043a6d536a
Model: fpadovani/ind-latn-100mb-after-ppt-Dp-100mb-ckpt500_seed3407 Source: Original Platform
30090 lines
825 KiB
JSON
30090 lines
825 KiB
JSON
{
|
|
"best_global_step": null,
|
|
"best_metric": null,
|
|
"best_model_checkpoint": null,
|
|
"epoch": 1.1670492122155223,
|
|
"eval_steps": 3000,
|
|
"global_step": 15000,
|
|
"is_hyper_param_search": false,
|
|
"is_local_process_zero": true,
|
|
"is_world_process_zero": true,
|
|
"log_history": [
|
|
{
|
|
"entropy": 7.269065999984742,
|
|
"epoch": 0.00038902937171756465,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 2e-06,
|
|
"loss": 6.9697,
|
|
"mean_token_accuracy": 0.09287577494978905,
|
|
"num_tokens": 8755.0,
|
|
"step": 5
|
|
},
|
|
{
|
|
"entropy": 7.24174690246582,
|
|
"epoch": 0.0007780587434351293,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 4.5e-06,
|
|
"loss": 6.8689,
|
|
"mean_token_accuracy": 0.10080403685569764,
|
|
"num_tokens": 17641.0,
|
|
"step": 10
|
|
},
|
|
{
|
|
"entropy": 7.2524326801300045,
|
|
"epoch": 0.001167088115152694,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 7e-06,
|
|
"loss": 6.8352,
|
|
"mean_token_accuracy": 0.1029132291674614,
|
|
"num_tokens": 26293.0,
|
|
"step": 15
|
|
},
|
|
{
|
|
"entropy": 7.236858367919922,
|
|
"epoch": 0.0015561174868702586,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 9.5e-06,
|
|
"loss": 6.9173,
|
|
"mean_token_accuracy": 0.09302133619785309,
|
|
"num_tokens": 35627.0,
|
|
"step": 20
|
|
},
|
|
{
|
|
"entropy": 7.244942045211792,
|
|
"epoch": 0.0019451468585878235,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 1.2e-05,
|
|
"loss": 6.7904,
|
|
"mean_token_accuracy": 0.09609957337379456,
|
|
"num_tokens": 43861.0,
|
|
"step": 25
|
|
},
|
|
{
|
|
"entropy": 7.265231990814209,
|
|
"epoch": 0.002334176230305388,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 1.4500000000000002e-05,
|
|
"loss": 6.9082,
|
|
"mean_token_accuracy": 0.10079698711633682,
|
|
"num_tokens": 52816.0,
|
|
"step": 30
|
|
},
|
|
{
|
|
"entropy": 7.206892585754394,
|
|
"epoch": 0.0027232056020229526,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 1.7000000000000003e-05,
|
|
"loss": 6.8845,
|
|
"mean_token_accuracy": 0.09604551345109939,
|
|
"num_tokens": 61370.0,
|
|
"step": 35
|
|
},
|
|
{
|
|
"entropy": 7.175060510635376,
|
|
"epoch": 0.0031122349737405172,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 1.95e-05,
|
|
"loss": 6.8414,
|
|
"mean_token_accuracy": 0.10664354413747787,
|
|
"num_tokens": 69444.0,
|
|
"step": 40
|
|
},
|
|
{
|
|
"entropy": 7.201863145828247,
|
|
"epoch": 0.003501264345458082,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 2.2e-05,
|
|
"loss": 6.8663,
|
|
"mean_token_accuracy": 0.09991251826286315,
|
|
"num_tokens": 77892.0,
|
|
"step": 45
|
|
},
|
|
{
|
|
"entropy": 7.237502717971802,
|
|
"epoch": 0.003890293717175647,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 2.4500000000000003e-05,
|
|
"loss": 6.8802,
|
|
"mean_token_accuracy": 0.1035572774708271,
|
|
"num_tokens": 86154.0,
|
|
"step": 50
|
|
},
|
|
{
|
|
"entropy": 7.233007097244263,
|
|
"epoch": 0.004279323088893211,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 2.7e-05,
|
|
"loss": 6.9801,
|
|
"mean_token_accuracy": 0.09926456362009048,
|
|
"num_tokens": 95589.0,
|
|
"step": 55
|
|
},
|
|
{
|
|
"entropy": 7.210332298278809,
|
|
"epoch": 0.004668352460610776,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 2.95e-05,
|
|
"loss": 6.9537,
|
|
"mean_token_accuracy": 0.09557500332593918,
|
|
"num_tokens": 105268.0,
|
|
"step": 60
|
|
},
|
|
{
|
|
"entropy": 7.221558570861816,
|
|
"epoch": 0.0050573818323283405,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 3.2e-05,
|
|
"loss": 6.8541,
|
|
"mean_token_accuracy": 0.10574058592319488,
|
|
"num_tokens": 113347.0,
|
|
"step": 65
|
|
},
|
|
{
|
|
"entropy": 7.273097324371338,
|
|
"epoch": 0.005446411204045905,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 3.4500000000000005e-05,
|
|
"loss": 6.8594,
|
|
"mean_token_accuracy": 0.10053766742348672,
|
|
"num_tokens": 121235.0,
|
|
"step": 70
|
|
},
|
|
{
|
|
"entropy": 7.158006048202514,
|
|
"epoch": 0.00583544057576347,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 3.7e-05,
|
|
"loss": 6.8223,
|
|
"mean_token_accuracy": 0.1106814831495285,
|
|
"num_tokens": 129529.0,
|
|
"step": 75
|
|
},
|
|
{
|
|
"entropy": 7.159645748138428,
|
|
"epoch": 0.0062244699474810344,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 3.95e-05,
|
|
"loss": 6.8396,
|
|
"mean_token_accuracy": 0.10305875688791274,
|
|
"num_tokens": 137918.0,
|
|
"step": 80
|
|
},
|
|
{
|
|
"entropy": 7.09834132194519,
|
|
"epoch": 0.006613499319198599,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 4.2000000000000004e-05,
|
|
"loss": 6.7712,
|
|
"mean_token_accuracy": 0.10598632469773292,
|
|
"num_tokens": 146445.0,
|
|
"step": 85
|
|
},
|
|
{
|
|
"entropy": 7.1553168296813965,
|
|
"epoch": 0.007002528690916164,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 4.45e-05,
|
|
"loss": 6.9491,
|
|
"mean_token_accuracy": 0.09710680171847344,
|
|
"num_tokens": 155904.0,
|
|
"step": 90
|
|
},
|
|
{
|
|
"entropy": 7.240512037277222,
|
|
"epoch": 0.007391558062633729,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 4.7000000000000004e-05,
|
|
"loss": 6.9027,
|
|
"mean_token_accuracy": 0.10225804299116134,
|
|
"num_tokens": 164436.0,
|
|
"step": 95
|
|
},
|
|
{
|
|
"entropy": 7.2635030269622805,
|
|
"epoch": 0.007780587434351294,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 4.9500000000000004e-05,
|
|
"loss": 6.8728,
|
|
"mean_token_accuracy": 0.10390063747763634,
|
|
"num_tokens": 172985.0,
|
|
"step": 100
|
|
},
|
|
{
|
|
"entropy": 7.08851170539856,
|
|
"epoch": 0.008169616806068859,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 5.2e-05,
|
|
"loss": 6.7724,
|
|
"mean_token_accuracy": 0.10272802859544754,
|
|
"num_tokens": 182084.0,
|
|
"step": 105
|
|
},
|
|
{
|
|
"entropy": 7.16212944984436,
|
|
"epoch": 0.008558646177786422,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 5.45e-05,
|
|
"loss": 6.8229,
|
|
"mean_token_accuracy": 0.1089494489133358,
|
|
"num_tokens": 190742.0,
|
|
"step": 110
|
|
},
|
|
{
|
|
"entropy": 7.2132182121276855,
|
|
"epoch": 0.008947675549503988,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 5.7e-05,
|
|
"loss": 6.8884,
|
|
"mean_token_accuracy": 0.10032395645976067,
|
|
"num_tokens": 199600.0,
|
|
"step": 115
|
|
},
|
|
{
|
|
"entropy": 7.168780326843262,
|
|
"epoch": 0.009336704921221552,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 5.9499999999999996e-05,
|
|
"loss": 6.8386,
|
|
"mean_token_accuracy": 0.10419367179274559,
|
|
"num_tokens": 207883.0,
|
|
"step": 120
|
|
},
|
|
{
|
|
"entropy": 7.225507020950317,
|
|
"epoch": 0.009725734292939117,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 6.2e-05,
|
|
"loss": 6.8926,
|
|
"mean_token_accuracy": 0.0991477519273758,
|
|
"num_tokens": 216216.0,
|
|
"step": 125
|
|
},
|
|
{
|
|
"entropy": 7.191225051879883,
|
|
"epoch": 0.010114763664656681,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 6.450000000000001e-05,
|
|
"loss": 6.8893,
|
|
"mean_token_accuracy": 0.10487327948212624,
|
|
"num_tokens": 225250.0,
|
|
"step": 130
|
|
},
|
|
{
|
|
"entropy": 7.161448907852173,
|
|
"epoch": 0.010503793036374246,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 6.7e-05,
|
|
"loss": 6.8787,
|
|
"mean_token_accuracy": 0.10188574716448784,
|
|
"num_tokens": 233748.0,
|
|
"step": 135
|
|
},
|
|
{
|
|
"entropy": 7.233650588989258,
|
|
"epoch": 0.01089282240809181,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 6.950000000000001e-05,
|
|
"loss": 6.8837,
|
|
"mean_token_accuracy": 0.09749628528952599,
|
|
"num_tokens": 242629.0,
|
|
"step": 140
|
|
},
|
|
{
|
|
"entropy": 7.180519533157349,
|
|
"epoch": 0.011281851779809376,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 7.2e-05,
|
|
"loss": 6.8705,
|
|
"mean_token_accuracy": 0.10328471511602402,
|
|
"num_tokens": 251458.0,
|
|
"step": 145
|
|
},
|
|
{
|
|
"entropy": 7.142206239700317,
|
|
"epoch": 0.01167088115152694,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 7.45e-05,
|
|
"loss": 6.8297,
|
|
"mean_token_accuracy": 0.10440876483917236,
|
|
"num_tokens": 260557.0,
|
|
"step": 150
|
|
},
|
|
{
|
|
"entropy": 7.2722063064575195,
|
|
"epoch": 0.012059910523244505,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 7.7e-05,
|
|
"loss": 6.9593,
|
|
"mean_token_accuracy": 0.09674710109829902,
|
|
"num_tokens": 269262.0,
|
|
"step": 155
|
|
},
|
|
{
|
|
"entropy": 7.189859008789062,
|
|
"epoch": 0.012448939894962069,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 7.950000000000001e-05,
|
|
"loss": 6.8201,
|
|
"mean_token_accuracy": 0.10559003949165344,
|
|
"num_tokens": 277804.0,
|
|
"step": 160
|
|
},
|
|
{
|
|
"entropy": 7.216961669921875,
|
|
"epoch": 0.012837969266679634,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 8.2e-05,
|
|
"loss": 6.7916,
|
|
"mean_token_accuracy": 0.10939481481909752,
|
|
"num_tokens": 287450.0,
|
|
"step": 165
|
|
},
|
|
{
|
|
"entropy": 7.1048828125,
|
|
"epoch": 0.013226998638397198,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 8.450000000000001e-05,
|
|
"loss": 6.8665,
|
|
"mean_token_accuracy": 0.101957518607378,
|
|
"num_tokens": 296497.0,
|
|
"step": 170
|
|
},
|
|
{
|
|
"entropy": 7.164185953140259,
|
|
"epoch": 0.013616028010114764,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 8.7e-05,
|
|
"loss": 6.7666,
|
|
"mean_token_accuracy": 0.10509978234767914,
|
|
"num_tokens": 305414.0,
|
|
"step": 175
|
|
},
|
|
{
|
|
"entropy": 7.161429691314697,
|
|
"epoch": 0.014005057381832327,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 8.95e-05,
|
|
"loss": 6.8125,
|
|
"mean_token_accuracy": 0.1063445545732975,
|
|
"num_tokens": 313639.0,
|
|
"step": 180
|
|
},
|
|
{
|
|
"entropy": 7.171407413482666,
|
|
"epoch": 0.014394086753549893,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 9.2e-05,
|
|
"loss": 6.846,
|
|
"mean_token_accuracy": 0.10659262537956238,
|
|
"num_tokens": 322855.0,
|
|
"step": 185
|
|
},
|
|
{
|
|
"entropy": 7.308965826034546,
|
|
"epoch": 0.014783116125267459,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 9.45e-05,
|
|
"loss": 6.9864,
|
|
"mean_token_accuracy": 0.10101070180535317,
|
|
"num_tokens": 332071.0,
|
|
"step": 190
|
|
},
|
|
{
|
|
"entropy": 7.14015564918518,
|
|
"epoch": 0.015172145496985022,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 9.7e-05,
|
|
"loss": 6.7852,
|
|
"mean_token_accuracy": 0.11069764196872711,
|
|
"num_tokens": 339990.0,
|
|
"step": 195
|
|
},
|
|
{
|
|
"entropy": 7.053653430938721,
|
|
"epoch": 0.015561174868702588,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 9.95e-05,
|
|
"loss": 6.8539,
|
|
"mean_token_accuracy": 0.10288179665803909,
|
|
"num_tokens": 348581.0,
|
|
"step": 200
|
|
},
|
|
{
|
|
"entropy": 7.240718221664428,
|
|
"epoch": 0.01595020424042015,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.000102,
|
|
"loss": 6.833,
|
|
"mean_token_accuracy": 0.10342259332537651,
|
|
"num_tokens": 357032.0,
|
|
"step": 205
|
|
},
|
|
{
|
|
"entropy": 7.196627473831176,
|
|
"epoch": 0.016339233612137717,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00010449999999999999,
|
|
"loss": 6.8178,
|
|
"mean_token_accuracy": 0.1009693332016468,
|
|
"num_tokens": 366562.0,
|
|
"step": 210
|
|
},
|
|
{
|
|
"entropy": 7.165555238723755,
|
|
"epoch": 0.016728262983855283,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.000107,
|
|
"loss": 6.8395,
|
|
"mean_token_accuracy": 0.10268025025725365,
|
|
"num_tokens": 374555.0,
|
|
"step": 215
|
|
},
|
|
{
|
|
"entropy": 7.192792892456055,
|
|
"epoch": 0.017117292355572845,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0001095,
|
|
"loss": 6.8655,
|
|
"mean_token_accuracy": 0.09840265959501267,
|
|
"num_tokens": 383583.0,
|
|
"step": 220
|
|
},
|
|
{
|
|
"entropy": 7.192580223083496,
|
|
"epoch": 0.01750632172729041,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.000112,
|
|
"loss": 6.9331,
|
|
"mean_token_accuracy": 0.10320700556039811,
|
|
"num_tokens": 392932.0,
|
|
"step": 225
|
|
},
|
|
{
|
|
"entropy": 7.128038835525513,
|
|
"epoch": 0.017895351099007976,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0001145,
|
|
"loss": 6.7238,
|
|
"mean_token_accuracy": 0.1055540271103382,
|
|
"num_tokens": 401653.0,
|
|
"step": 230
|
|
},
|
|
{
|
|
"entropy": 7.176790475845337,
|
|
"epoch": 0.01828438047072554,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00011700000000000001,
|
|
"loss": 6.849,
|
|
"mean_token_accuracy": 0.10869463607668876,
|
|
"num_tokens": 410432.0,
|
|
"step": 235
|
|
},
|
|
{
|
|
"entropy": 7.117323780059815,
|
|
"epoch": 0.018673409842443103,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00011949999999999999,
|
|
"loss": 6.8508,
|
|
"mean_token_accuracy": 0.09773495495319366,
|
|
"num_tokens": 419380.0,
|
|
"step": 240
|
|
},
|
|
{
|
|
"entropy": 7.0996729850769045,
|
|
"epoch": 0.01906243921416067,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.000122,
|
|
"loss": 6.7189,
|
|
"mean_token_accuracy": 0.10773764923214912,
|
|
"num_tokens": 427682.0,
|
|
"step": 245
|
|
},
|
|
{
|
|
"entropy": 7.116600799560547,
|
|
"epoch": 0.019451468585878234,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0001245,
|
|
"loss": 6.8466,
|
|
"mean_token_accuracy": 0.0980540618300438,
|
|
"num_tokens": 437708.0,
|
|
"step": 250
|
|
},
|
|
{
|
|
"entropy": 7.2894528865814205,
|
|
"epoch": 0.0198404979575958,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.000127,
|
|
"loss": 6.834,
|
|
"mean_token_accuracy": 0.10421091094613075,
|
|
"num_tokens": 446480.0,
|
|
"step": 255
|
|
},
|
|
{
|
|
"entropy": 7.118760585784912,
|
|
"epoch": 0.020229527329313362,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0001295,
|
|
"loss": 6.8561,
|
|
"mean_token_accuracy": 0.09987496063113213,
|
|
"num_tokens": 455273.0,
|
|
"step": 260
|
|
},
|
|
{
|
|
"entropy": 7.136530256271362,
|
|
"epoch": 0.020618556701030927,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.000132,
|
|
"loss": 6.7749,
|
|
"mean_token_accuracy": 0.10336558893322945,
|
|
"num_tokens": 464306.0,
|
|
"step": 265
|
|
},
|
|
{
|
|
"entropy": 7.040481853485107,
|
|
"epoch": 0.021007586072748493,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00013450000000000002,
|
|
"loss": 6.7841,
|
|
"mean_token_accuracy": 0.10204348638653755,
|
|
"num_tokens": 472812.0,
|
|
"step": 270
|
|
},
|
|
{
|
|
"entropy": 7.163069248199463,
|
|
"epoch": 0.02139661544446606,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00013700000000000002,
|
|
"loss": 6.7543,
|
|
"mean_token_accuracy": 0.10701820924878121,
|
|
"num_tokens": 481326.0,
|
|
"step": 275
|
|
},
|
|
{
|
|
"entropy": 7.119368600845337,
|
|
"epoch": 0.02178564481618362,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0001395,
|
|
"loss": 6.7243,
|
|
"mean_token_accuracy": 0.11118735149502754,
|
|
"num_tokens": 489147.0,
|
|
"step": 280
|
|
},
|
|
{
|
|
"entropy": 7.089112567901611,
|
|
"epoch": 0.022174674187901186,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.00014199999999999998,
|
|
"loss": 6.7413,
|
|
"mean_token_accuracy": 0.11033984646201134,
|
|
"num_tokens": 497455.0,
|
|
"step": 285
|
|
},
|
|
{
|
|
"entropy": 7.104836559295654,
|
|
"epoch": 0.02256370355961875,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0001445,
|
|
"loss": 6.6422,
|
|
"mean_token_accuracy": 0.10569282323122024,
|
|
"num_tokens": 506735.0,
|
|
"step": 290
|
|
},
|
|
{
|
|
"entropy": 7.0384293556213375,
|
|
"epoch": 0.022952732931336317,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.000147,
|
|
"loss": 6.7742,
|
|
"mean_token_accuracy": 0.10101545751094818,
|
|
"num_tokens": 515976.0,
|
|
"step": 295
|
|
},
|
|
{
|
|
"entropy": 7.085999059677124,
|
|
"epoch": 0.02334176230305388,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0001495,
|
|
"loss": 6.7517,
|
|
"mean_token_accuracy": 0.10693740099668503,
|
|
"num_tokens": 524986.0,
|
|
"step": 300
|
|
},
|
|
{
|
|
"entropy": 7.115248680114746,
|
|
"epoch": 0.023730791674771445,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.000152,
|
|
"loss": 6.77,
|
|
"mean_token_accuracy": 0.11312920972704887,
|
|
"num_tokens": 533146.0,
|
|
"step": 305
|
|
},
|
|
{
|
|
"entropy": 7.129676389694214,
|
|
"epoch": 0.02411982104648901,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00015450000000000001,
|
|
"loss": 6.6718,
|
|
"mean_token_accuracy": 0.11189078763127328,
|
|
"num_tokens": 541704.0,
|
|
"step": 310
|
|
},
|
|
{
|
|
"entropy": 6.9109279155731205,
|
|
"epoch": 0.024508850418206576,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.000157,
|
|
"loss": 6.6622,
|
|
"mean_token_accuracy": 0.11041900888085365,
|
|
"num_tokens": 550088.0,
|
|
"step": 315
|
|
},
|
|
{
|
|
"entropy": 7.081881046295166,
|
|
"epoch": 0.024897879789924138,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0001595,
|
|
"loss": 6.6645,
|
|
"mean_token_accuracy": 0.10930225849151612,
|
|
"num_tokens": 558763.0,
|
|
"step": 320
|
|
},
|
|
{
|
|
"entropy": 7.069768810272217,
|
|
"epoch": 0.025286909161641703,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.000162,
|
|
"loss": 6.7878,
|
|
"mean_token_accuracy": 0.10328762009739875,
|
|
"num_tokens": 567538.0,
|
|
"step": 325
|
|
},
|
|
{
|
|
"entropy": 7.069195127487182,
|
|
"epoch": 0.02567593853335927,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00016450000000000001,
|
|
"loss": 6.7761,
|
|
"mean_token_accuracy": 0.09954275414347649,
|
|
"num_tokens": 577626.0,
|
|
"step": 330
|
|
},
|
|
{
|
|
"entropy": 7.028294038772583,
|
|
"epoch": 0.026064967905076834,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00016700000000000002,
|
|
"loss": 6.7438,
|
|
"mean_token_accuracy": 0.09985075891017914,
|
|
"num_tokens": 587163.0,
|
|
"step": 335
|
|
},
|
|
{
|
|
"entropy": 7.067160749435425,
|
|
"epoch": 0.026453997276794396,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00016950000000000003,
|
|
"loss": 6.709,
|
|
"mean_token_accuracy": 0.10794477462768555,
|
|
"num_tokens": 595896.0,
|
|
"step": 340
|
|
},
|
|
{
|
|
"entropy": 7.129930925369263,
|
|
"epoch": 0.026843026648511962,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00017199999999999998,
|
|
"loss": 6.7398,
|
|
"mean_token_accuracy": 0.10768290907144547,
|
|
"num_tokens": 603815.0,
|
|
"step": 345
|
|
},
|
|
{
|
|
"entropy": 7.144747066497803,
|
|
"epoch": 0.027232056020229527,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.00017449999999999999,
|
|
"loss": 6.7651,
|
|
"mean_token_accuracy": 0.10645536631345749,
|
|
"num_tokens": 612208.0,
|
|
"step": 350
|
|
},
|
|
{
|
|
"entropy": 6.967557144165039,
|
|
"epoch": 0.027621085391947093,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.000177,
|
|
"loss": 6.7364,
|
|
"mean_token_accuracy": 0.10606642588973045,
|
|
"num_tokens": 621840.0,
|
|
"step": 355
|
|
},
|
|
{
|
|
"entropy": 7.141417503356934,
|
|
"epoch": 0.028010114763664655,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0001795,
|
|
"loss": 6.754,
|
|
"mean_token_accuracy": 0.10428969785571099,
|
|
"num_tokens": 630770.0,
|
|
"step": 360
|
|
},
|
|
{
|
|
"entropy": 7.057492446899414,
|
|
"epoch": 0.02839914413538222,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.000182,
|
|
"loss": 6.765,
|
|
"mean_token_accuracy": 0.10178582295775414,
|
|
"num_tokens": 640313.0,
|
|
"step": 365
|
|
},
|
|
{
|
|
"entropy": 7.117184162139893,
|
|
"epoch": 0.028788173507099786,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0001845,
|
|
"loss": 6.7728,
|
|
"mean_token_accuracy": 0.10945857390761375,
|
|
"num_tokens": 648594.0,
|
|
"step": 370
|
|
},
|
|
{
|
|
"entropy": 7.09682297706604,
|
|
"epoch": 0.02917720287881735,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.000187,
|
|
"loss": 6.7801,
|
|
"mean_token_accuracy": 0.10975684225559235,
|
|
"num_tokens": 656478.0,
|
|
"step": 375
|
|
},
|
|
{
|
|
"entropy": 7.008049154281617,
|
|
"epoch": 0.029566232250534917,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0001895,
|
|
"loss": 6.7466,
|
|
"mean_token_accuracy": 0.11092364862561226,
|
|
"num_tokens": 665405.0,
|
|
"step": 380
|
|
},
|
|
{
|
|
"entropy": 7.129104042053223,
|
|
"epoch": 0.02995526162225248,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.000192,
|
|
"loss": 6.7893,
|
|
"mean_token_accuracy": 0.10336535945534706,
|
|
"num_tokens": 674301.0,
|
|
"step": 385
|
|
},
|
|
{
|
|
"entropy": 7.0760479927062985,
|
|
"epoch": 0.030344290993970045,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0001945,
|
|
"loss": 6.7965,
|
|
"mean_token_accuracy": 0.10536759793758392,
|
|
"num_tokens": 683159.0,
|
|
"step": 390
|
|
},
|
|
{
|
|
"entropy": 6.909673643112183,
|
|
"epoch": 0.03073332036568761,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00019700000000000002,
|
|
"loss": 6.615,
|
|
"mean_token_accuracy": 0.11728166565299034,
|
|
"num_tokens": 690992.0,
|
|
"step": 395
|
|
},
|
|
{
|
|
"entropy": 7.008391714096069,
|
|
"epoch": 0.031122349737405176,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00019950000000000002,
|
|
"loss": 6.7088,
|
|
"mean_token_accuracy": 0.10719396844506264,
|
|
"num_tokens": 699934.0,
|
|
"step": 400
|
|
},
|
|
{
|
|
"entropy": 7.129413223266601,
|
|
"epoch": 0.03151137910912274,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.000202,
|
|
"loss": 6.7819,
|
|
"mean_token_accuracy": 0.10522214099764823,
|
|
"num_tokens": 708844.0,
|
|
"step": 405
|
|
},
|
|
{
|
|
"entropy": 7.064364719390869,
|
|
"epoch": 0.0319004084808403,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00020449999999999998,
|
|
"loss": 6.8195,
|
|
"mean_token_accuracy": 0.10306548178195954,
|
|
"num_tokens": 718148.0,
|
|
"step": 410
|
|
},
|
|
{
|
|
"entropy": 7.133789825439453,
|
|
"epoch": 0.03228943785255787,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.000207,
|
|
"loss": 6.795,
|
|
"mean_token_accuracy": 0.09738803058862686,
|
|
"num_tokens": 726859.0,
|
|
"step": 415
|
|
},
|
|
{
|
|
"entropy": 7.000170373916626,
|
|
"epoch": 0.032678467224275434,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0002095,
|
|
"loss": 6.7769,
|
|
"mean_token_accuracy": 0.10343157276511192,
|
|
"num_tokens": 735045.0,
|
|
"step": 420
|
|
},
|
|
{
|
|
"entropy": 6.958332872390747,
|
|
"epoch": 0.033067496595993,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.000212,
|
|
"loss": 6.6649,
|
|
"mean_token_accuracy": 0.10745938420295716,
|
|
"num_tokens": 743538.0,
|
|
"step": 425
|
|
},
|
|
{
|
|
"entropy": 7.100725936889648,
|
|
"epoch": 0.033456525967710565,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0002145,
|
|
"loss": 6.7126,
|
|
"mean_token_accuracy": 0.10536539554595947,
|
|
"num_tokens": 752518.0,
|
|
"step": 430
|
|
},
|
|
{
|
|
"entropy": 7.004069709777832,
|
|
"epoch": 0.033845555339428124,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.00021700000000000002,
|
|
"loss": 6.7377,
|
|
"mean_token_accuracy": 0.10655581876635552,
|
|
"num_tokens": 760354.0,
|
|
"step": 435
|
|
},
|
|
{
|
|
"entropy": 6.982064580917358,
|
|
"epoch": 0.03423458471114569,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0002195,
|
|
"loss": 6.7711,
|
|
"mean_token_accuracy": 0.10229354277253151,
|
|
"num_tokens": 769522.0,
|
|
"step": 440
|
|
},
|
|
{
|
|
"entropy": 7.065256071090698,
|
|
"epoch": 0.034623614082863255,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.000222,
|
|
"loss": 6.6997,
|
|
"mean_token_accuracy": 0.11091353893280029,
|
|
"num_tokens": 778548.0,
|
|
"step": 445
|
|
},
|
|
{
|
|
"entropy": 6.934096908569336,
|
|
"epoch": 0.03501264345458082,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0002245,
|
|
"loss": 6.7287,
|
|
"mean_token_accuracy": 0.1053735852241516,
|
|
"num_tokens": 787666.0,
|
|
"step": 450
|
|
},
|
|
{
|
|
"entropy": 7.024951171875,
|
|
"epoch": 0.035401672826298386,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00022700000000000002,
|
|
"loss": 6.6686,
|
|
"mean_token_accuracy": 0.11279149726033211,
|
|
"num_tokens": 796550.0,
|
|
"step": 455
|
|
},
|
|
{
|
|
"entropy": 7.041475820541382,
|
|
"epoch": 0.03579070219801595,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.00022950000000000002,
|
|
"loss": 6.75,
|
|
"mean_token_accuracy": 0.10563758090138435,
|
|
"num_tokens": 804549.0,
|
|
"step": 460
|
|
},
|
|
{
|
|
"entropy": 6.950169038772583,
|
|
"epoch": 0.03617973156973352,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00023200000000000003,
|
|
"loss": 6.712,
|
|
"mean_token_accuracy": 0.10642848908901215,
|
|
"num_tokens": 813328.0,
|
|
"step": 465
|
|
},
|
|
{
|
|
"entropy": 7.018851613998413,
|
|
"epoch": 0.03656876094145108,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00023449999999999998,
|
|
"loss": 6.7383,
|
|
"mean_token_accuracy": 0.10269406661391259,
|
|
"num_tokens": 821733.0,
|
|
"step": 470
|
|
},
|
|
{
|
|
"entropy": 7.025096035003662,
|
|
"epoch": 0.03695779031316864,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.000237,
|
|
"loss": 6.6845,
|
|
"mean_token_accuracy": 0.1043982096016407,
|
|
"num_tokens": 830243.0,
|
|
"step": 475
|
|
},
|
|
{
|
|
"entropy": 6.983623695373535,
|
|
"epoch": 0.03734681968488621,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0002395,
|
|
"loss": 6.6809,
|
|
"mean_token_accuracy": 0.10531210973858833,
|
|
"num_tokens": 839059.0,
|
|
"step": 480
|
|
},
|
|
{
|
|
"entropy": 6.874166250228882,
|
|
"epoch": 0.03773584905660377,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.000242,
|
|
"loss": 6.571,
|
|
"mean_token_accuracy": 0.1156509980559349,
|
|
"num_tokens": 846932.0,
|
|
"step": 485
|
|
},
|
|
{
|
|
"entropy": 7.06893572807312,
|
|
"epoch": 0.03812487842832134,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0002445,
|
|
"loss": 6.7823,
|
|
"mean_token_accuracy": 0.10051146373152733,
|
|
"num_tokens": 855333.0,
|
|
"step": 490
|
|
},
|
|
{
|
|
"entropy": 6.859884548187256,
|
|
"epoch": 0.0385139078000389,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.000247,
|
|
"loss": 6.533,
|
|
"mean_token_accuracy": 0.11017489805817604,
|
|
"num_tokens": 863571.0,
|
|
"step": 495
|
|
},
|
|
{
|
|
"entropy": 6.848187637329102,
|
|
"epoch": 0.03890293717175647,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0002495,
|
|
"loss": 6.6446,
|
|
"mean_token_accuracy": 0.11741312965750694,
|
|
"num_tokens": 872145.0,
|
|
"step": 500
|
|
},
|
|
{
|
|
"entropy": 6.888921165466309,
|
|
"epoch": 0.039291966543474034,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.000252,
|
|
"loss": 6.6846,
|
|
"mean_token_accuracy": 0.10648975148797035,
|
|
"num_tokens": 880634.0,
|
|
"step": 505
|
|
},
|
|
{
|
|
"entropy": 7.030638742446899,
|
|
"epoch": 0.0396809959151916,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0002545,
|
|
"loss": 6.621,
|
|
"mean_token_accuracy": 0.11071762889623642,
|
|
"num_tokens": 889178.0,
|
|
"step": 510
|
|
},
|
|
{
|
|
"entropy": 6.857705116271973,
|
|
"epoch": 0.04007002528690916,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.000257,
|
|
"loss": 6.64,
|
|
"mean_token_accuracy": 0.10953132063150406,
|
|
"num_tokens": 898255.0,
|
|
"step": 515
|
|
},
|
|
{
|
|
"entropy": 6.880079555511474,
|
|
"epoch": 0.040459054658626724,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0002595,
|
|
"loss": 6.7049,
|
|
"mean_token_accuracy": 0.1003771848976612,
|
|
"num_tokens": 907369.0,
|
|
"step": 520
|
|
},
|
|
{
|
|
"entropy": 6.928122329711914,
|
|
"epoch": 0.04084808403034429,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.000262,
|
|
"loss": 6.5786,
|
|
"mean_token_accuracy": 0.10770422816276551,
|
|
"num_tokens": 915946.0,
|
|
"step": 525
|
|
},
|
|
{
|
|
"entropy": 6.915776157379151,
|
|
"epoch": 0.041237113402061855,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00026450000000000003,
|
|
"loss": 6.6434,
|
|
"mean_token_accuracy": 0.10492169335484505,
|
|
"num_tokens": 925579.0,
|
|
"step": 530
|
|
},
|
|
{
|
|
"entropy": 6.934671211242676,
|
|
"epoch": 0.04162614277377942,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00026700000000000004,
|
|
"loss": 6.6488,
|
|
"mean_token_accuracy": 0.09940063878893853,
|
|
"num_tokens": 934732.0,
|
|
"step": 535
|
|
},
|
|
{
|
|
"entropy": 6.88787875175476,
|
|
"epoch": 0.042015172145496986,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00026950000000000005,
|
|
"loss": 6.7234,
|
|
"mean_token_accuracy": 0.0988178126513958,
|
|
"num_tokens": 943371.0,
|
|
"step": 540
|
|
},
|
|
{
|
|
"entropy": 6.90224323272705,
|
|
"epoch": 0.04240420151721455,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00027200000000000005,
|
|
"loss": 6.5663,
|
|
"mean_token_accuracy": 0.10707596987485886,
|
|
"num_tokens": 951977.0,
|
|
"step": 545
|
|
},
|
|
{
|
|
"entropy": 6.926870918273925,
|
|
"epoch": 0.04279323088893212,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0002745,
|
|
"loss": 6.5627,
|
|
"mean_token_accuracy": 0.11035381406545638,
|
|
"num_tokens": 960474.0,
|
|
"step": 550
|
|
},
|
|
{
|
|
"entropy": 6.9431356430053714,
|
|
"epoch": 0.04318226026064968,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.000277,
|
|
"loss": 6.6804,
|
|
"mean_token_accuracy": 0.10846401676535607,
|
|
"num_tokens": 969823.0,
|
|
"step": 555
|
|
},
|
|
{
|
|
"entropy": 6.909371852874756,
|
|
"epoch": 0.04357128963236724,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0002795,
|
|
"loss": 6.6018,
|
|
"mean_token_accuracy": 0.11796640902757645,
|
|
"num_tokens": 977417.0,
|
|
"step": 560
|
|
},
|
|
{
|
|
"entropy": 6.832342100143433,
|
|
"epoch": 0.04396031900408481,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.00028199999999999997,
|
|
"loss": 6.6171,
|
|
"mean_token_accuracy": 0.11622529998421668,
|
|
"num_tokens": 985519.0,
|
|
"step": 565
|
|
},
|
|
{
|
|
"entropy": 6.898900032043457,
|
|
"epoch": 0.04434934837580237,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0002845,
|
|
"loss": 6.6199,
|
|
"mean_token_accuracy": 0.11711302250623704,
|
|
"num_tokens": 994136.0,
|
|
"step": 570
|
|
},
|
|
{
|
|
"entropy": 6.815031576156616,
|
|
"epoch": 0.04473837774751994,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.000287,
|
|
"loss": 6.5923,
|
|
"mean_token_accuracy": 0.10916913151741028,
|
|
"num_tokens": 1002896.0,
|
|
"step": 575
|
|
},
|
|
{
|
|
"entropy": 6.979454898834229,
|
|
"epoch": 0.0451274071192375,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0002895,
|
|
"loss": 6.6758,
|
|
"mean_token_accuracy": 0.1161210797727108,
|
|
"num_tokens": 1011032.0,
|
|
"step": 580
|
|
},
|
|
{
|
|
"entropy": 6.81922025680542,
|
|
"epoch": 0.04551643649095507,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.000292,
|
|
"loss": 6.6441,
|
|
"mean_token_accuracy": 0.1030525617301464,
|
|
"num_tokens": 1019901.0,
|
|
"step": 585
|
|
},
|
|
{
|
|
"entropy": 6.864784288406372,
|
|
"epoch": 0.045905465862672634,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0002945,
|
|
"loss": 6.6474,
|
|
"mean_token_accuracy": 0.10804857909679413,
|
|
"num_tokens": 1029049.0,
|
|
"step": 590
|
|
},
|
|
{
|
|
"entropy": 6.756793975830078,
|
|
"epoch": 0.0462944952343902,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.000297,
|
|
"loss": 6.6037,
|
|
"mean_token_accuracy": 0.11960037648677826,
|
|
"num_tokens": 1037580.0,
|
|
"step": 595
|
|
},
|
|
{
|
|
"entropy": 6.98903341293335,
|
|
"epoch": 0.04668352460610776,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0002995,
|
|
"loss": 6.662,
|
|
"mean_token_accuracy": 0.1088825561106205,
|
|
"num_tokens": 1045804.0,
|
|
"step": 600
|
|
},
|
|
{
|
|
"entropy": 6.917456436157226,
|
|
"epoch": 0.047072553977825324,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.000302,
|
|
"loss": 6.6229,
|
|
"mean_token_accuracy": 0.10497673898935318,
|
|
"num_tokens": 1054719.0,
|
|
"step": 605
|
|
},
|
|
{
|
|
"entropy": 6.885978698730469,
|
|
"epoch": 0.04746158334954289,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0003045,
|
|
"loss": 6.5963,
|
|
"mean_token_accuracy": 0.11059815883636474,
|
|
"num_tokens": 1063373.0,
|
|
"step": 610
|
|
},
|
|
{
|
|
"entropy": 6.785440397262573,
|
|
"epoch": 0.047850612721260455,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.000307,
|
|
"loss": 6.5989,
|
|
"mean_token_accuracy": 0.11273155137896537,
|
|
"num_tokens": 1073021.0,
|
|
"step": 615
|
|
},
|
|
{
|
|
"entropy": 6.882770442962647,
|
|
"epoch": 0.04823964209297802,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0003095,
|
|
"loss": 6.6801,
|
|
"mean_token_accuracy": 0.1019173502922058,
|
|
"num_tokens": 1081547.0,
|
|
"step": 620
|
|
},
|
|
{
|
|
"entropy": 6.782485437393189,
|
|
"epoch": 0.048628671464695586,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.000312,
|
|
"loss": 6.6188,
|
|
"mean_token_accuracy": 0.10811661779880524,
|
|
"num_tokens": 1090695.0,
|
|
"step": 625
|
|
},
|
|
{
|
|
"entropy": 6.83217978477478,
|
|
"epoch": 0.04901770083641315,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0003145,
|
|
"loss": 6.5245,
|
|
"mean_token_accuracy": 0.11375772655010223,
|
|
"num_tokens": 1099563.0,
|
|
"step": 630
|
|
},
|
|
{
|
|
"entropy": 6.812391328811645,
|
|
"epoch": 0.04940673020813072,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.000317,
|
|
"loss": 6.5983,
|
|
"mean_token_accuracy": 0.106151232868433,
|
|
"num_tokens": 1109021.0,
|
|
"step": 635
|
|
},
|
|
{
|
|
"entropy": 6.875996255874634,
|
|
"epoch": 0.049795759579848276,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0003195,
|
|
"loss": 6.5918,
|
|
"mean_token_accuracy": 0.11454840824007988,
|
|
"num_tokens": 1118281.0,
|
|
"step": 640
|
|
},
|
|
{
|
|
"entropy": 6.812969303131103,
|
|
"epoch": 0.05018478895156584,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.000322,
|
|
"loss": 6.6272,
|
|
"mean_token_accuracy": 0.1035926029086113,
|
|
"num_tokens": 1127513.0,
|
|
"step": 645
|
|
},
|
|
{
|
|
"entropy": 6.718197965621949,
|
|
"epoch": 0.05057381832328341,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00032450000000000003,
|
|
"loss": 6.5164,
|
|
"mean_token_accuracy": 0.1071177065372467,
|
|
"num_tokens": 1136140.0,
|
|
"step": 650
|
|
},
|
|
{
|
|
"entropy": 6.824093341827393,
|
|
"epoch": 0.05096284769500097,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00032700000000000003,
|
|
"loss": 6.5399,
|
|
"mean_token_accuracy": 0.11261795312166215,
|
|
"num_tokens": 1144297.0,
|
|
"step": 655
|
|
},
|
|
{
|
|
"entropy": 6.786455917358398,
|
|
"epoch": 0.05135187706671854,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.00032950000000000004,
|
|
"loss": 6.6246,
|
|
"mean_token_accuracy": 0.10621164217591286,
|
|
"num_tokens": 1153639.0,
|
|
"step": 660
|
|
},
|
|
{
|
|
"entropy": 6.834279251098633,
|
|
"epoch": 0.0517409064384361,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00033200000000000005,
|
|
"loss": 6.5946,
|
|
"mean_token_accuracy": 0.10733903646469116,
|
|
"num_tokens": 1162825.0,
|
|
"step": 665
|
|
},
|
|
{
|
|
"entropy": 6.83927812576294,
|
|
"epoch": 0.05212993581015367,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00033450000000000005,
|
|
"loss": 6.6254,
|
|
"mean_token_accuracy": 0.11359924152493477,
|
|
"num_tokens": 1171887.0,
|
|
"step": 670
|
|
},
|
|
{
|
|
"entropy": 6.77231502532959,
|
|
"epoch": 0.052518965181871234,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.000337,
|
|
"loss": 6.5268,
|
|
"mean_token_accuracy": 0.1123774453997612,
|
|
"num_tokens": 1179963.0,
|
|
"step": 675
|
|
},
|
|
{
|
|
"entropy": 6.7494322776794435,
|
|
"epoch": 0.05290799455358879,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0003395,
|
|
"loss": 6.504,
|
|
"mean_token_accuracy": 0.11874646693468094,
|
|
"num_tokens": 1188408.0,
|
|
"step": 680
|
|
},
|
|
{
|
|
"entropy": 6.759702253341675,
|
|
"epoch": 0.05329702392530636,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.000342,
|
|
"loss": 6.5643,
|
|
"mean_token_accuracy": 0.1101931869983673,
|
|
"num_tokens": 1197751.0,
|
|
"step": 685
|
|
},
|
|
{
|
|
"entropy": 6.77538800239563,
|
|
"epoch": 0.053686053297023924,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00034449999999999997,
|
|
"loss": 6.6178,
|
|
"mean_token_accuracy": 0.10692482218146324,
|
|
"num_tokens": 1207101.0,
|
|
"step": 690
|
|
},
|
|
{
|
|
"entropy": 6.792410135269165,
|
|
"epoch": 0.05407508266874149,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000347,
|
|
"loss": 6.5926,
|
|
"mean_token_accuracy": 0.11028107032179832,
|
|
"num_tokens": 1216395.0,
|
|
"step": 695
|
|
},
|
|
{
|
|
"entropy": 6.769010829925537,
|
|
"epoch": 0.054464112040459055,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0003495,
|
|
"loss": 6.578,
|
|
"mean_token_accuracy": 0.1123175047338009,
|
|
"num_tokens": 1225496.0,
|
|
"step": 700
|
|
},
|
|
{
|
|
"entropy": 6.8211222171783445,
|
|
"epoch": 0.05485314141217662,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.000352,
|
|
"loss": 6.6649,
|
|
"mean_token_accuracy": 0.10871831476688384,
|
|
"num_tokens": 1233934.0,
|
|
"step": 705
|
|
},
|
|
{
|
|
"entropy": 6.785651206970215,
|
|
"epoch": 0.055242170783894186,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0003545,
|
|
"loss": 6.4982,
|
|
"mean_token_accuracy": 0.11507153287529945,
|
|
"num_tokens": 1242165.0,
|
|
"step": 710
|
|
},
|
|
{
|
|
"entropy": 6.7908707618713375,
|
|
"epoch": 0.05563120015561175,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.000357,
|
|
"loss": 6.582,
|
|
"mean_token_accuracy": 0.11247257515788078,
|
|
"num_tokens": 1250021.0,
|
|
"step": 715
|
|
},
|
|
{
|
|
"entropy": 6.806695175170899,
|
|
"epoch": 0.05602022952732931,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0003595,
|
|
"loss": 6.5923,
|
|
"mean_token_accuracy": 0.10604929178953171,
|
|
"num_tokens": 1258397.0,
|
|
"step": 720
|
|
},
|
|
{
|
|
"entropy": 6.7257074356079105,
|
|
"epoch": 0.056409258899046875,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.000362,
|
|
"loss": 6.5913,
|
|
"mean_token_accuracy": 0.10682924762368202,
|
|
"num_tokens": 1266764.0,
|
|
"step": 725
|
|
},
|
|
{
|
|
"entropy": 6.814504814147949,
|
|
"epoch": 0.05679828827076444,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0003645,
|
|
"loss": 6.5776,
|
|
"mean_token_accuracy": 0.10827752500772476,
|
|
"num_tokens": 1275643.0,
|
|
"step": 730
|
|
},
|
|
{
|
|
"entropy": 6.735859632492065,
|
|
"epoch": 0.057187317642482006,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.000367,
|
|
"loss": 6.548,
|
|
"mean_token_accuracy": 0.10943838953971863,
|
|
"num_tokens": 1284379.0,
|
|
"step": 735
|
|
},
|
|
{
|
|
"entropy": 6.693990755081177,
|
|
"epoch": 0.05757634701419957,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0003695,
|
|
"loss": 6.4186,
|
|
"mean_token_accuracy": 0.11652168333530426,
|
|
"num_tokens": 1293115.0,
|
|
"step": 740
|
|
},
|
|
{
|
|
"entropy": 6.756194734573365,
|
|
"epoch": 0.05796537638591714,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.000372,
|
|
"loss": 6.6259,
|
|
"mean_token_accuracy": 0.10827576220035554,
|
|
"num_tokens": 1301583.0,
|
|
"step": 745
|
|
},
|
|
{
|
|
"entropy": 6.813287878036499,
|
|
"epoch": 0.0583544057576347,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0003745,
|
|
"loss": 6.5331,
|
|
"mean_token_accuracy": 0.1124935545027256,
|
|
"num_tokens": 1310721.0,
|
|
"step": 750
|
|
},
|
|
{
|
|
"entropy": 6.780404138565063,
|
|
"epoch": 0.05874343512935227,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.000377,
|
|
"loss": 6.6926,
|
|
"mean_token_accuracy": 0.10063973814249039,
|
|
"num_tokens": 1319056.0,
|
|
"step": 755
|
|
},
|
|
{
|
|
"entropy": 6.718628644943237,
|
|
"epoch": 0.059132464501069834,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0003795,
|
|
"loss": 6.5705,
|
|
"mean_token_accuracy": 0.11318051740527153,
|
|
"num_tokens": 1327259.0,
|
|
"step": 760
|
|
},
|
|
{
|
|
"entropy": 6.667355155944824,
|
|
"epoch": 0.05952149387278739,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.000382,
|
|
"loss": 6.4715,
|
|
"mean_token_accuracy": 0.1107344388961792,
|
|
"num_tokens": 1335906.0,
|
|
"step": 765
|
|
},
|
|
{
|
|
"entropy": 6.738911390304565,
|
|
"epoch": 0.05991052324450496,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0003845,
|
|
"loss": 6.5202,
|
|
"mean_token_accuracy": 0.1040088415145874,
|
|
"num_tokens": 1344743.0,
|
|
"step": 770
|
|
},
|
|
{
|
|
"entropy": 6.700624132156372,
|
|
"epoch": 0.060299552616222524,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00038700000000000003,
|
|
"loss": 6.5224,
|
|
"mean_token_accuracy": 0.11556991934776306,
|
|
"num_tokens": 1353211.0,
|
|
"step": 775
|
|
},
|
|
{
|
|
"entropy": 6.810952758789062,
|
|
"epoch": 0.06068858198794009,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00038950000000000003,
|
|
"loss": 6.6387,
|
|
"mean_token_accuracy": 0.105211191624403,
|
|
"num_tokens": 1361849.0,
|
|
"step": 780
|
|
},
|
|
{
|
|
"entropy": 6.766528463363647,
|
|
"epoch": 0.061077611359657655,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.00039200000000000004,
|
|
"loss": 6.6322,
|
|
"mean_token_accuracy": 0.11231314763426781,
|
|
"num_tokens": 1369804.0,
|
|
"step": 785
|
|
},
|
|
{
|
|
"entropy": 6.6204534530639645,
|
|
"epoch": 0.06146664073137522,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00039450000000000005,
|
|
"loss": 6.4105,
|
|
"mean_token_accuracy": 0.11438998207449913,
|
|
"num_tokens": 1378478.0,
|
|
"step": 790
|
|
},
|
|
{
|
|
"entropy": 6.721090173721313,
|
|
"epoch": 0.061855670103092786,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00039700000000000005,
|
|
"loss": 6.5198,
|
|
"mean_token_accuracy": 0.11511333733797073,
|
|
"num_tokens": 1387225.0,
|
|
"step": 795
|
|
},
|
|
{
|
|
"entropy": 6.5949059009552,
|
|
"epoch": 0.06224469947481035,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0003995,
|
|
"loss": 6.4886,
|
|
"mean_token_accuracy": 0.11483033820986747,
|
|
"num_tokens": 1395338.0,
|
|
"step": 800
|
|
},
|
|
{
|
|
"entropy": 6.733497905731201,
|
|
"epoch": 0.06263372884652792,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.000402,
|
|
"loss": 6.4699,
|
|
"mean_token_accuracy": 0.11658778935670852,
|
|
"num_tokens": 1403794.0,
|
|
"step": 805
|
|
},
|
|
{
|
|
"entropy": 6.569311475753784,
|
|
"epoch": 0.06302275821824548,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004045,
|
|
"loss": 6.5601,
|
|
"mean_token_accuracy": 0.10899760574102402,
|
|
"num_tokens": 1412522.0,
|
|
"step": 810
|
|
},
|
|
{
|
|
"entropy": 6.656661939620972,
|
|
"epoch": 0.06341178758996305,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00040699999999999997,
|
|
"loss": 6.5467,
|
|
"mean_token_accuracy": 0.11179601773619652,
|
|
"num_tokens": 1421347.0,
|
|
"step": 815
|
|
},
|
|
{
|
|
"entropy": 6.727706336975098,
|
|
"epoch": 0.0638008169616806,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004095,
|
|
"loss": 6.5196,
|
|
"mean_token_accuracy": 0.11865966618061066,
|
|
"num_tokens": 1429788.0,
|
|
"step": 820
|
|
},
|
|
{
|
|
"entropy": 6.661208915710449,
|
|
"epoch": 0.06418984633339817,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.000412,
|
|
"loss": 6.5204,
|
|
"mean_token_accuracy": 0.11378848180174828,
|
|
"num_tokens": 1437442.0,
|
|
"step": 825
|
|
},
|
|
{
|
|
"entropy": 6.629270458221436,
|
|
"epoch": 0.06457887570511574,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004145,
|
|
"loss": 6.454,
|
|
"mean_token_accuracy": 0.11606807261705399,
|
|
"num_tokens": 1445604.0,
|
|
"step": 830
|
|
},
|
|
{
|
|
"entropy": 6.6420129299163815,
|
|
"epoch": 0.0649679050768333,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.000417,
|
|
"loss": 6.5193,
|
|
"mean_token_accuracy": 0.11452969834208489,
|
|
"num_tokens": 1454342.0,
|
|
"step": 835
|
|
},
|
|
{
|
|
"entropy": 6.6732264995574955,
|
|
"epoch": 0.06535693444855087,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004195,
|
|
"loss": 6.4938,
|
|
"mean_token_accuracy": 0.11808337047696113,
|
|
"num_tokens": 1463189.0,
|
|
"step": 840
|
|
},
|
|
{
|
|
"entropy": 6.653149843215942,
|
|
"epoch": 0.06574596382026843,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.000422,
|
|
"loss": 6.567,
|
|
"mean_token_accuracy": 0.11128631979227066,
|
|
"num_tokens": 1471608.0,
|
|
"step": 845
|
|
},
|
|
{
|
|
"entropy": 6.708612298965454,
|
|
"epoch": 0.066134993191986,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004245,
|
|
"loss": 6.5916,
|
|
"mean_token_accuracy": 0.11057313457131386,
|
|
"num_tokens": 1480452.0,
|
|
"step": 850
|
|
},
|
|
{
|
|
"entropy": 6.737775611877441,
|
|
"epoch": 0.06652402256370356,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.000427,
|
|
"loss": 6.4918,
|
|
"mean_token_accuracy": 0.11269054412841797,
|
|
"num_tokens": 1489118.0,
|
|
"step": 855
|
|
},
|
|
{
|
|
"entropy": 6.569603490829468,
|
|
"epoch": 0.06691305193542113,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004295,
|
|
"loss": 6.4927,
|
|
"mean_token_accuracy": 0.11193603426218032,
|
|
"num_tokens": 1498961.0,
|
|
"step": 860
|
|
},
|
|
{
|
|
"entropy": 6.6935163021087645,
|
|
"epoch": 0.06730208130713869,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.000432,
|
|
"loss": 6.4926,
|
|
"mean_token_accuracy": 0.1153524398803711,
|
|
"num_tokens": 1506772.0,
|
|
"step": 865
|
|
},
|
|
{
|
|
"entropy": 6.575390958786011,
|
|
"epoch": 0.06769111067885625,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004345,
|
|
"loss": 6.3711,
|
|
"mean_token_accuracy": 0.1255640558898449,
|
|
"num_tokens": 1515095.0,
|
|
"step": 870
|
|
},
|
|
{
|
|
"entropy": 6.487689113616943,
|
|
"epoch": 0.06808014005057382,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.000437,
|
|
"loss": 6.4268,
|
|
"mean_token_accuracy": 0.1207929216325283,
|
|
"num_tokens": 1523477.0,
|
|
"step": 875
|
|
},
|
|
{
|
|
"entropy": 6.609137725830078,
|
|
"epoch": 0.06846916942229138,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004395,
|
|
"loss": 6.4622,
|
|
"mean_token_accuracy": 0.1122494988143444,
|
|
"num_tokens": 1531786.0,
|
|
"step": 880
|
|
},
|
|
{
|
|
"entropy": 6.577953720092774,
|
|
"epoch": 0.06885819879400895,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.000442,
|
|
"loss": 6.5698,
|
|
"mean_token_accuracy": 0.10728892683982849,
|
|
"num_tokens": 1540737.0,
|
|
"step": 885
|
|
},
|
|
{
|
|
"entropy": 6.563678646087647,
|
|
"epoch": 0.06924722816572651,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004445,
|
|
"loss": 6.4067,
|
|
"mean_token_accuracy": 0.11786556467413903,
|
|
"num_tokens": 1548923.0,
|
|
"step": 890
|
|
},
|
|
{
|
|
"entropy": 6.6591590404510494,
|
|
"epoch": 0.06963625753744408,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.000447,
|
|
"loss": 6.3772,
|
|
"mean_token_accuracy": 0.12245090380311012,
|
|
"num_tokens": 1557043.0,
|
|
"step": 895
|
|
},
|
|
{
|
|
"entropy": 6.425973224639892,
|
|
"epoch": 0.07002528690916164,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00044950000000000003,
|
|
"loss": 6.3948,
|
|
"mean_token_accuracy": 0.12184141874313355,
|
|
"num_tokens": 1564994.0,
|
|
"step": 900
|
|
},
|
|
{
|
|
"entropy": 6.621947193145752,
|
|
"epoch": 0.0704143162808792,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00045200000000000004,
|
|
"loss": 6.4341,
|
|
"mean_token_accuracy": 0.11552446261048317,
|
|
"num_tokens": 1573859.0,
|
|
"step": 905
|
|
},
|
|
{
|
|
"entropy": 6.558233118057251,
|
|
"epoch": 0.07080334565259677,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00045450000000000004,
|
|
"loss": 6.3795,
|
|
"mean_token_accuracy": 0.11174411922693253,
|
|
"num_tokens": 1581947.0,
|
|
"step": 910
|
|
},
|
|
{
|
|
"entropy": 6.501549005508423,
|
|
"epoch": 0.07119237502431433,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00045700000000000005,
|
|
"loss": 6.3598,
|
|
"mean_token_accuracy": 0.11935553029179573,
|
|
"num_tokens": 1589971.0,
|
|
"step": 915
|
|
},
|
|
{
|
|
"entropy": 6.496150875091553,
|
|
"epoch": 0.0715814043960319,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00045950000000000006,
|
|
"loss": 6.3175,
|
|
"mean_token_accuracy": 0.11558070033788681,
|
|
"num_tokens": 1598612.0,
|
|
"step": 920
|
|
},
|
|
{
|
|
"entropy": 6.602824687957764,
|
|
"epoch": 0.07197043376774946,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000462,
|
|
"loss": 6.48,
|
|
"mean_token_accuracy": 0.11538315340876579,
|
|
"num_tokens": 1607378.0,
|
|
"step": 925
|
|
},
|
|
{
|
|
"entropy": 6.50120906829834,
|
|
"epoch": 0.07235946313946703,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004645,
|
|
"loss": 6.4767,
|
|
"mean_token_accuracy": 0.11768107563257217,
|
|
"num_tokens": 1615987.0,
|
|
"step": 930
|
|
},
|
|
{
|
|
"entropy": 6.3998870849609375,
|
|
"epoch": 0.07274849251118459,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.000467,
|
|
"loss": 6.267,
|
|
"mean_token_accuracy": 0.12143187299370765,
|
|
"num_tokens": 1625366.0,
|
|
"step": 935
|
|
},
|
|
{
|
|
"entropy": 6.5568748950958256,
|
|
"epoch": 0.07313752188290217,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004695,
|
|
"loss": 6.4532,
|
|
"mean_token_accuracy": 0.1182747282087803,
|
|
"num_tokens": 1633020.0,
|
|
"step": 940
|
|
},
|
|
{
|
|
"entropy": 6.497894620895385,
|
|
"epoch": 0.07352655125461972,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.000472,
|
|
"loss": 6.3506,
|
|
"mean_token_accuracy": 0.1186905786395073,
|
|
"num_tokens": 1641518.0,
|
|
"step": 945
|
|
},
|
|
{
|
|
"entropy": 6.450480842590332,
|
|
"epoch": 0.07391558062633728,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004745,
|
|
"loss": 6.4345,
|
|
"mean_token_accuracy": 0.11703515127301216,
|
|
"num_tokens": 1650472.0,
|
|
"step": 950
|
|
},
|
|
{
|
|
"entropy": 6.537283897399902,
|
|
"epoch": 0.07430460999805485,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.000477,
|
|
"loss": 6.4607,
|
|
"mean_token_accuracy": 0.11266638338565826,
|
|
"num_tokens": 1659037.0,
|
|
"step": 955
|
|
},
|
|
{
|
|
"entropy": 6.607353210449219,
|
|
"epoch": 0.07469363936977241,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004795,
|
|
"loss": 6.5347,
|
|
"mean_token_accuracy": 0.11601476818323135,
|
|
"num_tokens": 1667897.0,
|
|
"step": 960
|
|
},
|
|
{
|
|
"entropy": 6.535740089416504,
|
|
"epoch": 0.07508266874148999,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000482,
|
|
"loss": 6.3813,
|
|
"mean_token_accuracy": 0.11395608037710189,
|
|
"num_tokens": 1676535.0,
|
|
"step": 965
|
|
},
|
|
{
|
|
"entropy": 6.5092085838317875,
|
|
"epoch": 0.07547169811320754,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004845,
|
|
"loss": 6.4005,
|
|
"mean_token_accuracy": 0.11848380863666534,
|
|
"num_tokens": 1684415.0,
|
|
"step": 970
|
|
},
|
|
{
|
|
"entropy": 6.520880937576294,
|
|
"epoch": 0.07586072748492512,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.000487,
|
|
"loss": 6.3671,
|
|
"mean_token_accuracy": 0.1198020838201046,
|
|
"num_tokens": 1692443.0,
|
|
"step": 975
|
|
},
|
|
{
|
|
"entropy": 6.362412548065185,
|
|
"epoch": 0.07624975685664268,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004895,
|
|
"loss": 6.3659,
|
|
"mean_token_accuracy": 0.1187023714184761,
|
|
"num_tokens": 1700814.0,
|
|
"step": 980
|
|
},
|
|
{
|
|
"entropy": 6.35730767250061,
|
|
"epoch": 0.07663878622836025,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000492,
|
|
"loss": 6.2214,
|
|
"mean_token_accuracy": 0.1248444713652134,
|
|
"num_tokens": 1709591.0,
|
|
"step": 985
|
|
},
|
|
{
|
|
"entropy": 6.486499214172364,
|
|
"epoch": 0.0770278156000778,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004945,
|
|
"loss": 6.4827,
|
|
"mean_token_accuracy": 0.10848858430981637,
|
|
"num_tokens": 1718951.0,
|
|
"step": 990
|
|
},
|
|
{
|
|
"entropy": 6.543570804595947,
|
|
"epoch": 0.07741684497179536,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.000497,
|
|
"loss": 6.4135,
|
|
"mean_token_accuracy": 0.11604536175727845,
|
|
"num_tokens": 1727481.0,
|
|
"step": 995
|
|
},
|
|
{
|
|
"entropy": 6.459407806396484,
|
|
"epoch": 0.07780587434351294,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004995,
|
|
"loss": 6.4284,
|
|
"mean_token_accuracy": 0.11745274066925049,
|
|
"num_tokens": 1736985.0,
|
|
"step": 1000
|
|
},
|
|
{
|
|
"entropy": 6.491158437728882,
|
|
"epoch": 0.0781949037152305,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004999999989075146,
|
|
"loss": 6.5002,
|
|
"mean_token_accuracy": 0.11060269325971603,
|
|
"num_tokens": 1745470.0,
|
|
"step": 1005
|
|
},
|
|
{
|
|
"entropy": 6.516347074508667,
|
|
"epoch": 0.07858393308694807,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004999999944692927,
|
|
"loss": 6.4136,
|
|
"mean_token_accuracy": 0.11825821772217751,
|
|
"num_tokens": 1754185.0,
|
|
"step": 1010
|
|
},
|
|
{
|
|
"entropy": 6.44460391998291,
|
|
"epoch": 0.07897296245866563,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.000499999986617054,
|
|
"loss": 6.4162,
|
|
"mean_token_accuracy": 0.11377911269664764,
|
|
"num_tokens": 1762100.0,
|
|
"step": 1015
|
|
},
|
|
{
|
|
"entropy": 6.5485094547271725,
|
|
"epoch": 0.0793619918303832,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004999999753507986,
|
|
"loss": 6.4394,
|
|
"mean_token_accuracy": 0.11426319703459739,
|
|
"num_tokens": 1771070.0,
|
|
"step": 1020
|
|
},
|
|
{
|
|
"entropy": 6.456011343002319,
|
|
"epoch": 0.07975102120210076,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999999606705267,
|
|
"loss": 6.4206,
|
|
"mean_token_accuracy": 0.12124844938516617,
|
|
"num_tokens": 1780085.0,
|
|
"step": 1025
|
|
},
|
|
{
|
|
"entropy": 6.509607172012329,
|
|
"epoch": 0.08014005057381832,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999999425762385,
|
|
"loss": 6.4123,
|
|
"mean_token_accuracy": 0.12023361697793007,
|
|
"num_tokens": 1789316.0,
|
|
"step": 1030
|
|
},
|
|
{
|
|
"entropy": 6.405658102035522,
|
|
"epoch": 0.08052907994553589,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999999210679344,
|
|
"loss": 6.3376,
|
|
"mean_token_accuracy": 0.12158027142286301,
|
|
"num_tokens": 1797975.0,
|
|
"step": 1035
|
|
},
|
|
{
|
|
"entropy": 6.449187183380127,
|
|
"epoch": 0.08091810931725345,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004999998961456145,
|
|
"loss": 6.439,
|
|
"mean_token_accuracy": 0.12089505419135094,
|
|
"num_tokens": 1806129.0,
|
|
"step": 1040
|
|
},
|
|
{
|
|
"entropy": 6.582769203186035,
|
|
"epoch": 0.08130713868897102,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004999998678092794,
|
|
"loss": 6.4235,
|
|
"mean_token_accuracy": 0.11868287771940231,
|
|
"num_tokens": 1813956.0,
|
|
"step": 1045
|
|
},
|
|
{
|
|
"entropy": 6.448104381561279,
|
|
"epoch": 0.08169616806068858,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004999998360589293,
|
|
"loss": 6.4659,
|
|
"mean_token_accuracy": 0.11401538997888565,
|
|
"num_tokens": 1822572.0,
|
|
"step": 1050
|
|
},
|
|
{
|
|
"entropy": 6.397772264480591,
|
|
"epoch": 0.08208519743240615,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000499999800894565,
|
|
"loss": 6.3729,
|
|
"mean_token_accuracy": 0.11618264690041542,
|
|
"num_tokens": 1831870.0,
|
|
"step": 1055
|
|
},
|
|
{
|
|
"entropy": 6.396276235580444,
|
|
"epoch": 0.08247422680412371,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004999997623161866,
|
|
"loss": 6.4035,
|
|
"mean_token_accuracy": 0.11311562955379487,
|
|
"num_tokens": 1840414.0,
|
|
"step": 1060
|
|
},
|
|
{
|
|
"entropy": 6.509707975387573,
|
|
"epoch": 0.08286325617584128,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999997203237951,
|
|
"loss": 6.4232,
|
|
"mean_token_accuracy": 0.11671750396490096,
|
|
"num_tokens": 1850385.0,
|
|
"step": 1065
|
|
},
|
|
{
|
|
"entropy": 6.349100923538208,
|
|
"epoch": 0.08325228554755884,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.000499999674917391,
|
|
"loss": 6.3301,
|
|
"mean_token_accuracy": 0.11959458813071251,
|
|
"num_tokens": 1858479.0,
|
|
"step": 1070
|
|
},
|
|
{
|
|
"entropy": 6.396405172348023,
|
|
"epoch": 0.0836413149192764,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999996260969748,
|
|
"loss": 6.3942,
|
|
"mean_token_accuracy": 0.11066490933299064,
|
|
"num_tokens": 1867357.0,
|
|
"step": 1075
|
|
},
|
|
{
|
|
"entropy": 6.460949850082398,
|
|
"epoch": 0.08403034429099397,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004999995738625475,
|
|
"loss": 6.3502,
|
|
"mean_token_accuracy": 0.11260145679116249,
|
|
"num_tokens": 1876211.0,
|
|
"step": 1080
|
|
},
|
|
{
|
|
"entropy": 6.397575378417969,
|
|
"epoch": 0.08441937366271153,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999995182141099,
|
|
"loss": 6.2465,
|
|
"mean_token_accuracy": 0.11697900295257568,
|
|
"num_tokens": 1884301.0,
|
|
"step": 1085
|
|
},
|
|
{
|
|
"entropy": 6.488512945175171,
|
|
"epoch": 0.0848084030344291,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004999994591516626,
|
|
"loss": 6.4288,
|
|
"mean_token_accuracy": 0.12221448197960853,
|
|
"num_tokens": 1893191.0,
|
|
"step": 1090
|
|
},
|
|
{
|
|
"entropy": 6.3408417224884035,
|
|
"epoch": 0.08519743240614666,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004999993966752066,
|
|
"loss": 6.3132,
|
|
"mean_token_accuracy": 0.11494594365358353,
|
|
"num_tokens": 1901434.0,
|
|
"step": 1095
|
|
},
|
|
{
|
|
"entropy": 6.387303256988526,
|
|
"epoch": 0.08558646177786423,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.000499999330784743,
|
|
"loss": 6.2771,
|
|
"mean_token_accuracy": 0.1285716027021408,
|
|
"num_tokens": 1910054.0,
|
|
"step": 1100
|
|
},
|
|
{
|
|
"entropy": 6.3939227104187015,
|
|
"epoch": 0.08597549114958179,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004999992614802725,
|
|
"loss": 6.4446,
|
|
"mean_token_accuracy": 0.11863540709018708,
|
|
"num_tokens": 1918607.0,
|
|
"step": 1105
|
|
},
|
|
{
|
|
"entropy": 6.474938297271729,
|
|
"epoch": 0.08636452052129936,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999991887617966,
|
|
"loss": 6.3814,
|
|
"mean_token_accuracy": 0.11657218113541604,
|
|
"num_tokens": 1927610.0,
|
|
"step": 1110
|
|
},
|
|
{
|
|
"entropy": 6.318664693832398,
|
|
"epoch": 0.08675354989301692,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004999991126293158,
|
|
"loss": 6.3416,
|
|
"mean_token_accuracy": 0.11837150231003761,
|
|
"num_tokens": 1936174.0,
|
|
"step": 1115
|
|
},
|
|
{
|
|
"entropy": 6.345645761489868,
|
|
"epoch": 0.08714257926473448,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999990330828318,
|
|
"loss": 6.2413,
|
|
"mean_token_accuracy": 0.12376890331506729,
|
|
"num_tokens": 1944228.0,
|
|
"step": 1120
|
|
},
|
|
{
|
|
"entropy": 6.40051498413086,
|
|
"epoch": 0.08753160863645205,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999989501223456,
|
|
"loss": 6.3634,
|
|
"mean_token_accuracy": 0.11941671147942542,
|
|
"num_tokens": 1953144.0,
|
|
"step": 1125
|
|
},
|
|
{
|
|
"entropy": 6.440733289718628,
|
|
"epoch": 0.08792063800816961,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004999988637478584,
|
|
"loss": 6.4203,
|
|
"mean_token_accuracy": 0.11518307477235794,
|
|
"num_tokens": 1961947.0,
|
|
"step": 1130
|
|
},
|
|
{
|
|
"entropy": 6.461824369430542,
|
|
"epoch": 0.08830966737988719,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999987739593716,
|
|
"loss": 6.3829,
|
|
"mean_token_accuracy": 0.11827380210161209,
|
|
"num_tokens": 1970674.0,
|
|
"step": 1135
|
|
},
|
|
{
|
|
"entropy": 6.431883430480957,
|
|
"epoch": 0.08869869675160474,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999986807568865,
|
|
"loss": 6.365,
|
|
"mean_token_accuracy": 0.12334313988685608,
|
|
"num_tokens": 1979173.0,
|
|
"step": 1140
|
|
},
|
|
{
|
|
"entropy": 6.372844505310058,
|
|
"epoch": 0.08908772612332232,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004999985841404045,
|
|
"loss": 6.3371,
|
|
"mean_token_accuracy": 0.11852383315563202,
|
|
"num_tokens": 1988134.0,
|
|
"step": 1145
|
|
},
|
|
{
|
|
"entropy": 6.391638660430909,
|
|
"epoch": 0.08947675549503988,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004999984841099271,
|
|
"loss": 6.2876,
|
|
"mean_token_accuracy": 0.12107762843370437,
|
|
"num_tokens": 1996977.0,
|
|
"step": 1150
|
|
},
|
|
{
|
|
"entropy": 6.391640377044678,
|
|
"epoch": 0.08986578486675743,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000499998380665456,
|
|
"loss": 6.3584,
|
|
"mean_token_accuracy": 0.12090120986104011,
|
|
"num_tokens": 2005946.0,
|
|
"step": 1155
|
|
},
|
|
{
|
|
"entropy": 6.296943998336792,
|
|
"epoch": 0.090254814238475,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004999982738069924,
|
|
"loss": 6.1811,
|
|
"mean_token_accuracy": 0.12553199306130408,
|
|
"num_tokens": 2014882.0,
|
|
"step": 1160
|
|
},
|
|
{
|
|
"entropy": 6.333202648162842,
|
|
"epoch": 0.09064384361019256,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004999981635345382,
|
|
"loss": 6.3849,
|
|
"mean_token_accuracy": 0.11685461923480034,
|
|
"num_tokens": 2024858.0,
|
|
"step": 1165
|
|
},
|
|
{
|
|
"entropy": 6.306487035751343,
|
|
"epoch": 0.09103287298191014,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004999980498480949,
|
|
"loss": 6.2856,
|
|
"mean_token_accuracy": 0.12073395252227784,
|
|
"num_tokens": 2034072.0,
|
|
"step": 1170
|
|
},
|
|
{
|
|
"entropy": 6.3685564517974855,
|
|
"epoch": 0.0914219023536277,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999979327476644,
|
|
"loss": 6.3023,
|
|
"mean_token_accuracy": 0.12162838876247406,
|
|
"num_tokens": 2042649.0,
|
|
"step": 1175
|
|
},
|
|
{
|
|
"entropy": 6.33339786529541,
|
|
"epoch": 0.09181093172534527,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999978122332485,
|
|
"loss": 6.3388,
|
|
"mean_token_accuracy": 0.12147895991802216,
|
|
"num_tokens": 2050866.0,
|
|
"step": 1180
|
|
},
|
|
{
|
|
"entropy": 6.370361232757569,
|
|
"epoch": 0.09219996109706283,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004999976883048487,
|
|
"loss": 6.334,
|
|
"mean_token_accuracy": 0.11986096575856209,
|
|
"num_tokens": 2058914.0,
|
|
"step": 1185
|
|
},
|
|
{
|
|
"entropy": 6.332889032363892,
|
|
"epoch": 0.0925889904687804,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004999975609624673,
|
|
"loss": 6.278,
|
|
"mean_token_accuracy": 0.1223507359623909,
|
|
"num_tokens": 2068098.0,
|
|
"step": 1190
|
|
},
|
|
{
|
|
"entropy": 6.3218268871307375,
|
|
"epoch": 0.09297801984049796,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999974302061059,
|
|
"loss": 6.2704,
|
|
"mean_token_accuracy": 0.1148650012910366,
|
|
"num_tokens": 2077299.0,
|
|
"step": 1195
|
|
},
|
|
{
|
|
"entropy": 6.390355968475342,
|
|
"epoch": 0.09336704921221552,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004999972960357666,
|
|
"loss": 6.383,
|
|
"mean_token_accuracy": 0.11495971828699111,
|
|
"num_tokens": 2087868.0,
|
|
"step": 1200
|
|
},
|
|
{
|
|
"entropy": 6.305216693878174,
|
|
"epoch": 0.09375607858393309,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999971584514516,
|
|
"loss": 6.2961,
|
|
"mean_token_accuracy": 0.12794262543320656,
|
|
"num_tokens": 2096553.0,
|
|
"step": 1205
|
|
},
|
|
{
|
|
"entropy": 6.397095203399658,
|
|
"epoch": 0.09414510795565065,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004999970174531627,
|
|
"loss": 6.2711,
|
|
"mean_token_accuracy": 0.12017060816287994,
|
|
"num_tokens": 2104809.0,
|
|
"step": 1210
|
|
},
|
|
{
|
|
"entropy": 6.169622802734375,
|
|
"epoch": 0.09453413732736822,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999968730409022,
|
|
"loss": 6.2612,
|
|
"mean_token_accuracy": 0.12208836078643799,
|
|
"num_tokens": 2113869.0,
|
|
"step": 1215
|
|
},
|
|
{
|
|
"entropy": 6.299715995788574,
|
|
"epoch": 0.09492316669908578,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004999967252146723,
|
|
"loss": 6.0683,
|
|
"mean_token_accuracy": 0.12336821407079697,
|
|
"num_tokens": 2121749.0,
|
|
"step": 1220
|
|
},
|
|
{
|
|
"entropy": 6.232715845108032,
|
|
"epoch": 0.09531219607080335,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999965739744752,
|
|
"loss": 6.3103,
|
|
"mean_token_accuracy": 0.11484472751617432,
|
|
"num_tokens": 2130828.0,
|
|
"step": 1225
|
|
},
|
|
{
|
|
"entropy": 6.406879520416259,
|
|
"epoch": 0.09570122544252091,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999964193203132,
|
|
"loss": 6.2654,
|
|
"mean_token_accuracy": 0.11970051750540733,
|
|
"num_tokens": 2138928.0,
|
|
"step": 1230
|
|
},
|
|
{
|
|
"entropy": 6.278574371337891,
|
|
"epoch": 0.09609025481423847,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999962612521888,
|
|
"loss": 6.3029,
|
|
"mean_token_accuracy": 0.11736734807491303,
|
|
"num_tokens": 2147643.0,
|
|
"step": 1235
|
|
},
|
|
{
|
|
"entropy": 6.353299474716186,
|
|
"epoch": 0.09647928418595604,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999960997701041,
|
|
"loss": 6.2205,
|
|
"mean_token_accuracy": 0.1316021092236042,
|
|
"num_tokens": 2156766.0,
|
|
"step": 1240
|
|
},
|
|
{
|
|
"entropy": 6.2896465301513675,
|
|
"epoch": 0.0968683135576736,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999959348740618,
|
|
"loss": 6.2925,
|
|
"mean_token_accuracy": 0.12166507244110107,
|
|
"num_tokens": 2165517.0,
|
|
"step": 1245
|
|
},
|
|
{
|
|
"entropy": 6.241901206970215,
|
|
"epoch": 0.09725734292939117,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999957665640641,
|
|
"loss": 6.1634,
|
|
"mean_token_accuracy": 0.12425515949726104,
|
|
"num_tokens": 2174812.0,
|
|
"step": 1250
|
|
},
|
|
{
|
|
"entropy": 6.312180709838867,
|
|
"epoch": 0.09764637230110873,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000499995594840114,
|
|
"loss": 6.3094,
|
|
"mean_token_accuracy": 0.12275587990880013,
|
|
"num_tokens": 2183968.0,
|
|
"step": 1255
|
|
},
|
|
{
|
|
"entropy": 6.348030090332031,
|
|
"epoch": 0.0980354016728263,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004999954197022138,
|
|
"loss": 6.3421,
|
|
"mean_token_accuracy": 0.12190790548920631,
|
|
"num_tokens": 2191947.0,
|
|
"step": 1260
|
|
},
|
|
{
|
|
"entropy": 6.2868959426879885,
|
|
"epoch": 0.09842443104454386,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004999952411503661,
|
|
"loss": 6.1731,
|
|
"mean_token_accuracy": 0.12876865193247794,
|
|
"num_tokens": 2199951.0,
|
|
"step": 1265
|
|
},
|
|
{
|
|
"entropy": 6.198631954193115,
|
|
"epoch": 0.09881346041626143,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004999950591845738,
|
|
"loss": 6.3187,
|
|
"mean_token_accuracy": 0.12265456095337868,
|
|
"num_tokens": 2208714.0,
|
|
"step": 1270
|
|
},
|
|
{
|
|
"entropy": 6.255360126495361,
|
|
"epoch": 0.09920248978797899,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999948738048397,
|
|
"loss": 6.1829,
|
|
"mean_token_accuracy": 0.12252248078584671,
|
|
"num_tokens": 2217250.0,
|
|
"step": 1275
|
|
},
|
|
{
|
|
"entropy": 6.283931112289428,
|
|
"epoch": 0.09959151915969655,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004999946850111663,
|
|
"loss": 6.2283,
|
|
"mean_token_accuracy": 0.12672243788838386,
|
|
"num_tokens": 2225468.0,
|
|
"step": 1280
|
|
},
|
|
{
|
|
"entropy": 6.240218687057495,
|
|
"epoch": 0.09998054853141412,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004999944928035569,
|
|
"loss": 6.2003,
|
|
"mean_token_accuracy": 0.132812437415123,
|
|
"num_tokens": 2233893.0,
|
|
"step": 1285
|
|
},
|
|
{
|
|
"entropy": 6.388429498672485,
|
|
"epoch": 0.10036957790313168,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.000499994297182014,
|
|
"loss": 6.2488,
|
|
"mean_token_accuracy": 0.12291268333792686,
|
|
"num_tokens": 2242487.0,
|
|
"step": 1290
|
|
},
|
|
{
|
|
"entropy": 6.149504566192627,
|
|
"epoch": 0.10075860727484925,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004999940981465408,
|
|
"loss": 6.1059,
|
|
"mean_token_accuracy": 0.12876313999295236,
|
|
"num_tokens": 2250518.0,
|
|
"step": 1295
|
|
},
|
|
{
|
|
"entropy": 6.248823356628418,
|
|
"epoch": 0.10114763664656681,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004999938956971404,
|
|
"loss": 6.2617,
|
|
"mean_token_accuracy": 0.11773729845881462,
|
|
"num_tokens": 2259024.0,
|
|
"step": 1300
|
|
},
|
|
{
|
|
"entropy": 6.243083953857422,
|
|
"epoch": 0.10153666601828439,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999936898338156,
|
|
"loss": 6.3117,
|
|
"mean_token_accuracy": 0.11112835854291916,
|
|
"num_tokens": 2267832.0,
|
|
"step": 1305
|
|
},
|
|
{
|
|
"entropy": 6.353409099578857,
|
|
"epoch": 0.10192569539000194,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999934805565698,
|
|
"loss": 6.3648,
|
|
"mean_token_accuracy": 0.11365198269486428,
|
|
"num_tokens": 2276834.0,
|
|
"step": 1310
|
|
},
|
|
{
|
|
"entropy": 6.407787656784057,
|
|
"epoch": 0.10231472476171952,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000499993267865406,
|
|
"loss": 6.2935,
|
|
"mean_token_accuracy": 0.11966201588511467,
|
|
"num_tokens": 2285736.0,
|
|
"step": 1315
|
|
},
|
|
{
|
|
"entropy": 6.335090637207031,
|
|
"epoch": 0.10270375413343708,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999930517603275,
|
|
"loss": 6.234,
|
|
"mean_token_accuracy": 0.13229560926556588,
|
|
"num_tokens": 2294177.0,
|
|
"step": 1320
|
|
},
|
|
{
|
|
"entropy": 6.1624072074890135,
|
|
"epoch": 0.10309278350515463,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004999928322413374,
|
|
"loss": 6.0327,
|
|
"mean_token_accuracy": 0.13786780312657357,
|
|
"num_tokens": 2302784.0,
|
|
"step": 1325
|
|
},
|
|
{
|
|
"entropy": 6.157652235031128,
|
|
"epoch": 0.1034818128768722,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999926093084394,
|
|
"loss": 6.1444,
|
|
"mean_token_accuracy": 0.1264040432870388,
|
|
"num_tokens": 2311650.0,
|
|
"step": 1330
|
|
},
|
|
{
|
|
"entropy": 6.357713842391968,
|
|
"epoch": 0.10387084224858976,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999923829616365,
|
|
"loss": 6.2702,
|
|
"mean_token_accuracy": 0.1245061181485653,
|
|
"num_tokens": 2319828.0,
|
|
"step": 1335
|
|
},
|
|
{
|
|
"entropy": 6.228060579299926,
|
|
"epoch": 0.10425987162030734,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004999921532009323,
|
|
"loss": 6.268,
|
|
"mean_token_accuracy": 0.1238878071308136,
|
|
"num_tokens": 2328636.0,
|
|
"step": 1340
|
|
},
|
|
{
|
|
"entropy": 6.184857749938965,
|
|
"epoch": 0.1046489009920249,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004999919200263304,
|
|
"loss": 6.1518,
|
|
"mean_token_accuracy": 0.1284673720598221,
|
|
"num_tokens": 2336771.0,
|
|
"step": 1345
|
|
},
|
|
{
|
|
"entropy": 6.288402986526489,
|
|
"epoch": 0.10503793036374247,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999916834378342,
|
|
"loss": 6.3156,
|
|
"mean_token_accuracy": 0.11986559703946113,
|
|
"num_tokens": 2346106.0,
|
|
"step": 1350
|
|
},
|
|
{
|
|
"entropy": 6.338619947433472,
|
|
"epoch": 0.10542695973546003,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004999914434354472,
|
|
"loss": 6.2878,
|
|
"mean_token_accuracy": 0.12146384119987488,
|
|
"num_tokens": 2354943.0,
|
|
"step": 1355
|
|
},
|
|
{
|
|
"entropy": 6.151570415496826,
|
|
"epoch": 0.10581598910717759,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999912000191733,
|
|
"loss": 6.2057,
|
|
"mean_token_accuracy": 0.1271749369800091,
|
|
"num_tokens": 2363699.0,
|
|
"step": 1360
|
|
},
|
|
{
|
|
"entropy": 6.261769962310791,
|
|
"epoch": 0.10620501847889516,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000499990953189016,
|
|
"loss": 6.3372,
|
|
"mean_token_accuracy": 0.12160424366593361,
|
|
"num_tokens": 2373316.0,
|
|
"step": 1365
|
|
},
|
|
{
|
|
"entropy": 6.472919464111328,
|
|
"epoch": 0.10659404785061272,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004999907029449791,
|
|
"loss": 6.3908,
|
|
"mean_token_accuracy": 0.11671768948435783,
|
|
"num_tokens": 2381550.0,
|
|
"step": 1370
|
|
},
|
|
{
|
|
"entropy": 6.214975214004516,
|
|
"epoch": 0.10698307722233029,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999904492870663,
|
|
"loss": 6.2135,
|
|
"mean_token_accuracy": 0.12396282330155373,
|
|
"num_tokens": 2389546.0,
|
|
"step": 1375
|
|
},
|
|
{
|
|
"entropy": 6.331138038635254,
|
|
"epoch": 0.10737210659404785,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999901922152816,
|
|
"loss": 6.167,
|
|
"mean_token_accuracy": 0.1306578040122986,
|
|
"num_tokens": 2398852.0,
|
|
"step": 1380
|
|
},
|
|
{
|
|
"entropy": 6.1877685546875,
|
|
"epoch": 0.10776113596576542,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999899317296288,
|
|
"loss": 6.2625,
|
|
"mean_token_accuracy": 0.12318363636732102,
|
|
"num_tokens": 2407815.0,
|
|
"step": 1385
|
|
},
|
|
{
|
|
"entropy": 6.263129615783692,
|
|
"epoch": 0.10815016533748298,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999896678301121,
|
|
"loss": 6.1258,
|
|
"mean_token_accuracy": 0.1308325506746769,
|
|
"num_tokens": 2417300.0,
|
|
"step": 1390
|
|
},
|
|
{
|
|
"entropy": 6.185340309143067,
|
|
"epoch": 0.10853919470920055,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004999894005167352,
|
|
"loss": 6.2796,
|
|
"mean_token_accuracy": 0.12236608639359474,
|
|
"num_tokens": 2426257.0,
|
|
"step": 1395
|
|
},
|
|
{
|
|
"entropy": 6.417700147628784,
|
|
"epoch": 0.10892822408091811,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000499989129789502,
|
|
"loss": 6.2964,
|
|
"mean_token_accuracy": 0.12767537981271743,
|
|
"num_tokens": 2434595.0,
|
|
"step": 1400
|
|
},
|
|
{
|
|
"entropy": 6.336059093475342,
|
|
"epoch": 0.10931725345263567,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999888556484172,
|
|
"loss": 6.3127,
|
|
"mean_token_accuracy": 0.12117981314659118,
|
|
"num_tokens": 2443945.0,
|
|
"step": 1405
|
|
},
|
|
{
|
|
"entropy": 6.182463836669922,
|
|
"epoch": 0.10970628282435324,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999885780934845,
|
|
"loss": 6.1628,
|
|
"mean_token_accuracy": 0.1235832579433918,
|
|
"num_tokens": 2453141.0,
|
|
"step": 1410
|
|
},
|
|
{
|
|
"entropy": 6.290924787521362,
|
|
"epoch": 0.1100953121960708,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999882971247081,
|
|
"loss": 6.2496,
|
|
"mean_token_accuracy": 0.12170757949352265,
|
|
"num_tokens": 2461873.0,
|
|
"step": 1415
|
|
},
|
|
{
|
|
"entropy": 6.224940824508667,
|
|
"epoch": 0.11048434156778837,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004999880127420926,
|
|
"loss": 6.2886,
|
|
"mean_token_accuracy": 0.11874458640813827,
|
|
"num_tokens": 2471238.0,
|
|
"step": 1420
|
|
},
|
|
{
|
|
"entropy": 6.246773672103882,
|
|
"epoch": 0.11087337093950593,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004999877249456421,
|
|
"loss": 6.172,
|
|
"mean_token_accuracy": 0.13200448527932168,
|
|
"num_tokens": 2479412.0,
|
|
"step": 1425
|
|
},
|
|
{
|
|
"entropy": 6.087906742095948,
|
|
"epoch": 0.1112624003112235,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004999874337353609,
|
|
"loss": 6.0646,
|
|
"mean_token_accuracy": 0.1294640928506851,
|
|
"num_tokens": 2488150.0,
|
|
"step": 1430
|
|
},
|
|
{
|
|
"entropy": 6.218584394454956,
|
|
"epoch": 0.11165142968294106,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999871391112535,
|
|
"loss": 6.2369,
|
|
"mean_token_accuracy": 0.12804254814982413,
|
|
"num_tokens": 2498103.0,
|
|
"step": 1435
|
|
},
|
|
{
|
|
"entropy": 6.203536701202393,
|
|
"epoch": 0.11204045905465862,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999868410733244,
|
|
"loss": 6.0996,
|
|
"mean_token_accuracy": 0.13143314570188522,
|
|
"num_tokens": 2506211.0,
|
|
"step": 1440
|
|
},
|
|
{
|
|
"entropy": 6.0622382164001465,
|
|
"epoch": 0.11242948842637619,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000499986539621578,
|
|
"loss": 6.1473,
|
|
"mean_token_accuracy": 0.12935293465852737,
|
|
"num_tokens": 2514743.0,
|
|
"step": 1445
|
|
},
|
|
{
|
|
"entropy": 6.177716684341431,
|
|
"epoch": 0.11281851779809375,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999862347560191,
|
|
"loss": 6.1437,
|
|
"mean_token_accuracy": 0.12134760469198227,
|
|
"num_tokens": 2523824.0,
|
|
"step": 1450
|
|
},
|
|
{
|
|
"entropy": 6.279800128936768,
|
|
"epoch": 0.11320754716981132,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999859264766521,
|
|
"loss": 6.1986,
|
|
"mean_token_accuracy": 0.12378213405609131,
|
|
"num_tokens": 2532360.0,
|
|
"step": 1455
|
|
},
|
|
{
|
|
"entropy": 6.195611000061035,
|
|
"epoch": 0.11359657654152888,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999856147834817,
|
|
"loss": 6.147,
|
|
"mean_token_accuracy": 0.13270104676485062,
|
|
"num_tokens": 2540547.0,
|
|
"step": 1460
|
|
},
|
|
{
|
|
"entropy": 6.129956388473511,
|
|
"epoch": 0.11398560591324645,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004999852996765129,
|
|
"loss": 6.1665,
|
|
"mean_token_accuracy": 0.12596870586276054,
|
|
"num_tokens": 2549193.0,
|
|
"step": 1465
|
|
},
|
|
{
|
|
"entropy": 6.254879188537598,
|
|
"epoch": 0.11437463528496401,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999849811557502,
|
|
"loss": 6.1692,
|
|
"mean_token_accuracy": 0.12485439851880073,
|
|
"num_tokens": 2557553.0,
|
|
"step": 1470
|
|
},
|
|
{
|
|
"entropy": 6.3121579647064205,
|
|
"epoch": 0.11476366465668159,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999846592211984,
|
|
"loss": 6.2761,
|
|
"mean_token_accuracy": 0.12519683614373206,
|
|
"num_tokens": 2565945.0,
|
|
"step": 1475
|
|
},
|
|
{
|
|
"entropy": 6.2565967559814455,
|
|
"epoch": 0.11515269402839914,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004999843338728626,
|
|
"loss": 6.1446,
|
|
"mean_token_accuracy": 0.12215643152594566,
|
|
"num_tokens": 2574364.0,
|
|
"step": 1480
|
|
},
|
|
{
|
|
"entropy": 6.147215938568115,
|
|
"epoch": 0.1155417234001167,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999840051107476,
|
|
"loss": 6.0785,
|
|
"mean_token_accuracy": 0.12832588478922843,
|
|
"num_tokens": 2582825.0,
|
|
"step": 1485
|
|
},
|
|
{
|
|
"entropy": 6.265280485153198,
|
|
"epoch": 0.11593075277183428,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999836729348584,
|
|
"loss": 6.2112,
|
|
"mean_token_accuracy": 0.12704068496823312,
|
|
"num_tokens": 2591628.0,
|
|
"step": 1490
|
|
},
|
|
{
|
|
"entropy": 6.254674339294434,
|
|
"epoch": 0.11631978214355183,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999833373452,
|
|
"loss": 6.2213,
|
|
"mean_token_accuracy": 0.12300590127706527,
|
|
"num_tokens": 2600436.0,
|
|
"step": 1495
|
|
},
|
|
{
|
|
"entropy": 6.136021471023559,
|
|
"epoch": 0.1167088115152694,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004999829983417778,
|
|
"loss": 6.18,
|
|
"mean_token_accuracy": 0.12494545355439186,
|
|
"num_tokens": 2609709.0,
|
|
"step": 1500
|
|
},
|
|
{
|
|
"entropy": 6.273649883270264,
|
|
"epoch": 0.11709784088698696,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999826559245965,
|
|
"loss": 6.189,
|
|
"mean_token_accuracy": 0.1290210045874119,
|
|
"num_tokens": 2617992.0,
|
|
"step": 1505
|
|
},
|
|
{
|
|
"entropy": 6.112089776992798,
|
|
"epoch": 0.11748687025870454,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999823100936615,
|
|
"loss": 6.104,
|
|
"mean_token_accuracy": 0.12461598962545395,
|
|
"num_tokens": 2626706.0,
|
|
"step": 1510
|
|
},
|
|
{
|
|
"entropy": 6.306183671951294,
|
|
"epoch": 0.1178758996304221,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004999819608489781,
|
|
"loss": 6.1707,
|
|
"mean_token_accuracy": 0.13305557370185853,
|
|
"num_tokens": 2634642.0,
|
|
"step": 1515
|
|
},
|
|
{
|
|
"entropy": 6.24433331489563,
|
|
"epoch": 0.11826492900213967,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999816081905515,
|
|
"loss": 6.2072,
|
|
"mean_token_accuracy": 0.12206726670265197,
|
|
"num_tokens": 2644160.0,
|
|
"step": 1520
|
|
},
|
|
{
|
|
"entropy": 6.131756973266602,
|
|
"epoch": 0.11865395837385723,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999812521183872,
|
|
"loss": 6.1668,
|
|
"mean_token_accuracy": 0.12623140662908555,
|
|
"num_tokens": 2653390.0,
|
|
"step": 1525
|
|
},
|
|
{
|
|
"entropy": 6.26336030960083,
|
|
"epoch": 0.11904298774557479,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004999808926324903,
|
|
"loss": 6.2162,
|
|
"mean_token_accuracy": 0.12652711421251298,
|
|
"num_tokens": 2662561.0,
|
|
"step": 1530
|
|
},
|
|
{
|
|
"entropy": 6.205893182754517,
|
|
"epoch": 0.11943201711729236,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004999805297328665,
|
|
"loss": 6.1788,
|
|
"mean_token_accuracy": 0.12196686640381812,
|
|
"num_tokens": 2670694.0,
|
|
"step": 1535
|
|
},
|
|
{
|
|
"entropy": 6.123800992965698,
|
|
"epoch": 0.11982104648900992,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999801634195214,
|
|
"loss": 6.0751,
|
|
"mean_token_accuracy": 0.1296789526939392,
|
|
"num_tokens": 2679583.0,
|
|
"step": 1540
|
|
},
|
|
{
|
|
"entropy": 6.160254049301147,
|
|
"epoch": 0.12021007586072749,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999797936924603,
|
|
"loss": 6.0547,
|
|
"mean_token_accuracy": 0.13012141734361649,
|
|
"num_tokens": 2688429.0,
|
|
"step": 1545
|
|
},
|
|
{
|
|
"entropy": 6.245877122879028,
|
|
"epoch": 0.12059910523244505,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000499979420551689,
|
|
"loss": 6.1393,
|
|
"mean_token_accuracy": 0.127946737408638,
|
|
"num_tokens": 2697134.0,
|
|
"step": 1550
|
|
},
|
|
{
|
|
"entropy": 6.139470767974854,
|
|
"epoch": 0.12098813460416262,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000499979043997213,
|
|
"loss": 6.271,
|
|
"mean_token_accuracy": 0.12086955159902572,
|
|
"num_tokens": 2705641.0,
|
|
"step": 1555
|
|
},
|
|
{
|
|
"entropy": 6.244083309173584,
|
|
"epoch": 0.12137716397588018,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999786640290381,
|
|
"loss": 6.2182,
|
|
"mean_token_accuracy": 0.13000693321228027,
|
|
"num_tokens": 2714977.0,
|
|
"step": 1560
|
|
},
|
|
{
|
|
"entropy": 6.208574056625366,
|
|
"epoch": 0.12176619334759774,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004999782806471701,
|
|
"loss": 6.0715,
|
|
"mean_token_accuracy": 0.1309586115181446,
|
|
"num_tokens": 2723120.0,
|
|
"step": 1565
|
|
},
|
|
{
|
|
"entropy": 5.980209159851074,
|
|
"epoch": 0.12215522271931531,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004999778938516147,
|
|
"loss": 6.067,
|
|
"mean_token_accuracy": 0.13349125906825066,
|
|
"num_tokens": 2731964.0,
|
|
"step": 1570
|
|
},
|
|
{
|
|
"entropy": 6.338853549957276,
|
|
"epoch": 0.12254425209103287,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000499977503642378,
|
|
"loss": 6.1322,
|
|
"mean_token_accuracy": 0.12307027727365494,
|
|
"num_tokens": 2741537.0,
|
|
"step": 1575
|
|
},
|
|
{
|
|
"entropy": 6.1407702445983885,
|
|
"epoch": 0.12293328146275044,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999771100194656,
|
|
"loss": 6.255,
|
|
"mean_token_accuracy": 0.12590772435069084,
|
|
"num_tokens": 2751522.0,
|
|
"step": 1580
|
|
},
|
|
{
|
|
"entropy": 6.292725038528443,
|
|
"epoch": 0.123322310834468,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999767129828837,
|
|
"loss": 6.2501,
|
|
"mean_token_accuracy": 0.12044540867209434,
|
|
"num_tokens": 2761100.0,
|
|
"step": 1585
|
|
},
|
|
{
|
|
"entropy": 6.141694831848144,
|
|
"epoch": 0.12371134020618557,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004999763125326383,
|
|
"loss": 6.1863,
|
|
"mean_token_accuracy": 0.13047750890254975,
|
|
"num_tokens": 2769171.0,
|
|
"step": 1590
|
|
},
|
|
{
|
|
"entropy": 6.199422979354859,
|
|
"epoch": 0.12410036957790313,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004999759086687355,
|
|
"loss": 6.1082,
|
|
"mean_token_accuracy": 0.12826797664165496,
|
|
"num_tokens": 2778021.0,
|
|
"step": 1595
|
|
},
|
|
{
|
|
"entropy": 6.080332040786743,
|
|
"epoch": 0.1244893989496207,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999755013911813,
|
|
"loss": 6.0665,
|
|
"mean_token_accuracy": 0.12919810712337493,
|
|
"num_tokens": 2787206.0,
|
|
"step": 1600
|
|
},
|
|
{
|
|
"entropy": 6.090942096710205,
|
|
"epoch": 0.12487842832133826,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000499975090699982,
|
|
"loss": 6.138,
|
|
"mean_token_accuracy": 0.1256270095705986,
|
|
"num_tokens": 2796051.0,
|
|
"step": 1605
|
|
},
|
|
{
|
|
"entropy": 6.1865153312683105,
|
|
"epoch": 0.12526745769305583,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999746765951438,
|
|
"loss": 6.0788,
|
|
"mean_token_accuracy": 0.12857932075858117,
|
|
"num_tokens": 2804961.0,
|
|
"step": 1610
|
|
},
|
|
{
|
|
"entropy": 6.1580259799957275,
|
|
"epoch": 0.1256564870647734,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004999742590766729,
|
|
"loss": 6.0294,
|
|
"mean_token_accuracy": 0.1358417183160782,
|
|
"num_tokens": 2813691.0,
|
|
"step": 1615
|
|
},
|
|
{
|
|
"entropy": 6.080268669128418,
|
|
"epoch": 0.12604551643649095,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004999738381445757,
|
|
"loss": 6.176,
|
|
"mean_token_accuracy": 0.13041893243789673,
|
|
"num_tokens": 2822248.0,
|
|
"step": 1620
|
|
},
|
|
{
|
|
"entropy": 6.262363052368164,
|
|
"epoch": 0.1264345458082085,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999734137988586,
|
|
"loss": 6.1311,
|
|
"mean_token_accuracy": 0.1297252357006073,
|
|
"num_tokens": 2830826.0,
|
|
"step": 1625
|
|
},
|
|
{
|
|
"entropy": 6.137490463256836,
|
|
"epoch": 0.1268235751799261,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.000499972986039528,
|
|
"loss": 6.1052,
|
|
"mean_token_accuracy": 0.1270240917801857,
|
|
"num_tokens": 2839766.0,
|
|
"step": 1630
|
|
},
|
|
{
|
|
"entropy": 6.022924184799194,
|
|
"epoch": 0.12721260455164365,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999725548665904,
|
|
"loss": 6.0593,
|
|
"mean_token_accuracy": 0.1354152277112007,
|
|
"num_tokens": 2848728.0,
|
|
"step": 1635
|
|
},
|
|
{
|
|
"entropy": 6.118963813781738,
|
|
"epoch": 0.1276016339233612,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004999721202800524,
|
|
"loss": 6.0936,
|
|
"mean_token_accuracy": 0.12914758920669556,
|
|
"num_tokens": 2857221.0,
|
|
"step": 1640
|
|
},
|
|
{
|
|
"entropy": 6.207554531097412,
|
|
"epoch": 0.12799066329507877,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004999716822799206,
|
|
"loss": 6.1498,
|
|
"mean_token_accuracy": 0.129972605407238,
|
|
"num_tokens": 2865314.0,
|
|
"step": 1645
|
|
},
|
|
{
|
|
"entropy": 6.060013198852539,
|
|
"epoch": 0.12837969266679633,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004999712408662016,
|
|
"loss": 6.0296,
|
|
"mean_token_accuracy": 0.12889490500092507,
|
|
"num_tokens": 2873654.0,
|
|
"step": 1650
|
|
},
|
|
{
|
|
"entropy": 6.0302290439605715,
|
|
"epoch": 0.12876872203851392,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999707960389021,
|
|
"loss": 5.9344,
|
|
"mean_token_accuracy": 0.1405336044728756,
|
|
"num_tokens": 2881604.0,
|
|
"step": 1655
|
|
},
|
|
{
|
|
"entropy": 6.127301740646362,
|
|
"epoch": 0.12915775141023147,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004999703477980288,
|
|
"loss": 6.1187,
|
|
"mean_token_accuracy": 0.1259210415184498,
|
|
"num_tokens": 2890427.0,
|
|
"step": 1660
|
|
},
|
|
{
|
|
"entropy": 6.121555471420288,
|
|
"epoch": 0.12954678078194903,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999698961435885,
|
|
"loss": 6.0928,
|
|
"mean_token_accuracy": 0.12871603891253472,
|
|
"num_tokens": 2899206.0,
|
|
"step": 1665
|
|
},
|
|
{
|
|
"entropy": 6.1087963581085205,
|
|
"epoch": 0.1299358101536666,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999694410755882,
|
|
"loss": 6.0137,
|
|
"mean_token_accuracy": 0.1334090158343315,
|
|
"num_tokens": 2907738.0,
|
|
"step": 1670
|
|
},
|
|
{
|
|
"entropy": 6.163375568389893,
|
|
"epoch": 0.13032483952538418,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999689825940347,
|
|
"loss": 6.2312,
|
|
"mean_token_accuracy": 0.12564567625522613,
|
|
"num_tokens": 2916881.0,
|
|
"step": 1675
|
|
},
|
|
{
|
|
"entropy": 6.174770545959473,
|
|
"epoch": 0.13071386889710174,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999685206989349,
|
|
"loss": 6.1816,
|
|
"mean_token_accuracy": 0.12577074617147446,
|
|
"num_tokens": 2926467.0,
|
|
"step": 1680
|
|
},
|
|
{
|
|
"entropy": 6.191853427886963,
|
|
"epoch": 0.1311028982688193,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999680553902959,
|
|
"loss": 6.111,
|
|
"mean_token_accuracy": 0.13117136508226396,
|
|
"num_tokens": 2934671.0,
|
|
"step": 1685
|
|
},
|
|
{
|
|
"entropy": 6.092531633377075,
|
|
"epoch": 0.13149192764053685,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999675866681247,
|
|
"loss": 6.1368,
|
|
"mean_token_accuracy": 0.12292360961437225,
|
|
"num_tokens": 2943925.0,
|
|
"step": 1690
|
|
},
|
|
{
|
|
"entropy": 6.250123500823975,
|
|
"epoch": 0.1318809570122544,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004999671145324286,
|
|
"loss": 6.1817,
|
|
"mean_token_accuracy": 0.12874179482460021,
|
|
"num_tokens": 2952118.0,
|
|
"step": 1695
|
|
},
|
|
{
|
|
"entropy": 6.055361366271972,
|
|
"epoch": 0.132269986383972,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999666389832144,
|
|
"loss": 6.1426,
|
|
"mean_token_accuracy": 0.12821546643972398,
|
|
"num_tokens": 2961110.0,
|
|
"step": 1700
|
|
},
|
|
{
|
|
"entropy": 6.202066135406494,
|
|
"epoch": 0.13265901575568956,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999661600204897,
|
|
"loss": 6.0759,
|
|
"mean_token_accuracy": 0.13429482877254487,
|
|
"num_tokens": 2968877.0,
|
|
"step": 1705
|
|
},
|
|
{
|
|
"entropy": 6.162191772460938,
|
|
"epoch": 0.13304804512740712,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999656776442615,
|
|
"loss": 6.1445,
|
|
"mean_token_accuracy": 0.13220435604453087,
|
|
"num_tokens": 2977346.0,
|
|
"step": 1710
|
|
},
|
|
{
|
|
"entropy": 6.190565729141236,
|
|
"epoch": 0.13343707449912467,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999651918545372,
|
|
"loss": 6.1927,
|
|
"mean_token_accuracy": 0.12332916557788849,
|
|
"num_tokens": 2987494.0,
|
|
"step": 1715
|
|
},
|
|
{
|
|
"entropy": 6.103679990768432,
|
|
"epoch": 0.13382610387084226,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999647026513243,
|
|
"loss": 6.1068,
|
|
"mean_token_accuracy": 0.12716897055506707,
|
|
"num_tokens": 2996728.0,
|
|
"step": 1720
|
|
},
|
|
{
|
|
"entropy": 6.180693864822388,
|
|
"epoch": 0.13421513324255982,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00049996421003463,
|
|
"loss": 6.1498,
|
|
"mean_token_accuracy": 0.12552834004163743,
|
|
"num_tokens": 3005810.0,
|
|
"step": 1725
|
|
},
|
|
{
|
|
"entropy": 6.156610155105591,
|
|
"epoch": 0.13460416261427738,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004999637140044619,
|
|
"loss": 6.1577,
|
|
"mean_token_accuracy": 0.12653571218252183,
|
|
"num_tokens": 3014603.0,
|
|
"step": 1730
|
|
},
|
|
{
|
|
"entropy": 6.209864950180053,
|
|
"epoch": 0.13499319198599494,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004999632145608275,
|
|
"loss": 6.1373,
|
|
"mean_token_accuracy": 0.1348169304430485,
|
|
"num_tokens": 3023170.0,
|
|
"step": 1735
|
|
},
|
|
{
|
|
"entropy": 5.989885330200195,
|
|
"epoch": 0.1353822213577125,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004999627117037343,
|
|
"loss": 5.8964,
|
|
"mean_token_accuracy": 0.14146249517798423,
|
|
"num_tokens": 3030565.0,
|
|
"step": 1740
|
|
},
|
|
{
|
|
"entropy": 6.150790071487426,
|
|
"epoch": 0.13577125072943008,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00049996220543319,
|
|
"loss": 6.1608,
|
|
"mean_token_accuracy": 0.13290613517165184,
|
|
"num_tokens": 3040124.0,
|
|
"step": 1745
|
|
},
|
|
{
|
|
"entropy": 6.113092422485352,
|
|
"epoch": 0.13616028010114764,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999616957492025,
|
|
"loss": 6.0248,
|
|
"mean_token_accuracy": 0.133372500538826,
|
|
"num_tokens": 3048458.0,
|
|
"step": 1750
|
|
},
|
|
{
|
|
"entropy": 5.980424404144287,
|
|
"epoch": 0.1365493094728652,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999611826517793,
|
|
"loss": 5.9957,
|
|
"mean_token_accuracy": 0.12622589692473413,
|
|
"num_tokens": 3057926.0,
|
|
"step": 1755
|
|
},
|
|
{
|
|
"entropy": 6.088951873779297,
|
|
"epoch": 0.13693833884458276,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999606661409281,
|
|
"loss": 6.0346,
|
|
"mean_token_accuracy": 0.1311038538813591,
|
|
"num_tokens": 3066683.0,
|
|
"step": 1760
|
|
},
|
|
{
|
|
"entropy": 6.084488821029663,
|
|
"epoch": 0.13732736821630034,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999601462166569,
|
|
"loss": 6.1265,
|
|
"mean_token_accuracy": 0.12747237384319304,
|
|
"num_tokens": 3075117.0,
|
|
"step": 1765
|
|
},
|
|
{
|
|
"entropy": 6.2358348846435545,
|
|
"epoch": 0.1377163975880179,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999596228789736,
|
|
"loss": 6.1727,
|
|
"mean_token_accuracy": 0.12200985625386238,
|
|
"num_tokens": 3084399.0,
|
|
"step": 1770
|
|
},
|
|
{
|
|
"entropy": 6.0126197814941404,
|
|
"epoch": 0.13810542695973546,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999590961278859,
|
|
"loss": 5.9522,
|
|
"mean_token_accuracy": 0.13428694307804107,
|
|
"num_tokens": 3093030.0,
|
|
"step": 1775
|
|
},
|
|
{
|
|
"entropy": 6.139213275909424,
|
|
"epoch": 0.13849445633145302,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999585659634021,
|
|
"loss": 6.0093,
|
|
"mean_token_accuracy": 0.13519808501005173,
|
|
"num_tokens": 3101670.0,
|
|
"step": 1780
|
|
},
|
|
{
|
|
"entropy": 5.935570812225341,
|
|
"epoch": 0.13888348570317058,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999580323855301,
|
|
"loss": 6.0056,
|
|
"mean_token_accuracy": 0.1314087174832821,
|
|
"num_tokens": 3109703.0,
|
|
"step": 1785
|
|
},
|
|
{
|
|
"entropy": 6.029119539260864,
|
|
"epoch": 0.13927251507488816,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999574953942781,
|
|
"loss": 5.9691,
|
|
"mean_token_accuracy": 0.13666441813111305,
|
|
"num_tokens": 3118388.0,
|
|
"step": 1790
|
|
},
|
|
{
|
|
"entropy": 6.086500453948974,
|
|
"epoch": 0.13966154444660572,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999569549896541,
|
|
"loss": 5.9659,
|
|
"mean_token_accuracy": 0.1331724926829338,
|
|
"num_tokens": 3126466.0,
|
|
"step": 1795
|
|
},
|
|
{
|
|
"entropy": 6.04347071647644,
|
|
"epoch": 0.14005057381832328,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999564111716665,
|
|
"loss": 6.0297,
|
|
"mean_token_accuracy": 0.13553740605711936,
|
|
"num_tokens": 3135322.0,
|
|
"step": 1800
|
|
},
|
|
{
|
|
"entropy": 6.094385194778442,
|
|
"epoch": 0.14043960319004084,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999558639403232,
|
|
"loss": 6.022,
|
|
"mean_token_accuracy": 0.13918943479657173,
|
|
"num_tokens": 3144498.0,
|
|
"step": 1805
|
|
},
|
|
{
|
|
"entropy": 5.972038269042969,
|
|
"epoch": 0.1408286325617584,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999553132956328,
|
|
"loss": 5.9912,
|
|
"mean_token_accuracy": 0.1320311300456524,
|
|
"num_tokens": 3153573.0,
|
|
"step": 1810
|
|
},
|
|
{
|
|
"entropy": 6.018750381469727,
|
|
"epoch": 0.14121766193347599,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999547592376035,
|
|
"loss": 5.9291,
|
|
"mean_token_accuracy": 0.13997017741203308,
|
|
"num_tokens": 3161705.0,
|
|
"step": 1815
|
|
},
|
|
{
|
|
"entropy": 6.026726150512696,
|
|
"epoch": 0.14160669130519354,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004999542017662438,
|
|
"loss": 6.0922,
|
|
"mean_token_accuracy": 0.132773719727993,
