fpadovani/tur-latn-100mb-100mb_seed3407
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity
Files
1884f642bf34031aa5b2aca4637f42af939ea1e9
tur-latn-100mb-100mb_seed3407/checkpoint-18000/trainer_state.json
ModelHub XC 1884f642bf 初始化项目，由ModelHub XC社区提供模型 
Model: fpadovani/tur-latn-100mb-100mb_seed3407
Source: Original Platform
2026-07-30 04:33:19 +08:00

36101 lines
992 KiB
JSON
Raw Blame History

{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 1.7993202379167292,
"eval_steps": 3000,
"global_step": 18000,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"entropy": 10.691937923431396,
"epoch": 0.00049982506122857,
"grad_norm": 12.5625,
"learning_rate": 2e-06,
"loss": 10.8222,
"mean_token_accuracy": 0.0,
"num_tokens": 9036.0,
"step": 5
},
{
"entropy": 10.691910362243652,
"epoch": 0.00099965012245714,
"grad_norm": 10.5625,
"learning_rate": 4.5e-06,
"loss": 10.7866,
"mean_token_accuracy": 8.539709378965198e-05,
"num_tokens": 19391.0,
"step": 10
},
{
"entropy": 10.691011714935303,
"epoch": 0.00149947518368571,
"grad_norm": 9.125,
"learning_rate": 7e-06,
"loss": 10.5826,
"mean_token_accuracy": 0.024504283629357814,
"num_tokens": 27896.0,
"step": 15
},
{
"entropy": 10.666096115112305,
"epoch": 0.00199930024491428,
"grad_norm": 6.03125,
"learning_rate": 9.5e-06,
"loss": 10.3675,
"mean_token_accuracy": 0.04187114499509335,
"num_tokens": 37280.0,
"step": 20
},
{
"entropy": 10.540959644317628,
"epoch": 0.00249912530614285,
"grad_norm": 4.125,
"learning_rate": 1.2e-05,
"loss": 10.1113,
"mean_token_accuracy": 0.042646989598870276,
"num_tokens": 46010.0,
"step": 25
},
{
"entropy": 10.54243049621582,
"epoch": 0.00299895036737142,
"grad_norm": 3.359375,
"learning_rate": 1.4500000000000002e-05,
"loss": 10.0177,
"mean_token_accuracy": 0.043468796834349635,
"num_tokens": 55972.0,
"step": 30
},
{
"entropy": 10.496186542510987,
"epoch": 0.00349877542859999,
"grad_norm": 2.640625,
"learning_rate": 1.7000000000000003e-05,
"loss": 9.9866,
"mean_token_accuracy": 0.0411271832883358,
"num_tokens": 66142.0,
"step": 35
},
{
"entropy": 10.507702732086182,
"epoch": 0.00399860048982856,
"grad_norm": 2.640625,
"learning_rate": 1.95e-05,
"loss": 9.8811,
"mean_token_accuracy": 0.04595596119761467,
"num_tokens": 74978.0,
"step": 40
},
{
"entropy": 10.479924392700195,
"epoch": 0.00449842555105713,
"grad_norm": 2.84375,
"learning_rate": 2.2e-05,
"loss": 9.832,
"mean_token_accuracy": 0.04226104132831097,
"num_tokens": 84153.0,
"step": 45
},
{
"entropy": 10.43626766204834,
"epoch": 0.0049982506122857,
"grad_norm": 2.3125,
"learning_rate": 2.4500000000000003e-05,
"loss": 9.8813,
"mean_token_accuracy": 0.044375188648700714,
"num_tokens": 94463.0,
"step": 50
},
{
"entropy": 10.442836666107178,
"epoch": 0.00549807567351427,
"grad_norm": 2.328125,
"learning_rate": 2.7e-05,
"loss": 9.803,
"mean_token_accuracy": 0.05454329513013363,
"num_tokens": 104182.0,
"step": 55
},
{
"entropy": 10.401250076293945,
"epoch": 0.00599790073474284,
"grad_norm": 2.390625,
"learning_rate": 2.95e-05,
"loss": 9.6939,
"mean_token_accuracy": 0.06315181367099285,
"num_tokens": 114058.0,
"step": 60
},
{
"entropy": 10.25614423751831,
"epoch": 0.00649772579597141,
"grad_norm": 1.7890625,
"learning_rate": 3.2e-05,
"loss": 9.71,
"mean_token_accuracy": 0.05851850733160972,
"num_tokens": 124154.0,
"step": 65
},
{
"entropy": 10.31090784072876,
"epoch": 0.00699755085719998,
"grad_norm": 2.171875,
"learning_rate": 3.4500000000000005e-05,
"loss": 9.558,
"mean_token_accuracy": 0.06353861205279827,
"num_tokens": 132840.0,
"step": 70
},
{
"entropy": 10.33273687362671,
"epoch": 0.00749737591842855,
"grad_norm": 1.78125,
"learning_rate": 3.7e-05,
"loss": 9.5868,
"mean_token_accuracy": 0.06003404222428799,
"num_tokens": 143070.0,
"step": 75
},
{
"entropy": 10.269068050384522,
"epoch": 0.00799720097965712,
"grad_norm": 1.5859375,
"learning_rate": 3.95e-05,
"loss": 9.5521,
"mean_token_accuracy": 0.058086647838354113,
"num_tokens": 153319.0,
"step": 80
},
{
"entropy": 10.333018684387207,
"epoch": 0.00849702604088569,
"grad_norm": 1.578125,
"learning_rate": 4.2000000000000004e-05,
"loss": 9.4889,
"mean_token_accuracy": 0.056201324239373206,
"num_tokens": 163152.0,
"step": 85
},
{
"entropy": 10.19660234451294,
"epoch": 0.00899685110211426,
"grad_norm": 1.5703125,
"learning_rate": 4.45e-05,
"loss": 9.3242,
"mean_token_accuracy": 0.061852597072720526,
"num_tokens": 173321.0,
"step": 90
},
{
"entropy": 10.18037166595459,
"epoch": 0.00949667616334283,
"grad_norm": 1.4453125,
"learning_rate": 4.7000000000000004e-05,
"loss": 9.2932,
"mean_token_accuracy": 0.06662209033966064,
"num_tokens": 182827.0,
"step": 95
},
{
"entropy": 10.177055072784423,
"epoch": 0.0099965012245714,
"grad_norm": 1.5703125,
"learning_rate": 4.9500000000000004e-05,
"loss": 9.2359,
"mean_token_accuracy": 0.058009016513824466,
"num_tokens": 191776.0,
"step": 100
},
{
"entropy": 10.060395526885987,
"epoch": 0.01049632628579997,
"grad_norm": 1.4453125,
"learning_rate": 5.2e-05,
"loss": 9.1694,
"mean_token_accuracy": 0.06354880146682262,
"num_tokens": 201891.0,
"step": 105
},
{
"entropy": 10.131175804138184,
"epoch": 0.01099615134702854,
"grad_norm": 1.6015625,
"learning_rate": 5.45e-05,
"loss": 9.0742,
"mean_token_accuracy": 0.06335793063044548,
"num_tokens": 210385.0,
"step": 110
},
{
"entropy": 9.997744750976562,
"epoch": 0.01149597640825711,
"grad_norm": 1.3984375,
"learning_rate": 5.7e-05,
"loss": 9.0025,
"mean_token_accuracy": 0.06502830199897289,
"num_tokens": 220098.0,
"step": 115
},
{
"entropy": 9.930113220214844,
"epoch": 0.01199580146948568,
"grad_norm": 1.3125,
"learning_rate": 5.9499999999999996e-05,
"loss": 8.9257,
"mean_token_accuracy": 0.06774141155183315,
"num_tokens": 230703.0,
"step": 120
},
{
"entropy": 9.789262199401856,
"epoch": 0.01249562653071425,
"grad_norm": 1.3828125,
"learning_rate": 6.2e-05,
"loss": 8.8116,
"mean_token_accuracy": 0.06662507690489292,
"num_tokens": 239545.0,
"step": 125
},
{
"entropy": 9.746065139770508,
"epoch": 0.01299545159194282,
"grad_norm": 1.3125,
"learning_rate": 6.450000000000001e-05,
"loss": 8.75,
"mean_token_accuracy": 0.06277895718812943,
"num_tokens": 249726.0,
"step": 130
},
{
"entropy": 9.624966144561768,
"epoch": 0.01349527665317139,
"grad_norm": 1.4765625,
"learning_rate": 6.7e-05,
"loss": 8.8151,
"mean_token_accuracy": 0.06419860571622849,
"num_tokens": 259491.0,
"step": 135
},
{
"entropy": 9.605054950714111,
"epoch": 0.01399510171439996,
"grad_norm": 1.25,
"learning_rate": 6.950000000000001e-05,
"loss": 8.7127,
"mean_token_accuracy": 0.06086057834327221,
"num_tokens": 268239.0,
"step": 140
},
{
"entropy": 9.465878677368163,
"epoch": 0.01449492677562853,
"grad_norm": 1.28125,
"learning_rate": 7.2e-05,
"loss": 8.6254,
"mean_token_accuracy": 0.0687973827123642,
"num_tokens": 276767.0,
"step": 145
},
{
"entropy": 9.377824974060058,
"epoch": 0.0149947518368571,
"grad_norm": 1.0859375,
"learning_rate": 7.45e-05,
"loss": 8.5576,
"mean_token_accuracy": 0.070676776394248,
"num_tokens": 286072.0,
"step": 150
},
{
"entropy": 9.257752609252929,
"epoch": 0.01549457689808567,
"grad_norm": 1.3828125,
"learning_rate": 7.7e-05,
"loss": 8.5675,
"mean_token_accuracy": 0.06347934491932392,
"num_tokens": 295178.0,
"step": 155
},
{
"entropy": 9.222655963897704,
"epoch": 0.01599440195931424,
"grad_norm": 1.0703125,
"learning_rate": 7.950000000000001e-05,
"loss": 8.6111,
"mean_token_accuracy": 0.06264784783124924,
"num_tokens": 305537.0,
"step": 160
},
{
"entropy": 9.114503574371337,
"epoch": 0.01649422702054281,
"grad_norm": 1.296875,
"learning_rate": 8.2e-05,
"loss": 8.4682,
"mean_token_accuracy": 0.07314668670296669,
"num_tokens": 315316.0,
"step": 165
},
{
"entropy": 9.004597473144532,
"epoch": 0.01699405208177138,
"grad_norm": 1.2734375,
"learning_rate": 8.450000000000001e-05,
"loss": 8.491,
"mean_token_accuracy": 0.07030753418803215,
"num_tokens": 325089.0,
"step": 170
},
{
"entropy": 8.996741676330567,
"epoch": 0.01749387714299995,
"grad_norm": 1.578125,
"learning_rate": 8.7e-05,
"loss": 8.4612,
"mean_token_accuracy": 0.06281476058065891,
"num_tokens": 334009.0,
"step": 175
},
{
"entropy": 8.929500389099122,
"epoch": 0.01799370220422852,
"grad_norm": 1.28125,
"learning_rate": 8.95e-05,
"loss": 8.397,
"mean_token_accuracy": 0.06993251703679562,
"num_tokens": 342535.0,
"step": 180
},
{
"entropy": 8.847047901153564,
"epoch": 0.01849352726545709,
"grad_norm": 1.3515625,
"learning_rate": 9.2e-05,
"loss": 8.4064,
"mean_token_accuracy": 0.06550291888415813,
"num_tokens": 352324.0,
"step": 185
},
{
"entropy": 8.74924440383911,
"epoch": 0.01899335232668566,
"grad_norm": 1.609375,
"learning_rate": 9.45e-05,
"loss": 8.4174,
"mean_token_accuracy": 0.0638185866177082,
"num_tokens": 362824.0,
"step": 190
},
{
"entropy": 8.884198856353759,
"epoch": 0.01949317738791423,
"grad_norm": 1.109375,
"learning_rate": 9.7e-05,
"loss": 8.3963,
"mean_token_accuracy": 0.06174343600869179,
"num_tokens": 373056.0,
"step": 195
},
{
"entropy": 8.75450849533081,
"epoch": 0.0199930024491428,
"grad_norm": 1.0390625,
"learning_rate": 9.95e-05,
"loss": 8.3509,
"mean_token_accuracy": 0.07249316610395909,
"num_tokens": 382448.0,
"step": 200
},
{
"entropy": 8.695133495330811,
"epoch": 0.02049282751037137,
"grad_norm": 1.4296875,
"learning_rate": 0.000102,
"loss": 8.4227,
"mean_token_accuracy": 0.06916416324675083,
"num_tokens": 393640.0,
"step": 205
},
{
"entropy": 8.69532642364502,
"epoch": 0.02099265257159994,
"grad_norm": 1.171875,
"learning_rate": 0.00010449999999999999,
"loss": 8.4168,
"mean_token_accuracy": 0.07142675034701824,
"num_tokens": 403129.0,
"step": 210
},
{
"entropy": 8.696801376342773,
"epoch": 0.02149247763282851,
"grad_norm": 1.1640625,
"learning_rate": 0.000107,
"loss": 8.3599,
"mean_token_accuracy": 0.07293656915426254,
"num_tokens": 412673.0,
"step": 215
},
{
"entropy": 8.734815216064453,
"epoch": 0.02199230269405708,
"grad_norm": 1.0,
"learning_rate": 0.0001095,
"loss": 8.3822,
"mean_token_accuracy": 0.07273878008127213,
"num_tokens": 422960.0,
"step": 220
},
{
"entropy": 8.641194057464599,
"epoch": 0.02249212775528565,
"grad_norm": 1.109375,
"learning_rate": 0.000112,
"loss": 8.3671,
"mean_token_accuracy": 0.0694367703050375,
"num_tokens": 433248.0,
"step": 225
},
{
"entropy": 8.656941223144532,
"epoch": 0.02299195281651422,
"grad_norm": 1.3359375,
"learning_rate": 0.0001145,
"loss": 8.2924,
"mean_token_accuracy": 0.07617328315973282,
"num_tokens": 441738.0,
"step": 230
},
{
"entropy": 8.517578506469727,
"epoch": 0.02349177787774279,
"grad_norm": 1.046875,
"learning_rate": 0.00011700000000000001,
"loss": 8.3911,
"mean_token_accuracy": 0.07571800649166108,
"num_tokens": 451894.0,
"step": 235
},
{
"entropy": 8.691481590270996,
"epoch": 0.02399160293897136,
"grad_norm": 1.1171875,
"learning_rate": 0.00011949999999999999,
"loss": 8.3454,
"mean_token_accuracy": 0.078226138651371,
"num_tokens": 462829.0,
"step": 240
},
{
"entropy": 8.61854429244995,
"epoch": 0.02449142800019993,
"grad_norm": 1.2109375,
"learning_rate": 0.000122,
"loss": 8.3429,
"mean_token_accuracy": 0.07184191048145294,
"num_tokens": 472034.0,
"step": 245
},
{
"entropy": 8.58093318939209,
"epoch": 0.0249912530614285,
"grad_norm": 1.03125,
"learning_rate": 0.0001245,
"loss": 8.3983,
"mean_token_accuracy": 0.06812773868441582,
"num_tokens": 481963.0,
"step": 250
},
{
"entropy": 8.630074882507325,
"epoch": 0.02549107812265707,
"grad_norm": 1.0234375,
"learning_rate": 0.000127,
"loss": 8.2833,
"mean_token_accuracy": 0.07643958404660225,
"num_tokens": 491562.0,
"step": 255
},
{
"entropy": 8.551316165924073,
"epoch": 0.02599090318388564,
"grad_norm": 1.7890625,
"learning_rate": 0.0001295,
"loss": 8.226,
"mean_token_accuracy": 0.08187740184366703,
"num_tokens": 500884.0,
"step": 260
},
{
"entropy": 8.544846057891846,
"epoch": 0.026490728245114212,
"grad_norm": 1.203125,
"learning_rate": 0.000132,
"loss": 8.2814,
"mean_token_accuracy": 0.07459888011217117,
"num_tokens": 510287.0,
"step": 265
},
{
"entropy": 8.609485721588134,
"epoch": 0.02699055330634278,
"grad_norm": 1.3984375,
"learning_rate": 0.00013450000000000002,
"loss": 8.2357,
"mean_token_accuracy": 0.0795067872852087,
"num_tokens": 519633.0,
"step": 270
},
{
"entropy": 8.487185859680176,
"epoch": 0.02749037836757135,
"grad_norm": 1.140625,
"learning_rate": 0.00013700000000000002,
"loss": 8.3194,
"mean_token_accuracy": 0.07536891847848892,
"num_tokens": 528999.0,
"step": 275
},
{
"entropy": 8.59107551574707,
"epoch": 0.02799020342879992,
"grad_norm": 1.1171875,
"learning_rate": 0.0001395,
"loss": 8.2843,
"mean_token_accuracy": 0.07671510241925716,
"num_tokens": 538403.0,
"step": 280
},
{
"entropy": 8.52663278579712,
"epoch": 0.02849002849002849,
"grad_norm": 1.296875,
"learning_rate": 0.00014199999999999998,
"loss": 8.2385,
"mean_token_accuracy": 0.07777136862277985,
"num_tokens": 547716.0,
"step": 285
},
{
"entropy": 8.441480922698975,
"epoch": 0.02898985355125706,
"grad_norm": 1.0234375,
"learning_rate": 0.0001445,
"loss": 8.2467,
"mean_token_accuracy": 0.07836432494223118,
"num_tokens": 557714.0,
"step": 290
},
{
"entropy": 8.63280029296875,
"epoch": 0.02948967861248563,
"grad_norm": 1.3125,
"learning_rate": 0.000147,
"loss": 8.2838,
"mean_token_accuracy": 0.07826550751924514,
"num_tokens": 568591.0,
"step": 295
},
{
"entropy": 8.439323425292969,
"epoch": 0.0299895036737142,
"grad_norm": 1.125,
"learning_rate": 0.0001495,
"loss": 8.1958,
"mean_token_accuracy": 0.08220398984849453,
"num_tokens": 578435.0,
"step": 300
},
{
"entropy": 8.447675704956055,
"epoch": 0.03048932873494277,
"grad_norm": 1.1015625,
"learning_rate": 0.000152,
"loss": 8.2599,
"mean_token_accuracy": 0.07586241215467453,
"num_tokens": 587461.0,
"step": 305
},
{
"entropy": 8.497601222991943,
"epoch": 0.03098915379617134,
"grad_norm": 1.1640625,
"learning_rate": 0.00015450000000000001,
"loss": 8.2869,
"mean_token_accuracy": 0.073284100741148,
"num_tokens": 597004.0,
"step": 310
},
{
"entropy": 8.525490951538085,
"epoch": 0.03148897885739991,
"grad_norm": 1.03125,
"learning_rate": 0.000157,
"loss": 8.2464,
"mean_token_accuracy": 0.07317042723298073,
"num_tokens": 607831.0,
"step": 315
},
{
"entropy": 8.550362873077393,
"epoch": 0.03198880391862848,
"grad_norm": 1.34375,
"learning_rate": 0.0001595,
"loss": 8.227,
"mean_token_accuracy": 0.08139617070555687,
"num_tokens": 618008.0,
"step": 320
},
{
"entropy": 8.355420207977295,
"epoch": 0.03248862897985705,
"grad_norm": 1.078125,
"learning_rate": 0.000162,
"loss": 8.1332,
"mean_token_accuracy": 0.08453277647495269,
"num_tokens": 627970.0,
"step": 325
},
{
"entropy": 8.438968658447266,
"epoch": 0.03298845404108562,
"grad_norm": 1.0390625,
"learning_rate": 0.00016450000000000001,
"loss": 8.2245,
"mean_token_accuracy": 0.07926518805325031,
"num_tokens": 638059.0,
"step": 330
},
{
"entropy": 8.503382587432862,
"epoch": 0.03348827910231419,
"grad_norm": 1.171875,
"learning_rate": 0.00016700000000000002,
"loss": 8.2997,
"mean_token_accuracy": 0.07444430701434612,
"num_tokens": 648169.0,
"step": 335
},
{
"entropy": 8.4659499168396,
"epoch": 0.03398810416354276,
"grad_norm": 0.921875,
"learning_rate": 0.00016950000000000003,
"loss": 8.2816,
"mean_token_accuracy": 0.07408055253326892,
"num_tokens": 659351.0,
"step": 340
},
{
"entropy": 8.479489421844482,
"epoch": 0.03448792922477133,
"grad_norm": 1.0859375,
"learning_rate": 0.00017199999999999998,
"loss": 8.1133,
"mean_token_accuracy": 0.081477539986372,
"num_tokens": 669602.0,
"step": 345
},
{
"entropy": 8.449872016906738,
"epoch": 0.0349877542859999,
"grad_norm": 1.2109375,
"learning_rate": 0.00017449999999999999,
"loss": 8.208,
"mean_token_accuracy": 0.07832706868648528,
"num_tokens": 679497.0,
"step": 350
},
{
"entropy": 8.401834392547608,
"epoch": 0.03548757934722847,
"grad_norm": 0.97265625,
"learning_rate": 0.000177,
"loss": 8.1508,
"mean_token_accuracy": 0.08282142281532287,
"num_tokens": 689020.0,
"step": 355
},
{
"entropy": 8.419000816345214,
"epoch": 0.03598740440845704,
"grad_norm": 1.25,
"learning_rate": 0.0001795,
"loss": 8.1319,
"mean_token_accuracy": 0.08381059765815735,
"num_tokens": 697505.0,
"step": 360
},
{
"entropy": 8.416812896728516,
"epoch": 0.03648722946968561,
"grad_norm": 1.140625,
"learning_rate": 0.000182,
"loss": 8.1197,
"mean_token_accuracy": 0.07555183880031109,
"num_tokens": 707646.0,
"step": 365
},
{
"entropy": 8.340746212005616,
"epoch": 0.03698705453091418,
"grad_norm": 0.91015625,
"learning_rate": 0.0001845,
"loss": 8.0655,
"mean_token_accuracy": 0.0808980330824852,
"num_tokens": 717345.0,
"step": 370
},
{
"entropy": 8.354646587371827,
"epoch": 0.03748687959214275,
"grad_norm": 1.015625,
"learning_rate": 0.000187,
"loss": 8.1434,
"mean_token_accuracy": 0.08112207651138306,
"num_tokens": 727785.0,
"step": 375
},
{
"entropy": 8.41817512512207,
"epoch": 0.03798670465337132,
"grad_norm": 1.1328125,
"learning_rate": 0.0001895,
"loss": 8.1431,
"mean_token_accuracy": 0.08172658756375313,
"num_tokens": 737740.0,
"step": 380
},
{
"entropy": 8.356461238861083,
"epoch": 0.03848652971459989,
"grad_norm": 1.15625,
"learning_rate": 0.000192,
"loss": 8.1072,
"mean_token_accuracy": 0.07860676273703575,
"num_tokens": 747026.0,
"step": 385
},
{
"entropy": 8.281126689910888,
"epoch": 0.03898635477582846,
"grad_norm": 1.1953125,
"learning_rate": 0.0001945,
"loss": 8.0719,
"mean_token_accuracy": 0.08162726536393165,
"num_tokens": 756798.0,
"step": 390
},
{
"entropy": 8.545885276794433,
"epoch": 0.03948617983705703,
"grad_norm": 1.2890625,
"learning_rate": 0.00019700000000000002,
"loss": 8.1337,
"mean_token_accuracy": 0.07723894119262695,
"num_tokens": 765730.0,
"step": 395
},
{
"entropy": 8.221963024139404,
"epoch": 0.0399860048982856,
"grad_norm": 1.1953125,
"learning_rate": 0.00019950000000000002,
"loss": 8.1068,
"mean_token_accuracy": 0.08807171508669853,
"num_tokens": 776330.0,
"step": 400
},
{
"entropy": 8.33034019470215,
"epoch": 0.04048582995951417,
"grad_norm": 1.078125,
"learning_rate": 0.000202,
"loss": 8.1773,
"mean_token_accuracy": 0.0784314177930355,
"num_tokens": 785840.0,
"step": 405
},
{
"entropy": 8.340146541595459,
"epoch": 0.04098565502074274,
"grad_norm": 1.0546875,
"learning_rate": 0.00020449999999999998,
"loss": 8.0226,
"mean_token_accuracy": 0.08303822055459023,
"num_tokens": 795126.0,
"step": 410
},
{
"entropy": 8.34009313583374,
"epoch": 0.04148548008197131,
"grad_norm": 1.046875,
"learning_rate": 0.000207,
"loss": 8.1702,
"mean_token_accuracy": 0.07932347059249878,
"num_tokens": 805766.0,
"step": 415
},
{
"entropy": 8.330490493774414,
"epoch": 0.04198530514319988,
"grad_norm": 1.7734375,
"learning_rate": 0.0002095,
"loss": 8.1115,
"mean_token_accuracy": 0.08066079020500183,
"num_tokens": 815202.0,
"step": 420
},
{
"entropy": 8.372891998291015,
"epoch": 0.04248513020442845,
"grad_norm": 1.234375,
"learning_rate": 0.000212,
"loss": 8.0709,
"mean_token_accuracy": 0.08375605717301368,
"num_tokens": 825065.0,
"step": 425
},
{
"entropy": 8.171288871765137,
"epoch": 0.04298495526565702,
"grad_norm": 1.203125,
"learning_rate": 0.0002145,
"loss": 8.0681,
"mean_token_accuracy": 0.0807822324335575,
"num_tokens": 834088.0,
"step": 430
},
{
"entropy": 8.329067707061768,
"epoch": 0.04348478032688559,
"grad_norm": 1.0078125,
"learning_rate": 0.00021700000000000002,
"loss": 8.104,
"mean_token_accuracy": 0.08128277212381363,
"num_tokens": 843653.0,
"step": 435
},
{
"entropy": 8.247820854187012,
"epoch": 0.04398460538811416,
"grad_norm": 1.1640625,
"learning_rate": 0.0002195,
"loss": 7.9929,
"mean_token_accuracy": 0.08918308317661286,
"num_tokens": 853248.0,
"step": 440
},
{
"entropy": 8.318993091583252,
"epoch": 0.04448443044934273,
"grad_norm": 1.1875,
"learning_rate": 0.000222,
"loss": 8.1379,
"mean_token_accuracy": 0.08139327839016915,
"num_tokens": 863814.0,
"step": 445
},
{
"entropy": 8.30269651412964,
"epoch": 0.0449842555105713,
"grad_norm": 1.0078125,
"learning_rate": 0.0002245,
"loss": 8.0395,
"mean_token_accuracy": 0.08268025442957878,
"num_tokens": 874030.0,
"step": 450
},
{
"entropy": 8.289182376861572,
"epoch": 0.04548408057179987,
"grad_norm": 1.0703125,
"learning_rate": 0.00022700000000000002,
"loss": 8.0309,
"mean_token_accuracy": 0.09102015197277069,
"num_tokens": 883006.0,
"step": 455
},
{
"entropy": 8.175302314758301,
"epoch": 0.04598390563302844,
"grad_norm": 0.9921875,
"learning_rate": 0.00022950000000000002,
"loss": 7.9755,
"mean_token_accuracy": 0.0876532681286335,
"num_tokens": 892953.0,
"step": 460
},
{
"entropy": 8.333348941802978,
"epoch": 0.04648373069425701,
"grad_norm": 1.0703125,
"learning_rate": 0.00023200000000000003,
"loss": 8.1284,
"mean_token_accuracy": 0.08013307489454746,
"num_tokens": 904228.0,
"step": 465
},
{
"entropy": 8.185042667388917,
"epoch": 0.04698355575548558,
"grad_norm": 1.0390625,
"learning_rate": 0.00023449999999999998,
"loss": 8.0155,
"mean_token_accuracy": 0.0849261574447155,
"num_tokens": 915161.0,
"step": 470
},
{
"entropy": 8.251577377319336,
"epoch": 0.04748338081671415,
"grad_norm": 1.2109375,
"learning_rate": 0.000237,
"loss": 8.1226,
"mean_token_accuracy": 0.07527048066258431,
"num_tokens": 925167.0,
"step": 475
},
{
"entropy": 8.203055572509765,
"epoch": 0.04798320587794272,
"grad_norm": 1.0,
"learning_rate": 0.0002395,
"loss": 8.0031,
"mean_token_accuracy": 0.08475866988301277,
"num_tokens": 934742.0,
"step": 480
},
{
"entropy": 8.263946628570556,
"epoch": 0.04848303093917129,
"grad_norm": 1.09375,
"learning_rate": 0.000242,
"loss": 8.0565,
"mean_token_accuracy": 0.08061288818717002,
"num_tokens": 944549.0,
"step": 485
},
{
"entropy": 8.130996036529542,
"epoch": 0.04898285600039986,
"grad_norm": 1.0703125,
"learning_rate": 0.0002445,
"loss": 7.9566,
"mean_token_accuracy": 0.09062113910913468,
"num_tokens": 954668.0,
"step": 490
},
{
"entropy": 8.40848512649536,
"epoch": 0.04948268106162843,
"grad_norm": 1.0546875,
"learning_rate": 0.000247,
"loss": 8.0619,
"mean_token_accuracy": 0.07748850770294666,
"num_tokens": 964953.0,
"step": 495
},
{
"entropy": 8.065672302246094,
"epoch": 0.049982506122857,
"grad_norm": 1.0078125,
"learning_rate": 0.0002495,
"loss": 7.9449,
"mean_token_accuracy": 0.09317015185952186,
"num_tokens": 974820.0,
"step": 500
},
{
"entropy": 8.159075212478637,
"epoch": 0.05048233118408557,
"grad_norm": 1.1796875,
"learning_rate": 0.000252,
"loss": 7.9396,
"mean_token_accuracy": 0.0863773450255394,
"num_tokens": 984888.0,
"step": 505
},
{
"entropy": 8.047884082794189,
"epoch": 0.05098215624531414,
"grad_norm": 1.2109375,
"learning_rate": 0.0002545,
"loss": 7.9632,
"mean_token_accuracy": 0.08658726513385773,
"num_tokens": 993731.0,
"step": 510
},
{
"entropy": 8.219942665100097,
"epoch": 0.05148198130654271,
"grad_norm": 1.109375,
"learning_rate": 0.000257,
"loss": 7.9006,
"mean_token_accuracy": 0.08839990794658661,
"num_tokens": 1003138.0,
"step": 515
},
{
"entropy": 8.084060764312744,
"epoch": 0.05198180636777128,
"grad_norm": 1.1171875,
"learning_rate": 0.0002595,
"loss": 7.899,
"mean_token_accuracy": 0.08839784786105156,
"num_tokens": 1012058.0,
"step": 520
},
{
"entropy": 8.172471237182616,
"epoch": 0.05248163142899985,
"grad_norm": 1.2578125,
"learning_rate": 0.000262,
"loss": 7.9093,
"mean_token_accuracy": 0.09066133350133895,
"num_tokens": 1020804.0,
"step": 525
},
{
"entropy": 8.197671794891358,
"epoch": 0.052981456490228424,
"grad_norm": 1.046875,
"learning_rate": 0.00026450000000000003,
"loss": 7.9273,
"mean_token_accuracy": 0.08465270027518272,
"num_tokens": 1030432.0,
"step": 530
},
{
"entropy": 8.110610485076904,
"epoch": 0.05348128155145699,
"grad_norm": 1.0,
"learning_rate": 0.00026700000000000004,
"loss": 7.8986,
"mean_token_accuracy": 0.09049126878380775,
"num_tokens": 1039336.0,
"step": 535
},
{
"entropy": 8.07482190132141,
"epoch": 0.05398110661268556,
"grad_norm": 1.171875,
"learning_rate": 0.00026950000000000005,
"loss": 7.8544,
"mean_token_accuracy": 0.09336550831794739,
"num_tokens": 1049314.0,
"step": 540
},
{
"entropy": 8.168315505981445,
"epoch": 0.05448093167391413,
"grad_norm": 1.1484375,
"learning_rate": 0.00027200000000000005,
"loss": 7.9191,
"mean_token_accuracy": 0.0833043985068798,
"num_tokens": 1059248.0,
"step": 545
},
{
"entropy": 7.971222257614135,
"epoch": 0.0549807567351427,
"grad_norm": 1.0234375,
"learning_rate": 0.0002745,
"loss": 7.8734,
"mean_token_accuracy": 0.09001793414354324,
"num_tokens": 1069307.0,
"step": 550
},
{
"entropy": 8.128306674957276,
"epoch": 0.05548058179637127,
"grad_norm": 1.0625,
"learning_rate": 0.000277,
"loss": 7.8885,
"mean_token_accuracy": 0.10013765767216683,
"num_tokens": 1079603.0,
"step": 555
},
{
"entropy": 8.082885026931763,
"epoch": 0.05598040685759984,
"grad_norm": 1.0859375,
"learning_rate": 0.0002795,
"loss": 7.8572,
"mean_token_accuracy": 0.08783879578113556,
"num_tokens": 1089386.0,
"step": 560
},
{
"entropy": 8.03367247581482,
"epoch": 0.05648023191882841,
"grad_norm": 1.1640625,
"learning_rate": 0.00028199999999999997,
"loss": 7.9334,
"mean_token_accuracy": 0.09579939767718315,
"num_tokens": 1099501.0,
"step": 565
},
{
"entropy": 8.026818656921387,
"epoch": 0.05698005698005698,
"grad_norm": 1.21875,
"learning_rate": 0.0002845,
"loss": 7.8401,
"mean_token_accuracy": 0.08943256586790085,
"num_tokens": 1108942.0,
"step": 570
},
{
"entropy": 8.156963968276978,
"epoch": 0.05747988204128555,
"grad_norm": 1.0390625,
"learning_rate": 0.000287,
"loss": 7.9447,
"mean_token_accuracy": 0.08371670618653297,
"num_tokens": 1119484.0,
"step": 575
},
{
"entropy": 8.109134340286255,
"epoch": 0.05797970710251412,
"grad_norm": 1.0546875,
"learning_rate": 0.0002895,
"loss": 7.9051,
"mean_token_accuracy": 0.08559826985001565,
"num_tokens": 1130426.0,
"step": 580
},
{
"entropy": 8.004295110702515,
"epoch": 0.05847953216374269,
"grad_norm": 1.0625,
"learning_rate": 0.000292,
"loss": 7.8708,
"mean_token_accuracy": 0.08802263662219048,
"num_tokens": 1140917.0,
"step": 585
},
{
"entropy": 8.056009531021118,
"epoch": 0.05897935722497126,
"grad_norm": 1.21875,
"learning_rate": 0.0002945,
"loss": 7.8112,
"mean_token_accuracy": 0.09180943965911866,
"num_tokens": 1149863.0,
"step": 590
},
{
"entropy": 8.01901979446411,
"epoch": 0.05947918228619983,
"grad_norm": 1.015625,
"learning_rate": 0.000297,
"loss": 7.8604,
"mean_token_accuracy": 0.08644097074866294,
"num_tokens": 1158915.0,
"step": 595
},
{
"entropy": 7.974025106430053,
"epoch": 0.0599790073474284,
"grad_norm": 1.109375,
"learning_rate": 0.0002995,
"loss": 7.849,
"mean_token_accuracy": 0.08794929981231689,
"num_tokens": 1167886.0,
"step": 600
},
{
"entropy": 8.07925305366516,
"epoch": 0.06047883240865697,
"grad_norm": 0.9765625,
"learning_rate": 0.000302,
"loss": 7.8807,
"mean_token_accuracy": 0.09158162623643876,
"num_tokens": 1177878.0,
"step": 605
},
{
"entropy": 8.07640643119812,
"epoch": 0.06097865746988554,
"grad_norm": 1.1171875,
"learning_rate": 0.0003045,
"loss": 7.8965,
"mean_token_accuracy": 0.08518724367022515,
"num_tokens": 1189511.0,
"step": 610
},
{
"entropy": 8.041076612472533,
"epoch": 0.06147848253111411,
"grad_norm": 1.09375,
"learning_rate": 0.000307,
"loss": 7.8981,
"mean_token_accuracy": 0.08804430365562439,
"num_tokens": 1199350.0,
"step": 615
},
{
"entropy": 7.980624389648438,
"epoch": 0.06197830759234268,
"grad_norm": 1.2734375,
"learning_rate": 0.0003095,
"loss": 7.8271,
"mean_token_accuracy": 0.09052536413073539,
"num_tokens": 1209036.0,
"step": 620
},
{
"entropy": 7.91511549949646,
"epoch": 0.06247813265357125,
"grad_norm": 1.1015625,
"learning_rate": 0.000312,
"loss": 7.8584,
"mean_token_accuracy": 0.08907051086425781,
"num_tokens": 1218841.0,
"step": 625
},
{
"entropy": 8.153012752532959,
"epoch": 0.06297795771479982,
"grad_norm": 1.1171875,
"learning_rate": 0.0003145,
"loss": 7.857,
"mean_token_accuracy": 0.08877145648002624,
"num_tokens": 1229700.0,
"step": 630
},
{
"entropy": 8.000677156448365,
"epoch": 0.06347778277602839,
"grad_norm": 1.09375,
"learning_rate": 0.000317,
"loss": 7.8437,
"mean_token_accuracy": 0.08636783435940742,
"num_tokens": 1239604.0,
"step": 635
},
{
"entropy": 7.819658041000366,
"epoch": 0.06397760783725696,
"grad_norm": 1.2109375,
"learning_rate": 0.0003195,
"loss": 7.7281,
"mean_token_accuracy": 0.09608968570828438,
"num_tokens": 1249305.0,
"step": 640
},
{
"entropy": 8.016890144348144,
"epoch": 0.06447743289848552,
"grad_norm": 1.109375,
"learning_rate": 0.000322,
"loss": 7.8545,
"mean_token_accuracy": 0.09123507961630821,
"num_tokens": 1261289.0,
"step": 645
},
{
"entropy": 7.908722877502441,
"epoch": 0.0649772579597141,
"grad_norm": 1.125,
"learning_rate": 0.00032450000000000003,
"loss": 7.8074,
"mean_token_accuracy": 0.09392313659191132,
"num_tokens": 1271062.0,
"step": 650
},
{
"entropy": 7.9713281154632565,
"epoch": 0.06547708302094267,
"grad_norm": 0.984375,
"learning_rate": 0.00032700000000000003,
"loss": 7.8102,
"mean_token_accuracy": 0.08593089655041694,
"num_tokens": 1280259.0,
"step": 655
},
{
"entropy": 8.054199171066283,
"epoch": 0.06597690808217124,
"grad_norm": 1.1640625,
"learning_rate": 0.00032950000000000004,
"loss": 7.7935,
"mean_token_accuracy": 0.0905226230621338,
"num_tokens": 1289184.0,
"step": 660
},
{
"entropy": 7.912717294692993,
"epoch": 0.06647673314339982,
"grad_norm": 1.3359375,
"learning_rate": 0.00033200000000000005,
"loss": 7.7627,
"mean_token_accuracy": 0.09990859180688857,
"num_tokens": 1297916.0,
"step": 665
},
{
"entropy": 7.934937286376953,
"epoch": 0.06697655820462838,
"grad_norm": 1.171875,
"learning_rate": 0.00033450000000000005,
"loss": 7.8034,
"mean_token_accuracy": 0.09347057268023491,
"num_tokens": 1307786.0,
"step": 670
},
{
"entropy": 7.948394060134888,
"epoch": 0.06747638326585695,
"grad_norm": 1.109375,
"learning_rate": 0.000337,
"loss": 7.7035,
"mean_token_accuracy": 0.08821736723184585,
"num_tokens": 1317528.0,
"step": 675
},
{
"entropy": 7.898578214645386,
"epoch": 0.06797620832708552,
"grad_norm": 1.3203125,
"learning_rate": 0.0003395,
"loss": 7.7457,
"mean_token_accuracy": 0.09229791611433029,
"num_tokens": 1326170.0,
"step": 680
},
{
"entropy": 7.833027362823486,
"epoch": 0.0684760333883141,
"grad_norm": 1.1171875,
"learning_rate": 0.000342,
"loss": 7.7515,
"mean_token_accuracy": 0.09093709476292133,
"num_tokens": 1336469.0,
"step": 685
},
{
"entropy": 7.857772493362427,
"epoch": 0.06897585844954265,
"grad_norm": 1.015625,
"learning_rate": 0.00034449999999999997,
"loss": 7.7384,
"mean_token_accuracy": 0.0885499432682991,
"num_tokens": 1347449.0,
"step": 690
},
{
"entropy": 7.819149017333984,
"epoch": 0.06947568351077123,
"grad_norm": 1.078125,
"learning_rate": 0.000347,
"loss": 7.7794,
"mean_token_accuracy": 0.0962777391076088,
"num_tokens": 1357849.0,
"step": 695
},
{
"entropy": 7.873389196395874,
"epoch": 0.0699755085719998,
"grad_norm": 1.1484375,
"learning_rate": 0.0003495,
"loss": 7.7115,
"mean_token_accuracy": 0.08954642415046692,
"num_tokens": 1366784.0,
"step": 700
},
{
"entropy": 7.9029346942901615,
"epoch": 0.07047533363322837,
"grad_norm": 1.1171875,
"learning_rate": 0.000352,
"loss": 7.6777,
"mean_token_accuracy": 0.09408788681030274,
"num_tokens": 1376059.0,
"step": 705
},
{
"entropy": 7.817119073867798,
"epoch": 0.07097515869445695,
"grad_norm": 1.1328125,
"learning_rate": 0.0003545,
"loss": 7.6405,
"mean_token_accuracy": 0.09813722297549247,
"num_tokens": 1385505.0,
"step": 710
},
{
"entropy": 7.849679708480835,
"epoch": 0.0714749837556855,
"grad_norm": 1.1015625,
"learning_rate": 0.000357,
"loss": 7.6998,
"mean_token_accuracy": 0.10136872977018356,
"num_tokens": 1395200.0,
"step": 715
},
{
"entropy": 7.746676015853882,
"epoch": 0.07197480881691408,
"grad_norm": 1.3046875,
"learning_rate": 0.0003595,
"loss": 7.6351,
"mean_token_accuracy": 0.09838511943817138,
"num_tokens": 1404599.0,
"step": 720
},
{
"entropy": 7.806417465209961,
"epoch": 0.07247463387814265,
"grad_norm": 1.0078125,
"learning_rate": 0.000362,
"loss": 7.7018,
"mean_token_accuracy": 0.09462484046816826,
"num_tokens": 1414761.0,
"step": 725
},
{
"entropy": 7.835126304626465,
"epoch": 0.07297445893937123,
"grad_norm": 1.078125,
"learning_rate": 0.0003645,
"loss": 7.6427,
"mean_token_accuracy": 0.09922129213809967,
"num_tokens": 1424296.0,
"step": 730
},
{
"entropy": 7.799503755569458,
"epoch": 0.07347428400059978,
"grad_norm": 1.0,
"learning_rate": 0.000367,
"loss": 7.7093,
"mean_token_accuracy": 0.09564783871173858,
"num_tokens": 1433729.0,
"step": 735
},
{
"entropy": 7.859089279174805,
"epoch": 0.07397410906182836,
"grad_norm": 1.0703125,
"learning_rate": 0.0003695,
"loss": 7.7688,
"mean_token_accuracy": 0.08819435015320778,
"num_tokens": 1444214.0,
"step": 740
},
{
"entropy": 7.835516119003296,
"epoch": 0.07447393412305693,
"grad_norm": 0.91015625,
"learning_rate": 0.000372,
"loss": 7.7759,
"mean_token_accuracy": 0.0897902250289917,
"num_tokens": 1454364.0,
"step": 745
},
{
"entropy": 7.81394476890564,
"epoch": 0.0749737591842855,
"grad_norm": 1.0546875,
"learning_rate": 0.0003745,
"loss": 7.6208,
"mean_token_accuracy": 0.09887422099709511,
"num_tokens": 1465018.0,
"step": 750
},
{
"entropy": 7.76133918762207,
"epoch": 0.07547358424551406,
"grad_norm": 1.125,
"learning_rate": 0.000377,
"loss": 7.6162,
"mean_token_accuracy": 0.09769436419010162,
"num_tokens": 1474316.0,
"step": 755
},
{
"entropy": 7.754013442993164,
"epoch": 0.07597340930674264,
"grad_norm": 1.1484375,
"learning_rate": 0.0003795,
"loss": 7.6798,
"mean_token_accuracy": 0.09028005488216877,
"num_tokens": 1483867.0,
"step": 760
},
{
"entropy": 7.8395530700683596,
"epoch": 0.07647323436797121,
"grad_norm": 1.1171875,
"learning_rate": 0.000382,
"loss": 7.7473,
"mean_token_accuracy": 0.09097101353108883,
"num_tokens": 1493760.0,
"step": 765
},
{
"entropy": 7.770206785202026,
"epoch": 0.07697305942919978,
"grad_norm": 1.2421875,
"learning_rate": 0.0003845,
"loss": 7.6632,
"mean_token_accuracy": 0.09491882026195526,
"num_tokens": 1503984.0,
"step": 770
},
{
"entropy": 7.806950092315674,
"epoch": 0.07747288449042836,
"grad_norm": 1.078125,
"learning_rate": 0.00038700000000000003,
"loss": 7.7156,
"mean_token_accuracy": 0.09478980228304863,
"num_tokens": 1513550.0,
"step": 775
},
{
"entropy": 7.798428964614868,
"epoch": 0.07797270955165692,
"grad_norm": 1.0234375,
"learning_rate": 0.00038950000000000003,
"loss": 7.6753,
"mean_token_accuracy": 0.09549887105822563,
"num_tokens": 1523543.0,
"step": 780
},
{
"entropy": 7.81029634475708,
"epoch": 0.07847253461288549,
"grad_norm": 1.140625,
"learning_rate": 0.00039200000000000004,
"loss": 7.6472,
"mean_token_accuracy": 0.08958346769213676,
"num_tokens": 1533775.0,
"step": 785
},
{
"entropy": 7.677821111679077,
"epoch": 0.07897235967411406,
"grad_norm": 1.1328125,
"learning_rate": 0.00039450000000000005,
"loss": 7.645,
"mean_token_accuracy": 0.09512166753411293,
"num_tokens": 1545008.0,
"step": 790
},
{
"entropy": 7.821054697036743,
"epoch": 0.07947218473534264,
"grad_norm": 1.03125,
"learning_rate": 0.00039700000000000005,
"loss": 7.6518,
"mean_token_accuracy": 0.09396766498684883,
"num_tokens": 1554458.0,
"step": 795
},
{
"entropy": 7.712546682357788,
"epoch": 0.0799720097965712,
"grad_norm": 1.046875,
"learning_rate": 0.0003995,
"loss": 7.6531,
"mean_token_accuracy": 0.09004195109009742,
"num_tokens": 1565827.0,
"step": 800
},
{
"entropy": 7.851324605941772,
"epoch": 0.08047183485779977,
"grad_norm": 1.0234375,
"learning_rate": 0.000402,
"loss": 7.7369,
"mean_token_accuracy": 0.08832133710384368,
"num_tokens": 1577477.0,
"step": 805
},
{
"entropy": 7.62222638130188,
"epoch": 0.08097165991902834,
"grad_norm": 1.0,
"learning_rate": 0.0004045,
"loss": 7.5622,
"mean_token_accuracy": 0.09800169914960861,
"num_tokens": 1586622.0,
"step": 810
},
{
"entropy": 7.73266487121582,
"epoch": 0.08147148498025691,
"grad_norm": 1.0703125,
"learning_rate": 0.00040699999999999997,
"loss": 7.5753,
"mean_token_accuracy": 0.09251043051481248,
"num_tokens": 1596038.0,
"step": 815
},
{
"entropy": 7.748015069961548,
"epoch": 0.08197131004148547,
"grad_norm": 1.0078125,
"learning_rate": 0.0004095,
"loss": 7.6931,
"mean_token_accuracy": 0.09194686040282249,
"num_tokens": 1606419.0,
"step": 820
},
{
"entropy": 7.690671157836914,
"epoch": 0.08247113510271405,
"grad_norm": 1.140625,
"learning_rate": 0.000412,
"loss": 7.6348,
"mean_token_accuracy": 0.09269572645425797,
"num_tokens": 1617178.0,
"step": 825
},
{
"entropy": 7.766012477874756,
"epoch": 0.08297096016394262,
"grad_norm": 1.046875,
"learning_rate": 0.0004145,
"loss": 7.6793,
"mean_token_accuracy": 0.09032412022352218,
"num_tokens": 1628066.0,
"step": 830
},
{
"entropy": 7.6431036472320555,
"epoch": 0.08347078522517119,
"grad_norm": 1.25,
"learning_rate": 0.000417,
"loss": 7.6039,
"mean_token_accuracy": 0.09320124015212058,
"num_tokens": 1637956.0,
"step": 835
},
{
"entropy": 7.643291711807251,
"epoch": 0.08397061028639977,
"grad_norm": 1.171875,
"learning_rate": 0.0004195,
"loss": 7.6418,
"mean_token_accuracy": 0.09229156970977784,
"num_tokens": 1647388.0,
"step": 840
},
{
"entropy": 7.768024444580078,
"epoch": 0.08447043534762833,
"grad_norm": 1.09375,
"learning_rate": 0.000422,
"loss": 7.6579,
"mean_token_accuracy": 0.0924814723432064,
"num_tokens": 1656983.0,
"step": 845
},
{
"entropy": 7.680607414245605,
"epoch": 0.0849702604088569,
"grad_norm": 1.09375,
"learning_rate": 0.0004245,
"loss": 7.6387,
"mean_token_accuracy": 0.09638504981994629,
"num_tokens": 1666956.0,
"step": 850
},
{
"entropy": 7.58338680267334,
"epoch": 0.08547008547008547,
"grad_norm": 1.1875,
"learning_rate": 0.000427,
"loss": 7.4913,
"mean_token_accuracy": 0.10190274640917778,
"num_tokens": 1675249.0,
"step": 855
},
{
"entropy": 7.666333866119385,
"epoch": 0.08596991053131404,
"grad_norm": 1.0546875,
"learning_rate": 0.0004295,
"loss": 7.5701,
"mean_token_accuracy": 0.09594022110104561,
"num_tokens": 1684142.0,
"step": 860
},
{
"entropy": 7.699511909484864,
"epoch": 0.0864697355925426,
"grad_norm": 1.046875,
"learning_rate": 0.000432,
"loss": 7.6187,
"mean_token_accuracy": 0.09947884380817414,
"num_tokens": 1693512.0,
"step": 865
},
{
"entropy": 7.624828767776489,
"epoch": 0.08696956065377118,
"grad_norm": 1.1953125,
"learning_rate": 0.0004345,
"loss": 7.6047,
"mean_token_accuracy": 0.09352649301290512,
"num_tokens": 1703509.0,
"step": 870
},
{
"entropy": 7.652335834503174,
"epoch": 0.08746938571499975,
"grad_norm": 1.2421875,
"learning_rate": 0.000437,
"loss": 7.5447,
"mean_token_accuracy": 0.09779571294784546,
"num_tokens": 1712158.0,
"step": 875
},
{
"entropy": 7.610031938552856,
"epoch": 0.08796921077622832,
"grad_norm": 1.0859375,
"learning_rate": 0.0004395,
"loss": 7.5735,
"mean_token_accuracy": 0.09820363372564316,
"num_tokens": 1721797.0,
"step": 880
},
{
"entropy": 7.673763847351074,
"epoch": 0.0884690358374569,
"grad_norm": 1.1640625,
"learning_rate": 0.000442,
"loss": 7.6141,
"mean_token_accuracy": 0.08615203425288201,
"num_tokens": 1732139.0,
"step": 885
},
{
"entropy": 7.575803756713867,
"epoch": 0.08896886089868546,
"grad_norm": 0.92578125,
"learning_rate": 0.0004445,
"loss": 7.6571,
"mean_token_accuracy": 0.09244688376784324,
"num_tokens": 1742419.0,
"step": 890
},
{
"entropy": 7.63206787109375,
"epoch": 0.08946868595991403,
"grad_norm": 1.140625,
"learning_rate": 0.000447,
"loss": 7.6147,
"mean_token_accuracy": 0.094232327491045,
"num_tokens": 1752339.0,
"step": 895
},
{
"entropy": 7.5745398044586185,
"epoch": 0.0899685110211426,
"grad_norm": 1.0234375,
"learning_rate": 0.00044950000000000003,
"loss": 7.4909,
"mean_token_accuracy": 0.10000535398721695,
"num_tokens": 1763014.0,
"step": 900
},
{
"entropy": 7.5403139114379885,
"epoch": 0.09046833608237118,
"grad_norm": 1.2421875,
"learning_rate": 0.00045200000000000004,
"loss": 7.4726,
"mean_token_accuracy": 0.10507719144225121,
"num_tokens": 1772977.0,
"step": 905
},
{
"entropy": 7.720607757568359,
"epoch": 0.09096816114359974,
"grad_norm": 1.1171875,
"learning_rate": 0.00045450000000000004,
"loss": 7.5623,
"mean_token_accuracy": 0.10015249475836754,
"num_tokens": 1782085.0,
"step": 910
},
{
"entropy": 7.486642456054687,
"epoch": 0.09146798620482831,
"grad_norm": 1.0625,
"learning_rate": 0.00045700000000000005,
"loss": 7.6137,
"mean_token_accuracy": 0.09703461900353431,
"num_tokens": 1791856.0,
"step": 915
},
{
"entropy": 7.590369796752929,
"epoch": 0.09196781126605688,
"grad_norm": 1.2265625,
"learning_rate": 0.00045950000000000006,
"loss": 7.4354,
"mean_token_accuracy": 0.10379491597414017,
"num_tokens": 1800670.0,
"step": 920
},
{
"entropy": 7.600048780441284,
"epoch": 0.09246763632728545,
"grad_norm": 1.1171875,
"learning_rate": 0.000462,
"loss": 7.6196,
"mean_token_accuracy": 0.09851503968238831,
"num_tokens": 1811138.0,
"step": 925
},
{
"entropy": 7.567831325531006,
"epoch": 0.09296746138851401,
"grad_norm": 1.140625,
"learning_rate": 0.0004645,
"loss": 7.4695,
"mean_token_accuracy": 0.09572812095284462,
"num_tokens": 1819771.0,
"step": 930
},
{
"entropy": 7.476245737075805,
"epoch": 0.09346728644974259,
"grad_norm": 1.0,
"learning_rate": 0.000467,
"loss": 7.5219,
"mean_token_accuracy": 0.09602356925606728,
"num_tokens": 1829075.0,
"step": 935
},
{
"entropy": 7.541802167892456,
"epoch": 0.09396711151097116,
"grad_norm": 1.046875,
"learning_rate": 0.0004695,
"loss": 7.4949,
"mean_token_accuracy": 0.10372020304203033,
"num_tokens": 1837892.0,
"step": 940
},
{
"entropy": 7.549988889694214,
"epoch": 0.09446693657219973,
"grad_norm": 1.0234375,
"learning_rate": 0.000472,
"loss": 7.5496,
"mean_token_accuracy": 0.10090011283755303,
"num_tokens": 1848359.0,
"step": 945
},
{
"entropy": 7.562478113174438,
"epoch": 0.0949667616334283,
"grad_norm": 1.015625,
"learning_rate": 0.0004745,
"loss": 7.5137,
"mean_token_accuracy": 0.09830754399299621,
"num_tokens": 1857665.0,
"step": 950
},
{
"entropy": 7.611538076400757,
"epoch": 0.09546658669465687,
"grad_norm": 1.1171875,
"learning_rate": 0.000477,
"loss": 7.492,
"mean_token_accuracy": 0.09751785323023796,
"num_tokens": 1867313.0,
"step": 955
},
{
"entropy": 7.502454233169556,
"epoch": 0.09596641175588544,
"grad_norm": 0.97265625,
"learning_rate": 0.0004795,
"loss": 7.5782,
"mean_token_accuracy": 0.09409020766615868,
"num_tokens": 1877904.0,
"step": 960
},
{
"entropy": 7.5820417404174805,
"epoch": 0.09646623681711401,
"grad_norm": 1.0,
"learning_rate": 0.000482,
"loss": 7.5047,
"mean_token_accuracy": 0.10309838131070137,
"num_tokens": 1887173.0,
"step": 965
},
{
"entropy": 7.5440513610839846,
"epoch": 0.09696606187834259,
"grad_norm": 1.1015625,
"learning_rate": 0.0004845,
"loss": 7.5662,
"mean_token_accuracy": 0.09383099377155305,
"num_tokens": 1896326.0,
"step": 970
},
{
"entropy": 7.529570627212524,
"epoch": 0.09746588693957114,
"grad_norm": 1.1328125,
"learning_rate": 0.000487,
"loss": 7.4731,
"mean_token_accuracy": 0.09614739716053008,
"num_tokens": 1905403.0,
"step": 975
},
{
"entropy": 7.580197811126709,
"epoch": 0.09796571200079972,
"grad_norm": 1.15625,
"learning_rate": 0.0004895,
"loss": 7.536,
"mean_token_accuracy": 0.0945430114865303,
"num_tokens": 1915910.0,
"step": 980
},
{
"entropy": 7.4563874244689945,
"epoch": 0.09846553706202829,
"grad_norm": 0.99609375,
"learning_rate": 0.000492,
"loss": 7.4826,
"mean_token_accuracy": 0.10040049850940705,
"num_tokens": 1926538.0,
"step": 985
},
{
"entropy": 7.50741491317749,
"epoch": 0.09896536212325686,
"grad_norm": 0.984375,
"learning_rate": 0.0004945,
"loss": 7.528,
"mean_token_accuracy": 0.09595750495791436,
"num_tokens": 1936604.0,
"step": 990
},
{
"entropy": 7.472796154022217,
"epoch": 0.09946518718448542,
"grad_norm": 1.0234375,
"learning_rate": 0.000497,
"loss": 7.4013,
"mean_token_accuracy": 0.10520057901740074,
"num_tokens": 1946509.0,
"step": 995
},
{
"entropy": 7.56459412574768,
"epoch": 0.099965012245714,
"grad_norm": 0.99609375,
"learning_rate": 0.0004995,
"loss": 7.5791,
"mean_token_accuracy": 0.09190018028020859,
"num_tokens": 1955562.0,
"step": 1000
},
{
"entropy": 7.4920408725738525,
"epoch": 0.10046483730694257,
"grad_norm": 1.0390625,
"learning_rate": 0.0004999999981884985,
"loss": 7.4256,
"mean_token_accuracy": 0.1027059607207775,
"num_tokens": 1964805.0,
"step": 1005
},
{
"entropy": 7.523253917694092,
"epoch": 0.10096466236817114,
"grad_norm": 1.140625,
"learning_rate": 0.0004999999908292739,
"loss": 7.5189,
"mean_token_accuracy": 0.09549521021544934,
"num_tokens": 1973735.0,
"step": 1010
},
{
"entropy": 7.478187179565429,
"epoch": 0.10146448742939972,
"grad_norm": 1.078125,
"learning_rate": 0.0004999999778091072,
"loss": 7.4184,
"mean_token_accuracy": 0.09687747582793235,
"num_tokens": 1983657.0,
"step": 1015
},
{
"entropy": 7.534705352783203,
"epoch": 0.10196431249062828,
"grad_norm": 0.94921875,
"learning_rate": 0.0004999999591279991,
"loss": 7.4952,
"mean_token_accuracy": 0.10017814338207245,
"num_tokens": 1994767.0,
"step": 1020
},
{
"entropy": 7.406741523742676,
"epoch": 0.10246413755185685,
"grad_norm": 1.0,
"learning_rate": 0.00049999993478595,
"loss": 7.4923,
"mean_token_accuracy": 0.09699925854802131,
"num_tokens": 2004634.0,
"step": 1025
},
{
"entropy": 7.453082513809204,
"epoch": 0.10296396261308542,
"grad_norm": 0.9921875,
"learning_rate": 0.0004999999047829604,
"loss": 7.4188,
"mean_token_accuracy": 0.09885356277227401,
"num_tokens": 2014346.0,
"step": 1030
},
{
"entropy": 7.5082550048828125,
"epoch": 0.103463787674314,
"grad_norm": 1.0859375,
"learning_rate": 0.000499999869119031,
"loss": 7.5012,
"mean_token_accuracy": 0.0958604633808136,
"num_tokens": 2024132.0,
"step": 1035
},
{
"entropy": 7.439859199523926,
"epoch": 0.10396361273554255,
"grad_norm": 1.0234375,
"learning_rate": 0.0004999998277941629,
"loss": 7.4365,
"mean_token_accuracy": 0.09600495919585228,
"num_tokens": 2034230.0,
"step": 1040
},
{
"entropy": 7.54141902923584,
"epoch": 0.10446343779677113,
"grad_norm": 1.046875,
"learning_rate": 0.0004999997808083569,
"loss": 7.4949,
"mean_token_accuracy": 0.10028873011469841,
"num_tokens": 2043936.0,
"step": 1045
},
{
"entropy": 7.362693738937378,
"epoch": 0.1049632628579997,
"grad_norm": 1.140625,
"learning_rate": 0.0004999997281616144,
"loss": 7.4474,
"mean_token_accuracy": 0.0918818660080433,
"num_tokens": 2053386.0,
"step": 1050
},
{
"entropy": 7.414045619964599,
"epoch": 0.10546308791922827,
"grad_norm": 0.98046875,
"learning_rate": 0.0004999996698539366,
"loss": 7.3857,
"mean_token_accuracy": 0.10662863552570342,
"num_tokens": 2063604.0,
"step": 1055
},
{
"entropy": 7.388621807098389,
"epoch": 0.10596291298045685,
"grad_norm": 1.03125,
"learning_rate": 0.000499999605885325,
"loss": 7.4459,
"mean_token_accuracy": 0.09972845241427422,
"num_tokens": 2072795.0,
"step": 1060
},
{
"entropy": 7.523905897140503,
"epoch": 0.1064627380416854,
"grad_norm": 1.328125,
"learning_rate": 0.0004999995362557813,
"loss": 7.4036,
"mean_token_accuracy": 0.09751716852188111,
"num_tokens": 2082113.0,
"step": 1065
},
{
"entropy": 7.350507736206055,
"epoch": 0.10696256310291398,
"grad_norm": 1.0859375,
"learning_rate": 0.000499999460965307,
"loss": 7.3091,
"mean_token_accuracy": 0.10580763667821884,
"num_tokens": 2090484.0,
"step": 1070
},
{
"entropy": 7.332064962387085,
"epoch": 0.10746238816414255,
"grad_norm": 1.03125,
"learning_rate": 0.0004999993800139043,
"loss": 7.3631,
"mean_token_accuracy": 0.10295772925019264,
"num_tokens": 2100703.0,
"step": 1075
},
{
"entropy": 7.406967115402222,
"epoch": 0.10796221322537113,
"grad_norm": 0.95703125,
"learning_rate": 0.0004999992934015752,
"loss": 7.4699,
"mean_token_accuracy": 0.09553133919835091,
"num_tokens": 2110861.0,
"step": 1080
},
{
"entropy": 7.458237171173096,
"epoch": 0.10846203828659969,
"grad_norm": 0.9609375,
"learning_rate": 0.0004999992011283215,
"loss": 7.3992,
"mean_token_accuracy": 0.10053219199180603,
"num_tokens": 2121414.0,
"step": 1085
},
{
"entropy": 7.396937417984009,
"epoch": 0.10896186334782826,
"grad_norm": 1.0859375,
"learning_rate": 0.0004999991031941459,
"loss": 7.3715,
"mean_token_accuracy": 0.10346362516283988,
"num_tokens": 2131201.0,
"step": 1090
},
{
"entropy": 7.399014854431153,
"epoch": 0.10946168840905683,
"grad_norm": 0.9609375,
"learning_rate": 0.0004999989995990509,
"loss": 7.3818,
"mean_token_accuracy": 0.09918691813945771,
"num_tokens": 2142071.0,
"step": 1095
},
{
"entropy": 7.333117485046387,
"epoch": 0.1099615134702854,
"grad_norm": 1.0234375,
"learning_rate": 0.0004999988903430389,
"loss": 7.4204,
"mean_token_accuracy": 0.10025661289691926,
"num_tokens": 2151514.0,
"step": 1100
},
{
"entropy": 7.393906450271606,
"epoch": 0.11046133853151396,
"grad_norm": 1.015625,
"learning_rate": 0.0004999987754261126,
"loss": 7.4106,
"mean_token_accuracy": 0.10094344615936279,
"num_tokens": 2160828.0,
"step": 1105
},
{
"entropy": 7.414836597442627,
"epoch": 0.11096116359274254,
"grad_norm": 0.98828125,
"learning_rate": 0.0004999986548482751,
"loss": 7.4597,
"mean_token_accuracy": 0.1060835488140583,
"num_tokens": 2169968.0,
"step": 1110
},
{
"entropy": 7.483581686019898,
"epoch": 0.11146098865397111,
"grad_norm": 0.9296875,
"learning_rate": 0.0004999985286095293,
"loss": 7.3709,
"mean_token_accuracy": 0.10352779626846313,
"num_tokens": 2180434.0,
"step": 1115
},
{
"entropy": 7.310662508010864,
"epoch": 0.11196081371519968,
"grad_norm": 1.0,
"learning_rate": 0.0004999983967098785,
"loss": 7.3063,
"mean_token_accuracy": 0.10279445126652717,
"num_tokens": 2190024.0,
"step": 1120
},
{
"entropy": 7.4317279815673825,
"epoch": 0.11246063877642826,
"grad_norm": 0.97265625,
"learning_rate": 0.0004999982591493258,
"loss": 7.3398,
"mean_token_accuracy": 0.10492815002799034,
"num_tokens": 2199897.0,
"step": 1125
},
{
"entropy": 7.252266788482666,
"epoch": 0.11296046383765682,
"grad_norm": 1.0234375,
"learning_rate": 0.0004999981159278749,
"loss": 7.3836,
"mean_token_accuracy": 0.1030288316309452,
"num_tokens": 2209865.0,
"step": 1130
},
{
"entropy": 7.442229843139648,
"epoch": 0.11346028889888539,
"grad_norm": 1.3828125,
"learning_rate": 0.0004999979670455292,
"loss": 7.3598,
"mean_token_accuracy": 0.10323404967784881,
"num_tokens": 2219960.0,
"step": 1135
},
{
"entropy": 7.360328197479248,
"epoch": 0.11396011396011396,
"grad_norm": 0.890625,
"learning_rate": 0.0004999978125022926,
"loss": 7.3618,
"mean_token_accuracy": 0.10576653704047204,
"num_tokens": 2230699.0,
"step": 1140
},
{
"entropy": 7.313149166107178,
"epoch": 0.11445993902134254,
"grad_norm": 1.0,
"learning_rate": 0.000499997652298169,
"loss": 7.36,
"mean_token_accuracy": 0.10162058845162392,
"num_tokens": 2239694.0,
"step": 1145
},
{
"entropy": 7.436854648590088,
"epoch": 0.1149597640825711,
"grad_norm": 1.03125,
"learning_rate": 0.0004999974864331624,
"loss": 7.397,
"mean_token_accuracy": 0.10627919360995293,
"num_tokens": 2250624.0,
"step": 1150
},
{
"entropy": 7.397459411621094,
"epoch": 0.11545958914379967,
"grad_norm": 0.921875,
"learning_rate": 0.0004999973149072768,
"loss": 7.3916,
"mean_token_accuracy": 0.1006945587694645,
"num_tokens": 2260759.0,
"step": 1155
},
{
"entropy": 7.36720380783081,
"epoch": 0.11595941420502824,
"grad_norm": 1.1171875,
"learning_rate": 0.0004999971377205167,
"loss": 7.4208,
"mean_token_accuracy": 0.09522792771458626,
"num_tokens": 2271151.0,
"step": 1160
},
{
"entropy": 7.325729465484619,
"epoch": 0.11645923926625681,
"grad_norm": 1.0859375,
"learning_rate": 0.0004999969548728864,
"loss": 7.304,
"mean_token_accuracy": 0.10690259635448456,
"num_tokens": 2280014.0,
"step": 1165
},
{
"entropy": 7.326078319549561,
"epoch": 0.11695906432748537,
"grad_norm": 1.078125,
"learning_rate": 0.0004999967663643908,
"loss": 7.27,
"mean_token_accuracy": 0.10552891790866852,
"num_tokens": 2288550.0,
"step": 1170
},
{
"entropy": 7.31613564491272,
"epoch": 0.11745888938871395,
"grad_norm": 0.94921875,
"learning_rate": 0.0004999965721950345,
"loss": 7.3537,
"mean_token_accuracy": 0.10183741301298141,
"num_tokens": 2297899.0,
"step": 1175
},
{
"entropy": 7.382048177719116,
"epoch": 0.11795871444994252,
"grad_norm": 0.9921875,
"learning_rate": 0.0004999963723648222,
"loss": 7.3137,
"mean_token_accuracy": 0.1040842704474926,
"num_tokens": 2308021.0,
"step": 1180
},
{
"entropy": 7.371705961227417,
"epoch": 0.1184585395111711,
"grad_norm": 1.890625,
"learning_rate": 0.000499996166873759,
"loss": 7.3646,
"mean_token_accuracy": 0.10259623602032661,
"num_tokens": 2319607.0,
"step": 1185
},
{
"entropy": 7.252321338653564,
"epoch": 0.11895836457239967,
"grad_norm": 1.015625,
"learning_rate": 0.0004999959557218502,
"loss": 7.3417,
"mean_token_accuracy": 0.1054498240351677,
"num_tokens": 2329293.0,
"step": 1190
},
{
"entropy": 7.487326431274414,
"epoch": 0.11945818963362823,
"grad_norm": 1.0078125,
"learning_rate": 0.0004999957389091012,
"loss": 7.3749,
"mean_token_accuracy": 0.10124826729297638,
"num_tokens": 2339812.0,
"step": 1195
},
{
"entropy": 7.205873966217041,
"epoch": 0.1199580146948568,
"grad_norm": 0.99609375,
"learning_rate": 0.0004999955164355171,
"loss": 7.3442,
"mean_token_accuracy": 0.10133651569485665,
"num_tokens": 2349770.0,
"step": 1200
},
{
"entropy": 7.392103576660157,
"epoch": 0.12045783975608537,
"grad_norm": 1.75,
"learning_rate": 0.0004999952883011038,
"loss": 7.2228,
"mean_token_accuracy": 0.10647637471556663,
"num_tokens": 2360355.0,
"step": 1205
},
{
"entropy": 7.279506826400757,
"epoch": 0.12095766481731395,
"grad_norm": 1.0546875,
"learning_rate": 0.000499995054505867,
"loss": 7.4067,
"mean_token_accuracy": 0.10051269009709358,
"num_tokens": 2369444.0,
"step": 1210
},
{
"entropy": 7.258011054992676,
"epoch": 0.1214574898785425,
"grad_norm": 0.91015625,
"learning_rate": 0.0004999948150498124,
"loss": 7.2901,
"mean_token_accuracy": 0.10188745036721229,
"num_tokens": 2380172.0,
"step": 1215
},
{
"entropy": 7.421121406555176,
"epoch": 0.12195731493977108,
"grad_norm": 0.94921875,
"learning_rate": 0.0004999945699329462,
"loss": 7.4482,
"mean_token_accuracy": 0.09546739384531974,
"num_tokens": 2391520.0,
"step": 1220
},
{
"entropy": 7.376113033294677,
"epoch": 0.12245714000099965,
"grad_norm": 1.0078125,
"learning_rate": 0.0004999943191552745,
"loss": 7.3502,
"mean_token_accuracy": 0.09897809475660324,
"num_tokens": 2400977.0,
"step": 1225
},
{
"entropy": 7.440928745269775,
"epoch": 0.12295696506222822,
"grad_norm": 1.0625,
"learning_rate": 0.0004999940627168037,
"loss": 7.3375,
"mean_token_accuracy": 0.09716171771287918,
"num_tokens": 2410220.0,
"step": 1230
},
{
"entropy": 7.268915319442749,
"epoch": 0.12345679012345678,
"grad_norm": 0.95703125,
"learning_rate": 0.00049999380061754,
"loss": 7.3592,
"mean_token_accuracy": 0.10169207826256751,
"num_tokens": 2420000.0,
"step": 1235
},
{
"entropy": 7.363537454605103,
"epoch": 0.12395661518468536,
"grad_norm": 0.9765625,
"learning_rate": 0.0004999935328574903,
"loss": 7.3006,
"mean_token_accuracy": 0.10212150141596794,
"num_tokens": 2429236.0,
"step": 1240
},
{
"entropy": 7.231467533111572,
"epoch": 0.12445644024591393,
"grad_norm": 0.96484375,
"learning_rate": 0.0004999932594366613,
"loss": 7.2149,
"mean_token_accuracy": 0.1043446458876133,
"num_tokens": 2438830.0,
"step": 1245
},
{
"entropy": 7.279609155654907,
"epoch": 0.1249562653071425,
"grad_norm": 1.140625,
"learning_rate": 0.0004999929803550597,
"loss": 7.226,
"mean_token_accuracy": 0.11196640729904175,
"num_tokens": 2448218.0,
"step": 1250
},
{
"entropy": 7.277344560623169,
"epoch": 0.12545609036837108,
"grad_norm": 1.09375,
"learning_rate": 0.0004999926956126927,
"loss": 7.2902,
"mean_token_accuracy": 0.10263564661145211,
"num_tokens": 2458016.0,
"step": 1255
},
{
"entropy": 7.242998886108398,
"epoch": 0.12595591542959964,
"grad_norm": 1.0234375,
"learning_rate": 0.0004999924052095672,
"loss": 7.2023,
"mean_token_accuracy": 0.10558517500758172,
"num_tokens": 2467973.0,
"step": 1260
},
{
"entropy": 7.263315677642822,
"epoch": 0.12645574049082822,
"grad_norm": 0.96484375,
"learning_rate": 0.0004999921091456907,
"loss": 7.2933,
"mean_token_accuracy": 0.10375840216875076,
"num_tokens": 2477811.0,
"step": 1265
},
{
"entropy": 7.332778787612915,
"epoch": 0.12695556555205678,
"grad_norm": 0.98828125,
"learning_rate": 0.0004999918074210707,
"loss": 7.2845,
"mean_token_accuracy": 0.10562208667397499,
"num_tokens": 2487477.0,
"step": 1270
},
{
"entropy": 7.204593849182129,
"epoch": 0.12745539061328534,
"grad_norm": 1.0390625,
"learning_rate": 0.0004999915000357147,
"loss": 7.15,
"mean_token_accuracy": 0.11193068847060203,
"num_tokens": 2497127.0,
"step": 1275
},
{
"entropy": 7.1659417152404785,
"epoch": 0.12795521567451393,
"grad_norm": 0.94921875,
"learning_rate": 0.0004999911869896305,
"loss": 7.2694,
"mean_token_accuracy": 0.10395063161849975,
"num_tokens": 2506340.0,
"step": 1280
},
{
"entropy": 7.400280618667603,
"epoch": 0.1284550407357425,
"grad_norm": 1.0078125,
"learning_rate": 0.0004999908682828258,
"loss": 7.2879,
"mean_token_accuracy": 0.1014986701309681,
"num_tokens": 2515210.0,
"step": 1285
},
{
"entropy": 7.189401388168335,
"epoch": 0.12895486579697105,
"grad_norm": 0.98046875,
"learning_rate": 0.0004999905439153089,
"loss": 7.1957,
"mean_token_accuracy": 0.10809917151927947,
"num_tokens": 2524653.0,
"step": 1290
},
{
"entropy": 7.1879589557647705,
"epoch": 0.12945469085819963,
"grad_norm": 0.98046875,
"learning_rate": 0.0004999902138870878,
"loss": 7.2331,
"mean_token_accuracy": 0.10524520874023438,
"num_tokens": 2534243.0,
"step": 1295
},
{
"entropy": 7.331889247894287,
"epoch": 0.1299545159194282,
"grad_norm": 0.984375,
"learning_rate": 0.0004999898781981707,
"loss": 7.2957,
"mean_token_accuracy": 0.10106250122189522,
"num_tokens": 2543758.0,
"step": 1300
},
{
"entropy": 7.328159761428833,
"epoch": 0.13045434098065678,
"grad_norm": 1.0,
"learning_rate": 0.0004999895368485662,
"loss": 7.3204,
"mean_token_accuracy": 0.09906842038035393,
"num_tokens": 2553537.0,
"step": 1305
},
{
"entropy": 7.208748865127563,
"epoch": 0.13095416604188534,
"grad_norm": 1.0234375,
"learning_rate": 0.000499989189838283,
"loss": 7.2305,
"mean_token_accuracy": 0.10748344659805298,
"num_tokens": 2562812.0,
"step": 1310
},
{
"entropy": 7.291876220703125,
"epoch": 0.1314539911031139,
"grad_norm": 0.984375,
"learning_rate": 0.0004999888371673295,
"loss": 7.2098,
"mean_token_accuracy": 0.1063990943133831,
"num_tokens": 2571728.0,
"step": 1315
},
{
"entropy": 7.261162328720093,
"epoch": 0.13195381616434249,
"grad_norm": 1.015625,
"learning_rate": 0.0004999884788357147,
"loss": 7.3045,
"mean_token_accuracy": 0.10606675744056701,
"num_tokens": 2582309.0,
"step": 1320
},
{
"entropy": 7.262210941314697,
"epoch": 0.13245364122557104,
"grad_norm": 0.94921875,
"learning_rate": 0.0004999881148434478,
"loss": 7.215,
"mean_token_accuracy": 0.10733678117394448,
"num_tokens": 2591810.0,
"step": 1325
},
{
"entropy": 7.1788201332092285,
"epoch": 0.13295346628679963,
"grad_norm": 1.0546875,
"learning_rate": 0.0004999877451905378,
"loss": 7.195,
"mean_token_accuracy": 0.1115802325308323,
"num_tokens": 2602028.0,
"step": 1330
},
{
"entropy": 7.225124454498291,
"epoch": 0.1334532913480282,
"grad_norm": 1.0546875,
"learning_rate": 0.0004999873698769941,
"loss": 7.2008,
"mean_token_accuracy": 0.1077301986515522,
"num_tokens": 2610900.0,
"step": 1335
},
{
"entropy": 7.1687963008880615,
"epoch": 0.13395311640925675,
"grad_norm": 1.0234375,
"learning_rate": 0.000499986988902826,
"loss": 7.2126,
"mean_token_accuracy": 0.10684901028871537,
"num_tokens": 2620918.0,
"step": 1340
},
{
"entropy": 7.236085271835327,
"epoch": 0.13445294147048534,
"grad_norm": 0.94140625,
"learning_rate": 0.0004999866022680431,
"loss": 7.2222,
"mean_token_accuracy": 0.10958969220519066,
"num_tokens": 2631383.0,
"step": 1345
},
{
"entropy": 7.206014204025268,
"epoch": 0.1349527665317139,
"grad_norm": 1.046875,
"learning_rate": 0.0004999862099726552,
"loss": 7.2001,
"mean_token_accuracy": 0.1074417658150196,
"num_tokens": 2640824.0,
"step": 1350
},
{
"entropy": 7.281944513320923,
"epoch": 0.13545259159294248,
"grad_norm": 1.03125,
"learning_rate": 0.0004999858120166721,
"loss": 7.1667,
"mean_token_accuracy": 0.10898390486836433,
"num_tokens": 2649884.0,
"step": 1355
},
{
"entropy": 7.154571914672852,
"epoch": 0.13595241665417104,
"grad_norm": 1.125,
"learning_rate": 0.0004999854084001039,
"loss": 7.2461,
"mean_token_accuracy": 0.10870804488658906,
"num_tokens": 2659464.0,
"step": 1360
},
{
"entropy": 7.230677270889283,
"epoch": 0.1364522417153996,
"grad_norm": 1.046875,
"learning_rate": 0.0004999849991229608,
"loss": 7.2445,
"mean_token_accuracy": 0.10203292071819306,
"num_tokens": 2668271.0,
"step": 1365
},
{
"entropy": 7.276260185241699,
"epoch": 0.1369520667766282,
"grad_norm": 1.0625,
"learning_rate": 0.000499984584185253,
"loss": 7.2983,
"mean_token_accuracy": 0.1035520575940609,
"num_tokens": 2678353.0,
"step": 1370
},
{
"entropy": 7.259475326538086,
"epoch": 0.13745189183785675,
"grad_norm": 0.9296875,
"learning_rate": 0.0004999841635869909,
"loss": 7.2502,
"mean_token_accuracy": 0.10212932154536247,
"num_tokens": 2688082.0,
"step": 1375
},
{
"entropy": 7.254705953598022,
"epoch": 0.1379517168990853,
"grad_norm": 1.1015625,
"learning_rate": 0.0004999837373281852,
"loss": 7.2308,
"mean_token_accuracy": 0.1053150549530983,
"num_tokens": 2697780.0,
"step": 1380
},
{
"entropy": 7.250242757797241,
"epoch": 0.1384515419603139,
"grad_norm": 1.0,
"learning_rate": 0.0004999833054088465,
"loss": 7.2395,
"mean_token_accuracy": 0.1104842759668827,
"num_tokens": 2707851.0,
"step": 1385
},
{
"entropy": 7.221601819992065,
"epoch": 0.13895136702154245,
"grad_norm": 1.0390625,
"learning_rate": 0.0004999828678289858,
"loss": 7.3105,
"mean_token_accuracy": 0.10258962363004684,
"num_tokens": 2718041.0,
"step": 1390
},
{
"entropy": 7.2794324398040775,
"epoch": 0.13945119208277104,
"grad_norm": 1.046875,
"learning_rate": 0.000499982424588614,
"loss": 7.1656,
"mean_token_accuracy": 0.11230125948786736,
"num_tokens": 2726663.0,
"step": 1395
},
{
"entropy": 7.231584119796753,
"epoch": 0.1399510171439996,
"grad_norm": 1.0625,
"learning_rate": 0.0004999819756877422,
"loss": 7.161,
"mean_token_accuracy": 0.10904091596603394,
"num_tokens": 2734926.0,
"step": 1400
},
{
"entropy": 7.219024133682251,
"epoch": 0.14045084220522816,
"grad_norm": 0.99609375,
"learning_rate": 0.0004999815211263819,
"loss": 7.2276,
"mean_token_accuracy": 0.10750553607940674,
"num_tokens": 2744984.0,
"step": 1405
},
{
"entropy": 7.246548795700074,
"epoch": 0.14095066726645675,
"grad_norm": 1.03125,
"learning_rate": 0.0004999810609045444,
"loss": 7.1446,
"mean_token_accuracy": 0.1064922958612442,
"num_tokens": 2754293.0,
"step": 1410
},
{
"entropy": 7.148250722885132,
"epoch": 0.1414504923276853,
"grad_norm": 0.97265625,
"learning_rate": 0.0004999805950222412,
"loss": 7.1998,
"mean_token_accuracy": 0.1090632751584053,
"num_tokens": 2764602.0,
"step": 1415
},
{
"entropy": 7.227945852279663,
"epoch": 0.1419503173889139,
"grad_norm": 1.03125,
"learning_rate": 0.0004999801234794843,
"loss": 7.2471,
"mean_token_accuracy": 0.10523776635527611,
"num_tokens": 2775171.0,
"step": 1420
},
{
"entropy": 7.173311996459961,
"epoch": 0.14245014245014245,
"grad_norm": 0.9609375,
"learning_rate": 0.0004999796462762853,
"loss": 7.148,
"mean_token_accuracy": 0.11108063533902168,
"num_tokens": 2784739.0,
"step": 1425
},
{
"entropy": 7.279621887207031,
"epoch": 0.142949967511371,
"grad_norm": 1.3984375,
"learning_rate": 0.0004999791634126562,
"loss": 7.2429,
"mean_token_accuracy": 0.10983009338378906,
"num_tokens": 2794549.0,
"step": 1430
},
{
"entropy": 7.248407173156738,
"epoch": 0.1434497925725996,
"grad_norm": 0.984375,
"learning_rate": 0.0004999786748886094,
"loss": 7.2142,
"mean_token_accuracy": 0.11163983568549156,
"num_tokens": 2803235.0,
"step": 1435
},
{
"entropy": 7.1812433242797855,
"epoch": 0.14394961763382816,
"grad_norm": 1.265625,
"learning_rate": 0.0004999781807041569,
"loss": 7.1404,
"mean_token_accuracy": 0.10748916789889336,
"num_tokens": 2812367.0,
"step": 1440
},
{
"entropy": 7.127222061157227,
"epoch": 0.14444944269505672,
"grad_norm": 1.0859375,
"learning_rate": 0.0004999776808593113,
"loss": 7.1685,
"mean_token_accuracy": 0.11234024167060852,
"num_tokens": 2822173.0,
"step": 1445
},
{
"entropy": 7.284937810897827,
"epoch": 0.1449492677562853,
"grad_norm": 1.015625,
"learning_rate": 0.0004999771753540852,
"loss": 7.2282,
"mean_token_accuracy": 0.10868457481265067,
"num_tokens": 2831498.0,
"step": 1450
},
{
"entropy": 7.239250993728637,
"epoch": 0.14544909281751386,
"grad_norm": 1.03125,
"learning_rate": 0.0004999766641884912,
"loss": 7.323,
"mean_token_accuracy": 0.10500293597579002,
"num_tokens": 2840883.0,
"step": 1455
},
{
"entropy": 7.220022296905517,
"epoch": 0.14594891787874245,
"grad_norm": 1.109375,
"learning_rate": 0.0004999761473625422,
"loss": 7.1273,
"mean_token_accuracy": 0.10748794749379158,
"num_tokens": 2850694.0,
"step": 1460
},
{
"entropy": 7.092765665054321,
"epoch": 0.146448742939971,
"grad_norm": 1.0234375,
"learning_rate": 0.0004999756248762513,
"loss": 7.1412,
"mean_token_accuracy": 0.10885046645998955,
"num_tokens": 2861100.0,
"step": 1465
},
{
"entropy": 7.190248632431031,
"epoch": 0.14694856800119957,
"grad_norm": 0.9375,
"learning_rate": 0.0004999750967296315,
"loss": 7.0969,
"mean_token_accuracy": 0.11000208780169488,
"num_tokens": 2871054.0,
"step": 1470
},
{
"entropy": 7.077018547058105,
"epoch": 0.14744839306242816,
"grad_norm": 1.0,
"learning_rate": 0.0004999745629226962,
"loss": 7.0566,
"mean_token_accuracy": 0.11119223460555076,
"num_tokens": 2880244.0,
"step": 1475
},
{
"entropy": 7.110202312469482,
"epoch": 0.14794821812365672,
"grad_norm": 0.9140625,
"learning_rate": 0.0004999740234554589,
"loss": 7.168,
"mean_token_accuracy": 0.10733421966433525,
"num_tokens": 2891441.0,
"step": 1480
},
{
"entropy": 7.2041778564453125,
"epoch": 0.1484480431848853,
"grad_norm": 1.0390625,
"learning_rate": 0.0004999734783279327,
"loss": 7.1525,
"mean_token_accuracy": 0.1034772276878357,
"num_tokens": 2901784.0,
"step": 1485
},
{
"entropy": 7.202704334259034,
"epoch": 0.14894786824611386,
"grad_norm": 1.09375,
"learning_rate": 0.000499972927540132,
"loss": 7.1767,
"mean_token_accuracy": 0.1093523621559143,
"num_tokens": 2912294.0,
"step": 1490
},
{
"entropy": 7.128389835357666,
"epoch": 0.14944769330734242,
"grad_norm": 1.0390625,
"learning_rate": 0.0004999723710920703,
"loss": 7.0937,
"mean_token_accuracy": 0.10794242620468139,
"num_tokens": 2921558.0,
"step": 1495
},
{
"entropy": 7.174574518203736,
"epoch": 0.149947518368571,
"grad_norm": 0.9140625,
"learning_rate": 0.0004999718089837616,
"loss": 7.1091,
"mean_token_accuracy": 0.10652265399694442,
"num_tokens": 2930997.0,
"step": 1500
},
{
"entropy": 7.183879375457764,
"epoch": 0.15044734342979957,
"grad_norm": 1.25,
"learning_rate": 0.00049997124121522,
"loss": 7.0964,
"mean_token_accuracy": 0.1068081296980381,
"num_tokens": 2939199.0,
"step": 1505
},
{
"entropy": 7.077691125869751,
"epoch": 0.15094716849102813,
"grad_norm": 1.1328125,
"learning_rate": 0.0004999706677864599,
"loss": 7.1756,
"mean_token_accuracy": 0.1121082328259945,
"num_tokens": 2949466.0,
"step": 1510
},
{
"entropy": 7.178814506530761,
"epoch": 0.15144699355225671,
"grad_norm": 1.0546875,
"learning_rate": 0.0004999700886974958,
"loss": 7.095,
"mean_token_accuracy": 0.1137985847890377,
"num_tokens": 2959653.0,
"step": 1515
},
{
"entropy": 7.118761968612671,
"epoch": 0.15194681861348527,
"grad_norm": 0.89453125,
"learning_rate": 0.000499969503948342,
"loss": 7.11,
"mean_token_accuracy": 0.10633486434817314,
"num_tokens": 2970331.0,
"step": 1520
},
{
"entropy": 7.120200681686401,
"epoch": 0.15244664367471386,
"grad_norm": 1.015625,
"learning_rate": 0.0004999689135390134,
"loss": 7.0665,
"mean_token_accuracy": 0.11365851536393165,
"num_tokens": 2980375.0,
"step": 1525
},
{
"entropy": 7.091594552993774,
"epoch": 0.15294646873594242,
"grad_norm": 0.97265625,
"learning_rate": 0.0004999683174695249,
"loss": 7.1415,
"mean_token_accuracy": 0.11111581027507782,
"num_tokens": 2990562.0,
"step": 1530
},
{
"entropy": 7.181079769134522,
"epoch": 0.15344629379717098,
"grad_norm": 0.9921875,
"learning_rate": 0.0004999677157398914,
"loss": 7.067,
"mean_token_accuracy": 0.11519201397895813,
"num_tokens": 3000797.0,
"step": 1535
},
{
"entropy": 7.086948585510254,
"epoch": 0.15394611885839957,
"grad_norm": 0.9921875,
"learning_rate": 0.0004999671083501281,
"loss": 7.1387,
"mean_token_accuracy": 0.11010118499398232,
"num_tokens": 3010520.0,
"step": 1540
},
{
"entropy": 7.112814235687256,
"epoch": 0.15444594391962813,
"grad_norm": 1.0546875,
"learning_rate": 0.0004999664953002502,
"loss": 7.0513,
"mean_token_accuracy": 0.10723346099257469,
"num_tokens": 3020249.0,
"step": 1545
},
{
"entropy": 7.125877761840821,
"epoch": 0.1549457689808567,
"grad_norm": 0.9765625,
"learning_rate": 0.000499965876590273,
"loss": 7.2067,
"mean_token_accuracy": 0.11246679276227951,
"num_tokens": 3031721.0,
"step": 1550
},
{
"entropy": 7.1510156154632565,
"epoch": 0.15544559404208527,
"grad_norm": 1.0078125,
"learning_rate": 0.0004999652522202125,
"loss": 7.1458,
"mean_token_accuracy": 0.10964183732867241,
"num_tokens": 3041236.0,
"step": 1555
},
{
"entropy": 7.17815523147583,
"epoch": 0.15594541910331383,
"grad_norm": 0.85546875,
"learning_rate": 0.0004999646221900839,
"loss": 7.1011,
"mean_token_accuracy": 0.11013681590557098,
"num_tokens": 3051749.0,
"step": 1560
},
{
"entropy": 7.200712394714356,
"epoch": 0.15644524416454242,
"grad_norm": 0.96484375,
"learning_rate": 0.0004999639864999034,
"loss": 7.2262,
"mean_token_accuracy": 0.10536972433328629,
"num_tokens": 3061928.0,
"step": 1565
},
{
"entropy": 7.110249471664429,
"epoch": 0.15694506922577098,
"grad_norm": 0.99609375,
"learning_rate": 0.000499963345149687,
"loss": 7.0333,
"mean_token_accuracy": 0.11586274281144142,
"num_tokens": 3071598.0,
"step": 1570
},
{
"entropy": 7.061278009414673,
"epoch": 0.15744489428699954,
"grad_norm": 0.94140625,
"learning_rate": 0.0004999626981394506,
"loss": 7.083,
"mean_token_accuracy": 0.10698318555951118,
"num_tokens": 3081952.0,
"step": 1575
},
{
"entropy": 7.216292858123779,
"epoch": 0.15794471934822812,
"grad_norm": 1.078125,
"learning_rate": 0.0004999620454692106,
"loss": 7.1573,
"mean_token_accuracy": 0.10876896157860756,
"num_tokens": 3092047.0,
"step": 1580
},
{
"entropy": 7.157808446884156,
"epoch": 0.15844454440945668,
"grad_norm": 1.046875,
"learning_rate": 0.0004999613871389836,
"loss": 7.1185,
"mean_token_accuracy": 0.10651418566703796,
"num_tokens": 3101454.0,
"step": 1585
},
{
"entropy": 7.061008071899414,
"epoch": 0.15894436947068527,
"grad_norm": 1.0390625,
"learning_rate": 0.0004999607231487858,
"loss": 7.0878,
"mean_token_accuracy": 0.11018021926283836,
"num_tokens": 3111447.0,
"step": 1590
},
{
"entropy": 7.0413116931915285,
"epoch": 0.15944419453191383,
"grad_norm": 0.96875,
"learning_rate": 0.000499960053498634,
"loss": 6.9984,
"mean_token_accuracy": 0.11593033000826836,
"num_tokens": 3121085.0,
"step": 1595
},
{
"entropy": 7.061664676666259,
"epoch": 0.1599440195931424,
"grad_norm": 1.109375,
"learning_rate": 0.0004999593781885454,
"loss": 7.0532,
"mean_token_accuracy": 0.11079274788498879,
"num_tokens": 3131233.0,
"step": 1600
},
{
"entropy": 7.104235029220581,
"epoch": 0.16044384465437098,
"grad_norm": 1.0625,
"learning_rate": 0.0004999586972185366,
"loss": 7.1351,
"mean_token_accuracy": 0.10558126866817474,
"num_tokens": 3140541.0,
"step": 1605
},
{
"entropy": 7.144103956222534,
"epoch": 0.16094366971559954,
"grad_norm": 1.0078125,
"learning_rate": 0.0004999580105886248,
"loss": 7.1168,
"mean_token_accuracy": 0.10910270363092422,
"num_tokens": 3150166.0,
"step": 1610
},
{
"entropy": 7.1036604881286625,
"epoch": 0.16144349477682812,
"grad_norm": 1.0859375,
"learning_rate": 0.0004999573182988275,
"loss": 7.1171,
"mean_token_accuracy": 0.11519814357161522,
"num_tokens": 3160259.0,
"step": 1615
},
{
"entropy": 7.203520393371582,
"epoch": 0.16194331983805668,
"grad_norm": 1.1484375,
"learning_rate": 0.0004999566203491619,
"loss": 7.1016,
"mean_token_accuracy": 0.10444672331213951,
"num_tokens": 3168801.0,
"step": 1620
},
{
"entropy": 7.1718590259552,
"epoch": 0.16244314489928524,
"grad_norm": 0.96875,
"learning_rate": 0.0004999559167396455,
"loss": 7.2047,
"mean_token_accuracy": 0.10611712411046029,
"num_tokens": 3181029.0,
"step": 1625
},
{
"entropy": 7.069874811172485,
"epoch": 0.16294296996051383,
"grad_norm": 0.94140625,
"learning_rate": 0.0004999552074702963,
"loss": 7.0282,
"mean_token_accuracy": 0.11574400290846824,
"num_tokens": 3190963.0,
"step": 1630
},
{
"entropy": 7.015948343276977,
"epoch": 0.1634427950217424,
"grad_norm": 0.94140625,
"learning_rate": 0.0004999544925411318,
"loss": 7.0127,
"mean_token_accuracy": 0.11391307860612869,
"num_tokens": 3200714.0,
"step": 1635
},
{
"entropy": 7.125380325317383,
"epoch": 0.16394262008297095,
"grad_norm": 0.99609375,
"learning_rate": 0.0004999537719521703,
"loss": 7.0543,
"mean_token_accuracy": 0.11627331748604774,
"num_tokens": 3209965.0,
"step": 1640
},
{
"entropy": 7.081728458404541,
"epoch": 0.16444244514419953,
"grad_norm": 0.984375,
"learning_rate": 0.0004999530457034297,
"loss": 7.0694,
"mean_token_accuracy": 0.10980000048875808,
"num_tokens": 3218849.0,
"step": 1645
},
{
"entropy": 7.131386089324951,
"epoch": 0.1649422702054281,
"grad_norm": 0.94140625,
"learning_rate": 0.0004999523137949283,
"loss": 7.1137,
"mean_token_accuracy": 0.10928037911653518,
"num_tokens": 3229483.0,
"step": 1650
},
{
"entropy": 7.108076000213623,
"epoch": 0.16544209526665668,
"grad_norm": 0.98828125,
"learning_rate": 0.0004999515762266846,
"loss": 7.107,
"mean_token_accuracy": 0.10942549929022789,
"num_tokens": 3239818.0,
"step": 1655
},
{
"entropy": 7.173019933700561,
"epoch": 0.16594192032788524,
"grad_norm": 0.96484375,
"learning_rate": 0.0004999508329987173,
"loss": 7.1241,
"mean_token_accuracy": 0.10582287237048149,
"num_tokens": 3249136.0,
"step": 1660
},
{
"entropy": 7.111468029022217,
"epoch": 0.1664417453891138,
"grad_norm": 1.015625,
"learning_rate": 0.0004999500841110447,
"loss": 7.0154,
"mean_token_accuracy": 0.11225976943969726,
"num_tokens": 3258624.0,
"step": 1665
},
{
"entropy": 7.112836456298828,
"epoch": 0.16694157045034239,
"grad_norm": 0.96484375,
"learning_rate": 0.000499949329563686,
"loss": 7.1247,
"mean_token_accuracy": 0.10936064794659614,
"num_tokens": 3269079.0,
"step": 1670
},
{
"entropy": 7.053909111022949,
"epoch": 0.16744139551157095,
"grad_norm": 0.92578125,
"learning_rate": 0.00049994856935666,
"loss": 7.0621,
"mean_token_accuracy": 0.11304035782814026,
"num_tokens": 3280069.0,
"step": 1675
},
{
"entropy": 7.096081161499024,
"epoch": 0.16794122057279953,
"grad_norm": 0.99609375,
"learning_rate": 0.000499947803489986,
"loss": 7.0357,
"mean_token_accuracy": 0.11458788961172103,
"num_tokens": 3289520.0,
"step": 1680
},
{
"entropy": 7.1208868503570555,
"epoch": 0.1684410456340281,
"grad_norm": 0.98828125,
"learning_rate": 0.0004999470319636829,
"loss": 7.0512,
"mean_token_accuracy": 0.11174150407314301,
"num_tokens": 3299162.0,
"step": 1685
},
{
"entropy": 6.976963329315185,
"epoch": 0.16894087069525665,
"grad_norm": 0.9453125,
"learning_rate": 0.0004999462547777705,
"loss": 7.0277,
"mean_token_accuracy": 0.11063397377729416,
"num_tokens": 3308184.0,
"step": 1690
},
{
"entropy": 7.206235885620117,
"epoch": 0.16944069575648524,
"grad_norm": 1.140625,
"learning_rate": 0.0004999454719322682,
"loss": 7.0654,
"mean_token_accuracy": 0.11082289442420006,
"num_tokens": 3317647.0,
"step": 1695
},
{
"entropy": 7.0437695503234865,
"epoch": 0.1699405208177138,
"grad_norm": 0.9921875,
"learning_rate": 0.0004999446834271958,
"loss": 7.1133,
"mean_token_accuracy": 0.10917564556002617,
"num_tokens": 3329437.0,
"step": 1700
},
{
"entropy": 7.136263847351074,
"epoch": 0.17044034587894236,
"grad_norm": 0.921875,
"learning_rate": 0.0004999438892625728,
"loss": 7.056,
"mean_token_accuracy": 0.11442272663116455,
"num_tokens": 3340011.0,
"step": 1705
},
{
"entropy": 7.04804253578186,
"epoch": 0.17094017094017094,
"grad_norm": 1.015625,
"learning_rate": 0.0004999430894384198,
"loss": 7.0522,
"mean_token_accuracy": 0.11719416975975036,
"num_tokens": 3348979.0,
"step": 1710
},
{
"entropy": 7.136094808578491,
"epoch": 0.1714399960013995,
"grad_norm": 1.046875,
"learning_rate": 0.0004999422839547564,
"loss": 7.1209,
"mean_token_accuracy": 0.10911227688193322,
"num_tokens": 3359055.0,
"step": 1715
},
{
"entropy": 7.072116565704346,
"epoch": 0.1719398210626281,
"grad_norm": 1.09375,
"learning_rate": 0.0004999414728116029,
"loss": 7.0214,
"mean_token_accuracy": 0.1116297036409378,
"num_tokens": 3368206.0,
"step": 1720
},
{
"entropy": 7.029803943634033,
"epoch": 0.17243964612385665,
"grad_norm": 1.015625,
"learning_rate": 0.0004999406560089798,
"loss": 7.0601,
"mean_token_accuracy": 0.11080883666872979,
"num_tokens": 3378522.0,
"step": 1725
},
{
"entropy": 7.112205123901367,
"epoch": 0.1729394711850852,
"grad_norm": 0.99609375,
"learning_rate": 0.0004999398335469078,
"loss": 7.0555,
"mean_token_accuracy": 0.11062405034899711,
"num_tokens": 3389052.0,
"step": 1730
},
{
"entropy": 6.981901693344116,
"epoch": 0.1734392962463138,
"grad_norm": 1.078125,
"learning_rate": 0.0004999390054254074,
"loss": 6.9422,
"mean_token_accuracy": 0.12012189701199531,
"num_tokens": 3398269.0,
"step": 1735
},
{
"entropy": 7.079383420944214,
"epoch": 0.17393912130754235,
"grad_norm": 1.046875,
"learning_rate": 0.0004999381716444996,
"loss": 7.009,
"mean_token_accuracy": 0.11454930454492569,
"num_tokens": 3408063.0,
"step": 1740
},
{
"entropy": 7.0896364688873295,
"epoch": 0.17443894636877094,
"grad_norm": 1.2265625,
"learning_rate": 0.0004999373322042052,
"loss": 7.0899,
"mean_token_accuracy": 0.11016308888792992,
"num_tokens": 3418903.0,
"step": 1745
},
{
"entropy": 7.017670631408691,
"epoch": 0.1749387714299995,
"grad_norm": 1.0,
"learning_rate": 0.0004999364871045455,
"loss": 6.989,
"mean_token_accuracy": 0.11600941643118859,
"num_tokens": 3428831.0,
"step": 1750
},
{
"entropy": 6.994602680206299,
"epoch": 0.17543859649122806,
"grad_norm": 0.9375,
"learning_rate": 0.0004999356363455415,
"loss": 7.0469,
"mean_token_accuracy": 0.11205000951886177,
"num_tokens": 3438314.0,
"step": 1755
},
{
"entropy": 7.113824510574341,
"epoch": 0.17593842155245665,
"grad_norm": 0.953125,
"learning_rate": 0.000499934779927215,
"loss": 7.0623,
"mean_token_accuracy": 0.10831346586346627,
"num_tokens": 3449248.0,
"step": 1760
},
{
"entropy": 7.026305103302002,
"epoch": 0.1764382466136852,
"grad_norm": 1.0859375,
"learning_rate": 0.0004999339178495872,
"loss": 7.0311,
"mean_token_accuracy": 0.10976018756628036,
"num_tokens": 3460119.0,
"step": 1765
},
{
"entropy": 7.039245700836181,
"epoch": 0.1769380716749138,
"grad_norm": 1.0078125,
"learning_rate": 0.0004999330501126798,
"loss": 6.9514,
"mean_token_accuracy": 0.11899356544017792,
"num_tokens": 3469610.0,
"step": 1770
},
{
"entropy": 6.961409282684326,
"epoch": 0.17743789673614235,
"grad_norm": 0.96875,
"learning_rate": 0.0004999321767165148,
"loss": 6.9903,
"mean_token_accuracy": 0.1108189269900322,
"num_tokens": 3480219.0,
"step": 1775
},
{
"entropy": 7.098644351959228,
"epoch": 0.1779377217973709,
"grad_norm": 0.9453125,
"learning_rate": 0.0004999312976611142,
"loss": 6.9401,
"mean_token_accuracy": 0.11498842909932136,
"num_tokens": 3489445.0,
"step": 1780
},
{
"entropy": 7.004860305786133,
"epoch": 0.1784375468585995,
"grad_norm": 0.9296875,
"learning_rate": 0.0004999304129465,
"loss": 6.9697,
"mean_token_accuracy": 0.11644153371453285,
"num_tokens": 3499164.0,
"step": 1785
},
{
"entropy": 7.071631383895874,
"epoch": 0.17893737191982806,
"grad_norm": 0.96875,
"learning_rate": 0.0004999295225726945,
"loss": 7.0802,
"mean_token_accuracy": 0.10255986601114273,
"num_tokens": 3510242.0,
"step": 1790
},
{
"entropy": 7.021933746337891,
"epoch": 0.17943719698105662,
"grad_norm": 0.9921875,
"learning_rate": 0.00049992862653972,
"loss": 6.9818,
"mean_token_accuracy": 0.10971452966332436,
"num_tokens": 3519481.0,
"step": 1795
},
{
"entropy": 7.029817724227906,
"epoch": 0.1799370220422852,
"grad_norm": 0.96875,
"learning_rate": 0.0004999277248475992,
"loss": 7.0064,
"mean_token_accuracy": 0.11529789119958878,
"num_tokens": 3529706.0,
"step": 1800
},
{
"entropy": 6.9250016689300535,
"epoch": 0.18043684710351376,
"grad_norm": 1.0390625,
"learning_rate": 0.0004999268174963547,
"loss": 6.974,
"mean_token_accuracy": 0.11133951023221016,
"num_tokens": 3539239.0,
"step": 1805
},
{
"entropy": 7.046410942077637,
"epoch": 0.18093667216474235,
"grad_norm": 1.109375,
"learning_rate": 0.0004999259044860093,
"loss": 6.9372,
"mean_token_accuracy": 0.11808101162314415,
"num_tokens": 3548177.0,
"step": 1810
},
{
"entropy": 7.036075687408447,
"epoch": 0.1814364972259709,
"grad_norm": 0.94140625,
"learning_rate": 0.0004999249858165861,
"loss": 7.0122,
"mean_token_accuracy": 0.11086658462882042,
"num_tokens": 3557957.0,
"step": 1815
},
{
"entropy": 7.026245260238648,
"epoch": 0.18193632228719947,
"grad_norm": 0.8984375,
"learning_rate": 0.0004999240614881082,
"loss": 7.0253,
"mean_token_accuracy": 0.11065947040915489,
"num_tokens": 3567701.0,
"step": 1820
},
{
"entropy": 7.038810110092163,
"epoch": 0.18243614734842806,
"grad_norm": 1.015625,
"learning_rate": 0.0004999231315005987,
"loss": 6.9766,
"mean_token_accuracy": 0.11399839967489242,
"num_tokens": 3575830.0,
"step": 1825
},
{
"entropy": 7.004911994934082,
"epoch": 0.18293597240965662,
"grad_norm": 1.0234375,
"learning_rate": 0.0004999221958540811,
"loss": 6.9551,
"mean_token_accuracy": 0.12019872739911079,
"num_tokens": 3585453.0,
"step": 1830
},
{
"entropy": 6.924448537826538,
"epoch": 0.1834357974708852,
"grad_norm": 0.9765625,
"learning_rate": 0.0004999212545485789,
"loss": 6.9666,
"mean_token_accuracy": 0.11770169287919999,
"num_tokens": 3595340.0,
"step": 1835
},
{
"entropy": 7.108413887023926,
"epoch": 0.18393562253211376,
"grad_norm": 1.1953125,
"learning_rate": 0.0004999203075841159,
"loss": 6.9864,
"mean_token_accuracy": 0.1140538938343525,
"num_tokens": 3605083.0,
"step": 1840
},
{
"entropy": 7.03106656074524,
"epoch": 0.18443544759334232,
"grad_norm": 1.046875,
"learning_rate": 0.0004999193549607157,
"loss": 6.9503,
"mean_token_accuracy": 0.1139814093708992,
"num_tokens": 3614852.0,
"step": 1845
},
{
"entropy": 7.015335369110107,
"epoch": 0.1849352726545709,
"grad_norm": 1.015625,
"learning_rate": 0.0004999183966784026,
"loss": 6.9628,
"mean_token_accuracy": 0.11288752257823945,
"num_tokens": 3624267.0,
"step": 1850
},
{
"entropy": 6.954336786270142,
"epoch": 0.18543509771579947,
"grad_norm": 0.86328125,
"learning_rate": 0.0004999174327372004,
"loss": 6.8825,
"mean_token_accuracy": 0.1168724238872528,
"num_tokens": 3633826.0,
"step": 1855
},
{
"entropy": 7.025014400482178,
"epoch": 0.18593492277702803,
"grad_norm": 0.99609375,
"learning_rate": 0.0004999164631371335,
"loss": 7.0058,
"mean_token_accuracy": 0.10895812138915062,
"num_tokens": 3643236.0,
"step": 1860
},
{
"entropy": 6.908126974105835,
"epoch": 0.18643474783825661,
"grad_norm": 1.1015625,
"learning_rate": 0.0004999154878782262,
"loss": 6.879,
"mean_token_accuracy": 0.11762138828635216,
"num_tokens": 3652859.0,
"step": 1865
},
{
"entropy": 7.008557558059692,
"epoch": 0.18693457289948517,
"grad_norm": 0.96875,
"learning_rate": 0.000499914506960503,
"loss": 7.0378,
"mean_token_accuracy": 0.10980783402919769,
"num_tokens": 3663145.0,
"step": 1870
},
{
"entropy": 7.017056131362915,
"epoch": 0.18743439796071376,
"grad_norm": 0.9609375,
"learning_rate": 0.0004999135203839889,
"loss": 6.9746,
"mean_token_accuracy": 0.1128289632499218,
"num_tokens": 3673492.0,
"step": 1875
},
{
"entropy": 6.972816038131714,
"epoch": 0.18793422302194232,
"grad_norm": 1.0859375,
"learning_rate": 0.0004999125281487084,
"loss": 6.9977,
"mean_token_accuracy": 0.11690860837697983,
"num_tokens": 3683582.0,
"step": 1880
},
{
"entropy": 7.017599773406983,
"epoch": 0.18843404808317088,
"grad_norm": 1.03125,
"learning_rate": 0.0004999115302546866,
"loss": 6.9272,
"mean_token_accuracy": 0.11678347289562226,
"num_tokens": 3693075.0,
"step": 1885
},
{
"entropy": 6.947669601440429,
"epoch": 0.18893387314439947,
"grad_norm": 1.0078125,
"learning_rate": 0.0004999105267019486,
"loss": 6.9816,
"mean_token_accuracy": 0.11278985366225243,
"num_tokens": 3702290.0,
"step": 1890
},
{
"entropy": 7.008899068832397,
"epoch": 0.18943369820562803,
"grad_norm": 0.9375,
"learning_rate": 0.0004999095174905195,
"loss": 6.9368,
"mean_token_accuracy": 0.11327538117766381,
"num_tokens": 3711811.0,
"step": 1895
},
{
"entropy": 6.961658048629761,
"epoch": 0.1899335232668566,
"grad_norm": 0.9453125,
"learning_rate": 0.0004999085026204249,
"loss": 6.925,
"mean_token_accuracy": 0.11348919793963433,
"num_tokens": 3720863.0,
"step": 1900
},
{
"entropy": 7.038826322555542,
"epoch": 0.19043334832808517,
"grad_norm": 0.984375,
"learning_rate": 0.0004999074820916903,
"loss": 7.1659,
"mean_token_accuracy": 0.10545966401696205,
"num_tokens": 3731797.0,
"step": 1905
},
{
"entropy": 7.0656005859375,
"epoch": 0.19093317338931373,
"grad_norm": 1.0234375,
"learning_rate": 0.0004999064559043412,
"loss": 6.7917,
"mean_token_accuracy": 0.12273367866873741,
"num_tokens": 3741083.0,
"step": 1910
},
{
"entropy": 6.850661325454712,
"epoch": 0.19143299845054232,
"grad_norm": 1.2734375,
"learning_rate": 0.0004999054240584037,
"loss": 6.9217,
"mean_token_accuracy": 0.116951634734869,
"num_tokens": 3750438.0,
"step": 1915
},
{
"entropy": 7.075789117813111,
"epoch": 0.19193282351177088,
"grad_norm": 1.2734375,
"learning_rate": 0.0004999043865539035,
"loss": 6.9422,
"mean_token_accuracy": 0.11572268456220627,
"num_tokens": 3759763.0,
"step": 1920
},
{
"entropy": 6.927079534530639,
"epoch": 0.19243264857299944,
"grad_norm": 0.94140625,
"learning_rate": 0.0004999033433908667,
"loss": 6.8813,
"mean_token_accuracy": 0.12867123857140542,
"num_tokens": 3769523.0,
"step": 1925
},
{
"entropy": 6.874381685256958,
"epoch": 0.19293247363422802,
"grad_norm": 0.8515625,
"learning_rate": 0.0004999022945693198,
"loss": 6.9136,
"mean_token_accuracy": 0.12044937536120415,
"num_tokens": 3779290.0,
"step": 1930
},
{
"entropy": 7.032785797119141,
"epoch": 0.19343229869545658,
"grad_norm": 1.0390625,
"learning_rate": 0.000499901240089289,
"loss": 6.9319,
"mean_token_accuracy": 0.11947752237319946,
"num_tokens": 3788582.0,
"step": 1935
},
{
"entropy": 6.953524160385132,
"epoch": 0.19393212375668517,
"grad_norm": 0.9296875,
"learning_rate": 0.0004999001799508009,
"loss": 6.9225,
"mean_token_accuracy": 0.11011315360665322,
"num_tokens": 3798281.0,
"step": 1940
},
{
"entropy": 6.91785306930542,
"epoch": 0.19443194881791373,
"grad_norm": 1.09375,
"learning_rate": 0.0004998991141538821,
"loss": 6.9105,
"mean_token_accuracy": 0.11099191904067993,
"num_tokens": 3807775.0,
"step": 1945
},
{
"entropy": 7.051416206359863,
"epoch": 0.1949317738791423,
"grad_norm": 0.9453125,
"learning_rate": 0.0004998980426985596,
"loss": 7.0716,
"mean_token_accuracy": 0.11268870756030083,
"num_tokens": 3818852.0,
"step": 1950
},
{
"entropy": 7.099276971817017,
"epoch": 0.19543159894037088,
"grad_norm": 1.1171875,
"learning_rate": 0.00049989696558486,
"loss": 6.965,
"mean_token_accuracy": 0.10571991056203842,
"num_tokens": 3826924.0,
"step": 1955
},
{
"entropy": 6.861832475662231,
"epoch": 0.19593142400159944,
"grad_norm": 1.140625,
"learning_rate": 0.0004998958828128108,
"loss": 6.8775,
"mean_token_accuracy": 0.12424767538905143,
"num_tokens": 3835098.0,
"step": 1960
},
{
"entropy": 7.058041620254516,
"epoch": 0.19643124906282802,
"grad_norm": 0.95703125,
"learning_rate": 0.0004998947943824389,
"loss": 7.0427,
"mean_token_accuracy": 0.11062902957201004,
"num_tokens": 3845914.0,
"step": 1965
},
{
"entropy": 6.971142864227295,
"epoch": 0.19693107412405658,
"grad_norm": 1.0078125,
"learning_rate": 0.0004998937002937719,
"loss": 6.9044,
"mean_token_accuracy": 0.11801907047629356,
"num_tokens": 3855791.0,
"step": 1970
},
{
"entropy": 6.942867279052734,
"epoch": 0.19743089918528514,
"grad_norm": 0.93359375,
"learning_rate": 0.0004998926005468373,
"loss": 6.8828,
"mean_token_accuracy": 0.12405865415930747,
"num_tokens": 3865970.0,
"step": 1975
},
{
"entropy": 6.934929323196411,
"epoch": 0.19793072424651373,
"grad_norm": 0.9765625,
"learning_rate": 0.0004998914951416627,
"loss": 6.9457,
"mean_token_accuracy": 0.11826047450304031,
"num_tokens": 3875139.0,
"step": 1980
},
{
"entropy": 6.993371534347534,
"epoch": 0.1984305493077423,
"grad_norm": 1.046875,
"learning_rate": 0.000499890384078276,
"loss": 6.9586,
"mean_token_accuracy": 0.1164481833577156,
"num_tokens": 3884075.0,
"step": 1985
},
{
"entropy": 7.047069311141968,
"epoch": 0.19893037436897085,
"grad_norm": 0.96484375,
"learning_rate": 0.0004998892673567051,
"loss": 6.8696,
"mean_token_accuracy": 0.11561509147286415,
"num_tokens": 3894273.0,
"step": 1990
},
{
"entropy": 6.881417846679687,
"epoch": 0.19943019943019943,
"grad_norm": 1.09375,
"learning_rate": 0.0004998881449769781,
"loss": 6.919,
"mean_token_accuracy": 0.11565662696957588,
"num_tokens": 3904940.0,
"step": 1995
},
{
"entropy": 7.18874077796936,
"epoch": 0.199930024491428,
"grad_norm": 1.65625,
"learning_rate": 0.0004998870169391232,
"loss": 7.0733,
"mean_token_accuracy": 0.1034354567527771,
"num_tokens": 3916273.0,
"step": 2000
},
{
"entropy": 6.8554352760314945,
"epoch": 0.20042984955265658,
"grad_norm": 0.99609375,
"learning_rate": 0.000499885883243169,
"loss": 6.8612,
"mean_token_accuracy": 0.11686792820692063,
"num_tokens": 3926495.0,
"step": 2005
},
{
"entropy": 6.894193315505982,
"epoch": 0.20092967461388514,
"grad_norm": 1.1875,
"learning_rate": 0.0004998847438891437,
"loss": 6.9356,
"mean_token_accuracy": 0.11599919721484184,
"num_tokens": 3936286.0,
"step": 2010
},
{
"entropy": 7.00080976486206,
"epoch": 0.2014294996751137,
"grad_norm": 1.03125,
"learning_rate": 0.0004998835988770761,
"loss": 6.9699,
"mean_token_accuracy": 0.10990998297929763,
"num_tokens": 3946924.0,
"step": 2015
},
{
"entropy": 7.00573239326477,
"epoch": 0.20192932473634229,
"grad_norm": 1.0078125,
"learning_rate": 0.000499882448206995,
"loss": 6.8975,
"mean_token_accuracy": 0.11481108143925667,
"num_tokens": 3956815.0,
"step": 2020
},
{
"entropy": 6.867879438400268,
"epoch": 0.20242914979757085,
"grad_norm": 0.9375,
"learning_rate": 0.0004998812918789293,
"loss": 6.8577,
"mean_token_accuracy": 0.1193717747926712,
"num_tokens": 3967034.0,
"step": 2025
},
{
"entropy": 6.9768967628479,
"epoch": 0.20292897485879943,
"grad_norm": 1.0390625,
"learning_rate": 0.0004998801298929084,
"loss": 6.9322,
"mean_token_accuracy": 0.11179861947894096,
"num_tokens": 3976800.0,
"step": 2030
},
{
"entropy": 7.073401927947998,
"epoch": 0.203428799920028,
"grad_norm": 1.0703125,
"learning_rate": 0.0004998789622489611,
"loss": 6.9943,
"mean_token_accuracy": 0.11428194269537925,
"num_tokens": 3987279.0,
"step": 2035
},
{
"entropy": 6.901258516311645,
"epoch": 0.20392862498125655,
"grad_norm": 0.94921875,
"learning_rate": 0.0004998777889471171,
"loss": 6.8761,
"mean_token_accuracy": 0.11997782960534095,
"num_tokens": 3998414.0,
"step": 2040
},
{
"entropy": 6.8927994728088375,
"epoch": 0.20442845004248514,
"grad_norm": 1.0546875,
"learning_rate": 0.0004998766099874056,
"loss": 6.8762,
"mean_token_accuracy": 0.12286129742860794,
"num_tokens": 4007994.0,
"step": 2045
},
{
"entropy": 6.911945915222168,
"epoch": 0.2049282751037137,
"grad_norm": 0.96875,
"learning_rate": 0.0004998754253698566,
"loss": 6.8832,
"mean_token_accuracy": 0.11526042371988296,
"num_tokens": 4018285.0,
"step": 2050
},
{
"entropy": 7.050160837173462,
"epoch": 0.20542810016494226,
"grad_norm": 1.015625,
"learning_rate": 0.0004998742350944998,
"loss": 6.9687,
"mean_token_accuracy": 0.10755550190806389,
"num_tokens": 4028689.0,
"step": 2055
},
{
"entropy": 6.887995481491089,
"epoch": 0.20592792522617084,
"grad_norm": 1.03125,
"learning_rate": 0.0004998730391613651,
"loss": 6.8843,
"mean_token_accuracy": 0.12264417707920075,
"num_tokens": 4038944.0,
"step": 2060
},
{
"entropy": 7.012986135482788,
"epoch": 0.2064277502873994,
"grad_norm": 0.95703125,
"learning_rate": 0.0004998718375704825,
"loss": 6.9971,
"mean_token_accuracy": 0.11188706979155541,
"num_tokens": 4049048.0,
"step": 2065
},
{
"entropy": 6.976608419418335,
"epoch": 0.206927575348628,
"grad_norm": 1.0078125,
"learning_rate": 0.0004998706303218825,
"loss": 6.828,
"mean_token_accuracy": 0.12201604545116425,
"num_tokens": 4058710.0,
"step": 2070
},
{
"entropy": 6.8684539794921875,
"epoch": 0.20742740040985655,
"grad_norm": 1.0625,
"learning_rate": 0.0004998694174155952,
"loss": 6.8206,
"mean_token_accuracy": 0.11384685859084129,
"num_tokens": 4069517.0,
"step": 2075
},
{
"entropy": 6.8656822681427006,
"epoch": 0.2079272254710851,
"grad_norm": 1.0078125,
"learning_rate": 0.0004998681988516512,
"loss": 6.9341,
"mean_token_accuracy": 0.11590560525655746,
"num_tokens": 4080730.0,
"step": 2080
},
{
"entropy": 6.992557621002197,
"epoch": 0.2084270505323137,
"grad_norm": 1.046875,
"learning_rate": 0.0004998669746300811,
"loss": 6.8194,
"mean_token_accuracy": 0.11853130012750626,
"num_tokens": 4090505.0,
"step": 2085
},
{
"entropy": 6.830566310882569,
"epoch": 0.20892687559354226,
"grad_norm": 1.0078125,
"learning_rate": 0.0004998657447509159,
"loss": 6.8106,
"mean_token_accuracy": 0.12010636702179908,
"num_tokens": 4099963.0,
"step": 2090
},
{
"entropy": 6.972150182723999,
"epoch": 0.20942670065477084,
"grad_norm": 1.171875,
"learning_rate": 0.0004998645092141864,
"loss": 6.9136,
"mean_token_accuracy": 0.11967169344425202,
"num_tokens": 4109340.0,
"step": 2095
},
{
"entropy": 7.104512548446655,
"epoch": 0.2099265257159994,
"grad_norm": 1.0546875,
"learning_rate": 0.0004998632680199238,
"loss": 6.9387,
"mean_token_accuracy": 0.11301500350236893,
"num_tokens": 4118476.0,
"step": 2100
},
{
"entropy": 6.826396417617798,
"epoch": 0.21042635077722796,
"grad_norm": 1.03125,
"learning_rate": 0.0004998620211681591,
"loss": 6.8767,
"mean_token_accuracy": 0.1197544053196907,
"num_tokens": 4127922.0,
"step": 2105
},
{
"entropy": 6.892666673660278,
"epoch": 0.21092617583845655,
"grad_norm": 1.03125,
"learning_rate": 0.0004998607686589239,
"loss": 6.8679,
"mean_token_accuracy": 0.12079423889517785,
"num_tokens": 4137202.0,
"step": 2110
},
{
"entropy": 6.8921217918396,
"epoch": 0.2114260008996851,
"grad_norm": 0.94921875,
"learning_rate": 0.0004998595104922496,
"loss": 6.8529,
"mean_token_accuracy": 0.11905877813696861,
"num_tokens": 4146789.0,
"step": 2115
},
{
"entropy": 6.8600248336792,
"epoch": 0.2119258259609137,
"grad_norm": 1.0859375,
"learning_rate": 0.0004998582466681678,
"loss": 6.9388,
"mean_token_accuracy": 0.11638726368546486,
"num_tokens": 4157628.0,
"step": 2120
},
{
"entropy": 7.016875600814819,
"epoch": 0.21242565102214225,
"grad_norm": 1.0859375,
"learning_rate": 0.0004998569771867105,
"loss": 6.9026,
"mean_token_accuracy": 0.1167732298374176,
"num_tokens": 4168522.0,
"step": 2125
},
{
"entropy": 6.951946640014649,
"epoch": 0.2129254760833708,
"grad_norm": 1.171875,
"learning_rate": 0.0004998557020479095,
"loss": 6.9472,
"mean_token_accuracy": 0.11931234747171401,
"num_tokens": 4178590.0,
"step": 2130
},
{
"entropy": 6.875528860092163,
"epoch": 0.2134253011445994,
"grad_norm": 0.984375,
"learning_rate": 0.0004998544212517968,
"loss": 6.7534,
"mean_token_accuracy": 0.12599712759256362,
"num_tokens": 4188004.0,
"step": 2135
},
{
"entropy": 6.89941816329956,
"epoch": 0.21392512620582796,
"grad_norm": 1.0546875,
"learning_rate": 0.0004998531347984047,
"loss": 6.8609,
"mean_token_accuracy": 0.1177570328116417,
"num_tokens": 4197481.0,
"step": 2140
},
{
"entropy": 6.969382429122925,
"epoch": 0.21442495126705652,
"grad_norm": 1.1171875,
"learning_rate": 0.0004998518426877656,
"loss": 6.9259,
"mean_token_accuracy": 0.11888409554958343,
"num_tokens": 4207187.0,
"step": 2145
},
{
"entropy": 6.892043972015381,
"epoch": 0.2149247763282851,
"grad_norm": 1.09375,
"learning_rate": 0.0004998505449199122,
"loss": 6.8765,
"mean_token_accuracy": 0.12126196175813675,
"num_tokens": 4216485.0,
"step": 2150
},
{
"entropy": 6.897071361541748,
"epoch": 0.21542460138951366,
"grad_norm": 0.953125,
"learning_rate": 0.0004998492414948768,
"loss": 6.9547,
"mean_token_accuracy": 0.11528969705104827,
"num_tokens": 4228268.0,
"step": 2155
},
{
"entropy": 6.907302045822144,
"epoch": 0.21592442645074225,
"grad_norm": 1.03125,
"learning_rate": 0.0004998479324126924,
"loss": 6.7986,
"mean_token_accuracy": 0.12409409955143928,
"num_tokens": 4237755.0,
"step": 2160
},
{
"entropy": 6.982002592086792,
"epoch": 0.2164242515119708,
"grad_norm": 1.1328125,
"learning_rate": 0.0004998466176733918,
"loss": 6.932,
"mean_token_accuracy": 0.11655529513955117,
"num_tokens": 4247571.0,
"step": 2165
},
{
"entropy": 6.855451440811157,
"epoch": 0.21692407657319937,
"grad_norm": 1.03125,
"learning_rate": 0.0004998452972770082,
"loss": 6.8754,
"mean_token_accuracy": 0.11860855519771576,
"num_tokens": 4257003.0,
"step": 2170
},
{
"entropy": 6.956232166290283,
"epoch": 0.21742390163442796,
"grad_norm": 0.90625,
"learning_rate": 0.0004998439712235747,
"loss": 6.9122,
"mean_token_accuracy": 0.11430383697152138,
"num_tokens": 4266412.0,
"step": 2175
},
{
"entropy": 6.937617540359497,
"epoch": 0.21792372669565652,
"grad_norm": 1.1953125,
"learning_rate": 0.0004998426395131248,
"loss": 6.8452,
"mean_token_accuracy": 0.11389510557055474,
"num_tokens": 4276361.0,
"step": 2180
},
{
"entropy": 6.936740159988403,
"epoch": 0.2184235517568851,
"grad_norm": 1.078125,
"learning_rate": 0.0004998413021456919,
"loss": 6.8528,
"mean_token_accuracy": 0.12202164232730865,
"num_tokens": 4285815.0,
"step": 2185
},
{
"entropy": 6.907345581054687,
"epoch": 0.21892337681811366,
"grad_norm": 1.046875,
"learning_rate": 0.0004998399591213098,
"loss": 6.8365,
"mean_token_accuracy": 0.11947793588042259,
"num_tokens": 4296071.0,
"step": 2190
},
{
"entropy": 6.901845836639405,
"epoch": 0.21942320187934222,
"grad_norm": 1.1484375,
"learning_rate": 0.0004998386104400122,
"loss": 6.8387,
"mean_token_accuracy": 0.12116138637065887,
"num_tokens": 4306476.0,
"step": 2195
},
{
"entropy": 6.931117963790894,
"epoch": 0.2199230269405708,
"grad_norm": 1.046875,
"learning_rate": 0.0004998372561018329,
"loss": 6.8856,
"mean_token_accuracy": 0.11641964539885521,
"num_tokens": 4316312.0,
"step": 2200
},
{
"entropy": 6.847039604187012,
"epoch": 0.22042285200179937,
"grad_norm": 1.0390625,
"learning_rate": 0.0004998358961068062,
"loss": 6.7863,
"mean_token_accuracy": 0.12805279418826104,
"num_tokens": 4325443.0,
"step": 2205
},
{
"entropy": 6.916587829589844,
"epoch": 0.22092267706302793,
"grad_norm": 1.203125,
"learning_rate": 0.0004998345304549661,
"loss": 6.8401,
"mean_token_accuracy": 0.11731385514140129,
"num_tokens": 4334354.0,
"step": 2210
},
{
"entropy": 6.8048478126525875,
"epoch": 0.22142250212425652,
"grad_norm": 1.1015625,
"learning_rate": 0.0004998331591463471,
"loss": 6.7509,
"mean_token_accuracy": 0.12133458405733108,
"num_tokens": 4344714.0,
"step": 2215
},
{
"entropy": 6.86434965133667,
"epoch": 0.22192232718548507,
"grad_norm": 0.9375,
"learning_rate": 0.0004998317821809837,
"loss": 6.7932,
"mean_token_accuracy": 0.11775240227580071,
"num_tokens": 4354216.0,
"step": 2220
},
{
"entropy": 6.932387924194336,
"epoch": 0.22242215224671366,
"grad_norm": 0.98046875,
"learning_rate": 0.0004998303995589104,
"loss": 6.8418,
"mean_token_accuracy": 0.12000173777341842,
"num_tokens": 4364764.0,
"step": 2225
},
{
"entropy": 6.8684345245361325,
"epoch": 0.22292197730794222,
"grad_norm": 0.97265625,
"learning_rate": 0.0004998290112801623,
"loss": 6.9253,
"mean_token_accuracy": 0.11187315285205841,
"num_tokens": 4375289.0,
"step": 2230
},
{
"entropy": 6.82034010887146,
"epoch": 0.22342180236917078,
"grad_norm": 1.0390625,
"learning_rate": 0.000499827617344774,
"loss": 6.8133,
"mean_token_accuracy": 0.12498923987150193,
"num_tokens": 4384984.0,
"step": 2235
},
{
"entropy": 6.945557641983032,
"epoch": 0.22392162743039937,
"grad_norm": 1.015625,
"learning_rate": 0.0004998262177527807,
"loss": 6.795,
"mean_token_accuracy": 0.12080412805080414,
"num_tokens": 4393321.0,
"step": 2240
},
{
"entropy": 6.814831018447876,
"epoch": 0.22442145249162793,
"grad_norm": 0.95703125,
"learning_rate": 0.0004998248125042177,
"loss": 6.87,
"mean_token_accuracy": 0.11272740364074707,
"num_tokens": 4404908.0,
"step": 2245
},
{
"entropy": 7.018628549575806,
"epoch": 0.2249212775528565,
"grad_norm": 0.96484375,
"learning_rate": 0.0004998234015991202,
"loss": 6.9487,
"mean_token_accuracy": 0.1148961141705513,
"num_tokens": 4415530.0,
"step": 2250
},
{
"entropy": 6.964756965637207,
"epoch": 0.22542110261408507,
"grad_norm": 0.98046875,
"learning_rate": 0.0004998219850375238,
"loss": 6.8654,
"mean_token_accuracy": 0.11356062963604927,
"num_tokens": 4425678.0,
"step": 2255
},
{
"entropy": 6.778150987625122,
"epoch": 0.22592092767531363,
"grad_norm": 0.9921875,
"learning_rate": 0.0004998205628194641,
"loss": 6.8267,
"mean_token_accuracy": 0.11817835196852684,
"num_tokens": 4436890.0,
"step": 2260
},
{
"entropy": 6.915167760848999,
"epoch": 0.22642075273654222,
"grad_norm": 1.6171875,
"learning_rate": 0.0004998191349449768,
"loss": 6.6857,
"mean_token_accuracy": 0.12716825529932976,
"num_tokens": 4446947.0,
"step": 2265
},
{
"entropy": 6.998455286026001,
"epoch": 0.22692057779777078,
"grad_norm": 0.97265625,
"learning_rate": 0.0004998177014140981,
"loss": 6.8669,
"mean_token_accuracy": 0.12382732853293418,
"num_tokens": 4457052.0,
"step": 2270
},
{
"entropy": 6.763993167877198,
"epoch": 0.22742040285899934,
"grad_norm": 1.0703125,
"learning_rate": 0.0004998162622268637,
"loss": 6.7014,
"mean_token_accuracy": 0.12646981552243233,
"num_tokens": 4466171.0,
"step": 2275
},
{
"entropy": 6.834669017791748,
"epoch": 0.22792022792022792,
"grad_norm": 1.1328125,
"learning_rate": 0.0004998148173833101,
"loss": 6.9205,
"mean_token_accuracy": 0.11530092284083367,
"num_tokens": 4476147.0,
"step": 2280
},
{
"entropy": 6.9172093868255615,
"epoch": 0.22842005298145648,
"grad_norm": 1.1171875,
"learning_rate": 0.0004998133668834735,
"loss": 6.8285,
"mean_token_accuracy": 0.1202719822525978,
"num_tokens": 4485786.0,
"step": 2285
},
{
"entropy": 6.892522478103638,
"epoch": 0.22891987804268507,
"grad_norm": 0.96484375,
"learning_rate": 0.0004998119107273905,
"loss": 6.8783,
