token_accuracy": 0.18234771341085435,
|
|
"num_tokens": 59403760.0,
|
|
"step": 30370
|
|
},
|
|
{
|
|
"entropy": 5.91094388961792,
|
|
"epoch": 3.036287299445194,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004091786740441622,
|
|
"loss": 5.4461,
|
|
"mean_token_accuracy": 0.19291783422231673,
|
|
"num_tokens": 59413008.0,
|
|
"step": 30375
|
|
},
|
|
{
|
|
"entropy": 5.999368190765381,
|
|
"epoch": 3.036787124506423,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00040915002382989915,
|
|
"loss": 5.4489,
|
|
"mean_token_accuracy": 0.196339450776577,
|
|
"num_tokens": 59423668.0,
|
|
"step": 30380
|
|
},
|
|
{
|
|
"entropy": 5.959788513183594,
|
|
"epoch": 3.037286949567651,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000409121370240456,
|
|
"loss": 5.4855,
|
|
"mean_token_accuracy": 0.19561815410852432,
|
|
"num_tokens": 59433317.0,
|
|
"step": 30385
|
|
},
|
|
{
|
|
"entropy": 6.045798969268799,
|
|
"epoch": 3.03778677462888,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004090927132765537,
|
|
"loss": 5.5296,
|
|
"mean_token_accuracy": 0.18408620059490205,
|
|
"num_tokens": 59443608.0,
|
|
"step": 30390
|
|
},
|
|
{
|
|
"entropy": 5.890335464477539,
|
|
"epoch": 3.0382865996901085,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00040906405293891323,
|
|
"loss": 5.4346,
|
|
"mean_token_accuracy": 0.1964370682835579,
|
|
"num_tokens": 59453475.0,
|
|
"step": 30395
|
|
},
|
|
{
|
|
"entropy": 5.934202337265015,
|
|
"epoch": 3.038786424751337,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004090353892282557,
|
|
"loss": 5.5988,
|
|
"mean_token_accuracy": 0.17796805799007415,
|
|
"num_tokens": 59463415.0,
|
|
"step": 30400
|
|
},
|
|
{
|
|
"entropy": 5.991893529891968,
|
|
"epoch": 3.0392862498125655,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004090067221453024,
|
|
"loss": 5.4154,
|
|
"mean_token_accuracy": 0.1968083918094635,
|
|
"num_tokens": 59472787.0,
|
|
"step": 30405
|
|
},
|
|
{
|
|
"entropy": 5.959092330932617,
|
|
"epoch": 3.039786074873794,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004089780516907743,
|
|
"loss": 5.4009,
|
|
"mean_token_accuracy": 0.20062688291072844,
|
|
"num_tokens": 59482698.0,
|
|
"step": 30410
|
|
},
|
|
{
|
|
"entropy": 5.954780578613281,
|
|
"epoch": 3.040285899935023,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00040894937786539287,
|
|
"loss": 5.5317,
|
|
"mean_token_accuracy": 0.19056759625673295,
|
|
"num_tokens": 59492400.0,
|
|
"step": 30415
|
|
},
|
|
{
|
|
"entropy": 5.9337300777435305,
|
|
"epoch": 3.040785724996251,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00040892070066987966,
|
|
"loss": 5.5765,
|
|
"mean_token_accuracy": 0.1900107368826866,
|
|
"num_tokens": 59503635.0,
|
|
"step": 30420
|
|
},
|
|
{
|
|
"entropy": 5.886321640014648,
|
|
"epoch": 3.04128555005748,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00040889202010495595,
|
|
"loss": 5.3851,
|
|
"mean_token_accuracy": 0.199214106798172,
|
|
"num_tokens": 59513550.0,
|
|
"step": 30425
|
|
},
|
|
{
|
|
"entropy": 6.022853803634644,
|
|
"epoch": 3.0417853751187085,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004088633361713436,
|
|
"loss": 5.5735,
|
|
"mean_token_accuracy": 0.19244534373283387,
|
|
"num_tokens": 59523286.0,
|
|
"step": 30430
|
|
},
|
|
{
|
|
"entropy": 5.94807767868042,
|
|
"epoch": 3.042285200179937,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00040883464886976414,
|
|
"loss": 5.5044,
|
|
"mean_token_accuracy": 0.18333283364772796,
|
|
"num_tokens": 59533976.0,
|
|
"step": 30435
|
|
},
|
|
{
|
|
"entropy": 5.954601240158081,
|
|
"epoch": 3.0427850252411655,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004088059582009393,
|
|
"loss": 5.4401,
|
|
"mean_token_accuracy": 0.19942069351673125,
|
|
"num_tokens": 59542796.0,
|
|
"step": 30440
|
|
},
|
|
{
|
|
"entropy": 5.989485788345337,
|
|
"epoch": 3.043284850302394,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.000408777264165591,
|
|
"loss": 5.6221,
|
|
"mean_token_accuracy": 0.1760165885090828,
|
|
"num_tokens": 59553213.0,
|
|
"step": 30445
|
|
},
|
|
{
|
|
"entropy": 5.919064855575561,
|
|
"epoch": 3.043784675363623,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00040874856676444116,
|
|
"loss": 5.4608,
|
|
"mean_token_accuracy": 0.1908688485622406,
|
|
"num_tokens": 59562136.0,
|
|
"step": 30450
|
|
},
|
|
{
|
|
"entropy": 6.014276361465454,
|
|
"epoch": 3.044284500424851,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00040871986599821177,
|
|
"loss": 5.5861,
|
|
"mean_token_accuracy": 0.18083301931619644,
|
|
"num_tokens": 59572578.0,
|
|
"step": 30455
|
|
},
|
|
{
|
|
"entropy": 6.050519180297852,
|
|
"epoch": 3.04478432548608,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004086911618676251,
|
|
"loss": 5.5508,
|
|
"mean_token_accuracy": 0.17848475873470307,
|
|
"num_tokens": 59581976.0,
|
|
"step": 30460
|
|
},
|
|
{
|
|
"entropy": 5.980159759521484,
|
|
"epoch": 3.0452841505473085,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000408662454373403,
|
|
"loss": 5.4884,
|
|
"mean_token_accuracy": 0.1965405151247978,
|
|
"num_tokens": 59591879.0,
|
|
"step": 30465
|
|
},
|
|
{
|
|
"entropy": 6.003866195678711,
|
|
"epoch": 3.045783975608537,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000408633743516268,
|
|
"loss": 5.5636,
|
|
"mean_token_accuracy": 0.18985571563243867,
|
|
"num_tokens": 59601534.0,
|
|
"step": 30470
|
|
},
|
|
{
|
|
"entropy": 5.94048810005188,
|
|
"epoch": 3.0462838006697655,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00040860502929694246,
|
|
"loss": 5.482,
|
|
"mean_token_accuracy": 0.1920858934521675,
|
|
"num_tokens": 59611349.0,
|
|
"step": 30475
|
|
},
|
|
{
|
|
"entropy": 5.9560974597930905,
|
|
"epoch": 3.046783625730994,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00040857631171614873,
|
|
"loss": 5.5207,
|
|
"mean_token_accuracy": 0.18684811592102052,
|
|
"num_tokens": 59621743.0,
|
|
"step": 30480
|
|
},
|
|
{
|
|
"entropy": 6.023742580413819,
|
|
"epoch": 3.047283450792223,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00040854759077460934,
|
|
"loss": 5.4876,
|
|
"mean_token_accuracy": 0.19156688898801805,
|
|
"num_tokens": 59630967.0,
|
|
"step": 30485
|
|
},
|
|
{
|
|
"entropy": 6.007992458343506,
|
|
"epoch": 3.047783275853451,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00040851886647304703,
|
|
"loss": 5.4258,
|
|
"mean_token_accuracy": 0.19440371543169022,
|
|
"num_tokens": 59640388.0,
|
|
"step": 30490
|
|
},
|
|
{
|
|
"entropy": 5.898862218856811,
|
|
"epoch": 3.04828310091468,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004084901388121843,
|
|
"loss": 5.485,
|
|
"mean_token_accuracy": 0.1848222255706787,
|
|
"num_tokens": 59649720.0,
|
|
"step": 30495
|
|
},
|
|
{
|
|
"entropy": 5.868726539611816,
|
|
"epoch": 3.0487829259759085,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00040846140779274406,
|
|
"loss": 5.4456,
|
|
"mean_token_accuracy": 0.1968520849943161,
|
|
"num_tokens": 59659336.0,
|
|
"step": 30500
|
|
},
|
|
{
|
|
"entropy": 5.980198717117309,
|
|
"epoch": 3.049282751037137,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00040843267341544913,
|
|
"loss": 5.5685,
|
|
"mean_token_accuracy": 0.18037995994091033,
|
|
"num_tokens": 59669376.0,
|
|
"step": 30505
|
|
},
|
|
{
|
|
"entropy": 5.9805513381958,
|
|
"epoch": 3.0497825760983654,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00040840393568102246,
|
|
"loss": 5.4557,
|
|
"mean_token_accuracy": 0.19103697687387466,
|
|
"num_tokens": 59679180.0,
|
|
"step": 30510
|
|
},
|
|
{
|
|
"entropy": 5.963145208358765,
|
|
"epoch": 3.050282401159594,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004083751945901871,
|
|
"loss": 5.4788,
|
|
"mean_token_accuracy": 0.19516584724187852,
|
|
"num_tokens": 59689427.0,
|
|
"step": 30515
|
|
},
|
|
{
|
|
"entropy": 5.951128816604614,
|
|
"epoch": 3.050782226220823,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00040834645014366623,
|
|
"loss": 5.4325,
|
|
"mean_token_accuracy": 0.19055657237768173,
|
|
"num_tokens": 59698586.0,
|
|
"step": 30520
|
|
},
|
|
{
|
|
"entropy": 5.947955656051636,
|
|
"epoch": 3.051282051282051,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004083177023421829,
|
|
"loss": 5.4925,
|
|
"mean_token_accuracy": 0.19167300760746003,
|
|
"num_tokens": 59707927.0,
|
|
"step": 30525
|
|
},
|
|
{
|
|
"entropy": 5.945365858078003,
|
|
"epoch": 3.05178187634328,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004082889511864606,
|
|
"loss": 5.5599,
|
|
"mean_token_accuracy": 0.18759994357824325,
|
|
"num_tokens": 59718563.0,
|
|
"step": 30530
|
|
},
|
|
{
|
|
"entropy": 5.881500387191773,
|
|
"epoch": 3.0522817014045085,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00040826019667722244,
|
|
"loss": 5.2672,
|
|
"mean_token_accuracy": 0.2084543600678444,
|
|
"num_tokens": 59728718.0,
|
|
"step": 30535
|
|
},
|
|
{
|
|
"entropy": 5.961279058456421,
|
|
"epoch": 3.052781526465737,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004082314388151921,
|
|
"loss": 5.4657,
|
|
"mean_token_accuracy": 0.1925609290599823,
|
|
"num_tokens": 59738515.0,
|
|
"step": 30540
|
|
},
|
|
{
|
|
"entropy": 5.9347375392913815,
|
|
"epoch": 3.0532813515269654,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004082026776010931,
|
|
"loss": 5.5548,
|
|
"mean_token_accuracy": 0.1860482722520828,
|
|
"num_tokens": 59748606.0,
|
|
"step": 30545
|
|
},
|
|
{
|
|
"entropy": 5.9604943752288815,
|
|
"epoch": 3.053781176588194,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004081739130356489,
|
|
"loss": 5.4731,
|
|
"mean_token_accuracy": 0.19228885918855668,
|
|
"num_tokens": 59757454.0,
|
|
"step": 30550
|
|
},
|
|
{
|
|
"entropy": 5.96630744934082,
|
|
"epoch": 3.054281001649423,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00040814514511958335,
|
|
"loss": 5.4755,
|
|
"mean_token_accuracy": 0.1872725173830986,
|
|
"num_tokens": 59767500.0,
|
|
"step": 30555
|
|
},
|
|
{
|
|
"entropy": 5.96850848197937,
|
|
"epoch": 3.054780826710651,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00040811637385362024,
|
|
"loss": 5.5075,
|
|
"mean_token_accuracy": 0.19219366908073426,
|
|
"num_tokens": 59776663.0,
|
|
"step": 30560
|
|
},
|
|
{
|
|
"entropy": 5.9438190937042235,
|
|
"epoch": 3.05528065177188,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004080875992384834,
|
|
"loss": 5.4341,
|
|
"mean_token_accuracy": 0.1878676414489746,
|
|
"num_tokens": 59787075.0,
|
|
"step": 30565
|
|
},
|
|
{
|
|
"entropy": 5.894822597503662,
|
|
"epoch": 3.0557804768331085,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004080588212748968,
|
|
"loss": 5.3779,
|
|
"mean_token_accuracy": 0.20409613847732544,
|
|
"num_tokens": 59796385.0,
|
|
"step": 30570
|
|
},
|
|
{
|
|
"entropy": 5.9209987163543705,
|
|
"epoch": 3.056280301894337,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00040803003996358445,
|
|
"loss": 5.4281,
|
|
"mean_token_accuracy": 0.19748440086841584,
|
|
"num_tokens": 59805623.0,
|
|
"step": 30575
|
|
},
|
|
{
|
|
"entropy": 5.948598384857178,
|
|
"epoch": 3.0567801269555654,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00040800125530527064,
|
|
"loss": 5.5349,
|
|
"mean_token_accuracy": 0.17861153334379196,
|
|
"num_tokens": 59815041.0,
|
|
"step": 30580
|
|
},
|
|
{
|
|
"entropy": 5.919707155227661,
|
|
"epoch": 3.057279952016794,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00040797246730067937,
|
|
"loss": 5.3935,
|
|
"mean_token_accuracy": 0.201283760368824,
|
|
"num_tokens": 59824699.0,
|
|
"step": 30585
|
|
},
|
|
{
|
|
"entropy": 5.9655204772949215,
|
|
"epoch": 3.057779777078023,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004079436759505351,
|
|
"loss": 5.4704,
|
|
"mean_token_accuracy": 0.19429030865430832,
|
|
"num_tokens": 59834074.0,
|
|
"step": 30590
|
|
},
|
|
{
|
|
"entropy": 5.9388854026794435,
|
|
"epoch": 3.058279602139251,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004079148812555621,
|
|
"loss": 5.5353,
|
|
"mean_token_accuracy": 0.19175899922847747,
|
|
"num_tokens": 59844681.0,
|
|
"step": 30595
|
|
},
|
|
{
|
|
"entropy": 5.924275350570679,
|
|
"epoch": 3.05877942720048,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00040788608321648496,
|
|
"loss": 5.417,
|
|
"mean_token_accuracy": 0.20000615268945693,
|
|
"num_tokens": 59854033.0,
|
|
"step": 30600
|
|
},
|
|
{
|
|
"entropy": 6.009700202941895,
|
|
"epoch": 3.0592792522617085,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004078572818340281,
|
|
"loss": 5.597,
|
|
"mean_token_accuracy": 0.18517320305109025,
|
|
"num_tokens": 59864191.0,
|
|
"step": 30605
|
|
},
|
|
{
|
|
"entropy": 5.974575185775757,
|
|
"epoch": 3.059779077322937,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00040782847710891623,
|
|
"loss": 5.5038,
|
|
"mean_token_accuracy": 0.1922592893242836,
|
|
"num_tokens": 59873266.0,
|
|
"step": 30610
|
|
},
|
|
{
|
|
"entropy": 6.001249837875366,
|
|
"epoch": 3.0602789023841654,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00040779966904187407,
|
|
"loss": 5.5481,
|
|
"mean_token_accuracy": 0.18743086457252503,
|
|
"num_tokens": 59883050.0,
|
|
"step": 30615
|
|
},
|
|
{
|
|
"entropy": 5.992725086212158,
|
|
"epoch": 3.060778727445394,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00040777085763362634,
|
|
"loss": 5.4615,
|
|
"mean_token_accuracy": 0.19090454876422883,
|
|
"num_tokens": 59892897.0,
|
|
"step": 30620
|
|
},
|
|
{
|
|
"entropy": 6.0052801132202145,
|
|
"epoch": 3.061278552506623,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00040774204288489805,
|
|
"loss": 5.5389,
|
|
"mean_token_accuracy": 0.18565759658813477,
|
|
"num_tokens": 59902682.0,
|
|
"step": 30625
|
|
},
|
|
{
|
|
"entropy": 5.999075984954834,
|
|
"epoch": 3.061778377567851,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004077132247964142,
|
|
"loss": 5.5596,
|
|
"mean_token_accuracy": 0.18907654881477357,
|
|
"num_tokens": 59913176.0,
|
|
"step": 30630
|
|
},
|
|
{
|
|
"entropy": 5.917710638046264,
|
|
"epoch": 3.06227820262908,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00040768440336889965,
|
|
"loss": 5.4254,
|
|
"mean_token_accuracy": 0.19556996822357178,
|
|
"num_tokens": 59924238.0,
|
|
"step": 30635
|
|
},
|
|
{
|
|
"entropy": 5.9969617366790775,
|
|
"epoch": 3.0627780276903085,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004076555786030797,
|
|
"loss": 5.5089,
|
|
"mean_token_accuracy": 0.19488309621810912,
|
|
"num_tokens": 59933766.0,
|
|
"step": 30640
|
|
},
|
|
{
|
|
"entropy": 6.072267627716064,
|
|
"epoch": 3.063277852751537,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004076267504996795,
|
|
"loss": 5.5451,
|
|
"mean_token_accuracy": 0.18544900566339492,
|
|
"num_tokens": 59944008.0,
|
|
"step": 30645
|
|
},
|
|
{
|
|
"entropy": 6.002575302124024,
|
|
"epoch": 3.0637776778127654,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004075979190594244,
|
|
"loss": 5.5218,
|
|
"mean_token_accuracy": 0.18215171992778778,
|
|
"num_tokens": 59953882.0,
|
|
"step": 30650
|
|
},
|
|
{
|
|
"entropy": 5.990571975708008,
|
|
"epoch": 3.064277502873994,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00040756908428303984,
|
|
"loss": 5.6151,
|
|
"mean_token_accuracy": 0.18257615864276885,
|
|
"num_tokens": 59964271.0,
|
|
"step": 30655
|
|
},
|
|
{
|
|
"entropy": 6.072707796096802,
|
|
"epoch": 3.064777327935223,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00040754024617125115,
|
|
"loss": 5.454,
|
|
"mean_token_accuracy": 0.2010833889245987,
|
|
"num_tokens": 59975376.0,
|
|
"step": 30660
|
|
},
|
|
{
|
|
"entropy": 5.942374610900879,
|
|
"epoch": 3.065277152996451,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000407511404724784,
|
|
"loss": 5.4263,
|
|
"mean_token_accuracy": 0.19222953766584397,
|
|
"num_tokens": 59984200.0,
|
|
"step": 30665
|
|
},
|
|
{
|
|
"entropy": 5.8760051250457765,
|
|
"epoch": 3.06577697805768,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000407482559944364,
|
|
"loss": 5.4232,
|
|
"mean_token_accuracy": 0.19749486148357392,
|
|
"num_tokens": 59994289.0,
|
|
"step": 30670
|
|
},
|
|
{
|
|
"entropy": 5.956891441345215,
|
|
"epoch": 3.0662768031189085,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004074537118307169,
|
|
"loss": 5.5031,
|
|
"mean_token_accuracy": 0.19244490414857865,
|
|
"num_tokens": 60004218.0,
|
|
"step": 30675
|
|
},
|
|
{
|
|
"entropy": 5.9315962314605715,
|
|
"epoch": 3.0667766281801367,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004074248603845684,
|
|
"loss": 5.4085,
|
|
"mean_token_accuracy": 0.19878094345331193,
|
|
"num_tokens": 60012792.0,
|
|
"step": 30680
|
|
},
|
|
{
|
|
"entropy": 5.952469396591186,
|
|
"epoch": 3.0672764532413654,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00040739600560664457,
|
|
"loss": 5.4617,
|
|
"mean_token_accuracy": 0.19447196274995804,
|
|
"num_tokens": 60023022.0,
|
|
"step": 30685
|
|
},
|
|
{
|
|
"entropy": 5.980071306228638,
|
|
"epoch": 3.067776278302594,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00040736714749767136,
|
|
"loss": 5.4889,
|
|
"mean_token_accuracy": 0.19012262672185898,
|
|
"num_tokens": 60032379.0,
|
|
"step": 30690
|
|
},
|
|
{
|
|
"entropy": 5.8956708908081055,
|
|
"epoch": 3.068276103363823,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004073382860583747,
|
|
"loss": 5.4501,
|
|
"mean_token_accuracy": 0.19732764959335328,
|
|
"num_tokens": 60041851.0,
|
|
"step": 30695
|
|
},
|
|
{
|
|
"entropy": 6.0154260158538815,
|
|
"epoch": 3.068775928425051,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004073094212894809,
|
|
"loss": 5.6143,
|
|
"mean_token_accuracy": 0.19289949983358384,
|
|
"num_tokens": 60051648.0,
|
|
"step": 30700
|
|
},
|
|
{
|
|
"entropy": 6.028196239471436,
|
|
"epoch": 3.06927575348628,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000407280553191716,
|
|
"loss": 5.523,
|
|
"mean_token_accuracy": 0.19070162177085875,
|
|
"num_tokens": 60061479.0,
|
|
"step": 30705
|
|
},
|
|
{
|
|
"entropy": 5.94948410987854,
|
|
"epoch": 3.0697755785475085,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004072516817658065,
|
|
"loss": 5.4197,
|
|
"mean_token_accuracy": 0.20236573219299317,
|
|
"num_tokens": 60070378.0,
|
|
"step": 30710
|
|
},
|
|
{
|
|
"entropy": 5.90979118347168,
|
|
"epoch": 3.0702754036087367,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00040722280701247865,
|
|
"loss": 5.4616,
|
|
"mean_token_accuracy": 0.1982162743806839,
|
|
"num_tokens": 60079911.0,
|
|
"step": 30715
|
|
},
|
|
{
|
|
"entropy": 6.0716477394104,
|
|
"epoch": 3.0707752286699654,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00040719392893245903,
|
|
"loss": 5.6281,
|
|
"mean_token_accuracy": 0.17757324874401093,
|
|
"num_tokens": 60089850.0,
|
|
"step": 30720
|
|
},
|
|
{
|
|
"entropy": 5.933743619918824,
|
|
"epoch": 3.071275053731194,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004071650475264742,
|
|
"loss": 5.4162,
|
|
"mean_token_accuracy": 0.19839651584625245,
|
|
"num_tokens": 60100370.0,
|
|
"step": 30725
|
|
},
|
|
{
|
|
"entropy": 5.959923458099365,
|
|
"epoch": 3.071774878792423,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00040713616279525075,
|
|
"loss": 5.5033,
|
|
"mean_token_accuracy": 0.1938125491142273,
|
|
"num_tokens": 60109331.0,
|
|
"step": 30730
|
|
},
|
|
{
|
|
"entropy": 6.020395374298095,
|
|
"epoch": 3.072274703853651,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00040710727473951546,
|
|
"loss": 5.498,
|
|
"mean_token_accuracy": 0.18882239162921904,
|
|
"num_tokens": 60119053.0,
|
|
"step": 30735
|
|
},
|
|
{
|
|
"entropy": 6.002504587173462,
|
|
"epoch": 3.07277452891488,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004070783833599951,
|
|
"loss": 5.5537,
|
|
"mean_token_accuracy": 0.1924801528453827,
|
|
"num_tokens": 60129123.0,
|
|
"step": 30740
|
|
},
|
|
{
|
|
"entropy": 5.991722249984742,
|
|
"epoch": 3.0732743539761085,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004070494886574166,
|
|
"loss": 5.5369,
|
|
"mean_token_accuracy": 0.1900422304868698,
|
|
"num_tokens": 60138848.0,
|
|
"step": 30745
|
|
},
|
|
{
|
|
"entropy": 5.906140756607056,
|
|
"epoch": 3.0737741790373367,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000407020590632507,
|
|
"loss": 5.435,
|
|
"mean_token_accuracy": 0.19959826618433,
|
|
"num_tokens": 60148604.0,
|
|
"step": 30750
|
|
},
|
|
{
|
|
"entropy": 5.948051023483276,
|
|
"epoch": 3.0742740040985654,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004069916892859933,
|
|
"loss": 5.444,
|
|
"mean_token_accuracy": 0.18887707442045212,
|
|
"num_tokens": 60159958.0,
|
|
"step": 30755
|
|
},
|
|
{
|
|
"entropy": 5.9562770366668705,
|
|
"epoch": 3.074773829159794,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004069627846186026,
|
|
"loss": 5.4694,
|
|
"mean_token_accuracy": 0.19561128914356232,
|
|
"num_tokens": 60169110.0,
|
|
"step": 30760
|
|
},
|
|
{
|
|
"entropy": 5.900517082214355,
|
|
"epoch": 3.075273654221023,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00040693387663106223,
|
|
"loss": 5.4065,
|
|
"mean_token_accuracy": 0.20057374984025955,
|
|
"num_tokens": 60177917.0,
|
|
"step": 30765
|
|
},
|
|
{
|
|
"entropy": 5.98724045753479,
|
|
"epoch": 3.075773479282251,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004069049653240996,
|
|
"loss": 5.5409,
|
|
"mean_token_accuracy": 0.18784624934196473,
|
|
"num_tokens": 60187086.0,
|
|
"step": 30770
|
|
},
|
|
{
|
|
"entropy": 6.01384425163269,
|
|
"epoch": 3.07627330434348,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004068760506984418,
|
|
"loss": 5.5501,
|
|
"mean_token_accuracy": 0.18294054716825486,
|
|
"num_tokens": 60196457.0,
|
|
"step": 30775
|
|
},
|
|
{
|
|
"entropy": 6.0061054706573485,
|
|
"epoch": 3.0767731294047085,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004068471327548166,
|
|
"loss": 5.4927,
|
|
"mean_token_accuracy": 0.19099101126194,
|
|
"num_tokens": 60205160.0,
|
|
"step": 30780
|
|
},
|
|
{
|
|
"entropy": 6.056540012359619,
|
|
"epoch": 3.0772729544659367,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00040681821149395146,
|
|
"loss": 5.4873,
|
|
"mean_token_accuracy": 0.18653594553470612,
|
|
"num_tokens": 60214706.0,
|
|
"step": 30785
|
|
},
|
|
{
|
|
"entropy": 5.913959264755249,
|
|
"epoch": 3.0777727795271654,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00040678928691657395,
|
|
"loss": 5.4452,
|
|
"mean_token_accuracy": 0.1876579135656357,
|
|
"num_tokens": 60224741.0,
|
|
"step": 30790
|
|
},
|
|
{
|
|
"entropy": 5.977076148986816,
|
|
"epoch": 3.078272604588394,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00040676035902341195,
|
|
"loss": 5.5461,
|
|
"mean_token_accuracy": 0.19119371175765992,
|
|
"num_tokens": 60233666.0,
|
|
"step": 30795
|
|
},
|
|
{
|
|
"entropy": 6.00071234703064,
|
|
"epoch": 3.078772429649623,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004067314278151933,
|
|
"loss": 5.5275,
|
|
"mean_token_accuracy": 0.1867539942264557,
|
|
"num_tokens": 60244403.0,
|
|
"step": 30800
|
|
},
|
|
{
|
|
"entropy": 6.0108459949493405,
|
|
"epoch": 3.079272254710851,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00040670249329264577,
|
|
"loss": 5.5171,
|
|
"mean_token_accuracy": 0.19027844816446304,
|
|
"num_tokens": 60254339.0,
|
|
"step": 30805
|
|
},
|
|
{
|
|
"entropy": 5.991326999664307,
|
|
"epoch": 3.07977207977208,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004066735554564973,
|
|
"loss": 5.5596,
|
|
"mean_token_accuracy": 0.19335440546274185,
|
|
"num_tokens": 60264740.0,
|
|
"step": 30810
|
|
},
|
|
{
|
|
"entropy": 6.007949686050415,
|
|
"epoch": 3.0802719048333085,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004066446143074762,
|
|
"loss": 5.5238,
|
|
"mean_token_accuracy": 0.19301951676607132,
|
|
"num_tokens": 60273307.0,
|
|
"step": 30815
|
|
},
|
|
{
|
|
"entropy": 5.956336641311646,
|
|
"epoch": 3.0807717298945367,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004066156698463104,
|
|
"loss": 5.5093,
|
|
"mean_token_accuracy": 0.19119404703378678,
|
|
"num_tokens": 60283734.0,
|
|
"step": 30820
|
|
},
|
|
{
|
|
"entropy": 5.978907918930053,
|
|
"epoch": 3.0812715549557654,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004065867220737282,
|
|
"loss": 5.5205,
|
|
"mean_token_accuracy": 0.19013577550649643,
|
|
"num_tokens": 60294900.0,
|
|
"step": 30825
|
|
},
|
|
{
|
|
"entropy": 5.937345266342163,
|
|
"epoch": 3.081771380016994,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00040655777099045794,
|
|
"loss": 5.4725,
|
|
"mean_token_accuracy": 0.18940452188253404,
|
|
"num_tokens": 60305214.0,
|
|
"step": 30830
|
|
},
|
|
{
|
|
"entropy": 6.041521263122559,
|
|
"epoch": 3.082271205078223,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004065288165972281,
|
|
"loss": 5.4878,
|
|
"mean_token_accuracy": 0.2021217465400696,
|
|
"num_tokens": 60314563.0,
|
|
"step": 30835
|
|
},
|
|
{
|
|
"entropy": 6.01637897491455,
|
|
"epoch": 3.082771030139451,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000406499858894767,
|
|
"loss": 5.4865,
|
|
"mean_token_accuracy": 0.19325643181800842,
|
|
"num_tokens": 60324510.0,
|
|
"step": 30840
|
|
},
|
|
{
|
|
"entropy": 6.032748651504517,
|
|
"epoch": 3.08327085520068,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004064708978838033,
|
|
"loss": 5.6143,
|
|
"mean_token_accuracy": 0.182871276140213,
|
|
"num_tokens": 60335679.0,
|
|
"step": 30845
|
|
},
|
|
{
|
|
"entropy": 5.910690546035767,
|
|
"epoch": 3.0837706802619085,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00040644193356506565,
|
|
"loss": 5.3627,
|
|
"mean_token_accuracy": 0.19962731897830963,
|
|
"num_tokens": 60345006.0,
|
|
"step": 30850
|
|
},
|
|
{
|
|
"entropy": 5.9682004928588865,
|
|
"epoch": 3.0842705053231367,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004064129659392828,
|
|
"loss": 5.5229,
|
|
"mean_token_accuracy": 0.18682438135147095,
|
|
"num_tokens": 60354411.0,
|
|
"step": 30855
|
|
},
|
|
{
|
|
"entropy": 5.949279022216797,
|
|
"epoch": 3.0847703303843654,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004063839950071835,
|
|
"loss": 5.451,
|
|
"mean_token_accuracy": 0.19366564303636552,
|
|
"num_tokens": 60365347.0,
|
|
"step": 30860
|
|
},
|
|
{
|
|
"entropy": 5.868692207336426,
|
|
"epoch": 3.085270155445594,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00040635502076949665,
|
|
"loss": 5.4581,
|
|
"mean_token_accuracy": 0.19763658493757247,
|
|
"num_tokens": 60375197.0,
|
|
"step": 30865
|
|
},
|
|
{
|
|
"entropy": 5.899807071685791,
|
|
"epoch": 3.0857699805068224,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00040632604322695135,
|
|
"loss": 5.4477,
|
|
"mean_token_accuracy": 0.201005257666111,
|
|
"num_tokens": 60384380.0,
|
|
"step": 30870
|
|
},
|
|
{
|
|
"entropy": 5.900918960571289,
|
|
"epoch": 3.086269805568051,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004062970623802766,
|
|
"loss": 5.4175,
|
|
"mean_token_accuracy": 0.2000516176223755,
|
|
"num_tokens": 60393990.0,
|
|
"step": 30875
|
|
},
|
|
{
|
|
"entropy": 5.988381433486938,
|
|
"epoch": 3.08676963062928,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004062680782302015,
|
|
"loss": 5.4997,
|
|
"mean_token_accuracy": 0.19372162371873855,
|
|
"num_tokens": 60402835.0,
|
|
"step": 30880
|
|
},
|
|
{
|
|
"entropy": 5.972681188583374,
|
|
"epoch": 3.0872694556905085,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00040623909077745535,
|
|
"loss": 5.4502,
|
|
"mean_token_accuracy": 0.19762299209833145,
|
|
"num_tokens": 60412427.0,
|
|
"step": 30885
|
|
},
|
|
{
|
|
"entropy": 6.0708390235900875,
|
|
"epoch": 3.0877692807517367,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004062101000227674,
|
|
"loss": 5.6251,
|
|
"mean_token_accuracy": 0.18708744943141936,
|
|
"num_tokens": 60424064.0,
|
|
"step": 30890
|
|
},
|
|
{
|
|
"entropy": 6.028488063812256,
|
|
"epoch": 3.0882691058129654,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004061811059668672,
|
|
"loss": 5.6357,
|
|
"mean_token_accuracy": 0.18061028122901918,
|
|
"num_tokens": 60434182.0,
|
|
"step": 30895
|
|
},
|
|
{
|
|
"entropy": 5.994523429870606,
|
|
"epoch": 3.088768930874194,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004061521086104841,
|
|
"loss": 5.491,
|
|
"mean_token_accuracy": 0.18977169543504716,
|
|
"num_tokens": 60444138.0,
|
|
"step": 30900
|
|
},
|
|
{
|
|
"entropy": 6.005541849136352,
|
|
"epoch": 3.0892687559354224,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00040612310795434765,
|
|
"loss": 5.472,
|
|
"mean_token_accuracy": 0.18880541175603865,
|
|
"num_tokens": 60452823.0,
|
|
"step": 30905
|
|
},
|
|
{
|
|
"entropy": 5.922002696990967,
|
|
"epoch": 3.089768580996651,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.00040609410399918754,
|
|
"loss": 5.4705,
|
|
"mean_token_accuracy": 0.1890873894095421,
|
|
"num_tokens": 60462998.0,
|
|
"step": 30910
|
|
},
|
|
{
|
|
"entropy": 5.925285911560058,
|
|
"epoch": 3.09026840605788,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00040606509674573354,
|
|
"loss": 5.5602,
|
|
"mean_token_accuracy": 0.1827355608344078,
|
|
"num_tokens": 60472204.0,
|
|
"step": 30915
|
|
},
|
|
{
|
|
"entropy": 5.9126485824584964,
|
|
"epoch": 3.0907682311191085,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004060360861947155,
|
|
"loss": 5.4397,
|
|
"mean_token_accuracy": 0.19637588113546373,
|
|
"num_tokens": 60481848.0,
|
|
"step": 30920
|
|
},
|
|
{
|
|
"entropy": 5.964174747467041,
|
|
"epoch": 3.0912680561803367,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00040600707234686315,
|
|
"loss": 5.4832,
|
|
"mean_token_accuracy": 0.18880588859319686,
|
|
"num_tokens": 60491890.0,
|
|
"step": 30925
|
|
},
|
|
{
|
|
"entropy": 5.95098123550415,
|
|
"epoch": 3.0917678812415654,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00040597805520290657,
|
|
"loss": 5.4603,
|
|
"mean_token_accuracy": 0.19208641052246095,
|
|
"num_tokens": 60501617.0,
|
|
"step": 30930
|
|
},
|
|
{
|
|
"entropy": 5.927120304107666,
|
|
"epoch": 3.092267706302794,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004059490347635759,
|
|
"loss": 5.4957,
|
|
"mean_token_accuracy": 0.1882168471813202,
|
|
"num_tokens": 60511699.0,
|
|
"step": 30935
|
|
},
|
|
{
|
|
"entropy": 6.066510438919067,
|
|
"epoch": 3.0927675313640224,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00040592001102960116,
|
|
"loss": 5.6411,
|
|
"mean_token_accuracy": 0.1779520556330681,
|
|
"num_tokens": 60521631.0,
|
|
"step": 30940
|
|
},
|
|
{
|
|
"entropy": 5.955221033096313,
|
|
"epoch": 3.093267356425251,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004058909840017126,
|
|
"loss": 5.527,
|
|
"mean_token_accuracy": 0.1863068550825119,
|
|
"num_tokens": 60531760.0,
|
|
"step": 30945
|
|
},
|
|
{
|
|
"entropy": 5.9979040145874025,
|
|
"epoch": 3.09376718148648,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004058619536806407,
|
|
"loss": 5.5608,
|
|
"mean_token_accuracy": 0.18560519814491272,
|
|
"num_tokens": 60542249.0,
|
|
"step": 30950
|
|
},
|
|
{
|
|
"entropy": 5.983110046386718,
|
|
"epoch": 3.0942670065477085,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004058329200671155,
|
|
"loss": 5.5108,
|
|
"mean_token_accuracy": 0.18302125185728074,
|
|
"num_tokens": 60552638.0,
|
|
"step": 30955
|
|
},
|
|
{
|
|
"entropy": 6.037380886077881,
|
|
"epoch": 3.0947668316089367,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00040580388316186785,
|
|
"loss": 5.5565,
|
|
"mean_token_accuracy": 0.18930567800998688,
|
|
"num_tokens": 60562928.0,
|
|
"step": 30960
|
|
},
|
|
{
|
|
"entropy": 6.006596660614013,
|
|
"epoch": 3.0952666566701654,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004057748429656281,
|
|
"loss": 5.5463,
|
|
"mean_token_accuracy": 0.19197211563587188,
|
|
"num_tokens": 60573398.0,
|
|
"step": 30965
|
|
},
|
|
{
|
|
"entropy": 5.940107154846191,
|
|
"epoch": 3.095766481731394,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.000405745799479127,
|
|
"loss": 5.5101,
|
|
"mean_token_accuracy": 0.19477781504392624,
|
|
"num_tokens": 60582540.0,
|
|
"step": 30970
|
|
},
|
|
{
|
|
"entropy": 5.991557455062866,
|
|
"epoch": 3.0962663067926224,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004057167527030952,
|
|
"loss": 5.4458,
|
|
"mean_token_accuracy": 0.1967433959245682,
|
|
"num_tokens": 60592111.0,
|
|
"step": 30975
|
|
},
|
|
{
|
|
"entropy": 5.959309005737305,
|
|
"epoch": 3.096766131853851,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00040568770263826355,
|
|
"loss": 5.5014,
|
|
"mean_token_accuracy": 0.18984022438526155,
|
|
"num_tokens": 60601687.0,
|
|
"step": 30980
|
|
},
|
|
{
|
|
"entropy": 5.966148376464844,
|
|
"epoch": 3.0972659569150798,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004056586492853629,
|
|
"loss": 5.5421,
|
|
"mean_token_accuracy": 0.1908128097653389,
|
|
"num_tokens": 60611021.0,
|
|
"step": 30985
|
|
},
|
|
{
|
|
"entropy": 5.986058378219605,
|
|
"epoch": 3.0977657819763085,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004056295926451243,
|
|
"loss": 5.5802,
|
|
"mean_token_accuracy": 0.18826348334550858,
|
|
"num_tokens": 60620863.0,
|
|
"step": 30990
|
|
},
|
|
{
|
|
"entropy": 5.9453075408935545,
|
|
"epoch": 3.0982656070375367,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00040560053271827866,
|
|
"loss": 5.4613,
|
|
"mean_token_accuracy": 0.18835380524396897,
|
|
"num_tokens": 60630483.0,
|
|
"step": 30995
|
|
},
|
|
{
|
|
"entropy": 5.935856056213379,
|
|
"epoch": 3.0987654320987654,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00040557146950555734,
|
|
"loss": 5.494,
|
|
"mean_token_accuracy": 0.18994212597608567,
|
|
"num_tokens": 60640594.0,
|
|
"step": 31000
|
|
},
|
|
{
|
|
"entropy": 5.881002140045166,
|
|
"epoch": 3.099265257159994,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004055424030076914,
|
|
"loss": 5.4167,
|
|
"mean_token_accuracy": 0.1970501273870468,
|
|
"num_tokens": 60651162.0,
|
|
"step": 31005
|
|
},
|
|
{
|
|
"entropy": 5.991159534454345,
|
|
"epoch": 3.0997650822212224,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00040551333322541225,
|
|
"loss": 5.5353,
|
|
"mean_token_accuracy": 0.1924537807703018,
|
|
"num_tokens": 60661467.0,
|
|
"step": 31010
|
|
},
|
|
{
|
|
"entropy": 6.028145360946655,
|
|
"epoch": 3.100264907282451,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004054842601594512,
|
|
"loss": 5.5344,
|
|
"mean_token_accuracy": 0.18495346009731292,
|
|
"num_tokens": 60672395.0,
|
|
"step": 31015
|
|
},
|
|
{
|
|
"entropy": 6.015804862976074,
|
|
"epoch": 3.1007647323436798,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00040545518381053964,
|
|
"loss": 5.5497,
|
|
"mean_token_accuracy": 0.18404598981142045,
|
|
"num_tokens": 60680632.0,
|
|
"step": 31020
|
|
},
|
|
{
|
|
"entropy": 5.964470863342285,
|
|
"epoch": 3.1012645574049085,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00040542610417940926,
|
|
"loss": 5.5547,
|
|
"mean_token_accuracy": 0.18241467028856279,
|
|
"num_tokens": 60692228.0,
|
|
"step": 31025
|
|
},
|
|
{
|
|
"entropy": 6.016748237609863,
|
|
"epoch": 3.1017643824661367,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004053970212667917,
|
|
"loss": 5.4763,
|
|
"mean_token_accuracy": 0.1913584589958191,
|
|
"num_tokens": 60701287.0,
|
|
"step": 31030
|
|
},
|
|
{
|
|
"entropy": 5.987577199935913,
|
|
"epoch": 3.1022642075273654,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004053679350734186,
|
|
"loss": 5.5518,
|
|
"mean_token_accuracy": 0.19211607426404953,
|
|
"num_tokens": 60713267.0,
|
|
"step": 31035
|
|
},
|
|
{
|
|
"entropy": 5.915355539321899,
|
|
"epoch": 3.102764032588594,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00040533884560002196,
|
|
"loss": 5.4073,
|
|
"mean_token_accuracy": 0.1926419749855995,
|
|
"num_tokens": 60722509.0,
|
|
"step": 31040
|
|
},
|
|
{
|
|
"entropy": 5.919064044952393,
|
|
"epoch": 3.1032638576498224,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00040530975284733327,
|
|
"loss": 5.4966,
|
|
"mean_token_accuracy": 0.19005477130413057,
|
|
"num_tokens": 60732916.0,
|
|
"step": 31045
|
|
},
|
|
{
|
|
"entropy": 6.058548498153686,
|
|
"epoch": 3.103763682711051,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004052806568160849,
|
|
"loss": 5.5938,
|
|
"mean_token_accuracy": 0.1846601814031601,
|
|
"num_tokens": 60743257.0,
|
|
"step": 31050
|
|
},
|
|
{
|
|
"entropy": 5.877269983291626,
|
|
"epoch": 3.1042635077722798,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00040525155750700863,
|
|
"loss": 5.3153,
|
|
"mean_token_accuracy": 0.20228327363729476,
|
|
"num_tokens": 60752469.0,
|
|
"step": 31055
|
|
},
|
|
{
|
|
"entropy": 6.013674926757813,
|
|
"epoch": 3.1047633328335085,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00040522245492083674,
|
|
"loss": 5.5656,
|
|
"mean_token_accuracy": 0.18838447332382202,
|
|
"num_tokens": 60762986.0,
|
|
"step": 31060
|
|
},
|
|
{
|
|
"entropy": 5.983263254165649,
|
|
"epoch": 3.1052631578947367,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00040519334905830134,
|
|
"loss": 5.4413,
|
|
"mean_token_accuracy": 0.1910280928015709,
|
|
"num_tokens": 60772557.0,
|
|
"step": 31065
|
|
},
|
|
{
|
|
"entropy": 6.008750629425049,
|
|
"epoch": 3.1057629829559654,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004051642399201349,
|
|
"loss": 5.6304,
|
|
"mean_token_accuracy": 0.18019878268241882,
|
|
"num_tokens": 60782357.0,
|
|
"step": 31070
|
|
},
|
|
{
|
|
"entropy": 6.008349847793579,
|
|
"epoch": 3.106262808017194,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00040513512750706956,
|
|
"loss": 5.494,
|
|
"mean_token_accuracy": 0.19018735438585282,
|
|
"num_tokens": 60791821.0,
|
|
"step": 31075
|
|
},
|
|
{
|
|
"entropy": 6.079935312271118,
|
|
"epoch": 3.1067626330784224,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.000405106011819838,
|
|
"loss": 5.5764,
|
|
"mean_token_accuracy": 0.18561614453792571,
|
|
"num_tokens": 60801750.0,
|
|
"step": 31080
|
|
},
|
|
{
|
|
"entropy": 5.895438575744629,
|
|
"epoch": 3.107262458139651,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00040507689285917254,
|
|
"loss": 5.4271,
|
|
"mean_token_accuracy": 0.1902554839849472,
|
|
"num_tokens": 60811177.0,
|
|
"step": 31085
|
|
},
|
|
{
|
|
"entropy": 5.881518125534058,
|
|
"epoch": 3.1077622832008798,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00040504777062580597,
|
|
"loss": 5.3963,
|
|
"mean_token_accuracy": 0.2008064642548561,
|
|
"num_tokens": 60820817.0,
|
|
"step": 31090
|
|
},
|
|
{
|
|
"entropy": 6.085613632202149,
|
|
"epoch": 3.1082621082621085,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000405018645120471,
|
|
"loss": 5.6446,
|
|
"mean_token_accuracy": 0.1800984799861908,
|
|
"num_tokens": 60830827.0,
|
|
"step": 31095
|
|
},
|
|
{
|
|
"entropy": 6.093076467514038,
|
|
"epoch": 3.1087619333233367,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004049895163439003,
|
|
"loss": 5.6432,
|
|
"mean_token_accuracy": 0.17547455728054046,
|
|
"num_tokens": 60841523.0,
|
|
"step": 31100
|
|
},
|
|
{
|
|
"entropy": 5.993281364440918,
|
|
"epoch": 3.1092617583845654,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00040496038429682684,
|
|
"loss": 5.4838,
|
|
"mean_token_accuracy": 0.18944159299135208,
|
|
"num_tokens": 60850179.0,
|
|
"step": 31105
|
|
},
|
|
{
|
|
"entropy": 5.984975671768188,
|
|
"epoch": 3.109761583445794,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00040493124897998363,
|
|
"loss": 5.5039,
|
|
"mean_token_accuracy": 0.198259074985981,
|
|
"num_tokens": 60861571.0,
|
|
"step": 31110
|
|
},
|
|
{
|
|
"entropy": 5.988681221008301,
|
|
"epoch": 3.1102614085070224,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004049021103941036,
|
|
"loss": 5.5209,
|
|
"mean_token_accuracy": 0.18927924633026122,
|
|
"num_tokens": 60871148.0,
|
|
"step": 31115
|
|
},
|
|
{
|
|
"entropy": 5.996427297592163,
|
|
"epoch": 3.110761233568251,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00040487296853991984,
|
|
"loss": 5.534,
|
|
"mean_token_accuracy": 0.1851450890302658,
|
|
"num_tokens": 60880869.0,
|
|
"step": 31120
|
|
},
|
|
{
|
|
"entropy": 6.009502792358399,
|
|
"epoch": 3.1112610586294798,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004048438234181657,
|
|
"loss": 5.5161,
|
|
"mean_token_accuracy": 0.18861276060342788,
|
|
"num_tokens": 60890770.0,
|
|
"step": 31125
|
|
},
|
|
{
|
|
"entropy": 5.923921728134156,
|
|
"epoch": 3.1117608836907085,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00040481467502957426,
|
|
"loss": 5.436,
|
|
"mean_token_accuracy": 0.19820228964090347,
|
|
"num_tokens": 60900251.0,
|
|
"step": 31130
|
|
},
|
|
{
|
|
"entropy": 5.8553955078125,
|
|
"epoch": 3.1122607087519367,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.000404785523374879,
|
|
"loss": 5.4312,
|
|
"mean_token_accuracy": 0.19873209446668624,
|
|
"num_tokens": 60909053.0,
|
|
"step": 31135
|
|
},
|
|
{
|
|
"entropy": 5.926516342163086,
|
|
"epoch": 3.1127605338131654,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00040475636845481347,
|
|
"loss": 5.4069,
|
|
"mean_token_accuracy": 0.20128623098134996,
|
|
"num_tokens": 60918583.0,
|
|
"step": 31140
|
|
},
|
|
{
|
|
"entropy": 6.015041065216065,
|
|
"epoch": 3.113260358874394,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00040472721027011107,
|
|
"loss": 5.5289,
|
|
"mean_token_accuracy": 0.1883237972855568,
|
|
"num_tokens": 60927635.0,
|
|
"step": 31145
|
|
},
|
|
{
|
|
"entropy": 6.02846212387085,
|
|
"epoch": 3.1137601839356224,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004046980488215054,
|
|
"loss": 5.519,
|
|
"mean_token_accuracy": 0.18605010211467743,
|
|
"num_tokens": 60937831.0,
|
|
"step": 31150
|
|
},
|
|
{
|
|
"entropy": 6.050901794433594,
|
|
"epoch": 3.114260008996851,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00040466888410973026,
|
|
"loss": 5.6011,
|
|
"mean_token_accuracy": 0.18343207240104675,
|
|
"num_tokens": 60947333.0,
|
|
"step": 31155
|
|
},
|
|
{
|
|
"entropy": 6.0011176586151125,
|
|
"epoch": 3.1147598340580798,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004046397161355193,
|
|
"loss": 5.4774,
|
|
"mean_token_accuracy": 0.1890862226486206,
|
|
"num_tokens": 60956585.0,
|
|
"step": 31160
|
|
},
|
|
{
|
|
"entropy": 5.849151277542115,
|
|
"epoch": 3.1152596591193085,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004046105448996064,
|
|
"loss": 5.3378,
|
|
"mean_token_accuracy": 0.2083989590406418,
|
|
"num_tokens": 60966496.0,
|
|
"step": 31165
|
|
},
|
|
{
|
|
"entropy": 5.983863735198975,
|
|
"epoch": 3.1157594841805367,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004045813704027257,
|
|
"loss": 5.5404,
|
|
"mean_token_accuracy": 0.18798049688339233,
|
|
"num_tokens": 60976500.0,
|
|
"step": 31170
|
|
},
|
|
{
|
|
"entropy": 6.032502031326294,
|
|
"epoch": 3.1162593092417654,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004045521926456109,
|
|
"loss": 5.5331,
|
|
"mean_token_accuracy": 0.19060409367084502,
|
|
"num_tokens": 60985935.0,
|
|
"step": 31175
|
|
},
|
|
{
|
|
"entropy": 5.962229299545288,
|
|
"epoch": 3.116759134302994,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004045230116289964,
|
|
"loss": 5.4926,
|
|
"mean_token_accuracy": 0.1927427753806114,
|
|
"num_tokens": 60995349.0,
|
|
"step": 31180
|
|
},
|
|
{
|
|
"entropy": 5.998567390441894,
|
|
"epoch": 3.1172589593642224,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00040449382735361614,
|
|
"loss": 5.5622,
|
|
"mean_token_accuracy": 0.18820952326059343,
|
|
"num_tokens": 61006229.0,
|
|
"step": 31185
|
|
},
|
|
{
|
|
"entropy": 6.008651161193848,
|
|
"epoch": 3.117758784425451,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004044646398202046,
|
|
"loss": 5.5361,
|
|
"mean_token_accuracy": 0.19046901017427445,
|
|
"num_tokens": 61016394.0,
|
|
"step": 31190
|
|
},
|
|
{
|
|
"entropy": 5.979148435592651,
|
|
"epoch": 3.1182586094866798,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000404435449029496,
|
|
"loss": 5.4715,
|
|
"mean_token_accuracy": 0.1933071255683899,
|
|
"num_tokens": 61026206.0,
|
|
"step": 31195
|
|
},
|
|
{
|
|
"entropy": 5.884094858169556,
|
|
"epoch": 3.118758434547908,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004044062549822248,
|
|
"loss": 5.451,
|
|
"mean_token_accuracy": 0.19066386818885803,
|
|
"num_tokens": 61036081.0,
|
|
"step": 31200
|
|
},
|
|
{
|
|
"entropy": 5.948306035995484,
|
|
"epoch": 3.1192582596091367,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004043770576791255,
|
|
"loss": 5.5072,
|
|
"mean_token_accuracy": 0.18489427119493484,
|
|
"num_tokens": 61045812.0,
|
|
"step": 31205
|
|
},
|
|
{
|
|
"entropy": 5.966343545913697,
|
|
"epoch": 3.1197580846703654,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.0004043478571209328,
|
|
"loss": 5.4551,
|
|
"mean_token_accuracy": 0.20232053995132446,
|
|
"num_tokens": 61055122.0,
|
|
"step": 31210
|
|
},
|
|
{
|
|
"entropy": 5.870813655853271,
|
|
"epoch": 3.120257909731594,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004043186533083812,
|
|
"loss": 5.4416,
|
|
"mean_token_accuracy": 0.19489311426877975,
|
|
"num_tokens": 61064033.0,
|
|
"step": 31215
|
|
},
|
|
{
|
|
"entropy": 5.913409614562989,
|
|
"epoch": 3.1207577347928224,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00040428944624220557,
|
|
"loss": 5.4775,
|
|
"mean_token_accuracy": 0.18848209977149963,
|
|
"num_tokens": 61073881.0,
|
|
"step": 31220
|
|
},
|
|
{
|
|
"entropy": 5.965680551528931,
|
|
"epoch": 3.121257559854051,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004042602359231409,
|
|
"loss": 5.3865,
|
|
"mean_token_accuracy": 0.1991528421640396,
|
|
"num_tokens": 61083651.0,
|
|
"step": 31225
|
|
},
|
|
{
|
|
"entropy": 5.972289752960205,
|
|
"epoch": 3.1217573849152798,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004042310223519218,
|
|
"loss": 5.5681,
|
|
"mean_token_accuracy": 0.18551369160413742,
|
|
"num_tokens": 61092860.0,
|
|
"step": 31230
|
|
},
|
|
{
|
|
"entropy": 5.892760276794434,
|
|
"epoch": 3.122257209976508,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004042018055292835,
|
|
"loss": 5.4935,
|
|
"mean_token_accuracy": 0.19005959182977678,
|
|
"num_tokens": 61102937.0,
|
|
"step": 31235
|
|
},
|
|
{
|
|
"entropy": 5.9495141983032225,
|
|
"epoch": 3.1227570350377367,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004041725854559609,
|
|
"loss": 5.3448,
|
|
"mean_token_accuracy": 0.19681030064821242,
|
|
"num_tokens": 61112422.0,
|
|
"step": 31240
|
|
},
|
|
{
|
|
"entropy": 6.05602445602417,
|
|
"epoch": 3.1232568600989654,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00040414336213268943,
|
|
"loss": 5.6482,
|
|
"mean_token_accuracy": 0.1777706876397133,
|
|
"num_tokens": 61122814.0,
|
|
"step": 31245
|
|
},
|
|
{
|
|
"entropy": 5.957950162887573,
|
|
"epoch": 3.123756685160194,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004041141355602041,
|
|
"loss": 5.4831,
|
|
"mean_token_accuracy": 0.18516281098127366,
|
|
"num_tokens": 61133938.0,
|
|
"step": 31250
|
|
},
|
|
{
|
|
"entropy": 5.988904905319214,
|
|
"epoch": 3.1242565102214224,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004040849057392405,
|
|
"loss": 5.485,
|
|
"mean_token_accuracy": 0.1952081501483917,
|
|
"num_tokens": 61143941.0,
|
|
"step": 31255
|
|
},
|
|
{
|
|
"entropy": 5.974291181564331,
|
|
"epoch": 3.124756335282651,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004040556726705337,
|
|
"loss": 5.4422,
|
|
"mean_token_accuracy": 0.19295637160539628,
|
|
"num_tokens": 61152674.0,
|
|
"step": 31260
|
|
},
|
|
{
|
|
"entropy": 5.919627523422241,
|
|
"epoch": 3.1252561603438798,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004040264363548195,
|
|
"loss": 5.519,
|
|
"mean_token_accuracy": 0.1922778606414795,
|
|
"num_tokens": 61161825.0,
|
|
"step": 31265
|
|
},
|
|
{
|
|
"entropy": 5.959270763397217,
|
|
"epoch": 3.125755985405108,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004039971967928333,
|
|
"loss": 5.5011,
|
|
"mean_token_accuracy": 0.19119893014431,
|
|
"num_tokens": 61171283.0,
|
|
"step": 31270
|
|
},
|
|
{
|
|
"entropy": 5.995578908920288,
|
|
"epoch": 3.1262558104663367,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004039679539853108,
|
|
"loss": 5.4614,
|
|
"mean_token_accuracy": 0.18990177065134048,
|
|
"num_tokens": 61180736.0,
|
|
"step": 31275
|
|
},
|
|
{
|
|
"entropy": 6.037010526657104,
|
|
"epoch": 3.1267556355275654,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004039387079329878,
|
|
"loss": 5.5502,
|
|
"mean_token_accuracy": 0.19119937419891359,
|
|
"num_tokens": 61190210.0,
|
|
"step": 31280
|
|
},
|
|
{
|
|
"entropy": 6.088508796691895,
|
|
"epoch": 3.127255460588794,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004039094586366001,
|
|
"loss": 5.6192,
|
|
"mean_token_accuracy": 0.18094677329063416,
|
|
"num_tokens": 61201000.0,
|
|
"step": 31285
|
|
},
|
|
{
|
|
"entropy": 5.956289863586425,
|
|
"epoch": 3.1277552856500224,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00040388020609688366,
|
|
"loss": 5.4564,
|
|
"mean_token_accuracy": 0.19444239735603333,
|
|
"num_tokens": 61209924.0,
|
|
"step": 31290
|
|
},
|
|
{
|
|
"entropy": 5.985530948638916,
|
|
"epoch": 3.128255110711251,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00040385095031457435,
|
|
"loss": 5.4835,
|
|
"mean_token_accuracy": 0.1914413958787918,
|
|
"num_tokens": 61219472.0,
|
|
"step": 31295
|
|
},
|
|
{
|
|
"entropy": 5.923833751678467,
|
|
"epoch": 3.1287549357724798,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004038216912904082,
|
|
"loss": 5.4318,
|
|
"mean_token_accuracy": 0.19884171336889267,
|
|
"num_tokens": 61229609.0,
|
|
"step": 31300
|
|
},
|
|
{
|
|
"entropy": 6.004294490814209,
|
|
"epoch": 3.129254760833708,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004037924290251215,
|
|
"loss": 5.55,
|
|
"mean_token_accuracy": 0.19176710844039918,
|
|
"num_tokens": 61240352.0,
|
|
"step": 31305
|
|
},
|
|
{
|
|
"entropy": 5.963444948196411,
|
|
"epoch": 3.1297545858949367,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004037631635194505,
|
|
"loss": 5.4515,
|
|
"mean_token_accuracy": 0.19515498727560043,
|
|
"num_tokens": 61249789.0,
|
|
"step": 31310
|
|
},
|
|
{
|
|
"entropy": 5.814328861236572,
|
|
"epoch": 3.1302544109561654,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004037338947741313,
|
|
"loss": 5.3193,
|
|
"mean_token_accuracy": 0.2095335155725479,
|
|
"num_tokens": 61259788.0,
|
|
"step": 31315
|
|
},
|
|
{
|
|
"entropy": 5.810981416702271,
|
|
"epoch": 3.130754236017394,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00040370462278990055,
|
|
"loss": 5.2841,
|
|
"mean_token_accuracy": 0.21240253299474715,
|
|
"num_tokens": 61269115.0,
|
|
"step": 31320
|
|
},
|
|
{
|
|
"entropy": 5.844972276687622,
|
|
"epoch": 3.1312540610786224,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004036753475674945,
|
|
"loss": 5.4409,
|
|
"mean_token_accuracy": 0.19394911527633668,
|
|
"num_tokens": 61279272.0,
|
|
"step": 31325
|
|
},
|
|
{
|
|
"entropy": 5.9573146343231205,
|
|
"epoch": 3.131753886139851,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00040364606910764996,
|
|
"loss": 5.5022,
|
|
"mean_token_accuracy": 0.1899771049618721,
|
|
"num_tokens": 61290451.0,
|
|
"step": 31330
|
|
},
|
|
{
|
|
"entropy": 5.937620306015015,
|
|
"epoch": 3.1322537112010798,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004036167874111034,
|
|
"loss": 5.4586,
|
|
"mean_token_accuracy": 0.19320708960294725,
|
|
"num_tokens": 61299666.0,
|
|
"step": 31335
|
|
},
|
|
{
|
|
"entropy": 6.027484273910522,
|
|
"epoch": 3.132753536262308,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00040358750247859146,
|
|
"loss": 5.6063,
|
|
"mean_token_accuracy": 0.18249933272600175,
|
|
"num_tokens": 61308794.0,
|
|
"step": 31340
|
|
},
|
|
{
|
|
"entropy": 5.994818258285522,
|
|
"epoch": 3.1332533613235367,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004035582143108511,
|
|
"loss": 5.5622,
|
|
"mean_token_accuracy": 0.18542817682027818,
|
|
"num_tokens": 61319532.0,
|
|
"step": 31345
|
|
},
|
|
{
|
|
"entropy": 5.994992113113403,
|
|
"epoch": 3.1337531863847654,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00040352892290861916,
|
|
"loss": 5.5207,
|
|
"mean_token_accuracy": 0.18724164068698884,
|
|
"num_tokens": 61329995.0,
|
|
"step": 31350
|
|
},
|
|
{
|
|
"entropy": 5.948924207687378,
|
|
"epoch": 3.134253011445994,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004034996282726326,
|
|
"loss": 5.4809,
|
|
"mean_token_accuracy": 0.18786949813365936,
|
|
"num_tokens": 61339552.0,
|
|
"step": 31355
|
|
},
|
|
{
|
|
"entropy": 5.856586599349976,
|
|
"epoch": 3.1347528365072224,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00040347033040362835,
|
|
"loss": 5.4454,
|
|
"mean_token_accuracy": 0.19993999004364013,
|
|
"num_tokens": 61349411.0,
|
|
"step": 31360
|
|
},
|
|
{
|
|
"entropy": 6.016653728485108,
|
|
"epoch": 3.135252661568451,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00040344102930234385,
|
|
"loss": 5.4873,
|
|
"mean_token_accuracy": 0.19098584055900575,
|
|
"num_tokens": 61358538.0,
|
|
"step": 31365
|
|
},
|
|
{
|
|
"entropy": 6.000981569290161,
|
|
"epoch": 3.1357524866296798,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00040341172496951596,
|
|
"loss": 5.3813,
|
|
"mean_token_accuracy": 0.19591281414031983,
|
|
"num_tokens": 61368988.0,
|
|
"step": 31370
|
|
},
|
|
{
|
|
"entropy": 5.959142637252808,
|
|
"epoch": 3.136252311690908,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004033824174058821,
|
|
"loss": 5.5375,
|
|
"mean_token_accuracy": 0.1929696038365364,
|
|
"num_tokens": 61379643.0,
|
|
"step": 31375
|
|
},
|
|
{
|
|
"entropy": 5.962166118621826,
|
|
"epoch": 3.1367521367521367,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004033531066121797,
|
|
"loss": 5.5709,
|
|
"mean_token_accuracy": 0.18834471106529235,
|
|
"num_tokens": 61389460.0,
|
|
"step": 31380
|
|
},
|
|
{
|
|
"entropy": 6.008536624908447,
|
|
"epoch": 3.1372519618133654,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00040332379258914614,
|
|
"loss": 5.5364,
|
|
"mean_token_accuracy": 0.18524518311023713,
|
|
"num_tokens": 61400034.0,
|
|
"step": 31385
|
|
},
|
|
{
|
|
"entropy": 5.980181503295898,
|
|
"epoch": 3.1377517868745937,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000403294475337519,
|
|
"loss": 5.5113,
|
|
"mean_token_accuracy": 0.18046075254678726,
|
|
"num_tokens": 61409957.0,
|
|
"step": 31390
|
|
},
|
|
{
|
|
"entropy": 6.0448253631591795,
|
|
"epoch": 3.1382516119358224,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004032651548580359,
|
|
"loss": 5.5144,
|
|
"mean_token_accuracy": 0.18617370575666428,
|
|
"num_tokens": 61419265.0,
|
|
"step": 31395
|
|
},
|
|
{
|
|
"entropy": 5.961035871505738,
|
|
"epoch": 3.138751436997051,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00040323583115143446,
|
|
"loss": 5.5037,
|
|
"mean_token_accuracy": 0.19141481071710587,
|
|
"num_tokens": 61429007.0,
|
|
"step": 31400
|
|
},
|
|
{
|
|
"entropy": 5.9894547939300535,
|
|
"epoch": 3.1392512620582798,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00040320650421845256,
|
|
"loss": 5.5158,
|
|
"mean_token_accuracy": 0.19312978982925416,
|
|
"num_tokens": 61439866.0,
|
|
"step": 31405
|
|
},
|
|
{
|
|
"entropy": 6.058964014053345,
|
|
"epoch": 3.139751087119508,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00040317717405982797,
|
|
"loss": 5.583,
|
|
"mean_token_accuracy": 0.18591136187314988,
|
|
"num_tokens": 61448953.0,
|
|
"step": 31410
|
|
},
|
|
{
|
|
"entropy": 5.983038091659546,
|
|
"epoch": 3.1402509121807367,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00040314784067629867,
|
|
"loss": 5.5228,
|
|
"mean_token_accuracy": 0.18469350636005402,
|
|
"num_tokens": 61458469.0,
|
|
"step": 31415
|
|
},
|
|
{
|
|
"entropy": 5.941574239730835,
|
|
"epoch": 3.1407507372419654,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00040311850406860267,
|
|
"loss": 5.4036,
|
|
"mean_token_accuracy": 0.19102180302143096,
|
|
"num_tokens": 61468029.0,
|
|
"step": 31420
|
|
},
|
|
{
|
|
"entropy": 5.931477785110474,
|
|
"epoch": 3.1412505623031937,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00040308916423747803,
|
|
"loss": 5.5514,
|
|
"mean_token_accuracy": 0.19275960922241211,
|
|
"num_tokens": 61478112.0,
|
|
"step": 31425
|
|
},
|
|
{
|
|
"entropy": 5.966872310638427,
|
|
"epoch": 3.1417503873644224,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000403059821183663,
|
|
"loss": 5.4812,
|
|
"mean_token_accuracy": 0.1866894394159317,
|
|
"num_tokens": 61487730.0,
|
|
"step": 31430
|
|
},
|
|
{
|
|
"entropy": 5.959953355789184,
|
|
"epoch": 3.142250212425651,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004030304749078959,
|
|
"loss": 5.4594,
|
|
"mean_token_accuracy": 0.18901357650756836,
|
|
"num_tokens": 61497603.0,
|
|
"step": 31435
|
|
},
|
|
{
|
|
"entropy": 5.918599224090576,
|
|
"epoch": 3.1427500374868798,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00040300112541091494,
|
|
"loss": 5.509,
|
|
"mean_token_accuracy": 0.2015179604291916,
|
|
"num_tokens": 61508090.0,
|
|
"step": 31440
|
|
},
|
|
{
|
|
"entropy": 5.872516822814942,
|
|
"epoch": 3.143249862548108,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004029717726934586,
|
|
"loss": 5.3822,
|
|
"mean_token_accuracy": 0.19738091826438903,
|
|
"num_tokens": 61516684.0,
|
|
"step": 31445
|
|
},
|
|
{
|
|
"entropy": 5.951304817199707,
|
|
"epoch": 3.1437496876093367,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00040294241675626534,
|
|
"loss": 5.521,
|
|
"mean_token_accuracy": 0.19032310098409652,
|
|
"num_tokens": 61525617.0,
|
|
"step": 31450
|
|
},
|
|
{
|
|
"entropy": 5.891342830657959,
|
|
"epoch": 3.1442495126705654,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004029130576000739,
|
|
"loss": 5.5131,
|
|
"mean_token_accuracy": 0.1941784828901291,
|
|
"num_tokens": 61535365.0,
|
|
"step": 31455
|
|
},
|
|
{
|
|
"entropy": 5.921067762374878,
|
|
"epoch": 3.1447493377317937,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.0004028836952256227,
|
|
"loss": 5.4899,
|
|
"mean_token_accuracy": 0.19133597612380981,
|
|
"num_tokens": 61544355.0,
|
|
"step": 31460
|
|
},
|
|
{
|
|
"entropy": 6.003856420516968,
|
|
"epoch": 3.1452491627930224,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004028543296336508,
|
|
"loss": 5.4653,
|
|
"mean_token_accuracy": 0.1981509044766426,
|
|
"num_tokens": 61554291.0,
|
|
"step": 31465
|
|
},
|
|
{
|
|
"entropy": 6.0176397323608395,
|
|
"epoch": 3.145748987854251,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00040282496082489684,
|
|
"loss": 5.5302,
|
|
"mean_token_accuracy": 0.18410206735134124,
|
|
"num_tokens": 61563833.0,
|
|
"step": 31470
|
|
},
|
|
{
|
|
"entropy": 5.977270984649659,
|
|
"epoch": 3.1462488129154798,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00040279558880009967,
|
|
"loss": 5.5065,
|
|
"mean_token_accuracy": 0.18800708651542664,
|
|
"num_tokens": 61573328.0,
|
|
"step": 31475
|
|
},
|
|
{
|
|
"entropy": 6.007422304153442,
|
|
"epoch": 3.146748637976708,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004027662135599984,
|
|
"loss": 5.5418,
|
|
"mean_token_accuracy": 0.18818393498659133,
|
|
"num_tokens": 61583928.0,
|
|
"step": 31480
|
|
},
|
|
{
|
|
"entropy": 5.849923992156983,
|
|
"epoch": 3.1472484630379367,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004027368351053321,
|
|
"loss": 5.4764,
|
|
"mean_token_accuracy": 0.1933007001876831,
|
|
"num_tokens": 61593599.0,
|
|
"step": 31485
|
|
},
|
|
{
|
|
"entropy": 5.836234903335571,
|
|
"epoch": 3.1477482880991654,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004027074534368399,
|
|
"loss": 5.3309,
|
|
"mean_token_accuracy": 0.20826305449008942,
|
|
"num_tokens": 61603284.0,
|
|
"step": 31490
|
|
},
|
|
{
|
|
"entropy": 5.97140097618103,
|
|
"epoch": 3.1482481131603937,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00040267806855526103,
|
|
"loss": 5.4263,
|
|
"mean_token_accuracy": 0.1986226722598076,
|
|
"num_tokens": 61612027.0,
|
|
"step": 31495
|
|
},
|
|
{
|
|
"entropy": 5.972550535202027,
|
|
"epoch": 3.1487479382216224,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004026486804613347,
|
|
"loss": 5.5505,
|
|
"mean_token_accuracy": 0.183631132543087,
|
|
"num_tokens": 61621665.0,
|
|
"step": 31500
|
|
},
|
|
{
|
|
"entropy": 5.888342666625976,
|
|
"epoch": 3.149247763282851,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00040261928915580065,
|
|
"loss": 5.4946,
|
|
"mean_token_accuracy": 0.18988512009382247,
|
|
"num_tokens": 61632684.0,
|
|
"step": 31505
|
|
},
|
|
{
|
|
"entropy": 5.980754804611206,
|
|
"epoch": 3.1497475883440798,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004025898946393979,
|
|
"loss": 5.5263,
|
|
"mean_token_accuracy": 0.18966137021780013,
|
|
"num_tokens": 61642401.0,
|
|
"step": 31510
|
|
},
|
|
{
|
|
"entropy": 5.914760112762451,
|
|
"epoch": 3.150247413405308,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004025604969128663,
|
|
"loss": 5.4761,
|
|
"mean_token_accuracy": 0.1951388508081436,
|
|
"num_tokens": 61652644.0,
|
|
"step": 31515
|
|
},
|
|
{
|
|
"entropy": 5.909180641174316,
|
|
"epoch": 3.1507472384665367,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00040253109597694544,
|
|
"loss": 5.4011,
|
|
"mean_token_accuracy": 0.19972050338983535,
|
|
"num_tokens": 61661951.0,
|
|
"step": 31520
|
|
},
|
|
{
|
|
"entropy": 5.895602607727051,
|
|
"epoch": 3.1512470635277654,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00040250169183237507,
|
|
"loss": 5.4209,
|
|
"mean_token_accuracy": 0.19711074382066726,
|
|
"num_tokens": 61671637.0,
|
|
"step": 31525
|
|
},
|
|
{
|
|
"entropy": 5.908597040176391,
|
|
"epoch": 3.1517468885889937,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00040247228447989485,
|
|
"loss": 5.4769,
|
|
"mean_token_accuracy": 0.1896718204021454,
|
|
"num_tokens": 61681867.0,
|
|
"step": 31530
|
|
},
|
|
{
|
|
"entropy": 5.9682252407073975,
|
|
"epoch": 3.1522467136502224,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00040244287392024485,
|
|
"loss": 5.5232,
|
|
"mean_token_accuracy": 0.19125040620565414,
|
|
"num_tokens": 61691906.0,
|
|
"step": 31535
|
|
},
|
|
{
|
|
"entropy": 6.022475004196167,
|
|
"epoch": 3.152746538711451,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004024134601541649,
|
|
"loss": 5.4946,
|
|
"mean_token_accuracy": 0.19852046966552733,
|
|
"num_tokens": 61702927.0,
|
|
"step": 31540
|
|
},
|
|
{
|
|
"entropy": 5.927845239639282,
|
|
"epoch": 3.1532463637726798,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004023840431823951,
|
|
"loss": 5.4206,
|
|
"mean_token_accuracy": 0.2003851518034935,
|
|
"num_tokens": 61711585.0,
|
|
"step": 31545
|
|
},
|
|
{
|
|
"entropy": 5.869918870925903,
|
|
"epoch": 3.153746188833908,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004023546230056754,
|
|
"loss": 5.4496,
|
|
"mean_token_accuracy": 0.19821271002292634,
|
|
"num_tokens": 61721806.0,
|
|
"step": 31550
|
|
},
|
|
{
|
|
"entropy": 5.9121777534484865,
|
|
"epoch": 3.1542460138951367,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00040232519962474635,
|
|
"loss": 5.5157,
|
|
"mean_token_accuracy": 0.18533743023872376,
|
|
"num_tokens": 61731172.0,
|
|
"step": 31555
|
|
},
|
|
{
|
|
"entropy": 5.919577121734619,
|
|
"epoch": 3.1547458389563654,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00040229577304034793,
|
|
"loss": 5.4561,
|
|
"mean_token_accuracy": 0.19120607823133468,
|
|
"num_tokens": 61740075.0,
|
|
"step": 31560
|
|
},
|
|
{
|
|
"entropy": 5.9958940029144285,
|
|
"epoch": 3.1552456640175937,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00040226634325322063,
|
|
"loss": 5.5117,
|
|
"mean_token_accuracy": 0.18513087183237076,
|
|
"num_tokens": 61750760.0,
|
|
"step": 31565
|
|
},
|
|
{
|
|
"entropy": 6.027641296386719,
|
|
"epoch": 3.1557454890788224,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004022369102641049,
|
|
"loss": 5.4939,
|
|
"mean_token_accuracy": 0.18867244869470595,
|
|
"num_tokens": 61760256.0,
|
|
"step": 31570
|
|
},
|
|
{
|
|
"entropy": 5.9607563495635985,
|
|
"epoch": 3.156245314140051,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00040220747407374133,
|
|
"loss": 5.5157,
|
|
"mean_token_accuracy": 0.19065891057252884,
|
|
"num_tokens": 61769769.0,
|
|
"step": 31575
|
|
},
|
|
{
|
|
"entropy": 5.958459901809692,
|
|
"epoch": 3.1567451392012797,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00040217803468287034,
|
|
"loss": 5.5282,
|
|
"mean_token_accuracy": 0.18991998583078384,
|
|
"num_tokens": 61779408.0,
|
|
"step": 31580
|
|
},
|
|
{
|
|
"entropy": 6.041933345794678,
|
|
"epoch": 3.157244964262508,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00040214859209223273,
|
|
"loss": 5.5072,
|
|
"mean_token_accuracy": 0.18266693204641343,
|
|
"num_tokens": 61789940.0,
|
|
"step": 31585
|
|
},
|
|
{
|
|
"entropy": 6.016028213500976,
|
|
"epoch": 3.1577447893237367,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004021191463025693,
|
|
"loss": 5.5086,
|
|
"mean_token_accuracy": 0.18311268091201782,
|
|
"num_tokens": 61799837.0,
|
|
"step": 31590
|
|
},
|
|
{
|
|
"entropy": 5.851018905639648,
|
|
"epoch": 3.1582446143849654,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004020896973146208,
|
|
"loss": 5.4612,
|
|
"mean_token_accuracy": 0.1942916616797447,
|
|
"num_tokens": 61809861.0,
|
|
"step": 31595
|
|
},
|
|
{
|
|
"entropy": 5.939258575439453,
|
|
"epoch": 3.1587444394461937,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00040206024512912824,
|
|
"loss": 5.4217,
|
|
"mean_token_accuracy": 0.19645809084177018,
|
|
"num_tokens": 61818711.0,
|
|
"step": 31600
|
|
},
|
|
{
|
|
"entropy": 5.934887552261353,
|
|
"epoch": 3.1592442645074224,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00040203078974683265,
|
|
"loss": 5.4264,
|
|
"mean_token_accuracy": 0.20285273045301438,
|
|
"num_tokens": 61829195.0,
|
|
"step": 31605
|
|
},
|
|
{
|
|
"entropy": 5.965077972412109,
|
|
"epoch": 3.159744089568651,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004020013311684751,
|
|
"loss": 5.4888,
|
|
"mean_token_accuracy": 0.18601911664009094,
|
|
"num_tokens": 61838473.0,
|
|
"step": 31610
|
|
},
|
|
{
|
|
"entropy": 5.993681621551514,
|
|
"epoch": 3.1602439146298797,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00040197186939479665,
|
|
"loss": 5.4774,
|
|
"mean_token_accuracy": 0.19030555039644242,
|
|
"num_tokens": 61848569.0,
|
|
"step": 31615
|
|
},
|
|
{
|
|
"entropy": 5.972588586807251,
|
|
"epoch": 3.160743739691108,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00040194240442653867,
|
|
"loss": 5.5568,
|
|
"mean_token_accuracy": 0.18530673235654832,
|
|
"num_tokens": 61858248.0,
|
|
"step": 31620
|
|
},
|
|
{
|
|
"entropy": 6.0065450191497805,
|
|
"epoch": 3.1612435647523367,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004019129362644425,
|
|
"loss": 5.5263,
|
|
"mean_token_accuracy": 0.18834338635206221,
|
|
"num_tokens": 61867998.0,
|
|
"step": 31625
|
|
},
|
|
{
|
|
"entropy": 5.976588487625122,
|
|
"epoch": 3.1617433898135654,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004018834649092494,
|
|
"loss": 5.5364,
|
|
"mean_token_accuracy": 0.18888325095176697,
|
|
"num_tokens": 61878436.0,
|
|
"step": 31630
|
|
},
|
|
{
|
|
"entropy": 5.964180183410645,
|
|
"epoch": 3.1622432148747937,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004018539903617011,
|
|
"loss": 5.5075,
|
|
"mean_token_accuracy": 0.18390629589557647,
|
|
"num_tokens": 61887660.0,
|
|
"step": 31635
|
|
},
|
|
{
|
|
"entropy": 6.010381031036377,
|
|
"epoch": 3.1627430399360223,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00040182451262253904,
|
|
"loss": 5.4984,
|
|
"mean_token_accuracy": 0.19169190376996995,
|
|
"num_tokens": 61897280.0,
|
|
"step": 31640
|
|
},
|
|
{
|
|
"entropy": 5.895849752426147,
|
|
"epoch": 3.163242864997251,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004017950316925049,
|
|
"loss": 5.4422,
|
|
"mean_token_accuracy": 0.19861891716718674,
|
|
"num_tokens": 61907683.0,
|
|
"step": 31645
|
|
},
|
|
{
|
|
"entropy": 5.902418994903565,
|
|
"epoch": 3.1637426900584797,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00040176554757234017,
|
|
"loss": 5.463,
|
|
"mean_token_accuracy": 0.1932573437690735,
|
|
"num_tokens": 61917275.0,
|
|
"step": 31650
|
|
},
|
|
{
|
|
"entropy": 6.035749626159668,
|
|
"epoch": 3.164242515119708,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004017360602627871,
|
|
"loss": 5.6055,
|
|
"mean_token_accuracy": 0.1767893061041832,
|
|
"num_tokens": 61928754.0,
|
|
"step": 31655
|
|
},
|
|
{
|
|
"entropy": 6.041413879394531,
|
|
"epoch": 3.1647423401809367,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00040170656976458723,
|
|
"loss": 5.5608,
|
|
"mean_token_accuracy": 0.18393041640520097,
|
|
"num_tokens": 61937569.0,
|
|
"step": 31660
|
|
},
|
|
{
|
|
"entropy": 5.952351903915405,
|
|
"epoch": 3.1652421652421654,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00040167707607848273,
|
|
"loss": 5.3925,
|
|
"mean_token_accuracy": 0.19953236281871795,
|
|
"num_tokens": 61947058.0,
|
|
"step": 31665
|
|
},
|
|
{
|
|
"entropy": 5.890717554092407,
|
|
"epoch": 3.1657419903033936,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004016475792052157,
|
|
"loss": 5.3982,
|
|
"mean_token_accuracy": 0.20102277398109436,
|
|
"num_tokens": 61956862.0,
|
|
"step": 31670
|
|
},
|
|
{
|
|
"entropy": 5.932324838638306,
|
|
"epoch": 3.1662418153646223,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.000401618079145528,
|
|
"loss": 5.5366,
|
|
"mean_token_accuracy": 0.19397734999656677,
|
|
"num_tokens": 61966815.0,
|
|
"step": 31675
|
|
},
|
|
{
|
|
"entropy": 6.001742744445801,
|
|
"epoch": 3.166741640425851,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004015885759001621,
|
|
"loss": 5.5266,
|
|
"mean_token_accuracy": 0.1913384646177292,
|
|
"num_tokens": 61975872.0,
|
|
"step": 31680
|
|
},
|
|
{
|
|
"entropy": 6.026777648925782,
|
|
"epoch": 3.1672414654870797,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00040155906946986027,
|
|
"loss": 5.5352,
|
|
"mean_token_accuracy": 0.18462164103984832,
|
|
"num_tokens": 61986145.0,
|
|
"step": 31685
|
|
},
|
|
{
|
|
"entropy": 5.956171131134033,
|
|
"epoch": 3.167741290548308,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004015295598553647,
|
|
"loss": 5.4958,
|
|
"mean_token_accuracy": 0.18774734884500505,
|
|
"num_tokens": 61995305.0,
|
|
"step": 31690
|
|
},
|
|
{
|
|
"entropy": 5.871306991577148,
|
|
"epoch": 3.1682411156095367,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004015000470574179,
|
|
"loss": 5.4228,
|
|
"mean_token_accuracy": 0.1977726027369499,
|
|
"num_tokens": 62005364.0,
|
|
"step": 31695
|
|
},
|
|
{
|
|
"entropy": 5.932752275466919,
|
|
"epoch": 3.1687409406707654,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00040147053107676266,
|
|
"loss": 5.5708,
|
|
"mean_token_accuracy": 0.18379231840372084,
|
|
"num_tokens": 62015323.0,
|
|
"step": 31700
|
|
},
|
|
{
|
|
"entropy": 6.063929080963135,
|
|
"epoch": 3.1692407657319936,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00040144101191414127,
|
|
"loss": 5.5913,
|
|
"mean_token_accuracy": 0.1832031786441803,
|
|
"num_tokens": 62024898.0,
|
|
"step": 31705
|
|
},
|
|
{
|
|
"entropy": 5.97997350692749,
|
|
"epoch": 3.1697405907932223,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004014114895702966,
|
|
"loss": 5.3873,
|
|
"mean_token_accuracy": 0.2059793710708618,
|
|
"num_tokens": 62033617.0,
|
|
"step": 31710
|
|
},
|
|
{
|
|
"entropy": 5.906655931472779,
|
|
"epoch": 3.170240415854451,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004013819640459714,
|
|
"loss": 5.4313,
|
|
"mean_token_accuracy": 0.19767178744077682,
|
|
"num_tokens": 62042505.0,
|
|
"step": 31715
|
|
},
|
|
{
|
|
"entropy": 5.928984642028809,
|
|
"epoch": 3.1707402409156797,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00040135243534190847,
|
|
"loss": 5.5245,
|
|
"mean_token_accuracy": 0.19800559878349305,
|
|
"num_tokens": 62052787.0,
|
|
"step": 31720
|
|
},
|
|
{
|
|
"entropy": 5.952375221252441,
|
|
"epoch": 3.171240065976908,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00040132290345885077,
|
|
"loss": 5.4835,
|
|
"mean_token_accuracy": 0.19678571224212646,
|
|
"num_tokens": 62062389.0,
|
|
"step": 31725
|
|
},
|
|
{
|
|
"entropy": 5.935515928268432,
|
|
"epoch": 3.1717398910381367,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004012933683975413,
|
|
"loss": 5.3249,
|
|
"mean_token_accuracy": 0.2108585000038147,
|
|
"num_tokens": 62071954.0,
|
|
"step": 31730
|
|
},
|
|
{
|
|
"entropy": 5.971732473373413,
|
|
"epoch": 3.1722397160993654,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00040126383015872324,
|
|
"loss": 5.521,
|
|
"mean_token_accuracy": 0.18882901966571808,
|
|
"num_tokens": 62081667.0,
|
|
"step": 31735
|
|
},
|
|
{
|
|
"entropy": 5.965707874298095,
|
|
"epoch": 3.1727395411605936,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00040123428874313974,
|
|
"loss": 5.467,
|
|
"mean_token_accuracy": 0.1927170127630234,
|
|
"num_tokens": 62091714.0,
|
|
"step": 31740
|
|
},
|
|
{
|
|
"entropy": 5.8846982479095455,
|
|
"epoch": 3.1732393662218223,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00040120474415153396,
|
|
"loss": 5.3788,
|
|
"mean_token_accuracy": 0.19790816605091094,
|
|
"num_tokens": 62100601.0,
|
|
"step": 31745
|
|
},
|
|
{
|
|
"entropy": 5.937832164764404,
|
|
"epoch": 3.173739191283051,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00040117519638464935,
|
|
"loss": 5.4465,
|
|
"mean_token_accuracy": 0.19512440860271454,
|
|
"num_tokens": 62110051.0,
|
|
"step": 31750
|
|
},
|
|
{
|
|
"entropy": 5.971889591217041,
|
|
"epoch": 3.1742390163442793,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00040114564544322913,
|
|
"loss": 5.5093,
|
|
"mean_token_accuracy": 0.18474420607089997,
|
|
"num_tokens": 62119470.0,
|
|
"step": 31755
|
|
},
|
|
{
|
|
"entropy": 5.881129455566406,
|
|
"epoch": 3.174738841405508,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000401116091328017,
|
|
"loss": 5.4835,
|
|
"mean_token_accuracy": 0.19314350932836533,
|
|
"num_tokens": 62129763.0,
|
|
"step": 31760
|
|
},
|
|
{
|
|
"entropy": 5.98674168586731,
|
|
"epoch": 3.1752386664667367,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00040108653403975647,
|
|
"loss": 5.5072,
|
|
"mean_token_accuracy": 0.18610615134239197,
|
|
"num_tokens": 62139274.0,
|
|
"step": 31765
|
|
},
|
|
{
|
|
"entropy": 5.96137547492981,
|
|
"epoch": 3.1757384915279654,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004010569735791912,
|
|
"loss": 5.5202,
|
|
"mean_token_accuracy": 0.18871829360723497,
|
|
"num_tokens": 62149128.0,
|
|
"step": 31770
|
|
},
|
|
{
|
|
"entropy": 5.934392786026001,
|
|
"epoch": 3.1762383165891936,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004010274099470649,
|
|
"loss": 5.4859,
|
|
"mean_token_accuracy": 0.19396189004182815,
|
|
"num_tokens": 62158709.0,
|
|
"step": 31775
|
|
},
|
|
{
|
|
"entropy": 6.021481657028199,
|
|
"epoch": 3.1767381416504223,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004009978431441214,
|
|
"loss": 5.5607,
|
|
"mean_token_accuracy": 0.18891103565692902,
|
|
"num_tokens": 62168935.0,
|
|
"step": 31780
|
|
},
|
|
{
|
|
"entropy": 5.955359745025635,
|
|
"epoch": 3.177237966711651,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00040096827317110463,
|
|
"loss": 5.4696,
|
|
"mean_token_accuracy": 0.18624246418476104,
|
|
"num_tokens": 62179511.0,
|
|
"step": 31785
|
|
},
|
|
{
|
|
"entropy": 5.976002550125122,
|
|
"epoch": 3.1777377917728793,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004009387000287585,
|
|
"loss": 5.5081,
|
|
"mean_token_accuracy": 0.18532605320215226,
|
|
"num_tokens": 62190223.0,
|
|
"step": 31790
|
|
},
|
|
{
|
|
"entropy": 5.95839262008667,
|
|
"epoch": 3.178237616834108,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000400909123717827,
|
|
"loss": 5.483,
|
|
"mean_token_accuracy": 0.19616424888372422,
|
|
"num_tokens": 62200396.0,
|
|
"step": 31795
|
|
},
|
|
{
|
|
"entropy": 5.920940685272217,
|
|
"epoch": 3.1787374418953367,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004008795442390544,
|
|
"loss": 5.4754,
|
|
"mean_token_accuracy": 0.190849669277668,
|
|
"num_tokens": 62210893.0,
|
|
"step": 31800
|
|
},
|
|
{
|
|
"entropy": 5.885735273361206,
|
|
"epoch": 3.1792372669565654,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004008499615931849,
|
|
"loss": 5.3645,
|
|
"mean_token_accuracy": 0.20134837329387664,
|
|
"num_tokens": 62221028.0,
|
|
"step": 31805
|
|
},
|
|
{
|
|
"entropy": 5.856674242019653,
|
|
"epoch": 3.1797370920177936,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004008203757809627,
|
|
"loss": 5.3558,
|
|
"mean_token_accuracy": 0.20379842668771744,
|
|
"num_tokens": 62230752.0,
|
|
"step": 31810
|
|
},
|
|
{
|
|
"entropy": 5.96544919013977,
|
|
"epoch": 3.1802369170790223,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00040079078680313224,
|
|
"loss": 5.5497,
|
|
"mean_token_accuracy": 0.18668653666973115,
|
|
"num_tokens": 62240910.0,
|
|
"step": 31815
|
|
},
|
|
{
|
|
"entropy": 5.972360134124756,
|
|
"epoch": 3.180736742140251,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.000400761194660438,
|
|
"loss": 5.5083,
|
|
"mean_token_accuracy": 0.18703789710998536,
|
|
"num_tokens": 62249738.0,
|
|
"step": 31820
|
|
},
|
|
{
|
|
"entropy": 5.905544662475586,
|
|
"epoch": 3.1812365672014793,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004007315993536244,
|
|
"loss": 5.3226,
|
|
"mean_token_accuracy": 0.21115057468414306,
|
|
"num_tokens": 62259136.0,
|
|
"step": 31825
|
|
},
|
|
{
|
|
"entropy": 5.937586259841919,
|
|
"epoch": 3.181736392262708,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00040070200088343613,
|
|
"loss": 5.5011,
|
|
"mean_token_accuracy": 0.19039141684770583,