|
|
"num_tokens": 3170068.0,
|
|
"step": 1820
|
|
},
|
|
{
|
|
"entropy": 6.082734823226929,
|
|
"epoch": 0.1419957206769111,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004999536408815623,
|
|
"loss": 6.0932,
|
|
"mean_token_accuracy": 0.1262606404721737,
|
|
"num_tokens": 3178140.0,
|
|
"step": 1825
|
|
},
|
|
{
|
|
"entropy": 6.1050639152526855,
|
|
"epoch": 0.14238475004862866,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004999530765835672,
|
|
"loss": 6.0709,
|
|
"mean_token_accuracy": 0.1336948625743389,
|
|
"num_tokens": 3186518.0,
|
|
"step": 1830
|
|
},
|
|
{
|
|
"entropy": 6.0236879825592045,
|
|
"epoch": 0.14277377942034625,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999525088722673,
|
|
"loss": 6.0661,
|
|
"mean_token_accuracy": 0.12889007702469826,
|
|
"num_tokens": 3195246.0,
|
|
"step": 1835
|
|
},
|
|
{
|
|
"entropy": 6.133167791366577,
|
|
"epoch": 0.1431628087920638,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999519377476711,
|
|
"loss": 6.0603,
|
|
"mean_token_accuracy": 0.13114069998264313,
|
|
"num_tokens": 3203946.0,
|
|
"step": 1840
|
|
},
|
|
{
|
|
"entropy": 6.075826406478882,
|
|
"epoch": 0.14355183816378136,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004999513632097872,
|
|
"loss": 6.0779,
|
|
"mean_token_accuracy": 0.13058586344122886,
|
|
"num_tokens": 3212208.0,
|
|
"step": 1845
|
|
},
|
|
{
|
|
"entropy": 6.049823665618897,
|
|
"epoch": 0.14394086753549892,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999507852586245,
|
|
"loss": 6.032,
|
|
"mean_token_accuracy": 0.13192145377397538,
|
|
"num_tokens": 3221572.0,
|
|
"step": 1850
|
|
},
|
|
{
|
|
"entropy": 6.209538269042969,
|
|
"epoch": 0.14432989690721648,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999502038941917,
|
|
"loss": 6.1448,
|
|
"mean_token_accuracy": 0.12059496194124222,
|
|
"num_tokens": 3230898.0,
|
|
"step": 1855
|
|
},
|
|
{
|
|
"entropy": 6.027826261520386,
|
|
"epoch": 0.14471892627893407,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999496191164975,
|
|
"loss": 6.1193,
|
|
"mean_token_accuracy": 0.12588949352502823,
|
|
"num_tokens": 3240524.0,
|
|
"step": 1860
|
|
},
|
|
{
|
|
"entropy": 6.023482465744019,
|
|
"epoch": 0.14510795565065163,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000499949030925551,
|
|
"loss": 5.8799,
|
|
"mean_token_accuracy": 0.13492048904299736,
|
|
"num_tokens": 3248864.0,
|
|
"step": 1865
|
|
},
|
|
{
|
|
"entropy": 6.037996482849121,
|
|
"epoch": 0.14549698502236919,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004999484393213609,
|
|
"loss": 6.0606,
|
|
"mean_token_accuracy": 0.1355900526046753,
|
|
"num_tokens": 3256823.0,
|
|
"step": 1870
|
|
},
|
|
{
|
|
"entropy": 6.057331371307373,
|
|
"epoch": 0.14588601439408674,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999478443039363,
|
|
"loss": 5.9644,
|
|
"mean_token_accuracy": 0.1344914734363556,
|
|
"num_tokens": 3265621.0,
|
|
"step": 1875
|
|
},
|
|
{
|
|
"entropy": 6.0083879947662355,
|
|
"epoch": 0.14627504376580433,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004999472458732862,
|
|
"loss": 6.0102,
|
|
"mean_token_accuracy": 0.1359344206750393,
|
|
"num_tokens": 3273515.0,
|
|
"step": 1880
|
|
},
|
|
{
|
|
"entropy": 6.173804712295532,
|
|
"epoch": 0.1466640731375219,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004999466440294198,
|
|
"loss": 6.0896,
|
|
"mean_token_accuracy": 0.13156084194779397,
|
|
"num_tokens": 3282283.0,
|
|
"step": 1885
|
|
},
|
|
{
|
|
"entropy": 6.001734209060669,
|
|
"epoch": 0.14705310250923945,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000499946038772346,
|
|
"loss": 6.0773,
|
|
"mean_token_accuracy": 0.1352427139878273,
|
|
"num_tokens": 3290792.0,
|
|
"step": 1890
|
|
},
|
|
{
|
|
"entropy": 5.976762104034424,
|
|
"epoch": 0.147442131880957,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004999454301020741,
|
|
"loss": 5.9368,
|
|
"mean_token_accuracy": 0.13707238510251046,
|
|
"num_tokens": 3299430.0,
|
|
"step": 1895
|
|
},
|
|
{
|
|
"entropy": 5.993293809890747,
|
|
"epoch": 0.14783116125267456,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004999448180186133,
|
|
"loss": 5.9961,
|
|
"mean_token_accuracy": 0.13929180577397346,
|
|
"num_tokens": 3307949.0,
|
|
"step": 1900
|
|
},
|
|
{
|
|
"entropy": 6.047715377807617,
|
|
"epoch": 0.14822019062439215,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000499944202521973,
|
|
"loss": 6.0372,
|
|
"mean_token_accuracy": 0.13377096503973007,
|
|
"num_tokens": 3316900.0,
|
|
"step": 1905
|
|
},
|
|
{
|
|
"entropy": 6.015314245223999,
|
|
"epoch": 0.1486092199961097,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999435836121624,
|
|
"loss": 5.9554,
|
|
"mean_token_accuracy": 0.14088079035282136,
|
|
"num_tokens": 3325656.0,
|
|
"step": 1910
|
|
},
|
|
{
|
|
"entropy": 6.042827892303467,
|
|
"epoch": 0.14899824936782727,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000499942961289191,
|
|
"loss": 6.1932,
|
|
"mean_token_accuracy": 0.12162845060229302,
|
|
"num_tokens": 3334219.0,
|
|
"step": 1915
|
|
},
|
|
{
|
|
"entropy": 6.065869569778442,
|
|
"epoch": 0.14938727873954483,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999423355530683,
|
|
"loss": 5.9296,
|
|
"mean_token_accuracy": 0.1358857125043869,
|
|
"num_tokens": 3343637.0,
|
|
"step": 1920
|
|
},
|
|
{
|
|
"entropy": 6.0235090255737305,
|
|
"epoch": 0.1497763081112624,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999417064038035,
|
|
"loss": 6.0699,
|
|
"mean_token_accuracy": 0.13096352964639663,
|
|
"num_tokens": 3352624.0,
|
|
"step": 1925
|
|
},
|
|
{
|
|
"entropy": 6.052700424194336,
|
|
"epoch": 0.15016533748297997,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999410738414065,
|
|
"loss": 5.9984,
|
|
"mean_token_accuracy": 0.1420406959950924,
|
|
"num_tokens": 3361394.0,
|
|
"step": 1930
|
|
},
|
|
{
|
|
"entropy": 6.0979896068573,
|
|
"epoch": 0.15055436685469753,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999404378658866,
|
|
"loss": 6.0599,
|
|
"mean_token_accuracy": 0.13491503298282623,
|
|
"num_tokens": 3369406.0,
|
|
"step": 1935
|
|
},
|
|
{
|
|
"entropy": 6.103297758102417,
|
|
"epoch": 0.1509433962264151,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999397984772536,
|
|
"loss": 5.9888,
|
|
"mean_token_accuracy": 0.13660770356655122,
|
|
"num_tokens": 3377737.0,
|
|
"step": 1940
|
|
},
|
|
{
|
|
"entropy": 5.994455289840698,
|
|
"epoch": 0.15133242559813265,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999391556755172,
|
|
"loss": 6.0565,
|
|
"mean_token_accuracy": 0.12739683836698532,
|
|
"num_tokens": 3385514.0,
|
|
"step": 1945
|
|
},
|
|
{
|
|
"entropy": 6.098922872543335,
|
|
"epoch": 0.15172145496985023,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999385094606872,
|
|
"loss": 5.963,
|
|
"mean_token_accuracy": 0.13404503092169762,
|
|
"num_tokens": 3394500.0,
|
|
"step": 1950
|
|
},
|
|
{
|
|
"entropy": 5.984807252883911,
|
|
"epoch": 0.1521104843415678,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004999378598327733,
|
|
"loss": 5.9412,
|
|
"mean_token_accuracy": 0.1348331794142723,
|
|
"num_tokens": 3403289.0,
|
|
"step": 1955
|
|
},
|
|
{
|
|
"entropy": 5.939253139495849,
|
|
"epoch": 0.15249951371328535,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004999372067917854,
|
|
"loss": 5.8884,
|
|
"mean_token_accuracy": 0.15021392703056335,
|
|
"num_tokens": 3410892.0,
|
|
"step": 1960
|
|
},
|
|
{
|
|
"entropy": 5.834979009628296,
|
|
"epoch": 0.1528885430850029,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999365503377335,
|
|
"loss": 5.9617,
|
|
"mean_token_accuracy": 0.13714786618947983,
|
|
"num_tokens": 3420329.0,
|
|
"step": 1965
|
|
},
|
|
{
|
|
"entropy": 6.084909963607788,
|
|
"epoch": 0.1532775724567205,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004999358904706273,
|
|
"loss": 5.9688,
|
|
"mean_token_accuracy": 0.13642629608511925,
|
|
"num_tokens": 3429429.0,
|
|
"step": 1970
|
|
},
|
|
{
|
|
"entropy": 6.076066732406616,
|
|
"epoch": 0.15366660182843805,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004999352271904771,
|
|
"loss": 6.1029,
|
|
"mean_token_accuracy": 0.12609972804784775,
|
|
"num_tokens": 3438198.0,
|
|
"step": 1975
|
|
},
|
|
{
|
|
"entropy": 6.189109134674072,
|
|
"epoch": 0.1540556312001556,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999345604972928,
|
|
"loss": 6.2177,
|
|
"mean_token_accuracy": 0.13063327968120575,
|
|
"num_tokens": 3447732.0,
|
|
"step": 1980
|
|
},
|
|
{
|
|
"entropy": 6.029603958129883,
|
|
"epoch": 0.15444466057187317,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004999338903910846,
|
|
"loss": 6.0054,
|
|
"mean_token_accuracy": 0.13503487557172775,
|
|
"num_tokens": 3456392.0,
|
|
"step": 1985
|
|
},
|
|
{
|
|
"entropy": 6.005403804779053,
|
|
"epoch": 0.15483368994359073,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999332168718626,
|
|
"loss": 6.0161,
|
|
"mean_token_accuracy": 0.13200653418898584,
|
|
"num_tokens": 3464473.0,
|
|
"step": 1990
|
|
},
|
|
{
|
|
"entropy": 6.1040510654449465,
|
|
"epoch": 0.15522271931530832,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999325399396371,
|
|
"loss": 6.0141,
|
|
"mean_token_accuracy": 0.1325117267668247,
|
|
"num_tokens": 3473740.0,
|
|
"step": 1995
|
|
},
|
|
{
|
|
"entropy": 5.883322858810425,
|
|
"epoch": 0.15561174868702587,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999318595944183,
|
|
"loss": 5.8954,
|
|
"mean_token_accuracy": 0.13888766765594482,
|
|
"num_tokens": 3482249.0,
|
|
"step": 2000
|
|
},
|
|
{
|
|
"entropy": 6.13586015701294,
|
|
"epoch": 0.15600077805874343,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004999311758362166,
|
|
"loss": 6.1349,
|
|
"mean_token_accuracy": 0.13064591959118843,
|
|
"num_tokens": 3490753.0,
|
|
"step": 2005
|
|
},
|
|
{
|
|
"entropy": 6.116284036636353,
|
|
"epoch": 0.156389807430461,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999304886650422,
|
|
"loss": 6.0846,
|
|
"mean_token_accuracy": 0.13239059895277022,
|
|
"num_tokens": 3499373.0,
|
|
"step": 2010
|
|
},
|
|
{
|
|
"entropy": 6.054863214492798,
|
|
"epoch": 0.15677883680217858,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999297980809058,
|
|
"loss": 6.0559,
|
|
"mean_token_accuracy": 0.1292659781873226,
|
|
"num_tokens": 3508344.0,
|
|
"step": 2015
|
|
},
|
|
{
|
|
"entropy": 6.070051670074463,
|
|
"epoch": 0.15716786617389614,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999291040838176,
|
|
"loss": 6.0221,
|
|
"mean_token_accuracy": 0.1305907964706421,
|
|
"num_tokens": 3517009.0,
|
|
"step": 2020
|
|
},
|
|
{
|
|
"entropy": 5.993431854248047,
|
|
"epoch": 0.1575568955456137,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004999284066737884,
|
|
"loss": 6.0578,
|
|
"mean_token_accuracy": 0.13199557438492776,
|
|
"num_tokens": 3525989.0,
|
|
"step": 2025
|
|
},
|
|
{
|
|
"entropy": 6.075912952423096,
|
|
"epoch": 0.15794592491733125,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004999277058508285,
|
|
"loss": 5.937,
|
|
"mean_token_accuracy": 0.13278207182884216,
|
|
"num_tokens": 3533947.0,
|
|
"step": 2030
|
|
},
|
|
{
|
|
"entropy": 5.966842985153198,
|
|
"epoch": 0.1583349542890488,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004999270016149486,
|
|
"loss": 6.0045,
|
|
"mean_token_accuracy": 0.13214736357331275,
|
|
"num_tokens": 3541974.0,
|
|
"step": 2035
|
|
},
|
|
{
|
|
"entropy": 6.0549215316772464,
|
|
"epoch": 0.1587239836607664,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004999262939661596,
|
|
"loss": 5.9382,
|
|
"mean_token_accuracy": 0.13887585699558258,
|
|
"num_tokens": 3550436.0,
|
|
"step": 2040
|
|
},
|
|
{
|
|
"entropy": 6.002714729309082,
|
|
"epoch": 0.15911301303248396,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004999255829044721,
|
|
"loss": 5.9174,
|
|
"mean_token_accuracy": 0.14426243603229522,
|
|
"num_tokens": 3558283.0,
|
|
"step": 2045
|
|
},
|
|
{
|
|
"entropy": 5.845792150497436,
|
|
"epoch": 0.15950204240420152,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999248684298968,
|
|
"loss": 5.8663,
|
|
"mean_token_accuracy": 0.14373865500092506,
|
|
"num_tokens": 3566968.0,
|
|
"step": 2050
|
|
},
|
|
{
|
|
"entropy": 6.07386269569397,
|
|
"epoch": 0.15989107177591907,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999241505424447,
|
|
"loss": 5.9959,
|
|
"mean_token_accuracy": 0.13418042808771133,
|
|
"num_tokens": 3575580.0,
|
|
"step": 2055
|
|
},
|
|
{
|
|
"entropy": 6.02042441368103,
|
|
"epoch": 0.16028010114763663,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999234292421265,
|
|
"loss": 6.0676,
|
|
"mean_token_accuracy": 0.12927082180976868,
|
|
"num_tokens": 3584389.0,
|
|
"step": 2060
|
|
},
|
|
{
|
|
"entropy": 6.002479553222656,
|
|
"epoch": 0.16066913051935422,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999227045289535,
|
|
"loss": 5.8982,
|
|
"mean_token_accuracy": 0.13991354107856752,
|
|
"num_tokens": 3593009.0,
|
|
"step": 2065
|
|
},
|
|
{
|
|
"entropy": 5.889169025421142,
|
|
"epoch": 0.16105815989107178,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004999219764029363,
|
|
"loss": 5.9355,
|
|
"mean_token_accuracy": 0.13826065212488176,
|
|
"num_tokens": 3601914.0,
|
|
"step": 2070
|
|
},
|
|
{
|
|
"entropy": 5.950252914428711,
|
|
"epoch": 0.16144718926278934,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004999212448640861,
|
|
"loss": 5.9064,
|
|
"mean_token_accuracy": 0.13915136381983756,
|
|
"num_tokens": 3609883.0,
|
|
"step": 2075
|
|
},
|
|
{
|
|
"entropy": 5.898676490783691,
|
|
"epoch": 0.1618362186345069,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004999205099124141,
|
|
"loss": 5.8388,
|
|
"mean_token_accuracy": 0.14299683198332785,
|
|
"num_tokens": 3618103.0,
|
|
"step": 2080
|
|
},
|
|
{
|
|
"entropy": 6.112964773178101,
|
|
"epoch": 0.16222524800622448,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004999197715479313,
|
|
"loss": 6.1127,
|
|
"mean_token_accuracy": 0.13377076312899588,
|
|
"num_tokens": 3625861.0,
|
|
"step": 2085
|
|
},
|
|
{
|
|
"entropy": 5.9404994487762455,
|
|
"epoch": 0.16261427737794204,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004999190297706489,
|
|
"loss": 5.8925,
|
|
"mean_token_accuracy": 0.13251852318644525,
|
|
"num_tokens": 3634498.0,
|
|
"step": 2090
|
|
},
|
|
{
|
|
"entropy": 5.898734521865845,
|
|
"epoch": 0.1630033067496596,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999182845805783,
|
|
"loss": 5.8468,
|
|
"mean_token_accuracy": 0.13533063381910324,
|
|
"num_tokens": 3644186.0,
|
|
"step": 2095
|
|
},
|
|
{
|
|
"entropy": 5.939842367172242,
|
|
"epoch": 0.16339233612137716,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004999175359777306,
|
|
"loss": 5.9913,
|
|
"mean_token_accuracy": 0.13560497462749482,
|
|
"num_tokens": 3652831.0,
|
|
"step": 2100
|
|
},
|
|
{
|
|
"entropy": 6.046018981933594,
|
|
"epoch": 0.16378136549309472,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004999167839621174,
|
|
"loss": 5.828,
|
|
"mean_token_accuracy": 0.14007091671228408,
|
|
"num_tokens": 3661230.0,
|
|
"step": 2105
|
|
},
|
|
{
|
|
"entropy": 5.934693050384522,
|
|
"epoch": 0.1641703948648123,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004999160285337501,
|
|
"loss": 5.9996,
|
|
"mean_token_accuracy": 0.13516139164566993,
|
|
"num_tokens": 3669250.0,
|
|
"step": 2110
|
|
},
|
|
{
|
|
"entropy": 5.986788940429688,
|
|
"epoch": 0.16455942423652986,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004999152696926399,
|
|
"loss": 5.9652,
|
|
"mean_token_accuracy": 0.13469953909516336,
|
|
"num_tokens": 3677568.0,
|
|
"step": 2115
|
|
},
|
|
{
|
|
"entropy": 5.97665491104126,
|
|
"epoch": 0.16494845360824742,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004999145074387985,
|
|
"loss": 5.9642,
|
|
"mean_token_accuracy": 0.143291874229908,
|
|
"num_tokens": 3685488.0,
|
|
"step": 2120
|
|
},
|
|
{
|
|
"entropy": 5.9346582889556885,
|
|
"epoch": 0.16533748297996498,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999137417722374,
|
|
"loss": 5.9314,
|
|
"mean_token_accuracy": 0.13681203424930571,
|
|
"num_tokens": 3694357.0,
|
|
"step": 2125
|
|
},
|
|
{
|
|
"entropy": 6.027693557739258,
|
|
"epoch": 0.16572651235168256,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004999129726929684,
|
|
"loss": 6.0176,
|
|
"mean_token_accuracy": 0.13631885200738908,
|
|
"num_tokens": 3703173.0,
|
|
"step": 2130
|
|
},
|
|
{
|
|
"entropy": 5.972741603851318,
|
|
"epoch": 0.16611554172340012,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004999122002010029,
|
|
"loss": 5.9744,
|
|
"mean_token_accuracy": 0.13786721974611282,
|
|
"num_tokens": 3712070.0,
|
|
"step": 2135
|
|
},
|
|
{
|
|
"entropy": 5.934311628341675,
|
|
"epoch": 0.16650457109511768,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004999114242963527,
|
|
"loss": 5.8658,
|
|
"mean_token_accuracy": 0.1428729884326458,
|
|
"num_tokens": 3720245.0,
|
|
"step": 2140
|
|
},
|
|
{
|
|
"entropy": 5.971720123291016,
|
|
"epoch": 0.16689360046683524,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999106449790298,
|
|
"loss": 5.9747,
|
|
"mean_token_accuracy": 0.13528202399611472,
|
|
"num_tokens": 3730064.0,
|
|
"step": 2145
|
|
},
|
|
{
|
|
"entropy": 5.908024692535401,
|
|
"epoch": 0.1672826298385528,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004999098622490458,
|
|
"loss": 5.9253,
|
|
"mean_token_accuracy": 0.13815728724002838,
|
|
"num_tokens": 3738741.0,
|
|
"step": 2150
|
|
},
|
|
{
|
|
"entropy": 5.983948850631714,
|
|
"epoch": 0.16767165921027039,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004999090761064125,
|
|
"loss": 5.9862,
|
|
"mean_token_accuracy": 0.13889955803751947,
|
|
"num_tokens": 3747472.0,
|
|
"step": 2155
|
|
},
|
|
{
|
|
"entropy": 6.047973775863648,
|
|
"epoch": 0.16806068858198794,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000499908286551142,
|
|
"loss": 6.0004,
|
|
"mean_token_accuracy": 0.13207764700055122,
|
|
"num_tokens": 3756643.0,
|
|
"step": 2160
|
|
},
|
|
{
|
|
"entropy": 6.039718103408814,
|
|
"epoch": 0.1684497179537055,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004999074935832463,
|
|
"loss": 6.1237,
|
|
"mean_token_accuracy": 0.13122752457857131,
|
|
"num_tokens": 3765490.0,
|
|
"step": 2165
|
|
},
|
|
{
|
|
"entropy": 5.998812246322632,
|
|
"epoch": 0.16883874732542306,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004999066972027373,
|
|
"loss": 5.8821,
|
|
"mean_token_accuracy": 0.14074507653713225,
|
|
"num_tokens": 3773063.0,
|
|
"step": 2170
|
|
},
|
|
{
|
|
"entropy": 6.027257585525513,
|
|
"epoch": 0.16922777669714065,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999058974096271,
|
|
"loss": 6.0453,
|
|
"mean_token_accuracy": 0.13097696378827095,
|
|
"num_tokens": 3781763.0,
|
|
"step": 2175
|
|
},
|
|
{
|
|
"entropy": 5.983886289596557,
|
|
"epoch": 0.1696168060688582,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000499905094203928,
|
|
"loss": 6.0319,
|
|
"mean_token_accuracy": 0.13244281932711602,
|
|
"num_tokens": 3790582.0,
|
|
"step": 2180
|
|
},
|
|
{
|
|
"entropy": 5.956745243072509,
|
|
"epoch": 0.17000583544057576,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000499904287585652,
|
|
"loss": 5.8484,
|
|
"mean_token_accuracy": 0.13539646714925765,
|
|
"num_tokens": 3798745.0,
|
|
"step": 2185
|
|
},
|
|
{
|
|
"entropy": 5.91871862411499,
|
|
"epoch": 0.17039486481229332,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004999034775548113,
|
|
"loss": 5.9471,
|
|
"mean_token_accuracy": 0.13498375192284584,
|
|
"num_tokens": 3806901.0,
|
|
"step": 2190
|
|
},
|
|
{
|
|
"entropy": 6.0130002975463865,
|
|
"epoch": 0.17078389418401088,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004999026641114185,
|
|
"loss": 5.8993,
|
|
"mean_token_accuracy": 0.1435001976788044,
|
|
"num_tokens": 3815742.0,
|
|
"step": 2195
|
|
},
|
|
{
|
|
"entropy": 5.964316034317017,
|
|
"epoch": 0.17117292355572847,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004999018472554857,
|
|
"loss": 5.9788,
|
|
"mean_token_accuracy": 0.13596438691020013,
|
|
"num_tokens": 3824468.0,
|
|
"step": 2200
|
|
},
|
|
{
|
|
"entropy": 5.944164085388183,
|
|
"epoch": 0.17156195292744603,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004999010269870253,
|
|
"loss": 5.9378,
|
|
"mean_token_accuracy": 0.14268953651189803,
|
|
"num_tokens": 3832834.0,
|
|
"step": 2205
|
|
},
|
|
{
|
|
"entropy": 5.972387886047363,
|
|
"epoch": 0.17195098229916359,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999002033060498,
|
|
"loss": 5.9802,
|
|
"mean_token_accuracy": 0.14407992959022523,
|
|
"num_tokens": 3841780.0,
|
|
"step": 2210
|
|
},
|
|
{
|
|
"entropy": 6.041182041168213,
|
|
"epoch": 0.17234001167088114,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004998993762125716,
|
|
"loss": 6.0903,
|
|
"mean_token_accuracy": 0.13197002708911895,
|
|
"num_tokens": 3849840.0,
|
|
"step": 2215
|
|
},
|
|
{
|
|
"entropy": 6.026984310150146,
|
|
"epoch": 0.17272904104259873,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004998985457066034,
|
|
"loss": 6.0216,
|
|
"mean_token_accuracy": 0.13372369706630707,
|
|
"num_tokens": 3858204.0,
|
|
"step": 2220
|
|
},
|
|
{
|
|
"entropy": 6.0030601978302,
|
|
"epoch": 0.1731180704143163,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004998977117881576,
|
|
"loss": 5.9642,
|
|
"mean_token_accuracy": 0.13751499205827714,
|
|
"num_tokens": 3866615.0,
|
|
"step": 2225
|
|
},
|
|
{
|
|
"entropy": 6.007308483123779,
|
|
"epoch": 0.17350709978603385,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004998968744572472,
|
|
"loss": 5.9866,
|
|
"mean_token_accuracy": 0.14244203940033912,
|
|
"num_tokens": 3876003.0,
|
|
"step": 2230
|
|
},
|
|
{
|
|
"entropy": 5.93796820640564,
|
|
"epoch": 0.1738961291577514,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004998960337138845,
|
|
"loss": 5.9156,
|
|
"mean_token_accuracy": 0.13770739510655403,
|
|
"num_tokens": 3884362.0,
|
|
"step": 2235
|
|
},
|
|
{
|
|
"entropy": 5.9320573806762695,
|
|
"epoch": 0.17428515852946896,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004998951895580826,
|
|
"loss": 5.8774,
|
|
"mean_token_accuracy": 0.13987934663891793,
|
|
"num_tokens": 3893177.0,
|
|
"step": 2240
|
|
},
|
|
{
|
|
"entropy": 5.971139669418335,
|
|
"epoch": 0.17467418790118655,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004998943419898542,
|
|
"loss": 5.9155,
|
|
"mean_token_accuracy": 0.14205707982182503,
|
|
"num_tokens": 3903006.0,
|
|
"step": 2245
|
|
},
|
|
{
|
|
"entropy": 5.929980039596558,
|
|
"epoch": 0.1750632172729041,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004998934910092119,
|
|
"loss": 5.7919,
|
|
"mean_token_accuracy": 0.14135243073105813,
|
|
"num_tokens": 3912256.0,
|
|
"step": 2250
|
|
},
|
|
{
|
|
"entropy": 5.8668214797973635,
|
|
"epoch": 0.17545224664462167,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004998926366161689,
|
|
"loss": 5.9693,
|
|
"mean_token_accuracy": 0.13715998083353043,
|
|
"num_tokens": 3921121.0,
|
|
"step": 2255
|
|
},
|
|
{
|
|
"entropy": 5.989951181411743,
|
|
"epoch": 0.17584127601633923,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004998917788107383,
|
|
"loss": 5.913,
|
|
"mean_token_accuracy": 0.1377982333302498,
|
|
"num_tokens": 3929348.0,
|
|
"step": 2260
|
|
},
|
|
{
|
|
"entropy": 6.011690330505371,
|
|
"epoch": 0.17623030538805678,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004998909175929326,
|
|
"loss": 6.0839,
|
|
"mean_token_accuracy": 0.13305942490696906,
|
|
"num_tokens": 3938073.0,
|
|
"step": 2265
|
|
},
|
|
{
|
|
"entropy": 6.043408823013306,
|
|
"epoch": 0.17661933475977437,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004998900529627653,
|
|
"loss": 6.0569,
|
|
"mean_token_accuracy": 0.1335141181945801,
|
|
"num_tokens": 3946641.0,
|
|
"step": 2270
|
|
},
|
|
{
|
|
"entropy": 6.023313522338867,
|
|
"epoch": 0.17700836413149193,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004998891849202495,
|
|
"loss": 5.9174,
|
|
"mean_token_accuracy": 0.1370786502957344,
|
|
"num_tokens": 3954586.0,
|
|
"step": 2275
|
|
},
|
|
{
|
|
"entropy": 5.9676063537597654,
|
|
"epoch": 0.1773973935032095,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.000499888313465398,
|
|
"loss": 5.987,
|
|
"mean_token_accuracy": 0.13805045634508134,
|
|
"num_tokens": 3963745.0,
|
|
"step": 2280
|
|
},
|
|
{
|
|
"entropy": 5.902595329284668,
|
|
"epoch": 0.17778642287492705,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004998874385982247,
|
|
"loss": 5.7992,
|
|
"mean_token_accuracy": 0.14355223774909973,
|
|
"num_tokens": 3972452.0,
|
|
"step": 2285
|
|
},
|
|
{
|
|
"entropy": 5.860375881195068,
|
|
"epoch": 0.17817545224664463,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004998865603187421,
|
|
"loss": 5.9098,
|
|
"mean_token_accuracy": 0.14029547646641732,
|
|
"num_tokens": 3980770.0,
|
|
"step": 2290
|
|
},
|
|
{
|
|
"entropy": 6.034819173812866,
|
|
"epoch": 0.1785644816183622,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000499885678626964,
|
|
"loss": 5.953,
|
|
"mean_token_accuracy": 0.13449540436267854,
|
|
"num_tokens": 3989545.0,
|
|
"step": 2295
|
|
},
|
|
{
|
|
"entropy": 6.004922103881836,
|
|
"epoch": 0.17895351099007975,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004998847935229038,
|
|
"loss": 5.8959,
|
|
"mean_token_accuracy": 0.1386812575161457,
|
|
"num_tokens": 3998034.0,
|
|
"step": 2300
|
|
},
|
|
{
|
|
"entropy": 5.856968212127685,
|
|
"epoch": 0.1793425403617973,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004998839050065746,
|
|
"loss": 5.9295,
|
|
"mean_token_accuracy": 0.14095935076475144,
|
|
"num_tokens": 4007110.0,
|
|
"step": 2305
|
|
},
|
|
{
|
|
"entropy": 6.007277154922486,
|
|
"epoch": 0.17973156973351487,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004998830130779902,
|
|
"loss": 5.9892,
|
|
"mean_token_accuracy": 0.12848054468631745,
|
|
"num_tokens": 4015930.0,
|
|
"step": 2310
|
|
},
|
|
{
|
|
"entropy": 5.873305606842041,
|
|
"epoch": 0.18012059910523245,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000499882117737164,
|
|
"loss": 5.8077,
|
|
"mean_token_accuracy": 0.14259375482797623,
|
|
"num_tokens": 4024510.0,
|
|
"step": 2315
|
|
},
|
|
{
|
|
"entropy": 5.8865501403808596,
|
|
"epoch": 0.18050962847695,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004998812189841096,
|
|
"loss": 5.9269,
|
|
"mean_token_accuracy": 0.13981180191040038,
|
|
"num_tokens": 4033714.0,
|
|
"step": 2320
|
|
},
|
|
{
|
|
"entropy": 6.130800390243531,
|
|
"epoch": 0.18089865784866757,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004998803168188407,
|
|
"loss": 6.1026,
|
|
"mean_token_accuracy": 0.12641506418585777,
|
|
"num_tokens": 4042376.0,
|
|
"step": 2325
|
|
},
|
|
{
|
|
"entropy": 5.929910326004029,
|
|
"epoch": 0.18128768722038513,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004998794112413708,
|
|
"loss": 5.8759,
|
|
"mean_token_accuracy": 0.14239312782883645,
|
|
"num_tokens": 4050521.0,
|
|
"step": 2330
|
|
},
|
|
{
|
|
"entropy": 5.996482610702515,
|
|
"epoch": 0.18167671659210272,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004998785022517137,
|
|
"loss": 6.0508,
|
|
"mean_token_accuracy": 0.1390003964304924,
|
|
"num_tokens": 4059384.0,
|
|
"step": 2335
|
|
},
|
|
{
|
|
"entropy": 5.929978275299073,
|
|
"epoch": 0.18206574596382027,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004998775898498835,
|
|
"loss": 5.9167,
|
|
"mean_token_accuracy": 0.140751139074564,
|
|
"num_tokens": 4067655.0,
|
|
"step": 2340
|
|
},
|
|
{
|
|
"entropy": 6.006234645843506,
|
|
"epoch": 0.18245477533553783,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004998766740358936,
|
|
"loss": 5.8866,
|
|
"mean_token_accuracy": 0.1419488400220871,
|
|
"num_tokens": 4075828.0,
|
|
"step": 2345
|
|
},
|
|
{
|
|
"entropy": 5.950083684921265,
|
|
"epoch": 0.1828438047072554,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004998757548097582,
|
|
"loss": 5.8618,
|
|
"mean_token_accuracy": 0.141505366563797,
|
|
"num_tokens": 4083796.0,
|
|
"step": 2350
|
|
},
|
|
{
|
|
"entropy": 5.9189080715179445,
|
|
"epoch": 0.18323283407897295,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004998748321714911,
|
|
"loss": 5.9812,
|
|
"mean_token_accuracy": 0.14023018926382064,
|
|
"num_tokens": 4092981.0,
|
|
"step": 2355
|
|
},
|
|
{
|
|
"entropy": 5.950366830825805,
|
|
"epoch": 0.18362186345069054,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004998739061211065,
|
|
"loss": 5.8082,
|
|
"mean_token_accuracy": 0.14436838626861573,
|
|
"num_tokens": 4101363.0,
|
|
"step": 2360
|
|
},
|
|
{
|
|
"entropy": 5.902071523666382,
|
|
"epoch": 0.1840108928224081,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004998729766586181,
|
|
"loss": 5.8873,
|
|
"mean_token_accuracy": 0.13393877521157266,
|
|
"num_tokens": 4110164.0,
|
|
"step": 2365
|
|
},
|
|
{
|
|
"entropy": 6.013533592224121,
|
|
"epoch": 0.18439992219412565,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004998720437840403,
|
|
"loss": 5.9939,
|
|
"mean_token_accuracy": 0.13625792413949966,
|
|
"num_tokens": 4119098.0,
|
|
"step": 2370
|
|
},
|
|
{
|
|
"entropy": 5.958068323135376,
|
|
"epoch": 0.1847889515658432,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004998711074973871,
|
|
"loss": 5.9052,
|
|
"mean_token_accuracy": 0.1381172902882099,
|
|
"num_tokens": 4127522.0,
|
|
"step": 2375
|
|
},
|
|
{
|
|
"entropy": 5.918181610107422,
|
|
"epoch": 0.1851779809375608,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004998701677986728,
|
|
"loss": 5.9296,
|
|
"mean_token_accuracy": 0.14592336267232894,
|
|
"num_tokens": 4136311.0,
|
|
"step": 2380
|
|
},
|
|
{
|
|
"entropy": 5.891524600982666,
|
|
"epoch": 0.18556701030927836,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004998692246879116,
|
|
"loss": 5.8622,
|
|
"mean_token_accuracy": 0.1465703673660755,
|
|
"num_tokens": 4145160.0,
|
|
"step": 2385
|
|
},
|
|
{
|
|
"entropy": 5.92075252532959,
|
|
"epoch": 0.18595603968099592,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004998682781651178,
|
|
"loss": 5.8423,
|
|
"mean_token_accuracy": 0.14644088521599768,
|
|
"num_tokens": 4153921.0,
|
|
"step": 2390
|
|
},
|
|
{
|
|
"entropy": 5.897768163681031,
|
|
"epoch": 0.18634506905271347,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004998673282303059,
|
|
"loss": 5.9004,
|
|
"mean_token_accuracy": 0.1373889960348606,
|
|
"num_tokens": 4162580.0,
|
|
"step": 2395
|
|
},
|
|
{
|
|
"entropy": 5.938247013092041,
|
|
"epoch": 0.18673409842443103,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004998663748834901,
|
|
"loss": 5.9085,
|
|
"mean_token_accuracy": 0.1424074500799179,
|
|
"num_tokens": 4170623.0,
|
|
"step": 2400
|
|
},
|
|
{
|
|
"entropy": 5.89056625366211,
|
|
"epoch": 0.18712312779614862,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004998654181246851,
|
|
"loss": 5.9017,
|
|
"mean_token_accuracy": 0.14853493720293046,
|
|
"num_tokens": 4178724.0,
|
|
"step": 2405
|
|
},
|
|
{
|
|
"entropy": 5.93064398765564,
|
|
"epoch": 0.18751215716786618,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004998644579539052,
|
|
"loss": 5.9023,
|
|
"mean_token_accuracy": 0.144643697142601,
|
|
"num_tokens": 4187773.0,
|
|
"step": 2410
|
|
},
|
|
{
|
|
"entropy": 5.943702554702758,
|
|
"epoch": 0.18790118653958374,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000499863494371165,
|
|
"loss": 5.8964,
|
|
"mean_token_accuracy": 0.13755654245615007,
|
|
"num_tokens": 4196628.0,
|
|
"step": 2415
|
|
},
|
|
{
|
|
"entropy": 5.93807806968689,
|
|
"epoch": 0.1882902159113013,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004998625273764793,
|
|
"loss": 5.9298,
|
|
"mean_token_accuracy": 0.13933664411306382,
|
|
"num_tokens": 4205090.0,
|
|
"step": 2420
|
|
},
|
|
{
|
|
"entropy": 5.932505655288696,
|
|
"epoch": 0.18867924528301888,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004998615569698626,
|
|
"loss": 5.8363,
|
|
"mean_token_accuracy": 0.1450929120182991,
|
|
"num_tokens": 4212757.0,
|
|
"step": 2425
|
|
},
|
|
{
|
|
"entropy": 5.823395776748657,
|
|
"epoch": 0.18906827465473644,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004998605831513296,
|
|
"loss": 5.9182,
|
|
"mean_token_accuracy": 0.14058506786823272,
|
|
"num_tokens": 4221556.0,
|
|
"step": 2430
|
|
},
|
|
{
|
|
"entropy": 5.937485074996948,
|
|
"epoch": 0.189457304026454,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004998596059208953,
|
|
"loss": 5.9248,
|
|
"mean_token_accuracy": 0.1372585728764534,
|
|
"num_tokens": 4231524.0,
|
|
"step": 2435
|
|
},
|
|
{
|
|
"entropy": 5.953117704391479,
|
|
"epoch": 0.18984633339817156,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004998586252785743,
|
|
"loss": 5.9309,
|
|
"mean_token_accuracy": 0.1459472119808197,
|
|
"num_tokens": 4240229.0,
|
|
"step": 2440
|
|
},
|
|
{
|
|
"entropy": 5.9444538116455075,
|
|
"epoch": 0.19023536276988912,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004998576412243816,
|
|
"loss": 5.8143,
|
|
"mean_token_accuracy": 0.1471335157752037,
|
|
"num_tokens": 4248053.0,
|
|
"step": 2445
|
|
},
|
|
{
|
|
"entropy": 5.918678903579712,
|
|
"epoch": 0.1906243921416067,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004998566537583321,
|
|
"loss": 5.8532,
|
|
"mean_token_accuracy": 0.14176826030015946,
|
|
"num_tokens": 4256019.0,
|
|
"step": 2450
|
|
},
|
|
{
|
|
"entropy": 5.843954420089721,
|
|
"epoch": 0.19101342151332426,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004998556628804408,
|
|
"loss": 5.8438,
|
|
"mean_token_accuracy": 0.1426212564110756,
|
|
"num_tokens": 4263805.0,
|
|
"step": 2455
|
|
},
|
|
{
|
|
"entropy": 5.9143171310424805,
|
|
"epoch": 0.19140245088504182,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004998546685907225,
|
|
"loss": 5.9178,
|
|
"mean_token_accuracy": 0.1378533884882927,
|
|
"num_tokens": 4272712.0,
|
|
"step": 2460
|
|
},
|
|
{
|
|
"entropy": 5.991207647323608,
|
|
"epoch": 0.19179148025675938,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004998536708891927,
|
|
"loss": 5.8363,
|
|
"mean_token_accuracy": 0.144564937800169,
|
|
"num_tokens": 4281222.0,
|
|
"step": 2465
|
|
},
|
|
{
|
|
"entropy": 5.906220293045044,
|
|
"epoch": 0.19218050962847694,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004998526697758663,
|
|
"loss": 5.9584,
|
|
"mean_token_accuracy": 0.13287648782134057,
|
|
"num_tokens": 4290558.0,
|
|
"step": 2470
|
|
},
|
|
{
|
|
"entropy": 6.054517126083374,
|
|
"epoch": 0.19256953900019452,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004998516652507585,
|
|
"loss": 5.9903,
|
|
"mean_token_accuracy": 0.13348187655210494,
|
|
"num_tokens": 4299684.0,
|
|
"step": 2475
|
|
},
|
|
{
|
|
"entropy": 5.8710531234741214,
|
|
"epoch": 0.19295856837191208,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004998506573138846,
|
|
"loss": 5.927,
|
|
"mean_token_accuracy": 0.14006511270999908,
|
|
"num_tokens": 4308938.0,
|
|
"step": 2480
|
|
},
|
|
{
|
|
"entropy": 5.83897180557251,
|
|
"epoch": 0.19334759774362964,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004998496459652598,
|
|
"loss": 5.7816,
|
|
"mean_token_accuracy": 0.14527052342891694,
|
|
"num_tokens": 4317646.0,
|
|
"step": 2485
|
|
},
|
|
{
|
|
"entropy": 5.931606197357178,
|
|
"epoch": 0.1937366271153472,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004998486312048995,
|
|
"loss": 5.9224,
|
|
"mean_token_accuracy": 0.1375634677708149,
|
|
"num_tokens": 4326876.0,
|
|
"step": 2490
|
|
},
|
|
{
|
|
"entropy": 5.898051452636719,
|
|
"epoch": 0.19412565648706478,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004998476130328193,
|
|
"loss": 5.8935,
|
|
"mean_token_accuracy": 0.13777990266680717,
|
|
"num_tokens": 4335391.0,
|
|
"step": 2495
|
|
},
|
|
{
|
|
"entropy": 6.025007343292236,
|
|
"epoch": 0.19451468585878234,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004998465914490343,
|
|
"loss": 5.8689,
|
|
"mean_token_accuracy": 0.1444871500134468,
|
|
"num_tokens": 4343253.0,
|
|
"step": 2500
|
|
},
|
|
{
|
|
"entropy": 5.7705286026000975,
|
|
"epoch": 0.1949037152304999,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00049984556645356,
|
|
"loss": 5.8284,
|
|
"mean_token_accuracy": 0.1411684401333332,
|
|
"num_tokens": 4352161.0,
|
|
"step": 2505
|
|
},
|
|
{
|
|
"entropy": 5.90225625038147,
|
|
"epoch": 0.19529274460221746,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004998445380464124,
|
|
"loss": 5.7931,
|
|
"mean_token_accuracy": 0.14809902310371398,
|
|
"num_tokens": 4360414.0,
|
|
"step": 2510
|
|
},
|
|
{
|
|
"entropy": 5.826894283294678,
|
|
"epoch": 0.19568177397393502,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004998435062276066,
|
|
"loss": 5.7789,
|
|
"mean_token_accuracy": 0.14483817145228386,
|
|
"num_tokens": 4369375.0,
|
|
"step": 2515
|
|
},
|
|
{
|
|
"entropy": 5.788335657119751,
|
|
"epoch": 0.1960708033456526,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004998424709971586,
|
|
"loss": 5.8092,
|
|
"mean_token_accuracy": 0.14111023992300034,
|
|
"num_tokens": 4378638.0,
|
|
"step": 2520
|
|
},
|
|
{
|
|
"entropy": 5.939915323257447,
|
|
"epoch": 0.19645983271737016,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004998414323550839,
|
|
"loss": 5.8119,
|
|
"mean_token_accuracy": 0.14674035906791688,
|
|
"num_tokens": 4388262.0,
|
|
"step": 2525
|
|
},
|
|
{
|
|
"entropy": 5.7870588302612305,
|
|
"epoch": 0.19684886208908772,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004998403903013984,
|
|
"loss": 5.7979,
|
|
"mean_token_accuracy": 0.14782465547323226,
|
|
"num_tokens": 4396894.0,
|
|
"step": 2530
|
|
},
|
|
{
|
|
"entropy": 5.969921636581421,
|
|
"epoch": 0.19723789146080528,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004998393448361179,
|
|
"loss": 5.9433,
|
|
"mean_token_accuracy": 0.13837109357118607,
|
|
"num_tokens": 4405455.0,
|
|
"step": 2535
|
|
},
|
|
{
|
|
"entropy": 5.896631145477295,
|
|
"epoch": 0.19762692083252287,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.000499838295959258,
|
|
"loss": 5.8472,
|
|
"mean_token_accuracy": 0.1465500697493553,
|
|
"num_tokens": 4414355.0,
|
|
"step": 2540
|
|
},
|
|
{
|
|
"entropy": 5.742200183868408,
|
|
"epoch": 0.19801595020424043,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.000499837243670835,
|
|
"loss": 5.7279,
|
|
"mean_token_accuracy": 0.15352763384580612,
|
|
"num_tokens": 4422305.0,
|
|
"step": 2545
|
|
},
|
|
{
|
|
"entropy": 5.928265333175659,
|
|
"epoch": 0.19840497957595798,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004998361879708646,
|
|
"loss": 5.873,
|
|
"mean_token_accuracy": 0.14068381041288375,
|
|
"num_tokens": 4430813.0,
|
|
"step": 2550
|
|
},
|
|
{
|
|
"entropy": 5.926475143432617,
|
|
"epoch": 0.19879400894767554,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000499835128859363,
|
|
"loss": 5.841,
|
|
"mean_token_accuracy": 0.14374007433652877,
|
|
"num_tokens": 4440229.0,
|
|
"step": 2555
|
|
},
|
|
{
|
|
"entropy": 5.780596494674683,
|
|
"epoch": 0.1991830383193931,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004998340663363461,
|
|
"loss": 5.8532,
|
|
"mean_token_accuracy": 0.14352698847651482,
|
|
"num_tokens": 4449417.0,
|
|
"step": 2560
|
|
},
|
|
{
|
|
"entropy": 5.9219683647155765,
|
|
"epoch": 0.1995720676911107,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004998330004018301,
|
|
"loss": 5.8948,
|
|
"mean_token_accuracy": 0.13843950033187866,
|
|
"num_tokens": 4457377.0,
|
|
"step": 2565
|
|
},
|
|
{
|
|
"entropy": 5.9005780696868895,
|
|
"epoch": 0.19996109706282825,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004998319310558312,
|
|
"loss": 5.8246,
|
|
"mean_token_accuracy": 0.14109148308634759,
|
|
"num_tokens": 4466839.0,
|
|
"step": 2570
|
|
},
|
|
{
|
|
"entropy": 5.909777736663818,
|
|
"epoch": 0.2003501264345458,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004998308582983657,
|
|
"loss": 5.8519,
|
|
"mean_token_accuracy": 0.141663371771574,
|
|
"num_tokens": 4476369.0,
|
|
"step": 2575
|
|
},
|
|
{
|
|
"entropy": 5.903419256210327,
|
|
"epoch": 0.20073915580626336,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004998297821294497,
|
|
"loss": 5.9178,
|
|
"mean_token_accuracy": 0.13824092075228692,
|
|
"num_tokens": 4485609.0,
|
|
"step": 2580
|
|
},
|
|
{
|
|
"entropy": 5.908690786361694,
|
|
"epoch": 0.20112818517798095,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004998287025490995,
|
|
"loss": 5.8699,
|
|
"mean_token_accuracy": 0.14373262077569962,
|
|
"num_tokens": 4494535.0,
|
|
"step": 2585
|
|
},
|
|
{
|
|
"entropy": 5.880247259140015,
|
|
"epoch": 0.2015172145496985,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004998276195573317,
|
|
"loss": 5.8434,
|
|
"mean_token_accuracy": 0.1369951345026493,
|
|
"num_tokens": 4503133.0,
|
|
"step": 2590
|
|
},
|
|
{
|
|
"entropy": 5.810712814331055,
|
|
"epoch": 0.20190624392141607,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004998265331541627,
|
|
"loss": 5.7537,
|
|
"mean_token_accuracy": 0.1493122473359108,
|
|
"num_tokens": 4511465.0,
|
|
"step": 2595
|
|
},
|
|
{
|
|
"entropy": 5.871229648590088,
|
|
"epoch": 0.20229527329313363,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004998254433396088,
|
|
"loss": 5.8129,
|
|
"mean_token_accuracy": 0.14724370166659356,
|
|
"num_tokens": 4520177.0,
|
|
"step": 2600
|
|
},
|
|
{
|
|
"entropy": 5.932359218597412,
|
|
"epoch": 0.20268430266485118,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004998243501136867,
|
|
"loss": 5.9747,
|
|
"mean_token_accuracy": 0.13881682902574538,
|
|
"num_tokens": 4528370.0,
|
|
"step": 2605
|
|
},
|
|
{
|
|
"entropy": 5.977485609054566,
|
|
"epoch": 0.20307333203656877,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004998232534764129,
|
|
"loss": 6.0051,
|
|
"mean_token_accuracy": 0.13199136704206466,
|
|
"num_tokens": 4538258.0,
|
|
"step": 2610
|
|
},
|
|
{
|
|
"entropy": 5.909580421447754,
|
|
"epoch": 0.20346236140828633,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004998221534278041,
|
|
"loss": 5.8877,
|
|
"mean_token_accuracy": 0.14184263572096825,
|
|
"num_tokens": 4547300.0,
|
|
"step": 2615
|
|
},
|
|
{
|
|
"entropy": 5.943355751037598,
|
|
"epoch": 0.2038513907800039,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004998210499678769,
|
|
"loss": 5.9543,
|
|
"mean_token_accuracy": 0.1334600642323494,
|
|
"num_tokens": 4556877.0,
|
|
"step": 2620
|
|
},
|
|
{
|
|
"entropy": 5.888020420074463,
|
|
"epoch": 0.20424042015172145,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004998199430966481,
|
|
"loss": 5.7991,
|
|
"mean_token_accuracy": 0.14394191280007362,
|
|
"num_tokens": 4565999.0,
|
|
"step": 2625
|
|
},
|
|
{
|
|
"entropy": 5.844756460189819,
|
|
"epoch": 0.20462944952343903,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004998188328141346,
|
|
"loss": 5.8452,
|
|
"mean_token_accuracy": 0.1362882971763611,
|
|
"num_tokens": 4574027.0,
|
|
"step": 2630
|
|
},
|
|
{
|
|
"entropy": 5.827791595458985,
|
|
"epoch": 0.2050184788951566,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004998177191203531,
|
|
"loss": 5.8626,
|
|
"mean_token_accuracy": 0.13262804001569747,
|
|
"num_tokens": 4582402.0,
|
|
"step": 2635
|
|
},
|
|
{
|
|
"entropy": 5.906517028808594,
|
|
"epoch": 0.20540750826687415,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004998166020153204,
|
|
"loss": 5.7876,
|
|
"mean_token_accuracy": 0.14341192394495011,
|
|
"num_tokens": 4590381.0,
|
|
"step": 2640
|
|
},
|
|
{
|
|
"entropy": 5.874189233779907,
|
|
"epoch": 0.2057965376385917,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004998154814990538,
|
|
"loss": 5.8432,
|
|
"mean_token_accuracy": 0.14246118813753128,
|
|
"num_tokens": 4598910.0,
|
|
"step": 2645
|
|
},
|
|
{
|
|
"entropy": 5.984692335128784,
|
|
"epoch": 0.20618556701030927,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00049981435757157,
|
|
"loss": 5.9592,
|
|
"mean_token_accuracy": 0.13533280342817305,
|
|
"num_tokens": 4607400.0,
|
|
"step": 2650
|
|
},
|
|
{
|
|
"entropy": 5.855141973495483,
|
|
"epoch": 0.20657459638202685,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004998132302328862,
|
|
"loss": 5.9087,
|
|
"mean_token_accuracy": 0.14275118559598923,
|
|
"num_tokens": 4616510.0,
|
|
"step": 2655
|
|
},
|
|
{
|
|
"entropy": 5.980443096160888,
|
|
"epoch": 0.2069636257537444,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004998120994830195,
|
|
"loss": 5.8613,
|
|
"mean_token_accuracy": 0.14297095462679862,
|
|
"num_tokens": 4624529.0,
|
|
"step": 2660
|
|
},
|
|
{
|
|
"entropy": 5.857743644714356,
|
|
"epoch": 0.20735265512546197,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.000499810965321987,
|
|
"loss": 5.7977,
|
|
"mean_token_accuracy": 0.14490180611610412,
|
|
"num_tokens": 4632141.0,
|
|
"step": 2665
|
|
},
|
|
{
|
|
"entropy": 5.906196022033692,
|
|
"epoch": 0.20774168449717953,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004998098277498059,
|
|
"loss": 6.0009,
|
|
"mean_token_accuracy": 0.13804857656359673,
|
|
"num_tokens": 4640378.0,
|
|
"step": 2670
|
|
},
|
|
{
|
|
"entropy": 5.898653411865235,
|
|
"epoch": 0.2081307138688971,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004998086867664934,
|
|
"loss": 5.7895,
|
|
"mean_token_accuracy": 0.14342319518327712,
|
|
"num_tokens": 4649313.0,
|
|
"step": 2675
|
|
},
|
|
{
|
|
"entropy": 5.861611032485962,
|
|
"epoch": 0.20851974324061467,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.000499807542372067,
|
|
"loss": 5.8734,
|
|
"mean_token_accuracy": 0.14329290986061097,
|
|
"num_tokens": 4658272.0,
|
|
"step": 2680
|
|
},
|
|
{
|
|
"entropy": 5.853821468353272,
|
|
"epoch": 0.20890877261233223,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004998063945665439,
|
|
"loss": 5.7288,
|
|
"mean_token_accuracy": 0.14896599501371383,
|
|
"num_tokens": 4665970.0,
|
|
"step": 2685
|
|
},
|
|
{
|
|
"entropy": 5.961039733886719,
|
|
"epoch": 0.2092978019840498,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004998052433499416,
|
|
"loss": 6.0048,
|
|
"mean_token_accuracy": 0.13621870279312134,
|
|
"num_tokens": 4675308.0,
|
|
"step": 2690
|
|
},
|
|
{
|
|
"entropy": 5.8872617244720455,
|
|
"epoch": 0.20968683135576735,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004998040887222776,
|
|
"loss": 5.838,
|
|
"mean_token_accuracy": 0.14681472033262252,
|
|
"num_tokens": 4684316.0,
|
|
"step": 2695
|
|
},
|
|
{
|
|
"entropy": 5.83542914390564,
|
|
"epoch": 0.21007586072748494,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004998029306835693,
|
|
"loss": 5.7401,
|
|
"mean_token_accuracy": 0.14747732728719712,
|
|
"num_tokens": 4693029.0,
|
|
"step": 2700
|
|
},
|
|
{
|
|
"entropy": 5.883753108978271,
|
|
"epoch": 0.2104648900992025,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004998017692338344,
|
|
"loss": 5.9438,
|
|
"mean_token_accuracy": 0.13294942378997804,
|
|
"num_tokens": 4702404.0,
|
|
"step": 2705
|
|
},
|
|
{
|
|
"entropy": 5.915159034729004,
|
|
"epoch": 0.21085391947092005,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004998006043730905,
|
|
"loss": 5.9026,
|
|
"mean_token_accuracy": 0.13540939018130302,
|
|
"num_tokens": 4711126.0,
|
|
"step": 2710
|
|
},
|
|
{
|
|
"entropy": 5.926841735839844,
|
|
"epoch": 0.2112429488426376,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004997994361013551,
|
|
"loss": 5.9067,
|
|
"mean_token_accuracy": 0.14510797709226608,
|
|
"num_tokens": 4719816.0,
|
|
"step": 2715
|
|
},
|
|
{
|
|
"entropy": 5.919688940048218,
|
|
"epoch": 0.21163197821435517,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004997982644186461,
|
|
"loss": 5.8586,
|
|
"mean_token_accuracy": 0.1388926051557064,
|
|
"num_tokens": 4728294.0,
|
|
"step": 2720
|
|
},
|
|
{
|
|
"entropy": 5.849535512924194,
|
|
"epoch": 0.21202100758607276,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004997970893249813,
|
|
"loss": 5.7913,
|
|
"mean_token_accuracy": 0.14318636655807496,
|
|
"num_tokens": 4736708.0,
|
|
"step": 2725
|
|
},
|
|
{
|
|
"entropy": 5.886180353164673,
|
|
"epoch": 0.21241003695779032,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004997959108203785,
|
|
"loss": 5.9664,
|
|
"mean_token_accuracy": 0.12757724076509475,
|
|
"num_tokens": 4744893.0,
|
|
"step": 2730
|
|
},
|
|
{
|
|
"entropy": 6.0438158988952635,
|
|
"epoch": 0.21279906632950787,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004997947289048554,
|
|
"loss": 5.9255,
|
|
"mean_token_accuracy": 0.14040105268359185,
|
|
"num_tokens": 4753246.0,
|
|
"step": 2735
|
|
},
|
|
{
|
|
"entropy": 5.84286527633667,
|
|
"epoch": 0.21318809570122543,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004997935435784302,
|
|
"loss": 5.8594,
|
|
"mean_token_accuracy": 0.13238277807831764,
|
|
"num_tokens": 4762229.0,
|
|
"step": 2740
|
|
},
|
|
{
|
|
"entropy": 5.789167261123657,
|
|
"epoch": 0.21357712507294302,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004997923548411208,
|
|
"loss": 5.7953,
|
|
"mean_token_accuracy": 0.14477718472480774,
|
|
"num_tokens": 4771315.0,
|
|
"step": 2745
|
|
},
|
|
{
|
|
"entropy": 5.743027687072754,
|
|
"epoch": 0.21396615444466058,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.000499791162692945,
|
|
"loss": 5.7216,
|
|
"mean_token_accuracy": 0.1552059195935726,
|
|
"num_tokens": 4779848.0,
|
|
"step": 2750
|
|
},
|
|
{
|
|
"entropy": 5.923724365234375,
|
|
"epoch": 0.21435518381637814,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004997899671339214,
|
|
"loss": 5.9608,
|
|
"mean_token_accuracy": 0.13507696092128754,
|
|
"num_tokens": 4788939.0,
|
|
"step": 2755
|
|
},
|
|
{
|
|
"entropy": 5.928030967712402,
|
|
"epoch": 0.2147442131880957,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004997887681640675,
|
|
"loss": 5.862,
|
|
"mean_token_accuracy": 0.14092207103967666,
|
|
"num_tokens": 4797719.0,
|
|
"step": 2760
|
|
},
|
|
{
|
|
"entropy": 5.8962774753570555,
|
|
"epoch": 0.21513324255981325,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004997875657834021,
|
|
"loss": 5.9135,
|
|
"mean_token_accuracy": 0.14009084329009056,
|
|
"num_tokens": 4805601.0,
|
|
"step": 2765
|
|
},
|
|
{
|
|
"entropy": 5.9585367202758786,
|
|
"epoch": 0.21552227193153084,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004997863599919432,
|
|
"loss": 5.8841,
|
|
"mean_token_accuracy": 0.1363997220993042,
|
|
"num_tokens": 4814993.0,
|
|
"step": 2770
|
|
},
|
|
{
|
|
"entropy": 5.927289390563965,
|
|
"epoch": 0.2159113013032484,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004997851507897089,
|
|
"loss": 5.8243,
|
|
"mean_token_accuracy": 0.1399366356432438,
|
|
"num_tokens": 4824156.0,
|
|
"step": 2775
|
|
},
|
|
{
|
|
"entropy": 5.784321880340576,
|
|
"epoch": 0.21630033067496596,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004997839381767178,
|
|
"loss": 5.9144,
|
|
"mean_token_accuracy": 0.13532717600464822,
|
|
"num_tokens": 4833827.0,
|
|
"step": 2780
|
|
},
|
|
{
|
|
"entropy": 5.865825510025024,
|
|
"epoch": 0.21668936004668352,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004997827221529882,
|
|
"loss": 5.8668,
|
|
"mean_token_accuracy": 0.1405027724802494,
|
|
"num_tokens": 4842801.0,
|
|
"step": 2785
|
|
},
|
|
{
|
|
"entropy": 5.798394966125488,
|
|
"epoch": 0.2170783894184011,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004997815027185386,
|
|
"loss": 5.7286,
|
|
"mean_token_accuracy": 0.1471269391477108,
|
|
"num_tokens": 4850928.0,
|
|
"step": 2790
|
|
},
|
|
{
|
|
"entropy": 5.863477325439453,
|
|
"epoch": 0.21746741879011866,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004997802798733874,
|
|
"loss": 5.8353,
|
|
"mean_token_accuracy": 0.14645029380917549,
|
|
"num_tokens": 4859510.0,
|
|
"step": 2795
|
|
},
|
|
{
|
|
"entropy": 5.953133916854858,
|
|
"epoch": 0.21785644816183622,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004997790536175534,
|
|
"loss": 5.8818,
|
|
"mean_token_accuracy": 0.14332858324050904,
|
|
"num_tokens": 4868201.0,
|
|
"step": 2800
|
|
},
|
|
{
|
|
"entropy": 5.833751583099366,
|
|
"epoch": 0.21824547753355378,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004997778239510548,
|
|
"loss": 5.7971,
|
|
"mean_token_accuracy": 0.14518718123435975,
|
|
"num_tokens": 4876896.0,
|
|
"step": 2805
|
|
},
|
|
{
|
|
"entropy": 5.819661283493042,
|
|
"epoch": 0.21863450690527134,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004997765908739106,
|
|
"loss": 5.7628,
|
|
"mean_token_accuracy": 0.15467552095651627,
|
|
"num_tokens": 4885136.0,
|
|
"step": 2810
|
|
},
|
|
{
|
|
"entropy": 5.792523670196533,
|
|
"epoch": 0.21902353627698892,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004997753543861395,
|
|
"loss": 5.7614,
|
|
"mean_token_accuracy": 0.14659688621759415,
|
|
"num_tokens": 4893277.0,
|
|
"step": 2815
|
|
},
|
|
{
|
|
"entropy": 5.824806594848633,
|
|
"epoch": 0.21941256564870648,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00049977411448776,
|
|
"loss": 5.9272,
|
|
"mean_token_accuracy": 0.13800606727600098,
|
|
"num_tokens": 4901977.0,
|
|
"step": 2820
|
|
},
|
|
{
|
|
"entropy": 5.96837682723999,
|
|
"epoch": 0.21980159502042404,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004997728711787912,
|
|
"loss": 5.9202,
|
|
"mean_token_accuracy": 0.1327626369893551,
|
|
"num_tokens": 4910888.0,
|
|
"step": 2825
|
|
},
|
|
{
|
|
"entropy": 5.86808066368103,
|
|
"epoch": 0.2201906243921416,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004997716244592518,
|
|
"loss": 5.9356,
|
|
"mean_token_accuracy": 0.13502828925848007,
|
|
"num_tokens": 4920369.0,
|
|
"step": 2830
|
|
},
|
|
{
|
|
"entropy": 5.960182857513428,
|
|
"epoch": 0.22057965376385918,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004997703743291607,
|
|
"loss": 5.8985,
|
|
"mean_token_accuracy": 0.13375965356826783,
|
|
"num_tokens": 4928799.0,
|
|
"step": 2835
|
|
},
|
|
{
|
|
"entropy": 5.900925159454346,
|
|
"epoch": 0.22096868313557674,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.000499769120788537,
|
|
"loss": 5.7958,
|
|
"mean_token_accuracy": 0.14789656549692154,
|
|
"num_tokens": 4937194.0,
|
|
"step": 2840
|
|
},
|
|
{
|
|
"entropy": 5.85408844947815,
|
|
"epoch": 0.2213577125072943,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004997678638373995,
|
|
"loss": 5.8746,
|
|
"mean_token_accuracy": 0.138755963742733,
|
|
"num_tokens": 4946174.0,
|
|
"step": 2845
|
|
},
|
|
{
|
|
"entropy": 5.856148958206177,
|
|
"epoch": 0.22174674187901186,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004997666034757676,
|
|
"loss": 5.8355,
|
|
"mean_token_accuracy": 0.13359612822532654,
|
|
"num_tokens": 4955376.0,
|
|
"step": 2850
|
|
},
|
|
{
|
|
"entropy": 5.845991516113282,
|
|
"epoch": 0.22213577125072942,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004997653397036603,
|
|
"loss": 5.8388,
|
|
"mean_token_accuracy": 0.14885029271245004,
|
|
"num_tokens": 4964138.0,
|
|
"step": 2855
|
|
},
|
|
{
|
|
"entropy": 5.854672574996949,
|
|
"epoch": 0.222524800622447,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004997640725210965,
|
|
"loss": 5.924,
|
|
"mean_token_accuracy": 0.13829706981778145,
|
|
"num_tokens": 4973868.0,
|
|
"step": 2860
|
|
},
|
|
{
|
|
"entropy": 5.895060682296753,
|
|
"epoch": 0.22291382999416456,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004997628019280958,
|
|
"loss": 5.7884,
|
|
"mean_token_accuracy": 0.14855626970529556,
|
|
"num_tokens": 4982687.0,
|
|
"step": 2865
|
|
},
|
|
{
|
|
"entropy": 5.8665914058685305,
|
|
"epoch": 0.22330285936588212,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004997615279246773,
|
|
"loss": 5.8508,
|
|
"mean_token_accuracy": 0.1380278080701828,
|
|
"num_tokens": 4992072.0,
|
|
"step": 2870
|
|
},
|
|
{
|
|
"entropy": 5.860254573822021,
|
|
"epoch": 0.22369188873759968,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004997602505108603,
|
|
"loss": 5.7939,
|
|
"mean_token_accuracy": 0.1468532294034958,
|
|
"num_tokens": 5000551.0,
|
|
"step": 2875
|
|
},
|
|
{
|
|
"entropy": 5.867898797988891,
|
|
"epoch": 0.22408091810931724,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004997589696866644,
|
|
"loss": 5.958,
|
|
"mean_token_accuracy": 0.13906393349170684,
|
|
"num_tokens": 5009292.0,
|
|
"step": 2880
|
|
},
|
|
{
|
|
"entropy": 5.9254029273986815,
|
|
"epoch": 0.22446994748103483,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004997576854521088,
|
|
"loss": 5.8145,
|
|
"mean_token_accuracy": 0.14045907855033873,
|
|
"num_tokens": 5018407.0,
|
|
"step": 2885
|
|
},
|
|
{
|
|
"entropy": 5.851523542404175,
|
|
"epoch": 0.22485897685275238,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.000499756397807213,
|
|
"loss": 5.8635,
|
|
"mean_token_accuracy": 0.140239942073822,
|
|
"num_tokens": 5027353.0,
|
|
"step": 2890
|
|
},
|
|
{
|
|
"entropy": 5.953854656219482,
|
|
"epoch": 0.22524800622446994,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004997551067519966,
|
|
"loss": 5.8796,
|
|
"mean_token_accuracy": 0.1372043900191784,
|
|
"num_tokens": 5036476.0,
|
|
"step": 2895
|
|
},
|
|
{
|
|
"entropy": 5.852804660797119,
|
|
"epoch": 0.2256370355961875,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004997538122864792,
|
|
"loss": 5.8149,
|
|
"mean_token_accuracy": 0.13800968378782272,
|
|
"num_tokens": 5045132.0,
|
|
"step": 2900
|
|
},
|
|
{
|
|
"entropy": 5.872405099868774,
|
|
"epoch": 0.2260260649679051,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004997525144106804,
|
|
"loss": 5.8308,
|
|
"mean_token_accuracy": 0.14327656477689743,
|
|
"num_tokens": 5053665.0,
|
|
"step": 2905
|
|
},
|
|
{
|
|
"entropy": 5.875136280059815,
|
|
"epoch": 0.22641509433962265,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00049975121312462,
|
|
"loss": 5.7844,
|
|
"mean_token_accuracy": 0.14840312600135802,
|
|
"num_tokens": 5062516.0,
|
|
"step": 2910
|
|
},
|
|
{
|
|
"entropy": 5.844822549819947,
|
|
"epoch": 0.2268041237113402,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004997499084283177,
|
|
"loss": 5.8385,
|
|
"mean_token_accuracy": 0.13938512802124023,
|
|
"num_tokens": 5071260.0,
|
|
"step": 2915
|
|
},
|
|
{
|
|
"entropy": 5.7951945781707765,
|
|
"epoch": 0.22719315308305776,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004997486003217932,
|
|
"loss": 5.7898,
|
|
"mean_token_accuracy": 0.14976079612970353,
|
|
"num_tokens": 5079215.0,
|
|
"step": 2920
|
|
},
|
|
{
|
|
"entropy": 5.8469682216644285,
|
|
"epoch": 0.22758218245477532,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004997472888050664,
|
|
"loss": 5.841,
|
|
"mean_token_accuracy": 0.14187667444348334,
|
|
"num_tokens": 5088404.0,
|
|
"step": 2925
|
|
},
|
|
{
|
|
"entropy": 5.818438100814819,
|
|
"epoch": 0.2279712118264929,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004997459738781573,
|
|
"loss": 5.7768,
|
|
"mean_token_accuracy": 0.14647734835743903,
|
|
"num_tokens": 5096756.0,
|
|
"step": 2930
|
|
},
|
|
{
|
|
"entropy": 5.940578460693359,
|
|
"epoch": 0.22836024119821047,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004997446555410857,
|
|
"loss": 5.9467,
|
|
"mean_token_accuracy": 0.1395805224776268,
|
|
"num_tokens": 5106160.0,
|
|
"step": 2935
|
|
},
|
|
{
|
|
"entropy": 5.773259544372559,
|
|
"epoch": 0.22874927056992803,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004997433337938716,
|
|
"loss": 5.8927,
|
|
"mean_token_accuracy": 0.1411326617002487,
|
|
"num_tokens": 5114915.0,
|
|
"step": 2940
|
|
},
|
|
{
|
|
"entropy": 5.937809038162231,
|
|
"epoch": 0.22913829994164558,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004997420086365351,
|
|
"loss": 5.7841,
|
|
"mean_token_accuracy": 0.14255737289786338,
|
|
"num_tokens": 5123249.0,
|
|
"step": 2945
|
|
},
|
|
{
|
|
"entropy": 5.8355926990509035,
|
|
"epoch": 0.22952732931336317,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004997406800690966,
|
|
"loss": 5.7824,
|
|
"mean_token_accuracy": 0.14376138001680375,
|
|
"num_tokens": 5131906.0,
|
|
"step": 2950
|
|
},
|
|
{
|
|
"entropy": 5.827831602096557,
|
|
"epoch": 0.22991635868508073,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004997393480915758,
|
|
"loss": 5.7615,
|
|
"mean_token_accuracy": 0.14806403890252112,
|
|
"num_tokens": 5140740.0,
|
|
"step": 2955
|
|
},
|
|
{
|
|
"entropy": 5.875302410125732,
|
|
"epoch": 0.2303053880567983,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004997380127039931,
|
|
"loss": 5.9538,
|
|
"mean_token_accuracy": 0.14151290953159332,
|
|
"num_tokens": 5149748.0,
|
|
"step": 2960
|
|
},
|
|
{
|
|
"entropy": 5.797664833068848,
|
|
"epoch": 0.23069441742851585,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004997366739063688,
|
|
"loss": 5.6921,
|
|
"mean_token_accuracy": 0.15163349732756615,
|
|
"num_tokens": 5158475.0,
|
|
"step": 2965
|
|
},
|
|
{
|
|
"entropy": 5.846002006530762,
|
|
"epoch": 0.2310834468002334,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004997353316987231,
|
|
"loss": 5.8743,
|
|
"mean_token_accuracy": 0.13970237150788306,
|
|
"num_tokens": 5166593.0,
|
|
"step": 2970
|
|
},
|
|
{
|
|
"entropy": 5.920862007141113,
|
|
"epoch": 0.231472476171951,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004997339860810765,
|
|
"loss": 5.852,
|
|
"mean_token_accuracy": 0.14107609987258912,
|
|
"num_tokens": 5175557.0,
|
|
"step": 2975
|
|
},
|
|
{
|
|
"entropy": 5.845410299301148,
|
|
"epoch": 0.23186150554366855,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004997326370534495,
|
|
"loss": 5.7464,
|
|
"mean_token_accuracy": 0.14542281255126,
|
|
"num_tokens": 5184140.0,
|
|
"step": 2980
|
|
},
|
|
{
|
|
"entropy": 5.853820180892944,
|
|
"epoch": 0.2322505349153861,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004997312846158622,
|
|
"loss": 5.8495,
|
|
"mean_token_accuracy": 0.13995478302240372,
|
|
"num_tokens": 5192347.0,
|
|
"step": 2985
|
|
},
|
|
{
|
|
"entropy": 5.8931690692901615,
|
|
"epoch": 0.23263956428710367,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004997299287683355,
|
|
"loss": 5.8233,
|
|
"mean_token_accuracy": 0.14461204260587693,
|
|
"num_tokens": 5201327.0,
|
|
"step": 2990
|
|
},
|
|
{
|
|
"entropy": 5.848814344406128,
|
|
"epoch": 0.23302859365882125,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004997285695108898,
|
|
"loss": 5.8972,
|
|
"mean_token_accuracy": 0.14362578094005585,
|
|
"num_tokens": 5209873.0,
|
|
"step": 2995
|
|
},
|
|
{
|
|
"entropy": 5.941117906570435,
|
|
"epoch": 0.2334176230305388,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004997272068435458,
|
|
"loss": 5.8085,
|
|
"mean_token_accuracy": 0.14696044400334357,
|
|
"num_tokens": 5219176.0,
|
|
"step": 3000
|
|
},
|
|
{
|
|
"epoch": 0.2334176230305388,
|
|
"eval_entropy": 5.6975215174809914,
|
|
"eval_loss": 5.874110221862793,
|
|
"eval_mean_token_accuracy": 0.1492114957217647,
|
|
"eval_num_tokens": 5219176.0,
|
|
"eval_runtime": 28.4771,
|
|
"eval_samples_per_second": 1459.348,
|
|
"eval_steps_per_second": 182.427,
|
|
"step": 3000
|
|
},
|
|
{
|
|
"entropy": 5.7831292152404785,
|
|
"epoch": 0.23380665240225637,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.000499725840766324,
|
|
"loss": 5.7429,
|
|
"mean_token_accuracy": 0.14964141547679902,
|
|
"num_tokens": 5227310.0,
|
|
"step": 3005
|
|
},
|
|
{
|
|
"entropy": 5.899445486068726,
|
|
"epoch": 0.23419568177397393,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004997244712792453,
|
|
"loss": 5.8408,
|
|
"mean_token_accuracy": 0.14146490544080734,
|
|
"num_tokens": 5235882.0,
|
|
"step": 3010
|
|
},
|
|
{
|
|
"entropy": 5.845815849304199,
|
|
"epoch": 0.2345847111456915,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004997230983823305,
|
|
"loss": 5.7588,
|
|
"mean_token_accuracy": 0.1443546399474144,
|
|
"num_tokens": 5244149.0,
|
|
"step": 3015
|
|
},
|
|
{
|
|
"entropy": 5.651363325119019,
|
|
"epoch": 0.23497374051740907,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004997217220756003,
|
|
"loss": 5.6202,
|
|
"mean_token_accuracy": 0.1493588164448738,
|
|
"num_tokens": 5252473.0,
|
|
"step": 3020
|
|
},
|
|
{
|
|
"entropy": 5.794226217269897,
|
|
"epoch": 0.23536276988912663,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004997203423590757,
|
|
"loss": 5.7704,
|
|
"mean_token_accuracy": 0.14729913771152497,
|
|
"num_tokens": 5260972.0,
|
|
"step": 3025
|
|
},
|
|
{
|
|
"entropy": 5.830422019958496,
|
|
"epoch": 0.2357517992608442,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004997189592327775,
|
|
"loss": 5.7831,
|
|
"mean_token_accuracy": 0.1408008575439453,
|
|
"num_tokens": 5270513.0,
|
|
"step": 3030
|
|
},
|
|
{
|
|
"entropy": 5.835352849960327,
|
|
"epoch": 0.23614082863256175,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004997175726967268,
|
|
"loss": 5.7502,
|
|
"mean_token_accuracy": 0.13931970819830894,
|
|
"num_tokens": 5278433.0,
|
|
"step": 3035
|
|
},
|
|
{
|
|
"entropy": 5.77889084815979,
|
|
"epoch": 0.23652985800427934,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004997161827509447,
|
|
"loss": 5.7714,
|
|
"mean_token_accuracy": 0.14076305702328681,
|
|
"num_tokens": 5287389.0,
|
|
"step": 3040
|
|
},
|
|
{
|
|
"entropy": 5.832659387588501,
|
|
"epoch": 0.2369188873759969,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004997147893954521,
|
|
"loss": 5.8628,
|
|
"mean_token_accuracy": 0.14170193374156953,
|
|
"num_tokens": 5296220.0,
|
|
"step": 3045
|
|
},
|
|
{
|
|
"entropy": 5.894949436187744,
|
|
"epoch": 0.23730791674771445,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004997133926302702,
|
|
"loss": 5.8093,
|
|
"mean_token_accuracy": 0.1460500732064247,
|
|
"num_tokens": 5304152.0,
|
|
"step": 3050
|
|
},
|
|
{
|
|
"entropy": 5.852946043014526,
|
|
"epoch": 0.237696946119432,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004997119924554204,
|
|
"loss": 5.8277,
|
|
"mean_token_accuracy": 0.14553060084581376,
|
|
"num_tokens": 5312374.0,
|
|
"step": 3055
|
|
},
|
|
{
|
|
"entropy": 5.763966751098633,
|
|
"epoch": 0.23808597549114957,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004997105888709236,
|
|
"loss": 5.7408,
|
|
"mean_token_accuracy": 0.14599811732769014,
|
|
"num_tokens": 5320696.0,
|
|
"step": 3060
|
|
},
|
|
{
|
|
"entropy": 5.867942905426025,
|
|
"epoch": 0.23847500486286716,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004997091818768015,
|
|
"loss": 5.8867,
|
|
"mean_token_accuracy": 0.14129042029380798,
|
|
"num_tokens": 5328754.0,
|
|
"step": 3065
|
|
},
|
|
{
|
|
"entropy": 5.856729507446289,
|
|
"epoch": 0.23886403423458472,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000499707771473075,
|
|
"loss": 5.8397,
|
|
"mean_token_accuracy": 0.14289526790380477,
|
|
"num_tokens": 5337553.0,
|
|
"step": 3070
|
|
},
|
|
{
|
|
"entropy": 5.830549812316894,
|
|
"epoch": 0.23925306360630227,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004997063576597659,
|
|
"loss": 5.7799,
|
|
"mean_token_accuracy": 0.14660679548978806,
|
|
"num_tokens": 5346063.0,
|
|
"step": 3075
|
|
},
|
|
{
|
|
"entropy": 5.812898921966553,
|
|
"epoch": 0.23964209297801983,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004997049404368954,
|
|
"loss": 5.8386,
|
|
"mean_token_accuracy": 0.14468818083405494,
|
|
"num_tokens": 5354187.0,
|
|
"step": 3080
|
|
},
|
|
{
|
|
"entropy": 5.902703523635864,
|
|
"epoch": 0.2400311223497374,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.000499703519804485,
|
|
"loss": 5.8822,
|
|
"mean_token_accuracy": 0.1354278989136219,
|
|
"num_tokens": 5362819.0,
|
|
"step": 3085
|
|
},
|
|
{
|
|
"entropy": 5.818790054321289,
|
|
"epoch": 0.24042015172145498,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004997020957625564,
|
|
"loss": 5.7535,
|
|
"mean_token_accuracy": 0.15776385366916656,
|
|
"num_tokens": 5371249.0,
|
|
"step": 3090
|
|
},
|
|
{
|
|
"entropy": 5.804762887954712,
|
|
"epoch": 0.24080918109317254,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004997006683111312,
|
|
"loss": 5.763,
|
|
"mean_token_accuracy": 0.14027815461158752,
|
|
"num_tokens": 5379284.0,
|
|
"step": 3095
|
|
},
|
|
{
|
|
"entropy": 5.892832899093628,
|
|
"epoch": 0.2411982104648901,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.000499699237450231,
|
|
"loss": 5.8516,
|
|
"mean_token_accuracy": 0.14159384444355966,
|
|
"num_tokens": 5388541.0,
|
|
"step": 3100
|
|
},
|
|
{
|
|
"entropy": 5.850871276855469,
|
|
"epoch": 0.24158723983660765,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004996978031798774,
|
|
"loss": 5.9148,
|
|
"mean_token_accuracy": 0.14342978745698928,
|
|
"num_tokens": 5397226.0,
|
|
"step": 3105
|
|
},
|
|
{
|
|
"entropy": 5.8842658519744875,
|
|
"epoch": 0.24197626920832524,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004996963655000924,
|
|
"loss": 5.8323,
|
|
"mean_token_accuracy": 0.14171799793839454,
|
|
"num_tokens": 5405579.0,
|
|
"step": 3110
|
|
},
|
|
{
|
|
"entropy": 5.872433137893677,
|
|
"epoch": 0.2423652985800428,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004996949244108977,
|
|
"loss": 5.9401,
|
|
"mean_token_accuracy": 0.1336903415620327,
|
|
"num_tokens": 5414529.0,
|
|
"step": 3115
|
|
},
|
|
{
|
|
"entropy": 5.976354360580444,
|
|
"epoch": 0.24275432795176036,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.000499693479912315,
|
|
"loss": 5.9025,
|
|
"mean_token_accuracy": 0.1467768967151642,
|
|
"num_tokens": 5423641.0,
|
|
"step": 3120
|
|
},
|
|
{
|
|
"entropy": 5.834774971008301,
|
|
"epoch": 0.24314335732347792,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004996920320043666,
|
|
"loss": 5.7943,
|
|
"mean_token_accuracy": 0.1434284932911396,
|
|
"num_tokens": 5432558.0,
|
|
"step": 3125
|
|
},
|
|
{
|
|
"entropy": 5.809767198562622,
|
|
"epoch": 0.24353238669519547,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004996905806870742,
|
|
"loss": 5.7496,
|
|
"mean_token_accuracy": 0.14280148446559907,
|
|
"num_tokens": 5441449.0,
|
|
"step": 3130
|
|
},
|
|
{
|
|
"entropy": 5.809779644012451,
|
|
"epoch": 0.24392141606691306,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004996891259604598,
|
|
"loss": 5.7766,
|
|
"mean_token_accuracy": 0.14280980229377746,
|
|
"num_tokens": 5451142.0,
|
|
"step": 3135
|
|
},
|
|
{
|
|
"entropy": 5.825923299789428,
|
|
"epoch": 0.24431044543863062,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004996876678245455,
|
|
"loss": 5.7306,
|
|
"mean_token_accuracy": 0.14882245287299156,
|
|
"num_tokens": 5459290.0,
|
|
"step": 3140
|
|
},
|
|
{
|
|
"entropy": 5.803335380554199,
|
|
"epoch": 0.24469947481034818,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004996862062793536,
|
|
"loss": 5.7535,
|
|
"mean_token_accuracy": 0.14721433073282242,
|
|
"num_tokens": 5467776.0,
|
|
"step": 3145
|
|
},
|
|
{
|
|
"entropy": 5.753667497634888,
|
|
"epoch": 0.24508850418206574,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004996847413249061,
|
|
"loss": 5.6285,
|
|
"mean_token_accuracy": 0.1525197446346283,
|
|
"num_tokens": 5476005.0,
|
|
"step": 3150
|
|
},
|
|
{
|
|
"entropy": 5.901924514770508,
|
|
"epoch": 0.24547753355378332,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004996832729612252,
|
|
"loss": 5.8222,
|
|
"mean_token_accuracy": 0.1398533895611763,
|
|
"num_tokens": 5484225.0,
|
|
"step": 3155
|
|
},
|
|
{
|
|
"entropy": 5.722384595870972,
|
|
"epoch": 0.24586656292550088,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004996818011883333,
|
|
"loss": 5.7531,
|
|
"mean_token_accuracy": 0.14632738083601,
|
|
"num_tokens": 5493111.0,
|
|
"step": 3160
|
|
},
|
|
{
|
|
"entropy": 5.773323059082031,
|
|
"epoch": 0.24625559229721844,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004996803260062527,
|
|
"loss": 5.7375,
|
|
"mean_token_accuracy": 0.15358287543058396,
|
|
"num_tokens": 5501574.0,
|
|
"step": 3165
|
|
},
|
|
{
|
|
"entropy": 5.874489784240723,
|
|
"epoch": 0.246644621668936,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004996788474150057,
|
|
"loss": 5.793,
|
|
"mean_token_accuracy": 0.1409103363752365,
|
|
"num_tokens": 5511136.0,
|
|
"step": 3170
|
|
},
|
|
{
|
|
"entropy": 5.796777057647705,
|
|
"epoch": 0.24703365104065356,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004996773654146149,
|
|
"loss": 5.7617,
|
|
"mean_token_accuracy": 0.14908162355422974,
|
|
"num_tokens": 5520324.0,
|
|
"step": 3175
|
|
},
|
|
{
|
|
"entropy": 5.828974485397339,
|
|
"epoch": 0.24742268041237114,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004996758800051026,
|
|
"loss": 5.7227,
|
|
"mean_token_accuracy": 0.1487872287631035,
|
|
"num_tokens": 5528960.0,
|
|
"step": 3180
|
|
},
|
|
{
|
|
"entropy": 5.8049417495727536,
|
|
"epoch": 0.2478117097840887,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004996743911864916,
|
|
"loss": 5.8804,
|
|
"mean_token_accuracy": 0.14291784390807152,
|
|
"num_tokens": 5537391.0,
|
|
"step": 3185
|
|
},
|
|
{
|
|
"entropy": 5.917615747451782,
|
|
"epoch": 0.24820073915580626,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004996728989588041,
|
|
"loss": 5.834,
|
|
"mean_token_accuracy": 0.1434634618461132,
|
|
"num_tokens": 5546577.0,
|
|
"step": 3190
|
|
},
|
|
{
|
|
"entropy": 5.884346914291382,
|
|
"epoch": 0.24858976852752382,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004996714033220632,
|
|
"loss": 5.7562,
|
|
"mean_token_accuracy": 0.1481050357222557,
|
|
"num_tokens": 5555247.0,
|
|
"step": 3195
|
|
},
|
|
{
|
|
"entropy": 5.699357271194458,
|
|
"epoch": 0.2489787978992414,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004996699042762911,
|
|
"loss": 5.7203,
|
|
"mean_token_accuracy": 0.15132239758968352,
|
|
"num_tokens": 5563598.0,
|
|
"step": 3200
|
|
},
|
|
{
|
|
"entropy": 5.847423028945923,
|
|
"epoch": 0.24936782727095896,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004996684018215111,
|
|
"loss": 5.7631,
|
|
"mean_token_accuracy": 0.14482942670583726,
|
|
"num_tokens": 5572734.0,
|
|
"step": 3205
|
|
},
|
|
{
|
|
"entropy": 5.848396682739258,
|
|
"epoch": 0.24975685664267652,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004996668959577453,
|
|
"loss": 5.8678,
|
|
"mean_token_accuracy": 0.14266868978738784,
|
|
"num_tokens": 5581224.0,
|
|
"step": 3210
|
|
},
|
|
{
|
|
"entropy": 5.861301279067993,
|
|
"epoch": 0.2501458860143941,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004996653866850173,
|
|
"loss": 5.8819,
|
|
"mean_token_accuracy": 0.13627659901976585,
|
|
"num_tokens": 5590138.0,
|
|
"step": 3215
|
|
},
|
|
{
|
|
"entropy": 5.835147476196289,
|
|
"epoch": 0.25053491538611167,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004996638740033495,
|
|
"loss": 5.7984,
|
|
"mean_token_accuracy": 0.15306344777345657,
|
|
"num_tokens": 5598654.0,
|
|
"step": 3220
|
|
},
|
|
{
|
|
"entropy": 5.726409387588501,
|
|
"epoch": 0.2509239447578292,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004996623579127651,
|
|
"loss": 5.7373,
|
|
"mean_token_accuracy": 0.14696021378040314,
|
|
"num_tokens": 5607404.0,
|
|
"step": 3225
|
|
},
|
|
{
|
|
"entropy": 5.83788480758667,
|
|
"epoch": 0.2513129741295468,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004996608384132868,
|
|
"loss": 5.7697,
|
|
"mean_token_accuracy": 0.1407344162464142,
|
|
"num_tokens": 5617133.0,
|
|
"step": 3230
|
|
},
|
|
{
|
|
"entropy": 5.759439134597779,
|
|
"epoch": 0.25170200350126437,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.000499659315504938,
|
|
"loss": 5.7893,
|
|
"mean_token_accuracy": 0.1451351173222065,
|
|
"num_tokens": 5625389.0,
|
|
"step": 3235
|
|
},
|
|
{
|
|
"entropy": 5.745432138442993,
|
|
"epoch": 0.2520910328729819,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004996577891877417,
|
|
"loss": 5.6746,
|
|
"mean_token_accuracy": 0.15796666443347931,
|
|
"num_tokens": 5633985.0,
|
|
"step": 3240
|
|
},
|
|
{
|
|
"entropy": 5.842095518112183,
|
|
"epoch": 0.2524800622446995,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004996562594617209,
|
|
"loss": 5.7869,
|
|
"mean_token_accuracy": 0.14331955164670945,
|
|
"num_tokens": 5642524.0,
|
|
"step": 3245
|
|
},
|
|
{
|
|
"entropy": 5.836315774917603,
|
|
"epoch": 0.252869091616417,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004996547263268991,
|
|
"loss": 5.7387,
|
|
"mean_token_accuracy": 0.14796270579099655,
|
|
"num_tokens": 5651788.0,
|
|
"step": 3250
|
|
},
|
|
{
|
|
"entropy": 5.7449119091033936,
|
|
"epoch": 0.2532581209881346,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004996531897832993,
|
|
"loss": 5.7848,
|
|
"mean_token_accuracy": 0.14473533779382705,
|
|
"num_tokens": 5660757.0,
|
|
"step": 3255
|
|
},
|
|
{
|
|
"entropy": 5.9398521900177,
|
|
"epoch": 0.2536471503598522,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.000499651649830945,
|
|
"loss": 5.885,
|
|
"mean_token_accuracy": 0.14777640923857688,
|
|
"num_tokens": 5669760.0,
|
|
"step": 3260
|
|
},
|
|
{
|
|
"entropy": 5.771513032913208,
|
|
"epoch": 0.2540361797315697,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004996501064698593,
|
|
"loss": 5.7947,
|
|
"mean_token_accuracy": 0.14532019346952438,
|
|
"num_tokens": 5678313.0,
|
|
"step": 3265
|
|
},
|
|
{
|
|
"entropy": 5.85140585899353,
|
|
"epoch": 0.2544252091032873,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.000499648559700066,
|
|
"loss": 5.7314,
|
|
"mean_token_accuracy": 0.14908790588378906,
|
|
"num_tokens": 5686942.0,
|
|
"step": 3270
|
|
},
|
|
{
|
|
"entropy": 5.789841270446777,
|
|
"epoch": 0.25481423847500484,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004996470095215884,
|
|
"loss": 5.7221,
|
|
"mean_token_accuracy": 0.1519012577831745,
|
|
"num_tokens": 5695612.0,
|
|
"step": 3275
|
|
},
|
|
{
|
|
"entropy": 5.863343143463135,
|
|
"epoch": 0.2552032678467224,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004996454559344498,
|
|
"loss": 5.9189,
|
|
"mean_token_accuracy": 0.1333018012344837,
|
|
"num_tokens": 5705067.0,
|
|
"step": 3280
|
|
},
|
|
{
|
|
"entropy": 5.840832281112671,
|
|
"epoch": 0.25559229721844,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004996438989386741,
|
|
"loss": 5.7991,
|
|
"mean_token_accuracy": 0.1484616681933403,
|
|
"num_tokens": 5714092.0,
|
|
"step": 3285
|
|
},
|
|
{
|
|
"entropy": 5.822746801376343,
|
|
"epoch": 0.25598132659015754,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004996423385342847,
|
|
"loss": 5.7708,
|
|
"mean_token_accuracy": 0.1442373812198639,
|
|
"num_tokens": 5722638.0,
|
|
"step": 3290
|
|
},
|
|
{
|
|
"entropy": 5.812889862060547,
|
|
"epoch": 0.25637035596187513,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004996407747213055,
|
|
"loss": 5.7699,
|
|
"mean_token_accuracy": 0.14374466091394425,
|
|
"num_tokens": 5731511.0,
|
|
"step": 3295
|
|
},
|
|
{
|
|
"entropy": 5.793052339553833,
|
|
"epoch": 0.25675938533359266,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00049963920749976,
|
|
"loss": 5.7688,
|
|
"mean_token_accuracy": 0.1460559368133545,
|
|
"num_tokens": 5740950.0,
|
|
"step": 3300
|
|
},
|
|
{
|
|
"entropy": 5.794534301757812,
|
|
"epoch": 0.25714841470531025,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004996376368696721,
|
|
"loss": 5.7379,
|
|
"mean_token_accuracy": 0.14432745426893234,
|
|
"num_tokens": 5749163.0,
|
|
"step": 3305
|
|
},
|
|
{
|
|
"entropy": 5.8286988735198975,
|
|
"epoch": 0.25753744407702783,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004996360628310656,
|
|
"loss": 5.7923,
|
|
"mean_token_accuracy": 0.14562163800001143,
|
|
"num_tokens": 5758321.0,
|
|
"step": 3310
|
|
},
|
|
{
|
|
"entropy": 5.879156112670898,
|
|
"epoch": 0.25792647344874536,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004996344853839644,
|
|
"loss": 5.8284,
|
|
"mean_token_accuracy": 0.14626478105783464,
|
|
"num_tokens": 5767277.0,
|
|
"step": 3315
|
|
},
|
|
{
|
|
"entropy": 5.766361665725708,
|
|
"epoch": 0.25831550282046295,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004996329045283924,
|
|
"loss": 5.7226,
|
|
"mean_token_accuracy": 0.152338245511055,
|
|
"num_tokens": 5775694.0,
|
|
"step": 3320
|
|
},
|
|
{
|
|
"entropy": 5.680768013000488,
|
|
"epoch": 0.25870453219218054,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004996313202643737,
|
|
"loss": 5.6564,
|
|
"mean_token_accuracy": 0.1541413575410843,
|
|
"num_tokens": 5783932.0,
|
|
"step": 3325
|
|
},
|
|
{
|
|
"entropy": 5.800959300994873,
|
|
"epoch": 0.25909356156389807,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004996297325919321,
|
|
"loss": 5.7648,
|
|
"mean_token_accuracy": 0.14932677298784255,
|
|
"num_tokens": 5792100.0,
|
|
"step": 3330
|
|
},
|
|
{
|
|
"entropy": 5.766122674942016,
|
|
"epoch": 0.25948259093561565,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004996281415110919,
|
|
"loss": 5.7636,
|
|
"mean_token_accuracy": 0.14551785439252854,
|
|
"num_tokens": 5801481.0,
|
|
"step": 3335
|
|
},
|
|
{
|
|
"entropy": 5.843465900421142,
|
|
"epoch": 0.2598716203073332,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004996265470218773,
|
|
"loss": 5.857,
|
|
"mean_token_accuracy": 0.1407374620437622,
|
|
"num_tokens": 5810053.0,
|
|
"step": 3340
|
|
},
|
|
{
|
|
"entropy": 5.755332374572754,
|
|
"epoch": 0.26026064967905077,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004996249491243122,
|
|
"loss": 5.6543,
|
|
"mean_token_accuracy": 0.153837913274765,
|
|
"num_tokens": 5818454.0,
|
|
"step": 3345
|
|
},
|
|
{
|
|
"entropy": 5.758892393112182,
|
|
"epoch": 0.26064967905076836,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004996233478184211,
|
|
"loss": 5.82,
|
|
"mean_token_accuracy": 0.13935508951544762,
|
|
"num_tokens": 5827013.0,
|
|
"step": 3350
|
|
},
|
|
{
|
|
"entropy": 5.772738647460938,
|
|
"epoch": 0.2610387084224859,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004996217431042282,
|
|
"loss": 5.8191,
|
|
"mean_token_accuracy": 0.14132679700851442,
|
|
"num_tokens": 5835862.0,
|
|
"step": 3355
|
|
},
|
|
{
|
|
"entropy": 5.736359262466431,
|
|
"epoch": 0.2614277377942035,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000499620134981758,
|
|
"loss": 5.577,
|
|
"mean_token_accuracy": 0.15000103861093522,
|
|
"num_tokens": 5843827.0,
|
|
"step": 3360
|
|
},
|
|
{
|
|
"entropy": 5.703031015396118,
|
|
"epoch": 0.261816767165921,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004996185234510346,
|
|
"loss": 5.7901,
|
|
"mean_token_accuracy": 0.13962001726031303,
|
|
"num_tokens": 5852677.0,
|
|
"step": 3365
|
|
},
|
|
{
|
|
"entropy": 5.877244329452514,
|
|
"epoch": 0.2622057965376386,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004996169085120828,
|
|
"loss": 5.7382,
|
|
"mean_token_accuracy": 0.1485821083188057,
|
|
"num_tokens": 5861686.0,
|
|
"step": 3370
|
|
},
|
|
{
|
|
"entropy": 5.689363050460815,
|
|
"epoch": 0.2625948259093562,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004996152901649268,
|
|
"loss": 5.725,
|
|
"mean_token_accuracy": 0.1416231408715248,
|
|
"num_tokens": 5870690.0,
|
|
"step": 3375
|
|
},
|
|
{
|
|
"entropy": 5.743702983856201,
|
|
"epoch": 0.2629838552810737,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004996136684095913,
|
|
"loss": 5.7835,
|
|
"mean_token_accuracy": 0.14579864591360092,
|
|
"num_tokens": 5879804.0,
|
|
"step": 3380
|
|
},
|
|
{
|
|
"entropy": 5.950654411315918,
|
|
"epoch": 0.2633728846527913,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004996120432461009,
|
|
"loss": 5.869,
|
|
"mean_token_accuracy": 0.13930928632616996,
|
|
"num_tokens": 5888781.0,
|
|
"step": 3385
|
|
},
|
|
{
|
|
"entropy": 5.868631219863891,
|
|
"epoch": 0.2637619140245088,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004996104146744804,
|
|
"loss": 5.7771,
|
|
"mean_token_accuracy": 0.1415348656475544,
|
|
"num_tokens": 5897439.0,
|
|
"step": 3390
|
|
},
|
|
{
|
|
"entropy": 5.760622358322143,
|
|
"epoch": 0.2641509433962264,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004996087826947541,
|
|
"loss": 5.7275,
|
|
"mean_token_accuracy": 0.1547902464866638,
|
|
"num_tokens": 5905471.0,
|
|
"step": 3395
|
|
},
|
|
{
|
|
"entropy": 5.733852291107178,
|
|
"epoch": 0.264539972767944,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004996071473069471,
|
|
"loss": 5.763,
|
|
"mean_token_accuracy": 0.14708420559763907,
|
|
"num_tokens": 5913795.0,
|
|
"step": 3400
|
|
},
|
|
{
|
|
"entropy": 5.930234575271607,
|
|
"epoch": 0.26492900213966153,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004996055085110842,
|
|
"loss": 5.8291,
|
|
"mean_token_accuracy": 0.14742809608578683,
|
|
"num_tokens": 5922119.0,
|
|
"step": 3405
|
|
},
|
|
{
|
|
"entropy": 5.715909337997436,
|
|
"epoch": 0.2653180315113791,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004996038663071902,
|
|
"loss": 5.7014,
|
|
"mean_token_accuracy": 0.14781875312328338,
|
|
"num_tokens": 5930759.0,
|
|
"step": 3410
|
|
},
|
|
{
|
|
"entropy": 5.780412006378174,
|
|
"epoch": 0.26570706088309665,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004996022206952901,
|
|
"loss": 5.7402,
|
|
"mean_token_accuracy": 0.15140870213508606,
|
|
"num_tokens": 5939830.0,
|
|
"step": 3415
|
|
},
|
|
{
|
|
"entropy": 5.8248049259185795,
|
|
"epoch": 0.26609609025481423,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004996005716754086,
|
|
"loss": 5.7605,
|
|
"mean_token_accuracy": 0.1474993720650673,
|
|
"num_tokens": 5947737.0,
|
|
"step": 3420
|
|
},
|
|
{
|
|
"entropy": 5.673804140090942,
|
|
"epoch": 0.2664851196265318,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.000499598919247571,
|
|
"loss": 5.7192,
|
|
"mean_token_accuracy": 0.15081372782588004,
|
|
"num_tokens": 5955905.0,
|
|
"step": 3425
|
|
},
|
|
{
|
|
"entropy": 5.754757499694824,
|
|
"epoch": 0.26687414899824935,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004995972634118023,
|
|
"loss": 5.7772,
|
|
"mean_token_accuracy": 0.14792786687612533,
|
|
"num_tokens": 5965223.0,
|
|
"step": 3430
|
|
},
|
|
{
|
|
"entropy": 5.867637968063354,
|
|
"epoch": 0.26726317836996694,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004995956041681277,
|
|
"loss": 5.7822,
|
|
"mean_token_accuracy": 0.1515558920800686,
|
|
"num_tokens": 5973615.0,
|
|
"step": 3435
|
|
},
|
|
{
|
|
"entropy": 5.753899335861206,
|
|
"epoch": 0.2676522077416845,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004995939415165722,
|
|
"loss": 5.6975,
|
|
"mean_token_accuracy": 0.15376841723918916,
|
|
"num_tokens": 5981600.0,
|
|
"step": 3440
|
|
},
|
|
{
|
|
"entropy": 5.765840864181518,
|
|
"epoch": 0.26804123711340205,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004995922754571611,
|
|
"loss": 5.7208,
|
|
"mean_token_accuracy": 0.14557234048843384,
|
|
"num_tokens": 5989928.0,
|
|
"step": 3445
|
|
},
|
|
{
|
|
"entropy": 5.7377198219299315,
|
|
"epoch": 0.26843026648511964,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004995906059899197,
|
|
"loss": 5.784,
|
|
"mean_token_accuracy": 0.14729606062173844,
|
|
"num_tokens": 5998704.0,
|
|
"step": 3450
|
|
},
|
|
{
|
|
"entropy": 5.831356477737427,
|
|
"epoch": 0.26881929585683717,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004995889331148733,
|
|
"loss": 5.7571,
|
|
"mean_token_accuracy": 0.14637779593467712,
|
|
"num_tokens": 6007476.0,
|
|
"step": 3455
|
|
},
|
|
{
|
|
"entropy": 5.8942183494567875,
|
|
"epoch": 0.26920832522855476,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004995872568320474,
|
|
"loss": 5.8232,
|
|
"mean_token_accuracy": 0.14493844136595727,
|
|
"num_tokens": 6016324.0,
|
|
"step": 3460
|
|
},
|
|
{
|
|
"entropy": 5.772535514831543,
|
|
"epoch": 0.26959735460027234,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004995855771414673,
|
|
"loss": 5.7637,
|
|
"mean_token_accuracy": 0.1480872981250286,
|
|
"num_tokens": 6024709.0,
|
|
"step": 3465
|
|
},
|
|
{
|
|
"entropy": 5.7089063167572025,
|
|
"epoch": 0.2699863839719899,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004995838940431585,
|
|
"loss": 5.6207,
|
|
"mean_token_accuracy": 0.15393780767917634,
|
|
"num_tokens": 6033131.0,
|
|
"step": 3470
|
|
},
|
|
{
|
|
"entropy": 5.721988534927368,
|
|
"epoch": 0.27037541334370746,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004995822075371466,
|
|
"loss": 5.8059,
|
|
"mean_token_accuracy": 0.14825249463319778,
|
|
"num_tokens": 6042310.0,
|
|
"step": 3475
|
|
},
|
|
{
|
|
"entropy": 5.806495904922485,
|
|
"epoch": 0.270764442715425,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004995805176234571,
|
|
"loss": 5.6489,
|
|
"mean_token_accuracy": 0.15398290306329726,
|
|
"num_tokens": 6050617.0,
|
|
"step": 3480
|
|
},
|
|
{
|
|
"entropy": 5.81084794998169,
|
|
"epoch": 0.2711534720871426,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004995788243021158,
|
|
"loss": 5.8099,
|
|
"mean_token_accuracy": 0.14377037510275842,
|
|
"num_tokens": 6060090.0,
|
|
"step": 3485
|
|
},
|
|
{
|
|
"entropy": 5.797818422317505,
|
|
"epoch": 0.27154250145886016,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004995771275731483,
|
|
"loss": 5.7419,
|
|
"mean_token_accuracy": 0.15020338743925093,
|
|
"num_tokens": 6068646.0,
|
|
"step": 3490
|
|
},
|
|
{
|
|
"entropy": 5.805457019805909,
|
|
"epoch": 0.2719315308305777,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004995754274365802,
|
|
"loss": 5.8078,
|
|
"mean_token_accuracy": 0.14822555482387542,
|
|
"num_tokens": 6077896.0,
|
|
"step": 3495
|
|
},
|
|
{
|
|
"entropy": 5.829698324203491,
|
|
"epoch": 0.2723205602022953,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004995737238924376,
|
|
"loss": 5.7387,
|
|
"mean_token_accuracy": 0.14886911809444428,
|
|
"num_tokens": 6087189.0,
|
|
"step": 3500
|
|
},
|
|
{
|
|
"entropy": 5.807201290130616,
|
|
"epoch": 0.2727095895740128,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004995720169407461,
|
|
"loss": 5.7258,
|
|
"mean_token_accuracy": 0.14581827446818352,
|
|
"num_tokens": 6095394.0,
|
|
"step": 3505
|
|
},
|
|
{
|
|
"entropy": 5.779724836349487,
|
|
"epoch": 0.2730986189457304,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004995703065815317,
|
|
"loss": 5.6964,
|
|
"mean_token_accuracy": 0.14818193018436432,
|
|
"num_tokens": 6104135.0,
|
|
"step": 3510
|
|
},
|
|
{
|
|
"entropy": 5.782814025878906,
|
|
"epoch": 0.273487648317448,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004995685928148203,
|
|
"loss": 5.8185,
|
|
"mean_token_accuracy": 0.13873943611979483,
|
|
"num_tokens": 6112160.0,
|
|
"step": 3515
|
|
},
|
|
{
|
|
"entropy": 5.889563655853271,
|
|
"epoch": 0.2738766776891655,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000499566875640638,
|
|
"loss": 5.8082,
|
|
"mean_token_accuracy": 0.14778889939188958,
|
|
"num_tokens": 6120575.0,
|
|
"step": 3520
|
|
},
|
|
{
|
|
"entropy": 5.831877183914185,
|
|
"epoch": 0.2742657070608831,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004995651550590108,
|
|
"loss": 5.8065,
|
|
"mean_token_accuracy": 0.1462782323360443,
|
|
"num_tokens": 6129367.0,
|
|
"step": 3525
|
|
},
|
|
{
|
|
"entropy": 5.786219835281372,
|
|
"epoch": 0.2746547364326007,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004995634310699647,
|
|
"loss": 5.7881,
|
|
"mean_token_accuracy": 0.14894402176141738,
|
|
"num_tokens": 6137440.0,
|
|
"step": 3530
|
|
},
|
|
{
|
|
"entropy": 5.806088399887085,
|
|
"epoch": 0.2750437658043182,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004995617036735261,
|
|
"loss": 5.7137,
|
|
"mean_token_accuracy": 0.15182468742132188,
|
|
"num_tokens": 6146770.0,
|
|
"step": 3535
|
|
},
|
|
{
|
|
"entropy": 5.8849130153656,
|
|
"epoch": 0.2754327951760358,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004995599728697211,
|
|
"loss": 5.8051,
|
|
"mean_token_accuracy": 0.14528674632310867,
|
|
"num_tokens": 6155994.0,
|
|
"step": 3540
|
|
},
|
|
{
|
|
"entropy": 5.732000875473022,
|
|
"epoch": 0.27582182454775334,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004995582386585759,
|
|
"loss": 5.7017,
|
|
"mean_token_accuracy": 0.14667895957827567,
|
|
"num_tokens": 6163941.0,
|
|
"step": 3545
|
|
},
|
|
{
|
|
"entropy": 5.730872774124146,
|
|
"epoch": 0.2762108539194709,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004995565010401167,
|
|
"loss": 5.7757,
|
|
"mean_token_accuracy": 0.14480799287557602,
|
|
"num_tokens": 6172681.0,
|
|
"step": 3550
|
|
},
|
|
{
|
|
"entropy": 5.857365274429322,
|
|
"epoch": 0.2765998832911885,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004995547600143702,
|
|
"loss": 5.7458,
|
|
"mean_token_accuracy": 0.14071987494826316,
|
|
"num_tokens": 6181449.0,
|
|
"step": 3555
|
|
},
|
|
{
|
|
"entropy": 5.7990813732147215,
|
|
"epoch": 0.27698891266290604,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004995530155813625,
|
|
"loss": 5.7345,
|
|
"mean_token_accuracy": 0.14359339326620102,
|
|
"num_tokens": 6190275.0,
|
|
"step": 3560
|
|
},
|
|
{
|
|
"entropy": 5.802273225784302,
|
|
"epoch": 0.2773779420346236,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004995512677411203,
|
|
"loss": 5.7468,
|
|
"mean_token_accuracy": 0.1445533514022827,
|
|
"num_tokens": 6198521.0,
|
|
"step": 3565
|
|
},
|
|
{
|
|
"entropy": 5.780069971084595,
|
|
"epoch": 0.27776697140634116,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004995495164936698,
|
|
"loss": 5.8063,
|
|
"mean_token_accuracy": 0.13917019516229628,
|
|
"num_tokens": 6207318.0,
|
|
"step": 3570
|
|
},
|
|
{
|
|
"entropy": 5.830804681777954,
|
|
"epoch": 0.27815600077805874,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004995477618390381,
|
|
"loss": 5.6985,
|
|
"mean_token_accuracy": 0.15309059321880342,
|
|
"num_tokens": 6216693.0,
|
|
"step": 3575
|
|
},
|
|
{
|
|
"entropy": 5.786478662490845,
|
|
"epoch": 0.27854503014977633,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004995460037772513,
|
|
"loss": 5.774,
|
|
"mean_token_accuracy": 0.14531423151493073,
|
|
"num_tokens": 6225207.0,
|
|
"step": 3580
|
|
},
|
|
{
|
|
"entropy": 5.739966011047363,
|
|
"epoch": 0.27893405952149386,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004995442423083365,
|
|
"loss": 5.6923,
|
|
"mean_token_accuracy": 0.15383105129003524,
|
|
"num_tokens": 6232653.0,
|
|
"step": 3585
|
|
},
|
|
{
|
|
"entropy": 5.6744976997375485,
|
|
"epoch": 0.27932308889321145,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004995424774323201,
|
|
"loss": 5.69,
|
|
"mean_token_accuracy": 0.1559629037976265,
|
|
"num_tokens": 6241093.0,
|
|
"step": 3590
|
|
},
|
|
{
|
|
"entropy": 5.717198085784912,
|
|
"epoch": 0.279712118264929,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.000499540709149229,
|
|
"loss": 5.5898,
|
|
"mean_token_accuracy": 0.15695664137601853,
|
|
"num_tokens": 6249144.0,
|
|
"step": 3595
|
|
},
|
|
{
|
|
"entropy": 5.769004201889038,
|
|
"epoch": 0.28010114763664656,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004995389374590901,
|
|
"loss": 5.6725,
|
|
"mean_token_accuracy": 0.15143965780735016,
|
|
"num_tokens": 6257622.0,
|
|
"step": 3600
|
|
},
|
|
{
|
|
"entropy": 5.731729984283447,
|
|
"epoch": 0.28049017700836415,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004995371623619301,
|
|
"loss": 5.7123,
|
|
"mean_token_accuracy": 0.14922656640410423,
|
|
"num_tokens": 6266435.0,
|
|
"step": 3605
|
|
},
|
|
{
|
|
"entropy": 5.78806791305542,
|
|