"mean_token_accuracy": 0.12116087898612023,
"num_tokens": 4495376.0,
"step": 2290
},
{
"entropy": 6.980706357955933,
"epoch": 0.22941970310391363,
"grad_norm": 1.3046875,
"learning_rate": 0.0004998104489150975,
"loss": 6.8384,
"mean_token_accuracy": 0.11390652880072594,
"num_tokens": 4504500.0,
"step": 2295
},
{
"entropy": 6.80579104423523,
"epoch": 0.2299195281651422,
"grad_norm": 0.953125,
"learning_rate": 0.0004998089814466318,
"loss": 6.9246,
"mean_token_accuracy": 0.11344198286533355,
"num_tokens": 4514842.0,
"step": 2300
},
{
"entropy": 6.911924409866333,
"epoch": 0.23041935322637078,
"grad_norm": 1.1640625,
"learning_rate": 0.0004998075083220295,
"loss": 6.787,
"mean_token_accuracy": 0.12299882918596268,
"num_tokens": 4523794.0,
"step": 2305
},
{
"entropy": 6.934869241714478,
"epoch": 0.23091917828759934,
"grad_norm": 1.0,
"learning_rate": 0.0004998060295413286,
"loss": 6.8514,
"mean_token_accuracy": 0.11584107503294945,
"num_tokens": 4533315.0,
"step": 2310
},
{
"entropy": 6.789450931549072,
"epoch": 0.23141900334882792,
"grad_norm": 1.0078125,
"learning_rate": 0.0004998045451045656,
"loss": 6.7111,
"mean_token_accuracy": 0.1275709204375744,
"num_tokens": 4542996.0,
"step": 2315
},
{
"entropy": 6.862829113006592,
"epoch": 0.23191882841005648,
"grad_norm": 0.97265625,
"learning_rate": 0.0004998030550117782,
"loss": 6.7841,
"mean_token_accuracy": 0.12046822234988212,
"num_tokens": 4552719.0,
"step": 2320
},
{
"entropy": 6.794938373565674,
"epoch": 0.23241865347128504,
"grad_norm": 0.9921875,
"learning_rate": 0.0004998015592630037,
"loss": 6.7181,
"mean_token_accuracy": 0.12457696348428726,
"num_tokens": 4562040.0,
"step": 2325
},
{
"entropy": 6.7735360622406,
"epoch": 0.23291847853251363,
"grad_norm": 1.0625,
"learning_rate": 0.0004998000578582798,
"loss": 6.7695,
"mean_token_accuracy": 0.1228984922170639,
"num_tokens": 4570855.0,
"step": 2330
},
{
"entropy": 6.912277126312256,
"epoch": 0.2334183035937422,
"grad_norm": 1.03125,
"learning_rate": 0.0004997985507976443,
"loss": 6.8861,
"mean_token_accuracy": 0.11459040716290474,
"num_tokens": 4581814.0,
"step": 2335
},
{
"entropy": 6.869301176071167,
"epoch": 0.23391812865497075,
"grad_norm": 1.046875,
"learning_rate": 0.0004997970380811351,
"loss": 6.785,
"mean_token_accuracy": 0.12393666356801987,
"num_tokens": 4590731.0,
"step": 2340
},
{
"entropy": 6.845894432067871,
"epoch": 0.23441795371619933,
"grad_norm": 0.9296875,
"learning_rate": 0.0004997955197087904,
"loss": 6.7703,
"mean_token_accuracy": 0.11945929154753684,
"num_tokens": 4600440.0,
"step": 2345
},
{
"entropy": 6.842683792114258,
"epoch": 0.2349177787774279,
"grad_norm": 1.0546875,
"learning_rate": 0.0004997939956806481,
"loss": 6.774,
"mean_token_accuracy": 0.12290067374706268,
"num_tokens": 4609510.0,
"step": 2350
},
{
"entropy": 6.863666009902954,
"epoch": 0.23541760383865648,
"grad_norm": 0.95703125,
"learning_rate": 0.0004997924659967467,
"loss": 6.8539,
"mean_token_accuracy": 0.11659590974450111,
"num_tokens": 4620481.0,
"step": 2355
},
{
"entropy": 6.893025636672974,
"epoch": 0.23591742889988504,
"grad_norm": 1.125,
"learning_rate": 0.0004997909306571248,
"loss": 6.7085,
"mean_token_accuracy": 0.12738291099667548,
"num_tokens": 4629388.0,
"step": 2360
},
{
"entropy": 6.7053995609283445,
"epoch": 0.2364172539611136,
"grad_norm": 1.109375,
"learning_rate": 0.0004997893896618209,
"loss": 6.7177,
"mean_token_accuracy": 0.1286756858229637,
"num_tokens": 4638429.0,
"step": 2365
},
{
"entropy": 6.883879661560059,
"epoch": 0.2369170790223422,
"grad_norm": 0.91015625,
"learning_rate": 0.0004997878430108738,
"loss": 6.845,
"mean_token_accuracy": 0.1211053729057312,
"num_tokens": 4648995.0,
"step": 2370
},
{
"entropy": 6.898133850097656,
"epoch": 0.23741690408357075,
"grad_norm": 1.0078125,
"learning_rate": 0.0004997862907043224,
"loss": 6.7398,
"mean_token_accuracy": 0.11961732506752014,
"num_tokens": 4658584.0,
"step": 2375
},
{
"entropy": 6.765787029266358,
"epoch": 0.23791672914479933,
"grad_norm": 1.0078125,
"learning_rate": 0.0004997847327422059,
"loss": 6.7737,
"mean_token_accuracy": 0.12453893274068832,
"num_tokens": 4668859.0,
"step": 2380
},
{
"entropy": 6.8678569316864015,
"epoch": 0.2384165542060279,
"grad_norm": 0.93359375,
"learning_rate": 0.0004997831691245632,
"loss": 6.825,
"mean_token_accuracy": 0.11157805621623992,
"num_tokens": 4678389.0,
"step": 2385
},
{
"entropy": 6.839744949340821,
"epoch": 0.23891637926725645,
"grad_norm": 0.9453125,
"learning_rate": 0.0004997815998514337,
"loss": 6.8357,
"mean_token_accuracy": 0.1212715081870556,
"num_tokens": 4688763.0,
"step": 2390
},
{
"entropy": 6.8042905807495115,
"epoch": 0.23941620432848504,
"grad_norm": 1.1015625,
"learning_rate": 0.0004997800249228572,
"loss": 6.7007,
"mean_token_accuracy": 0.12444251105189323,
"num_tokens": 4698180.0,
"step": 2395
},
{
"entropy": 6.778486728668213,
"epoch": 0.2399160293897136,
"grad_norm": 0.91796875,
"learning_rate": 0.0004997784443388732,
"loss": 6.6789,
"mean_token_accuracy": 0.1236902080476284,
"num_tokens": 4708111.0,
"step": 2400
},
{
"entropy": 6.81549825668335,
"epoch": 0.24041585445094216,
"grad_norm": 1.140625,
"learning_rate": 0.0004997768580995212,
"loss": 6.8155,
"mean_token_accuracy": 0.1198317751288414,
"num_tokens": 4717247.0,
"step": 2405
},
{
"entropy": 6.83826060295105,
"epoch": 0.24091567951217074,
"grad_norm": 1.0390625,
"learning_rate": 0.0004997752662048413,
"loss": 6.7476,
"mean_token_accuracy": 0.12130436301231384,
"num_tokens": 4727062.0,
"step": 2410
},
{
"entropy": 6.770843982696533,
"epoch": 0.2414155045733993,
"grad_norm": 1.046875,
"learning_rate": 0.0004997736686548736,
"loss": 6.6909,
"mean_token_accuracy": 0.13135136663913727,
"num_tokens": 4735806.0,
"step": 2415
},
{
"entropy": 6.909219455718994,
"epoch": 0.2419153296346279,
"grad_norm": 1.0,
"learning_rate": 0.0004997720654496582,
"loss": 6.8409,
"mean_token_accuracy": 0.11559810191392898,
"num_tokens": 4745246.0,
"step": 2420
},
{
"entropy": 6.834303331375122,
"epoch": 0.24241515469585645,
"grad_norm": 1.0234375,
"learning_rate": 0.0004997704565892355,
"loss": 6.7325,
"mean_token_accuracy": 0.12480264231562614,
"num_tokens": 4754867.0,
"step": 2425
},
{
"entropy": 6.803612899780274,
"epoch": 0.242914979757085,
"grad_norm": 1.015625,
"learning_rate": 0.0004997688420736459,
"loss": 6.8049,
"mean_token_accuracy": 0.12716324329376222,
"num_tokens": 4764418.0,
"step": 2430
},
{
"entropy": 6.777321815490723,
"epoch": 0.2434148048183136,
"grad_norm": 1.046875,
"learning_rate": 0.0004997672219029301,
"loss": 6.7701,
"mean_token_accuracy": 0.11963262781500816,
"num_tokens": 4774137.0,
"step": 2435
},
{
"entropy": 6.8135435581207275,
"epoch": 0.24391462987954216,
"grad_norm": 1.125,
"learning_rate": 0.0004997655960771288,
"loss": 6.8014,
"mean_token_accuracy": 0.12224104627966881,
"num_tokens": 4784503.0,
"step": 2440
},
{
"entropy": 6.83231143951416,
"epoch": 0.24441445494077074,
"grad_norm": 0.9765625,
"learning_rate": 0.000499763964596283,
"loss": 6.8487,
"mean_token_accuracy": 0.11832178011536598,
"num_tokens": 4795847.0,
"step": 2445
},
{
"entropy": 6.819264650344849,
"epoch": 0.2449142800019993,
"grad_norm": 1.109375,
"learning_rate": 0.0004997623274604336,
"loss": 6.7086,
"mean_token_accuracy": 0.1282437562942505,
"num_tokens": 4805230.0,
"step": 2450
},
{
"entropy": 6.745674896240234,
"epoch": 0.24541410506322786,
"grad_norm": 0.96875,
"learning_rate": 0.000499760684669622,
"loss": 6.6627,
"mean_token_accuracy": 0.1251753568649292,
"num_tokens": 4815345.0,
"step": 2455
},
{
"entropy": 6.792028522491455,
"epoch": 0.24591393012445645,
"grad_norm": 1.09375,
"learning_rate": 0.0004997590362238894,
"loss": 6.7252,
"mean_token_accuracy": 0.12097799107432365,
"num_tokens": 4824819.0,
"step": 2460
},
{
"entropy": 6.798549795150757,
"epoch": 0.246413755185685,
"grad_norm": 0.95703125,
"learning_rate": 0.0004997573821232772,
"loss": 6.7776,
"mean_token_accuracy": 0.12377737537026405,
"num_tokens": 4834339.0,
"step": 2465
},
{
"entropy": 6.775806903839111,
"epoch": 0.24691358024691357,
"grad_norm": 1.078125,
"learning_rate": 0.0004997557223678272,
"loss": 6.746,
"mean_token_accuracy": 0.12383496910333633,
"num_tokens": 4844440.0,
"step": 2470
},
{
"entropy": 6.874798965454102,
"epoch": 0.24741340530814215,
"grad_norm": 1.0546875,
"learning_rate": 0.0004997540569575809,
"loss": 6.7441,
"mean_token_accuracy": 0.11938895136117936,
"num_tokens": 4854688.0,
"step": 2475
},
{
"entropy": 6.734471464157105,
"epoch": 0.2479132303693707,
"grad_norm": 0.9765625,
"learning_rate": 0.0004997523858925805,
"loss": 6.7423,
"mean_token_accuracy": 0.1235843650996685,
"num_tokens": 4864629.0,
"step": 2480
},
{
"entropy": 6.783338022232056,
"epoch": 0.2484130554305993,
"grad_norm": 1.046875,
"learning_rate": 0.0004997507091728678,
"loss": 6.7186,
"mean_token_accuracy": 0.12358858436346054,
"num_tokens": 4873693.0,
"step": 2485
},
{
"entropy": 6.776330995559692,
"epoch": 0.24891288049182786,
"grad_norm": 0.984375,
"learning_rate": 0.0004997490267984853,
"loss": 6.6959,
"mean_token_accuracy": 0.127644382417202,
"num_tokens": 4882640.0,
"step": 2490
},
{
"entropy": 6.767954730987549,
"epoch": 0.24941270555305642,
"grad_norm": 1.2734375,
"learning_rate": 0.0004997473387694749,
"loss": 6.7975,
"mean_token_accuracy": 0.11814235299825668,
"num_tokens": 4893452.0,
"step": 2495
},
{
"entropy": 6.799860954284668,
"epoch": 0.249912530614285,
"grad_norm": 1.109375,
"learning_rate": 0.0004997456450858793,
"loss": 6.8177,
"mean_token_accuracy": 0.11675577834248543,
"num_tokens": 4902949.0,
"step": 2500
},
{
"entropy": 6.891696548461914,
"epoch": 0.25041235567551356,
"grad_norm": 1.125,
"learning_rate": 0.0004997439457477412,
"loss": 6.7823,
"mean_token_accuracy": 0.11894313916563988,
"num_tokens": 4912748.0,
"step": 2505
},
{
"entropy": 6.8100135803222654,
"epoch": 0.25091218073674215,
"grad_norm": 1.0234375,
"learning_rate": 0.0004997422407551032,
"loss": 6.7257,
"mean_token_accuracy": 0.12602523788809777,
"num_tokens": 4922405.0,
"step": 2510
},
{
"entropy": 6.72805871963501,
"epoch": 0.2514120057979707,
"grad_norm": 0.99609375,
"learning_rate": 0.0004997405301080082,
"loss": 6.7064,
"mean_token_accuracy": 0.12541015595197677,
"num_tokens": 4931826.0,
"step": 2515
},
{
"entropy": 6.752864646911621,
"epoch": 0.25191183085919927,
"grad_norm": 1.0,
"learning_rate": 0.0004997388138064994,
"loss": 6.773,
"mean_token_accuracy": 0.12637126743793486,
"num_tokens": 4942165.0,
"step": 2520
},
{
"entropy": 6.872462368011474,
"epoch": 0.25241165592042786,
"grad_norm": 1.0078125,
"learning_rate": 0.0004997370918506198,
"loss": 6.7321,
"mean_token_accuracy": 0.11997186169028282,
"num_tokens": 4951287.0,
"step": 2525
},
{
"entropy": 6.76559042930603,
"epoch": 0.25291148098165644,
"grad_norm": 1.0625,
"learning_rate": 0.0004997353642404129,
"loss": 6.6975,
"mean_token_accuracy": 0.12422825694084168,
"num_tokens": 4960452.0,
"step": 2530
},
{
"entropy": 6.764957475662231,
"epoch": 0.253411306042885,
"grad_norm": 1.1015625,
"learning_rate": 0.0004997336309759219,
"loss": 6.7601,
"mean_token_accuracy": 0.12294914424419404,
"num_tokens": 4971310.0,
"step": 2535
},
{
"entropy": 6.915872573852539,
"epoch": 0.25391113110411356,
"grad_norm": 1.0234375,
"learning_rate": 0.0004997318920571907,
"loss": 6.7266,
"mean_token_accuracy": 0.12278066650032997,
"num_tokens": 4980609.0,
"step": 2540
},
{
"entropy": 6.753065395355224,
"epoch": 0.25441095616534215,
"grad_norm": 1.03125,
"learning_rate": 0.000499730147484263,
"loss": 6.7388,
"mean_token_accuracy": 0.12710461020469666,
"num_tokens": 4989991.0,
"step": 2545
},
{
"entropy": 6.74550838470459,
"epoch": 0.2549107812265707,
"grad_norm": 1.0390625,
"learning_rate": 0.0004997283972571824,
"loss": 6.7283,
"mean_token_accuracy": 0.12032875418663025,
"num_tokens": 5000493.0,
"step": 2550
},
{
"entropy": 6.821319437026977,
"epoch": 0.25541060628779927,
"grad_norm": 1.0234375,
"learning_rate": 0.0004997266413759934,
"loss": 6.8219,
"mean_token_accuracy": 0.12391160577535629,
"num_tokens": 5010496.0,
"step": 2555
},
{
"entropy": 6.91074390411377,
"epoch": 0.25591043134902786,
"grad_norm": 1.0625,
"learning_rate": 0.0004997248798407397,
"loss": 6.8677,
"mean_token_accuracy": 0.11413910016417503,
"num_tokens": 5020783.0,
"step": 2560
},
{
"entropy": 6.725059556961059,
"epoch": 0.2564102564102564,
"grad_norm": 1.109375,
"learning_rate": 0.0004997231126514659,
"loss": 6.7697,
"mean_token_accuracy": 0.12141788229346276,
"num_tokens": 5029939.0,
"step": 2565
},
{
"entropy": 6.9148595333099365,
"epoch": 0.256910081471485,
"grad_norm": 1.0390625,
"learning_rate": 0.0004997213398082165,
"loss": 6.7619,
"mean_token_accuracy": 0.12135729119181633,
"num_tokens": 5039491.0,
"step": 2570
},
{
"entropy": 6.8569738388061525,
"epoch": 0.25740990653271356,
"grad_norm": 0.99609375,
"learning_rate": 0.000499719561311036,
"loss": 6.7675,
"mean_token_accuracy": 0.12060310840606689,
"num_tokens": 5049780.0,
"step": 2575
},
{
"entropy": 6.771124410629272,
"epoch": 0.2579097315939421,
"grad_norm": 1.03125,
"learning_rate": 0.0004997177771599691,
"loss": 6.7195,
"mean_token_accuracy": 0.12665437906980515,
"num_tokens": 5058986.0,
"step": 2580
},
{
"entropy": 6.762947845458984,
"epoch": 0.2584095566551707,
"grad_norm": 1.0859375,
"learning_rate": 0.0004997159873550607,
"loss": 6.6629,
"mean_token_accuracy": 0.1242829754948616,
"num_tokens": 5068269.0,
"step": 2585
},
{
"entropy": 6.781703472137451,
"epoch": 0.25890938171639927,
"grad_norm": 1.0234375,
"learning_rate": 0.0004997141918963561,
"loss": 6.7982,
"mean_token_accuracy": 0.11847331300377846,
"num_tokens": 5078674.0,
"step": 2590
},
{
"entropy": 6.817697381973266,
"epoch": 0.25940920677762785,
"grad_norm": 0.96875,
"learning_rate": 0.0004997123907839001,
"loss": 6.7285,
"mean_token_accuracy": 0.1285196512937546,
"num_tokens": 5087599.0,
"step": 2595
},
{
"entropy": 6.75245213508606,
"epoch": 0.2599090318388564,
"grad_norm": 1.078125,
"learning_rate": 0.0004997105840177381,
"loss": 6.6444,
"mean_token_accuracy": 0.12771404534578323,
"num_tokens": 5097418.0,
"step": 2600
},
{
"entropy": 6.720393276214599,
"epoch": 0.260408856900085,
"grad_norm": 1.015625,
"learning_rate": 0.0004997087715979157,
"loss": 6.7088,
"mean_token_accuracy": 0.12440732717514039,
"num_tokens": 5108248.0,
"step": 2605
},
{
"entropy": 6.849985408782959,
"epoch": 0.26090868196131356,
"grad_norm": 1.125,
"learning_rate": 0.0004997069535244785,
"loss": 6.6605,
"mean_token_accuracy": 0.12989854514598848,
"num_tokens": 5118284.0,
"step": 2610
},
{
"entropy": 6.731876516342163,
"epoch": 0.2614085070225421,
"grad_norm": 0.9921875,
"learning_rate": 0.0004997051297974722,
"loss": 6.8218,
"mean_token_accuracy": 0.12219112440943718,
"num_tokens": 5128485.0,
"step": 2615
},
{
"entropy": 6.833446025848389,
"epoch": 0.2619083320837707,
"grad_norm": 1.0234375,
"learning_rate": 0.0004997033004169425,
"loss": 6.745,
"mean_token_accuracy": 0.11980004459619523,
"num_tokens": 5138058.0,
"step": 2620
},
{
"entropy": 6.705493688583374,
"epoch": 0.26240815714499927,
"grad_norm": 1.0,
"learning_rate": 0.0004997014653829357,
"loss": 6.6385,
"mean_token_accuracy": 0.1275268502533436,
"num_tokens": 5148555.0,
"step": 2625
},
{
"entropy": 6.7973309516906735,
"epoch": 0.2629079822062278,
"grad_norm": 0.921875,
"learning_rate": 0.0004996996246954977,
"loss": 6.8189,
"mean_token_accuracy": 0.11919309869408608,
"num_tokens": 5158729.0,
"step": 2630
},
{
"entropy": 6.896182250976563,
"epoch": 0.2634078072674564,
"grad_norm": 0.97265625,
"learning_rate": 0.0004996977783546752,
"loss": 6.8511,
"mean_token_accuracy": 0.11748289540410042,
"num_tokens": 5168900.0,
"step": 2635
},
{
"entropy": 6.777275085449219,
"epoch": 0.26390763232868497,
"grad_norm": 1.046875,
"learning_rate": 0.0004996959263605143,
"loss": 6.7687,
"mean_token_accuracy": 0.11863479912281036,
"num_tokens": 5179742.0,
"step": 2640
},
{
"entropy": 6.876881885528564,
"epoch": 0.2644074573899135,
"grad_norm": 1.0234375,
"learning_rate": 0.0004996940687130617,
"loss": 6.7661,
"mean_token_accuracy": 0.1250888466835022,
"num_tokens": 5190221.0,
"step": 2645
},
{
"entropy": 6.781659746170044,
"epoch": 0.2649072824511421,
"grad_norm": 0.953125,
"learning_rate": 0.0004996922054123641,
"loss": 6.7396,
"mean_token_accuracy": 0.12349513024091721,
"num_tokens": 5200252.0,
"step": 2650
},
{
"entropy": 6.696864986419678,
"epoch": 0.2654071075123707,
"grad_norm": 1.09375,
"learning_rate": 0.0004996903364584685,
"loss": 6.6989,
"mean_token_accuracy": 0.1287691190838814,
"num_tokens": 5209388.0,
"step": 2655
},
{
"entropy": 6.807218217849732,
"epoch": 0.26590693257359926,
"grad_norm": 0.98828125,
"learning_rate": 0.0004996884618514219,
"loss": 6.6763,
"mean_token_accuracy": 0.12565898299217224,
"num_tokens": 5219806.0,
"step": 2660
},
{
"entropy": 6.739374589920044,
"epoch": 0.2664067576348278,
"grad_norm": 0.984375,
"learning_rate": 0.0004996865815912713,
"loss": 6.7091,
"mean_token_accuracy": 0.1312312088906765,
"num_tokens": 5229485.0,
"step": 2665
},
{
"entropy": 6.822212362289429,
"epoch": 0.2669065826960564,
"grad_norm": 1.0703125,
"learning_rate": 0.0004996846956780642,
"loss": 6.6959,
"mean_token_accuracy": 0.12174614071846009,
"num_tokens": 5238922.0,
"step": 2670
},
{
"entropy": 6.74418044090271,
"epoch": 0.26740640775728497,
"grad_norm": 1.0703125,
"learning_rate": 0.000499682804111848,
"loss": 6.6966,
"mean_token_accuracy": 0.1255224473774433,
"num_tokens": 5248391.0,
"step": 2675
},
{
"entropy": 6.749328470230102,
"epoch": 0.2679062328185135,
"grad_norm": 1.0703125,
"learning_rate": 0.0004996809068926702,
"loss": 6.7147,
"mean_token_accuracy": 0.11848349198698997,
"num_tokens": 5257605.0,
"step": 2680
},
{
"entropy": 6.922802114486695,
"epoch": 0.2684060578797421,
"grad_norm": 1.140625,
"learning_rate": 0.0004996790040205786,
"loss": 6.8072,
"mean_token_accuracy": 0.12140284031629563,
"num_tokens": 5266808.0,
"step": 2685
},
{
"entropy": 6.742965745925903,
"epoch": 0.2689058829409707,
"grad_norm": 1.1171875,
"learning_rate": 0.0004996770954956211,
"loss": 6.6396,
"mean_token_accuracy": 0.12836444452404977,
"num_tokens": 5276471.0,
"step": 2690
},
{
"entropy": 6.656261253356933,
"epoch": 0.2694057080021992,
"grad_norm": 0.9296875,
"learning_rate": 0.0004996751813178456,
"loss": 6.6459,
"mean_token_accuracy": 0.12415419071912766,
"num_tokens": 5285312.0,
"step": 2695
},
{
"entropy": 6.784100151062011,
"epoch": 0.2699055330634278,
"grad_norm": 0.98828125,
"learning_rate": 0.0004996732614873005,
"loss": 6.7723,
"mean_token_accuracy": 0.11762264221906663,
"num_tokens": 5295608.0,
"step": 2700
},
{
"entropy": 6.837291526794433,
"epoch": 0.2704053581246564,
"grad_norm": 1.0234375,
"learning_rate": 0.0004996713360040339,
"loss": 6.7089,
"mean_token_accuracy": 0.12051343023777009,
"num_tokens": 5305181.0,
"step": 2705
},
{
"entropy": 6.760000276565552,
"epoch": 0.27090518318588497,
"grad_norm": 1.0234375,
"learning_rate": 0.0004996694048680942,
"loss": 6.7168,
"mean_token_accuracy": 0.11832475885748864,
"num_tokens": 5314706.0,
"step": 2710
},
{
"entropy": 6.771784496307373,
"epoch": 0.2714050082471135,
"grad_norm": 1.0703125,
"learning_rate": 0.0004996674680795302,
"loss": 6.6436,
"mean_token_accuracy": 0.12209197878837585,
"num_tokens": 5324207.0,
"step": 2715
},
{
"entropy": 6.7553201675415036,
"epoch": 0.2719048333083421,
"grad_norm": 1.046875,
"learning_rate": 0.0004996655256383905,
"loss": 6.7058,
"mean_token_accuracy": 0.12452286705374718,
"num_tokens": 5333554.0,
"step": 2720
},
{
"entropy": 6.809931802749634,
"epoch": 0.2724046583695707,
"grad_norm": 1.2421875,
"learning_rate": 0.000499663577544724,
"loss": 6.7933,
"mean_token_accuracy": 0.12039531022310257,
"num_tokens": 5343811.0,
"step": 2725
},
{
"entropy": 6.77467360496521,
"epoch": 0.2729044834307992,
"grad_norm": 1.1015625,
"learning_rate": 0.0004996616237985796,
"loss": 6.7307,
"mean_token_accuracy": 0.12147506698966026,
"num_tokens": 5353980.0,
"step": 2730
},
{
"entropy": 6.783198595046997,
"epoch": 0.2734043084920278,
"grad_norm": 1.0625,
"learning_rate": 0.0004996596644000066,
"loss": 6.7045,
"mean_token_accuracy": 0.12822512909770012,
"num_tokens": 5363681.0,
"step": 2735
},
{
"entropy": 6.7205146789550785,
"epoch": 0.2739041335532564,
"grad_norm": 1.0234375,
"learning_rate": 0.0004996576993490543,
"loss": 6.6347,
"mean_token_accuracy": 0.1307567574083805,
"num_tokens": 5373855.0,
"step": 2740
},
{
"entropy": 6.799875783920288,
"epoch": 0.2744039586144849,
"grad_norm": 0.9375,
"learning_rate": 0.0004996557286457721,
"loss": 6.6961,
"mean_token_accuracy": 0.12730289548635482,
"num_tokens": 5383831.0,
"step": 2745
},
{
"entropy": 6.746462345123291,
"epoch": 0.2749037836757135,
"grad_norm": 1.125,
"learning_rate": 0.0004996537522902096,
"loss": 6.7273,
"mean_token_accuracy": 0.12303572297096252,
"num_tokens": 5392247.0,
"step": 2750
},
{
"entropy": 6.783823299407959,
"epoch": 0.2754036087369421,
"grad_norm": 1.0234375,
"learning_rate": 0.0004996517702824163,
"loss": 6.6701,
"mean_token_accuracy": 0.12064638286828995,
"num_tokens": 5401091.0,
"step": 2755
},
{
"entropy": 6.716385412216186,
"epoch": 0.2759034337981706,
"grad_norm": 1.1015625,
"learning_rate": 0.0004996497826224425,
"loss": 6.6708,
"mean_token_accuracy": 0.12038891389966011,
"num_tokens": 5409809.0,
"step": 2760
},
{
"entropy": 6.699102449417114,
"epoch": 0.2764032588593992,
"grad_norm": 1.03125,
"learning_rate": 0.0004996477893103379,
"loss": 6.6376,
"mean_token_accuracy": 0.12431047409772873,
"num_tokens": 5420104.0,
"step": 2765
},
{
"entropy": 6.762558364868164,
"epoch": 0.2769030839206278,
"grad_norm": 1.1953125,
"learning_rate": 0.0004996457903461527,
"loss": 6.679,
"mean_token_accuracy": 0.1296892248094082,
"num_tokens": 5427905.0,
"step": 2770
},
{
"entropy": 6.644171094894409,
"epoch": 0.2774029089818564,
"grad_norm": 0.9609375,
"learning_rate": 0.0004996437857299373,
"loss": 6.6837,
"mean_token_accuracy": 0.1241793692111969,
"num_tokens": 5438537.0,
"step": 2775
},
{
"entropy": 6.750694274902344,
"epoch": 0.2779027340430849,
"grad_norm": 1.1640625,
"learning_rate": 0.000499641775461742,
"loss": 6.7575,
"mean_token_accuracy": 0.11740487441420555,
"num_tokens": 5447622.0,
"step": 2780
},
{
"entropy": 6.782175016403198,
"epoch": 0.2784025591043135,
"grad_norm": 1.1640625,
"learning_rate": 0.0004996397595416173,
"loss": 6.6512,
"mean_token_accuracy": 0.12953489869832993,
"num_tokens": 5457407.0,
"step": 2785
},
{
"entropy": 6.708248949050903,
"epoch": 0.2789023841655421,
"grad_norm": 0.99609375,
"learning_rate": 0.0004996377379696143,
"loss": 6.6579,
"mean_token_accuracy": 0.1291919894516468,
"num_tokens": 5467187.0,
"step": 2790
},
{
"entropy": 6.750952816009521,
"epoch": 0.2794022092267706,
"grad_norm": 0.953125,
"learning_rate": 0.0004996357107457834,
"loss": 6.7178,
"mean_token_accuracy": 0.11987345665693283,
"num_tokens": 5477188.0,
"step": 2795
},
{
"entropy": 6.771980571746826,
"epoch": 0.2799020342879992,
"grad_norm": 0.9921875,
"learning_rate": 0.000499633677870176,
"loss": 6.6586,
"mean_token_accuracy": 0.12479908540844917,
"num_tokens": 5485851.0,
"step": 2800
},
{
"entropy": 6.677957534790039,
"epoch": 0.2804018593492278,
"grad_norm": 1.1171875,
"learning_rate": 0.0004996316393428429,
"loss": 6.7292,
"mean_token_accuracy": 0.12249960973858834,
"num_tokens": 5496415.0,
"step": 2805
},
{
"entropy": 6.791005992889405,
"epoch": 0.2809016844104563,
"grad_norm": 1.109375,
"learning_rate": 0.0004996295951638357,
"loss": 6.6295,
"mean_token_accuracy": 0.12775769904255868,
"num_tokens": 5505538.0,
"step": 2810
},
{
"entropy": 6.640494632720947,
"epoch": 0.2814015094716849,
"grad_norm": 1.1015625,
"learning_rate": 0.0004996275453332057,
"loss": 6.7225,
"mean_token_accuracy": 0.12422475144267082,
"num_tokens": 5514608.0,
"step": 2815
},
{
"entropy": 6.744523715972901,
"epoch": 0.2819013345329135,
"grad_norm": 0.98046875,
"learning_rate": 0.0004996254898510043,
"loss": 6.6858,
"mean_token_accuracy": 0.12396883815526963,
"num_tokens": 5523935.0,
"step": 2820
},
{
"entropy": 6.709538793563842,
"epoch": 0.282401159594142,
"grad_norm": 0.98046875,
"learning_rate": 0.0004996234287172835,
"loss": 6.6203,
"mean_token_accuracy": 0.13199909776449203,
"num_tokens": 5534393.0,
"step": 2825
},
{
"entropy": 6.747164535522461,
"epoch": 0.2829009846553706,
"grad_norm": 1.0625,
"learning_rate": 0.000499621361932095,
"loss": 6.6333,
"mean_token_accuracy": 0.12683428451418877,
"num_tokens": 5543414.0,
"step": 2830
},
{
"entropy": 6.645808696746826,
"epoch": 0.2834008097165992,
"grad_norm": 0.9296875,
"learning_rate": 0.0004996192894954909,
"loss": 6.645,
"mean_token_accuracy": 0.12200098410248757,
"num_tokens": 5553742.0,
"step": 2835
},
{
"entropy": 6.673884487152099,
"epoch": 0.2839006347778278,
"grad_norm": 1.1796875,
"learning_rate": 0.0004996172114075232,
"loss": 6.5438,
"mean_token_accuracy": 0.14016968458890916,
"num_tokens": 5562092.0,
"step": 2840
},
{
"entropy": 6.776102590560913,
"epoch": 0.2844004598390563,
"grad_norm": 1.0625,
"learning_rate": 0.0004996151276682443,
"loss": 6.7735,
"mean_token_accuracy": 0.11559542641043663,
"num_tokens": 5571130.0,
"step": 2845
},
{
"entropy": 6.898355340957641,
"epoch": 0.2849002849002849,
"grad_norm": 1.1953125,
"learning_rate": 0.0004996130382777065,
"loss": 6.921,
"mean_token_accuracy": 0.11242175698280335,
"num_tokens": 5581237.0,
"step": 2850
},
{
"entropy": 6.831335830688476,
"epoch": 0.2854001099615135,
"grad_norm": 0.9921875,
"learning_rate": 0.0004996109432359625,
"loss": 6.7548,
"mean_token_accuracy": 0.12118344977498055,
"num_tokens": 5592488.0,
"step": 2855
},
{
"entropy": 6.713303327560425,
"epoch": 0.285899935022742,
"grad_norm": 0.95703125,
"learning_rate": 0.0004996088425430651,
"loss": 6.715,
"mean_token_accuracy": 0.12256577387452125,
"num_tokens": 5602958.0,
"step": 2860
},
{
"entropy": 6.751800870895385,
"epoch": 0.2863997600839706,
"grad_norm": 1.0625,
"learning_rate": 0.0004996067361990669,
"loss": 6.6478,
"mean_token_accuracy": 0.12125275358557701,
"num_tokens": 5613247.0,
"step": 2865
},
{
"entropy": 6.7146094799041744,
"epoch": 0.2868995851451992,
"grad_norm": 1.0546875,
"learning_rate": 0.0004996046242040209,
"loss": 6.6927,
"mean_token_accuracy": 0.1286645956337452,
"num_tokens": 5624102.0,
"step": 2870
},
{
"entropy": 6.78165636062622,
"epoch": 0.28739941020642773,
"grad_norm": 1.0546875,
"learning_rate": 0.0004996025065579805,
"loss": 6.6226,
"mean_token_accuracy": 0.1292881041765213,
"num_tokens": 5633147.0,
"step": 2875
},
{
"entropy": 6.605591201782227,
"epoch": 0.2878992352676563,
"grad_norm": 0.94140625,
"learning_rate": 0.0004996003832609988,
"loss": 6.5787,
"mean_token_accuracy": 0.12823207154870034,
"num_tokens": 5643399.0,
"step": 2880
},
{
"entropy": 6.7568765640258786,
"epoch": 0.2883990603288849,
"grad_norm": 1.03125,
"learning_rate": 0.0004995982543131292,
"loss": 6.7275,
"mean_token_accuracy": 0.12245923131704331,
"num_tokens": 5653129.0,
"step": 2885
},
{
"entropy": 6.714034366607666,
"epoch": 0.28889888539011344,
"grad_norm": 1.0703125,
"learning_rate": 0.0004995961197144254,
"loss": 6.6475,
"mean_token_accuracy": 0.12331639975309372,
"num_tokens": 5662834.0,
"step": 2890
},
{
"entropy": 6.715389919281006,
"epoch": 0.289398710451342,
"grad_norm": 1.015625,
"learning_rate": 0.000499593979464941,
"loss": 6.5933,
"mean_token_accuracy": 0.13576119020581245,
"num_tokens": 5672393.0,
"step": 2895
},
{
"entropy": 6.6997795581817625,
"epoch": 0.2898985355125706,
"grad_norm": 1.1875,
"learning_rate": 0.0004995918335647298,
"loss": 6.7143,
"mean_token_accuracy": 0.12798105850815772,
"num_tokens": 5683189.0,
"step": 2900
},
{
"entropy": 6.763655710220337,
"epoch": 0.2903983605737992,
"grad_norm": 1.0625,
"learning_rate": 0.0004995896820138459,
"loss": 6.6676,
"mean_token_accuracy": 0.12548011690378189,
"num_tokens": 5692999.0,
"step": 2905
},
{
"entropy": 6.654674625396728,
"epoch": 0.29089818563502773,
"grad_norm": 1.140625,
"learning_rate": 0.0004995875248123434,
"loss": 6.6322,
"mean_token_accuracy": 0.1301705814898014,
"num_tokens": 5701707.0,
"step": 2910
},
{
"entropy": 6.656778240203858,
"epoch": 0.2913980106962563,
"grad_norm": 0.9296875,
"learning_rate": 0.0004995853619602766,
"loss": 6.5872,
"mean_token_accuracy": 0.1278572127223015,
"num_tokens": 5711824.0,
"step": 2915
},
{
"entropy": 6.718242835998535,
"epoch": 0.2918978357574849,
"grad_norm": 1.09375,
"learning_rate": 0.0004995831934576998,
"loss": 6.7023,
"mean_token_accuracy": 0.12706222161650657,
"num_tokens": 5722681.0,
"step": 2920
},
{
"entropy": 6.7669517993927,
"epoch": 0.29239766081871343,
"grad_norm": 1.0390625,
"learning_rate": 0.0004995810193046677,
"loss": 6.6955,
"mean_token_accuracy": 0.12328885868191719,
"num_tokens": 5731806.0,
"step": 2925
},
{
"entropy": 6.707439041137695,
"epoch": 0.292897485879942,
"grad_norm": 1.15625,
"learning_rate": 0.000499578839501235,
"loss": 6.6603,
"mean_token_accuracy": 0.12864745929837226,
"num_tokens": 5742144.0,
"step": 2930
},
{
"entropy": 6.705581617355347,
"epoch": 0.2933973109411706,
"grad_norm": 1.4765625,
"learning_rate": 0.0004995766540474564,
"loss": 6.6626,
"mean_token_accuracy": 0.1203208550810814,
"num_tokens": 5752752.0,
"step": 2935
},
{
"entropy": 6.731801557540893,
"epoch": 0.29389713600239914,
"grad_norm": 1.09375,
"learning_rate": 0.000499574462943387,
"loss": 6.6124,
"mean_token_accuracy": 0.12901480495929718,
"num_tokens": 5762031.0,
"step": 2940
},
{
"entropy": 6.616041278839111,
"epoch": 0.2943969610636277,
"grad_norm": 1.09375,
"learning_rate": 0.000499572266189082,
"loss": 6.5485,
"mean_token_accuracy": 0.128142399340868,
"num_tokens": 5772160.0,
"step": 2945
},
{
"entropy": 6.778317594528199,
"epoch": 0.2948967861248563,
"grad_norm": 1.0625,
"learning_rate": 0.0004995700637845964,
"loss": 6.6606,
"mean_token_accuracy": 0.1271796479821205,
"num_tokens": 5782145.0,
"step": 2950
},
{
"entropy": 6.600551319122315,
"epoch": 0.29539661118608485,
"grad_norm": 1.1953125,
"learning_rate": 0.0004995678557299859,
"loss": 6.5148,
"mean_token_accuracy": 0.13630254417657853,
"num_tokens": 5790889.0,
"step": 2955
},
{
"entropy": 6.717923641204834,
"epoch": 0.29589643624731343,
"grad_norm": 1.078125,
"learning_rate": 0.0004995656420253058,
"loss": 6.6642,
"mean_token_accuracy": 0.1262128658592701,
"num_tokens": 5801239.0,
"step": 2960
},
{
"entropy": 6.854567575454712,
"epoch": 0.296396261308542,
"grad_norm": 1.0390625,
"learning_rate": 0.000499563422670612,
"loss": 6.7637,
"mean_token_accuracy": 0.12252128720283509,
"num_tokens": 5811390.0,
"step": 2965
},
{
"entropy": 6.738302850723267,
"epoch": 0.2968960863697706,
"grad_norm": 0.98828125,
"learning_rate": 0.0004995611976659604,
"loss": 6.7237,
"mean_token_accuracy": 0.11966272965073585,
"num_tokens": 5821529.0,
"step": 2970
},
{
"entropy": 6.708627653121948,
"epoch": 0.29739591143099914,
"grad_norm": 1.0546875,
"learning_rate": 0.0004995589670114067,
"loss": 6.6697,
"mean_token_accuracy": 0.12530870959162713,
"num_tokens": 5830551.0,
"step": 2975
},
{
"entropy": 6.744061517715454,
"epoch": 0.2978957364922277,
"grad_norm": 1.0859375,
"learning_rate": 0.0004995567307070072,
"loss": 6.6927,
"mean_token_accuracy": 0.1294789083302021,
"num_tokens": 5840768.0,
"step": 2980
},
{
"entropy": 6.7781086444854735,
"epoch": 0.2983955615534563,
"grad_norm": 1.046875,
"learning_rate": 0.0004995544887528182,
"loss": 6.7099,
"mean_token_accuracy": 0.11977946162223815,
"num_tokens": 5850515.0,
"step": 2985
},
{
"entropy": 6.709803867340088,
"epoch": 0.29889538661468484,
"grad_norm": 1.0859375,
"learning_rate": 0.0004995522411488959,
"loss": 6.6054,
"mean_token_accuracy": 0.13315768986940385,
"num_tokens": 5859480.0,
"step": 2990
},
{
"entropy": 6.7460136890411375,
"epoch": 0.29939521167591343,
"grad_norm": 1.0546875,
"learning_rate": 0.0004995499878952971,
"loss": 6.6644,
"mean_token_accuracy": 0.12363893687725067,
"num_tokens": 5871255.0,
"step": 2995
},
{
"entropy": 6.610029220581055,
"epoch": 0.299895036737142,
"grad_norm": 1.03125,
"learning_rate": 0.0004995477289920784,
"loss": 6.5893,
"mean_token_accuracy": 0.1339652419090271,
"num_tokens": 5881306.0,
"step": 3000
},
{
"epoch": 0.299895036737142,
"eval_entropy": 6.529951082188823,
"eval_loss": 6.702248573303223,
"eval_mean_token_accuracy": 0.1290466456501981,
"eval_num_tokens": 5881306.0,
"eval_runtime": 23.7239,
"eval_samples_per_second": 1308.597,
"eval_steps_per_second": 163.59,
"step": 3000
},
{
"entropy": 6.681021976470947,
"epoch": 0.30039486179837055,
"grad_norm": 0.984375,
"learning_rate": 0.0004995454644392967,
"loss": 6.6686,
"mean_token_accuracy": 0.1230406939983368,
"num_tokens": 5891209.0,
"step": 3005
},
{
"entropy": 6.797600841522216,
"epoch": 0.30089468685959914,
"grad_norm": 0.84765625,
"learning_rate": 0.0004995431942370087,
"loss": 6.7259,
"mean_token_accuracy": 0.12509791404008866,
"num_tokens": 5902003.0,
"step": 3010
},
{
"entropy": 6.776391315460205,
"epoch": 0.3013945119208277,
"grad_norm": 1.1328125,
"learning_rate": 0.0004995409183852718,
"loss": 6.6609,
"mean_token_accuracy": 0.12573762908577918,
"num_tokens": 5911327.0,
"step": 3015
},
{
"entropy": 6.587473058700562,
"epoch": 0.30189433698205626,
"grad_norm": 1.0546875,
"learning_rate": 0.0004995386368841432,
"loss": 6.5949,
"mean_token_accuracy": 0.13132134079933167,
"num_tokens": 5920385.0,
"step": 3020
},
{
"entropy": 6.644120168685913,
"epoch": 0.30239416204328484,
"grad_norm": 1.09375,
"learning_rate": 0.0004995363497336802,
"loss": 6.5472,
"mean_token_accuracy": 0.13319996371865273,
"num_tokens": 5929784.0,
"step": 3025
},
{
"entropy": 6.675529146194458,
"epoch": 0.30289398710451343,
"grad_norm": 1.1015625,
"learning_rate": 0.0004995340569339405,
"loss": 6.6351,
"mean_token_accuracy": 0.1254398010671139,
"num_tokens": 5938766.0,
"step": 3030
},
{
"entropy": 6.780316305160523,
"epoch": 0.303393812165742,
"grad_norm": 1.046875,
"learning_rate": 0.0004995317584849817,
"loss": 6.7465,
"mean_token_accuracy": 0.12507161349058152,
"num_tokens": 5948869.0,
"step": 3035
},
{
"entropy": 6.685397911071777,
"epoch": 0.30389363722697055,
"grad_norm": 0.984375,
"learning_rate": 0.0004995294543868615,
"loss": 6.5529,
"mean_token_accuracy": 0.12421033307909965,
"num_tokens": 5959074.0,
"step": 3040
},
{
"entropy": 6.659611654281616,
"epoch": 0.30439346228819913,
"grad_norm": 1.140625,
"learning_rate": 0.0004995271446396382,
"loss": 6.6669,
"mean_token_accuracy": 0.12645429074764253,
"num_tokens": 5968608.0,
"step": 3045
},
{
"entropy": 6.73339958190918,
"epoch": 0.3048932873494277,
"grad_norm": 0.9921875,
"learning_rate": 0.0004995248292433697,
"loss": 6.6962,
"mean_token_accuracy": 0.11696835681796074,
"num_tokens": 5979756.0,
"step": 3050
},
{
"entropy": 6.779122972488404,
"epoch": 0.30539311241065625,
"grad_norm": 1.078125,
"learning_rate": 0.0004995225081981142,
"loss": 6.7665,
"mean_token_accuracy": 0.11112019196152687,
"num_tokens": 5990299.0,
"step": 3055
},
{
"entropy": 6.774257707595825,
"epoch": 0.30589293747188484,
"grad_norm": 1.0625,
"learning_rate": 0.0004995201815039301,
"loss": 6.6607,
"mean_token_accuracy": 0.11963343843817711,
"num_tokens": 6001721.0,
"step": 3060
},
{
"entropy": 6.6790704250335695,
"epoch": 0.3063927625331134,
"grad_norm": 1.0234375,
"learning_rate": 0.0004995178491608762,
"loss": 6.7327,
"mean_token_accuracy": 0.12029238194227218,
"num_tokens": 6012658.0,
"step": 3065
},
{
"entropy": 6.768873167037964,
"epoch": 0.30689258759434196,
"grad_norm": 1.0859375,
"learning_rate": 0.0004995155111690107,
"loss": 6.6766,
"mean_token_accuracy": 0.12649752125144004,
"num_tokens": 6022470.0,
"step": 3070
},
{
"entropy": 6.687690401077271,
"epoch": 0.30739241265557055,
"grad_norm": 1.265625,
"learning_rate": 0.000499513167528393,
"loss": 6.5548,
"mean_token_accuracy": 0.1281000018119812,
"num_tokens": 6034227.0,
"step": 3075
},
{
"entropy": 6.632200527191162,
"epoch": 0.30789223771679913,
"grad_norm": 1.09375,
"learning_rate": 0.0004995108182390815,
"loss": 6.5696,
"mean_token_accuracy": 0.12978074327111244,
"num_tokens": 6043122.0,
"step": 3080
},
{
"entropy": 6.67748007774353,
"epoch": 0.30839206277802766,
"grad_norm": 1.0625,
"learning_rate": 0.0004995084633011359,
"loss": 6.5892,
"mean_token_accuracy": 0.12593309059739113,
"num_tokens": 6052988.0,
"step": 3085
},
{
"entropy": 6.651902532577514,
"epoch": 0.30889188783925625,
"grad_norm": 1.078125,
"learning_rate": 0.000499506102714615,
"loss": 6.6284,
"mean_token_accuracy": 0.12826041579246522,
"num_tokens": 6062800.0,
"step": 3090
},
{
"entropy": 6.814677333831787,
"epoch": 0.30939171290048484,
"grad_norm": 1.140625,
"learning_rate": 0.0004995037364795782,
"loss": 6.7035,
"mean_token_accuracy": 0.1235254593193531,
"num_tokens": 6071327.0,
"step": 3095
},
{
"entropy": 6.7643333911895756,
"epoch": 0.3098915379617134,
"grad_norm": 1.21875,
"learning_rate": 0.0004995013645960853,
"loss": 6.7053,
"mean_token_accuracy": 0.12090670987963677,
"num_tokens": 6080574.0,
"step": 3100
},
{
"entropy": 6.6897650241851805,
"epoch": 0.31039136302294196,
"grad_norm": 1.1953125,
"learning_rate": 0.0004994989870641958,
"loss": 6.6029,
"mean_token_accuracy": 0.12805371433496476,
"num_tokens": 6088081.0,
"step": 3105
},
{
"entropy": 6.722474527359009,
"epoch": 0.31089118808417054,
"grad_norm": 1.125,
"learning_rate": 0.0004994966038839695,
"loss": 6.7177,
"mean_token_accuracy": 0.12565394565463067,
"num_tokens": 6097785.0,
"step": 3110
},
{
"entropy": 6.713695383071899,
"epoch": 0.31139101314539913,
"grad_norm": 1.140625,
"learning_rate": 0.0004994942150554666,
"loss": 6.6408,
"mean_token_accuracy": 0.12528237476944923,
"num_tokens": 6107402.0,
"step": 3115
},
{
"entropy": 6.668991994857788,
"epoch": 0.31189083820662766,
"grad_norm": 1.109375,
"learning_rate": 0.0004994918205787468,
"loss": 6.5943,
"mean_token_accuracy": 0.12502402663230897,
"num_tokens": 6116439.0,
"step": 3120
},
{
"entropy": 6.699170875549316,
"epoch": 0.31239066326785625,
"grad_norm": 1.1171875,
"learning_rate": 0.0004994894204538706,
"loss": 6.6482,
"mean_token_accuracy": 0.13096092343330384,
"num_tokens": 6126854.0,
"step": 3125
},
{
"entropy": 6.679208469390869,
"epoch": 0.31289048832908484,
"grad_norm": 1.03125,
"learning_rate": 0.0004994870146808984,
"loss": 6.5964,
"mean_token_accuracy": 0.12942466214299203,
"num_tokens": 6136869.0,
"step": 3130
},
{
"entropy": 6.625993967056274,
"epoch": 0.31339031339031337,
"grad_norm": 1.109375,
"learning_rate": 0.0004994846032598906,
"loss": 6.5813,
"mean_token_accuracy": 0.1329791858792305,
"num_tokens": 6146772.0,
"step": 3135
},
{
"entropy": 6.709695720672608,
"epoch": 0.31389013845154196,
"grad_norm": 1.109375,
"learning_rate": 0.0004994821861909082,
"loss": 6.6718,
"mean_token_accuracy": 0.12659213691949844,
"num_tokens": 6156329.0,
"step": 3140
},
{
"entropy": 6.67364616394043,
"epoch": 0.31438996351277054,
"grad_norm": 1.0,
"learning_rate": 0.0004994797634740114,
"loss": 6.5739,
"mean_token_accuracy": 0.12842462211847305,
"num_tokens": 6166198.0,
"step": 3145
},
{
"entropy": 6.628734970092774,
"epoch": 0.3148897885739991,
"grad_norm": 1.0703125,
"learning_rate": 0.0004994773351092618,
"loss": 6.6481,
"mean_token_accuracy": 0.12540496289730071,
"num_tokens": 6176180.0,
"step": 3150
},
{
"entropy": 6.687831735610962,
"epoch": 0.31538961363522766,
"grad_norm": 1.1484375,
"learning_rate": 0.00049947490109672,
"loss": 6.5962,
"mean_token_accuracy": 0.1281987413764,
"num_tokens": 6185776.0,
"step": 3155
},
{
"entropy": 6.728115272521973,
"epoch": 0.31588943869645625,
"grad_norm": 1.1171875,
"learning_rate": 0.0004994724614364476,
"loss": 6.7325,
"mean_token_accuracy": 0.12246878519654274,
"num_tokens": 6196472.0,
"step": 3160
},
{
"entropy": 6.630450296401977,
"epoch": 0.31638926375768484,
"grad_norm": 1.1171875,
"learning_rate": 0.0004994700161285058,
"loss": 6.5934,
"mean_token_accuracy": 0.1263155981898308,
"num_tokens": 6206064.0,
"step": 3165
},
{
"entropy": 6.755979919433594,
"epoch": 0.31688908881891337,
"grad_norm": 1.0,
"learning_rate": 0.000499467565172956,
"loss": 6.6224,
"mean_token_accuracy": 0.129413178563118,
"num_tokens": 6217044.0,
"step": 3170
},
{
"entropy": 6.671145963668823,
"epoch": 0.31738891388014195,
"grad_norm": 0.98828125,
"learning_rate": 0.0004994651085698602,
"loss": 6.6066,
"mean_token_accuracy": 0.12426463291049003,
"num_tokens": 6228294.0,
"step": 3175
},
{
"entropy": 6.670057916641236,
"epoch": 0.31788873894137054,
"grad_norm": 1.09375,
"learning_rate": 0.00049946264631928,
"loss": 6.5465,
"mean_token_accuracy": 0.1360152244567871,
"num_tokens": 6238525.0,
"step": 3180
},
{
"entropy": 6.499093770980835,
"epoch": 0.3183885640025991,
"grad_norm": 1.0859375,
"learning_rate": 0.0004994601784212774,
"loss": 6.4419,
"mean_token_accuracy": 0.13964417427778245,
"num_tokens": 6247457.0,
"step": 3185
},
{
"entropy": 6.5308064937591555,
"epoch": 0.31888838906382766,
"grad_norm": 1.1171875,
"learning_rate": 0.0004994577048759144,
"loss": 6.573,
"mean_token_accuracy": 0.13198508694767952,
"num_tokens": 6256414.0,
"step": 3190
},
{
"entropy": 6.607933044433594,
"epoch": 0.31938821412505625,
"grad_norm": 1.0390625,
"learning_rate": 0.0004994552256832533,
"loss": 6.5048,
"mean_token_accuracy": 0.13686242029070855,
"num_tokens": 6266093.0,
"step": 3195
},
{
"entropy": 6.649296379089355,
"epoch": 0.3198880391862848,
"grad_norm": 1.0703125,
"learning_rate": 0.0004994527408433566,
"loss": 6.5681,
"mean_token_accuracy": 0.13355113565921783,
"num_tokens": 6276340.0,
"step": 3200
},
{
"entropy": 6.617343235015869,
"epoch": 0.32038786424751337,
"grad_norm": 1.203125,
"learning_rate": 0.0004994502503562865,
"loss": 6.5877,
"mean_token_accuracy": 0.12834486067295076,
"num_tokens": 6285044.0,
"step": 3205
},
{
"entropy": 6.681250047683716,
"epoch": 0.32088768930874195,
"grad_norm": 1.09375,
"learning_rate": 0.000499447754222106,
"loss": 6.5154,
"mean_token_accuracy": 0.1330440990626812,
"num_tokens": 6294105.0,
"step": 3210
},
{
"entropy": 6.555824518203735,
"epoch": 0.3213875143699705,
"grad_norm": 1.15625,
"learning_rate": 0.0004994452524408777,
"loss": 6.5729,
"mean_token_accuracy": 0.12900223657488824,
"num_tokens": 6302503.0,
"step": 3215
},
{
"entropy": 6.677013397216797,
"epoch": 0.32188733943119907,
"grad_norm": 1.1328125,
"learning_rate": 0.0004994427450126646,
"loss": 6.5874,
"mean_token_accuracy": 0.12441989108920097,
"num_tokens": 6313068.0,
"step": 3220
},
{
"entropy": 6.760306739807129,
"epoch": 0.32238716449242766,
"grad_norm": 1.0625,
"learning_rate": 0.0004994402319375298,
"loss": 6.6682,
"mean_token_accuracy": 0.12115811482071877,
"num_tokens": 6322770.0,
"step": 3225
},
{
"entropy": 6.5807883739471436,
"epoch": 0.32288698955365625,
"grad_norm": 1.1015625,
"learning_rate": 0.0004994377132155366,
"loss": 6.5463,
"mean_token_accuracy": 0.13018904775381088,
"num_tokens": 6333055.0,
"step": 3230
},
{
"entropy": 6.49958643913269,
"epoch": 0.3233868146148848,
"grad_norm": 1.0546875,
"learning_rate": 0.0004994351888467482,
"loss": 6.5625,
"mean_token_accuracy": 0.13032179921865464,
"num_tokens": 6342780.0,
"step": 3235
},
{
"entropy": 6.701545906066895,
"epoch": 0.32388663967611336,
"grad_norm": 1.25,
"learning_rate": 0.0004994326588312282,
"loss": 6.5456,
"mean_token_accuracy": 0.12095091342926026,
"num_tokens": 6352021.0,
"step": 3240
},
{
"entropy": 6.605896663665772,
"epoch": 0.32438646473734195,
"grad_norm": 1.1484375,
"learning_rate": 0.0004994301231690403,
"loss": 6.62,
"mean_token_accuracy": 0.12656017392873764,
"num_tokens": 6361062.0,
"step": 3245
},
{
"entropy": 6.672325706481933,
"epoch": 0.3248862897985705,
"grad_norm": 1.0078125,
"learning_rate": 0.0004994275818602482,
"loss": 6.6412,
"mean_token_accuracy": 0.12171561419963836,
"num_tokens": 6371318.0,
"step": 3250
},
{
"entropy": 6.815335893630982,
"epoch": 0.32538611485979907,
"grad_norm": 1.09375,
"learning_rate": 0.0004994250349049159,
"loss": 6.7133,
"mean_token_accuracy": 0.12552304565906525,
"num_tokens": 6381078.0,
"step": 3255
},
{
"entropy": 6.70945520401001,
"epoch": 0.32588593992102766,
"grad_norm": 1.09375,
"learning_rate": 0.0004994224823031075,
"loss": 6.5515,
"mean_token_accuracy": 0.13201567009091378,
"num_tokens": 6390382.0,
"step": 3260
},
{
"entropy": 6.613358116149902,
"epoch": 0.3263857649822562,
"grad_norm": 1.0859375,
"learning_rate": 0.0004994199240548873,
"loss": 6.6023,
"mean_token_accuracy": 0.12341969534754753,
"num_tokens": 6399849.0,
"step": 3265
},
{
"entropy": 6.684066915512085,
"epoch": 0.3268855900434848,
"grad_norm": 1.1171875,
"learning_rate": 0.0004994173601603194,
"loss": 6.6252,
"mean_token_accuracy": 0.12377856075763702,
"num_tokens": 6409150.0,
"step": 3270
},
{
"entropy": 6.724408197402954,
"epoch": 0.32738541510471336,
"grad_norm": 1.1640625,
"learning_rate": 0.0004994147906194684,
"loss": 6.6265,
"mean_token_accuracy": 0.12532238364219667,
"num_tokens": 6419525.0,
"step": 3275
},
{
"entropy": 6.663235378265381,
"epoch": 0.3278852401659419,
"grad_norm": 1.1484375,
"learning_rate": 0.0004994122154323992,
"loss": 6.5806,
"mean_token_accuracy": 0.12679464221000672,
"num_tokens": 6430185.0,
"step": 3280
},
{
"entropy": 6.722297477722168,
"epoch": 0.3283850652271705,
"grad_norm": 1.2109375,
"learning_rate": 0.0004994096345991763,
"loss": 6.5563,
"mean_token_accuracy": 0.12995896786451339,
"num_tokens": 6440221.0,
"step": 3285
},
{
"entropy": 6.607683229446411,
"epoch": 0.32888489028839907,
"grad_norm": 1.0234375,
"learning_rate": 0.0004994070481198649,
"loss": 6.6327,
"mean_token_accuracy": 0.12762965336441995,
"num_tokens": 6448861.0,
"step": 3290
},
{
"entropy": 6.682978582382202,
"epoch": 0.32938471534962765,
"grad_norm": 1.0625,
"learning_rate": 0.0004994044559945296,
"loss": 6.5257,
"mean_token_accuracy": 0.12889787256717683,
"num_tokens": 6458782.0,
"step": 3295
},
{
"entropy": 6.590939092636108,
"epoch": 0.3298845404108562,
"grad_norm": 0.9921875,
"learning_rate": 0.0004994018582232361,
"loss": 6.5764,
"mean_token_accuracy": 0.1253158003091812,
"num_tokens": 6470201.0,
"step": 3300
},
{
"entropy": 6.598582696914673,
"epoch": 0.3303843654720848,
"grad_norm": 1.03125,
"learning_rate": 0.0004993992548060497,
"loss": 6.6021,
"mean_token_accuracy": 0.1266971670091152,
"num_tokens": 6479507.0,
"step": 3305
},
{
"entropy": 6.683953285217285,
"epoch": 0.33088419053331336,
"grad_norm": 1.2109375,
"learning_rate": 0.0004993966457430357,
"loss": 6.6047,
"mean_token_accuracy": 0.13037028759717942,
"num_tokens": 6488902.0,
"step": 3310
},
{
"entropy": 6.6829265594482425,
"epoch": 0.3313840155945419,
"grad_norm": 1.0625,
"learning_rate": 0.0004993940310342598,
"loss": 6.5886,
"mean_token_accuracy": 0.13307278156280516,
"num_tokens": 6498781.0,
"step": 3315
},
{
"entropy": 6.58431830406189,
"epoch": 0.3318838406557705,
"grad_norm": 1.15625,
"learning_rate": 0.0004993914106797879,
"loss": 6.5041,
"mean_token_accuracy": 0.13261542543768884,
"num_tokens": 6507358.0,
"step": 3320
},
{
"entropy": 6.600981760025024,
"epoch": 0.33238366571699907,
"grad_norm": 1.015625,
"learning_rate": 0.0004993887846796858,
"loss": 6.5627,
"mean_token_accuracy": 0.1347931757569313,
"num_tokens": 6517976.0,
"step": 3325
},
{
"entropy": 6.740728521347046,
"epoch": 0.3328834907782276,
"grad_norm": 1.15625,
"learning_rate": 0.0004993861530340196,
"loss": 6.6813,
"mean_token_accuracy": 0.11708623915910721,
"num_tokens": 6528407.0,
"step": 3330
},
{
"entropy": 6.799725008010864,
"epoch": 0.3333833158394562,
"grad_norm": 1.109375,
"learning_rate": 0.0004993835157428555,
"loss": 6.5809,
"mean_token_accuracy": 0.12460994869470596,
"num_tokens": 6537619.0,
"step": 3335
},
{
"entropy": 6.518185138702393,
"epoch": 0.33388314090068477,
"grad_norm": 0.96484375,
"learning_rate": 0.0004993808728062599,
"loss": 6.4912,
"mean_token_accuracy": 0.1300904169678688,
"num_tokens": 6548393.0,
"step": 3340
},
{
"entropy": 6.65168776512146,
"epoch": 0.3343829659619133,
"grad_norm": 1.0234375,
"learning_rate": 0.0004993782242242994,
"loss": 6.5803,
"mean_token_accuracy": 0.13166460916399955,
"num_tokens": 6558646.0,
"step": 3345
},
{
"entropy": 6.66806435585022,
"epoch": 0.3348827910231419,
"grad_norm": 1.0859375,
"learning_rate": 0.0004993755699970404,
"loss": 6.5693,
"mean_token_accuracy": 0.13037904500961303,
"num_tokens": 6567534.0,
"step": 3350
},
{
"entropy": 6.610126113891601,
"epoch": 0.3353826160843705,
"grad_norm": 1.0,
"learning_rate": 0.0004993729101245498,
"loss": 6.5987,
"mean_token_accuracy": 0.13262755200266838,
"num_tokens": 6577940.0,
"step": 3355
},
{
"entropy": 6.6294848918914795,
"epoch": 0.33588244114559906,
"grad_norm": 1.0859375,
"learning_rate": 0.0004993702446068945,
"loss": 6.6147,
"mean_token_accuracy": 0.12785486727952958,
"num_tokens": 6587421.0,
"step": 3360
},
{
"entropy": 6.703089475631714,
"epoch": 0.3363822662068276,
"grad_norm": 1.015625,
"learning_rate": 0.0004993675734441416,
"loss": 6.5881,
"mean_token_accuracy": 0.12631361037492753,
"num_tokens": 6597509.0,
"step": 3365
},
{
"entropy": 6.6260514736175535,
"epoch": 0.3368820912680562,
"grad_norm": 1.15625,
"learning_rate": 0.0004993648966363583,
"loss": 6.5338,
"mean_token_accuracy": 0.1388427048921585,
"num_tokens": 6607003.0,
"step": 3370
},
{
"entropy": 6.511269807815552,
"epoch": 0.33738191632928477,
"grad_norm": 1.0859375,
"learning_rate": 0.000499362214183612,
"loss": 6.5903,
"mean_token_accuracy": 0.13173537701368332,
"num_tokens": 6617454.0,
"step": 3375
},
{
"entropy": 6.572839879989624,
"epoch": 0.3378817413905133,
"grad_norm": 1.2109375,
"learning_rate": 0.00049935952608597,
"loss": 6.5478,
"mean_token_accuracy": 0.13501427173614503,
"num_tokens": 6628327.0,
"step": 3380
},
{
"entropy": 6.63575119972229,
"epoch": 0.3383815664517419,
"grad_norm": 1.0,
"learning_rate": 0.0004993568323435002,
"loss": 6.5033,
"mean_token_accuracy": 0.1291576936841011,
"num_tokens": 6638282.0,
"step": 3385
},
{
"entropy": 6.588334560394287,
"epoch": 0.3388813915129705,
"grad_norm": 1.0859375,
"learning_rate": 0.0004993541329562702,
"loss": 6.4992,
"mean_token_accuracy": 0.134891277551651,
"num_tokens": 6647138.0,
"step": 3390
},
{
"entropy": 6.609392261505127,
"epoch": 0.339381216574199,
"grad_norm": 1.0625,
"learning_rate": 0.0004993514279243477,
"loss": 6.5918,
"mean_token_accuracy": 0.12653654739260672,
"num_tokens": 6656129.0,
"step": 3395
},
{
"entropy": 6.626824617385864,
"epoch": 0.3398810416354276,
"grad_norm": 1.0234375,
"learning_rate": 0.0004993487172478012,
"loss": 6.5766,
"mean_token_accuracy": 0.13372050300240518,
"num_tokens": 6666485.0,
"step": 3400
},
{
"entropy": 6.744373178482055,
"epoch": 0.3403808666966562,
"grad_norm": 1.078125,
"learning_rate": 0.0004993460009266988,
"loss": 6.6583,
"mean_token_accuracy": 0.12640992775559426,
"num_tokens": 6676885.0,
"step": 3405
},
{
"entropy": 6.656079721450806,
"epoch": 0.3408806917578847,
"grad_norm": 1.0625,
"learning_rate": 0.0004993432789611086,
"loss": 6.5465,
"mean_token_accuracy": 0.13199173286557198,
"num_tokens": 6687309.0,
"step": 3410
},
{
"entropy": 6.588942384719848,
"epoch": 0.3413805168191133,
"grad_norm": 1.09375,
"learning_rate": 0.0004993405513510992,
"loss": 6.6823,
"mean_token_accuracy": 0.1306323938071728,
"num_tokens": 6696868.0,
"step": 3415
},
{
"entropy": 6.7879961967468265,
"epoch": 0.3418803418803419,
"grad_norm": 1.1484375,
"learning_rate": 0.0004993378180967394,
"loss": 6.6172,
"mean_token_accuracy": 0.13136079236865045,
"num_tokens": 6706526.0,
"step": 3420
},
{
"entropy": 6.6939380168914795,
"epoch": 0.3423801669415705,
"grad_norm": 1.0703125,
"learning_rate": 0.0004993350791980978,
"loss": 6.6379,
"mean_token_accuracy": 0.12985037490725518,
"num_tokens": 6716792.0,
"step": 3425
},
{
"entropy": 6.478039693832398,
"epoch": 0.342879992002799,
"grad_norm": 1.171875,
"learning_rate": 0.0004993323346552433,
"loss": 6.4695,
"mean_token_accuracy": 0.137115740776062,
"num_tokens": 6726268.0,
"step": 3430
},
{
"entropy": 6.616924524307251,
"epoch": 0.3433798170640276,
"grad_norm": 1.1171875,
"learning_rate": 0.0004993295844682449,
"loss": 6.563,
"mean_token_accuracy": 0.1286364048719406,
"num_tokens": 6735687.0,
"step": 3435
},
{
"entropy": 6.569231176376343,
"epoch": 0.3438796421252562,
"grad_norm": 0.98046875,
"learning_rate": 0.000499326828637172,
"loss": 6.3953,
"mean_token_accuracy": 0.1459199793636799,
"num_tokens": 6747055.0,
"step": 3440
},
{
"entropy": 6.508210897445679,
"epoch": 0.3443794671864847,
"grad_norm": 1.015625,
"learning_rate": 0.0004993240671620938,
"loss": 6.5133,
"mean_token_accuracy": 0.1337944194674492,
"num_tokens": 6756190.0,
"step": 3445
},
{
"entropy": 6.681909513473511,
"epoch": 0.3448792922477133,
"grad_norm": 1.078125,
"learning_rate": 0.0004993213000430797,
"loss": 6.6284,
"mean_token_accuracy": 0.12544018179178237,
"num_tokens": 6766145.0,
"step": 3450
},
{
"entropy": 6.676771545410157,
"epoch": 0.3453791173089419,
"grad_norm": 1.1328125,
"learning_rate": 0.0004993185272801995,
"loss": 6.5238,
"mean_token_accuracy": 0.13093370348215103,
"num_tokens": 6776294.0,
"step": 3455
},
{
"entropy": 6.61463098526001,
"epoch": 0.3458789423701704,
"grad_norm": 1.140625,
"learning_rate": 0.0004993157488735228,
"loss": 6.5721,
"mean_token_accuracy": 0.1304081656038761,
"num_tokens": 6785349.0,
"step": 3460
},
{
"entropy": 6.556643724441528,
"epoch": 0.346378767431399,
"grad_norm": 1.0546875,
"learning_rate": 0.0004993129648231197,
"loss": 6.4718,
"mean_token_accuracy": 0.1271122671663761,
"num_tokens": 6794733.0,
"step": 3465
},
{
"entropy": 6.679942560195923,
"epoch": 0.3468785924926276,
"grad_norm": 1.0390625,
"learning_rate": 0.00049931017512906,
"loss": 6.5658,
"mean_token_accuracy": 0.1287422724068165,
"num_tokens": 6803850.0,
"step": 3470
},
{
"entropy": 6.58225417137146,
"epoch": 0.3473784175538562,
"grad_norm": 0.9921875,
"learning_rate": 0.0004993073797914141,
"loss": 6.4847,
"mean_token_accuracy": 0.13215459883213043,
"num_tokens": 6813201.0,
"step": 3475
},
{
"entropy": 6.512684631347656,
"epoch": 0.3478782426150847,
"grad_norm": 1.0625,
"learning_rate": 0.0004993045788102522,
"loss": 6.4682,
"mean_token_accuracy": 0.13046691417694092,
"num_tokens": 6822238.0,
"step": 3480
},
{
"entropy": 6.667408657073975,
"epoch": 0.3483780676763133,
"grad_norm": 1.03125,
"learning_rate": 0.0004993017721856449,
"loss": 6.5978,
"mean_token_accuracy": 0.12310194596648216,
"num_tokens": 6832586.0,
"step": 3485
},
{
"entropy": 6.626319503784179,
"epoch": 0.3488778927375419,
"grad_norm": 1.09375,
"learning_rate": 0.0004992989599176626,
"loss": 6.5654,
"mean_token_accuracy": 0.12846530228853226,
"num_tokens": 6841699.0,
"step": 3490
},
{
"entropy": 6.644284200668335,
"epoch": 0.3493777177987704,
"grad_norm": 1.1171875,
"learning_rate": 0.0004992961420063763,
"loss": 6.6131,
"mean_token_accuracy": 0.12847285494208335,
"num_tokens": 6851455.0,
"step": 3495
},
{
"entropy": 6.666490936279297,
"epoch": 0.349877542859999,
"grad_norm": 1.078125,
"learning_rate": 0.0004992933184518567,
"loss": 6.524,
"mean_token_accuracy": 0.13283096253871918,
"num_tokens": 6860646.0,
"step": 3500
},
{
"entropy": 6.571482467651367,
"epoch": 0.3503773679212276,
"grad_norm": 1.0546875,
"learning_rate": 0.0004992904892541749,
"loss": 6.6076,
"mean_token_accuracy": 0.1293070636689663,
"num_tokens": 6870641.0,
"step": 3505
},
{
"entropy": 6.676307153701782,
"epoch": 0.3508771929824561,
"grad_norm": 1.2421875,
"learning_rate": 0.0004992876544134022,
"loss": 6.6352,
"mean_token_accuracy": 0.12403724417090416,
"num_tokens": 6880831.0,
"step": 3510
},
{
"entropy": 6.666634845733642,
"epoch": 0.3513770180436847,
"grad_norm": 1.25,
"learning_rate": 0.0004992848139296098,
"loss": 6.6234,
"mean_token_accuracy": 0.12937338277697563,
"num_tokens": 6890305.0,
"step": 3515
},
{
"entropy": 6.595576810836792,
"epoch": 0.3518768431049133,
"grad_norm": 1.15625,
"learning_rate": 0.0004992819678028692,
"loss": 6.4999,
"mean_token_accuracy": 0.1348331443965435,
"num_tokens": 6900147.0,
"step": 3520
},
{
"entropy": 6.579501390457153,
"epoch": 0.3523766681661418,
"grad_norm": 1.1875,
"learning_rate": 0.000499279116033252,
"loss": 6.4869,
"mean_token_accuracy": 0.13790729492902756,
"num_tokens": 6910367.0,
"step": 3525
},
{
"entropy": 6.558926105499268,
"epoch": 0.3528764932273704,
"grad_norm": 1.1015625,
"learning_rate": 0.0004992762586208299,
"loss": 6.4736,
"mean_token_accuracy": 0.13376323729753495,
"num_tokens": 6919843.0,
"step": 3530
},
{
"entropy": 6.577578544616699,
"epoch": 0.353376318288599,
"grad_norm": 1.0390625,
"learning_rate": 0.0004992733955656749,
"loss": 6.5312,
"mean_token_accuracy": 0.130813892185688,
"num_tokens": 6929912.0,
"step": 3535
},
{
"entropy": 6.646571493148803,
"epoch": 0.3538761433498276,
"grad_norm": 1.046875,
"learning_rate": 0.0004992705268678589,
"loss": 6.6069,
"mean_token_accuracy": 0.1239285834133625,
"num_tokens": 6940836.0,
"step": 3540
},
{
"entropy": 6.639316368103027,
"epoch": 0.3543759684110561,
"grad_norm": 1.109375,
"learning_rate": 0.0004992676525274542,
"loss": 6.5687,
"mean_token_accuracy": 0.12876028642058374,
"num_tokens": 6950313.0,
"step": 3545
},
{
"entropy": 6.594517707824707,
"epoch": 0.3548757934722847,
"grad_norm": 1.1328125,
"learning_rate": 0.0004992647725445331,
"loss": 6.4392,
"mean_token_accuracy": 0.135837110131979,
"num_tokens": 6958786.0,
"step": 3550
},
{
"entropy": 6.62755856513977,
"epoch": 0.3553756185335133,
"grad_norm": 1.109375,
"learning_rate": 0.000499261886919168,
"loss": 6.6161,
"mean_token_accuracy": 0.1281417541205883,
"num_tokens": 6968453.0,
"step": 3555
},
{
"entropy": 6.581298780441284,
"epoch": 0.3558754435947418,
"grad_norm": 1.0390625,
"learning_rate": 0.0004992589956514316,
"loss": 6.4422,
"mean_token_accuracy": 0.13865550979971886,
"num_tokens": 6978143.0,
"step": 3560
},
{
"entropy": 6.53548493385315,
"epoch": 0.3563752686559704,
"grad_norm": 1.3359375,
"learning_rate": 0.0004992560987413965,
"loss": 6.4639,
"mean_token_accuracy": 0.12931203544139863,
"num_tokens": 6986711.0,
"step": 3565
},
{
"entropy": 6.544329118728638,
"epoch": 0.356875093717199,
"grad_norm": 1.171875,
"learning_rate": 0.0004992531961891356,
"loss": 6.5277,
"mean_token_accuracy": 0.12880890145897866,
"num_tokens": 6995904.0,
"step": 3570
},
{
"entropy": 6.643979883193969,
"epoch": 0.35737491877842753,
"grad_norm": 1.1171875,
"learning_rate": 0.0004992502879947222,
"loss": 6.4592,
"mean_token_accuracy": 0.13585175648331643,
"num_tokens": 7005479.0,
"step": 3575
},
{
"entropy": 6.481806850433349,
"epoch": 0.3578747438396561,
"grad_norm": 1.15625,
"learning_rate": 0.0004992473741582291,
"loss": 6.3796,
"mean_token_accuracy": 0.13654778599739076,
"num_tokens": 7015048.0,
"step": 3580
},
{
"entropy": 6.577729082107544,
"epoch": 0.3583745689008847,
"grad_norm": 1.109375,
"learning_rate": 0.0004992444546797298,
"loss": 6.5845,
"mean_token_accuracy": 0.13363236263394357,
"num_tokens": 7024738.0,
"step": 3585
},
{
"entropy": 6.586815977096558,
"epoch": 0.35887439396211324,
"grad_norm": 1.1171875,
"learning_rate": 0.0004992415295592977,
"loss": 6.4966,
"mean_token_accuracy": 0.13316498100757598,
"num_tokens": 7033972.0,
"step": 3590
},
{
"entropy": 6.603455924987793,
"epoch": 0.3593742190233418,
"grad_norm": 1.0703125,
"learning_rate": 0.0004992385987970064,
"loss": 6.5519,
"mean_token_accuracy": 0.1288654737174511,
"num_tokens": 7043713.0,
"step": 3595
},
{
"entropy": 6.652811193466187,
"epoch": 0.3598740440845704,
"grad_norm": 1.015625,
"learning_rate": 0.0004992356623929297,
"loss": 6.519,
"mean_token_accuracy": 0.1351366400718689,
"num_tokens": 7053276.0,
"step": 3600
},
{
"entropy": 6.5362269401550295,
"epoch": 0.360373869145799,
"grad_norm": 1.0546875,
"learning_rate": 0.0004992327203471414,
"loss": 6.5317,
"mean_token_accuracy": 0.1316842831671238,
"num_tokens": 7063610.0,
"step": 3605
},
{
"entropy": 6.559109115600586,
"epoch": 0.36087369420702753,
"grad_norm": 0.99609375,
"learning_rate": 0.0004992297726597156,
"loss": 6.4861,
"mean_token_accuracy": 0.1344970740377903,
"num_tokens": 7073497.0,
"step": 3610
},
{
"entropy": 6.649214267730713,
"epoch": 0.3613735192682561,
"grad_norm": 0.96875,
"learning_rate": 0.0004992268193307264,
"loss": 6.5818,
"mean_token_accuracy": 0.12460133656859398,
"num_tokens": 7084387.0,
"step": 3615
},
{
"entropy": 6.543021535873413,
"epoch": 0.3618733443294847,
"grad_norm": 1.1171875,
"learning_rate": 0.0004992238603602481,
"loss": 6.437,
"mean_token_accuracy": 0.13871280774474143,
"num_tokens": 7093774.0,
"step": 3620
},
{
"entropy": 6.616115570068359,
"epoch": 0.36237316939071323,
"grad_norm": 1.1328125,
"learning_rate": 0.0004992208957483552,
"loss": 6.5866,
"mean_token_accuracy": 0.12746953293681146,
"num_tokens": 7103367.0,
"step": 3625
},
{
"entropy": 6.621992683410644,
"epoch": 0.3628729944519418,
"grad_norm": 1.0625,
"learning_rate": 0.0004992179254951223,
"loss": 6.4998,
"mean_token_accuracy": 0.13220270052552224,
"num_tokens": 7113261.0,
"step": 3630
},
{
"entropy": 6.59494800567627,
"epoch": 0.3633728195131704,
"grad_norm": 1.1640625,
"learning_rate": 0.000499214949600624,
"loss": 6.4897,
"mean_token_accuracy": 0.13366419523954393,
"num_tokens": 7122775.0,
"step": 3635
},
{
"entropy": 6.53905143737793,
"epoch": 0.36387264457439894,
"grad_norm": 1.5078125,
"learning_rate": 0.0004992119680649355,
"loss": 6.5602,
"mean_token_accuracy": 0.13340957909822465,
"num_tokens": 7133369.0,
"step": 3640
},
{
"entropy": 6.573632335662841,
"epoch": 0.3643724696356275,
"grad_norm": 1.125,
"learning_rate": 0.0004992089808881313,
"loss": 6.4246,
"mean_token_accuracy": 0.13840428218245507,
"num_tokens": 7142589.0,
"step": 3645
},
{
"entropy": 6.643885660171509,
"epoch": 0.3648722946968561,
"grad_norm": 1.2109375,
"learning_rate": 0.0004992059880702869,
"loss": 6.6195,
"mean_token_accuracy": 0.12722167894244193,
"num_tokens": 7152260.0,
"step": 3650
},
{
"entropy": 6.599239015579224,
"epoch": 0.36537211975808465,
"grad_norm": 1.21875,
"learning_rate": 0.0004992029896114775,
"loss": 6.5375,
"mean_token_accuracy": 0.1395278438925743,
"num_tokens": 7161297.0,
"step": 3655
},
{
"entropy": 6.536885595321655,
"epoch": 0.36587194481931323,
"grad_norm": 1.0390625,
"learning_rate": 0.0004991999855117787,
"loss": 6.5857,
"mean_token_accuracy": 0.13029498904943465,
"num_tokens": 7172835.0,
"step": 3660
},
{
"entropy": 6.597273063659668,
"epoch": 0.3663717698805418,
"grad_norm": 1.0625,
"learning_rate": 0.0004991969757712659,
"loss": 6.5049,
"mean_token_accuracy": 0.13501314967870712,
"num_tokens": 7182647.0,
"step": 3665
},
{
"entropy": 6.534729909896851,
"epoch": 0.3668715949417704,
"grad_norm": 2.125,
"learning_rate": 0.0004991939603900149,
"loss": 6.5792,
"mean_token_accuracy": 0.1312929093837738,
"num_tokens": 7192048.0,
"step": 3670
},
{
"entropy": 6.60098032951355,
"epoch": 0.36737142000299894,
"grad_norm": 1.0234375,
"learning_rate": 0.0004991909393681015,
"loss": 6.471,
"mean_token_accuracy": 0.13519922867417336,
"num_tokens": 7201747.0,
"step": 3675
},
{
"entropy": 6.591159105300903,
"epoch": 0.3678712450642275,
"grad_norm": 1.1484375,
"learning_rate": 0.0004991879127056017,
"loss": 6.4275,
"mean_token_accuracy": 0.13343789130449296,
"num_tokens": 7210660.0,
"step": 3680
},
{
"entropy": 6.5157793998718265,
"epoch": 0.3683710701254561,
"grad_norm": 1.0703125,
"learning_rate": 0.0004991848804025918,
"loss": 6.4901,
"mean_token_accuracy": 0.13628655001521112,
"num_tokens": 7221474.0,
"step": 3685
},
{
"entropy": 6.5517813205719,
"epoch": 0.36887089518668464,
"grad_norm": 0.9765625,
"learning_rate": 0.000499181842459148,
"loss": 6.4418,
"mean_token_accuracy": 0.13546881526708604,
"num_tokens": 7231700.0,
"step": 3690
},
{
"entropy": 6.497189235687256,
"epoch": 0.36937072024791323,
"grad_norm": 1.0078125,
"learning_rate": 0.0004991787988753467,
"loss": 6.4947,
"mean_token_accuracy": 0.1415654666721821,
"num_tokens": 7241887.0,
"step": 3695
},
{
"entropy": 6.602890396118164,
"epoch": 0.3698705453091418,
"grad_norm": 1.1171875,
"learning_rate": 0.0004991757496512645,
"loss": 6.5258,
"mean_token_accuracy": 0.1301959529519081,
"num_tokens": 7251399.0,
"step": 3700
},
{
"entropy": 6.628644800186157,
"epoch": 0.37037037037037035,
"grad_norm": 1.1953125,
"learning_rate": 0.0004991726947869782,
"loss": 6.6282,
"mean_token_accuracy": 0.1286029815673828,
"num_tokens": 7260555.0,
"step": 3705
},
{
"entropy": 6.601524877548218,
"epoch": 0.37087019543159894,
"grad_norm": 1.0390625,
"learning_rate": 0.0004991696342825645,
"loss": 6.5001,
"mean_token_accuracy": 0.13672052770853044,
"num_tokens": 7270706.0,
"step": 3710
},
{
"entropy": 6.555157279968261,
"epoch": 0.3713700204928275,
"grad_norm": 1.1328125,
"learning_rate": 0.0004991665681381005,
"loss": 6.4983,
"mean_token_accuracy": 0.1283060520887375,
"num_tokens": 7282491.0,
"step": 3715
},
{
"entropy": 6.5200635433197025,
"epoch": 0.37186984555405606,
"grad_norm": 1.0703125,
"learning_rate": 0.0004991634963536633,
"loss": 6.4865,
"mean_token_accuracy": 0.13692417591810227,
"num_tokens": 7292620.0,
"step": 3720
},
{
"entropy": 6.602332019805909,
"epoch": 0.37236967061528464,
"grad_norm": 1.1484375,
"learning_rate": 0.0004991604189293303,
"loss": 6.5526,
"mean_token_accuracy": 0.1268191084265709,
"num_tokens": 7302383.0,
"step": 3725
},
{
"entropy": 6.567366886138916,
"epoch": 0.37286949567651323,
"grad_norm": 1.1953125,
"learning_rate": 0.0004991573358651787,
"loss": 6.4428,
"mean_token_accuracy": 0.14117802530527115,
"num_tokens": 7312429.0,
"step": 3730
},
{
"entropy": 6.622728967666626,
"epoch": 0.3733693207377418,
"grad_norm": 1.1015625,
"learning_rate": 0.0004991542471612864,
"loss": 6.6193,
"mean_token_accuracy": 0.12092858403921128,
"num_tokens": 7322870.0,
"step": 3735
},
{
"entropy": 6.623894309997558,
"epoch": 0.37386914579897035,
"grad_norm": 1.1484375,
"learning_rate": 0.0004991511528177307,
"loss": 6.5435,
"mean_token_accuracy": 0.13075806349515914,
"num_tokens": 7333931.0,
"step": 3740
},
{
"entropy": 6.624968338012695,
"epoch": 0.37436897086019894,
"grad_norm": 1.1484375,
"learning_rate": 0.0004991480528345898,
"loss": 6.5639,
"mean_token_accuracy": 0.12912058010697364,
"num_tokens": 7344083.0,
"step": 3745
},
{
"entropy": 6.618381929397583,
"epoch": 0.3748687959214275,
"grad_norm": 1.140625,
"learning_rate": 0.0004991449472119416,
"loss": 6.5166,
"mean_token_accuracy": 0.134030569344759,
"num_tokens": 7353544.0,
"step": 3750
},
{
"entropy": 6.582413530349731,
"epoch": 0.37536862098265605,
"grad_norm": 1.046875,
"learning_rate": 0.0004991418359498642,
"loss": 6.4539,
"mean_token_accuracy": 0.13216032832860947,
"num_tokens": 7362406.0,
"step": 3755
},
{
"entropy": 6.570158672332764,
"epoch": 0.37586844604388464,
"grad_norm": 1.03125,
"learning_rate": 0.0004991387190484358,
"loss": 6.4796,
"mean_token_accuracy": 0.12776686772704124,
"num_tokens": 7372056.0,
"step": 3760
},
{
"entropy": 6.582331991195678,
"epoch": 0.37636827110511323,
"grad_norm": 1.0703125,
"learning_rate": 0.000499135596507735,
"loss": 6.4762,
"mean_token_accuracy": 0.13580433204770087,
"num_tokens": 7381849.0,
"step": 3765
},
{
"entropy": 6.500207090377808,
"epoch": 0.37686809616634176,
"grad_norm": 1.0859375,
"learning_rate": 0.0004991324683278402,
"loss": 6.4542,
"mean_token_accuracy": 0.13190585225820542,
"num_tokens": 7392648.0,
"step": 3770
},
{
"entropy": 6.490663242340088,
"epoch": 0.37736792122757035,
"grad_norm": 1.109375,
"learning_rate": 0.0004991293345088301,
"loss": 6.3956,
"mean_token_accuracy": 0.13850160986185073,
"num_tokens": 7402121.0,
"step": 3775
},
{
"entropy": 6.571650695800781,
"epoch": 0.37786774628879893,
"grad_norm": 1.1171875,
"learning_rate": 0.0004991261950507837,
"loss": 6.4674,
"mean_token_accuracy": 0.13403821289539336,
"num_tokens": 7412097.0,
"step": 3780
},
{
"entropy": 6.6062475681304935,
"epoch": 0.37836757135002747,
"grad_norm": 1.1484375,
"learning_rate": 0.00049912304995378,
"loss": 6.5886,
"mean_token_accuracy": 0.1247012197971344,
"num_tokens": 7421945.0,
"step": 3785
},
{
"entropy": 6.676407146453857,
"epoch": 0.37886739641125605,
"grad_norm": 0.99609375,
"learning_rate": 0.0004991198992178979,
"loss": 6.5542,
"mean_token_accuracy": 0.1313321188092232,
"num_tokens": 7432245.0,
"step": 3790
},
{
"entropy": 6.555547618865967,
"epoch": 0.37936722147248464,
"grad_norm": 1.0859375,
"learning_rate": 0.0004991167428432168,
"loss": 6.4796,
"mean_token_accuracy": 0.1320396013557911,
"num_tokens": 7441258.0,
"step": 3795
},
{
"entropy": 6.578624200820923,
"epoch": 0.3798670465337132,
"grad_norm": 1.1875,
"learning_rate": 0.0004991135808298162,
"loss": 6.5653,
"mean_token_accuracy": 0.12515707761049272,
"num_tokens": 7451141.0,
"step": 3800
},
{
"entropy": 6.627640056610107,
"epoch": 0.38036687159494176,
"grad_norm": 1.15625,
"learning_rate": 0.0004991104131777755,
"loss": 6.4685,
"mean_token_accuracy": 0.13078691586852073,
"num_tokens": 7461146.0,
"step": 3805
},
{
"entropy": 6.551756477355957,
"epoch": 0.38086669665617034,
"grad_norm": 1.125,
"learning_rate": 0.0004991072398871746,
"loss": 6.4666,
"mean_token_accuracy": 0.1355071634054184,
"num_tokens": 7470307.0,
"step": 3810
},
{
"entropy": 6.52693772315979,
"epoch": 0.38136652171739893,
"grad_norm": 1.078125,
"learning_rate": 0.0004991040609580932,
"loss": 6.5449,
"mean_token_accuracy": 0.13105655312538148,
"num_tokens": 7478944.0,
"step": 3815
},
{
"entropy": 6.558730554580689,
"epoch": 0.38186634677862746,
"grad_norm": 1.1484375,
"learning_rate": 0.0004991008763906112,
"loss": 6.5259,
"mean_token_accuracy": 0.12738186717033387,
"num_tokens": 7488143.0,
"step": 3820
},
{
"entropy": 6.596171617507935,
"epoch": 0.38236617183985605,
"grad_norm": 1.171875,
"learning_rate": 0.0004990976861848087,
"loss": 6.5044,
"mean_token_accuracy": 0.12671239748597146,
"num_tokens": 7497211.0,
"step": 3825
},
{
"entropy": 6.578602981567383,
"epoch": 0.38286599690108464,
"grad_norm": 1.09375,
"learning_rate": 0.0004990944903407663,
"loss": 6.5238,
"mean_token_accuracy": 0.12751783207058906,
"num_tokens": 7506299.0,
"step": 3830
},
{
"entropy": 6.636028146743774,
"epoch": 0.38336582196231317,
"grad_norm": 1.140625,
"learning_rate": 0.0004990912888585641,
"loss": 6.5582,
"mean_token_accuracy": 0.12867696061730385,
"num_tokens": 7516637.0,
"step": 3835
},
{
"entropy": 6.610043239593506,
"epoch": 0.38386564702354176,
"grad_norm": 1.0859375,
"learning_rate": 0.0004990880817382828,
"loss": 6.4581,
"mean_token_accuracy": 0.13559791818261147,
"num_tokens": 7526332.0,
"step": 3840
},
{
"entropy": 6.48463249206543,
"epoch": 0.38436547208477034,
"grad_norm": 1.1640625,
"learning_rate": 0.000499084868980003,
"loss": 6.4213,
"mean_token_accuracy": 0.14019213169813155,
"num_tokens": 7535217.0,
"step": 3845
},
{
"entropy": 6.532036399841308,
"epoch": 0.3848652971459989,
"grad_norm": 1.1484375,
"learning_rate": 0.0004990816505838054,
"loss": 6.5355,
"mean_token_accuracy": 0.13005966916680337,
"num_tokens": 7544538.0,
"step": 3850
},
{
"entropy": 6.659787130355835,
"epoch": 0.38536512220722746,
"grad_norm": 1.0859375,
"learning_rate": 0.0004990784265497713,
"loss": 6.5168,
"mean_token_accuracy": 0.13391273766756057,
"num_tokens": 7555302.0,
"step": 3855
},
{
"entropy": 6.620770120620728,
"epoch": 0.38586494726845605,
"grad_norm": 1.0625,
"learning_rate": 0.0004990751968779817,
"loss": 6.4618,
"mean_token_accuracy": 0.13038535714149474,
"num_tokens": 7564543.0,
"step": 3860
},
{
"entropy": 6.47852931022644,
"epoch": 0.38636477232968464,
"grad_norm": 1.421875,
"learning_rate": 0.0004990719615685176,
"loss": 6.5904,
"mean_token_accuracy": 0.1307446077466011,
"num_tokens": 7575042.0,
"step": 3865
},
{
"entropy": 6.63844108581543,
"epoch": 0.38686459739091317,
"grad_norm": 1.1875,
"learning_rate": 0.0004990687206214608,
"loss": 6.5497,
"mean_token_accuracy": 0.1223531797528267,
"num_tokens": 7584467.0,
"step": 3870
},
{
"entropy": 6.5762358665466305,
"epoch": 0.38736442245214175,
"grad_norm": 1.078125,
"learning_rate": 0.0004990654740368925,
"loss": 6.5193,
"mean_token_accuracy": 0.13060501590371132,
"num_tokens": 7594446.0,
"step": 3875
},
{
"entropy": 6.498785972595215,
"epoch": 0.38786424751337034,
"grad_norm": 1.125,
"learning_rate": 0.0004990622218148947,
"loss": 6.4181,
"mean_token_accuracy": 0.13888733163475991,
"num_tokens": 7603200.0,
"step": 3880
},
{
"entropy": 6.602738571166992,
"epoch": 0.3883640725745989,
"grad_norm": 1.1171875,
"learning_rate": 0.0004990589639555489,
"loss": 6.4854,
"mean_token_accuracy": 0.1386620283126831,
"num_tokens": 7613513.0,
"step": 3885
},
{
"entropy": 6.544764709472656,
"epoch": 0.38886389763582746,
"grad_norm": 1.046875,
"learning_rate": 0.0004990557004589373,
"loss": 6.4546,
"mean_token_accuracy": 0.13224028423428535,
"num_tokens": 7622913.0,
"step": 3890
},
{
"entropy": 6.551820611953735,
"epoch": 0.38936372269705605,
"grad_norm": 1.1015625,
"learning_rate": 0.0004990524313251419,
"loss": 6.492,
"mean_token_accuracy": 0.1308333083987236,
"num_tokens": 7632992.0,
"step": 3895
},
{
"entropy": 6.6810994148254395,
"epoch": 0.3898635477582846,
"grad_norm": 1.375,
"learning_rate": 0.0004990491565542449,
"loss": 6.5105,
"mean_token_accuracy": 0.13149116560816765,
"num_tokens": 7642620.0,
"step": 3900
},
{
"entropy": 6.43835825920105,
"epoch": 0.39036337281951317,
"grad_norm": 1.21875,
"learning_rate": 0.0004990458761463289,
"loss": 6.4185,
"mean_token_accuracy": 0.1379806824028492,
"num_tokens": 7651998.0,
"step": 3905
},
{
"entropy": 6.525279712677002,
"epoch": 0.39086319788074175,
"grad_norm": 1.3125,
"learning_rate": 0.0004990425901014763,
"loss": 6.5002,
"mean_token_accuracy": 0.1255796730518341,
"num_tokens": 7660084.0,
"step": 3910
},
{
"entropy": 6.609419631958008,
"epoch": 0.3913630229419703,
"grad_norm": 1.125,
"learning_rate": 0.0004990392984197697,
"loss": 6.4169,
"mean_token_accuracy": 0.14190827161073685,
"num_tokens": 7668833.0,
"step": 3915
},
{
"entropy": 6.5328577041625975,
"epoch": 0.39186284800319887,
"grad_norm": 1.09375,
"learning_rate": 0.0004990360011012921,
"loss": 6.4779,
"mean_token_accuracy": 0.12975661903619767,
"num_tokens": 7677617.0,
"step": 3920
},
{
"entropy": 6.549026203155518,
"epoch": 0.39236267306442746,
"grad_norm": 1.2265625,
"learning_rate": 0.0004990326981461264,
"loss": 6.5655,
"mean_token_accuracy": 0.12997373789548874,
"num_tokens": 7687794.0,
"step": 3925
},
{
"entropy": 6.6215620040893555,
"epoch": 0.39286249812565605,
"grad_norm": 1.0859375,
"learning_rate": 0.0004990293895543555,
"loss": 6.5157,
"mean_token_accuracy": 0.12998607531189918,
"num_tokens": 7697608.0,
"step": 3930
},
{
"entropy": 6.549281597137451,
"epoch": 0.3933623231868846,
"grad_norm": 1.078125,
"learning_rate": 0.000499026075326063,
"loss": 6.4323,
"mean_token_accuracy": 0.13656977489590644,
"num_tokens": 7707391.0,
"step": 3935
},
{
"entropy": 6.527210140228272,
"epoch": 0.39386214824811316,
"grad_norm": 1.046875,
"learning_rate": 0.000499022755461332,
"loss": 6.4927,
"mean_token_accuracy": 0.1286533445119858,
"num_tokens": 7718715.0,
"step": 3940
},
{
"entropy": 6.575077056884766,
"epoch": 0.39436197330934175,
"grad_norm": 0.9609375,
"learning_rate": 0.000499019429960246,
"loss": 6.4977,
"mean_token_accuracy": 0.129810693860054,
"num_tokens": 7729481.0,
"step": 3945
},
{
"entropy": 6.479593324661255,
"epoch": 0.3948617983705703,
"grad_norm": 1.03125,
"learning_rate": 0.0004990160988228888,
"loss": 6.4501,
"mean_token_accuracy": 0.13362663462758065,
"num_tokens": 7739733.0,
"step": 3950
},
{
"entropy": 6.543328714370728,
"epoch": 0.39536162343179887,
"grad_norm": 1.1796875,
"learning_rate": 0.0004990127620493444,
"loss": 6.4738,
"mean_token_accuracy": 0.1381253831088543,
"num_tokens": 7749109.0,
"step": 3955
},
{
"entropy": 6.560599946975708,
"epoch": 0.39586144849302746,
"grad_norm": 1.421875,
"learning_rate": 0.0004990094196396964,
"loss": 6.535,
"mean_token_accuracy": 0.12604611963033677,
"num_tokens": 7758853.0,
"step": 3960
},
{
"entropy": 6.605568790435791,
"epoch": 0.396361273554256,
"grad_norm": 0.98828125,
"learning_rate": 0.000499006071594029,
"loss": 6.5449,
"mean_token_accuracy": 0.12700080797076224,
"num_tokens": 7770831.0,
"step": 3965
},
{
"entropy": 6.66841197013855,
"epoch": 0.3968610986154846,
"grad_norm": 1.0,
"learning_rate": 0.0004990027179124266,
"loss": 6.5871,
"mean_token_accuracy": 0.12789231762290001,
"num_tokens": 7781094.0,
"step": 3970
},
{
"entropy": 6.71191143989563,
"epoch": 0.39736092367671316,
"grad_norm": 1.125,
"learning_rate": 0.0004989993585949733,
"loss": 6.5594,
"mean_token_accuracy": 0.12633242458105087,
"num_tokens": 7790713.0,
"step": 3975
},
{
"entropy": 6.474120569229126,
"epoch": 0.3978607487379417,
"grad_norm": 1.1640625,
"learning_rate": 0.0004989959936417541,
"loss": 6.4874,
"mean_token_accuracy": 0.13250206485390664,
"num_tokens": 7799425.0,
"step": 3980
},
{
"entropy": 6.495586729049682,
"epoch": 0.3983605737991703,
"grad_norm": 1.5,
"learning_rate": 0.000498992623052853,
"loss": 6.4709,
"mean_token_accuracy": 0.13688051775097848,
"num_tokens": 7809451.0,
"step": 3985
},
{
"entropy": 6.643878364562989,
"epoch": 0.39886039886039887,
"grad_norm": 1.1328125,
"learning_rate": 0.0004989892468283553,
"loss": 6.4957,
"mean_token_accuracy": 0.1341211050748825,
"num_tokens": 7819707.0,
"step": 3990
},
{
"entropy": 6.478731727600097,
"epoch": 0.39936022392162746,
"grad_norm": 1.1796875,
"learning_rate": 0.0004989858649683457,
"loss": 6.4211,
"mean_token_accuracy": 0.13438353165984154,
"num_tokens": 7828851.0,
"step": 3995
},
{
"entropy": 6.477199506759644,
"epoch": 0.399860048982856,
"grad_norm": 1.1953125,
"learning_rate": 0.0004989824774729094,
"loss": 6.4987,
"mean_token_accuracy": 0.13335368856787683,
"num_tokens": 7837999.0,
"step": 4000
},
{
"entropy": 6.646010208129883,
"epoch": 0.4003598740440846,
"grad_norm": 1.125,
"learning_rate": 0.0004989790843421317,
"loss": 6.586,
"mean_token_accuracy": 0.1316763199865818,
"num_tokens": 7847227.0,
"step": 4005
},
{
"entropy": 6.672080945968628,
"epoch": 0.40085969910531316,
"grad_norm": 1.2109375,
"learning_rate": 0.0004989756855760979,
"loss": 6.5304,
"mean_token_accuracy": 0.13430671617388726,
"num_tokens": 7857102.0,
"step": 4010
},
{
"entropy": 6.524146556854248,
"epoch": 0.4013595241665417,
"grad_norm": 1.2578125,
"learning_rate": 0.0004989722811748934,
"loss": 6.5753,
"mean_token_accuracy": 0.12646115496754645,
"num_tokens": 7867395.0,
"step": 4015
},
{
"entropy": 6.590912961959839,
"epoch": 0.4018593492277703,
"grad_norm": 1.171875,
"learning_rate": 0.0004989688711386039,
"loss": 6.4217,
"mean_token_accuracy": 0.13748682290315628,
"num_tokens": 7876461.0,
"step": 4020
},
{
"entropy": 6.519725799560547,
"epoch": 0.40235917428899887,
"grad_norm": 1.140625,
"learning_rate": 0.0004989654554673152,
"loss": 6.5127,
"mean_token_accuracy": 0.12524235621094704,
"num_tokens": 7886856.0,
"step": 4025
},
{
"entropy": 6.491343593597412,
"epoch": 0.4028589993502274,
"grad_norm": 1.03125,
"learning_rate": 0.0004989620341611133,
"loss": 6.3593,
"mean_token_accuracy": 0.1446170762181282,
"num_tokens": 7896255.0,
"step": 4030
},
{
"entropy": 6.551962852478027,
"epoch": 0.403358824411456,
"grad_norm": 1.0078125,
"learning_rate": 0.0004989586072200843,
"loss": 6.5105,
"mean_token_accuracy": 0.13109808564186096,
"num_tokens": 7905827.0,
"step": 4035
},
{
"entropy": 6.5564357280731205,
"epoch": 0.40385864947268457,
"grad_norm": 1.140625,
"learning_rate": 0.0004989551746443143,
"loss": 6.4984,
"mean_token_accuracy": 0.12900145277380942,
"num_tokens": 7915610.0,
"step": 4040
},
{
"entropy": 6.583031940460205,
"epoch": 0.4043584745339131,
"grad_norm": 1.109375,
"learning_rate": 0.0004989517364338899,
"loss": 6.5231,
"mean_token_accuracy": 0.1292193613946438,
"num_tokens": 7926209.0,
"step": 4045
},
{
"entropy": 6.561289119720459,
"epoch": 0.4048582995951417,
"grad_norm": 1.203125,
"learning_rate": 0.0004989482925888974,
"loss": 6.5025,
"mean_token_accuracy": 0.13480555191636084,
"num_tokens": 7936411.0,
"step": 4050
},
{
"entropy": 6.505609750747681,
"epoch": 0.4053581246563703,
"grad_norm": 1.1015625,
"learning_rate": 0.0004989448431094233,
"loss": 6.4467,
"mean_token_accuracy": 0.1410248190164566,
"num_tokens": 7945874.0,
"step": 4055
},
{
"entropy": 6.591428661346436,
"epoch": 0.40585794971759886,
"grad_norm": 1.15625,
"learning_rate": 0.0004989413879955548,
"loss": 6.4565,
"mean_token_accuracy": 0.12914087250828743,
"num_tokens": 7955303.0,
"step": 4060
},
{
"entropy": 6.515615463256836,
"epoch": 0.4063577747788274,
"grad_norm": 1.0859375,
"learning_rate": 0.0004989379272473785,
"loss": 6.4364,
"mean_token_accuracy": 0.13901440128684045,
"num_tokens": 7964365.0,
"step": 4065
},
{
"entropy": 6.532591009140015,
"epoch": 0.406857599840056,
"grad_norm": 1.0703125,
"learning_rate": 0.0004989344608649815,
"loss": 6.4414,
"mean_token_accuracy": 0.13178981989622116,
"num_tokens": 7973692.0,
"step": 4070
},
{
"entropy": 6.5347418785095215,
"epoch": 0.40735742490128457,
"grad_norm": 1.0625,
"learning_rate": 0.0004989309888484511,
"loss": 6.4575,
"mean_token_accuracy": 0.1335175082087517,
"num_tokens": 7984003.0,
"step": 4075
},
{
"entropy": 6.627656030654907,
"epoch": 0.4078572499625131,
"grad_norm": 1.3203125,
"learning_rate": 0.0004989275111978748,
"loss": 6.5465,
"mean_token_accuracy": 0.1315997950732708,
"num_tokens": 7994515.0,
"step": 4080
},
{
"entropy": 6.502608394622802,
"epoch": 0.4083570750237417,
"grad_norm": 1.203125,
"learning_rate": 0.0004989240279133398,
"loss": 6.433,
"mean_token_accuracy": 0.1282997891306877,
"num_tokens": 8004000.0,
"step": 4085
},
{
"entropy": 6.487736749649048,
"epoch": 0.4088569000849703,
"grad_norm": 1.1796875,
"learning_rate": 0.0004989205389949339,
"loss": 6.4803,
"mean_token_accuracy": 0.13587168827652932,
"num_tokens": 8013880.0,
"step": 4090
},
{
"entropy": 6.555855751037598,
"epoch": 0.4093567251461988,
"grad_norm": 1.0859375,
"learning_rate": 0.0004989170444427448,
"loss": 6.3614,
"mean_token_accuracy": 0.1401887021958828,
"num_tokens": 8024395.0,
"step": 4095
},
{
"entropy": 6.534576511383056,
"epoch": 0.4098565502074274,
"grad_norm": 1.2421875,
"learning_rate": 0.0004989135442568606,
"loss": 6.4302,
"mean_token_accuracy": 0.13582985028624533,
"num_tokens": 8033198.0,
"step": 4100
},
{
"entropy": 6.4525598049163815,
"epoch": 0.410356375268656,
"grad_norm": 1.1015625,
"learning_rate": 0.0004989100384373693,
"loss": 6.3785,
"mean_token_accuracy": 0.1344170868396759,
"num_tokens": 8042387.0,
"step": 4105
},
{
"entropy": 6.509235954284668,
"epoch": 0.4108562003298845,
"grad_norm": 1.3046875,
"learning_rate": 0.0004989065269843588,
"loss": 6.516,
"mean_token_accuracy": 0.12826233580708504,
"num_tokens": 8051993.0,
"step": 4110
},
{
"entropy": 6.524654579162598,
"epoch": 0.4113560253911131,
"grad_norm": 1.109375,
"learning_rate": 0.000498903009897918,
"loss": 6.4876,
"mean_token_accuracy": 0.1279144637286663,
"num_tokens": 8062122.0,
"step": 4115
},
{
"entropy": 6.60549750328064,
"epoch": 0.4118558504523417,
"grad_norm": 1.15625,
"learning_rate": 0.0004988994871781349,
"loss": 6.4879,
"mean_token_accuracy": 0.13297053351998328,
"num_tokens": 8071828.0,
"step": 4120
},
{
"entropy": 6.536817789077759,
"epoch": 0.4123556755135703,
"grad_norm": 1.0703125,
"learning_rate": 0.0004988959588250983,
"loss": 6.445,
"mean_token_accuracy": 0.1284802883863449,
"num_tokens": 8081017.0,
"step": 4125
},
{
"entropy": 6.535213756561279,
"epoch": 0.4128555005747988,
"grad_norm": 1.2421875,
"learning_rate": 0.000498892424838897,
"loss": 6.4904,
"mean_token_accuracy": 0.13281431496143342,
"num_tokens": 8091706.0,
"step": 4130
},
{
"entropy": 6.538304424285888,
"epoch": 0.4133553256360274,
"grad_norm": 1.140625,
"learning_rate": 0.0004988888852196199,
"loss": 6.4655,
"mean_token_accuracy": 0.1341558001935482,
"num_tokens": 8100098.0,
"step": 4135
},
{
"entropy": 6.576635551452637,
"epoch": 0.413855150697256,
"grad_norm": 1.21875,
"learning_rate": 0.0004988853399673562,
"loss": 6.5215,
"mean_token_accuracy": 0.1287394106388092,
"num_tokens": 8110003.0,
"step": 4140
},
{
"entropy": 6.525849962234497,
"epoch": 0.4143549757584845,
"grad_norm": 1.1015625,
"learning_rate": 0.0004988817890821948,
"loss": 6.4145,
"mean_token_accuracy": 0.13765130341053008,
"num_tokens": 8119440.0,
"step": 4145
},
{
"entropy": 6.53408031463623,
"epoch": 0.4148548008197131,
"grad_norm": 1.046875,
"learning_rate": 0.0004988782325642252,
"loss": 6.4767,
"mean_token_accuracy": 0.13233601972460746,
"num_tokens": 8130347.0,
"step": 4150
},
{
"entropy": 6.593100214004517,
"epoch": 0.4153546258809417,
"grad_norm": 1.15625,
"learning_rate": 0.000498874670413537,
"loss": 6.4934,
"mean_token_accuracy": 0.1305489718914032,
"num_tokens": 8139252.0,
"step": 4155
},
{
"entropy": 6.594889116287232,
"epoch": 0.4158544509421702,
"grad_norm": 1.2421875,
"learning_rate": 0.0004988711026302197,
"loss": 6.5715,
"mean_token_accuracy": 0.12711631059646605,
"num_tokens": 8149130.0,
"step": 4160
},
{
"entropy": 6.5417625427246096,
"epoch": 0.4163542760033988,
"grad_norm": 1.1796875,
"learning_rate": 0.0004988675292143629,
"loss": 6.4799,
"mean_token_accuracy": 0.13304642513394355,
"num_tokens": 8158300.0,
"step": 4165
},
{
"entropy": 6.560239791870117,
"epoch": 0.4168541010646274,
"grad_norm": 1.0859375,
"learning_rate": 0.0004988639501660568,
"loss": 6.4359,
"mean_token_accuracy": 0.13240988105535506,
"num_tokens": 8168631.0,
"step": 4170
},
{
"entropy": 6.556834077835083,
"epoch": 0.4173539261258559,
"grad_norm": 1.140625,
"learning_rate": 0.0004988603654853913,
"loss": 6.5486,
"mean_token_accuracy": 0.12870696261525155,
"num_tokens": 8178942.0,
"step": 4175
},
{
"entropy": 6.592477560043335,
"epoch": 0.4178537511870845,
"grad_norm": 1.09375,
"learning_rate": 0.0004988567751724565,
"loss": 6.4592,
"mean_token_accuracy": 0.1329029843211174,
"num_tokens": 8188633.0,
"step": 4180
},
{
"entropy": 6.53848614692688,
"epoch": 0.4183535762483131,
"grad_norm": 1.03125,
"learning_rate": 0.000498853179227343,
"loss": 6.4481,
"mean_token_accuracy": 0.13518220633268357,
"num_tokens": 8198486.0,
"step": 4185
},
{
"entropy": 6.5179526805877686,
"epoch": 0.4188534013095417,
"grad_norm": 1.125,
"learning_rate": 0.000498849577650141,
"loss": 6.481,
"mean_token_accuracy": 0.13624608516693115,
"num_tokens": 8208369.0,
"step": 4190
},
{
"entropy": 6.452465963363648,
"epoch": 0.4193532263707702,
"grad_norm": 1.078125,
"learning_rate": 0.0004988459704409413,
"loss": 6.3423,
"mean_token_accuracy": 0.14007183760404587,
"num_tokens": 8217968.0,
"step": 4195
},
{
"entropy": 6.56020336151123,
"epoch": 0.4198530514319988,
"grad_norm": 1.1015625,
"learning_rate": 0.0004988423575998345,
"loss": 6.4993,
"mean_token_accuracy": 0.13017036393284798,
"num_tokens": 8228704.0,
"step": 4200
},
{
"entropy": 6.545264673233032,
"epoch": 0.4203528764932274,
"grad_norm": 1.1640625,
"learning_rate": 0.0004988387391269117,
"loss": 6.4002,
"mean_token_accuracy": 0.1359180249273777,
"num_tokens": 8239185.0,
"step": 4205
},
{
"entropy": 6.438202905654907,
"epoch": 0.4208527015544559,
"grad_norm": 1.1953125,
"learning_rate": 0.0004988351150222638,
"loss": 6.4721,
"mean_token_accuracy": 0.13446867540478707,
"num_tokens": 8248644.0,
"step": 4210
},
{
"entropy": 6.527329444885254,
"epoch": 0.4213525266156845,
"grad_norm": 1.40625,
"learning_rate": 0.0004988314852859819,
"loss": 6.5223,
"mean_token_accuracy": 0.12920535802841188,
"num_tokens": 8259875.0,
"step": 4215
},
{
"entropy": 6.443457221984863,
"epoch": 0.4218523516769131,
"grad_norm": 1.2109375,
"learning_rate": 0.0004988278499181575,
"loss": 6.4116,
"mean_token_accuracy": 0.13716713190078736,
"num_tokens": 8268894.0,
"step": 4220
},
{
"entropy": 6.511584758758545,
"epoch": 0.4223521767381416,
"grad_norm": 1.2265625,
"learning_rate": 0.000498824208918882,
"loss": 6.4848,
"mean_token_accuracy": 0.12496452629566193,
"num_tokens": 8279236.0,
"step": 4225
},
{
"entropy": 6.498587369918823,
"epoch": 0.4228520017993702,
"grad_norm": 1.09375,
"learning_rate": 0.000498820562288247,
"loss": 6.3875,
"mean_token_accuracy": 0.1388476811349392,
"num_tokens": 8288464.0,
"step": 4230
},
{
"entropy": 6.420559930801391,
"epoch": 0.4233518268605988,
"grad_norm": 1.03125,
"learning_rate": 0.0004988169100263442,
"loss": 6.3736,
"mean_token_accuracy": 0.13870823681354522,
"num_tokens": 8298291.0,
"step": 4235
},
{
"entropy": 6.570061349868775,
"epoch": 0.4238516519218274,
"grad_norm": 1.0859375,
"learning_rate": 0.0004988132521332656,
"loss": 6.5566,
"mean_token_accuracy": 0.1263101190328598,
"num_tokens": 8308543.0,
"step": 4240
},
{
"entropy": 6.634110450744629,
"epoch": 0.4243514769830559,
"grad_norm": 1.2421875,
"learning_rate": 0.0004988095886091031,
"loss": 6.541,
"mean_token_accuracy": 0.12622241377830506,
"num_tokens": 8318310.0,
"step": 4245
},
{
"entropy": 6.533967781066894,
"epoch": 0.4248513020442845,
"grad_norm": 1.1875,
"learning_rate": 0.0004988059194539489,
"loss": 6.4387,
"mean_token_accuracy": 0.12934722527861595,
"num_tokens": 8327853.0,
"step": 4250
},
{
"entropy": 6.508464908599853,
"epoch": 0.4253511271055131,
"grad_norm": 1.078125,
"learning_rate": 0.0004988022446678954,
"loss": 6.5343,
"mean_token_accuracy": 0.1303732469677925,
"num_tokens": 8337734.0,
"step": 4255
},
{
"entropy": 6.5576441287994385,
"epoch": 0.4258509521667416,
"grad_norm": 1.0859375,
"learning_rate": 0.0004987985642510352,
"loss": 6.483,
"mean_token_accuracy": 0.13290337175130845,
"num_tokens": 8346681.0,
"step": 4260
},
{
"entropy": 6.561308908462524,
"epoch": 0.4263507772279702,
"grad_norm": 1.0859375,
"learning_rate": 0.0004987948782034605,
"loss": 6.3408,
"mean_token_accuracy": 0.137284716963768,
"num_tokens": 8355597.0,
"step": 4265
},
{
"entropy": 6.51908130645752,
"epoch": 0.4268506022891988,
"grad_norm": 1.09375,
"learning_rate": 0.0004987911865252644,
"loss": 6.4712,
"mean_token_accuracy": 0.13078599497675897,
"num_tokens": 8365529.0,
"step": 4270
},
{
"entropy": 6.421928787231446,
"epoch": 0.42735042735042733,
"grad_norm": 1.078125,
"learning_rate": 0.0004987874892165395,
"loss": 6.4018,
"mean_token_accuracy": 0.1368158020079136,
"num_tokens": 8374727.0,
"step": 4275
},
{
"entropy": 6.50489821434021,
"epoch": 0.4278502524116559,
"grad_norm": 1.015625,
"learning_rate": 0.000498783786277379,
"loss": 6.4324,
"mean_token_accuracy": 0.13258315697312356,
"num_tokens": 8385624.0,
"step": 4280
},
{
"entropy": 6.5570708274841305,
"epoch": 0.4283500774728845,
"grad_norm": 1.234375,
"learning_rate": 0.0004987800777078759,
"loss": 6.415,
"mean_token_accuracy": 0.13189322054386138,
"num_tokens": 8395242.0,
"step": 4285
},
{
"entropy": 6.376562833786011,
"epoch": 0.42884990253411304,
"grad_norm": 1.046875,
"learning_rate": 0.0004987763635081238,
"loss": 6.3413,
"mean_token_accuracy": 0.13998268991708757,
"num_tokens": 8404946.0,
"step": 4290
},
{
"entropy": 6.521537446975708,
"epoch": 0.4293497275953416,
"grad_norm": 1.171875,
"learning_rate": 0.000498772643678216,
"loss": 6.6026,
"mean_token_accuracy": 0.12647197842597963,
"num_tokens": 8413835.0,
"step": 4295
},
{
"entropy": 6.618172264099121,
"epoch": 0.4298495526565702,
"grad_norm": 1.140625,
"learning_rate": 0.0004987689182182459,
"loss": 6.4391,
"mean_token_accuracy": 0.13389185667037964,
"num_tokens": 8423338.0,
"step": 4300
},
{
"entropy": 6.585845947265625,
"epoch": 0.4303493777177988,
"grad_norm": 1.1484375,
"learning_rate": 0.0004987651871283075,
"loss": 6.5685,
"mean_token_accuracy": 0.12797584161162376,
"num_tokens": 8434370.0,
"step": 4305
},
{
"entropy": 6.524690246582031,
"epoch": 0.43084920277902733,
"grad_norm": 1.046875,
"learning_rate": 0.0004987614504084946,
"loss": 6.4106,
"mean_token_accuracy": 0.1358144573867321,
"num_tokens": 8444517.0,
"step": 4310
},
{
"entropy": 6.499991178512573,
"epoch": 0.4313490278402559,
"grad_norm": 1.2890625,
"learning_rate": 0.0004987577080589012,
"loss": 6.4371,
"mean_token_accuracy": 0.13471659496426583,
"num_tokens": 8453269.0,
"step": 4315
},
{
"entropy": 6.513748502731323,
"epoch": 0.4318488529014845,
"grad_norm": 1.1640625,
"learning_rate": 0.0004987539600796213,
"loss": 6.4578,
"mean_token_accuracy": 0.13477371484041215,
"num_tokens": 8462142.0,
"step": 4320
},
{
"entropy": 6.614743041992187,
"epoch": 0.43234867796271303,
"grad_norm": 1.109375,
"learning_rate": 0.0004987502064707494,
"loss": 6.4766,
"mean_token_accuracy": 0.12982487678527832,
"num_tokens": 8472020.0,
"step": 4325
},
{
"entropy": 6.492146778106689,
"epoch": 0.4328485030239416,
"grad_norm": 1.1484375,
"learning_rate": 0.0004987464472323799,
"loss": 6.4943,
"mean_token_accuracy": 0.13149992004036903,
"num_tokens": 8481985.0,
"step": 4330
},
{
"entropy": 6.5443164825439455,
"epoch": 0.4333483280851702,
"grad_norm": 1.125,
"learning_rate": 0.0004987426823646074,
"loss": 6.4616,
"mean_token_accuracy": 0.13821166157722473,
"num_tokens": 8490859.0,
"step": 4335
},
{
"entropy": 6.5202713966369625,
"epoch": 0.43384815314639874,
"grad_norm": 1.109375,
"learning_rate": 0.0004987389118675266,
"loss": 6.4504,
"mean_token_accuracy": 0.13739967420697213,
"num_tokens": 8500714.0,
"step": 4340
},
{
"entropy": 6.4656414031982425,
"epoch": 0.4343479782076273,
"grad_norm": 1.1953125,
"learning_rate": 0.0004987351357412322,
"loss": 6.359,
"mean_token_accuracy": 0.13838136345148086,
"num_tokens": 8509832.0,
"step": 4345
},
{
"entropy": 6.387941169738769,
"epoch": 0.4348478032688559,
"grad_norm": 1.2109375,
"learning_rate": 0.0004987313539858196,
"loss": 6.3165,
"mean_token_accuracy": 0.13517126068472862,
"num_tokens": 8519455.0,
"step": 4350
},
{
"entropy": 6.603800630569458,
"epoch": 0.43534762833008445,
"grad_norm": 1.2890625,
"learning_rate": 0.0004987275666013836,
"loss": 6.5333,
"mean_token_accuracy": 0.12609480768442155,
"num_tokens": 8529015.0,
"step": 4355
},
{
"entropy": 6.546134996414184,
"epoch": 0.43584745339131303,
"grad_norm": 1.09375,
"learning_rate": 0.0004987237735880195,
"loss": 6.4506,
"mean_token_accuracy": 0.12945613712072374,
"num_tokens": 8539081.0,
"step": 4360
},
{
"entropy": 6.472061967849731,
"epoch": 0.4363472784525416,
"grad_norm": 0.9765625,
"learning_rate": 0.0004987199749458229,
"loss": 6.4586,
"mean_token_accuracy": 0.13243156746029855,
"num_tokens": 8549889.0,
"step": 4365
},
{
"entropy": 6.561690330505371,
"epoch": 0.4368471035137702,
"grad_norm": 1.0390625,
"learning_rate": 0.0004987161706748893,
"loss": 6.4557,
"mean_token_accuracy": 0.1361939549446106,
"num_tokens": 8560331.0,
"step": 4370
},
{
"entropy": 6.500359106063843,
"epoch": 0.43734692857499874,
"grad_norm": 1.1328125,
"learning_rate": 0.0004987123607753144,
"loss": 6.406,
"mean_token_accuracy": 0.13452138230204583,
"num_tokens": 8570035.0,
"step": 4375
},
{
"entropy": 6.502156162261963,
"epoch": 0.4378467536362273,
"grad_norm": 1.2265625,
"learning_rate": 0.000498708545247194,
"loss": 6.4084,
"mean_token_accuracy": 0.135636755079031,
"num_tokens": 8579069.0,
"step": 4380
},
{
"entropy": 6.543806171417236,
"epoch": 0.4383465786974559,
"grad_norm": 1.1015625,
"learning_rate": 0.0004987047240906243,
"loss": 6.5111,
"mean_token_accuracy": 0.13440850898623466,
"num_tokens": 8589542.0,
"step": 4385
},
{
"entropy": 6.561945962905884,
"epoch": 0.43884640375868444,
"grad_norm": 1.3046875,
"learning_rate": 0.0004987008973057012,
"loss": 6.4396,
"mean_token_accuracy": 0.13307615146040916,
"num_tokens": 8600143.0,
"step": 4390
},
{
"entropy": 6.540645694732666,
"epoch": 0.43934622881991303,
"grad_norm": 1.125,
"learning_rate": 0.0004986970648925211,
"loss": 6.4148,
"mean_token_accuracy": 0.1355074718594551,
"num_tokens": 8609062.0,
"step": 4395
},
{
"entropy": 6.533525371551514,
"epoch": 0.4398460538811416,
"grad_norm": 1.140625,
"learning_rate": 0.0004986932268511804,
"loss": 6.461,
"mean_token_accuracy": 0.1307988114655018,
"num_tokens": 8618115.0,
"step": 4400
},
{
"entropy": 6.419683265686035,
"epoch": 0.44034587894237015,
"grad_norm": 1.1484375,
"learning_rate": 0.0004986893831817758,
"loss": 6.3072,
"mean_token_accuracy": 0.14577516689896583,
"num_tokens": 8627091.0,
"step": 4405
},
{
"entropy": 6.4738565444946286,
"epoch": 0.44084570400359874,
"grad_norm": 1.1484375,
"learning_rate": 0.0004986855338844038,
"loss": 6.381,
"mean_token_accuracy": 0.1391140937805176,
"num_tokens": 8637194.0,
"step": 4410
},
{
"entropy": 6.47957673072815,
"epoch": 0.4413455290648273,
"grad_norm": 1.390625,
"learning_rate": 0.0004986816789591613,
"loss": 6.4288,
"mean_token_accuracy": 0.13185917735099792,
"num_tokens": 8647281.0,
"step": 4415
},
{
"entropy": 6.6051921367645265,
"epoch": 0.44184535412605586,
"grad_norm": 1.1953125,
"learning_rate": 0.0004986778184061453,
"loss": 6.5441,
"mean_token_accuracy": 0.13117969557642936,
"num_tokens": 8658004.0,
"step": 4420
},
{
"entropy": 6.441143751144409,
"epoch": 0.44234517918728444,
"grad_norm": 1.1640625,
"learning_rate": 0.0004986739522254529,
"loss": 6.3107,
"mean_token_accuracy": 0.14155919775366782,
"num_tokens": 8666878.0,
"step": 4425
},
{
"entropy": 6.481678533554077,
"epoch": 0.44284500424851303,
"grad_norm": 1.1171875,
"learning_rate": 0.0004986700804171816,
"loss": 6.4058,
"mean_token_accuracy": 0.1369277760386467,
"num_tokens": 8677695.0,
"step": 4430
},
{
"entropy": 6.407256317138672,
"epoch": 0.4433448293097416,
"grad_norm": 1.140625,
"learning_rate": 0.0004986662029814285,
"loss": 6.2354,
"mean_token_accuracy": 0.14666323587298394,
"num_tokens": 8686767.0,
"step": 4435
},
{
"entropy": 6.504606628417969,
"epoch": 0.44384465437097015,
"grad_norm": 1.171875,
"learning_rate": 0.0004986623199182913,
"loss": 6.4643,
"mean_token_accuracy": 0.13264728337526321,
"num_tokens": 8695804.0,
"step": 4440
},
{
"entropy": 6.438683414459229,
"epoch": 0.44434447943219874,
"grad_norm": 1.0859375,
"learning_rate": 0.0004986584312278678,
"loss": 6.4185,
"mean_token_accuracy": 0.13090021386742592,
"num_tokens": 8706079.0,
"step": 4445
},
{
"entropy": 6.667967414855957,
"epoch": 0.4448443044934273,
"grad_norm": 1.09375,
"learning_rate": 0.0004986545369102556,
"loss": 6.5395,
"mean_token_accuracy": 0.13461889550089837,
"num_tokens": 8715754.0,
"step": 4450
},
{
"entropy": 6.575337076187134,
"epoch": 0.44534412955465585,
"grad_norm": 1.1328125,
"learning_rate": 0.0004986506369655528,
"loss": 6.4377,
"mean_token_accuracy": 0.13373658135533334,
"num_tokens": 8725745.0,
"step": 4455
},
{
"entropy": 6.422351360321045,
"epoch": 0.44584395461588444,
"grad_norm": 1.234375,
"learning_rate": 0.0004986467313938575,
"loss": 6.4272,
"mean_token_accuracy": 0.13778617233037949,
"num_tokens": 8735043.0,
"step": 4460
},
{
"entropy": 6.448146152496338,
"epoch": 0.44634377967711303,
"grad_norm": 1.140625,
"learning_rate": 0.000498642820195268,
"loss": 6.3667,
"mean_token_accuracy": 0.13664159774780274,
"num_tokens": 8744631.0,
"step": 4465
},
{
"entropy": 6.504123306274414,
"epoch": 0.44684360473834156,
"grad_norm": 1.1640625,
"learning_rate": 0.0004986389033698827,
"loss": 6.4403,
"mean_token_accuracy": 0.1341246597468853,
"num_tokens": 8754148.0,
"step": 4470
},
{
"entropy": 6.534858274459839,
"epoch": 0.44734342979957015,
"grad_norm": 1.15625,
"learning_rate": 0.0004986349809178002,
"loss": 6.4663,
"mean_token_accuracy": 0.13697151467204094,
"num_tokens": 8763230.0,
"step": 4475
},
{
"entropy": 6.5859139919281,
"epoch": 0.44784325486079873,
"grad_norm": 1.1875,
"learning_rate": 0.0004986310528391192,
"loss": 6.5168,
"mean_token_accuracy": 0.1334538169205189,
"num_tokens": 8772547.0,
"step": 4480
},
{
"entropy": 6.53432879447937,
"epoch": 0.44834307992202727,
"grad_norm": 1.2265625,
"learning_rate": 0.0004986271191339383,
"loss": 6.36,
"mean_token_accuracy": 0.13986174315214156,
"num_tokens": 8782766.0,
"step": 4485
},
{
"entropy": 6.493881511688232,
"epoch": 0.44884290498325585,
"grad_norm": 1.1484375,
"learning_rate": 0.0004986231798023566,
"loss": 6.4023,
"mean_token_accuracy": 0.13627419099211693,
"num_tokens": 8791793.0,
"step": 4490
},
{
"entropy": 6.477091693878174,
"epoch": 0.44934273004448444,
"grad_norm": 1.046875,
"learning_rate": 0.0004986192348444734,
"loss": 6.4534,
"mean_token_accuracy": 0.1348723776638508,
"num_tokens": 8801888.0,
"step": 4495
},
{
"entropy": 6.488378667831421,
"epoch": 0.449842555105713,
"grad_norm": 1.296875,
"learning_rate": 0.0004986152842603877,
"loss": 6.2839,
"mean_token_accuracy": 0.14627811834216117,
"num_tokens": 8810629.0,
"step": 4500
},
{
"entropy": 6.524313354492188,
"epoch": 0.45034238016694156,
"grad_norm": 1.1328125,
"learning_rate": 0.0004986113280501989,
"loss": 6.5078,
"mean_token_accuracy": 0.1245477132499218,
"num_tokens": 8820598.0,
"step": 4505
},
{
"entropy": 6.5409088134765625,
"epoch": 0.45084220522817015,
"grad_norm": 1.0703125,
"learning_rate": 0.0004986073662140068,
"loss": 6.4382,
"mean_token_accuracy": 0.13651844710111619,
"num_tokens": 8829814.0,
"step": 4510
},
{
"entropy": 6.469896697998047,
"epoch": 0.45134203028939873,
"grad_norm": 1.1171875,
"learning_rate": 0.0004986033987519109,
"loss": 6.4126,
"mean_token_accuracy": 0.12688309997320174,
"num_tokens": 8839899.0,
"step": 4515
},
{
"entropy": 6.608504676818848,
"epoch": 0.45184185535062726,
"grad_norm": 1.171875,
"learning_rate": 0.0004985994256640108,
"loss": 6.4306,
"mean_token_accuracy": 0.13766766712069511,
"num_tokens": 8848318.0,
"step": 4520
},
{
"entropy": 6.532405996322632,
"epoch": 0.45234168041185585,
"grad_norm": 1.0859375,
"learning_rate": 0.0004985954469504069,
"loss": 6.408,
"mean_token_accuracy": 0.13353217393159866,
"num_tokens": 8857965.0,
"step": 4525
},
{
"entropy": 6.439678907394409,
"epoch": 0.45284150547308444,
"grad_norm": 1.3046875,
"learning_rate": 0.0004985914626111991,
"loss": 6.421,
"mean_token_accuracy": 0.13979350104928018,
"num_tokens": 8868324.0,
"step": 4530
},
{
"entropy": 6.4588335990905765,
"epoch": 0.45334133053431297,
"grad_norm": 1.140625,
"learning_rate": 0.0004985874726464875,
"loss": 6.4175,
"mean_token_accuracy": 0.13455140441656113,
"num_tokens": 8877110.0,
"step": 4535
},
{
"entropy": 6.46298451423645,
"epoch": 0.45384115559554156,
"grad_norm": 1.2265625,
"learning_rate": 0.0004985834770563727,
"loss": 6.3951,
"mean_token_accuracy": 0.13256110697984697,
"num_tokens": 8886635.0,
"step": 4540
},
{
"entropy": 6.49652886390686,
"epoch": 0.45434098065677014,
"grad_norm": 1.1875,
"learning_rate": 0.0004985794758409552,
"loss": 6.3737,