|
|
"num_tokens": 62269056.0,
|
|
"step": 31830
|
|
},
|
|
{
|
|
"entropy": 5.985012578964233,
|
|
"epoch": 3.1822362173239367,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00040067239925061784,
|
|
"loss": 5.5349,
|
|
"mean_token_accuracy": 0.18993627578020095,
|
|
"num_tokens": 62279164.0,
|
|
"step": 31835
|
|
},
|
|
{
|
|
"entropy": 6.003317165374756,
|
|
"epoch": 3.1827360423851654,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004006427944559144,
|
|
"loss": 5.5615,
|
|
"mean_token_accuracy": 0.1840553477406502,
|
|
"num_tokens": 62289860.0,
|
|
"step": 31840
|
|
},
|
|
{
|
|
"entropy": 5.9883510112762455,
|
|
"epoch": 3.1832358674463936,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00040061318650007045,
|
|
"loss": 5.5766,
|
|
"mean_token_accuracy": 0.18302729427814485,
|
|
"num_tokens": 62300543.0,
|
|
"step": 31845
|
|
},
|
|
{
|
|
"entropy": 5.9642048358917235,
|
|
"epoch": 3.1837356925076223,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00040058357538383117,
|
|
"loss": 5.5313,
|
|
"mean_token_accuracy": 0.19264671057462693,
|
|
"num_tokens": 62310892.0,
|
|
"step": 31850
|
|
},
|
|
{
|
|
"entropy": 6.022899436950683,
|
|
"epoch": 3.184235517568851,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004005539611079414,
|
|
"loss": 5.4918,
|
|
"mean_token_accuracy": 0.19109055399894714,
|
|
"num_tokens": 62320139.0,
|
|
"step": 31855
|
|
},
|
|
{
|
|
"entropy": 5.903331184387207,
|
|
"epoch": 3.1847353426300793,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00040052434367314634,
|
|
"loss": 5.5023,
|
|
"mean_token_accuracy": 0.190876404941082,
|
|
"num_tokens": 62330810.0,
|
|
"step": 31860
|
|
},
|
|
{
|
|
"entropy": 6.021193265914917,
|
|
"epoch": 3.185235167691308,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00040049472308019104,
|
|
"loss": 5.5713,
|
|
"mean_token_accuracy": 0.18111571669578552,
|
|
"num_tokens": 62340609.0,
|
|
"step": 31865
|
|
},
|
|
{
|
|
"entropy": 5.968600130081176,
|
|
"epoch": 3.1857349927525367,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00040046509932982076,
|
|
"loss": 5.4707,
|
|
"mean_token_accuracy": 0.19309856593608857,
|
|
"num_tokens": 62351714.0,
|
|
"step": 31870
|
|
},
|
|
{
|
|
"entropy": 6.012744665145874,
|
|
"epoch": 3.1862348178137654,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004004354724227809,
|
|
"loss": 5.4757,
|
|
"mean_token_accuracy": 0.19441653341054915,
|
|
"num_tokens": 62361965.0,
|
|
"step": 31875
|
|
},
|
|
{
|
|
"entropy": 5.965483808517456,
|
|
"epoch": 3.1867346428749936,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004004058423598168,
|
|
"loss": 5.5528,
|
|
"mean_token_accuracy": 0.18479526340961455,
|
|
"num_tokens": 62371215.0,
|
|
"step": 31880
|
|
},
|
|
{
|
|
"entropy": 5.951533555984497,
|
|
"epoch": 3.1872344679362223,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00040037620914167406,
|
|
"loss": 5.5092,
|
|
"mean_token_accuracy": 0.19077071398496628,
|
|
"num_tokens": 62381497.0,
|
|
"step": 31885
|
|
},
|
|
{
|
|
"entropy": 5.971516942977905,
|
|
"epoch": 3.187734292997451,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004003465727690981,
|
|
"loss": 5.4261,
|
|
"mean_token_accuracy": 0.20351123809814453,
|
|
"num_tokens": 62390852.0,
|
|
"step": 31890
|
|
},
|
|
{
|
|
"entropy": 5.981365823745728,
|
|
"epoch": 3.1882341180586793,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00040031693324283464,
|
|
"loss": 5.5071,
|
|
"mean_token_accuracy": 0.1859159767627716,
|
|
"num_tokens": 62400444.0,
|
|
"step": 31895
|
|
},
|
|
{
|
|
"entropy": 6.017460680007934,
|
|
"epoch": 3.188733943119908,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004002872905636294,
|
|
"loss": 5.5765,
|
|
"mean_token_accuracy": 0.1810726374387741,
|
|
"num_tokens": 62410377.0,
|
|
"step": 31900
|
|
},
|
|
{
|
|
"entropy": 5.918696069717408,
|
|
"epoch": 3.1892337681811367,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00040025764473222816,
|
|
"loss": 5.4444,
|
|
"mean_token_accuracy": 0.18514297008514405,
|
|
"num_tokens": 62420943.0,
|
|
"step": 31905
|
|
},
|
|
{
|
|
"entropy": 5.866464900970459,
|
|
"epoch": 3.189733593242365,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00040022799574937674,
|
|
"loss": 5.4006,
|
|
"mean_token_accuracy": 0.20597436428070068,
|
|
"num_tokens": 62430090.0,
|
|
"step": 31910
|
|
},
|
|
{
|
|
"entropy": 5.8680335521698,
|
|
"epoch": 3.1902334183035936,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00040019834361582123,
|
|
"loss": 5.4022,
|
|
"mean_token_accuracy": 0.2009678766131401,
|
|
"num_tokens": 62439311.0,
|
|
"step": 31915
|
|
},
|
|
{
|
|
"entropy": 5.920231771469116,
|
|
"epoch": 3.1907332433648223,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00040016868833230766,
|
|
"loss": 5.5232,
|
|
"mean_token_accuracy": 0.19111137092113495,
|
|
"num_tokens": 62450600.0,
|
|
"step": 31920
|
|
},
|
|
{
|
|
"entropy": 5.978774213790894,
|
|
"epoch": 3.191233068426051,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004001390298995821,
|
|
"loss": 5.4807,
|
|
"mean_token_accuracy": 0.19141968935728074,
|
|
"num_tokens": 62460483.0,
|
|
"step": 31925
|
|
},
|
|
{
|
|
"entropy": 5.996170473098755,
|
|
"epoch": 3.1917328934872793,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00040010936831839065,
|
|
"loss": 5.4598,
|
|
"mean_token_accuracy": 0.1942485511302948,
|
|
"num_tokens": 62469903.0,
|
|
"step": 31930
|
|
},
|
|
{
|
|
"entropy": 5.8958595275878904,
|
|
"epoch": 3.192232718548508,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00040007970358947977,
|
|
"loss": 5.3794,
|
|
"mean_token_accuracy": 0.202092507481575,
|
|
"num_tokens": 62479524.0,
|
|
"step": 31935
|
|
},
|
|
{
|
|
"entropy": 5.975874757766723,
|
|
"epoch": 3.1927325436097367,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00040005003571359565,
|
|
"loss": 5.5729,
|
|
"mean_token_accuracy": 0.18527375906705856,
|
|
"num_tokens": 62489925.0,
|
|
"step": 31940
|
|
},
|
|
{
|
|
"entropy": 5.943883752822876,
|
|
"epoch": 3.193232368670965,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00040002036469148486,
|
|
"loss": 5.455,
|
|
"mean_token_accuracy": 0.19837071895599365,
|
|
"num_tokens": 62499261.0,
|
|
"step": 31945
|
|
},
|
|
{
|
|
"entropy": 6.027377080917359,
|
|
"epoch": 3.1937321937321936,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00039999069052389384,
|
|
"loss": 5.6048,
|
|
"mean_token_accuracy": 0.18433847427368164,
|
|
"num_tokens": 62509513.0,
|
|
"step": 31950
|
|
},
|
|
{
|
|
"entropy": 5.958047914505005,
|
|
"epoch": 3.1942320187934223,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00039996101321156926,
|
|
"loss": 5.4679,
|
|
"mean_token_accuracy": 0.1968442603945732,
|
|
"num_tokens": 62518711.0,
|
|
"step": 31955
|
|
},
|
|
{
|
|
"entropy": 5.9646430015563965,
|
|
"epoch": 3.194731843854651,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00039993133275525777,
|
|
"loss": 5.4708,
|
|
"mean_token_accuracy": 0.18882942646741868,
|
|
"num_tokens": 62529495.0,
|
|
"step": 31960
|
|
},
|
|
{
|
|
"entropy": 6.011513042449951,
|
|
"epoch": 3.1952316689158793,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000399901649155706,
|
|
"loss": 5.5722,
|
|
"mean_token_accuracy": 0.18512096703052522,
|
|
"num_tokens": 62539263.0,
|
|
"step": 31965
|
|
},
|
|
{
|
|
"entropy": 6.039476537704468,
|
|
"epoch": 3.195731493977108,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00039987196241366086,
|
|
"loss": 5.5926,
|
|
"mean_token_accuracy": 0.18813793659210204,
|
|
"num_tokens": 62548708.0,
|
|
"step": 31970
|
|
},
|
|
{
|
|
"entropy": 6.0087402820587155,
|
|
"epoch": 3.1962313190383367,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00039984227252986936,
|
|
"loss": 5.4515,
|
|
"mean_token_accuracy": 0.19327920228242873,
|
|
"num_tokens": 62558051.0,
|
|
"step": 31975
|
|
},
|
|
{
|
|
"entropy": 5.977998876571656,
|
|
"epoch": 3.196731144099565,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00039981257950507835,
|
|
"loss": 5.5502,
|
|
"mean_token_accuracy": 0.19024235010147095,
|
|
"num_tokens": 62568741.0,
|
|
"step": 31980
|
|
},
|
|
{
|
|
"entropy": 5.859783792495728,
|
|
"epoch": 3.1972309691607936,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.000399782883340035,
|
|
"loss": 5.3968,
|
|
"mean_token_accuracy": 0.20742938071489334,
|
|
"num_tokens": 62578695.0,
|
|
"step": 31985
|
|
},
|
|
{
|
|
"entropy": 5.900671815872192,
|
|
"epoch": 3.1977307942220223,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0003997531840354865,
|
|
"loss": 5.3051,
|
|
"mean_token_accuracy": 0.21617020964622496,
|
|
"num_tokens": 62588282.0,
|
|
"step": 31990
|
|
},
|
|
{
|
|
"entropy": 5.959847545623779,
|
|
"epoch": 3.198230619283251,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00039972348159217987,
|
|
"loss": 5.4827,
|
|
"mean_token_accuracy": 0.19162984788417817,
|
|
"num_tokens": 62597502.0,
|
|
"step": 31995
|
|
},
|
|
{
|
|
"entropy": 5.920942211151123,
|
|
"epoch": 3.1987304443444793,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00039969377601086257,
|
|
"loss": 5.5066,
|
|
"mean_token_accuracy": 0.19503107219934462,
|
|
"num_tokens": 62607782.0,
|
|
"step": 32000
|
|
},
|
|
{
|
|
"entropy": 5.896142816543579,
|
|
"epoch": 3.199230269405708,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00039966406729228187,
|
|
"loss": 5.4382,
|
|
"mean_token_accuracy": 0.19980003833770751,
|
|
"num_tokens": 62617270.0,
|
|
"step": 32005
|
|
},
|
|
{
|
|
"entropy": 5.935961198806763,
|
|
"epoch": 3.1997300944669367,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00039963435543718544,
|
|
"loss": 5.4441,
|
|
"mean_token_accuracy": 0.200960573554039,
|
|
"num_tokens": 62627060.0,
|
|
"step": 32010
|
|
},
|
|
{
|
|
"entropy": 6.03423662185669,
|
|
"epoch": 3.200229919528165,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00039960464044632067,
|
|
"loss": 5.6243,
|
|
"mean_token_accuracy": 0.18170947432518006,
|
|
"num_tokens": 62637510.0,
|
|
"step": 32015
|
|
},
|
|
{
|
|
"entropy": 5.995988082885742,
|
|
"epoch": 3.2007297445893936,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0003995749223204351,
|
|
"loss": 5.4634,
|
|
"mean_token_accuracy": 0.19615570902824403,
|
|
"num_tokens": 62646666.0,
|
|
"step": 32020
|
|
},
|
|
{
|
|
"entropy": 5.9019652843475345,
|
|
"epoch": 3.2012295696506223,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0003995452010602767,
|
|
"loss": 5.5085,
|
|
"mean_token_accuracy": 0.19297758340835572,
|
|
"num_tokens": 62655909.0,
|
|
"step": 32025
|
|
},
|
|
{
|
|
"entropy": 5.866576337814331,
|
|
"epoch": 3.201729394711851,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00039951547666659305,
|
|
"loss": 5.4151,
|
|
"mean_token_accuracy": 0.19716638773679734,
|
|
"num_tokens": 62664405.0,
|
|
"step": 32030
|
|
},
|
|
{
|
|
"entropy": 5.957521677017212,
|
|
"epoch": 3.2022292197730793,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000399485749140132,
|
|
"loss": 5.4666,
|
|
"mean_token_accuracy": 0.19159817397594453,
|
|
"num_tokens": 62673813.0,
|
|
"step": 32035
|
|
},
|
|
{
|
|
"entropy": 5.95025405883789,
|
|
"epoch": 3.202729044834308,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00039945601848164153,
|
|
"loss": 5.4849,
|
|
"mean_token_accuracy": 0.18882200121879578,
|
|
"num_tokens": 62683711.0,
|
|
"step": 32040
|
|
},
|
|
{
|
|
"entropy": 5.904882001876831,
|
|
"epoch": 3.2032288698955367,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0003994262846918697,
|
|
"loss": 5.452,
|
|
"mean_token_accuracy": 0.1960326373577118,
|
|
"num_tokens": 62693868.0,
|
|
"step": 32045
|
|
},
|
|
{
|
|
"entropy": 5.989405488967895,
|
|
"epoch": 3.203728694956765,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00039939654777156454,
|
|
"loss": 5.5698,
|
|
"mean_token_accuracy": 0.18059938848018647,
|
|
"num_tokens": 62705459.0,
|
|
"step": 32050
|
|
},
|
|
{
|
|
"entropy": 5.990280199050903,
|
|
"epoch": 3.2042285200179936,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0003993668077214742,
|
|
"loss": 5.5954,
|
|
"mean_token_accuracy": 0.181866554915905,
|
|
"num_tokens": 62715725.0,
|
|
"step": 32055
|
|
},
|
|
{
|
|
"entropy": 5.878073406219483,
|
|
"epoch": 3.2047283450792223,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0003993370645423471,
|
|
"loss": 5.3842,
|
|
"mean_token_accuracy": 0.19487155377864837,
|
|
"num_tokens": 62725161.0,
|
|
"step": 32060
|
|
},
|
|
{
|
|
"entropy": 5.961828184127808,
|
|
"epoch": 3.205228170140451,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00039930731823493136,
|
|
"loss": 5.4695,
|
|
"mean_token_accuracy": 0.19084675163030623,
|
|
"num_tokens": 62733834.0,
|
|
"step": 32065
|
|
},
|
|
{
|
|
"entropy": 5.997138595581054,
|
|
"epoch": 3.2057279952016793,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00039927756879997556,
|
|
"loss": 5.5029,
|
|
"mean_token_accuracy": 0.18776375204324722,
|
|
"num_tokens": 62743875.0,
|
|
"step": 32070
|
|
},
|
|
{
|
|
"entropy": 5.965974807739258,
|
|
"epoch": 3.206227820262908,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00039924781623822803,
|
|
"loss": 5.4826,
|
|
"mean_token_accuracy": 0.19839407056570052,
|
|
"num_tokens": 62753354.0,
|
|
"step": 32075
|
|
},
|
|
{
|
|
"entropy": 5.937996053695679,
|
|
"epoch": 3.2067276453241367,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0003992180605504374,
|
|
"loss": 5.5051,
|
|
"mean_token_accuracy": 0.1924077793955803,
|
|
"num_tokens": 62763231.0,
|
|
"step": 32080
|
|
},
|
|
{
|
|
"entropy": 5.969790077209472,
|
|
"epoch": 3.207227470385365,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0003991883017373523,
|
|
"loss": 5.5799,
|
|
"mean_token_accuracy": 0.18577539920806885,
|
|
"num_tokens": 62773650.0,
|
|
"step": 32085
|
|
},
|
|
{
|
|
"entropy": 6.021047067642212,
|
|
"epoch": 3.2077272954465936,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0003991585397997216,
|
|
"loss": 5.5217,
|
|
"mean_token_accuracy": 0.18965620398521424,
|
|
"num_tokens": 62783021.0,
|
|
"step": 32090
|
|
},
|
|
{
|
|
"entropy": 5.953107213973999,
|
|
"epoch": 3.2082271205078223,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000399128774738294,
|
|
"loss": 5.4812,
|
|
"mean_token_accuracy": 0.1928168222308159,
|
|
"num_tokens": 62793698.0,
|
|
"step": 32095
|
|
},
|
|
{
|
|
"entropy": 6.011811113357544,
|
|
"epoch": 3.208726945569051,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0003990990065538183,
|
|
"loss": 5.5552,
|
|
"mean_token_accuracy": 0.18704302608966827,
|
|
"num_tokens": 62802742.0,
|
|
"step": 32100
|
|
},
|
|
{
|
|
"entropy": 5.976027107238769,
|
|
"epoch": 3.2092267706302793,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0003990692352470435,
|
|
"loss": 5.486,
|
|
"mean_token_accuracy": 0.19332744777202607,
|
|
"num_tokens": 62812809.0,
|
|
"step": 32105
|
|
},
|
|
{
|
|
"entropy": 5.917392110824585,
|
|
"epoch": 3.209726595691508,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00039903946081871865,
|
|
"loss": 5.4033,
|
|
"mean_token_accuracy": 0.1995804414153099,
|
|
"num_tokens": 62821577.0,
|
|
"step": 32110
|
|
},
|
|
{
|
|
"entropy": 5.820883750915527,
|
|
"epoch": 3.2102264207527367,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00039900968326959295,
|
|
"loss": 5.3965,
|
|
"mean_token_accuracy": 0.19622128307819367,
|
|
"num_tokens": 62830319.0,
|
|
"step": 32115
|
|
},
|
|
{
|
|
"entropy": 5.940261459350586,
|
|
"epoch": 3.210726245813965,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00039897990260041557,
|
|
"loss": 5.5317,
|
|
"mean_token_accuracy": 0.18833452463150024,
|
|
"num_tokens": 62840571.0,
|
|
"step": 32120
|
|
},
|
|
{
|
|
"entropy": 6.002398252487183,
|
|
"epoch": 3.2112260708751936,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0003989501188119357,
|
|
"loss": 5.4714,
|
|
"mean_token_accuracy": 0.19561624377965928,
|
|
"num_tokens": 62850916.0,
|
|
"step": 32125
|
|
},
|
|
{
|
|
"entropy": 5.93045015335083,
|
|
"epoch": 3.2117258959364223,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00039892033190490274,
|
|
"loss": 5.5068,
|
|
"mean_token_accuracy": 0.18760419487953187,
|
|
"num_tokens": 62860952.0,
|
|
"step": 32130
|
|
},
|
|
{
|
|
"entropy": 5.898148775100708,
|
|
"epoch": 3.212225720997651,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00039889054188006615,
|
|
"loss": 5.3836,
|
|
"mean_token_accuracy": 0.20390522927045823,
|
|
"num_tokens": 62871097.0,
|
|
"step": 32135
|
|
},
|
|
{
|
|
"entropy": 5.951409530639649,
|
|
"epoch": 3.2127255460588793,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0003988607487381753,
|
|
"loss": 5.426,
|
|
"mean_token_accuracy": 0.19566136300563813,
|
|
"num_tokens": 62881542.0,
|
|
"step": 32140
|
|
},
|
|
{
|
|
"entropy": 5.954371452331543,
|
|
"epoch": 3.213225371120108,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0003988309524799799,
|
|
"loss": 5.4145,
|
|
"mean_token_accuracy": 0.19618402272462845,
|
|
"num_tokens": 62891690.0,
|
|
"step": 32145
|
|
},
|
|
{
|
|
"entropy": 5.924855756759643,
|
|
"epoch": 3.2137251961813367,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00039880115310622974,
|
|
"loss": 5.4761,
|
|
"mean_token_accuracy": 0.18405429124832154,
|
|
"num_tokens": 62901663.0,
|
|
"step": 32150
|
|
},
|
|
{
|
|
"entropy": 5.986825704574585,
|
|
"epoch": 3.214225021242565,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00039877135061767424,
|
|
"loss": 5.5362,
|
|
"mean_token_accuracy": 0.18770390450954438,
|
|
"num_tokens": 62911782.0,
|
|
"step": 32155
|
|
},
|
|
{
|
|
"entropy": 6.065871620178223,
|
|
"epoch": 3.2147248463037936,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0003987415450150635,
|
|
"loss": 5.4959,
|
|
"mean_token_accuracy": 0.1981392666697502,
|
|
"num_tokens": 62922803.0,
|
|
"step": 32160
|
|
},
|
|
{
|
|
"entropy": 6.002687740325928,
|
|
"epoch": 3.2152246713650223,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00039871173629914736,
|
|
"loss": 5.5094,
|
|
"mean_token_accuracy": 0.19333816617727279,
|
|
"num_tokens": 62932166.0,
|
|
"step": 32165
|
|
},
|
|
{
|
|
"entropy": 5.9530130386352536,
|
|
"epoch": 3.215724496426251,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00039868192447067575,
|
|
"loss": 5.5374,
|
|
"mean_token_accuracy": 0.18767941892147064,
|
|
"num_tokens": 62941722.0,
|
|
"step": 32170
|
|
},
|
|
{
|
|
"entropy": 5.942202806472778,
|
|
"epoch": 3.2162243214874793,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00039865210953039863,
|
|
"loss": 5.5009,
|
|
"mean_token_accuracy": 0.19073086678981782,
|
|
"num_tokens": 62951148.0,
|
|
"step": 32175
|
|
},
|
|
{
|
|
"entropy": 5.920685148239135,
|
|
"epoch": 3.216724146548708,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0003986222914790664,
|
|
"loss": 5.4892,
|
|
"mean_token_accuracy": 0.1898471251130104,
|
|
"num_tokens": 62961156.0,
|
|
"step": 32180
|
|
},
|
|
{
|
|
"entropy": 5.906648015975952,
|
|
"epoch": 3.2172239716099367,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.00039859247031742907,
|
|
"loss": 5.4537,
|
|
"mean_token_accuracy": 0.19461354464292527,
|
|
"num_tokens": 62970902.0,
|
|
"step": 32185
|
|
},
|
|
{
|
|
"entropy": 5.9226147651672365,
|
|
"epoch": 3.217723796671165,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000398562646046237,
|
|
"loss": 5.4728,
|
|
"mean_token_accuracy": 0.18548427820205687,
|
|
"num_tokens": 62980137.0,
|
|
"step": 32190
|
|
},
|
|
{
|
|
"entropy": 6.000004482269287,
|
|
"epoch": 3.2182236217323936,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00039853281866624054,
|
|
"loss": 5.5627,
|
|
"mean_token_accuracy": 0.18927187472581863,
|
|
"num_tokens": 62989957.0,
|
|
"step": 32195
|
|
},
|
|
{
|
|
"entropy": 5.979886245727539,
|
|
"epoch": 3.2187234467936223,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00039850298817819017,
|
|
"loss": 5.4706,
|
|
"mean_token_accuracy": 0.19647155553102494,
|
|
"num_tokens": 62999043.0,
|
|
"step": 32200
|
|
},
|
|
{
|
|
"entropy": 5.962296819686889,
|
|
"epoch": 3.219223271854851,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0003984731545828364,
|
|
"loss": 5.4955,
|
|
"mean_token_accuracy": 0.1941283479332924,
|
|
"num_tokens": 63008858.0,
|
|
"step": 32205
|
|
},
|
|
{
|
|
"entropy": 5.971834182739258,
|
|
"epoch": 3.2197230969160793,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00039844331788092986,
|
|
"loss": 5.5093,
|
|
"mean_token_accuracy": 0.19040346443653106,
|
|
"num_tokens": 63017979.0,
|
|
"step": 32210
|
|
},
|
|
{
|
|
"entropy": 5.993889904022216,
|
|
"epoch": 3.220222921977308,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0003984134780732211,
|
|
"loss": 5.5175,
|
|
"mean_token_accuracy": 0.1834310546517372,
|
|
"num_tokens": 63027226.0,
|
|
"step": 32215
|
|
},
|
|
{
|
|
"entropy": 6.020875453948975,
|
|
"epoch": 3.2207227470385367,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0003983836351604611,
|
|
"loss": 5.5058,
|
|
"mean_token_accuracy": 0.18619866371154786,
|
|
"num_tokens": 63036822.0,
|
|
"step": 32220
|
|
},
|
|
{
|
|
"entropy": 5.9307252883911135,
|
|
"epoch": 3.221222572099765,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0003983537891434005,
|
|
"loss": 5.4859,
|
|
"mean_token_accuracy": 0.1927650734782219,
|
|
"num_tokens": 63048045.0,
|
|
"step": 32225
|
|
},
|
|
{
|
|
"entropy": 5.921756649017334,
|
|
"epoch": 3.2217223971609936,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0003983239400227903,
|
|
"loss": 5.4311,
|
|
"mean_token_accuracy": 0.18898901343345642,
|
|
"num_tokens": 63057528.0,
|
|
"step": 32230
|
|
},
|
|
{
|
|
"entropy": 5.985216188430786,
|
|
"epoch": 3.2222222222222223,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0003982940877993816,
|
|
"loss": 5.5291,
|
|
"mean_token_accuracy": 0.1891218140721321,
|
|
"num_tokens": 63067111.0,
|
|
"step": 32235
|
|
},
|
|
{
|
|
"entropy": 5.956599378585816,
|
|
"epoch": 3.222722047283451,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00039826423247392537,
|
|
"loss": 5.4575,
|
|
"mean_token_accuracy": 0.19601886123418807,
|
|
"num_tokens": 63078350.0,
|
|
"step": 32240
|
|
},
|
|
{
|
|
"entropy": 5.937183094024658,
|
|
"epoch": 3.2232218723446793,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0003982343740471727,
|
|
"loss": 5.5102,
|
|
"mean_token_accuracy": 0.19241268038749695,
|
|
"num_tokens": 63087459.0,
|
|
"step": 32245
|
|
},
|
|
{
|
|
"entropy": 5.954749965667725,
|
|
"epoch": 3.223721697405908,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00039820451251987494,
|
|
"loss": 5.4554,
|
|
"mean_token_accuracy": 0.19119566082954406,
|
|
"num_tokens": 63097095.0,
|
|
"step": 32250
|
|
},
|
|
{
|
|
"entropy": 5.930164575576782,
|
|
"epoch": 3.2242215224671367,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00039817464789278326,
|
|
"loss": 5.4688,
|
|
"mean_token_accuracy": 0.18957039415836335,
|
|
"num_tokens": 63106545.0,
|
|
"step": 32255
|
|
},
|
|
{
|
|
"entropy": 5.836164855957032,
|
|
"epoch": 3.224721347528365,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00039814478016664923,
|
|
"loss": 5.398,
|
|
"mean_token_accuracy": 0.20404874086380004,
|
|
"num_tokens": 63115624.0,
|
|
"step": 32260
|
|
},
|
|
{
|
|
"entropy": 6.017184925079346,
|
|
"epoch": 3.2252211725895936,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00039811490934222416,
|
|
"loss": 5.5832,
|
|
"mean_token_accuracy": 0.18034271597862245,
|
|
"num_tokens": 63126931.0,
|
|
"step": 32265
|
|
},
|
|
{
|
|
"entropy": 5.99272928237915,
|
|
"epoch": 3.2257209976508223,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0003980850354202598,
|
|
"loss": 5.489,
|
|
"mean_token_accuracy": 0.19535598307847976,
|
|
"num_tokens": 63137837.0,
|
|
"step": 32270
|
|
},
|
|
{
|
|
"entropy": 5.95709719657898,
|
|
"epoch": 3.226220822712051,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00039805515840150743,
|
|
"loss": 5.4664,
|
|
"mean_token_accuracy": 0.19199140667915343,
|
|
"num_tokens": 63147361.0,
|
|
"step": 32275
|
|
},
|
|
{
|
|
"entropy": 5.774520349502564,
|
|
"epoch": 3.2267206477732793,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00039802527828671896,
|
|
"loss": 5.2328,
|
|
"mean_token_accuracy": 0.2193585753440857,
|
|
"num_tokens": 63158059.0,
|
|
"step": 32280
|
|
},
|
|
{
|
|
"entropy": 5.983424329757691,
|
|
"epoch": 3.227220472834508,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0003979953950766462,
|
|
"loss": 5.49,
|
|
"mean_token_accuracy": 0.19275095462799072,
|
|
"num_tokens": 63167970.0,
|
|
"step": 32285
|
|
},
|
|
{
|
|
"entropy": 5.931370735168457,
|
|
"epoch": 3.2277202978957367,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00039796550877204095,
|
|
"loss": 5.393,
|
|
"mean_token_accuracy": 0.21315503120422363,
|
|
"num_tokens": 63176532.0,
|
|
"step": 32290
|
|
},
|
|
{
|
|
"entropy": 6.029599523544311,
|
|
"epoch": 3.228220122956965,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00039793561937365515,
|
|
"loss": 5.6472,
|
|
"mean_token_accuracy": 0.17147014290094376,
|
|
"num_tokens": 63185734.0,
|
|
"step": 32295
|
|
},
|
|
{
|
|
"entropy": 5.913270473480225,
|
|
"epoch": 3.2287199480181936,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00039790572688224075,
|
|
"loss": 5.4025,
|
|
"mean_token_accuracy": 0.19568155854940414,
|
|
"num_tokens": 63195458.0,
|
|
"step": 32300
|
|
},
|
|
{
|
|
"entropy": 5.949927520751953,
|
|
"epoch": 3.2292197730794223,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00039787583129854997,
|
|
"loss": 5.5205,
|
|
"mean_token_accuracy": 0.18591762483119964,
|
|
"num_tokens": 63205248.0,
|
|
"step": 32305
|
|
},
|
|
{
|
|
"entropy": 5.933763694763184,
|
|
"epoch": 3.2297195981406506,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0003978459326233349,
|
|
"loss": 5.4352,
|
|
"mean_token_accuracy": 0.19826154112815858,
|
|
"num_tokens": 63215327.0,
|
|
"step": 32310
|
|
},
|
|
{
|
|
"entropy": 6.082646417617798,
|
|
"epoch": 3.2302194232018793,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0003978160308573477,
|
|
"loss": 5.6251,
|
|
"mean_token_accuracy": 0.18413420468568803,
|
|
"num_tokens": 63225142.0,
|
|
"step": 32315
|
|
},
|
|
{
|
|
"entropy": 5.981820583343506,
|
|
"epoch": 3.230719248263108,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0003977861260013407,
|
|
"loss": 5.5264,
|
|
"mean_token_accuracy": 0.18556848615407945,
|
|
"num_tokens": 63233825.0,
|
|
"step": 32320
|
|
},
|
|
{
|
|
"entropy": 5.933321380615235,
|
|
"epoch": 3.2312190733243367,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0003977562180560665,
|
|
"loss": 5.5044,
|
|
"mean_token_accuracy": 0.18948459029197692,
|
|
"num_tokens": 63243389.0,
|
|
"step": 32325
|
|
},
|
|
{
|
|
"entropy": 5.93659234046936,
|
|
"epoch": 3.231718898385565,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0003977263070222774,
|
|
"loss": 5.4677,
|
|
"mean_token_accuracy": 0.1899391233921051,
|
|
"num_tokens": 63253684.0,
|
|
"step": 32330
|
|
},
|
|
{
|
|
"entropy": 5.94621467590332,
|
|
"epoch": 3.2322187234467936,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.000397696392900726,
|
|
"loss": 5.5017,
|
|
"mean_token_accuracy": 0.18899404406547546,
|
|
"num_tokens": 63263463.0,
|
|
"step": 32335
|
|
},
|
|
{
|
|
"entropy": 5.900418901443482,
|
|
"epoch": 3.2327185485080223,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0003976664756921649,
|
|
"loss": 5.3863,
|
|
"mean_token_accuracy": 0.20550207644701005,
|
|
"num_tokens": 63273274.0,
|
|
"step": 32340
|
|
},
|
|
{
|
|
"entropy": 5.96881947517395,
|
|
"epoch": 3.2332183735692506,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0003976365553973469,
|
|
"loss": 5.427,
|
|
"mean_token_accuracy": 0.1949423909187317,
|
|
"num_tokens": 63282429.0,
|
|
"step": 32345
|
|
},
|
|
{
|
|
"entropy": 5.873551845550537,
|
|
"epoch": 3.2337181986304793,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0003976066320170247,
|
|
"loss": 5.34,
|
|
"mean_token_accuracy": 0.20702901780605315,
|
|
"num_tokens": 63292356.0,
|
|
"step": 32350
|
|
},
|
|
{
|
|
"entropy": 5.8967209815979,
|
|
"epoch": 3.234218023691708,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00039757670555195114,
|
|
"loss": 5.5708,
|
|
"mean_token_accuracy": 0.18579607754945754,
|
|
"num_tokens": 63302852.0,
|
|
"step": 32355
|
|
},
|
|
{
|
|
"entropy": 5.964049291610718,
|
|
"epoch": 3.2347178487529367,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00039754677600287923,
|
|
"loss": 5.4428,
|
|
"mean_token_accuracy": 0.19680788218975068,
|
|
"num_tokens": 63313557.0,
|
|
"step": 32360
|
|
},
|
|
{
|
|
"entropy": 5.985125398635864,
|
|
"epoch": 3.235217673814165,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00039751684337056197,
|
|
"loss": 5.4705,
|
|
"mean_token_accuracy": 0.19015207439661025,
|
|
"num_tokens": 63323248.0,
|
|
"step": 32365
|
|
},
|
|
{
|
|
"entropy": 5.99817476272583,
|
|
"epoch": 3.2357174988753936,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0003974869076557525,
|
|
"loss": 5.5191,
|
|
"mean_token_accuracy": 0.1875983491539955,
|
|
"num_tokens": 63333698.0,
|
|
"step": 32370
|
|
},
|
|
{
|
|
"entropy": 5.915520286560058,
|
|
"epoch": 3.2362173239366223,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0003974569688592038,
|
|
"loss": 5.4666,
|
|
"mean_token_accuracy": 0.18660909533500672,
|
|
"num_tokens": 63343017.0,
|
|
"step": 32375
|
|
},
|
|
{
|
|
"entropy": 5.955946397781372,
|
|
"epoch": 3.2367171489978506,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0003974270269816695,
|
|
"loss": 5.4501,
|
|
"mean_token_accuracy": 0.18684629648923873,
|
|
"num_tokens": 63352165.0,
|
|
"step": 32380
|
|
},
|
|
{
|
|
"entropy": 6.004802083969116,
|
|
"epoch": 3.2372169740590793,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00039739708202390255,
|
|
"loss": 5.5244,
|
|
"mean_token_accuracy": 0.18421930372714995,
|
|
"num_tokens": 63360724.0,
|
|
"step": 32385
|
|
},
|
|
{
|
|
"entropy": 5.898009204864502,
|
|
"epoch": 3.237716799120308,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0003973671339866566,
|
|
"loss": 5.5282,
|
|
"mean_token_accuracy": 0.19126805663108826,
|
|
"num_tokens": 63370352.0,
|
|
"step": 32390
|
|
},
|
|
{
|
|
"entropy": 5.907414245605469,
|
|
"epoch": 3.2382166241815367,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.00039733718287068495,
|
|
"loss": 5.381,
|
|
"mean_token_accuracy": 0.20191751122474672,
|
|
"num_tokens": 63380155.0,
|
|
"step": 32395
|
|
},
|
|
{
|
|
"entropy": 5.859576082229614,
|
|
"epoch": 3.238716449242765,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0003973072286767413,
|
|
"loss": 5.3498,
|
|
"mean_token_accuracy": 0.20571786314249038,
|
|
"num_tokens": 63389472.0,
|
|
"step": 32400
|
|
},
|
|
{
|
|
"entropy": 5.906685638427734,
|
|
"epoch": 3.2392162743039936,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0003972772714055793,
|
|
"loss": 5.475,
|
|
"mean_token_accuracy": 0.19482003152370453,
|
|
"num_tokens": 63400004.0,
|
|
"step": 32405
|
|
},
|
|
{
|
|
"entropy": 5.917477655410766,
|
|
"epoch": 3.2397160993652223,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00039724731105795255,
|
|
"loss": 5.4629,
|
|
"mean_token_accuracy": 0.19717988073825837,
|
|
"num_tokens": 63410685.0,
|
|
"step": 32410
|
|
},
|
|
{
|
|
"entropy": 5.9321308612823485,
|
|
"epoch": 3.2402159244264506,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.000397217347634615,
|
|
"loss": 5.4166,
|
|
"mean_token_accuracy": 0.2035890743136406,
|
|
"num_tokens": 63419659.0,
|
|
"step": 32415
|
|
},
|
|
{
|
|
"entropy": 5.8386616706848145,
|
|
"epoch": 3.2407157494876793,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0003971873811363203,
|
|
"loss": 5.3049,
|
|
"mean_token_accuracy": 0.21291651278734208,
|
|
"num_tokens": 63430740.0,
|
|
"step": 32420
|
|
},
|
|
{
|
|
"entropy": 5.9891375541687015,
|
|
"epoch": 3.241215574548908,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00039715741156382255,
|
|
"loss": 5.5902,
|
|
"mean_token_accuracy": 0.1818642795085907,
|
|
"num_tokens": 63440129.0,
|
|
"step": 32425
|
|
},
|
|
{
|
|
"entropy": 5.948035717010498,
|
|
"epoch": 3.241715399610136,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0003971274389178759,
|
|
"loss": 5.5432,
|
|
"mean_token_accuracy": 0.18264979273080825,
|
|
"num_tokens": 63449569.0,
|
|
"step": 32430
|
|
},
|
|
{
|
|
"entropy": 5.996486234664917,
|
|
"epoch": 3.242215224671365,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0003970974631992342,
|
|
"loss": 5.5069,
|
|
"mean_token_accuracy": 0.1900986522436142,
|
|
"num_tokens": 63458814.0,
|
|
"step": 32435
|
|
},
|
|
{
|
|
"entropy": 5.987437438964844,
|
|
"epoch": 3.2427150497325936,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0003970674844086517,
|
|
"loss": 5.539,
|
|
"mean_token_accuracy": 0.18755592703819274,
|
|
"num_tokens": 63468507.0,
|
|
"step": 32440
|
|
},
|
|
{
|
|
"entropy": 5.9895580291748045,
|
|
"epoch": 3.2432148747938223,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0003970375025468829,
|
|
"loss": 5.5369,
|
|
"mean_token_accuracy": 0.18626384437084198,
|
|
"num_tokens": 63477934.0,
|
|
"step": 32445
|
|
},
|
|
{
|
|
"entropy": 5.916245651245117,
|
|
"epoch": 3.2437146998550506,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00039700751761468175,
|
|
"loss": 5.455,
|
|
"mean_token_accuracy": 0.19152401387691498,
|
|
"num_tokens": 63488799.0,
|
|
"step": 32450
|
|
},
|
|
{
|
|
"entropy": 5.9978334426879885,
|
|
"epoch": 3.2442145249162793,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0003969775296128029,
|
|
"loss": 5.511,
|
|
"mean_token_accuracy": 0.18875336647033691,
|
|
"num_tokens": 63497664.0,
|
|
"step": 32455
|
|
},
|
|
{
|
|
"entropy": 5.901860666275025,
|
|
"epoch": 3.244714349977508,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0003969475385420008,
|
|
"loss": 5.4683,
|
|
"mean_token_accuracy": 0.19414547830820084,
|
|
"num_tokens": 63507775.0,
|
|
"step": 32460
|
|
},
|
|
{
|
|
"entropy": 5.91322431564331,
|
|
"epoch": 3.245214175038736,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00039691754440303003,
|
|
"loss": 5.4549,
|
|
"mean_token_accuracy": 0.19056464582681656,
|
|
"num_tokens": 63517379.0,
|
|
"step": 32465
|
|
},
|
|
{
|
|
"entropy": 5.983073997497558,
|
|
"epoch": 3.245714000099965,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00039688754719664516,
|
|
"loss": 5.4959,
|
|
"mean_token_accuracy": 0.19126543700695037,
|
|
"num_tokens": 63528012.0,
|
|
"step": 32470
|
|
},
|
|
{
|
|
"entropy": 6.024136209487915,
|
|
"epoch": 3.2462138251611936,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.000396857546923601,
|
|
"loss": 5.5503,
|
|
"mean_token_accuracy": 0.1883141130208969,
|
|
"num_tokens": 63537226.0,
|
|
"step": 32475
|
|
},
|
|
{
|
|
"entropy": 6.106269407272339,
|
|
"epoch": 3.2467136502224223,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0003968275435846523,
|
|
"loss": 5.6286,
|
|
"mean_token_accuracy": 0.17761726528406144,
|
|
"num_tokens": 63548470.0,
|
|
"step": 32480
|
|
},
|
|
{
|
|
"entropy": 6.118303012847901,
|
|
"epoch": 3.2472134752836506,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000396797537180554,
|
|
"loss": 5.6321,
|
|
"mean_token_accuracy": 0.18147435337305068,
|
|
"num_tokens": 63559254.0,
|
|
"step": 32485
|
|
},
|
|
{
|
|
"entropy": 5.927468872070312,
|
|
"epoch": 3.2477133003448793,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000396767527712061,
|
|
"loss": 5.4149,
|
|
"mean_token_accuracy": 0.2022380769252777,
|
|
"num_tokens": 63568772.0,
|
|
"step": 32490
|
|
},
|
|
{
|
|
"entropy": 5.910913562774658,
|
|
"epoch": 3.248213125406108,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00039673751517992827,
|
|
"loss": 5.5098,
|
|
"mean_token_accuracy": 0.1877431496977806,
|
|
"num_tokens": 63579331.0,
|
|
"step": 32495
|
|
},
|
|
{
|
|
"entropy": 5.9413903713226315,
|
|
"epoch": 3.248712950467336,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00039670749958491103,
|
|
"loss": 5.433,
|
|
"mean_token_accuracy": 0.19422514289617537,
|
|
"num_tokens": 63588616.0,
|
|
"step": 32500
|
|
},
|
|
{
|
|
"entropy": 5.945079278945923,
|
|
"epoch": 3.249212775528565,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00039667748092776453,
|
|
"loss": 5.3973,
|
|
"mean_token_accuracy": 0.2053944319486618,
|
|
"num_tokens": 63598989.0,
|
|
"step": 32505
|
|
},
|
|
{
|
|
"entropy": 5.9182820320129395,
|
|
"epoch": 3.2497126005897936,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00039664745920924374,
|
|
"loss": 5.4336,
|
|
"mean_token_accuracy": 0.1936650887131691,
|
|
"num_tokens": 63609568.0,
|
|
"step": 32510
|
|
},
|
|
{
|
|
"entropy": 5.964445781707764,
|
|
"epoch": 3.2502124256510223,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0003966174344301043,
|
|
"loss": 5.5681,
|
|
"mean_token_accuracy": 0.19036237001419068,
|
|
"num_tokens": 63619561.0,
|
|
"step": 32515
|
|
},
|
|
{
|
|
"entropy": 6.011283445358276,
|
|
"epoch": 3.2507122507122506,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0003965874065911014,
|
|
"loss": 5.5527,
|
|
"mean_token_accuracy": 0.18582680970430374,
|
|
"num_tokens": 63629881.0,
|
|
"step": 32520
|
|
},
|
|
{
|
|
"entropy": 5.999875164031982,
|
|
"epoch": 3.2512120757734793,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00039655737569299073,
|
|
"loss": 5.5488,
|
|
"mean_token_accuracy": 0.191310878098011,
|
|
"num_tokens": 63640897.0,
|
|
"step": 32525
|
|
},
|
|
{
|
|
"entropy": 5.979747200012207,
|
|
"epoch": 3.251711900834708,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0003965273417365277,
|
|
"loss": 5.5216,
|
|
"mean_token_accuracy": 0.18923893123865126,
|
|
"num_tokens": 63651031.0,
|
|
"step": 32530
|
|
},
|
|
{
|
|
"entropy": 5.953755617141724,
|
|
"epoch": 3.252211725895936,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00039649730472246796,
|
|
"loss": 5.4015,
|
|
"mean_token_accuracy": 0.19785789102315904,
|
|
"num_tokens": 63661961.0,
|
|
"step": 32535
|
|
},
|
|
{
|
|
"entropy": 5.7822737216949465,
|
|
"epoch": 3.252711550957165,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0003964672646515674,
|
|
"loss": 5.2346,
|
|
"mean_token_accuracy": 0.21566050499677658,
|
|
"num_tokens": 63672495.0,
|
|
"step": 32540
|
|
},
|
|
{
|
|
"entropy": 5.798746776580811,
|
|
"epoch": 3.2532113760183936,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.0003964372215245817,
|
|
"loss": 5.3493,
|
|
"mean_token_accuracy": 0.20777523666620254,
|
|
"num_tokens": 63682792.0,
|
|
"step": 32545
|
|
},
|
|
{
|
|
"entropy": 5.972514677047729,
|
|
"epoch": 3.2537112010796223,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00039640717534226684,
|
|
"loss": 5.5615,
|
|
"mean_token_accuracy": 0.18724046200513839,
|
|
"num_tokens": 63692940.0,
|
|
"step": 32550
|
|
},
|
|
{
|
|
"entropy": 6.04606990814209,
|
|
"epoch": 3.2542110261408506,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0003963771261053786,
|
|
"loss": 5.5632,
|
|
"mean_token_accuracy": 0.18522105664014815,
|
|
"num_tokens": 63703347.0,
|
|
"step": 32555
|
|
},
|
|
{
|
|
"entropy": 5.978206157684326,
|
|
"epoch": 3.2547108512020793,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00039634707381467303,
|
|
"loss": 5.5538,
|
|
"mean_token_accuracy": 0.1906444936990738,
|
|
"num_tokens": 63713776.0,
|
|
"step": 32560
|
|
},
|
|
{
|
|
"entropy": 5.977937936782837,
|
|
"epoch": 3.255210676263308,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0003963170184709064,
|
|
"loss": 5.5566,
|
|
"mean_token_accuracy": 0.18342183977365495,
|
|
"num_tokens": 63723507.0,
|
|
"step": 32565
|
|
},
|
|
{
|
|
"entropy": 5.894962358474731,
|
|
"epoch": 3.255710501324536,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00039628696007483477,
|
|
"loss": 5.3957,
|
|
"mean_token_accuracy": 0.19929590523242952,
|
|
"num_tokens": 63733278.0,
|
|
"step": 32570
|
|
},
|
|
{
|
|
"entropy": 5.873308706283569,
|
|
"epoch": 3.256210326385765,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00039625689862721447,
|
|
"loss": 5.3661,
|
|
"mean_token_accuracy": 0.21372217386960984,
|
|
"num_tokens": 63742205.0,
|
|
"step": 32575
|
|
},
|
|
{
|
|
"entropy": 5.956088495254517,
|
|
"epoch": 3.2567101514469936,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00039622683412880174,
|
|
"loss": 5.542,
|
|
"mean_token_accuracy": 0.18649986237287522,
|
|
"num_tokens": 63752908.0,
|
|
"step": 32580
|
|
},
|
|
{
|
|
"entropy": 5.971355295181274,
|
|
"epoch": 3.2572099765082223,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0003961967665803532,
|
|
"loss": 5.5683,
|
|
"mean_token_accuracy": 0.18700272738933563,
|
|
"num_tokens": 63762682.0,
|
|
"step": 32585
|
|
},
|
|
{
|
|
"entropy": 5.93848729133606,
|
|
"epoch": 3.2577098015694506,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00039616669598262504,
|
|
"loss": 5.4562,
|
|
"mean_token_accuracy": 0.19077215641736983,
|
|
"num_tokens": 63771757.0,
|
|
"step": 32590
|
|
},
|
|
{
|
|
"entropy": 5.976434755325317,
|
|
"epoch": 3.2582096266306793,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00039613662233637406,
|
|
"loss": 5.5005,
|
|
"mean_token_accuracy": 0.19158951044082642,
|
|
"num_tokens": 63780805.0,
|
|
"step": 32595
|
|
},
|
|
{
|
|
"entropy": 5.955968046188355,
|
|
"epoch": 3.258709451691908,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00039610654564235684,
|
|
"loss": 5.4765,
|
|
"mean_token_accuracy": 0.18495263457298278,
|
|
"num_tokens": 63790279.0,
|
|
"step": 32600
|
|
},
|
|
{
|
|
"entropy": 6.080842065811157,
|
|
"epoch": 3.259209276753136,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0003960764659013301,
|
|
"loss": 5.576,
|
|
"mean_token_accuracy": 0.18645012378692627,
|
|
"num_tokens": 63799788.0,
|
|
"step": 32605
|
|
},
|
|
{
|
|
"entropy": 6.053795337677002,
|
|
"epoch": 3.259709101814365,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0003960463831140505,
|
|
"loss": 5.5418,
|
|
"mean_token_accuracy": 0.19028252959251404,
|
|
"num_tokens": 63810020.0,
|
|
"step": 32610
|
|
},
|
|
{
|
|
"entropy": 5.934622430801392,
|
|
"epoch": 3.2602089268755936,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00039601629728127524,
|
|
"loss": 5.489,
|
|
"mean_token_accuracy": 0.19516502171754838,
|
|
"num_tokens": 63819174.0,
|
|
"step": 32615
|
|
},
|
|
{
|
|
"entropy": 5.886014604568482,
|
|
"epoch": 3.2607087519368223,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00039598620840376096,
|
|
"loss": 5.4476,
|
|
"mean_token_accuracy": 0.1956273213028908,
|
|
"num_tokens": 63830199.0,
|
|
"step": 32620
|
|
},
|
|
{
|
|
"entropy": 5.938934230804444,
|
|
"epoch": 3.2612085769980506,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00039595611648226485,
|
|
"loss": 5.4674,
|
|
"mean_token_accuracy": 0.19726410657167434,
|
|
"num_tokens": 63839570.0,
|
|
"step": 32625
|
|
},
|
|
{
|
|
"entropy": 5.943731307983398,
|
|
"epoch": 3.2617084020592793,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000395926021517544,
|
|
"loss": 5.4636,
|
|
"mean_token_accuracy": 0.19775892347097396,
|
|
"num_tokens": 63848817.0,
|
|
"step": 32630
|
|
},
|
|
{
|
|
"entropy": 6.009447240829468,
|
|
"epoch": 3.262208227120508,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00039589592351035554,
|
|
"loss": 5.5143,
|
|
"mean_token_accuracy": 0.19021005183458328,
|
|
"num_tokens": 63858057.0,
|
|
"step": 32635
|
|
},
|
|
{
|
|
"entropy": 5.9571298122406,
|
|
"epoch": 3.262708052181736,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0003958658224614567,
|
|
"loss": 5.5051,
|
|
"mean_token_accuracy": 0.1973468169569969,
|
|
"num_tokens": 63868105.0,
|
|
"step": 32640
|
|
},
|
|
{
|
|
"entropy": 5.928451251983643,
|
|
"epoch": 3.263207877242965,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00039583571837160497,
|
|
"loss": 5.4927,
|
|
"mean_token_accuracy": 0.18794523030519486,
|
|
"num_tokens": 63879126.0,
|
|
"step": 32645
|
|
},
|
|
{
|
|
"entropy": 6.011271524429321,
|
|
"epoch": 3.2637077023041936,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0003958056112415576,
|
|
"loss": 5.4899,
|
|
"mean_token_accuracy": 0.1925611525774002,
|
|
"num_tokens": 63889045.0,
|
|
"step": 32650
|
|
},
|
|
{
|
|
"entropy": 6.0046311378479,
|
|
"epoch": 3.2642075273654223,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0003957755010720721,
|
|
"loss": 5.5179,
|
|
"mean_token_accuracy": 0.18667396008968354,
|
|
"num_tokens": 63899167.0,
|
|
"step": 32655
|
|
},
|
|
{
|
|
"entropy": 5.975201416015625,
|
|
"epoch": 3.2647073524266506,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00039574538786390617,
|
|
"loss": 5.4693,
|
|
"mean_token_accuracy": 0.19099191427230836,
|
|
"num_tokens": 63909591.0,
|
|
"step": 32660
|
|
},
|
|
{
|
|
"entropy": 5.961937952041626,
|
|
"epoch": 3.2652071774878793,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0003957152716178173,
|
|
"loss": 5.5087,
|
|
"mean_token_accuracy": 0.18780390918254852,
|
|
"num_tokens": 63918975.0,
|
|
"step": 32665
|
|
},
|
|
{
|
|
"entropy": 6.0063282489776615,
|
|
"epoch": 3.265707002549108,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00039568515233456326,
|
|
"loss": 5.4797,
|
|
"mean_token_accuracy": 0.190560881793499,
|
|
"num_tokens": 63928618.0,
|
|
"step": 32670
|
|
},
|
|
{
|
|
"entropy": 6.000592565536499,
|
|
"epoch": 3.266206827610336,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0003956550300149018,
|
|
"loss": 5.4655,
|
|
"mean_token_accuracy": 0.19145485013723373,
|
|
"num_tokens": 63938581.0,
|
|
"step": 32675
|
|
},
|
|
{
|
|
"entropy": 6.031433820724487,
|
|
"epoch": 3.266706652671565,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0003956249046595909,
|
|
"loss": 5.4597,
|
|
"mean_token_accuracy": 0.19397959113121033,
|
|
"num_tokens": 63947842.0,
|
|
"step": 32680
|
|
},
|
|
{
|
|
"entropy": 6.048959541320801,
|
|
"epoch": 3.2672064777327936,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0003955947762693884,
|
|
"loss": 5.5374,
|
|
"mean_token_accuracy": 0.1853583738207817,
|
|
"num_tokens": 63956975.0,
|
|
"step": 32685
|
|
},
|
|
{
|
|
"entropy": 5.963301515579223,
|
|
"epoch": 3.2677063027940223,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00039556464484505235,
|
|
"loss": 5.5589,
|
|
"mean_token_accuracy": 0.18978646993637086,
|
|
"num_tokens": 63966215.0,
|
|
"step": 32690
|
|
},
|
|
{
|
|
"entropy": 5.9432666301727295,
|
|
"epoch": 3.2682061278552506,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0003955345103873409,
|
|
"loss": 5.4415,
|
|
"mean_token_accuracy": 0.1987342432141304,
|
|
"num_tokens": 63975440.0,
|
|
"step": 32695
|
|
},
|
|
{
|
|
"entropy": 5.952206420898437,
|
|
"epoch": 3.2687059529164793,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0003955043728970121,
|
|
"loss": 5.4801,
|
|
"mean_token_accuracy": 0.19866942763328552,
|
|
"num_tokens": 63984616.0,
|
|
"step": 32700
|
|
},
|
|
{
|
|
"entropy": 5.943383407592774,
|
|
"epoch": 3.269205777977708,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0003954742323748244,
|
|
"loss": 5.4813,
|
|
"mean_token_accuracy": 0.19550982862710953,
|
|
"num_tokens": 63994792.0,
|
|
"step": 32705
|
|
},
|
|
{
|
|
"entropy": 6.03586163520813,
|
|
"epoch": 3.269705603038936,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00039544408882153596,
|
|
"loss": 5.6328,
|
|
"mean_token_accuracy": 0.18475722521543503,
|
|
"num_tokens": 64005068.0,
|
|
"step": 32710
|
|
},
|
|
{
|
|
"entropy": 6.024407815933228,
|
|
"epoch": 3.270205428100165,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0003954139422379052,
|
|
"loss": 5.5563,
|
|
"mean_token_accuracy": 0.1884896069765091,
|
|
"num_tokens": 64014393.0,
|
|
"step": 32715
|
|
},
|
|
{
|
|
"entropy": 6.038368892669678,
|
|
"epoch": 3.2707052531613936,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0003953837926246907,
|
|
"loss": 5.4628,
|
|
"mean_token_accuracy": 0.18459360748529435,
|
|
"num_tokens": 64024310.0,
|
|
"step": 32720
|
|
},
|
|
{
|
|
"entropy": 6.005084991455078,
|
|
"epoch": 3.2712050782226223,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00039535363998265095,
|
|
"loss": 5.5988,
|
|
"mean_token_accuracy": 0.1830632895231247,
|
|
"num_tokens": 64033867.0,
|
|
"step": 32725
|
|
},
|
|
{
|
|
"entropy": 6.0081240177154545,
|
|
"epoch": 3.2717049032838506,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00039532348431254455,
|
|
"loss": 5.5297,
|
|
"mean_token_accuracy": 0.18494281470775603,
|
|
"num_tokens": 64044548.0,
|
|
"step": 32730
|
|
},
|
|
{
|
|
"entropy": 6.067212295532227,
|
|
"epoch": 3.2722047283450792,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0003952933256151303,
|
|
"loss": 5.5932,
|
|
"mean_token_accuracy": 0.18227040022611618,
|
|
"num_tokens": 64054360.0,
|
|
"step": 32735
|
|
},
|
|
{
|
|
"entropy": 5.876645231246949,
|
|
"epoch": 3.272704553406308,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0003952631638911669,
|
|
"loss": 5.3629,
|
|
"mean_token_accuracy": 0.19853029102087022,
|
|
"num_tokens": 64065181.0,
|
|
"step": 32740
|
|
},
|
|
{
|
|
"entropy": 5.938180351257325,
|
|
"epoch": 3.273204378467536,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0003952329991414132,
|
|
"loss": 5.4124,
|
|
"mean_token_accuracy": 0.19581257402896882,
|
|
"num_tokens": 64075052.0,
|
|
"step": 32745
|
|
},
|
|
{
|
|
"entropy": 5.9401486873626705,
|
|
"epoch": 3.273704203528765,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00039520283136662825,
|
|
"loss": 5.4785,
|
|
"mean_token_accuracy": 0.19122551530599594,
|
|
"num_tokens": 64083934.0,
|
|
"step": 32750
|
|
},
|
|
{
|
|
"entropy": 5.981229829788208,
|
|
"epoch": 3.2742040285899936,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00039517266056757097,
|
|
"loss": 5.5413,
|
|
"mean_token_accuracy": 0.18074856996536254,
|
|
"num_tokens": 64094402.0,
|
|
"step": 32755
|
|
},
|
|
{
|
|
"entropy": 5.943113803863525,
|
|
"epoch": 3.2747038536512223,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00039514248674500055,
|
|
"loss": 5.4723,
|
|
"mean_token_accuracy": 0.18644844144582748,
|
|
"num_tokens": 64103681.0,
|
|
"step": 32760
|
|
},
|
|
{
|
|
"entropy": 5.982483673095703,
|
|
"epoch": 3.2752036787124506,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00039511230989967594,
|
|
"loss": 5.4976,
|
|
"mean_token_accuracy": 0.18322503119707106,
|
|
"num_tokens": 64113332.0,
|
|
"step": 32765
|
|
},
|
|
{
|
|
"entropy": 5.9375683784484865,
|
|
"epoch": 3.2757035037736792,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0003950821300323566,
|
|
"loss": 5.5124,
|
|
"mean_token_accuracy": 0.19627835005521774,
|
|
"num_tokens": 64123079.0,
|
|
"step": 32770
|
|
},
|
|
{
|
|
"entropy": 5.991313076019287,
|
|
"epoch": 3.276203328834908,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0003950519471438017,
|
|
"loss": 5.5167,
|
|
"mean_token_accuracy": 0.19078685939311982,
|
|
"num_tokens": 64134034.0,
|
|
"step": 32775
|
|
},
|
|
{
|
|
"entropy": 5.943087244033814,
|
|
"epoch": 3.276703153896136,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00039502176123477076,
|
|
"loss": 5.2805,
|
|
"mean_token_accuracy": 0.20638687610626222,
|
|
"num_tokens": 64144157.0,
|
|
"step": 32780
|
|
},
|
|
{
|
|
"entropy": 5.973707771301269,
|
|
"epoch": 3.277202978957365,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00039499157230602313,
|
|
"loss": 5.4924,
|
|
"mean_token_accuracy": 0.20116790980100632,
|
|
"num_tokens": 64154150.0,
|
|
"step": 32785
|
|
},
|
|
{
|
|
"entropy": 5.919702005386353,
|
|
"epoch": 3.2777028040185936,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00039496138035831845,
|
|
"loss": 5.4432,
|
|
"mean_token_accuracy": 0.1982642114162445,
|
|
"num_tokens": 64163553.0,
|
|
"step": 32790
|
|
},
|
|
{
|
|
"entropy": 5.886202335357666,
|
|
"epoch": 3.2782026290798223,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00039493118539241643,
|
|
"loss": 5.4304,
|
|
"mean_token_accuracy": 0.1968575745820999,
|
|
"num_tokens": 64173735.0,
|
|
"step": 32795
|
|
},
|
|
{
|
|
"entropy": 5.857209157943726,
|
|
"epoch": 3.2787024541410505,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00039490098740907654,
|
|
"loss": 5.3831,
|
|
"mean_token_accuracy": 0.2006188616156578,
|
|
"num_tokens": 64183501.0,
|
|
"step": 32800
|
|
},
|
|
{
|
|
"entropy": 5.908825016021728,
|
|
"epoch": 3.2792022792022792,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00039487078640905866,
|
|
"loss": 5.4082,
|
|
"mean_token_accuracy": 0.19570671916007995,
|
|
"num_tokens": 64192131.0,
|
|
"step": 32805
|
|
},
|
|
{
|
|
"entropy": 5.918664503097534,
|
|
"epoch": 3.279702104263508,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00039484058239312264,
|
|
"loss": 5.5339,
|
|
"mean_token_accuracy": 0.1952373906970024,
|
|
"num_tokens": 64201467.0,
|
|
"step": 32810
|
|
},
|
|
{
|
|
"entropy": 5.9345471382141115,
|
|
"epoch": 3.280201929324736,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00039481037536202835,
|
|
"loss": 5.516,
|
|
"mean_token_accuracy": 0.18744914531707763,
|
|
"num_tokens": 64213159.0,
|
|
"step": 32815
|
|
},
|
|
{
|
|
"entropy": 6.002274417877198,
|
|
"epoch": 3.280701754385965,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00039478016531653586,
|
|
"loss": 5.5535,
|
|
"mean_token_accuracy": 0.18248897194862365,
|
|
"num_tokens": 64223627.0,
|
|
"step": 32820
|
|
},
|
|
{
|
|
"entropy": 6.017393350601196,
|
|
"epoch": 3.2812015794471936,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00039474995225740526,
|
|
"loss": 5.5335,
|
|
"mean_token_accuracy": 0.18342894166707993,
|
|
"num_tokens": 64232920.0,
|
|
"step": 32825
|
|
},
|
|
{
|
|
"entropy": 5.935495328903198,
|
|
"epoch": 3.2817014045084223,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0003947197361853968,
|
|
"loss": 5.4582,
|
|
"mean_token_accuracy": 0.20051568746566772,
|
|
"num_tokens": 64242222.0,
|
|
"step": 32830
|
|
},
|
|
{
|
|
"entropy": 5.844779062271118,
|
|
"epoch": 3.2822012295696505,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00039468951710127043,
|
|
"loss": 5.3162,
|
|
"mean_token_accuracy": 0.21211963295936584,
|
|
"num_tokens": 64252065.0,
|
|
"step": 32835
|
|
},
|
|
{
|
|
"entropy": 5.948410606384277,
|
|
"epoch": 3.2827010546308792,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0003946592950057867,
|
|
"loss": 5.4727,
|
|
"mean_token_accuracy": 0.19567649215459823,
|
|
"num_tokens": 64262290.0,
|
|
"step": 32840
|
|
},
|
|
{
|
|
"entropy": 5.845480108261109,
|
|
"epoch": 3.283200879692108,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0003946290698997058,
|
|
"loss": 5.3525,
|
|
"mean_token_accuracy": 0.20303490310907363,
|
|
"num_tokens": 64270828.0,
|
|
"step": 32845
|
|
},
|
|
{
|
|
"entropy": 5.94779748916626,
|
|
"epoch": 3.283700704753336,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0003945988417837883,
|
|
"loss": 5.5658,
|
|
"mean_token_accuracy": 0.18812687397003175,
|
|
"num_tokens": 64281365.0,
|
|
"step": 32850
|
|
},
|
|
{
|
|
"entropy": 5.7381127834320065,
|
|
"epoch": 3.284200529814565,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0003945686106587948,
|
|
"loss": 5.2213,
|
|
"mean_token_accuracy": 0.2165135532617569,
|
|
"num_tokens": 64290954.0,
|
|
"step": 32855
|
|
},
|
|
{
|
|
"entropy": 5.944731569290161,
|
|
"epoch": 3.2847003548757936,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00039453837652548575,
|
|
"loss": 5.4371,
|
|
"mean_token_accuracy": 0.2005191072821617,
|
|
"num_tokens": 64300720.0,
|
|
"step": 32860
|
|
},
|
|
{
|
|
"entropy": 5.956956481933593,
|
|
"epoch": 3.2852001799370223,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00039450813938462197,
|
|
"loss": 5.5235,
|
|
"mean_token_accuracy": 0.18574778363108635,
|
|
"num_tokens": 64311164.0,
|
|
"step": 32865
|
|
},
|
|
{
|
|
"entropy": 5.981363821029663,
|
|
"epoch": 3.2857000049982505,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00039447789923696415,
|
|
"loss": 5.4999,
|
|
"mean_token_accuracy": 0.19257143288850784,
|
|
"num_tokens": 64321792.0,
|
|
"step": 32870
|
|
},
|
|
{
|
|
"entropy": 5.923344135284424,
|
|
"epoch": 3.2861998300594792,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000394447656083273,
|
|
"loss": 5.5772,
|
|
"mean_token_accuracy": 0.18468340039253234,
|
|
"num_tokens": 64331757.0,
|
|
"step": 32875
|
|
},
|
|
{
|
|
"entropy": 5.852582025527954,
|
|
"epoch": 3.286699655120708,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00039441740992430965,
|
|
"loss": 5.3326,
|
|
"mean_token_accuracy": 0.21252510845661163,
|
|
"num_tokens": 64341923.0,
|
|
"step": 32880
|
|
},
|
|
{
|
|
"entropy": 5.972553062438965,
|
|
"epoch": 3.287199480181936,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00039438716076083504,
|
|
"loss": 5.4676,
|
|
"mean_token_accuracy": 0.19411904513835906,
|
|
"num_tokens": 64351729.0,
|
|
"step": 32885
|
|
},
|
|
{
|
|
"entropy": 5.922009038925171,
|
|
"epoch": 3.287699305243165,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00039435690859361013,
|
|
"loss": 5.3886,
|
|
"mean_token_accuracy": 0.19540176540613174,
|
|
"num_tokens": 64362357.0,
|
|
"step": 32890
|
|
},
|
|
{
|
|
"entropy": 5.855547046661377,
|
|
"epoch": 3.2881991303043936,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00039432665342339614,
|
|
"loss": 5.3549,
|
|
"mean_token_accuracy": 0.20308560281991958,
|
|
"num_tokens": 64373800.0,
|
|
"step": 32895
|
|
},
|
|
{
|
|
"entropy": 5.959363031387329,
|
|
"epoch": 3.288698955365622,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0003942963952509543,
|
|
"loss": 5.5451,
|
|
"mean_token_accuracy": 0.1880182683467865,
|
|
"num_tokens": 64383329.0,
|
|
"step": 32900
|
|
},
|
|
{
|
|
"entropy": 5.928496980667115,
|
|
"epoch": 3.2891987804268505,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00039426613407704574,
|
|
"loss": 5.4434,
|
|
"mean_token_accuracy": 0.1896875336766243,
|
|
"num_tokens": 64391717.0,
|
|
"step": 32905
|
|
},
|
|
{
|
|
"entropy": 5.9267994403839115,
|
|
"epoch": 3.2896986054880792,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000394235869902432,
|
|
"loss": 5.4416,
|
|
"mean_token_accuracy": 0.20011298954486847,
|
|
"num_tokens": 64401496.0,
|
|
"step": 32910
|
|
},
|
|
{
|
|
"entropy": 5.895116567611694,
|
|
"epoch": 3.2901984305493075,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00039420560272787446,
|
|
"loss": 5.4283,
|
|
"mean_token_accuracy": 0.19712469726800919,
|
|
"num_tokens": 64411280.0,
|
|
"step": 32915
|
|
},
|
|
{
|
|
"entropy": 5.945271921157837,
|
|
"epoch": 3.290698255610536,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00039417533255413465,
|
|
"loss": 5.5098,
|
|
"mean_token_accuracy": 0.18726110756397246,
|
|
"num_tokens": 64421560.0,
|
|
"step": 32920
|
|
},
|
|
{
|
|
"entropy": 5.905635118484497,
|
|
"epoch": 3.291198080671765,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00039414505938197404,
|
|
"loss": 5.4559,
|
|
"mean_token_accuracy": 0.19626750499010087,
|
|
"num_tokens": 64432580.0,
|
|
"step": 32925
|
|
},
|
|
{
|
|
"entropy": 5.995359897613525,
|
|
"epoch": 3.2916979057329936,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0003941147832121545,
|
|
"loss": 5.4662,
|
|
"mean_token_accuracy": 0.1934517040848732,
|
|
"num_tokens": 64442937.0,
|
|
"step": 32930
|
|
},
|
|
{
|
|
"entropy": 5.97247200012207,
|
|
"epoch": 3.292197730794222,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0003940845040454376,
|
|
"loss": 5.5069,
|
|
"mean_token_accuracy": 0.18884942233562468,
|
|
"num_tokens": 64452763.0,
|
|
"step": 32935
|
|
},
|
|
{
|
|
"entropy": 5.8959722995758055,
|
|
"epoch": 3.2926975558554505,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0003940542218825853,
|
|
"loss": 5.4317,
|
|
"mean_token_accuracy": 0.19405391961336135,
|
|
"num_tokens": 64462036.0,
|
|
"step": 32940
|
|
},
|
|
{
|
|
"entropy": 5.963416814804077,
|
|
"epoch": 3.2931973809166792,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00039402393672435934,
|
|
"loss": 5.4978,
|
|
"mean_token_accuracy": 0.19447241276502608,
|
|
"num_tokens": 64472258.0,
|
|
"step": 32945
|
|
},
|
|
{
|
|
"entropy": 5.910714483261108,
|
|
"epoch": 3.2936972059779075,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00039399364857152177,
|
|
"loss": 5.4817,
|
|
"mean_token_accuracy": 0.19344239979982375,
|
|
"num_tokens": 64481521.0,
|
|
"step": 32950
|
|
},
|
|
{
|
|
"entropy": 5.987719106674194,
|
|
"epoch": 3.294197031039136,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0003939633574248346,
|
|
"loss": 5.5756,
|
|
"mean_token_accuracy": 0.1852563962340355,
|
|
"num_tokens": 64491561.0,
|
|
"step": 32955
|
|
},
|
|
{
|
|
"entropy": 5.984194231033325,
|
|
"epoch": 3.294696856100365,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00039393306328506004,
|
|
"loss": 5.4581,
|
|
"mean_token_accuracy": 0.18663376122713088,
|
|
"num_tokens": 64501408.0,
|
|
"step": 32960
|
|
},
|
|
{
|
|
"entropy": 5.924819993972778,
|
|
"epoch": 3.2951966811615936,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00039390276615296015,
|
|
"loss": 5.4438,
|
|
"mean_token_accuracy": 0.19239216893911362,
|
|
"num_tokens": 64510788.0,
|
|
"step": 32965
|
|
},
|
|
{
|
|
"entropy": 5.899043178558349,
|
|
"epoch": 3.295696506222822,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00039387246602929726,
|
|
"loss": 5.5479,
|
|
"mean_token_accuracy": 0.18524550944566726,
|
|
"num_tokens": 64521644.0,
|
|
"step": 32970
|
|
},
|
|
{
|
|
"entropy": 5.995121049880981,
|
|
"epoch": 3.2961963312840505,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0003938421629148338,
|
|
"loss": 5.4965,
|
|
"mean_token_accuracy": 0.2009488523006439,
|
|
"num_tokens": 64531209.0,
|
|
"step": 32975
|
|
},
|
|
{
|
|
"entropy": 6.068511915206909,
|
|
"epoch": 3.2966961563452792,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000393811856810332,
|
|
"loss": 5.6007,
|
|
"mean_token_accuracy": 0.1886782869696617,
|
|
"num_tokens": 64541280.0,
|
|
"step": 32980
|
|
},
|
|
{
|
|
"entropy": 5.909303092956543,
|
|
"epoch": 3.2971959814065075,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0003937815477165545,
|
|
"loss": 5.4785,
|
|
"mean_token_accuracy": 0.19109215438365937,
|
|
"num_tokens": 64552440.0,
|
|
"step": 32985
|
|
},
|
|
{
|
|
"entropy": 5.863267660140991,
|
|
"epoch": 3.297695806467736,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0003937512356342638,
|
|
"loss": 5.4347,
|
|
"mean_token_accuracy": 0.19618020057678223,
|
|
"num_tokens": 64561994.0,
|
|
"step": 32990
|
|
},
|
|
{
|
|
"entropy": 5.8985120296478275,
|
|
"epoch": 3.298195631528965,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0003937209205642226,
|
|
"loss": 5.3863,
|
|
"mean_token_accuracy": 0.19978415220975876,
|
|
"num_tokens": 64571022.0,
|
|
"step": 32995
|
|
},
|
|
{
|
|
"entropy": 5.942198371887207,
|
|
"epoch": 3.2986954565901936,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0003936906025071936,
|
|
"loss": 5.5897,
|
|
"mean_token_accuracy": 0.17952914535999298,
|
|
"num_tokens": 64581376.0,
|
|
"step": 33000
|
|
},
|
|
{
|
|
"epoch": 3.2986954565901936,
|
|
"eval_entropy": 5.737896766652769,
|
|
"eval_loss": 5.621498107910156,
|
|
"eval_mean_token_accuracy": 0.1947371522490203,
|
|
"eval_num_tokens": 64581376.0,
|
|
"eval_runtime": 23.6001,
|
|
"eval_samples_per_second": 1315.462,
|
|
"eval_steps_per_second": 164.449,
|
|
"step": 33000
|
|
},
|
|
{
|
|
"entropy": 6.003585958480835,
|
|
"epoch": 3.299195281651422,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00039366028146393955,
|
|
"loss": 5.4831,
|
|
"mean_token_accuracy": 0.19496664851903917,
|
|
"num_tokens": 64590656.0,
|
|
"step": 33005
|
|
},
|
|
{
|
|
"entropy": 5.965392208099365,
|
|
"epoch": 3.2996951067126505,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0003936299574352233,
|
|
"loss": 5.4428,
|
|
"mean_token_accuracy": 0.2017723798751831,
|
|
"num_tokens": 64601276.0,
|
|
"step": 33010
|
|
},
|
|
{
|
|
"entropy": 5.96477484703064,
|
|
"epoch": 3.3001949317738792,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.000393599630421808,
|
|
"loss": 5.4767,
|
|
"mean_token_accuracy": 0.19235289990901946,
|
|
"num_tokens": 64611251.0,
|
|
"step": 33015
|
|
},
|
|
{
|
|
"entropy": 5.986451435089111,
|
|
"epoch": 3.3006947568351075,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0003935693004244564,
|
|
"loss": 5.5214,
|
|
"mean_token_accuracy": 0.18912889808416367,
|
|
"num_tokens": 64619721.0,
|
|
"step": 33020
|
|
},
|
|
{
|
|
"entropy": 5.915600156784057,
|
|
"epoch": 3.301194581896336,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00039353896744393163,
|
|
"loss": 5.4377,
|
|
"mean_token_accuracy": 0.19524847269058226,
|
|
"num_tokens": 64629456.0,
|
|
"step": 33025
|
|
},
|
|
{
|
|
"entropy": 5.937558364868164,
|
|
"epoch": 3.301694406957565,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0003935086314809971,
|
|
"loss": 5.4364,
|
|
"mean_token_accuracy": 0.19289976805448533,
|
|
"num_tokens": 64639513.0,
|
|
"step": 33030
|
|
},
|
|
{
|
|
"entropy": 5.88983678817749,
|
|
"epoch": 3.3021942320187936,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00039347829253641583,
|
|
"loss": 5.3861,
|
|
"mean_token_accuracy": 0.19664547145366668,
|
|
"num_tokens": 64648653.0,
|
|
"step": 33035
|
|
},
|
|
{
|
|
"entropy": 5.9817955493927,
|
|
"epoch": 3.302694057080022,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00039344795061095123,
|
|
"loss": 5.5518,
|
|
"mean_token_accuracy": 0.19159853607416152,
|
|
"num_tokens": 64659566.0,
|
|
"step": 33040
|
|
},
|
|
{
|
|
"entropy": 5.894167232513428,
|
|
"epoch": 3.3031938821412505,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0003934176057053667,
|
|
"loss": 5.3803,
|
|
"mean_token_accuracy": 0.20240379273891448,
|
|
"num_tokens": 64669041.0,
|
|
"step": 33045
|
|
},
|
|
{
|
|
"entropy": 6.000369501113892,
|
|
"epoch": 3.3036937072024792,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00039338725782042563,
|
|
"loss": 5.5765,
|
|
"mean_token_accuracy": 0.1845160275697708,
|
|
"num_tokens": 64678262.0,
|
|
"step": 33050
|
|
},
|
|
{
|
|
"entropy": 5.851711177825928,
|
|
"epoch": 3.3041935322637075,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00039335690695689157,
|
|
"loss": 5.3629,
|
|
"mean_token_accuracy": 0.209077912569046,
|
|
"num_tokens": 64687530.0,
|
|
"step": 33055
|
|
},
|
|
{
|
|
"entropy": 6.037154340744019,
|
|
"epoch": 3.304693357324936,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0003933265531155283,
|
|
"loss": 5.6116,
|
|
"mean_token_accuracy": 0.18459556251764297,
|
|
"num_tokens": 64697034.0,
|
|
"step": 33060
|
|
},
|
|
{
|
|
"entropy": 6.015407848358154,
|
|
"epoch": 3.305193182386165,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00039329619629709935,
|
|
"loss": 5.5398,
|
|
"mean_token_accuracy": 0.1911531776189804,
|
|
"num_tokens": 64706047.0,
|
|
"step": 33065
|
|
},
|
|
{
|
|
"entropy": 5.994312715530396,
|
|
"epoch": 3.3056930074473936,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00039326583650236847,
|
|
"loss": 5.5725,
|
|
"mean_token_accuracy": 0.1933403193950653,
|
|
"num_tokens": 64715225.0,
|
|
"step": 33070
|
|
},
|
|
{
|
|
"entropy": 5.906211042404175,
|
|
"epoch": 3.306192832508622,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00039323547373209974,
|
|
"loss": 5.4503,
|
|
"mean_token_accuracy": 0.19305870980024337,
|
|
"num_tokens": 64724332.0,
|
|
"step": 33075
|
|
},
|
|
{
|
|
"entropy": 5.926331281661987,
|
|
"epoch": 3.3066926575698505,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00039320510798705684,
|
|
"loss": 5.4624,
|
|
"mean_token_accuracy": 0.19980597198009492,
|
|
"num_tokens": 64734022.0,
|
|
"step": 33080
|
|
},
|
|
{
|
|
"entropy": 5.9375348567962645,
|
|
"epoch": 3.3071924826310792,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0003931747392680038,
|
|
"loss": 5.4979,
|
|
"mean_token_accuracy": 0.19103476256132126,
|
|
"num_tokens": 64742677.0,
|
|
"step": 33085
|
|
},
|
|
{
|
|
"entropy": 5.945942163467407,
|
|
"epoch": 3.3076923076923075,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0003931443675757047,
|
|
"loss": 5.5158,
|
|
"mean_token_accuracy": 0.19395490139722824,
|
|
"num_tokens": 64752052.0,
|
|
"step": 33090
|
|
},
|
|
{
|
|
"entropy": 6.009165096282959,
|
|
"epoch": 3.308192132753536,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00039311399291092384,
|
|
"loss": 5.5162,
|
|
"mean_token_accuracy": 0.1894082859158516,
|
|
"num_tokens": 64761465.0,
|
|
"step": 33095
|
|
},
|
|
{
|
|
"entropy": 5.942259359359741,
|
|
"epoch": 3.308691957814765,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0003930836152744251,
|
|
"loss": 5.4622,
|
|
"mean_token_accuracy": 0.19514210075139998,
|
|
"num_tokens": 64772233.0,
|
|
"step": 33100
|
|
},
|
|
{
|
|
"entropy": 5.942761087417603,
|
|
"epoch": 3.3091917828759936,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00039305323466697317,
|
|
"loss": 5.4583,
|
|
"mean_token_accuracy": 0.19267103224992752,
|
|
"num_tokens": 64782006.0,
|
|
"step": 33105
|
|
},
|
|
{
|
|
"entropy": 5.991004276275635,
|
|
"epoch": 3.309691607937222,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00039302285108933224,
|
|
"loss": 5.4333,
|
|
"mean_token_accuracy": 0.19432367980480195,
|
|
"num_tokens": 64790755.0,
|
|
"step": 33110
|
|
},
|
|
{
|
|
"entropy": 5.844174909591675,
|
|
"epoch": 3.3101914329984505,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0003929924645422667,
|
|
"loss": 5.3922,
|
|
"mean_token_accuracy": 0.20360391438007355,
|
|
"num_tokens": 64800970.0,
|
|
"step": 33115
|
|
},
|
|
{
|
|
"entropy": 5.937156009674072,
|
|
"epoch": 3.3106912580596792,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00039296207502654103,
|
|
"loss": 5.5444,
|
|
"mean_token_accuracy": 0.1851602613925934,
|
|
"num_tokens": 64810679.0,
|
|
"step": 33120
|
|
},
|
|
{
|
|
"entropy": 5.939009380340576,
|
|
"epoch": 3.3111910831209075,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00039293168254292,
|
|
"loss": 5.4486,
|
|
"mean_token_accuracy": 0.1964645579457283,
|
|
"num_tokens": 64820469.0,
|
|
"step": 33125
|
|
},
|
|
{
|
|
"entropy": 5.935971307754516,
|
|
"epoch": 3.311690908182136,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0003929012870921681,
|
|
"loss": 5.412,
|
|
"mean_token_accuracy": 0.19929085671901703,
|
|
"num_tokens": 64830839.0,
|
|
"step": 33130
|
|
},
|
|
{
|
|
"entropy": 5.983817625045776,
|
|
"epoch": 3.312190733243365,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0003928708886750503,
|
|
"loss": 5.5533,
|
|
"mean_token_accuracy": 0.19281919598579406,
|
|
"num_tokens": 64840985.0,
|
|
"step": 33135
|
|
},
|
|
{
|
|
"entropy": 6.003246164321899,
|
|
"epoch": 3.3126905583045936,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00039284048729233115,
|
|
"loss": 5.5154,
|
|
"mean_token_accuracy": 0.1905466914176941,
|
|
"num_tokens": 64850874.0,
|
|
"step": 33140
|
|
},
|
|
{
|
|
"entropy": 5.938575315475464,
|
|
"epoch": 3.313190383365822,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0003928100829447757,
|
|
"loss": 5.5078,
|
|
"mean_token_accuracy": 0.19130292981863023,
|
|
"num_tokens": 64860374.0,
|
|
"step": 33145
|
|
},
|
|
{
|
|
"entropy": 5.967776536941528,
|
|
"epoch": 3.3136902084270505,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0003927796756331489,
|
|
"loss": 5.4835,
|
|
"mean_token_accuracy": 0.18290238380432128,
|
|
"num_tokens": 64869441.0,
|
|
"step": 33150
|
|
},
|
|
{
|
|
"entropy": 5.934050226211548,
|
|
"epoch": 3.3141900334882792,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0003927492653582157,
|
|
"loss": 5.5516,
|
|
"mean_token_accuracy": 0.18359677642583846,
|
|
"num_tokens": 64879981.0,
|
|
"step": 33155
|
|
},
|
|
{
|
|
"entropy": 5.921477746963501,
|
|
"epoch": 3.3146898585495075,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00039271885212074134,
|
|
"loss": 5.4659,
|
|
"mean_token_accuracy": 0.19149557501077652,
|
|
"num_tokens": 64889124.0,
|
|
"step": 33160
|
|
},
|
|
{
|
|
"entropy": 5.987066698074341,
|
|
"epoch": 3.315189683610736,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00039268843592149094,
|
|
"loss": 5.5199,
|
|
"mean_token_accuracy": 0.1916437566280365,
|
|
"num_tokens": 64897931.0,
|
|
"step": 33165
|
|
},
|
|
{
|
|
"entropy": 6.041148996353149,
|
|
"epoch": 3.315689508671965,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00039265801676122977,
|
|
"loss": 5.534,
|
|
"mean_token_accuracy": 0.19251001626253128,
|
|
"num_tokens": 64908253.0,
|
|
"step": 33170
|
|
},
|
|
{
|
|
"entropy": 5.9533766746521,
|
|
"epoch": 3.3161893337331936,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00039262759464072316,
|
|
"loss": 5.4694,
|
|
"mean_token_accuracy": 0.19759344160556794,
|
|
"num_tokens": 64917950.0,
|
|
"step": 33175
|
|
},
|
|
{
|
|
"entropy": 5.892058277130127,
|
|
"epoch": 3.316689158794422,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0003925971695607366,
|
|
"loss": 5.4114,
|
|
"mean_token_accuracy": 0.20176073014736176,
|
|
"num_tokens": 64927614.0,
|
|
"step": 33180
|
|
},
|
|
{
|
|
"entropy": 6.01614089012146,
|
|
"epoch": 3.3171889838556505,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00039256674152203546,
|
|
"loss": 5.5123,
|
|
"mean_token_accuracy": 0.18631895780563354,
|
|
"num_tokens": 64938011.0,
|
|
"step": 33185
|
|
},
|
|
{
|
|
"entropy": 5.972945308685302,
|
|
"epoch": 3.3176888089168792,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0003925363105253854,
|
|
"loss": 5.4294,
|
|
"mean_token_accuracy": 0.19316908717155457,
|
|
"num_tokens": 64947048.0,
|
|
"step": 33190
|
|
},
|
|
{
|
|
"entropy": 5.9595787525177,
|
|
"epoch": 3.3181886339781075,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00039250587657155197,
|
|
"loss": 5.4444,
|
|
"mean_token_accuracy": 0.199239481985569,
|
|
"num_tokens": 64956997.0,
|
|
"step": 33195
|
|
},
|
|
{
|
|
"entropy": 5.935969877243042,
|
|
"epoch": 3.318688459039336,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0003924754396613009,
|
|
"loss": 5.5018,
|
|
"mean_token_accuracy": 0.19128110706806184,
|
|
"num_tokens": 64967921.0,
|
|
"step": 33200
|
|
},
|
|
{
|
|
"entropy": 5.910596799850464,
|
|
"epoch": 3.319188284100565,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0003924449997953981,
|
|
"loss": 5.4214,
|
|
"mean_token_accuracy": 0.19872968643903732,
|
|
"num_tokens": 64977641.0,
|
|
"step": 33205
|
|
},
|
|
{
|
|
"entropy": 5.906330585479736,
|
|
"epoch": 3.3196881091617936,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00039241455697460923,
|
|
"loss": 5.4406,
|
|
"mean_token_accuracy": 0.1980560228228569,
|
|
"num_tokens": 64987576.0,
|
|
"step": 33210
|
|
},
|
|
{
|
|
"entropy": 5.96078782081604,
|
|
"epoch": 3.320187934223022,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00039238411119970034,
|
|
"loss": 5.47,
|
|
"mean_token_accuracy": 0.18554098308086395,
|
|
"num_tokens": 64997072.0,
|
|
"step": 33215
|
|
},
|
|
{
|
|
"entropy": 5.9448549270629885,
|
|
"epoch": 3.3206877592842505,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0003923536624714374,
|
|
"loss": 5.4605,
|
|
"mean_token_accuracy": 0.1919273927807808,
|
|
"num_tokens": 65007072.0,
|
|
"step": 33220
|
|
},
|
|
{
|
|
"entropy": 5.96418399810791,
|
|
"epoch": 3.3211875843454792,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00039232321079058657,
|
|
"loss": 5.5049,
|
|
"mean_token_accuracy": 0.19309650510549545,
|
|
"num_tokens": 65017067.0,
|
|
"step": 33225
|
|
},
|
|
{
|
|
"entropy": 6.043481111526489,
|
|
"epoch": 3.3216874094067075,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00039229275615791393,
|
|
"loss": 5.5648,
|
|
"mean_token_accuracy": 0.19228506982326507,
|
|
"num_tokens": 65026302.0,
|
|
"step": 33230
|
|
},
|
|
{
|
|
"entropy": 5.918261003494263,
|
|
"epoch": 3.322187234467936,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0003922622985741857,
|
|
"loss": 5.5015,
|
|
"mean_token_accuracy": 0.1970707207918167,
|
|
"num_tokens": 65036485.0,
|
|
"step": 33235
|
|
},
|
|
{
|
|
"entropy": 5.949941396713257,
|
|
"epoch": 3.322687059529165,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00039223183804016823,
|
|
"loss": 5.6119,
|
|
"mean_token_accuracy": 0.17754855304956435,
|
|
"num_tokens": 65045704.0,
|
|
"step": 33240
|
|
},
|
|
{
|
|
"entropy": 6.007886457443237,
|
|
"epoch": 3.3231868845903936,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00039220137455662785,
|
|
"loss": 5.4756,
|
|
"mean_token_accuracy": 0.1949585944414139,
|
|
"num_tokens": 65054997.0,
|
|
"step": 33245
|
|
},
|
|
{
|
|
"entropy": 6.103413391113281,
|
|
"epoch": 3.323686709651622,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00039217090812433106,
|
|
"loss": 5.6493,
|
|
"mean_token_accuracy": 0.17940160185098647,
|
|
"num_tokens": 65065381.0,
|
|
"step": 33250
|
|
},
|
|
{
|
|
"entropy": 5.931881856918335,
|
|
"epoch": 3.3241865347128505,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0003921404387440444,
|
|
"loss": 5.4208,
|
|
"mean_token_accuracy": 0.19898680299520494,
|
|
"num_tokens": 65075348.0,
|
|
"step": 33255
|
|
},
|
|
{
|
|
"entropy": 5.934202861785889,
|
|
"epoch": 3.3246863597740792,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0003921099664165344,
|
|
"loss": 5.5149,
|
|
"mean_token_accuracy": 0.19803481549024582,
|
|
"num_tokens": 65084566.0,
|
|
"step": 33260
|
|
},
|
|
{
|
|
"entropy": 5.937153577804565,
|
|
"epoch": 3.3251861848353075,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0003920794911425678,
|
|
"loss": 5.5038,
|
|
"mean_token_accuracy": 0.19222253412008286,
|
|
"num_tokens": 65094585.0,
|
|
"step": 33265
|
|
},
|
|
{
|
|
"entropy": 5.988105964660645,
|
|
"epoch": 3.325686009896536,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00039204901292291133,
|
|
"loss": 5.4729,
|
|
"mean_token_accuracy": 0.19522039145231246,
|
|
"num_tokens": 65105288.0,
|
|
"step": 33270
|
|
},
|
|
{
|
|
"entropy": 5.961154747009277,
|
|
"epoch": 3.326185834957765,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0003920185317583318,
|
|
"loss": 5.4558,
|
|
"mean_token_accuracy": 0.19578785598278045,
|
|
"num_tokens": 65115815.0,
|
|
"step": 33275
|
|
},
|
|
{
|
|
"entropy": 6.009720754623413,
|
|
"epoch": 3.3266856600189936,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0003919880476495962,
|
|
"loss": 5.573,
|
|
"mean_token_accuracy": 0.1812488928437233,
|
|