"epoch": 0.2808792063800817,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.000499535383857776,
|
|
"loss": 5.8212,
|
|
"mean_token_accuracy": 0.14109619781374932,
|
|
"num_tokens": 6275053.0,
|
|
"step": 3610
|
|
},
|
|
{
|
|
"entropy": 5.799437713623047,
|
|
"epoch": 0.28126823575179927,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.000499533601946655,
|
|
"loss": 5.7138,
|
|
"mean_token_accuracy": 0.1458030089735985,
|
|
"num_tokens": 6283240.0,
|
|
"step": 3615
|
|
},
|
|
{
|
|
"entropy": 5.693672180175781,
|
|
"epoch": 0.2816572651235168,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004995318166285938,
|
|
"loss": 5.6685,
|
|
"mean_token_accuracy": 0.15400461852550507,
|
|
"num_tokens": 6292133.0,
|
|
"step": 3620
|
|
},
|
|
{
|
|
"entropy": 5.798172426223755,
|
|
"epoch": 0.2820462944952344,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004995300279036199,
|
|
"loss": 5.7764,
|
|
"mean_token_accuracy": 0.14602856785058976,
|
|
"num_tokens": 6300954.0,
|
|
"step": 3625
|
|
},
|
|
{
|
|
"entropy": 5.738204431533814,
|
|
"epoch": 0.28243532386695197,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00049952823577176,
|
|
"loss": 5.6495,
|
|
"mean_token_accuracy": 0.15521105974912644,
|
|
"num_tokens": 6309637.0,
|
|
"step": 3630
|
|
},
|
|
{
|
|
"entropy": 5.747934818267822,
|
|
"epoch": 0.2828243532386695,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004995264402330416,
|
|
"loss": 5.7416,
|
|
"mean_token_accuracy": 0.14806705266237258,
|
|
"num_tokens": 6318539.0,
|
|
"step": 3635
|
|
},
|
|
{
|
|
"entropy": 5.795380783081055,
|
|
"epoch": 0.2832133826103871,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004995246412874919,
|
|
"loss": 5.6451,
|
|
"mean_token_accuracy": 0.152295258641243,
|
|
"num_tokens": 6327109.0,
|
|
"step": 3640
|
|
},
|
|
{
|
|
"entropy": 5.641116523742676,
|
|
"epoch": 0.2836024119821047,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.000499522838935138,
|
|
"loss": 5.6457,
|
|
"mean_token_accuracy": 0.1501530423760414,
|
|
"num_tokens": 6335555.0,
|
|
"step": 3645
|
|
},
|
|
{
|
|
"entropy": 5.823719310760498,
|
|
"epoch": 0.2839914413538222,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004995210331760074,
|
|
"loss": 5.8046,
|
|
"mean_token_accuracy": 0.14390790238976478,
|
|
"num_tokens": 6344716.0,
|
|
"step": 3650
|
|
},
|
|
{
|
|
"entropy": 5.763507223129272,
|
|
"epoch": 0.2843804707255398,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004995192240101275,
|
|
"loss": 5.6674,
|
|
"mean_token_accuracy": 0.15561642944812776,
|
|
"num_tokens": 6353618.0,
|
|
"step": 3655
|
|
},
|
|
{
|
|
"entropy": 5.809588813781739,
|
|
"epoch": 0.2847695000972573,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004995174114375258,
|
|
"loss": 5.7991,
|
|
"mean_token_accuracy": 0.14580731019377707,
|
|
"num_tokens": 6362039.0,
|
|
"step": 3660
|
|
},
|
|
{
|
|
"entropy": 5.824526309967041,
|
|
"epoch": 0.2851585294689749,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004995155954582297,
|
|
"loss": 5.7105,
|
|
"mean_token_accuracy": 0.14895076751708985,
|
|
"num_tokens": 6370331.0,
|
|
"step": 3665
|
|
},
|
|
{
|
|
"entropy": 5.7808431625366214,
|
|
"epoch": 0.2855475588406925,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004995137760722668,
|
|
"loss": 5.7124,
|
|
"mean_token_accuracy": 0.15209874212741853,
|
|
"num_tokens": 6378943.0,
|
|
"step": 3670
|
|
},
|
|
{
|
|
"entropy": 5.768771934509277,
|
|
"epoch": 0.28593658821241,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004995119532796646,
|
|
"loss": 5.7632,
|
|
"mean_token_accuracy": 0.14161582738161088,
|
|
"num_tokens": 6387745.0,
|
|
"step": 3675
|
|
},
|
|
{
|
|
"entropy": 5.628377485275268,
|
|
"epoch": 0.2863256175841276,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.000499510127080451,
|
|
"loss": 5.6018,
|
|
"mean_token_accuracy": 0.15134189054369926,
|
|
"num_tokens": 6396915.0,
|
|
"step": 3680
|
|
},
|
|
{
|
|
"entropy": 5.728256511688232,
|
|
"epoch": 0.28671464695584514,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004995082974746535,
|
|
"loss": 5.651,
|
|
"mean_token_accuracy": 0.15115621611475943,
|
|
"num_tokens": 6405453.0,
|
|
"step": 3685
|
|
},
|
|
{
|
|
"entropy": 5.774420547485351,
|
|
"epoch": 0.28710367632756273,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004995064644622999,
|
|
"loss": 5.7196,
|
|
"mean_token_accuracy": 0.1510769948363304,
|
|
"num_tokens": 6413693.0,
|
|
"step": 3690
|
|
},
|
|
{
|
|
"entropy": 5.68609504699707,
|
|
"epoch": 0.2874927056992803,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004995046280434181,
|
|
"loss": 5.7202,
|
|
"mean_token_accuracy": 0.15133974701166153,
|
|
"num_tokens": 6422738.0,
|
|
"step": 3695
|
|
},
|
|
{
|
|
"entropy": 5.765851640701294,
|
|
"epoch": 0.28788173507099785,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004995027882180358,
|
|
"loss": 5.6729,
|
|
"mean_token_accuracy": 0.149416945874691,
|
|
"num_tokens": 6431743.0,
|
|
"step": 3700
|
|
},
|
|
{
|
|
"entropy": 5.762576484680176,
|
|
"epoch": 0.28827076444271543,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004995009449861812,
|
|
"loss": 5.7151,
|
|
"mean_token_accuracy": 0.14814867302775384,
|
|
"num_tokens": 6440586.0,
|
|
"step": 3705
|
|
},
|
|
{
|
|
"entropy": 5.734358072280884,
|
|
"epoch": 0.28865979381443296,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.000499499098347882,
|
|
"loss": 5.7687,
|
|
"mean_token_accuracy": 0.1449608936905861,
|
|
"num_tokens": 6449644.0,
|
|
"step": 3710
|
|
},
|
|
{
|
|
"entropy": 5.747537469863891,
|
|
"epoch": 0.28904882318615055,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004994972483031662,
|
|
"loss": 5.6556,
|
|
"mean_token_accuracy": 0.1551126554608345,
|
|
"num_tokens": 6458752.0,
|
|
"step": 3715
|
|
},
|
|
{
|
|
"entropy": 5.671671295166016,
|
|
"epoch": 0.28943785255786814,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.000499495394852062,
|
|
"loss": 5.72,
|
|
"mean_token_accuracy": 0.15402934402227403,
|
|
"num_tokens": 6468333.0,
|
|
"step": 3720
|
|
},
|
|
{
|
|
"entropy": 5.632138729095459,
|
|
"epoch": 0.28982688192958567,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004994935379945977,
|
|
"loss": 5.5744,
|
|
"mean_token_accuracy": 0.15026432350277902,
|
|
"num_tokens": 6477406.0,
|
|
"step": 3725
|
|
},
|
|
{
|
|
"entropy": 5.841580057144165,
|
|
"epoch": 0.29021591130130325,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004994916777308012,
|
|
"loss": 5.744,
|
|
"mean_token_accuracy": 0.1481349840760231,
|
|
"num_tokens": 6486399.0,
|
|
"step": 3730
|
|
},
|
|
{
|
|
"entropy": 5.684890651702881,
|
|
"epoch": 0.29060494067302084,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004994898140607007,
|
|
"loss": 5.6343,
|
|
"mean_token_accuracy": 0.15071317702531814,
|
|
"num_tokens": 6494853.0,
|
|
"step": 3735
|
|
},
|
|
{
|
|
"entropy": 5.795504951477051,
|
|
"epoch": 0.29099397004473837,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004994879469843247,
|
|
"loss": 5.7953,
|
|
"mean_token_accuracy": 0.14516895562410354,
|
|
"num_tokens": 6503301.0,
|
|
"step": 3740
|
|
},
|
|
{
|
|
"entropy": 5.801367568969726,
|
|
"epoch": 0.29138299941645596,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004994860765017013,
|
|
"loss": 5.6841,
|
|
"mean_token_accuracy": 0.14791862815618514,
|
|
"num_tokens": 6512685.0,
|
|
"step": 3745
|
|
},
|
|
{
|
|
"entropy": 5.708689165115357,
|
|
"epoch": 0.2917720287881735,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.000499484202612859,
|
|
"loss": 5.7907,
|
|
"mean_token_accuracy": 0.145990938693285,
|
|
"num_tokens": 6520673.0,
|
|
"step": 3750
|
|
},
|
|
{
|
|
"entropy": 5.8158228397369385,
|
|
"epoch": 0.2921610581598911,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004994823253178264,
|
|
"loss": 5.7085,
|
|
"mean_token_accuracy": 0.14853528290987014,
|
|
"num_tokens": 6529039.0,
|
|
"step": 3755
|
|
},
|
|
{
|
|
"entropy": 5.766492509841919,
|
|
"epoch": 0.29255008753160866,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004994804446166317,
|
|
"loss": 5.7787,
|
|
"mean_token_accuracy": 0.14217330813407897,
|
|
"num_tokens": 6537932.0,
|
|
"step": 3760
|
|
},
|
|
{
|
|
"entropy": 5.738761138916016,
|
|
"epoch": 0.2929391169033262,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004994785605093035,
|
|
"loss": 5.6614,
|
|
"mean_token_accuracy": 0.14945704191923143,
|
|
"num_tokens": 6546278.0,
|
|
"step": 3765
|
|
},
|
|
{
|
|
"entropy": 5.7169417381286625,
|
|
"epoch": 0.2933281462750438,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004994766729958705,
|
|
"loss": 5.7246,
|
|
"mean_token_accuracy": 0.15161917060613633,
|
|
"num_tokens": 6554449.0,
|
|
"step": 3770
|
|
},
|
|
{
|
|
"entropy": 5.740348386764526,
|
|
"epoch": 0.2937171756467613,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004994747820763612,
|
|
"loss": 5.7073,
|
|
"mean_token_accuracy": 0.15263478457927704,
|
|
"num_tokens": 6563272.0,
|
|
"step": 3775
|
|
},
|
|
{
|
|
"entropy": 5.782098960876465,
|
|
"epoch": 0.2941062050184789,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004994728877508046,
|
|
"loss": 5.713,
|
|
"mean_token_accuracy": 0.1488537795841694,
|
|
"num_tokens": 6571864.0,
|
|
"step": 3780
|
|
},
|
|
{
|
|
"entropy": 5.741234636306762,
|
|
"epoch": 0.2944952343901965,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004994709900192289,
|
|
"loss": 5.7281,
|
|
"mean_token_accuracy": 0.1500175341963768,
|
|
"num_tokens": 6580435.0,
|
|
"step": 3785
|
|
},
|
|
{
|
|
"entropy": 5.771685266494751,
|
|
"epoch": 0.294884263761914,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004994690888816635,
|
|
"loss": 5.7076,
|
|
"mean_token_accuracy": 0.15417710989713668,
|
|
"num_tokens": 6589261.0,
|
|
"step": 3790
|
|
},
|
|
{
|
|
"entropy": 5.765047073364258,
|
|
"epoch": 0.2952732931336316,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004994671843381367,
|
|
"loss": 5.7987,
|
|
"mean_token_accuracy": 0.15160125195980073,
|
|
"num_tokens": 6598057.0,
|
|
"step": 3795
|
|
},
|
|
{
|
|
"entropy": 5.821505737304688,
|
|
"epoch": 0.29566232250534913,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004994652763886778,
|
|
"loss": 5.7513,
|
|
"mean_token_accuracy": 0.14843295365571976,
|
|
"num_tokens": 6606439.0,
|
|
"step": 3800
|
|
},
|
|
{
|
|
"entropy": 5.766422510147095,
|
|
"epoch": 0.2960513518770667,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004994633650333155,
|
|
"loss": 5.7634,
|
|
"mean_token_accuracy": 0.14703089296817778,
|
|
"num_tokens": 6615350.0,
|
|
"step": 3805
|
|
},
|
|
{
|
|
"entropy": 5.821816062927246,
|
|
"epoch": 0.2964403812487843,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004994614502720792,
|
|
"loss": 5.8078,
|
|
"mean_token_accuracy": 0.1505200482904911,
|
|
"num_tokens": 6624258.0,
|
|
"step": 3810
|
|
},
|
|
{
|
|
"entropy": 5.860561466217041,
|
|
"epoch": 0.29682941062050183,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004994595321049974,
|
|
"loss": 5.8156,
|
|
"mean_token_accuracy": 0.14286257103085517,
|
|
"num_tokens": 6632382.0,
|
|
"step": 3815
|
|
},
|
|
{
|
|
"entropy": 5.704246664047242,
|
|
"epoch": 0.2972184399922194,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004994576105320994,
|
|
"loss": 5.7175,
|
|
"mean_token_accuracy": 0.14342779219150542,
|
|
"num_tokens": 6640482.0,
|
|
"step": 3820
|
|
},
|
|
{
|
|
"entropy": 5.7658362865448,
|
|
"epoch": 0.29760746936393695,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004994556855534146,
|
|
"loss": 5.6998,
|
|
"mean_token_accuracy": 0.149716167896986,
|
|
"num_tokens": 6648912.0,
|
|
"step": 3825
|
|
},
|
|
{
|
|
"entropy": 5.769665098190307,
|
|
"epoch": 0.29799649873565454,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004994537571689719,
|
|
"loss": 5.669,
|
|
"mean_token_accuracy": 0.15446349382400512,
|
|
"num_tokens": 6656912.0,
|
|
"step": 3830
|
|
},
|
|
{
|
|
"entropy": 5.691803979873657,
|
|
"epoch": 0.2983855281073721,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004994518253788007,
|
|
"loss": 5.7111,
|
|
"mean_token_accuracy": 0.15156170278787612,
|
|
"num_tokens": 6665900.0,
|
|
"step": 3835
|
|
},
|
|
{
|
|
"entropy": 5.825985717773437,
|
|
"epoch": 0.29877455747908965,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004994498901829304,
|
|
"loss": 5.7354,
|
|
"mean_token_accuracy": 0.1470371499657631,
|
|
"num_tokens": 6674426.0,
|
|
"step": 3840
|
|
},
|
|
{
|
|
"entropy": 5.767888307571411,
|
|
"epoch": 0.29916358685080724,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004994479515813903,
|
|
"loss": 5.7082,
|
|
"mean_token_accuracy": 0.14955729991197586,
|
|
"num_tokens": 6683566.0,
|
|
"step": 3845
|
|
},
|
|
{
|
|
"entropy": 5.7769775390625,
|
|
"epoch": 0.2995526162225248,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004994460095742096,
|
|
"loss": 5.7373,
|
|
"mean_token_accuracy": 0.14816780611872674,
|
|
"num_tokens": 6693341.0,
|
|
"step": 3850
|
|
},
|
|
{
|
|
"entropy": 5.763691473007202,
|
|
"epoch": 0.29994164559424236,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.000499444064161418,
|
|
"loss": 5.6322,
|
|
"mean_token_accuracy": 0.14713368117809295,
|
|
"num_tokens": 6701734.0,
|
|
"step": 3855
|
|
},
|
|
{
|
|
"entropy": 5.729468107223511,
|
|
"epoch": 0.30033067496595994,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000499442115343045,
|
|
"loss": 5.6515,
|
|
"mean_token_accuracy": 0.14751814007759095,
|
|
"num_tokens": 6710572.0,
|
|
"step": 3860
|
|
},
|
|
{
|
|
"entropy": 5.818091011047363,
|
|
"epoch": 0.3007197043376775,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004994401631191202,
|
|
"loss": 5.7777,
|
|
"mean_token_accuracy": 0.14385256469249724,
|
|
"num_tokens": 6719355.0,
|
|
"step": 3865
|
|
},
|
|
{
|
|
"entropy": 5.869049596786499,
|
|
"epoch": 0.30110873370939506,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004994382074896731,
|
|
"loss": 5.8134,
|
|
"mean_token_accuracy": 0.14362031519412993,
|
|
"num_tokens": 6729279.0,
|
|
"step": 3870
|
|
},
|
|
{
|
|
"entropy": 5.736733388900757,
|
|
"epoch": 0.30149776308111265,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004994362484547335,
|
|
"loss": 5.6397,
|
|
"mean_token_accuracy": 0.14999447017908096,
|
|
"num_tokens": 6737318.0,
|
|
"step": 3875
|
|
},
|
|
{
|
|
"entropy": 5.725610685348511,
|
|
"epoch": 0.3018867924528302,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004994342860143309,
|
|
"loss": 5.7038,
|
|
"mean_token_accuracy": 0.14922786131501198,
|
|
"num_tokens": 6746520.0,
|
|
"step": 3880
|
|
},
|
|
{
|
|
"entropy": 5.773070478439331,
|
|
"epoch": 0.30227582182454776,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004994323201684953,
|
|
"loss": 5.6479,
|
|
"mean_token_accuracy": 0.15274196863174438,
|
|
"num_tokens": 6755685.0,
|
|
"step": 3885
|
|
},
|
|
{
|
|
"entropy": 5.773148155212402,
|
|
"epoch": 0.3026648511962653,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004994303509172566,
|
|
"loss": 5.8026,
|
|
"mean_token_accuracy": 0.14690820202231408,
|
|
"num_tokens": 6764347.0,
|
|
"step": 3890
|
|
},
|
|
{
|
|
"entropy": 5.814873266220093,
|
|
"epoch": 0.3030538805679829,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004994283782606444,
|
|
"loss": 5.7737,
|
|
"mean_token_accuracy": 0.14735113084316254,
|
|
"num_tokens": 6772887.0,
|
|
"step": 3895
|
|
},
|
|
{
|
|
"entropy": 5.727507257461548,
|
|
"epoch": 0.30344290993970047,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004994264021986888,
|
|
"loss": 5.7295,
|
|
"mean_token_accuracy": 0.1467637374997139,
|
|
"num_tokens": 6780860.0,
|
|
"step": 3900
|
|
},
|
|
{
|
|
"entropy": 5.724376440048218,
|
|
"epoch": 0.303831939311418,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004994244227314197,
|
|
"loss": 5.7569,
|
|
"mean_token_accuracy": 0.14601460099220276,
|
|
"num_tokens": 6789491.0,
|
|
"step": 3905
|
|
},
|
|
{
|
|
"entropy": 5.803851795196533,
|
|
"epoch": 0.3042209686831356,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004994224398588672,
|
|
"loss": 5.6626,
|
|
"mean_token_accuracy": 0.1493813693523407,
|
|
"num_tokens": 6797128.0,
|
|
"step": 3910
|
|
},
|
|
{
|
|
"entropy": 5.731702136993408,
|
|
"epoch": 0.3046099980548531,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004994204535810615,
|
|
"loss": 5.7137,
|
|
"mean_token_accuracy": 0.15297965854406356,
|
|
"num_tokens": 6805235.0,
|
|
"step": 3915
|
|
},
|
|
{
|
|
"entropy": 5.711788034439087,
|
|
"epoch": 0.3049990274265707,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004994184638980326,
|
|
"loss": 5.6228,
|
|
"mean_token_accuracy": 0.15258978605270385,
|
|
"num_tokens": 6813863.0,
|
|
"step": 3920
|
|
},
|
|
{
|
|
"entropy": 5.789138412475586,
|
|
"epoch": 0.3053880567982883,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004994164708098107,
|
|
"loss": 5.6812,
|
|
"mean_token_accuracy": 0.14739597737789153,
|
|
"num_tokens": 6822015.0,
|
|
"step": 3925
|
|
},
|
|
{
|
|
"entropy": 5.762054491043091,
|
|
"epoch": 0.3057770861700058,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.000499414474316426,
|
|
"loss": 5.7437,
|
|
"mean_token_accuracy": 0.14832285046577454,
|
|
"num_tokens": 6830598.0,
|
|
"step": 3930
|
|
},
|
|
{
|
|
"entropy": 5.757642412185669,
|
|
"epoch": 0.3061661155417234,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004994124744179088,
|
|
"loss": 5.7274,
|
|
"mean_token_accuracy": 0.15362328812479972,
|
|
"num_tokens": 6839129.0,
|
|
"step": 3935
|
|
},
|
|
{
|
|
"entropy": 5.780041217803955,
|
|
"epoch": 0.306555144913441,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004994104711142896,
|
|
"loss": 5.6925,
|
|
"mean_token_accuracy": 0.14965419173240663,
|
|
"num_tokens": 6848199.0,
|
|
"step": 3940
|
|
},
|
|
{
|
|
"entropy": 5.703006458282471,
|
|
"epoch": 0.3069441742851585,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004994084644055986,
|
|
"loss": 5.698,
|
|
"mean_token_accuracy": 0.15254101604223252,
|
|
"num_tokens": 6857340.0,
|
|
"step": 3945
|
|
},
|
|
{
|
|
"entropy": 5.744833517074585,
|
|
"epoch": 0.3073332036568761,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004994064542918664,
|
|
"loss": 5.7401,
|
|
"mean_token_accuracy": 0.14557312354445456,
|
|
"num_tokens": 6865830.0,
|
|
"step": 3950
|
|
},
|
|
{
|
|
"entropy": 5.823490333557129,
|
|
"epoch": 0.30772223302859364,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004994044407731235,
|
|
"loss": 5.7968,
|
|
"mean_token_accuracy": 0.14378844499588012,
|
|
"num_tokens": 6874318.0,
|
|
"step": 3955
|
|
},
|
|
{
|
|
"entropy": 5.840137577056884,
|
|
"epoch": 0.3081112624003112,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004994024238494002,
|
|
"loss": 5.7848,
|
|
"mean_token_accuracy": 0.14851943552494049,
|
|
"num_tokens": 6882008.0,
|
|
"step": 3960
|
|
},
|
|
{
|
|
"entropy": 5.689302730560303,
|
|
"epoch": 0.3085002917720288,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004994004035207274,
|
|
"loss": 5.6568,
|
|
"mean_token_accuracy": 0.15387474596500397,
|
|
"num_tokens": 6890411.0,
|
|
"step": 3965
|
|
},
|
|
{
|
|
"entropy": 5.723822784423828,
|
|
"epoch": 0.30888932114374634,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004993983797871356,
|
|
"loss": 5.714,
|
|
"mean_token_accuracy": 0.1433463215827942,
|
|
"num_tokens": 6899201.0,
|
|
"step": 3970
|
|
},
|
|
{
|
|
"entropy": 5.720257997512817,
|
|
"epoch": 0.30927835051546393,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004993963526486555,
|
|
"loss": 5.7017,
|
|
"mean_token_accuracy": 0.1482631281018257,
|
|
"num_tokens": 6907470.0,
|
|
"step": 3975
|
|
},
|
|
{
|
|
"entropy": 5.764560747146606,
|
|
"epoch": 0.30966737988718146,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.000499394322105318,
|
|
"loss": 5.7458,
|
|
"mean_token_accuracy": 0.1479402005672455,
|
|
"num_tokens": 6916542.0,
|
|
"step": 3980
|
|
},
|
|
{
|
|
"entropy": 5.787787580490113,
|
|
"epoch": 0.31005640925889905,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004993922881571538,
|
|
"loss": 5.7351,
|
|
"mean_token_accuracy": 0.15070068687200547,
|
|
"num_tokens": 6925974.0,
|
|
"step": 3985
|
|
},
|
|
{
|
|
"entropy": 5.844771099090576,
|
|
"epoch": 0.31044543863061663,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004993902508041939,
|
|
"loss": 5.7617,
|
|
"mean_token_accuracy": 0.14442063346505166,
|
|
"num_tokens": 6934987.0,
|
|
"step": 3990
|
|
},
|
|
{
|
|
"entropy": 5.740097379684448,
|
|
"epoch": 0.31083446800233416,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.000499388210046469,
|
|
"loss": 5.627,
|
|
"mean_token_accuracy": 0.1496351808309555,
|
|
"num_tokens": 6944497.0,
|
|
"step": 3995
|
|
},
|
|
{
|
|
"entropy": 5.780975723266602,
|
|
"epoch": 0.31122349737405175,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004993861658840102,
|
|
"loss": 5.7836,
|
|
"mean_token_accuracy": 0.14486094415187836,
|
|
"num_tokens": 6953394.0,
|
|
"step": 4000
|
|
},
|
|
{
|
|
"entropy": 5.812648963928223,
|
|
"epoch": 0.3116125267457693,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004993841183168484,
|
|
"loss": 5.6935,
|
|
"mean_token_accuracy": 0.1492105931043625,
|
|
"num_tokens": 6961715.0,
|
|
"step": 4005
|
|
},
|
|
{
|
|
"entropy": 5.715365362167359,
|
|
"epoch": 0.31200155611748687,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004993820673450148,
|
|
"loss": 5.6817,
|
|
"mean_token_accuracy": 0.1526123121380806,
|
|
"num_tokens": 6970041.0,
|
|
"step": 4010
|
|
},
|
|
{
|
|
"entropy": 5.77872633934021,
|
|
"epoch": 0.31239058548920445,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004993800129685404,
|
|
"loss": 5.8191,
|
|
"mean_token_accuracy": 0.14505433291196823,
|
|
"num_tokens": 6979522.0,
|
|
"step": 4015
|
|
},
|
|
{
|
|
"entropy": 5.8086690425872805,
|
|
"epoch": 0.312779614860922,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004993779551874565,
|
|
"loss": 5.7951,
|
|
"mean_token_accuracy": 0.14526814669370652,
|
|
"num_tokens": 6988470.0,
|
|
"step": 4020
|
|
},
|
|
{
|
|
"entropy": 5.850487136840821,
|
|
"epoch": 0.31316864423263957,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004993758940017943,
|
|
"loss": 5.8028,
|
|
"mean_token_accuracy": 0.1522517517209053,
|
|
"num_tokens": 6996696.0,
|
|
"step": 4025
|
|
},
|
|
{
|
|
"entropy": 5.793247890472412,
|
|
"epoch": 0.31355767360435716,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.000499373829411585,
|
|
"loss": 5.6706,
|
|
"mean_token_accuracy": 0.15075592398643495,
|
|
"num_tokens": 7005297.0,
|
|
"step": 4030
|
|
},
|
|
{
|
|
"entropy": 5.730261754989624,
|
|
"epoch": 0.3139467029760747,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00049937176141686,
|
|
"loss": 5.6801,
|
|
"mean_token_accuracy": 0.14645842760801314,
|
|
"num_tokens": 7013569.0,
|
|
"step": 4035
|
|
},
|
|
{
|
|
"entropy": 5.691849660873413,
|
|
"epoch": 0.3143357323477923,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004993696900176506,
|
|
"loss": 5.6296,
|
|
"mean_token_accuracy": 0.15090864151716232,
|
|
"num_tokens": 7021449.0,
|
|
"step": 4040
|
|
},
|
|
{
|
|
"entropy": 5.768454551696777,
|
|
"epoch": 0.3147247617195098,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004993676152139883,
|
|
"loss": 5.7441,
|
|
"mean_token_accuracy": 0.1498594529926777,
|
|
"num_tokens": 7029663.0,
|
|
"step": 4045
|
|
},
|
|
{
|
|
"entropy": 5.767329740524292,
|
|
"epoch": 0.3151137910912274,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004993655370059046,
|
|
"loss": 5.7465,
|
|
"mean_token_accuracy": 0.14821898937225342,
|
|
"num_tokens": 7039038.0,
|
|
"step": 4050
|
|
},
|
|
{
|
|
"entropy": 5.761368322372436,
|
|
"epoch": 0.315502820462945,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004993634553934309,
|
|
"loss": 5.6943,
|
|
"mean_token_accuracy": 0.14744272455573082,
|
|
"num_tokens": 7047595.0,
|
|
"step": 4055
|
|
},
|
|
{
|
|
"entropy": 5.742858934402466,
|
|
"epoch": 0.3158918498346625,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004993613703765989,
|
|
"loss": 5.6969,
|
|
"mean_token_accuracy": 0.1454830937087536,
|
|
"num_tokens": 7055711.0,
|
|
"step": 4060
|
|
},
|
|
{
|
|
"entropy": 5.778909635543823,
|
|
"epoch": 0.3162808792063801,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004993592819554402,
|
|
"loss": 5.6788,
|
|
"mean_token_accuracy": 0.1514374330639839,
|
|
"num_tokens": 7064100.0,
|
|
"step": 4065
|
|
},
|
|
{
|
|
"entropy": 5.762971687316894,
|
|
"epoch": 0.3166699085780976,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004993571901299866,
|
|
"loss": 5.645,
|
|
"mean_token_accuracy": 0.15330631136894227,
|
|
"num_tokens": 7073040.0,
|
|
"step": 4070
|
|
},
|
|
{
|
|
"entropy": 5.745030260086059,
|
|
"epoch": 0.3170589379498152,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004993550949002697,
|
|
"loss": 5.7589,
|
|
"mean_token_accuracy": 0.14727019667625427,
|
|
"num_tokens": 7081513.0,
|
|
"step": 4075
|
|
},
|
|
{
|
|
"entropy": 5.708121204376221,
|
|
"epoch": 0.3174479673215328,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004993529962663213,
|
|
"loss": 5.6375,
|
|
"mean_token_accuracy": 0.15988217294216156,
|
|
"num_tokens": 7090704.0,
|
|
"step": 4080
|
|
},
|
|
{
|
|
"entropy": 5.765259790420532,
|
|
"epoch": 0.31783699669325033,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004993508942281732,
|
|
"loss": 5.8133,
|
|
"mean_token_accuracy": 0.14034881591796874,
|
|
"num_tokens": 7099692.0,
|
|
"step": 4085
|
|
},
|
|
{
|
|
"entropy": 5.717344760894775,
|
|
"epoch": 0.3182260260649679,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004993487887858575,
|
|
"loss": 5.6353,
|
|
"mean_token_accuracy": 0.15290754809975624,
|
|
"num_tokens": 7108021.0,
|
|
"step": 4090
|
|
},
|
|
{
|
|
"entropy": 5.70963306427002,
|
|
"epoch": 0.31861505543668545,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.000499346679939406,
|
|
"loss": 5.707,
|
|
"mean_token_accuracy": 0.1538894698023796,
|
|
"num_tokens": 7116689.0,
|
|
"step": 4095
|
|
},
|
|
{
|
|
"entropy": 5.800936269760132,
|
|
"epoch": 0.31900408480840303,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004993445676888507,
|
|
"loss": 5.8047,
|
|
"mean_token_accuracy": 0.14508455172181128,
|
|
"num_tokens": 7125453.0,
|
|
"step": 4100
|
|
},
|
|
{
|
|
"entropy": 5.8856371402740475,
|
|
"epoch": 0.3193931141801206,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004993424520342236,
|
|
"loss": 5.8201,
|
|
"mean_token_accuracy": 0.14714180082082748,
|
|
"num_tokens": 7133692.0,
|
|
"step": 4105
|
|
},
|
|
{
|
|
"entropy": 5.786088180541992,
|
|
"epoch": 0.31978214355183815,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004993403329755569,
|
|
"loss": 5.6686,
|
|
"mean_token_accuracy": 0.15330086052417755,
|
|
"num_tokens": 7142362.0,
|
|
"step": 4110
|
|
},
|
|
{
|
|
"entropy": 5.654343366622925,
|
|
"epoch": 0.32017117292355574,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004993382105128828,
|
|
"loss": 5.6641,
|
|
"mean_token_accuracy": 0.1514657586812973,
|
|
"num_tokens": 7151020.0,
|
|
"step": 4115
|
|
},
|
|
{
|
|
"entropy": 5.736981534957886,
|
|
"epoch": 0.32056020229527327,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004993360846462333,
|
|
"loss": 5.5871,
|
|
"mean_token_accuracy": 0.1543400302529335,
|
|
"num_tokens": 7159453.0,
|
|
"step": 4120
|
|
},
|
|
{
|
|
"entropy": 5.794591903686523,
|
|
"epoch": 0.32094923166699085,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004993339553756408,
|
|
"loss": 5.8648,
|
|
"mean_token_accuracy": 0.13662225604057313,
|
|
"num_tokens": 7168758.0,
|
|
"step": 4125
|
|
},
|
|
{
|
|
"entropy": 5.78389081954956,
|
|
"epoch": 0.32133826103870844,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004993318227011378,
|
|
"loss": 5.65,
|
|
"mean_token_accuracy": 0.1481809712946415,
|
|
"num_tokens": 7177835.0,
|
|
"step": 4130
|
|
},
|
|
{
|
|
"entropy": 5.765730667114258,
|
|
"epoch": 0.32172729041042597,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004993296866227562,
|
|
"loss": 5.7138,
|
|
"mean_token_accuracy": 0.1530051663517952,
|
|
"num_tokens": 7186424.0,
|
|
"step": 4135
|
|
},
|
|
{
|
|
"entropy": 5.728504276275634,
|
|
"epoch": 0.32211631978214356,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004993275471405288,
|
|
"loss": 5.68,
|
|
"mean_token_accuracy": 0.15667371749877929,
|
|
"num_tokens": 7194800.0,
|
|
"step": 4140
|
|
},
|
|
{
|
|
"entropy": 5.669158315658569,
|
|
"epoch": 0.32250534915386114,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004993254042544879,
|
|
"loss": 5.601,
|
|
"mean_token_accuracy": 0.15557201132178305,
|
|
"num_tokens": 7203820.0,
|
|
"step": 4145
|
|
},
|
|
{
|
|
"entropy": 5.740382957458496,
|
|
"epoch": 0.3228943785255787,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.000499323257964666,
|
|
"loss": 5.5999,
|
|
"mean_token_accuracy": 0.1512857735157013,
|
|
"num_tokens": 7211793.0,
|
|
"step": 4150
|
|
},
|
|
{
|
|
"entropy": 5.754996395111084,
|
|
"epoch": 0.32328340789729626,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004993211082710957,
|
|
"loss": 5.6797,
|
|
"mean_token_accuracy": 0.15267374813556672,
|
|
"num_tokens": 7220471.0,
|
|
"step": 4155
|
|
},
|
|
{
|
|
"entropy": 5.714694833755493,
|
|
"epoch": 0.3236724372690138,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004993189551738097,
|
|
"loss": 5.7188,
|
|
"mean_token_accuracy": 0.15086812674999237,
|
|
"num_tokens": 7228788.0,
|
|
"step": 4160
|
|
},
|
|
{
|
|
"entropy": 5.782597208023072,
|
|
"epoch": 0.3240614666407314,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004993167986728405,
|
|
"loss": 5.883,
|
|
"mean_token_accuracy": 0.15023963153362274,
|
|
"num_tokens": 7237707.0,
|
|
"step": 4165
|
|
},
|
|
{
|
|
"entropy": 5.8458487033844,
|
|
"epoch": 0.32445049601244896,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.000499314638768221,
|
|
"loss": 5.6281,
|
|
"mean_token_accuracy": 0.15212774872779847,
|
|
"num_tokens": 7246296.0,
|
|
"step": 4170
|
|
},
|
|
{
|
|
"entropy": 5.644246339797974,
|
|
"epoch": 0.3248395253841665,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004993124754599839,
|
|
"loss": 5.5669,
|
|
"mean_token_accuracy": 0.15392066538333893,
|
|
"num_tokens": 7255076.0,
|
|
"step": 4175
|
|
},
|
|
{
|
|
"entropy": 5.574113368988037,
|
|
"epoch": 0.3252285547558841,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004993103087481619,
|
|
"loss": 5.6564,
|
|
"mean_token_accuracy": 0.15235278755426407,
|
|
"num_tokens": 7263169.0,
|
|
"step": 4180
|
|
},
|
|
{
|
|
"entropy": 5.799724388122558,
|
|
"epoch": 0.3256175841276016,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004993081386327881,
|
|
"loss": 5.7203,
|
|
"mean_token_accuracy": 0.15436835139989852,
|
|
"num_tokens": 7271748.0,
|
|
"step": 4185
|
|
},
|
|
{
|
|
"entropy": 5.6705467224121096,
|
|
"epoch": 0.3260066134993192,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004993059651138953,
|
|
"loss": 5.5211,
|
|
"mean_token_accuracy": 0.15592404454946518,
|
|
"num_tokens": 7280291.0,
|
|
"step": 4190
|
|
},
|
|
{
|
|
"entropy": 5.644945335388184,
|
|
"epoch": 0.3263956428710368,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004993037881915165,
|
|
"loss": 5.7325,
|
|
"mean_token_accuracy": 0.14804291874170303,
|
|
"num_tokens": 7290307.0,
|
|
"step": 4195
|
|
},
|
|
{
|
|
"entropy": 5.853249645233154,
|
|
"epoch": 0.3267846722427543,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004993016078656847,
|
|
"loss": 5.808,
|
|
"mean_token_accuracy": 0.13991236835718154,
|
|
"num_tokens": 7297942.0,
|
|
"step": 4200
|
|
},
|
|
{
|
|
"entropy": 5.6778463363647464,
|
|
"epoch": 0.3271737016144719,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.000499299424136433,
|
|
"loss": 5.6824,
|
|
"mean_token_accuracy": 0.1468929223716259,
|
|
"num_tokens": 7307378.0,
|
|
"step": 4205
|
|
},
|
|
{
|
|
"entropy": 5.6782612800598145,
|
|
"epoch": 0.32756273098618943,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004992972370037946,
|
|
"loss": 5.6425,
|
|
"mean_token_accuracy": 0.15878840833902358,
|
|
"num_tokens": 7315985.0,
|
|
"step": 4210
|
|
},
|
|
{
|
|
"entropy": 5.799611949920655,
|
|
"epoch": 0.327951760357907,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004992950464678026,
|
|
"loss": 5.7613,
|
|
"mean_token_accuracy": 0.14839818179607392,
|
|
"num_tokens": 7324142.0,
|
|
"step": 4215
|
|
},
|
|
{
|
|
"entropy": 5.699645185470581,
|
|
"epoch": 0.3283407897296246,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004992928525284903,
|
|
"loss": 5.5936,
|
|
"mean_token_accuracy": 0.152157411724329,
|
|
"num_tokens": 7333012.0,
|
|
"step": 4220
|
|
},
|
|
{
|
|
"entropy": 5.69219651222229,
|
|
"epoch": 0.32872981910134214,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.000499290655185891,
|
|
"loss": 5.6537,
|
|
"mean_token_accuracy": 0.1559728801250458,
|
|
"num_tokens": 7341838.0,
|
|
"step": 4225
|
|
},
|
|
{
|
|
"entropy": 5.7062290668487545,
|
|
"epoch": 0.3291188484730597,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.000499288454440038,
|
|
"loss": 5.585,
|
|
"mean_token_accuracy": 0.16270716190338136,
|
|
"num_tokens": 7349986.0,
|
|
"step": 4230
|
|
},
|
|
{
|
|
"entropy": 5.8121857166290285,
|
|
"epoch": 0.3295078778447773,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004992862502909645,
|
|
"loss": 5.8354,
|
|
"mean_token_accuracy": 0.14307828694581987,
|
|
"num_tokens": 7359428.0,
|
|
"step": 4235
|
|
},
|
|
{
|
|
"entropy": 5.842578935623169,
|
|
"epoch": 0.32989690721649484,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004992840427387043,
|
|
"loss": 5.7562,
|
|
"mean_token_accuracy": 0.14591426253318787,
|
|
"num_tokens": 7368524.0,
|
|
"step": 4240
|
|
},
|
|
{
|
|
"entropy": 5.77540431022644,
|
|
"epoch": 0.3302859365882124,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004992818317832908,
|
|
"loss": 5.6245,
|
|
"mean_token_accuracy": 0.15161149799823762,
|
|
"num_tokens": 7377979.0,
|
|
"step": 4245
|
|
},
|
|
{
|
|
"entropy": 5.651564407348633,
|
|
"epoch": 0.33067496595992996,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004992796174247574,
|
|
"loss": 5.5426,
|
|
"mean_token_accuracy": 0.1534463346004486,
|
|
"num_tokens": 7386283.0,
|
|
"step": 4250
|
|
},
|
|
{
|
|
"entropy": 5.697298908233643,
|
|
"epoch": 0.33106399533164754,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004992773996631378,
|
|
"loss": 5.6872,
|
|
"mean_token_accuracy": 0.14380473047494888,
|
|
"num_tokens": 7395409.0,
|
|
"step": 4255
|
|
},
|
|
{
|
|
"entropy": 5.798315048217773,
|
|
"epoch": 0.33145302470336513,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004992751784984656,
|
|
"loss": 5.7596,
|
|
"mean_token_accuracy": 0.15002959668636323,
|
|
"num_tokens": 7403389.0,
|
|
"step": 4260
|
|
},
|
|
{
|
|
"entropy": 5.749740076065064,
|
|
"epoch": 0.33184205407508266,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004992729539307745,
|
|
"loss": 5.6936,
|
|
"mean_token_accuracy": 0.15267568230628967,
|
|
"num_tokens": 7411506.0,
|
|
"step": 4265
|
|
},
|
|
{
|
|
"entropy": 5.777366876602173,
|
|
"epoch": 0.33223108344680025,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004992707259600984,
|
|
"loss": 5.7505,
|
|
"mean_token_accuracy": 0.15245750099420546,
|
|
"num_tokens": 7420219.0,
|
|
"step": 4270
|
|
},
|
|
{
|
|
"entropy": 5.74856219291687,
|
|
"epoch": 0.3326201128185178,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004992684945864709,
|
|
"loss": 5.6674,
|
|
"mean_token_accuracy": 0.1537133276462555,
|
|
"num_tokens": 7428442.0,
|
|
"step": 4275
|
|
},
|
|
{
|
|
"entropy": 5.694894027709961,
|
|
"epoch": 0.33300914219023536,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004992662598099261,
|
|
"loss": 5.6273,
|
|
"mean_token_accuracy": 0.15412922501564025,
|
|
"num_tokens": 7436364.0,
|
|
"step": 4280
|
|
},
|
|
{
|
|
"entropy": 5.754441976547241,
|
|
"epoch": 0.33339817156195295,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004992640216304975,
|
|
"loss": 5.7116,
|
|
"mean_token_accuracy": 0.1454751044511795,
|
|
"num_tokens": 7444122.0,
|
|
"step": 4285
|
|
},
|
|
{
|
|
"entropy": 5.800494909286499,
|
|
"epoch": 0.3337872009336705,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004992617800482196,
|
|
"loss": 5.7159,
|
|
"mean_token_accuracy": 0.14412682875990868,
|
|
"num_tokens": 7454122.0,
|
|
"step": 4290
|
|
},
|
|
{
|
|
"entropy": 5.803664112091065,
|
|
"epoch": 0.33417623030538807,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.000499259535063126,
|
|
"loss": 5.7076,
|
|
"mean_token_accuracy": 0.14881345629692078,
|
|
"num_tokens": 7463057.0,
|
|
"step": 4295
|
|
},
|
|
{
|
|
"entropy": 5.784649085998535,
|
|
"epoch": 0.3345652596771056,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.000499257286675251,
|
|
"loss": 5.7042,
|
|
"mean_token_accuracy": 0.14605928510427474,
|
|
"num_tokens": 7471675.0,
|
|
"step": 4300
|
|
},
|
|
{
|
|
"entropy": 5.628243780136108,
|
|
"epoch": 0.3349542890488232,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004992550348846285,
|
|
"loss": 5.6254,
|
|
"mean_token_accuracy": 0.1545520916581154,
|
|
"num_tokens": 7479870.0,
|
|
"step": 4305
|
|
},
|
|
{
|
|
"entropy": 5.712979745864868,
|
|
"epoch": 0.33534331842054077,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004992527796912928,
|
|
"loss": 5.7166,
|
|
"mean_token_accuracy": 0.15018269568681716,
|
|
"num_tokens": 7489830.0,
|
|
"step": 4310
|
|
},
|
|
{
|
|
"entropy": 5.794428443908691,
|
|
"epoch": 0.3357323477922583,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004992505210952782,
|
|
"loss": 5.6457,
|
|
"mean_token_accuracy": 0.16175043433904648,
|
|
"num_tokens": 7497852.0,
|
|
"step": 4315
|
|
},
|
|
{
|
|
"entropy": 5.750661849975586,
|
|
"epoch": 0.3361213771639759,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004992482590966188,
|
|
"loss": 5.7708,
|
|
"mean_token_accuracy": 0.14660928770899773,
|
|
"num_tokens": 7506419.0,
|
|
"step": 4320
|
|
},
|
|
{
|
|
"entropy": 5.787262010574341,
|
|
"epoch": 0.3365104065356934,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004992459936953489,
|
|
"loss": 5.6804,
|
|
"mean_token_accuracy": 0.1589351177215576,
|
|
"num_tokens": 7514757.0,
|
|
"step": 4325
|
|
},
|
|
{
|
|
"entropy": 5.7645039558410645,
|
|
"epoch": 0.336899435907411,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004992437248915032,
|
|
"loss": 5.7262,
|
|
"mean_token_accuracy": 0.14898428171873093,
|
|
"num_tokens": 7523912.0,
|
|
"step": 4330
|
|
},
|
|
{
|
|
"entropy": 5.694207620620728,
|
|
"epoch": 0.3372884652791286,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004992414526851157,
|
|
"loss": 5.607,
|
|
"mean_token_accuracy": 0.1599605530500412,
|
|
"num_tokens": 7532401.0,
|
|
"step": 4335
|
|
},
|
|
{
|
|
"entropy": 5.60562539100647,
|
|
"epoch": 0.3376774946508461,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004992391770762212,
|
|
"loss": 5.5788,
|
|
"mean_token_accuracy": 0.15543587058782576,
|
|
"num_tokens": 7541257.0,
|
|
"step": 4340
|
|
},
|
|
{
|
|
"entropy": 5.666599273681641,
|
|
"epoch": 0.3380665240225637,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.000499236898064854,
|
|
"loss": 5.5247,
|
|
"mean_token_accuracy": 0.1493674822151661,
|
|
"num_tokens": 7549812.0,
|
|
"step": 4345
|
|
},
|
|
{
|
|
"entropy": 5.672925329208374,
|
|
"epoch": 0.3384555533942813,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004992346156510488,
|
|
"loss": 5.6191,
|
|
"mean_token_accuracy": 0.15019316226243973,
|
|
"num_tokens": 7559319.0,
|
|
"step": 4350
|
|
},
|
|
{
|
|
"entropy": 5.704488229751587,
|
|
"epoch": 0.3388445827659988,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004992323298348403,
|
|
"loss": 5.7552,
|
|
"mean_token_accuracy": 0.14404967427253723,
|
|
"num_tokens": 7567900.0,
|
|
"step": 4355
|
|
},
|
|
{
|
|
"entropy": 5.824366855621338,
|
|
"epoch": 0.3392336121377164,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.000499230040616263,
|
|
"loss": 5.6927,
|
|
"mean_token_accuracy": 0.14388166666030883,
|
|
"num_tokens": 7576163.0,
|
|
"step": 4360
|
|
},
|
|
{
|
|
"entropy": 5.722295093536377,
|
|
"epoch": 0.33962264150943394,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004992277479953518,
|
|
"loss": 5.6128,
|
|
"mean_token_accuracy": 0.15612045228481292,
|
|
"num_tokens": 7584221.0,
|
|
"step": 4365
|
|
},
|
|
{
|
|
"entropy": 5.714900970458984,
|
|
"epoch": 0.34001167088115153,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004992254519721414,
|
|
"loss": 5.6134,
|
|
"mean_token_accuracy": 0.1523975744843483,
|
|
"num_tokens": 7593569.0,
|
|
"step": 4370
|
|
},
|
|
{
|
|
"entropy": 5.7702394962310795,
|
|
"epoch": 0.3404007002528691,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004992231525466666,
|
|
"loss": 5.6852,
|
|
"mean_token_accuracy": 0.15293398201465608,
|
|
"num_tokens": 7602666.0,
|
|
"step": 4375
|
|
},
|
|
{
|
|
"entropy": 5.707553815841675,
|
|
"epoch": 0.34078972962458665,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004992208497189624,
|
|
"loss": 5.7505,
|
|
"mean_token_accuracy": 0.1456447049975395,
|
|
"num_tokens": 7611874.0,
|
|
"step": 4380
|
|
},
|
|
{
|
|
"entropy": 5.727844762802124,
|
|
"epoch": 0.34117875899630423,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004992185434890637,
|
|
"loss": 5.7134,
|
|
"mean_token_accuracy": 0.15101800262928008,
|
|
"num_tokens": 7620385.0,
|
|
"step": 4385
|
|
},
|
|
{
|
|
"entropy": 5.799562740325928,
|
|
"epoch": 0.34156778836802176,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004992162338570055,
|
|
"loss": 5.7695,
|
|
"mean_token_accuracy": 0.1401805505156517,
|
|
"num_tokens": 7628786.0,
|
|
"step": 4390
|
|
},
|
|
{
|
|
"entropy": 5.7082726001739506,
|
|
"epoch": 0.34195681773973935,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004992139208228227,
|
|
"loss": 5.5552,
|
|
"mean_token_accuracy": 0.1596037358045578,
|
|
"num_tokens": 7637389.0,
|
|
"step": 4395
|
|
},
|
|
{
|
|
"entropy": 5.713421058654785,
|
|
"epoch": 0.34234584711145694,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004992116043865506,
|
|
"loss": 5.7409,
|
|
"mean_token_accuracy": 0.15249803960323333,
|
|
"num_tokens": 7645793.0,
|
|
"step": 4400
|
|
},
|
|
{
|
|
"entropy": 5.833503723144531,
|
|
"epoch": 0.34273487648317447,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004992092845482244,
|
|
"loss": 5.6819,
|
|
"mean_token_accuracy": 0.155016727745533,
|
|
"num_tokens": 7653951.0,
|
|
"step": 4405
|
|
},
|
|
{
|
|
"entropy": 5.618052053451538,
|
|
"epoch": 0.34312390585489205,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004992069613078791,
|
|
"loss": 5.5504,
|
|
"mean_token_accuracy": 0.15958452820777894,
|
|
"num_tokens": 7662753.0,
|
|
"step": 4410
|
|
},
|
|
{
|
|
"entropy": 5.604360771179199,
|
|
"epoch": 0.3435129352266096,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004992046346655499,
|
|
"loss": 5.5333,
|
|
"mean_token_accuracy": 0.15088599622249604,
|
|
"num_tokens": 7671832.0,
|
|
"step": 4415
|
|
},
|
|
{
|
|
"entropy": 5.7284270286560055,
|
|
"epoch": 0.34390196459832717,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004992023046212723,
|
|
"loss": 5.7002,
|
|
"mean_token_accuracy": 0.1477256342768669,
|
|
"num_tokens": 7680969.0,
|
|
"step": 4420
|
|
},
|
|
{
|
|
"entropy": 5.806493806838989,
|
|
"epoch": 0.34429099397004476,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004991999711750816,
|
|
"loss": 5.7023,
|
|
"mean_token_accuracy": 0.14641763120889664,
|
|
"num_tokens": 7689277.0,
|
|
"step": 4425
|
|
},
|
|
{
|
|
"entropy": 5.647880125045776,
|
|
"epoch": 0.3446800233417623,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004991976343270133,
|
|
"loss": 5.6217,
|
|
"mean_token_accuracy": 0.15686147212982177,
|
|
"num_tokens": 7697373.0,
|
|
"step": 4430
|
|
},
|
|
{
|
|
"entropy": 5.785163259506225,
|
|
"epoch": 0.3450690527134799,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004991952940771026,
|
|
"loss": 5.7001,
|
|
"mean_token_accuracy": 0.14787215143442153,
|
|
"num_tokens": 7705767.0,
|
|
"step": 4435
|
|
},
|
|
{
|
|
"entropy": 5.7423583507537845,
|
|
"epoch": 0.34545808208519746,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004991929504253852,
|
|
"loss": 5.5801,
|
|
"mean_token_accuracy": 0.15587211549282073,
|
|
"num_tokens": 7713746.0,
|
|
"step": 4440
|
|
},
|
|
{
|
|
"entropy": 5.66847972869873,
|
|
"epoch": 0.345847111456915,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004991906033718966,
|
|
"loss": 5.7078,
|
|
"mean_token_accuracy": 0.1501286268234253,
|
|
"num_tokens": 7721829.0,
|
|
"step": 4445
|
|
},
|
|
{
|
|
"entropy": 5.678005170822144,
|
|
"epoch": 0.3462361408286326,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004991882529166724,
|
|
"loss": 5.606,
|
|
"mean_token_accuracy": 0.15749830454587938,
|
|
"num_tokens": 7730479.0,
|
|
"step": 4450
|
|
},
|
|
{
|
|
"entropy": 5.733396720886231,
|
|
"epoch": 0.3466251702003501,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004991858990597483,
|
|
"loss": 5.5688,
|
|
"mean_token_accuracy": 0.15935127139091493,
|
|
"num_tokens": 7738659.0,
|
|
"step": 4455
|
|
},
|
|
{
|
|
"entropy": 5.74834976196289,
|
|
"epoch": 0.3470141995720677,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004991835418011601,
|
|
"loss": 5.8354,
|
|
"mean_token_accuracy": 0.14780224710702897,
|
|
"num_tokens": 7747597.0,
|
|
"step": 4460
|
|
},
|
|
{
|
|
"entropy": 5.7559380531311035,
|
|
"epoch": 0.3474032289437853,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004991811811409434,
|
|
"loss": 5.6723,
|
|
"mean_token_accuracy": 0.15141887217760086,
|
|
"num_tokens": 7756666.0,
|
|
"step": 4465
|
|
},
|
|
{
|
|
"entropy": 5.747393035888672,
|
|
"epoch": 0.3477922583155028,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004991788170791341,
|
|
"loss": 5.7316,
|
|
"mean_token_accuracy": 0.14892500191926955,
|
|
"num_tokens": 7765621.0,
|
|
"step": 4470
|
|
},
|
|
{
|
|
"entropy": 5.701046562194824,
|
|
"epoch": 0.3481812876872204,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004991764496157682,
|
|
"loss": 5.6057,
|
|
"mean_token_accuracy": 0.15355693995952607,
|
|
"num_tokens": 7774137.0,
|
|
"step": 4475
|
|
},
|
|
{
|
|
"entropy": 5.773831367492676,
|
|
"epoch": 0.34857031705893793,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004991740787508814,
|
|
"loss": 5.7278,
|
|
"mean_token_accuracy": 0.1457068294286728,
|
|
"num_tokens": 7783144.0,
|
|
"step": 4480
|
|
},
|
|
{
|
|
"entropy": 5.776837158203125,
|
|
"epoch": 0.3489593464306555,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004991717044845097,
|
|
"loss": 5.7565,
|
|
"mean_token_accuracy": 0.1431121490895748,
|
|
"num_tokens": 7791530.0,
|
|
"step": 4485
|
|
},
|
|
{
|
|
"entropy": 5.703598833084106,
|
|
"epoch": 0.3493483758023731,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004991693268166892,
|
|
"loss": 5.6122,
|
|
"mean_token_accuracy": 0.15465120673179628,
|
|
"num_tokens": 7800869.0,
|
|
"step": 4490
|
|
},
|
|
{
|
|
"entropy": 5.708342218399048,
|
|
"epoch": 0.34973740517409063,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004991669457474559,
|
|
"loss": 5.6957,
|
|
"mean_token_accuracy": 0.14969323873519896,
|
|
"num_tokens": 7810201.0,
|
|
"step": 4495
|
|
},
|
|
{
|
|
"entropy": 5.738919591903686,
|
|
"epoch": 0.3501264345458082,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004991645612768461,
|
|
"loss": 5.5816,
|
|
"mean_token_accuracy": 0.15750054121017457,
|
|
"num_tokens": 7818529.0,
|
|
"step": 4500
|
|
},
|
|
{
|
|
"entropy": 5.6987754821777346,
|
|
"epoch": 0.35051546391752575,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004991621734048958,
|
|
"loss": 5.6281,
|
|
"mean_token_accuracy": 0.15793436765670776,
|
|
"num_tokens": 7827254.0,
|
|
"step": 4505
|
|
},
|
|
{
|
|
"entropy": 5.717825222015381,
|
|
"epoch": 0.35090449328924334,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004991597821316415,
|
|
"loss": 5.6367,
|
|
"mean_token_accuracy": 0.15578689575195312,
|
|
"num_tokens": 7836437.0,
|
|
"step": 4510
|
|
},
|
|
{
|
|
"entropy": 5.6809944152832035,
|
|
"epoch": 0.3512935226609609,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004991573874571192,
|
|
"loss": 5.6505,
|
|
"mean_token_accuracy": 0.15625278949737548,
|
|
"num_tokens": 7844939.0,
|
|
"step": 4515
|
|
},
|
|
{
|
|
"entropy": 5.744171571731568,
|
|
"epoch": 0.35168255203267845,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004991549893813653,
|
|
"loss": 5.6467,
|
|
"mean_token_accuracy": 0.15111799389123917,
|
|
"num_tokens": 7852889.0,
|
|
"step": 4520
|
|
},
|
|
{
|
|
"entropy": 5.718905258178711,
|
|
"epoch": 0.35207158140439604,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004991525879044162,
|
|
"loss": 5.7742,
|
|
"mean_token_accuracy": 0.14285053610801696,
|
|
"num_tokens": 7861867.0,
|
|
"step": 4525
|
|
},
|
|
{
|
|
"entropy": 5.70173134803772,
|
|
"epoch": 0.35246061077611357,
|
|
"grad_norm": 1.96875,
|
|
"learning_rate": 0.0004991501830263084,
|
|
"loss": 5.5581,
|
|
"mean_token_accuracy": 0.16079542636871338,
|
|
"num_tokens": 7869343.0,
|
|
"step": 4530
|
|
},
|
|
{
|
|
"entropy": 5.718532371520996,
|
|
"epoch": 0.35284964014783116,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004991477747470783,
|
|
"loss": 5.6141,
|
|
"mean_token_accuracy": 0.1536390244960785,
|
|
"num_tokens": 7877142.0,
|
|
"step": 4535
|
|
},
|
|
{
|
|
"entropy": 5.6804680824279785,
|
|
"epoch": 0.35323866951954874,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004991453630667625,
|
|
"loss": 5.6319,
|
|
"mean_token_accuracy": 0.15317441150546074,
|
|
"num_tokens": 7885183.0,
|
|
"step": 4540
|
|
},
|
|
{
|
|
"entropy": 5.5954615592956545,
|
|
"epoch": 0.3536276988912663,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004991429479853976,
|
|
"loss": 5.4785,
|
|
"mean_token_accuracy": 0.16167025715112687,
|
|
"num_tokens": 7893848.0,
|
|
"step": 4545
|
|
},
|
|
{
|
|
"entropy": 5.702354192733765,
|
|
"epoch": 0.35401672826298386,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004991405295030202,
|
|
"loss": 5.6413,
|
|
"mean_token_accuracy": 0.1551177144050598,
|
|
"num_tokens": 7902438.0,
|
|
"step": 4550
|
|
},
|
|
{
|
|
"entropy": 5.719379806518555,
|
|
"epoch": 0.35440575763470145,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004991381076196671,
|
|
"loss": 5.6199,
|
|
"mean_token_accuracy": 0.14993839859962463,
|
|
"num_tokens": 7910951.0,
|
|
"step": 4555
|
|
},
|
|
{
|
|
"entropy": 5.703114366531372,
|
|
"epoch": 0.354794787006419,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004991356823353748,
|
|
"loss": 5.7324,
|
|
"mean_token_accuracy": 0.14920267686247826,
|
|
"num_tokens": 7920375.0,
|
|
"step": 4560
|
|
},
|
|
{
|
|
"entropy": 5.6194535255432125,
|
|
"epoch": 0.35518381637813656,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004991332536501804,
|
|
"loss": 5.5954,
|
|
"mean_token_accuracy": 0.15626102834939956,
|
|
"num_tokens": 7928656.0,
|
|
"step": 4565
|
|
},
|
|
{
|
|
"entropy": 5.860740423202515,
|
|
"epoch": 0.3555728457498541,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004991308215641205,
|
|
"loss": 5.8495,
|
|
"mean_token_accuracy": 0.14026160910725594,
|
|
"num_tokens": 7936929.0,
|
|
"step": 4570
|
|
},
|
|
{
|
|
"entropy": 5.760818243026733,
|
|
"epoch": 0.3559618751215717,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004991283860772323,
|
|
"loss": 5.6492,
|
|
"mean_token_accuracy": 0.14879961758852006,
|
|
"num_tokens": 7945592.0,
|
|
"step": 4575
|
|
},
|
|
{
|
|
"entropy": 5.650161838531494,
|
|
"epoch": 0.35635090449328927,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004991259471895525,
|
|
"loss": 5.6004,
|
|
"mean_token_accuracy": 0.15918619483709334,
|
|
"num_tokens": 7953656.0,
|
|
"step": 4580
|
|
},
|
|
{
|
|
"entropy": 5.738786506652832,
|
|
"epoch": 0.3567399338650068,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004991235049011182,
|
|
"loss": 5.6646,
|
|
"mean_token_accuracy": 0.1567249059677124,
|
|
"num_tokens": 7962038.0,
|
|
"step": 4585
|
|
},
|
|
{
|
|
"entropy": 5.75248613357544,
|
|
"epoch": 0.3571289632367244,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004991210592119663,
|
|
"loss": 5.7409,
|
|
"mean_token_accuracy": 0.15061618089675904,
|
|
"num_tokens": 7970338.0,
|
|
"step": 4590
|
|
},
|
|
{
|
|
"entropy": 5.7730889320373535,
|
|
"epoch": 0.3575179926084419,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004991186101221342,
|
|
"loss": 5.6885,
|
|
"mean_token_accuracy": 0.1533726707100868,
|
|
"num_tokens": 7979173.0,
|
|
"step": 4595
|
|
},
|
|
{
|
|
"entropy": 5.684975576400757,
|
|
"epoch": 0.3579070219801595,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.000499116157631659,
|
|
"loss": 5.5434,
|
|
"mean_token_accuracy": 0.15786126405000686,
|
|
"num_tokens": 7987245.0,
|
|
"step": 4600
|
|
},
|
|
{
|
|
"entropy": 5.746752738952637,
|
|
"epoch": 0.3582960513518771,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004991137017405777,
|
|
"loss": 5.7517,
|
|
"mean_token_accuracy": 0.1434320978820324,
|
|
"num_tokens": 7995551.0,
|
|
"step": 4605
|
|
},
|
|
{
|
|
"entropy": 5.696102046966553,
|
|
"epoch": 0.3586850807235946,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004991112424489277,
|
|
"loss": 5.5554,
|
|
"mean_token_accuracy": 0.1520062044262886,
|
|
"num_tokens": 8004069.0,
|
|
"step": 4610
|
|
},
|
|
{
|
|
"entropy": 5.6995116710662845,
|
|
"epoch": 0.3590741100953122,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004991087797567462,
|
|
"loss": 5.6281,
|
|
"mean_token_accuracy": 0.15816846638917922,
|
|
"num_tokens": 8012537.0,
|
|
"step": 4615
|
|
},
|
|
{
|
|
"entropy": 5.74906325340271,
|
|
"epoch": 0.35946313946702974,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004991063136640709,
|
|
"loss": 5.6291,
|
|
"mean_token_accuracy": 0.1546050116419792,
|
|
"num_tokens": 8021387.0,
|
|
"step": 4620
|
|
},
|
|
{
|
|
"entropy": 5.695987272262573,
|
|
"epoch": 0.3598521688387473,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004991038441709388,
|
|
"loss": 5.5895,
|
|
"mean_token_accuracy": 0.14997338727116585,
|
|
"num_tokens": 8030261.0,
|
|
"step": 4625
|
|
},
|
|
{
|
|
"entropy": 5.689025735855102,
|
|
"epoch": 0.3602411982104649,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004991013712773877,
|
|
"loss": 5.6312,
|
|
"mean_token_accuracy": 0.153862264752388,
|
|
"num_tokens": 8038161.0,
|
|
"step": 4630
|
|
},
|
|
{
|
|
"entropy": 5.657052612304687,
|
|
"epoch": 0.36063022758218244,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004990988949834549,
|
|
"loss": 5.7432,
|
|
"mean_token_accuracy": 0.15323333889245988,
|
|
"num_tokens": 8046340.0,
|
|
"step": 4635
|
|
},
|
|
{
|
|
"entropy": 5.715617418289185,
|
|
"epoch": 0.3610192569539,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.000499096415289178,
|
|
"loss": 5.6568,
|
|
"mean_token_accuracy": 0.14950874000787734,
|
|
"num_tokens": 8054997.0,
|
|
"step": 4640
|
|
},
|
|
{
|
|
"entropy": 5.695255374908447,
|
|
"epoch": 0.3614082863256176,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004990939321945948,
|
|
"loss": 5.5849,
|
|
"mean_token_accuracy": 0.1639966607093811,
|
|
"num_tokens": 8063686.0,
|
|
"step": 4645
|
|
},
|
|
{
|
|
"entropy": 5.710863208770752,
|
|
"epoch": 0.36179731569733514,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004990914456997427,
|
|
"loss": 5.7086,
|
|
"mean_token_accuracy": 0.1489490434527397,
|
|
"num_tokens": 8072999.0,
|
|
"step": 4650
|
|
},
|
|
{
|
|
"entropy": 5.690041255950928,
|
|
"epoch": 0.36218634506905273,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004990889558046598,
|
|
"loss": 5.5645,
|
|
"mean_token_accuracy": 0.1560773268342018,
|
|
"num_tokens": 8081596.0,
|
|
"step": 4655
|
|
},
|
|
{
|
|
"entropy": 5.72937912940979,
|
|
"epoch": 0.36257537444077026,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004990864625093836,
|
|
"loss": 5.7816,
|
|
"mean_token_accuracy": 0.14247273206710814,
|
|
"num_tokens": 8090948.0,
|
|
"step": 4660
|
|
},
|
|
{
|
|
"entropy": 5.6643657207489015,
|
|
"epoch": 0.36296440381248785,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004990839658139519,
|
|
"loss": 5.799,
|
|
"mean_token_accuracy": 0.1458192102611065,
|
|
"num_tokens": 8099445.0,
|
|
"step": 4665
|
|
},
|
|
{
|
|
"entropy": 5.813397216796875,
|
|
"epoch": 0.36335343318420543,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004990814657184028,
|
|
"loss": 5.6501,
|
|
"mean_token_accuracy": 0.1459254652261734,
|
|
"num_tokens": 8108119.0,
|
|
"step": 4670
|
|
},
|
|
{
|
|
"entropy": 5.736115980148315,
|
|
"epoch": 0.36374246255592296,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004990789622227741,
|
|
"loss": 5.6347,
|
|
"mean_token_accuracy": 0.155676993727684,
|
|
"num_tokens": 8117060.0,
|
|
"step": 4675
|
|
},
|
|
{
|
|
"entropy": 5.6474851131439205,
|
|
"epoch": 0.36413149192764055,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004990764553271038,
|
|
"loss": 5.6449,
|
|
"mean_token_accuracy": 0.15143004208803176,
|
|
"num_tokens": 8126229.0,
|
|
"step": 4680
|
|
},
|
|
{
|
|
"entropy": 5.770573329925537,
|
|
"epoch": 0.3645205212993581,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004990739450314299,
|
|
"loss": 5.5885,
|
|
"mean_token_accuracy": 0.16371004581451415,
|
|
"num_tokens": 8134694.0,
|
|
"step": 4685
|
|
},
|
|
{
|
|
"entropy": 5.711445045471192,
|
|
"epoch": 0.36490955067107567,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004990714313357906,
|
|
"loss": 5.6771,
|
|
"mean_token_accuracy": 0.15631382912397385,
|
|
"num_tokens": 8143329.0,
|
|
"step": 4690
|
|
},
|
|
{
|
|
"entropy": 5.730293607711792,
|
|
"epoch": 0.36529858004279325,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.000499068914240224,
|
|
"loss": 5.6411,
|
|
"mean_token_accuracy": 0.15634608566761016,
|
|
"num_tokens": 8151432.0,
|
|
"step": 4695
|
|
},
|
|
{
|
|
"entropy": 5.707852506637574,
|
|
"epoch": 0.3656876094145108,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004990663937447682,
|
|
"loss": 5.6118,
|
|
"mean_token_accuracy": 0.1526152104139328,
|
|
"num_tokens": 8159677.0,
|
|
"step": 4700
|
|
},
|
|
{
|
|
"entropy": 5.667193222045898,
|
|
"epoch": 0.36607663878622837,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004990638698494615,
|
|
"loss": 5.6807,
|
|
"mean_token_accuracy": 0.1495601326227188,
|
|
"num_tokens": 8168710.0,
|
|
"step": 4705
|
|
},
|
|
{
|
|
"entropy": 5.735263824462891,
|
|
"epoch": 0.3664656681579459,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004990613425543423,
|
|
"loss": 5.6641,
|
|
"mean_token_accuracy": 0.15385617315769196,
|
|
"num_tokens": 8177501.0,
|
|
"step": 4710
|
|
},
|
|
{
|
|
"entropy": 5.808036041259766,
|
|
"epoch": 0.3668546975296635,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004990588118594487,
|
|
"loss": 5.7201,
|
|
"mean_token_accuracy": 0.14891381859779357,
|
|
"num_tokens": 8185791.0,
|
|
"step": 4715
|
|
},
|
|
{
|
|
"entropy": 5.8024543762207035,
|
|
"epoch": 0.3672437269013811,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004990562777648194,
|
|
"loss": 5.7748,
|
|
"mean_token_accuracy": 0.14869312196969986,
|
|
"num_tokens": 8195020.0,
|
|
"step": 4720
|
|
},
|
|
{
|
|
"entropy": 5.676599073410034,
|
|
"epoch": 0.3676327562730986,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004990537402704928,
|
|
"loss": 5.6258,
|
|
"mean_token_accuracy": 0.15125969499349595,
|
|
"num_tokens": 8203540.0,
|
|
"step": 4725
|
|
},
|
|
{
|
|
"entropy": 5.7572613716125485,
|
|
"epoch": 0.3680217856448162,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004990511993765071,
|
|
"loss": 5.6237,
|
|
"mean_token_accuracy": 0.145894156396389,
|
|
"num_tokens": 8211985.0,
|
|
"step": 4730
|
|
},
|
|
{
|
|
"entropy": 5.705409526824951,
|
|
"epoch": 0.3684108150165337,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004990486550829011,
|
|
"loss": 5.722,
|
|
"mean_token_accuracy": 0.15292975902557374,
|
|
"num_tokens": 8220289.0,
|
|
"step": 4735
|
|
},
|
|
{
|
|
"entropy": 5.775411319732666,
|
|
"epoch": 0.3687998443882513,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004990461073897134,
|
|
"loss": 5.7296,
|
|
"mean_token_accuracy": 0.14575534611940383,
|
|
"num_tokens": 8229652.0,
|
|
"step": 4740
|
|
},
|
|
{
|
|
"entropy": 5.7946971416473385,
|
|
"epoch": 0.3691888737599689,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004990435562969827,
|
|
"loss": 5.7238,
|
|
"mean_token_accuracy": 0.1478371188044548,
|
|
"num_tokens": 8237728.0,
|
|
"step": 4745
|
|
},
|
|
{
|
|
"entropy": 5.672537851333618,
|
|
"epoch": 0.3695779031316864,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004990410018047475,
|
|
"loss": 5.6033,
|
|
"mean_token_accuracy": 0.1582069531083107,
|
|
"num_tokens": 8246393.0,
|
|
"step": 4750
|
|
},
|
|
{
|
|
"entropy": 5.65901894569397,
|
|
"epoch": 0.369966932503404,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004990384439130467,
|
|
"loss": 5.5803,
|
|
"mean_token_accuracy": 0.1581738367676735,
|
|
"num_tokens": 8256736.0,
|
|
"step": 4755
|
|
},
|
|
{
|
|
"entropy": 5.713288354873657,
|
|
"epoch": 0.3703559618751216,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004990358826219192,
|
|
"loss": 5.6671,
|
|
"mean_token_accuracy": 0.1525496646761894,
|
|
"num_tokens": 8265126.0,
|
|
"step": 4760
|
|
},
|
|
{
|
|
"entropy": 5.673987913131714,
|
|
"epoch": 0.37074499124683913,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004990333179314038,
|
|
"loss": 5.5675,
|
|
"mean_token_accuracy": 0.16033463254570962,
|
|
"num_tokens": 8273136.0,
|
|
"step": 4765
|
|
},
|
|
{
|
|
"entropy": 5.5935968399047855,
|
|
"epoch": 0.3711340206185567,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004990307498415393,
|
|
"loss": 5.5157,
|
|
"mean_token_accuracy": 0.15778175815939904,
|
|
"num_tokens": 8281697.0,
|
|
"step": 4770
|
|
},
|
|
{
|
|
"entropy": 5.661153793334961,
|
|
"epoch": 0.37152304999027425,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004990281783523648,
|
|
"loss": 5.6416,
|
|
"mean_token_accuracy": 0.15251789540052413,
|
|
"num_tokens": 8290765.0,
|
|
"step": 4775
|
|
},
|
|
{
|
|
"entropy": 5.774856805801392,
|
|
"epoch": 0.37191207936199183,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004990256034639192,
|
|
"loss": 5.7424,
|
|
"mean_token_accuracy": 0.15171144902706146,
|
|
"num_tokens": 8299875.0,
|
|
"step": 4780
|
|
},
|
|
{
|
|
"entropy": 5.723652935028076,
|
|
"epoch": 0.3723011087337094,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004990230251762418,
|
|
"loss": 5.5917,
|
|
"mean_token_accuracy": 0.15435779988765716,
|
|
"num_tokens": 8308515.0,
|
|
"step": 4785
|
|
},
|
|
{
|
|
"entropy": 5.643715858459473,
|
|
"epoch": 0.37269013810542695,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004990204434893713,
|
|
"loss": 5.5321,
|
|
"mean_token_accuracy": 0.16223240792751312,
|
|
"num_tokens": 8317260.0,
|
|
"step": 4790
|
|
},
|
|
{
|
|
"entropy": 5.733455801010132,
|
|
"epoch": 0.37307916747714454,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004990178584033474,
|
|
"loss": 5.7032,
|
|
"mean_token_accuracy": 0.14542452991008759,
|
|
"num_tokens": 8325887.0,
|
|
"step": 4795
|
|
},
|
|
{
|
|
"entropy": 5.807884931564331,
|
|
"epoch": 0.37346819684886207,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004990152699182089,
|
|
"loss": 5.6957,
|
|
"mean_token_accuracy": 0.14746703654527665,
|
|
"num_tokens": 8333974.0,
|
|
"step": 4800
|
|
},
|
|
{
|
|
"entropy": 5.663190746307373,
|
|
"epoch": 0.37385722622057965,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004990126780339953,
|
|
"loss": 5.6718,
|
|
"mean_token_accuracy": 0.150137347728014,
|
|
"num_tokens": 8343199.0,
|
|
"step": 4805
|
|
},
|
|
{
|
|
"entropy": 5.65055775642395,
|
|
"epoch": 0.37424625559229724,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004990100827507459,
|
|
"loss": 5.4679,
|
|
"mean_token_accuracy": 0.15703100562095643,
|
|
"num_tokens": 8351202.0,
|
|
"step": 4810
|
|
},
|
|
{
|
|
"entropy": 5.8034525394439695,
|
|
"epoch": 0.37463528496401477,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004990074840684999,
|
|
"loss": 5.8139,
|
|
"mean_token_accuracy": 0.14493113085627557,
|
|
"num_tokens": 8360011.0,
|
|
"step": 4815
|
|
},
|
|
{
|
|
"entropy": 5.730612754821777,
|
|
"epoch": 0.37502431433573236,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004990048819872969,
|
|
"loss": 5.6824,
|
|
"mean_token_accuracy": 0.14951779693365097,
|
|
"num_tokens": 8367874.0,
|
|
"step": 4820
|
|
},
|
|
{
|
|
"entropy": 5.764990949630738,
|
|
"epoch": 0.3754133437074499,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004990022765071765,
|
|
"loss": 5.6266,
|
|
"mean_token_accuracy": 0.1553083539009094,
|
|
"num_tokens": 8376708.0,
|
|
"step": 4825
|
|
},
|
|
{
|
|
"entropy": 5.751033639907837,
|
|
"epoch": 0.3758023730791675,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.000498999667628178,
|
|
"loss": 5.6593,
|
|
"mean_token_accuracy": 0.15553711280226706,
|
|
"num_tokens": 8385467.0,
|
|
"step": 4830
|
|
},
|
|
{
|
|
"entropy": 5.661866140365601,
|
|
"epoch": 0.37619140245088506,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004989970553503411,
|
|
"loss": 5.6369,
|
|
"mean_token_accuracy": 0.1533681184053421,
|
|
"num_tokens": 8393574.0,
|
|
"step": 4835
|
|
},
|
|
{
|
|
"entropy": 5.700920581817627,
|
|
"epoch": 0.3765804318226026,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004989944396737054,
|
|
"loss": 5.6883,
|
|
"mean_token_accuracy": 0.15565296560525893,
|
|
"num_tokens": 8402857.0,
|
|
"step": 4840
|
|
},
|
|
{
|
|
"entropy": 5.719412469863892,
|
|
"epoch": 0.3769694611943202,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004989918205983106,
|
|
"loss": 5.6927,
|
|
"mean_token_accuracy": 0.15826139450073243,
|
|
"num_tokens": 8411728.0,
|
|
"step": 4845
|
|
},
|
|
{
|
|
"entropy": 5.737651777267456,
|
|
"epoch": 0.37735849056603776,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004989891981241964,
|
|
"loss": 5.6565,
|
|
"mean_token_accuracy": 0.15724968016147614,
|
|
"num_tokens": 8420307.0,
|
|
"step": 4850
|
|
},
|
|
{
|
|
"entropy": 5.77147650718689,
|
|
"epoch": 0.3777475199377553,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004989865722514027,
|
|
"loss": 5.6531,
|
|
"mean_token_accuracy": 0.1501496620476246,
|
|
"num_tokens": 8429442.0,
|
|
"step": 4855
|
|
},
|
|
{
|
|
"entropy": 5.659721899032593,
|
|
"epoch": 0.3781365493094729,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004989839429799692,
|
|
"loss": 5.5716,
|
|
"mean_token_accuracy": 0.15629539638757706,
|
|
"num_tokens": 8437945.0,
|
|
"step": 4860
|
|
},
|
|
{
|
|
"entropy": 5.714521837234497,
|
|
"epoch": 0.3785255786811904,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.000498981310309936,
|
|
"loss": 5.5716,
|
|
"mean_token_accuracy": 0.15861747562885284,
|
|
"num_tokens": 8445743.0,
|
|
"step": 4865
|
|
},
|
|
{
|
|
"entropy": 5.695272302627563,
|
|
"epoch": 0.378914608052908,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.0004989786742413428,
|
|
"loss": 5.6519,
|
|
"mean_token_accuracy": 0.14744135290384291,
|
|
"num_tokens": 8454091.0,
|
|
"step": 4870
|
|
},
|
|
{
|
|
"entropy": 5.798042869567871,
|
|
"epoch": 0.3793036374246256,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004989760347742298,
|
|
"loss": 5.6442,
|
|
"mean_token_accuracy": 0.15111523866653442,
|
|
"num_tokens": 8461992.0,
|
|
"step": 4875
|
|
},
|
|
{
|
|
"entropy": 5.67188515663147,
|
|
"epoch": 0.3796926667963431,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004989733919086369,
|
|
"loss": 5.5914,
|
|
"mean_token_accuracy": 0.15108274072408676,
|
|
"num_tokens": 8470730.0,
|
|
"step": 4880
|
|
},
|
|
{
|
|
"entropy": 5.6487571716308596,
|
|
"epoch": 0.3800816961680607,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004989707456446043,
|
|
"loss": 5.6359,
|
|
"mean_token_accuracy": 0.1524697870016098,
|
|
"num_tokens": 8479947.0,
|
|
"step": 4885
|
|
},
|
|
{
|
|
"entropy": 5.820005083084107,
|
|
"epoch": 0.38047072553977823,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.0004989680959821721,
|
|
"loss": 5.7174,
|
|
"mean_token_accuracy": 0.15552355349063873,
|
|
"num_tokens": 8488237.0,
|
|
"step": 4890
|
|
},
|
|
{
|
|
"entropy": 5.730929136276245,
|
|
"epoch": 0.3808597549114958,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004989654429213805,
|
|
"loss": 5.5951,
|
|
"mean_token_accuracy": 0.15518385022878647,
|
|
"num_tokens": 8497146.0,
|
|
"step": 4895
|
|
},
|
|
{
|
|
"entropy": 5.732660722732544,
|
|
"epoch": 0.3812487842832134,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004989627864622699,
|
|
"loss": 5.6644,
|
|
"mean_token_accuracy": 0.1581107959151268,
|
|
"num_tokens": 8505736.0,
|
|
"step": 4900
|
|
},
|
|
{
|
|
"entropy": 5.759604024887085,
|
|
"epoch": 0.38163781365493094,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004989601266048804,
|
|
"loss": 5.6906,
|
|
"mean_token_accuracy": 0.1508707135915756,
|
|
"num_tokens": 8515368.0,
|
|
"step": 4905
|
|
},
|
|
{
|
|
"entropy": 5.648067283630371,
|
|
"epoch": 0.3820268430266485,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004989574633492525,
|
|
"loss": 5.6427,
|
|
"mean_token_accuracy": 0.15200707018375398,
|
|
"num_tokens": 8524141.0,
|
|
"step": 4910
|
|
},
|
|
{
|
|
"entropy": 5.746055269241333,
|
|
"epoch": 0.38241587239836605,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004989547966954266,
|
|
"loss": 5.5739,
|
|
"mean_token_accuracy": 0.15738762766122819,
|
|
"num_tokens": 8533116.0,
|
|
"step": 4915
|
|
},
|
|
{
|
|
"entropy": 5.676274251937866,
|
|
"epoch": 0.38280490177008364,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.000498952126643443,
|
|
"loss": 5.7048,
|
|
"mean_token_accuracy": 0.1555192805826664,
|
|
"num_tokens": 8541919.0,
|
|
"step": 4920
|
|
},
|
|
{
|
|
"entropy": 5.666186428070068,
|
|
"epoch": 0.3831939311418012,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004989494531933424,
|
|
"loss": 5.5779,
|
|
"mean_token_accuracy": 0.16277866214513778,
|
|
"num_tokens": 8550372.0,
|
|
"step": 4925
|
|
},
|
|
{
|
|
"entropy": 5.69950647354126,
|
|
"epoch": 0.38358296051351876,
|
|
"grad_norm": 1.9921875,
|
|
"learning_rate": 0.0004989467763451652,
|
|
"loss": 5.6805,
|
|
"mean_token_accuracy": 0.15124470740556717,
|
|
"num_tokens": 8559246.0,
|
|
"step": 4930
|
|
},
|
|
{
|
|
"entropy": 5.686834812164307,
|
|
"epoch": 0.38397198988523634,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004989440960989523,
|
|
"loss": 5.4475,
|
|
"mean_token_accuracy": 0.15825097039341926,
|
|
"num_tokens": 8567005.0,
|
|
"step": 4935
|
|
},
|
|
{
|
|
"entropy": 5.639964866638183,
|
|
"epoch": 0.3843610192569539,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.000498941412454744,
|
|
"loss": 5.6371,
|
|
"mean_token_accuracy": 0.1471511870622635,
|
|
"num_tokens": 8575399.0,
|
|
"step": 4940
|
|
},
|
|
{
|
|
"entropy": 5.759636640548706,
|
|
"epoch": 0.38475004862867146,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004989387254125813,
|
|
"loss": 5.7076,
|
|
"mean_token_accuracy": 0.1482891246676445,
|
|
"num_tokens": 8583994.0,
|
|
"step": 4945
|
|
},
|
|
{
|
|
"entropy": 5.673126363754273,
|
|
"epoch": 0.38513907800038905,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004989360349725049,
|
|
"loss": 5.6343,
|
|
"mean_token_accuracy": 0.15608929246664047,
|
|
"num_tokens": 8593446.0,
|
|
"step": 4950
|
|
},
|
|
{
|
|
"entropy": 5.6657758235931395,
|
|
"epoch": 0.3855281073721066,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004989333411345555,
|
|
"loss": 5.6386,
|
|
"mean_token_accuracy": 0.157931412756443,
|
|
"num_tokens": 8602821.0,
|
|
"step": 4955
|
|
},
|
|
{
|
|
"entropy": 5.712670803070068,
|
|
"epoch": 0.38591713674382416,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004989306438987742,
|
|
"loss": 5.72,
|
|
"mean_token_accuracy": 0.1497579336166382,
|
|
"num_tokens": 8611831.0,
|
|
"step": 4960
|
|
},
|
|
{
|
|
"entropy": 5.770417785644531,
|
|
"epoch": 0.38630616611554175,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004989279432652018,
|
|
"loss": 5.6366,
|
|
"mean_token_accuracy": 0.1543237864971161,
|
|
"num_tokens": 8620986.0,
|
|
"step": 4965
|
|
},
|
|
{
|
|
"entropy": 5.70151948928833,
|
|
"epoch": 0.3866951954872593,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004989252392338791,
|
|
"loss": 5.5811,
|
|
"mean_token_accuracy": 0.15260136350989342,
|
|
"num_tokens": 8629822.0,
|
|
"step": 4970
|
|
},
|
|
{
|
|
"entropy": 5.686306619644165,
|
|
"epoch": 0.38708422485897687,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004989225318048475,
|
|
"loss": 5.6852,
|
|
"mean_token_accuracy": 0.15193748623132705,
|
|
"num_tokens": 8637679.0,
|
|
"step": 4975
|
|
},
|
|
{
|
|
"entropy": 5.7545572280883786,
|
|
"epoch": 0.3874732542306944,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004989198209781478,
|
|
"loss": 5.6936,
|
|
"mean_token_accuracy": 0.14812016040086745,
|
|
"num_tokens": 8646705.0,
|
|
"step": 4980
|
|
},
|
|
{
|
|
"entropy": 5.724243593215943,
|
|
"epoch": 0.387862283602412,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004989171067538211,
|
|
"loss": 5.6237,
|
|
"mean_token_accuracy": 0.1545564353466034,
|
|
"num_tokens": 8655599.0,
|
|
"step": 4985
|
|
},
|
|
{
|
|
"entropy": 5.619625043869019,
|
|
"epoch": 0.38825131297412957,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.000498914389131909,
|
|
"loss": 5.6442,
|
|
"mean_token_accuracy": 0.15381217300891875,
|
|
"num_tokens": 8665025.0,
|
|
"step": 4990
|
|
},
|
|
{
|
|
"entropy": 5.708271598815918,
|
|
"epoch": 0.3886403423458471,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004989116681124523,
|
|
"loss": 5.5306,
|
|
"mean_token_accuracy": 0.1580642953515053,
|
|
"num_tokens": 8672994.0,
|
|
"step": 4995
|
|
},
|
|
{
|
|
"entropy": 5.65806941986084,
|
|
"epoch": 0.3890293717175647,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004989089436954924,
|
|
"loss": 5.6668,
|
|
"mean_token_accuracy": 0.14796073883771896,
|
|
"num_tokens": 8682457.0,
|
|
"step": 5000
|
|
},
|
|
{
|
|
"entropy": 5.756362533569336,
|
|
"epoch": 0.3894184010892822,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004989062158810706,
|
|
"loss": 5.6494,
|
|
"mean_token_accuracy": 0.14854784011840821,
|
|
"num_tokens": 8690888.0,
|
|
"step": 5005
|
|
},
|
|
{
|
|
"entropy": 5.874982452392578,
|
|
"epoch": 0.3898074304609998,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004989034846692284,
|
|
"loss": 5.7342,
|
|
"mean_token_accuracy": 0.14854283779859542,
|
|
"num_tokens": 8699632.0,
|
|
"step": 5010
|
|
},
|
|
{
|
|
"entropy": 5.618406581878662,
|
|
"epoch": 0.3901964598327174,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004989007500600073,
|
|
"loss": 5.5681,
|
|
"mean_token_accuracy": 0.1586075857281685,
|
|
"num_tokens": 8707955.0,
|
|
"step": 5015
|
|
},
|
|
{
|
|
"entropy": 5.696351194381714,
|
|
"epoch": 0.3905854892044349,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004988980120534486,
|
|
"loss": 5.7249,
|
|
"mean_token_accuracy": 0.15431059300899505,
|
|
"num_tokens": 8716103.0,
|
|
"step": 5020
|
|
},
|
|
{
|
|
"entropy": 5.717636823654175,
|
|
"epoch": 0.3909745185761525,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.000498895270649594,
|
|
"loss": 5.5969,
|
|
"mean_token_accuracy": 0.15844181925058365,
|
|
"num_tokens": 8724499.0,
|
|
"step": 5025
|
|
},
|
|
{
|
|
"entropy": 5.652965831756592,
|
|
"epoch": 0.39136354794787004,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.000498892525848485,
|
|
"loss": 5.5992,
|
|
"mean_token_accuracy": 0.16202757209539415,
|
|
"num_tokens": 8732829.0,
|
|
"step": 5030
|
|
},
|
|
{
|
|
"entropy": 5.615494728088379,
|
|
"epoch": 0.3917525773195876,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004988897776501633,
|
|
"loss": 5.4632,
|
|
"mean_token_accuracy": 0.16178750693798066,
|
|
"num_tokens": 8741617.0,
|
|
"step": 5035
|
|
},
|
|
{
|
|
"entropy": 5.631573343276978,
|
|
"epoch": 0.3921416066913052,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004988870260546705,
|
|
"loss": 5.4519,
|
|
"mean_token_accuracy": 0.16094308644533156,
|
|
"num_tokens": 8750146.0,
|
|
"step": 5040
|
|
},
|
|
{
|
|
"entropy": 5.665295839309692,
|
|
"epoch": 0.39253063606302274,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004988842710620486,
|
|
"loss": 5.6205,
|
|
"mean_token_accuracy": 0.15644755065441132,
|
|
"num_tokens": 8758744.0,
|
|
"step": 5045
|
|
},
|
|
{
|
|
"entropy": 5.642523574829101,
|
|
"epoch": 0.39291966543474033,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004988815126723391,
|
|
"loss": 5.6359,
|
|
"mean_token_accuracy": 0.1529886543750763,
|
|
"num_tokens": 8768219.0,
|
|
"step": 5050
|
|
},
|
|
{
|
|
"entropy": 5.702886581420898,
|
|
"epoch": 0.3933086948064579,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004988787508855841,
|
|
"loss": 5.6474,
|
|
"mean_token_accuracy": 0.14970360174775124,
|
|
"num_tokens": 8777047.0,
|
|
"step": 5055
|
|
},
|
|
{
|
|
"entropy": 5.625737905502319,
|
|
"epoch": 0.39369772417817545,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004988759857018253,
|
|
"loss": 5.5216,
|
|
"mean_token_accuracy": 0.15340084880590438,
|
|
"num_tokens": 8785918.0,
|
|
"step": 5060
|
|
},
|
|
{
|
|
"entropy": 5.632894802093506,
|
|
"epoch": 0.39408675354989303,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004988732171211048,
|
|
"loss": 5.6229,
|
|
"mean_token_accuracy": 0.14756991118192672,
|
|
"num_tokens": 8794253.0,
|
|
"step": 5065
|
|
},
|
|
{
|
|
"entropy": 5.746179866790771,
|
|
"epoch": 0.39447578292161056,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004988704451434644,
|
|
"loss": 5.6565,
|
|
"mean_token_accuracy": 0.1576842710375786,
|
|
"num_tokens": 8802352.0,
|
|
"step": 5070
|
|
},
|
|
{
|
|
"entropy": 5.767830085754395,
|
|
"epoch": 0.39486481229332815,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004988676697689465,
|
|
"loss": 5.621,
|
|
"mean_token_accuracy": 0.151576666533947,
|
|
"num_tokens": 8810956.0,
|
|
"step": 5075
|
|
},
|
|
{
|
|
"entropy": 5.624795770645141,
|
|
"epoch": 0.39525384166504574,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.000498864890997593,
|
|
"loss": 5.5581,
|
|
"mean_token_accuracy": 0.15553110241889953,
|
|
"num_tokens": 8819062.0,
|
|
"step": 5080
|
|
},
|
|
{
|
|
"entropy": 5.646152591705322,
|
|
"epoch": 0.39564287103676327,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004988621088294461,
|
|
"loss": 5.6539,
|
|
"mean_token_accuracy": 0.1493374839425087,
|
|
"num_tokens": 8827470.0,
|
|
"step": 5085
|
|
},
|
|
{
|
|
"entropy": 5.708134746551513,
|
|
"epoch": 0.39603190040848085,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.000498859323264548,
|
|
"loss": 5.6725,
|
|
"mean_token_accuracy": 0.14790750443935394,
|
|
"num_tokens": 8837003.0,
|
|
"step": 5090
|
|
},
|
|
{
|
|
"entropy": 5.7410211086273195,
|
|
"epoch": 0.3964209297801984,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.000498856534302941,
|
|
"loss": 5.6732,
|
|
"mean_token_accuracy": 0.1470965027809143,
|
|
"num_tokens": 8846605.0,
|
|
"step": 5095
|
|
},
|
|
{
|
|
"entropy": 5.743842220306396,
|
|
"epoch": 0.39680995915191597,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004988537419446673,
|
|
"loss": 5.7112,
|
|
"mean_token_accuracy": 0.1480950817465782,
|
|
"num_tokens": 8855232.0,
|
|
"step": 5100
|
|
},
|
|
{
|
|
"entropy": 5.761359596252442,
|
|
"epoch": 0.39719898852363356,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004988509461897694,
|
|
"loss": 5.6011,
|
|
"mean_token_accuracy": 0.1598680794239044,
|
|
"num_tokens": 8864176.0,
|
|
"step": 5105
|
|
},
|
|
{
|
|
"entropy": 5.7343761920928955,
|
|
"epoch": 0.3975880178953511,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004988481470382897,
|
|
"loss": 5.6728,
|
|
"mean_token_accuracy": 0.1582700490951538,
|
|
"num_tokens": 8872671.0,
|
|
"step": 5110
|
|
},
|
|
{
|
|
"entropy": 5.5497277736663815,
|
|
"epoch": 0.3979770472670687,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004988453444902708,
|
|
"loss": 5.5766,
|
|
"mean_token_accuracy": 0.15400554835796357,
|
|
"num_tokens": 8881316.0,
|
|
"step": 5115
|
|
},
|
|
{
|
|
"entropy": 5.764847993850708,
|
|
"epoch": 0.3983660766387862,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004988425385457549,
|
|
"loss": 5.7077,
|
|
"mean_token_accuracy": 0.1536114804446697,
|
|
"num_tokens": 8890114.0,
|
|
"step": 5120
|
|
},
|
|
{
|
|
"entropy": 5.713496255874634,
|
|
"epoch": 0.3987551060105038,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.0004988397292047848,
|
|
"loss": 5.615,
|
|
"mean_token_accuracy": 0.16225254833698272,
|
|
"num_tokens": 8899598.0,
|
|
"step": 5125
|
|
},
|
|
{
|
|
"entropy": 5.534601783752441,
|
|
"epoch": 0.3991441353822214,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004988369164674032,
|
|
"loss": 5.4969,
|
|
"mean_token_accuracy": 0.15686479806900025,
|
|
"num_tokens": 8908244.0,
|
|
"step": 5130
|
|
},
|
|
{
|
|
"entropy": 5.720940351486206,
|
|
"epoch": 0.3995331647539389,
|
|
"grad_norm": 1.9921875,
|
|
"learning_rate": 0.0004988341003336526,
|
|
"loss": 5.5418,
|
|
"mean_token_accuracy": 0.1534431904554367,
|
|
"num_tokens": 8916280.0,
|
|
"step": 5135
|
|
},
|
|
{
|
|
"entropy": 5.7164599895477295,
|
|
"epoch": 0.3999221941256565,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004988312808035757,
|
|
"loss": 5.5819,
|
|
"mean_token_accuracy": 0.15383855104446412,
|
|
"num_tokens": 8923947.0,
|
|
"step": 5140
|
|
},
|
|
{
|
|
"entropy": 5.585909128189087,
|
|
"epoch": 0.400311223497374,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004988284578772155,
|
|
"loss": 5.6366,
|
|
"mean_token_accuracy": 0.14846336841583252,
|
|
"num_tokens": 8933374.0,
|
|
"step": 5145
|
|
},
|
|
{
|
|
"entropy": 5.666031980514527,
|
|
"epoch": 0.4007002528690916,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004988256315546146,
|
|
"loss": 5.5524,
|
|
"mean_token_accuracy": 0.15621831119060517,
|
|
"num_tokens": 8941757.0,
|
|
"step": 5150
|
|
},
|
|
{
|
|
"entropy": 5.637358474731445,
|
|
"epoch": 0.4010892822408092,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004988228018358161,
|
|
"loss": 5.4634,
|
|
"mean_token_accuracy": 0.15753690749406815,
|
|
"num_tokens": 8950128.0,
|
|
"step": 5155
|
|
},
|
|
{
|
|
"entropy": 5.669348335266113,
|
|
"epoch": 0.40147831161252673,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004988199687208628,
|
|
"loss": 5.6254,
|
|
"mean_token_accuracy": 0.15137961506843567,
|
|
"num_tokens": 8958939.0,
|
|
"step": 5160
|
|
},
|
|
{
|
|
"entropy": 5.726896333694458,
|
|
"epoch": 0.4018673409842443,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004988171322097977,
|
|
"loss": 5.5864,
|
|
"mean_token_accuracy": 0.15410467535257338,
|
|
"num_tokens": 8967519.0,
|
|
"step": 5165
|
|
},
|
|
{
|
|
"entropy": 5.581399202346802,
|
|
"epoch": 0.4022563703559619,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004988142923026638,
|
|
"loss": 5.4531,
|
|
"mean_token_accuracy": 0.16463563144207,
|
|
"num_tokens": 8976215.0,
|
|
"step": 5170
|
|
},
|
|
{
|
|
"entropy": 5.6362786293029785,
|
|
"epoch": 0.40264539972767943,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004988114489995044,
|
|
"loss": 5.6771,
|
|
"mean_token_accuracy": 0.14953848719596863,
|
|
"num_tokens": 8984060.0,
|
|
"step": 5175
|
|
},
|
|
{
|
|
"entropy": 5.668490648269653,
|
|
"epoch": 0.403034429099397,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004988086023003624,
|
|
"loss": 5.6158,
|
|
"mean_token_accuracy": 0.15242444425821305,
|
|
"num_tokens": 8992301.0,
|
|
"step": 5180
|
|
},
|
|
{
|
|
"entropy": 5.772063255310059,
|
|
"epoch": 0.40342345847111455,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004988057522052811,
|
|
"loss": 5.6508,
|
|
"mean_token_accuracy": 0.1539979301393032,
|
|
"num_tokens": 9000517.0,
|
|
"step": 5185
|
|
},
|
|
{
|
|
"entropy": 5.649879312515258,
|
|
"epoch": 0.40381248784283214,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004988028987143037,
|
|
"loss": 5.5998,
|
|
"mean_token_accuracy": 0.1542803391814232,
|
|
"num_tokens": 9008826.0,
|
|
"step": 5190
|
|
},
|
|
{
|
|
"entropy": 5.694010400772095,
|
|
"epoch": 0.4042015172145497,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004988000418274736,
|
|
"loss": 5.5911,
|
|
"mean_token_accuracy": 0.14661916792392732,
|
|
"num_tokens": 9017952.0,
|
|
"step": 5195
|
|
},
|
|
{
|
|
"entropy": 5.6865051746368405,
|
|
"epoch": 0.40459054658626725,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.0004987971815448341,
|
|
"loss": 5.5957,
|
|
"mean_token_accuracy": 0.16185417920351028,
|
|
"num_tokens": 9026688.0,
|
|
"step": 5200
|
|
},
|
|
{
|
|
"entropy": 5.608153390884399,
|
|
"epoch": 0.40497957595798484,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004987943178664285,
|
|
"loss": 5.5667,
|
|
"mean_token_accuracy": 0.15899718478322028,
|
|
"num_tokens": 9035761.0,
|
|
"step": 5205
|
|
},
|
|
{
|
|
"entropy": 5.688658380508423,
|
|
"epoch": 0.40536860532970237,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004987914507923004,
|
|
"loss": 5.6834,
|
|
"mean_token_accuracy": 0.14655253812670707,
|
|
"num_tokens": 9044510.0,
|
|
"step": 5210
|
|
},
|
|
{
|
|
"entropy": 5.66621994972229,
|
|
"epoch": 0.40575763470141996,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004987885803224931,
|
|
"loss": 5.555,
|
|
"mean_token_accuracy": 0.1531756892800331,
|
|
"num_tokens": 9053031.0,
|
|
"step": 5215
|
|
},
|
|
{
|
|
"entropy": 5.600265884399414,
|
|
"epoch": 0.40614666407313754,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004987857064570505,
|
|
"loss": 5.5263,
|
|
"mean_token_accuracy": 0.15929925590753555,
|
|
"num_tokens": 9061580.0,
|
|
"step": 5220
|
|
},
|
|
{
|
|
"entropy": 5.708470964431763,
|
|
"epoch": 0.4065356934448551,
|
|
"grad_norm": 2.4375,
|
|
"learning_rate": 0.0004987828291960158,
|
|
"loss": 5.6472,
|
|
"mean_token_accuracy": 0.15523430109024047,
|
|
"num_tokens": 9069741.0,
|
|
"step": 5225
|
|
},
|
|
{
|
|
"entropy": 5.787652397155762,
|
|
"epoch": 0.40692472281657266,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.000498779948539433,
|
|
"loss": 5.6794,
|
|
"mean_token_accuracy": 0.14232235848903657,
|
|
"num_tokens": 9079214.0,
|
|
"step": 5230
|
|
},
|
|
{
|
|
"entropy": 5.717964124679566,
|
|
"epoch": 0.4073137521882902,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004987770644873455,
|
|
"loss": 5.6351,
|
|
"mean_token_accuracy": 0.15510015487670897,
|
|
"num_tokens": 9088201.0,
|
|
"step": 5235
|
|
},
|
|
{
|
|
"entropy": 5.682655620574951,
|
|
"epoch": 0.4077027815600078,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004987741770397974,
|
|
"loss": 5.6552,
|
|
"mean_token_accuracy": 0.1491895794868469,
|
|
"num_tokens": 9096829.0,
|
|
"step": 5240
|
|
},
|
|
{
|
|
"entropy": 5.72006139755249,
|
|
"epoch": 0.40809181093172536,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004987712861968323,
|
|
"loss": 5.6303,
|
|
"mean_token_accuracy": 0.15172734037041663,
|
|
"num_tokens": 9105515.0,
|
|
"step": 5245
|
|
},
|
|
{
|
|
"entropy": 5.7496589660644535,
|
|
"epoch": 0.4084808403034429,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.000498768391958494,
|
|
"loss": 5.5921,
|
|
"mean_token_accuracy": 0.1561399593949318,
|
|
"num_tokens": 9113614.0,
|
|
"step": 5250
|
|
},
|
|
{
|
|
"entropy": 5.703589248657226,
|
|
"epoch": 0.4088698696751605,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004987654943248266,
|
|
"loss": 5.6687,
|
|
"mean_token_accuracy": 0.14717486798763274,
|
|
"num_tokens": 9122337.0,
|
|
"step": 5255
|
|
},
|
|
{
|
|
"entropy": 5.69605655670166,
|
|
"epoch": 0.40925889904687807,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004987625932958739,
|
|
"loss": 5.5582,
|
|
"mean_token_accuracy": 0.1577390491962433,
|
|
"num_tokens": 9130417.0,
|
|
"step": 5260
|
|
},
|
|
{
|
|
"entropy": 5.713752317428589,
|
|
"epoch": 0.4096479284185956,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004987596888716801,
|
|
"loss": 5.6418,
|
|
"mean_token_accuracy": 0.15083522349596024,
|
|
"num_tokens": 9139317.0,
|
|
"step": 5265
|
|
},
|
|
{
|
|
"entropy": 5.681883144378662,
|
|
"epoch": 0.4100369577903132,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004987567810522892,
|
|
"loss": 5.6121,
|
|
"mean_token_accuracy": 0.1543550096452236,
|
|
"num_tokens": 9147808.0,
|
|
"step": 5270
|
|
},
|
|
{
|
|
"entropy": 5.7918376445770265,
|
|
"epoch": 0.4104259871620307,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004987538698377451,
|
|
"loss": 5.7206,
|
|
"mean_token_accuracy": 0.1443312905728817,
|
|
"num_tokens": 9157117.0,
|
|
"step": 5275
|
|
},
|
|
{
|
|
"entropy": 5.725800943374634,
|
|
"epoch": 0.4108150165337483,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004987509552280924,
|
|
"loss": 5.5583,
|
|
"mean_token_accuracy": 0.15271155685186386,
|
|
"num_tokens": 9165297.0,
|
|
"step": 5280
|
|
},
|
|
{
|
|
"entropy": 5.716037034988403,
|
|
"epoch": 0.4112040459054659,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.000498748037223375,
|
|
"loss": 5.7045,
|
|
"mean_token_accuracy": 0.15257550179958343,
|
|
"num_tokens": 9172945.0,
|
|
"step": 5285
|
|
},
|
|
{
|
|
"entropy": 5.727522563934326,
|
|
"epoch": 0.4115930752771834,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004987451158236372,
|
|
"loss": 5.6202,
|
|
"mean_token_accuracy": 0.1598150685429573,
|
|
"num_tokens": 9181445.0,
|
|
"step": 5290
|
|
},
|
|
{
|
|
"entropy": 5.610752868652344,
|
|
"epoch": 0.411982104648901,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004987421910289234,
|
|
"loss": 5.465,
|
|
"mean_token_accuracy": 0.1573048248887062,
|
|
"num_tokens": 9189535.0,
|
|
"step": 5295
|
|
},
|
|
{
|
|
"entropy": 5.629565954208374,
|
|
"epoch": 0.41237113402061853,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004987392628392781,
|
|
"loss": 5.6652,
|
|
"mean_token_accuracy": 0.15188628435134888,
|
|
"num_tokens": 9198328.0,
|
|
"step": 5300
|
|
},
|
|
{
|
|
"entropy": 5.688240051269531,
|
|
"epoch": 0.4127601633923361,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004987363312547456,
|
|
"loss": 5.576,
|
|
"mean_token_accuracy": 0.1569174513220787,
|
|
"num_tokens": 9206840.0,
|
|
"step": 5305
|
|
},
|
|
{
|
|
"entropy": 5.673935890197754,
|
|
"epoch": 0.4131491927640537,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004987333962753703,
|
|
"loss": 5.4883,
|
|
"mean_token_accuracy": 0.15501619651913642,
|
|
"num_tokens": 9215155.0,
|
|
"step": 5310
|
|
},
|
|
{
|
|
"entropy": 5.673168325424195,
|
|
"epoch": 0.41353822213577124,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004987304579011967,
|
|
"loss": 5.664,
|
|
"mean_token_accuracy": 0.15122487396001816,
|
|
"num_tokens": 9224426.0,
|
|
"step": 5315
|
|
},
|
|
{
|
|
"entropy": 5.729065608978272,
|
|
"epoch": 0.4139272515074888,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004987275161322697,
|
|
"loss": 5.6773,
|
|
"mean_token_accuracy": 0.1495743751525879,
|
|
"num_tokens": 9233785.0,
|
|
"step": 5320
|
|
},
|
|
{
|
|
"entropy": 5.730423545837402,
|
|
"epoch": 0.41431628087920636,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004987245709686337,
|
|
"loss": 5.6254,
|
|
"mean_token_accuracy": 0.1559661418199539,
|
|
"num_tokens": 9242168.0,
|
|
"step": 5325
|
|
},
|
|
{
|
|
"entropy": 5.676369905471802,
|
|
"epoch": 0.41470531025092394,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004987216224103334,
|
|
"loss": 5.6476,
|
|
"mean_token_accuracy": 0.15575910955667496,
|
|
"num_tokens": 9250862.0,
|
|
"step": 5330
|
|
},
|
|
{
|
|
"entropy": 5.642132043838501,
|
|
"epoch": 0.41509433962264153,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004987186704574136,
|
|
"loss": 5.67,
|
|
"mean_token_accuracy": 0.14981329441070557,
|
|
"num_tokens": 9259957.0,
|
|
"step": 5335
|
|
},
|
|
{
|
|
"entropy": 5.621898508071899,
|
|
"epoch": 0.41548336899435906,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004987157151099189,
|
|
"loss": 5.5336,
|
|
"mean_token_accuracy": 0.15282652229070665,
|
|
"num_tokens": 9268590.0,
|
|
"step": 5340
|
|
},
|
|
{
|
|
"entropy": 5.765911483764649,
|
|
"epoch": 0.41587239836607665,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004987127563678945,
|
|
"loss": 5.591,
|
|
"mean_token_accuracy": 0.15727531164884567,
|
|
"num_tokens": 9276872.0,
|
|
"step": 5345
|
|
},
|
|
{
|
|
"entropy": 5.629314422607422,
|
|
"epoch": 0.4162614277377942,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004987097942313852,
|
|
"loss": 5.498,
|
|
"mean_token_accuracy": 0.15631380677223206,
|
|
"num_tokens": 9284556.0,
|
|
"step": 5350
|
|
},
|
|
{
|
|
"entropy": 5.607842302322387,
|
|
"epoch": 0.41665045710951176,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004987068287004355,
|
|
"loss": 5.6369,
|
|
"mean_token_accuracy": 0.15501972585916518,
|
|
"num_tokens": 9293315.0,
|
|
"step": 5355
|
|
},
|
|
{
|
|
"entropy": 5.767564725875855,
|
|
"epoch": 0.41703948648122935,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004987038597750909,
|
|
"loss": 5.6026,
|
|
"mean_token_accuracy": 0.15421222746372223,
|
|
"num_tokens": 9302923.0,
|
|
"step": 5360
|
|
},
|
|
{
|
|
"entropy": 5.713073825836181,
|
|
"epoch": 0.4174285158529469,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004987008874553964,
|
|
"loss": 5.55,
|
|
"mean_token_accuracy": 0.15480501800775529,
|
|
"num_tokens": 9311388.0,
|
|
"step": 5365
|
|
},
|
|
{
|
|
"entropy": 5.581174850463867,
|
|
"epoch": 0.41781754522466447,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004986979117413969,
|
|
"loss": 5.5188,
|
|
"mean_token_accuracy": 0.15659940093755723,
|
|
"num_tokens": 9319880.0,
|
|
"step": 5370
|
|
},
|
|
{
|
|
"entropy": 5.625206518173218,
|
|
"epoch": 0.41820657459638205,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004986949326331376,
|
|
"loss": 5.6364,
|
|
"mean_token_accuracy": 0.15710621625185012,
|
|
"num_tokens": 9328374.0,
|
|
"step": 5375
|
|
},
|
|
{
|
|
"entropy": 5.841898488998413,
|
|
"epoch": 0.4185956039680996,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004986919501306638,
|
|
"loss": 5.5993,
|
|
"mean_token_accuracy": 0.16092789843678473,
|
|
"num_tokens": 9336428.0,
|
|
"step": 5380
|
|
},
|
|
{
|
|
"entropy": 5.608292770385742,
|
|
"epoch": 0.41898463333981717,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004986889642340207,
|
|
"loss": 5.691,
|
|
"mean_token_accuracy": 0.15082264617085456,
|
|
"num_tokens": 9345794.0,
|
|
"step": 5385
|
|
},
|
|
{
|
|
"entropy": 5.735980892181397,
|
|
"epoch": 0.4193736627115347,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004986859749432536,
|
|
"loss": 5.6508,
|
|
"mean_token_accuracy": 0.15251213908195496,
|
|
"num_tokens": 9354724.0,
|
|
"step": 5390
|
|
},
|
|
{
|
|
"entropy": 5.766054344177246,
|
|
"epoch": 0.4197626920832523,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004986829822584078,
|
|
"loss": 5.6605,
|
|
"mean_token_accuracy": 0.14837022870779037,
|
|
"num_tokens": 9364008.0,
|
|
"step": 5395
|
|
},
|
|
{
|
|
"entropy": 5.706441450119018,
|
|
"epoch": 0.4201517214549699,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.0004986799861795289,
|
|
"loss": 5.6169,
|
|
"mean_token_accuracy": 0.16091901808977127,
|
|
"num_tokens": 9372409.0,
|
|
"step": 5400
|
|
},
|
|
{
|
|
"entropy": 5.632897090911865,