"mean_token_accuracy": 0.13694811761379241,
"num_tokens": 8895184.0,
"step": 4545
},
{
"entropy": 6.395736885070801,
"epoch": 0.4548408057179987,
"grad_norm": 1.375,
"learning_rate": 0.0004985754690003354,
"loss": 6.3589,
"mean_token_accuracy": 0.14108183607459068,
"num_tokens": 8905638.0,
"step": 4550
},
{
"entropy": 6.502994155883789,
"epoch": 0.45534063077922726,
"grad_norm": 1.1875,
"learning_rate": 0.0004985714565346145,
"loss": 6.4459,
"mean_token_accuracy": 0.13694894015789033,
"num_tokens": 8915038.0,
"step": 4555
},
{
"entropy": 6.537573909759521,
"epoch": 0.45584045584045585,
"grad_norm": 1.15625,
"learning_rate": 0.0004985674384438933,
"loss": 6.4107,
"mean_token_accuracy": 0.13412584215402604,
"num_tokens": 8923745.0,
"step": 4560
},
{
"entropy": 6.398061323165893,
"epoch": 0.45634028090168444,
"grad_norm": 1.078125,
"learning_rate": 0.0004985634147282729,
"loss": 6.3852,
"mean_token_accuracy": 0.1342081107199192,
"num_tokens": 8934019.0,
"step": 4565
},
{
"entropy": 6.565010213851929,
"epoch": 0.45684010596291297,
"grad_norm": 1.109375,
"learning_rate": 0.0004985593853878544,
"loss": 6.4597,
"mean_token_accuracy": 0.13615109026432037,
"num_tokens": 8943763.0,
"step": 4570
},
{
"entropy": 6.4767285823822025,
"epoch": 0.45733993102414155,
"grad_norm": 1.1171875,
"learning_rate": 0.0004985553504227394,
"loss": 6.3688,
"mean_token_accuracy": 0.13533643633127213,
"num_tokens": 8953757.0,
"step": 4575
},
{
"entropy": 6.380968999862671,
"epoch": 0.45783975608537014,
"grad_norm": 1.0625,
"learning_rate": 0.0004985513098330293,
"loss": 6.3726,
"mean_token_accuracy": 0.13547075018286706,
"num_tokens": 8963233.0,
"step": 4580
},
{
"entropy": 6.429535341262818,
"epoch": 0.4583395811465987,
"grad_norm": 1.2109375,
"learning_rate": 0.0004985472636188257,
"loss": 6.334,
"mean_token_accuracy": 0.14010989367961885,
"num_tokens": 8972210.0,
"step": 4585
},
{
"entropy": 6.4599534034729,
"epoch": 0.45883940620782726,
"grad_norm": 1.1328125,
"learning_rate": 0.0004985432117802305,
"loss": 6.2878,
"mean_token_accuracy": 0.14164225086569787,
"num_tokens": 8982818.0,
"step": 4590
},
{
"entropy": 6.512010669708252,
"epoch": 0.45933923126905585,
"grad_norm": 1.1484375,
"learning_rate": 0.0004985391543173456,
"loss": 6.4562,
"mean_token_accuracy": 0.13241320922970773,
"num_tokens": 8992019.0,
"step": 4595
},
{
"entropy": 6.457628440856934,
"epoch": 0.4598390563302844,
"grad_norm": 1.1875,
"learning_rate": 0.000498535091230273,
"loss": 6.3613,
"mean_token_accuracy": 0.1401025503873825,
"num_tokens": 9000891.0,
"step": 4600
},
{
"entropy": 6.527205944061279,
"epoch": 0.46033888139151297,
"grad_norm": 1.296875,
"learning_rate": 0.0004985310225191152,
"loss": 6.412,
"mean_token_accuracy": 0.1276500105857849,
"num_tokens": 9010660.0,
"step": 4605
},
{
"entropy": 6.482425165176392,
"epoch": 0.46083870645274155,
"grad_norm": 1.046875,
"learning_rate": 0.0004985269481839744,
"loss": 6.4576,
"mean_token_accuracy": 0.13516637980937957,
"num_tokens": 9020078.0,
"step": 4610
},
{
"entropy": 6.481579303741455,
"epoch": 0.4613385315139701,
"grad_norm": 1.0859375,
"learning_rate": 0.0004985228682249529,
"loss": 6.3964,
"mean_token_accuracy": 0.1379421815276146,
"num_tokens": 9030728.0,
"step": 4615
},
{
"entropy": 6.526381587982177,
"epoch": 0.46183835657519867,
"grad_norm": 1.125,
"learning_rate": 0.0004985187826421538,
"loss": 6.3237,
"mean_token_accuracy": 0.13987818658351897,
"num_tokens": 9041271.0,
"step": 4620
},
{
"entropy": 6.385977172851563,
"epoch": 0.46233818163642726,
"grad_norm": 1.0703125,
"learning_rate": 0.0004985146914356795,
"loss": 6.4432,
"mean_token_accuracy": 0.13601470440626146,
"num_tokens": 9050135.0,
"step": 4625
},
{
"entropy": 6.5035289287567135,
"epoch": 0.46283800669765585,
"grad_norm": 1.1328125,
"learning_rate": 0.000498510594605633,
"loss": 6.4235,
"mean_token_accuracy": 0.13525536954402922,
"num_tokens": 9059374.0,
"step": 4630
},
{
"entropy": 6.548880481719971,
"epoch": 0.4633378317588844,
"grad_norm": 1.1171875,
"learning_rate": 0.0004985064921521177,
"loss": 6.4377,
"mean_token_accuracy": 0.13258222863078117,
"num_tokens": 9069568.0,
"step": 4635
},
{
"entropy": 6.504767894744873,
"epoch": 0.46383765682011296,
"grad_norm": 1.125,
"learning_rate": 0.0004985023840752364,
"loss": 6.3755,
"mean_token_accuracy": 0.14026534408330918,
"num_tokens": 9079952.0,
"step": 4640
},
{
"entropy": 6.401940536499024,
"epoch": 0.46433748188134155,
"grad_norm": 1.390625,
"learning_rate": 0.0004984982703750926,
"loss": 6.3212,
"mean_token_accuracy": 0.149515238404274,
"num_tokens": 9088968.0,
"step": 4645
},
{
"entropy": 6.44706449508667,
"epoch": 0.4648373069425701,
"grad_norm": 1.171875,
"learning_rate": 0.0004984941510517899,
"loss": 6.4427,
"mean_token_accuracy": 0.13683839961886407,
"num_tokens": 9099736.0,
"step": 4650
},
{
"entropy": 6.4781208515167235,
"epoch": 0.46533713200379867,
"grad_norm": 1.140625,
"learning_rate": 0.0004984900261054319,
"loss": 6.4369,
"mean_token_accuracy": 0.13208477199077606,
"num_tokens": 9109200.0,
"step": 4655
},
{
"entropy": 6.534184360504151,
"epoch": 0.46583695706502726,
"grad_norm": 1.140625,
"learning_rate": 0.0004984858955361224,
"loss": 6.5517,
"mean_token_accuracy": 0.12318905889987945,
"num_tokens": 9118283.0,
"step": 4660
},
{
"entropy": 6.538456726074219,
"epoch": 0.4663367821262558,
"grad_norm": 1.203125,
"learning_rate": 0.0004984817593439651,
"loss": 6.3773,
"mean_token_accuracy": 0.13581222742795945,
"num_tokens": 9126765.0,
"step": 4665
},
{
"entropy": 6.465129613876343,
"epoch": 0.4668366071874844,
"grad_norm": 1.1796875,
"learning_rate": 0.0004984776175290643,
"loss": 6.4294,
"mean_token_accuracy": 0.13170129358768462,
"num_tokens": 9137210.0,
"step": 4670
},
{
"entropy": 6.479430150985718,
"epoch": 0.46733643224871296,
"grad_norm": 1.1796875,
"learning_rate": 0.0004984734700915242,
"loss": 6.3411,
"mean_token_accuracy": 0.14183183684945105,
"num_tokens": 9147811.0,
"step": 4675
},
{
"entropy": 6.435356187820434,
"epoch": 0.4678362573099415,
"grad_norm": 1.1796875,
"learning_rate": 0.000498469317031449,
"loss": 6.3485,
"mean_token_accuracy": 0.137740558385849,
"num_tokens": 9159080.0,
"step": 4680
},
{
"entropy": 6.416247367858887,
"epoch": 0.4683360823711701,
"grad_norm": 1.2734375,
"learning_rate": 0.0004984651583489434,
"loss": 6.3671,
"mean_token_accuracy": 0.13596429228782653,
"num_tokens": 9168959.0,
"step": 4685
},
{
"entropy": 6.447586631774902,
"epoch": 0.46883590743239867,
"grad_norm": 1.296875,
"learning_rate": 0.0004984609940441119,
"loss": 6.4147,
"mean_token_accuracy": 0.1337486557662487,
"num_tokens": 9178873.0,
"step": 4690
},
{
"entropy": 6.451929187774658,
"epoch": 0.46933573249362726,
"grad_norm": 1.1796875,
"learning_rate": 0.0004984568241170593,
"loss": 6.2733,
"mean_token_accuracy": 0.1413310095667839,
"num_tokens": 9188056.0,
"step": 4695
},
{
"entropy": 6.450091743469239,
"epoch": 0.4698355575548558,
"grad_norm": 1.125,
"learning_rate": 0.0004984526485678905,
"loss": 6.4999,
"mean_token_accuracy": 0.1394587591290474,
"num_tokens": 9197993.0,
"step": 4700
},
{
"entropy": 6.562577104568481,
"epoch": 0.4703353826160844,
"grad_norm": 1.09375,
"learning_rate": 0.0004984484673967105,
"loss": 6.4733,
"mean_token_accuracy": 0.13233150988817216,
"num_tokens": 9207719.0,
"step": 4705
},
{
"entropy": 6.489262342453003,
"epoch": 0.47083520767731296,
"grad_norm": 1.2109375,
"learning_rate": 0.0004984442806036246,
"loss": 6.3661,
"mean_token_accuracy": 0.1441465824842453,
"num_tokens": 9217036.0,
"step": 4710
},
{
"entropy": 6.422714519500732,
"epoch": 0.4713350327385415,
"grad_norm": 1.1171875,
"learning_rate": 0.0004984400881887381,
"loss": 6.3662,
"mean_token_accuracy": 0.1343640834093094,
"num_tokens": 9226132.0,
"step": 4715
},
{
"entropy": 6.536276626586914,
"epoch": 0.4718348577997701,
"grad_norm": 1.3203125,
"learning_rate": 0.0004984358901521565,
"loss": 6.4179,
"mean_token_accuracy": 0.13391911014914512,
"num_tokens": 9235914.0,
"step": 4720
},
{
"entropy": 6.55507378578186,
"epoch": 0.47233468286099867,
"grad_norm": 1.203125,
"learning_rate": 0.0004984316864939853,
"loss": 6.4239,
"mean_token_accuracy": 0.1325272463262081,
"num_tokens": 9245269.0,
"step": 4725
},
{
"entropy": 6.311108779907227,
"epoch": 0.4728345079222272,
"grad_norm": 1.15625,
"learning_rate": 0.0004984274772143304,
"loss": 6.2979,
"mean_token_accuracy": 0.1423199161887169,
"num_tokens": 9254107.0,
"step": 4730
},
{
"entropy": 6.557476949691773,
"epoch": 0.4733343329834558,
"grad_norm": 1.203125,
"learning_rate": 0.0004984232623132977,
"loss": 6.4943,
"mean_token_accuracy": 0.12752621173858641,
"num_tokens": 9265219.0,
"step": 4735
},
{
"entropy": 6.538834142684936,
"epoch": 0.4738341580446844,
"grad_norm": 1.4765625,
"learning_rate": 0.0004984190417909932,
"loss": 6.4225,
"mean_token_accuracy": 0.13008161038160324,
"num_tokens": 9274610.0,
"step": 4740
},
{
"entropy": 6.45155897140503,
"epoch": 0.4743339831059129,
"grad_norm": 1.1328125,
"learning_rate": 0.0004984148156475231,
"loss": 6.436,
"mean_token_accuracy": 0.13551058396697044,
"num_tokens": 9283576.0,
"step": 4745
},
{
"entropy": 6.529959487915039,
"epoch": 0.4748338081671415,
"grad_norm": 1.2109375,
"learning_rate": 0.0004984105838829937,
"loss": 6.4436,
"mean_token_accuracy": 0.13864721208810807,
"num_tokens": 9293377.0,
"step": 4750
},
{
"entropy": 6.529016351699829,
"epoch": 0.4753336332283701,
"grad_norm": 1.171875,
"learning_rate": 0.0004984063464975116,
"loss": 6.5055,
"mean_token_accuracy": 0.1282574638724327,
"num_tokens": 9302647.0,
"step": 4755
},
{
"entropy": 6.542206239700318,
"epoch": 0.47583345828959867,
"grad_norm": 1.1171875,
"learning_rate": 0.0004984021034911833,
"loss": 6.4795,
"mean_token_accuracy": 0.12635858356952667,
"num_tokens": 9312153.0,
"step": 4760
},
{
"entropy": 6.540885162353516,
"epoch": 0.4763332833508272,
"grad_norm": 1.2265625,
"learning_rate": 0.0004983978548641154,
"loss": 6.3736,
"mean_token_accuracy": 0.1392926350235939,
"num_tokens": 9320537.0,
"step": 4765
},
{
"entropy": 6.387734365463257,
"epoch": 0.4768331084120558,
"grad_norm": 1.078125,
"learning_rate": 0.0004983936006164151,
"loss": 6.2867,
"mean_token_accuracy": 0.1454198345541954,
"num_tokens": 9330193.0,
"step": 4770
},
{
"entropy": 6.492685031890869,
"epoch": 0.47733293347328437,
"grad_norm": 1.1171875,
"learning_rate": 0.0004983893407481892,
"loss": 6.4815,
"mean_token_accuracy": 0.13175106048583984,
"num_tokens": 9340377.0,
"step": 4775
},
{
"entropy": 6.528011465072632,
"epoch": 0.4778327585345129,
"grad_norm": 1.2109375,
"learning_rate": 0.0004983850752595451,
"loss": 6.4333,
"mean_token_accuracy": 0.13777383416891098,
"num_tokens": 9349773.0,
"step": 4780
},
{
"entropy": 6.4005608558654785,
"epoch": 0.4783325835957415,
"grad_norm": 1.1328125,
"learning_rate": 0.0004983808041505898,
"loss": 6.3544,
"mean_token_accuracy": 0.13698267564177513,
"num_tokens": 9359844.0,
"step": 4785
},
{
"entropy": 6.4836437702178955,
"epoch": 0.4788324086569701,
"grad_norm": 1.1484375,
"learning_rate": 0.0004983765274214311,
"loss": 6.4306,
"mean_token_accuracy": 0.1377669893205166,
"num_tokens": 9369744.0,
"step": 4790
},
{
"entropy": 6.507730484008789,
"epoch": 0.4793322337181986,
"grad_norm": 1.0859375,
"learning_rate": 0.0004983722450721764,
"loss": 6.3844,
"mean_token_accuracy": 0.13529214337468148,
"num_tokens": 9378489.0,
"step": 4795
},
{
"entropy": 6.529411745071411,
"epoch": 0.4798320587794272,
"grad_norm": 1.15625,
"learning_rate": 0.0004983679571029336,
"loss": 6.4549,
"mean_token_accuracy": 0.13523728400468826,
"num_tokens": 9388833.0,
"step": 4800
},
{
"entropy": 6.493711948394775,
"epoch": 0.4803318838406558,
"grad_norm": 1.15625,
"learning_rate": 0.0004983636635138103,
"loss": 6.3591,
"mean_token_accuracy": 0.13547564148902894,
"num_tokens": 9398010.0,
"step": 4805
},
{
"entropy": 6.490125274658203,
"epoch": 0.4808317089018843,
"grad_norm": 1.0078125,
"learning_rate": 0.0004983593643049148,
"loss": 6.4615,
"mean_token_accuracy": 0.13016107976436614,
"num_tokens": 9407847.0,
"step": 4810
},
{
"entropy": 6.425223159790039,
"epoch": 0.4813315339631129,
"grad_norm": 1.1875,
"learning_rate": 0.0004983550594763552,
"loss": 6.3871,
"mean_token_accuracy": 0.13814985528588294,
"num_tokens": 9416965.0,
"step": 4815
},
{
"entropy": 6.485588502883911,
"epoch": 0.4818313590243415,
"grad_norm": 1.171875,
"learning_rate": 0.0004983507490282397,
"loss": 6.3954,
"mean_token_accuracy": 0.1414204254746437,
"num_tokens": 9426646.0,
"step": 4820
},
{
"entropy": 6.435629606246948,
"epoch": 0.4823311840855701,
"grad_norm": 1.2265625,
"learning_rate": 0.0004983464329606768,
"loss": 6.3709,
"mean_token_accuracy": 0.13402513712644576,
"num_tokens": 9435961.0,
"step": 4825
},
{
"entropy": 6.4540657043457035,
"epoch": 0.4828310091467986,
"grad_norm": 1.1328125,
"learning_rate": 0.0004983421112737752,
"loss": 6.3523,
"mean_token_accuracy": 0.1387752465903759,
"num_tokens": 9446369.0,
"step": 4830
},
{
"entropy": 6.523642683029175,
"epoch": 0.4833308342080272,
"grad_norm": 1.203125,
"learning_rate": 0.0004983377839676435,
"loss": 6.347,
"mean_token_accuracy": 0.1420137882232666,
"num_tokens": 9456315.0,
"step": 4835
},
{
"entropy": 6.528051900863647,
"epoch": 0.4838306592692558,
"grad_norm": 1.1640625,
"learning_rate": 0.0004983334510423906,
"loss": 6.5053,
"mean_token_accuracy": 0.12767389342188834,
"num_tokens": 9465500.0,
"step": 4840
},
{
"entropy": 6.427554559707642,
"epoch": 0.4843304843304843,
"grad_norm": 1.1015625,
"learning_rate": 0.0004983291124981257,
"loss": 6.4475,
"mean_token_accuracy": 0.13194834515452386,
"num_tokens": 9475437.0,
"step": 4845
},
{
"entropy": 6.48316764831543,
"epoch": 0.4848303093917129,
"grad_norm": 1.1171875,
"learning_rate": 0.0004983247683349576,
"loss": 6.3722,
"mean_token_accuracy": 0.1303052343428135,
"num_tokens": 9485178.0,
"step": 4850
},
{
"entropy": 6.5141924858093265,
"epoch": 0.4853301344529415,
"grad_norm": 1.125,
"learning_rate": 0.0004983204185529959,
"loss": 6.3816,
"mean_token_accuracy": 0.13886707350611688,
"num_tokens": 9494666.0,
"step": 4855
},
{
"entropy": 6.416102647781372,
"epoch": 0.48582995951417,
"grad_norm": 1.1640625,
"learning_rate": 0.0004983160631523499,
"loss": 6.4427,
"mean_token_accuracy": 0.14189637899398805,
"num_tokens": 9504538.0,
"step": 4860
},
{
"entropy": 6.554702472686768,
"epoch": 0.4863297845753986,
"grad_norm": 1.0625,
"learning_rate": 0.0004983117021331293,
"loss": 6.4054,
"mean_token_accuracy": 0.13481321856379508,
"num_tokens": 9514660.0,
"step": 4865
},
{
"entropy": 6.397809267044067,
"epoch": 0.4868296096366272,
"grad_norm": 1.140625,
"learning_rate": 0.0004983073354954436,
"loss": 6.3722,
"mean_token_accuracy": 0.1399870201945305,
"num_tokens": 9524734.0,
"step": 4870
},
{
"entropy": 6.486401319503784,
"epoch": 0.4873294346978557,
"grad_norm": 1.3046875,
"learning_rate": 0.0004983029632394029,
"loss": 6.3394,
"mean_token_accuracy": 0.13598363772034644,
"num_tokens": 9533469.0,
"step": 4875
},
{
"entropy": 6.479533624649048,
"epoch": 0.4878292597590843,
"grad_norm": 1.09375,
"learning_rate": 0.000498298585365117,
"loss": 6.3949,
"mean_token_accuracy": 0.1376280166208744,
"num_tokens": 9543916.0,
"step": 4880
},
{
"entropy": 6.520917797088623,
"epoch": 0.4883290848203129,
"grad_norm": 1.1484375,
"learning_rate": 0.0004982942018726963,
"loss": 6.3099,
"mean_token_accuracy": 0.140919092297554,
"num_tokens": 9553767.0,
"step": 4885
},
{
"entropy": 6.464224529266358,
"epoch": 0.4888289098815415,
"grad_norm": 1.140625,
"learning_rate": 0.0004982898127622508,
"loss": 6.4237,
"mean_token_accuracy": 0.1348918780684471,
"num_tokens": 9564713.0,
"step": 4890
},
{
"entropy": 6.415190839767456,
"epoch": 0.48932873494277,
"grad_norm": 1.09375,
"learning_rate": 0.0004982854180338911,
"loss": 6.4848,
"mean_token_accuracy": 0.1310221068561077,
"num_tokens": 9576216.0,
"step": 4895
},
{
"entropy": 6.580247640609741,
"epoch": 0.4898285600039986,
"grad_norm": 1.0859375,
"learning_rate": 0.0004982810176877279,
"loss": 6.4432,
"mean_token_accuracy": 0.13468685895204544,
"num_tokens": 9586428.0,
"step": 4900
},
{
"entropy": 6.5749287605285645,
"epoch": 0.4903283850652272,
"grad_norm": 1.171875,
"learning_rate": 0.0004982766117238716,
"loss": 6.4563,
"mean_token_accuracy": 0.13091298565268517,
"num_tokens": 9596548.0,
"step": 4905
},
{
"entropy": 6.4557301044464115,
"epoch": 0.4908282101264557,
"grad_norm": 1.203125,
"learning_rate": 0.0004982722001424331,
"loss": 6.3512,
"mean_token_accuracy": 0.13645192086696625,
"num_tokens": 9605190.0,
"step": 4910
},
{
"entropy": 6.470714426040649,
"epoch": 0.4913280351876843,
"grad_norm": 1.109375,
"learning_rate": 0.0004982677829435236,
"loss": 6.3487,
"mean_token_accuracy": 0.13710420876741408,
"num_tokens": 9614682.0,
"step": 4915
},
{
"entropy": 6.482896995544434,
"epoch": 0.4918278602489129,
"grad_norm": 1.109375,
"learning_rate": 0.0004982633601272543,
"loss": 6.3889,
"mean_token_accuracy": 0.1296637199819088,
"num_tokens": 9625026.0,
"step": 4920
},
{
"entropy": 6.420542049407959,
"epoch": 0.4923276853101414,
"grad_norm": 1.21875,
"learning_rate": 0.0004982589316937361,
"loss": 6.3716,
"mean_token_accuracy": 0.13665490970015526,
"num_tokens": 9634301.0,
"step": 4925
},
{
"entropy": 6.427209806442261,
"epoch": 0.49282751037137,
"grad_norm": 1.2421875,
"learning_rate": 0.0004982544976430808,
"loss": 6.3837,
"mean_token_accuracy": 0.1369131959974766,
"num_tokens": 9645025.0,
"step": 4930
},
{
"entropy": 6.456084489822388,
"epoch": 0.4933273354325986,
"grad_norm": 1.078125,
"learning_rate": 0.0004982500579753995,
"loss": 6.3413,
"mean_token_accuracy": 0.14008644819259644,
"num_tokens": 9655595.0,
"step": 4935
},
{
"entropy": 6.4558305740356445,
"epoch": 0.49382716049382713,
"grad_norm": 1.171875,
"learning_rate": 0.0004982456126908044,
"loss": 6.3777,
"mean_token_accuracy": 0.13302047550678253,
"num_tokens": 9664770.0,
"step": 4940
},
{
"entropy": 6.510966777801514,
"epoch": 0.4943269855550557,
"grad_norm": 1.21875,
"learning_rate": 0.0004982411617894071,
"loss": 6.3645,
"mean_token_accuracy": 0.13752162009477614,
"num_tokens": 9673820.0,
"step": 4945
},
{
"entropy": 6.418698024749756,
"epoch": 0.4948268106162843,
"grad_norm": 1.0703125,
"learning_rate": 0.0004982367052713196,
"loss": 6.3652,
"mean_token_accuracy": 0.14175712838768958,
"num_tokens": 9683087.0,
"step": 4950
},
{
"entropy": 6.533307361602783,
"epoch": 0.4953266356775129,
"grad_norm": 1.1796875,
"learning_rate": 0.0004982322431366541,
"loss": 6.4969,
"mean_token_accuracy": 0.13403859436511995,
"num_tokens": 9692798.0,
"step": 4955
},
{
"entropy": 6.5089301586151125,
"epoch": 0.4958264607387414,
"grad_norm": 1.2109375,
"learning_rate": 0.0004982277753855227,
"loss": 6.291,
"mean_token_accuracy": 0.1398764967918396,
"num_tokens": 9703062.0,
"step": 4960
},
{
"entropy": 6.411831426620483,
"epoch": 0.49632628579997,
"grad_norm": 1.1796875,
"learning_rate": 0.000498223302018038,
"loss": 6.2841,
"mean_token_accuracy": 0.1449793666601181,
"num_tokens": 9713223.0,
"step": 4965
},
{
"entropy": 6.429420089721679,
"epoch": 0.4968261108611986,
"grad_norm": 1.328125,
"learning_rate": 0.0004982188230343124,
"loss": 6.3939,
"mean_token_accuracy": 0.13417016491293907,
"num_tokens": 9722483.0,
"step": 4970
},
{
"entropy": 6.4690508365631105,
"epoch": 0.49732593592242713,
"grad_norm": 1.1484375,
"learning_rate": 0.0004982143384344587,
"loss": 6.3529,
"mean_token_accuracy": 0.13833339735865594,
"num_tokens": 9732350.0,
"step": 4975
},
{
"entropy": 6.46622486114502,
"epoch": 0.4978257609836557,
"grad_norm": 1.2421875,
"learning_rate": 0.0004982098482185897,
"loss": 6.3785,
"mean_token_accuracy": 0.13927287757396697,
"num_tokens": 9741824.0,
"step": 4980
},
{
"entropy": 6.43610634803772,
"epoch": 0.4983255860448843,
"grad_norm": 1.1640625,
"learning_rate": 0.0004982053523868182,
"loss": 6.332,
"mean_token_accuracy": 0.13948794230818748,
"num_tokens": 9751428.0,
"step": 4985
},
{
"entropy": 6.389789247512818,
"epoch": 0.49882541110611284,
"grad_norm": 1.09375,
"learning_rate": 0.0004982008509392576,
"loss": 6.2551,
"mean_token_accuracy": 0.1467537611722946,
"num_tokens": 9761430.0,
"step": 4990
},
{
"entropy": 6.504963636398315,
"epoch": 0.4993252361673414,
"grad_norm": 1.234375,
"learning_rate": 0.000498196343876021,
"loss": 6.4839,
"mean_token_accuracy": 0.13137512877583504,
"num_tokens": 9771540.0,
"step": 4995
},
{
"entropy": 6.538363409042359,
"epoch": 0.49982506122857,
"grad_norm": 1.09375,
"learning_rate": 0.0004981918311972219,
"loss": 6.4581,
"mean_token_accuracy": 0.1347872421145439,
"num_tokens": 9781342.0,
"step": 5000
},
{
"entropy": 6.491554594039917,
"epoch": 0.5003248862897985,
"grad_norm": 1.1796875,
"learning_rate": 0.0004981873129029737,
"loss": 6.4406,
"mean_token_accuracy": 0.13302661776542662,
"num_tokens": 9790313.0,
"step": 5005
},
{
"entropy": 6.572258710861206,
"epoch": 0.5008247113510271,
"grad_norm": 1.140625,
"learning_rate": 0.00049818278899339,
"loss": 6.3802,
"mean_token_accuracy": 0.1342344142496586,
"num_tokens": 9799656.0,
"step": 5010
},
{
"entropy": 6.428929805755615,
"epoch": 0.5013245364122557,
"grad_norm": 1.3125,
"learning_rate": 0.000498178259468585,
"loss": 6.3472,
"mean_token_accuracy": 0.14534548670053482,
"num_tokens": 9808971.0,
"step": 5015
},
{
"entropy": 6.464481258392334,
"epoch": 0.5018243614734843,
"grad_norm": 1.1875,
"learning_rate": 0.0004981737243286722,
"loss": 6.4189,
"mean_token_accuracy": 0.13541440293192863,
"num_tokens": 9820397.0,
"step": 5020
},
{
"entropy": 6.518436908721924,
"epoch": 0.5023241865347129,
"grad_norm": 1.1640625,
"learning_rate": 0.0004981691835737661,
"loss": 6.3917,
"mean_token_accuracy": 0.13676153644919395,
"num_tokens": 9829309.0,
"step": 5025
},
{
"entropy": 6.472116947174072,
"epoch": 0.5028240115959414,
"grad_norm": 1.140625,
"learning_rate": 0.0004981646372039807,
"loss": 6.3974,
"mean_token_accuracy": 0.13122374638915063,
"num_tokens": 9838950.0,
"step": 5030
},
{
"entropy": 6.494530963897705,
"epoch": 0.50332383665717,
"grad_norm": 1.3671875,
"learning_rate": 0.0004981600852194305,
"loss": 6.3491,
"mean_token_accuracy": 0.14054525196552276,
"num_tokens": 9849613.0,
"step": 5035
},
{
"entropy": 6.537146854400635,
"epoch": 0.5038236617183985,
"grad_norm": 1.078125,
"learning_rate": 0.00049815552762023,
"loss": 6.5049,
"mean_token_accuracy": 0.12978233993053437,
"num_tokens": 9860842.0,
"step": 5040
},
{
"entropy": 6.366571950912475,
"epoch": 0.5043234867796271,
"grad_norm": 1.0390625,
"learning_rate": 0.0004981509644064937,
"loss": 6.3503,
"mean_token_accuracy": 0.14064454808831214,
"num_tokens": 9871936.0,
"step": 5045
},
{
"entropy": 6.407763433456421,
"epoch": 0.5048233118408557,
"grad_norm": 1.171875,
"learning_rate": 0.0004981463955783367,
"loss": 6.2417,
"mean_token_accuracy": 0.14102230221033096,
"num_tokens": 9882142.0,
"step": 5050
},
{
"entropy": 6.455689096450806,
"epoch": 0.5053231369020843,
"grad_norm": 1.21875,
"learning_rate": 0.0004981418211358736,
"loss": 6.3604,
"mean_token_accuracy": 0.13463332876563072,
"num_tokens": 9892713.0,
"step": 5055
},
{
"entropy": 6.457704782485962,
"epoch": 0.5058229619633129,
"grad_norm": 1.0859375,
"learning_rate": 0.0004981372410792199,
"loss": 6.4166,
"mean_token_accuracy": 0.13474635332822799,
"num_tokens": 9901706.0,
"step": 5060
},
{
"entropy": 6.381054067611695,
"epoch": 0.5063227870245414,
"grad_norm": 1.109375,
"learning_rate": 0.0004981326554084906,
"loss": 6.3465,
"mean_token_accuracy": 0.1387743279337883,
"num_tokens": 9912444.0,
"step": 5065
},
{
"entropy": 6.56711049079895,
"epoch": 0.50682261208577,
"grad_norm": 1.1640625,
"learning_rate": 0.0004981280641238011,
"loss": 6.3506,
"mean_token_accuracy": 0.13491351827979087,
"num_tokens": 9921593.0,
"step": 5070
},
{
"entropy": 6.379525375366211,
"epoch": 0.5073224371469985,
"grad_norm": 1.09375,
"learning_rate": 0.0004981234672252669,
"loss": 6.2987,
"mean_token_accuracy": 0.14403324723243713,
"num_tokens": 9931362.0,
"step": 5075
},
{
"entropy": 6.52586612701416,
"epoch": 0.5078222622082271,
"grad_norm": 1.15625,
"learning_rate": 0.0004981188647130037,
"loss": 6.4528,
"mean_token_accuracy": 0.13757158145308496,
"num_tokens": 9941877.0,
"step": 5080
},
{
"entropy": 6.583056926727295,
"epoch": 0.5083220872694557,
"grad_norm": 1.0546875,
"learning_rate": 0.0004981142565871272,
"loss": 6.5055,
"mean_token_accuracy": 0.12831874638795854,
"num_tokens": 9952516.0,
"step": 5085
},
{
"entropy": 6.603437805175782,
"epoch": 0.5088219123306843,
"grad_norm": 1.1796875,
"learning_rate": 0.0004981096428477535,
"loss": 6.5572,
"mean_token_accuracy": 0.12907882556319236,
"num_tokens": 9963078.0,
"step": 5090
},
{
"entropy": 6.561179685592651,
"epoch": 0.5093217373919128,
"grad_norm": 1.15625,
"learning_rate": 0.0004981050234949986,
"loss": 6.4342,
"mean_token_accuracy": 0.1301390290260315,
"num_tokens": 9972816.0,
"step": 5095
},
{
"entropy": 6.472829532623291,
"epoch": 0.5098215624531414,
"grad_norm": 1.1328125,
"learning_rate": 0.0004981003985289786,
"loss": 6.3965,
"mean_token_accuracy": 0.1327144332230091,
"num_tokens": 9982773.0,
"step": 5100
},
{
"entropy": 6.4751060009002686,
"epoch": 0.51032138751437,
"grad_norm": 1.296875,
"learning_rate": 0.0004980957679498101,
"loss": 6.3835,
"mean_token_accuracy": 0.14121959432959558,
"num_tokens": 9992602.0,
"step": 5105
},
{
"entropy": 6.479527425765991,
"epoch": 0.5108212125755985,
"grad_norm": 1.15625,
"learning_rate": 0.0004980911317576095,
"loss": 6.3428,
"mean_token_accuracy": 0.13944500610232352,
"num_tokens": 10002185.0,
"step": 5110
},
{
"entropy": 6.4052345752716064,
"epoch": 0.5113210376368271,
"grad_norm": 1.171875,
"learning_rate": 0.0004980864899524933,
"loss": 6.3415,
"mean_token_accuracy": 0.13430991321802138,
"num_tokens": 10012028.0,
"step": 5115
},
{
"entropy": 6.437929916381836,
"epoch": 0.5118208626980557,
"grad_norm": 1.2265625,
"learning_rate": 0.0004980818425345786,
"loss": 6.4286,
"mean_token_accuracy": 0.13085610717535018,
"num_tokens": 10021914.0,
"step": 5120
},
{
"entropy": 6.511262130737305,
"epoch": 0.5123206877592843,
"grad_norm": 1.1328125,
"learning_rate": 0.000498077189503982,
"loss": 6.3966,
"mean_token_accuracy": 0.13715369179844855,
"num_tokens": 10031246.0,
"step": 5125
},
{
"entropy": 6.553551101684571,
"epoch": 0.5128205128205128,
"grad_norm": 1.203125,
"learning_rate": 0.0004980725308608208,
"loss": 6.402,
"mean_token_accuracy": 0.13357761651277542,
"num_tokens": 10042064.0,
"step": 5130
},
{
"entropy": 6.362481212615966,
"epoch": 0.5133203378817414,
"grad_norm": 2.21875,
"learning_rate": 0.0004980678666052121,
"loss": 6.19,
"mean_token_accuracy": 0.14961197972297668,
"num_tokens": 10052943.0,
"step": 5135
},
{
"entropy": 6.404932165145874,
"epoch": 0.51382016294297,
"grad_norm": 1.1640625,
"learning_rate": 0.0004980631967372733,
"loss": 6.3697,
"mean_token_accuracy": 0.13727065026760102,
"num_tokens": 10062497.0,
"step": 5140
},
{
"entropy": 6.464839744567871,
"epoch": 0.5143199880041985,
"grad_norm": 1.1171875,
"learning_rate": 0.0004980585212571218,
"loss": 6.3645,
"mean_token_accuracy": 0.1414380431175232,
"num_tokens": 10072819.0,
"step": 5145
},
{
"entropy": 6.358304023742676,
"epoch": 0.5148198130654271,
"grad_norm": 1.1015625,
"learning_rate": 0.0004980538401648753,
"loss": 6.2407,
"mean_token_accuracy": 0.14484174624085427,
"num_tokens": 10081834.0,
"step": 5150
},
{
"entropy": 6.44873366355896,
"epoch": 0.5153196381266557,
"grad_norm": 1.1328125,
"learning_rate": 0.0004980491534606517,
"loss": 6.3624,
"mean_token_accuracy": 0.14508387371897696,
"num_tokens": 10090746.0,
"step": 5155
},
{
"entropy": 6.4216272830963135,
"epoch": 0.5158194631878842,
"grad_norm": 1.1796875,
"learning_rate": 0.0004980444611445686,
"loss": 6.3656,
"mean_token_accuracy": 0.13868543729186059,
"num_tokens": 10101728.0,
"step": 5160
},
{
"entropy": 6.4501988887786865,
"epoch": 0.5163192882491128,
"grad_norm": 1.21875,
"learning_rate": 0.0004980397632167444,
"loss": 6.3363,
"mean_token_accuracy": 0.14399878904223443,
"num_tokens": 10111641.0,
"step": 5165
},
{
"entropy": 6.4942793369293215,
"epoch": 0.5168191133103414,
"grad_norm": 1.140625,
"learning_rate": 0.0004980350596772971,
"loss": 6.3046,
"mean_token_accuracy": 0.13481297269463538,
"num_tokens": 10120708.0,
"step": 5170
},
{
"entropy": 6.419431209564209,
"epoch": 0.51731893837157,
"grad_norm": 1.203125,
"learning_rate": 0.0004980303505263451,
"loss": 6.3311,
"mean_token_accuracy": 0.1368158668279648,
"num_tokens": 10131279.0,
"step": 5175
},
{
"entropy": 6.412103843688965,
"epoch": 0.5178187634327985,
"grad_norm": 1.1796875,
"learning_rate": 0.0004980256357640069,
"loss": 6.2256,
"mean_token_accuracy": 0.14284660071134567,
"num_tokens": 10140329.0,
"step": 5180
},
{
"entropy": 6.509219026565551,
"epoch": 0.5183185884940271,
"grad_norm": 1.046875,
"learning_rate": 0.0004980209153904011,
"loss": 6.4162,
"mean_token_accuracy": 0.13610876351594925,
"num_tokens": 10149658.0,
"step": 5185
},
{
"entropy": 6.340816640853882,
"epoch": 0.5188184135552557,
"grad_norm": 1.140625,
"learning_rate": 0.0004980161894056464,
"loss": 6.2127,
"mean_token_accuracy": 0.14570229947566987,
"num_tokens": 10159131.0,
"step": 5190
},
{
"entropy": 6.353019285202026,
"epoch": 0.5193182386164842,
"grad_norm": 1.1328125,
"learning_rate": 0.0004980114578098618,
"loss": 6.3856,
"mean_token_accuracy": 0.13546337187290192,
"num_tokens": 10169094.0,
"step": 5195
},
{
"entropy": 6.487119054794311,
"epoch": 0.5198180636777128,
"grad_norm": 1.1484375,
"learning_rate": 0.0004980067206031663,
"loss": 6.2793,
"mean_token_accuracy": 0.14671253859996797,
"num_tokens": 10177910.0,
"step": 5200
},
{
"entropy": 6.437972784042358,
"epoch": 0.5203178887389414,
"grad_norm": 1.234375,
"learning_rate": 0.0004980019777856791,
"loss": 6.328,
"mean_token_accuracy": 0.14403121471405028,
"num_tokens": 10186801.0,
"step": 5205
},
{
"entropy": 6.483811330795288,
"epoch": 0.52081771380017,
"grad_norm": 1.2109375,
"learning_rate": 0.0004979972293575195,
"loss": 6.4062,
"mean_token_accuracy": 0.1334290087223053,
"num_tokens": 10196841.0,
"step": 5210
},
{
"entropy": 6.502076721191406,
"epoch": 0.5213175388613985,
"grad_norm": 1.1953125,
"learning_rate": 0.0004979924753188069,
"loss": 6.4635,
"mean_token_accuracy": 0.12991615235805512,
"num_tokens": 10207829.0,
"step": 5215
},
{
"entropy": 6.441777324676513,
"epoch": 0.5218173639226271,
"grad_norm": 1.375,
"learning_rate": 0.0004979877156696612,
"loss": 6.4525,
"mean_token_accuracy": 0.13123227879405022,
"num_tokens": 10217029.0,
"step": 5220
},
{
"entropy": 6.426708173751831,
"epoch": 0.5223171889838556,
"grad_norm": 1.2265625,
"learning_rate": 0.0004979829504102018,
"loss": 6.3068,
"mean_token_accuracy": 0.14138131588697433,
"num_tokens": 10227602.0,
"step": 5225
},
{
"entropy": 6.425765800476074,
"epoch": 0.5228170140450842,
"grad_norm": 1.1796875,
"learning_rate": 0.0004979781795405488,
"loss": 6.3371,
"mean_token_accuracy": 0.13900671154260635,
"num_tokens": 10237990.0,
"step": 5230
},
{
"entropy": 6.462211942672729,
"epoch": 0.5233168391063128,
"grad_norm": 1.0546875,
"learning_rate": 0.0004979734030608222,
"loss": 6.3787,
"mean_token_accuracy": 0.1397375248372555,
"num_tokens": 10247381.0,
"step": 5235
},
{
"entropy": 6.40122652053833,
"epoch": 0.5238166641675414,
"grad_norm": 1.234375,
"learning_rate": 0.0004979686209711422,
"loss": 6.1952,
"mean_token_accuracy": 0.15425493717193603,
"num_tokens": 10256444.0,
"step": 5240
},
{
"entropy": 6.466607666015625,
"epoch": 0.5243164892287699,
"grad_norm": 1.2421875,
"learning_rate": 0.000497963833271629,
"loss": 6.3641,
"mean_token_accuracy": 0.13539370372891427,
"num_tokens": 10266965.0,
"step": 5245
},
{
"entropy": 6.396874952316284,
"epoch": 0.5248163142899985,
"grad_norm": 1.171875,
"learning_rate": 0.0004979590399624031,
"loss": 6.2913,
"mean_token_accuracy": 0.14410683065652846,
"num_tokens": 10276520.0,
"step": 5250
},
{
"entropy": 6.452992725372314,
"epoch": 0.5253161393512271,
"grad_norm": 1.234375,
"learning_rate": 0.0004979542410435852,
"loss": 6.3688,
"mean_token_accuracy": 0.13349135145545005,
"num_tokens": 10285676.0,
"step": 5255
},
{
"entropy": 6.369792509078979,
"epoch": 0.5258159644124556,
"grad_norm": 1.1953125,
"learning_rate": 0.0004979494365152959,
"loss": 6.2599,
"mean_token_accuracy": 0.1452934131026268,
"num_tokens": 10295643.0,
"step": 5260
},
{
"entropy": 6.447965335845947,
"epoch": 0.5263157894736842,
"grad_norm": 1.15625,
"learning_rate": 0.0004979446263776562,
"loss": 6.3667,
"mean_token_accuracy": 0.13000320717692376,
"num_tokens": 10305555.0,
"step": 5265
},
{
"entropy": 6.454273414611817,
"epoch": 0.5268156145349128,
"grad_norm": 1.1796875,
"learning_rate": 0.000497939810630787,
"loss": 6.3263,
"mean_token_accuracy": 0.14252042546868324,
"num_tokens": 10315399.0,
"step": 5270
},
{
"entropy": 6.36467227935791,
"epoch": 0.5273154395961414,
"grad_norm": 1.0625,
"learning_rate": 0.0004979349892748096,
"loss": 6.3697,
"mean_token_accuracy": 0.14212508723139763,
"num_tokens": 10325414.0,
"step": 5275
},
{
"entropy": 6.4512800693511965,
"epoch": 0.5278152646573699,
"grad_norm": 1.2734375,
"learning_rate": 0.0004979301623098452,
"loss": 6.3436,
"mean_token_accuracy": 0.1363958165049553,
"num_tokens": 10334701.0,
"step": 5280
},
{
"entropy": 6.416783666610717,
"epoch": 0.5283150897185985,
"grad_norm": 1.2890625,
"learning_rate": 0.0004979253297360153,
"loss": 6.4277,
"mean_token_accuracy": 0.1374026782810688,
"num_tokens": 10343951.0,
"step": 5285
},
{
"entropy": 6.408209896087646,
"epoch": 0.528814914779827,
"grad_norm": 1.2109375,
"learning_rate": 0.0004979204915534415,
"loss": 6.2931,
"mean_token_accuracy": 0.14456386864185333,
"num_tokens": 10352990.0,
"step": 5290
},
{
"entropy": 6.448209238052368,
"epoch": 0.5293147398410556,
"grad_norm": 1.0859375,
"learning_rate": 0.0004979156477622454,
"loss": 6.3515,
"mean_token_accuracy": 0.14031895026564598,
"num_tokens": 10363059.0,
"step": 5295
},
{
"entropy": 6.498208045959473,
"epoch": 0.5298145649022842,
"grad_norm": 1.203125,
"learning_rate": 0.0004979107983625491,
"loss": 6.341,
"mean_token_accuracy": 0.14113035723567008,
"num_tokens": 10373237.0,
"step": 5300
},
{
"entropy": 6.5129311084747314,
"epoch": 0.5303143899635128,
"grad_norm": 1.2578125,
"learning_rate": 0.0004979059433544744,
"loss": 6.44,
"mean_token_accuracy": 0.13211785033345222,
"num_tokens": 10383373.0,
"step": 5305
},
{
"entropy": 6.4633525848388675,
"epoch": 0.5308142150247414,
"grad_norm": 1.1484375,
"learning_rate": 0.0004979010827381435,
"loss": 6.3274,
"mean_token_accuracy": 0.12966383323073388,
"num_tokens": 10392612.0,
"step": 5310
},
{
"entropy": 6.362445640563965,
"epoch": 0.5313140400859699,
"grad_norm": 3.609375,
"learning_rate": 0.0004978962165136787,
"loss": 6.272,
"mean_token_accuracy": 0.13932389095425607,
"num_tokens": 10402201.0,
"step": 5315
},
{
"entropy": 6.4546863555908205,
"epoch": 0.5318138651471985,
"grad_norm": 1.15625,
"learning_rate": 0.0004978913446812025,
"loss": 6.3025,
"mean_token_accuracy": 0.14247895479202272,
"num_tokens": 10411847.0,
"step": 5320
},
{
"entropy": 6.419976806640625,
"epoch": 0.532313690208427,
"grad_norm": 1.2265625,
"learning_rate": 0.0004978864672408374,
"loss": 6.3926,
"mean_token_accuracy": 0.13130954205989837,
"num_tokens": 10422035.0,
"step": 5325
},
{
"entropy": 6.40062460899353,
"epoch": 0.5328135152696556,
"grad_norm": 1.1953125,
"learning_rate": 0.0004978815841927061,
"loss": 6.3389,
"mean_token_accuracy": 0.1398831605911255,
"num_tokens": 10432097.0,
"step": 5330
},
{
"entropy": 6.454918003082275,
"epoch": 0.5333133403308842,
"grad_norm": 1.28125,
"learning_rate": 0.0004978766955369315,
"loss": 6.3387,
"mean_token_accuracy": 0.14079173132777215,
"num_tokens": 10442357.0,
"step": 5335
},
{
"entropy": 6.311182165145874,
"epoch": 0.5338131653921128,
"grad_norm": 1.1328125,
"learning_rate": 0.0004978718012736367,
"loss": 6.275,
"mean_token_accuracy": 0.1485537901520729,
"num_tokens": 10453491.0,
"step": 5340
},
{
"entropy": 6.431671237945556,
"epoch": 0.5343129904533414,
"grad_norm": 1.265625,
"learning_rate": 0.0004978669014029446,
"loss": 6.3142,
"mean_token_accuracy": 0.14028706550598144,
"num_tokens": 10464016.0,
"step": 5345
},
{
"entropy": 6.473352241516113,
"epoch": 0.5348128155145699,
"grad_norm": 1.25,
"learning_rate": 0.0004978619959249787,
"loss": 6.311,
"mean_token_accuracy": 0.13191917762160302,
"num_tokens": 10473471.0,
"step": 5350
},
{
"entropy": 6.363288736343383,
"epoch": 0.5353126405757984,
"grad_norm": 1.3203125,
"learning_rate": 0.0004978570848398623,
"loss": 6.3153,
"mean_token_accuracy": 0.13890534415841102,
"num_tokens": 10482329.0,
"step": 5355
},
{
"entropy": 6.4296393394470215,
"epoch": 0.535812465637027,
"grad_norm": 1.234375,
"learning_rate": 0.000497852168147719,
"loss": 6.418,
"mean_token_accuracy": 0.13311819806694986,
"num_tokens": 10491731.0,
"step": 5360
},
{
"entropy": 6.529134321212768,
"epoch": 0.5363122906982556,
"grad_norm": 1.125,
"learning_rate": 0.0004978472458486724,
"loss": 6.4002,
"mean_token_accuracy": 0.13935512900352479,
"num_tokens": 10501317.0,
"step": 5365
},
{
"entropy": 6.475551557540894,
"epoch": 0.5368121157594842,
"grad_norm": 1.1328125,
"learning_rate": 0.0004978423179428466,
"loss": 6.2984,
"mean_token_accuracy": 0.13850174099206924,
"num_tokens": 10509849.0,
"step": 5370
},
{
"entropy": 6.3376429080963135,
"epoch": 0.5373119408207128,
"grad_norm": 1.3515625,
"learning_rate": 0.0004978373844303653,
"loss": 6.3189,
"mean_token_accuracy": 0.13514501750469207,
"num_tokens": 10518714.0,
"step": 5375
},
{
"entropy": 6.466615438461304,
"epoch": 0.5378117658819414,
"grad_norm": 1.0390625,
"learning_rate": 0.0004978324453113528,
"loss": 6.357,
"mean_token_accuracy": 0.13815916925668717,
"num_tokens": 10529128.0,
"step": 5380
},
{
"entropy": 6.475117874145508,
"epoch": 0.5383115909431699,
"grad_norm": 1.125,
"learning_rate": 0.0004978275005859333,
"loss": 6.2947,
"mean_token_accuracy": 0.1379874348640442,
"num_tokens": 10538748.0,
"step": 5385
},
{
"entropy": 6.381226968765259,
"epoch": 0.5388114160043984,
"grad_norm": 1.125,
"learning_rate": 0.0004978225502542313,
"loss": 6.3256,
"mean_token_accuracy": 0.13793647438287734,
"num_tokens": 10549273.0,
"step": 5390
},
{
"entropy": 6.4153244972229,
"epoch": 0.539311241065627,
"grad_norm": 1.1484375,
"learning_rate": 0.0004978175943163712,
"loss": 6.2757,
"mean_token_accuracy": 0.14547774568200111,
"num_tokens": 10559332.0,
"step": 5395
},
{
"entropy": 6.370609998703003,
"epoch": 0.5398110661268556,
"grad_norm": 1.171875,
"learning_rate": 0.0004978126327724777,
"loss": 6.2962,
"mean_token_accuracy": 0.1446087673306465,
"num_tokens": 10568699.0,
"step": 5400
},
{
"entropy": 6.355083084106445,
"epoch": 0.5403108911880842,
"grad_norm": 1.203125,
"learning_rate": 0.0004978076656226758,
"loss": 6.2665,
"mean_token_accuracy": 0.14076985865831376,
"num_tokens": 10579129.0,
"step": 5405
},
{
"entropy": 6.394743204116821,
"epoch": 0.5408107162493128,
"grad_norm": 1.25,
"learning_rate": 0.0004978026928670902,
"loss": 6.3442,
"mean_token_accuracy": 0.13657924234867097,
"num_tokens": 10589093.0,
"step": 5410
},
{
"entropy": 6.347167110443115,
"epoch": 0.5413105413105413,
"grad_norm": 1.3046875,
"learning_rate": 0.0004977977145058463,
"loss": 6.359,
"mean_token_accuracy": 0.1375754989683628,
"num_tokens": 10598766.0,
"step": 5415
},
{
"entropy": 6.3665509700775145,
"epoch": 0.5418103663717699,
"grad_norm": 1.1640625,
"learning_rate": 0.0004977927305390693,
"loss": 6.2774,
"mean_token_accuracy": 0.14815937578678132,
"num_tokens": 10609148.0,
"step": 5420
},
{
"entropy": 6.5036862850189205,
"epoch": 0.5423101914329984,
"grad_norm": 1.3359375,
"learning_rate": 0.0004977877409668845,
"loss": 6.4375,
"mean_token_accuracy": 0.12969812080264093,
"num_tokens": 10618160.0,
"step": 5425
},
{
"entropy": 6.421460199356079,
"epoch": 0.542810016494227,
"grad_norm": 1.765625,
"learning_rate": 0.0004977827457894174,
"loss": 6.3537,
"mean_token_accuracy": 0.13131480067968368,
"num_tokens": 10628839.0,
"step": 5430
},
{
"entropy": 6.460460519790649,
"epoch": 0.5433098415554556,
"grad_norm": 1.21875,
"learning_rate": 0.0004977777450067937,
"loss": 6.3418,
"mean_token_accuracy": 0.1394140265882015,
"num_tokens": 10638312.0,
"step": 5435
},
{
"entropy": 6.474530363082886,
"epoch": 0.5438096666166842,
"grad_norm": 1.1640625,
"learning_rate": 0.0004977727386191393,
"loss": 6.34,
"mean_token_accuracy": 0.13660069406032563,
"num_tokens": 10647128.0,
"step": 5440
},
{
"entropy": 6.42323112487793,
"epoch": 0.5443094916779128,
"grad_norm": 1.71875,
"learning_rate": 0.0004977677266265802,
"loss": 6.4833,
"mean_token_accuracy": 0.13081137612462043,
"num_tokens": 10657574.0,
"step": 5445
},
{
"entropy": 6.390897369384765,
"epoch": 0.5448093167391413,
"grad_norm": 1.109375,
"learning_rate": 0.0004977627090292424,
"loss": 6.3382,
"mean_token_accuracy": 0.13386189714074134,
"num_tokens": 10668497.0,
"step": 5450
},
{
"entropy": 6.447263383865357,
"epoch": 0.5453091418003698,
"grad_norm": 1.1328125,
"learning_rate": 0.0004977576858272521,
"loss": 6.3542,
"mean_token_accuracy": 0.13918982222676277,
"num_tokens": 10678728.0,
"step": 5455
},
{
"entropy": 6.445428705215454,
"epoch": 0.5458089668615984,
"grad_norm": 1.078125,
"learning_rate": 0.0004977526570207358,
"loss": 6.3574,
"mean_token_accuracy": 0.1380918189883232,
"num_tokens": 10688953.0,
"step": 5460
},
{
"entropy": 6.358369588851929,
"epoch": 0.546308791922827,
"grad_norm": 1.0703125,
"learning_rate": 0.0004977476226098199,
"loss": 6.3195,
"mean_token_accuracy": 0.1424561321735382,
"num_tokens": 10698570.0,
"step": 5465
},
{
"entropy": 6.385986232757569,
"epoch": 0.5468086169840556,
"grad_norm": 1.1953125,
"learning_rate": 0.0004977425825946312,
"loss": 6.2164,
"mean_token_accuracy": 0.15032757222652435,
"num_tokens": 10708438.0,
"step": 5470
},
{
"entropy": 6.409063243865967,
"epoch": 0.5473084420452842,
"grad_norm": 1.140625,
"learning_rate": 0.0004977375369752964,
"loss": 6.2968,
"mean_token_accuracy": 0.1432842992246151,
"num_tokens": 10718559.0,
"step": 5475
},
{
"entropy": 6.278464078903198,
"epoch": 0.5478082671065128,
"grad_norm": 1.1484375,
"learning_rate": 0.0004977324857519425,
"loss": 6.4167,
"mean_token_accuracy": 0.13704861402511598,
"num_tokens": 10729348.0,
"step": 5480
},
{
"entropy": 6.529194259643555,
"epoch": 0.5483080921677413,
"grad_norm": 1.0859375,
"learning_rate": 0.0004977274289246967,
"loss": 6.3946,
"mean_token_accuracy": 0.1368100695312023,
"num_tokens": 10739139.0,
"step": 5485
},
{
"entropy": 6.433472776412964,
"epoch": 0.5488079172289698,
"grad_norm": 1.09375,
"learning_rate": 0.0004977223664936859,
"loss": 6.4331,
"mean_token_accuracy": 0.1324752040207386,
"num_tokens": 10749451.0,
"step": 5490
},
{
"entropy": 6.420543003082275,
"epoch": 0.5493077422901984,
"grad_norm": 1.2578125,
"learning_rate": 0.0004977172984590378,
"loss": 6.2767,
"mean_token_accuracy": 0.14483995437622071,
"num_tokens": 10757990.0,
"step": 5495
},
{
"entropy": 6.463605546951294,
"epoch": 0.549807567351427,
"grad_norm": 1.359375,
"learning_rate": 0.0004977122248208798,
"loss": 6.2347,
"mean_token_accuracy": 0.14013865888118743,
"num_tokens": 10766825.0,
"step": 5500
},
{
"entropy": 6.337217140197754,
"epoch": 0.5503073924126556,
"grad_norm": 1.09375,
"learning_rate": 0.0004977071455793394,
"loss": 6.3059,
"mean_token_accuracy": 0.13765543773770333,
"num_tokens": 10776670.0,
"step": 5505
},
{
"entropy": 6.328641700744629,
"epoch": 0.5508072174738842,
"grad_norm": 1.1640625,
"learning_rate": 0.0004977020607345445,
"loss": 6.2604,
"mean_token_accuracy": 0.14444502145051957,
"num_tokens": 10787152.0,
"step": 5510
},
{
"entropy": 6.4152027606964115,
"epoch": 0.5513070425351128,
"grad_norm": 1.296875,
"learning_rate": 0.0004976969702866231,
"loss": 6.3943,
"mean_token_accuracy": 0.1340176969766617,
"num_tokens": 10796903.0,
"step": 5515
},
{
"entropy": 6.4490638256073,
"epoch": 0.5518068675963412,
"grad_norm": 1.1796875,
"learning_rate": 0.0004976918742357033,
"loss": 6.3518,
"mean_token_accuracy": 0.1396077059209347,
"num_tokens": 10806549.0,
"step": 5520
},
{
"entropy": 6.55826325416565,
"epoch": 0.5523066926575698,
"grad_norm": 1.1015625,
"learning_rate": 0.0004976867725819133,
"loss": 6.4667,
"mean_token_accuracy": 0.12954409047961235,
"num_tokens": 10816755.0,
"step": 5525
},
{
"entropy": 6.432829999923706,
"epoch": 0.5528065177187984,
"grad_norm": 1.25,
"learning_rate": 0.0004976816653253813,
"loss": 6.3043,
"mean_token_accuracy": 0.13626608103513718,
"num_tokens": 10827171.0,
"step": 5530
},
{
"entropy": 6.405724048614502,
"epoch": 0.553306342780027,
"grad_norm": 1.296875,
"learning_rate": 0.0004976765524662359,
"loss": 6.3277,
"mean_token_accuracy": 0.13775218650698662,
"num_tokens": 10837048.0,
"step": 5535
},
{
"entropy": 6.480524730682373,
"epoch": 0.5538061678412556,
"grad_norm": 1.0859375,
"learning_rate": 0.0004976714340046058,
"loss": 6.3299,
"mean_token_accuracy": 0.13683032765984535,
"num_tokens": 10846775.0,
"step": 5540
},
{
"entropy": 6.393848705291748,
"epoch": 0.5543059929024842,
"grad_norm": 1.125,
"learning_rate": 0.0004976663099406196,
"loss": 6.3462,
"mean_token_accuracy": 0.13975223451852797,
"num_tokens": 10856234.0,
"step": 5545
},
{
"entropy": 6.385819816589356,
"epoch": 0.5548058179637128,
"grad_norm": 1.21875,
"learning_rate": 0.0004976611802744066,
"loss": 6.3697,
"mean_token_accuracy": 0.13305724635720254,
"num_tokens": 10865943.0,
"step": 5550
},
{
"entropy": 6.4838074207305905,
"epoch": 0.5553056430249412,
"grad_norm": 1.1171875,
"learning_rate": 0.0004976560450060954,
"loss": 6.2818,
"mean_token_accuracy": 0.1389782540500164,
"num_tokens": 10875286.0,
"step": 5555
},
{
"entropy": 6.499625110626221,
"epoch": 0.5558054680861698,
"grad_norm": 1.1015625,
"learning_rate": 0.0004976509041358154,
"loss": 6.3717,
"mean_token_accuracy": 0.1385914698243141,
"num_tokens": 10884491.0,
"step": 5560
},
{
"entropy": 6.310593986511231,
"epoch": 0.5563052931473984,
"grad_norm": 1.109375,
"learning_rate": 0.000497645757663696,
"loss": 6.2337,
"mean_token_accuracy": 0.1463724382221699,
"num_tokens": 10892773.0,
"step": 5565
},
{
"entropy": 6.375320720672607,
"epoch": 0.556805118208627,
"grad_norm": 1.1015625,
"learning_rate": 0.0004976406055898665,
"loss": 6.3869,
"mean_token_accuracy": 0.13724598586559295,
"num_tokens": 10903517.0,
"step": 5570
},
{
"entropy": 6.4880389213562015,
"epoch": 0.5573049432698556,
"grad_norm": 1.1796875,
"learning_rate": 0.0004976354479144568,
"loss": 6.3472,
"mean_token_accuracy": 0.14230165705084802,
"num_tokens": 10913075.0,
"step": 5575
},
{
"entropy": 6.462172603607177,
"epoch": 0.5578047683310842,
"grad_norm": 1.2109375,
"learning_rate": 0.0004976302846375965,
"loss": 6.3483,
"mean_token_accuracy": 0.14335301369428635,
"num_tokens": 10922962.0,
"step": 5580
},
{
"entropy": 6.373585605621338,
"epoch": 0.5583045933923126,
"grad_norm": 1.2578125,
"learning_rate": 0.0004976251157594155,
"loss": 6.2853,
"mean_token_accuracy": 0.13618385270237923,
"num_tokens": 10932192.0,
"step": 5585
},
{
"entropy": 6.384717607498169,
"epoch": 0.5588044184535412,
"grad_norm": 1.1484375,
"learning_rate": 0.0004976199412800437,
"loss": 6.2727,
"mean_token_accuracy": 0.14798521846532822,
"num_tokens": 10941748.0,
"step": 5590
},
{
"entropy": 6.47556438446045,
"epoch": 0.5593042435147698,
"grad_norm": 1.4296875,
"learning_rate": 0.0004976147611996118,
"loss": 6.442,
"mean_token_accuracy": 0.13446364551782608,
"num_tokens": 10951467.0,
"step": 5595
},
{
"entropy": 6.48672456741333,
"epoch": 0.5598040685759984,
"grad_norm": 1.015625,
"learning_rate": 0.0004976095755182496,
"loss": 6.3428,
"mean_token_accuracy": 0.1381102494895458,
"num_tokens": 10962598.0,
"step": 5600
},
{
"entropy": 6.37509593963623,
"epoch": 0.560303893637227,
"grad_norm": 1.4765625,
"learning_rate": 0.0004976043842360877,
"loss": 6.2609,
"mean_token_accuracy": 0.13521101251244544,
"num_tokens": 10971206.0,
"step": 5605
},
{
"entropy": 6.305227756500244,
"epoch": 0.5608037186984556,
"grad_norm": 1.203125,
"learning_rate": 0.000497599187353257,
"loss": 6.2494,
"mean_token_accuracy": 0.13938769847154617,
"num_tokens": 10979922.0,
"step": 5610
},
{
"entropy": 6.3692711353302,
"epoch": 0.5613035437596842,
"grad_norm": 1.2890625,
"learning_rate": 0.0004975939848698879,
"loss": 6.2814,
"mean_token_accuracy": 0.14390315264463424,
"num_tokens": 10988886.0,
"step": 5615
},
{
"entropy": 6.265742683410645,
"epoch": 0.5618033688209126,
"grad_norm": 1.21875,
"learning_rate": 0.0004975887767861113,
"loss": 6.2927,
"mean_token_accuracy": 0.14396480172872544,
"num_tokens": 10998570.0,
"step": 5620
},
{
"entropy": 6.376459693908691,
"epoch": 0.5623031938821412,
"grad_norm": 1.1171875,
"learning_rate": 0.0004975835631020585,
"loss": 6.2357,
"mean_token_accuracy": 0.14439999610185622,
"num_tokens": 11009549.0,
"step": 5625
},
{
"entropy": 6.293685102462769,
"epoch": 0.5628030189433698,
"grad_norm": 1.59375,
"learning_rate": 0.0004975783438178605,
"loss": 6.127,
"mean_token_accuracy": 0.16214562952518463,
"num_tokens": 11019382.0,
"step": 5630
},
{
"entropy": 6.418667936325074,
"epoch": 0.5633028440045984,
"grad_norm": 1.2265625,
"learning_rate": 0.0004975731189336487,
"loss": 6.3599,
"mean_token_accuracy": 0.13114651739597322,
"num_tokens": 11028205.0,
"step": 5635
},
{
"entropy": 6.422270679473877,
"epoch": 0.563802669065827,
"grad_norm": 1.2265625,
"learning_rate": 0.0004975678884495544,
"loss": 6.2863,
"mean_token_accuracy": 0.14224059656262397,
"num_tokens": 11037684.0,
"step": 5640
},
{
"entropy": 6.349951314926147,
"epoch": 0.5643024941270556,
"grad_norm": 1.359375,
"learning_rate": 0.0004975626523657093,
"loss": 6.2584,
"mean_token_accuracy": 0.1368769459426403,
"num_tokens": 11047119.0,
"step": 5645
},
{
"entropy": 6.251744365692138,
"epoch": 0.564802319188284,
"grad_norm": 1.171875,
"learning_rate": 0.0004975574106822451,
"loss": 6.2619,
"mean_token_accuracy": 0.14665021300315856,
"num_tokens": 11057362.0,
"step": 5650
},
{
"entropy": 6.3798047542572025,
"epoch": 0.5653021442495126,
"grad_norm": 1.0859375,
"learning_rate": 0.0004975521633992938,
"loss": 6.216,
"mean_token_accuracy": 0.14489733055233955,
"num_tokens": 11067685.0,
"step": 5655
},
{
"entropy": 6.39489893913269,
"epoch": 0.5658019693107412,
"grad_norm": 1.0625,
"learning_rate": 0.0004975469105169873,
"loss": 6.2072,
"mean_token_accuracy": 0.14295902103185654,
"num_tokens": 11077468.0,
"step": 5660
},
{
"entropy": 6.413747930526734,
"epoch": 0.5663017943719698,
"grad_norm": 1.125,
"learning_rate": 0.0004975416520354579,
"loss": 6.404,
"mean_token_accuracy": 0.1398212917149067,
"num_tokens": 11087266.0,
"step": 5665
},
{
"entropy": 6.374395275115967,
"epoch": 0.5668016194331984,
"grad_norm": 1.1640625,
"learning_rate": 0.0004975363879548377,
"loss": 6.2982,
"mean_token_accuracy": 0.13866044878959655,
"num_tokens": 11098053.0,
"step": 5670
},
{
"entropy": 6.532749032974243,
"epoch": 0.567301444494427,
"grad_norm": 1.515625,
"learning_rate": 0.0004975311182752592,
"loss": 6.3584,
"mean_token_accuracy": 0.14000722095370294,
"num_tokens": 11107341.0,
"step": 5675
},
{
"entropy": 6.361231470108033,
"epoch": 0.5678012695556556,
"grad_norm": 1.15625,
"learning_rate": 0.0004975258429968551,
"loss": 6.278,
"mean_token_accuracy": 0.13990237116813659,
"num_tokens": 11116356.0,
"step": 5680
},
{
"entropy": 6.34175477027893,
"epoch": 0.568301094616884,
"grad_norm": 1.125,
"learning_rate": 0.0004975205621197581,
"loss": 6.3034,
"mean_token_accuracy": 0.1467010609805584,
"num_tokens": 11126504.0,
"step": 5685
},
{
"entropy": 6.370285272598267,
"epoch": 0.5688009196781126,
"grad_norm": 1.171875,
"learning_rate": 0.0004975152756441009,
"loss": 6.2407,
"mean_token_accuracy": 0.14483981877565383,
"num_tokens": 11136473.0,
"step": 5690
},
{
"entropy": 6.404270839691162,
"epoch": 0.5693007447393412,
"grad_norm": 1.234375,
"learning_rate": 0.0004975099835700166,
"loss": 6.3122,
"mean_token_accuracy": 0.13850560039281845,
"num_tokens": 11146798.0,
"step": 5695
},
{
"entropy": 6.444261980056763,
"epoch": 0.5698005698005698,
"grad_norm": 1.1484375,
"learning_rate": 0.0004975046858976386,
"loss": 6.3302,
"mean_token_accuracy": 0.13601220175623893,
"num_tokens": 11156833.0,
"step": 5700
},
{
"entropy": 6.441240215301514,
"epoch": 0.5703003948617984,
"grad_norm": 1.234375,
"learning_rate": 0.0004974993826270997,
"loss": 6.3672,
"mean_token_accuracy": 0.1342060700058937,
"num_tokens": 11165229.0,
"step": 5705
},
{
"entropy": 6.3729188442230225,
"epoch": 0.570800219923027,
"grad_norm": 1.109375,
"learning_rate": 0.0004974940737585337,
"loss": 6.2005,
"mean_token_accuracy": 0.1447728879749775,
"num_tokens": 11174126.0,
"step": 5710
},
{
"entropy": 6.333694076538086,
"epoch": 0.5713000449842555,
"grad_norm": 1.265625,
"learning_rate": 0.000497488759292074,
"loss": 6.2725,
"mean_token_accuracy": 0.14456492960453032,
"num_tokens": 11183558.0,
"step": 5715
},
{
"entropy": 6.397473096847534,
"epoch": 0.571799870045484,
"grad_norm": 1.234375,
"learning_rate": 0.0004974834392278545,
"loss": 6.3665,
"mean_token_accuracy": 0.13695593401789666,
"num_tokens": 11193449.0,
"step": 5720
},
{
"entropy": 6.510390138626098,
"epoch": 0.5722996951067126,
"grad_norm": 1.1015625,
"learning_rate": 0.0004974781135660088,
"loss": 6.3552,
"mean_token_accuracy": 0.1336575262248516,
"num_tokens": 11203805.0,
"step": 5725
},
{
"entropy": 6.2931036949157715,
"epoch": 0.5727995201679412,
"grad_norm": 1.1484375,
"learning_rate": 0.0004974727823066709,
"loss": 6.2007,
"mean_token_accuracy": 0.1508660152554512,
"num_tokens": 11213578.0,
"step": 5730
},
{
"entropy": 6.409654521942139,
"epoch": 0.5732993452291698,
"grad_norm": 1.3671875,
"learning_rate": 0.0004974674454499753,
"loss": 6.4052,
"mean_token_accuracy": 0.13590671718120576,
"num_tokens": 11223398.0,
"step": 5735
},
{
"entropy": 6.534228086471558,
"epoch": 0.5737991702903984,
"grad_norm": 1.1640625,
"learning_rate": 0.0004974621029960559,
"loss": 6.4722,
"mean_token_accuracy": 0.1311562441289425,
"num_tokens": 11232947.0,
"step": 5740
},
{
"entropy": 6.430829477310181,
"epoch": 0.574298995351627,
"grad_norm": 1.1796875,
"learning_rate": 0.0004974567549450472,
"loss": 6.2514,
"mean_token_accuracy": 0.14314207136631013,
"num_tokens": 11242992.0,
"step": 5745
},
{
"entropy": 6.474722623825073,
"epoch": 0.5747988204128555,
"grad_norm": 1.171875,
"learning_rate": 0.0004974514012970839,
"loss": 6.4338,
"mean_token_accuracy": 0.12969737872481346,
"num_tokens": 11252825.0,
"step": 5750
},
{
"entropy": 6.461831951141358,
"epoch": 0.575298645474084,
"grad_norm": 1.390625,
"learning_rate": 0.0004974460420523005,
"loss": 6.2943,
"mean_token_accuracy": 0.13857915103435517,
"num_tokens": 11262777.0,
"step": 5755
},
{
"entropy": 6.393844127655029,
"epoch": 0.5757984705353126,
"grad_norm": 1.09375,
"learning_rate": 0.0004974406772108319,
"loss": 6.3349,
"mean_token_accuracy": 0.1352956660091877,
"num_tokens": 11272828.0,
"step": 5760
},
{
"entropy": 6.438638210296631,
"epoch": 0.5762982955965412,
"grad_norm": 1.140625,
"learning_rate": 0.0004974353067728132,
"loss": 6.3349,
"mean_token_accuracy": 0.13701027631759644,
"num_tokens": 11282290.0,
"step": 5765
},
{
"entropy": 6.486875677108765,
"epoch": 0.5767981206577698,
"grad_norm": 1.234375,
"learning_rate": 0.0004974299307383794,
"loss": 6.3594,
"mean_token_accuracy": 0.13259207010269164,
"num_tokens": 11290844.0,
"step": 5770
},
{
"entropy": 6.417836284637451,
"epoch": 0.5772979457189984,
"grad_norm": 1.2421875,
"learning_rate": 0.0004974245491076656,
"loss": 6.2733,
"mean_token_accuracy": 0.1455862581729889,
"num_tokens": 11299243.0,
"step": 5775
},
{
"entropy": 6.392756128311158,
"epoch": 0.5777977707802269,
"grad_norm": 1.2578125,
"learning_rate": 0.0004974191618808075,
"loss": 6.3121,
"mean_token_accuracy": 0.14002888053655624,
"num_tokens": 11308556.0,
"step": 5780
},
{
"entropy": 6.4467826843261715,
"epoch": 0.5782975958414555,
"grad_norm": 1.3203125,
"learning_rate": 0.0004974137690579405,
"loss": 6.4027,
"mean_token_accuracy": 0.13739326298236848,
"num_tokens": 11318172.0,
"step": 5785
},
{
"entropy": 6.481961727142334,
"epoch": 0.578797420902684,
"grad_norm": 1.09375,
"learning_rate": 0.0004974083706392004,
"loss": 6.37,
"mean_token_accuracy": 0.1334846369922161,
"num_tokens": 11328967.0,
"step": 5790
},
{
"entropy": 6.410213136672974,
"epoch": 0.5792972459639126,
"grad_norm": 1.296875,
"learning_rate": 0.0004974029666247228,
"loss": 6.3549,
"mean_token_accuracy": 0.13774811178445817,
"num_tokens": 11339234.0,
"step": 5795
},
{
"entropy": 6.555100679397583,
"epoch": 0.5797970710251412,
"grad_norm": 1.0703125,
"learning_rate": 0.0004973975570146438,
"loss": 6.3383,
"mean_token_accuracy": 0.13209013119339943,
"num_tokens": 11349934.0,
"step": 5800
},
{
"entropy": 6.487929391860962,
"epoch": 0.5802968960863698,
"grad_norm": 1.15625,
"learning_rate": 0.0004973921418090997,
"loss": 6.4426,
"mean_token_accuracy": 0.1348351262509823,
"num_tokens": 11359817.0,
"step": 5805
},
{
"entropy": 6.3201491355896,
"epoch": 0.5807967211475984,
"grad_norm": 1.2734375,
"learning_rate": 0.0004973867210082263,
"loss": 6.231,
"mean_token_accuracy": 0.1433400556445122,
"num_tokens": 11369565.0,
"step": 5810
},
{
"entropy": 6.4635889530181885,
"epoch": 0.5812965462088269,
"grad_norm": 1.2734375,
"learning_rate": 0.0004973812946121603,
"loss": 6.3417,
"mean_token_accuracy": 0.13727482929825782,
"num_tokens": 11379543.0,
"step": 5815
},
{
"entropy": 6.470111989974976,
"epoch": 0.5817963712700555,
"grad_norm": 1.328125,
"learning_rate": 0.0004973758626210382,
"loss": 6.3705,
"mean_token_accuracy": 0.13818111643195152,
"num_tokens": 11388909.0,
"step": 5820
},
{
"entropy": 6.4237206935882565,
"epoch": 0.582296196331284,
"grad_norm": 1.21875,
"learning_rate": 0.0004973704250349965,
"loss": 6.408,
"mean_token_accuracy": 0.13562145829200745,
"num_tokens": 11399774.0,
"step": 5825
},
{
"entropy": 6.384641695022583,
"epoch": 0.5827960213925126,
"grad_norm": 1.1015625,
"learning_rate": 0.0004973649818541722,
"loss": 6.2902,
"mean_token_accuracy": 0.13921330794692038,
"num_tokens": 11408701.0,
"step": 5830
},
{
"entropy": 6.441925477981568,
"epoch": 0.5832958464537412,
"grad_norm": 1.140625,
"learning_rate": 0.0004973595330787022,
"loss": 6.278,
"mean_token_accuracy": 0.13829041719436647,
"num_tokens": 11418582.0,
"step": 5835
},
{
"entropy": 6.426104784011841,
"epoch": 0.5837956715149698,
"grad_norm": 1.171875,
"learning_rate": 0.0004973540787087235,
"loss": 6.3553,
"mean_token_accuracy": 0.13323938548564912,
"num_tokens": 11429155.0,
"step": 5840
},
{
"entropy": 6.451894903182984,
"epoch": 0.5842954965761983,
"grad_norm": 1.203125,
"learning_rate": 0.0004973486187443734,
"loss": 6.1996,
"mean_token_accuracy": 0.14416561275720596,
"num_tokens": 11438798.0,
"step": 5845
},
{
"entropy": 6.370334959030151,
"epoch": 0.5847953216374269,
"grad_norm": 1.1171875,
"learning_rate": 0.0004973431531857893,
"loss": 6.3668,
"mean_token_accuracy": 0.1347464457154274,
"num_tokens": 11449862.0,
"step": 5850
},
{
"entropy": 6.389704418182373,
"epoch": 0.5852951466986555,
"grad_norm": 1.515625,
"learning_rate": 0.0004973376820331087,
"loss": 6.3353,
"mean_token_accuracy": 0.13906349390745162,
"num_tokens": 11459697.0,
"step": 5855
},
{
"entropy": 6.568944025039673,
"epoch": 0.585794971759884,
"grad_norm": 1.3359375,
"learning_rate": 0.0004973322052864692,
"loss": 6.4479,
"mean_token_accuracy": 0.13794757351279258,
"num_tokens": 11468973.0,
"step": 5860
},
{
"entropy": 6.350123071670533,
"epoch": 0.5862947968211126,
"grad_norm": 1.8203125,
"learning_rate": 0.0004973267229460087,
"loss": 6.2825,
"mean_token_accuracy": 0.14003330916166307,
"num_tokens": 11479453.0,
"step": 5865
},
{
"entropy": 6.348764133453369,
"epoch": 0.5867946218823412,
"grad_norm": 1.25,
"learning_rate": 0.000497321235011865,
"loss": 6.3255,
"mean_token_accuracy": 0.1448430150747299,
"num_tokens": 11488642.0,
"step": 5870
},
{
"entropy": 6.46609206199646,
"epoch": 0.5872944469435698,
"grad_norm": 1.3046875,
"learning_rate": 0.0004973157414841763,
"loss": 6.2234,
"mean_token_accuracy": 0.1438489742577076,
"num_tokens": 11497898.0,
"step": 5875
},
{
"entropy": 6.345861911773682,
"epoch": 0.5877942720047983,
"grad_norm": 1.1328125,
"learning_rate": 0.0004973102423630806,
"loss": 6.3128,
"mean_token_accuracy": 0.1439259171485901,
"num_tokens": 11508337.0,
"step": 5880
},
{
"entropy": 6.454480886459351,
"epoch": 0.5882940970660269,
"grad_norm": 1.03125,
"learning_rate": 0.0004973047376487166,
"loss": 6.3716,
"mean_token_accuracy": 0.1348287396132946,
"num_tokens": 11518045.0,
"step": 5885
},
{
"entropy": 6.3810920238494875,
"epoch": 0.5887939221272555,
"grad_norm": 1.2109375,
"learning_rate": 0.0004972992273412224,
"loss": 6.2677,
"mean_token_accuracy": 0.1362629845738411,
"num_tokens": 11527297.0,
"step": 5890
},
{
"entropy": 6.40717921257019,
"epoch": 0.589293747188484,
"grad_norm": 1.1640625,
"learning_rate": 0.0004972937114407369,
"loss": 6.2796,
"mean_token_accuracy": 0.1401158943772316,
"num_tokens": 11537674.0,
"step": 5895
},
{
"entropy": 6.4201148509979244,
"epoch": 0.5897935722497126,
"grad_norm": 1.15625,
"learning_rate": 0.000497288189947399,
"loss": 6.3198,
"mean_token_accuracy": 0.13654682859778405,
"num_tokens": 11548046.0,
"step": 5900
},
{
"entropy": 6.358149099349975,
"epoch": 0.5902933973109412,
"grad_norm": 1.2578125,
"learning_rate": 0.0004972826628613472,
"loss": 6.3285,
"mean_token_accuracy": 0.1363440714776516,
"num_tokens": 11558075.0,
"step": 5905
},
{
"entropy": 6.422307348251342,
"epoch": 0.5907932223721697,
"grad_norm": 1.171875,
"learning_rate": 0.0004972771301827209,
"loss": 6.3127,
"mean_token_accuracy": 0.14183902814984323,
"num_tokens": 11567983.0,
"step": 5910
},
{
"entropy": 6.358101272583008,
"epoch": 0.5912930474333983,
"grad_norm": 1.125,
"learning_rate": 0.0004972715919116592,
"loss": 6.2968,
"mean_token_accuracy": 0.13985158875584602,
"num_tokens": 11577438.0,
"step": 5915
},
{
"entropy": 6.39671106338501,
"epoch": 0.5917928724946269,
"grad_norm": 1.1875,
"learning_rate": 0.0004972660480483015,
"loss": 6.209,
"mean_token_accuracy": 0.14532208442687988,
"num_tokens": 11586579.0,
"step": 5920
},
{
"entropy": 6.3205595970153805,
"epoch": 0.5922926975558555,
"grad_norm": 1.1953125,
"learning_rate": 0.0004972604985927871,
"loss": 6.3116,
"mean_token_accuracy": 0.14388131871819496,
"num_tokens": 11595380.0,
"step": 5925
},
{
"entropy": 6.387597513198853,
"epoch": 0.592792522617084,
"grad_norm": 1.3828125,
"learning_rate": 0.0004972549435452558,
"loss": 6.2972,
"mean_token_accuracy": 0.13740020841360093,
"num_tokens": 11605383.0,
"step": 5930
},
{
"entropy": 6.463783597946167,
"epoch": 0.5932923476783126,
"grad_norm": 1.265625,
"learning_rate": 0.0004972493829058474,
"loss": 6.359,
"mean_token_accuracy": 0.14069342389702796,
"num_tokens": 11614783.0,
"step": 5935
},
{
"entropy": 6.466608619689941,
"epoch": 0.5937921727395412,
"grad_norm": 1.34375,
"learning_rate": 0.0004972438166747016,
"loss": 6.3119,
"mean_token_accuracy": 0.13708549216389657,
"num_tokens": 11624524.0,
"step": 5940
},
{
"entropy": 6.298400211334228,
"epoch": 0.5942919978007697,
"grad_norm": 1.109375,
"learning_rate": 0.0004972382448519586,
"loss": 6.1874,
"mean_token_accuracy": 0.1489984482526779,
"num_tokens": 11633908.0,
"step": 5945
},
{
"entropy": 6.313541412353516,
"epoch": 0.5947918228619983,
"grad_norm": 1.1796875,
"learning_rate": 0.0004972326674377586,
"loss": 6.2471,
"mean_token_accuracy": 0.14342263489961624,
"num_tokens": 11644076.0,
"step": 5950
},
{
"entropy": 6.478358364105224,
"epoch": 0.5952916479232269,
"grad_norm": 1.234375,
"learning_rate": 0.0004972270844322418,
"loss": 6.3154,
"mean_token_accuracy": 0.1340063951909542,
"num_tokens": 11652754.0,
"step": 5955
},
{
"entropy": 6.3840117931365965,
"epoch": 0.5957914729844555,
"grad_norm": 1.265625,
"learning_rate": 0.0004972214958355488,
"loss": 6.2413,
"mean_token_accuracy": 0.14417502284049988,
"num_tokens": 11663468.0,
"step": 5960
},
{
"entropy": 6.2802550315856935,
"epoch": 0.596291298045684,
"grad_norm": 1.09375,
"learning_rate": 0.0004972159016478201,
"loss": 6.3219,
"mean_token_accuracy": 0.1371239349246025,
"num_tokens": 11672711.0,
"step": 5965
},
{
"entropy": 6.364471530914306,
"epoch": 0.5967911231069126,
"grad_norm": 1.1875,
"learning_rate": 0.0004972103018691965,
"loss": 6.2571,
"mean_token_accuracy": 0.14432041645050048,
"num_tokens": 11681800.0,
"step": 5970
},
{
"entropy": 6.402378940582276,
"epoch": 0.5972909481681411,
"grad_norm": 1.2265625,
"learning_rate": 0.0004972046964998189,
"loss": 6.2579,
"mean_token_accuracy": 0.15038390457630157,
"num_tokens": 11691229.0,
"step": 5975
},
{
"entropy": 6.344723320007324,
"epoch": 0.5977907732293697,
"grad_norm": 1.203125,
"learning_rate": 0.0004971990855398283,
"loss": 6.2803,
"mean_token_accuracy": 0.1394992120563984,
"num_tokens": 11700027.0,
"step": 5980
},
{
"entropy": 6.363552808761597,
"epoch": 0.5982905982905983,
"grad_norm": 1.46875,
"learning_rate": 0.0004971934689893658,
"loss": 6.2544,
"mean_token_accuracy": 0.14758194386959075,
"num_tokens": 11708899.0,
"step": 5985
},
{
"entropy": 6.332235479354859,
"epoch": 0.5987904233518269,
"grad_norm": 1.1875,
"learning_rate": 0.0004971878468485729,
"loss": 6.2442,
"mean_token_accuracy": 0.1447736620903015,
"num_tokens": 11719325.0,
"step": 5990
},
{
"entropy": 6.4186420917510985,
"epoch": 0.5992902484130554,
"grad_norm": 1.1171875,
"learning_rate": 0.000497182219117591,
"loss": 6.3036,
"mean_token_accuracy": 0.14428125098347663,
"num_tokens": 11728835.0,
"step": 5995
},
{
"entropy": 6.458810138702392,
"epoch": 0.599790073474284,
"grad_norm": 1.1328125,
"learning_rate": 0.0004971765857965615,
"loss": 6.3674,
"mean_token_accuracy": 0.1335064485669136,
"num_tokens": 11738252.0,
"step": 6000
},
{
"epoch": 0.599790073474284,
"eval_entropy": 6.222119353106882,
"eval_loss": 6.3355512619018555,
"eval_mean_token_accuracy": 0.14418950053812593,
"eval_num_tokens": 11738252.0,
"eval_runtime": 23.5717,
"eval_samples_per_second": 1317.044,
"eval_steps_per_second": 164.646,
"step": 6000
},
{
"entropy": 6.325327777862549,
"epoch": 0.6002898985355126,
"grad_norm": 1.1953125,
"learning_rate": 0.0004971709468856263,
"loss": 6.2236,
"mean_token_accuracy": 0.14892019629478453,
"num_tokens": 11748448.0,
"step": 6005
},
{
"entropy": 6.398207139968872,
"epoch": 0.6007897235967411,
"grad_norm": 1.2421875,
"learning_rate": 0.0004971653023849274,
"loss": 6.3865,
"mean_token_accuracy": 0.13725630715489387,
"num_tokens": 11757835.0,
"step": 6010
},
{
"entropy": 6.421339845657348,
"epoch": 0.6012895486579697,
"grad_norm": 2.375,
"learning_rate": 0.0004971596522946065,
"loss": 6.3902,
"mean_token_accuracy": 0.13375852182507514,
"num_tokens": 11767792.0,
"step": 6015
},
{
"entropy": 6.409697961807251,
"epoch": 0.6017893737191983,
"grad_norm": 1.21875,
"learning_rate": 0.0004971539966148059,
"loss": 6.2522,
"mean_token_accuracy": 0.1491508424282074,
"num_tokens": 11777329.0,
"step": 6020
},
{
"entropy": 6.45603346824646,
"epoch": 0.6022891987804269,
"grad_norm": 1.5234375,
"learning_rate": 0.0004971483353456681,
"loss": 6.3417,
"mean_token_accuracy": 0.13632039725780487,
"num_tokens": 11786776.0,
"step": 6025
},
{
"entropy": 6.340818881988525,
"epoch": 0.6027890238416554,
"grad_norm": 1.1796875,
"learning_rate": 0.0004971426684873352,
"loss": 6.2798,
"mean_token_accuracy": 0.14493238925933838,
"num_tokens": 11797669.0,
"step": 6030
},
{
"entropy": 6.345732593536377,
"epoch": 0.603288848902884,
"grad_norm": 1.2265625,
"learning_rate": 0.0004971369960399499,
"loss": 6.2366,
"mean_token_accuracy": 0.14206422567367555,
"num_tokens": 11807661.0,
"step": 6035
},
{
"entropy": 6.460015678405762,
"epoch": 0.6037886739641125,
"grad_norm": 1.296875,
"learning_rate": 0.000497131318003655,
"loss": 6.3393,
"mean_token_accuracy": 0.13968021869659425,
"num_tokens": 11817943.0,
"step": 6040
},
{
"entropy": 6.445551586151123,
"epoch": 0.6042884990253411,
"grad_norm": 1.28125,
"learning_rate": 0.0004971256343785932,
"loss": 6.2836,
"mean_token_accuracy": 0.13863051161170006,
"num_tokens": 11826896.0,
"step": 6045
},
{
"entropy": 6.375212240219116,
"epoch": 0.6047883240865697,
"grad_norm": 1.203125,
"learning_rate": 0.0004971199451649078,
"loss": 6.2311,
"mean_token_accuracy": 0.14266153275966645,
"num_tokens": 11836306.0,
"step": 6050
},
{
"entropy": 6.270658349990844,
"epoch": 0.6052881491477983,
"grad_norm": 1.109375,
"learning_rate": 0.0004971142503627415,
"loss": 6.3285,
"mean_token_accuracy": 0.14062388837337494,
"num_tokens": 11845998.0,
"step": 6055
},
{
"entropy": 6.43452296257019,
"epoch": 0.6057879742090269,
"grad_norm": 1.2109375,
"learning_rate": 0.000497108549972238,
"loss": 6.3235,
"mean_token_accuracy": 0.13975783661007882,
"num_tokens": 11855009.0,
"step": 6060
},
{
"entropy": 6.4450713157653805,
"epoch": 0.6062877992702554,
"grad_norm": 1.125,
"learning_rate": 0.0004971028439935404,
"loss": 6.1624,
"mean_token_accuracy": 0.14758953154087068,
"num_tokens": 11865163.0,
"step": 6065
},
{
"entropy": 6.294251155853272,
"epoch": 0.606787624331484,
"grad_norm": 1.2265625,
"learning_rate": 0.0004970971324267925,
"loss": 6.4501,
"mean_token_accuracy": 0.13839514106512069,
"num_tokens": 11875720.0,
"step": 6070
},
{
"entropy": 6.459564876556397,
"epoch": 0.6072874493927125,
"grad_norm": 1.375,
"learning_rate": 0.0004970914152721378,
"loss": 6.3616,
"mean_token_accuracy": 0.140549136698246,
"num_tokens": 11884247.0,
"step": 6075
},
{
"entropy": 6.385787153244019,
"epoch": 0.6077872744539411,
"grad_norm": 1.234375,
"learning_rate": 0.0004970856925297204,
"loss": 6.2151,
"mean_token_accuracy": 0.1424304224550724,
"num_tokens": 11894978.0,
"step": 6080
},
{
"entropy": 6.377972269058228,
"epoch": 0.6082870995151697,
"grad_norm": 1.0859375,
"learning_rate": 0.000497079964199684,
"loss": 6.3207,
"mean_token_accuracy": 0.13819993436336517,
"num_tokens": 11904904.0,
"step": 6085
},
{
"entropy": 6.467128086090088,
"epoch": 0.6087869245763983,
"grad_norm": 1.1796875,
"learning_rate": 0.0004970742302821729,
"loss": 6.3632,
"mean_token_accuracy": 0.13567261695861815,
"num_tokens": 11915339.0,
"step": 6090
},
{
"entropy": 6.372006750106811,
"epoch": 0.6092867496376269,
"grad_norm": 1.4765625,
"learning_rate": 0.0004970684907773312,
"loss": 6.2845,
"mean_token_accuracy": 0.13606042191386222,
"num_tokens": 11925451.0,
"step": 6095
},
{
"entropy": 6.32097544670105,
"epoch": 0.6097865746988554,
"grad_norm": 1.21875,
"learning_rate": 0.0004970627456853036,
"loss": 6.2565,
"mean_token_accuracy": 0.1369823195040226,
"num_tokens": 11934931.0,
"step": 6100
},
{
"entropy": 6.380632066726685,
"epoch": 0.6102863997600839,
"grad_norm": 1.1953125,
"learning_rate": 0.0004970569950062343,
"loss": 6.1756,
"mean_token_accuracy": 0.15396128892898558,
"num_tokens": 11943492.0,
"step": 6105
},
{
"entropy": 6.380721664428711,
"epoch": 0.6107862248213125,
"grad_norm": 1.109375,
"learning_rate": 0.0004970512387402682,
"loss": 6.3263,
"mean_token_accuracy": 0.13436108753085135,
"num_tokens": 11952880.0,
"step": 6110
},
{
"entropy": 6.472577905654907,
"epoch": 0.6112860498825411,
"grad_norm": 1.2109375,
"learning_rate": 0.0004970454768875501,
"loss": 6.2861,
"mean_token_accuracy": 0.14190733432769775,
"num_tokens": 11961840.0,
"step": 6115
},
{
"entropy": 6.404052686691284,
"epoch": 0.6117858749437697,
"grad_norm": 1.1796875,
"learning_rate": 0.0004970397094482249,
"loss": 6.3363,
"mean_token_accuracy": 0.14052857607603073,
"num_tokens": 11970833.0,
"step": 6120
},
{
"entropy": 6.338464975357056,
"epoch": 0.6122857000049983,
"grad_norm": 1.2109375,
"learning_rate": 0.0004970339364224378,
"loss": 6.3224,
"mean_token_accuracy": 0.13694415241479874,
"num_tokens": 11980497.0,
"step": 6125
},
{
"entropy": 6.460524559020996,
"epoch": 0.6127855250662269,
"grad_norm": 1.2421875,
"learning_rate": 0.0004970281578103339,
"loss": 6.2292,
"mean_token_accuracy": 0.1439013287425041,
"num_tokens": 11989505.0,
"step": 6130
},
{
"entropy": 6.408053779602051,
"epoch": 0.6132853501274554,
"grad_norm": 1.1015625,
"learning_rate": 0.0004970223736120587,
"loss": 6.341,
"mean_token_accuracy": 0.13839608207345008,
"num_tokens": 11998952.0,
"step": 6135
},
{
"entropy": 6.287954950332642,
"epoch": 0.6137851751886839,
"grad_norm": 1.109375,
"learning_rate": 0.0004970165838277578,
"loss": 6.1233,
"mean_token_accuracy": 0.1451805427670479,
"num_tokens": 12009249.0,
"step": 6140
},
{
"entropy": 6.353747034072876,
"epoch": 0.6142850002499125,
"grad_norm": 1.1953125,
"learning_rate": 0.0004970107884575767,
"loss": 6.2299,
"mean_token_accuracy": 0.14374330639839172,
"num_tokens": 12018345.0,
"step": 6145
},
{
"entropy": 6.419749116897583,
"epoch": 0.6147848253111411,
"grad_norm": 1.2734375,
"learning_rate": 0.0004970049875016613,
"loss": 6.2872,
"mean_token_accuracy": 0.14101603254675865,
"num_tokens": 12026530.0,
"step": 6150
},
{
"entropy": 6.288591432571411,
"epoch": 0.6152846503723697,
"grad_norm": 1.34375,
"learning_rate": 0.0004969991809601576,
"loss": 6.2292,
"mean_token_accuracy": 0.14639043360948562,
"num_tokens": 12036232.0,
"step": 6155
},
{
"entropy": 6.28270525932312,
"epoch": 0.6157844754335983,
"grad_norm": 1.2421875,
"learning_rate": 0.0004969933688332115,
"loss": 6.1509,
"mean_token_accuracy": 0.15005660951137542,
"num_tokens": 12045668.0,
"step": 6160
},
{
"entropy": 6.331249141693116,
"epoch": 0.6162843004948269,
"grad_norm": 1.203125,
"learning_rate": 0.0004969875511209694,
"loss": 6.1846,
"mean_token_accuracy": 0.151524630934,
"num_tokens": 12055544.0,
"step": 6165
},
{
"entropy": 6.4789731979370115,
"epoch": 0.6167841255560553,
"grad_norm": 1.21875,
"learning_rate": 0.0004969817278235777,
"loss": 6.3812,
"mean_token_accuracy": 0.13332609012722968,
"num_tokens": 12065076.0,
"step": 6170
},
{
"entropy": 6.428238248825073,
"epoch": 0.6172839506172839,
"grad_norm": 1.15625,
"learning_rate": 0.0004969758989411829,
"loss": 6.3562,
"mean_token_accuracy": 0.1403255730867386,
"num_tokens": 12074623.0,
"step": 6175
},
{
"entropy": 6.40726146697998,
"epoch": 0.6177837756785125,
"grad_norm": 1.171875,
"learning_rate": 0.0004969700644739315,
"loss": 6.2462,
"mean_token_accuracy": 0.14269398003816605,
"num_tokens": 12085040.0,
"step": 6180
},
{
"entropy": 6.3842200756073,
"epoch": 0.6182836007397411,
"grad_norm": 1.203125,
"learning_rate": 0.0004969642244219705,
"loss": 6.2858,
"mean_token_accuracy": 0.1406437113881111,
"num_tokens": 12094699.0,
"step": 6185
},
{
"entropy": 6.470867395401001,
"epoch": 0.6187834258009697,
"grad_norm": 1.1875,
"learning_rate": 0.0004969583787854467,
"loss": 6.2961,
"mean_token_accuracy": 0.1383143611252308,
"num_tokens": 12104256.0,
"step": 6190
},
{
"entropy": 6.342094802856446,
"epoch": 0.6192832508621983,
"grad_norm": 1.078125,
"learning_rate": 0.0004969525275645071,
"loss": 6.2767,
"mean_token_accuracy": 0.1414248526096344,
"num_tokens": 12114058.0,
"step": 6195
},
{
"entropy": 6.2767980098724365,
"epoch": 0.6197830759234269,
"grad_norm": 1.1640625,
"learning_rate": 0.0004969466707592991,
"loss": 6.3137,
"mean_token_accuracy": 0.14230649843811988,
"num_tokens": 12124483.0,
"step": 6200
},
{
"entropy": 6.425835084915161,
"epoch": 0.6202829009846553,
"grad_norm": 1.1328125,
"learning_rate": 0.00049694080836997,
"loss": 6.3082,
"mean_token_accuracy": 0.14319800660014154,
"num_tokens": 12134700.0,
"step": 6205
},
{
"entropy": 6.489741659164428,
"epoch": 0.6207827260458839,
"grad_norm": 1.1640625,
"learning_rate": 0.0004969349403966672,
"loss": 6.3279,
"mean_token_accuracy": 0.13634368106722833,
"num_tokens": 12144688.0,
"step": 6210
},
{
"entropy": 6.350111293792724,
"epoch": 0.6212825511071125,
"grad_norm": 1.2578125,
"learning_rate": 0.0004969290668395385,
"loss": 6.1983,
"mean_token_accuracy": 0.14928776174783706,
"num_tokens": 12154597.0,
"step": 6215
},
{
"entropy": 6.39958701133728,
"epoch": 0.6217823761683411,
"grad_norm": 1.1484375,
"learning_rate": 0.0004969231876987315,
"loss": 6.366,
"mean_token_accuracy": 0.13354292288422584,
"num_tokens": 12164730.0,
"step": 6220
},
{
"entropy": 6.458413171768188,
"epoch": 0.6222822012295697,
"grad_norm": 1.2109375,
"learning_rate": 0.0004969173029743942,
"loss": 6.416,
"mean_token_accuracy": 0.1325943648815155,
"num_tokens": 12174238.0,
"step": 6225
},
{
"entropy": 6.3747138500213625,
"epoch": 0.6227820262907983,
"grad_norm": 1.2109375,
"learning_rate": 0.0004969114126666746,
"loss": 6.261,
"mean_token_accuracy": 0.13903287425637245,
"num_tokens": 12183124.0,
"step": 6230
},
{
"entropy": 6.434756898880005,
"epoch": 0.6232818513520267,
"grad_norm": 1.203125,
"learning_rate": 0.0004969055167757211,
"loss": 6.2724,
"mean_token_accuracy": 0.1443145103752613,
"num_tokens": 12192076.0,
"step": 6235
},
{
"entropy": 6.368928384780884,
"epoch": 0.6237816764132553,
"grad_norm": 1.1328125,
"learning_rate": 0.0004968996153016819,
"loss": 6.244,
"mean_token_accuracy": 0.14949045404791833,
"num_tokens": 12201244.0,
"step": 6240
},
{
"entropy": 6.376616477966309,
"epoch": 0.6242815014744839,
"grad_norm": 1.21875,
"learning_rate": 0.0004968937082447054,
"loss": 6.3194,
"mean_token_accuracy": 0.13708976432681083,
"num_tokens": 12211349.0,
"step": 6245
},
{
"entropy": 6.39571590423584,
"epoch": 0.6247813265357125,
"grad_norm": 1.1484375,
"learning_rate": 0.0004968877956049403,
"loss": 6.2638,
"mean_token_accuracy": 0.13884067833423613,
"num_tokens": 12220880.0,
"step": 6250
},
{
"entropy": 6.406757259368897,
"epoch": 0.6252811515969411,
"grad_norm": 1.3046875,
"learning_rate": 0.0004968818773825355,
"loss": 6.3422,
"mean_token_accuracy": 0.13541234284639359,
"num_tokens": 12231398.0,
"step": 6255
},
{
"entropy": 6.470320844650269,
"epoch": 0.6257809766581697,
"grad_norm": 1.1953125,
"learning_rate": 0.0004968759535776396,
"loss": 6.3211,
"mean_token_accuracy": 0.13639183416962625,
"num_tokens": 12239487.0,
"step": 6260
},
{
"entropy": 6.464857482910157,
"epoch": 0.6262808017193983,
"grad_norm": 1.2109375,
"learning_rate": 0.0004968700241904018,
"loss": 6.4451,
"mean_token_accuracy": 0.13263344913721084,
"num_tokens": 12249984.0,
"step": 6265
},
{
"entropy": 6.422102642059326,
"epoch": 0.6267806267806267,
"grad_norm": 1.046875,
"learning_rate": 0.0004968640892209714,
"loss": 6.2522,
"mean_token_accuracy": 0.1418606497347355,
"num_tokens": 12259876.0,
"step": 6270
},
{
"entropy": 6.341937017440796,
"epoch": 0.6272804518418553,
"grad_norm": 1.109375,
"learning_rate": 0.0004968581486694975,
"loss": 6.2422,
"mean_token_accuracy": 0.14051881656050683,
"num_tokens": 12270262.0,
"step": 6275
},
{
"entropy": 6.332383489608764,
"epoch": 0.6277802769030839,
"grad_norm": 1.2265625,
"learning_rate": 0.0004968522025361297,
"loss": 6.2613,
"mean_token_accuracy": 0.1410231687128544,
"num_tokens": 12280432.0,
"step": 6280
},
{
"entropy": 6.426399374008179,
"epoch": 0.6282801019643125,
"grad_norm": 1.140625,
"learning_rate": 0.0004968462508210176,
"loss": 6.2601,
"mean_token_accuracy": 0.14495118483901023,
"num_tokens": 12290518.0,
"step": 6285
},
{
"entropy": 6.441583204269409,
"epoch": 0.6287799270255411,
"grad_norm": 1.28125,
"learning_rate": 0.0004968402935243109,
"loss": 6.3392,
"mean_token_accuracy": 0.13528941050171853,
"num_tokens": 12300305.0,
"step": 6290
},
{
"entropy": 6.272086238861084,
"epoch": 0.6292797520867697,
"grad_norm": 1.203125,
"learning_rate": 0.0004968343306461595,
"loss": 6.2696,
"mean_token_accuracy": 0.14362943097949027,
"num_tokens": 12309079.0,
"step": 6295
},
{
"entropy": 6.456324338912964,
"epoch": 0.6297795771479981,
"grad_norm": 1.3046875,
"learning_rate": 0.0004968283621867134,
"loss": 6.3645,
"mean_token_accuracy": 0.13107775077223777,
"num_tokens": 12319502.0,
"step": 6300
},
{
"entropy": 6.49516339302063,
"epoch": 0.6302794022092267,
"grad_norm": 1.1796875,
"learning_rate": 0.0004968223881461227,
"loss": 6.238,
"mean_token_accuracy": 0.1446000263094902,
"num_tokens": 12329025.0,
"step": 6305
},
{
"entropy": 6.355226039886475,
"epoch": 0.6307792272704553,
"grad_norm": 1.4375,
"learning_rate": 0.000496816408524538,
"loss": 6.3026,
"mean_token_accuracy": 0.1373799405992031,
"num_tokens": 12338822.0,
"step": 6310
},
{
"entropy": 6.361549615859985,
"epoch": 0.6312790523316839,
"grad_norm": 1.21875,
"learning_rate": 0.0004968104233221094,
"loss": 6.3376,
"mean_token_accuracy": 0.14064089059829712,
"num_tokens": 12348592.0,
"step": 6315
},
{
"entropy": 6.360891723632813,
"epoch": 0.6317788773929125,
"grad_norm": 1.125,
"learning_rate": 0.0004968044325389877,
"loss": 6.237,
"mean_token_accuracy": 0.14268747121095657,
"num_tokens": 12357673.0,
"step": 6320
},
{
"entropy": 6.414012718200683,
"epoch": 0.6322787024541411,
"grad_norm": 1.1328125,
"learning_rate": 0.0004967984361753235,
"loss": 6.2885,
"mean_token_accuracy": 0.14190788641572,
"num_tokens": 12367603.0,
"step": 6325
},
{
"entropy": 6.426939821243286,
"epoch": 0.6327785275153697,
"grad_norm": 1.1015625,
"learning_rate": 0.0004967924342312677,
"loss": 6.2996,
"mean_token_accuracy": 0.14523561894893647,
"num_tokens": 12376532.0,
"step": 6330
},
{
"entropy": 6.366886568069458,
"epoch": 0.6332783525765981,
"grad_norm": 1.1796875,
"learning_rate": 0.0004967864267069713,
"loss": 6.2622,
"mean_token_accuracy": 0.14098296463489532,
"num_tokens": 12386553.0,
"step": 6335
},
{
"entropy": 6.382465600967407,
"epoch": 0.6337781776378267,
"grad_norm": 1.171875,
"learning_rate": 0.0004967804136025856,
"loss": 6.291,
"mean_token_accuracy": 0.14418137967586517,
"num_tokens": 12396274.0,
"step": 6340
},
{
"entropy": 6.338514947891236,
"epoch": 0.6342780026990553,
"grad_norm": 1.2578125,
"learning_rate": 0.0004967743949182617,
"loss": 6.2284,
"mean_token_accuracy": 0.14256718009710312,
"num_tokens": 12405993.0,
"step": 6345
},
{
"entropy": 6.320691299438477,
"epoch": 0.6347778277602839,
"grad_norm": 1.265625,
"learning_rate": 0.0004967683706541511,
"loss": 6.2761,
"mean_token_accuracy": 0.1457001529633999,
"num_tokens": 12417309.0,
"step": 6350
},
{
"entropy": 6.32744460105896,
"epoch": 0.6352776528215125,
"grad_norm": 1.2421875,
"learning_rate": 0.0004967623408104054,
"loss": 6.1474,
"mean_token_accuracy": 0.14919132813811303,
"num_tokens": 12425981.0,
"step": 6355
},
{
"entropy": 6.4638735294342045,
"epoch": 0.6357774778827411,
"grad_norm": 1.1875,
"learning_rate": 0.0004967563053871762,
"loss": 6.2484,
"mean_token_accuracy": 0.14249523878097534,
"num_tokens": 12435197.0,
"step": 6360
},
{
"entropy": 6.355536365509034,
"epoch": 0.6362773029439696,
"grad_norm": 1.2265625,
"learning_rate": 0.0004967502643846155,
"loss": 6.2285,
"mean_token_accuracy": 0.14414375722408296,
"num_tokens": 12444697.0,
"step": 6365
},
{
"entropy": 6.346193933486939,
"epoch": 0.6367771280051981,
"grad_norm": 1.1484375,
"learning_rate": 0.000496744217802875,
"loss": 6.2236,
"mean_token_accuracy": 0.1432081863284111,
"num_tokens": 12454490.0,
"step": 6370
},
{
"entropy": 6.429242277145386,
"epoch": 0.6372769530664267,
"grad_norm": 1.140625,
"learning_rate": 0.0004967381656421073,
"loss": 6.2565,
"mean_token_accuracy": 0.13868944570422173,
"num_tokens": 12463440.0,
"step": 6375
},
{
"entropy": 6.363940620422364,
"epoch": 0.6377767781276553,
"grad_norm": 1.3515625,
"learning_rate": 0.0004967321079024643,
"loss": 6.3476,
"mean_token_accuracy": 0.140744711458683,
"num_tokens": 12473285.0,
"step": 6380
},
{
"entropy": 6.408857345581055,
"epoch": 0.6382766031888839,
"grad_norm": 1.3203125,
"learning_rate": 0.0004967260445840985,
"loss": 6.2048,
"mean_token_accuracy": 0.14893916323781015,
"num_tokens": 12481975.0,
"step": 6385
},
{
"entropy": 6.345850801467895,
"epoch": 0.6387764282501125,
"grad_norm": 1.109375,
"learning_rate": 0.0004967199756871624,
"loss": 6.2573,
"mean_token_accuracy": 0.14267202094197273,
"num_tokens": 12491736.0,
"step": 6390
},
{
"entropy": 6.292747259140015,
"epoch": 0.6392762533113411,
"grad_norm": 1.1171875,
"learning_rate": 0.0004967139012118088,
"loss": 6.3098,
"mean_token_accuracy": 0.13867436423897744,
"num_tokens": 12502369.0,
"step": 6395
},
{
"entropy": 6.410211420059204,
"epoch": 0.6397760783725696,
"grad_norm": 1.3046875,
"learning_rate": 0.0004967078211581907,
"loss": 6.2699,
"mean_token_accuracy": 0.1411287911236286,
"num_tokens": 12512906.0,
"step": 6400
},
{
"entropy": 6.413819694519043,
"epoch": 0.6402759034337981,
"grad_norm": 1.265625,
"learning_rate": 0.0004967017355264606,
"loss": 6.226,
"mean_token_accuracy": 0.14184003695845604,
"num_tokens": 12523454.0,
"step": 6405
},
{
"entropy": 6.363322067260742,
"epoch": 0.6407757284950267,
"grad_norm": 1.203125,
"learning_rate": 0.000496695644316772,
"loss": 6.3898,
"mean_token_accuracy": 0.1342937633395195,
"num_tokens": 12533228.0,
"step": 6410
},
{
"entropy": 6.439122819900513,
"epoch": 0.6412755535562553,
"grad_norm": 1.2421875,
"learning_rate": 0.0004966895475292781,
"loss": 6.3724,
"mean_token_accuracy": 0.13641492798924446,
"num_tokens": 12543188.0,
"step": 6415
},
{
"entropy": 6.3917735576629635,
"epoch": 0.6417753786174839,
"grad_norm": 1.1328125,
"learning_rate": 0.0004966834451641322,
"loss": 6.3076,
"mean_token_accuracy": 0.1359946012496948,
"num_tokens": 12553844.0,
"step": 6420
},
{
"entropy": 6.37999997138977,
"epoch": 0.6422752036787125,
"grad_norm": 1.2578125,
"learning_rate": 0.0004966773372214878,
"loss": 6.1957,
"mean_token_accuracy": 0.1438866063952446,
"num_tokens": 12563544.0,
"step": 6425
},
{
"entropy": 6.335693407058716,
"epoch": 0.642775028739941,
"grad_norm": 1.1640625,
"learning_rate": 0.0004966712237014987,
"loss": 6.2323,
"mean_token_accuracy": 0.1441716805100441,
"num_tokens": 12572894.0,
"step": 6430
},
{
"entropy": 6.394088935852051,
"epoch": 0.6432748538011696,
"grad_norm": 1.34375,
"learning_rate": 0.0004966651046043186,
"loss": 6.368,
"mean_token_accuracy": 0.1325935512781143,
"num_tokens": 12583533.0,
"step": 6435
},
{
"entropy": 6.432648086547852,
"epoch": 0.6437746788623981,
"grad_norm": 1.3671875,
"learning_rate": 0.0004966589799301016,
"loss": 6.2497,
"mean_token_accuracy": 0.14007219299674034,
"num_tokens": 12593160.0,
"step": 6440
},
{
"entropy": 6.490913581848145,
"epoch": 0.6442745039236267,
"grad_norm": 1.2421875,
"learning_rate": 0.0004966528496790015,
"loss": 6.3399,
"mean_token_accuracy": 0.1376480370759964,
"num_tokens": 12604010.0,
"step": 6445
},
{
"entropy": 6.316685390472412,
"epoch": 0.6447743289848553,
"grad_norm": 1.1640625,
"learning_rate": 0.0004966467138511729,
"loss": 6.2561,
"mean_token_accuracy": 0.14571298211812972,
"num_tokens": 12614256.0,
"step": 6450
},
{
"entropy": 6.35328164100647,
"epoch": 0.6452741540460839,
"grad_norm": 1.140625,
"learning_rate": 0.00049664057244677,
"loss": 6.3535,
"mean_token_accuracy": 0.13842764869332314,
"num_tokens": 12624228.0,
"step": 6455
},
{
"entropy": 6.425360584259034,
"epoch": 0.6457739791073125,
"grad_norm": 1.2421875,
"learning_rate": 0.0004966344254659473,
"loss": 6.2052,
"mean_token_accuracy": 0.14232587143778802,
"num_tokens": 12634611.0,
"step": 6460
},
{
"entropy": 6.3840900421142575,
"epoch": 0.646273804168541,
"grad_norm": 1.265625,
"learning_rate": 0.0004966282729088595,
"loss": 6.234,
"mean_token_accuracy": 0.13821083605289458,
"num_tokens": 12645309.0,
"step": 6465
},
{
"entropy": 6.39522705078125,
"epoch": 0.6467736292297696,
"grad_norm": 1.2578125,
"learning_rate": 0.0004966221147756615,
"loss": 6.2236,
"mean_token_accuracy": 0.14299412965774536,
"num_tokens": 12655283.0,
"step": 6470
},
{
"entropy": 6.333930921554566,
"epoch": 0.6472734542909981,
"grad_norm": 1.25,
"learning_rate": 0.0004966159510665079,
"loss": 6.2429,
"mean_token_accuracy": 0.14506687670946122,
"num_tokens": 12664531.0,
"step": 6475
},
{
"entropy": 6.336265420913696,
"epoch": 0.6477732793522267,
"grad_norm": 1.234375,
"learning_rate": 0.0004966097817815542,
"loss": 6.2894,
"mean_token_accuracy": 0.1429209031164646,
"num_tokens": 12674791.0,
"step": 6480
},
{
"entropy": 6.372271251678467,
"epoch": 0.6482731044134553,
"grad_norm": 1.2109375,
"learning_rate": 0.0004966036069209552,
"loss": 6.275,
"mean_token_accuracy": 0.1434067502617836,
"num_tokens": 12685359.0,
"step": 6485
},
{
"entropy": 6.332733774185181,
"epoch": 0.6487729294746839,
"grad_norm": 1.09375,
"learning_rate": 0.0004965974264848666,
"loss": 6.2598,
"mean_token_accuracy": 0.14337700605392456,
"num_tokens": 12694719.0,
"step": 6490
},
{
"entropy": 6.415884351730346,
"epoch": 0.6492727545359124,
"grad_norm": 1.59375,
"learning_rate": 0.0004965912404734438,
"loss": 6.281,
"mean_token_accuracy": 0.1463285878300667,
"num_tokens": 12704032.0,
"step": 6495
},
{
"entropy": 6.384467601776123,
"epoch": 0.649772579597141,
"grad_norm": 1.3515625,
"learning_rate": 0.0004965850488868424,
"loss": 6.2595,
"mean_token_accuracy": 0.14304308742284774,
"num_tokens": 12713785.0,
"step": 6500
},
{
"entropy": 6.264138174057007,
"epoch": 0.6502724046583696,
"grad_norm": 1.1484375,
"learning_rate": 0.0004965788517252181,
"loss": 6.1968,
"mean_token_accuracy": 0.14354190677404405,
"num_tokens": 12724718.0,
"step": 6505
},
{
"entropy": 6.4190146923065186,
"epoch": 0.6507722297195981,
"grad_norm": 1.2109375,
"learning_rate": 0.000496572648988727,
"loss": 6.3057,
"mean_token_accuracy": 0.143632373213768,
"num_tokens": 12733518.0,
"step": 6510
},
{
"entropy": 6.426302146911621,
"epoch": 0.6512720547808267,
"grad_norm": 1.2890625,
"learning_rate": 0.000496566440677525,
"loss": 6.2295,
"mean_token_accuracy": 0.14380089417099953,
"num_tokens": 12743453.0,
"step": 6515
},
{
"entropy": 6.307664966583252,
"epoch": 0.6517718798420553,
"grad_norm": 1.203125,
"learning_rate": 0.0004965602267917685,
"loss": 6.3183,
"mean_token_accuracy": 0.14244844019412994,
"num_tokens": 12753717.0,
"step": 6520
},
{
"entropy": 6.2848169803619385,
"epoch": 0.6522717049032839,
"grad_norm": 1.2109375,
"learning_rate": 0.0004965540073316136,
"loss": 6.2033,
"mean_token_accuracy": 0.14699351489543916,
"num_tokens": 12763240.0,
"step": 6525
},
{
"entropy": 6.396650123596191,
"epoch": 0.6527715299645124,
"grad_norm": 1.65625,
"learning_rate": 0.0004965477822972169,
"loss": 6.2913,
"mean_token_accuracy": 0.1478447750210762,
"num_tokens": 12773284.0,
"step": 6530
},
{
"entropy": 6.4042840003967285,
"epoch": 0.653271355025741,
"grad_norm": 1.296875,
"learning_rate": 0.0004965415516887349,
"loss": 6.2819,
"mean_token_accuracy": 0.13938205316662788,
"num_tokens": 12782189.0,
"step": 6535
},
{
"entropy": 6.255416440963745,
"epoch": 0.6537711800869695,
"grad_norm": 1.9921875,
"learning_rate": 0.0004965353155063246,
"loss": 6.2102,
"mean_token_accuracy": 0.14704835787415504,
"num_tokens": 12792790.0,
"step": 6540
},
{
"entropy": 6.35142970085144,
"epoch": 0.6542710051481981,
"grad_norm": 1.140625,
"learning_rate": 0.0004965290737501427,
"loss": 6.1764,
"mean_token_accuracy": 0.14953116625547408,
"num_tokens": 12802368.0,
"step": 6545
},
{
"entropy": 6.385757875442505,
"epoch": 0.6547708302094267,
"grad_norm": 1.171875,
"learning_rate": 0.0004965228264203464,
"loss": 6.2031,
"mean_token_accuracy": 0.14364102780818938,
"num_tokens": 12812226.0,
"step": 6550
},
{
"entropy": 6.329181432723999,
"epoch": 0.6552706552706553,
"grad_norm": 1.1328125,
"learning_rate": 0.0004965165735170928,
"loss": 6.2396,
"mean_token_accuracy": 0.14335149079561232,
"num_tokens": 12820986.0,
"step": 6555
},
{
"entropy": 6.272090101242066,
"epoch": 0.6557704803318838,
"grad_norm": 1.21875,
"learning_rate": 0.000496510315040539,
"loss": 6.2643,
"mean_token_accuracy": 0.14013660252094268,
"num_tokens": 12830690.0,
"step": 6560
},
{
"entropy": 6.421197843551636,
"epoch": 0.6562703053931124,
"grad_norm": 1.0859375,
"learning_rate": 0.0004965040509908429,
"loss": 6.302,
"mean_token_accuracy": 0.14080157801508902,
"num_tokens": 12841780.0,
"step": 6565
},
{
"entropy": 6.420072317123413,
"epoch": 0.656770130454341,
"grad_norm": 1.25,
"learning_rate": 0.0004964977813681618,
"loss": 6.2329,
"mean_token_accuracy": 0.14666478782892228,
"num_tokens": 12850713.0,
"step": 6570
},
{
"entropy": 6.315571737289429,
"epoch": 0.6572699555155695,
"grad_norm": 1.1640625,
"learning_rate": 0.0004964915061726534,
"loss": 6.2867,
"mean_token_accuracy": 0.14022428989410402,
"num_tokens": 12862211.0,
"step": 6575
},
{
"entropy": 6.335816144943237,
"epoch": 0.6577697805767981,
"grad_norm": 1.3203125,
"learning_rate": 0.0004964852254044759,
"loss": 6.3364,
"mean_token_accuracy": 0.13908637017011644,
"num_tokens": 12871171.0,
"step": 6580
},
{
"entropy": 6.371293926239014,
"epoch": 0.6582696056380267,
"grad_norm": 1.2265625,
"learning_rate": 0.0004964789390637871,
"loss": 6.1955,
"mean_token_accuracy": 0.14533864110708236,
"num_tokens": 12880601.0,
"step": 6585
},
{
"entropy": 6.34336256980896,
"epoch": 0.6587694306992553,
"grad_norm": 1.4453125,
"learning_rate": 0.0004964726471507451,
"loss": 6.1693,
"mean_token_accuracy": 0.14412349313497544,
"num_tokens": 12890702.0,
"step": 6590
},
{
"entropy": 6.350169134140015,
"epoch": 0.6592692557604838,
"grad_norm": 1.1015625,
"learning_rate": 0.0004964663496655083,
"loss": 6.2731,
"mean_token_accuracy": 0.13806238025426865,
"num_tokens": 12901156.0,
"step": 6595
},
{
"entropy": 6.4678342819213865,
"epoch": 0.6597690808217124,
"grad_norm": 1.375,
"learning_rate": 0.0004964600466082351,
"loss": 6.2836,
"mean_token_accuracy": 0.13456722125411033,
"num_tokens": 12912183.0,
"step": 6600
},
{
"entropy": 6.349811172485351,
"epoch": 0.660268905882941,
"grad_norm": 1.4296875,
"learning_rate": 0.0004964537379790842,
"loss": 6.2579,
"mean_token_accuracy": 0.14334989637136458,
"num_tokens": 12922200.0,
"step": 6605
},
{
"entropy": 6.2914872646331785,
"epoch": 0.6607687309441695,
"grad_norm": 1.203125,
"learning_rate": 0.0004964474237782141,
"loss": 6.146,
"mean_token_accuracy": 0.14655178785324097,
"num_tokens": 12931201.0,
"step": 6610
},
{
"entropy": 6.24609341621399,
"epoch": 0.6612685560053981,
"grad_norm": 1.1640625,
"learning_rate": 0.0004964411040057839,
"loss": 6.1381,
"mean_token_accuracy": 0.1485193267464638,
"num_tokens": 12941290.0,
"step": 6615
},
{
"entropy": 6.218661212921143,
"epoch": 0.6617683810666267,
"grad_norm": 1.1953125,
"learning_rate": 0.0004964347786619524,
"loss": 6.1749,
"mean_token_accuracy": 0.14614703878760338,
"num_tokens": 12953458.0,
"step": 6620
},
{
"entropy": 6.239731502532959,
"epoch": 0.6622682061278552,
"grad_norm": 1.609375,
"learning_rate": 0.0004964284477468791,
"loss": 6.0361,
"mean_token_accuracy": 0.1567079909145832,
"num_tokens": 12964072.0,
"step": 6625
},
{
"entropy": 6.469099521636963,
"epoch": 0.6627680311890838,
"grad_norm": 1.625,
"learning_rate": 0.0004964221112607228,
"loss": 6.2393,
"mean_token_accuracy": 0.1375857874751091,
"num_tokens": 12974092.0,
"step": 6630
},
{
"entropy": 6.321001815795898,
"epoch": 0.6632678562503124,
"grad_norm": 1.203125,
"learning_rate": 0.0004964157692036432,
"loss": 6.154,
"mean_token_accuracy": 0.14844254329800605,
"num_tokens": 12983546.0,
"step": 6635
},
{
"entropy": 6.345171070098877,
"epoch": 0.663767681311541,
"grad_norm": 1.2578125,
"learning_rate": 0.0004964094215757998,
"loss": 6.2617,
"mean_token_accuracy": 0.13610675185918808,
"num_tokens": 12993690.0,
"step": 6640
},
{
"entropy": 6.352869176864624,
"epoch": 0.6642675063727695,
"grad_norm": 1.21875,
"learning_rate": 0.0004964030683773525,
"loss": 6.1906,
"mean_token_accuracy": 0.14434328600764273,
"num_tokens": 13003248.0,
"step": 6645
},
{
"entropy": 6.354497718811035,
"epoch": 0.6647673314339981,
"grad_norm": 1.15625,
"learning_rate": 0.0004963967096084608,
"loss": 6.191,
"mean_token_accuracy": 0.14685217142105103,
"num_tokens": 13013182.0,
"step": 6650
},
{
"entropy": 6.293743562698364,
"epoch": 0.6652671564952267,
"grad_norm": 1.234375,
"learning_rate": 0.0004963903452692849,
"loss": 6.1996,
"mean_token_accuracy": 0.14745060428977014,
"num_tokens": 13022726.0,
"step": 6655
},
{
"entropy": 6.244716358184815,
"epoch": 0.6657669815564552,
"grad_norm": 1.1796875,
"learning_rate": 0.0004963839753599848,
"loss": 6.1575,
"mean_token_accuracy": 0.14454718828201293,
"num_tokens": 13031811.0,
"step": 6660
},
{
"entropy": 6.376889085769653,
"epoch": 0.6662668066176838,
"grad_norm": 1.1484375,
"learning_rate": 0.000496377599880721,
"loss": 6.1934,
"mean_token_accuracy": 0.14934000223875046,
"num_tokens": 13040884.0,
"step": 6665
},
{
"entropy": 6.3811346054077145,
"epoch": 0.6667666316789124,
"grad_norm": 1.3203125,
"learning_rate": 0.0004963712188316537,
"loss": 6.3223,
"mean_token_accuracy": 0.1370953120291233,
"num_tokens": 13049937.0,
"step": 6670
},
{
"entropy": 6.324701452255249,
"epoch": 0.667266456740141,
"grad_norm": 1.1640625,
"learning_rate": 0.0004963648322129435,
"loss": 6.1589,
"mean_token_accuracy": 0.1480522409081459,
"num_tokens": 13059307.0,
"step": 6675
},
{
"entropy": 6.3423168659210205,
"epoch": 0.6677662818013695,
"grad_norm": 1.21875,
"learning_rate": 0.000496358440024751,
"loss": 6.2881,
"mean_token_accuracy": 0.13714971542358398,
"num_tokens": 13069400.0,
"step": 6680
},
{
"entropy": 6.373897504806519,
"epoch": 0.6682661068625981,
"grad_norm": 1.1015625,
"learning_rate": 0.0004963520422672372,
"loss": 6.1803,
"mean_token_accuracy": 0.14665843173861504,
"num_tokens": 13079965.0,
"step": 6685
},
{
"entropy": 6.381875228881836,
"epoch": 0.6687659319238266,
"grad_norm": 1.15625,
"learning_rate": 0.000496345638940563,
"loss": 6.3575,
"mean_token_accuracy": 0.13467492684721946,
"num_tokens": 13090144.0,
"step": 6690
},
{
"entropy": 6.363946866989136,
"epoch": 0.6692657569850552,
"grad_norm": 1.1953125,
"learning_rate": 0.0004963392300448894,
"loss": 6.1517,
"mean_token_accuracy": 0.14645947366952897,
"num_tokens": 13100217.0,
"step": 6695
},
{
"entropy": 6.30076265335083,
"epoch": 0.6697655820462838,
"grad_norm": 1.3046875,
"learning_rate": 0.0004963328155803778,
"loss": 6.224,
"mean_token_accuracy": 0.14600871056318282,
"num_tokens": 13109031.0,
"step": 6700
},
{
"entropy": 6.380642557144165,
"epoch": 0.6702654071075124,
"grad_norm": 1.1640625,
"learning_rate": 0.0004963263955471895,
"loss": 6.3368,
"mean_token_accuracy": 0.13109761849045753,
"num_tokens": 13119073.0,
"step": 6705
},
{
"entropy": 6.366076898574829,
"epoch": 0.670765232168741,
"grad_norm": 1.21875,
"learning_rate": 0.000496319969945486,
"loss": 6.2847,
"mean_token_accuracy": 0.14624615982174874,
"num_tokens": 13129208.0,
"step": 6710
},
{
"entropy": 6.332978916168213,
"epoch": 0.6712650572299695,
"grad_norm": 1.2265625,
"learning_rate": 0.000496313538775429,
"loss": 6.2159,
"mean_token_accuracy": 0.14699893817305565,
"num_tokens": 13138559.0,
"step": 6715
},
{
"entropy": 6.361584281921386,
"epoch": 0.6717648822911981,
"grad_norm": 1.125,
"learning_rate": 0.0004963071020371803,
"loss": 6.3321,
"mean_token_accuracy": 0.14095332175493241,
"num_tokens": 13148456.0,
"step": 6720
},
{
"entropy": 6.360890054702759,
"epoch": 0.6722647073524266,
"grad_norm": 1.171875,
"learning_rate": 0.0004963006597309019,
"loss": 6.2481,
"mean_token_accuracy": 0.14297167286276818,
"num_tokens": 13158245.0,
"step": 6725
},
{
"entropy": 6.439178943634033,
"epoch": 0.6727645324136552,
"grad_norm": 1.1953125,
"learning_rate": 0.0004962942118567559,
"loss": 6.2805,
"mean_token_accuracy": 0.15162380859255792,
"num_tokens": 13166269.0,
"step": 6730
},
{
"entropy": 6.339335823059082,
"epoch": 0.6732643574748838,
"grad_norm": 1.2265625,
"learning_rate": 0.0004962877584149043,
"loss": 6.2415,
"mean_token_accuracy": 0.14097519665956498,
"num_tokens": 13176763.0,
"step": 6735
},
{
"entropy": 6.280173015594483,
"epoch": 0.6737641825361124,
"grad_norm": 1.1875,
"learning_rate": 0.0004962812994055098,
"loss": 6.2024,
"mean_token_accuracy": 0.14538279920816422,
"num_tokens": 13185945.0,
"step": 6740
},
{
"entropy": 6.405073738098144,
"epoch": 0.674264007597341,
"grad_norm": 1.234375,
"learning_rate": 0.0004962748348287347,
"loss": 6.2836,
"mean_token_accuracy": 0.14246615618467331,
"num_tokens": 13197205.0,
"step": 6745
},
{
"entropy": 6.296693897247314,
"epoch": 0.6747638326585695,
"grad_norm": 1.203125,
"learning_rate": 0.0004962683646847416,
"loss": 6.2635,
"mean_token_accuracy": 0.13742260485887528,
"num_tokens": 13206939.0,
"step": 6750
},
{
"entropy": 6.308182954788208,
"epoch": 0.675263657719798,
"grad_norm": 1.15625,
"learning_rate": 0.0004962618889736936,
"loss": 6.2009,
"mean_token_accuracy": 0.14284489750862123,
"num_tokens": 13216317.0,
"step": 6755
},
{
"entropy": 6.358166742324829,
"epoch": 0.6757634827810266,
"grad_norm": 1.234375,
"learning_rate": 0.0004962554076957533,
"loss": 6.2331,
"mean_token_accuracy": 0.1492699772119522,
"num_tokens": 13226594.0,
"step": 6760
},
{
"entropy": 6.428493928909302,
"epoch": 0.6762633078422552,
"grad_norm": 1.203125,
"learning_rate": 0.0004962489208510838,
"loss": 6.3811,
"mean_token_accuracy": 0.13592161610722542,
"num_tokens": 13237477.0,
"step": 6765
},
{
"entropy": 6.396593189239502,
"epoch": 0.6767631329034838,
"grad_norm": 1.2890625,
"learning_rate": 0.0004962424284398484,
"loss": 6.1747,
"mean_token_accuracy": 0.1454145684838295,
"num_tokens": 13247041.0,
"step": 6770
},
{
"entropy": 6.282503604888916,
"epoch": 0.6772629579647124,
"grad_norm": 1.296875,
"learning_rate": 0.0004962359304622105,
"loss": 6.1662,
"mean_token_accuracy": 0.14722471535205842,
"num_tokens": 13257223.0,
"step": 6775
},
{
"entropy": 6.334440422058106,
"epoch": 0.677762783025941,
"grad_norm": 1.1328125,
"learning_rate": 0.0004962294269183335,
"loss": 6.2123,
"mean_token_accuracy": 0.14640141129493714,
"num_tokens": 13267457.0,
"step": 6780
},
{
"entropy": 6.386912631988525,
"epoch": 0.6782626080871695,
"grad_norm": 1.171875,
"learning_rate": 0.000496222917808381,
"loss": 6.2375,
"mean_token_accuracy": 0.1386418327689171,
"num_tokens": 13277656.0,
"step": 6785
},
{
"entropy": 6.325541257858276,
"epoch": 0.678762433148398,
"grad_norm": 1.1015625,
"learning_rate": 0.0004962164031325169,
"loss": 6.2273,
"mean_token_accuracy": 0.14622305184602738,
"num_tokens": 13288483.0,
"step": 6790
},
{
"entropy": 6.298862409591675,
"epoch": 0.6792622582096266,
"grad_norm": 1.1875,
"learning_rate": 0.000496209882890905,
"loss": 6.1493,
"mean_token_accuracy": 0.15328536182641983,