"num_tokens": 65126654.0,
|
|
"step": 33280
|
|
},
|
|
{
|
|
"entropy": 5.956664419174194,
|
|
"epoch": 3.327185485080222,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0003919575605974713,
|
|
"loss": 5.5392,
|
|
"mean_token_accuracy": 0.18761251866817474,
|
|
"num_tokens": 65137061.0,
|
|
"step": 33285
|
|
},
|
|
{
|
|
"entropy": 6.045987462997436,
|
|
"epoch": 3.3276853101414505,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0003919270706027244,
|
|
"loss": 5.5552,
|
|
"mean_token_accuracy": 0.19344282895326614,
|
|
"num_tokens": 65146991.0,
|
|
"step": 33290
|
|
},
|
|
{
|
|
"entropy": 5.991027164459228,
|
|
"epoch": 3.3281851352026792,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0003918965776661224,
|
|
"loss": 5.4947,
|
|
"mean_token_accuracy": 0.1882070481777191,
|
|
"num_tokens": 65156146.0,
|
|
"step": 33295
|
|
},
|
|
{
|
|
"entropy": 5.931119441986084,
|
|
"epoch": 3.3286849602639075,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00039186608178843257,
|
|
"loss": 5.5223,
|
|
"mean_token_accuracy": 0.1917535439133644,
|
|
"num_tokens": 65166005.0,
|
|
"step": 33300
|
|
},
|
|
{
|
|
"entropy": 5.9257025718688965,
|
|
"epoch": 3.329184785325136,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00039183558297042225,
|
|
"loss": 5.4942,
|
|
"mean_token_accuracy": 0.19342846423387527,
|
|
"num_tokens": 65177311.0,
|
|
"step": 33305
|
|
},
|
|
{
|
|
"entropy": 5.966166925430298,
|
|
"epoch": 3.329684610386365,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00039180508121285866,
|
|
"loss": 5.4482,
|
|
"mean_token_accuracy": 0.19243630021810532,
|
|
"num_tokens": 65186371.0,
|
|
"step": 33310
|
|
},
|
|
{
|
|
"entropy": 5.980241918563843,
|
|
"epoch": 3.3301844354475936,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0003917745765165094,
|
|
"loss": 5.4721,
|
|
"mean_token_accuracy": 0.1927392676472664,
|
|
"num_tokens": 65194861.0,
|
|
"step": 33315
|
|
},
|
|
{
|
|
"entropy": 5.945227098464966,
|
|
"epoch": 3.330684260508822,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0003917440688821417,
|
|
"loss": 5.5714,
|
|
"mean_token_accuracy": 0.1853356420993805,
|
|
"num_tokens": 65204479.0,
|
|
"step": 33320
|
|
},
|
|
{
|
|
"entropy": 5.953518342971802,
|
|
"epoch": 3.3311840855700505,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0003917135583105235,
|
|
"loss": 5.463,
|
|
"mean_token_accuracy": 0.18862586617469787,
|
|
"num_tokens": 65213756.0,
|
|
"step": 33325
|
|
},
|
|
{
|
|
"entropy": 5.967887020111084,
|
|
"epoch": 3.331683910631279,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00039168304480242196,
|
|
"loss": 5.4958,
|
|
"mean_token_accuracy": 0.1887494221329689,
|
|
"num_tokens": 65223061.0,
|
|
"step": 33330
|
|
},
|
|
{
|
|
"entropy": 5.908823299407959,
|
|
"epoch": 3.3321837356925075,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0003916525283586051,
|
|
"loss": 5.3718,
|
|
"mean_token_accuracy": 0.20462483763694764,
|
|
"num_tokens": 65231743.0,
|
|
"step": 33335
|
|
},
|
|
{
|
|
"entropy": 6.007478427886963,
|
|
"epoch": 3.332683560753736,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0003916220089798407,
|
|
"loss": 5.5314,
|
|
"mean_token_accuracy": 0.19578975588083267,
|
|
"num_tokens": 65240629.0,
|
|
"step": 33340
|
|
},
|
|
{
|
|
"entropy": 5.930036354064941,
|
|
"epoch": 3.333183385814965,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00039159148666689656,
|
|
"loss": 5.5247,
|
|
"mean_token_accuracy": 0.1890843242406845,
|
|
"num_tokens": 65249766.0,
|
|
"step": 33345
|
|
},
|
|
{
|
|
"entropy": 5.930952262878418,
|
|
"epoch": 3.3336832108761936,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0003915609614205406,
|
|
"loss": 5.4425,
|
|
"mean_token_accuracy": 0.20178742706775665,
|
|
"num_tokens": 65258621.0,
|
|
"step": 33350
|
|
},
|
|
{
|
|
"entropy": 5.981604433059692,
|
|
"epoch": 3.334183035937422,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0003915304332415408,
|
|
"loss": 5.4927,
|
|
"mean_token_accuracy": 0.19681073427200318,
|
|
"num_tokens": 65268036.0,
|
|
"step": 33355
|
|
},
|
|
{
|
|
"entropy": 5.9480236053466795,
|
|
"epoch": 3.3346828609986505,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0003914999021306653,
|
|
"loss": 5.4832,
|
|
"mean_token_accuracy": 0.19339950382709503,
|
|
"num_tokens": 65278377.0,
|
|
"step": 33360
|
|
},
|
|
{
|
|
"entropy": 5.918806505203247,
|
|
"epoch": 3.335182686059879,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0003914693680886823,
|
|
"loss": 5.495,
|
|
"mean_token_accuracy": 0.19138063192367555,
|
|
"num_tokens": 65288778.0,
|
|
"step": 33365
|
|
},
|
|
{
|
|
"entropy": 5.879415035247803,
|
|
"epoch": 3.3356825111211075,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00039143883111635995,
|
|
"loss": 5.3962,
|
|
"mean_token_accuracy": 0.20086403489112853,
|
|
"num_tokens": 65297993.0,
|
|
"step": 33370
|
|
},
|
|
{
|
|
"entropy": 6.002231645584106,
|
|
"epoch": 3.336182336182336,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0003914082912144666,
|
|
"loss": 5.5399,
|
|
"mean_token_accuracy": 0.18431989401578902,
|
|
"num_tokens": 65307551.0,
|
|
"step": 33375
|
|
},
|
|
{
|
|
"entropy": 5.9076841354370115,
|
|
"epoch": 3.336682161243565,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00039137774838377047,
|
|
"loss": 5.4347,
|
|
"mean_token_accuracy": 0.1931011274456978,
|
|
"num_tokens": 65317747.0,
|
|
"step": 33380
|
|
},
|
|
{
|
|
"entropy": 5.998347425460816,
|
|
"epoch": 3.3371819863047936,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0003913472026250402,
|
|
"loss": 5.5786,
|
|
"mean_token_accuracy": 0.18219032883644104,
|
|
"num_tokens": 65328383.0,
|
|
"step": 33385
|
|
},
|
|
{
|
|
"entropy": 6.019373798370362,
|
|
"epoch": 3.337681811366022,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0003913166539390443,
|
|
"loss": 5.5916,
|
|
"mean_token_accuracy": 0.18520181030035018,
|
|
"num_tokens": 65338134.0,
|
|
"step": 33390
|
|
},
|
|
{
|
|
"entropy": 5.969875621795654,
|
|
"epoch": 3.3381816364272505,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0003912861023265513,
|
|
"loss": 5.4814,
|
|
"mean_token_accuracy": 0.19423045665025712,
|
|
"num_tokens": 65348520.0,
|
|
"step": 33395
|
|
},
|
|
{
|
|
"entropy": 5.951163244247437,
|
|
"epoch": 3.338681461488479,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0003912555477883299,
|
|
"loss": 5.4504,
|
|
"mean_token_accuracy": 0.19374593049287797,
|
|
"num_tokens": 65357383.0,
|
|
"step": 33400
|
|
},
|
|
{
|
|
"entropy": 5.91621503829956,
|
|
"epoch": 3.3391812865497075,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0003912249903251488,
|
|
"loss": 5.4615,
|
|
"mean_token_accuracy": 0.19894734174013137,
|
|
"num_tokens": 65367463.0,
|
|
"step": 33405
|
|
},
|
|
{
|
|
"entropy": 5.977438354492188,
|
|
"epoch": 3.339681111610936,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0003911944299377768,
|
|
"loss": 5.5053,
|
|
"mean_token_accuracy": 0.18876027762889863,
|
|
"num_tokens": 65377276.0,
|
|
"step": 33410
|
|
},
|
|
{
|
|
"entropy": 5.897323417663574,
|
|
"epoch": 3.340180936672165,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0003911638666269829,
|
|
"loss": 5.4594,
|
|
"mean_token_accuracy": 0.1989895224571228,
|
|
"num_tokens": 65386716.0,
|
|
"step": 33415
|
|
},
|
|
{
|
|
"entropy": 5.870097923278808,
|
|
"epoch": 3.340680761733393,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00039113330039353605,
|
|
"loss": 5.4144,
|
|
"mean_token_accuracy": 0.2020581528544426,
|
|
"num_tokens": 65396900.0,
|
|
"step": 33420
|
|
},
|
|
{
|
|
"entropy": 5.921707677841186,
|
|
"epoch": 3.341180586794622,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00039110273123820524,
|
|
"loss": 5.4177,
|
|
"mean_token_accuracy": 0.20060823112726212,
|
|
"num_tokens": 65406036.0,
|
|
"step": 33425
|
|
},
|
|
{
|
|
"entropy": 5.95600733757019,
|
|
"epoch": 3.3416804118558505,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00039107215916175947,
|
|
"loss": 5.4564,
|
|
"mean_token_accuracy": 0.19710676670074462,
|
|
"num_tokens": 65415374.0,
|
|
"step": 33430
|
|
},
|
|
{
|
|
"entropy": 5.950402307510376,
|
|
"epoch": 3.3421802369170788,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0003910415841649681,
|
|
"loss": 5.3949,
|
|
"mean_token_accuracy": 0.1985665589570999,
|
|
"num_tokens": 65424969.0,
|
|
"step": 33435
|
|
},
|
|
{
|
|
"entropy": 5.883012199401856,
|
|
"epoch": 3.3426800619783075,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0003910110062486004,
|
|
"loss": 5.4066,
|
|
"mean_token_accuracy": 0.1993997201323509,
|
|
"num_tokens": 65434068.0,
|
|
"step": 33440
|
|
},
|
|
{
|
|
"entropy": 5.973568105697632,
|
|
"epoch": 3.343179887039536,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00039098042541342554,
|
|
"loss": 5.5978,
|
|
"mean_token_accuracy": 0.1835126370191574,
|
|
"num_tokens": 65445169.0,
|
|
"step": 33445
|
|
},
|
|
{
|
|
"entropy": 5.929827451705933,
|
|
"epoch": 3.343679712100765,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00039094984166021307,
|
|
"loss": 5.4239,
|
|
"mean_token_accuracy": 0.20088978856801987,
|
|
"num_tokens": 65454409.0,
|
|
"step": 33450
|
|
},
|
|
{
|
|
"entropy": 5.983497571945191,
|
|
"epoch": 3.344179537161993,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0003909192549897325,
|
|
"loss": 5.5145,
|
|
"mean_token_accuracy": 0.1933015391230583,
|
|
"num_tokens": 65464101.0,
|
|
"step": 33455
|
|
},
|
|
{
|
|
"entropy": 6.0618531703948975,
|
|
"epoch": 3.344679362223222,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0003908886654027532,
|
|
"loss": 5.6502,
|
|
"mean_token_accuracy": 0.1805142879486084,
|
|
"num_tokens": 65473774.0,
|
|
"step": 33460
|
|
},
|
|
{
|
|
"entropy": 5.929384803771972,
|
|
"epoch": 3.3451791872844505,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00039085807290004495,
|
|
"loss": 5.4339,
|
|
"mean_token_accuracy": 0.1933978945016861,
|
|
"num_tokens": 65483414.0,
|
|
"step": 33465
|
|
},
|
|
{
|
|
"entropy": 5.853053712844849,
|
|
"epoch": 3.3456790123456788,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00039082747748237737,
|
|
"loss": 5.4542,
|
|
"mean_token_accuracy": 0.19806677848100662,
|
|
"num_tokens": 65493875.0,
|
|
"step": 33470
|
|
},
|
|
{
|
|
"entropy": 5.936354732513427,
|
|
"epoch": 3.3461788374069075,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0003907968791505202,
|
|
"loss": 5.5031,
|
|
"mean_token_accuracy": 0.19219911843538284,
|
|
"num_tokens": 65503801.0,
|
|
"step": 33475
|
|
},
|
|
{
|
|
"entropy": 5.984921312332153,
|
|
"epoch": 3.346678662468136,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00039076627790524343,
|
|
"loss": 5.4656,
|
|
"mean_token_accuracy": 0.1999216318130493,
|
|
"num_tokens": 65514151.0,
|
|
"step": 33480
|
|
},
|
|
{
|
|
"entropy": 5.9768674850463865,
|
|
"epoch": 3.347178487529365,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00039073567374731685,
|
|
"loss": 5.4774,
|
|
"mean_token_accuracy": 0.19478786140680313,
|
|
"num_tokens": 65525246.0,
|
|
"step": 33485
|
|
},
|
|
{
|
|
"entropy": 5.8519409656524655,
|
|
"epoch": 3.347678312590593,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00039070506667751066,
|
|
"loss": 5.3905,
|
|
"mean_token_accuracy": 0.20333162993192672,
|
|
"num_tokens": 65534766.0,
|
|
"step": 33490
|
|
},
|
|
{
|
|
"entropy": 5.968207597732544,
|
|
"epoch": 3.348178137651822,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0003906744566965946,
|
|
"loss": 5.5528,
|
|
"mean_token_accuracy": 0.1919400542974472,
|
|
"num_tokens": 65545058.0,
|
|
"step": 33495
|
|
},
|
|
{
|
|
"entropy": 5.979120111465454,
|
|
"epoch": 3.3486779627130505,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000390643843805339,
|
|
"loss": 5.452,
|
|
"mean_token_accuracy": 0.19676698744297028,
|
|
"num_tokens": 65554234.0,
|
|
"step": 33500
|
|
},
|
|
{
|
|
"entropy": 6.03738808631897,
|
|
"epoch": 3.3491777877742788,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000390613228004514,
|
|
"loss": 5.6162,
|
|
"mean_token_accuracy": 0.18995852321386336,
|
|
"num_tokens": 65565115.0,
|
|
"step": 33505
|
|
},
|
|
{
|
|
"entropy": 5.864552640914917,
|
|
"epoch": 3.3496776128355075,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00039058260929489,
|
|
"loss": 5.4186,
|
|
"mean_token_accuracy": 0.19965252578258513,
|
|
"num_tokens": 65575291.0,
|
|
"step": 33510
|
|
},
|
|
{
|
|
"entropy": 5.928391647338867,
|
|
"epoch": 3.350177437896736,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00039055198767723725,
|
|
"loss": 5.4718,
|
|
"mean_token_accuracy": 0.19901888072490692,
|
|
"num_tokens": 65585105.0,
|
|
"step": 33515
|
|
},
|
|
{
|
|
"entropy": 6.012979173660279,
|
|
"epoch": 3.350677262957965,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00039052136315232625,
|
|
"loss": 5.4856,
|
|
"mean_token_accuracy": 0.19604048728942872,
|
|
"num_tokens": 65594786.0,
|
|
"step": 33520
|
|
},
|
|
{
|
|
"entropy": 5.907447004318238,
|
|
"epoch": 3.351177088019193,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00039049073572092755,
|
|
"loss": 5.3669,
|
|
"mean_token_accuracy": 0.19863395839929582,
|
|
"num_tokens": 65604553.0,
|
|
"step": 33525
|
|
},
|
|
{
|
|
"entropy": 5.90217695236206,
|
|
"epoch": 3.351676913080422,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0003904601053838116,
|
|
"loss": 5.4839,
|
|
"mean_token_accuracy": 0.1990802302956581,
|
|
"num_tokens": 65613808.0,
|
|
"step": 33530
|
|
},
|
|
{
|
|
"entropy": 5.9769080638885494,
|
|
"epoch": 3.3521767381416505,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00039042947214174906,
|
|
"loss": 5.4932,
|
|
"mean_token_accuracy": 0.19170901477336882,
|
|
"num_tokens": 65622741.0,
|
|
"step": 33535
|
|
},
|
|
{
|
|
"entropy": 5.925945568084717,
|
|
"epoch": 3.3526765632028788,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00039039883599551074,
|
|
"loss": 5.4233,
|
|
"mean_token_accuracy": 0.19947504103183747,
|
|
"num_tokens": 65632325.0,
|
|
"step": 33540
|
|
},
|
|
{
|
|
"entropy": 5.988364505767822,
|
|
"epoch": 3.3531763882641075,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0003903681969458674,
|
|
"loss": 5.4446,
|
|
"mean_token_accuracy": 0.1979219675064087,
|
|
"num_tokens": 65642636.0,
|
|
"step": 33545
|
|
},
|
|
{
|
|
"entropy": 5.9744751930236815,
|
|
"epoch": 3.353676213325336,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0003903375549935899,
|
|
"loss": 5.507,
|
|
"mean_token_accuracy": 0.19143182784318924,
|
|
"num_tokens": 65652058.0,
|
|
"step": 33550
|
|
},
|
|
{
|
|
"entropy": 5.907715654373169,
|
|
"epoch": 3.354176038386565,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0003903069101394492,
|
|
"loss": 5.4504,
|
|
"mean_token_accuracy": 0.19627675116062165,
|
|
"num_tokens": 65662213.0,
|
|
"step": 33555
|
|
},
|
|
{
|
|
"entropy": 6.026298379898071,
|
|
"epoch": 3.354675863447793,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0003902762623842164,
|
|
"loss": 5.609,
|
|
"mean_token_accuracy": 0.179832124710083,
|
|
"num_tokens": 65672302.0,
|
|
"step": 33560
|
|
},
|
|
{
|
|
"entropy": 5.8611303806304935,
|
|
"epoch": 3.355175688509022,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00039024561172866236,
|
|
"loss": 5.2822,
|
|
"mean_token_accuracy": 0.2073721095919609,
|
|
"num_tokens": 65681642.0,
|
|
"step": 33565
|
|
},
|
|
{
|
|
"entropy": 5.902415990829468,
|
|
"epoch": 3.3556755135702505,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0003902149581735585,
|
|
"loss": 5.3767,
|
|
"mean_token_accuracy": 0.20008856803178787,
|
|
"num_tokens": 65691165.0,
|
|
"step": 33570
|
|
},
|
|
{
|
|
"entropy": 5.851033306121826,
|
|
"epoch": 3.3561753386314788,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00039018430171967584,
|
|
"loss": 5.4732,
|
|
"mean_token_accuracy": 0.19636656492948532,
|
|
"num_tokens": 65701556.0,
|
|
"step": 33575
|
|
},
|
|
{
|
|
"entropy": 5.908744621276855,
|
|
"epoch": 3.3566751636927075,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0003901536423677859,
|
|
"loss": 5.4306,
|
|
"mean_token_accuracy": 0.2046293795108795,
|
|
"num_tokens": 65711481.0,
|
|
"step": 33580
|
|
},
|
|
{
|
|
"entropy": 5.999990367889405,
|
|
"epoch": 3.357174988753936,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0003901229801186598,
|
|
"loss": 5.4249,
|
|
"mean_token_accuracy": 0.19772581607103348,
|
|
"num_tokens": 65720731.0,
|
|
"step": 33585
|
|
},
|
|
{
|
|
"entropy": 5.899659919738769,
|
|
"epoch": 3.357674813815165,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0003900923149730693,
|
|
"loss": 5.3874,
|
|
"mean_token_accuracy": 0.20408902168273926,
|
|
"num_tokens": 65730219.0,
|
|
"step": 33590
|
|
},
|
|
{
|
|
"entropy": 5.954953813552857,
|
|
"epoch": 3.358174638876393,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00039006164693178573,
|
|
"loss": 5.4917,
|
|
"mean_token_accuracy": 0.20047009289264678,
|
|
"num_tokens": 65739893.0,
|
|
"step": 33595
|
|
},
|
|
{
|
|
"entropy": 5.974736881256104,
|
|
"epoch": 3.358674463937622,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0003900309759955806,
|
|
"loss": 5.5427,
|
|
"mean_token_accuracy": 0.19283135533332824,
|
|
"num_tokens": 65748925.0,
|
|
"step": 33600
|
|
},
|
|
{
|
|
"entropy": 5.992804479598999,
|
|
"epoch": 3.3591742889988505,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0003900003021652259,
|
|
"loss": 5.5505,
|
|
"mean_token_accuracy": 0.1868687614798546,
|
|
"num_tokens": 65759355.0,
|
|
"step": 33605
|
|
},
|
|
{
|
|
"entropy": 5.975573492050171,
|
|
"epoch": 3.3596741140600788,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00038996962544149313,
|
|
"loss": 5.447,
|
|
"mean_token_accuracy": 0.19790701419115067,
|
|
"num_tokens": 65767853.0,
|
|
"step": 33610
|
|
},
|
|
{
|
|
"entropy": 5.879975700378418,
|
|
"epoch": 3.3601739391213075,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0003899389458251541,
|
|
"loss": 5.4627,
|
|
"mean_token_accuracy": 0.19572226703166962,
|
|
"num_tokens": 65776672.0,
|
|
"step": 33615
|
|
},
|
|
{
|
|
"entropy": 5.905025577545166,
|
|
"epoch": 3.360673764182536,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0003899082633169808,
|
|
"loss": 5.4705,
|
|
"mean_token_accuracy": 0.18584811687469482,
|
|
"num_tokens": 65785839.0,
|
|
"step": 33620
|
|
},
|
|
{
|
|
"entropy": 5.9718160152435305,
|
|
"epoch": 3.361173589243765,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00038987757791774513,
|
|
"loss": 5.6096,
|
|
"mean_token_accuracy": 0.18507128208875656,
|
|
"num_tokens": 65796648.0,
|
|
"step": 33625
|
|
},
|
|
{
|
|
"entropy": 5.917266035079956,
|
|
"epoch": 3.361673414304993,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0003898468896282193,
|
|
"loss": 5.4199,
|
|
"mean_token_accuracy": 0.193768647313118,
|
|
"num_tokens": 65806170.0,
|
|
"step": 33630
|
|
},
|
|
{
|
|
"entropy": 6.069835472106933,
|
|
"epoch": 3.362173239366222,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0003898161984491752,
|
|
"loss": 5.5757,
|
|
"mean_token_accuracy": 0.1857938513159752,
|
|
"num_tokens": 65816319.0,
|
|
"step": 33635
|
|
},
|
|
{
|
|
"entropy": 5.83911919593811,
|
|
"epoch": 3.3626730644274505,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00038978550438138504,
|
|
"loss": 5.4534,
|
|
"mean_token_accuracy": 0.20133153796195985,
|
|
"num_tokens": 65827334.0,
|
|
"step": 33640
|
|
},
|
|
{
|
|
"entropy": 5.842231273651123,
|
|
"epoch": 3.3631728894886788,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0003897548074256211,
|
|
"loss": 5.42,
|
|
"mean_token_accuracy": 0.20431708544492722,
|
|
"num_tokens": 65835948.0,
|
|
"step": 33645
|
|
},
|
|
{
|
|
"entropy": 5.934733200073242,
|
|
"epoch": 3.3636727145499075,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0003897241075826559,
|
|
"loss": 5.485,
|
|
"mean_token_accuracy": 0.2038044348359108,
|
|
"num_tokens": 65845026.0,
|
|
"step": 33650
|
|
},
|
|
{
|
|
"entropy": 5.898617935180664,
|
|
"epoch": 3.364172539611136,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00038969340485326147,
|
|
"loss": 5.4688,
|
|
"mean_token_accuracy": 0.19049846678972243,
|
|
"num_tokens": 65854820.0,
|
|
"step": 33655
|
|
},
|
|
{
|
|
"entropy": 5.911277198791504,
|
|
"epoch": 3.364672364672365,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0003896626992382106,
|
|
"loss": 5.4792,
|
|
"mean_token_accuracy": 0.1955721616744995,
|
|
"num_tokens": 65864557.0,
|
|
"step": 33660
|
|
},
|
|
{
|
|
"entropy": 5.996156501770019,
|
|
"epoch": 3.365172189733593,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00038963199073827574,
|
|
"loss": 5.5537,
|
|
"mean_token_accuracy": 0.1951324850320816,
|
|
"num_tokens": 65874534.0,
|
|
"step": 33665
|
|
},
|
|
{
|
|
"entropy": 5.876225280761719,
|
|
"epoch": 3.365672014794822,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00038960127935422947,
|
|
"loss": 5.3538,
|
|
"mean_token_accuracy": 0.20741759836673737,
|
|
"num_tokens": 65883722.0,
|
|
"step": 33670
|
|
},
|
|
{
|
|
"entropy": 5.903943681716919,
|
|
"epoch": 3.3661718398560505,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0003895705650868445,
|
|
"loss": 5.4383,
|
|
"mean_token_accuracy": 0.19410601258277893,
|
|
"num_tokens": 65894061.0,
|
|
"step": 33675
|
|
},
|
|
{
|
|
"entropy": 5.86383547782898,
|
|
"epoch": 3.3666716649172788,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00038953984793689355,
|
|
"loss": 5.4494,
|
|
"mean_token_accuracy": 0.1949499562382698,
|
|
"num_tokens": 65904495.0,
|
|
"step": 33680
|
|
},
|
|
{
|
|
"entropy": 5.983147382736206,
|
|
"epoch": 3.3671714899785075,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00038950912790514954,
|
|
"loss": 5.544,
|
|
"mean_token_accuracy": 0.1877785325050354,
|
|
"num_tokens": 65915958.0,
|
|
"step": 33685
|
|
},
|
|
{
|
|
"entropy": 5.904328680038452,
|
|
"epoch": 3.367671315039736,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0003894784049923854,
|
|
"loss": 5.4249,
|
|
"mean_token_accuracy": 0.19893889576196672,
|
|
"num_tokens": 65925689.0,
|
|
"step": 33690
|
|
},
|
|
{
|
|
"entropy": 5.915316152572632,
|
|
"epoch": 3.368171140100965,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0003894476791993739,
|
|
"loss": 5.4137,
|
|
"mean_token_accuracy": 0.19291827380657195,
|
|
"num_tokens": 65935024.0,
|
|
"step": 33695
|
|
},
|
|
{
|
|
"entropy": 5.875950479507447,
|
|
"epoch": 3.368670965162193,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00038941695052688833,
|
|
"loss": 5.4684,
|
|
"mean_token_accuracy": 0.19440394937992095,
|
|
"num_tokens": 65944646.0,
|
|
"step": 33700
|
|
},
|
|
{
|
|
"entropy": 5.9612250328063965,
|
|
"epoch": 3.369170790223422,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00038938621897570175,
|
|
"loss": 5.5529,
|
|
"mean_token_accuracy": 0.19070293605327607,
|
|
"num_tokens": 65954670.0,
|
|
"step": 33705
|
|
},
|
|
{
|
|
"entropy": 6.043454647064209,
|
|
"epoch": 3.3696706152846505,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0003893554845465873,
|
|
"loss": 5.5949,
|
|
"mean_token_accuracy": 0.18067453503608705,
|
|
"num_tokens": 65964844.0,
|
|
"step": 33710
|
|
},
|
|
{
|
|
"entropy": 6.050707721710205,
|
|
"epoch": 3.3701704403458788,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0003893247472403183,
|
|
"loss": 5.5648,
|
|
"mean_token_accuracy": 0.18974282443523408,
|
|
"num_tokens": 65974625.0,
|
|
"step": 33715
|
|
},
|
|
{
|
|
"entropy": 5.933426713943481,
|
|
"epoch": 3.3706702654071075,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.000389294007057668,
|
|
"loss": 5.4929,
|
|
"mean_token_accuracy": 0.187282557785511,
|
|
"num_tokens": 65983266.0,
|
|
"step": 33720
|
|
},
|
|
{
|
|
"entropy": 6.046300649642944,
|
|
"epoch": 3.371170090468336,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00038926326399941,
|
|
"loss": 5.7085,
|
|
"mean_token_accuracy": 0.17281196415424346,
|
|
"num_tokens": 65992611.0,
|
|
"step": 33725
|
|
},
|
|
{
|
|
"entropy": 5.959706163406372,
|
|
"epoch": 3.371669915529565,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0003892325180663176,
|
|
"loss": 5.4883,
|
|
"mean_token_accuracy": 0.19411114752292633,
|
|
"num_tokens": 66003387.0,
|
|
"step": 33730
|
|
},
|
|
{
|
|
"entropy": 6.016661071777344,
|
|
"epoch": 3.372169740590793,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0003892017692591645,
|
|
"loss": 5.6141,
|
|
"mean_token_accuracy": 0.18555651158094405,
|
|
"num_tokens": 66013574.0,
|
|
"step": 33735
|
|
},
|
|
{
|
|
"entropy": 5.9908722877502445,
|
|
"epoch": 3.372669565652022,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00038917101757872434,
|
|
"loss": 5.4743,
|
|
"mean_token_accuracy": 0.18995198607444763,
|
|
"num_tokens": 66024312.0,
|
|
"step": 33740
|
|
},
|
|
{
|
|
"entropy": 5.979120492935181,
|
|
"epoch": 3.3731693907132505,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0003891402630257706,
|
|
"loss": 5.4935,
|
|
"mean_token_accuracy": 0.18883745074272157,
|
|
"num_tokens": 66034444.0,
|
|
"step": 33745
|
|
},
|
|
{
|
|
"entropy": 5.87585825920105,
|
|
"epoch": 3.3736692157744788,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00038910950560107734,
|
|
"loss": 5.4641,
|
|
"mean_token_accuracy": 0.19905768632888793,
|
|
"num_tokens": 66043524.0,
|
|
"step": 33750
|
|
},
|
|
{
|
|
"entropy": 5.867743635177613,
|
|
"epoch": 3.3741690408357075,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00038907874530541824,
|
|
"loss": 5.4155,
|
|
"mean_token_accuracy": 0.19469310939311982,
|
|
"num_tokens": 66053223.0,
|
|
"step": 33755
|
|
},
|
|
{
|
|
"entropy": 5.847289800643921,
|
|
"epoch": 3.374668865896936,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00038904798213956716,
|
|
"loss": 5.4314,
|
|
"mean_token_accuracy": 0.20132435411214827,
|
|
"num_tokens": 66062042.0,
|
|
"step": 33760
|
|
},
|
|
{
|
|
"entropy": 5.87286787033081,
|
|
"epoch": 3.375168690958165,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0003890172161042983,
|
|
"loss": 5.5223,
|
|
"mean_token_accuracy": 0.19560135155916214,
|
|
"num_tokens": 66071685.0,
|
|
"step": 33765
|
|
},
|
|
{
|
|
"entropy": 5.921923351287842,
|
|
"epoch": 3.375668516019393,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00038898644720038563,
|
|
"loss": 5.5022,
|
|
"mean_token_accuracy": 0.19694085866212846,
|
|
"num_tokens": 66080677.0,
|
|
"step": 33770
|
|
},
|
|
{
|
|
"entropy": 5.950573062896728,
|
|
"epoch": 3.376168341080622,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0003889556754286032,
|
|
"loss": 5.4718,
|
|
"mean_token_accuracy": 0.19659730643033982,
|
|
"num_tokens": 66089310.0,
|
|
"step": 33775
|
|
},
|
|
{
|
|
"entropy": 5.8734626293182375,
|
|
"epoch": 3.3766681661418505,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00038892490078972544,
|
|
"loss": 5.4192,
|
|
"mean_token_accuracy": 0.19846172630786896,
|
|
"num_tokens": 66099818.0,
|
|
"step": 33780
|
|
},
|
|
{
|
|
"entropy": 5.894863796234131,
|
|
"epoch": 3.3771679912030788,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0003888941232845264,
|
|
"loss": 5.4058,
|
|
"mean_token_accuracy": 0.19790617525577545,
|
|
"num_tokens": 66109622.0,
|
|
"step": 33785
|
|
},
|
|
{
|
|
"entropy": 5.884588718414307,
|
|
"epoch": 3.3776678162643075,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00038886334291378047,
|
|
"loss": 5.4159,
|
|
"mean_token_accuracy": 0.19739241749048234,
|
|
"num_tokens": 66118677.0,
|
|
"step": 33790
|
|
},
|
|
{
|
|
"entropy": 5.806522274017334,
|
|
"epoch": 3.378167641325536,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0003888325596782622,
|
|
"loss": 5.3834,
|
|
"mean_token_accuracy": 0.19905606508255005,
|
|
"num_tokens": 66127818.0,
|
|
"step": 33795
|
|
},
|
|
{
|
|
"entropy": 5.972617435455322,
|
|
"epoch": 3.378667466386765,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.000388801773578746,
|
|
"loss": 5.5031,
|
|
"mean_token_accuracy": 0.1954567551612854,
|
|
"num_tokens": 66138972.0,
|
|
"step": 33800
|
|
},
|
|
{
|
|
"entropy": 5.949275064468384,
|
|
"epoch": 3.379167291447993,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0003887709846160065,
|
|
"loss": 5.4352,
|
|
"mean_token_accuracy": 0.19451077729463578,
|
|
"num_tokens": 66147900.0,
|
|
"step": 33805
|
|
},
|
|
{
|
|
"entropy": 5.69210786819458,
|
|
"epoch": 3.379667116509222,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0003887401927908183,
|
|
"loss": 5.271,
|
|
"mean_token_accuracy": 0.21723345369100572,
|
|
"num_tokens": 66158302.0,
|
|
"step": 33810
|
|
},
|
|
{
|
|
"entropy": 5.959599304199219,
|
|
"epoch": 3.3801669415704505,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00038870939810395605,
|
|
"loss": 5.5351,
|
|
"mean_token_accuracy": 0.18865936547517775,
|
|
"num_tokens": 66168069.0,
|
|
"step": 33815
|
|
},
|
|
{
|
|
"entropy": 6.013097143173217,
|
|
"epoch": 3.3806667666316788,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00038867860055619456,
|
|
"loss": 5.5537,
|
|
"mean_token_accuracy": 0.1876016601920128,
|
|
"num_tokens": 66176702.0,
|
|
"step": 33820
|
|
},
|
|
{
|
|
"entropy": 5.884380197525024,
|
|
"epoch": 3.3811665916929075,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0003886478001483089,
|
|
"loss": 5.4317,
|
|
"mean_token_accuracy": 0.20108166337013245,
|
|
"num_tokens": 66185293.0,
|
|
"step": 33825
|
|
},
|
|
{
|
|
"entropy": 5.837329769134522,
|
|
"epoch": 3.381666416754136,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0003886169968810737,
|
|
"loss": 5.2798,
|
|
"mean_token_accuracy": 0.2123381167650223,
|
|
"num_tokens": 66195289.0,
|
|
"step": 33830
|
|
},
|
|
{
|
|
"entropy": 5.841838788986206,
|
|
"epoch": 3.382166241815365,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0003885861907552642,
|
|
"loss": 5.3873,
|
|
"mean_token_accuracy": 0.20538408011198045,
|
|
"num_tokens": 66205778.0,
|
|
"step": 33835
|
|
},
|
|
{
|
|
"entropy": 5.9521646976470945,
|
|
"epoch": 3.382666066876593,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0003885553817716553,
|
|
"loss": 5.4577,
|
|
"mean_token_accuracy": 0.19163903295993806,
|
|
"num_tokens": 66214861.0,
|
|
"step": 33840
|
|
},
|
|
{
|
|
"entropy": 5.951155328750611,
|
|
"epoch": 3.383165891937822,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0003885245699310223,
|
|
"loss": 5.5261,
|
|
"mean_token_accuracy": 0.18901787996292113,
|
|
"num_tokens": 66224721.0,
|
|
"step": 33845
|
|
},
|
|
{
|
|
"entropy": 5.899516296386719,
|
|
"epoch": 3.3836657169990505,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0003884937552341402,
|
|
"loss": 5.4787,
|
|
"mean_token_accuracy": 0.19404699951410292,
|
|
"num_tokens": 66234132.0,
|
|
"step": 33850
|
|
},
|
|
{
|
|
"entropy": 6.00852746963501,
|
|
"epoch": 3.3841655420602788,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00038846293768178444,
|
|
"loss": 5.5989,
|
|
"mean_token_accuracy": 0.19041644632816315,
|
|
"num_tokens": 66244098.0,
|
|
"step": 33855
|
|
},
|
|
{
|
|
"entropy": 5.950526428222656,
|
|
"epoch": 3.3846653671215075,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0003884321172747304,
|
|
"loss": 5.4086,
|
|
"mean_token_accuracy": 0.2045530915260315,
|
|
"num_tokens": 66253813.0,
|
|
"step": 33860
|
|
},
|
|
{
|
|
"entropy": 5.963084745407104,
|
|
"epoch": 3.385165192182736,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0003884012940137536,
|
|
"loss": 5.4492,
|
|
"mean_token_accuracy": 0.19359734803438186,
|
|
"num_tokens": 66263699.0,
|
|
"step": 33865
|
|
},
|
|
{
|
|
"entropy": 5.905384635925293,
|
|
"epoch": 3.385665017243965,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0003883704678996293,
|
|
"loss": 5.4791,
|
|
"mean_token_accuracy": 0.1949758693575859,
|
|
"num_tokens": 66273493.0,
|
|
"step": 33870
|
|
},
|
|
{
|
|
"entropy": 5.838614463806152,
|
|
"epoch": 3.386164842305193,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00038833963893313326,
|
|
"loss": 5.4177,
|
|
"mean_token_accuracy": 0.19701452553272247,
|
|
"num_tokens": 66282372.0,
|
|
"step": 33875
|
|
},
|
|
{
|
|
"entropy": 5.923374223709106,
|
|
"epoch": 3.386664667366422,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0003883088071150409,
|
|
"loss": 5.4693,
|
|
"mean_token_accuracy": 0.19502011984586715,
|
|
"num_tokens": 66291799.0,
|
|
"step": 33880
|
|
},
|
|
{
|
|
"entropy": 5.977214193344116,
|
|
"epoch": 3.3871644924276505,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0003882779724461282,
|
|
"loss": 5.4535,
|
|
"mean_token_accuracy": 0.19306301921606064,
|
|
"num_tokens": 66301973.0,
|
|
"step": 33885
|
|
},
|
|
{
|
|
"entropy": 5.868738794326783,
|
|
"epoch": 3.3876643174888788,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00038824713492717093,
|
|
"loss": 5.426,
|
|
"mean_token_accuracy": 0.19758781790733337,
|
|
"num_tokens": 66311590.0,
|
|
"step": 33890
|
|
},
|
|
{
|
|
"entropy": 5.9031288623809814,
|
|
"epoch": 3.3881641425501074,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0003882162945589449,
|
|
"loss": 5.4344,
|
|
"mean_token_accuracy": 0.19452486038208008,
|
|
"num_tokens": 66321331.0,
|
|
"step": 33895
|
|
},
|
|
{
|
|
"entropy": 5.97901759147644,
|
|
"epoch": 3.388663967611336,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0003881854513422259,
|
|
"loss": 5.4647,
|
|
"mean_token_accuracy": 0.18966536372900009,
|
|
"num_tokens": 66331012.0,
|
|
"step": 33900
|
|
},
|
|
{
|
|
"entropy": 5.925577974319458,
|
|
"epoch": 3.389163792672565,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00038815460527779017,
|
|
"loss": 5.4533,
|
|
"mean_token_accuracy": 0.197658209502697,
|
|
"num_tokens": 66340160.0,
|
|
"step": 33905
|
|
},
|
|
{
|
|
"entropy": 5.863860559463501,
|
|
"epoch": 3.389663617733793,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00038812375636641366,
|
|
"loss": 5.3917,
|
|
"mean_token_accuracy": 0.19801856577396393,
|
|
"num_tokens": 66350943.0,
|
|
"step": 33910
|
|
},
|
|
{
|
|
"entropy": 5.839590835571289,
|
|
"epoch": 3.390163442795022,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00038809290460887255,
|
|
"loss": 5.3197,
|
|
"mean_token_accuracy": 0.20272687077522278,
|
|
"num_tokens": 66360538.0,
|
|
"step": 33915
|
|
},
|
|
{
|
|
"entropy": 5.961167240142823,
|
|
"epoch": 3.3906632678562505,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00038806205000594307,
|
|
"loss": 5.4582,
|
|
"mean_token_accuracy": 0.1921697422862053,
|
|
"num_tokens": 66369357.0,
|
|
"step": 33920
|
|
},
|
|
{
|
|
"entropy": 5.9624467372894285,
|
|
"epoch": 3.3911630929174787,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0003880311925584015,
|
|
"loss": 5.5559,
|
|
"mean_token_accuracy": 0.18674810081720353,
|
|
"num_tokens": 66378863.0,
|
|
"step": 33925
|
|
},
|
|
{
|
|
"entropy": 5.9279262065887455,
|
|
"epoch": 3.3916629179787074,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00038800033226702417,
|
|
"loss": 5.4586,
|
|
"mean_token_accuracy": 0.2023158609867096,
|
|
"num_tokens": 66388461.0,
|
|
"step": 33930
|
|
},
|
|
{
|
|
"entropy": 5.867239618301392,
|
|
"epoch": 3.392162743039936,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0003879694691325877,
|
|
"loss": 5.3312,
|
|
"mean_token_accuracy": 0.21174702942371368,
|
|
"num_tokens": 66398083.0,
|
|
"step": 33935
|
|
},
|
|
{
|
|
"entropy": 5.954160737991333,
|
|
"epoch": 3.3926625681011644,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00038793860315586824,
|
|
"loss": 5.5648,
|
|
"mean_token_accuracy": 0.1901094913482666,
|
|
"num_tokens": 66407411.0,
|
|
"step": 33940
|
|
},
|
|
{
|
|
"entropy": 5.943978691101075,
|
|
"epoch": 3.393162393162393,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0003879077343376428,
|
|
"loss": 5.3944,
|
|
"mean_token_accuracy": 0.2021176666021347,
|
|
"num_tokens": 66416996.0,
|
|
"step": 33945
|
|
},
|
|
{
|
|
"entropy": 5.960674142837524,
|
|
"epoch": 3.393662218223622,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00038787686267868765,
|
|
"loss": 5.4446,
|
|
"mean_token_accuracy": 0.19606734067201614,
|
|
"num_tokens": 66426855.0,
|
|
"step": 33950
|
|
},
|
|
{
|
|
"entropy": 5.8884049415588375,
|
|
"epoch": 3.3941620432848505,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0003878459881797798,
|
|
"loss": 5.4767,
|
|
"mean_token_accuracy": 0.1893296167254448,
|
|
"num_tokens": 66437003.0,
|
|
"step": 33955
|
|
},
|
|
{
|
|
"entropy": 5.84303560256958,
|
|
"epoch": 3.3946618683460787,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00038781511084169586,
|
|
"loss": 5.3534,
|
|
"mean_token_accuracy": 0.20120154619216918,
|
|
"num_tokens": 66447013.0,
|
|
"step": 33960
|
|
},
|
|
{
|
|
"entropy": 5.91284966468811,
|
|
"epoch": 3.3951616934073074,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00038778423066521275,
|
|
"loss": 5.4668,
|
|
"mean_token_accuracy": 0.19106291383504867,
|
|
"num_tokens": 66456240.0,
|
|
"step": 33965
|
|
},
|
|
{
|
|
"entropy": 5.9342286586761475,
|
|
"epoch": 3.395661518468536,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00038775334765110746,
|
|
"loss": 5.4104,
|
|
"mean_token_accuracy": 0.20345381051301956,
|
|
"num_tokens": 66466284.0,
|
|
"step": 33970
|
|
},
|
|
{
|
|
"entropy": 5.989613246917725,
|
|
"epoch": 3.3961613435297644,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00038772246180015694,
|
|
"loss": 5.5486,
|
|
"mean_token_accuracy": 0.19206062257289885,
|
|
"num_tokens": 66476983.0,
|
|
"step": 33975
|
|
},
|
|
{
|
|
"entropy": 5.88757472038269,
|
|
"epoch": 3.396661168590993,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0003876915731131383,
|
|
"loss": 5.46,
|
|
"mean_token_accuracy": 0.1941433757543564,
|
|
"num_tokens": 66488143.0,
|
|
"step": 33980
|
|
},
|
|
{
|
|
"entropy": 5.917300224304199,
|
|
"epoch": 3.397160993652222,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0003876606815908286,
|
|
"loss": 5.3993,
|
|
"mean_token_accuracy": 0.2011224150657654,
|
|
"num_tokens": 66498354.0,
|
|
"step": 33985
|
|
},
|
|
{
|
|
"entropy": 5.86291732788086,
|
|
"epoch": 3.39766081871345,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0003876297872340052,
|
|
"loss": 5.3298,
|
|
"mean_token_accuracy": 0.20871856212615966,
|
|
"num_tokens": 66508751.0,
|
|
"step": 33990
|
|
},
|
|
{
|
|
"entropy": 5.901874971389771,
|
|
"epoch": 3.3981606437746787,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00038759889004344537,
|
|
"loss": 5.4856,
|
|
"mean_token_accuracy": 0.19690574705600739,
|
|
"num_tokens": 66518414.0,
|
|
"step": 33995
|
|
},
|
|
{
|
|
"entropy": 5.933637189865112,
|
|
"epoch": 3.3986604688359074,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00038756799001992646,
|
|
"loss": 5.4642,
|
|
"mean_token_accuracy": 0.19651562720537186,
|
|
"num_tokens": 66527876.0,
|
|
"step": 34000
|
|
},
|
|
{
|
|
"entropy": 5.970250368118286,
|
|
"epoch": 3.399160293897136,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0003875370871642258,
|
|
"loss": 5.4699,
|
|
"mean_token_accuracy": 0.19561113566160201,
|
|
"num_tokens": 66536964.0,
|
|
"step": 34005
|
|
},
|
|
{
|
|
"entropy": 5.952974653244018,
|
|
"epoch": 3.3996601189583644,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00038750618147712106,
|
|
"loss": 5.5341,
|
|
"mean_token_accuracy": 0.18740656971931458,
|
|
"num_tokens": 66546271.0,
|
|
"step": 34010
|
|
},
|
|
{
|
|
"entropy": 5.825676774978637,
|
|
"epoch": 3.400159944019593,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00038747527295938966,
|
|
"loss": 5.4315,
|
|
"mean_token_accuracy": 0.2067000836133957,
|
|
"num_tokens": 66556056.0,
|
|
"step": 34015
|
|
},
|
|
{
|
|
"entropy": 5.9185834407806395,
|
|
"epoch": 3.400659769080822,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0003874443616118095,
|
|
"loss": 5.4676,
|
|
"mean_token_accuracy": 0.19623686373233795,
|
|
"num_tokens": 66565588.0,
|
|
"step": 34020
|
|
},
|
|
{
|
|
"entropy": 6.00439567565918,
|
|
"epoch": 3.40115959414205,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00038741344743515796,
|
|
"loss": 5.4652,
|
|
"mean_token_accuracy": 0.19051608741283416,
|
|
"num_tokens": 66575814.0,
|
|
"step": 34025
|
|
},
|
|
{
|
|
"entropy": 5.974312162399292,
|
|
"epoch": 3.4016594192032787,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000387382530430213,
|
|
"loss": 5.4305,
|
|
"mean_token_accuracy": 0.19853768944740297,
|
|
"num_tokens": 66586290.0,
|
|
"step": 34030
|
|
},
|
|
{
|
|
"entropy": 5.977732992172241,
|
|
"epoch": 3.4021592442645074,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0003873516105977526,
|
|
"loss": 5.4745,
|
|
"mean_token_accuracy": 0.19467606395483017,
|
|
"num_tokens": 66595203.0,
|
|
"step": 34035
|
|
},
|
|
{
|
|
"entropy": 5.916185808181763,
|
|
"epoch": 3.402659069325736,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00038732068793855456,
|
|
"loss": 5.4417,
|
|
"mean_token_accuracy": 0.19755664020776748,
|
|
"num_tokens": 66604945.0,
|
|
"step": 34040
|
|
},
|
|
{
|
|
"entropy": 5.889283514022827,
|
|
"epoch": 3.4031588943869644,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0003872897624533969,
|
|
"loss": 5.5363,
|
|
"mean_token_accuracy": 0.19022635966539383,
|
|
"num_tokens": 66614730.0,
|
|
"step": 34045
|
|
},
|
|
{
|
|
"entropy": 6.007603406906128,
|
|
"epoch": 3.403658719448193,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0003872588341430577,
|
|
"loss": 5.5502,
|
|
"mean_token_accuracy": 0.19337694048881532,
|
|
"num_tokens": 66625567.0,
|
|
"step": 34050
|
|
},
|
|
{
|
|
"entropy": 5.885432434082031,
|
|
"epoch": 3.404158544509422,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0003872279030083151,
|
|
"loss": 5.4047,
|
|
"mean_token_accuracy": 0.19899912327528,
|
|
"num_tokens": 66635517.0,
|
|
"step": 34055
|
|
},
|
|
{
|
|
"entropy": 5.934545087814331,
|
|
"epoch": 3.40465836957065,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00038719696904994746,
|
|
"loss": 5.5142,
|
|
"mean_token_accuracy": 0.19064997285604476,
|
|
"num_tokens": 66645497.0,
|
|
"step": 34060
|
|
},
|
|
{
|
|
"entropy": 5.972386360168457,
|
|
"epoch": 3.4051581946318787,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00038716603226873286,
|
|
"loss": 5.5108,
|
|
"mean_token_accuracy": 0.19110226929187774,
|
|
"num_tokens": 66655283.0,
|
|
"step": 34065
|
|
},
|
|
{
|
|
"entropy": 5.941416883468628,
|
|
"epoch": 3.4056580196931074,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00038713509266544973,
|
|
"loss": 5.4814,
|
|
"mean_token_accuracy": 0.19019319862127304,
|
|
"num_tokens": 66664925.0,
|
|
"step": 34070
|
|
},
|
|
{
|
|
"entropy": 5.948081016540527,
|
|
"epoch": 3.406157844754336,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0003871041502408765,
|
|
"loss": 5.5143,
|
|
"mean_token_accuracy": 0.1926988333463669,
|
|
"num_tokens": 66674273.0,
|
|
"step": 34075
|
|
},
|
|
{
|
|
"entropy": 5.952268838882446,
|
|
"epoch": 3.4066576698155644,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00038707320499579176,
|
|
"loss": 5.392,
|
|
"mean_token_accuracy": 0.19684886336326599,
|
|
"num_tokens": 66683225.0,
|
|
"step": 34080
|
|
},
|
|
{
|
|
"entropy": 5.879487609863281,
|
|
"epoch": 3.407157494876793,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00038704225693097404,
|
|
"loss": 5.3957,
|
|
"mean_token_accuracy": 0.19836195707321166,
|
|
"num_tokens": 66693614.0,
|
|
"step": 34085
|
|
},
|
|
{
|
|
"entropy": 5.94861068725586,
|
|
"epoch": 3.407657319938022,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00038701130604720194,
|
|
"loss": 5.4752,
|
|
"mean_token_accuracy": 0.20171436816453933,
|
|
"num_tokens": 66703877.0,
|
|
"step": 34090
|
|
},
|
|
{
|
|
"entropy": 5.987554740905762,
|
|
"epoch": 3.40815714499925,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0003869803523452542,
|
|
"loss": 5.4817,
|
|
"mean_token_accuracy": 0.19686731398105622,
|
|
"num_tokens": 66713800.0,
|
|
"step": 34095
|
|
},
|
|
{
|
|
"entropy": 5.97938642501831,
|
|
"epoch": 3.4086569700604787,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0003869493958259096,
|
|
"loss": 5.5287,
|
|
"mean_token_accuracy": 0.18508690297603608,
|
|
"num_tokens": 66724387.0,
|
|
"step": 34100
|
|
},
|
|
{
|
|
"entropy": 5.9675116539001465,
|
|
"epoch": 3.4091567951217074,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.000386918436489947,
|
|
"loss": 5.4301,
|
|
"mean_token_accuracy": 0.20383234769105912,
|
|
"num_tokens": 66733435.0,
|
|
"step": 34105
|
|
},
|
|
{
|
|
"entropy": 5.969278001785279,
|
|
"epoch": 3.409656620182936,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0003868874743381453,
|
|
"loss": 5.5694,
|
|
"mean_token_accuracy": 0.1819090723991394,
|
|
"num_tokens": 66742799.0,
|
|
"step": 34110
|
|
},
|
|
{
|
|
"entropy": 5.970613479614258,
|
|
"epoch": 3.4101564452441644,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0003868565093712836,
|
|
"loss": 5.5122,
|
|
"mean_token_accuracy": 0.18857724368572235,
|
|
"num_tokens": 66753417.0,
|
|
"step": 34115
|
|
},
|
|
{
|
|
"entropy": 5.931589031219483,
|
|
"epoch": 3.410656270305393,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00038682554159014094,
|
|
"loss": 5.4564,
|
|
"mean_token_accuracy": 0.19662688076496124,
|
|
"num_tokens": 66763141.0,
|
|
"step": 34120
|
|
},
|
|
{
|
|
"entropy": 5.993570375442505,
|
|
"epoch": 3.411156095366622,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00038679457099549637,
|
|
"loss": 5.516,
|
|
"mean_token_accuracy": 0.19326028525829314,
|
|
"num_tokens": 66772929.0,
|
|
"step": 34125
|
|
},
|
|
{
|
|
"entropy": 5.961824512481689,
|
|
"epoch": 3.41165592042785,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0003867635975881292,
|
|
"loss": 5.5022,
|
|
"mean_token_accuracy": 0.19047563523054123,
|
|
"num_tokens": 66783343.0,
|
|
"step": 34130
|
|
},
|
|
{
|
|
"entropy": 5.981850957870483,
|
|
"epoch": 3.4121557454890787,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0003867326213688186,
|
|
"loss": 5.4738,
|
|
"mean_token_accuracy": 0.19419968873262405,
|
|
"num_tokens": 66792069.0,
|
|
"step": 34135
|
|
},
|
|
{
|
|
"entropy": 5.979427003860474,
|
|
"epoch": 3.4126555705503074,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00038670164233834406,
|
|
"loss": 5.5406,
|
|
"mean_token_accuracy": 0.18356143534183503,
|
|
"num_tokens": 66803736.0,
|
|
"step": 34140
|
|
},
|
|
{
|
|
"entropy": 5.865974760055542,
|
|
"epoch": 3.413155395611536,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00038667066049748487,
|
|
"loss": 5.4983,
|
|
"mean_token_accuracy": 0.19172572940587998,
|
|
"num_tokens": 66813007.0,
|
|
"step": 34145
|
|
},
|
|
{
|
|
"entropy": 6.018586158752441,
|
|
"epoch": 3.4136552206727644,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00038663967584702064,
|
|
"loss": 5.616,
|
|
"mean_token_accuracy": 0.18322108387947084,
|
|
"num_tokens": 66823305.0,
|
|
"step": 34150
|
|
},
|
|
{
|
|
"entropy": 5.9619019508361815,
|
|
"epoch": 3.414155045733993,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.000386608688387731,
|
|
"loss": 5.4617,
|
|
"mean_token_accuracy": 0.20059992074966432,
|
|
"num_tokens": 66833051.0,
|
|
"step": 34155
|
|
},
|
|
{
|
|
"entropy": 5.931880903244019,
|
|
"epoch": 3.414654870795222,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00038657769812039535,
|
|
"loss": 5.4487,
|
|
"mean_token_accuracy": 0.19363468438386916,
|
|
"num_tokens": 66842992.0,
|
|
"step": 34160
|
|
},
|
|
{
|
|
"entropy": 5.843361139297485,
|
|
"epoch": 3.41515469585645,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0003865467050457935,
|
|
"loss": 5.3736,
|
|
"mean_token_accuracy": 0.20659541487693786,
|
|
"num_tokens": 66852290.0,
|
|
"step": 34165
|
|
},
|
|
{
|
|
"entropy": 5.9082499027252195,
|
|
"epoch": 3.4156545209176787,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00038651570916470535,
|
|
"loss": 5.4172,
|
|
"mean_token_accuracy": 0.1965693861246109,
|
|
"num_tokens": 66862597.0,
|
|
"step": 34170
|
|
},
|
|
{
|
|
"entropy": 5.923307991027832,
|
|
"epoch": 3.4161543459789074,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00038648471047791064,
|
|
"loss": 5.4299,
|
|
"mean_token_accuracy": 0.19938699901103973,
|
|
"num_tokens": 66873815.0,
|
|
"step": 34175
|
|
},
|
|
{
|
|
"entropy": 6.023079204559326,
|
|
"epoch": 3.416654171040136,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00038645370898618924,
|
|
"loss": 5.5233,
|
|
"mean_token_accuracy": 0.19642741829156876,
|
|
"num_tokens": 66884855.0,
|
|
"step": 34180
|
|
},
|
|
{
|
|
"entropy": 5.8552570819854735,
|
|
"epoch": 3.4171539961013644,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00038642270469032127,
|
|
"loss": 5.3984,
|
|
"mean_token_accuracy": 0.20773790329694747,
|
|
"num_tokens": 66893850.0,
|
|
"step": 34185
|
|
},
|
|
{
|
|
"entropy": 5.987556743621826,
|
|
"epoch": 3.417653821162593,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0003863916975910867,
|
|
"loss": 5.5092,
|
|
"mean_token_accuracy": 0.1955697789788246,
|
|
"num_tokens": 66903587.0,
|
|
"step": 34190
|
|
},
|
|
{
|
|
"entropy": 5.969009971618652,
|
|
"epoch": 3.418153646223822,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0003863606876892657,
|
|
"loss": 5.452,
|
|
"mean_token_accuracy": 0.1856751635670662,
|
|
"num_tokens": 66912520.0,
|
|
"step": 34195
|
|
},
|
|
{
|
|
"entropy": 5.898852729797364,
|
|
"epoch": 3.41865347128505,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00038632967498563843,
|
|
"loss": 5.4192,
|
|
"mean_token_accuracy": 0.2009149372577667,
|
|
"num_tokens": 66923115.0,
|
|
"step": 34200
|
|
},
|
|
{
|
|
"entropy": 5.9667065143585205,
|
|
"epoch": 3.4191532963462787,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00038629865948098515,
|
|
"loss": 5.5217,
|
|
"mean_token_accuracy": 0.18811901211738585,
|
|
"num_tokens": 66932688.0,
|
|
"step": 34205
|
|
},
|
|
{
|
|
"entropy": 5.92742657661438,
|
|
"epoch": 3.4196531214075074,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00038626764117608627,
|
|
"loss": 5.5012,
|
|
"mean_token_accuracy": 0.19260625839233397,
|
|
"num_tokens": 66944013.0,
|
|
"step": 34210
|
|
},
|
|
{
|
|
"entropy": 5.958287477493286,
|
|
"epoch": 3.420152946468736,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0003862366200717222,
|
|
"loss": 5.5832,
|
|
"mean_token_accuracy": 0.18565982729196548,
|
|
"num_tokens": 66953924.0,
|
|
"step": 34215
|
|
},
|
|
{
|
|
"entropy": 6.020943975448608,
|
|
"epoch": 3.4206527715299644,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0003862055961686733,
|
|
"loss": 5.6107,
|
|
"mean_token_accuracy": 0.18741927593946456,
|
|
"num_tokens": 66963749.0,
|
|
"step": 34220
|
|
},
|
|
{
|
|
"entropy": 5.9511455535888675,
|
|
"epoch": 3.421152596591193,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00038617456946772035,
|
|
"loss": 5.3865,
|
|
"mean_token_accuracy": 0.19976251274347306,
|
|
"num_tokens": 66973370.0,
|
|
"step": 34225
|
|
},
|
|
{
|
|
"entropy": 5.948998260498047,
|
|
"epoch": 3.421652421652422,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0003861435399696437,
|
|
"loss": 5.5165,
|
|
"mean_token_accuracy": 0.19608266949653624,
|
|
"num_tokens": 66983556.0,
|
|
"step": 34230
|
|
},
|
|
{
|
|
"entropy": 5.854497909545898,
|
|
"epoch": 3.42215224671365,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00038611250767522427,
|
|
"loss": 5.3632,
|
|
"mean_token_accuracy": 0.20526758283376695,
|
|
"num_tokens": 66993002.0,
|
|
"step": 34235
|
|
},
|
|
{
|
|
"entropy": 5.889090442657471,
|
|
"epoch": 3.4226520717748787,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00038608147258524273,
|
|
"loss": 5.4043,
|
|
"mean_token_accuracy": 0.19320705980062486,
|
|
"num_tokens": 67002111.0,
|
|
"step": 34240
|
|
},
|
|
{
|
|
"entropy": 5.987304162979126,
|
|
"epoch": 3.4231518968361074,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0003860504347004799,
|
|
"loss": 5.4333,
|
|
"mean_token_accuracy": 0.19700082242488862,
|
|
"num_tokens": 67011236.0,
|
|
"step": 34245
|
|
},
|
|
{
|
|
"entropy": 6.03878607749939,
|
|
"epoch": 3.423651721897336,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00038601939402171676,
|
|
"loss": 5.5387,
|
|
"mean_token_accuracy": 0.1939018726348877,
|
|
"num_tokens": 67021636.0,
|
|
"step": 34250
|
|
},
|
|
{
|
|
"entropy": 5.955110359191894,
|
|
"epoch": 3.4241515469585644,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00038598835054973413,
|
|
"loss": 5.501,
|
|
"mean_token_accuracy": 0.19428949505090715,
|
|
"num_tokens": 67032099.0,
|
|
"step": 34255
|
|
},
|
|
{
|
|
"entropy": 5.917082023620606,
|
|
"epoch": 3.424651372019793,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00038595730428531323,
|
|
"loss": 5.4679,
|
|
"mean_token_accuracy": 0.19049711972475053,
|
|
"num_tokens": 67041714.0,
|
|
"step": 34260
|
|
},
|
|
{
|
|
"entropy": 5.9204058170318605,
|
|
"epoch": 3.425151197081022,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00038592625522923513,
|
|
"loss": 5.4414,
|
|
"mean_token_accuracy": 0.19853278994560242,
|
|
"num_tokens": 67051500.0,
|
|
"step": 34265
|
|
},
|
|
{
|
|
"entropy": 5.971344089508056,
|
|
"epoch": 3.42565102214225,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00038589520338228094,
|
|
"loss": 5.4843,
|
|
"mean_token_accuracy": 0.19723236858844756,
|
|
"num_tokens": 67060706.0,
|
|
"step": 34270
|
|
},
|
|
{
|
|
"entropy": 5.840265083312988,
|
|
"epoch": 3.4261508472034787,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00038586414874523204,
|
|
"loss": 5.3758,
|
|
"mean_token_accuracy": 0.21767666190862656,
|
|
"num_tokens": 67070351.0,
|
|
"step": 34275
|
|
},
|
|
{
|
|
"entropy": 5.805117988586426,
|
|
"epoch": 3.4266506722647074,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0003858330913188696,
|
|
"loss": 5.3529,
|
|
"mean_token_accuracy": 0.2016624018549919,
|
|
"num_tokens": 67081058.0,
|
|
"step": 34280
|
|
},
|
|
{
|
|
"entropy": 5.857317113876343,
|
|
"epoch": 3.427150497325936,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00038580203110397517,
|
|
"loss": 5.419,
|
|
"mean_token_accuracy": 0.19399441480636598,
|
|
"num_tokens": 67090789.0,
|
|
"step": 34285
|
|
},
|
|
{
|
|
"entropy": 5.926255989074707,
|
|
"epoch": 3.4276503223871644,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00038577096810133013,
|
|
"loss": 5.4353,
|
|
"mean_token_accuracy": 0.20171635895967482,
|
|
"num_tokens": 67099277.0,
|
|
"step": 34290
|
|
},
|
|
{
|
|
"entropy": 6.023154592514038,
|
|
"epoch": 3.428150147448393,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00038573990231171603,
|
|
"loss": 5.5467,
|
|
"mean_token_accuracy": 0.18531157672405243,
|
|
"num_tokens": 67109219.0,
|
|
"step": 34295
|
|
},
|
|
{
|
|
"entropy": 5.910036563873291,
|
|
"epoch": 3.428649972509622,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00038570883373591447,
|
|
"loss": 5.4181,
|
|
"mean_token_accuracy": 0.19530549347400666,
|
|
"num_tokens": 67119656.0,
|
|
"step": 34300
|
|
},
|
|
{
|
|
"entropy": 5.891841125488281,
|
|
"epoch": 3.42914979757085,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00038567776237470716,
|
|
"loss": 5.4062,
|
|
"mean_token_accuracy": 0.19798339307308196,
|
|
"num_tokens": 67128810.0,
|
|
"step": 34305
|
|
},
|
|
{
|
|
"entropy": 5.889173221588135,
|
|
"epoch": 3.4296496226320787,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00038564668822887576,
|
|
"loss": 5.3721,
|
|
"mean_token_accuracy": 0.2012108474969864,
|
|
"num_tokens": 67137748.0,
|
|
"step": 34310
|
|
},
|
|
{
|
|
"entropy": 5.933526468276978,
|
|
"epoch": 3.4301494476933074,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00038561561129920224,
|
|
"loss": 5.5104,
|
|
"mean_token_accuracy": 0.19266816675662995,
|
|
"num_tokens": 67147787.0,
|
|
"step": 34315
|
|
},
|
|
{
|
|
"entropy": 5.981335830688477,
|
|
"epoch": 3.430649272754536,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0003855845315864684,
|
|
"loss": 5.5862,
|
|
"mean_token_accuracy": 0.18840442299842836,
|
|
"num_tokens": 67158356.0,
|
|
"step": 34320
|
|
},
|
|
{
|
|
"entropy": 5.915089321136475,
|
|
"epoch": 3.4311490978157644,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0003855534490914562,
|
|
"loss": 5.4707,
|
|
"mean_token_accuracy": 0.194793638586998,
|
|
"num_tokens": 67167583.0,
|
|
"step": 34325
|
|
},
|
|
{
|
|
"entropy": 5.900483226776123,
|
|
"epoch": 3.431648922876993,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0003855223638149476,
|
|
"loss": 5.4058,
|
|
"mean_token_accuracy": 0.20119132250547409,
|
|
"num_tokens": 67179126.0,
|
|
"step": 34330
|
|
},
|
|
{
|
|
"entropy": 5.942169332504273,
|
|
"epoch": 3.4321487479382218,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0003854912757577249,
|
|
"loss": 5.4724,
|
|
"mean_token_accuracy": 0.19205773770809173,
|
|
"num_tokens": 67188947.0,
|
|
"step": 34335
|
|
},
|
|
{
|
|
"entropy": 5.929435205459595,
|
|
"epoch": 3.43264857299945,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00038546018492057,
|
|
"loss": 5.4314,
|
|
"mean_token_accuracy": 0.19753021895885467,
|
|
"num_tokens": 67198084.0,
|
|
"step": 34340
|
|
},
|
|
{
|
|
"entropy": 5.95058240890503,
|
|
"epoch": 3.4331483980606787,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00038542909130426527,
|
|
"loss": 5.5045,
|
|
"mean_token_accuracy": 0.19626030176877976,
|
|
"num_tokens": 67207207.0,
|
|
"step": 34345
|
|
},
|
|
{
|
|
"entropy": 5.964443016052246,
|
|
"epoch": 3.4336482231219074,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0003853979949095931,
|
|
"loss": 5.492,
|
|
"mean_token_accuracy": 0.1970304071903229,
|
|
"num_tokens": 67217568.0,
|
|
"step": 34350
|
|
},
|
|
{
|
|
"entropy": 5.949394750595093,
|
|
"epoch": 3.434148048183136,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00038536689573733575,
|
|
"loss": 5.4252,
|
|
"mean_token_accuracy": 0.1974743828177452,
|
|
"num_tokens": 67228086.0,
|
|
"step": 34355
|
|
},
|
|
{
|
|
"entropy": 5.9646586894989015,
|
|
"epoch": 3.4346478732443644,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00038533579378827567,
|
|
"loss": 5.5314,
|
|
"mean_token_accuracy": 0.19024821519851684,
|
|
"num_tokens": 67238123.0,
|
|
"step": 34360
|
|
},
|
|
{
|
|
"entropy": 5.91797661781311,
|
|
"epoch": 3.435147698305593,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0003853046890631955,
|
|
"loss": 5.4785,
|
|
"mean_token_accuracy": 0.19346430152654648,
|
|
"num_tokens": 67247570.0,
|
|
"step": 34365
|
|
},
|
|
{
|
|
"entropy": 5.8972728729248045,
|
|
"epoch": 3.4356475233668218,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00038527358156287766,
|
|
"loss": 5.4498,
|
|
"mean_token_accuracy": 0.19758383482694625,
|
|
"num_tokens": 67257298.0,
|
|
"step": 34370
|
|
},
|
|
{
|
|
"entropy": 5.943633413314819,
|
|
"epoch": 3.43614734842805,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0003852424712881049,
|
|
"loss": 5.5543,
|
|
"mean_token_accuracy": 0.18722303509712218,
|
|
"num_tokens": 67266219.0,
|
|
"step": 34375
|
|
},
|
|
{
|
|
"entropy": 5.905250597000122,
|
|
"epoch": 3.4366471734892787,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00038521135823965994,
|
|
"loss": 5.3834,
|
|
"mean_token_accuracy": 0.20827464610338212,
|
|
"num_tokens": 67276436.0,
|
|
"step": 34380
|
|
},
|
|
{
|
|
"entropy": 5.941431474685669,
|
|
"epoch": 3.4371469985505074,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00038518024241832553,
|
|
"loss": 5.4529,
|
|
"mean_token_accuracy": 0.19428510516881942,
|
|
"num_tokens": 67286661.0,
|
|
"step": 34385
|
|
},
|
|
{
|
|
"entropy": 5.966383075714111,
|
|
"epoch": 3.437646823611736,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0003851491238248846,
|
|
"loss": 5.5134,
|
|
"mean_token_accuracy": 0.19326536655426024,
|
|
"num_tokens": 67295586.0,
|
|
"step": 34390
|
|
},
|
|
{
|
|
"entropy": 5.950391864776611,
|
|
"epoch": 3.4381466486729644,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0003851180024601201,
|
|
"loss": 5.4464,
|
|
"mean_token_accuracy": 0.19190459698438644,
|
|
"num_tokens": 67304701.0,
|
|
"step": 34395
|
|
},
|
|
{
|
|
"entropy": 5.8976398468017575,
|
|
"epoch": 3.438646473734193,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.000385086878324815,
|
|
"loss": 5.4851,
|
|
"mean_token_accuracy": 0.19949835240840913,
|
|
"num_tokens": 67313825.0,
|
|
"step": 34400
|
|
},
|
|
{
|
|
"entropy": 5.9018923282623295,
|
|
"epoch": 3.4391462987954218,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0003850557514197523,
|
|
"loss": 5.4228,
|
|
"mean_token_accuracy": 0.1908803328871727,
|
|
"num_tokens": 67323306.0,
|
|
"step": 34405
|
|
},
|
|
{
|
|
"entropy": 5.969317626953125,
|
|
"epoch": 3.43964612385665,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0003850246217457152,
|
|
"loss": 5.5068,
|
|
"mean_token_accuracy": 0.18288948833942414,
|
|
"num_tokens": 67333579.0,
|
|
"step": 34410
|
|
},
|
|
{
|
|
"entropy": 5.974358797073364,
|
|
"epoch": 3.4401459489178787,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000384993489303487,
|
|
"loss": 5.4651,
|
|
"mean_token_accuracy": 0.19329252392053603,
|
|
"num_tokens": 67343242.0,
|
|
"step": 34415
|
|
},
|
|
{
|
|
"entropy": 6.000909519195557,
|
|
"epoch": 3.4406457739791074,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00038496235409385084,
|
|
"loss": 5.4708,
|
|
"mean_token_accuracy": 0.1867142826318741,
|
|
"num_tokens": 67352466.0,
|
|
"step": 34420
|
|
},
|
|
{
|
|
"entropy": 5.87743558883667,
|
|
"epoch": 3.441145599040336,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00038493121611759016,
|
|
"loss": 5.4287,
|
|
"mean_token_accuracy": 0.2011679917573929,
|
|
"num_tokens": 67361298.0,
|
|
"step": 34425
|
|
},
|
|
{
|
|
"entropy": 5.918802070617676,
|
|
"epoch": 3.4416454241015644,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00038490007537548843,
|
|
"loss": 5.5003,
|
|
"mean_token_accuracy": 0.1906790018081665,
|
|
"num_tokens": 67370007.0,
|
|
"step": 34430
|
|
},
|
|
{
|
|
"entropy": 5.939883756637573,
|
|
"epoch": 3.442145249162793,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0003848689318683291,
|
|
"loss": 5.4497,
|
|
"mean_token_accuracy": 0.1999095767736435,
|
|
"num_tokens": 67381047.0,
|
|
"step": 34435
|
|
},
|
|
{
|
|
"entropy": 5.906305980682373,
|
|
"epoch": 3.4426450742240218,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0003848377855968957,
|
|
"loss": 5.4479,
|
|
"mean_token_accuracy": 0.19394621104002,
|
|
"num_tokens": 67390021.0,
|
|
"step": 34440
|
|
},
|
|
{
|
|
"entropy": 5.897031688690186,
|
|
"epoch": 3.44314489928525,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0003848066365619718,
|
|
"loss": 5.447,
|
|
"mean_token_accuracy": 0.19130592346191405,
|
|
"num_tokens": 67399723.0,
|
|
"step": 34445
|
|
},
|
|
{
|
|
"entropy": 5.832881355285645,
|
|
"epoch": 3.4436447243464787,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0003847754847643412,
|
|
"loss": 5.3404,
|
|
"mean_token_accuracy": 0.21535129249095916,
|
|
"num_tokens": 67410296.0,
|
|
"step": 34450
|
|
},
|
|
{
|
|
"entropy": 5.877086591720581,
|
|
"epoch": 3.4441445494077074,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0003847443302047877,
|
|
"loss": 5.4608,
|
|
"mean_token_accuracy": 0.19681969434022903,
|
|
"num_tokens": 67420000.0,
|
|
"step": 34455
|
|
},
|
|
{
|
|
"entropy": 5.890182638168335,
|
|
"epoch": 3.444644374468936,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.000384713172884095,
|
|
"loss": 5.4039,
|
|
"mean_token_accuracy": 0.19858485013246535,
|
|
"num_tokens": 67428599.0,
|
|
"step": 34460
|
|
},
|
|
{
|
|
"entropy": 5.877026748657227,
|
|
"epoch": 3.4451441995301644,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0003846820128030472,
|
|
"loss": 5.445,
|
|
"mean_token_accuracy": 0.19923816621303558,
|
|
"num_tokens": 67438390.0,
|
|
"step": 34465
|
|
},
|
|
{
|
|
"entropy": 5.935630846023559,
|
|
"epoch": 3.445644024591393,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00038465084996242824,
|
|
"loss": 5.441,
|
|
"mean_token_accuracy": 0.19625091105699538,
|
|
"num_tokens": 67448189.0,
|
|
"step": 34470
|
|
},
|
|
{
|
|
"entropy": 5.897636651992798,
|
|
"epoch": 3.4461438496526218,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000384619684363022,
|
|
"loss": 5.4823,
|
|
"mean_token_accuracy": 0.19640648514032363,
|
|
"num_tokens": 67458650.0,
|
|
"step": 34475
|
|
},
|
|
{
|
|
"entropy": 5.8783143043518065,
|
|
"epoch": 3.44664367471385,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0003845885160056127,
|
|
"loss": 5.4404,
|
|
"mean_token_accuracy": 0.1978878691792488,
|
|
"num_tokens": 67468316.0,
|
|
"step": 34480
|
|
},
|
|
{
|
|
"entropy": 5.864918375015259,
|
|
"epoch": 3.4471434997750787,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00038455734489098453,
|
|
"loss": 5.4127,
|
|
"mean_token_accuracy": 0.19230341166257858,
|
|
"num_tokens": 67477507.0,
|
|
"step": 34485
|
|
},
|
|
{
|
|
"entropy": 5.9205094337463375,
|
|
"epoch": 3.4476433248363074,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0003845261710199218,
|
|
"loss": 5.4877,
|
|
"mean_token_accuracy": 0.1885392889380455,
|
|
"num_tokens": 67487310.0,
|
|
"step": 34490
|
|
},
|
|
{
|
|
"entropy": 5.914922189712525,
|
|
"epoch": 3.4481431498975357,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00038449499439320876,
|
|
"loss": 5.4062,
|
|
"mean_token_accuracy": 0.20244037210941315,
|
|
"num_tokens": 67496930.0,
|
|
"step": 34495
|
|
},
|
|
{
|
|
"entropy": 6.0467699527740475,
|
|
"epoch": 3.4486429749587644,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00038446381501162983,
|
|
"loss": 5.5502,
|
|
"mean_token_accuracy": 0.18738383650779725,
|
|
"num_tokens": 67506105.0,
|
|
"step": 34500
|
|
},
|
|
{
|
|
"entropy": 5.895125007629394,
|
|
"epoch": 3.449142800019993,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00038443263287596966,
|
|
"loss": 5.3702,
|
|
"mean_token_accuracy": 0.20902429521083832,
|
|
"num_tokens": 67516326.0,
|
|
"step": 34505
|
|
},
|
|
{
|
|
"entropy": 5.863125944137574,
|
|
"epoch": 3.4496426250812213,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0003844014479870124,
|
|
"loss": 5.4312,
|
|
"mean_token_accuracy": 0.20283697098493575,
|
|
"num_tokens": 67525709.0,
|
|
"step": 34510
|
|
},
|
|
{
|
|
"entropy": 5.874116325378418,
|
|
"epoch": 3.45014245014245,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00038437026034554285,
|
|
"loss": 5.3411,
|
|
"mean_token_accuracy": 0.20350470691919326,
|
|
"num_tokens": 67534790.0,
|
|
"step": 34515
|
|
},
|
|
{
|
|
"entropy": 5.753525161743164,
|
|
"epoch": 3.4506422752036787,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0003843390699523458,
|
|
"loss": 5.2346,
|
|
"mean_token_accuracy": 0.21648120284080505,
|
|
"num_tokens": 67544446.0,
|
|
"step": 34520
|
|
},
|
|
{
|
|
"entropy": 5.923121643066406,
|
|
"epoch": 3.4511421002649074,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0003843078768082058,
|
|
"loss": 5.4789,
|
|
"mean_token_accuracy": 0.19213939011096953,
|
|
"num_tokens": 67554029.0,
|
|
"step": 34525
|
|
},
|
|
{
|
|
"entropy": 5.958922863006592,
|
|
"epoch": 3.4516419253261357,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00038427668091390785,
|
|
"loss": 5.4552,
|
|
"mean_token_accuracy": 0.18972249180078507,
|
|
"num_tokens": 67563224.0,
|
|
"step": 34530
|
|
},
|
|
{
|
|
"entropy": 5.938675880432129,
|
|
"epoch": 3.4521417503873644,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00038424548227023657,
|
|
"loss": 5.4566,
|
|
"mean_token_accuracy": 0.19325418323278426,
|
|
"num_tokens": 67572228.0,
|
|
"step": 34535
|
|
},
|
|
{
|
|
"entropy": 5.982130241394043,
|
|
"epoch": 3.452641575448593,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00038421428087797725,
|
|
"loss": 5.5022,
|
|
"mean_token_accuracy": 0.19248849004507065,
|
|
"num_tokens": 67582222.0,
|
|
"step": 34540
|
|
},
|
|
{
|
|
"entropy": 5.9186890602111815,
|
|
"epoch": 3.4531414005098213,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00038418307673791465,
|
|
"loss": 5.4067,
|
|
"mean_token_accuracy": 0.20191590785980223,
|
|
"num_tokens": 67591692.0,
|
|
"step": 34545
|
|
},
|
|
{
|
|
"entropy": 5.953020811080933,
|
|
"epoch": 3.45364122557105,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0003841518698508339,
|
|
"loss": 5.5243,
|
|
"mean_token_accuracy": 0.1899039089679718,
|
|
"num_tokens": 67600972.0,
|
|
"step": 34550
|
|
},
|
|
{
|
|
"entropy": 5.935927629470825,
|
|
"epoch": 3.4541410506322787,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0003841206602175202,
|
|
"loss": 5.3753,
|
|
"mean_token_accuracy": 0.2032573863863945,
|
|
"num_tokens": 67610697.0,
|
|
"step": 34555
|
|
},
|
|
{
|
|
"entropy": 5.929256343841553,
|
|
"epoch": 3.4546408756935074,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0003840894478387588,
|
|
"loss": 5.483,
|
|
"mean_token_accuracy": 0.19748149961233138,
|
|
"num_tokens": 67620268.0,
|
|
"step": 34560
|
|
},
|
|
{
|
|
"entropy": 5.874195098876953,
|
|
"epoch": 3.4551407007547357,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00038405823271533496,
|
|
"loss": 5.4258,
|
|
"mean_token_accuracy": 0.20322313755750657,
|
|
"num_tokens": 67629100.0,
|
|
"step": 34565
|
|
},
|
|
{
|
|
"entropy": 5.9491129398345945,
|
|
"epoch": 3.4556405258159644,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00038402701484803404,
|
|
"loss": 5.5071,
|
|
"mean_token_accuracy": 0.18859318643808365,
|
|
"num_tokens": 67639339.0,
|
|
"step": 34570
|
|
},
|
|
{
|
|
"entropy": 5.967541885375977,
|
|
"epoch": 3.456140350877193,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00038399579423764146,
|
|
"loss": 5.4678,
|
|
"mean_token_accuracy": 0.19183466136455535,
|
|
"num_tokens": 67649310.0,
|
|
"step": 34575
|
|
},
|
|
{
|
|
"entropy": 5.966200685501098,
|
|
"epoch": 3.4566401759384213,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0003839645708849428,
|
|
"loss": 5.4858,
|
|
"mean_token_accuracy": 0.19957449436187744,
|
|
"num_tokens": 67659272.0,
|
|
"step": 34580
|
|
},
|
|
{
|
|
"entropy": 5.896160364151001,
|
|
"epoch": 3.45714000099965,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0003839333447907235,
|
|
"loss": 5.4602,
|
|
"mean_token_accuracy": 0.1959846556186676,
|
|
"num_tokens": 67668906.0,
|
|
"step": 34585
|
|
},
|
|
{
|
|
"entropy": 5.911605405807495,
|
|
"epoch": 3.4576398260608787,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0003839021159557693,
|
|
"loss": 5.4577,
|
|
"mean_token_accuracy": 0.18956841975450517,
|
|
"num_tokens": 67679030.0,
|
|
"step": 34590
|
|
},
|
|
{
|
|
"entropy": 5.8952531814575195,
|
|
"epoch": 3.4581396511221074,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0003838708843808659,
|
|
"loss": 5.3908,
|
|
"mean_token_accuracy": 0.19983399659395218,
|
|
"num_tokens": 67688347.0,
|
|
"step": 34595
|
|
},
|
|
{
|
|
"entropy": 5.986264085769653,
|
|
"epoch": 3.4586394761833357,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00038383965006679913,
|
|
"loss": 5.5656,
|
|
"mean_token_accuracy": 0.18559337705373763,
|
|
"num_tokens": 67697681.0,
|
|
"step": 34600
|
|
},
|
|
{
|
|
"entropy": 5.918498516082764,
|
|
"epoch": 3.4591393012445644,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00038380841301435467,
|
|
"loss": 5.4925,
|
|
"mean_token_accuracy": 0.19250052869319917,
|
|
"num_tokens": 67707068.0,
|
|
"step": 34605
|
|
},
|
|
{
|
|
"entropy": 6.023798561096191,
|
|
"epoch": 3.459639126305793,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0003837771732243186,
|
|
"loss": 5.5113,
|
|
"mean_token_accuracy": 0.18790342658758163,
|
|
"num_tokens": 67716201.0,
|
|
"step": 34610
|
|
},
|
|
{
|
|
"entropy": 5.963696813583374,
|
|
"epoch": 3.4601389513670213,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0003837459306974768,
|
|
"loss": 5.5505,
|
|
"mean_token_accuracy": 0.186627858877182,
|
|
"num_tokens": 67726251.0,
|
|
"step": 34615
|
|
},
|
|
{
|
|
"entropy": 5.898096942901612,
|
|
"epoch": 3.46063877642825,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0003837146854346154,
|
|
"loss": 5.4712,
|
|
"mean_token_accuracy": 0.19929771423339843,
|
|
"num_tokens": 67736158.0,
|
|
"step": 34620
|
|
},
|
|
{
|
|
"entropy": 5.90753927230835,
|
|
"epoch": 3.4611386014894787,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00038368343743652044,
|
|
"loss": 5.3646,
|
|
"mean_token_accuracy": 0.2067810371518135,
|
|
"num_tokens": 67744686.0,
|
|
"step": 34625
|
|
},
|
|
{
|
|
"entropy": 5.963289451599121,
|
|
"epoch": 3.4616384265507074,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0003836521867039782,
|
|
"loss": 5.4754,
|
|
"mean_token_accuracy": 0.1897603064775467,
|
|
"num_tokens": 67754977.0,
|
|
"step": 34630
|
|
},
|
|
{
|
|
"entropy": 6.047275543212891,
|
|
"epoch": 3.4621382516119357,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00038362093323777486,
|
|
"loss": 5.6511,
|
|
"mean_token_accuracy": 0.17481419146060945,
|
|
"num_tokens": 67765801.0,
|
|
"step": 34635
|
|
},
|
|
{
|
|
"entropy": 5.958988189697266,
|
|
"epoch": 3.4626380766731644,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0003835896770386968,
|
|
"loss": 5.4987,
|
|
"mean_token_accuracy": 0.19640391916036606,
|
|
"num_tokens": 67775733.0,
|
|
"step": 34640
|
|
},
|
|
{
|
|
"entropy": 5.919845008850098,
|
|
"epoch": 3.463137901734393,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00038355841810753047,
|
|
"loss": 5.3711,
|
|
"mean_token_accuracy": 0.20437223613262176,
|
|
"num_tokens": 67785379.0,
|
|
"step": 34645
|
|
},
|
|
{
|
|
"entropy": 5.905098724365234,
|
|
"epoch": 3.4636377267956213,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0003835271564450622,
|
|
"loss": 5.3974,
|
|
"mean_token_accuracy": 0.20299324095249177,
|
|
"num_tokens": 67794561.0,
|
|
"step": 34650
|
|
},
|
|
{
|
|
"entropy": 5.882570075988769,
|
|
"epoch": 3.46413755185685,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0003834958920520786,
|
|
"loss": 5.4218,
|
|
"mean_token_accuracy": 0.20690759420394897,
|
|
"num_tokens": 67803398.0,
|
|
"step": 34655
|
|
},
|
|
{
|
|
"entropy": 5.907194948196411,
|
|
"epoch": 3.4646373769180787,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0003834646249293664,
|
|
"loss": 5.4909,
|
|
"mean_token_accuracy": 0.20270473808050155,
|
|
"num_tokens": 67813073.0,
|
|
"step": 34660
|
|
},
|
|
{
|
|
"entropy": 5.842949151992798,
|
|
"epoch": 3.4651372019793074,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00038343335507771205,
|
|
"loss": 5.3693,
|
|
"mean_token_accuracy": 0.19912279099226,
|
|
"num_tokens": 67823191.0,
|
|
"step": 34665
|
|
},
|
|
{
|
|
"entropy": 5.879367876052856,
|
|
"epoch": 3.4656370270405357,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00038340208249790236,
|
|
"loss": 5.4169,
|
|
"mean_token_accuracy": 0.20203491896390915,
|
|
"num_tokens": 67833426.0,
|
|
"step": 34670
|
|
},
|
|
{
|
|
"entropy": 5.897451591491699,
|
|
"epoch": 3.4661368521017644,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0003833708071907242,
|
|
"loss": 5.489,
|
|
"mean_token_accuracy": 0.18944235593080522,
|
|
"num_tokens": 67842225.0,
|
|
"step": 34675
|
|
},
|
|
{
|
|
"entropy": 5.904661703109741,
|
|
"epoch": 3.466636677162993,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0003833395291569644,
|
|
"loss": 5.4618,
|
|
"mean_token_accuracy": 0.19953178316354753,
|
|
"num_tokens": 67850772.0,
|
|
"step": 34680
|
|
},
|
|
{
|
|
"entropy": 5.973672533035279,
|
|
"epoch": 3.4671365022242213,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00038330824839740996,
|
|
"loss": 5.4851,
|
|
"mean_token_accuracy": 0.18902743756771087,
|
|
"num_tokens": 67860811.0,
|
|
"step": 34685
|
|
},
|
|
{
|
|
"entropy": 6.04745831489563,
|
|
"epoch": 3.46763632728545,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00038327696491284786,
|
|
"loss": 5.5362,
|
|
"mean_token_accuracy": 0.19242200553417205,
|
|
"num_tokens": 67871297.0,
|
|
"step": 34690
|
|
},
|
|
{
|
|
"entropy": 5.855612850189209,
|
|
"epoch": 3.4681361523466787,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00038324567870406517,
|
|
"loss": 5.402,
|
|
"mean_token_accuracy": 0.1990138664841652,
|
|
"num_tokens": 67881530.0,
|
|
"step": 34695
|
|
},
|
|
{
|
|
"entropy": 5.977526569366455,
|
|
"epoch": 3.4686359774079074,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000383214389771849,
|
|
"loss": 5.5656,
|
|
"mean_token_accuracy": 0.18432590514421462,
|
|
"num_tokens": 67891655.0,
|
|
"step": 34700
|
|
},
|
|
{
|
|
"entropy": 5.914781093597412,
|
|
"epoch": 3.4691358024691357,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0003831830981169867,
|
|
"loss": 5.3927,
|
|
"mean_token_accuracy": 0.20892363935709,
|
|
"num_tokens": 67900941.0,
|
|
"step": 34705
|
|
},
|
|
{
|
|
"entropy": 5.884496736526489,
|
|
"epoch": 3.4696356275303644,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0003831518037402655,
|
|
"loss": 5.453,
|
|
"mean_token_accuracy": 0.2045101895928383,
|
|
"num_tokens": 67910713.0,
|
|
"step": 34710
|
|
},
|
|
{
|
|
"entropy": 5.905143594741821,
|
|
"epoch": 3.470135452591593,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0003831205066424728,
|
|
"loss": 5.4751,
|
|
"mean_token_accuracy": 0.19373014718294143,
|
|
"num_tokens": 67920274.0,
|
|
"step": 34715
|
|
},
|
|
{
|
|
"entropy": 5.9703020572662355,
|
|
"epoch": 3.4706352776528213,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00038308920682439586,
|
|
"loss": 5.5441,
|
|
"mean_token_accuracy": 0.18924791514873504,
|
|
"num_tokens": 67930357.0,
|
|
"step": 34720
|
|
},
|
|
{
|
|
"entropy": 5.9290220737457275,
|
|
"epoch": 3.47113510271405,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0003830579042868223,
|
|
"loss": 5.4467,
|
|
"mean_token_accuracy": 0.20879292339086533,
|
|
"num_tokens": 67939375.0,
|
|
"step": 34725
|
|
},
|
|
{
|
|
"entropy": 5.879792594909668,
|
|
"epoch": 3.4716349277752787,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0003830265990305397,
|
|
"loss": 5.4417,
|
|
"mean_token_accuracy": 0.19630779474973678,
|
|
"num_tokens": 67947901.0,
|
|
"step": 34730
|
|
},
|
|
{
|
|
"entropy": 5.88857741355896,
|
|
"epoch": 3.4721347528365074,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0003829952910563356,
|
|
"loss": 5.4708,
|
|
"mean_token_accuracy": 0.1969543293118477,
|
|
"num_tokens": 67958801.0,
|
|
"step": 34735
|
|
},
|
|
{
|
|
"entropy": 5.972600603103638,
|
|
"epoch": 3.4726345778977357,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00038296398036499784,