|
|
"epoch": 0.4205407508266874,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004986769867066622,
|
|
"loss": 5.5696,
|
|
"mean_token_accuracy": 0.15019408240914345,
|
|
"num_tokens": 9381172.0,
|
|
"step": 5405
|
|
},
|
|
{
|
|
"entropy": 5.699292421340942,
|
|
"epoch": 0.420929780198405,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004986739838398532,
|
|
"loss": 5.5931,
|
|
"mean_token_accuracy": 0.15890666395425795,
|
|
"num_tokens": 9389245.0,
|
|
"step": 5410
|
|
},
|
|
{
|
|
"entropy": 5.669768238067627,
|
|
"epoch": 0.4213188095701225,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004986709775791475,
|
|
"loss": 5.6361,
|
|
"mean_token_accuracy": 0.1545052334666252,
|
|
"num_tokens": 9397954.0,
|
|
"step": 5415
|
|
},
|
|
{
|
|
"entropy": 5.686574935913086,
|
|
"epoch": 0.4217078389418401,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004986679679245907,
|
|
"loss": 5.7068,
|
|
"mean_token_accuracy": 0.15322575643658637,
|
|
"num_tokens": 9406986.0,
|
|
"step": 5420
|
|
},
|
|
{
|
|
"entropy": 5.694334697723389,
|
|
"epoch": 0.4220968683135577,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004986649548762286,
|
|
"loss": 5.6744,
|
|
"mean_token_accuracy": 0.15553520172834395,
|
|
"num_tokens": 9415163.0,
|
|
"step": 5425
|
|
},
|
|
{
|
|
"entropy": 5.6281413555145265,
|
|
"epoch": 0.4224858976852752,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004986619384341066,
|
|
"loss": 5.5039,
|
|
"mean_token_accuracy": 0.16974841058254242,
|
|
"num_tokens": 9423422.0,
|
|
"step": 5430
|
|
},
|
|
{
|
|
"entropy": 5.616047143936157,
|
|
"epoch": 0.4228749270569928,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004986589185982708,
|
|
"loss": 5.5299,
|
|
"mean_token_accuracy": 0.16799319237470628,
|
|
"num_tokens": 9431349.0,
|
|
"step": 5435
|
|
},
|
|
{
|
|
"entropy": 5.6762138366699215,
|
|
"epoch": 0.42326395642871034,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004986558953687671,
|
|
"loss": 5.6327,
|
|
"mean_token_accuracy": 0.15191021859645842,
|
|
"num_tokens": 9439715.0,
|
|
"step": 5440
|
|
},
|
|
{
|
|
"entropy": 5.70176420211792,
|
|
"epoch": 0.42365298580042793,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.0004986528687456409,
|
|
"loss": 5.6345,
|
|
"mean_token_accuracy": 0.1586211621761322,
|
|
"num_tokens": 9448216.0,
|
|
"step": 5445
|
|
},
|
|
{
|
|
"entropy": 5.690141868591309,
|
|
"epoch": 0.4240420151721455,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004986498387289384,
|
|
"loss": 5.5688,
|
|
"mean_token_accuracy": 0.1581912711262703,
|
|
"num_tokens": 9456346.0,
|
|
"step": 5450
|
|
},
|
|
{
|
|
"entropy": 5.701142740249634,
|
|
"epoch": 0.42443104454386305,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004986468053187058,
|
|
"loss": 5.6661,
|
|
"mean_token_accuracy": 0.15444247871637345,
|
|
"num_tokens": 9465476.0,
|
|
"step": 5455
|
|
},
|
|
{
|
|
"entropy": 5.754557275772095,
|
|
"epoch": 0.42482007391558063,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004986437685149887,
|
|
"loss": 5.7045,
|
|
"mean_token_accuracy": 0.1523694947361946,
|
|
"num_tokens": 9474582.0,
|
|
"step": 5460
|
|
},
|
|
{
|
|
"entropy": 5.716640567779541,
|
|
"epoch": 0.4252091032872982,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004986407283178334,
|
|
"loss": 5.5774,
|
|
"mean_token_accuracy": 0.15223048627376556,
|
|
"num_tokens": 9482801.0,
|
|
"step": 5465
|
|
},
|
|
{
|
|
"entropy": 5.658149290084839,
|
|
"epoch": 0.42559813265901575,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004986376847272861,
|
|
"loss": 5.6035,
|
|
"mean_token_accuracy": 0.1587924137711525,
|
|
"num_tokens": 9490894.0,
|
|
"step": 5470
|
|
},
|
|
{
|
|
"entropy": 5.631808567047119,
|
|
"epoch": 0.42598716203073334,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004986346377433929,
|
|
"loss": 5.5854,
|
|
"mean_token_accuracy": 0.15215555876493453,
|
|
"num_tokens": 9499414.0,
|
|
"step": 5475
|
|
},
|
|
{
|
|
"entropy": 5.610310506820679,
|
|
"epoch": 0.42637619140245087,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004986315873661999,
|
|
"loss": 5.5424,
|
|
"mean_token_accuracy": 0.15248426645994187,
|
|
"num_tokens": 9508945.0,
|
|
"step": 5480
|
|
},
|
|
{
|
|
"entropy": 5.682540321350098,
|
|
"epoch": 0.42676522077416845,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004986285335957536,
|
|
"loss": 5.6202,
|
|
"mean_token_accuracy": 0.1547765851020813,
|
|
"num_tokens": 9517833.0,
|
|
"step": 5485
|
|
},
|
|
{
|
|
"entropy": 5.763080024719239,
|
|
"epoch": 0.42715425014588604,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004986254764321002,
|
|
"loss": 5.7587,
|
|
"mean_token_accuracy": 0.1462617114186287,
|
|
"num_tokens": 9526551.0,
|
|
"step": 5490
|
|
},
|
|
{
|
|
"entropy": 5.692221546173096,
|
|
"epoch": 0.42754327951760357,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.0004986224158752861,
|
|
"loss": 5.5271,
|
|
"mean_token_accuracy": 0.15631710290908812,
|
|
"num_tokens": 9535224.0,
|
|
"step": 5495
|
|
},
|
|
{
|
|
"entropy": 5.70320725440979,
|
|
"epoch": 0.42793230888932116,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004986193519253578,
|
|
"loss": 5.6263,
|
|
"mean_token_accuracy": 0.14933848679065703,
|
|
"num_tokens": 9544466.0,
|
|
"step": 5500
|
|
},
|
|
{
|
|
"entropy": 5.652177000045777,
|
|
"epoch": 0.4283213382610387,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004986162845823618,
|
|
"loss": 5.6334,
|
|
"mean_token_accuracy": 0.15253791362047195,
|
|
"num_tokens": 9553520.0,
|
|
"step": 5505
|
|
},
|
|
{
|
|
"entropy": 5.7178675651550295,
|
|
"epoch": 0.4287103676327563,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004986132138463446,
|
|
"loss": 5.5518,
|
|
"mean_token_accuracy": 0.15862294137477875,
|
|
"num_tokens": 9562053.0,
|
|
"step": 5510
|
|
},
|
|
{
|
|
"entropy": 5.663863658905029,
|
|
"epoch": 0.42909939700447386,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004986101397173528,
|
|
"loss": 5.5187,
|
|
"mean_token_accuracy": 0.16098337322473527,
|
|
"num_tokens": 9570632.0,
|
|
"step": 5515
|
|
},
|
|
{
|
|
"entropy": 5.6511577606201175,
|
|
"epoch": 0.4294884263761914,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.000498607062195433,
|
|
"loss": 5.5456,
|
|
"mean_token_accuracy": 0.15594051033258438,
|
|
"num_tokens": 9578739.0,
|
|
"step": 5520
|
|
},
|
|
{
|
|
"entropy": 5.590314817428589,
|
|
"epoch": 0.429877455747909,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.000498603981280632,
|
|
"loss": 5.5728,
|
|
"mean_token_accuracy": 0.15462178885936737,
|
|
"num_tokens": 9587314.0,
|
|
"step": 5525
|
|
},
|
|
{
|
|
"entropy": 5.7138384819030765,
|
|
"epoch": 0.4302664851196265,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004986008969729964,
|
|
"loss": 5.6425,
|
|
"mean_token_accuracy": 0.15185408741235734,
|
|
"num_tokens": 9595954.0,
|
|
"step": 5530
|
|
},
|
|
{
|
|
"entropy": 5.74177918434143,
|
|
"epoch": 0.4306555144913441,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004985978092725731,
|
|
"loss": 5.6405,
|
|
"mean_token_accuracy": 0.1507391259074211,
|
|
"num_tokens": 9604767.0,
|
|
"step": 5535
|
|
},
|
|
{
|
|
"entropy": 5.650885343551636,
|
|
"epoch": 0.4310445438630617,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.000498594718179409,
|
|
"loss": 5.5223,
|
|
"mean_token_accuracy": 0.15448743104934692,
|
|
"num_tokens": 9613173.0,
|
|
"step": 5540
|
|
},
|
|
{
|
|
"entropy": 5.715137147903443,
|
|
"epoch": 0.4314335732347792,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004985916236935508,
|
|
"loss": 5.6053,
|
|
"mean_token_accuracy": 0.153990425914526,
|
|
"num_tokens": 9622777.0,
|
|
"step": 5545
|
|
},
|
|
{
|
|
"entropy": 5.635022735595703,
|
|
"epoch": 0.4318226026064968,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004985885258150458,
|
|
"loss": 5.5388,
|
|
"mean_token_accuracy": 0.15460200384259223,
|
|
"num_tokens": 9631019.0,
|
|
"step": 5550
|
|
},
|
|
{
|
|
"entropy": 5.683343029022216,
|
|
"epoch": 0.43221163197821433,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004985854245439408,
|
|
"loss": 5.6136,
|
|
"mean_token_accuracy": 0.1511878952383995,
|
|
"num_tokens": 9639797.0,
|
|
"step": 5555
|
|
},
|
|
{
|
|
"entropy": 5.661354446411133,
|
|
"epoch": 0.4326006613499319,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004985823198802827,
|
|
"loss": 5.595,
|
|
"mean_token_accuracy": 0.15743356198072433,
|
|
"num_tokens": 9648393.0,
|
|
"step": 5560
|
|
},
|
|
{
|
|
"entropy": 5.68243179321289,
|
|
"epoch": 0.4329896907216495,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.0004985792118241188,
|
|
"loss": 5.5772,
|
|
"mean_token_accuracy": 0.1587914675474167,
|
|
"num_tokens": 9657260.0,
|
|
"step": 5565
|
|
},
|
|
{
|
|
"entropy": 5.6807139873504635,
|
|
"epoch": 0.43337872009336703,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004985761003754961,
|
|
"loss": 5.6439,
|
|
"mean_token_accuracy": 0.1596544787287712,
|
|
"num_tokens": 9665883.0,
|
|
"step": 5570
|
|
},
|
|
{
|
|
"entropy": 5.718773937225341,
|
|
"epoch": 0.4337677494650846,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004985729855344622,
|
|
"loss": 5.6629,
|
|
"mean_token_accuracy": 0.159003321826458,
|
|
"num_tokens": 9674100.0,
|
|
"step": 5575
|
|
},
|
|
{
|
|
"entropy": 5.675301170349121,
|
|
"epoch": 0.4341567788368022,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.000498569867301064,
|
|
"loss": 5.643,
|
|
"mean_token_accuracy": 0.1527624897658825,
|
|
"num_tokens": 9683236.0,
|
|
"step": 5580
|
|
},
|
|
{
|
|
"entropy": 5.7263641357421875,
|
|
"epoch": 0.43454580820851973,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004985667456753489,
|
|
"loss": 5.6038,
|
|
"mean_token_accuracy": 0.1540868639945984,
|
|
"num_tokens": 9692076.0,
|
|
"step": 5585
|
|
},
|
|
{
|
|
"entropy": 5.749101829528809,
|
|
"epoch": 0.4349348375802373,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004985636206573642,
|
|
"loss": 5.6473,
|
|
"mean_token_accuracy": 0.1545097589492798,
|
|
"num_tokens": 9700266.0,
|
|
"step": 5590
|
|
},
|
|
{
|
|
"entropy": 5.63895468711853,
|
|
"epoch": 0.43532386695195485,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004985604922471575,
|
|
"loss": 5.5611,
|
|
"mean_token_accuracy": 0.1559956818819046,
|
|
"num_tokens": 9708643.0,
|
|
"step": 5595
|
|
},
|
|
{
|
|
"entropy": 5.696415281295776,
|
|
"epoch": 0.43571289632367244,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004985573604447761,
|
|
"loss": 5.6252,
|
|
"mean_token_accuracy": 0.15173855572938919,
|
|
"num_tokens": 9717459.0,
|
|
"step": 5600
|
|
},
|
|
{
|
|
"entropy": 5.713142585754395,
|
|
"epoch": 0.43610192569539,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004985542252502676,
|
|
"loss": 5.536,
|
|
"mean_token_accuracy": 0.16011471450328826,
|
|
"num_tokens": 9726251.0,
|
|
"step": 5605
|
|
},
|
|
{
|
|
"entropy": 5.546394634246826,
|
|
"epoch": 0.43649095506710756,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004985510866636796,
|
|
"loss": 5.529,
|
|
"mean_token_accuracy": 0.1569727137684822,
|
|
"num_tokens": 9735327.0,
|
|
"step": 5610
|
|
},
|
|
{
|
|
"entropy": 5.635249328613281,
|
|
"epoch": 0.43687998443882514,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004985479446850596,
|
|
"loss": 5.6969,
|
|
"mean_token_accuracy": 0.1478659600019455,
|
|
"num_tokens": 9743642.0,
|
|
"step": 5615
|
|
},
|
|
{
|
|
"entropy": 5.744920492172241,
|
|
"epoch": 0.4372690138105427,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004985447993144554,
|
|
"loss": 5.5534,
|
|
"mean_token_accuracy": 0.1610129863023758,
|
|
"num_tokens": 9752235.0,
|
|
"step": 5620
|
|
},
|
|
{
|
|
"entropy": 5.727913284301758,
|
|
"epoch": 0.43765804318226026,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004985416505519147,
|
|
"loss": 5.6485,
|
|
"mean_token_accuracy": 0.14669111520051956,
|
|
"num_tokens": 9761012.0,
|
|
"step": 5625
|
|
},
|
|
{
|
|
"entropy": 5.647424125671387,
|
|
"epoch": 0.43804707255397785,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004985384983974853,
|
|
"loss": 5.5906,
|
|
"mean_token_accuracy": 0.16118393540382386,
|
|
"num_tokens": 9769810.0,
|
|
"step": 5630
|
|
},
|
|
{
|
|
"entropy": 5.690002822875977,
|
|
"epoch": 0.4384361019256954,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004985353428512148,
|
|
"loss": 5.5313,
|
|
"mean_token_accuracy": 0.15689640045166015,
|
|
"num_tokens": 9778186.0,
|
|
"step": 5635
|
|
},
|
|
{
|
|
"entropy": 5.617481708526611,
|
|
"epoch": 0.43882513129741296,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004985321839131514,
|
|
"loss": 5.6102,
|
|
"mean_token_accuracy": 0.15669983327388765,
|
|
"num_tokens": 9786456.0,
|
|
"step": 5640
|
|
},
|
|
{
|
|
"entropy": 5.634613656997681,
|
|
"epoch": 0.4392141606691305,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004985290215833428,
|
|
"loss": 5.6179,
|
|
"mean_token_accuracy": 0.15137500166893006,
|
|
"num_tokens": 9794613.0,
|
|
"step": 5645
|
|
},
|
|
{
|
|
"entropy": 5.776523065567017,
|
|
"epoch": 0.4396031900408481,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004985258558618372,
|
|
"loss": 5.5407,
|
|
"mean_token_accuracy": 0.16228375136852263,
|
|
"num_tokens": 9803388.0,
|
|
"step": 5650
|
|
},
|
|
{
|
|
"entropy": 5.655756616592408,
|
|
"epoch": 0.43999221941256567,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004985226867486825,
|
|
"loss": 5.6093,
|
|
"mean_token_accuracy": 0.15270971208810807,
|
|
"num_tokens": 9812450.0,
|
|
"step": 5655
|
|
},
|
|
{
|
|
"entropy": 5.640044784545898,
|
|
"epoch": 0.4403812487842832,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004985195142439267,
|
|
"loss": 5.6843,
|
|
"mean_token_accuracy": 0.15173425972461702,
|
|
"num_tokens": 9821377.0,
|
|
"step": 5660
|
|
},
|
|
{
|
|
"entropy": 5.711916112899781,
|
|
"epoch": 0.4407702781560008,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004985163383476181,
|
|
"loss": 5.5903,
|
|
"mean_token_accuracy": 0.15132837891578674,
|
|
"num_tokens": 9829761.0,
|
|
"step": 5665
|
|
},
|
|
{
|
|
"entropy": 5.734554624557495,
|
|
"epoch": 0.44115930752771837,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004985131590598048,
|
|
"loss": 5.6712,
|
|
"mean_token_accuracy": 0.15261898189783096,
|
|
"num_tokens": 9838921.0,
|
|
"step": 5670
|
|
},
|
|
{
|
|
"entropy": 5.642977952957153,
|
|
"epoch": 0.4415483368994359,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.0004985099763805352,
|
|
"loss": 5.4959,
|
|
"mean_token_accuracy": 0.16712506413459777,
|
|
"num_tokens": 9846822.0,
|
|
"step": 5675
|
|
},
|
|
{
|
|
"entropy": 5.732327270507812,
|
|
"epoch": 0.4419373662711535,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 0.0004985067903098574,
|
|
"loss": 5.715,
|
|
"mean_token_accuracy": 0.15435596704483032,
|
|
"num_tokens": 9855951.0,
|
|
"step": 5680
|
|
},
|
|
{
|
|
"entropy": 5.722942876815796,
|
|
"epoch": 0.442326395642871,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004985036008478197,
|
|
"loss": 5.6521,
|
|
"mean_token_accuracy": 0.15621139109134674,
|
|
"num_tokens": 9864875.0,
|
|
"step": 5685
|
|
},
|
|
{
|
|
"entropy": 5.720158243179322,
|
|
"epoch": 0.4427154250145886,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.0004985004079944707,
|
|
"loss": 5.6296,
|
|
"mean_token_accuracy": 0.15742181092500687,
|
|
"num_tokens": 9873785.0,
|
|
"step": 5690
|
|
},
|
|
{
|
|
"entropy": 5.6961874008178714,
|
|
"epoch": 0.4431044543863062,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0004984972117498587,
|
|
"loss": 5.6008,
|
|
"mean_token_accuracy": 0.15231376364827157,
|
|
"num_tokens": 9883214.0,
|
|
"step": 5695
|
|
},
|
|
{
|
|
"entropy": 5.6411467552185055,
|
|
"epoch": 0.4434934837580237,
|
|
"grad_norm": 1.8515625,
|
|
"learning_rate": 0.0004984940121140323,
|
|
"loss": 5.5908,
|
|
"mean_token_accuracy": 0.15693965703248977,
|
|
"num_tokens": 9891346.0,
|
|
"step": 5700
|
|
},
|
|
{
|
|
"entropy": 5.599026918411255,
|
|
"epoch": 0.4438825131297413,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.00049849080908704,
|
|
"loss": 5.512,
|
|
"mean_token_accuracy": 0.15608782470226287,
|
|
"num_tokens": 9900646.0,
|
|
"step": 5705
|
|
},
|
|
{
|
|
"entropy": 5.760201930999756,
|
|
"epoch": 0.44427154250145884,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004984876026689302,
|
|
"loss": 5.6736,
|
|
"mean_token_accuracy": 0.15531087070703506,
|
|
"num_tokens": 9910851.0,
|
|
"step": 5710
|
|
},
|
|
{
|
|
"entropy": 5.741092729568481,
|
|
"epoch": 0.4446605718731764,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.000498484392859752,
|
|
"loss": 5.6805,
|
|
"mean_token_accuracy": 0.15023813992738724,
|
|
"num_tokens": 9919919.0,
|
|
"step": 5715
|
|
},
|
|
{
|
|
"entropy": 5.736074161529541,
|
|
"epoch": 0.445049601244894,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004984811796595538,
|
|
"loss": 5.5998,
|
|
"mean_token_accuracy": 0.1526205599308014,
|
|
"num_tokens": 9928831.0,
|
|
"step": 5720
|
|
},
|
|
{
|
|
"entropy": 5.626043033599854,
|
|
"epoch": 0.44543863061661154,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004984779630683843,
|
|
"loss": 5.5426,
|
|
"mean_token_accuracy": 0.16297227293252944,
|
|
"num_tokens": 9936840.0,
|
|
"step": 5725
|
|
},
|
|
{
|
|
"entropy": 5.6324889183044435,
|
|
"epoch": 0.44582765998832913,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004984747430862924,
|
|
"loss": 5.63,
|
|
"mean_token_accuracy": 0.1549576573073864,
|
|
"num_tokens": 9945845.0,
|
|
"step": 5730
|
|
},
|
|
{
|
|
"entropy": 5.711879062652588,
|
|
"epoch": 0.44621668936004666,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004984715197133271,
|
|
"loss": 5.6424,
|
|
"mean_token_accuracy": 0.1565379649400711,
|
|
"num_tokens": 9955176.0,
|
|
"step": 5735
|
|
},
|
|
{
|
|
"entropy": 5.692287302017212,
|
|
"epoch": 0.44660571873176425,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004984682929495371,
|
|
"loss": 5.505,
|
|
"mean_token_accuracy": 0.16135647743940354,
|
|
"num_tokens": 9963182.0,
|
|
"step": 5740
|
|
},
|
|
{
|
|
"entropy": 5.623046445846557,
|
|
"epoch": 0.44699474810348183,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.0004984650627949715,
|
|
"loss": 5.6566,
|
|
"mean_token_accuracy": 0.1496202103793621,
|
|
"num_tokens": 9971239.0,
|
|
"step": 5745
|
|
},
|
|
{
|
|
"entropy": 5.651198291778565,
|
|
"epoch": 0.44738377747519936,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004984618292496792,
|
|
"loss": 5.6122,
|
|
"mean_token_accuracy": 0.15542484670877457,
|
|
"num_tokens": 9980285.0,
|
|
"step": 5750
|
|
},
|
|
{
|
|
"entropy": 5.771606063842773,
|
|
"epoch": 0.44777280684691695,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004984585923137093,
|
|
"loss": 5.6111,
|
|
"mean_token_accuracy": 0.1551290050148964,
|
|
"num_tokens": 9988922.0,
|
|
"step": 5755
|
|
},
|
|
{
|
|
"entropy": 5.7198814868927,
|
|
"epoch": 0.4481618362186345,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.000498455351987111,
|
|
"loss": 5.6919,
|
|
"mean_token_accuracy": 0.14821690917015076,
|
|
"num_tokens": 9998538.0,
|
|
"step": 5760
|
|
},
|
|
{
|
|
"entropy": 5.769218492507934,
|
|
"epoch": 0.44855086559035207,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.0004984521082699333,
|
|
"loss": 5.5963,
|
|
"mean_token_accuracy": 0.15861361473798752,
|
|
"num_tokens": 10006646.0,
|
|
"step": 5765
|
|
},
|
|
{
|
|
"entropy": 5.67115592956543,
|
|
"epoch": 0.44893989496206965,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004984488611622256,
|
|
"loss": 5.599,
|
|
"mean_token_accuracy": 0.1557679831981659,
|
|
"num_tokens": 10016511.0,
|
|
"step": 5770
|
|
},
|
|
{
|
|
"entropy": 5.605710554122925,
|
|
"epoch": 0.4493289243337872,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.000498445610664037,
|
|
"loss": 5.4922,
|
|
"mean_token_accuracy": 0.15822974145412444,
|
|
"num_tokens": 10025223.0,
|
|
"step": 5775
|
|
},
|
|
{
|
|
"entropy": 5.643562269210816,
|
|
"epoch": 0.44971795370550477,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.000498442356775417,
|
|
"loss": 5.5864,
|
|
"mean_token_accuracy": 0.15544288456439972,
|
|
"num_tokens": 10033678.0,
|
|
"step": 5780
|
|
},
|
|
{
|
|
"entropy": 5.660170698165894,
|
|
"epoch": 0.45010698307722236,
|
|
"grad_norm": 1.875,
|
|
"learning_rate": 0.0004984390994964148,
|
|
"loss": 5.4978,
|
|
"mean_token_accuracy": 0.15725428760051727,
|
|
"num_tokens": 10042028.0,
|
|
"step": 5785
|
|
},
|
|
{
|
|
"entropy": 5.649860429763794,
|
|
"epoch": 0.4504960124489399,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.00049843583882708,
|
|
"loss": 5.685,
|
|
"mean_token_accuracy": 0.14959444254636764,
|
|
"num_tokens": 10050758.0,
|
|
"step": 5790
|
|
},
|
|
{
|
|
"entropy": 5.629285097122192,
|
|
"epoch": 0.4508850418206575,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.000498432574767462,
|
|
"loss": 5.4397,
|
|
"mean_token_accuracy": 0.16886657178401948,
|
|
"num_tokens": 10058688.0,
|
|
"step": 5795
|
|
},
|
|
{
|
|
"entropy": 5.657595205307007,
|
|
"epoch": 0.451274071192375,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004984293073176103,
|
|
"loss": 5.5341,
|
|
"mean_token_accuracy": 0.16321758031845093,
|
|
"num_tokens": 10067302.0,
|
|
"step": 5800
|
|
},
|
|
{
|
|
"entropy": 5.606902170181274,
|
|
"epoch": 0.4516631005640926,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004984260364775744,
|
|
"loss": 5.5356,
|
|
"mean_token_accuracy": 0.15514699518680572,
|
|
"num_tokens": 10076424.0,
|
|
"step": 5805
|
|
},
|
|
{
|
|
"entropy": 5.687009668350219,
|
|
"epoch": 0.4520521299358102,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.000498422762247404,
|
|
"loss": 5.659,
|
|
"mean_token_accuracy": 0.14999792873859405,
|
|
"num_tokens": 10086307.0,
|
|
"step": 5810
|
|
},
|
|
{
|
|
"entropy": 5.669498872756958,
|
|
"epoch": 0.4524411593075277,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004984194846271489,
|
|
"loss": 5.5266,
|
|
"mean_token_accuracy": 0.1543448433279991,
|
|
"num_tokens": 10094954.0,
|
|
"step": 5815
|
|
},
|
|
{
|
|
"entropy": 5.670117568969727,
|
|
"epoch": 0.4528301886792453,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004984162036168586,
|
|
"loss": 5.6191,
|
|
"mean_token_accuracy": 0.14899968653917312,
|
|
"num_tokens": 10104401.0,
|
|
"step": 5820
|
|
},
|
|
{
|
|
"entropy": 5.639754581451416,
|
|
"epoch": 0.4532192180509628,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004984129192165831,
|
|
"loss": 5.6215,
|
|
"mean_token_accuracy": 0.1567351996898651,
|
|
"num_tokens": 10112596.0,
|
|
"step": 5825
|
|
},
|
|
{
|
|
"entropy": 5.708570718765259,
|
|
"epoch": 0.4536082474226804,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004984096314263722,
|
|
"loss": 5.6597,
|
|
"mean_token_accuracy": 0.15042801424860955,
|
|
"num_tokens": 10121311.0,
|
|
"step": 5830
|
|
},
|
|
{
|
|
"entropy": 5.611916875839233,
|
|
"epoch": 0.453997276794398,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004984063402462757,
|
|
"loss": 5.4792,
|
|
"mean_token_accuracy": 0.1603013962507248,
|
|
"num_tokens": 10130010.0,
|
|
"step": 5835
|
|
},
|
|
{
|
|
"entropy": 5.618326425552368,
|
|
"epoch": 0.45438630616611553,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004984030456763435,
|
|
"loss": 5.5699,
|
|
"mean_token_accuracy": 0.15638218820095062,
|
|
"num_tokens": 10138473.0,
|
|
"step": 5840
|
|
},
|
|
{
|
|
"entropy": 5.758038330078125,
|
|
"epoch": 0.4547753355378331,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004983997477166257,
|
|
"loss": 5.6439,
|
|
"mean_token_accuracy": 0.15722280889749526,
|
|
"num_tokens": 10146843.0,
|
|
"step": 5845
|
|
},
|
|
{
|
|
"entropy": 5.647872734069824,
|
|
"epoch": 0.45516436490955064,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004983964463671723,
|
|
"loss": 5.5049,
|
|
"mean_token_accuracy": 0.1628858208656311,
|
|
"num_tokens": 10155319.0,
|
|
"step": 5850
|
|
},
|
|
{
|
|
"entropy": 5.656351375579834,
|
|
"epoch": 0.45555339428126823,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004983931416280334,
|
|
"loss": 5.6806,
|
|
"mean_token_accuracy": 0.14831521585583687,
|
|
"num_tokens": 10164308.0,
|
|
"step": 5855
|
|
},
|
|
{
|
|
"entropy": 5.701720476150513,
|
|
"epoch": 0.4559424236529858,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004983898334992591,
|
|
"loss": 5.6882,
|
|
"mean_token_accuracy": 0.1529135026037693,
|
|
"num_tokens": 10173173.0,
|
|
"step": 5860
|
|
},
|
|
{
|
|
"entropy": 5.713402509689331,
|
|
"epoch": 0.45633145302470335,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004983865219808998,
|
|
"loss": 5.5949,
|
|
"mean_token_accuracy": 0.15679018795490265,
|
|
"num_tokens": 10181376.0,
|
|
"step": 5865
|
|
},
|
|
{
|
|
"entropy": 5.712046957015991,
|
|
"epoch": 0.45672048239642093,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004983832070730055,
|
|
"loss": 5.6881,
|
|
"mean_token_accuracy": 0.1543760657310486,
|
|
"num_tokens": 10189701.0,
|
|
"step": 5870
|
|
},
|
|
{
|
|
"entropy": 5.684455680847168,
|
|
"epoch": 0.4571095117681385,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004983798887756265,
|
|
"loss": 5.5556,
|
|
"mean_token_accuracy": 0.15939364433288575,
|
|
"num_tokens": 10198721.0,
|
|
"step": 5875
|
|
},
|
|
{
|
|
"entropy": 5.639842891693116,
|
|
"epoch": 0.45749854113985605,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004983765670888133,
|
|
"loss": 5.4467,
|
|
"mean_token_accuracy": 0.16593533754348755,
|
|
"num_tokens": 10206428.0,
|
|
"step": 5880
|
|
},
|
|
{
|
|
"entropy": 5.554336214065552,
|
|
"epoch": 0.45788757051157364,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004983732420126163,
|
|
"loss": 5.6108,
|
|
"mean_token_accuracy": 0.15324113368988038,
|
|
"num_tokens": 10214941.0,
|
|
"step": 5885
|
|
},
|
|
{
|
|
"entropy": 5.637087631225586,
|
|
"epoch": 0.45827659988329117,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004983699135470858,
|
|
"loss": 5.6055,
|
|
"mean_token_accuracy": 0.15487226396799086,
|
|
"num_tokens": 10223491.0,
|
|
"step": 5890
|
|
},
|
|
{
|
|
"entropy": 5.68569712638855,
|
|
"epoch": 0.45866562925500876,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004983665816922723,
|
|
"loss": 5.5321,
|
|
"mean_token_accuracy": 0.16137731224298477,
|
|
"num_tokens": 10231820.0,
|
|
"step": 5895
|
|
},
|
|
{
|
|
"entropy": 5.634616374969482,
|
|
"epoch": 0.45905465862672634,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004983632464482267,
|
|
"loss": 5.5282,
|
|
"mean_token_accuracy": 0.15775095969438552,
|
|
"num_tokens": 10239781.0,
|
|
"step": 5900
|
|
},
|
|
{
|
|
"entropy": 5.637348699569702,
|
|
"epoch": 0.4594436879984439,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004983599078149991,
|
|
"loss": 5.5441,
|
|
"mean_token_accuracy": 0.16737619191408157,
|
|
"num_tokens": 10248093.0,
|
|
"step": 5905
|
|
},
|
|
{
|
|
"entropy": 5.650561046600342,
|
|
"epoch": 0.45983271737016146,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004983565657926405,
|
|
"loss": 5.5692,
|
|
"mean_token_accuracy": 0.1580337852239609,
|
|
"num_tokens": 10256370.0,
|
|
"step": 5910
|
|
},
|
|
{
|
|
"entropy": 5.611146354675293,
|
|
"epoch": 0.460221746741879,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004983532203812017,
|
|
"loss": 5.5496,
|
|
"mean_token_accuracy": 0.15376363545656205,
|
|
"num_tokens": 10264924.0,
|
|
"step": 5915
|
|
},
|
|
{
|
|
"entropy": 5.630252170562744,
|
|
"epoch": 0.4606107761135966,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.0004983498715807331,
|
|
"loss": 5.4836,
|
|
"mean_token_accuracy": 0.15821914225816727,
|
|
"num_tokens": 10273488.0,
|
|
"step": 5920
|
|
},
|
|
{
|
|
"entropy": 5.638236379623413,
|
|
"epoch": 0.46099980548531416,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004983465193912857,
|
|
"loss": 5.5738,
|
|
"mean_token_accuracy": 0.1547227308154106,
|
|
"num_tokens": 10281534.0,
|
|
"step": 5925
|
|
},
|
|
{
|
|
"entropy": 5.689153718948364,
|
|
"epoch": 0.4613888348570317,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004983431638129104,
|
|
"loss": 5.6065,
|
|
"mean_token_accuracy": 0.15480573624372482,
|
|
"num_tokens": 10289613.0,
|
|
"step": 5930
|
|
},
|
|
{
|
|
"entropy": 5.73140025138855,
|
|
"epoch": 0.4617778642287493,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004983398048456581,
|
|
"loss": 5.6704,
|
|
"mean_token_accuracy": 0.155525304377079,
|
|
"num_tokens": 10299027.0,
|
|
"step": 5935
|
|
},
|
|
{
|
|
"entropy": 5.76631727218628,
|
|
"epoch": 0.4621668936004668,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004983364424895796,
|
|
"loss": 5.6149,
|
|
"mean_token_accuracy": 0.14618097692728044,
|
|
"num_tokens": 10308727.0,
|
|
"step": 5940
|
|
},
|
|
{
|
|
"entropy": 5.7385248184204105,
|
|
"epoch": 0.4625559229721844,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004983330767447262,
|
|
"loss": 5.6457,
|
|
"mean_token_accuracy": 0.15461504608392715,
|
|
"num_tokens": 10318129.0,
|
|
"step": 5945
|
|
},
|
|
{
|
|
"entropy": 5.644460153579712,
|
|
"epoch": 0.462944952343902,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004983297076111489,
|
|
"loss": 5.4898,
|
|
"mean_token_accuracy": 0.164915631711483,
|
|
"num_tokens": 10326504.0,
|
|
"step": 5950
|
|
},
|
|
{
|
|
"entropy": 5.602808809280395,
|
|
"epoch": 0.4633339817156195,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004983263350888987,
|
|
"loss": 5.5608,
|
|
"mean_token_accuracy": 0.16057233810424804,
|
|
"num_tokens": 10334585.0,
|
|
"step": 5955
|
|
},
|
|
{
|
|
"entropy": 5.68095030784607,
|
|
"epoch": 0.4637230110873371,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004983229591780268,
|
|
"loss": 5.5629,
|
|
"mean_token_accuracy": 0.16142504960298537,
|
|
"num_tokens": 10343328.0,
|
|
"step": 5960
|
|
},
|
|
{
|
|
"entropy": 5.663587331771851,
|
|
"epoch": 0.46411204045905463,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004983195798785844,
|
|
"loss": 5.5942,
|
|
"mean_token_accuracy": 0.15438419133424758,
|
|
"num_tokens": 10352289.0,
|
|
"step": 5965
|
|
},
|
|
{
|
|
"entropy": 5.670922183990479,
|
|
"epoch": 0.4645010698307722,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004983161971906228,
|
|
"loss": 5.6988,
|
|
"mean_token_accuracy": 0.14709374755620958,
|
|
"num_tokens": 10360847.0,
|
|
"step": 5970
|
|
},
|
|
{
|
|
"entropy": 5.68585786819458,
|
|
"epoch": 0.4648900992024898,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004983128111141935,
|
|
"loss": 5.6141,
|
|
"mean_token_accuracy": 0.16091488301753998,
|
|
"num_tokens": 10368911.0,
|
|
"step": 5975
|
|
},
|
|
{
|
|
"entropy": 5.704102945327759,
|
|
"epoch": 0.46527912857420733,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004983094216493475,
|
|
"loss": 5.5623,
|
|
"mean_token_accuracy": 0.1592513546347618,
|
|
"num_tokens": 10377257.0,
|
|
"step": 5980
|
|
},
|
|
{
|
|
"entropy": 5.665352773666382,
|
|
"epoch": 0.4656681579459249,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004983060287961367,
|
|
"loss": 5.6032,
|
|
"mean_token_accuracy": 0.15520215779542923,
|
|
"num_tokens": 10386167.0,
|
|
"step": 5985
|
|
},
|
|
{
|
|
"entropy": 5.621913242340088,
|
|
"epoch": 0.4660571873176425,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004983026325546123,
|
|
"loss": 5.503,
|
|
"mean_token_accuracy": 0.1555902063846588,
|
|
"num_tokens": 10395802.0,
|
|
"step": 5990
|
|
},
|
|
{
|
|
"entropy": 5.6354053020477295,
|
|
"epoch": 0.46644621668936004,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0004982992329248257,
|
|
"loss": 5.6251,
|
|
"mean_token_accuracy": 0.15431609004735947,
|
|
"num_tokens": 10404836.0,
|
|
"step": 5995
|
|
},
|
|
{
|
|
"entropy": 5.778206014633179,
|
|
"epoch": 0.4668352460610776,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004982958299068289,
|
|
"loss": 5.61,
|
|
"mean_token_accuracy": 0.15327388048171997,
|
|
"num_tokens": 10413394.0,
|
|
"step": 6000
|
|
},
|
|
{
|
|
"epoch": 0.4668352460610776,
|
|
"eval_entropy": 5.568441938504907,
|
|
"eval_loss": 5.637884616851807,
|
|
"eval_mean_token_accuracy": 0.16190429531231423,
|
|
"eval_num_tokens": 10413394.0,
|
|
"eval_runtime": 28.6058,
|
|
"eval_samples_per_second": 1452.783,
|
|
"eval_steps_per_second": 181.607,
|
|
"step": 6000
|
|
},
|
|
{
|
|
"entropy": 5.629551267623901,
|
|
"epoch": 0.46722427543279516,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.000498292423500673,
|
|
"loss": 5.5085,
|
|
"mean_token_accuracy": 0.1613881528377533,
|
|
"num_tokens": 10421916.0,
|
|
"step": 6005
|
|
},
|
|
{
|
|
"entropy": 5.6133910655975345,
|
|
"epoch": 0.46761330480451274,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004982890137064102,
|
|
"loss": 5.5831,
|
|
"mean_token_accuracy": 0.15664852559566497,
|
|
"num_tokens": 10430703.0,
|
|
"step": 6010
|
|
},
|
|
{
|
|
"entropy": 5.699441194534302,
|
|
"epoch": 0.46800233417623033,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.000498285600524092,
|
|
"loss": 5.6139,
|
|
"mean_token_accuracy": 0.16078107208013534,
|
|
"num_tokens": 10439523.0,
|
|
"step": 6015
|
|
},
|
|
{
|
|
"entropy": 5.705765581130981,
|
|
"epoch": 0.46839136354794786,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004982821839537701,
|
|
"loss": 5.5469,
|
|
"mean_token_accuracy": 0.1609642446041107,
|
|
"num_tokens": 10447777.0,
|
|
"step": 6020
|
|
},
|
|
{
|
|
"entropy": 5.631252908706665,
|
|
"epoch": 0.46878039291966545,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004982787639954966,
|
|
"loss": 5.5302,
|
|
"mean_token_accuracy": 0.16111329346895217,
|
|
"num_tokens": 10456105.0,
|
|
"step": 6025
|
|
},
|
|
{
|
|
"entropy": 5.624731254577637,
|
|
"epoch": 0.469169422291383,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.0004982753406493232,
|
|
"loss": 5.5732,
|
|
"mean_token_accuracy": 0.16137044578790666,
|
|
"num_tokens": 10464590.0,
|
|
"step": 6030
|
|
},
|
|
{
|
|
"entropy": 5.685329246520996,
|
|
"epoch": 0.46955845166310056,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004982719139153018,
|
|
"loss": 5.5791,
|
|
"mean_token_accuracy": 0.15369294285774232,
|
|
"num_tokens": 10472702.0,
|
|
"step": 6035
|
|
},
|
|
{
|
|
"entropy": 5.599481582641602,
|
|
"epoch": 0.46994748103481815,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.0004982684837934845,
|
|
"loss": 5.5158,
|
|
"mean_token_accuracy": 0.16099927127361296,
|
|
"num_tokens": 10480682.0,
|
|
"step": 6040
|
|
},
|
|
{
|
|
"entropy": 5.690699625015259,
|
|
"epoch": 0.4703365104065357,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004982650502839234,
|
|
"loss": 5.6214,
|
|
"mean_token_accuracy": 0.15555374920368195,
|
|
"num_tokens": 10488873.0,
|
|
"step": 6045
|
|
},
|
|
{
|
|
"entropy": 5.654029464721679,
|
|
"epoch": 0.47072553977825327,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004982616133866705,
|
|
"loss": 5.5687,
|
|
"mean_token_accuracy": 0.16214696764945985,
|
|
"num_tokens": 10497077.0,
|
|
"step": 6050
|
|
},
|
|
{
|
|
"entropy": 5.6827222347259525,
|
|
"epoch": 0.4711145691499708,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004982581731017779,
|
|
"loss": 5.5602,
|
|
"mean_token_accuracy": 0.16201916337013245,
|
|
"num_tokens": 10506072.0,
|
|
"step": 6055
|
|
},
|
|
{
|
|
"entropy": 5.680045700073242,
|
|
"epoch": 0.4715035985216884,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004982547294292979,
|
|
"loss": 5.624,
|
|
"mean_token_accuracy": 0.15231324285268782,
|
|
"num_tokens": 10515175.0,
|
|
"step": 6060
|
|
},
|
|
{
|
|
"entropy": 5.6123758316040036,
|
|
"epoch": 0.47189262789340597,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004982512823692828,
|
|
"loss": 5.5009,
|
|
"mean_token_accuracy": 0.1587204873561859,
|
|
"num_tokens": 10524800.0,
|
|
"step": 6065
|
|
},
|
|
{
|
|
"entropy": 5.673708391189575,
|
|
"epoch": 0.4722816572651235,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004982478319217848,
|
|
"loss": 5.6996,
|
|
"mean_token_accuracy": 0.14872199892997742,
|
|
"num_tokens": 10534608.0,
|
|
"step": 6070
|
|
},
|
|
{
|
|
"entropy": 5.769088983535767,
|
|
"epoch": 0.4726706866368411,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004982443780868562,
|
|
"loss": 5.5885,
|
|
"mean_token_accuracy": 0.15391682237386703,
|
|
"num_tokens": 10542992.0,
|
|
"step": 6075
|
|
},
|
|
{
|
|
"entropy": 5.676683807373047,
|
|
"epoch": 0.4730597160085587,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004982409208645496,
|
|
"loss": 5.6062,
|
|
"mean_token_accuracy": 0.15553525015711783,
|
|
"num_tokens": 10551682.0,
|
|
"step": 6080
|
|
},
|
|
{
|
|
"entropy": 5.655210304260254,
|
|
"epoch": 0.4734487453802762,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.0004982374602549173,
|
|
"loss": 5.5571,
|
|
"mean_token_accuracy": 0.16011223793029786,
|
|
"num_tokens": 10560556.0,
|
|
"step": 6085
|
|
},
|
|
{
|
|
"entropy": 5.748055696487427,
|
|
"epoch": 0.4738377747519938,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004982339962580119,
|
|
"loss": 5.7189,
|
|
"mean_token_accuracy": 0.150186175853014,
|
|
"num_tokens": 10569361.0,
|
|
"step": 6090
|
|
},
|
|
{
|
|
"entropy": 5.594575500488281,
|
|
"epoch": 0.4742268041237113,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004982305288738859,
|
|
"loss": 5.5491,
|
|
"mean_token_accuracy": 0.1564720705151558,
|
|
"num_tokens": 10577997.0,
|
|
"step": 6095
|
|
},
|
|
{
|
|
"entropy": 5.701799774169922,
|
|
"epoch": 0.4746158334954289,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004982270581025919,
|
|
"loss": 5.6426,
|
|
"mean_token_accuracy": 0.156770983338356,
|
|
"num_tokens": 10587005.0,
|
|
"step": 6100
|
|
},
|
|
{
|
|
"entropy": 5.697467517852783,
|
|
"epoch": 0.4750048628671465,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004982235839441826,
|
|
"loss": 5.5024,
|
|
"mean_token_accuracy": 0.16635954827070237,
|
|
"num_tokens": 10595196.0,
|
|
"step": 6105
|
|
},
|
|
{
|
|
"entropy": 5.729319858551025,
|
|
"epoch": 0.475393892238864,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004982201063987108,
|
|
"loss": 5.6547,
|
|
"mean_token_accuracy": 0.148310686647892,
|
|
"num_tokens": 10603796.0,
|
|
"step": 6110
|
|
},
|
|
{
|
|
"entropy": 5.703490686416626,
|
|
"epoch": 0.4757829216105816,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004982166254662292,
|
|
"loss": 5.6063,
|
|
"mean_token_accuracy": 0.1550201877951622,
|
|
"num_tokens": 10612895.0,
|
|
"step": 6115
|
|
},
|
|
{
|
|
"entropy": 5.7789592266082765,
|
|
"epoch": 0.47617195098229914,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004982131411467904,
|
|
"loss": 5.6865,
|
|
"mean_token_accuracy": 0.15575188100337983,
|
|
"num_tokens": 10621310.0,
|
|
"step": 6120
|
|
},
|
|
{
|
|
"entropy": 5.606504154205322,
|
|
"epoch": 0.4765609803540167,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004982096534404476,
|
|
"loss": 5.505,
|
|
"mean_token_accuracy": 0.16188933551311493,
|
|
"num_tokens": 10629598.0,
|
|
"step": 6125
|
|
},
|
|
{
|
|
"entropy": 5.653936815261841,
|
|
"epoch": 0.4769500097257343,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004982061623472535,
|
|
"loss": 5.5187,
|
|
"mean_token_accuracy": 0.15846583545207976,
|
|
"num_tokens": 10638218.0,
|
|
"step": 6130
|
|
},
|
|
{
|
|
"entropy": 5.716986656188965,
|
|
"epoch": 0.47733903909745184,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004982026678672612,
|
|
"loss": 5.6296,
|
|
"mean_token_accuracy": 0.15181267410516738,
|
|
"num_tokens": 10647215.0,
|
|
"step": 6135
|
|
},
|
|
{
|
|
"entropy": 5.702236032485962,
|
|
"epoch": 0.47772806846916943,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004981991700005238,
|
|
"loss": 5.7243,
|
|
"mean_token_accuracy": 0.14576748311519622,
|
|
"num_tokens": 10655755.0,
|
|
"step": 6140
|
|
},
|
|
{
|
|
"entropy": 5.7578771114349365,
|
|
"epoch": 0.47811709784088696,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.000498195668747094,
|
|
"loss": 5.6187,
|
|
"mean_token_accuracy": 0.15430370718240738,
|
|
"num_tokens": 10663969.0,
|
|
"step": 6145
|
|
},
|
|
{
|
|
"entropy": 5.698591709136963,
|
|
"epoch": 0.47850612721260455,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004981921641070254,
|
|
"loss": 5.49,
|
|
"mean_token_accuracy": 0.15365786403417586,
|
|
"num_tokens": 10672048.0,
|
|
"step": 6150
|
|
},
|
|
{
|
|
"entropy": 5.617149353027344,
|
|
"epoch": 0.47889515658432213,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004981886560803708,
|
|
"loss": 5.5889,
|
|
"mean_token_accuracy": 0.15536809265613555,
|
|
"num_tokens": 10681802.0,
|
|
"step": 6155
|
|
},
|
|
{
|
|
"entropy": 5.750160074234008,
|
|
"epoch": 0.47928418595603967,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.0004981851446671838,
|
|
"loss": 5.6392,
|
|
"mean_token_accuracy": 0.1540787011384964,
|
|
"num_tokens": 10690618.0,
|
|
"step": 6160
|
|
},
|
|
{
|
|
"entropy": 5.684419918060303,
|
|
"epoch": 0.47967321532775725,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004981816298675173,
|
|
"loss": 5.5504,
|
|
"mean_token_accuracy": 0.16353705152869225,
|
|
"num_tokens": 10699080.0,
|
|
"step": 6165
|
|
},
|
|
{
|
|
"entropy": 5.588387775421142,
|
|
"epoch": 0.4800622446994748,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004981781116814248,
|
|
"loss": 5.5668,
|
|
"mean_token_accuracy": 0.15334318876266478,
|
|
"num_tokens": 10708939.0,
|
|
"step": 6170
|
|
},
|
|
{
|
|
"entropy": 5.690774250030517,
|
|
"epoch": 0.48045127407119237,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004981745901089596,
|
|
"loss": 5.4828,
|
|
"mean_token_accuracy": 0.15659850239753723,
|
|
"num_tokens": 10717356.0,
|
|
"step": 6175
|
|
},
|
|
{
|
|
"entropy": 5.639165019989013,
|
|
"epoch": 0.48084030344290996,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004981710651501753,
|
|
"loss": 5.5756,
|
|
"mean_token_accuracy": 0.1490494817495346,
|
|
"num_tokens": 10725616.0,
|
|
"step": 6180
|
|
},
|
|
{
|
|
"entropy": 5.568220520019532,
|
|
"epoch": 0.4812293328146275,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004981675368051254,
|
|
"loss": 5.5815,
|
|
"mean_token_accuracy": 0.1579618126153946,
|
|
"num_tokens": 10734337.0,
|
|
"step": 6185
|
|
},
|
|
{
|
|
"entropy": 5.66068434715271,
|
|
"epoch": 0.4816183621863451,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004981640050738633,
|
|
"loss": 5.6054,
|
|
"mean_token_accuracy": 0.1561347499489784,
|
|
"num_tokens": 10742720.0,
|
|
"step": 6190
|
|
},
|
|
{
|
|
"entropy": 5.7725035667419435,
|
|
"epoch": 0.48200739155806266,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004981604699564426,
|
|
"loss": 5.6445,
|
|
"mean_token_accuracy": 0.14953835010528566,
|
|
"num_tokens": 10751809.0,
|
|
"step": 6195
|
|
},
|
|
{
|
|
"entropy": 5.646055459976196,
|
|
"epoch": 0.4823964209297802,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004981569314529169,
|
|
"loss": 5.4959,
|
|
"mean_token_accuracy": 0.16389817744493484,
|
|
"num_tokens": 10759879.0,
|
|
"step": 6200
|
|
},
|
|
{
|
|
"entropy": 5.572002315521241,
|
|
"epoch": 0.4827854503014978,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.00049815338956334,
|
|
"loss": 5.554,
|
|
"mean_token_accuracy": 0.15412390381097793,
|
|
"num_tokens": 10769309.0,
|
|
"step": 6205
|
|
},
|
|
{
|
|
"entropy": 5.642454004287719,
|
|
"epoch": 0.4831744796732153,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0004981498442877656,
|
|
"loss": 5.4995,
|
|
"mean_token_accuracy": 0.16186270713806153,
|
|
"num_tokens": 10777676.0,
|
|
"step": 6210
|
|
},
|
|
{
|
|
"entropy": 5.608219718933105,
|
|
"epoch": 0.4835635090449329,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004981462956262474,
|
|
"loss": 5.6997,
|
|
"mean_token_accuracy": 0.15294308215379715,
|
|
"num_tokens": 10786278.0,
|
|
"step": 6215
|
|
},
|
|
{
|
|
"entropy": 5.7101478099823,
|
|
"epoch": 0.4839525384166505,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004981427435788396,
|
|
"loss": 5.6283,
|
|
"mean_token_accuracy": 0.15803202390670776,
|
|
"num_tokens": 10795323.0,
|
|
"step": 6220
|
|
},
|
|
{
|
|
"entropy": 5.676022005081177,
|
|
"epoch": 0.484341567788368,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004981391881455957,
|
|
"loss": 5.5123,
|
|
"mean_token_accuracy": 0.1589615076780319,
|
|
"num_tokens": 10803978.0,
|
|
"step": 6225
|
|
},
|
|
{
|
|
"entropy": 5.659019994735718,
|
|
"epoch": 0.4847305971600856,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004981356293265696,
|
|
"loss": 5.6166,
|
|
"mean_token_accuracy": 0.15300326198339462,
|
|
"num_tokens": 10812488.0,
|
|
"step": 6230
|
|
},
|
|
{
|
|
"entropy": 5.642748737335205,
|
|
"epoch": 0.4851196265318031,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0004981320671218157,
|
|
"loss": 5.5991,
|
|
"mean_token_accuracy": 0.15167004540562629,
|
|
"num_tokens": 10821076.0,
|
|
"step": 6235
|
|
},
|
|
{
|
|
"entropy": 5.5737348079681395,
|
|
"epoch": 0.4855086559035207,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004981285015313877,
|
|
"loss": 5.4243,
|
|
"mean_token_accuracy": 0.17024301141500472,
|
|
"num_tokens": 10828634.0,
|
|
"step": 6240
|
|
},
|
|
{
|
|
"entropy": 5.58956880569458,
|
|
"epoch": 0.4858976852752383,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004981249325553399,
|
|
"loss": 5.5494,
|
|
"mean_token_accuracy": 0.16450238227844238,
|
|
"num_tokens": 10837481.0,
|
|
"step": 6245
|
|
},
|
|
{
|
|
"entropy": 5.655309247970581,
|
|
"epoch": 0.48628671464695583,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004981213601937264,
|
|
"loss": 5.6613,
|
|
"mean_token_accuracy": 0.150309956073761,
|
|
"num_tokens": 10846729.0,
|
|
"step": 6250
|
|
},
|
|
{
|
|
"entropy": 5.713288116455078,
|
|
"epoch": 0.4866757440186734,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004981177844466013,
|
|
"loss": 5.6214,
|
|
"mean_token_accuracy": 0.15035200268030166,
|
|
"num_tokens": 10855344.0,
|
|
"step": 6255
|
|
},
|
|
{
|
|
"entropy": 5.727412748336792,
|
|
"epoch": 0.48706477339039095,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004981142053140192,
|
|
"loss": 5.6404,
|
|
"mean_token_accuracy": 0.15218437761068343,
|
|
"num_tokens": 10863934.0,
|
|
"step": 6260
|
|
},
|
|
{
|
|
"entropy": 5.6626691818237305,
|
|
"epoch": 0.48745380276210853,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004981106227960339,
|
|
"loss": 5.6274,
|
|
"mean_token_accuracy": 0.15228987336158753,
|
|
"num_tokens": 10872031.0,
|
|
"step": 6265
|
|
},
|
|
{
|
|
"entropy": 5.675407791137696,
|
|
"epoch": 0.4878428321338261,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.0004981070368927001,
|
|
"loss": 5.6858,
|
|
"mean_token_accuracy": 0.15372779071331025,
|
|
"num_tokens": 10881385.0,
|
|
"step": 6270
|
|
},
|
|
{
|
|
"entropy": 5.669041538238526,
|
|
"epoch": 0.48823186150554365,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.000498103447604072,
|
|
"loss": 5.5879,
|
|
"mean_token_accuracy": 0.16089208722114562,
|
|
"num_tokens": 10890483.0,
|
|
"step": 6275
|
|
},
|
|
{
|
|
"entropy": 5.696747446060181,
|
|
"epoch": 0.48862089087726124,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004980998549302044,
|
|
"loss": 5.6235,
|
|
"mean_token_accuracy": 0.16344629526138305,
|
|
"num_tokens": 10898338.0,
|
|
"step": 6280
|
|
},
|
|
{
|
|
"entropy": 5.634139537811279,
|
|
"epoch": 0.4890099202489788,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004980962588711516,
|
|
"loss": 5.6076,
|
|
"mean_token_accuracy": 0.15650987178087233,
|
|
"num_tokens": 10908087.0,
|
|
"step": 6285
|
|
},
|
|
{
|
|
"entropy": 5.699162721633911,
|
|
"epoch": 0.48939894962069636,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.000498092659426968,
|
|
"loss": 5.5951,
|
|
"mean_token_accuracy": 0.14966844767332077,
|
|
"num_tokens": 10916704.0,
|
|
"step": 6290
|
|
},
|
|
{
|
|
"entropy": 5.710136556625367,
|
|
"epoch": 0.48978797899241394,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.0004980890565977085,
|
|
"loss": 5.5604,
|
|
"mean_token_accuracy": 0.15742921754717826,
|
|
"num_tokens": 10925186.0,
|
|
"step": 6295
|
|
},
|
|
{
|
|
"entropy": 5.676451396942139,
|
|
"epoch": 0.4901770083641315,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004980854503834276,
|
|
"loss": 5.6055,
|
|
"mean_token_accuracy": 0.1546354204416275,
|
|
"num_tokens": 10934247.0,
|
|
"step": 6300
|
|
},
|
|
{
|
|
"entropy": 5.716699838638306,
|
|
"epoch": 0.49056603773584906,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004980818407841802,
|
|
"loss": 5.6518,
|
|
"mean_token_accuracy": 0.1529087468981743,
|
|
"num_tokens": 10944260.0,
|
|
"step": 6305
|
|
},
|
|
{
|
|
"entropy": 5.690576171875,
|
|
"epoch": 0.49095506710756665,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004980782278000207,
|
|
"loss": 5.6054,
|
|
"mean_token_accuracy": 0.14937896132469178,
|
|
"num_tokens": 10954065.0,
|
|
"step": 6310
|
|
},
|
|
{
|
|
"entropy": 5.664132452011108,
|
|
"epoch": 0.4913440964792842,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.0004980746114310043,
|
|
"loss": 5.6488,
|
|
"mean_token_accuracy": 0.1546714961528778,
|
|
"num_tokens": 10962918.0,
|
|
"step": 6315
|
|
},
|
|
{
|
|
"entropy": 5.577079391479492,
|
|
"epoch": 0.49173312585100176,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004980709916771858,
|
|
"loss": 5.5307,
|
|
"mean_token_accuracy": 0.1586841955780983,
|
|
"num_tokens": 10972356.0,
|
|
"step": 6320
|
|
},
|
|
{
|
|
"entropy": 5.611245918273926,
|
|
"epoch": 0.4921221552227193,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004980673685386198,
|
|
"loss": 5.5614,
|
|
"mean_token_accuracy": 0.15363311916589736,
|
|
"num_tokens": 10980984.0,
|
|
"step": 6325
|
|
},
|
|
{
|
|
"entropy": 5.643860816955566,
|
|
"epoch": 0.4925111845944369,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004980637420153618,
|
|
"loss": 5.53,
|
|
"mean_token_accuracy": 0.1608725979924202,
|
|
"num_tokens": 10989809.0,
|
|
"step": 6330
|
|
},
|
|
{
|
|
"entropy": 5.6936290740966795,
|
|
"epoch": 0.49290021396615447,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.0004980601121074664,
|
|
"loss": 5.56,
|
|
"mean_token_accuracy": 0.153535445779562,
|
|
"num_tokens": 10998824.0,
|
|
"step": 6335
|
|
},
|
|
{
|
|
"entropy": 5.728955459594727,
|
|
"epoch": 0.493289243337872,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.0004980564788149889,
|
|
"loss": 5.6626,
|
|
"mean_token_accuracy": 0.15556565821170806,
|
|
"num_tokens": 11006755.0,
|
|
"step": 6340
|
|
},
|
|
{
|
|
"entropy": 5.65275502204895,
|
|
"epoch": 0.4936782727095896,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004980528421379844,
|
|
"loss": 5.5599,
|
|
"mean_token_accuracy": 0.15920377969741822,
|
|
"num_tokens": 11015337.0,
|
|
"step": 6345
|
|
},
|
|
{
|
|
"entropy": 5.612233114242554,
|
|
"epoch": 0.4940673020813071,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.000498049202076508,
|
|
"loss": 5.4651,
|
|
"mean_token_accuracy": 0.1664075404405594,
|
|
"num_tokens": 11024186.0,
|
|
"step": 6350
|
|
},
|
|
{
|
|
"entropy": 5.65667462348938,
|
|
"epoch": 0.4944563314530247,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004980455586306149,
|
|
"loss": 5.5865,
|
|
"mean_token_accuracy": 0.16023100167512894,
|
|
"num_tokens": 11032504.0,
|
|
"step": 6355
|
|
},
|
|
{
|
|
"entropy": 5.676429986953735,
|
|
"epoch": 0.4948453608247423,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004980419118003605,
|
|
"loss": 5.553,
|
|
"mean_token_accuracy": 0.15278212875127792,
|
|
"num_tokens": 11042252.0,
|
|
"step": 6360
|
|
},
|
|
{
|
|
"entropy": 5.750020265579224,
|
|
"epoch": 0.4952343901964598,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004980382615858001,
|
|
"loss": 5.6082,
|
|
"mean_token_accuracy": 0.15880184024572372,
|
|
"num_tokens": 11051361.0,
|
|
"step": 6365
|
|
},
|
|
{
|
|
"entropy": 5.6557018756866455,
|
|
"epoch": 0.4956234195681774,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004980346079869892,
|
|
"loss": 5.5874,
|
|
"mean_token_accuracy": 0.15210525542497635,
|
|
"num_tokens": 11060822.0,
|
|
"step": 6370
|
|
},
|
|
{
|
|
"entropy": 5.686988830566406,
|
|
"epoch": 0.49601244893989493,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.000498030951003983,
|
|
"loss": 5.6344,
|
|
"mean_token_accuracy": 0.15813659280538558,
|
|
"num_tokens": 11069528.0,
|
|
"step": 6375
|
|
},
|
|
{
|
|
"entropy": 5.6128278255462645,
|
|
"epoch": 0.4964014783116125,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004980272906368371,
|
|
"loss": 5.4827,
|
|
"mean_token_accuracy": 0.16487869769334793,
|
|
"num_tokens": 11077917.0,
|
|
"step": 6380
|
|
},
|
|
{
|
|
"entropy": 5.632443428039551,
|
|
"epoch": 0.4967905076833301,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004980236268856071,
|
|
"loss": 5.551,
|
|
"mean_token_accuracy": 0.15362292379140854,
|
|
"num_tokens": 11085938.0,
|
|
"step": 6385
|
|
},
|
|
{
|
|
"entropy": 5.609829044342041,
|
|
"epoch": 0.49717953705504764,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004980199597503487,
|
|
"loss": 5.6138,
|
|
"mean_token_accuracy": 0.1502000316977501,
|
|
"num_tokens": 11094898.0,
|
|
"step": 6390
|
|
},
|
|
{
|
|
"entropy": 5.621690034866333,
|
|
"epoch": 0.4975685664267652,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004980162892311171,
|
|
"loss": 5.4643,
|
|
"mean_token_accuracy": 0.16103583425283433,
|
|
"num_tokens": 11103038.0,
|
|
"step": 6395
|
|
},
|
|
{
|
|
"entropy": 5.729760646820068,
|
|
"epoch": 0.4979575957984828,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004980126153279684,
|
|
"loss": 5.575,
|
|
"mean_token_accuracy": 0.160553440451622,
|
|
"num_tokens": 11111965.0,
|
|
"step": 6400
|
|
},
|
|
{
|
|
"entropy": 5.654656314849854,
|
|
"epoch": 0.49834662517020034,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004980089380409583,
|
|
"loss": 5.6028,
|
|
"mean_token_accuracy": 0.14948188066482543,
|
|
"num_tokens": 11121482.0,
|
|
"step": 6405
|
|
},
|
|
{
|
|
"entropy": 5.6757025718688965,
|
|
"epoch": 0.4987356545419179,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004980052573701424,
|
|
"loss": 5.5836,
|
|
"mean_token_accuracy": 0.16052414774894713,
|
|
"num_tokens": 11129742.0,
|
|
"step": 6410
|
|
},
|
|
{
|
|
"entropy": 5.637845230102539,
|
|
"epoch": 0.49912468391363546,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004980015733155767,
|
|
"loss": 5.5757,
|
|
"mean_token_accuracy": 0.15860638469457627,
|
|
"num_tokens": 11138388.0,
|
|
"step": 6415
|
|
},
|
|
{
|
|
"entropy": 5.462844562530518,
|
|
"epoch": 0.49951371328535304,
|
|
"grad_norm": 1.96875,
|
|
"learning_rate": 0.0004979978858773171,
|
|
"loss": 5.3159,
|
|
"mean_token_accuracy": 0.16803677380084991,
|
|
"num_tokens": 11146967.0,
|
|
"step": 6420
|
|
},
|
|
{
|
|
"entropy": 5.632554769515991,
|
|
"epoch": 0.49990274265707063,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.0004979941950554195,
|
|
"loss": 5.6902,
|
|
"mean_token_accuracy": 0.15228309333324433,
|
|
"num_tokens": 11155888.0,
|
|
"step": 6425
|
|
},
|
|
{
|
|
"entropy": 5.735075187683106,
|
|
"epoch": 0.5002917720287882,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004979905008499399,
|
|
"loss": 5.5297,
|
|
"mean_token_accuracy": 0.1570112720131874,
|
|
"num_tokens": 11164358.0,
|
|
"step": 6430
|
|
},
|
|
{
|
|
"entropy": 5.557287931442261,
|
|
"epoch": 0.5006808014005057,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004979868032609344,
|
|
"loss": 5.3946,
|
|
"mean_token_accuracy": 0.17054508477449418,
|
|
"num_tokens": 11172416.0,
|
|
"step": 6435
|
|
},
|
|
{
|
|
"entropy": 5.653583955764771,
|
|
"epoch": 0.5010698307722233,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004979831022884591,
|
|
"loss": 5.5805,
|
|
"mean_token_accuracy": 0.15527529418468475,
|
|
"num_tokens": 11181159.0,
|
|
"step": 6440
|
|
},
|
|
{
|
|
"entropy": 5.719984531402588,
|
|
"epoch": 0.5014588601439409,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004979793979325701,
|
|
"loss": 5.6211,
|
|
"mean_token_accuracy": 0.15462423712015153,
|
|
"num_tokens": 11189725.0,
|
|
"step": 6445
|
|
},
|
|
{
|
|
"entropy": 5.6761411190032955,
|
|
"epoch": 0.5018478895156584,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004979756901933236,
|
|
"loss": 5.607,
|
|
"mean_token_accuracy": 0.15461336821317673,
|
|
"num_tokens": 11197795.0,
|
|
"step": 6450
|
|
},
|
|
{
|
|
"entropy": 5.661126232147216,
|
|
"epoch": 0.502236918887376,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.000497971979070776,
|
|
"loss": 5.5499,
|
|
"mean_token_accuracy": 0.16126018166542053,
|
|
"num_tokens": 11205352.0,
|
|
"step": 6455
|
|
},
|
|
{
|
|
"entropy": 5.647138690948486,
|
|
"epoch": 0.5026259482590936,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004979682645649834,
|
|
"loss": 5.6053,
|
|
"mean_token_accuracy": 0.16011005714535714,
|
|
"num_tokens": 11214142.0,
|
|
"step": 6460
|
|
},
|
|
{
|
|
"entropy": 5.651855516433716,
|
|
"epoch": 0.5030149776308112,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004979645466760025,
|
|
"loss": 5.4865,
|
|
"mean_token_accuracy": 0.158424311876297,
|
|
"num_tokens": 11222565.0,
|
|
"step": 6465
|
|
},
|
|
{
|
|
"entropy": 5.640393257141113,
|
|
"epoch": 0.5034040070025287,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004979608254038892,
|
|
"loss": 5.5947,
|
|
"mean_token_accuracy": 0.15077592730522155,
|
|
"num_tokens": 11231829.0,
|
|
"step": 6470
|
|
},
|
|
{
|
|
"entropy": 5.606630086898804,
|
|
"epoch": 0.5037930363742462,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004979571007487003,
|
|
"loss": 5.5766,
|
|
"mean_token_accuracy": 0.16073868423700333,
|
|
"num_tokens": 11240302.0,
|
|
"step": 6475
|
|
},
|
|
{
|
|
"entropy": 5.7437659740448,
|
|
"epoch": 0.5041820657459638,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004979533727104924,
|
|
"loss": 5.6772,
|
|
"mean_token_accuracy": 0.14755369126796722,
|
|
"num_tokens": 11248610.0,
|
|
"step": 6480
|
|
},
|
|
{
|
|
"entropy": 5.71062536239624,
|
|
"epoch": 0.5045710951176814,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.000497949641289322,
|
|
"loss": 5.6081,
|
|
"mean_token_accuracy": 0.15848981738090515,
|
|
"num_tokens": 11257441.0,
|
|
"step": 6485
|
|
},
|
|
{
|
|
"entropy": 5.6013991355896,
|
|
"epoch": 0.504960124489399,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004979459064852456,
|
|
"loss": 5.4765,
|
|
"mean_token_accuracy": 0.1602603167295456,
|
|
"num_tokens": 11265915.0,
|
|
"step": 6490
|
|
},
|
|
{
|
|
"entropy": 5.679823303222657,
|
|
"epoch": 0.5053491538611166,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0004979421682983197,
|
|
"loss": 5.5921,
|
|
"mean_token_accuracy": 0.1491402804851532,
|
|
"num_tokens": 11274165.0,
|
|
"step": 6495
|
|
},
|
|
{
|
|
"entropy": 5.700294399261475,
|
|
"epoch": 0.505738183232834,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004979384267286015,
|
|
"loss": 5.5452,
|
|
"mean_token_accuracy": 0.160502190887928,
|
|
"num_tokens": 11283316.0,
|
|
"step": 6500
|
|
},
|
|
{
|
|
"entropy": 5.702039480209351,
|
|
"epoch": 0.5061272126045516,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004979346817761475,
|
|
"loss": 5.6669,
|
|
"mean_token_accuracy": 0.15230532437562944,
|
|
"num_tokens": 11292289.0,
|
|
"step": 6505
|
|
},
|
|
{
|
|
"entropy": 5.676564931869507,
|
|
"epoch": 0.5065162419762692,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004979309334410144,
|
|
"loss": 5.5663,
|
|
"mean_token_accuracy": 0.1540845066308975,
|
|
"num_tokens": 11301192.0,
|
|
"step": 6510
|
|
},
|
|
{
|
|
"entropy": 5.714155769348144,
|
|
"epoch": 0.5069052713479868,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004979271817232594,
|
|
"loss": 5.5919,
|
|
"mean_token_accuracy": 0.15891016125679017,
|
|
"num_tokens": 11309906.0,
|
|
"step": 6515
|
|
},
|
|
{
|
|
"entropy": 5.707177019119262,
|
|
"epoch": 0.5072943007197044,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004979234266229391,
|
|
"loss": 5.5947,
|
|
"mean_token_accuracy": 0.1564686119556427,
|
|
"num_tokens": 11318227.0,
|
|
"step": 6520
|
|
},
|
|
{
|
|
"entropy": 5.581366682052613,
|
|
"epoch": 0.5076833300914219,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004979196681401106,
|
|
"loss": 5.6066,
|
|
"mean_token_accuracy": 0.15133707523345946,
|
|
"num_tokens": 11327524.0,
|
|
"step": 6525
|
|
},
|
|
{
|
|
"entropy": 5.6488265037536625,
|
|
"epoch": 0.5080723594631394,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.000497915906274831,
|
|
"loss": 5.5322,
|
|
"mean_token_accuracy": 0.15982652455568314,
|
|
"num_tokens": 11336214.0,
|
|
"step": 6530
|
|
},
|
|
{
|
|
"entropy": 5.627641773223877,
|
|
"epoch": 0.508461388834857,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004979121410271574,
|
|
"loss": 5.4009,
|
|
"mean_token_accuracy": 0.16517358124256135,
|
|
"num_tokens": 11344551.0,
|
|
"step": 6535
|
|
},
|
|
{
|
|
"entropy": 5.553968477249145,
|
|
"epoch": 0.5088504182065746,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004979083723971468,
|
|
"loss": 5.4724,
|
|
"mean_token_accuracy": 0.16233978569507598,
|
|
"num_tokens": 11353180.0,
|
|
"step": 6540
|
|
},
|
|
{
|
|
"entropy": 5.508282327651978,
|
|
"epoch": 0.5092394475782922,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004979046003848564,
|
|
"loss": 5.4411,
|
|
"mean_token_accuracy": 0.16504863947629927,
|
|
"num_tokens": 11361343.0,
|
|
"step": 6545
|
|
},
|
|
{
|
|
"entropy": 5.617854309082031,
|
|
"epoch": 0.5096284769500097,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004979008249903435,
|
|
"loss": 5.5552,
|
|
"mean_token_accuracy": 0.15905145108699797,
|
|
"num_tokens": 11369915.0,
|
|
"step": 6550
|
|
},
|
|
{
|
|
"entropy": 5.674259948730469,
|
|
"epoch": 0.5100175063217273,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004978970462136655,
|
|
"loss": 5.5669,
|
|
"mean_token_accuracy": 0.15540537238121033,
|
|
"num_tokens": 11379813.0,
|
|
"step": 6555
|
|
},
|
|
{
|
|
"entropy": 5.675784635543823,
|
|
"epoch": 0.5104065356934449,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004978932640548794,
|
|
"loss": 5.5297,
|
|
"mean_token_accuracy": 0.16335135251283645,
|
|
"num_tokens": 11388029.0,
|
|
"step": 6560
|
|
},
|
|
{
|
|
"entropy": 5.639474105834961,
|
|
"epoch": 0.5107955650651624,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004978894785140429,
|
|
"loss": 5.4445,
|
|
"mean_token_accuracy": 0.16073926836252211,
|
|
"num_tokens": 11395852.0,
|
|
"step": 6565
|
|
},
|
|
{
|
|
"entropy": 5.655018377304077,
|
|
"epoch": 0.51118459443688,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004978856895912132,
|
|
"loss": 5.5413,
|
|
"mean_token_accuracy": 0.1564188316464424,
|
|
"num_tokens": 11404756.0,
|
|
"step": 6570
|
|
},
|
|
{
|
|
"entropy": 5.755813550949097,
|
|
"epoch": 0.5115736238085975,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 0.0004978818972864481,
|
|
"loss": 5.7065,
|
|
"mean_token_accuracy": 0.14963974803686142,
|
|
"num_tokens": 11413301.0,
|
|
"step": 6575
|
|
},
|
|
{
|
|
"entropy": 5.664954710006714,
|
|
"epoch": 0.5119626531803151,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0004978781015998048,
|
|
"loss": 5.4669,
|
|
"mean_token_accuracy": 0.1635374277830124,
|
|
"num_tokens": 11421034.0,
|
|
"step": 6580
|
|
},
|
|
{
|
|
"entropy": 5.578311252593994,
|
|
"epoch": 0.5123516825520327,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004978743025313413,
|
|
"loss": 5.5041,
|
|
"mean_token_accuracy": 0.1537765234708786,
|
|
"num_tokens": 11429066.0,
|
|
"step": 6585
|
|
},
|
|
{
|
|
"entropy": 5.549916791915893,
|
|
"epoch": 0.5127407119237503,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004978705000811148,
|
|
"loss": 5.5306,
|
|
"mean_token_accuracy": 0.15937168151140213,
|
|
"num_tokens": 11438109.0,
|
|
"step": 6590
|
|
},
|
|
{
|
|
"entropy": 5.723791074752808,
|
|
"epoch": 0.5131297412954678,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004978666942491832,
|
|
"loss": 5.558,
|
|
"mean_token_accuracy": 0.15773135274648667,
|
|
"num_tokens": 11446787.0,
|
|
"step": 6595
|
|
},
|
|
{
|
|
"entropy": 5.584632110595703,
|
|
"epoch": 0.5135187706671853,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 0.0004978628850356043,
|
|
"loss": 5.5056,
|
|
"mean_token_accuracy": 0.15432734936475753,
|
|
"num_tokens": 11456262.0,
|
|
"step": 6600
|
|
},
|
|
{
|
|
"entropy": 5.645711898803711,
|
|
"epoch": 0.5139078000389029,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004978590724404358,
|
|
"loss": 5.5123,
|
|
"mean_token_accuracy": 0.16353395730257034,
|
|
"num_tokens": 11464297.0,
|
|
"step": 6605
|
|
},
|
|
{
|
|
"entropy": 5.72183837890625,
|
|
"epoch": 0.5142968294106205,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004978552564637356,
|
|
"loss": 5.6086,
|
|
"mean_token_accuracy": 0.15540100187063216,
|
|
"num_tokens": 11473519.0,
|
|
"step": 6610
|
|
},
|
|
{
|
|
"entropy": 5.702983427047729,
|
|
"epoch": 0.5146858587823381,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.0004978514371055616,
|
|
"loss": 5.5795,
|
|
"mean_token_accuracy": 0.1491965666413307,
|
|
"num_tokens": 11482249.0,
|
|
"step": 6615
|
|
},
|
|
{
|
|
"entropy": 5.577159833908081,
|
|
"epoch": 0.5150748881540557,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.0004978476143659718,
|
|
"loss": 5.5398,
|
|
"mean_token_accuracy": 0.1571039080619812,
|
|
"num_tokens": 11490687.0,
|
|
"step": 6620
|
|
},
|
|
{
|
|
"entropy": 5.608038711547851,
|
|
"epoch": 0.5154639175257731,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004978437882450241,
|
|
"loss": 5.5616,
|
|
"mean_token_accuracy": 0.15619437545537948,
|
|
"num_tokens": 11500225.0,
|
|
"step": 6625
|
|
},
|
|
{
|
|
"entropy": 5.666680955886841,
|
|
"epoch": 0.5158529468974907,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.0004978399587427766,
|
|
"loss": 5.4953,
|
|
"mean_token_accuracy": 0.1533425435423851,
|
|
"num_tokens": 11508116.0,
|
|
"step": 6630
|
|
},
|
|
{
|
|
"entropy": 5.592615365982056,
|
|
"epoch": 0.5162419762692083,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004978361258592874,
|
|
"loss": 5.5636,
|
|
"mean_token_accuracy": 0.15597649812698364,
|
|
"num_tokens": 11516525.0,
|
|
"step": 6635
|
|
},
|
|
{
|
|
"entropy": 5.570996522903442,
|
|
"epoch": 0.5166310056409259,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004978322895946147,
|
|
"loss": 5.5418,
|
|
"mean_token_accuracy": 0.16293194890022278,
|
|
"num_tokens": 11525434.0,
|
|
"step": 6640
|
|
},
|
|
{
|
|
"entropy": 5.697331666946411,
|
|
"epoch": 0.5170200350126435,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004978284499488167,
|
|
"loss": 5.5891,
|
|
"mean_token_accuracy": 0.15939099341630936,
|
|
"num_tokens": 11534318.0,
|
|
"step": 6645
|
|
},
|
|
{
|
|
"entropy": 5.677669429779053,
|
|
"epoch": 0.5174090643843611,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.0004978246069219516,
|
|
"loss": 5.5172,
|
|
"mean_token_accuracy": 0.16647360622882842,
|
|
"num_tokens": 11542777.0,
|
|
"step": 6650
|
|
},
|
|
{
|
|
"entropy": 5.538128852844238,
|
|
"epoch": 0.5177980937560785,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004978207605140777,
|
|
"loss": 5.5117,
|
|
"mean_token_accuracy": 0.1648077517747879,
|
|
"num_tokens": 11550888.0,
|
|
"step": 6655
|
|
},
|
|
{
|
|
"entropy": 5.609681606292725,
|
|
"epoch": 0.5181871231277961,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.0004978169107252534,
|
|
"loss": 5.5468,
|
|
"mean_token_accuracy": 0.15201089009642602,
|
|
"num_tokens": 11560047.0,
|
|
"step": 6660
|
|
},
|
|
{
|
|
"entropy": 5.719398736953735,
|
|
"epoch": 0.5185761524995137,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004978130575555373,
|
|
"loss": 5.563,
|
|
"mean_token_accuracy": 0.15973781645298005,
|
|
"num_tokens": 11568862.0,
|
|
"step": 6665
|
|
},
|
|
{
|
|
"entropy": 5.626110649108886,
|
|
"epoch": 0.5189651818712313,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004978092010049877,
|
|
"loss": 5.5118,
|
|
"mean_token_accuracy": 0.16364447623491288,
|
|
"num_tokens": 11577509.0,
|
|
"step": 6670
|
|
},
|
|
{
|
|
"entropy": 5.682620191574097,
|
|
"epoch": 0.5193542112429489,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.000497805341073663,
|
|
"loss": 5.6344,
|
|
"mean_token_accuracy": 0.15549029260873795,
|
|
"num_tokens": 11585902.0,
|
|
"step": 6675
|
|
},
|
|
{
|
|
"entropy": 5.673947095870972,
|
|
"epoch": 0.5197432406146664,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.0004978014777616219,
|
|
"loss": 5.629,
|
|
"mean_token_accuracy": 0.1575734183192253,
|
|
"num_tokens": 11594895.0,
|
|
"step": 6680
|
|
},
|
|
{
|
|
"entropy": 5.579812717437744,
|
|
"epoch": 0.520132269986384,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004977976110689229,
|
|
"loss": 5.4366,
|
|
"mean_token_accuracy": 0.1603616327047348,
|
|
"num_tokens": 11604080.0,
|
|
"step": 6685
|
|
},
|
|
{
|
|
"entropy": 5.697282886505127,
|
|
"epoch": 0.5205212993581015,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.000497793740995625,
|
|
"loss": 5.5729,
|
|
"mean_token_accuracy": 0.15553624778985978,
|
|
"num_tokens": 11613370.0,
|
|
"step": 6690
|
|
},
|
|
{
|
|
"entropy": 5.6387876033782955,
|
|
"epoch": 0.5209103287298191,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.0004977898675417866,
|
|
"loss": 5.5522,
|
|
"mean_token_accuracy": 0.1519399181008339,
|
|
"num_tokens": 11621913.0,
|
|
"step": 6695
|
|
},
|
|
{
|
|
"entropy": 5.686840772628784,
|
|
"epoch": 0.5212993581015367,
|
|
"grad_norm": 1.84375,
|
|
"learning_rate": 0.0004977859907074664,
|
|
"loss": 5.6704,
|
|
"mean_token_accuracy": 0.15187918841838838,
|
|
"num_tokens": 11630393.0,
|
|
"step": 6700
|
|
},
|
|
{
|
|
"entropy": 5.711111545562744,
|
|
"epoch": 0.5216883874732542,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0004977821104927236,
|
|
"loss": 5.627,
|
|
"mean_token_accuracy": 0.15826086550951005,
|
|
"num_tokens": 11639038.0,
|
|
"step": 6705
|
|
},
|
|
{
|
|
"entropy": 5.619731855392456,
|
|
"epoch": 0.5220774168449718,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004977782268976167,
|
|
"loss": 5.5299,
|
|
"mean_token_accuracy": 0.15893726497888566,
|
|
"num_tokens": 11647355.0,
|
|
"step": 6710
|
|
},
|
|
{
|
|
"entropy": 5.591154432296753,
|
|
"epoch": 0.5224664462166894,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.0004977743399222048,
|
|
"loss": 5.5186,
|
|
"mean_token_accuracy": 0.156563962996006,
|
|
"num_tokens": 11655899.0,
|
|
"step": 6715
|
|
},
|
|
{
|
|
"entropy": 5.75395131111145,
|
|
"epoch": 0.522855475588407,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004977704495665471,
|
|
"loss": 5.6881,
|
|
"mean_token_accuracy": 0.1467943161725998,
|
|
"num_tokens": 11664602.0,
|
|
"step": 6720
|
|
},
|
|
{
|
|
"entropy": 5.686694002151489,
|
|
"epoch": 0.5232445049601245,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004977665558307023,
|
|
"loss": 5.5377,
|
|
"mean_token_accuracy": 0.1604433313012123,
|
|
"num_tokens": 11673011.0,
|
|
"step": 6725
|
|
},
|
|
{
|
|
"entropy": 5.7638593196868895,
|
|
"epoch": 0.523633534331842,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004977626587147295,
|
|
"loss": 5.722,
|
|
"mean_token_accuracy": 0.14738779366016388,
|
|
"num_tokens": 11681989.0,
|
|
"step": 6730
|
|
},
|
|
{
|
|
"entropy": 5.7711700916290285,
|
|
"epoch": 0.5240225637035596,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.000497758758218688,
|
|
"loss": 5.6352,
|
|
"mean_token_accuracy": 0.15125580877065659,
|
|
"num_tokens": 11690502.0,
|
|
"step": 6735
|
|
},
|
|
{
|
|
"entropy": 5.705477237701416,
|
|
"epoch": 0.5244115930752772,
|
|
"grad_norm": 1.921875,
|
|
"learning_rate": 0.0004977548543426368,
|
|
"loss": 5.6305,
|
|
"mean_token_accuracy": 0.15084460079669954,
|
|
"num_tokens": 11699594.0,
|
|
"step": 6740
|
|
},
|
|
{
|
|
"entropy": 5.604963397979736,
|
|
"epoch": 0.5248006224469948,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0004977509470866353,
|
|
"loss": 5.481,
|
|
"mean_token_accuracy": 0.1593596838414669,
|
|
"num_tokens": 11708009.0,
|
|
"step": 6745
|
|
},
|
|
{
|
|
"entropy": 5.740193605422974,
|
|
"epoch": 0.5251896518187124,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004977470364507427,
|
|
"loss": 5.6609,
|
|
"mean_token_accuracy": 0.14922915548086166,
|
|
"num_tokens": 11716592.0,
|
|
"step": 6750
|
|
},
|
|
{
|
|
"entropy": 5.689943075180054,
|
|
"epoch": 0.5255786811904298,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004977431224350184,
|
|
"loss": 5.688,
|
|
"mean_token_accuracy": 0.14554595500230788,
|
|
"num_tokens": 11725894.0,
|
|
"step": 6755
|
|
},
|
|
{
|
|
"entropy": 5.773393678665161,
|
|
"epoch": 0.5259677105621474,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0004977392050395217,
|
|
"loss": 5.5485,
|
|
"mean_token_accuracy": 0.15920153111219407,
|
|
"num_tokens": 11734141.0,
|
|
"step": 6760
|
|
},
|
|
{
|
|
"entropy": 5.667986345291138,
|
|
"epoch": 0.526356739933865,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004977352842643121,
|
|
"loss": 5.6483,
|
|
"mean_token_accuracy": 0.15431325882673264,
|
|
"num_tokens": 11742539.0,
|
|
"step": 6765
|
|
},
|
|
{
|
|
"entropy": 5.708223152160644,
|
|
"epoch": 0.5267457693055826,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.000497731360109449,
|
|
"loss": 5.6123,
|
|
"mean_token_accuracy": 0.15050556659698486,
|
|
"num_tokens": 11751649.0,
|
|
"step": 6770
|
|
},
|
|
{
|
|
"entropy": 5.753337812423706,
|
|
"epoch": 0.5271347986773002,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004977274325749922,
|
|
"loss": 5.6048,
|
|
"mean_token_accuracy": 0.15385161116719245,
|
|
"num_tokens": 11760376.0,
|
|
"step": 6775
|
|
},
|
|
{
|
|
"entropy": 5.746728897094727,
|
|
"epoch": 0.5275238280490177,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004977235016610011,
|
|
"loss": 5.5795,
|
|
"mean_token_accuracy": 0.15702240467071532,
|
|
"num_tokens": 11768644.0,
|
|
"step": 6780
|
|
},
|
|
{
|
|
"entropy": 5.764103364944458,
|
|
"epoch": 0.5279128574207352,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004977195673675353,
|
|
"loss": 5.6494,
|
|
"mean_token_accuracy": 0.15692424327135085,
|
|
"num_tokens": 11777282.0,
|
|
"step": 6785
|
|
},
|
|
{
|
|
"entropy": 5.675798320770264,
|
|
"epoch": 0.5283018867924528,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004977156296946545,
|
|
"loss": 5.5416,
|
|
"mean_token_accuracy": 0.1602182298898697,
|
|
"num_tokens": 11786108.0,
|
|
"step": 6790
|
|
},
|
|
{
|
|
"entropy": 5.666502380371094,
|
|
"epoch": 0.5286909161641704,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004977116886424187,
|
|
"loss": 5.5864,
|
|
"mean_token_accuracy": 0.15119998008012772,
|
|
"num_tokens": 11795151.0,
|
|
"step": 6795
|
|
},
|
|
{
|
|
"entropy": 5.783410549163818,
|
|
"epoch": 0.529079945535888,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004977077442108873,
|
|
"loss": 5.554,
|
|
"mean_token_accuracy": 0.15910998433828355,
|
|
"num_tokens": 11803971.0,
|
|
"step": 6800
|
|
},
|
|
{
|
|
"entropy": 5.62806978225708,
|
|
"epoch": 0.5294689749076055,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004977037964001204,
|
|
"loss": 5.5976,
|
|
"mean_token_accuracy": 0.1572650596499443,
|
|
"num_tokens": 11812483.0,
|
|
"step": 6805
|
|
},
|
|
{
|
|
"entropy": 5.618113851547241,
|
|
"epoch": 0.5298580042793231,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.000497699845210178,
|
|
"loss": 5.5055,
|
|
"mean_token_accuracy": 0.16720063090324402,
|
|
"num_tokens": 11821144.0,
|
|
"step": 6810
|
|
},
|
|
{
|
|
"entropy": 5.653380250930786,
|
|
"epoch": 0.5302470336510406,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004976958906411197,
|
|
"loss": 5.4534,
|
|
"mean_token_accuracy": 0.16973180323839188,
|
|
"num_tokens": 11829298.0,
|
|
"step": 6815
|
|
},
|
|
{
|
|
"entropy": 5.62983136177063,
|
|
"epoch": 0.5306360630227582,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004976919326930059,
|
|
"loss": 5.5432,
|
|
"mean_token_accuracy": 0.16084313318133353,
|
|
"num_tokens": 11837558.0,
|
|
"step": 6820
|
|
},
|
|
{
|
|
"entropy": 5.516823768615723,
|
|
"epoch": 0.5310250923944758,
|
|
"grad_norm": 2.296875,
|
|
"learning_rate": 0.0004976879713658964,
|
|
"loss": 5.4418,
|
|
"mean_token_accuracy": 0.15914363116025926,
|
|
"num_tokens": 11845770.0,
|
|
"step": 6825
|
|
},
|
|
{
|
|
"entropy": 5.696159219741821,
|
|
"epoch": 0.5314141217661933,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004976840066598514,
|
|
"loss": 5.6447,
|
|
"mean_token_accuracy": 0.14841388761997223,
|
|
"num_tokens": 11854351.0,
|
|
"step": 6830
|
|
},
|
|
{
|
|
"entropy": 5.862872743606568,
|
|
"epoch": 0.5318031511379109,
|
|
"grad_norm": 2.3125,
|
|
"learning_rate": 0.0004976800385749309,
|
|
"loss": 5.6348,
|
|
"mean_token_accuracy": 0.15798128098249437,
|
|
"num_tokens": 11862610.0,
|
|
"step": 6835
|
|
},
|
|
{
|
|
"entropy": 5.686704397201538,
|
|
"epoch": 0.5321921805096285,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004976760671111954,
|
|
"loss": 5.6108,
|
|
"mean_token_accuracy": 0.15772643238306044,
|
|
"num_tokens": 11871078.0,
|
|
"step": 6840
|
|
},
|
|
{
|
|
"entropy": 5.578802299499512,
|
|
"epoch": 0.532581209881346,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.000497672092268705,
|
|
"loss": 5.4583,
|
|
"mean_token_accuracy": 0.1677114337682724,
|
|
"num_tokens": 11879303.0,
|
|
"step": 6845
|
|
},
|
|
{
|
|
"entropy": 5.626303482055664,
|
|
"epoch": 0.5329702392530636,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.00049766811404752,
|
|
"loss": 5.5305,
|
|
"mean_token_accuracy": 0.1624523416161537,
|
|
"num_tokens": 11887855.0,
|
|
"step": 6850
|
|
},
|
|
{
|
|
"entropy": 5.7215758800506595,
|
|
"epoch": 0.5333592686247812,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004976641324477008,
|
|
"loss": 5.491,
|
|
"mean_token_accuracy": 0.1590698853135109,
|
|
"num_tokens": 11896262.0,
|
|
"step": 6855
|
|
},
|
|
{
|
|
"entropy": 5.540533924102784,
|
|
"epoch": 0.5337482979964987,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.0004976601474693077,
|
|
"loss": 5.4027,
|
|
"mean_token_accuracy": 0.16541368514299393,
|
|
"num_tokens": 11905140.0,
|
|
"step": 6860
|
|
},
|
|
{
|
|
"entropy": 5.539865493774414,
|
|
"epoch": 0.5341373273682163,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004976561591124014,
|
|
"loss": 5.4552,
|
|
"mean_token_accuracy": 0.16123025864362717,
|
|
"num_tokens": 11913177.0,
|
|
"step": 6865
|
|
},
|
|
{
|
|
"entropy": 5.529560852050781,
|
|
"epoch": 0.5345263567399339,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004976521673770421,
|
|
"loss": 5.4933,
|
|
"mean_token_accuracy": 0.1606004297733307,
|
|
"num_tokens": 11921955.0,
|
|
"step": 6870
|
|
},
|
|
{
|
|
"entropy": 5.634306287765503,
|
|
"epoch": 0.5349153861116515,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004976481722632907,
|
|
"loss": 5.4734,
|
|
"mean_token_accuracy": 0.15833614021539688,
|
|
"num_tokens": 11930976.0,
|
|
"step": 6875
|
|
},
|
|
{
|
|
"entropy": 5.58788480758667,
|
|
"epoch": 0.535304415483369,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004976441737712076,
|
|
"loss": 5.4244,
|
|
"mean_token_accuracy": 0.1578416720032692,
|
|
"num_tokens": 11939708.0,
|
|
"step": 6880
|
|
},
|
|
{
|
|
"entropy": 5.636071586608887,
|
|
"epoch": 0.5356934448550865,
|
|
"grad_norm": 1.96875,
|
|
"learning_rate": 0.0004976401719008536,
|
|
"loss": 5.6091,
|
|
"mean_token_accuracy": 0.15459367111325265,
|
|
"num_tokens": 11949176.0,
|
|
"step": 6885
|
|
},
|
|
{
|
|
"entropy": 5.666082382202148,
|
|
"epoch": 0.5360824742268041,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004976361666522893,
|
|
"loss": 5.4626,
|
|
"mean_token_accuracy": 0.16275524199008942,
|
|
"num_tokens": 11958089.0,
|
|
"step": 6890
|
|
},
|
|
{
|
|
"entropy": 5.6072547912597654,
|
|
"epoch": 0.5364715035985217,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004976321580255755,
|
|
"loss": 5.5487,
|
|
"mean_token_accuracy": 0.16223233491182326,
|
|
"num_tokens": 11966719.0,
|
|
"step": 6895
|
|
},
|
|
{
|
|
"entropy": 5.681102991104126,
|
|
"epoch": 0.5368605329702393,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004976281460207731,
|
|
"loss": 5.627,
|
|
"mean_token_accuracy": 0.15269040167331696,
|
|
"num_tokens": 11975959.0,
|
|
"step": 6900
|
|
},
|
|
{
|
|
"entropy": 5.733845901489258,
|
|
"epoch": 0.5372495623419569,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.000497624130637943,
|
|
"loss": 5.567,
|
|
"mean_token_accuracy": 0.1594778597354889,
|
|
"num_tokens": 11984282.0,
|
|
"step": 6905
|
|
},
|
|
{
|
|
"entropy": 5.667761516571045,
|
|
"epoch": 0.5376385917136743,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.000497620111877146,
|
|
"loss": 5.5787,
|
|
"mean_token_accuracy": 0.15442643016576768,
|
|
"num_tokens": 11993289.0,
|
|
"step": 6910
|
|
},
|
|
{
|
|
"entropy": 5.637051391601562,
|
|
"epoch": 0.5380276210853919,
|
|
"grad_norm": 1.9140625,
|
|
"learning_rate": 0.0004976160897384431,
|
|
"loss": 5.5044,
|
|
"mean_token_accuracy": 0.15614233464002608,
|
|
"num_tokens": 12002425.0,
|
|
"step": 6915
|
|
},
|
|
{
|
|
"entropy": 5.69523549079895,
|
|
"epoch": 0.5384166504571095,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004976120642218955,
|
|
"loss": 5.525,
|
|
"mean_token_accuracy": 0.16103218197822572,
|
|
"num_tokens": 12010435.0,
|
|
"step": 6920
|
|
},
|
|
{
|
|
"entropy": 5.585979366302491,
|
|
"epoch": 0.5388056798288271,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.000497608035327564,
|
|
"loss": 5.5674,
|
|
"mean_token_accuracy": 0.151433002948761,
|
|
"num_tokens": 12018768.0,
|
|
"step": 6925
|
|
},
|
|
{
|
|
"entropy": 5.654223823547364,
|
|
"epoch": 0.5391947092005447,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.00049760400305551,
|
|
"loss": 5.5796,
|
|
"mean_token_accuracy": 0.1578141525387764,
|
|
"num_tokens": 12027617.0,
|
|
"step": 6930
|
|
},
|
|
{
|
|
"entropy": 5.715594100952148,
|
|
"epoch": 0.5395837385722622,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004975999674057944,
|
|
"loss": 5.5538,
|
|
"mean_token_accuracy": 0.1522558592259884,
|
|
"num_tokens": 12036024.0,
|
|
"step": 6935
|
|
},
|
|
{
|
|
"entropy": 5.7062911033630375,
|
|
"epoch": 0.5399727679439797,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004975959283784787,
|
|
"loss": 5.5767,
|
|
"mean_token_accuracy": 0.15493114590644835,
|
|
"num_tokens": 12044206.0,
|
|
"step": 6940
|
|
},
|
|
{
|
|
"entropy": 5.610129928588867,
|
|
"epoch": 0.5403617973156973,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004975918859736241,
|
|
"loss": 5.476,
|
|
"mean_token_accuracy": 0.16617640256881713,
|
|
"num_tokens": 12052294.0,
|
|
"step": 6945
|
|
},
|
|
{
|
|
"entropy": 5.627176713943482,
|
|
"epoch": 0.5407508266874149,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004975878401912919,
|
|
"loss": 5.5924,
|
|
"mean_token_accuracy": 0.15193110331892967,
|
|
"num_tokens": 12060446.0,
|
|
"step": 6950
|
|
},
|
|
{
|
|
"entropy": 5.6887932300567625,
|
|
"epoch": 0.5411398560591325,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004975837910315436,
|
|
"loss": 5.6741,
|
|
"mean_token_accuracy": 0.1515423372387886,
|
|
"num_tokens": 12069267.0,
|
|
"step": 6955
|
|
},
|
|
{
|
|
"entropy": 5.70375018119812,
|
|
"epoch": 0.54152888543085,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.0004975797384944405,
|
|
"loss": 5.6015,
|
|
"mean_token_accuracy": 0.15626930743455886,
|
|
"num_tokens": 12077808.0,
|
|
"step": 6960
|
|
},
|
|
{
|
|
"entropy": 5.637791299819947,
|
|
"epoch": 0.5419179148025676,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.000497575682580044,
|
|
"loss": 5.5489,
|
|
"mean_token_accuracy": 0.15620417445898055,
|
|
"num_tokens": 12086893.0,
|
|
"step": 6965
|
|
},
|
|
{
|
|
"entropy": 5.6194240093231205,
|
|
"epoch": 0.5423069441742852,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.000497571623288416,
|
|
"loss": 5.442,
|
|
"mean_token_accuracy": 0.16180325746536256,
|
|
"num_tokens": 12095462.0,
|
|
"step": 6970
|
|
},
|
|
{
|
|
"entropy": 5.624150943756104,
|
|
"epoch": 0.5426959735460027,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004975675606196177,
|
|
"loss": 5.5336,
|
|
"mean_token_accuracy": 0.15985793471336365,
|
|
"num_tokens": 12103477.0,
|
|
"step": 6975
|
|
},
|
|
{
|
|
"entropy": 5.728774833679199,
|
|
"epoch": 0.5430850029177203,
|
|
"grad_norm": 2.578125,
|
|
"learning_rate": 0.000497563494573711,
|
|
"loss": 5.6643,
|
|
"mean_token_accuracy": 0.15420561283826828,
|
|
"num_tokens": 12112752.0,
|
|
"step": 6980
|
|
},
|
|
{
|
|
"entropy": 5.74130482673645,
|
|
"epoch": 0.5434740322894378,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004975594251507575,
|
|
"loss": 5.5961,
|
|
"mean_token_accuracy": 0.14960930198431016,
|
|
"num_tokens": 12121883.0,
|
|
"step": 6985
|
|
},
|
|
{
|
|
"entropy": 5.667213439941406,
|
|
"epoch": 0.5438630616611554,
|
|
"grad_norm": 1.9296875,
|
|
"learning_rate": 0.000497555352350819,
|
|
"loss": 5.5382,
|
|
"mean_token_accuracy": 0.15813797265291213,
|
|
"num_tokens": 12130316.0,
|
|
"step": 6990
|
|
},
|
|
{
|
|
"entropy": 5.608577489852905,
|
|
"epoch": 0.544252091032873,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004975512761739572,
|
|
"loss": 5.5082,
|
|
"mean_token_accuracy": 0.15483314245939256,
|
|
"num_tokens": 12138856.0,
|
|
"step": 6995
|
|
},
|
|
{
|
|
"entropy": 5.596859073638916,
|
|
"epoch": 0.5446411204045906,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.000497547196620234,
|
|
"loss": 5.5857,
|
|
"mean_token_accuracy": 0.15458821803331374,
|
|
"num_tokens": 12147933.0,
|
|
"step": 7000
|
|
},
|
|
{
|
|
"entropy": 5.64696855545044,
|
|
"epoch": 0.5450301497763081,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004975431136897114,
|
|
"loss": 5.4734,
|
|
"mean_token_accuracy": 0.16336166560649873,
|
|
"num_tokens": 12156529.0,
|
|
"step": 7005
|
|
},
|
|
{
|
|
"entropy": 5.618450355529785,
|
|
"epoch": 0.5454191791480256,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004975390273824512,
|
|
"loss": 5.423,
|
|
"mean_token_accuracy": 0.16375362277030944,
|
|
"num_tokens": 12165233.0,
|
|
"step": 7010
|
|
},
|
|
{
|
|
"entropy": 5.689289093017578,
|
|
"epoch": 0.5458082085197432,
|
|
"grad_norm": 1.84375,
|
|
"learning_rate": 0.0004975349376985155,
|
|
"loss": 5.6091,
|
|
"mean_token_accuracy": 0.15117039233446122,
|
|
"num_tokens": 12173260.0,
|
|
"step": 7015
|
|
},
|
|
{
|
|
"entropy": 5.690649938583374,
|
|
"epoch": 0.5461972378914608,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004975308446379663,
|
|
"loss": 5.6347,
|
|
"mean_token_accuracy": 0.15114786326885224,
|
|
"num_tokens": 12181676.0,
|
|
"step": 7020
|
|
},
|
|
{
|
|
"entropy": 5.647702264785766,
|
|
"epoch": 0.5465862672631784,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004975267482008657,
|
|
"loss": 5.5421,
|
|
"mean_token_accuracy": 0.15484113842248917,
|
|
"num_tokens": 12189485.0,
|
|
"step": 7025
|
|
},
|
|
{
|
|
"entropy": 5.634745836257935,
|
|
"epoch": 0.546975296634896,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.000497522648387276,
|
|
"loss": 5.4544,
|
|
"mean_token_accuracy": 0.16015653163194657,
|
|
"num_tokens": 12198429.0,
|
|
"step": 7030
|
|
},
|
|
{
|
|
"entropy": 5.6571352005004885,
|
|
"epoch": 0.5473643260066134,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.0004975185451972592,
|
|
"loss": 5.5801,
|
|
"mean_token_accuracy": 0.1574718177318573,
|
|
"num_tokens": 12207404.0,
|
|
"step": 7035
|
|
},
|
|
{
|
|
"entropy": 5.703709650039673,
|
|
"epoch": 0.547753355378331,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004975144386308776,
|
|
"loss": 5.5682,
|
|
"mean_token_accuracy": 0.15560432076454161,
|
|
"num_tokens": 12216301.0,
|
|
"step": 7040
|
|
},
|
|
{
|
|
"entropy": 5.583737707138061,
|
|
"epoch": 0.5481423847500486,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.0004975103286881936,
|
|
"loss": 5.5382,
|
|
"mean_token_accuracy": 0.1608162447810173,
|
|
"num_tokens": 12224873.0,
|
|
"step": 7045
|
|
},
|
|
{
|
|
"entropy": 5.542259263992309,
|
|
"epoch": 0.5485314141217662,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.0004975062153692696,
|
|
"loss": 5.5109,
|
|
"mean_token_accuracy": 0.16012222468852996,
|
|
"num_tokens": 12233439.0,
|
|
"step": 7050
|
|
},
|
|
{
|
|
"entropy": 5.683546447753907,
|
|
"epoch": 0.5489204434934838,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004975020986741678,
|
|
"loss": 5.5959,
|
|
"mean_token_accuracy": 0.15372914522886277,
|
|
"num_tokens": 12242235.0,
|
|
"step": 7055
|
|
},
|
|
{
|
|
"entropy": 5.658541107177735,
|
|
"epoch": 0.5493094728652014,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004974979786029509,
|
|
"loss": 5.516,
|
|
"mean_token_accuracy": 0.1605488106608391,
|
|
"num_tokens": 12251295.0,
|
|
"step": 7060
|
|
},
|
|
{
|
|
"entropy": 5.650334739685059,
|
|
"epoch": 0.5496985022369189,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004974938551556814,
|
|
"loss": 5.4479,
|
|
"mean_token_accuracy": 0.1698696255683899,
|
|
"num_tokens": 12260130.0,
|
|
"step": 7065
|
|
},
|
|
{
|
|
"entropy": 5.5806965827941895,
|
|
"epoch": 0.5500875316086364,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004974897283324217,
|
|
"loss": 5.5386,
|
|
"mean_token_accuracy": 0.15596865564584733,
|
|
"num_tokens": 12269542.0,
|
|
"step": 7070
|
|
},
|
|
{
|
|
"entropy": 5.605713272094727,
|
|
"epoch": 0.550476560980354,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 0.0004974855981332343,
|
|
"loss": 5.6084,
|
|
"mean_token_accuracy": 0.1583064466714859,
|
|
"num_tokens": 12278174.0,
|
|
"step": 7075
|
|
},
|
|
{
|
|
"entropy": 5.662755489349365,
|
|
"epoch": 0.5508655903520716,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004974814645581823,
|
|
"loss": 5.6768,
|
|
"mean_token_accuracy": 0.14716447219252587,
|
|
"num_tokens": 12287651.0,
|
|
"step": 7080
|
|
},
|
|
{
|
|
"entropy": 5.802349328994751,
|
|
"epoch": 0.5512546197237892,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004974773276073282,
|
|
"loss": 5.6637,
|
|
"mean_token_accuracy": 0.15257747769355773,
|
|
"num_tokens": 12296009.0,
|
|
"step": 7085
|
|
},
|
|
{
|
|
"entropy": 5.65597562789917,
|
|
"epoch": 0.5516436490955067,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004974731872807347,
|
|
"loss": 5.5493,
|
|
"mean_token_accuracy": 0.15140283182263375,
|
|
"num_tokens": 12305406.0,
|
|
"step": 7090
|
|
},
|
|
{
|
|
"entropy": 5.657384634017944,
|
|
"epoch": 0.5520326784672243,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004974690435784647,
|
|
"loss": 5.5872,
|
|
"mean_token_accuracy": 0.15931931436061858,
|
|
"num_tokens": 12314169.0,
|
|
"step": 7095
|
|
},
|
|
{
|
|
"entropy": 5.591557884216309,
|
|
"epoch": 0.5524217078389418,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004974648965005811,
|
|
"loss": 5.4718,
|
|
"mean_token_accuracy": 0.1641459584236145,
|
|
"num_tokens": 12323019.0,
|
|
"step": 7100
|
|
},
|
|
{
|
|
"entropy": 5.611501979827881,
|
|
"epoch": 0.5528107372106594,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004974607460471466,
|
|
"loss": 5.5832,
|
|
"mean_token_accuracy": 0.155895234644413,
|
|
"num_tokens": 12331491.0,
|
|
"step": 7105
|
|
},
|
|
{
|
|
"entropy": 5.696614456176758,
|
|
"epoch": 0.553199766582377,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004974565922182246,
|
|
"loss": 5.5469,
|
|
"mean_token_accuracy": 0.16092757135629654,
|
|
"num_tokens": 12339647.0,
|
|
"step": 7110
|
|
},
|
|
{
|
|
"entropy": 5.668904209136963,
|
|
"epoch": 0.5535887959540945,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004974524350138777,
|
|
"loss": 5.5435,
|
|
"mean_token_accuracy": 0.1599072754383087,
|
|
"num_tokens": 12348469.0,
|
|
"step": 7115
|
|
},
|
|
{
|
|
"entropy": 5.63965220451355,
|
|
"epoch": 0.5539778253258121,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004974482744341693,
|
|
"loss": 5.5177,
|
|
"mean_token_accuracy": 0.15749800205230713,
|
|
"num_tokens": 12357168.0,
|
|
"step": 7120
|
|
},
|
|
{
|
|
"entropy": 5.533153247833252,
|
|
"epoch": 0.5543668546975297,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004974441104791624,
|
|
"loss": 5.5151,
|
|
"mean_token_accuracy": 0.15641161054372787,
|
|
"num_tokens": 12365750.0,
|
|
"step": 7125
|
|
},
|
|
{
|
|
"entropy": 5.619474458694458,
|
|
"epoch": 0.5547558840692473,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004974399431489201,
|
|
"loss": 5.5567,
|
|
"mean_token_accuracy": 0.15669889748096466,
|
|
"num_tokens": 12374086.0,
|
|
"step": 7130
|
|
},
|
|
{
|
|
"entropy": 5.632277202606201,
|
|
"epoch": 0.5551449134409648,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004974357724435057,
|
|
"loss": 5.486,
|
|
"mean_token_accuracy": 0.1624843955039978,
|
|
"num_tokens": 12381997.0,
|
|
"step": 7135
|
|
},
|
|
{
|
|
"entropy": 5.644105386734009,
|
|
"epoch": 0.5555339428126823,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.0004974315983629825,
|
|
"loss": 5.5839,
|
|
"mean_token_accuracy": 0.1633768931031227,
|
|
"num_tokens": 12391083.0,
|
|
"step": 7140
|
|
},
|
|
{
|
|
"entropy": 5.641611623764038,
|
|
"epoch": 0.5559229721843999,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004974274209074139,
|
|
"loss": 5.4902,
|
|
"mean_token_accuracy": 0.16029936969280242,
|
|
"num_tokens": 12400016.0,
|
|
"step": 7145
|
|
},
|
|
{
|
|
"entropy": 5.7136517524719235,
|
|
"epoch": 0.5563120015561175,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004974232400768632,
|
|
"loss": 5.6197,
|
|
"mean_token_accuracy": 0.1593371108174324,
|
|
"num_tokens": 12409255.0,
|
|
"step": 7150
|
|
},
|
|
{
|
|
"entropy": 5.686195755004883,
|
|
"epoch": 0.5567010309278351,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004974190558713939,
|
|
"loss": 5.506,
|
|
"mean_token_accuracy": 0.16573817282915115,
|
|
"num_tokens": 12417765.0,
|
|
"step": 7155
|
|
},
|
|
{
|
|
"entropy": 5.6866135597229,
|
|
"epoch": 0.5570900602995527,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.0004974148682910694,
|
|
"loss": 5.7551,
|
|
"mean_token_accuracy": 0.1465160384774208,
|
|
"num_tokens": 12427588.0,
|
|
"step": 7160
|
|
},
|
|
{
|
|
"entropy": 5.583876132965088,
|
|
"epoch": 0.5574790896712701,
|
|
"grad_norm": 1.9921875,
|
|
"learning_rate": 0.0004974106773359533,
|
|
"loss": 5.4141,
|
|
"mean_token_accuracy": 0.16548473089933396,
|
|
"num_tokens": 12435773.0,
|
|
"step": 7165
|
|
},
|
|
{
|
|
"entropy": 5.620090770721435,
|
|
"epoch": 0.5578681190429877,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.0004974064830061091,
|
|
"loss": 5.5571,
|
|
"mean_token_accuracy": 0.1578982651233673,
|
|
"num_tokens": 12443837.0,
|
|
"step": 7170
|
|
},
|
|
{
|
|
"entropy": 5.597108602523804,
|
|
"epoch": 0.5582571484147053,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004974022853016006,
|
|
"loss": 5.5589,
|
|
"mean_token_accuracy": 0.1618955463171005,
|
|
"num_tokens": 12452945.0,
|
|
"step": 7175
|
|
},
|
|
{
|
|
"entropy": 5.617226076126099,
|
|
"epoch": 0.5586461777864229,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.0004973980842224913,
|
|
"loss": 5.4724,
|
|
"mean_token_accuracy": 0.16712482050061225,
|
|
"num_tokens": 12461008.0,
|
|
"step": 7180
|
|
},
|
|
{
|
|
"entropy": 5.542527437210083,
|
|
"epoch": 0.5590352071581405,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0004973938797688452,
|
|
"loss": 5.4693,
|
|