"num_tokens": 13298312.0,
"step": 6795
},
{
"entropy": 6.229435968399048,
"epoch": 0.6797620832708552,
"grad_norm": 1.0390625,
"learning_rate": 0.0004962033570837094,
"loss": 6.0584,
"mean_token_accuracy": 0.14531668201088904,
"num_tokens": 13308038.0,
"step": 6800
},
{
"entropy": 6.285090208053589,
"epoch": 0.6802619083320838,
"grad_norm": 1.40625,
"learning_rate": 0.0004961968257110941,
"loss": 6.1565,
"mean_token_accuracy": 0.14741025865077972,
"num_tokens": 13317963.0,
"step": 6805
},
{
"entropy": 6.300033330917358,
"epoch": 0.6807617333933124,
"grad_norm": 1.109375,
"learning_rate": 0.0004961902887732236,
"loss": 6.2292,
"mean_token_accuracy": 0.14750295728445054,
"num_tokens": 13328210.0,
"step": 6810
},
{
"entropy": 6.311105060577392,
"epoch": 0.681261558454541,
"grad_norm": 1.1640625,
"learning_rate": 0.0004961837462702626,
"loss": 6.1991,
"mean_token_accuracy": 0.1448679596185684,
"num_tokens": 13337778.0,
"step": 6815
},
{
"entropy": 6.301775026321411,
"epoch": 0.6817613835157694,
"grad_norm": 1.078125,
"learning_rate": 0.0004961771982023752,
"loss": 6.1802,
"mean_token_accuracy": 0.14408588409423828,
"num_tokens": 13348117.0,
"step": 6820
},
{
"entropy": 6.342627429962159,
"epoch": 0.682261208576998,
"grad_norm": 1.234375,
"learning_rate": 0.0004961706445697265,
"loss": 6.1443,
"mean_token_accuracy": 0.14329586327075958,
"num_tokens": 13356379.0,
"step": 6825
},
{
"entropy": 6.260994005203247,
"epoch": 0.6827610336382266,
"grad_norm": 1.1640625,
"learning_rate": 0.0004961640853724813,
"loss": 6.1644,
"mean_token_accuracy": 0.14717764109373094,
"num_tokens": 13366621.0,
"step": 6830
},
{
"entropy": 6.316004228591919,
"epoch": 0.6832608586994552,
"grad_norm": 1.2421875,
"learning_rate": 0.0004961575206108046,
"loss": 6.3077,
"mean_token_accuracy": 0.13996322378516196,
"num_tokens": 13375596.0,
"step": 6835
},
{
"entropy": 6.387084531784057,
"epoch": 0.6837606837606838,
"grad_norm": 1.1875,
"learning_rate": 0.0004961509502848616,
"loss": 6.2583,
"mean_token_accuracy": 0.14108679220080375,
"num_tokens": 13385871.0,
"step": 6840
},
{
"entropy": 6.380372047424316,
"epoch": 0.6842605088219124,
"grad_norm": 1.25,
"learning_rate": 0.0004961443743948177,
"loss": 6.2637,
"mean_token_accuracy": 0.14109894260764122,
"num_tokens": 13395277.0,
"step": 6845
},
{
"entropy": 6.296953868865967,
"epoch": 0.684760333883141,
"grad_norm": 1.1171875,
"learning_rate": 0.000496137792940838,
"loss": 6.2915,
"mean_token_accuracy": 0.13900421634316446,
"num_tokens": 13405064.0,
"step": 6850
},
{
"entropy": 6.381401443481446,
"epoch": 0.6852601589443694,
"grad_norm": 1.2109375,
"learning_rate": 0.0004961312059230885,
"loss": 6.2604,
"mean_token_accuracy": 0.1429591543972492,
"num_tokens": 13414399.0,
"step": 6855
},
{
"entropy": 6.348307752609253,
"epoch": 0.685759984005598,
"grad_norm": 1.15625,
"learning_rate": 0.0004961246133417348,
"loss": 6.3415,
"mean_token_accuracy": 0.1393718972802162,
"num_tokens": 13424343.0,
"step": 6860
},
{
"entropy": 6.346564483642578,
"epoch": 0.6862598090668266,
"grad_norm": 1.2109375,
"learning_rate": 0.0004961180151969427,
"loss": 6.2204,
"mean_token_accuracy": 0.14897054955363273,
"num_tokens": 13434362.0,
"step": 6865
},
{
"entropy": 6.379272031784057,
"epoch": 0.6867596341280552,
"grad_norm": 1.2421875,
"learning_rate": 0.0004961114114888782,
"loss": 6.223,
"mean_token_accuracy": 0.14392918422818185,
"num_tokens": 13444578.0,
"step": 6870
},
{
"entropy": 6.2164021015167235,
"epoch": 0.6872594591892838,
"grad_norm": 1.1796875,
"learning_rate": 0.0004961048022177074,
"loss": 6.1051,
"mean_token_accuracy": 0.14629753604531287,
"num_tokens": 13454184.0,
"step": 6875
},
{
"entropy": 6.307594108581543,
"epoch": 0.6877592842505124,
"grad_norm": 1.2265625,
"learning_rate": 0.0004960981873835968,
"loss": 6.2097,
"mean_token_accuracy": 0.14229094237089157,
"num_tokens": 13464269.0,
"step": 6880
},
{
"entropy": 6.40620789527893,
"epoch": 0.6882591093117408,
"grad_norm": 1.2734375,
"learning_rate": 0.0004960915669867126,
"loss": 6.2728,
"mean_token_accuracy": 0.13971073776483536,
"num_tokens": 13472747.0,
"step": 6885
},
{
"entropy": 6.281014919281006,
"epoch": 0.6887589343729694,
"grad_norm": 1.1953125,
"learning_rate": 0.0004960849410272216,
"loss": 6.2331,
"mean_token_accuracy": 0.14719310104846955,
"num_tokens": 13481670.0,
"step": 6890
},
{
"entropy": 6.250548791885376,
"epoch": 0.689258759434198,
"grad_norm": 1.234375,
"learning_rate": 0.0004960783095052903,
"loss": 6.1379,
"mean_token_accuracy": 0.15078865438699723,
"num_tokens": 13490428.0,
"step": 6895
},
{
"entropy": 6.264186763763428,
"epoch": 0.6897585844954266,
"grad_norm": 1.109375,
"learning_rate": 0.0004960716724210856,
"loss": 6.1004,
"mean_token_accuracy": 0.14907412976026535,
"num_tokens": 13499549.0,
"step": 6900
},
{
"entropy": 6.317903137207031,
"epoch": 0.6902584095566552,
"grad_norm": 1.1171875,
"learning_rate": 0.0004960650297747746,
"loss": 6.2773,
"mean_token_accuracy": 0.14041923731565475,
"num_tokens": 13508930.0,
"step": 6905
},
{
"entropy": 6.352906656265259,
"epoch": 0.6907582346178838,
"grad_norm": 1.21875,
"learning_rate": 0.0004960583815665242,
"loss": 6.2872,
"mean_token_accuracy": 0.1401541970670223,
"num_tokens": 13518858.0,
"step": 6910
},
{
"entropy": 6.3616118907928465,
"epoch": 0.6912580596791124,
"grad_norm": 1.234375,
"learning_rate": 0.0004960517277965018,
"loss": 6.2321,
"mean_token_accuracy": 0.13450878858566284,
"num_tokens": 13529346.0,
"step": 6915
},
{
"entropy": 6.332385587692261,
"epoch": 0.6917578847403408,
"grad_norm": 1.359375,
"learning_rate": 0.0004960450684648749,
"loss": 6.2224,
"mean_token_accuracy": 0.13784221857786177,
"num_tokens": 13539096.0,
"step": 6920
},
{
"entropy": 6.3196052551269535,
"epoch": 0.6922577098015694,
"grad_norm": 1.21875,
"learning_rate": 0.000496038403571811,
"loss": 6.2533,
"mean_token_accuracy": 0.14087265878915786,
"num_tokens": 13548698.0,
"step": 6925
},
{
"entropy": 6.305506658554077,
"epoch": 0.692757534862798,
"grad_norm": 1.1328125,
"learning_rate": 0.0004960317331174777,
"loss": 6.2405,
"mean_token_accuracy": 0.14463794156908988,
"num_tokens": 13559550.0,
"step": 6930
},
{
"entropy": 6.391615772247315,
"epoch": 0.6932573599240266,
"grad_norm": 1.1953125,
"learning_rate": 0.0004960250571020428,
"loss": 6.3138,
"mean_token_accuracy": 0.13640302568674087,
"num_tokens": 13569248.0,
"step": 6935
},
{
"entropy": 6.390089273452759,
"epoch": 0.6937571849852552,
"grad_norm": 1.2578125,
"learning_rate": 0.0004960183755256744,
"loss": 6.1873,
"mean_token_accuracy": 0.14286122098565102,
"num_tokens": 13578957.0,
"step": 6940
},
{
"entropy": 6.385510396957398,
"epoch": 0.6942570100464838,
"grad_norm": 1.1328125,
"learning_rate": 0.0004960116883885406,
"loss": 6.2871,
"mean_token_accuracy": 0.13741213977336883,
"num_tokens": 13589630.0,
"step": 6945
},
{
"entropy": 6.340646982192993,
"epoch": 0.6947568351077124,
"grad_norm": 1.3515625,
"learning_rate": 0.0004960049956908095,
"loss": 6.1921,
"mean_token_accuracy": 0.14678001776337624,
"num_tokens": 13599067.0,
"step": 6950
},
{
"entropy": 6.34862060546875,
"epoch": 0.6952566601689408,
"grad_norm": 1.1953125,
"learning_rate": 0.0004959982974326496,
"loss": 6.2588,
"mean_token_accuracy": 0.1393041916191578,
"num_tokens": 13609068.0,
"step": 6955
},
{
"entropy": 6.370382833480835,
"epoch": 0.6957564852301694,
"grad_norm": 1.390625,
"learning_rate": 0.0004959915936142294,
"loss": 6.3076,
"mean_token_accuracy": 0.1441367633640766,
"num_tokens": 13619112.0,
"step": 6960
},
{
"entropy": 6.406302356719971,
"epoch": 0.696256310291398,
"grad_norm": 1.1328125,
"learning_rate": 0.0004959848842357175,
"loss": 6.3195,
"mean_token_accuracy": 0.14691561609506607,
"num_tokens": 13629518.0,
"step": 6965
},
{
"entropy": 6.4604637145996096,
"epoch": 0.6967561353526266,
"grad_norm": 1.1875,
"learning_rate": 0.0004959781692972829,
"loss": 6.332,
"mean_token_accuracy": 0.14065197557210923,
"num_tokens": 13639796.0,
"step": 6970
},
{
"entropy": 6.385721206665039,
"epoch": 0.6972559604138552,
"grad_norm": 1.3203125,
"learning_rate": 0.0004959714487990943,
"loss": 6.2734,
"mean_token_accuracy": 0.1430683322250843,
"num_tokens": 13649876.0,
"step": 6975
},
{
"entropy": 6.388269281387329,
"epoch": 0.6977557854750838,
"grad_norm": 1.296875,
"learning_rate": 0.000495964722741321,
"loss": 6.2511,
"mean_token_accuracy": 0.14366811960935594,
"num_tokens": 13660670.0,
"step": 6980
},
{
"entropy": 6.321117496490478,
"epoch": 0.6982556105363122,
"grad_norm": 1.171875,
"learning_rate": 0.0004959579911241322,
"loss": 6.1838,
"mean_token_accuracy": 0.14604139775037767,
"num_tokens": 13669958.0,
"step": 6985
},
{
"entropy": 6.266972541809082,
"epoch": 0.6987554355975408,
"grad_norm": 1.3671875,
"learning_rate": 0.0004959512539476971,
"loss": 6.1279,
"mean_token_accuracy": 0.1502666801214218,
"num_tokens": 13678414.0,
"step": 6990
},
{
"entropy": 6.276806116104126,
"epoch": 0.6992552606587694,
"grad_norm": 1.4453125,
"learning_rate": 0.0004959445112121853,
"loss": 6.1646,
"mean_token_accuracy": 0.1487281210720539,
"num_tokens": 13687424.0,
"step": 6995
},
{
"entropy": 6.331806278228759,
"epoch": 0.699755085719998,
"grad_norm": 1.296875,
"learning_rate": 0.0004959377629177665,
"loss": 6.3056,
"mean_token_accuracy": 0.13894835487008095,
"num_tokens": 13697249.0,
"step": 7000
},
{
"entropy": 6.304219770431518,
"epoch": 0.7002549107812266,
"grad_norm": 1.28125,
"learning_rate": 0.0004959310090646104,
"loss": 6.1942,
"mean_token_accuracy": 0.145977284014225,
"num_tokens": 13707059.0,
"step": 7005
},
{
"entropy": 6.3667525291442875,
"epoch": 0.7007547358424552,
"grad_norm": 1.171875,
"learning_rate": 0.0004959242496528869,
"loss": 6.1456,
"mean_token_accuracy": 0.1492059513926506,
"num_tokens": 13715899.0,
"step": 7010
},
{
"entropy": 6.317831707000733,
"epoch": 0.7012545609036838,
"grad_norm": 1.2265625,
"learning_rate": 0.0004959174846827663,
"loss": 6.2824,
"mean_token_accuracy": 0.13746010214090348,
"num_tokens": 13725318.0,
"step": 7015
},
{
"entropy": 6.337517499923706,
"epoch": 0.7017543859649122,
"grad_norm": 1.2265625,
"learning_rate": 0.0004959107141544186,
"loss": 6.2518,
"mean_token_accuracy": 0.1441350281238556,
"num_tokens": 13734816.0,
"step": 7020
},
{
"entropy": 6.415861749649048,
"epoch": 0.7022542110261408,
"grad_norm": 1.234375,
"learning_rate": 0.000495903938068014,
"loss": 6.278,
"mean_token_accuracy": 0.13754311501979827,
"num_tokens": 13744323.0,
"step": 7025
},
{
"entropy": 6.501106691360474,
"epoch": 0.7027540360873694,
"grad_norm": 1.171875,
"learning_rate": 0.0004958971564237233,
"loss": 6.4612,
"mean_token_accuracy": 0.12470668181777,
"num_tokens": 13754301.0,
"step": 7030
},
{
"entropy": 6.422401475906372,
"epoch": 0.703253861148598,
"grad_norm": 1.1953125,
"learning_rate": 0.000495890369221717,
"loss": 6.319,
"mean_token_accuracy": 0.13458661139011383,
"num_tokens": 13763561.0,
"step": 7035
},
{
"entropy": 6.3136241912841795,
"epoch": 0.7037536862098266,
"grad_norm": 1.15625,
"learning_rate": 0.0004958835764621657,
"loss": 6.2031,
"mean_token_accuracy": 0.14579539373517036,
"num_tokens": 13773500.0,
"step": 7040
},
{
"entropy": 6.417852783203125,
"epoch": 0.7042535112710552,
"grad_norm": 1.15625,
"learning_rate": 0.0004958767781452406,
"loss": 6.2024,
"mean_token_accuracy": 0.14278700202703476,
"num_tokens": 13782390.0,
"step": 7045
},
{
"entropy": 6.33878607749939,
"epoch": 0.7047533363322837,
"grad_norm": 1.265625,
"learning_rate": 0.0004958699742711126,
"loss": 6.1845,
"mean_token_accuracy": 0.1478372909128666,
"num_tokens": 13791790.0,
"step": 7050
},
{
"entropy": 6.353102159500122,
"epoch": 0.7052531613935122,
"grad_norm": 1.6796875,
"learning_rate": 0.0004958631648399528,
"loss": 6.2748,
"mean_token_accuracy": 0.1372276224195957,
"num_tokens": 13802352.0,
"step": 7055
},
{
"entropy": 6.361660957336426,
"epoch": 0.7057529864547408,
"grad_norm": 1.21875,
"learning_rate": 0.0004958563498519327,
"loss": 6.2238,
"mean_token_accuracy": 0.14929865226149558,
"num_tokens": 13812905.0,
"step": 7060
},
{
"entropy": 6.359763526916504,
"epoch": 0.7062528115159694,
"grad_norm": 1.234375,
"learning_rate": 0.0004958495293072235,
"loss": 6.3244,
"mean_token_accuracy": 0.13780978322029114,
"num_tokens": 13823456.0,
"step": 7065
},
{
"entropy": 6.3433257102966305,
"epoch": 0.706752636577198,
"grad_norm": 1.2109375,
"learning_rate": 0.0004958427032059971,
"loss": 6.1683,
"mean_token_accuracy": 0.15489820539951324,
"num_tokens": 13832110.0,
"step": 7070
},
{
"entropy": 6.2405171394348145,
"epoch": 0.7072524616384266,
"grad_norm": 1.2265625,
"learning_rate": 0.0004958358715484251,
"loss": 6.188,
"mean_token_accuracy": 0.14749221354722977,
"num_tokens": 13841637.0,
"step": 7075
},
{
"entropy": 6.304652833938599,
"epoch": 0.7077522866996552,
"grad_norm": 1.234375,
"learning_rate": 0.0004958290343346795,
"loss": 6.1774,
"mean_token_accuracy": 0.14241352155804635,
"num_tokens": 13852185.0,
"step": 7080
},
{
"entropy": 6.319034194946289,
"epoch": 0.7082521117608837,
"grad_norm": 1.2265625,
"learning_rate": 0.000495822191564932,
"loss": 6.1181,
"mean_token_accuracy": 0.15449463427066804,
"num_tokens": 13862469.0,
"step": 7085
},
{
"entropy": 6.327530145645142,
"epoch": 0.7087519368221122,
"grad_norm": 1.265625,
"learning_rate": 0.0004958153432393553,
"loss": 6.208,
"mean_token_accuracy": 0.14218529164791108,
"num_tokens": 13872472.0,
"step": 7090
},
{
"entropy": 6.312508249282837,
"epoch": 0.7092517618833408,
"grad_norm": 1.046875,
"learning_rate": 0.000495808489358121,
"loss": 6.2414,
"mean_token_accuracy": 0.13936603292822838,
"num_tokens": 13882622.0,
"step": 7095
},
{
"entropy": 6.330296850204467,
"epoch": 0.7097515869445694,
"grad_norm": 1.234375,
"learning_rate": 0.0004958016299214022,
"loss": 6.2367,
"mean_token_accuracy": 0.1445574387907982,
"num_tokens": 13891836.0,
"step": 7100
},
{
"entropy": 6.404167985916137,
"epoch": 0.710251412005798,
"grad_norm": 1.1796875,
"learning_rate": 0.0004957947649293712,
"loss": 6.1339,
"mean_token_accuracy": 0.14620952308177948,
"num_tokens": 13901555.0,
"step": 7105
},
{
"entropy": 6.3054383277893065,
"epoch": 0.7107512370670266,
"grad_norm": 1.21875,
"learning_rate": 0.0004957878943822006,
"loss": 6.2362,
"mean_token_accuracy": 0.1425202839076519,
"num_tokens": 13911145.0,
"step": 7110
},
{
"entropy": 6.234632587432861,
"epoch": 0.7112510621282551,
"grad_norm": 1.21875,
"learning_rate": 0.0004957810182800634,
"loss": 6.1371,
"mean_token_accuracy": 0.15011852607131004,
"num_tokens": 13920375.0,
"step": 7115
},
{
"entropy": 6.272734117507935,
"epoch": 0.7117508871894836,
"grad_norm": 1.125,
"learning_rate": 0.0004957741366231327,
"loss": 6.1423,
"mean_token_accuracy": 0.15246715471148492,
"num_tokens": 13930175.0,
"step": 7120
},
{
"entropy": 6.287425947189331,
"epoch": 0.7122507122507122,
"grad_norm": 1.09375,
"learning_rate": 0.0004957672494115815,
"loss": 6.222,
"mean_token_accuracy": 0.15177012532949447,
"num_tokens": 13939935.0,
"step": 7125
},
{
"entropy": 6.3001793384552,
"epoch": 0.7127505373119408,
"grad_norm": 1.3046875,
"learning_rate": 0.000495760356645583,
"loss": 6.1919,
"mean_token_accuracy": 0.1353710785508156,
"num_tokens": 13950356.0,
"step": 7130
},
{
"entropy": 6.36169319152832,
"epoch": 0.7132503623731694,
"grad_norm": 1.203125,
"learning_rate": 0.0004957534583253108,
"loss": 6.2097,
"mean_token_accuracy": 0.14495083540678025,
"num_tokens": 13960661.0,
"step": 7135
},
{
"entropy": 6.388730478286743,
"epoch": 0.713750187434398,
"grad_norm": 1.1640625,
"learning_rate": 0.0004957465544509384,
"loss": 6.2234,
"mean_token_accuracy": 0.14034337550401688,
"num_tokens": 13970629.0,
"step": 7140
},
{
"entropy": 6.263514757156372,
"epoch": 0.7142500124956266,
"grad_norm": 1.3671875,
"learning_rate": 0.0004957396450226395,
"loss": 6.1301,
"mean_token_accuracy": 0.15107150077819825,
"num_tokens": 13979801.0,
"step": 7145
},
{
"entropy": 6.31006269454956,
"epoch": 0.7147498375568551,
"grad_norm": 1.2578125,
"learning_rate": 0.0004957327300405879,
"loss": 6.3376,
"mean_token_accuracy": 0.14776059985160828,
"num_tokens": 13989749.0,
"step": 7150
},
{
"entropy": 6.3592592716217045,
"epoch": 0.7152496626180836,
"grad_norm": 1.1171875,
"learning_rate": 0.0004957258095049577,
"loss": 6.2236,
"mean_token_accuracy": 0.14252349361777306,
"num_tokens": 13999483.0,
"step": 7155
},
{
"entropy": 6.30907096862793,
"epoch": 0.7157494876793122,
"grad_norm": 1.15625,
"learning_rate": 0.0004957188834159229,
"loss": 6.1988,
"mean_token_accuracy": 0.15286268293857574,
"num_tokens": 14009243.0,
"step": 7160
},
{
"entropy": 6.210056018829346,
"epoch": 0.7162493127405408,
"grad_norm": 1.1640625,
"learning_rate": 0.0004957119517736577,
"loss": 6.1664,
"mean_token_accuracy": 0.1418146498501301,
"num_tokens": 14020452.0,
"step": 7165
},
{
"entropy": 6.310309791564942,
"epoch": 0.7167491378017694,
"grad_norm": 1.1171875,
"learning_rate": 0.0004957050145783366,
"loss": 6.1662,
"mean_token_accuracy": 0.13924267292022705,
"num_tokens": 14030446.0,
"step": 7170
},
{
"entropy": 6.401497268676758,
"epoch": 0.717248962862998,
"grad_norm": 1.140625,
"learning_rate": 0.0004956980718301342,
"loss": 6.3636,
"mean_token_accuracy": 0.13962490484118462,
"num_tokens": 14040742.0,
"step": 7175
},
{
"entropy": 6.335114574432373,
"epoch": 0.7177487879242265,
"grad_norm": 1.546875,
"learning_rate": 0.0004956911235292251,
"loss": 6.175,
"mean_token_accuracy": 0.14628776982426644,
"num_tokens": 14050255.0,
"step": 7180
},
{
"entropy": 6.326679706573486,
"epoch": 0.7182486129854551,
"grad_norm": 1.3828125,
"learning_rate": 0.0004956841696757841,
"loss": 6.128,
"mean_token_accuracy": 0.15696224793791771,
"num_tokens": 14059745.0,
"step": 7185
},
{
"entropy": 6.26316556930542,
"epoch": 0.7187484380466836,
"grad_norm": 1.21875,
"learning_rate": 0.0004956772102699862,
"loss": 6.1602,
"mean_token_accuracy": 0.14652982652187346,
"num_tokens": 14069741.0,
"step": 7190
},
{
"entropy": 6.308904933929443,
"epoch": 0.7192482631079122,
"grad_norm": 1.1484375,
"learning_rate": 0.0004956702453120064,
"loss": 6.2324,
"mean_token_accuracy": 0.14142434820532798,
"num_tokens": 14078758.0,
"step": 7195
},
{
"entropy": 6.391016483306885,
"epoch": 0.7197480881691408,
"grad_norm": 1.34375,
"learning_rate": 0.0004956632748020201,
"loss": 6.2724,
"mean_token_accuracy": 0.14334044381976127,
"num_tokens": 14087770.0,
"step": 7200
},
{
"entropy": 6.332693386077881,
"epoch": 0.7202479132303694,
"grad_norm": 1.328125,
"learning_rate": 0.0004956562987402026,
"loss": 6.256,
"mean_token_accuracy": 0.13745878636837006,
"num_tokens": 14097139.0,
"step": 7205
},
{
"entropy": 6.224049139022827,
"epoch": 0.720747738291598,
"grad_norm": 1.4921875,
"learning_rate": 0.0004956493171267293,
"loss": 6.1086,
"mean_token_accuracy": 0.15160176977515222,
"num_tokens": 14107040.0,
"step": 7210
},
{
"entropy": 6.383421754837036,
"epoch": 0.7212475633528265,
"grad_norm": 1.296875,
"learning_rate": 0.000495642329961776,
"loss": 6.2514,
"mean_token_accuracy": 0.14360006675124168,
"num_tokens": 14117103.0,
"step": 7215
},
{
"entropy": 6.401718473434448,
"epoch": 0.7217473884140551,
"grad_norm": 1.2265625,
"learning_rate": 0.0004956353372455185,
"loss": 6.2504,
"mean_token_accuracy": 0.14321641996502876,
"num_tokens": 14127608.0,
"step": 7220
},
{
"entropy": 6.27881383895874,
"epoch": 0.7222472134752836,
"grad_norm": 1.1328125,
"learning_rate": 0.0004956283389781327,
"loss": 6.1753,
"mean_token_accuracy": 0.14906150475144386,
"num_tokens": 14137618.0,
"step": 7225
},
{
"entropy": 6.2777174949646,
"epoch": 0.7227470385365122,
"grad_norm": 1.2109375,
"learning_rate": 0.0004956213351597946,
"loss": 6.2148,
"mean_token_accuracy": 0.14890653192996978,
"num_tokens": 14147285.0,
"step": 7230
},
{
"entropy": 6.284318304061889,
"epoch": 0.7232468635977408,
"grad_norm": 1.1875,
"learning_rate": 0.0004956143257906805,
"loss": 6.1478,
"mean_token_accuracy": 0.14911566078662872,
"num_tokens": 14156398.0,
"step": 7235
},
{
"entropy": 6.239259529113769,
"epoch": 0.7237466886589694,
"grad_norm": 1.265625,
"learning_rate": 0.0004956073108709667,
"loss": 6.2226,
"mean_token_accuracy": 0.13758197352290152,
"num_tokens": 14166562.0,
"step": 7240
},
{
"entropy": 6.265067005157471,
"epoch": 0.7242465137201979,
"grad_norm": 1.1328125,
"learning_rate": 0.0004956002904008298,
"loss": 6.0888,
"mean_token_accuracy": 0.1526718482375145,
"num_tokens": 14175824.0,
"step": 7245
},
{
"entropy": 6.3486902713775635,
"epoch": 0.7247463387814265,
"grad_norm": 1.34375,
"learning_rate": 0.0004955932643804463,
"loss": 6.1528,
"mean_token_accuracy": 0.1450277164578438,
"num_tokens": 14185181.0,
"step": 7250
},
{
"entropy": 6.3490941524505615,
"epoch": 0.7252461638426551,
"grad_norm": 1.4609375,
"learning_rate": 0.000495586232809993,
"loss": 6.2731,
"mean_token_accuracy": 0.14282962530851365,
"num_tokens": 14194622.0,
"step": 7255
},
{
"entropy": 6.366567850112915,
"epoch": 0.7257459889038836,
"grad_norm": 1.4921875,
"learning_rate": 0.0004955791956896469,
"loss": 6.2137,
"mean_token_accuracy": 0.14499950930476188,
"num_tokens": 14204758.0,
"step": 7260
},
{
"entropy": 6.292021656036377,
"epoch": 0.7262458139651122,
"grad_norm": 1.0859375,
"learning_rate": 0.000495572153019585,
"loss": 6.1878,
"mean_token_accuracy": 0.14332186356186866,
"num_tokens": 14214926.0,
"step": 7265
},
{
"entropy": 6.323084688186645,
"epoch": 0.7267456390263408,
"grad_norm": 1.1640625,
"learning_rate": 0.0004955651047999844,
"loss": 6.2134,
"mean_token_accuracy": 0.14154637306928636,
"num_tokens": 14225372.0,
"step": 7270
},
{
"entropy": 6.328884792327881,
"epoch": 0.7272454640875694,
"grad_norm": 1.375,
"learning_rate": 0.0004955580510310226,
"loss": 6.1521,
"mean_token_accuracy": 0.1474081188440323,
"num_tokens": 14235676.0,
"step": 7275
},
{
"entropy": 6.300685214996338,
"epoch": 0.7277452891487979,
"grad_norm": 1.2109375,
"learning_rate": 0.0004955509917128771,
"loss": 6.2624,
"mean_token_accuracy": 0.13789445906877518,
"num_tokens": 14244196.0,
"step": 7280
},
{
"entropy": 6.312507438659668,
"epoch": 0.7282451142100265,
"grad_norm": 1.21875,
"learning_rate": 0.0004955439268457252,
"loss": 6.2368,
"mean_token_accuracy": 0.1401965029537678,
"num_tokens": 14253648.0,
"step": 7285
},
{
"entropy": 6.46242733001709,
"epoch": 0.728744939271255,
"grad_norm": 1.125,
"learning_rate": 0.0004955368564297449,
"loss": 6.3592,
"mean_token_accuracy": 0.13597094565629958,
"num_tokens": 14264373.0,
"step": 7290
},
{
"entropy": 6.311672306060791,
"epoch": 0.7292447643324836,
"grad_norm": 1.28125,
"learning_rate": 0.0004955297804651142,
"loss": 6.128,
"mean_token_accuracy": 0.1502915844321251,
"num_tokens": 14274544.0,
"step": 7295
},
{
"entropy": 6.363030481338501,
"epoch": 0.7297445893937122,
"grad_norm": 1.09375,
"learning_rate": 0.0004955226989520107,
"loss": 6.2276,
"mean_token_accuracy": 0.13519150614738465,
"num_tokens": 14284648.0,
"step": 7300
},
{
"entropy": 6.253767395019532,
"epoch": 0.7302444144549408,
"grad_norm": 1.09375,
"learning_rate": 0.000495515611890613,
"loss": 6.1655,
"mean_token_accuracy": 0.14713185355067254,
"num_tokens": 14294308.0,
"step": 7305
},
{
"entropy": 6.295068836212158,
"epoch": 0.7307442395161693,
"grad_norm": 1.203125,
"learning_rate": 0.0004955085192810993,
"loss": 6.2184,
"mean_token_accuracy": 0.1475299045443535,
"num_tokens": 14304965.0,
"step": 7310
},
{
"entropy": 6.299453830718994,
"epoch": 0.7312440645773979,
"grad_norm": 1.2578125,
"learning_rate": 0.0004955014211236479,
"loss": 6.1768,
"mean_token_accuracy": 0.14760952666401864,
"num_tokens": 14315880.0,
"step": 7315
},
{
"entropy": 6.2900251865386965,
"epoch": 0.7317438896386265,
"grad_norm": 1.3359375,
"learning_rate": 0.0004954943174184375,
"loss": 6.2375,
"mean_token_accuracy": 0.14287684857845306,
"num_tokens": 14326316.0,
"step": 7320
},
{
"entropy": 6.290630865097046,
"epoch": 0.732243714699855,
"grad_norm": 1.3046875,
"learning_rate": 0.0004954872081656469,
"loss": 6.1776,
"mean_token_accuracy": 0.15054567158222198,
"num_tokens": 14335802.0,
"step": 7325
},
{
"entropy": 6.2418053150177,
"epoch": 0.7327435397610836,
"grad_norm": 1.2109375,
"learning_rate": 0.0004954800933654548,
"loss": 6.1637,
"mean_token_accuracy": 0.15217621996998787,
"num_tokens": 14346050.0,
"step": 7330
},
{
"entropy": 6.333403587341309,
"epoch": 0.7332433648223122,
"grad_norm": 1.1171875,
"learning_rate": 0.0004954729730180403,
"loss": 6.1368,
"mean_token_accuracy": 0.15035522133111953,
"num_tokens": 14355483.0,
"step": 7335
},
{
"entropy": 6.31912317276001,
"epoch": 0.7337431898835408,
"grad_norm": 1.203125,
"learning_rate": 0.0004954658471235825,
"loss": 6.0991,
"mean_token_accuracy": 0.1499519780278206,
"num_tokens": 14364649.0,
"step": 7340
},
{
"entropy": 6.217097806930542,
"epoch": 0.7342430149447693,
"grad_norm": 1.234375,
"learning_rate": 0.0004954587156822607,
"loss": 6.1188,
"mean_token_accuracy": 0.1522404246032238,
"num_tokens": 14374495.0,
"step": 7345
},
{
"entropy": 6.310339021682739,
"epoch": 0.7347428400059979,
"grad_norm": 1.1796875,
"learning_rate": 0.0004954515786942544,
"loss": 6.2123,
"mean_token_accuracy": 0.1365861713886261,
"num_tokens": 14384247.0,
"step": 7350
},
{
"entropy": 6.312385892868042,
"epoch": 0.7352426650672265,
"grad_norm": 1.390625,
"learning_rate": 0.000495444436159743,
"loss": 6.2561,
"mean_token_accuracy": 0.1367305785417557,
"num_tokens": 14393675.0,
"step": 7355
},
{
"entropy": 6.292232418060303,
"epoch": 0.735742490128455,
"grad_norm": 1.1875,
"learning_rate": 0.0004954372880789064,
"loss": 6.1558,
"mean_token_accuracy": 0.14200675413012503,
"num_tokens": 14403579.0,
"step": 7360
},
{
"entropy": 6.392525148391724,
"epoch": 0.7362423151896836,
"grad_norm": 1.34375,
"learning_rate": 0.0004954301344519244,
"loss": 6.1461,
"mean_token_accuracy": 0.14907317757606506,
"num_tokens": 14413506.0,
"step": 7365
},
{
"entropy": 6.4459082126617435,
"epoch": 0.7367421402509122,
"grad_norm": 1.2578125,
"learning_rate": 0.0004954229752789769,
"loss": 6.3216,
"mean_token_accuracy": 0.14311579316854478,
"num_tokens": 14422960.0,
"step": 7370
},
{
"entropy": 6.364059925079346,
"epoch": 0.7372419653121407,
"grad_norm": 1.1484375,
"learning_rate": 0.0004954158105602441,
"loss": 6.3018,
"mean_token_accuracy": 0.14146305993199348,
"num_tokens": 14432207.0,
"step": 7375
},
{
"entropy": 6.295948457717896,
"epoch": 0.7377417903733693,
"grad_norm": 1.3671875,
"learning_rate": 0.0004954086402959061,
"loss": 6.2681,
"mean_token_accuracy": 0.13732415065169334,
"num_tokens": 14441785.0,
"step": 7380
},
{
"entropy": 6.390121078491211,
"epoch": 0.7382416154345979,
"grad_norm": 1.390625,
"learning_rate": 0.0004954014644861435,
"loss": 6.2016,
"mean_token_accuracy": 0.14674563556909562,
"num_tokens": 14451320.0,
"step": 7385
},
{
"entropy": 6.33625340461731,
"epoch": 0.7387414404958265,
"grad_norm": 1.28125,
"learning_rate": 0.0004953942831311367,
"loss": 6.3319,
"mean_token_accuracy": 0.1442642666399479,
"num_tokens": 14460777.0,
"step": 7390
},
{
"entropy": 6.3263829231262205,
"epoch": 0.739241265557055,
"grad_norm": 1.1640625,
"learning_rate": 0.0004953870962310666,
"loss": 6.2129,
"mean_token_accuracy": 0.14810526967048646,
"num_tokens": 14469729.0,
"step": 7395
},
{
"entropy": 6.303956747055054,
"epoch": 0.7397410906182836,
"grad_norm": 1.390625,
"learning_rate": 0.0004953799037861138,
"loss": 6.1468,
"mean_token_accuracy": 0.15309115573763848,
"num_tokens": 14480559.0,
"step": 7400
},
{
"entropy": 6.348096942901611,
"epoch": 0.7402409156795122,
"grad_norm": 1.3359375,
"learning_rate": 0.0004953727057964594,
"loss": 6.1687,
"mean_token_accuracy": 0.1470792919397354,
"num_tokens": 14489631.0,
"step": 7405
},
{
"entropy": 6.414287137985229,
"epoch": 0.7407407407407407,
"grad_norm": 1.4296875,
"learning_rate": 0.0004953655022622843,
"loss": 6.3846,
"mean_token_accuracy": 0.13241870626807212,
"num_tokens": 14498994.0,
"step": 7410
},
{
"entropy": 6.377609348297119,
"epoch": 0.7412405658019693,
"grad_norm": 1.2265625,
"learning_rate": 0.0004953582931837699,
"loss": 6.2013,
"mean_token_accuracy": 0.14467180967330934,
"num_tokens": 14508456.0,
"step": 7415
},
{
"entropy": 6.278591775894165,
"epoch": 0.7417403908631979,
"grad_norm": 1.1640625,
"learning_rate": 0.0004953510785610976,
"loss": 6.1901,
"mean_token_accuracy": 0.1473128877580166,
"num_tokens": 14517388.0,
"step": 7420
},
{
"entropy": 6.390936088562012,
"epoch": 0.7422402159244265,
"grad_norm": 1.25,
"learning_rate": 0.0004953438583944487,
"loss": 6.2798,
"mean_token_accuracy": 0.14066454768180847,
"num_tokens": 14526889.0,
"step": 7425
},
{
"entropy": 6.32545428276062,
"epoch": 0.742740040985655,
"grad_norm": 1.3046875,
"learning_rate": 0.0004953366326840052,
"loss": 6.2261,
"mean_token_accuracy": 0.1506802536547184,
"num_tokens": 14537115.0,
"step": 7430
},
{
"entropy": 6.290111494064331,
"epoch": 0.7432398660468836,
"grad_norm": 1.296875,
"learning_rate": 0.0004953294014299486,
"loss": 6.1758,
"mean_token_accuracy": 0.1470622569322586,
"num_tokens": 14547354.0,
"step": 7435
},
{
"entropy": 6.395859909057617,
"epoch": 0.7437396911081121,
"grad_norm": 1.3828125,
"learning_rate": 0.0004953221646324611,
"loss": 6.3802,
"mean_token_accuracy": 0.1334720805287361,
"num_tokens": 14557689.0,
"step": 7440
},
{
"entropy": 6.3484086990356445,
"epoch": 0.7442395161693407,
"grad_norm": 1.2421875,
"learning_rate": 0.0004953149222917245,
"loss": 6.2089,
"mean_token_accuracy": 0.14387989565730094,
"num_tokens": 14567687.0,
"step": 7445
},
{
"entropy": 6.309614610671997,
"epoch": 0.7447393412305693,
"grad_norm": 1.25,
"learning_rate": 0.0004953076744079213,
"loss": 6.2618,
"mean_token_accuracy": 0.14552861154079438,
"num_tokens": 14577800.0,
"step": 7450
},
{
"entropy": 6.416631507873535,
"epoch": 0.7452391662917979,
"grad_norm": 1.28125,
"learning_rate": 0.0004953004209812335,
"loss": 6.1934,
"mean_token_accuracy": 0.14524638801813125,
"num_tokens": 14587467.0,
"step": 7455
},
{
"entropy": 6.330381250381469,
"epoch": 0.7457389913530265,
"grad_norm": 1.28125,
"learning_rate": 0.0004952931620118439,
"loss": 6.1681,
"mean_token_accuracy": 0.15144518688321112,
"num_tokens": 14597710.0,
"step": 7460
},
{
"entropy": 6.295101499557495,
"epoch": 0.746238816414255,
"grad_norm": 1.375,
"learning_rate": 0.0004952858974999351,
"loss": 6.1211,
"mean_token_accuracy": 0.14862216413021087,
"num_tokens": 14607212.0,
"step": 7465
},
{
"entropy": 6.357637023925781,
"epoch": 0.7467386414754836,
"grad_norm": 1.296875,
"learning_rate": 0.0004952786274456896,
"loss": 6.1922,
"mean_token_accuracy": 0.1411703571677208,
"num_tokens": 14616237.0,
"step": 7470
},
{
"entropy": 6.238756418228149,
"epoch": 0.7472384665367121,
"grad_norm": 1.265625,
"learning_rate": 0.0004952713518492907,
"loss": 6.1136,
"mean_token_accuracy": 0.14785224124789237,
"num_tokens": 14625645.0,
"step": 7475
},
{
"entropy": 6.261566305160523,
"epoch": 0.7477382915979407,
"grad_norm": 1.1171875,
"learning_rate": 0.0004952640707109213,
"loss": 6.0904,
"mean_token_accuracy": 0.15164580941200256,
"num_tokens": 14634897.0,
"step": 7480
},
{
"entropy": 6.231878280639648,
"epoch": 0.7482381166591693,
"grad_norm": 1.2734375,
"learning_rate": 0.0004952567840307644,
"loss": 6.2032,
"mean_token_accuracy": 0.14593568965792655,
"num_tokens": 14645310.0,
"step": 7485
},
{
"entropy": 6.349256467819214,
"epoch": 0.7487379417203979,
"grad_norm": 1.2421875,
"learning_rate": 0.0004952494918090036,
"loss": 6.3066,
"mean_token_accuracy": 0.13680757507681846,
"num_tokens": 14654983.0,
"step": 7490
},
{
"entropy": 6.37339506149292,
"epoch": 0.7492377667816265,
"grad_norm": 1.25,
"learning_rate": 0.0004952421940458222,
"loss": 6.2013,
"mean_token_accuracy": 0.14576212391257287,
"num_tokens": 14664384.0,
"step": 7495
},
{
"entropy": 6.368697166442871,
"epoch": 0.749737591842855,
"grad_norm": 1.3125,
"learning_rate": 0.0004952348907414039,
"loss": 6.2379,
"mean_token_accuracy": 0.13812749087810516,
"num_tokens": 14674375.0,
"step": 7500
},
{
"entropy": 6.311900806427002,
"epoch": 0.7502374169040835,
"grad_norm": 1.265625,
"learning_rate": 0.0004952275818959325,
"loss": 6.1687,
"mean_token_accuracy": 0.15201991945505142,
"num_tokens": 14683212.0,
"step": 7505
},
{
"entropy": 6.248887443542481,
"epoch": 0.7507372419653121,
"grad_norm": 1.1875,
"learning_rate": 0.0004952202675095916,
"loss": 6.1631,
"mean_token_accuracy": 0.14759597778320313,
"num_tokens": 14693267.0,
"step": 7510
},
{
"entropy": 6.29571270942688,
"epoch": 0.7512370670265407,
"grad_norm": 1.28125,
"learning_rate": 0.0004952129475825657,
"loss": 6.1575,
"mean_token_accuracy": 0.14932916387915612,
"num_tokens": 14702835.0,
"step": 7515
},
{
"entropy": 6.290961742401123,
"epoch": 0.7517368920877693,
"grad_norm": 1.2734375,
"learning_rate": 0.0004952056221150385,
"loss": 6.1967,
"mean_token_accuracy": 0.14851897954940796,
"num_tokens": 14713243.0,
"step": 7520
},
{
"entropy": 6.385180330276489,
"epoch": 0.7522367171489979,
"grad_norm": 1.171875,
"learning_rate": 0.0004951982911071945,
"loss": 6.2558,
"mean_token_accuracy": 0.1477909989655018,
"num_tokens": 14724943.0,
"step": 7525
},
{
"entropy": 6.343636846542358,
"epoch": 0.7527365422102265,
"grad_norm": 1.28125,
"learning_rate": 0.0004951909545592183,
"loss": 6.162,
"mean_token_accuracy": 0.14616925567388533,
"num_tokens": 14734812.0,
"step": 7530
},
{
"entropy": 6.261893796920776,
"epoch": 0.753236367271455,
"grad_norm": 1.515625,
"learning_rate": 0.0004951836124712942,
"loss": 6.2621,
"mean_token_accuracy": 0.14915494248270988,
"num_tokens": 14745465.0,
"step": 7535
},
{
"entropy": 6.3355108261108395,
"epoch": 0.7537361923326835,
"grad_norm": 1.3515625,
"learning_rate": 0.0004951762648436073,
"loss": 6.2271,
"mean_token_accuracy": 0.1380041189491749,
"num_tokens": 14755088.0,
"step": 7540
},
{
"entropy": 6.450184440612793,
"epoch": 0.7542360173939121,
"grad_norm": 1.359375,
"learning_rate": 0.0004951689116763419,
"loss": 6.2808,
"mean_token_accuracy": 0.14245418682694436,
"num_tokens": 14764866.0,
"step": 7545
},
{
"entropy": 6.356716775894165,
"epoch": 0.7547358424551407,
"grad_norm": 1.1875,
"learning_rate": 0.0004951615529696835,
"loss": 6.189,
"mean_token_accuracy": 0.14138278663158416,
"num_tokens": 14775528.0,
"step": 7550
},
{
"entropy": 6.25912070274353,
"epoch": 0.7552356675163693,
"grad_norm": 1.265625,
"learning_rate": 0.0004951541887238172,
"loss": 6.1638,
"mean_token_accuracy": 0.14905866235494614,
"num_tokens": 14785698.0,
"step": 7555
},
{
"entropy": 6.253559494018555,
"epoch": 0.7557354925775979,
"grad_norm": 1.2734375,
"learning_rate": 0.0004951468189389281,
"loss": 6.1715,
"mean_token_accuracy": 0.14896537810564042,
"num_tokens": 14794765.0,
"step": 7560
},
{
"entropy": 6.468278932571411,
"epoch": 0.7562353176388265,
"grad_norm": 1.21875,
"learning_rate": 0.0004951394436152016,
"loss": 6.3354,
"mean_token_accuracy": 0.1366427555680275,
"num_tokens": 14804185.0,
"step": 7565
},
{
"entropy": 6.339979600906372,
"epoch": 0.7567351427000549,
"grad_norm": 1.171875,
"learning_rate": 0.0004951320627528234,
"loss": 6.1077,
"mean_token_accuracy": 0.1485820382833481,
"num_tokens": 14814270.0,
"step": 7570
},
{
"entropy": 6.174428033828735,
"epoch": 0.7572349677612835,
"grad_norm": 1.6328125,
"learning_rate": 0.0004951246763519791,
"loss": 6.1613,
"mean_token_accuracy": 0.15507109686732293,
"num_tokens": 14824879.0,
"step": 7575
},
{
"entropy": 6.349507474899292,
"epoch": 0.7577347928225121,
"grad_norm": 1.2109375,
"learning_rate": 0.0004951172844128546,
"loss": 6.2203,
"mean_token_accuracy": 0.14171002209186553,
"num_tokens": 14834882.0,
"step": 7580
},
{
"entropy": 6.302507305145264,
"epoch": 0.7582346178837407,
"grad_norm": 1.203125,
"learning_rate": 0.0004951098869356358,
"loss": 6.1612,
"mean_token_accuracy": 0.14080809876322747,
"num_tokens": 14845518.0,
"step": 7585
},
{
"entropy": 6.331415033340454,
"epoch": 0.7587344429449693,
"grad_norm": 1.1015625,
"learning_rate": 0.000495102483920509,
"loss": 6.2704,
"mean_token_accuracy": 0.13857753649353982,
"num_tokens": 14856046.0,
"step": 7590
},
{
"entropy": 6.437483024597168,
"epoch": 0.7592342680061979,
"grad_norm": 1.21875,
"learning_rate": 0.0004950950753676603,
"loss": 6.3698,
"mean_token_accuracy": 0.13390636444091797,
"num_tokens": 14865214.0,
"step": 7595
},
{
"entropy": 6.334856748580933,
"epoch": 0.7597340930674265,
"grad_norm": 1.1484375,
"learning_rate": 0.0004950876612772763,
"loss": 6.1715,
"mean_token_accuracy": 0.14836979806423187,
"num_tokens": 14875708.0,
"step": 7600
},
{
"entropy": 6.258086204528809,
"epoch": 0.7602339181286549,
"grad_norm": 1.28125,
"learning_rate": 0.0004950802416495431,
"loss": 6.2071,
"mean_token_accuracy": 0.13905663117766381,
"num_tokens": 14886041.0,
"step": 7605
},
{
"entropy": 6.249067163467407,
"epoch": 0.7607337431898835,
"grad_norm": 1.15625,
"learning_rate": 0.0004950728164846478,
"loss": 6.089,
"mean_token_accuracy": 0.14997563660144805,
"num_tokens": 14895824.0,
"step": 7610
},
{
"entropy": 6.280237627029419,
"epoch": 0.7612335682511121,
"grad_norm": 1.2578125,
"learning_rate": 0.0004950653857827771,
"loss": 6.1205,
"mean_token_accuracy": 0.14796930998563768,
"num_tokens": 14904946.0,
"step": 7615
},
{
"entropy": 6.315958070755005,
"epoch": 0.7617333933123407,
"grad_norm": 1.2265625,
"learning_rate": 0.0004950579495441177,
"loss": 6.0885,
"mean_token_accuracy": 0.14441069811582566,
"num_tokens": 14914088.0,
"step": 7620
},
{
"entropy": 6.2729331970214846,
"epoch": 0.7622332183735693,
"grad_norm": 1.2734375,
"learning_rate": 0.0004950505077688572,
"loss": 6.2955,
"mean_token_accuracy": 0.1413036197423935,
"num_tokens": 14924780.0,
"step": 7625
},
{
"entropy": 6.262010478973389,
"epoch": 0.7627330434347979,
"grad_norm": 1.1875,
"learning_rate": 0.0004950430604571824,
"loss": 6.1122,
"mean_token_accuracy": 0.14823548048734664,
"num_tokens": 14933857.0,
"step": 7630
},
{
"entropy": 6.290208959579468,
"epoch": 0.7632328684960263,
"grad_norm": 1.171875,
"learning_rate": 0.0004950356076092808,
"loss": 6.1411,
"mean_token_accuracy": 0.14823199659585953,
"num_tokens": 14944223.0,
"step": 7635
},
{
"entropy": 6.408723020553589,
"epoch": 0.7637326935572549,
"grad_norm": 1.265625,
"learning_rate": 0.00049502814922534,
"loss": 6.3959,
"mean_token_accuracy": 0.13327127322554588,
"num_tokens": 14953677.0,
"step": 7640
},
{
"entropy": 6.331975746154785,
"epoch": 0.7642325186184835,
"grad_norm": 1.15625,
"learning_rate": 0.0004950206853055475,
"loss": 6.1984,
"mean_token_accuracy": 0.14544573724269866,
"num_tokens": 14963883.0,
"step": 7645
},
{
"entropy": 6.28794298171997,
"epoch": 0.7647323436797121,
"grad_norm": 1.21875,
"learning_rate": 0.0004950132158500913,
"loss": 6.1373,
"mean_token_accuracy": 0.14800980389118196,
"num_tokens": 14973680.0,
"step": 7650
},
{
"entropy": 6.302719020843506,
"epoch": 0.7652321687409407,
"grad_norm": 1.3359375,
"learning_rate": 0.0004950057408591591,
"loss": 6.1147,
"mean_token_accuracy": 0.15342116802930833,
"num_tokens": 14982492.0,
"step": 7655
},
{
"entropy": 6.254760456085205,
"epoch": 0.7657319938021693,
"grad_norm": 1.1953125,
"learning_rate": 0.0004949982603329391,
"loss": 6.0667,
"mean_token_accuracy": 0.15364200472831727,
"num_tokens": 14991555.0,
"step": 7660
},
{
"entropy": 6.404291868209839,
"epoch": 0.7662318188633979,
"grad_norm": 1.3515625,
"learning_rate": 0.0004949907742716195,
"loss": 6.2873,
"mean_token_accuracy": 0.13565628826618195,
"num_tokens": 15000678.0,
"step": 7665
},
{
"entropy": 6.234206485748291,
"epoch": 0.7667316439246263,
"grad_norm": 1.2734375,
"learning_rate": 0.0004949832826753886,
"loss": 6.1604,
"mean_token_accuracy": 0.14629355669021607,
"num_tokens": 15010418.0,
"step": 7670
},
{
"entropy": 6.300794219970703,
"epoch": 0.7672314689858549,
"grad_norm": 1.1328125,
"learning_rate": 0.000494975785544435,
"loss": 6.2963,
"mean_token_accuracy": 0.13721828237175943,
"num_tokens": 15020829.0,
"step": 7675
},
{
"entropy": 6.392731952667236,
"epoch": 0.7677312940470835,
"grad_norm": 1.203125,
"learning_rate": 0.0004949682828789472,
"loss": 6.1841,
"mean_token_accuracy": 0.13928207382559776,
"num_tokens": 15030055.0,
"step": 7680
},
{
"entropy": 6.297975635528564,
"epoch": 0.7682311191083121,
"grad_norm": 1.3515625,
"learning_rate": 0.000494960774679114,
"loss": 6.1291,
"mean_token_accuracy": 0.14844092950224877,
"num_tokens": 15039620.0,
"step": 7685
},
{
"entropy": 6.240979719161987,
"epoch": 0.7687309441695407,
"grad_norm": 1.375,
"learning_rate": 0.0004949532609451242,
"loss": 6.2057,
"mean_token_accuracy": 0.14623843207955362,
"num_tokens": 15049299.0,
"step": 7690
},
{
"entropy": 6.267113161087036,
"epoch": 0.7692307692307693,
"grad_norm": 1.3671875,
"learning_rate": 0.0004949457416771671,
"loss": 6.1522,
"mean_token_accuracy": 0.14873508661985396,
"num_tokens": 15059554.0,
"step": 7695
},
{
"entropy": 6.189442825317383,
"epoch": 0.7697305942919977,
"grad_norm": 2.234375,
"learning_rate": 0.0004949382168754316,
"loss": 6.0736,
"mean_token_accuracy": 0.14874422699213027,
"num_tokens": 15069651.0,
"step": 7700
},
{
"entropy": 6.325786161422729,
"epoch": 0.7702304193532263,
"grad_norm": 1.3984375,
"learning_rate": 0.0004949306865401073,
"loss": 6.201,
"mean_token_accuracy": 0.14223990142345427,
"num_tokens": 15080000.0,
"step": 7705
},
{
"entropy": 6.334896802902222,
"epoch": 0.7707302444144549,
"grad_norm": 1.2890625,
"learning_rate": 0.0004949231506713833,
"loss": 6.1585,
"mean_token_accuracy": 0.14810031652450562,
"num_tokens": 15089237.0,
"step": 7710
},
{
"entropy": 6.212333106994629,
"epoch": 0.7712300694756835,
"grad_norm": 1.4609375,
"learning_rate": 0.0004949156092694496,
"loss": 6.0421,
"mean_token_accuracy": 0.15409350246191025,
"num_tokens": 15097829.0,
"step": 7715
},
{
"entropy": 6.285293436050415,
"epoch": 0.7717298945369121,
"grad_norm": 1.3046875,
"learning_rate": 0.0004949080623344958,
"loss": 6.1972,
"mean_token_accuracy": 0.14618782103061675,
"num_tokens": 15106697.0,
"step": 7720
},
{
"entropy": 6.244736862182617,
"epoch": 0.7722297195981407,
"grad_norm": 1.2109375,
"learning_rate": 0.0004949005098667117,
"loss": 6.0343,
"mean_token_accuracy": 0.15691149085760117,
"num_tokens": 15115003.0,
"step": 7725
},
{
"entropy": 6.2918518543243405,
"epoch": 0.7727295446593693,
"grad_norm": 1.328125,
"learning_rate": 0.0004948929518662873,
"loss": 6.2722,
"mean_token_accuracy": 0.1464829236268997,
"num_tokens": 15125281.0,
"step": 7730
},
{
"entropy": 6.303362321853638,
"epoch": 0.7732293697205977,
"grad_norm": 1.328125,
"learning_rate": 0.0004948853883334129,
"loss": 6.1208,
"mean_token_accuracy": 0.1569477140903473,
"num_tokens": 15134609.0,
"step": 7735
},
{
"entropy": 6.3459583759307865,
"epoch": 0.7737291947818263,
"grad_norm": 1.3046875,
"learning_rate": 0.0004948778192682787,
"loss": 6.2618,
"mean_token_accuracy": 0.13910077661275863,
"num_tokens": 15143922.0,
"step": 7740
},
{
"entropy": 6.350108957290649,
"epoch": 0.7742290198430549,
"grad_norm": 1.328125,
"learning_rate": 0.000494870244671075,
"loss": 6.1995,
"mean_token_accuracy": 0.14947025924921037,
"num_tokens": 15153490.0,
"step": 7745
},
{
"entropy": 6.323730897903443,
"epoch": 0.7747288449042835,
"grad_norm": 1.2578125,
"learning_rate": 0.0004948626645419926,
"loss": 6.195,
"mean_token_accuracy": 0.14370884448289872,
"num_tokens": 15162422.0,
"step": 7750
},
{
"entropy": 6.229171800613403,
"epoch": 0.7752286699655121,
"grad_norm": 1.4375,
"learning_rate": 0.0004948550788812222,
"loss": 6.1359,
"mean_token_accuracy": 0.14826637655496597,
"num_tokens": 15171016.0,
"step": 7755
},
{
"entropy": 6.280304574966431,
"epoch": 0.7757284950267407,
"grad_norm": 1.375,
"learning_rate": 0.0004948474876889545,
"loss": 6.1154,
"mean_token_accuracy": 0.15118646621704102,
"num_tokens": 15179880.0,
"step": 7760
},
{
"entropy": 6.314484405517578,
"epoch": 0.7762283200879692,
"grad_norm": 1.265625,
"learning_rate": 0.0004948398909653806,
"loss": 6.2287,
"mean_token_accuracy": 0.14712076783180236,
"num_tokens": 15190412.0,
"step": 7765
},
{
"entropy": 6.374810361862183,
"epoch": 0.7767281451491977,
"grad_norm": 1.234375,
"learning_rate": 0.0004948322887106917,
"loss": 6.3399,
"mean_token_accuracy": 0.1330977775156498,
"num_tokens": 15201311.0,
"step": 7770
},
{
"entropy": 6.433690595626831,
"epoch": 0.7772279702104263,
"grad_norm": 1.234375,
"learning_rate": 0.0004948246809250788,
"loss": 6.2174,
"mean_token_accuracy": 0.14403920024633407,
"num_tokens": 15210058.0,
"step": 7775
},
{
"entropy": 6.407169008255005,
"epoch": 0.7777277952716549,
"grad_norm": 1.2421875,
"learning_rate": 0.0004948170676087338,
"loss": 6.2546,
"mean_token_accuracy": 0.13774337321519853,
"num_tokens": 15220023.0,
"step": 7780
},
{
"entropy": 6.252200317382813,
"epoch": 0.7782276203328835,
"grad_norm": 1.328125,
"learning_rate": 0.0004948094487618476,
"loss": 6.1277,
"mean_token_accuracy": 0.15259376019239426,
"num_tokens": 15229757.0,
"step": 7785
},
{
"entropy": 6.3349220752716064,
"epoch": 0.7787274453941121,
"grad_norm": 1.1640625,
"learning_rate": 0.0004948018243846126,
"loss": 6.2034,
"mean_token_accuracy": 0.14446027725934982,
"num_tokens": 15238928.0,
"step": 7790
},
{
"entropy": 6.24542465209961,
"epoch": 0.7792272704553407,
"grad_norm": 1.1640625,
"learning_rate": 0.0004947941944772199,
"loss": 6.1897,
"mean_token_accuracy": 0.1440369591116905,
"num_tokens": 15248864.0,
"step": 7795
},
{
"entropy": 6.351641511917114,
"epoch": 0.7797270955165692,
"grad_norm": 1.1953125,
"learning_rate": 0.000494786559039862,
"loss": 6.2759,
"mean_token_accuracy": 0.14626755490899085,
"num_tokens": 15259135.0,
"step": 7800
},
{
"entropy": 6.331418418884278,
"epoch": 0.7802269205777977,
"grad_norm": 1.2578125,
"learning_rate": 0.0004947789180727308,
"loss": 6.0978,
"mean_token_accuracy": 0.1545046254992485,
"num_tokens": 15268410.0,
"step": 7805
},
{
"entropy": 6.27475380897522,
"epoch": 0.7807267456390263,
"grad_norm": 1.1953125,
"learning_rate": 0.0004947712715760186,
"loss": 6.1379,
"mean_token_accuracy": 0.14849400520324707,
"num_tokens": 15277863.0,
"step": 7810
},
{
"entropy": 6.279900646209716,
"epoch": 0.7812265707002549,
"grad_norm": 1.4296875,
"learning_rate": 0.0004947636195499177,
"loss": 6.1926,
"mean_token_accuracy": 0.14714178889989854,
"num_tokens": 15286638.0,
"step": 7815
},
{
"entropy": 6.27982382774353,
"epoch": 0.7817263957614835,
"grad_norm": 1.546875,
"learning_rate": 0.0004947559619946207,
"loss": 6.1257,
"mean_token_accuracy": 0.14487288370728493,
"num_tokens": 15296395.0,
"step": 7820
},
{
"entropy": 6.279161071777343,
"epoch": 0.7822262208227121,
"grad_norm": 1.140625,
"learning_rate": 0.0004947482989103203,
"loss": 6.2005,
"mean_token_accuracy": 0.15035826414823533,
"num_tokens": 15305940.0,
"step": 7825
},
{
"entropy": 6.27035756111145,
"epoch": 0.7827260458839406,
"grad_norm": 1.171875,
"learning_rate": 0.0004947406302972092,
"loss": 6.2127,
"mean_token_accuracy": 0.1441306971013546,
"num_tokens": 15315803.0,
"step": 7830
},
{
"entropy": 6.343496179580688,
"epoch": 0.7832258709451692,
"grad_norm": 1.2265625,
"learning_rate": 0.0004947329561554804,
"loss": 6.2409,
"mean_token_accuracy": 0.14269353970885276,
"num_tokens": 15325742.0,
"step": 7835
},
{
"entropy": 6.29396653175354,
"epoch": 0.7837256960063977,
"grad_norm": 1.1171875,
"learning_rate": 0.0004947252764853269,
"loss": 6.1228,
"mean_token_accuracy": 0.1486676186323166,
"num_tokens": 15336366.0,
"step": 7840
},
{
"entropy": 6.298370313644409,
"epoch": 0.7842255210676263,
"grad_norm": 1.3125,
"learning_rate": 0.0004947175912869421,
"loss": 6.1952,
"mean_token_accuracy": 0.14569169357419015,
"num_tokens": 15347044.0,
"step": 7845
},
{
"entropy": 6.263945770263672,
"epoch": 0.7847253461288549,
"grad_norm": 1.1484375,
"learning_rate": 0.0004947099005605191,
"loss": 6.0748,
"mean_token_accuracy": 0.14707342982292176,
"num_tokens": 15356397.0,
"step": 7850
},
{
"entropy": 6.227381467819214,
"epoch": 0.7852251711900835,
"grad_norm": 1.0234375,
"learning_rate": 0.0004947022043062517,
"loss": 6.1692,
"mean_token_accuracy": 0.1494780331850052,
"num_tokens": 15366105.0,
"step": 7855
},
{
"entropy": 6.302454137802124,
"epoch": 0.7857249962513121,
"grad_norm": 1.3828125,
"learning_rate": 0.0004946945025243333,
"loss": 6.2518,
"mean_token_accuracy": 0.14066690802574158,
"num_tokens": 15375377.0,
"step": 7860
},
{
"entropy": 6.33960919380188,
"epoch": 0.7862248213125406,
"grad_norm": 1.109375,
"learning_rate": 0.0004946867952149577,
"loss": 6.2359,
"mean_token_accuracy": 0.14246560111641884,
"num_tokens": 15385718.0,
"step": 7865
},
{
"entropy": 6.358570384979248,
"epoch": 0.7867246463737692,
"grad_norm": 1.21875,
"learning_rate": 0.0004946790823783189,
"loss": 6.244,
"mean_token_accuracy": 0.13942286223173142,
"num_tokens": 15395032.0,
"step": 7870
},
{
"entropy": 6.308583784103393,
"epoch": 0.7872244714349977,
"grad_norm": 1.265625,
"learning_rate": 0.000494671364014611,
"loss": 6.2348,
"mean_token_accuracy": 0.1442372642457485,
"num_tokens": 15405023.0,
"step": 7875
},
{
"entropy": 6.24981164932251,
"epoch": 0.7877242964962263,
"grad_norm": 1.1328125,
"learning_rate": 0.000494663640124028,
"loss": 6.115,
"mean_token_accuracy": 0.15042841732501983,
"num_tokens": 15414174.0,
"step": 7880
},
{
"entropy": 6.247652196884156,
"epoch": 0.7882241215574549,
"grad_norm": 1.09375,
"learning_rate": 0.0004946559107067643,
"loss": 6.1461,
"mean_token_accuracy": 0.14153414517641066,
"num_tokens": 15423622.0,
"step": 7885
},
{
"entropy": 6.322947835922241,
"epoch": 0.7887239466186835,
"grad_norm": 1.3359375,
"learning_rate": 0.0004946481757630146,
"loss": 6.1988,
"mean_token_accuracy": 0.145340296626091,
"num_tokens": 15433873.0,
"step": 7890
},
{
"entropy": 6.275658893585205,
"epoch": 0.789223771679912,
"grad_norm": 1.2890625,
"learning_rate": 0.0004946404352929732,
"loss": 6.0666,
"mean_token_accuracy": 0.15388471707701684,
"num_tokens": 15443600.0,
"step": 7895
},
{
"entropy": 6.2278729438781735,
"epoch": 0.7897235967411406,
"grad_norm": 1.3046875,
"learning_rate": 0.000494632689296835,
"loss": 6.19,
"mean_token_accuracy": 0.14828322902321817,
"num_tokens": 15454531.0,
"step": 7900
},
{
"entropy": 6.2535449981689455,
"epoch": 0.7902234218023692,
"grad_norm": 1.3359375,
"learning_rate": 0.0004946249377747947,
"loss": 6.0927,
"mean_token_accuracy": 0.16011133044958115,
"num_tokens": 15464313.0,
"step": 7905
},
{
"entropy": 6.257008361816406,
"epoch": 0.7907232468635977,
"grad_norm": 1.1328125,
"learning_rate": 0.0004946171807270476,
"loss": 6.1771,
"mean_token_accuracy": 0.14582148790359498,
"num_tokens": 15473363.0,
"step": 7910
},
{
"entropy": 6.287841749191284,
"epoch": 0.7912230719248263,
"grad_norm": 1.234375,
"learning_rate": 0.0004946094181537887,
"loss": 6.2153,
"mean_token_accuracy": 0.14719806015491485,
"num_tokens": 15483296.0,
"step": 7915
},
{
"entropy": 6.246859884262085,
"epoch": 0.7917228969860549,
"grad_norm": 1.046875,
"learning_rate": 0.0004946016500552134,
"loss": 6.2386,
"mean_token_accuracy": 0.14390528574585915,
"num_tokens": 15493579.0,
"step": 7920
},
{
"entropy": 6.356759929656983,
"epoch": 0.7922227220472835,
"grad_norm": 1.1875,
"learning_rate": 0.0004945938764315171,
"loss": 6.1395,
"mean_token_accuracy": 0.14601777642965316,
"num_tokens": 15502105.0,
"step": 7925
},
{
"entropy": 6.340047168731689,
"epoch": 0.792722547108512,
"grad_norm": 1.2265625,
"learning_rate": 0.0004945860972828954,
"loss": 6.1239,
"mean_token_accuracy": 0.1426735945045948,
"num_tokens": 15511888.0,
"step": 7930
},
{
"entropy": 6.251442003250122,
"epoch": 0.7932223721697406,
"grad_norm": 1.125,
"learning_rate": 0.0004945783126095439,
"loss": 6.1639,
"mean_token_accuracy": 0.1460930399596691,
"num_tokens": 15522469.0,
"step": 7935
},
{
"entropy": 6.211803579330445,
"epoch": 0.7937221972309692,
"grad_norm": 1.078125,
"learning_rate": 0.0004945705224116586,
"loss": 6.2522,
"mean_token_accuracy": 0.1411016419529915,
"num_tokens": 15533332.0,
"step": 7940
},
{
"entropy": 6.373286342620849,
"epoch": 0.7942220222921977,
"grad_norm": 1.09375,
"learning_rate": 0.0004945627266894354,
"loss": 6.1511,
"mean_token_accuracy": 0.1492772251367569,
"num_tokens": 15542861.0,
"step": 7945
},
{
"entropy": 6.275880813598633,
"epoch": 0.7947218473534263,
"grad_norm": 1.3046875,
"learning_rate": 0.0004945549254430707,
"loss": 6.1326,
"mean_token_accuracy": 0.1411457486450672,
"num_tokens": 15552503.0,
"step": 7950
},
{
"entropy": 6.191089248657226,
"epoch": 0.7952216724146549,
"grad_norm": 1.1171875,
"learning_rate": 0.0004945471186727603,
"loss": 6.1315,
"mean_token_accuracy": 0.15307629704475403,
"num_tokens": 15562397.0,
"step": 7955
},
{
"entropy": 6.374970006942749,
"epoch": 0.7957214974758834,
"grad_norm": 1.1875,
"learning_rate": 0.0004945393063787011,
"loss": 6.1719,
"mean_token_accuracy": 0.13816557079553604,
"num_tokens": 15570956.0,
"step": 7960
},
{
"entropy": 6.2921782493591305,
"epoch": 0.796221322537112,
"grad_norm": 1.2265625,
"learning_rate": 0.0004945314885610894,
"loss": 6.0866,
"mean_token_accuracy": 0.15081177949905394,
"num_tokens": 15579938.0,
"step": 7965
},
{
"entropy": 6.2503406524658205,
"epoch": 0.7967211475983406,
"grad_norm": 1.328125,
"learning_rate": 0.0004945236652201219,
"loss": 6.1551,
"mean_token_accuracy": 0.1501242384314537,
"num_tokens": 15589906.0,
"step": 7970
},
{
"entropy": 6.34084849357605,
"epoch": 0.7972209726595691,
"grad_norm": 1.546875,
"learning_rate": 0.0004945158363559955,
"loss": 6.2331,
"mean_token_accuracy": 0.14189469441771507,
"num_tokens": 15599891.0,
"step": 7975
},
{
"entropy": 6.373281097412109,
"epoch": 0.7977207977207977,
"grad_norm": 1.421875,
"learning_rate": 0.0004945080019689071,
"loss": 6.336,
"mean_token_accuracy": 0.13428587540984155,
"num_tokens": 15609669.0,
"step": 7980
},
{
"entropy": 6.389525651931763,
"epoch": 0.7982206227820263,
"grad_norm": 1.125,
"learning_rate": 0.0004945001620590538,
"loss": 6.2552,
"mean_token_accuracy": 0.14018792957067489,
"num_tokens": 15619899.0,
"step": 7985
},
{
"entropy": 6.377849531173706,
"epoch": 0.7987204478432549,
"grad_norm": 1.28125,
"learning_rate": 0.000494492316626633,
"loss": 6.2389,
"mean_token_accuracy": 0.1450905069708824,
"num_tokens": 15629822.0,
"step": 7990
},
{
"entropy": 6.282259845733643,
"epoch": 0.7992202729044834,
"grad_norm": 1.1875,
"learning_rate": 0.0004944844656718419,
"loss": 6.1636,
"mean_token_accuracy": 0.1422221541404724,
"num_tokens": 15639810.0,
"step": 7995
},
{
"entropy": 6.291674280166626,
"epoch": 0.799720097965712,
"grad_norm": 1.265625,
"learning_rate": 0.0004944766091948783,
"loss": 6.1564,
"mean_token_accuracy": 0.1462959423661232,
"num_tokens": 15649701.0,
"step": 8000
},
{
"entropy": 6.413050603866577,
"epoch": 0.8002199230269406,
"grad_norm": 1.359375,
"learning_rate": 0.0004944687471959395,
"loss": 6.2271,
"mean_token_accuracy": 0.147781403362751,
"num_tokens": 15659969.0,
"step": 8005
},
{
"entropy": 6.317382669448852,
"epoch": 0.8007197480881691,
"grad_norm": 1.203125,
"learning_rate": 0.0004944608796752237,
"loss": 6.1593,
"mean_token_accuracy": 0.14672942608594894,
"num_tokens": 15669947.0,
"step": 8010
},
{
"entropy": 6.271909618377686,
"epoch": 0.8012195731493977,
"grad_norm": 1.3203125,
"learning_rate": 0.0004944530066329284,
"loss": 6.2251,
"mean_token_accuracy": 0.14509136080741883,
"num_tokens": 15678799.0,
"step": 8015
},
{
"entropy": 6.385493469238281,
"epoch": 0.8017193982106263,
"grad_norm": 1.3828125,
"learning_rate": 0.0004944451280692521,
"loss": 6.1579,
"mean_token_accuracy": 0.1431487664580345,
"num_tokens": 15688859.0,
"step": 8020
},
{
"entropy": 6.231485366821289,
"epoch": 0.8022192232718548,
"grad_norm": 1.4296875,
"learning_rate": 0.0004944372439843927,
"loss": 6.1033,
"mean_token_accuracy": 0.14942432045936585,
"num_tokens": 15697121.0,
"step": 8025
},
{
"entropy": 6.251531600952148,
"epoch": 0.8027190483330834,
"grad_norm": 1.15625,
"learning_rate": 0.0004944293543785489,
"loss": 6.2614,
"mean_token_accuracy": 0.14371100664138795,
"num_tokens": 15707918.0,
"step": 8030
},
{
"entropy": 6.3498780727386475,
"epoch": 0.803218873394312,
"grad_norm": 1.4609375,
"learning_rate": 0.0004944214592519188,
"loss": 6.1619,
"mean_token_accuracy": 0.1502821072936058,
"num_tokens": 15717342.0,
"step": 8035
},
{
"entropy": 6.317608880996704,
"epoch": 0.8037186984555406,
"grad_norm": 1.296875,
"learning_rate": 0.0004944135586047014,
"loss": 6.1718,
"mean_token_accuracy": 0.1466163255274296,
"num_tokens": 15727767.0,
"step": 8040
},
{
"entropy": 6.276845550537109,
"epoch": 0.8042185235167691,
"grad_norm": 1.1953125,
"learning_rate": 0.0004944056524370953,
"loss": 6.1787,
"mean_token_accuracy": 0.14879640713334083,
"num_tokens": 15737049.0,
"step": 8045
},
{
"entropy": 6.244410133361816,
"epoch": 0.8047183485779977,
"grad_norm": 1.1796875,
"learning_rate": 0.0004943977407492994,
"loss": 6.1089,
"mean_token_accuracy": 0.1464175522327423,
"num_tokens": 15746640.0,
"step": 8050
},
{
"entropy": 6.334406089782715,
"epoch": 0.8052181736392263,
"grad_norm": 1.4765625,
"learning_rate": 0.0004943898235415128,
"loss": 6.1206,
"mean_token_accuracy": 0.15196825116872786,
"num_tokens": 15756151.0,
"step": 8055
},
{
"entropy": 6.2099662780761715,
"epoch": 0.8057179987004548,
"grad_norm": 1.25,
"learning_rate": 0.0004943819008139347,
"loss": 6.066,
"mean_token_accuracy": 0.15285230278968812,
"num_tokens": 15765226.0,
"step": 8060
},
{
"entropy": 6.149449968338013,
"epoch": 0.8062178237616834,
"grad_norm": 1.1953125,
"learning_rate": 0.0004943739725667644,
"loss": 6.1187,
"mean_token_accuracy": 0.1511198878288269,
"num_tokens": 15775916.0,
"step": 8065
},
{
"entropy": 6.32827205657959,
"epoch": 0.806717648822912,
"grad_norm": 1.2890625,
"learning_rate": 0.0004943660388002014,
"loss": 6.2377,
"mean_token_accuracy": 0.14484416469931602,
"num_tokens": 15785660.0,
"step": 8070
},
{
"entropy": 6.28638973236084,
"epoch": 0.8072174738841406,
"grad_norm": 1.1953125,
"learning_rate": 0.0004943580995144454,
"loss": 6.2019,
"mean_token_accuracy": 0.15317482724785805,
"num_tokens": 15794995.0,
"step": 8075
},
{
"entropy": 6.3401306629180905,
"epoch": 0.8077172989453691,
"grad_norm": 1.28125,
"learning_rate": 0.0004943501547096961,
"loss": 6.1806,
"mean_token_accuracy": 0.14184014201164247,
"num_tokens": 15804370.0,
"step": 8080
},
{
"entropy": 6.218646812438965,
"epoch": 0.8082171240065977,
"grad_norm": 1.234375,
"learning_rate": 0.0004943422043861531,
"loss": 6.1134,
"mean_token_accuracy": 0.15055215433239938,
"num_tokens": 15814759.0,
"step": 8085
},
{
"entropy": 6.297994947433471,
"epoch": 0.8087169490678262,
"grad_norm": 1.5625,
"learning_rate": 0.0004943342485440169,
"loss": 6.1938,
"mean_token_accuracy": 0.15205567330121994,
"num_tokens": 15823385.0,
"step": 8090
},
{
"entropy": 6.244811487197876,
"epoch": 0.8092167741290548,
"grad_norm": 1.265625,
"learning_rate": 0.0004943262871834874,
"loss": 6.1738,
"mean_token_accuracy": 0.1462759181857109,
"num_tokens": 15833226.0,
"step": 8095
},
{
"entropy": 6.390608835220337,
"epoch": 0.8097165991902834,
"grad_norm": 1.5390625,
"learning_rate": 0.0004943183203047649,
"loss": 6.2845,
"mean_token_accuracy": 0.14520051181316376,
"num_tokens": 15842565.0,
"step": 8100
},
{
"entropy": 6.274631977081299,
"epoch": 0.810216424251512,
"grad_norm": 1.28125,
"learning_rate": 0.0004943103479080499,
"loss": 6.1271,
"mean_token_accuracy": 0.1518069326877594,
"num_tokens": 15851816.0,
"step": 8105
},
{
"entropy": 6.209253740310669,
"epoch": 0.8107162493127406,
"grad_norm": 1.2421875,
"learning_rate": 0.000494302369993543,
"loss": 6.0968,
"mean_token_accuracy": 0.14296378046274186,
"num_tokens": 15861830.0,
"step": 8110
},
{
"entropy": 6.260493326187134,
"epoch": 0.8112160743739691,
"grad_norm": 1.1328125,
"learning_rate": 0.0004942943865614449,
"loss": 6.2279,
"mean_token_accuracy": 0.13823597356677056,
"num_tokens": 15871118.0,
"step": 8115
},
{
"entropy": 6.336203908920288,
"epoch": 0.8117158994351977,
"grad_norm": 1.15625,
"learning_rate": 0.0004942863976119565,
"loss": 6.2283,
"mean_token_accuracy": 0.13980461284518242,
"num_tokens": 15880935.0,
"step": 8120
},
{
"entropy": 6.367153692245483,
"epoch": 0.8122157244964262,
"grad_norm": 1.1484375,
"learning_rate": 0.0004942784031452788,
"loss": 6.1417,
"mean_token_accuracy": 0.14696732461452483,
"num_tokens": 15890458.0,
"step": 8125
},
{
"entropy": 6.203979349136352,
"epoch": 0.8127155495576548,
"grad_norm": 1.328125,
"learning_rate": 0.0004942704031616127,
"loss": 6.0586,
"mean_token_accuracy": 0.14927561432123185,
"num_tokens": 15899194.0,
"step": 8130
},
{
"entropy": 6.208375549316406,
"epoch": 0.8132153746188834,
"grad_norm": 1.2578125,
"learning_rate": 0.0004942623976611598,
"loss": 6.1639,
"mean_token_accuracy": 0.15308842584490776,
"num_tokens": 15909529.0,
"step": 8135
},
{
"entropy": 6.291259622573852,
"epoch": 0.813715199680112,
"grad_norm": 1.3828125,
"learning_rate": 0.0004942543866441215,
"loss": 6.2505,
"mean_token_accuracy": 0.1476470075547695,
"num_tokens": 15919370.0,
"step": 8140
},
{
"entropy": 6.343314504623413,
"epoch": 0.8142150247413406,
"grad_norm": 1.25,
"learning_rate": 0.0004942463701106992,
"loss": 6.1068,
"mean_token_accuracy": 0.15364054441452027,
"num_tokens": 15928651.0,
"step": 8145
},
{
"entropy": 6.287114906311035,
"epoch": 0.8147148498025691,
"grad_norm": 1.25,
"learning_rate": 0.0004942383480610946,
"loss": 6.1388,
"mean_token_accuracy": 0.14867808893322945,
"num_tokens": 15937738.0,
"step": 8150
},
{
"entropy": 6.345033597946167,
"epoch": 0.8152146748637976,
"grad_norm": 1.25,
"learning_rate": 0.0004942303204955096,
"loss": 6.2771,
"mean_token_accuracy": 0.13467902988195418,
"num_tokens": 15947167.0,
"step": 8155
},
{
"entropy": 6.300409889221191,
"epoch": 0.8157144999250262,
"grad_norm": 1.203125,
"learning_rate": 0.0004942222874141461,
"loss": 6.2211,
"mean_token_accuracy": 0.14762133210897446,
"num_tokens": 15956611.0,
"step": 8160
},
{
"entropy": 6.292691469192505,
"epoch": 0.8162143249862548,
"grad_norm": 1.2890625,
"learning_rate": 0.0004942142488172063,
"loss": 6.1801,
"mean_token_accuracy": 0.14196729362010957,
"num_tokens": 15967085.0,
"step": 8165
},
{
"entropy": 6.2443643569946286,
"epoch": 0.8167141500474834,
"grad_norm": 1.203125,
"learning_rate": 0.0004942062047048924,
"loss": 6.2016,
"mean_token_accuracy": 0.1424353078007698,
"num_tokens": 15978008.0,
"step": 8170
},
{
"entropy": 6.329860973358154,
"epoch": 0.817213975108712,
"grad_norm": 2.921875,
"learning_rate": 0.0004941981550774068,
"loss": 6.35,
"mean_token_accuracy": 0.13919807672500611,
"num_tokens": 15986975.0,
"step": 8175
},
{
"entropy": 6.230203342437744,
"epoch": 0.8177138001699406,
"grad_norm": 1.578125,
"learning_rate": 0.0004941900999349521,
"loss": 6.0889,
"mean_token_accuracy": 0.1468741074204445,
"num_tokens": 15997334.0,
"step": 8180
},
{
"entropy": 6.1699385166168215,
"epoch": 0.8182136252311691,
"grad_norm": 1.171875,
"learning_rate": 0.0004941820392777307,
"loss": 6.0674,
"mean_token_accuracy": 0.15493642836809157,
"num_tokens": 16007485.0,
"step": 8185
},
{
"entropy": 6.325546979904175,
"epoch": 0.8187134502923976,
"grad_norm": 1.4453125,
"learning_rate": 0.0004941739731059457,
"loss": 6.233,
"mean_token_accuracy": 0.14546746611595154,
"num_tokens": 16017874.0,
"step": 8190
},
{
"entropy": 6.322471952438354,
"epoch": 0.8192132753536262,
"grad_norm": 1.265625,
"learning_rate": 0.0004941659014198,
"loss": 6.2657,
"mean_token_accuracy": 0.14471103101968766,
"num_tokens": 16027778.0,
"step": 8195
},
{
"entropy": 6.2709838390350345,
"epoch": 0.8197131004148548,
"grad_norm": 1.203125,
"learning_rate": 0.0004941578242194965,
"loss": 6.1732,
"mean_token_accuracy": 0.15058131366968155,
"num_tokens": 16037116.0,
"step": 8200
},
{
"entropy": 6.369179821014404,
"epoch": 0.8202129254760834,
"grad_norm": 1.4296875,
"learning_rate": 0.0004941497415052387,
"loss": 6.2796,
"mean_token_accuracy": 0.14499787837266923,
"num_tokens": 16046890.0,
"step": 8205
},
{
"entropy": 6.347852897644043,
"epoch": 0.820712750537312,
"grad_norm": 1.2578125,
"learning_rate": 0.0004941416532772296,
"loss": 6.1714,
"mean_token_accuracy": 0.14729817807674409,
"num_tokens": 16057870.0,
"step": 8210
},
{
"entropy": 6.401031064987182,
"epoch": 0.8212125755985406,
"grad_norm": 1.265625,
"learning_rate": 0.000494133559535673,
"loss": 6.2138,
"mean_token_accuracy": 0.14139816612005235,
"num_tokens": 16067578.0,
"step": 8215
},
{
"entropy": 6.268149089813233,
"epoch": 0.821712400659769,
"grad_norm": 1.1796875,
"learning_rate": 0.0004941254602807724,
"loss": 6.1671,
"mean_token_accuracy": 0.14500691890716552,
"num_tokens": 16077108.0,
"step": 8220
},
{
"entropy": 6.294595336914062,
"epoch": 0.8222122257209976,
"grad_norm": 1.2421875,
"learning_rate": 0.0004941173555127315,
"loss": 6.1241,
"mean_token_accuracy": 0.14990601688623428,
"num_tokens": 16087864.0,
"step": 8225
},
{
"entropy": 6.2137383937835695,
"epoch": 0.8227120507822262,
"grad_norm": 1.3203125,
"learning_rate": 0.0004941092452317546,
"loss": 6.0478,
"mean_token_accuracy": 0.15572260990738868,
"num_tokens": 16096853.0,
"step": 8230
},
{
"entropy": 6.235782194137573,
"epoch": 0.8232118758434548,
"grad_norm": 1.3125,
"learning_rate": 0.0004941011294380452,
"loss": 6.0889,
"mean_token_accuracy": 0.1527320623397827,
"num_tokens": 16106012.0,
"step": 8235
},
{
"entropy": 6.210958337783813,
"epoch": 0.8237117009046834,
"grad_norm": 1.1796875,
"learning_rate": 0.0004940930081318079,
"loss": 6.1215,
"mean_token_accuracy": 0.1504502296447754,
"num_tokens": 16115764.0,
"step": 8240
},
{
"entropy": 6.3026824474334715,
"epoch": 0.824211525965912,
"grad_norm": 1.28125,
"learning_rate": 0.0004940848813132469,
"loss": 6.1893,
"mean_token_accuracy": 0.14391789063811303,
"num_tokens": 16127211.0,
"step": 8245
},
{
"entropy": 6.3200828552246096,
"epoch": 0.8247113510271405,
"grad_norm": 1.3203125,
"learning_rate": 0.0004940767489825666,
"loss": 6.1577,
"mean_token_accuracy": 0.14688317924737931,
"num_tokens": 16136204.0,
"step": 8250
},
{
"entropy": 6.283053302764893,
"epoch": 0.825211176088369,
"grad_norm": 1.2890625,
"learning_rate": 0.0004940686111399716,
"loss": 6.0914,
"mean_token_accuracy": 0.15165790915489197,
"num_tokens": 16145411.0,
"step": 8255
},
{
"entropy": 6.258586645126343,
"epoch": 0.8257110011495976,
"grad_norm": 1.125,
"learning_rate": 0.0004940604677856669,
"loss": 6.2159,
"mean_token_accuracy": 0.1371447592973709,
"num_tokens": 16156575.0,
"step": 8260
},
{
"entropy": 6.276592111587524,
"epoch": 0.8262108262108262,
"grad_norm": 1.1953125,
"learning_rate": 0.000494052318919857,
"loss": 6.1344,
"mean_token_accuracy": 0.14887368381023408,
"num_tokens": 16167387.0,
"step": 8265
},
{
"entropy": 6.294545316696167,
"epoch": 0.8267106512720548,
"grad_norm": 1.203125,
"learning_rate": 0.0004940441645427473,
"loss": 6.1382,
"mean_token_accuracy": 0.14058304578065872,
"num_tokens": 16177302.0,
"step": 8270
},
{
"entropy": 6.307913827896118,
"epoch": 0.8272104763332834,
"grad_norm": 1.2734375,
"learning_rate": 0.0004940360046545427,
"loss": 6.2619,
"mean_token_accuracy": 0.13909060433506965,
"num_tokens": 16186830.0,
"step": 8275
},
{
"entropy": 6.350049018859863,
"epoch": 0.827710301394512,
"grad_norm": 1.28125,
"learning_rate": 0.0004940278392554486,
"loss": 6.1848,
"mean_token_accuracy": 0.14652676433324813,
"num_tokens": 16197424.0,
"step": 8280
},
{
"entropy": 6.299580240249634,
"epoch": 0.8282101264557404,
"grad_norm": 1.3828125,
"learning_rate": 0.0004940196683456704,
"loss": 6.1634,
"mean_token_accuracy": 0.14599313586950302,
"num_tokens": 16207209.0,
"step": 8285
},
{
"entropy": 6.320684099197388,
"epoch": 0.828709951516969,
"grad_norm": 1.6171875,
"learning_rate": 0.0004940114919254137,
"loss": 6.1622,
"mean_token_accuracy": 0.14545141607522966,
"num_tokens": 16217952.0,
"step": 8290
},
{
"entropy": 6.238395404815674,
"epoch": 0.8292097765781976,
"grad_norm": 1.265625,
"learning_rate": 0.0004940033099948843,
"loss": 6.2038,
"mean_token_accuracy": 0.14643324688076972,
"num_tokens": 16227749.0,
"step": 8295
},
{
"entropy": 6.255685615539551,
"epoch": 0.8297096016394262,
"grad_norm": 1.1953125,
"learning_rate": 0.0004939951225542879,
"loss": 6.1628,
"mean_token_accuracy": 0.14679743573069573,
"num_tokens": 16236716.0,
"step": 8300
},
{
"entropy": 6.295976638793945,
"epoch": 0.8302094267006548,
"grad_norm": 1.21875,
"learning_rate": 0.0004939869296038306,
"loss": 6.1365,
"mean_token_accuracy": 0.15375211387872695,
"num_tokens": 16246471.0,
"step": 8305
},
{
"entropy": 6.325051164627075,
"epoch": 0.8307092517618834,
"grad_norm": 1.2578125,
"learning_rate": 0.0004939787311437185,
"loss": 6.2404,
"mean_token_accuracy": 0.13944485038518906,
"num_tokens": 16256694.0,
"step": 8310
},
{
"entropy": 6.252741193771362,
"epoch": 0.831209076823112,
"grad_norm": 1.2265625,
"learning_rate": 0.0004939705271741579,
"loss": 6.0911,
"mean_token_accuracy": 0.15199627876281738,
"num_tokens": 16266073.0,
"step": 8315
},
{
"entropy": 6.314142036437988,
"epoch": 0.8317089018843404,
"grad_norm": 1.2890625,
"learning_rate": 0.0004939623176953551,
"loss": 6.1238,
"mean_token_accuracy": 0.14674125984311104,
"num_tokens": 16274608.0,
"step": 8320
},
{
"entropy": 6.229287338256836,
"epoch": 0.832208726945569,
"grad_norm": 1.3515625,
"learning_rate": 0.0004939541027075168,
"loss": 6.0944,
"mean_token_accuracy": 0.14839435517787933,
"num_tokens": 16284311.0,
"step": 8325
},
{
"entropy": 6.165537977218628,
"epoch": 0.8327085520067976,
"grad_norm": 1.21875,
"learning_rate": 0.0004939458822108496,
"loss": 6.151,
"mean_token_accuracy": 0.1514931321144104,
"num_tokens": 16293829.0,
"step": 8330
},
{
"entropy": 6.2559449672698975,
"epoch": 0.8332083770680262,
"grad_norm": 1.3515625,
"learning_rate": 0.0004939376562055602,
"loss": 6.2531,
"mean_token_accuracy": 0.1485627844929695,
"num_tokens": 16303876.0,
"step": 8335
},
{
"entropy": 6.3408948421478275,
"epoch": 0.8337082021292548,
"grad_norm": 1.515625,
"learning_rate": 0.0004939294246918558,
"loss": 6.1175,
"mean_token_accuracy": 0.1488794781267643,
"num_tokens": 16313781.0,
"step": 8340
},
{
"entropy": 6.197822999954224,
"epoch": 0.8342080271904834,
"grad_norm": 1.1953125,
"learning_rate": 0.0004939211876699435,
"loss": 6.0491,
"mean_token_accuracy": 0.16324939131736754,
"num_tokens": 16325214.0,
"step": 8345
},
{
"entropy": 6.286114311218261,
"epoch": 0.8347078522517118,
"grad_norm": 1.234375,
"learning_rate": 0.0004939129451400305,
"loss": 6.0656,
"mean_token_accuracy": 0.1533803328871727,
"num_tokens": 16335635.0,
"step": 8350
},
{
"entropy": 6.336215257644653,
"epoch": 0.8352076773129404,
"grad_norm": 1.46875,
"learning_rate": 0.000493904697102324,
"loss": 6.1886,
"mean_token_accuracy": 0.14563629031181335,
"num_tokens": 16345459.0,
"step": 8355
},
{
"entropy": 6.193558835983277,
"epoch": 0.835707502374169,
"grad_norm": 1.25,
"learning_rate": 0.0004938964435570317,
"loss": 6.0571,
"mean_token_accuracy": 0.15347934812307357,
"num_tokens": 16354972.0,
"step": 8360
},
{
"entropy": 6.225519466400146,
"epoch": 0.8362073274353976,
"grad_norm": 1.21875,
"learning_rate": 0.0004938881845043612,
"loss": 6.0837,
"mean_token_accuracy": 0.15230301022529602,
"num_tokens": 16363257.0,
"step": 8365
},
{
"entropy": 6.145082473754883,
"epoch": 0.8367071524966262,
"grad_norm": 1.203125,
"learning_rate": 0.0004938799199445202,
"loss": 6.1078,
"mean_token_accuracy": 0.16600719094276428,
"num_tokens": 16374102.0,
"step": 8370
},
{
"entropy": 6.240188789367676,
"epoch": 0.8372069775578548,
"grad_norm": 1.2734375,
"learning_rate": 0.0004938716498777169,
"loss": 6.1285,
"mean_token_accuracy": 0.15080219507217407,
"num_tokens": 16383809.0,
"step": 8375
},
{
"entropy": 6.250911235809326,
"epoch": 0.8377068026190834,
"grad_norm": 1.2265625,
"learning_rate": 0.0004938633743041592,
"loss": 6.2034,
"mean_token_accuracy": 0.14554041400551795,
"num_tokens": 16393743.0,
"step": 8380
},
{
"entropy": 6.239728212356567,
"epoch": 0.8382066276803118,
"grad_norm": 1.171875,
"learning_rate": 0.0004938550932240552,
"loss": 6.0823,
"mean_token_accuracy": 0.15832468420267104,
"num_tokens": 16403225.0,
"step": 8385
},
{
"entropy": 6.365964031219482,
"epoch": 0.8387064527415404,
"grad_norm": 1.1875,
"learning_rate": 0.0004938468066376134,
"loss": 6.1324,
"mean_token_accuracy": 0.15150270536541938,
"num_tokens": 16413104.0,
"step": 8390
},
{
"entropy": 6.239263105392456,
"epoch": 0.839206277802769,
"grad_norm": 1.1953125,
"learning_rate": 0.0004938385145450423,
"loss": 6.1778,
"mean_token_accuracy": 0.14437811747193335,
"num_tokens": 16422831.0,
"step": 8395
},
{
"entropy": 6.247150516510009,
"epoch": 0.8397061028639976,
"grad_norm": 1.2734375,
"learning_rate": 0.0004938302169465505,
"loss": 6.1406,
"mean_token_accuracy": 0.1472749799489975,
"num_tokens": 16431955.0,
"step": 8400
},
{
"entropy": 6.376676082611084,
"epoch": 0.8402059279252262,
"grad_norm": 1.2109375,
"learning_rate": 0.0004938219138423467,
"loss": 6.2567,
"mean_token_accuracy": 0.13974295556545258,
"num_tokens": 16443266.0,
"step": 8405
},
{
"entropy": 6.307219123840332,
"epoch": 0.8407057529864548,
"grad_norm": 1.25,
"learning_rate": 0.0004938136052326399,
"loss": 6.1413,
"mean_token_accuracy": 0.1493738502264023,
"num_tokens": 16454264.0,
"step": 8410
},
{
"entropy": 6.160571050643921,
"epoch": 0.8412055780476833,
"grad_norm": 1.2265625,
"learning_rate": 0.0004938052911176392,
"loss": 6.0445,
"mean_token_accuracy": 0.15207744389772415,
"num_tokens": 16463613.0,
"step": 8415
},
{
"entropy": 6.239917182922364,
"epoch": 0.8417054031089118,
"grad_norm": 1.359375,
"learning_rate": 0.0004937969714975534,
"loss": 6.0886,
"mean_token_accuracy": 0.14654372185468673,
"num_tokens": 16472517.0,
"step": 8420
},
{
"entropy": 6.329404306411743,
"epoch": 0.8422052281701404,
"grad_norm": 1.21875,
"learning_rate": 0.0004937886463725923,
"loss": 6.1709,
"mean_token_accuracy": 0.14707983881235123,
"num_tokens": 16482328.0,
"step": 8425
},
{
"entropy": 6.246041631698608,
"epoch": 0.842705053231369,
"grad_norm": 1.28125,
"learning_rate": 0.0004937803157429651,
"loss": 6.1793,
"mean_token_accuracy": 0.14606166630983353,
"num_tokens": 16492152.0,
"step": 8430
},
{
"entropy": 6.281878995895386,
"epoch": 0.8432048782925976,
"grad_norm": 1.265625,
"learning_rate": 0.0004937719796088815,
"loss": 6.1332,
"mean_token_accuracy": 0.1467640444636345,
"num_tokens": 16501740.0,
"step": 8435
},
{
"entropy": 6.295157194137573,
"epoch": 0.8437047033538262,
"grad_norm": 1.1328125,
"learning_rate": 0.0004937636379705511,
"loss": 6.1495,
"mean_token_accuracy": 0.14300159215927125,
"num_tokens": 16512048.0,
"step": 8440
},
{
"entropy": 6.245462656021118,
"epoch": 0.8442045284150548,
"grad_norm": 1.9140625,
"learning_rate": 0.0004937552908281839,
"loss": 6.1474,
"mean_token_accuracy": 0.1498699739575386,
"num_tokens": 16521935.0,
"step": 8445
},
{
"entropy": 6.266146326065064,
"epoch": 0.8447043534762833,
"grad_norm": 1.3515625,
"learning_rate": 0.0004937469381819899,
"loss": 6.1776,
"mean_token_accuracy": 0.1444061204791069,
"num_tokens": 16531953.0,
"step": 8450
},
{
"entropy": 6.266036653518677,
"epoch": 0.8452041785375118,
"grad_norm": 1.1640625,
"learning_rate": 0.0004937385800321792,
"loss": 6.0846,
"mean_token_accuracy": 0.1474167063832283,
"num_tokens": 16541196.0,
"step": 8455
},
{
"entropy": 6.223774814605713,
"epoch": 0.8457040035987404,
"grad_norm": 1.265625,
"learning_rate": 0.0004937302163789621,
"loss": 5.9902,
"mean_token_accuracy": 0.15602245628833772,
"num_tokens": 16550453.0,
"step": 8460
},
{
"entropy": 6.284070110321045,
"epoch": 0.846203828659969,
"grad_norm": 1.4375,
"learning_rate": 0.0004937218472225491,
"loss": 6.1619,
"mean_token_accuracy": 0.14609891474246978,
"num_tokens": 16560125.0,
"step": 8465
},
{
"entropy": 6.225284671783447,
"epoch": 0.8467036537211976,
"grad_norm": 1.3984375,
"learning_rate": 0.0004937134725631506,
"loss": 6.1037,
"mean_token_accuracy": 0.14829656332731248,
"num_tokens": 16569097.0,
"step": 8470
},
{
"entropy": 6.32614483833313,
"epoch": 0.8472034787824262,
"grad_norm": 1.3203125,
"learning_rate": 0.0004937050924009775,
"loss": 6.2555,
"mean_token_accuracy": 0.14651484340429305,
"num_tokens": 16579032.0,
"step": 8475
},
{
"entropy": 6.333699655532837,
"epoch": 0.8477033038436548,
"grad_norm": 1.3359375,
"learning_rate": 0.0004936967067362406,
"loss": 6.1513,
"mean_token_accuracy": 0.14502770006656646,
"num_tokens": 16588868.0,
"step": 8480
},
{
"entropy": 6.25390133857727,
"epoch": 0.8482031289048833,
"grad_norm": 1.21875,
"learning_rate": 0.0004936883155691507,
"loss": 6.0918,
"mean_token_accuracy": 0.15236334428191184,
"num_tokens": 16598043.0,
"step": 8485
},
{
"entropy": 6.176337385177613,
"epoch": 0.8487029539661118,
"grad_norm": 1.234375,
"learning_rate": 0.0004936799188999192,
"loss": 6.0935,
"mean_token_accuracy": 0.1534414619207382,
"num_tokens": 16607145.0,
"step": 8490
},
{
"entropy": 6.229042625427246,
"epoch": 0.8492027790273404,
"grad_norm": 1.359375,
"learning_rate": 0.0004936715167287571,
"loss": 6.1205,
"mean_token_accuracy": 0.1504385069012642,
"num_tokens": 16616930.0,
"step": 8495
},
{
"entropy": 6.247959089279175,
"epoch": 0.849702604088569,
"grad_norm": 1.25,
"learning_rate": 0.000493663109055876,
"loss": 6.1233,
"mean_token_accuracy": 0.14941577315330506,
"num_tokens": 16628175.0,
"step": 8500
},
{
"entropy": 6.283598709106445,
"epoch": 0.8502024291497976,
"grad_norm": 1.2109375,
"learning_rate": 0.0004936546958814873,
"loss": 6.1722,
"mean_token_accuracy": 0.1443457432091236,
"num_tokens": 16638914.0,
"step": 8505
},
{
"entropy": 6.25822491645813,
"epoch": 0.8507022542110262,
"grad_norm": 1.8671875,
"learning_rate": 0.0004936462772058026,
"loss": 6.1616,
"mean_token_accuracy": 0.14130658209323882,
"num_tokens": 16648299.0,
"step": 8510
},
{
"entropy": 6.251192188262939,
"epoch": 0.8512020792722547,
"grad_norm": 1.359375,
"learning_rate": 0.0004936378530290339,
"loss": 6.1581,
"mean_token_accuracy": 0.1452266737818718,
"num_tokens": 16658088.0,
"step": 8515
},
{
"entropy": 6.284399557113647,
"epoch": 0.8517019043334833,
"grad_norm": 1.1171875,
"learning_rate": 0.0004936294233513931,
"loss": 6.2275,
"mean_token_accuracy": 0.1381968230009079,
"num_tokens": 16669324.0,
"step": 8520
},
{
"entropy": 6.276660060882568,
"epoch": 0.8522017293947118,
"grad_norm": 1.3515625,
"learning_rate": 0.0004936209881730922,
"loss": 6.1025,
"mean_token_accuracy": 0.14990838542580603,
"num_tokens": 16679118.0,
"step": 8525
},
{
"entropy": 6.315235900878906,
"epoch": 0.8527015544559404,
"grad_norm": 1.3984375,
"learning_rate": 0.0004936125474943436,
"loss": 6.1766,
"mean_token_accuracy": 0.1414633259177208,
"num_tokens": 16689245.0,
"step": 8530
},
{
"entropy": 6.2860133171081545,
"epoch": 0.853201379517169,
"grad_norm": 1.3828125,
"learning_rate": 0.0004936041013153596,
"loss": 6.1596,
"mean_token_accuracy": 0.1472108855843544,
"num_tokens": 16698364.0,
"step": 8535
},
{
"entropy": 6.240392827987671,
"epoch": 0.8537012045783976,
"grad_norm": 1.328125,
"learning_rate": 0.0004935956496363525,
"loss": 6.1159,
"mean_token_accuracy": 0.15300555378198624,
"num_tokens": 16708059.0,
"step": 8540
},
{
"entropy": 6.319275665283203,
"epoch": 0.8542010296396262,
"grad_norm": 1.296875,
"learning_rate": 0.0004935871924575352,
"loss": 6.1122,
"mean_token_accuracy": 0.1480521686375141,
"num_tokens": 16717206.0,
"step": 8545
},
{
"entropy": 6.212071132659912,
"epoch": 0.8547008547008547,
"grad_norm": 1.375,
"learning_rate": 0.0004935787297791204,
"loss": 6.0694,
"mean_token_accuracy": 0.14809702038764955,
"num_tokens": 16726889.0,
"step": 8550
},
{
"entropy": 6.264035415649414,
"epoch": 0.8552006797620832,
"grad_norm": 1.203125,
"learning_rate": 0.0004935702616013209,
"loss": 6.1998,
"mean_token_accuracy": 0.14563535302877426,
"num_tokens": 16737232.0,
"step": 8555
},
{
"entropy": 6.258747243881226,
"epoch": 0.8557005048233118,
"grad_norm": 1.625,
"learning_rate": 0.00049356178792435,
"loss": 6.0702,
"mean_token_accuracy": 0.1547325909137726,
"num_tokens": 16747213.0,
"step": 8560
},
{
"entropy": 6.283885812759399,
"epoch": 0.8562003298845404,
"grad_norm": 1.734375,
"learning_rate": 0.0004935533087484207,
"loss": 6.1025,
"mean_token_accuracy": 0.1454384870827198,
"num_tokens": 16756412.0,
"step": 8565
},
{
"entropy": 6.245044755935669,
"epoch": 0.856700154945769,
"grad_norm": 1.2578125,
"learning_rate": 0.0004935448240737464,
"loss": 6.133,
"mean_token_accuracy": 0.14659983813762664,
"num_tokens": 16766475.0,
"step": 8570
},
{
"entropy": 6.245946741104126,
"epoch": 0.8571999800069976,
"grad_norm": 1.359375,
"learning_rate": 0.0004935363339005405,
"loss": 6.1232,
"mean_token_accuracy": 0.14707613587379456,
"num_tokens": 16775903.0,
"step": 8575
},
{
"entropy": 6.349631881713867,
"epoch": 0.8576998050682261,
"grad_norm": 1.453125,
"learning_rate": 0.0004935278382290168,
"loss": 6.2153,
"mean_token_accuracy": 0.14394367411732673,
"num_tokens": 16785347.0,
"step": 8580
},
{
"entropy": 6.274719715118408,
"epoch": 0.8581996301294547,
"grad_norm": 1.25,
"learning_rate": 0.0004935193370593887,
"loss": 6.1482,
"mean_token_accuracy": 0.15185702890157698,
"num_tokens": 16794704.0,
"step": 8585
},
{
"entropy": 6.280138826370239,
"epoch": 0.8586994551906832,
"grad_norm": 1.203125,
"learning_rate": 0.0004935108303918705,
"loss": 6.0957,
"mean_token_accuracy": 0.15252209901809693,
"num_tokens": 16804711.0,
"step": 8590
},
{
"entropy": 6.243320417404175,
"epoch": 0.8591992802519118,
"grad_norm": 1.4921875,
"learning_rate": 0.0004935023182266761,
"loss": 6.1518,
"mean_token_accuracy": 0.14576567336916924,
"num_tokens": 16814217.0,
"step": 8595
},
{
"entropy": 6.274166011810303,
"epoch": 0.8596991053131404,
"grad_norm": 1.2265625,
"learning_rate": 0.0004934938005640194,
"loss": 6.1158,
"mean_token_accuracy": 0.15240332633256912,
"num_tokens": 16823652.0,
"step": 8600
},
{
"entropy": 6.298847579956055,
"epoch": 0.860198930374369,
"grad_norm": 1.625,
"learning_rate": 0.000493485277404115,
"loss": 6.1401,
"mean_token_accuracy": 0.14576715901494025,
"num_tokens": 16832293.0,
"step": 8605
},
{
"entropy": 6.276272249221802,
"epoch": 0.8606987554355976,
"grad_norm": 1.4296875,
"learning_rate": 0.0004934767487471772,
"loss": 6.1681,
"mean_token_accuracy": 0.1488754317164421,
"num_tokens": 16840877.0,
"step": 8610
},
{
"entropy": 6.2254273891448975,
"epoch": 0.8611985804968261,
"grad_norm": 1.2109375,
"learning_rate": 0.0004934682145934207,
"loss": 6.175,
"mean_token_accuracy": 0.1431325152516365,
"num_tokens": 16851245.0,
"step": 8615
},
{
"entropy": 6.28835620880127,
"epoch": 0.8616984055580547,
"grad_norm": 1.21875,
"learning_rate": 0.00049345967494306,
"loss": 6.1557,
"mean_token_accuracy": 0.14635056629776955,
"num_tokens": 16862023.0,
"step": 8620
},
{
"entropy": 6.266018295288086,
"epoch": 0.8621982306192832,
"grad_norm": 1.2890625,
"learning_rate": 0.0004934511297963102,
"loss": 6.1371,
"mean_token_accuracy": 0.15106738954782487,
"num_tokens": 16871262.0,
"step": 8625
},
{
"entropy": 6.350247859954834,
"epoch": 0.8626980556805118,
"grad_norm": 1.265625,
"learning_rate": 0.0004934425791533861,
"loss": 6.253,
"mean_token_accuracy": 0.14286625608801842,
"num_tokens": 16881513.0,
"step": 8630
},
{
"entropy": 6.161167764663697,
"epoch": 0.8631978807417404,
"grad_norm": 1.3125,
"learning_rate": 0.0004934340230145031,
"loss": 6.0221,
"mean_token_accuracy": 0.15355553328990937,
"num_tokens": 16891516.0,
"step": 8635
},
{
"entropy": 6.260900688171387,
"epoch": 0.863697705802969,
"grad_norm": 1.1953125,
"learning_rate": 0.0004934254613798761,
"loss": 6.1814,
"mean_token_accuracy": 0.1463272601366043,
"num_tokens": 16901405.0,
"step": 8640
},
{
"entropy": 6.237873315811157,
"epoch": 0.8641975308641975,
"grad_norm": 1.203125,
"learning_rate": 0.0004934168942497207,
"loss": 6.0945,
"mean_token_accuracy": 0.15495193153619766,
"num_tokens": 16911404.0,
"step": 8645
},
{
"entropy": 6.266516017913818,
"epoch": 0.8646973559254261,
"grad_norm": 1.3046875,
"learning_rate": 0.0004934083216242526,
"loss": 6.0834,
"mean_token_accuracy": 0.14429578334093093,
"num_tokens": 16920837.0,
"step": 8650
},
{
"entropy": 6.308184576034546,
"epoch": 0.8651971809866547,
"grad_norm": 1.6171875,
"learning_rate": 0.0004933997435036873,
"loss": 6.2177,
"mean_token_accuracy": 0.13706560134887696,
"num_tokens": 16930255.0,
"step": 8655
},
{
"entropy": 6.246794843673706,
"epoch": 0.8656970060478832,
"grad_norm": 1.203125,
"learning_rate": 0.0004933911598882405,
"loss": 6.1557,
"mean_token_accuracy": 0.139996225386858,
"num_tokens": 16940188.0,
"step": 8660
},
{
"entropy": 6.337051057815552,
"epoch": 0.8661968311091118,
"grad_norm": 1.21875,
"learning_rate": 0.0004933825707781284,
"loss": 6.2342,
"mean_token_accuracy": 0.14369843080639838,
"num_tokens": 16950260.0,
"step": 8665
},
{
"entropy": 6.298245859146118,
"epoch": 0.8666966561703404,
"grad_norm": 1.28125,
"learning_rate": 0.0004933739761735671,
"loss": 6.1377,
"mean_token_accuracy": 0.1453426033258438,
"num_tokens": 16959299.0,
"step": 8670
},
{
"entropy": 6.285887098312378,
"epoch": 0.867196481231569,
"grad_norm": 1.3828125,
"learning_rate": 0.0004933653760747726,
"loss": 6.3056,
"mean_token_accuracy": 0.14031370133161544,
"num_tokens": 16969541.0,
"step": 8675
},
{
"entropy": 6.270383405685425,
"epoch": 0.8676963062927975,
"grad_norm": 1.2734375,
"learning_rate": 0.0004933567704819615,
"loss": 6.1201,
"mean_token_accuracy": 0.1441718354821205,
"num_tokens": 16978754.0,
"step": 8680
},
{
"entropy": 6.34366021156311,
"epoch": 0.8681961313540261,
"grad_norm": 1.4140625,
"learning_rate": 0.0004933481593953502,
"loss": 6.2036,
"mean_token_accuracy": 0.1441444545984268,
"num_tokens": 16989188.0,
"step": 8685
},
{
"entropy": 6.252267456054687,
"epoch": 0.8686959564152547,
"grad_norm": 1.2421875,
"learning_rate": 0.0004933395428151554,
"loss": 6.1265,
"mean_token_accuracy": 0.14513652995228768,
"num_tokens": 16999295.0,
"step": 8690
},
{
"entropy": 6.338964605331421,
"epoch": 0.8691957814764832,
"grad_norm": 1.34375,
"learning_rate": 0.000493330920741594,
"loss": 6.1758,
"mean_token_accuracy": 0.1430986523628235,
"num_tokens": 17009080.0,
"step": 8695
},
{
"entropy": 6.277364492416382,
"epoch": 0.8696956065377118,
"grad_norm": 1.2578125,
"learning_rate": 0.0004933222931748827,
"loss": 6.1703,
"mean_token_accuracy": 0.1485441356897354,
"num_tokens": 17018201.0,
"step": 8700
},
{
"entropy": 6.307969236373902,
"epoch": 0.8701954315989404,
"grad_norm": 1.2109375,
"learning_rate": 0.0004933136601152387,
"loss": 6.2214,
"mean_token_accuracy": 0.14555304497480392,
"num_tokens": 17027896.0,
"step": 8705
},
{
"entropy": 6.21087236404419,
"epoch": 0.8706952566601689,
"grad_norm": 1.3046875,
"learning_rate": 0.0004933050215628793,
"loss": 6.0449,
"mean_token_accuracy": 0.1521621271967888,
"num_tokens": 17038846.0,
"step": 8710
},
{
"entropy": 6.279975843429566,
"epoch": 0.8711950817213975,
"grad_norm": 1.296875,
"learning_rate": 0.0004932963775180216,
"loss": 6.1021,
"mean_token_accuracy": 0.15255472660064698,
"num_tokens": 17048021.0,
"step": 8715
},
{
"entropy": 6.260575914382935,
"epoch": 0.8716949067826261,
"grad_norm": 1.1796875,
"learning_rate": 0.0004932877279808833,
"loss": 6.1888,
"mean_token_accuracy": 0.14471224546432496,
"num_tokens": 17058076.0,
"step": 8720
},
{
"entropy": 6.268863773345947,
"epoch": 0.8721947318438547,
"grad_norm": 1.3671875,
"learning_rate": 0.0004932790729516818,
"loss": 6.1404,
"mean_token_accuracy": 0.1452201411128044,
"num_tokens": 17068988.0,
"step": 8725
},
{
"entropy": 6.273371410369873,
"epoch": 0.8726945569050832,
"grad_norm": 1.375,
"learning_rate": 0.0004932704124306352,
"loss": 6.2403,
"mean_token_accuracy": 0.14546009749174119,
"num_tokens": 17079423.0,
"step": 8730
},
{
"entropy": 6.329331016540527,
"epoch": 0.8731943819663118,
"grad_norm": 1.2421875,
"learning_rate": 0.000493261746417961,
"loss": 6.166,
"mean_token_accuracy": 0.15287376195192337,
"num_tokens": 17089675.0,
"step": 8735
},
{
"entropy": 6.220649480819702,
"epoch": 0.8736942070275404,
"grad_norm": 1.21875,
"learning_rate": 0.0004932530749138775,
"loss": 6.0656,
"mean_token_accuracy": 0.1565648451447487,
"num_tokens": 17099234.0,
"step": 8740
},
{
"entropy": 6.265024137496948,
"epoch": 0.8741940320887689,
"grad_norm": 1.2578125,
"learning_rate": 0.0004932443979186028,
"loss": 6.1024,
"mean_token_accuracy": 0.14622531980276107,
"num_tokens": 17108966.0,
"step": 8745
},
{
"entropy": 6.226924848556519,
"epoch": 0.8746938571499975,
"grad_norm": 1.2421875,
"learning_rate": 0.0004932357154323552,
"loss": 6.1551,
"mean_token_accuracy": 0.1478735774755478,
"num_tokens": 17117941.0,
"step": 8750
},
{
"entropy": 6.210325908660889,
"epoch": 0.8751936822112261,
"grad_norm": 1.25,
"learning_rate": 0.0004932270274553531,
"loss": 6.0586,
"mean_token_accuracy": 0.15065574496984482,
"num_tokens": 17127561.0,
"step": 8755
},
{
"entropy": 6.23476209640503,
"epoch": 0.8756935072724547,
"grad_norm": 1.140625,
"learning_rate": 0.0004932183339878153,
"loss": 6.1267,
"mean_token_accuracy": 0.14655791670084,
"num_tokens": 17137645.0,
"step": 8760
},
{
"entropy": 6.286288213729859,
"epoch": 0.8761933323336832,
"grad_norm": 1.21875,
"learning_rate": 0.0004932096350299602,
"loss": 6.1751,
"mean_token_accuracy": 0.14319735318422316,
"num_tokens": 17146955.0,
"step": 8765
},
{
"entropy": 6.35867862701416,
"epoch": 0.8766931573949118,
"grad_norm": 1.34375,
"learning_rate": 0.0004932009305820069,
"loss": 6.1974,
"mean_token_accuracy": 0.13611237928271294,
"num_tokens": 17158287.0,
"step": 8770
},
{
"entropy": 6.406553649902344,
"epoch": 0.8771929824561403,
"grad_norm": 1.3671875,
"learning_rate": 0.0004931922206441743,
"loss": 6.1839,
"mean_token_accuracy": 0.13917835652828217,
"num_tokens": 17168646.0,
"step": 8775
},
{
"entropy": 6.299132919311523,
"epoch": 0.8776928075173689,
"grad_norm": 1.21875,
"learning_rate": 0.0004931835052166817,
"loss": 6.1734,
"mean_token_accuracy": 0.1393842414021492,
"num_tokens": 17178533.0,
"step": 8780
},
{
"entropy": 6.2566431045532225,
"epoch": 0.8781926325785975,
"grad_norm": 1.234375,
"learning_rate": 0.0004931747842997481,
"loss": 6.1973,
"mean_token_accuracy": 0.145637845993042,
"num_tokens": 17189584.0,
"step": 8785
},
{
"entropy": 6.196907377243042,
"epoch": 0.8786924576398261,
"grad_norm": 1.203125,
"learning_rate": 0.0004931660578935931,
"loss": 6.0891,
"mean_token_accuracy": 0.1511687532067299,
"num_tokens": 17199521.0,
"step": 8790
},
{
"entropy": 6.29045090675354,
"epoch": 0.8791922827010547,
"grad_norm": 1.3671875,
"learning_rate": 0.0004931573259984363,
"loss": 6.137,
"mean_token_accuracy": 0.15247608572244645,
"num_tokens": 17209812.0,
"step": 8795
},
{
"entropy": 6.373798274993897,
"epoch": 0.8796921077622832,
"grad_norm": 1.265625,
"learning_rate": 0.0004931485886144972,
"loss": 6.1929,
"mean_token_accuracy": 0.14428210705518724,
"num_tokens": 17220119.0,
"step": 8800
},
{
"entropy": 6.2596338272094725,
"epoch": 0.8801919328235118,
"grad_norm": 1.28125,
"learning_rate": 0.0004931398457419959,
"loss": 6.1045,
"mean_token_accuracy": 0.15475255697965623,
"num_tokens": 17229777.0,
"step": 8805
},
{
"entropy": 6.2191637516021725,
"epoch": 0.8806917578847403,
"grad_norm": 1.2734375,
"learning_rate": 0.0004931310973811521,
"loss": 6.0956,
"mean_token_accuracy": 0.15246562510728837,
"num_tokens": 17239039.0,
"step": 8810
},
{
"entropy": 6.198563814163208,
"epoch": 0.8811915829459689,
"grad_norm": 1.171875,
"learning_rate": 0.000493122343532186,
"loss": 6.0504,
"mean_token_accuracy": 0.14824269264936446,
"num_tokens": 17248202.0,
"step": 8815
},
{
"entropy": 6.252795553207397,
"epoch": 0.8816914080071975,
"grad_norm": 1.296875,
"learning_rate": 0.000493113584195318,
"loss": 6.1398,
"mean_token_accuracy": 0.15230997055768966,
"num_tokens": 17258253.0,
"step": 8820
},
{
"entropy": 6.24111795425415,
"epoch": 0.8821912330684261,
"grad_norm": 1.265625,
"learning_rate": 0.0004931048193707681,
"loss": 6.109,
"mean_token_accuracy": 0.15066774785518647,
"num_tokens": 17268381.0,
"step": 8825
},
{
"entropy": 6.338550710678101,
"epoch": 0.8826910581296546,
"grad_norm": 1.2578125,
"learning_rate": 0.0004930960490587573,
"loss": 6.1959,
"mean_token_accuracy": 0.14700786992907525,
"num_tokens": 17278220.0,
"step": 8830
},
{
"entropy": 6.355367136001587,
"epoch": 0.8831908831908832,
"grad_norm": 1.625,
"learning_rate": 0.000493087273259506,
"loss": 6.2674,
"mean_token_accuracy": 0.1471392810344696,
"num_tokens": 17288388.0,
"step": 8835
},
{
"entropy": 6.366063785552979,
"epoch": 0.8836907082521117,
"grad_norm": 1.359375,
"learning_rate": 0.0004930784919732349,
"loss": 6.2666,
"mean_token_accuracy": 0.14705021008849145,
"num_tokens": 17297308.0,
"step": 8840
},
{
"entropy": 6.149344253540039,
"epoch": 0.8841905333133403,
"grad_norm": 1.90625,
"learning_rate": 0.0004930697052001651,
"loss": 6.0487,
"mean_token_accuracy": 0.1563984841108322,
"num_tokens": 17307586.0,
"step": 8845
},
{
"entropy": 6.247825813293457,
"epoch": 0.8846903583745689,
"grad_norm": 1.3515625,
"learning_rate": 0.0004930609129405177,
"loss": 6.1605,
"mean_token_accuracy": 0.14380409121513366,
"num_tokens": 17317342.0,
"step": 8850
},
{
"entropy": 6.260551643371582,
"epoch": 0.8851901834357975,
"grad_norm": 1.578125,
"learning_rate": 0.0004930521151945138,
"loss": 6.0982,
"mean_token_accuracy": 0.15146129280328752,
"num_tokens": 17326586.0,
"step": 8855
},
{
"entropy": 6.301983737945557,
"epoch": 0.8856900084970261,
"grad_norm": 1.28125,
"learning_rate": 0.0004930433119623749,
"loss": 6.2406,
"mean_token_accuracy": 0.13693952932953835,
"num_tokens": 17337551.0,
"step": 8860
},
{
"entropy": 6.342548179626465,
"epoch": 0.8861898335582546,
"grad_norm": 1.21875,
"learning_rate": 0.0004930345032443221,
"loss": 6.1657,
"mean_token_accuracy": 0.13816626965999604,
"num_tokens": 17346702.0,
"step": 8865
},
{
"entropy": 6.235070276260376,
"epoch": 0.8866896586194832,
"grad_norm": 1.1796875,
"learning_rate": 0.0004930256890405777,
"loss": 6.1318,
"mean_token_accuracy": 0.15403689593076705,
"num_tokens": 17356595.0,
"step": 8870
},
{
"entropy": 6.319204950332642,
"epoch": 0.8871894836807117,
"grad_norm": 1.1796875,
"learning_rate": 0.0004930168693513627,
"loss": 6.1846,
"mean_token_accuracy": 0.149034284055233,
"num_tokens": 17366264.0,
"step": 8875
},
{
"entropy": 6.317347145080566,
"epoch": 0.8876893087419403,
"grad_norm": 1.2734375,
"learning_rate": 0.0004930080441768995,
"loss": 6.184,
"mean_token_accuracy": 0.14377377703785896,
"num_tokens": 17376324.0,
"step": 8880
},
{
"entropy": 6.286531019210815,
"epoch": 0.8881891338031689,
"grad_norm": 1.109375,
"learning_rate": 0.00049299921351741,
"loss": 6.1255,
"mean_token_accuracy": 0.14417110681533812,
"num_tokens": 17386436.0,
"step": 8885
},
{
"entropy": 6.24146785736084,
"epoch": 0.8886889588643975,
"grad_norm": 1.28125,
"learning_rate": 0.0004929903773731164,
"loss": 6.1036,
"mean_token_accuracy": 0.15214107781648636,
"num_tokens": 17395511.0,
"step": 8890
},
{
"entropy": 6.212081861495972,
"epoch": 0.8891887839256261,
"grad_norm": 1.15625,
"learning_rate": 0.0004929815357442409,
"loss": 6.1006,
"mean_token_accuracy": 0.15339987799525262,
"num_tokens": 17404887.0,
"step": 8895
},
{
"entropy": 6.261399555206299,
"epoch": 0.8896886089868546,
"grad_norm": 1.2890625,
"learning_rate": 0.0004929726886310062,
"loss": 6.0859,
"mean_token_accuracy": 0.14992300420999527,
"num_tokens": 17413936.0,
"step": 8900
},
{
"entropy": 6.2568460464477536,
"epoch": 0.8901884340480831,
"grad_norm": 1.2421875,
"learning_rate": 0.0004929638360336348,
"loss": 6.1673,
"mean_token_accuracy": 0.14320943355560303,
"num_tokens": 17425011.0,
"step": 8905
},
{
"entropy": 6.276605701446533,
"epoch": 0.8906882591093117,
"grad_norm": 1.3125,
"learning_rate": 0.0004929549779523492,
"loss": 6.109,
"mean_token_accuracy": 0.14854919016361237,
"num_tokens": 17434508.0,
"step": 8910
},
{
"entropy": 6.292928075790405,
"epoch": 0.8911880841705403,
"grad_norm": 1.21875,
"learning_rate": 0.0004929461143873725,
"loss": 6.128,
"mean_token_accuracy": 0.1482929363846779,
"num_tokens": 17444155.0,
"step": 8915
},
{
"entropy": 6.3267906665802,
"epoch": 0.8916879092317689,
"grad_norm": 1.5,
"learning_rate": 0.0004929372453389277,
"loss": 6.2345,
"mean_token_accuracy": 0.13820834085345268,
"num_tokens": 17453834.0,
"step": 8920
},
{
"entropy": 6.204963541030883,
"epoch": 0.8921877342929975,
"grad_norm": 1.265625,
"learning_rate": 0.0004929283708072378,
"loss": 6.0846,
"mean_token_accuracy": 0.15507842898368834,
"num_tokens": 17463491.0,
"step": 8925
},
{
"entropy": 6.149940347671508,
"epoch": 0.8926875593542261,
"grad_norm": 1.2265625,
"learning_rate": 0.0004929194907925262,
"loss": 6.0434,
"mean_token_accuracy": 0.15164035111665725,
"num_tokens": 17472882.0,
"step": 8930
},
{
"entropy": 6.264197540283203,
"epoch": 0.8931873844154546,
"grad_norm": 1.25,
"learning_rate": 0.0004929106052950163,
"loss": 6.1573,
"mean_token_accuracy": 0.1497704066336155,
"num_tokens": 17483318.0,
"step": 8935
},
{
"entropy": 6.20780839920044,
"epoch": 0.8936872094766831,
"grad_norm": 1.171875,
"learning_rate": 0.0004929017143149317,
"loss": 6.0778,
"mean_token_accuracy": 0.15200841426849365,
"num_tokens": 17493212.0,
"step": 8940
},
{
"entropy": 6.2409679889678955,
"epoch": 0.8941870345379117,
"grad_norm": 1.3203125,
"learning_rate": 0.000492892817852496,
"loss": 6.08,
"mean_token_accuracy": 0.14508683681488038,
"num_tokens": 17502782.0,
"step": 8945
},
{
"entropy": 6.2060588836669925,
"epoch": 0.8946868595991403,
"grad_norm": 1.5703125,
"learning_rate": 0.000492883915907933,
"loss": 6.2528,
"mean_token_accuracy": 0.1420326016843319,
"num_tokens": 17514321.0,
"step": 8950
},
{
"entropy": 6.278987550735474,
"epoch": 0.8951866846603689,
"grad_norm": 1.3515625,
"learning_rate": 0.0004928750084814668,
"loss": 6.0974,
"mean_token_accuracy": 0.15245210826396943,
"num_tokens": 17522910.0,
"step": 8955
},
{
"entropy": 6.29258918762207,
"epoch": 0.8956865097215975,
"grad_norm": 1.3046875,
"learning_rate": 0.0004928660955733214,
"loss": 6.133,
"mean_token_accuracy": 0.1421135902404785,
"num_tokens": 17532747.0,
"step": 8960
},
{
"entropy": 6.244504737854004,
"epoch": 0.896186334782826,
"grad_norm": 1.4765625,
"learning_rate": 0.0004928571771837211,
"loss": 6.1204,
"mean_token_accuracy": 0.14728728979825972,
"num_tokens": 17542956.0,
"step": 8965
},
{
"entropy": 6.259652090072632,
"epoch": 0.8966861598440545,
"grad_norm": 1.4296875,
"learning_rate": 0.0004928482533128902,
"loss": 6.2129,
"mean_token_accuracy": 0.14703244119882583,
"num_tokens": 17552462.0,
"step": 8970
},
{
"entropy": 6.317249488830567,
"epoch": 0.8971859849052831,
"grad_norm": 1.2265625,
"learning_rate": 0.0004928393239610535,
"loss": 6.144,
"mean_token_accuracy": 0.14515073150396346,
"num_tokens": 17561413.0,
"step": 8975
},
{
"entropy": 6.286448812484741,
"epoch": 0.8976858099665117,
"grad_norm": 1.3671875,
"learning_rate": 0.0004928303891284354,
"loss": 6.1159,
"mean_token_accuracy": 0.15042459070682526,
"num_tokens": 17571157.0,
"step": 8980
},
{
"entropy": 6.341135454177857,
"epoch": 0.8981856350277403,
"grad_norm": 1.265625,
"learning_rate": 0.0004928214488152607,
"loss": 6.1778,
"mean_token_accuracy": 0.14475326165556907,
"num_tokens": 17581645.0,
"step": 8985
},
{
"entropy": 6.242169046401978,
"epoch": 0.8986854600889689,
"grad_norm": 1.359375,
"learning_rate": 0.0004928125030217545,
"loss": 6.1383,
"mean_token_accuracy": 0.15014248639345168,
"num_tokens": 17591990.0,
"step": 8990
},
{
"entropy": 6.308021068572998,
"epoch": 0.8991852851501975,
"grad_norm": 1.328125,
"learning_rate": 0.0004928035517481416,
"loss": 6.1545,
"mean_token_accuracy": 0.15807769894599916,
"num_tokens": 17602063.0,
"step": 8995
},
{
"entropy": 6.250316143035889,
"epoch": 0.899685110211426,
"grad_norm": 1.4140625,
"learning_rate": 0.0004927945949946476,
"loss": 6.1708,
"mean_token_accuracy": 0.14406087920069693,
"num_tokens": 17612258.0,
"step": 9000
},
{
"epoch": 0.899685110211426,
"eval_entropy": 6.139723458814731,
"eval_loss": 6.176752090454102,
"eval_mean_token_accuracy": 0.15213278615816034,
"eval_num_tokens": 17612258.0,
"eval_runtime": 23.5839,
"eval_samples_per_second": 1316.365,
"eval_steps_per_second": 164.562,
"step": 9000
},
{
"entropy": 6.2707662105560305,
"epoch": 0.9001849352726545,
"grad_norm": 2.390625,
"learning_rate": 0.0004927856327614975,
"loss": 6.0846,
"mean_token_accuracy": 0.15197736918926238,
"num_tokens": 17621901.0,
"step": 9005
},
{
"entropy": 6.253821086883545,
"epoch": 0.9006847603338831,
"grad_norm": 1.6484375,
"learning_rate": 0.000492776665048917,
"loss": 6.0862,
"mean_token_accuracy": 0.14120185673236846,
"num_tokens": 17630854.0,
"step": 9010
},
{
"entropy": 6.353455495834351,
"epoch": 0.9011845853951117,
"grad_norm": 1.4140625,
"learning_rate": 0.0004927676918571316,
"loss": 6.2257,
"mean_token_accuracy": 0.1396675944328308,
"num_tokens": 17640758.0,
"step": 9015
},
{
"entropy": 6.273074388504028,
"epoch": 0.9016844104563403,
"grad_norm": 1.296875,
"learning_rate": 0.0004927587131863671,
"loss": 6.0932,
"mean_token_accuracy": 0.15239740163087845,
"num_tokens": 17650171.0,
"step": 9020
},
{
"entropy": 6.249118423461914,
"epoch": 0.9021842355175689,
"grad_norm": 1.4140625,
"learning_rate": 0.0004927497290368493,
"loss": 6.2324,
"mean_token_accuracy": 0.1458345539867878,
"num_tokens": 17660403.0,
"step": 9025
},
{
"entropy": 6.338074636459351,
"epoch": 0.9026840605787975,
"grad_norm": 1.4140625,
"learning_rate": 0.0004927407394088046,
"loss": 6.2377,
"mean_token_accuracy": 0.14179567918181418,
"num_tokens": 17670764.0,
"step": 9030
},
{
"entropy": 6.211802864074707,
"epoch": 0.9031838856400259,
"grad_norm": 1.375,
"learning_rate": 0.0004927317443024587,
"loss": 6.1339,
"mean_token_accuracy": 0.14813459068536758,
"num_tokens": 17679804.0,
"step": 9035
},
{
"entropy": 6.350583171844482,
"epoch": 0.9036837107012545,
"grad_norm": 1.2421875,
"learning_rate": 0.0004927227437180382,
"loss": 6.1886,
"mean_token_accuracy": 0.14003006517887115,
"num_tokens": 17689819.0,
"step": 9040
},
{
"entropy": 6.320320272445679,
"epoch": 0.9041835357624831,
"grad_norm": 1.7421875,
"learning_rate": 0.0004927137376557696,
"loss": 6.2241,
"mean_token_accuracy": 0.14652050137519837,