|
|
"loss": 5.5187,
|
|
"mean_token_accuracy": 0.1883957251906395,
|
|
"num_tokens": 67967291.0,
|
|
"step": 34740
|
|
},
|
|
{
|
|
"entropy": 5.9361473560333256,
|
|
"epoch": 3.4731344029589644,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00038293266695731414,
|
|
"loss": 5.3891,
|
|
"mean_token_accuracy": 0.20224207043647766,
|
|
"num_tokens": 67978304.0,
|
|
"step": 34745
|
|
},
|
|
{
|
|
"entropy": 5.988872289657593,
|
|
"epoch": 3.473634228020193,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00038290135083407235,
|
|
"loss": 5.4652,
|
|
"mean_token_accuracy": 0.19262256026268004,
|
|
"num_tokens": 67987931.0,
|
|
"step": 34750
|
|
},
|
|
{
|
|
"entropy": 5.9259929180145265,
|
|
"epoch": 3.4741340530814213,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00038287003199606026,
|
|
"loss": 5.5088,
|
|
"mean_token_accuracy": 0.18996842652559282,
|
|
"num_tokens": 67998199.0,
|
|
"step": 34755
|
|
},
|
|
{
|
|
"entropy": 5.8217850685119625,
|
|
"epoch": 3.47463387814265,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0003828387104440659,
|
|
"loss": 5.47,
|
|
"mean_token_accuracy": 0.20253816545009612,
|
|
"num_tokens": 68010650.0,
|
|
"step": 34760
|
|
},
|
|
{
|
|
"entropy": 5.967388486862182,
|
|
"epoch": 3.4751337032038787,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0003828073861788773,
|
|
"loss": 5.5054,
|
|
"mean_token_accuracy": 0.18893494755029677,
|
|
"num_tokens": 68019803.0,
|
|
"step": 34765
|
|
},
|
|
{
|
|
"entropy": 5.980349111557007,
|
|
"epoch": 3.4756335282651074,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00038277605920128275,
|
|
"loss": 5.5137,
|
|
"mean_token_accuracy": 0.19168319851160048,
|
|
"num_tokens": 68029809.0,
|
|
"step": 34770
|
|
},
|
|
{
|
|
"entropy": 5.91628246307373,
|
|
"epoch": 3.4761333533263357,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0003827447295120702,
|
|
"loss": 5.371,
|
|
"mean_token_accuracy": 0.20250632017850875,
|
|
"num_tokens": 68039644.0,
|
|
"step": 34775
|
|
},
|
|
{
|
|
"entropy": 5.888224458694458,
|
|
"epoch": 3.4766331783875644,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00038271339711202796,
|
|
"loss": 5.4115,
|
|
"mean_token_accuracy": 0.1939457669854164,
|
|
"num_tokens": 68049610.0,
|
|
"step": 34780
|
|
},
|
|
{
|
|
"entropy": 6.000068807601929,
|
|
"epoch": 3.477133003448793,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0003826820620019444,
|
|
"loss": 5.5363,
|
|
"mean_token_accuracy": 0.18518902808427812,
|
|
"num_tokens": 68059959.0,
|
|
"step": 34785
|
|
},
|
|
{
|
|
"entropy": 5.903310012817383,
|
|
"epoch": 3.4776328285100213,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0003826507241826079,
|
|
"loss": 5.4711,
|
|
"mean_token_accuracy": 0.19274502694606782,
|
|
"num_tokens": 68070174.0,
|
|
"step": 34790
|
|
},
|
|
{
|
|
"entropy": 5.863117408752442,
|
|
"epoch": 3.47813265357125,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00038261938365480677,
|
|
"loss": 5.4383,
|
|
"mean_token_accuracy": 0.1956130161881447,
|
|
"num_tokens": 68081080.0,
|
|
"step": 34795
|
|
},
|
|
{
|
|
"entropy": 5.923991060256958,
|
|
"epoch": 3.4786324786324787,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0003825880404193297,
|
|
"loss": 5.4563,
|
|
"mean_token_accuracy": 0.19315972775220872,
|
|
"num_tokens": 68090595.0,
|
|
"step": 34800
|
|
},
|
|
{
|
|
"entropy": 5.917164468765259,
|
|
"epoch": 3.4791323036937074,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00038255669447696523,
|
|
"loss": 5.4516,
|
|
"mean_token_accuracy": 0.19931181520223618,
|
|
"num_tokens": 68100187.0,
|
|
"step": 34805
|
|
},
|
|
{
|
|
"entropy": 5.921387815475464,
|
|
"epoch": 3.4796321287549357,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000382525345828502,
|
|
"loss": 5.4326,
|
|
"mean_token_accuracy": 0.19611538350582122,
|
|
"num_tokens": 68109793.0,
|
|
"step": 34810
|
|
},
|
|
{
|
|
"entropy": 5.945957946777344,
|
|
"epoch": 3.4801319538161644,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0003824939944747288,
|
|
"loss": 5.5241,
|
|
"mean_token_accuracy": 0.19197115451097488,
|
|
"num_tokens": 68119773.0,
|
|
"step": 34815
|
|
},
|
|
{
|
|
"entropy": 5.947470045089721,
|
|
"epoch": 3.480631778877393,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0003824626404164343,
|
|
"loss": 5.4196,
|
|
"mean_token_accuracy": 0.19701048880815505,
|
|
"num_tokens": 68129839.0,
|
|
"step": 34820
|
|
},
|
|
{
|
|
"entropy": 5.917461681365967,
|
|
"epoch": 3.4811316039386213,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00038243128365440744,
|
|
"loss": 5.4756,
|
|
"mean_token_accuracy": 0.19779601246118544,
|
|
"num_tokens": 68139168.0,
|
|
"step": 34825
|
|
},
|
|
{
|
|
"entropy": 5.848917388916016,
|
|
"epoch": 3.48163142899985,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000382399924189437,
|
|
"loss": 5.4117,
|
|
"mean_token_accuracy": 0.20455446541309358,
|
|
"num_tokens": 68148062.0,
|
|
"step": 34830
|
|
},
|
|
{
|
|
"entropy": 5.928724908828736,
|
|
"epoch": 3.4821312540610787,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0003823685620223122,
|
|
"loss": 5.4676,
|
|
"mean_token_accuracy": 0.19913809448480607,
|
|
"num_tokens": 68157266.0,
|
|
"step": 34835
|
|
},
|
|
{
|
|
"entropy": 5.896325397491455,
|
|
"epoch": 3.4826310791223074,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0003823371971538221,
|
|
"loss": 5.4187,
|
|
"mean_token_accuracy": 0.20381030142307283,
|
|
"num_tokens": 68167156.0,
|
|
"step": 34840
|
|
},
|
|
{
|
|
"entropy": 6.014058828353882,
|
|
"epoch": 3.4831309041835357,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00038230582958475565,
|
|
"loss": 5.5474,
|
|
"mean_token_accuracy": 0.18457821756601334,
|
|
"num_tokens": 68176900.0,
|
|
"step": 34845
|
|
},
|
|
{
|
|
"entropy": 5.890753555297851,
|
|
"epoch": 3.4836307292447644,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00038227445931590215,
|
|
"loss": 5.4217,
|
|
"mean_token_accuracy": 0.20159479528665541,
|
|
"num_tokens": 68186193.0,
|
|
"step": 34850
|
|
},
|
|
{
|
|
"entropy": 5.910853576660156,
|
|
"epoch": 3.484130554305993,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0003822430863480508,
|
|
"loss": 5.4347,
|
|
"mean_token_accuracy": 0.1986345648765564,
|
|
"num_tokens": 68195962.0,
|
|
"step": 34855
|
|
},
|
|
{
|
|
"entropy": 5.986239194869995,
|
|
"epoch": 3.4846303793672213,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00038221171068199104,
|
|
"loss": 5.5442,
|
|
"mean_token_accuracy": 0.18939049839973449,
|
|
"num_tokens": 68205002.0,
|
|
"step": 34860
|
|
},
|
|
{
|
|
"entropy": 5.9238790512084964,
|
|
"epoch": 3.48513020442845,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0003821803323185123,
|
|
"loss": 5.3998,
|
|
"mean_token_accuracy": 0.20302311927080155,
|
|
"num_tokens": 68213229.0,
|
|
"step": 34865
|
|
},
|
|
{
|
|
"entropy": 5.997788143157959,
|
|
"epoch": 3.4856300294896787,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0003821489512584039,
|
|
"loss": 5.4863,
|
|
"mean_token_accuracy": 0.19273341298103333,
|
|
"num_tokens": 68223390.0,
|
|
"step": 34870
|
|
},
|
|
{
|
|
"entropy": 5.959941577911377,
|
|
"epoch": 3.4861298545509074,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00038211756750245547,
|
|
"loss": 5.5518,
|
|
"mean_token_accuracy": 0.18592564016580582,
|
|
"num_tokens": 68233363.0,
|
|
"step": 34875
|
|
},
|
|
{
|
|
"entropy": 6.002761745452881,
|
|
"epoch": 3.4866296796121357,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0003820861810514566,
|
|
"loss": 5.5071,
|
|
"mean_token_accuracy": 0.19355617463588715,
|
|
"num_tokens": 68245139.0,
|
|
"step": 34880
|
|
},
|
|
{
|
|
"entropy": 5.980663871765136,
|
|
"epoch": 3.4871295046733644,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00038205479190619703,
|
|
"loss": 5.5278,
|
|
"mean_token_accuracy": 0.19459039270877837,
|
|
"num_tokens": 68254347.0,
|
|
"step": 34885
|
|
},
|
|
{
|
|
"entropy": 5.968006944656372,
|
|
"epoch": 3.487629329734593,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00038202340006746635,
|
|
"loss": 5.5172,
|
|
"mean_token_accuracy": 0.19090825021266938,
|
|
"num_tokens": 68263900.0,
|
|
"step": 34890
|
|
},
|
|
{
|
|
"entropy": 5.911361455917358,
|
|
"epoch": 3.4881291547958213,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0003819920055360545,
|
|
"loss": 5.3662,
|
|
"mean_token_accuracy": 0.19939675331115722,
|
|
"num_tokens": 68273348.0,
|
|
"step": 34895
|
|
},
|
|
{
|
|
"entropy": 5.836695146560669,
|
|
"epoch": 3.48862897985705,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00038196060831275134,
|
|
"loss": 5.385,
|
|
"mean_token_accuracy": 0.19803554117679595,
|
|
"num_tokens": 68282448.0,
|
|
"step": 34900
|
|
},
|
|
{
|
|
"entropy": 5.8430788040161135,
|
|
"epoch": 3.4891288049182787,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0003819292083983468,
|
|
"loss": 5.3841,
|
|
"mean_token_accuracy": 0.20175137966871262,
|
|
"num_tokens": 68291945.0,
|
|
"step": 34905
|
|
},
|
|
{
|
|
"entropy": 5.802953910827637,
|
|
"epoch": 3.4896286299795074,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0003818978057936308,
|
|
"loss": 5.3525,
|
|
"mean_token_accuracy": 0.20477608740329742,
|
|
"num_tokens": 68302072.0,
|
|
"step": 34910
|
|
},
|
|
{
|
|
"entropy": 5.932099771499634,
|
|
"epoch": 3.4901284550407357,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00038186640049939365,
|
|
"loss": 5.4917,
|
|
"mean_token_accuracy": 0.1971712216734886,
|
|
"num_tokens": 68310968.0,
|
|
"step": 34915
|
|
},
|
|
{
|
|
"entropy": 5.958176755905152,
|
|
"epoch": 3.4906282801019644,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0003818349925164253,
|
|
"loss": 5.5003,
|
|
"mean_token_accuracy": 0.19431747645139694,
|
|
"num_tokens": 68320925.0,
|
|
"step": 34920
|
|
},
|
|
{
|
|
"entropy": 5.965729904174805,
|
|
"epoch": 3.491128105163193,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000381803581845516,
|
|
"loss": 5.4841,
|
|
"mean_token_accuracy": 0.19315267354249954,
|
|
"num_tokens": 68331440.0,
|
|
"step": 34925
|
|
},
|
|
{
|
|
"entropy": 5.966488933563232,
|
|
"epoch": 3.4916279302244213,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00038177216848745614,
|
|
"loss": 5.4649,
|
|
"mean_token_accuracy": 0.19039061814546585,
|
|
"num_tokens": 68340726.0,
|
|
"step": 34930
|
|
},
|
|
{
|
|
"entropy": 5.889063453674316,
|
|
"epoch": 3.49212775528565,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0003817407524430359,
|
|
"loss": 5.4008,
|
|
"mean_token_accuracy": 0.19812109768390657,
|
|
"num_tokens": 68349835.0,
|
|
"step": 34935
|
|
},
|
|
{
|
|
"entropy": 5.852931642532349,
|
|
"epoch": 3.4926275803468787,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00038170933371304585,
|
|
"loss": 5.4855,
|
|
"mean_token_accuracy": 0.20321957021951675,
|
|
"num_tokens": 68360270.0,
|
|
"step": 34940
|
|
},
|
|
{
|
|
"entropy": 5.918484687805176,
|
|
"epoch": 3.4931274054081074,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0003816779122982765,
|
|
"loss": 5.3693,
|
|
"mean_token_accuracy": 0.20598713010549546,
|
|
"num_tokens": 68370268.0,
|
|
"step": 34945
|
|
},
|
|
{
|
|
"entropy": 5.877489948272705,
|
|
"epoch": 3.4936272304693357,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0003816464881995182,
|
|
"loss": 5.3902,
|
|
"mean_token_accuracy": 0.20376270413398742,
|
|
"num_tokens": 68379698.0,
|
|
"step": 34950
|
|
},
|
|
{
|
|
"entropy": 5.927291584014893,
|
|
"epoch": 3.4941270555305644,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0003816150614175617,
|
|
"loss": 5.4713,
|
|
"mean_token_accuracy": 0.1956939861178398,
|
|
"num_tokens": 68388825.0,
|
|
"step": 34955
|
|
},
|
|
{
|
|
"entropy": 6.002257490158081,
|
|
"epoch": 3.494626880591793,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0003815836319531978,
|
|
"loss": 5.5534,
|
|
"mean_token_accuracy": 0.18744712620973586,
|
|
"num_tokens": 68398553.0,
|
|
"step": 34960
|
|
},
|
|
{
|
|
"entropy": 5.8471901416778564,
|
|
"epoch": 3.4951267056530213,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000381552199807217,
|
|
"loss": 5.3474,
|
|
"mean_token_accuracy": 0.20605300068855287,
|
|
"num_tokens": 68407933.0,
|
|
"step": 34965
|
|
},
|
|
{
|
|
"entropy": 5.93325023651123,
|
|
"epoch": 3.49562653071425,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0003815207649804104,
|
|
"loss": 5.5,
|
|
"mean_token_accuracy": 0.19723999500274658,
|
|
"num_tokens": 68417224.0,
|
|
"step": 34970
|
|
},
|
|
{
|
|
"entropy": 5.886516284942627,
|
|
"epoch": 3.4961263557754787,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0003814893274735687,
|
|
"loss": 5.4445,
|
|
"mean_token_accuracy": 0.19884793013334273,
|
|
"num_tokens": 68426614.0,
|
|
"step": 34975
|
|
},
|
|
{
|
|
"entropy": 5.9105555534362795,
|
|
"epoch": 3.4966261808367074,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00038145788728748294,
|
|
"loss": 5.4306,
|
|
"mean_token_accuracy": 0.19616647958755493,
|
|
"num_tokens": 68435681.0,
|
|
"step": 34980
|
|
},
|
|
{
|
|
"entropy": 5.982066583633423,
|
|
"epoch": 3.4971260058979357,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0003814264444229441,
|
|
"loss": 5.6014,
|
|
"mean_token_accuracy": 0.18961697220802307,
|
|
"num_tokens": 68444900.0,
|
|
"step": 34985
|
|
},
|
|
{
|
|
"entropy": 5.94188175201416,
|
|
"epoch": 3.4976258309591644,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0003813949988807434,
|
|
"loss": 5.4697,
|
|
"mean_token_accuracy": 0.19484659284353256,
|
|
"num_tokens": 68453810.0,
|
|
"step": 34990
|
|
},
|
|
{
|
|
"entropy": 5.918289136886597,
|
|
"epoch": 3.498125656020393,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00038136355066167177,
|
|
"loss": 5.414,
|
|
"mean_token_accuracy": 0.19452234506607055,
|
|
"num_tokens": 68462850.0,
|
|
"step": 34995
|
|
},
|
|
{
|
|
"entropy": 6.022929954528808,
|
|
"epoch": 3.4986254810816213,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0003813320997665207,
|
|
"loss": 5.5927,
|
|
"mean_token_accuracy": 0.1916166678071022,
|
|
"num_tokens": 68472900.0,
|
|
"step": 35000
|
|
},
|
|
{
|
|
"entropy": 5.880709505081176,
|
|
"epoch": 3.49912530614285,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00038130064619608123,
|
|
"loss": 5.4194,
|
|
"mean_token_accuracy": 0.20469479113817216,
|
|
"num_tokens": 68482620.0,
|
|
"step": 35005
|
|
},
|
|
{
|
|
"entropy": 5.910068511962891,
|
|
"epoch": 3.4996251312040787,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000381269189951145,
|
|
"loss": 5.4267,
|
|
"mean_token_accuracy": 0.19728778004646302,
|
|
"num_tokens": 68492145.0,
|
|
"step": 35010
|
|
},
|
|
{
|
|
"entropy": 5.940859460830689,
|
|
"epoch": 3.5001249562653074,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0003812377310325032,
|
|
"loss": 5.4909,
|
|
"mean_token_accuracy": 0.19015180468559265,
|
|
"num_tokens": 68501193.0,
|
|
"step": 35015
|
|
},
|
|
{
|
|
"entropy": 5.9469461917877195,
|
|
"epoch": 3.5006247813265357,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0003812062694409474,
|
|
"loss": 5.4739,
|
|
"mean_token_accuracy": 0.1904076889157295,
|
|
"num_tokens": 68511525.0,
|
|
"step": 35020
|
|
},
|
|
{
|
|
"entropy": 5.955618762969971,
|
|
"epoch": 3.5011246063877643,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0003811748051772693,
|
|
"loss": 5.5063,
|
|
"mean_token_accuracy": 0.1973567560315132,
|
|
"num_tokens": 68521612.0,
|
|
"step": 35025
|
|
},
|
|
{
|
|
"entropy": 5.980499505996704,
|
|
"epoch": 3.5016244314489926,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00038114333824226034,
|
|
"loss": 5.5897,
|
|
"mean_token_accuracy": 0.18498645275831221,
|
|
"num_tokens": 68531986.0,
|
|
"step": 35030
|
|
},
|
|
{
|
|
"entropy": 5.955321645736694,
|
|
"epoch": 3.5021242565102213,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0003811118686367123,
|
|
"loss": 5.4949,
|
|
"mean_token_accuracy": 0.19885458797216415,
|
|
"num_tokens": 68541008.0,
|
|
"step": 35035
|
|
},
|
|
{
|
|
"entropy": 5.944861555099488,
|
|
"epoch": 3.50262408157145,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000381080396361417,
|
|
"loss": 5.5134,
|
|
"mean_token_accuracy": 0.19288308471441268,
|
|
"num_tokens": 68550805.0,
|
|
"step": 35040
|
|
},
|
|
{
|
|
"entropy": 5.958786201477051,
|
|
"epoch": 3.5031239066326787,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0003810489214171662,
|
|
"loss": 5.4817,
|
|
"mean_token_accuracy": 0.191903218626976,
|
|
"num_tokens": 68561428.0,
|
|
"step": 35045
|
|
},
|
|
{
|
|
"entropy": 5.895131683349609,
|
|
"epoch": 3.5036237316939074,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0003810174438047517,
|
|
"loss": 5.449,
|
|
"mean_token_accuracy": 0.1939161539077759,
|
|
"num_tokens": 68569624.0,
|
|
"step": 35050
|
|
},
|
|
{
|
|
"entropy": 5.943133449554443,
|
|
"epoch": 3.5041235567551356,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0003809859635249658,
|
|
"loss": 5.445,
|
|
"mean_token_accuracy": 0.19297327399253844,
|
|
"num_tokens": 68579464.0,
|
|
"step": 35055
|
|
},
|
|
{
|
|
"entropy": 5.945265626907348,
|
|
"epoch": 3.5046233818163643,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0003809544805786003,
|
|
"loss": 5.5109,
|
|
"mean_token_accuracy": 0.19311208426952362,
|
|
"num_tokens": 68589440.0,
|
|
"step": 35060
|
|
},
|
|
{
|
|
"entropy": 5.932695484161377,
|
|
"epoch": 3.5051232068775926,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0003809229949664473,
|
|
"loss": 5.4564,
|
|
"mean_token_accuracy": 0.19445010274648666,
|
|
"num_tokens": 68599267.0,
|
|
"step": 35065
|
|
},
|
|
{
|
|
"entropy": 5.861459112167358,
|
|
"epoch": 3.5056230319388213,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0003808915066892989,
|
|
"loss": 5.3902,
|
|
"mean_token_accuracy": 0.20352087020874024,
|
|
"num_tokens": 68608976.0,
|
|
"step": 35070
|
|
},
|
|
{
|
|
"entropy": 6.045478820800781,
|
|
"epoch": 3.50612285700005,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00038086001574794755,
|
|
"loss": 5.5621,
|
|
"mean_token_accuracy": 0.18702063858509063,
|
|
"num_tokens": 68618342.0,
|
|
"step": 35075
|
|
},
|
|
{
|
|
"entropy": 5.9127294540405275,
|
|
"epoch": 3.5066226820612787,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0003808285221431854,
|
|
"loss": 5.375,
|
|
"mean_token_accuracy": 0.20984205603599548,
|
|
"num_tokens": 68628519.0,
|
|
"step": 35080
|
|
},
|
|
{
|
|
"entropy": 5.949393033981323,
|
|
"epoch": 3.5071225071225074,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.00038079702587580486,
|
|
"loss": 5.5909,
|
|
"mean_token_accuracy": 0.18246482610702514,
|
|
"num_tokens": 68639408.0,
|
|
"step": 35085
|
|
},
|
|
{
|
|
"entropy": 5.936061382293701,
|
|
"epoch": 3.5076223321837356,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00038076552694659837,
|
|
"loss": 5.461,
|
|
"mean_token_accuracy": 0.19262837320566178,
|
|
"num_tokens": 68650484.0,
|
|
"step": 35090
|
|
},
|
|
{
|
|
"entropy": 6.024917459487915,
|
|
"epoch": 3.5081221572449643,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00038073402535635854,
|
|
"loss": 5.5202,
|
|
"mean_token_accuracy": 0.1890524834394455,
|
|
"num_tokens": 68660567.0,
|
|
"step": 35095
|
|
},
|
|
{
|
|
"entropy": 5.931787204742432,
|
|
"epoch": 3.5086219823061926,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00038070252110587776,
|
|
"loss": 5.4958,
|
|
"mean_token_accuracy": 0.19311690777540208,
|
|
"num_tokens": 68671340.0,
|
|
"step": 35100
|
|
},
|
|
{
|
|
"entropy": 5.9499194622039795,
|
|
"epoch": 3.5091218073674213,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00038067101419594874,
|
|
"loss": 5.4606,
|
|
"mean_token_accuracy": 0.19882899075746535,
|
|
"num_tokens": 68680866.0,
|
|
"step": 35105
|
|
},
|
|
{
|
|
"entropy": 5.709552001953125,
|
|
"epoch": 3.50962163242865,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00038063950462736425,
|
|
"loss": 5.2633,
|
|
"mean_token_accuracy": 0.2239456668496132,
|
|
"num_tokens": 68690682.0,
|
|
"step": 35110
|
|
},
|
|
{
|
|
"entropy": 5.972379064559936,
|
|
"epoch": 3.5101214574898787,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0003806079924009169,
|
|
"loss": 5.4795,
|
|
"mean_token_accuracy": 0.1931251749396324,
|
|
"num_tokens": 68700586.0,
|
|
"step": 35115
|
|
},
|
|
{
|
|
"entropy": 5.935898876190185,
|
|
"epoch": 3.510621282551107,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00038057647751739963,
|
|
"loss": 5.4487,
|
|
"mean_token_accuracy": 0.19791597425937651,
|
|
"num_tokens": 68710878.0,
|
|
"step": 35120
|
|
},
|
|
{
|
|
"entropy": 5.966893482208252,
|
|
"epoch": 3.5111211076123356,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0003805449599776055,
|
|
"loss": 5.5131,
|
|
"mean_token_accuracy": 0.1859495684504509,
|
|
"num_tokens": 68720611.0,
|
|
"step": 35125
|
|
},
|
|
{
|
|
"entropy": 5.889208221435547,
|
|
"epoch": 3.5116209326735643,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0003805134397823273,
|
|
"loss": 5.4108,
|
|
"mean_token_accuracy": 0.20279201716184617,
|
|
"num_tokens": 68730871.0,
|
|
"step": 35130
|
|
},
|
|
{
|
|
"entropy": 5.914928722381592,
|
|
"epoch": 3.5121207577347926,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.000380481916932358,
|
|
"loss": 5.3306,
|
|
"mean_token_accuracy": 0.20625526309013367,
|
|
"num_tokens": 68740981.0,
|
|
"step": 35135
|
|
},
|
|
{
|
|
"entropy": 5.925696277618409,
|
|
"epoch": 3.5126205827960213,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0003804503914284909,
|
|
"loss": 5.4243,
|
|
"mean_token_accuracy": 0.19959226101636887,
|
|
"num_tokens": 68751323.0,
|
|
"step": 35140
|
|
},
|
|
{
|
|
"entropy": 5.97372612953186,
|
|
"epoch": 3.51312040785725,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00038041886327151904,
|
|
"loss": 5.5478,
|
|
"mean_token_accuracy": 0.19223955422639846,
|
|
"num_tokens": 68761803.0,
|
|
"step": 35145
|
|
},
|
|
{
|
|
"entropy": 5.940538024902343,
|
|
"epoch": 3.5136202329184787,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00038038733246223574,
|
|
"loss": 5.4503,
|
|
"mean_token_accuracy": 0.19876730144023896,
|
|
"num_tokens": 68770455.0,
|
|
"step": 35150
|
|
},
|
|
{
|
|
"entropy": 5.915380859375,
|
|
"epoch": 3.514120057979707,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0003803557990014343,
|
|
"loss": 5.4973,
|
|
"mean_token_accuracy": 0.19640215188264848,
|
|
"num_tokens": 68779826.0,
|
|
"step": 35155
|
|
},
|
|
{
|
|
"entropy": 5.896182012557984,
|
|
"epoch": 3.5146198830409356,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000380324262889908,
|
|
"loss": 5.4612,
|
|
"mean_token_accuracy": 0.19508711099624634,
|
|
"num_tokens": 68789323.0,
|
|
"step": 35160
|
|
},
|
|
{
|
|
"entropy": 5.9238873481750485,
|
|
"epoch": 3.5151197081021643,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0003802927241284504,
|
|
"loss": 5.4098,
|
|
"mean_token_accuracy": 0.19972846657037735,
|
|
"num_tokens": 68799967.0,
|
|
"step": 35165
|
|
},
|
|
{
|
|
"entropy": 5.848488998413086,
|
|
"epoch": 3.5156195331633926,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0003802611827178549,
|
|
"loss": 5.3516,
|
|
"mean_token_accuracy": 0.2097217008471489,
|
|
"num_tokens": 68808997.0,
|
|
"step": 35170
|
|
},
|
|
{
|
|
"entropy": 5.921591758728027,
|
|
"epoch": 3.5161193582246213,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00038022963865891514,
|
|
"loss": 5.4545,
|
|
"mean_token_accuracy": 0.19701062738895417,
|
|
"num_tokens": 68818597.0,
|
|
"step": 35175
|
|
},
|
|
{
|
|
"entropy": 5.917372417449951,
|
|
"epoch": 3.51661918328585,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00038019809195242484,
|
|
"loss": 5.4025,
|
|
"mean_token_accuracy": 0.20065779983997345,
|
|
"num_tokens": 68827813.0,
|
|
"step": 35180
|
|
},
|
|
{
|
|
"entropy": 5.895416164398194,
|
|
"epoch": 3.5171190083470787,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0003801665425991775,
|
|
"loss": 5.4304,
|
|
"mean_token_accuracy": 0.19686079621315003,
|
|
"num_tokens": 68836359.0,
|
|
"step": 35185
|
|
},
|
|
{
|
|
"entropy": 5.877724456787109,
|
|
"epoch": 3.517618833408307,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0003801349905999671,
|
|
"loss": 5.4929,
|
|
"mean_token_accuracy": 0.19083866626024246,
|
|
"num_tokens": 68845063.0,
|
|
"step": 35190
|
|
},
|
|
{
|
|
"entropy": 5.967829370498658,
|
|
"epoch": 3.5181186584695356,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0003801034359555873,
|
|
"loss": 5.539,
|
|
"mean_token_accuracy": 0.18402726352214813,
|
|
"num_tokens": 68855262.0,
|
|
"step": 35195
|
|
},
|
|
{
|
|
"entropy": 5.981233310699463,
|
|
"epoch": 3.5186184835307643,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00038007187866683217,
|
|
"loss": 5.4552,
|
|
"mean_token_accuracy": 0.19568523913621902,
|
|
"num_tokens": 68864768.0,
|
|
"step": 35200
|
|
},
|
|
{
|
|
"entropy": 5.960919332504273,
|
|
"epoch": 3.5191183085919926,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0003800403187344955,
|
|
"loss": 5.4231,
|
|
"mean_token_accuracy": 0.19288297444581987,
|
|
"num_tokens": 68874950.0,
|
|
"step": 35205
|
|
},
|
|
{
|
|
"entropy": 5.888282442092896,
|
|
"epoch": 3.5196181336532213,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0003800087561593716,
|
|
"loss": 5.5019,
|
|
"mean_token_accuracy": 0.1963847756385803,
|
|
"num_tokens": 68884331.0,
|
|
"step": 35210
|
|
},
|
|
{
|
|
"entropy": 5.778667879104614,
|
|
"epoch": 3.52011795871445,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0003799771909422543,
|
|
"loss": 5.3236,
|
|
"mean_token_accuracy": 0.21552788764238356,
|
|
"num_tokens": 68894610.0,
|
|
"step": 35215
|
|
},
|
|
{
|
|
"entropy": 5.93616828918457,
|
|
"epoch": 3.5206177837756787,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.00037994562308393793,
|
|
"loss": 5.4839,
|
|
"mean_token_accuracy": 0.2001464232802391,
|
|
"num_tokens": 68904482.0,
|
|
"step": 35220
|
|
},
|
|
{
|
|
"entropy": 5.965753126144409,
|
|
"epoch": 3.521117608836907,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0003799140525852167,
|
|
"loss": 5.4341,
|
|
"mean_token_accuracy": 0.19561997205018997,
|
|
"num_tokens": 68914219.0,
|
|
"step": 35225
|
|
},
|
|
{
|
|
"entropy": 5.856391334533692,
|
|
"epoch": 3.5216174338981356,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0003798824794468849,
|
|
"loss": 5.3861,
|
|
"mean_token_accuracy": 0.19891568571329116,
|
|
"num_tokens": 68922980.0,
|
|
"step": 35230
|
|
},
|
|
{
|
|
"entropy": 5.893104124069214,
|
|
"epoch": 3.5221172589593643,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0003798509036697369,
|
|
"loss": 5.4424,
|
|
"mean_token_accuracy": 0.19706473648548126,
|
|
"num_tokens": 68933014.0,
|
|
"step": 35235
|
|
},
|
|
{
|
|
"entropy": 5.898953676223755,
|
|
"epoch": 3.5226170840205926,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00037981932525456714,
|
|
"loss": 5.381,
|
|
"mean_token_accuracy": 0.19627373218536376,
|
|
"num_tokens": 68942942.0,
|
|
"step": 35240
|
|
},
|
|
{
|
|
"entropy": 5.867590808868409,
|
|
"epoch": 3.5231169090818213,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0003797877442021701,
|
|
"loss": 5.3818,
|
|
"mean_token_accuracy": 0.19835375994443893,
|
|
"num_tokens": 68953575.0,
|
|
"step": 35245
|
|
},
|
|
{
|
|
"entropy": 5.896879577636719,
|
|
"epoch": 3.52361673414305,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0003797561605133404,
|
|
"loss": 5.4293,
|
|
"mean_token_accuracy": 0.19584892243146895,
|
|
"num_tokens": 68963549.0,
|
|
"step": 35250
|
|
},
|
|
{
|
|
"entropy": 5.95869026184082,
|
|
"epoch": 3.5241165592042787,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0003797245741888727,
|
|
"loss": 5.5322,
|
|
"mean_token_accuracy": 0.19193585962057114,
|
|
"num_tokens": 68973616.0,
|
|
"step": 35255
|
|
},
|
|
{
|
|
"entropy": 5.9598711967468265,
|
|
"epoch": 3.524616384265507,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00037969298522956156,
|
|
"loss": 5.4183,
|
|
"mean_token_accuracy": 0.19720132201910018,
|
|
"num_tokens": 68983786.0,
|
|
"step": 35260
|
|
},
|
|
{
|
|
"entropy": 5.889087677001953,
|
|
"epoch": 3.5251162093267356,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00037966139363620197,
|
|
"loss": 5.4169,
|
|
"mean_token_accuracy": 0.20763128399848937,
|
|
"num_tokens": 68993900.0,
|
|
"step": 35265
|
|
},
|
|
{
|
|
"entropy": 5.953653621673584,
|
|
"epoch": 3.5256160343879643,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0003796297994095886,
|
|
"loss": 5.5789,
|
|
"mean_token_accuracy": 0.18732599765062333,
|
|
"num_tokens": 69003062.0,
|
|
"step": 35270
|
|
},
|
|
{
|
|
"entropy": 5.74766058921814,
|
|
"epoch": 3.5261158594491926,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0003795982025505164,
|
|
"loss": 5.228,
|
|
"mean_token_accuracy": 0.21301816552877426,
|
|
"num_tokens": 69011466.0,
|
|
"step": 35275
|
|
},
|
|
{
|
|
"entropy": 5.884221935272217,
|
|
"epoch": 3.5266156845104213,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0003795666030597803,
|
|
"loss": 5.4517,
|
|
"mean_token_accuracy": 0.19780916273593901,
|
|
"num_tokens": 69020821.0,
|
|
"step": 35280
|
|
},
|
|
{
|
|
"entropy": 5.97890191078186,
|
|
"epoch": 3.52711550957165,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00037953500093817544,
|
|
"loss": 5.5157,
|
|
"mean_token_accuracy": 0.19508963972330093,
|
|
"num_tokens": 69031788.0,
|
|
"step": 35285
|
|
},
|
|
{
|
|
"entropy": 5.848756408691406,
|
|
"epoch": 3.5276153346328787,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00037950339618649675,
|
|
"loss": 5.3949,
|
|
"mean_token_accuracy": 0.2002318635582924,
|
|
"num_tokens": 69041520.0,
|
|
"step": 35290
|
|
},
|
|
{
|
|
"entropy": 5.936892366409301,
|
|
"epoch": 3.528115159694107,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0003794717888055397,
|
|
"loss": 5.5286,
|
|
"mean_token_accuracy": 0.19004183560609816,
|
|
"num_tokens": 69050781.0,
|
|
"step": 35295
|
|
},
|
|
{
|
|
"entropy": 5.930929231643677,
|
|
"epoch": 3.5286149847553356,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00037944017879609917,
|
|
"loss": 5.4844,
|
|
"mean_token_accuracy": 0.20004541724920272,
|
|
"num_tokens": 69062108.0,
|
|
"step": 35300
|
|
},
|
|
{
|
|
"entropy": 5.964897155761719,
|
|
"epoch": 3.5291148098165643,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0003794085661589707,
|
|
"loss": 5.4406,
|
|
"mean_token_accuracy": 0.20001233518123626,
|
|
"num_tokens": 69071695.0,
|
|
"step": 35305
|
|
},
|
|
{
|
|
"entropy": 6.04203691482544,
|
|
"epoch": 3.5296146348777926,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00037937695089494943,
|
|
"loss": 5.4671,
|
|
"mean_token_accuracy": 0.20207710415124894,
|
|
"num_tokens": 69081431.0,
|
|
"step": 35310
|
|
},
|
|
{
|
|
"entropy": 5.887417316436768,
|
|
"epoch": 3.5301144599390213,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000379345333004831,
|
|
"loss": 5.4445,
|
|
"mean_token_accuracy": 0.20670673847198487,
|
|
"num_tokens": 69091907.0,
|
|
"step": 35315
|
|
},
|
|
{
|
|
"entropy": 5.912931871414185,
|
|
"epoch": 3.53061428500025,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0003793137124894109,
|
|
"loss": 5.4712,
|
|
"mean_token_accuracy": 0.19610077291727065,
|
|
"num_tokens": 69100655.0,
|
|
"step": 35320
|
|
},
|
|
{
|
|
"entropy": 5.905416536331177,
|
|
"epoch": 3.5311141100614787,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00037928208934948467,
|
|
"loss": 5.3776,
|
|
"mean_token_accuracy": 0.2033736988902092,
|
|
"num_tokens": 69111253.0,
|
|
"step": 35325
|
|
},
|
|
{
|
|
"entropy": 5.8739691257476805,
|
|
"epoch": 3.531613935122707,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00037925046358584775,
|
|
"loss": 5.4205,
|
|
"mean_token_accuracy": 0.20003282129764557,
|
|
"num_tokens": 69121658.0,
|
|
"step": 35330
|
|
},
|
|
{
|
|
"entropy": 5.986206102371216,
|
|
"epoch": 3.5321137601839356,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0003792188351992961,
|
|
"loss": 5.5239,
|
|
"mean_token_accuracy": 0.19452777206897737,
|
|
"num_tokens": 69131572.0,
|
|
"step": 35335
|
|
},
|
|
{
|
|
"entropy": 5.910033702850342,
|
|
"epoch": 3.5326135852451643,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00037918720419062536,
|
|
"loss": 5.4096,
|
|
"mean_token_accuracy": 0.1940983548760414,
|
|
"num_tokens": 69143265.0,
|
|
"step": 35340
|
|
},
|
|
{
|
|
"entropy": 5.9412205696105955,
|
|
"epoch": 3.5331134103063926,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0003791555705606314,
|
|
"loss": 5.5073,
|
|
"mean_token_accuracy": 0.19522807747125626,
|
|
"num_tokens": 69152660.0,
|
|
"step": 35345
|
|
},
|
|
{
|
|
"entropy": 5.935263919830322,
|
|
"epoch": 3.5336132353676213,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00037912393431011005,
|
|
"loss": 5.4237,
|
|
"mean_token_accuracy": 0.2008708104491234,
|
|
"num_tokens": 69162118.0,
|
|
"step": 35350
|
|
},
|
|
{
|
|
"entropy": 6.000158786773682,
|
|
"epoch": 3.53411306042885,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0003790922954398573,
|
|
"loss": 5.5336,
|
|
"mean_token_accuracy": 0.1860753521323204,
|
|
"num_tokens": 69172394.0,
|
|
"step": 35355
|
|
},
|
|
{
|
|
"entropy": 5.838395500183106,
|
|
"epoch": 3.5346128854900787,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0003790606539506692,
|
|
"loss": 5.401,
|
|
"mean_token_accuracy": 0.20069787800312042,
|
|
"num_tokens": 69181656.0,
|
|
"step": 35360
|
|
},
|
|
{
|
|
"entropy": 5.833018589019775,
|
|
"epoch": 3.535112710551307,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00037902900984334176,
|
|
"loss": 5.3435,
|
|
"mean_token_accuracy": 0.2067536324262619,
|
|
"num_tokens": 69191309.0,
|
|
"step": 35365
|
|
},
|
|
{
|
|
"entropy": 5.958764219284058,
|
|
"epoch": 3.5356125356125356,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00037899736311867126,
|
|
"loss": 5.5133,
|
|
"mean_token_accuracy": 0.19125891029834746,
|
|
"num_tokens": 69200835.0,
|
|
"step": 35370
|
|
},
|
|
{
|
|
"entropy": 5.8893609046936035,
|
|
"epoch": 3.5361123606737643,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00037896571377745385,
|
|
"loss": 5.4137,
|
|
"mean_token_accuracy": 0.1974979966878891,
|
|
"num_tokens": 69210810.0,
|
|
"step": 35375
|
|
},
|
|
{
|
|
"entropy": 5.912593030929566,
|
|
"epoch": 3.5366121857349926,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0003789340618204859,
|
|
"loss": 5.484,
|
|
"mean_token_accuracy": 0.19745322167873383,
|
|
"num_tokens": 69220411.0,
|
|
"step": 35380
|
|
},
|
|
{
|
|
"entropy": 5.943247270584107,
|
|
"epoch": 3.5371120107962213,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0003789024072485637,
|
|
"loss": 5.531,
|
|
"mean_token_accuracy": 0.19174366742372512,
|
|
"num_tokens": 69230304.0,
|
|
"step": 35385
|
|
},
|
|
{
|
|
"entropy": 5.996662569046021,
|
|
"epoch": 3.53761183585745,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00037887075006248354,
|
|
"loss": 5.5109,
|
|
"mean_token_accuracy": 0.19603712856769562,
|
|
"num_tokens": 69241199.0,
|
|
"step": 35390
|
|
},
|
|
{
|
|
"entropy": 5.938900947570801,
|
|
"epoch": 3.5381116609186787,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00037883909026304206,
|
|
"loss": 5.5176,
|
|
"mean_token_accuracy": 0.19783590137958526,
|
|
"num_tokens": 69251869.0,
|
|
"step": 35395
|
|
},
|
|
{
|
|
"entropy": 5.889521646499634,
|
|
"epoch": 3.538611485979907,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00037880742785103584,
|
|
"loss": 5.3701,
|
|
"mean_token_accuracy": 0.20462715476751328,
|
|
"num_tokens": 69261940.0,
|
|
"step": 35400
|
|
},
|
|
{
|
|
"entropy": 5.8794910430908205,
|
|
"epoch": 3.5391113110411356,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00037877576282726146,
|
|
"loss": 5.4031,
|
|
"mean_token_accuracy": 0.2020760178565979,
|
|
"num_tokens": 69271471.0,
|
|
"step": 35405
|
|
},
|
|
{
|
|
"entropy": 5.880375385284424,
|
|
"epoch": 3.5396111361023643,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00037874409519251563,
|
|
"loss": 5.4448,
|
|
"mean_token_accuracy": 0.19983729720115662,
|
|
"num_tokens": 69280370.0,
|
|
"step": 35410
|
|
},
|
|
{
|
|
"entropy": 5.891604423522949,
|
|
"epoch": 3.5401109611635926,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000378712424947595,
|
|
"loss": 5.4371,
|
|
"mean_token_accuracy": 0.1991509571671486,
|
|
"num_tokens": 69290621.0,
|
|
"step": 35415
|
|
},
|
|
{
|
|
"entropy": 6.083489179611206,
|
|
"epoch": 3.5406107862248213,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00037868075209329644,
|
|
"loss": 5.5725,
|
|
"mean_token_accuracy": 0.19285314679145812,
|
|
"num_tokens": 69300613.0,
|
|
"step": 35420
|
|
},
|
|
{
|
|
"entropy": 5.909744787216186,
|
|
"epoch": 3.54111061128605,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00037864907663041686,
|
|
"loss": 5.398,
|
|
"mean_token_accuracy": 0.20316721349954606,
|
|
"num_tokens": 69310974.0,
|
|
"step": 35425
|
|
},
|
|
{
|
|
"entropy": 5.875445699691772,
|
|
"epoch": 3.5416104363472787,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00037861739855975316,
|
|
"loss": 5.4097,
|
|
"mean_token_accuracy": 0.2025715783238411,
|
|
"num_tokens": 69321155.0,
|
|
"step": 35430
|
|
},
|
|
{
|
|
"entropy": 5.8707489490509035,
|
|
"epoch": 3.542110261408507,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00037858571788210236,
|
|
"loss": 5.419,
|
|
"mean_token_accuracy": 0.19808844178915025,
|
|
"num_tokens": 69331280.0,
|
|
"step": 35435
|
|
},
|
|
{
|
|
"entropy": 5.937459468841553,
|
|
"epoch": 3.5426100864697356,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0003785540345982616,
|
|
"loss": 5.4658,
|
|
"mean_token_accuracy": 0.1961518794298172,
|
|
"num_tokens": 69341350.0,
|
|
"step": 35440
|
|
},
|
|
{
|
|
"entropy": 5.928362321853638,
|
|
"epoch": 3.5431099115309643,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.000378522348709028,
|
|
"loss": 5.4801,
|
|
"mean_token_accuracy": 0.19303417652845384,
|
|
"num_tokens": 69352133.0,
|
|
"step": 35445
|
|
},
|
|
{
|
|
"entropy": 5.921168088912964,
|
|
"epoch": 3.5436097365921926,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0003784906602151987,
|
|
"loss": 5.4984,
|
|
"mean_token_accuracy": 0.19138066470623016,
|
|
"num_tokens": 69362141.0,
|
|
"step": 35450
|
|
},
|
|
{
|
|
"entropy": 5.861552906036377,
|
|
"epoch": 3.5441095616534213,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.000378458969117571,
|
|
"loss": 5.4032,
|
|
"mean_token_accuracy": 0.20073224753141403,
|
|
"num_tokens": 69371149.0,
|
|
"step": 35455
|
|
},
|
|
{
|
|
"entropy": 5.854162693023682,
|
|
"epoch": 3.54460938671465,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00037842727541694226,
|
|
"loss": 5.342,
|
|
"mean_token_accuracy": 0.2119455710053444,
|
|
"num_tokens": 69381576.0,
|
|
"step": 35460
|
|
},
|
|
{
|
|
"entropy": 5.960726404190064,
|
|
"epoch": 3.5451092117758787,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0003783955791141099,
|
|
"loss": 5.5308,
|
|
"mean_token_accuracy": 0.19116899520158767,
|
|
"num_tokens": 69392917.0,
|
|
"step": 35465
|
|
},
|
|
{
|
|
"entropy": 5.951188325881958,
|
|
"epoch": 3.545609036837107,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0003783638802098714,
|
|
"loss": 5.4754,
|
|
"mean_token_accuracy": 0.19822998493909835,
|
|
"num_tokens": 69402203.0,
|
|
"step": 35470
|
|
},
|
|
{
|
|
"entropy": 5.939035177230835,
|
|
"epoch": 3.5461088618983356,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0003783321787050243,
|
|
"loss": 5.5419,
|
|
"mean_token_accuracy": 0.19078940600156785,
|
|
"num_tokens": 69412910.0,
|
|
"step": 35475
|
|
},
|
|
{
|
|
"entropy": 5.861520862579345,
|
|
"epoch": 3.546608686959564,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0003783004746003661,
|
|
"loss": 5.4393,
|
|
"mean_token_accuracy": 0.20328904837369918,
|
|
"num_tokens": 69422412.0,
|
|
"step": 35480
|
|
},
|
|
{
|
|
"entropy": 5.89364104270935,
|
|
"epoch": 3.5471085120207926,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0003782687678966946,
|
|
"loss": 5.4328,
|
|
"mean_token_accuracy": 0.19729434847831726,
|
|
"num_tokens": 69432123.0,
|
|
"step": 35485
|
|
},
|
|
{
|
|
"entropy": 5.904936838150024,
|
|
"epoch": 3.5476083370820213,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0003782370585948074,
|
|
"loss": 5.3638,
|
|
"mean_token_accuracy": 0.20761755257844924,
|
|
"num_tokens": 69440844.0,
|
|
"step": 35490
|
|
},
|
|
{
|
|
"entropy": 5.861453247070313,
|
|
"epoch": 3.54810816214325,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0003782053466955024,
|
|
"loss": 5.4425,
|
|
"mean_token_accuracy": 0.19728114157915116,
|
|
"num_tokens": 69451466.0,
|
|
"step": 35495
|
|
},
|
|
{
|
|
"entropy": 5.911453533172607,
|
|
"epoch": 3.5486079872044787,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00037817363219957745,
|
|
"loss": 5.5706,
|
|
"mean_token_accuracy": 0.18543479591608047,
|
|
"num_tokens": 69461322.0,
|
|
"step": 35500
|
|
},
|
|
{
|
|
"entropy": 5.953326320648193,
|
|
"epoch": 3.549107812265707,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00037814191510783047,
|
|
"loss": 5.3906,
|
|
"mean_token_accuracy": 0.20866564363241197,
|
|
"num_tokens": 69469875.0,
|
|
"step": 35505
|
|
},
|
|
{
|
|
"entropy": 5.944395256042481,
|
|
"epoch": 3.5496076373269356,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0003781101954210594,
|
|
"loss": 5.4604,
|
|
"mean_token_accuracy": 0.19990016967058183,
|
|
"num_tokens": 69479774.0,
|
|
"step": 35510
|
|
},
|
|
{
|
|
"entropy": 5.903732013702393,
|
|
"epoch": 3.550107462388164,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00037807847314006246,
|
|
"loss": 5.3886,
|
|
"mean_token_accuracy": 0.20931484401226044,
|
|
"num_tokens": 69490259.0,
|
|
"step": 35515
|
|
},
|
|
{
|
|
"entropy": 5.891544818878174,
|
|
"epoch": 3.5506072874493926,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0003780467482656375,
|
|
"loss": 5.4567,
|
|
"mean_token_accuracy": 0.1967145621776581,
|
|
"num_tokens": 69501050.0,
|
|
"step": 35520
|
|
},
|
|
{
|
|
"entropy": 5.906019163131714,
|
|
"epoch": 3.5511071125106213,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00037801502079858295,
|
|
"loss": 5.5138,
|
|
"mean_token_accuracy": 0.19211415201425552,
|
|
"num_tokens": 69511475.0,
|
|
"step": 35525
|
|
},
|
|
{
|
|
"entropy": 5.779649353027343,
|
|
"epoch": 3.55160693757185,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000377983290739697,
|
|
"loss": 5.223,
|
|
"mean_token_accuracy": 0.220878067612648,
|
|
"num_tokens": 69521105.0,
|
|
"step": 35530
|
|
},
|
|
{
|
|
"entropy": 5.950412940979004,
|
|
"epoch": 3.5521067626330787,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0003779515580897779,
|
|
"loss": 5.5434,
|
|
"mean_token_accuracy": 0.19219585806131362,
|
|
"num_tokens": 69530616.0,
|
|
"step": 35535
|
|
},
|
|
{
|
|
"entropy": 5.842019557952881,
|
|
"epoch": 3.552606587694307,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00037791982284962416,
|
|
"loss": 5.3829,
|
|
"mean_token_accuracy": 0.20671510249376296,
|
|
"num_tokens": 69540349.0,
|
|
"step": 35540
|
|
},
|
|
{
|
|
"entropy": 5.958058786392212,
|
|
"epoch": 3.5531064127555356,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00037788808502003414,
|
|
"loss": 5.5148,
|
|
"mean_token_accuracy": 0.18614504486322403,
|
|
"num_tokens": 69550134.0,
|
|
"step": 35545
|
|
},
|
|
{
|
|
"entropy": 5.951762104034424,
|
|
"epoch": 3.553606237816764,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00037785634460180633,
|
|
"loss": 5.4819,
|
|
"mean_token_accuracy": 0.1916712775826454,
|
|
"num_tokens": 69560335.0,
|
|
"step": 35550
|
|
},
|
|
{
|
|
"entropy": 5.895352506637574,
|
|
"epoch": 3.5541060628779926,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00037782460159573944,
|
|
"loss": 5.429,
|
|
"mean_token_accuracy": 0.19271095395088195,
|
|
"num_tokens": 69569828.0,
|
|
"step": 35555
|
|
},
|
|
{
|
|
"entropy": 5.817148637771607,
|
|
"epoch": 3.5546058879392213,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00037779285600263195,
|
|
"loss": 5.3354,
|
|
"mean_token_accuracy": 0.214264178276062,
|
|
"num_tokens": 69579840.0,
|
|
"step": 35560
|
|
},
|
|
{
|
|
"entropy": 6.01115198135376,
|
|
"epoch": 3.55510571300045,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0003777611078232827,
|
|
"loss": 5.5739,
|
|
"mean_token_accuracy": 0.19003626555204392,
|
|
"num_tokens": 69589513.0,
|
|
"step": 35565
|
|
},
|
|
{
|
|
"entropy": 5.931106042861939,
|
|
"epoch": 3.5556055380616787,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00037772935705849046,
|
|
"loss": 5.4412,
|
|
"mean_token_accuracy": 0.19812317490577697,
|
|
"num_tokens": 69598505.0,
|
|
"step": 35570
|
|
},
|
|
{
|
|
"entropy": 5.826751613616944,
|
|
"epoch": 3.556105363122907,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0003776976037090539,
|
|
"loss": 5.3845,
|
|
"mean_token_accuracy": 0.20567671954631805,
|
|
"num_tokens": 69608955.0,
|
|
"step": 35575
|
|
},
|
|
{
|
|
"entropy": 5.88532247543335,
|
|
"epoch": 3.5566051881841356,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00037766584777577223,
|
|
"loss": 5.3532,
|
|
"mean_token_accuracy": 0.20837970227003097,
|
|
"num_tokens": 69618130.0,
|
|
"step": 35580
|
|
},
|
|
{
|
|
"entropy": 5.919984626770019,
|
|
"epoch": 3.557105013245364,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0003776340892594441,
|
|
"loss": 5.438,
|
|
"mean_token_accuracy": 0.19644505232572557,
|
|
"num_tokens": 69627605.0,
|
|
"step": 35585
|
|
},
|
|
{
|
|
"entropy": 5.896532440185547,
|
|
"epoch": 3.5576048383065926,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00037760232816086875,
|
|
"loss": 5.4181,
|
|
"mean_token_accuracy": 0.19696574360132219,
|
|
"num_tokens": 69637631.0,
|
|
"step": 35590
|
|
},
|
|
{
|
|
"entropy": 5.900136089324951,
|
|
"epoch": 3.5581046633678213,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0003775705644808452,
|
|
"loss": 5.5404,
|
|
"mean_token_accuracy": 0.1901030421257019,
|
|
"num_tokens": 69647568.0,
|
|
"step": 35595
|
|
},
|
|
{
|
|
"entropy": 5.951075029373169,
|
|
"epoch": 3.55860448842905,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00037753879822017265,
|
|
"loss": 5.4792,
|
|
"mean_token_accuracy": 0.1986595571041107,
|
|
"num_tokens": 69656768.0,
|
|
"step": 35600
|
|
},
|
|
{
|
|
"entropy": 5.9733078956604,
|
|
"epoch": 3.5591043134902787,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0003775070293796504,
|
|
"loss": 5.5057,
|
|
"mean_token_accuracy": 0.1892249643802643,
|
|
"num_tokens": 69665758.0,
|
|
"step": 35605
|
|
},
|
|
{
|
|
"entropy": 5.963682794570923,
|
|
"epoch": 3.559604138551507,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0003774752579600776,
|
|
"loss": 5.5631,
|
|
"mean_token_accuracy": 0.19127997756004333,
|
|
"num_tokens": 69675281.0,
|
|
"step": 35610
|
|
},
|
|
{
|
|
"entropy": 6.031425905227661,
|
|
"epoch": 3.5601039636127356,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0003774434839622537,
|
|
"loss": 5.4677,
|
|
"mean_token_accuracy": 0.18606849312782286,
|
|
"num_tokens": 69685354.0,
|
|
"step": 35615
|
|
},
|
|
{
|
|
"entropy": 6.018463897705078,
|
|
"epoch": 3.560603788673964,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00037741170738697806,
|
|
"loss": 5.5496,
|
|
"mean_token_accuracy": 0.18529616445302963,
|
|
"num_tokens": 69695516.0,
|
|
"step": 35620
|
|
},
|
|
{
|
|
"entropy": 5.952667474746704,
|
|
"epoch": 3.5611036137351926,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0003773799282350503,
|
|
"loss": 5.4671,
|
|
"mean_token_accuracy": 0.19368596971035004,
|
|
"num_tokens": 69704096.0,
|
|
"step": 35625
|
|
},
|
|
{
|
|
"entropy": 5.921174192428589,
|
|
"epoch": 3.5616034387964213,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0003773481465072698,
|
|
"loss": 5.4378,
|
|
"mean_token_accuracy": 0.19971949607133865,
|
|
"num_tokens": 69714175.0,
|
|
"step": 35630
|
|
},
|
|
{
|
|
"entropy": 5.803120565414429,
|
|
"epoch": 3.56210326385765,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00037731636220443625,
|
|
"loss": 5.3892,
|
|
"mean_token_accuracy": 0.20510978400707244,
|
|
"num_tokens": 69723481.0,
|
|
"step": 35635
|
|
},
|
|
{
|
|
"entropy": 5.895900058746338,
|
|
"epoch": 3.5626030889188787,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00037728457532734943,
|
|
"loss": 5.4118,
|
|
"mean_token_accuracy": 0.1969359815120697,
|
|
"num_tokens": 69733976.0,
|
|
"step": 35640
|
|
},
|
|
{
|
|
"entropy": 5.934411334991455,
|
|
"epoch": 3.563102913980107,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000377252785876809,
|
|
"loss": 5.4452,
|
|
"mean_token_accuracy": 0.1996287077665329,
|
|
"num_tokens": 69744111.0,
|
|
"step": 35645
|
|
},
|
|
{
|
|
"entropy": 5.950687980651855,
|
|
"epoch": 3.5636027390413356,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00037722099385361475,
|
|
"loss": 5.475,
|
|
"mean_token_accuracy": 0.19220500886440278,
|
|
"num_tokens": 69753629.0,
|
|
"step": 35650
|
|
},
|
|
{
|
|
"entropy": 5.891046047210693,
|
|
"epoch": 3.564102564102564,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0003771891992585667,
|
|
"loss": 5.4321,
|
|
"mean_token_accuracy": 0.20098870545625686,
|
|
"num_tokens": 69762406.0,
|
|
"step": 35655
|
|
},
|
|
{
|
|
"entropy": 5.883587789535523,
|
|
"epoch": 3.5646023891637926,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0003771574020924646,
|
|
"loss": 5.3637,
|
|
"mean_token_accuracy": 0.20255242735147477,
|
|
"num_tokens": 69771976.0,
|
|
"step": 35660
|
|
},
|
|
{
|
|
"entropy": 5.902087020874023,
|
|
"epoch": 3.5651022142250213,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0003771256023561086,
|
|
"loss": 5.4329,
|
|
"mean_token_accuracy": 0.19929988384246827,
|
|
"num_tokens": 69781779.0,
|
|
"step": 35665
|
|
},
|
|
{
|
|
"entropy": 5.893157577514648,
|
|
"epoch": 3.56560203928625,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0003770938000502987,
|
|
"loss": 5.4152,
|
|
"mean_token_accuracy": 0.20315370559692383,
|
|
"num_tokens": 69792254.0,
|
|
"step": 35670
|
|
},
|
|
{
|
|
"entropy": 5.926397705078125,
|
|
"epoch": 3.5661018643474782,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.000377061995175835,
|
|
"loss": 5.4557,
|
|
"mean_token_accuracy": 0.19549063742160797,
|
|
"num_tokens": 69801394.0,
|
|
"step": 35675
|
|
},
|
|
{
|
|
"entropy": 5.939139986038208,
|
|
"epoch": 3.566601689408707,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0003770301877335178,
|
|
"loss": 5.4737,
|
|
"mean_token_accuracy": 0.19360555410385133,
|
|
"num_tokens": 69811273.0,
|
|
"step": 35680
|
|
},
|
|
{
|
|
"entropy": 5.917264461517334,
|
|
"epoch": 3.5671015144699356,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00037699837772414734,
|
|
"loss": 5.3887,
|
|
"mean_token_accuracy": 0.2095478281378746,
|
|
"num_tokens": 69820241.0,
|
|
"step": 35685
|
|
},
|
|
{
|
|
"entropy": 5.882426166534424,
|
|
"epoch": 3.567601339531164,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000376966565148524,
|
|
"loss": 5.4275,
|
|
"mean_token_accuracy": 0.2094918206334114,
|
|
"num_tokens": 69829650.0,
|
|
"step": 35690
|
|
},
|
|
{
|
|
"entropy": 5.99082465171814,
|
|
"epoch": 3.5681011645923926,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00037693475000744807,
|
|
"loss": 5.5785,
|
|
"mean_token_accuracy": 0.18279659152030944,
|
|
"num_tokens": 69839934.0,
|
|
"step": 35695
|
|
},
|
|
{
|
|
"entropy": 5.976824378967285,
|
|
"epoch": 3.5686009896536213,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00037690293230172007,
|
|
"loss": 5.5421,
|
|
"mean_token_accuracy": 0.1904687613248825,
|
|
"num_tokens": 69849406.0,
|
|
"step": 35700
|
|
},
|
|
{
|
|
"entropy": 5.921488094329834,
|
|
"epoch": 3.56910081471485,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00037687111203214054,
|
|
"loss": 5.4226,
|
|
"mean_token_accuracy": 0.1970747858285904,
|
|
"num_tokens": 69858546.0,
|
|
"step": 35705
|
|
},
|
|
{
|
|
"entropy": 5.952044248580933,
|
|
"epoch": 3.569600639776078,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00037683928919951006,
|
|
"loss": 5.4268,
|
|
"mean_token_accuracy": 0.19628771841526033,
|
|
"num_tokens": 69868752.0,
|
|
"step": 35710
|
|
},
|
|
{
|
|
"entropy": 5.848211288452148,
|
|
"epoch": 3.570100464837307,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00037680746380462914,
|
|
"loss": 5.3811,
|
|
"mean_token_accuracy": 0.19991766959428786,
|
|
"num_tokens": 69878601.0,
|
|
"step": 35715
|
|
},
|
|
{
|
|
"entropy": 5.947481870651245,
|
|
"epoch": 3.5706002898985356,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0003767756358482987,
|
|
"loss": 5.4418,
|
|
"mean_token_accuracy": 0.196417136490345,
|
|
"num_tokens": 69888976.0,
|
|
"step": 35720
|
|
},
|
|
{
|
|
"entropy": 6.021180248260498,
|
|
"epoch": 3.571100114959764,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0003767438053313195,
|
|
"loss": 5.5342,
|
|
"mean_token_accuracy": 0.18422460854053496,
|
|
"num_tokens": 69898532.0,
|
|
"step": 35725
|
|
},
|
|
{
|
|
"entropy": 5.843384695053101,
|
|
"epoch": 3.5715999400209926,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0003767119722544923,
|
|
"loss": 5.4691,
|
|
"mean_token_accuracy": 0.20301568359136582,
|
|
"num_tokens": 69907260.0,
|
|
"step": 35730
|
|
},
|
|
{
|
|
"entropy": 5.9047047138214115,
|
|
"epoch": 3.5720997650822213,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0003766801366186181,
|
|
"loss": 5.516,
|
|
"mean_token_accuracy": 0.1911611005663872,
|
|
"num_tokens": 69917347.0,
|
|
"step": 35735
|
|
},
|
|
{
|
|
"entropy": 5.917845106124878,
|
|
"epoch": 3.57259959014345,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0003766482984244978,
|
|
"loss": 5.4166,
|
|
"mean_token_accuracy": 0.19968331456184388,
|
|
"num_tokens": 69926900.0,
|
|
"step": 35740
|
|
},
|
|
{
|
|
"entropy": 5.996547842025757,
|
|
"epoch": 3.573099415204678,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0003766164576729324,
|
|
"loss": 5.4791,
|
|
"mean_token_accuracy": 0.1965376615524292,
|
|
"num_tokens": 69935838.0,
|
|
"step": 35745
|
|
},
|
|
{
|
|
"entropy": 5.8525162696838375,
|
|
"epoch": 3.573599240265907,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00037658461436472306,
|
|
"loss": 5.3202,
|
|
"mean_token_accuracy": 0.20802567899227142,
|
|
"num_tokens": 69946310.0,
|
|
"step": 35750
|
|
},
|
|
{
|
|
"entropy": 5.845802164077758,
|
|
"epoch": 3.5740990653271356,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.00037655276850067103,
|
|
"loss": 5.289,
|
|
"mean_token_accuracy": 0.20340359807014466,
|
|
"num_tokens": 69955179.0,
|
|
"step": 35755
|
|
},
|
|
{
|
|
"entropy": 5.97095685005188,
|
|
"epoch": 3.574598890388364,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0003765209200815776,
|
|
"loss": 5.5048,
|
|
"mean_token_accuracy": 0.18975666016340256,
|
|
"num_tokens": 69965408.0,
|
|
"step": 35760
|
|
},
|
|
{
|
|
"entropy": 5.857628393173218,
|
|
"epoch": 3.5750987154495926,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00037648906910824374,
|
|
"loss": 5.3324,
|
|
"mean_token_accuracy": 0.2145179957151413,
|
|
"num_tokens": 69973751.0,
|
|
"step": 35765
|
|
},
|
|
{
|
|
"entropy": 5.8906388759613035,
|
|
"epoch": 3.5755985405108213,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00037645721558147104,
|
|
"loss": 5.4967,
|
|
"mean_token_accuracy": 0.19111180156469346,
|
|
"num_tokens": 69983857.0,
|
|
"step": 35770
|
|
},
|
|
{
|
|
"entropy": 5.8686192512512205,
|
|
"epoch": 3.57609836557205,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000376425359502061,
|
|
"loss": 5.3476,
|
|
"mean_token_accuracy": 0.2037769615650177,
|
|
"num_tokens": 69993000.0,
|
|
"step": 35775
|
|
},
|
|
{
|
|
"entropy": 5.946612739562989,
|
|
"epoch": 3.576598190633278,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00037639350087081497,
|
|
"loss": 5.4333,
|
|
"mean_token_accuracy": 0.1931193381547928,
|
|
"num_tokens": 70003009.0,
|
|
"step": 35780
|
|
},
|
|
{
|
|
"entropy": 5.945284700393676,
|
|
"epoch": 3.577098015694507,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00037636163968853453,
|
|
"loss": 5.4391,
|
|
"mean_token_accuracy": 0.19764904975891112,
|
|
"num_tokens": 70012246.0,
|
|
"step": 35785
|
|
},
|
|
{
|
|
"entropy": 5.877476549148559,
|
|
"epoch": 3.5775978407557356,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0003763297759560213,
|
|
"loss": 5.3919,
|
|
"mean_token_accuracy": 0.19046708941459656,
|
|
"num_tokens": 70022822.0,
|
|
"step": 35790
|
|
},
|
|
{
|
|
"entropy": 5.988349151611328,
|
|
"epoch": 3.578097665816964,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0003762979096740771,
|
|
"loss": 5.5666,
|
|
"mean_token_accuracy": 0.19150039404630662,
|
|
"num_tokens": 70032852.0,
|
|
"step": 35795
|
|
},
|
|
{
|
|
"entropy": 5.936214303970337,
|
|
"epoch": 3.5785974908781926,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0003762660408435035,
|
|
"loss": 5.4291,
|
|
"mean_token_accuracy": 0.19341126829385757,
|
|
"num_tokens": 70043367.0,
|
|
"step": 35800
|
|
},
|
|
{
|
|
"entropy": 5.939048624038696,
|
|
"epoch": 3.5790973159394213,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0003762341694651023,
|
|
"loss": 5.4184,
|
|
"mean_token_accuracy": 0.20522000640630722,
|
|
"num_tokens": 70052935.0,
|
|
"step": 35805
|
|
},
|
|
{
|
|
"entropy": 5.904234933853149,
|
|
"epoch": 3.57959714100065,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00037620229553967543,
|
|
"loss": 5.4709,
|
|
"mean_token_accuracy": 0.19362186789512634,
|
|
"num_tokens": 70064361.0,
|
|
"step": 35810
|
|
},
|
|
{
|
|
"entropy": 5.970966482162476,
|
|
"epoch": 3.580096966061878,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00037617041906802496,
|
|
"loss": 5.4696,
|
|
"mean_token_accuracy": 0.19248463064432145,
|
|
"num_tokens": 70074183.0,
|
|
"step": 35815
|
|
},
|
|
{
|
|
"entropy": 5.905843782424927,
|
|
"epoch": 3.580596791123107,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0003761385400509527,
|
|
"loss": 5.4115,
|
|
"mean_token_accuracy": 0.19861292243003845,
|
|
"num_tokens": 70083929.0,
|
|
"step": 35820
|
|
},
|
|
{
|
|
"entropy": 5.9304506301879885,
|
|
"epoch": 3.5810966161843356,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00037610665848926086,
|
|
"loss": 5.4483,
|
|
"mean_token_accuracy": 0.19848117381334304,
|
|
"num_tokens": 70094956.0,
|
|
"step": 35825
|
|
},
|
|
{
|
|
"entropy": 5.963109254837036,
|
|
"epoch": 3.581596441245564,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0003760747743837515,
|
|
"loss": 5.5258,
|
|
"mean_token_accuracy": 0.19458891302347184,
|
|
"num_tokens": 70103814.0,
|
|
"step": 35830
|
|
},
|
|
{
|
|
"entropy": 5.898111200332641,
|
|
"epoch": 3.5820962663067926,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00037604288773522673,
|
|
"loss": 5.3451,
|
|
"mean_token_accuracy": 0.21134549677371978,
|
|
"num_tokens": 70113715.0,
|
|
"step": 35835
|
|
},
|
|
{
|
|
"entropy": 5.876807165145874,
|
|
"epoch": 3.5825960913680213,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00037601099854448893,
|
|
"loss": 5.4106,
|
|
"mean_token_accuracy": 0.2005839914083481,
|
|
"num_tokens": 70123034.0,
|
|
"step": 35840
|
|
},
|
|
{
|
|
"entropy": 5.982635736465454,
|
|
"epoch": 3.58309591642925,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00037597910681234047,
|
|
"loss": 5.4793,
|
|
"mean_token_accuracy": 0.19531694501638414,
|
|
"num_tokens": 70132592.0,
|
|
"step": 35845
|
|
},
|
|
{
|
|
"entropy": 5.962263774871826,
|
|
"epoch": 3.583595741490478,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0003759472125395837,
|
|
"loss": 5.5102,
|
|
"mean_token_accuracy": 0.19570136815309525,
|
|
"num_tokens": 70142288.0,
|
|
"step": 35850
|
|
},
|
|
{
|
|
"entropy": 5.894360685348511,
|
|
"epoch": 3.584095566551707,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0003759153157270209,
|
|
"loss": 5.47,
|
|
"mean_token_accuracy": 0.19414278119802475,
|
|
"num_tokens": 70152063.0,
|
|
"step": 35855
|
|
},
|
|
{
|
|
"entropy": 5.927735185623169,
|
|
"epoch": 3.5845953916129356,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00037588341637545487,
|
|
"loss": 5.4487,
|
|
"mean_token_accuracy": 0.19729680567979813,
|
|
"num_tokens": 70162153.0,
|
|
"step": 35860
|
|
},
|
|
{
|
|
"entropy": 5.910901689529419,
|
|
"epoch": 3.585095216674164,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00037585151448568796,
|
|
"loss": 5.4051,
|
|
"mean_token_accuracy": 0.19714695811271668,
|
|
"num_tokens": 70171615.0,
|
|
"step": 35865
|
|
},
|
|
{
|
|
"entropy": 5.910897731781006,
|
|
"epoch": 3.5855950417353926,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00037581961005852296,
|
|
"loss": 5.4349,
|
|
"mean_token_accuracy": 0.20455242097377777,
|
|
"num_tokens": 70181056.0,
|
|
"step": 35870
|
|
},
|
|
{
|
|
"entropy": 5.936184215545654,
|
|
"epoch": 3.5860948667966213,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0003757877030947624,
|
|
"loss": 5.4942,
|
|
"mean_token_accuracy": 0.18987231254577636,
|
|
"num_tokens": 70191336.0,
|
|
"step": 35875
|
|
},
|
|
{
|
|
"entropy": 5.9844889640808105,
|
|
"epoch": 3.58659469185785,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0003757557935952092,
|
|
"loss": 5.5594,
|
|
"mean_token_accuracy": 0.1782221481204033,
|
|
"num_tokens": 70200935.0,
|
|
"step": 35880
|
|
},
|
|
{
|
|
"entropy": 5.990892171859741,
|
|
"epoch": 3.587094516919078,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00037572388156066627,
|
|
"loss": 5.4634,
|
|
"mean_token_accuracy": 0.193561652302742,
|
|
"num_tokens": 70210111.0,
|
|
"step": 35885
|
|
},
|
|
{
|
|
"entropy": 5.831349515914917,
|
|
"epoch": 3.587594341980307,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00037569196699193633,
|
|
"loss": 5.3126,
|
|
"mean_token_accuracy": 0.20934545397758483,
|
|
"num_tokens": 70219946.0,
|
|
"step": 35890
|
|
},
|
|
{
|
|
"entropy": 5.867762708663941,
|
|
"epoch": 3.5880941670415356,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00037566004988982235,
|
|
"loss": 5.4967,
|
|
"mean_token_accuracy": 0.19158076196908952,
|
|
"num_tokens": 70230145.0,
|
|
"step": 35895
|
|
},
|
|
{
|
|
"entropy": 6.0027077198028564,
|
|
"epoch": 3.588593992102764,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0003756281302551274,
|
|
"loss": 5.5268,
|
|
"mean_token_accuracy": 0.1925497531890869,
|
|
"num_tokens": 70239080.0,
|
|
"step": 35900
|
|
},
|
|
{
|
|
"entropy": 5.963592290878296,
|
|
"epoch": 3.5890938171639926,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00037559620808865467,
|
|
"loss": 5.4657,
|
|
"mean_token_accuracy": 0.19975230246782302,
|
|
"num_tokens": 70248936.0,
|
|
"step": 35905
|
|
},
|
|
{
|
|
"entropy": 5.85003514289856,
|
|
"epoch": 3.5895936422252213,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00037556428339120725,
|
|
"loss": 5.3721,
|
|
"mean_token_accuracy": 0.21483764201402664,
|
|
"num_tokens": 70258355.0,
|
|
"step": 35910
|
|
},
|
|
{
|
|
"entropy": 5.892858266830444,
|
|
"epoch": 3.59009346728645,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00037553235616358835,
|
|
"loss": 5.4473,
|
|
"mean_token_accuracy": 0.20010334402322769,
|
|
"num_tokens": 70267787.0,
|
|
"step": 35915
|
|
},
|
|
{
|
|
"entropy": 6.040414762496948,
|
|
"epoch": 3.590593292347678,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00037550042640660113,
|
|
"loss": 5.6041,
|
|
"mean_token_accuracy": 0.18825111985206605,
|
|
"num_tokens": 70278695.0,
|
|
"step": 35920
|
|
},
|
|
{
|
|
"entropy": 5.903332233428955,
|
|
"epoch": 3.591093117408907,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0003754684941210491,
|
|
"loss": 5.3345,
|
|
"mean_token_accuracy": 0.21534382551908493,
|
|
"num_tokens": 70288033.0,
|
|
"step": 35925
|
|
},
|
|
{
|
|
"entropy": 5.925547313690186,
|
|
"epoch": 3.5915929424701356,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00037543655930773564,
|
|
"loss": 5.5157,
|
|
"mean_token_accuracy": 0.19281494468450547,
|
|
"num_tokens": 70297431.0,
|
|
"step": 35930
|
|
},
|
|
{
|
|
"entropy": 5.938385534286499,
|
|
"epoch": 3.592092767531364,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0003754046219674641,
|
|
"loss": 5.4957,
|
|
"mean_token_accuracy": 0.1887412801384926,
|
|
"num_tokens": 70307693.0,
|
|
"step": 35935
|
|
},
|
|
{
|
|
"entropy": 5.944396829605102,
|
|
"epoch": 3.5925925925925926,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00037537268210103826,
|
|
"loss": 5.4751,
|
|
"mean_token_accuracy": 0.1983519971370697,
|
|
"num_tokens": 70317121.0,
|
|
"step": 35940
|
|
},
|
|
{
|
|
"entropy": 5.917228412628174,
|
|
"epoch": 3.5930924176538213,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0003753407397092614,
|
|
"loss": 5.4111,
|
|
"mean_token_accuracy": 0.19816168695688247,
|
|
"num_tokens": 70326564.0,
|
|
"step": 35945
|
|
},
|
|
{
|
|
"entropy": 5.930854034423828,
|
|
"epoch": 3.59359224271505,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0003753087947929375,
|
|
"loss": 5.526,
|
|
"mean_token_accuracy": 0.1879077285528183,
|
|
"num_tokens": 70337668.0,
|
|
"step": 35950
|
|
},
|
|
{
|
|
"entropy": 5.943690490722656,
|
|
"epoch": 3.594092067776278,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00037527684735287007,
|
|
"loss": 5.496,
|
|
"mean_token_accuracy": 0.1916789725422859,
|
|
"num_tokens": 70347096.0,
|
|
"step": 35955
|
|
},
|
|
{
|
|
"entropy": 5.901597213745117,
|
|
"epoch": 3.594591892837507,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0003752448973898629,
|
|
"loss": 5.3645,
|
|
"mean_token_accuracy": 0.19971867203712462,
|
|
"num_tokens": 70356814.0,
|
|
"step": 35960
|
|
},
|
|
{
|
|
"entropy": 5.841806507110595,
|
|
"epoch": 3.5950917178987356,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00037521294490472,
|
|
"loss": 5.3805,
|
|
"mean_token_accuracy": 0.20762289315462112,
|
|
"num_tokens": 70365796.0,
|
|
"step": 35965
|
|
},
|
|
{
|
|
"entropy": 5.958086204528809,
|
|
"epoch": 3.595591542959964,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0003751809898982451,
|
|
"loss": 5.488,
|
|
"mean_token_accuracy": 0.19572093784809114,
|
|
"num_tokens": 70376411.0,
|
|
"step": 35970
|
|
},
|
|
{
|
|
"entropy": 5.8636211395263675,
|
|
"epoch": 3.5960913680211926,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0003751490323712424,
|
|
"loss": 5.3438,
|
|
"mean_token_accuracy": 0.20484855026006699,
|
|
"num_tokens": 70385758.0,
|
|
"step": 35975
|
|
},
|
|
{
|
|
"entropy": 5.893889665603638,
|
|
"epoch": 3.5965911930824213,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0003751170723245157,
|
|
"loss": 5.3857,
|
|
"mean_token_accuracy": 0.19870295226573945,
|
|
"num_tokens": 70395035.0,
|
|
"step": 35980
|
|
},
|
|
{
|
|
"entropy": 5.876269149780273,
|
|
"epoch": 3.59709101814365,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00037508510975886925,
|
|
"loss": 5.4552,
|
|
"mean_token_accuracy": 0.19832950532436372,
|
|
"num_tokens": 70405620.0,
|
|
"step": 35985
|
|
},
|
|
{
|
|
"entropy": 5.935745573043823,
|
|
"epoch": 3.597590843204878,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00037505314467510726,
|
|
"loss": 5.4842,
|
|
"mean_token_accuracy": 0.19589751660823823,
|
|
"num_tokens": 70415697.0,
|
|
"step": 35990
|
|
},
|
|
{
|
|
"entropy": 5.929702234268189,
|
|
"epoch": 3.598090668266107,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0003750211770740338,
|
|
"loss": 5.3734,
|
|
"mean_token_accuracy": 0.2022384762763977,
|
|
"num_tokens": 70425121.0,
|
|
"step": 35995
|
|
},
|
|
{
|
|
"entropy": 5.904887962341308,
|
|
"epoch": 3.598590493327335,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0003749892069564533,
|
|
"loss": 5.4084,
|
|
"mean_token_accuracy": 0.2014475643634796,
|
|
"num_tokens": 70435140.0,
|
|
"step": 36000
|
|
},
|
|
{
|
|
"epoch": 3.598590493327335,
|
|
"eval_entropy": 5.719541950036619,
|
|
"eval_loss": 5.573085308074951,
|
|
"eval_mean_token_accuracy": 0.19990853655913446,
|
|
"eval_num_tokens": 70435140.0,
|
|
"eval_runtime": 23.5853,
|
|
"eval_samples_per_second": 1316.286,
|
|
"eval_steps_per_second": 164.552,
|
|
"step": 36000
|
|
},
|
|
{
|
|
"entropy": 5.980925846099853,
|
|
"epoch": 3.599090318388564,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0003749572343231701,
|
|
"loss": 5.5057,
|
|
"mean_token_accuracy": 0.18889158219099045,
|
|
"num_tokens": 70445058.0,
|
|
"step": 36005
|
|
},
|
|
{
|
|
"entropy": 5.916155052185059,
|
|
"epoch": 3.5995901434497926,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0003749252591749887,
|
|
"loss": 5.4547,
|
|
"mean_token_accuracy": 0.19807368665933608,
|
|
"num_tokens": 70456343.0,
|
|
"step": 36010
|
|
},
|
|
{
|
|
"entropy": 5.867662715911865,
|
|
"epoch": 3.6000899685110213,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0003748932815127133,
|
|
"loss": 5.4179,
|
|
"mean_token_accuracy": 0.21147752404212952,
|
|
"num_tokens": 70465521.0,
|
|
"step": 36015
|
|
},
|
|
{
|
|
"entropy": 5.964622879028321,
|
|
"epoch": 3.60058979357225,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00037486130133714874,
|
|
"loss": 5.4915,
|
|
"mean_token_accuracy": 0.1910827323794365,
|
|
"num_tokens": 70476174.0,
|
|
"step": 36020
|
|
},
|
|
{
|
|
"entropy": 5.931241416931153,
|
|
"epoch": 3.601089618633478,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0003748293186490995,
|
|
"loss": 5.4692,
|
|
"mean_token_accuracy": 0.19948563873767852,
|
|
"num_tokens": 70485121.0,
|
|
"step": 36025
|
|
},
|
|
{
|
|
"entropy": 5.911547565460205,
|
|
"epoch": 3.601589443694707,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0003747973334493703,
|
|
"loss": 5.4869,
|
|
"mean_token_accuracy": 0.19507462233304979,
|
|
"num_tokens": 70494714.0,
|
|
"step": 36030
|
|
},
|
|
{
|
|
"entropy": 5.8130189895629885,
|
|
"epoch": 3.602089268755935,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0003747653457387659,
|
|
"loss": 5.2425,
|
|
"mean_token_accuracy": 0.22041991502046585,
|
|
"num_tokens": 70504371.0,
|
|
"step": 36035
|
|
},
|
|
{
|
|
"entropy": 5.94769139289856,
|
|
"epoch": 3.602589093817164,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00037473335551809107,
|
|
"loss": 5.4622,
|
|
"mean_token_accuracy": 0.19805620163679122,
|
|
"num_tokens": 70514634.0,
|
|
"step": 36040
|
|
},
|
|
{
|
|
"entropy": 5.826299571990967,
|
|
"epoch": 3.6030889188783926,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.00037470136278815067,
|
|
"loss": 5.3924,
|
|
"mean_token_accuracy": 0.2132050096988678,
|
|
"num_tokens": 70524407.0,
|
|
"step": 36045
|
|
},
|
|
{
|
|
"entropy": 5.911607694625855,
|
|
"epoch": 3.6035887439396213,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00037466936754974964,
|
|
"loss": 5.3814,
|
|
"mean_token_accuracy": 0.19946314245462418,
|
|
"num_tokens": 70534180.0,
|
|
"step": 36050
|
|
},
|
|
{
|
|
"entropy": 5.917072868347168,
|
|
"epoch": 3.60408856900085,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00037463736980369297,
|
|
"loss": 5.4428,
|
|
"mean_token_accuracy": 0.19449391812086106,
|
|
"num_tokens": 70544183.0,
|
|
"step": 36055
|
|
},
|
|
{
|
|
"entropy": 5.921222591400147,
|
|
"epoch": 3.604588394062078,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0003746053695507856,
|
|
"loss": 5.4817,
|
|
"mean_token_accuracy": 0.19432006925344467,
|
|
"num_tokens": 70554427.0,
|
|
"step": 36060
|
|
},
|
|
{
|
|
"entropy": 5.9980712890625,
|
|
"epoch": 3.605088219123307,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0003745733667918329,
|
|
"loss": 5.6043,
|
|
"mean_token_accuracy": 0.1853531390428543,
|
|
"num_tokens": 70564969.0,
|
|
"step": 36065
|
|
},
|
|
{
|
|
"entropy": 5.954585123062134,
|
|
"epoch": 3.605588044184535,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0003745413615276399,
|
|
"loss": 5.4501,
|
|
"mean_token_accuracy": 0.20076673924922944,
|
|
"num_tokens": 70574141.0,
|
|
"step": 36070
|
|
},
|
|
{
|
|
"entropy": 5.908354139328003,
|
|
"epoch": 3.606087869245764,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00037450935375901186,
|
|
"loss": 5.437,
|
|
"mean_token_accuracy": 0.19237482845783233,
|
|
"num_tokens": 70584009.0,
|
|
"step": 36075
|
|
},
|
|
{
|
|
"entropy": 5.850166940689087,
|
|
"epoch": 3.6065876943069926,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000374477343486754,
|
|
"loss": 5.3906,
|
|
"mean_token_accuracy": 0.20559005439281464,
|
|
"num_tokens": 70595276.0,
|
|
"step": 36080
|
|
},
|
|
{
|
|
"entropy": 5.960249567031861,
|
|
"epoch": 3.6070875193682213,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0003744453307116719,
|
|
"loss": 5.5027,
|
|
"mean_token_accuracy": 0.19217336624860765,
|
|
"num_tokens": 70604901.0,
|
|
"step": 36085
|
|
},
|
|
{
|
|
"entropy": 5.821631908416748,
|
|
"epoch": 3.60758734442945,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00037441331543457075,
|
|
"loss": 5.4396,
|
|
"mean_token_accuracy": 0.20300260186195374,
|
|
"num_tokens": 70614832.0,
|
|
"step": 36090
|
|
},
|
|
{
|
|
"entropy": 5.948661375045776,
|
|
"epoch": 3.608087169490678,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00037438129765625627,
|
|
"loss": 5.4468,
|
|
"mean_token_accuracy": 0.19082941263914108,
|
|
"num_tokens": 70623674.0,
|
|
"step": 36095
|
|
},
|
|
{
|
|
"entropy": 6.026602649688721,
|
|
"epoch": 3.608586994551907,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00037434927737753387,
|
|
"loss": 5.5733,
|
|
"mean_token_accuracy": 0.18624036461114885,
|
|
"num_tokens": 70633197.0,
|
|
"step": 36100
|
|
},
|
|
{
|
|
"entropy": 5.977251577377319,
|
|
"epoch": 3.609086819613135,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00037431725459920927,
|
|
"loss": 5.5399,
|
|
"mean_token_accuracy": 0.19112327098846435,
|
|
"num_tokens": 70644053.0,
|
|
"step": 36105
|
|
},
|
|
{
|
|
"entropy": 5.984229993820191,
|
|
"epoch": 3.609586644674364,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00037428522932208804,
|
|
"loss": 5.5408,
|
|
"mean_token_accuracy": 0.19099769741296768,
|
|
"num_tokens": 70656229.0,
|
|
"step": 36110
|
|
},
|
|
{
|
|
"entropy": 5.907214689254761,
|
|
"epoch": 3.6100864697355926,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00037425320154697595,
|
|
"loss": 5.4321,
|
|
"mean_token_accuracy": 0.20463010370731355,
|
|
"num_tokens": 70666262.0,
|
|
"step": 36115
|
|
},
|
|
{
|
|
"entropy": 6.011709928512573,
|
|
"epoch": 3.6105862947968212,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00037422117127467884,
|
|
"loss": 5.525,
|
|
"mean_token_accuracy": 0.18595429062843322,
|
|
"num_tokens": 70675941.0,
|
|
"step": 36120
|
|
},
|
|
{
|
|
"entropy": 5.854348278045654,
|
|
"epoch": 3.61108611985805,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0003741891385060027,
|
|
"loss": 5.3716,
|
|
"mean_token_accuracy": 0.20847855806350707,
|
|
"num_tokens": 70685174.0,
|
|
"step": 36125
|
|
},
|
|
{
|
|
"entropy": 5.856348037719727,
|
|
"epoch": 3.611585944919278,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0003741571032417533,
|
|
"loss": 5.457,
|
|
"mean_token_accuracy": 0.19749577790498735,
|
|
"num_tokens": 70694090.0,
|
|
"step": 36130
|
|
},
|
|
{
|
|
"entropy": 5.8827966213226315,
|
|
"epoch": 3.612085769980507,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0003741250654827367,
|
|
"loss": 5.3577,
|
|
"mean_token_accuracy": 0.20365958511829377,
|
|
"num_tokens": 70703230.0,
|
|
"step": 36135
|
|
},
|
|
{
|
|
"entropy": 6.0298246383667,
|
|
"epoch": 3.612585595041735,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00037409302522975897,
|
|
"loss": 5.4148,
|
|
"mean_token_accuracy": 0.20453756004571916,
|
|
"num_tokens": 70715029.0,
|
|
"step": 36140
|
|
},
|
|
{
|
|
"entropy": 5.973222970962524,
|
|
"epoch": 3.613085420102964,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00037406098248362625,
|
|
"loss": 5.5199,
|
|
"mean_token_accuracy": 0.19503476321697236,
|
|
"num_tokens": 70724515.0,
|
|
"step": 36145
|
|
},
|
|
{
|
|
"entropy": 5.847645568847656,
|
|
"epoch": 3.6135852451641925,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00037402893724514466,
|
|
"loss": 5.3956,
|
|
"mean_token_accuracy": 0.19683243632316588,
|
|
"num_tokens": 70734129.0,
|
|
"step": 36150
|
|
},
|
|
{
|
|
"entropy": 5.874614810943603,
|
|
"epoch": 3.6140850702254212,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00037399688951512044,
|
|
"loss": 5.3776,
|
|
"mean_token_accuracy": 0.1991051658987999,
|
|
"num_tokens": 70743525.0,
|
|
"step": 36155
|
|
},
|
|
{
|
|
"entropy": 5.910234212875366,
|
|
"epoch": 3.61458489528665,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0003739648392943601,
|
|
"loss": 5.4622,
|
|
"mean_token_accuracy": 0.1911250337958336,
|
|
"num_tokens": 70753219.0,
|
|
"step": 36160
|
|
},
|
|
{
|
|
"entropy": 5.888140678405762,
|
|
"epoch": 3.615084720347878,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0003739327865836697,
|
|
"loss": 5.3668,
|
|
"mean_token_accuracy": 0.2045993909239769,
|
|
"num_tokens": 70761876.0,
|
|
"step": 36165
|
|
},
|
|
{
|
|
"entropy": 5.908159589767456,
|
|
"epoch": 3.615584545409107,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00037390073138385597,
|
|
"loss": 5.4456,
|
|
"mean_token_accuracy": 0.20279683470726012,
|
|
"num_tokens": 70771710.0,
|
|
"step": 36170
|
|
},
|
|
{
|
|
"entropy": 5.958648204803467,
|
|
"epoch": 3.616084370470335,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0003738686736957253,
|
|
"loss": 5.5243,
|
|
"mean_token_accuracy": 0.19125261753797532,
|
|
"num_tokens": 70781670.0,
|
|
"step": 36175
|
|
},
|
|
{
|
|
"entropy": 5.924035549163818,
|
|
"epoch": 3.616584195531564,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00037383661352008413,
|
|
"loss": 5.4055,
|
|
"mean_token_accuracy": 0.19716356843709945,
|
|
"num_tokens": 70790376.0,
|
|
"step": 36180
|
|
},
|
|
{
|
|
"entropy": 5.947341108322144,
|
|
"epoch": 3.6170840205927925,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00037380455085773924,
|
|
"loss": 5.5604,
|
|
"mean_token_accuracy": 0.18528756499290466,
|
|
"num_tokens": 70800659.0,
|
|
"step": 36185
|
|
},
|
|
{
|
|
"entropy": 5.9906400680542,
|
|
"epoch": 3.6175838456540212,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00037377248570949733,
|
|
"loss": 5.3878,
|
|
"mean_token_accuracy": 0.1961662784218788,