"mean_token_accuracy": 0.1560630664229393,
|
|
"num_tokens": 12469314.0,
|
|
"step": 7185
|
|
},
|
|
{
|
|
"entropy": 5.636436462402344,
|
|
"epoch": 0.559424236529858,
|
|
"grad_norm": 1.953125,
|
|
"learning_rate": 0.0004973896719407259,
|
|
"loss": 5.4897,
|
|
"mean_token_accuracy": 0.15964962393045426,
|
|
"num_tokens": 12477540.0,
|
|
"step": 7190
|
|
},
|
|
{
|
|
"entropy": 5.596930932998657,
|
|
"epoch": 0.5598132659015755,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004973854607381972,
|
|
"loss": 5.576,
|
|
"mean_token_accuracy": 0.15696000158786774,
|
|
"num_tokens": 12486894.0,
|
|
"step": 7195
|
|
},
|
|
{
|
|
"entropy": 5.635582160949707,
|
|
"epoch": 0.5602022952732931,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.0004973812461613232,
|
|
"loss": 5.5553,
|
|
"mean_token_accuracy": 0.15301310420036315,
|
|
"num_tokens": 12496213.0,
|
|
"step": 7200
|
|
},
|
|
{
|
|
"entropy": 5.647828674316406,
|
|
"epoch": 0.5605913246450107,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.0004973770282101677,
|
|
"loss": 5.5246,
|
|
"mean_token_accuracy": 0.15997655987739562,
|
|
"num_tokens": 12504160.0,
|
|
"step": 7205
|
|
},
|
|
{
|
|
"entropy": 5.517643880844116,
|
|
"epoch": 0.5609803540167283,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.0004973728068847947,
|
|
"loss": 5.4829,
|
|
"mean_token_accuracy": 0.16585087180137634,
|
|
"num_tokens": 12511915.0,
|
|
"step": 7210
|
|
},
|
|
{
|
|
"entropy": 5.581799030303955,
|
|
"epoch": 0.5613693833884458,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004973685821852684,
|
|
"loss": 5.5138,
|
|
"mean_token_accuracy": 0.15690659135580062,
|
|
"num_tokens": 12520400.0,
|
|
"step": 7215
|
|
},
|
|
{
|
|
"entropy": 5.546680736541748,
|
|
"epoch": 0.5617584127601634,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004973643541116528,
|
|
"loss": 5.4268,
|
|
"mean_token_accuracy": 0.16706114411354064,
|
|
"num_tokens": 12528724.0,
|
|
"step": 7220
|
|
},
|
|
{
|
|
"entropy": 5.660353088378907,
|
|
"epoch": 0.562147442131881,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.000497360122664012,
|
|
"loss": 5.5998,
|
|
"mean_token_accuracy": 0.15986159592866897,
|
|
"num_tokens": 12537378.0,
|
|
"step": 7225
|
|
},
|
|
{
|
|
"entropy": 5.673803234100342,
|
|
"epoch": 0.5625364715035985,
|
|
"grad_norm": 1.8515625,
|
|
"learning_rate": 0.0004973558878424104,
|
|
"loss": 5.5398,
|
|
"mean_token_accuracy": 0.16054396480321884,
|
|
"num_tokens": 12546080.0,
|
|
"step": 7230
|
|
},
|
|
{
|
|
"entropy": 5.722423696517945,
|
|
"epoch": 0.5629255008753161,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004973516496469119,
|
|
"loss": 5.5727,
|
|
"mean_token_accuracy": 0.15393828749656677,
|
|
"num_tokens": 12554526.0,
|
|
"step": 7235
|
|
},
|
|
{
|
|
"entropy": 5.625352764129639,
|
|
"epoch": 0.5633145302470336,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004973474080775811,
|
|
"loss": 5.5233,
|
|
"mean_token_accuracy": 0.16156897842884063,
|
|
"num_tokens": 12563018.0,
|
|
"step": 7240
|
|
},
|
|
{
|
|
"entropy": 5.620291805267334,
|
|
"epoch": 0.5637035596187512,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.0004973431631344824,
|
|
"loss": 5.5642,
|
|
"mean_token_accuracy": 0.15838960856199263,
|
|
"num_tokens": 12571611.0,
|
|
"step": 7245
|
|
},
|
|
{
|
|
"entropy": 5.73533787727356,
|
|
"epoch": 0.5640925889904688,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.00049733891481768,
|
|
"loss": 5.6577,
|
|
"mean_token_accuracy": 0.15306596606969833,
|
|
"num_tokens": 12580168.0,
|
|
"step": 7250
|
|
},
|
|
{
|
|
"entropy": 5.603563928604126,
|
|
"epoch": 0.5644816183621864,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004973346631272384,
|
|
"loss": 5.555,
|
|
"mean_token_accuracy": 0.15743908584117888,
|
|
"num_tokens": 12589843.0,
|
|
"step": 7255
|
|
},
|
|
{
|
|
"entropy": 5.709521913528443,
|
|
"epoch": 0.5648706477339039,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004973304080632222,
|
|
"loss": 5.6121,
|
|
"mean_token_accuracy": 0.15040622875094414,
|
|
"num_tokens": 12598219.0,
|
|
"step": 7260
|
|
},
|
|
{
|
|
"entropy": 5.6934057712554935,
|
|
"epoch": 0.5652596771056215,
|
|
"grad_norm": 2.375,
|
|
"learning_rate": 0.000497326149625696,
|
|
"loss": 5.5799,
|
|
"mean_token_accuracy": 0.1590030699968338,
|
|
"num_tokens": 12606665.0,
|
|
"step": 7265
|
|
},
|
|
{
|
|
"entropy": 5.669231653213501,
|
|
"epoch": 0.565648706477339,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004973218878147244,
|
|
"loss": 5.4977,
|
|
"mean_token_accuracy": 0.1618253543972969,
|
|
"num_tokens": 12615062.0,
|
|
"step": 7270
|
|
},
|
|
{
|
|
"entropy": 5.755176973342896,
|
|
"epoch": 0.5660377358490566,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004973176226303719,
|
|
"loss": 5.601,
|
|
"mean_token_accuracy": 0.15456392467021943,
|
|
"num_tokens": 12623923.0,
|
|
"step": 7275
|
|
},
|
|
{
|
|
"entropy": 5.64637393951416,
|
|
"epoch": 0.5664267652207742,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004973133540727033,
|
|
"loss": 5.5055,
|
|
"mean_token_accuracy": 0.1566670298576355,
|
|
"num_tokens": 12632579.0,
|
|
"step": 7280
|
|
},
|
|
{
|
|
"entropy": 5.648503541946411,
|
|
"epoch": 0.5668157945924918,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004973090821417835,
|
|
"loss": 5.4891,
|
|
"mean_token_accuracy": 0.1574890896677971,
|
|
"num_tokens": 12640847.0,
|
|
"step": 7285
|
|
},
|
|
{
|
|
"entropy": 5.654255819320679,
|
|
"epoch": 0.5672048239642093,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004973048068376772,
|
|
"loss": 5.4626,
|
|
"mean_token_accuracy": 0.16273824572563172,
|
|
"num_tokens": 12649020.0,
|
|
"step": 7290
|
|
},
|
|
{
|
|
"entropy": 5.480013275146485,
|
|
"epoch": 0.5675938533359268,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004973005281604492,
|
|
"loss": 5.4124,
|
|
"mean_token_accuracy": 0.16097676753997803,
|
|
"num_tokens": 12657569.0,
|
|
"step": 7295
|
|
},
|
|
{
|
|
"entropy": 5.701761722564697,
|
|
"epoch": 0.5679828827076444,
|
|
"grad_norm": 1.875,
|
|
"learning_rate": 0.0004972962461101646,
|
|
"loss": 5.6756,
|
|
"mean_token_accuracy": 0.14673136174678802,
|
|
"num_tokens": 12666681.0,
|
|
"step": 7300
|
|
},
|
|
{
|
|
"entropy": 5.677568054199218,
|
|
"epoch": 0.568371912079362,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.0004972919606868883,
|
|
"loss": 5.4855,
|
|
"mean_token_accuracy": 0.15889087915420533,
|
|
"num_tokens": 12675210.0,
|
|
"step": 7305
|
|
},
|
|
{
|
|
"entropy": 5.615791654586792,
|
|
"epoch": 0.5687609414510796,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004972876718906852,
|
|
"loss": 5.537,
|
|
"mean_token_accuracy": 0.1522613376379013,
|
|
"num_tokens": 12684019.0,
|
|
"step": 7310
|
|
},
|
|
{
|
|
"entropy": 5.593216037750244,
|
|
"epoch": 0.5691499708227972,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004972833797216206,
|
|
"loss": 5.5584,
|
|
"mean_token_accuracy": 0.15070008486509323,
|
|
"num_tokens": 12692891.0,
|
|
"step": 7315
|
|
},
|
|
{
|
|
"entropy": 5.66307430267334,
|
|
"epoch": 0.5695390001945146,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004972790841797595,
|
|
"loss": 5.4788,
|
|
"mean_token_accuracy": 0.1566777989268303,
|
|
"num_tokens": 12700606.0,
|
|
"step": 7320
|
|
},
|
|
{
|
|
"entropy": 5.605720949172974,
|
|
"epoch": 0.5699280295662322,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.000497274785265167,
|
|
"loss": 5.5782,
|
|
"mean_token_accuracy": 0.15317728072404863,
|
|
"num_tokens": 12709116.0,
|
|
"step": 7325
|
|
},
|
|
{
|
|
"entropy": 5.630136728286743,
|
|
"epoch": 0.5703170589379498,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004972704829779086,
|
|
"loss": 5.497,
|
|
"mean_token_accuracy": 0.16416667252779008,
|
|
"num_tokens": 12717484.0,
|
|
"step": 7330
|
|
},
|
|
{
|
|
"entropy": 5.548515129089355,
|
|
"epoch": 0.5707060883096674,
|
|
"grad_norm": 1.8515625,
|
|
"learning_rate": 0.0004972661773180492,
|
|
"loss": 5.4543,
|
|
"mean_token_accuracy": 0.16415228471159934,
|
|
"num_tokens": 12726216.0,
|
|
"step": 7335
|
|
},
|
|
{
|
|
"entropy": 5.616742515563965,
|
|
"epoch": 0.571095117681385,
|
|
"grad_norm": 1.90625,
|
|
"learning_rate": 0.0004972618682856545,
|
|
"loss": 5.468,
|
|
"mean_token_accuracy": 0.1636758416891098,
|
|
"num_tokens": 12735312.0,
|
|
"step": 7340
|
|
},
|
|
{
|
|
"entropy": 5.625062084197998,
|
|
"epoch": 0.5714841470531025,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004972575558807896,
|
|
"loss": 5.5898,
|
|
"mean_token_accuracy": 0.15392533540725709,
|
|
"num_tokens": 12744641.0,
|
|
"step": 7345
|
|
},
|
|
{
|
|
"entropy": 5.64231243133545,
|
|
"epoch": 0.57187317642482,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004972532401035201,
|
|
"loss": 5.5423,
|
|
"mean_token_accuracy": 0.1595461830496788,
|
|
"num_tokens": 12753951.0,
|
|
"step": 7350
|
|
},
|
|
{
|
|
"entropy": 5.682752513885498,
|
|
"epoch": 0.5722622057965376,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004972489209539114,
|
|
"loss": 5.5471,
|
|
"mean_token_accuracy": 0.1579516515135765,
|
|
"num_tokens": 12762571.0,
|
|
"step": 7355
|
|
},
|
|
{
|
|
"entropy": 5.660006332397461,
|
|
"epoch": 0.5726512351682552,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004972445984320292,
|
|
"loss": 5.6203,
|
|
"mean_token_accuracy": 0.16043269485235215,
|
|
"num_tokens": 12771275.0,
|
|
"step": 7360
|
|
},
|
|
{
|
|
"entropy": 5.663341617584228,
|
|
"epoch": 0.5730402645399728,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.0004972402725379388,
|
|
"loss": 5.5241,
|
|
"mean_token_accuracy": 0.15962804704904557,
|
|
"num_tokens": 12780488.0,
|
|
"step": 7365
|
|
},
|
|
{
|
|
"entropy": 5.683029413223267,
|
|
"epoch": 0.5734292939116903,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.000497235943271706,
|
|
"loss": 5.5512,
|
|
"mean_token_accuracy": 0.1618207685649395,
|
|
"num_tokens": 12788588.0,
|
|
"step": 7370
|
|
},
|
|
{
|
|
"entropy": 5.579796695709229,
|
|
"epoch": 0.5738183232834079,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004972316106333966,
|
|
"loss": 5.4978,
|
|
"mean_token_accuracy": 0.15558528602123262,
|
|
"num_tokens": 12797010.0,
|
|
"step": 7375
|
|
},
|
|
{
|
|
"entropy": 5.636358070373535,
|
|
"epoch": 0.5742073526551255,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.0004972272746230761,
|
|
"loss": 5.5951,
|
|
"mean_token_accuracy": 0.16071680337190627,
|
|
"num_tokens": 12805430.0,
|
|
"step": 7380
|
|
},
|
|
{
|
|
"entropy": 5.728164339065552,
|
|
"epoch": 0.574596382026843,
|
|
"grad_norm": 3.671875,
|
|
"learning_rate": 0.0004972229352408104,
|
|
"loss": 5.5594,
|
|
"mean_token_accuracy": 0.15541741102933884,
|
|
"num_tokens": 12813912.0,
|
|
"step": 7385
|
|
},
|
|
{
|
|
"entropy": 5.724589252471924,
|
|
"epoch": 0.5749854113985606,
|
|
"grad_norm": 2.6875,
|
|
"learning_rate": 0.0004972185924866655,
|
|
"loss": 5.5698,
|
|
"mean_token_accuracy": 0.1507866822183132,
|
|
"num_tokens": 12822421.0,
|
|
"step": 7390
|
|
},
|
|
{
|
|
"entropy": 5.577664518356324,
|
|
"epoch": 0.5753744407702781,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004972142463607071,
|
|
"loss": 5.451,
|
|
"mean_token_accuracy": 0.15760032534599305,
|
|
"num_tokens": 12830670.0,
|
|
"step": 7395
|
|
},
|
|
{
|
|
"entropy": 5.6341667652130125,
|
|
"epoch": 0.5757634701419957,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004972098968630012,
|
|
"loss": 5.5706,
|
|
"mean_token_accuracy": 0.15929183810949327,
|
|
"num_tokens": 12839887.0,
|
|
"step": 7400
|
|
},
|
|
{
|
|
"entropy": 5.58133602142334,
|
|
"epoch": 0.5761524995137133,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004972055439936137,
|
|
"loss": 5.4801,
|
|
"mean_token_accuracy": 0.16356320977210997,
|
|
"num_tokens": 12848028.0,
|
|
"step": 7405
|
|
},
|
|
{
|
|
"entropy": 5.590980958938599,
|
|
"epoch": 0.5765415288854309,
|
|
"grad_norm": 1.875,
|
|
"learning_rate": 0.0004972011877526109,
|
|
"loss": 5.4861,
|
|
"mean_token_accuracy": 0.15774858146905898,
|
|
"num_tokens": 12857248.0,
|
|
"step": 7410
|
|
},
|
|
{
|
|
"entropy": 5.666098880767822,
|
|
"epoch": 0.5769305582571485,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004971968281400587,
|
|
"loss": 5.4913,
|
|
"mean_token_accuracy": 0.16380030661821365,
|
|
"num_tokens": 12866352.0,
|
|
"step": 7415
|
|
},
|
|
{
|
|
"entropy": 5.647558641433716,
|
|
"epoch": 0.5773195876288659,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004971924651560233,
|
|
"loss": 5.5769,
|
|
"mean_token_accuracy": 0.1545090951025486,
|
|
"num_tokens": 12874548.0,
|
|
"step": 7420
|
|
},
|
|
{
|
|
"entropy": 5.662309646606445,
|
|
"epoch": 0.5777086170005835,
|
|
"grad_norm": 1.875,
|
|
"learning_rate": 0.0004971880988005709,
|
|
"loss": 5.4354,
|
|
"mean_token_accuracy": 0.16391527503728867,
|
|
"num_tokens": 12883172.0,
|
|
"step": 7425
|
|
},
|
|
{
|
|
"entropy": 5.51320219039917,
|
|
"epoch": 0.5780976463723011,
|
|
"grad_norm": 2.28125,
|
|
"learning_rate": 0.0004971837290737677,
|
|
"loss": 5.4937,
|
|
"mean_token_accuracy": 0.16112108379602433,
|
|
"num_tokens": 12891776.0,
|
|
"step": 7430
|
|
},
|
|
{
|
|
"entropy": 5.5713831901550295,
|
|
"epoch": 0.5784866757440187,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004971793559756801,
|
|
"loss": 5.4468,
|
|
"mean_token_accuracy": 0.16626273095607758,
|
|
"num_tokens": 12900530.0,
|
|
"step": 7435
|
|
},
|
|
{
|
|
"entropy": 5.6204736709594725,
|
|
"epoch": 0.5788757051157363,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004971749795063744,
|
|
"loss": 5.4906,
|
|
"mean_token_accuracy": 0.15834079533815384,
|
|
"num_tokens": 12909260.0,
|
|
"step": 7440
|
|
},
|
|
{
|
|
"entropy": 5.674386644363404,
|
|
"epoch": 0.5792647344874537,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.000497170599665917,
|
|
"loss": 5.463,
|
|
"mean_token_accuracy": 0.15851330906152725,
|
|
"num_tokens": 12918143.0,
|
|
"step": 7445
|
|
},
|
|
{
|
|
"entropy": 5.662165832519531,
|
|
"epoch": 0.5796537638591713,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004971662164543743,
|
|
"loss": 5.5472,
|
|
"mean_token_accuracy": 0.16198030710220337,
|
|
"num_tokens": 12926361.0,
|
|
"step": 7450
|
|
},
|
|
{
|
|
"entropy": 5.559260606765747,
|
|
"epoch": 0.5800427932308889,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.0004971618298718131,
|
|
"loss": 5.466,
|
|
"mean_token_accuracy": 0.16223221719264985,
|
|
"num_tokens": 12935080.0,
|
|
"step": 7455
|
|
},
|
|
{
|
|
"entropy": 5.643280172348023,
|
|
"epoch": 0.5804318226026065,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004971574399182995,
|
|
"loss": 5.6291,
|
|
"mean_token_accuracy": 0.15445849448442459,
|
|
"num_tokens": 12944078.0,
|
|
"step": 7460
|
|
},
|
|
{
|
|
"entropy": 5.653989934921265,
|
|
"epoch": 0.5808208519743241,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004971530465939005,
|
|
"loss": 5.5499,
|
|
"mean_token_accuracy": 0.15607427209615707,
|
|
"num_tokens": 12952800.0,
|
|
"step": 7465
|
|
},
|
|
{
|
|
"entropy": 5.728119134902954,
|
|
"epoch": 0.5812098813460417,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0004971486498986825,
|
|
"loss": 5.6295,
|
|
"mean_token_accuracy": 0.15064105689525603,
|
|
"num_tokens": 12962402.0,
|
|
"step": 7470
|
|
},
|
|
{
|
|
"entropy": 5.6236701011657715,
|
|
"epoch": 0.5815989107177592,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004971442498327124,
|
|
"loss": 5.4158,
|
|
"mean_token_accuracy": 0.16757138669490815,
|
|
"num_tokens": 12971116.0,
|
|
"step": 7475
|
|
},
|
|
{
|
|
"entropy": 5.58604884147644,
|
|
"epoch": 0.5819879400894767,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004971398463960568,
|
|
"loss": 5.5007,
|
|
"mean_token_accuracy": 0.1532836765050888,
|
|
"num_tokens": 12979570.0,
|
|
"step": 7480
|
|
},
|
|
{
|
|
"entropy": 5.669705057144165,
|
|
"epoch": 0.5823769694611943,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.0004971354395887827,
|
|
"loss": 5.5305,
|
|
"mean_token_accuracy": 0.1630375012755394,
|
|
"num_tokens": 12987942.0,
|
|
"step": 7485
|
|
},
|
|
{
|
|
"entropy": 5.637955856323242,
|
|
"epoch": 0.5827659988329119,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004971310294109569,
|
|
"loss": 5.5889,
|
|
"mean_token_accuracy": 0.15620096027851105,
|
|
"num_tokens": 12996499.0,
|
|
"step": 7490
|
|
},
|
|
{
|
|
"entropy": 5.621541118621826,
|
|
"epoch": 0.5831550282046295,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004971266158626461,
|
|
"loss": 5.5192,
|
|
"mean_token_accuracy": 0.1607734739780426,
|
|
"num_tokens": 13005622.0,
|
|
"step": 7495
|
|
},
|
|
{
|
|
"entropy": 5.653079891204834,
|
|
"epoch": 0.583544057576347,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.0004971221989439177,
|
|
"loss": 5.5334,
|
|
"mean_token_accuracy": 0.15359631478786467,
|
|
"num_tokens": 13014417.0,
|
|
"step": 7500
|
|
},
|
|
{
|
|
"entropy": 5.633698415756226,
|
|
"epoch": 0.5839330869480646,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004971177786548384,
|
|
"loss": 5.4605,
|
|
"mean_token_accuracy": 0.1590988278388977,
|
|
"num_tokens": 13022887.0,
|
|
"step": 7505
|
|
},
|
|
{
|
|
"entropy": 5.63294472694397,
|
|
"epoch": 0.5843221163197821,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004971133549954753,
|
|
"loss": 5.5675,
|
|
"mean_token_accuracy": 0.15792251974344254,
|
|
"num_tokens": 13031676.0,
|
|
"step": 7510
|
|
},
|
|
{
|
|
"entropy": 5.633120727539063,
|
|
"epoch": 0.5847111456914997,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.0004971089279658954,
|
|
"loss": 5.5238,
|
|
"mean_token_accuracy": 0.15790767222642899,
|
|
"num_tokens": 13040489.0,
|
|
"step": 7515
|
|
},
|
|
{
|
|
"entropy": 5.598013067245484,
|
|
"epoch": 0.5851001750632173,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004971044975661663,
|
|
"loss": 5.4431,
|
|
"mean_token_accuracy": 0.1560145914554596,
|
|
"num_tokens": 13048280.0,
|
|
"step": 7520
|
|
},
|
|
{
|
|
"entropy": 5.569012546539307,
|
|
"epoch": 0.5854892044349348,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004971000637963549,
|
|
"loss": 5.4219,
|
|
"mean_token_accuracy": 0.1682547613978386,
|
|
"num_tokens": 13056471.0,
|
|
"step": 7525
|
|
},
|
|
{
|
|
"entropy": 5.678000593185425,
|
|
"epoch": 0.5858782338066524,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.0004970956266565285,
|
|
"loss": 5.5974,
|
|
"mean_token_accuracy": 0.157860104739666,
|
|
"num_tokens": 13065289.0,
|
|
"step": 7530
|
|
},
|
|
{
|
|
"entropy": 5.699495935440064,
|
|
"epoch": 0.58626726317837,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004970911861467544,
|
|
"loss": 5.6258,
|
|
"mean_token_accuracy": 0.1569194346666336,
|
|
"num_tokens": 13073648.0,
|
|
"step": 7535
|
|
},
|
|
{
|
|
"entropy": 5.620066928863525,
|
|
"epoch": 0.5866562925500876,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004970867422671002,
|
|
"loss": 5.6277,
|
|
"mean_token_accuracy": 0.1613432765007019,
|
|
"num_tokens": 13082205.0,
|
|
"step": 7540
|
|
},
|
|
{
|
|
"entropy": 5.715727376937866,
|
|
"epoch": 0.5870453219218051,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.000497082295017633,
|
|
"loss": 5.4943,
|
|
"mean_token_accuracy": 0.15655620396137238,
|
|
"num_tokens": 13090970.0,
|
|
"step": 7545
|
|
},
|
|
{
|
|
"entropy": 5.6958287239074705,
|
|
"epoch": 0.5874343512935226,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004970778443984206,
|
|
"loss": 5.4117,
|
|
"mean_token_accuracy": 0.16782016009092332,
|
|
"num_tokens": 13098290.0,
|
|
"step": 7550
|
|
},
|
|
{
|
|
"entropy": 5.5419275760650635,
|
|
"epoch": 0.5878233806652402,
|
|
"grad_norm": 3.015625,
|
|
"learning_rate": 0.0004970733904095303,
|
|
"loss": 5.3869,
|
|
"mean_token_accuracy": 0.1684104695916176,
|
|
"num_tokens": 13106971.0,
|
|
"step": 7555
|
|
},
|
|
{
|
|
"entropy": 5.7066200256347654,
|
|
"epoch": 0.5882124100369578,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004970689330510298,
|
|
"loss": 5.6556,
|
|
"mean_token_accuracy": 0.15344583094120026,
|
|
"num_tokens": 13115742.0,
|
|
"step": 7560
|
|
},
|
|
{
|
|
"entropy": 5.675275468826294,
|
|
"epoch": 0.5886014394086754,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 0.0004970644723229868,
|
|
"loss": 5.6122,
|
|
"mean_token_accuracy": 0.1583535112440586,
|
|
"num_tokens": 13124192.0,
|
|
"step": 7565
|
|
},
|
|
{
|
|
"entropy": 5.657108974456787,
|
|
"epoch": 0.588990468780393,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004970600082254687,
|
|
"loss": 5.4445,
|
|
"mean_token_accuracy": 0.16011936068534852,
|
|
"num_tokens": 13133510.0,
|
|
"step": 7570
|
|
},
|
|
{
|
|
"entropy": 5.5871819972991945,
|
|
"epoch": 0.5893794981521104,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0004970555407585436,
|
|
"loss": 5.558,
|
|
"mean_token_accuracy": 0.1549673855304718,
|
|
"num_tokens": 13141704.0,
|
|
"step": 7575
|
|
},
|
|
{
|
|
"entropy": 5.4972978115081785,
|
|
"epoch": 0.589768527523828,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.000497051069922279,
|
|
"loss": 5.4354,
|
|
"mean_token_accuracy": 0.1562228761613369,
|
|
"num_tokens": 13150559.0,
|
|
"step": 7580
|
|
},
|
|
{
|
|
"entropy": 5.580500984191895,
|
|
"epoch": 0.5901575568955456,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004970465957167429,
|
|
"loss": 5.4949,
|
|
"mean_token_accuracy": 0.16270770579576493,
|
|
"num_tokens": 13159428.0,
|
|
"step": 7585
|
|
},
|
|
{
|
|
"entropy": 5.641658735275269,
|
|
"epoch": 0.5905465862672632,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.000497042118142003,
|
|
"loss": 5.6357,
|
|
"mean_token_accuracy": 0.15142156556248665,
|
|
"num_tokens": 13168299.0,
|
|
"step": 7590
|
|
},
|
|
{
|
|
"entropy": 5.593786144256592,
|
|
"epoch": 0.5909356156389808,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004970376371981275,
|
|
"loss": 5.4946,
|
|
"mean_token_accuracy": 0.16250490695238112,
|
|
"num_tokens": 13176906.0,
|
|
"step": 7595
|
|
},
|
|
{
|
|
"entropy": 5.696356105804443,
|
|
"epoch": 0.5913246450106983,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.0004970331528851842,
|
|
"loss": 5.6068,
|
|
"mean_token_accuracy": 0.15478727519512175,
|
|
"num_tokens": 13186180.0,
|
|
"step": 7600
|
|
},
|
|
{
|
|
"entropy": 5.615195655822754,
|
|
"epoch": 0.5917136743824158,
|
|
"grad_norm": 1.875,
|
|
"learning_rate": 0.0004970286652032412,
|
|
"loss": 5.437,
|
|
"mean_token_accuracy": 0.1628949835896492,
|
|
"num_tokens": 13195111.0,
|
|
"step": 7605
|
|
},
|
|
{
|
|
"entropy": 5.627978420257568,
|
|
"epoch": 0.5921027037541334,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.0004970241741523667,
|
|
"loss": 5.4988,
|
|
"mean_token_accuracy": 0.1577683761715889,
|
|
"num_tokens": 13204170.0,
|
|
"step": 7610
|
|
},
|
|
{
|
|
"entropy": 5.648256111145019,
|
|
"epoch": 0.592491733125851,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.0004970196797326286,
|
|
"loss": 5.5127,
|
|
"mean_token_accuracy": 0.15796152353286744,
|
|
"num_tokens": 13213479.0,
|
|
"step": 7615
|
|
},
|
|
{
|
|
"entropy": 5.647126388549805,
|
|
"epoch": 0.5928807624975686,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004970151819440955,
|
|
"loss": 5.5521,
|
|
"mean_token_accuracy": 0.1582399308681488,
|
|
"num_tokens": 13222182.0,
|
|
"step": 7620
|
|
},
|
|
{
|
|
"entropy": 5.540087509155273,
|
|
"epoch": 0.5932697918692861,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004970106807868351,
|
|
"loss": 5.416,
|
|
"mean_token_accuracy": 0.16221292912960053,
|
|
"num_tokens": 13230681.0,
|
|
"step": 7625
|
|
},
|
|
{
|
|
"entropy": 5.702774858474731,
|
|
"epoch": 0.5936588212410037,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.000497006176260916,
|
|
"loss": 5.6049,
|
|
"mean_token_accuracy": 0.15711014419794084,
|
|
"num_tokens": 13239254.0,
|
|
"step": 7630
|
|
},
|
|
{
|
|
"entropy": 5.582187366485596,
|
|
"epoch": 0.5940478506127213,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004970016683664068,
|
|
"loss": 5.4589,
|
|
"mean_token_accuracy": 0.1659811370074749,
|
|
"num_tokens": 13248317.0,
|
|
"step": 7635
|
|
},
|
|
{
|
|
"entropy": 5.6564781188964846,
|
|
"epoch": 0.5944368799844388,
|
|
"grad_norm": 1.9375,
|
|
"learning_rate": 0.0004969971571033754,
|
|
"loss": 5.5323,
|
|
"mean_token_accuracy": 0.15865378230810165,
|
|
"num_tokens": 13256977.0,
|
|
"step": 7640
|
|
},
|
|
{
|
|
"entropy": 5.671256971359253,
|
|
"epoch": 0.5948259093561564,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.0004969926424718906,
|
|
"loss": 5.5964,
|
|
"mean_token_accuracy": 0.16032464653253556,
|
|
"num_tokens": 13266012.0,
|
|
"step": 7645
|
|
},
|
|
{
|
|
"entropy": 5.714561033248901,
|
|
"epoch": 0.5952149387278739,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004969881244720207,
|
|
"loss": 5.625,
|
|
"mean_token_accuracy": 0.15944082736968995,
|
|
"num_tokens": 13275248.0,
|
|
"step": 7650
|
|
},
|
|
{
|
|
"entropy": 5.620053148269653,
|
|
"epoch": 0.5956039680995915,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004969836031038343,
|
|
"loss": 5.452,
|
|
"mean_token_accuracy": 0.1548725590109825,
|
|
"num_tokens": 13284235.0,
|
|
"step": 7655
|
|
},
|
|
{
|
|
"entropy": 5.629696273803711,
|
|
"epoch": 0.5959929974713091,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004969790783674002,
|
|
"loss": 5.5463,
|
|
"mean_token_accuracy": 0.15149156898260116,
|
|
"num_tokens": 13292423.0,
|
|
"step": 7660
|
|
},
|
|
{
|
|
"entropy": 5.651600980758667,
|
|
"epoch": 0.5963820268430267,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004969745502627868,
|
|
"loss": 5.5862,
|
|
"mean_token_accuracy": 0.15504664331674575,
|
|
"num_tokens": 13300936.0,
|
|
"step": 7665
|
|
},
|
|
{
|
|
"entropy": 5.570025300979614,
|
|
"epoch": 0.5967710562147442,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004969700187900629,
|
|
"loss": 5.387,
|
|
"mean_token_accuracy": 0.17372642755508422,
|
|
"num_tokens": 13308881.0,
|
|
"step": 7670
|
|
},
|
|
{
|
|
"entropy": 5.662284421920776,
|
|
"epoch": 0.5971600855864618,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004969654839492973,
|
|
"loss": 5.5651,
|
|
"mean_token_accuracy": 0.1568134069442749,
|
|
"num_tokens": 13317864.0,
|
|
"step": 7675
|
|
},
|
|
{
|
|
"entropy": 5.648973703384399,
|
|
"epoch": 0.5975491149581793,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.0004969609457405588,
|
|
"loss": 5.5279,
|
|
"mean_token_accuracy": 0.15506339222192764,
|
|
"num_tokens": 13326990.0,
|
|
"step": 7680
|
|
},
|
|
{
|
|
"entropy": 5.754145956039428,
|
|
"epoch": 0.5979381443298969,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004969564041639163,
|
|
"loss": 5.7012,
|
|
"mean_token_accuracy": 0.14814776554703712,
|
|
"num_tokens": 13336437.0,
|
|
"step": 7685
|
|
},
|
|
{
|
|
"entropy": 5.663251733779907,
|
|
"epoch": 0.5983271737016145,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004969518592194386,
|
|
"loss": 5.5312,
|
|
"mean_token_accuracy": 0.15718320161104202,
|
|
"num_tokens": 13345368.0,
|
|
"step": 7690
|
|
},
|
|
{
|
|
"entropy": 5.565625238418579,
|
|
"epoch": 0.5987162030733321,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004969473109071946,
|
|
"loss": 5.5522,
|
|
"mean_token_accuracy": 0.1609119489789009,
|
|
"num_tokens": 13354171.0,
|
|
"step": 7695
|
|
},
|
|
{
|
|
"entropy": 5.715798997879029,
|
|
"epoch": 0.5991052324450497,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004969427592272535,
|
|
"loss": 5.5771,
|
|
"mean_token_accuracy": 0.15664048567414285,
|
|
"num_tokens": 13362912.0,
|
|
"step": 7700
|
|
},
|
|
{
|
|
"entropy": 5.6679292678833,
|
|
"epoch": 0.5994942618167671,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004969382041796843,
|
|
"loss": 5.4632,
|
|
"mean_token_accuracy": 0.1576875314116478,
|
|
"num_tokens": 13370913.0,
|
|
"step": 7705
|
|
},
|
|
{
|
|
"entropy": 5.60019097328186,
|
|
"epoch": 0.5998832911884847,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.000496933645764556,
|
|
"loss": 5.6154,
|
|
"mean_token_accuracy": 0.1539946123957634,
|
|
"num_tokens": 13379557.0,
|
|
"step": 7710
|
|
},
|
|
{
|
|
"entropy": 5.65548791885376,
|
|
"epoch": 0.6002723205602023,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004969290839819381,
|
|
"loss": 5.5184,
|
|
"mean_token_accuracy": 0.16378386318683624,
|
|
"num_tokens": 13388129.0,
|
|
"step": 7715
|
|
},
|
|
{
|
|
"entropy": 5.711482954025269,
|
|
"epoch": 0.6006613499319199,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004969245188318994,
|
|
"loss": 5.6423,
|
|
"mean_token_accuracy": 0.15548501312732696,
|
|
"num_tokens": 13396713.0,
|
|
"step": 7720
|
|
},
|
|
{
|
|
"entropy": 5.681234216690063,
|
|
"epoch": 0.6010503793036375,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004969199503145093,
|
|
"loss": 5.5844,
|
|
"mean_token_accuracy": 0.15729426443576813,
|
|
"num_tokens": 13406171.0,
|
|
"step": 7725
|
|
},
|
|
{
|
|
"entropy": 5.602319955825806,
|
|
"epoch": 0.601439408675355,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.0004969153784298374,
|
|
"loss": 5.4834,
|
|
"mean_token_accuracy": 0.16185905635356904,
|
|
"num_tokens": 13415107.0,
|
|
"step": 7730
|
|
},
|
|
{
|
|
"entropy": 5.555932092666626,
|
|
"epoch": 0.6018284380470725,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004969108031779527,
|
|
"loss": 5.5917,
|
|
"mean_token_accuracy": 0.15284654945135118,
|
|
"num_tokens": 13423533.0,
|
|
"step": 7735
|
|
},
|
|
{
|
|
"entropy": 5.698648691177368,
|
|
"epoch": 0.6022174674187901,
|
|
"grad_norm": 2.359375,
|
|
"learning_rate": 0.0004969062245589247,
|
|
"loss": 5.5681,
|
|
"mean_token_accuracy": 0.1539204865694046,
|
|
"num_tokens": 13432798.0,
|
|
"step": 7740
|
|
},
|
|
{
|
|
"entropy": 5.73698673248291,
|
|
"epoch": 0.6026064967905077,
|
|
"grad_norm": 1.890625,
|
|
"learning_rate": 0.0004969016425728231,
|
|
"loss": 5.5235,
|
|
"mean_token_accuracy": 0.1647236555814743,
|
|
"num_tokens": 13441123.0,
|
|
"step": 7745
|
|
},
|
|
{
|
|
"entropy": 5.560197257995606,
|
|
"epoch": 0.6029955261622253,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004968970572197172,
|
|
"loss": 5.4421,
|
|
"mean_token_accuracy": 0.16674410104751586,
|
|
"num_tokens": 13449548.0,
|
|
"step": 7750
|
|
},
|
|
{
|
|
"entropy": 5.62289719581604,
|
|
"epoch": 0.6033845555339428,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004968924684996765,
|
|
"loss": 5.5415,
|
|
"mean_token_accuracy": 0.1578146517276764,
|
|
"num_tokens": 13458022.0,
|
|
"step": 7755
|
|
},
|
|
{
|
|
"entropy": 5.602722597122193,
|
|
"epoch": 0.6037735849056604,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.000496887876412771,
|
|
"loss": 5.4922,
|
|
"mean_token_accuracy": 0.1603412702679634,
|
|
"num_tokens": 13466871.0,
|
|
"step": 7760
|
|
},
|
|
{
|
|
"entropy": 5.609094762802124,
|
|
"epoch": 0.6041626142773779,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004968832809590701,
|
|
"loss": 5.5337,
|
|
"mean_token_accuracy": 0.15866299122571945,
|
|
"num_tokens": 13475659.0,
|
|
"step": 7765
|
|
},
|
|
{
|
|
"entropy": 5.6732141971588135,
|
|
"epoch": 0.6045516436490955,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004968786821386435,
|
|
"loss": 5.539,
|
|
"mean_token_accuracy": 0.1558965489268303,
|
|
"num_tokens": 13484146.0,
|
|
"step": 7770
|
|
},
|
|
{
|
|
"entropy": 5.657039213180542,
|
|
"epoch": 0.6049406730208131,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004968740799515611,
|
|
"loss": 5.5473,
|
|
"mean_token_accuracy": 0.1569312885403633,
|
|
"num_tokens": 13492831.0,
|
|
"step": 7775
|
|
},
|
|
{
|
|
"entropy": 5.63938536643982,
|
|
"epoch": 0.6053297023925306,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004968694743978926,
|
|
"loss": 5.5335,
|
|
"mean_token_accuracy": 0.15908339470624924,
|
|
"num_tokens": 13501640.0,
|
|
"step": 7780
|
|
},
|
|
{
|
|
"entropy": 5.655659008026123,
|
|
"epoch": 0.6057187317642482,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004968648654777081,
|
|
"loss": 5.5259,
|
|
"mean_token_accuracy": 0.15935870930552481,
|
|
"num_tokens": 13509816.0,
|
|
"step": 7785
|
|
},
|
|
{
|
|
"entropy": 5.664575719833374,
|
|
"epoch": 0.6061077611359658,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.0004968602531910773,
|
|
"loss": 5.5854,
|
|
"mean_token_accuracy": 0.15632208436727524,
|
|
"num_tokens": 13518384.0,
|
|
"step": 7790
|
|
},
|
|
{
|
|
"entropy": 5.559035873413086,
|
|
"epoch": 0.6064967905076833,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004968556375380704,
|
|
"loss": 5.4399,
|
|
"mean_token_accuracy": 0.15988280028104782,
|
|
"num_tokens": 13527115.0,
|
|
"step": 7795
|
|
},
|
|
{
|
|
"entropy": 5.62734317779541,
|
|
"epoch": 0.6068858198794009,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004968510185187571,
|
|
"loss": 5.6659,
|
|
"mean_token_accuracy": 0.1577243313193321,
|
|
"num_tokens": 13535743.0,
|
|
"step": 7800
|
|
},
|
|
{
|
|
"entropy": 5.645373916625976,
|
|
"epoch": 0.6072748492511184,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.000496846396133208,
|
|
"loss": 5.4717,
|
|
"mean_token_accuracy": 0.16361497193574906,
|
|
"num_tokens": 13544167.0,
|
|
"step": 7805
|
|
},
|
|
{
|
|
"entropy": 5.65470404624939,
|
|
"epoch": 0.607663878622836,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0004968417703814928,
|
|
"loss": 5.5413,
|
|
"mean_token_accuracy": 0.15961019396781922,
|
|
"num_tokens": 13552291.0,
|
|
"step": 7810
|
|
},
|
|
{
|
|
"entropy": 5.658768939971924,
|
|
"epoch": 0.6080529079945536,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0004968371412636818,
|
|
"loss": 5.598,
|
|
"mean_token_accuracy": 0.15241592079401017,
|
|
"num_tokens": 13561185.0,
|
|
"step": 7815
|
|
},
|
|
{
|
|
"entropy": 5.680170726776123,
|
|
"epoch": 0.6084419373662712,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 0.0004968325087798453,
|
|
"loss": 5.4805,
|
|
"mean_token_accuracy": 0.16755058616399765,
|
|
"num_tokens": 13569815.0,
|
|
"step": 7820
|
|
},
|
|
{
|
|
"entropy": 5.645559692382813,
|
|
"epoch": 0.6088309667379888,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004968278729300536,
|
|
"loss": 5.5931,
|
|
"mean_token_accuracy": 0.1549022302031517,
|
|
"num_tokens": 13578882.0,
|
|
"step": 7825
|
|
},
|
|
{
|
|
"entropy": 5.5938530445098875,
|
|
"epoch": 0.6092199961097062,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004968232337143769,
|
|
"loss": 5.4606,
|
|
"mean_token_accuracy": 0.16442210376262664,
|
|
"num_tokens": 13587479.0,
|
|
"step": 7830
|
|
},
|
|
{
|
|
"entropy": 5.5308496952056885,
|
|
"epoch": 0.6096090254814238,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004968185911328858,
|
|
"loss": 5.368,
|
|
"mean_token_accuracy": 0.1584856018424034,
|
|
"num_tokens": 13596049.0,
|
|
"step": 7835
|
|
},
|
|
{
|
|
"entropy": 5.704044675827026,
|
|
"epoch": 0.6099980548531414,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004968139451856506,
|
|
"loss": 5.6346,
|
|
"mean_token_accuracy": 0.15484179705381393,
|
|
"num_tokens": 13604766.0,
|
|
"step": 7840
|
|
},
|
|
{
|
|
"entropy": 5.709261465072632,
|
|
"epoch": 0.610387084224859,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004968092958727419,
|
|
"loss": 5.5978,
|
|
"mean_token_accuracy": 0.15936251878738403,
|
|
"num_tokens": 13614051.0,
|
|
"step": 7845
|
|
},
|
|
{
|
|
"entropy": 5.57492094039917,
|
|
"epoch": 0.6107761135965766,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.00049680464319423,
|
|
"loss": 5.5471,
|
|
"mean_token_accuracy": 0.15839914828538895,
|
|
"num_tokens": 13623100.0,
|
|
"step": 7850
|
|
},
|
|
{
|
|
"entropy": 5.637682151794434,
|
|
"epoch": 0.6111651429682942,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.0004967999871501858,
|
|
"loss": 5.574,
|
|
"mean_token_accuracy": 0.16042812466621398,
|
|
"num_tokens": 13631732.0,
|
|
"step": 7855
|
|
},
|
|
{
|
|
"entropy": 5.680285310745239,
|
|
"epoch": 0.6115541723400116,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004967953277406798,
|
|
"loss": 5.5447,
|
|
"mean_token_accuracy": 0.1600274458527565,
|
|
"num_tokens": 13640355.0,
|
|
"step": 7860
|
|
},
|
|
{
|
|
"entropy": 5.679409170150757,
|
|
"epoch": 0.6119432017117292,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004967906649657828,
|
|
"loss": 5.6109,
|
|
"mean_token_accuracy": 0.15921020805835723,
|
|
"num_tokens": 13649108.0,
|
|
"step": 7865
|
|
},
|
|
{
|
|
"entropy": 5.611932373046875,
|
|
"epoch": 0.6123322310834468,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.0004967859988255655,
|
|
"loss": 5.4595,
|
|
"mean_token_accuracy": 0.17007074505090714,
|
|
"num_tokens": 13656765.0,
|
|
"step": 7870
|
|
},
|
|
{
|
|
"entropy": 5.622920560836792,
|
|
"epoch": 0.6127212604551644,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.0004967813293200985,
|
|
"loss": 5.5314,
|
|
"mean_token_accuracy": 0.15998297780752183,
|
|
"num_tokens": 13664692.0,
|
|
"step": 7875
|
|
},
|
|
{
|
|
"entropy": 5.509643507003784,
|
|
"epoch": 0.613110289826882,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004967766564494529,
|
|
"loss": 5.4134,
|
|
"mean_token_accuracy": 0.1656013548374176,
|
|
"num_tokens": 13672913.0,
|
|
"step": 7880
|
|
},
|
|
{
|
|
"entropy": 5.570711946487426,
|
|
"epoch": 0.6134993191985995,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.0004967719802136996,
|
|
"loss": 5.4076,
|
|
"mean_token_accuracy": 0.1669822558760643,
|
|
"num_tokens": 13682427.0,
|
|
"step": 7885
|
|
},
|
|
{
|
|
"entropy": 5.617518424987793,
|
|
"epoch": 0.613888348570317,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.0004967673006129094,
|
|
"loss": 5.51,
|
|
"mean_token_accuracy": 0.16002740561962128,
|
|
"num_tokens": 13690815.0,
|
|
"step": 7890
|
|
},
|
|
{
|
|
"entropy": 5.692722797393799,
|
|
"epoch": 0.6142773779420346,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0004967626176471536,
|
|
"loss": 5.6195,
|
|
"mean_token_accuracy": 0.15270492061972618,
|
|
"num_tokens": 13699522.0,
|
|
"step": 7895
|
|
},
|
|
{
|
|
"entropy": 5.734070205688477,
|
|
"epoch": 0.6146664073137522,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004967579313165028,
|
|
"loss": 5.6449,
|
|
"mean_token_accuracy": 0.15162678360939025,
|
|
"num_tokens": 13708075.0,
|
|
"step": 7900
|
|
},
|
|
{
|
|
"entropy": 5.660864686965942,
|
|
"epoch": 0.6150554366854698,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.0004967532416210284,
|
|
"loss": 5.5265,
|
|
"mean_token_accuracy": 0.15871732383966447,
|
|
"num_tokens": 13716397.0,
|
|
"step": 7905
|
|
},
|
|
{
|
|
"entropy": 5.586922693252563,
|
|
"epoch": 0.6154444660571873,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004967485485608016,
|
|
"loss": 5.5239,
|
|
"mean_token_accuracy": 0.15802053809165956,
|
|
"num_tokens": 13724724.0,
|
|
"step": 7910
|
|
},
|
|
{
|
|
"entropy": 5.649572563171387,
|
|
"epoch": 0.6158334954289049,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004967438521358934,
|
|
"loss": 5.4866,
|
|
"mean_token_accuracy": 0.16373735219240187,
|
|
"num_tokens": 13733389.0,
|
|
"step": 7915
|
|
},
|
|
{
|
|
"entropy": 5.595465278625488,
|
|
"epoch": 0.6162225248006225,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004967391523463754,
|
|
"loss": 5.4359,
|
|
"mean_token_accuracy": 0.16241636574268342,
|
|
"num_tokens": 13742569.0,
|
|
"step": 7920
|
|
},
|
|
{
|
|
"entropy": 5.5772239685058596,
|
|
"epoch": 0.61661155417234,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.0004967344491923185,
|
|
"loss": 5.4218,
|
|
"mean_token_accuracy": 0.16591064780950546,
|
|
"num_tokens": 13750975.0,
|
|
"step": 7925
|
|
},
|
|
{
|
|
"entropy": 5.563429355621338,
|
|
"epoch": 0.6170005835440576,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004967297426737943,
|
|
"loss": 5.4856,
|
|
"mean_token_accuracy": 0.1643957808613777,
|
|
"num_tokens": 13758782.0,
|
|
"step": 7930
|
|
},
|
|
{
|
|
"entropy": 5.668042898178101,
|
|
"epoch": 0.6173896129157751,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004967250327908742,
|
|
"loss": 5.6196,
|
|
"mean_token_accuracy": 0.14822143763303758,
|
|
"num_tokens": 13767321.0,
|
|
"step": 7935
|
|
},
|
|
{
|
|
"entropy": 5.691036033630371,
|
|
"epoch": 0.6177786422874927,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004967203195436297,
|
|
"loss": 5.5946,
|
|
"mean_token_accuracy": 0.16070252805948257,
|
|
"num_tokens": 13775992.0,
|
|
"step": 7940
|
|
},
|
|
{
|
|
"entropy": 5.633575963973999,
|
|
"epoch": 0.6181676716592103,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004967156029321322,
|
|
"loss": 5.4437,
|
|
"mean_token_accuracy": 0.16718493700027465,
|
|
"num_tokens": 13784358.0,
|
|
"step": 7945
|
|
},
|
|
{
|
|
"entropy": 5.593190431594849,
|
|
"epoch": 0.6185567010309279,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004967108829564532,
|
|
"loss": 5.4463,
|
|
"mean_token_accuracy": 0.1668060004711151,
|
|
"num_tokens": 13792834.0,
|
|
"step": 7950
|
|
},
|
|
{
|
|
"entropy": 5.646222639083862,
|
|
"epoch": 0.6189457304026454,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.0004967061596166646,
|
|
"loss": 5.5263,
|
|
"mean_token_accuracy": 0.1547102853655815,
|
|
"num_tokens": 13801414.0,
|
|
"step": 7955
|
|
},
|
|
{
|
|
"entropy": 5.640058898925782,
|
|
"epoch": 0.6193347597743629,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.0004967014329128378,
|
|
"loss": 5.5671,
|
|
"mean_token_accuracy": 0.1626493901014328,
|
|
"num_tokens": 13810459.0,
|
|
"step": 7960
|
|
},
|
|
{
|
|
"entropy": 5.6000128269195555,
|
|
"epoch": 0.6197237891460805,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004966967028450448,
|
|
"loss": 5.382,
|
|
"mean_token_accuracy": 0.17020908743143082,
|
|
"num_tokens": 13818460.0,
|
|
"step": 7965
|
|
},
|
|
{
|
|
"entropy": 5.5928339004516605,
|
|
"epoch": 0.6201128185177981,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.000496691969413357,
|
|
"loss": 5.528,
|
|
"mean_token_accuracy": 0.1588208943605423,
|
|
"num_tokens": 13827693.0,
|
|
"step": 7970
|
|
},
|
|
{
|
|
"entropy": 5.672547101974487,
|
|
"epoch": 0.6205018478895157,
|
|
"grad_norm": 1.9375,
|
|
"learning_rate": 0.0004966872326178466,
|
|
"loss": 5.5338,
|
|
"mean_token_accuracy": 0.15306152999401093,
|
|
"num_tokens": 13836506.0,
|
|
"step": 7975
|
|
},
|
|
{
|
|
"entropy": 5.672850656509399,
|
|
"epoch": 0.6208908772612333,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004966824924585851,
|
|
"loss": 5.5582,
|
|
"mean_token_accuracy": 0.1514398269355297,
|
|
"num_tokens": 13844977.0,
|
|
"step": 7980
|
|
},
|
|
{
|
|
"entropy": 5.626597213745117,
|
|
"epoch": 0.6212799066329507,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004966777489356448,
|
|
"loss": 5.5108,
|
|
"mean_token_accuracy": 0.15777090787887574,
|
|
"num_tokens": 13854514.0,
|
|
"step": 7985
|
|
},
|
|
{
|
|
"entropy": 5.607633590698242,
|
|
"epoch": 0.6216689360046683,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004966730020490975,
|
|
"loss": 5.5103,
|
|
"mean_token_accuracy": 0.1543690964579582,
|
|
"num_tokens": 13863037.0,
|
|
"step": 7990
|
|
},
|
|
{
|
|
"entropy": 5.600288200378418,
|
|
"epoch": 0.6220579653763859,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.000496668251799015,
|
|
"loss": 5.4816,
|
|
"mean_token_accuracy": 0.16558290272951126,
|
|
"num_tokens": 13871720.0,
|
|
"step": 7995
|
|
},
|
|
{
|
|
"entropy": 5.677790260314941,
|
|
"epoch": 0.6224469947481035,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.0004966634981854699,
|
|
"loss": 5.5383,
|
|
"mean_token_accuracy": 0.16763988882303238,
|
|
"num_tokens": 13880214.0,
|
|
"step": 8000
|
|
},
|
|
{
|
|
"entropy": 5.6742125988006595,
|
|
"epoch": 0.6228360241198211,
|
|
"grad_norm": 4.375,
|
|
"learning_rate": 0.0004966587412085339,
|
|
"loss": 5.6197,
|
|
"mean_token_accuracy": 0.1495073728263378,
|
|
"num_tokens": 13888784.0,
|
|
"step": 8005
|
|
},
|
|
{
|
|
"entropy": 5.703689241409302,
|
|
"epoch": 0.6232250534915386,
|
|
"grad_norm": 2.625,
|
|
"learning_rate": 0.0004966539808682793,
|
|
"loss": 5.5248,
|
|
"mean_token_accuracy": 0.15729485750198363,
|
|
"num_tokens": 13897466.0,
|
|
"step": 8010
|
|
},
|
|
{
|
|
"entropy": 5.565239477157593,
|
|
"epoch": 0.6236140828632561,
|
|
"grad_norm": 1.9765625,
|
|
"learning_rate": 0.0004966492171647783,
|
|
"loss": 5.5435,
|
|
"mean_token_accuracy": 0.15722897797822952,
|
|
"num_tokens": 13906556.0,
|
|
"step": 8015
|
|
},
|
|
{
|
|
"entropy": 5.549352598190308,
|
|
"epoch": 0.6240031122349737,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004966444500981032,
|
|
"loss": 5.4709,
|
|
"mean_token_accuracy": 0.1600986048579216,
|
|
"num_tokens": 13915473.0,
|
|
"step": 8020
|
|
},
|
|
{
|
|
"entropy": 5.702391815185547,
|
|
"epoch": 0.6243921416066913,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004966396796683265,
|
|
"loss": 5.6322,
|
|
"mean_token_accuracy": 0.15696300864219664,
|
|
"num_tokens": 13924775.0,
|
|
"step": 8025
|
|
},
|
|
{
|
|
"entropy": 5.7412676334381105,
|
|
"epoch": 0.6247811709784089,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.0004966349058755204,
|
|
"loss": 5.5199,
|
|
"mean_token_accuracy": 0.15458499491214753,
|
|
"num_tokens": 13933992.0,
|
|
"step": 8030
|
|
},
|
|
{
|
|
"entropy": 5.725110340118408,
|
|
"epoch": 0.6251702003501264,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.0004966301287197573,
|
|
"loss": 5.6825,
|
|
"mean_token_accuracy": 0.1565156638622284,
|
|
"num_tokens": 13942877.0,
|
|
"step": 8035
|
|
},
|
|
{
|
|
"entropy": 5.628981590270996,
|
|
"epoch": 0.625559229721844,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.0004966253482011098,
|
|
"loss": 5.5355,
|
|
"mean_token_accuracy": 0.15889608711004258,
|
|
"num_tokens": 13952003.0,
|
|
"step": 8040
|
|
},
|
|
{
|
|
"entropy": 5.719999551773071,
|
|
"epoch": 0.6259482590935616,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.0004966205643196503,
|
|
"loss": 5.4882,
|
|
"mean_token_accuracy": 0.16299010068178177,
|
|
"num_tokens": 13959801.0,
|
|
"step": 8045
|
|
},
|
|
{
|
|
"entropy": 5.589718627929687,
|
|
"epoch": 0.6263372884652791,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.0004966157770754516,
|
|
"loss": 5.4812,
|
|
"mean_token_accuracy": 0.15558162629604338,
|
|
"num_tokens": 13968535.0,
|
|
"step": 8050
|
|
},
|
|
{
|
|
"entropy": 5.6859715461730955,
|
|
"epoch": 0.6267263178369967,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.000496610986468586,
|
|
"loss": 5.4602,
|
|
"mean_token_accuracy": 0.16301203072071074,
|
|
"num_tokens": 13977079.0,
|
|
"step": 8055
|
|
},
|
|
{
|
|
"entropy": 5.607573413848877,
|
|
"epoch": 0.6271153472087143,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.0004966061924991267,
|
|
"loss": 5.4761,
|
|
"mean_token_accuracy": 0.16994809061288835,
|
|
"num_tokens": 13985118.0,
|
|
"step": 8060
|
|
},
|
|
{
|
|
"entropy": 5.565037870407105,
|
|
"epoch": 0.6275043765804318,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.000496601395167146,
|
|
"loss": 5.4372,
|
|
"mean_token_accuracy": 0.16356648206710817,
|
|
"num_tokens": 13994061.0,
|
|
"step": 8065
|
|
},
|
|
{
|
|
"entropy": 5.643871784210205,
|
|
"epoch": 0.6278934059521494,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.0004965965944727168,
|
|
"loss": 5.576,
|
|
"mean_token_accuracy": 0.15536743700504302,
|
|
"num_tokens": 14002879.0,
|
|
"step": 8070
|
|
},
|
|
{
|
|
"entropy": 5.688621950149536,
|
|
"epoch": 0.628282435323867,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.0004965917904159121,
|
|
"loss": 5.549,
|
|
"mean_token_accuracy": 0.15940080732107162,
|
|
"num_tokens": 14011570.0,
|
|
"step": 8075
|
|
},
|
|
{
|
|
"entropy": 5.5830262184143065,
|
|
"epoch": 0.6286714646955845,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004965869829968046,
|
|
"loss": 5.4017,
|
|
"mean_token_accuracy": 0.16647689491510392,
|
|
"num_tokens": 14019282.0,
|
|
"step": 8080
|
|
},
|
|
{
|
|
"entropy": 5.56063232421875,
|
|
"epoch": 0.6290604940673021,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 0.0004965821722154674,
|
|
"loss": 5.3969,
|
|
"mean_token_accuracy": 0.17424622774124146,
|
|
"num_tokens": 14027774.0,
|
|
"step": 8085
|
|
},
|
|
{
|
|
"entropy": 5.574239873886109,
|
|
"epoch": 0.6294495234390196,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004965773580719734,
|
|
"loss": 5.4117,
|
|
"mean_token_accuracy": 0.16344402283430098,
|
|
"num_tokens": 14036754.0,
|
|
"step": 8090
|
|
},
|
|
{
|
|
"entropy": 5.6545671939849855,
|
|
"epoch": 0.6298385528107372,
|
|
"grad_norm": 1.96875,
|
|
"learning_rate": 0.0004965725405663957,
|
|
"loss": 5.5941,
|
|
"mean_token_accuracy": 0.16004988849163054,
|
|
"num_tokens": 14045714.0,
|
|
"step": 8095
|
|
},
|
|
{
|
|
"entropy": 5.713851499557495,
|
|
"epoch": 0.6302275821824548,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004965677196988073,
|
|
"loss": 5.632,
|
|
"mean_token_accuracy": 0.15257349908351897,
|
|
"num_tokens": 14054973.0,
|
|
"step": 8100
|
|
},
|
|
{
|
|
"entropy": 5.625101852416992,
|
|
"epoch": 0.6306166115541724,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0004965628954692815,
|
|
"loss": 5.53,
|
|
"mean_token_accuracy": 0.1556107297539711,
|
|
"num_tokens": 14064037.0,
|
|
"step": 8105
|
|
},
|
|
{
|
|
"entropy": 5.600952816009522,
|
|
"epoch": 0.63100564092589,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004965580678778913,
|
|
"loss": 5.5492,
|
|
"mean_token_accuracy": 0.15927803218364717,
|
|
"num_tokens": 14072269.0,
|
|
"step": 8110
|
|
},
|
|
{
|
|
"entropy": 5.62748966217041,
|
|
"epoch": 0.6313946702976074,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004965532369247102,
|
|
"loss": 5.4841,
|
|
"mean_token_accuracy": 0.1578640028834343,
|
|
"num_tokens": 14080595.0,
|
|
"step": 8115
|
|
},
|
|
{
|
|
"entropy": 5.6428416728973385,
|
|
"epoch": 0.631783699669325,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.0004965484026098111,
|
|
"loss": 5.4563,
|
|
"mean_token_accuracy": 0.16344968378543853,
|
|
"num_tokens": 14089159.0,
|
|
"step": 8120
|
|
},
|
|
{
|
|
"entropy": 5.625972509384155,
|
|
"epoch": 0.6321727290410426,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.0004965435649332679,
|
|
"loss": 5.56,
|
|
"mean_token_accuracy": 0.15567976236343384,
|
|
"num_tokens": 14098192.0,
|
|
"step": 8125
|
|
},
|
|
{
|
|
"entropy": 5.599277305603027,
|
|
"epoch": 0.6325617584127602,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0004965387238951536,
|
|
"loss": 5.3668,
|
|
"mean_token_accuracy": 0.16741398572921753,
|
|
"num_tokens": 14106552.0,
|
|
"step": 8130
|
|
},
|
|
{
|
|
"entropy": 5.604122018814087,
|
|
"epoch": 0.6329507877844778,
|
|
"grad_norm": 1.875,
|
|
"learning_rate": 0.0004965338794955418,
|
|
"loss": 5.4456,
|
|
"mean_token_accuracy": 0.15920378565788268,
|
|
"num_tokens": 14114783.0,
|
|
"step": 8135
|
|
},
|
|
{
|
|
"entropy": 5.567695188522339,
|
|
"epoch": 0.6333398171561953,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004965290317345061,
|
|
"loss": 5.509,
|
|
"mean_token_accuracy": 0.154242904484272,
|
|
"num_tokens": 14124182.0,
|
|
"step": 8140
|
|
},
|
|
{
|
|
"entropy": 5.6882342338562015,
|
|
"epoch": 0.6337288465279128,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004965241806121198,
|
|
"loss": 5.5365,
|
|
"mean_token_accuracy": 0.1539142057299614,
|
|
"num_tokens": 14133037.0,
|
|
"step": 8145
|
|
},
|
|
{
|
|
"entropy": 5.678627157211304,
|
|
"epoch": 0.6341178758996304,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004965193261284567,
|
|
"loss": 5.4995,
|
|
"mean_token_accuracy": 0.16124187856912614,
|
|
"num_tokens": 14141677.0,
|
|
"step": 8150
|
|
},
|
|
{
|
|
"entropy": 5.606456184387207,
|
|
"epoch": 0.634506905271348,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.0004965144682835904,
|
|
"loss": 5.4704,
|
|
"mean_token_accuracy": 0.16963428109884263,
|
|
"num_tokens": 14149980.0,
|
|
"step": 8155
|
|
},
|
|
{
|
|
"entropy": 5.6169435501098635,
|
|
"epoch": 0.6348959346430656,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.0004965096070775946,
|
|
"loss": 5.5208,
|
|
"mean_token_accuracy": 0.16687773764133454,
|
|
"num_tokens": 14158298.0,
|
|
"step": 8160
|
|
},
|
|
{
|
|
"entropy": 5.672353506088257,
|
|
"epoch": 0.6352849640147831,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004965047425105431,
|
|
"loss": 5.4717,
|
|
"mean_token_accuracy": 0.17023685872554778,
|
|
"num_tokens": 14166321.0,
|
|
"step": 8165
|
|
},
|
|
{
|
|
"entropy": 5.5544921398162845,
|
|
"epoch": 0.6356739933865007,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004964998745825097,
|
|
"loss": 5.436,
|
|
"mean_token_accuracy": 0.16873080879449845,
|
|
"num_tokens": 14174619.0,
|
|
"step": 8170
|
|
},
|
|
{
|
|
"entropy": 5.608109426498413,
|
|
"epoch": 0.6360630227582182,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.0004964950032935682,
|
|
"loss": 5.4554,
|
|
"mean_token_accuracy": 0.16270688623189927,
|
|
"num_tokens": 14183548.0,
|
|
"step": 8175
|
|
},
|
|
{
|
|
"entropy": 5.751680660247803,
|
|
"epoch": 0.6364520521299358,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.0004964901286437927,
|
|
"loss": 5.6339,
|
|
"mean_token_accuracy": 0.15778876543045045,
|
|
"num_tokens": 14192306.0,
|
|
"step": 8180
|
|
},
|
|
{
|
|
"entropy": 5.590329885482788,
|
|
"epoch": 0.6368410815016534,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004964852506332568,
|
|
"loss": 5.3502,
|
|
"mean_token_accuracy": 0.1696975663304329,
|
|
"num_tokens": 14200280.0,
|
|
"step": 8185
|
|
},
|
|
{
|
|
"entropy": 5.592594766616822,
|
|
"epoch": 0.6372301108733709,
|
|
"grad_norm": 1.875,
|
|
"learning_rate": 0.000496480369262035,
|
|
"loss": 5.5858,
|
|
"mean_token_accuracy": 0.15954417288303374,
|
|
"num_tokens": 14208484.0,
|
|
"step": 8190
|
|
},
|
|
{
|
|
"entropy": 5.622953748703003,
|
|
"epoch": 0.6376191402450885,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.000496475484530201,
|
|
"loss": 5.5555,
|
|
"mean_token_accuracy": 0.1564874991774559,
|
|
"num_tokens": 14217368.0,
|
|
"step": 8195
|
|
},
|
|
{
|
|
"entropy": 5.747897338867188,
|
|
"epoch": 0.6380081696168061,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004964705964378292,
|
|
"loss": 5.5758,
|
|
"mean_token_accuracy": 0.1538155347108841,
|
|
"num_tokens": 14226663.0,
|
|
"step": 8200
|
|
},
|
|
{
|
|
"entropy": 5.645639514923095,
|
|
"epoch": 0.6383971989885237,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004964657049849934,
|
|
"loss": 5.4352,
|
|
"mean_token_accuracy": 0.16428688466548919,
|
|
"num_tokens": 14235153.0,
|
|
"step": 8205
|
|
},
|
|
{
|
|
"entropy": 5.56176381111145,
|
|
"epoch": 0.6387862283602412,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.0004964608101717681,
|
|
"loss": 5.58,
|
|
"mean_token_accuracy": 0.15763667821884156,
|
|
"num_tokens": 14244245.0,
|
|
"step": 8210
|
|
},
|
|
{
|
|
"entropy": 5.678912687301636,
|
|
"epoch": 0.6391752577319587,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.0004964559119982275,
|
|
"loss": 5.4851,
|
|
"mean_token_accuracy": 0.16121247708797454,
|
|
"num_tokens": 14252666.0,
|
|
"step": 8215
|
|
},
|
|
{
|
|
"entropy": 5.674066495895386,
|
|
"epoch": 0.6395642871036763,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.000496451010464446,
|
|
"loss": 5.5428,
|
|
"mean_token_accuracy": 0.15889398753643036,
|
|
"num_tokens": 14262232.0,
|
|
"step": 8220
|
|
},
|
|
{
|
|
"entropy": 5.616907978057862,
|
|
"epoch": 0.6399533164753939,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004964461055704978,
|
|
"loss": 5.4962,
|
|
"mean_token_accuracy": 0.16153504699468613,
|
|
"num_tokens": 14270496.0,
|
|
"step": 8225
|
|
},
|
|
{
|
|
"entropy": 5.580246067047119,
|
|
"epoch": 0.6403423458471115,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004964411973164574,
|
|
"loss": 5.4253,
|
|
"mean_token_accuracy": 0.1703116178512573,
|
|
"num_tokens": 14278597.0,
|
|
"step": 8230
|
|
},
|
|
{
|
|
"entropy": 5.52676420211792,
|
|
"epoch": 0.6407313752188291,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004964362857023993,
|
|
"loss": 5.4943,
|
|
"mean_token_accuracy": 0.15600418001413346,
|
|
"num_tokens": 14287444.0,
|
|
"step": 8235
|
|
},
|
|
{
|
|
"entropy": 5.5457216739654545,
|
|
"epoch": 0.6411204045905465,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.000496431370728398,
|
|
"loss": 5.3929,
|
|
"mean_token_accuracy": 0.16601495295763016,
|
|
"num_tokens": 14296041.0,
|
|
"step": 8240
|
|
},
|
|
{
|
|
"entropy": 5.58643536567688,
|
|
"epoch": 0.6415094339622641,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004964264523945281,
|
|
"loss": 5.4348,
|
|
"mean_token_accuracy": 0.16209615021944046,
|
|
"num_tokens": 14304700.0,
|
|
"step": 8245
|
|
},
|
|
{
|
|
"entropy": 5.600837182998657,
|
|
"epoch": 0.6418984633339817,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004964215307008643,
|
|
"loss": 5.548,
|
|
"mean_token_accuracy": 0.16066765785217285,
|
|
"num_tokens": 14312873.0,
|
|
"step": 8250
|
|
},
|
|
{
|
|
"entropy": 5.67624135017395,
|
|
"epoch": 0.6422874927056993,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004964166056474811,
|
|
"loss": 5.5433,
|
|
"mean_token_accuracy": 0.15643927901983262,
|
|
"num_tokens": 14321697.0,
|
|
"step": 8255
|
|
},
|
|
{
|
|
"entropy": 5.620931148529053,
|
|
"epoch": 0.6426765220774169,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004964116772344534,
|
|
"loss": 5.5296,
|
|
"mean_token_accuracy": 0.15321040153503418,
|
|
"num_tokens": 14330074.0,
|
|
"step": 8260
|
|
},
|
|
{
|
|
"entropy": 5.694720315933227,
|
|
"epoch": 0.6430655514491345,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.0004964067454618559,
|
|
"loss": 5.6178,
|
|
"mean_token_accuracy": 0.15140570402145387,
|
|
"num_tokens": 14339485.0,
|
|
"step": 8265
|
|
},
|
|
{
|
|
"entropy": 5.714789342880249,
|
|
"epoch": 0.6434545808208519,
|
|
"grad_norm": 2.453125,
|
|
"learning_rate": 0.0004964018103297634,
|
|
"loss": 5.5563,
|
|
"mean_token_accuracy": 0.15764311999082564,
|
|
"num_tokens": 14348182.0,
|
|
"step": 8270
|
|
},
|
|
{
|
|
"entropy": 5.762400913238525,
|
|
"epoch": 0.6438436101925695,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004963968718382509,
|
|
"loss": 5.6267,
|
|
"mean_token_accuracy": 0.15202651768922806,
|
|
"num_tokens": 14357202.0,
|
|
"step": 8275
|
|
},
|
|
{
|
|
"entropy": 5.644727182388306,
|
|
"epoch": 0.6442326395642871,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0004963919299873931,
|
|
"loss": 5.5317,
|
|
"mean_token_accuracy": 0.1548861563205719,
|
|
"num_tokens": 14366001.0,
|
|
"step": 8280
|
|
},
|
|
{
|
|
"entropy": 5.661684799194336,
|
|
"epoch": 0.6446216689360047,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.0004963869847772653,
|
|
"loss": 5.5895,
|
|
"mean_token_accuracy": 0.15226613059639932,
|
|
"num_tokens": 14374894.0,
|
|
"step": 8285
|
|
},
|
|
{
|
|
"entropy": 5.6282572746276855,
|
|
"epoch": 0.6450106983077223,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004963820362079423,
|
|
"loss": 5.5143,
|
|
"mean_token_accuracy": 0.15727802962064744,
|
|
"num_tokens": 14383396.0,
|
|
"step": 8290
|
|
},
|
|
{
|
|
"entropy": 5.629455280303955,
|
|
"epoch": 0.6453997276794398,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004963770842794994,
|
|
"loss": 5.4469,
|
|
"mean_token_accuracy": 0.17078810632228852,
|
|
"num_tokens": 14392514.0,
|
|
"step": 8295
|
|
},
|
|
{
|
|
"entropy": 5.656761884689331,
|
|
"epoch": 0.6457887570511573,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.0004963721289920115,
|
|
"loss": 5.5031,
|
|
"mean_token_accuracy": 0.1541423887014389,
|
|
"num_tokens": 14401916.0,
|
|
"step": 8300
|
|
},
|
|
{
|
|
"entropy": 5.6500287532806395,
|
|
"epoch": 0.6461777864228749,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004963671703455538,
|
|
"loss": 5.5758,
|
|
"mean_token_accuracy": 0.15413750410079957,
|
|
"num_tokens": 14410476.0,
|
|
"step": 8305
|
|
},
|
|
{
|
|
"entropy": 5.664961814880371,
|
|
"epoch": 0.6465668157945925,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004963622083402018,
|
|
"loss": 5.5587,
|
|
"mean_token_accuracy": 0.1544247552752495,
|
|
"num_tokens": 14418437.0,
|
|
"step": 8310
|
|
},
|
|
{
|
|
"entropy": 5.613209295272827,
|
|
"epoch": 0.6469558451663101,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004963572429760305,
|
|
"loss": 5.5038,
|
|
"mean_token_accuracy": 0.1593249961733818,
|
|
"num_tokens": 14426978.0,
|
|
"step": 8315
|
|
},
|
|
{
|
|
"entropy": 5.688936853408814,
|
|
"epoch": 0.6473448745380276,
|
|
"grad_norm": 1.9375,
|
|
"learning_rate": 0.0004963522742531155,
|
|
"loss": 5.5247,
|
|
"mean_token_accuracy": 0.15553096532821656,
|
|
"num_tokens": 14435043.0,
|
|
"step": 8320
|
|
},
|
|
{
|
|
"entropy": 5.659121370315551,
|
|
"epoch": 0.6477339039097452,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.000496347302171532,
|
|
"loss": 5.4333,
|
|
"mean_token_accuracy": 0.17211561501026154,
|
|
"num_tokens": 14443397.0,
|
|
"step": 8325
|
|
},
|
|
{
|
|
"entropy": 5.632126331329346,
|
|
"epoch": 0.6481229332814628,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004963423267313554,
|
|
"loss": 5.5373,
|
|
"mean_token_accuracy": 0.15899365097284318,
|
|
"num_tokens": 14452536.0,
|
|
"step": 8330
|
|
},
|
|
{
|
|
"entropy": 5.641506767272949,
|
|
"epoch": 0.6485119626531803,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.0004963373479326614,
|
|
"loss": 5.5798,
|
|
"mean_token_accuracy": 0.15403404235839843,
|
|
"num_tokens": 14461901.0,
|
|
"step": 8335
|
|
},
|
|
{
|
|
"entropy": 5.612789440155029,
|
|
"epoch": 0.6489009920248979,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.0004963323657755255,
|
|
"loss": 5.5229,
|
|
"mean_token_accuracy": 0.16365441381931306,
|
|
"num_tokens": 14470547.0,
|
|
"step": 8340
|
|
},
|
|
{
|
|
"entropy": 5.568451738357544,
|
|
"epoch": 0.6492900213966154,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004963273802600231,
|
|
"loss": 5.3867,
|
|
"mean_token_accuracy": 0.16192733198404313,
|
|
"num_tokens": 14478439.0,
|
|
"step": 8345
|
|
},
|
|
{
|
|
"entropy": 5.5863793849945065,
|
|
"epoch": 0.649679050768333,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.00049632239138623,
|
|
"loss": 5.4576,
|
|
"mean_token_accuracy": 0.1650322139263153,
|
|
"num_tokens": 14486621.0,
|
|
"step": 8350
|
|
},
|
|
{
|
|
"entropy": 5.5568140029907225,
|
|
"epoch": 0.6500680801400506,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.0004963173991542219,
|
|
"loss": 5.4351,
|
|
"mean_token_accuracy": 0.16386538296937941,
|
|
"num_tokens": 14495313.0,
|
|
"step": 8355
|
|
},
|
|
{
|
|
"entropy": 5.641188097000122,
|
|
"epoch": 0.6504571095117682,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004963124035640746,
|
|
"loss": 5.5206,
|
|
"mean_token_accuracy": 0.1590793639421463,
|
|
"num_tokens": 14503647.0,
|
|
"step": 8360
|
|
},
|
|
{
|
|
"entropy": 5.633780574798584,
|
|
"epoch": 0.6508461388834857,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.0004963074046158637,
|
|
"loss": 5.4433,
|
|
"mean_token_accuracy": 0.1663560226559639,
|
|
"num_tokens": 14512350.0,
|
|
"step": 8365
|
|
},
|
|
{
|
|
"entropy": 5.671565389633178,
|
|
"epoch": 0.6512351682552032,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004963024023096652,
|
|
"loss": 5.5786,
|
|
"mean_token_accuracy": 0.1506078436970711,
|
|
"num_tokens": 14521801.0,
|
|
"step": 8370
|
|
},
|
|
{
|
|
"entropy": 5.605286026000977,
|
|
"epoch": 0.6516241976269208,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004962973966455551,
|
|
"loss": 5.4278,
|
|
"mean_token_accuracy": 0.16242532432079315,
|
|
"num_tokens": 14530045.0,
|
|
"step": 8375
|
|
},
|
|
{
|
|
"entropy": 5.640976905822754,
|
|
"epoch": 0.6520132269986384,
|
|
"grad_norm": 1.921875,
|
|
"learning_rate": 0.0004962923876236092,
|
|
"loss": 5.5308,
|
|
"mean_token_accuracy": 0.16341629326343537,
|
|
"num_tokens": 14538944.0,
|
|
"step": 8380
|
|
},
|
|
{
|
|
"entropy": 5.673352861404419,
|
|
"epoch": 0.652402256370356,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.0004962873752439035,
|
|
"loss": 5.5652,
|
|
"mean_token_accuracy": 0.1534780204296112,
|
|
"num_tokens": 14548180.0,
|
|
"step": 8385
|
|
},
|
|
{
|
|
"entropy": 5.648133897781372,
|
|
"epoch": 0.6527912857420736,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004962823595065141,
|
|
"loss": 5.5594,
|
|
"mean_token_accuracy": 0.15530768036842346,
|
|
"num_tokens": 14556907.0,
|
|
"step": 8390
|
|
},
|
|
{
|
|
"entropy": 5.659310817718506,
|
|
"epoch": 0.653180315113791,
|
|
"grad_norm": 2.40625,
|
|
"learning_rate": 0.0004962773404115172,
|
|
"loss": 5.5417,
|
|
"mean_token_accuracy": 0.15009303390979767,
|
|
"num_tokens": 14565317.0,
|
|
"step": 8395
|
|
},
|
|
{
|
|
"entropy": 5.694459915161133,
|
|
"epoch": 0.6535693444855086,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.0004962723179589886,
|
|
"loss": 5.604,
|
|
"mean_token_accuracy": 0.1595344513654709,
|
|
"num_tokens": 14574485.0,
|
|
"step": 8400
|
|
},
|
|
{
|
|
"entropy": 5.724558544158936,
|
|
"epoch": 0.6539583738572262,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.000496267292149005,
|
|
"loss": 5.5029,
|
|
"mean_token_accuracy": 0.15957963466644287,
|
|
"num_tokens": 14584002.0,
|
|
"step": 8405
|
|
},
|
|
{
|
|
"entropy": 5.606374025344849,
|
|
"epoch": 0.6543474032289438,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004962622629816423,
|
|
"loss": 5.4298,
|
|
"mean_token_accuracy": 0.16107886284589767,
|
|
"num_tokens": 14592033.0,
|
|
"step": 8410
|
|
},
|
|
{
|
|
"entropy": 5.603494310379029,
|
|
"epoch": 0.6547364326006614,
|
|
"grad_norm": 1.875,
|
|
"learning_rate": 0.000496257230456977,
|
|
"loss": 5.5695,
|
|
"mean_token_accuracy": 0.1592939466238022,
|
|
"num_tokens": 14600084.0,
|
|
"step": 8415
|
|
},
|
|
{
|
|
"entropy": 5.578213214874268,
|
|
"epoch": 0.6551254619723789,
|
|
"grad_norm": 2.46875,
|
|
"learning_rate": 0.0004962521945750855,
|
|
"loss": 5.4971,
|
|
"mean_token_accuracy": 0.1668678641319275,
|
|
"num_tokens": 14608380.0,
|
|
"step": 8420
|
|
},
|
|
{
|
|
"entropy": 5.610316419601441,
|
|
"epoch": 0.6555144913440965,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.000496247155336044,
|
|
"loss": 5.5628,
|
|
"mean_token_accuracy": 0.1621503487229347,
|
|
"num_tokens": 14616864.0,
|
|
"step": 8425
|
|
},
|
|
{
|
|
"entropy": 5.659423685073852,
|
|
"epoch": 0.655903520715814,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.0004962421127399291,
|
|
"loss": 5.5914,
|
|
"mean_token_accuracy": 0.1568238154053688,
|
|
"num_tokens": 14627054.0,
|
|
"step": 8430
|
|
},
|
|
{
|
|
"entropy": 5.726030683517456,
|
|
"epoch": 0.6562925500875316,
|
|
"grad_norm": 1.8984375,
|
|
"learning_rate": 0.0004962370667868172,
|
|
"loss": 5.4785,
|
|
"mean_token_accuracy": 0.16295430213212966,
|
|
"num_tokens": 14634985.0,
|
|
"step": 8435
|
|
},
|
|
{
|
|
"entropy": 5.6965233325958256,
|
|
"epoch": 0.6566815794592492,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.0004962320174767851,
|
|
"loss": 5.5493,
|
|
"mean_token_accuracy": 0.1606361523270607,
|
|
"num_tokens": 14644135.0,
|
|
"step": 8440
|
|
},
|
|
{
|
|
"entropy": 5.655184364318847,
|
|
"epoch": 0.6570706088309667,
|
|
"grad_norm": 1.875,
|
|
"learning_rate": 0.000496226964809909,
|
|
"loss": 5.4987,
|
|
"mean_token_accuracy": 0.16110980808734893,
|
|
"num_tokens": 14652997.0,
|
|
"step": 8445
|
|
},
|
|
{
|
|
"entropy": 5.617531156539917,
|
|
"epoch": 0.6574596382026843,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.000496221908786266,
|
|
"loss": 5.5826,
|
|
"mean_token_accuracy": 0.15483639836311341,
|
|
"num_tokens": 14661961.0,
|
|
"step": 8450
|
|
},
|
|
{
|
|
"entropy": 5.751500463485717,
|
|
"epoch": 0.6578486675744019,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004962168494059327,
|
|
"loss": 5.692,
|
|
"mean_token_accuracy": 0.14975932091474534,
|
|
"num_tokens": 14671407.0,
|
|
"step": 8455
|
|
},
|
|
{
|
|
"entropy": 5.664218282699585,
|
|
"epoch": 0.6582376969461194,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.0004962117866689857,
|
|
"loss": 5.5503,
|
|
"mean_token_accuracy": 0.158315971493721,
|
|
"num_tokens": 14680015.0,
|
|
"step": 8460
|
|
},
|
|
{
|
|
"entropy": 5.554697895050049,
|
|
"epoch": 0.658626726317837,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.000496206720575502,
|
|
"loss": 5.4022,
|
|
"mean_token_accuracy": 0.16425073891878128,
|
|
"num_tokens": 14688444.0,
|
|
"step": 8465
|
|
},
|
|
{
|
|
"entropy": 5.611348390579224,
|
|
"epoch": 0.6590157556895546,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004962016511255584,
|
|
"loss": 5.5564,
|
|
"mean_token_accuracy": 0.15699147582054138,
|
|
"num_tokens": 14697246.0,
|
|
"step": 8470
|
|
},
|
|
{
|
|
"entropy": 5.610384368896485,
|
|
"epoch": 0.6594047850612721,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004961965783192318,
|
|
"loss": 5.4104,
|
|
"mean_token_accuracy": 0.1625382572412491,
|
|
"num_tokens": 14706066.0,
|
|
"step": 8475
|
|
},
|
|
{
|
|
"entropy": 5.654651784896851,
|
|
"epoch": 0.6597938144329897,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004961915021565992,
|
|
"loss": 5.5185,
|
|
"mean_token_accuracy": 0.15606666058301927,
|
|
"num_tokens": 14714327.0,
|
|
"step": 8480
|
|
},
|
|
{
|
|
"entropy": 5.581632661819458,
|
|
"epoch": 0.6601828438047073,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.0004961864226377377,
|
|
"loss": 5.415,
|
|
"mean_token_accuracy": 0.16276211142539979,
|
|
"num_tokens": 14723053.0,
|
|
"step": 8485
|
|
},
|
|
{
|
|
"entropy": 5.569181060791015,
|
|
"epoch": 0.6605718731764249,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004961813397627241,
|
|
"loss": 5.3847,
|
|
"mean_token_accuracy": 0.17425692081451416,
|
|
"num_tokens": 14731825.0,
|
|
"step": 8490
|
|
},
|
|
{
|
|
"entropy": 5.636592769622803,
|
|
"epoch": 0.6609609025481424,
|
|
"grad_norm": 1.9296875,
|
|
"learning_rate": 0.0004961762535316358,
|
|
"loss": 5.614,
|
|
"mean_token_accuracy": 0.1498458780348301,
|
|
"num_tokens": 14740751.0,
|
|
"step": 8495
|
|
},
|
|
{
|
|
"entropy": 5.628172779083252,
|
|
"epoch": 0.6613499319198599,
|
|
"grad_norm": 2.515625,
|
|
"learning_rate": 0.0004961711639445499,
|
|
"loss": 5.466,
|
|
"mean_token_accuracy": 0.1632356747984886,
|
|
"num_tokens": 14748994.0,
|
|
"step": 8500
|
|
},
|
|
{
|
|
"entropy": 5.612378454208374,
|
|
"epoch": 0.6617389612915775,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.0004961660710015435,
|
|
"loss": 5.4656,
|
|
"mean_token_accuracy": 0.15940798372030257,
|
|
"num_tokens": 14757388.0,
|
|
"step": 8505
|
|
},
|
|
{
|
|
"entropy": 5.721138000488281,
|
|
"epoch": 0.6621279906632951,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.0004961609747026943,
|
|
"loss": 5.6214,
|
|
"mean_token_accuracy": 0.15444083586335183,
|
|
"num_tokens": 14766654.0,
|
|
"step": 8510
|
|
},
|
|
{
|
|
"entropy": 5.6626979351043705,
|
|
"epoch": 0.6625170200350127,
|
|
"grad_norm": 1.8984375,
|
|
"learning_rate": 0.0004961558750480791,
|
|
"loss": 5.5252,
|
|
"mean_token_accuracy": 0.1575162798166275,
|
|
"num_tokens": 14775561.0,
|
|
"step": 8515
|
|
},
|
|
{
|
|
"entropy": 5.650518321990967,
|
|
"epoch": 0.6629060494067303,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.0004961507720377756,
|
|
"loss": 5.5684,
|
|
"mean_token_accuracy": 0.1542758047580719,
|
|
"num_tokens": 14783596.0,
|
|
"step": 8520
|
|
},
|
|
{
|
|
"entropy": 5.711835861206055,
|
|
"epoch": 0.6632950787784477,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.0004961456656718611,
|
|
"loss": 5.5719,
|
|
"mean_token_accuracy": 0.15824297368526458,
|
|
"num_tokens": 14791932.0,
|
|
"step": 8525
|
|
},
|
|
{
|
|
"entropy": 5.707588768005371,
|
|
"epoch": 0.6636841081501653,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.000496140555950413,
|
|
"loss": 5.6084,
|
|
"mean_token_accuracy": 0.1585446685552597,
|
|
"num_tokens": 14801261.0,
|
|
"step": 8530
|
|
},
|
|
{
|
|
"entropy": 5.625937414169312,
|
|
"epoch": 0.6640731375218829,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004961354428735091,
|
|
"loss": 5.4847,
|
|
"mean_token_accuracy": 0.15456562489271164,
|
|
"num_tokens": 14809788.0,
|
|
"step": 8535
|
|
},
|
|
{
|
|
"entropy": 5.549485111236573,
|
|
"epoch": 0.6644621668936005,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004961303264412267,
|
|
"loss": 5.476,
|
|
"mean_token_accuracy": 0.15823260098695754,
|
|
"num_tokens": 14818324.0,
|
|
"step": 8540
|
|
},
|
|
{
|
|
"entropy": 5.570508337020874,
|
|
"epoch": 0.6648511962653181,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004961252066536437,
|
|
"loss": 5.4414,
|
|
"mean_token_accuracy": 0.16257568448781967,
|
|
"num_tokens": 14827020.0,
|
|
"step": 8545
|
|
},
|
|
{
|
|
"entropy": 5.574400806427002,
|
|
"epoch": 0.6652402256370356,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004961200835108375,
|
|
"loss": 5.5549,
|
|
"mean_token_accuracy": 0.15907474458217621,
|
|
"num_tokens": 14835522.0,
|
|
"step": 8550
|
|
},
|
|
{
|
|
"entropy": 5.642110776901245,
|
|
"epoch": 0.6656292550087531,
|
|
"grad_norm": 1.9921875,
|
|
"learning_rate": 0.000496114957012886,
|
|
"loss": 5.5198,
|
|
"mean_token_accuracy": 0.1613421067595482,
|
|
"num_tokens": 14844676.0,
|
|
"step": 8555
|
|
},
|
|
{
|
|
"entropy": 5.712966775894165,
|
|
"epoch": 0.6660182843804707,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004961098271598671,
|
|
"loss": 5.5476,
|
|
"mean_token_accuracy": 0.1592008203268051,
|
|
"num_tokens": 14853996.0,
|
|
"step": 8560
|
|
},
|
|
{
|
|
"entropy": 5.6499645709991455,
|
|
"epoch": 0.6664073137521883,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004961046939518585,
|
|
"loss": 5.5404,
|
|
"mean_token_accuracy": 0.1563110366463661,
|
|
"num_tokens": 14862981.0,
|
|
"step": 8565
|
|
},
|
|
{
|
|
"entropy": 5.6688775539398195,
|
|
"epoch": 0.6667963431239059,
|
|
"grad_norm": 1.9296875,
|
|
"learning_rate": 0.0004960995573889379,
|
|
"loss": 5.5756,
|
|
"mean_token_accuracy": 0.1530095875263214,
|
|
"num_tokens": 14872378.0,
|
|
"step": 8570
|
|
},
|
|
{
|
|
"entropy": 5.650428819656372,
|
|
"epoch": 0.6671853724956234,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004960944174711836,
|
|
"loss": 5.5062,
|
|
"mean_token_accuracy": 0.1554716408252716,
|
|
"num_tokens": 14881662.0,
|
|
"step": 8575
|
|
},
|
|
{
|
|
"entropy": 5.646929121017456,
|
|
"epoch": 0.667574401867341,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.0004960892741986734,
|
|
"loss": 5.3935,
|
|
"mean_token_accuracy": 0.16164069920778273,
|
|
"num_tokens": 14890211.0,
|
|
"step": 8580
|
|
},
|
|
{
|
|
"entropy": 5.671356678009033,
|
|
"epoch": 0.6679634312390585,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.0004960841275714853,
|
|
"loss": 5.6131,
|
|
"mean_token_accuracy": 0.15282653272151947,
|
|
"num_tokens": 14899865.0,
|
|
"step": 8585
|
|
},
|
|
{
|
|
"entropy": 5.623284864425659,
|
|
"epoch": 0.6683524606107761,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004960789775896975,
|
|
"loss": 5.5466,
|
|
"mean_token_accuracy": 0.15914573520421982,
|
|
"num_tokens": 14908334.0,
|
|
"step": 8590
|
|
},
|
|
{
|
|
"entropy": 5.580433416366577,
|
|
"epoch": 0.6687414899824937,
|
|
"grad_norm": 1.8984375,
|
|
"learning_rate": 0.0004960738242533881,
|
|
"loss": 5.51,
|
|
"mean_token_accuracy": 0.15933505892753602,
|
|
"num_tokens": 14916477.0,
|
|
"step": 8595
|
|
},
|
|
{
|
|
"entropy": 5.617793178558349,
|
|
"epoch": 0.6691305193542112,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004960686675626353,
|
|
"loss": 5.4352,
|
|
"mean_token_accuracy": 0.164647114276886,
|
|
"num_tokens": 14925223.0,
|
|
"step": 8600
|
|
},
|
|
{
|
|
"entropy": 5.681310606002808,
|
|
"epoch": 0.6695195487259288,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.0004960635075175173,
|
|
"loss": 5.5586,
|
|
"mean_token_accuracy": 0.1621955692768097,
|
|
"num_tokens": 14934427.0,
|
|
"step": 8605
|
|
},
|
|
{
|
|
"entropy": 5.649712610244751,
|
|
"epoch": 0.6699085780976464,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004960583441181124,
|
|
"loss": 5.4867,
|
|
"mean_token_accuracy": 0.16183265298604965,
|
|
"num_tokens": 14943175.0,
|
|
"step": 8610
|
|
},
|
|
{
|
|
"entropy": 5.66594967842102,
|
|
"epoch": 0.670297607469364,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004960531773644992,
|
|
"loss": 5.5274,
|
|
"mean_token_accuracy": 0.15886154323816298,
|
|
"num_tokens": 14951933.0,
|
|
"step": 8615
|
|
},
|
|
{
|
|
"entropy": 5.576411485671997,
|
|
"epoch": 0.6706866368410815,
|
|
"grad_norm": 1.875,
|
|
"learning_rate": 0.0004960480072567557,
|
|
"loss": 5.5142,
|
|
"mean_token_accuracy": 0.16025878936052323,
|
|
"num_tokens": 14960735.0,
|
|
"step": 8620
|
|
},
|
|
{
|
|
"entropy": 5.617590761184692,
|
|
"epoch": 0.671075666212799,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004960428337949604,
|
|
"loss": 5.591,
|
|
"mean_token_accuracy": 0.15304946452379226,
|
|
"num_tokens": 14970326.0,
|
|
"step": 8625
|
|
},
|
|
{
|
|
"entropy": 5.6727522850036625,
|
|
"epoch": 0.6714646955845166,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.0004960376569791921,
|
|
"loss": 5.4539,
|
|
"mean_token_accuracy": 0.1658519499003887,
|
|
"num_tokens": 14979822.0,
|
|
"step": 8630
|
|
},
|
|
{
|
|
"entropy": 5.696259164810181,
|
|
"epoch": 0.6718537249562342,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004960324768095291,
|
|
"loss": 5.565,
|
|
"mean_token_accuracy": 0.154909910261631,
|
|
"num_tokens": 14989350.0,
|
|
"step": 8635
|
|
},
|
|
{
|
|
"entropy": 5.646508979797363,
|
|
"epoch": 0.6722427543279518,
|
|
"grad_norm": 1.8984375,
|
|
"learning_rate": 0.0004960272932860502,
|
|
"loss": 5.5749,
|
|
"mean_token_accuracy": 0.15166825354099273,
|
|
"num_tokens": 14998763.0,
|
|
"step": 8640
|
|
},
|
|
{
|
|
"entropy": 5.637317037582397,
|
|
"epoch": 0.6726317836996694,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004960221064088338,
|
|
"loss": 5.4454,
|
|
"mean_token_accuracy": 0.16248841732740402,
|
|
"num_tokens": 15006497.0,
|
|
"step": 8645
|
|
},
|
|
{
|
|
"entropy": 5.531035041809082,
|
|
"epoch": 0.6730208130713868,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004960169161779588,
|
|
"loss": 5.4067,
|
|
"mean_token_accuracy": 0.16369789242744445,
|
|
"num_tokens": 15014397.0,
|
|
"step": 8650
|
|
},
|
|
{
|
|
"entropy": 5.575918388366699,
|
|
"epoch": 0.6734098424431044,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004960117225935038,
|
|
"loss": 5.4554,
|
|
"mean_token_accuracy": 0.1646529421210289,
|
|
"num_tokens": 15022726.0,
|
|
"step": 8655
|
|
},
|
|
{
|
|
"entropy": 5.742713737487793,
|
|
"epoch": 0.673798871814822,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.0004960065256555477,
|
|
"loss": 5.6571,
|
|
"mean_token_accuracy": 0.14834950268268585,
|
|
"num_tokens": 15032317.0,
|
|
"step": 8660
|
|
},
|
|
{
|
|
"entropy": 5.691679334640503,
|
|
"epoch": 0.6741879011865396,
|
|
"grad_norm": 1.921875,
|
|
"learning_rate": 0.0004960013253641695,
|
|
"loss": 5.5092,
|
|
"mean_token_accuracy": 0.16287997663021087,
|
|
"num_tokens": 15041091.0,
|
|
"step": 8665
|
|
},
|
|
{
|
|
"entropy": 5.699982976913452,
|
|
"epoch": 0.6745769305582572,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004959961217194477,
|
|
"loss": 5.6681,
|
|
"mean_token_accuracy": 0.1512497015297413,
|
|
"num_tokens": 15049797.0,
|
|
"step": 8670
|
|
},
|
|
{
|
|
"entropy": 5.55004563331604,
|
|
"epoch": 0.6749659599299748,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.0004959909147214615,
|
|
"loss": 5.3342,
|
|
"mean_token_accuracy": 0.17136287540197373,
|
|
"num_tokens": 15057736.0,
|
|
"step": 8675
|
|
},
|
|
{
|
|
"entropy": 5.582203340530396,
|
|
"epoch": 0.6753549893016922,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004959857043702902,
|
|
"loss": 5.5279,
|
|
"mean_token_accuracy": 0.16295597106218337,
|
|
"num_tokens": 15066072.0,
|
|
"step": 8680
|
|
},
|
|
{
|
|
"entropy": 5.602957439422608,
|
|
"epoch": 0.6757440186734098,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004959804906660124,
|
|
"loss": 5.4295,
|
|
"mean_token_accuracy": 0.16854963302612305,
|
|
"num_tokens": 15073918.0,
|
|
"step": 8685
|
|
},
|
|
{
|
|
"entropy": 5.659347152709961,
|
|
"epoch": 0.6761330480451274,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.0004959752736087073,
|
|
"loss": 5.5404,
|
|
"mean_token_accuracy": 0.15619544982910155,
|
|
"num_tokens": 15082937.0,
|
|
"step": 8690
|
|
},
|
|
{
|
|
"entropy": 5.5592786312103275,
|
|
"epoch": 0.676522077416845,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 0.0004959700531984543,
|
|
"loss": 5.4982,
|
|
"mean_token_accuracy": 0.16490236818790435,
|
|
"num_tokens": 15091218.0,
|
|
"step": 8695
|
|
},
|
|
{
|
|
"entropy": 5.5837174415588375,
|
|
"epoch": 0.6769111067885626,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0004959648294353324,
|
|
"loss": 5.4135,
|
|
"mean_token_accuracy": 0.16881164014339448,
|
|
"num_tokens": 15099640.0,
|
|
"step": 8700
|
|
},
|
|
{
|
|
"entropy": 5.646589708328247,
|
|
"epoch": 0.6773001361602801,
|
|
"grad_norm": 1.8984375,
|
|
"learning_rate": 0.0004959596023194208,
|
|
"loss": 5.4964,
|
|
"mean_token_accuracy": 0.15902033373713492,
|
|
"num_tokens": 15108710.0,
|
|
"step": 8705
|
|
},
|
|
{
|
|
"entropy": 5.569454717636108,
|
|
"epoch": 0.6776891655319977,
|
|
"grad_norm": 2.953125,
|
|
"learning_rate": 0.000495954371850799,
|
|
"loss": 5.4858,
|
|
"mean_token_accuracy": 0.16042321026325226,
|
|
"num_tokens": 15117074.0,
|
|
"step": 8710
|
|
},
|
|
{
|
|
"entropy": 5.663643503189087,
|
|
"epoch": 0.6780781949037152,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004959491380295463,
|
|
"loss": 5.4386,
|
|
"mean_token_accuracy": 0.1646001473069191,
|
|
"num_tokens": 15124714.0,
|
|
"step": 8715
|
|
},
|
|
{
|
|
"entropy": 5.612705993652344,
|
|
"epoch": 0.6784672242754328,
|
|
"grad_norm": 2.359375,
|
|
"learning_rate": 0.0004959439008557422,
|
|
"loss": 5.459,
|
|
"mean_token_accuracy": 0.16234805732965468,
|
|
"num_tokens": 15134177.0,
|
|
"step": 8720
|
|
},
|
|
{
|
|
"entropy": 5.612493276596069,
|
|
"epoch": 0.6788562536471504,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.000495938660329466,
|
|
"loss": 5.4796,
|
|
"mean_token_accuracy": 0.15789630264043808,
|
|
"num_tokens": 15142659.0,
|
|
"step": 8725
|
|
},
|
|
{
|
|
"entropy": 5.616532039642334,
|
|
"epoch": 0.6792452830188679,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.0004959334164507973,
|
|
"loss": 5.6108,
|
|
"mean_token_accuracy": 0.15909717231988907,
|
|
"num_tokens": 15151423.0,
|
|
"step": 8730
|
|
},
|
|
{
|
|
"entropy": 5.615394735336304,
|
|
"epoch": 0.6796343123905855,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.0004959281692198155,
|
|
"loss": 5.4347,
|
|
"mean_token_accuracy": 0.1637183368206024,
|
|
"num_tokens": 15159986.0,
|
|
"step": 8735
|
|
},
|
|
{
|
|
"entropy": 5.575001239776611,
|
|
"epoch": 0.6800233417623031,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.0004959229186366007,
|
|
"loss": 5.4917,
|
|
"mean_token_accuracy": 0.15788483023643493,
|
|
"num_tokens": 15168183.0,
|
|
"step": 8740
|
|
},
|
|
{
|
|
"entropy": 5.529715967178345,
|
|
"epoch": 0.6804123711340206,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.000495917664701232,
|
|
"loss": 5.4119,
|
|
"mean_token_accuracy": 0.16142059713602067,
|
|
"num_tokens": 15176476.0,
|
|
"step": 8745
|
|
},
|
|
{
|
|
"entropy": 5.79360523223877,
|
|
"epoch": 0.6808014005057382,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004959124074137894,
|
|
"loss": 5.6919,
|
|
"mean_token_accuracy": 0.1518779918551445,
|
|
"num_tokens": 15186873.0,
|
|
"step": 8750
|
|
},
|
|
{
|
|
"entropy": 5.695074796676636,
|
|
"epoch": 0.6811904298774557,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.0004959071467743526,
|
|
"loss": 5.4714,
|
|
"mean_token_accuracy": 0.15784681513905524,
|
|
"num_tokens": 15194965.0,
|
|
"step": 8755
|
|
},
|
|
{
|
|
"entropy": 5.529453945159912,
|
|
"epoch": 0.6815794592491733,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004959018827830016,
|
|
"loss": 5.3476,
|
|
"mean_token_accuracy": 0.16466234773397445,
|
|
"num_tokens": 15204028.0,
|
|
"step": 8760
|
|
},
|
|
{
|
|
"entropy": 5.5011200428009035,
|
|
"epoch": 0.6819684886208909,
|
|
"grad_norm": 1.9609375,
|
|
"learning_rate": 0.000495896615439816,
|
|
"loss": 5.3716,
|
|
"mean_token_accuracy": 0.1737161621451378,
|
|
"num_tokens": 15212011.0,
|
|
"step": 8765
|
|
},
|
|
{
|
|
"entropy": 5.570515918731689,
|
|
"epoch": 0.6823575179926085,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.0004958913447448759,
|
|
"loss": 5.4669,
|
|
"mean_token_accuracy": 0.16217222511768342,
|
|
"num_tokens": 15220088.0,
|
|
"step": 8770
|
|
},
|
|
{
|
|
"entropy": 5.635524034500122,
|
|
"epoch": 0.682746547364326,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.0004958860706982613,
|
|
"loss": 5.4007,
|
|
"mean_token_accuracy": 0.1679010197520256,
|
|
"num_tokens": 15228676.0,
|
|
"step": 8775
|
|
},
|
|
{
|
|
"entropy": 5.56300687789917,
|
|
"epoch": 0.6831355767360435,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.000495880793300052,
|
|
"loss": 5.4403,
|
|
"mean_token_accuracy": 0.16561521738767623,
|
|
"num_tokens": 15237392.0,
|
|
"step": 8780
|
|
},
|
|
{
|
|
"entropy": 5.596027278900147,
|
|
"epoch": 0.6835246061077611,
|
|
"grad_norm": 2.3125,
|
|
"learning_rate": 0.0004958755125503284,
|
|
"loss": 5.592,
|
|
"mean_token_accuracy": 0.15963526591658592,
|
|
"num_tokens": 15246738.0,
|
|
"step": 8785
|
|
},
|
|
{
|
|
"entropy": 5.717942333221435,
|
|
"epoch": 0.6839136354794787,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004958702284491703,
|
|
"loss": 5.5814,
|
|
"mean_token_accuracy": 0.15875980854034424,
|
|
"num_tokens": 15255154.0,
|
|
"step": 8790
|
|
},
|
|
{
|
|
"entropy": 5.636683750152588,
|
|
"epoch": 0.6843026648511963,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.0004958649409966581,
|
|
"loss": 5.4356,
|
|
"mean_token_accuracy": 0.16528652012348174,
|
|
"num_tokens": 15264178.0,
|
|
"step": 8795
|
|
},
|
|
{
|
|
"entropy": 5.621670055389404,
|
|
"epoch": 0.6846916942229139,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.000495859650192872,
|
|
"loss": 5.5452,
|
|
"mean_token_accuracy": 0.161554317176342,
|
|
"num_tokens": 15272591.0,
|
|
"step": 8800
|
|
},
|
|
{
|
|
"entropy": 5.629113292694091,
|
|
"epoch": 0.6850807235946313,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004958543560378922,
|
|
"loss": 5.4387,
|
|
"mean_token_accuracy": 0.15784372687339782,
|
|
"num_tokens": 15281280.0,
|
|
"step": 8805
|
|
},
|
|
{
|
|
"entropy": 5.624751186370849,
|
|
"epoch": 0.6854697529663489,
|
|
"grad_norm": 2.265625,
|
|
"learning_rate": 0.0004958490585317991,
|
|
"loss": 5.41,
|
|
"mean_token_accuracy": 0.1661291778087616,
|
|
"num_tokens": 15290639.0,
|
|
"step": 8810
|
|
},
|
|
{
|
|
"entropy": 5.5839275360107425,
|
|
"epoch": 0.6858587823380665,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.000495843757674673,
|
|
"loss": 5.3923,
|
|
"mean_token_accuracy": 0.15482802540063859,
|
|
"num_tokens": 15298877.0,
|
|
"step": 8815
|
|
},
|
|
{
|
|
"entropy": 5.6236021518707275,
|
|
"epoch": 0.6862478117097841,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.0004958384534665945,
|
|
"loss": 5.5289,
|
|
"mean_token_accuracy": 0.16352324783802033,
|
|
"num_tokens": 15307710.0,
|
|
"step": 8820
|
|
},
|
|
{
|
|
"entropy": 5.678792524337768,
|
|
"epoch": 0.6866368410815017,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.0004958331459076438,
|
|
"loss": 5.5491,
|
|
"mean_token_accuracy": 0.16083763390779496,
|
|
"num_tokens": 15315749.0,
|
|
"step": 8825
|
|
},
|
|
{
|
|
"entropy": 5.626476907730103,
|
|
"epoch": 0.6870258704532192,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004958278349979018,
|
|
"loss": 5.4927,
|
|
"mean_token_accuracy": 0.15530785620212556,
|
|
"num_tokens": 15324161.0,
|
|
"step": 8830
|
|
},
|
|
{
|
|
"entropy": 5.524054527282715,
|
|
"epoch": 0.6874148998249368,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.0004958225207374488,
|
|
"loss": 5.3932,
|
|
"mean_token_accuracy": 0.16635617166757583,
|
|
"num_tokens": 15333414.0,
|
|
"step": 8835
|
|
},
|
|
{
|
|
"entropy": 5.592375755310059,
|
|
"epoch": 0.6878039291966543,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004958172031263655,
|
|
"loss": 5.4747,
|
|
"mean_token_accuracy": 0.16181471645832063,
|
|
"num_tokens": 15342369.0,
|
|
"step": 8840
|
|
},
|
|
{
|
|
"entropy": 5.6411394596099855,
|
|
"epoch": 0.6881929585683719,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004958118821647326,
|
|
"loss": 5.5584,
|
|
"mean_token_accuracy": 0.15322692543268204,
|
|
"num_tokens": 15351109.0,
|
|
"step": 8845
|
|
},
|
|
{
|
|
"entropy": 5.57485408782959,
|
|
"epoch": 0.6885819879400895,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.0004958065578526308,
|
|
"loss": 5.4434,
|
|
"mean_token_accuracy": 0.16486693024635315,
|
|
"num_tokens": 15359837.0,
|
|
"step": 8850
|
|
},
|
|
{
|
|
"entropy": 5.562979078292846,
|
|
"epoch": 0.688971017311807,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.000495801230190141,
|
|
"loss": 5.488,
|
|
"mean_token_accuracy": 0.16259763464331628,
|
|
"num_tokens": 15368776.0,
|
|
"step": 8855
|
|
},
|
|
{
|
|
"entropy": 5.625402355194092,
|
|
"epoch": 0.6893600466835246,
|
|
"grad_norm": 2.625,
|
|
"learning_rate": 0.0004957958991773441,
|
|
"loss": 5.4583,
|
|
"mean_token_accuracy": 0.16856665164232254,
|
|
"num_tokens": 15378127.0,
|
|
"step": 8860
|
|
},
|
|
{
|
|
"entropy": 5.638774490356445,
|
|
"epoch": 0.6897490760552422,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004957905648143206,
|
|
"loss": 5.4425,
|
|
"mean_token_accuracy": 0.16533851325511933,
|
|
"num_tokens": 15386580.0,
|
|
"step": 8865
|
|
},
|
|
{
|
|
"entropy": 5.619088506698608,
|
|
"epoch": 0.6901381054269597,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.0004957852271011519,
|
|
"loss": 5.5804,
|
|
"mean_token_accuracy": 0.16143989711999893,
|
|
"num_tokens": 15395973.0,
|
|
"step": 8870
|
|
},
|
|
{
|
|
"entropy": 5.631026124954223,
|
|
"epoch": 0.6905271347986773,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004957798860379187,
|
|
"loss": 5.469,
|
|
"mean_token_accuracy": 0.1609748274087906,
|
|
"num_tokens": 15404738.0,
|
|
"step": 8875
|
|
},
|
|
{
|
|
"entropy": 5.707740259170532,
|
|
"epoch": 0.6909161641703949,
|
|
"grad_norm": 2.953125,
|
|
"learning_rate": 0.0004957745416247022,
|
|
"loss": 5.6161,
|
|
"mean_token_accuracy": 0.16215184330940247,
|
|
"num_tokens": 15413530.0,
|
|
"step": 8880
|
|
},
|
|
{
|
|
"entropy": 5.658771181106568,
|
|
"epoch": 0.6913051935421124,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004957691938615833,
|
|
"loss": 5.5979,
|
|
"mean_token_accuracy": 0.1575539380311966,
|
|
"num_tokens": 15423268.0,
|
|
"step": 8885
|
|
},
|
|
{
|
|
"entropy": 5.570215463638306,
|
|
"epoch": 0.69169422291383,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004957638427486434,
|
|
"loss": 5.4021,
|
|
"mean_token_accuracy": 0.16531491428613662,
|
|
"num_tokens": 15431690.0,
|
|
"step": 8890
|
|
},
|
|
{
|
|
"entropy": 5.5720734119415285,
|
|
"epoch": 0.6920832522855476,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004957584882859636,
|
|
"loss": 5.569,
|
|
"mean_token_accuracy": 0.15523021072149276,
|
|
"num_tokens": 15440110.0,
|
|
"step": 8895
|
|
},
|
|
{
|
|
"entropy": 5.686567497253418,
|
|
"epoch": 0.6924722816572652,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.0004957531304736251,
|
|
"loss": 5.576,
|
|
"mean_token_accuracy": 0.15708936154842376,
|
|
"num_tokens": 15449022.0,
|
|
"step": 8900
|
|
},
|
|
{
|
|
"entropy": 5.728050661087036,
|
|
"epoch": 0.6928613110289827,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.0004957477693117091,
|
|
"loss": 5.6224,
|
|
"mean_token_accuracy": 0.15154694020748138,
|
|
"num_tokens": 15457826.0,
|
|
"step": 8905
|
|
},
|
|
{
|
|
"entropy": 5.601177978515625,
|
|
"epoch": 0.6932503404007002,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004957424048002971,
|
|
"loss": 5.5138,
|
|
"mean_token_accuracy": 0.1563497856259346,
|
|
"num_tokens": 15466631.0,
|
|
"step": 8910
|
|
},
|
|
{
|
|
"entropy": 5.528668403625488,
|
|
"epoch": 0.6936393697724178,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0004957370369394706,
|
|
"loss": 5.4116,
|
|
"mean_token_accuracy": 0.16306893676519393,
|
|
"num_tokens": 15474666.0,
|
|
"step": 8915
|
|
},
|
|
{
|
|
"entropy": 5.543035888671875,
|
|
"epoch": 0.6940283991441354,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.0004957316657293107,
|
|
"loss": 5.4129,
|
|
"mean_token_accuracy": 0.16565580666065216,
|
|
"num_tokens": 15483576.0,
|
|
"step": 8920
|
|
},
|
|
{
|
|
"entropy": 5.803154230117798,
|
|
"epoch": 0.694417428515853,
|
|
"grad_norm": 2.421875,
|
|
"learning_rate": 0.0004957262911698992,
|
|
"loss": 5.566,
|
|
"mean_token_accuracy": 0.15601008310914039,
|
|
"num_tokens": 15491313.0,
|
|
"step": 8925
|
|
},
|
|
{
|
|
"entropy": 5.666537857055664,
|
|
"epoch": 0.6948064578875706,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.0004957209132613175,
|
|
"loss": 5.5152,
|
|
"mean_token_accuracy": 0.15791357979178428,
|
|
"num_tokens": 15500638.0,
|
|
"step": 8930
|
|
},
|
|
{
|
|
"entropy": 5.618542051315307,
|
|
"epoch": 0.695195487259288,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004957155320036473,
|
|
"loss": 5.5223,
|
|
"mean_token_accuracy": 0.15979767590761185,
|
|
"num_tokens": 15509170.0,
|
|
"step": 8935
|
|
},
|
|
{
|
|
"entropy": 5.7393208026885985,
|
|
"epoch": 0.6955845166310056,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.0004957101473969702,
|
|
"loss": 5.6088,
|
|
"mean_token_accuracy": 0.15350990295410155,
|
|
"num_tokens": 15518108.0,
|
|
"step": 8940
|
|
},
|
|
{
|
|
"entropy": 5.579078960418701,
|
|
"epoch": 0.6959735460027232,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.000495704759441368,
|
|
"loss": 5.4479,
|
|
"mean_token_accuracy": 0.16417913734912873,
|
|
"num_tokens": 15526558.0,
|
|
"step": 8945
|
|
},
|
|
{
|
|
"entropy": 5.583064270019531,
|
|
"epoch": 0.6963625753744408,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004956993681369221,
|
|
"loss": 5.413,
|
|
"mean_token_accuracy": 0.16395225673913955,
|
|
"num_tokens": 15535685.0,
|
|
"step": 8950
|
|
},
|
|
{
|
|
"entropy": 5.628601312637329,
|
|
"epoch": 0.6967516047461584,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 0.0004956939734837148,
|
|
"loss": 5.4753,
|
|
"mean_token_accuracy": 0.16717747002840042,
|
|
"num_tokens": 15544072.0,
|
|
"step": 8955
|
|
},
|
|
{
|
|
"entropy": 5.632556056976318,
|
|
"epoch": 0.6971406341178759,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.0004956885754818277,
|
|
"loss": 5.5789,
|
|
"mean_token_accuracy": 0.15277515202760697,
|
|
"num_tokens": 15553303.0,
|
|
"step": 8960
|
|
},
|
|
{
|
|
"entropy": 5.644996452331543,
|
|
"epoch": 0.6975296634895934,
|
|
"grad_norm": 3.03125,
|
|
"learning_rate": 0.0004956831741313427,
|
|
"loss": 5.5102,
|
|
"mean_token_accuracy": 0.16035827547311782,
|
|
"num_tokens": 15561942.0,
|
|
"step": 8965
|
|
},
|
|
{
|
|
"entropy": 5.62465991973877,
|
|
"epoch": 0.697918692861311,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0004956777694323418,
|
|
"loss": 5.3747,
|
|
"mean_token_accuracy": 0.16847677677869796,
|
|
"num_tokens": 15569988.0,
|
|
"step": 8970
|
|
},
|
|
{
|
|
"entropy": 5.6361072063446045,
|
|
"epoch": 0.6983077222330286,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.000495672361384907,