"num_tokens": 17699716.0,
"step": 9045
},
{
"entropy": 6.284196043014527,
"epoch": 0.9046833608237117,
"grad_norm": 1.34375,
"learning_rate": 0.0004927047261158793,
"loss": 6.0889,
"mean_token_accuracy": 0.1529783457517624,
"num_tokens": 17709988.0,
"step": 9050
},
{
"entropy": 6.215233230590821,
"epoch": 0.9051831858849403,
"grad_norm": 1.4765625,
"learning_rate": 0.0004926957090985942,
"loss": 6.0651,
"mean_token_accuracy": 0.1509389117360115,
"num_tokens": 17719821.0,
"step": 9055
},
{
"entropy": 6.356567287445069,
"epoch": 0.9056830109461689,
"grad_norm": 1.3125,
"learning_rate": 0.0004926866866041409,
"loss": 6.2254,
"mean_token_accuracy": 0.13990216851234435,
"num_tokens": 17728813.0,
"step": 9060
},
{
"entropy": 6.25905179977417,
"epoch": 0.9061828360073975,
"grad_norm": 1.2109375,
"learning_rate": 0.0004926776586327467,
"loss": 6.1044,
"mean_token_accuracy": 0.14727877229452133,
"num_tokens": 17738906.0,
"step": 9065
},
{
"entropy": 6.2407087802886965,
"epoch": 0.9066826610686259,
"grad_norm": 1.4453125,
"learning_rate": 0.0004926686251846386,
"loss": 6.0907,
"mean_token_accuracy": 0.15298380106687545,
"num_tokens": 17748869.0,
"step": 9070
},
{
"entropy": 6.310334300994873,
"epoch": 0.9071824861298545,
"grad_norm": 1.3984375,
"learning_rate": 0.0004926595862600439,
"loss": 6.2291,
"mean_token_accuracy": 0.14141777753829957,
"num_tokens": 17758772.0,
"step": 9075
},
{
"entropy": 6.275823593139648,
"epoch": 0.9076823111910831,
"grad_norm": 1.203125,
"learning_rate": 0.0004926505418591901,
"loss": 6.2106,
"mean_token_accuracy": 0.14034887477755548,
"num_tokens": 17768575.0,
"step": 9080
},
{
"entropy": 6.290746831893921,
"epoch": 0.9081821362523117,
"grad_norm": 1.28125,
"learning_rate": 0.0004926414919823045,
"loss": 6.2528,
"mean_token_accuracy": 0.13516096472740174,
"num_tokens": 17777445.0,
"step": 9085
},
{
"entropy": 6.245418357849121,
"epoch": 0.9086819613135403,
"grad_norm": 1.1640625,
"learning_rate": 0.0004926324366296151,
"loss": 6.0626,
"mean_token_accuracy": 0.1501642346382141,
"num_tokens": 17787995.0,
"step": 9090
},
{
"entropy": 6.252548456192017,
"epoch": 0.9091817863747689,
"grad_norm": 1.4296875,
"learning_rate": 0.0004926233758013494,
"loss": 6.0509,
"mean_token_accuracy": 0.15676427111029625,
"num_tokens": 17797899.0,
"step": 9095
},
{
"entropy": 6.309170579910278,
"epoch": 0.9096816114359974,
"grad_norm": 1.2734375,
"learning_rate": 0.0004926143094977359,
"loss": 6.1063,
"mean_token_accuracy": 0.14765240550041198,
"num_tokens": 17807640.0,
"step": 9100
},
{
"entropy": 6.227313899993897,
"epoch": 0.9101814364972259,
"grad_norm": 1.4453125,
"learning_rate": 0.0004926052377190022,
"loss": 6.126,
"mean_token_accuracy": 0.14825500398874283,
"num_tokens": 17817997.0,
"step": 9105
},
{
"entropy": 6.280065679550171,
"epoch": 0.9106812615584545,
"grad_norm": 1.2734375,
"learning_rate": 0.0004925961604653765,
"loss": 6.1605,
"mean_token_accuracy": 0.1422814592719078,
"num_tokens": 17828145.0,
"step": 9110
},
{
"entropy": 6.333649015426635,
"epoch": 0.9111810866196831,
"grad_norm": 1.265625,
"learning_rate": 0.0004925870777370877,
"loss": 6.061,
"mean_token_accuracy": 0.15739258974790574,
"num_tokens": 17837403.0,
"step": 9115
},
{
"entropy": 6.26377911567688,
"epoch": 0.9116809116809117,
"grad_norm": 1.296875,
"learning_rate": 0.0004925779895343639,
"loss": 6.1299,
"mean_token_accuracy": 0.15004582032561303,
"num_tokens": 17846745.0,
"step": 9120
},
{
"entropy": 6.284781503677368,
"epoch": 0.9121807367421403,
"grad_norm": 1.2578125,
"learning_rate": 0.0004925688958574339,
"loss": 6.1596,
"mean_token_accuracy": 0.14793580621480942,
"num_tokens": 17857422.0,
"step": 9125
},
{
"entropy": 6.243457460403443,
"epoch": 0.9126805618033689,
"grad_norm": 1.2265625,
"learning_rate": 0.0004925597967065264,
"loss": 6.0508,
"mean_token_accuracy": 0.15382441878318787,
"num_tokens": 17867004.0,
"step": 9130
},
{
"entropy": 6.3056535720825195,
"epoch": 0.9131803868645973,
"grad_norm": 1.2734375,
"learning_rate": 0.0004925506920818705,
"loss": 6.1942,
"mean_token_accuracy": 0.14008287340402603,
"num_tokens": 17876933.0,
"step": 9135
},
{
"entropy": 6.278475189208985,
"epoch": 0.9136802119258259,
"grad_norm": 1.4765625,
"learning_rate": 0.0004925415819836951,
"loss": 6.147,
"mean_token_accuracy": 0.14869310557842255,
"num_tokens": 17887639.0,
"step": 9140
},
{
"entropy": 6.264593410491943,
"epoch": 0.9141800369870545,
"grad_norm": 1.28125,
"learning_rate": 0.0004925324664122294,
"loss": 6.0287,
"mean_token_accuracy": 0.16113806515932083,
"num_tokens": 17897125.0,
"step": 9145
},
{
"entropy": 6.203950595855713,
"epoch": 0.9146798620482831,
"grad_norm": 1.234375,
"learning_rate": 0.0004925233453677029,
"loss": 6.1733,
"mean_token_accuracy": 0.1448161281645298,
"num_tokens": 17907580.0,
"step": 9150
},
{
"entropy": 6.204181718826294,
"epoch": 0.9151796871095117,
"grad_norm": 1.3125,
"learning_rate": 0.0004925142188503451,
"loss": 6.0453,
"mean_token_accuracy": 0.16035950779914857,
"num_tokens": 17915937.0,
"step": 9155
},
{
"entropy": 6.19406476020813,
"epoch": 0.9156795121707403,
"grad_norm": 1.4140625,
"learning_rate": 0.0004925050868603854,
"loss": 6.0208,
"mean_token_accuracy": 0.15496256798505784,
"num_tokens": 17926337.0,
"step": 9160
},
{
"entropy": 6.271029281616211,
"epoch": 0.9161793372319688,
"grad_norm": 1.3203125,
"learning_rate": 0.0004924959493980537,
"loss": 6.2103,
"mean_token_accuracy": 0.13686318099498748,
"num_tokens": 17936123.0,
"step": 9165
},
{
"entropy": 6.252589225769043,
"epoch": 0.9166791622931973,
"grad_norm": 1.2265625,
"learning_rate": 0.0004924868064635798,
"loss": 6.0696,
"mean_token_accuracy": 0.15073217675089837,
"num_tokens": 17946143.0,
"step": 9170
},
{
"entropy": 6.3810343742370605,
"epoch": 0.9171789873544259,
"grad_norm": 1.296875,
"learning_rate": 0.000492477658057194,
"loss": 6.2246,
"mean_token_accuracy": 0.14059614315629004,
"num_tokens": 17956034.0,
"step": 9175
},
{
"entropy": 6.257679653167725,
"epoch": 0.9176788124156545,
"grad_norm": 1.28125,
"learning_rate": 0.0004924685041791262,
"loss": 6.0979,
"mean_token_accuracy": 0.1443646177649498,
"num_tokens": 17965455.0,
"step": 9180
},
{
"entropy": 6.234354829788208,
"epoch": 0.9181786374768831,
"grad_norm": 1.2578125,
"learning_rate": 0.0004924593448296068,
"loss": 6.126,
"mean_token_accuracy": 0.1433185011148453,
"num_tokens": 17974506.0,
"step": 9185
},
{
"entropy": 6.228525876998901,
"epoch": 0.9186784625381117,
"grad_norm": 1.2890625,
"learning_rate": 0.0004924501800088662,
"loss": 6.1433,
"mean_token_accuracy": 0.14215124770998955,
"num_tokens": 17984750.0,
"step": 9190
},
{
"entropy": 6.241401338577271,
"epoch": 0.9191782875993403,
"grad_norm": 1.1640625,
"learning_rate": 0.0004924410097171351,
"loss": 6.1377,
"mean_token_accuracy": 0.15220036059617997,
"num_tokens": 17993871.0,
"step": 9195
},
{
"entropy": 6.244402694702148,
"epoch": 0.9196781126605688,
"grad_norm": 1.3984375,
"learning_rate": 0.000492431833954644,
"loss": 6.1068,
"mean_token_accuracy": 0.1497140794992447,
"num_tokens": 18003686.0,
"step": 9200
},
{
"entropy": 6.2604717254638675,
"epoch": 0.9201779377217973,
"grad_norm": 1.3359375,
"learning_rate": 0.0004924226527216241,
"loss": 6.1346,
"mean_token_accuracy": 0.15008196532726287,
"num_tokens": 18013024.0,
"step": 9205
},
{
"entropy": 6.263730907440186,
"epoch": 0.9206777627830259,
"grad_norm": 1.3125,
"learning_rate": 0.0004924134660183061,
"loss": 6.099,
"mean_token_accuracy": 0.14889158681035042,
"num_tokens": 18022718.0,
"step": 9210
},
{
"entropy": 6.1407952308654785,
"epoch": 0.9211775878442545,
"grad_norm": 1.2578125,
"learning_rate": 0.0004924042738449212,
"loss": 5.9555,
"mean_token_accuracy": 0.1525575503706932,
"num_tokens": 18032185.0,
"step": 9215
},
{
"entropy": 6.300953340530396,
"epoch": 0.9216774129054831,
"grad_norm": 1.2421875,
"learning_rate": 0.0004923950762017008,
"loss": 6.153,
"mean_token_accuracy": 0.15161130726337432,
"num_tokens": 18041864.0,
"step": 9220
},
{
"entropy": 6.154758739471435,
"epoch": 0.9221772379667117,
"grad_norm": 1.375,
"learning_rate": 0.0004923858730888762,
"loss": 5.9918,
"mean_token_accuracy": 0.16416605710983276,
"num_tokens": 18050797.0,
"step": 9225
},
{
"entropy": 6.179091119766236,
"epoch": 0.9226770630279402,
"grad_norm": 1.140625,
"learning_rate": 0.000492376664506679,
"loss": 6.0166,
"mean_token_accuracy": 0.15271463394165039,
"num_tokens": 18060414.0,
"step": 9230
},
{
"entropy": 6.22623610496521,
"epoch": 0.9231768880891688,
"grad_norm": 1.2421875,
"learning_rate": 0.0004923674504553408,
"loss": 6.1484,
"mean_token_accuracy": 0.14723171293735504,
"num_tokens": 18070832.0,
"step": 9235
},
{
"entropy": 6.272461795806885,
"epoch": 0.9236767131503973,
"grad_norm": 1.3046875,
"learning_rate": 0.0004923582309350935,
"loss": 6.0973,
"mean_token_accuracy": 0.1501172050833702,
"num_tokens": 18078918.0,
"step": 9240
},
{
"entropy": 6.294412660598755,
"epoch": 0.9241765382116259,
"grad_norm": 1.2421875,
"learning_rate": 0.000492349005946169,
"loss": 6.154,
"mean_token_accuracy": 0.15143943578004837,
"num_tokens": 18087896.0,
"step": 9245
},
{
"entropy": 6.333119869232178,
"epoch": 0.9246763632728545,
"grad_norm": 1.21875,
"learning_rate": 0.0004923397754887994,
"loss": 6.2102,
"mean_token_accuracy": 0.1431832417845726,
"num_tokens": 18097535.0,
"step": 9250
},
{
"entropy": 6.176212930679322,
"epoch": 0.9251761883340831,
"grad_norm": 1.140625,
"learning_rate": 0.0004923305395632172,
"loss": 6.0806,
"mean_token_accuracy": 0.1512439213693142,
"num_tokens": 18107503.0,
"step": 9255
},
{
"entropy": 6.24899845123291,
"epoch": 0.9256760133953117,
"grad_norm": 1.2890625,
"learning_rate": 0.0004923212981696543,
"loss": 6.0854,
"mean_token_accuracy": 0.14923255667090415,
"num_tokens": 18117188.0,
"step": 9260
},
{
"entropy": 6.343647813796997,
"epoch": 0.9261758384565402,
"grad_norm": 1.3515625,
"learning_rate": 0.0004923120513083436,
"loss": 6.2589,
"mean_token_accuracy": 0.1378469757735729,
"num_tokens": 18127965.0,
"step": 9265
},
{
"entropy": 6.249783658981324,
"epoch": 0.9266756635177688,
"grad_norm": 1.390625,
"learning_rate": 0.0004923027989795175,
"loss": 6.1178,
"mean_token_accuracy": 0.1457314074039459,
"num_tokens": 18136861.0,
"step": 9270
},
{
"entropy": 6.21954026222229,
"epoch": 0.9271754885789973,
"grad_norm": 1.40625,
"learning_rate": 0.000492293541183409,
"loss": 6.0943,
"mean_token_accuracy": 0.14869869351387024,
"num_tokens": 18145702.0,
"step": 9275
},
{
"entropy": 6.291553354263305,
"epoch": 0.9276753136402259,
"grad_norm": 1.34375,
"learning_rate": 0.0004922842779202509,
"loss": 6.1743,
"mean_token_accuracy": 0.14882912039756774,
"num_tokens": 18155177.0,
"step": 9280
},
{
"entropy": 6.2452467918396,
"epoch": 0.9281751387014545,
"grad_norm": 1.25,
"learning_rate": 0.0004922750091902763,
"loss": 6.051,
"mean_token_accuracy": 0.15065366998314858,
"num_tokens": 18165361.0,
"step": 9285
},
{
"entropy": 6.2458032131195065,
"epoch": 0.9286749637626831,
"grad_norm": 1.4375,
"learning_rate": 0.0004922657349937183,
"loss": 6.1009,
"mean_token_accuracy": 0.14763772413134574,
"num_tokens": 18175300.0,
"step": 9290
},
{
"entropy": 6.337135219573975,
"epoch": 0.9291747888239116,
"grad_norm": 1.3359375,
"learning_rate": 0.0004922564553308103,
"loss": 6.0998,
"mean_token_accuracy": 0.15319805443286896,
"num_tokens": 18183985.0,
"step": 9295
},
{
"entropy": 6.3126795291900635,
"epoch": 0.9296746138851402,
"grad_norm": 1.3046875,
"learning_rate": 0.000492247170201786,
"loss": 6.2181,
"mean_token_accuracy": 0.1427415542304516,
"num_tokens": 18193251.0,
"step": 9300
},
{
"entropy": 6.283484363555909,
"epoch": 0.9301744389463688,
"grad_norm": 1.28125,
"learning_rate": 0.0004922378796068785,
"loss": 6.0612,
"mean_token_accuracy": 0.1548401892185211,
"num_tokens": 18202081.0,
"step": 9305
},
{
"entropy": 6.229377031326294,
"epoch": 0.9306742640075973,
"grad_norm": 1.3203125,
"learning_rate": 0.000492228583546322,
"loss": 6.0642,
"mean_token_accuracy": 0.14648374244570733,
"num_tokens": 18211499.0,
"step": 9310
},
{
"entropy": 6.197189092636108,
"epoch": 0.9311740890688259,
"grad_norm": 1.2890625,
"learning_rate": 0.0004922192820203502,
"loss": 6.0649,
"mean_token_accuracy": 0.15283203125,
"num_tokens": 18220764.0,
"step": 9315
},
{
"entropy": 6.174600744247437,
"epoch": 0.9316739141300545,
"grad_norm": 1.2578125,
"learning_rate": 0.0004922099750291972,
"loss": 6.0707,
"mean_token_accuracy": 0.15849846601486206,
"num_tokens": 18230126.0,
"step": 9320
},
{
"entropy": 6.16498441696167,
"epoch": 0.9321737391912831,
"grad_norm": 1.2734375,
"learning_rate": 0.0004922006625730971,
"loss": 6.07,
"mean_token_accuracy": 0.15209577828645707,
"num_tokens": 18238426.0,
"step": 9325
},
{
"entropy": 6.267601490020752,
"epoch": 0.9326735642525116,
"grad_norm": 1.4765625,
"learning_rate": 0.0004921913446522843,
"loss": 6.1628,
"mean_token_accuracy": 0.14164744094014167,
"num_tokens": 18248215.0,
"step": 9330
},
{
"entropy": 6.257072877883911,
"epoch": 0.9331733893137402,
"grad_norm": 1.4921875,
"learning_rate": 0.000492182021266993,
"loss": 6.1171,
"mean_token_accuracy": 0.14654496014118196,
"num_tokens": 18258967.0,
"step": 9335
},
{
"entropy": 6.314351749420166,
"epoch": 0.9336732143749688,
"grad_norm": 1.2578125,
"learning_rate": 0.000492172692417458,
"loss": 6.1712,
"mean_token_accuracy": 0.14318839460611343,
"num_tokens": 18268901.0,
"step": 9340
},
{
"entropy": 6.377855396270752,
"epoch": 0.9341730394361973,
"grad_norm": 1.1640625,
"learning_rate": 0.000492163358103914,
"loss": 6.1883,
"mean_token_accuracy": 0.14365150183439254,
"num_tokens": 18279615.0,
"step": 9345
},
{
"entropy": 6.18309850692749,
"epoch": 0.9346728644974259,
"grad_norm": 1.84375,
"learning_rate": 0.0004921540183265957,
"loss": 6.0974,
"mean_token_accuracy": 0.15152767300605774,
"num_tokens": 18289630.0,
"step": 9350
},
{
"entropy": 6.195323753356933,
"epoch": 0.9351726895586545,
"grad_norm": 1.3671875,
"learning_rate": 0.0004921446730857383,
"loss": 6.146,
"mean_token_accuracy": 0.1466882348060608,
"num_tokens": 18299764.0,
"step": 9355
},
{
"entropy": 6.234064388275146,
"epoch": 0.935672514619883,
"grad_norm": 1.4140625,
"learning_rate": 0.0004921353223815767,
"loss": 6.0384,
"mean_token_accuracy": 0.1607164114713669,
"num_tokens": 18310252.0,
"step": 9360
},
{
"entropy": 6.3009199619293215,
"epoch": 0.9361723396811116,
"grad_norm": 1.21875,
"learning_rate": 0.0004921259662143463,
"loss": 6.1126,
"mean_token_accuracy": 0.15220096856355667,
"num_tokens": 18319753.0,
"step": 9365
},
{
"entropy": 6.259305334091186,
"epoch": 0.9366721647423402,
"grad_norm": 1.2578125,
"learning_rate": 0.0004921166045842825,
"loss": 6.1351,
"mean_token_accuracy": 0.14800689816474916,
"num_tokens": 18330307.0,
"step": 9370
},
{
"entropy": 6.269847869873047,
"epoch": 0.9371719898035688,
"grad_norm": 1.203125,
"learning_rate": 0.0004921072374916208,
"loss": 6.1744,
"mean_token_accuracy": 0.14757596403360368,
"num_tokens": 18340867.0,
"step": 9375
},
{
"entropy": 6.221883916854859,
"epoch": 0.9376718148647973,
"grad_norm": 1.28125,
"learning_rate": 0.0004920978649365968,
"loss": 6.0099,
"mean_token_accuracy": 0.16141703575849534,
"num_tokens": 18350852.0,
"step": 9380
},
{
"entropy": 6.1437976360321045,
"epoch": 0.9381716399260259,
"grad_norm": 1.2109375,
"learning_rate": 0.0004920884869194463,
"loss": 6.017,
"mean_token_accuracy": 0.1564452603459358,
"num_tokens": 18361821.0,
"step": 9385
},
{
"entropy": 6.2910590171813965,
"epoch": 0.9386714649872545,
"grad_norm": 1.1875,
"learning_rate": 0.0004920791034404054,
"loss": 6.1575,
"mean_token_accuracy": 0.1417326919734478,
"num_tokens": 18371391.0,
"step": 9390
},
{
"entropy": 6.321835088729858,
"epoch": 0.939171290048483,
"grad_norm": 1.265625,
"learning_rate": 0.0004920697144997102,
"loss": 6.1515,
"mean_token_accuracy": 0.14812880083918573,
"num_tokens": 18380661.0,
"step": 9395
},
{
"entropy": 6.218744850158691,
"epoch": 0.9396711151097116,
"grad_norm": 1.375,
"learning_rate": 0.0004920603200975968,
"loss": 6.0963,
"mean_token_accuracy": 0.15220969915390015,
"num_tokens": 18390365.0,
"step": 9400
},
{
"entropy": 6.159506130218506,
"epoch": 0.9401709401709402,
"grad_norm": 1.21875,
"learning_rate": 0.0004920509202343016,
"loss": 6.0546,
"mean_token_accuracy": 0.15513156801462175,
"num_tokens": 18399536.0,
"step": 9405
},
{
"entropy": 6.252153158187866,
"epoch": 0.9406707652321687,
"grad_norm": 1.21875,
"learning_rate": 0.000492041514910061,
"loss": 6.1117,
"mean_token_accuracy": 0.15268371999263763,
"num_tokens": 18408769.0,
"step": 9410
},
{
"entropy": 6.232716798782349,
"epoch": 0.9411705902933973,
"grad_norm": 1.8125,
"learning_rate": 0.0004920321041251118,
"loss": 6.1341,
"mean_token_accuracy": 0.14862325713038443,
"num_tokens": 18418554.0,
"step": 9415
},
{
"entropy": 6.1887129783630375,
"epoch": 0.9416704153546259,
"grad_norm": 1.4296875,
"learning_rate": 0.0004920226878796908,
"loss": 6.1078,
"mean_token_accuracy": 0.1459977775812149,
"num_tokens": 18429670.0,
"step": 9420
},
{
"entropy": 6.301774692535401,
"epoch": 0.9421702404158544,
"grad_norm": 1.3203125,
"learning_rate": 0.0004920132661740348,
"loss": 6.2093,
"mean_token_accuracy": 0.14631576389074324,
"num_tokens": 18438747.0,
"step": 9425
},
{
"entropy": 6.320364332199096,
"epoch": 0.942670065477083,
"grad_norm": 1.4765625,
"learning_rate": 0.0004920038390083808,
"loss": 6.159,
"mean_token_accuracy": 0.14723806083202362,
"num_tokens": 18449350.0,
"step": 9430
},
{
"entropy": 6.248285722732544,
"epoch": 0.9431698905383116,
"grad_norm": 1.3125,
"learning_rate": 0.000491994406382966,
"loss": 6.0732,
"mean_token_accuracy": 0.15016899704933168,
"num_tokens": 18459052.0,
"step": 9435
},
{
"entropy": 6.2822265625,
"epoch": 0.9436697155995402,
"grad_norm": 1.2890625,
"learning_rate": 0.0004919849682980278,
"loss": 6.1799,
"mean_token_accuracy": 0.1491839364171028,
"num_tokens": 18469266.0,
"step": 9440
},
{
"entropy": 6.316525650024414,
"epoch": 0.9441695406607687,
"grad_norm": 1.265625,
"learning_rate": 0.0004919755247538037,
"loss": 6.1667,
"mean_token_accuracy": 0.14303553029894828,
"num_tokens": 18479381.0,
"step": 9445
},
{
"entropy": 6.2104589462280275,
"epoch": 0.9446693657219973,
"grad_norm": 1.421875,
"learning_rate": 0.0004919660757505312,
"loss": 6.017,
"mean_token_accuracy": 0.15580771639943122,
"num_tokens": 18488973.0,
"step": 9450
},
{
"entropy": 6.113431310653686,
"epoch": 0.9451691907832259,
"grad_norm": 1.296875,
"learning_rate": 0.0004919566212884481,
"loss": 6.0157,
"mean_token_accuracy": 0.15505917519330978,
"num_tokens": 18497907.0,
"step": 9455
},
{
"entropy": 6.197196292877197,
"epoch": 0.9456690158444544,
"grad_norm": 1.203125,
"learning_rate": 0.0004919471613677921,
"loss": 6.0762,
"mean_token_accuracy": 0.15334462970495225,
"num_tokens": 18507628.0,
"step": 9460
},
{
"entropy": 6.27160120010376,
"epoch": 0.946168840905683,
"grad_norm": 1.4296875,
"learning_rate": 0.0004919376959888015,
"loss": 6.2124,
"mean_token_accuracy": 0.14611563980579376,
"num_tokens": 18516346.0,
"step": 9465
},
{
"entropy": 6.3423604488372805,
"epoch": 0.9466686659669116,
"grad_norm": 1.4296875,
"learning_rate": 0.0004919282251517142,
"loss": 6.0291,
"mean_token_accuracy": 0.15277713537216187,
"num_tokens": 18525568.0,
"step": 9470
},
{
"entropy": 6.232535314559937,
"epoch": 0.9471684910281402,
"grad_norm": 1.359375,
"learning_rate": 0.0004919187488567686,
"loss": 6.1486,
"mean_token_accuracy": 0.1497054398059845,
"num_tokens": 18536715.0,
"step": 9475
},
{
"entropy": 6.240742635726929,
"epoch": 0.9476683160893687,
"grad_norm": 1.6875,
"learning_rate": 0.0004919092671042031,
"loss": 6.1723,
"mean_token_accuracy": 0.14626911133527756,
"num_tokens": 18546405.0,
"step": 9480
},
{
"entropy": 6.326673173904419,
"epoch": 0.9481681411505973,
"grad_norm": 1.3125,
"learning_rate": 0.0004918997798942562,
"loss": 6.2309,
"mean_token_accuracy": 0.14294743835926055,
"num_tokens": 18556721.0,
"step": 9485
},
{
"entropy": 6.348190832138061,
"epoch": 0.9486679662118258,
"grad_norm": 1.21875,
"learning_rate": 0.0004918902872271668,
"loss": 6.2329,
"mean_token_accuracy": 0.14100321829319,
"num_tokens": 18567875.0,
"step": 9490
},
{
"entropy": 6.213951063156128,
"epoch": 0.9491677912730544,
"grad_norm": 1.3515625,
"learning_rate": 0.0004918807891031734,
"loss": 6.1294,
"mean_token_accuracy": 0.14599598199129105,
"num_tokens": 18578185.0,
"step": 9495
},
{
"entropy": 6.215129137039185,
"epoch": 0.949667616334283,
"grad_norm": 1.2265625,
"learning_rate": 0.0004918712855225154,
"loss": 6.0844,
"mean_token_accuracy": 0.14716582745313644,
"num_tokens": 18587503.0,
"step": 9500
},
{
"entropy": 6.264170551300049,
"epoch": 0.9501674413955116,
"grad_norm": 1.2578125,
"learning_rate": 0.0004918617764854314,
"loss": 6.1256,
"mean_token_accuracy": 0.14867414385080338,
"num_tokens": 18597018.0,
"step": 9505
},
{
"entropy": 6.31040391921997,
"epoch": 0.9506672664567402,
"grad_norm": 1.3671875,
"learning_rate": 0.000491852261992161,
"loss": 6.1152,
"mean_token_accuracy": 0.1543574959039688,
"num_tokens": 18606262.0,
"step": 9510
},
{
"entropy": 6.339242839813233,
"epoch": 0.9511670915179687,
"grad_norm": 1.6796875,
"learning_rate": 0.0004918427420429435,
"loss": 6.1806,
"mean_token_accuracy": 0.14710851907730102,
"num_tokens": 18616070.0,
"step": 9515
},
{
"entropy": 6.186763763427734,
"epoch": 0.9516669165791973,
"grad_norm": 1.625,
"learning_rate": 0.0004918332166380185,
"loss": 6.1427,
"mean_token_accuracy": 0.14604226350784302,
"num_tokens": 18625882.0,
"step": 9520
},
{
"entropy": 6.2373744487762455,
"epoch": 0.9521667416404258,
"grad_norm": 1.296875,
"learning_rate": 0.0004918236857776254,
"loss": 6.2148,
"mean_token_accuracy": 0.14268339425325394,
"num_tokens": 18635997.0,
"step": 9525
},
{
"entropy": 6.240341567993164,
"epoch": 0.9526665667016544,
"grad_norm": 1.3203125,
"learning_rate": 0.0004918141494620042,
"loss": 6.0507,
"mean_token_accuracy": 0.1521468661725521,
"num_tokens": 18646234.0,
"step": 9530
},
{
"entropy": 6.223635721206665,
"epoch": 0.953166391762883,
"grad_norm": 1.3359375,
"learning_rate": 0.0004918046076913949,
"loss": 6.0991,
"mean_token_accuracy": 0.1467491492629051,
"num_tokens": 18655407.0,
"step": 9535
},
{
"entropy": 6.190256214141845,
"epoch": 0.9536662168241116,
"grad_norm": 1.4609375,
"learning_rate": 0.0004917950604660374,
"loss": 6.0453,
"mean_token_accuracy": 0.16087137907743454,
"num_tokens": 18664695.0,
"step": 9540
},
{
"entropy": 6.259846878051758,
"epoch": 0.9541660418853402,
"grad_norm": 1.2578125,
"learning_rate": 0.000491785507786172,
"loss": 6.0172,
"mean_token_accuracy": 0.15543370842933654,
"num_tokens": 18675170.0,
"step": 9545
},
{
"entropy": 6.145201396942139,
"epoch": 0.9546658669465687,
"grad_norm": 1.171875,
"learning_rate": 0.0004917759496520388,
"loss": 5.9989,
"mean_token_accuracy": 0.15719758570194245,
"num_tokens": 18684619.0,
"step": 9550
},
{
"entropy": 6.1628499031066895,
"epoch": 0.9551656920077972,
"grad_norm": 1.3984375,
"learning_rate": 0.0004917663860638787,
"loss": 6.1726,
"mean_token_accuracy": 0.14980884343385698,
"num_tokens": 18694133.0,
"step": 9555
},
{
"entropy": 6.261532545089722,
"epoch": 0.9556655170690258,
"grad_norm": 1.390625,
"learning_rate": 0.0004917568170219321,
"loss": 6.1228,
"mean_token_accuracy": 0.14827767312526702,
"num_tokens": 18705084.0,
"step": 9560
},
{
"entropy": 6.208607912063599,
"epoch": 0.9561653421302544,
"grad_norm": 1.34375,
"learning_rate": 0.0004917472425264397,
"loss": 6.0517,
"mean_token_accuracy": 0.15078692212700845,
"num_tokens": 18714822.0,
"step": 9565
},
{
"entropy": 6.269644165039063,
"epoch": 0.956665167191483,
"grad_norm": 1.2578125,
"learning_rate": 0.0004917376625776425,
"loss": 6.1685,
"mean_token_accuracy": 0.14474971145391463,
"num_tokens": 18725471.0,
"step": 9570
},
{
"entropy": 6.276574611663818,
"epoch": 0.9571649922527116,
"grad_norm": 1.2421875,
"learning_rate": 0.0004917280771757814,
"loss": 6.1427,
"mean_token_accuracy": 0.14567931443452836,
"num_tokens": 18734884.0,
"step": 9575
},
{
"entropy": 6.122213411331177,
"epoch": 0.9576648173139402,
"grad_norm": 1.3828125,
"learning_rate": 0.0004917184863210977,
"loss": 5.8731,
"mean_token_accuracy": 0.1681960791349411,
"num_tokens": 18744720.0,
"step": 9580
},
{
"entropy": 6.229800128936768,
"epoch": 0.9581646423751687,
"grad_norm": 1.421875,
"learning_rate": 0.0004917088900138326,
"loss": 6.1122,
"mean_token_accuracy": 0.15004415959119796,
"num_tokens": 18753636.0,
"step": 9585
},
{
"entropy": 6.322670745849609,
"epoch": 0.9586644674363972,
"grad_norm": 1.1640625,
"learning_rate": 0.0004916992882542276,
"loss": 6.1006,
"mean_token_accuracy": 0.14908642694354057,
"num_tokens": 18763750.0,
"step": 9590
},
{
"entropy": 6.207269859313965,
"epoch": 0.9591642924976258,
"grad_norm": 1.3828125,
"learning_rate": 0.0004916896810425244,
"loss": 6.0546,
"mean_token_accuracy": 0.15118743479251862,
"num_tokens": 18773626.0,
"step": 9595
},
{
"entropy": 6.219454288482666,
"epoch": 0.9596641175588544,
"grad_norm": 1.28125,
"learning_rate": 0.0004916800683789645,
"loss": 6.063,
"mean_token_accuracy": 0.1522775650024414,
"num_tokens": 18782898.0,
"step": 9600
},
{
"entropy": 6.327855587005615,
"epoch": 0.960163942620083,
"grad_norm": 1.25,
"learning_rate": 0.0004916704502637897,
"loss": 6.1931,
"mean_token_accuracy": 0.14349066764116286,
"num_tokens": 18792894.0,
"step": 9605
},
{
"entropy": 6.2121885299682615,
"epoch": 0.9606637676813116,
"grad_norm": 1.21875,
"learning_rate": 0.0004916608266972422,
"loss": 6.0935,
"mean_token_accuracy": 0.15067237615585327,
"num_tokens": 18802030.0,
"step": 9610
},
{
"entropy": 6.207405042648316,
"epoch": 0.9611635927425402,
"grad_norm": 1.265625,
"learning_rate": 0.0004916511976795642,
"loss": 6.1992,
"mean_token_accuracy": 0.14298802688717843,
"num_tokens": 18812011.0,
"step": 9615
},
{
"entropy": 6.286406755447388,
"epoch": 0.9616634178037686,
"grad_norm": 1.2109375,
"learning_rate": 0.0004916415632109977,
"loss": 6.0969,
"mean_token_accuracy": 0.15050239562988282,
"num_tokens": 18821217.0,
"step": 9620
},
{
"entropy": 6.3407751560211185,
"epoch": 0.9621632428649972,
"grad_norm": 1.390625,
"learning_rate": 0.0004916319232917852,
"loss": 6.1646,
"mean_token_accuracy": 0.1435486912727356,
"num_tokens": 18831597.0,
"step": 9625
},
{
"entropy": 6.311895704269409,
"epoch": 0.9626630679262258,
"grad_norm": 1.3984375,
"learning_rate": 0.0004916222779221694,
"loss": 6.1218,
"mean_token_accuracy": 0.15257727950811387,
"num_tokens": 18840925.0,
"step": 9630
},
{
"entropy": 6.224952697753906,
"epoch": 0.9631628929874544,
"grad_norm": 1.4609375,
"learning_rate": 0.0004916126271023926,
"loss": 6.1388,
"mean_token_accuracy": 0.1492209255695343,
"num_tokens": 18850838.0,
"step": 9635
},
{
"entropy": 6.3141227722167965,
"epoch": 0.963662718048683,
"grad_norm": 1.5078125,
"learning_rate": 0.000491602970832698,
"loss": 6.1396,
"mean_token_accuracy": 0.1446845680475235,
"num_tokens": 18860527.0,
"step": 9640
},
{
"entropy": 6.239820194244385,
"epoch": 0.9641625431099116,
"grad_norm": 1.3671875,
"learning_rate": 0.0004915933091133284,
"loss": 6.0754,
"mean_token_accuracy": 0.15459849685430527,
"num_tokens": 18870971.0,
"step": 9645
},
{
"entropy": 6.197712230682373,
"epoch": 0.9646623681711401,
"grad_norm": 1.25,
"learning_rate": 0.0004915836419445268,
"loss": 6.0609,
"mean_token_accuracy": 0.15507566183805466,
"num_tokens": 18879985.0,
"step": 9650
},
{
"entropy": 6.272829675674439,
"epoch": 0.9651621932323686,
"grad_norm": 1.546875,
"learning_rate": 0.0004915739693265365,
"loss": 6.0868,
"mean_token_accuracy": 0.14531096816062927,
"num_tokens": 18889583.0,
"step": 9655
},
{
"entropy": 6.2158444881439205,
"epoch": 0.9656620182935972,
"grad_norm": 1.2421875,
"learning_rate": 0.0004915642912596009,
"loss": 6.0941,
"mean_token_accuracy": 0.1546364977955818,
"num_tokens": 18900520.0,
"step": 9660
},
{
"entropy": 6.277464723587036,
"epoch": 0.9661618433548258,
"grad_norm": 1.34375,
"learning_rate": 0.0004915546077439634,
"loss": 6.1368,
"mean_token_accuracy": 0.14698187932372092,
"num_tokens": 18910924.0,
"step": 9665
},
{
"entropy": 6.326194810867309,
"epoch": 0.9666616684160544,
"grad_norm": 1.2109375,
"learning_rate": 0.0004915449187798677,
"loss": 6.0649,
"mean_token_accuracy": 0.15707309246063234,
"num_tokens": 18919628.0,
"step": 9670
},
{
"entropy": 6.27040205001831,
"epoch": 0.967161493477283,
"grad_norm": 1.4921875,
"learning_rate": 0.0004915352243675576,
"loss": 6.1672,
"mean_token_accuracy": 0.14706978052854539,
"num_tokens": 18929779.0,
"step": 9675
},
{
"entropy": 6.212332487106323,
"epoch": 0.9676613185385116,
"grad_norm": 1.2109375,
"learning_rate": 0.000491525524507277,
"loss": 6.0862,
"mean_token_accuracy": 0.15082838758826256,
"num_tokens": 18939791.0,
"step": 9680
},
{
"entropy": 6.168014717102051,
"epoch": 0.96816114359974,
"grad_norm": 1.140625,
"learning_rate": 0.0004915158191992699,
"loss": 6.0265,
"mean_token_accuracy": 0.15056950077414513,
"num_tokens": 18949611.0,
"step": 9685
},
{
"entropy": 6.259332752227783,
"epoch": 0.9686609686609686,
"grad_norm": 1.34375,
"learning_rate": 0.0004915061084437805,
"loss": 6.0868,
"mean_token_accuracy": 0.15144484788179396,
"num_tokens": 18959018.0,
"step": 9690
},
{
"entropy": 6.279534196853637,
"epoch": 0.9691607937221972,
"grad_norm": 1.2421875,
"learning_rate": 0.0004914963922410531,
"loss": 6.0371,
"mean_token_accuracy": 0.15167754665017127,
"num_tokens": 18967460.0,
"step": 9695
},
{
"entropy": 6.227499103546142,
"epoch": 0.9696606187834258,
"grad_norm": 1.359375,
"learning_rate": 0.0004914866705913322,
"loss": 6.1346,
"mean_token_accuracy": 0.14630355685949326,
"num_tokens": 18977545.0,
"step": 9700
},
{
"entropy": 6.212757682800293,
"epoch": 0.9701604438446544,
"grad_norm": 1.2578125,
"learning_rate": 0.0004914769434948623,
"loss": 6.1159,
"mean_token_accuracy": 0.15726826936006547,
"num_tokens": 18987304.0,
"step": 9705
},
{
"entropy": 6.2686597347259525,
"epoch": 0.970660268905883,
"grad_norm": 1.34375,
"learning_rate": 0.0004914672109518883,
"loss": 6.1898,
"mean_token_accuracy": 0.14999598041176795,
"num_tokens": 18996571.0,
"step": 9710
},
{
"entropy": 6.367182636260987,
"epoch": 0.9711600939671116,
"grad_norm": 1.234375,
"learning_rate": 0.000491457472962655,
"loss": 6.1262,
"mean_token_accuracy": 0.1426181748509407,
"num_tokens": 19007345.0,
"step": 9715
},
{
"entropy": 6.298504829406738,
"epoch": 0.97165991902834,
"grad_norm": 1.3515625,
"learning_rate": 0.0004914477295274073,
"loss": 6.1449,
"mean_token_accuracy": 0.14534396007657052,
"num_tokens": 19018202.0,
"step": 9720
},
{
"entropy": 6.232018566131591,
"epoch": 0.9721597440895686,
"grad_norm": 1.21875,
"learning_rate": 0.0004914379806463905,
"loss": 6.099,
"mean_token_accuracy": 0.15088520646095277,
"num_tokens": 19027642.0,
"step": 9725
},
{
"entropy": 6.28934063911438,
"epoch": 0.9726595691507972,
"grad_norm": 1.46875,
"learning_rate": 0.0004914282263198498,
"loss": 6.121,
"mean_token_accuracy": 0.14836250022053718,
"num_tokens": 19037433.0,
"step": 9730
},
{
"entropy": 6.295781850814819,
"epoch": 0.9731593942120258,
"grad_norm": 1.6328125,
"learning_rate": 0.0004914184665480305,
"loss": 6.1348,
"mean_token_accuracy": 0.15056052729487418,
"num_tokens": 19046835.0,
"step": 9735
},
{
"entropy": 6.308745050430298,
"epoch": 0.9736592192732544,
"grad_norm": 1.125,
"learning_rate": 0.0004914087013311784,
"loss": 6.2008,
"mean_token_accuracy": 0.14433033019304276,
"num_tokens": 19057109.0,
"step": 9740
},
{
"entropy": 6.199694108963013,
"epoch": 0.974159044334483,
"grad_norm": 1.5078125,
"learning_rate": 0.0004913989306695389,
"loss": 6.0974,
"mean_token_accuracy": 0.14893966019153596,
"num_tokens": 19067688.0,
"step": 9745
},
{
"entropy": 6.2316741943359375,
"epoch": 0.9746588693957114,
"grad_norm": 1.796875,
"learning_rate": 0.0004913891545633582,
"loss": 6.0769,
"mean_token_accuracy": 0.15238936841487885,
"num_tokens": 19077127.0,
"step": 9750
},
{
"entropy": 6.235041713714599,
"epoch": 0.97515869445694,
"grad_norm": 1.2265625,
"learning_rate": 0.000491379373012882,
"loss": 6.1371,
"mean_token_accuracy": 0.15783379822969437,
"num_tokens": 19088797.0,
"step": 9755
},
{
"entropy": 6.2633801937103275,
"epoch": 0.9756585195181686,
"grad_norm": 1.28125,
"learning_rate": 0.0004913695860183563,
"loss": 6.0675,
"mean_token_accuracy": 0.15472119748592378,
"num_tokens": 19098647.0,
"step": 9760
},
{
"entropy": 6.1970987796783445,
"epoch": 0.9761583445793972,
"grad_norm": 1.4609375,
"learning_rate": 0.0004913597935800276,
"loss": 6.0359,
"mean_token_accuracy": 0.15427698493003844,
"num_tokens": 19108385.0,
"step": 9765
},
{
"entropy": 6.281727409362793,
"epoch": 0.9766581696406258,
"grad_norm": 1.3046875,
"learning_rate": 0.0004913499956981422,
"loss": 6.153,
"mean_token_accuracy": 0.1440155953168869,
"num_tokens": 19117593.0,
"step": 9770
},
{
"entropy": 6.268272018432617,
"epoch": 0.9771579947018544,
"grad_norm": 1.5390625,
"learning_rate": 0.0004913401923729465,
"loss": 6.0627,
"mean_token_accuracy": 0.14705411940813065,
"num_tokens": 19127440.0,
"step": 9775
},
{
"entropy": 6.287357664108276,
"epoch": 0.977657819763083,
"grad_norm": 1.390625,
"learning_rate": 0.0004913303836046873,
"loss": 6.0704,
"mean_token_accuracy": 0.14986386001110077,
"num_tokens": 19136649.0,
"step": 9780
},
{
"entropy": 6.1856701374053955,
"epoch": 0.9781576448243114,
"grad_norm": 1.3359375,
"learning_rate": 0.0004913205693936112,
"loss": 6.1414,
"mean_token_accuracy": 0.15199240893125535,
"num_tokens": 19147702.0,
"step": 9785
},
{
"entropy": 6.18320255279541,
"epoch": 0.97865746988554,
"grad_norm": 1.2421875,
"learning_rate": 0.0004913107497399653,
"loss": 6.0955,
"mean_token_accuracy": 0.15147413164377213,
"num_tokens": 19157146.0,
"step": 9790
},
{
"entropy": 6.292190265655518,
"epoch": 0.9791572949467686,
"grad_norm": 1.2265625,
"learning_rate": 0.0004913009246439966,
"loss": 6.201,
"mean_token_accuracy": 0.1434192307293415,
"num_tokens": 19167157.0,
"step": 9795
},
{
"entropy": 6.403326797485351,
"epoch": 0.9796571200079972,
"grad_norm": 1.328125,
"learning_rate": 0.0004912910941059525,
"loss": 6.1692,
"mean_token_accuracy": 0.13740362450480462,
"num_tokens": 19177188.0,
"step": 9800
},
{
"entropy": 6.1945184707641605,
"epoch": 0.9801569450692258,
"grad_norm": 1.328125,
"learning_rate": 0.0004912812581260799,
"loss": 5.9667,
"mean_token_accuracy": 0.15585940182209015,
"num_tokens": 19185940.0,
"step": 9805
},
{
"entropy": 6.1670811653137205,
"epoch": 0.9806567701304544,
"grad_norm": 1.390625,
"learning_rate": 0.0004912714167046265,
"loss": 6.0547,
"mean_token_accuracy": 0.14437031447887422,
"num_tokens": 19194634.0,
"step": 9810
},
{
"entropy": 6.2410194873809814,
"epoch": 0.9811565951916829,
"grad_norm": 1.28125,
"learning_rate": 0.0004912615698418399,
"loss": 6.0531,
"mean_token_accuracy": 0.1570142239332199,
"num_tokens": 19203835.0,
"step": 9815
},
{
"entropy": 6.244063186645508,
"epoch": 0.9816564202529114,
"grad_norm": 1.2734375,
"learning_rate": 0.0004912517175379679,
"loss": 6.0751,
"mean_token_accuracy": 0.15095652863383294,
"num_tokens": 19213458.0,
"step": 9820
},
{
"entropy": 6.275372648239136,
"epoch": 0.98215624531414,
"grad_norm": 1.4453125,
"learning_rate": 0.0004912418597932584,
"loss": 6.1628,
"mean_token_accuracy": 0.14198298379778862,
"num_tokens": 19222494.0,
"step": 9825
},
{
"entropy": 6.239107131958008,
"epoch": 0.9826560703753686,
"grad_norm": 1.6484375,
"learning_rate": 0.0004912319966079592,
"loss": 6.0586,
"mean_token_accuracy": 0.1510770469903946,
"num_tokens": 19232153.0,
"step": 9830
},
{
"entropy": 6.232474040985108,
"epoch": 0.9831558954365972,
"grad_norm": 1.296875,
"learning_rate": 0.0004912221279823187,
"loss": 6.1188,
"mean_token_accuracy": 0.1450786381959915,
"num_tokens": 19241673.0,
"step": 9835
},
{
"entropy": 6.318443775177002,
"epoch": 0.9836557204978258,
"grad_norm": 1.34375,
"learning_rate": 0.0004912122539165851,
"loss": 6.0878,
"mean_token_accuracy": 0.14770561456680298,
"num_tokens": 19250146.0,
"step": 9840
},
{
"entropy": 6.358970689773559,
"epoch": 0.9841555455590544,
"grad_norm": 1.59375,
"learning_rate": 0.0004912023744110068,
"loss": 6.1973,
"mean_token_accuracy": 0.14836482256650924,
"num_tokens": 19259969.0,
"step": 9845
},
{
"entropy": 6.210375022888184,
"epoch": 0.9846553706202829,
"grad_norm": 1.2109375,
"learning_rate": 0.0004911924894658324,
"loss": 6.1255,
"mean_token_accuracy": 0.13817757442593576,
"num_tokens": 19269502.0,
"step": 9850
},
{
"entropy": 6.180826568603516,
"epoch": 0.9851551956815114,
"grad_norm": 1.1796875,
"learning_rate": 0.0004911825990813107,
"loss": 6.0081,
"mean_token_accuracy": 0.15917390957474709,
"num_tokens": 19277965.0,
"step": 9855
},
{
"entropy": 6.2200109481811525,
"epoch": 0.98565502074274,
"grad_norm": 1.40625,
"learning_rate": 0.0004911727032576903,
"loss": 6.0717,
"mean_token_accuracy": 0.15084305107593537,
"num_tokens": 19287618.0,
"step": 9860
},
{
"entropy": 6.27437047958374,
"epoch": 0.9861548458039686,
"grad_norm": 1.2265625,
"learning_rate": 0.0004911628019952203,
"loss": 6.0694,
"mean_token_accuracy": 0.15520483776926994,
"num_tokens": 19297865.0,
"step": 9865
},
{
"entropy": 6.219357442855835,
"epoch": 0.9866546708651972,
"grad_norm": 1.265625,
"learning_rate": 0.0004911528952941499,
"loss": 6.057,
"mean_token_accuracy": 0.14999715387821197,
"num_tokens": 19308957.0,
"step": 9870
},
{
"entropy": 6.273249578475952,
"epoch": 0.9871544959264258,
"grad_norm": 1.28125,
"learning_rate": 0.0004911429831547283,
"loss": 6.1398,
"mean_token_accuracy": 0.14897414892911912,
"num_tokens": 19319310.0,
"step": 9875
},
{
"entropy": 6.235526418685913,
"epoch": 0.9876543209876543,
"grad_norm": 1.3203125,
"learning_rate": 0.0004911330655772047,
"loss": 6.1229,
"mean_token_accuracy": 0.15258189737796785,
"num_tokens": 19329854.0,
"step": 9880
},
{
"entropy": 6.254607200622559,
"epoch": 0.9881541460488829,
"grad_norm": 1.28125,
"learning_rate": 0.000491123142561829,
"loss": 6.0935,
"mean_token_accuracy": 0.14468444660305976,
"num_tokens": 19340327.0,
"step": 9885
},
{
"entropy": 6.221146154403686,
"epoch": 0.9886539711101114,
"grad_norm": 1.25,
"learning_rate": 0.0004911132141088505,
"loss": 6.0007,
"mean_token_accuracy": 0.15526287406682968,
"num_tokens": 19349577.0,
"step": 9890
},
{
"entropy": 6.247826623916626,
"epoch": 0.98915379617134,
"grad_norm": 1.234375,
"learning_rate": 0.0004911032802185192,
"loss": 6.1243,
"mean_token_accuracy": 0.14174894317984582,
"num_tokens": 19359601.0,
"step": 9895
},
{
"entropy": 6.249024820327759,
"epoch": 0.9896536212325686,
"grad_norm": 1.3671875,
"learning_rate": 0.000491093340891085,
"loss": 6.1376,
"mean_token_accuracy": 0.14840798303484917,
"num_tokens": 19368592.0,
"step": 9900
},
{
"entropy": 6.295890235900879,
"epoch": 0.9901534462937972,
"grad_norm": 1.1484375,
"learning_rate": 0.0004910833961267979,
"loss": 6.1158,
"mean_token_accuracy": 0.14280205890536307,
"num_tokens": 19379220.0,
"step": 9905
},
{
"entropy": 6.18821439743042,
"epoch": 0.9906532713550258,
"grad_norm": 1.3515625,
"learning_rate": 0.0004910734459259081,
"loss": 6.0108,
"mean_token_accuracy": 0.15101381316781043,
"num_tokens": 19388339.0,
"step": 9910
},
{
"entropy": 6.186379432678223,
"epoch": 0.9911530964162543,
"grad_norm": 1.3828125,
"learning_rate": 0.0004910634902886662,
"loss": 6.0671,
"mean_token_accuracy": 0.154706159979105,
"num_tokens": 19396873.0,
"step": 9915
},
{
"entropy": 6.24030294418335,
"epoch": 0.9916529214774829,
"grad_norm": 1.2734375,
"learning_rate": 0.0004910535292153224,
"loss": 6.0602,
"mean_token_accuracy": 0.15034509524703027,
"num_tokens": 19406268.0,
"step": 9920
},
{
"entropy": 6.338252305984497,
"epoch": 0.9921527465387114,
"grad_norm": 1.3125,
"learning_rate": 0.0004910435627061273,
"loss": 6.1289,
"mean_token_accuracy": 0.15386831238865853,
"num_tokens": 19415478.0,
"step": 9925
},
{
"entropy": 6.196127462387085,
"epoch": 0.99265257159994,
"grad_norm": 1.2734375,
"learning_rate": 0.0004910335907613318,
"loss": 6.0463,
"mean_token_accuracy": 0.15231262072920798,
"num_tokens": 19424835.0,
"step": 9930
},
{
"entropy": 6.209330606460571,
"epoch": 0.9931523966611686,
"grad_norm": 1.25,
"learning_rate": 0.0004910236133811867,
"loss": 6.0792,
"mean_token_accuracy": 0.1524357818067074,
"num_tokens": 19434147.0,
"step": 9935
},
{
"entropy": 6.321203422546387,
"epoch": 0.9936522217223972,
"grad_norm": 1.4296875,
"learning_rate": 0.0004910136305659432,
"loss": 6.1433,
"mean_token_accuracy": 0.1473076358437538,
"num_tokens": 19444157.0,
"step": 9940
},
{
"entropy": 6.218345499038696,
"epoch": 0.9941520467836257,
"grad_norm": 1.3125,
"learning_rate": 0.0004910036423158523,
"loss": 6.0778,
"mean_token_accuracy": 0.154684891551733,
"num_tokens": 19453859.0,
"step": 9945
},
{
"entropy": 6.220662307739258,
"epoch": 0.9946518718448543,
"grad_norm": 2.3125,
"learning_rate": 0.0004909936486311653,
"loss": 6.1279,
"mean_token_accuracy": 0.1507511630654335,
"num_tokens": 19464191.0,
"step": 9950
},
{
"entropy": 6.216753435134888,
"epoch": 0.9951516969060828,
"grad_norm": 1.3984375,
"learning_rate": 0.0004909836495121336,
"loss": 6.0838,
"mean_token_accuracy": 0.15288073271512986,
"num_tokens": 19473025.0,
"step": 9955
},
{
"entropy": 6.311555194854736,
"epoch": 0.9956515219673114,
"grad_norm": 1.28125,
"learning_rate": 0.0004909736449590091,
"loss": 6.2291,
"mean_token_accuracy": 0.14836422055959703,
"num_tokens": 19483329.0,
"step": 9960
},
{
"entropy": 6.265091037750244,
"epoch": 0.99615134702854,
"grad_norm": 1.4296875,
"learning_rate": 0.000490963634972043,
"loss": 6.1194,
"mean_token_accuracy": 0.14428912550210954,
"num_tokens": 19492756.0,
"step": 9965
},
{
"entropy": 6.248616743087768,
"epoch": 0.9966511720897686,
"grad_norm": 1.40625,
"learning_rate": 0.0004909536195514875,
"loss": 6.1577,
"mean_token_accuracy": 0.14273637533187866,
"num_tokens": 19502363.0,
"step": 9970
},
{
"entropy": 6.30375599861145,
"epoch": 0.9971509971509972,
"grad_norm": 1.453125,
"learning_rate": 0.0004909435986975946,
"loss": 6.1818,
"mean_token_accuracy": 0.14637240916490554,
"num_tokens": 19512180.0,
"step": 9975
},
{
"entropy": 6.343056917190552,
"epoch": 0.9976508222122257,
"grad_norm": 1.265625,
"learning_rate": 0.0004909335724106162,
"loss": 6.1829,
"mean_token_accuracy": 0.1457211971282959,
"num_tokens": 19521819.0,
"step": 9980
},
{
"entropy": 6.246092462539673,
"epoch": 0.9981506472734543,
"grad_norm": 1.34375,
"learning_rate": 0.0004909235406908047,
"loss": 6.1158,
"mean_token_accuracy": 0.14938534647226334,
"num_tokens": 19531960.0,
"step": 9985
},
{
"entropy": 6.198645114898682,
"epoch": 0.9986504723346828,
"grad_norm": 1.5078125,
"learning_rate": 0.0004909135035384126,
"loss": 6.0848,
"mean_token_accuracy": 0.15256978422403336,
"num_tokens": 19542278.0,
"step": 9990
},
{
"entropy": 6.292979001998901,
"epoch": 0.9991502973959114,
"grad_norm": 1.234375,
"learning_rate": 0.0004909034609536922,
"loss": 6.1316,
"mean_token_accuracy": 0.14888818711042404,
"num_tokens": 19552740.0,
"step": 9995
},
{
"entropy": 6.264652347564697,
"epoch": 0.99965012245714,
"grad_norm": 2.65625,
"learning_rate": 0.0004908934129368963,
"loss": 6.0738,
"mean_token_accuracy": 0.15019856691360473,
"num_tokens": 19563174.0,
"step": 10000
},
{
"entropy": 6.2063873079088,
"epoch": 1.0000999650122457,
"grad_norm": 1.3203125,
"learning_rate": 0.0004908833594882777,
"loss": 6.0633,
"mean_token_accuracy": 0.15104605505863825,
"num_tokens": 19571268.0,
"step": 10005
},
{
"entropy": 6.232393836975097,
"epoch": 1.0005997900734742,
"grad_norm": 1.2734375,
"learning_rate": 0.0004908733006080893,
"loss": 5.9542,
"mean_token_accuracy": 0.15942276418209075,
"num_tokens": 19580615.0,
"step": 10010
},
{
"entropy": 6.238720989227295,
"epoch": 1.001099615134703,
"grad_norm": 1.46875,
"learning_rate": 0.0004908632362965842,
"loss": 6.0111,
"mean_token_accuracy": 0.15403904542326927,
"num_tokens": 19590983.0,
"step": 10015
},
{
"entropy": 6.223530387878418,
"epoch": 1.0015994401959314,
"grad_norm": 1.265625,
"learning_rate": 0.0004908531665540158,
"loss": 5.9916,
"mean_token_accuracy": 0.15515465661883354,
"num_tokens": 19600440.0,
"step": 10020
},
{
"entropy": 6.174214029312134,
"epoch": 1.00209926525716,
"grad_norm": 1.2890625,
"learning_rate": 0.000490843091380637,
"loss": 6.027,
"mean_token_accuracy": 0.15265021175146104,
"num_tokens": 19610779.0,
"step": 10025
},
{
"entropy": 6.2175719261169435,
"epoch": 1.0025990903183886,
"grad_norm": 1.4296875,
"learning_rate": 0.0004908330107767018,
"loss": 6.0422,
"mean_token_accuracy": 0.14577231854200362,
"num_tokens": 19620729.0,
"step": 10030
},
{
"entropy": 6.2749419689178465,
"epoch": 1.003098915379617,
"grad_norm": 1.328125,
"learning_rate": 0.0004908229247424633,
"loss": 6.017,
"mean_token_accuracy": 0.15350845009088515,
"num_tokens": 19630493.0,
"step": 10035
},
{
"entropy": 6.247971391677856,
"epoch": 1.0035987404408457,
"grad_norm": 1.21875,
"learning_rate": 0.0004908128332781758,
"loss": 6.0068,
"mean_token_accuracy": 0.15064608454704284,
"num_tokens": 19640672.0,
"step": 10040
},
{
"entropy": 6.244055938720703,
"epoch": 1.0040985655020742,
"grad_norm": 1.2734375,
"learning_rate": 0.0004908027363840928,
"loss": 6.0266,
"mean_token_accuracy": 0.15170393139123917,
"num_tokens": 19651009.0,
"step": 10045
},
{
"entropy": 6.238856267929077,
"epoch": 1.004598390563303,
"grad_norm": 3.78125,
"learning_rate": 0.0004907926340604686,
"loss": 6.0609,
"mean_token_accuracy": 0.1516696944832802,
"num_tokens": 19661422.0,
"step": 10050
},
{
"entropy": 6.234027481079101,
"epoch": 1.0050982156245314,
"grad_norm": 1.796875,
"learning_rate": 0.0004907825263075573,
"loss": 6.0173,
"mean_token_accuracy": 0.14826187938451768,
"num_tokens": 19671039.0,
"step": 10055
},
{
"entropy": 6.220024871826172,
"epoch": 1.00559804068576,
"grad_norm": 1.515625,
"learning_rate": 0.0004907724131256129,
"loss": 6.0105,
"mean_token_accuracy": 0.14830300211906433,
"num_tokens": 19680385.0,
"step": 10060
},
{
"entropy": 6.250578784942627,
"epoch": 1.0060978657469886,
"grad_norm": 1.546875,
"learning_rate": 0.0004907622945148903,
"loss": 6.0703,
"mean_token_accuracy": 0.14842513725161552,
"num_tokens": 19690626.0,
"step": 10065
},
{
"entropy": 6.26675443649292,
"epoch": 1.006597690808217,
"grad_norm": 1.3046875,
"learning_rate": 0.0004907521704756438,
"loss": 6.0142,
"mean_token_accuracy": 0.14238255470991135,
"num_tokens": 19700234.0,
"step": 10070
},
{
"entropy": 6.253324270248413,
"epoch": 1.0070975158694457,
"grad_norm": 1.2890625,
"learning_rate": 0.0004907420410081284,
"loss": 6.012,
"mean_token_accuracy": 0.15270191207528114,
"num_tokens": 19708986.0,
"step": 10075
},
{
"entropy": 6.190138483047486,
"epoch": 1.0075973409306742,
"grad_norm": 1.7265625,
"learning_rate": 0.0004907319061125986,
"loss": 6.0593,
"mean_token_accuracy": 0.14822639375925065,
"num_tokens": 19718292.0,
"step": 10080
},
{
"entropy": 6.131137800216675,
"epoch": 1.008097165991903,
"grad_norm": 1.3046875,
"learning_rate": 0.0004907217657893096,
"loss": 5.9624,
"mean_token_accuracy": 0.15677581131458282,
"num_tokens": 19727563.0,
"step": 10085
},
{
"entropy": 6.2391736030578615,
"epoch": 1.0085969910531314,
"grad_norm": 1.4453125,
"learning_rate": 0.0004907116200385165,
"loss": 6.0164,
"mean_token_accuracy": 0.14878358393907548,
"num_tokens": 19737649.0,
"step": 10090
},
{
"entropy": 6.274553918838501,
"epoch": 1.00909681611436,
"grad_norm": 2.453125,
"learning_rate": 0.0004907014688604745,
"loss": 6.0487,
"mean_token_accuracy": 0.14974594712257386,
"num_tokens": 19746911.0,
"step": 10095
},
{
"entropy": 6.12417688369751,
"epoch": 1.0095966411755886,
"grad_norm": 1.40625,
"learning_rate": 0.0004906913122554391,
"loss": 6.0357,
"mean_token_accuracy": 0.1512255534529686,
"num_tokens": 19757144.0,
"step": 10100
},
{
"entropy": 6.188208818435669,
"epoch": 1.010096466236817,
"grad_norm": 1.3984375,
"learning_rate": 0.0004906811502236657,
"loss": 5.9563,
"mean_token_accuracy": 0.15488606095314025,
"num_tokens": 19766422.0,
"step": 10105
},
{
"entropy": 6.288571739196778,
"epoch": 1.0105962912980457,
"grad_norm": 1.546875,
"learning_rate": 0.0004906709827654101,
"loss": 6.0183,
"mean_token_accuracy": 0.15200354978442193,
"num_tokens": 19774711.0,
"step": 10110
},
{
"entropy": 6.228627681732178,
"epoch": 1.0110961163592742,
"grad_norm": 1.4765625,
"learning_rate": 0.0004906608098809281,
"loss": 6.0166,
"mean_token_accuracy": 0.15119887739419938,
"num_tokens": 19784347.0,
"step": 10115
},
{
"entropy": 6.216867923736572,
"epoch": 1.011595941420503,
"grad_norm": 1.3671875,
"learning_rate": 0.0004906506315704756,
"loss": 6.1396,
"mean_token_accuracy": 0.1457881286740303,
"num_tokens": 19796100.0,
"step": 10120
},
{
"entropy": 6.213804864883423,
"epoch": 1.0120957664817314,
"grad_norm": 1.2265625,
"learning_rate": 0.0004906404478343087,
"loss": 5.9726,
"mean_token_accuracy": 0.1545696146786213,
"num_tokens": 19805942.0,
"step": 10125
},
{
"entropy": 6.2151491165161135,
"epoch": 1.0125955915429599,
"grad_norm": 1.3046875,
"learning_rate": 0.0004906302586726837,
"loss": 5.9497,
"mean_token_accuracy": 0.1608385443687439,
"num_tokens": 19814707.0,
"step": 10130
},
{
"entropy": 6.171500635147095,
"epoch": 1.0130954166041886,
"grad_norm": 1.90625,
"learning_rate": 0.0004906200640858567,
"loss": 6.0763,
"mean_token_accuracy": 0.1448494404554367,
"num_tokens": 19825061.0,
"step": 10135
},
{
"entropy": 6.216320323944092,
"epoch": 1.013595241665417,
"grad_norm": 1.46875,
"learning_rate": 0.0004906098640740846,
"loss": 6.0204,
"mean_token_accuracy": 0.15389695912599563,
"num_tokens": 19834572.0,
"step": 10140
},
{
"entropy": 6.281344985961914,
"epoch": 1.0140950667266457,
"grad_norm": 1.265625,
"learning_rate": 0.0004905996586376236,
"loss": 6.0519,
"mean_token_accuracy": 0.1448914423584938,
"num_tokens": 19844691.0,
"step": 10145
},
{
"entropy": 6.169038724899292,
"epoch": 1.0145948917878742,
"grad_norm": 1.375,
"learning_rate": 0.0004905894477767308,
"loss": 5.9251,
"mean_token_accuracy": 0.157583612203598,
"num_tokens": 19854806.0,
"step": 10150
},
{
"entropy": 6.229771947860717,
"epoch": 1.015094716849103,
"grad_norm": 1.34375,
"learning_rate": 0.0004905792314916629,
"loss": 6.0357,
"mean_token_accuracy": 0.15063023269176484,
"num_tokens": 19863943.0,
"step": 10155
},
{
"entropy": 6.25595064163208,
"epoch": 1.0155945419103314,
"grad_norm": 1.53125,
"learning_rate": 0.0004905690097826769,
"loss": 6.0342,
"mean_token_accuracy": 0.1471012368798256,
"num_tokens": 19873417.0,
"step": 10160
},
{
"entropy": 6.181386232376099,
"epoch": 1.0160943669715599,
"grad_norm": 1.203125,
"learning_rate": 0.0004905587826500303,
"loss": 5.9824,
"mean_token_accuracy": 0.1477060340344906,
"num_tokens": 19883088.0,
"step": 10165
},
{
"entropy": 6.240792942047119,
"epoch": 1.0165941920327886,
"grad_norm": 1.1953125,
"learning_rate": 0.0004905485500939801,
"loss": 6.017,
"mean_token_accuracy": 0.15172144919633865,
"num_tokens": 19893851.0,
"step": 10170
},
{
"entropy": 6.1961061477661135,
"epoch": 1.017094017094017,
"grad_norm": 1.2890625,
"learning_rate": 0.0004905383121147838,
"loss": 5.975,
"mean_token_accuracy": 0.14715945199131966,
"num_tokens": 19904243.0,
"step": 10175
},
{
"entropy": 6.211069011688233,
"epoch": 1.0175938421552457,
"grad_norm": 1.296875,
"learning_rate": 0.0004905280687126991,
"loss": 6.1422,
"mean_token_accuracy": 0.14917925298213958,
"num_tokens": 19914825.0,
"step": 10180
},
{
"entropy": 6.208258771896363,
"epoch": 1.0180936672164742,
"grad_norm": 1.46875,
"learning_rate": 0.0004905178198879837,
"loss": 6.0314,
"mean_token_accuracy": 0.1490439787507057,
"num_tokens": 19925455.0,
"step": 10185
},
{
"entropy": 6.183230209350586,
"epoch": 1.018593492277703,
"grad_norm": 1.3984375,
"learning_rate": 0.0004905075656408953,
"loss": 6.0414,
"mean_token_accuracy": 0.1503809280693531,
"num_tokens": 19935810.0,
"step": 10190
},
{
"entropy": 6.2322876930236815,
"epoch": 1.0190933173389314,
"grad_norm": 1.4375,
"learning_rate": 0.000490497305971692,
"loss": 6.0094,
"mean_token_accuracy": 0.1514083370566368,
"num_tokens": 19945508.0,
"step": 10195
},
{
"entropy": 6.1991111755371096,
"epoch": 1.0195931424001599,
"grad_norm": 1.4375,
"learning_rate": 0.000490487040880632,
"loss": 5.9498,
"mean_token_accuracy": 0.14916113317012786,
"num_tokens": 19955148.0,
"step": 10200
},
{
"entropy": 6.083432722091675,
"epoch": 1.0200929674613886,
"grad_norm": 1.265625,
"learning_rate": 0.0004904767703679735,
"loss": 5.9694,
"mean_token_accuracy": 0.1529839128255844,
"num_tokens": 19965607.0,
"step": 10205
},
{
"entropy": 6.199935722351074,
"epoch": 1.020592792522617,
"grad_norm": 1.3671875,
"learning_rate": 0.0004904664944339748,
"loss": 6.0094,
"mean_token_accuracy": 0.15225431248545646,
"num_tokens": 19976598.0,
"step": 10210
},
{
"entropy": 6.219248676300049,
"epoch": 1.0210926175838457,
"grad_norm": 1.390625,
"learning_rate": 0.0004904562130788947,
"loss": 5.9254,
"mean_token_accuracy": 0.15705513060092927,
"num_tokens": 19986183.0,
"step": 10215
},
{
"entropy": 6.234408330917359,
"epoch": 1.0215924426450742,
"grad_norm": 1.1328125,
"learning_rate": 0.0004904459263029916,
"loss": 6.0236,
"mean_token_accuracy": 0.15483262985944748,
"num_tokens": 19995930.0,
"step": 10220
},
{
"entropy": 6.254371213912964,
"epoch": 1.0220922677063027,
"grad_norm": 1.265625,
"learning_rate": 0.0004904356341065245,
"loss": 6.114,
"mean_token_accuracy": 0.14660026878118515,
"num_tokens": 20005826.0,
"step": 10225
},
{
"entropy": 6.203324651718139,
"epoch": 1.0225920927675314,
"grad_norm": 1.40625,
"learning_rate": 0.0004904253364897521,
"loss": 6.0415,
"mean_token_accuracy": 0.15484552532434465,
"num_tokens": 20015057.0,
"step": 10230
},
{
"entropy": 6.275355815887451,
"epoch": 1.0230919178287599,
"grad_norm": 1.15625,
"learning_rate": 0.0004904150334529339,
"loss": 6.0039,
"mean_token_accuracy": 0.14145815819501878,
"num_tokens": 20024181.0,
"step": 10235
},
{
"entropy": 6.20418791770935,
"epoch": 1.0235917428899886,
"grad_norm": 1.296875,
"learning_rate": 0.0004904047249963289,
"loss": 6.0136,
"mean_token_accuracy": 0.15010612159967424,
"num_tokens": 20033453.0,
"step": 10240
},
{
"entropy": 6.191885232925415,
"epoch": 1.024091567951217,
"grad_norm": 1.4140625,
"learning_rate": 0.0004903944111201964,
"loss": 6.0341,
"mean_token_accuracy": 0.14934864044189453,
"num_tokens": 20043324.0,
"step": 10245
},
{
"entropy": 6.186628770828247,
"epoch": 1.0245913930124457,
"grad_norm": 1.4375,
"learning_rate": 0.0004903840918247958,
"loss": 6.0387,
"mean_token_accuracy": 0.15226204469799995,
"num_tokens": 20053010.0,
"step": 10250
},
{
"entropy": 6.261638259887695,
"epoch": 1.0250912180736742,
"grad_norm": 1.25,
"learning_rate": 0.000490373767110387,
"loss": 5.998,
"mean_token_accuracy": 0.1554411008954048,
"num_tokens": 20063457.0,
"step": 10255
},
{
"entropy": 6.268414926528931,
"epoch": 1.0255910431349027,
"grad_norm": 1.3671875,
"learning_rate": 0.0004903634369772296,
"loss": 6.027,
"mean_token_accuracy": 0.15048531740903853,
"num_tokens": 20073479.0,
"step": 10260
},
{
"entropy": 6.209446239471435,
"epoch": 1.0260908681961314,
"grad_norm": 1.296875,
"learning_rate": 0.0004903531014255835,
"loss": 6.0275,
"mean_token_accuracy": 0.14842105507850648,
"num_tokens": 20082711.0,
"step": 10265
},
{
"entropy": 6.161308097839355,
"epoch": 1.0265906932573599,
"grad_norm": 1.296875,
"learning_rate": 0.0004903427604557089,
"loss": 5.9931,
"mean_token_accuracy": 0.1566895477473736,
"num_tokens": 20092535.0,
"step": 10270
},
{
"entropy": 6.219944286346435,
"epoch": 1.0270905183185886,
"grad_norm": 1.21875,
"learning_rate": 0.0004903324140678658,
"loss": 5.969,
"mean_token_accuracy": 0.15915192663669586,
"num_tokens": 20101564.0,
"step": 10275
},
{
"entropy": 6.080531597137451,
"epoch": 1.027590343379817,
"grad_norm": 1.34375,
"learning_rate": 0.0004903220622623146,
"loss": 5.8839,
"mean_token_accuracy": 0.16180048733949662,
"num_tokens": 20110361.0,
"step": 10280
},
{
"entropy": 6.205290794372559,
"epoch": 1.0280901684410457,
"grad_norm": 1.3359375,
"learning_rate": 0.0004903117050393157,
"loss": 5.9714,
"mean_token_accuracy": 0.1575970396399498,
"num_tokens": 20119816.0,
"step": 10285
},
{
"entropy": 6.224004745483398,
"epoch": 1.0285899935022742,
"grad_norm": 1.375,
"learning_rate": 0.0004903013423991296,
"loss": 6.0305,
"mean_token_accuracy": 0.15508941411972046,
"num_tokens": 20129246.0,
"step": 10290
},
{
"entropy": 6.230030488967896,
"epoch": 1.0290898185635027,
"grad_norm": 1.3046875,
"learning_rate": 0.0004902909743420173,
"loss": 6.0114,
"mean_token_accuracy": 0.15104206651449203,
"num_tokens": 20140029.0,
"step": 10295
},
{
"entropy": 6.171510219573975,
"epoch": 1.0295896436247314,
"grad_norm": 1.3671875,
"learning_rate": 0.0004902806008682394,
"loss": 5.9213,
"mean_token_accuracy": 0.1589931681752205,
"num_tokens": 20150684.0,
"step": 10300
},
{
"entropy": 6.208301639556884,
"epoch": 1.0300894686859599,
"grad_norm": 1.203125,
"learning_rate": 0.000490270221978057,
"loss": 6.0154,
"mean_token_accuracy": 0.15298869758844375,
"num_tokens": 20160007.0,
"step": 10305
},
{
"entropy": 6.283911991119385,
"epoch": 1.0305892937471886,
"grad_norm": 1.2734375,
"learning_rate": 0.0004902598376717312,
"loss": 6.0973,
"mean_token_accuracy": 0.14645808115601539,
"num_tokens": 20170512.0,
"step": 10310
},
{
"entropy": 6.1785553932189945,
"epoch": 1.031089118808417,
"grad_norm": 1.3671875,
"learning_rate": 0.0004902494479495233,
"loss": 5.9764,
"mean_token_accuracy": 0.1595336154103279,
"num_tokens": 20181954.0,
"step": 10315
},
{
"entropy": 6.168446111679077,
"epoch": 1.0315889438696457,
"grad_norm": 1.265625,
"learning_rate": 0.0004902390528116946,
"loss": 5.9889,
"mean_token_accuracy": 0.15001600831747056,
"num_tokens": 20191780.0,
"step": 10320
},
{
"entropy": 6.200594520568847,
"epoch": 1.0320887689308742,
"grad_norm": 1.28125,
"learning_rate": 0.0004902286522585068,
"loss": 6.0616,
"mean_token_accuracy": 0.14833675771951677,
"num_tokens": 20201646.0,
"step": 10325
},
{
"entropy": 6.217910385131836,
"epoch": 1.0325885939921027,
"grad_norm": 1.4375,
"learning_rate": 0.0004902182462902215,
"loss": 6.0482,
"mean_token_accuracy": 0.15123704597353935,
"num_tokens": 20210943.0,
"step": 10330
},
{
"entropy": 6.263118553161621,
"epoch": 1.0330884190533314,
"grad_norm": 1.4609375,
"learning_rate": 0.0004902078349071004,
"loss": 6.0208,
"mean_token_accuracy": 0.1466373957693577,
"num_tokens": 20219901.0,
"step": 10335
},
{
"entropy": 6.228824520111084,
"epoch": 1.0335882441145599,
"grad_norm": 1.359375,
"learning_rate": 0.0004901974181094057,
"loss": 6.0035,
"mean_token_accuracy": 0.14916652366518973,
"num_tokens": 20229630.0,
"step": 10340
},
{
"entropy": 6.251888084411621,
"epoch": 1.0340880691757885,
"grad_norm": 1.234375,
"learning_rate": 0.0004901869958973991,
"loss": 6.0552,
"mean_token_accuracy": 0.14913733750581742,
"num_tokens": 20239932.0,
"step": 10345
},
{
"entropy": 6.268005466461181,
"epoch": 1.034587894237017,
"grad_norm": 1.296875,
"learning_rate": 0.0004901765682713432,
"loss": 5.9677,
"mean_token_accuracy": 0.151399664580822,
"num_tokens": 20248863.0,
"step": 10350
},
{
"entropy": 6.136422920227051,
"epoch": 1.0350877192982457,
"grad_norm": 1.265625,
"learning_rate": 0.0004901661352315003,
"loss": 5.8774,
"mean_token_accuracy": 0.15820712298154832,
"num_tokens": 20257916.0,
"step": 10355
},
{
"entropy": 6.166300964355469,
"epoch": 1.0355875443594742,
"grad_norm": 1.265625,
"learning_rate": 0.0004901556967781327,
"loss": 6.0053,
"mean_token_accuracy": 0.15192359387874604,
"num_tokens": 20267579.0,
"step": 10360
},
{
"entropy": 6.221320056915284,
"epoch": 1.0360873694207027,
"grad_norm": 1.8515625,
"learning_rate": 0.0004901452529115031,
"loss": 6.053,
"mean_token_accuracy": 0.1449980169534683,
"num_tokens": 20278909.0,
"step": 10365
},
{
"entropy": 6.228009033203125,
"epoch": 1.0365871944819314,
"grad_norm": 1.2578125,
"learning_rate": 0.0004901348036318743,
"loss": 6.0021,
"mean_token_accuracy": 0.1474953457713127,
"num_tokens": 20288933.0,
"step": 10370
},
{
"entropy": 6.25818452835083,
"epoch": 1.0370870195431598,
"grad_norm": 1.1796875,
"learning_rate": 0.0004901243489395093,
"loss": 6.0188,
"mean_token_accuracy": 0.142359459400177,
"num_tokens": 20298329.0,
"step": 10375
},
{
"entropy": 6.209525299072266,
"epoch": 1.0375868446043885,
"grad_norm": 1.2265625,
"learning_rate": 0.000490113888834671,
"loss": 6.0595,
"mean_token_accuracy": 0.15545681565999986,
"num_tokens": 20308742.0,
"step": 10380
},
{
"entropy": 6.078628826141357,
"epoch": 1.038086669665617,
"grad_norm": 1.3359375,
"learning_rate": 0.0004901034233176227,
"loss": 5.8697,
"mean_token_accuracy": 0.16828331351280212,
"num_tokens": 20318379.0,
"step": 10385
},
{
"entropy": 6.185838270187378,
"epoch": 1.0385864947268455,
"grad_norm": 1.2890625,
"learning_rate": 0.0004900929523886274,
"loss": 5.9431,
"mean_token_accuracy": 0.1534660667181015,
"num_tokens": 20328127.0,
"step": 10390
},
{
"entropy": 6.208504390716553,
"epoch": 1.0390863197880742,
"grad_norm": 1.2421875,
"learning_rate": 0.000490082476047949,
"loss": 6.0128,
"mean_token_accuracy": 0.15713909715414048,
"num_tokens": 20338562.0,
"step": 10395
},
{
"entropy": 6.223556089401245,
"epoch": 1.0395861448493027,
"grad_norm": 1.296875,
"learning_rate": 0.0004900719942958506,
"loss": 5.9656,
"mean_token_accuracy": 0.15980771481990813,
"num_tokens": 20346984.0,
"step": 10400
},
{
"entropy": 6.175549173355103,
"epoch": 1.0400859699105314,
"grad_norm": 1.1484375,
"learning_rate": 0.0004900615071325963,
"loss": 5.9839,
"mean_token_accuracy": 0.15786415189504624,
"num_tokens": 20356666.0,
"step": 10405
},
{
"entropy": 6.2009861946105955,
"epoch": 1.0405857949717598,
"grad_norm": 1.40625,
"learning_rate": 0.00049005101455845,
"loss": 5.9634,
"mean_token_accuracy": 0.15166688710451126,
"num_tokens": 20365834.0,
"step": 10410
},
{
"entropy": 6.219707012176514,
"epoch": 1.0410856200329885,
"grad_norm": 1.28125,
"learning_rate": 0.0004900405165736753,
"loss": 6.0495,
"mean_token_accuracy": 0.1460423782467842,
"num_tokens": 20377184.0,
"step": 10415
},
{
"entropy": 6.1475263118743895,
"epoch": 1.041585445094217,
"grad_norm": 1.6796875,
"learning_rate": 0.0004900300131785365,
"loss": 5.9767,
"mean_token_accuracy": 0.15538606345653533,
"num_tokens": 20387059.0,
"step": 10420
},
{
"entropy": 6.238153600692749,
"epoch": 1.0420852701554455,
"grad_norm": 1.4765625,
"learning_rate": 0.000490019504373298,
"loss": 6.0851,
"mean_token_accuracy": 0.1474063776433468,
"num_tokens": 20397162.0,
"step": 10425
},
{
"entropy": 6.14004487991333,
"epoch": 1.0425850952166742,
"grad_norm": 1.2109375,
"learning_rate": 0.0004900089901582241,
"loss": 5.9125,
"mean_token_accuracy": 0.15710821002721786,
"num_tokens": 20407755.0,
"step": 10430
},
{
"entropy": 6.217952919006348,
"epoch": 1.0430849202779027,
"grad_norm": 1.3125,
"learning_rate": 0.0004899984705335792,
"loss": 6.0208,
"mean_token_accuracy": 0.15002369731664658,
"num_tokens": 20417729.0,
"step": 10435
},
{
"entropy": 6.2227928161621096,
"epoch": 1.0435847453391314,
"grad_norm": 1.234375,
"learning_rate": 0.0004899879454996282,
"loss": 6.018,
"mean_token_accuracy": 0.15074368119239806,
"num_tokens": 20428523.0,
"step": 10440
},
{
"entropy": 6.113245487213135,
"epoch": 1.0440845704003598,
"grad_norm": 1.234375,
"learning_rate": 0.0004899774150566358,
"loss": 5.9576,
"mean_token_accuracy": 0.1617699906229973,
"num_tokens": 20438667.0,
"step": 10445
},
{
"entropy": 6.2017255306243895,
"epoch": 1.0445843954615885,
"grad_norm": 1.25,
"learning_rate": 0.000489966879204867,
"loss": 6.0098,
"mean_token_accuracy": 0.14654252529144288,
"num_tokens": 20449568.0,
"step": 10450
},
{
"entropy": 6.210640621185303,
"epoch": 1.045084220522817,
"grad_norm": 1.3828125,
"learning_rate": 0.0004899563379445869,
"loss": 5.9826,
"mean_token_accuracy": 0.15381477624177933,
"num_tokens": 20458665.0,
"step": 10455
},
{
"entropy": 6.176488447189331,
"epoch": 1.0455840455840455,
"grad_norm": 1.2890625,
"learning_rate": 0.0004899457912760605,
"loss": 5.9248,
"mean_token_accuracy": 0.1588617593050003,
"num_tokens": 20468587.0,
"step": 10460
},
{
"entropy": 6.173476934432983,
"epoch": 1.0460838706452742,
"grad_norm": 2.546875,
"learning_rate": 0.0004899352391995533,
"loss": 5.951,
"mean_token_accuracy": 0.15408904403448104,
"num_tokens": 20479186.0,
"step": 10465
},
{
"entropy": 6.28180079460144,
"epoch": 1.0465836957065027,
"grad_norm": 1.2734375,
"learning_rate": 0.0004899246817153309,
"loss": 6.054,
"mean_token_accuracy": 0.14951284378767013,
"num_tokens": 20488035.0,
"step": 10470
},
{
"entropy": 6.236543655395508,
"epoch": 1.0470835207677314,
"grad_norm": 1.359375,
"learning_rate": 0.0004899141188236587,
"loss": 6.0141,
"mean_token_accuracy": 0.14833798184990882,
"num_tokens": 20498189.0,
"step": 10475
},
{
"entropy": 6.244407272338867,
"epoch": 1.0475833458289598,
"grad_norm": 1.3671875,
"learning_rate": 0.0004899035505248027,
"loss": 5.9661,
"mean_token_accuracy": 0.15517472326755524,
"num_tokens": 20508199.0,
"step": 10480
},
{
"entropy": 6.223096179962158,
"epoch": 1.0480831708901883,
"grad_norm": 1.390625,
"learning_rate": 0.0004898929768190286,
"loss": 6.1192,
"mean_token_accuracy": 0.14485445469617844,
"num_tokens": 20517155.0,
"step": 10485
},
{
"entropy": 6.180911302566528,
"epoch": 1.048582995951417,
"grad_norm": 1.1796875,
"learning_rate": 0.0004898823977066024,
"loss": 5.9759,
"mean_token_accuracy": 0.155949904024601,
"num_tokens": 20526559.0,
"step": 10490
},
{
"entropy": 6.211443281173706,
"epoch": 1.0490828210126455,
"grad_norm": 1.265625,
"learning_rate": 0.0004898718131877906,
"loss": 6.059,
"mean_token_accuracy": 0.14521945565938948,
"num_tokens": 20536299.0,
"step": 10495
},
{
"entropy": 6.166639709472657,
"epoch": 1.0495826460738742,
"grad_norm": 1.2265625,
"learning_rate": 0.0004898612232628591,
"loss": 5.8651,
"mean_token_accuracy": 0.1686046227812767,
"num_tokens": 20545290.0,
"step": 10500
},
{
"entropy": 6.227097749710083,
"epoch": 1.0500824711351027,
"grad_norm": 1.2421875,
"learning_rate": 0.0004898506279320745,
"loss": 5.9984,
"mean_token_accuracy": 0.15078563019633293,
"num_tokens": 20554691.0,
"step": 10505
},
{
"entropy": 6.168217563629151,
"epoch": 1.0505822961963314,
"grad_norm": 1.2578125,
"learning_rate": 0.0004898400271957034,
"loss": 6.0044,
"mean_token_accuracy": 0.1502242401242256,
"num_tokens": 20564595.0,
"step": 10510
},
{
"entropy": 6.148492622375488,
"epoch": 1.0510821212575598,
"grad_norm": 1.15625,
"learning_rate": 0.0004898294210540126,
"loss": 5.9346,
"mean_token_accuracy": 0.15621903389692307,
"num_tokens": 20574174.0,
"step": 10515
},
{
"entropy": 6.212651681900025,
"epoch": 1.0515819463187883,
"grad_norm": 1.296875,
"learning_rate": 0.0004898188095072688,
"loss": 5.9515,
"mean_token_accuracy": 0.16079924553632735,
"num_tokens": 20583666.0,
"step": 10520
},
{
"entropy": 6.260073328018189,
"epoch": 1.052081771380017,
"grad_norm": 1.25,
"learning_rate": 0.000489808192555739,
"loss": 6.0718,
"mean_token_accuracy": 0.14773667305707933,
"num_tokens": 20594040.0,
"step": 10525
},
{
"entropy": 6.239969968795776,
"epoch": 1.0525815964412455,
"grad_norm": 1.1484375,
"learning_rate": 0.0004897975701996903,
"loss": 6.0859,
"mean_token_accuracy": 0.1449655145406723,
"num_tokens": 20605329.0,
"step": 10530
},
{
"entropy": 6.113816165924073,
"epoch": 1.0530814215024742,
"grad_norm": 1.2421875,
"learning_rate": 0.0004897869424393902,
"loss": 5.9011,
"mean_token_accuracy": 0.15849124789237976,
"num_tokens": 20615107.0,
"step": 10535
},
{
"entropy": 6.148946714401245,
"epoch": 1.0535812465637027,
"grad_norm": 1.296875,
"learning_rate": 0.0004897763092751057,
"loss": 5.943,
"mean_token_accuracy": 0.15736338645219802,
"num_tokens": 20624636.0,
"step": 10540
},
{
"entropy": 6.224472904205323,
"epoch": 1.0540810716249314,
"grad_norm": 1.203125,
"learning_rate": 0.0004897656707071045,
"loss": 5.9333,
"mean_token_accuracy": 0.15725087225437165,
"num_tokens": 20634541.0,
"step": 10545
},
{
"entropy": 6.167675495147705,
"epoch": 1.0545808966861598,
"grad_norm": 1.2734375,
"learning_rate": 0.0004897550267356545,
"loss": 6.0043,
"mean_token_accuracy": 0.15720853358507156,
"num_tokens": 20644941.0,
"step": 10550
},
{
"entropy": 6.206024074554444,
"epoch": 1.0550807217473883,
"grad_norm": 1.2265625,
"learning_rate": 0.0004897443773610231,
"loss": 5.9177,
"mean_token_accuracy": 0.16083155423402787,
"num_tokens": 20653609.0,
"step": 10555
},
{
"entropy": 6.173372459411621,
"epoch": 1.055580546808617,
"grad_norm": 1.21875,
"learning_rate": 0.0004897337225834785,
"loss": 5.9299,
"mean_token_accuracy": 0.15974637418985366,
"num_tokens": 20663302.0,
"step": 10560
},
{
"entropy": 6.085679197311402,
"epoch": 1.0560803718698455,
"grad_norm": 1.8203125,
"learning_rate": 0.0004897230624032888,
"loss": 5.8477,
"mean_token_accuracy": 0.16446128487586975,
"num_tokens": 20673785.0,
"step": 10565
},
{
"entropy": 6.16916971206665,
"epoch": 1.0565801969310742,
"grad_norm": 1.2734375,
"learning_rate": 0.0004897123968207219,
"loss": 5.9182,
"mean_token_accuracy": 0.15650865957140922,
"num_tokens": 20683156.0,
"step": 10570
},
{
"entropy": 6.206054067611694,
"epoch": 1.0570800219923027,
"grad_norm": 1.3984375,
"learning_rate": 0.0004897017258360465,
"loss": 6.0008,
"mean_token_accuracy": 0.15478356480598449,
"num_tokens": 20692153.0,
"step": 10575
},
{
"entropy": 6.216446590423584,
"epoch": 1.0575798470535314,
"grad_norm": 1.2421875,
"learning_rate": 0.0004896910494495308,
"loss": 6.0069,
"mean_token_accuracy": 0.154074514657259,
"num_tokens": 20702343.0,
"step": 10580
},
{
"entropy": 6.090823841094971,
"epoch": 1.0580796721147598,
"grad_norm": 1.3359375,
"learning_rate": 0.0004896803676614436,
"loss": 5.836,
"mean_token_accuracy": 0.17420537769794464,
"num_tokens": 20712866.0,
"step": 10585
},
{
"entropy": 6.191429710388183,
"epoch": 1.0585794971759883,
"grad_norm": 1.8671875,
"learning_rate": 0.0004896696804720536,
"loss": 6.1025,
"mean_token_accuracy": 0.14527041912078859,
"num_tokens": 20722679.0,
"step": 10590
},
{
"entropy": 6.277051115036011,
"epoch": 1.059079322237217,
"grad_norm": 1.3125,
"learning_rate": 0.0004896589878816297,
"loss": 6.0793,
"mean_token_accuracy": 0.15211109071969986,
"num_tokens": 20732177.0,
"step": 10595
},
{
"entropy": 6.262920618057251,
"epoch": 1.0595791472984455,
"grad_norm": 1.296875,
"learning_rate": 0.0004896482898904409,
"loss": 6.0768,
"mean_token_accuracy": 0.14589622914791106,
"num_tokens": 20742900.0,
"step": 10600
},
{
"entropy": 6.156751203536987,
"epoch": 1.0600789723596742,
"grad_norm": 1.3125,
"learning_rate": 0.0004896375864987563,
"loss": 5.8896,
"mean_token_accuracy": 0.1574319362640381,
"num_tokens": 20752039.0,
"step": 10605
},
{
"entropy": 6.14383716583252,
"epoch": 1.0605787974209027,
"grad_norm": 1.25,
"learning_rate": 0.0004896268777068453,
"loss": 5.9322,
"mean_token_accuracy": 0.15913830548524857,
"num_tokens": 20760352.0,
"step": 10610
},
{
"entropy": 6.313779878616333,
"epoch": 1.0610786224821314,
"grad_norm": 1.265625,
"learning_rate": 0.0004896161635149773,
"loss": 6.136,
"mean_token_accuracy": 0.1449337162077427,
"num_tokens": 20770038.0,
"step": 10615
},
{
"entropy": 6.149812698364258,
"epoch": 1.0615784475433598,
"grad_norm": 1.3125,
"learning_rate": 0.0004896054439234217,
"loss": 5.899,
"mean_token_accuracy": 0.16779386401176452,
"num_tokens": 20779076.0,
"step": 10620
},
{
"entropy": 6.205066680908203,
"epoch": 1.0620782726045883,
"grad_norm": 1.2578125,
"learning_rate": 0.0004895947189324486,
"loss": 6.0226,
"mean_token_accuracy": 0.14764627516269685,
"num_tokens": 20789272.0,
"step": 10625
},
{
"entropy": 6.167108345031738,
"epoch": 1.062578097665817,
"grad_norm": 1.296875,
"learning_rate": 0.0004895839885423273,
"loss": 5.994,
"mean_token_accuracy": 0.15537745207548143,
"num_tokens": 20799381.0,
"step": 10630
},
{
"entropy": 6.137248277664185,
"epoch": 1.0630779227270455,
"grad_norm": 1.25,
"learning_rate": 0.0004895732527533283,
"loss": 5.9129,
"mean_token_accuracy": 0.15839783921837808,
"num_tokens": 20809886.0,
"step": 10635
},
{
"entropy": 6.237708711624146,
"epoch": 1.0635777477882742,
"grad_norm": 1.328125,
"learning_rate": 0.0004895625115657215,
"loss": 6.0272,
"mean_token_accuracy": 0.15324915051460267,
"num_tokens": 20819625.0,
"step": 10640
},
{
"entropy": 6.201759195327758,
"epoch": 1.0640775728495027,
"grad_norm": 1.3203125,
"learning_rate": 0.000489551764979777,
"loss": 5.979,
"mean_token_accuracy": 0.15168224275112152,
"num_tokens": 20829481.0,
"step": 10645
},
{
"entropy": 6.16482400894165,
"epoch": 1.0645773979107314,
"grad_norm": 1.3515625,
"learning_rate": 0.0004895410129957653,
"loss": 6.0045,
"mean_token_accuracy": 0.15040917173027993,
"num_tokens": 20840715.0,
"step": 10650
},
{
"entropy": 6.099859571456909,
"epoch": 1.0650772229719598,
"grad_norm": 1.3125,
"learning_rate": 0.0004895302556139569,
"loss": 5.9922,
"mean_token_accuracy": 0.156874181330204,
"num_tokens": 20851334.0,
"step": 10655
},
{
"entropy": 6.211218166351318,
"epoch": 1.0655770480331883,
"grad_norm": 1.453125,
"learning_rate": 0.0004895194928346226,
"loss": 5.9463,
"mean_token_accuracy": 0.1544322907924652,
"num_tokens": 20860357.0,
"step": 10660
},
{
"entropy": 6.198316669464111,
"epoch": 1.066076873094417,
"grad_norm": 1.375,
"learning_rate": 0.000489508724658033,
"loss": 6.0777,
"mean_token_accuracy": 0.14833938628435134,
"num_tokens": 20870360.0,
"step": 10665
},
{
"entropy": 6.25762619972229,
"epoch": 1.0665766981556455,
"grad_norm": 1.328125,
"learning_rate": 0.000489497951084459,
"loss": 6.0167,
"mean_token_accuracy": 0.15636848658323288,
"num_tokens": 20880640.0,
"step": 10670
},
{
"entropy": 6.207287073135376,
"epoch": 1.0670765232168742,
"grad_norm": 1.3515625,
"learning_rate": 0.0004894871721141718,
"loss": 5.984,
"mean_token_accuracy": 0.15058879926800728,
"num_tokens": 20890524.0,
"step": 10675
},
{
"entropy": 6.165485954284668,
"epoch": 1.0675763482781027,
"grad_norm": 1.328125,
"learning_rate": 0.0004894763877474426,
"loss": 5.9886,
"mean_token_accuracy": 0.1526798278093338,
"num_tokens": 20901469.0,
"step": 10680
},
{
"entropy": 6.1404252529144285,
"epoch": 1.0680761733393311,
"grad_norm": 1.28125,
"learning_rate": 0.0004894655979845427,
"loss": 6.0336,
"mean_token_accuracy": 0.15069067627191543,
"num_tokens": 20910703.0,
"step": 10685
},
{
"entropy": 6.189463376998901,
"epoch": 1.0685759984005598,
"grad_norm": 1.359375,
"learning_rate": 0.0004894548028257434,
"loss": 5.9625,
"mean_token_accuracy": 0.15357812792062758,
"num_tokens": 20920241.0,
"step": 10690
},
{
"entropy": 6.175825881958008,
"epoch": 1.0690758234617883,
"grad_norm": 1.3359375,
"learning_rate": 0.0004894440022713165,
"loss": 5.9953,
"mean_token_accuracy": 0.15783682316541672,
"num_tokens": 20930138.0,
"step": 10695
},
{
"entropy": 6.208317995071411,
"epoch": 1.069575648523017,
"grad_norm": 1.265625,
"learning_rate": 0.0004894331963215337,
"loss": 5.9661,
"mean_token_accuracy": 0.15733662694692613,
"num_tokens": 20939592.0,
"step": 10700
},
{
"entropy": 6.177032327651977,
"epoch": 1.0700754735842455,
"grad_norm": 1.3828125,
"learning_rate": 0.000489422384976667,
"loss": 5.9618,
"mean_token_accuracy": 0.16215263307094574,
"num_tokens": 20948208.0,
"step": 10705
},
{
"entropy": 6.152873229980469,
"epoch": 1.0705752986454742,
"grad_norm": 1.203125,
"learning_rate": 0.0004894115682369881,
"loss": 5.965,
"mean_token_accuracy": 0.155369308590889,
"num_tokens": 20958323.0,
"step": 10710
},
{
"entropy": 6.165218877792358,
"epoch": 1.0710751237067027,
"grad_norm": 1.3828125,
"learning_rate": 0.0004894007461027693,
"loss": 5.9414,
"mean_token_accuracy": 0.15968192964792252,
"num_tokens": 20967593.0,
"step": 10715
},
{
"entropy": 6.1513505458831785,
"epoch": 1.0715749487679311,
"grad_norm": 1.5,
"learning_rate": 0.0004893899185742828,
"loss": 5.9382,
"mean_token_accuracy": 0.15624755024909973,
"num_tokens": 20977236.0,
"step": 10720
},
{
"entropy": 6.1235023021698,
"epoch": 1.0720747738291598,
"grad_norm": 1.375,
"learning_rate": 0.0004893790856518014,
"loss": 6.0122,
"mean_token_accuracy": 0.15551438182592392,
"num_tokens": 20986346.0,
"step": 10725
},
{
"entropy": 6.096535158157349,
"epoch": 1.0725745988903883,
"grad_norm": 1.5546875,
"learning_rate": 0.0004893682473355972,
"loss": 5.8771,
"mean_token_accuracy": 0.164378722012043,
"num_tokens": 20995794.0,
"step": 10730
},
{
"entropy": 6.129690170288086,
"epoch": 1.073074423951617,
"grad_norm": 1.296875,
"learning_rate": 0.0004893574036259432,
"loss": 5.8848,
"mean_token_accuracy": 0.15969372540712357,
"num_tokens": 21005133.0,
"step": 10735
},
{
"entropy": 6.183308029174805,
"epoch": 1.0735742490128455,
"grad_norm": 1.3671875,
"learning_rate": 0.0004893465545231119,
"loss": 6.0091,
"mean_token_accuracy": 0.15558296740055083,
"num_tokens": 21014445.0,
"step": 10740
},
{
"entropy": 6.107181167602539,
"epoch": 1.074074074074074,
"grad_norm": 1.4140625,
"learning_rate": 0.0004893357000273765,
"loss": 5.8958,
"mean_token_accuracy": 0.15392211303114892,
"num_tokens": 21023093.0,
"step": 10745
},
{
"entropy": 6.131949329376221,
"epoch": 1.0745738991353027,
"grad_norm": 1.390625,
"learning_rate": 0.00048932484013901,
"loss": 5.9758,
"mean_token_accuracy": 0.15346091389656066,
"num_tokens": 21031445.0,
"step": 10750
},
{
"entropy": 6.152755403518677,
"epoch": 1.0750737241965311,
"grad_norm": 1.28125,
"learning_rate": 0.0004893139748582857,
"loss": 5.9546,
"mean_token_accuracy": 0.15513472855091096,
"num_tokens": 21041026.0,
"step": 10755
},
{
"entropy": 6.191868543624878,
"epoch": 1.0755735492577598,
"grad_norm": 1.3671875,
"learning_rate": 0.000489303104185477,
"loss": 5.9994,
"mean_token_accuracy": 0.15582500100135804,
"num_tokens": 21050665.0,
"step": 10760
},
{
"entropy": 6.122053718566894,
"epoch": 1.0760733743189883,
"grad_norm": 1.1875,
"learning_rate": 0.0004892922281208573,
"loss": 5.9622,
"mean_token_accuracy": 0.1509912982583046,
"num_tokens": 21060470.0,
"step": 10765
},
{
"entropy": 6.257739162445068,
"epoch": 1.076573199380217,
"grad_norm": 1.3125,
"learning_rate": 0.0004892813466647002,
"loss": 6.0881,
"mean_token_accuracy": 0.14919286593794823,
"num_tokens": 21070174.0,
"step": 10770
},
{
"entropy": 6.286755180358886,
"epoch": 1.0770730244414455,
"grad_norm": 1.34375,
"learning_rate": 0.0004892704598172797,
"loss": 6.0849,
"mean_token_accuracy": 0.147285782545805,
"num_tokens": 21079686.0,
"step": 10775
},
{
"entropy": 6.276339292526245,
"epoch": 1.077572849502674,
"grad_norm": 1.1796875,
"learning_rate": 0.0004892595675788696,
"loss": 6.0283,
"mean_token_accuracy": 0.1505945973098278,
"num_tokens": 21089509.0,
"step": 10780
},
{
"entropy": 6.2047687530517575,
"epoch": 1.0780726745639027,
"grad_norm": 1.1953125,
"learning_rate": 0.0004892486699497439,
"loss": 6.0629,
"mean_token_accuracy": 0.14613900184631348,
"num_tokens": 21099992.0,
"step": 10785
},
{
"entropy": 6.196640062332153,
"epoch": 1.0785724996251311,
"grad_norm": 1.6328125,
"learning_rate": 0.0004892377669301766,
"loss": 5.9806,
"mean_token_accuracy": 0.1502140372991562,
"num_tokens": 21109593.0,
"step": 10790
},
{
"entropy": 6.214747905731201,
"epoch": 1.0790723246863598,
"grad_norm": 1.296875,
"learning_rate": 0.0004892268585204423,
"loss": 5.9555,
"mean_token_accuracy": 0.15461448580026627,
"num_tokens": 21119837.0,
"step": 10795
},
{
"entropy": 6.230557203292847,
"epoch": 1.0795721497475883,
"grad_norm": 1.1953125,
"learning_rate": 0.0004892159447208154,
"loss": 6.0314,
"mean_token_accuracy": 0.1533092364668846,
"num_tokens": 21129908.0,
"step": 10800
},
{
"entropy": 6.182940101623535,
"epoch": 1.080071974808817,
"grad_norm": 1.453125,
"learning_rate": 0.0004892050255315705,
"loss": 6.0394,
"mean_token_accuracy": 0.1535039946436882,
"num_tokens": 21140362.0,
"step": 10805
},
{
"entropy": 6.176079416275025,
"epoch": 1.0805717998700455,
"grad_norm": 1.2265625,
"learning_rate": 0.0004891941009529822,
"loss": 6.0191,
"mean_token_accuracy": 0.15578728914260864,
"num_tokens": 21151617.0,
"step": 10810
},
{
"entropy": 6.207557916641235,
"epoch": 1.081071624931274,
"grad_norm": 1.2734375,
"learning_rate": 0.0004891831709853255,
"loss": 5.9982,
"mean_token_accuracy": 0.1497117042541504,
"num_tokens": 21160736.0,
"step": 10815
},
{
"entropy": 6.051417636871338,
"epoch": 1.0815714499925027,
"grad_norm": 1.3203125,
"learning_rate": 0.0004891722356288752,
"loss": 5.9356,
"mean_token_accuracy": 0.15966171622276307,
"num_tokens": 21170311.0,
"step": 10820
},
{
"entropy": 6.105764865875244,
"epoch": 1.0820712750537311,
"grad_norm": 1.28125,
"learning_rate": 0.0004891612948839068,
"loss": 5.9166,
"mean_token_accuracy": 0.1541769325733185,
"num_tokens": 21179732.0,
"step": 10825
},
{
"entropy": 6.186644411087036,
"epoch": 1.0825711001149598,
"grad_norm": 1.390625,
"learning_rate": 0.0004891503487506951,
"loss": 5.9288,
"mean_token_accuracy": 0.1542472004890442,
"num_tokens": 21189600.0,
"step": 10830
},
{
"entropy": 6.243680143356324,
"epoch": 1.0830709251761883,
"grad_norm": 1.234375,
"learning_rate": 0.0004891393972295159,
"loss": 5.9761,
"mean_token_accuracy": 0.1528242439031601,
"num_tokens": 21199016.0,
"step": 10835
},
{
"entropy": 6.146160650253296,
"epoch": 1.083570750237417,
"grad_norm": 1.359375,
"learning_rate": 0.0004891284403206444,
"loss": 5.9792,
"mean_token_accuracy": 0.1563607394695282,
"num_tokens": 21208176.0,
"step": 10840
},
{
"entropy": 6.114896821975708,
"epoch": 1.0840705752986455,
"grad_norm": 1.40625,
"learning_rate": 0.0004891174780243566,
"loss": 5.9194,
"mean_token_accuracy": 0.1608621172606945,
"num_tokens": 21217948.0,
"step": 10845
},
{
"entropy": 6.113623762130738,
"epoch": 1.084570400359874,
"grad_norm": 1.3203125,
"learning_rate": 0.000489106510340928,
"loss": 5.9065,
"mean_token_accuracy": 0.17097460627555847,
"num_tokens": 21227994.0,
"step": 10850
},
{
"entropy": 6.159657001495361,
"epoch": 1.0850702254211027,
"grad_norm": 1.375,
"learning_rate": 0.0004890955372706348,
"loss": 5.9294,
"mean_token_accuracy": 0.1630495309829712,
"num_tokens": 21237676.0,
"step": 10855
},
{
"entropy": 6.129100227355957,
"epoch": 1.0855700504823311,
"grad_norm": 1.3203125,
"learning_rate": 0.0004890845588137531,
"loss": 5.9007,
"mean_token_accuracy": 0.15763380229473115,
"num_tokens": 21248992.0,
"step": 10860
},
{
"entropy": 6.144695234298706,
"epoch": 1.0860698755435598,
"grad_norm": 1.234375,
"learning_rate": 0.0004890735749705587,
"loss": 5.9705,
"mean_token_accuracy": 0.15795147344470023,
"num_tokens": 21258414.0,
"step": 10865
},
{
"entropy": 6.172103929519653,
"epoch": 1.0865697006047883,
"grad_norm": 1.46875,
"learning_rate": 0.0004890625857413283,
"loss": 5.953,
"mean_token_accuracy": 0.1554660201072693,
"num_tokens": 21267687.0,
"step": 10870
},
{
"entropy": 6.184333848953247,
"epoch": 1.087069525666017,
"grad_norm": 1.3515625,
"learning_rate": 0.0004890515911263385,
"loss": 6.0041,
"mean_token_accuracy": 0.15596673488616944,
"num_tokens": 21277623.0,
"step": 10875
},
{
"entropy": 6.214262580871582,
"epoch": 1.0875693507272455,
"grad_norm": 1.4140625,
"learning_rate": 0.0004890405911258656,
"loss": 6.0632,
"mean_token_accuracy": 0.14790254086256027,
"num_tokens": 21288178.0,
"step": 10880
},
{
"entropy": 6.226759958267212,
"epoch": 1.088069175788474,
"grad_norm": 1.2421875,
"learning_rate": 0.0004890295857401866,
"loss": 5.988,
"mean_token_accuracy": 0.15190412253141403,
"num_tokens": 21298367.0,
"step": 10885
},
{
"entropy": 6.179524707794189,
"epoch": 1.0885690008497027,
"grad_norm": 2.046875,
"learning_rate": 0.0004890185749695783,
"loss": 6.018,
"mean_token_accuracy": 0.15185327380895614,
"num_tokens": 21307475.0,
"step": 10890
},
{
"entropy": 6.194209814071655,
"epoch": 1.0890688259109311,
"grad_norm": 1.40625,
"learning_rate": 0.0004890075588143176,
"loss": 6.0038,
"mean_token_accuracy": 0.14982156902551652,
"num_tokens": 21317715.0,
"step": 10895
},
{
"entropy": 6.171987915039063,
"epoch": 1.0895686509721598,
"grad_norm": 1.25,
"learning_rate": 0.0004889965372746819,
"loss": 6.046,
"mean_token_accuracy": 0.1440729543566704,
"num_tokens": 21327487.0,
"step": 10900
},
{
"entropy": 6.138454103469849,
"epoch": 1.0900684760333883,
"grad_norm": 1.2578125,
"learning_rate": 0.0004889855103509484,
"loss": 5.9496,
"mean_token_accuracy": 0.15668963491916657,
"num_tokens": 21337588.0,
"step": 10905
},
{
"entropy": 6.114659214019776,
"epoch": 1.090568301094617,
"grad_norm": 1.2734375,
"learning_rate": 0.0004889744780433944,
"loss": 5.8373,
"mean_token_accuracy": 0.16587060540914536,
"num_tokens": 21347037.0,
"step": 10910
},
{
"entropy": 6.092364358901977,
"epoch": 1.0910681261558455,
"grad_norm": 1.5078125,
"learning_rate": 0.0004889634403522976,
"loss": 6.0346,
"mean_token_accuracy": 0.15080819725990297,
"num_tokens": 21358784.0,
"step": 10915
},
{
"entropy": 6.179441833496094,
"epoch": 1.091567951217074,
"grad_norm": 1.4921875,
"learning_rate": 0.0004889523972779359,
"loss": 6.0012,
"mean_token_accuracy": 0.1521432429552078,
"num_tokens": 21368245.0,
"step": 10920
},
{
"entropy": 6.164575147628784,
"epoch": 1.0920677762783026,
"grad_norm": 1.40625,
"learning_rate": 0.0004889413488205868,
"loss": 5.9383,
"mean_token_accuracy": 0.1602636493742466,
"num_tokens": 21377409.0,
"step": 10925
},
{
"entropy": 6.211748313903809,
"epoch": 1.0925676013395311,
"grad_norm": 1.3046875,
"learning_rate": 0.0004889302949805283,
"loss": 5.9395,
"mean_token_accuracy": 0.1582891032099724,
"num_tokens": 21388109.0,
"step": 10930
},
{
"entropy": 6.133979177474975,
"epoch": 1.0930674264007598,
"grad_norm": 1.2265625,
"learning_rate": 0.0004889192357580388,
"loss": 5.8426,
"mean_token_accuracy": 0.1629247024655342,
"num_tokens": 21396645.0,
"step": 10935
},
{
"entropy": 6.202014446258545,
"epoch": 1.0935672514619883,
"grad_norm": 1.328125,
"learning_rate": 0.0004889081711533964,
"loss": 6.0632,
"mean_token_accuracy": 0.14829194620251657,
"num_tokens": 21407398.0,
"step": 10940
},
{
"entropy": 6.129686546325684,
"epoch": 1.0940670765232168,
"grad_norm": 1.296875,
"learning_rate": 0.0004888971011668793,
"loss": 5.8757,
"mean_token_accuracy": 0.15977948531508446,
"num_tokens": 21417185.0,
"step": 10945
},
{
"entropy": 6.200656366348267,
"epoch": 1.0945669015844455,
"grad_norm": 1.28125,
"learning_rate": 0.0004888860257987662,
"loss": 6.067,
"mean_token_accuracy": 0.14702474176883698,
"num_tokens": 21426743.0,
"step": 10950
},
{
"entropy": 6.163834047317505,
"epoch": 1.095066726645674,
"grad_norm": 1.3515625,
"learning_rate": 0.0004888749450493358,
"loss": 5.9904,
"mean_token_accuracy": 0.153190453350544,
"num_tokens": 21436528.0,
"step": 10955
},
{
"entropy": 6.124946546554566,
"epoch": 1.0955665517069026,
"grad_norm": 1.71875,
"learning_rate": 0.0004888638589188669,
"loss": 5.9688,
"mean_token_accuracy": 0.1614849388599396,
"num_tokens": 21445286.0,
"step": 10960
},
{
"entropy": 6.249599027633667,
"epoch": 1.0960663767681311,
"grad_norm": 1.5,
"learning_rate": 0.0004888527674076382,
"loss": 6.1074,
"mean_token_accuracy": 0.15115003436803817,
"num_tokens": 21455695.0,
"step": 10965
},
{
"entropy": 6.2146913528442385,
"epoch": 1.0965662018293598,
"grad_norm": 6.0625,
"learning_rate": 0.000488841670515929,
"loss": 5.9652,
"mean_token_accuracy": 0.15328542068600653,
"num_tokens": 21465305.0,
"step": 10970
},
{
"entropy": 6.111506605148316,
"epoch": 1.0970660268905883,
"grad_norm": 1.5,
"learning_rate": 0.0004888305682440183,
"loss": 5.8667,
"mean_token_accuracy": 0.1672878496348858,
"num_tokens": 21475101.0,
"step": 10975
},
{
"entropy": 6.141602325439453,
"epoch": 1.0975658519518168,
"grad_norm": 1.6328125,
"learning_rate": 0.0004888194605921855,
"loss": 5.9257,
"mean_token_accuracy": 0.1610399529337883,
"num_tokens": 21484240.0,
"step": 10980
},
{
"entropy": 6.239077758789063,
"epoch": 1.0980656770130455,
"grad_norm": 1.53125,
"learning_rate": 0.0004888083475607102,
"loss": 6.0302,
"mean_token_accuracy": 0.151107993721962,
"num_tokens": 21494700.0,
"step": 10985
},
{
"entropy": 6.094038200378418,
"epoch": 1.098565502074274,
"grad_norm": 1.3671875,
"learning_rate": 0.0004887972291498718,
"loss": 5.919,
"mean_token_accuracy": 0.15702562481164933,
"num_tokens": 21504418.0,
"step": 10990
},
{
"entropy": 6.207502317428589,
"epoch": 1.0990653271355026,
"grad_norm": 1.296875,
"learning_rate": 0.0004887861053599503,
"loss": 5.9236,
"mean_token_accuracy": 0.15595513731241226,
"num_tokens": 21514019.0,
"step": 10995
},
{
"entropy": 6.174081325531006,
"epoch": 1.0995651521967311,
"grad_norm": 1.40625,
"learning_rate": 0.0004887749761912252,
"loss": 5.9453,
"mean_token_accuracy": 0.15641257166862488,
"num_tokens": 21524279.0,
"step": 11000
},
{
"entropy": 6.2020337104797365,
"epoch": 1.1000649772579596,
"grad_norm": 1.3046875,
"learning_rate": 0.0004887638416439768,
"loss": 5.9632,
"mean_token_accuracy": 0.15037081837654115,
"num_tokens": 21533851.0,
"step": 11005
},
{
"entropy": 6.16806993484497,
"epoch": 1.1005648023191883,
"grad_norm": 1.328125,
"learning_rate": 0.0004887527017184851,
"loss": 5.924,
"mean_token_accuracy": 0.1546926960349083,
"num_tokens": 21542589.0,
"step": 11010
},
{
"entropy": 6.166245985031128,
"epoch": 1.1010646273804168,
"grad_norm": 1.4765625,
"learning_rate": 0.0004887415564150305,
"loss": 5.9927,
"mean_token_accuracy": 0.15054001212120055,
"num_tokens": 21553018.0,
"step": 11015
},
{
"entropy": 6.267609882354736,
"epoch": 1.1015644524416455,
"grad_norm": 1.4453125,
"learning_rate": 0.0004887304057338934,
"loss": 6.1011,
"mean_token_accuracy": 0.14651739820837975,
"num_tokens": 21561830.0,
"step": 11020
},
{
"entropy": 6.239610910415649,
"epoch": 1.102064277502874,
"grad_norm": 1.3984375,
"learning_rate": 0.000488719249675354,
"loss": 5.9536,
"mean_token_accuracy": 0.1536804363131523,
"num_tokens": 21571126.0,
"step": 11025
},
{
"entropy": 6.110537815093994,
"epoch": 1.1025641025641026,
"grad_norm": 1.2578125,
"learning_rate": 0.0004887080882396936,
"loss": 5.9592,
"mean_token_accuracy": 0.16280061453580857,
"num_tokens": 21580771.0,
"step": 11030
},
{
"entropy": 6.194991540908814,
"epoch": 1.1030639276253311,
"grad_norm": 1.359375,
"learning_rate": 0.0004886969214271925,
"loss": 6.0825,
"mean_token_accuracy": 0.1497802786529064,
"num_tokens": 21591687.0,
"step": 11035
},
{
"entropy": 6.169806623458863,
"epoch": 1.1035637526865596,
"grad_norm": 1.515625,
"learning_rate": 0.0004886857492381319,
"loss": 5.9685,
"mean_token_accuracy": 0.15749285072088243,
"num_tokens": 21601056.0,
"step": 11040
},
{
"entropy": 6.153095388412476,
"epoch": 1.1040635777477883,
"grad_norm": 1.3203125,
"learning_rate": 0.0004886745716727928,
"loss": 5.948,
"mean_token_accuracy": 0.15879009515047074,
"num_tokens": 21610846.0,
"step": 11045
},
{
"entropy": 6.152535533905029,
"epoch": 1.1045634028090168,
"grad_norm": 1.2578125,
"learning_rate": 0.0004886633887314565,
"loss": 5.929,
"mean_token_accuracy": 0.1538671150803566,
"num_tokens": 21621504.0,
"step": 11050
},
{
"entropy": 6.1460926055908205,
"epoch": 1.1050632278702455,
"grad_norm": 1.46875,
"learning_rate": 0.0004886522004144044,
"loss": 5.8941,
"mean_token_accuracy": 0.1651014119386673,
"num_tokens": 21631566.0,
"step": 11055
},
{
"entropy": 6.207142639160156,
"epoch": 1.105563052931474,
"grad_norm": 1.3046875,
"learning_rate": 0.0004886410067219178,
"loss": 5.9515,
"mean_token_accuracy": 0.1587765023112297,
"num_tokens": 21641392.0,
"step": 11060
},
{
"entropy": 6.1335869312286375,
"epoch": 1.1060628779927026,
"grad_norm": 1.375,
"learning_rate": 0.0004886298076542785,
"loss": 5.909,
"mean_token_accuracy": 0.16362943798303603,
"num_tokens": 21650356.0,
"step": 11065
},
{
"entropy": 6.18138017654419,
"epoch": 1.1065627030539311,
"grad_norm": 1.3515625,
"learning_rate": 0.0004886186032117682,
"loss": 6.0298,
"mean_token_accuracy": 0.1514166846871376,
"num_tokens": 21660704.0,
"step": 11070
},
{
"entropy": 6.198483610153199,
"epoch": 1.1070625281151596,
"grad_norm": 1.40625,
"learning_rate": 0.0004886073933946688,
"loss": 5.9551,
"mean_token_accuracy": 0.15121551752090454,
"num_tokens": 21671002.0,
"step": 11075
},
{
"entropy": 6.121125268936157,
"epoch": 1.1075623531763883,
"grad_norm": 1.5234375,
"learning_rate": 0.0004885961782032624,
"loss": 5.9094,
"mean_token_accuracy": 0.16212226897478105,
"num_tokens": 21680802.0,
"step": 11080
},
{
"entropy": 6.103603553771973,
"epoch": 1.1080621782376168,
"grad_norm": 1.375,
"learning_rate": 0.000488584957637831,
"loss": 5.9135,
"mean_token_accuracy": 0.16017423272132875,
"num_tokens": 21690535.0,
"step": 11085
},
{
"entropy": 6.161426162719726,
"epoch": 1.1085620032988455,
"grad_norm": 1.359375,
"learning_rate": 0.0004885737316986571,
"loss": 6.0137,
"mean_token_accuracy": 0.15026820525527002,
"num_tokens": 21700283.0,
"step": 11090
},
{
"entropy": 6.263440227508545,
"epoch": 1.109061828360074,
"grad_norm": 1.2578125,
"learning_rate": 0.000488562500386023,
"loss": 5.9578,
"mean_token_accuracy": 0.1532932013273239,
"num_tokens": 21709927.0,
"step": 11095
},
{
"entropy": 6.171089220046997,
"epoch": 1.1095616534213026,
"grad_norm": 1.4921875,
"learning_rate": 0.0004885512637002115,
"loss": 5.892,
"mean_token_accuracy": 0.16278183534741403,
"num_tokens": 21720011.0,
"step": 11100
},
{
"entropy": 6.138248157501221,
"epoch": 1.1100614784825311,
"grad_norm": 1.3203125,
"learning_rate": 0.0004885400216415051,
"loss": 6.0124,
"mean_token_accuracy": 0.1482589364051819,
"num_tokens": 21729456.0,
"step": 11105
},
{
"entropy": 6.25309476852417,
"epoch": 1.1105613035437596,
"grad_norm": 1.234375,
"learning_rate": 0.0004885287742101865,
"loss": 6.0614,
"mean_token_accuracy": 0.15060478895902635,
"num_tokens": 21739341.0,
"step": 11110
},
{
"entropy": 6.265266466140747,
"epoch": 1.1110611286049883,
"grad_norm": 1.3203125,
"learning_rate": 0.0004885175214065392,
"loss": 6.0519,
"mean_token_accuracy": 0.1445502944290638,
"num_tokens": 21749549.0,
"step": 11115
},
{
"entropy": 6.207500743865967,
"epoch": 1.1115609536662168,
"grad_norm": 1.25,
"learning_rate": 0.0004885062632308457,
"loss": 5.938,
"mean_token_accuracy": 0.15182265043258666,
"num_tokens": 21760030.0,
"step": 11120
},
{
"entropy": 6.202724313735962,
"epoch": 1.1120607787274455,
"grad_norm": 1.3984375,
"learning_rate": 0.0004884949996833898,
"loss": 6.0307,
"mean_token_accuracy": 0.15140736252069473,
"num_tokens": 21769754.0,
"step": 11125
},
{
"entropy": 6.169153642654419,
"epoch": 1.112560603788674,
"grad_norm": 1.328125,
"learning_rate": 0.0004884837307644545,
"loss": 6.0096,
"mean_token_accuracy": 0.1515662595629692,
"num_tokens": 21780248.0,
"step": 11130
},
{
"entropy": 6.148779201507568,
"epoch": 1.1130604288499026,
"grad_norm": 1.3671875,
"learning_rate": 0.0004884724564743236,
"loss": 5.9073,
"mean_token_accuracy": 0.16309308856725693,
"num_tokens": 21789014.0,
"step": 11135
},
{
"entropy": 6.12496509552002,
"epoch": 1.1135602539111311,
"grad_norm": 1.2578125,
"learning_rate": 0.0004884611768132805,
"loss": 5.9201,
"mean_token_accuracy": 0.15609773248434067,
"num_tokens": 21798210.0,
"step": 11140
},
{
"entropy": 6.127873659133911,
"epoch": 1.1140600789723596,
"grad_norm": 1.6171875,
"learning_rate": 0.0004884498917816092,
"loss": 5.9496,
"mean_token_accuracy": 0.15685731619596482,
"num_tokens": 21807947.0,
"step": 11145
},
{
"entropy": 6.15563588142395,
"epoch": 1.1145599040335883,
"grad_norm": 1.359375,
"learning_rate": 0.0004884386013795935,
"loss": 5.995,
"mean_token_accuracy": 0.15536333695054055,
"num_tokens": 21816685.0,
"step": 11150
},
{
"entropy": 6.236415004730224,
"epoch": 1.1150597290948168,
"grad_norm": 1.34375,
"learning_rate": 0.0004884273056075175,
"loss": 5.9608,
"mean_token_accuracy": 0.15593728125095369,
"num_tokens": 21826479.0,
"step": 11155
},
{
"entropy": 6.109762191772461,
"epoch": 1.1155595541560455,
"grad_norm": 1.5,
"learning_rate": 0.0004884160044656654,
"loss": 5.9672,
"mean_token_accuracy": 0.15251924693584443,
"num_tokens": 21837518.0,
"step": 11160
},
{
"entropy": 6.139361047744751,
"epoch": 1.116059379217274,
"grad_norm": 1.46875,
"learning_rate": 0.0004884046979543217,
"loss": 5.8871,
"mean_token_accuracy": 0.15499355643987656,
"num_tokens": 21846069.0,
"step": 11165
},
{
"entropy": 6.2051229000091555,
"epoch": 1.1165592042785026,
"grad_norm": 1.4765625,
"learning_rate": 0.0004883933860737706,
"loss": 6.0897,
"mean_token_accuracy": 0.15541018843650817,
"num_tokens": 21855594.0,
"step": 11170
},
{
"entropy": 6.150937128067016,
"epoch": 1.1170590293397311,
"grad_norm": 1.3125,
"learning_rate": 0.0004883820688242968,
"loss": 5.9701,
"mean_token_accuracy": 0.15113090425729753,
"num_tokens": 21864648.0,
"step": 11175
},
{
"entropy": 6.250085353851318,
"epoch": 1.1175588544009596,
"grad_norm": 1.3125,
"learning_rate": 0.0004883707462061851,
"loss": 5.9985,
"mean_token_accuracy": 0.14634210839867592,
"num_tokens": 21875516.0,
"step": 11180
},
{
"entropy": 6.170653057098389,
"epoch": 1.1180586794621883,
"grad_norm": 1.40625,
"learning_rate": 0.0004883594182197203,
"loss": 6.0051,
"mean_token_accuracy": 0.15406120121479033,
"num_tokens": 21885232.0,
"step": 11185
},
{
"entropy": 6.151582145690918,
"epoch": 1.1185585045234168,
"grad_norm": 1.328125,
"learning_rate": 0.0004883480848651875,
"loss": 5.9497,
"mean_token_accuracy": 0.1579062432050705,
"num_tokens": 21895913.0,
"step": 11190
},
{
"entropy": 6.206772232055664,
"epoch": 1.1190583295846455,
"grad_norm": 1.9296875,
"learning_rate": 0.0004883367461428716,
"loss": 6.0344,
"mean_token_accuracy": 0.15026285350322724,
"num_tokens": 21906160.0,
"step": 11195
},
{
"entropy": 6.1354296684265135,
"epoch": 1.119558154645874,
"grad_norm": 1.28125,
"learning_rate": 0.0004883254020530582,
"loss": 5.9039,
"mean_token_accuracy": 0.16246647089719773,
"num_tokens": 21915326.0,
"step": 11200
},
{
"entropy": 6.1779218196868895,
"epoch": 1.1200579797071024,
"grad_norm": 1.3515625,
"learning_rate": 0.0004883140525960327,
"loss": 5.9831,
"mean_token_accuracy": 0.15215202867984773,
"num_tokens": 21925804.0,
"step": 11205
},
{
"entropy": 6.193980550765991,
"epoch": 1.1205578047683311,
"grad_norm": 1.3125,
"learning_rate": 0.0004883026977720803,
"loss": 5.8979,
"mean_token_accuracy": 0.1616089776158333,
"num_tokens": 21934226.0,
"step": 11210
},
{
"entropy": 6.047083520889283,
"epoch": 1.1210576298295596,
"grad_norm": 1.390625,
"learning_rate": 0.000488291337581487,
"loss": 5.786,
"mean_token_accuracy": 0.17675856202840806,
"num_tokens": 21944068.0,
"step": 11215
},
{
"entropy": 6.168870306015014,
"epoch": 1.1215574548907883,
"grad_norm": 1.40625,
"learning_rate": 0.0004882799720245385,
"loss": 6.0231,
"mean_token_accuracy": 0.15611078590154648,
"num_tokens": 21954509.0,
"step": 11220
},
{
"entropy": 6.177779817581177,
"epoch": 1.1220572799520168,
"grad_norm": 1.390625,
"learning_rate": 0.0004882686011015208,
"loss": 6.0283,
"mean_token_accuracy": 0.14786954671144487,
"num_tokens": 21963753.0,
"step": 11225
},
{
"entropy": 6.165050840377807,
"epoch": 1.1225571050132455,
"grad_norm": 1.515625,
"learning_rate": 0.00048825722481272006,
"loss": 5.97,
"mean_token_accuracy": 0.15491714999079703,
"num_tokens": 21973634.0,
"step": 11230
},
{
"entropy": 6.187585163116455,
"epoch": 1.123056930074474,
"grad_norm": 1.296875,
"learning_rate": 0.0004882458431584223,
"loss": 6.0091,
"mean_token_accuracy": 0.15739966481924056,
"num_tokens": 21984029.0,
"step": 11235
},
{
"entropy": 6.16133942604065,
"epoch": 1.1235567551357024,
"grad_norm": 1.828125,
"learning_rate": 0.0004882344561389141,
"loss": 6.0509,
"mean_token_accuracy": 0.15195800587534905,
"num_tokens": 21994270.0,
"step": 11240
},
{
"entropy": 6.318618488311768,
"epoch": 1.124056580196931,
"grad_norm": 1.3984375,
"learning_rate": 0.00048822306375448176,
"loss": 6.0697,
"mean_token_accuracy": 0.14534596353769302,
"num_tokens": 22002911.0,
"step": 11245
},
{
"entropy": 6.152344369888306,
"epoch": 1.1245564052581596,
"grad_norm": 1.4296875,
"learning_rate": 0.0004882116660054121,
"loss": 6.0296,
"mean_token_accuracy": 0.15108929127454757,
"num_tokens": 22012615.0,
"step": 11250
},
{
"entropy": 6.1539805889129635,
"epoch": 1.1250562303193883,
"grad_norm": 1.28125,
"learning_rate": 0.0004882002628919917,
"loss": 6.0056,
"mean_token_accuracy": 0.15410257130861282,
"num_tokens": 22022274.0,
"step": 11255
},
{
"entropy": 6.140741014480591,
"epoch": 1.1255560553806168,
"grad_norm": 1.4921875,
"learning_rate": 0.0004881888544145076,
"loss": 5.8754,
"mean_token_accuracy": 0.15651678293943405,
"num_tokens": 22031238.0,
"step": 11260
},
{
"entropy": 6.146964836120605,
"epoch": 1.1260558804418452,
"grad_norm": 1.4140625,
"learning_rate": 0.00048817744057324673,
"loss": 5.9355,
"mean_token_accuracy": 0.15283789336681367,
"num_tokens": 22041003.0,
"step": 11265
},
{
"entropy": 6.0776032447814945,
"epoch": 1.126555705503074,
"grad_norm": 1.2890625,
"learning_rate": 0.00048816602136849644,
"loss": 5.9292,
"mean_token_accuracy": 0.15870113000273706,
"num_tokens": 22050621.0,
"step": 11270
},
{
"entropy": 6.154777145385742,
"epoch": 1.1270555305643024,
"grad_norm": 1.5234375,
"learning_rate": 0.00048815459680054375,
"loss": 6.0131,
"mean_token_accuracy": 0.14526955634355546,
"num_tokens": 22060382.0,
"step": 11275
},
{
"entropy": 6.177711439132691,
"epoch": 1.127555355625531,
"grad_norm": 1.328125,
"learning_rate": 0.00048814316686967635,
"loss": 5.9604,
"mean_token_accuracy": 0.1567354157567024,
"num_tokens": 22069896.0,
"step": 11280
},
{
"entropy": 6.198789834976196,
"epoch": 1.1280551806867596,
"grad_norm": 1.3515625,
"learning_rate": 0.0004881317315761817,
"loss": 5.8908,
"mean_token_accuracy": 0.16615169793367385,
"num_tokens": 22080234.0,
"step": 11285
},
{
"entropy": 6.133270645141602,
"epoch": 1.1285550057479883,
"grad_norm": 1.3359375,
"learning_rate": 0.00048812029092034747,
"loss": 6.0069,
"mean_token_accuracy": 0.15555982068181037,
"num_tokens": 22089866.0,
"step": 11290
},
{
"entropy": 6.116809701919555,
"epoch": 1.1290548308092168,
"grad_norm": 1.2890625,
"learning_rate": 0.00048810884490246164,
"loss": 5.9464,
"mean_token_accuracy": 0.15819924473762512,
"num_tokens": 22100740.0,
"step": 11295
},
{
"entropy": 6.212266063690185,
"epoch": 1.1295546558704452,