|
|
"num_tokens": 70810614.0,
|
|
"step": 36190
|
|
},
|
|
{
|
|
"entropy": 5.909713363647461,
|
|
"epoch": 3.6180836707152495,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00037374041807616506,
|
|
"loss": 5.4042,
|
|
"mean_token_accuracy": 0.20270926654338836,
|
|
"num_tokens": 70820097.0,
|
|
"step": 36195
|
|
},
|
|
{
|
|
"entropy": 5.886361980438233,
|
|
"epoch": 3.618583495776478,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00037370834795854923,
|
|
"loss": 5.4519,
|
|
"mean_token_accuracy": 0.19421520978212356,
|
|
"num_tokens": 70829864.0,
|
|
"step": 36200
|
|
},
|
|
{
|
|
"entropy": 5.923863220214844,
|
|
"epoch": 3.619083320837707,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0003736762753574568,
|
|
"loss": 5.3343,
|
|
"mean_token_accuracy": 0.20763341784477235,
|
|
"num_tokens": 70838999.0,
|
|
"step": 36205
|
|
},
|
|
{
|
|
"entropy": 5.8570859909057615,
|
|
"epoch": 3.619583145898935,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00037364420027369467,
|
|
"loss": 5.3727,
|
|
"mean_token_accuracy": 0.2118109866976738,
|
|
"num_tokens": 70848473.0,
|
|
"step": 36210
|
|
},
|
|
{
|
|
"entropy": 5.898418283462524,
|
|
"epoch": 3.620082970960164,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0003736121227080699,
|
|
"loss": 5.393,
|
|
"mean_token_accuracy": 0.20067893862724304,
|
|
"num_tokens": 70859067.0,
|
|
"step": 36215
|
|
},
|
|
{
|
|
"entropy": 5.85217661857605,
|
|
"epoch": 3.6205827960213925,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00037358004266138943,
|
|
"loss": 5.4473,
|
|
"mean_token_accuracy": 0.1976715311408043,
|
|
"num_tokens": 70868028.0,
|
|
"step": 36220
|
|
},
|
|
{
|
|
"entropy": 5.873902606964111,
|
|
"epoch": 3.6210826210826212,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00037354796013446044,
|
|
"loss": 5.3922,
|
|
"mean_token_accuracy": 0.19755477011203765,
|
|
"num_tokens": 70878326.0,
|
|
"step": 36225
|
|
},
|
|
{
|
|
"entropy": 5.936981964111328,
|
|
"epoch": 3.6215824461438495,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0003735158751280902,
|
|
"loss": 5.4214,
|
|
"mean_token_accuracy": 0.19582841396331788,
|
|
"num_tokens": 70887634.0,
|
|
"step": 36230
|
|
},
|
|
{
|
|
"entropy": 5.923907470703125,
|
|
"epoch": 3.622082271205078,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0003734837876430859,
|
|
"loss": 5.4396,
|
|
"mean_token_accuracy": 0.19699936360120773,
|
|
"num_tokens": 70898154.0,
|
|
"step": 36235
|
|
},
|
|
{
|
|
"entropy": 5.9844520568847654,
|
|
"epoch": 3.622582096266307,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0003734516976802548,
|
|
"loss": 5.5937,
|
|
"mean_token_accuracy": 0.18973330408334732,
|
|
"num_tokens": 70907247.0,
|
|
"step": 36240
|
|
},
|
|
{
|
|
"entropy": 5.9722202777862545,
|
|
"epoch": 3.623081921327535,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0003734196052404043,
|
|
"loss": 5.4712,
|
|
"mean_token_accuracy": 0.1904744729399681,
|
|
"num_tokens": 70916665.0,
|
|
"step": 36245
|
|
},
|
|
{
|
|
"entropy": 6.003719997406006,
|
|
"epoch": 3.623581746388764,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0003733875103243419,
|
|
"loss": 5.6023,
|
|
"mean_token_accuracy": 0.1846073791384697,
|
|
"num_tokens": 70928166.0,
|
|
"step": 36250
|
|
},
|
|
{
|
|
"entropy": 5.9375622272491455,
|
|
"epoch": 3.6240815714499925,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0003733554129328751,
|
|
"loss": 5.4626,
|
|
"mean_token_accuracy": 0.19723271131515502,
|
|
"num_tokens": 70936809.0,
|
|
"step": 36255
|
|
},
|
|
{
|
|
"entropy": 5.967856693267822,
|
|
"epoch": 3.6245813965112212,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00037332331306681136,
|
|
"loss": 5.5586,
|
|
"mean_token_accuracy": 0.19065824002027512,
|
|
"num_tokens": 70947131.0,
|
|
"step": 36260
|
|
},
|
|
{
|
|
"entropy": 5.924395513534546,
|
|
"epoch": 3.6250812215724495,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00037329121072695833,
|
|
"loss": 5.4319,
|
|
"mean_token_accuracy": 0.1993176057934761,
|
|
"num_tokens": 70956728.0,
|
|
"step": 36265
|
|
},
|
|
{
|
|
"entropy": 5.900323486328125,
|
|
"epoch": 3.625581046633678,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00037325910591412374,
|
|
"loss": 5.372,
|
|
"mean_token_accuracy": 0.20196812897920607,
|
|
"num_tokens": 70966422.0,
|
|
"step": 36270
|
|
},
|
|
{
|
|
"entropy": 5.957156848907471,
|
|
"epoch": 3.626080871694907,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0003732269986291154,
|
|
"loss": 5.4146,
|
|
"mean_token_accuracy": 0.20424090027809144,
|
|
"num_tokens": 70976063.0,
|
|
"step": 36275
|
|
},
|
|
{
|
|
"entropy": 5.966577100753784,
|
|
"epoch": 3.626580696756135,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00037319488887274096,
|
|
"loss": 5.5021,
|
|
"mean_token_accuracy": 0.19558592438697814,
|
|
"num_tokens": 70986772.0,
|
|
"step": 36280
|
|
},
|
|
{
|
|
"entropy": 5.922550535202026,
|
|
"epoch": 3.627080521817364,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0003731627766458084,
|
|
"loss": 5.3829,
|
|
"mean_token_accuracy": 0.19933864921331407,
|
|
"num_tokens": 70996458.0,
|
|
"step": 36285
|
|
},
|
|
{
|
|
"entropy": 6.005239009857178,
|
|
"epoch": 3.6275803468785925,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0003731306619491257,
|
|
"loss": 5.5701,
|
|
"mean_token_accuracy": 0.20115631967782974,
|
|
"num_tokens": 71006612.0,
|
|
"step": 36290
|
|
},
|
|
{
|
|
"entropy": 5.875125741958618,
|
|
"epoch": 3.6280801719398212,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0003730985447835008,
|
|
"loss": 5.3421,
|
|
"mean_token_accuracy": 0.20315505117177962,
|
|
"num_tokens": 71016058.0,
|
|
"step": 36295
|
|
},
|
|
{
|
|
"entropy": 5.997361373901367,
|
|
"epoch": 3.6285799970010495,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0003730664251497417,
|
|
"loss": 5.4932,
|
|
"mean_token_accuracy": 0.19739015996456147,
|
|
"num_tokens": 71025267.0,
|
|
"step": 36300
|
|
},
|
|
{
|
|
"entropy": 5.952113008499145,
|
|
"epoch": 3.629079822062278,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0003730343030486566,
|
|
"loss": 5.4638,
|
|
"mean_token_accuracy": 0.2006573960185051,
|
|
"num_tokens": 71033972.0,
|
|
"step": 36305
|
|
},
|
|
{
|
|
"entropy": 6.023788833618164,
|
|
"epoch": 3.629579647123507,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0003730021784810536,
|
|
"loss": 5.5593,
|
|
"mean_token_accuracy": 0.19287274181842803,
|
|
"num_tokens": 71045014.0,
|
|
"step": 36310
|
|
},
|
|
{
|
|
"entropy": 5.892094087600708,
|
|
"epoch": 3.630079472184735,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0003729700514477411,
|
|
"loss": 5.3606,
|
|
"mean_token_accuracy": 0.195553520321846,
|
|
"num_tokens": 71053559.0,
|
|
"step": 36315
|
|
},
|
|
{
|
|
"entropy": 5.914298582077026,
|
|
"epoch": 3.630579297245964,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0003729379219495273,
|
|
"loss": 5.4804,
|
|
"mean_token_accuracy": 0.19341374039649964,
|
|
"num_tokens": 71063495.0,
|
|
"step": 36320
|
|
},
|
|
{
|
|
"entropy": 5.901910066604614,
|
|
"epoch": 3.6310791223071925,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0003729057899872206,
|
|
"loss": 5.4485,
|
|
"mean_token_accuracy": 0.19252800196409225,
|
|
"num_tokens": 71072998.0,
|
|
"step": 36325
|
|
},
|
|
{
|
|
"entropy": 5.926194667816162,
|
|
"epoch": 3.6315789473684212,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0003728736555616293,
|
|
"loss": 5.3846,
|
|
"mean_token_accuracy": 0.20073135048151017,
|
|
"num_tokens": 71083517.0,
|
|
"step": 36330
|
|
},
|
|
{
|
|
"entropy": 5.9737437725067135,
|
|
"epoch": 3.6320787724296495,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00037284151867356217,
|
|
"loss": 5.5148,
|
|
"mean_token_accuracy": 0.1944445103406906,
|
|
"num_tokens": 71094789.0,
|
|
"step": 36335
|
|
},
|
|
{
|
|
"entropy": 5.957343053817749,
|
|
"epoch": 3.632578597490878,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00037280937932382754,
|
|
"loss": 5.4865,
|
|
"mean_token_accuracy": 0.19513378739356996,
|
|
"num_tokens": 71103933.0,
|
|
"step": 36340
|
|
},
|
|
{
|
|
"entropy": 5.941267967224121,
|
|
"epoch": 3.633078422552107,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000372777237513234,
|
|
"loss": 5.3844,
|
|
"mean_token_accuracy": 0.20098205655813217,
|
|
"num_tokens": 71112650.0,
|
|
"step": 36345
|
|
},
|
|
{
|
|
"entropy": 5.949472951889038,
|
|
"epoch": 3.633578247613335,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00037274509324259047,
|
|
"loss": 5.5034,
|
|
"mean_token_accuracy": 0.19746912270784378,
|
|
"num_tokens": 71122415.0,
|
|
"step": 36350
|
|
},
|
|
{
|
|
"entropy": 5.932740163803101,
|
|
"epoch": 3.634078072674564,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0003727129465127055,
|
|
"loss": 5.4087,
|
|
"mean_token_accuracy": 0.20065378844738008,
|
|
"num_tokens": 71133092.0,
|
|
"step": 36355
|
|
},
|
|
{
|
|
"entropy": 5.8539598941802975,
|
|
"epoch": 3.6345778977357925,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0003726807973243879,
|
|
"loss": 5.3908,
|
|
"mean_token_accuracy": 0.2071634367108345,
|
|
"num_tokens": 71143924.0,
|
|
"step": 36360
|
|
},
|
|
{
|
|
"entropy": 5.821384763717651,
|
|
"epoch": 3.6350777227970212,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00037264864567844664,
|
|
"loss": 5.3933,
|
|
"mean_token_accuracy": 0.2036502778530121,
|
|
"num_tokens": 71154109.0,
|
|
"step": 36365
|
|
},
|
|
{
|
|
"entropy": 5.857444858551025,
|
|
"epoch": 3.6355775478582495,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0003726164915756905,
|
|
"loss": 5.2902,
|
|
"mean_token_accuracy": 0.21735429465770723,
|
|
"num_tokens": 71163621.0,
|
|
"step": 36370
|
|
},
|
|
{
|
|
"entropy": 5.983155393600464,
|
|
"epoch": 3.636077372919478,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00037258433501692856,
|
|
"loss": 5.4617,
|
|
"mean_token_accuracy": 0.19351218193769454,
|
|
"num_tokens": 71173525.0,
|
|
"step": 36375
|
|
},
|
|
{
|
|
"entropy": 5.873544120788575,
|
|
"epoch": 3.636577197980707,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0003725521760029699,
|
|
"loss": 5.3181,
|
|
"mean_token_accuracy": 0.2051018536090851,
|
|
"num_tokens": 71182224.0,
|
|
"step": 36380
|
|
},
|
|
{
|
|
"entropy": 5.744286966323853,
|
|
"epoch": 3.637077023041935,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00037252001453462366,
|
|
"loss": 5.344,
|
|
"mean_token_accuracy": 0.19692880660295486,
|
|
"num_tokens": 71191104.0,
|
|
"step": 36385
|
|
},
|
|
{
|
|
"entropy": 5.9019763469696045,
|
|
"epoch": 3.637576848103164,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00037248785061269883,
|
|
"loss": 5.5159,
|
|
"mean_token_accuracy": 0.19494041204452514,
|
|
"num_tokens": 71201193.0,
|
|
"step": 36390
|
|
},
|
|
{
|
|
"entropy": 6.037937450408935,
|
|
"epoch": 3.6380766731643925,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0003724556842380048,
|
|
"loss": 5.4761,
|
|
"mean_token_accuracy": 0.19183921813964844,
|
|
"num_tokens": 71210679.0,
|
|
"step": 36395
|
|
},
|
|
{
|
|
"entropy": 6.012771415710449,
|
|
"epoch": 3.6385764982256212,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00037242351541135084,
|
|
"loss": 5.546,
|
|
"mean_token_accuracy": 0.19804125279188156,
|
|
"num_tokens": 71221615.0,
|
|
"step": 36400
|
|
},
|
|
{
|
|
"entropy": 5.910343313217163,
|
|
"epoch": 3.6390763232868495,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00037239134413354633,
|
|
"loss": 5.4737,
|
|
"mean_token_accuracy": 0.18992414325475693,
|
|
"num_tokens": 71231728.0,
|
|
"step": 36405
|
|
},
|
|
{
|
|
"entropy": 5.93896598815918,
|
|
"epoch": 3.639576148348078,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0003723591704054006,
|
|
"loss": 5.4997,
|
|
"mean_token_accuracy": 0.20553192645311355,
|
|
"num_tokens": 71241754.0,
|
|
"step": 36410
|
|
},
|
|
{
|
|
"entropy": 5.944372987747192,
|
|
"epoch": 3.640075973409307,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00037232699422772323,
|
|
"loss": 5.4547,
|
|
"mean_token_accuracy": 0.1904184639453888,
|
|
"num_tokens": 71251232.0,
|
|
"step": 36415
|
|
},
|
|
{
|
|
"entropy": 5.898862266540528,
|
|
"epoch": 3.640575798470535,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0003722948156013238,
|
|
"loss": 5.3923,
|
|
"mean_token_accuracy": 0.20434790551662446,
|
|
"num_tokens": 71261158.0,
|
|
"step": 36420
|
|
},
|
|
{
|
|
"entropy": 5.900595045089721,
|
|
"epoch": 3.641075623531764,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00037226263452701177,
|
|
"loss": 5.4319,
|
|
"mean_token_accuracy": 0.19404417276382446,
|
|
"num_tokens": 71270204.0,
|
|
"step": 36425
|
|
},
|
|
{
|
|
"entropy": 5.88863615989685,
|
|
"epoch": 3.6415754485929925,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0003722304510055969,
|
|
"loss": 5.3843,
|
|
"mean_token_accuracy": 0.1985199496150017,
|
|
"num_tokens": 71280305.0,
|
|
"step": 36430
|
|
},
|
|
{
|
|
"entropy": 5.935490274429322,
|
|
"epoch": 3.6420752736542212,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00037219826503788884,
|
|
"loss": 5.4079,
|
|
"mean_token_accuracy": 0.2003839924931526,
|
|
"num_tokens": 71288724.0,
|
|
"step": 36435
|
|
},
|
|
{
|
|
"entropy": 5.8206535339355465,
|
|
"epoch": 3.6425750987154495,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0003721660766246975,
|
|
"loss": 5.4089,
|
|
"mean_token_accuracy": 0.2030041456222534,
|
|
"num_tokens": 71297662.0,
|
|
"step": 36440
|
|
},
|
|
{
|
|
"entropy": 5.929647636413574,
|
|
"epoch": 3.643074923776678,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0003721338857668327,
|
|
"loss": 5.4435,
|
|
"mean_token_accuracy": 0.19644272029399873,
|
|
"num_tokens": 71307892.0,
|
|
"step": 36445
|
|
},
|
|
{
|
|
"entropy": 5.970460367202759,
|
|
"epoch": 3.643574748837907,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0003721016924651042,
|
|
"loss": 5.4523,
|
|
"mean_token_accuracy": 0.1955600380897522,
|
|
"num_tokens": 71318380.0,
|
|
"step": 36450
|
|
},
|
|
{
|
|
"entropy": 5.891325235366821,
|
|
"epoch": 3.644074573899135,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0003720694967203223,
|
|
"loss": 5.3672,
|
|
"mean_token_accuracy": 0.20471305549144744,
|
|
"num_tokens": 71327172.0,
|
|
"step": 36455
|
|
},
|
|
{
|
|
"entropy": 5.813264560699463,
|
|
"epoch": 3.644574398960364,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00037203729853329675,
|
|
"loss": 5.3797,
|
|
"mean_token_accuracy": 0.2079006776213646,
|
|
"num_tokens": 71337039.0,
|
|
"step": 36460
|
|
},
|
|
{
|
|
"entropy": 5.88571081161499,
|
|
"epoch": 3.6450742240215925,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00037200509790483773,
|
|
"loss": 5.4513,
|
|
"mean_token_accuracy": 0.19451733976602553,
|
|
"num_tokens": 71347305.0,
|
|
"step": 36465
|
|
},
|
|
{
|
|
"entropy": 5.983437585830688,
|
|
"epoch": 3.6455740490828212,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0003719728948357554,
|
|
"loss": 5.5319,
|
|
"mean_token_accuracy": 0.1934321254491806,
|
|
"num_tokens": 71356975.0,
|
|
"step": 36470
|
|
},
|
|
{
|
|
"entropy": 5.975502920150757,
|
|
"epoch": 3.6460738741440495,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00037194068932686,
|
|
"loss": 5.5012,
|
|
"mean_token_accuracy": 0.19069854021072388,
|
|
"num_tokens": 71366489.0,
|
|
"step": 36475
|
|
},
|
|
{
|
|
"entropy": 5.840117645263672,
|
|
"epoch": 3.646573699205278,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00037190848137896176,
|
|
"loss": 5.3686,
|
|
"mean_token_accuracy": 0.21222463101148606,
|
|
"num_tokens": 71376364.0,
|
|
"step": 36480
|
|
},
|
|
{
|
|
"entropy": 5.88534836769104,
|
|
"epoch": 3.647073524266507,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00037187627099287114,
|
|
"loss": 5.3847,
|
|
"mean_token_accuracy": 0.20192834436893464,
|
|
"num_tokens": 71385679.0,
|
|
"step": 36485
|
|
},
|
|
{
|
|
"entropy": 5.9304883003234865,
|
|
"epoch": 3.647573349327735,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00037184405816939847,
|
|
"loss": 5.3652,
|
|
"mean_token_accuracy": 0.2031943157315254,
|
|
"num_tokens": 71395778.0,
|
|
"step": 36490
|
|
},
|
|
{
|
|
"entropy": 5.875094366073609,
|
|
"epoch": 3.648073174388964,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0003718118429093542,
|
|
"loss": 5.4397,
|
|
"mean_token_accuracy": 0.20370718389749526,
|
|
"num_tokens": 71407547.0,
|
|
"step": 36495
|
|
},
|
|
{
|
|
"entropy": 5.875795841217041,
|
|
"epoch": 3.6485729994501925,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0003717796252135488,
|
|
"loss": 5.4016,
|
|
"mean_token_accuracy": 0.2022812619805336,
|
|
"num_tokens": 71417013.0,
|
|
"step": 36500
|
|
},
|
|
{
|
|
"entropy": 5.929789018630982,
|
|
"epoch": 3.6490728245114212,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00037174740508279296,
|
|
"loss": 5.3828,
|
|
"mean_token_accuracy": 0.20153059363365172,
|
|
"num_tokens": 71426768.0,
|
|
"step": 36505
|
|
},
|
|
{
|
|
"entropy": 5.835695791244507,
|
|
"epoch": 3.6495726495726495,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0003717151825178974,
|
|
"loss": 5.3511,
|
|
"mean_token_accuracy": 0.21299168467521667,
|
|
"num_tokens": 71437099.0,
|
|
"step": 36510
|
|
},
|
|
{
|
|
"entropy": 5.910240411758423,
|
|
"epoch": 3.650072474633878,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0003716829575196726,
|
|
"loss": 5.4008,
|
|
"mean_token_accuracy": 0.19492483735084534,
|
|
"num_tokens": 71447740.0,
|
|
"step": 36515
|
|
},
|
|
{
|
|
"entropy": 5.992998266220093,
|
|
"epoch": 3.6505722996951064,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0003716507300889296,
|
|
"loss": 5.4423,
|
|
"mean_token_accuracy": 0.19846674352884291,
|
|
"num_tokens": 71457994.0,
|
|
"step": 36520
|
|
},
|
|
{
|
|
"entropy": 5.896043539047241,
|
|
"epoch": 3.651072124756335,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00037161850022647905,
|
|
"loss": 5.4405,
|
|
"mean_token_accuracy": 0.20104419887065889,
|
|
"num_tokens": 71467800.0,
|
|
"step": 36525
|
|
},
|
|
{
|
|
"entropy": 5.88218846321106,
|
|
"epoch": 3.651571949817564,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0003715862679331318,
|
|
"loss": 5.4438,
|
|
"mean_token_accuracy": 0.198181714117527,
|
|
"num_tokens": 71477275.0,
|
|
"step": 36530
|
|
},
|
|
{
|
|
"entropy": 6.02241621017456,
|
|
"epoch": 3.6520717748787925,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00037155403320969906,
|
|
"loss": 5.5376,
|
|
"mean_token_accuracy": 0.19352928102016448,
|
|
"num_tokens": 71487868.0,
|
|
"step": 36535
|
|
},
|
|
{
|
|
"entropy": 5.923523616790772,
|
|
"epoch": 3.6525715999400212,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0003715217960569915,
|
|
"loss": 5.4784,
|
|
"mean_token_accuracy": 0.19974743872880935,
|
|
"num_tokens": 71497315.0,
|
|
"step": 36540
|
|
},
|
|
{
|
|
"entropy": 5.862793588638306,
|
|
"epoch": 3.6530714250012495,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00037148955647582063,
|
|
"loss": 5.381,
|
|
"mean_token_accuracy": 0.20358240306377412,
|
|
"num_tokens": 71507800.0,
|
|
"step": 36545
|
|
},
|
|
{
|
|
"entropy": 5.921111822128296,
|
|
"epoch": 3.653571250062478,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00037145731446699715,
|
|
"loss": 5.512,
|
|
"mean_token_accuracy": 0.19334552735090255,
|
|
"num_tokens": 71517996.0,
|
|
"step": 36550
|
|
},
|
|
{
|
|
"entropy": 5.929838705062866,
|
|
"epoch": 3.6540710751237064,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0003714250700313325,
|
|
"loss": 5.5058,
|
|
"mean_token_accuracy": 0.1962505891919136,
|
|
"num_tokens": 71528162.0,
|
|
"step": 36555
|
|
},
|
|
{
|
|
"entropy": 5.905144548416137,
|
|
"epoch": 3.654570900184935,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00037139282316963804,
|
|
"loss": 5.4346,
|
|
"mean_token_accuracy": 0.19580438137054443,
|
|
"num_tokens": 71536641.0,
|
|
"step": 36560
|
|
},
|
|
{
|
|
"entropy": 5.867732143402099,
|
|
"epoch": 3.655070725246164,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0003713605738827248,
|
|
"loss": 5.3401,
|
|
"mean_token_accuracy": 0.20001389235258102,
|
|
"num_tokens": 71547182.0,
|
|
"step": 36565
|
|
},
|
|
{
|
|
"entropy": 5.8455925464630125,
|
|
"epoch": 3.6555705503073925,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0003713283221714044,
|
|
"loss": 5.3518,
|
|
"mean_token_accuracy": 0.20319843888282776,
|
|
"num_tokens": 71556220.0,
|
|
"step": 36570
|
|
},
|
|
{
|
|
"entropy": 5.925971364974975,
|
|
"epoch": 3.6560703753686212,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00037129606803648814,
|
|
"loss": 5.4367,
|
|
"mean_token_accuracy": 0.1992378056049347,
|
|
"num_tokens": 71565488.0,
|
|
"step": 36575
|
|
},
|
|
{
|
|
"entropy": 5.905408239364624,
|
|
"epoch": 3.6565702004298495,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00037126381147878763,
|
|
"loss": 5.4322,
|
|
"mean_token_accuracy": 0.20054108798503875,
|
|
"num_tokens": 71575396.0,
|
|
"step": 36580
|
|
},
|
|
{
|
|
"entropy": 5.902328300476074,
|
|
"epoch": 3.657070025491078,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00037123155249911435,
|
|
"loss": 5.4154,
|
|
"mean_token_accuracy": 0.20218820720911027,
|
|
"num_tokens": 71585380.0,
|
|
"step": 36585
|
|
},
|
|
{
|
|
"entropy": 5.873482990264892,
|
|
"epoch": 3.6575698505523064,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00037119929109828,
|
|
"loss": 5.3389,
|
|
"mean_token_accuracy": 0.20361616909503938,
|
|
"num_tokens": 71594936.0,
|
|
"step": 36590
|
|
},
|
|
{
|
|
"entropy": 5.885591888427735,
|
|
"epoch": 3.658069675613535,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0003711670272770962,
|
|
"loss": 5.3005,
|
|
"mean_token_accuracy": 0.21597175151109696,
|
|
"num_tokens": 71604418.0,
|
|
"step": 36595
|
|
},
|
|
{
|
|
"entropy": 5.907588481903076,
|
|
"epoch": 3.658569500674764,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00037113476103637483,
|
|
"loss": 5.4868,
|
|
"mean_token_accuracy": 0.19709782004356385,
|
|
"num_tokens": 71614780.0,
|
|
"step": 36600
|
|
},
|
|
{
|
|
"entropy": 5.919304704666137,
|
|
"epoch": 3.6590693257359925,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0003711024923769275,
|
|
"loss": 5.4366,
|
|
"mean_token_accuracy": 0.19920530319213867,
|
|
"num_tokens": 71623868.0,
|
|
"step": 36605
|
|
},
|
|
{
|
|
"entropy": 5.981871700286865,
|
|
"epoch": 3.6595691507972212,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0003710702212995662,
|
|
"loss": 5.5443,
|
|
"mean_token_accuracy": 0.18766223788261413,
|
|
"num_tokens": 71634481.0,
|
|
"step": 36610
|
|
},
|
|
{
|
|
"entropy": 5.949837017059326,
|
|
"epoch": 3.6600689758584495,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00037103794780510296,
|
|
"loss": 5.4785,
|
|
"mean_token_accuracy": 0.19240762442350387,
|
|
"num_tokens": 71643180.0,
|
|
"step": 36615
|
|
},
|
|
{
|
|
"entropy": 5.905886793136597,
|
|
"epoch": 3.660568800919678,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00037100567189434966,
|
|
"loss": 5.361,
|
|
"mean_token_accuracy": 0.19953129738569259,
|
|
"num_tokens": 71652370.0,
|
|
"step": 36620
|
|
},
|
|
{
|
|
"entropy": 5.786084270477295,
|
|
"epoch": 3.6610686259809064,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0003709733935681183,
|
|
"loss": 5.3001,
|
|
"mean_token_accuracy": 0.20892855972051622,
|
|
"num_tokens": 71663047.0,
|
|
"step": 36625
|
|
},
|
|
{
|
|
"entropy": 5.906598615646362,
|
|
"epoch": 3.661568451042135,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.000370941112827221,
|
|
"loss": 5.4459,
|
|
"mean_token_accuracy": 0.19365739524364473,
|
|
"num_tokens": 71672879.0,
|
|
"step": 36630
|
|
},
|
|
{
|
|
"entropy": 6.018243598937988,
|
|
"epoch": 3.662068276103364,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00037090882967247003,
|
|
"loss": 5.5427,
|
|
"mean_token_accuracy": 0.19366661459207535,
|
|
"num_tokens": 71682773.0,
|
|
"step": 36635
|
|
},
|
|
{
|
|
"entropy": 5.987270164489746,
|
|
"epoch": 3.6625681011645925,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0003708765441046776,
|
|
"loss": 5.4563,
|
|
"mean_token_accuracy": 0.2029008150100708,
|
|
"num_tokens": 71692374.0,
|
|
"step": 36640
|
|
},
|
|
{
|
|
"entropy": 6.014819145202637,
|
|
"epoch": 3.6630679262258212,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00037084425612465605,
|
|
"loss": 5.581,
|
|
"mean_token_accuracy": 0.18341819941997528,
|
|
"num_tokens": 71701703.0,
|
|
"step": 36645
|
|
},
|
|
{
|
|
"entropy": 5.927193021774292,
|
|
"epoch": 3.6635677512870495,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0003708119657332176,
|
|
"loss": 5.4771,
|
|
"mean_token_accuracy": 0.1961955413222313,
|
|
"num_tokens": 71711783.0,
|
|
"step": 36650
|
|
},
|
|
{
|
|
"entropy": 5.906699323654175,
|
|
"epoch": 3.664067576348278,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00037077967293117477,
|
|
"loss": 5.4403,
|
|
"mean_token_accuracy": 0.20711207687854766,
|
|
"num_tokens": 71721374.0,
|
|
"step": 36655
|
|
},
|
|
{
|
|
"entropy": 5.964288663864136,
|
|
"epoch": 3.6645674014095064,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00037074737771933996,
|
|
"loss": 5.4362,
|
|
"mean_token_accuracy": 0.20169422328472136,
|
|
"num_tokens": 71729742.0,
|
|
"step": 36660
|
|
},
|
|
{
|
|
"entropy": 5.958707332611084,
|
|
"epoch": 3.665067226470735,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0003707150800985259,
|
|
"loss": 5.5913,
|
|
"mean_token_accuracy": 0.1823717713356018,
|
|
"num_tokens": 71739759.0,
|
|
"step": 36665
|
|
},
|
|
{
|
|
"entropy": 5.895709276199341,
|
|
"epoch": 3.665567051531964,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00037068278006954493,
|
|
"loss": 5.3898,
|
|
"mean_token_accuracy": 0.20481766313314437,
|
|
"num_tokens": 71749882.0,
|
|
"step": 36670
|
|
},
|
|
{
|
|
"entropy": 5.978379774093628,
|
|
"epoch": 3.6660668765931925,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00037065047763320993,
|
|
"loss": 5.475,
|
|
"mean_token_accuracy": 0.1942192479968071,
|
|
"num_tokens": 71760212.0,
|
|
"step": 36675
|
|
},
|
|
{
|
|
"entropy": 5.936039543151855,
|
|
"epoch": 3.6665667016544212,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0003706181727903334,
|
|
"loss": 5.5145,
|
|
"mean_token_accuracy": 0.1940144568681717,
|
|
"num_tokens": 71770151.0,
|
|
"step": 36680
|
|
},
|
|
{
|
|
"entropy": 5.89086389541626,
|
|
"epoch": 3.6670665267156495,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00037058586554172834,
|
|
"loss": 5.4147,
|
|
"mean_token_accuracy": 0.1993902251124382,
|
|
"num_tokens": 71780435.0,
|
|
"step": 36685
|
|
},
|
|
{
|
|
"entropy": 5.923269939422608,
|
|
"epoch": 3.667566351776878,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00037055355588820746,
|
|
"loss": 5.5191,
|
|
"mean_token_accuracy": 0.19304763078689574,
|
|
"num_tokens": 71790782.0,
|
|
"step": 36690
|
|
},
|
|
{
|
|
"entropy": 5.943858957290649,
|
|
"epoch": 3.6680661768381064,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0003705212438305837,
|
|
"loss": 5.4612,
|
|
"mean_token_accuracy": 0.19375374913215637,
|
|
"num_tokens": 71800166.0,
|
|
"step": 36695
|
|
},
|
|
{
|
|
"entropy": 5.955493831634522,
|
|
"epoch": 3.668566001899335,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0003704889293696701,
|
|
"loss": 5.4944,
|
|
"mean_token_accuracy": 0.19238533526659013,
|
|
"num_tokens": 71810344.0,
|
|
"step": 36700
|
|
},
|
|
{
|
|
"entropy": 5.890170955657959,
|
|
"epoch": 3.669065826960564,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00037045661250627955,
|
|
"loss": 5.4707,
|
|
"mean_token_accuracy": 0.19674754291772842,
|
|
"num_tokens": 71819289.0,
|
|
"step": 36705
|
|
},
|
|
{
|
|
"entropy": 5.955357646942138,
|
|
"epoch": 3.6695656520217925,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0003704242932412252,
|
|
"loss": 5.4712,
|
|
"mean_token_accuracy": 0.19745474606752395,
|
|
"num_tokens": 71829287.0,
|
|
"step": 36710
|
|
},
|
|
{
|
|
"entropy": 5.982674169540405,
|
|
"epoch": 3.6700654770830208,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00037039197157532017,
|
|
"loss": 5.4945,
|
|
"mean_token_accuracy": 0.19105600863695144,
|
|
"num_tokens": 71838598.0,
|
|
"step": 36715
|
|
},
|
|
{
|
|
"entropy": 5.933334922790527,
|
|
"epoch": 3.6705653021442495,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0003703596475093776,
|
|
"loss": 5.4297,
|
|
"mean_token_accuracy": 0.19877131432294845,
|
|
"num_tokens": 71848655.0,
|
|
"step": 36720
|
|
},
|
|
{
|
|
"entropy": 5.87599196434021,
|
|
"epoch": 3.671065127205478,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00037032732104421096,
|
|
"loss": 5.4238,
|
|
"mean_token_accuracy": 0.20171120166778564,
|
|
"num_tokens": 71858328.0,
|
|
"step": 36725
|
|
},
|
|
{
|
|
"entropy": 5.779014253616333,
|
|
"epoch": 3.6715649522667064,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00037029499218063346,
|
|
"loss": 5.3331,
|
|
"mean_token_accuracy": 0.19925537556409836,
|
|
"num_tokens": 71868119.0,
|
|
"step": 36730
|
|
},
|
|
{
|
|
"entropy": 5.858573961257934,
|
|
"epoch": 3.672064777327935,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00037026266091945843,
|
|
"loss": 5.3442,
|
|
"mean_token_accuracy": 0.21025677770376205,
|
|
"num_tokens": 71877486.0,
|
|
"step": 36735
|
|
},
|
|
{
|
|
"entropy": 5.876883220672608,
|
|
"epoch": 3.672564602389164,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0003702303272614994,
|
|
"loss": 5.374,
|
|
"mean_token_accuracy": 0.20716897398233414,
|
|
"num_tokens": 71888078.0,
|
|
"step": 36740
|
|
},
|
|
{
|
|
"entropy": 5.947955179214477,
|
|
"epoch": 3.6730644274503925,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0003701979912075698,
|
|
"loss": 5.4404,
|
|
"mean_token_accuracy": 0.20117010474205016,
|
|
"num_tokens": 71897217.0,
|
|
"step": 36745
|
|
},
|
|
{
|
|
"entropy": 5.875837135314941,
|
|
"epoch": 3.6735642525116208,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0003701656527584832,
|
|
"loss": 5.3679,
|
|
"mean_token_accuracy": 0.20704882442951203,
|
|
"num_tokens": 71905619.0,
|
|
"step": 36750
|
|
},
|
|
{
|
|
"entropy": 5.917196321487427,
|
|
"epoch": 3.6740640775728495,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0003701333119150534,
|
|
"loss": 5.5037,
|
|
"mean_token_accuracy": 0.18442580252885818,
|
|
"num_tokens": 71917197.0,
|
|
"step": 36755
|
|
},
|
|
{
|
|
"entropy": 5.885432529449463,
|
|
"epoch": 3.674563902634078,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00037010096867809384,
|
|
"loss": 5.3384,
|
|
"mean_token_accuracy": 0.21393146961927414,
|
|
"num_tokens": 71928601.0,
|
|
"step": 36760
|
|
},
|
|
{
|
|
"entropy": 5.948820304870606,
|
|
"epoch": 3.6750637276953064,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00037006862304841845,
|
|
"loss": 5.4052,
|
|
"mean_token_accuracy": 0.2002149984240532,
|
|
"num_tokens": 71938490.0,
|
|
"step": 36765
|
|
},
|
|
{
|
|
"entropy": 5.876509809494019,
|
|
"epoch": 3.675563552756535,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0003700362750268409,
|
|
"loss": 5.379,
|
|
"mean_token_accuracy": 0.20630409568548203,
|
|
"num_tokens": 71947998.0,
|
|
"step": 36770
|
|
},
|
|
{
|
|
"entropy": 5.9336120128631595,
|
|
"epoch": 3.676063377817764,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0003700039246141752,
|
|
"loss": 5.4939,
|
|
"mean_token_accuracy": 0.19725125432014465,
|
|
"num_tokens": 71958839.0,
|
|
"step": 36775
|
|
},
|
|
{
|
|
"entropy": 5.816559267044068,
|
|
"epoch": 3.6765632028789925,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0003699715718112351,
|
|
"loss": 5.3817,
|
|
"mean_token_accuracy": 0.2010641247034073,
|
|
"num_tokens": 71968296.0,
|
|
"step": 36780
|
|
},
|
|
{
|
|
"entropy": 6.03801121711731,
|
|
"epoch": 3.6770630279402208,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00036993921661883475,
|
|
"loss": 5.503,
|
|
"mean_token_accuracy": 0.19205492436885835,
|
|
"num_tokens": 71978246.0,
|
|
"step": 36785
|
|
},
|
|
{
|
|
"entropy": 6.012359523773194,
|
|
"epoch": 3.6775628530014495,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00036990685903778815,
|
|
"loss": 5.5349,
|
|
"mean_token_accuracy": 0.19424243420362472,
|
|
"num_tokens": 71988101.0,
|
|
"step": 36790
|
|
},
|
|
{
|
|
"entropy": 5.9261109828948975,
|
|
"epoch": 3.678062678062678,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00036987449906890937,
|
|
"loss": 5.3932,
|
|
"mean_token_accuracy": 0.20595365315675734,
|
|
"num_tokens": 71998000.0,
|
|
"step": 36795
|
|
},
|
|
{
|
|
"entropy": 5.850264692306519,
|
|
"epoch": 3.6785625031239064,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00036984213671301266,
|
|
"loss": 5.299,
|
|
"mean_token_accuracy": 0.20407790541648865,
|
|
"num_tokens": 72007438.0,
|
|
"step": 36800
|
|
},
|
|
{
|
|
"entropy": 5.934997797012329,
|
|
"epoch": 3.679062328185135,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00036980977197091213,
|
|
"loss": 5.5808,
|
|
"mean_token_accuracy": 0.19234393537044525,
|
|
"num_tokens": 72017995.0,
|
|
"step": 36805
|
|
},
|
|
{
|
|
"entropy": 5.853705024719238,
|
|
"epoch": 3.679562153246364,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00036977740484342214,
|
|
"loss": 5.4259,
|
|
"mean_token_accuracy": 0.19979346841573714,
|
|
"num_tokens": 72027289.0,
|
|
"step": 36810
|
|
},
|
|
{
|
|
"entropy": 5.826716947555542,
|
|
"epoch": 3.6800619783075925,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0003697450353313571,
|
|
"loss": 5.311,
|
|
"mean_token_accuracy": 0.211357681453228,
|
|
"num_tokens": 72036721.0,
|
|
"step": 36815
|
|
},
|
|
{
|
|
"entropy": 5.911601305007935,
|
|
"epoch": 3.6805618033688208,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0003697126634355313,
|
|
"loss": 5.4388,
|
|
"mean_token_accuracy": 0.19697387814521788,
|
|
"num_tokens": 72046760.0,
|
|
"step": 36820
|
|
},
|
|
{
|
|
"entropy": 5.96556077003479,
|
|
"epoch": 3.6810616284300495,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00036968028915675924,
|
|
"loss": 5.4856,
|
|
"mean_token_accuracy": 0.19277264028787613,
|
|
"num_tokens": 72056285.0,
|
|
"step": 36825
|
|
},
|
|
{
|
|
"entropy": 5.948189449310303,
|
|
"epoch": 3.681561453491278,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0003696479124958555,
|
|
"loss": 5.4932,
|
|
"mean_token_accuracy": 0.18925540000200272,
|
|
"num_tokens": 72067082.0,
|
|
"step": 36830
|
|
},
|
|
{
|
|
"entropy": 5.933656501770019,
|
|
"epoch": 3.6820612785525064,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0003696155334536346,
|
|
"loss": 5.3968,
|
|
"mean_token_accuracy": 0.19974917322397232,
|
|
"num_tokens": 72077203.0,
|
|
"step": 36835
|
|
},
|
|
{
|
|
"entropy": 5.973536252975464,
|
|
"epoch": 3.682561103613735,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0003695831520309113,
|
|
"loss": 5.597,
|
|
"mean_token_accuracy": 0.1854213997721672,
|
|
"num_tokens": 72086669.0,
|
|
"step": 36840
|
|
},
|
|
{
|
|
"entropy": 5.927193593978882,
|
|
"epoch": 3.683060928674964,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00036955076822850014,
|
|
"loss": 5.4343,
|
|
"mean_token_accuracy": 0.1932585582137108,
|
|
"num_tokens": 72097752.0,
|
|
"step": 36845
|
|
},
|
|
{
|
|
"entropy": 5.938465785980225,
|
|
"epoch": 3.6835607537361925,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00036951838204721607,
|
|
"loss": 5.4343,
|
|
"mean_token_accuracy": 0.19953548312187194,
|
|
"num_tokens": 72107446.0,
|
|
"step": 36850
|
|
},
|
|
{
|
|
"entropy": 5.897481489181518,
|
|
"epoch": 3.6840605787974208,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00036948599348787375,
|
|
"loss": 5.392,
|
|
"mean_token_accuracy": 0.20160798877477645,
|
|
"num_tokens": 72117099.0,
|
|
"step": 36855
|
|
},
|
|
{
|
|
"entropy": 5.890657234191894,
|
|
"epoch": 3.6845604038586495,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00036945360255128816,
|
|
"loss": 5.4194,
|
|
"mean_token_accuracy": 0.19288410991430283,
|
|
"num_tokens": 72126472.0,
|
|
"step": 36860
|
|
},
|
|
{
|
|
"entropy": 5.96768159866333,
|
|
"epoch": 3.685060228919878,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00036942120923827426,
|
|
"loss": 5.4986,
|
|
"mean_token_accuracy": 0.1975233346223831,
|
|
"num_tokens": 72135910.0,
|
|
"step": 36865
|
|
},
|
|
{
|
|
"entropy": 5.9186547756195065,
|
|
"epoch": 3.6855600539811064,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00036938881354964704,
|
|
"loss": 5.445,
|
|
"mean_token_accuracy": 0.20064194202423097,
|
|
"num_tokens": 72145173.0,
|
|
"step": 36870
|
|
},
|
|
{
|
|
"entropy": 5.878488683700562,
|
|
"epoch": 3.686059879042335,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00036935641548622154,
|
|
"loss": 5.4261,
|
|
"mean_token_accuracy": 0.19789824783802032,
|
|
"num_tokens": 72154930.0,
|
|
"step": 36875
|
|
},
|
|
{
|
|
"entropy": 5.828638410568237,
|
|
"epoch": 3.686559704103564,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0003693240150488129,
|
|
"loss": 5.2708,
|
|
"mean_token_accuracy": 0.2081148147583008,
|
|
"num_tokens": 72165221.0,
|
|
"step": 36880
|
|
},
|
|
{
|
|
"entropy": 5.867763185501099,
|
|
"epoch": 3.6870595291647925,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0003692916122382364,
|
|
"loss": 5.4096,
|
|
"mean_token_accuracy": 0.19550271332263947,
|
|
"num_tokens": 72175532.0,
|
|
"step": 36885
|
|
},
|
|
{
|
|
"entropy": 5.932864856719971,
|
|
"epoch": 3.6875593542260208,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00036925920705530713,
|
|
"loss": 5.4993,
|
|
"mean_token_accuracy": 0.18557946234941483,
|
|
"num_tokens": 72185588.0,
|
|
"step": 36890
|
|
},
|
|
{
|
|
"entropy": 5.897397232055664,
|
|
"epoch": 3.6880591792872495,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00036922679950084043,
|
|
"loss": 5.452,
|
|
"mean_token_accuracy": 0.195526359975338,
|
|
"num_tokens": 72196051.0,
|
|
"step": 36895
|
|
},
|
|
{
|
|
"entropy": 5.970999240875244,
|
|
"epoch": 3.688559004348478,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0003691943895756518,
|
|
"loss": 5.5228,
|
|
"mean_token_accuracy": 0.19598030745983125,
|
|
"num_tokens": 72207530.0,
|
|
"step": 36900
|
|
},
|
|
{
|
|
"entropy": 5.9654374599456785,
|
|
"epoch": 3.6890588294097064,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00036916197728055646,
|
|
"loss": 5.4648,
|
|
"mean_token_accuracy": 0.19369197636842728,
|
|
"num_tokens": 72217764.0,
|
|
"step": 36905
|
|
},
|
|
{
|
|
"entropy": 5.8938984870910645,
|
|
"epoch": 3.689558654470935,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00036912956261637005,
|
|
"loss": 5.3382,
|
|
"mean_token_accuracy": 0.21135512888431549,
|
|
"num_tokens": 72226971.0,
|
|
"step": 36910
|
|
},
|
|
{
|
|
"entropy": 5.955629444122314,
|
|
"epoch": 3.690058479532164,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0003690971455839081,
|
|
"loss": 5.5269,
|
|
"mean_token_accuracy": 0.19973358660936355,
|
|
"num_tokens": 72236045.0,
|
|
"step": 36915
|
|
},
|
|
{
|
|
"entropy": 5.993536949157715,
|
|
"epoch": 3.6905583045933925,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00036906472618398605,
|
|
"loss": 5.515,
|
|
"mean_token_accuracy": 0.18456605225801467,
|
|
"num_tokens": 72246150.0,
|
|
"step": 36920
|
|
},
|
|
{
|
|
"entropy": 5.927529621124267,
|
|
"epoch": 3.6910581296546208,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00036903230441741986,
|
|
"loss": 5.3915,
|
|
"mean_token_accuracy": 0.1985076442360878,
|
|
"num_tokens": 72254916.0,
|
|
"step": 36925
|
|
},
|
|
{
|
|
"entropy": 5.92929220199585,
|
|
"epoch": 3.6915579547158495,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00036899988028502495,
|
|
"loss": 5.4874,
|
|
"mean_token_accuracy": 0.194769549369812,
|
|
"num_tokens": 72265104.0,
|
|
"step": 36930
|
|
},
|
|
{
|
|
"entropy": 5.94810380935669,
|
|
"epoch": 3.692057779777078,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00036896745378761734,
|
|
"loss": 5.4777,
|
|
"mean_token_accuracy": 0.19996136128902436,
|
|
"num_tokens": 72274899.0,
|
|
"step": 36935
|
|
},
|
|
{
|
|
"entropy": 5.947926425933838,
|
|
"epoch": 3.6925576048383064,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00036893502492601273,
|
|
"loss": 5.4254,
|
|
"mean_token_accuracy": 0.19460831135511397,
|
|
"num_tokens": 72285618.0,
|
|
"step": 36940
|
|
},
|
|
{
|
|
"entropy": 5.954575252532959,
|
|
"epoch": 3.693057429899535,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0003689025937010271,
|
|
"loss": 5.4156,
|
|
"mean_token_accuracy": 0.19945402890443803,
|
|
"num_tokens": 72294943.0,
|
|
"step": 36945
|
|
},
|
|
{
|
|
"entropy": 5.873834133148193,
|
|
"epoch": 3.693557254960764,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00036887016011347633,
|
|
"loss": 5.3912,
|
|
"mean_token_accuracy": 0.20111304968595506,
|
|
"num_tokens": 72304908.0,
|
|
"step": 36950
|
|
},
|
|
{
|
|
"entropy": 5.880606555938721,
|
|
"epoch": 3.6940570800219925,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0003688377241641765,
|
|
"loss": 5.407,
|
|
"mean_token_accuracy": 0.20094767212867737,
|
|
"num_tokens": 72314646.0,
|
|
"step": 36955
|
|
},
|
|
{
|
|
"entropy": 5.996635007858276,
|
|
"epoch": 3.6945569050832208,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00036880528585394364,
|
|
"loss": 5.4818,
|
|
"mean_token_accuracy": 0.19935799688100814,
|
|
"num_tokens": 72324329.0,
|
|
"step": 36960
|
|
},
|
|
{
|
|
"entropy": 5.971225786209106,
|
|
"epoch": 3.6950567301444495,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.000368772845183594,
|
|
"loss": 5.4911,
|
|
"mean_token_accuracy": 0.19836924225091934,
|
|
"num_tokens": 72333201.0,
|
|
"step": 36965
|
|
},
|
|
{
|
|
"entropy": 5.887076139450073,
|
|
"epoch": 3.695556555205678,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00036874040215394366,
|
|
"loss": 5.3849,
|
|
"mean_token_accuracy": 0.20863622725009917,
|
|
"num_tokens": 72343922.0,
|
|
"step": 36970
|
|
},
|
|
{
|
|
"entropy": 6.0018058776855465,
|
|
"epoch": 3.6960563802669064,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00036870795676580885,
|
|
"loss": 5.5484,
|
|
"mean_token_accuracy": 0.18794349431991578,
|
|
"num_tokens": 72354081.0,
|
|
"step": 36975
|
|
},
|
|
{
|
|
"entropy": 5.893040990829467,
|
|
"epoch": 3.696556205328135,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0003686755090200061,
|
|
"loss": 5.4311,
|
|
"mean_token_accuracy": 0.19522782862186433,
|
|
"num_tokens": 72363646.0,
|
|
"step": 36980
|
|
},
|
|
{
|
|
"entropy": 5.912151193618774,
|
|
"epoch": 3.697056030389364,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0003686430589173516,
|
|
"loss": 5.4713,
|
|
"mean_token_accuracy": 0.18987156003713607,
|
|
"num_tokens": 72373847.0,
|
|
"step": 36985
|
|
},
|
|
{
|
|
"entropy": 5.920148181915283,
|
|
"epoch": 3.6975558554505925,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00036861060645866184,
|
|
"loss": 5.2794,
|
|
"mean_token_accuracy": 0.20749632120132447,
|
|
"num_tokens": 72382991.0,
|
|
"step": 36990
|
|
},
|
|
{
|
|
"entropy": 5.876805591583252,
|
|
"epoch": 3.6980556805118208,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0003685781516447533,
|
|
"loss": 5.3822,
|
|
"mean_token_accuracy": 0.20046328008174896,
|
|
"num_tokens": 72392260.0,
|
|
"step": 36995
|
|
},
|
|
{
|
|
"entropy": 5.953722524642944,
|
|
"epoch": 3.6985555055730495,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0003685456944764425,
|
|
"loss": 5.4969,
|
|
"mean_token_accuracy": 0.18677756190299988,
|
|
"num_tokens": 72401542.0,
|
|
"step": 37000
|
|
},
|
|
{
|
|
"entropy": 5.9922287940979,
|
|
"epoch": 3.699055330634278,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00036851323495454616,
|
|
"loss": 5.5694,
|
|
"mean_token_accuracy": 0.19127267450094224,
|
|
"num_tokens": 72412690.0,
|
|
"step": 37005
|
|
},
|
|
{
|
|
"entropy": 5.894913625717163,
|
|
"epoch": 3.6995551556955064,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00036848077307988084,
|
|
"loss": 5.4172,
|
|
"mean_token_accuracy": 0.20429878830909728,
|
|
"num_tokens": 72421925.0,
|
|
"step": 37010
|
|
},
|
|
{
|
|
"entropy": 5.876536703109741,
|
|
"epoch": 3.700054980756735,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00036844830885326334,
|
|
"loss": 5.4083,
|
|
"mean_token_accuracy": 0.19418491125106813,
|
|
"num_tokens": 72432252.0,
|
|
"step": 37015
|
|
},
|
|
{
|
|
"entropy": 5.958055639266968,
|
|
"epoch": 3.700554805817964,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00036841584227551043,
|
|
"loss": 5.4656,
|
|
"mean_token_accuracy": 0.19811100214719773,
|
|
"num_tokens": 72441210.0,
|
|
"step": 37020
|
|
},
|
|
{
|
|
"entropy": 5.9052793979644775,
|
|
"epoch": 3.7010546308791925,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000368383373347439,
|
|
"loss": 5.42,
|
|
"mean_token_accuracy": 0.19802291542291642,
|
|
"num_tokens": 72450570.0,
|
|
"step": 37025
|
|
},
|
|
{
|
|
"entropy": 5.920838356018066,
|
|
"epoch": 3.7015544559404208,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00036835090206986594,
|
|
"loss": 5.4634,
|
|
"mean_token_accuracy": 0.19204154014587402,
|
|
"num_tokens": 72460597.0,
|
|
"step": 37030
|
|
},
|
|
{
|
|
"entropy": 5.952597761154175,
|
|
"epoch": 3.7020542810016495,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00036831842844360814,
|
|
"loss": 5.4941,
|
|
"mean_token_accuracy": 0.19100959450006486,
|
|
"num_tokens": 72471232.0,
|
|
"step": 37035
|
|
},
|
|
{
|
|
"entropy": 5.903926038742066,
|
|
"epoch": 3.702554106062878,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0003682859524694827,
|
|
"loss": 5.3794,
|
|
"mean_token_accuracy": 0.20260900557041167,
|
|
"num_tokens": 72480547.0,
|
|
"step": 37040
|
|
},
|
|
{
|
|
"entropy": 5.85078797340393,
|
|
"epoch": 3.7030539311241064,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00036825347414830674,
|
|
"loss": 5.3497,
|
|
"mean_token_accuracy": 0.20335743129253386,
|
|
"num_tokens": 72490507.0,
|
|
"step": 37045
|
|
},
|
|
{
|
|
"entropy": 5.889937973022461,
|
|
"epoch": 3.703553756185335,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00036822099348089737,
|
|
"loss": 5.4556,
|
|
"mean_token_accuracy": 0.19892672300338746,
|
|
"num_tokens": 72499651.0,
|
|
"step": 37050
|
|
},
|
|
{
|
|
"entropy": 5.88638858795166,
|
|
"epoch": 3.704053581246564,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00036818851046807176,
|
|
"loss": 5.4174,
|
|
"mean_token_accuracy": 0.19822971671819686,
|
|
"num_tokens": 72509580.0,
|
|
"step": 37055
|
|
},
|
|
{
|
|
"entropy": 5.882008695602417,
|
|
"epoch": 3.7045534063077925,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00036815602511064725,
|
|
"loss": 5.3894,
|
|
"mean_token_accuracy": 0.19918327927589416,
|
|
"num_tokens": 72519184.0,
|
|
"step": 37060
|
|
},
|
|
{
|
|
"entropy": 5.872717761993409,
|
|
"epoch": 3.7050532313690208,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00036812353740944104,
|
|
"loss": 5.4173,
|
|
"mean_token_accuracy": 0.19983880668878556,
|
|
"num_tokens": 72528112.0,
|
|
"step": 37065
|
|
},
|
|
{
|
|
"entropy": 5.955219793319702,
|
|
"epoch": 3.7055530564302495,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00036809104736527064,
|
|
"loss": 5.5134,
|
|
"mean_token_accuracy": 0.19143061339855194,
|
|
"num_tokens": 72537197.0,
|
|
"step": 37070
|
|
},
|
|
{
|
|
"entropy": 5.9560822486877445,
|
|
"epoch": 3.7060528814914777,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00036805855497895346,
|
|
"loss": 5.542,
|
|
"mean_token_accuracy": 0.18901809304952621,
|
|
"num_tokens": 72547443.0,
|
|
"step": 37075
|
|
},
|
|
{
|
|
"entropy": 5.960722589492798,
|
|
"epoch": 3.7065527065527064,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00036802606025130696,
|
|
"loss": 5.4134,
|
|
"mean_token_accuracy": 0.19643639028072357,
|
|
"num_tokens": 72556741.0,
|
|
"step": 37080
|
|
},
|
|
{
|
|
"entropy": 5.902273464202881,
|
|
"epoch": 3.707052531613935,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0003679935631831488,
|
|
"loss": 5.4703,
|
|
"mean_token_accuracy": 0.19613355845212938,
|
|
"num_tokens": 72567448.0,
|
|
"step": 37085
|
|
},
|
|
{
|
|
"entropy": 5.876287364959717,
|
|
"epoch": 3.707552356675164,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00036796106377529644,
|
|
"loss": 5.4411,
|
|
"mean_token_accuracy": 0.19430944472551345,
|
|
"num_tokens": 72577433.0,
|
|
"step": 37090
|
|
},
|
|
{
|
|
"entropy": 5.942993211746216,
|
|
"epoch": 3.7080521817363925,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0003679285620285676,
|
|
"loss": 5.4395,
|
|
"mean_token_accuracy": 0.20300710052251816,
|
|
"num_tokens": 72587754.0,
|
|
"step": 37095
|
|
},
|
|
{
|
|
"entropy": 5.913302230834961,
|
|
"epoch": 3.7085520067976208,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00036789605794378013,
|
|
"loss": 5.3733,
|
|
"mean_token_accuracy": 0.1994330480694771,
|
|
"num_tokens": 72596333.0,
|
|
"step": 37100
|
|
},
|
|
{
|
|
"entropy": 5.948376321792603,
|
|
"epoch": 3.7090518318588495,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00036786355152175173,
|
|
"loss": 5.4979,
|
|
"mean_token_accuracy": 0.1952742651104927,
|
|
"num_tokens": 72605813.0,
|
|
"step": 37105
|
|
},
|
|
{
|
|
"entropy": 5.862094163894653,
|
|
"epoch": 3.7095516569200777,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0003678310427633003,
|
|
"loss": 5.4609,
|
|
"mean_token_accuracy": 0.19675320535898208,
|
|
"num_tokens": 72615435.0,
|
|
"step": 37110
|
|
},
|
|
{
|
|
"entropy": 5.934744644165039,
|
|
"epoch": 3.7100514819813064,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00036779853166924353,
|
|
"loss": 5.4679,
|
|
"mean_token_accuracy": 0.19743644297122956,
|
|
"num_tokens": 72625276.0,
|
|
"step": 37115
|
|
},
|
|
{
|
|
"entropy": 5.876795864105224,
|
|
"epoch": 3.710551307042535,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0003677660182403998,
|
|
"loss": 5.3038,
|
|
"mean_token_accuracy": 0.20676542818546295,
|
|
"num_tokens": 72634225.0,
|
|
"step": 37120
|
|
},
|
|
{
|
|
"entropy": 5.877161312103271,
|
|
"epoch": 3.711051132103764,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00036773350247758685,
|
|
"loss": 5.3857,
|
|
"mean_token_accuracy": 0.20737158358097077,
|
|
"num_tokens": 72644133.0,
|
|
"step": 37125
|
|
},
|
|
{
|
|
"entropy": 5.946097707748413,
|
|
"epoch": 3.7115509571649925,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0003677009843816228,
|
|
"loss": 5.4442,
|
|
"mean_token_accuracy": 0.1977183222770691,
|
|
"num_tokens": 72653758.0,
|
|
"step": 37130
|
|
},
|
|
{
|
|
"entropy": 5.935758781433106,
|
|
"epoch": 3.7120507822262208,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0003676684639533259,
|
|
"loss": 5.483,
|
|
"mean_token_accuracy": 0.19373213201761247,
|
|
"num_tokens": 72664049.0,
|
|
"step": 37135
|
|
},
|
|
{
|
|
"entropy": 5.971741962432861,
|
|
"epoch": 3.7125506072874495,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0003676359411935143,
|
|
"loss": 5.5066,
|
|
"mean_token_accuracy": 0.1938013657927513,
|
|
"num_tokens": 72673419.0,
|
|
"step": 37140
|
|
},
|
|
{
|
|
"entropy": 5.873705625534058,
|
|
"epoch": 3.7130504323486777,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0003676034161030062,
|
|
"loss": 5.3612,
|
|
"mean_token_accuracy": 0.2034209430217743,
|
|
"num_tokens": 72682392.0,
|
|
"step": 37145
|
|
},
|
|
{
|
|
"entropy": 5.9066259384155275,
|
|
"epoch": 3.7135502574099064,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00036757088868262,
|
|
"loss": 5.4892,
|
|
"mean_token_accuracy": 0.19667861759662628,
|
|
"num_tokens": 72692092.0,
|
|
"step": 37150
|
|
},
|
|
{
|
|
"entropy": 5.952124786376953,
|
|
"epoch": 3.714050082471135,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00036753835893317413,
|
|
"loss": 5.5128,
|
|
"mean_token_accuracy": 0.1940167263150215,
|
|
"num_tokens": 72700098.0,
|
|
"step": 37155
|
|
},
|
|
{
|
|
"entropy": 5.9249097347259525,
|
|
"epoch": 3.714549907532364,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0003675058268554868,
|
|
"loss": 5.3842,
|
|
"mean_token_accuracy": 0.19681847095489502,
|
|
"num_tokens": 72709443.0,
|
|
"step": 37160
|
|
},
|
|
{
|
|
"entropy": 6.013835620880127,
|
|
"epoch": 3.7150497325935925,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0003674732924503768,
|
|
"loss": 5.6219,
|
|
"mean_token_accuracy": 0.18823485374450682,
|
|
"num_tokens": 72718849.0,
|
|
"step": 37165
|
|
},
|
|
{
|
|
"entropy": 6.049854278564453,
|
|
"epoch": 3.7155495576548208,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0003674407557186625,
|
|
"loss": 5.476,
|
|
"mean_token_accuracy": 0.1899016886949539,
|
|
"num_tokens": 72728414.0,
|
|
"step": 37170
|
|
},
|
|
{
|
|
"entropy": 5.903722476959229,
|
|
"epoch": 3.7160493827160495,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00036740821666116265,
|
|
"loss": 5.3557,
|
|
"mean_token_accuracy": 0.2139686018228531,
|
|
"num_tokens": 72736432.0,
|
|
"step": 37175
|
|
},
|
|
{
|
|
"entropy": 5.675520706176758,
|
|
"epoch": 3.7165492077772777,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0003673756752786958,
|
|
"loss": 5.2854,
|
|
"mean_token_accuracy": 0.20464946329593658,
|
|
"num_tokens": 72745630.0,
|
|
"step": 37180
|
|
},
|
|
{
|
|
"entropy": 5.877851104736328,
|
|
"epoch": 3.7170490328385064,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00036734313157208066,
|
|
"loss": 5.4557,
|
|
"mean_token_accuracy": 0.19972522258758546,
|
|
"num_tokens": 72755590.0,
|
|
"step": 37185
|
|
},
|
|
{
|
|
"entropy": 5.935886478424072,
|
|
"epoch": 3.717548857899735,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0003673105855421362,
|
|
"loss": 5.3806,
|
|
"mean_token_accuracy": 0.19998735040426255,
|
|
"num_tokens": 72765187.0,
|
|
"step": 37190
|
|
},
|
|
{
|
|
"entropy": 5.845800542831421,
|
|
"epoch": 3.718048682960964,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0003672780371896811,
|
|
"loss": 5.3279,
|
|
"mean_token_accuracy": 0.20427443236112594,
|
|
"num_tokens": 72775306.0,
|
|
"step": 37195
|
|
},
|
|
{
|
|
"entropy": 5.905604887008667,
|
|
"epoch": 3.7185485080221925,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00036724548651553433,
|
|
"loss": 5.4493,
|
|
"mean_token_accuracy": 0.19882710874080659,
|
|
"num_tokens": 72784616.0,
|
|
"step": 37200
|
|
},
|
|
{
|
|
"entropy": 5.895833444595337,
|
|
"epoch": 3.7190483330834208,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00036721293352051486,
|
|
"loss": 5.3912,
|
|
"mean_token_accuracy": 0.20361107140779494,
|
|
"num_tokens": 72794220.0,
|
|
"step": 37205
|
|
},
|
|
{
|
|
"entropy": 5.998435163497925,
|
|
"epoch": 3.7195481581446495,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0003671803782054418,
|
|
"loss": 5.6064,
|
|
"mean_token_accuracy": 0.1810755729675293,
|
|
"num_tokens": 72804364.0,
|
|
"step": 37210
|
|
},
|
|
{
|
|
"entropy": 5.9032224178314205,
|
|
"epoch": 3.7200479832058777,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000367147820571134,
|
|
"loss": 5.4102,
|
|
"mean_token_accuracy": 0.2046579122543335,
|
|
"num_tokens": 72814572.0,
|
|
"step": 37215
|
|
},
|
|
{
|
|
"entropy": 5.818304347991943,
|
|
"epoch": 3.7205478082671064,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00036711526061841086,
|
|
"loss": 5.2881,
|
|
"mean_token_accuracy": 0.20816614031791686,
|
|
"num_tokens": 72825249.0,
|
|
"step": 37220
|
|
},
|
|
{
|
|
"entropy": 5.98826847076416,
|
|
"epoch": 3.721047633328335,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0003670826983480914,
|
|
"loss": 5.5785,
|
|
"mean_token_accuracy": 0.1826557531952858,
|
|
"num_tokens": 72835525.0,
|
|
"step": 37225
|
|
},
|
|
{
|
|
"entropy": 5.96145281791687,
|
|
"epoch": 3.721547458389564,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00036705013376099496,
|
|
"loss": 5.4882,
|
|
"mean_token_accuracy": 0.19312144219875335,
|
|
"num_tokens": 72845973.0,
|
|
"step": 37230
|
|
},
|
|
{
|
|
"entropy": 5.959549045562744,
|
|
"epoch": 3.7220472834507925,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0003670175668579409,
|
|
"loss": 5.4645,
|
|
"mean_token_accuracy": 0.19943243116140366,
|
|
"num_tokens": 72855650.0,
|
|
"step": 37235
|
|
},
|
|
{
|
|
"entropy": 5.903789806365967,
|
|
"epoch": 3.7225471085120208,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0003669849976397484,
|
|
"loss": 5.4292,
|
|
"mean_token_accuracy": 0.19914090037345886,
|
|
"num_tokens": 72865798.0,
|
|
"step": 37240
|
|
},
|
|
{
|
|
"entropy": 5.845339250564575,
|
|
"epoch": 3.7230469335732495,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0003669524261072371,
|
|
"loss": 5.427,
|
|
"mean_token_accuracy": 0.2045523464679718,
|
|
"num_tokens": 72875536.0,
|
|
"step": 37245
|
|
},
|
|
{
|
|
"entropy": 5.830274486541748,
|
|
"epoch": 3.7235467586344777,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0003669198522612265,
|
|
"loss": 5.3632,
|
|
"mean_token_accuracy": 0.19810008257627487,
|
|
"num_tokens": 72886134.0,
|
|
"step": 37250
|
|
},
|
|
{
|
|
"entropy": 6.008238506317139,
|
|
"epoch": 3.7240465836957064,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00036688727610253595,
|
|
"loss": 5.4826,
|
|
"mean_token_accuracy": 0.19533274024724961,
|
|
"num_tokens": 72896269.0,
|
|
"step": 37255
|
|
},
|
|
{
|
|
"entropy": 5.968602705001831,
|
|
"epoch": 3.724546408756935,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0003668546976319853,
|
|
"loss": 5.3575,
|
|
"mean_token_accuracy": 0.20063167959451675,
|
|
"num_tokens": 72906528.0,
|
|
"step": 37260
|
|
},
|
|
{
|
|
"entropy": 5.903660678863526,
|
|
"epoch": 3.725046233818164,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000366822116850394,
|
|
"loss": 5.4654,
|
|
"mean_token_accuracy": 0.20234954953193665,
|
|
"num_tokens": 72915390.0,
|
|
"step": 37265
|
|
},
|
|
{
|
|
"entropy": 5.882051277160644,
|
|
"epoch": 3.725546058879392,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0003667895337585819,
|
|
"loss": 5.4317,
|
|
"mean_token_accuracy": 0.19883154779672624,
|
|
"num_tokens": 72926194.0,
|
|
"step": 37270
|
|
},
|
|
{
|
|
"entropy": 5.829296541213989,
|
|
"epoch": 3.7260458839406208,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00036675694835736875,
|
|
"loss": 5.3596,
|
|
"mean_token_accuracy": 0.1994268089532852,
|
|
"num_tokens": 72935434.0,
|
|
"step": 37275
|
|
},
|
|
{
|
|
"entropy": 5.89245491027832,
|
|
"epoch": 3.7265457090018494,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0003667243606475744,
|
|
"loss": 5.4435,
|
|
"mean_token_accuracy": 0.19754681885242462,
|
|
"num_tokens": 72944664.0,
|
|
"step": 37280
|
|
},
|
|
{
|
|
"entropy": 5.908683967590332,
|
|
"epoch": 3.7270455340630777,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00036669177063001866,
|
|
"loss": 5.4926,
|
|
"mean_token_accuracy": 0.1987003430724144,
|
|
"num_tokens": 72954213.0,
|
|
"step": 37285
|
|
},
|
|
{
|
|
"entropy": 5.904730367660522,
|
|
"epoch": 3.7275453591243064,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0003666591783055216,
|
|
"loss": 5.3564,
|
|
"mean_token_accuracy": 0.20089375227689743,
|
|
"num_tokens": 72964097.0,
|
|
"step": 37290
|
|
},
|
|
{
|
|
"entropy": 5.838534021377564,
|
|
"epoch": 3.728045184185535,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0003666265836749033,
|
|
"loss": 5.3534,
|
|
"mean_token_accuracy": 0.20637383162975312,
|
|
"num_tokens": 72973807.0,
|
|
"step": 37295
|
|
},
|
|
{
|
|
"entropy": 5.996181631088257,
|
|
"epoch": 3.728545009246764,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00036659398673898356,
|
|
"loss": 5.4954,
|
|
"mean_token_accuracy": 0.19032168835401536,
|
|
"num_tokens": 72983466.0,
|
|
"step": 37300
|
|
},
|
|
{
|
|
"entropy": 5.828741121292114,
|
|
"epoch": 3.729044834307992,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00036656138749858287,
|
|
"loss": 5.3345,
|
|
"mean_token_accuracy": 0.20983941555023194,
|
|
"num_tokens": 72992377.0,
|
|
"step": 37305
|
|
},
|
|
{
|
|
"entropy": 5.822503185272216,
|
|
"epoch": 3.7295446593692207,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00036652878595452105,
|
|
"loss": 5.4239,
|
|
"mean_token_accuracy": 0.19817618131637574,
|
|
"num_tokens": 73001699.0,
|
|
"step": 37310
|
|
},
|
|
{
|
|
"entropy": 5.816320276260376,
|
|
"epoch": 3.7300444844304494,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0003664961821076187,
|
|
"loss": 5.3807,
|
|
"mean_token_accuracy": 0.21081642657518387,
|
|
"num_tokens": 73011011.0,
|
|
"step": 37315
|
|
},
|
|
{
|
|
"entropy": 5.86040849685669,
|
|
"epoch": 3.7305443094916777,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00036646357595869586,
|
|
"loss": 5.3861,
|
|
"mean_token_accuracy": 0.21215945929288865,
|
|
"num_tokens": 73019868.0,
|
|
"step": 37320
|
|
},
|
|
{
|
|
"entropy": 5.8745499610900875,
|
|
"epoch": 3.7310441345529064,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.000366430967508573,
|
|
"loss": 5.3634,
|
|
"mean_token_accuracy": 0.2027176335453987,
|
|
"num_tokens": 73028812.0,
|
|
"step": 37325
|
|
},
|
|
{
|
|
"entropy": 5.825143051147461,
|
|
"epoch": 3.731543959614135,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0003663983567580705,
|
|
"loss": 5.3131,
|
|
"mean_token_accuracy": 0.21541768908500672,
|
|
"num_tokens": 73038138.0,
|
|
"step": 37330
|
|
},
|
|
{
|
|
"entropy": 5.92899374961853,
|
|
"epoch": 3.732043784675364,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00036636574370800887,
|
|
"loss": 5.4493,
|
|
"mean_token_accuracy": 0.19335847795009614,
|
|
"num_tokens": 73048705.0,
|
|
"step": 37335
|
|
},
|
|
{
|
|
"entropy": 5.9081096172332765,
|
|
"epoch": 3.732543609736592,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0003663331283592086,
|
|
"loss": 5.4438,
|
|
"mean_token_accuracy": 0.19966055750846862,
|
|
"num_tokens": 73058107.0,
|
|
"step": 37340
|
|
},
|
|
{
|
|
"entropy": 5.882592248916626,
|
|
"epoch": 3.7330434347978207,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00036630051071249043,
|
|
"loss": 5.3832,
|
|
"mean_token_accuracy": 0.20181644409894944,
|
|
"num_tokens": 73067869.0,
|
|
"step": 37345
|
|
},
|
|
{
|
|
"entropy": 5.875599050521851,
|
|
"epoch": 3.7335432598590494,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00036626789076867484,
|
|
"loss": 5.4228,
|
|
"mean_token_accuracy": 0.2003587394952774,
|
|
"num_tokens": 73078020.0,
|
|
"step": 37350
|
|
},
|
|
{
|
|
"entropy": 5.900698471069336,
|
|
"epoch": 3.7340430849202777,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0003662352685285826,
|
|
"loss": 5.4215,
|
|
"mean_token_accuracy": 0.19714551270008088,
|
|
"num_tokens": 73088451.0,
|
|
"step": 37355
|
|
},
|
|
{
|
|
"entropy": 5.906790828704834,
|
|
"epoch": 3.7345429099815064,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0003662026439930345,
|
|
"loss": 5.4064,
|
|
"mean_token_accuracy": 0.19530534297227858,
|
|
"num_tokens": 73098409.0,
|
|
"step": 37360
|
|
},
|
|
{
|
|
"entropy": 6.016816902160644,
|
|
"epoch": 3.735042735042735,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00036617001716285135,
|
|
"loss": 5.5259,
|
|
"mean_token_accuracy": 0.19018280804157256,
|
|
"num_tokens": 73109022.0,
|
|
"step": 37365
|
|
},
|
|
{
|
|
"entropy": 5.889622354507447,
|
|
"epoch": 3.735542560103964,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000366137388038854,
|
|
"loss": 5.4572,
|
|
"mean_token_accuracy": 0.19890487045049668,
|
|
"num_tokens": 73118585.0,
|
|
"step": 37370
|
|
},
|
|
{
|
|
"entropy": 5.918763494491577,
|
|
"epoch": 3.736042385165192,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00036610475662186343,
|
|
"loss": 5.5297,
|
|
"mean_token_accuracy": 0.19981056749820708,
|
|
"num_tokens": 73128152.0,
|
|
"step": 37375
|
|
},
|
|
{
|
|
"entropy": 5.986102676391601,
|
|
"epoch": 3.7365422102264207,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0003660721229127006,
|
|
"loss": 5.457,
|
|
"mean_token_accuracy": 0.19839480817317962,
|
|
"num_tokens": 73137103.0,
|
|
"step": 37380
|
|
},
|
|
{
|
|
"entropy": 5.918239259719849,
|
|
"epoch": 3.7370420352876494,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00036603948691218665,
|
|
"loss": 5.412,
|
|
"mean_token_accuracy": 0.19858383089303971,
|
|
"num_tokens": 73145867.0,
|
|
"step": 37385
|
|
},
|
|
{
|
|
"entropy": 5.922932100296021,
|
|
"epoch": 3.7375418603488777,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0003660068486211426,
|
|
"loss": 5.461,
|
|
"mean_token_accuracy": 0.2017269179224968,
|
|
"num_tokens": 73154381.0,
|
|
"step": 37390
|
|
},
|
|
{
|
|
"entropy": 5.854419803619384,
|
|
"epoch": 3.7380416854101064,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0003659742080403897,
|
|
"loss": 5.4339,
|
|
"mean_token_accuracy": 0.19842758178710937,
|
|
"num_tokens": 73164493.0,
|
|
"step": 37395
|
|
},
|
|
{
|
|
"entropy": 5.891550350189209,
|
|
"epoch": 3.738541510471335,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0003659415651707491,
|
|
"loss": 5.4141,
|
|
"mean_token_accuracy": 0.20040974617004395,
|
|
"num_tokens": 73174230.0,
|
|
"step": 37400
|
|
},
|
|
{
|
|
"entropy": 5.915473079681396,
|
|
"epoch": 3.739041335532564,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0003659089200130421,
|
|
"loss": 5.4004,
|
|
"mean_token_accuracy": 0.19832430481910707,
|
|
"num_tokens": 73184858.0,
|
|
"step": 37405
|
|
},
|
|
{
|
|
"entropy": 5.9407741069793705,
|
|
"epoch": 3.739541160593792,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00036587627256809,
|
|
"loss": 5.4629,
|
|
"mean_token_accuracy": 0.2056085467338562,
|
|
"num_tokens": 73194770.0,
|
|
"step": 37410
|
|
},
|
|
{
|
|
"entropy": 5.952243423461914,
|
|
"epoch": 3.7400409856550207,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0003658436228367144,
|
|
"loss": 5.382,
|
|
"mean_token_accuracy": 0.20508067756891252,
|
|
"num_tokens": 73203836.0,
|
|
"step": 37415
|
|
},
|
|
{
|
|
"entropy": 5.8733601570129395,
|
|
"epoch": 3.7405408107162494,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00036581097081973655,
|
|
"loss": 5.443,
|
|
"mean_token_accuracy": 0.19431849718093872,
|
|
"num_tokens": 73213359.0,
|
|
"step": 37420
|
|
},
|
|
{
|
|
"entropy": 5.834999418258667,
|
|
"epoch": 3.7410406357774777,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0003657783165179781,
|
|
"loss": 5.327,
|
|
"mean_token_accuracy": 0.20879416465759276,
|
|
"num_tokens": 73223064.0,
|
|
"step": 37425
|
|
},
|
|
{
|
|
"entropy": 5.92591438293457,
|
|
"epoch": 3.7415404608387064,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0003657456599322606,
|
|
"loss": 5.3906,
|
|
"mean_token_accuracy": 0.20269918143749238,
|
|
"num_tokens": 73232036.0,
|
|
"step": 37430
|
|
},
|
|
{
|
|
"entropy": 5.8624261856079105,
|
|
"epoch": 3.742040285899935,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00036571300106340553,
|
|
"loss": 5.4177,
|
|
"mean_token_accuracy": 0.20232183635234832,
|
|
"num_tokens": 73242346.0,
|
|
"step": 37435
|
|
},
|
|
{
|
|
"entropy": 5.868614339828492,
|
|
"epoch": 3.742540110961164,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00036568033991223476,
|
|
"loss": 5.371,
|
|
"mean_token_accuracy": 0.19982619285583497,
|
|
"num_tokens": 73249471.0,
|
|
"step": 37440
|
|
},
|
|
{
|
|
"entropy": 5.888575744628906,
|
|
"epoch": 3.743039936022392,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00036564767647956993,
|
|
"loss": 5.4869,
|
|
"mean_token_accuracy": 0.1923097178339958,
|
|
"num_tokens": 73258709.0,
|
|
"step": 37445
|
|
},
|
|
{
|
|
"entropy": 5.908742904663086,
|
|
"epoch": 3.7435397610836207,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0003656150107662329,
|
|
"loss": 5.3713,
|
|
"mean_token_accuracy": 0.20621506869792938,
|
|
"num_tokens": 73267432.0,
|
|
"step": 37450
|
|
},
|
|
{
|
|
"entropy": 5.930830001831055,
|
|
"epoch": 3.7440395861448494,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00036558234277304555,
|
|
"loss": 5.4935,
|
|
"mean_token_accuracy": 0.19586808383464813,
|
|
"num_tokens": 73277071.0,
|
|
"step": 37455
|
|
},
|
|
{
|
|
"entropy": 5.890607929229736,
|
|
"epoch": 3.7445394112060777,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00036554967250082977,
|
|
"loss": 5.4041,
|
|
"mean_token_accuracy": 0.19416830390691758,
|
|
"num_tokens": 73285528.0,
|
|
"step": 37460
|
|
},
|
|
{
|
|
"entropy": 5.874712419509888,
|
|
"epoch": 3.7450392362673064,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00036551699995040755,
|
|
"loss": 5.3615,
|
|
"mean_token_accuracy": 0.20537507385015488,
|
|
"num_tokens": 73294530.0,
|
|
"step": 37465
|
|
},
|
|
{
|
|
"entropy": 5.963297033309937,
|
|
"epoch": 3.745539061328535,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00036548432512260084,
|
|
"loss": 5.4882,
|
|
"mean_token_accuracy": 0.19434599280357362,
|
|
"num_tokens": 73304960.0,
|
|
"step": 37470
|
|
},
|
|
{
|
|
"entropy": 5.913380479812622,
|
|
"epoch": 3.746038886389764,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0003654516480182318,
|
|
"loss": 5.4108,
|
|
"mean_token_accuracy": 0.2027120530605316,
|
|
"num_tokens": 73314523.0,
|
|
"step": 37475
|
|
},
|
|
{
|
|
"entropy": 5.891267919540406,
|
|
"epoch": 3.746538711450992,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0003654189686381225,
|
|
"loss": 5.4414,
|
|
"mean_token_accuracy": 0.19965122044086456,
|
|
"num_tokens": 73323618.0,
|
|
"step": 37480
|
|
},
|
|
{
|
|
"entropy": 5.970777702331543,
|
|
"epoch": 3.7470385365122207,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0003653862869830953,
|
|
"loss": 5.5232,
|
|
"mean_token_accuracy": 0.1908091798424721,
|
|
"num_tokens": 73334443.0,
|
|
"step": 37485
|
|
},
|
|
{
|
|
"entropy": 5.863719081878662,
|
|
"epoch": 3.7475383615734494,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0003653536030539725,
|
|
"loss": 5.4207,
|
|
"mean_token_accuracy": 0.19602528512477874,
|
|
"num_tokens": 73344902.0,
|
|
"step": 37490
|
|
},
|
|
{
|
|
"entropy": 5.8606040477752686,
|
|
"epoch": 3.7480381866346777,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00036532091685157614,
|
|
"loss": 5.3249,
|
|
"mean_token_accuracy": 0.20908438712358474,
|
|
"num_tokens": 73354129.0,
|
|
"step": 37495
|
|
},
|
|
{
|
|
"entropy": 5.861543369293213,
|
|
"epoch": 3.7485380116959064,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00036528822837672884,
|
|
"loss": 5.323,
|
|
"mean_token_accuracy": 0.20433585345745087,
|
|
"num_tokens": 73363711.0,
|
|
"step": 37500
|
|
},
|
|
{
|
|
"entropy": 5.874893045425415,
|
|
"epoch": 3.749037836757135,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0003652555376302528,
|
|
"loss": 5.4183,
|
|
"mean_token_accuracy": 0.20054252296686173,
|
|
"num_tokens": 73372746.0,
|
|
"step": 37505
|
|
},
|
|
{
|
|
"entropy": 5.874812078475952,
|
|
"epoch": 3.749537661818364,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00036522284461297077,
|
|
"loss": 5.4113,
|
|
"mean_token_accuracy": 0.19905982911586761,
|
|
"num_tokens": 73383767.0,
|
|
"step": 37510
|
|
},
|
|
{
|
|
"entropy": 6.0121376514434814,
|
|
"epoch": 3.750037486879592,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00036519014932570517,
|
|
"loss": 5.5148,
|
|
"mean_token_accuracy": 0.19502818435430527,
|
|
"num_tokens": 73392592.0,
|
|
"step": 37515
|
|
},
|
|
{
|
|
"entropy": 5.880180168151855,
|
|
"epoch": 3.7505373119408207,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00036515745176927863,
|
|
"loss": 5.4191,
|
|
"mean_token_accuracy": 0.2018033117055893,
|
|
"num_tokens": 73401634.0,
|
|
"step": 37520
|
|
},
|
|
{
|
|
"entropy": 5.909526014328003,
|
|
"epoch": 3.7510371370020494,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0003651247519445138,
|
|
"loss": 5.3874,
|
|
"mean_token_accuracy": 0.20465926676988602,
|
|
"num_tokens": 73411086.0,
|
|
"step": 37525
|
|
},
|
|
{
|
|
"entropy": 5.923387098312378,
|
|
"epoch": 3.7515369620632777,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00036509204985223336,
|
|
"loss": 5.4871,
|
|
"mean_token_accuracy": 0.1905408263206482,
|
|
"num_tokens": 73420300.0,
|
|
"step": 37530
|
|
},
|
|
{
|
|
"entropy": 5.877337455749512,
|
|
"epoch": 3.7520367871245064,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0003650593454932602,
|
|
"loss": 5.352,
|
|
"mean_token_accuracy": 0.20739323794841766,
|
|
"num_tokens": 73429983.0,
|
|
"step": 37535
|
|
},
|
|
{
|
|
"entropy": 5.899239921569825,
|
|
"epoch": 3.752536612185735,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.000365026638868417,
|
|
"loss": 5.3761,
|
|
"mean_token_accuracy": 0.19625130891799927,
|
|
"num_tokens": 73439075.0,
|
|
"step": 37540
|
|
},
|
|
{
|
|
"entropy": 5.945751333236695,
|
|
"epoch": 3.753036437246964,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00036499392997852684,
|
|
"loss": 5.4253,
|
|
"mean_token_accuracy": 0.20047151893377305,
|
|
"num_tokens": 73448708.0,
|
|
"step": 37545
|
|
},
|
|
{
|
|
"entropy": 5.910602569580078,
|
|
"epoch": 3.753536262308192,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0003649612188244125,
|
|
"loss": 5.4964,
|
|
"mean_token_accuracy": 0.19775783121585847,
|
|
"num_tokens": 73457331.0,
|
|
"step": 37550
|
|
},
|
|
{
|
|
"entropy": 5.81986632347107,
|
|
"epoch": 3.7540360873694207,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.000364928505406897,
|
|
"loss": 5.2643,
|
|
"mean_token_accuracy": 0.20995398759841918,
|
|
"num_tokens": 73466061.0,
|
|
"step": 37555
|
|
},
|
|
{
|
|
"entropy": 5.827133560180664,
|
|
"epoch": 3.7545359124306494,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0003648957897268035,
|
|
"loss": 5.4138,
|
|
"mean_token_accuracy": 0.20310803800821303,
|
|
"num_tokens": 73477598.0,
|
|
"step": 37560
|
|
},
|
|
{
|
|
"entropy": 5.799484920501709,
|
|
"epoch": 3.7550357374918777,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0003648630717849551,
|
|
"loss": 5.2262,
|
|
"mean_token_accuracy": 0.22185556292533876,
|
|
"num_tokens": 73487453.0,
|
|
"step": 37565
|
|
},
|
|
{
|
|
"entropy": 5.94003963470459,
|
|
"epoch": 3.7555355625531064,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00036483035158217485,
|
|
"loss": 5.4867,
|
|
"mean_token_accuracy": 0.1967829018831253,
|
|
"num_tokens": 73496239.0,
|
|
"step": 37570
|
|
},
|
|
{
|
|
"entropy": 5.920931482315064,
|
|
"epoch": 3.756035387614335,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00036479762911928606,
|
|
"loss": 5.4448,
|
|
"mean_token_accuracy": 0.19778620153665544,
|
|
"num_tokens": 73506295.0,
|
|
"step": 37575
|
|
},
|
|
{
|
|
"entropy": 5.829993629455567,
|
|
"epoch": 3.756535212675564,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00036476490439711206,
|
|
"loss": 5.362,
|
|
"mean_token_accuracy": 0.21012719869613647,
|
|
"num_tokens": 73516474.0,
|
|
"step": 37580
|
|
},
|
|
{
|
|
"entropy": 5.849249935150146,
|
|
"epoch": 3.757035037736792,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0003647321774164762,
|
|
"loss": 5.2943,
|
|
"mean_token_accuracy": 0.21092111319303514,
|
|
"num_tokens": 73526141.0,
|
|
"step": 37585
|
|
},
|
|
{
|
|
"entropy": 6.010075664520263,
|
|
"epoch": 3.7575348627980207,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0003646994481782018,
|
|
"loss": 5.5579,
|
|
"mean_token_accuracy": 0.1842276230454445,
|
|
"num_tokens": 73536203.0,
|
|
"step": 37590
|
|
},
|
|
{
|
|
"entropy": 5.787912464141845,
|
|
"epoch": 3.758034687859249,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0003646667166831124,
|
|
"loss": 5.2517,
|
|
"mean_token_accuracy": 0.2194826915860176,
|
|
"num_tokens": 73545785.0,
|
|
"step": 37595
|
|
},
|
|
{
|
|
"entropy": 5.867824602127075,
|
|
"epoch": 3.7585345129204777,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0003646339829320315,
|
|
"loss": 5.3577,
|
|
"mean_token_accuracy": 0.19828973710536957,
|
|
"num_tokens": 73554736.0,
|
|
"step": 37600
|
|
},
|
|
{
|
|
"entropy": 5.897922325134277,
|
|
"epoch": 3.7590343379817064,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0003646012469257826,
|
|
"loss": 5.3989,
|
|
"mean_token_accuracy": 0.20273986905813218,
|
|
"num_tokens": 73564507.0,
|
|
"step": 37605
|
|
},
|
|
{
|
|
"entropy": 5.962158298492431,
|
|
"epoch": 3.759534163042935,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0003645685086651894,
|
|
"loss": 5.4561,
|
|
"mean_token_accuracy": 0.19809554815292357,
|
|
"num_tokens": 73574120.0,
|
|
"step": 37610
|
|
},
|
|
{
|
|
"entropy": 5.930420637130737,
|
|
"epoch": 3.760033988104164,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0003645357681510756,
|
|
"loss": 5.4612,
|
|
"mean_token_accuracy": 0.20145188719034196,
|
|
"num_tokens": 73584191.0,
|
|
"step": 37615
|
|
},
|
|
{
|
|
"entropy": 5.911304187774658,
|
|
"epoch": 3.760533813165392,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0003645030253842649,
|
|
"loss": 5.4066,
|
|
"mean_token_accuracy": 0.19948935955762864,
|
|
"num_tokens": 73593964.0,
|
|
"step": 37620
|
|
},
|
|
{
|
|
"entropy": 5.962034416198731,
|
|
"epoch": 3.7610336382266207,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00036447028036558105,
|
|
"loss": 5.5226,
|
|
"mean_token_accuracy": 0.19198649525642394,
|
|
"num_tokens": 73603952.0,
|
|
"step": 37625
|
|
},
|
|
{
|
|
"entropy": 5.974860143661499,
|
|
"epoch": 3.761533463287849,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.000364437533095848,
|
|
"loss": 5.4842,
|
|
"mean_token_accuracy": 0.19277866333723068,
|
|
"num_tokens": 73612868.0,
|
|
"step": 37630
|
|
},
|
|
{
|
|
"entropy": 5.9293749809265135,
|
|
"epoch": 3.7620332883490777,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00036440478357588964,
|
|
"loss": 5.5206,
|
|
"mean_token_accuracy": 0.19425837248563765,
|
|
"num_tokens": 73623272.0,
|
|
"step": 37635
|
|
},
|
|
{
|
|
"entropy": 5.8945478916168215,
|
|
"epoch": 3.7625331134103064,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00036437203180653,
|
|
"loss": 5.3764,
|
|
"mean_token_accuracy": 0.19622708708047867,
|
|
"num_tokens": 73634050.0,
|
|
"step": 37640
|
|
},
|
|
{
|
|
"entropy": 5.927659130096435,
|
|
"epoch": 3.763032938471535,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.000364339277788593,
|
|
"loss": 5.3654,
|
|
"mean_token_accuracy": 0.20623940378427505,
|
|
"num_tokens": 73643327.0,
|
|
"step": 37645
|
|
},
|
|
{
|
|
"entropy": 5.907354688644409,