|
|
"loss": 5.549,
|
|
"mean_token_accuracy": 0.16136890202760695,
|
|
"num_tokens": 15579816.0,
|
|
"step": 8975
|
|
},
|
|
{
|
|
"entropy": 5.63524284362793,
|
|
"epoch": 0.6986967516047462,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.0004956669499891202,
|
|
"loss": 5.4326,
|
|
"mean_token_accuracy": 0.16256033033132553,
|
|
"num_tokens": 15587843.0,
|
|
"step": 8980
|
|
},
|
|
{
|
|
"entropy": 5.624484348297119,
|
|
"epoch": 0.6990857809764637,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.0004956615352450639,
|
|
"loss": 5.4869,
|
|
"mean_token_accuracy": 0.1596302568912506,
|
|
"num_tokens": 15596798.0,
|
|
"step": 8985
|
|
},
|
|
{
|
|
"entropy": 5.646032047271729,
|
|
"epoch": 0.6994748103481813,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004956561171528198,
|
|
"loss": 5.5867,
|
|
"mean_token_accuracy": 0.16378770321607589,
|
|
"num_tokens": 15605360.0,
|
|
"step": 8990
|
|
},
|
|
{
|
|
"entropy": 5.6322832107543945,
|
|
"epoch": 0.6998638397198989,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004956506957124704,
|
|
"loss": 5.4436,
|
|
"mean_token_accuracy": 0.16614063680171967,
|
|
"num_tokens": 15613557.0,
|
|
"step": 8995
|
|
},
|
|
{
|
|
"entropy": 5.640901947021485,
|
|
"epoch": 0.7002528690916164,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.000495645270924098,
|
|
"loss": 5.5026,
|
|
"mean_token_accuracy": 0.16067280769348144,
|
|
"num_tokens": 15622144.0,
|
|
"step": 9000
|
|
},
|
|
{
|
|
"epoch": 0.7002528690916164,
|
|
"eval_entropy": 5.481020225344999,
|
|
"eval_loss": 5.542707443237305,
|
|
"eval_mean_token_accuracy": 0.1670644561311049,
|
|
"eval_num_tokens": 15622144.0,
|
|
"eval_runtime": 28.4159,
|
|
"eval_samples_per_second": 1462.491,
|
|
"eval_steps_per_second": 182.82,
|
|
"step": 9000
|
|
},
|
|
{
|
|
"entropy": 5.585732746124267,
|
|
"epoch": 0.700641898463334,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0004956398427877847,
|
|
"loss": 5.4665,
|
|
"mean_token_accuracy": 0.16098597049713134,
|
|
"num_tokens": 15631119.0,
|
|
"step": 9005
|
|
},
|
|
{
|
|
"entropy": 5.586934518814087,
|
|
"epoch": 0.7010309278350515,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.000495634411303613,
|
|
"loss": 5.3769,
|
|
"mean_token_accuracy": 0.17008570432662964,
|
|
"num_tokens": 15639969.0,
|
|
"step": 9010
|
|
},
|
|
{
|
|
"entropy": 5.6259363174438475,
|
|
"epoch": 0.7014199572067691,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004956289764716654,
|
|
"loss": 5.5113,
|
|
"mean_token_accuracy": 0.1631990358233452,
|
|
"num_tokens": 15648522.0,
|
|
"step": 9015
|
|
},
|
|
{
|
|
"entropy": 5.5738709449768065,
|
|
"epoch": 0.7018089865784867,
|
|
"grad_norm": 1.9375,
|
|
"learning_rate": 0.0004956235382920241,
|
|
"loss": 5.4516,
|
|
"mean_token_accuracy": 0.15761517211794854,
|
|
"num_tokens": 15656834.0,
|
|
"step": 9020
|
|
},
|
|
{
|
|
"entropy": 5.699477100372315,
|
|
"epoch": 0.7021980159502043,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.0004956180967647717,
|
|
"loss": 5.6285,
|
|
"mean_token_accuracy": 0.15442633032798767,
|
|
"num_tokens": 15665066.0,
|
|
"step": 9025
|
|
},
|
|
{
|
|
"entropy": 5.655051946640015,
|
|
"epoch": 0.7025870453219218,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.0004956126518899911,
|
|
"loss": 5.5198,
|
|
"mean_token_accuracy": 0.1598118796944618,
|
|
"num_tokens": 15673733.0,
|
|
"step": 9030
|
|
},
|
|
{
|
|
"entropy": 5.681368207931518,
|
|
"epoch": 0.7029760746936393,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004956072036677644,
|
|
"loss": 5.5498,
|
|
"mean_token_accuracy": 0.16067148745059967,
|
|
"num_tokens": 15682212.0,
|
|
"step": 9035
|
|
},
|
|
{
|
|
"entropy": 5.657479095458984,
|
|
"epoch": 0.7033651040653569,
|
|
"grad_norm": 1.9375,
|
|
"learning_rate": 0.0004956017520981746,
|
|
"loss": 5.5429,
|
|
"mean_token_accuracy": 0.15632517486810685,
|
|
"num_tokens": 15690518.0,
|
|
"step": 9040
|
|
},
|
|
{
|
|
"entropy": 5.725580358505249,
|
|
"epoch": 0.7037541334370745,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.0004955962971813044,
|
|
"loss": 5.5902,
|
|
"mean_token_accuracy": 0.14784593582153321,
|
|
"num_tokens": 15699474.0,
|
|
"step": 9045
|
|
},
|
|
{
|
|
"entropy": 5.709520435333252,
|
|
"epoch": 0.7041431628087921,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.0004955908389172364,
|
|
"loss": 5.6139,
|
|
"mean_token_accuracy": 0.1545947015285492,
|
|
"num_tokens": 15708571.0,
|
|
"step": 9050
|
|
},
|
|
{
|
|
"entropy": 5.7216517448425295,
|
|
"epoch": 0.7045321921805097,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004955853773060536,
|
|
"loss": 5.5799,
|
|
"mean_token_accuracy": 0.15980926752090455,
|
|
"num_tokens": 15717307.0,
|
|
"step": 9055
|
|
},
|
|
{
|
|
"entropy": 5.637844657897949,
|
|
"epoch": 0.7049212215522271,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004955799123478388,
|
|
"loss": 5.3684,
|
|
"mean_token_accuracy": 0.16487945318222047,
|
|
"num_tokens": 15725502.0,
|
|
"step": 9060
|
|
},
|
|
{
|
|
"entropy": 5.572454261779785,
|
|
"epoch": 0.7053102509239447,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 0.0004955744440426748,
|
|
"loss": 5.5754,
|
|
"mean_token_accuracy": 0.15618395507335664,
|
|
"num_tokens": 15734805.0,
|
|
"step": 9065
|
|
},
|
|
{
|
|
"entropy": 5.585596179962158,
|
|
"epoch": 0.7056992802956623,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.0004955689723906448,
|
|
"loss": 5.4442,
|
|
"mean_token_accuracy": 0.1570254385471344,
|
|
"num_tokens": 15743313.0,
|
|
"step": 9070
|
|
},
|
|
{
|
|
"entropy": 5.547364377975464,
|
|
"epoch": 0.7060883096673799,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004955634973918318,
|
|
"loss": 5.3747,
|
|
"mean_token_accuracy": 0.1677783727645874,
|
|
"num_tokens": 15752552.0,
|
|
"step": 9075
|
|
},
|
|
{
|
|
"entropy": 5.6287641525268555,
|
|
"epoch": 0.7064773390390975,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004955580190463186,
|
|
"loss": 5.5068,
|
|
"mean_token_accuracy": 0.16526139080524443,
|
|
"num_tokens": 15761404.0,
|
|
"step": 9080
|
|
},
|
|
{
|
|
"entropy": 5.6734143733978275,
|
|
"epoch": 0.7068663684108151,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004955525373541886,
|
|
"loss": 5.5707,
|
|
"mean_token_accuracy": 0.1583953768014908,
|
|
"num_tokens": 15770605.0,
|
|
"step": 9085
|
|
},
|
|
{
|
|
"entropy": 5.640336370468139,
|
|
"epoch": 0.7072553977825325,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.0004955470523155249,
|
|
"loss": 5.4436,
|
|
"mean_token_accuracy": 0.16466528326272964,
|
|
"num_tokens": 15778047.0,
|
|
"step": 9090
|
|
},
|
|
{
|
|
"entropy": 5.5981364250183105,
|
|
"epoch": 0.7076444271542501,
|
|
"grad_norm": 3.046875,
|
|
"learning_rate": 0.0004955415639304107,
|
|
"loss": 5.5078,
|
|
"mean_token_accuracy": 0.16325851976871492,
|
|
"num_tokens": 15788304.0,
|
|
"step": 9095
|
|
},
|
|
{
|
|
"entropy": 5.685591745376587,
|
|
"epoch": 0.7080334565259677,
|
|
"grad_norm": 4.96875,
|
|
"learning_rate": 0.0004955360721989292,
|
|
"loss": 5.5033,
|
|
"mean_token_accuracy": 0.16002848297357558,
|
|
"num_tokens": 15796448.0,
|
|
"step": 9100
|
|
},
|
|
{
|
|
"entropy": 5.63884391784668,
|
|
"epoch": 0.7084224858976853,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004955305771211641,
|
|
"loss": 5.4685,
|
|
"mean_token_accuracy": 0.16199948340654374,
|
|
"num_tokens": 15805072.0,
|
|
"step": 9105
|
|
},
|
|
{
|
|
"entropy": 5.595241117477417,
|
|
"epoch": 0.7088115152694029,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004955250786971982,
|
|
"loss": 5.5189,
|
|
"mean_token_accuracy": 0.15925498455762863,
|
|
"num_tokens": 15813918.0,
|
|
"step": 9110
|
|
},
|
|
{
|
|
"entropy": 5.73417592048645,
|
|
"epoch": 0.7092005446411204,
|
|
"grad_norm": 1.890625,
|
|
"learning_rate": 0.0004955195769271154,
|
|
"loss": 5.6505,
|
|
"mean_token_accuracy": 0.15475647300481796,
|
|
"num_tokens": 15822675.0,
|
|
"step": 9115
|
|
},
|
|
{
|
|
"entropy": 5.64673171043396,
|
|
"epoch": 0.709589574012838,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004955140718109991,
|
|
"loss": 5.505,
|
|
"mean_token_accuracy": 0.15632180571556092,
|
|
"num_tokens": 15831056.0,
|
|
"step": 9120
|
|
},
|
|
{
|
|
"entropy": 5.625209045410156,
|
|
"epoch": 0.7099786033845555,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004955085633489326,
|
|
"loss": 5.5815,
|
|
"mean_token_accuracy": 0.15593838989734649,
|
|
"num_tokens": 15839948.0,
|
|
"step": 9125
|
|
},
|
|
{
|
|
"entropy": 5.690494441986084,
|
|
"epoch": 0.7103676327562731,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004955030515409997,
|
|
"loss": 5.4862,
|
|
"mean_token_accuracy": 0.16232281774282456,
|
|
"num_tokens": 15848738.0,
|
|
"step": 9130
|
|
},
|
|
{
|
|
"entropy": 5.669245862960816,
|
|
"epoch": 0.7107566621279907,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004954975363872838,
|
|
"loss": 5.5545,
|
|
"mean_token_accuracy": 0.1527140259742737,
|
|
"num_tokens": 15859073.0,
|
|
"step": 9135
|
|
},
|
|
{
|
|
"entropy": 5.635107851028442,
|
|
"epoch": 0.7111456914997082,
|
|
"grad_norm": 2.6875,
|
|
"learning_rate": 0.0004954920178878689,
|
|
"loss": 5.4571,
|
|
"mean_token_accuracy": 0.16001232713460922,
|
|
"num_tokens": 15868146.0,
|
|
"step": 9140
|
|
},
|
|
{
|
|
"entropy": 5.543806743621826,
|
|
"epoch": 0.7115347208714258,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004954864960428385,
|
|
"loss": 5.4088,
|
|
"mean_token_accuracy": 0.16015568524599075,
|
|
"num_tokens": 15876915.0,
|
|
"step": 9145
|
|
},
|
|
{
|
|
"entropy": 5.559432744979858,
|
|
"epoch": 0.7119237502431434,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004954809708522765,
|
|
"loss": 5.4847,
|
|
"mean_token_accuracy": 0.16128282994031906,
|
|
"num_tokens": 15884947.0,
|
|
"step": 9150
|
|
},
|
|
{
|
|
"entropy": 5.6296576976776125,
|
|
"epoch": 0.712312779614861,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.0004954754423162667,
|
|
"loss": 5.4904,
|
|
"mean_token_accuracy": 0.15905167758464814,
|
|
"num_tokens": 15894595.0,
|
|
"step": 9155
|
|
},
|
|
{
|
|
"entropy": 5.665063953399658,
|
|
"epoch": 0.7127018089865785,
|
|
"grad_norm": 2.671875,
|
|
"learning_rate": 0.000495469910434893,
|
|
"loss": 5.4715,
|
|
"mean_token_accuracy": 0.16523981988430023,
|
|
"num_tokens": 15902920.0,
|
|
"step": 9160
|
|
},
|
|
{
|
|
"entropy": 5.6030768871307375,
|
|
"epoch": 0.713090838358296,
|
|
"grad_norm": 2.453125,
|
|
"learning_rate": 0.0004954643752082392,
|
|
"loss": 5.4704,
|
|
"mean_token_accuracy": 0.15966468602418898,
|
|
"num_tokens": 15911414.0,
|
|
"step": 9165
|
|
},
|
|
{
|
|
"entropy": 5.681358098983765,
|
|
"epoch": 0.7134798677300136,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.0004954588366363896,
|
|
"loss": 5.5542,
|
|
"mean_token_accuracy": 0.15529291331768036,
|
|
"num_tokens": 15919855.0,
|
|
"step": 9170
|
|
},
|
|
{
|
|
"entropy": 5.660662412643433,
|
|
"epoch": 0.7138688971017312,
|
|
"grad_norm": 1.90625,
|
|
"learning_rate": 0.0004954532947194279,
|
|
"loss": 5.4792,
|
|
"mean_token_accuracy": 0.1614113688468933,
|
|
"num_tokens": 15928932.0,
|
|
"step": 9175
|
|
},
|
|
{
|
|
"entropy": 5.656718635559082,
|
|
"epoch": 0.7142579264734488,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.0004954477494574384,
|
|
"loss": 5.5263,
|
|
"mean_token_accuracy": 0.1601121410727501,
|
|
"num_tokens": 15938266.0,
|
|
"step": 9180
|
|
},
|
|
{
|
|
"entropy": 5.685669565200806,
|
|
"epoch": 0.7146469558451664,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004954422008505052,
|
|
"loss": 5.554,
|
|
"mean_token_accuracy": 0.1583024173974991,
|
|
"num_tokens": 15947100.0,
|
|
"step": 9185
|
|
},
|
|
{
|
|
"entropy": 5.656893396377564,
|
|
"epoch": 0.7150359852168838,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.0004954366488987125,
|
|
"loss": 5.5747,
|
|
"mean_token_accuracy": 0.153174552321434,
|
|
"num_tokens": 15955544.0,
|
|
"step": 9190
|
|
},
|
|
{
|
|
"entropy": 5.734490299224854,
|
|
"epoch": 0.7154250145886014,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.0004954310936021444,
|
|
"loss": 5.5682,
|
|
"mean_token_accuracy": 0.15914405286312103,
|
|
"num_tokens": 15963372.0,
|
|
"step": 9195
|
|
},
|
|
{
|
|
"entropy": 5.683928108215332,
|
|
"epoch": 0.715814043960319,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.0004954255349608853,
|
|
"loss": 5.5464,
|
|
"mean_token_accuracy": 0.14897577464580536,
|
|
"num_tokens": 15972940.0,
|
|
"step": 9200
|
|
},
|
|
{
|
|
"entropy": 5.631432104110718,
|
|
"epoch": 0.7162030733320366,
|
|
"grad_norm": 2.296875,
|
|
"learning_rate": 0.0004954199729750198,
|
|
"loss": 5.5127,
|
|
"mean_token_accuracy": 0.15798016041517257,
|
|
"num_tokens": 15982238.0,
|
|
"step": 9205
|
|
},
|
|
{
|
|
"entropy": 5.685957050323486,
|
|
"epoch": 0.7165921027037542,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.0004954144076446318,
|
|
"loss": 5.5261,
|
|
"mean_token_accuracy": 0.15847227573394776,
|
|
"num_tokens": 15990835.0,
|
|
"step": 9210
|
|
},
|
|
{
|
|
"entropy": 5.739234828948975,
|
|
"epoch": 0.7169811320754716,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.0004954088389698061,
|
|
"loss": 5.6394,
|
|
"mean_token_accuracy": 0.15139928087592125,
|
|
"num_tokens": 16000649.0,
|
|
"step": 9215
|
|
},
|
|
{
|
|
"entropy": 5.637101650238037,
|
|
"epoch": 0.7173701614471892,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.000495403266950627,
|
|
"loss": 5.5311,
|
|
"mean_token_accuracy": 0.15559172630310059,
|
|
"num_tokens": 16009214.0,
|
|
"step": 9220
|
|
},
|
|
{
|
|
"entropy": 5.65802001953125,
|
|
"epoch": 0.7177591908189068,
|
|
"grad_norm": 2.359375,
|
|
"learning_rate": 0.0004953976915871792,
|
|
"loss": 5.5336,
|
|
"mean_token_accuracy": 0.16114290058612823,
|
|
"num_tokens": 16018173.0,
|
|
"step": 9225
|
|
},
|
|
{
|
|
"entropy": 5.5929539680480955,
|
|
"epoch": 0.7181482201906244,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.0004953921128795472,
|
|
"loss": 5.3917,
|
|
"mean_token_accuracy": 0.17421648204326629,
|
|
"num_tokens": 16026857.0,
|
|
"step": 9230
|
|
},
|
|
{
|
|
"entropy": 5.600043630599975,
|
|
"epoch": 0.718537249562342,
|
|
"grad_norm": 2.375,
|
|
"learning_rate": 0.0004953865308278156,
|
|
"loss": 5.5882,
|
|
"mean_token_accuracy": 0.15707600712776185,
|
|
"num_tokens": 16035792.0,
|
|
"step": 9235
|
|
},
|
|
{
|
|
"entropy": 5.655224943161011,
|
|
"epoch": 0.7189262789340595,
|
|
"grad_norm": 1.90625,
|
|
"learning_rate": 0.0004953809454320693,
|
|
"loss": 5.5049,
|
|
"mean_token_accuracy": 0.1625637248158455,
|
|
"num_tokens": 16044874.0,
|
|
"step": 9240
|
|
},
|
|
{
|
|
"entropy": 5.674201583862304,
|
|
"epoch": 0.7193153083057771,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.0004953753566923929,
|
|
"loss": 5.4761,
|
|
"mean_token_accuracy": 0.15769220739603043,
|
|
"num_tokens": 16053705.0,
|
|
"step": 9245
|
|
},
|
|
{
|
|
"entropy": 5.661291933059692,
|
|
"epoch": 0.7197043376774946,
|
|
"grad_norm": 1.984375,
|
|
"learning_rate": 0.0004953697646088712,
|
|
"loss": 5.498,
|
|
"mean_token_accuracy": 0.1612485483288765,
|
|
"num_tokens": 16062987.0,
|
|
"step": 9250
|
|
},
|
|
{
|
|
"entropy": 5.610112619400025,
|
|
"epoch": 0.7200933670492122,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 0.0004953641691815891,
|
|
"loss": 5.4493,
|
|
"mean_token_accuracy": 0.16196974664926528,
|
|
"num_tokens": 16071247.0,
|
|
"step": 9255
|
|
},
|
|
{
|
|
"entropy": 5.546336889266968,
|
|
"epoch": 0.7204823964209298,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004953585704106315,
|
|
"loss": 5.4047,
|
|
"mean_token_accuracy": 0.1604311063885689,
|
|
"num_tokens": 16080190.0,
|
|
"step": 9260
|
|
},
|
|
{
|
|
"entropy": 5.650618076324463,
|
|
"epoch": 0.7208714257926473,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004953529682960832,
|
|
"loss": 5.4958,
|
|
"mean_token_accuracy": 0.16436949074268342,
|
|
"num_tokens": 16088885.0,
|
|
"step": 9265
|
|
},
|
|
{
|
|
"entropy": 5.637788772583008,
|
|
"epoch": 0.7212604551643649,
|
|
"grad_norm": 2.40625,
|
|
"learning_rate": 0.0004953473628380295,
|
|
"loss": 5.4379,
|
|
"mean_token_accuracy": 0.164384363591671,
|
|
"num_tokens": 16097202.0,
|
|
"step": 9270
|
|
},
|
|
{
|
|
"entropy": 5.562393522262573,
|
|
"epoch": 0.7216494845360825,
|
|
"grad_norm": 1.9375,
|
|
"learning_rate": 0.0004953417540365553,
|
|
"loss": 5.4136,
|
|
"mean_token_accuracy": 0.15989380627870559,
|
|
"num_tokens": 16105468.0,
|
|
"step": 9275
|
|
},
|
|
{
|
|
"entropy": 5.646288299560547,
|
|
"epoch": 0.7220385139078,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.0004953361418917455,
|
|
"loss": 5.5627,
|
|
"mean_token_accuracy": 0.16040711998939514,
|
|
"num_tokens": 16114624.0,
|
|
"step": 9280
|
|
},
|
|
{
|
|
"entropy": 5.594670629501342,
|
|
"epoch": 0.7224275432795176,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004953305264036856,
|
|
"loss": 5.4097,
|
|
"mean_token_accuracy": 0.16768305003643036,
|
|
"num_tokens": 16123983.0,
|
|
"step": 9285
|
|
},
|
|
{
|
|
"entropy": 5.630219411849976,
|
|
"epoch": 0.7228165726512352,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.0004953249075724607,
|
|
"loss": 5.5111,
|
|
"mean_token_accuracy": 0.16575048118829727,
|
|
"num_tokens": 16132886.0,
|
|
"step": 9290
|
|
},
|
|
{
|
|
"entropy": 5.560100746154785,
|
|
"epoch": 0.7232056020229527,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.0004953192853981559,
|
|
"loss": 5.3652,
|
|
"mean_token_accuracy": 0.16712887436151505,
|
|
"num_tokens": 16141526.0,
|
|
"step": 9295
|
|
},
|
|
{
|
|
"entropy": 5.614591646194458,
|
|
"epoch": 0.7235946313946703,
|
|
"grad_norm": 2.578125,
|
|
"learning_rate": 0.0004953136598808566,
|
|
"loss": 5.5744,
|
|
"mean_token_accuracy": 0.16574664711952208,
|
|
"num_tokens": 16149949.0,
|
|
"step": 9300
|
|
},
|
|
{
|
|
"entropy": 5.6114363193511965,
|
|
"epoch": 0.7239836607663879,
|
|
"grad_norm": 1.9296875,
|
|
"learning_rate": 0.0004953080310206481,
|
|
"loss": 5.5194,
|
|
"mean_token_accuracy": 0.15931165367364883,
|
|
"num_tokens": 16158131.0,
|
|
"step": 9305
|
|
},
|
|
{
|
|
"entropy": 5.5885687351226805,
|
|
"epoch": 0.7243726901381055,
|
|
"grad_norm": 1.96875,
|
|
"learning_rate": 0.0004953023988176162,
|
|
"loss": 5.4361,
|
|
"mean_token_accuracy": 0.1658329576253891,
|
|
"num_tokens": 16167131.0,
|
|
"step": 9310
|
|
},
|
|
{
|
|
"entropy": 5.680842876434326,
|
|
"epoch": 0.724761719509823,
|
|
"grad_norm": 1.921875,
|
|
"learning_rate": 0.0004952967632718458,
|
|
"loss": 5.6565,
|
|
"mean_token_accuracy": 0.157668836414814,
|
|
"num_tokens": 16176198.0,
|
|
"step": 9315
|
|
},
|
|
{
|
|
"entropy": 5.606712198257446,
|
|
"epoch": 0.7251507488815405,
|
|
"grad_norm": 2.421875,
|
|
"learning_rate": 0.0004952911243834227,
|
|
"loss": 5.5042,
|
|
"mean_token_accuracy": 0.16173390448093414,
|
|
"num_tokens": 16184860.0,
|
|
"step": 9320
|
|
},
|
|
{
|
|
"entropy": 5.60709581375122,
|
|
"epoch": 0.7255397782532581,
|
|
"grad_norm": 1.84375,
|
|
"learning_rate": 0.0004952854821524324,
|
|
"loss": 5.5053,
|
|
"mean_token_accuracy": 0.15811700522899627,
|
|
"num_tokens": 16193126.0,
|
|
"step": 9325
|
|
},
|
|
{
|
|
"entropy": 5.606113290786743,
|
|
"epoch": 0.7259288076249757,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.0004952798365789606,
|
|
"loss": 5.481,
|
|
"mean_token_accuracy": 0.16182010918855666,
|
|
"num_tokens": 16201763.0,
|
|
"step": 9330
|
|
},
|
|
{
|
|
"entropy": 5.634562635421753,
|
|
"epoch": 0.7263178369966933,
|
|
"grad_norm": 2.78125,
|
|
"learning_rate": 0.0004952741876630928,
|
|
"loss": 5.4294,
|
|
"mean_token_accuracy": 0.16526045501232148,
|
|
"num_tokens": 16210947.0,
|
|
"step": 9335
|
|
},
|
|
{
|
|
"entropy": 5.6353339672088625,
|
|
"epoch": 0.7267068663684109,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004952685354049148,
|
|
"loss": 5.521,
|
|
"mean_token_accuracy": 0.1525568626821041,
|
|
"num_tokens": 16219772.0,
|
|
"step": 9340
|
|
},
|
|
{
|
|
"entropy": 5.6257201671600345,
|
|
"epoch": 0.7270958957401283,
|
|
"grad_norm": 1.9609375,
|
|
"learning_rate": 0.0004952628798045124,
|
|
"loss": 5.4972,
|
|
"mean_token_accuracy": 0.16923587322235106,
|
|
"num_tokens": 16227759.0,
|
|
"step": 9345
|
|
},
|
|
{
|
|
"entropy": 5.551531410217285,
|
|
"epoch": 0.7274849251118459,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.0004952572208619714,
|
|
"loss": 5.3975,
|
|
"mean_token_accuracy": 0.16126310378313063,
|
|
"num_tokens": 16236913.0,
|
|
"step": 9350
|
|
},
|
|
{
|
|
"entropy": 5.649960708618164,
|
|
"epoch": 0.7278739544835635,
|
|
"grad_norm": 1.9296875,
|
|
"learning_rate": 0.0004952515585773778,
|
|
"loss": 5.5149,
|
|
"mean_token_accuracy": 0.15768635123968125,
|
|
"num_tokens": 16246190.0,
|
|
"step": 9355
|
|
},
|
|
{
|
|
"entropy": 5.641130685806274,
|
|
"epoch": 0.7282629838552811,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004952458929508171,
|
|
"loss": 5.4686,
|
|
"mean_token_accuracy": 0.1606806308031082,
|
|
"num_tokens": 16255476.0,
|
|
"step": 9360
|
|
},
|
|
{
|
|
"entropy": 5.638977527618408,
|
|
"epoch": 0.7286520132269987,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.0004952402239823757,
|
|
"loss": 5.5236,
|
|
"mean_token_accuracy": 0.15900709182024003,
|
|
"num_tokens": 16264701.0,
|
|
"step": 9365
|
|
},
|
|
{
|
|
"entropy": 5.504604482650757,
|
|
"epoch": 0.7290410425987162,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004952345516721393,
|
|
"loss": 5.3403,
|
|
"mean_token_accuracy": 0.17384974509477616,
|
|
"num_tokens": 16272999.0,
|
|
"step": 9370
|
|
},
|
|
{
|
|
"entropy": 5.679075050354004,
|
|
"epoch": 0.7294300719704337,
|
|
"grad_norm": 1.96875,
|
|
"learning_rate": 0.0004952288760201942,
|
|
"loss": 5.6432,
|
|
"mean_token_accuracy": 0.15582889020442964,
|
|
"num_tokens": 16282537.0,
|
|
"step": 9375
|
|
},
|
|
{
|
|
"entropy": 5.6804201126098635,
|
|
"epoch": 0.7298191013421513,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.0004952231970266265,
|
|
"loss": 5.4852,
|
|
"mean_token_accuracy": 0.16253642141819,
|
|
"num_tokens": 16291155.0,
|
|
"step": 9380
|
|
},
|
|
{
|
|
"entropy": 5.7331489562988285,
|
|
"epoch": 0.7302081307138689,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.0004952175146915223,
|
|
"loss": 5.5439,
|
|
"mean_token_accuracy": 0.15446304231882096,
|
|
"num_tokens": 16300466.0,
|
|
"step": 9385
|
|
},
|
|
{
|
|
"entropy": 5.696057319641113,
|
|
"epoch": 0.7305971600855865,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.0004952118290149679,
|
|
"loss": 5.4473,
|
|
"mean_token_accuracy": 0.1621690273284912,
|
|
"num_tokens": 16309250.0,
|
|
"step": 9390
|
|
},
|
|
{
|
|
"entropy": 5.6693626880645756,
|
|
"epoch": 0.730986189457304,
|
|
"grad_norm": 3.734375,
|
|
"learning_rate": 0.0004952061399970492,
|
|
"loss": 5.5543,
|
|
"mean_token_accuracy": 0.15923163443803787,
|
|
"num_tokens": 16318056.0,
|
|
"step": 9395
|
|
},
|
|
{
|
|
"entropy": 5.563495874404907,
|
|
"epoch": 0.7313752188290216,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.000495200447637853,
|
|
"loss": 5.4149,
|
|
"mean_token_accuracy": 0.16186962574720382,
|
|
"num_tokens": 16326455.0,
|
|
"step": 9400
|
|
},
|
|
{
|
|
"entropy": 5.613676595687866,
|
|
"epoch": 0.7317642482007392,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.0004951947519374655,
|
|
"loss": 5.3851,
|
|
"mean_token_accuracy": 0.16593369841575623,
|
|
"num_tokens": 16334584.0,
|
|
"step": 9405
|
|
},
|
|
{
|
|
"entropy": 5.593530511856079,
|
|
"epoch": 0.7321532775724567,
|
|
"grad_norm": 1.9375,
|
|
"learning_rate": 0.0004951890528959731,
|
|
"loss": 5.432,
|
|
"mean_token_accuracy": 0.17181985527276994,
|
|
"num_tokens": 16342361.0,
|
|
"step": 9410
|
|
},
|
|
{
|
|
"entropy": 5.641056728363037,
|
|
"epoch": 0.7325423069441743,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.0004951833505134623,
|
|
"loss": 5.5799,
|
|
"mean_token_accuracy": 0.15473203659057616,
|
|
"num_tokens": 16350414.0,
|
|
"step": 9415
|
|
},
|
|
{
|
|
"entropy": 5.582821655273437,
|
|
"epoch": 0.7329313363158918,
|
|
"grad_norm": 1.984375,
|
|
"learning_rate": 0.0004951776447900196,
|
|
"loss": 5.4128,
|
|
"mean_token_accuracy": 0.16726149916648864,
|
|
"num_tokens": 16359266.0,
|
|
"step": 9420
|
|
},
|
|
{
|
|
"entropy": 5.5615119457244875,
|
|
"epoch": 0.7333203656876094,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.0004951719357257317,
|
|
"loss": 5.3759,
|
|
"mean_token_accuracy": 0.16367839574813842,
|
|
"num_tokens": 16367558.0,
|
|
"step": 9425
|
|
},
|
|
{
|
|
"entropy": 5.491123342514038,
|
|
"epoch": 0.733709395059327,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.000495166223320685,
|
|
"loss": 5.371,
|
|
"mean_token_accuracy": 0.1723216563463211,
|
|
"num_tokens": 16375690.0,
|
|
"step": 9430
|
|
},
|
|
{
|
|
"entropy": 5.596658229827881,
|
|
"epoch": 0.7340984244310446,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.0004951605075749662,
|
|
"loss": 5.4948,
|
|
"mean_token_accuracy": 0.15959431380033492,
|
|
"num_tokens": 16384157.0,
|
|
"step": 9435
|
|
},
|
|
{
|
|
"entropy": 5.695177221298218,
|
|
"epoch": 0.7344874538027621,
|
|
"grad_norm": 1.9453125,
|
|
"learning_rate": 0.0004951547884886623,
|
|
"loss": 5.5234,
|
|
"mean_token_accuracy": 0.1647638648748398,
|
|
"num_tokens": 16392153.0,
|
|
"step": 9440
|
|
},
|
|
{
|
|
"entropy": 5.591506910324097,
|
|
"epoch": 0.7348764831744796,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.0004951490660618598,
|
|
"loss": 5.28,
|
|
"mean_token_accuracy": 0.17572504729032518,
|
|
"num_tokens": 16400132.0,
|
|
"step": 9445
|
|
},
|
|
{
|
|
"entropy": 5.574398231506348,
|
|
"epoch": 0.7352655125461972,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.0004951433402946457,
|
|
"loss": 5.467,
|
|
"mean_token_accuracy": 0.168536040186882,
|
|
"num_tokens": 16408297.0,
|
|
"step": 9450
|
|
},
|
|
{
|
|
"entropy": 5.567717790603638,
|
|
"epoch": 0.7356545419179148,
|
|
"grad_norm": 2.5625,
|
|
"learning_rate": 0.0004951376111871068,
|
|
"loss": 5.5293,
|
|
"mean_token_accuracy": 0.15959716439247132,
|
|
"num_tokens": 16417977.0,
|
|
"step": 9455
|
|
},
|
|
{
|
|
"entropy": 5.616516733169556,
|
|
"epoch": 0.7360435712896324,
|
|
"grad_norm": 1.90625,
|
|
"learning_rate": 0.0004951318787393299,
|
|
"loss": 5.4177,
|
|
"mean_token_accuracy": 0.16546871066093444,
|
|
"num_tokens": 16427156.0,
|
|
"step": 9460
|
|
},
|
|
{
|
|
"entropy": 5.722203397750855,
|
|
"epoch": 0.73643260066135,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004951261429514023,
|
|
"loss": 5.5909,
|
|
"mean_token_accuracy": 0.15716658234596254,
|
|
"num_tokens": 16435845.0,
|
|
"step": 9465
|
|
},
|
|
{
|
|
"entropy": 5.7211699962615965,
|
|
"epoch": 0.7368216300330674,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004951204038234106,
|
|
"loss": 5.5765,
|
|
"mean_token_accuracy": 0.16062406599521636,
|
|
"num_tokens": 16445876.0,
|
|
"step": 9470
|
|
},
|
|
{
|
|
"entropy": 5.644733333587647,
|
|
"epoch": 0.737210659404785,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004951146613554424,
|
|
"loss": 5.518,
|
|
"mean_token_accuracy": 0.15978551656007767,
|
|
"num_tokens": 16454688.0,
|
|
"step": 9475
|
|
},
|
|
{
|
|
"entropy": 5.646075773239136,
|
|
"epoch": 0.7375996887765026,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.0004951089155475843,
|
|
"loss": 5.5867,
|
|
"mean_token_accuracy": 0.15822823643684386,
|
|
"num_tokens": 16463932.0,
|
|
"step": 9480
|
|
},
|
|
{
|
|
"entropy": 5.664718961715698,
|
|
"epoch": 0.7379887181482202,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.000495103166399924,
|
|
"loss": 5.513,
|
|
"mean_token_accuracy": 0.16208630800247192,
|
|
"num_tokens": 16472627.0,
|
|
"step": 9485
|
|
},
|
|
{
|
|
"entropy": 5.715599441528321,
|
|
"epoch": 0.7383777475199378,
|
|
"grad_norm": 1.9375,
|
|
"learning_rate": 0.0004950974139125484,
|
|
"loss": 5.5396,
|
|
"mean_token_accuracy": 0.15638376772403717,
|
|
"num_tokens": 16480819.0,
|
|
"step": 9490
|
|
},
|
|
{
|
|
"entropy": 5.66302342414856,
|
|
"epoch": 0.7387667768916554,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0004950916580855448,
|
|
"loss": 5.5059,
|
|
"mean_token_accuracy": 0.1624343454837799,
|
|
"num_tokens": 16489055.0,
|
|
"step": 9495
|
|
},
|
|
{
|
|
"entropy": 5.622740983963013,
|
|
"epoch": 0.7391558062633728,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004950858989190007,
|
|
"loss": 5.4823,
|
|
"mean_token_accuracy": 0.16776468753814697,
|
|
"num_tokens": 16497375.0,
|
|
"step": 9500
|
|
},
|
|
{
|
|
"entropy": 5.537393188476562,
|
|
"epoch": 0.7395448356350904,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004950801364130032,
|
|
"loss": 5.3209,
|
|
"mean_token_accuracy": 0.16765717417001724,
|
|
"num_tokens": 16505183.0,
|
|
"step": 9505
|
|
},
|
|
{
|
|
"entropy": 5.615147638320923,
|
|
"epoch": 0.739933865006808,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.0004950743705676401,
|
|
"loss": 5.6049,
|
|
"mean_token_accuracy": 0.1514967694878578,
|
|
"num_tokens": 16514018.0,
|
|
"step": 9510
|
|
},
|
|
{
|
|
"entropy": 5.692941188812256,
|
|
"epoch": 0.7403228943785256,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004950686013829987,
|
|
"loss": 5.4906,
|
|
"mean_token_accuracy": 0.15955932885408403,
|
|
"num_tokens": 16522954.0,
|
|
"step": 9515
|
|
},
|
|
{
|
|
"entropy": 5.768866348266601,
|
|
"epoch": 0.7407119237502432,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004950628288591665,
|
|
"loss": 5.5342,
|
|
"mean_token_accuracy": 0.1594507798552513,
|
|
"num_tokens": 16530845.0,
|
|
"step": 9520
|
|
},
|
|
{
|
|
"entropy": 5.552059316635132,
|
|
"epoch": 0.7411009531219607,
|
|
"grad_norm": 1.90625,
|
|
"learning_rate": 0.0004950570529962311,
|
|
"loss": 5.5063,
|
|
"mean_token_accuracy": 0.15784285664558412,
|
|
"num_tokens": 16540464.0,
|
|
"step": 9525
|
|
},
|
|
{
|
|
"entropy": 5.485754013061523,
|
|
"epoch": 0.7414899824936783,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.0004950512737942803,
|
|
"loss": 5.4146,
|
|
"mean_token_accuracy": 0.17287331372499465,
|
|
"num_tokens": 16549485.0,
|
|
"step": 9530
|
|
},
|
|
{
|
|
"entropy": 5.656132221221924,
|
|
"epoch": 0.7418790118653958,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.0004950454912534015,
|
|
"loss": 5.5384,
|
|
"mean_token_accuracy": 0.16219408214092254,
|
|
"num_tokens": 16557854.0,
|
|
"step": 9535
|
|
},
|
|
{
|
|
"entropy": 5.697181510925293,
|
|
"epoch": 0.7422680412371134,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004950397053736827,
|
|
"loss": 5.5818,
|
|
"mean_token_accuracy": 0.1597079962491989,
|
|
"num_tokens": 16565975.0,
|
|
"step": 9540
|
|
},
|
|
{
|
|
"entropy": 5.628687334060669,
|
|
"epoch": 0.742657070608831,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004950339161552117,
|
|
"loss": 5.5408,
|
|
"mean_token_accuracy": 0.1615551769733429,
|
|
"num_tokens": 16575038.0,
|
|
"step": 9545
|
|
},
|
|
{
|
|
"entropy": 5.597901058197022,
|
|
"epoch": 0.7430460999805485,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004950281235980761,
|
|
"loss": 5.4056,
|
|
"mean_token_accuracy": 0.16709177792072297,
|
|
"num_tokens": 16584292.0,
|
|
"step": 9550
|
|
},
|
|
{
|
|
"entropy": 5.629160594940186,
|
|
"epoch": 0.7434351293522661,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.000495022327702364,
|
|
"loss": 5.4903,
|
|
"mean_token_accuracy": 0.1640079140663147,
|
|
"num_tokens": 16592331.0,
|
|
"step": 9555
|
|
},
|
|
{
|
|
"entropy": 5.612167119979858,
|
|
"epoch": 0.7438241587239837,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004950165284681631,
|
|
"loss": 5.4326,
|
|
"mean_token_accuracy": 0.16338339149951936,
|
|
"num_tokens": 16601845.0,
|
|
"step": 9560
|
|
},
|
|
{
|
|
"entropy": 5.6223516941070555,
|
|
"epoch": 0.7442131880957013,
|
|
"grad_norm": 1.90625,
|
|
"learning_rate": 0.0004950107258955618,
|
|
"loss": 5.5388,
|
|
"mean_token_accuracy": 0.16336617320775987,
|
|
"num_tokens": 16610438.0,
|
|
"step": 9565
|
|
},
|
|
{
|
|
"entropy": 5.549783086776733,
|
|
"epoch": 0.7446022174674188,
|
|
"grad_norm": 4.3125,
|
|
"learning_rate": 0.0004950049199846479,
|
|
"loss": 5.4327,
|
|
"mean_token_accuracy": 0.1653188481926918,
|
|
"num_tokens": 16618892.0,
|
|
"step": 9570
|
|
},
|
|
{
|
|
"entropy": 5.635569953918457,
|
|
"epoch": 0.7449912468391363,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.0004949991107355095,
|
|
"loss": 5.488,
|
|
"mean_token_accuracy": 0.16314953267574311,
|
|
"num_tokens": 16627702.0,
|
|
"step": 9575
|
|
},
|
|
{
|
|
"entropy": 5.593403911590576,
|
|
"epoch": 0.7453802762108539,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.0004949932981482347,
|
|
"loss": 5.3788,
|
|
"mean_token_accuracy": 0.1739512264728546,
|
|
"num_tokens": 16635653.0,
|
|
"step": 9580
|
|
},
|
|
{
|
|
"entropy": 5.597661828994751,
|
|
"epoch": 0.7457693055825715,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.0004949874822229118,
|
|
"loss": 5.5474,
|
|
"mean_token_accuracy": 0.15821805745363235,
|
|
"num_tokens": 16643898.0,
|
|
"step": 9585
|
|
},
|
|
{
|
|
"entropy": 5.598042345046997,
|
|
"epoch": 0.7461583349542891,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004949816629596288,
|
|
"loss": 5.4078,
|
|
"mean_token_accuracy": 0.1656778112053871,
|
|
"num_tokens": 16653126.0,
|
|
"step": 9590
|
|
},
|
|
{
|
|
"entropy": 5.6670866966247555,
|
|
"epoch": 0.7465473643260067,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.0004949758403584746,
|
|
"loss": 5.508,
|
|
"mean_token_accuracy": 0.1603545591235161,
|
|
"num_tokens": 16661561.0,
|
|
"step": 9595
|
|
},
|
|
{
|
|
"entropy": 5.632758951187133,
|
|
"epoch": 0.7469363936977241,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004949700144195368,
|
|
"loss": 5.4803,
|
|
"mean_token_accuracy": 0.16294486522674562,
|
|
"num_tokens": 16669657.0,
|
|
"step": 9600
|
|
},
|
|
{
|
|
"entropy": 5.568662023544311,
|
|
"epoch": 0.7473254230694417,
|
|
"grad_norm": 1.84375,
|
|
"learning_rate": 0.0004949641851429043,
|
|
"loss": 5.4804,
|
|
"mean_token_accuracy": 0.16198135763406754,
|
|
"num_tokens": 16678486.0,
|
|
"step": 9605
|
|
},
|
|
{
|
|
"entropy": 5.644936990737915,
|
|
"epoch": 0.7477144524411593,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004949583525286654,
|
|
"loss": 5.4425,
|
|
"mean_token_accuracy": 0.15747484266757966,
|
|
"num_tokens": 16686638.0,
|
|
"step": 9610
|
|
},
|
|
{
|
|
"entropy": 5.614390516281128,
|
|
"epoch": 0.7481034818128769,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004949525165769085,
|
|
"loss": 5.424,
|
|
"mean_token_accuracy": 0.16317679584026337,
|
|
"num_tokens": 16694393.0,
|
|
"step": 9615
|
|
},
|
|
{
|
|
"entropy": 5.61008129119873,
|
|
"epoch": 0.7484925111845945,
|
|
"grad_norm": 1.9140625,
|
|
"learning_rate": 0.0004949466772877224,
|
|
"loss": 5.4639,
|
|
"mean_token_accuracy": 0.16950817108154298,
|
|
"num_tokens": 16702613.0,
|
|
"step": 9620
|
|
},
|
|
{
|
|
"entropy": 5.608772802352905,
|
|
"epoch": 0.748881540556312,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004949408346611955,
|
|
"loss": 5.3889,
|
|
"mean_token_accuracy": 0.16656982600688935,
|
|
"num_tokens": 16711210.0,
|
|
"step": 9625
|
|
},
|
|
{
|
|
"entropy": 5.595449590682984,
|
|
"epoch": 0.7492705699280295,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004949349886974165,
|
|
"loss": 5.4488,
|
|
"mean_token_accuracy": 0.1682933509349823,
|
|
"num_tokens": 16719124.0,
|
|
"step": 9630
|
|
},
|
|
{
|
|
"entropy": 5.579593658447266,
|
|
"epoch": 0.7496595992997471,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.0004949291393964741,
|
|
"loss": 5.4598,
|
|
"mean_token_accuracy": 0.1643265649676323,
|
|
"num_tokens": 16727240.0,
|
|
"step": 9635
|
|
},
|
|
{
|
|
"entropy": 5.601654529571533,
|
|
"epoch": 0.7500486286714647,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.000494923286758457,
|
|
"loss": 5.5688,
|
|
"mean_token_accuracy": 0.16121819615364075,
|
|
"num_tokens": 16736524.0,
|
|
"step": 9640
|
|
},
|
|
{
|
|
"entropy": 5.749722051620483,
|
|
"epoch": 0.7504376580431823,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.0004949174307834541,
|
|
"loss": 5.6888,
|
|
"mean_token_accuracy": 0.14733791872859,
|
|
"num_tokens": 16745798.0,
|
|
"step": 9645
|
|
},
|
|
{
|
|
"entropy": 5.637568950653076,
|
|
"epoch": 0.7508266874148998,
|
|
"grad_norm": 3.65625,
|
|
"learning_rate": 0.0004949115714715543,
|
|
"loss": 5.4464,
|
|
"mean_token_accuracy": 0.16167363822460173,
|
|
"num_tokens": 16754263.0,
|
|
"step": 9650
|
|
},
|
|
{
|
|
"entropy": 5.548205995559693,
|
|
"epoch": 0.7512157167866174,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.0004949057088228465,
|
|
"loss": 5.3209,
|
|
"mean_token_accuracy": 0.1741849347949028,
|
|
"num_tokens": 16762610.0,
|
|
"step": 9655
|
|
},
|
|
{
|
|
"entropy": 5.601999711990357,
|
|
"epoch": 0.751604746158335,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004948998428374194,
|
|
"loss": 5.5526,
|
|
"mean_token_accuracy": 0.15824036300182343,
|
|
"num_tokens": 16771436.0,
|
|
"step": 9660
|
|
},
|
|
{
|
|
"entropy": 5.720792627334594,
|
|
"epoch": 0.7519937755300525,
|
|
"grad_norm": 1.890625,
|
|
"learning_rate": 0.0004948939735153622,
|
|
"loss": 5.5861,
|
|
"mean_token_accuracy": 0.15715258419513703,
|
|
"num_tokens": 16779647.0,
|
|
"step": 9665
|
|
},
|
|
{
|
|
"entropy": 5.694600772857666,
|
|
"epoch": 0.7523828049017701,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.0004948881008567641,
|
|
"loss": 5.5309,
|
|
"mean_token_accuracy": 0.1593555301427841,
|
|
"num_tokens": 16788116.0,
|
|
"step": 9670
|
|
},
|
|
{
|
|
"entropy": 5.596370029449463,
|
|
"epoch": 0.7527718342734876,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.0004948822248617139,
|
|
"loss": 5.4586,
|
|
"mean_token_accuracy": 0.1673708215355873,
|
|
"num_tokens": 16796518.0,
|
|
"step": 9675
|
|
},
|
|
{
|
|
"entropy": 5.634789562225341,
|
|
"epoch": 0.7531608636452052,
|
|
"grad_norm": 2.53125,
|
|
"learning_rate": 0.000494876345530301,
|
|
"loss": 5.4535,
|
|
"mean_token_accuracy": 0.16142473965883256,
|
|
"num_tokens": 16805511.0,
|
|
"step": 9680
|
|
},
|
|
{
|
|
"entropy": 5.620686054229736,
|
|
"epoch": 0.7535498930169228,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0004948704628626145,
|
|
"loss": 5.4385,
|
|
"mean_token_accuracy": 0.16403505504131316,
|
|
"num_tokens": 16813173.0,
|
|
"step": 9685
|
|
},
|
|
{
|
|
"entropy": 5.619124221801758,
|
|
"epoch": 0.7539389223886404,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004948645768587437,
|
|
"loss": 5.5632,
|
|
"mean_token_accuracy": 0.15338002592325212,
|
|
"num_tokens": 16822193.0,
|
|
"step": 9690
|
|
},
|
|
{
|
|
"entropy": 5.541334009170532,
|
|
"epoch": 0.7543279517603579,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.0004948586875187778,
|
|
"loss": 5.2753,
|
|
"mean_token_accuracy": 0.17436991780996322,
|
|
"num_tokens": 16830421.0,
|
|
"step": 9695
|
|
},
|
|
{
|
|
"entropy": 5.594313144683838,
|
|
"epoch": 0.7547169811320755,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004948527948428064,
|
|
"loss": 5.4127,
|
|
"mean_token_accuracy": 0.16543810814619064,
|
|
"num_tokens": 16838988.0,
|
|
"step": 9700
|
|
},
|
|
{
|
|
"entropy": 5.5910563468933105,
|
|
"epoch": 0.755106010503793,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004948468988309187,
|
|
"loss": 5.5025,
|
|
"mean_token_accuracy": 0.16316866129636765,
|
|
"num_tokens": 16847980.0,
|
|
"step": 9705
|
|
},
|
|
{
|
|
"entropy": 5.5515848159790036,
|
|
"epoch": 0.7554950398755106,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004948409994832043,
|
|
"loss": 5.4208,
|
|
"mean_token_accuracy": 0.16732092052698136,
|
|
"num_tokens": 16857263.0,
|
|
"step": 9710
|
|
},
|
|
{
|
|
"entropy": 5.606499147415161,
|
|
"epoch": 0.7558840692472282,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004948350967997526,
|
|
"loss": 5.412,
|
|
"mean_token_accuracy": 0.16535467952489852,
|
|
"num_tokens": 16865314.0,
|
|
"step": 9715
|
|
},
|
|
{
|
|
"entropy": 5.628205585479736,
|
|
"epoch": 0.7562730986189458,
|
|
"grad_norm": 2.3125,
|
|
"learning_rate": 0.0004948291907806532,
|
|
"loss": 5.5087,
|
|
"mean_token_accuracy": 0.16264305263757706,
|
|
"num_tokens": 16875359.0,
|
|
"step": 9720
|
|
},
|
|
{
|
|
"entropy": 5.638123369216919,
|
|
"epoch": 0.7566621279906633,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004948232814259957,
|
|
"loss": 5.6149,
|
|
"mean_token_accuracy": 0.15074117928743364,
|
|
"num_tokens": 16885279.0,
|
|
"step": 9725
|
|
},
|
|
{
|
|
"entropy": 5.727572250366211,
|
|
"epoch": 0.7570511573623808,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.0004948173687358699,
|
|
"loss": 5.5641,
|
|
"mean_token_accuracy": 0.15789591521024704,
|
|
"num_tokens": 16894463.0,
|
|
"step": 9730
|
|
},
|
|
{
|
|
"entropy": 5.666401481628418,
|
|
"epoch": 0.7574401867340984,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004948114527103652,
|
|
"loss": 5.4906,
|
|
"mean_token_accuracy": 0.15589875131845474,
|
|
"num_tokens": 16903378.0,
|
|
"step": 9735
|
|
},
|
|
{
|
|
"entropy": 5.561936664581299,
|
|
"epoch": 0.757829216105816,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004948055333495717,
|
|
"loss": 5.5327,
|
|
"mean_token_accuracy": 0.1594816192984581,
|
|
"num_tokens": 16912039.0,
|
|
"step": 9740
|
|
},
|
|
{
|
|
"entropy": 5.585045242309571,
|
|
"epoch": 0.7582182454775336,
|
|
"grad_norm": 1.9609375,
|
|
"learning_rate": 0.0004947996106535791,
|
|
"loss": 5.4665,
|
|
"mean_token_accuracy": 0.15762123391032218,
|
|
"num_tokens": 16920516.0,
|
|
"step": 9745
|
|
},
|
|
{
|
|
"entropy": 5.6873210906982425,
|
|
"epoch": 0.7586072748492512,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004947936846224773,
|
|
"loss": 5.4869,
|
|
"mean_token_accuracy": 0.16267888247966766,
|
|
"num_tokens": 16929131.0,
|
|
"step": 9750
|
|
},
|
|
{
|
|
"entropy": 5.560367298126221,
|
|
"epoch": 0.7589963042209686,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004947877552563562,
|
|
"loss": 5.4938,
|
|
"mean_token_accuracy": 0.16611549407243728,
|
|
"num_tokens": 16937352.0,
|
|
"step": 9755
|
|
},
|
|
{
|
|
"entropy": 5.570096778869629,
|
|
"epoch": 0.7593853335926862,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.0004947818225553056,
|
|
"loss": 5.6031,
|
|
"mean_token_accuracy": 0.15492894351482392,
|
|
"num_tokens": 16946439.0,
|
|
"step": 9760
|
|
},
|
|
{
|
|
"entropy": 5.649069738388062,
|
|
"epoch": 0.7597743629644038,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.0004947758865194156,
|
|
"loss": 5.4817,
|
|
"mean_token_accuracy": 0.16115445047616958,
|
|
"num_tokens": 16955402.0,
|
|
"step": 9765
|
|
},
|
|
{
|
|
"entropy": 5.528527927398682,
|
|
"epoch": 0.7601633923361214,
|
|
"grad_norm": 1.8984375,
|
|
"learning_rate": 0.0004947699471487766,
|
|
"loss": 5.4096,
|
|
"mean_token_accuracy": 0.16653518974781037,
|
|
"num_tokens": 16964299.0,
|
|
"step": 9770
|
|
},
|
|
{
|
|
"entropy": 5.547059202194214,
|
|
"epoch": 0.760552421707839,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.0004947640044434782,
|
|
"loss": 5.4474,
|
|
"mean_token_accuracy": 0.16271981298923494,
|
|
"num_tokens": 16973483.0,
|
|
"step": 9775
|
|
},
|
|
{
|
|
"entropy": 5.6179847240448,
|
|
"epoch": 0.7609414510795565,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.0004947580584036109,
|
|
"loss": 5.4923,
|
|
"mean_token_accuracy": 0.16550723612308502,
|
|
"num_tokens": 16982234.0,
|
|
"step": 9780
|
|
},
|
|
{
|
|
"entropy": 5.589510583877564,
|
|
"epoch": 0.761330480451274,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.0004947521090292649,
|
|
"loss": 5.4568,
|
|
"mean_token_accuracy": 0.16144444346427916,
|
|
"num_tokens": 16990669.0,
|
|
"step": 9785
|
|
},
|
|
{
|
|
"entropy": 5.696868467330932,
|
|
"epoch": 0.7617195098229916,
|
|
"grad_norm": 1.9609375,
|
|
"learning_rate": 0.0004947461563205304,
|
|
"loss": 5.5359,
|
|
"mean_token_accuracy": 0.16111889481544495,
|
|
"num_tokens": 16999998.0,
|
|
"step": 9790
|
|
},
|
|
{
|
|
"entropy": 5.675904226303101,
|
|
"epoch": 0.7621085391947092,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004947402002774977,
|
|
"loss": 5.5174,
|
|
"mean_token_accuracy": 0.16485368460416794,
|
|
"num_tokens": 17008518.0,
|
|
"step": 9795
|
|
},
|
|
{
|
|
"entropy": 5.574523067474365,
|
|
"epoch": 0.7624975685664268,
|
|
"grad_norm": 1.9609375,
|
|
"learning_rate": 0.0004947342409002572,
|
|
"loss": 5.4554,
|
|
"mean_token_accuracy": 0.1643468677997589,
|
|
"num_tokens": 17017182.0,
|
|
"step": 9800
|
|
},
|
|
{
|
|
"entropy": 5.602089977264404,
|
|
"epoch": 0.7628865979381443,
|
|
"grad_norm": 1.9453125,
|
|
"learning_rate": 0.0004947282781888994,
|
|
"loss": 5.4913,
|
|
"mean_token_accuracy": 0.1593044713139534,
|
|
"num_tokens": 17026186.0,
|
|
"step": 9805
|
|
},
|
|
{
|
|
"entropy": 5.523351097106934,
|
|
"epoch": 0.7632756273098619,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004947223121435147,
|
|
"loss": 5.3592,
|
|
"mean_token_accuracy": 0.17013092041015626,
|
|
"num_tokens": 17034295.0,
|
|
"step": 9810
|
|
},
|
|
{
|
|
"entropy": 5.527068138122559,
|
|
"epoch": 0.7636646566815795,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004947163427641936,
|
|
"loss": 5.4334,
|
|
"mean_token_accuracy": 0.1630199909210205,
|
|
"num_tokens": 17043195.0,
|
|
"step": 9815
|
|
},
|
|
{
|
|
"entropy": 5.496135520935058,
|
|
"epoch": 0.764053686053297,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.0004947103700510268,
|
|
"loss": 5.3693,
|
|
"mean_token_accuracy": 0.1657385140657425,
|
|
"num_tokens": 17051903.0,
|
|
"step": 9820
|
|
},
|
|
{
|
|
"entropy": 5.510083484649658,
|
|
"epoch": 0.7644427154250146,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.0004947043940041047,
|
|
"loss": 5.448,
|
|
"mean_token_accuracy": 0.16842743009328842,
|
|
"num_tokens": 17060495.0,
|
|
"step": 9825
|
|
},
|
|
{
|
|
"entropy": 5.642737817764282,
|
|
"epoch": 0.7648317447967321,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.0004946984146235183,
|
|
"loss": 5.5012,
|
|
"mean_token_accuracy": 0.16197007149457932,
|
|
"num_tokens": 17069254.0,
|
|
"step": 9830
|
|
},
|
|
{
|
|
"entropy": 5.702970409393311,
|
|
"epoch": 0.7652207741684497,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004946924319093579,
|
|
"loss": 5.4765,
|
|
"mean_token_accuracy": 0.16286686658859253,
|
|
"num_tokens": 17077323.0,
|
|
"step": 9835
|
|
},
|
|
{
|
|
"entropy": 5.558821821212769,
|
|
"epoch": 0.7656098035401673,
|
|
"grad_norm": 1.921875,
|
|
"learning_rate": 0.0004946864458617148,
|
|
"loss": 5.3502,
|
|
"mean_token_accuracy": 0.17199598699808122,
|
|
"num_tokens": 17085377.0,
|
|
"step": 9840
|
|
},
|
|
{
|
|
"entropy": 5.517863988876343,
|
|
"epoch": 0.7659988329118849,
|
|
"grad_norm": 1.9765625,
|
|
"learning_rate": 0.0004946804564806793,
|
|
"loss": 5.4326,
|
|
"mean_token_accuracy": 0.16524434983730316,
|
|
"num_tokens": 17094288.0,
|
|
"step": 9845
|
|
},
|
|
{
|
|
"entropy": 5.5912291526794435,
|
|
"epoch": 0.7663878622836025,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004946744637663427,
|
|
"loss": 5.3417,
|
|
"mean_token_accuracy": 0.17538647800683976,
|
|
"num_tokens": 17101572.0,
|
|
"step": 9850
|
|
},
|
|
{
|
|
"entropy": 5.61966609954834,
|
|
"epoch": 0.7667768916553199,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.0004946684677187956,
|
|
"loss": 5.4961,
|
|
"mean_token_accuracy": 0.16341074407100678,
|
|
"num_tokens": 17110151.0,
|
|
"step": 9855
|
|
},
|
|
{
|
|
"entropy": 5.643578243255615,
|
|
"epoch": 0.7671659210270375,
|
|
"grad_norm": 1.96875,
|
|
"learning_rate": 0.0004946624683381292,
|
|
"loss": 5.4791,
|
|
"mean_token_accuracy": 0.16218418926000594,
|
|
"num_tokens": 17118172.0,
|
|
"step": 9860
|
|
},
|
|
{
|
|
"entropy": 5.557650184631347,
|
|
"epoch": 0.7675549503987551,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.0004946564656244345,
|
|
"loss": 5.3659,
|
|
"mean_token_accuracy": 0.17097386866807937,
|
|
"num_tokens": 17126855.0,
|
|
"step": 9865
|
|
},
|
|
{
|
|
"entropy": 5.593514156341553,
|
|
"epoch": 0.7679439797704727,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.0004946504595778026,
|
|
"loss": 5.5509,
|
|
"mean_token_accuracy": 0.16081059873104095,
|
|
"num_tokens": 17135737.0,
|
|
"step": 9870
|
|
},
|
|
{
|
|
"entropy": 5.709822750091552,
|
|
"epoch": 0.7683330091421903,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004946444501983246,
|
|
"loss": 5.493,
|
|
"mean_token_accuracy": 0.1597936987876892,
|
|
"num_tokens": 17144521.0,
|
|
"step": 9875
|
|
},
|
|
{
|
|
"entropy": 5.75422945022583,
|
|
"epoch": 0.7687220385139077,
|
|
"grad_norm": 2.84375,
|
|
"learning_rate": 0.0004946384374860916,
|
|
"loss": 5.5858,
|
|
"mean_token_accuracy": 0.160514298081398,
|
|
"num_tokens": 17153534.0,
|
|
"step": 9880
|
|
},
|
|
{
|
|
"entropy": 5.539037895202637,
|
|
"epoch": 0.7691110678856253,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.0004946324214411949,
|
|
"loss": 5.4381,
|
|
"mean_token_accuracy": 0.16201438307762145,
|
|
"num_tokens": 17162600.0,
|
|
"step": 9885
|
|
},
|
|
{
|
|
"entropy": 5.566135406494141,
|
|
"epoch": 0.7695000972573429,
|
|
"grad_norm": 1.9296875,
|
|
"learning_rate": 0.0004946264020637259,
|
|
"loss": 5.5001,
|
|
"mean_token_accuracy": 0.15808079838752748,
|
|
"num_tokens": 17171373.0,
|
|
"step": 9890
|
|
},
|
|
{
|
|
"entropy": 5.698829269409179,
|
|
"epoch": 0.7698891266290605,
|
|
"grad_norm": 1.984375,
|
|
"learning_rate": 0.0004946203793537757,
|
|
"loss": 5.5289,
|
|
"mean_token_accuracy": 0.16029061377048492,
|
|
"num_tokens": 17180090.0,
|
|
"step": 9895
|
|
},
|
|
{
|
|
"entropy": 5.701949167251587,
|
|
"epoch": 0.7702781560007781,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.0004946143533114358,
|
|
"loss": 5.4505,
|
|
"mean_token_accuracy": 0.16616697162389754,
|
|
"num_tokens": 17189592.0,
|
|
"step": 9900
|
|
},
|
|
{
|
|
"entropy": 5.608913946151733,
|
|
"epoch": 0.7706671853724957,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 0.0004946083239367976,
|
|
"loss": 5.3903,
|
|
"mean_token_accuracy": 0.16684449315071107,
|
|
"num_tokens": 17198287.0,
|
|
"step": 9905
|
|
},
|
|
{
|
|
"entropy": 5.6060953617095945,
|
|
"epoch": 0.7710562147442132,
|
|
"grad_norm": 3.03125,
|
|
"learning_rate": 0.0004946022912299527,
|
|
"loss": 5.4779,
|
|
"mean_token_accuracy": 0.16104824990034103,
|
|
"num_tokens": 17206349.0,
|
|
"step": 9910
|
|
},
|
|
{
|
|
"entropy": 5.582810306549073,
|
|
"epoch": 0.7714452441159307,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.0004945962551909926,
|
|
"loss": 5.6104,
|
|
"mean_token_accuracy": 0.15242502987384796,
|
|
"num_tokens": 17215408.0,
|
|
"step": 9915
|
|
},
|
|
{
|
|
"entropy": 5.692499303817749,
|
|
"epoch": 0.7718342734876483,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.0004945902158200089,
|
|
"loss": 5.531,
|
|
"mean_token_accuracy": 0.162887778878212,
|
|
"num_tokens": 17224342.0,
|
|
"step": 9920
|
|
},
|
|
{
|
|
"entropy": 5.675246477127075,
|
|
"epoch": 0.7722233028593659,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.0004945841731170931,
|
|
"loss": 5.4028,
|
|
"mean_token_accuracy": 0.1654059633612633,
|
|
"num_tokens": 17232532.0,
|
|
"step": 9925
|
|
},
|
|
{
|
|
"entropy": 5.5252869606018065,
|
|
"epoch": 0.7726123322310835,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.0004945781270823369,
|
|
"loss": 5.4245,
|
|
"mean_token_accuracy": 0.1700804501771927,
|
|
"num_tokens": 17240786.0,
|
|
"step": 9930
|
|
},
|
|
{
|
|
"entropy": 5.554746437072754,
|
|
"epoch": 0.773001361602801,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.0004945720777158323,
|
|
"loss": 5.3959,
|
|
"mean_token_accuracy": 0.17170931845903398,
|
|
"num_tokens": 17248515.0,
|
|
"step": 9935
|
|
},
|
|
{
|
|
"entropy": 5.643727159500122,
|
|
"epoch": 0.7733903909745186,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.0004945660250176708,
|
|
"loss": 5.4644,
|
|
"mean_token_accuracy": 0.1631182461977005,
|
|
"num_tokens": 17257098.0,
|
|
"step": 9940
|
|
},
|
|
{
|
|
"entropy": 5.596380043029785,
|
|
"epoch": 0.7737794203462361,
|
|
"grad_norm": 1.8515625,
|
|
"learning_rate": 0.0004945599689879443,
|
|
"loss": 5.4567,
|
|
"mean_token_accuracy": 0.16021543443202974,
|
|
"num_tokens": 17266851.0,
|
|
"step": 9945
|
|
},
|
|
{
|
|
"entropy": 5.5926926612854,
|
|
"epoch": 0.7741684497179537,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.0004945539096267448,
|
|
"loss": 5.4125,
|
|
"mean_token_accuracy": 0.15545879751443864,
|
|
"num_tokens": 17275568.0,
|
|
"step": 9950
|
|
},
|
|
{
|
|
"entropy": 5.559701347351075,
|
|
"epoch": 0.7745574790896713,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004945478469341642,
|
|
"loss": 5.3661,
|
|
"mean_token_accuracy": 0.16687587201595305,
|
|
"num_tokens": 17284528.0,
|
|
"step": 9955
|
|
},
|
|
{
|
|
"entropy": 5.666002082824707,
|
|
"epoch": 0.7749465084613888,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.0004945417809102944,
|
|
"loss": 5.5247,
|
|
"mean_token_accuracy": 0.1571332708001137,
|
|
"num_tokens": 17293973.0,
|
|
"step": 9960
|
|
},
|
|
{
|
|
"entropy": 5.589224767684937,
|
|
"epoch": 0.7753355378331064,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004945357115552275,
|
|
"loss": 5.3938,
|
|
"mean_token_accuracy": 0.16693559885025025,
|
|
"num_tokens": 17302321.0,
|
|
"step": 9965
|
|
},
|
|
{
|
|
"entropy": 5.662674474716186,
|
|
"epoch": 0.775724567204824,
|
|
"grad_norm": 2.421875,
|
|
"learning_rate": 0.0004945296388690557,
|
|
"loss": 5.5341,
|
|
"mean_token_accuracy": 0.15898776054382324,
|
|
"num_tokens": 17311226.0,
|
|
"step": 9970
|
|
},
|
|
{
|
|
"entropy": 5.670564126968384,
|
|
"epoch": 0.7761135965765416,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.000494523562851871,
|
|
"loss": 5.5136,
|
|
"mean_token_accuracy": 0.16233190447092055,
|
|
"num_tokens": 17319818.0,
|
|
"step": 9975
|
|
},
|
|
{
|
|
"entropy": 5.685512733459473,
|
|
"epoch": 0.7765026259482591,
|
|
"grad_norm": 1.890625,
|
|
"learning_rate": 0.0004945174835037655,
|
|
"loss": 5.5526,
|
|
"mean_token_accuracy": 0.15104843601584433,
|
|
"num_tokens": 17329195.0,
|
|
"step": 9980
|
|
},
|
|
{
|
|
"entropy": 5.68356032371521,
|
|
"epoch": 0.7768916553199766,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.0004945114008248319,
|
|
"loss": 5.6065,
|
|
"mean_token_accuracy": 0.16331554502248763,
|
|
"num_tokens": 17337689.0,
|
|
"step": 9985
|
|
},
|
|
{
|
|
"entropy": 5.6124224185943605,
|
|
"epoch": 0.7772806846916942,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.0004945053148151619,
|
|
"loss": 5.3523,
|
|
"mean_token_accuracy": 0.16628433167934417,
|
|
"num_tokens": 17345467.0,
|
|
"step": 9990
|
|
},
|
|
{
|
|
"entropy": 5.592377948760986,
|
|
"epoch": 0.7776697140634118,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 0.0004944992254748482,
|
|
"loss": 5.5264,
|
|
"mean_token_accuracy": 0.1615174800157547,
|
|
"num_tokens": 17353651.0,
|
|
"step": 9995
|
|
},
|
|
{
|
|
"entropy": 5.66843729019165,
|
|
"epoch": 0.7780587434351294,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.0004944931328039832,
|
|
"loss": 5.5606,
|
|
"mean_token_accuracy": 0.1593351796269417,
|
|
"num_tokens": 17362777.0,
|
|
"step": 10000
|
|
},
|
|
{
|
|
"entropy": 5.720261096954346,
|
|
"epoch": 0.778447772806847,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004944870368026592,
|
|
"loss": 5.5077,
|
|
"mean_token_accuracy": 0.16661525070667266,
|
|
"num_tokens": 17371562.0,
|
|
"step": 10005
|
|
},
|
|
{
|
|
"entropy": 5.66126389503479,
|
|
"epoch": 0.7788368021785644,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004944809374709689,
|
|
"loss": 5.5056,
|
|
"mean_token_accuracy": 0.1567501202225685,
|
|
"num_tokens": 17381185.0,
|
|
"step": 10010
|
|
},
|
|
{
|
|
"entropy": 5.650999212265015,
|
|
"epoch": 0.779225831550282,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004944748348090045,
|
|
"loss": 5.4784,
|
|
"mean_token_accuracy": 0.16496318429708481,
|
|
"num_tokens": 17390658.0,
|
|
"step": 10015
|
|
},
|
|
{
|
|
"entropy": 5.561220407485962,
|
|
"epoch": 0.7796148609219996,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.0004944687288168589,
|
|
"loss": 5.4052,
|
|
"mean_token_accuracy": 0.16336870938539505,
|
|
"num_tokens": 17399968.0,
|
|
"step": 10020
|
|
},
|
|
{
|
|
"entropy": 5.627987957000732,
|
|
"epoch": 0.7800038902937172,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004944626194946246,
|
|
"loss": 5.5257,
|
|
"mean_token_accuracy": 0.15906717181205748,
|
|
"num_tokens": 17408727.0,
|
|
"step": 10025
|
|
},
|
|
{
|
|
"entropy": 5.714763355255127,
|
|
"epoch": 0.7803929196654348,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004944565068423945,
|
|
"loss": 5.5476,
|
|
"mean_token_accuracy": 0.1611577019095421,
|
|
"num_tokens": 17417517.0,
|
|
"step": 10030
|
|
},
|
|
{
|
|
"entropy": 5.6924371242523195,
|
|
"epoch": 0.7807819490371523,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004944503908602612,
|
|
"loss": 5.5196,
|
|
"mean_token_accuracy": 0.16490633487701417,
|
|
"num_tokens": 17427035.0,
|
|
"step": 10035
|
|
},
|
|
{
|
|
"entropy": 5.672628164291382,
|
|
"epoch": 0.7811709784088698,
|
|
"grad_norm": 1.9140625,
|
|
"learning_rate": 0.0004944442715483174,
|
|
"loss": 5.4281,
|
|
"mean_token_accuracy": 0.1619464337825775,
|
|
"num_tokens": 17435585.0,
|
|
"step": 10040
|
|
},
|
|
{
|
|
"entropy": 5.6093337059021,
|
|
"epoch": 0.7815600077805874,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.0004944381489066561,
|
|
"loss": 5.4563,
|
|
"mean_token_accuracy": 0.16509817242622377,
|
|
"num_tokens": 17444317.0,
|
|
"step": 10045
|
|
},
|
|
{
|
|
"entropy": 5.709244155883789,
|
|
"epoch": 0.781949037152305,
|
|
"grad_norm": 2.578125,
|
|
"learning_rate": 0.0004944320229353702,
|
|
"loss": 5.6611,
|
|
"mean_token_accuracy": 0.15847226828336716,
|
|
"num_tokens": 17453585.0,
|
|
"step": 10050
|
|
},
|
|
{
|
|
"entropy": 5.638391828536987,
|
|
"epoch": 0.7823380665240226,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004944258936345526,
|
|
"loss": 5.4239,
|
|
"mean_token_accuracy": 0.1677062466740608,
|
|
"num_tokens": 17462233.0,
|
|
"step": 10055
|
|
},
|
|
{
|
|
"entropy": 5.592179250717163,
|
|
"epoch": 0.7827270958957401,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004944197610042963,
|
|
"loss": 5.374,
|
|
"mean_token_accuracy": 0.1731768473982811,
|
|
"num_tokens": 17470566.0,
|
|
"step": 10060
|
|
},
|
|
{
|
|
"entropy": 5.555074787139892,
|
|
"epoch": 0.7831161252674577,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.0004944136250446944,
|
|
"loss": 5.4461,
|
|
"mean_token_accuracy": 0.16081113815307618,
|
|
"num_tokens": 17479267.0,
|
|
"step": 10065
|
|
},
|
|
{
|
|
"entropy": 5.532630395889282,
|
|
"epoch": 0.7835051546391752,
|
|
"grad_norm": 1.890625,
|
|
"learning_rate": 0.0004944074857558399,
|
|
"loss": 5.3603,
|
|
"mean_token_accuracy": 0.17020478397607802,
|
|
"num_tokens": 17488060.0,
|
|
"step": 10070
|
|
},
|
|
{
|
|
"entropy": 5.679540061950684,
|
|
"epoch": 0.7838941840108928,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.0004944013431378261,
|
|
"loss": 5.6014,
|
|
"mean_token_accuracy": 0.16150971502065659,
|
|
"num_tokens": 17497240.0,
|
|
"step": 10075
|
|
},
|
|
{
|
|
"entropy": 5.680597019195557,
|
|
"epoch": 0.7842832133826104,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004943951971907461,
|
|
"loss": 5.5579,
|
|
"mean_token_accuracy": 0.16160822808742523,
|
|
"num_tokens": 17506017.0,
|
|
"step": 10080
|
|
},
|
|
{
|
|
"entropy": 5.655553865432739,
|
|
"epoch": 0.7846722427543279,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004943890479146933,
|
|
"loss": 5.5105,
|
|
"mean_token_accuracy": 0.16028194576501847,
|
|
"num_tokens": 17514764.0,
|
|
"step": 10085
|
|
},
|
|
{
|
|
"entropy": 5.573654890060425,
|
|
"epoch": 0.7850612721260455,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004943828953097607,
|
|
"loss": 5.4865,
|
|
"mean_token_accuracy": 0.16224425733089448,
|
|
"num_tokens": 17524183.0,
|
|
"step": 10090
|
|
},
|
|
{
|
|
"entropy": 5.585941410064697,
|
|
"epoch": 0.7854503014977631,
|
|
"grad_norm": 2.5625,
|
|
"learning_rate": 0.000494376739376042,
|
|
"loss": 5.4299,
|
|
"mean_token_accuracy": 0.16732798516750336,
|
|
"num_tokens": 17533426.0,
|
|
"step": 10095
|
|
},
|
|
{
|
|
"entropy": 5.631689739227295,
|
|
"epoch": 0.7858393308694807,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004943705801136304,
|
|
"loss": 5.3726,
|
|
"mean_token_accuracy": 0.1689580962061882,
|
|
"num_tokens": 17541966.0,
|
|
"step": 10100
|
|
},
|
|
{
|
|
"entropy": 5.663729190826416,
|
|
"epoch": 0.7862283602411982,
|
|
"grad_norm": 2.484375,
|
|
"learning_rate": 0.0004943644175226193,
|
|
"loss": 5.4734,
|
|
"mean_token_accuracy": 0.16434135437011718,
|
|
"num_tokens": 17551157.0,
|
|
"step": 10105
|
|
},
|
|
{
|
|
"entropy": 5.602836322784424,
|
|
"epoch": 0.7866173896129158,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004943582516031025,
|
|
"loss": 5.3757,
|
|
"mean_token_accuracy": 0.17025305032730104,
|
|
"num_tokens": 17559999.0,
|
|
"step": 10110
|
|
},
|
|
{
|
|
"entropy": 5.598563098907471,
|
|
"epoch": 0.7870064189846333,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004943520823551732,
|
|
"loss": 5.4291,
|
|
"mean_token_accuracy": 0.1633608639240265,
|
|
"num_tokens": 17568873.0,
|
|
"step": 10115
|
|
},
|
|
{
|
|
"entropy": 5.6024843692779545,
|
|
"epoch": 0.7873954483563509,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004943459097789252,
|
|
"loss": 5.5135,
|
|
"mean_token_accuracy": 0.16989543288946152,
|
|
"num_tokens": 17577807.0,
|
|
"step": 10120
|
|
},
|
|
{
|
|
"entropy": 5.668852376937866,
|
|
"epoch": 0.7877844777280685,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004943397338744523,
|
|
"loss": 5.5331,
|
|
"mean_token_accuracy": 0.15648714005947112,
|
|
"num_tokens": 17586646.0,
|
|
"step": 10125
|
|
},
|
|
{
|
|
"entropy": 5.7241333484649655,
|
|
"epoch": 0.7881735070997861,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.000494333554641848,
|
|
"loss": 5.5828,
|
|
"mean_token_accuracy": 0.15697579979896545,
|
|
"num_tokens": 17595458.0,
|
|
"step": 10130
|
|
},
|
|
{
|
|
"entropy": 5.635165357589722,
|
|
"epoch": 0.7885625364715037,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.000494327372081206,
|
|
"loss": 5.5027,
|
|
"mean_token_accuracy": 0.16089629828929902,
|
|
"num_tokens": 17603997.0,
|
|
"step": 10135
|
|
},
|
|
{
|
|
"entropy": 5.653491687774658,
|
|
"epoch": 0.7889515658432211,
|
|
"grad_norm": 1.9609375,
|
|
"learning_rate": 0.0004943211861926204,
|
|
"loss": 5.512,
|
|
"mean_token_accuracy": 0.15793127566576004,
|
|
"num_tokens": 17612347.0,
|
|
"step": 10140
|
|
},
|
|
{
|
|
"entropy": 5.556810331344605,
|
|
"epoch": 0.7893405952149387,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.0004943149969761848,
|
|
"loss": 5.3819,
|
|
"mean_token_accuracy": 0.17163314372301103,
|
|
"num_tokens": 17620618.0,
|
|
"step": 10145
|
|
},
|
|
{
|
|
"entropy": 5.5603265285491945,
|
|
"epoch": 0.7897296245866563,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.0004943088044319932,
|
|
"loss": 5.393,
|
|
"mean_token_accuracy": 0.1651839479804039,
|
|
"num_tokens": 17629164.0,
|
|
"step": 10150
|
|
},
|
|
{
|
|
"entropy": 5.695376968383789,
|
|
"epoch": 0.7901186539583739,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.0004943026085601395,
|
|
"loss": 5.5766,
|
|
"mean_token_accuracy": 0.16014289036393164,
|
|
"num_tokens": 17638454.0,
|
|
"step": 10155
|
|
},
|
|
{
|
|
"entropy": 5.647540712356568,
|
|
"epoch": 0.7905076833300915,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0004942964093607178,
|
|
"loss": 5.4897,
|
|
"mean_token_accuracy": 0.1556386798620224,
|
|
"num_tokens": 17647099.0,
|
|
"step": 10160
|
|
},
|
|
{
|
|
"entropy": 5.679839277267456,
|
|
"epoch": 0.790896712701809,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004942902068338222,
|
|
"loss": 5.4529,
|
|
"mean_token_accuracy": 0.1638456791639328,
|
|
"num_tokens": 17655214.0,
|
|
"step": 10165
|
|
},
|
|
{
|
|
"entropy": 5.593786287307739,
|
|
"epoch": 0.7912857420735265,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.0004942840009795466,
|
|
"loss": 5.4179,
|
|
"mean_token_accuracy": 0.1640210047364235,
|
|
"num_tokens": 17663342.0,
|
|
"step": 10170
|
|
},
|
|
{
|
|
"entropy": 5.701464080810547,
|
|
"epoch": 0.7916747714452441,
|
|
"grad_norm": 2.390625,
|
|
"learning_rate": 0.0004942777917979855,
|
|
"loss": 5.6259,
|
|
"mean_token_accuracy": 0.1510114476084709,
|
|
"num_tokens": 17671725.0,
|
|
"step": 10175
|
|
},
|
|
{
|
|
"entropy": 5.611249780654907,
|
|
"epoch": 0.7920638008169617,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004942715792892328,
|
|
"loss": 5.5146,
|
|
"mean_token_accuracy": 0.1566399648785591,
|
|
"num_tokens": 17680627.0,
|
|
"step": 10180
|
|
},
|
|
{
|
|
"entropy": 5.672344446182251,
|
|
"epoch": 0.7924528301886793,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.000494265363453383,
|
|
"loss": 5.4837,
|
|
"mean_token_accuracy": 0.16607389748096466,
|
|
"num_tokens": 17688392.0,
|
|
"step": 10185
|
|
},
|
|
{
|
|
"entropy": 5.548071432113647,
|
|
"epoch": 0.7928418595603968,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004942591442905302,
|
|
"loss": 5.425,
|
|
"mean_token_accuracy": 0.1644718125462532,
|
|
"num_tokens": 17697546.0,
|
|
"step": 10190
|
|
},
|
|
{
|
|
"entropy": 5.549247455596924,
|
|
"epoch": 0.7932308889321144,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.0004942529218007689,
|
|
"loss": 5.4192,
|
|
"mean_token_accuracy": 0.16359905451536177,
|
|
"num_tokens": 17705555.0,
|
|
"step": 10195
|
|
},
|
|
{
|
|
"entropy": 5.596877384185791,
|
|
"epoch": 0.7936199183038319,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004942466959841936,
|
|
"loss": 5.5657,
|
|
"mean_token_accuracy": 0.15450920462608336,
|
|
"num_tokens": 17715652.0,
|
|
"step": 10200
|
|
},
|
|
{
|
|
"entropy": 5.594890785217285,
|
|
"epoch": 0.7940089476755495,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.0004942404668408985,
|
|
"loss": 5.323,
|
|
"mean_token_accuracy": 0.16661404371261596,
|
|
"num_tokens": 17724111.0,
|
|
"step": 10205
|
|
},
|
|
{
|
|
"entropy": 5.51533203125,
|
|
"epoch": 0.7943979770472671,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004942342343709783,
|
|
"loss": 5.3237,
|
|
"mean_token_accuracy": 0.16806813329458237,
|
|
"num_tokens": 17732732.0,
|
|
"step": 10210
|
|
},
|
|
{
|
|
"entropy": 5.557484579086304,
|
|
"epoch": 0.7947870064189846,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004942279985745275,
|
|
"loss": 5.4222,
|
|
"mean_token_accuracy": 0.16745371371507645,
|
|
"num_tokens": 17741338.0,
|
|
"step": 10215
|
|
},
|
|
{
|
|
"entropy": 5.651669549942016,
|
|
"epoch": 0.7951760357907022,
|
|
"grad_norm": 1.953125,
|
|
"learning_rate": 0.0004942217594516409,
|
|
"loss": 5.6297,
|
|
"mean_token_accuracy": 0.15270405262708664,
|
|
"num_tokens": 17750651.0,
|
|
"step": 10220
|
|
},
|
|
{
|
|
"entropy": 5.672304582595825,
|
|
"epoch": 0.7955650651624198,
|
|
"grad_norm": 2.34375,
|
|
"learning_rate": 0.000494215517002413,
|
|
"loss": 5.4465,
|
|
"mean_token_accuracy": 0.1657976910471916,
|
|
"num_tokens": 17759052.0,
|
|
"step": 10225
|
|
},
|
|
{
|
|
"entropy": 5.622222137451172,
|
|
"epoch": 0.7959540945341373,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 0.0004942092712269384,
|
|
"loss": 5.4995,
|
|
"mean_token_accuracy": 0.15836849063634872,
|
|
"num_tokens": 17767246.0,
|
|
"step": 10230
|
|
},
|
|
{
|
|
"entropy": 5.6600964069366455,
|
|
"epoch": 0.7963431239058549,
|
|
"grad_norm": 1.90625,
|
|
"learning_rate": 0.0004942030221253122,
|
|
"loss": 5.5259,
|
|
"mean_token_accuracy": 0.1660325661301613,
|
|
"num_tokens": 17777022.0,
|
|
"step": 10235
|
|
},
|
|
{
|
|
"entropy": 5.610336446762085,
|
|
"epoch": 0.7967321532775724,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.0004941967696976289,
|
|
"loss": 5.4857,
|
|
"mean_token_accuracy": 0.15924048274755478,
|
|
"num_tokens": 17785586.0,
|
|
"step": 10240
|
|
},
|
|
{
|
|
"entropy": 5.569327688217163,
|
|
"epoch": 0.79712118264929,
|
|
"grad_norm": 3.15625,
|
|
"learning_rate": 0.0004941905139439835,
|
|
"loss": 5.491,
|
|
"mean_token_accuracy": 0.15838305354118348,
|
|
"num_tokens": 17794320.0,
|
|
"step": 10245
|
|
},
|
|
{
|
|
"entropy": 5.64916410446167,
|
|
"epoch": 0.7975102120210076,
|
|
"grad_norm": 1.90625,
|
|
"learning_rate": 0.0004941842548644712,
|
|
"loss": 5.494,
|
|
"mean_token_accuracy": 0.16658835113048553,
|
|
"num_tokens": 17803384.0,
|
|
"step": 10250
|
|
},
|
|
{
|
|
"entropy": 5.621331739425659,
|
|
"epoch": 0.7978992413927252,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004941779924591864,
|
|
"loss": 5.4568,
|
|
"mean_token_accuracy": 0.16018279045820236,
|
|
"num_tokens": 17811955.0,
|
|
"step": 10255
|
|
},
|
|
{
|
|
"entropy": 5.600093746185303,
|
|
"epoch": 0.7982882707644428,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004941717267282244,
|
|
"loss": 5.5035,
|
|
"mean_token_accuracy": 0.15930808931589127,
|
|
"num_tokens": 17820582.0,
|
|
"step": 10260
|
|
},
|
|
{
|
|
"entropy": 5.6477625370025635,
|
|
"epoch": 0.7986773001361602,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.0004941654576716806,
|
|
"loss": 5.422,
|
|
"mean_token_accuracy": 0.17183213979005812,
|
|
"num_tokens": 17828465.0,
|
|
"step": 10265
|
|
},
|
|
{
|
|
"entropy": 5.583280467987061,
|
|
"epoch": 0.7990663295078778,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.0004941591852896495,
|
|
"loss": 5.4359,
|
|
"mean_token_accuracy": 0.16712730526924133,
|
|
"num_tokens": 17836931.0,
|
|
"step": 10270
|
|
},
|
|
{
|
|
"entropy": 5.593148994445801,
|
|
"epoch": 0.7994553588795954,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.0004941529095822268,
|
|
"loss": 5.5076,
|
|
"mean_token_accuracy": 0.16192793101072311,
|
|
"num_tokens": 17845192.0,
|
|
"step": 10275
|
|
},
|
|
{
|
|
"entropy": 5.613137865066529,
|
|
"epoch": 0.799844388251313,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 0.0004941466305495074,
|
|
"loss": 5.4882,
|
|
"mean_token_accuracy": 0.1638793796300888,
|
|
"num_tokens": 17854121.0,
|
|
"step": 10280
|
|
},
|
|
{
|
|
"entropy": 5.679468488693237,
|
|
"epoch": 0.8002334176230306,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.0004941403481915867,
|
|
"loss": 5.4811,
|
|
"mean_token_accuracy": 0.16117021888494493,
|
|
"num_tokens": 17862931.0,
|
|
"step": 10285
|
|
},
|
|
{
|
|
"entropy": 5.711264896392822,
|
|
"epoch": 0.800622446994748,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.0004941340625085601,
|
|
"loss": 5.5046,
|
|
"mean_token_accuracy": 0.1594366416335106,
|
|
"num_tokens": 17871909.0,
|
|
"step": 10290
|
|
},
|
|
{
|
|
"entropy": 5.58612847328186,
|
|
"epoch": 0.8010114763664656,
|
|
"grad_norm": 1.875,
|
|
"learning_rate": 0.0004941277735005228,
|
|
"loss": 5.4172,
|
|
"mean_token_accuracy": 0.17171649187803267,
|
|
"num_tokens": 17880487.0,
|
|
"step": 10295
|
|
},
|
|
{
|
|
"entropy": 5.5800947666168215,
|
|
"epoch": 0.8014005057381832,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.0004941214811675702,
|
|
"loss": 5.4917,
|
|
"mean_token_accuracy": 0.16468902677297592,
|
|
"num_tokens": 17888712.0,
|
|
"step": 10300
|
|
},
|
|
{
|
|
"entropy": 5.657146358489991,
|
|
"epoch": 0.8017895351099008,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004941151855097982,
|
|
"loss": 5.5167,
|
|
"mean_token_accuracy": 0.15736292600631713,
|
|
"num_tokens": 17898163.0,
|
|
"step": 10305
|
|
},
|
|
{
|
|
"entropy": 5.544344663619995,
|
|
"epoch": 0.8021785644816184,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.0004941088865273018,
|
|
"loss": 5.3978,
|
|
"mean_token_accuracy": 0.16945990920066833,
|
|
"num_tokens": 17906849.0,
|
|
"step": 10310
|
|
},
|
|
{
|
|
"entropy": 5.604688549041748,
|
|
"epoch": 0.802567593853336,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.0004941025842201769,
|
|
"loss": 5.4233,
|
|
"mean_token_accuracy": 0.16326107680797577,
|
|
"num_tokens": 17915695.0,
|
|
"step": 10315
|
|
},
|
|
{
|
|
"entropy": 5.642625379562378,
|
|
"epoch": 0.8029566232250535,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.0004940962785885189,
|
|
"loss": 5.5412,
|
|
"mean_token_accuracy": 0.1609931468963623,
|
|
"num_tokens": 17924706.0,
|
|
"step": 10320
|
|
},
|
|
{
|
|
"entropy": 5.598984241485596,
|
|
"epoch": 0.803345652596771,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.0004940899696324237,
|
|
"loss": 5.5098,
|
|
"mean_token_accuracy": 0.16656170636415482,
|
|
"num_tokens": 17934061.0,
|
|
"step": 10325
|
|
},
|
|
{
|
|
"entropy": 5.541709327697754,
|
|
"epoch": 0.8037346819684886,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0004940836573519868,
|
|
"loss": 5.3957,
|
|
"mean_token_accuracy": 0.1614055261015892,
|
|
"num_tokens": 17942580.0,
|
|
"step": 10330
|
|
},
|
|
{
|
|
"entropy": 5.559194278717041,
|
|
"epoch": 0.8041237113402062,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004940773417473043,
|
|
"loss": 5.302,
|
|
"mean_token_accuracy": 0.17452752441167832,
|
|
"num_tokens": 17951171.0,
|
|
"step": 10335
|
|
},
|
|
{
|
|
"entropy": 5.575502920150757,
|
|
"epoch": 0.8045127407119238,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.0004940710228184717,
|
|
"loss": 5.3725,
|
|
"mean_token_accuracy": 0.1767213225364685,
|
|
"num_tokens": 17959674.0,
|
|
"step": 10340
|
|
},
|
|
{
|
|
"entropy": 5.588793230056763,
|
|
"epoch": 0.8049017700836413,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.000494064700565585,
|
|
"loss": 5.4334,
|
|
"mean_token_accuracy": 0.16568266302347184,
|
|
"num_tokens": 17969036.0,
|
|
"step": 10345
|
|
},
|
|
{
|
|
"entropy": 5.5657895565032955,
|
|
"epoch": 0.8052907994553589,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004940583749887403,
|
|
"loss": 5.4374,
|
|
"mean_token_accuracy": 0.16805848479270935,
|
|
"num_tokens": 17977406.0,
|
|
"step": 10350
|
|
},
|
|
{
|
|
"entropy": 5.572657823562622,
|
|
"epoch": 0.8056798288270764,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.0004940520460880333,
|
|
"loss": 5.4144,
|
|
"mean_token_accuracy": 0.16339076906442643,
|
|
"num_tokens": 17985981.0,
|
|
"step": 10355
|
|
},
|
|
{
|
|
"entropy": 5.7101295471191404,
|
|
"epoch": 0.806068858198794,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004940457138635601,
|
|
"loss": 5.6024,
|
|
"mean_token_accuracy": 0.15701119005680084,
|
|
"num_tokens": 17994246.0,
|
|
"step": 10360
|
|
},
|
|
{
|
|
"entropy": 5.596508741378784,
|
|
"epoch": 0.8064578875705116,
|
|
"grad_norm": 1.9453125,
|
|
"learning_rate": 0.0004940393783154169,
|
|
"loss": 5.4242,
|
|
"mean_token_accuracy": 0.16401692777872084,
|
|
"num_tokens": 18002444.0,
|
|
"step": 10365
|
|
},
|
|
{
|
|
"entropy": 5.541873407363892,
|
|
"epoch": 0.8068469169422291,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.0004940330394436999,
|
|
"loss": 5.3579,
|
|
"mean_token_accuracy": 0.17150308489799498,
|
|
"num_tokens": 18011076.0,
|
|
"step": 10370
|
|
},
|
|
{
|
|
"entropy": 5.6240965843200685,
|
|
"epoch": 0.8072359463139467,
|
|
"grad_norm": 1.84375,
|
|
"learning_rate": 0.000494026697248505,
|
|
"loss": 5.6713,
|
|
"mean_token_accuracy": 0.1503859505057335,
|
|
"num_tokens": 18020232.0,
|
|
"step": 10375
|
|
},
|
|
{
|
|
"entropy": 5.6511329174041744,
|
|
"epoch": 0.8076249756856643,
|
|
"grad_norm": 1.890625,
|
|
"learning_rate": 0.0004940203517299287,
|
|
"loss": 5.4864,
|
|
"mean_token_accuracy": 0.16003672331571578,
|
|
"num_tokens": 18029055.0,
|
|
"step": 10380
|
|
},
|
|
{
|
|
"entropy": 5.762785768508911,
|
|
"epoch": 0.8080140050573819,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.000494014002888067,
|
|
"loss": 5.632,
|
|
"mean_token_accuracy": 0.150436607003212,
|
|
"num_tokens": 18037827.0,
|
|
"step": 10385
|
|
},
|
|
{
|
|
"entropy": 5.588500881195069,
|
|
"epoch": 0.8084030344290994,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0004940076507230166,
|
|
"loss": 5.4386,
|
|
"mean_token_accuracy": 0.15955962091684342,
|
|
"num_tokens": 18047017.0,
|
|
"step": 10390
|
|
},
|
|
{
|
|
"entropy": 5.612473344802856,
|
|
"epoch": 0.8087920638008169,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.0004940012952348735,
|
|
"loss": 5.5409,
|
|
"mean_token_accuracy": 0.158518485724926,
|
|
"num_tokens": 18056256.0,
|
|
"step": 10395
|
|
},
|
|
{
|
|
"entropy": 5.599542331695557,
|
|
"epoch": 0.8091810931725345,
|
|
"grad_norm": 1.84375,
|
|
"learning_rate": 0.0004939949364237345,
|
|
"loss": 5.3102,
|
|
"mean_token_accuracy": 0.17979826033115387,
|
|
"num_tokens": 18064127.0,
|
|
"step": 10400
|
|
},
|
|
{
|
|
"entropy": 5.569639539718628,
|
|
"epoch": 0.8095701225442521,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.0004939885742896958,
|
|
"loss": 5.4529,
|
|
"mean_token_accuracy": 0.1667359307408333,
|
|
"num_tokens": 18072766.0,
|
|
"step": 10405
|
|
},
|
|
{
|
|
"entropy": 5.559090089797974,
|
|
"epoch": 0.8099591519159697,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.000493982208832854,
|
|
"loss": 5.4188,
|
|
"mean_token_accuracy": 0.15746911466121674,
|
|
"num_tokens": 18080685.0,
|
|
"step": 10410
|
|
},
|
|
{
|
|
"entropy": 5.587021017074585,
|
|
"epoch": 0.8103481812876873,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004939758400533058,
|
|
"loss": 5.5308,
|
|
"mean_token_accuracy": 0.15705058574676514,
|
|
"num_tokens": 18090026.0,
|
|
"step": 10415
|
|
},
|
|
{
|
|
"entropy": 5.58308367729187,
|
|
"epoch": 0.8107372106594047,
|
|
"grad_norm": 2.859375,
|
|
"learning_rate": 0.0004939694679511478,
|
|
"loss": 5.4052,
|
|
"mean_token_accuracy": 0.16692954003810884,
|
|
"num_tokens": 18098638.0,
|
|
"step": 10420
|
|
},
|
|
{
|
|
"entropy": 5.600553894042969,
|
|
"epoch": 0.8111262400311223,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.0004939630925264765,
|
|
"loss": 5.4222,
|
|
"mean_token_accuracy": 0.16326284259557725,
|
|
"num_tokens": 18106844.0,
|
|
"step": 10425
|
|
},
|
|
{
|
|
"entropy": 5.610729455947876,
|
|
"epoch": 0.8115152694028399,
|
|
"grad_norm": 1.8515625,
|
|
"learning_rate": 0.000493956713779389,
|
|
"loss": 5.434,
|
|
"mean_token_accuracy": 0.1650155320763588,
|
|
"num_tokens": 18114758.0,
|
|
"step": 10430
|
|
},
|
|
{
|
|
"entropy": 5.518386268615723,
|
|
"epoch": 0.8119042987745575,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004939503317099817,
|
|
"loss": 5.4104,
|
|
"mean_token_accuracy": 0.16730024963617324,
|
|
"num_tokens": 18122839.0,
|
|
"step": 10435
|
|
},
|
|
{
|
|
"entropy": 5.56161150932312,
|
|
"epoch": 0.8122933281462751,
|
|
"grad_norm": 2.515625,
|
|
"learning_rate": 0.0004939439463183517,
|
|
"loss": 5.4972,
|
|
"mean_token_accuracy": 0.16520994454622268,
|
|
"num_tokens": 18131709.0,
|
|
"step": 10440
|
|
},
|
|
{
|
|
"entropy": 5.6161283493042,
|
|
"epoch": 0.8126823575179926,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004939375576045958,
|
|
"loss": 5.4849,
|
|
"mean_token_accuracy": 0.1618633598089218,
|
|
"num_tokens": 18140334.0,
|
|
"step": 10445
|
|
},
|
|
{
|
|
"entropy": 5.571049785614013,
|
|
"epoch": 0.8130713868897101,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004939311655688109,
|
|
"loss": 5.4513,
|
|
"mean_token_accuracy": 0.162336765229702,
|
|
"num_tokens": 18148648.0,
|
|
"step": 10450
|
|
},
|
|
{
|
|
"entropy": 5.554464483261109,
|
|
"epoch": 0.8134604162614277,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004939247702110941,
|
|
"loss": 5.4759,
|
|
"mean_token_accuracy": 0.1643720656633377,
|
|
"num_tokens": 18156891.0,
|
|
"step": 10455
|
|
},
|
|
{
|
|
"entropy": 5.603726720809936,
|
|
"epoch": 0.8138494456331453,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.0004939183715315423,
|
|
"loss": 5.435,
|
|
"mean_token_accuracy": 0.1627091020345688,
|
|
"num_tokens": 18166512.0,
|
|
"step": 10460
|
|
},
|
|
{
|
|
"entropy": 5.647644519805908,
|
|
"epoch": 0.8142384750048629,
|
|
"grad_norm": 1.9453125,
|
|
"learning_rate": 0.0004939119695302526,
|
|
"loss": 5.3935,
|
|
"mean_token_accuracy": 0.16472610086202621,
|
|
"num_tokens": 18175064.0,
|
|
"step": 10465
|
|
},
|
|
{
|
|
"entropy": 5.628536558151245,
|
|
"epoch": 0.8146275043765804,
|
|
"grad_norm": 1.921875,
|
|
"learning_rate": 0.0004939055642073224,
|
|
"loss": 5.5153,
|
|
"mean_token_accuracy": 0.15932594537734984,
|
|
"num_tokens": 18184251.0,
|
|
"step": 10470
|
|
},
|
|
{
|
|
"entropy": 5.572991132736206,
|
|
"epoch": 0.815016533748298,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004938991555628484,
|
|
"loss": 5.3747,
|
|
"mean_token_accuracy": 0.1688463032245636,
|
|
"num_tokens": 18193274.0,
|
|
"step": 10475
|
|
},
|
|
{
|
|
"entropy": 5.583941078186035,
|
|
"epoch": 0.8154055631200156,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.0004938927435969283,
|
|
"loss": 5.4113,
|
|
"mean_token_accuracy": 0.17508703023195266,
|
|
"num_tokens": 18201878.0,
|
|
"step": 10480
|
|
},
|
|
{
|
|
"entropy": 5.524939155578613,
|
|
"epoch": 0.8157945924917331,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.0004938863283096592,
|
|
"loss": 5.3672,
|
|
"mean_token_accuracy": 0.17121683210134506,
|
|
"num_tokens": 18210343.0,
|
|
"step": 10485
|
|
},
|
|
{
|
|
"entropy": 5.561619758605957,
|
|
"epoch": 0.8161836218634507,
|
|
"grad_norm": 2.34375,
|
|
"learning_rate": 0.0004938799097011384,
|
|
"loss": 5.5013,
|
|
"mean_token_accuracy": 0.16554916948080062,
|
|
"num_tokens": 18218599.0,
|
|
"step": 10490
|
|
},
|
|
{
|
|
"entropy": 5.51134672164917,
|
|
"epoch": 0.8165726512351682,
|
|
"grad_norm": 1.8515625,
|
|
"learning_rate": 0.0004938734877714634,
|
|
"loss": 5.3957,
|
|
"mean_token_accuracy": 0.17630584985017778,
|
|
"num_tokens": 18226384.0,
|
|
"step": 10495
|
|
},
|
|
{
|
|
"entropy": 5.538822889328003,
|
|
"epoch": 0.8169616806068858,
|
|
"grad_norm": 1.9453125,
|
|
"learning_rate": 0.0004938670625207317,
|
|
"loss": 5.3982,
|
|
"mean_token_accuracy": 0.16391255110502242,
|
|
"num_tokens": 18234894.0,
|
|
"step": 10500
|
|
},
|
|
{
|
|
"entropy": 5.574197673797608,
|
|
"epoch": 0.8173507099786034,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.0004938606339490406,
|
|
"loss": 5.4576,
|
|
"mean_token_accuracy": 0.16420527845621108,
|
|
"num_tokens": 18243768.0,
|
|
"step": 10505
|
|
},
|
|
{
|
|
"entropy": 5.6353496551513675,
|
|
"epoch": 0.817739739350321,
|
|
"grad_norm": 1.9140625,
|
|
"learning_rate": 0.0004938542020564877,
|
|
"loss": 5.465,
|
|
"mean_token_accuracy": 0.17037460654973985,
|
|
"num_tokens": 18252364.0,
|
|
"step": 10510
|
|
},
|
|
{
|
|
"entropy": 5.547120714187622,
|
|
"epoch": 0.8181287687220385,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.0004938477668431706,
|
|
"loss": 5.411,
|
|
"mean_token_accuracy": 0.16430456414818764,
|
|
"num_tokens": 18260997.0,
|
|
"step": 10515
|
|
},
|
|
{
|
|
"entropy": 5.6836306095123295,
|
|
"epoch": 0.8185177980937561,
|
|
"grad_norm": 1.8515625,
|
|
"learning_rate": 0.0004938413283091871,
|
|
"loss": 5.615,
|
|
"mean_token_accuracy": 0.1555199921131134,
|
|
"num_tokens": 18270171.0,
|
|
"step": 10520
|
|
},
|
|
{
|
|
"entropy": 5.702025604248047,
|
|
"epoch": 0.8189068274654736,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.0004938348864546347,
|
|
"loss": 5.4604,
|
|
"mean_token_accuracy": 0.16791959404945372,
|
|
"num_tokens": 18278772.0,
|
|
"step": 10525
|
|
},
|
|
{
|
|
"entropy": 5.496766424179077,
|
|
"epoch": 0.8192958568371912,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.0004938284412796111,
|
|
"loss": 5.2898,
|
|
"mean_token_accuracy": 0.17371753752231597,
|
|
"num_tokens": 18287305.0,
|
|
"step": 10530
|
|
},
|
|
{
|
|
"entropy": 5.461152744293213,
|
|
"epoch": 0.8196848862089088,
|
|
"grad_norm": 1.9921875,
|
|
"learning_rate": 0.0004938219927842144,
|
|
"loss": 5.502,
|
|
"mean_token_accuracy": 0.15855669975280762,
|
|
"num_tokens": 18296532.0,
|
|
"step": 10535
|
|
},
|
|
{
|
|
"entropy": 5.571554946899414,
|
|
"epoch": 0.8200739155806264,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.0004938155409685422,
|
|
"loss": 5.3647,
|
|
"mean_token_accuracy": 0.17604526430368422,
|
|
"num_tokens": 18304612.0,
|
|
"step": 10540
|
|
},
|
|
{
|
|
"entropy": 5.64055905342102,
|
|
"epoch": 0.820462944952344,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.0004938090858326923,
|
|
"loss": 5.4692,
|
|
"mean_token_accuracy": 0.1662233591079712,
|
|
"num_tokens": 18312970.0,
|
|
"step": 10545
|
|
},
|
|
{
|
|
"entropy": 5.655428886413574,
|
|
"epoch": 0.8208519743240614,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.000493802627376763,
|
|
"loss": 5.4582,
|
|
"mean_token_accuracy": 0.15710145533084868,
|
|
"num_tokens": 18321073.0,
|
|
"step": 10550
|
|
},
|
|
{
|
|
"entropy": 5.634154891967773,
|
|
"epoch": 0.821241003695779,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.0004937961656008518,
|
|
"loss": 5.4422,
|
|
"mean_token_accuracy": 0.16527319252490996,
|
|
"num_tokens": 18329960.0,
|
|
"step": 10555
|
|
},
|
|
{
|
|
"entropy": 5.594606256484985,
|
|
"epoch": 0.8216300330674966,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004937897005050573,
|
|
"loss": 5.432,
|
|
"mean_token_accuracy": 0.16835622638463973,
|
|
"num_tokens": 18337935.0,
|
|
"step": 10560
|
|
},
|
|
{
|
|
"entropy": 5.612130117416382,
|
|
"epoch": 0.8220190624392142,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.0004937832320894772,
|
|
"loss": 5.422,
|
|
"mean_token_accuracy": 0.16456200182437897,
|
|
"num_tokens": 18347445.0,
|
|
"step": 10565
|
|
},
|
|
{
|
|
"entropy": 5.608657741546631,
|
|
"epoch": 0.8224080918109318,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.0004937767603542098,
|
|
"loss": 5.4317,
|
|
"mean_token_accuracy": 0.16358766853809356,
|
|
"num_tokens": 18355817.0,
|
|
"step": 10570
|
|
},
|
|
{
|
|
"entropy": 5.643616819381714,
|
|
"epoch": 0.8227971211826492,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.0004937702852993534,
|
|
"loss": 5.428,
|
|
"mean_token_accuracy": 0.17017525881528855,
|
|
"num_tokens": 18363478.0,
|
|
"step": 10575
|
|
},
|
|
{
|
|
"entropy": 5.603677272796631,
|
|
"epoch": 0.8231861505543668,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.000493763806925006,
|
|
"loss": 5.4006,
|
|
"mean_token_accuracy": 0.1685510367155075,
|
|
"num_tokens": 18371788.0,
|
|
"step": 10580
|
|
},
|
|
{
|
|
"entropy": 5.5479573726654055,
|
|
"epoch": 0.8235751799260844,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.0004937573252312661,
|
|
"loss": 5.4321,
|
|
"mean_token_accuracy": 0.16589140743017197,
|
|
"num_tokens": 18380361.0,
|
|
"step": 10585
|
|
},
|
|
{
|
|
"entropy": 5.662957715988159,
|
|
"epoch": 0.823964209297802,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.000493750840218232,
|
|
"loss": 5.4881,
|
|
"mean_token_accuracy": 0.16637186259031295,
|
|
"num_tokens": 18389396.0,
|
|
"step": 10590
|
|
},
|
|
{
|
|
"entropy": 5.618829965591431,
|
|
"epoch": 0.8243532386695196,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.0004937443518860021,
|
|
"loss": 5.5703,
|
|
"mean_token_accuracy": 0.15324463993310927,
|
|
"num_tokens": 18398517.0,
|
|
"step": 10595
|
|
},
|
|
{
|
|
"entropy": 5.680560541152954,
|
|
"epoch": 0.8247422680412371,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 0.0004937378602346747,
|
|
"loss": 5.4868,
|
|
"mean_token_accuracy": 0.16931004375219344,
|
|
"num_tokens": 18406620.0,
|
|
"step": 10600
|
|
},
|
|
{
|
|
"entropy": 5.627822828292847,
|
|
"epoch": 0.8251312974129547,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0004937313652643485,
|
|
"loss": 5.5075,
|
|
"mean_token_accuracy": 0.15966977626085282,
|
|
"num_tokens": 18414849.0,
|
|
"step": 10605
|
|
},
|
|
{
|
|
"entropy": 5.5299896717071535,
|
|
"epoch": 0.8255203267846722,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.000493724866975122,
|
|
"loss": 5.4512,
|
|
"mean_token_accuracy": 0.15895414650440215,
|
|
"num_tokens": 18423675.0,
|
|
"step": 10610
|
|
},
|
|
{
|
|
"entropy": 5.648396110534668,
|
|
"epoch": 0.8259093561563898,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.0004937183653670937,
|
|
"loss": 5.5292,
|
|
"mean_token_accuracy": 0.1629027396440506,
|
|
"num_tokens": 18432848.0,
|
|
"step": 10615
|
|
},
|
|
{
|
|
"entropy": 5.684186744689941,
|
|
"epoch": 0.8262983855281074,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.0004937118604403623,
|
|
"loss": 5.5562,
|
|
"mean_token_accuracy": 0.16056231930851936,
|
|
"num_tokens": 18441210.0,
|
|
"step": 10620
|
|
},
|
|
{
|
|
"entropy": 5.709887838363647,
|
|
"epoch": 0.8266874148998249,
|
|
"grad_norm": 3.078125,
|
|
"learning_rate": 0.0004937053521950266,
|
|
"loss": 5.4572,
|
|
"mean_token_accuracy": 0.1593840554356575,
|
|
"num_tokens": 18450084.0,
|
|
"step": 10625
|
|
},
|
|
{
|
|
"entropy": 5.532354021072388,
|
|
"epoch": 0.8270764442715425,
|
|
"grad_norm": 2.6875,
|
|
"learning_rate": 0.0004936988406311854,
|
|
"loss": 5.3374,
|
|
"mean_token_accuracy": 0.1632529839873314,
|
|
"num_tokens": 18458329.0,
|
|
"step": 10630
|
|
},
|
|
{
|
|
"entropy": 5.558997011184692,
|
|
"epoch": 0.8274654736432601,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.0004936923257489373,
|
|
"loss": 5.464,
|
|
"mean_token_accuracy": 0.15941233411431313,
|
|
"num_tokens": 18467518.0,
|
|
"step": 10635
|
|
},
|
|
{
|
|
"entropy": 5.59447660446167,
|
|
"epoch": 0.8278545030149776,
|
|
"grad_norm": 3.515625,
|
|
"learning_rate": 0.0004936858075483811,
|
|
"loss": 5.3695,
|
|
"mean_token_accuracy": 0.17412900924682617,
|
|
"num_tokens": 18476051.0,
|
|
"step": 10640
|
|
},
|
|
{
|
|
"entropy": 5.623357057571411,
|
|
"epoch": 0.8282435323866952,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.000493679286029616,
|
|
"loss": 5.468,
|
|
"mean_token_accuracy": 0.16722351014614106,
|
|
"num_tokens": 18484492.0,
|
|
"step": 10645
|
|
},
|
|
{
|
|
"entropy": 5.600402116775513,
|
|
"epoch": 0.8286325617584127,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.0004936727611927407,
|
|
"loss": 5.5114,
|
|
"mean_token_accuracy": 0.1545984774827957,
|
|
"num_tokens": 18493759.0,
|
|
"step": 10650
|
|
},
|
|
{
|
|
"entropy": 5.621153974533081,
|
|
"epoch": 0.8290215911301303,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.0004936662330378546,
|
|
"loss": 5.377,
|
|
"mean_token_accuracy": 0.16482014507055281,
|
|
"num_tokens": 18501750.0,
|
|
"step": 10655
|
|
},
|
|
{
|
|
"entropy": 5.531733512878418,
|
|
"epoch": 0.8294106205018479,
|
|
"grad_norm": 2.53125,
|
|
"learning_rate": 0.0004936597015650561,
|
|
"loss": 5.3815,
|
|
"mean_token_accuracy": 0.16743748486042023,
|
|
"num_tokens": 18511003.0,
|
|
"step": 10660
|
|
},
|
|
{
|
|
"entropy": 5.543027877807617,
|
|
"epoch": 0.8297996498735655,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.0004936531667744448,
|
|
"loss": 5.4478,
|
|
"mean_token_accuracy": 0.1689344108104706,
|
|
"num_tokens": 18519544.0,
|
|
"step": 10665
|
|
},
|
|
{
|
|
"entropy": 5.7377807140350345,
|
|
"epoch": 0.8301886792452831,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004936466286661197,
|
|
"loss": 5.5388,
|
|
"mean_token_accuracy": 0.15954119265079497,
|
|
"num_tokens": 18528766.0,
|
|
"step": 10670
|
|
},
|
|
{
|
|
"entropy": 5.659150457382202,
|
|
"epoch": 0.8305777086170005,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.00049364008724018,
|
|
"loss": 5.5187,
|
|
"mean_token_accuracy": 0.16357494443655013,
|
|
"num_tokens": 18538243.0,
|
|
"step": 10675
|
|
},
|
|
{
|
|
"entropy": 5.625740814208984,
|
|
"epoch": 0.8309667379887181,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.000493633542496725,
|
|
"loss": 5.5363,
|
|
"mean_token_accuracy": 0.16319507211446763,
|
|
"num_tokens": 18547028.0,
|
|
"step": 10680
|
|
},
|
|
{
|
|
"entropy": 5.6835099220275875,
|
|
"epoch": 0.8313557673604357,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004936269944358539,
|
|
"loss": 5.5398,
|
|
"mean_token_accuracy": 0.1575927972793579,
|
|
"num_tokens": 18555821.0,
|
|
"step": 10685
|
|
},
|
|
{
|
|
"entropy": 5.609963035583496,
|
|
"epoch": 0.8317447967321533,
|
|
"grad_norm": 1.9296875,
|
|
"learning_rate": 0.0004936204430576664,
|
|
"loss": 5.5093,
|
|
"mean_token_accuracy": 0.16261549592018126,
|
|
"num_tokens": 18564213.0,
|
|
"step": 10690
|
|
},
|
|
{
|
|
"entropy": 5.63144884109497,
|
|
"epoch": 0.8321338261038709,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004936138883622614,
|
|
"loss": 5.4735,
|
|
"mean_token_accuracy": 0.15985123217105865,
|
|
"num_tokens": 18573132.0,
|
|
"step": 10695
|
|
},
|
|
{
|
|
"entropy": 5.6417686462402346,
|
|
"epoch": 0.8325228554755884,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004936073303497387,
|
|
"loss": 5.3979,
|
|
"mean_token_accuracy": 0.16487181633710862,
|
|
"num_tokens": 18581131.0,
|
|
"step": 10700
|
|
},
|
|
{
|
|
"entropy": 5.551865196228027,
|
|
"epoch": 0.8329118848473059,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.0004936007690201976,
|
|
"loss": 5.4684,
|
|
"mean_token_accuracy": 0.15795023441314698,
|
|
"num_tokens": 18589602.0,
|
|
"step": 10705
|
|
},
|
|
{
|
|
"entropy": 5.591616535186768,
|
|
"epoch": 0.8333009142190235,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.000493594204373738,
|
|
"loss": 5.4534,
|
|
"mean_token_accuracy": 0.1631766602396965,
|
|
"num_tokens": 18598263.0,
|
|
"step": 10710
|
|
},
|
|
{
|
|
"entropy": 5.668677425384521,
|
|
"epoch": 0.8336899435907411,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.0004935876364104591,
|
|
"loss": 5.3665,
|
|
"mean_token_accuracy": 0.17012717872858046,
|
|
"num_tokens": 18606432.0,
|
|
"step": 10715
|
|
},
|
|
{
|
|
"entropy": 5.572932767868042,
|
|
"epoch": 0.8340789729624587,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.0004935810651304608,
|
|
"loss": 5.4929,
|
|
"mean_token_accuracy": 0.157133112847805,
|
|
"num_tokens": 18614769.0,
|
|
"step": 10720
|
|
},
|
|
{
|
|
"entropy": 5.583090305328369,
|
|
"epoch": 0.8344680023341763,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.0004935744905338427,
|
|
"loss": 5.4724,
|
|
"mean_token_accuracy": 0.1589192792773247,
|
|
"num_tokens": 18623505.0,
|
|
"step": 10725
|
|
},
|
|
{
|
|
"entropy": 5.650672674179077,
|
|
"epoch": 0.8348570317058938,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.0004935679126207046,
|
|
"loss": 5.4316,
|
|
"mean_token_accuracy": 0.17060806900262832,
|
|
"num_tokens": 18632072.0,
|
|
"step": 10730
|
|
},
|
|
{
|
|
"entropy": 5.676616048812866,
|
|
"epoch": 0.8352460610776113,
|
|
"grad_norm": 1.9453125,
|
|
"learning_rate": 0.0004935613313911463,
|
|
"loss": 5.5158,
|
|
"mean_token_accuracy": 0.16289742290973663,
|
|
"num_tokens": 18640439.0,
|
|
"step": 10735
|
|
},
|
|
{
|
|
"entropy": 5.633995294570923,
|
|
"epoch": 0.8356350904493289,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.0004935547468452678,
|
|
"loss": 5.5108,
|
|
"mean_token_accuracy": 0.1559978485107422,
|
|
"num_tokens": 18649554.0,
|
|
"step": 10740
|
|
},
|
|
{
|
|
"entropy": 5.611474895477295,
|
|
"epoch": 0.8360241198210465,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.0004935481589831688,
|
|
"loss": 5.3737,
|
|
"mean_token_accuracy": 0.16466816663742065,
|
|
"num_tokens": 18657918.0,
|
|
"step": 10745
|
|
},
|
|
{
|
|
"entropy": 5.609343767166138,
|
|
"epoch": 0.8364131491927641,
|
|
"grad_norm": 2.9375,
|
|
"learning_rate": 0.0004935415678049492,
|
|
"loss": 5.5058,
|
|
"mean_token_accuracy": 0.15636600106954573,
|
|
"num_tokens": 18666735.0,
|
|
"step": 10750
|
|
},
|
|
{
|
|
"entropy": 5.601467084884644,
|
|