"grad_norm": 1.3515625,
"learning_rate": 0.000488097393522812,
"loss": 5.9596,
"mean_token_accuracy": 0.15572836399078369,
"num_tokens": 22110519.0,
"step": 11300
},
{
"entropy": 6.074816608428955,
"epoch": 1.130054480931674,
"grad_norm": 1.3203125,
"learning_rate": 0.0004880859367816868,
"loss": 5.8915,
"mean_token_accuracy": 0.16337006241083146,
"num_tokens": 22119671.0,
"step": 11305
},
{
"entropy": 6.168532609939575,
"epoch": 1.1305543059929024,
"grad_norm": 1.21875,
"learning_rate": 0.0004880744746793744,
"loss": 5.9533,
"mean_token_accuracy": 0.14340534657239914,
"num_tokens": 22130022.0,
"step": 11310
},
{
"entropy": 6.2538656234741214,
"epoch": 1.131054131054131,
"grad_norm": 1.28125,
"learning_rate": 0.00048806300721616295,
"loss": 6.0265,
"mean_token_accuracy": 0.1557791382074356,
"num_tokens": 22140875.0,
"step": 11315
},
{
"entropy": 6.235920095443726,
"epoch": 1.1315539561153596,
"grad_norm": 1.4375,
"learning_rate": 0.00048805153439234107,
"loss": 5.9836,
"mean_token_accuracy": 0.1580161690711975,
"num_tokens": 22150144.0,
"step": 11320
},
{
"entropy": 6.10329122543335,
"epoch": 1.1320537811765883,
"grad_norm": 1.3359375,
"learning_rate": 0.0004880400562081974,
"loss": 5.9325,
"mean_token_accuracy": 0.16385404765605927,
"num_tokens": 22158951.0,
"step": 11325
},
{
"entropy": 6.061306476593018,
"epoch": 1.1325536062378168,
"grad_norm": 1.4765625,
"learning_rate": 0.00048802857266402075,
"loss": 5.9391,
"mean_token_accuracy": 0.15585393458604813,
"num_tokens": 22167458.0,
"step": 11330
},
{
"entropy": 6.118793392181397,
"epoch": 1.1330534312990452,
"grad_norm": 1.421875,
"learning_rate": 0.0004880170837601,
"loss": 5.9046,
"mean_token_accuracy": 0.15917653292417527,
"num_tokens": 22176760.0,
"step": 11335
},
{
"entropy": 6.180065250396728,
"epoch": 1.133553256360274,
"grad_norm": 1.3203125,
"learning_rate": 0.0004880055894967242,
"loss": 5.9567,
"mean_token_accuracy": 0.15223372280597686,
"num_tokens": 22186476.0,
"step": 11340
},
{
"entropy": 6.086314868927002,
"epoch": 1.1340530814215024,
"grad_norm": 1.328125,
"learning_rate": 0.00048799408987418264,
"loss": 5.948,
"mean_token_accuracy": 0.1579450786113739,
"num_tokens": 22196420.0,
"step": 11345
},
{
"entropy": 6.120630168914795,
"epoch": 1.134552906482731,
"grad_norm": 1.640625,
"learning_rate": 0.00048798258489276457,
"loss": 5.9755,
"mean_token_accuracy": 0.1537513867020607,
"num_tokens": 22204989.0,
"step": 11350
},
{
"entropy": 6.121804285049438,
"epoch": 1.1350527315439596,
"grad_norm": 1.4375,
"learning_rate": 0.0004879710745527595,
"loss": 5.934,
"mean_token_accuracy": 0.15794263705611228,
"num_tokens": 22214831.0,
"step": 11355
},
{
"entropy": 6.270429039001465,
"epoch": 1.1355525566051883,
"grad_norm": 1.5234375,
"learning_rate": 0.00048795955885445696,
"loss": 6.0159,
"mean_token_accuracy": 0.15609221607446672,
"num_tokens": 22223772.0,
"step": 11360
},
{
"entropy": 6.1366418361663815,
"epoch": 1.1360523816664168,
"grad_norm": 1.4140625,
"learning_rate": 0.0004879480377981467,
"loss": 5.8898,
"mean_token_accuracy": 0.1610545590519905,
"num_tokens": 22231989.0,
"step": 11365
},
{
"entropy": 6.1556631565094,
"epoch": 1.1365522067276452,
"grad_norm": 1.421875,
"learning_rate": 0.00048793651138411866,
"loss": 5.9214,
"mean_token_accuracy": 0.15981796383857727,
"num_tokens": 22241018.0,
"step": 11370
},
{
"entropy": 6.0874158382415775,
"epoch": 1.137052031788874,
"grad_norm": 1.375,
"learning_rate": 0.00048792497961266273,
"loss": 5.9029,
"mean_token_accuracy": 0.15424375087022782,
"num_tokens": 22250575.0,
"step": 11375
},
{
"entropy": 6.121708822250366,
"epoch": 1.1375518568501024,
"grad_norm": 1.3125,
"learning_rate": 0.00048791344248406916,
"loss": 5.9929,
"mean_token_accuracy": 0.15789100676774978,
"num_tokens": 22259471.0,
"step": 11380
},
{
"entropy": 6.217072534561157,
"epoch": 1.138051681911331,
"grad_norm": 1.4921875,
"learning_rate": 0.00048790189999862814,
"loss": 5.9681,
"mean_token_accuracy": 0.1552117332816124,
"num_tokens": 22269402.0,
"step": 11385
},
{
"entropy": 6.152390098571777,
"epoch": 1.1385515069725596,
"grad_norm": 1.578125,
"learning_rate": 0.00048789035215663013,
"loss": 6.0122,
"mean_token_accuracy": 0.151630799472332,
"num_tokens": 22279685.0,
"step": 11390
},
{
"entropy": 6.170343494415283,
"epoch": 1.1390513320337883,
"grad_norm": 1.4375,
"learning_rate": 0.00048787879895836563,
"loss": 5.9357,
"mean_token_accuracy": 0.15431418418884277,
"num_tokens": 22288628.0,
"step": 11395
},
{
"entropy": 6.229870986938477,
"epoch": 1.1395511570950168,
"grad_norm": 1.4921875,
"learning_rate": 0.0004878672404041253,
"loss": 5.9597,
"mean_token_accuracy": 0.15678505897521972,
"num_tokens": 22297762.0,
"step": 11400
},
{
"entropy": 6.208660221099853,
"epoch": 1.1400509821562452,
"grad_norm": 1.3203125,
"learning_rate": 0.00048785567649419994,
"loss": 6.1304,
"mean_token_accuracy": 0.14967557042837143,
"num_tokens": 22307838.0,
"step": 11405
},
{
"entropy": 6.124197578430175,
"epoch": 1.140550807217474,
"grad_norm": 1.1953125,
"learning_rate": 0.0004878441072288806,
"loss": 5.9103,
"mean_token_accuracy": 0.1615430399775505,
"num_tokens": 22317553.0,
"step": 11410
},
{
"entropy": 6.112193632125854,
"epoch": 1.1410506322787024,
"grad_norm": 1.3125,
"learning_rate": 0.00048783253260845826,
"loss": 5.8345,
"mean_token_accuracy": 0.16616780012845994,
"num_tokens": 22327892.0,
"step": 11415
},
{
"entropy": 6.13757734298706,
"epoch": 1.141550457339931,
"grad_norm": 1.40625,
"learning_rate": 0.0004878209526332242,
"loss": 5.922,
"mean_token_accuracy": 0.16156515702605248,
"num_tokens": 22338363.0,
"step": 11420
},
{
"entropy": 6.150075817108155,
"epoch": 1.1420502824011596,
"grad_norm": 1.40625,
"learning_rate": 0.00048780936730346967,
"loss": 5.915,
"mean_token_accuracy": 0.15303796753287316,
"num_tokens": 22347645.0,
"step": 11425
},
{
"entropy": 6.15480899810791,
"epoch": 1.1425501074623883,
"grad_norm": 1.296875,
"learning_rate": 0.00048779777661948627,
"loss": 5.9766,
"mean_token_accuracy": 0.15863730162382125,
"num_tokens": 22356906.0,
"step": 11430
},
{
"entropy": 6.122133827209472,
"epoch": 1.1430499325236168,
"grad_norm": 1.40625,
"learning_rate": 0.0004877861805815655,
"loss": 5.9222,
"mean_token_accuracy": 0.1561330460011959,
"num_tokens": 22365806.0,
"step": 11435
},
{
"entropy": 6.0671271800994875,
"epoch": 1.1435497575848452,
"grad_norm": 1.5859375,
"learning_rate": 0.0004877745791899993,
"loss": 5.8228,
"mean_token_accuracy": 0.16571658253669738,
"num_tokens": 22374752.0,
"step": 11440
},
{
"entropy": 6.1428862571716305,
"epoch": 1.144049582646074,
"grad_norm": 1.390625,
"learning_rate": 0.00048776297244507936,
"loss": 5.8945,
"mean_token_accuracy": 0.15657515674829484,
"num_tokens": 22383280.0,
"step": 11445
},
{
"entropy": 6.165312623977661,
"epoch": 1.1445494077073024,
"grad_norm": 1.609375,
"learning_rate": 0.00048775136034709784,
"loss": 5.9955,
"mean_token_accuracy": 0.15749927014112472,
"num_tokens": 22393873.0,
"step": 11450
},
{
"entropy": 6.163510656356811,
"epoch": 1.145049232768531,
"grad_norm": 1.7109375,
"learning_rate": 0.00048773974289634676,
"loss": 5.9035,
"mean_token_accuracy": 0.158704175055027,
"num_tokens": 22404880.0,
"step": 11455
},
{
"entropy": 6.19859766960144,
"epoch": 1.1455490578297596,
"grad_norm": 1.2578125,
"learning_rate": 0.0004877281200931185,
"loss": 6.0206,
"mean_token_accuracy": 0.14970198422670364,
"num_tokens": 22414848.0,
"step": 11460
},
{
"entropy": 6.160959148406983,
"epoch": 1.1460488828909883,
"grad_norm": 1.265625,
"learning_rate": 0.00048771649193770554,
"loss": 5.9725,
"mean_token_accuracy": 0.15001334100961686,
"num_tokens": 22425377.0,
"step": 11465
},
{
"entropy": 6.2000030994415285,
"epoch": 1.1465487079522168,
"grad_norm": 1.3125,
"learning_rate": 0.0004877048584304004,
"loss": 5.9616,
"mean_token_accuracy": 0.15394231602549552,
"num_tokens": 22435787.0,
"step": 11470
},
{
"entropy": 6.257690572738648,
"epoch": 1.1470485330134452,
"grad_norm": 1.3359375,
"learning_rate": 0.00048769321957149557,
"loss": 6.1308,
"mean_token_accuracy": 0.1421785295009613,
"num_tokens": 22446540.0,
"step": 11475
},
{
"entropy": 6.150134801864624,
"epoch": 1.147548358074674,
"grad_norm": 1.2421875,
"learning_rate": 0.0004876815753612843,
"loss": 5.946,
"mean_token_accuracy": 0.15582237839698793,
"num_tokens": 22456170.0,
"step": 11480
},
{
"entropy": 6.17533507347107,
"epoch": 1.1480481831359024,
"grad_norm": 1.6484375,
"learning_rate": 0.0004876699258000592,
"loss": 5.9736,
"mean_token_accuracy": 0.1515693411231041,
"num_tokens": 22464502.0,
"step": 11485
},
{
"entropy": 6.2002216339111325,
"epoch": 1.148548008197131,
"grad_norm": 1.328125,
"learning_rate": 0.0004876582708881135,
"loss": 6.0029,
"mean_token_accuracy": 0.1539310559630394,
"num_tokens": 22475093.0,
"step": 11490
},
{
"entropy": 6.204256629943847,
"epoch": 1.1490478332583596,
"grad_norm": 1.421875,
"learning_rate": 0.0004876466106257404,
"loss": 6.019,
"mean_token_accuracy": 0.1511889174580574,
"num_tokens": 22484229.0,
"step": 11495
},
{
"entropy": 6.256861829757691,
"epoch": 1.149547658319588,
"grad_norm": 1.5390625,
"learning_rate": 0.00048763494501323333,
"loss": 6.0411,
"mean_token_accuracy": 0.15025287568569184,
"num_tokens": 22493979.0,
"step": 11500
},
{
"entropy": 6.237468004226685,
"epoch": 1.1500474833808167,
"grad_norm": 1.3125,
"learning_rate": 0.00048762327405088573,
"loss": 5.989,
"mean_token_accuracy": 0.15696250796318054,
"num_tokens": 22504675.0,
"step": 11505
},
{
"entropy": 6.1411888122558596,
"epoch": 1.1505473084420452,
"grad_norm": 1.296875,
"learning_rate": 0.0004876115977389913,
"loss": 5.937,
"mean_token_accuracy": 0.16081333607435228,
"num_tokens": 22514407.0,
"step": 11510
},
{
"entropy": 6.194857406616211,
"epoch": 1.151047133503274,
"grad_norm": 1.3203125,
"learning_rate": 0.00048759991607784375,
"loss": 6.0247,
"mean_token_accuracy": 0.15047699809074402,
"num_tokens": 22524234.0,
"step": 11515
},
{
"entropy": 6.11414155960083,
"epoch": 1.1515469585645024,
"grad_norm": 1.234375,
"learning_rate": 0.00048758822906773706,
"loss": 5.8637,
"mean_token_accuracy": 0.16002584546804427,
"num_tokens": 22534004.0,
"step": 11520
},
{
"entropy": 6.186272096633911,
"epoch": 1.1520467836257309,
"grad_norm": 1.3984375,
"learning_rate": 0.00048757653670896523,
"loss": 6.0321,
"mean_token_accuracy": 0.16344474107027054,
"num_tokens": 22543926.0,
"step": 11525
},
{
"entropy": 6.203880691528321,
"epoch": 1.1525466086869596,
"grad_norm": 1.3515625,
"learning_rate": 0.0004875648390018224,
"loss": 5.9611,
"mean_token_accuracy": 0.16035965383052825,
"num_tokens": 22553671.0,
"step": 11530
},
{
"entropy": 6.146420812606811,
"epoch": 1.153046433748188,
"grad_norm": 1.2890625,
"learning_rate": 0.000487553135946603,
"loss": 5.9182,
"mean_token_accuracy": 0.1558047965168953,
"num_tokens": 22562503.0,
"step": 11535
},
{
"entropy": 6.2046802043914795,
"epoch": 1.1535462588094167,
"grad_norm": 1.25,
"learning_rate": 0.00048754142754360135,
"loss": 5.9458,
"mean_token_accuracy": 0.1544528529047966,
"num_tokens": 22572555.0,
"step": 11540
},
{
"entropy": 6.2499706745147705,
"epoch": 1.1540460838706452,
"grad_norm": 1.296875,
"learning_rate": 0.0004875297137931121,
"loss": 6.0325,
"mean_token_accuracy": 0.1516187831759453,
"num_tokens": 22583720.0,
"step": 11545
},
{
"entropy": 6.164298677444458,
"epoch": 1.154545908931874,
"grad_norm": 1.3359375,
"learning_rate": 0.0004875179946954298,
"loss": 5.9787,
"mean_token_accuracy": 0.1521018013358116,
"num_tokens": 22593373.0,
"step": 11550
},
{
"entropy": 6.18038420677185,
"epoch": 1.1550457339931024,
"grad_norm": 1.3515625,
"learning_rate": 0.00048750627025084955,
"loss": 5.9081,
"mean_token_accuracy": 0.1573541522026062,
"num_tokens": 22604229.0,
"step": 11555
},
{
"entropy": 6.172487592697143,
"epoch": 1.1555455590543309,
"grad_norm": 1.359375,
"learning_rate": 0.0004874945404596662,
"loss": 5.8722,
"mean_token_accuracy": 0.16478561013936996,
"num_tokens": 22613451.0,
"step": 11560
},
{
"entropy": 6.132219648361206,
"epoch": 1.1560453841155596,
"grad_norm": 1.3125,
"learning_rate": 0.00048748280532217485,
"loss": 6.0671,
"mean_token_accuracy": 0.14978796392679214,
"num_tokens": 22622809.0,
"step": 11565
},
{
"entropy": 6.21790566444397,
"epoch": 1.156545209176788,
"grad_norm": 1.65625,
"learning_rate": 0.0004874710648386709,
"loss": 6.0349,
"mean_token_accuracy": 0.14883778393268585,
"num_tokens": 22633121.0,
"step": 11570
},
{
"entropy": 6.207902908325195,
"epoch": 1.1570450342380167,
"grad_norm": 1.2109375,
"learning_rate": 0.0004874593190094496,
"loss": 5.977,
"mean_token_accuracy": 0.1548261061310768,
"num_tokens": 22642346.0,
"step": 11575
},
{
"entropy": 6.162228155136108,
"epoch": 1.1575448592992452,
"grad_norm": 1.265625,
"learning_rate": 0.0004874475678348065,
"loss": 5.9194,
"mean_token_accuracy": 0.1591774970293045,
"num_tokens": 22653157.0,
"step": 11580
},
{
"entropy": 6.172361612319946,
"epoch": 1.158044684360474,
"grad_norm": 1.3984375,
"learning_rate": 0.00048743581131503716,
"loss": 5.9909,
"mean_token_accuracy": 0.15582970380783082,
"num_tokens": 22663841.0,
"step": 11585
},
{
"entropy": 6.320128440856934,
"epoch": 1.1585445094217024,
"grad_norm": 1.671875,
"learning_rate": 0.0004874240494504376,
"loss": 6.0651,
"mean_token_accuracy": 0.15741583704948425,
"num_tokens": 22674242.0,
"step": 11590
},
{
"entropy": 6.120945310592651,
"epoch": 1.1590443344829309,
"grad_norm": 1.25,
"learning_rate": 0.00048741228224130357,
"loss": 5.891,
"mean_token_accuracy": 0.16382880061864852,
"num_tokens": 22683371.0,
"step": 11595
},
{
"entropy": 6.130554676055908,
"epoch": 1.1595441595441596,
"grad_norm": 1.2265625,
"learning_rate": 0.00048740050968793116,
"loss": 5.9234,
"mean_token_accuracy": 0.15389275550842285,
"num_tokens": 22693767.0,
"step": 11600
},
{
"entropy": 6.157484483718872,
"epoch": 1.160043984605388,
"grad_norm": 1.2109375,
"learning_rate": 0.0004873887317906166,
"loss": 5.9831,
"mean_token_accuracy": 0.15227321088314055,
"num_tokens": 22705108.0,
"step": 11605
},
{
"entropy": 6.204415512084961,
"epoch": 1.1605438096666167,
"grad_norm": 1.2421875,
"learning_rate": 0.00048737694854965617,
"loss": 5.8975,
"mean_token_accuracy": 0.1590589240193367,
"num_tokens": 22715244.0,
"step": 11610
},
{
"entropy": 6.136318302154541,
"epoch": 1.1610436347278452,
"grad_norm": 1.3203125,
"learning_rate": 0.00048736515996534644,
"loss": 5.8802,
"mean_token_accuracy": 0.1690744325518608,
"num_tokens": 22724519.0,
"step": 11615
},
{
"entropy": 6.034622764587402,
"epoch": 1.161543459789074,
"grad_norm": 1.28125,
"learning_rate": 0.0004873533660379839,
"loss": 5.8388,
"mean_token_accuracy": 0.16576862186193467,
"num_tokens": 22733847.0,
"step": 11620
},
{
"entropy": 6.082125616073609,
"epoch": 1.1620432848503024,
"grad_norm": 1.4765625,
"learning_rate": 0.00048734156676786525,
"loss": 5.9044,
"mean_token_accuracy": 0.15905808061361312,
"num_tokens": 22743023.0,
"step": 11625
},
{
"entropy": 6.155583667755127,
"epoch": 1.1625431099115309,
"grad_norm": 1.2578125,
"learning_rate": 0.0004873297621552875,
"loss": 5.9702,
"mean_token_accuracy": 0.15693069845438004,
"num_tokens": 22754101.0,
"step": 11630
},
{
"entropy": 6.153883361816407,
"epoch": 1.1630429349727596,
"grad_norm": 1.3125,
"learning_rate": 0.00048731795220054755,
"loss": 5.9143,
"mean_token_accuracy": 0.15300537794828414,
"num_tokens": 22763815.0,
"step": 11635
},
{
"entropy": 6.141056251525879,
"epoch": 1.163542760033988,
"grad_norm": 1.421875,
"learning_rate": 0.0004873061369039425,
"loss": 6.0335,
"mean_token_accuracy": 0.1516496606171131,
"num_tokens": 22774041.0,
"step": 11640
},
{
"entropy": 6.204327249526978,
"epoch": 1.1640425850952167,
"grad_norm": 1.2421875,
"learning_rate": 0.0004872943162657697,
"loss": 6.0123,
"mean_token_accuracy": 0.16086317598819733,
"num_tokens": 22784046.0,
"step": 11645
},
{
"entropy": 6.249092435836792,
"epoch": 1.1645424101564452,
"grad_norm": 1.40625,
"learning_rate": 0.0004872824902863265,
"loss": 6.0314,
"mean_token_accuracy": 0.1481860026717186,
"num_tokens": 22794316.0,
"step": 11650
},
{
"entropy": 6.1565898895263675,
"epoch": 1.165042235217674,
"grad_norm": 1.2578125,
"learning_rate": 0.0004872706589659106,
"loss": 5.9171,
"mean_token_accuracy": 0.16067816466093063,
"num_tokens": 22805185.0,
"step": 11655
},
{
"entropy": 6.132637405395508,
"epoch": 1.1655420602789024,
"grad_norm": 1.28125,
"learning_rate": 0.00048725882230481947,
"loss": 6.0076,
"mean_token_accuracy": 0.1558746039867401,
"num_tokens": 22815336.0,
"step": 11660
},
{
"entropy": 6.207607316970825,
"epoch": 1.1660418853401309,
"grad_norm": 1.6640625,
"learning_rate": 0.00048724698030335096,
"loss": 6.0496,
"mean_token_accuracy": 0.15027876570820808,
"num_tokens": 22825530.0,
"step": 11665
},
{
"entropy": 6.167031574249267,
"epoch": 1.1665417104013596,
"grad_norm": 1.25,
"learning_rate": 0.0004872351329618031,
"loss": 5.8551,
"mean_token_accuracy": 0.1735166698694229,
"num_tokens": 22834194.0,
"step": 11670
},
{
"entropy": 6.179953861236572,
"epoch": 1.167041535462588,
"grad_norm": 1.3046875,
"learning_rate": 0.00048722328028047386,
"loss": 6.0446,
"mean_token_accuracy": 0.14853890910744666,
"num_tokens": 22844688.0,
"step": 11675
},
{
"entropy": 6.223675060272217,
"epoch": 1.1675413605238167,
"grad_norm": 1.4765625,
"learning_rate": 0.00048721142225966146,
"loss": 6.0334,
"mean_token_accuracy": 0.1501857616007328,
"num_tokens": 22855239.0,
"step": 11680
},
{
"entropy": 6.091694021224976,
"epoch": 1.1680411855850452,
"grad_norm": 1.4375,
"learning_rate": 0.0004871995588996644,
"loss": 5.8221,
"mean_token_accuracy": 0.16536771059036254,
"num_tokens": 22866248.0,
"step": 11685
},
{
"entropy": 6.125625944137573,
"epoch": 1.168541010646274,
"grad_norm": 1.3203125,
"learning_rate": 0.0004871876902007809,
"loss": 5.9786,
"mean_token_accuracy": 0.15631398260593415,
"num_tokens": 22876119.0,
"step": 11690
},
{
"entropy": 6.1542541027069095,
"epoch": 1.1690408357075024,
"grad_norm": 1.3671875,
"learning_rate": 0.00048717581616330985,
"loss": 5.8895,
"mean_token_accuracy": 0.1662924036383629,
"num_tokens": 22885854.0,
"step": 11695
},
{
"entropy": 6.202460718154907,
"epoch": 1.1695406607687309,
"grad_norm": 1.234375,
"learning_rate": 0.00048716393678754975,
"loss": 6.0112,
"mean_token_accuracy": 0.1531591981649399,
"num_tokens": 22895544.0,
"step": 11700
},
{
"entropy": 6.215129756927491,
"epoch": 1.1700404858299596,
"grad_norm": 1.4140625,
"learning_rate": 0.0004871520520737996,
"loss": 6.0203,
"mean_token_accuracy": 0.1494310110807419,
"num_tokens": 22904608.0,
"step": 11705
},
{
"entropy": 6.18988265991211,
"epoch": 1.170540310891188,
"grad_norm": 1.3671875,
"learning_rate": 0.0004871401620223585,
"loss": 6.0019,
"mean_token_accuracy": 0.16044313013553618,
"num_tokens": 22914716.0,
"step": 11710
},
{
"entropy": 6.247105264663697,
"epoch": 1.1710401359524167,
"grad_norm": 1.4609375,
"learning_rate": 0.0004871282666335255,
"loss": 6.0721,
"mean_token_accuracy": 0.14879173710942267,
"num_tokens": 22925466.0,
"step": 11715
},
{
"entropy": 6.110837841033936,
"epoch": 1.1715399610136452,
"grad_norm": 1.2109375,
"learning_rate": 0.00048711636590759985,
"loss": 5.9501,
"mean_token_accuracy": 0.15398866906762124,
"num_tokens": 22934499.0,
"step": 11720
},
{
"entropy": 6.146024322509765,
"epoch": 1.172039786074874,
"grad_norm": 1.296875,
"learning_rate": 0.00048710445984488106,
"loss": 5.9468,
"mean_token_accuracy": 0.15472581833600998,
"num_tokens": 22943822.0,
"step": 11725
},
{
"entropy": 6.102200269699097,
"epoch": 1.1725396111361024,
"grad_norm": 1.3984375,
"learning_rate": 0.0004870925484456686,
"loss": 5.9651,
"mean_token_accuracy": 0.15842757895588874,
"num_tokens": 22952375.0,
"step": 11730
},
{
"entropy": 6.163388967514038,
"epoch": 1.1730394361973309,
"grad_norm": 1.4140625,
"learning_rate": 0.0004870806317102622,
"loss": 5.9631,
"mean_token_accuracy": 0.15419413149356842,
"num_tokens": 22961945.0,
"step": 11735
},
{
"entropy": 6.23486738204956,
"epoch": 1.1735392612585596,
"grad_norm": 1.25,
"learning_rate": 0.0004870687096389617,
"loss": 6.0773,
"mean_token_accuracy": 0.15317733585834503,
"num_tokens": 22972029.0,
"step": 11740
},
{
"entropy": 6.223558568954468,
"epoch": 1.174039086319788,
"grad_norm": 1.265625,
"learning_rate": 0.000487056782232067,
"loss": 5.9731,
"mean_token_accuracy": 0.15458502024412155,
"num_tokens": 22980954.0,
"step": 11745
},
{
"entropy": 6.1261388778686525,
"epoch": 1.1745389113810167,
"grad_norm": 1.28125,
"learning_rate": 0.00048704484948987824,
"loss": 5.9165,
"mean_token_accuracy": 0.1554683819413185,
"num_tokens": 22991213.0,
"step": 11750
},
{
"entropy": 6.160103368759155,
"epoch": 1.1750387364422452,
"grad_norm": 1.2578125,
"learning_rate": 0.0004870329114126956,
"loss": 5.9331,
"mean_token_accuracy": 0.15347087979316712,
"num_tokens": 23000833.0,
"step": 11755
},
{
"entropy": 6.233826971054077,
"epoch": 1.1755385615034737,
"grad_norm": 1.3671875,
"learning_rate": 0.0004870209680008196,
"loss": 6.0181,
"mean_token_accuracy": 0.15664072781801225,
"num_tokens": 23010598.0,
"step": 11760
},
{
"entropy": 6.191549396514892,
"epoch": 1.1760383865647024,
"grad_norm": 1.265625,
"learning_rate": 0.0004870090192545505,
"loss": 5.9955,
"mean_token_accuracy": 0.14790518060326577,
"num_tokens": 23019929.0,
"step": 11765
},
{
"entropy": 6.118762683868408,
"epoch": 1.1765382116259309,
"grad_norm": 1.359375,
"learning_rate": 0.000486997065174189,
"loss": 5.9078,
"mean_token_accuracy": 0.15689281672239302,
"num_tokens": 23029880.0,
"step": 11770
},
{
"entropy": 6.16850528717041,
"epoch": 1.1770380366871596,
"grad_norm": 1.1796875,
"learning_rate": 0.00048698510576003593,
"loss": 6.0333,
"mean_token_accuracy": 0.15020066350698472,
"num_tokens": 23039153.0,
"step": 11775
},
{
"entropy": 6.257021236419678,
"epoch": 1.177537861748388,
"grad_norm": 1.3359375,
"learning_rate": 0.00048697314101239217,
"loss": 5.9915,
"mean_token_accuracy": 0.15751764327287673,
"num_tokens": 23049578.0,
"step": 11780
},
{
"entropy": 6.064672136306763,
"epoch": 1.1780376868096165,
"grad_norm": 1.265625,
"learning_rate": 0.0004869611709315587,
"loss": 5.8522,
"mean_token_accuracy": 0.16184662729501725,
"num_tokens": 23058882.0,
"step": 11785
},
{
"entropy": 6.1092462062835695,
"epoch": 1.1785375118708452,
"grad_norm": 1.28125,
"learning_rate": 0.00048694919551783665,
"loss": 5.9683,
"mean_token_accuracy": 0.15907809883356094,
"num_tokens": 23069056.0,
"step": 11790
},
{
"entropy": 6.162931632995606,
"epoch": 1.1790373369320737,
"grad_norm": 1.3359375,
"learning_rate": 0.00048693721477152755,
"loss": 5.9839,
"mean_token_accuracy": 0.15467517226934432,
"num_tokens": 23079155.0,
"step": 11795
},
{
"entropy": 6.288737630844116,
"epoch": 1.1795371619933024,
"grad_norm": 1.296875,
"learning_rate": 0.00048692522869293246,
"loss": 6.1071,
"mean_token_accuracy": 0.14290804862976075,
"num_tokens": 23089001.0,
"step": 11800
},
{
"entropy": 6.1644086837768555,
"epoch": 1.1800369870545309,
"grad_norm": 1.4609375,
"learning_rate": 0.0004869132372823533,
"loss": 5.918,
"mean_token_accuracy": 0.15994679033756257,
"num_tokens": 23098824.0,
"step": 11805
},
{
"entropy": 6.192744874954224,
"epoch": 1.1805368121157596,
"grad_norm": 1.265625,
"learning_rate": 0.00048690124054009157,
"loss": 5.9361,
"mean_token_accuracy": 0.15142097622156142,
"num_tokens": 23107752.0,
"step": 11810
},
{
"entropy": 6.046417665481568,
"epoch": 1.181036637176988,
"grad_norm": 1.25,
"learning_rate": 0.0004868892384664491,
"loss": 5.883,
"mean_token_accuracy": 0.1543777108192444,
"num_tokens": 23116815.0,
"step": 11815
},
{
"entropy": 6.0947174549102785,
"epoch": 1.1815364622382165,
"grad_norm": 1.2421875,
"learning_rate": 0.00048687723106172805,
"loss": 5.8626,
"mean_token_accuracy": 0.15405744910240174,
"num_tokens": 23126093.0,
"step": 11820
},
{
"entropy": 6.251590585708618,
"epoch": 1.1820362872994452,
"grad_norm": 1.4453125,
"learning_rate": 0.00048686521832623026,
"loss": 5.9645,
"mean_token_accuracy": 0.15875712484121324,
"num_tokens": 23135928.0,
"step": 11825
},
{
"entropy": 6.261361694335937,
"epoch": 1.1825361123606737,
"grad_norm": 1.6953125,
"learning_rate": 0.0004868532002602581,
"loss": 6.063,
"mean_token_accuracy": 0.1460098072886467,
"num_tokens": 23145345.0,
"step": 11830
},
{
"entropy": 6.178055095672607,
"epoch": 1.1830359374219024,
"grad_norm": 1.2421875,
"learning_rate": 0.000486841176864114,
"loss": 5.9866,
"mean_token_accuracy": 0.1543113648891449,
"num_tokens": 23155184.0,
"step": 11835
},
{
"entropy": 6.189496088027954,
"epoch": 1.1835357624831309,
"grad_norm": 1.21875,
"learning_rate": 0.00048682914813810035,
"loss": 6.0306,
"mean_token_accuracy": 0.15057751089334487,
"num_tokens": 23166297.0,
"step": 11840
},
{
"entropy": 6.14486174583435,
"epoch": 1.1840355875443596,
"grad_norm": 1.3046875,
"learning_rate": 0.00048681711408251986,
"loss": 5.9121,
"mean_token_accuracy": 0.1537284106016159,
"num_tokens": 23175268.0,
"step": 11845
},
{
"entropy": 6.2232283592224125,
"epoch": 1.184535412605588,
"grad_norm": 1.328125,
"learning_rate": 0.00048680507469767533,
"loss": 5.9371,
"mean_token_accuracy": 0.15343511030077933,
"num_tokens": 23185400.0,
"step": 11850
},
{
"entropy": 6.2029297828674315,
"epoch": 1.1850352376668165,
"grad_norm": 1.3046875,
"learning_rate": 0.0004867930299838696,
"loss": 6.0237,
"mean_token_accuracy": 0.1510491192340851,
"num_tokens": 23194540.0,
"step": 11855
},
{
"entropy": 6.162105989456177,
"epoch": 1.1855350627280452,
"grad_norm": 1.390625,
"learning_rate": 0.00048678097994140566,
"loss": 6.084,
"mean_token_accuracy": 0.15456485450267793,
"num_tokens": 23205049.0,
"step": 11860
},
{
"entropy": 6.232222080230713,
"epoch": 1.1860348877892737,
"grad_norm": 1.34375,
"learning_rate": 0.00048676892457058687,
"loss": 5.9848,
"mean_token_accuracy": 0.15396279692649842,
"num_tokens": 23214369.0,
"step": 11865
},
{
"entropy": 6.1500202178955075,
"epoch": 1.1865347128505024,
"grad_norm": 1.296875,
"learning_rate": 0.0004867568638717164,
"loss": 5.9202,
"mean_token_accuracy": 0.16146257519721985,
"num_tokens": 23223806.0,
"step": 11870
},
{
"entropy": 6.195460510253906,
"epoch": 1.1870345379117309,
"grad_norm": 1.203125,
"learning_rate": 0.00048674479784509766,
"loss": 6.0084,
"mean_token_accuracy": 0.15282646864652633,
"num_tokens": 23233086.0,
"step": 11875
},
{
"entropy": 6.130538272857666,
"epoch": 1.1875343629729596,
"grad_norm": 1.2734375,
"learning_rate": 0.00048673272649103435,
"loss": 5.9486,
"mean_token_accuracy": 0.16294859498739242,
"num_tokens": 23242564.0,
"step": 11880
},
{
"entropy": 6.101591396331787,
"epoch": 1.188034188034188,
"grad_norm": 1.203125,
"learning_rate": 0.00048672064980983013,
"loss": 5.8707,
"mean_token_accuracy": 0.1602120578289032,
"num_tokens": 23252396.0,
"step": 11885
},
{
"entropy": 6.161205863952636,
"epoch": 1.1885340130954165,
"grad_norm": 1.4296875,
"learning_rate": 0.00048670856780178874,
"loss": 5.9889,
"mean_token_accuracy": 0.15480765253305434,
"num_tokens": 23261528.0,
"step": 11890
},
{
"entropy": 6.225141286849976,
"epoch": 1.1890338381566452,
"grad_norm": 1.3671875,
"learning_rate": 0.00048669648046721436,
"loss": 6.0448,
"mean_token_accuracy": 0.15721153765916823,
"num_tokens": 23271794.0,
"step": 11895
},
{
"entropy": 6.222901725769043,
"epoch": 1.1895336632178737,
"grad_norm": 1.2109375,
"learning_rate": 0.000486684387806411,
"loss": 5.9754,
"mean_token_accuracy": 0.1520319923758507,
"num_tokens": 23281340.0,
"step": 11900
},
{
"entropy": 6.202496194839478,
"epoch": 1.1900334882791024,
"grad_norm": 1.3984375,
"learning_rate": 0.00048667228981968285,
"loss": 6.0075,
"mean_token_accuracy": 0.15111462846398355,
"num_tokens": 23290579.0,
"step": 11905
},
{
"entropy": 6.069172430038452,
"epoch": 1.1905333133403309,
"grad_norm": 1.328125,
"learning_rate": 0.00048666018650733446,
"loss": 5.898,
"mean_token_accuracy": 0.16001971513032914,
"num_tokens": 23300762.0,
"step": 11910
},
{
"entropy": 6.121626710891723,
"epoch": 1.1910331384015596,
"grad_norm": 1.3515625,
"learning_rate": 0.0004866480778696702,
"loss": 5.9547,
"mean_token_accuracy": 0.15563222020864487,
"num_tokens": 23310793.0,
"step": 11915
},
{
"entropy": 6.1300910949707035,
"epoch": 1.191532963462788,
"grad_norm": 1.2578125,
"learning_rate": 0.00048663596390699477,
"loss": 5.8641,
"mean_token_accuracy": 0.1581147477030754,
"num_tokens": 23321289.0,
"step": 11920
},
{
"entropy": 6.159178113937378,
"epoch": 1.1920327885240165,
"grad_norm": 1.1953125,
"learning_rate": 0.0004866238446196129,
"loss": 6.0433,
"mean_token_accuracy": 0.1495481550693512,
"num_tokens": 23331173.0,
"step": 11925
},
{
"entropy": 6.2463466167449955,
"epoch": 1.1925326135852452,
"grad_norm": 1.390625,
"learning_rate": 0.0004866117200078296,
"loss": 6.1323,
"mean_token_accuracy": 0.14346483647823333,
"num_tokens": 23341905.0,
"step": 11930
},
{
"entropy": 6.230529260635376,
"epoch": 1.1930324386464737,
"grad_norm": 1.3046875,
"learning_rate": 0.00048659959007194985,
"loss": 5.9735,
"mean_token_accuracy": 0.15860424935817719,
"num_tokens": 23351840.0,
"step": 11935
},
{
"entropy": 6.271266174316406,
"epoch": 1.1935322637077024,
"grad_norm": 1.421875,
"learning_rate": 0.00048658745481227884,
"loss": 6.066,
"mean_token_accuracy": 0.1421751447021961,
"num_tokens": 23362269.0,
"step": 11940
},
{
"entropy": 6.297079181671142,
"epoch": 1.1940320887689309,
"grad_norm": 1.265625,
"learning_rate": 0.000486575314229122,
"loss": 6.1371,
"mean_token_accuracy": 0.1469311907887459,
"num_tokens": 23372431.0,
"step": 11945
},
{
"entropy": 6.239289236068726,
"epoch": 1.1945319138301596,
"grad_norm": 1.859375,
"learning_rate": 0.0004865631683227846,
"loss": 5.8938,
"mean_token_accuracy": 0.15750027745962142,
"num_tokens": 23381650.0,
"step": 11950
},
{
"entropy": 6.064280414581299,
"epoch": 1.195031738891388,
"grad_norm": 1.3828125,
"learning_rate": 0.00048655101709357243,
"loss": 5.8974,
"mean_token_accuracy": 0.1651660308241844,
"num_tokens": 23390842.0,
"step": 11955
},
{
"entropy": 6.111900806427002,
"epoch": 1.1955315639526165,
"grad_norm": 1.3125,
"learning_rate": 0.000486538860541791,
"loss": 5.9164,
"mean_token_accuracy": 0.1615041524171829,
"num_tokens": 23400109.0,
"step": 11960
},
{
"entropy": 6.099809074401856,
"epoch": 1.1960313890138452,
"grad_norm": 1.2734375,
"learning_rate": 0.00048652669866774636,
"loss": 5.8022,
"mean_token_accuracy": 0.1601795196533203,
"num_tokens": 23409234.0,
"step": 11965
},
{
"entropy": 6.120146942138672,
"epoch": 1.1965312140750737,
"grad_norm": 1.3125,
"learning_rate": 0.0004865145314717443,
"loss": 5.9488,
"mean_token_accuracy": 0.1562504068017006,
"num_tokens": 23419094.0,
"step": 11970
},
{
"entropy": 6.233087396621704,
"epoch": 1.1970310391363024,
"grad_norm": 1.3984375,
"learning_rate": 0.00048650235895409115,
"loss": 5.9267,
"mean_token_accuracy": 0.15422954261302949,
"num_tokens": 23428185.0,
"step": 11975
},
{
"entropy": 6.166892004013062,
"epoch": 1.1975308641975309,
"grad_norm": 1.296875,
"learning_rate": 0.0004864901811150931,
"loss": 5.9913,
"mean_token_accuracy": 0.1541443184018135,
"num_tokens": 23438224.0,
"step": 11980
},
{
"entropy": 6.116296577453613,
"epoch": 1.1980306892587596,
"grad_norm": 1.203125,
"learning_rate": 0.0004864779979550564,
"loss": 5.9018,
"mean_token_accuracy": 0.16291505396366118,
"num_tokens": 23447982.0,
"step": 11985
},
{
"entropy": 6.156915616989136,
"epoch": 1.198530514319988,
"grad_norm": 1.1796875,
"learning_rate": 0.0004864658094742878,
"loss": 5.9539,
"mean_token_accuracy": 0.1563790649175644,
"num_tokens": 23458237.0,
"step": 11990
},
{
"entropy": 6.213999795913696,
"epoch": 1.1990303393812165,
"grad_norm": 1.6015625,
"learning_rate": 0.00048645361567309375,
"loss": 6.0088,
"mean_token_accuracy": 0.15272126346826553,
"num_tokens": 23467570.0,
"step": 11995
},
{
"entropy": 6.265379762649536,
"epoch": 1.1995301644424452,
"grad_norm": 1.3203125,
"learning_rate": 0.0004864414165517812,
"loss": 6.0025,
"mean_token_accuracy": 0.15862176865339278,
"num_tokens": 23478192.0,
"step": 12000
},
{
"epoch": 1.1995301644424452,
"eval_entropy": 6.050195842267189,
"eval_loss": 6.077088832855225,
"eval_mean_token_accuracy": 0.15807910671246955,
"eval_num_tokens": 23478192.0,
"eval_runtime": 23.8568,
"eval_samples_per_second": 1301.308,
"eval_steps_per_second": 162.679,
"step": 12000
},
{
"entropy": 6.199899435043335,
"epoch": 1.2000299895036737,
"grad_norm": 1.3203125,
"learning_rate": 0.000486429212110657,
"loss": 6.0296,
"mean_token_accuracy": 0.15094629377126695,
"num_tokens": 23488128.0,
"step": 12005
},
{
"entropy": 6.191727209091186,
"epoch": 1.2005298145649024,
"grad_norm": 1.3125,
"learning_rate": 0.0004864170023500282,
"loss": 6.0276,
"mean_token_accuracy": 0.15196529328823088,
"num_tokens": 23496740.0,
"step": 12010
},
{
"entropy": 6.14084210395813,
"epoch": 1.2010296396261309,
"grad_norm": 1.4453125,
"learning_rate": 0.0004864047872702021,
"loss": 5.8915,
"mean_token_accuracy": 0.16810173839330672,
"num_tokens": 23505606.0,
"step": 12015
},
{
"entropy": 6.147327947616577,
"epoch": 1.2015294646873593,
"grad_norm": 1.671875,
"learning_rate": 0.0004863925668714859,
"loss": 5.8945,
"mean_token_accuracy": 0.15749603807926177,
"num_tokens": 23515001.0,
"step": 12020
},
{
"entropy": 6.156831550598144,
"epoch": 1.202029289748588,
"grad_norm": 1.203125,
"learning_rate": 0.0004863803411541871,
"loss": 6.0392,
"mean_token_accuracy": 0.14907794296741486,
"num_tokens": 23526353.0,
"step": 12025
},
{
"entropy": 6.105481481552124,
"epoch": 1.2025291148098165,
"grad_norm": 1.15625,
"learning_rate": 0.0004863681101186134,
"loss": 5.8411,
"mean_token_accuracy": 0.1668488249182701,
"num_tokens": 23535571.0,
"step": 12030
},
{
"entropy": 6.064318418502808,
"epoch": 1.2030289398710452,
"grad_norm": 1.234375,
"learning_rate": 0.0004863558737650723,
"loss": 5.9277,
"mean_token_accuracy": 0.16584953665733337,
"num_tokens": 23545495.0,
"step": 12035
},
{
"entropy": 6.168333911895752,
"epoch": 1.2035287649322737,
"grad_norm": 1.140625,
"learning_rate": 0.0004863436320938719,
"loss": 5.9089,
"mean_token_accuracy": 0.15826427340507507,
"num_tokens": 23554942.0,
"step": 12040
},
{
"entropy": 6.180454730987549,
"epoch": 1.2040285899935022,
"grad_norm": 1.171875,
"learning_rate": 0.00048633138510532003,
"loss": 5.992,
"mean_token_accuracy": 0.15368711203336716,
"num_tokens": 23564297.0,
"step": 12045
},
{
"entropy": 6.16219687461853,
"epoch": 1.2045284150547308,
"grad_norm": 1.1875,
"learning_rate": 0.00048631913279972497,
"loss": 5.9947,
"mean_token_accuracy": 0.15627450197935105,
"num_tokens": 23574899.0,
"step": 12050
},
{
"entropy": 6.201348829269409,
"epoch": 1.2050282401159593,
"grad_norm": 1.2890625,
"learning_rate": 0.00048630687517739484,
"loss": 6.0546,
"mean_token_accuracy": 0.15214102044701577,
"num_tokens": 23585309.0,
"step": 12055
},
{
"entropy": 6.10280933380127,
"epoch": 1.205528065177188,
"grad_norm": 1.2421875,
"learning_rate": 0.0004862946122386381,
"loss": 5.9048,
"mean_token_accuracy": 0.15918524265289308,
"num_tokens": 23595270.0,
"step": 12060
},
{
"entropy": 6.186801624298096,
"epoch": 1.2060278902384165,
"grad_norm": 1.1484375,
"learning_rate": 0.00048628234398376334,
"loss": 5.9816,
"mean_token_accuracy": 0.1590077519416809,
"num_tokens": 23604698.0,
"step": 12065
},
{
"entropy": 6.159816026687622,
"epoch": 1.2065277152996452,
"grad_norm": 1.296875,
"learning_rate": 0.00048627007041307914,
"loss": 6.0137,
"mean_token_accuracy": 0.15074703842401505,
"num_tokens": 23614588.0,
"step": 12070
},
{
"entropy": 6.098800802230835,
"epoch": 1.2070275403608737,
"grad_norm": 1.2421875,
"learning_rate": 0.00048625779152689435,
"loss": 5.8602,
"mean_token_accuracy": 0.16643391102552413,
"num_tokens": 23624394.0,
"step": 12075
},
{
"entropy": 6.200442790985107,
"epoch": 1.2075273654221022,
"grad_norm": 1.4609375,
"learning_rate": 0.0004862455073255179,
"loss": 5.9267,
"mean_token_accuracy": 0.15674215704202651,
"num_tokens": 23633558.0,
"step": 12080
},
{
"entropy": 6.185452604293824,
"epoch": 1.2080271904833308,
"grad_norm": 1.234375,
"learning_rate": 0.00048623321780925883,
"loss": 5.9803,
"mean_token_accuracy": 0.15276988968253136,
"num_tokens": 23643320.0,
"step": 12085
},
{
"entropy": 6.156462574005127,
"epoch": 1.2085270155445593,
"grad_norm": 1.65625,
"learning_rate": 0.00048622092297842637,
"loss": 6.0712,
"mean_token_accuracy": 0.1507236272096634,
"num_tokens": 23653660.0,
"step": 12090
},
{
"entropy": 6.167096185684204,
"epoch": 1.209026840605788,
"grad_norm": 1.21875,
"learning_rate": 0.0004862086228333298,
"loss": 5.9342,
"mean_token_accuracy": 0.15746346414089202,
"num_tokens": 23662556.0,
"step": 12095
},
{
"entropy": 6.117544746398925,
"epoch": 1.2095266656670165,
"grad_norm": 1.2890625,
"learning_rate": 0.00048619631737427865,
"loss": 5.9434,
"mean_token_accuracy": 0.15573475062847136,
"num_tokens": 23672628.0,
"step": 12100
},
{
"entropy": 6.06883692741394,
"epoch": 1.2100264907282452,
"grad_norm": 1.390625,
"learning_rate": 0.0004861840066015825,
"loss": 5.8632,
"mean_token_accuracy": 0.165093731880188,
"num_tokens": 23682574.0,
"step": 12105
},
{
"entropy": 6.154279470443726,
"epoch": 1.2105263157894737,
"grad_norm": 1.21875,
"learning_rate": 0.00048617169051555113,
"loss": 6.0038,
"mean_token_accuracy": 0.1495068795979023,
"num_tokens": 23691870.0,
"step": 12110
},
{
"entropy": 6.16855206489563,
"epoch": 1.2110261408507021,
"grad_norm": 1.234375,
"learning_rate": 0.0004861593691164942,
"loss": 5.8913,
"mean_token_accuracy": 0.15467180982232093,
"num_tokens": 23701896.0,
"step": 12115
},
{
"entropy": 6.114151191711426,
"epoch": 1.2115259659119308,
"grad_norm": 1.2890625,
"learning_rate": 0.0004861470424047221,
"loss": 5.9388,
"mean_token_accuracy": 0.15587804466485977,
"num_tokens": 23711960.0,
"step": 12120
},
{
"entropy": 6.098422956466675,
"epoch": 1.2120257909731593,
"grad_norm": 1.484375,
"learning_rate": 0.0004861347103805446,
"loss": 6.002,
"mean_token_accuracy": 0.15374198853969573,
"num_tokens": 23721090.0,
"step": 12125
},
{
"entropy": 6.2354999542236325,
"epoch": 1.212525616034388,
"grad_norm": 1.3125,
"learning_rate": 0.0004861223730442722,
"loss": 6.1465,
"mean_token_accuracy": 0.14846143424510955,
"num_tokens": 23731245.0,
"step": 12130
},
{
"entropy": 6.1624328136444095,
"epoch": 1.2130254410956165,
"grad_norm": 1.5625,
"learning_rate": 0.00048611003039621516,
"loss": 5.9823,
"mean_token_accuracy": 0.15259638279676438,
"num_tokens": 23740891.0,
"step": 12135
},
{
"entropy": 6.225450754165649,
"epoch": 1.2135252661568452,
"grad_norm": 1.375,
"learning_rate": 0.0004860976824366841,
"loss": 6.0508,
"mean_token_accuracy": 0.14930666536092757,
"num_tokens": 23751275.0,
"step": 12140
},
{
"entropy": 6.281868028640747,
"epoch": 1.2140250912180737,
"grad_norm": 1.3515625,
"learning_rate": 0.00048608532916598964,
"loss": 6.1028,
"mean_token_accuracy": 0.14672356620430946,
"num_tokens": 23760994.0,
"step": 12145
},
{
"entropy": 6.182911920547485,
"epoch": 1.2145249162793021,
"grad_norm": 1.3046875,
"learning_rate": 0.00048607297058444267,
"loss": 5.8982,
"mean_token_accuracy": 0.15400320142507554,
"num_tokens": 23770084.0,
"step": 12150
},
{
"entropy": 6.094257545471192,
"epoch": 1.2150247413405308,
"grad_norm": 1.8515625,
"learning_rate": 0.0004860606066923541,
"loss": 5.9288,
"mean_token_accuracy": 0.15634187757968904,
"num_tokens": 23780241.0,
"step": 12155
},
{
"entropy": 6.069482231140137,
"epoch": 1.2155245664017593,
"grad_norm": 1.2578125,
"learning_rate": 0.00048604823749003485,
"loss": 5.8901,
"mean_token_accuracy": 0.1635168671607971,
"num_tokens": 23789970.0,
"step": 12160
},
{
"entropy": 6.228507232666016,
"epoch": 1.216024391462988,
"grad_norm": 1.171875,
"learning_rate": 0.0004860358629777963,
"loss": 6.0117,
"mean_token_accuracy": 0.15150651335716248,
"num_tokens": 23799924.0,
"step": 12165
},
{
"entropy": 6.214637088775635,
"epoch": 1.2165242165242165,
"grad_norm": 1.2109375,
"learning_rate": 0.0004860234831559498,
"loss": 5.8825,
"mean_token_accuracy": 0.16508516669273376,
"num_tokens": 23809258.0,
"step": 12170
},
{
"entropy": 6.018302488327026,
"epoch": 1.2170240415854452,
"grad_norm": 1.390625,
"learning_rate": 0.00048601109802480676,
"loss": 5.8768,
"mean_token_accuracy": 0.15989995300769805,
"num_tokens": 23817979.0,
"step": 12175
},
{
"entropy": 6.096931123733521,
"epoch": 1.2175238666466737,
"grad_norm": 1.453125,
"learning_rate": 0.00048599870758467875,
"loss": 5.8733,
"mean_token_accuracy": 0.16377185583114623,
"num_tokens": 23828182.0,
"step": 12180
},
{
"entropy": 6.195300340652466,
"epoch": 1.2180236917079021,
"grad_norm": 1.7578125,
"learning_rate": 0.00048598631183587753,
"loss": 5.8914,
"mean_token_accuracy": 0.16429374366998672,
"num_tokens": 23838135.0,
"step": 12185
},
{
"entropy": 6.103349924087524,
"epoch": 1.2185235167691308,
"grad_norm": 1.1640625,
"learning_rate": 0.00048597391077871504,
"loss": 5.8454,
"mean_token_accuracy": 0.1595311015844345,
"num_tokens": 23847586.0,
"step": 12190
},
{
"entropy": 6.0575824737548825,
"epoch": 1.2190233418303593,
"grad_norm": 1.171875,
"learning_rate": 0.00048596150441350324,
"loss": 5.9005,
"mean_token_accuracy": 0.15736396312713624,
"num_tokens": 23857112.0,
"step": 12195
},
{
"entropy": 6.156764078140259,
"epoch": 1.219523166891588,
"grad_norm": 1.546875,
"learning_rate": 0.0004859490927405543,
"loss": 6.1165,
"mean_token_accuracy": 0.14905385971069335,
"num_tokens": 23866990.0,
"step": 12200
},
{
"entropy": 6.300009441375733,
"epoch": 1.2200229919528165,
"grad_norm": 1.2421875,
"learning_rate": 0.0004859366757601804,
"loss": 6.122,
"mean_token_accuracy": 0.14187795519828797,
"num_tokens": 23877037.0,
"step": 12205
},
{
"entropy": 6.2392415523529055,
"epoch": 1.2205228170140452,
"grad_norm": 1.328125,
"learning_rate": 0.00048592425347269405,
"loss": 6.0376,
"mean_token_accuracy": 0.14966610074043274,
"num_tokens": 23886341.0,
"step": 12210
},
{
"entropy": 6.250817728042603,
"epoch": 1.2210226420752737,
"grad_norm": 1.8671875,
"learning_rate": 0.00048591182587840777,
"loss": 6.0122,
"mean_token_accuracy": 0.15051086097955704,
"num_tokens": 23896143.0,
"step": 12215
},
{
"entropy": 6.28934531211853,
"epoch": 1.2215224671365021,
"grad_norm": 1.265625,
"learning_rate": 0.0004858993929776342,
"loss": 6.0249,
"mean_token_accuracy": 0.15044788718223573,
"num_tokens": 23906086.0,
"step": 12220
},
{
"entropy": 6.184673690795899,
"epoch": 1.2220222921977308,
"grad_norm": 1.34375,
"learning_rate": 0.00048588695477068617,
"loss": 5.9468,
"mean_token_accuracy": 0.1532865807414055,
"num_tokens": 23914669.0,
"step": 12225
},
{
"entropy": 6.153165292739868,
"epoch": 1.2225221172589593,
"grad_norm": 1.359375,
"learning_rate": 0.00048587451125787665,
"loss": 5.9387,
"mean_token_accuracy": 0.15872783213853836,
"num_tokens": 23925461.0,
"step": 12230
},
{
"entropy": 6.092390632629394,
"epoch": 1.223021942320188,
"grad_norm": 1.3984375,
"learning_rate": 0.0004858620624395187,
"loss": 5.9922,
"mean_token_accuracy": 0.1596124455332756,
"num_tokens": 23934436.0,
"step": 12235
},
{
"entropy": 6.150168800354004,
"epoch": 1.2235217673814165,
"grad_norm": 1.2421875,
"learning_rate": 0.00048584960831592547,
"loss": 6.0182,
"mean_token_accuracy": 0.15344582572579385,
"num_tokens": 23944894.0,
"step": 12240
},
{
"entropy": 6.237721967697143,
"epoch": 1.2240215924426452,
"grad_norm": 1.2734375,
"learning_rate": 0.00048583714888741035,
"loss": 5.9093,
"mean_token_accuracy": 0.164944389462471,
"num_tokens": 23954621.0,
"step": 12245
},
{
"entropy": 6.11160798072815,
"epoch": 1.2245214175038737,
"grad_norm": 1.3671875,
"learning_rate": 0.00048582468415428687,
"loss": 5.8995,
"mean_token_accuracy": 0.15842829570174216,
"num_tokens": 23964379.0,
"step": 12250
},
{
"entropy": 6.087403869628906,
"epoch": 1.2250212425651021,
"grad_norm": 1.2734375,
"learning_rate": 0.00048581221411686857,
"loss": 5.8854,
"mean_token_accuracy": 0.1606437861919403,
"num_tokens": 23973414.0,
"step": 12255
},
{
"entropy": 6.1575233936309814,
"epoch": 1.2255210676263308,
"grad_norm": 1.2734375,
"learning_rate": 0.00048579973877546916,
"loss": 5.9403,
"mean_token_accuracy": 0.15637090131640435,
"num_tokens": 23982912.0,
"step": 12260
},
{
"entropy": 6.299131298065186,
"epoch": 1.2260208926875593,
"grad_norm": 1.1953125,
"learning_rate": 0.00048578725813040263,
"loss": 6.076,
"mean_token_accuracy": 0.14022471606731415,
"num_tokens": 23993927.0,
"step": 12265
},
{
"entropy": 6.163681840896606,
"epoch": 1.226520717748788,
"grad_norm": 1.421875,
"learning_rate": 0.0004857747721819829,
"loss": 5.8892,
"mean_token_accuracy": 0.1539958342909813,
"num_tokens": 24003518.0,
"step": 12270
},
{
"entropy": 6.11926851272583,
"epoch": 1.2270205428100165,
"grad_norm": 1.3203125,
"learning_rate": 0.0004857622809305241,
"loss": 5.9938,
"mean_token_accuracy": 0.16001538932323456,
"num_tokens": 24013013.0,
"step": 12275
},
{
"entropy": 6.231849479675293,
"epoch": 1.2275203678712452,
"grad_norm": 1.265625,
"learning_rate": 0.00048574978437634057,
"loss": 6.0715,
"mean_token_accuracy": 0.1545599564909935,
"num_tokens": 24022276.0,
"step": 12280
},
{
"entropy": 6.086420345306396,
"epoch": 1.2280201929324737,
"grad_norm": 1.1953125,
"learning_rate": 0.0004857372825197468,
"loss": 5.8851,
"mean_token_accuracy": 0.16119584143161775,
"num_tokens": 24032165.0,
"step": 12285
},
{
"entropy": 6.201887893676758,
"epoch": 1.2285200179937021,
"grad_norm": 1.3828125,
"learning_rate": 0.0004857247753610571,
"loss": 5.9491,
"mean_token_accuracy": 0.15815795063972474,
"num_tokens": 24041313.0,
"step": 12290
},
{
"entropy": 6.220150566101074,
"epoch": 1.2290198430549308,
"grad_norm": 1.265625,
"learning_rate": 0.00048571226290058635,
"loss": 6.0064,
"mean_token_accuracy": 0.1566406197845936,
"num_tokens": 24050810.0,
"step": 12295
},
{
"entropy": 6.1585455417633055,
"epoch": 1.2295196681161593,
"grad_norm": 1.40625,
"learning_rate": 0.0004856997451386492,
"loss": 5.9369,
"mean_token_accuracy": 0.16096862852573396,
"num_tokens": 24060582.0,
"step": 12300
},
{
"entropy": 6.1547523021698,
"epoch": 1.2300194931773878,
"grad_norm": 1.265625,
"learning_rate": 0.0004856872220755607,
"loss": 6.0176,
"mean_token_accuracy": 0.15021227300167084,
"num_tokens": 24070208.0,
"step": 12305
},
{
"entropy": 6.055608701705933,
"epoch": 1.2305193182386165,
"grad_norm": 1.2421875,
"learning_rate": 0.000485674693711636,
"loss": 5.9667,
"mean_token_accuracy": 0.15747600495815278,
"num_tokens": 24080837.0,
"step": 12310
},
{
"entropy": 6.156947278976441,
"epoch": 1.231019143299845,
"grad_norm": 1.3828125,
"learning_rate": 0.0004856621600471901,
"loss": 5.9748,
"mean_token_accuracy": 0.15534792095422745,
"num_tokens": 24090696.0,
"step": 12315
},
{
"entropy": 6.246610927581787,
"epoch": 1.2315189683610737,
"grad_norm": 1.3046875,
"learning_rate": 0.00048564962108253853,
"loss": 6.0324,
"mean_token_accuracy": 0.1530123807489872,
"num_tokens": 24100957.0,
"step": 12320
},
{
"entropy": 6.222395229339599,
"epoch": 1.2320187934223021,
"grad_norm": 1.375,
"learning_rate": 0.0004856370768179967,
"loss": 5.9551,
"mean_token_accuracy": 0.16419268846511842,
"num_tokens": 24109177.0,
"step": 12325
},
{
"entropy": 6.098350715637207,
"epoch": 1.2325186184835308,
"grad_norm": 1.375,
"learning_rate": 0.00048562452725388024,
"loss": 5.9636,
"mean_token_accuracy": 0.15708701759576799,
"num_tokens": 24118918.0,
"step": 12330
},
{
"entropy": 6.128720283508301,
"epoch": 1.2330184435447593,
"grad_norm": 1.2890625,
"learning_rate": 0.0004856119723905048,
"loss": 5.8923,
"mean_token_accuracy": 0.15524128675460816,
"num_tokens": 24128255.0,
"step": 12335
},
{
"entropy": 6.211879444122315,
"epoch": 1.2335182686059878,
"grad_norm": 1.1953125,
"learning_rate": 0.0004855994122281864,
"loss": 5.9818,
"mean_token_accuracy": 0.15366657227277755,
"num_tokens": 24137670.0,
"step": 12340
},
{
"entropy": 6.130569410324097,
"epoch": 1.2340180936672165,
"grad_norm": 1.375,
"learning_rate": 0.00048558684676724083,
"loss": 5.9443,
"mean_token_accuracy": 0.15951559990644454,
"num_tokens": 24147417.0,
"step": 12345
},
{
"entropy": 6.1573724269866945,
"epoch": 1.234517918728445,
"grad_norm": 1.21875,
"learning_rate": 0.00048557427600798454,
"loss": 5.9636,
"mean_token_accuracy": 0.15548376441001893,
"num_tokens": 24158019.0,
"step": 12350
},
{
"entropy": 6.195652484893799,
"epoch": 1.2350177437896737,
"grad_norm": 1.390625,
"learning_rate": 0.0004855616999507336,
"loss": 5.9889,
"mean_token_accuracy": 0.15028104186058044,
"num_tokens": 24168118.0,
"step": 12355
},
{
"entropy": 6.213690233230591,
"epoch": 1.2355175688509021,
"grad_norm": 1.3671875,
"learning_rate": 0.00048554911859580445,
"loss": 6.0358,
"mean_token_accuracy": 0.1507461652159691,
"num_tokens": 24177700.0,
"step": 12360
},
{
"entropy": 6.143312883377075,
"epoch": 1.2360173939121308,
"grad_norm": 1.359375,
"learning_rate": 0.0004855365319435137,
"loss": 5.9379,
"mean_token_accuracy": 0.16281663924455642,
"num_tokens": 24187701.0,
"step": 12365
},
{
"entropy": 6.149842309951782,
"epoch": 1.2365172189733593,
"grad_norm": 1.2890625,
"learning_rate": 0.000485523939994178,
"loss": 5.9403,
"mean_token_accuracy": 0.15686926245689392,
"num_tokens": 24197364.0,
"step": 12370
},
{
"entropy": 6.153480577468872,
"epoch": 1.2370170440345878,
"grad_norm": 1.4296875,
"learning_rate": 0.0004855113427481141,
"loss": 6.0088,
"mean_token_accuracy": 0.15855405032634734,
"num_tokens": 24208015.0,
"step": 12375
},
{
"entropy": 6.149875164031982,
"epoch": 1.2375168690958165,
"grad_norm": 1.3125,
"learning_rate": 0.000485498740205639,
"loss": 5.9812,
"mean_token_accuracy": 0.15330363661050797,
"num_tokens": 24218576.0,
"step": 12380
},
{
"entropy": 6.2113172054290775,
"epoch": 1.238016694157045,
"grad_norm": 1.515625,
"learning_rate": 0.00048548613236706976,
"loss": 6.0093,
"mean_token_accuracy": 0.151277507096529,
"num_tokens": 24228727.0,
"step": 12385
},
{
"entropy": 6.156699705123901,
"epoch": 1.2385165192182737,
"grad_norm": 1.203125,
"learning_rate": 0.0004854735192327236,
"loss": 5.9657,
"mean_token_accuracy": 0.16014844924211502,
"num_tokens": 24238580.0,
"step": 12390
},
{
"entropy": 6.17481050491333,
"epoch": 1.2390163442795021,
"grad_norm": 1.1953125,
"learning_rate": 0.00048546090080291783,
"loss": 5.9352,
"mean_token_accuracy": 0.15282906144857406,
"num_tokens": 24249543.0,
"step": 12395
},
{
"entropy": 6.122203302383423,
"epoch": 1.2395161693407308,
"grad_norm": 1.4453125,
"learning_rate": 0.00048544827707797,
"loss": 5.9602,
"mean_token_accuracy": 0.15565237849950792,
"num_tokens": 24259346.0,
"step": 12400
},
{
"entropy": 6.183234977722168,
"epoch": 1.2400159944019593,
"grad_norm": 1.3359375,
"learning_rate": 0.00048543564805819764,
"loss": 5.8678,
"mean_token_accuracy": 0.1634332776069641,
"num_tokens": 24267987.0,
"step": 12405
},
{
"entropy": 6.0854127407073975,
"epoch": 1.2405158194631878,
"grad_norm": 1.265625,
"learning_rate": 0.0004854230137439185,
"loss": 5.8558,
"mean_token_accuracy": 0.16354030668735503,
"num_tokens": 24278398.0,
"step": 12410
},
{
"entropy": 6.27455358505249,
"epoch": 1.2410156445244165,
"grad_norm": 2.109375,
"learning_rate": 0.00048541037413545046,
"loss": 6.1808,
"mean_token_accuracy": 0.14410172551870346,
"num_tokens": 24289425.0,
"step": 12415
},
{
"entropy": 6.233187484741211,
"epoch": 1.241515469585645,
"grad_norm": 1.46875,
"learning_rate": 0.0004853977292331116,
"loss": 6.004,
"mean_token_accuracy": 0.15627337321639062,
"num_tokens": 24298866.0,
"step": 12420
},
{
"entropy": 6.216458940505982,
"epoch": 1.2420152946468737,
"grad_norm": 1.2578125,
"learning_rate": 0.0004853850790372201,
"loss": 5.9109,
"mean_token_accuracy": 0.16707831248641014,
"num_tokens": 24309237.0,
"step": 12425
},
{
"entropy": 6.127988386154175,
"epoch": 1.2425151197081021,
"grad_norm": 1.3359375,
"learning_rate": 0.00048537242354809403,
"loss": 5.9041,
"mean_token_accuracy": 0.15482162311673164,
"num_tokens": 24320175.0,
"step": 12430
},
{
"entropy": 6.0925554752349855,
"epoch": 1.2430149447693308,
"grad_norm": 2.140625,
"learning_rate": 0.00048535976276605186,
"loss": 5.94,
"mean_token_accuracy": 0.15460563749074935,
"num_tokens": 24328896.0,
"step": 12435
},
{
"entropy": 6.20690884590149,
"epoch": 1.2435147698305593,
"grad_norm": 1.4296875,
"learning_rate": 0.0004853470966914123,
"loss": 5.9924,
"mean_token_accuracy": 0.15424013435840606,
"num_tokens": 24337988.0,
"step": 12440
},
{
"entropy": 6.194861936569214,
"epoch": 1.2440145948917878,
"grad_norm": 1.484375,
"learning_rate": 0.0004853344253244939,
"loss": 5.8915,
"mean_token_accuracy": 0.16522590070962906,
"num_tokens": 24347154.0,
"step": 12445
},
{
"entropy": 6.172908687591553,
"epoch": 1.2445144199530165,
"grad_norm": 1.5703125,
"learning_rate": 0.00048532174866561543,
"loss": 6.0144,
"mean_token_accuracy": 0.1485647216439247,
"num_tokens": 24357564.0,
"step": 12450
},
{
"entropy": 6.1157862663269045,
"epoch": 1.245014245014245,
"grad_norm": 1.421875,
"learning_rate": 0.00048530906671509597,
"loss": 5.9035,
"mean_token_accuracy": 0.15980457365512848,
"num_tokens": 24366413.0,
"step": 12455
},
{
"entropy": 6.128127717971802,
"epoch": 1.2455140700754737,
"grad_norm": 1.28125,
"learning_rate": 0.00048529637947325444,
"loss": 5.8593,
"mean_token_accuracy": 0.16693251430988312,
"num_tokens": 24374950.0,
"step": 12460
},
{
"entropy": 5.98353590965271,
"epoch": 1.2460138951367021,
"grad_norm": 1.4921875,
"learning_rate": 0.0004852836869404101,
"loss": 5.6992,
"mean_token_accuracy": 0.17168040797114373,
"num_tokens": 24384354.0,
"step": 12465
},
{
"entropy": 6.108272361755371,
"epoch": 1.2465137201979308,
"grad_norm": 1.390625,
"learning_rate": 0.0004852709891168823,
"loss": 5.9202,
"mean_token_accuracy": 0.15317668169736862,
"num_tokens": 24395671.0,
"step": 12470
},
{
"entropy": 6.210268545150757,
"epoch": 1.2470135452591593,
"grad_norm": 1.3125,
"learning_rate": 0.0004852582860029906,
"loss": 5.9122,
"mean_token_accuracy": 0.15453821420669556,
"num_tokens": 24404497.0,
"step": 12475
},
{
"entropy": 6.07373571395874,
"epoch": 1.2475133703203878,
"grad_norm": 1.4921875,
"learning_rate": 0.00048524557759905445,
"loss": 5.9138,
"mean_token_accuracy": 0.15981688350439072,
"num_tokens": 24413651.0,
"step": 12480
},
{
"entropy": 6.109033870697021,
"epoch": 1.2480131953816165,
"grad_norm": 1.453125,
"learning_rate": 0.0004852328639053937,
"loss": 5.9806,
"mean_token_accuracy": 0.15506304055452347,
"num_tokens": 24424037.0,
"step": 12485
},
{
"entropy": 6.166393852233886,
"epoch": 1.248513020442845,
"grad_norm": 1.265625,
"learning_rate": 0.0004852201449223282,
"loss": 5.8688,
"mean_token_accuracy": 0.16324560344219208,
"num_tokens": 24433005.0,
"step": 12490
},
{
"entropy": 6.181481122970581,
"epoch": 1.2490128455040737,
"grad_norm": 1.3671875,
"learning_rate": 0.000485207420650178,
"loss": 6.0455,
"mean_token_accuracy": 0.14739421606063843,
"num_tokens": 24443241.0,
"step": 12495
},
{
"entropy": 6.192589807510376,
"epoch": 1.2495126705653021,
"grad_norm": 1.296875,
"learning_rate": 0.0004851946910892631,
"loss": 5.9055,
"mean_token_accuracy": 0.1573794886469841,
"num_tokens": 24452676.0,
"step": 12500
},
{
"entropy": 6.198310089111328,
"epoch": 1.2500124956265308,
"grad_norm": 1.2734375,
"learning_rate": 0.0004851819562399039,
"loss": 5.9903,
"mean_token_accuracy": 0.1519806668162346,
"num_tokens": 24462287.0,
"step": 12505
},
{
"entropy": 6.2249424934387205,
"epoch": 1.2505123206877593,
"grad_norm": 1.3671875,
"learning_rate": 0.0004851692161024207,
"loss": 6.0557,
"mean_token_accuracy": 0.1481504112482071,
"num_tokens": 24471707.0,
"step": 12510
},
{
"entropy": 6.179369068145752,
"epoch": 1.2510121457489878,
"grad_norm": 1.5859375,
"learning_rate": 0.00048515647067713425,
"loss": 5.9241,
"mean_token_accuracy": 0.15510827153921128,
"num_tokens": 24481920.0,
"step": 12515
},
{
"entropy": 6.094916772842407,
"epoch": 1.2515119708102165,
"grad_norm": 1.375,
"learning_rate": 0.000485143719964365,
"loss": 5.8493,
"mean_token_accuracy": 0.16588624864816665,
"num_tokens": 24491890.0,
"step": 12520
},
{
"entropy": 6.112090253829956,
"epoch": 1.252011795871445,
"grad_norm": 1.203125,
"learning_rate": 0.0004851309639644338,
"loss": 5.94,
"mean_token_accuracy": 0.15722692161798477,
"num_tokens": 24501563.0,
"step": 12525
},
{
"entropy": 6.155604076385498,
"epoch": 1.2525116209326734,
"grad_norm": 1.4609375,
"learning_rate": 0.0004851182026776616,
"loss": 5.8743,
"mean_token_accuracy": 0.16577624678611755,
"num_tokens": 24511828.0,
"step": 12530
},
{
"entropy": 6.203512382507324,
"epoch": 1.2530114459939021,
"grad_norm": 1.8984375,
"learning_rate": 0.0004851054361043696,
"loss": 5.9352,
"mean_token_accuracy": 0.1568019226193428,
"num_tokens": 24521695.0,
"step": 12535
},
{
"entropy": 6.209982252120971,
"epoch": 1.2535112710551308,
"grad_norm": 1.2734375,
"learning_rate": 0.00048509266424487873,
"loss": 6.0153,
"mean_token_accuracy": 0.1475982442498207,
"num_tokens": 24531755.0,
"step": 12540
},
{
"entropy": 6.174740266799927,
"epoch": 1.2540110961163593,
"grad_norm": 1.2578125,
"learning_rate": 0.0004850798870995106,
"loss": 5.9125,
"mean_token_accuracy": 0.1610000878572464,
"num_tokens": 24540221.0,
"step": 12545
},
{
"entropy": 6.198403358459473,
"epoch": 1.2545109211775878,
"grad_norm": 1.4296875,
"learning_rate": 0.00048506710466858657,
"loss": 5.9395,
"mean_token_accuracy": 0.15496189147233963,
"num_tokens": 24549749.0,
"step": 12550
},
{
"entropy": 6.190253353118896,
"epoch": 1.2550107462388165,
"grad_norm": 1.3671875,
"learning_rate": 0.00048505431695242823,
"loss": 5.9745,
"mean_token_accuracy": 0.15337319523096085,
"num_tokens": 24559318.0,
"step": 12555
},
{
"entropy": 6.205845022201538,
"epoch": 1.255510571300045,
"grad_norm": 1.34375,
"learning_rate": 0.00048504152395135726,
"loss": 5.9933,
"mean_token_accuracy": 0.1553647756576538,
"num_tokens": 24568779.0,
"step": 12560
},
{
"entropy": 6.143230152130127,
"epoch": 1.2560103963612734,
"grad_norm": 1.4296875,
"learning_rate": 0.00048502872566569564,
"loss": 5.9804,
"mean_token_accuracy": 0.14577547758817672,
"num_tokens": 24578258.0,
"step": 12565
},
{
"entropy": 6.197085571289063,
"epoch": 1.2565102214225021,
"grad_norm": 1.265625,
"learning_rate": 0.00048501592209576535,
"loss": 5.9536,
"mean_token_accuracy": 0.15800777673721314,
"num_tokens": 24587485.0,
"step": 12570
},
{
"entropy": 6.163204336166382,
"epoch": 1.2570100464837308,
"grad_norm": 1.40625,
"learning_rate": 0.0004850031132418885,
"loss": 5.9331,
"mean_token_accuracy": 0.1545553222298622,
"num_tokens": 24597656.0,
"step": 12575
},
{
"entropy": 6.150587320327759,
"epoch": 1.2575098715449593,
"grad_norm": 1.3125,
"learning_rate": 0.00048499029910438734,
"loss": 5.8624,
"mean_token_accuracy": 0.15785117894411088,
"num_tokens": 24606986.0,
"step": 12580
},
{
"entropy": 6.122126674652099,
"epoch": 1.2580096966061878,
"grad_norm": 1.3359375,
"learning_rate": 0.00048497747968358424,
"loss": 5.8975,
"mean_token_accuracy": 0.1607358291745186,
"num_tokens": 24617091.0,
"step": 12585
},
{
"entropy": 6.156837511062622,
"epoch": 1.2585095216674165,
"grad_norm": 1.421875,
"learning_rate": 0.0004849646549798019,
"loss": 5.9413,
"mean_token_accuracy": 0.15593989938497543,
"num_tokens": 24627139.0,
"step": 12590
},
{
"entropy": 6.296873998641968,
"epoch": 1.259009346728645,
"grad_norm": 1.2578125,
"learning_rate": 0.00048495182499336275,
"loss": 6.0213,
"mean_token_accuracy": 0.14943011328577996,
"num_tokens": 24635632.0,
"step": 12595
},
{
"entropy": 6.174128866195678,
"epoch": 1.2595091717898734,
"grad_norm": 2.25,
"learning_rate": 0.00048493898972458985,
"loss": 5.9751,
"mean_token_accuracy": 0.15206774920225144,
"num_tokens": 24646590.0,
"step": 12600
},
{
"entropy": 6.177919530868531,
"epoch": 1.2600089968511021,
"grad_norm": 1.4296875,
"learning_rate": 0.0004849261491738059,
"loss": 6.046,
"mean_token_accuracy": 0.14794811233878136,
"num_tokens": 24656865.0,
"step": 12605
},
{
"entropy": 6.223530673980713,
"epoch": 1.2605088219123306,
"grad_norm": 1.2109375,
"learning_rate": 0.00048491330334133405,
"loss": 6.0435,
"mean_token_accuracy": 0.14721440821886062,
"num_tokens": 24666438.0,
"step": 12610
},
{
"entropy": 6.234167051315308,
"epoch": 1.2610086469735593,
"grad_norm": 1.265625,
"learning_rate": 0.00048490045222749744,
"loss": 5.9879,
"mean_token_accuracy": 0.15502232760190965,
"num_tokens": 24675935.0,
"step": 12615
},
{
"entropy": 6.115681171417236,
"epoch": 1.2615084720347878,
"grad_norm": 1.390625,
"learning_rate": 0.00048488759583261955,
"loss": 5.8836,
"mean_token_accuracy": 0.16638837456703187,
"num_tokens": 24686165.0,
"step": 12620
},
{
"entropy": 6.1963643550872805,
"epoch": 1.2620082970960165,
"grad_norm": 1.2109375,
"learning_rate": 0.0004848747341570238,
"loss": 5.9733,
"mean_token_accuracy": 0.1505975231528282,
"num_tokens": 24696564.0,
"step": 12625
},
{
"entropy": 6.18072543144226,
"epoch": 1.262508122157245,
"grad_norm": 1.2265625,
"learning_rate": 0.00048486186720103364,
"loss": 5.9166,
"mean_token_accuracy": 0.15619558095932007,
"num_tokens": 24706462.0,
"step": 12630
},
{
"entropy": 6.1127362728118895,
"epoch": 1.2630079472184734,
"grad_norm": 1.3359375,
"learning_rate": 0.000484848994964973,
"loss": 5.9055,
"mean_token_accuracy": 0.15823880210518837,
"num_tokens": 24715153.0,
"step": 12635
},
{
"entropy": 6.076861619949341,
"epoch": 1.2635077722797021,
"grad_norm": 1.4140625,
"learning_rate": 0.00048483611744916556,
"loss": 5.9402,
"mean_token_accuracy": 0.15647810325026512,
"num_tokens": 24725215.0,
"step": 12640
},
{
"entropy": 6.097990655899048,
"epoch": 1.2640075973409306,
"grad_norm": 1.40625,
"learning_rate": 0.00048482323465393545,
"loss": 5.9287,
"mean_token_accuracy": 0.16446128636598586,
"num_tokens": 24735081.0,
"step": 12645
},
{
"entropy": 6.158984375,
"epoch": 1.2645074224021593,
"grad_norm": 1.21875,
"learning_rate": 0.0004848103465796067,
"loss": 5.9042,
"mean_token_accuracy": 0.16131824851036072,
"num_tokens": 24744948.0,
"step": 12650
},
{
"entropy": 6.104265594482422,
"epoch": 1.2650072474633878,
"grad_norm": 1.2734375,
"learning_rate": 0.0004847974532265037,
"loss": 5.9158,
"mean_token_accuracy": 0.15820914506912231,
"num_tokens": 24754123.0,
"step": 12655
},
{
"entropy": 6.1608141422271725,
"epoch": 1.2655070725246165,
"grad_norm": 1.5625,
"learning_rate": 0.0004847845545949507,
"loss": 6.0207,
"mean_token_accuracy": 0.14851216673851014,
"num_tokens": 24763864.0,
"step": 12660
},
{
"entropy": 6.2003148078918455,
"epoch": 1.266006897585845,
"grad_norm": 1.296875,
"learning_rate": 0.00048477165068527237,
"loss": 6.0028,
"mean_token_accuracy": 0.15384961515665055,
"num_tokens": 24774088.0,
"step": 12665
},
{
"entropy": 6.185011291503907,
"epoch": 1.2665067226470734,
"grad_norm": 1.4375,
"learning_rate": 0.00048475874149779313,
"loss": 5.9237,
"mean_token_accuracy": 0.16217005923390387,
"num_tokens": 24782485.0,
"step": 12670
},
{
"entropy": 6.165617418289185,
"epoch": 1.2670065477083021,
"grad_norm": 1.40625,
"learning_rate": 0.000484745827032838,
"loss": 5.927,
"mean_token_accuracy": 0.15649309605360032,
"num_tokens": 24791776.0,
"step": 12675
},
{
"entropy": 6.19484167098999,
"epoch": 1.2675063727695306,
"grad_norm": 1.4140625,
"learning_rate": 0.00048473290729073194,
"loss": 5.9892,
"mean_token_accuracy": 0.1556473195552826,
"num_tokens": 24802053.0,
"step": 12680
},
{
"entropy": 6.1477924346923825,
"epoch": 1.2680061978307593,
"grad_norm": 1.5,
"learning_rate": 0.0004847199822717998,
"loss": 5.9218,
"mean_token_accuracy": 0.15525194704532624,
"num_tokens": 24811235.0,
"step": 12685
},
{
"entropy": 6.190126228332519,
"epoch": 1.2685060228919878,
"grad_norm": 1.28125,
"learning_rate": 0.0004847070519763668,
"loss": 6.0308,
"mean_token_accuracy": 0.14525450244545937,
"num_tokens": 24821904.0,
"step": 12690
},
{
"entropy": 6.148566150665284,
"epoch": 1.2690058479532165,
"grad_norm": 1.1484375,
"learning_rate": 0.0004846941164047585,
"loss": 5.9223,
"mean_token_accuracy": 0.15534555315971374,
"num_tokens": 24831555.0,
"step": 12695
},
{
"entropy": 6.306117582321167,
"epoch": 1.269505673014445,
"grad_norm": 1.2421875,
"learning_rate": 0.00048468117555730013,
"loss": 6.0668,
"mean_token_accuracy": 0.15397983714938163,
"num_tokens": 24841840.0,
"step": 12700
},
{
"entropy": 6.118523263931275,
"epoch": 1.2700054980756734,
"grad_norm": 1.2734375,
"learning_rate": 0.0004846682294343173,
"loss": 5.9343,
"mean_token_accuracy": 0.15664737299084663,
"num_tokens": 24850172.0,
"step": 12705
},
{
"entropy": 6.175709772109985,
"epoch": 1.2705053231369021,
"grad_norm": 1.328125,
"learning_rate": 0.0004846552780361358,
"loss": 5.9189,
"mean_token_accuracy": 0.15455542802810668,
"num_tokens": 24860433.0,
"step": 12710
},
{
"entropy": 6.2268554210662845,
"epoch": 1.2710051481981306,
"grad_norm": 1.140625,
"learning_rate": 0.00048464232136308146,
"loss": 5.9968,
"mean_token_accuracy": 0.15506697446107864,
"num_tokens": 24870677.0,
"step": 12715
},
{
"entropy": 6.203292798995972,
"epoch": 1.2715049732593593,
"grad_norm": 1.234375,
"learning_rate": 0.0004846293594154802,
"loss": 5.9956,
"mean_token_accuracy": 0.15151088386774064,
"num_tokens": 24881804.0,
"step": 12720
},
{
"entropy": 6.167476034164428,
"epoch": 1.2720047983205878,
"grad_norm": 1.1796875,
"learning_rate": 0.0004846163921936583,
"loss": 5.9184,
"mean_token_accuracy": 0.1620791420340538,
"num_tokens": 24892632.0,
"step": 12725
},
{
"entropy": 6.171008062362671,
"epoch": 1.2725046233818165,
"grad_norm": 1.2421875,
"learning_rate": 0.00048460341969794183,
"loss": 5.9572,
"mean_token_accuracy": 0.15405600816011428,
"num_tokens": 24902055.0,
"step": 12730
},
{
"entropy": 6.235155916213989,
"epoch": 1.273004448443045,
"grad_norm": 1.2734375,
"learning_rate": 0.00048459044192865726,
"loss": 6.081,
"mean_token_accuracy": 0.14752552807331085,
"num_tokens": 24912450.0,
"step": 12735
},
{
"entropy": 6.225162410736084,
"epoch": 1.2735042735042734,
"grad_norm": 1.203125,
"learning_rate": 0.0004845774588861311,
"loss": 5.9905,
"mean_token_accuracy": 0.15358151495456696,
"num_tokens": 24922206.0,
"step": 12740
},
{
"entropy": 6.1136133670806885,
"epoch": 1.2740040985655021,
"grad_norm": 1.234375,
"learning_rate": 0.00048456447057069004,
"loss": 5.7777,
"mean_token_accuracy": 0.16790566295385362,
"num_tokens": 24931295.0,
"step": 12745
},
{
"entropy": 6.075013589859009,
"epoch": 1.2745039236267306,
"grad_norm": 1.2265625,
"learning_rate": 0.00048455147698266084,
"loss": 5.8873,
"mean_token_accuracy": 0.16287400871515273,
"num_tokens": 24940979.0,
"step": 12750
},
{
"entropy": 6.0834370136260985,
"epoch": 1.2750037486879593,
"grad_norm": 1.265625,
"learning_rate": 0.0004845384781223703,
"loss": 5.9452,
"mean_token_accuracy": 0.15070963203907012,
"num_tokens": 24950704.0,
"step": 12755
},
{
"entropy": 6.237839412689209,
"epoch": 1.2755035737491878,
"grad_norm": 1.21875,
"learning_rate": 0.00048452547399014566,
"loss": 6.032,
"mean_token_accuracy": 0.15142979919910432,
"num_tokens": 24961667.0,
"step": 12760
},
{
"entropy": 6.181571531295776,
"epoch": 1.2760033988104165,
"grad_norm": 1.3515625,
"learning_rate": 0.000484512464586314,
"loss": 5.982,
"mean_token_accuracy": 0.15340655744075776,
"num_tokens": 24971531.0,
"step": 12765
},
{
"entropy": 6.122630310058594,
"epoch": 1.276503223871645,
"grad_norm": 1.328125,
"learning_rate": 0.00048449944991120264,
"loss": 5.8567,
"mean_token_accuracy": 0.1574491396546364,
"num_tokens": 24981002.0,
"step": 12770
},
{
"entropy": 6.146213483810425,
"epoch": 1.2770030489328734,
"grad_norm": 1.375,
"learning_rate": 0.0004844864299651391,
"loss": 5.945,
"mean_token_accuracy": 0.1571796491742134,
"num_tokens": 24990402.0,
"step": 12775
},
{
"entropy": 6.0939295291900635,
"epoch": 1.2775028739941021,
"grad_norm": 1.2421875,
"learning_rate": 0.00048447340474845076,
"loss": 5.8885,
"mean_token_accuracy": 0.1661619082093239,
"num_tokens": 24999399.0,
"step": 12780
},
{
"entropy": 6.019286012649536,
"epoch": 1.2780026990553306,
"grad_norm": 1.21875,
"learning_rate": 0.00048446037426146555,
"loss": 5.7372,
"mean_token_accuracy": 0.1805116832256317,
"num_tokens": 25010411.0,
"step": 12785
},
{
"entropy": 6.23597149848938,
"epoch": 1.278502524116559,
"grad_norm": 1.2578125,
"learning_rate": 0.0004844473385045112,
"loss": 6.0329,
"mean_token_accuracy": 0.1500043675303459,
"num_tokens": 25019834.0,
"step": 12790
},
{
"entropy": 6.212685489654541,
"epoch": 1.2790023491777878,
"grad_norm": 1.1640625,
"learning_rate": 0.0004844342974779157,
"loss": 6.0253,
"mean_token_accuracy": 0.15458481535315513,
"num_tokens": 25030331.0,
"step": 12795
},
{
"entropy": 6.175279235839843,
"epoch": 1.2795021742390165,
"grad_norm": 1.2734375,
"learning_rate": 0.00048442125118200707,
"loss": 5.9306,
"mean_token_accuracy": 0.15867668390274048,
"num_tokens": 25040369.0,
"step": 12800
},
{
"entropy": 6.125909233093262,
"epoch": 1.280001999300245,
"grad_norm": 1.625,
"learning_rate": 0.0004844081996171137,
"loss": 5.8994,
"mean_token_accuracy": 0.16179734468460083,
"num_tokens": 25049798.0,
"step": 12805
},
{
"entropy": 6.233055496215821,
"epoch": 1.2805018243614734,
"grad_norm": 1.6875,
"learning_rate": 0.000484395142783564,
"loss": 5.9719,
"mean_token_accuracy": 0.15110021233558654,
"num_tokens": 25060982.0,
"step": 12810
},
{
"entropy": 6.181978225708008,
"epoch": 1.2810016494227021,
"grad_norm": 1.2109375,
"learning_rate": 0.0004843820806816863,
"loss": 6.0458,
"mean_token_accuracy": 0.1447092741727829,
"num_tokens": 25070532.0,
"step": 12815
},
{
"entropy": 6.149425745010376,
"epoch": 1.2815014744839306,
"grad_norm": 1.25,
"learning_rate": 0.0004843690133118094,
"loss": 5.9561,
"mean_token_accuracy": 0.16143618375062943,
"num_tokens": 25080146.0,
"step": 12820
},
{
"entropy": 6.084601259231567,
"epoch": 1.282001299545159,
"grad_norm": 1.3125,
"learning_rate": 0.000484355940674262,
"loss": 5.9208,
"mean_token_accuracy": 0.15589116215705873,
"num_tokens": 25090758.0,
"step": 12825
},
{
"entropy": 6.106634092330933,
"epoch": 1.2825011246063878,
"grad_norm": 1.1796875,
"learning_rate": 0.00048434286276937294,
"loss": 5.9725,
"mean_token_accuracy": 0.1615099087357521,
"num_tokens": 25100735.0,
"step": 12830
},
{
"entropy": 6.157269430160523,
"epoch": 1.2830009496676165,
"grad_norm": 1.1875,
"learning_rate": 0.0004843297795974713,
"loss": 5.9329,
"mean_token_accuracy": 0.1614208459854126,
"num_tokens": 25110996.0,
"step": 12835
},
{
"entropy": 6.243693494796753,
"epoch": 1.283500774728845,
"grad_norm": 1.328125,
"learning_rate": 0.0004843166911588864,
"loss": 5.8845,
"mean_token_accuracy": 0.1576448991894722,
"num_tokens": 25119720.0,
"step": 12840
},
{
"entropy": 6.1188921451568605,
"epoch": 1.2840005997900734,
"grad_norm": 1.3515625,
"learning_rate": 0.0004843035974539473,
"loss": 5.984,
"mean_token_accuracy": 0.15494607985019684,
"num_tokens": 25129916.0,
"step": 12845
},
{
"entropy": 6.175960302352905,
"epoch": 1.2845004248513021,
"grad_norm": 1.296875,
"learning_rate": 0.00048429049848298364,
"loss": 6.0163,
"mean_token_accuracy": 0.15332424342632295,
"num_tokens": 25138647.0,
"step": 12850
},
{
"entropy": 6.221134233474731,
"epoch": 1.2850002499125306,
"grad_norm": 1.4765625,
"learning_rate": 0.00048427739424632485,
"loss": 5.8836,
"mean_token_accuracy": 0.1586208239197731,
"num_tokens": 25146621.0,
"step": 12855
},
{
"entropy": 6.157750034332276,
"epoch": 1.285500074973759,
"grad_norm": 1.2109375,
"learning_rate": 0.00048426428474430055,
"loss": 6.0018,
"mean_token_accuracy": 0.15330712497234344,
"num_tokens": 25158600.0,
"step": 12860
},
{
"entropy": 6.158607864379883,
"epoch": 1.2859999000349878,
"grad_norm": 1.3203125,
"learning_rate": 0.00048425116997724083,
"loss": 5.9212,
"mean_token_accuracy": 0.156647789478302,
"num_tokens": 25169051.0,
"step": 12865
},
{
"entropy": 6.1217035293579105,
"epoch": 1.2864997250962165,
"grad_norm": 1.59375,
"learning_rate": 0.00048423804994547555,
"loss": 5.8521,
"mean_token_accuracy": 0.1661289304494858,
"num_tokens": 25177866.0,
"step": 12870
},
{
"entropy": 6.149631309509277,
"epoch": 1.286999550157445,
"grad_norm": 1.3515625,
"learning_rate": 0.00048422492464933464,
"loss": 5.9288,
"mean_token_accuracy": 0.15456630736589433,
"num_tokens": 25186868.0,
"step": 12875
},
{
"entropy": 6.131720781326294,
"epoch": 1.2874993752186734,
"grad_norm": 1.3359375,
"learning_rate": 0.00048421179408914857,
"loss": 6.028,
"mean_token_accuracy": 0.15176038071513176,
"num_tokens": 25196682.0,
"step": 12880
},
{
"entropy": 6.200189828872681,
"epoch": 1.2879992002799021,
"grad_norm": 1.4765625,
"learning_rate": 0.00048419865826524757,
"loss": 6.0082,
"mean_token_accuracy": 0.15438259541988372,
"num_tokens": 25206326.0,
"step": 12885
},
{
"entropy": 6.207353925704956,
"epoch": 1.2884990253411306,
"grad_norm": 1.3671875,
"learning_rate": 0.00048418551717796217,
"loss": 6.0186,
"mean_token_accuracy": 0.14796894490718843,
"num_tokens": 25216499.0,
"step": 12890
},
{
"entropy": 6.174864959716797,
"epoch": 1.288998850402359,
"grad_norm": 1.3125,
"learning_rate": 0.00048417237082762295,
"loss": 5.8844,
"mean_token_accuracy": 0.161013862490654,
"num_tokens": 25226854.0,
"step": 12895
},
{
"entropy": 6.243460988998413,
"epoch": 1.2894986754635878,
"grad_norm": 1.4921875,
"learning_rate": 0.00048415921921456074,
"loss": 6.1354,
"mean_token_accuracy": 0.14885302856564522,
"num_tokens": 25237536.0,
"step": 12900
},
{
"entropy": 6.129333019256592,
"epoch": 1.2899985005248162,
"grad_norm": 1.453125,
"learning_rate": 0.00048414606233910634,
"loss": 5.8832,
"mean_token_accuracy": 0.15784451216459275,
"num_tokens": 25246536.0,
"step": 12905
},
{
"entropy": 6.130053901672364,
"epoch": 1.290498325586045,
"grad_norm": 1.2734375,
"learning_rate": 0.0004841329002015909,
"loss": 5.9771,
"mean_token_accuracy": 0.15738071799278258,
"num_tokens": 25256305.0,
"step": 12910
},
{
"entropy": 6.176922941207886,
"epoch": 1.2909981506472734,
"grad_norm": 1.203125,
"learning_rate": 0.00048411973280234553,
"loss": 5.8917,
"mean_token_accuracy": 0.16168347746133804,
"num_tokens": 25265691.0,
"step": 12915
},
{
"entropy": 6.237619161605835,
"epoch": 1.291497975708502,
"grad_norm": 1.4140625,
"learning_rate": 0.00048410656014170135,
"loss": 6.0088,
"mean_token_accuracy": 0.15427018851041793,
"num_tokens": 25275963.0,
"step": 12920
},
{
"entropy": 6.160730504989624,
"epoch": 1.2919978007697306,
"grad_norm": 1.25,
"learning_rate": 0.00048409338221999,
"loss": 5.9387,
"mean_token_accuracy": 0.1586361676454544,
"num_tokens": 25286646.0,
"step": 12925
},
{
"entropy": 6.117222499847412,
"epoch": 1.292497625830959,
"grad_norm": 1.375,
"learning_rate": 0.00048408019903754297,
"loss": 5.9795,
"mean_token_accuracy": 0.15848901569843293,
"num_tokens": 25296144.0,
"step": 12930
},
{
"entropy": 6.15462851524353,
"epoch": 1.2929974508921878,
"grad_norm": 1.1953125,
"learning_rate": 0.000484067010594692,
"loss": 5.9774,
"mean_token_accuracy": 0.14803930819034578,
"num_tokens": 25306802.0,
"step": 12935
},
{
"entropy": 6.1699628829956055,
"epoch": 1.2934972759534162,
"grad_norm": 1.375,
"learning_rate": 0.00048405381689176877,
"loss": 5.9325,
"mean_token_accuracy": 0.15921355336904525,
"num_tokens": 25316021.0,
"step": 12940
},
{
"entropy": 6.156700944900512,
"epoch": 1.293997101014645,
"grad_norm": 1.2890625,
"learning_rate": 0.00048404061792910527,
"loss": 5.9056,
"mean_token_accuracy": 0.15876879990100862,
"num_tokens": 25325583.0,
"step": 12945
},
{
"entropy": 6.0968907356262205,
"epoch": 1.2944969260758734,
"grad_norm": 1.828125,
"learning_rate": 0.00048402741370703363,
"loss": 5.9253,
"mean_token_accuracy": 0.15834522992372513,
"num_tokens": 25335046.0,
"step": 12950
},
{
"entropy": 6.183151912689209,
"epoch": 1.294996751137102,
"grad_norm": 1.296875,
"learning_rate": 0.0004840142042258861,
"loss": 5.9926,
"mean_token_accuracy": 0.146283096075058,
"num_tokens": 25344180.0,
"step": 12955
},
{
"entropy": 6.1754312992095945,
"epoch": 1.2954965761983306,
"grad_norm": 1.3671875,
"learning_rate": 0.000484000989485995,
"loss": 5.9001,
"mean_token_accuracy": 0.15345722287893296,
"num_tokens": 25353131.0,
"step": 12960
},
{
"entropy": 6.173001050949097,
"epoch": 1.295996401259559,
"grad_norm": 1.1796875,
"learning_rate": 0.00048398776948769265,
"loss": 5.9602,
"mean_token_accuracy": 0.1508757397532463,
"num_tokens": 25362546.0,
"step": 12965
},
{
"entropy": 6.095330095291137,
"epoch": 1.2964962263207878,
"grad_norm": 1.3203125,
"learning_rate": 0.0004839745442313119,
"loss": 5.8368,
"mean_token_accuracy": 0.1665271058678627,
"num_tokens": 25372773.0,
"step": 12970
},
{
"entropy": 6.1797911643981935,
"epoch": 1.2969960513820162,
"grad_norm": 1.4453125,
"learning_rate": 0.00048396131371718535,
"loss": 5.909,
"mean_token_accuracy": 0.15641495883464812,
"num_tokens": 25382459.0,
"step": 12975
},
{
"entropy": 6.12809796333313,
"epoch": 1.297495876443245,
"grad_norm": 1.3828125,
"learning_rate": 0.00048394807794564586,
"loss": 5.9063,
"mean_token_accuracy": 0.15339850038290023,
"num_tokens": 25392561.0,
"step": 12980
},
{
"entropy": 6.064737224578858,
"epoch": 1.2979957015044734,
"grad_norm": 1.3125,
"learning_rate": 0.0004839348369170266,
"loss": 5.841,
"mean_token_accuracy": 0.1741722121834755,
"num_tokens": 25402250.0,
"step": 12985
},
{
"entropy": 6.094322633743286,
"epoch": 1.298495526565702,
"grad_norm": 1.203125,
"learning_rate": 0.00048392159063166055,
"loss": 5.8954,
"mean_token_accuracy": 0.15702453404664993,
"num_tokens": 25411813.0,
"step": 12990
},
{
"entropy": 6.075023031234741,
"epoch": 1.2989953516269306,
"grad_norm": 1.34375,
"learning_rate": 0.0004839083390898811,
"loss": 5.8913,
"mean_token_accuracy": 0.16241199374198914,
"num_tokens": 25421232.0,
"step": 12995
},
{
"entropy": 6.129521274566651,
"epoch": 1.299495176688159,
"grad_norm": 1.3046875,
"learning_rate": 0.0004838950822920215,
"loss": 5.9502,
"mean_token_accuracy": 0.15682778358459473,
"num_tokens": 25430617.0,
"step": 13000
},
{
"entropy": 6.118180274963379,
"epoch": 1.2999950017493878,
"grad_norm": 1.6640625,
"learning_rate": 0.0004838818202384155,
"loss": 5.8628,
"mean_token_accuracy": 0.16855358183383942,
"num_tokens": 25440514.0,
"step": 13005
},
{
"entropy": 6.249346446990967,
"epoch": 1.3004948268106162,
"grad_norm": 1.5390625,
"learning_rate": 0.00048386855292939664,
"loss": 6.0214,
"mean_token_accuracy": 0.15124907046556474,
"num_tokens": 25450058.0,
"step": 13010
},
{
"entropy": 6.165060186386109,
"epoch": 1.300994651871845,
"grad_norm": 1.2578125,
"learning_rate": 0.0004838552803652986,
"loss": 5.923,
"mean_token_accuracy": 0.15582990944385527,
"num_tokens": 25459418.0,
"step": 13015
},
{
"entropy": 6.1334309577941895,
"epoch": 1.3014944769330734,
"grad_norm": 1.390625,
"learning_rate": 0.00048384200254645557,
"loss": 6.019,
"mean_token_accuracy": 0.1524246908724308,
"num_tokens": 25468944.0,
"step": 13020
},
{
"entropy": 6.103222942352295,
"epoch": 1.301994301994302,
"grad_norm": 1.2421875,
"learning_rate": 0.00048382871947320145,
"loss": 5.8882,
"mean_token_accuracy": 0.16581465154886246,
"num_tokens": 25478072.0,
"step": 13025
},
{
"entropy": 6.1755729675292965,
"epoch": 1.3024941270555306,
"grad_norm": 1.34375,
"learning_rate": 0.0004838154311458705,
"loss": 6.004,
"mean_token_accuracy": 0.1543924868106842,
"num_tokens": 25488301.0,
"step": 13030
},
{
"entropy": 6.201048851013184,
"epoch": 1.302993952116759,
"grad_norm": 1.4296875,
"learning_rate": 0.00048380213756479704,
"loss": 5.9731,
"mean_token_accuracy": 0.14989329874515533,
"num_tokens": 25498343.0,
"step": 13035
},
{
"entropy": 6.233013343811035,
"epoch": 1.3034937771779878,
"grad_norm": 1.328125,
"learning_rate": 0.00048378883873031553,
"loss": 6.0593,
"mean_token_accuracy": 0.15224601328372955,
"num_tokens": 25509302.0,
"step": 13040
},
{
"entropy": 6.189176416397094,
"epoch": 1.3039936022392162,
"grad_norm": 1.1015625,
"learning_rate": 0.0004837755346427605,
"loss": 5.9774,
"mean_token_accuracy": 0.15510757267475128,
"num_tokens": 25520246.0,
"step": 13045
},
{
"entropy": 6.155944013595581,
"epoch": 1.3044934273004447,
"grad_norm": 1.359375,
"learning_rate": 0.00048376222530246684,
"loss": 5.9385,
"mean_token_accuracy": 0.156169556081295,
"num_tokens": 25528879.0,
"step": 13050
},
{
"entropy": 6.1424487113952635,
"epoch": 1.3049932523616734,
"grad_norm": 1.2421875,
"learning_rate": 0.00048374891070976925,
"loss": 5.9378,
"mean_token_accuracy": 0.1628851920366287,
"num_tokens": 25538029.0,
"step": 13055
},
{
"entropy": 6.1625477313995365,
"epoch": 1.305493077422902,
"grad_norm": 1.5390625,
"learning_rate": 0.0004837355908650028,
"loss": 5.9768,
"mean_token_accuracy": 0.15717717111110688,
"num_tokens": 25547752.0,
"step": 13060
},
{
"entropy": 6.176790523529053,
"epoch": 1.3059929024841306,
"grad_norm": 1.4453125,
"learning_rate": 0.0004837222657685026,
"loss": 5.9496,
"mean_token_accuracy": 0.16078850328922273,
"num_tokens": 25558197.0,
"step": 13065
},
{
"entropy": 6.185945749282837,
"epoch": 1.306492727545359,
"grad_norm": 1.296875,
"learning_rate": 0.00048370893542060383,
"loss": 5.9793,
"mean_token_accuracy": 0.15298392549157142,
"num_tokens": 25569910.0,
"step": 13070
},
{
"entropy": 6.212973117828369,
"epoch": 1.3069925526065878,
"grad_norm": 1.3203125,
"learning_rate": 0.0004836955998216421,
"loss": 5.9926,
"mean_token_accuracy": 0.15732813775539398,
"num_tokens": 25579069.0,
"step": 13075
},
{
"entropy": 6.192774963378906,
"epoch": 1.3074923776678162,
"grad_norm": 1.2109375,
"learning_rate": 0.00048368225897195264,
"loss": 5.9684,
"mean_token_accuracy": 0.15628271400928498,
"num_tokens": 25588164.0,
"step": 13080
},
{
"entropy": 6.116890621185303,
"epoch": 1.3079922027290447,
"grad_norm": 1.1796875,
"learning_rate": 0.00048366891287187133,
"loss": 6.0194,
"mean_token_accuracy": 0.1481206849217415,
"num_tokens": 25598741.0,
"step": 13085
},
{
"entropy": 6.0692455768585205,
"epoch": 1.3084920277902734,
"grad_norm": 1.390625,
"learning_rate": 0.0004836555615217337,
"loss": 5.8395,
"mean_token_accuracy": 0.16094954013824464,
"num_tokens": 25608572.0,
"step": 13090
},
{
"entropy": 6.135541534423828,
"epoch": 1.308991852851502,
"grad_norm": 2.140625,
"learning_rate": 0.0004836422049218761,
"loss": 5.8578,
"mean_token_accuracy": 0.16072544902563096,
"num_tokens": 25617686.0,
"step": 13095
},
{
"entropy": 6.057381725311279,
"epoch": 1.3094916779127306,
"grad_norm": 1.21875,
"learning_rate": 0.00048362884307263416,
"loss": 5.8695,
"mean_token_accuracy": 0.15520852208137512,
"num_tokens": 25627268.0,
"step": 13100
},
{
"entropy": 6.121604585647583,
"epoch": 1.309991502973959,
"grad_norm": 1.4375,
"learning_rate": 0.00048361547597434426,
"loss": 5.8561,
"mean_token_accuracy": 0.15929325371980668,
"num_tokens": 25636341.0,
"step": 13105
},
{
"entropy": 6.212964248657227,
"epoch": 1.3104913280351878,
"grad_norm": 1.484375,
"learning_rate": 0.00048360210362734257,
"loss": 6.0031,
"mean_token_accuracy": 0.15165067762136458,
"num_tokens": 25645403.0,
"step": 13110
},
{
"entropy": 6.137271213531494,
"epoch": 1.3109911530964162,
"grad_norm": 1.4609375,
"learning_rate": 0.0004835887260319657,
"loss": 5.9577,
"mean_token_accuracy": 0.16124185621738435,
"num_tokens": 25656062.0,
"step": 13115
},
{
"entropy": 6.097936201095581,
"epoch": 1.3114909781576447,
"grad_norm": 1.4296875,
"learning_rate": 0.0004835753431885502,
"loss": 5.8483,
"mean_token_accuracy": 0.1620157927274704,
"num_tokens": 25665449.0,
"step": 13120
},
{
"entropy": 6.081419849395752,
"epoch": 1.3119908032188734,
"grad_norm": 1.34375,
"learning_rate": 0.00048356195509743265,
"loss": 5.9227,
"mean_token_accuracy": 0.15958764851093293,
"num_tokens": 25674844.0,
"step": 13125
},
{
"entropy": 6.166410684585571,
"epoch": 1.312490628280102,
"grad_norm": 1.5,
"learning_rate": 0.00048354856175895,
"loss": 6.0375,
"mean_token_accuracy": 0.14873254373669625,
"num_tokens": 25686058.0,
"step": 13130
},
{
"entropy": 6.212475347518921,
"epoch": 1.3129904533413306,
"grad_norm": 1.1953125,
"learning_rate": 0.0004835351631734392,
"loss": 5.9679,
"mean_token_accuracy": 0.15593373030424118,
"num_tokens": 25696000.0,
"step": 13135
},
{
"entropy": 6.1812999725341795,
"epoch": 1.313490278402559,
"grad_norm": 1.2734375,
"learning_rate": 0.0004835217593412374,
"loss": 5.8802,
"mean_token_accuracy": 0.1658456340432167,
"num_tokens": 25705912.0,
"step": 13140
},
{
"entropy": 6.050013256072998,
"epoch": 1.3139901034637878,
"grad_norm": 1.234375,
"learning_rate": 0.0004835083502626818,
"loss": 5.8605,
"mean_token_accuracy": 0.159502974152565,
"num_tokens": 25716288.0,
"step": 13145
},
{
"entropy": 6.171238851547241,
"epoch": 1.3144899285250162,
"grad_norm": 1.3359375,
"learning_rate": 0.00048349493593810973,
"loss": 5.9794,
"mean_token_accuracy": 0.15527609884738922,
"num_tokens": 25726235.0,
"step": 13150
},
{
"entropy": 6.15140290260315,
"epoch": 1.3149897535862447,
"grad_norm": 1.5625,
"learning_rate": 0.0004834815163678587,
"loss": 5.969,
"mean_token_accuracy": 0.15463163778185846,
"num_tokens": 25735740.0,
"step": 13155
},
{
"entropy": 6.101669502258301,
"epoch": 1.3154895786474734,
"grad_norm": 1.265625,
"learning_rate": 0.0004834680915522664,
"loss": 5.8612,
"mean_token_accuracy": 0.16768842488527297,
"num_tokens": 25744500.0,
"step": 13160
},
{
"entropy": 6.164356136322022,
"epoch": 1.3159894037087019,
"grad_norm": 1.234375,
"learning_rate": 0.0004834546614916705,
"loss": 5.9321,
"mean_token_accuracy": 0.16489131450653077,
"num_tokens": 25754798.0,
"step": 13165
},
{
"entropy": 6.170533752441406,
"epoch": 1.3164892287699306,
"grad_norm": 1.34375,
"learning_rate": 0.00048344122618640905,
"loss": 5.9023,
"mean_token_accuracy": 0.16477506160736083,
"num_tokens": 25764985.0,
"step": 13170
},
{
"entropy": 6.177911233901978,
"epoch": 1.316989053831159,
"grad_norm": 1.3671875,
"learning_rate": 0.0004834277856368199,
"loss": 5.9171,
"mean_token_accuracy": 0.1580347090959549,
"num_tokens": 25775929.0,
"step": 13175
},
{
"entropy": 6.243767786026001,
"epoch": 1.3174888788923877,
"grad_norm": 1.4765625,
"learning_rate": 0.00048341433984324127,
"loss": 6.1217,
"mean_token_accuracy": 0.1444265626370907,
"num_tokens": 25786319.0,
"step": 13180
},
{
"entropy": 6.097338485717773,
"epoch": 1.3179887039536162,
"grad_norm": 1.3125,
"learning_rate": 0.00048340088880601163,
"loss": 5.9411,
"mean_token_accuracy": 0.15827794075012208,
"num_tokens": 25796394.0,
"step": 13185
},
{
"entropy": 6.164988040924072,
"epoch": 1.3184885290148447,
"grad_norm": 1.4140625,
"learning_rate": 0.0004833874325254691,
"loss": 5.8826,
"mean_token_accuracy": 0.15987986475229263,
"num_tokens": 25805965.0,
"step": 13190
},
{
"entropy": 6.20246057510376,
"epoch": 1.3189883540760734,
"grad_norm": 1.140625,
"learning_rate": 0.00048337397100195245,
"loss": 5.9191,
"mean_token_accuracy": 0.15538064688444136,
"num_tokens": 25816219.0,
"step": 13195
},
{
"entropy": 6.187918090820313,
"epoch": 1.3194881791373019,
"grad_norm": 1.2890625,
"learning_rate": 0.0004833605042358003,
"loss": 5.9871,
"mean_token_accuracy": 0.1588281899690628,
"num_tokens": 25826263.0,
"step": 13200
},
{
"entropy": 6.1791199207305905,
"epoch": 1.3199880041985306,
"grad_norm": 1.359375,
"learning_rate": 0.0004833470322273515,
"loss": 5.9675,
"mean_token_accuracy": 0.15493707805871965,
"num_tokens": 25836262.0,
"step": 13205
},
{
"entropy": 6.1938573837280275,
"epoch": 1.320487829259759,
"grad_norm": 1.3203125,
"learning_rate": 0.00048333355497694506,
"loss": 5.8877,
"mean_token_accuracy": 0.1619814544916153,
"num_tokens": 25845906.0,
"step": 13210
},
{
"entropy": 6.092811155319214,
"epoch": 1.3209876543209877,
"grad_norm": 1.515625,
"learning_rate": 0.0004833200724849199,
"loss": 5.8757,
"mean_token_accuracy": 0.16639862358570098,
"num_tokens": 25856251.0,
"step": 13215
},
{
"entropy": 6.079971075057983,
"epoch": 1.3214874793822162,
"grad_norm": 1.1953125,
"learning_rate": 0.00048330658475161526,
"loss": 5.9503,
"mean_token_accuracy": 0.16594918742775916,
"num_tokens": 25866695.0,
"step": 13220
},
{
"entropy": 6.146766662597656,
"epoch": 1.3219873044434447,
"grad_norm": 1.2265625,
"learning_rate": 0.0004832930917773706,
"loss": 6.0106,
"mean_token_accuracy": 0.15031296908855438,
"num_tokens": 25877208.0,
"step": 13225
},
{
"entropy": 6.221292495727539,
"epoch": 1.3224871295046734,
"grad_norm": 1.625,
"learning_rate": 0.00048327959356252544,
"loss": 5.889,
"mean_token_accuracy": 0.162984199821949,
"num_tokens": 25887062.0,
"step": 13230
},
{
"entropy": 6.237447357177734,
"epoch": 1.3229869545659019,
"grad_norm": 1.2890625,
"learning_rate": 0.0004832660901074192,
"loss": 5.9903,
"mean_token_accuracy": 0.15430379658937454,
"num_tokens": 25896410.0,
"step": 13235
},
{
"entropy": 6.095164155960083,
"epoch": 1.3234867796271306,
"grad_norm": 1.7265625,
"learning_rate": 0.00048325258141239174,
"loss": 5.8512,
"mean_token_accuracy": 0.16410801857709884,
"num_tokens": 25905085.0,
"step": 13240
},
{
"entropy": 6.1868115901947025,
"epoch": 1.323986604688359,
"grad_norm": 1.3984375,
"learning_rate": 0.0004832390674777829,
"loss": 5.9324,
"mean_token_accuracy": 0.15469116270542144,
"num_tokens": 25914334.0,
"step": 13245
},
{
"entropy": 6.152792739868164,
"epoch": 1.3244864297495877,
"grad_norm": 1.4375,
"learning_rate": 0.00048322554830393274,
"loss": 5.9387,
"mean_token_accuracy": 0.15107419788837434,
"num_tokens": 25922676.0,
"step": 13250
},
{
"entropy": 6.171576642990113,
"epoch": 1.3249862548108162,
"grad_norm": 1.3046875,
"learning_rate": 0.0004832120238911813,
"loss": 5.9645,
"mean_token_accuracy": 0.16050836443901062,
"num_tokens": 25931910.0,
"step": 13255
},
{
"entropy": 6.096503114700317,
"epoch": 1.3254860798720447,
"grad_norm": 1.296875,
"learning_rate": 0.000483198494239869,
"loss": 5.8261,
"mean_token_accuracy": 0.16611166894435883,
"num_tokens": 25942713.0,
"step": 13260
},
{
"entropy": 6.09018497467041,
"epoch": 1.3259859049332734,
"grad_norm": 1.234375,
"learning_rate": 0.00048318495935033615,
"loss": 5.8314,
"mean_token_accuracy": 0.16736013144254686,
"num_tokens": 25951462.0,
"step": 13265
},
{
"entropy": 6.180334424972534,
"epoch": 1.3264857299945019,
"grad_norm": 1.3828125,
"learning_rate": 0.00048317141922292326,
"loss": 5.8896,
"mean_token_accuracy": 0.1599945217370987,
"num_tokens": 25961172.0,
"step": 13270
},
{
"entropy": 6.131149339675903,
"epoch": 1.3269855550557306,
"grad_norm": 1.2421875,
"learning_rate": 0.0004831578738579711,
"loss": 5.9066,
"mean_token_accuracy": 0.15385794788599014,
"num_tokens": 25971119.0,
"step": 13275
},
{
"entropy": 6.218445539474487,
"epoch": 1.327485380116959,
"grad_norm": 1.3515625,
"learning_rate": 0.0004831443232558203,
"loss": 6.0542,
"mean_token_accuracy": 0.1535279430449009,
"num_tokens": 25981758.0,
"step": 13280
},
{
"entropy": 6.24181718826294,
"epoch": 1.3279852051781877,
"grad_norm": 1.265625,
"learning_rate": 0.00048313076741681186,
"loss": 6.0046,
"mean_token_accuracy": 0.1506742499768734,
"num_tokens": 25991033.0,
"step": 13285
},
{
"entropy": 6.132058572769165,
"epoch": 1.3284850302394162,
"grad_norm": 1.7578125,
"learning_rate": 0.00048311720634128697,
"loss": 6.0269,
"mean_token_accuracy": 0.15611413046717643,
"num_tokens": 26001547.0,
"step": 13290
},
{
"entropy": 6.234566068649292,
"epoch": 1.3289848553006447,
"grad_norm": 1.265625,
"learning_rate": 0.0004831036400295867,
"loss": 6.0596,
"mean_token_accuracy": 0.14754553139209747,
"num_tokens": 26012140.0,
"step": 13295
},
{
"entropy": 6.2622216701507565,
"epoch": 1.3294846803618734,
"grad_norm": 1.2734375,
"learning_rate": 0.00048309006848205237,
"loss": 5.9631,
"mean_token_accuracy": 0.15471525192260743,
"num_tokens": 26022068.0,
"step": 13300
},
{
"entropy": 6.217406511306763,
"epoch": 1.3299845054231019,
"grad_norm": 1.3515625,
"learning_rate": 0.0004830764916990255,
"loss": 5.8982,
"mean_token_accuracy": 0.15676374733448029,
"num_tokens": 26031313.0,
"step": 13305
},
{
"entropy": 6.141649770736694,
"epoch": 1.3304843304843303,
"grad_norm": 1.2890625,
"learning_rate": 0.0004830629096808476,
"loss": 5.8818,
"mean_token_accuracy": 0.16377949118614196,
"num_tokens": 26040937.0,
"step": 13310
},
{
"entropy": 6.07700514793396,
"epoch": 1.330984155545559,
"grad_norm": 1.390625,
"learning_rate": 0.0004830493224278605,
"loss": 5.7635,
"mean_token_accuracy": 0.1744140073657036,
"num_tokens": 26049719.0,
"step": 13315
},
{
"entropy": 6.250267505645752,
"epoch": 1.3314839806067877,
"grad_norm": 1.2578125,
"learning_rate": 0.0004830357299404059,
"loss": 6.0062,
"mean_token_accuracy": 0.15176339596509933,
"num_tokens": 26060064.0,
"step": 13320
},
{
"entropy": 6.137303686141967,
"epoch": 1.3319838056680162,
"grad_norm": 1.2265625,
"learning_rate": 0.0004830221322188259,
"loss": 5.8916,
"mean_token_accuracy": 0.1669079393148422,
"num_tokens": 26069605.0,
"step": 13325
},
{
"entropy": 6.189572334289551,
"epoch": 1.3324836307292447,
"grad_norm": 1.46875,
"learning_rate": 0.0004830085292634626,
"loss": 5.9857,
"mean_token_accuracy": 0.14881925731897355,
"num_tokens": 26079075.0,
"step": 13330
},
{
"entropy": 6.1138369083404545,
"epoch": 1.3329834557904734,
"grad_norm": 1.2421875,
"learning_rate": 0.00048299492107465816,
"loss": 5.9362,
"mean_token_accuracy": 0.15054402500391006,
"num_tokens": 26089003.0,
"step": 13335
},
{
"entropy": 6.184536027908325,
"epoch": 1.3334832808517019,
"grad_norm": 1.375,
"learning_rate": 0.0004829813076527551,
"loss": 5.9585,
"mean_token_accuracy": 0.153141750395298,
"num_tokens": 26099044.0,
"step": 13340
},
{
"entropy": 6.142232131958008,
"epoch": 1.3339831059129303,
"grad_norm": 1.3515625,
"learning_rate": 0.00048296768899809577,
"loss": 5.9226,
"mean_token_accuracy": 0.15283889323472977,
"num_tokens": 26109044.0,
"step": 13345
},
{
"entropy": 6.120077228546142,
"epoch": 1.334482930974159,
"grad_norm": 1.5,
"learning_rate": 0.00048295406511102303,
"loss": 5.9936,
"mean_token_accuracy": 0.14861363768577576,
"num_tokens": 26118593.0,
"step": 13350
},
{
"entropy": 6.192146635055542,
"epoch": 1.3349827560353877,
"grad_norm": 1.5234375,
"learning_rate": 0.0004829404359918795,
"loss": 6.0032,
"mean_token_accuracy": 0.15580553114414214,
"num_tokens": 26128885.0,
"step": 13355
},
{
"entropy": 6.209059143066407,
"epoch": 1.3354825810966162,
"grad_norm": 1.3046875,
"learning_rate": 0.000482926801641008,
"loss": 5.9842,
"mean_token_accuracy": 0.15600850507616998,
"num_tokens": 26138173.0,
"step": 13360
},
{
"entropy": 6.214423942565918,
"epoch": 1.3359824061578447,
"grad_norm": 1.3359375,
"learning_rate": 0.00048291316205875174,
"loss": 5.9321,
"mean_token_accuracy": 0.15535638630390167,
"num_tokens": 26147724.0,
"step": 13365
},
{
"entropy": 6.0966239929199215,
"epoch": 1.3364822312190734,
"grad_norm": 1.2890625,
"learning_rate": 0.00048289951724545384,
"loss": 5.8791,
"mean_token_accuracy": 0.16094851940870286,
"num_tokens": 26156970.0,
"step": 13370
},
{
"entropy": 6.055920505523682,
"epoch": 1.3369820562803019,
"grad_norm": 1.1796875,
"learning_rate": 0.00048288586720145757,
"loss": 5.8449,
"mean_token_accuracy": 0.15795587003231049,
"num_tokens": 26166757.0,
"step": 13375
},
{
"entropy": 6.142801761627197,
"epoch": 1.3374818813415303,
"grad_norm": 1.3046875,
"learning_rate": 0.0004828722119271064,
"loss": 5.9961,
"mean_token_accuracy": 0.14875075742602348,
"num_tokens": 26176944.0,
"step": 13380
},
{
"entropy": 6.157301044464111,
"epoch": 1.337981706402759,
"grad_norm": 1.1875,
"learning_rate": 0.00048285855142274375,
"loss": 5.8436,
"mean_token_accuracy": 0.16563331186771393,
"num_tokens": 26185380.0,
"step": 13385
},
{
"entropy": 6.157561635971069,
"epoch": 1.3384815314639877,
"grad_norm": 1.2734375,
"learning_rate": 0.0004828448856887135,
"loss": 5.9464,
"mean_token_accuracy": 0.15706296488642693,
"num_tokens": 26194936.0,
"step": 13390
},
{
"entropy": 6.081349611282349,
"epoch": 1.3389813565252162,
"grad_norm": 1.28125,
"learning_rate": 0.0004828312147253595,
"loss": 5.8551,
"mean_token_accuracy": 0.15932156890630722,
"num_tokens": 26205825.0,
"step": 13395
},
{
"entropy": 6.249830484390259,
"epoch": 1.3394811815864447,
"grad_norm": 1.4296875,
"learning_rate": 0.0004828175385330255,
"loss": 6.0098,
"mean_token_accuracy": 0.1462766632437706,
"num_tokens": 26215977.0,
"step": 13400
},
{
"entropy": 6.216329956054688,
"epoch": 1.3399810066476734,
"grad_norm": 1.34375,
"learning_rate": 0.0004828038571120558,
"loss": 5.9591,
"mean_token_accuracy": 0.15963440835475923,
"num_tokens": 26225424.0,
"step": 13405
},
{
"entropy": 6.17230806350708,
"epoch": 1.3404808317089019,
"grad_norm": 1.2421875,
"learning_rate": 0.00048279017046279446,
"loss": 5.9815,
"mean_token_accuracy": 0.1597868949174881,
"num_tokens": 26235491.0,
"step": 13410
},
{
"entropy": 6.165284824371338,
"epoch": 1.3409806567701303,
"grad_norm": 1.328125,
"learning_rate": 0.00048277647858558596,
"loss": 6.0194,
"mean_token_accuracy": 0.1536007598042488,
"num_tokens": 26246030.0,
"step": 13415
},
{
"entropy": 6.244114065170288,
"epoch": 1.341480481831359,
"grad_norm": 1.3359375,
"learning_rate": 0.00048276278148077465,
"loss": 6.0436,
"mean_token_accuracy": 0.1454267144203186,
"num_tokens": 26255008.0,
"step": 13420
},
{
"entropy": 6.08438401222229,
"epoch": 1.3419803068925875,
"grad_norm": 1.4609375,
"learning_rate": 0.00048274907914870526,
"loss": 5.7393,
"mean_token_accuracy": 0.17554350942373276,
"num_tokens": 26263319.0,
"step": 13425
},
{
"entropy": 6.084990358352661,
"epoch": 1.3424801319538162,
"grad_norm": 1.25,
"learning_rate": 0.00048273537158972246,
"loss": 5.8583,
"mean_token_accuracy": 0.1612003803253174,
"num_tokens": 26272555.0,
"step": 13430
},
{
"entropy": 6.139375782012939,
"epoch": 1.3429799570150447,
"grad_norm": 1.5859375,
"learning_rate": 0.00048272165880417124,
"loss": 5.946,
"mean_token_accuracy": 0.15595633089542388,
"num_tokens": 26282915.0,
"step": 13435
},
{
"entropy": 6.167522716522217,
"epoch": 1.3434797820762734,
"grad_norm": 1.3671875,
"learning_rate": 0.00048270794079239643,
"loss": 5.8949,
"mean_token_accuracy": 0.16371387541294097,
"num_tokens": 26292705.0,
"step": 13440
},
{
"entropy": 6.268767404556274,
"epoch": 1.3439796071375019,
"grad_norm": 1.296875,
"learning_rate": 0.00048269421755474336,
"loss": 6.0126,
"mean_token_accuracy": 0.14959271177649497,
"num_tokens": 26303678.0,
"step": 13445
},
{
"entropy": 6.164479064941406,
"epoch": 1.3444794321987303,
"grad_norm": 1.2265625,
"learning_rate": 0.0004826804890915572,
"loss": 5.9351,
"mean_token_accuracy": 0.15266655683517455,
"num_tokens": 26312844.0,
"step": 13450
},
{
"entropy": 6.218075942993164,
"epoch": 1.344979257259959,
"grad_norm": 1.484375,
"learning_rate": 0.0004826667554031834,
"loss": 6.0046,
"mean_token_accuracy": 0.149177997559309,
"num_tokens": 26322763.0,
"step": 13455
},
{
"entropy": 6.127144145965576,
"epoch": 1.3454790823211875,
"grad_norm": 1.3125,
"learning_rate": 0.0004826530164899674,
"loss": 5.9154,
"mean_token_accuracy": 0.15740453824400902,
"num_tokens": 26331381.0,
"step": 13460
},
{
"entropy": 6.029008865356445,
"epoch": 1.3459789073824162,
"grad_norm": 1.2890625,
"learning_rate": 0.00048263927235225505,
"loss": 5.684,
"mean_token_accuracy": 0.17971582114696502,
"num_tokens": 26340637.0,
"step": 13465
},
{
"entropy": 6.17818512916565,
"epoch": 1.3464787324436447,
"grad_norm": 1.5859375,
"learning_rate": 0.0004826255229903919,
"loss": 5.894,
"mean_token_accuracy": 0.15740025490522386,
"num_tokens": 26350508.0,
"step": 13470
},
{
"entropy": 6.170793628692627,
"epoch": 1.3469785575048734,
"grad_norm": 2.328125,
"learning_rate": 0.00048261176840472416,
"loss": 6.0833,
"mean_token_accuracy": 0.15282572209835052,
"num_tokens": 26360419.0,
"step": 13475
},
{
"entropy": 6.1905053615570065,
"epoch": 1.3474783825661019,
"grad_norm": 1.6171875,
"learning_rate": 0.00048259800859559764,
"loss": 5.9293,
"mean_token_accuracy": 0.1533403255045414,
"num_tokens": 26370355.0,
"step": 13480
},
{
"entropy": 6.086648464202881,
"epoch": 1.3479782076273303,
"grad_norm": 1.6328125,
"learning_rate": 0.0004825842435633587,
"loss": 5.8828,
"mean_token_accuracy": 0.16225536167621613,
"num_tokens": 26380085.0,
"step": 13485
},
{
"entropy": 6.131977605819702,
"epoch": 1.348478032688559,
"grad_norm": 1.2734375,
"learning_rate": 0.00048257047330835354,
"loss": 5.9217,
"mean_token_accuracy": 0.16104235649108886,
"num_tokens": 26389571.0,
"step": 13490
},
{
"entropy": 6.093983221054077,
"epoch": 1.3489778577497875,
"grad_norm": 1.3515625,
"learning_rate": 0.00048255669783092876,
"loss": 5.9047,
"mean_token_accuracy": 0.15970612764358522,
"num_tokens": 26399560.0,
"step": 13495
},
{
"entropy": 6.131382846832276,
"epoch": 1.3494776828110162,
"grad_norm": 1.375,
"learning_rate": 0.00048254291713143083,
"loss": 5.9108,
"mean_token_accuracy": 0.15783733278512954,
"num_tokens": 26409290.0,
"step": 13500
},
{
"entropy": 6.1973714351654055,
"epoch": 1.3499775078722447,
"grad_norm": 1.8359375,
"learning_rate": 0.0004825291312102066,
"loss": 5.9663,
"mean_token_accuracy": 0.15795569270849227,
"num_tokens": 26419458.0,
"step": 13505
},
{
"entropy": 6.170440435409546,
"epoch": 1.3504773329334734,
"grad_norm": 1.3125,
"learning_rate": 0.0004825153400676027,
"loss": 5.8587,
"mean_token_accuracy": 0.16096708923578262,
"num_tokens": 26428947.0,
"step": 13510
},
{
"entropy": 5.949077510833741,
"epoch": 1.3509771579947019,
"grad_norm": 1.2109375,
"learning_rate": 0.0004825015437039663,
"loss": 5.7805,
"mean_token_accuracy": 0.1663256913423538,
"num_tokens": 26438874.0,
"step": 13515
},
{
"entropy": 6.128787851333618,
"epoch": 1.3514769830559303,
"grad_norm": 1.2421875,
"learning_rate": 0.0004824877421196444,
"loss": 5.8647,
"mean_token_accuracy": 0.16112425327301025,
"num_tokens": 26448510.0,
"step": 13520
},
{
"entropy": 6.032810020446777,
"epoch": 1.351976808117159,
"grad_norm": 1.2890625,
"learning_rate": 0.0004824739353149844,
"loss": 5.8352,
"mean_token_accuracy": 0.1590333729982376,
"num_tokens": 26458552.0,
"step": 13525
},
{
"entropy": 6.099111604690552,
"epoch": 1.3524766331783875,
"grad_norm": 1.3984375,
"learning_rate": 0.00048246012329033355,
"loss": 5.9426,
"mean_token_accuracy": 0.1562192842364311,
"num_tokens": 26467900.0,
"step": 13530
},
{
"entropy": 6.199307489395141,
"epoch": 1.3529764582396162,
