6046 lines
164 KiB
JSON
6046 lines
164 KiB
JSON
{
|
|
"best_global_step": null,
|
|
"best_metric": null,
|
|
"best_model_checkpoint": null,
|
|
"epoch": 0.299895036737142,
|
|
"eval_steps": 3000,
|
|
"global_step": 3000,
|
|
"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
|
|
}
|
|
],
|
|
"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": 9369189218304000.0,
|
|
"train_batch_size": 16,
|
|
"trial_name": null,
|
|
"trial_params": null
|
|
}
|