|
|
"epoch": 3.763532763532764,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0003643065215229027,
|
|
"loss": 5.4018,
|
|
"mean_token_accuracy": 0.2004733204841614,
|
|
"num_tokens": 73653644.0,
|
|
"step": 37650
|
|
},
|
|
{
|
|
"entropy": 5.897337532043457,
|
|
"epoch": 3.764032588593992,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00036427376301028335,
|
|
"loss": 5.3956,
|
|
"mean_token_accuracy": 0.20098572820425034,
|
|
"num_tokens": 73663711.0,
|
|
"step": 37655
|
|
},
|
|
{
|
|
"entropy": 5.905106830596924,
|
|
"epoch": 3.7645324136552207,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0003642410022515591,
|
|
"loss": 5.3594,
|
|
"mean_token_accuracy": 0.20255983620882034,
|
|
"num_tokens": 73673078.0,
|
|
"step": 37660
|
|
},
|
|
{
|
|
"entropy": 5.823409700393677,
|
|
"epoch": 3.765032238716449,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0003642082392475541,
|
|
"loss": 5.2602,
|
|
"mean_token_accuracy": 0.21709766387939453,
|
|
"num_tokens": 73682144.0,
|
|
"step": 37665
|
|
},
|
|
{
|
|
"entropy": 5.814628648757934,
|
|
"epoch": 3.7655320637776777,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00036417547399909285,
|
|
"loss": 5.2508,
|
|
"mean_token_accuracy": 0.21454740166664124,
|
|
"num_tokens": 73691502.0,
|
|
"step": 37670
|
|
},
|
|
{
|
|
"entropy": 5.952034521102905,
|
|
"epoch": 3.7660318888389064,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00036414270650699963,
|
|
"loss": 5.5751,
|
|
"mean_token_accuracy": 0.18600787371397018,
|
|
"num_tokens": 73701584.0,
|
|
"step": 37675
|
|
},
|
|
{
|
|
"entropy": 5.89638876914978,
|
|
"epoch": 3.766531713900135,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.00036410993677209885,
|
|
"loss": 5.4441,
|
|
"mean_token_accuracy": 0.200168976187706,
|
|
"num_tokens": 73711495.0,
|
|
"step": 37680
|
|
},
|
|
{
|
|
"entropy": 5.882650423049927,
|
|
"epoch": 3.767031538961364,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000364077164795215,
|
|
"loss": 5.3711,
|
|
"mean_token_accuracy": 0.2067409485578537,
|
|
"num_tokens": 73721531.0,
|
|
"step": 37685
|
|
},
|
|
{
|
|
"entropy": 5.8722024917602536,
|
|
"epoch": 3.767531364022592,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0003640443905771726,
|
|
"loss": 5.3453,
|
|
"mean_token_accuracy": 0.2042869970202446,
|
|
"num_tokens": 73731900.0,
|
|
"step": 37690
|
|
},
|
|
{
|
|
"entropy": 5.949018669128418,
|
|
"epoch": 3.7680311890838207,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00036401161411879615,
|
|
"loss": 5.4102,
|
|
"mean_token_accuracy": 0.20502785444259644,
|
|
"num_tokens": 73741861.0,
|
|
"step": 37695
|
|
},
|
|
{
|
|
"entropy": 5.85091462135315,
|
|
"epoch": 3.768531014145049,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00036397883542091045,
|
|
"loss": 5.3539,
|
|
"mean_token_accuracy": 0.20780776888132096,
|
|
"num_tokens": 73751672.0,
|
|
"step": 37700
|
|
},
|
|
{
|
|
"entropy": 5.809645891189575,
|
|
"epoch": 3.7690308392062777,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00036394605448434014,
|
|
"loss": 5.2784,
|
|
"mean_token_accuracy": 0.22339563220739364,
|
|
"num_tokens": 73761287.0,
|
|
"step": 37705
|
|
},
|
|
{
|
|
"entropy": 5.804127740859985,
|
|
"epoch": 3.7695306642675064,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0003639132713099101,
|
|
"loss": 5.3956,
|
|
"mean_token_accuracy": 0.20532727390527725,
|
|
"num_tokens": 73771377.0,
|
|
"step": 37710
|
|
},
|
|
{
|
|
"entropy": 6.084051942825317,
|
|
"epoch": 3.770030489328735,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0003638804858984449,
|
|
"loss": 5.5774,
|
|
"mean_token_accuracy": 0.1862462893128395,
|
|
"num_tokens": 73781995.0,
|
|
"step": 37715
|
|
},
|
|
{
|
|
"entropy": 5.951820182800293,
|
|
"epoch": 3.7705303143899638,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00036384769825076964,
|
|
"loss": 5.4566,
|
|
"mean_token_accuracy": 0.1942182868719101,
|
|
"num_tokens": 73792372.0,
|
|
"step": 37720
|
|
},
|
|
{
|
|
"entropy": 5.877911853790283,
|
|
"epoch": 3.771030139451192,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.000363814908367709,
|
|
"loss": 5.4027,
|
|
"mean_token_accuracy": 0.20015596300363542,
|
|
"num_tokens": 73801298.0,
|
|
"step": 37725
|
|
},
|
|
{
|
|
"entropy": 5.862935400009155,
|
|
"epoch": 3.7715299645124207,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00036378211625008827,
|
|
"loss": 5.4144,
|
|
"mean_token_accuracy": 0.20038105994462968,
|
|
"num_tokens": 73810913.0,
|
|
"step": 37730
|
|
},
|
|
{
|
|
"entropy": 5.915466022491455,
|
|
"epoch": 3.772029789573649,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0003637493218987323,
|
|
"loss": 5.3808,
|
|
"mean_token_accuracy": 0.20771348029375075,
|
|
"num_tokens": 73821558.0,
|
|
"step": 37735
|
|
},
|
|
{
|
|
"entropy": 5.884829807281494,
|
|
"epoch": 3.7725296146348777,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0003637165253144662,
|
|
"loss": 5.3963,
|
|
"mean_token_accuracy": 0.19770123809576035,
|
|
"num_tokens": 73830820.0,
|
|
"step": 37740
|
|
},
|
|
{
|
|
"entropy": 5.84587926864624,
|
|
"epoch": 3.7730294396961064,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0003636837264981152,
|
|
"loss": 5.377,
|
|
"mean_token_accuracy": 0.20680940002202988,
|
|
"num_tokens": 73840877.0,
|
|
"step": 37745
|
|
},
|
|
{
|
|
"entropy": 5.90924391746521,
|
|
"epoch": 3.773529264757335,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0003636509254505045,
|
|
"loss": 5.5171,
|
|
"mean_token_accuracy": 0.19494106620550156,
|
|
"num_tokens": 73850054.0,
|
|
"step": 37750
|
|
},
|
|
{
|
|
"entropy": 5.950474548339844,
|
|
"epoch": 3.7740290898185638,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0003636181221724592,
|
|
"loss": 5.4333,
|
|
"mean_token_accuracy": 0.19423091858625413,
|
|
"num_tokens": 73860478.0,
|
|
"step": 37755
|
|
},
|
|
{
|
|
"entropy": 5.947601985931397,
|
|
"epoch": 3.774528914879792,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00036358531666480477,
|
|
"loss": 5.4811,
|
|
"mean_token_accuracy": 0.20105350613594056,
|
|
"num_tokens": 73870793.0,
|
|
"step": 37760
|
|
},
|
|
{
|
|
"entropy": 5.853797149658203,
|
|
"epoch": 3.7750287399410207,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00036355250892836663,
|
|
"loss": 5.3211,
|
|
"mean_token_accuracy": 0.20606264770030974,
|
|
"num_tokens": 73880411.0,
|
|
"step": 37765
|
|
},
|
|
{
|
|
"entropy": 5.801045370101929,
|
|
"epoch": 3.775528565002249,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00036351969896397006,
|
|
"loss": 5.4188,
|
|
"mean_token_accuracy": 0.2176204115152359,
|
|
"num_tokens": 73890626.0,
|
|
"step": 37770
|
|
},
|
|
{
|
|
"entropy": 5.974842548370361,
|
|
"epoch": 3.7760283900634777,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00036348688677244074,
|
|
"loss": 5.4835,
|
|
"mean_token_accuracy": 0.1932828515768051,
|
|
"num_tokens": 73900131.0,
|
|
"step": 37775
|
|
},
|
|
{
|
|
"entropy": 5.792484998703003,
|
|
"epoch": 3.7765282151247064,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00036345407235460417,
|
|
"loss": 5.2542,
|
|
"mean_token_accuracy": 0.2229540914297104,
|
|
"num_tokens": 73909905.0,
|
|
"step": 37780
|
|
},
|
|
{
|
|
"entropy": 5.896183252334595,
|
|
"epoch": 3.777028040185935,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00036342125571128575,
|
|
"loss": 5.489,
|
|
"mean_token_accuracy": 0.20092465877532958,
|
|
"num_tokens": 73920064.0,
|
|
"step": 37785
|
|
},
|
|
{
|
|
"entropy": 5.8860069751739506,
|
|
"epoch": 3.7775278652471633,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00036338843684331133,
|
|
"loss": 5.481,
|
|
"mean_token_accuracy": 0.197785621881485,
|
|
"num_tokens": 73929698.0,
|
|
"step": 37790
|
|
},
|
|
{
|
|
"entropy": 5.9007758617401125,
|
|
"epoch": 3.778027690308392,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00036335561575150663,
|
|
"loss": 5.509,
|
|
"mean_token_accuracy": 0.19675492942333223,
|
|
"num_tokens": 73939465.0,
|
|
"step": 37795
|
|
},
|
|
{
|
|
"entropy": 5.948888683319092,
|
|
"epoch": 3.7785275153696207,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00036332279243669733,
|
|
"loss": 5.4506,
|
|
"mean_token_accuracy": 0.19290764927864074,
|
|
"num_tokens": 73949071.0,
|
|
"step": 37800
|
|
},
|
|
{
|
|
"entropy": 5.922906732559204,
|
|
"epoch": 3.779027340430849,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00036328996689970937,
|
|
"loss": 5.3623,
|
|
"mean_token_accuracy": 0.21038519144058226,
|
|
"num_tokens": 73957979.0,
|
|
"step": 37805
|
|
},
|
|
{
|
|
"entropy": 5.891550540924072,
|
|
"epoch": 3.7795271654920777,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0003632571391413685,
|
|
"loss": 5.3662,
|
|
"mean_token_accuracy": 0.20740678608417512,
|
|
"num_tokens": 73967312.0,
|
|
"step": 37810
|
|
},
|
|
{
|
|
"entropy": 5.934532642364502,
|
|
"epoch": 3.7800269905533064,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00036322430916250077,
|
|
"loss": 5.4948,
|
|
"mean_token_accuracy": 0.1962443172931671,
|
|
"num_tokens": 73976933.0,
|
|
"step": 37815
|
|
},
|
|
{
|
|
"entropy": 5.989095306396484,
|
|
"epoch": 3.780526815614535,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00036319147696393207,
|
|
"loss": 5.5512,
|
|
"mean_token_accuracy": 0.19381757229566574,
|
|
"num_tokens": 73986527.0,
|
|
"step": 37820
|
|
},
|
|
{
|
|
"entropy": 5.952241134643555,
|
|
"epoch": 3.7810266406757633,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0003631586425464885,
|
|
"loss": 5.539,
|
|
"mean_token_accuracy": 0.18980220556259156,
|
|
"num_tokens": 73996225.0,
|
|
"step": 37825
|
|
},
|
|
{
|
|
"entropy": 5.955448341369629,
|
|
"epoch": 3.781526465736992,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00036312580591099625,
|
|
"loss": 5.4928,
|
|
"mean_token_accuracy": 0.1902571514248848,
|
|
"num_tokens": 74006509.0,
|
|
"step": 37830
|
|
},
|
|
{
|
|
"entropy": 5.896400690078735,
|
|
"epoch": 3.7820262907982207,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0003630929670582813,
|
|
"loss": 5.3458,
|
|
"mean_token_accuracy": 0.21099519580602646,
|
|
"num_tokens": 74014924.0,
|
|
"step": 37835
|
|
},
|
|
{
|
|
"entropy": 5.914353561401367,
|
|
"epoch": 3.782526115859449,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00036306012598917,
|
|
"loss": 5.4409,
|
|
"mean_token_accuracy": 0.19981443881988525,
|
|
"num_tokens": 74024880.0,
|
|
"step": 37840
|
|
},
|
|
{
|
|
"entropy": 5.915721988677978,
|
|
"epoch": 3.7830259409206777,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0003630272827044886,
|
|
"loss": 5.4418,
|
|
"mean_token_accuracy": 0.19870901852846146,
|
|
"num_tokens": 74033695.0,
|
|
"step": 37845
|
|
},
|
|
{
|
|
"entropy": 5.944330835342408,
|
|
"epoch": 3.7835257659819064,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00036299443720506344,
|
|
"loss": 5.4016,
|
|
"mean_token_accuracy": 0.20056407451629638,
|
|
"num_tokens": 74044044.0,
|
|
"step": 37850
|
|
},
|
|
{
|
|
"entropy": 5.953894519805909,
|
|
"epoch": 3.784025591043135,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00036296158949172087,
|
|
"loss": 5.5075,
|
|
"mean_token_accuracy": 0.18957449644804,
|
|
"num_tokens": 74052961.0,
|
|
"step": 37855
|
|
},
|
|
{
|
|
"entropy": 5.900658178329468,
|
|
"epoch": 3.7845254161043633,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0003629287395652873,
|
|
"loss": 5.4226,
|
|
"mean_token_accuracy": 0.19921696931123734,
|
|
"num_tokens": 74063116.0,
|
|
"step": 37860
|
|
},
|
|
{
|
|
"entropy": 5.871813631057739,
|
|
"epoch": 3.785025241165592,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0003628958874265893,
|
|
"loss": 5.409,
|
|
"mean_token_accuracy": 0.2030545264482498,
|
|
"num_tokens": 74073191.0,
|
|
"step": 37865
|
|
},
|
|
{
|
|
"entropy": 5.89633002281189,
|
|
"epoch": 3.7855250662268207,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0003628630330764534,
|
|
"loss": 5.4155,
|
|
"mean_token_accuracy": 0.1991475686430931,
|
|
"num_tokens": 74082974.0,
|
|
"step": 37870
|
|
},
|
|
{
|
|
"entropy": 5.942548942565918,
|
|
"epoch": 3.786024891288049,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0003628301765157062,
|
|
"loss": 5.4622,
|
|
"mean_token_accuracy": 0.20021466314792633,
|
|
"num_tokens": 74092287.0,
|
|
"step": 37875
|
|
},
|
|
{
|
|
"entropy": 5.921846199035644,
|
|
"epoch": 3.7865247163492777,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00036279731774517435,
|
|
"loss": 5.5015,
|
|
"mean_token_accuracy": 0.19147938042879104,
|
|
"num_tokens": 74101618.0,
|
|
"step": 37880
|
|
},
|
|
{
|
|
"entropy": 5.889029788970947,
|
|
"epoch": 3.7870245414105064,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00036276445676568453,
|
|
"loss": 5.3981,
|
|
"mean_token_accuracy": 0.20166699588298798,
|
|
"num_tokens": 74111412.0,
|
|
"step": 37885
|
|
},
|
|
{
|
|
"entropy": 5.911684799194336,
|
|
"epoch": 3.787524366471735,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00036273159357806363,
|
|
"loss": 5.4583,
|
|
"mean_token_accuracy": 0.19385015368461608,
|
|
"num_tokens": 74121435.0,
|
|
"step": 37890
|
|
},
|
|
{
|
|
"entropy": 5.900535249710083,
|
|
"epoch": 3.7880241915329633,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00036269872818313836,
|
|
"loss": 5.3977,
|
|
"mean_token_accuracy": 0.2069611132144928,
|
|
"num_tokens": 74131763.0,
|
|
"step": 37895
|
|
},
|
|
{
|
|
"entropy": 5.892107105255127,
|
|
"epoch": 3.788524016594192,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0003626658605817357,
|
|
"loss": 5.4512,
|
|
"mean_token_accuracy": 0.19869794994592666,
|
|
"num_tokens": 74141671.0,
|
|
"step": 37900
|
|
},
|
|
{
|
|
"entropy": 5.820750951766968,
|
|
"epoch": 3.7890238416554207,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00036263299077468256,
|
|
"loss": 5.2989,
|
|
"mean_token_accuracy": 0.20796840488910676,
|
|
"num_tokens": 74151554.0,
|
|
"step": 37905
|
|
},
|
|
{
|
|
"entropy": 5.812291812896729,
|
|
"epoch": 3.789523666716649,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0003626001187628059,
|
|
"loss": 5.2116,
|
|
"mean_token_accuracy": 0.21367325633764267,
|
|
"num_tokens": 74160420.0,
|
|
"step": 37910
|
|
},
|
|
{
|
|
"entropy": 5.818101596832276,
|
|
"epoch": 3.7900234917778777,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0003625672445469327,
|
|
"loss": 5.3703,
|
|
"mean_token_accuracy": 0.21056603789329528,
|
|
"num_tokens": 74171966.0,
|
|
"step": 37915
|
|
},
|
|
{
|
|
"entropy": 5.816205215454102,
|
|
"epoch": 3.7905233168391064,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00036253436812789034,
|
|
"loss": 5.3265,
|
|
"mean_token_accuracy": 0.2152823120355606,
|
|
"num_tokens": 74181938.0,
|
|
"step": 37920
|
|
},
|
|
{
|
|
"entropy": 5.946191453933716,
|
|
"epoch": 3.791023141900335,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0003625014895065057,
|
|
"loss": 5.4549,
|
|
"mean_token_accuracy": 0.20365008115768432,
|
|
"num_tokens": 74191557.0,
|
|
"step": 37925
|
|
},
|
|
{
|
|
"entropy": 5.936143684387207,
|
|
"epoch": 3.7915229669615633,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0003624686086836061,
|
|
"loss": 5.3848,
|
|
"mean_token_accuracy": 0.20601063519716262,
|
|
"num_tokens": 74200807.0,
|
|
"step": 37930
|
|
},
|
|
{
|
|
"entropy": 5.914489221572876,
|
|
"epoch": 3.792022792022792,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0003624357256600188,
|
|
"loss": 5.4579,
|
|
"mean_token_accuracy": 0.20195910781621934,
|
|
"num_tokens": 74210635.0,
|
|
"step": 37935
|
|
},
|
|
{
|
|
"entropy": 5.91637921333313,
|
|
"epoch": 3.7925226170840207,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0003624028404365712,
|
|
"loss": 5.4873,
|
|
"mean_token_accuracy": 0.19227667897939682,
|
|
"num_tokens": 74220189.0,
|
|
"step": 37940
|
|
},
|
|
{
|
|
"entropy": 5.97881383895874,
|
|
"epoch": 3.793022442145249,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0003623699530140906,
|
|
"loss": 5.4416,
|
|
"mean_token_accuracy": 0.20238297879695893,
|
|
"num_tokens": 74229916.0,
|
|
"step": 37945
|
|
},
|
|
{
|
|
"entropy": 5.985875511169434,
|
|
"epoch": 3.7935222672064777,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0003623370633934043,
|
|
"loss": 5.4936,
|
|
"mean_token_accuracy": 0.19392294436693192,
|
|
"num_tokens": 74239829.0,
|
|
"step": 37950
|
|
},
|
|
{
|
|
"entropy": 5.954116439819336,
|
|
"epoch": 3.7940220922677064,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0003623041715753402,
|
|
"loss": 5.4654,
|
|
"mean_token_accuracy": 0.19604499787092208,
|
|
"num_tokens": 74248395.0,
|
|
"step": 37955
|
|
},
|
|
{
|
|
"entropy": 5.868711185455322,
|
|
"epoch": 3.794521917328935,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00036227127756072554,
|
|
"loss": 5.3664,
|
|
"mean_token_accuracy": 0.2043442025780678,
|
|
"num_tokens": 74258122.0,
|
|
"step": 37960
|
|
},
|
|
{
|
|
"entropy": 5.945320987701416,
|
|
"epoch": 3.7950217423901633,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0003622383813503879,
|
|
"loss": 5.4853,
|
|
"mean_token_accuracy": 0.19661034345626832,
|
|
"num_tokens": 74268100.0,
|
|
"step": 37965
|
|
},
|
|
{
|
|
"entropy": 6.030032300949097,
|
|
"epoch": 3.795521567451392,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00036220548294515516,
|
|
"loss": 5.5393,
|
|
"mean_token_accuracy": 0.1912879690527916,
|
|
"num_tokens": 74278251.0,
|
|
"step": 37970
|
|
},
|
|
{
|
|
"entropy": 5.891888856887817,
|
|
"epoch": 3.7960213925126207,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0003621725823458549,
|
|
"loss": 5.3928,
|
|
"mean_token_accuracy": 0.20097958892583848,
|
|
"num_tokens": 74288379.0,
|
|
"step": 37975
|
|
},
|
|
{
|
|
"entropy": 5.952390146255493,
|
|
"epoch": 3.796521217573849,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00036213967955331475,
|
|
"loss": 5.4281,
|
|
"mean_token_accuracy": 0.20598578453063965,
|
|
"num_tokens": 74297867.0,
|
|
"step": 37980
|
|
},
|
|
{
|
|
"entropy": 5.917731761932373,
|
|
"epoch": 3.7970210426350777,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00036210677456836285,
|
|
"loss": 5.4177,
|
|
"mean_token_accuracy": 0.20842327028512955,
|
|
"num_tokens": 74308305.0,
|
|
"step": 37985
|
|
},
|
|
{
|
|
"entropy": 5.884946727752686,
|
|
"epoch": 3.7975208676963064,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00036207386739182685,
|
|
"loss": 5.4394,
|
|
"mean_token_accuracy": 0.20174210369586945,
|
|
"num_tokens": 74318217.0,
|
|
"step": 37990
|
|
},
|
|
{
|
|
"entropy": 5.833962726593017,
|
|
"epoch": 3.798020692757535,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0003620409580245348,
|
|
"loss": 5.3857,
|
|
"mean_token_accuracy": 0.2079685300588608,
|
|
"num_tokens": 74327420.0,
|
|
"step": 37995
|
|
},
|
|
{
|
|
"entropy": 5.93918285369873,
|
|
"epoch": 3.7985205178187633,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00036200804646731457,
|
|
"loss": 5.4896,
|
|
"mean_token_accuracy": 0.19574186503887175,
|
|
"num_tokens": 74336805.0,
|
|
"step": 38000
|
|
},
|
|
{
|
|
"entropy": 5.957928133010864,
|
|
"epoch": 3.799020342879992,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0003619751327209943,
|
|
"loss": 5.4531,
|
|
"mean_token_accuracy": 0.20263783186674117,
|
|
"num_tokens": 74346989.0,
|
|
"step": 38005
|
|
},
|
|
{
|
|
"entropy": 5.894336986541748,
|
|
"epoch": 3.7995201679412207,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00036194221678640206,
|
|
"loss": 5.3801,
|
|
"mean_token_accuracy": 0.20377071350812911,
|
|
"num_tokens": 74356637.0,
|
|
"step": 38010
|
|
},
|
|
{
|
|
"entropy": 5.9027512550354,
|
|
"epoch": 3.800019993002449,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000361909298664366,
|
|
"loss": 5.4299,
|
|
"mean_token_accuracy": 0.19589220583438874,
|
|
"num_tokens": 74366024.0,
|
|
"step": 38015
|
|
},
|
|
{
|
|
"entropy": 5.944643783569336,
|
|
"epoch": 3.8005198180636777,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0003618763783557144,
|
|
"loss": 5.3741,
|
|
"mean_token_accuracy": 0.2092084541916847,
|
|
"num_tokens": 74375630.0,
|
|
"step": 38020
|
|
},
|
|
{
|
|
"entropy": 5.8469460010528564,
|
|
"epoch": 3.8010196431249064,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0003618434558612755,
|
|
"loss": 5.3771,
|
|
"mean_token_accuracy": 0.20224653631448747,
|
|
"num_tokens": 74385473.0,
|
|
"step": 38025
|
|
},
|
|
{
|
|
"entropy": 5.861813020706177,
|
|
"epoch": 3.801519468186135,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00036181053118187757,
|
|
"loss": 5.4227,
|
|
"mean_token_accuracy": 0.1982473075389862,
|
|
"num_tokens": 74395516.0,
|
|
"step": 38030
|
|
},
|
|
{
|
|
"entropy": 5.824170875549316,
|
|
"epoch": 3.8020192932473633,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00036177760431834897,
|
|
"loss": 5.3573,
|
|
"mean_token_accuracy": 0.2080201044678688,
|
|
"num_tokens": 74405421.0,
|
|
"step": 38035
|
|
},
|
|
{
|
|
"entropy": 5.963036918640137,
|
|
"epoch": 3.802519118308592,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0003617446752715182,
|
|
"loss": 5.5596,
|
|
"mean_token_accuracy": 0.1929216280579567,
|
|
"num_tokens": 74416142.0,
|
|
"step": 38040
|
|
},
|
|
{
|
|
"entropy": 5.975061655044556,
|
|
"epoch": 3.8030189433698207,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00036171174404221377,
|
|
"loss": 5.4085,
|
|
"mean_token_accuracy": 0.19854085594415666,
|
|
"num_tokens": 74425943.0,
|
|
"step": 38045
|
|
},
|
|
{
|
|
"entropy": 5.957652473449707,
|
|
"epoch": 3.803518768431049,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00036167881063126414,
|
|
"loss": 5.443,
|
|
"mean_token_accuracy": 0.1974718376994133,
|
|
"num_tokens": 74435088.0,
|
|
"step": 38050
|
|
},
|
|
{
|
|
"entropy": 5.925312185287476,
|
|
"epoch": 3.8040185934922777,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0003616458750394979,
|
|
"loss": 5.5031,
|
|
"mean_token_accuracy": 0.19375652074813843,
|
|
"num_tokens": 74444922.0,
|
|
"step": 38055
|
|
},
|
|
{
|
|
"entropy": 5.938510465621948,
|
|
"epoch": 3.8045184185535064,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0003616129372677438,
|
|
"loss": 5.4353,
|
|
"mean_token_accuracy": 0.20033693313598633,
|
|
"num_tokens": 74455243.0,
|
|
"step": 38060
|
|
},
|
|
{
|
|
"entropy": 5.928186225891113,
|
|
"epoch": 3.805018243614735,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0003615799973168305,
|
|
"loss": 5.5119,
|
|
"mean_token_accuracy": 0.20150204449892045,
|
|
"num_tokens": 74464925.0,
|
|
"step": 38065
|
|
},
|
|
{
|
|
"entropy": 5.924234867095947,
|
|
"epoch": 3.8055180686759633,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0003615470551875867,
|
|
"loss": 5.4443,
|
|
"mean_token_accuracy": 0.2024811789393425,
|
|
"num_tokens": 74474438.0,
|
|
"step": 38070
|
|
},
|
|
{
|
|
"entropy": 5.997099161148071,
|
|
"epoch": 3.806017893737192,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0003615141108808412,
|
|
"loss": 5.4034,
|
|
"mean_token_accuracy": 0.20500251799821853,
|
|
"num_tokens": 74484311.0,
|
|
"step": 38075
|
|
},
|
|
{
|
|
"entropy": 6.017017126083374,
|
|
"epoch": 3.8065177187984207,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000361481164397423,
|
|
"loss": 5.5468,
|
|
"mean_token_accuracy": 0.1937139078974724,
|
|
"num_tokens": 74494841.0,
|
|
"step": 38080
|
|
},
|
|
{
|
|
"entropy": 5.830761671066284,
|
|
"epoch": 3.807017543859649,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00036144821573816095,
|
|
"loss": 5.3999,
|
|
"mean_token_accuracy": 0.20200523138046264,
|
|
"num_tokens": 74505354.0,
|
|
"step": 38085
|
|
},
|
|
{
|
|
"entropy": 5.873218679428101,
|
|
"epoch": 3.8075173689208777,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00036141526490388406,
|
|
"loss": 5.4008,
|
|
"mean_token_accuracy": 0.2006699725985527,
|
|
"num_tokens": 74514182.0,
|
|
"step": 38090
|
|
},
|
|
{
|
|
"entropy": 6.020280838012695,
|
|
"epoch": 3.8080171939821064,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00036138231189542137,
|
|
"loss": 5.4538,
|
|
"mean_token_accuracy": 0.19715034067630768,
|
|
"num_tokens": 74523824.0,
|
|
"step": 38095
|
|
},
|
|
{
|
|
"entropy": 5.947732400894165,
|
|
"epoch": 3.808517019043335,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0003613493567136019,
|
|
"loss": 5.5039,
|
|
"mean_token_accuracy": 0.18953435122966766,
|
|
"num_tokens": 74534016.0,
|
|
"step": 38100
|
|
},
|
|
{
|
|
"entropy": 5.857332849502564,
|
|
"epoch": 3.8090168441045633,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0003613163993592548,
|
|
"loss": 5.3044,
|
|
"mean_token_accuracy": 0.21073267310857774,
|
|
"num_tokens": 74542935.0,
|
|
"step": 38105
|
|
},
|
|
{
|
|
"entropy": 5.871117639541626,
|
|
"epoch": 3.809516669165792,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0003612834398332093,
|
|
"loss": 5.4266,
|
|
"mean_token_accuracy": 0.2025311514735222,
|
|
"num_tokens": 74553556.0,
|
|
"step": 38110
|
|
},
|
|
{
|
|
"entropy": 5.857955551147461,
|
|
"epoch": 3.8100164942270203,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0003612504781362947,
|
|
"loss": 5.3282,
|
|
"mean_token_accuracy": 0.21688662618398666,
|
|
"num_tokens": 74563691.0,
|
|
"step": 38115
|
|
},
|
|
{
|
|
"entropy": 5.966893005371094,
|
|
"epoch": 3.810516319288249,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0003612175142693402,
|
|
"loss": 5.3762,
|
|
"mean_token_accuracy": 0.2044510453939438,
|
|
"num_tokens": 74572512.0,
|
|
"step": 38120
|
|
},
|
|
{
|
|
"entropy": 5.815323972702027,
|
|
"epoch": 3.8110161443494777,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0003611845482331753,
|
|
"loss": 5.3199,
|
|
"mean_token_accuracy": 0.21147667318582536,
|
|
"num_tokens": 74582542.0,
|
|
"step": 38125
|
|
},
|
|
{
|
|
"entropy": 5.893059778213501,
|
|
"epoch": 3.8115159694107064,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00036115158002862933,
|
|
"loss": 5.4078,
|
|
"mean_token_accuracy": 0.19957083761692046,
|
|
"num_tokens": 74591367.0,
|
|
"step": 38130
|
|
},
|
|
{
|
|
"entropy": 5.887476682662964,
|
|
"epoch": 3.812015794471935,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0003611186096565318,
|
|
"loss": 5.4535,
|
|
"mean_token_accuracy": 0.19593133628368378,
|
|
"num_tokens": 74600732.0,
|
|
"step": 38135
|
|
},
|
|
{
|
|
"entropy": 5.930505418777466,
|
|
"epoch": 3.8125156195331633,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0003610856371177122,
|
|
"loss": 5.4334,
|
|
"mean_token_accuracy": 0.19727435559034348,
|
|
"num_tokens": 74610220.0,
|
|
"step": 38140
|
|
},
|
|
{
|
|
"entropy": 5.955567693710327,
|
|
"epoch": 3.813015444594392,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00036105266241300005,
|
|
"loss": 5.3936,
|
|
"mean_token_accuracy": 0.20500056743621825,
|
|
"num_tokens": 74619545.0,
|
|
"step": 38145
|
|
},
|
|
{
|
|
"entropy": 5.928073120117188,
|
|
"epoch": 3.8135152696556203,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0003610196855432251,
|
|
"loss": 5.4324,
|
|
"mean_token_accuracy": 0.20056302845478058,
|
|
"num_tokens": 74628942.0,
|
|
"step": 38150
|
|
},
|
|
{
|
|
"entropy": 5.8927570343017575,
|
|
"epoch": 3.814015094716849,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00036098670650921706,
|
|
"loss": 5.4126,
|
|
"mean_token_accuracy": 0.20319707095623016,
|
|
"num_tokens": 74639774.0,
|
|
"step": 38155
|
|
},
|
|
{
|
|
"entropy": 5.906811285018921,
|
|
"epoch": 3.8145149197780777,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0003609537253118056,
|
|
"loss": 5.4074,
|
|
"mean_token_accuracy": 0.20396799296140672,
|
|
"num_tokens": 74649824.0,
|
|
"step": 38160
|
|
},
|
|
{
|
|
"entropy": 5.961496448516845,
|
|
"epoch": 3.8150147448393064,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0003609207419518204,
|
|
"loss": 5.4362,
|
|
"mean_token_accuracy": 0.2043752044439316,
|
|
"num_tokens": 74660021.0,
|
|
"step": 38165
|
|
},
|
|
{
|
|
"entropy": 5.8887053489685055,
|
|
"epoch": 3.815514569900535,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0003608877564300915,
|
|
"loss": 5.4546,
|
|
"mean_token_accuracy": 0.20394265055656433,
|
|
"num_tokens": 74669545.0,
|
|
"step": 38170
|
|
},
|
|
{
|
|
"entropy": 5.9041660785675045,
|
|
"epoch": 3.8160143949617633,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0003608547687474488,
|
|
"loss": 5.3834,
|
|
"mean_token_accuracy": 0.19706854671239854,
|
|
"num_tokens": 74678353.0,
|
|
"step": 38175
|
|
},
|
|
{
|
|
"entropy": 5.8335853099823,
|
|
"epoch": 3.816514220022992,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00036082177890472224,
|
|
"loss": 5.3452,
|
|
"mean_token_accuracy": 0.21258064806461335,
|
|
"num_tokens": 74687559.0,
|
|
"step": 38180
|
|
},
|
|
{
|
|
"entropy": 5.897381591796875,
|
|
"epoch": 3.8170140450842203,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00036078878690274177,
|
|
"loss": 5.5162,
|
|
"mean_token_accuracy": 0.19248427599668502,
|
|
"num_tokens": 74698288.0,
|
|
"step": 38185
|
|
},
|
|
{
|
|
"entropy": 5.913212537765503,
|
|
"epoch": 3.817513870145449,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0003607557927423374,
|
|
"loss": 5.3607,
|
|
"mean_token_accuracy": 0.2095065101981163,
|
|
"num_tokens": 74707671.0,
|
|
"step": 38190
|
|
},
|
|
{
|
|
"entropy": 5.971322870254516,
|
|
"epoch": 3.8180136952066777,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00036072279642433946,
|
|
"loss": 5.5184,
|
|
"mean_token_accuracy": 0.1934210792183876,
|
|
"num_tokens": 74717492.0,
|
|
"step": 38195
|
|
},
|
|
{
|
|
"entropy": 5.895115232467651,
|
|
"epoch": 3.8185135202679064,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00036068979794957797,
|
|
"loss": 5.3718,
|
|
"mean_token_accuracy": 0.2055327907204628,
|
|
"num_tokens": 74727711.0,
|
|
"step": 38200
|
|
},
|
|
{
|
|
"entropy": 5.864942264556885,
|
|
"epoch": 3.819013345329135,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0003606567973188833,
|
|
"loss": 5.4132,
|
|
"mean_token_accuracy": 0.1980542615056038,
|
|
"num_tokens": 74738126.0,
|
|
"step": 38205
|
|
},
|
|
{
|
|
"entropy": 5.977771139144897,
|
|
"epoch": 3.8195131703903633,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00036062379453308556,
|
|
"loss": 5.5033,
|
|
"mean_token_accuracy": 0.19536873698234558,
|
|
"num_tokens": 74748262.0,
|
|
"step": 38210
|
|
},
|
|
{
|
|
"entropy": 5.897575330734253,
|
|
"epoch": 3.820012995451592,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00036059078959301515,
|
|
"loss": 5.3611,
|
|
"mean_token_accuracy": 0.20826099067926407,
|
|
"num_tokens": 74758161.0,
|
|
"step": 38215
|
|
},
|
|
{
|
|
"entropy": 5.840405750274658,
|
|
"epoch": 3.8205128205128203,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0003605577824995026,
|
|
"loss": 5.3267,
|
|
"mean_token_accuracy": 0.21611780822277069,
|
|
"num_tokens": 74767970.0,
|
|
"step": 38220
|
|
},
|
|
{
|
|
"entropy": 5.937797498703003,
|
|
"epoch": 3.821012645574049,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00036052477325337824,
|
|
"loss": 5.4978,
|
|
"mean_token_accuracy": 0.1955578401684761,
|
|
"num_tokens": 74779410.0,
|
|
"step": 38225
|
|
},
|
|
{
|
|
"entropy": 5.951720428466797,
|
|
"epoch": 3.8215124706352777,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00036049176185547254,
|
|
"loss": 5.5025,
|
|
"mean_token_accuracy": 0.1912665218114853,
|
|
"num_tokens": 74788200.0,
|
|
"step": 38230
|
|
},
|
|
{
|
|
"entropy": 5.91150918006897,
|
|
"epoch": 3.8220122956965064,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00036045874830661613,
|
|
"loss": 5.4695,
|
|
"mean_token_accuracy": 0.2041679099202156,
|
|
"num_tokens": 74797776.0,
|
|
"step": 38235
|
|
},
|
|
{
|
|
"entropy": 5.924875783920288,
|
|
"epoch": 3.822512120757735,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0003604257326076397,
|
|
"loss": 5.4335,
|
|
"mean_token_accuracy": 0.19916752427816392,
|
|
"num_tokens": 74807103.0,
|
|
"step": 38240
|
|
},
|
|
{
|
|
"entropy": 5.866823530197143,
|
|
"epoch": 3.8230119458189633,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00036039271475937366,
|
|
"loss": 5.359,
|
|
"mean_token_accuracy": 0.2066227227449417,
|
|
"num_tokens": 74816003.0,
|
|
"step": 38245
|
|
},
|
|
{
|
|
"entropy": 5.908021736145019,
|
|
"epoch": 3.823511770880192,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.000360359694762649,
|
|
"loss": 5.3886,
|
|
"mean_token_accuracy": 0.20458775013685226,
|
|
"num_tokens": 74825387.0,
|
|
"step": 38250
|
|
},
|
|
{
|
|
"entropy": 5.932528686523438,
|
|
"epoch": 3.8240115959414203,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0003603266726182963,
|
|
"loss": 5.464,
|
|
"mean_token_accuracy": 0.19879324585199357,
|
|
"num_tokens": 74833909.0,
|
|
"step": 38255
|
|
},
|
|
{
|
|
"entropy": 5.999309778213501,
|
|
"epoch": 3.824511421002649,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0003602936483271465,
|
|
"loss": 5.5319,
|
|
"mean_token_accuracy": 0.18560422360897064,
|
|
"num_tokens": 74843685.0,
|
|
"step": 38260
|
|
},
|
|
{
|
|
"entropy": 5.900116205215454,
|
|
"epoch": 3.8250112460638777,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00036026062189003046,
|
|
"loss": 5.3948,
|
|
"mean_token_accuracy": 0.20355995148420333,
|
|
"num_tokens": 74852376.0,
|
|
"step": 38265
|
|
},
|
|
{
|
|
"entropy": 5.9263359069824215,
|
|
"epoch": 3.8255110711251064,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0003602275933077792,
|
|
"loss": 5.4346,
|
|
"mean_token_accuracy": 0.20304107815027236,
|
|
"num_tokens": 74863057.0,
|
|
"step": 38270
|
|
},
|
|
{
|
|
"entropy": 5.958641481399536,
|
|
"epoch": 3.826010896186335,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00036019456258122346,
|
|
"loss": 5.4902,
|
|
"mean_token_accuracy": 0.19715456217527388,
|
|
"num_tokens": 74873337.0,
|
|
"step": 38275
|
|
},
|
|
{
|
|
"entropy": 5.8524500846862795,
|
|
"epoch": 3.8265107212475633,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00036016152971119457,
|
|
"loss": 5.3069,
|
|
"mean_token_accuracy": 0.20626944154500962,
|
|
"num_tokens": 74882994.0,
|
|
"step": 38280
|
|
},
|
|
{
|
|
"entropy": 5.902990674972534,
|
|
"epoch": 3.827010546308792,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0003601284946985235,
|
|
"loss": 5.4739,
|
|
"mean_token_accuracy": 0.1912621319293976,
|
|
"num_tokens": 74893490.0,
|
|
"step": 38285
|
|
},
|
|
{
|
|
"entropy": 5.914991331100464,
|
|
"epoch": 3.8275103713700203,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0003600954575440414,
|
|
"loss": 5.4017,
|
|
"mean_token_accuracy": 0.20442755669355392,
|
|
"num_tokens": 74903152.0,
|
|
"step": 38290
|
|
},
|
|
{
|
|
"entropy": 5.884138345718384,
|
|
"epoch": 3.828010196431249,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0003600624182485794,
|
|
"loss": 5.3639,
|
|
"mean_token_accuracy": 0.20222368240356445,
|
|
"num_tokens": 74913146.0,
|
|
"step": 38295
|
|
},
|
|
{
|
|
"entropy": 5.913400173187256,
|
|
"epoch": 3.8285100214924777,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0003600293768129689,
|
|
"loss": 5.5627,
|
|
"mean_token_accuracy": 0.19001364707946777,
|
|
"num_tokens": 74923313.0,
|
|
"step": 38300
|
|
},
|
|
{
|
|
"entropy": 5.917418193817139,
|
|
"epoch": 3.8290098465537064,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00035999633323804123,
|
|
"loss": 5.4788,
|
|
"mean_token_accuracy": 0.195296810567379,
|
|
"num_tokens": 74933339.0,
|
|
"step": 38305
|
|
},
|
|
{
|
|
"entropy": 5.979712295532226,
|
|
"epoch": 3.8295096716149346,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00035996328752462757,
|
|
"loss": 5.4734,
|
|
"mean_token_accuracy": 0.194766366481781,
|
|
"num_tokens": 74943047.0,
|
|
"step": 38310
|
|
},
|
|
{
|
|
"entropy": 6.077754211425781,
|
|
"epoch": 3.8300094966761633,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00035993023967355954,
|
|
"loss": 5.594,
|
|
"mean_token_accuracy": 0.19022419452667236,
|
|
"num_tokens": 74952040.0,
|
|
"step": 38315
|
|
},
|
|
{
|
|
"entropy": 5.93092565536499,
|
|
"epoch": 3.830509321737392,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00035989718968566846,
|
|
"loss": 5.4253,
|
|
"mean_token_accuracy": 0.20013635009527206,
|
|
"num_tokens": 74960848.0,
|
|
"step": 38320
|
|
},
|
|
{
|
|
"entropy": 5.8065132141113285,
|
|
"epoch": 3.8310091467986203,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000359864137561786,
|
|
"loss": 5.3433,
|
|
"mean_token_accuracy": 0.20461703687906266,
|
|
"num_tokens": 74970357.0,
|
|
"step": 38325
|
|
},
|
|
{
|
|
"entropy": 6.003630113601685,
|
|
"epoch": 3.831508971859849,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0003598310833027437,
|
|
"loss": 5.4748,
|
|
"mean_token_accuracy": 0.18973956555128096,
|
|
"num_tokens": 74979433.0,
|
|
"step": 38330
|
|
},
|
|
{
|
|
"entropy": 5.888448286056518,
|
|
"epoch": 3.8320087969210777,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00035979802690937315,
|
|
"loss": 5.3213,
|
|
"mean_token_accuracy": 0.2046092391014099,
|
|
"num_tokens": 74989733.0,
|
|
"step": 38335
|
|
},
|
|
{
|
|
"entropy": 5.855917739868164,
|
|
"epoch": 3.8325086219823064,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00035976496838250607,
|
|
"loss": 5.3511,
|
|
"mean_token_accuracy": 0.201078961789608,
|
|
"num_tokens": 75000139.0,
|
|
"step": 38340
|
|
},
|
|
{
|
|
"entropy": 5.945271396636963,
|
|
"epoch": 3.8330084470435346,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00035973190772297417,
|
|
"loss": 5.5509,
|
|
"mean_token_accuracy": 0.192061747610569,
|
|
"num_tokens": 75009165.0,
|
|
"step": 38345
|
|
},
|
|
{
|
|
"entropy": 5.92502007484436,
|
|
"epoch": 3.8335082721047633,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00035969884493160925,
|
|
"loss": 5.4525,
|
|
"mean_token_accuracy": 0.20035519003868102,
|
|
"num_tokens": 75019077.0,
|
|
"step": 38350
|
|
},
|
|
{
|
|
"entropy": 5.864055204391479,
|
|
"epoch": 3.834008097165992,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00035966578000924324,
|
|
"loss": 5.3589,
|
|
"mean_token_accuracy": 0.2093534305691719,
|
|
"num_tokens": 75029351.0,
|
|
"step": 38355
|
|
},
|
|
{
|
|
"entropy": 5.921615505218506,
|
|
"epoch": 3.8345079222272203,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0003596327129567079,
|
|
"loss": 5.4118,
|
|
"mean_token_accuracy": 0.20660298615694045,
|
|
"num_tokens": 75038542.0,
|
|
"step": 38360
|
|
},
|
|
{
|
|
"entropy": 5.923371458053589,
|
|
"epoch": 3.835007747288449,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00035959964377483536,
|
|
"loss": 5.46,
|
|
"mean_token_accuracy": 0.20410557687282563,
|
|
"num_tokens": 75049288.0,
|
|
"step": 38365
|
|
},
|
|
{
|
|
"entropy": 5.895770168304443,
|
|
"epoch": 3.8355075723496777,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0003595665724644576,
|
|
"loss": 5.4802,
|
|
"mean_token_accuracy": 0.1970208019018173,
|
|
"num_tokens": 75059595.0,
|
|
"step": 38370
|
|
},
|
|
{
|
|
"entropy": 5.932824039459229,
|
|
"epoch": 3.8360073974109063,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0003595334990264065,
|
|
"loss": 5.4285,
|
|
"mean_token_accuracy": 0.19847799688577653,
|
|
"num_tokens": 75069566.0,
|
|
"step": 38375
|
|
},
|
|
{
|
|
"entropy": 5.998429489135742,
|
|
"epoch": 3.8365072224721346,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0003595004234615144,
|
|
"loss": 5.5144,
|
|
"mean_token_accuracy": 0.18698466718196868,
|
|
"num_tokens": 75079555.0,
|
|
"step": 38380
|
|
},
|
|
{
|
|
"entropy": 5.947276782989502,
|
|
"epoch": 3.8370070475333633,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00035946734577061345,
|
|
"loss": 5.3875,
|
|
"mean_token_accuracy": 0.19996127635240554,
|
|
"num_tokens": 75088703.0,
|
|
"step": 38385
|
|
},
|
|
{
|
|
"entropy": 5.888426828384399,
|
|
"epoch": 3.837506872594592,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0003594342659545357,
|
|
"loss": 5.5049,
|
|
"mean_token_accuracy": 0.19626972526311875,
|
|
"num_tokens": 75098328.0,
|
|
"step": 38390
|
|
},
|
|
{
|
|
"entropy": 5.879063129425049,
|
|
"epoch": 3.8380066976558203,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0003594011840141136,
|
|
"loss": 5.3341,
|
|
"mean_token_accuracy": 0.2024145632982254,
|
|
"num_tokens": 75108248.0,
|
|
"step": 38395
|
|
},
|
|
{
|
|
"entropy": 5.963167667388916,
|
|
"epoch": 3.838506522717049,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00035936809995017936,
|
|
"loss": 5.4802,
|
|
"mean_token_accuracy": 0.19653368145227432,
|
|
"num_tokens": 75116876.0,
|
|
"step": 38400
|
|
},
|
|
{
|
|
"entropy": 5.890320253372193,
|
|
"epoch": 3.8390063477782777,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00035933501376356555,
|
|
"loss": 5.407,
|
|
"mean_token_accuracy": 0.2052927866578102,
|
|
"num_tokens": 75126977.0,
|
|
"step": 38405
|
|
},
|
|
{
|
|
"entropy": 5.936894655227661,
|
|
"epoch": 3.8395061728395063,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0003593019254551045,
|
|
"loss": 5.3562,
|
|
"mean_token_accuracy": 0.2009981691837311,
|
|
"num_tokens": 75136565.0,
|
|
"step": 38410
|
|
},
|
|
{
|
|
"entropy": 5.919638967514038,
|
|
"epoch": 3.8400059979007346,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00035926883502562855,
|
|
"loss": 5.4725,
|
|
"mean_token_accuracy": 0.18912460654973984,
|
|
"num_tokens": 75146438.0,
|
|
"step": 38415
|
|
},
|
|
{
|
|
"entropy": 5.926318979263305,
|
|
"epoch": 3.8405058229619633,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00035923574247597053,
|
|
"loss": 5.4666,
|
|
"mean_token_accuracy": 0.20070822685956954,
|
|
"num_tokens": 75155875.0,
|
|
"step": 38420
|
|
},
|
|
{
|
|
"entropy": 5.830075979232788,
|
|
"epoch": 3.841005648023192,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00035920264780696284,
|
|
"loss": 5.2899,
|
|
"mean_token_accuracy": 0.20101078152656554,
|
|
"num_tokens": 75164875.0,
|
|
"step": 38425
|
|
},
|
|
{
|
|
"entropy": 5.884807586669922,
|
|
"epoch": 3.8415054730844203,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0003591695510194382,
|
|
"loss": 5.3453,
|
|
"mean_token_accuracy": 0.2063461571931839,
|
|
"num_tokens": 75174384.0,
|
|
"step": 38430
|
|
},
|
|
{
|
|
"entropy": 5.8777854442596436,
|
|
"epoch": 3.842005298145649,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0003591364521142293,
|
|
"loss": 5.3182,
|
|
"mean_token_accuracy": 0.19941887110471726,
|
|
"num_tokens": 75183766.0,
|
|
"step": 38435
|
|
},
|
|
{
|
|
"entropy": 5.850503587722779,
|
|
"epoch": 3.8425051232068776,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00035910335109216895,
|
|
"loss": 5.4336,
|
|
"mean_token_accuracy": 0.19704096913337707,
|
|
"num_tokens": 75193453.0,
|
|
"step": 38440
|
|
},
|
|
{
|
|
"entropy": 5.91665825843811,
|
|
"epoch": 3.8430049482681063,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00035907024795409,
|
|
"loss": 5.4438,
|
|
"mean_token_accuracy": 0.2055942177772522,
|
|
"num_tokens": 75203193.0,
|
|
"step": 38445
|
|
},
|
|
{
|
|
"entropy": 5.884782028198242,
|
|
"epoch": 3.8435047733293346,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00035903714270082515,
|
|
"loss": 5.3651,
|
|
"mean_token_accuracy": 0.20516912788152694,
|
|
"num_tokens": 75212465.0,
|
|
"step": 38450
|
|
},
|
|
{
|
|
"entropy": 6.00685863494873,
|
|
"epoch": 3.8440045983905633,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0003590040353332074,
|
|
"loss": 5.5381,
|
|
"mean_token_accuracy": 0.19167448580265045,
|
|
"num_tokens": 75221529.0,
|
|
"step": 38455
|
|
},
|
|
{
|
|
"entropy": 5.888544511795044,
|
|
"epoch": 3.844504423451792,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0003589709258520698,
|
|
"loss": 5.3975,
|
|
"mean_token_accuracy": 0.20839498341083526,
|
|
"num_tokens": 75231676.0,
|
|
"step": 38460
|
|
},
|
|
{
|
|
"entropy": 5.882231760025024,
|
|
"epoch": 3.8450042485130203,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0003589378142582453,
|
|
"loss": 5.4161,
|
|
"mean_token_accuracy": 0.20420735329389572,
|
|
"num_tokens": 75241420.0,
|
|
"step": 38465
|
|
},
|
|
{
|
|
"entropy": 5.908380508422852,
|
|
"epoch": 3.845504073574249,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00035890470055256697,
|
|
"loss": 5.4563,
|
|
"mean_token_accuracy": 0.19375113695859908,
|
|
"num_tokens": 75250725.0,
|
|
"step": 38470
|
|
},
|
|
{
|
|
"entropy": 5.860838794708252,
|
|
"epoch": 3.8460038986354776,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00035887158473586793,
|
|
"loss": 5.2335,
|
|
"mean_token_accuracy": 0.21000296175479888,
|
|
"num_tokens": 75260915.0,
|
|
"step": 38475
|
|
},
|
|
{
|
|
"entropy": 5.8693585872650145,
|
|
"epoch": 3.8465037236967063,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0003588384668089815,
|
|
"loss": 5.3505,
|
|
"mean_token_accuracy": 0.20931501388549806,
|
|
"num_tokens": 75270803.0,
|
|
"step": 38480
|
|
},
|
|
{
|
|
"entropy": 5.884265756607055,
|
|
"epoch": 3.8470035487579346,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00035880534677274075,
|
|
"loss": 5.3618,
|
|
"mean_token_accuracy": 0.19828314930200577,
|
|
"num_tokens": 75280323.0,
|
|
"step": 38485
|
|
},
|
|
{
|
|
"entropy": 5.867340040206909,
|
|
"epoch": 3.8475033738191633,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000358772224627979,
|
|
"loss": 5.3689,
|
|
"mean_token_accuracy": 0.20186927020549775,
|
|
"num_tokens": 75290115.0,
|
|
"step": 38490
|
|
},
|
|
{
|
|
"entropy": 5.888512372970581,
|
|
"epoch": 3.848003198880392,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00035873910037552973,
|
|
"loss": 5.3964,
|
|
"mean_token_accuracy": 0.20793589651584626,
|
|
"num_tokens": 75300868.0,
|
|
"step": 38495
|
|
},
|
|
{
|
|
"entropy": 5.976015186309814,
|
|
"epoch": 3.8485030239416202,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0003587059740162262,
|
|
"loss": 5.4347,
|
|
"mean_token_accuracy": 0.19774852246046065,
|
|
"num_tokens": 75310859.0,
|
|
"step": 38500
|
|
},
|
|
{
|
|
"entropy": 5.972559833526612,
|
|
"epoch": 3.849002849002849,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0003586728455509019,
|
|
"loss": 5.4438,
|
|
"mean_token_accuracy": 0.20096648782491683,
|
|
"num_tokens": 75320682.0,
|
|
"step": 38505
|
|
},
|
|
{
|
|
"entropy": 6.009554147720337,
|
|
"epoch": 3.8495026740640776,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00035863971498039033,
|
|
"loss": 5.516,
|
|
"mean_token_accuracy": 0.19705291837453842,
|
|
"num_tokens": 75330466.0,
|
|
"step": 38510
|
|
},
|
|
{
|
|
"entropy": 5.891138076782227,
|
|
"epoch": 3.8500024991253063,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00035860658230552506,
|
|
"loss": 5.3783,
|
|
"mean_token_accuracy": 0.20355788767337799,
|
|
"num_tokens": 75339650.0,
|
|
"step": 38515
|
|
},
|
|
{
|
|
"entropy": 5.9386711597442625,
|
|
"epoch": 3.8505023241865346,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0003585734475271397,
|
|
"loss": 5.4823,
|
|
"mean_token_accuracy": 0.19447044730186464,
|
|
"num_tokens": 75350093.0,
|
|
"step": 38520
|
|
},
|
|
{
|
|
"entropy": 5.986282539367676,
|
|
"epoch": 3.8510021492477633,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0003585403106460679,
|
|
"loss": 5.4819,
|
|
"mean_token_accuracy": 0.19526466429233552,
|
|
"num_tokens": 75358433.0,
|
|
"step": 38525
|
|
},
|
|
{
|
|
"entropy": 5.863544464111328,
|
|
"epoch": 3.851501974308992,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0003585071716631433,
|
|
"loss": 5.2566,
|
|
"mean_token_accuracy": 0.21681101322174073,
|
|
"num_tokens": 75366538.0,
|
|
"step": 38530
|
|
},
|
|
{
|
|
"entropy": 5.885765171051025,
|
|
"epoch": 3.8520017993702202,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0003584740305791999,
|
|
"loss": 5.3847,
|
|
"mean_token_accuracy": 0.20742541700601577,
|
|
"num_tokens": 75376314.0,
|
|
"step": 38535
|
|
},
|
|
{
|
|
"entropy": 5.953379678726196,
|
|
"epoch": 3.852501624431449,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0003584408873950713,
|
|
"loss": 5.418,
|
|
"mean_token_accuracy": 0.2028330907225609,
|
|
"num_tokens": 75386097.0,
|
|
"step": 38540
|
|
},
|
|
{
|
|
"entropy": 5.9081768035888675,
|
|
"epoch": 3.8530014494926776,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00035840774211159146,
|
|
"loss": 5.3923,
|
|
"mean_token_accuracy": 0.20685160756111146,
|
|
"num_tokens": 75396407.0,
|
|
"step": 38545
|
|
},
|
|
{
|
|
"entropy": 5.889927673339844,
|
|
"epoch": 3.8535012745539063,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00035837459472959425,
|
|
"loss": 5.4239,
|
|
"mean_token_accuracy": 0.19974106252193452,
|
|
"num_tokens": 75406119.0,
|
|
"step": 38550
|
|
},
|
|
{
|
|
"entropy": 5.838792133331299,
|
|
"epoch": 3.8540010996151346,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0003583414452499137,
|
|
"loss": 5.3374,
|
|
"mean_token_accuracy": 0.20883720964193345,
|
|
"num_tokens": 75415642.0,
|
|
"step": 38555
|
|
},
|
|
{
|
|
"entropy": 6.0206063747406,
|
|
"epoch": 3.8545009246763633,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00035830829367338384,
|
|
"loss": 5.6066,
|
|
"mean_token_accuracy": 0.18993386179208754,
|
|
"num_tokens": 75426005.0,
|
|
"step": 38560
|
|
},
|
|
{
|
|
"entropy": 5.9818824291229244,
|
|
"epoch": 3.855000749737592,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0003582751400008388,
|
|
"loss": 5.3817,
|
|
"mean_token_accuracy": 0.20828510522842408,
|
|
"num_tokens": 75435641.0,
|
|
"step": 38565
|
|
},
|
|
{
|
|
"entropy": 5.830692958831787,
|
|
"epoch": 3.8555005747988202,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00035824198423311263,
|
|
"loss": 5.3021,
|
|
"mean_token_accuracy": 0.21833040565252304,
|
|
"num_tokens": 75445329.0,
|
|
"step": 38570
|
|
},
|
|
{
|
|
"entropy": 5.880799055099487,
|
|
"epoch": 3.856000399860049,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0003582088263710396,
|
|
"loss": 5.4686,
|
|
"mean_token_accuracy": 0.20491384267807006,
|
|
"num_tokens": 75455247.0,
|
|
"step": 38575
|
|
},
|
|
{
|
|
"entropy": 5.905498409271241,
|
|
"epoch": 3.8565002249212776,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00035817566641545376,
|
|
"loss": 5.3774,
|
|
"mean_token_accuracy": 0.21198478937149048,
|
|
"num_tokens": 75465986.0,
|
|
"step": 38580
|
|
},
|
|
{
|
|
"entropy": 5.948647499084473,
|
|
"epoch": 3.8570000499825063,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0003581425043671897,
|
|
"loss": 5.4239,
|
|
"mean_token_accuracy": 0.20184001475572586,
|
|
"num_tokens": 75475367.0,
|
|
"step": 38585
|
|
},
|
|
{
|
|
"entropy": 5.942521429061889,
|
|
"epoch": 3.8574998750437346,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0003581093402270816,
|
|
"loss": 5.3735,
|
|
"mean_token_accuracy": 0.20219378620386125,
|
|
"num_tokens": 75484531.0,
|
|
"step": 38590
|
|
},
|
|
{
|
|
"entropy": 5.924127912521362,
|
|
"epoch": 3.8579997001049633,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00035807617399596383,
|
|
"loss": 5.4493,
|
|
"mean_token_accuracy": 0.1991154819726944,
|
|
"num_tokens": 75493740.0,
|
|
"step": 38595
|
|
},
|
|
{
|
|
"entropy": 5.913506078720093,
|
|
"epoch": 3.858499525166192,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0003580430056746709,
|
|
"loss": 5.4691,
|
|
"mean_token_accuracy": 0.19955197870731353,
|
|
"num_tokens": 75503225.0,
|
|
"step": 38600
|
|
},
|
|
{
|
|
"entropy": 6.028610420227051,
|
|
"epoch": 3.8589993502274202,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0003580098352640374,
|
|
"loss": 5.5378,
|
|
"mean_token_accuracy": 0.19234509915113449,
|
|
"num_tokens": 75513229.0,
|
|
"step": 38605
|
|
},
|
|
{
|
|
"entropy": 5.924443531036377,
|
|
"epoch": 3.859499175288649,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00035797666276489773,
|
|
"loss": 5.3555,
|
|
"mean_token_accuracy": 0.2035664677619934,
|
|
"num_tokens": 75523299.0,
|
|
"step": 38610
|
|
},
|
|
{
|
|
"entropy": 5.930805969238281,
|
|
"epoch": 3.8599990003498776,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00035794348817808666,
|
|
"loss": 5.5168,
|
|
"mean_token_accuracy": 0.19120816588401796,
|
|
"num_tokens": 75532740.0,
|
|
"step": 38615
|
|
},
|
|
{
|
|
"entropy": 5.905756616592408,
|
|
"epoch": 3.8604988254111063,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00035791031150443864,
|
|
"loss": 5.3976,
|
|
"mean_token_accuracy": 0.20352283716201783,
|
|
"num_tokens": 75543140.0,
|
|
"step": 38620
|
|
},
|
|
{
|
|
"entropy": 5.894943571090698,
|
|
"epoch": 3.8609986504723346,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0003578771327447886,
|
|
"loss": 5.3732,
|
|
"mean_token_accuracy": 0.2024240627884865,
|
|
"num_tokens": 75552482.0,
|
|
"step": 38625
|
|
},
|
|
{
|
|
"entropy": 5.9174947261810305,
|
|
"epoch": 3.8614984755335633,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0003578439518999712,
|
|
"loss": 5.4256,
|
|
"mean_token_accuracy": 0.20265734195709229,
|
|
"num_tokens": 75561564.0,
|
|
"step": 38630
|
|
},
|
|
{
|
|
"entropy": 5.924064016342163,
|
|
"epoch": 3.861998300594792,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00035781076897082134,
|
|
"loss": 5.4932,
|
|
"mean_token_accuracy": 0.19274832457304,
|
|
"num_tokens": 75570352.0,
|
|
"step": 38635
|
|
},
|
|
{
|
|
"entropy": 5.985706853866577,
|
|
"epoch": 3.8624981256560202,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00035777758395817374,
|
|
"loss": 5.5242,
|
|
"mean_token_accuracy": 0.19386618882417678,
|
|
"num_tokens": 75579977.0,
|
|
"step": 38640
|
|
},
|
|
{
|
|
"entropy": 5.879966783523559,
|
|
"epoch": 3.862997950717249,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0003577443968628635,
|
|
"loss": 5.3294,
|
|
"mean_token_accuracy": 0.20758864283561707,
|
|
"num_tokens": 75589926.0,
|
|
"step": 38645
|
|
},
|
|
{
|
|
"entropy": 5.897511005401611,
|
|
"epoch": 3.8634977757784776,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0003577112076857256,
|
|
"loss": 5.2813,
|
|
"mean_token_accuracy": 0.21273604780435562,
|
|
"num_tokens": 75600432.0,
|
|
"step": 38650
|
|
},
|
|
{
|
|
"entropy": 5.855538272857666,
|
|
"epoch": 3.8639976008397063,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00035767801642759485,
|
|
"loss": 5.3737,
|
|
"mean_token_accuracy": 0.19980128407478331,
|
|
"num_tokens": 75610545.0,
|
|
"step": 38655
|
|
},
|
|
{
|
|
"entropy": 5.906834983825684,
|
|
"epoch": 3.8644974259009346,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00035764482308930657,
|
|
"loss": 5.4565,
|
|
"mean_token_accuracy": 0.1954510733485222,
|
|
"num_tokens": 75620430.0,
|
|
"step": 38660
|
|
},
|
|
{
|
|
"entropy": 5.683893728256225,
|
|
"epoch": 3.8649972509621633,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0003576116276716958,
|
|
"loss": 5.1952,
|
|
"mean_token_accuracy": 0.23962364643812178,
|
|
"num_tokens": 75631597.0,
|
|
"step": 38665
|
|
},
|
|
{
|
|
"entropy": 5.992547988891602,
|
|
"epoch": 3.8654970760233915,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0003575784301755977,
|
|
"loss": 5.5061,
|
|
"mean_token_accuracy": 0.18976165652275084,
|
|
"num_tokens": 75641201.0,
|
|
"step": 38670
|
|
},
|
|
{
|
|
"entropy": 6.008423948287964,
|
|
"epoch": 3.8659969010846202,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00035754523060184753,
|
|
"loss": 5.5128,
|
|
"mean_token_accuracy": 0.1941210687160492,
|
|
"num_tokens": 75650465.0,
|
|
"step": 38675
|
|
},
|
|
{
|
|
"entropy": 5.887610197067261,
|
|
"epoch": 3.866496726145849,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00035751202895128065,
|
|
"loss": 5.4119,
|
|
"mean_token_accuracy": 0.19398937970399857,
|
|
"num_tokens": 75659258.0,
|
|
"step": 38680
|
|
},
|
|
{
|
|
"entropy": 5.904757785797119,
|
|
"epoch": 3.8669965512070776,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0003574788252247324,
|
|
"loss": 5.4581,
|
|
"mean_token_accuracy": 0.19242732524871825,
|
|
"num_tokens": 75669103.0,
|
|
"step": 38685
|
|
},
|
|
{
|
|
"entropy": 6.006309461593628,
|
|
"epoch": 3.8674963762683063,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00035744561942303805,
|
|
"loss": 5.5364,
|
|
"mean_token_accuracy": 0.19404992759227752,
|
|
"num_tokens": 75679651.0,
|
|
"step": 38690
|
|
},
|
|
{
|
|
"entropy": 5.876746129989624,
|
|
"epoch": 3.8679962013295346,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0003574124115470332,
|
|
"loss": 5.297,
|
|
"mean_token_accuracy": 0.20842970460653304,
|
|
"num_tokens": 75689668.0,
|
|
"step": 38695
|
|
},
|
|
{
|
|
"entropy": 5.845290040969848,
|
|
"epoch": 3.8684960263907633,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00035737920159755317,
|
|
"loss": 5.3839,
|
|
"mean_token_accuracy": 0.20164426565170288,
|
|
"num_tokens": 75698617.0,
|
|
"step": 38700
|
|
},
|
|
{
|
|
"entropy": 5.878968238830566,
|
|
"epoch": 3.8689958514519915,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0003573459895754337,
|
|
"loss": 5.3673,
|
|
"mean_token_accuracy": 0.19759101569652557,
|
|
"num_tokens": 75707526.0,
|
|
"step": 38705
|
|
},
|
|
{
|
|
"entropy": 5.923867702484131,
|
|
"epoch": 3.8694956765132202,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0003573127754815103,
|
|
"loss": 5.4798,
|
|
"mean_token_accuracy": 0.19299668818712234,
|
|
"num_tokens": 75718251.0,
|
|
"step": 38710
|
|
},
|
|
{
|
|
"entropy": 5.848904752731324,
|
|
"epoch": 3.869995501574449,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00035727955931661863,
|
|
"loss": 5.318,
|
|
"mean_token_accuracy": 0.2105345219373703,
|
|
"num_tokens": 75729567.0,
|
|
"step": 38715
|
|
},
|
|
{
|
|
"entropy": 5.9682238578796385,
|
|
"epoch": 3.8704953266356776,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00035724634108159453,
|
|
"loss": 5.5096,
|
|
"mean_token_accuracy": 0.189920175075531,
|
|
"num_tokens": 75738422.0,
|
|
"step": 38720
|
|
},
|
|
{
|
|
"entropy": 5.889411163330078,
|
|
"epoch": 3.8709951516969063,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0003572131207772736,
|
|
"loss": 5.4525,
|
|
"mean_token_accuracy": 0.20352282226085663,
|
|
"num_tokens": 75748247.0,
|
|
"step": 38725
|
|
},
|
|
{
|
|
"entropy": 5.9221641540527346,
|
|
"epoch": 3.8714949767581346,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0003571798984044916,
|
|
"loss": 5.482,
|
|
"mean_token_accuracy": 0.19293311834335328,
|
|
"num_tokens": 75757169.0,
|
|
"step": 38730
|
|
},
|
|
{
|
|
"entropy": 6.021063899993896,
|
|
"epoch": 3.8719948018193633,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00035714667396408455,
|
|
"loss": 5.5056,
|
|
"mean_token_accuracy": 0.19299972653388978,
|
|
"num_tokens": 75766062.0,
|
|
"step": 38735
|
|
},
|
|
{
|
|
"entropy": 5.913920593261719,
|
|
"epoch": 3.8724946268805915,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0003571134474568883,
|
|
"loss": 5.3547,
|
|
"mean_token_accuracy": 0.21186237782239914,
|
|
"num_tokens": 75776049.0,
|
|
"step": 38740
|
|
},
|
|
{
|
|
"entropy": 5.887004137039185,
|
|
"epoch": 3.8729944519418202,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000357080218883739,
|
|
"loss": 5.4229,
|
|
"mean_token_accuracy": 0.2021134003996849,
|
|
"num_tokens": 75786917.0,
|
|
"step": 38745
|
|
},
|
|
{
|
|
"entropy": 5.903777265548706,
|
|
"epoch": 3.873494277003049,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0003570469882454724,
|
|
"loss": 5.3541,
|
|
"mean_token_accuracy": 0.20865517407655715,
|
|
"num_tokens": 75796393.0,
|
|
"step": 38750
|
|
},
|
|
{
|
|
"entropy": 5.933313369750977,
|
|
"epoch": 3.8739941020642776,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00035701375554292477,
|
|
"loss": 5.4149,
|
|
"mean_token_accuracy": 0.20370143055915832,
|
|
"num_tokens": 75806522.0,
|
|
"step": 38755
|
|
},
|
|
{
|
|
"entropy": 5.993686199188232,
|
|
"epoch": 3.8744939271255063,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00035698052077693206,
|
|
"loss": 5.4942,
|
|
"mean_token_accuracy": 0.19302306622266768,
|
|
"num_tokens": 75817072.0,
|
|
"step": 38760
|
|
},
|
|
{
|
|
"entropy": 5.982120513916016,
|
|
"epoch": 3.8749937521867346,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0003569472839483305,
|
|
"loss": 5.4697,
|
|
"mean_token_accuracy": 0.19550397396087646,
|
|
"num_tokens": 75827858.0,
|
|
"step": 38765
|
|
},
|
|
{
|
|
"entropy": 5.955065727233887,
|
|
"epoch": 3.8754935772479633,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00035691404505795645,
|
|
"loss": 5.421,
|
|
"mean_token_accuracy": 0.2006463423371315,
|
|
"num_tokens": 75837256.0,
|
|
"step": 38770
|
|
},
|
|
{
|
|
"entropy": 5.867808389663696,
|
|
"epoch": 3.8759934023091915,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0003568808041066461,
|
|
"loss": 5.3827,
|
|
"mean_token_accuracy": 0.20273382514715194,
|
|
"num_tokens": 75846853.0,
|
|
"step": 38775
|
|
},
|
|
{
|
|
"entropy": 5.859707641601562,
|
|
"epoch": 3.8764932273704202,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0003568475610952357,
|
|
"loss": 5.378,
|
|
"mean_token_accuracy": 0.19477179497480393,
|
|
"num_tokens": 75856843.0,
|
|
"step": 38780
|
|
},
|
|
{
|
|
"entropy": 5.937252569198608,
|
|
"epoch": 3.876993052431649,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00035681431602456183,
|
|
"loss": 5.4492,
|
|
"mean_token_accuracy": 0.19913258999586106,
|
|
"num_tokens": 75866682.0,
|
|
"step": 38785
|
|
},
|
|
{
|
|
"entropy": 5.935880041122436,
|
|
"epoch": 3.8774928774928776,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00035678106889546087,
|
|
"loss": 5.4736,
|
|
"mean_token_accuracy": 0.19229585975408553,
|
|
"num_tokens": 75876211.0,
|
|
"step": 38790
|
|
},
|
|
{
|
|
"entropy": 6.0173125743865965,
|
|
"epoch": 3.8779927025541063,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00035674781970876905,
|
|
"loss": 5.5015,
|
|
"mean_token_accuracy": 0.19255692660808563,
|
|
"num_tokens": 75885580.0,
|
|
"step": 38795
|
|
},
|
|
{
|
|
"entropy": 5.903500270843506,
|
|
"epoch": 3.8784925276153346,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0003567145684653233,
|
|
"loss": 5.3735,
|
|
"mean_token_accuracy": 0.20536746829748154,
|
|
"num_tokens": 75894831.0,
|
|
"step": 38800
|
|
},
|
|
{
|
|
"entropy": 5.850639724731446,
|
|
"epoch": 3.8789923526765633,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00035668131516596,
|
|
"loss": 5.4416,
|
|
"mean_token_accuracy": 0.19496531784534454,
|
|
"num_tokens": 75905773.0,
|
|
"step": 38805
|
|
},
|
|
{
|
|
"entropy": 5.96590142250061,
|
|
"epoch": 3.8794921777377915,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00035664805981151576,
|
|
"loss": 5.4501,
|
|
"mean_token_accuracy": 0.19660207331180574,
|
|
"num_tokens": 75916264.0,
|
|
"step": 38810
|
|
},
|
|
{
|
|
"entropy": 6.009407615661621,
|
|
"epoch": 3.8799920027990202,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0003566148024028274,
|
|
"loss": 5.5267,
|
|
"mean_token_accuracy": 0.19422237426042557,
|
|
"num_tokens": 75925602.0,
|
|
"step": 38815
|
|
},
|
|
{
|
|
"entropy": 5.87533483505249,
|
|
"epoch": 3.880491827860249,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00035658154294073157,
|
|
"loss": 5.3585,
|
|
"mean_token_accuracy": 0.20543222576379777,
|
|
"num_tokens": 75934027.0,
|
|
"step": 38820
|
|
},
|
|
{
|
|
"entropy": 5.83517689704895,
|
|
"epoch": 3.8809916529214776,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00035654828142606517,
|
|
"loss": 5.3992,
|
|
"mean_token_accuracy": 0.20407965034246445,
|
|
"num_tokens": 75943076.0,
|
|
"step": 38825
|
|
},
|
|
{
|
|
"entropy": 5.96433048248291,
|
|
"epoch": 3.8814914779827063,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000356515017859665,
|
|
"loss": 5.5268,
|
|
"mean_token_accuracy": 0.18632938861846923,
|
|
"num_tokens": 75953569.0,
|
|
"step": 38830
|
|
},
|
|
{
|
|
"entropy": 5.885870504379272,
|
|
"epoch": 3.8819913030439346,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00035648175224236797,
|
|
"loss": 5.3991,
|
|
"mean_token_accuracy": 0.1992517426609993,
|
|
"num_tokens": 75963289.0,
|
|
"step": 38835
|
|
},
|
|
{
|
|
"entropy": 5.871713781356812,
|
|
"epoch": 3.8824911281051633,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00035644848457501096,
|
|
"loss": 5.3263,
|
|
"mean_token_accuracy": 0.20810329616069795,
|
|
"num_tokens": 75973521.0,
|
|
"step": 38840
|
|
},
|
|
{
|
|
"entropy": 6.000151300430298,
|
|
"epoch": 3.8829909531663915,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000356415214858431,
|
|
"loss": 5.56,
|
|
"mean_token_accuracy": 0.18563183397054672,
|
|
"num_tokens": 75984598.0,
|
|
"step": 38845
|
|
},
|
|
{
|
|
"entropy": 5.934888648986816,
|
|
"epoch": 3.8834907782276202,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0003563819430934652,
|
|
"loss": 5.4223,
|
|
"mean_token_accuracy": 0.20003298670053482,
|
|
"num_tokens": 75994178.0,
|
|
"step": 38850
|
|
},
|
|
{
|
|
"entropy": 5.928068208694458,
|
|
"epoch": 3.883990603288849,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0003563486692809508,
|
|
"loss": 5.4258,
|
|
"mean_token_accuracy": 0.202710884809494,
|
|
"num_tokens": 76003848.0,
|
|
"step": 38855
|
|
},
|
|
{
|
|
"entropy": 5.982316017150879,
|
|
"epoch": 3.8844904283500776,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0003563153934217246,
|
|
"loss": 5.5314,
|
|
"mean_token_accuracy": 0.18707114607095718,
|
|
"num_tokens": 76014385.0,
|
|
"step": 38860
|
|
},
|
|
{
|
|
"entropy": 5.862750053405762,
|
|
"epoch": 3.884990253411306,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0003562821155166242,
|
|
"loss": 5.3305,
|
|
"mean_token_accuracy": 0.20165758430957795,
|
|
"num_tokens": 76022997.0,
|
|
"step": 38865
|
|
},
|
|
{
|
|
"entropy": 5.820032691955566,
|
|
"epoch": 3.8854900784725346,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00035624883556648664,
|
|
"loss": 5.3044,
|
|
"mean_token_accuracy": 0.20525601357221604,
|
|
"num_tokens": 76034463.0,
|
|
"step": 38870
|
|
},
|
|
{
|
|
"entropy": 5.928339529037475,
|
|
"epoch": 3.8859899035337633,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0003562155535721492,
|
|
"loss": 5.3791,
|
|
"mean_token_accuracy": 0.207764895260334,
|
|
"num_tokens": 76042909.0,
|
|
"step": 38875
|
|
},
|
|
{
|
|
"entropy": 5.967875623703003,
|
|
"epoch": 3.8864897285949915,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0003561822695344494,
|
|
"loss": 5.5355,
|
|
"mean_token_accuracy": 0.18984848856925965,
|
|
"num_tokens": 76052665.0,
|
|
"step": 38880
|
|
},
|
|
{
|
|
"entropy": 5.918890333175659,
|
|
"epoch": 3.8869895536562202,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0003561489834542246,
|
|
"loss": 5.396,
|
|
"mean_token_accuracy": 0.20064618140459062,
|
|
"num_tokens": 76062628.0,
|
|
"step": 38885
|
|
},
|
|
{
|
|
"entropy": 5.908771896362305,
|
|
"epoch": 3.887489378717449,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00035611569533231224,
|
|
"loss": 5.4894,
|
|
"mean_token_accuracy": 0.20193052142858506,
|
|
"num_tokens": 76072847.0,
|
|
"step": 38890
|
|
},
|
|
{
|
|
"entropy": 5.951827430725098,
|
|
"epoch": 3.8879892037786776,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.00035608240516954995,
|
|
"loss": 5.3616,
|
|
"mean_token_accuracy": 0.20845242142677306,
|
|
"num_tokens": 76081077.0,
|
|
"step": 38895
|
|
},
|
|
{
|
|
"entropy": 5.906956911087036,
|
|
"epoch": 3.888489028839906,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00035604911296677503,
|
|
"loss": 5.3814,
|
|
"mean_token_accuracy": 0.20246455520391465,
|
|
"num_tokens": 76090919.0,
|
|
"step": 38900
|
|
},
|
|
{
|
|
"entropy": 5.908812570571899,
|
|
"epoch": 3.8889888539011346,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0003560158187248254,
|
|
"loss": 5.4225,
|
|
"mean_token_accuracy": 0.20589217990636827,
|
|
"num_tokens": 76101529.0,
|
|
"step": 38905
|
|
},
|
|
{
|
|
"entropy": 5.970638370513916,
|
|
"epoch": 3.8894886789623633,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0003559825224445386,
|
|
"loss": 5.4087,
|
|
"mean_token_accuracy": 0.20439572185277938,
|
|
"num_tokens": 76110332.0,
|
|
"step": 38910
|
|
},
|
|
{
|
|
"entropy": 5.926605081558227,
|
|
"epoch": 3.8899885040235915,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0003559492241267524,
|
|
"loss": 5.5026,
|
|
"mean_token_accuracy": 0.1936708465218544,
|
|
"num_tokens": 76119951.0,
|
|
"step": 38915
|
|
},
|
|
{
|
|
"entropy": 5.916158771514892,
|
|
"epoch": 3.8904883290848202,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00035591592377230447,
|
|
"loss": 5.3929,
|
|
"mean_token_accuracy": 0.20354137867689132,
|
|
"num_tokens": 76129316.0,
|
|
"step": 38920
|
|
},
|
|
{
|
|
"entropy": 5.906718158721924,
|
|
"epoch": 3.890988154146049,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00035588262138203276,
|
|
"loss": 5.3298,
|
|
"mean_token_accuracy": 0.20216991305351256,
|
|
"num_tokens": 76139103.0,
|
|
"step": 38925
|
|
},
|
|
{
|
|
"entropy": 5.922601270675659,
|
|
"epoch": 3.8914879792072776,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00035584931695677516,
|
|
"loss": 5.4325,
|
|
"mean_token_accuracy": 0.20235687643289565,
|
|
"num_tokens": 76148310.0,
|
|
"step": 38930
|
|
},
|
|
{
|
|
"entropy": 5.839245462417603,
|
|
"epoch": 3.891987804268506,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0003558160104973695,
|
|
"loss": 5.3174,
|
|
"mean_token_accuracy": 0.2109463930130005,
|
|
"num_tokens": 76158594.0,
|
|
"step": 38935
|
|
},
|
|
{
|
|
"entropy": 5.922640752792359,
|
|
"epoch": 3.8924876293297346,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0003557827020046538,
|
|
"loss": 5.4673,
|
|
"mean_token_accuracy": 0.20037267059087754,
|
|
"num_tokens": 76168111.0,
|
|
"step": 38940
|
|
},
|
|
{
|
|
"entropy": 5.927685642242432,
|
|
"epoch": 3.8929874543909633,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0003557493914794661,
|
|
"loss": 5.4848,
|
|
"mean_token_accuracy": 0.1944077119231224,
|
|
"num_tokens": 76177616.0,
|
|
"step": 38945
|
|
},
|
|
{
|
|
"entropy": 5.973097515106201,
|
|
"epoch": 3.8934872794521915,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0003557160789226445,
|
|
"loss": 5.4665,
|
|
"mean_token_accuracy": 0.1963161811232567,
|
|
"num_tokens": 76186969.0,
|
|
"step": 38950
|
|
},
|
|
{
|
|
"entropy": 5.898161363601685,
|
|
"epoch": 3.8939871045134202,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0003556827643350271,
|
|
"loss": 5.3531,
|
|
"mean_token_accuracy": 0.20624442994594575,
|
|
"num_tokens": 76196206.0,
|
|
"step": 38955
|
|
},
|
|
{
|
|
"entropy": 5.928978443145752,
|
|
"epoch": 3.894486929574649,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0003556494477174522,
|
|
"loss": 5.4987,
|
|
"mean_token_accuracy": 0.19601942002773284,
|
|
"num_tokens": 76205446.0,
|
|
"step": 38960
|
|
},
|
|
{
|
|
"entropy": 6.073874235153198,
|
|
"epoch": 3.8949867546358776,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00035561612907075794,
|
|
"loss": 5.6988,
|
|
"mean_token_accuracy": 0.1807509370148182,
|
|
"num_tokens": 76214880.0,
|
|
"step": 38965
|
|
},
|
|
{
|
|
"entropy": 5.884599399566651,
|
|
"epoch": 3.895486579697106,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00035558280839578256,
|
|
"loss": 5.3401,
|
|
"mean_token_accuracy": 0.20775689780712128,
|
|
"num_tokens": 76224928.0,
|
|
"step": 38970
|
|
},
|
|
{
|
|
"entropy": 5.942240571975708,
|
|
"epoch": 3.8959864047583346,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0003555494856933644,
|
|
"loss": 5.4251,
|
|
"mean_token_accuracy": 0.19780954867601394,
|
|
"num_tokens": 76233802.0,
|
|
"step": 38975
|
|
},
|
|
{
|
|
"entropy": 5.951817607879638,
|
|
"epoch": 3.8964862298195633,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.000355516160964342,
|
|
"loss": 5.4462,
|
|
"mean_token_accuracy": 0.19694766402244568,
|
|
"num_tokens": 76243303.0,
|
|
"step": 38980
|
|
},
|
|
{
|
|
"entropy": 5.882217979431152,
|
|
"epoch": 3.8969860548807915,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00035548283420955377,
|
|
"loss": 5.4185,
|
|
"mean_token_accuracy": 0.19248166531324387,
|
|
"num_tokens": 76253154.0,
|
|
"step": 38985
|
|
},
|
|
{
|
|
"entropy": 5.979866027832031,
|
|
"epoch": 3.8974858799420202,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00035544950542983793,
|
|
"loss": 5.5008,
|
|
"mean_token_accuracy": 0.19769063591957092,
|
|
"num_tokens": 76262007.0,
|
|
"step": 38990
|
|
},
|
|
{
|
|
"entropy": 5.995425701141357,
|
|
"epoch": 3.897985705003249,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00035541617462603336,
|
|
"loss": 5.4899,
|
|
"mean_token_accuracy": 0.19076629728078842,
|
|
"num_tokens": 76271104.0,
|
|
"step": 38995
|
|
},
|
|
{
|
|
"entropy": 5.872303295135498,
|
|
"epoch": 3.8984855300644776,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0003553828417989786,
|
|
"loss": 5.4419,
|
|
"mean_token_accuracy": 0.20457399040460586,
|
|
"num_tokens": 76282285.0,
|
|
"step": 39000
|
|
},
|
|
{
|
|
"epoch": 3.8984855300644776,
|
|
"eval_entropy": 5.635780362977222,
|
|
"eval_loss": 5.535248756408691,
|
|
"eval_mean_token_accuracy": 0.20434680147515502,
|
|
"eval_num_tokens": 76282285.0,
|
|
"eval_runtime": 23.7314,
|
|
"eval_samples_per_second": 1308.182,
|
|
"eval_steps_per_second": 163.539,
|
|
"step": 39000
|
|
},
|
|
{
|
|
"entropy": 5.829316139221191,
|
|
"epoch": 3.898985355125706,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00035534950694951213,
|
|
"loss": 5.2986,
|
|
"mean_token_accuracy": 0.20463787168264388,
|
|
"num_tokens": 76291465.0,
|
|
"step": 39005
|
|
},
|
|
{
|
|
"entropy": 5.762841415405274,
|
|
"epoch": 3.8994851801869346,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0003553161700784728,
|
|
"loss": 5.3223,
|
|
"mean_token_accuracy": 0.22062199115753173,
|
|
"num_tokens": 76300641.0,
|
|
"step": 39010
|
|
},
|
|
{
|
|
"entropy": 5.9163566589355465,
|
|
"epoch": 3.8999850052481633,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0003552828311866992,
|
|
"loss": 5.4018,
|
|
"mean_token_accuracy": 0.20751187354326248,
|
|
"num_tokens": 76310747.0,
|
|
"step": 39015
|
|
},
|
|
{
|
|
"entropy": 5.946560573577881,
|
|
"epoch": 3.9004848303093915,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0003552494902750303,
|
|
"loss": 5.3992,
|
|
"mean_token_accuracy": 0.20366501659154893,
|
|
"num_tokens": 76321307.0,
|
|
"step": 39020
|
|
},
|
|
{
|
|
"entropy": 5.863547277450562,
|
|
"epoch": 3.9009846553706202,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00035521614734430483,
|
|
"loss": 5.4472,
|
|
"mean_token_accuracy": 0.1987607166171074,
|
|
"num_tokens": 76330807.0,
|
|
"step": 39025
|
|
},
|
|
{
|
|
"entropy": 5.8748046398162845,
|
|
"epoch": 3.901484480431849,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00035518280239536174,
|
|
"loss": 5.3283,
|
|
"mean_token_accuracy": 0.2101208671927452,
|
|
"num_tokens": 76340683.0,
|
|
"step": 39030
|
|
},
|
|
{
|
|
"entropy": 5.825131416320801,
|
|
"epoch": 3.9019843054930776,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0003551494554290401,
|
|
"loss": 5.2904,
|
|
"mean_token_accuracy": 0.2139466643333435,
|
|
"num_tokens": 76350793.0,
|
|
"step": 39035
|
|
},
|
|
{
|
|
"entropy": 5.965637159347534,
|
|
"epoch": 3.902484130554306,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00035511610644617863,
|
|
"loss": 5.4877,
|
|
"mean_token_accuracy": 0.19904567450284957,
|
|
"num_tokens": 76360221.0,
|
|
"step": 39040
|
|
},
|
|
{
|
|
"entropy": 5.8624077320098875,
|
|
"epoch": 3.9029839556155346,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0003550827554476166,
|
|
"loss": 5.4042,
|
|
"mean_token_accuracy": 0.20484892129898072,
|
|
"num_tokens": 76369094.0,
|
|
"step": 39045
|
|
},
|
|
{
|
|
"entropy": 5.810252523422241,
|
|
"epoch": 3.9034837806767633,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00035504940243419303,
|
|
"loss": 5.3965,
|
|
"mean_token_accuracy": 0.2024252563714981,
|
|
"num_tokens": 76379044.0,
|
|
"step": 39050
|
|
},
|
|
{
|
|
"entropy": 5.875404024124146,
|
|
"epoch": 3.9039836057379915,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0003550160474067471,
|
|
"loss": 5.4378,
|
|
"mean_token_accuracy": 0.1988320454955101,
|
|
"num_tokens": 76388473.0,
|
|
"step": 39055
|
|
},
|
|
{
|
|
"entropy": 5.97124285697937,
|
|
"epoch": 3.9044834307992202,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000354982690366118,
|
|
"loss": 5.5364,
|
|
"mean_token_accuracy": 0.19010760337114335,
|
|
"num_tokens": 76400490.0,
|
|
"step": 39060
|
|
},
|
|
{
|
|
"entropy": 5.963494729995728,
|
|
"epoch": 3.904983255860449,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.000354949331313145,
|
|
"loss": 5.4889,
|
|
"mean_token_accuracy": 0.19725898206233977,
|
|
"num_tokens": 76410418.0,
|
|
"step": 39065
|
|
},
|
|
{
|
|
"entropy": 5.938531398773193,
|
|
"epoch": 3.9054830809216776,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00035491597024866746,
|
|
"loss": 5.5748,
|
|
"mean_token_accuracy": 0.19014397263526917,
|
|
"num_tokens": 76419878.0,
|
|
"step": 39070
|
|
},
|
|
{
|
|
"entropy": 5.893889760971069,
|
|
"epoch": 3.905982905982906,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0003548826071735246,
|
|
"loss": 5.4345,
|
|
"mean_token_accuracy": 0.19878777712583542,
|
|
"num_tokens": 76430078.0,
|
|
"step": 39075
|
|
},
|
|
{
|
|
"entropy": 5.877825975418091,
|
|
"epoch": 3.9064827310441346,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0003548492420885559,
|
|
"loss": 5.4602,
|
|
"mean_token_accuracy": 0.19903624951839446,
|
|
"num_tokens": 76439259.0,
|
|
"step": 39080
|
|
},
|
|
{
|
|
"entropy": 5.968653345108033,
|
|
"epoch": 3.9069825561053633,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00035481587499460083,
|
|
"loss": 5.4024,
|
|
"mean_token_accuracy": 0.20097783654928209,
|
|
"num_tokens": 76448622.0,
|
|
"step": 39085
|
|
},
|
|
{
|
|
"entropy": 5.8125646114349365,
|
|
"epoch": 3.9074823811665915,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0003547825058924989,
|
|
"loss": 5.3202,
|
|
"mean_token_accuracy": 0.20822692960500716,
|
|
"num_tokens": 76458197.0,
|
|
"step": 39090
|
|
},
|
|
{
|
|
"entropy": 5.91019835472107,
|
|
"epoch": 3.90798220622782,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0003547491347830896,
|
|
"loss": 5.4424,
|
|
"mean_token_accuracy": 0.2032961830496788,
|
|
"num_tokens": 76466787.0,
|
|
"step": 39095
|
|
},
|
|
{
|
|
"entropy": 5.960926818847656,
|
|