"grad_norm": 1.4453125,
"learning_rate": 0.00048244630604603935,
"loss": 5.923,
"mean_token_accuracy": 0.15992572978138925,
"num_tokens": 26477229.0,
"step": 13535
},
{
"entropy": 6.192346858978271,
"epoch": 1.3534762833008447,
"grad_norm": 1.265625,
"learning_rate": 0.00048243248358244945,
"loss": 5.9574,
"mean_token_accuracy": 0.15444340258836747,
"num_tokens": 26487358.0,
"step": 13540
},
{
"entropy": 6.096559619903564,
"epoch": 1.3539761083620734,
"grad_norm": 1.3203125,
"learning_rate": 0.0004824186558999117,
"loss": 5.8243,
"mean_token_accuracy": 0.16178459376096727,
"num_tokens": 26496399.0,
"step": 13545
},
{
"entropy": 6.083345174789429,
"epoch": 1.3544759334233019,
"grad_norm": 1.21875,
"learning_rate": 0.00048240482299877386,
"loss": 5.9252,
"mean_token_accuracy": 0.15940019339323044,
"num_tokens": 26506170.0,
"step": 13550
},
{
"entropy": 6.1777738571167,
"epoch": 1.3549757584845303,
"grad_norm": 1.3828125,
"learning_rate": 0.0004823909848793841,
"loss": 5.9536,
"mean_token_accuracy": 0.15433786511421205,
"num_tokens": 26516414.0,
"step": 13555
},
{
"entropy": 6.080035829544068,
"epoch": 1.355475583545759,
"grad_norm": 1.28125,
"learning_rate": 0.00048237714154209053,
"loss": 5.8576,
"mean_token_accuracy": 0.1628124311566353,
"num_tokens": 26526345.0,
"step": 13560
},
{
"entropy": 6.209974861145019,
"epoch": 1.3559754086069875,
"grad_norm": 1.46875,
"learning_rate": 0.0004823632929872415,
"loss": 5.9555,
"mean_token_accuracy": 0.15523934960365296,
"num_tokens": 26535768.0,
"step": 13565
},
{
"entropy": 6.157249307632446,
"epoch": 1.3564752336682162,
"grad_norm": 1.2421875,
"learning_rate": 0.00048234943921518524,
"loss": 5.9434,
"mean_token_accuracy": 0.15802091956138611,
"num_tokens": 26546181.0,
"step": 13570
},
{
"entropy": 6.106801319122314,
"epoch": 1.3569750587294447,
"grad_norm": 1.3046875,
"learning_rate": 0.0004823355802262705,
"loss": 5.8975,
"mean_token_accuracy": 0.16192759722471237,
"num_tokens": 26555664.0,
"step": 13575
},
{
"entropy": 6.200563859939575,
"epoch": 1.3574748837906734,
"grad_norm": 1.59375,
"learning_rate": 0.0004823217160208459,
"loss": 5.99,
"mean_token_accuracy": 0.153380536288023,
"num_tokens": 26564801.0,
"step": 13580
},
{
"entropy": 6.2960512161254885,
"epoch": 1.3579747088519019,
"grad_norm": 1.515625,
"learning_rate": 0.0004823078465992604,
"loss": 6.0684,
"mean_token_accuracy": 0.15203940719366074,
"num_tokens": 26575397.0,
"step": 13585
},
{
"entropy": 6.129009580612182,
"epoch": 1.3584745339131303,
"grad_norm": 1.3046875,
"learning_rate": 0.0004822939719618627,
"loss": 5.9131,
"mean_token_accuracy": 0.16364746242761613,
"num_tokens": 26584533.0,
"step": 13590
},
{
"entropy": 6.188502454757691,
"epoch": 1.358974358974359,
"grad_norm": 1.3203125,
"learning_rate": 0.000482280092109002,
"loss": 5.9201,
"mean_token_accuracy": 0.16066576838493346,
"num_tokens": 26594176.0,
"step": 13595
},
{
"entropy": 6.15440788269043,
"epoch": 1.3594741840355875,
"grad_norm": 1.3046875,
"learning_rate": 0.00048226620704102757,
"loss": 5.9469,
"mean_token_accuracy": 0.14897557497024536,
"num_tokens": 26603033.0,
"step": 13600
},
{
"entropy": 6.2116961002349855,
"epoch": 1.359974009096816,
"grad_norm": 1.34375,
"learning_rate": 0.0004822523167582886,
"loss": 5.919,
"mean_token_accuracy": 0.1595153883099556,
"num_tokens": 26612327.0,
"step": 13605
},
{
"entropy": 6.123779916763306,
"epoch": 1.3604738341580447,
"grad_norm": 1.40625,
"learning_rate": 0.0004822384212611348,
"loss": 5.8976,
"mean_token_accuracy": 0.15832812935113907,
"num_tokens": 26622180.0,
"step": 13610
},
{
"entropy": 6.139707946777344,
"epoch": 1.3609736592192734,
"grad_norm": 1.3359375,
"learning_rate": 0.00048222452054991563,
"loss": 6.0204,
"mean_token_accuracy": 0.14583451449871063,
"num_tokens": 26633137.0,
"step": 13615
},
{
"entropy": 6.097583818435669,
"epoch": 1.3614734842805019,
"grad_norm": 1.265625,
"learning_rate": 0.0004822106146249808,
"loss": 5.8025,
"mean_token_accuracy": 0.16549130752682686,
"num_tokens": 26642642.0,
"step": 13620
},
{
"entropy": 6.235262680053711,
"epoch": 1.3619733093417303,
"grad_norm": 1.4375,
"learning_rate": 0.00048219670348668026,
"loss": 6.0105,
"mean_token_accuracy": 0.1557586185634136,
"num_tokens": 26652465.0,
"step": 13625
},
{
"entropy": 6.191774463653564,
"epoch": 1.362473134402959,
"grad_norm": 1.671875,
"learning_rate": 0.00048218278713536394,
"loss": 5.9482,
"mean_token_accuracy": 0.1562319315969944,
"num_tokens": 26662971.0,
"step": 13630
},
{
"entropy": 6.023241281509399,
"epoch": 1.3629729594641875,
"grad_norm": 1.3203125,
"learning_rate": 0.0004821688655713821,
"loss": 5.8445,
"mean_token_accuracy": 0.16247360557317733,
"num_tokens": 26672373.0,
"step": 13635
},
{
"entropy": 6.081688356399536,
"epoch": 1.363472784525416,
"grad_norm": 1.4453125,
"learning_rate": 0.00048215493879508474,
"loss": 5.8556,
"mean_token_accuracy": 0.164544714987278,
"num_tokens": 26681491.0,
"step": 13640
},
{
"entropy": 6.191488742828369,
"epoch": 1.3639726095866447,
"grad_norm": 1.5546875,
"learning_rate": 0.0004821410068068226,
"loss": 5.9481,
"mean_token_accuracy": 0.15922945141792297,
"num_tokens": 26690094.0,
"step": 13645
},
{
"entropy": 6.2064262390136715,
"epoch": 1.3644724346478734,
"grad_norm": 1.5859375,
"learning_rate": 0.0004821270696069459,
"loss": 5.9424,
"mean_token_accuracy": 0.15093102306127548,
"num_tokens": 26699525.0,
"step": 13650
},
{
"entropy": 6.106315755844117,
"epoch": 1.3649722597091019,
"grad_norm": 1.390625,
"learning_rate": 0.00048211312719580553,
"loss": 5.8567,
"mean_token_accuracy": 0.1582114189863205,
"num_tokens": 26709943.0,
"step": 13655
},
{
"entropy": 6.122861862182617,
"epoch": 1.3654720847703303,
"grad_norm": 1.4765625,
"learning_rate": 0.0004820991795737521,
"loss": 5.9131,
"mean_token_accuracy": 0.1552156075835228,
"num_tokens": 26719517.0,
"step": 13660
},
{
"entropy": 6.157819366455078,
"epoch": 1.365971909831559,
"grad_norm": 1.3671875,
"learning_rate": 0.00048208522674113665,
"loss": 5.9672,
"mean_token_accuracy": 0.1622170627117157,
"num_tokens": 26728753.0,
"step": 13665
},
{
"entropy": 6.166556692123413,
"epoch": 1.3664717348927875,
"grad_norm": 1.265625,
"learning_rate": 0.0004820712686983101,
"loss": 5.9249,
"mean_token_accuracy": 0.15511706247925758,
"num_tokens": 26737662.0,
"step": 13670
},
{
"entropy": 6.080324792861939,
"epoch": 1.366971559954016,
"grad_norm": 1.2109375,
"learning_rate": 0.00048205730544562385,
"loss": 5.8745,
"mean_token_accuracy": 0.16297486126422883,
"num_tokens": 26748167.0,
"step": 13675
},
{
"entropy": 6.179111576080322,
"epoch": 1.3674713850152447,
"grad_norm": 1.4375,
"learning_rate": 0.000482043336983429,
"loss": 5.9859,
"mean_token_accuracy": 0.15291956067085266,
"num_tokens": 26756692.0,
"step": 13680
},
{
"entropy": 6.096879625320435,
"epoch": 1.3679712100764732,
"grad_norm": 1.234375,
"learning_rate": 0.00048202936331207707,
"loss": 5.8964,
"mean_token_accuracy": 0.16100419610738753,
"num_tokens": 26766201.0,
"step": 13685
},
{
"entropy": 6.075778579711914,
"epoch": 1.3684710351377019,
"grad_norm": 1.3125,
"learning_rate": 0.0004820153844319196,
"loss": 5.9083,
"mean_token_accuracy": 0.16028712838888168,
"num_tokens": 26774911.0,
"step": 13690
},
{
"entropy": 6.144129991531372,
"epoch": 1.3689708601989303,
"grad_norm": 1.1953125,
"learning_rate": 0.00048200140034330844,
"loss": 5.8822,
"mean_token_accuracy": 0.16373094469308852,
"num_tokens": 26784271.0,
"step": 13695
},
{
"entropy": 6.252957534790039,
"epoch": 1.369470685260159,
"grad_norm": 1.203125,
"learning_rate": 0.00048198741104659516,
"loss": 5.9744,
"mean_token_accuracy": 0.1594805970788002,
"num_tokens": 26794975.0,
"step": 13700
},
{
"entropy": 6.199783849716186,
"epoch": 1.3699705103213875,
"grad_norm": 1.203125,
"learning_rate": 0.000481973416542132,
"loss": 6.0297,
"mean_token_accuracy": 0.15491671115159988,
"num_tokens": 26805989.0,
"step": 13705
},
{
"entropy": 6.174100160598755,
"epoch": 1.370470335382616,
"grad_norm": 1.3046875,
"learning_rate": 0.0004819594168302709,
"loss": 5.9731,
"mean_token_accuracy": 0.1575739249587059,
"num_tokens": 26815961.0,
"step": 13710
},
{
"entropy": 6.104086780548096,
"epoch": 1.3709701604438447,
"grad_norm": 1.2734375,
"learning_rate": 0.0004819454119113641,
"loss": 5.8171,
"mean_token_accuracy": 0.16839422136545182,
"num_tokens": 26825697.0,
"step": 13715
},
{
"entropy": 6.154540872573852,
"epoch": 1.3714699855050732,
"grad_norm": 1.2734375,
"learning_rate": 0.000481931401785764,
"loss": 5.8792,
"mean_token_accuracy": 0.15832828879356384,
"num_tokens": 26834965.0,
"step": 13720
},
{
"entropy": 6.115646839141846,
"epoch": 1.3719698105663019,
"grad_norm": 1.3203125,
"learning_rate": 0.0004819173864538231,
"loss": 5.9075,
"mean_token_accuracy": 0.16441078633069992,
"num_tokens": 26845621.0,
"step": 13725
},
{
"entropy": 6.222882461547852,
"epoch": 1.3724696356275303,
"grad_norm": 1.34375,
"learning_rate": 0.00048190336591589394,
"loss": 6.0035,
"mean_token_accuracy": 0.1523177832365036,
"num_tokens": 26855176.0,
"step": 13730
},
{
"entropy": 6.239377069473266,
"epoch": 1.372969460688759,
"grad_norm": 1.53125,
"learning_rate": 0.0004818893401723294,
"loss": 5.9625,
"mean_token_accuracy": 0.15688011199235916,
"num_tokens": 26864197.0,
"step": 13735
},
{
"entropy": 6.157269763946533,
"epoch": 1.3734692857499875,
"grad_norm": 1.4140625,
"learning_rate": 0.00048187530922348226,
"loss": 5.9229,
"mean_token_accuracy": 0.15628610253334047,
"num_tokens": 26873895.0,
"step": 13740
},
{
"entropy": 6.144111204147339,
"epoch": 1.373969110811216,
"grad_norm": 1.2734375,
"learning_rate": 0.0004818612730697056,
"loss": 6.0457,
"mean_token_accuracy": 0.15030306577682495,
"num_tokens": 26883685.0,
"step": 13745
},
{
"entropy": 6.193239688873291,
"epoch": 1.3744689358724447,
"grad_norm": 1.203125,
"learning_rate": 0.00048184723171135256,
"loss": 5.8024,
"mean_token_accuracy": 0.1606294184923172,
"num_tokens": 26893939.0,
"step": 13750
},
{
"entropy": 6.116706037521363,
"epoch": 1.3749687609336732,
"grad_norm": 1.40625,
"learning_rate": 0.00048183318514877634,
"loss": 5.8972,
"mean_token_accuracy": 0.16470476984977722,
"num_tokens": 26903588.0,
"step": 13755
},
{
"entropy": 6.174177885055542,
"epoch": 1.3754685859949018,
"grad_norm": 1.46875,
"learning_rate": 0.0004818191333823305,
"loss": 6.0456,
"mean_token_accuracy": 0.1523826986551285,
"num_tokens": 26914068.0,
"step": 13760
},
{
"entropy": 6.15484848022461,
"epoch": 1.3759684110561303,
"grad_norm": 1.2890625,
"learning_rate": 0.0004818050764123684,
"loss": 5.9254,
"mean_token_accuracy": 0.15486986190080643,
"num_tokens": 26923928.0,
"step": 13765
},
{
"entropy": 6.119842624664306,
"epoch": 1.376468236117359,
"grad_norm": 1.421875,
"learning_rate": 0.0004817910142392438,
"loss": 5.8632,
"mean_token_accuracy": 0.16237968504428862,
"num_tokens": 26933202.0,
"step": 13770
},
{
"entropy": 6.031164121627808,
"epoch": 1.3769680611785875,
"grad_norm": 1.5390625,
"learning_rate": 0.00048177694686331047,
"loss": 5.7526,
"mean_token_accuracy": 0.1667496904730797,
"num_tokens": 26943466.0,
"step": 13775
},
{
"entropy": 6.09368371963501,
"epoch": 1.377467886239816,
"grad_norm": 1.265625,
"learning_rate": 0.0004817628742849224,
"loss": 5.8706,
"mean_token_accuracy": 0.15734305381774902,
"num_tokens": 26953996.0,
"step": 13780
},
{
"entropy": 6.108762311935425,
"epoch": 1.3779677113010447,
"grad_norm": 1.3671875,
"learning_rate": 0.00048174879650443364,
"loss": 5.923,
"mean_token_accuracy": 0.1599729061126709,
"num_tokens": 26963238.0,
"step": 13785
},
{
"entropy": 6.127309894561767,
"epoch": 1.3784675363622731,
"grad_norm": 1.2890625,
"learning_rate": 0.00048173471352219835,
"loss": 5.9181,
"mean_token_accuracy": 0.14826206415891646,
"num_tokens": 26973124.0,
"step": 13790
},
{
"entropy": 6.117661237716675,
"epoch": 1.3789673614235018,
"grad_norm": 1.40625,
"learning_rate": 0.0004817206253385708,
"loss": 5.8523,
"mean_token_accuracy": 0.16209922283887862,
"num_tokens": 26981698.0,
"step": 13795
},
{
"entropy": 6.140020227432251,
"epoch": 1.3794671864847303,
"grad_norm": 1.203125,
"learning_rate": 0.00048170653195390555,
"loss": 5.9609,
"mean_token_accuracy": 0.15860718116164207,
"num_tokens": 26991263.0,
"step": 13800
},
{
"entropy": 6.058004236221313,
"epoch": 1.379967011545959,
"grad_norm": 1.953125,
"learning_rate": 0.0004816924333685572,
"loss": 5.8667,
"mean_token_accuracy": 0.16487080976366997,
"num_tokens": 27001835.0,
"step": 13805
},
{
"entropy": 6.117015027999878,
"epoch": 1.3804668366071875,
"grad_norm": 1.40625,
"learning_rate": 0.0004816783295828804,
"loss": 5.9002,
"mean_token_accuracy": 0.15816379338502884,
"num_tokens": 27011306.0,
"step": 13810
},
{
"entropy": 6.315247869491577,
"epoch": 1.380966661668416,
"grad_norm": 1.65625,
"learning_rate": 0.00048166422059722996,
"loss": 6.074,
"mean_token_accuracy": 0.14898498728871346,
"num_tokens": 27022038.0,
"step": 13815
},
{
"entropy": 6.229460144042969,
"epoch": 1.3814664867296447,
"grad_norm": 1.1484375,
"learning_rate": 0.0004816501064119609,
"loss": 5.9649,
"mean_token_accuracy": 0.15633662045001984,
"num_tokens": 27032225.0,
"step": 13820
},
{
"entropy": 6.187652444839477,
"epoch": 1.3819663117908731,
"grad_norm": 1.421875,
"learning_rate": 0.0004816359870274284,
"loss": 5.9128,
"mean_token_accuracy": 0.1568162754178047,
"num_tokens": 27042770.0,
"step": 13825
},
{
"entropy": 6.149801206588745,
"epoch": 1.3824661368521018,
"grad_norm": 1.4765625,
"learning_rate": 0.0004816218624439876,
"loss": 5.9497,
"mean_token_accuracy": 0.15984033346176146,
"num_tokens": 27052543.0,
"step": 13830
},
{
"entropy": 6.182939243316651,
"epoch": 1.3829659619133303,
"grad_norm": 1.6171875,
"learning_rate": 0.00048160773266199384,
"loss": 5.9568,
"mean_token_accuracy": 0.15122343301773072,
"num_tokens": 27061955.0,
"step": 13835
},
{
"entropy": 6.109112977981567,
"epoch": 1.383465786974559,
"grad_norm": 1.8515625,
"learning_rate": 0.0004815935976818028,
"loss": 5.8423,
"mean_token_accuracy": 0.1650175616145134,
"num_tokens": 27071458.0,
"step": 13840
},
{
"entropy": 6.146598291397095,
"epoch": 1.3839656120357875,
"grad_norm": 1.3125,
"learning_rate": 0.00048157945750377005,
"loss": 5.8852,
"mean_token_accuracy": 0.1602638304233551,
"num_tokens": 27081331.0,
"step": 13845
},
{
"entropy": 6.077832221984863,
"epoch": 1.384465437097016,
"grad_norm": 1.375,
"learning_rate": 0.0004815653121282512,
"loss": 5.8383,
"mean_token_accuracy": 0.16466595232486725,
"num_tokens": 27090159.0,
"step": 13850
},
{
"entropy": 6.130023956298828,
"epoch": 1.3849652621582447,
"grad_norm": 1.234375,
"learning_rate": 0.00048155116155560227,
"loss": 5.9213,
"mean_token_accuracy": 0.1590987116098404,
"num_tokens": 27099389.0,
"step": 13855
},
{
"entropy": 6.192239904403687,
"epoch": 1.3854650872194731,
"grad_norm": 1.3125,
"learning_rate": 0.00048153700578617924,
"loss": 5.9934,
"mean_token_accuracy": 0.15302683860063554,
"num_tokens": 27109878.0,
"step": 13860
},
{
"entropy": 6.180838537216187,
"epoch": 1.3859649122807016,
"grad_norm": 1.6953125,
"learning_rate": 0.0004815228448203384,
"loss": 5.9757,
"mean_token_accuracy": 0.15419846177101135,
"num_tokens": 27119556.0,
"step": 13865
},
{
"entropy": 6.160820960998535,
"epoch": 1.3864647373419303,
"grad_norm": 1.2421875,
"learning_rate": 0.0004815086786584358,
"loss": 5.8969,
"mean_token_accuracy": 0.1629953607916832,
"num_tokens": 27129086.0,
"step": 13870
},
{
"entropy": 6.154081535339356,
"epoch": 1.386964562403159,
"grad_norm": 1.296875,
"learning_rate": 0.000481494507300828,
"loss": 5.9865,
"mean_token_accuracy": 0.1620579943060875,
"num_tokens": 27138908.0,
"step": 13875
},
{
"entropy": 6.091911125183105,
"epoch": 1.3874643874643875,
"grad_norm": 1.2421875,
"learning_rate": 0.0004814803307478716,
"loss": 5.8943,
"mean_token_accuracy": 0.1623252347111702,
"num_tokens": 27149306.0,
"step": 13880
},
{
"entropy": 6.052503061294556,
"epoch": 1.387964212525616,
"grad_norm": 1.5859375,
"learning_rate": 0.00048146614899992313,
"loss": 5.762,
"mean_token_accuracy": 0.1719990998506546,
"num_tokens": 27159293.0,
"step": 13885
},
{
"entropy": 6.099456691741944,
"epoch": 1.3884640375868447,
"grad_norm": 1.3671875,
"learning_rate": 0.00048145196205733954,
"loss": 5.8659,
"mean_token_accuracy": 0.1618460476398468,
"num_tokens": 27168450.0,
"step": 13890
},
{
"entropy": 6.111635971069336,
"epoch": 1.3889638626480731,
"grad_norm": 1.375,
"learning_rate": 0.00048143776992047767,
"loss": 5.8654,
"mean_token_accuracy": 0.16381198912858963,
"num_tokens": 27177548.0,
"step": 13895
},
{
"entropy": 6.11266860961914,
"epoch": 1.3894636877093016,
"grad_norm": 1.171875,
"learning_rate": 0.00048142357258969465,
"loss": 5.9278,
"mean_token_accuracy": 0.1604678899049759,
"num_tokens": 27186826.0,
"step": 13900
},
{
"entropy": 6.155711841583252,
"epoch": 1.3899635127705303,
"grad_norm": 1.2265625,
"learning_rate": 0.0004814093700653477,
"loss": 5.8989,
"mean_token_accuracy": 0.15810148566961288,
"num_tokens": 27196363.0,
"step": 13905
},
{
"entropy": 6.2352190017700195,
"epoch": 1.390463337831759,
"grad_norm": 1.2578125,
"learning_rate": 0.00048139516234779403,
"loss": 5.9631,
"mean_token_accuracy": 0.15756095051765442,
"num_tokens": 27205461.0,
"step": 13910
},
{
"entropy": 6.246933841705323,
"epoch": 1.3909631628929875,
"grad_norm": 1.328125,
"learning_rate": 0.00048138094943739123,
"loss": 6.0993,
"mean_token_accuracy": 0.1442100629210472,
"num_tokens": 27214490.0,
"step": 13915
},
{
"entropy": 6.0951512336730955,
"epoch": 1.391462987954216,
"grad_norm": 1.265625,
"learning_rate": 0.00048136673133449687,
"loss": 5.8902,
"mean_token_accuracy": 0.16283289194107056,
"num_tokens": 27224020.0,
"step": 13920
},
{
"entropy": 6.012313508987427,
"epoch": 1.3919628130154447,
"grad_norm": 1.8359375,
"learning_rate": 0.0004813525080394686,
"loss": 5.8459,
"mean_token_accuracy": 0.16710145846009256,
"num_tokens": 27234591.0,
"step": 13925
},
{
"entropy": 6.158491230010986,
"epoch": 1.3924626380766731,
"grad_norm": 1.265625,
"learning_rate": 0.0004813382795526644,
"loss": 5.9062,
"mean_token_accuracy": 0.160186704993248,
"num_tokens": 27244991.0,
"step": 13930
},
{
"entropy": 6.103867387771606,
"epoch": 1.3929624631379016,
"grad_norm": 1.3359375,
"learning_rate": 0.0004813240458744421,
"loss": 5.8801,
"mean_token_accuracy": 0.16120165437459946,
"num_tokens": 27254663.0,
"step": 13935
},
{
"entropy": 6.190715217590332,
"epoch": 1.3934622881991303,
"grad_norm": 1.3984375,
"learning_rate": 0.00048130980700516,
"loss": 5.9864,
"mean_token_accuracy": 0.15098951309919356,
"num_tokens": 27265238.0,
"step": 13940
},
{
"entropy": 6.164424037933349,
"epoch": 1.3939621132603588,
"grad_norm": 1.2890625,
"learning_rate": 0.0004812955629451761,
"loss": 5.9311,
"mean_token_accuracy": 0.16472459733486175,
"num_tokens": 27273844.0,
"step": 13945
},
{
"entropy": 6.096916246414184,
"epoch": 1.3944619383215875,
"grad_norm": 1.4296875,
"learning_rate": 0.0004812813136948491,
"loss": 5.8643,
"mean_token_accuracy": 0.1559591919183731,
"num_tokens": 27283356.0,
"step": 13950
},
{
"entropy": 5.921930265426636,
"epoch": 1.394961763382816,
"grad_norm": 1.3046875,
"learning_rate": 0.00048126705925453716,
"loss": 5.6979,
"mean_token_accuracy": 0.18205879777669906,
"num_tokens": 27292685.0,
"step": 13955
},
{
"entropy": 6.094734048843383,
"epoch": 1.3954615884440447,
"grad_norm": 1.25,
"learning_rate": 0.0004812527996245992,
"loss": 5.8533,
"mean_token_accuracy": 0.15713960379362107,
"num_tokens": 27302347.0,
"step": 13960
},
{
"entropy": 6.21630449295044,
"epoch": 1.3959614135052731,
"grad_norm": 1.6484375,
"learning_rate": 0.0004812385348053938,
"loss": 5.9887,
"mean_token_accuracy": 0.15596369206905364,
"num_tokens": 27311807.0,
"step": 13965
},
{
"entropy": 6.153706693649292,
"epoch": 1.3964612385665016,
"grad_norm": 1.3515625,
"learning_rate": 0.00048122426479728,
"loss": 5.9693,
"mean_token_accuracy": 0.15437859743833543,
"num_tokens": 27322561.0,
"step": 13970
},
{
"entropy": 6.141304397583008,
"epoch": 1.3969610636277303,
"grad_norm": 1.3125,
"learning_rate": 0.0004812099896006167,
"loss": 5.8954,
"mean_token_accuracy": 0.16642517298460008,
"num_tokens": 27332105.0,
"step": 13975
},
{
"entropy": 6.061940670013428,
"epoch": 1.3974608886889588,
"grad_norm": 1.65625,
"learning_rate": 0.0004811957092157631,
"loss": 5.8869,
"mean_token_accuracy": 0.1639922022819519,
"num_tokens": 27341900.0,
"step": 13980
},
{
"entropy": 6.04265947341919,
"epoch": 1.3979607137501875,
"grad_norm": 1.234375,
"learning_rate": 0.00048118142364307864,
"loss": 5.8196,
"mean_token_accuracy": 0.166228486597538,
"num_tokens": 27351991.0,
"step": 13985
},
{
"entropy": 6.142511034011841,
"epoch": 1.398460538811416,
"grad_norm": 1.28125,
"learning_rate": 0.0004811671328829225,
"loss": 5.8908,
"mean_token_accuracy": 0.16402522325515748,
"num_tokens": 27361634.0,
"step": 13990
},
{
"entropy": 6.180378198623657,
"epoch": 1.3989603638726447,
"grad_norm": 1.25,
"learning_rate": 0.00048115283693565445,
"loss": 5.9159,
"mean_token_accuracy": 0.15981507897377015,
"num_tokens": 27373528.0,
"step": 13995
},
{
"entropy": 6.148707723617553,
"epoch": 1.3994601889338731,
"grad_norm": 1.375,
"learning_rate": 0.000481138535801634,
"loss": 5.9146,
"mean_token_accuracy": 0.1565297707915306,
"num_tokens": 27382123.0,
"step": 14000
},
{
"entropy": 6.144369220733642,
"epoch": 1.3999600139951016,
"grad_norm": 1.2578125,
"learning_rate": 0.000481124229481221,
"loss": 5.8873,
"mean_token_accuracy": 0.16118423491716385,
"num_tokens": 27392486.0,
"step": 14005
},
{
"entropy": 6.159963512420655,
"epoch": 1.4004598390563303,
"grad_norm": 1.3046875,
"learning_rate": 0.0004811099179747755,
"loss": 5.8903,
"mean_token_accuracy": 0.16086832582950591,
"num_tokens": 27402018.0,
"step": 14010
},
{
"entropy": 6.145850753784179,
"epoch": 1.4009596641175588,
"grad_norm": 1.46875,
"learning_rate": 0.00048109560128265747,
"loss": 5.8914,
"mean_token_accuracy": 0.1591351494193077,
"num_tokens": 27411404.0,
"step": 14015
},
{
"entropy": 6.185385370254517,
"epoch": 1.4014594891787875,
"grad_norm": 1.2734375,
"learning_rate": 0.0004810812794052271,
"loss": 6.0506,
"mean_token_accuracy": 0.14900418370962143,
"num_tokens": 27420968.0,
"step": 14020
},
{
"entropy": 6.172234344482422,
"epoch": 1.401959314240016,
"grad_norm": 1.21875,
"learning_rate": 0.0004810669523428449,
"loss": 5.8959,
"mean_token_accuracy": 0.15800752714276314,
"num_tokens": 27430964.0,
"step": 14025
},
{
"entropy": 6.123978996276856,
"epoch": 1.4024591393012447,
"grad_norm": 1.359375,
"learning_rate": 0.000481052620095871,
"loss": 5.9186,
"mean_token_accuracy": 0.15444019436836243,
"num_tokens": 27440517.0,
"step": 14030
},
{
"entropy": 6.056941080093384,
"epoch": 1.4029589643624731,
"grad_norm": 1.390625,
"learning_rate": 0.0004810382826646664,
"loss": 5.9343,
"mean_token_accuracy": 0.15636221468448638,
"num_tokens": 27449085.0,
"step": 14035
},
{
"entropy": 6.069472932815552,
"epoch": 1.4034587894237016,
"grad_norm": 1.2265625,
"learning_rate": 0.0004810239400495915,
"loss": 5.8326,
"mean_token_accuracy": 0.1678320050239563,
"num_tokens": 27457637.0,
"step": 14040
},
{
"entropy": 6.157347393035889,
"epoch": 1.4039586144849303,
"grad_norm": 1.375,
"learning_rate": 0.0004810095922510073,
"loss": 5.9574,
"mean_token_accuracy": 0.15599428713321686,
"num_tokens": 27467967.0,
"step": 14045
},
{
"entropy": 6.114198541641235,
"epoch": 1.4044584395461588,
"grad_norm": 1.4140625,
"learning_rate": 0.00048099523926927487,
"loss": 5.9249,
"mean_token_accuracy": 0.15783270448446274,
"num_tokens": 27477386.0,
"step": 14050
},
{
"entropy": 6.108553791046143,
"epoch": 1.4049582646073875,
"grad_norm": 1.203125,
"learning_rate": 0.0004809808811047552,
"loss": 5.83,
"mean_token_accuracy": 0.16031135469675065,
"num_tokens": 27487289.0,
"step": 14055
},
{
"entropy": 6.147035026550293,
"epoch": 1.405458089668616,
"grad_norm": 1.359375,
"learning_rate": 0.00048096651775780943,
"loss": 5.8258,
"mean_token_accuracy": 0.1638666421175003,
"num_tokens": 27496687.0,
"step": 14060
},
{
"entropy": 6.085003137588501,
"epoch": 1.4059579147298447,
"grad_norm": 1.6796875,
"learning_rate": 0.0004809521492287992,
"loss": 5.8524,
"mean_token_accuracy": 0.16258841902017593,
"num_tokens": 27507040.0,
"step": 14065
},
{
"entropy": 6.180186653137207,
"epoch": 1.4064577397910731,
"grad_norm": 1.2734375,
"learning_rate": 0.0004809377755180858,
"loss": 5.9704,
"mean_token_accuracy": 0.14970656707882882,
"num_tokens": 27516861.0,
"step": 14070
},
{
"entropy": 6.1892537593841555,
"epoch": 1.4069575648523016,
"grad_norm": 1.3671875,
"learning_rate": 0.0004809233966260311,
"loss": 5.8383,
"mean_token_accuracy": 0.17061182111501694,
"num_tokens": 27526816.0,
"step": 14075
},
{
"entropy": 6.134786653518677,
"epoch": 1.4074573899135303,
"grad_norm": 1.2421875,
"learning_rate": 0.0004809090125529966,
"loss": 5.9106,
"mean_token_accuracy": 0.16102984845638274,
"num_tokens": 27535984.0,
"step": 14080
},
{
"entropy": 6.131832313537598,
"epoch": 1.4079572149747588,
"grad_norm": 1.375,
"learning_rate": 0.00048089462329934437,
"loss": 5.9056,
"mean_token_accuracy": 0.15271441340446473,
"num_tokens": 27545515.0,
"step": 14085
},
{
"entropy": 6.107638025283814,
"epoch": 1.4084570400359875,
"grad_norm": 1.40625,
"learning_rate": 0.00048088022886543636,
"loss": 5.8664,
"mean_token_accuracy": 0.1622526004910469,
"num_tokens": 27554673.0,
"step": 14090
},
{
"entropy": 6.18196816444397,
"epoch": 1.408956865097216,
"grad_norm": 1.2265625,
"learning_rate": 0.0004808658292516348,
"loss": 5.8817,
"mean_token_accuracy": 0.15931390970945358,
"num_tokens": 27564282.0,
"step": 14095
},
{
"entropy": 6.1313880443572994,
"epoch": 1.4094566901584447,
"grad_norm": 1.3359375,
"learning_rate": 0.00048085142445830197,
"loss": 5.9656,
"mean_token_accuracy": 0.14879624396562577,
"num_tokens": 27574205.0,
"step": 14100
},
{
"entropy": 6.183283472061158,
"epoch": 1.4099565152196731,
"grad_norm": 1.265625,
"learning_rate": 0.00048083701448580027,
"loss": 5.9254,
"mean_token_accuracy": 0.1590803638100624,
"num_tokens": 27584283.0,
"step": 14105
},
{
"entropy": 6.182303047180175,
"epoch": 1.4104563402809016,
"grad_norm": 1.4765625,
"learning_rate": 0.00048082259933449224,
"loss": 5.8782,
"mean_token_accuracy": 0.156558820605278,
"num_tokens": 27592828.0,
"step": 14110
},
{
"entropy": 6.088471984863281,
"epoch": 1.4109561653421303,
"grad_norm": 1.4140625,
"learning_rate": 0.0004808081790047406,
"loss": 5.9015,
"mean_token_accuracy": 0.16590752750635146,
"num_tokens": 27602412.0,
"step": 14115
},
{
"entropy": 6.125770807266235,
"epoch": 1.4114559904033588,
"grad_norm": 1.1953125,
"learning_rate": 0.00048079375349690807,
"loss": 5.8844,
"mean_token_accuracy": 0.15807032883167266,
"num_tokens": 27611685.0,
"step": 14120
},
{
"entropy": 6.174746751785278,
"epoch": 1.4119558154645873,
"grad_norm": 1.28125,
"learning_rate": 0.00048077932281135775,
"loss": 5.927,
"mean_token_accuracy": 0.15109578222036363,
"num_tokens": 27621108.0,
"step": 14125
},
{
"entropy": 6.211177730560303,
"epoch": 1.412455640525816,
"grad_norm": 1.2421875,
"learning_rate": 0.00048076488694845257,
"loss": 5.8653,
"mean_token_accuracy": 0.16404128521680833,
"num_tokens": 27631212.0,
"step": 14130
},
{
"entropy": 6.160654544830322,
"epoch": 1.4129554655870447,
"grad_norm": 1.359375,
"learning_rate": 0.00048075044590855574,
"loss": 6.0095,
"mean_token_accuracy": 0.15512877851724624,
"num_tokens": 27641071.0,
"step": 14135
},
{
"entropy": 6.164603757858276,
"epoch": 1.4134552906482731,
"grad_norm": 1.1484375,
"learning_rate": 0.00048073599969203064,
"loss": 6.0095,
"mean_token_accuracy": 0.14836524203419685,
"num_tokens": 27650903.0,
"step": 14140
},
{
"entropy": 6.162520170211792,
"epoch": 1.4139551157095016,
"grad_norm": 1.2109375,
"learning_rate": 0.0004807215482992408,
"loss": 5.9085,
"mean_token_accuracy": 0.15974087715148927,
"num_tokens": 27661272.0,
"step": 14145
},
{
"entropy": 6.146009397506714,
"epoch": 1.4144549407707303,
"grad_norm": 1.2421875,
"learning_rate": 0.0004807070917305497,
"loss": 5.9002,
"mean_token_accuracy": 0.15626959800720214,
"num_tokens": 27671042.0,
"step": 14150
},
{
"entropy": 6.132666158676147,
"epoch": 1.4149547658319588,
"grad_norm": 1.203125,
"learning_rate": 0.00048069262998632115,
"loss": 5.9089,
"mean_token_accuracy": 0.15504830479621887,
"num_tokens": 27680876.0,
"step": 14155
},
{
"entropy": 6.178604316711426,
"epoch": 1.4154545908931873,
"grad_norm": 1.4140625,
"learning_rate": 0.0004806781630669189,
"loss": 5.8828,
"mean_token_accuracy": 0.15710073336958885,
"num_tokens": 27690193.0,
"step": 14160
},
{
"entropy": 6.142898654937744,
"epoch": 1.415954415954416,
"grad_norm": 1.3046875,
"learning_rate": 0.00048066369097270694,
"loss": 5.8739,
"mean_token_accuracy": 0.1657583996653557,
"num_tokens": 27700095.0,
"step": 14165
},
{
"entropy": 6.082460927963257,
"epoch": 1.4164542410156447,
"grad_norm": 1.34375,
"learning_rate": 0.0004806492137040495,
"loss": 5.9274,
"mean_token_accuracy": 0.15387239009141923,
"num_tokens": 27710172.0,
"step": 14170
},
{
"entropy": 6.121841382980347,
"epoch": 1.4169540660768731,
"grad_norm": 1.3046875,
"learning_rate": 0.00048063473126131086,
"loss": 5.8603,
"mean_token_accuracy": 0.16136195212602616,
"num_tokens": 27720241.0,
"step": 14175
},
{
"entropy": 6.166153240203857,
"epoch": 1.4174538911381016,
"grad_norm": 1.296875,
"learning_rate": 0.0004806202436448551,
"loss": 5.9291,
"mean_token_accuracy": 0.16084531098604202,
"num_tokens": 27730959.0,
"step": 14180
},
{
"entropy": 6.100432586669922,
"epoch": 1.4179537161993303,
"grad_norm": 1.28125,
"learning_rate": 0.0004806057508550471,
"loss": 5.9178,
"mean_token_accuracy": 0.16295157372951508,
"num_tokens": 27740690.0,
"step": 14185
},
{
"entropy": 6.111538982391357,
"epoch": 1.4184535412605588,
"grad_norm": 1.3515625,
"learning_rate": 0.0004805912528922512,
"loss": 5.803,
"mean_token_accuracy": 0.16402893662452697,
"num_tokens": 27749538.0,
"step": 14190
},
{
"entropy": 6.147728681564331,
"epoch": 1.4189533663217873,
"grad_norm": 1.25,
"learning_rate": 0.0004805767497568323,
"loss": 5.8972,
"mean_token_accuracy": 0.1583215981721878,
"num_tokens": 27759150.0,
"step": 14195
},
{
"entropy": 6.15982346534729,
"epoch": 1.419453191383016,
"grad_norm": 1.359375,
"learning_rate": 0.00048056224144915534,
"loss": 5.892,
"mean_token_accuracy": 0.15838515907526016,
"num_tokens": 27767150.0,
"step": 14200
},
{
"entropy": 6.155028247833252,
"epoch": 1.4199530164442444,
"grad_norm": 1.546875,
"learning_rate": 0.00048054772796958517,
"loss": 5.9291,
"mean_token_accuracy": 0.1578789696097374,
"num_tokens": 27776866.0,
"step": 14205
},
{
"entropy": 6.101190519332886,
"epoch": 1.4204528415054731,
"grad_norm": 1.1484375,
"learning_rate": 0.00048053320931848713,
"loss": 5.7892,
"mean_token_accuracy": 0.16822739839553832,
"num_tokens": 27786941.0,
"step": 14210
},
{
"entropy": 6.2098836421966555,
"epoch": 1.4209526665667016,
"grad_norm": 1.28125,
"learning_rate": 0.00048051868549622644,
"loss": 6.0136,
"mean_token_accuracy": 0.15156687945127487,
"num_tokens": 27796962.0,
"step": 14215
},
{
"entropy": 6.102784156799316,
"epoch": 1.4214524916279303,
"grad_norm": 1.3203125,
"learning_rate": 0.00048050415650316853,
"loss": 5.901,
"mean_token_accuracy": 0.15864731073379518,
"num_tokens": 27806609.0,
"step": 14220
},
{
"entropy": 6.164079999923706,
"epoch": 1.4219523166891588,
"grad_norm": 1.21875,
"learning_rate": 0.0004804896223396789,
"loss": 5.9177,
"mean_token_accuracy": 0.1578953206539154,
"num_tokens": 27816734.0,
"step": 14225
},
{
"entropy": 6.1364082336425785,
"epoch": 1.4224521417503873,
"grad_norm": 1.296875,
"learning_rate": 0.0004804750830061232,
"loss": 5.9716,
"mean_token_accuracy": 0.14960987567901612,
"num_tokens": 27826686.0,
"step": 14230
},
{
"entropy": 6.16151762008667,
"epoch": 1.422951966811616,
"grad_norm": 1.4140625,
"learning_rate": 0.0004804605385028673,
"loss": 5.897,
"mean_token_accuracy": 0.1558688461780548,
"num_tokens": 27836193.0,
"step": 14235
},
{
"entropy": 6.100816249847412,
"epoch": 1.4234517918728444,
"grad_norm": 1.3515625,
"learning_rate": 0.0004804459888302772,
"loss": 5.8565,
"mean_token_accuracy": 0.1650846168398857,
"num_tokens": 27845175.0,
"step": 14240
},
{
"entropy": 6.120284366607666,
"epoch": 1.4239516169340731,
"grad_norm": 1.3984375,
"learning_rate": 0.00048043143398871874,
"loss": 5.8821,
"mean_token_accuracy": 0.163255175948143,
"num_tokens": 27853829.0,
"step": 14245
},
{
"entropy": 6.17583818435669,
"epoch": 1.4244514419953016,
"grad_norm": 1.328125,
"learning_rate": 0.0004804168739785583,
"loss": 5.948,
"mean_token_accuracy": 0.15891079008579254,
"num_tokens": 27863468.0,
"step": 14250
},
{
"entropy": 6.164515542984009,
"epoch": 1.4249512670565303,
"grad_norm": 1.359375,
"learning_rate": 0.0004804023088001623,
"loss": 5.9232,
"mean_token_accuracy": 0.1552080787718296,
"num_tokens": 27873565.0,
"step": 14255
},
{
"entropy": 6.255309820175171,
"epoch": 1.4254510921177588,
"grad_norm": 1.390625,
"learning_rate": 0.0004803877384538969,
"loss": 6.0268,
"mean_token_accuracy": 0.15062852203845978,
"num_tokens": 27883687.0,
"step": 14260
},
{
"entropy": 6.171930599212646,
"epoch": 1.4259509171789873,
"grad_norm": 1.25,
"learning_rate": 0.000480373162940129,
"loss": 6.0408,
"mean_token_accuracy": 0.15009994357824324,
"num_tokens": 27893702.0,
"step": 14265
},
{
"entropy": 6.186646318435669,
"epoch": 1.426450742240216,
"grad_norm": 1.2890625,
"learning_rate": 0.00048035858225922506,
"loss": 5.8781,
"mean_token_accuracy": 0.1635551504790783,
"num_tokens": 27902809.0,
"step": 14270
},
{
"entropy": 6.294264078140259,
"epoch": 1.4269505673014444,
"grad_norm": 1.5,
"learning_rate": 0.00048034399641155206,
"loss": 5.9893,
"mean_token_accuracy": 0.15167927071452142,
"num_tokens": 27912810.0,
"step": 14275
},
{
"entropy": 6.174759387969971,
"epoch": 1.4274503923626731,
"grad_norm": 1.28125,
"learning_rate": 0.00048032940539747697,
"loss": 5.9558,
"mean_token_accuracy": 0.15171603709459305,
"num_tokens": 27922402.0,
"step": 14280
},
{
"entropy": 6.11567645072937,
"epoch": 1.4279502174239016,
"grad_norm": 1.2265625,
"learning_rate": 0.00048031480921736686,
"loss": 5.9448,
"mean_token_accuracy": 0.16087897419929503,
"num_tokens": 27932379.0,
"step": 14285
},
{
"entropy": 6.228717374801636,
"epoch": 1.4284500424851303,
"grad_norm": 1.1953125,
"learning_rate": 0.000480300207871589,
"loss": 6.1143,
"mean_token_accuracy": 0.1481747403740883,
"num_tokens": 27942994.0,
"step": 14290
},
{
"entropy": 6.218153476715088,
"epoch": 1.4289498675463588,
"grad_norm": 1.359375,
"learning_rate": 0.00048028560136051076,
"loss": 5.9136,
"mean_token_accuracy": 0.15851071774959563,
"num_tokens": 27952860.0,
"step": 14295
},
{
"entropy": 6.164930152893066,
"epoch": 1.4294496926075873,
"grad_norm": 1.3046875,
"learning_rate": 0.00048027098968449954,
"loss": 5.9422,
"mean_token_accuracy": 0.15416307449340821,
"num_tokens": 27962435.0,
"step": 14300
},
{
"entropy": 6.149840688705444,
"epoch": 1.429949517668816,
"grad_norm": 1.265625,
"learning_rate": 0.0004802563728439231,
"loss": 5.8957,
"mean_token_accuracy": 0.15777752697467803,
"num_tokens": 27971889.0,
"step": 14305
},
{
"entropy": 6.174994277954101,
"epoch": 1.4304493427300444,
"grad_norm": 1.171875,
"learning_rate": 0.0004802417508391491,
"loss": 5.9658,
"mean_token_accuracy": 0.1528554804623127,
"num_tokens": 27982683.0,
"step": 14310
},
{
"entropy": 6.132606363296508,
"epoch": 1.4309491677912731,
"grad_norm": 1.1953125,
"learning_rate": 0.0004802271236705455,
"loss": 5.8754,
"mean_token_accuracy": 0.1624034583568573,
"num_tokens": 27992408.0,
"step": 14315
},
{
"entropy": 6.265625905990601,
"epoch": 1.4314489928525016,
"grad_norm": 1.2109375,
"learning_rate": 0.00048021249133848025,
"loss": 5.9676,
"mean_token_accuracy": 0.15260375365614892,
"num_tokens": 28002592.0,
"step": 14320
},
{
"entropy": 6.198496913909912,
"epoch": 1.4319488179137303,
"grad_norm": 1.1484375,
"learning_rate": 0.00048019785384332154,
"loss": 5.9437,
"mean_token_accuracy": 0.1547225907444954,
"num_tokens": 28012148.0,
"step": 14325
},
{
"entropy": 6.150672912597656,
"epoch": 1.4324486429749588,
"grad_norm": 1.375,
"learning_rate": 0.0004801832111854376,
"loss": 5.9591,
"mean_token_accuracy": 0.15324863344430922,
"num_tokens": 28021341.0,
"step": 14330
},
{
"entropy": 6.132143592834472,
"epoch": 1.4329484680361873,
"grad_norm": 1.2109375,
"learning_rate": 0.0004801685633651969,
"loss": 5.9021,
"mean_token_accuracy": 0.16061148047447205,
"num_tokens": 28030721.0,
"step": 14335
},
{
"entropy": 6.072684812545776,
"epoch": 1.433448293097416,
"grad_norm": 1.25,
"learning_rate": 0.0004801539103829679,
"loss": 5.7969,
"mean_token_accuracy": 0.1627567395567894,
"num_tokens": 28040665.0,
"step": 14340
},
{
"entropy": 6.255423450469971,
"epoch": 1.4339481181586444,
"grad_norm": 1.21875,
"learning_rate": 0.0004801392522391193,
"loss": 6.0391,
"mean_token_accuracy": 0.144136743247509,
"num_tokens": 28052307.0,
"step": 14345
},
{
"entropy": 6.175729131698608,
"epoch": 1.4344479432198731,
"grad_norm": 1.1953125,
"learning_rate": 0.00048012458893401995,
"loss": 5.8851,
"mean_token_accuracy": 0.16727278977632523,
"num_tokens": 28061347.0,
"step": 14350
},
{
"entropy": 6.2000020980834964,
"epoch": 1.4349477682811016,
"grad_norm": 1.265625,
"learning_rate": 0.0004801099204680387,
"loss": 5.9354,
"mean_token_accuracy": 0.1569803312420845,
"num_tokens": 28072088.0,
"step": 14355
},
{
"entropy": 6.2106773853302,
"epoch": 1.4354475933423303,
"grad_norm": 1.1875,
"learning_rate": 0.00048009524684154464,
"loss": 5.9715,
"mean_token_accuracy": 0.1545247182250023,
"num_tokens": 28081674.0,
"step": 14360
},
{
"entropy": 6.08840503692627,
"epoch": 1.4359474184035588,
"grad_norm": 1.21875,
"learning_rate": 0.0004800805680549069,
"loss": 5.8681,
"mean_token_accuracy": 0.16416578441858293,
"num_tokens": 28091530.0,
"step": 14365
},
{
"entropy": 6.087087249755859,
"epoch": 1.4364472434647872,
"grad_norm": 1.328125,
"learning_rate": 0.00048006588410849497,
"loss": 5.8791,
"mean_token_accuracy": 0.1558594673871994,
"num_tokens": 28102322.0,
"step": 14370
},
{
"entropy": 6.188942718505859,
"epoch": 1.436947068526016,
"grad_norm": 1.296875,
"learning_rate": 0.000480051195002678,
"loss": 5.879,
"mean_token_accuracy": 0.15761257112026214,
"num_tokens": 28112041.0,
"step": 14375
},
{
"entropy": 6.199165105819702,
"epoch": 1.4374468935872444,
"grad_norm": 1.2265625,
"learning_rate": 0.00048003650073782586,
"loss": 5.9557,
"mean_token_accuracy": 0.15307693034410477,
"num_tokens": 28122451.0,
"step": 14380
},
{
"entropy": 6.120172691345215,
"epoch": 1.437946718648473,
"grad_norm": 1.3125,
"learning_rate": 0.000480021801314308,
"loss": 5.8822,
"mean_token_accuracy": 0.1597979858517647,
"num_tokens": 28131949.0,
"step": 14385
},
{
"entropy": 6.114171886444092,
"epoch": 1.4384465437097016,
"grad_norm": 1.3671875,
"learning_rate": 0.0004800070967324944,
"loss": 5.9239,
"mean_token_accuracy": 0.1504079930484295,
"num_tokens": 28141905.0,
"step": 14390
},
{
"entropy": 6.076116371154785,
"epoch": 1.4389463687709303,
"grad_norm": 1.265625,
"learning_rate": 0.00047999238699275506,
"loss": 5.8984,
"mean_token_accuracy": 0.15590541511774064,
"num_tokens": 28150735.0,
"step": 14395
},
{
"entropy": 6.157782649993896,
"epoch": 1.4394461938321588,
"grad_norm": 1.3203125,
"learning_rate": 0.00047997767209546,
"loss": 5.8771,
"mean_token_accuracy": 0.16161351650953293,
"num_tokens": 28160872.0,
"step": 14400
},
{
"entropy": 6.1595374584198,
"epoch": 1.4399460188933872,
"grad_norm": 1.375,
"learning_rate": 0.0004799629520409795,
"loss": 5.9406,
"mean_token_accuracy": 0.15811784267425538,
"num_tokens": 28170873.0,
"step": 14405
},
{
"entropy": 6.179621076583862,
"epoch": 1.440445843954616,
"grad_norm": 1.25,
"learning_rate": 0.00047994822682968373,
"loss": 5.9148,
"mean_token_accuracy": 0.15638519823551178,
"num_tokens": 28180637.0,
"step": 14410
},
{
"entropy": 6.154677009582519,
"epoch": 1.4409456690158444,
"grad_norm": 1.34375,
"learning_rate": 0.00047993349646194343,
"loss": 5.9394,
"mean_token_accuracy": 0.15639625787734984,
"num_tokens": 28189326.0,
"step": 14415
},
{
"entropy": 6.110971260070801,
"epoch": 1.441445494077073,
"grad_norm": 1.234375,
"learning_rate": 0.00047991876093812904,
"loss": 5.8613,
"mean_token_accuracy": 0.1570332944393158,
"num_tokens": 28198729.0,
"step": 14420
},
{
"entropy": 6.109112930297852,
"epoch": 1.4419453191383016,
"grad_norm": 1.3671875,
"learning_rate": 0.00047990402025861143,
"loss": 5.8232,
"mean_token_accuracy": 0.16734228283166885,
"num_tokens": 28207525.0,
"step": 14425
},
{
"entropy": 6.187689876556396,
"epoch": 1.4424451441995303,
"grad_norm": 1.328125,
"learning_rate": 0.0004798892744237613,
"loss": 6.0315,
"mean_token_accuracy": 0.15251780599355697,
"num_tokens": 28218176.0,
"step": 14430
},
{
"entropy": 6.219600582122803,
"epoch": 1.4429449692607588,
"grad_norm": 1.2734375,
"learning_rate": 0.00047987452343394976,
"loss": 5.9204,
"mean_token_accuracy": 0.1582502841949463,
"num_tokens": 28229207.0,
"step": 14435
},
{
"entropy": 6.203507614135742,
"epoch": 1.4434447943219872,
"grad_norm": 1.265625,
"learning_rate": 0.00047985976728954794,
"loss": 5.8668,
"mean_token_accuracy": 0.1604503870010376,
"num_tokens": 28238124.0,
"step": 14440
},
{
"entropy": 6.094093132019043,
"epoch": 1.443944619383216,
"grad_norm": 1.515625,
"learning_rate": 0.0004798450059909271,
"loss": 5.9807,
"mean_token_accuracy": 0.14802010506391525,
"num_tokens": 28248359.0,
"step": 14445
},
{
"entropy": 6.220690679550171,
"epoch": 1.4444444444444444,
"grad_norm": 1.2421875,
"learning_rate": 0.0004798302395384586,
"loss": 5.9605,
"mean_token_accuracy": 0.14771072342991828,
"num_tokens": 28258200.0,
"step": 14450
},
{
"entropy": 6.238508176803589,
"epoch": 1.444944269505673,
"grad_norm": 1.2109375,
"learning_rate": 0.00047981546793251405,
"loss": 5.9454,
"mean_token_accuracy": 0.14885313659906388,
"num_tokens": 28268512.0,
"step": 14455
},
{
"entropy": 6.106968545913697,
"epoch": 1.4454440945669016,
"grad_norm": 1.171875,
"learning_rate": 0.000479800691173465,
"loss": 5.8972,
"mean_token_accuracy": 0.16408976316452026,
"num_tokens": 28278657.0,
"step": 14460
},
{
"entropy": 6.078235340118408,
"epoch": 1.4459439196281303,
"grad_norm": 1.6328125,
"learning_rate": 0.0004797859092616832,
"loss": 5.9617,
"mean_token_accuracy": 0.15647161602973939,
"num_tokens": 28289104.0,
"step": 14465
},
{
"entropy": 6.134978723526001,
"epoch": 1.4464437446893588,
"grad_norm": 1.484375,
"learning_rate": 0.00047977112219754064,
"loss": 5.8255,
"mean_token_accuracy": 0.16141843646764756,
"num_tokens": 28299110.0,
"step": 14470
},
{
"entropy": 6.124222946166992,
"epoch": 1.4469435697505872,
"grad_norm": 1.4453125,
"learning_rate": 0.0004797563299814094,
"loss": 5.886,
"mean_token_accuracy": 0.16420616954565048,
"num_tokens": 28309350.0,
"step": 14475
},
{
"entropy": 6.062426996231079,
"epoch": 1.447443394811816,
"grad_norm": 1.234375,
"learning_rate": 0.00047974153261366156,
"loss": 5.7562,
"mean_token_accuracy": 0.166972354054451,
"num_tokens": 28319080.0,
"step": 14480
},
{
"entropy": 6.159498071670532,
"epoch": 1.4479432198730444,
"grad_norm": 1.1640625,
"learning_rate": 0.0004797267300946694,
"loss": 5.8977,
"mean_token_accuracy": 0.15600424483418465,
"num_tokens": 28328853.0,
"step": 14485
},
{
"entropy": 6.172773122787476,
"epoch": 1.448443044934273,
"grad_norm": 1.3046875,
"learning_rate": 0.00047971192242480544,
"loss": 5.9304,
"mean_token_accuracy": 0.15610072016716003,
"num_tokens": 28339499.0,
"step": 14490
},
{
"entropy": 6.153044986724853,
"epoch": 1.4489428699955016,
"grad_norm": 1.4296875,
"learning_rate": 0.0004796971096044422,
"loss": 5.9281,
"mean_token_accuracy": 0.15699478089809418,
"num_tokens": 28350068.0,
"step": 14495
},
{
"entropy": 6.1847161769866945,
"epoch": 1.44944269505673,
"grad_norm": 1.1171875,
"learning_rate": 0.0004796822916339523,
"loss": 5.9728,
"mean_token_accuracy": 0.15529006868600845,
"num_tokens": 28360912.0,
"step": 14500
},
{
"entropy": 6.166716623306274,
"epoch": 1.4499425201179588,
"grad_norm": 1.3125,
"learning_rate": 0.00047966746851370865,
"loss": 5.9246,
"mean_token_accuracy": 0.15355965495109558,
"num_tokens": 28370094.0,
"step": 14505
},
{
"entropy": 6.098060274124146,
"epoch": 1.4504423451791872,
"grad_norm": 1.2578125,
"learning_rate": 0.0004796526402440841,
"loss": 5.9046,
"mean_token_accuracy": 0.15746061354875565,
"num_tokens": 28380520.0,
"step": 14510
},
{
"entropy": 6.1130444526672365,
"epoch": 1.450942170240416,
"grad_norm": 1.265625,
"learning_rate": 0.0004796378068254518,
"loss": 5.9872,
"mean_token_accuracy": 0.16089940965175628,
"num_tokens": 28390406.0,
"step": 14515
},
{
"entropy": 6.181748247146606,
"epoch": 1.4514419953016444,
"grad_norm": 1.296875,
"learning_rate": 0.000479622968258185,
"loss": 5.9006,
"mean_token_accuracy": 0.16395324021577834,
"num_tokens": 28399935.0,
"step": 14520
},
{
"entropy": 6.119853925704956,
"epoch": 1.451941820362873,
"grad_norm": 1.203125,
"learning_rate": 0.0004796081245426569,
"loss": 5.8947,
"mean_token_accuracy": 0.16107099056243895,
"num_tokens": 28409167.0,
"step": 14525
},
{
"entropy": 6.158179473876953,
"epoch": 1.4524416454241016,
"grad_norm": 1.359375,
"learning_rate": 0.00047959327567924115,
"loss": 5.9649,
"mean_token_accuracy": 0.15481597036123276,
"num_tokens": 28419093.0,
"step": 14530
},
{
"entropy": 6.101051378250122,
"epoch": 1.45294147048533,
"grad_norm": 1.21875,
"learning_rate": 0.00047957842166831103,
"loss": 5.8876,
"mean_token_accuracy": 0.15812289863824844,
"num_tokens": 28428803.0,
"step": 14535
},
{
"entropy": 6.112209796905518,
"epoch": 1.4534412955465588,
"grad_norm": 1.375,
"learning_rate": 0.00047956356251024066,
"loss": 5.8754,
"mean_token_accuracy": 0.16673296988010405,
"num_tokens": 28439724.0,
"step": 14540
},
{
"entropy": 6.178677320480347,
"epoch": 1.4539411206077872,
"grad_norm": 1.203125,
"learning_rate": 0.0004795486982054036,
"loss": 5.8549,
"mean_token_accuracy": 0.17007712721824647,
"num_tokens": 28448450.0,
"step": 14545
},
{
"entropy": 6.129712057113648,
"epoch": 1.454440945669016,
"grad_norm": 1.3359375,
"learning_rate": 0.000479533828754174,
"loss": 5.9913,
"mean_token_accuracy": 0.15599589496850969,
"num_tokens": 28458862.0,
"step": 14550
},
{
"entropy": 6.170761585235596,
"epoch": 1.4549407707302444,
"grad_norm": 1.2421875,
"learning_rate": 0.0004795189541569258,
"loss": 6.0435,
"mean_token_accuracy": 0.1463349536061287,
"num_tokens": 28469602.0,
"step": 14555
},
{
"entropy": 6.193738985061645,
"epoch": 1.455440595791473,
"grad_norm": 1.265625,
"learning_rate": 0.00047950407441403343,
"loss": 5.8647,
"mean_token_accuracy": 0.1647908315062523,
"num_tokens": 28480635.0,
"step": 14560
},
{
"entropy": 6.165647554397583,
"epoch": 1.4559404208527016,
"grad_norm": 1.265625,
"learning_rate": 0.0004794891895258711,
"loss": 5.8913,
"mean_token_accuracy": 0.16056907474994658,
"num_tokens": 28490471.0,
"step": 14565
},
{
"entropy": 6.049009561538696,
"epoch": 1.45644024591393,
"grad_norm": 1.9296875,
"learning_rate": 0.0004794742994928134,
"loss": 5.7871,
"mean_token_accuracy": 0.17293789088726044,
"num_tokens": 28499595.0,
"step": 14570
},
{
"entropy": 6.1181245803833,
"epoch": 1.4569400709751588,
"grad_norm": 1.2109375,
"learning_rate": 0.000479459404315235,
"loss": 5.8931,
"mean_token_accuracy": 0.1584995061159134,
"num_tokens": 28508278.0,
"step": 14575
},
{
"entropy": 6.099142074584961,
"epoch": 1.4574398960363872,
"grad_norm": 1.2890625,
"learning_rate": 0.00047944450399351054,
"loss": 5.9302,
"mean_token_accuracy": 0.15288180559873582,
"num_tokens": 28518286.0,
"step": 14580
},
{
"entropy": 6.181583833694458,
"epoch": 1.457939721097616,
"grad_norm": 1.421875,
"learning_rate": 0.000479429598528015,
"loss": 5.9513,
"mean_token_accuracy": 0.15104594081640244,
"num_tokens": 28527517.0,
"step": 14585
},
{
"entropy": 6.354275846481324,
"epoch": 1.4584395461588444,
"grad_norm": 1.3203125,
"learning_rate": 0.0004794146879191233,
"loss": 6.1493,
"mean_token_accuracy": 0.1467358313500881,
"num_tokens": 28538521.0,
"step": 14590
},
{
"entropy": 6.191965818405151,
"epoch": 1.458939371220073,
"grad_norm": 1.203125,
"learning_rate": 0.0004793997721672107,
"loss": 5.9166,
"mean_token_accuracy": 0.15522282123565673,
"num_tokens": 28547696.0,
"step": 14595
},
{
"entropy": 6.075242757797241,
"epoch": 1.4594391962813016,
"grad_norm": 1.171875,
"learning_rate": 0.00047938485127265243,
"loss": 5.9063,
"mean_token_accuracy": 0.16249443590641022,
"num_tokens": 28558083.0,
"step": 14600
},
{
"entropy": 6.138222694396973,
"epoch": 1.45993902134253,
"grad_norm": 1.2734375,
"learning_rate": 0.0004793699252358239,
"loss": 5.8731,
"mean_token_accuracy": 0.1642042025923729,
"num_tokens": 28568453.0,
"step": 14605
},
{
"entropy": 6.110101270675659,
"epoch": 1.4604388464037588,
"grad_norm": 1.3203125,
"learning_rate": 0.0004793549940571006,
"loss": 5.9006,
"mean_token_accuracy": 0.15804723501205445,
"num_tokens": 28578401.0,
"step": 14610
},
{
"entropy": 6.17487645149231,
"epoch": 1.4609386714649872,
"grad_norm": 1.2578125,
"learning_rate": 0.00047934005773685824,
"loss": 5.917,
"mean_token_accuracy": 0.16274190843105316,
"num_tokens": 28587717.0,
"step": 14615
},
{
"entropy": 6.189158391952515,
"epoch": 1.461438496526216,
"grad_norm": 1.40625,
"learning_rate": 0.00047932511627547266,
"loss": 5.9197,
"mean_token_accuracy": 0.15721644163131715,
"num_tokens": 28597609.0,
"step": 14620
},
{
"entropy": 6.116632652282715,
"epoch": 1.4619383215874444,
"grad_norm": 1.3203125,
"learning_rate": 0.0004793101696733197,
"loss": 5.854,
"mean_token_accuracy": 0.1576530657708645,
"num_tokens": 28606742.0,
"step": 14625
},
{
"entropy": 6.090998029708862,
"epoch": 1.4624381466486729,
"grad_norm": 1.203125,
"learning_rate": 0.00047929521793077545,
"loss": 5.8662,
"mean_token_accuracy": 0.1610901713371277,
"num_tokens": 28615822.0,
"step": 14630
},
{
"entropy": 6.1250653743743895,
"epoch": 1.4629379717099016,
"grad_norm": 1.25,
"learning_rate": 0.0004792802610482161,
"loss": 5.9559,
"mean_token_accuracy": 0.15274227187037467,
"num_tokens": 28625372.0,
"step": 14635
},
{
"entropy": 6.178671932220459,
"epoch": 1.46343779677113,
"grad_norm": 1.2421875,
"learning_rate": 0.0004792652990260179,
"loss": 5.9443,
"mean_token_accuracy": 0.15415917783975602,
"num_tokens": 28635329.0,
"step": 14640
},
{
"entropy": 6.18708987236023,
"epoch": 1.4639376218323585,
"grad_norm": 1.421875,
"learning_rate": 0.0004792503318645574,
"loss": 5.94,
"mean_token_accuracy": 0.15805829763412477,
"num_tokens": 28645534.0,
"step": 14645
},
{
"entropy": 6.17720046043396,
"epoch": 1.4644374468935872,
"grad_norm": 1.375,
"learning_rate": 0.00047923535956421104,
"loss": 6.0049,
"mean_token_accuracy": 0.15069349855184555,
"num_tokens": 28657207.0,
"step": 14650
},
{
"entropy": 6.156323862075806,
"epoch": 1.464937271954816,
"grad_norm": 1.25,
"learning_rate": 0.00047922038212535565,
"loss": 5.9406,
"mean_token_accuracy": 0.15996264815330505,
"num_tokens": 28667260.0,
"step": 14655
},
{
"entropy": 6.135656547546387,
"epoch": 1.4654370970160444,
"grad_norm": 1.140625,
"learning_rate": 0.00047920539954836793,
"loss": 5.8258,
"mean_token_accuracy": 0.15990129858255386,
"num_tokens": 28677255.0,
"step": 14660
},
{
"entropy": 6.133906602859497,
"epoch": 1.4659369220772729,
"grad_norm": 1.21875,
"learning_rate": 0.000479190411833625,
"loss": 5.8922,
"mean_token_accuracy": 0.16863906234502793,
"num_tokens": 28687136.0,
"step": 14665
},
{
"entropy": 6.1888512134552,
"epoch": 1.4664367471385016,
"grad_norm": 1.5,
"learning_rate": 0.00047917541898150377,
"loss": 5.9443,
"mean_token_accuracy": 0.15653647035360335,
"num_tokens": 28697499.0,
"step": 14670
},
{
"entropy": 6.215901803970337,
"epoch": 1.46693657219973,
"grad_norm": 1.2109375,
"learning_rate": 0.00047916042099238154,
"loss": 6.143,
"mean_token_accuracy": 0.1443213030695915,
"num_tokens": 28706843.0,
"step": 14675
},
{
"entropy": 6.159741306304932,
"epoch": 1.4674363972609585,
"grad_norm": 1.2265625,
"learning_rate": 0.00047914541786663566,
"loss": 5.9218,
"mean_token_accuracy": 0.15912147015333175,
"num_tokens": 28715676.0,
"step": 14680
},
{
"entropy": 6.040154075622558,
"epoch": 1.4679362223221872,
"grad_norm": 1.25,
"learning_rate": 0.00047913040960464363,
"loss": 5.8458,
"mean_token_accuracy": 0.16045166850090026,
"num_tokens": 28725714.0,
"step": 14685
},
{
"entropy": 6.109461879730224,
"epoch": 1.468436047383416,
"grad_norm": 1.25,
"learning_rate": 0.00047911539620678305,
"loss": 5.8981,
"mean_token_accuracy": 0.1575067088007927,
"num_tokens": 28734928.0,
"step": 14690
},
{
"entropy": 6.214490652084351,
"epoch": 1.4689358724446444,
"grad_norm": 1.28125,
"learning_rate": 0.0004791003776734316,
"loss": 5.8827,
"mean_token_accuracy": 0.16021695584058762,
"num_tokens": 28743999.0,
"step": 14695
},
{
"entropy": 6.110587310791016,
"epoch": 1.4694356975058729,
"grad_norm": 1.3203125,
"learning_rate": 0.00047908535400496713,
"loss": 5.8697,
"mean_token_accuracy": 0.16157838702201843,
"num_tokens": 28753220.0,
"step": 14700
},
{
"entropy": 6.102980613708496,
"epoch": 1.4699355225671016,
"grad_norm": 1.65625,
"learning_rate": 0.00047907032520176765,
"loss": 5.9195,
"mean_token_accuracy": 0.15651477873325348,
"num_tokens": 28762525.0,
"step": 14705
},
{
"entropy": 6.119652509689331,
"epoch": 1.47043534762833,
"grad_norm": 1.1640625,
"learning_rate": 0.0004790552912642113,
"loss": 5.8493,
"mean_token_accuracy": 0.16263106763362883,
"num_tokens": 28772749.0,
"step": 14710
},
{
"entropy": 6.09613618850708,
"epoch": 1.4709351726895585,
"grad_norm": 1.3671875,
"learning_rate": 0.00047904025219267643,
"loss": 5.8545,
"mean_token_accuracy": 0.16698092073202134,
"num_tokens": 28782685.0,
"step": 14715
},
{
"entropy": 6.1994640827178955,
"epoch": 1.4714349977507872,
"grad_norm": 1.46875,
"learning_rate": 0.00047902520798754125,
"loss": 6.0044,
"mean_token_accuracy": 0.1522551216185093,
"num_tokens": 28794172.0,
"step": 14720
},
{
"entropy": 6.172838163375855,
"epoch": 1.471934822812016,
"grad_norm": 1.4140625,
"learning_rate": 0.0004790101586491843,
"loss": 5.9801,
"mean_token_accuracy": 0.1458091601729393,
"num_tokens": 28805513.0,
"step": 14725
},
{
"entropy": 6.186948156356811,
"epoch": 1.4724346478732444,
"grad_norm": 1.640625,
"learning_rate": 0.0004789951041779843,
"loss": 5.9139,
"mean_token_accuracy": 0.16275637447834015,
"num_tokens": 28815737.0,
"step": 14730
},
{
"entropy": 6.125944757461548,
"epoch": 1.4729344729344729,
"grad_norm": 1.25,
"learning_rate": 0.00047898004457432,
"loss": 5.8995,
"mean_token_accuracy": 0.1576883852481842,
"num_tokens": 28824901.0,
"step": 14735
},
{
"entropy": 6.105707836151123,
"epoch": 1.4734342979957016,
"grad_norm": 1.2421875,
"learning_rate": 0.0004789649798385702,
"loss": 5.8519,
"mean_token_accuracy": 0.1626073956489563,
"num_tokens": 28833625.0,
"step": 14740
},
{
"entropy": 6.000137519836426,
"epoch": 1.47393412305693,
"grad_norm": 1.3203125,
"learning_rate": 0.00047894990997111403,
"loss": 5.788,
"mean_token_accuracy": 0.17254174053668975,
"num_tokens": 28843084.0,
"step": 14745
},
{
"entropy": 6.099820137023926,
"epoch": 1.4744339481181585,
"grad_norm": 1.2265625,
"learning_rate": 0.00047893483497233057,
"loss": 5.8222,
"mean_token_accuracy": 0.16964966654777527,
"num_tokens": 28852320.0,
"step": 14750
},
{
"entropy": 6.124870920181275,
"epoch": 1.4749337731793872,
"grad_norm": 1.3984375,
"learning_rate": 0.0004789197548425992,
"loss": 5.8601,
"mean_token_accuracy": 0.16351866126060485,
"num_tokens": 28861379.0,
"step": 14755
},
{
"entropy": 6.057726812362671,
"epoch": 1.4754335982406157,
"grad_norm": 1.2265625,
"learning_rate": 0.0004789046695822992,
"loss": 5.8656,
"mean_token_accuracy": 0.1662130355834961,
"num_tokens": 28871181.0,
"step": 14760
},
{
"entropy": 6.161553573608399,
"epoch": 1.4759334233018444,
"grad_norm": 1.1796875,
"learning_rate": 0.00047888957919181026,
"loss": 5.9235,
"mean_token_accuracy": 0.16569416970014572,
"num_tokens": 28880763.0,
"step": 14765
},
{
"entropy": 6.042367172241211,
"epoch": 1.4764332483630729,
"grad_norm": 1.15625,
"learning_rate": 0.0004788744836715119,
"loss": 5.8459,
"mean_token_accuracy": 0.16730682253837587,
"num_tokens": 28889876.0,
"step": 14770
},
{
"entropy": 6.173138570785523,
"epoch": 1.4769330734243016,
"grad_norm": 1.1796875,
"learning_rate": 0.0004788593830217841,
"loss": 5.8908,
"mean_token_accuracy": 0.1583087906241417,
"num_tokens": 28899765.0,
"step": 14775
},
{
"entropy": 6.176129913330078,
"epoch": 1.47743289848553,
"grad_norm": 1.234375,
"learning_rate": 0.00047884427724300657,
"loss": 5.9449,
"mean_token_accuracy": 0.15468351691961288,
"num_tokens": 28909755.0,
"step": 14780
},
{
"entropy": 6.149960899353028,
"epoch": 1.4779327235467585,
"grad_norm": 1.375,
"learning_rate": 0.0004788291663355595,
"loss": 5.894,
"mean_token_accuracy": 0.1665000408887863,
"num_tokens": 28919368.0,
"step": 14785
},
{
"entropy": 6.165680408477783,
"epoch": 1.4784325486079872,
"grad_norm": 1.3828125,
"learning_rate": 0.0004788140502998231,
"loss": 5.9294,
"mean_token_accuracy": 0.15894270688295364,
"num_tokens": 28930076.0,
"step": 14790
},
{
"entropy": 6.140274333953857,
"epoch": 1.4789323736692157,
"grad_norm": 1.3359375,
"learning_rate": 0.0004787989291361776,
"loss": 5.9205,
"mean_token_accuracy": 0.1603965252637863,
"num_tokens": 28939555.0,
"step": 14795
},
{
"entropy": 6.148188877105713,
"epoch": 1.4794321987304444,
"grad_norm": 1.328125,
"learning_rate": 0.0004787838028450035,
"loss": 5.9848,
"mean_token_accuracy": 0.14777956530451775,
"num_tokens": 28951084.0,
"step": 14800
},
{
"entropy": 6.226462173461914,
"epoch": 1.4799320237916729,
"grad_norm": 1.2109375,
"learning_rate": 0.00047876867142668136,
"loss": 5.9414,
"mean_token_accuracy": 0.1543032169342041,
"num_tokens": 28960798.0,
"step": 14805
},
{
"entropy": 6.1780486583709715,
"epoch": 1.4804318488529016,
"grad_norm": 1.6640625,
"learning_rate": 0.0004787535348815918,
"loss": 5.864,
"mean_token_accuracy": 0.16375095248222352,
"num_tokens": 28970543.0,
"step": 14810
},
{
"entropy": 6.194151735305786,
"epoch": 1.48093167391413,
"grad_norm": 1.2734375,
"learning_rate": 0.00047873839321011587,
"loss": 6.012,
"mean_token_accuracy": 0.14943614453077317,
"num_tokens": 28979863.0,
"step": 14815
},
{
"entropy": 6.129429864883423,
"epoch": 1.4814314989753585,
"grad_norm": 1.6328125,
"learning_rate": 0.0004787232464126343,
"loss": 5.8644,
"mean_token_accuracy": 0.16435156166553497,
"num_tokens": 28989774.0,
"step": 14820
},
{
"entropy": 6.19352879524231,
"epoch": 1.4819313240365872,
"grad_norm": 1.515625,
"learning_rate": 0.0004787080944895283,
"loss": 5.996,
"mean_token_accuracy": 0.1473240524530411,
"num_tokens": 29000608.0,
"step": 14825
},
{
"entropy": 6.1841965675354,
"epoch": 1.4824311490978157,
"grad_norm": 1.1875,
"learning_rate": 0.00047869293744117906,
"loss": 6.0098,
"mean_token_accuracy": 0.15313551798462868,
"num_tokens": 29010977.0,
"step": 14830
},
{
"entropy": 6.220831680297851,
"epoch": 1.4829309741590444,
"grad_norm": 1.28125,
"learning_rate": 0.00047867777526796793,
"loss": 5.856,
"mean_token_accuracy": 0.15731898695230484,
"num_tokens": 29021868.0,
"step": 14835
},
{
"entropy": 6.115712213516235,
"epoch": 1.4834307992202729,
"grad_norm": 1.40625,
"learning_rate": 0.0004786626079702764,
"loss": 5.9075,
"mean_token_accuracy": 0.15869607031345367,
"num_tokens": 29031878.0,
"step": 14840
},
{
"entropy": 6.217625761032105,
"epoch": 1.4839306242815016,
"grad_norm": 1.40625,
"learning_rate": 0.0004786474355484861,
"loss": 6.0335,
"mean_token_accuracy": 0.15758893713355066,
"num_tokens": 29041862.0,
"step": 14845
},
{
"entropy": 6.116294860839844,
"epoch": 1.48443044934273,
"grad_norm": 1.2421875,
"learning_rate": 0.0004786322580029786,
"loss": 5.949,
"mean_token_accuracy": 0.1577303647994995,
"num_tokens": 29052534.0,
"step": 14850
},
{
"entropy": 6.123795652389527,
"epoch": 1.4849302744039585,
"grad_norm": 1.2109375,
"learning_rate": 0.00047861707533413593,
"loss": 5.8547,
"mean_token_accuracy": 0.16392020434141158,
"num_tokens": 29061958.0,
"step": 14855
},
{
"entropy": 6.063033246994019,
"epoch": 1.4854300994651872,
"grad_norm": 1.3203125,
"learning_rate": 0.0004786018875423401,
"loss": 5.7618,
"mean_token_accuracy": 0.166125600785017,
"num_tokens": 29071816.0,
"step": 14860
},
{
"entropy": 6.1030198097229,
"epoch": 1.4859299245264157,
"grad_norm": 1.234375,
"learning_rate": 0.00047858669462797317,
"loss": 5.8596,
"mean_token_accuracy": 0.1690874069929123,
"num_tokens": 29081198.0,
"step": 14865
},
{
"entropy": 6.134812068939209,
"epoch": 1.4864297495876444,
"grad_norm": 1.1796875,
"learning_rate": 0.00047857149659141736,
"loss": 5.9842,
"mean_token_accuracy": 0.1529584437608719,
"num_tokens": 29091197.0,
"step": 14870
},
{
"entropy": 6.141243028640747,
"epoch": 1.4869295746488729,
"grad_norm": 1.4375,
"learning_rate": 0.0004785562934330551,
"loss": 5.9408,
"mean_token_accuracy": 0.15979982614517213,
"num_tokens": 29100386.0,
"step": 14875
},
{
"entropy": 6.164915895462036,
"epoch": 1.4874293997101016,
"grad_norm": 1.3984375,
"learning_rate": 0.00047854108515326885,
"loss": 5.9109,
"mean_token_accuracy": 0.15709883868694305,
"num_tokens": 29110056.0,
"step": 14880
},
{
"entropy": 6.093268585205078,
"epoch": 1.48792922477133,
"grad_norm": 1.28125,
"learning_rate": 0.0004785258717524412,
"loss": 5.7527,
"mean_token_accuracy": 0.17023885250091553,
"num_tokens": 29119157.0,
"step": 14885
},
{
"entropy": 6.172559642791748,
"epoch": 1.4884290498325585,
"grad_norm": 1.3515625,
"learning_rate": 0.00047851065323095514,
"loss": 5.8884,
"mean_token_accuracy": 0.15377486795186995,
"num_tokens": 29129075.0,
"step": 14890
},
{
"entropy": 6.14768352508545,
"epoch": 1.4889288748937872,
"grad_norm": 1.203125,
"learning_rate": 0.0004784954295891933,
"loss": 5.9267,
"mean_token_accuracy": 0.1599687159061432,
"num_tokens": 29139026.0,
"step": 14895
},
{
"entropy": 6.131284952163696,
"epoch": 1.4894286999550157,
"grad_norm": 1.3671875,
"learning_rate": 0.00047848020082753883,
"loss": 5.8344,
"mean_token_accuracy": 0.16366566866636276,
"num_tokens": 29149315.0,
"step": 14900
},
{
"entropy": 6.11028904914856,
"epoch": 1.4899285250162442,
"grad_norm": 1.203125,
"learning_rate": 0.0004784649669463749,
"loss": 5.901,
"mean_token_accuracy": 0.1520991563796997,
"num_tokens": 29158916.0,
"step": 14905
},
{
"entropy": 6.122009515762329,
"epoch": 1.4904283500774729,
"grad_norm": 1.265625,
"learning_rate": 0.00047844972794608474,
"loss": 5.887,
"mean_token_accuracy": 0.15574095398187637,
"num_tokens": 29166844.0,
"step": 14910
},
{
"entropy": 6.097465562820434,
"epoch": 1.4909281751387016,
"grad_norm": 1.328125,
"learning_rate": 0.00047843448382705185,
"loss": 5.8494,
"mean_token_accuracy": 0.17061115056276321,
"num_tokens": 29176057.0,
"step": 14915
},
{
"entropy": 6.091483068466187,
"epoch": 1.49142800019993,
"grad_norm": 1.375,
"learning_rate": 0.00047841923458965966,
"loss": 5.893,
"mean_token_accuracy": 0.16030517518520354,
"num_tokens": 29186212.0,
"step": 14920
},
{
"entropy": 6.044935894012451,
"epoch": 1.4919278252611585,
"grad_norm": 1.2421875,
"learning_rate": 0.00047840398023429176,
"loss": 5.83,
"mean_token_accuracy": 0.16389580219984054,
"num_tokens": 29196138.0,
"step": 14925
},
{
"entropy": 6.248041582107544,
"epoch": 1.4924276503223872,
"grad_norm": 1.828125,
"learning_rate": 0.00047838872076133213,
"loss": 5.9521,
"mean_token_accuracy": 0.15093939006328583,
"num_tokens": 29205979.0,
"step": 14930
},
{
"entropy": 6.1723264217376705,
"epoch": 1.4929274753836157,
"grad_norm": 1.2734375,
"learning_rate": 0.0004783734561711647,
"loss": 5.9478,
"mean_token_accuracy": 0.15050376653671266,
"num_tokens": 29214776.0,
"step": 14935
},
{
"entropy": 6.058135271072388,
"epoch": 1.4934273004448442,
"grad_norm": 1.203125,
"learning_rate": 0.00047835818646417333,
"loss": 5.8007,
"mean_token_accuracy": 0.16314827799797058,
"num_tokens": 29223823.0,
"step": 14940
},
{
"entropy": 6.123723745346069,
"epoch": 1.4939271255060729,
"grad_norm": 1.15625,
"learning_rate": 0.0004783429116407423,
"loss": 5.883,
"mean_token_accuracy": 0.16150118112564088,
"num_tokens": 29232974.0,
"step": 14945
},
{
"entropy": 6.146603631973266,
"epoch": 1.4944269505673016,
"grad_norm": 1.203125,
"learning_rate": 0.00047832763170125605,
"loss": 5.8555,
"mean_token_accuracy": 0.1592354506254196,
"num_tokens": 29241773.0,
"step": 14950
},
{
"entropy": 6.093553876876831,
"epoch": 1.49492677562853,
"grad_norm": 1.2421875,
"learning_rate": 0.00047831234664609887,
"loss": 5.8239,
"mean_token_accuracy": 0.1623486638069153,
"num_tokens": 29251490.0,
"step": 14955
},
{
"entropy": 6.033182525634766,
"epoch": 1.4954266006897585,
"grad_norm": 1.390625,
"learning_rate": 0.00047829705647565535,
"loss": 5.8263,
"mean_token_accuracy": 0.17424614429473878,
"num_tokens": 29260338.0,
"step": 14960
},
{
"entropy": 6.075300455093384,
"epoch": 1.4959264257509872,
"grad_norm": 1.203125,
"learning_rate": 0.0004782817611903102,
"loss": 5.8884,
"mean_token_accuracy": 0.16413553506135942,
"num_tokens": 29270192.0,
"step": 14965
},
{
"entropy": 6.177013301849366,
"epoch": 1.4964262508122157,
"grad_norm": 1.2265625,
"learning_rate": 0.00047826646079044826,
"loss": 5.9925,
"mean_token_accuracy": 0.15769227743148803,
"num_tokens": 29281413.0,
"step": 14970
},
{
"entropy": 6.214835739135742,
"epoch": 1.4969260758734442,
"grad_norm": 1.1484375,
"learning_rate": 0.00047825115527645447,
"loss": 5.9375,
"mean_token_accuracy": 0.16006978526711463,
"num_tokens": 29291959.0,
"step": 14975
},
{
"entropy": 6.159595537185669,
"epoch": 1.4974259009346729,
"grad_norm": 1.53125,
"learning_rate": 0.0004782358446487139,
"loss": 5.9376,
"mean_token_accuracy": 0.1653369426727295,
"num_tokens": 29302577.0,
"step": 14980
},
{
"entropy": 6.090263938903808,
"epoch": 1.4979257259959016,
"grad_norm": 1.21875,
"learning_rate": 0.00047822052890761173,
"loss": 5.8455,
"mean_token_accuracy": 0.16826079934835433,
"num_tokens": 29312437.0,
"step": 14985
},
{
"entropy": 6.018375253677368,
"epoch": 1.49842555105713,
"grad_norm": 1.2734375,
"learning_rate": 0.0004782052080535334,
"loss": 5.8087,
"mean_token_accuracy": 0.16640501022338866,
"num_tokens": 29321777.0,
"step": 14990
},
{
"entropy": 6.174808120727539,
"epoch": 1.4989253761183585,
"grad_norm": 1.3046875,
"learning_rate": 0.0004781898820868644,
"loss": 5.8705,
"mean_token_accuracy": 0.16114144772291183,
"num_tokens": 29330551.0,
"step": 14995
},
{
"entropy": 6.155779838562012,
"epoch": 1.4994252011795872,
"grad_norm": 1.234375,
"learning_rate": 0.0004781745510079901,
"loss": 5.8858,
"mean_token_accuracy": 0.15882690846920014,
"num_tokens": 29340110.0,
"step": 15000
},
{
"epoch": 1.4994252011795872,
"eval_entropy": 5.969068961916311,
"eval_loss": 5.9901204109191895,
"eval_mean_token_accuracy": 0.16268406624655476,
"eval_num_tokens": 29340110.0,
"eval_runtime": 23.8708,
"eval_samples_per_second": 1300.543,
"eval_steps_per_second": 162.584,
"step": 15000
},
{
"entropy": 6.136759567260742,
"epoch": 1.4999250262408157,
"grad_norm": 1.2109375,
"learning_rate": 0.00047815921481729647,
"loss": 5.9589,
"mean_token_accuracy": 0.1545475646853447,
"num_tokens": 29348935.0,
"step": 15005
},
{
"entropy": 6.1694427013397215,
"epoch": 1.5004248513020442,
"grad_norm": 1.28125,
"learning_rate": 0.0004781438735151693,
"loss": 5.9873,
"mean_token_accuracy": 0.1474507212638855,
"num_tokens": 29359108.0,
"step": 15010
},
{
"entropy": 6.155844497680664,
"epoch": 1.5009246763632729,
"grad_norm": 1.3984375,
"learning_rate": 0.00047812852710199446,
"loss": 5.8629,
"mean_token_accuracy": 0.17175030708312988,
"num_tokens": 29369074.0,
"step": 15015
},
{
"entropy": 6.116925764083862,
"epoch": 1.5014245014245016,
"grad_norm": 1.34375,
"learning_rate": 0.0004781131755781582,
"loss": 5.9026,
"mean_token_accuracy": 0.14713370203971862,
"num_tokens": 29379138.0,
"step": 15020
},
{
"entropy": 6.125406885147095,
"epoch": 1.50192432648573,
"grad_norm": 1.1953125,
"learning_rate": 0.0004780978189440467,
"loss": 5.9195,
"mean_token_accuracy": 0.15533546209335328,
"num_tokens": 29389124.0,
"step": 15025
},
{
"entropy": 6.08275671005249,
"epoch": 1.5024241515469585,
"grad_norm": 1.203125,
"learning_rate": 0.00047808245720004633,
"loss": 5.791,
"mean_token_accuracy": 0.17125678062438965,
"num_tokens": 29398179.0,
"step": 15030
},
{
"entropy": 6.158256149291992,
"epoch": 1.5029239766081872,
"grad_norm": 1.1640625,
"learning_rate": 0.00047806709034654355,
"loss": 5.8612,
"mean_token_accuracy": 0.15952516198158265,
"num_tokens": 29408177.0,
"step": 15035
},
{
"entropy": 6.1401965618133545,
"epoch": 1.5034238016694157,
"grad_norm": 1.2421875,
"learning_rate": 0.0004780517183839251,
"loss": 5.9062,
"mean_token_accuracy": 0.15829854160547258,
"num_tokens": 29418699.0,
"step": 15040
},
{
"entropy": 6.11042857170105,
"epoch": 1.5039236267306442,
"grad_norm": 1.109375,
"learning_rate": 0.0004780363413125777,
"loss": 5.9532,
"mean_token_accuracy": 0.16332702040672303,
"num_tokens": 29429271.0,
"step": 15045
},
{
"entropy": 6.222468280792237,
"epoch": 1.5044234517918729,
"grad_norm": 1.2578125,
"learning_rate": 0.00047802095913288814,
"loss": 6.0609,
"mean_token_accuracy": 0.15482898354530333,
"num_tokens": 29439004.0,
"step": 15050
},
{
"entropy": 6.212536144256592,
"epoch": 1.5049232768531016,
"grad_norm": 1.2734375,
"learning_rate": 0.00047800557184524345,
"loss": 6.0066,
"mean_token_accuracy": 0.1551068164408207,
"num_tokens": 29449359.0,
"step": 15055
},
{
"entropy": 6.163725566864014,
"epoch": 1.5054231019143298,
"grad_norm": 1.296875,
"learning_rate": 0.0004779901794500308,
"loss": 5.9846,
"mean_token_accuracy": 0.1515995517373085,
"num_tokens": 29459277.0,
"step": 15060
},
{
"entropy": 6.151822710037232,
"epoch": 1.5059229269755585,
"grad_norm": 1.25,
"learning_rate": 0.00047797478194763754,
"loss": 5.9079,
"mean_token_accuracy": 0.15930714681744576,
"num_tokens": 29468676.0,
"step": 15065
},
{
"entropy": 6.190333271026612,
"epoch": 1.5064227520367872,
"grad_norm": 1.5,
"learning_rate": 0.00047795937933845103,
"loss": 5.9837,
"mean_token_accuracy": 0.15031797289848328,
"num_tokens": 29478343.0,
"step": 15070
},
{
"entropy": 6.194295978546142,
"epoch": 1.5069225770980157,
"grad_norm": 1.2734375,
"learning_rate": 0.0004779439716228587,
"loss": 5.8796,
"mean_token_accuracy": 0.15300556197762488,
"num_tokens": 29488434.0,
"step": 15075
},
{
"entropy": 6.120421552658081,
"epoch": 1.5074224021592442,
"grad_norm": 1.1796875,
"learning_rate": 0.0004779285588012482,
"loss": 5.8355,
"mean_token_accuracy": 0.16310104876756668,
"num_tokens": 29498303.0,
"step": 15080
},
{
"entropy": 6.135522127151489,
"epoch": 1.5079222272204729,
"grad_norm": 1.3125,
"learning_rate": 0.00047791314087400745,
"loss": 5.9743,
"mean_token_accuracy": 0.15061080157756807,
"num_tokens": 29508597.0,
"step": 15085
},
{
"entropy": 6.112280464172363,
"epoch": 1.5084220522817016,
"grad_norm": 1.2890625,
"learning_rate": 0.0004778977178415243,
"loss": 5.859,
"mean_token_accuracy": 0.169554241001606,
"num_tokens": 29517640.0,
"step": 15090
},
{
"entropy": 6.188988971710205,
"epoch": 1.5089218773429298,
"grad_norm": 1.2265625,
"learning_rate": 0.0004778822897041868,
"loss": 5.9274,
"mean_token_accuracy": 0.15721369832754134,
"num_tokens": 29527415.0,
"step": 15095
},
{
"entropy": 6.209465456008911,
"epoch": 1.5094217024041585,
"grad_norm": 1.3046875,
"learning_rate": 0.000477866856462383,
"loss": 5.8605,
"mean_token_accuracy": 0.15844809412956237,
"num_tokens": 29537296.0,
"step": 15100
},
{
"entropy": 6.197969102859497,
"epoch": 1.5099215274653872,
"grad_norm": 1.3203125,
"learning_rate": 0.0004778514181165014,
"loss": 5.9588,
"mean_token_accuracy": 0.15580889582633972,
"num_tokens": 29546709.0,
"step": 15105
},
{
"entropy": 6.186705923080444,
"epoch": 1.5104213525266157,
"grad_norm": 1.8984375,
"learning_rate": 0.00047783597466693025,
"loss": 5.9633,
"mean_token_accuracy": 0.14912043362855912,
"num_tokens": 29556627.0,
"step": 15110
},
{
"entropy": 6.220252609252929,
"epoch": 1.5109211775878442,
"grad_norm": 1.453125,
"learning_rate": 0.0004778205261140582,
"loss": 5.926,
"mean_token_accuracy": 0.15555409342050552,
"num_tokens": 29566381.0,
"step": 15115
},
{
"entropy": 6.15552773475647,
"epoch": 1.5114210026490729,
"grad_norm": 1.3125,
"learning_rate": 0.0004778050724582739,
"loss": 5.9514,
"mean_token_accuracy": 0.15807626098394395,
"num_tokens": 29575634.0,
"step": 15120
},
{
"entropy": 6.0975908756256105,
"epoch": 1.5119208277103013,
"grad_norm": 1.4453125,
"learning_rate": 0.00047778961369996623,
"loss": 5.8829,
"mean_token_accuracy": 0.16284081786870958,
"num_tokens": 29586103.0,
"step": 15125
},
{
"entropy": 6.158964395523071,
"epoch": 1.5124206527715298,
"grad_norm": 1.125,
"learning_rate": 0.000477774149839524,
"loss": 5.8585,
"mean_token_accuracy": 0.16471410542726517,
"num_tokens": 29596764.0,
"step": 15130
},
{
"entropy": 6.153457593917847,
"epoch": 1.5129204778327585,
"grad_norm": 1.234375,
"learning_rate": 0.00047775868087733634,
"loss": 5.8687,
"mean_token_accuracy": 0.15700220316648483,
"num_tokens": 29606642.0,
"step": 15135
},
{
"entropy": 6.119776487350464,
"epoch": 1.5134203028939872,
"grad_norm": 1.296875,
"learning_rate": 0.00047774320681379237,
"loss": 5.9441,
"mean_token_accuracy": 0.15507982820272445,
"num_tokens": 29616583.0,
"step": 15140
},
{
"entropy": 6.067386531829834,
"epoch": 1.5139201279552157,
"grad_norm": 1.234375,
"learning_rate": 0.0004777277276492816,
"loss": 5.8794,
"mean_token_accuracy": 0.1614138051867485,
"num_tokens": 29625961.0,
"step": 15145
},
{
"entropy": 6.19804801940918,
"epoch": 1.5144199530164442,
"grad_norm": 1.296875,
"learning_rate": 0.00047771224338419326,
"loss": 5.8563,
"mean_token_accuracy": 0.1565035417675972,
"num_tokens": 29636089.0,
"step": 15150
},
{
"entropy": 6.150305318832397,
"epoch": 1.5149197780776729,
"grad_norm": 1.2578125,
"learning_rate": 0.0004776967540189171,
"loss": 5.8817,
"mean_token_accuracy": 0.16364790499210358,
"num_tokens": 29646068.0,
"step": 15155
},
{
"entropy": 6.071046972274781,
"epoch": 1.5154196031389013,
"grad_norm": 1.3203125,
"learning_rate": 0.0004776812595538428,
"loss": 5.838,
"mean_token_accuracy": 0.16742997318506242,
"num_tokens": 29655248.0,
"step": 15160
},
{
"entropy": 6.117970705032349,
"epoch": 1.5159194282001298,
"grad_norm": 1.21875,
"learning_rate": 0.00047766575998936013,
"loss": 5.9373,
"mean_token_accuracy": 0.15023559853434562,
"num_tokens": 29665073.0,
"step": 15165
},
{
"entropy": 6.197440958023071,
"epoch": 1.5164192532613585,
"grad_norm": 1.1953125,
"learning_rate": 0.00047765025532585907,
"loss": 5.948,
"mean_token_accuracy": 0.15950971692800522,
"num_tokens": 29674714.0,
"step": 15170
},
{
"entropy": 6.190606117248535,
"epoch": 1.5169190783225872,
"grad_norm": 1.25,
"learning_rate": 0.0004776347455637298,
"loss": 5.9363,
"mean_token_accuracy": 0.16096141040325165,
"num_tokens": 29683658.0,
"step": 15175
},
{
"entropy": 6.089086961746216,
"epoch": 1.5174189033838157,
"grad_norm": 1.3203125,
"learning_rate": 0.0004776192307033624,
"loss": 5.8169,
"mean_token_accuracy": 0.1700205460190773,
"num_tokens": 29693089.0,
"step": 15180
},
{
"entropy": 6.169860601425171,
"epoch": 1.5179187284450442,
"grad_norm": 1.4140625,
"learning_rate": 0.0004776037107451473,
"loss": 5.8853,
"mean_token_accuracy": 0.16439483165740967,
"num_tokens": 29702727.0,
"step": 15185
},
{
"entropy": 6.1305726051330565,
"epoch": 1.5184185535062729,
"grad_norm": 1.421875,
"learning_rate": 0.000477588185689475,
"loss": 5.9308,
"mean_token_accuracy": 0.16092125773429872,
"num_tokens": 29713882.0,
"step": 15190
},
{
"entropy": 6.0984578132629395,
"epoch": 1.5189183785675013,
"grad_norm": 1.265625,
"learning_rate": 0.00047757265553673606,
"loss": 5.7868,
"mean_token_accuracy": 0.17264163494110107,
"num_tokens": 29722792.0,
"step": 15195
},
{
"entropy": 6.127743816375732,
"epoch": 1.5194182036287298,
"grad_norm": 1.3046875,
"learning_rate": 0.00047755712028732126,
"loss": 5.9729,
"mean_token_accuracy": 0.1568317450582981,
"num_tokens": 29734246.0,
"step": 15200
},
{
"entropy": 6.293207502365112,
"epoch": 1.5199180286899585,
"grad_norm": 1.265625,
"learning_rate": 0.0004775415799416214,
"loss": 5.9807,
"mean_token_accuracy": 0.15994197130203247,
"num_tokens": 29743747.0,
"step": 15205
},
{
"entropy": 6.1655213832855225,
"epoch": 1.5204178537511872,
"grad_norm": 1.2734375,
"learning_rate": 0.0004775260345000275,
"loss": 5.8287,
"mean_token_accuracy": 0.1625361904501915,
"num_tokens": 29754136.0,
"step": 15210
},
{
"entropy": 6.06421685218811,
"epoch": 1.5209176788124157,
"grad_norm": 1.2265625,
"learning_rate": 0.00047751048396293077,
"loss": 5.7872,
"mean_token_accuracy": 0.16893598884344102,
"num_tokens": 29763802.0,
"step": 15215
},
{
"entropy": 6.041688394546509,
"epoch": 1.5214175038736442,
"grad_norm": 1.1875,
"learning_rate": 0.00047749492833072226,
"loss": 5.8142,
"mean_token_accuracy": 0.157342828810215,
"num_tokens": 29773376.0,
"step": 15220
},
{
"entropy": 6.132526111602783,
"epoch": 1.5219173289348729,
"grad_norm": 1.3125,
"learning_rate": 0.00047747936760379354,
"loss": 5.8995,
"mean_token_accuracy": 0.16234552711248398,
"num_tokens": 29784407.0,
"step": 15225
},
{
"entropy": 6.145341539382935,
"epoch": 1.5224171539961013,
"grad_norm": 1.359375,
"learning_rate": 0.000477463801782536,
"loss": 5.8678,
"mean_token_accuracy": 0.15537516698241233,
"num_tokens": 29794745.0,
"step": 15230
},
{
"entropy": 6.1384529113769535,
"epoch": 1.5229169790573298,
"grad_norm": 1.1171875,
"learning_rate": 0.00047744823086734136,
"loss": 5.8573,
"mean_token_accuracy": 0.15867346078157424,
"num_tokens": 29804393.0,
"step": 15235
},
{
"entropy": 6.1012818813323975,
"epoch": 1.5234168041185585,
"grad_norm": 1.2421875,
"learning_rate": 0.00047743265485860123,
"loss": 5.8416,
"mean_token_accuracy": 0.1608274683356285,
"num_tokens": 29814306.0,
"step": 15240
},
{
"entropy": 6.17518720626831,
"epoch": 1.5239166291797872,
"grad_norm": 1.3203125,
"learning_rate": 0.00047741707375670766,
"loss": 5.8899,
"mean_token_accuracy": 0.1588516876101494,
"num_tokens": 29823730.0,
"step": 15245
},
{
"entropy": 6.14407172203064,
"epoch": 1.5244164542410157,
"grad_norm": 1.171875,
"learning_rate": 0.0004774014875620526,
"loss": 5.8686,
"mean_token_accuracy": 0.15934555977582932,
"num_tokens": 29833901.0,
"step": 15250
},
{
"entropy": 6.098142433166504,
"epoch": 1.5249162793022442,
"grad_norm": 1.171875,
"learning_rate": 0.00047738589627502814,
"loss": 5.8196,
"mean_token_accuracy": 0.17014452815055847,
"num_tokens": 29843874.0,
"step": 15255
},
{
"entropy": 6.143678855895996,
"epoch": 1.5254161043634729,
"grad_norm": 1.6796875,
"learning_rate": 0.00047737029989602665,
"loss": 5.8578,
"mean_token_accuracy": 0.1587330222129822,
"num_tokens": 29853031.0,
"step": 15260
},
{
"entropy": 6.098814392089844,
"epoch": 1.5259159294247013,
"grad_norm": 1.328125,
"learning_rate": 0.0004773546984254405,
"loss": 5.9006,
"mean_token_accuracy": 0.1571081519126892,
"num_tokens": 29862437.0,
"step": 15265
},
{
"entropy": 6.051092958450317,
"epoch": 1.5264157544859298,
"grad_norm": 1.34375,
"learning_rate": 0.0004773390918636622,
"loss": 5.8133,
"mean_token_accuracy": 0.1645175188779831,
"num_tokens": 29870914.0,
"step": 15270
},
{
"entropy": 6.107993698120117,
"epoch": 1.5269155795471585,
"grad_norm": 1.515625,
"learning_rate": 0.0004773234802110844,
"loss": 5.8412,
"mean_token_accuracy": 0.16391278356313704,
"num_tokens": 29880745.0,
"step": 15275
},
{
"entropy": 6.195461988449097,
"epoch": 1.5274154046083872,
"grad_norm": 1.3515625,
"learning_rate": 0.0004773078634681,
"loss": 6.0267,
"mean_token_accuracy": 0.15176126584410668,
"num_tokens": 29890049.0,
"step": 15280
},
{
"entropy": 6.271877479553223,
"epoch": 1.5279152296696157,
"grad_norm": 1.234375,
"learning_rate": 0.00047729224163510167,
"loss": 6.0177,
"mean_token_accuracy": 0.15353228598833085,
"num_tokens": 29899664.0,
"step": 15285
},
{
"entropy": 6.16676082611084,
"epoch": 1.5284150547308442,
"grad_norm": 1.4140625,
"learning_rate": 0.00047727661471248263,
"loss": 5.8847,
"mean_token_accuracy": 0.16869666203856468,
"num_tokens": 29909261.0,
"step": 15290
},
{
"entropy": 6.118931674957276,
"epoch": 1.5289148797920729,
"grad_norm": 1.359375,
"learning_rate": 0.000477260982700636,
"loss": 5.7521,
"mean_token_accuracy": 0.16772303879261016,
"num_tokens": 29920137.0,
"step": 15295
},
{
"entropy": 6.131432580947876,
"epoch": 1.5294147048533013,
"grad_norm": 1.1796875,
"learning_rate": 0.0004772453455999552,
"loss": 5.9367,
"mean_token_accuracy": 0.15772649943828582,
"num_tokens": 29930708.0,
"step": 15300
},
{
"entropy": 6.138315057754516,
"epoch": 1.5299145299145298,
"grad_norm": 1.203125,
"learning_rate": 0.0004772297034108334,
"loss": 6.0102,
"mean_token_accuracy": 0.15555102229118348,
"num_tokens": 29940804.0,
"step": 15305
},
{
"entropy": 6.088601922988891,
"epoch": 1.5304143549757585,
"grad_norm": 1.296875,
"learning_rate": 0.00047721405613366434,
"loss": 5.8207,
"mean_token_accuracy": 0.16179277896881103,
"num_tokens": 29951609.0,
"step": 15310
},
{
"entropy": 6.227131271362305,
"epoch": 1.5309141800369872,
"grad_norm": 1.3359375,
"learning_rate": 0.00047719840376884173,
"loss": 5.9768,
"mean_token_accuracy": 0.16435107588768005,
"num_tokens": 29961764.0,
"step": 15315
},
{
"entropy": 6.128134107589721,
"epoch": 1.5314140050982155,
"grad_norm": 1.4765625,
"learning_rate": 0.0004771827463167593,
"loss": 5.8996,
"mean_token_accuracy": 0.1534770041704178,
"num_tokens": 29972160.0,
"step": 15320
},
{
"entropy": 6.084901809692383,
"epoch": 1.5319138301594442,
"grad_norm": 1.21875,
"learning_rate": 0.0004771670837778109,
"loss": 5.8095,
"mean_token_accuracy": 0.16341745853424072,
"num_tokens": 29982190.0,
"step": 15325
},
{
"entropy": 6.184044551849365,
"epoch": 1.5324136552206729,
"grad_norm": 1.4296875,
"learning_rate": 0.00047715141615239075,
"loss": 5.9234,
"mean_token_accuracy": 0.16050842702388762,
"num_tokens": 29992020.0,
"step": 15330
},
{
"entropy": 6.1740881443023685,
"epoch": 1.5329134802819013,
"grad_norm": 1.296875,
"learning_rate": 0.00047713574344089305,
"loss": 5.9493,
"mean_token_accuracy": 0.15685709416866303,
"num_tokens": 30002585.0,
"step": 15335
},
{
"entropy": 6.136387157440185,
"epoch": 1.5334133053431298,
"grad_norm": 1.234375,
"learning_rate": 0.000477120065643712,
"loss": 5.9106,
"mean_token_accuracy": 0.15703713297843933,
"num_tokens": 30012210.0,
"step": 15340
},
{
"entropy": 6.179438781738281,
"epoch": 1.5339131304043585,
"grad_norm": 1.3203125,
"learning_rate": 0.0004771043827612421,
"loss": 5.9805,
"mean_token_accuracy": 0.15978062599897386,
"num_tokens": 30022339.0,
"step": 15345
},
{
"entropy": 6.106447029113769,
"epoch": 1.5344129554655872,
"grad_norm": 1.328125,
"learning_rate": 0.00047708869479387795,
"loss": 5.8581,
"mean_token_accuracy": 0.16432844549417497,
"num_tokens": 30032313.0,
"step": 15350
},
{
"entropy": 6.11654314994812,
"epoch": 1.5349127805268155,
"grad_norm": 1.3515625,
"learning_rate": 0.0004770730017420143,
"loss": 5.8515,
"mean_token_accuracy": 0.16480098515748978,
"num_tokens": 30041840.0,
"step": 15355
},
{
"entropy": 6.078329801559448,
"epoch": 1.5354126055880442,
"grad_norm": 1.265625,
"learning_rate": 0.0004770573036060458,
"loss": 5.8162,
"mean_token_accuracy": 0.16789164394140244,
"num_tokens": 30052118.0,
"step": 15360
},
{
"entropy": 6.194440507888794,
"epoch": 1.5359124306492729,
"grad_norm": 1.2578125,
"learning_rate": 0.0004770416003863676,
"loss": 5.9919,
"mean_token_accuracy": 0.15537165254354476,
"num_tokens": 30062352.0,
"step": 15365
},
{
"entropy": 6.16536955833435,
"epoch": 1.5364122557105013,
"grad_norm": 1.3828125,
"learning_rate": 0.0004770258920833748,
"loss": 5.9621,
"mean_token_accuracy": 0.15180836692452432,
"num_tokens": 30072657.0,
"step": 15370
},
{
"entropy": 6.133648920059204,
"epoch": 1.5369120807717298,
"grad_norm": 1.4296875,
"learning_rate": 0.00047701017869746236,
"loss": 5.9192,
"mean_token_accuracy": 0.15897963792085648,
"num_tokens": 30082759.0,
"step": 15375
},
{
"entropy": 6.172386121749878,
"epoch": 1.5374119058329585,
"grad_norm": 1.1796875,
"learning_rate": 0.00047699446022902596,
"loss": 6.0099,
"mean_token_accuracy": 0.15272779539227485,
"num_tokens": 30092762.0,
"step": 15380
},
{
"entropy": 6.164754009246826,
"epoch": 1.537911730894187,
"grad_norm": 1.4375,
"learning_rate": 0.00047697873667846094,
"loss": 5.8878,
"mean_token_accuracy": 0.15395362675189972,
"num_tokens": 30101492.0,
"step": 15385
},
{
"entropy": 6.2284934520721436,
"epoch": 1.5384115559554155,
"grad_norm": 1.3515625,
"learning_rate": 0.00047696300804616276,
"loss": 5.9068,
"mean_token_accuracy": 0.1619730770587921,
"num_tokens": 30111136.0,
"step": 15390
},
{
"entropy": 6.153344678878784,
"epoch": 1.5389113810166442,
"grad_norm": 1.4765625,
"learning_rate": 0.0004769472743325273,
"loss": 5.9322,
"mean_token_accuracy": 0.16065984070301056,
"num_tokens": 30120804.0,
"step": 15395
},
{
"entropy": 6.20813512802124,
"epoch": 1.5394112060778729,
"grad_norm": 1.203125,
"learning_rate": 0.00047693153553795046,
"loss": 5.9483,
"mean_token_accuracy": 0.1560834527015686,
"num_tokens": 30130976.0,
"step": 15400
},
{
"entropy": 6.137753343582153,
"epoch": 1.5399110311391013,
"grad_norm": 1.28125,
"learning_rate": 0.0004769157916628281,
"loss": 5.8742,
"mean_token_accuracy": 0.1624482661485672,
"num_tokens": 30140060.0,
"step": 15405
},
{
"entropy": 6.1509441375732425,
"epoch": 1.5404108562003298,
"grad_norm": 1.2109375,
"learning_rate": 0.00047690004270755634,
"loss": 5.9368,
"mean_token_accuracy": 0.1568168044090271,
"num_tokens": 30150474.0,
"step": 15410
},
{
"entropy": 6.185036277770996,
"epoch": 1.5409106812615585,
"grad_norm": 1.1796875,
"learning_rate": 0.0004768842886725314,
"loss": 5.9424,
"mean_token_accuracy": 0.15672353953123092,
"num_tokens": 30159529.0,
"step": 15415
},
{
"entropy": 6.158765602111816,
"epoch": 1.541410506322787,
"grad_norm": 1.390625,
"learning_rate": 0.00047686852955814986,
"loss": 6.0631,
"mean_token_accuracy": 0.1555615782737732,
"num_tokens": 30169352.0,
"step": 15420
},
{
"entropy": 6.135985565185547,
"epoch": 1.5419103313840155,
"grad_norm": 1.2890625,
"learning_rate": 0.000476852765364808,
"loss": 5.8281,
"mean_token_accuracy": 0.16499021351337434,
"num_tokens": 30178190.0,
"step": 15425
},
{
"entropy": 6.070001888275146,
"epoch": 1.5424101564452442,
"grad_norm": 1.1640625,
"learning_rate": 0.0004768369960929025,
"loss": 5.8128,
"mean_token_accuracy": 0.16403407156467437,
"num_tokens": 30187878.0,
"step": 15430
},
{
"entropy": 6.108920955657959,
"epoch": 1.5429099815064728,
"grad_norm": 1.3046875,
"learning_rate": 0.0004768212217428301,
"loss": 5.9128,
"mean_token_accuracy": 0.15988751947879792,
"num_tokens": 30197786.0,
"step": 15435
},
{
"entropy": 6.189189434051514,
"epoch": 1.5434098065677013,
"grad_norm": 1.3203125,
"learning_rate": 0.00047680544231498766,
"loss": 5.9148,
"mean_token_accuracy": 0.16264031529426576,
"num_tokens": 30207837.0,
"step": 15440
},
{
"entropy": 6.080624198913574,
"epoch": 1.5439096316289298,
"grad_norm": 1.1875,
"learning_rate": 0.0004767896578097723,
"loss": 5.8654,
"mean_token_accuracy": 0.16577401608228684,
"num_tokens": 30217135.0,
"step": 15445
},
{
"entropy": 6.026799154281616,
"epoch": 1.5444094566901585,
"grad_norm": 1.2421875,
"learning_rate": 0.0004767738682275811,
"loss": 5.848,
"mean_token_accuracy": 0.1592901200056076,
"num_tokens": 30227339.0,
"step": 15450
},
{
"entropy": 6.217907476425171,
"epoch": 1.544909281751387,
"grad_norm": 1.3125,
"learning_rate": 0.0004767580735688112,
"loss": 6.0234,
"mean_token_accuracy": 0.15032312870025635,
"num_tokens": 30235735.0,
"step": 15455
},
{
"entropy": 6.148895120620727,
"epoch": 1.5454091068126155,
"grad_norm": 1.2578125,
"learning_rate": 0.0004767422738338601,
"loss": 5.8368,
"mean_token_accuracy": 0.16673685014247894,
"num_tokens": 30245921.0,
"step": 15460
},
{
"entropy": 6.0757598876953125,
"epoch": 1.5459089318738441,
"grad_norm": 1.3203125,
"learning_rate": 0.0004767264690231253,
"loss": 5.8337,
"mean_token_accuracy": 0.16876982003450394,
"num_tokens": 30256047.0,
"step": 15465
},
{
"entropy": 6.08550910949707,
"epoch": 1.5464087569350728,
"grad_norm": 1.2890625,
"learning_rate": 0.0004767106591370045,
"loss": 5.8694,
"mean_token_accuracy": 0.16294163167476655,
"num_tokens": 30266460.0,
"step": 15470
},
{
"entropy": 6.144644641876221,
"epoch": 1.5469085819963013,
"grad_norm": 1.5390625,
"learning_rate": 0.00047669484417589537,
"loss": 5.873,
"mean_token_accuracy": 0.16082055121660233,
"num_tokens": 30275937.0,
"step": 15475
},
{
"entropy": 6.184883975982666,
"epoch": 1.5474084070575298,
"grad_norm": 1.171875,
"learning_rate": 0.00047667902414019585,
"loss": 5.8217,
"mean_token_accuracy": 0.16800087243318557,
"num_tokens": 30285608.0,
"step": 15480
},
{
"entropy": 6.037270259857178,
"epoch": 1.5479082321187585,
"grad_norm": 1.2421875,
"learning_rate": 0.000476663199030304,
"loss": 5.853,
"mean_token_accuracy": 0.16526937931776048,
"num_tokens": 30295071.0,
"step": 15485
},
{
"entropy": 5.952275800704956,
"epoch": 1.548408057179987,
"grad_norm": 1.2265625,
"learning_rate": 0.00047664736884661804,
"loss": 5.8508,
"mean_token_accuracy": 0.16396021693944932,
"num_tokens": 30305878.0,
"step": 15490
},
{
"entropy": 6.212483263015747,
"epoch": 1.5489078822412155,
"grad_norm": 1.171875,
"learning_rate": 0.00047663153358953604,
"loss": 5.9522,
"mean_token_accuracy": 0.16168071031570436,
"num_tokens": 30316544.0,
"step": 15495
},
{
"entropy": 6.234240531921387,
"epoch": 1.5494077073024441,
"grad_norm": 1.2578125,
"learning_rate": 0.0004766156932594566,
"loss": 5.8539,
"mean_token_accuracy": 0.1589973583817482,
"num_tokens": 30325819.0,
"step": 15500
},
{
"entropy": 6.113700723648071,
"epoch": 1.5499075323636728,
"grad_norm": 1.171875,
"learning_rate": 0.00047659984785677824,
"loss": 5.8208,
"mean_token_accuracy": 0.16180218607187272,
"num_tokens": 30335160.0,
"step": 15505
},
{
"entropy": 6.088001012802124,
"epoch": 1.5504073574249013,
"grad_norm": 1.2421875,
"learning_rate": 0.00047658399738189955,
"loss": 5.9021,
"mean_token_accuracy": 0.1632031410932541,
"num_tokens": 30343412.0,
"step": 15510
},
{
"entropy": 6.024244260787964,
"epoch": 1.5509071824861298,
"grad_norm": 1.25,
"learning_rate": 0.00047656814183521937,
"loss": 5.8259,
"mean_token_accuracy": 0.16587333977222443,
"num_tokens": 30352336.0,
"step": 15515
},
{
"entropy": 6.163676357269287,
"epoch": 1.5514070075473585,
"grad_norm": 1.3046875,
"learning_rate": 0.0004765522812171366,
"loss": 5.8262,
"mean_token_accuracy": 0.1605166971683502,
"num_tokens": 30362476.0,
"step": 15520
},
{
"entropy": 6.151455879211426,
"epoch": 1.551906832608587,
"grad_norm": 1.2578125,
"learning_rate": 0.00047653641552805023,
"loss": 5.8935,
"mean_token_accuracy": 0.16111961305141448,
"num_tokens": 30372639.0,
"step": 15525
},
{
"entropy": 6.098763465881348,
"epoch": 1.5524066576698154,
"grad_norm": 1.2109375,
"learning_rate": 0.0004765205447683595,
"loss": 5.7604,
"mean_token_accuracy": 0.16646797209978104,
"num_tokens": 30382443.0,
"step": 15530
},
{
"entropy": 6.097776317596436,
"epoch": 1.5529064827310441,
"grad_norm": 1.3515625,
"learning_rate": 0.0004765046689384638,
"loss": 5.8165,
"mean_token_accuracy": 0.15879101008176805,
"num_tokens": 30390969.0,
"step": 15535
},
{
"entropy": 6.078667497634887,
"epoch": 1.5534063077922728,
"grad_norm": 1.2109375,
"learning_rate": 0.0004764887880387625,
"loss": 5.9042,
"mean_token_accuracy": 0.15626829117536545,
"num_tokens": 30401773.0,
"step": 15540
},
{
"entropy": 6.202826499938965,
"epoch": 1.5539061328535013,
"grad_norm": 1.125,
"learning_rate": 0.00047647290206965506,
"loss": 5.973,
"mean_token_accuracy": 0.15267098024487497,
"num_tokens": 30412393.0,
"step": 15545
},
{
"entropy": 6.16403603553772,
"epoch": 1.5544059579147298,
"grad_norm": 1.234375,
"learning_rate": 0.00047645701103154125,
"loss": 5.8849,
"mean_token_accuracy": 0.157875719666481,
"num_tokens": 30422274.0,
"step": 15550
},
{
"entropy": 6.173828411102295,
"epoch": 1.5549057829759585,
"grad_norm": 2.8125,
"learning_rate": 0.00047644111492482094,
"loss": 5.9209,
"mean_token_accuracy": 0.15894222855567933,
"num_tokens": 30432345.0,
"step": 15555
},
{
"entropy": 6.1405264377594,
"epoch": 1.555405608037187,
"grad_norm": 1.0390625,
"learning_rate": 0.000476425213749894,
"loss": 5.78,
"mean_token_accuracy": 0.16812246292829514,
"num_tokens": 30443016.0,
"step": 15560
},
{
"entropy": 6.041651058197021,
"epoch": 1.5559054330984154,
"grad_norm": 1.28125,
"learning_rate": 0.0004764093075071605,
"loss": 5.741,
"mean_token_accuracy": 0.16955182254314421,
"num_tokens": 30452392.0,
"step": 15565
},
{
"entropy": 6.04131064414978,
"epoch": 1.5564052581596441,
"grad_norm": 1.2890625,
"learning_rate": 0.0004763933961970206,
"loss": 5.8578,
"mean_token_accuracy": 0.16227657049894334,
"num_tokens": 30461178.0,
"step": 15570
},
{
"entropy": 6.1343790054321286,
"epoch": 1.5569050832208728,
"grad_norm": 1.203125,
"learning_rate": 0.0004763774798198748,
"loss": 5.8603,
"mean_token_accuracy": 0.16114207208156586,
"num_tokens": 30470616.0,
"step": 15575
},
{
"entropy": 6.142730283737182,
"epoch": 1.5574049082821013,
"grad_norm": 1.1328125,
"learning_rate": 0.0004763615583761234,
"loss": 5.8334,
"mean_token_accuracy": 0.1626288890838623,
"num_tokens": 30479393.0,
"step": 15580
},
{
"entropy": 6.148135185241699,
"epoch": 1.5579047333433298,
"grad_norm": 1.1484375,
"learning_rate": 0.0004763456318661669,
"loss": 5.8416,
"mean_token_accuracy": 0.16323017328977585,
"num_tokens": 30488927.0,
"step": 15585
},
{
"entropy": 6.054379034042358,
"epoch": 1.5584045584045585,
"grad_norm": 1.2890625,
"learning_rate": 0.0004763297002904062,
"loss": 5.9169,
"mean_token_accuracy": 0.15800921767950057,
"num_tokens": 30498973.0,
"step": 15590
},
{
"entropy": 6.112800741195679,
"epoch": 1.558904383465787,
"grad_norm": 1.34375,
"learning_rate": 0.00047631376364924195,
"loss": 5.8338,
"mean_token_accuracy": 0.16736518889665603,
"num_tokens": 30508643.0,
"step": 15595
},
{
"entropy": 6.055330610275268,
"epoch": 1.5594042085270154,
"grad_norm": 1.2578125,
"learning_rate": 0.0004762978219430753,
"loss": 5.7908,
"mean_token_accuracy": 0.16724276542663574,
"num_tokens": 30518321.0,
"step": 15600
},
{
"entropy": 6.119699239730835,
"epoch": 1.5599040335882441,
"grad_norm": 1.3125,
"learning_rate": 0.0004762818751723072,
"loss": 5.8016,
"mean_token_accuracy": 0.16162988543510437,
"num_tokens": 30528127.0,
"step": 15605
},
{
"entropy": 6.1009547233581545,
"epoch": 1.5604038586494728,
"grad_norm": 2.0625,
"learning_rate": 0.00047626592333733895,
"loss": 5.7484,
"mean_token_accuracy": 0.17222401052713393,
"num_tokens": 30538411.0,
"step": 15610
},
{
"entropy": 6.053055095672607,
"epoch": 1.560903683710701,
"grad_norm": 1.4296875,
"learning_rate": 0.0004762499664385719,
"loss": 5.8894,
"mean_token_accuracy": 0.1579878196120262,
"num_tokens": 30548118.0,
"step": 15615
},
{
"entropy": 6.124635314941406,
"epoch": 1.5614035087719298,
"grad_norm": 1.140625,
"learning_rate": 0.00047623400447640733,
"loss": 5.9133,
"mean_token_accuracy": 0.15761272609233856,
"num_tokens": 30557920.0,
"step": 15620
},
{
"entropy": 6.263584756851197,
"epoch": 1.5619033338331585,
"grad_norm": 1.2421875,
"learning_rate": 0.00047621803745124717,
"loss": 5.9315,
"mean_token_accuracy": 0.15884170085191726,
"num_tokens": 30567189.0,
"step": 15625
},
{
"entropy": 6.151346254348755,
"epoch": 1.562403158894387,
"grad_norm": 1.203125,
"learning_rate": 0.00047620206536349294,
"loss": 5.9317,
"mean_token_accuracy": 0.16056433767080308,
"num_tokens": 30578208.0,
"step": 15630
},
{
"entropy": 6.093531799316406,
"epoch": 1.5629029839556154,
"grad_norm": 1.28125,
"learning_rate": 0.00047618608821354636,
"loss": 5.8628,
"mean_token_accuracy": 0.15800632536411285,
"num_tokens": 30587845.0,
"step": 15635
},
{
"entropy": 6.148631000518799,
"epoch": 1.5634028090168441,
"grad_norm": 1.3515625,
"learning_rate": 0.0004761701060018097,
"loss": 5.9025,
"mean_token_accuracy": 0.1599184937775135,
"num_tokens": 30596601.0,
"step": 15640
},
{
"entropy": 6.20504412651062,
"epoch": 1.5639026340780728,
"grad_norm": 1.1640625,
"learning_rate": 0.000476154118728685,
"loss": 5.9598,
"mean_token_accuracy": 0.15227677077054977,
"num_tokens": 30606860.0,
"step": 15645
},
{
"entropy": 6.106543731689453,
"epoch": 1.564402459139301,
"grad_norm": 1.3515625,
"learning_rate": 0.00047613812639457425,
"loss": 5.8481,
"mean_token_accuracy": 0.16099748760461807,
"num_tokens": 30614980.0,
"step": 15650
},
{
"entropy": 6.078296041488647,
"epoch": 1.5649022842005298,
"grad_norm": 1.21875,
"learning_rate": 0.0004761221289998801,
"loss": 5.9434,
"mean_token_accuracy": 0.16075193881988525,
"num_tokens": 30625833.0,
"step": 15655
},
{
"entropy": 6.1446483612060545,
"epoch": 1.5654021092617585,
"grad_norm": 1.328125,
"learning_rate": 0.0004761061265450049,
"loss": 5.8947,
"mean_token_accuracy": 0.16505882367491723,
"num_tokens": 30636052.0,
"step": 15660
},
{
"entropy": 6.211981582641601,
"epoch": 1.565901934322987,
"grad_norm": 1.2890625,
"learning_rate": 0.00047609011903035136,
"loss": 5.9089,
"mean_token_accuracy": 0.1541065126657486,
"num_tokens": 30646421.0,
"step": 15665
},
{
"entropy": 6.129273843765259,
"epoch": 1.5664017593842154,
"grad_norm": 1.1953125,
"learning_rate": 0.00047607410645632216,
"loss": 5.9708,
"mean_token_accuracy": 0.1589779920876026,
"num_tokens": 30655903.0,
"step": 15670
},
{
"entropy": 6.048210716247558,
"epoch": 1.5669015844454441,
"grad_norm": 1.3046875,
"learning_rate": 0.00047605808882332013,
"loss": 5.7702,
"mean_token_accuracy": 0.16247298270463945,
"num_tokens": 30664963.0,
"step": 15675
},
{
"entropy": 6.169276094436645,
"epoch": 1.5674014095066726,
"grad_norm": 1.203125,
"learning_rate": 0.0004760420661317484,
"loss": 5.8704,
"mean_token_accuracy": 0.16183864176273347,
"num_tokens": 30675182.0,
"step": 15680
},
{
"entropy": 6.185893154144287,
"epoch": 1.567901234567901,
"grad_norm": 1.328125,
"learning_rate": 0.0004760260383820099,
"loss": 5.9885,
"mean_token_accuracy": 0.15695508122444152,
"num_tokens": 30685267.0,
"step": 15685
},
{
"entropy": 6.223132753372193,
"epoch": 1.5684010596291298,
"grad_norm": 1.296875,
"learning_rate": 0.00047601000557450816,
"loss": 5.9883,
"mean_token_accuracy": 0.15326895266771318,
"num_tokens": 30697462.0,
"step": 15690
},
{
"entropy": 6.1554662704467775,
"epoch": 1.5689008846903585,
"grad_norm": 1.265625,
"learning_rate": 0.0004759939677096463,
"loss": 5.8151,
"mean_token_accuracy": 0.16152628064155578,
"num_tokens": 30706754.0,
"step": 15695
},
{
"entropy": 6.048240995407104,
"epoch": 1.569400709751587,
"grad_norm": 1.3125,
"learning_rate": 0.0004759779247878279,
"loss": 5.9025,
"mean_token_accuracy": 0.15399678349494933,
"num_tokens": 30717136.0,
"step": 15700
},
{
"entropy": 6.086741828918457,
"epoch": 1.5699005348128154,
"grad_norm": 1.2890625,
"learning_rate": 0.00047596187680945675,
"loss": 5.803,
"mean_token_accuracy": 0.1613622322678566,
"num_tokens": 30725830.0,
"step": 15705
},
{
"entropy": 6.226022577285766,
"epoch": 1.5704003598740441,
"grad_norm": 1.46875,
"learning_rate": 0.0004759458237749364,
"loss": 5.9127,
"mean_token_accuracy": 0.16303760260343553,
"num_tokens": 30736494.0,
"step": 15710
},
{
"entropy": 6.220048999786377,
"epoch": 1.5709001849352726,
"grad_norm": 1.2421875,
"learning_rate": 0.0004759297656846708,
"loss": 5.9,
"mean_token_accuracy": 0.15465883985161782,
"num_tokens": 30746006.0,
"step": 15715
},
{
"entropy": 6.118537044525146,
"epoch": 1.571400009996501,
"grad_norm": 1.421875,
"learning_rate": 0.00047591370253906415,
"loss": 5.8604,
"mean_token_accuracy": 0.15504343062639236,
"num_tokens": 30754776.0,
"step": 15720
},
{
"entropy": 6.003805160522461,
"epoch": 1.5718998350577298,
"grad_norm": 1.3203125,
"learning_rate": 0.00047589763433852027,
"loss": 5.8477,
"mean_token_accuracy": 0.16667582839727402,
"num_tokens": 30764342.0,
"step": 15725
},
{
"entropy": 6.147149705886841,
"epoch": 1.5723996601189585,
"grad_norm": 1.1015625,
"learning_rate": 0.0004758815610834437,
"loss": 5.8582,
"mean_token_accuracy": 0.1581901341676712,
"num_tokens": 30773282.0,
"step": 15730
},
{
"entropy": 6.177919006347656,
"epoch": 1.572899485180187,
"grad_norm": 1.28125,
"learning_rate": 0.00047586548277423873,
"loss": 5.8269,
"mean_token_accuracy": 0.1640584349632263,
"num_tokens": 30783407.0,
"step": 15735
},
{
"entropy": 6.092030048370361,
"epoch": 1.5733993102414154,
"grad_norm": 1.2890625,
"learning_rate": 0.00047584939941130994,
"loss": 5.8534,
"mean_token_accuracy": 0.16158094704151155,
"num_tokens": 30793922.0,
"step": 15740
},
{
"entropy": 6.072525882720948,
"epoch": 1.5738991353026441,
"grad_norm": 1.2578125,
"learning_rate": 0.0004758333109950619,
"loss": 5.8144,
"mean_token_accuracy": 0.1618849106132984,
"num_tokens": 30802721.0,
"step": 15745
},
{
"entropy": 6.1073509693145756,
"epoch": 1.5743989603638726,
"grad_norm": 1.25,
"learning_rate": 0.00047581721752589943,
"loss": 5.9691,
"mean_token_accuracy": 0.15507132261991502,
"num_tokens": 30813229.0,
"step": 15750
},
{
"entropy": 6.1787354946136475,
"epoch": 1.574898785425101,
"grad_norm": 1.2578125,
"learning_rate": 0.0004758011190042274,
"loss": 5.9205,
"mean_token_accuracy": 0.1574215590953827,
"num_tokens": 30822989.0,
"step": 15755
},
{
"entropy": 6.143587398529053,
"epoch": 1.5753986104863298,
"grad_norm": 1.234375,
"learning_rate": 0.0004757850154304509,
"loss": 5.9364,
"mean_token_accuracy": 0.15265523567795752,
"num_tokens": 30832134.0,
"step": 15760
},
{
"entropy": 6.169547080993652,
"epoch": 1.5758984355475585,
"grad_norm": 1.15625,
"learning_rate": 0.0004757689068049752,
"loss": 5.9403,
"mean_token_accuracy": 0.16043658852577208,
"num_tokens": 30841528.0,
"step": 15765
},
{
"entropy": 6.081172370910645,
"epoch": 1.576398260608787,
"grad_norm": 1.53125,
"learning_rate": 0.00047575279312820533,
"loss": 5.8693,
