12057 lines
329 KiB
JSON
12057 lines
329 KiB
JSON
{
|
|
"best_global_step": null,
|
|
"best_metric": null,
|
|
"best_model_checkpoint": null,
|
|
"epoch": 0.599790073474284,
|
|
"eval_steps": 3000,
|
|
"global_step": 6000,
|
|
"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
|
|
}
|
|
],
|
|
"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": 1.8593238878208e+16,
|
|
"train_batch_size": 16,
|
|
"trial_name": null,
|
|
"trial_params": null
|
|
}
|