"epoch": 0.8368021785644816,
|
|
"grad_norm": 1.953125,
|
|
"learning_rate": 0.0004935349733107094,
|
|
"loss": 5.3764,
|
|
"mean_token_accuracy": 0.16538919359445572,
|
|
"num_tokens": 18674977.0,
|
|
"step": 10755
|
|
},
|
|
{
|
|
"entropy": 5.596753263473511,
|
|
"epoch": 0.8371912079361992,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.000493528375500549,
|
|
"loss": 5.5191,
|
|
"mean_token_accuracy": 0.16155448257923127,
|
|
"num_tokens": 18683624.0,
|
|
"step": 10760
|
|
},
|
|
{
|
|
"entropy": 5.559602308273315,
|
|
"epoch": 0.8375802373079168,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.0004935217743745685,
|
|
"loss": 5.4278,
|
|
"mean_token_accuracy": 0.16552993953227996,
|
|
"num_tokens": 18692183.0,
|
|
"step": 10765
|
|
},
|
|
{
|
|
"entropy": 5.666599559783935,
|
|
"epoch": 0.8379692666796343,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.0004935151699328677,
|
|
"loss": 5.499,
|
|
"mean_token_accuracy": 0.15672486275434494,
|
|
"num_tokens": 18700989.0,
|
|
"step": 10770
|
|
},
|
|
{
|
|
"entropy": 5.591551017761231,
|
|
"epoch": 0.8383582960513519,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004935085621755471,
|
|
"loss": 5.3908,
|
|
"mean_token_accuracy": 0.17094944417476654,
|
|
"num_tokens": 18709126.0,
|
|
"step": 10775
|
|
},
|
|
{
|
|
"entropy": 5.582367753982544,
|
|
"epoch": 0.8387473254230694,
|
|
"grad_norm": 1.9609375,
|
|
"learning_rate": 0.000493501951102707,
|
|
"loss": 5.4686,
|
|
"mean_token_accuracy": 0.16579371690750122,
|
|
"num_tokens": 18717378.0,
|
|
"step": 10780
|
|
},
|
|
{
|
|
"entropy": 5.660096120834351,
|
|
"epoch": 0.839136354794787,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004934953367144474,
|
|
"loss": 5.5309,
|
|
"mean_token_accuracy": 0.15830570906400682,
|
|
"num_tokens": 18725694.0,
|
|
"step": 10785
|
|
},
|
|
{
|
|
"entropy": 5.624583578109741,
|
|
"epoch": 0.8395253841665046,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0004934887190108688,
|
|
"loss": 5.4156,
|
|
"mean_token_accuracy": 0.16701147109270095,
|
|
"num_tokens": 18734737.0,
|
|
"step": 10790
|
|
},
|
|
{
|
|
"entropy": 5.767678737640381,
|
|
"epoch": 0.8399144135382222,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 0.0004934820979920719,
|
|
"loss": 5.6585,
|
|
"mean_token_accuracy": 0.15456946641206742,
|
|
"num_tokens": 18743895.0,
|
|
"step": 10795
|
|
},
|
|
{
|
|
"entropy": 5.707660770416259,
|
|
"epoch": 0.8403034429099397,
|
|
"grad_norm": 2.5,
|
|
"learning_rate": 0.0004934754736581567,
|
|
"loss": 5.5085,
|
|
"mean_token_accuracy": 0.15829433649778366,
|
|
"num_tokens": 18753105.0,
|
|
"step": 10800
|
|
},
|
|
{
|
|
"entropy": 5.59853982925415,
|
|
"epoch": 0.8406924722816572,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.000493468846009224,
|
|
"loss": 5.3783,
|
|
"mean_token_accuracy": 0.1648821398615837,
|
|
"num_tokens": 18761593.0,
|
|
"step": 10805
|
|
},
|
|
{
|
|
"entropy": 5.657355213165284,
|
|
"epoch": 0.8410815016533748,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004934622150453742,
|
|
"loss": 5.4387,
|
|
"mean_token_accuracy": 0.16632137447595596,
|
|
"num_tokens": 18770105.0,
|
|
"step": 10810
|
|
},
|
|
{
|
|
"entropy": 5.578534269332886,
|
|
"epoch": 0.8414705310250924,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.000493455580766708,
|
|
"loss": 5.4783,
|
|
"mean_token_accuracy": 0.16191161870956422,
|
|
"num_tokens": 18778429.0,
|
|
"step": 10815
|
|
},
|
|
{
|
|
"entropy": 5.7210088729858395,
|
|
"epoch": 0.84185956039681,
|
|
"grad_norm": 1.9140625,
|
|
"learning_rate": 0.0004934489431733262,
|
|
"loss": 5.5272,
|
|
"mean_token_accuracy": 0.16185631603002548,
|
|
"num_tokens": 18787072.0,
|
|
"step": 10820
|
|
},
|
|
{
|
|
"entropy": 5.606151676177978,
|
|
"epoch": 0.8422485897685276,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.0004934423022653293,
|
|
"loss": 5.3896,
|
|
"mean_token_accuracy": 0.1717859461903572,
|
|
"num_tokens": 18795628.0,
|
|
"step": 10825
|
|
},
|
|
{
|
|
"entropy": 5.580146932601929,
|
|
"epoch": 0.842637619140245,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.0004934356580428182,
|
|
"loss": 5.4847,
|
|
"mean_token_accuracy": 0.1630293145775795,
|
|
"num_tokens": 18804313.0,
|
|
"step": 10830
|
|
},
|
|
{
|
|
"entropy": 5.64032244682312,
|
|
"epoch": 0.8430266485119626,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004934290105058937,
|
|
"loss": 5.5012,
|
|
"mean_token_accuracy": 0.15396807193756104,
|
|
"num_tokens": 18813170.0,
|
|
"step": 10835
|
|
},
|
|
{
|
|
"entropy": 5.614888048171997,
|
|
"epoch": 0.8434156778836802,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.0004934223596546565,
|
|
"loss": 5.4316,
|
|
"mean_token_accuracy": 0.16521376371383667,
|
|
"num_tokens": 18823009.0,
|
|
"step": 10840
|
|
},
|
|
{
|
|
"entropy": 5.626336193084716,
|
|
"epoch": 0.8438047072553978,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.0004934157054892077,
|
|
"loss": 5.5091,
|
|
"mean_token_accuracy": 0.1625869408249855,
|
|
"num_tokens": 18831272.0,
|
|
"step": 10845
|
|
},
|
|
{
|
|
"entropy": 5.58029990196228,
|
|
"epoch": 0.8441937366271154,
|
|
"grad_norm": 1.890625,
|
|
"learning_rate": 0.0004934090480096482,
|
|
"loss": 5.4635,
|
|
"mean_token_accuracy": 0.1612754136323929,
|
|
"num_tokens": 18839481.0,
|
|
"step": 10850
|
|
},
|
|
{
|
|
"entropy": 5.5860175609588625,
|
|
"epoch": 0.8445827659988329,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004934023872160791,
|
|
"loss": 5.4629,
|
|
"mean_token_accuracy": 0.1646273612976074,
|
|
"num_tokens": 18848586.0,
|
|
"step": 10855
|
|
},
|
|
{
|
|
"entropy": 5.636395359039307,
|
|
"epoch": 0.8449717953705504,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004933957231086014,
|
|
"loss": 5.3536,
|
|
"mean_token_accuracy": 0.1664646029472351,
|
|
"num_tokens": 18856948.0,
|
|
"step": 10860
|
|
},
|
|
{
|
|
"entropy": 5.608237028121948,
|
|
"epoch": 0.845360824742268,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004933890556873161,
|
|
"loss": 5.4246,
|
|
"mean_token_accuracy": 0.16303920298814772,
|
|
"num_tokens": 18864741.0,
|
|
"step": 10865
|
|
},
|
|
{
|
|
"entropy": 5.601611471176147,
|
|
"epoch": 0.8457498541139856,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004933823849523246,
|
|
"loss": 5.487,
|
|
"mean_token_accuracy": 0.1628875717520714,
|
|
"num_tokens": 18873373.0,
|
|
"step": 10870
|
|
},
|
|
{
|
|
"entropy": 5.6636919498443605,
|
|
"epoch": 0.8461388834857032,
|
|
"grad_norm": 1.8984375,
|
|
"learning_rate": 0.0004933757109037279,
|
|
"loss": 5.3659,
|
|
"mean_token_accuracy": 0.1616743564605713,
|
|
"num_tokens": 18881590.0,
|
|
"step": 10875
|
|
},
|
|
{
|
|
"entropy": 5.593954610824585,
|
|
"epoch": 0.8465279128574207,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.0004933690335416274,
|
|
"loss": 5.4656,
|
|
"mean_token_accuracy": 0.16539863348007203,
|
|
"num_tokens": 18889838.0,
|
|
"step": 10880
|
|
},
|
|
{
|
|
"entropy": 5.547439193725586,
|
|
"epoch": 0.8469169422291383,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004933623528661245,
|
|
"loss": 5.3853,
|
|
"mean_token_accuracy": 0.16657217293977739,
|
|
"num_tokens": 18898577.0,
|
|
"step": 10885
|
|
},
|
|
{
|
|
"entropy": 5.627489328384399,
|
|
"epoch": 0.8473059716008559,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.0004933556688773203,
|
|
"loss": 5.5316,
|
|
"mean_token_accuracy": 0.1601867124438286,
|
|
"num_tokens": 18907309.0,
|
|
"step": 10890
|
|
},
|
|
{
|
|
"entropy": 5.6386476993560795,
|
|
"epoch": 0.8476950009725734,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.0004933489815753165,
|
|
"loss": 5.4577,
|
|
"mean_token_accuracy": 0.16943264454603196,
|
|
"num_tokens": 18915956.0,
|
|
"step": 10895
|
|
},
|
|
{
|
|
"entropy": 5.594503593444824,
|
|
"epoch": 0.848084030344291,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004933422909602143,
|
|
"loss": 5.5428,
|
|
"mean_token_accuracy": 0.1612271785736084,
|
|
"num_tokens": 18924603.0,
|
|
"step": 10900
|
|
},
|
|
{
|
|
"entropy": 5.5920453548431395,
|
|
"epoch": 0.8484730597160085,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.0004933355970321155,
|
|
"loss": 5.4211,
|
|
"mean_token_accuracy": 0.17264553308486938,
|
|
"num_tokens": 18933231.0,
|
|
"step": 10905
|
|
},
|
|
{
|
|
"entropy": 5.6834397315979,
|
|
"epoch": 0.8488620890877261,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004933288997911215,
|
|
"loss": 5.5479,
|
|
"mean_token_accuracy": 0.15402281135320664,
|
|
"num_tokens": 18942172.0,
|
|
"step": 10910
|
|
},
|
|
{
|
|
"entropy": 5.59771203994751,
|
|
"epoch": 0.8492511184594437,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004933221992373338,
|
|
"loss": 5.4833,
|
|
"mean_token_accuracy": 0.16327161639928817,
|
|
"num_tokens": 18951440.0,
|
|
"step": 10915
|
|
},
|
|
{
|
|
"entropy": 5.5913207054138185,
|
|
"epoch": 0.8496401478311613,
|
|
"grad_norm": 3.546875,
|
|
"learning_rate": 0.0004933154953708544,
|
|
"loss": 5.4305,
|
|
"mean_token_accuracy": 0.16286325454711914,
|
|
"num_tokens": 18959797.0,
|
|
"step": 10920
|
|
},
|
|
{
|
|
"entropy": 5.660141468048096,
|
|
"epoch": 0.8500291772028788,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.0004933087881917848,
|
|
"loss": 5.4544,
|
|
"mean_token_accuracy": 0.1625726714730263,
|
|
"num_tokens": 18968811.0,
|
|
"step": 10925
|
|
},
|
|
{
|
|
"entropy": 5.708744668960572,
|
|
"epoch": 0.8504182065745964,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004933020777002268,
|
|
"loss": 5.5848,
|
|
"mean_token_accuracy": 0.15446060448884963,
|
|
"num_tokens": 18977467.0,
|
|
"step": 10930
|
|
},
|
|
{
|
|
"entropy": 5.683827066421509,
|
|
"epoch": 0.8508072359463139,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004932953638962823,
|
|
"loss": 5.4659,
|
|
"mean_token_accuracy": 0.1637033551931381,
|
|
"num_tokens": 18985760.0,
|
|
"step": 10935
|
|
},
|
|
{
|
|
"entropy": 5.676061058044434,
|
|
"epoch": 0.8511962653180315,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.000493288646780053,
|
|
"loss": 5.5188,
|
|
"mean_token_accuracy": 0.1511535733938217,
|
|
"num_tokens": 18993812.0,
|
|
"step": 10940
|
|
},
|
|
{
|
|
"entropy": 5.6075294494628904,
|
|
"epoch": 0.8515852946897491,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.0004932819263516409,
|
|
"loss": 5.5068,
|
|
"mean_token_accuracy": 0.15953125208616256,
|
|
"num_tokens": 19003056.0,
|
|
"step": 10945
|
|
},
|
|
{
|
|
"entropy": 5.65568699836731,
|
|
"epoch": 0.8519743240614667,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004932752026111481,
|
|
"loss": 5.4952,
|
|
"mean_token_accuracy": 0.16747940629720687,
|
|
"num_tokens": 19011533.0,
|
|
"step": 10950
|
|
},
|
|
{
|
|
"entropy": 5.638143587112427,
|
|
"epoch": 0.8523633534331843,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004932684755586765,
|
|
"loss": 5.4503,
|
|
"mean_token_accuracy": 0.1679576128721237,
|
|
"num_tokens": 19020773.0,
|
|
"step": 10955
|
|
},
|
|
{
|
|
"entropy": 5.610541296005249,
|
|
"epoch": 0.8527523828049017,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.0004932617451943282,
|
|
"loss": 5.4595,
|
|
"mean_token_accuracy": 0.16216137409210205,
|
|
"num_tokens": 19029809.0,
|
|
"step": 10960
|
|
},
|
|
{
|
|
"entropy": 5.605466604232788,
|
|
"epoch": 0.8531414121766193,
|
|
"grad_norm": 2.390625,
|
|
"learning_rate": 0.0004932550115182053,
|
|
"loss": 5.3852,
|
|
"mean_token_accuracy": 0.16381414383649825,
|
|
"num_tokens": 19038875.0,
|
|
"step": 10965
|
|
},
|
|
{
|
|
"entropy": 5.637158155441284,
|
|
"epoch": 0.8535304415483369,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.00049324827453041,
|
|
"loss": 5.4885,
|
|
"mean_token_accuracy": 0.1694040685892105,
|
|
"num_tokens": 19047273.0,
|
|
"step": 10970
|
|
},
|
|
{
|
|
"entropy": 5.568561792373657,
|
|
"epoch": 0.8539194709200545,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004932415342310446,
|
|
"loss": 5.4235,
|
|
"mean_token_accuracy": 0.16522018760442733,
|
|
"num_tokens": 19056309.0,
|
|
"step": 10975
|
|
},
|
|
{
|
|
"entropy": 5.598409271240234,
|
|
"epoch": 0.8543085002917721,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004932347906202111,
|
|
"loss": 5.3848,
|
|
"mean_token_accuracy": 0.16564959287643433,
|
|
"num_tokens": 19064487.0,
|
|
"step": 10980
|
|
},
|
|
{
|
|
"entropy": 5.613663625717163,
|
|
"epoch": 0.8546975296634896,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.000493228043698012,
|
|
"loss": 5.611,
|
|
"mean_token_accuracy": 0.15799091160297393,
|
|
"num_tokens": 19073431.0,
|
|
"step": 10985
|
|
},
|
|
{
|
|
"entropy": 5.61237416267395,
|
|
"epoch": 0.8550865590352071,
|
|
"grad_norm": 1.890625,
|
|
"learning_rate": 0.0004932212934645498,
|
|
"loss": 5.4869,
|
|
"mean_token_accuracy": 0.1639371022582054,
|
|
"num_tokens": 19081648.0,
|
|
"step": 10990
|
|
},
|
|
{
|
|
"entropy": 5.552393102645874,
|
|
"epoch": 0.8554755884069247,
|
|
"grad_norm": 1.96875,
|
|
"learning_rate": 0.0004932145399199268,
|
|
"loss": 5.4015,
|
|
"mean_token_accuracy": 0.16887827664613725,
|
|
"num_tokens": 19090581.0,
|
|
"step": 10995
|
|
},
|
|
{
|
|
"entropy": 5.669221019744873,
|
|
"epoch": 0.8558646177786423,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004932077830642455,
|
|
"loss": 5.4923,
|
|
"mean_token_accuracy": 0.16095945239067078,
|
|
"num_tokens": 19098924.0,
|
|
"step": 11000
|
|
},
|
|
{
|
|
"entropy": 5.638146638870239,
|
|
"epoch": 0.8562536471503599,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004932010228976084,
|
|
"loss": 5.4869,
|
|
"mean_token_accuracy": 0.16549017429351806,
|
|
"num_tokens": 19108267.0,
|
|
"step": 11005
|
|
},
|
|
{
|
|
"entropy": 5.7128057956695555,
|
|
"epoch": 0.8566426765220774,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.000493194259420118,
|
|
"loss": 5.4973,
|
|
"mean_token_accuracy": 0.15768655389547348,
|
|
"num_tokens": 19117158.0,
|
|
"step": 11010
|
|
},
|
|
{
|
|
"entropy": 5.610513210296631,
|
|
"epoch": 0.857031705893795,
|
|
"grad_norm": 2.828125,
|
|
"learning_rate": 0.000493187492631877,
|
|
"loss": 5.4715,
|
|
"mean_token_accuracy": 0.16342298537492753,
|
|
"num_tokens": 19126013.0,
|
|
"step": 11015
|
|
},
|
|
{
|
|
"entropy": 5.5142913341522215,
|
|
"epoch": 0.8574207352655125,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.0004931807225329882,
|
|
"loss": 5.4189,
|
|
"mean_token_accuracy": 0.16237692832946776,
|
|
"num_tokens": 19134655.0,
|
|
"step": 11020
|
|
},
|
|
{
|
|
"entropy": 5.530030536651611,
|
|
"epoch": 0.8578097646372301,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004931739491235541,
|
|
"loss": 5.2935,
|
|
"mean_token_accuracy": 0.16517002135515213,
|
|
"num_tokens": 19143311.0,
|
|
"step": 11025
|
|
},
|
|
{
|
|
"entropy": 5.637990999221802,
|
|
"epoch": 0.8581987940089477,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004931671724036777,
|
|
"loss": 5.4646,
|
|
"mean_token_accuracy": 0.17016117870807648,
|
|
"num_tokens": 19152422.0,
|
|
"step": 11030
|
|
},
|
|
{
|
|
"entropy": 5.642723274230957,
|
|
"epoch": 0.8585878233806652,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.0004931603923734616,
|
|
"loss": 5.5296,
|
|
"mean_token_accuracy": 0.16236407160758973,
|
|
"num_tokens": 19161510.0,
|
|
"step": 11035
|
|
},
|
|
{
|
|
"entropy": 5.541413259506226,
|
|
"epoch": 0.8589768527523828,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.0004931536090330088,
|
|
"loss": 5.3829,
|
|
"mean_token_accuracy": 0.16918981373310088,
|
|
"num_tokens": 19170097.0,
|
|
"step": 11040
|
|
},
|
|
{
|
|
"entropy": 5.62370457649231,
|
|
"epoch": 0.8593658821241004,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004931468223824222,
|
|
"loss": 5.4284,
|
|
"mean_token_accuracy": 0.16561289727687836,
|
|
"num_tokens": 19179131.0,
|
|
"step": 11045
|
|
},
|
|
{
|
|
"entropy": 5.502949905395508,
|
|
"epoch": 0.859754911495818,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004931400324218048,
|
|
"loss": 5.3372,
|
|
"mean_token_accuracy": 0.17328149378299712,
|
|
"num_tokens": 19187289.0,
|
|
"step": 11050
|
|
},
|
|
{
|
|
"entropy": 5.547070121765136,
|
|
"epoch": 0.8601439408675355,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004931332391512597,
|
|
"loss": 5.4613,
|
|
"mean_token_accuracy": 0.1671719267964363,
|
|
"num_tokens": 19195746.0,
|
|
"step": 11055
|
|
},
|
|
{
|
|
"entropy": 5.691220664978028,
|
|
"epoch": 0.860532970239253,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004931264425708897,
|
|
"loss": 5.466,
|
|
"mean_token_accuracy": 0.159692120552063,
|
|
"num_tokens": 19204683.0,
|
|
"step": 11060
|
|
},
|
|
{
|
|
"entropy": 5.560989332199097,
|
|
"epoch": 0.8609219996109706,
|
|
"grad_norm": 1.84375,
|
|
"learning_rate": 0.0004931196426807983,
|
|
"loss": 5.3821,
|
|
"mean_token_accuracy": 0.1581795945763588,
|
|
"num_tokens": 19213405.0,
|
|
"step": 11065
|
|
},
|
|
{
|
|
"entropy": 5.608947992324829,
|
|
"epoch": 0.8613110289826882,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.0004931128394810884,
|
|
"loss": 5.4838,
|
|
"mean_token_accuracy": 0.164456707239151,
|
|
"num_tokens": 19222717.0,
|
|
"step": 11070
|
|
},
|
|
{
|
|
"entropy": 5.664914512634278,
|
|
"epoch": 0.8617000583544058,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.0004931060329718634,
|
|
"loss": 5.4778,
|
|
"mean_token_accuracy": 0.1608600564301014,
|
|
"num_tokens": 19230688.0,
|
|
"step": 11075
|
|
},
|
|
{
|
|
"entropy": 5.601462030410767,
|
|
"epoch": 0.8620890877261234,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.0004930992231532265,
|
|
"loss": 5.5435,
|
|
"mean_token_accuracy": 0.15547362491488456,
|
|
"num_tokens": 19239192.0,
|
|
"step": 11080
|
|
},
|
|
{
|
|
"entropy": 5.663993453979492,
|
|
"epoch": 0.8624781170978408,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.000493092410025281,
|
|
"loss": 5.5433,
|
|
"mean_token_accuracy": 0.1593363881111145,
|
|
"num_tokens": 19247903.0,
|
|
"step": 11085
|
|
},
|
|
{
|
|
"entropy": 5.613435745239258,
|
|
"epoch": 0.8628671464695584,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004930855935881302,
|
|
"loss": 5.4378,
|
|
"mean_token_accuracy": 0.16696920841932297,
|
|
"num_tokens": 19256127.0,
|
|
"step": 11090
|
|
},
|
|
{
|
|
"entropy": 5.592149305343628,
|
|
"epoch": 0.863256175841276,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 0.0004930787738418777,
|
|
"loss": 5.423,
|
|
"mean_token_accuracy": 0.1664299875497818,
|
|
"num_tokens": 19264742.0,
|
|
"step": 11095
|
|
},
|
|
{
|
|
"entropy": 5.536935091018677,
|
|
"epoch": 0.8636452052129936,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.0004930719507866269,
|
|
"loss": 5.3956,
|
|
"mean_token_accuracy": 0.16626548022031784,
|
|
"num_tokens": 19273618.0,
|
|
"step": 11100
|
|
},
|
|
{
|
|
"entropy": 5.585460996627807,
|
|
"epoch": 0.8640342345847112,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004930651244224814,
|
|
"loss": 5.4407,
|
|
"mean_token_accuracy": 0.16741829961538315,
|
|
"num_tokens": 19281792.0,
|
|
"step": 11105
|
|
},
|
|
{
|
|
"entropy": 5.541091251373291,
|
|
"epoch": 0.8644232639564287,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.0004930582947495448,
|
|
"loss": 5.4234,
|
|
"mean_token_accuracy": 0.16469394862651826,
|
|
"num_tokens": 19289738.0,
|
|
"step": 11110
|
|
},
|
|
{
|
|
"entropy": 5.66100287437439,
|
|
"epoch": 0.8648122933281462,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004930514617679206,
|
|
"loss": 5.4086,
|
|
"mean_token_accuracy": 0.16892794221639634,
|
|
"num_tokens": 19298711.0,
|
|
"step": 11115
|
|
},
|
|
{
|
|
"entropy": 5.667518424987793,
|
|
"epoch": 0.8652013226998638,
|
|
"grad_norm": 1.8515625,
|
|
"learning_rate": 0.0004930446254777125,
|
|
"loss": 5.5038,
|
|
"mean_token_accuracy": 0.15695202499628066,
|
|
"num_tokens": 19307435.0,
|
|
"step": 11120
|
|
},
|
|
{
|
|
"entropy": 5.569238662719727,
|
|
"epoch": 0.8655903520715814,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.0004930377858790242,
|
|
"loss": 5.3637,
|
|
"mean_token_accuracy": 0.16685487926006318,
|
|
"num_tokens": 19315327.0,
|
|
"step": 11125
|
|
},
|
|
{
|
|
"entropy": 5.5374448776245115,
|
|
"epoch": 0.865979381443299,
|
|
"grad_norm": 1.9453125,
|
|
"learning_rate": 0.0004930309429719595,
|
|
"loss": 5.3549,
|
|
"mean_token_accuracy": 0.16606869399547577,
|
|
"num_tokens": 19323261.0,
|
|
"step": 11130
|
|
},
|
|
{
|
|
"entropy": 5.462720441818237,
|
|
"epoch": 0.8663684108150166,
|
|
"grad_norm": 1.9296875,
|
|
"learning_rate": 0.0004930240967566224,
|
|
"loss": 5.3267,
|
|
"mean_token_accuracy": 0.16801577657461167,
|
|
"num_tokens": 19332297.0,
|
|
"step": 11135
|
|
},
|
|
{
|
|
"entropy": 5.561023759841919,
|
|
"epoch": 0.8667574401867341,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004930172472331167,
|
|
"loss": 5.3171,
|
|
"mean_token_accuracy": 0.17380981594324113,
|
|
"num_tokens": 19340848.0,
|
|
"step": 11140
|
|
},
|
|
{
|
|
"entropy": 5.5794753074646,
|
|
"epoch": 0.8671464695584516,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.0004930103944015463,
|
|
"loss": 5.3917,
|
|
"mean_token_accuracy": 0.16731711477041245,
|
|
"num_tokens": 19349072.0,
|
|
"step": 11145
|
|
},
|
|
{
|
|
"entropy": 5.643822050094604,
|
|
"epoch": 0.8675354989301692,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0004930035382620149,
|
|
"loss": 5.4462,
|
|
"mean_token_accuracy": 0.16319260746240616,
|
|
"num_tokens": 19357723.0,
|
|
"step": 11150
|
|
},
|
|
{
|
|
"entropy": 5.541302919387817,
|
|
"epoch": 0.8679245283018868,
|
|
"grad_norm": 1.9765625,
|
|
"learning_rate": 0.000492996678814627,
|
|
"loss": 5.3759,
|
|
"mean_token_accuracy": 0.1692714661359787,
|
|
"num_tokens": 19365925.0,
|
|
"step": 11155
|
|
},
|
|
{
|
|
"entropy": 5.545079565048217,
|
|
"epoch": 0.8683135576736044,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004929898160594865,
|
|
"loss": 5.4292,
|
|
"mean_token_accuracy": 0.17178272008895873,
|
|
"num_tokens": 19374190.0,
|
|
"step": 11160
|
|
},
|
|
{
|
|
"entropy": 5.583577394485474,
|
|
"epoch": 0.8687025870453219,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.0004929829499966974,
|
|
"loss": 5.4211,
|
|
"mean_token_accuracy": 0.16865333765745164,
|
|
"num_tokens": 19382375.0,
|
|
"step": 11165
|
|
},
|
|
{
|
|
"entropy": 5.652921390533447,
|
|
"epoch": 0.8690916164170395,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.0004929760806263641,
|
|
"loss": 5.4836,
|
|
"mean_token_accuracy": 0.16410215198993683,
|
|
"num_tokens": 19390191.0,
|
|
"step": 11170
|
|
},
|
|
{
|
|
"entropy": 5.5531957149505615,
|
|
"epoch": 0.8694806457887571,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004929692079485906,
|
|
"loss": 5.2848,
|
|
"mean_token_accuracy": 0.17280343919992447,
|
|
"num_tokens": 19399401.0,
|
|
"step": 11175
|
|
},
|
|
{
|
|
"entropy": 5.527303886413574,
|
|
"epoch": 0.8698696751604746,
|
|
"grad_norm": 1.9140625,
|
|
"learning_rate": 0.0004929623319634814,
|
|
"loss": 5.3696,
|
|
"mean_token_accuracy": 0.1724821150302887,
|
|
"num_tokens": 19407956.0,
|
|
"step": 11180
|
|
},
|
|
{
|
|
"entropy": 5.584284162521362,
|
|
"epoch": 0.8702587045321922,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.0004929554526711407,
|
|
"loss": 5.5522,
|
|
"mean_token_accuracy": 0.15761916637420653,
|
|
"num_tokens": 19416432.0,
|
|
"step": 11185
|
|
},
|
|
{
|
|
"entropy": 5.559841871261597,
|
|
"epoch": 0.8706477339039097,
|
|
"grad_norm": 2.90625,
|
|
"learning_rate": 0.0004929485700716729,
|
|
"loss": 5.3959,
|
|
"mean_token_accuracy": 0.16579597294330597,
|
|
"num_tokens": 19425208.0,
|
|
"step": 11190
|
|
},
|
|
{
|
|
"entropy": 5.721555614471436,
|
|
"epoch": 0.8710367632756273,
|
|
"grad_norm": 1.90625,
|
|
"learning_rate": 0.0004929416841651824,
|
|
"loss": 5.5473,
|
|
"mean_token_accuracy": 0.16297764033079148,
|
|
"num_tokens": 19434169.0,
|
|
"step": 11195
|
|
},
|
|
{
|
|
"entropy": 5.581093788146973,
|
|
"epoch": 0.8714257926473449,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.0004929347949517739,
|
|
"loss": 5.3063,
|
|
"mean_token_accuracy": 0.1769345611333847,
|
|
"num_tokens": 19443484.0,
|
|
"step": 11200
|
|
},
|
|
{
|
|
"entropy": 5.532596826553345,
|
|
"epoch": 0.8718148220190625,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.0004929279024315516,
|
|
"loss": 5.4528,
|
|
"mean_token_accuracy": 0.16987681090831758,
|
|
"num_tokens": 19452193.0,
|
|
"step": 11205
|
|
},
|
|
{
|
|
"entropy": 5.703162717819214,
|
|
"epoch": 0.87220385139078,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.0004929210066046204,
|
|
"loss": 5.5974,
|
|
"mean_token_accuracy": 0.1519150525331497,
|
|
"num_tokens": 19460684.0,
|
|
"step": 11210
|
|
},
|
|
{
|
|
"entropy": 5.61011004447937,
|
|
"epoch": 0.8725928807624975,
|
|
"grad_norm": 2.515625,
|
|
"learning_rate": 0.0004929141074710847,
|
|
"loss": 5.4156,
|
|
"mean_token_accuracy": 0.1684863656759262,
|
|
"num_tokens": 19469206.0,
|
|
"step": 11215
|
|
},
|
|
{
|
|
"entropy": 5.585877990722656,
|
|
"epoch": 0.8729819101342151,
|
|
"grad_norm": 2.765625,
|
|
"learning_rate": 0.0004929072050310491,
|
|
"loss": 5.4514,
|
|
"mean_token_accuracy": 0.16691024005413055,
|
|
"num_tokens": 19477514.0,
|
|
"step": 11220
|
|
},
|
|
{
|
|
"entropy": 5.588381099700928,
|
|
"epoch": 0.8733709395059327,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.0004929002992846188,
|
|
"loss": 5.5181,
|
|
"mean_token_accuracy": 0.15903030708432198,
|
|
"num_tokens": 19486792.0,
|
|
"step": 11225
|
|
},
|
|
{
|
|
"entropy": 5.607358837127686,
|
|
"epoch": 0.8737599688776503,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004928933902318981,
|
|
"loss": 5.4641,
|
|
"mean_token_accuracy": 0.1683722749352455,
|
|
"num_tokens": 19495708.0,
|
|
"step": 11230
|
|
},
|
|
{
|
|
"entropy": 5.662119197845459,
|
|
"epoch": 0.8741489982493679,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.000492886477872992,
|
|
"loss": 5.5943,
|
|
"mean_token_accuracy": 0.1506945863366127,
|
|
"num_tokens": 19505063.0,
|
|
"step": 11235
|
|
},
|
|
{
|
|
"entropy": 5.6910947322845455,
|
|
"epoch": 0.8745380276210853,
|
|
"grad_norm": 2.265625,
|
|
"learning_rate": 0.0004928795622080054,
|
|
"loss": 5.5353,
|
|
"mean_token_accuracy": 0.1598251774907112,
|
|
"num_tokens": 19514641.0,
|
|
"step": 11240
|
|
},
|
|
{
|
|
"entropy": 5.633415365219117,
|
|
"epoch": 0.8749270569928029,
|
|
"grad_norm": 2.296875,
|
|
"learning_rate": 0.0004928726432370434,
|
|
"loss": 5.4213,
|
|
"mean_token_accuracy": 0.16929391473531724,
|
|
"num_tokens": 19523136.0,
|
|
"step": 11245
|
|
},
|
|
{
|
|
"entropy": 5.551081943511963,
|
|
"epoch": 0.8753160863645205,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.0004928657209602107,
|
|
"loss": 5.3213,
|
|
"mean_token_accuracy": 0.1730360582470894,
|
|
"num_tokens": 19532258.0,
|
|
"step": 11250
|
|
},
|
|
{
|
|
"entropy": 5.617392063140869,
|
|
"epoch": 0.8757051157362381,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.0004928587953776125,
|
|
"loss": 5.5649,
|
|
"mean_token_accuracy": 0.16101454198360443,
|
|
"num_tokens": 19541235.0,
|
|
"step": 11255
|
|
},
|
|
{
|
|
"entropy": 5.634084224700928,
|
|
"epoch": 0.8760941451079557,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.0004928518664893538,
|
|
"loss": 5.4865,
|
|
"mean_token_accuracy": 0.1626735359430313,
|
|
"num_tokens": 19550259.0,
|
|
"step": 11260
|
|
},
|
|
{
|
|
"entropy": 5.6849696159362795,
|
|
"epoch": 0.8764831744796732,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.0004928449342955397,
|
|
"loss": 5.464,
|
|
"mean_token_accuracy": 0.16722146421670914,
|
|
"num_tokens": 19558500.0,
|
|
"step": 11265
|
|
},
|
|
{
|
|
"entropy": 5.594943904876709,
|
|
"epoch": 0.8768722038513908,
|
|
"grad_norm": 3.015625,
|
|
"learning_rate": 0.0004928379987962756,
|
|
"loss": 5.4165,
|
|
"mean_token_accuracy": 0.16317967623472213,
|
|
"num_tokens": 19566562.0,
|
|
"step": 11270
|
|
},
|
|
{
|
|
"entropy": 5.521223878860473,
|
|
"epoch": 0.8772612332231083,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.0004928310599916666,
|
|
"loss": 5.4308,
|
|
"mean_token_accuracy": 0.16181573122739792,
|
|
"num_tokens": 19575219.0,
|
|
"step": 11275
|
|
},
|
|
{
|
|
"entropy": 5.5214362144470215,
|
|
"epoch": 0.8776502625948259,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.0004928241178818178,
|
|
"loss": 5.3413,
|
|
"mean_token_accuracy": 0.1718982219696045,
|
|
"num_tokens": 19584311.0,
|
|
"step": 11280
|
|
},
|
|
{
|
|
"entropy": 5.6188047409057615,
|
|
"epoch": 0.8780392919665435,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.0004928171724668349,
|
|
"loss": 5.5088,
|
|
"mean_token_accuracy": 0.15695698261260987,
|
|
"num_tokens": 19593802.0,
|
|
"step": 11285
|
|
},
|
|
{
|
|
"entropy": 5.594609975814819,
|
|
"epoch": 0.878428321338261,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.0004928102237468229,
|
|
"loss": 5.467,
|
|
"mean_token_accuracy": 0.1578998565673828,
|
|
"num_tokens": 19603046.0,
|
|
"step": 11290
|
|
},
|
|
{
|
|
"entropy": 5.497394609451294,
|
|
"epoch": 0.8788173507099786,
|
|
"grad_norm": 1.921875,
|
|
"learning_rate": 0.0004928032717218876,
|
|
"loss": 5.3614,
|
|
"mean_token_accuracy": 0.165121890604496,
|
|
"num_tokens": 19611609.0,
|
|
"step": 11295
|
|
},
|
|
{
|
|
"entropy": 5.5575244426727295,
|
|
"epoch": 0.8792063800816962,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004927963163921343,
|
|
"loss": 5.3636,
|
|
"mean_token_accuracy": 0.16076015383005143,
|
|
"num_tokens": 19619380.0,
|
|
"step": 11300
|
|
},
|
|
{
|
|
"entropy": 5.706099224090576,
|
|
"epoch": 0.8795954094534137,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.0004927893577576685,
|
|
"loss": 5.5475,
|
|
"mean_token_accuracy": 0.15549730360507966,
|
|
"num_tokens": 19628336.0,
|
|
"step": 11305
|
|
},
|
|
{
|
|
"entropy": 5.612709951400757,
|
|
"epoch": 0.8799844388251313,
|
|
"grad_norm": 2.5625,
|
|
"learning_rate": 0.0004927823958185959,
|
|
"loss": 5.4992,
|
|
"mean_token_accuracy": 0.1678774818778038,
|
|
"num_tokens": 19637888.0,
|
|
"step": 11310
|
|
},
|
|
{
|
|
"entropy": 5.485748767852783,
|
|
"epoch": 0.8803734681968488,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.000492775430575022,
|
|
"loss": 5.4317,
|
|
"mean_token_accuracy": 0.16003298610448838,
|
|
"num_tokens": 19646123.0,
|
|
"step": 11315
|
|
},
|
|
{
|
|
"entropy": 5.5363319396972654,
|
|
"epoch": 0.8807624975685664,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.0004927684620270527,
|
|
"loss": 5.4093,
|
|
"mean_token_accuracy": 0.16914606392383574,
|
|
"num_tokens": 19655264.0,
|
|
"step": 11320
|
|
},
|
|
{
|
|
"entropy": 5.720416736602783,
|
|
"epoch": 0.881151526940284,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 0.0004927614901747935,
|
|
"loss": 5.5469,
|
|
"mean_token_accuracy": 0.1551755353808403,
|
|
"num_tokens": 19663594.0,
|
|
"step": 11325
|
|
},
|
|
{
|
|
"entropy": 5.663323068618775,
|
|
"epoch": 0.8815405563120016,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 0.0004927545150183503,
|
|
"loss": 5.4751,
|
|
"mean_token_accuracy": 0.16405114084482192,
|
|
"num_tokens": 19671515.0,
|
|
"step": 11330
|
|
},
|
|
{
|
|
"entropy": 5.541317701339722,
|
|
"epoch": 0.8819295856837192,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.000492747536557829,
|
|
"loss": 5.348,
|
|
"mean_token_accuracy": 0.1685470908880234,
|
|
"num_tokens": 19680288.0,
|
|
"step": 11335
|
|
},
|
|
{
|
|
"entropy": 5.592640209197998,
|
|
"epoch": 0.8823186150554367,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.0004927405547933353,
|
|
"loss": 5.3518,
|
|
"mean_token_accuracy": 0.1638496845960617,
|
|
"num_tokens": 19688717.0,
|
|
"step": 11340
|
|
},
|
|
{
|
|
"entropy": 5.525131177902222,
|
|
"epoch": 0.8827076444271542,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.0004927335697249753,
|
|
"loss": 5.3127,
|
|
"mean_token_accuracy": 0.17157813906669617,
|
|
"num_tokens": 19697412.0,
|
|
"step": 11345
|
|
},
|
|
{
|
|
"entropy": 5.558753824234008,
|
|
"epoch": 0.8830966737988718,
|
|
"grad_norm": 2.359375,
|
|
"learning_rate": 0.0004927265813528549,
|
|
"loss": 5.4792,
|
|
"mean_token_accuracy": 0.16281554251909255,
|
|
"num_tokens": 19706127.0,
|
|
"step": 11350
|
|
},
|
|
{
|
|
"entropy": 5.654833698272705,
|
|
"epoch": 0.8834857031705894,
|
|
"grad_norm": 2.265625,
|
|
"learning_rate": 0.0004927195896770804,
|
|
"loss": 5.5351,
|
|
"mean_token_accuracy": 0.15757657885551452,
|
|
"num_tokens": 19715178.0,
|
|
"step": 11355
|
|
},
|
|
{
|
|
"entropy": 5.622646617889404,
|
|
"epoch": 0.883874732542307,
|
|
"grad_norm": 1.9765625,
|
|
"learning_rate": 0.0004927125946977574,
|
|
"loss": 5.4334,
|
|
"mean_token_accuracy": 0.16595035493373872,
|
|
"num_tokens": 19723814.0,
|
|
"step": 11360
|
|
},
|
|
{
|
|
"entropy": 5.69975528717041,
|
|
"epoch": 0.8842637619140246,
|
|
"grad_norm": 2.765625,
|
|
"learning_rate": 0.0004927055964149923,
|
|
"loss": 5.5409,
|
|
"mean_token_accuracy": 0.15971720814704896,
|
|
"num_tokens": 19732153.0,
|
|
"step": 11365
|
|
},
|
|
{
|
|
"entropy": 5.694883060455322,
|
|
"epoch": 0.884652791285742,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.0004926985948288914,
|
|
"loss": 5.4591,
|
|
"mean_token_accuracy": 0.16487395167350768,
|
|
"num_tokens": 19740251.0,
|
|
"step": 11370
|
|
},
|
|
{
|
|
"entropy": 5.5759907245635985,
|
|
"epoch": 0.8850418206574596,
|
|
"grad_norm": 1.921875,
|
|
"learning_rate": 0.0004926915899395608,
|
|
"loss": 5.3748,
|
|
"mean_token_accuracy": 0.1745230033993721,
|
|
"num_tokens": 19748695.0,
|
|
"step": 11375
|
|
},
|
|
{
|
|
"entropy": 5.58020248413086,
|
|
"epoch": 0.8854308500291772,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.0004926845817471068,
|
|
"loss": 5.4062,
|
|
"mean_token_accuracy": 0.1646032765507698,
|
|
"num_tokens": 19757674.0,
|
|
"step": 11380
|
|
},
|
|
{
|
|
"entropy": 5.527360296249389,
|
|
"epoch": 0.8858198794008948,
|
|
"grad_norm": 2.6875,
|
|
"learning_rate": 0.0004926775702516358,
|
|
"loss": 5.2745,
|
|
"mean_token_accuracy": 0.1739967241883278,
|
|
"num_tokens": 19765555.0,
|
|
"step": 11385
|
|
},
|
|
{
|
|
"entropy": 5.5133788108825685,
|
|
"epoch": 0.8862089087726124,
|
|
"grad_norm": 1.9765625,
|
|
"learning_rate": 0.0004926705554532541,
|
|
"loss": 5.4193,
|
|
"mean_token_accuracy": 0.16872652918100356,
|
|
"num_tokens": 19773986.0,
|
|
"step": 11390
|
|
},
|
|
{
|
|
"entropy": 5.593877172470092,
|
|
"epoch": 0.8865979381443299,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.0004926635373520682,
|
|
"loss": 5.4501,
|
|
"mean_token_accuracy": 0.172575543820858,
|
|
"num_tokens": 19782308.0,
|
|
"step": 11395
|
|
},
|
|
{
|
|
"entropy": 5.598495817184448,
|
|
"epoch": 0.8869869675160474,
|
|
"grad_norm": 1.9296875,
|
|
"learning_rate": 0.0004926565159481845,
|
|
"loss": 5.4058,
|
|
"mean_token_accuracy": 0.16553364247083663,
|
|
"num_tokens": 19790447.0,
|
|
"step": 11400
|
|
},
|
|
{
|
|
"entropy": 5.621879386901855,
|
|
"epoch": 0.887375996887765,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004926494912417097,
|
|
"loss": 5.5337,
|
|
"mean_token_accuracy": 0.164414381980896,
|
|
"num_tokens": 19798889.0,
|
|
"step": 11405
|
|
},
|
|
{
|
|
"entropy": 5.621202659606934,
|
|
"epoch": 0.8877650262594826,
|
|
"grad_norm": 2.578125,
|
|
"learning_rate": 0.0004926424632327503,
|
|
"loss": 5.3406,
|
|
"mean_token_accuracy": 0.17174527049064636,
|
|
"num_tokens": 19807192.0,
|
|
"step": 11410
|
|
},
|
|
{
|
|
"entropy": 5.643064641952515,
|
|
"epoch": 0.8881540556312002,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.0004926354319214129,
|
|
"loss": 5.4708,
|
|
"mean_token_accuracy": 0.1634674474596977,
|
|
"num_tokens": 19815864.0,
|
|
"step": 11415
|
|
},
|
|
{
|
|
"entropy": 5.588284969329834,
|
|
"epoch": 0.8885430850029177,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 0.0004926283973078041,
|
|
"loss": 5.3868,
|
|
"mean_token_accuracy": 0.163224695622921,
|
|
"num_tokens": 19823218.0,
|
|
"step": 11420
|
|
},
|
|
{
|
|
"entropy": 5.582258892059326,
|
|
"epoch": 0.8889321143746353,
|
|
"grad_norm": 1.9453125,
|
|
"learning_rate": 0.0004926213593920309,
|
|
"loss": 5.4655,
|
|
"mean_token_accuracy": 0.1646492749452591,
|
|
"num_tokens": 19832098.0,
|
|
"step": 11425
|
|
},
|
|
{
|
|
"entropy": 5.607512092590332,
|
|
"epoch": 0.8893211437463528,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004926143181742,
|
|
"loss": 5.3805,
|
|
"mean_token_accuracy": 0.17268338352441787,
|
|
"num_tokens": 19840180.0,
|
|
"step": 11430
|
|
},
|
|
{
|
|
"entropy": 5.575509977340698,
|
|
"epoch": 0.8897101731180704,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.0004926072736544181,
|
|
"loss": 5.4401,
|
|
"mean_token_accuracy": 0.16741681545972825,
|
|
"num_tokens": 19849016.0,
|
|
"step": 11435
|
|
},
|
|
{
|
|
"entropy": 5.513274097442627,
|
|
"epoch": 0.890099202489788,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.0004926002258327922,
|
|
"loss": 5.3804,
|
|
"mean_token_accuracy": 0.17018379718065263,
|
|
"num_tokens": 19858044.0,
|
|
"step": 11440
|
|
},
|
|
{
|
|
"entropy": 5.51502161026001,
|
|
"epoch": 0.8904882318615055,
|
|
"grad_norm": 2.578125,
|
|
"learning_rate": 0.0004925931747094292,
|
|
"loss": 5.3254,
|
|
"mean_token_accuracy": 0.174643312394619,
|
|
"num_tokens": 19867557.0,
|
|
"step": 11445
|
|
},
|
|
{
|
|
"entropy": 5.59889440536499,
|
|
"epoch": 0.8908772612332231,
|
|
"grad_norm": 1.96875,
|
|
"learning_rate": 0.0004925861202844361,
|
|
"loss": 5.4333,
|
|
"mean_token_accuracy": 0.1621198520064354,
|
|
"num_tokens": 19876009.0,
|
|
"step": 11450
|
|
},
|
|
{
|
|
"entropy": 5.6350596904754635,
|
|
"epoch": 0.8912662906049407,
|
|
"grad_norm": 2.515625,
|
|
"learning_rate": 0.00049257906255792,
|
|
"loss": 5.5237,
|
|
"mean_token_accuracy": 0.1602950230240822,
|
|
"num_tokens": 19885085.0,
|
|
"step": 11455
|
|
},
|
|
{
|
|
"entropy": 5.670140218734741,
|
|
"epoch": 0.8916553199766583,
|
|
"grad_norm": 2.3125,
|
|
"learning_rate": 0.000492572001529988,
|
|
"loss": 5.4511,
|
|
"mean_token_accuracy": 0.16675348877906798,
|
|
"num_tokens": 19893877.0,
|
|
"step": 11460
|
|
},
|
|
{
|
|
"entropy": 5.689091682434082,
|
|
"epoch": 0.8920443493483758,
|
|
"grad_norm": 2.484375,
|
|
"learning_rate": 0.0004925649372007469,
|
|
"loss": 5.5955,
|
|
"mean_token_accuracy": 0.16308746933937074,
|
|
"num_tokens": 19902480.0,
|
|
"step": 11465
|
|
},
|
|
{
|
|
"entropy": 5.593124723434448,
|
|
"epoch": 0.8924333787200933,
|
|
"grad_norm": 2.40625,
|
|
"learning_rate": 0.0004925578695703045,
|
|
"loss": 5.3633,
|
|
"mean_token_accuracy": 0.1698886588215828,
|
|
"num_tokens": 19910981.0,
|
|
"step": 11470
|
|
},
|
|
{
|
|
"entropy": 5.611347770690918,
|
|
"epoch": 0.8928224080918109,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004925507986387676,
|
|
"loss": 5.4698,
|
|
"mean_token_accuracy": 0.16551238745450975,
|
|
"num_tokens": 19920055.0,
|
|
"step": 11475
|
|
},
|
|
{
|
|
"entropy": 5.664920282363892,
|
|
"epoch": 0.8932114374635285,
|
|
"grad_norm": 1.9453125,
|
|
"learning_rate": 0.0004925437244062436,
|
|
"loss": 5.5276,
|
|
"mean_token_accuracy": 0.15842723697423935,
|
|
"num_tokens": 19928010.0,
|
|
"step": 11480
|
|
},
|
|
{
|
|
"entropy": 5.642582702636719,
|
|
"epoch": 0.8936004668352461,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.0004925366468728397,
|
|
"loss": 5.4314,
|
|
"mean_token_accuracy": 0.16325610205531121,
|
|
"num_tokens": 19935992.0,
|
|
"step": 11485
|
|
},
|
|
{
|
|
"entropy": 5.60139307975769,
|
|
"epoch": 0.8939894962069637,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.0004925295660386635,
|
|
"loss": 5.5074,
|
|
"mean_token_accuracy": 0.1630593255162239,
|
|
"num_tokens": 19944522.0,
|
|
"step": 11490
|
|
},
|
|
{
|
|
"entropy": 5.701743412017822,
|
|
"epoch": 0.8943785255786811,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.0004925224819038224,
|
|
"loss": 5.4598,
|
|
"mean_token_accuracy": 0.16489219069480895,
|
|
"num_tokens": 19952991.0,
|
|
"step": 11495
|
|
},
|
|
{
|
|
"entropy": 5.639671421051025,
|
|
"epoch": 0.8947675549503987,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.0004925153944684239,
|
|
"loss": 5.4943,
|
|
"mean_token_accuracy": 0.16422748267650605,
|
|
"num_tokens": 19962301.0,
|
|
"step": 11500
|
|
},
|
|
{
|
|
"entropy": 5.676139163970947,
|
|
"epoch": 0.8951565843221163,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.0004925083037325754,
|
|
"loss": 5.5551,
|
|
"mean_token_accuracy": 0.15274980366230012,
|
|
"num_tokens": 19971159.0,
|
|
"step": 11505
|
|
},
|
|
{
|
|
"entropy": 5.669641304016113,
|
|
"epoch": 0.8955456136938339,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 0.0004925012096963847,
|
|
"loss": 5.4234,
|
|
"mean_token_accuracy": 0.157592710852623,
|
|
"num_tokens": 19979608.0,
|
|
"step": 11510
|
|
},
|
|
{
|
|
"entropy": 5.638739919662475,
|
|
"epoch": 0.8959346430655515,
|
|
"grad_norm": 2.375,
|
|
"learning_rate": 0.0004924941123599593,
|
|
"loss": 5.4343,
|
|
"mean_token_accuracy": 0.16266440898180007,
|
|
"num_tokens": 19988348.0,
|
|
"step": 11515
|
|
},
|
|
{
|
|
"entropy": 5.582215404510498,
|
|
"epoch": 0.896323672437269,
|
|
"grad_norm": 2.875,
|
|
"learning_rate": 0.0004924870117234069,
|
|
"loss": 5.4403,
|
|
"mean_token_accuracy": 0.16273754239082336,
|
|
"num_tokens": 19996970.0,
|
|
"step": 11520
|
|
},
|
|
{
|
|
"entropy": 5.685968732833862,
|
|
"epoch": 0.8967127018089865,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.0004924799077868353,
|
|
"loss": 5.5596,
|
|
"mean_token_accuracy": 0.16202354729175567,
|
|
"num_tokens": 20005297.0,
|
|
"step": 11525
|
|
},
|
|
{
|
|
"entropy": 5.640393209457398,
|
|
"epoch": 0.8971017311807041,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.0004924728005503522,
|
|
"loss": 5.4871,
|
|
"mean_token_accuracy": 0.1575512856245041,
|
|
"num_tokens": 20013971.0,
|
|
"step": 11530
|
|
},
|
|
{
|
|
"entropy": 5.607353067398071,
|
|
"epoch": 0.8974907605524217,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.0004924656900140655,
|
|
"loss": 5.4498,
|
|
"mean_token_accuracy": 0.16247977912425995,
|
|
"num_tokens": 20022536.0,
|
|
"step": 11535
|
|
},
|
|
{
|
|
"entropy": 5.554500102996826,
|
|
"epoch": 0.8978797899241393,
|
|
"grad_norm": 2.5625,
|
|
"learning_rate": 0.0004924585761780831,
|
|
"loss": 5.3735,
|
|
"mean_token_accuracy": 0.16697362065315247,
|
|
"num_tokens": 20031676.0,
|
|
"step": 11540
|
|
},
|
|
{
|
|
"entropy": 5.657486534118652,
|
|
"epoch": 0.8982688192958569,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.000492451459042513,
|
|
"loss": 5.4431,
|
|
"mean_token_accuracy": 0.16532307863235474,
|
|
"num_tokens": 20039783.0,
|
|
"step": 11545
|
|
},
|
|
{
|
|
"entropy": 5.595508861541748,
|
|
"epoch": 0.8986578486675744,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.000492444338607463,
|
|
"loss": 5.4926,
|
|
"mean_token_accuracy": 0.1628775879740715,
|
|
"num_tokens": 20047859.0,
|
|
"step": 11550
|
|
},
|
|
{
|
|
"entropy": 5.67577748298645,
|
|
"epoch": 0.899046878039292,
|
|
"grad_norm": 1.9296875,
|
|
"learning_rate": 0.0004924372148730413,
|
|
"loss": 5.5352,
|
|
"mean_token_accuracy": 0.15492248088121413,
|
|
"num_tokens": 20056711.0,
|
|
"step": 11555
|
|
},
|
|
{
|
|
"entropy": 5.5820619583129885,
|
|
"epoch": 0.8994359074110095,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.000492430087839356,
|
|
"loss": 5.3688,
|
|
"mean_token_accuracy": 0.16599613279104233,
|
|
"num_tokens": 20065715.0,
|
|
"step": 11560
|
|
},
|
|
{
|
|
"entropy": 5.5715466976165775,
|
|
"epoch": 0.8998249367827271,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.0004924229575065152,
|
|
"loss": 5.4553,
|
|
"mean_token_accuracy": 0.16316367983818053,
|
|
"num_tokens": 20073815.0,
|
|
"step": 11565
|
|
},
|
|
{
|
|
"entropy": 5.676203727722168,
|
|
"epoch": 0.9002139661544447,
|
|
"grad_norm": 1.9296875,
|
|
"learning_rate": 0.000492415823874627,
|
|
"loss": 5.466,
|
|
"mean_token_accuracy": 0.16193810403347014,
|
|
"num_tokens": 20082331.0,
|
|
"step": 11570
|
|
},
|
|
{
|
|
"entropy": 5.658157920837402,
|
|
"epoch": 0.9006029955261622,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.0004924086869437998,
|
|
"loss": 5.5338,
|
|
"mean_token_accuracy": 0.16427928656339646,
|
|
"num_tokens": 20091095.0,
|
|
"step": 11575
|
|
},
|
|
{
|
|
"entropy": 5.6368265628814695,
|
|
"epoch": 0.9009920248978798,
|
|
"grad_norm": 2.390625,
|
|
"learning_rate": 0.0004924015467141417,
|
|
"loss": 5.4422,
|
|
"mean_token_accuracy": 0.17044978886842727,
|
|
"num_tokens": 20100111.0,
|
|
"step": 11580
|
|
},
|
|
{
|
|
"entropy": 5.686902809143066,
|
|
"epoch": 0.9013810542695974,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.0004923944031857613,
|
|
"loss": 5.5104,
|
|
"mean_token_accuracy": 0.16596270352602005,
|
|
"num_tokens": 20108542.0,
|
|
"step": 11585
|
|
},
|
|
{
|
|
"entropy": 5.554878664016724,
|
|
"epoch": 0.901770083641315,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004923872563587668,
|
|
"loss": 5.4093,
|
|
"mean_token_accuracy": 0.16970572918653487,
|
|
"num_tokens": 20117831.0,
|
|
"step": 11590
|
|
},
|
|
{
|
|
"entropy": 5.57031283378601,
|
|
"epoch": 0.9021591130130325,
|
|
"grad_norm": 2.96875,
|
|
"learning_rate": 0.0004923801062332666,
|
|
"loss": 5.3822,
|
|
"mean_token_accuracy": 0.16386802196502687,
|
|
"num_tokens": 20127322.0,
|
|
"step": 11595
|
|
},
|
|
{
|
|
"entropy": 5.740408420562744,
|
|
"epoch": 0.90254814238475,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004923729528093694,
|
|
"loss": 5.4592,
|
|
"mean_token_accuracy": 0.16018658578395845,
|
|
"num_tokens": 20135772.0,
|
|
"step": 11600
|
|
},
|
|
{
|
|
"entropy": 5.6419977188110355,
|
|
"epoch": 0.9029371717564676,
|
|
"grad_norm": 3.171875,
|
|
"learning_rate": 0.0004923657960871836,
|
|
"loss": 5.4561,
|
|
"mean_token_accuracy": 0.16688821315765381,
|
|
"num_tokens": 20144110.0,
|
|
"step": 11605
|
|
},
|
|
{
|
|
"entropy": 5.630534076690674,
|
|
"epoch": 0.9033262011281852,
|
|
"grad_norm": 3.46875,
|
|
"learning_rate": 0.0004923586360668178,
|
|
"loss": 5.5595,
|
|
"mean_token_accuracy": 0.158059723675251,
|
|
"num_tokens": 20153391.0,
|
|
"step": 11610
|
|
},
|
|
{
|
|
"entropy": 5.581576490402222,
|
|
"epoch": 0.9037152304999028,
|
|
"grad_norm": 1.953125,
|
|
"learning_rate": 0.0004923514727483807,
|
|
"loss": 5.3789,
|
|
"mean_token_accuracy": 0.1663112536072731,
|
|
"num_tokens": 20161877.0,
|
|
"step": 11615
|
|
},
|
|
{
|
|
"entropy": 5.489307403564453,
|
|
"epoch": 0.9041042598716204,
|
|
"grad_norm": 1.890625,
|
|
"learning_rate": 0.000492344306131981,
|
|
"loss": 5.3495,
|
|
"mean_token_accuracy": 0.16973853409290313,
|
|
"num_tokens": 20169922.0,
|
|
"step": 11620
|
|
},
|
|
{
|
|
"entropy": 5.496005249023438,
|
|
"epoch": 0.9044932892433378,
|
|
"grad_norm": 1.90625,
|
|
"learning_rate": 0.0004923371362177272,
|
|
"loss": 5.3932,
|
|
"mean_token_accuracy": 0.16410769522190094,
|
|
"num_tokens": 20177780.0,
|
|
"step": 11625
|
|
},
|
|
{
|
|
"entropy": 5.605054092407227,
|
|
"epoch": 0.9048823186150554,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.0004923299630057284,
|
|
"loss": 5.3869,
|
|
"mean_token_accuracy": 0.1718130573630333,
|
|
"num_tokens": 20186303.0,
|
|
"step": 11630
|
|
},
|
|
{
|
|
"entropy": 5.576459074020386,
|
|
"epoch": 0.905271347986773,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.0004923227864960934,
|
|
"loss": 5.3735,
|
|
"mean_token_accuracy": 0.17176561951637268,
|
|
"num_tokens": 20194042.0,
|
|
"step": 11635
|
|
},
|
|
{
|
|
"entropy": 5.487547492980957,
|
|
"epoch": 0.9056603773584906,
|
|
"grad_norm": 2.546875,
|
|
"learning_rate": 0.000492315606688931,
|
|
"loss": 5.3734,
|
|
"mean_token_accuracy": 0.17016348242759705,
|
|
"num_tokens": 20202929.0,
|
|
"step": 11640
|
|
},
|
|
{
|
|
"entropy": 5.558788299560547,
|
|
"epoch": 0.9060494067302082,
|
|
"grad_norm": 2.578125,
|
|
"learning_rate": 0.0004923084235843501,
|
|
"loss": 5.4287,
|
|
"mean_token_accuracy": 0.16365135312080384,
|
|
"num_tokens": 20210864.0,
|
|
"step": 11645
|
|
},
|
|
{
|
|
"entropy": 5.677164220809937,
|
|
"epoch": 0.9064384361019256,
|
|
"grad_norm": 2.34375,
|
|
"learning_rate": 0.0004923012371824598,
|
|
"loss": 5.4438,
|
|
"mean_token_accuracy": 0.16505979746580124,
|
|
"num_tokens": 20219390.0,
|
|
"step": 11650
|
|
},
|
|
{
|
|
"entropy": 5.601957941055298,
|
|
"epoch": 0.9068274654736432,
|
|
"grad_norm": 1.984375,
|
|
"learning_rate": 0.000492294047483369,
|
|
"loss": 5.3628,
|
|
"mean_token_accuracy": 0.1755385607481003,
|
|
"num_tokens": 20227241.0,
|
|
"step": 11655
|
|
},
|
|
{
|
|
"entropy": 5.562573099136353,
|
|
"epoch": 0.9072164948453608,
|
|
"grad_norm": 3.28125,
|
|
"learning_rate": 0.0004922868544871869,
|
|
"loss": 5.5422,
|
|
"mean_token_accuracy": 0.16312246322631835,
|
|
"num_tokens": 20236001.0,
|
|
"step": 11660
|
|
},
|
|
{
|
|
"entropy": 5.696888971328735,
|
|
"epoch": 0.9076055242170784,
|
|
"grad_norm": 4.0625,
|
|
"learning_rate": 0.0004922796581940227,
|
|
"loss": 5.4266,
|
|
"mean_token_accuracy": 0.16519952416419983,
|
|
"num_tokens": 20244316.0,
|
|
"step": 11665
|
|
},
|
|
{
|
|
"entropy": 5.594516754150391,
|
|
"epoch": 0.907994553588796,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004922724586039855,
|
|
"loss": 5.3854,
|
|
"mean_token_accuracy": 0.16992224901914596,
|
|
"num_tokens": 20252693.0,
|
|
"step": 11670
|
|
},
|
|
{
|
|
"entropy": 5.558274793624878,
|
|
"epoch": 0.9083835829605135,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.0004922652557171846,
|
|
"loss": 5.4486,
|
|
"mean_token_accuracy": 0.16772947907447816,
|
|
"num_tokens": 20262252.0,
|
|
"step": 11675
|
|
},
|
|
{
|
|
"entropy": 5.565059804916382,
|
|
"epoch": 0.9087726123322311,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004922580495337292,
|
|
"loss": 5.3063,
|
|
"mean_token_accuracy": 0.17319000959396363,
|
|
"num_tokens": 20270755.0,
|
|
"step": 11680
|
|
},
|
|
{
|
|
"entropy": 5.575618696212769,
|
|
"epoch": 0.9091616417039486,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004922508400537288,
|
|
"loss": 5.3731,
|
|
"mean_token_accuracy": 0.16483633816242219,
|
|
"num_tokens": 20278739.0,
|
|
"step": 11685
|
|
},
|
|
{
|
|
"entropy": 5.61230435371399,
|
|
"epoch": 0.9095506710756662,
|
|
"grad_norm": 1.96875,
|
|
"learning_rate": 0.0004922436272772926,
|
|
"loss": 5.5273,
|
|
"mean_token_accuracy": 0.15592199712991714,
|
|
"num_tokens": 20288160.0,
|
|
"step": 11690
|
|
},
|
|
{
|
|
"entropy": 5.5906919002532955,
|
|
"epoch": 0.9099397004473838,
|
|
"grad_norm": 1.9921875,
|
|
"learning_rate": 0.0004922364112045301,
|
|
"loss": 5.465,
|
|
"mean_token_accuracy": 0.1650765970349312,
|
|
"num_tokens": 20296730.0,
|
|
"step": 11695
|
|
},
|
|
{
|
|
"entropy": 5.585020399093628,
|
|
"epoch": 0.9103287298191013,
|
|
"grad_norm": 1.921875,
|
|
"learning_rate": 0.000492229191835551,
|
|
"loss": 5.4151,
|
|
"mean_token_accuracy": 0.16091546416282654,
|
|
"num_tokens": 20305941.0,
|
|
"step": 11700
|
|
},
|
|
{
|
|
"entropy": 5.578007650375366,
|
|
"epoch": 0.9107177591908189,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.0004922219691704645,
|
|
"loss": 5.4271,
|
|
"mean_token_accuracy": 0.1666374608874321,
|
|
"num_tokens": 20314081.0,
|
|
"step": 11705
|
|
},
|
|
{
|
|
"entropy": 5.6462891578674315,
|
|
"epoch": 0.9111067885625365,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 0.0004922147432093805,
|
|
"loss": 5.49,
|
|
"mean_token_accuracy": 0.1564846381545067,
|
|
"num_tokens": 20323004.0,
|
|
"step": 11710
|
|
},
|
|
{
|
|
"entropy": 5.582883739471436,
|
|
"epoch": 0.911495817934254,
|
|
"grad_norm": 2.59375,
|
|
"learning_rate": 0.0004922075139524083,
|
|
"loss": 5.4096,
|
|
"mean_token_accuracy": 0.1619486540555954,
|
|
"num_tokens": 20331122.0,
|
|
"step": 11715
|
|
},
|
|
{
|
|
"entropy": 5.567840480804444,
|
|
"epoch": 0.9118848473059716,
|
|
"grad_norm": 1.890625,
|
|
"learning_rate": 0.000492200281399658,
|
|
"loss": 5.4779,
|
|
"mean_token_accuracy": 0.15915930271148682,
|
|
"num_tokens": 20339602.0,
|
|
"step": 11720
|
|
},
|
|
{
|
|
"entropy": 5.575936031341553,
|
|
"epoch": 0.9122738766776891,
|
|
"grad_norm": 1.921875,
|
|
"learning_rate": 0.000492193045551239,
|
|
"loss": 5.3617,
|
|
"mean_token_accuracy": 0.16848860085010528,
|
|
"num_tokens": 20348431.0,
|
|
"step": 11725
|
|
},
|
|
{
|
|
"entropy": 5.5410106658935545,
|
|
"epoch": 0.9126629060494067,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.0004921858064072612,
|
|
"loss": 5.4015,
|
|
"mean_token_accuracy": 0.1677713766694069,
|
|
"num_tokens": 20357235.0,
|
|
"step": 11730
|
|
},
|
|
{
|
|
"entropy": 5.600786638259888,
|
|
"epoch": 0.9130519354211243,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.0004921785639678347,
|
|
"loss": 5.35,
|
|
"mean_token_accuracy": 0.16323687881231308,
|
|
"num_tokens": 20366169.0,
|
|
"step": 11735
|
|
},
|
|
{
|
|
"entropy": 5.638849496841431,
|
|
"epoch": 0.9134409647928419,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.000492171318233069,
|
|
"loss": 5.4452,
|
|
"mean_token_accuracy": 0.16390205621719361,
|
|
"num_tokens": 20375213.0,
|
|
"step": 11740
|
|
},
|
|
{
|
|
"entropy": 5.565562295913696,
|
|
"epoch": 0.9138299941645595,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.0004921640692030742,
|
|
"loss": 5.419,
|
|
"mean_token_accuracy": 0.16754938066005706,
|
|
"num_tokens": 20383992.0,
|
|
"step": 11745
|
|
},
|
|
{
|
|
"entropy": 5.608250141143799,
|
|
"epoch": 0.914219023536277,
|
|
"grad_norm": 1.984375,
|
|
"learning_rate": 0.0004921568168779603,
|
|
"loss": 5.4042,
|
|
"mean_token_accuracy": 0.17085883766412735,
|
|
"num_tokens": 20392318.0,
|
|
"step": 11750
|
|
},
|
|
{
|
|
"entropy": 5.6887932300567625,
|
|
"epoch": 0.9146080529079945,
|
|
"grad_norm": 2.578125,
|
|
"learning_rate": 0.0004921495612578374,
|
|
"loss": 5.5388,
|
|
"mean_token_accuracy": 0.16315759122371673,
|
|
"num_tokens": 20401556.0,
|
|
"step": 11755
|
|
},
|
|
{
|
|
"entropy": 5.563545751571655,
|
|
"epoch": 0.9149970822797121,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.0004921423023428156,
|
|
"loss": 5.4188,
|
|
"mean_token_accuracy": 0.16635851413011551,
|
|
"num_tokens": 20410480.0,
|
|
"step": 11760
|
|
},
|
|
{
|
|
"entropy": 5.557062005996704,
|
|
"epoch": 0.9153861116514297,
|
|
"grad_norm": 2.671875,
|
|
"learning_rate": 0.0004921350401330049,
|
|
"loss": 5.3864,
|
|
"mean_token_accuracy": 0.16722941100597383,
|
|
"num_tokens": 20419748.0,
|
|
"step": 11765
|
|
},
|
|
{
|
|
"entropy": 5.635919666290283,
|
|
"epoch": 0.9157751410231473,
|
|
"grad_norm": 2.734375,
|
|
"learning_rate": 0.0004921277746285155,
|
|
"loss": 5.4406,
|
|
"mean_token_accuracy": 0.15854950845241547,
|
|
"num_tokens": 20429552.0,
|
|
"step": 11770
|
|
},
|
|
{
|
|
"entropy": 5.682742309570313,
|
|
"epoch": 0.9161641703948649,
|
|
"grad_norm": 1.9453125,
|
|
"learning_rate": 0.0004921205058294579,
|
|
"loss": 5.5056,
|
|
"mean_token_accuracy": 0.15398671627044677,
|
|
"num_tokens": 20438476.0,
|
|
"step": 11775
|
|
},
|
|
{
|
|
"entropy": 5.555865526199341,
|
|
"epoch": 0.9165531997665823,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.000492113233735942,
|
|
"loss": 5.3045,
|
|
"mean_token_accuracy": 0.16874464899301528,
|
|
"num_tokens": 20447035.0,
|
|
"step": 11780
|
|
},
|
|
{
|
|
"entropy": 5.616372776031494,
|
|
"epoch": 0.9169422291382999,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.0004921059583480785,
|
|
"loss": 5.464,
|
|
"mean_token_accuracy": 0.1669568568468094,
|
|
"num_tokens": 20456200.0,
|
|
"step": 11785
|
|
},
|
|
{
|
|
"entropy": 5.619090795516968,
|
|
"epoch": 0.9173312585100175,
|
|
"grad_norm": 2.578125,
|
|
"learning_rate": 0.0004920986796659775,
|
|
"loss": 5.4753,
|
|
"mean_token_accuracy": 0.16653817147016525,
|
|
"num_tokens": 20465444.0,
|
|
"step": 11790
|
|
},
|
|
{
|
|
"entropy": 5.598866939544678,
|
|
"epoch": 0.9177202878817351,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.0004920913976897498,
|
|
"loss": 5.3326,
|
|
"mean_token_accuracy": 0.16743399500846862,
|
|
"num_tokens": 20473851.0,
|
|
"step": 11795
|
|
},
|
|
{
|
|
"entropy": 5.608018636703491,
|
|
"epoch": 0.9181093172534527,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.0004920841124195055,
|
|
"loss": 5.457,
|
|
"mean_token_accuracy": 0.16556763350963594,
|
|
"num_tokens": 20482232.0,
|
|
"step": 11800
|
|
},
|
|
{
|
|
"entropy": 5.500268888473511,
|
|
"epoch": 0.9184983466251702,
|
|
"grad_norm": 1.8515625,
|
|
"learning_rate": 0.0004920768238553554,
|
|
"loss": 5.3191,
|
|
"mean_token_accuracy": 0.1796584516763687,
|
|
"num_tokens": 20490498.0,
|
|
"step": 11805
|
|
},
|
|
{
|
|
"entropy": 5.523838233947754,
|
|
"epoch": 0.9188873759968877,
|
|
"grad_norm": 3.125,
|
|
"learning_rate": 0.0004920695319974099,
|
|
"loss": 5.4127,
|
|
"mean_token_accuracy": 0.1660748988389969,
|
|
"num_tokens": 20499125.0,
|
|
"step": 11810
|
|
},
|
|
{
|
|
"entropy": 5.626104831695557,
|
|
"epoch": 0.9192764053686053,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.0004920622368457798,
|
|
"loss": 5.5684,
|
|
"mean_token_accuracy": 0.15675143748521805,
|
|
"num_tokens": 20507665.0,
|
|
"step": 11815
|
|
},
|
|
{
|
|
"entropy": 5.67587366104126,
|
|
"epoch": 0.9196654347403229,
|
|
"grad_norm": 3.84375,
|
|
"learning_rate": 0.0004920549384005759,
|
|
"loss": 5.4808,
|
|
"mean_token_accuracy": 0.1667581468820572,
|
|
"num_tokens": 20516509.0,
|
|
"step": 11820
|
|
},
|
|
{
|
|
"entropy": 5.650551843643188,
|
|
"epoch": 0.9200544641120405,
|
|
"grad_norm": 1.84375,
|
|
"learning_rate": 0.0004920476366619086,
|
|
"loss": 5.514,
|
|
"mean_token_accuracy": 0.16333641037344931,
|
|
"num_tokens": 20524830.0,
|
|
"step": 11825
|
|
},
|
|
{
|
|
"entropy": 5.605641031265259,
|
|
"epoch": 0.920443493483758,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.000492040331629889,
|
|
"loss": 5.407,
|
|
"mean_token_accuracy": 0.16556126922369002,
|
|
"num_tokens": 20533746.0,
|
|
"step": 11830
|
|
},
|
|
{
|
|
"entropy": 5.547481727600098,
|
|
"epoch": 0.9208325228554756,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004920330233046277,
|
|
"loss": 5.3536,
|
|
"mean_token_accuracy": 0.17004832178354262,
|
|
"num_tokens": 20542350.0,
|
|
"step": 11835
|
|
},
|
|
{
|
|
"entropy": 5.602860975265503,
|
|
"epoch": 0.9212215522271932,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.0004920257116862359,
|
|
"loss": 5.5246,
|
|
"mean_token_accuracy": 0.16358970403671264,
|
|
"num_tokens": 20551670.0,
|
|
"step": 11840
|
|
},
|
|
{
|
|
"entropy": 5.5952003479003904,
|
|
"epoch": 0.9216105815989107,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.0004920183967748241,
|
|
"loss": 5.4417,
|
|
"mean_token_accuracy": 0.1622401922941208,
|
|
"num_tokens": 20560692.0,
|
|
"step": 11845
|
|
},
|
|
{
|
|
"entropy": 5.629176044464112,
|
|
"epoch": 0.9219996109706283,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.0004920110785705037,
|
|
"loss": 5.3992,
|
|
"mean_token_accuracy": 0.16306326985359193,
|
|
"num_tokens": 20569262.0,
|
|
"step": 11850
|
|
},
|
|
{
|
|
"entropy": 5.5652570724487305,
|
|
"epoch": 0.9223886403423458,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.0004920037570733857,
|
|
"loss": 5.4038,
|
|
"mean_token_accuracy": 0.1673546627163887,
|
|
"num_tokens": 20577850.0,
|
|
"step": 11855
|
|
},
|
|
{
|
|
"entropy": 5.577003145217896,
|
|
"epoch": 0.9227776697140634,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004919964322835809,
|
|
"loss": 5.4829,
|
|
"mean_token_accuracy": 0.15511251389980316,
|
|
"num_tokens": 20587021.0,
|
|
"step": 11860
|
|
},
|
|
{
|
|
"entropy": 5.613102197647095,
|
|
"epoch": 0.923166699085781,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004919891042012006,
|
|
"loss": 5.4249,
|
|
"mean_token_accuracy": 0.16336755454540253,
|
|
"num_tokens": 20594631.0,
|
|
"step": 11865
|
|
},
|
|
{
|
|
"entropy": 5.523421144485473,
|
|
"epoch": 0.9235557284574986,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004919817728263562,
|
|
"loss": 5.3592,
|
|
"mean_token_accuracy": 0.16631494462490082,
|
|
"num_tokens": 20602765.0,
|
|
"step": 11870
|
|
},
|
|
{
|
|
"entropy": 5.603576755523681,
|
|
"epoch": 0.9239447578292161,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.0004919744381591586,
|
|
"loss": 5.4732,
|
|
"mean_token_accuracy": 0.17236589789390563,
|
|
"num_tokens": 20611350.0,
|
|
"step": 11875
|
|
},
|
|
{
|
|
"entropy": 5.587359189987183,
|
|
"epoch": 0.9243337872009336,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.0004919671001997193,
|
|
"loss": 5.3993,
|
|
"mean_token_accuracy": 0.16717078387737275,
|
|
"num_tokens": 20620201.0,
|
|
"step": 11880
|
|
},
|
|
{
|
|
"entropy": 5.634953165054322,
|
|
"epoch": 0.9247228165726512,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004919597589481497,
|
|
"loss": 5.4495,
|
|
"mean_token_accuracy": 0.16752370595932006,
|
|
"num_tokens": 20627870.0,
|
|
"step": 11885
|
|
},
|
|
{
|
|
"entropy": 5.564960527420044,
|
|
"epoch": 0.9251118459443688,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.000491952414404561,
|
|
"loss": 5.426,
|
|
"mean_token_accuracy": 0.16260659098625183,
|
|
"num_tokens": 20635894.0,
|
|
"step": 11890
|
|
},
|
|
{
|
|
"entropy": 5.66273250579834,
|
|
"epoch": 0.9255008753160864,
|
|
"grad_norm": 2.53125,
|
|
"learning_rate": 0.0004919450665690646,
|
|
"loss": 5.5047,
|
|
"mean_token_accuracy": 0.16478935033082961,
|
|
"num_tokens": 20644091.0,
|
|
"step": 11895
|
|
},
|
|
{
|
|
"entropy": 5.6283807277679445,
|
|
"epoch": 0.925889904687804,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.0004919377154417724,
|
|
"loss": 5.3468,
|
|
"mean_token_accuracy": 0.17177147269248963,
|
|
"num_tokens": 20651994.0,
|
|
"step": 11900
|
|
},
|
|
{
|
|
"entropy": 5.538891887664795,
|
|
"epoch": 0.9262789340595214,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.0004919303610227954,
|
|
"loss": 5.383,
|
|
"mean_token_accuracy": 0.17125571966171266,
|
|
"num_tokens": 20660192.0,
|
|
"step": 11905
|
|
},
|
|
{
|
|
"entropy": 5.6591273784637455,
|
|
"epoch": 0.926667963431239,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.0004919230033122457,
|
|
"loss": 5.4382,
|
|
"mean_token_accuracy": 0.16060300618410112,
|
|
"num_tokens": 20668275.0,
|
|
"step": 11910
|
|
},
|
|
{
|
|
"entropy": 5.573952722549438,
|
|
"epoch": 0.9270569928029566,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.0004919156423102345,
|
|
"loss": 5.4237,
|
|
"mean_token_accuracy": 0.16882454752922058,
|
|
"num_tokens": 20676936.0,
|
|
"step": 11915
|
|
},
|
|
{
|
|
"entropy": 5.65876030921936,
|
|
"epoch": 0.9274460221746742,
|
|
"grad_norm": 1.9453125,
|
|
"learning_rate": 0.0004919082780168736,
|
|
"loss": 5.5334,
|
|
"mean_token_accuracy": 0.16089269518852234,
|
|
"num_tokens": 20685600.0,
|
|
"step": 11920
|
|
},
|
|
{
|
|
"entropy": 5.625549364089966,
|
|
"epoch": 0.9278350515463918,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004919009104322751,
|
|
"loss": 5.4548,
|
|
"mean_token_accuracy": 0.16796746999025344,
|
|
"num_tokens": 20693714.0,
|
|
"step": 11925
|
|
},
|
|
{
|
|
"entropy": 5.56932225227356,
|
|
"epoch": 0.9282240809181093,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.0004918935395565503,
|
|
"loss": 5.4313,
|
|
"mean_token_accuracy": 0.16442747861146928,
|
|
"num_tokens": 20702529.0,
|
|
"step": 11930
|
|
},
|
|
{
|
|
"entropy": 5.610908031463623,
|
|
"epoch": 0.9286131102898268,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.0004918861653898113,
|
|
"loss": 5.3713,
|
|
"mean_token_accuracy": 0.16198727935552598,
|
|
"num_tokens": 20711775.0,
|
|
"step": 11935
|
|
},
|
|
{
|
|
"entropy": 5.628123378753662,
|
|
"epoch": 0.9290021396615444,
|
|
"grad_norm": 3.1875,
|
|
"learning_rate": 0.0004918787879321701,
|
|
"loss": 5.4188,
|
|
"mean_token_accuracy": 0.16877151727676393,
|
|
"num_tokens": 20720653.0,
|
|
"step": 11940
|
|
},
|
|
{
|
|
"entropy": 5.554147148132325,
|
|
"epoch": 0.929391169033262,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004918714071837384,
|
|
"loss": 5.4434,
|
|
"mean_token_accuracy": 0.16346981525421142,
|
|
"num_tokens": 20729208.0,
|
|
"step": 11945
|
|
},
|
|
{
|
|
"entropy": 5.641031074523926,
|
|
"epoch": 0.9297801984049796,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0004918640231446282,
|
|
"loss": 5.4941,
|
|
"mean_token_accuracy": 0.16509802788496017,
|
|
"num_tokens": 20738670.0,
|
|
"step": 11950
|
|
},
|
|
{
|
|
"entropy": 5.633650302886963,
|
|
"epoch": 0.9301692277766972,
|
|
"grad_norm": 1.90625,
|
|
"learning_rate": 0.0004918566358149517,
|
|
"loss": 5.5364,
|
|
"mean_token_accuracy": 0.15772674456238747,
|
|
"num_tokens": 20748315.0,
|
|
"step": 11955
|
|
},
|
|
{
|
|
"entropy": 5.618883371353149,
|
|
"epoch": 0.9305582571484147,
|
|
"grad_norm": 1.9140625,
|
|
"learning_rate": 0.000491849245194821,
|
|
"loss": 5.6063,
|
|
"mean_token_accuracy": 0.15980128794908524,
|
|
"num_tokens": 20757623.0,
|
|
"step": 11960
|
|
},
|
|
{
|
|
"entropy": 5.646411752700805,
|
|
"epoch": 0.9309472865201323,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.0004918418512843479,
|
|
"loss": 5.4361,
|
|
"mean_token_accuracy": 0.16582998633384705,
|
|
"num_tokens": 20765817.0,
|
|
"step": 11965
|
|
},
|
|
{
|
|
"entropy": 5.583756732940674,
|
|
"epoch": 0.9313363158918498,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004918344540836451,
|
|
"loss": 5.3098,
|
|
"mean_token_accuracy": 0.17631375789642334,
|
|
"num_tokens": 20773931.0,
|
|
"step": 11970
|
|
},
|
|
{
|
|
"entropy": 5.642791986465454,
|
|
"epoch": 0.9317253452635674,
|
|
"grad_norm": 2.359375,
|
|
"learning_rate": 0.0004918270535928244,
|
|
"loss": 5.4425,
|
|
"mean_token_accuracy": 0.16102655082941056,
|
|
"num_tokens": 20782652.0,
|
|
"step": 11975
|
|
},
|
|
{
|
|
"entropy": 5.527781343460083,
|
|
"epoch": 0.932114374635285,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.0004918196498119984,
|
|
"loss": 5.3575,
|
|
"mean_token_accuracy": 0.17098654806613922,
|
|
"num_tokens": 20791293.0,
|
|
"step": 11980
|
|
},
|
|
{
|
|
"entropy": 5.5788249492645265,
|
|
"epoch": 0.9325034040070025,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.0004918122427412793,
|
|
"loss": 5.4714,
|
|
"mean_token_accuracy": 0.16024997979402542,
|
|
"num_tokens": 20800317.0,
|
|
"step": 11985
|
|
},
|
|
{
|
|
"entropy": 5.609372615814209,
|
|
"epoch": 0.9328924333787201,
|
|
"grad_norm": 2.890625,
|
|
"learning_rate": 0.0004918048323807795,
|
|
"loss": 5.4495,
|
|
"mean_token_accuracy": 0.16463207453489304,
|
|
"num_tokens": 20809231.0,
|
|
"step": 11990
|
|
},
|
|
{
|
|
"entropy": 5.60000958442688,
|
|
"epoch": 0.9332814627504377,
|
|
"grad_norm": 2.390625,
|
|
"learning_rate": 0.0004917974187306114,
|
|
"loss": 5.3595,
|
|
"mean_token_accuracy": 0.16376359164714813,
|
|
"num_tokens": 20818327.0,
|
|
"step": 11995
|
|
},
|
|
{
|
|
"entropy": 5.668776655197144,
|
|
"epoch": 0.9336704921221552,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.0004917900017908875,
|
|
"loss": 5.5225,
|
|
"mean_token_accuracy": 0.1555524706840515,
|
|
"num_tokens": 20826995.0,
|
|
"step": 12000
|
|
},
|
|
{
|
|
"epoch": 0.9336704921221552,
|
|
"eval_entropy": 5.4913999491407965,
|
|
"eval_loss": 5.485260963439941,
|
|
"eval_mean_token_accuracy": 0.1705613749913864,
|
|
"eval_num_tokens": 20826995.0,
|
|
"eval_runtime": 28.5437,
|
|
"eval_samples_per_second": 1455.942,
|
|
"eval_steps_per_second": 182.001,
|
|
"step": 12000
|
|
},
|
|
{
|
|
"entropy": 5.529295158386231,
|
|
"epoch": 0.9340595214938728,
|
|
"grad_norm": 2.703125,
|
|
"learning_rate": 0.0004917825815617205,
|
|
"loss": 5.2417,
|
|
"mean_token_accuracy": 0.17508028149604798,
|
|
"num_tokens": 20835641.0,
|
|
"step": 12005
|
|
},
|
|
{
|
|
"entropy": 5.599151659011841,
|
|
"epoch": 0.9344485508655903,
|
|
"grad_norm": 2.40625,
|
|
"learning_rate": 0.0004917751580432229,
|
|
"loss": 5.3842,
|
|
"mean_token_accuracy": 0.1658439815044403,
|
|
"num_tokens": 20844728.0,
|
|
"step": 12010
|
|
},
|
|
{
|
|
"entropy": 5.543066215515137,
|
|
"epoch": 0.9348375802373079,
|
|
"grad_norm": 1.921875,
|
|
"learning_rate": 0.0004917677312355072,
|
|
"loss": 5.3608,
|
|
"mean_token_accuracy": 0.16970049142837523,
|
|
"num_tokens": 20853013.0,
|
|
"step": 12015
|
|
},
|
|
{
|
|
"entropy": 5.6628947257995605,
|
|
"epoch": 0.9352266096090255,
|
|
"grad_norm": 1.8984375,
|
|
"learning_rate": 0.0004917603011386863,
|
|
"loss": 5.4439,
|
|
"mean_token_accuracy": 0.15975013226270676,
|
|
"num_tokens": 20861592.0,
|
|
"step": 12020
|
|
},
|
|
{
|
|
"entropy": 5.5719037532806395,
|
|
"epoch": 0.9356156389807431,
|
|
"grad_norm": 2.265625,
|
|
"learning_rate": 0.0004917528677528727,
|
|
"loss": 5.4027,
|
|
"mean_token_accuracy": 0.1634494721889496,
|
|
"num_tokens": 20869645.0,
|
|
"step": 12025
|
|
},
|
|
{
|
|
"entropy": 5.565957975387573,
|
|
"epoch": 0.9360046683524607,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.0004917454310781795,
|
|
"loss": 5.4394,
|
|
"mean_token_accuracy": 0.1640925794839859,
|
|
"num_tokens": 20878154.0,
|
|
"step": 12030
|
|
},
|
|
{
|
|
"entropy": 5.584660530090332,
|
|
"epoch": 0.9363936977241781,
|
|
"grad_norm": 2.28125,
|
|
"learning_rate": 0.0004917379911147193,
|
|
"loss": 5.3983,
|
|
"mean_token_accuracy": 0.17574554234743117,
|
|
"num_tokens": 20886260.0,
|
|
"step": 12035
|
|
},
|
|
{
|
|
"entropy": 5.623343467712402,
|
|
"epoch": 0.9367827270958957,
|
|
"grad_norm": 2.5,
|
|
"learning_rate": 0.0004917305478626049,
|
|
"loss": 5.3501,
|
|
"mean_token_accuracy": 0.16753097549080848,
|
|
"num_tokens": 20895688.0,
|
|
"step": 12040
|
|
},
|
|
{
|
|
"entropy": 5.575954341888428,
|
|
"epoch": 0.9371717564676133,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.0004917231013219495,
|
|
"loss": 5.4827,
|
|
"mean_token_accuracy": 0.1613457351922989,
|
|
"num_tokens": 20903904.0,
|
|
"step": 12045
|
|
},
|
|
{
|
|
"entropy": 5.61733341217041,
|
|
"epoch": 0.9375607858393309,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.000491715651492866,
|
|
"loss": 5.4577,
|
|
"mean_token_accuracy": 0.16116144359111786,
|
|
"num_tokens": 20913411.0,
|
|
"step": 12050
|
|
},
|
|
{
|
|
"entropy": 5.634273815155029,
|
|
"epoch": 0.9379498152110485,
|
|
"grad_norm": 2.359375,
|
|
"learning_rate": 0.0004917081983754675,
|
|
"loss": 5.4383,
|
|
"mean_token_accuracy": 0.15884150564670563,
|
|
"num_tokens": 20922088.0,
|
|
"step": 12055
|
|
},
|
|
{
|
|
"entropy": 5.488911962509155,
|
|
"epoch": 0.938338844582766,
|
|
"grad_norm": 2.625,
|
|
"learning_rate": 0.0004917007419698669,
|
|
"loss": 5.4141,
|
|
"mean_token_accuracy": 0.16428075581789017,
|
|
"num_tokens": 20930879.0,
|
|
"step": 12060
|
|
},
|
|
{
|
|
"entropy": 5.53802261352539,
|
|
"epoch": 0.9387278739544835,
|
|
"grad_norm": 1.8984375,
|
|
"learning_rate": 0.0004916932822761776,
|
|
"loss": 5.375,
|
|
"mean_token_accuracy": 0.166110660135746,
|
|
"num_tokens": 20939092.0,
|
|
"step": 12065
|
|
},
|
|
{
|
|
"entropy": 5.588111495971679,
|
|
"epoch": 0.9391169033262011,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0004916858192945126,
|
|
"loss": 5.4461,
|
|
"mean_token_accuracy": 0.16670889407396317,
|
|
"num_tokens": 20947599.0,
|
|
"step": 12070
|
|
},
|
|
{
|
|
"entropy": 5.697923851013184,
|
|
"epoch": 0.9395059326979187,
|
|
"grad_norm": 1.90625,
|
|
"learning_rate": 0.0004916783530249852,
|
|
"loss": 5.4884,
|
|
"mean_token_accuracy": 0.16140548139810562,
|
|
"num_tokens": 20955725.0,
|
|
"step": 12075
|
|
},
|
|
{
|
|
"entropy": 5.567690372467041,
|
|
"epoch": 0.9398949620696363,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 0.0004916708834677086,
|
|
"loss": 5.3254,
|
|
"mean_token_accuracy": 0.16997745633125305,
|
|
"num_tokens": 20965040.0,
|
|
"step": 12080
|
|
},
|
|
{
|
|
"entropy": 5.596985912322998,
|
|
"epoch": 0.9402839914413538,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.0004916634106227962,
|
|
"loss": 5.4827,
|
|
"mean_token_accuracy": 0.15716896802186966,
|
|
"num_tokens": 20974204.0,
|
|
"step": 12085
|
|
},
|
|
{
|
|
"entropy": 5.712417125701904,
|
|
"epoch": 0.9406730208130714,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.0004916559344903614,
|
|
"loss": 5.4418,
|
|
"mean_token_accuracy": 0.16644417345523835,
|
|
"num_tokens": 20982109.0,
|
|
"step": 12090
|
|
},
|
|
{
|
|
"entropy": 5.601548051834106,
|
|
"epoch": 0.941062050184789,
|
|
"grad_norm": 1.953125,
|
|
"learning_rate": 0.0004916484550705176,
|
|
"loss": 5.4764,
|
|
"mean_token_accuracy": 0.15794880390167237,
|
|
"num_tokens": 20990375.0,
|
|
"step": 12095
|
|
},
|
|
{
|
|
"entropy": 5.527898836135864,
|
|
"epoch": 0.9414510795565065,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.0004916409723633785,
|
|
"loss": 5.4833,
|
|
"mean_token_accuracy": 0.16283233910799028,
|
|
"num_tokens": 20998535.0,
|
|
"step": 12100
|
|
},
|
|
{
|
|
"entropy": 5.52505259513855,
|
|
"epoch": 0.9418401089282241,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.0004916334863690573,
|
|
"loss": 5.3334,
|
|
"mean_token_accuracy": 0.1683484844863415,
|
|
"num_tokens": 21006597.0,
|
|
"step": 12105
|
|
},
|
|
{
|
|
"entropy": 5.615225219726563,
|
|
"epoch": 0.9422291382999416,
|
|
"grad_norm": 1.84375,
|
|
"learning_rate": 0.0004916259970876678,
|
|
"loss": 5.4204,
|
|
"mean_token_accuracy": 0.1711857497692108,
|
|
"num_tokens": 21015498.0,
|
|
"step": 12110
|
|
},
|
|
{
|
|
"entropy": 5.680117511749268,
|
|
"epoch": 0.9426181676716592,
|
|
"grad_norm": 1.921875,
|
|
"learning_rate": 0.0004916185045193237,
|
|
"loss": 5.4438,
|
|
"mean_token_accuracy": 0.16099658459424973,
|
|
"num_tokens": 21024090.0,
|
|
"step": 12115
|
|
},
|
|
{
|
|
"entropy": 5.638439083099366,
|
|
"epoch": 0.9430071970433768,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.0004916110086641384,
|
|
"loss": 5.4773,
|
|
"mean_token_accuracy": 0.15922530591487885,
|
|
"num_tokens": 21032928.0,
|
|
"step": 12120
|
|
},
|
|
{
|
|
"entropy": 5.600735664367676,
|
|
"epoch": 0.9433962264150944,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.0004916035095222259,
|
|
"loss": 5.5222,
|
|
"mean_token_accuracy": 0.16178220361471177,
|
|
"num_tokens": 21041467.0,
|
|
"step": 12125
|
|
},
|
|
{
|
|
"entropy": 5.6023845195770265,
|
|
"epoch": 0.9437852557868119,
|
|
"grad_norm": 1.9765625,
|
|
"learning_rate": 0.0004915960070936999,
|
|
"loss": 5.4444,
|
|
"mean_token_accuracy": 0.17256748974323272,
|
|
"num_tokens": 21049325.0,
|
|
"step": 12130
|
|
},
|
|
{
|
|
"entropy": 5.641587257385254,
|
|
"epoch": 0.9441742851585294,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.0004915885013786742,
|
|
"loss": 5.5015,
|
|
"mean_token_accuracy": 0.16282495856285095,
|
|
"num_tokens": 21057911.0,
|
|
"step": 12135
|
|
},
|
|
{
|
|
"entropy": 5.68573408126831,
|
|
"epoch": 0.944563314530247,
|
|
"grad_norm": 2.359375,
|
|
"learning_rate": 0.0004915809923772628,
|
|
"loss": 5.5009,
|
|
"mean_token_accuracy": 0.1549901157617569,
|
|
"num_tokens": 21066974.0,
|
|
"step": 12140
|
|
},
|
|
{
|
|
"entropy": 5.6227216720581055,
|
|
"epoch": 0.9449523439019646,
|
|
"grad_norm": 1.9609375,
|
|
"learning_rate": 0.0004915734800895796,
|
|
"loss": 5.4197,
|
|
"mean_token_accuracy": 0.16332541704177855,
|
|
"num_tokens": 21075591.0,
|
|
"step": 12145
|
|
},
|
|
{
|
|
"entropy": 5.624902963638306,
|
|
"epoch": 0.9453413732736822,
|
|
"grad_norm": 2.328125,
|
|
"learning_rate": 0.0004915659645157383,
|
|
"loss": 5.4835,
|
|
"mean_token_accuracy": 0.16144971996545793,
|
|
"num_tokens": 21084496.0,
|
|
"step": 12150
|
|
},
|
|
{
|
|
"entropy": 5.619552516937256,
|
|
"epoch": 0.9457304026453998,
|
|
"grad_norm": 2.734375,
|
|
"learning_rate": 0.0004915584456558535,
|
|
"loss": 5.372,
|
|
"mean_token_accuracy": 0.16533171832561494,
|
|
"num_tokens": 21092811.0,
|
|
"step": 12155
|
|
},
|
|
{
|
|
"entropy": 5.628385257720947,
|
|
"epoch": 0.9461194320171173,
|
|
"grad_norm": 1.9453125,
|
|
"learning_rate": 0.0004915509235100388,
|
|
"loss": 5.4174,
|
|
"mean_token_accuracy": 0.16735924631357194,
|
|
"num_tokens": 21101449.0,
|
|
"step": 12160
|
|
},
|
|
{
|
|
"entropy": 5.709081172943115,
|
|
"epoch": 0.9465084613888348,
|
|
"grad_norm": 1.984375,
|
|
"learning_rate": 0.0004915433980784086,
|
|
"loss": 5.5349,
|
|
"mean_token_accuracy": 0.1557691439986229,
|
|
"num_tokens": 21109476.0,
|
|
"step": 12165
|
|
},
|
|
{
|
|
"entropy": 5.630402994155884,
|
|
"epoch": 0.9468974907605524,
|
|
"grad_norm": 3.046875,
|
|
"learning_rate": 0.0004915358693610769,
|
|
"loss": 5.4453,
|
|
"mean_token_accuracy": 0.1661228820681572,
|
|
"num_tokens": 21118431.0,
|
|
"step": 12170
|
|
},
|
|
{
|
|
"entropy": 5.59259352684021,
|
|
"epoch": 0.94728652013227,
|
|
"grad_norm": 1.984375,
|
|
"learning_rate": 0.0004915283373581581,
|
|
"loss": 5.4004,
|
|
"mean_token_accuracy": 0.16927942782640457,
|
|
"num_tokens": 21127390.0,
|
|
"step": 12175
|
|
},
|
|
{
|
|
"entropy": 5.69592547416687,
|
|
"epoch": 0.9476755495039876,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.0004915208020697664,
|
|
"loss": 5.5211,
|
|
"mean_token_accuracy": 0.1614257037639618,
|
|
"num_tokens": 21136323.0,
|
|
"step": 12180
|
|
},
|
|
{
|
|
"entropy": 5.622841548919678,
|
|
"epoch": 0.9480645788757052,
|
|
"grad_norm": 1.921875,
|
|
"learning_rate": 0.0004915132634960162,
|
|
"loss": 5.4542,
|
|
"mean_token_accuracy": 0.16568393111228943,
|
|
"num_tokens": 21145228.0,
|
|
"step": 12185
|
|
},
|
|
{
|
|
"entropy": 5.654486227035522,
|
|
"epoch": 0.9484536082474226,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004915057216370218,
|
|
"loss": 5.3462,
|
|
"mean_token_accuracy": 0.1716327577829361,
|
|
"num_tokens": 21153288.0,
|
|
"step": 12190
|
|
},
|
|
{
|
|
"entropy": 5.609825944900512,
|
|
"epoch": 0.9488426376191402,
|
|
"grad_norm": 2.34375,
|
|
"learning_rate": 0.0004914981764928977,
|
|
"loss": 5.4054,
|
|
"mean_token_accuracy": 0.1715080589056015,
|
|
"num_tokens": 21161802.0,
|
|
"step": 12195
|
|
},
|
|
{
|
|
"entropy": 5.514717531204224,
|
|
"epoch": 0.9492316669908578,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004914906280637584,
|
|
"loss": 5.3513,
|
|
"mean_token_accuracy": 0.17415064573287964,
|
|
"num_tokens": 21170018.0,
|
|
"step": 12200
|
|
},
|
|
{
|
|
"entropy": 5.656940078735351,
|
|
"epoch": 0.9496206963625754,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.0004914830763497183,
|
|
"loss": 5.5551,
|
|
"mean_token_accuracy": 0.15528118014335632,
|
|
"num_tokens": 21179128.0,
|
|
"step": 12205
|
|
},
|
|
{
|
|
"entropy": 5.731035947799683,
|
|
"epoch": 0.950009725734293,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.0004914755213508922,
|
|
"loss": 5.3863,
|
|
"mean_token_accuracy": 0.16710515320301056,
|
|
"num_tokens": 21188138.0,
|
|
"step": 12210
|
|
},
|
|
{
|
|
"entropy": 5.655791234970093,
|
|
"epoch": 0.9503987551060105,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.0004914679630673945,
|
|
"loss": 5.4597,
|
|
"mean_token_accuracy": 0.16265584975481034,
|
|
"num_tokens": 21196465.0,
|
|
"step": 12215
|
|
},
|
|
{
|
|
"entropy": 5.548721027374268,
|
|
"epoch": 0.950787784477728,
|
|
"grad_norm": 2.359375,
|
|
"learning_rate": 0.0004914604014993401,
|
|
"loss": 5.3835,
|
|
"mean_token_accuracy": 0.16774536520242692,
|
|
"num_tokens": 21205309.0,
|
|
"step": 12220
|
|
},
|
|
{
|
|
"entropy": 5.58810830116272,
|
|
"epoch": 0.9511768138494456,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 0.0004914528366468436,
|
|
"loss": 5.3319,
|
|
"mean_token_accuracy": 0.17688675373792648,
|
|
"num_tokens": 21214216.0,
|
|
"step": 12225
|
|
},
|
|
{
|
|
"entropy": 5.589582109451294,
|
|
"epoch": 0.9515658432211632,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004914452685100199,
|
|
"loss": 5.3684,
|
|
"mean_token_accuracy": 0.1670580878853798,
|
|
"num_tokens": 21222246.0,
|
|
"step": 12230
|
|
},
|
|
{
|
|
"entropy": 5.601297807693482,
|
|
"epoch": 0.9519548725928808,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004914376970889836,
|
|
"loss": 5.4241,
|
|
"mean_token_accuracy": 0.16404641568660736,
|
|
"num_tokens": 21230696.0,
|
|
"step": 12235
|
|
},
|
|
{
|
|
"entropy": 5.627651071548462,
|
|
"epoch": 0.9523439019645983,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004914301223838497,
|
|
"loss": 5.5362,
|
|
"mean_token_accuracy": 0.1631936624646187,
|
|
"num_tokens": 21239909.0,
|
|
"step": 12240
|
|
},
|
|
{
|
|
"entropy": 5.604155874252319,
|
|
"epoch": 0.9527329313363159,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.0004914225443947334,
|
|
"loss": 5.3964,
|
|
"mean_token_accuracy": 0.1640986144542694,
|
|
"num_tokens": 21248124.0,
|
|
"step": 12245
|
|
},
|
|
{
|
|
"entropy": 5.756840944290161,
|
|
"epoch": 0.9531219607080335,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0004914149631217494,
|
|
"loss": 5.5876,
|
|
"mean_token_accuracy": 0.15205297023057937,
|
|
"num_tokens": 21257042.0,
|
|
"step": 12250
|
|
},
|
|
{
|
|
"entropy": 5.731447315216064,
|
|
"epoch": 0.953510990079751,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0004914073785650127,
|
|
"loss": 5.5167,
|
|
"mean_token_accuracy": 0.16341665685176848,
|
|
"num_tokens": 21265627.0,
|
|
"step": 12255
|
|
},
|
|
{
|
|
"entropy": 5.629907417297363,
|
|
"epoch": 0.9539000194514686,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.0004913997907246385,
|
|
"loss": 5.4332,
|
|
"mean_token_accuracy": 0.1615334078669548,
|
|
"num_tokens": 21273688.0,
|
|
"step": 12260
|
|
},
|
|
{
|
|
"entropy": 5.565264081954956,
|
|
"epoch": 0.9542890488231861,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.000491392199600742,
|
|
"loss": 5.4054,
|
|
"mean_token_accuracy": 0.1678546741604805,
|
|
"num_tokens": 21283432.0,
|
|
"step": 12265
|
|
},
|
|
{
|
|
"entropy": 5.65198769569397,
|
|
"epoch": 0.9546780781949037,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004913846051934382,
|
|
"loss": 5.4648,
|
|
"mean_token_accuracy": 0.1631398856639862,
|
|
"num_tokens": 21292003.0,
|
|
"step": 12270
|
|
},
|
|
{
|
|
"entropy": 5.61608657836914,
|
|
"epoch": 0.9550671075666213,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.0004913770075028425,
|
|
"loss": 5.3638,
|
|
"mean_token_accuracy": 0.17072062641382219,
|
|
"num_tokens": 21299914.0,
|
|
"step": 12275
|
|
},
|
|
{
|
|
"entropy": 5.6000275135040285,
|
|
"epoch": 0.9554561369383389,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.0004913694065290701,
|
|
"loss": 5.5554,
|
|
"mean_token_accuracy": 0.15840027183294297,
|
|
"num_tokens": 21309398.0,
|
|
"step": 12280
|
|
},
|
|
{
|
|
"entropy": 5.63468337059021,
|
|
"epoch": 0.9558451663100564,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.0004913618022722363,
|
|
"loss": 5.4154,
|
|
"mean_token_accuracy": 0.16588005274534226,
|
|
"num_tokens": 21317828.0,
|
|
"step": 12285
|
|
},
|
|
{
|
|
"entropy": 5.683631801605225,
|
|
"epoch": 0.9562341956817739,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.0004913541947324566,
|
|
"loss": 5.5267,
|
|
"mean_token_accuracy": 0.1623057469725609,
|
|
"num_tokens": 21326266.0,
|
|
"step": 12290
|
|
},
|
|
{
|
|
"entropy": 5.6774848937988285,
|
|
"epoch": 0.9566232250534915,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.0004913465839098463,
|
|
"loss": 5.4456,
|
|
"mean_token_accuracy": 0.16179952025413513,
|
|
"num_tokens": 21335476.0,
|
|
"step": 12295
|
|
},
|
|
{
|
|
"entropy": 5.663231611251831,
|
|
"epoch": 0.9570122544252091,
|
|
"grad_norm": 1.9921875,
|
|
"learning_rate": 0.0004913389698045209,
|
|
"loss": 5.3903,
|
|
"mean_token_accuracy": 0.1663038745522499,
|
|
"num_tokens": 21344045.0,
|
|
"step": 12300
|
|
},
|
|
{
|
|
"entropy": 5.597242975234986,
|
|
"epoch": 0.9574012837969267,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.000491331352416596,
|
|
"loss": 5.4203,
|
|
"mean_token_accuracy": 0.1614898830652237,
|
|
"num_tokens": 21352309.0,
|
|
"step": 12305
|
|
},
|
|
{
|
|
"entropy": 5.5800012111663815,
|
|
"epoch": 0.9577903131686443,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004913237317461872,
|
|
"loss": 5.4607,
|
|
"mean_token_accuracy": 0.16515436619520188,
|
|
"num_tokens": 21362164.0,
|
|
"step": 12310
|
|
},
|
|
{
|
|
"entropy": 5.71044602394104,
|
|
"epoch": 0.9581793425403617,
|
|
"grad_norm": 1.84375,
|
|
"learning_rate": 0.00049131610779341,
|
|
"loss": 5.4481,
|
|
"mean_token_accuracy": 0.16084448918700217,
|
|
"num_tokens": 21372817.0,
|
|
"step": 12315
|
|
},
|
|
{
|
|
"entropy": 5.612222385406494,
|
|
"epoch": 0.9585683719120793,
|
|
"grad_norm": 1.9140625,
|
|
"learning_rate": 0.0004913084805583803,
|
|
"loss": 5.4193,
|
|
"mean_token_accuracy": 0.16439441442489625,
|
|
"num_tokens": 21381035.0,
|
|
"step": 12320
|
|
},
|
|
{
|
|
"entropy": 5.540774536132813,
|
|
"epoch": 0.9589574012837969,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004913008500412136,
|
|
"loss": 5.378,
|
|
"mean_token_accuracy": 0.1764953002333641,
|
|
"num_tokens": 21390074.0,
|
|
"step": 12325
|
|
},
|
|
{
|
|
"entropy": 5.605381107330322,
|
|
"epoch": 0.9593464306555145,
|
|
"grad_norm": 2.3125,
|
|
"learning_rate": 0.0004912932162420259,
|
|
"loss": 5.4443,
|
|
"mean_token_accuracy": 0.16384571492671968,
|
|
"num_tokens": 21398726.0,
|
|
"step": 12330
|
|
},
|
|
{
|
|
"entropy": 5.640875720977784,
|
|
"epoch": 0.9597354600272321,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.0004912855791609327,
|
|
"loss": 5.4085,
|
|
"mean_token_accuracy": 0.16411788314580916,
|
|
"num_tokens": 21407225.0,
|
|
"step": 12335
|
|
},
|
|
{
|
|
"entropy": 5.544402694702148,
|
|
"epoch": 0.9601244893989496,
|
|
"grad_norm": 2.703125,
|
|
"learning_rate": 0.0004912779387980502,
|
|
"loss": 5.4216,
|
|
"mean_token_accuracy": 0.15945865511894225,
|
|
"num_tokens": 21416746.0,
|
|
"step": 12340
|
|
},
|
|
{
|
|
"entropy": 5.639695692062378,
|
|
"epoch": 0.9605135187706672,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004912702951534942,
|
|
"loss": 5.4987,
|
|
"mean_token_accuracy": 0.15481483340263366,
|
|
"num_tokens": 21425621.0,
|
|
"step": 12345
|
|
},
|
|
{
|
|
"entropy": 5.6458429336547855,
|
|
"epoch": 0.9609025481423847,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 0.0004912626482273809,
|
|
"loss": 5.3679,
|
|
"mean_token_accuracy": 0.1741405114531517,
|
|
"num_tokens": 21433674.0,
|
|
"step": 12350
|
|
},
|
|
{
|
|
"entropy": 5.626150321960449,
|
|
"epoch": 0.9612915775141023,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.0004912549980198258,
|
|
"loss": 5.4697,
|
|
"mean_token_accuracy": 0.16437991559505463,
|
|
"num_tokens": 21442285.0,
|
|
"step": 12355
|
|
},
|
|
{
|
|
"entropy": 5.635745000839234,
|
|
"epoch": 0.9616806068858199,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.0004912473445309455,
|
|
"loss": 5.4404,
|
|
"mean_token_accuracy": 0.16701813340187072,
|
|
"num_tokens": 21450345.0,
|
|
"step": 12360
|
|
},
|
|
{
|
|
"entropy": 5.4874303340911865,
|
|
"epoch": 0.9620696362575375,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.000491239687760856,
|
|
"loss": 5.3173,
|
|
"mean_token_accuracy": 0.17735288441181182,
|
|
"num_tokens": 21458618.0,
|
|
"step": 12365
|
|
},
|
|
{
|
|
"entropy": 5.51342453956604,
|
|
"epoch": 0.962458665629255,
|
|
"grad_norm": 1.9609375,
|
|
"learning_rate": 0.0004912320277096732,
|
|
"loss": 5.3645,
|
|
"mean_token_accuracy": 0.1659383311867714,
|
|
"num_tokens": 21467410.0,
|
|
"step": 12370
|
|
},
|
|
{
|
|
"entropy": 5.548876953125,
|
|
"epoch": 0.9628476950009726,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004912243643775137,
|
|
"loss": 5.4233,
|
|
"mean_token_accuracy": 0.16114128828048707,
|
|
"num_tokens": 21475454.0,
|
|
"step": 12375
|
|
},
|
|
{
|
|
"entropy": 5.60258150100708,
|
|
"epoch": 0.9632367243726901,
|
|
"grad_norm": 1.8984375,
|
|
"learning_rate": 0.0004912166977644936,
|
|
"loss": 5.3563,
|
|
"mean_token_accuracy": 0.1722332775592804,
|
|
"num_tokens": 21483431.0,
|
|
"step": 12380
|
|
},
|
|
{
|
|
"entropy": 5.618895530700684,
|
|
"epoch": 0.9636257537444077,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004912090278707293,
|
|
"loss": 5.4138,
|
|
"mean_token_accuracy": 0.16790021508932113,
|
|
"num_tokens": 21491199.0,
|
|
"step": 12385
|
|
},
|
|
{
|
|
"entropy": 5.585316181182861,
|
|
"epoch": 0.9640147831161253,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.000491201354696337,
|
|
"loss": 5.4987,
|
|
"mean_token_accuracy": 0.15913947969675063,
|
|
"num_tokens": 21500339.0,
|
|
"step": 12390
|
|
},
|
|
{
|
|
"entropy": 5.613671493530274,
|
|
"epoch": 0.9644038124878428,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.0004911936782414334,
|
|
"loss": 5.4435,
|
|
"mean_token_accuracy": 0.16230569928884506,
|
|
"num_tokens": 21508945.0,
|
|
"step": 12395
|
|
},
|
|
{
|
|
"entropy": 5.662711572647095,
|
|
"epoch": 0.9647928418595604,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.0004911859985061348,
|
|
"loss": 5.4159,
|
|
"mean_token_accuracy": 0.16538402438163757,
|
|
"num_tokens": 21517649.0,
|
|
"step": 12400
|
|
},
|
|
{
|
|
"entropy": 5.642771244049072,
|
|
"epoch": 0.965181871231278,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.0004911783154905577,
|
|
"loss": 5.4267,
|
|
"mean_token_accuracy": 0.16018734574317933,
|
|
"num_tokens": 21526650.0,
|
|
"step": 12405
|
|
},
|
|
{
|
|
"entropy": 5.606813907623291,
|
|
"epoch": 0.9655709006029956,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.0004911706291948188,
|
|
"loss": 5.4398,
|
|
"mean_token_accuracy": 0.1638248771429062,
|
|
"num_tokens": 21535401.0,
|
|
"step": 12410
|
|
},
|
|
{
|
|
"entropy": 5.625056362152099,
|
|
"epoch": 0.9659599299747131,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.0004911629396190348,
|
|
"loss": 5.4509,
|
|
"mean_token_accuracy": 0.16487383097410202,
|
|
"num_tokens": 21543973.0,
|
|
"step": 12415
|
|
},
|
|
{
|
|
"entropy": 5.579789876937866,
|
|
"epoch": 0.9663489593464306,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.0004911552467633221,
|
|
"loss": 5.3935,
|
|
"mean_token_accuracy": 0.16671295762062072,
|
|
"num_tokens": 21552875.0,
|
|
"step": 12420
|
|
},
|
|
{
|
|
"entropy": 5.545711803436279,
|
|
"epoch": 0.9667379887181482,
|
|
"grad_norm": 1.984375,
|
|
"learning_rate": 0.0004911475506277976,
|
|
"loss": 5.3201,
|
|
"mean_token_accuracy": 0.1696278229355812,
|
|
"num_tokens": 21561469.0,
|
|
"step": 12425
|
|
},
|
|
{
|
|
"entropy": 5.620049619674683,
|
|
"epoch": 0.9671270180898658,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.000491139851212578,
|
|
"loss": 5.4108,
|
|
"mean_token_accuracy": 0.17355171889066695,
|
|
"num_tokens": 21569523.0,
|
|
"step": 12430
|
|
},
|
|
{
|
|
"entropy": 5.582766008377075,
|
|
"epoch": 0.9675160474615834,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004911321485177802,
|
|
"loss": 5.3544,
|
|
"mean_token_accuracy": 0.16908264458179473,
|
|
"num_tokens": 21577700.0,
|
|
"step": 12435
|
|
},
|
|
{
|
|
"entropy": 5.646632528305053,
|
|
"epoch": 0.967905076833301,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.0004911244425435212,
|
|
"loss": 5.4236,
|
|
"mean_token_accuracy": 0.16666791290044786,
|
|
"num_tokens": 21586233.0,
|
|
"step": 12440
|
|
},
|
|
{
|
|
"entropy": 5.613484811782837,
|
|
"epoch": 0.9682941062050184,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.0004911167332899176,
|
|
"loss": 5.4592,
|
|
"mean_token_accuracy": 0.1648248016834259,
|
|
"num_tokens": 21595330.0,
|
|
"step": 12445
|
|
},
|
|
{
|
|
"entropy": 5.554804420471191,
|
|
"epoch": 0.968683135576736,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.0004911090207570867,
|
|
"loss": 5.383,
|
|
"mean_token_accuracy": 0.17037907540798186,
|
|
"num_tokens": 21604522.0,
|
|
"step": 12450
|
|
},
|
|
{
|
|
"entropy": 5.637841463088989,
|
|
"epoch": 0.9690721649484536,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004911013049451453,
|
|
"loss": 5.3676,
|
|
"mean_token_accuracy": 0.16388257890939711,
|
|
"num_tokens": 21613599.0,
|
|
"step": 12455
|
|
},
|
|
{
|
|
"entropy": 5.6220635890960695,
|
|
"epoch": 0.9694611943201712,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.0004910935858542106,
|
|
"loss": 5.4347,
|
|
"mean_token_accuracy": 0.16195111870765685,
|
|
"num_tokens": 21622587.0,
|
|
"step": 12460
|
|
},
|
|
{
|
|
"entropy": 5.600628089904785,
|
|
"epoch": 0.9698502236918888,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.0004910858634843997,
|
|
"loss": 5.4262,
|
|
"mean_token_accuracy": 0.163477124273777,
|
|
"num_tokens": 21630782.0,
|
|
"step": 12465
|
|
},
|
|
{
|
|
"entropy": 5.623278522491455,
|
|
"epoch": 0.9702392530636063,
|
|
"grad_norm": 6.4375,
|
|
"learning_rate": 0.0004910781378358297,
|
|
"loss": 5.3348,
|
|
"mean_token_accuracy": 0.17372669875621796,
|
|
"num_tokens": 21639354.0,
|
|
"step": 12470
|
|
},
|
|
{
|
|
"entropy": 5.515239810943603,
|
|
"epoch": 0.9706282824353238,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.0004910704089086178,
|
|
"loss": 5.4802,
|
|
"mean_token_accuracy": 0.15698706358671188,
|
|
"num_tokens": 21648292.0,
|
|
"step": 12475
|
|
},
|
|
{
|
|
"entropy": 5.625759315490723,
|
|
"epoch": 0.9710173118070414,
|
|
"grad_norm": 1.9375,
|
|
"learning_rate": 0.0004910626767028815,
|
|
"loss": 5.4259,
|
|
"mean_token_accuracy": 0.16549592167139054,
|
|
"num_tokens": 21657382.0,
|
|
"step": 12480
|
|
},
|
|
{
|
|
"entropy": 5.673313283920288,
|
|
"epoch": 0.971406341178759,
|
|
"grad_norm": 1.875,
|
|
"learning_rate": 0.0004910549412187379,
|
|
"loss": 5.4142,
|
|
"mean_token_accuracy": 0.16160742193460464,
|
|
"num_tokens": 21666327.0,
|
|
"step": 12485
|
|
},
|
|
{
|
|
"entropy": 5.641364479064942,
|
|
"epoch": 0.9717953705504766,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.0004910472024563045,
|
|
"loss": 5.4517,
|
|
"mean_token_accuracy": 0.168923020362854,
|
|
"num_tokens": 21674882.0,
|
|
"step": 12490
|
|
},
|
|
{
|
|
"entropy": 5.732049512863159,
|
|
"epoch": 0.9721843999221941,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.0004910394604156987,
|
|
"loss": 5.5288,
|
|
"mean_token_accuracy": 0.15408443957567214,
|
|
"num_tokens": 21683255.0,
|
|
"step": 12495
|
|
},
|
|
{
|
|
"entropy": 5.663116836547852,
|
|
"epoch": 0.9725734292939117,
|
|
"grad_norm": 4.34375,
|
|
"learning_rate": 0.0004910317150970379,
|
|
"loss": 5.4011,
|
|
"mean_token_accuracy": 0.16347605586051941,
|
|
"num_tokens": 21692274.0,
|
|
"step": 12500
|
|
},
|
|
{
|
|
"entropy": 5.528823280334473,
|
|
"epoch": 0.9729624586656292,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.0004910239665004397,
|
|
"loss": 5.3159,
|
|
"mean_token_accuracy": 0.17649521678686142,
|
|
"num_tokens": 21700767.0,
|
|
"step": 12505
|
|
},
|
|
{
|
|
"entropy": 5.587145090103149,
|
|
"epoch": 0.9733514880373468,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.0004910162146260216,
|
|
"loss": 5.4841,
|
|
"mean_token_accuracy": 0.16269294321537017,
|
|
"num_tokens": 21709430.0,
|
|
"step": 12510
|
|
},
|
|
{
|
|
"entropy": 5.5482102394104,
|
|
"epoch": 0.9737405174090644,
|
|
"grad_norm": 2.328125,
|
|
"learning_rate": 0.0004910084594739013,
|
|
"loss": 5.3604,
|
|
"mean_token_accuracy": 0.1677957758307457,
|
|
"num_tokens": 21717978.0,
|
|
"step": 12515
|
|
},
|
|
{
|
|
"entropy": 5.472861433029175,
|
|
"epoch": 0.9741295467807819,
|
|
"grad_norm": 1.9453125,
|
|
"learning_rate": 0.0004910007010441964,
|
|
"loss": 5.2476,
|
|
"mean_token_accuracy": 0.17790153324604036,
|
|
"num_tokens": 21726608.0,
|
|
"step": 12520
|
|
},
|
|
{
|
|
"entropy": 5.564755535125732,
|
|
"epoch": 0.9745185761524995,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004909929393370248,
|
|
"loss": 5.4168,
|
|
"mean_token_accuracy": 0.16508375257253646,
|
|
"num_tokens": 21735402.0,
|
|
"step": 12525
|
|
},
|
|
{
|
|
"entropy": 5.5967389106750485,
|
|