"epoch": 3.908482031289049,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00035471576166721267,
|
|
"loss": 5.4914,
|
|
"mean_token_accuracy": 0.19184990972280502,
|
|
"num_tokens": 76475610.0,
|
|
"step": 39100
|
|
},
|
|
{
|
|
"entropy": 5.870230722427368,
|
|
"epoch": 3.9089818563502776,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00035468238654570765,
|
|
"loss": 5.3765,
|
|
"mean_token_accuracy": 0.20098086446523666,
|
|
"num_tokens": 76484903.0,
|
|
"step": 39105
|
|
},
|
|
{
|
|
"entropy": 5.938354110717773,
|
|
"epoch": 3.909481681411506,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0003546490094194142,
|
|
"loss": 5.473,
|
|
"mean_token_accuracy": 0.1956272080540657,
|
|
"num_tokens": 76495908.0,
|
|
"step": 39110
|
|
},
|
|
{
|
|
"entropy": 6.02572340965271,
|
|
"epoch": 3.9099815064727346,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00035461563028917233,
|
|
"loss": 5.5179,
|
|
"mean_token_accuracy": 0.19274607300758362,
|
|
"num_tokens": 76505851.0,
|
|
"step": 39115
|
|
},
|
|
{
|
|
"entropy": 5.898442125320434,
|
|
"epoch": 3.9104813315339633,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00035458224915582156,
|
|
"loss": 5.4031,
|
|
"mean_token_accuracy": 0.1945781424641609,
|
|
"num_tokens": 76516207.0,
|
|
"step": 39120
|
|
},
|
|
{
|
|
"entropy": 5.8774536609649655,
|
|
"epoch": 3.9109811565951915,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00035454886602020194,
|
|
"loss": 5.3825,
|
|
"mean_token_accuracy": 0.20449555069208145,
|
|
"num_tokens": 76526882.0,
|
|
"step": 39125
|
|
},
|
|
{
|
|
"entropy": 5.896577262878418,
|
|
"epoch": 3.91148098165642,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00035451548088315325,
|
|
"loss": 5.4445,
|
|
"mean_token_accuracy": 0.19164662957191467,
|
|
"num_tokens": 76536865.0,
|
|
"step": 39130
|
|
},
|
|
{
|
|
"entropy": 5.88628511428833,
|
|
"epoch": 3.911980806717649,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0003544820937455156,
|
|
"loss": 5.3942,
|
|
"mean_token_accuracy": 0.19945187866687775,
|
|
"num_tokens": 76547046.0,
|
|
"step": 39135
|
|
},
|
|
{
|
|
"entropy": 5.850132942199707,
|
|
"epoch": 3.9124806317788776,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00035444870460812894,
|
|
"loss": 5.3319,
|
|
"mean_token_accuracy": 0.21162482500076293,
|
|
"num_tokens": 76556941.0,
|
|
"step": 39140
|
|
},
|
|
{
|
|
"entropy": 5.939380788803101,
|
|
"epoch": 3.912980456840106,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00035441531347183325,
|
|
"loss": 5.4892,
|
|
"mean_token_accuracy": 0.18930096477270125,
|
|
"num_tokens": 76566843.0,
|
|
"step": 39145
|
|
},
|
|
{
|
|
"entropy": 5.888040351867676,
|
|
"epoch": 3.9134802819013346,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0003543819203374688,
|
|
"loss": 5.4439,
|
|
"mean_token_accuracy": 0.19783090502023698,
|
|
"num_tokens": 76576069.0,
|
|
"step": 39150
|
|
},
|
|
{
|
|
"entropy": 5.942334938049316,
|
|
"epoch": 3.9139801069625633,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0003543485252058756,
|
|
"loss": 5.4334,
|
|
"mean_token_accuracy": 0.20286260843276976,
|
|
"num_tokens": 76587000.0,
|
|
"step": 39155
|
|
},
|
|
{
|
|
"entropy": 5.928274345397949,
|
|
"epoch": 3.9144799320237915,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0003543151280778939,
|
|
"loss": 5.4157,
|
|
"mean_token_accuracy": 0.2029333755373955,
|
|
"num_tokens": 76596133.0,
|
|
"step": 39160
|
|
},
|
|
{
|
|
"entropy": 5.911880207061768,
|
|
"epoch": 3.91497975708502,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.000354281728954364,
|
|
"loss": 5.4466,
|
|
"mean_token_accuracy": 0.20041777491569518,
|
|
"num_tokens": 76606249.0,
|
|
"step": 39165
|
|
},
|
|
{
|
|
"entropy": 5.870549726486206,
|
|
"epoch": 3.915479582146249,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00035424832783612623,
|
|
"loss": 5.4609,
|
|
"mean_token_accuracy": 0.19926988184452057,
|
|
"num_tokens": 76615822.0,
|
|
"step": 39170
|
|
},
|
|
{
|
|
"entropy": 5.845954847335816,
|
|
"epoch": 3.9159794072074776,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0003542149247240209,
|
|
"loss": 5.3699,
|
|
"mean_token_accuracy": 0.20625622421503068,
|
|
"num_tokens": 76625677.0,
|
|
"step": 39175
|
|
},
|
|
{
|
|
"entropy": 5.987308406829834,
|
|
"epoch": 3.916479232268706,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00035418151961888846,
|
|
"loss": 5.5012,
|
|
"mean_token_accuracy": 0.1970837026834488,
|
|
"num_tokens": 76634783.0,
|
|
"step": 39180
|
|
},
|
|
{
|
|
"entropy": 5.89487886428833,
|
|
"epoch": 3.9169790573299346,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.00035414811252156936,
|
|
"loss": 5.4222,
|
|
"mean_token_accuracy": 0.2003050997853279,
|
|
"num_tokens": 76644299.0,
|
|
"step": 39185
|
|
},
|
|
{
|
|
"entropy": 5.927688694000244,
|
|
"epoch": 3.917478882391163,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0003541147034329041,
|
|
"loss": 5.4604,
|
|
"mean_token_accuracy": 0.19677974432706832,
|
|
"num_tokens": 76653992.0,
|
|
"step": 39190
|
|
},
|
|
{
|
|
"entropy": 5.9057084083557125,
|
|
"epoch": 3.9179787074523915,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00035408129235373325,
|
|
"loss": 5.3962,
|
|
"mean_token_accuracy": 0.2093646064400673,
|
|
"num_tokens": 76663723.0,
|
|
"step": 39195
|
|
},
|
|
{
|
|
"entropy": 5.902581024169922,
|
|
"epoch": 3.91847853251362,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00035404787928489746,
|
|
"loss": 5.3757,
|
|
"mean_token_accuracy": 0.19834733605384827,
|
|
"num_tokens": 76673299.0,
|
|
"step": 39200
|
|
},
|
|
{
|
|
"entropy": 5.879455280303955,
|
|
"epoch": 3.918978357574849,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00035401446422723737,
|
|
"loss": 5.3529,
|
|
"mean_token_accuracy": 0.20751993209123612,
|
|
"num_tokens": 76683264.0,
|
|
"step": 39205
|
|
},
|
|
{
|
|
"entropy": 5.872554111480713,
|
|
"epoch": 3.9194781826360776,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00035398104718159366,
|
|
"loss": 5.3854,
|
|
"mean_token_accuracy": 0.20748020708560944,
|
|
"num_tokens": 76693004.0,
|
|
"step": 39210
|
|
},
|
|
{
|
|
"entropy": 5.771066761016845,
|
|
"epoch": 3.919978007697306,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0003539476281488072,
|
|
"loss": 5.3394,
|
|
"mean_token_accuracy": 0.2046721711754799,
|
|
"num_tokens": 76701885.0,
|
|
"step": 39215
|
|
},
|
|
{
|
|
"entropy": 5.841376209259034,
|
|
"epoch": 3.9204778327585346,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00035391420712971864,
|
|
"loss": 5.2667,
|
|
"mean_token_accuracy": 0.20997015982866288,
|
|
"num_tokens": 76711224.0,
|
|
"step": 39220
|
|
},
|
|
{
|
|
"entropy": 5.987983083724975,
|
|
"epoch": 3.920977657819763,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.000353880784125169,
|
|
"loss": 5.5342,
|
|
"mean_token_accuracy": 0.1964841827750206,
|
|
"num_tokens": 76721258.0,
|
|
"step": 39225
|
|
},
|
|
{
|
|
"entropy": 5.941566801071167,
|
|
"epoch": 3.9214774828809915,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00035384735913599906,
|
|
"loss": 5.4433,
|
|
"mean_token_accuracy": 0.1955796167254448,
|
|
"num_tokens": 76731510.0,
|
|
"step": 39230
|
|
},
|
|
{
|
|
"entropy": 5.835210227966309,
|
|
"epoch": 3.92197730794222,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0003538139321630499,
|
|
"loss": 5.3575,
|
|
"mean_token_accuracy": 0.20815038532018662,
|
|
"num_tokens": 76741221.0,
|
|
"step": 39235
|
|
},
|
|
{
|
|
"entropy": 5.889283800125122,
|
|
"epoch": 3.922477133003449,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0003537805032071625,
|
|
"loss": 5.3831,
|
|
"mean_token_accuracy": 0.2011759102344513,
|
|
"num_tokens": 76751246.0,
|
|
"step": 39240
|
|
},
|
|
{
|
|
"entropy": 5.87063193321228,
|
|
"epoch": 3.9229769580646776,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0003537470722691779,
|
|
"loss": 5.3688,
|
|
"mean_token_accuracy": 0.2132796749472618,
|
|
"num_tokens": 76761346.0,
|
|
"step": 39245
|
|
},
|
|
{
|
|
"entropy": 5.8245257377624515,
|
|
"epoch": 3.923476783125906,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0003537136393499372,
|
|
"loss": 5.4242,
|
|
"mean_token_accuracy": 0.19470858722925186,
|
|
"num_tokens": 76771463.0,
|
|
"step": 39250
|
|
},
|
|
{
|
|
"entropy": 5.860735273361206,
|
|
"epoch": 3.9239766081871346,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0003536802044502816,
|
|
"loss": 5.4047,
|
|
"mean_token_accuracy": 0.20071855783462525,
|
|
"num_tokens": 76781079.0,
|
|
"step": 39255
|
|
},
|
|
{
|
|
"entropy": 5.904424238204956,
|
|
"epoch": 3.924476433248363,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00035364676757105234,
|
|
"loss": 5.369,
|
|
"mean_token_accuracy": 0.20631918758153917,
|
|
"num_tokens": 76790582.0,
|
|
"step": 39260
|
|
},
|
|
{
|
|
"entropy": 5.963982677459716,
|
|
"epoch": 3.9249762583095915,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0003536133287130906,
|
|
"loss": 5.4481,
|
|
"mean_token_accuracy": 0.19849318712949754,
|
|
"num_tokens": 76800119.0,
|
|
"step": 39265
|
|
},
|
|
{
|
|
"entropy": 5.927193117141724,
|
|
"epoch": 3.92547608337082,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00035357988787723774,
|
|
"loss": 5.4469,
|
|
"mean_token_accuracy": 0.20026382356882094,
|
|
"num_tokens": 76810190.0,
|
|
"step": 39270
|
|
},
|
|
{
|
|
"entropy": 5.933011198043824,
|
|
"epoch": 3.925975908432049,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00035354644506433515,
|
|
"loss": 5.4748,
|
|
"mean_token_accuracy": 0.1931094378232956,
|
|
"num_tokens": 76819130.0,
|
|
"step": 39275
|
|
},
|
|
{
|
|
"entropy": 5.898830413818359,
|
|
"epoch": 3.9264757334932776,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0003535130002752242,
|
|
"loss": 5.3239,
|
|
"mean_token_accuracy": 0.20572028458118438,
|
|
"num_tokens": 76828375.0,
|
|
"step": 39280
|
|
},
|
|
{
|
|
"entropy": 5.702844047546387,
|
|
"epoch": 3.926975558554506,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0003534795535107464,
|
|
"loss": 5.19,
|
|
"mean_token_accuracy": 0.2282722547650337,
|
|
"num_tokens": 76838423.0,
|
|
"step": 39285
|
|
},
|
|
{
|
|
"entropy": 5.8967698097229,
|
|
"epoch": 3.9274753836157346,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00035344610477174314,
|
|
"loss": 5.3883,
|
|
"mean_token_accuracy": 0.20168508142232894,
|
|
"num_tokens": 76848558.0,
|
|
"step": 39290
|
|
},
|
|
{
|
|
"entropy": 5.962520599365234,
|
|
"epoch": 3.927975208676963,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00035341265405905615,
|
|
"loss": 5.4576,
|
|
"mean_token_accuracy": 0.1979383647441864,
|
|
"num_tokens": 76857251.0,
|
|
"step": 39295
|
|
},
|
|
{
|
|
"entropy": 5.860413074493408,
|
|
"epoch": 3.9284750337381915,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000353379201373527,
|
|
"loss": 5.2738,
|
|
"mean_token_accuracy": 0.2085508793592453,
|
|
"num_tokens": 76866244.0,
|
|
"step": 39300
|
|
},
|
|
{
|
|
"entropy": 5.853622674942017,
|
|
"epoch": 3.92897485879942,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00035334574671599717,
|
|
"loss": 5.3678,
|
|
"mean_token_accuracy": 0.19745078086853027,
|
|
"num_tokens": 76875679.0,
|
|
"step": 39305
|
|
},
|
|
{
|
|
"entropy": 5.8972084522247314,
|
|
"epoch": 3.929474683860649,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0003533122900873086,
|
|
"loss": 5.4377,
|
|
"mean_token_accuracy": 0.19305181056261062,
|
|
"num_tokens": 76886440.0,
|
|
"step": 39310
|
|
},
|
|
{
|
|
"entropy": 5.960725164413452,
|
|
"epoch": 3.9299745089218776,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0003532788314883029,
|
|
"loss": 5.4911,
|
|
"mean_token_accuracy": 0.19456148892641068,
|
|
"num_tokens": 76896541.0,
|
|
"step": 39315
|
|
},
|
|
{
|
|
"entropy": 5.947029161453247,
|
|
"epoch": 3.930474333983106,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00035324537091982206,
|
|
"loss": 5.4064,
|
|
"mean_token_accuracy": 0.20064301788806915,
|
|
"num_tokens": 76905339.0,
|
|
"step": 39320
|
|
},
|
|
{
|
|
"entropy": 5.905066299438476,
|
|
"epoch": 3.9309741590443346,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00035321190838270773,
|
|
"loss": 5.321,
|
|
"mean_token_accuracy": 0.21358383893966676,
|
|
"num_tokens": 76916004.0,
|
|
"step": 39325
|
|
},
|
|
{
|
|
"entropy": 5.872992992401123,
|
|
"epoch": 3.931473984105563,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.000353178443877802,
|
|
"loss": 5.3246,
|
|
"mean_token_accuracy": 0.20288608372211456,
|
|
"num_tokens": 76924885.0,
|
|
"step": 39330
|
|
},
|
|
{
|
|
"entropy": 5.865999412536621,
|
|
"epoch": 3.9319738091667915,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00035314497740594666,
|
|
"loss": 5.4206,
|
|
"mean_token_accuracy": 0.19798905849456788,
|
|
"num_tokens": 76934874.0,
|
|
"step": 39335
|
|
},
|
|
{
|
|
"entropy": 5.924005031585693,
|
|
"epoch": 3.93247363422802,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0003531115089679837,
|
|
"loss": 5.41,
|
|
"mean_token_accuracy": 0.20271172970533372,
|
|
"num_tokens": 76945831.0,
|
|
"step": 39340
|
|
},
|
|
{
|
|
"entropy": 5.891977024078369,
|
|
"epoch": 3.932973459289249,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00035307803856475544,
|
|
"loss": 5.3871,
|
|
"mean_token_accuracy": 0.2049300953745842,
|
|
"num_tokens": 76955972.0,
|
|
"step": 39345
|
|
},
|
|
{
|
|
"entropy": 5.99162802696228,
|
|
"epoch": 3.9334732843504776,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0003530445661971038,
|
|
"loss": 5.5486,
|
|
"mean_token_accuracy": 0.18865056037902833,
|
|
"num_tokens": 76965940.0,
|
|
"step": 39350
|
|
},
|
|
{
|
|
"entropy": 5.8734063625335695,
|
|
"epoch": 3.933973109411706,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00035301109186587095,
|
|
"loss": 5.2641,
|
|
"mean_token_accuracy": 0.20907797217369078,
|
|
"num_tokens": 76975302.0,
|
|
"step": 39355
|
|
},
|
|
{
|
|
"entropy": 5.8795641422271725,
|
|
"epoch": 3.9344729344729346,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00035297761557189904,
|
|
"loss": 5.4288,
|
|
"mean_token_accuracy": 0.19678483605384828,
|
|
"num_tokens": 76984788.0,
|
|
"step": 39360
|
|
},
|
|
{
|
|
"entropy": 5.818291330337525,
|
|
"epoch": 3.934972759534163,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00035294413731603035,
|
|
"loss": 5.3744,
|
|
"mean_token_accuracy": 0.20655304193496704,
|
|
"num_tokens": 76994608.0,
|
|
"step": 39365
|
|
},
|
|
{
|
|
"entropy": 5.923579263687134,
|
|
"epoch": 3.9354725845953915,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00035291065709910734,
|
|
"loss": 5.4464,
|
|
"mean_token_accuracy": 0.1942530855536461,
|
|
"num_tokens": 77004070.0,
|
|
"step": 39370
|
|
},
|
|
{
|
|
"entropy": 5.96448130607605,
|
|
"epoch": 3.93597240965662,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0003528771749219722,
|
|
"loss": 5.4493,
|
|
"mean_token_accuracy": 0.19590165019035338,
|
|
"num_tokens": 77013807.0,
|
|
"step": 39375
|
|
},
|
|
{
|
|
"entropy": 5.828288888931274,
|
|
"epoch": 3.936472234717849,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0003528436907854674,
|
|
"loss": 5.3698,
|
|
"mean_token_accuracy": 0.19923969358205795,
|
|
"num_tokens": 77022967.0,
|
|
"step": 39380
|
|
},
|
|
{
|
|
"entropy": 5.835413932800293,
|
|
"epoch": 3.936972059779077,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0003528102046904354,
|
|
"loss": 5.3709,
|
|
"mean_token_accuracy": 0.20461405813694,
|
|
"num_tokens": 77032629.0,
|
|
"step": 39385
|
|
},
|
|
{
|
|
"entropy": 5.873472785949707,
|
|
"epoch": 3.937471884840306,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0003527767166377186,
|
|
"loss": 5.3298,
|
|
"mean_token_accuracy": 0.20155592411756515,
|
|
"num_tokens": 77042449.0,
|
|
"step": 39390
|
|
},
|
|
{
|
|
"entropy": 5.8307921409606935,
|
|
"epoch": 3.9379717099015346,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0003527432266281597,
|
|
"loss": 5.3791,
|
|
"mean_token_accuracy": 0.20166189819574357,
|
|
"num_tokens": 77052048.0,
|
|
"step": 39395
|
|
},
|
|
{
|
|
"entropy": 6.017306709289551,
|
|
"epoch": 3.938471534962763,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0003527097346626011,
|
|
"loss": 5.5851,
|
|
"mean_token_accuracy": 0.18375966250896453,
|
|
"num_tokens": 77062438.0,
|
|
"step": 39400
|
|
},
|
|
{
|
|
"entropy": 5.86997504234314,
|
|
"epoch": 3.9389713600239915,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00035267624074188564,
|
|
"loss": 5.3178,
|
|
"mean_token_accuracy": 0.2048723116517067,
|
|
"num_tokens": 77071584.0,
|
|
"step": 39405
|
|
},
|
|
{
|
|
"entropy": 5.820470809936523,
|
|
"epoch": 3.93947118508522,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00035264274486685593,
|
|
"loss": 5.4094,
|
|
"mean_token_accuracy": 0.20776069909334183,
|
|
"num_tokens": 77082099.0,
|
|
"step": 39410
|
|
},
|
|
{
|
|
"entropy": 5.737512588500977,
|
|
"epoch": 3.939971010146449,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0003526092470383548,
|
|
"loss": 5.2802,
|
|
"mean_token_accuracy": 0.20824412554502486,
|
|
"num_tokens": 77091260.0,
|
|
"step": 39415
|
|
},
|
|
{
|
|
"entropy": 5.990840005874634,
|
|
"epoch": 3.940470835207677,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00035257574725722495,
|
|
"loss": 5.51,
|
|
"mean_token_accuracy": 0.19461533129215242,
|
|
"num_tokens": 77101467.0,
|
|
"step": 39420
|
|
},
|
|
{
|
|
"entropy": 6.015194463729858,
|
|
"epoch": 3.940970660268906,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00035254224552430923,
|
|
"loss": 5.5903,
|
|
"mean_token_accuracy": 0.18775151968002318,
|
|
"num_tokens": 77111881.0,
|
|
"step": 39425
|
|
},
|
|
{
|
|
"entropy": 5.887946319580078,
|
|
"epoch": 3.9414704853301346,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00035250874184045063,
|
|
"loss": 5.3477,
|
|
"mean_token_accuracy": 0.20857197493314744,
|
|
"num_tokens": 77121944.0,
|
|
"step": 39430
|
|
},
|
|
{
|
|
"entropy": 5.895471715927124,
|
|
"epoch": 3.941970310391363,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00035247523620649196,
|
|
"loss": 5.3794,
|
|
"mean_token_accuracy": 0.20006880760192872,
|
|
"num_tokens": 77131576.0,
|
|
"step": 39435
|
|
},
|
|
{
|
|
"entropy": 5.918225622177124,
|
|
"epoch": 3.9424701354525915,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00035244172862327635,
|
|
"loss": 5.4354,
|
|
"mean_token_accuracy": 0.19772546291351317,
|
|
"num_tokens": 77141013.0,
|
|
"step": 39440
|
|
},
|
|
{
|
|
"entropy": 5.885604333877564,
|
|
"epoch": 3.94296996051382,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00035240821909164675,
|
|
"loss": 5.4732,
|
|
"mean_token_accuracy": 0.19993555247783662,
|
|
"num_tokens": 77151386.0,
|
|
"step": 39445
|
|
},
|
|
{
|
|
"entropy": 5.9743602752685545,
|
|
"epoch": 3.943469785575049,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0003523747076124462,
|
|
"loss": 5.5101,
|
|
"mean_token_accuracy": 0.19277986288070678,
|
|
"num_tokens": 77161382.0,
|
|
"step": 39450
|
|
},
|
|
{
|
|
"entropy": 5.832074928283691,
|
|
"epoch": 3.943969610636277,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00035234119418651804,
|
|
"loss": 5.2997,
|
|
"mean_token_accuracy": 0.21328236609697343,
|
|
"num_tokens": 77173000.0,
|
|
"step": 39455
|
|
},
|
|
{
|
|
"entropy": 5.870760583877564,
|
|
"epoch": 3.944469435697506,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0003523076788147053,
|
|
"loss": 5.3973,
|
|
"mean_token_accuracy": 0.19889612942934037,
|
|
"num_tokens": 77183149.0,
|
|
"step": 39460
|
|
},
|
|
{
|
|
"entropy": 5.888088750839233,
|
|
"epoch": 3.9449692607587346,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0003522741614978512,
|
|
"loss": 5.4105,
|
|
"mean_token_accuracy": 0.2007528930902481,
|
|
"num_tokens": 77192667.0,
|
|
"step": 39465
|
|
},
|
|
{
|
|
"entropy": 5.94702672958374,
|
|
"epoch": 3.945469085819963,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00035224064223679914,
|
|
"loss": 5.4762,
|
|
"mean_token_accuracy": 0.19765177369117737,
|
|
"num_tokens": 77202670.0,
|
|
"step": 39470
|
|
},
|
|
{
|
|
"entropy": 5.9642448902130125,
|
|
"epoch": 3.9459689108811915,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0003522071210323924,
|
|
"loss": 5.4767,
|
|
"mean_token_accuracy": 0.19595250189304353,
|
|
"num_tokens": 77213060.0,
|
|
"step": 39475
|
|
},
|
|
{
|
|
"entropy": 5.916742897033691,
|
|
"epoch": 3.94646873594242,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0003521735978854743,
|
|
"loss": 5.461,
|
|
"mean_token_accuracy": 0.1938777193427086,
|
|
"num_tokens": 77223272.0,
|
|
"step": 39480
|
|
},
|
|
{
|
|
"entropy": 5.831552410125733,
|
|
"epoch": 3.946968561003649,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0003521400727968884,
|
|
"loss": 5.3683,
|
|
"mean_token_accuracy": 0.20474896132946013,
|
|
"num_tokens": 77233350.0,
|
|
"step": 39485
|
|
},
|
|
{
|
|
"entropy": 5.909369707107544,
|
|
"epoch": 3.947468386064877,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00035210654576747806,
|
|
"loss": 5.4029,
|
|
"mean_token_accuracy": 0.19879352003335954,
|
|
"num_tokens": 77242614.0,
|
|
"step": 39490
|
|
},
|
|
{
|
|
"entropy": 5.948340320587159,
|
|
"epoch": 3.947968211126106,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00035207301679808685,
|
|
"loss": 5.4596,
|
|
"mean_token_accuracy": 0.1995987668633461,
|
|
"num_tokens": 77253579.0,
|
|
"step": 39495
|
|
},
|
|
{
|
|
"entropy": 5.9663163185119625,
|
|
"epoch": 3.9484680361873346,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0003520394858895584,
|
|
"loss": 5.4554,
|
|
"mean_token_accuracy": 0.1997484892606735,
|
|
"num_tokens": 77262921.0,
|
|
"step": 39500
|
|
},
|
|
{
|
|
"entropy": 5.822769546508789,
|
|
"epoch": 3.948967861248563,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0003520059530427364,
|
|
"loss": 5.2863,
|
|
"mean_token_accuracy": 0.20700518190860748,
|
|
"num_tokens": 77272261.0,
|
|
"step": 39505
|
|
},
|
|
{
|
|
"entropy": 5.8723796844482425,
|
|
"epoch": 3.9494676863097915,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0003519724182584643,
|
|
"loss": 5.4745,
|
|
"mean_token_accuracy": 0.19800956696271896,
|
|
"num_tokens": 77282295.0,
|
|
"step": 39510
|
|
},
|
|
{
|
|
"entropy": 5.822712993621826,
|
|
"epoch": 3.94996751137102,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0003519388815375861,
|
|
"loss": 5.2959,
|
|
"mean_token_accuracy": 0.21064318716526031,
|
|
"num_tokens": 77291300.0,
|
|
"step": 39515
|
|
},
|
|
{
|
|
"entropy": 5.891577100753784,
|
|
"epoch": 3.950467336432249,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00035190534288094533,
|
|
"loss": 5.4328,
|
|
"mean_token_accuracy": 0.20027821213006974,
|
|
"num_tokens": 77303195.0,
|
|
"step": 39520
|
|
},
|
|
{
|
|
"entropy": 5.872915029525757,
|
|
"epoch": 3.950967161493477,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00035187180228938593,
|
|
"loss": 5.3075,
|
|
"mean_token_accuracy": 0.21006383746862411,
|
|
"num_tokens": 77312550.0,
|
|
"step": 39525
|
|
},
|
|
{
|
|
"entropy": 5.922851705551148,
|
|
"epoch": 3.951466986554706,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0003518382597637518,
|
|
"loss": 5.3942,
|
|
"mean_token_accuracy": 0.20448674857616425,
|
|
"num_tokens": 77323668.0,
|
|
"step": 39530
|
|
},
|
|
{
|
|
"entropy": 5.867141389846802,
|
|
"epoch": 3.9519668116159345,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0003518047153048868,
|
|
"loss": 5.3734,
|
|
"mean_token_accuracy": 0.2119976133108139,
|
|
"num_tokens": 77334080.0,
|
|
"step": 39535
|
|
},
|
|
{
|
|
"entropy": 5.9711095809936525,
|
|
"epoch": 3.952466636677163,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.000351771168913635,
|
|
"loss": 5.5087,
|
|
"mean_token_accuracy": 0.19533714205026625,
|
|
"num_tokens": 77343849.0,
|
|
"step": 39540
|
|
},
|
|
{
|
|
"entropy": 5.858613014221191,
|
|
"epoch": 3.9529664617383915,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0003517376205908403,
|
|
"loss": 5.3864,
|
|
"mean_token_accuracy": 0.20625365376472474,
|
|
"num_tokens": 77353037.0,
|
|
"step": 39545
|
|
},
|
|
{
|
|
"entropy": 5.843146181106567,
|
|
"epoch": 3.95346628679962,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0003517040703373467,
|
|
"loss": 5.4163,
|
|
"mean_token_accuracy": 0.19557926505804063,
|
|
"num_tokens": 77362758.0,
|
|
"step": 39550
|
|
},
|
|
{
|
|
"entropy": 5.8292809009552,
|
|
"epoch": 3.953966111860849,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0003516705181539986,
|
|
"loss": 5.3721,
|
|
"mean_token_accuracy": 0.21066875457763673,
|
|
"num_tokens": 77372099.0,
|
|
"step": 39555
|
|
},
|
|
{
|
|
"entropy": 5.969992971420288,
|
|
"epoch": 3.954465936922077,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0003516369640416399,
|
|
"loss": 5.492,
|
|
"mean_token_accuracy": 0.19399455338716506,
|
|
"num_tokens": 77382126.0,
|
|
"step": 39560
|
|
},
|
|
{
|
|
"entropy": 5.848130607604981,
|
|
"epoch": 3.954965761983306,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00035160340800111496,
|
|
"loss": 5.2792,
|
|
"mean_token_accuracy": 0.2158572182059288,
|
|
"num_tokens": 77391674.0,
|
|
"step": 39565
|
|
},
|
|
{
|
|
"entropy": 5.947427368164062,
|
|
"epoch": 3.9554655870445345,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.000351569850033268,
|
|
"loss": 5.5239,
|
|
"mean_token_accuracy": 0.19289917796850203,
|
|
"num_tokens": 77401193.0,
|
|
"step": 39570
|
|
},
|
|
{
|
|
"entropy": 5.914840173721314,
|
|
"epoch": 3.955965412105763,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0003515362901389432,
|
|
"loss": 5.4486,
|
|
"mean_token_accuracy": 0.19932233691215515,
|
|
"num_tokens": 77410876.0,
|
|
"step": 39575
|
|
},
|
|
{
|
|
"entropy": 5.872971487045288,
|
|
"epoch": 3.9564652371669915,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0003515027283189851,
|
|
"loss": 5.4038,
|
|
"mean_token_accuracy": 0.21090967059135438,
|
|
"num_tokens": 77420095.0,
|
|
"step": 39580
|
|
},
|
|
{
|
|
"entropy": 5.883964490890503,
|
|
"epoch": 3.95696506222822,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0003514691645742381,
|
|
"loss": 5.4357,
|
|
"mean_token_accuracy": 0.20414653569459915,
|
|
"num_tokens": 77430526.0,
|
|
"step": 39585
|
|
},
|
|
{
|
|
"entropy": 5.89617886543274,
|
|
"epoch": 3.957464887289449,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0003514355989055465,
|
|
"loss": 5.383,
|
|
"mean_token_accuracy": 0.20287369638681413,
|
|
"num_tokens": 77440042.0,
|
|
"step": 39590
|
|
},
|
|
{
|
|
"entropy": 5.907179450988769,
|
|
"epoch": 3.957964712350677,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.000351402031313755,
|
|
"loss": 5.4097,
|
|
"mean_token_accuracy": 0.20734004825353622,
|
|
"num_tokens": 77450237.0,
|
|
"step": 39595
|
|
},
|
|
{
|
|
"entropy": 5.938443374633789,
|
|
"epoch": 3.958464537411906,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00035136846179970797,
|
|
"loss": 5.3425,
|
|
"mean_token_accuracy": 0.20398123264312745,
|
|
"num_tokens": 77459726.0,
|
|
"step": 39600
|
|
},
|
|
{
|
|
"entropy": 5.805893802642823,
|
|
"epoch": 3.9589643624731345,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00035133489036425007,
|
|
"loss": 5.3365,
|
|
"mean_token_accuracy": 0.2054558888077736,
|
|
"num_tokens": 77469477.0,
|
|
"step": 39605
|
|
},
|
|
{
|
|
"entropy": 5.880054616928101,
|
|
"epoch": 3.959464187534363,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00035130131700822603,
|
|
"loss": 5.4749,
|
|
"mean_token_accuracy": 0.19624924063682556,
|
|
"num_tokens": 77479474.0,
|
|
"step": 39610
|
|
},
|
|
{
|
|
"entropy": 5.908041095733642,
|
|
"epoch": 3.9599640125955915,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0003512677417324805,
|
|
"loss": 5.3322,
|
|
"mean_token_accuracy": 0.1999180093407631,
|
|
"num_tokens": 77489149.0,
|
|
"step": 39615
|
|
},
|
|
{
|
|
"entropy": 5.8918692111969,
|
|
"epoch": 3.96046383765682,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0003512341645378582,
|
|
"loss": 5.3634,
|
|
"mean_token_accuracy": 0.20411933809518815,
|
|
"num_tokens": 77499267.0,
|
|
"step": 39620
|
|
},
|
|
{
|
|
"entropy": 5.835613059997558,
|
|
"epoch": 3.960963662718049,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0003512005854252039,
|
|
"loss": 5.2936,
|
|
"mean_token_accuracy": 0.21134842783212662,
|
|
"num_tokens": 77509225.0,
|
|
"step": 39625
|
|
},
|
|
{
|
|
"entropy": 5.8396360874176025,
|
|
"epoch": 3.961463487779277,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00035116700439536254,
|
|
"loss": 5.4412,
|
|
"mean_token_accuracy": 0.1970639333128929,
|
|
"num_tokens": 77518380.0,
|
|
"step": 39630
|
|
},
|
|
{
|
|
"entropy": 5.903079700469971,
|
|
"epoch": 3.961963312840506,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00035113342144917894,
|
|
"loss": 5.4732,
|
|
"mean_token_accuracy": 0.18877975046634674,
|
|
"num_tokens": 77527689.0,
|
|
"step": 39635
|
|
},
|
|
{
|
|
"entropy": 6.007467412948609,
|
|
"epoch": 3.9624631379017345,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00035109983658749796,
|
|
"loss": 5.499,
|
|
"mean_token_accuracy": 0.18911160677671432,
|
|
"num_tokens": 77538265.0,
|
|
"step": 39640
|
|
},
|
|
{
|
|
"entropy": 5.911316967010498,
|
|
"epoch": 3.962962962962963,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0003510662498111648,
|
|
"loss": 5.3678,
|
|
"mean_token_accuracy": 0.20994365364313125,
|
|
"num_tokens": 77548771.0,
|
|
"step": 39645
|
|
},
|
|
{
|
|
"entropy": 5.840372371673584,
|
|
"epoch": 3.9634627880241915,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00035103266112102423,
|
|
"loss": 5.4321,
|
|
"mean_token_accuracy": 0.20309276431798934,
|
|
"num_tokens": 77559224.0,
|
|
"step": 39650
|
|
},
|
|
{
|
|
"entropy": 5.991041946411133,
|
|
"epoch": 3.96396261308542,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00035099907051792153,
|
|
"loss": 5.4752,
|
|
"mean_token_accuracy": 0.19510035514831542,
|
|
"num_tokens": 77568593.0,
|
|
"step": 39655
|
|
},
|
|
{
|
|
"entropy": 5.847603845596313,
|
|
"epoch": 3.964462438146649,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0003509654780027018,
|
|
"loss": 5.3038,
|
|
"mean_token_accuracy": 0.21481499075889587,
|
|
"num_tokens": 77577867.0,
|
|
"step": 39660
|
|
},
|
|
{
|
|
"entropy": 5.871453857421875,
|
|
"epoch": 3.964962263207877,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0003509318835762102,
|
|
"loss": 5.3931,
|
|
"mean_token_accuracy": 0.20464532673358918,
|
|
"num_tokens": 77588207.0,
|
|
"step": 39665
|
|
},
|
|
{
|
|
"entropy": 5.904485130310059,
|
|
"epoch": 3.965462088269106,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0003508982872392919,
|
|
"loss": 5.3314,
|
|
"mean_token_accuracy": 0.2036467358469963,
|
|
"num_tokens": 77597538.0,
|
|
"step": 39670
|
|
},
|
|
{
|
|
"entropy": 5.907218503952026,
|
|
"epoch": 3.9659619133303345,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0003508646889927923,
|
|
"loss": 5.4636,
|
|
"mean_token_accuracy": 0.19507857859134675,
|
|
"num_tokens": 77607538.0,
|
|
"step": 39675
|
|
},
|
|
{
|
|
"entropy": 5.8136763095855715,
|
|
"epoch": 3.966461738391563,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00035083108883755647,
|
|
"loss": 5.3281,
|
|
"mean_token_accuracy": 0.20565124303102494,
|
|
"num_tokens": 77618339.0,
|
|
"step": 39680
|
|
},
|
|
{
|
|
"entropy": 5.8600493431091305,
|
|
"epoch": 3.9669615634527915,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00035079748677443014,
|
|
"loss": 5.3389,
|
|
"mean_token_accuracy": 0.20058367252349854,
|
|
"num_tokens": 77627022.0,
|
|
"step": 39685
|
|
},
|
|
{
|
|
"entropy": 5.934490966796875,
|
|
"epoch": 3.96746138851402,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0003507638828042585,
|
|
"loss": 5.5057,
|
|
"mean_token_accuracy": 0.1915998101234436,
|
|
"num_tokens": 77637129.0,
|
|
"step": 39690
|
|
},
|
|
{
|
|
"entropy": 5.927036380767822,
|
|
"epoch": 3.967961213575249,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0003507302769278871,
|
|
"loss": 5.4459,
|
|
"mean_token_accuracy": 0.1985992580652237,
|
|
"num_tokens": 77647325.0,
|
|
"step": 39695
|
|
},
|
|
{
|
|
"entropy": 5.896065521240234,
|
|
"epoch": 3.968461038636477,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0003506966691461614,
|
|
"loss": 5.3843,
|
|
"mean_token_accuracy": 0.2065093070268631,
|
|
"num_tokens": 77657673.0,
|
|
"step": 39700
|
|
},
|
|
{
|
|
"entropy": 5.853139781951905,
|
|
"epoch": 3.968960863697706,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0003506630594599269,
|
|
"loss": 5.3277,
|
|
"mean_token_accuracy": 0.2157742515206337,
|
|
"num_tokens": 77667168.0,
|
|
"step": 39705
|
|
},
|
|
{
|
|
"entropy": 5.917938756942749,
|
|
"epoch": 3.969460688758934,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0003506294478700293,
|
|
"loss": 5.4043,
|
|
"mean_token_accuracy": 0.2040386512875557,
|
|
"num_tokens": 77675125.0,
|
|
"step": 39710
|
|
},
|
|
{
|
|
"entropy": 5.896115732192993,
|
|
"epoch": 3.969960513820163,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00035059583437731435,
|
|
"loss": 5.4076,
|
|
"mean_token_accuracy": 0.20189566761255265,
|
|
"num_tokens": 77685256.0,
|
|
"step": 39715
|
|
},
|
|
{
|
|
"entropy": 5.9611979007720945,
|
|
"epoch": 3.9704603388813915,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00035056221898262756,
|
|
"loss": 5.46,
|
|
"mean_token_accuracy": 0.19393232315778733,
|
|
"num_tokens": 77696278.0,
|
|
"step": 39720
|
|
},
|
|
{
|
|
"entropy": 5.932159900665283,
|
|
"epoch": 3.97096016394262,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00035052860168681486,
|
|
"loss": 5.3859,
|
|
"mean_token_accuracy": 0.19588393718004227,
|
|
"num_tokens": 77705493.0,
|
|
"step": 39725
|
|
},
|
|
{
|
|
"entropy": 5.916222047805786,
|
|
"epoch": 3.971459989003849,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.000350494982490722,
|
|
"loss": 5.4023,
|
|
"mean_token_accuracy": 0.2081959456205368,
|
|
"num_tokens": 77715429.0,
|
|
"step": 39730
|
|
},
|
|
{
|
|
"entropy": 5.908181953430176,
|
|
"epoch": 3.971959814065077,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00035046136139519474,
|
|
"loss": 5.4271,
|
|
"mean_token_accuracy": 0.2018759310245514,
|
|
"num_tokens": 77725529.0,
|
|
"step": 39735
|
|
},
|
|
{
|
|
"entropy": 5.859587287902832,
|
|
"epoch": 3.972459639126306,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.000350427738401079,
|
|
"loss": 5.2888,
|
|
"mean_token_accuracy": 0.21131231486797333,
|
|
"num_tokens": 77734191.0,
|
|
"step": 39740
|
|
},
|
|
{
|
|
"entropy": 5.818923377990723,
|
|
"epoch": 3.972959464187534,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0003503941135092209,
|
|
"loss": 5.3598,
|
|
"mean_token_accuracy": 0.20638765394687653,
|
|
"num_tokens": 77744145.0,
|
|
"step": 39745
|
|
},
|
|
{
|
|
"entropy": 5.982017898559571,
|
|
"epoch": 3.973459289248763,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0003503604867204662,
|
|
"loss": 5.485,
|
|
"mean_token_accuracy": 0.1936240553855896,
|
|
"num_tokens": 77754027.0,
|
|
"step": 39750
|
|
},
|
|
{
|
|
"entropy": 5.980476903915405,
|
|
"epoch": 3.9739591143099915,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0003503268580356611,
|
|
"loss": 5.4649,
|
|
"mean_token_accuracy": 0.20049377977848054,
|
|
"num_tokens": 77766002.0,
|
|
"step": 39755
|
|
},
|
|
{
|
|
"entropy": 5.932611179351807,
|
|
"epoch": 3.97445893937122,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00035029322745565165,
|
|
"loss": 5.4192,
|
|
"mean_token_accuracy": 0.20238121300935746,
|
|
"num_tokens": 77775995.0,
|
|
"step": 39760
|
|
},
|
|
{
|
|
"entropy": 6.045635557174682,
|
|
"epoch": 3.974958764432449,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0003502595949812839,
|
|
"loss": 5.5938,
|
|
"mean_token_accuracy": 0.19488381445407868,
|
|
"num_tokens": 77786890.0,
|
|
"step": 39765
|
|
},
|
|
{
|
|
"entropy": 5.796756362915039,
|
|
"epoch": 3.975458589493677,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00035022596061340416,
|
|
"loss": 5.2958,
|
|
"mean_token_accuracy": 0.20593849420547486,
|
|
"num_tokens": 77797236.0,
|
|
"step": 39770
|
|
},
|
|
{
|
|
"entropy": 5.848336124420166,
|
|
"epoch": 3.975958414554906,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00035019232435285863,
|
|
"loss": 5.3748,
|
|
"mean_token_accuracy": 0.21065428704023362,
|
|
"num_tokens": 77807564.0,
|
|
"step": 39775
|
|
},
|
|
{
|
|
"entropy": 5.893971014022827,
|
|
"epoch": 3.976458239616134,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0003501586862004935,
|
|
"loss": 5.391,
|
|
"mean_token_accuracy": 0.1971661239862442,
|
|
"num_tokens": 77817297.0,
|
|
"step": 39780
|
|
},
|
|
{
|
|
"entropy": 5.862850618362427,
|
|
"epoch": 3.976958064677363,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0003501250461571552,
|
|
"loss": 5.3557,
|
|
"mean_token_accuracy": 0.20652484148740768,
|
|
"num_tokens": 77826209.0,
|
|
"step": 39785
|
|
},
|
|
{
|
|
"entropy": 5.910838413238525,
|
|
"epoch": 3.9774578897385915,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0003500914042236901,
|
|
"loss": 5.5055,
|
|
"mean_token_accuracy": 0.19866784811019897,
|
|
"num_tokens": 77836076.0,
|
|
"step": 39790
|
|
},
|
|
{
|
|
"entropy": 5.92017011642456,
|
|
"epoch": 3.97795771479982,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0003500577604009445,
|
|
"loss": 5.3932,
|
|
"mean_token_accuracy": 0.1970211759209633,
|
|
"num_tokens": 77845032.0,
|
|
"step": 39795
|
|
},
|
|
{
|
|
"entropy": 5.905075883865356,
|
|
"epoch": 3.978457539861049,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00035002411468976506,
|
|
"loss": 5.408,
|
|
"mean_token_accuracy": 0.20163841396570206,
|
|
"num_tokens": 77856069.0,
|
|
"step": 39800
|
|
},
|
|
{
|
|
"entropy": 5.804954147338867,
|
|
"epoch": 3.978957364922277,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00034999046709099815,
|
|
"loss": 5.3064,
|
|
"mean_token_accuracy": 0.20622747540473937,
|
|
"num_tokens": 77865917.0,
|
|
"step": 39805
|
|
},
|
|
{
|
|
"entropy": 5.8241589069366455,
|
|
"epoch": 3.979457189983506,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0003499568176054904,
|
|
"loss": 5.318,
|
|
"mean_token_accuracy": 0.20862223356962203,
|
|
"num_tokens": 77874597.0,
|
|
"step": 39810
|
|
},
|
|
{
|
|
"entropy": 5.8732294082641605,
|
|
"epoch": 3.979957015044734,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00034992316623408843,
|
|
"loss": 5.4068,
|
|
"mean_token_accuracy": 0.2046348750591278,
|
|
"num_tokens": 77885014.0,
|
|
"step": 39815
|
|
},
|
|
{
|
|
"entropy": 5.945839834213257,
|
|
"epoch": 3.980456840105963,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00034988951297763887,
|
|
"loss": 5.3943,
|
|
"mean_token_accuracy": 0.1995888814330101,
|
|
"num_tokens": 77894901.0,
|
|
"step": 39820
|
|
},
|
|
{
|
|
"entropy": 5.97642068862915,
|
|
"epoch": 3.9809566651671915,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00034985585783698845,
|
|
"loss": 5.4345,
|
|
"mean_token_accuracy": 0.1965652346611023,
|
|
"num_tokens": 77904466.0,
|
|
"step": 39825
|
|
},
|
|
{
|
|
"entropy": 5.904294490814209,
|
|
"epoch": 3.98145649022842,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0003498222008129838,
|
|
"loss": 5.4434,
|
|
"mean_token_accuracy": 0.202816641330719,
|
|
"num_tokens": 77913700.0,
|
|
"step": 39830
|
|
},
|
|
{
|
|
"entropy": 5.912311458587647,
|
|
"epoch": 3.981956315289649,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00034978854190647197,
|
|
"loss": 5.433,
|
|
"mean_token_accuracy": 0.19369412809610367,
|
|
"num_tokens": 77923385.0,
|
|
"step": 39835
|
|
},
|
|
{
|
|
"entropy": 5.899946308135986,
|
|
"epoch": 3.982456140350877,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00034975488111829955,
|
|
"loss": 5.3947,
|
|
"mean_token_accuracy": 0.2016891732811928,
|
|
"num_tokens": 77933193.0,
|
|
"step": 39840
|
|
},
|
|
{
|
|
"entropy": 5.821408128738403,
|
|
"epoch": 3.982955965412106,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00034972121844931365,
|
|
"loss": 5.3769,
|
|
"mean_token_accuracy": 0.20308226346969604,
|
|
"num_tokens": 77942878.0,
|
|
"step": 39845
|
|
},
|
|
{
|
|
"entropy": 5.890228223800659,
|
|
"epoch": 3.983455790473334,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00034968755390036107,
|
|
"loss": 5.4484,
|
|
"mean_token_accuracy": 0.20299578458070755,
|
|
"num_tokens": 77953499.0,
|
|
"step": 39850
|
|
},
|
|
{
|
|
"entropy": 5.907921314239502,
|
|
"epoch": 3.983955615534563,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00034965388747228886,
|
|
"loss": 5.3822,
|
|
"mean_token_accuracy": 0.1970231130719185,
|
|
"num_tokens": 77963716.0,
|
|
"step": 39855
|
|
},
|
|
{
|
|
"entropy": 5.85168194770813,
|
|
"epoch": 3.9844554405957915,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00034962021916594405,
|
|
"loss": 5.4069,
|
|
"mean_token_accuracy": 0.19789472222328186,
|
|
"num_tokens": 77973118.0,
|
|
"step": 39860
|
|
},
|
|
{
|
|
"entropy": 5.883727931976319,
|
|
"epoch": 3.98495526565702,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0003495865489821737,
|
|
"loss": 5.4096,
|
|
"mean_token_accuracy": 0.20086561590433122,
|
|
"num_tokens": 77983658.0,
|
|
"step": 39865
|
|
},
|
|
{
|
|
"entropy": 5.9074060916900635,
|
|
"epoch": 3.985455090718249,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000349552876921825,
|
|
"loss": 5.4126,
|
|
"mean_token_accuracy": 0.2016417622566223,
|
|
"num_tokens": 77993661.0,
|
|
"step": 39870
|
|
},
|
|
{
|
|
"entropy": 5.936170864105224,
|
|
"epoch": 3.985954915779477,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0003495192029857452,
|
|
"loss": 5.4905,
|
|
"mean_token_accuracy": 0.18953229784965514,
|
|
"num_tokens": 78003900.0,
|
|
"step": 39875
|
|
},
|
|
{
|
|
"entropy": 5.891404438018799,
|
|
"epoch": 3.986454740840706,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0003494855271747813,
|
|
"loss": 5.4353,
|
|
"mean_token_accuracy": 0.1943899467587471,
|
|
"num_tokens": 78013936.0,
|
|
"step": 39880
|
|
},
|
|
{
|
|
"entropy": 5.94400315284729,
|
|
"epoch": 3.986954565901934,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00034945184948978074,
|
|
"loss": 5.4258,
|
|
"mean_token_accuracy": 0.20343435406684876,
|
|
"num_tokens": 78025190.0,
|
|
"step": 39885
|
|
},
|
|
{
|
|
"entropy": 5.874195575714111,
|
|
"epoch": 3.987454390963163,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0003494181699315908,
|
|
"loss": 5.4222,
|
|
"mean_token_accuracy": 0.19973687082529068,
|
|
"num_tokens": 78034562.0,
|
|
"step": 39890
|
|
},
|
|
{
|
|
"entropy": 5.952563238143921,
|
|
"epoch": 3.9879542160243915,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0003493844885010589,
|
|
"loss": 5.4979,
|
|
"mean_token_accuracy": 0.19997268319129943,
|
|
"num_tokens": 78044793.0,
|
|
"step": 39895
|
|
},
|
|
{
|
|
"entropy": 5.855329322814941,
|
|
"epoch": 3.98845404108562,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00034935080519903235,
|
|
"loss": 5.4538,
|
|
"mean_token_accuracy": 0.20401146709918977,
|
|
"num_tokens": 78054099.0,
|
|
"step": 39900
|
|
},
|
|
{
|
|
"entropy": 5.933668422698974,
|
|
"epoch": 3.9889538661468484,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0003493171200263586,
|
|
"loss": 5.5431,
|
|
"mean_token_accuracy": 0.2012740209698677,
|
|
"num_tokens": 78064647.0,
|
|
"step": 39905
|
|
},
|
|
{
|
|
"entropy": 5.9464921951293945,
|
|
"epoch": 3.989453691208077,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0003492834329838854,
|
|
"loss": 5.4019,
|
|
"mean_token_accuracy": 0.20579409897327422,
|
|
"num_tokens": 78073787.0,
|
|
"step": 39910
|
|
},
|
|
{
|
|
"entropy": 5.930048036575317,
|
|
"epoch": 3.989953516269306,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00034924974407246005,
|
|
"loss": 5.4454,
|
|
"mean_token_accuracy": 0.20560663789510727,
|
|
"num_tokens": 78082780.0,
|
|
"step": 39915
|
|
},
|
|
{
|
|
"entropy": 5.9034045219421385,
|
|
"epoch": 3.990453341330534,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00034921605329293025,
|
|
"loss": 5.4365,
|
|
"mean_token_accuracy": 0.20064650624990463,
|
|
"num_tokens": 78092379.0,
|
|
"step": 39920
|
|
},
|
|
{
|
|
"entropy": 5.8972334384918215,
|
|
"epoch": 3.990953166391763,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00034918236064614366,
|
|
"loss": 5.455,
|
|
"mean_token_accuracy": 0.20227731615304947,
|
|
"num_tokens": 78101311.0,
|
|
"step": 39925
|
|
},
|
|
{
|
|
"entropy": 5.878802108764648,
|
|
"epoch": 3.9914529914529915,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000349148666132948,
|
|
"loss": 5.3934,
|
|
"mean_token_accuracy": 0.20344831198453903,
|
|
"num_tokens": 78111646.0,
|
|
"step": 39930
|
|
},
|
|
{
|
|
"entropy": 5.9469335079193115,
|
|
"epoch": 3.99195281651422,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0003491149697541909,
|
|
"loss": 5.4452,
|
|
"mean_token_accuracy": 0.1984753578901291,
|
|
"num_tokens": 78122350.0,
|
|
"step": 39935
|
|
},
|
|
{
|
|
"entropy": 5.9327576637268065,
|
|
"epoch": 3.9924526415754484,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00034908127151072027,
|
|
"loss": 5.3743,
|
|
"mean_token_accuracy": 0.2046155422925949,
|
|
"num_tokens": 78133724.0,
|
|
"step": 39940
|
|
},
|
|
{
|
|
"entropy": 5.8265056133270265,
|
|
"epoch": 3.992952466636677,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0003490475714033839,
|
|
"loss": 5.4184,
|
|
"mean_token_accuracy": 0.20750141888856888,
|
|
"num_tokens": 78143001.0,
|
|
"step": 39945
|
|
},
|
|
{
|
|
"entropy": 6.020064496994019,
|
|
"epoch": 3.993452291697906,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00034901386943302976,
|
|
"loss": 5.4196,
|
|
"mean_token_accuracy": 0.20031941682100296,
|
|
"num_tokens": 78152882.0,
|
|
"step": 39950
|
|
},
|
|
{
|
|
"entropy": 5.938579130172729,
|
|
"epoch": 3.993952116759134,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0003489801656005057,
|
|
"loss": 5.3712,
|
|
"mean_token_accuracy": 0.20285177677869798,
|
|
"num_tokens": 78162011.0,
|
|
"step": 39955
|
|
},
|
|
{
|
|
"entropy": 5.826035356521606,
|
|
"epoch": 3.994451941820363,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00034894645990665957,
|
|
"loss": 5.3169,
|
|
"mean_token_accuracy": 0.21178019493818284,
|
|
"num_tokens": 78172142.0,
|
|
"step": 39960
|
|
},
|
|
{
|
|
"entropy": 5.863522005081177,
|
|
"epoch": 3.9949517668815915,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00034891275235233966,
|
|
"loss": 5.3733,
|
|
"mean_token_accuracy": 0.20464538782835007,
|
|
"num_tokens": 78181429.0,
|
|
"step": 39965
|
|
},
|
|
{
|
|
"entropy": 5.830819702148437,
|
|
"epoch": 3.99545159194282,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00034887904293839385,
|
|
"loss": 5.3388,
|
|
"mean_token_accuracy": 0.20468215197324752,
|
|
"num_tokens": 78190314.0,
|
|
"step": 39970
|
|
},
|
|
{
|
|
"entropy": 5.910914039611816,
|
|
"epoch": 3.9959514170040484,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0003488453316656704,
|
|
"loss": 5.3234,
|
|
"mean_token_accuracy": 0.2093757376074791,
|
|
"num_tokens": 78200256.0,
|
|
"step": 39975
|
|
},
|
|
{
|
|
"entropy": 5.922846746444702,
|
|
"epoch": 3.996451242065277,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0003488116185350174,
|
|
"loss": 5.4635,
|
|
"mean_token_accuracy": 0.2048483282327652,
|
|
"num_tokens": 78210596.0,
|
|
"step": 39980
|
|
},
|
|
{
|
|
"entropy": 5.896381282806397,
|
|
"epoch": 3.996951067126506,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00034877790354728304,
|
|
"loss": 5.3508,
|
|
"mean_token_accuracy": 0.20672179013490677,
|
|
"num_tokens": 78220254.0,
|
|
"step": 39985
|
|
},
|
|
{
|
|
"entropy": 5.905796909332276,
|
|
"epoch": 3.997450892187734,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0003487441867033156,
|
|
"loss": 5.4117,
|
|
"mean_token_accuracy": 0.19648048430681228,
|
|
"num_tokens": 78229243.0,
|
|
"step": 39990
|
|
},
|
|
{
|
|
"entropy": 5.855044841766357,
|
|
"epoch": 3.997950717248963,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0003487104680039634,
|
|
"loss": 5.3278,
|
|
"mean_token_accuracy": 0.20561585575342178,
|
|
"num_tokens": 78239312.0,
|
|
"step": 39995
|
|
},
|
|
{
|
|
"entropy": 5.8640382289886475,
|
|
"epoch": 3.9984505423101915,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0003486767474500748,
|
|
"loss": 5.3824,
|
|
"mean_token_accuracy": 0.19915643185377122,
|
|
"num_tokens": 78249306.0,
|
|
"step": 40000
|
|
},
|
|
{
|
|
"entropy": 5.898044538497925,
|
|
"epoch": 3.99895036737142,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00034864302504249823,
|
|
"loss": 5.3968,
|
|
"mean_token_accuracy": 0.2053048700094223,
|
|
"num_tokens": 78258186.0,
|
|
"step": 40005
|
|
},
|
|
{
|
|
"entropy": 5.907183361053467,
|
|
"epoch": 3.9994501924326484,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00034860930078208207,
|
|
"loss": 5.4251,
|
|
"mean_token_accuracy": 0.2051353022456169,
|
|
"num_tokens": 78268051.0,
|
|
"step": 40010
|
|
},
|
|
{
|
|
"entropy": 5.938029336929321,
|
|
"epoch": 3.999950017493877,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00034857557466967486,
|
|
"loss": 5.3656,
|
|
"mean_token_accuracy": 0.2047462061047554,
|
|
"num_tokens": 78277574.0,
|
|
"step": 40015
|
|
},
|
|
{
|
|
"entropy": 5.854080041249593,
|
|
"epoch": 4.000399860048983,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00034854184670612514,
|
|
"loss": 5.3807,
|
|
"mean_token_accuracy": 0.21000194880697462,
|
|
"num_tokens": 78286849.0,
|
|
"step": 40020
|
|
},
|
|
{
|
|
"entropy": 5.874545860290527,
|
|
"epoch": 4.000899685110212,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0003485081168922814,
|
|
"loss": 5.3501,
|
|
"mean_token_accuracy": 0.21127417236566542,
|
|
"num_tokens": 78297180.0,
|
|
"step": 40025
|
|
},
|
|
{
|
|
"entropy": 5.99434723854065,
|
|
"epoch": 4.00139951017144,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00034847438522899246,
|
|
"loss": 5.5167,
|
|
"mean_token_accuracy": 0.19418458491563798,
|
|
"num_tokens": 78307613.0,
|
|
"step": 40030
|
|
},
|
|
{
|
|
"entropy": 5.893305492401123,
|
|
"epoch": 4.001899335232668,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0003484406517171068,
|
|
"loss": 5.2605,
|
|
"mean_token_accuracy": 0.21855278313159943,
|
|
"num_tokens": 78316955.0,
|
|
"step": 40035
|
|
},
|
|
{
|
|
"entropy": 5.914851331710816,
|
|
"epoch": 4.002399160293897,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0003484069163574733,
|
|
"loss": 5.3346,
|
|
"mean_token_accuracy": 0.20931560248136521,
|
|
"num_tokens": 78327458.0,
|
|
"step": 40040
|
|
},
|
|
{
|
|
"entropy": 5.927508974075318,
|
|
"epoch": 4.002898985355126,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00034837317915094063,
|
|
"loss": 5.3495,
|
|
"mean_token_accuracy": 0.21200476139783858,
|
|
"num_tokens": 78337636.0,
|
|
"step": 40045
|
|
},
|
|
{
|
|
"entropy": 5.848135232925415,
|
|
"epoch": 4.003398810416354,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00034833944009835774,
|
|
"loss": 5.2059,
|
|
"mean_token_accuracy": 0.2167441725730896,
|
|
"num_tokens": 78346845.0,
|
|
"step": 40050
|
|
},
|
|
{
|
|
"entropy": 5.89793586730957,
|
|
"epoch": 4.003898635477583,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00034830569920057323,
|
|
"loss": 5.3399,
|
|
"mean_token_accuracy": 0.20001727640628814,
|
|
"num_tokens": 78357797.0,
|
|
"step": 40055
|
|
},
|
|
{
|
|
"entropy": 5.913517856597901,
|
|
"epoch": 4.004398460538812,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00034827195645843636,
|
|
"loss": 5.4064,
|
|
"mean_token_accuracy": 0.20548370927572251,
|
|
"num_tokens": 78368194.0,
|
|
"step": 40060
|
|
},
|
|
{
|
|
"entropy": 5.846703147888183,
|
|
"epoch": 4.00489828560004,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0003482382118727959,
|
|
"loss": 5.2632,
|
|
"mean_token_accuracy": 0.2133168175816536,
|
|
"num_tokens": 78378394.0,
|
|
"step": 40065
|
|
},
|
|
{
|
|
"entropy": 5.852924823760986,
|
|
"epoch": 4.005398110661268,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0003482044654445008,
|
|
"loss": 5.3064,
|
|
"mean_token_accuracy": 0.20997496247291564,
|
|
"num_tokens": 78387549.0,
|
|
"step": 40070
|
|
},
|
|
{
|
|
"entropy": 5.927299308776855,
|
|
"epoch": 4.005897935722497,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00034817071717440024,
|
|
"loss": 5.369,
|
|
"mean_token_accuracy": 0.20127872079610826,
|
|
"num_tokens": 78396896.0,
|
|
"step": 40075
|
|
},
|
|
{
|
|
"entropy": 5.949935865402222,
|
|
"epoch": 4.006397760783726,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0003481369670633433,
|
|
"loss": 5.3171,
|
|
"mean_token_accuracy": 0.21210142821073533,
|
|
"num_tokens": 78404754.0,
|
|
"step": 40080
|
|
},
|
|
{
|
|
"entropy": 5.6907144546508786,
|
|
"epoch": 4.006897585844954,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00034810321511217894,
|
|
"loss": 5.1535,
|
|
"mean_token_accuracy": 0.2265438109636307,
|
|
"num_tokens": 78415645.0,
|
|
"step": 40085
|
|
},
|
|
{
|
|
"entropy": 5.865801191329956,
|
|
"epoch": 4.007397410906183,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0003480694613217567,
|
|
"loss": 5.2668,
|
|
"mean_token_accuracy": 0.2188647523522377,
|
|
"num_tokens": 78425821.0,
|
|
"step": 40090
|
|
},
|
|
{
|
|
"entropy": 5.904714298248291,
|
|
"epoch": 4.007897235967412,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0003480357056929255,
|
|
"loss": 5.2972,
|
|
"mean_token_accuracy": 0.21810372173786163,
|
|
"num_tokens": 78436260.0,
|
|
"step": 40095
|
|
},
|
|
{
|
|
"entropy": 5.930590724945068,
|
|
"epoch": 4.00839706102864,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00034800194822653474,
|
|
"loss": 5.3949,
|
|
"mean_token_accuracy": 0.19818030297756195,
|
|
"num_tokens": 78446042.0,
|
|
"step": 40100
|
|
},
|
|
{
|
|
"entropy": 5.87636284828186,
|
|
"epoch": 4.008896886089868,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00034796818892343374,
|
|
"loss": 5.3792,
|
|
"mean_token_accuracy": 0.20058034509420394,
|
|
"num_tokens": 78455120.0,
|
|
"step": 40105
|
|
},
|
|
{
|
|
"entropy": 5.908489608764649,
|
|
"epoch": 4.009396711151097,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00034793442778447196,
|
|
"loss": 5.3171,
|
|
"mean_token_accuracy": 0.21622552573680878,
|
|
"num_tokens": 78465173.0,
|
|
"step": 40110
|
|
},
|
|
{
|
|
"entropy": 5.868877029418945,
|
|
"epoch": 4.009896536212326,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0003479006648104987,
|
|
"loss": 5.3685,
|
|
"mean_token_accuracy": 0.1979575514793396,
|
|
"num_tokens": 78475154.0,
|
|
"step": 40115
|
|
},
|
|
{
|
|
"entropy": 5.874142217636108,
|
|
"epoch": 4.010396361273554,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0003478669000023634,
|
|
"loss": 5.3714,
|
|
"mean_token_accuracy": 0.20353790670633315,
|
|
"num_tokens": 78485270.0,
|
|
"step": 40120
|
|
},
|
|
{
|
|
"entropy": 5.879984521865845,
|
|
"epoch": 4.010896186334783,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00034783313336091576,
|
|
"loss": 5.3313,
|
|
"mean_token_accuracy": 0.20957515388727188,
|
|
"num_tokens": 78495576.0,
|
|
"step": 40125
|
|
},
|
|
{
|
|
"entropy": 5.9675298690795895,
|
|
"epoch": 4.011396011396012,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00034779936488700514,
|
|
"loss": 5.4535,
|
|
"mean_token_accuracy": 0.2050752818584442,
|
|
"num_tokens": 78505444.0,
|
|
"step": 40130
|
|
},
|
|
{
|
|
"entropy": 5.902853202819824,
|
|
"epoch": 4.01189583645724,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0003477655945814812,
|
|
"loss": 5.4166,
|
|
"mean_token_accuracy": 0.20041916966438295,
|
|
"num_tokens": 78514476.0,
|
|
"step": 40135
|
|
},
|
|
{
|
|
"entropy": 5.819104957580566,
|
|
"epoch": 4.012395661518468,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00034773182244519376,
|
|
"loss": 5.3413,
|
|
"mean_token_accuracy": 0.21036993861198425,
|
|
"num_tokens": 78523864.0,
|
|
"step": 40140
|
|
},
|
|
{
|
|
"entropy": 5.875414085388184,
|
|
"epoch": 4.012895486579697,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0003476980484789923,
|
|
"loss": 5.3387,
|
|
"mean_token_accuracy": 0.20448888838291168,
|
|
"num_tokens": 78533402.0,
|
|
"step": 40145
|
|
},
|
|
{
|
|
"entropy": 5.848667144775391,
|
|
"epoch": 4.0133953116409256,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0003476642726837267,
|
|
"loss": 5.268,
|
|
"mean_token_accuracy": 0.21445134729146959,
|
|
"num_tokens": 78542919.0,
|
|
"step": 40150
|
|
},
|
|
{
|
|
"entropy": 5.87219648361206,
|
|
"epoch": 4.013895136702154,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00034763049506024657,
|
|
"loss": 5.3226,
|
|
"mean_token_accuracy": 0.2060456618666649,
|
|
"num_tokens": 78552360.0,
|
|
"step": 40155
|
|
},
|
|
{
|
|
"entropy": 5.81826958656311,
|
|
"epoch": 4.014394961763383,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.000347596715609402,
|
|
"loss": 5.2764,
|
|
"mean_token_accuracy": 0.21685488224029542,
|
|
"num_tokens": 78561943.0,
|
|
"step": 40160
|
|
},
|
|
{
|
|
"entropy": 5.911429166793823,
|
|
"epoch": 4.014894786824612,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0003475629343320427,
|
|
"loss": 5.2875,
|
|
"mean_token_accuracy": 0.2147127643227577,
|
|
"num_tokens": 78571538.0,
|
|
"step": 40165
|
|
},
|
|
{
|
|
"entropy": 5.947323179244995,
|
|
"epoch": 4.01539461188584,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00034752915122901863,
|
|
"loss": 5.3947,
|
|
"mean_token_accuracy": 0.20034800767898558,
|
|
"num_tokens": 78581369.0,
|
|
"step": 40170
|
|
},
|
|
{
|
|
"entropy": 5.819918870925903,
|
|
"epoch": 4.015894436947068,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00034749536630117984,
|
|
"loss": 5.309,
|
|
"mean_token_accuracy": 0.21252495050430298,
|
|
"num_tokens": 78592412.0,
|
|
"step": 40175
|
|
},
|
|
{
|
|
"entropy": 5.814606380462647,
|
|
"epoch": 4.016394262008297,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0003474615795493763,
|
|
"loss": 5.3355,
|
|
"mean_token_accuracy": 0.20541565120220184,
|
|
"num_tokens": 78601527.0,
|
|
"step": 40180
|
|
},
|
|
{
|
|
"entropy": 5.867548179626465,
|
|
"epoch": 4.0168940870695256,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00034742779097445795,
|
|
"loss": 5.3344,
|
|
"mean_token_accuracy": 0.2024636074900627,
|
|
"num_tokens": 78611906.0,
|
|
"step": 40185
|
|
},
|
|
{
|
|
"entropy": 5.934337520599366,
|
|
"epoch": 4.017393912130754,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0003473940005772751,
|
|
"loss": 5.3316,
|
|
"mean_token_accuracy": 0.2045963704586029,
|
|
"num_tokens": 78621153.0,
|
|
"step": 40190
|
|
},
|
|
{
|
|
"entropy": 5.998322772979736,
|
|
"epoch": 4.017893737191983,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00034736020835867776,
|
|
"loss": 5.4806,
|
|
"mean_token_accuracy": 0.19665276259183884,
|
|
"num_tokens": 78629851.0,
|
|
"step": 40195
|
|
},
|
|
{
|
|
"entropy": 5.96296968460083,
|
|
"epoch": 4.018393562253212,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00034732641431951626,
|
|
"loss": 5.4321,
|
|
"mean_token_accuracy": 0.2007502570748329,
|
|
"num_tokens": 78639837.0,
|
|
"step": 40200
|
|
},
|
|
{
|
|
"entropy": 5.916271066665649,
|
|
"epoch": 4.01889338731444,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0003472926184606408,
|
|
"loss": 5.3469,
|
|
"mean_token_accuracy": 0.20310922116041183,
|
|
"num_tokens": 78649341.0,
|
|
"step": 40205
|
|
},
|
|
{
|
|
"entropy": 5.879378604888916,
|
|
"epoch": 4.019393212375668,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00034725882078290163,
|
|
"loss": 5.2835,
|
|
"mean_token_accuracy": 0.20600902140140534,
|
|
"num_tokens": 78657360.0,
|
|
"step": 40210
|
|
},
|
|
{
|
|
"entropy": 5.8944072246551515,
|
|
"epoch": 4.019893037436897,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0003472250212871491,
|
|
"loss": 5.3474,
|
|
"mean_token_accuracy": 0.2004527971148491,
|
|
"num_tokens": 78667787.0,
|
|
"step": 40215
|
|
},
|
|
{
|
|
"entropy": 5.800003290176392,
|
|
"epoch": 4.0203928624981256,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00034719121997423366,
|
|
"loss": 5.236,
|
|
"mean_token_accuracy": 0.2199109673500061,
|
|
"num_tokens": 78677158.0,
|
|
"step": 40220
|
|
},
|
|
{
|
|
"entropy": 5.774662923812866,
|
|
"epoch": 4.020892687559354,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0003471574168450057,
|
|
"loss": 5.2631,
|
|
"mean_token_accuracy": 0.22209386080503463,
|
|
"num_tokens": 78687805.0,
|
|
"step": 40225
|
|
},
|
|
{
|
|
"entropy": 5.947607898712159,
|
|
"epoch": 4.021392512620583,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00034712361190031564,
|
|
"loss": 5.4219,
|
|
"mean_token_accuracy": 0.19479101598262788,
|
|
"num_tokens": 78697937.0,
|
|
"step": 40230
|
|
},
|
|
{
|
|
"entropy": 5.8470603942871096,
|
|
"epoch": 4.021892337681812,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0003470898051410141,
|
|
"loss": 5.2771,
|
|
"mean_token_accuracy": 0.2182079017162323,
|
|
"num_tokens": 78708591.0,
|
|
"step": 40235
|
|
},
|
|
{
|
|
"entropy": 5.9169999122619625,
|
|
"epoch": 4.02239216274304,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0003470559965679516,
|
|
"loss": 5.3344,
|
|
"mean_token_accuracy": 0.2057160571217537,
|
|
"num_tokens": 78718559.0,
|
|
"step": 40240
|
|
},
|
|
{
|
|
"entropy": 5.79963526725769,
|
|
"epoch": 4.022891987804268,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00034702218618197885,
|
|
"loss": 5.2381,
|
|
"mean_token_accuracy": 0.22023030370473862,
|
|
"num_tokens": 78727412.0,
|
|
"step": 40245
|
|
},
|
|
{
|
|
"entropy": 5.7459746360778805,
|
|
"epoch": 4.023391812865497,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0003469883739839463,
|
|
"loss": 5.1918,
|
|
"mean_token_accuracy": 0.21755573004484177,
|
|
"num_tokens": 78737298.0,
|
|
"step": 40250
|
|
},
|
|
{
|
|
"entropy": 5.850762224197387,
|
|
"epoch": 4.0238916379267256,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00034695455997470486,
|
|
"loss": 5.2966,
|
|
"mean_token_accuracy": 0.2101851850748062,
|
|
"num_tokens": 78747301.0,
|
|
"step": 40255
|
|
},
|
|
{
|
|
"entropy": 5.8714026927948,
|
|
"epoch": 4.024391462987954,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00034692074415510523,
|
|
"loss": 5.3209,
|
|
"mean_token_accuracy": 0.2046821027994156,
|
|
"num_tokens": 78756615.0,
|
|
"step": 40260
|
|
},
|
|
{
|
|
"entropy": 5.935210657119751,
|
|
"epoch": 4.024891288049183,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00034688692652599815,
|
|
"loss": 5.342,
|
|
"mean_token_accuracy": 0.21166651397943498,
|
|
"num_tokens": 78766277.0,
|
|
"step": 40265
|
|
},
|
|
{
|
|
"entropy": 5.886999464035034,
|
|
"epoch": 4.025391113110412,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0003468531070882345,
|
|
"loss": 5.3397,
|
|
"mean_token_accuracy": 0.19784923195838927,
|
|
"num_tokens": 78775899.0,
|
|
"step": 40270
|
|
},
|
|
{
|
|
"entropy": 5.827088975906372,
|
|
"epoch": 4.02589093817164,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00034681928584266513,
|
|
"loss": 5.2433,
|
|
"mean_token_accuracy": 0.21626030951738356,
|
|
"num_tokens": 78785472.0,
|
|
"step": 40275
|
|
},
|
|
{
|
|
"entropy": 5.844315052032471,
|
|
"epoch": 4.026390763232868,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000346785462790141,
|
|
"loss": 5.3087,
|
|
"mean_token_accuracy": 0.2139813557267189,
|
|
"num_tokens": 78795312.0,
|
|
"step": 40280
|
|
},
|
|
{
|
|
"entropy": 5.831213092803955,
|
|
"epoch": 4.026890588294097,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00034675163793151313,
|
|
"loss": 5.2836,
|
|
"mean_token_accuracy": 0.2105007365345955,
|
|
"num_tokens": 78805767.0,
|
|
"step": 40285
|
|
},
|
|
{
|
|
"entropy": 5.853751802444458,
|
|
"epoch": 4.0273904133553255,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00034671781126763263,
|
|
"loss": 5.3475,
|
|
"mean_token_accuracy": 0.21314230859279631,
|
|
"num_tokens": 78815138.0,
|
|
"step": 40290
|
|
},
|
|
{
|
|
"entropy": 5.866969776153565,
|
|
"epoch": 4.027890238416554,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00034668398279935034,
|
|
"loss": 5.342,
|
|
"mean_token_accuracy": 0.20640713423490525,
|
|
"num_tokens": 78823958.0,
|
|
"step": 40295
|
|
},
|
|
{
|
|
"entropy": 5.915859031677246,
|
|
"epoch": 4.028390063477783,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00034665015252751747,
|
|
"loss": 5.3769,
|
|
"mean_token_accuracy": 0.19806821793317794,
|
|
"num_tokens": 78833921.0,
|
|
"step": 40300
|
|
},
|
|
{
|
|
"entropy": 5.9942789554595945,
|
|
"epoch": 4.028889888539012,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0003466163204529852,
|
|
"loss": 5.4027,
|
|
"mean_token_accuracy": 0.2003367841243744,
|
|
"num_tokens": 78843640.0,
|
|
"step": 40305
|
|
},
|
|
{
|
|
"entropy": 5.838567638397217,
|
|
"epoch": 4.02938971360024,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00034658248657660476,
|
|
"loss": 5.2008,
|
|
"mean_token_accuracy": 0.22272054553031922,
|
|
"num_tokens": 78854917.0,
|
|
"step": 40310
|
|
},
|
|
{
|
|
"entropy": 5.895652532577515,
|
|
"epoch": 4.029889538661468,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0003465486508992274,
|
|
"loss": 5.3506,
|
|
"mean_token_accuracy": 0.21144044846296312,
|
|
"num_tokens": 78865487.0,
|
|
"step": 40315
|
|
},
|
|
{
|
|
"entropy": 5.903009366989136,
|
|
"epoch": 4.030389363722697,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0003465148134217043,
|
|
"loss": 5.343,
|
|
"mean_token_accuracy": 0.19990328699350357,
|
|
"num_tokens": 78874759.0,
|
|
"step": 40320
|
|
},
|
|
{
|
|
"entropy": 5.7802502632141115,
|
|
"epoch": 4.0308891887839255,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0003464809741448871,
|
|
"loss": 5.2108,
|
|
"mean_token_accuracy": 0.21791630536317824,
|
|
"num_tokens": 78884132.0,
|
|
"step": 40325
|
|
},
|
|
{
|
|
"entropy": 5.868863439559936,
|
|
"epoch": 4.031389013845154,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0003464471330696268,
|
|
"loss": 5.3703,
|
|
"mean_token_accuracy": 0.19994018375873565,
|
|
"num_tokens": 78893730.0,
|
|
"step": 40330
|
|
},
|
|
{
|
|
"entropy": 5.840091562271118,
|
|
"epoch": 4.031888838906383,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0003464132901967751,
|
|
"loss": 5.3065,
|
|
"mean_token_accuracy": 0.21542450338602065,
|
|
"num_tokens": 78903769.0,
|
|
"step": 40335
|
|
},
|
|
{
|
|
"entropy": 5.818470239639282,
|
|
"epoch": 4.032388663967612,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0003463794455271833,
|
|
"loss": 5.2567,
|
|
"mean_token_accuracy": 0.21700039356946946,
|
|
"num_tokens": 78913442.0,
|
|
"step": 40340
|
|
},
|
|
{
|
|
"entropy": 5.9534399032592775,
|
|
"epoch": 4.03288848902884,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00034634559906170304,
|
|
"loss": 5.3643,
|
|
"mean_token_accuracy": 0.20207031667232514,
|
|
"num_tokens": 78923292.0,
|
|
"step": 40345
|
|
},
|
|
{
|
|
"entropy": 5.947425699234008,
|
|
"epoch": 4.033388314090068,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000346311750801186,
|
|
"loss": 5.3252,
|
|
"mean_token_accuracy": 0.2040533244609833,
|
|
"num_tokens": 78933393.0,
|
|
"step": 40350
|
|
},
|
|
{
|
|
"entropy": 5.929657220840454,
|
|
"epoch": 4.033888139151297,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0003462779007464835,
|
|
"loss": 5.37,
|
|
"mean_token_accuracy": 0.20383382886648177,
|
|
"num_tokens": 78942319.0,
|
|
"step": 40355
|
|
},
|
|
{
|
|
"entropy": 5.836457681655884,
|
|
"epoch": 4.0343879642125255,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0003462440488984475,
|
|
"loss": 5.3055,
|
|
"mean_token_accuracy": 0.205668842792511,
|
|
"num_tokens": 78952666.0,
|
|
"step": 40360
|
|
},
|
|
{
|
|
"entropy": 5.836556148529053,
|
|
"epoch": 4.034887789273754,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00034621019525792946,
|
|
"loss": 5.3281,
|
|
"mean_token_accuracy": 0.2065702423453331,
|
|
"num_tokens": 78962443.0,
|
|
"step": 40365
|
|
},
|
|
{
|
|
"entropy": 5.882770919799805,
|
|
"epoch": 4.035387614334983,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00034617633982578124,
|
|
"loss": 5.3576,
|
|
"mean_token_accuracy": 0.2180725485086441,
|
|
"num_tokens": 78972384.0,
|
|
"step": 40370
|
|
},
|
|
{
|
|
"entropy": 5.890749835968018,
|
|
"epoch": 4.035887439396212,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0003461424826028546,
|
|
"loss": 5.3752,
|
|
"mean_token_accuracy": 0.2086075097322464,
|
|
"num_tokens": 78980799.0,
|
|
"step": 40375
|
|
},
|
|
{
|
|
"entropy": 5.83342866897583,
|
|
"epoch": 4.03638726445744,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00034610862359000144,
|
|
"loss": 5.3087,
|
|
"mean_token_accuracy": 0.20159241706132888,
|
|
"num_tokens": 78990753.0,
|
|
"step": 40380
|
|
},
|
|
{
|
|
"entropy": 5.845309686660767,
|
|
"epoch": 4.036887089518668,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0003460747627880736,
|
|
"loss": 5.2913,
|
|
"mean_token_accuracy": 0.21080712527036666,
|
|
"num_tokens": 79000160.0,
|
|
"step": 40385
|
|
},
|
|
{
|
|
"entropy": 5.836395931243897,
|
|
"epoch": 4.037386914579897,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0003460409001979231,
|
|
"loss": 5.3031,
|
|
"mean_token_accuracy": 0.2075577661395073,
|
|
"num_tokens": 79009602.0,
|
|
"step": 40390
|
|
},
|
|
{
|
|
"entropy": 5.886026287078858,
|
|
"epoch": 4.0378867396411255,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00034600703582040183,
|
|
"loss": 5.3755,
|
|
"mean_token_accuracy": 0.21703993678092956,
|
|
"num_tokens": 79019196.0,
|
|
"step": 40395
|
|
},
|
|
{
|
|
"entropy": 5.826005601882935,
|
|
"epoch": 4.038386564702354,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00034597316965636173,
|
|
"loss": 5.256,
|
|
"mean_token_accuracy": 0.2196658030152321,
|
|
"num_tokens": 79028142.0,
|
|
"step": 40400
|
|
},
|
|
{
|
|
"entropy": 5.947606801986694,
|
|
"epoch": 4.038886389763583,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00034593930170665496,
|
|
"loss": 5.425,
|
|
"mean_token_accuracy": 0.20488528162240982,
|
|
"num_tokens": 79038044.0,
|
|
"step": 40405
|
|
},
|
|
{
|
|
"entropy": 5.928623151779175,
|
|
"epoch": 4.039386214824812,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00034590543197213355,
|
|
"loss": 5.3947,
|
|
"mean_token_accuracy": 0.2004254713654518,
|
|
"num_tokens": 79047462.0,
|
|
"step": 40410
|
|
},
|
|
{
|
|
"entropy": 5.829793548583984,
|
|
"epoch": 4.0398860398860394,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00034587156045364983,
|
|
"loss": 5.2882,
|
|
"mean_token_accuracy": 0.20914130210876464,
|
|
"num_tokens": 79057454.0,
|
|
"step": 40415
|
|
},
|
|
{
|
|
"entropy": 5.924875640869141,
|
|
"epoch": 4.040385864947268,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00034583768715205584,
|
|
"loss": 5.3616,
|
|
"mean_token_accuracy": 0.20409196019172668,
|
|
"num_tokens": 79066665.0,
|
|
"step": 40420
|
|
},
|
|
{
|
|
"entropy": 5.912578392028808,
|
|
"epoch": 4.040885690008497,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0003458038120682038,
|
|
"loss": 5.3411,
|
|
"mean_token_accuracy": 0.2095300540328026,
|
|
"num_tokens": 79076138.0,
|
|
"step": 40425
|
|
},
|
|
{
|
|
"entropy": 5.859139251708984,
|
|
"epoch": 4.0413855150697255,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00034576993520294623,
|
|
"loss": 5.2589,
|
|
"mean_token_accuracy": 0.2102453216910362,
|
|
"num_tokens": 79086378.0,
|
|
"step": 40430
|
|
},
|
|
{
|
|
"entropy": 5.920034456253052,
|
|
"epoch": 4.041885340130954,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00034573605655713514,
|
|
"loss": 5.3794,
|
|
"mean_token_accuracy": 0.20130418688058854,
|
|
"num_tokens": 79096751.0,
|
|
"step": 40435
|
|
},
|
|
{
|
|
"entropy": 5.856688499450684,
|
|
"epoch": 4.042385165192183,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00034570217613162315,
|
|
"loss": 5.2926,
|
|
"mean_token_accuracy": 0.20365709215402603,
|
|
"num_tokens": 79106469.0,
|
|
"step": 40440
|
|
},
|
|
{
|
|
"entropy": 5.813297605514526,
|
|
"epoch": 4.042884990253412,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00034566829392726256,
|
|
"loss": 5.3012,
|
|
"mean_token_accuracy": 0.20656277984380722,
|
|
"num_tokens": 79116411.0,
|
|
"step": 40445
|
|
},
|
|
{
|
|
"entropy": 5.898997020721436,
|
|
"epoch": 4.0433848153146394,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0003456344099449059,
|
|
"loss": 5.3886,
|
|
"mean_token_accuracy": 0.2096347078680992,
|
|
"num_tokens": 79125595.0,
|
|
"step": 40450
|
|
},
|
|
{
|
|
"entropy": 5.853444957733155,
|
|
"epoch": 4.043884640375868,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00034560052418540564,
|
|
"loss": 5.3011,
|
|
"mean_token_accuracy": 0.20893958508968352,
|
|
"num_tokens": 79134250.0,
|
|
"step": 40455
|
|
},
|
|
{
|
|
"entropy": 6.017518138885498,
|
|
"epoch": 4.044384465437097,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0003455666366496145,
|
|
"loss": 5.4764,
|
|
"mean_token_accuracy": 0.18953132927417754,
|
|
"num_tokens": 79146249.0,
|
|
"step": 40460
|
|
},
|
|
{
|
|
"entropy": 5.863305282592774,
|
|
"epoch": 4.0448842904983255,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00034553274733838476,
|
|
"loss": 5.2302,
|
|
"mean_token_accuracy": 0.21590540558099747,
|
|
"num_tokens": 79156128.0,
|
|
"step": 40465
|
|
},
|
|
{
|
|
"entropy": 5.8597653865814205,
|
|
"epoch": 4.045384115559554,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0003454988562525693,
|
|
"loss": 5.3049,
|
|
"mean_token_accuracy": 0.21096935868263245,
|
|
"num_tokens": 79166399.0,
|
|
"step": 40470
|
|
},
|
|
{
|
|
"entropy": 5.865856266021728,
|
|
"epoch": 4.045883940620783,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00034546496339302077,
|
|
"loss": 5.3134,
|
|
"mean_token_accuracy": 0.20883911699056626,
|
|
"num_tokens": 79177084.0,
|
|
"step": 40475
|
|
},
|
|
{
|
|
"entropy": 5.875614261627197,
|
|
"epoch": 4.046383765682012,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0003454310687605919,
|
|
"loss": 5.3865,
|
|
"mean_token_accuracy": 0.20562995076179505,
|
|
"num_tokens": 79185506.0,
|
|
"step": 40480
|
|
},
|
|
{
|
|
"entropy": 5.827583456039429,
|
|
"epoch": 4.0468835907432394,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00034539717235613544,
|
|
"loss": 5.2326,
|
|
"mean_token_accuracy": 0.2186788335442543,
|
|
"num_tokens": 79195175.0,
|
|
"step": 40485
|
|
},
|
|
{
|
|
"entropy": 5.925769567489624,
|
|
"epoch": 4.047383415804468,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0003453632741805042,
|
|
"loss": 5.4517,
|
|
"mean_token_accuracy": 0.200842547416687,
|
|
"num_tokens": 79205022.0,
|
|
"step": 40490
|
|
},
|
|
{
|
|
"entropy": 5.857706546783447,
|
|
"epoch": 4.047883240865697,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0003453293742345512,
|
|
"loss": 5.2281,
|
|
"mean_token_accuracy": 0.2244262292981148,
|
|
"num_tokens": 79214219.0,
|
|
"step": 40495
|
|
},
|
|
{
|
|
"entropy": 5.8431161403656,
|
|
"epoch": 4.0483830659269255,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00034529547251912926,
|
|
"loss": 5.3712,
|
|
"mean_token_accuracy": 0.21093901842832566,
|
|
"num_tokens": 79223538.0,
|
|
"step": 40500
|
|
},
|
|
{
|
|
"entropy": 5.897706985473633,
|
|
"epoch": 4.048882890988154,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00034526156903509116,
|
|
"loss": 5.3469,
|
|
"mean_token_accuracy": 0.20455337762832643,
|
|
"num_tokens": 79233056.0,
|
|
"step": 40505
|
|
},
|
|
{
|
|
"entropy": 5.871204948425293,
|
|
"epoch": 4.049382716049383,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0003452276637832902,
|
|
"loss": 5.3987,
|
|
"mean_token_accuracy": 0.20629215985536575,
|
|
"num_tokens": 79242292.0,
|
|
"step": 40510
|
|
},
|
|
{
|
|
"entropy": 5.796900892257691,
|
|
"epoch": 4.049882541110612,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0003451937567645792,
|
|
"loss": 5.2165,
|
|
"mean_token_accuracy": 0.21735187917947768,
|
|
"num_tokens": 79252273.0,
|
|
"step": 40515
|
|
},
|
|
{
|
|
"entropy": 5.878788328170776,
|
|
"epoch": 4.050382366171839,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00034515984797981136,
|
|
"loss": 5.3568,
|
|
"mean_token_accuracy": 0.21280103772878647,
|
|
"num_tokens": 79261086.0,
|
|
"step": 40520
|
|
},
|
|
{
|
|
"entropy": 5.89950647354126,
|
|
"epoch": 4.050882191233068,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0003451259374298398,
|
|
"loss": 5.367,
|
|
"mean_token_accuracy": 0.20586059391498565,
|
|
"num_tokens": 79270233.0,
|
|
"step": 40525
|
|
},
|
|
{
|
|
"entropy": 5.950909948348999,
|
|
"epoch": 4.051382016294297,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00034509202511551776,
|
|
"loss": 5.3959,
|
|
"mean_token_accuracy": 0.201619516313076,
|
|
"num_tokens": 79279905.0,
|
|
"step": 40530
|
|
},
|
|
{
|
|
"entropy": 5.92984676361084,
|
|
"epoch": 4.0518818413555255,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0003450581110376984,
|
|
"loss": 5.3857,
|
|
"mean_token_accuracy": 0.20259910076856613,
|
|
"num_tokens": 79289744.0,
|
|
"step": 40535
|
|
},
|
|
{
|
|
"entropy": 5.865519285202026,
|
|
"epoch": 4.052381666416754,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0003450241951972349,
|
|
"loss": 5.4322,
|
|
"mean_token_accuracy": 0.204230198264122,
|
|
"num_tokens": 79298190.0,
|
|
"step": 40540
|
|
},
|
|
{
|
|
"entropy": 5.885431957244873,
|
|
"epoch": 4.052881491477983,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0003449902775949807,
|
|
"loss": 5.3482,
|
|
"mean_token_accuracy": 0.20317158550024034,
|
|
"num_tokens": 79307261.0,
|
|
"step": 40545
|
|
},
|
|
{
|
|
"entropy": 5.90433177947998,
|
|
"epoch": 4.053381316539212,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00034495635823178917,
|
|
"loss": 5.3261,
|
|
"mean_token_accuracy": 0.2127659350633621,
|
|
"num_tokens": 79316148.0,
|
|
"step": 40550
|
|
},
|
|
{
|
|
"entropy": 5.938582849502564,
|
|
"epoch": 4.053881141600439,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0003449224371085136,
|
|
"loss": 5.4134,
|
|
"mean_token_accuracy": 0.19744097739458083,
|
|
"num_tokens": 79326218.0,
|
|
"step": 40555
|
|
},
|
|
{
|
|
"entropy": 5.938761949539185,
|