"mean_token_accuracy": 0.15912111699581147,
"num_tokens": 30852166.0,
"step": 15770
},
{
"entropy": 6.171766042709351,
"epoch": 1.5768980856700154,
"grad_norm": 1.21875,
"learning_rate": 0.0004757366744005469,
"loss": 5.9244,
"mean_token_accuracy": 0.1573824778199196,
"num_tokens": 30862188.0,
"step": 15775
},
{
"entropy": 6.1935049533844,
"epoch": 1.5773979107312441,
"grad_norm": 1.21875,
"learning_rate": 0.00047572055062240537,
"loss": 5.9349,
"mean_token_accuracy": 0.15564235746860505,
"num_tokens": 30871057.0,
"step": 15780
},
{
"entropy": 6.16683783531189,
"epoch": 1.5778977357924726,
"grad_norm": 1.203125,
"learning_rate": 0.0004757044217941865,
"loss": 5.7699,
"mean_token_accuracy": 0.16504726111888884,
"num_tokens": 30880884.0,
"step": 15785
},
{
"entropy": 6.06003041267395,
"epoch": 1.578397560853701,
"grad_norm": 1.234375,
"learning_rate": 0.00047568828791629605,
"loss": 5.8574,
"mean_token_accuracy": 0.15600989162921905,
"num_tokens": 30891017.0,
"step": 15790
},
{
"entropy": 6.108499908447266,
"epoch": 1.5788973859149298,
"grad_norm": 1.140625,
"learning_rate": 0.0004756721489891398,
"loss": 5.8672,
"mean_token_accuracy": 0.1605653703212738,
"num_tokens": 30901008.0,
"step": 15795
},
{
"entropy": 6.17630786895752,
"epoch": 1.5793972109761585,
"grad_norm": 1.2890625,
"learning_rate": 0.0004756560050131239,
"loss": 5.9588,
"mean_token_accuracy": 0.15656841844320296,
"num_tokens": 30911266.0,
"step": 15800
},
{
"entropy": 6.103103733062744,
"epoch": 1.579897036037387,
"grad_norm": 1.2578125,
"learning_rate": 0.00047563985598865466,
"loss": 5.8463,
"mean_token_accuracy": 0.16243888288736344,
"num_tokens": 30921758.0,
"step": 15805
},
{
"entropy": 6.126082801818848,
"epoch": 1.5803968610986154,
"grad_norm": 1.3046875,
"learning_rate": 0.00047562370191613816,
"loss": 5.9081,
"mean_token_accuracy": 0.1579236790537834,
"num_tokens": 30931446.0,
"step": 15810
},
{
"entropy": 6.157434463500977,
"epoch": 1.5808966861598441,
"grad_norm": 1.203125,
"learning_rate": 0.0004756075427959811,
"loss": 6.0207,
"mean_token_accuracy": 0.15780184268951417,
"num_tokens": 30942651.0,
"step": 15815
},
{
"entropy": 6.074296760559082,
"epoch": 1.5813965112210726,
"grad_norm": 1.265625,
"learning_rate": 0.0004755913786285898,
"loss": 5.7637,
"mean_token_accuracy": 0.16211674511432647,
"num_tokens": 30952039.0,
"step": 15820
},
{
"entropy": 6.101223182678223,
"epoch": 1.581896336282301,
"grad_norm": 1.2734375,
"learning_rate": 0.00047557520941437093,
"loss": 5.8412,
"mean_token_accuracy": 0.1625264972448349,
"num_tokens": 30961834.0,
"step": 15825
},
{
"entropy": 6.15417103767395,
"epoch": 1.5823961613435298,
"grad_norm": 1.34375,
"learning_rate": 0.00047555903515373156,
"loss": 5.9197,
"mean_token_accuracy": 0.15694278180599214,
"num_tokens": 30972015.0,
"step": 15830
},
{
"entropy": 6.078415966033935,
"epoch": 1.5828959864047585,
"grad_norm": 1.25,
"learning_rate": 0.00047554285584707834,
"loss": 5.7942,
"mean_token_accuracy": 0.16642882525920868,
"num_tokens": 30982082.0,
"step": 15835
},
{
"entropy": 6.105426454544068,
"epoch": 1.583395811465987,
"grad_norm": 1.1953125,
"learning_rate": 0.0004755266714948186,
"loss": 5.796,
"mean_token_accuracy": 0.16809799373149872,
"num_tokens": 30991273.0,
"step": 15840
},
{
"entropy": 6.09671630859375,
"epoch": 1.5838956365272154,
"grad_norm": 1.21875,
"learning_rate": 0.0004755104820973593,
"loss": 5.835,
"mean_token_accuracy": 0.16358477622270584,
"num_tokens": 31001062.0,
"step": 15845
},
{
"entropy": 6.0429517269134525,
"epoch": 1.5843954615884441,
"grad_norm": 1.28125,
"learning_rate": 0.00047549428765510793,
"loss": 5.796,
"mean_token_accuracy": 0.16111780256032943,
"num_tokens": 31009905.0,
"step": 15850
},
{
"entropy": 6.0670185565948485,
"epoch": 1.5848952866496726,
"grad_norm": 1.171875,
"learning_rate": 0.00047547808816847186,
"loss": 5.9045,
"mean_token_accuracy": 0.15322913378477096,
"num_tokens": 31020517.0,
"step": 15855
},
{
"entropy": 6.170886516571045,
"epoch": 1.585395111710901,
"grad_norm": 1.109375,
"learning_rate": 0.0004754618836378587,
"loss": 5.8911,
"mean_token_accuracy": 0.1553575351834297,
"num_tokens": 31030789.0,
"step": 15860
},
{
"entropy": 6.155055236816406,
"epoch": 1.5858949367721298,
"grad_norm": 1.1796875,
"learning_rate": 0.0004754456740636761,
"loss": 5.8445,
"mean_token_accuracy": 0.17112063765525817,
"num_tokens": 31040459.0,
"step": 15865
},
{
"entropy": 6.093184232711792,
"epoch": 1.5863947618333585,
"grad_norm": 1.21875,
"learning_rate": 0.00047542945944633187,
"loss": 5.8616,
"mean_token_accuracy": 0.1651126265525818,
"num_tokens": 31050049.0,
"step": 15870
},
{
"entropy": 6.040435934066773,
"epoch": 1.5868945868945867,
"grad_norm": 1.3125,
"learning_rate": 0.00047541323978623405,
"loss": 5.8639,
"mean_token_accuracy": 0.16348167955875398,
"num_tokens": 31058678.0,
"step": 15875
},
{
"entropy": 6.128684711456299,
"epoch": 1.5873944119558154,
"grad_norm": 1.3515625,
"learning_rate": 0.00047539701508379073,
"loss": 5.9129,
"mean_token_accuracy": 0.15773721784353256,
"num_tokens": 31067878.0,
"step": 15880
},
{
"entropy": 6.1564939498901365,
"epoch": 1.5878942370170441,
"grad_norm": 1.171875,
"learning_rate": 0.0004753807853394101,
"loss": 5.8961,
"mean_token_accuracy": 0.15775365829467775,
"num_tokens": 31077632.0,
"step": 15885
},
{
"entropy": 6.138030004501343,
"epoch": 1.5883940620782726,
"grad_norm": 1.2421875,
"learning_rate": 0.00047536455055350034,
"loss": 5.9488,
"mean_token_accuracy": 0.15829872861504554,
"num_tokens": 31087576.0,
"step": 15890
},
{
"entropy": 6.062282609939575,
"epoch": 1.588893887139501,
"grad_norm": 1.1484375,
"learning_rate": 0.00047534831072647016,
"loss": 5.8406,
"mean_token_accuracy": 0.1625261053442955,
"num_tokens": 31097053.0,
"step": 15895
},
{
"entropy": 6.08411226272583,
"epoch": 1.5893937122007298,
"grad_norm": 1.25,
"learning_rate": 0.00047533206585872805,
"loss": 5.8588,
"mean_token_accuracy": 0.1598147064447403,
"num_tokens": 31106426.0,
"step": 15900
},
{
"entropy": 6.1566907405853275,
"epoch": 1.5898935372619585,
"grad_norm": 1.3984375,
"learning_rate": 0.0004753158159506827,
"loss": 5.841,
"mean_token_accuracy": 0.16317206919193267,
"num_tokens": 31115645.0,
"step": 15905
},
{
"entropy": 6.097361135482788,
"epoch": 1.5903933623231867,
"grad_norm": 1.234375,
"learning_rate": 0.0004752995610027429,
"loss": 5.8717,
"mean_token_accuracy": 0.1649112105369568,
"num_tokens": 31125275.0,
"step": 15910
},
{
"entropy": 6.083859014511108,
"epoch": 1.5908931873844154,
"grad_norm": 1.2109375,
"learning_rate": 0.00047528330101531777,
"loss": 5.8439,
"mean_token_accuracy": 0.1593996524810791,
"num_tokens": 31136444.0,
"step": 15915
},
{
"entropy": 6.06806526184082,
"epoch": 1.5913930124456441,
"grad_norm": 1.2890625,
"learning_rate": 0.00047526703598881623,
"loss": 5.8507,
"mean_token_accuracy": 0.16740842461585997,
"num_tokens": 31145489.0,
"step": 15920
},
{
"entropy": 6.189351177215576,
"epoch": 1.5918928375068726,
"grad_norm": 1.2421875,
"learning_rate": 0.0004752507659236476,
"loss": 5.9385,
"mean_token_accuracy": 0.15564728975296022,
"num_tokens": 31154239.0,
"step": 15925
},
{
"entropy": 6.137935066223145,
"epoch": 1.592392662568101,
"grad_norm": 1.203125,
"learning_rate": 0.0004752344908202213,
"loss": 5.8527,
"mean_token_accuracy": 0.16458972841501235,
"num_tokens": 31163401.0,
"step": 15930
},
{
"entropy": 6.052607440948487,
"epoch": 1.5928924876293298,
"grad_norm": 1.34375,
"learning_rate": 0.0004752182106789467,
"loss": 5.836,
"mean_token_accuracy": 0.16648358553647996,
"num_tokens": 31173567.0,
"step": 15935
},
{
"entropy": 6.1300661087036135,
"epoch": 1.5933923126905583,
"grad_norm": 1.1875,
"learning_rate": 0.00047520192550023344,
"loss": 5.8845,
"mean_token_accuracy": 0.16116737425327302,
"num_tokens": 31183654.0,
"step": 15940
},
{
"entropy": 6.1397350311279295,
"epoch": 1.5938921377517867,
"grad_norm": 1.1328125,
"learning_rate": 0.0004751856352844913,
"loss": 5.9,
"mean_token_accuracy": 0.16272855252027513,
"num_tokens": 31193814.0,
"step": 15945
},
{
"entropy": 6.131307697296142,
"epoch": 1.5943919628130154,
"grad_norm": 1.3046875,
"learning_rate": 0.00047516934003213,
"loss": 5.8681,
"mean_token_accuracy": 0.1593376249074936,
"num_tokens": 31203834.0,
"step": 15950
},
{
"entropy": 6.133946943283081,
"epoch": 1.5948917878742441,
"grad_norm": 1.3203125,
"learning_rate": 0.00047515303974355965,
"loss": 5.9983,
"mean_token_accuracy": 0.14716990143060685,
"num_tokens": 31214625.0,
"step": 15955
},
{
"entropy": 6.21510944366455,
"epoch": 1.5953916129354726,
"grad_norm": 1.46875,
"learning_rate": 0.00047513673441919036,
"loss": 5.9219,
"mean_token_accuracy": 0.16002627462148666,
"num_tokens": 31224125.0,
"step": 15960
},
{
"entropy": 6.148350191116333,
"epoch": 1.595891437996701,
"grad_norm": 1.28125,
"learning_rate": 0.0004751204240594323,
"loss": 5.9072,
"mean_token_accuracy": 0.16153207868337632,
"num_tokens": 31233869.0,
"step": 15965
},
{
"entropy": 6.195877027511597,
"epoch": 1.5963912630579298,
"grad_norm": 1.2265625,
"learning_rate": 0.0004751041086646959,
"loss": 6.0079,
"mean_token_accuracy": 0.15301622301340104,
"num_tokens": 31244652.0,
"step": 15970
},
{
"entropy": 6.205608224868774,
"epoch": 1.5968910881191583,
"grad_norm": 1.1640625,
"learning_rate": 0.0004750877882353915,
"loss": 5.9491,
"mean_token_accuracy": 0.16067053526639938,
"num_tokens": 31254754.0,
"step": 15975
},
{
"entropy": 6.168276071548462,
"epoch": 1.5973909131803867,
"grad_norm": 1.4296875,
"learning_rate": 0.00047507146277192997,
"loss": 5.963,
"mean_token_accuracy": 0.16296229660511016,
"num_tokens": 31263768.0,
"step": 15980
},
{
"entropy": 6.070095729827881,
"epoch": 1.5978907382416154,
"grad_norm": 1.1484375,
"learning_rate": 0.0004750551322747219,
"loss": 5.8897,
"mean_token_accuracy": 0.15907872021198272,
"num_tokens": 31273295.0,
"step": 15985
},
{
"entropy": 6.19075231552124,
"epoch": 1.5983905633028441,
"grad_norm": 1.203125,
"learning_rate": 0.0004750387967441781,
"loss": 5.9596,
"mean_token_accuracy": 0.1528765633702278,
"num_tokens": 31284996.0,
"step": 15990
},
{
"entropy": 6.20226035118103,
"epoch": 1.5988903883640726,
"grad_norm": 1.375,
"learning_rate": 0.00047502245618070976,
"loss": 5.8844,
"mean_token_accuracy": 0.15611421167850495,
"num_tokens": 31294496.0,
"step": 15995
},
{
"entropy": 6.091341161727906,
"epoch": 1.599390213425301,
"grad_norm": 1.1953125,
"learning_rate": 0.00047500611058472783,
"loss": 5.7908,
"mean_token_accuracy": 0.16094809025526047,
"num_tokens": 31303655.0,
"step": 16000
},
{
"entropy": 6.095734119415283,
"epoch": 1.5998900384865298,
"grad_norm": 1.234375,
"learning_rate": 0.00047498975995664356,
"loss": 5.8331,
"mean_token_accuracy": 0.16860375851392745,
"num_tokens": 31313058.0,
"step": 16005
},
{
"entropy": 6.084413719177246,
"epoch": 1.6003898635477583,
"grad_norm": 1.1640625,
"learning_rate": 0.0004749734042968685,
"loss": 5.8257,
"mean_token_accuracy": 0.16647930145263673,
"num_tokens": 31323214.0,
"step": 16010
},
{
"entropy": 6.179101800918579,
"epoch": 1.6008896886089867,
"grad_norm": 1.2578125,
"learning_rate": 0.000474957043605814,
"loss": 5.9745,
"mean_token_accuracy": 0.15763366222381592,
"num_tokens": 31333691.0,
"step": 16015
},
{
"entropy": 6.25221815109253,
"epoch": 1.6013895136702154,
"grad_norm": 1.2421875,
"learning_rate": 0.00047494067788389174,
"loss": 5.9245,
"mean_token_accuracy": 0.15439243465662003,
"num_tokens": 31342240.0,
"step": 16020
},
{
"entropy": 6.129102373123169,
"epoch": 1.6018893387314441,
"grad_norm": 1.34375,
"learning_rate": 0.00047492430713151347,
"loss": 5.825,
"mean_token_accuracy": 0.16748217195272447,
"num_tokens": 31351955.0,
"step": 16025
},
{
"entropy": 6.040925645828247,
"epoch": 1.6023891637926726,
"grad_norm": 1.234375,
"learning_rate": 0.0004749079313490911,
"loss": 5.8032,
"mean_token_accuracy": 0.16716589778661728,
"num_tokens": 31361583.0,
"step": 16030
},
{
"entropy": 6.088488483428955,
"epoch": 1.602888988853901,
"grad_norm": 1.3046875,
"learning_rate": 0.00047489155053703655,
"loss": 5.8741,
"mean_token_accuracy": 0.16249251663684844,
"num_tokens": 31371219.0,
"step": 16035
},
{
"entropy": 6.178510999679565,
"epoch": 1.6033888139151298,
"grad_norm": 1.328125,
"learning_rate": 0.0004748751646957621,
"loss": 5.883,
"mean_token_accuracy": 0.1556862361729145,
"num_tokens": 31381561.0,
"step": 16040
},
{
"entropy": 6.168209981918335,
"epoch": 1.6038886389763582,
"grad_norm": 1.1640625,
"learning_rate": 0.0004748587738256799,
"loss": 5.8484,
"mean_token_accuracy": 0.1638987123966217,
"num_tokens": 31391385.0,
"step": 16045
},
{
"entropy": 6.168503475189209,
"epoch": 1.6043884640375867,
"grad_norm": 1.09375,
"learning_rate": 0.0004748423779272024,
"loss": 5.8815,
"mean_token_accuracy": 0.1574132263660431,
"num_tokens": 31400817.0,
"step": 16050
},
{
"entropy": 6.146331691741944,
"epoch": 1.6048882890988154,
"grad_norm": 1.25,
"learning_rate": 0.00047482597700074204,
"loss": 5.9494,
"mean_token_accuracy": 0.15307085812091828,
"num_tokens": 31411460.0,
"step": 16055
},
{
"entropy": 6.0337268829345705,
"epoch": 1.6053881141600441,
"grad_norm": 1.2265625,
"learning_rate": 0.00047480957104671157,
"loss": 5.8128,
"mean_token_accuracy": 0.1718428060412407,
"num_tokens": 31420407.0,
"step": 16060
},
{
"entropy": 6.137241649627685,
"epoch": 1.6058879392212726,
"grad_norm": 1.3203125,
"learning_rate": 0.0004747931600655237,
"loss": 5.9577,
"mean_token_accuracy": 0.15480193942785264,
"num_tokens": 31430964.0,
"step": 16065
},
{
"entropy": 6.097628402709961,
"epoch": 1.606387764282501,
"grad_norm": 1.4609375,
"learning_rate": 0.00047477674405759136,
"loss": 5.7798,
"mean_token_accuracy": 0.1686554506421089,
"num_tokens": 31440143.0,
"step": 16070
},
{
"entropy": 6.0729447364807125,
"epoch": 1.6068875893437298,
"grad_norm": 1.234375,
"learning_rate": 0.0004747603230233275,
"loss": 5.8731,
"mean_token_accuracy": 0.1646135799586773,
"num_tokens": 31449615.0,
"step": 16075
},
{
"entropy": 6.146064043045044,
"epoch": 1.6073874144049582,
"grad_norm": 1.4140625,
"learning_rate": 0.0004747438969631453,
"loss": 5.9572,
"mean_token_accuracy": 0.14821103364229202,
"num_tokens": 31459238.0,
"step": 16080
},
{
"entropy": 6.139043998718262,
"epoch": 1.6078872394661867,
"grad_norm": 1.21875,
"learning_rate": 0.0004747274658774581,
"loss": 5.8567,
"mean_token_accuracy": 0.1695764794945717,
"num_tokens": 31468540.0,
"step": 16085
},
{
"entropy": 6.126196479797363,
"epoch": 1.6083870645274154,
"grad_norm": 1.1328125,
"learning_rate": 0.0004747110297666793,
"loss": 5.84,
"mean_token_accuracy": 0.16754427701234817,
"num_tokens": 31478999.0,
"step": 16090
},
{
"entropy": 6.078820896148682,
"epoch": 1.6088868895886441,
"grad_norm": 1.203125,
"learning_rate": 0.0004746945886312223,
"loss": 5.8786,
"mean_token_accuracy": 0.16174889951944352,
"num_tokens": 31490237.0,
"step": 16095
},
{
"entropy": 6.116386222839355,
"epoch": 1.6093867146498726,
"grad_norm": 1.3046875,
"learning_rate": 0.0004746781424715009,
"loss": 5.9263,
"mean_token_accuracy": 0.15998089611530303,
"num_tokens": 31500250.0,
"step": 16100
},
{
"entropy": 6.196410226821899,
"epoch": 1.609886539711101,
"grad_norm": 1.2265625,
"learning_rate": 0.00047466169128792873,
"loss": 5.9695,
"mean_token_accuracy": 0.1575181305408478,
"num_tokens": 31511559.0,
"step": 16105
},
{
"entropy": 6.218584299087524,
"epoch": 1.6103863647723298,
"grad_norm": 1.2421875,
"learning_rate": 0.0004746452350809198,
"loss": 5.9225,
"mean_token_accuracy": 0.15792882591485977,
"num_tokens": 31520189.0,
"step": 16110
},
{
"entropy": 6.028193855285645,
"epoch": 1.6108861898335582,
"grad_norm": 1.2421875,
"learning_rate": 0.00047462877385088815,
"loss": 5.7647,
"mean_token_accuracy": 0.16634624153375627,
"num_tokens": 31529361.0,
"step": 16115
},
{
"entropy": 6.022070646286011,
"epoch": 1.6113860148947867,
"grad_norm": 1.3359375,
"learning_rate": 0.00047461230759824794,
"loss": 5.92,
"mean_token_accuracy": 0.1547860860824585,
"num_tokens": 31539530.0,
"step": 16120
},
{
"entropy": 6.248088026046753,
"epoch": 1.6118858399560154,
"grad_norm": 1.2734375,
"learning_rate": 0.00047459583632341343,
"loss": 5.9867,
"mean_token_accuracy": 0.15121661722660065,
"num_tokens": 31549166.0,
"step": 16125
},
{
"entropy": 6.1368013381958,
"epoch": 1.6123856650172441,
"grad_norm": 1.359375,
"learning_rate": 0.00047457936002679905,
"loss": 5.8656,
"mean_token_accuracy": 0.16321052461862565,
"num_tokens": 31558643.0,
"step": 16130
},
{
"entropy": 6.143841314315796,
"epoch": 1.6128854900784724,
"grad_norm": 1.2890625,
"learning_rate": 0.00047456287870881924,
"loss": 5.8547,
"mean_token_accuracy": 0.16555679887533187,
"num_tokens": 31568752.0,
"step": 16135
},
{
"entropy": 6.145507764816284,
"epoch": 1.613385315139701,
"grad_norm": 1.15625,
"learning_rate": 0.0004745463923698888,
"loss": 5.9352,
"mean_token_accuracy": 0.15683097392320633,
"num_tokens": 31577894.0,
"step": 16140
},
{
"entropy": 6.069931840896606,
"epoch": 1.6138851402009298,
"grad_norm": 1.3515625,
"learning_rate": 0.0004745299010104226,
"loss": 5.8693,
"mean_token_accuracy": 0.16115620732307434,
"num_tokens": 31586348.0,
"step": 16145
},
{
"entropy": 6.1560405731201175,
"epoch": 1.6143849652621582,
"grad_norm": 1.3203125,
"learning_rate": 0.00047451340463083527,
"loss": 5.9046,
"mean_token_accuracy": 0.16242365390062333,
"num_tokens": 31596472.0,
"step": 16150
},
{
"entropy": 6.214483404159546,
"epoch": 1.6148847903233867,
"grad_norm": 1.1875,
"learning_rate": 0.00047449690323154206,
"loss": 5.8725,
"mean_token_accuracy": 0.16163890585303306,
"num_tokens": 31606342.0,
"step": 16155
},
{
"entropy": 6.145944595336914,
"epoch": 1.6153846153846154,
"grad_norm": 1.2890625,
"learning_rate": 0.00047448039681295814,
"loss": 5.9283,
"mean_token_accuracy": 0.15377518832683562,
"num_tokens": 31615548.0,
"step": 16160
},
{
"entropy": 6.060011482238769,
"epoch": 1.6158844404458441,
"grad_norm": 1.265625,
"learning_rate": 0.00047446388537549867,
"loss": 5.9148,
"mean_token_accuracy": 0.15456662774086,
"num_tokens": 31626290.0,
"step": 16165
},
{
"entropy": 6.147197103500366,
"epoch": 1.6163842655070724,
"grad_norm": 1.2890625,
"learning_rate": 0.0004744473689195793,
"loss": 5.8867,
"mean_token_accuracy": 0.1610730528831482,
"num_tokens": 31635620.0,
"step": 16170
},
{
"entropy": 6.148130989074707,
"epoch": 1.616884090568301,
"grad_norm": 1.2109375,
"learning_rate": 0.0004744308474456154,
"loss": 5.9225,
"mean_token_accuracy": 0.16163863986730576,
"num_tokens": 31647168.0,
"step": 16175
},
{
"entropy": 6.145283603668213,
"epoch": 1.6173839156295298,
"grad_norm": 1.4140625,
"learning_rate": 0.0004744143209540227,
"loss": 5.8004,
"mean_token_accuracy": 0.16176878809928893,
"num_tokens": 31656173.0,
"step": 16180
},
{
"entropy": 6.074552154541015,
"epoch": 1.6178837406907582,
"grad_norm": 1.21875,
"learning_rate": 0.0004743977894452169,
"loss": 5.8816,
"mean_token_accuracy": 0.15985965430736543,
"num_tokens": 31665224.0,
"step": 16185
},
{
"entropy": 6.0285186767578125,
"epoch": 1.6183835657519867,
"grad_norm": 1.3671875,
"learning_rate": 0.0004743812529196142,
"loss": 5.8347,
"mean_token_accuracy": 0.1609862968325615,
"num_tokens": 31674623.0,
"step": 16190
},
{
"entropy": 6.153869533538819,
"epoch": 1.6188833908132154,
"grad_norm": 1.15625,
"learning_rate": 0.0004743647113776304,
"loss": 5.8802,
"mean_token_accuracy": 0.16540788412094115,
"num_tokens": 31684565.0,
"step": 16195
},
{
"entropy": 6.143793249130249,
"epoch": 1.619383215874444,
"grad_norm": 1.40625,
"learning_rate": 0.00047434816481968175,
"loss": 5.9153,
"mean_token_accuracy": 0.1597794361412525,
"num_tokens": 31694885.0,
"step": 16200
},
{
"entropy": 6.162732028961182,
"epoch": 1.6198830409356724,
"grad_norm": 1.375,
"learning_rate": 0.00047433161324618456,
"loss": 5.9115,
"mean_token_accuracy": 0.15935486555099487,
"num_tokens": 31704077.0,
"step": 16205
},
{
"entropy": 6.241324710845947,
"epoch": 1.620382865996901,
"grad_norm": 1.359375,
"learning_rate": 0.0004743150566575553,
"loss": 5.9493,
"mean_token_accuracy": 0.15140072554349898,
"num_tokens": 31713773.0,
"step": 16210
},
{
"entropy": 6.164005899429322,
"epoch": 1.6208826910581298,
"grad_norm": 1.328125,
"learning_rate": 0.0004742984950542105,
"loss": 5.9592,
"mean_token_accuracy": 0.16007295548915862,
"num_tokens": 31724020.0,
"step": 16215
},
{
"entropy": 6.136595821380615,
"epoch": 1.6213825161193582,
"grad_norm": 1.2109375,
"learning_rate": 0.00047428192843656684,
"loss": 5.8983,
"mean_token_accuracy": 0.15775277614593505,
"num_tokens": 31733992.0,
"step": 16220
},
{
"entropy": 6.211799573898316,
"epoch": 1.6218823411805867,
"grad_norm": 1.515625,
"learning_rate": 0.00047426535680504105,
"loss": 5.9286,
"mean_token_accuracy": 0.15749860554933548,
"num_tokens": 31745153.0,
"step": 16225
},
{
"entropy": 6.176314926147461,
"epoch": 1.6223821662418154,
"grad_norm": 1.234375,
"learning_rate": 0.00047424878016005036,
"loss": 5.8505,
"mean_token_accuracy": 0.1599099263548851,
"num_tokens": 31755110.0,
"step": 16230
},
{
"entropy": 6.119541597366333,
"epoch": 1.622881991303044,
"grad_norm": 1.5234375,
"learning_rate": 0.0004742321985020115,
"loss": 5.8757,
"mean_token_accuracy": 0.1598087340593338,
"num_tokens": 31764219.0,
"step": 16235
},
{
"entropy": 6.0570111751556395,
"epoch": 1.6233818163642724,
"grad_norm": 1.2734375,
"learning_rate": 0.0004742156118313418,
"loss": 5.7731,
"mean_token_accuracy": 0.15940103381872178,
"num_tokens": 31773597.0,
"step": 16240
},
{
"entropy": 6.146574544906616,
"epoch": 1.623881641425501,
"grad_norm": 1.1875,
"learning_rate": 0.00047419902014845855,
"loss": 5.884,
"mean_token_accuracy": 0.15996838510036468,
"num_tokens": 31783302.0,
"step": 16245
},
{
"entropy": 6.081358146667481,
"epoch": 1.6243814664867298,
"grad_norm": 1.2265625,
"learning_rate": 0.0004741824234537793,
"loss": 5.9193,
"mean_token_accuracy": 0.1561587020754814,
"num_tokens": 31793127.0,
"step": 16250
},
{
"entropy": 6.108809566497802,
"epoch": 1.6248812915479582,
"grad_norm": 1.1796875,
"learning_rate": 0.00047416582174772143,
"loss": 5.8956,
"mean_token_accuracy": 0.1611502155661583,
"num_tokens": 31802756.0,
"step": 16255
},
{
"entropy": 6.164645338058472,
"epoch": 1.6253811166091867,
"grad_norm": 1.5234375,
"learning_rate": 0.00047414921503070276,
"loss": 5.9376,
"mean_token_accuracy": 0.15861285477876663,
"num_tokens": 31813390.0,
"step": 16260
},
{
"entropy": 6.150406217575073,
"epoch": 1.6258809416704154,
"grad_norm": 1.171875,
"learning_rate": 0.00047413260330314116,
"loss": 5.9144,
"mean_token_accuracy": 0.16733056157827378,
"num_tokens": 31823304.0,
"step": 16265
},
{
"entropy": 6.1531651496887205,
"epoch": 1.626380766731644,
"grad_norm": 1.265625,
"learning_rate": 0.0004741159865654544,
"loss": 5.8864,
"mean_token_accuracy": 0.16533361673355101,
"num_tokens": 31832878.0,
"step": 16270
},
{
"entropy": 6.140581941604614,
"epoch": 1.6268805917928724,
"grad_norm": 1.421875,
"learning_rate": 0.00047409936481806076,
"loss": 5.8978,
"mean_token_accuracy": 0.16217795461416246,
"num_tokens": 31841753.0,
"step": 16275
},
{
"entropy": 6.006665754318237,
"epoch": 1.627380416854101,
"grad_norm": 1.2578125,
"learning_rate": 0.0004740827380613782,
"loss": 5.727,
"mean_token_accuracy": 0.1673479810357094,
"num_tokens": 31851451.0,
"step": 16280
},
{
"entropy": 6.1131706714630125,
"epoch": 1.6278802419153298,
"grad_norm": 1.2421875,
"learning_rate": 0.00047406610629582526,
"loss": 5.8488,
"mean_token_accuracy": 0.16459959745407104,
"num_tokens": 31860885.0,
"step": 16285
},
{
"entropy": 6.07653431892395,
"epoch": 1.6283800669765582,
"grad_norm": 1.2265625,
"learning_rate": 0.00047404946952182034,
"loss": 5.806,
"mean_token_accuracy": 0.1725273311138153,
"num_tokens": 31870056.0,
"step": 16290
},
{
"entropy": 6.099943494796753,
"epoch": 1.6288798920377867,
"grad_norm": 1.1640625,
"learning_rate": 0.0004740328277397819,
"loss": 5.8739,
"mean_token_accuracy": 0.16686343550682067,
"num_tokens": 31879513.0,
"step": 16295
},
{
"entropy": 6.134911966323853,
"epoch": 1.6293797170990154,
"grad_norm": 1.109375,
"learning_rate": 0.0004740161809501288,
"loss": 5.8439,
"mean_token_accuracy": 0.16484363973140717,
"num_tokens": 31890288.0,
"step": 16300
},
{
"entropy": 6.157239961624145,
"epoch": 1.6298795421602439,
"grad_norm": 1.2734375,
"learning_rate": 0.00047399952915327975,
"loss": 5.8498,
"mean_token_accuracy": 0.15603400096297265,
"num_tokens": 31900168.0,
"step": 16305
},
{
"entropy": 6.126083183288574,
"epoch": 1.6303793672214724,
"grad_norm": 1.3515625,
"learning_rate": 0.0004739828723496538,
"loss": 5.8298,
"mean_token_accuracy": 0.15930139273405075,
"num_tokens": 31908788.0,
"step": 16310
},
{
"entropy": 6.072530746459961,
"epoch": 1.630879192282701,
"grad_norm": 1.2578125,
"learning_rate": 0.00047396621053967,
"loss": 5.843,
"mean_token_accuracy": 0.16678276360034944,
"num_tokens": 31916968.0,
"step": 16315
},
{
"entropy": 6.175118923187256,
"epoch": 1.6313790173439298,
"grad_norm": 1.203125,
"learning_rate": 0.00047394954372374743,
"loss": 5.9,
"mean_token_accuracy": 0.1551012173295021,
"num_tokens": 31927205.0,
"step": 16320
},
{
"entropy": 6.165901947021484,
"epoch": 1.6318788424051582,
"grad_norm": 1.390625,
"learning_rate": 0.00047393287190230566,
"loss": 5.8356,
"mean_token_accuracy": 0.1604092925786972,
"num_tokens": 31937001.0,
"step": 16325
},
{
"entropy": 6.110785913467407,
"epoch": 1.6323786674663867,
"grad_norm": 1.3046875,
"learning_rate": 0.0004739161950757639,
"loss": 5.8767,
"mean_token_accuracy": 0.15767664611339569,
"num_tokens": 31946915.0,
"step": 16330
},
{
"entropy": 6.145122861862182,
"epoch": 1.6328784925276154,
"grad_norm": 1.984375,
"learning_rate": 0.000473899513244542,
"loss": 5.8431,
"mean_token_accuracy": 0.1618260011076927,
"num_tokens": 31956615.0,
"step": 16335
},
{
"entropy": 6.118664646148682,
"epoch": 1.6333783175888439,
"grad_norm": 1.328125,
"learning_rate": 0.0004738828264090594,
"loss": 5.9207,
"mean_token_accuracy": 0.15699604600667955,
"num_tokens": 31967203.0,
"step": 16340
},
{
"entropy": 6.106103754043579,
"epoch": 1.6338781426500724,
"grad_norm": 1.25,
"learning_rate": 0.00047386613456973614,
"loss": 5.7884,
"mean_token_accuracy": 0.167632058262825,
"num_tokens": 31976736.0,
"step": 16345
},
{
"entropy": 6.065636396408081,
"epoch": 1.634377967711301,
"grad_norm": 1.2265625,
"learning_rate": 0.0004738494377269921,
"loss": 5.8112,
"mean_token_accuracy": 0.16667845398187636,
"num_tokens": 31987000.0,
"step": 16350
},
{
"entropy": 6.174714660644531,
"epoch": 1.6348777927725298,
"grad_norm": 1.3984375,
"learning_rate": 0.00047383273588124736,
"loss": 6.0091,
"mean_token_accuracy": 0.15545531809329988,
"num_tokens": 31996238.0,
"step": 16355
},
{
"entropy": 6.193500614166259,
"epoch": 1.6353776178337582,
"grad_norm": 1.3515625,
"learning_rate": 0.0004738160290329222,
"loss": 5.9092,
"mean_token_accuracy": 0.15937088429927826,
"num_tokens": 32005785.0,
"step": 16360
},
{
"entropy": 6.130488872528076,
"epoch": 1.6358774428949867,
"grad_norm": 1.296875,
"learning_rate": 0.00047379931718243684,
"loss": 5.9608,
"mean_token_accuracy": 0.1601053312420845,
"num_tokens": 32017140.0,
"step": 16365
},
{
"entropy": 6.065225601196289,
"epoch": 1.6363772679562154,
"grad_norm": 1.359375,
"learning_rate": 0.0004737826003302118,
"loss": 5.7485,
"mean_token_accuracy": 0.1746237576007843,
"num_tokens": 32026431.0,
"step": 16370
},
{
"entropy": 6.193103456497193,
"epoch": 1.6368770930174439,
"grad_norm": 1.2578125,
"learning_rate": 0.00047376587847666767,
"loss": 6.0052,
"mean_token_accuracy": 0.15909340977668762,
"num_tokens": 32036211.0,
"step": 16375
},
{
"entropy": 6.1763709545135494,
"epoch": 1.6373769180786724,
"grad_norm": 1.1875,
"learning_rate": 0.0004737491516222253,
"loss": 5.9123,
"mean_token_accuracy": 0.15526963174343109,
"num_tokens": 32047231.0,
"step": 16380
},
{
"entropy": 6.128999280929565,
"epoch": 1.637876743139901,
"grad_norm": 1.3125,
"learning_rate": 0.00047373241976730537,
"loss": 5.8866,
"mean_token_accuracy": 0.1579688683152199,
"num_tokens": 32057649.0,
"step": 16385
},
{
"entropy": 6.175368356704712,
"epoch": 1.6383765682011298,
"grad_norm": 1.3515625,
"learning_rate": 0.0004737156829123289,
"loss": 5.8511,
"mean_token_accuracy": 0.16340236961841584,
"num_tokens": 32066208.0,
"step": 16390
},
{
"entropy": 6.16707181930542,
"epoch": 1.638876393262358,
"grad_norm": 1.296875,
"learning_rate": 0.00047369894105771693,
"loss": 5.9053,
"mean_token_accuracy": 0.17434269040822983,
"num_tokens": 32076451.0,
"step": 16395
},
{
"entropy": 6.19351601600647,
"epoch": 1.6393762183235867,
"grad_norm": 1.3359375,
"learning_rate": 0.00047368219420389077,
"loss": 5.9459,
"mean_token_accuracy": 0.15300357192754746,
"num_tokens": 32085642.0,
"step": 16400
},
{
"entropy": 6.162382745742798,
"epoch": 1.6398760433848154,
"grad_norm": 1.2421875,
"learning_rate": 0.0004736654423512717,
"loss": 5.9166,
"mean_token_accuracy": 0.15671353936195373,
"num_tokens": 32094350.0,
"step": 16405
},
{
"entropy": 6.108351421356201,
"epoch": 1.6403758684460439,
"grad_norm": 1.1953125,
"learning_rate": 0.0004736486855002813,
"loss": 5.8847,
"mean_token_accuracy": 0.16184229105710984,
"num_tokens": 32104981.0,
"step": 16410
},
{
"entropy": 6.111570596694946,
"epoch": 1.6408756935072724,
"grad_norm": 1.2421875,
"learning_rate": 0.000473631923651341,
"loss": 5.8661,
"mean_token_accuracy": 0.16245781034231185,
"num_tokens": 32114198.0,
"step": 16415
},
{
"entropy": 6.144701957702637,
"epoch": 1.641375518568501,
"grad_norm": 1.2890625,
"learning_rate": 0.0004736151568048726,
"loss": 5.861,
"mean_token_accuracy": 0.16171735972166063,
"num_tokens": 32124622.0,
"step": 16420
},
{
"entropy": 6.130097484588623,
"epoch": 1.6418753436297298,
"grad_norm": 1.3671875,
"learning_rate": 0.000473598384961298,
"loss": 5.9076,
"mean_token_accuracy": 0.15210689455270768,
"num_tokens": 32134466.0,
"step": 16425
},
{
"entropy": 6.20010085105896,
"epoch": 1.642375168690958,
"grad_norm": 1.359375,
"learning_rate": 0.00047358160812103925,
"loss": 5.9369,
"mean_token_accuracy": 0.15536476522684098,
"num_tokens": 32144104.0,
"step": 16430
},
{
"entropy": 6.103492689132691,
"epoch": 1.6428749937521867,
"grad_norm": 1.296875,
"learning_rate": 0.0004735648262845182,
"loss": 5.8178,
"mean_token_accuracy": 0.16161573380231858,
"num_tokens": 32156432.0,
"step": 16435
},
{
"entropy": 6.173177719116211,
"epoch": 1.6433748188134154,
"grad_norm": 1.6328125,
"learning_rate": 0.00047354803945215727,
"loss": 5.9117,
"mean_token_accuracy": 0.16193071156740188,
"num_tokens": 32166853.0,
"step": 16440
},
{
"entropy": 6.119800758361817,
"epoch": 1.6438746438746439,
"grad_norm": 1.2578125,
"learning_rate": 0.00047353124762437865,
"loss": 5.784,
"mean_token_accuracy": 0.17476997822523116,
"num_tokens": 32175604.0,
"step": 16445
},
{
"entropy": 6.078823232650757,
"epoch": 1.6443744689358724,
"grad_norm": 1.5625,
"learning_rate": 0.0004735144508016051,
"loss": 5.8635,
"mean_token_accuracy": 0.16064816415309907,
"num_tokens": 32185878.0,
"step": 16450
},
{
"entropy": 6.157793188095093,
"epoch": 1.644874293997101,
"grad_norm": 1.28125,
"learning_rate": 0.0004734976489842589,
"loss": 5.9683,
"mean_token_accuracy": 0.15036503970623016,
"num_tokens": 32196061.0,
"step": 16455
},
{
"entropy": 6.153126049041748,
"epoch": 1.6453741190583295,
"grad_norm": 1.328125,
"learning_rate": 0.000473480842172763,
"loss": 5.8624,
"mean_token_accuracy": 0.16707222908735275,
"num_tokens": 32207470.0,
"step": 16460
},
{
"entropy": 6.203348827362061,
"epoch": 1.645873944119558,
"grad_norm": 1.4140625,
"learning_rate": 0.00047346403036754023,
"loss": 5.9734,
"mean_token_accuracy": 0.15738432258367538,
"num_tokens": 32216660.0,
"step": 16465
},
{
"entropy": 6.18003659248352,
"epoch": 1.6463737691807867,
"grad_norm": 1.2578125,
"learning_rate": 0.00047344721356901344,
"loss": 5.8517,
"mean_token_accuracy": 0.16395285129547119,
"num_tokens": 32226472.0,
"step": 16470
},
{
"entropy": 6.1828264713287355,
"epoch": 1.6468735942420154,
"grad_norm": 1.3046875,
"learning_rate": 0.0004734303917776059,
"loss": 5.9556,
"mean_token_accuracy": 0.15418880432844162,
"num_tokens": 32235841.0,
"step": 16475
},
{
"entropy": 6.0212301254272464,
"epoch": 1.6473734193032439,
"grad_norm": 1.2109375,
"learning_rate": 0.00047341356499374065,
"loss": 5.7304,
"mean_token_accuracy": 0.17145554572343827,
"num_tokens": 32245388.0,
"step": 16480
},
{
"entropy": 6.1301007747650145,
"epoch": 1.6478732443644724,
"grad_norm": 1.625,
"learning_rate": 0.0004733967332178412,
"loss": 5.9145,
"mean_token_accuracy": 0.16238226294517516,
"num_tokens": 32255089.0,
"step": 16485
},
{
"entropy": 6.080270481109619,
"epoch": 1.648373069425701,
"grad_norm": 1.171875,
"learning_rate": 0.0004733798964503311,
"loss": 5.7587,
"mean_token_accuracy": 0.16990573704242706,
"num_tokens": 32265196.0,
"step": 16490
},
{
"entropy": 6.046630907058716,
"epoch": 1.6488728944869295,
"grad_norm": 1.328125,
"learning_rate": 0.0004733630546916338,
"loss": 5.7531,
"mean_token_accuracy": 0.16512000411748887,
"num_tokens": 32276734.0,
"step": 16495
},
{
"entropy": 6.11317777633667,
"epoch": 1.649372719548158,
"grad_norm": 1.421875,
"learning_rate": 0.00047334620794217306,
"loss": 5.9064,
"mean_token_accuracy": 0.15816880017518997,
"num_tokens": 32286098.0,
"step": 16500
},
{
"entropy": 6.127501678466797,
"epoch": 1.6498725446093867,
"grad_norm": 1.1484375,
"learning_rate": 0.0004733293562023727,
"loss": 5.9403,
"mean_token_accuracy": 0.1565721280872822,
"num_tokens": 32295123.0,
"step": 16505
},
{
"entropy": 6.124748039245605,
"epoch": 1.6503723696706154,
"grad_norm": 1.6015625,
"learning_rate": 0.00047331249947265685,
"loss": 5.845,
"mean_token_accuracy": 0.1652669683098793,
"num_tokens": 32304016.0,
"step": 16510
},
{
"entropy": 6.107478523254395,
"epoch": 1.6508721947318439,
"grad_norm": 1.328125,
"learning_rate": 0.0004732956377534496,
"loss": 5.8196,
"mean_token_accuracy": 0.15800952166318893,
"num_tokens": 32313437.0,
"step": 16515
},
{
"entropy": 6.141150999069214,
"epoch": 1.6513720197930724,
"grad_norm": 1.359375,
"learning_rate": 0.000473278771045175,
"loss": 5.8973,
"mean_token_accuracy": 0.1629784122109413,
"num_tokens": 32322966.0,
"step": 16520
},
{
"entropy": 6.077485466003418,
"epoch": 1.651871844854301,
"grad_norm": 1.28125,
"learning_rate": 0.00047326189934825764,
"loss": 5.9097,
"mean_token_accuracy": 0.15579638332128526,
"num_tokens": 32333555.0,
"step": 16525
},
{
"entropy": 6.10307354927063,
"epoch": 1.6523716699155295,
"grad_norm": 1.2890625,
"learning_rate": 0.0004732450226631219,
"loss": 5.8092,
"mean_token_accuracy": 0.16455169171094894,
"num_tokens": 32343946.0,
"step": 16530
},
{
"entropy": 6.163082599639893,
"epoch": 1.652871494976758,
"grad_norm": 1.59375,
"learning_rate": 0.00047322814099019236,
"loss": 5.8632,
"mean_token_accuracy": 0.16236407831311225,
"num_tokens": 32353932.0,
"step": 16535
},
{
"entropy": 6.035224771499633,
"epoch": 1.6533713200379867,
"grad_norm": 1.3828125,
"learning_rate": 0.0004732112543298938,
"loss": 5.7755,
"mean_token_accuracy": 0.16848057508468628,
"num_tokens": 32363156.0,
"step": 16540
},
{
"entropy": 6.034097576141358,
"epoch": 1.6538711450992154,
"grad_norm": 1.3515625,
"learning_rate": 0.0004731943626826511,
"loss": 5.8133,
"mean_token_accuracy": 0.16707777976989746,
"num_tokens": 32371987.0,
"step": 16545
},
{
"entropy": 6.182418441772461,
"epoch": 1.6543709701604439,
"grad_norm": 1.390625,
"learning_rate": 0.00047317746604888923,
"loss": 5.8935,
"mean_token_accuracy": 0.15517692565917968,
"num_tokens": 32381391.0,
"step": 16550
},
{
"entropy": 6.1798159122467045,
"epoch": 1.6548707952216724,
"grad_norm": 1.4921875,
"learning_rate": 0.00047316056442903333,
"loss": 5.9185,
"mean_token_accuracy": 0.16136854588985444,
"num_tokens": 32390980.0,
"step": 16555
},
{
"entropy": 6.067631721496582,
"epoch": 1.655370620282901,
"grad_norm": 1.234375,
"learning_rate": 0.0004731436578235086,
"loss": 5.8164,
"mean_token_accuracy": 0.16624444723129272,
"num_tokens": 32399240.0,
"step": 16560
},
{
"entropy": 6.116207933425903,
"epoch": 1.6558704453441295,
"grad_norm": 1.21875,
"learning_rate": 0.00047312674623274046,
"loss": 5.8597,
"mean_token_accuracy": 0.1602943480014801,
"num_tokens": 32409793.0,
"step": 16565
},
{
"entropy": 6.194666862487793,
"epoch": 1.656370270405358,
"grad_norm": 1.3203125,
"learning_rate": 0.0004731098296571543,
"loss": 5.8586,
"mean_token_accuracy": 0.1631217524409294,
"num_tokens": 32420658.0,
"step": 16570
},
{
"entropy": 6.318262434005737,
"epoch": 1.6568700954665867,
"grad_norm": 1.234375,
"learning_rate": 0.00047309290809717584,
"loss": 6.0513,
"mean_token_accuracy": 0.15152612403035165,
"num_tokens": 32430044.0,
"step": 16575
},
{
"entropy": 6.099453020095825,
"epoch": 1.6573699205278154,
"grad_norm": 1.6796875,
"learning_rate": 0.00047307598155323083,
"loss": 5.8998,
"mean_token_accuracy": 0.16494379788637162,
"num_tokens": 32439913.0,
"step": 16580
},
{
"entropy": 6.084395694732666,
"epoch": 1.6578697455890439,
"grad_norm": 1.265625,
"learning_rate": 0.000473059050025745,
"loss": 5.8404,
"mean_token_accuracy": 0.1604056864976883,
"num_tokens": 32449125.0,
"step": 16585
},
{
"entropy": 6.10713758468628,
"epoch": 1.6583695706502724,
"grad_norm": 1.21875,
"learning_rate": 0.0004730421135151445,
"loss": 5.8632,
"mean_token_accuracy": 0.16448641568422318,
"num_tokens": 32458549.0,
"step": 16590
},
{
"entropy": 6.142619562149048,
"epoch": 1.658869395711501,
"grad_norm": 1.578125,
"learning_rate": 0.0004730251720218554,
"loss": 5.8393,
"mean_token_accuracy": 0.16367946565151215,
"num_tokens": 32468860.0,
"step": 16595
},
{
"entropy": 6.1834149837493895,
"epoch": 1.6593692207727295,
"grad_norm": 1.21875,
"learning_rate": 0.00047300822554630393,
"loss": 5.8339,
"mean_token_accuracy": 0.16432933509349823,
"num_tokens": 32479090.0,
"step": 16600
},
{
"entropy": 6.109146976470948,
"epoch": 1.659869045833958,
"grad_norm": 1.28125,
"learning_rate": 0.0004729912740889164,
"loss": 5.7733,
"mean_token_accuracy": 0.16865911483764648,
"num_tokens": 32488611.0,
"step": 16605
},
{
"entropy": 6.086883115768432,
"epoch": 1.6603688708951867,
"grad_norm": 1.25,
"learning_rate": 0.00047297431765011945,
"loss": 5.814,
"mean_token_accuracy": 0.16205232739448547,
"num_tokens": 32497821.0,
"step": 16610
},
{
"entropy": 6.013880825042724,
"epoch": 1.6608686959564154,
"grad_norm": 1.3671875,
"learning_rate": 0.00047295735623033953,
"loss": 5.8043,
"mean_token_accuracy": 0.17166174501180648,
"num_tokens": 32507324.0,
"step": 16615
},
{
"entropy": 6.066670036315918,
"epoch": 1.6613685210176439,
"grad_norm": 1.2578125,
"learning_rate": 0.0004729403898300035,
"loss": 5.7885,
"mean_token_accuracy": 0.17106807976961136,
"num_tokens": 32517498.0,
"step": 16620
},
{
"entropy": 6.088050174713135,
"epoch": 1.6618683460788723,
"grad_norm": 1.2109375,
"learning_rate": 0.00047292341844953813,
"loss": 5.8529,
"mean_token_accuracy": 0.16081804931163787,
"num_tokens": 32526527.0,
"step": 16625
},
{
"entropy": 6.113596391677857,
"epoch": 1.662368171140101,
"grad_norm": 2.265625,
"learning_rate": 0.0004729064420893706,
"loss": 5.8285,
"mean_token_accuracy": 0.16891932040452956,
"num_tokens": 32535017.0,
"step": 16630
},
{
"entropy": 5.991485214233398,
"epoch": 1.6628679962013295,
"grad_norm": 1.4140625,
"learning_rate": 0.0004728894607499278,
"loss": 5.7041,
"mean_token_accuracy": 0.1837837055325508,
"num_tokens": 32545687.0,
"step": 16635
},
{
"entropy": 6.100140953063965,
"epoch": 1.663367821262558,
"grad_norm": 1.28125,
"learning_rate": 0.0004728724744316371,
"loss": 5.8612,
"mean_token_accuracy": 0.15739219039678573,
"num_tokens": 32554876.0,
"step": 16640
},
{
"entropy": 6.177180624008178,
"epoch": 1.6638676463237867,
"grad_norm": 1.2265625,
"learning_rate": 0.00047285548313492594,
"loss": 5.948,
"mean_token_accuracy": 0.15829978436231612,
"num_tokens": 32565453.0,
"step": 16645
},
{
"entropy": 6.180706882476807,
"epoch": 1.6643674713850154,
"grad_norm": 1.296875,
"learning_rate": 0.0004728384868602217,
"loss": 5.8384,
"mean_token_accuracy": 0.16195722222328185,
"num_tokens": 32573882.0,
"step": 16650
},
{
"entropy": 6.189860057830811,
"epoch": 1.6648672964462436,
"grad_norm": 1.25,
"learning_rate": 0.000472821485607952,
"loss": 5.9748,
"mean_token_accuracy": 0.15073680728673935,
"num_tokens": 32583182.0,
"step": 16655
},
{
"entropy": 6.18095760345459,
"epoch": 1.6653671215074723,
"grad_norm": 1.3515625,
"learning_rate": 0.0004728044793785446,
"loss": 5.9228,
"mean_token_accuracy": 0.15684778541326522,
"num_tokens": 32593405.0,
"step": 16660
},
{
"entropy": 6.112678146362304,
"epoch": 1.665866946568701,
"grad_norm": 1.265625,
"learning_rate": 0.00047278746817242754,
"loss": 5.872,
"mean_token_accuracy": 0.1557893767952919,
"num_tokens": 32603451.0,
"step": 16665
},
{
"entropy": 6.163123989105225,
"epoch": 1.6663667716299295,
"grad_norm": 1.390625,
"learning_rate": 0.0004727704519900286,
"loss": 5.9932,
"mean_token_accuracy": 0.1594257779419422,
"num_tokens": 32614054.0,
"step": 16670
},
{
"entropy": 6.124230480194091,
"epoch": 1.666866596691158,
"grad_norm": 1.2578125,
"learning_rate": 0.000472753430831776,
"loss": 5.8322,
"mean_token_accuracy": 0.16533894389867781,
"num_tokens": 32623154.0,
"step": 16675
},
{
"entropy": 6.162586402893067,
"epoch": 1.6673664217523867,
"grad_norm": 1.2421875,
"learning_rate": 0.00047273640469809786,
"loss": 5.9991,
"mean_token_accuracy": 0.15644034147262573,
"num_tokens": 32633252.0,
"step": 16680
},
{
"entropy": 6.048516654968262,
"epoch": 1.6678662468136154,
"grad_norm": 1.2109375,
"learning_rate": 0.0004727193735894227,
"loss": 5.7968,
"mean_token_accuracy": 0.16567823737859727,
"num_tokens": 32643681.0,
"step": 16685
},
{
"entropy": 6.042785692214966,
"epoch": 1.6683660718748436,
"grad_norm": 1.421875,
"learning_rate": 0.00047270233750617907,
"loss": 5.7137,
"mean_token_accuracy": 0.17545314282178878,
"num_tokens": 32653094.0,
"step": 16690
},
{
"entropy": 6.086886024475097,
"epoch": 1.6688658969360723,
"grad_norm": 1.15625,
"learning_rate": 0.00047268529644879545,
"loss": 5.7412,
"mean_token_accuracy": 0.16168431490659713,
"num_tokens": 32663795.0,
"step": 16695
},
{
"entropy": 6.142530536651611,
"epoch": 1.669365721997301,
"grad_norm": 1.453125,
"learning_rate": 0.00047266825041770066,
"loss": 5.8382,
"mean_token_accuracy": 0.16479238569736482,
"num_tokens": 32673763.0,
"step": 16700
},
{
"entropy": 6.070951318740844,
"epoch": 1.6698655470585295,
"grad_norm": 1.453125,
"learning_rate": 0.0004726511994133235,
"loss": 5.8007,
"mean_token_accuracy": 0.16941775232553483,
"num_tokens": 32683436.0,
"step": 16705
},
{
"entropy": 6.112431144714355,
"epoch": 1.670365372119758,
"grad_norm": 1.21875,
"learning_rate": 0.00047263414343609307,
"loss": 5.774,
"mean_token_accuracy": 0.1645307183265686,
"num_tokens": 32692563.0,
"step": 16710
},
{
"entropy": 6.102208232879638,
"epoch": 1.6708651971809867,
"grad_norm": 1.3359375,
"learning_rate": 0.00047261708248643846,
"loss": 5.861,
"mean_token_accuracy": 0.1599726803600788,
"num_tokens": 32700973.0,
"step": 16715
},
{
"entropy": 6.050986337661743,
"epoch": 1.6713650222422152,
"grad_norm": 1.3515625,
"learning_rate": 0.0004726000165647888,
"loss": 5.8013,
"mean_token_accuracy": 0.1739999383687973,
"num_tokens": 32710299.0,
"step": 16720
},
{
"entropy": 6.157758140563965,
"epoch": 1.6718648473034436,
"grad_norm": 1.375,
"learning_rate": 0.0004725829456715737,
"loss": 5.9079,
"mean_token_accuracy": 0.1563047409057617,
"num_tokens": 32719421.0,
"step": 16725
},
{
"entropy": 6.127217483520508,
"epoch": 1.6723646723646723,
"grad_norm": 1.34375,
"learning_rate": 0.0004725658698072225,
"loss": 5.873,
"mean_token_accuracy": 0.16384452134370803,
"num_tokens": 32729052.0,
"step": 16730
},
{
"entropy": 6.01908049583435,
"epoch": 1.672864497425901,
"grad_norm": 1.375,
"learning_rate": 0.0004725487889721648,
"loss": 5.7503,
"mean_token_accuracy": 0.17131175249814987,
"num_tokens": 32738953.0,
"step": 16735
},
{
"entropy": 6.111048650741577,
"epoch": 1.6733643224871295,
"grad_norm": 1.296875,
"learning_rate": 0.0004725317031668304,
"loss": 5.8915,
"mean_token_accuracy": 0.16039555221796037,
"num_tokens": 32748728.0,
"step": 16740
},
{
"entropy": 6.138377523422241,
"epoch": 1.673864147548358,
"grad_norm": 1.1796875,
"learning_rate": 0.00047251461239164916,
"loss": 5.8508,
"mean_token_accuracy": 0.15747175067663194,
"num_tokens": 32758305.0,
"step": 16745
},
{
"entropy": 6.1284078598022464,
"epoch": 1.6743639726095867,
"grad_norm": 1.2421875,
"learning_rate": 0.0004724975166470512,
"loss": 5.8942,
"mean_token_accuracy": 0.16370432302355767,
"num_tokens": 32768398.0,
"step": 16750
},
{
"entropy": 6.089828729629517,
"epoch": 1.6748637976708152,
"grad_norm": 1.296875,
"learning_rate": 0.0004724804159334665,
"loss": 5.8553,
"mean_token_accuracy": 0.16417628079652785,
"num_tokens": 32778970.0,
"step": 16755
},
{
"entropy": 6.106259679794311,
"epoch": 1.6753636227320436,
"grad_norm": 1.6875,
"learning_rate": 0.0004724633102513253,
"loss": 5.7687,
"mean_token_accuracy": 0.16122331470251083,
"num_tokens": 32789815.0,
"step": 16760
},
{
"entropy": 6.133359098434449,
"epoch": 1.6758634477932723,
"grad_norm": 1.40625,
"learning_rate": 0.0004724461996010581,
"loss": 5.8858,
"mean_token_accuracy": 0.16086881905794143,
"num_tokens": 32799378.0,
"step": 16765
},
{
"entropy": 6.072362184524536,
"epoch": 1.676363272854501,
"grad_norm": 1.40625,
"learning_rate": 0.0004724290839830953,
"loss": 5.7782,
"mean_token_accuracy": 0.17221519201993943,
"num_tokens": 32809380.0,
"step": 16770
},
{
"entropy": 6.047758960723877,
"epoch": 1.6768630979157295,
"grad_norm": 1.2265625,
"learning_rate": 0.0004724119633978675,
"loss": 5.7789,
"mean_token_accuracy": 0.169873508810997,
"num_tokens": 32818645.0,
"step": 16775
},
{
"entropy": 6.0860795974731445,
"epoch": 1.677362922976958,
"grad_norm": 1.234375,
"learning_rate": 0.00047239483784580554,
"loss": 5.8306,
"mean_token_accuracy": 0.16674723625183105,
"num_tokens": 32827832.0,
"step": 16780
},
{
"entropy": 6.174402141571045,
"epoch": 1.6778627480381867,
"grad_norm": 1.28125,
"learning_rate": 0.0004723777073273403,
"loss": 5.9242,
"mean_token_accuracy": 0.15221443623304368,
"num_tokens": 32839312.0,
"step": 16785
},
{
"entropy": 6.08099331855774,
"epoch": 1.6783625730994152,
"grad_norm": 1.2421875,
"learning_rate": 0.0004723605718429026,
"loss": 5.8051,
"mean_token_accuracy": 0.16935500651597976,
"num_tokens": 32849065.0,
"step": 16790
},
{
"entropy": 6.119829845428467,
"epoch": 1.6788623981606436,
"grad_norm": 1.265625,
"learning_rate": 0.0004723434313929238,
"loss": 5.8112,
"mean_token_accuracy": 0.16109203770756722,
"num_tokens": 32858469.0,
"step": 16795
},
{
"entropy": 6.135422849655152,
"epoch": 1.6793622232218723,
"grad_norm": 1.1875,
"learning_rate": 0.00047232628597783507,
"loss": 5.9151,
"mean_token_accuracy": 0.15433017909526825,
"num_tokens": 32868700.0,
"step": 16800
},
{
"entropy": 6.1444700241088865,
"epoch": 1.679862048283101,
"grad_norm": 1.2578125,
"learning_rate": 0.00047230913559806773,
"loss": 5.8086,
"mean_token_accuracy": 0.16680509299039842,
"num_tokens": 32878403.0,
"step": 16805
},
{
"entropy": 6.147442960739136,
"epoch": 1.6803618733443295,
"grad_norm": 1.40625,
"learning_rate": 0.0004722919802540533,
"loss": 5.8986,
"mean_token_accuracy": 0.15698599070310593,
"num_tokens": 32888322.0,
"step": 16810
},
{
"entropy": 6.12728066444397,
"epoch": 1.680861698405558,
"grad_norm": 1.3046875,
"learning_rate": 0.0004722748199462234,
"loss": 5.8635,
"mean_token_accuracy": 0.159330415725708,
"num_tokens": 32897170.0,
"step": 16815
},
{
"entropy": 6.052549552917481,
"epoch": 1.6813615234667867,
"grad_norm": 1.2265625,
"learning_rate": 0.0004722576546750098,
"loss": 5.7042,
"mean_token_accuracy": 0.17216254025697708,
"num_tokens": 32906503.0,
"step": 16820
},
{
"entropy": 6.075279998779297,
"epoch": 1.6818613485280152,
"grad_norm": 1.2890625,
"learning_rate": 0.00047224048444084434,
"loss": 5.8336,
"mean_token_accuracy": 0.16550259590148925,
"num_tokens": 32915723.0,
"step": 16825
},
{
"entropy": 6.093961572647094,
"epoch": 1.6823611735892436,
"grad_norm": 1.203125,
"learning_rate": 0.00047222330924415906,
"loss": 5.9038,
"mean_token_accuracy": 0.16662451177835463,
"num_tokens": 32925589.0,
"step": 16830
},
{
"entropy": 6.1602335453033445,
"epoch": 1.6828609986504723,
"grad_norm": 1.2734375,
"learning_rate": 0.0004722061290853862,
"loss": 5.9084,
"mean_token_accuracy": 0.1639178767800331,
"num_tokens": 32935727.0,
"step": 16835
},
{
"entropy": 6.090109395980835,
"epoch": 1.683360823711701,
"grad_norm": 1.3359375,
"learning_rate": 0.00047218894396495765,
"loss": 5.8112,
"mean_token_accuracy": 0.16744061261415483,
"num_tokens": 32944257.0,
"step": 16840
},
{
"entropy": 6.109005117416382,
"epoch": 1.6838606487729295,
"grad_norm": 1.234375,
"learning_rate": 0.0004721717538833061,
"loss": 5.8888,
"mean_token_accuracy": 0.15798853188753129,
"num_tokens": 32954341.0,
"step": 16845
},
{
"entropy": 6.121562433242798,
"epoch": 1.684360473834158,
"grad_norm": 1.28125,
"learning_rate": 0.000472154558840864,
"loss": 5.8541,
"mean_token_accuracy": 0.16148653477430344,
"num_tokens": 32963997.0,
"step": 16850
},
{
"entropy": 6.036176681518555,
"epoch": 1.6848602988953867,
"grad_norm": 1.265625,
"learning_rate": 0.000472137358838064,
"loss": 5.8285,
"mean_token_accuracy": 0.16132424920797347,
"num_tokens": 32974301.0,
"step": 16855
},
{
"entropy": 6.174757575988769,
"epoch": 1.6853601239566152,
"grad_norm": 1.2734375,
"learning_rate": 0.0004721201538753387,
"loss": 5.8774,
"mean_token_accuracy": 0.15793148055672646,
"num_tokens": 32983535.0,
"step": 16860
},
{
"entropy": 6.117872428894043,
"epoch": 1.6858599490178436,
"grad_norm": 1.28125,
"learning_rate": 0.00047210294395312103,
"loss": 5.8647,
"mean_token_accuracy": 0.16725480556488037,
"num_tokens": 32993392.0,
"step": 16865
},
{
"entropy": 5.919343948364258,
"epoch": 1.6863597740790723,
"grad_norm": 1.234375,
"learning_rate": 0.000472085729071844,
"loss": 5.592,
"mean_token_accuracy": 0.18676192611455916,
"num_tokens": 33002103.0,
"step": 16870
},
{
"entropy": 6.057176160812378,
"epoch": 1.686859599140301,
"grad_norm": 1.2265625,
"learning_rate": 0.00047206850923194076,
"loss": 5.8691,
"mean_token_accuracy": 0.16298008114099502,
"num_tokens": 33011557.0,
"step": 16875
},
{
"entropy": 6.165191173553467,
"epoch": 1.6873594242015295,
"grad_norm": 1.3359375,
"learning_rate": 0.00047205128443384456,
"loss": 5.8753,
"mean_token_accuracy": 0.16192150712013245,
"num_tokens": 33021015.0,
"step": 16880
},
{
"entropy": 6.145686149597168,
"epoch": 1.687859249262758,
"grad_norm": 1.2578125,
"learning_rate": 0.0004720340546779887,
"loss": 5.8274,
"mean_token_accuracy": 0.16373817920684813,
"num_tokens": 33029719.0,
"step": 16885
},
{
"entropy": 6.161823558807373,
"epoch": 1.6883590743239867,
"grad_norm": 2.09375,
"learning_rate": 0.0004720168199648068,
"loss": 5.8898,
"mean_token_accuracy": 0.15919446796178818,
"num_tokens": 33039424.0,
"step": 16890
},
{
"entropy": 6.141677713394165,
"epoch": 1.6888588993852152,
"grad_norm": 1.3359375,
"learning_rate": 0.00047199958029473237,
"loss": 5.8612,
"mean_token_accuracy": 0.16170452684164047,
"num_tokens": 33050175.0,
"step": 16895
},
{
"entropy": 6.117555856704712,
"epoch": 1.6893587244464436,
"grad_norm": 1.1953125,
"learning_rate": 0.00047198233566819915,
"loss": 5.8715,
"mean_token_accuracy": 0.16236645728349686,
"num_tokens": 33061352.0,
"step": 16900
},
{
"entropy": 6.137941217422485,
"epoch": 1.6898585495076723,
"grad_norm": 1.2890625,
"learning_rate": 0.0004719650860856411,
"loss": 5.8369,
"mean_token_accuracy": 0.16249137073755265,
"num_tokens": 33069946.0,
"step": 16905
},
{
"entropy": 6.082652997970581,
"epoch": 1.690358374568901,
"grad_norm": 1.2734375,
"learning_rate": 0.00047194783154749217,
"loss": 5.8216,
"mean_token_accuracy": 0.16467711627483367,
"num_tokens": 33078478.0,
"step": 16910
},
{
"entropy": 6.099985027313233,
"epoch": 1.6908581996301293,
"grad_norm": 1.203125,
"learning_rate": 0.0004719305720541865,
"loss": 5.7986,
"mean_token_accuracy": 0.17374778538942337,
"num_tokens": 33088073.0,
"step": 16915
},
{
"entropy": 6.059681463241577,
"epoch": 1.691358024691358,
"grad_norm": 1.3125,
"learning_rate": 0.00047191330760615823,
"loss": 5.7897,
"mean_token_accuracy": 0.16655015647411348,
"num_tokens": 33097127.0,
"step": 16920
},
{
"entropy": 6.0413487434387205,
"epoch": 1.6918578497525867,
"grad_norm": 1.1875,
"learning_rate": 0.00047189603820384186,
"loss": 5.8092,
"mean_token_accuracy": 0.16877787411212922,
"num_tokens": 33107250.0,
"step": 16925
},
{
"entropy": 6.064757776260376,
"epoch": 1.6923576748138152,
"grad_norm": 1.28125,
"learning_rate": 0.00047187876384767187,
"loss": 5.815,
"mean_token_accuracy": 0.1657470151782036,
"num_tokens": 33117585.0,
"step": 16930
},
{
"entropy": 6.1313450813293455,
"epoch": 1.6928574998750436,
"grad_norm": 1.2265625,
"learning_rate": 0.00047186148453808274,
"loss": 5.8251,
"mean_token_accuracy": 0.16052726805210113,
"num_tokens": 33127077.0,
"step": 16935
},
{
"entropy": 6.121941375732422,
"epoch": 1.6933573249362723,
"grad_norm": 1.359375,
"learning_rate": 0.0004718442002755094,
"loss": 5.8585,
"mean_token_accuracy": 0.15812154561281205,
"num_tokens": 33136327.0,
"step": 16940
},
{
"entropy": 6.081155061721802,
"epoch": 1.693857149997501,
"grad_norm": 1.2265625,
"learning_rate": 0.0004718269110603866,
"loss": 5.7339,
"mean_token_accuracy": 0.1690545752644539,
"num_tokens": 33145528.0,
"step": 16945
},
{
"entropy": 6.0176373481750485,
"epoch": 1.6943569750587293,
"grad_norm": 1.265625,
"learning_rate": 0.00047180961689314937,
"loss": 5.8284,
"mean_token_accuracy": 0.17070186585187913,
"num_tokens": 33154651.0,
"step": 16950
},
{
"entropy": 6.047551774978638,
"epoch": 1.694856800119958,
"grad_norm": 1.171875,
"learning_rate": 0.0004717923177742329,
"loss": 5.8313,
"mean_token_accuracy": 0.16603592932224273,
"num_tokens": 33164602.0,
"step": 16955
},
{
"entropy": 6.192107629776001,
"epoch": 1.6953566251811867,
"grad_norm": 1.1796875,
"learning_rate": 0.00047177501370407223,
"loss": 5.937,
"mean_token_accuracy": 0.15762703120708466,
"num_tokens": 33173534.0,
"step": 16960
},
{
"entropy": 6.0753912925720215,
"epoch": 1.6958564502424152,
"grad_norm": 1.328125,
"learning_rate": 0.00047175770468310294,
"loss": 5.909,
"mean_token_accuracy": 0.16273582577705384,
"num_tokens": 33183528.0,
"step": 16965
},
{
"entropy": 6.213628101348877,
"epoch": 1.6963562753036436,
"grad_norm": 1.3671875,
"learning_rate": 0.00047174039071176037,
"loss": 5.9708,
"mean_token_accuracy": 0.14892186373472213,
"num_tokens": 33193762.0,
"step": 16970
},
{
"entropy": 6.129265022277832,
"epoch": 1.6968561003648723,
"grad_norm": 1.421875,
"learning_rate": 0.00047172307179048025,
"loss": 5.8195,
"mean_token_accuracy": 0.16547536998987197,
"num_tokens": 33203050.0,
"step": 16975
},
{
"entropy": 6.2035455226898195,
"epoch": 1.697355925426101,
"grad_norm": 1.28125,
"learning_rate": 0.0004717057479196982,
"loss": 5.9411,
"mean_token_accuracy": 0.1654243603348732,
"num_tokens": 33212975.0,
"step": 16980
},
{
"entropy": 6.145605564117432,
"epoch": 1.6978557504873293,
"grad_norm": 1.3046875,
"learning_rate": 0.0004716884190998502,
"loss": 5.883,
"mean_token_accuracy": 0.16100297421216964,
"num_tokens": 33222967.0,
"step": 16985
},
{
"entropy": 6.132839488983154,
"epoch": 1.698355575548558,
"grad_norm": 1.21875,
"learning_rate": 0.0004716710853313721,
"loss": 5.8576,
"mean_token_accuracy": 0.15872777104377747,
"num_tokens": 33233000.0,
"step": 16990
},
{
"entropy": 6.2149194240570065,
"epoch": 1.6988554006097867,
"grad_norm": 1.1640625,
"learning_rate": 0.00047165374661470023,
"loss": 5.9507,
"mean_token_accuracy": 0.15825337469577788,
"num_tokens": 33242429.0,
"step": 16995
},
{
"entropy": 6.135564470291138,
"epoch": 1.6993552256710152,
"grad_norm": 1.21875,
"learning_rate": 0.00047163640295027064,
"loss": 5.8569,
"mean_token_accuracy": 0.1600394919514656,
"num_tokens": 33252474.0,
"step": 17000
},
{
"entropy": 6.1082510471344,
"epoch": 1.6998550507322436,
"grad_norm": 1.2265625,
"learning_rate": 0.00047161905433851974,
"loss": 5.9147,
"mean_token_accuracy": 0.15451256185770035,
"num_tokens": 33261296.0,
"step": 17005
},
{
"entropy": 6.079780912399292,
"epoch": 1.7003548757934723,
"grad_norm": 1.1953125,
"learning_rate": 0.00047160170077988403,
"loss": 5.7617,
"mean_token_accuracy": 0.17053687274456025,
"num_tokens": 33271382.0,
"step": 17010
},
{
"entropy": 6.172500991821289,
"epoch": 1.7008547008547008,
"grad_norm": 1.265625,
"learning_rate": 0.0004715843422748001,
"loss": 5.9072,
"mean_token_accuracy": 0.1569389060139656,
"num_tokens": 33281512.0,
"step": 17015
},
{
"entropy": 6.165734052658081,
"epoch": 1.7013545259159293,
"grad_norm": 1.2734375,
"learning_rate": 0.00047156697882370474,
"loss": 5.8705,
"mean_token_accuracy": 0.1596240818500519,
"num_tokens": 33290974.0,
"step": 17020
},
{
"entropy": 6.131651496887207,
"epoch": 1.701854350977158,
"grad_norm": 1.171875,
"learning_rate": 0.0004715496104270348,
"loss": 5.9188,
"mean_token_accuracy": 0.15352497845888138,
"num_tokens": 33301576.0,
"step": 17025
},
{
"entropy": 6.056046438217163,
"epoch": 1.7023541760383867,
"grad_norm": 1.1953125,
"learning_rate": 0.0004715322370852272,
"loss": 5.7189,
"mean_token_accuracy": 0.17549443989992142,
"num_tokens": 33311277.0,
"step": 17030
},
{
"entropy": 6.042885684967041,
"epoch": 1.7028540010996152,
"grad_norm": 1.359375,
"learning_rate": 0.00047151485879871907,
"loss": 5.8076,
"mean_token_accuracy": 0.1702376827597618,
"num_tokens": 33322018.0,
"step": 17035
},
{
"entropy": 6.114020824432373,
"epoch": 1.7033538261608436,
"grad_norm": 1.1953125,
"learning_rate": 0.00047149747556794763,
"loss": 5.8814,
"mean_token_accuracy": 0.16093982458114625,
"num_tokens": 33331804.0,
"step": 17040
},
{
"entropy": 6.181418514251709,
"epoch": 1.7038536512220723,
"grad_norm": 1.3046875,
"learning_rate": 0.00047148008739335035,
"loss": 5.8834,
"mean_token_accuracy": 0.15723083913326263,
"num_tokens": 33342014.0,
"step": 17045
},
{
"entropy": 6.140880680084228,
"epoch": 1.7043534762833008,
"grad_norm": 1.234375,
"learning_rate": 0.0004714626942753646,
"loss": 5.8291,
"mean_token_accuracy": 0.1655607968568802,
"num_tokens": 33352086.0,
"step": 17050
},
{
"entropy": 6.136274671554565,
"epoch": 1.7048533013445293,
"grad_norm": 1.28125,
"learning_rate": 0.000471445296214428,
"loss": 5.8128,
"mean_token_accuracy": 0.17023831605911255,
"num_tokens": 33362067.0,
"step": 17055
},
{
"entropy": 6.094441556930542,
"epoch": 1.705353126405758,
"grad_norm": 1.09375,
"learning_rate": 0.00047142789321097834,
"loss": 5.8324,
"mean_token_accuracy": 0.16534274369478225,
"num_tokens": 33371803.0,
"step": 17060
},
{
"entropy": 6.163855123519897,
"epoch": 1.7058529514669867,
"grad_norm": 1.2578125,
"learning_rate": 0.0004714104852654534,
"loss": 5.8558,
"mean_token_accuracy": 0.16327501237392425,
"num_tokens": 33381258.0,
"step": 17065
},
{
"entropy": 6.136796236038208,
"epoch": 1.7063527765282152,
"grad_norm": 1.21875,
"learning_rate": 0.0004713930723782912,
"loss": 5.8642,
"mean_token_accuracy": 0.16078613847494125,
"num_tokens": 33390709.0,
"step": 17070
},
{
"entropy": 6.161985063552857,
"epoch": 1.7068526015894436,
"grad_norm": 1.28125,
"learning_rate": 0.00047137565454992983,
"loss": 5.8769,
"mean_token_accuracy": 0.16147163063287734,
"num_tokens": 33400831.0,
"step": 17075
},
{
"entropy": 6.119814395904541,
"epoch": 1.7073524266506723,
"grad_norm": 1.2578125,
"learning_rate": 0.00047135823178080745,
"loss": 5.8329,
"mean_token_accuracy": 0.1637144520878792,
"num_tokens": 33410974.0,
"step": 17080
},
{
"entropy": 6.188448238372803,
"epoch": 1.7078522517119008,
"grad_norm": 1.2109375,
"learning_rate": 0.0004713408040713626,
"loss": 5.9522,
"mean_token_accuracy": 0.15507494658231735,
"num_tokens": 33420555.0,
"step": 17085
},
{
"entropy": 6.145060443878174,
"epoch": 1.7083520767731293,
"grad_norm": 1.265625,
"learning_rate": 0.00047132337142203365,
"loss": 5.961,
"mean_token_accuracy": 0.15563779324293137,
"num_tokens": 33431064.0,
"step": 17090
},
{
"entropy": 6.130756139755249,
"epoch": 1.708851901834358,
"grad_norm": 1.40625,
"learning_rate": 0.0004713059338332591,
"loss": 5.8181,
"mean_token_accuracy": 0.16710542887449265,
"num_tokens": 33441223.0,
"step": 17095
},
{
"entropy": 6.143070459365845,
"epoch": 1.7093517268955867,
"grad_norm": 1.2734375,
"learning_rate": 0.00047128849130547774,
"loss": 5.8613,
"mean_token_accuracy": 0.1648654267191887,
"num_tokens": 33451520.0,
"step": 17100
},
{
"entropy": 6.07532811164856,
"epoch": 1.7098515519568152,
"grad_norm": 1.375,
"learning_rate": 0.00047127104383912856,
"loss": 5.7956,
"mean_token_accuracy": 0.16675146520137787,
"num_tokens": 33461310.0,
"step": 17105
},
{
"entropy": 6.168755340576172,
"epoch": 1.7103513770180436,
"grad_norm": 1.2421875,
"learning_rate": 0.0004712535914346504,
"loss": 5.9052,
"mean_token_accuracy": 0.16413626670837403,
"num_tokens": 33471250.0,
"step": 17110
},
{
"entropy": 6.093137121200561,
"epoch": 1.7108512020792723,
"grad_norm": 1.2734375,
"learning_rate": 0.00047123613409248233,
"loss": 5.7793,
"mean_token_accuracy": 0.16176048517227173,
"num_tokens": 33480950.0,
"step": 17115
},
{
"entropy": 6.0771674633026125,
"epoch": 1.7113510271405008,
"grad_norm": 1.234375,
"learning_rate": 0.00047121867181306365,
"loss": 5.7401,
"mean_token_accuracy": 0.16837601065635682,
"num_tokens": 33490394.0,
"step": 17120
},
{
"entropy": 6.03310546875,
"epoch": 1.7118508522017293,
"grad_norm": 1.28125,
"learning_rate": 0.0004712012045968337,
"loss": 5.8518,
"mean_token_accuracy": 0.15960967242717744,
"num_tokens": 33500130.0,
"step": 17125
},
{
"entropy": 6.122752285003662,
"epoch": 1.712350677262958,
"grad_norm": 1.59375,
"learning_rate": 0.00047118373244423197,
"loss": 5.9186,
"mean_token_accuracy": 0.1663791298866272,
"num_tokens": 33510698.0,
"step": 17130
},
{
"entropy": 6.13548903465271,
"epoch": 1.7128505023241867,
"grad_norm": 1.2265625,
"learning_rate": 0.00047116625535569787,
"loss": 5.8228,
"mean_token_accuracy": 0.16140831857919694,
"num_tokens": 33520161.0,
"step": 17135
},
{
"entropy": 6.0874275207519535,
"epoch": 1.7133503273854152,
"grad_norm": 1.25,
"learning_rate": 0.00047114877333167133,
"loss": 5.8708,
"mean_token_accuracy": 0.16802819073200226,
"num_tokens": 33530190.0,
"step": 17140
},
{
"entropy": 6.1481077671051025,
"epoch": 1.7138501524466436,
"grad_norm": 1.4453125,
"learning_rate": 0.00047113128637259216,
"loss": 5.8432,
"mean_token_accuracy": 0.1689216434955597,
"num_tokens": 33539376.0,
"step": 17145
},
{
"entropy": 6.160684633255005,
"epoch": 1.7143499775078723,
"grad_norm": 1.3828125,
"learning_rate": 0.0004711137944789003,
"loss": 5.8371,
"mean_token_accuracy": 0.16129862517118454,
"num_tokens": 33549290.0,
"step": 17150
},
{
"entropy": 6.116025495529175,
"epoch": 1.7148498025691008,
"grad_norm": 1.140625,
"learning_rate": 0.00047109629765103577,
"loss": 5.9134,
"mean_token_accuracy": 0.15745049417018891,
"num_tokens": 33559483.0,
"step": 17155
},
{
"entropy": 6.128926372528076,
"epoch": 1.7153496276303293,
"grad_norm": 1.34375,
"learning_rate": 0.00047107879588943887,
"loss": 5.8878,
"mean_token_accuracy": 0.16217012107372283,
"num_tokens": 33569464.0,
"step": 17160
},
{
"entropy": 6.2021440982818605,
"epoch": 1.715849452691558,
"grad_norm": 1.234375,
"learning_rate": 0.00047106128919455,
"loss": 5.9805,
"mean_token_accuracy": 0.1558922439813614,
"num_tokens": 33579759.0,
"step": 17165
},
{
"entropy": 6.134302759170533,
"epoch": 1.7163492777527867,
"grad_norm": 1.2734375,
"learning_rate": 0.0004710437775668094,
"loss": 5.817,
"mean_token_accuracy": 0.16416923701763153,
"num_tokens": 33590054.0,
"step": 17170
},
{
"entropy": 6.088890266418457,
"epoch": 1.7168491028140151,
"grad_norm": 1.25,
"learning_rate": 0.0004710262610066579,
"loss": 5.8138,
"mean_token_accuracy": 0.16810918152332305,
"num_tokens": 33600014.0,
"step": 17175
},
{
"entropy": 6.166955947875977,
"epoch": 1.7173489278752436,
"grad_norm": 1.2578125,
"learning_rate": 0.00047100873951453617,
"loss": 5.8297,
"mean_token_accuracy": 0.16101797074079513,
"num_tokens": 33609579.0,
"step": 17180
},
{
"entropy": 6.159162187576294,
"epoch": 1.7178487529364723,
"grad_norm": 1.25,
"learning_rate": 0.00047099121309088487,
"loss": 5.8983,
"mean_token_accuracy": 0.15850197076797484,
"num_tokens": 33618082.0,
"step": 17185
},
{
"entropy": 6.064070224761963,
"epoch": 1.7183485779977008,
"grad_norm": 1.6328125,
"learning_rate": 0.00047097368173614515,
"loss": 5.8657,
"mean_token_accuracy": 0.16142818331718445,
"num_tokens": 33627835.0,
"step": 17190
},
{
"entropy": 6.100105476379395,
"epoch": 1.7188484030589293,
"grad_norm": 1.265625,
"learning_rate": 0.00047095614545075807,
"loss": 5.8664,
"mean_token_accuracy": 0.1596950702369213,
"num_tokens": 33638187.0,
"step": 17195
},
{
"entropy": 6.195778179168701,
"epoch": 1.719348228120158,
"grad_norm": 1.3046875,
"learning_rate": 0.0004709386042351647,
"loss": 5.8594,
"mean_token_accuracy": 0.15646356642246245,
"num_tokens": 33647805.0,
"step": 17200
},
{
"entropy": 6.154709768295288,
"epoch": 1.7198480531813867,
"grad_norm": 1.3359375,
"learning_rate": 0.0004709210580898065,
"loss": 5.8642,
"mean_token_accuracy": 0.16096559017896653,
"num_tokens": 33656657.0,
"step": 17205
},
{
"entropy": 6.091437816619873,
"epoch": 1.720347878242615,
"grad_norm": 1.2734375,
"learning_rate": 0.0004709035070151249,
"loss": 5.8149,
"mean_token_accuracy": 0.16366640329360962,
"num_tokens": 33666025.0,
"step": 17210
},
{
"entropy": 6.074840974807739,
"epoch": 1.7208477033038436,
"grad_norm": 1.1484375,
"learning_rate": 0.0004708859510115614,
"loss": 5.7601,
"mean_token_accuracy": 0.16853323727846145,
"num_tokens": 33676378.0,
"step": 17215
},
{
"entropy": 6.252654695510865,
"epoch": 1.7213475283650723,
"grad_norm": 1.40625,
"learning_rate": 0.0004708683900795579,
"loss": 5.9689,
"mean_token_accuracy": 0.15362064391374589,
"num_tokens": 33685899.0,
"step": 17220
},
{
"entropy": 6.159629917144775,
"epoch": 1.7218473534263008,
"grad_norm": 1.3671875,
"learning_rate": 0.00047085082421955603,
"loss": 5.8592,
"mean_token_accuracy": 0.16372107863426208,
"num_tokens": 33696155.0,
"step": 17225
},
{
"entropy": 6.165194272994995,
"epoch": 1.7223471784875293,
"grad_norm": 1.1796875,
"learning_rate": 0.00047083325343199786,
"loss": 5.8627,
"mean_token_accuracy": 0.16175238341093062,
"num_tokens": 33704685.0,
"step": 17230
},
{
"entropy": 6.229802894592285,
"epoch": 1.722847003548758,
"grad_norm": 1.375,
"learning_rate": 0.0004708156777173254,
"loss": 5.9696,
"mean_token_accuracy": 0.15388983786106109,
"num_tokens": 33715189.0,
"step": 17235
},
{
"entropy": 6.135674381256104,
"epoch": 1.7233468286099867,
"grad_norm": 1.296875,
"learning_rate": 0.0004707980970759809,
"loss": 5.8647,
"mean_token_accuracy": 0.16149176359176637,
"num_tokens": 33724619.0,
"step": 17240
},
{
"entropy": 6.1062451839447025,
"epoch": 1.723846653671215,
"grad_norm": 1.4140625,
"learning_rate": 0.00047078051150840666,
"loss": 5.8523,
"mean_token_accuracy": 0.1665616363286972,
"num_tokens": 33734371.0,
"step": 17245
},
{
"entropy": 6.038412284851074,
"epoch": 1.7243464787324436,
"grad_norm": 1.2890625,
"learning_rate": 0.0004707629210150451,
"loss": 5.7953,
"mean_token_accuracy": 0.1671959176659584,
"num_tokens": 33743592.0,
"step": 17250
},
{
"entropy": 6.1577225685119625,
"epoch": 1.7248463037936723,
"grad_norm": 1.7890625,
"learning_rate": 0.0004707453255963388,
"loss": 5.8399,
"mean_token_accuracy": 0.1666915476322174,
"num_tokens": 33753686.0,
"step": 17255
},
{
"entropy": 6.1662595748901365,
"epoch": 1.7253461288549008,
"grad_norm": 1.390625,
"learning_rate": 0.00047072772525273053,
"loss": 5.912,
"mean_token_accuracy": 0.16065869629383087,
"num_tokens": 33763076.0,
"step": 17260
},
{
"entropy": 6.032483291625977,
"epoch": 1.7258459539161293,
"grad_norm": 1.40625,
"learning_rate": 0.00047071011998466304,
"loss": 5.6985,
"mean_token_accuracy": 0.1735437273979187,
"num_tokens": 33772283.0,
"step": 17265
},
{
"entropy": 6.096075439453125,
"epoch": 1.726345778977358,
"grad_norm": 1.4609375,
"learning_rate": 0.00047069250979257934,
"loss": 5.7943,
"mean_token_accuracy": 0.16639554053544997,
"num_tokens": 33782208.0,
"step": 17270
},
{
"entropy": 6.039402055740356,
"epoch": 1.7268456040385864,
"grad_norm": 1.4765625,
"learning_rate": 0.00047067489467692236,
"loss": 5.7735,
"mean_token_accuracy": 0.17472267523407936,
"num_tokens": 33792048.0,
"step": 17275
},
{
"entropy": 6.017827701568604,
"epoch": 1.727345429099815,
"grad_norm": 1.515625,
"learning_rate": 0.0004706572746381354,
"loss": 5.8265,
"mean_token_accuracy": 0.1701744467020035,
"num_tokens": 33800903.0,
"step": 17280
},
{
"entropy": 6.10653657913208,
"epoch": 1.7278452541610436,
"grad_norm": 1.3359375,
"learning_rate": 0.00047063964967666177,
"loss": 5.8701,
"mean_token_accuracy": 0.1601317122578621,
"num_tokens": 33810575.0,
"step": 17285
},
{
"entropy": 6.050252437591553,
"epoch": 1.7283450792222723,
"grad_norm": 1.515625,
"learning_rate": 0.0004706220197929449,
"loss": 5.7935,
"mean_token_accuracy": 0.16602483093738557,
"num_tokens": 33819365.0,
"step": 17290
},
{
"entropy": 6.167187690734863,
"epoch": 1.7288449042835008,
"grad_norm": 1.328125,
"learning_rate": 0.0004706043849874284,
"loss": 5.9259,
"mean_token_accuracy": 0.1592279002070427,
"num_tokens": 33828941.0,
"step": 17295
},
{
"entropy": 6.104386949539185,
"epoch": 1.7293447293447293,
"grad_norm": 1.53125,
"learning_rate": 0.00047058674526055585,
"loss": 5.8333,
"mean_token_accuracy": 0.16255820840597152,
"num_tokens": 33838700.0,
"step": 17300
},
{
"entropy": 6.183803081512451,
"epoch": 1.729844554405958,
"grad_norm": 1.125,
"learning_rate": 0.00047056910061277115,
"loss": 5.8674,
"mean_token_accuracy": 0.1564794175326824,
"num_tokens": 33848592.0,
"step": 17305
},
{
"entropy": 6.124628639221191,
"epoch": 1.7303443794671864,
"grad_norm": 1.421875,
"learning_rate": 0.0004705514510445182,
"loss": 5.8451,
"mean_token_accuracy": 0.16737015545368195,
"num_tokens": 33858037.0,
"step": 17310
},
{
"entropy": 6.119843816757202,
"epoch": 1.730844204528415,
"grad_norm": 1.3671875,
"learning_rate": 0.000470533796556241,
"loss": 5.9123,
"mean_token_accuracy": 0.1630480632185936,
"num_tokens": 33867284.0,
"step": 17315
},
{
"entropy": 6.113216209411621,
"epoch": 1.7313440295896436,
"grad_norm": 1.3984375,
"learning_rate": 0.0004705161371483839,
"loss": 5.7946,
"mean_token_accuracy": 0.16674706041812898,
"num_tokens": 33876006.0,
"step": 17320
},
{
"entropy": 6.061402988433838,
"epoch": 1.7318438546508723,
"grad_norm": 1.2265625,
"learning_rate": 0.00047049847282139095,
"loss": 5.6878,
"mean_token_accuracy": 0.17149617969989778,
"num_tokens": 33885273.0,
"step": 17325
},
{
"entropy": 6.191039419174194,
"epoch": 1.7323436797121008,
"grad_norm": 1.34375,
"learning_rate": 0.00047048080357570685,
"loss": 5.9288,
"mean_token_accuracy": 0.15592167973518373,
"num_tokens": 33894332.0,
"step": 17330
},
{
"entropy": 6.11606183052063,
"epoch": 1.7328435047733293,
"grad_norm": 1.2578125,
"learning_rate": 0.000470463129411776,
"loss": 5.8082,
"mean_token_accuracy": 0.1665389597415924,
"num_tokens": 33903556.0,
"step": 17335
},
{
"entropy": 6.209295797348022,
"epoch": 1.733343329834558,
"grad_norm": 1.140625,
"learning_rate": 0.0004704454503300431,
"loss": 5.991,
"mean_token_accuracy": 0.14674981981515883,
"num_tokens": 33913129.0,
"step": 17340
},
{
"entropy": 6.107484531402588,
"epoch": 1.7338431548957864,
"grad_norm": 1.390625,
"learning_rate": 0.000470427766330953,
"loss": 5.8705,
"mean_token_accuracy": 0.1660257324576378,
"num_tokens": 33923016.0,
"step": 17345
},
{
"entropy": 6.169083833694458,
"epoch": 1.734342979957015,
"grad_norm": 1.375,
"learning_rate": 0.0004704100774149506,
"loss": 5.8279,
"mean_token_accuracy": 0.16138252019882202,
"num_tokens": 33932336.0,
"step": 17350
},
{
"entropy": 6.20218300819397,
"epoch": 1.7348428050182436,
"grad_norm": 1.296875,
"learning_rate": 0.00047039238358248086,
"loss": 5.8502,
"mean_token_accuracy": 0.1620868667960167,
"num_tokens": 33941488.0,
"step": 17355
},
{
"entropy": 6.077953147888183,
"epoch": 1.7353426300794723,
"grad_norm": 1.34375,
"learning_rate": 0.000470374684833989,
"loss": 5.6988,
"mean_token_accuracy": 0.17255197316408158,
"num_tokens": 33950919.0,
"step": 17360
},
{
"entropy": 6.028074169158936,
"epoch": 1.7358424551407008,
"grad_norm": 1.3359375,
"learning_rate": 0.0004703569811699205,
"loss": 5.7531,
"mean_token_accuracy": 0.17374650835990907,
"num_tokens": 33960609.0,
"step": 17365
},
{
"entropy": 6.146865749359131,
"epoch": 1.7363422802019293,
"grad_norm": 1.3046875,
"learning_rate": 0.00047033927259072046,
"loss": 5.8988,
"mean_token_accuracy": 0.15924923568964006,
"num_tokens": 33970454.0,
"step": 17370
},
{
"entropy": 6.0890239715576175,
"epoch": 1.736842105263158,
"grad_norm": 1.46875,
"learning_rate": 0.00047032155909683464,
"loss": 5.7684,
"mean_token_accuracy": 0.16922948509454727,
"num_tokens": 33979029.0,
"step": 17375
},
{
"entropy": 6.236788368225097,
"epoch": 1.7373419303243864,
"grad_norm": 1.2890625,
"learning_rate": 0.0004703038406887087,
"loss": 5.9959,
"mean_token_accuracy": 0.150369743257761,
"num_tokens": 33990525.0,
"step": 17380
},
{
"entropy": 6.100458240509033,
"epoch": 1.737841755385615,
"grad_norm": 1.265625,
"learning_rate": 0.00047028611736678837,
"loss": 5.792,
"mean_token_accuracy": 0.17331325113773347,
"num_tokens": 34000022.0,
"step": 17385
},
{
"entropy": 6.091656732559204,
"epoch": 1.7383415804468436,
"grad_norm": 1.4609375,
"learning_rate": 0.0004702683891315196,
"loss": 5.8964,
"mean_token_accuracy": 0.15669012516736985,
"num_tokens": 34010082.0,
"step": 17390
},
{
"entropy": 6.137772130966186,
"epoch": 1.7388414055080723,
"grad_norm": 1.2890625,
"learning_rate": 0.00047025065598334834,
"loss": 5.8516,
"mean_token_accuracy": 0.15300845205783845,
"num_tokens": 34020245.0,
"step": 17395
},
{
"entropy": 6.127038383483887,
"epoch": 1.7393412305693008,
"grad_norm": 1.3125,
"learning_rate": 0.0004702329179227208,
"loss": 5.8408,
"mean_token_accuracy": 0.15858988016843795,
"num_tokens": 34029359.0,
"step": 17400
},
{
"entropy": 6.2134583473205565,
"epoch": 1.7398410556305293,
"grad_norm": 1.3046875,
"learning_rate": 0.00047021517495008335,
"loss": 5.8837,
"mean_token_accuracy": 0.15703776627779006,
"num_tokens": 34039778.0,
"step": 17405
},
{
"entropy": 6.170652770996094,
"epoch": 1.740340880691758,
"grad_norm": 1.234375,
"learning_rate": 0.00047019742706588233,
"loss": 5.932,
"mean_token_accuracy": 0.15969896763563157,
"num_tokens": 34050102.0,
"step": 17410
},
{
"entropy": 6.129020404815674,
"epoch": 1.7408407057529864,
"grad_norm": 1.2890625,
"learning_rate": 0.0004701796742705642,
"loss": 5.7895,
"mean_token_accuracy": 0.1681482821702957,
"num_tokens": 34059292.0,
"step": 17415
},
{
"entropy": 6.115680456161499,
"epoch": 1.741340530814215,
"grad_norm": 1.1171875,
"learning_rate": 0.00047016191656457573,
"loss": 5.8766,
"mean_token_accuracy": 0.1602344885468483,
"num_tokens": 34068547.0,
"step": 17420
},
{
"entropy": 6.0543890476226805,
"epoch": 1.7418403558754436,
"grad_norm": 1.2578125,
"learning_rate": 0.00047014415394836374,
"loss": 5.7789,
"mean_token_accuracy": 0.16812487691640854,
"num_tokens": 34078142.0,
"step": 17425
},
{
"entropy": 6.086417865753174,
"epoch": 1.7423401809366723,
"grad_norm": 1.6796875,
"learning_rate": 0.0004701263864223749,
"loss": 5.8535,
"mean_token_accuracy": 0.15521161556243895,
"num_tokens": 34087780.0,
"step": 17430
},
{
"entropy": 6.19147801399231,
"epoch": 1.7428400059979008,
"grad_norm": 1.2734375,
"learning_rate": 0.0004701086139870565,
"loss": 5.9054,
"mean_token_accuracy": 0.1536896988749504,
"num_tokens": 34097988.0,
"step": 17435
},
{
"entropy": 6.155747938156128,
"epoch": 1.7433398310591293,
"grad_norm": 1.390625,
"learning_rate": 0.0004700908366428556,
"loss": 5.8751,
"mean_token_accuracy": 0.15489028245210648,
"num_tokens": 34107310.0,
"step": 17440
},
{
"entropy": 6.193790340423584,
"epoch": 1.743839656120358,
"grad_norm": 1.2890625,
"learning_rate": 0.0004700730543902194,
"loss": 5.957,
"mean_token_accuracy": 0.15726105570793153,
"num_tokens": 34117063.0,
"step": 17445
},
{
"entropy": 6.057797145843506,
"epoch": 1.7443394811815864,
"grad_norm": 1.3125,
"learning_rate": 0.00047005526722959537,
"loss": 5.8048,
"mean_token_accuracy": 0.16806154251098632,
"num_tokens": 34125391.0,
"step": 17450
},
{
"entropy": 6.066979503631591,
"epoch": 1.744839306242815,
"grad_norm": 1.234375,
"learning_rate": 0.00047003747516143095,
"loss": 5.902,
"mean_token_accuracy": 0.15875881314277648,
"num_tokens": 34135816.0,
"step": 17455
},
{
"entropy": 6.14509015083313,
"epoch": 1.7453391313040436,
"grad_norm": 1.3515625,
"learning_rate": 0.00047001967818617385,
"loss": 5.9288,
"mean_token_accuracy": 0.15735705941915512,
"num_tokens": 34146366.0,
"step": 17460
},
{
"entropy": 6.194706964492798,
"epoch": 1.7458389563652723,
"grad_norm": 1.25,
"learning_rate": 0.0004700018763042719,
"loss": 5.8572,
"mean_token_accuracy": 0.15940831750631332,
"num_tokens": 34155982.0,
"step": 17465
},
{
"entropy": 6.154786539077759,
"epoch": 1.7463387814265006,
"grad_norm": 1.390625,
"learning_rate": 0.0004699840695161728,
"loss": 5.8951,
"mean_token_accuracy": 0.16209059804677964,
"num_tokens": 34164808.0,
"step": 17470
},
{
"entropy": 6.059711742401123,
"epoch": 1.7468386064877293,
"grad_norm": 1.5078125,
"learning_rate": 0.0004699662578223248,
"loss": 5.7937,
"mean_token_accuracy": 0.1725698485970497,
"num_tokens": 34174010.0,
"step": 17475
},
{
"entropy": 6.110303211212158,
"epoch": 1.747338431548958,
"grad_norm": 1.2265625,
"learning_rate": 0.00046994844122317587,
"loss": 5.779,
"mean_token_accuracy": 0.16369424313306807,
"num_tokens": 34183116.0,
"step": 17480
},
{
"entropy": 6.11467752456665,
"epoch": 1.7478382566101864,
"grad_norm": 1.265625,
"learning_rate": 0.00046993061971917433,
"loss": 5.8482,
"mean_token_accuracy": 0.1702541619539261,
"num_tokens": 34191976.0,
"step": 17485
},
{
"entropy": 6.120127725601196,
"epoch": 1.748338081671415,
"grad_norm": 1.328125,
"learning_rate": 0.00046991279331076865,
"loss": 5.8731,
"mean_token_accuracy": 0.16079101860523223,
"num_tokens": 34200211.0,
"step": 17490
},
{
"entropy": 6.126020050048828,
"epoch": 1.7488379067326436,
"grad_norm": 1.2265625,
"learning_rate": 0.0004698949619984071,
"loss": 5.8616,
"mean_token_accuracy": 0.1645189106464386,
"num_tokens": 34210392.0,
"step": 17495
},
{
"entropy": 6.108590126037598,
"epoch": 1.7493377317938723,
"grad_norm": 1.3984375,
"learning_rate": 0.0004698771257825385,
"loss": 5.8566,
"mean_token_accuracy": 0.1622546821832657,
"num_tokens": 34220139.0,
"step": 17500
},
{
"entropy": 6.118734216690063,
"epoch": 1.7498375568551006,
"grad_norm": 1.2109375,
"learning_rate": 0.0004698592846636116,
"loss": 5.8708,
"mean_token_accuracy": 0.16140561252832414,
"num_tokens": 34230413.0,
"step": 17505
},
{
"entropy": 6.045577764511108,
"epoch": 1.7503373819163293,
"grad_norm": 1.171875,
"learning_rate": 0.0004698414386420752,
"loss": 5.885,
"mean_token_accuracy": 0.1680714726448059,
"num_tokens": 34240312.0,
"step": 17510
},
{
"entropy": 6.120620679855347,
"epoch": 1.750837206977558,
"grad_norm": 1.2109375,
"learning_rate": 0.0004698235877183784,
"loss": 5.8959,
"mean_token_accuracy": 0.15875301361083985,
"num_tokens": 34250043.0,
"step": 17515
},
{
"entropy": 6.173157119750977,
"epoch": 1.7513370320387864,
"grad_norm": 1.296875,
"learning_rate": 0.00046980573189297017,
"loss": 5.8513,
"mean_token_accuracy": 0.1642141193151474,
"num_tokens": 34259424.0,
"step": 17520
},
{
"entropy": 6.1149389266967775,
"epoch": 1.751836857100015,
"grad_norm": 1.265625,
"learning_rate": 0.0004697878711662999,
"loss": 5.8156,
"mean_token_accuracy": 0.16539095640182494,
"num_tokens": 34268133.0,
"step": 17525
},
{
"entropy": 6.071035623550415,
"epoch": 1.7523366821612436,
"grad_norm": 1.1953125,
"learning_rate": 0.00046977000553881696,
"loss": 5.8432,
"mean_token_accuracy": 0.1641629531979561,
"num_tokens": 34277090.0,
"step": 17530
},
{
"entropy": 6.099884843826294,
"epoch": 1.752836507222472,
"grad_norm": 1.28125,
"learning_rate": 0.00046975213501097076,
"loss": 5.8367,
"mean_token_accuracy": 0.1652570128440857,
"num_tokens": 34285684.0,
"step": 17535
},
{
"entropy": 6.064550256729126,
"epoch": 1.7533363322837006,
"grad_norm": 1.40625,
"learning_rate": 0.0004697342595832109,
"loss": 5.7157,
"mean_token_accuracy": 0.17021902054548263,
"num_tokens": 34294483.0,
"step": 17540
},
{
"entropy": 6.109165382385254,
"epoch": 1.7538361573449293,
"grad_norm": 1.390625,
"learning_rate": 0.00046971637925598725,
"loss": 5.8277,
"mean_token_accuracy": 0.16380289644002916,
"num_tokens": 34303027.0,
"step": 17545
},
{
"entropy": 6.145949840545654,
"epoch": 1.754335982406158,
"grad_norm": 1.3203125,
"learning_rate": 0.0004696984940297496,
"loss": 5.8676,
"mean_token_accuracy": 0.15415992587804794,
"num_tokens": 34313034.0,
"step": 17550
},
{
"entropy": 6.063510322570801,
"epoch": 1.7548358074673864,
"grad_norm": 1.3203125,
"learning_rate": 0.000469680603904948,
"loss": 5.8161,
"mean_token_accuracy": 0.16809021830558776,
"num_tokens": 34323345.0,
"step": 17555
},
{
"entropy": 6.073070096969604,
"epoch": 1.755335632528615,
"grad_norm": 1.359375,
"learning_rate": 0.00046966270888203237,
"loss": 5.8427,
"mean_token_accuracy": 0.16222451031208038,
"num_tokens": 34332273.0,
"step": 17560
},
{
"entropy": 6.20688157081604,
"epoch": 1.7558354575898436,
"grad_norm": 1.4765625,
"learning_rate": 0.0004696448089614532,
"loss": 5.924,
"mean_token_accuracy": 0.16014135926961898,
"num_tokens": 34342071.0,
"step": 17565
},
{
"entropy": 6.10514817237854,
"epoch": 1.756335282651072,
"grad_norm": 1.2734375,
"learning_rate": 0.0004696269041436606,
"loss": 5.7223,
"mean_token_accuracy": 0.1719916433095932,
"num_tokens": 34352204.0,
"step": 17570
},
{
"entropy": 6.034449434280395,
"epoch": 1.7568351077123006,
"grad_norm": 1.4453125,
"learning_rate": 0.0004696089944291052,
"loss": 5.7745,
"mean_token_accuracy": 0.1708928555250168,
"num_tokens": 34362033.0,
"step": 17575
},
{
"entropy": 6.141708326339722,
"epoch": 1.7573349327735293,
"grad_norm": 1.484375,
"learning_rate": 0.0004695910798182377,
"loss": 5.8597,
"mean_token_accuracy": 0.1637091413140297,
"num_tokens": 34371770.0,
"step": 17580
},
{
"entropy": 6.117165613174438,
"epoch": 1.757834757834758,
"grad_norm": 1.4453125,
"learning_rate": 0.0004695731603115086,
"loss": 5.8811,
"mean_token_accuracy": 0.16035598814487456,
"num_tokens": 34381755.0,
"step": 17585
},
{
"entropy": 6.059657001495362,
"epoch": 1.7583345828959864,
"grad_norm": 1.453125,
"learning_rate": 0.00046955523590936884,
"loss": 5.7773,
"mean_token_accuracy": 0.1669861450791359,
"num_tokens": 34390909.0,
"step": 17590
},
{
"entropy": 6.1609423637390135,
"epoch": 1.758834407957215,
"grad_norm": 1.5625,
"learning_rate": 0.0004695373066122694,
"loss": 5.8754,
"mean_token_accuracy": 0.16121077090501784,
"num_tokens": 34401051.0,
"step": 17595
},
{
"entropy": 6.174912166595459,
"epoch": 1.7593342330184436,
"grad_norm": 1.3828125,
"learning_rate": 0.0004695193724206615,
"loss": 5.8877,
"mean_token_accuracy": 0.16476171165704728,
"num_tokens": 34410099.0,
"step": 17600
},
{
"entropy": 6.091646194458008,
"epoch": 1.759834058079672,
"grad_norm": 1.203125,
"learning_rate": 0.00046950143333499613,
"loss": 5.7982,
"mean_token_accuracy": 0.15888398587703706,
"num_tokens": 34418895.0,
"step": 17605
},
{
"entropy": 6.0000206470489506,
"epoch": 1.7603338831409006,
"grad_norm": 1.2734375,
"learning_rate": 0.00046948348935572476,
"loss": 5.8475,
"mean_token_accuracy": 0.16446249485015868,
"num_tokens": 34429369.0,
"step": 17610
},
{
"entropy": 6.119893503189087,
"epoch": 1.7608337082021293,
"grad_norm": 1.1796875,
"learning_rate": 0.0004694655404832988,
"loss": 5.8955,
"mean_token_accuracy": 0.16525406241416932,
"num_tokens": 34439773.0,
"step": 17615
},
{
"entropy": 6.2512036800384525,
"epoch": 1.761333533263358,
"grad_norm": 1.3671875,
"learning_rate": 0.00046944758671817,
"loss": 5.9273,
"mean_token_accuracy": 0.15854718908667564,
"num_tokens": 34450613.0,
"step": 17620
},
{
"entropy": 6.173658990859986,
"epoch": 1.7618333583245864,
"grad_norm": 1.171875,
"learning_rate": 0.0004694296280607899,
"loss": 5.9216,
"mean_token_accuracy": 0.16239755749702453,
"num_tokens": 34460785.0,
"step": 17625
},
{
"entropy": 6.247310495376587,
"epoch": 1.762333183385815,
"grad_norm": 1.359375,
"learning_rate": 0.0004694116645116104,
"loss": 5.9591,
"mean_token_accuracy": 0.1549449719488621,
"num_tokens": 34471152.0,
"step": 17630
},
{
"entropy": 6.099266815185547,
"epoch": 1.7628330084470436,
"grad_norm": 1.171875,
"learning_rate": 0.0004693936960710834,
"loss": 5.7747,
"mean_token_accuracy": 0.1703835666179657,
"num_tokens": 34481511.0,
"step": 17635
},
{
"entropy": 6.078824377059936,
"epoch": 1.763332833508272,
"grad_norm": 1.2890625,
"learning_rate": 0.00046937572273966104,
"loss": 5.8402,
"mean_token_accuracy": 0.1673873782157898,
"num_tokens": 34490556.0,
"step": 17640
},
{
"entropy": 6.092703866958618,
"epoch": 1.7638326585695006,
"grad_norm": 1.3125,
"learning_rate": 0.00046935774451779556,
"loss": 5.8343,
"mean_token_accuracy": 0.1668176457285881,
"num_tokens": 34500363.0,
"step": 17645
},
{
"entropy": 6.059854030609131,
"epoch": 1.7643324836307293,
"grad_norm": 1.1328125,
"learning_rate": 0.0004693397614059392,
"loss": 5.8336,
"mean_token_accuracy": 0.16878130286931992,
"num_tokens": 34511009.0,
"step": 17650
},
{
"entropy": 6.228938055038452,
"epoch": 1.764832308691958,
"grad_norm": 1.328125,
"learning_rate": 0.0004693217734045445,
"loss": 5.8986,
"mean_token_accuracy": 0.1588161088526249,
"num_tokens": 34520806.0,
"step": 17655
},
{
"entropy": 6.191421699523926,
"epoch": 1.7653321337531864,
"grad_norm": 1.25,
"learning_rate": 0.00046930378051406393,
"loss": 5.8236,
"mean_token_accuracy": 0.16540293842554094,
"num_tokens": 34531266.0,
"step": 17660
},
{
"entropy": 6.235346078872681,
"epoch": 1.765831958814415,
"grad_norm": 1.2578125,
"learning_rate": 0.00046928578273495026,
"loss": 5.9887,
"mean_token_accuracy": 0.15136819034814836,
"num_tokens": 34542503.0,
"step": 17665
},
{
"entropy": 6.144253969192505,
"epoch": 1.7663317838756436,
"grad_norm": 1.4375,
"learning_rate": 0.0004692677800676563,
"loss": 5.8656,
"mean_token_accuracy": 0.1645709827542305,
"num_tokens": 34552639.0,
"step": 17670
},
{
"entropy": 6.04638147354126,
"epoch": 1.766831608936872,
"grad_norm": 1.15625,
"learning_rate": 0.00046924977251263495,
"loss": 5.7821,
"mean_token_accuracy": 0.16980100274086,
"num_tokens": 34562411.0,
"step": 17675
},
{
"entropy": 6.083621311187744,
"epoch": 1.7673314339981006,
"grad_norm": 1.453125,
"learning_rate": 0.00046923176007033937,
"loss": 5.8471,
"mean_token_accuracy": 0.16053920984268188,
"num_tokens": 34571532.0,
"step": 17680
},
{
"entropy": 6.131117677688598,
"epoch": 1.7678312590593293,
"grad_norm": 1.296875,
"learning_rate": 0.00046921374274122265,
"loss": 5.7707,
"mean_token_accuracy": 0.16452214270830154,
"num_tokens": 34580338.0,
"step": 17685
},
{
"entropy": 6.041928291320801,
"epoch": 1.768331084120558,
"grad_norm": 1.1875,
"learning_rate": 0.00046919572052573814,
"loss": 5.7905,
"mean_token_accuracy": 0.16990778148174285,
"num_tokens": 34589353.0,
"step": 17690
},
{
"entropy": 6.162481212615967,
"epoch": 1.7688309091817864,
"grad_norm": 1.3828125,
"learning_rate": 0.00046917769342433925,
"loss": 5.9723,
"mean_token_accuracy": 0.16018515080213547,
"num_tokens": 34599981.0,
"step": 17695
},
{
"entropy": 6.068850708007813,
"epoch": 1.769330734243015,
"grad_norm": 1.2578125,
"learning_rate": 0.0004691596614374796,
"loss": 5.6985,
"mean_token_accuracy": 0.1741074427962303,
"num_tokens": 34608927.0,
"step": 17700
},
{
"entropy": 6.127185678482055,
"epoch": 1.7698305593042436,
"grad_norm": 1.5390625,
"learning_rate": 0.0004691416245656128,
"loss": 5.8698,
"mean_token_accuracy": 0.15983858406543733,
"num_tokens": 34619455.0,
"step": 17705
},
{
"entropy": 6.1132001876831055,
"epoch": 1.770330384365472,
"grad_norm": 1.203125,
"learning_rate": 0.00046912358280919267,
"loss": 5.7504,
"mean_token_accuracy": 0.1665702134370804,
"num_tokens": 34628761.0,
"step": 17710
},
{
"entropy": 6.102512407302856,
"epoch": 1.7708302094267006,
"grad_norm": 1.1015625,
"learning_rate": 0.00046910553616867314,
"loss": 5.8856,
"mean_token_accuracy": 0.15870064944028855,
"num_tokens": 34638859.0,
"step": 17715
},
{
"entropy": 6.043902397155762,
"epoch": 1.7713300344879293,
"grad_norm": 1.2109375,
"learning_rate": 0.0004690874846445083,
"loss": 5.7589,
"mean_token_accuracy": 0.1702035993337631,
"num_tokens": 34648466.0,
"step": 17720
},
{
"entropy": 6.045576906204223,
"epoch": 1.771829859549158,
"grad_norm": 1.28125,
"learning_rate": 0.0004690694282371523,
"loss": 5.7575,
"mean_token_accuracy": 0.16930388659238815,
"num_tokens": 34658567.0,
"step": 17725
},
{
"entropy": 6.026725578308105,
"epoch": 1.7723296846103862,
"grad_norm": 1.296875,
"learning_rate": 0.0004690513669470594,
"loss": 5.6783,
"mean_token_accuracy": 0.17870956510305405,
"num_tokens": 34667555.0,
"step": 17730
},
{
"entropy": 6.167243146896363,
"epoch": 1.772829509671615,
"grad_norm": 1.3046875,
"learning_rate": 0.000469033300774684,
"loss": 5.8563,
"mean_token_accuracy": 0.159641832113266,
"num_tokens": 34678002.0,
"step": 17735
},
{
"entropy": 6.114215898513794,
"epoch": 1.7733293347328436,
"grad_norm": 1.2421875,
"learning_rate": 0.0004690152297204808,
"loss": 5.7973,
"mean_token_accuracy": 0.17122994512319564,
"num_tokens": 34688112.0,
"step": 17740
},
{
"entropy": 6.091564083099366,
"epoch": 1.773829159794072,
"grad_norm": 1.140625,
"learning_rate": 0.00046899715378490427,
"loss": 5.8783,
"mean_token_accuracy": 0.16099835634231568,
"num_tokens": 34697960.0,
"step": 17745
},
{
"entropy": 6.072007417678833,
"epoch": 1.7743289848553006,
"grad_norm": 1.484375,
"learning_rate": 0.00046897907296840927,
"loss": 5.7114,
"mean_token_accuracy": 0.17345488518476487,
"num_tokens": 34708072.0,
"step": 17750
},
{
"entropy": 6.037260723114014,
"epoch": 1.7748288099165292,
"grad_norm": 1.28125,
"learning_rate": 0.0004689609872714507,
"loss": 5.7423,
"mean_token_accuracy": 0.1698773831129074,
"num_tokens": 34717723.0,
"step": 17755
},
{
"entropy": 6.125628423690796,
"epoch": 1.775328634977758,
"grad_norm": 1.34375,
"learning_rate": 0.00046894289669448366,
"loss": 5.8725,
"mean_token_accuracy": 0.16127837896347047,
"num_tokens": 34727326.0,
"step": 17760
},
{
"entropy": 6.1628705024719235,
"epoch": 1.7758284600389862,
"grad_norm": 1.3125,
"learning_rate": 0.00046892480123796314,
"loss": 5.8302,
"mean_token_accuracy": 0.16487298905849457,
"num_tokens": 34737203.0,
"step": 17765
},
{
"entropy": 6.091555118560791,
"epoch": 1.776328285100215,
"grad_norm": 1.2265625,
"learning_rate": 0.0004689067009023446,
"loss": 5.8387,
"mean_token_accuracy": 0.16337076127529143,
"num_tokens": 34746287.0,
"step": 17770
},
{
"entropy": 6.071529531478882,
"epoch": 1.7768281101614436,
"grad_norm": 1.171875,
"learning_rate": 0.0004688885956880834,
"loss": 5.7809,
"mean_token_accuracy": 0.16863114833831788,
"num_tokens": 34757478.0,
"step": 17775
},
{
"entropy": 6.119533681869507,
"epoch": 1.777327935222672,
"grad_norm": 1.21875,
"learning_rate": 0.0004688704855956349,
"loss": 5.7676,
"mean_token_accuracy": 0.17045095413923264,
"num_tokens": 34766474.0,
"step": 17780
},
{
"entropy": 6.12436990737915,
"epoch": 1.7778277602839005,
"grad_norm": 1.4609375,
"learning_rate": 0.00046885237062545493,
"loss": 5.7611,
"mean_token_accuracy": 0.16922566145658494,
"num_tokens": 34775500.0,
"step": 17785
},
{
"entropy": 6.067885780334473,
"epoch": 1.7783275853451292,
"grad_norm": 1.25,
"learning_rate": 0.00046883425077799923,
"loss": 5.8745,
"mean_token_accuracy": 0.1645024374127388,
"num_tokens": 34785290.0,
"step": 17790
},
{
"entropy": 6.242372035980225,
"epoch": 1.7788274104063577,
"grad_norm": 1.109375,
"learning_rate": 0.0004688161260537236,
"loss": 6.0462,
"mean_token_accuracy": 0.14957467913627626,
"num_tokens": 34794485.0,
"step": 17795
},
{
"entropy": 6.182308959960937,
"epoch": 1.7793272354675862,
"grad_norm": 1.2265625,
"learning_rate": 0.0004687979964530842,
"loss": 5.8002,
"mean_token_accuracy": 0.1666768506169319,
"num_tokens": 34803825.0,
"step": 17800
},
{
"entropy": 6.172938537597656,
"epoch": 1.779827060528815,
"grad_norm": 1.1640625,
"learning_rate": 0.000468779861976537,
"loss": 5.9273,
"mean_token_accuracy": 0.15534346997737886,
"num_tokens": 34812553.0,
"step": 17805
},
{
"entropy": 6.076042222976684,
"epoch": 1.7803268855900436,
"grad_norm": 1.2890625,
"learning_rate": 0.00046876172262453843,
"loss": 5.883,
"mean_token_accuracy": 0.1644313305616379,
"num_tokens": 34822427.0,
"step": 17810
},
{
"entropy": 6.14277982711792,
"epoch": 1.780826710651272,
"grad_norm": 1.34375,
"learning_rate": 0.00046874357839754463,
"loss": 6.0362,
"mean_token_accuracy": 0.15067177414894103,
"num_tokens": 34831918.0,
"step": 17815
},
{
"entropy": 6.1720499992370605,
"epoch": 1.7813265357125005,
"grad_norm": 1.296875,
"learning_rate": 0.00046872542929601234,
"loss": 5.8057,
"mean_token_accuracy": 0.16108608543872832,
"num_tokens": 34840429.0,
"step": 17820
},
{
"entropy": 6.1331264019012455,
"epoch": 1.7818263607737292,
"grad_norm": 1.1796875,
"learning_rate": 0.00046870727532039816,
"loss": 5.7996,
"mean_token_accuracy": 0.16690599620342256,
"num_tokens": 34850455.0,
"step": 17825
},
{
"entropy": 6.082704067230225,
"epoch": 1.7823261858349577,
"grad_norm": 1.21875,
"learning_rate": 0.0004686891164711586,
"loss": 5.7976,
"mean_token_accuracy": 0.1670275777578354,
"num_tokens": 34860062.0,
"step": 17830
},
{
"entropy": 6.118826055526734,
"epoch": 1.7828260108961862,
"grad_norm": 1.1640625,
"learning_rate": 0.00046867095274875085,
"loss": 5.8153,
"mean_token_accuracy": 0.17085691392421723,
"num_tokens": 34869987.0,
"step": 17835
},
{
"entropy": 6.142798042297363,
"epoch": 1.783325835957415,
"grad_norm": 1.1640625,
"learning_rate": 0.00046865278415363174,
"loss": 5.927,
"mean_token_accuracy": 0.15881933867931367,
"num_tokens": 34881593.0,
"step": 17840
},
{
"entropy": 6.159872531890869,
"epoch": 1.7838256610186436,
"grad_norm": 1.1953125,
"learning_rate": 0.0004686346106862584,
"loss": 5.8703,
"mean_token_accuracy": 0.16152282953262329,
"num_tokens": 34891468.0,
"step": 17845
},
{
"entropy": 6.11032280921936,
"epoch": 1.784325486079872,
"grad_norm": 1.171875,
"learning_rate": 0.0004686164323470881,
"loss": 5.7565,
"mean_token_accuracy": 0.16973702907562255,
"num_tokens": 34900591.0,
"step": 17850
},
{
"entropy": 6.101046991348267,
"epoch": 1.7848253111411005,
"grad_norm": 1.578125,
"learning_rate": 0.0004685982491365781,
"loss": 5.7677,
"mean_token_accuracy": 0.17229566723108292,
"num_tokens": 34909514.0,
"step": 17855
},
{
"entropy": 6.15239634513855,
"epoch": 1.7853251362023292,
"grad_norm": 1.3515625,
"learning_rate": 0.00046858006105518615,
"loss": 5.7741,
"mean_token_accuracy": 0.16635277271270751,
"num_tokens": 34918836.0,
"step": 17860
},
{
"entropy": 6.0001977443695065,
"epoch": 1.7858249612635577,
"grad_norm": 1.25,
"learning_rate": 0.0004685618681033695,
"loss": 5.7128,
"mean_token_accuracy": 0.1717883124947548,
"num_tokens": 34928040.0,
"step": 17865
},
{
"entropy": 6.057123851776123,
"epoch": 1.7863247863247862,
"grad_norm": 1.390625,
"learning_rate": 0.0004685436702815861,
"loss": 5.7675,
"mean_token_accuracy": 0.17020978927612304,
"num_tokens": 34936879.0,
"step": 17870
},
{
"entropy": 6.085494613647461,
"epoch": 1.786824611386015,
"grad_norm": 1.296875,
"learning_rate": 0.0004685254675902938,
"loss": 5.8067,
"mean_token_accuracy": 0.16087810844182968,
"num_tokens": 34946986.0,
"step": 17875
},
{
"entropy": 6.081479024887085,
"epoch": 1.7873244364472436,
"grad_norm": 1.28125,
"learning_rate": 0.0004685072600299505,
"loss": 5.8054,
"mean_token_accuracy": 0.16483895629644393,
"num_tokens": 34956848.0,
"step": 17880
},
{
"entropy": 6.176258754730225,
"epoch": 1.787824261508472,
"grad_norm": 1.2578125,
"learning_rate": 0.0004684890476010144,
"loss": 5.8546,
"mean_token_accuracy": 0.1653517633676529,
"num_tokens": 34966656.0,
"step": 17885
},
{
"entropy": 6.13749852180481,
"epoch": 1.7883240865697005,
"grad_norm": 1.1953125,
"learning_rate": 0.0004684708303039435,
"loss": 5.7726,
"mean_token_accuracy": 0.17276311218738555,
"num_tokens": 34975672.0,
"step": 17890
},
{
"entropy": 5.996784400939942,
"epoch": 1.7888239116309292,
"grad_norm": 1.3046875,
"learning_rate": 0.00046845260813919645,
"loss": 5.7867,
"mean_token_accuracy": 0.1718239188194275,
"num_tokens": 34985253.0,
"step": 17895
},
{
"entropy": 6.0682902336120605,
"epoch": 1.7893237366921577,
"grad_norm": 1.1875,
"learning_rate": 0.00046843438110723143,
"loss": 5.7723,
"mean_token_accuracy": 0.17010565996170043,
"num_tokens": 34995115.0,
"step": 17900
},
{
"entropy": 6.1444720268249515,
"epoch": 1.7898235617533862,
"grad_norm": 1.3359375,
"learning_rate": 0.00046841614920850724,
"loss": 5.834,
"mean_token_accuracy": 0.16808309853076936,
"num_tokens": 35005317.0,
"step": 17905
},
{
"entropy": 6.154652833938599,
"epoch": 1.790323386814615,
"grad_norm": 1.328125,
"learning_rate": 0.00046839791244348243,
"loss": 5.8445,
"mean_token_accuracy": 0.16633743196725845,
"num_tokens": 35015296.0,
"step": 17910
},
{
"entropy": 6.009828329086304,
"epoch": 1.7908232118758436,
"grad_norm": 1.2890625,
"learning_rate": 0.00046837967081261606,
"loss": 5.6048,
"mean_token_accuracy": 0.1857542872428894,
"num_tokens": 35023575.0,
"step": 17915
},
{
"entropy": 6.110335016250611,
"epoch": 1.791323036937072,
"grad_norm": 1.203125,
"learning_rate": 0.0004683614243163668,
"loss": 5.9133,
"mean_token_accuracy": 0.16155678406357765,
"num_tokens": 35034350.0,
"step": 17920
},
{
"entropy": 6.073188447952271,
"epoch": 1.7918228619983005,
"grad_norm": 1.1796875,
"learning_rate": 0.0004683431729551939,
"loss": 5.8271,
"mean_token_accuracy": 0.1652176186442375,
"num_tokens": 35045125.0,
"step": 17925
},
{
"entropy": 6.0837592601776125,
"epoch": 1.7923226870595292,
"grad_norm": 1.2890625,
"learning_rate": 0.0004683249167295565,
"loss": 5.7568,
"mean_token_accuracy": 0.1712494522333145,
"num_tokens": 35055160.0,
"step": 17930
},
{
"entropy": 6.133599519729614,
"epoch": 1.7928225121207577,
"grad_norm": 1.34375,
"learning_rate": 0.000468306655639914,
"loss": 5.9088,
"mean_token_accuracy": 0.15774717032909394,
"num_tokens": 35065626.0,
"step": 17935
},
{
"entropy": 6.177978944778443,
"epoch": 1.7933223371819862,
"grad_norm": 1.3828125,
"learning_rate": 0.0004682883896867257,
"loss": 5.8963,
"mean_token_accuracy": 0.16228712052106858,
"num_tokens": 35077294.0,
"step": 17940
},
{
"entropy": 6.085515022277832,
"epoch": 1.793822162243215,
"grad_norm": 1.296875,
"learning_rate": 0.0004682701188704513,
"loss": 5.7614,
"mean_token_accuracy": 0.1748046860098839,
"num_tokens": 35086022.0,
"step": 17945
},
{
"entropy": 6.114905548095703,
"epoch": 1.7943219873044436,
"grad_norm": 1.2109375,
"learning_rate": 0.0004682518431915505,
"loss": 5.9613,
"mean_token_accuracy": 0.1619322381913662,
"num_tokens": 35095966.0,
"step": 17950
},
{
"entropy": 6.117956733703613,
"epoch": 1.794821812365672,
"grad_norm": 1.140625,
"learning_rate": 0.00046823356265048293,
"loss": 5.7815,
"mean_token_accuracy": 0.1601074978709221,
"num_tokens": 35105554.0,
"step": 17955
},
{
"entropy": 6.063162517547608,
"epoch": 1.7953216374269005,
"grad_norm": 1.25,
"learning_rate": 0.0004682152772477087,
"loss": 5.749,
"mean_token_accuracy": 0.16868563890457153,
"num_tokens": 35114485.0,
"step": 17960
},
{
"entropy": 6.07885217666626,
"epoch": 1.7958214624881292,
"grad_norm": 1.25,
"learning_rate": 0.00046819698698368785,
"loss": 5.8404,
"mean_token_accuracy": 0.16081240624189377,
"num_tokens": 35124765.0,
"step": 17965
},
{
"entropy": 6.12259087562561,
"epoch": 1.7963212875493577,
"grad_norm": 1.1953125,
"learning_rate": 0.00046817869185888044,
"loss": 5.8664,
"mean_token_accuracy": 0.16100157648324967,
"num_tokens": 35134474.0,
"step": 17970
},
{
"entropy": 6.116328001022339,
"epoch": 1.7968211126105862,
"grad_norm": 1.2734375,
"learning_rate": 0.0004681603918737469,
"loss": 5.8284,
"mean_token_accuracy": 0.16755760163068772,
"num_tokens": 35144717.0,
"step": 17975
},
{
"entropy": 6.176896286010742,
"epoch": 1.7973209376718149,
"grad_norm": 1.40625,
"learning_rate": 0.00046814208702874766,
"loss": 5.8264,
"mean_token_accuracy": 0.17200229167938233,
"num_tokens": 35153889.0,
"step": 17980
},
{
"entropy": 6.051694250106811,
"epoch": 1.7978207627330436,
"grad_norm": 1.4140625,
"learning_rate": 0.00046812377732434316,
"loss": 5.7729,
"mean_token_accuracy": 0.16642460376024246,
"num_tokens": 35163909.0,
"step": 17985
},
{
"entropy": 6.11577000617981,
"epoch": 1.7983205877942718,
"grad_norm": 1.4921875,
"learning_rate": 0.00046810546276099415,
"loss": 5.8648,
"mean_token_accuracy": 0.15462714284658433,
"num_tokens": 35174614.0,
"step": 17990
},
{
"entropy": 6.104050779342652,
"epoch": 1.7988204128555005,
"grad_norm": 1.203125,
"learning_rate": 0.0004680871433391613,
"loss": 5.8538,
"mean_token_accuracy": 0.16439516097307205,
"num_tokens": 35184568.0,
"step": 17995
},
{
"entropy": 6.0546222686767575,
"epoch": 1.7993202379167292,
"grad_norm": 1.234375,
"learning_rate": 0.00046806881905930565,
"loss": 5.8015,
"mean_token_accuracy": 0.16840032786130904,
"num_tokens": 35194594.0,
"step": 18000
},
{
"epoch": 1.7993202379167292,
"eval_entropy": 5.8954797842796856,
"eval_loss": 5.926145553588867,
"eval_mean_token_accuracy": 0.16697430877983033,
"eval_num_tokens": 35194594.0,
"eval_runtime": 23.8527,
"eval_samples_per_second": 1301.53,
"eval_steps_per_second": 162.707,
"step": 18000
}
],
"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": 5.5764382058496e+16,
"train_batch_size": 16,
"trial_name": null,
"trial_params": null
}
Reference in New Issue View Git Blame Copy Permalink