|
"epoch": 4.054380966661668,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0003448885142260076,
|
|
"loss": 5.4615,
|
|
"mean_token_accuracy": 0.19301000237464905,
|
|
"num_tokens": 79336045.0,
|
|
"step": 40560
|
|
},
|
|
{
|
|
"entropy": 5.806593132019043,
|
|
"epoch": 4.054880791722897,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00034485458958512444,
|
|
"loss": 5.1998,
|
|
"mean_token_accuracy": 0.22387578934431077,
|
|
"num_tokens": 79348579.0,
|
|
"step": 40565
|
|
},
|
|
{
|
|
"entropy": 5.856840467453003,
|
|
"epoch": 4.0553806167841255,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0003448206631867179,
|
|
"loss": 5.2846,
|
|
"mean_token_accuracy": 0.20593420714139937,
|
|
"num_tokens": 79359358.0,
|
|
"step": 40570
|
|
},
|
|
{
|
|
"entropy": 5.87780442237854,
|
|
"epoch": 4.055880441845354,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00034478673503164143,
|
|
"loss": 5.3559,
|
|
"mean_token_accuracy": 0.20944310426712037,
|
|
"num_tokens": 79369376.0,
|
|
"step": 40575
|
|
},
|
|
{
|
|
"entropy": 5.871637964248658,
|
|
"epoch": 4.056380266906583,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0003447528051207486,
|
|
"loss": 5.2933,
|
|
"mean_token_accuracy": 0.21456663459539413,
|
|
"num_tokens": 79378260.0,
|
|
"step": 40580
|
|
},
|
|
{
|
|
"entropy": 5.8511350631713865,
|
|
"epoch": 4.056880091967812,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0003447188734548932,
|
|
"loss": 5.3506,
|
|
"mean_token_accuracy": 0.2109883025288582,
|
|
"num_tokens": 79387681.0,
|
|
"step": 40585
|
|
},
|
|
{
|
|
"entropy": 5.9145739555358885,
|
|
"epoch": 4.057379917029039,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0003446849400349289,
|
|
"loss": 5.3617,
|
|
"mean_token_accuracy": 0.20480755120515823,
|
|
"num_tokens": 79396733.0,
|
|
"step": 40590
|
|
},
|
|
{
|
|
"entropy": 5.848046684265137,
|
|
"epoch": 4.057879742090268,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0003446510048617093,
|
|
"loss": 5.2749,
|
|
"mean_token_accuracy": 0.222873517870903,
|
|
"num_tokens": 79405664.0,
|
|
"step": 40595
|
|
},
|
|
{
|
|
"entropy": 5.773663806915283,
|
|
"epoch": 4.058379567151497,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0003446170679360884,
|
|
"loss": 5.1392,
|
|
"mean_token_accuracy": 0.23580290973186493,
|
|
"num_tokens": 79415046.0,
|
|
"step": 40600
|
|
},
|
|
{
|
|
"entropy": 5.908975267410279,
|
|
"epoch": 4.0588793922127255,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0003445831292589201,
|
|
"loss": 5.4349,
|
|
"mean_token_accuracy": 0.19817097932100297,
|
|
"num_tokens": 79425139.0,
|
|
"step": 40605
|
|
},
|
|
{
|
|
"entropy": 5.941745567321777,
|
|
"epoch": 4.059379217273954,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0003445491888310581,
|
|
"loss": 5.366,
|
|
"mean_token_accuracy": 0.20606880336999894,
|
|
"num_tokens": 79434973.0,
|
|
"step": 40610
|
|
},
|
|
{
|
|
"entropy": 5.959715938568115,
|
|
"epoch": 4.059879042335183,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0003445152466533564,
|
|
"loss": 5.429,
|
|
"mean_token_accuracy": 0.197304368019104,
|
|
"num_tokens": 79443880.0,
|
|
"step": 40615
|
|
},
|
|
{
|
|
"entropy": 5.787577676773071,
|
|
"epoch": 4.060378867396412,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000344481302726669,
|
|
"loss": 5.2244,
|
|
"mean_token_accuracy": 0.22202280014753342,
|
|
"num_tokens": 79454300.0,
|
|
"step": 40620
|
|
},
|
|
{
|
|
"entropy": 5.799486255645752,
|
|
"epoch": 4.060878692457639,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00034444735705184984,
|
|
"loss": 5.2938,
|
|
"mean_token_accuracy": 0.2158372461795807,
|
|
"num_tokens": 79463771.0,
|
|
"step": 40625
|
|
},
|
|
{
|
|
"entropy": 5.860074281692505,
|
|
"epoch": 4.061378517518868,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0003444134096297531,
|
|
"loss": 5.3804,
|
|
"mean_token_accuracy": 0.2102698266506195,
|
|
"num_tokens": 79473227.0,
|
|
"step": 40630
|
|
},
|
|
{
|
|
"entropy": 5.8953001499176025,
|
|
"epoch": 4.061878342580097,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0003443794604612328,
|
|
"loss": 5.2912,
|
|
"mean_token_accuracy": 0.20877347886562347,
|
|
"num_tokens": 79483797.0,
|
|
"step": 40635
|
|
},
|
|
{
|
|
"entropy": 5.891064214706421,
|
|
"epoch": 4.0623781676413255,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0003443455095471432,
|
|
"loss": 5.2929,
|
|
"mean_token_accuracy": 0.2125117540359497,
|
|
"num_tokens": 79492773.0,
|
|
"step": 40640
|
|
},
|
|
{
|
|
"entropy": 5.897169399261474,
|
|
"epoch": 4.062877992702554,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00034431155688833837,
|
|
"loss": 5.4003,
|
|
"mean_token_accuracy": 0.19710389226675035,
|
|
"num_tokens": 79502795.0,
|
|
"step": 40645
|
|
},
|
|
{
|
|
"entropy": 5.9105082035064695,
|
|
"epoch": 4.063377817763783,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0003442776024856727,
|
|
"loss": 5.4188,
|
|
"mean_token_accuracy": 0.19538585990667343,
|
|
"num_tokens": 79513374.0,
|
|
"step": 40650
|
|
},
|
|
{
|
|
"entropy": 5.924462604522705,
|
|
"epoch": 4.063877642825012,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00034424364634000023,
|
|
"loss": 5.3824,
|
|
"mean_token_accuracy": 0.21051886081695556,
|
|
"num_tokens": 79523542.0,
|
|
"step": 40655
|
|
},
|
|
{
|
|
"entropy": 5.998580503463745,
|
|
"epoch": 4.064377467886239,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0003442096884521754,
|
|
"loss": 5.3988,
|
|
"mean_token_accuracy": 0.20517695546150208,
|
|
"num_tokens": 79533143.0,
|
|
"step": 40660
|
|
},
|
|
{
|
|
"entropy": 5.857427978515625,
|
|
"epoch": 4.064877292947468,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00034417572882305275,
|
|
"loss": 5.3541,
|
|
"mean_token_accuracy": 0.2059904858469963,
|
|
"num_tokens": 79542683.0,
|
|
"step": 40665
|
|
},
|
|
{
|
|
"entropy": 5.890766143798828,
|
|
"epoch": 4.065377118008697,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0003441417674534865,
|
|
"loss": 5.3547,
|
|
"mean_token_accuracy": 0.21278961449861528,
|
|
"num_tokens": 79552521.0,
|
|
"step": 40670
|
|
},
|
|
{
|
|
"entropy": 5.914562368392945,
|
|
"epoch": 4.0658769430699255,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0003441078043443313,
|
|
"loss": 5.3478,
|
|
"mean_token_accuracy": 0.2026023879647255,
|
|
"num_tokens": 79561843.0,
|
|
"step": 40675
|
|
},
|
|
{
|
|
"entropy": 5.861581897735595,
|
|
"epoch": 4.066376768131154,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00034407383949644146,
|
|
"loss": 5.2311,
|
|
"mean_token_accuracy": 0.21344741880893708,
|
|
"num_tokens": 79571153.0,
|
|
"step": 40680
|
|
},
|
|
{
|
|
"entropy": 5.868919801712036,
|
|
"epoch": 4.066876593192383,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0003440398729106715,
|
|
"loss": 5.3124,
|
|
"mean_token_accuracy": 0.2106739655137062,
|
|
"num_tokens": 79581126.0,
|
|
"step": 40685
|
|
},
|
|
{
|
|
"entropy": 5.930249977111816,
|
|
"epoch": 4.067376418253612,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0003440059045878761,
|
|
"loss": 5.4667,
|
|
"mean_token_accuracy": 0.1921370133757591,
|
|
"num_tokens": 79590647.0,
|
|
"step": 40690
|
|
},
|
|
{
|
|
"entropy": 5.848881721496582,
|
|
"epoch": 4.067876243314839,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00034397193452891003,
|
|
"loss": 5.2395,
|
|
"mean_token_accuracy": 0.22006645649671555,
|
|
"num_tokens": 79599723.0,
|
|
"step": 40695
|
|
},
|
|
{
|
|
"entropy": 5.9258047580719,
|
|
"epoch": 4.068376068376068,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0003439379627346277,
|
|
"loss": 5.386,
|
|
"mean_token_accuracy": 0.20918323695659638,
|
|
"num_tokens": 79609699.0,
|
|
"step": 40700
|
|
},
|
|
{
|
|
"entropy": 5.780306434631347,
|
|
"epoch": 4.068875893437297,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00034390398920588404,
|
|
"loss": 5.1951,
|
|
"mean_token_accuracy": 0.21953801959753036,
|
|
"num_tokens": 79619173.0,
|
|
"step": 40705
|
|
},
|
|
{
|
|
"entropy": 5.817774820327759,
|
|
"epoch": 4.0693757184985255,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0003438700139435338,
|
|
"loss": 5.2256,
|
|
"mean_token_accuracy": 0.2164638951420784,
|
|
"num_tokens": 79628685.0,
|
|
"step": 40710
|
|
},
|
|
{
|
|
"entropy": 5.957954931259155,
|
|
"epoch": 4.069875543559754,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0003438360369484317,
|
|
"loss": 5.3462,
|
|
"mean_token_accuracy": 0.20859258621931076,
|
|
"num_tokens": 79639117.0,
|
|
"step": 40715
|
|
},
|
|
{
|
|
"entropy": 5.924720430374146,
|
|
"epoch": 4.070375368620983,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0003438020582214325,
|
|
"loss": 5.4286,
|
|
"mean_token_accuracy": 0.1962926357984543,
|
|
"num_tokens": 79649502.0,
|
|
"step": 40720
|
|
},
|
|
{
|
|
"entropy": 5.939388370513916,
|
|
"epoch": 4.070875193682212,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0003437680777633913,
|
|
"loss": 5.403,
|
|
"mean_token_accuracy": 0.1975165367126465,
|
|
"num_tokens": 79658787.0,
|
|
"step": 40725
|
|
},
|
|
{
|
|
"entropy": 5.932096004486084,
|
|
"epoch": 4.071375018743439,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.000343734095575163,
|
|
"loss": 5.378,
|
|
"mean_token_accuracy": 0.1995319202542305,
|
|
"num_tokens": 79667979.0,
|
|
"step": 40730
|
|
},
|
|
{
|
|
"entropy": 5.956786203384399,
|
|
"epoch": 4.071874843804668,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0003437001116576025,
|
|
"loss": 5.4447,
|
|
"mean_token_accuracy": 0.20091296285390853,
|
|
"num_tokens": 79677997.0,
|
|
"step": 40735
|
|
},
|
|
{
|
|
"entropy": 5.900134134292602,
|
|
"epoch": 4.072374668865897,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00034366612601156486,
|
|
"loss": 5.3963,
|
|
"mean_token_accuracy": 0.2072787255048752,
|
|
"num_tokens": 79687205.0,
|
|
"step": 40740
|
|
},
|
|
{
|
|
"entropy": 5.893323040008545,
|
|
"epoch": 4.0728744939271255,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00034363213863790527,
|
|
"loss": 5.3323,
|
|
"mean_token_accuracy": 0.203429214656353,
|
|
"num_tokens": 79698425.0,
|
|
"step": 40745
|
|
},
|
|
{
|
|
"entropy": 5.869809484481811,
|
|
"epoch": 4.073374318988354,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00034359814953747856,
|
|
"loss": 5.2808,
|
|
"mean_token_accuracy": 0.2165010467171669,
|
|
"num_tokens": 79707923.0,
|
|
"step": 40750
|
|
},
|
|
{
|
|
"entropy": 5.912756013870239,
|
|
"epoch": 4.073874144049583,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00034356415871114013,
|
|
"loss": 5.3407,
|
|
"mean_token_accuracy": 0.20254804342985153,
|
|
"num_tokens": 79719294.0,
|
|
"step": 40755
|
|
},
|
|
{
|
|
"entropy": 5.956681776046753,
|
|
"epoch": 4.074373969110812,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00034353016615974513,
|
|
"loss": 5.5046,
|
|
"mean_token_accuracy": 0.19454555660486222,
|
|
"num_tokens": 79728400.0,
|
|
"step": 40760
|
|
},
|
|
{
|
|
"entropy": 5.90856785774231,
|
|
"epoch": 4.074873794172039,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0003434961718841488,
|
|
"loss": 5.2777,
|
|
"mean_token_accuracy": 0.2084631711244583,
|
|
"num_tokens": 79737749.0,
|
|
"step": 40765
|
|
},
|
|
{
|
|
"entropy": 5.880066347122193,
|
|
"epoch": 4.075373619233268,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00034346217588520636,
|
|
"loss": 5.3901,
|
|
"mean_token_accuracy": 0.19695814549922944,
|
|
"num_tokens": 79747438.0,
|
|
"step": 40770
|
|
},
|
|
{
|
|
"entropy": 5.8276842594146725,
|
|
"epoch": 4.075873444294497,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0003434281781637732,
|
|
"loss": 5.2936,
|
|
"mean_token_accuracy": 0.21784134954214096,
|
|
"num_tokens": 79757820.0,
|
|
"step": 40775
|
|
},
|
|
{
|
|
"entropy": 5.943890619277954,
|
|
"epoch": 4.0763732693557255,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00034339417872070464,
|
|
"loss": 5.427,
|
|
"mean_token_accuracy": 0.19721820205450058,
|
|
"num_tokens": 79767827.0,
|
|
"step": 40780
|
|
},
|
|
{
|
|
"entropy": 5.9975543975830075,
|
|
"epoch": 4.076873094416954,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00034336017755685623,
|
|
"loss": 5.4205,
|
|
"mean_token_accuracy": 0.20315600782632828,
|
|
"num_tokens": 79777687.0,
|
|
"step": 40785
|
|
},
|
|
{
|
|
"entropy": 5.842853450775147,
|
|
"epoch": 4.077372919478183,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0003433261746730833,
|
|
"loss": 5.3007,
|
|
"mean_token_accuracy": 0.20992844551801682,
|
|
"num_tokens": 79788111.0,
|
|
"step": 40790
|
|
},
|
|
{
|
|
"entropy": 5.810299301147461,
|
|
"epoch": 4.077872744539412,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00034329217007024145,
|
|
"loss": 5.3249,
|
|
"mean_token_accuracy": 0.21161804348230362,
|
|
"num_tokens": 79796897.0,
|
|
"step": 40795
|
|
},
|
|
{
|
|
"entropy": 5.788960027694702,
|
|
"epoch": 4.078372569600639,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0003432581637491862,
|
|
"loss": 5.1916,
|
|
"mean_token_accuracy": 0.22617084085941314,
|
|
"num_tokens": 79806759.0,
|
|
"step": 40800
|
|
},
|
|
{
|
|
"entropy": 5.957154560089111,
|
|
"epoch": 4.078872394661868,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.000343224155710773,
|
|
"loss": 5.3944,
|
|
"mean_token_accuracy": 0.20094456374645234,
|
|
"num_tokens": 79817125.0,
|
|
"step": 40805
|
|
},
|
|
{
|
|
"entropy": 5.9687896251678465,
|
|
"epoch": 4.079372219723097,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00034319014595585764,
|
|
"loss": 5.4443,
|
|
"mean_token_accuracy": 0.194761161506176,
|
|
"num_tokens": 79828114.0,
|
|
"step": 40810
|
|
},
|
|
{
|
|
"entropy": 5.908229970932007,
|
|
"epoch": 4.0798720447843255,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00034315613448529574,
|
|
"loss": 5.3359,
|
|
"mean_token_accuracy": 0.2017219915986061,
|
|
"num_tokens": 79838427.0,
|
|
"step": 40815
|
|
},
|
|
{
|
|
"entropy": 5.884963893890381,
|
|
"epoch": 4.080371869845554,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0003431221212999431,
|
|
"loss": 5.3264,
|
|
"mean_token_accuracy": 0.21094251275062562,
|
|
"num_tokens": 79847620.0,
|
|
"step": 40820
|
|
},
|
|
{
|
|
"entropy": 5.808345460891724,
|
|
"epoch": 4.080871694906783,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00034308810640065534,
|
|
"loss": 5.2389,
|
|
"mean_token_accuracy": 0.22130346894264222,
|
|
"num_tokens": 79858061.0,
|
|
"step": 40825
|
|
},
|
|
{
|
|
"entropy": 5.928107643127442,
|
|
"epoch": 4.081371519968012,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0003430540897882884,
|
|
"loss": 5.4093,
|
|
"mean_token_accuracy": 0.20111141502857208,
|
|
"num_tokens": 79868902.0,
|
|
"step": 40830
|
|
},
|
|
{
|
|
"entropy": 5.952142524719238,
|
|
"epoch": 4.081871345029239,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.000343020071463698,
|
|
"loss": 5.3838,
|
|
"mean_token_accuracy": 0.20828788876533508,
|
|
"num_tokens": 79879763.0,
|
|
"step": 40835
|
|
},
|
|
{
|
|
"entropy": 5.83530478477478,
|
|
"epoch": 4.082371170090468,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00034298605142774014,
|
|
"loss": 5.3123,
|
|
"mean_token_accuracy": 0.2059604123234749,
|
|
"num_tokens": 79890014.0,
|
|
"step": 40840
|
|
},
|
|
{
|
|
"entropy": 5.681638097763061,
|
|
"epoch": 4.082870995151697,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0003429520296812708,
|
|
"loss": 5.1647,
|
|
"mean_token_accuracy": 0.22991160452365875,
|
|
"num_tokens": 79898978.0,
|
|
"step": 40845
|
|
},
|
|
{
|
|
"entropy": 5.8922279357910154,
|
|
"epoch": 4.0833708202129255,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0003429180062251458,
|
|
"loss": 5.4238,
|
|
"mean_token_accuracy": 0.19767896234989166,
|
|
"num_tokens": 79908706.0,
|
|
"step": 40850
|
|
},
|
|
{
|
|
"entropy": 5.895838212966919,
|
|
"epoch": 4.083870645274154,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0003428839810602212,
|
|
"loss": 5.2899,
|
|
"mean_token_accuracy": 0.2147096648812294,
|
|
"num_tokens": 79918916.0,
|
|
"step": 40855
|
|
},
|
|
{
|
|
"entropy": 5.9698668956756595,
|
|
"epoch": 4.084370470335383,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0003428499541873532,
|
|
"loss": 5.411,
|
|
"mean_token_accuracy": 0.2071390703320503,
|
|
"num_tokens": 79927289.0,
|
|
"step": 40860
|
|
},
|
|
{
|
|
"entropy": 5.85516037940979,
|
|
"epoch": 4.084870295396612,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00034281592560739775,
|
|
"loss": 5.2631,
|
|
"mean_token_accuracy": 0.21611225455999375,
|
|
"num_tokens": 79936141.0,
|
|
"step": 40865
|
|
},
|
|
{
|
|
"entropy": 5.870234584808349,
|
|
"epoch": 4.085370120457839,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0003427818953212111,
|
|
"loss": 5.3324,
|
|
"mean_token_accuracy": 0.2127949371933937,
|
|
"num_tokens": 79946136.0,
|
|
"step": 40870
|
|
},
|
|
{
|
|
"entropy": 5.834068536758423,
|
|
"epoch": 4.085869945519068,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00034274786332964943,
|
|
"loss": 5.207,
|
|
"mean_token_accuracy": 0.22059902250766755,
|
|
"num_tokens": 79956747.0,
|
|
"step": 40875
|
|
},
|
|
{
|
|
"entropy": 5.732472276687622,
|
|
"epoch": 4.086369770580297,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0003427138296335688,
|
|
"loss": 5.2627,
|
|
"mean_token_accuracy": 0.2119881108403206,
|
|
"num_tokens": 79966694.0,
|
|
"step": 40880
|
|
},
|
|
{
|
|
"entropy": 5.866554832458496,
|
|
"epoch": 4.0868695956415255,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0003426797942338258,
|
|
"loss": 5.3552,
|
|
"mean_token_accuracy": 0.201319120824337,
|
|
"num_tokens": 79976334.0,
|
|
"step": 40885
|
|
},
|
|
{
|
|
"entropy": 5.867662620544434,
|
|
"epoch": 4.087369420702754,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0003426457571312766,
|
|
"loss": 5.323,
|
|
"mean_token_accuracy": 0.21480027735233306,
|
|
"num_tokens": 79985520.0,
|
|
"step": 40890
|
|
},
|
|
{
|
|
"entropy": 5.81685733795166,
|
|
"epoch": 4.087869245763983,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00034261171832677744,
|
|
"loss": 5.2673,
|
|
"mean_token_accuracy": 0.2122579738497734,
|
|
"num_tokens": 79995023.0,
|
|
"step": 40895
|
|
},
|
|
{
|
|
"entropy": 5.87034239768982,
|
|
"epoch": 4.088369070825211,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0003425776778211849,
|
|
"loss": 5.4122,
|
|
"mean_token_accuracy": 0.19632455557584763,
|
|
"num_tokens": 80005298.0,
|
|
"step": 40900
|
|
},
|
|
{
|
|
"entropy": 5.925408363342285,
|
|
"epoch": 4.088868895886439,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0003425436356153554,
|
|
"loss": 5.3777,
|
|
"mean_token_accuracy": 0.2056168481707573,
|
|
"num_tokens": 80015057.0,
|
|
"step": 40905
|
|
},
|
|
{
|
|
"entropy": 5.936406755447388,
|
|
"epoch": 4.089368720947668,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00034250959171014536,
|
|
"loss": 5.3364,
|
|
"mean_token_accuracy": 0.20723443031311034,
|
|
"num_tokens": 80024419.0,
|
|
"step": 40910
|
|
},
|
|
{
|
|
"entropy": 5.902056741714477,
|
|
"epoch": 4.089868546008897,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0003424755461064114,
|
|
"loss": 5.3749,
|
|
"mean_token_accuracy": 0.207858082652092,
|
|
"num_tokens": 80034845.0,
|
|
"step": 40915
|
|
},
|
|
{
|
|
"entropy": 5.940364789962769,
|
|
"epoch": 4.0903683710701255,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00034244149880501007,
|
|
"loss": 5.3696,
|
|
"mean_token_accuracy": 0.2051284819841385,
|
|
"num_tokens": 80044373.0,
|
|
"step": 40920
|
|
},
|
|
{
|
|
"entropy": 5.955650568008423,
|
|
"epoch": 4.090868196131354,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.000342407449806798,
|
|
"loss": 5.4208,
|
|
"mean_token_accuracy": 0.20119163990020753,
|
|
"num_tokens": 80055454.0,
|
|
"step": 40925
|
|
},
|
|
{
|
|
"entropy": 5.807128429412842,
|
|
"epoch": 4.091368021192583,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00034237339911263176,
|
|
"loss": 5.246,
|
|
"mean_token_accuracy": 0.22029076218605043,
|
|
"num_tokens": 80065554.0,
|
|
"step": 40930
|
|
},
|
|
{
|
|
"entropy": 5.911515903472901,
|
|
"epoch": 4.091867846253811,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00034233934672336827,
|
|
"loss": 5.432,
|
|
"mean_token_accuracy": 0.20132312774658204,
|
|
"num_tokens": 80074962.0,
|
|
"step": 40935
|
|
},
|
|
{
|
|
"entropy": 6.036282396316528,
|
|
"epoch": 4.092367671315039,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000342305292639864,
|
|
"loss": 5.417,
|
|
"mean_token_accuracy": 0.19422968327999116,
|
|
"num_tokens": 80084105.0,
|
|
"step": 40940
|
|
},
|
|
{
|
|
"entropy": 5.8974799633026125,
|
|
"epoch": 4.092867496376268,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0003422712368629759,
|
|
"loss": 5.4309,
|
|
"mean_token_accuracy": 0.20203859508037567,
|
|
"num_tokens": 80095032.0,
|
|
"step": 40945
|
|
},
|
|
{
|
|
"entropy": 5.855019426345825,
|
|
"epoch": 4.093367321437497,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00034223717939356083,
|
|
"loss": 5.3716,
|
|
"mean_token_accuracy": 0.20934683978557586,
|
|
"num_tokens": 80104667.0,
|
|
"step": 40950
|
|
},
|
|
{
|
|
"entropy": 5.8476582050323485,
|
|
"epoch": 4.0938671464987255,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0003422031202324757,
|
|
"loss": 5.3039,
|
|
"mean_token_accuracy": 0.21131452918052673,
|
|
"num_tokens": 80114566.0,
|
|
"step": 40955
|
|
},
|
|
{
|
|
"entropy": 5.9218496799469,
|
|
"epoch": 4.094366971559954,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0003421690593805773,
|
|
"loss": 5.3538,
|
|
"mean_token_accuracy": 0.20173035115003585,
|
|
"num_tokens": 80126228.0,
|
|
"step": 40960
|
|
},
|
|
{
|
|
"entropy": 5.939748334884643,
|
|
"epoch": 4.094866796621183,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00034213499683872264,
|
|
"loss": 5.4089,
|
|
"mean_token_accuracy": 0.19714315831661225,
|
|
"num_tokens": 80136034.0,
|
|
"step": 40965
|
|
},
|
|
{
|
|
"entropy": 5.923983192443847,
|
|
"epoch": 4.095366621682411,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00034210093260776865,
|
|
"loss": 5.3518,
|
|
"mean_token_accuracy": 0.20705893635749817,
|
|
"num_tokens": 80146784.0,
|
|
"step": 40970
|
|
},
|
|
{
|
|
"entropy": 5.811035633087158,
|
|
"epoch": 4.095866446743639,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00034206686668857255,
|
|
"loss": 5.1781,
|
|
"mean_token_accuracy": 0.22413581758737564,
|
|
"num_tokens": 80156777.0,
|
|
"step": 40975
|
|
},
|
|
{
|
|
"entropy": 5.703139972686768,
|
|
"epoch": 4.096366271804868,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00034203279908199137,
|
|
"loss": 5.1592,
|
|
"mean_token_accuracy": 0.22367251366376878,
|
|
"num_tokens": 80167486.0,
|
|
"step": 40980
|
|
},
|
|
{
|
|
"entropy": 5.877409744262695,
|
|
"epoch": 4.096866096866097,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0003419987297888822,
|
|
"loss": 5.3426,
|
|
"mean_token_accuracy": 0.21279132217168809,
|
|
"num_tokens": 80176618.0,
|
|
"step": 40985
|
|
},
|
|
{
|
|
"entropy": 5.8698865413665775,
|
|
"epoch": 4.0973659219273255,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0003419646588101022,
|
|
"loss": 5.281,
|
|
"mean_token_accuracy": 0.21706329584121703,
|
|
"num_tokens": 80186334.0,
|
|
"step": 40990
|
|
},
|
|
{
|
|
"entropy": 5.825859451293946,
|
|
"epoch": 4.097865746988554,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00034193058614650866,
|
|
"loss": 5.2514,
|
|
"mean_token_accuracy": 0.21502114981412887,
|
|
"num_tokens": 80195871.0,
|
|
"step": 40995
|
|
},
|
|
{
|
|
"entropy": 5.892081594467163,
|
|
"epoch": 4.098365572049783,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0003418965117989587,
|
|
"loss": 5.294,
|
|
"mean_token_accuracy": 0.21534076780080796,
|
|
"num_tokens": 80205855.0,
|
|
"step": 41000
|
|
},
|
|
{
|
|
"entropy": 5.841750288009644,
|
|
"epoch": 4.098865397111011,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00034186243576830985,
|
|
"loss": 5.2565,
|
|
"mean_token_accuracy": 0.21692740321159362,
|
|
"num_tokens": 80215010.0,
|
|
"step": 41005
|
|
},
|
|
{
|
|
"entropy": 5.761357259750366,
|
|
"epoch": 4.099365222172239,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00034182835805541916,
|
|
"loss": 5.1128,
|
|
"mean_token_accuracy": 0.23309172242879866,
|
|
"num_tokens": 80223710.0,
|
|
"step": 41010
|
|
},
|
|
{
|
|
"entropy": 5.864399480819702,
|
|
"epoch": 4.099865047233468,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0003417942786611443,
|
|
"loss": 5.3528,
|
|
"mean_token_accuracy": 0.20663107186555862,
|
|
"num_tokens": 80232821.0,
|
|
"step": 41015
|
|
},
|
|
{
|
|
"entropy": 5.873990058898926,
|
|
"epoch": 4.100364872294697,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0003417601975863425,
|
|
"loss": 5.3596,
|
|
"mean_token_accuracy": 0.20784523487091064,
|
|
"num_tokens": 80242339.0,
|
|
"step": 41020
|
|
},
|
|
{
|
|
"entropy": 5.945441484451294,
|
|
"epoch": 4.1008646973559255,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00034172611483187143,
|
|
"loss": 5.4115,
|
|
"mean_token_accuracy": 0.20508401989936828,
|
|
"num_tokens": 80251965.0,
|
|
"step": 41025
|
|
},
|
|
{
|
|
"entropy": 5.859619379043579,
|
|
"epoch": 4.101364522417154,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0003416920303985884,
|
|
"loss": 5.3346,
|
|
"mean_token_accuracy": 0.2123958095908165,
|
|
"num_tokens": 80260859.0,
|
|
"step": 41030
|
|
},
|
|
{
|
|
"entropy": 5.797124910354614,
|
|
"epoch": 4.101864347478383,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00034165794428735104,
|
|
"loss": 5.2936,
|
|
"mean_token_accuracy": 0.21768329590559005,
|
|
"num_tokens": 80270056.0,
|
|
"step": 41035
|
|
},
|
|
{
|
|
"entropy": 5.892802619934082,
|
|
"epoch": 4.102364172539611,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00034162385649901694,
|
|
"loss": 5.4575,
|
|
"mean_token_accuracy": 0.19706150889396667,
|
|
"num_tokens": 80279574.0,
|
|
"step": 41040
|
|
},
|
|
{
|
|
"entropy": 5.956516170501709,
|
|
"epoch": 4.102863997600839,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00034158976703444377,
|
|
"loss": 5.4316,
|
|
"mean_token_accuracy": 0.19875307530164718,
|
|
"num_tokens": 80288510.0,
|
|
"step": 41045
|
|
},
|
|
{
|
|
"entropy": 5.903237199783325,
|
|
"epoch": 4.103363822662068,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00034155567589448925,
|
|
"loss": 5.263,
|
|
"mean_token_accuracy": 0.21005670130252838,
|
|
"num_tokens": 80298292.0,
|
|
"step": 41050
|
|
},
|
|
{
|
|
"entropy": 5.938534593582153,
|
|
"epoch": 4.103863647723297,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000341521583080011,
|
|
"loss": 5.5071,
|
|
"mean_token_accuracy": 0.19050415158271788,
|
|
"num_tokens": 80308756.0,
|
|
"step": 41055
|
|
},
|
|
{
|
|
"entropy": 5.854353332519532,
|
|
"epoch": 4.1043634727845255,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0003414874885918669,
|
|
"loss": 5.338,
|
|
"mean_token_accuracy": 0.20678829699754714,
|
|
"num_tokens": 80318553.0,
|
|
"step": 41060
|
|
},
|
|
{
|
|
"entropy": 5.876233625411987,
|
|
"epoch": 4.104863297845754,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00034145339243091456,
|
|
"loss": 5.2698,
|
|
"mean_token_accuracy": 0.21377581506967544,
|
|
"num_tokens": 80327952.0,
|
|
"step": 41065
|
|
},
|
|
{
|
|
"entropy": 5.871127939224243,
|
|
"epoch": 4.105363122906983,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0003414192945980121,
|
|
"loss": 5.3646,
|
|
"mean_token_accuracy": 0.19944396764039993,
|
|
"num_tokens": 80338712.0,
|
|
"step": 41070
|
|
},
|
|
{
|
|
"entropy": 5.91192946434021,
|
|
"epoch": 4.105862947968211,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0003413851950940172,
|
|
"loss": 5.3751,
|
|
"mean_token_accuracy": 0.19986508637666703,
|
|
"num_tokens": 80349300.0,
|
|
"step": 41075
|
|
},
|
|
{
|
|
"entropy": 5.9107279777526855,
|
|
"epoch": 4.106362773029439,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00034135109391978785,
|
|
"loss": 5.3485,
|
|
"mean_token_accuracy": 0.21217606514692305,
|
|
"num_tokens": 80358746.0,
|
|
"step": 41080
|
|
},
|
|
{
|
|
"entropy": 5.874108076095581,
|
|
"epoch": 4.106862598090668,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00034131699107618215,
|
|
"loss": 5.3047,
|
|
"mean_token_accuracy": 0.21302927136421204,
|
|
"num_tokens": 80367505.0,
|
|
"step": 41085
|
|
},
|
|
{
|
|
"entropy": 5.905963659286499,
|
|
"epoch": 4.107362423151897,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00034128288656405794,
|
|
"loss": 5.4518,
|
|
"mean_token_accuracy": 0.19598018527030944,
|
|
"num_tokens": 80377875.0,
|
|
"step": 41090
|
|
},
|
|
{
|
|
"entropy": 6.0506397724151615,
|
|
"epoch": 4.1078622482131255,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00034124878038427337,
|
|
"loss": 5.4906,
|
|
"mean_token_accuracy": 0.1992749273777008,
|
|
"num_tokens": 80386143.0,
|
|
"step": 41095
|
|
},
|
|
{
|
|
"entropy": 5.955010938644409,
|
|
"epoch": 4.108362073274354,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00034121467253768657,
|
|
"loss": 5.4019,
|
|
"mean_token_accuracy": 0.20280323773622513,
|
|
"num_tokens": 80396658.0,
|
|
"step": 41100
|
|
},
|
|
{
|
|
"entropy": 5.905811405181884,
|
|
"epoch": 4.108861898335583,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0003411805630251556,
|
|
"loss": 5.3219,
|
|
"mean_token_accuracy": 0.21317333430051805,
|
|
"num_tokens": 80406063.0,
|
|
"step": 41105
|
|
},
|
|
{
|
|
"entropy": 5.979547023773193,
|
|
"epoch": 4.109361723396811,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00034114645184753873,
|
|
"loss": 5.4696,
|
|
"mean_token_accuracy": 0.20568116009235382,
|
|
"num_tokens": 80415298.0,
|
|
"step": 41110
|
|
},
|
|
{
|
|
"entropy": 5.893607330322266,
|
|
"epoch": 4.109861548458039,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00034111233900569415,
|
|
"loss": 5.349,
|
|
"mean_token_accuracy": 0.19556809961795807,
|
|
"num_tokens": 80425689.0,
|
|
"step": 41115
|
|
},
|
|
{
|
|
"entropy": 5.930994272232056,
|
|
"epoch": 4.110361373519268,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00034107822450048014,
|
|
"loss": 5.3627,
|
|
"mean_token_accuracy": 0.2030873790383339,
|
|
"num_tokens": 80435999.0,
|
|
"step": 41120
|
|
},
|
|
{
|
|
"entropy": 5.866029119491577,
|
|
"epoch": 4.110861198580497,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000341044108332755,
|
|
"loss": 5.2531,
|
|
"mean_token_accuracy": 0.209970360994339,
|
|
"num_tokens": 80445025.0,
|
|
"step": 41125
|
|
},
|
|
{
|
|
"entropy": 5.885035562515259,
|
|
"epoch": 4.1113610236417255,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00034100999050337705,
|
|
"loss": 5.4057,
|
|
"mean_token_accuracy": 0.19918311685323714,
|
|
"num_tokens": 80455375.0,
|
|
"step": 41130
|
|
},
|
|
{
|
|
"entropy": 5.806454658508301,
|
|
"epoch": 4.111860848702954,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00034097587101320474,
|
|
"loss": 5.2639,
|
|
"mean_token_accuracy": 0.2068606808781624,
|
|
"num_tokens": 80464202.0,
|
|
"step": 41135
|
|
},
|
|
{
|
|
"entropy": 5.872619247436523,
|
|
"epoch": 4.112360673764183,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00034094174986309657,
|
|
"loss": 5.3455,
|
|
"mean_token_accuracy": 0.2049868404865265,
|
|
"num_tokens": 80473216.0,
|
|
"step": 41140
|
|
},
|
|
{
|
|
"entropy": 5.9601438522338865,
|
|
"epoch": 4.112860498825411,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0003409076270539108,
|
|
"loss": 5.4124,
|
|
"mean_token_accuracy": 0.20483038574457169,
|
|
"num_tokens": 80482455.0,
|
|
"step": 41145
|
|
},
|
|
{
|
|
"entropy": 5.862099695205688,
|
|
"epoch": 4.113360323886639,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0003408735025865062,
|
|
"loss": 5.3353,
|
|
"mean_token_accuracy": 0.2079566314816475,
|
|
"num_tokens": 80492319.0,
|
|
"step": 41150
|
|
},
|
|
{
|
|
"entropy": 5.903080892562866,
|
|
"epoch": 4.113860148947868,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0003408393764617412,
|
|
"loss": 5.4215,
|
|
"mean_token_accuracy": 0.1924478977918625,
|
|
"num_tokens": 80502798.0,
|
|
"step": 41155
|
|
},
|
|
{
|
|
"entropy": 5.868599796295166,
|
|
"epoch": 4.114359974009097,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00034080524868047445,
|
|
"loss": 5.3447,
|
|
"mean_token_accuracy": 0.20703958719968796,
|
|
"num_tokens": 80511766.0,
|
|
"step": 41160
|
|
},
|
|
{
|
|
"entropy": 5.870865726470948,
|
|
"epoch": 4.1148597990703255,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0003407711192435646,
|
|
"loss": 5.2699,
|
|
"mean_token_accuracy": 0.21782246232032776,
|
|
"num_tokens": 80521728.0,
|
|
"step": 41165
|
|
},
|
|
{
|
|
"entropy": 5.879757499694824,
|
|
"epoch": 4.115359624131554,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0003407369881518702,
|
|
"loss": 5.2989,
|
|
"mean_token_accuracy": 0.2118883490562439,
|
|
"num_tokens": 80530543.0,
|
|
"step": 41170
|
|
},
|
|
{
|
|
"entropy": 5.804811286926269,
|
|
"epoch": 4.115859449192783,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0003407028554062502,
|
|
"loss": 5.2915,
|
|
"mean_token_accuracy": 0.20583482682704926,
|
|
"num_tokens": 80540402.0,
|
|
"step": 41175
|
|
},
|
|
{
|
|
"entropy": 5.8298468589782715,
|
|
"epoch": 4.116359274254011,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0003406687210075632,
|
|
"loss": 5.2982,
|
|
"mean_token_accuracy": 0.21121144890785218,
|
|
"num_tokens": 80550777.0,
|
|
"step": 41180
|
|
},
|
|
{
|
|
"entropy": 5.924352979660034,
|
|
"epoch": 4.116859099315239,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0003406345849566681,
|
|
"loss": 5.3798,
|
|
"mean_token_accuracy": 0.20842893719673156,
|
|
"num_tokens": 80560236.0,
|
|
"step": 41185
|
|
},
|
|
{
|
|
"entropy": 5.875800561904907,
|
|
"epoch": 4.117358924376468,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0003406004472544237,
|
|
"loss": 5.319,
|
|
"mean_token_accuracy": 0.20390630513429642,
|
|
"num_tokens": 80569537.0,
|
|
"step": 41190
|
|
},
|
|
{
|
|
"entropy": 5.9727057933807375,
|
|
"epoch": 4.117858749437697,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0003405663079016889,
|
|
"loss": 5.4043,
|
|
"mean_token_accuracy": 0.2008717194199562,
|
|
"num_tokens": 80578825.0,
|
|
"step": 41195
|
|
},
|
|
{
|
|
"entropy": 5.846225881576538,
|
|
"epoch": 4.1183585744989255,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0003405321668993228,
|
|
"loss": 5.3654,
|
|
"mean_token_accuracy": 0.21454232335090637,
|
|
"num_tokens": 80589620.0,
|
|
"step": 41200
|
|
},
|
|
{
|
|
"entropy": 5.830656957626343,
|
|
"epoch": 4.118858399560154,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0003404980242481842,
|
|
"loss": 5.1974,
|
|
"mean_token_accuracy": 0.22633785158395767,
|
|
"num_tokens": 80599489.0,
|
|
"step": 41205
|
|
},
|
|
{
|
|
"entropy": 5.862797355651855,
|
|
"epoch": 4.119358224621383,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00034046387994913216,
|
|
"loss": 5.3573,
|
|
"mean_token_accuracy": 0.20231668949127196,
|
|
"num_tokens": 80610100.0,
|
|
"step": 41210
|
|
},
|
|
{
|
|
"entropy": 5.9528320789337155,
|
|
"epoch": 4.119858049682611,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0003404297340030257,
|
|
"loss": 5.3607,
|
|
"mean_token_accuracy": 0.20128368139266967,
|
|
"num_tokens": 80619949.0,
|
|
"step": 41215
|
|
},
|
|
{
|
|
"entropy": 5.951389408111572,
|
|
"epoch": 4.120357874743839,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00034039558641072397,
|
|
"loss": 5.4082,
|
|
"mean_token_accuracy": 0.20013125091791154,
|
|
"num_tokens": 80630194.0,
|
|
"step": 41220
|
|
},
|
|
{
|
|
"entropy": 5.931763553619385,
|
|
"epoch": 4.120857699805068,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0003403614371730861,
|
|
"loss": 5.3838,
|
|
"mean_token_accuracy": 0.19926987141370772,
|
|
"num_tokens": 80640394.0,
|
|
"step": 41225
|
|
},
|
|
{
|
|
"entropy": 5.899427223205566,
|
|
"epoch": 4.121357524866297,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00034032728629097137,
|
|
"loss": 5.3211,
|
|
"mean_token_accuracy": 0.20851425230503082,
|
|
"num_tokens": 80651056.0,
|
|
"step": 41230
|
|
},
|
|
{
|
|
"entropy": 5.906445789337158,
|
|
"epoch": 4.1218573499275255,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0003402931337652389,
|
|
"loss": 5.3959,
|
|
"mean_token_accuracy": 0.20349971055984498,
|
|
"num_tokens": 80661370.0,
|
|
"step": 41235
|
|
},
|
|
{
|
|
"entropy": 5.873290967941284,
|
|
"epoch": 4.122357174988754,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.000340258979596748,
|
|
"loss": 5.385,
|
|
"mean_token_accuracy": 0.2065315678715706,
|
|
"num_tokens": 80670627.0,
|
|
"step": 41240
|
|
},
|
|
{
|
|
"entropy": 5.882259035110474,
|
|
"epoch": 4.122857000049983,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0003402248237863579,
|
|
"loss": 5.3227,
|
|
"mean_token_accuracy": 0.2113737404346466,
|
|
"num_tokens": 80680535.0,
|
|
"step": 41245
|
|
},
|
|
{
|
|
"entropy": 5.828943872451783,
|
|
"epoch": 4.123356825111211,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0003401906663349281,
|
|
"loss": 5.236,
|
|
"mean_token_accuracy": 0.21779255270957948,
|
|
"num_tokens": 80689808.0,
|
|
"step": 41250
|
|
},
|
|
{
|
|
"entropy": 5.858275127410889,
|
|
"epoch": 4.123856650172439,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00034015650724331776,
|
|
"loss": 5.3288,
|
|
"mean_token_accuracy": 0.21859159916639329,
|
|
"num_tokens": 80698537.0,
|
|
"step": 41255
|
|
},
|
|
{
|
|
"entropy": 5.8926163673400875,
|
|
"epoch": 4.124356475233668,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00034012234651238654,
|
|
"loss": 5.4058,
|
|
"mean_token_accuracy": 0.20951407700777053,
|
|
"num_tokens": 80709044.0,
|
|
"step": 41260
|
|
},
|
|
{
|
|
"entropy": 5.881525373458862,
|
|
"epoch": 4.124856300294897,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0003400881841429939,
|
|
"loss": 5.2631,
|
|
"mean_token_accuracy": 0.22191748768091202,
|
|
"num_tokens": 80718644.0,
|
|
"step": 41265
|
|
},
|
|
{
|
|
"entropy": 5.84345121383667,
|
|
"epoch": 4.1253561253561255,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0003400540201359992,
|
|
"loss": 5.2645,
|
|
"mean_token_accuracy": 0.21596986055374146,
|
|
"num_tokens": 80728410.0,
|
|
"step": 41270
|
|
},
|
|
{
|
|
"entropy": 5.877434349060058,
|
|
"epoch": 4.125855950417354,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0003400198544922622,
|
|
"loss": 5.4093,
|
|
"mean_token_accuracy": 0.19889434576034545,
|
|
"num_tokens": 80739075.0,
|
|
"step": 41275
|
|
},
|
|
{
|
|
"entropy": 5.899873685836792,
|
|
"epoch": 4.126355775478583,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0003399856872126424,
|
|
"loss": 5.2741,
|
|
"mean_token_accuracy": 0.2141192927956581,
|
|
"num_tokens": 80748663.0,
|
|
"step": 41280
|
|
},
|
|
{
|
|
"entropy": 5.907307910919189,
|
|
"epoch": 4.126855600539811,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00033995151829799926,
|
|
"loss": 5.2689,
|
|
"mean_token_accuracy": 0.21263358741998672,
|
|
"num_tokens": 80758164.0,
|
|
"step": 41285
|
|
},
|
|
{
|
|
"entropy": 5.764791679382324,
|
|
"epoch": 4.127355425601039,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00033991734774919274,
|
|
"loss": 5.3208,
|
|
"mean_token_accuracy": 0.21391544193029405,
|
|
"num_tokens": 80768098.0,
|
|
"step": 41290
|
|
},
|
|
{
|
|
"entropy": 5.8534387111663815,
|
|
"epoch": 4.127855250662268,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0003398831755670825,
|
|
"loss": 5.3145,
|
|
"mean_token_accuracy": 0.20791954249143602,
|
|
"num_tokens": 80776716.0,
|
|
"step": 41295
|
|
},
|
|
{
|
|
"entropy": 5.973248386383057,
|
|
"epoch": 4.128355075723497,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0003398490017525283,
|
|
"loss": 5.395,
|
|
"mean_token_accuracy": 0.2005654066801071,
|
|
"num_tokens": 80787000.0,
|
|
"step": 41300
|
|
},
|
|
{
|
|
"entropy": 5.89378604888916,
|
|
"epoch": 4.1288549007847255,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00033981482630638976,
|
|
"loss": 5.3438,
|
|
"mean_token_accuracy": 0.2082360252737999,
|
|
"num_tokens": 80796872.0,
|
|
"step": 41305
|
|
},
|
|
{
|
|
"entropy": 5.920051765441895,
|
|
"epoch": 4.129354725845954,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00033978064922952694,
|
|
"loss": 5.3712,
|
|
"mean_token_accuracy": 0.19885637015104293,
|
|
"num_tokens": 80807057.0,
|
|
"step": 41310
|
|
},
|
|
{
|
|
"entropy": 5.809976577758789,
|
|
"epoch": 4.129854550907183,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00033974647052279963,
|
|
"loss": 5.2546,
|
|
"mean_token_accuracy": 0.21373467296361923,
|
|
"num_tokens": 80816710.0,
|
|
"step": 41315
|
|
},
|
|
{
|
|
"entropy": 5.963050603866577,
|
|
"epoch": 4.130354375968411,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0003397122901870678,
|
|
"loss": 5.4441,
|
|
"mean_token_accuracy": 0.2026151344180107,
|
|
"num_tokens": 80826381.0,
|
|
"step": 41320
|
|
},
|
|
{
|
|
"entropy": 5.829420852661133,
|
|
"epoch": 4.130854201029639,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0003396781082231914,
|
|
"loss": 5.2349,
|
|
"mean_token_accuracy": 0.21859236657619477,
|
|
"num_tokens": 80835131.0,
|
|
"step": 41325
|
|
},
|
|
{
|
|
"entropy": 5.835323619842529,
|
|
"epoch": 4.131354026090868,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00033964392463203043,
|
|
"loss": 5.3298,
|
|
"mean_token_accuracy": 0.21287394016981126,
|
|
"num_tokens": 80844179.0,
|
|
"step": 41330
|
|
},
|
|
{
|
|
"entropy": 5.861175918579102,
|
|
"epoch": 4.131853851152097,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00033960973941444503,
|
|
"loss": 5.2538,
|
|
"mean_token_accuracy": 0.21000756472349166,
|
|
"num_tokens": 80853666.0,
|
|
"step": 41335
|
|
},
|
|
{
|
|
"entropy": 5.901293992996216,
|
|
"epoch": 4.1323536762133255,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00033957555257129514,
|
|
"loss": 5.2691,
|
|
"mean_token_accuracy": 0.2149239882826805,
|
|
"num_tokens": 80862931.0,
|
|
"step": 41340
|
|
},
|
|
{
|
|
"entropy": 5.890782642364502,
|
|
"epoch": 4.132853501274554,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0003395413641034409,
|
|
"loss": 5.361,
|
|
"mean_token_accuracy": 0.2035434812307358,
|
|
"num_tokens": 80871742.0,
|
|
"step": 41345
|
|
},
|
|
{
|
|
"entropy": 5.843810176849365,
|
|
"epoch": 4.133353326335783,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0003395071740117426,
|
|
"loss": 5.3296,
|
|
"mean_token_accuracy": 0.20643959194421768,
|
|
"num_tokens": 80880421.0,
|
|
"step": 41350
|
|
},
|
|
{
|
|
"entropy": 5.811445236206055,
|
|
"epoch": 4.133853151397011,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00033947298229706043,
|
|
"loss": 5.2088,
|
|
"mean_token_accuracy": 0.22179872095584868,
|
|
"num_tokens": 80889663.0,
|
|
"step": 41355
|
|
},
|
|
{
|
|
"entropy": 5.952727890014648,
|
|
"epoch": 4.134352976458239,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0003394387889602546,
|
|
"loss": 5.3565,
|
|
"mean_token_accuracy": 0.20097180008888244,
|
|
"num_tokens": 80898406.0,
|
|
"step": 41360
|
|
},
|
|
{
|
|
"entropy": 5.859926319122314,
|
|
"epoch": 4.134852801519468,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0003394045940021854,
|
|
"loss": 5.3206,
|
|
"mean_token_accuracy": 0.20822320580482484,
|
|
"num_tokens": 80908634.0,
|
|
"step": 41365
|
|
},
|
|
{
|
|
"entropy": 5.871146249771118,
|
|
"epoch": 4.135352626580697,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00033937039742371327,
|
|
"loss": 5.3806,
|
|
"mean_token_accuracy": 0.20589987188577652,
|
|
"num_tokens": 80919014.0,
|
|
"step": 41370
|
|
},
|
|
{
|
|
"entropy": 5.892584180831909,
|
|
"epoch": 4.1358524516419255,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00033933619922569847,
|
|
"loss": 5.3543,
|
|
"mean_token_accuracy": 0.20591855943202972,
|
|
"num_tokens": 80929714.0,
|
|
"step": 41375
|
|
},
|
|
{
|
|
"entropy": 5.885867309570313,
|
|
"epoch": 4.136352276703154,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0003393019994090014,
|
|
"loss": 5.275,
|
|
"mean_token_accuracy": 0.2129104971885681,
|
|
"num_tokens": 80939590.0,
|
|
"step": 41380
|
|
},
|
|
{
|
|
"entropy": 5.81646032333374,
|
|
"epoch": 4.136852101764383,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00033926779797448253,
|
|
"loss": 5.2996,
|
|
"mean_token_accuracy": 0.21018279641866683,
|
|
"num_tokens": 80949569.0,
|
|
"step": 41385
|
|
},
|
|
{
|
|
"entropy": 5.888633680343628,
|
|
"epoch": 4.137351926825611,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0003392335949230025,
|
|
"loss": 5.371,
|
|
"mean_token_accuracy": 0.20861188173294068,
|
|
"num_tokens": 80960288.0,
|
|
"step": 41390
|
|
},
|
|
{
|
|
"entropy": 5.885562992095947,
|
|
"epoch": 4.137851751886839,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00033919939025542166,
|
|
"loss": 5.326,
|
|
"mean_token_accuracy": 0.2090885490179062,
|
|
"num_tokens": 80969680.0,
|
|
"step": 41395
|
|
},
|
|
{
|
|
"entropy": 5.928156852722168,
|
|
"epoch": 4.138351576948068,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0003391651839726008,
|
|
"loss": 5.3823,
|
|
"mean_token_accuracy": 0.2060715898871422,
|
|
"num_tokens": 80978935.0,
|
|
"step": 41400
|
|
},
|
|
{
|
|
"entropy": 5.905943822860718,
|
|
"epoch": 4.138851402009297,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0003391309760754004,
|
|
"loss": 5.3922,
|
|
"mean_token_accuracy": 0.1982008472084999,
|
|
"num_tokens": 80988206.0,
|
|
"step": 41405
|
|
},
|
|
{
|
|
"entropy": 5.904887342453003,
|
|
"epoch": 4.1393512270705255,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0003390967665646811,
|
|
"loss": 5.3847,
|
|
"mean_token_accuracy": 0.20442997813224792,
|
|
"num_tokens": 80997550.0,
|
|
"step": 41410
|
|
},
|
|
{
|
|
"entropy": 5.811082601547241,
|
|
"epoch": 4.139851052131754,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0003390625554413036,
|
|
"loss": 5.2883,
|
|
"mean_token_accuracy": 0.2078908532857895,
|
|
"num_tokens": 81007401.0,
|
|
"step": 41415
|
|
},
|
|
{
|
|
"entropy": 5.947504138946533,
|
|
"epoch": 4.140350877192983,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0003390283427061288,
|
|
"loss": 5.4232,
|
|
"mean_token_accuracy": 0.20436221212148667,
|
|
"num_tokens": 81017132.0,
|
|
"step": 41420
|
|
},
|
|
{
|
|
"entropy": 5.949694633483887,
|
|
"epoch": 4.140850702254211,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0003389941283600173,
|
|
"loss": 5.3909,
|
|
"mean_token_accuracy": 0.20203249305486679,
|
|
"num_tokens": 81026365.0,
|
|
"step": 41425
|
|
},
|
|
{
|
|
"entropy": 5.934750938415528,
|
|
"epoch": 4.141350527315439,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00033895991240383,
|
|
"loss": 5.335,
|
|
"mean_token_accuracy": 0.20495910942554474,
|
|
"num_tokens": 81036888.0,
|
|
"step": 41430
|
|
},
|
|
{
|
|
"entropy": 5.833208322525024,
|
|
"epoch": 4.141850352376668,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0003389256948384278,
|
|
"loss": 5.3505,
|
|
"mean_token_accuracy": 0.21255892962217332,
|
|
"num_tokens": 81047461.0,
|
|
"step": 41435
|
|
},
|
|
{
|
|
"entropy": 5.8688092708587645,
|
|
"epoch": 4.142350177437897,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0003388914756646715,
|
|
"loss": 5.3576,
|
|
"mean_token_accuracy": 0.2063329204916954,
|
|
"num_tokens": 81057631.0,
|
|
"step": 41440
|
|
},
|
|
{
|
|
"entropy": 5.994868326187134,
|
|
"epoch": 4.1428500024991255,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0003388572548834222,
|
|
"loss": 5.3926,
|
|
"mean_token_accuracy": 0.20360596477985382,
|
|
"num_tokens": 81068047.0,
|
|
"step": 41445
|
|
},
|
|
{
|
|
"entropy": 5.934713888168335,
|
|
"epoch": 4.143349827560354,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0003388230324955407,
|
|
"loss": 5.3229,
|
|
"mean_token_accuracy": 0.206496225297451,
|
|
"num_tokens": 81077382.0,
|
|
"step": 41450
|
|
},
|
|
{
|
|
"entropy": 5.883053636550903,
|
|
"epoch": 4.143849652621583,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00033878880850188813,
|
|
"loss": 5.2643,
|
|
"mean_token_accuracy": 0.217536561191082,
|
|
"num_tokens": 81086985.0,
|
|
"step": 41455
|
|
},
|
|
{
|
|
"entropy": 5.927677631378174,
|
|
"epoch": 4.144349477682811,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0003387545829033257,
|
|
"loss": 5.352,
|
|
"mean_token_accuracy": 0.2089991956949234,
|
|
"num_tokens": 81096796.0,
|
|
"step": 41460
|
|
},
|
|
{
|
|
"entropy": 5.850594091415405,
|
|
"epoch": 4.144849302744039,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00033872035570071425,
|
|
"loss": 5.2824,
|
|
"mean_token_accuracy": 0.21720893830060958,
|
|
"num_tokens": 81105611.0,
|
|
"step": 41465
|
|
},
|
|
{
|
|
"entropy": 5.878569746017456,
|
|
"epoch": 4.145349127805268,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00033868612689491503,
|
|
"loss": 5.327,
|
|
"mean_token_accuracy": 0.20428986400365828,
|
|
"num_tokens": 81115079.0,
|
|
"step": 41470
|
|
},
|
|
{
|
|
"entropy": 5.854608774185181,
|
|
"epoch": 4.145848952866497,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00033865189648678935,
|
|
"loss": 5.3429,
|
|
"mean_token_accuracy": 0.20825671255588532,
|
|
"num_tokens": 81124180.0,
|
|
"step": 41475
|
|
},
|
|
{
|
|
"entropy": 5.909371089935303,
|
|
"epoch": 4.1463487779277255,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00033861766447719824,
|
|
"loss": 5.4312,
|
|
"mean_token_accuracy": 0.2042916461825371,
|
|
"num_tokens": 81132827.0,
|
|
"step": 41480
|
|
},
|
|
{
|
|
"entropy": 5.95251612663269,
|
|
"epoch": 4.146848602988954,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00033858343086700304,
|
|
"loss": 5.3835,
|
|
"mean_token_accuracy": 0.20557016879320145,
|
|
"num_tokens": 81142704.0,
|
|
"step": 41485
|
|
},
|
|
{
|
|
"entropy": 5.895669603347779,
|
|
"epoch": 4.147348428050183,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00033854919565706515,
|
|
"loss": 5.2981,
|
|
"mean_token_accuracy": 0.20705629587173463,
|
|
"num_tokens": 81151936.0,
|
|
"step": 41490
|
|
},
|
|
{
|
|
"entropy": 5.914319944381714,
|
|
"epoch": 4.147848253111411,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00033851495884824586,
|
|
"loss": 5.3698,
|
|
"mean_token_accuracy": 0.2070123478770256,
|
|
"num_tokens": 81161880.0,
|
|
"step": 41495
|
|
},
|
|
{
|
|
"entropy": 5.916010522842408,
|
|
"epoch": 4.148348078172639,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0003384807204414065,
|
|
"loss": 5.3203,
|
|
"mean_token_accuracy": 0.2089023098349571,
|
|
"num_tokens": 81171481.0,
|
|
"step": 41500
|
|
},
|
|
{
|
|
"entropy": 5.881155395507813,
|
|
"epoch": 4.148847903233868,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0003384464804374086,
|
|
"loss": 5.3498,
|
|
"mean_token_accuracy": 0.20125409364700317,
|
|
"num_tokens": 81181479.0,
|
|
"step": 41505
|
|
},
|
|
{
|
|
"entropy": 5.868193960189819,
|
|
"epoch": 4.149347728295097,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0003384122388371135,
|
|
"loss": 5.341,
|
|
"mean_token_accuracy": 0.21064985543489456,
|
|
"num_tokens": 81190143.0,
|
|
"step": 41510
|
|
},
|
|
{
|
|
"entropy": 5.878230905532837,
|
|
"epoch": 4.1498475533563255,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0003383779956413829,
|
|
"loss": 5.3498,
|
|
"mean_token_accuracy": 0.20978809893131256,
|
|
"num_tokens": 81199475.0,
|
|
"step": 41515
|
|
},
|
|
{
|
|
"entropy": 5.921501207351684,
|
|
"epoch": 4.150347378417554,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0003383437508510781,
|
|
"loss": 5.3196,
|
|
"mean_token_accuracy": 0.21182744950056076,
|
|
"num_tokens": 81208344.0,
|
|
"step": 41520
|
|
},
|
|
{
|
|
"entropy": 5.838136100769043,
|
|
"epoch": 4.150847203478782,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0003383095044670609,
|
|
"loss": 5.2122,
|
|
"mean_token_accuracy": 0.22631081342697143,
|
|
"num_tokens": 81217939.0,
|
|
"step": 41525
|
|
},
|
|
{
|
|
"entropy": 5.770044898986816,
|
|
"epoch": 4.151347028540011,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00033827525649019293,
|
|
"loss": 5.2441,
|
|
"mean_token_accuracy": 0.21669430434703826,
|
|
"num_tokens": 81227672.0,
|
|
"step": 41530
|
|
},
|
|
{
|
|
"entropy": 5.847643661499023,
|
|
"epoch": 4.151846853601239,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00033824100692133566,
|
|
"loss": 5.2891,
|
|
"mean_token_accuracy": 0.21337797343730927,
|
|
"num_tokens": 81237061.0,
|
|
"step": 41535
|
|
},
|
|
{
|
|
"entropy": 5.94083046913147,
|
|
"epoch": 4.152346678662468,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.000338206755761351,
|
|
"loss": 5.2945,
|
|
"mean_token_accuracy": 0.21463214457035065,
|
|
"num_tokens": 81247546.0,
|
|
"step": 41540
|
|
},
|
|
{
|
|
"entropy": 5.875171947479248,
|
|
"epoch": 4.152846503723697,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0003381725030111006,
|
|
"loss": 5.3478,
|
|
"mean_token_accuracy": 0.20112679153680801,
|
|
"num_tokens": 81257874.0,
|
|
"step": 41545
|
|
},
|
|
{
|
|
"entropy": 5.7153565883636475,
|
|
"epoch": 4.1533463287849255,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0003381382486714463,
|
|
"loss": 5.1722,
|
|
"mean_token_accuracy": 0.23120564818382264,
|
|
"num_tokens": 81267788.0,
|
|
"step": 41550
|
|
},
|
|
{
|
|
"entropy": 5.943997573852539,
|
|
"epoch": 4.153846153846154,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.00033810399274324994,
|
|
"loss": 5.3744,
|
|
"mean_token_accuracy": 0.20393904745578767,
|
|
"num_tokens": 81277623.0,
|
|
"step": 41555
|
|
},
|
|
{
|
|
"entropy": 5.903497695922852,
|
|
"epoch": 4.154345978907382,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00033806973522737326,
|
|
"loss": 5.3294,
|
|
"mean_token_accuracy": 0.20878972709178925,
|
|
"num_tokens": 81287888.0,
|
|
"step": 41560
|
|
},
|
|
{
|
|
"entropy": 5.811821031570434,
|
|
"epoch": 4.154845803968611,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0003380354761246784,
|
|
"loss": 5.2326,
|
|
"mean_token_accuracy": 0.21466774493455887,
|
|
"num_tokens": 81296595.0,
|
|
"step": 41565
|
|
},
|
|
{
|
|
"entropy": 5.800955200195313,
|
|
"epoch": 4.155345629029839,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0003380012154360271,
|
|
"loss": 5.3272,
|
|
"mean_token_accuracy": 0.2093423679471016,
|
|
"num_tokens": 81306910.0,
|
|
"step": 41570
|
|
},
|
|
{
|
|
"entropy": 5.87511248588562,
|
|
"epoch": 4.155845454091068,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0003379669531622814,
|
|
"loss": 5.3474,
|
|
"mean_token_accuracy": 0.20789800584316254,
|
|
"num_tokens": 81315971.0,
|
|
"step": 41575
|
|
},
|
|
{
|
|
"entropy": 5.917051506042481,
|
|
"epoch": 4.156345279152297,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0003379326893043034,
|
|
"loss": 5.3825,
|
|
"mean_token_accuracy": 0.19944969564676285,
|
|
"num_tokens": 81326229.0,
|
|
"step": 41580
|
|
},
|
|
{
|
|
"entropy": 5.890831327438354,
|
|
"epoch": 4.1568451042135255,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0003378984238629552,
|
|
"loss": 5.3256,
|
|
"mean_token_accuracy": 0.21268305629491807,
|
|
"num_tokens": 81336256.0,
|
|
"step": 41585
|
|
},
|
|
{
|
|
"entropy": 5.858073663711548,
|
|
"epoch": 4.157344929274754,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0003378641568390988,
|
|
"loss": 5.2962,
|
|
"mean_token_accuracy": 0.20730402320623398,
|
|
"num_tokens": 81345535.0,
|
|
"step": 41590
|
|
},
|
|
{
|
|
"entropy": 5.903807878494263,
|
|
"epoch": 4.157844754335982,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0003378298882335963,
|
|
"loss": 5.2917,
|
|
"mean_token_accuracy": 0.21606025844812393,
|
|
"num_tokens": 81354418.0,
|
|
"step": 41595
|
|
},
|
|
{
|
|
"entropy": 5.9662901878356935,
|
|
"epoch": 4.158344579397211,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00033779561804731005,
|
|
"loss": 5.4765,
|
|
"mean_token_accuracy": 0.19073695838451385,
|
|
"num_tokens": 81365390.0,
|
|
"step": 41600
|
|
},
|
|
{
|
|
"entropy": 5.84029369354248,
|
|
"epoch": 4.158844404458439,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0003377613462811022,
|
|
"loss": 5.2984,
|
|
"mean_token_accuracy": 0.21220533400774003,
|
|
"num_tokens": 81376662.0,
|
|
"step": 41605
|
|
},
|
|
{
|
|
"entropy": 5.962385559082032,
|
|
"epoch": 4.159344229519668,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0003377270729358351,
|
|
"loss": 5.3857,
|
|
"mean_token_accuracy": 0.19838718622922896,
|
|
"num_tokens": 81387071.0,
|
|
"step": 41610
|
|
},
|
|
{
|
|
"entropy": 5.927651453018188,
|
|
"epoch": 4.159844054580897,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0003376927980123709,
|
|
"loss": 5.4452,
|
|
"mean_token_accuracy": 0.20338589549064637,
|
|
"num_tokens": 81397202.0,
|
|
"step": 41615
|
|
},
|
|
{
|
|
"entropy": 5.825046396255493,
|
|
"epoch": 4.1603438796421255,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0003376585215115721,
|
|
"loss": 5.2642,
|
|
"mean_token_accuracy": 0.21369843780994416,
|
|
"num_tokens": 81406757.0,
|
|
"step": 41620
|
|
},
|
|
{
|
|
"entropy": 5.9005126953125,
|
|
"epoch": 4.160843704703354,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00033762424343430106,
|
|
"loss": 5.3743,
|
|
"mean_token_accuracy": 0.2017272502183914,
|
|
"num_tokens": 81416493.0,
|
|
"step": 41625
|
|
},
|
|
{
|
|
"entropy": 5.880653047561646,
|
|
"epoch": 4.161343529764582,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00033758996378142,
|
|
"loss": 5.3854,
|
|
"mean_token_accuracy": 0.2113005116581917,
|
|
"num_tokens": 81427108.0,
|
|
"step": 41630
|
|
},
|
|
{
|
|
"entropy": 5.906683158874512,
|
|
"epoch": 4.161843354825811,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00033755568255379166,
|
|
"loss": 5.3518,
|
|
"mean_token_accuracy": 0.204648719727993,
|
|
"num_tokens": 81436112.0,
|
|
"step": 41635
|
|
},
|
|
{
|
|
"entropy": 5.928301763534546,
|
|
"epoch": 4.162343179887039,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0003375213997522784,
|
|
"loss": 5.3395,
|
|
"mean_token_accuracy": 0.20643699318170547,
|
|
"num_tokens": 81447198.0,
|
|
"step": 41640
|
|
},
|
|
{
|
|
"entropy": 5.858123540878296,
|
|
"epoch": 4.162843004948268,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00033748711537774287,
|
|
"loss": 5.3301,
|
|
"mean_token_accuracy": 0.21257968693971635,
|
|
"num_tokens": 81457203.0,
|
|
"step": 41645
|
|
},
|
|
{
|
|
"entropy": 5.965526914596557,
|
|
"epoch": 4.163342830009497,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0003374528294310476,
|
|
"loss": 5.4043,
|
|
"mean_token_accuracy": 0.20325331389904022,
|
|
"num_tokens": 81467264.0,
|
|
"step": 41650
|
|
},
|
|
{
|
|
"entropy": 5.92089433670044,
|
|
"epoch": 4.1638426550707255,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00033741854191305515,
|
|
"loss": 5.3398,
|
|
"mean_token_accuracy": 0.2013572186231613,
|
|
"num_tokens": 81476590.0,
|
|
"step": 41655
|
|
},
|
|
{
|
|
"entropy": 5.87788610458374,
|
|
"epoch": 4.164342480131954,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0003373842528246283,
|
|
"loss": 5.356,
|
|
"mean_token_accuracy": 0.20276009887456894,
|
|
"num_tokens": 81487224.0,
|
|
"step": 41660
|
|
},
|
|
{
|
|
"entropy": 5.910291957855224,
|
|
"epoch": 4.164842305193182,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0003373499621666296,
|
|
"loss": 5.3155,
|
|
"mean_token_accuracy": 0.21572205722332,
|
|
"num_tokens": 81496498.0,
|
|
"step": 41665
|
|
},
|
|
{
|
|
"entropy": 5.878171920776367,
|
|
"epoch": 4.165342130254411,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00033731566993992204,
|
|
"loss": 5.2704,
|
|
"mean_token_accuracy": 0.2103830024600029,
|
|
"num_tokens": 81505323.0,
|
|
"step": 41670
|
|
},
|
|
{
|
|
"entropy": 5.88123664855957,
|
|
"epoch": 4.165841955315639,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00033728137614536815,
|
|
"loss": 5.3474,
|
|
"mean_token_accuracy": 0.21585964262485505,
|
|
"num_tokens": 81515609.0,
|
|
"step": 41675
|
|
},
|
|
{
|
|
"entropy": 5.891832542419434,
|
|
"epoch": 4.166341780376868,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0003372470807838309,
|
|
"loss": 5.3905,
|
|
"mean_token_accuracy": 0.20976355522871018,
|
|
"num_tokens": 81525199.0,
|
|
"step": 41680
|
|
},
|
|
{
|
|
"entropy": 5.895206689834595,
|
|
"epoch": 4.166841605438097,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00033721278385617315,
|
|
"loss": 5.2841,
|
|
"mean_token_accuracy": 0.21071446388959886,
|
|
"num_tokens": 81536283.0,
|
|
"step": 41685
|
|
},
|
|
{
|
|
"entropy": 5.923553228378296,
|
|
"epoch": 4.1673414304993255,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0003371784853632577,
|
|
"loss": 5.4113,
|
|
"mean_token_accuracy": 0.2002642944455147,
|
|
"num_tokens": 81545711.0,
|
|
"step": 41690
|
|
},
|
|
{
|
|
"entropy": 5.815177726745605,
|
|
"epoch": 4.167841255560554,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00033714418530594767,
|
|
"loss": 5.2383,
|
|
"mean_token_accuracy": 0.21198870986700058,
|
|
"num_tokens": 81556032.0,
|
|
"step": 41695
|
|
},
|
|
{
|
|
"entropy": 5.932927846908569,
|
|
"epoch": 4.168341080621782,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0003371098836851058,
|
|
"loss": 5.4301,
|
|
"mean_token_accuracy": 0.1989677593111992,
|
|
"num_tokens": 81567939.0,
|
|
"step": 41700
|
|
},
|
|
{
|
|
"entropy": 5.900043201446533,
|
|
"epoch": 4.168840905683011,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0003370755805015953,
|
|
"loss": 5.2663,
|
|
"mean_token_accuracy": 0.21374820470809935,
|
|
"num_tokens": 81576900.0,
|
|
"step": 41705
|
|
},
|
|
{
|
|
"entropy": 5.956386613845825,
|
|
"epoch": 4.169340730744239,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0003370412757562792,
|
|
"loss": 5.3604,
|
|
"mean_token_accuracy": 0.20486236959695817,
|
|
"num_tokens": 81586776.0,
|
|
"step": 41710
|
|
},
|
|
{
|
|
"entropy": 5.857656574249267,
|
|
"epoch": 4.169840555805468,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0003370069694500205,
|
|
"loss": 5.2401,
|
|
"mean_token_accuracy": 0.21648634374141693,
|
|
"num_tokens": 81598043.0,
|
|
"step": 41715
|
|
},
|
|
{
|
|
"entropy": 5.859766149520874,
|
|
"epoch": 4.170340380866697,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0003369726615836825,
|
|
"loss": 5.2741,
|
|
"mean_token_accuracy": 0.21326974034309387,
|
|
"num_tokens": 81607522.0,
|
|
"step": 41720
|
|
},
|
|
{
|
|
"entropy": 5.951134395599365,
|
|
"epoch": 4.1708402059279255,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0003369383521581282,
|
|
"loss": 5.4578,
|
|
"mean_token_accuracy": 0.1980753183364868,
|
|
"num_tokens": 81616668.0,
|
|
"step": 41725
|
|
},
|
|
{
|
|
"entropy": 5.911991739273072,
|
|
"epoch": 4.171340030989154,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00033690404117422084,
|
|
"loss": 5.3554,
|
|
"mean_token_accuracy": 0.20771685242652893,
|
|
"num_tokens": 81626967.0,
|
|
"step": 41730
|
|
},
|
|
{
|
|
"entropy": 5.926793718338013,
|
|
"epoch": 4.171839856050382,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00033686972863282384,
|
|
"loss": 5.3905,
|
|
"mean_token_accuracy": 0.21059872061014176,
|
|
"num_tokens": 81637399.0,
|
|
"step": 41735
|
|
},
|
|
{
|
|
"entropy": 5.878499269485474,
|
|
"epoch": 4.172339681111611,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0003368354145348003,
|
|
"loss": 5.375,
|
|
"mean_token_accuracy": 0.20495781004428865,
|
|
"num_tokens": 81646959.0,
|
|
"step": 41740
|
|
},
|
|
{
|
|
"entropy": 5.845876836776734,
|
|
"epoch": 4.172839506172839,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00033680109888101375,
|
|
"loss": 5.3162,
|
|
"mean_token_accuracy": 0.2097728207707405,
|
|
"num_tokens": 81656110.0,
|
|
"step": 41745
|
|
},
|
|
{
|
|
"entropy": 5.840163230895996,
|
|
"epoch": 4.173339331234068,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0003367667816723274,
|
|
"loss": 5.2906,
|
|
"mean_token_accuracy": 0.21367159783840178,
|
|
"num_tokens": 81666077.0,
|
|
"step": 41750
|
|
},
|
|
{
|
|
"entropy": 5.954771232604981,
|
|
"epoch": 4.173839156295297,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0003367324629096047,
|
|
"loss": 5.4079,
|
|
"mean_token_accuracy": 0.20146235972642898,
|
|
"num_tokens": 81675000.0,
|
|
"step": 41755
|
|
},
|
|
{
|
|
"entropy": 5.89793438911438,
|
|
"epoch": 4.1743389813565255,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0003366981425937091,
|
|
"loss": 5.293,
|
|
"mean_token_accuracy": 0.21113371700048447,
|
|
"num_tokens": 81685347.0,
|
|
"step": 41760
|
|
},
|
|
{
|
|
"entropy": 5.900915193557739,
|
|
"epoch": 4.174838806417754,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00033666382072550417,
|
|
"loss": 5.4026,
|
|
"mean_token_accuracy": 0.20330791920423508,
|
|
"num_tokens": 81694953.0,
|
|
"step": 41765
|
|
},
|
|
{
|
|
"entropy": 5.92438383102417,
|
|
"epoch": 4.175338631478982,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00033662949730585336,
|
|
"loss": 5.3814,
|
|
"mean_token_accuracy": 0.20374057739973067,
|
|
"num_tokens": 81704883.0,
|
|
"step": 41770
|
|
},
|
|
{
|
|
"entropy": 5.896563482284546,
|
|
"epoch": 4.175838456540211,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0003365951723356202,
|
|
"loss": 5.2977,
|
|
"mean_token_accuracy": 0.21230882853269578,
|
|
"num_tokens": 81713404.0,
|
|
"step": 41775
|
|
},
|
|
{
|
|
"entropy": 5.8655914783477785,
|
|
"epoch": 4.176338281601439,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00033656084581566844,
|
|
"loss": 5.3225,
|
|
"mean_token_accuracy": 0.2067017748951912,
|
|
"num_tokens": 81722656.0,
|
|
"step": 41780
|
|
},
|
|
{
|
|
"entropy": 5.828904008865356,
|
|
"epoch": 4.176838106662668,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00033652651774686163,
|
|
"loss": 5.2591,
|
|
"mean_token_accuracy": 0.20949292033910752,
|
|
"num_tokens": 81732862.0,
|
|
"step": 41785
|
|
},
|
|
{
|
|
"entropy": 5.94668231010437,
|
|
"epoch": 4.177337931723897,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00033649218813006337,
|
|
"loss": 5.4015,
|
|
"mean_token_accuracy": 0.20739783197641373,
|
|
"num_tokens": 81742730.0,
|
|
"step": 41790
|
|
},
|
|
{
|
|
"entropy": 5.902008533477783,
|
|
"epoch": 4.1778377567851255,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0003364578569661376,
|
|
"loss": 5.3596,
|
|
"mean_token_accuracy": 0.20695759505033492,
|
|
"num_tokens": 81752177.0,
|
|
"step": 41795
|
|
},
|
|
{
|
|
"entropy": 5.909472799301147,
|
|
"epoch": 4.178337581846354,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00033642352425594787,
|
|
"loss": 5.3417,
|
|
"mean_token_accuracy": 0.2009623810648918,
|
|
"num_tokens": 81761377.0,
|
|
"step": 41800
|
|
},
|
|
{
|
|
"entropy": 5.870336961746216,
|
|
"epoch": 4.178837406907582,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00033638919000035815,
|
|
"loss": 5.3587,
|
|
"mean_token_accuracy": 0.20621226876974105,
|
|
"num_tokens": 81771417.0,
|
|
"step": 41805
|
|
},
|
|
{
|
|
"entropy": 5.49597053527832,
|
|
"epoch": 4.179337231968811,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00033635485420023217,
|
|
"loss": 4.9506,
|
|
"mean_token_accuracy": 0.25460559874773026,
|
|
"num_tokens": 81780626.0,
|
|
"step": 41810
|
|
},
|
|
{
|
|
"entropy": 5.945091629028321,
|
|
"epoch": 4.179837057030039,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0003363205168564338,
|
|
"loss": 5.3819,
|
|
"mean_token_accuracy": 0.20193677097558976,
|
|
"num_tokens": 81790954.0,
|
|
"step": 41815
|
|
},
|
|
{
|
|
"entropy": 5.910964250564575,
|
|
"epoch": 4.180336882091268,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00033628617796982707,
|
|
"loss": 5.4021,
|
|
"mean_token_accuracy": 0.20435738414525986,
|
|
"num_tokens": 81801343.0,
|
|
"step": 41820
|
|
},
|
|
{
|
|
"entropy": 5.9155271530151365,
|
|
"epoch": 4.180836707152497,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00033625183754127584,
|
|
"loss": 5.3932,
|
|
"mean_token_accuracy": 0.20216701030731202,
|
|
"num_tokens": 81810615.0,
|
|
"step": 41825
|
|
},
|
|
{
|
|
"entropy": 5.946329021453858,
|
|
"epoch": 4.1813365322137255,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0003362174955716442,
|
|
"loss": 5.4396,
|
|
"mean_token_accuracy": 0.2035554528236389,
|
|
"num_tokens": 81821104.0,
|
|
"step": 41830
|
|
},
|
|
{
|
|
"entropy": 5.858975744247436,
|
|
"epoch": 4.181836357274954,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00033618315206179614,
|
|
"loss": 5.3267,
|
|
"mean_token_accuracy": 0.20307343900203706,
|
|
"num_tokens": 81830841.0,
|
|
"step": 41835
|
|
},
|
|
{
|
|
"entropy": 5.8826438903808596,
|
|
"epoch": 4.182336182336182,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0003361488070125956,
|
|
"loss": 5.3038,
|
|
"mean_token_accuracy": 0.2069324553012848,
|
|
"num_tokens": 81840356.0,
|
|
"step": 41840
|
|
},
|
|
{
|
|
"entropy": 5.9301928043365475,
|
|
"epoch": 4.182836007397411,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0003361144604249069,
|
|
"loss": 5.3585,
|
|
"mean_token_accuracy": 0.2121896043419838,
|
|
"num_tokens": 81850768.0,
|
|
"step": 41845
|
|
},
|
|
{
|
|
"entropy": 5.844897365570068,
|
|
"epoch": 4.183335832458639,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00033608011229959404,
|
|
"loss": 5.3363,
|
|
"mean_token_accuracy": 0.20363711714744567,
|
|
"num_tokens": 81862285.0,
|
|
"step": 41850
|
|
},
|
|
{
|
|
"entropy": 5.961703157424926,
|
|
"epoch": 4.183835657519868,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0003360457626375213,
|
|
"loss": 5.3591,
|
|
"mean_token_accuracy": 0.20840547233819962,
|
|
"num_tokens": 81871662.0,
|
|
"step": 41855
|
|
},
|
|
{
|
|
"entropy": 5.891100168228149,
|
|
"epoch": 4.184335482581097,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0003360114114395529,
|
|
"loss": 5.3677,
|
|
"mean_token_accuracy": 0.2088279515504837,
|
|
"num_tokens": 81881170.0,
|
|
"step": 41860
|
|
},
|
|
{
|
|
"entropy": 5.849641180038452,
|
|
"epoch": 4.1848353076423255,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000335977058706553,
|
|
"loss": 5.2874,
|
|
"mean_token_accuracy": 0.21289737969636918,
|
|
"num_tokens": 81891782.0,
|
|
"step": 41865
|
|
},
|
|
{
|
|
"entropy": 5.934802007675171,
|
|
"epoch": 4.185335132703554,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00033594270443938604,
|
|
"loss": 5.4029,
|
|
"mean_token_accuracy": 0.199313186109066,
|
|
"num_tokens": 81900945.0,
|
|
"step": 41870
|
|
},
|
|
{
|
|
"entropy": 5.949049949645996,
|
|
"epoch": 4.185834957764782,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00033590834863891645,
|
|
"loss": 5.3107,
|
|
"mean_token_accuracy": 0.20744525790214538,
|
|
"num_tokens": 81910114.0,
|
|
"step": 41875
|
|
},
|
|
{
|
|
"entropy": 5.879236936569214,
|
|
"epoch": 4.186334782826011,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0003358739913060083,
|
|
"loss": 5.3404,
|
|
"mean_token_accuracy": 0.20906075835227966,
|
|
"num_tokens": 81919605.0,
|
|
"step": 41880
|
|
},
|
|
{
|
|
"entropy": 5.8944145202636715,
|
|
"epoch": 4.186834607887239,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0003358396324415263,
|
|
"loss": 5.4445,
|
|
"mean_token_accuracy": 0.19775208532810212,
|
|
"num_tokens": 81929585.0,
|
|
"step": 41885
|
|
},
|
|
{
|
|
"entropy": 5.921318626403808,
|
|
"epoch": 4.187334432948468,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00033580527204633473,
|
|
"loss": 5.3949,
|
|
"mean_token_accuracy": 0.20411209613084794,
|
|
"num_tokens": 81938666.0,
|
|
"step": 41890
|
|
},
|
|
{
|
|
"entropy": 5.885322332382202,
|
|
"epoch": 4.187834258009697,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0003357709101212983,
|
|
"loss": 5.3674,
|
|
"mean_token_accuracy": 0.2042846918106079,
|
|
"num_tokens": 81949517.0,
|
|
"step": 41895
|
|
},
|
|
{
|
|
"entropy": 5.832884836196899,
|
|
"epoch": 4.1883340830709255,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00033573654666728127,
|
|
"loss": 5.314,
|
|
"mean_token_accuracy": 0.21544160544872284,
|
|
"num_tokens": 81960997.0,
|
|
"step": 41900
|
|
},
|
|
{
|
|
"entropy": 5.843998384475708,
|
|
"epoch": 4.188833908132154,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0003357021816851484,
|
|
"loss": 5.318,
|
|
"mean_token_accuracy": 0.20804181098937988,
|
|
"num_tokens": 81971613.0,
|
|
"step": 41905
|
|
},
|
|
{
|
|
"entropy": 5.864389324188233,
|
|
"epoch": 4.189333733193382,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0003356678151757643,
|
|
"loss": 5.2656,
|
|
"mean_token_accuracy": 0.21032350212335588,
|
|
"num_tokens": 81980030.0,
|
|
"step": 41910
|
|
},
|
|
{
|
|
"entropy": 5.873065233230591,
|
|
"epoch": 4.189833558254611,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00033563344713999344,
|
|
"loss": 5.3477,
|
|
"mean_token_accuracy": 0.21250497698783874,
|
|
"num_tokens": 81989610.0,
|
|
"step": 41915
|
|
},
|
|
{
|
|
"entropy": 5.793652200698853,
|
|
"epoch": 4.190333383315839,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00033559907757870074,
|
|
"loss": 5.3203,
|
|
"mean_token_accuracy": 0.21508147418498993,
|
|
"num_tokens": 81999808.0,
|
|
"step": 41920
|
|
},
|
|
{
|
|
"entropy": 5.896332216262818,
|
|
"epoch": 4.190833208377068,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00033556470649275086,
|
|
"loss": 5.2579,
|
|
"mean_token_accuracy": 0.21684550046920775,
|
|
"num_tokens": 82009520.0,
|
|
"step": 41925
|
|
},
|
|
{
|
|
"entropy": 5.7810756206512455,
|
|
"epoch": 4.191333033438297,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0003355303338830086,
|
|
"loss": 5.2055,
|
|
"mean_token_accuracy": 0.21704887151718139,
|
|
"num_tokens": 82019920.0,
|
|
"step": 41930
|
|
},
|
|
{
|
|
"entropy": 5.941970491409302,
|
|
"epoch": 4.1918328584995255,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0003354959597503386,
|
|
"loss": 5.3758,
|
|
"mean_token_accuracy": 0.19944633394479752,
|
|
"num_tokens": 82030098.0,
|
|
"step": 41935
|
|
},
|
|
{
|
|
"entropy": 5.916138553619385,
|
|
"epoch": 4.192332683560753,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00033546158409560587,
|
|
"loss": 5.3845,
|
|
"mean_token_accuracy": 0.2032526895403862,
|
|
"num_tokens": 82039830.0,
|
|
"step": 41940
|
|
},
|
|
{
|
|
"entropy": 5.913213729858398,
|
|
"epoch": 4.192832508621982,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0003354272069196752,
|
|
"loss": 5.3709,
|
|
"mean_token_accuracy": 0.20699184238910676,
|
|
"num_tokens": 82049428.0,
|
|
"step": 41945
|
|
},
|
|
{
|
|
"entropy": 5.851233911514282,
|
|
"epoch": 4.193332333683211,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0003353928282234116,
|
|
"loss": 5.3843,
|
|
"mean_token_accuracy": 0.21255514472723008,
|
|
"num_tokens": 82059970.0,
|
|
"step": 41950
|
|
},
|
|
{
|
|
"entropy": 5.803523111343384,
|
|
"epoch": 4.193832158744439,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00033535844800768,
|
|
"loss": 5.148,
|
|
"mean_token_accuracy": 0.23292334675788878,
|
|
"num_tokens": 82069944.0,
|
|
"step": 41955
|
|
},
|
|
{
|
|
"entropy": 5.963912487030029,
|
|
"epoch": 4.194331983805668,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00033532406627334534,
|
|
"loss": 5.3753,
|
|
"mean_token_accuracy": 0.20600321143865585,
|
|
"num_tokens": 82079061.0,
|
|
"step": 41960
|
|
},
|
|
{
|
|
"entropy": 5.874491214752197,
|
|
"epoch": 4.194831808866897,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0003352896830212728,
|
|
"loss": 5.3133,
|
|
"mean_token_accuracy": 0.20905964076519012,
|
|
"num_tokens": 82088304.0,
|
|
"step": 41965
|
|
},
|
|
{
|
|
"entropy": 5.830759000778198,
|
|
"epoch": 4.1953316339281255,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0003352552982523272,
|
|
"loss": 5.3245,
|
|
"mean_token_accuracy": 0.21429652720689774,
|
|
"num_tokens": 82098721.0,
|
|
"step": 41970
|
|
},
|
|
{
|
|
"entropy": 5.827608871459961,
|
|
"epoch": 4.195831458989353,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0003352209119673739,
|
|
"loss": 5.4058,
|
|
"mean_token_accuracy": 0.19622579962015152,
|
|
"num_tokens": 82108845.0,
|
|
"step": 41975
|
|
},
|
|
{
|
|
"entropy": 5.885152387619018,
|
|
"epoch": 4.196331284050582,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00033518652416727785,
|
|
"loss": 5.274,
|
|
"mean_token_accuracy": 0.20517093539237977,
|
|
"num_tokens": 82118327.0,
|
|
"step": 41980
|
|
},
|
|
{
|
|
"entropy": 5.846117782592773,
|
|
"epoch": 4.196831109111811,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0003351521348529044,
|
|
"loss": 5.2724,
|
|
"mean_token_accuracy": 0.21387373358011247,
|
|
"num_tokens": 82127601.0,
|
|
"step": 41985
|
|
},
|
|
{
|
|
"entropy": 5.827354431152344,
|
|
"epoch": 4.197330934173039,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00033511774402511876,
|
|
"loss": 5.223,
|
|
"mean_token_accuracy": 0.22201705873012542,
|
|
"num_tokens": 82138311.0,
|
|
"step": 41990
|
|
},
|
|
{
|
|
"entropy": 5.815892219543457,
|
|
"epoch": 4.197830759234268,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0003350833516847861,
|
|
"loss": 5.2638,
|
|
"mean_token_accuracy": 0.22115264534950257,
|
|
"num_tokens": 82148430.0,
|
|
"step": 41995
|
|
},
|
|
{
|
|
"entropy": 5.807044124603271,
|
|
"epoch": 4.198330584295497,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00033504895783277176,
|
|
"loss": 5.2853,
|
|
"mean_token_accuracy": 0.2075140282511711,
|
|
"num_tokens": 82158032.0,
|
|
"step": 42000
|
|
},
|
|
{
|
|
"epoch": 4.198330584295497,
|
|
"eval_entropy": 5.610873275244245,
|
|
"eval_loss": 5.503930568695068,
|
|
"eval_mean_token_accuracy": 0.2084536862422114,
|
|
"eval_num_tokens": 82158032.0,
|
|
"eval_runtime": 23.7259,
|
|
"eval_samples_per_second": 1308.487,
|
|
"eval_steps_per_second": 163.577,
|
|
"step": 42000
|
|
}
|
|
],
|
|
"logging_steps": 5,
|
|
"max_steps": 100030,
|
|
"num_input_tokens_seen": 0,
|
|
"num_train_epochs": 10,
|
|
"save_steps": 3000,
|
|
"stateful_callbacks": {
|
|
"TrainerControl": {
|
|
"args": {
|
|
"should_epoch_stop": false,
|
|
"should_evaluate": false,
|
|
"should_log": false,
|
|
"should_save": true,
|
|
"should_training_stop": false
|
|
},
|
|
"attributes": {}
|
|
}
|
|
},
|
|
"total_flos": 1.30353956831232e+17,
|
|
"train_batch_size": 16,
|
|
"trial_name": null,
|
|
"trial_params": null
|
|
}
|