"epoch": 0.9749076055242171,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004909851743525041,
|
|
"loss": 5.4079,
|
|
"mean_token_accuracy": 0.16675586253404617,
|
|
"num_tokens": 21744620.0,
|
|
"step": 12530
|
|
},
|
|
{
|
|
"entropy": 5.643410158157349,
|
|
"epoch": 0.9752966348959347,
|
|
"grad_norm": 1.9765625,
|
|
"learning_rate": 0.000490977406090752,
|
|
"loss": 5.4389,
|
|
"mean_token_accuracy": 0.16459746807813644,
|
|
"num_tokens": 21753270.0,
|
|
"step": 12535
|
|
},
|
|
{
|
|
"entropy": 5.6979015350341795,
|
|
"epoch": 0.9756856642676522,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.0004909696345518867,
|
|
"loss": 5.4597,
|
|
"mean_token_accuracy": 0.1638670802116394,
|
|
"num_tokens": 21761477.0,
|
|
"step": 12540
|
|
},
|
|
{
|
|
"entropy": 5.488833284378051,
|
|
"epoch": 0.9760746936393697,
|
|
"grad_norm": 1.9375,
|
|
"learning_rate": 0.0004909618597360258,
|
|
"loss": 5.3876,
|
|
"mean_token_accuracy": 0.16794765889644622,
|
|
"num_tokens": 21769925.0,
|
|
"step": 12545
|
|
},
|
|
{
|
|
"entropy": 5.589802694320679,
|
|
"epoch": 0.9764637230110873,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.0004909540816432876,
|
|
"loss": 5.4586,
|
|
"mean_token_accuracy": 0.16755053251981736,
|
|
"num_tokens": 21778850.0,
|
|
"step": 12550
|
|
},
|
|
{
|
|
"entropy": 5.659890937805176,
|
|
"epoch": 0.9768527523828049,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004909463002737897,
|
|
"loss": 5.4901,
|
|
"mean_token_accuracy": 0.16207392811775206,
|
|
"num_tokens": 21787408.0,
|
|
"step": 12555
|
|
},
|
|
{
|
|
"entropy": 5.651714420318603,
|
|
"epoch": 0.9772417817545225,
|
|
"grad_norm": 1.96875,
|
|
"learning_rate": 0.0004909385156276506,
|
|
"loss": 5.4394,
|
|
"mean_token_accuracy": 0.17184505462646485,
|
|
"num_tokens": 21795967.0,
|
|
"step": 12560
|
|
},
|
|
{
|
|
"entropy": 5.5746184349060055,
|
|
"epoch": 0.9776308111262401,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004909307277049881,
|
|
"loss": 5.4039,
|
|
"mean_token_accuracy": 0.1665019005537033,
|
|
"num_tokens": 21804472.0,
|
|
"step": 12565
|
|
},
|
|
{
|
|
"entropy": 5.524310827255249,
|
|
"epoch": 0.9780198404979576,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0004909229365059205,
|
|
"loss": 5.3895,
|
|
"mean_token_accuracy": 0.16160913705825805,
|
|
"num_tokens": 21813233.0,
|
|
"step": 12570
|
|
},
|
|
{
|
|
"entropy": 5.5600556373596195,
|
|
"epoch": 0.9784088698696751,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.0004909151420305661,
|
|
"loss": 5.2734,
|
|
"mean_token_accuracy": 0.1807188332080841,
|
|
"num_tokens": 21821413.0,
|
|
"step": 12575
|
|
},
|
|
{
|
|
"entropy": 5.6009989261627195,
|
|
"epoch": 0.9787978992413927,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.000490907344279043,
|
|
"loss": 5.3592,
|
|
"mean_token_accuracy": 0.16747906506061555,
|
|
"num_tokens": 21829222.0,
|
|
"step": 12580
|
|
},
|
|
{
|
|
"entropy": 5.556995248794555,
|
|
"epoch": 0.9791869286131103,
|
|
"grad_norm": 1.8515625,
|
|
"learning_rate": 0.0004908995432514698,
|
|
"loss": 5.3936,
|
|
"mean_token_accuracy": 0.16868300586938859,
|
|
"num_tokens": 21837033.0,
|
|
"step": 12585
|
|
},
|
|
{
|
|
"entropy": 5.659626770019531,
|
|
"epoch": 0.9795759579848279,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.0004908917389479645,
|
|
"loss": 5.4417,
|
|
"mean_token_accuracy": 0.16005606353282928,
|
|
"num_tokens": 21845464.0,
|
|
"step": 12590
|
|
},
|
|
{
|
|
"entropy": 5.554674673080444,
|
|
"epoch": 0.9799649873565455,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.0004908839313686456,
|
|
"loss": 5.3859,
|
|
"mean_token_accuracy": 0.1710491105914116,
|
|
"num_tokens": 21853497.0,
|
|
"step": 12595
|
|
},
|
|
{
|
|
"entropy": 5.617833805084229,
|
|
"epoch": 0.980354016728263,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004908761205136319,
|
|
"loss": 5.4596,
|
|
"mean_token_accuracy": 0.16379410475492479,
|
|
"num_tokens": 21861710.0,
|
|
"step": 12600
|
|
},
|
|
{
|
|
"entropy": 5.675917625427246,
|
|
"epoch": 0.9807430460999805,
|
|
"grad_norm": 4.21875,
|
|
"learning_rate": 0.0004908683063830414,
|
|
"loss": 5.4149,
|
|
"mean_token_accuracy": 0.15332768559455873,
|
|
"num_tokens": 21870472.0,
|
|
"step": 12605
|
|
},
|
|
{
|
|
"entropy": 5.717903757095337,
|
|
"epoch": 0.9811320754716981,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.0004908604889769932,
|
|
"loss": 5.4764,
|
|
"mean_token_accuracy": 0.16210412681102754,
|
|
"num_tokens": 21878287.0,
|
|
"step": 12610
|
|
},
|
|
{
|
|
"entropy": 5.664337491989135,
|
|
"epoch": 0.9815211048434157,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.0004908526682956054,
|
|
"loss": 5.5211,
|
|
"mean_token_accuracy": 0.16029609590768815,
|
|
"num_tokens": 21887587.0,
|
|
"step": 12615
|
|
},
|
|
{
|
|
"entropy": 5.570968341827393,
|
|
"epoch": 0.9819101342151333,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.0004908448443389972,
|
|
"loss": 5.3451,
|
|
"mean_token_accuracy": 0.17372812628746032,
|
|
"num_tokens": 21895923.0,
|
|
"step": 12620
|
|
},
|
|
{
|
|
"entropy": 5.650736665725708,
|
|
"epoch": 0.9822991635868508,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.0004908370171072869,
|
|
"loss": 5.3986,
|
|
"mean_token_accuracy": 0.17044544070959092,
|
|
"num_tokens": 21904439.0,
|
|
"step": 12625
|
|
},
|
|
{
|
|
"entropy": 5.590007638931274,
|
|
"epoch": 0.9826881929585684,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.0004908291866005933,
|
|
"loss": 5.3393,
|
|
"mean_token_accuracy": 0.16950118988752366,
|
|
"num_tokens": 21912473.0,
|
|
"step": 12630
|
|
},
|
|
{
|
|
"entropy": 5.512787914276123,
|
|
"epoch": 0.9830772223302859,
|
|
"grad_norm": 1.9609375,
|
|
"learning_rate": 0.0004908213528190355,
|
|
"loss": 5.4296,
|
|
"mean_token_accuracy": 0.1646110311150551,
|
|
"num_tokens": 21921631.0,
|
|
"step": 12635
|
|
},
|
|
{
|
|
"entropy": 5.502424716949463,
|
|
"epoch": 0.9834662517020035,
|
|
"grad_norm": 3.796875,
|
|
"learning_rate": 0.0004908135157627321,
|
|
"loss": 5.3509,
|
|
"mean_token_accuracy": 0.1730327144265175,
|
|
"num_tokens": 21929984.0,
|
|
"step": 12640
|
|
},
|
|
{
|
|
"entropy": 5.532140064239502,
|
|
"epoch": 0.9838552810737211,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0004908056754318022,
|
|
"loss": 5.2736,
|
|
"mean_token_accuracy": 0.1692282125353813,
|
|
"num_tokens": 21937349.0,
|
|
"step": 12645
|
|
},
|
|
{
|
|
"entropy": 5.572642087936401,
|
|
"epoch": 0.9842443104454386,
|
|
"grad_norm": 1.890625,
|
|
"learning_rate": 0.0004907978318263646,
|
|
"loss": 5.4201,
|
|
"mean_token_accuracy": 0.1677776038646698,
|
|
"num_tokens": 21946176.0,
|
|
"step": 12650
|
|
},
|
|
{
|
|
"entropy": 5.591643333435059,
|
|
"epoch": 0.9846333398171562,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004907899849465383,
|
|
"loss": 5.3923,
|
|
"mean_token_accuracy": 0.17154815793037415,
|
|
"num_tokens": 21954645.0,
|
|
"step": 12655
|
|
},
|
|
{
|
|
"entropy": 5.57898473739624,
|
|
"epoch": 0.9850223691888738,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004907821347924424,
|
|
"loss": 5.4434,
|
|
"mean_token_accuracy": 0.16054333746433258,
|
|
"num_tokens": 21963290.0,
|
|
"step": 12660
|
|
},
|
|
{
|
|
"entropy": 5.625823020935059,
|
|
"epoch": 0.9854113985605913,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.0004907742813641963,
|
|
"loss": 5.426,
|
|
"mean_token_accuracy": 0.16523936837911607,
|
|
"num_tokens": 21971005.0,
|
|
"step": 12665
|
|
},
|
|
{
|
|
"entropy": 5.576694345474243,
|
|
"epoch": 0.9858004279323089,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.0004907664246619187,
|
|
"loss": 5.3671,
|
|
"mean_token_accuracy": 0.17177429795265198,
|
|
"num_tokens": 21980067.0,
|
|
"step": 12670
|
|
},
|
|
{
|
|
"entropy": 5.565968465805054,
|
|
"epoch": 0.9861894573040264,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.0004907585646857293,
|
|
"loss": 5.383,
|
|
"mean_token_accuracy": 0.1695752337574959,
|
|
"num_tokens": 21988511.0,
|
|
"step": 12675
|
|
},
|
|
{
|
|
"entropy": 5.557537603378296,
|
|
"epoch": 0.986578486675744,
|
|
"grad_norm": 1.9765625,
|
|
"learning_rate": 0.0004907507014357467,
|
|
"loss": 5.3828,
|
|
"mean_token_accuracy": 0.1675651490688324,
|
|
"num_tokens": 21997074.0,
|
|
"step": 12680
|
|
},
|
|
{
|
|
"entropy": 5.648717880249023,
|
|
"epoch": 0.9869675160474616,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.0004907428349120909,
|
|
"loss": 5.5022,
|
|
"mean_token_accuracy": 0.16320418566465378,
|
|
"num_tokens": 22005412.0,
|
|
"step": 12685
|
|
},
|
|
{
|
|
"entropy": 5.615092658996582,
|
|
"epoch": 0.9873565454191792,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.0004907349651148809,
|
|
"loss": 5.3162,
|
|
"mean_token_accuracy": 0.17057496309280396,
|
|
"num_tokens": 22013588.0,
|
|
"step": 12690
|
|
},
|
|
{
|
|
"entropy": 5.560420131683349,
|
|
"epoch": 0.9877455747908968,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.0004907270920442361,
|
|
"loss": 5.4403,
|
|
"mean_token_accuracy": 0.1682940125465393,
|
|
"num_tokens": 22021669.0,
|
|
"step": 12695
|
|
},
|
|
{
|
|
"entropy": 5.5455451011657715,
|
|
"epoch": 0.9881346041626142,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.0004907192157002762,
|
|
"loss": 5.3142,
|
|
"mean_token_accuracy": 0.17333479225635529,
|
|
"num_tokens": 22030295.0,
|
|
"step": 12700
|
|
},
|
|
{
|
|
"entropy": 5.649390649795532,
|
|
"epoch": 0.9885236335343318,
|
|
"grad_norm": 1.8984375,
|
|
"learning_rate": 0.0004907113360831204,
|
|
"loss": 5.4785,
|
|
"mean_token_accuracy": 0.16038983911275864,
|
|
"num_tokens": 22038924.0,
|
|
"step": 12705
|
|
},
|
|
{
|
|
"entropy": 5.594985103607177,
|
|
"epoch": 0.9889126629060494,
|
|
"grad_norm": 1.84375,
|
|
"learning_rate": 0.0004907034531928886,
|
|
"loss": 5.3784,
|
|
"mean_token_accuracy": 0.17309531569480896,
|
|
"num_tokens": 22047586.0,
|
|
"step": 12710
|
|
},
|
|
{
|
|
"entropy": 5.504135227203369,
|
|
"epoch": 0.989301692277767,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004906955670297001,
|
|
"loss": 5.365,
|
|
"mean_token_accuracy": 0.16617025732994078,
|
|
"num_tokens": 22055695.0,
|
|
"step": 12715
|
|
},
|
|
{
|
|
"entropy": 5.632635307312012,
|
|
"epoch": 0.9896907216494846,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.0004906876775936746,
|
|
"loss": 5.5245,
|
|
"mean_token_accuracy": 0.16032247766852378,
|
|
"num_tokens": 22064472.0,
|
|
"step": 12720
|
|
},
|
|
{
|
|
"entropy": 5.681120586395264,
|
|
"epoch": 0.990079751021202,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004906797848849321,
|
|
"loss": 5.4497,
|
|
"mean_token_accuracy": 0.16262938529253007,
|
|
"num_tokens": 22072726.0,
|
|
"step": 12725
|
|
},
|
|
{
|
|
"entropy": 5.611200857162475,
|
|
"epoch": 0.9904687803929196,
|
|
"grad_norm": 2.234375,
|
|
"learning_rate": 0.000490671888903592,
|
|
"loss": 5.3341,
|
|
"mean_token_accuracy": 0.17683761864900588,
|
|
"num_tokens": 22081074.0,
|
|
"step": 12730
|
|
},
|
|
{
|
|
"entropy": 5.456222724914551,
|
|
"epoch": 0.9908578097646372,
|
|
"grad_norm": 1.984375,
|
|
"learning_rate": 0.0004906639896497744,
|
|
"loss": 5.3364,
|
|
"mean_token_accuracy": 0.17494695633649826,
|
|
"num_tokens": 22089924.0,
|
|
"step": 12735
|
|
},
|
|
{
|
|
"entropy": 5.599759244918824,
|
|
"epoch": 0.9912468391363548,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004906560871235988,
|
|
"loss": 5.3402,
|
|
"mean_token_accuracy": 0.16935001611709594,
|
|
"num_tokens": 22099088.0,
|
|
"step": 12740
|
|
},
|
|
{
|
|
"entropy": 5.7038367748260494,
|
|
"epoch": 0.9916358685080724,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004906481813251854,
|
|
"loss": 5.5212,
|
|
"mean_token_accuracy": 0.16124668270349501,
|
|
"num_tokens": 22108344.0,
|
|
"step": 12745
|
|
},
|
|
{
|
|
"entropy": 5.607229709625244,
|
|
"epoch": 0.9920248978797899,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004906402722546542,
|
|
"loss": 5.4036,
|
|
"mean_token_accuracy": 0.16377143561840057,
|
|
"num_tokens": 22116476.0,
|
|
"step": 12750
|
|
},
|
|
{
|
|
"entropy": 5.600761032104492,
|
|
"epoch": 0.9924139272515075,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.000490632359912125,
|
|
"loss": 5.5083,
|
|
"mean_token_accuracy": 0.1588748961687088,
|
|
"num_tokens": 22125445.0,
|
|
"step": 12755
|
|
},
|
|
{
|
|
"entropy": 5.666949319839477,
|
|
"epoch": 0.992802956623225,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.000490624444297718,
|
|
"loss": 5.5451,
|
|
"mean_token_accuracy": 0.1596327044069767,
|
|
"num_tokens": 22134886.0,
|
|
"step": 12760
|
|
},
|
|
{
|
|
"entropy": 5.56507453918457,
|
|
"epoch": 0.9931919859949426,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004906165254115533,
|
|
"loss": 5.3714,
|
|
"mean_token_accuracy": 0.16933584660291673,
|
|
"num_tokens": 22144521.0,
|
|
"step": 12765
|
|
},
|
|
{
|
|
"entropy": 5.574407052993775,
|
|
"epoch": 0.9935810153666602,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.000490608603253751,
|
|
"loss": 5.3766,
|
|
"mean_token_accuracy": 0.17370123267173768,
|
|
"num_tokens": 22152754.0,
|
|
"step": 12770
|
|
},
|
|
{
|
|
"entropy": 5.611014080047608,
|
|
"epoch": 0.9939700447383778,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.0004906006778244312,
|
|
"loss": 5.3761,
|
|
"mean_token_accuracy": 0.16630607545375825,
|
|
"num_tokens": 22161711.0,
|
|
"step": 12775
|
|
},
|
|
{
|
|
"entropy": 5.635999059677124,
|
|
"epoch": 0.9943590741100953,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004905927491237145,
|
|
"loss": 5.4897,
|
|
"mean_token_accuracy": 0.1675174281001091,
|
|
"num_tokens": 22169762.0,
|
|
"step": 12780
|
|
},
|
|
{
|
|
"entropy": 5.5520223617553714,
|
|
"epoch": 0.9947481034818129,
|
|
"grad_norm": 1.953125,
|
|
"learning_rate": 0.0004905848171517208,
|
|
"loss": 5.3403,
|
|
"mean_token_accuracy": 0.17097441107034683,
|
|
"num_tokens": 22178415.0,
|
|
"step": 12785
|
|
},
|
|
{
|
|
"entropy": 5.478490877151489,
|
|
"epoch": 0.9951371328535304,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.0004905768819085706,
|
|
"loss": 5.3202,
|
|
"mean_token_accuracy": 0.1715176984667778,
|
|
"num_tokens": 22187643.0,
|
|
"step": 12790
|
|
},
|
|
{
|
|
"entropy": 5.486677742004394,
|
|
"epoch": 0.995526162225248,
|
|
"grad_norm": 2.609375,
|
|
"learning_rate": 0.0004905689433943846,
|
|
"loss": 5.338,
|
|
"mean_token_accuracy": 0.1722996786236763,
|
|
"num_tokens": 22196355.0,
|
|
"step": 12795
|
|
},
|
|
{
|
|
"entropy": 5.662151098251343,
|
|
"epoch": 0.9959151915969656,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004905610016092828,
|
|
"loss": 5.4398,
|
|
"mean_token_accuracy": 0.16498246490955354,
|
|
"num_tokens": 22204648.0,
|
|
"step": 12800
|
|
},
|
|
{
|
|
"entropy": 5.570864963531494,
|
|
"epoch": 0.9963042209686831,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.0004905530565533859,
|
|
"loss": 5.4189,
|
|
"mean_token_accuracy": 0.16731907576322555,
|
|
"num_tokens": 22212811.0,
|
|
"step": 12805
|
|
},
|
|
{
|
|
"entropy": 5.492367839813232,
|
|
"epoch": 0.9966932503404007,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.0004905451082268146,
|
|
"loss": 5.3807,
|
|
"mean_token_accuracy": 0.16945702135562896,
|
|
"num_tokens": 22220611.0,
|
|
"step": 12810
|
|
},
|
|
{
|
|
"entropy": 5.672435998916626,
|
|
"epoch": 0.9970822797121183,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004905371566296891,
|
|
"loss": 5.4038,
|
|
"mean_token_accuracy": 0.1607921004295349,
|
|
"num_tokens": 22229606.0,
|
|
"step": 12815
|
|
},
|
|
{
|
|
"entropy": 5.6658851146698,
|
|
"epoch": 0.9974713090838359,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004905292017621305,
|
|
"loss": 5.3849,
|
|
"mean_token_accuracy": 0.16959793865680695,
|
|
"num_tokens": 22238157.0,
|
|
"step": 12820
|
|
},
|
|
{
|
|
"entropy": 5.522281217575073,
|
|
"epoch": 0.9978603384555534,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.0004905212436242593,
|
|
"loss": 5.4065,
|
|
"mean_token_accuracy": 0.16651226878166198,
|
|
"num_tokens": 22246696.0,
|
|
"step": 12825
|
|
},
|
|
{
|
|
"entropy": 5.537300443649292,
|
|
"epoch": 0.9982493678272709,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.0004905132822161962,
|
|
"loss": 5.4544,
|
|
"mean_token_accuracy": 0.16416783928871154,
|
|
"num_tokens": 22255028.0,
|
|
"step": 12830
|
|
},
|
|
{
|
|
"entropy": 5.713491439819336,
|
|
"epoch": 0.9986383971989885,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.0004905053175380621,
|
|
"loss": 5.4804,
|
|
"mean_token_accuracy": 0.1670887604355812,
|
|
"num_tokens": 22263198.0,
|
|
"step": 12835
|
|
},
|
|
{
|
|
"entropy": 5.70943284034729,
|
|
"epoch": 0.9990274265707061,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.0004904973495899778,
|
|
"loss": 5.5093,
|
|
"mean_token_accuracy": 0.16536807268857956,
|
|
"num_tokens": 22273780.0,
|
|
"step": 12840
|
|
},
|
|
{
|
|
"entropy": 5.620561408996582,
|
|
"epoch": 0.9994164559424237,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.0004904893783720642,
|
|
"loss": 5.5068,
|
|
"mean_token_accuracy": 0.16328150182962417,
|
|
"num_tokens": 22281545.0,
|
|
"step": 12845
|
|
},
|
|
{
|
|
"entropy": 5.5460693359375,
|
|
"epoch": 0.9998054853141413,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004904814038844424,
|
|
"loss": 5.4282,
|
|
"mean_token_accuracy": 0.1607063591480255,
|
|
"num_tokens": 22290426.0,
|
|
"step": 12850
|
|
},
|
|
{
|
|
"entropy": 5.5979288419087725,
|
|
"epoch": 1.000155611748687,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.0004904734261272332,
|
|
"loss": 5.4648,
|
|
"mean_token_accuracy": 0.17120369440979427,
|
|
"num_tokens": 22297475.0,
|
|
"step": 12855
|
|
},
|
|
{
|
|
"entropy": 5.542007970809936,
|
|
"epoch": 1.0005446411204046,
|
|
"grad_norm": 1.875,
|
|
"learning_rate": 0.0004904654451005576,
|
|
"loss": 5.1817,
|
|
"mean_token_accuracy": 0.17860206812620164,
|
|
"num_tokens": 22305784.0,
|
|
"step": 12860
|
|
},
|
|
{
|
|
"entropy": 5.517305612564087,
|
|
"epoch": 1.0009336704921221,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004904574608045369,
|
|
"loss": 5.3009,
|
|
"mean_token_accuracy": 0.17512911260128022,
|
|
"num_tokens": 22313951.0,
|
|
"step": 12865
|
|
},
|
|
{
|
|
"entropy": 5.642424583435059,
|
|
"epoch": 1.0013226998638398,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004904494732392923,
|
|
"loss": 5.3832,
|
|
"mean_token_accuracy": 0.17077729105949402,
|
|
"num_tokens": 22322509.0,
|
|
"step": 12870
|
|
},
|
|
{
|
|
"entropy": 5.52863335609436,
|
|
"epoch": 1.0017117292355573,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004904414824049448,
|
|
"loss": 5.3486,
|
|
"mean_token_accuracy": 0.17009214013814927,
|
|
"num_tokens": 22331475.0,
|
|
"step": 12875
|
|
},
|
|
{
|
|
"entropy": 5.5100969791412355,
|
|
"epoch": 1.0021007586072748,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004904334883016156,
|
|
"loss": 5.288,
|
|
"mean_token_accuracy": 0.17327210754156114,
|
|
"num_tokens": 22341114.0,
|
|
"step": 12880
|
|
},
|
|
{
|
|
"entropy": 5.584574890136719,
|
|
"epoch": 1.0024897879789925,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004904254909294261,
|
|
"loss": 5.3495,
|
|
"mean_token_accuracy": 0.16872695982456207,
|
|
"num_tokens": 22349199.0,
|
|
"step": 12885
|
|
},
|
|
{
|
|
"entropy": 5.519780588150025,
|
|
"epoch": 1.00287881735071,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004904174902884978,
|
|
"loss": 5.3431,
|
|
"mean_token_accuracy": 0.165811787545681,
|
|
"num_tokens": 22358485.0,
|
|
"step": 12890
|
|
},
|
|
{
|
|
"entropy": 5.593499946594238,
|
|
"epoch": 1.0032678467224276,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.0004904094863789519,
|
|
"loss": 5.3912,
|
|
"mean_token_accuracy": 0.1618057981133461,
|
|
"num_tokens": 22366936.0,
|
|
"step": 12895
|
|
},
|
|
{
|
|
"entropy": 5.66274209022522,
|
|
"epoch": 1.0036568760941451,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.00049040147920091,
|
|
"loss": 5.3666,
|
|
"mean_token_accuracy": 0.1673392668366432,
|
|
"num_tokens": 22376007.0,
|
|
"step": 12900
|
|
},
|
|
{
|
|
"entropy": 5.540733480453492,
|
|
"epoch": 1.0040459054658626,
|
|
"grad_norm": 2.578125,
|
|
"learning_rate": 0.0004903934687544933,
|
|
"loss": 5.3131,
|
|
"mean_token_accuracy": 0.1762034699320793,
|
|
"num_tokens": 22384747.0,
|
|
"step": 12905
|
|
},
|
|
{
|
|
"entropy": 5.510494422912598,
|
|
"epoch": 1.0044349348375803,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 0.0004903854550398237,
|
|
"loss": 5.3153,
|
|
"mean_token_accuracy": 0.17209814339876175,
|
|
"num_tokens": 22393730.0,
|
|
"step": 12910
|
|
},
|
|
{
|
|
"entropy": 5.619092321395874,
|
|
"epoch": 1.0048239642092978,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004903774380570226,
|
|
"loss": 5.3396,
|
|
"mean_token_accuracy": 0.1631534293293953,
|
|
"num_tokens": 22402121.0,
|
|
"step": 12915
|
|
},
|
|
{
|
|
"entropy": 5.619703388214111,
|
|
"epoch": 1.0052129935810155,
|
|
"grad_norm": 1.84375,
|
|
"learning_rate": 0.0004903694178062117,
|
|
"loss": 5.3648,
|
|
"mean_token_accuracy": 0.1633022353053093,
|
|
"num_tokens": 22410943.0,
|
|
"step": 12920
|
|
},
|
|
{
|
|
"entropy": 5.60378589630127,
|
|
"epoch": 1.005602022952733,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004903613942875126,
|
|
"loss": 5.4403,
|
|
"mean_token_accuracy": 0.1632104516029358,
|
|
"num_tokens": 22420137.0,
|
|
"step": 12925
|
|
},
|
|
{
|
|
"entropy": 5.568807935714721,
|
|
"epoch": 1.0059910523244504,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004903533675010472,
|
|
"loss": 5.3629,
|
|
"mean_token_accuracy": 0.16422339230775834,
|
|
"num_tokens": 22429031.0,
|
|
"step": 12930
|
|
},
|
|
{
|
|
"entropy": 5.584084558486938,
|
|
"epoch": 1.006380081696168,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.0004903453374469373,
|
|
"loss": 5.3991,
|
|
"mean_token_accuracy": 0.1641605481505394,
|
|
"num_tokens": 22438735.0,
|
|
"step": 12935
|
|
},
|
|
{
|
|
"entropy": 5.61544885635376,
|
|
"epoch": 1.0067691110678856,
|
|
"grad_norm": 1.9296875,
|
|
"learning_rate": 0.0004903373041253045,
|
|
"loss": 5.3929,
|
|
"mean_token_accuracy": 0.16759471893310546,
|
|
"num_tokens": 22447374.0,
|
|
"step": 12940
|
|
},
|
|
{
|
|
"entropy": 5.6362590312957765,
|
|
"epoch": 1.0071581404396033,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.0004903292675362709,
|
|
"loss": 5.3141,
|
|
"mean_token_accuracy": 0.17238984107971192,
|
|
"num_tokens": 22455542.0,
|
|
"step": 12945
|
|
},
|
|
{
|
|
"entropy": 5.505145788192749,
|
|
"epoch": 1.0075471698113208,
|
|
"grad_norm": 2.65625,
|
|
"learning_rate": 0.0004903212276799584,
|
|
"loss": 5.3619,
|
|
"mean_token_accuracy": 0.16940085589885712,
|
|
"num_tokens": 22464591.0,
|
|
"step": 12950
|
|
},
|
|
{
|
|
"entropy": 5.5873900890350345,
|
|
"epoch": 1.0079361991830382,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 0.0004903131845564889,
|
|
"loss": 5.3148,
|
|
"mean_token_accuracy": 0.17614834308624266,
|
|
"num_tokens": 22472315.0,
|
|
"step": 12955
|
|
},
|
|
{
|
|
"entropy": 5.613324451446533,
|
|
"epoch": 1.008325228554756,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.0004903051381659847,
|
|
"loss": 5.4465,
|
|
"mean_token_accuracy": 0.16300565004348755,
|
|
"num_tokens": 22480662.0,
|
|
"step": 12960
|
|
},
|
|
{
|
|
"entropy": 5.4808722019195555,
|
|
"epoch": 1.0087142579264734,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004902970885085677,
|
|
"loss": 5.3199,
|
|
"mean_token_accuracy": 0.17492171078920365,
|
|
"num_tokens": 22489600.0,
|
|
"step": 12965
|
|
},
|
|
{
|
|
"entropy": 5.621557521820068,
|
|
"epoch": 1.009103287298191,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.00049028903558436,
|
|
"loss": 5.3858,
|
|
"mean_token_accuracy": 0.1620638594031334,
|
|
"num_tokens": 22498114.0,
|
|
"step": 12970
|
|
},
|
|
{
|
|
"entropy": 5.551367855072021,
|
|
"epoch": 1.0094923166699086,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004902809793934838,
|
|
"loss": 5.2365,
|
|
"mean_token_accuracy": 0.1755081444978714,
|
|
"num_tokens": 22506349.0,
|
|
"step": 12975
|
|
},
|
|
{
|
|
"entropy": 5.545008945465088,
|
|
"epoch": 1.009881346041626,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.0004902729199360615,
|
|
"loss": 5.3275,
|
|
"mean_token_accuracy": 0.16617290526628495,
|
|
"num_tokens": 22514878.0,
|
|
"step": 12980
|
|
},
|
|
{
|
|
"entropy": 5.551216268539429,
|
|
"epoch": 1.0102703754133437,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.0004902648572122153,
|
|
"loss": 5.3387,
|
|
"mean_token_accuracy": 0.1621580272912979,
|
|
"num_tokens": 22522992.0,
|
|
"step": 12985
|
|
},
|
|
{
|
|
"entropy": 5.67969069480896,
|
|
"epoch": 1.0106594047850612,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004902567912220674,
|
|
"loss": 5.3935,
|
|
"mean_token_accuracy": 0.1589156597852707,
|
|
"num_tokens": 22531407.0,
|
|
"step": 12990
|
|
},
|
|
{
|
|
"entropy": 5.54848575592041,
|
|
"epoch": 1.011048434156779,
|
|
"grad_norm": 2.40625,
|
|
"learning_rate": 0.0004902487219657404,
|
|
"loss": 5.2849,
|
|
"mean_token_accuracy": 0.16945454627275466,
|
|
"num_tokens": 22540255.0,
|
|
"step": 12995
|
|
},
|
|
{
|
|
"entropy": 5.547482013702393,
|
|
"epoch": 1.0114374635284964,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004902406494433566,
|
|
"loss": 5.3275,
|
|
"mean_token_accuracy": 0.17176171392202377,
|
|
"num_tokens": 22549139.0,
|
|
"step": 13000
|
|
},
|
|
{
|
|
"entropy": 5.615173864364624,
|
|
"epoch": 1.0118264929002139,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 0.0004902325736550386,
|
|
"loss": 5.3381,
|
|
"mean_token_accuracy": 0.16898633688688278,
|
|
"num_tokens": 22557746.0,
|
|
"step": 13005
|
|
},
|
|
{
|
|
"entropy": 5.549011850357056,
|
|
"epoch": 1.0122155222719316,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.0004902244946009088,
|
|
"loss": 5.3055,
|
|
"mean_token_accuracy": 0.16827258616685867,
|
|
"num_tokens": 22566695.0,
|
|
"step": 13010
|
|
},
|
|
{
|
|
"entropy": 5.518293762207032,
|
|
"epoch": 1.012604551643649,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004902164122810899,
|
|
"loss": 5.3309,
|
|
"mean_token_accuracy": 0.16612116247415543,
|
|
"num_tokens": 22575196.0,
|
|
"step": 13015
|
|
},
|
|
{
|
|
"entropy": 5.582631587982178,
|
|
"epoch": 1.0129935810153667,
|
|
"grad_norm": 1.90625,
|
|
"learning_rate": 0.0004902083266957045,
|
|
"loss": 5.3362,
|
|
"mean_token_accuracy": 0.16990406215190887,
|
|
"num_tokens": 22583520.0,
|
|
"step": 13020
|
|
},
|
|
{
|
|
"entropy": 5.567165517807007,
|
|
"epoch": 1.0133826103870842,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.0004902002378448753,
|
|
"loss": 5.3713,
|
|
"mean_token_accuracy": 0.16287715435028077,
|
|
"num_tokens": 22591896.0,
|
|
"step": 13025
|
|
},
|
|
{
|
|
"entropy": 5.52042031288147,
|
|
"epoch": 1.0137716397588017,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.000490192145728725,
|
|
"loss": 5.3089,
|
|
"mean_token_accuracy": 0.1736544817686081,
|
|
"num_tokens": 22600097.0,
|
|
"step": 13030
|
|
},
|
|
{
|
|
"entropy": 5.55564866065979,
|
|
"epoch": 1.0141606691305194,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004901840503473764,
|
|
"loss": 5.2385,
|
|
"mean_token_accuracy": 0.1687760055065155,
|
|
"num_tokens": 22607956.0,
|
|
"step": 13035
|
|
},
|
|
{
|
|
"entropy": 5.56544828414917,
|
|
"epoch": 1.0145496985022369,
|
|
"grad_norm": 1.875,
|
|
"learning_rate": 0.0004901759517009522,
|
|
"loss": 5.3214,
|
|
"mean_token_accuracy": 0.16376885920763015,
|
|
"num_tokens": 22616549.0,
|
|
"step": 13040
|
|
},
|
|
{
|
|
"entropy": 5.534838724136352,
|
|
"epoch": 1.0149387278739546,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004901678497895755,
|
|
"loss": 5.2522,
|
|
"mean_token_accuracy": 0.1693417176604271,
|
|
"num_tokens": 22625138.0,
|
|
"step": 13045
|
|
},
|
|
{
|
|
"entropy": 5.540400600433349,
|
|
"epoch": 1.015327757245672,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.0004901597446133692,
|
|
"loss": 5.3506,
|
|
"mean_token_accuracy": 0.161795973777771,
|
|
"num_tokens": 22633808.0,
|
|
"step": 13050
|
|
},
|
|
{
|
|
"entropy": 5.543810558319092,
|
|
"epoch": 1.0157167866173895,
|
|
"grad_norm": 1.9296875,
|
|
"learning_rate": 0.0004901516361724564,
|
|
"loss": 5.3123,
|
|
"mean_token_accuracy": 0.17465132623910903,
|
|
"num_tokens": 22642517.0,
|
|
"step": 13055
|
|
},
|
|
{
|
|
"entropy": 5.617796564102173,
|
|
"epoch": 1.0161058159891072,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.0004901435244669597,
|
|
"loss": 5.3596,
|
|
"mean_token_accuracy": 0.16288644224405288,
|
|
"num_tokens": 22651822.0,
|
|
"step": 13060
|
|
},
|
|
{
|
|
"entropy": 5.579719924926758,
|
|
"epoch": 1.0164948453608247,
|
|
"grad_norm": 1.9921875,
|
|
"learning_rate": 0.0004901354094970025,
|
|
"loss": 5.3457,
|
|
"mean_token_accuracy": 0.16347450166940689,
|
|
"num_tokens": 22660763.0,
|
|
"step": 13065
|
|
},
|
|
{
|
|
"entropy": 5.5017345428466795,
|
|
"epoch": 1.0168838747325424,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004901272912627081,
|
|
"loss": 5.3398,
|
|
"mean_token_accuracy": 0.16765276193618775,
|
|
"num_tokens": 22669449.0,
|
|
"step": 13070
|
|
},
|
|
{
|
|
"entropy": 5.5804413795471195,
|
|
"epoch": 1.0172729041042599,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.0004901191697641992,
|
|
"loss": 5.3861,
|
|
"mean_token_accuracy": 0.1657060131430626,
|
|
"num_tokens": 22678212.0,
|
|
"step": 13075
|
|
},
|
|
{
|
|
"entropy": 5.562907409667969,
|
|
"epoch": 1.0176619334759773,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0004901110450015994,
|
|
"loss": 5.295,
|
|
"mean_token_accuracy": 0.17451861798763274,
|
|
"num_tokens": 22686509.0,
|
|
"step": 13080
|
|
},
|
|
{
|
|
"entropy": 5.543142414093017,
|
|
"epoch": 1.018050962847695,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.0004901029169750319,
|
|
"loss": 5.3281,
|
|
"mean_token_accuracy": 0.16775942146778106,
|
|
"num_tokens": 22695473.0,
|
|
"step": 13085
|
|
},
|
|
{
|
|
"entropy": 5.609576463699341,
|
|
"epoch": 1.0184399922194125,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.0004900947856846201,
|
|
"loss": 5.4127,
|
|
"mean_token_accuracy": 0.16441992670297623,
|
|
"num_tokens": 22704567.0,
|
|
"step": 13090
|
|
},
|
|
{
|
|
"entropy": 5.562847089767456,
|
|
"epoch": 1.0188290215911302,
|
|
"grad_norm": 1.984375,
|
|
"learning_rate": 0.000490086651130487,
|
|
"loss": 5.2721,
|
|
"mean_token_accuracy": 0.1747107222676277,
|
|
"num_tokens": 22713981.0,
|
|
"step": 13095
|
|
},
|
|
{
|
|
"entropy": 5.429905033111572,
|
|
"epoch": 1.0192180509628477,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004900785133127566,
|
|
"loss": 5.1944,
|
|
"mean_token_accuracy": 0.18478695452213287,
|
|
"num_tokens": 22722855.0,
|
|
"step": 13100
|
|
},
|
|
{
|
|
"entropy": 5.485940790176391,
|
|
"epoch": 1.0196070803345652,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.000490070372231552,
|
|
"loss": 5.3328,
|
|
"mean_token_accuracy": 0.16357437372207642,
|
|
"num_tokens": 22732454.0,
|
|
"step": 13105
|
|
},
|
|
{
|
|
"entropy": 5.606695032119751,
|
|
"epoch": 1.0199961097062828,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004900622278869968,
|
|
"loss": 5.2102,
|
|
"mean_token_accuracy": 0.1799958288669586,
|
|
"num_tokens": 22741331.0,
|
|
"step": 13110
|
|
},
|
|
{
|
|
"entropy": 5.593059062957764,
|
|
"epoch": 1.0203851390780003,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004900540802792146,
|
|
"loss": 5.3746,
|
|
"mean_token_accuracy": 0.16873959600925445,
|
|
"num_tokens": 22749983.0,
|
|
"step": 13115
|
|
},
|
|
{
|
|
"entropy": 5.492002773284912,
|
|
"epoch": 1.020774168449718,
|
|
"grad_norm": 3.765625,
|
|
"learning_rate": 0.000490045929408329,
|
|
"loss": 5.3309,
|
|
"mean_token_accuracy": 0.1734270080924034,
|
|
"num_tokens": 22759112.0,
|
|
"step": 13120
|
|
},
|
|
{
|
|
"entropy": 5.556809425354004,
|
|
"epoch": 1.0211631978214355,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004900377752744637,
|
|
"loss": 5.3925,
|
|
"mean_token_accuracy": 0.16835140734910964,
|
|
"num_tokens": 22768456.0,
|
|
"step": 13125
|
|
},
|
|
{
|
|
"entropy": 5.606002378463745,
|
|
"epoch": 1.021552227193153,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004900296178777426,
|
|
"loss": 5.3026,
|
|
"mean_token_accuracy": 0.17280267179012299,
|
|
"num_tokens": 22777450.0,
|
|
"step": 13130
|
|
},
|
|
{
|
|
"entropy": 5.5872917652130125,
|
|
"epoch": 1.0219412565648707,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.000490021457218289,
|
|
"loss": 5.3213,
|
|
"mean_token_accuracy": 0.1747939854860306,
|
|
"num_tokens": 22785704.0,
|
|
"step": 13135
|
|
},
|
|
{
|
|
"entropy": 5.507707643508911,
|
|
"epoch": 1.0223302859365881,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004900132932962272,
|
|
"loss": 5.3197,
|
|
"mean_token_accuracy": 0.16345871686935426,
|
|
"num_tokens": 22794649.0,
|
|
"step": 13140
|
|
},
|
|
{
|
|
"entropy": 5.5883222103118895,
|
|
"epoch": 1.0227193153083058,
|
|
"grad_norm": 1.8515625,
|
|
"learning_rate": 0.000490005126111681,
|
|
"loss": 5.4399,
|
|
"mean_token_accuracy": 0.16187312155961991,
|
|
"num_tokens": 22803501.0,
|
|
"step": 13145
|
|
},
|
|
{
|
|
"entropy": 5.684654664993286,
|
|
"epoch": 1.0231083446800233,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.000489996955664774,
|
|
"loss": 5.348,
|
|
"mean_token_accuracy": 0.16720695942640304,
|
|
"num_tokens": 22811779.0,
|
|
"step": 13150
|
|
},
|
|
{
|
|
"entropy": 5.524373149871826,
|
|
"epoch": 1.023497374051741,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004899887819556306,
|
|
"loss": 5.36,
|
|
"mean_token_accuracy": 0.17376210838556289,
|
|
"num_tokens": 22821108.0,
|
|
"step": 13155
|
|
},
|
|
{
|
|
"entropy": 5.6401018619537355,
|
|
"epoch": 1.0238864034234585,
|
|
"grad_norm": 1.921875,
|
|
"learning_rate": 0.0004899806049843745,
|
|
"loss": 5.39,
|
|
"mean_token_accuracy": 0.1614253655076027,
|
|
"num_tokens": 22829369.0,
|
|
"step": 13160
|
|
},
|
|
{
|
|
"entropy": 5.572082281112671,
|
|
"epoch": 1.024275432795176,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.0004899724247511299,
|
|
"loss": 5.3402,
|
|
"mean_token_accuracy": 0.16769103705883026,
|
|
"num_tokens": 22838441.0,
|
|
"step": 13165
|
|
},
|
|
{
|
|
"entropy": 5.531656885147095,
|
|
"epoch": 1.0246644621668937,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.000489964241256021,
|
|
"loss": 5.309,
|
|
"mean_token_accuracy": 0.16549871414899825,
|
|
"num_tokens": 22847587.0,
|
|
"step": 13170
|
|
},
|
|
{
|
|
"entropy": 5.474168586730957,
|
|
"epoch": 1.0250534915386111,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004899560544991718,
|
|
"loss": 5.3023,
|
|
"mean_token_accuracy": 0.17257890105247498,
|
|
"num_tokens": 22856051.0,
|
|
"step": 13175
|
|
},
|
|
{
|
|
"entropy": 5.60618748664856,
|
|
"epoch": 1.0254425209103288,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004899478644807068,
|
|
"loss": 5.371,
|
|
"mean_token_accuracy": 0.16718021035194397,
|
|
"num_tokens": 22864822.0,
|
|
"step": 13180
|
|
},
|
|
{
|
|
"entropy": 5.553058004379272,
|
|
"epoch": 1.0258315502820463,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.0004899396712007498,
|
|
"loss": 5.3414,
|
|
"mean_token_accuracy": 0.1723121538758278,
|
|
"num_tokens": 22873199.0,
|
|
"step": 13185
|
|
},
|
|
{
|
|
"entropy": 5.524868726730347,
|
|
"epoch": 1.0262205796537638,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.0004899314746594256,
|
|
"loss": 5.3994,
|
|
"mean_token_accuracy": 0.15958003848791122,
|
|
"num_tokens": 22881184.0,
|
|
"step": 13190
|
|
},
|
|
{
|
|
"entropy": 5.605687379837036,
|
|
"epoch": 1.0266096090254815,
|
|
"grad_norm": 1.84375,
|
|
"learning_rate": 0.0004899232748568584,
|
|
"loss": 5.2965,
|
|
"mean_token_accuracy": 0.17100712656974792,
|
|
"num_tokens": 22890087.0,
|
|
"step": 13195
|
|
},
|
|
{
|
|
"entropy": 5.579258823394776,
|
|
"epoch": 1.026998638397199,
|
|
"grad_norm": 1.96875,
|
|
"learning_rate": 0.0004899150717931724,
|
|
"loss": 5.3099,
|
|
"mean_token_accuracy": 0.16823868006467818,
|
|
"num_tokens": 22899013.0,
|
|
"step": 13200
|
|
},
|
|
{
|
|
"entropy": 5.545676279067993,
|
|
"epoch": 1.0273876677689167,
|
|
"grad_norm": 1.953125,
|
|
"learning_rate": 0.0004899068654684924,
|
|
"loss": 5.4749,
|
|
"mean_token_accuracy": 0.16100508570671082,
|
|
"num_tokens": 22908740.0,
|
|
"step": 13205
|
|
},
|
|
{
|
|
"entropy": 5.6598708152771,
|
|
"epoch": 1.0277766971406341,
|
|
"grad_norm": 2.265625,
|
|
"learning_rate": 0.0004898986558829428,
|
|
"loss": 5.3829,
|
|
"mean_token_accuracy": 0.17246803343296052,
|
|
"num_tokens": 22917502.0,
|
|
"step": 13210
|
|
},
|
|
{
|
|
"entropy": 5.559323310852051,
|
|
"epoch": 1.0281657265123516,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.0004898904430366479,
|
|
"loss": 5.3148,
|
|
"mean_token_accuracy": 0.16957433819770812,
|
|
"num_tokens": 22927076.0,
|
|
"step": 13215
|
|
},
|
|
{
|
|
"entropy": 5.551990985870361,
|
|
"epoch": 1.0285547558840693,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.0004898822269297328,
|
|
"loss": 5.3843,
|
|
"mean_token_accuracy": 0.1583206206560135,
|
|
"num_tokens": 22936111.0,
|
|
"step": 13220
|
|
},
|
|
{
|
|
"entropy": 5.5573498725891115,
|
|
"epoch": 1.0289437852557868,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004898740075623218,
|
|
"loss": 5.2474,
|
|
"mean_token_accuracy": 0.17229943722486496,
|
|
"num_tokens": 22944752.0,
|
|
"step": 13225
|
|
},
|
|
{
|
|
"entropy": 5.616778039932251,
|
|
"epoch": 1.0293328146275045,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.0004898657849345399,
|
|
"loss": 5.4473,
|
|
"mean_token_accuracy": 0.1688223049044609,
|
|
"num_tokens": 22952971.0,
|
|
"step": 13230
|
|
},
|
|
{
|
|
"entropy": 5.5658811092376705,
|
|
"epoch": 1.029721843999222,
|
|
"grad_norm": 3.9375,
|
|
"learning_rate": 0.0004898575590465116,
|
|
"loss": 5.368,
|
|
"mean_token_accuracy": 0.17380984276533126,
|
|
"num_tokens": 22961257.0,
|
|
"step": 13235
|
|
},
|
|
{
|
|
"entropy": 5.5469003200531,
|
|
"epoch": 1.0301108733709394,
|
|
"grad_norm": 4.6875,
|
|
"learning_rate": 0.0004898493298983619,
|
|
"loss": 5.4142,
|
|
"mean_token_accuracy": 0.16502669006586074,
|
|
"num_tokens": 22970659.0,
|
|
"step": 13240
|
|
},
|
|
{
|
|
"entropy": 5.521573686599732,
|
|
"epoch": 1.0304999027426571,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.0004898410974902155,
|
|
"loss": 5.3558,
|
|
"mean_token_accuracy": 0.17028875946998595,
|
|
"num_tokens": 22978830.0,
|
|
"step": 13245
|
|
},
|
|
{
|
|
"entropy": 5.579059696197509,
|
|
"epoch": 1.0308889321143746,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.0004898328618221974,
|
|
"loss": 5.3152,
|
|
"mean_token_accuracy": 0.17687464207410813,
|
|
"num_tokens": 22987100.0,
|
|
"step": 13250
|
|
},
|
|
{
|
|
"entropy": 5.578388023376465,
|
|
"epoch": 1.0312779614860923,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004898246228944327,
|
|
"loss": 5.3554,
|
|
"mean_token_accuracy": 0.16435202658176423,
|
|
"num_tokens": 22995749.0,
|
|
"step": 13255
|
|
},
|
|
{
|
|
"entropy": 5.605004167556762,
|
|
"epoch": 1.0316669908578098,
|
|
"grad_norm": 2.40625,
|
|
"learning_rate": 0.0004898163807070461,
|
|
"loss": 5.413,
|
|
"mean_token_accuracy": 0.17330105900764464,
|
|
"num_tokens": 23004410.0,
|
|
"step": 13260
|
|
},
|
|
{
|
|
"entropy": 5.594409990310669,
|
|
"epoch": 1.0320560202295272,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.0004898081352601629,
|
|
"loss": 5.288,
|
|
"mean_token_accuracy": 0.16828453540802002,
|
|
"num_tokens": 23012935.0,
|
|
"step": 13265
|
|
},
|
|
{
|
|
"entropy": 5.50854754447937,
|
|
"epoch": 1.032445049601245,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004897998865539082,
|
|
"loss": 5.2804,
|
|
"mean_token_accuracy": 0.17281851768493653,
|
|
"num_tokens": 23021769.0,
|
|
"step": 13270
|
|
},
|
|
{
|
|
"entropy": 5.520813226699829,
|
|
"epoch": 1.0328340789729624,
|
|
"grad_norm": 1.9453125,
|
|
"learning_rate": 0.0004897916345884069,
|
|
"loss": 5.2721,
|
|
"mean_token_accuracy": 0.1756499245762825,
|
|
"num_tokens": 23030915.0,
|
|
"step": 13275
|
|
},
|
|
{
|
|
"entropy": 5.504369640350342,
|
|
"epoch": 1.0332231083446801,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.0004897833793637847,
|
|
"loss": 5.3924,
|
|
"mean_token_accuracy": 0.15951500087976456,
|
|
"num_tokens": 23039422.0,
|
|
"step": 13280
|
|
},
|
|
{
|
|
"entropy": 5.569696378707886,
|
|
"epoch": 1.0336121377163976,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.0004897751208801665,
|
|
"loss": 5.4454,
|
|
"mean_token_accuracy": 0.16261413246393203,
|
|
"num_tokens": 23048485.0,
|
|
"step": 13285
|
|
},
|
|
{
|
|
"entropy": 5.535351037979126,
|
|
"epoch": 1.034001167088115,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.0004897668591376777,
|
|
"loss": 5.3256,
|
|
"mean_token_accuracy": 0.17330169230699538,
|
|
"num_tokens": 23057506.0,
|
|
"step": 13290
|
|
},
|
|
{
|
|
"entropy": 5.449153470993042,
|
|
"epoch": 1.0343901964598328,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004897585941364436,
|
|
"loss": 5.1798,
|
|
"mean_token_accuracy": 0.17621085941791534,
|
|
"num_tokens": 23065430.0,
|
|
"step": 13295
|
|
},
|
|
{
|
|
"entropy": 5.445277500152588,
|
|
"epoch": 1.0347792258315502,
|
|
"grad_norm": 2.296875,
|
|
"learning_rate": 0.0004897503258765896,
|
|
"loss": 5.2903,
|
|
"mean_token_accuracy": 0.16864744275808335,
|
|
"num_tokens": 23074533.0,
|
|
"step": 13300
|
|
},
|
|
{
|
|
"entropy": 5.608288717269898,
|
|
"epoch": 1.035168255203268,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.0004897420543582413,
|
|
"loss": 5.3078,
|
|
"mean_token_accuracy": 0.1686733141541481,
|
|
"num_tokens": 23083020.0,
|
|
"step": 13305
|
|
},
|
|
{
|
|
"entropy": 5.526839733123779,
|
|
"epoch": 1.0355572845749854,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.000489733779581524,
|
|
"loss": 5.3554,
|
|
"mean_token_accuracy": 0.17150050699710845,
|
|
"num_tokens": 23091992.0,
|
|
"step": 13310
|
|
},
|
|
{
|
|
"entropy": 5.46464204788208,
|
|
"epoch": 1.035946313946703,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.0004897255015465635,
|
|
"loss": 5.3077,
|
|
"mean_token_accuracy": 0.16987432390451432,
|
|
"num_tokens": 23100411.0,
|
|
"step": 13315
|
|
},
|
|
{
|
|
"entropy": 5.525960111618042,
|
|
"epoch": 1.0363353433184206,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004897172202534853,
|
|
"loss": 5.3994,
|
|
"mean_token_accuracy": 0.16838788241147995,
|
|
"num_tokens": 23108867.0,
|
|
"step": 13320
|
|
},
|
|
{
|
|
"entropy": 5.542663431167602,
|
|
"epoch": 1.036724372690138,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.000489708935702415,
|
|
"loss": 5.2597,
|
|
"mean_token_accuracy": 0.1718900367617607,
|
|
"num_tokens": 23116692.0,
|
|
"step": 13325
|
|
},
|
|
{
|
|
"entropy": 5.5665501117706295,
|
|
"epoch": 1.0371134020618558,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004897006478934784,
|
|
"loss": 5.3174,
|
|
"mean_token_accuracy": 0.17098373919725418,
|
|
"num_tokens": 23125138.0,
|
|
"step": 13330
|
|
},
|
|
{
|
|
"entropy": 5.512345886230468,
|
|
"epoch": 1.0375024314335732,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004896923568268011,
|
|
"loss": 5.3352,
|
|
"mean_token_accuracy": 0.16749261319637299,
|
|
"num_tokens": 23133263.0,
|
|
"step": 13335
|
|
},
|
|
{
|
|
"entropy": 5.591986513137817,
|
|
"epoch": 1.0378914608052907,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.000489684062502509,
|
|
"loss": 5.3282,
|
|
"mean_token_accuracy": 0.16933337599039078,
|
|
"num_tokens": 23141984.0,
|
|
"step": 13340
|
|
},
|
|
{
|
|
"entropy": 5.555146884918213,
|
|
"epoch": 1.0382804901770084,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.0004896757649207281,
|
|
"loss": 5.2813,
|
|
"mean_token_accuracy": 0.1743380233645439,
|
|
"num_tokens": 23151598.0,
|
|
"step": 13345
|
|
},
|
|
{
|
|
"entropy": 5.550322675704956,
|
|
"epoch": 1.0386695195487259,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.000489667464081584,
|
|
"loss": 5.4211,
|
|
"mean_token_accuracy": 0.1643439456820488,
|
|
"num_tokens": 23159737.0,
|
|
"step": 13350
|
|
},
|
|
{
|
|
"entropy": 5.4744720458984375,
|
|
"epoch": 1.0390585489204436,
|
|
"grad_norm": 3.265625,
|
|
"learning_rate": 0.0004896591599852029,
|
|
"loss": 5.2708,
|
|
"mean_token_accuracy": 0.17863331139087676,
|
|
"num_tokens": 23168852.0,
|
|
"step": 13355
|
|
},
|
|
{
|
|
"entropy": 5.624505949020386,
|
|
"epoch": 1.039447578292161,
|
|
"grad_norm": 1.84375,
|
|
"learning_rate": 0.0004896508526317107,
|
|
"loss": 5.376,
|
|
"mean_token_accuracy": 0.17188506573438644,
|
|
"num_tokens": 23178227.0,
|
|
"step": 13360
|
|
},
|
|
{
|
|
"entropy": 5.537820959091187,
|
|
"epoch": 1.0398366076638785,
|
|
"grad_norm": 3.375,
|
|
"learning_rate": 0.0004896425420212334,
|
|
"loss": 5.2847,
|
|
"mean_token_accuracy": 0.17426070421934128,
|
|
"num_tokens": 23187286.0,
|
|
"step": 13365
|
|
},
|
|
{
|
|
"entropy": 5.562308311462402,
|
|
"epoch": 1.0402256370355962,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.0004896342281538973,
|
|
"loss": 5.3546,
|
|
"mean_token_accuracy": 0.17472760677337645,
|
|
"num_tokens": 23196163.0,
|
|
"step": 13370
|
|
},
|
|
{
|
|
"entropy": 5.550947189331055,
|
|
"epoch": 1.0406146664073137,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.0004896259110298283,
|
|
"loss": 5.2869,
|
|
"mean_token_accuracy": 0.1753503128886223,
|
|
"num_tokens": 23203742.0,
|
|
"step": 13375
|
|
},
|
|
{
|
|
"entropy": 5.60201244354248,
|
|
"epoch": 1.0410036957790314,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004896175906491528,
|
|
"loss": 5.4758,
|
|
"mean_token_accuracy": 0.16407623142004013,
|
|
"num_tokens": 23212860.0,
|
|
"step": 13380
|
|
},
|
|
{
|
|
"entropy": 5.590807676315308,
|
|
"epoch": 1.0413927251507489,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004896092670119968,
|
|
"loss": 5.3203,
|
|
"mean_token_accuracy": 0.1673245757818222,
|
|
"num_tokens": 23222558.0,
|
|
"step": 13385
|
|
},
|
|
{
|
|
"entropy": 5.551709508895874,
|
|
"epoch": 1.0417817545224664,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0004896009401184869,
|
|
"loss": 5.3574,
|
|
"mean_token_accuracy": 0.1720505490899086,
|
|
"num_tokens": 23231413.0,
|
|
"step": 13390
|
|
},
|
|
{
|
|
"entropy": 5.555619239807129,
|
|
"epoch": 1.042170783894184,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004895926099687493,
|
|
"loss": 5.3363,
|
|
"mean_token_accuracy": 0.17034251093864441,
|
|
"num_tokens": 23240783.0,
|
|
"step": 13395
|
|
},
|
|
{
|
|
"entropy": 5.532523155212402,
|
|
"epoch": 1.0425598132659015,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004895842765629104,
|
|
"loss": 5.4313,
|
|
"mean_token_accuracy": 0.1656470015645027,
|
|
"num_tokens": 23249125.0,
|
|
"step": 13400
|
|
},
|
|
{
|
|
"entropy": 5.5374926090240475,
|
|
"epoch": 1.0429488426376192,
|
|
"grad_norm": 1.9453125,
|
|
"learning_rate": 0.0004895759399010966,
|
|
"loss": 5.2574,
|
|
"mean_token_accuracy": 0.17450618147850036,
|
|
"num_tokens": 23257793.0,
|
|
"step": 13405
|
|
},
|
|
{
|
|
"entropy": 5.488899517059326,
|
|
"epoch": 1.0433378720093367,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004895675999834345,
|
|
"loss": 5.2485,
|
|
"mean_token_accuracy": 0.17603913247585296,
|
|
"num_tokens": 23266361.0,
|
|
"step": 13410
|
|
},
|
|
{
|
|
"entropy": 5.473702669143677,
|
|
"epoch": 1.0437269013810542,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004895592568100505,
|
|
"loss": 5.2495,
|
|
"mean_token_accuracy": 0.17226188629865646,
|
|
"num_tokens": 23274914.0,
|
|
"step": 13415
|
|
},
|
|
{
|
|
"entropy": 5.504036140441895,
|
|
"epoch": 1.0441159307527719,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004895509103810714,
|
|
"loss": 5.3223,
|
|
"mean_token_accuracy": 0.1680256873369217,
|
|
"num_tokens": 23283067.0,
|
|
"step": 13420
|
|
},
|
|
{
|
|
"entropy": 5.557072162628174,
|
|
"epoch": 1.0445049601244893,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004895425606966237,
|
|
"loss": 5.3217,
|
|
"mean_token_accuracy": 0.163113597035408,
|
|
"num_tokens": 23291114.0,
|
|
"step": 13425
|
|
},
|
|
{
|
|
"entropy": 5.450375986099243,
|
|
"epoch": 1.044893989496207,
|
|
"grad_norm": 1.8984375,
|
|
"learning_rate": 0.000489534207756834,
|
|
"loss": 5.2017,
|
|
"mean_token_accuracy": 0.17558492422103883,
|
|
"num_tokens": 23300525.0,
|
|
"step": 13430
|
|
},
|
|
{
|
|
"entropy": 5.52487735748291,
|
|
"epoch": 1.0452830188679245,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004895258515618293,
|
|
"loss": 5.2735,
|
|
"mean_token_accuracy": 0.1722135841846466,
|
|
"num_tokens": 23308984.0,
|
|
"step": 13435
|
|
},
|
|
{
|
|
"entropy": 5.515931081771851,
|
|
"epoch": 1.045672048239642,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.0004895174921117362,
|
|
"loss": 5.398,
|
|
"mean_token_accuracy": 0.16419498920440673,
|
|
"num_tokens": 23318137.0,
|
|
"step": 13440
|
|
},
|
|
{
|
|
"entropy": 5.631139802932739,
|
|
"epoch": 1.0460610776113597,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.0004895091294066816,
|
|
"loss": 5.466,
|
|
"mean_token_accuracy": 0.16149957478046417,
|
|
"num_tokens": 23326276.0,
|
|
"step": 13445
|
|
},
|
|
{
|
|
"entropy": 5.5653404712677,
|
|
"epoch": 1.0464501069830772,
|
|
"grad_norm": 5.46875,
|
|
"learning_rate": 0.0004895007634467924,
|
|
"loss": 5.3336,
|
|
"mean_token_accuracy": 0.16442983001470565,
|
|
"num_tokens": 23334578.0,
|
|
"step": 13450
|
|
},
|
|
{
|
|
"entropy": 5.5236992835998535,
|
|
"epoch": 1.0468391363547949,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.0004894923942321955,
|
|
"loss": 5.3667,
|
|
"mean_token_accuracy": 0.16518339812755584,
|
|
"num_tokens": 23344173.0,
|
|
"step": 13455
|
|
},
|
|
{
|
|
"entropy": 5.45450530052185,
|
|
"epoch": 1.0472281657265123,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.0004894840217630179,
|
|
"loss": 5.2131,
|
|
"mean_token_accuracy": 0.1739779755473137,
|
|
"num_tokens": 23353098.0,
|
|
"step": 13460
|
|
},
|
|
{
|
|
"entropy": 5.545091152191162,
|
|
"epoch": 1.0476171950982298,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.0004894756460393868,
|
|
"loss": 5.3689,
|
|
"mean_token_accuracy": 0.16889076977968215,
|
|
"num_tokens": 23362364.0,
|
|
"step": 13465
|
|
},
|
|
{
|
|
"entropy": 5.585870885848999,
|
|
"epoch": 1.0480062244699475,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.000489467267061429,
|
|
"loss": 5.3796,
|
|
"mean_token_accuracy": 0.16421883255243303,
|
|
"num_tokens": 23371903.0,
|
|
"step": 13470
|
|
},
|
|
{
|
|
"entropy": 5.528911972045899,
|
|
"epoch": 1.048395253841665,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.0004894588848292718,
|
|
"loss": 5.2958,
|
|
"mean_token_accuracy": 0.1789999470114708,
|
|
"num_tokens": 23381711.0,
|
|
"step": 13475
|
|
},
|
|
{
|
|
"entropy": 5.494165229797363,
|
|
"epoch": 1.0487842832133827,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004894504993430425,
|
|
"loss": 5.2593,
|
|
"mean_token_accuracy": 0.17366714477539064,
|
|
"num_tokens": 23389812.0,
|
|
"step": 13480
|
|
},
|
|
{
|
|
"entropy": 5.5530492782592775,
|
|
"epoch": 1.0491733125851002,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.000489442110602868,
|
|
"loss": 5.3081,
|
|
"mean_token_accuracy": 0.17094554156064987,
|
|
"num_tokens": 23399231.0,
|
|
"step": 13485
|
|
},
|
|
{
|
|
"entropy": 5.487275505065918,
|
|
"epoch": 1.0495623419568176,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.0004894337186088759,
|
|
"loss": 5.2841,
|
|
"mean_token_accuracy": 0.1659332662820816,
|
|
"num_tokens": 23407764.0,
|
|
"step": 13490
|
|
},
|
|
{
|
|
"entropy": 5.5286774158477785,
|
|
"epoch": 1.0499513713285353,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.0004894253233611934,
|
|
"loss": 5.2446,
|
|
"mean_token_accuracy": 0.1730544626712799,
|
|
"num_tokens": 23416368.0,
|
|
"step": 13495
|
|
},
|
|
{
|
|
"entropy": 5.639736795425415,
|
|
"epoch": 1.0503404007002528,
|
|
"grad_norm": 2.4375,
|
|
"learning_rate": 0.000489416924859948,
|
|
"loss": 5.4894,
|
|
"mean_token_accuracy": 0.16800302565097808,
|
|
"num_tokens": 23425415.0,
|
|
"step": 13500
|
|
},
|
|
{
|
|
"entropy": 5.536448860168457,
|
|
"epoch": 1.0507294300719705,
|
|
"grad_norm": 1.84375,
|
|
"learning_rate": 0.000489408523105267,
|
|
"loss": 5.2872,
|
|
"mean_token_accuracy": 0.1671121671795845,
|
|
"num_tokens": 23433435.0,
|
|
"step": 13505
|
|
},
|
|
{
|
|
"entropy": 5.552934885025024,
|
|
"epoch": 1.051118459443688,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004894001180972779,
|
|
"loss": 5.3458,
|
|
"mean_token_accuracy": 0.16198213696479796,
|
|
"num_tokens": 23442002.0,
|
|
"step": 13510
|
|
},
|
|
{
|
|
"entropy": 5.460280799865723,
|
|
"epoch": 1.0515074888154055,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004893917098361082,
|
|
"loss": 5.129,
|
|
"mean_token_accuracy": 0.17113102972507477,
|
|
"num_tokens": 23450437.0,
|
|
"step": 13515
|
|
},
|
|
{
|
|
"entropy": 5.430174255371094,
|
|
"epoch": 1.0518965181871232,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004893832983218856,
|
|
"loss": 5.2445,
|
|
"mean_token_accuracy": 0.1798498347401619,
|
|
"num_tokens": 23458755.0,
|
|
"step": 13520
|
|
},
|
|
{
|
|
"entropy": 5.521679639816284,
|
|
"epoch": 1.0522855475588406,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.0004893748835547377,
|
|
"loss": 5.3737,
|
|
"mean_token_accuracy": 0.16954777538776397,
|
|
"num_tokens": 23467138.0,
|
|
"step": 13525
|
|
},
|
|
{
|
|
"entropy": 5.526899528503418,
|
|
"epoch": 1.0526745769305583,
|
|
"grad_norm": 1.9296875,
|
|
"learning_rate": 0.0004893664655347921,
|
|
"loss": 5.2156,
|
|
"mean_token_accuracy": 0.18104494959115983,
|
|
"num_tokens": 23475494.0,
|
|
"step": 13530
|
|
},
|
|
{
|
|
"entropy": 5.476758813858032,
|
|
"epoch": 1.0530636063022758,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004893580442621767,
|
|
"loss": 5.1712,
|
|
"mean_token_accuracy": 0.1776981845498085,
|
|
"num_tokens": 23484215.0,
|
|
"step": 13535
|
|
},
|
|
{
|
|
"entropy": 5.448919153213501,
|
|
"epoch": 1.0534526356739935,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.000489349619737019,
|
|
"loss": 5.2794,
|
|
"mean_token_accuracy": 0.1688210740685463,
|
|
"num_tokens": 23492604.0,
|
|
"step": 13540
|
|
},
|
|
{
|
|
"entropy": 5.625758361816406,
|
|
"epoch": 1.053841665045711,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.000489341191959447,
|
|
"loss": 5.5158,
|
|
"mean_token_accuracy": 0.16465489864349364,
|
|
"num_tokens": 23501817.0,
|
|
"step": 13545
|
|
},
|
|
{
|
|
"entropy": 5.688231372833252,
|
|
"epoch": 1.0542306944174284,
|
|
"grad_norm": 1.8984375,
|
|
"learning_rate": 0.0004893327609295887,
|
|
"loss": 5.3976,
|
|
"mean_token_accuracy": 0.166701802611351,
|
|
"num_tokens": 23509996.0,
|
|
"step": 13550
|
|
},
|
|
{
|
|
"entropy": 5.488688516616821,
|
|
"epoch": 1.0546197237891461,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.0004893243266475719,
|
|
"loss": 5.1279,
|
|
"mean_token_accuracy": 0.18925662487745284,
|
|
"num_tokens": 23518316.0,
|
|
"step": 13555
|
|
},
|
|
{
|
|
"entropy": 5.438503170013428,
|
|
"epoch": 1.0550087531608636,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.0004893158891135245,
|
|
"loss": 5.3466,
|
|
"mean_token_accuracy": 0.17034787386655809,
|
|
"num_tokens": 23526851.0,
|
|
"step": 13560
|
|
},
|
|
{
|
|
"entropy": 5.599426221847534,
|
|
"epoch": 1.055397782532581,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004893074483275746,
|
|
"loss": 5.2417,
|
|
"mean_token_accuracy": 0.17986735254526137,
|
|
"num_tokens": 23534757.0,
|
|
"step": 13565
|
|
},
|
|
{
|
|
"entropy": 5.533323001861572,
|
|
"epoch": 1.0557868119042988,
|
|
"grad_norm": 1.9921875,
|
|
"learning_rate": 0.0004892990042898503,
|
|
"loss": 5.317,
|
|
"mean_token_accuracy": 0.16803385317325592,
|
|
"num_tokens": 23544102.0,
|
|
"step": 13570
|
|
},
|
|
{
|
|
"entropy": 5.498766088485718,
|
|
"epoch": 1.0561758412760163,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 0.0004892905570004798,
|
|
"loss": 5.3716,
|
|
"mean_token_accuracy": 0.1609747067093849,
|
|
"num_tokens": 23552663.0,
|
|
"step": 13575
|
|
},
|
|
{
|
|
"entropy": 5.548025035858155,
|
|
"epoch": 1.056564870647734,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.000489282106459591,
|
|
"loss": 5.261,
|
|
"mean_token_accuracy": 0.17763492316007615,
|
|
"num_tokens": 23561144.0,
|
|
"step": 13580
|
|
},
|
|
{
|
|
"entropy": 5.489684057235718,
|
|
"epoch": 1.0569539000194514,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0004892736526673124,
|
|
"loss": 5.2252,
|
|
"mean_token_accuracy": 0.17533099055290222,
|
|
"num_tokens": 23569833.0,
|
|
"step": 13585
|
|
},
|
|
{
|
|
"entropy": 5.490369081497192,
|
|
"epoch": 1.0573429293911691,
|
|
"grad_norm": 1.9921875,
|
|
"learning_rate": 0.0004892651956237721,
|
|
"loss": 5.2939,
|
|
"mean_token_accuracy": 0.16659164279699326,
|
|
"num_tokens": 23578643.0,
|
|
"step": 13590
|
|
},
|
|
{
|
|
"entropy": 5.571764039993286,
|
|
"epoch": 1.0577319587628866,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004892567353290986,
|
|
"loss": 5.3916,
|
|
"mean_token_accuracy": 0.16605135798454285,
|
|
"num_tokens": 23587324.0,
|
|
"step": 13595
|
|
},
|
|
{
|
|
"entropy": 5.539520597457885,
|
|
"epoch": 1.058120988134604,
|
|
"grad_norm": 1.9609375,
|
|
"learning_rate": 0.0004892482717834201,
|
|
"loss": 5.3228,
|
|
"mean_token_accuracy": 0.16938469856977462,
|
|
"num_tokens": 23595670.0,
|
|
"step": 13600
|
|
},
|
|
{
|
|
"entropy": 5.527829551696778,
|
|
"epoch": 1.0585100175063218,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004892398049868651,
|
|
"loss": 5.2215,
|
|
"mean_token_accuracy": 0.18556489795446396,
|
|
"num_tokens": 23603833.0,
|
|
"step": 13605
|
|
},
|
|
{
|
|
"entropy": 5.548771095275879,
|
|
"epoch": 1.0588990468780393,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.000489231334939562,
|
|
"loss": 5.3121,
|
|
"mean_token_accuracy": 0.16952638179063798,
|
|
"num_tokens": 23612815.0,
|
|
"step": 13610
|
|
},
|
|
{
|
|
"entropy": 5.550862836837768,
|
|
"epoch": 1.059288076249757,
|
|
"grad_norm": 1.84375,
|
|
"learning_rate": 0.0004892228616416395,
|
|
"loss": 5.3338,
|
|
"mean_token_accuracy": 0.16514284014701844,
|
|
"num_tokens": 23621178.0,
|
|
"step": 13615
|
|
},
|
|
{
|
|
"entropy": 5.519290113449097,
|
|
"epoch": 1.0596771056214744,
|
|
"grad_norm": 1.921875,
|
|
"learning_rate": 0.0004892143850932259,
|
|
"loss": 5.5217,
|
|
"mean_token_accuracy": 0.1620602086186409,
|
|
"num_tokens": 23630681.0,
|
|
"step": 13620
|
|
},
|
|
{
|
|
"entropy": 5.610091304779052,
|
|
"epoch": 1.060066134993192,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.00048920590529445,
|
|
"loss": 5.2906,
|
|
"mean_token_accuracy": 0.17381037920713424,
|
|
"num_tokens": 23639374.0,
|
|
"step": 13625
|
|
},
|
|
{
|
|
"entropy": 5.5493511199951175,
|
|
"epoch": 1.0604551643649096,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004891974222454406,
|
|
"loss": 5.3158,
|
|
"mean_token_accuracy": 0.16927194893360137,
|
|
"num_tokens": 23648217.0,
|
|
"step": 13630
|
|
},
|
|
{
|
|
"entropy": 5.546140384674072,
|
|
"epoch": 1.060844193736627,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0004891889359463261,
|
|
"loss": 5.2912,
|
|
"mean_token_accuracy": 0.17525749206542968,
|
|
"num_tokens": 23656688.0,
|
|
"step": 13635
|
|
},
|
|
{
|
|
"entropy": 5.519538307189942,
|
|
"epoch": 1.0612332231083448,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.0004891804463972354,
|
|
"loss": 5.3856,
|
|
"mean_token_accuracy": 0.17082139402627944,
|
|
"num_tokens": 23666646.0,
|
|
"step": 13640
|
|
},
|
|
{
|
|
"entropy": 5.506044149398804,
|
|
"epoch": 1.0616222524800623,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.0004891719535982974,
|
|
"loss": 5.2685,
|
|
"mean_token_accuracy": 0.1757483959197998,
|
|
"num_tokens": 23675278.0,
|
|
"step": 13645
|
|
},
|
|
{
|
|
"entropy": 5.5799956798553465,
|
|
"epoch": 1.0620112818517797,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004891634575496408,
|
|
"loss": 5.3718,
|
|
"mean_token_accuracy": 0.16496569961309432,
|
|
"num_tokens": 23684263.0,
|
|
"step": 13650
|
|
},
|
|
{
|
|
"entropy": 5.533175611495972,
|
|
"epoch": 1.0624003112234974,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004891549582513946,
|
|
"loss": 5.1949,
|
|
"mean_token_accuracy": 0.1763758271932602,
|
|
"num_tokens": 23692249.0,
|
|
"step": 13655
|
|
},
|
|
{
|
|
"entropy": 5.519052743911743,
|
|
"epoch": 1.062789340595215,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.000489146455703688,
|
|
"loss": 5.4316,
|
|
"mean_token_accuracy": 0.16579757630825043,
|
|
"num_tokens": 23701082.0,
|
|
"step": 13660
|
|
},
|
|
{
|
|
"entropy": 5.511084318161011,
|
|
"epoch": 1.0631783699669326,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.0004891379499066495,
|
|
"loss": 5.3888,
|
|
"mean_token_accuracy": 0.16003262400627136,
|
|
"num_tokens": 23710277.0,
|
|
"step": 13665
|
|
},
|
|
{
|
|
"entropy": 5.591446256637573,
|
|
"epoch": 1.06356739933865,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004891294408604087,
|
|
"loss": 5.3262,
|
|
"mean_token_accuracy": 0.17292562425136565,
|
|
"num_tokens": 23719131.0,
|
|
"step": 13670
|
|
},
|
|
{
|
|
"entropy": 5.529497766494751,
|
|
"epoch": 1.0639564287103676,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004891209285650942,
|
|
"loss": 5.2515,
|
|
"mean_token_accuracy": 0.16838730722665787,
|
|
"num_tokens": 23727674.0,
|
|
"step": 13675
|
|
},
|
|
{
|
|
"entropy": 5.542909049987793,
|
|
"epoch": 1.0643454580820852,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004891124130208355,
|
|
"loss": 5.3917,
|
|
"mean_token_accuracy": 0.16422800868749618,
|
|
"num_tokens": 23736181.0,
|
|
"step": 13680
|
|
},
|
|
{
|
|
"entropy": 5.493327903747558,
|
|
"epoch": 1.0647344874538027,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004891038942277618,
|
|
"loss": 5.2803,
|
|
"mean_token_accuracy": 0.17243594080209732,
|
|
"num_tokens": 23744552.0,
|
|
"step": 13685
|
|
},
|
|
{
|
|
"entropy": 5.603013706207276,
|
|
"epoch": 1.0651235168255204,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.0004890953721860022,
|
|
"loss": 5.4232,
|
|
"mean_token_accuracy": 0.15965529829263686,
|
|
"num_tokens": 23753755.0,
|
|
"step": 13690
|
|
},
|
|
{
|
|
"entropy": 5.551307678222656,
|
|
"epoch": 1.065512546197238,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004890868468956862,
|
|
"loss": 5.3168,
|
|
"mean_token_accuracy": 0.17368309795856476,
|
|
"num_tokens": 23761759.0,
|
|
"step": 13695
|
|
},
|
|
{
|
|
"entropy": 5.498054885864258,
|
|
"epoch": 1.0659015755689554,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.000489078318356943,
|
|
"loss": 5.3209,
|
|
"mean_token_accuracy": 0.16459089070558547,
|
|
"num_tokens": 23769952.0,
|
|
"step": 13700
|
|
},
|
|
{
|
|
"entropy": 5.510284090042115,
|
|
"epoch": 1.066290604940673,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004890697865699021,
|
|
"loss": 5.3246,
|
|
"mean_token_accuracy": 0.17355043739080428,
|
|
"num_tokens": 23778045.0,
|
|
"step": 13705
|
|
},
|
|
{
|
|
"entropy": 5.598343563079834,
|
|
"epoch": 1.0666796343123905,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.0004890612515346929,
|
|
"loss": 5.2972,
|
|
"mean_token_accuracy": 0.16458800286054612,
|
|
"num_tokens": 23787477.0,
|
|
"step": 13710
|
|
},
|
|
{
|
|
"entropy": 5.543606758117676,
|
|
"epoch": 1.0670686636841082,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004890527132514448,
|
|
"loss": 5.2742,
|
|
"mean_token_accuracy": 0.1778631791472435,
|
|
"num_tokens": 23795905.0,
|
|
"step": 13715
|
|
},
|
|
{
|
|
"entropy": 5.582602167129517,
|
|
"epoch": 1.0674576930558257,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.0004890441717202876,
|
|
"loss": 5.3556,
|
|
"mean_token_accuracy": 0.17180385887622834,
|
|
"num_tokens": 23804339.0,
|
|
"step": 13720
|
|
},
|
|
{
|
|
"entropy": 5.527411699295044,
|
|
"epoch": 1.0678467224275432,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004890356269413507,
|
|
"loss": 5.3629,
|
|
"mean_token_accuracy": 0.1620781749486923,
|
|
"num_tokens": 23813032.0,
|
|
"step": 13725
|
|
},
|
|
{
|
|
"entropy": 5.546605014801026,
|
|
"epoch": 1.068235751799261,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.000489027078914764,
|
|
"loss": 5.2527,
|
|
"mean_token_accuracy": 0.18358878940343856,
|
|
"num_tokens": 23822047.0,
|
|
"step": 13730
|
|
},
|
|
{
|
|
"entropy": 5.436023426055908,
|
|
"epoch": 1.0686247811709784,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004890185276406569,
|
|
"loss": 5.2346,
|
|
"mean_token_accuracy": 0.17424950748682022,
|
|
"num_tokens": 23831220.0,
|
|
"step": 13735
|
|
},
|
|
{
|
|
"entropy": 5.485828590393067,
|
|
"epoch": 1.069013810542696,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004890099731191592,
|
|
"loss": 5.3814,
|
|
"mean_token_accuracy": 0.16473645269870757,
|
|
"num_tokens": 23840118.0,
|
|
"step": 13740
|
|
},
|
|
{
|
|
"entropy": 5.561111402511597,
|
|
"epoch": 1.0694028399144135,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.000489001415350401,
|
|
"loss": 5.3398,
|
|
"mean_token_accuracy": 0.1681963786482811,
|
|
"num_tokens": 23848826.0,
|
|
"step": 13745
|
|
},
|
|
{
|
|
"entropy": 5.640467834472656,
|
|
"epoch": 1.069791869286131,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004889928543345118,
|
|
"loss": 5.4526,
|
|
"mean_token_accuracy": 0.1646828055381775,
|
|
"num_tokens": 23857462.0,
|
|
"step": 13750
|
|
},
|
|
{
|
|
"entropy": 5.524610567092895,
|
|
"epoch": 1.0701808986578487,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004889842900716217,
|
|
"loss": 5.3067,
|
|
"mean_token_accuracy": 0.1701535239815712,
|
|
"num_tokens": 23866842.0,
|
|
"step": 13755
|
|
},
|
|
{
|
|
"entropy": 5.5305116176605225,
|
|
"epoch": 1.0705699280295662,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004889757225618606,
|
|
"loss": 5.3539,
|
|
"mean_token_accuracy": 0.16610678285360336,
|
|
"num_tokens": 23875079.0,
|
|
"step": 13760
|
|
},
|
|
{
|
|
"entropy": 5.589465188980102,
|
|
"epoch": 1.0709589574012839,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004889671518053584,
|
|
"loss": 5.2968,
|
|
"mean_token_accuracy": 0.1696449860930443,
|
|
"num_tokens": 23883963.0,
|
|
"step": 13765
|
|
},
|
|
{
|
|
"entropy": 5.517028760910034,
|
|
"epoch": 1.0713479867730014,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.0004889585778022453,
|
|
"loss": 5.2828,
|
|
"mean_token_accuracy": 0.1754229560494423,
|
|
"num_tokens": 23892709.0,
|
|
"step": 13770
|
|
},
|
|
{
|
|
"entropy": 5.547016382217407,
|
|
"epoch": 1.0717370161447188,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004889500005526514,
|
|
"loss": 5.4254,
|
|
"mean_token_accuracy": 0.16663182601332666,
|
|
"num_tokens": 23901124.0,
|
|
"step": 13775
|
|
},
|
|
{
|
|
"entropy": 5.576437950134277,
|
|
"epoch": 1.0721260455164365,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004889414200567067,
|
|
"loss": 5.3612,
|
|
"mean_token_accuracy": 0.16628114134073257,
|
|
"num_tokens": 23909442.0,
|
|
"step": 13780
|
|
},
|
|
{
|
|
"entropy": 5.554904842376709,
|
|
"epoch": 1.072515074888154,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004889328363145415,
|
|
"loss": 5.3222,
|
|
"mean_token_accuracy": 0.17079944610595704,
|
|
"num_tokens": 23918143.0,
|
|
"step": 13785
|
|
},
|
|
{
|
|
"entropy": 5.547575569152832,
|
|
"epoch": 1.0729041042598717,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004889242493262859,
|
|
"loss": 5.2872,
|
|
"mean_token_accuracy": 0.17710011452436447,
|
|
"num_tokens": 23926432.0,
|
|
"step": 13790
|
|
},
|
|
{
|
|
"entropy": 5.57346773147583,
|
|
"epoch": 1.0732931336315892,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.0004889156590920704,
|
|
"loss": 5.419,
|
|
"mean_token_accuracy": 0.16299348920583726,
|
|
"num_tokens": 23935362.0,
|
|
"step": 13795
|
|
},
|
|
{
|
|
"entropy": 5.424457740783692,
|
|
"epoch": 1.0736821630033067,
|
|
"grad_norm": 1.96875,
|
|
"learning_rate": 0.0004889070656120253,
|
|
"loss": 5.1752,
|
|
"mean_token_accuracy": 0.17433948516845704,
|
|
"num_tokens": 23943926.0,
|
|
"step": 13800
|
|
},
|
|
{
|
|
"entropy": 5.547138786315918,
|
|
"epoch": 1.0740711923750244,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.0004888984688862809,
|
|
"loss": 5.3232,
|
|
"mean_token_accuracy": 0.17381875067949296,
|
|
"num_tokens": 23952513.0,
|
|
"step": 13805
|
|
},
|
|
{
|
|
"entropy": 5.546496057510376,
|
|
"epoch": 1.0744602217467418,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.0004888898689149677,
|
|
"loss": 5.3708,
|
|
"mean_token_accuracy": 0.16427473425865174,
|
|
"num_tokens": 23961529.0,
|
|
"step": 13810
|
|
},
|
|
{
|
|
"entropy": 5.668095874786377,
|
|
"epoch": 1.0748492511184595,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004888812656982162,
|
|
"loss": 5.4278,
|
|
"mean_token_accuracy": 0.1626336991786957,
|
|
"num_tokens": 23971156.0,
|
|
"step": 13815
|
|
},
|
|
{
|
|
"entropy": 5.582630729675293,
|
|
"epoch": 1.075238280490177,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.0004888726592361569,
|
|
"loss": 5.3064,
|
|
"mean_token_accuracy": 0.16782575249671935,
|
|
"num_tokens": 23979676.0,
|
|
"step": 13820
|
|
},
|
|
{
|
|
"entropy": 5.530002403259277,
|
|
"epoch": 1.0756273098618945,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0004888640495289204,
|
|
"loss": 5.2576,
|
|
"mean_token_accuracy": 0.17889272123575212,
|
|
"num_tokens": 23987764.0,
|
|
"step": 13825
|
|
},
|
|
{
|
|
"entropy": 5.543236923217774,
|
|
"epoch": 1.0760163392336122,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004888554365766374,
|
|
"loss": 5.2987,
|
|
"mean_token_accuracy": 0.1686909705400467,
|
|
"num_tokens": 23995844.0,
|
|
"step": 13830
|
|
},
|
|
{
|
|
"entropy": 5.544515943527221,
|
|
"epoch": 1.0764053686053296,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 0.0004888468203794385,
|
|
"loss": 5.3814,
|
|
"mean_token_accuracy": 0.16718253195285798,
|
|
"num_tokens": 24003824.0,
|
|
"step": 13835
|
|
},
|
|
{
|
|
"entropy": 5.534544324874878,
|
|
"epoch": 1.0767943979770473,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.0004888382009374545,
|
|
"loss": 5.338,
|
|
"mean_token_accuracy": 0.17008200883865357,
|
|
"num_tokens": 24012471.0,
|
|
"step": 13840
|
|
},
|
|
{
|
|
"entropy": 5.537197113037109,
|
|
"epoch": 1.0771834273487648,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004888295782508161,
|
|
"loss": 5.3117,
|
|
"mean_token_accuracy": 0.17573910802602768,
|
|
"num_tokens": 24021344.0,
|
|
"step": 13845
|
|
},
|
|
{
|
|
"entropy": 5.519123125076294,
|
|
"epoch": 1.0775724567204823,
|
|
"grad_norm": 1.9921875,
|
|
"learning_rate": 0.0004888209523196542,
|
|
"loss": 5.2742,
|
|
"mean_token_accuracy": 0.1699921503663063,
|
|
"num_tokens": 24029598.0,
|
|
"step": 13850
|
|
},
|
|
{
|
|
"entropy": 5.493518495559693,
|
|
"epoch": 1.0779614860922,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004888123231440997,
|
|
"loss": 5.3088,
|
|
"mean_token_accuracy": 0.17752090841531754,
|
|
"num_tokens": 24038097.0,
|
|
"step": 13855
|
|
},
|
|
{
|
|
"entropy": 5.544915628433228,
|
|
"epoch": 1.0783505154639175,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.0004888036907242834,
|
|
"loss": 5.3656,
|
|
"mean_token_accuracy": 0.17000244855880736,
|
|
"num_tokens": 24046812.0,
|
|
"step": 13860
|
|
},
|
|
{
|
|
"entropy": 5.571366930007935,
|
|
"epoch": 1.0787395448356352,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.0004887950550603366,
|
|
"loss": 5.3265,
|
|
"mean_token_accuracy": 0.17285169810056686,
|
|
"num_tokens": 24054908.0,
|
|
"step": 13865
|
|
},
|
|
{
|
|
"entropy": 5.487083053588867,
|
|
"epoch": 1.0791285742073526,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.0004887864161523901,
|
|
"loss": 5.3062,
|
|
"mean_token_accuracy": 0.17101576626300813,
|
|
"num_tokens": 24063695.0,
|
|
"step": 13870
|
|
},
|
|
{
|
|
"entropy": 5.55040979385376,
|
|
"epoch": 1.0795176035790701,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0004887777740005749,
|
|
"loss": 5.3198,
|
|
"mean_token_accuracy": 0.17476630955934525,
|
|
"num_tokens": 24072481.0,
|
|
"step": 13875
|
|
},
|
|
{
|
|
"entropy": 5.495706701278687,
|
|
"epoch": 1.0799066329507878,
|
|
"grad_norm": 1.875,
|
|
"learning_rate": 0.0004887691286050224,
|
|
"loss": 5.3031,
|
|
"mean_token_accuracy": 0.17353216111660003,
|
|
"num_tokens": 24080751.0,
|
|
"step": 13880
|
|
},
|
|
{
|
|
"entropy": 5.494110059738159,
|
|
"epoch": 1.0802956623225053,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004887604799658635,
|
|
"loss": 5.3031,
|
|
"mean_token_accuracy": 0.1741626441478729,
|
|
"num_tokens": 24088618.0,
|
|
"step": 13885
|
|
},
|
|
{
|
|
"entropy": 5.5444908618927,
|
|
"epoch": 1.080684691694223,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004887518280832295,
|
|
"loss": 5.3701,
|
|
"mean_token_accuracy": 0.16689498722553253,
|
|
"num_tokens": 24096754.0,
|
|
"step": 13890
|
|
},
|
|
{
|
|
"entropy": 5.538621997833252,
|
|
"epoch": 1.0810737210659405,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004887431729572519,
|
|
"loss": 5.3311,
|
|
"mean_token_accuracy": 0.17545728087425233,
|
|
"num_tokens": 24104793.0,
|
|
"step": 13895
|
|
},
|
|
{
|
|
"entropy": 5.660008478164673,
|
|
"epoch": 1.081462750437658,
|
|
"grad_norm": 2.46875,
|
|
"learning_rate": 0.0004887345145880617,
|
|
"loss": 5.4753,
|
|
"mean_token_accuracy": 0.15550873130559922,
|
|
"num_tokens": 24113816.0,
|
|
"step": 13900
|
|
},
|
|
{
|
|
"entropy": 5.5120923042297365,
|
|
"epoch": 1.0818517798093756,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004887258529757904,
|
|
"loss": 5.2377,
|
|
"mean_token_accuracy": 0.17260441929101944,
|
|
"num_tokens": 24123002.0,
|
|
"step": 13905
|
|
},
|
|
{
|
|
"entropy": 5.5679949760437015,
|
|
"epoch": 1.082240809181093,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.0004887171881205696,
|
|
"loss": 5.3006,
|
|
"mean_token_accuracy": 0.1716482862830162,
|
|
"num_tokens": 24130841.0,
|
|
"step": 13910
|
|
},
|
|
{
|
|
"entropy": 5.534440612792968,
|
|
"epoch": 1.0826298385528108,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.0004887085200225306,
|
|
"loss": 5.3576,
|
|
"mean_token_accuracy": 0.16980937719345093,
|
|
"num_tokens": 24139236.0,
|
|
"step": 13915
|
|
},
|
|
{
|
|
"entropy": 5.519405746459961,
|
|
"epoch": 1.0830188679245283,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.0004886998486818049,
|
|
"loss": 5.2359,
|
|
"mean_token_accuracy": 0.17444780021905898,
|
|
"num_tokens": 24147824.0,
|
|
"step": 13920
|
|
},
|
|
{
|
|
"entropy": 5.5440919399261475,
|
|
"epoch": 1.083407897296246,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004886911740985242,
|
|
"loss": 5.3509,
|
|
"mean_token_accuracy": 0.1725696936249733,
|
|
"num_tokens": 24156555.0,
|
|
"step": 13925
|
|
},
|
|
{
|
|
"entropy": 5.597066736221313,
|
|
"epoch": 1.0837969266679635,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.00048868249627282,
|
|
"loss": 5.2853,
|
|
"mean_token_accuracy": 0.17199783474206926,
|
|
"num_tokens": 24164424.0,
|
|
"step": 13930
|
|
},
|
|
{
|
|
"entropy": 5.56901216506958,
|
|
"epoch": 1.084185956039681,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.000488673815204824,
|
|
"loss": 5.3072,
|
|
"mean_token_accuracy": 0.17326202541589736,
|
|
"num_tokens": 24173325.0,
|
|
"step": 13935
|
|
},
|
|
{
|
|
"entropy": 5.60181303024292,
|
|
"epoch": 1.0845749854113986,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.0004886651308946681,
|
|
"loss": 5.4628,
|
|
"mean_token_accuracy": 0.16134414970874786,
|
|
"num_tokens": 24181781.0,
|
|
"step": 13940
|
|
},
|
|
{
|
|
"entropy": 5.569963502883911,
|
|
"epoch": 1.084964014783116,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004886564433424839,
|
|
"loss": 5.2527,
|
|
"mean_token_accuracy": 0.17445340603590012,
|
|
"num_tokens": 24190065.0,
|
|
"step": 13945
|
|
},
|
|
{
|
|
"entropy": 5.602535581588745,
|
|
"epoch": 1.0853530441548336,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.0004886477525484032,
|
|
"loss": 5.4105,
|
|
"mean_token_accuracy": 0.1641104206442833,
|
|
"num_tokens": 24198814.0,
|
|
"step": 13950
|
|
},
|
|
{
|
|
"entropy": 5.509954214096069,
|
|
"epoch": 1.0857420735265513,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004886390585125579,
|
|
"loss": 5.2907,
|
|
"mean_token_accuracy": 0.16721510142087936,
|
|
"num_tokens": 24208008.0,
|
|
"step": 13955
|
|
},
|
|
{
|
|
"entropy": 5.568111801147461,
|
|
"epoch": 1.0861311028982688,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0004886303612350799,
|
|
"loss": 5.3003,
|
|
"mean_token_accuracy": 0.17392658889293672,
|
|
"num_tokens": 24216098.0,
|
|
"step": 13960
|
|
},
|
|
{
|
|
"entropy": 5.444877672195434,
|
|
"epoch": 1.0865201322699864,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004886216607161013,
|
|
"loss": 5.2432,
|
|
"mean_token_accuracy": 0.17455094009637834,
|
|
"num_tokens": 24224943.0,
|
|
"step": 13965
|
|
},
|
|
{
|
|
"entropy": 5.497115564346314,
|
|
"epoch": 1.086909161641704,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.0004886129569557538,
|
|
"loss": 5.3063,
|
|
"mean_token_accuracy": 0.16339687407016754,
|
|
"num_tokens": 24232950.0,
|
|
"step": 13970
|
|
},
|
|
{
|
|
"entropy": 5.599544334411621,
|
|
"epoch": 1.0872981910134216,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004886042499541699,
|
|
"loss": 5.4389,
|
|
"mean_token_accuracy": 0.16725558042526245,
|
|
"num_tokens": 24242355.0,
|
|
"step": 13975
|
|
},
|
|
{
|
|
"entropy": 5.519319105148315,
|
|
"epoch": 1.087687220385139,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004885955397114813,
|
|
"loss": 5.2966,
|
|
"mean_token_accuracy": 0.1744234025478363,
|
|
"num_tokens": 24251247.0,
|
|
"step": 13980
|
|
},
|
|
{
|
|
"entropy": 5.496453046798706,
|
|
"epoch": 1.0880762497568566,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004885868262278205,
|
|
"loss": 5.3618,
|
|
"mean_token_accuracy": 0.1670030727982521,
|
|
"num_tokens": 24260281.0,
|
|
"step": 13985
|
|
},
|
|
{
|
|
"entropy": 5.629408931732177,
|
|
"epoch": 1.0884652791285743,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.0004885781095033195,
|
|
"loss": 5.4018,
|
|
"mean_token_accuracy": 0.16499805599451065,
|
|
"num_tokens": 24268474.0,
|
|
"step": 13990
|
|
},
|
|
{
|
|
"entropy": 5.594612741470337,
|
|
"epoch": 1.0888543085002917,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004885693895381108,
|
|
"loss": 5.3295,
|
|
"mean_token_accuracy": 0.1741635948419571,
|
|
"num_tokens": 24276897.0,
|
|
"step": 13995
|
|
},
|
|
{
|
|
"entropy": 5.562593650817871,
|
|
"epoch": 1.0892433378720092,
|
|
"grad_norm": 2.3125,
|
|
"learning_rate": 0.0004885606663323263,
|
|
"loss": 5.3202,
|
|
"mean_token_accuracy": 0.1684825450181961,
|
|
"num_tokens": 24285892.0,
|
|
"step": 14000
|
|
},
|
|
{
|
|
"entropy": 5.516541528701782,
|
|
"epoch": 1.089632367243727,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.0004885519398860987,
|
|
"loss": 5.376,
|
|
"mean_token_accuracy": 0.1690691128373146,
|
|
"num_tokens": 24294141.0,
|
|
"step": 14005
|
|
},
|
|
{
|
|
"entropy": 5.440137481689453,
|
|
"epoch": 1.0900213966154444,
|
|
"grad_norm": 1.875,
|
|
"learning_rate": 0.0004885432101995604,
|
|
"loss": 5.2852,
|
|
"mean_token_accuracy": 0.17104621529579161,
|
|
"num_tokens": 24302803.0,
|
|
"step": 14010
|
|
},
|
|
{
|
|
"entropy": 5.662224531173706,
|
|
"epoch": 1.090410425987162,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.0004885344772728436,
|
|
"loss": 5.456,
|
|
"mean_token_accuracy": 0.16429179161787033,
|
|
"num_tokens": 24311755.0,
|
|
"step": 14015
|
|
},
|
|
{
|
|
"entropy": 5.5629510402679445,
|
|
"epoch": 1.0907994553588796,
|
|
"grad_norm": 1.9296875,
|
|
"learning_rate": 0.0004885257411060812,
|
|
"loss": 5.2736,
|
|
"mean_token_accuracy": 0.17992735803127288,
|
|
"num_tokens": 24320913.0,
|
|
"step": 14020
|
|
},
|
|
{
|
|
"entropy": 5.6122242450714115,
|
|
"epoch": 1.0911884847305973,
|
|
"grad_norm": 2.234375,
|
|
"learning_rate": 0.0004885170016994053,
|
|
"loss": 5.4634,
|
|
"mean_token_accuracy": 0.16216795593500138,
|
|
"num_tokens": 24331112.0,
|
|
"step": 14025
|
|
},
|
|
{
|
|
"entropy": 5.501348447799683,
|
|
"epoch": 1.0915775141023147,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.0004885082590529489,
|
|
"loss": 5.2428,
|
|
"mean_token_accuracy": 0.17210256457328796,
|
|
"num_tokens": 24339286.0,
|
|
"step": 14030
|
|
},
|
|
{
|
|
"entropy": 5.490026330947876,
|
|
"epoch": 1.0919665434740322,
|
|
"grad_norm": 2.328125,
|
|
"learning_rate": 0.0004884995131668445,
|
|
"loss": 5.259,
|
|
"mean_token_accuracy": 0.17423467487096786,
|
|
"num_tokens": 24347787.0,
|
|
"step": 14035
|
|
},
|
|
{
|
|
"entropy": 5.561874198913574,
|
|
"epoch": 1.09235557284575,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.0004884907640412248,
|
|
"loss": 5.241,
|
|
"mean_token_accuracy": 0.17780353277921676,
|
|
"num_tokens": 24356340.0,
|
|
"step": 14040
|
|
},
|
|
{
|
|
"entropy": 5.600111770629883,
|
|
"epoch": 1.0927446022174674,
|
|
"grad_norm": 2.40625,
|
|
"learning_rate": 0.0004884820116762225,
|
|
"loss": 5.3192,
|
|
"mean_token_accuracy": 0.16375503838062286,
|
|
"num_tokens": 24365182.0,
|
|
"step": 14045
|
|
},
|
|
{
|
|
"entropy": 5.6121917247772215,
|
|
"epoch": 1.093133631589185,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.0004884732560719706,
|
|
"loss": 5.359,
|
|
"mean_token_accuracy": 0.1658143848180771,
|
|
"num_tokens": 24373455.0,
|
|
"step": 14050
|
|
},
|
|
{
|
|
"entropy": 5.588863277435303,
|
|
"epoch": 1.0935226609609026,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.0004884644972286017,
|
|
"loss": 5.4197,
|
|
"mean_token_accuracy": 0.1676062151789665,
|
|
"num_tokens": 24382433.0,
|
|
"step": 14055
|
|
},
|
|
{
|
|
"entropy": 5.498603677749633,
|
|
"epoch": 1.09391169033262,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.0004884557351462488,
|
|
"loss": 5.2391,
|
|
"mean_token_accuracy": 0.17488151639699936,
|
|
"num_tokens": 24390971.0,
|
|
"step": 14060
|
|
},
|
|
{
|
|
"entropy": 5.5869687557220455,
|
|
"epoch": 1.0943007197043377,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004884469698250449,
|
|
"loss": 5.319,
|
|
"mean_token_accuracy": 0.16738669574260712,
|
|
"num_tokens": 24399508.0,
|
|
"step": 14065
|
|
},
|
|
{
|
|
"entropy": 5.536074638366699,
|
|
"epoch": 1.0946897490760552,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 0.000488438201265123,
|
|
"loss": 5.2706,
|
|
"mean_token_accuracy": 0.16931046694517135,
|
|
"num_tokens": 24408424.0,
|
|
"step": 14070
|
|
},
|
|
{
|
|
"entropy": 5.451840448379516,
|
|
"epoch": 1.095078778447773,
|
|
"grad_norm": 1.8984375,
|
|
"learning_rate": 0.0004884294294666161,
|
|
"loss": 5.3739,
|
|
"mean_token_accuracy": 0.16374844014644624,
|
|
"num_tokens": 24416918.0,
|
|
"step": 14075
|
|
},
|
|
{
|
|
"entropy": 5.520238304138184,
|
|
"epoch": 1.0954678078194904,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.0004884206544296573,
|
|
"loss": 5.2216,
|
|
"mean_token_accuracy": 0.17465755790472032,
|
|
"num_tokens": 24425779.0,
|
|
"step": 14080
|
|
},
|
|
{
|
|
"entropy": 5.45942006111145,
|
|
"epoch": 1.0958568371912079,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004884118761543797,
|
|
"loss": 5.2683,
|
|
"mean_token_accuracy": 0.177483731508255,
|
|
"num_tokens": 24434567.0,
|
|
"step": 14085
|
|
},
|
|
{
|
|
"entropy": 5.470007038116455,
|
|
"epoch": 1.0962458665629256,
|
|
"grad_norm": 1.96875,
|
|
"learning_rate": 0.0004884030946409167,
|
|
"loss": 5.3565,
|
|
"mean_token_accuracy": 0.16683439612388612,
|
|
"num_tokens": 24442980.0,
|
|
"step": 14090
|
|
},
|
|
{
|
|
"entropy": 5.5060585021972654,
|
|
"epoch": 1.096634895934643,
|
|
"grad_norm": 1.9296875,
|
|
"learning_rate": 0.0004883943098894013,
|
|
"loss": 5.2673,
|
|
"mean_token_accuracy": 0.17494895607233046,
|
|
"num_tokens": 24452273.0,
|
|
"step": 14095
|
|
},
|
|
{
|
|
"entropy": 5.612516212463379,
|
|
"epoch": 1.0970239253063607,
|
|
"grad_norm": 1.9765625,
|
|
"learning_rate": 0.000488385521899967,
|
|
"loss": 5.3716,
|
|
"mean_token_accuracy": 0.17370207011699676,
|
|
"num_tokens": 24461854.0,
|
|
"step": 14100
|
|
},
|
|
{
|
|
"entropy": 5.601830339431762,
|
|
"epoch": 1.0974129546780782,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.000488376730672747,
|
|
"loss": 5.4085,
|
|
"mean_token_accuracy": 0.16524589136242868,
|
|
"num_tokens": 24470468.0,
|
|
"step": 14105
|
|
},
|
|
{
|
|
"entropy": 5.507510185241699,
|
|
"epoch": 1.0978019840497957,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004883679362078746,
|
|
"loss": 5.2807,
|
|
"mean_token_accuracy": 0.17569466531276703,
|
|
"num_tokens": 24479282.0,
|
|
"step": 14110
|
|
},
|
|
{
|
|
"entropy": 5.561517429351807,
|
|
"epoch": 1.0981910134215134,
|
|
"grad_norm": 2.296875,
|
|
"learning_rate": 0.0004883591385054836,
|
|
"loss": 5.3392,
|
|
"mean_token_accuracy": 0.17581553757190704,
|
|
"num_tokens": 24487331.0,
|
|
"step": 14115
|
|
},
|
|
{
|
|
"entropy": 5.52597827911377,
|
|
"epoch": 1.0985800427932308,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004883503375657072,
|
|
"loss": 5.269,
|
|
"mean_token_accuracy": 0.17624805718660355,
|
|
"num_tokens": 24496101.0,
|
|
"step": 14120
|
|
},
|
|
{
|
|
"entropy": 5.643872880935669,
|
|
"epoch": 1.0989690721649485,
|
|
"grad_norm": 1.90625,
|
|
"learning_rate": 0.0004883415333886789,
|
|
"loss": 5.3563,
|
|
"mean_token_accuracy": 0.1693339005112648,
|
|
"num_tokens": 24504321.0,
|
|
"step": 14125
|
|
},
|
|
{
|
|
"entropy": 5.5826866149902346,
|
|
"epoch": 1.099358101536666,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.0004883327259745325,
|
|
"loss": 5.2435,
|
|
"mean_token_accuracy": 0.176491180062294,
|
|
"num_tokens": 24511887.0,
|
|
"step": 14130
|
|
},
|
|
{
|
|
"entropy": 5.463118219375611,
|
|
"epoch": 1.0997471309083835,
|
|
"grad_norm": 2.59375,
|
|
"learning_rate": 0.0004883239153234015,
|
|
"loss": 5.2757,
|
|
"mean_token_accuracy": 0.171638822555542,
|
|
"num_tokens": 24521188.0,
|
|
"step": 14135
|
|
},
|
|
{
|
|
"entropy": 5.526982593536377,
|
|
"epoch": 1.1001361602801012,
|
|
"grad_norm": 1.921875,
|
|
"learning_rate": 0.0004883151014354197,
|
|
"loss": 5.2468,
|
|
"mean_token_accuracy": 0.1738795593380928,
|
|
"num_tokens": 24530656.0,
|
|
"step": 14140
|
|
},
|
|
{
|
|
"entropy": 5.511045742034912,
|
|
"epoch": 1.1005251896518187,
|
|
"grad_norm": 1.84375,
|
|
"learning_rate": 0.0004883062843107207,
|
|
"loss": 5.2569,
|
|
"mean_token_accuracy": 0.16837164461612703,
|
|
"num_tokens": 24539438.0,
|
|
"step": 14145
|
|
},
|
|
{
|
|
"entropy": 5.576252222061157,
|
|
"epoch": 1.1009142190235364,
|
|
"grad_norm": 1.96875,
|
|
"learning_rate": 0.0004882974639494383,
|
|
"loss": 5.354,
|
|
"mean_token_accuracy": 0.17138106673955916,
|
|
"num_tokens": 24548005.0,
|
|
"step": 14150
|
|
},
|
|
{
|
|
"entropy": 5.6106963634490965,
|
|
"epoch": 1.1013032483952538,
|
|
"grad_norm": 2.359375,
|
|
"learning_rate": 0.0004882886403517065,
|
|
"loss": 5.3967,
|
|
"mean_token_accuracy": 0.16944039911031722,
|
|
"num_tokens": 24556507.0,
|
|
"step": 14155
|
|
},
|
|
{
|
|
"entropy": 5.52460560798645,
|
|
"epoch": 1.1016922777669713,
|
|
"grad_norm": 2.28125,
|
|
"learning_rate": 0.0004882798135176589,
|
|
"loss": 5.3344,
|
|
"mean_token_accuracy": 0.17049439996480942,
|
|
"num_tokens": 24565228.0,
|
|
"step": 14160
|
|
},
|
|
{
|
|
"entropy": 5.474211311340332,
|
|
"epoch": 1.102081307138689,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.00048827098344742973,
|
|
"loss": 5.2843,
|
|
"mean_token_accuracy": 0.17208753973245622,
|
|
"num_tokens": 24573977.0,
|
|
"step": 14165
|
|
},
|
|
{
|
|
"entropy": 5.49917893409729,
|
|
"epoch": 1.1024703365104065,
|
|
"grad_norm": 1.9140625,
|
|
"learning_rate": 0.0004882621501411528,
|
|
"loss": 5.224,
|
|
"mean_token_accuracy": 0.17466724216938018,
|
|
"num_tokens": 24582897.0,
|
|
"step": 14170
|
|
},
|
|
{
|
|
"entropy": 5.533160257339477,
|
|
"epoch": 1.1028593658821242,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.0004882533135989622,
|
|
"loss": 5.2201,
|
|
"mean_token_accuracy": 0.1758916676044464,
|
|
"num_tokens": 24591132.0,
|
|
"step": 14175
|
|
},
|
|
{
|
|
"entropy": 5.432278823852539,
|
|
"epoch": 1.1032483952538417,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.000488244473820992,
|
|
"loss": 5.2732,
|
|
"mean_token_accuracy": 0.1746155560016632,
|
|
"num_tokens": 24600111.0,
|
|
"step": 14180
|
|
},
|
|
{
|
|
"entropy": 5.497148275375366,
|
|
"epoch": 1.1036374246255591,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.00048823563080737634,
|
|
"loss": 5.3117,
|
|
"mean_token_accuracy": 0.1665785312652588,
|
|
"num_tokens": 24609229.0,
|
|
"step": 14185
|
|
},
|
|
{
|
|
"entropy": 5.531980514526367,
|
|
"epoch": 1.1040264539972768,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004882267845582493,
|
|
"loss": 5.2434,
|
|
"mean_token_accuracy": 0.1705525204539299,
|
|
"num_tokens": 24618012.0,
|
|
"step": 14190
|
|
},
|
|
{
|
|
"entropy": 5.480249357223511,
|
|
"epoch": 1.1044154833689943,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.00048821793507374526,
|
|
"loss": 5.3144,
|
|
"mean_token_accuracy": 0.17153472155332566,
|
|
"num_tokens": 24626801.0,
|
|
"step": 14195
|
|
},
|
|
{
|
|
"entropy": 5.611691093444824,
|
|
"epoch": 1.104804512740712,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004882090823539984,
|
|
"loss": 5.3569,
|
|
"mean_token_accuracy": 0.17281283289194108,
|
|
"num_tokens": 24635365.0,
|
|
"step": 14200
|
|
},
|
|
{
|
|
"entropy": 5.529832553863526,
|
|
"epoch": 1.1051935421124295,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004882002263991431,
|
|
"loss": 5.283,
|
|
"mean_token_accuracy": 0.17273492515087127,
|
|
"num_tokens": 24643745.0,
|
|
"step": 14205
|
|
},
|
|
{
|
|
"entropy": 5.427512788772583,
|
|
"epoch": 1.105582571484147,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.00048819136720931364,
|
|
"loss": 5.2117,
|
|
"mean_token_accuracy": 0.16911209374666214,
|
|
"num_tokens": 24652760.0,
|
|
"step": 14210
|
|
},
|
|
{
|
|
"entropy": 5.516819906234741,
|
|
"epoch": 1.1059716008558647,
|
|
"grad_norm": 3.46875,
|
|
"learning_rate": 0.00048818250478464457,
|
|
"loss": 5.331,
|
|
"mean_token_accuracy": 0.16977904438972474,
|
|
"num_tokens": 24661326.0,
|
|
"step": 14215
|
|
},
|
|
{
|
|
"entropy": 5.577160406112671,
|
|
"epoch": 1.1063606302275821,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004881736391252703,
|
|
"loss": 5.225,
|
|
"mean_token_accuracy": 0.18441488593816757,
|
|
"num_tokens": 24669611.0,
|
|
"step": 14220
|
|
},
|
|
{
|
|
"entropy": 5.550752830505371,
|
|
"epoch": 1.1067496595992998,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004881647702313253,
|
|
"loss": 5.3629,
|
|
"mean_token_accuracy": 0.16810504496097564,
|
|
"num_tokens": 24677780.0,
|
|
"step": 14225
|
|
},
|
|
{
|
|
"entropy": 5.464678955078125,
|
|
"epoch": 1.1071386889710173,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.00048815589810294427,
|
|
"loss": 5.2261,
|
|
"mean_token_accuracy": 0.1713106542825699,
|
|
"num_tokens": 24685807.0,
|
|
"step": 14230
|
|
},
|
|
{
|
|
"entropy": 5.516006565093994,
|
|
"epoch": 1.1075277183427348,
|
|
"grad_norm": 2.46875,
|
|
"learning_rate": 0.00048814702274026174,
|
|
"loss": 5.29,
|
|
"mean_token_accuracy": 0.17232769578695298,
|
|
"num_tokens": 24694383.0,
|
|
"step": 14235
|
|
},
|
|
{
|
|
"entropy": 5.487272930145264,
|
|
"epoch": 1.1079167477144525,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.0004881381441434124,
|
|
"loss": 5.2388,
|
|
"mean_token_accuracy": 0.17909597903490065,
|
|
"num_tokens": 24702325.0,
|
|
"step": 14240
|
|
},
|
|
{
|
|
"entropy": 5.5549072265625,
|
|
"epoch": 1.10830577708617,
|
|
"grad_norm": 1.953125,
|
|
"learning_rate": 0.000488129262312531,
|
|
"loss": 5.2933,
|
|
"mean_token_accuracy": 0.17124199569225312,
|
|
"num_tokens": 24710725.0,
|
|
"step": 14245
|
|
},
|
|
{
|
|
"entropy": 5.496373081207276,
|
|
"epoch": 1.1086948064578876,
|
|
"grad_norm": 1.875,
|
|
"learning_rate": 0.00048812037724775217,
|
|
"loss": 5.3265,
|
|
"mean_token_accuracy": 0.16964268684387207,
|
|
"num_tokens": 24720230.0,
|
|
"step": 14250
|
|
},
|
|
{
|
|
"entropy": 5.516942071914673,
|
|
"epoch": 1.1090838358296051,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.0004881114889492109,
|
|
"loss": 5.2756,
|
|
"mean_token_accuracy": 0.17141272276639938,
|
|
"num_tokens": 24728896.0,
|
|
"step": 14255
|
|
},
|
|
{
|
|
"entropy": 5.562738132476807,
|
|
"epoch": 1.1094728652013226,
|
|
"grad_norm": 1.84375,
|
|
"learning_rate": 0.00048810259741704197,
|
|
"loss": 5.3434,
|
|
"mean_token_accuracy": 0.16922492831945418,
|
|
"num_tokens": 24737731.0,
|
|
"step": 14260
|
|
},
|
|
{
|
|
"entropy": 5.535038661956787,
|
|
"epoch": 1.1098618945730403,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.0004880937026513803,
|
|
"loss": 5.228,
|
|
"mean_token_accuracy": 0.17575253546237946,
|
|
"num_tokens": 24746335.0,
|
|
"step": 14265
|
|
},
|
|
{
|
|
"entropy": 5.48253984451294,
|
|
"epoch": 1.1102509239447578,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004880848046523609,
|
|
"loss": 5.2474,
|
|
"mean_token_accuracy": 0.1755129560828209,
|
|
"num_tokens": 24755917.0,
|
|
"step": 14270
|
|
},
|
|
{
|
|
"entropy": 5.558473920822143,
|
|
"epoch": 1.1106399533164755,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.00048807590342011875,
|
|
"loss": 5.3885,
|
|
"mean_token_accuracy": 0.16232267618179322,
|
|
"num_tokens": 24764713.0,
|
|
"step": 14275
|
|
},
|
|
{
|
|
"entropy": 5.682742977142334,
|
|
"epoch": 1.111028982688193,
|
|
"grad_norm": 1.875,
|
|
"learning_rate": 0.00048806699895478895,
|
|
"loss": 5.3839,
|
|
"mean_token_accuracy": 0.16875440776348113,
|
|
"num_tokens": 24773464.0,
|
|
"step": 14280
|
|
},
|
|
{
|
|
"entropy": 5.541551876068115,
|
|
"epoch": 1.1114180120599104,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.0004880580912565065,
|
|
"loss": 5.3113,
|
|
"mean_token_accuracy": 0.17400919198989867,
|
|
"num_tokens": 24781437.0,
|
|
"step": 14285
|
|
},
|
|
{
|
|
"entropy": 5.4384446144104,
|
|
"epoch": 1.1118070414316281,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004880491803254067,
|
|
"loss": 5.1498,
|
|
"mean_token_accuracy": 0.18029990941286086,
|
|
"num_tokens": 24789505.0,
|
|
"step": 14290
|
|
},
|
|
{
|
|
"entropy": 5.5582538604736325,
|
|
"epoch": 1.1121960708033456,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004880402661616246,
|
|
"loss": 5.3936,
|
|
"mean_token_accuracy": 0.16577622443437576,
|
|
"num_tokens": 24798492.0,
|
|
"step": 14295
|
|
},
|
|
{
|
|
"entropy": 5.540700626373291,
|
|
"epoch": 1.1125851001750633,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.0004880313487652956,
|
|
"loss": 5.3431,
|
|
"mean_token_accuracy": 0.16139609813690187,
|
|
"num_tokens": 24807472.0,
|
|
"step": 14300
|
|
},
|
|
{
|
|
"entropy": 5.598321008682251,
|
|
"epoch": 1.1129741295467808,
|
|
"grad_norm": 1.9375,
|
|
"learning_rate": 0.00048802242813655503,
|
|
"loss": 5.3619,
|
|
"mean_token_accuracy": 0.17163712084293364,
|
|
"num_tokens": 24815838.0,
|
|
"step": 14305
|
|
},
|
|
{
|
|
"entropy": 5.457903957366943,
|
|
"epoch": 1.1133631589184985,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.000488013504275538,
|
|
"loss": 5.2217,
|
|
"mean_token_accuracy": 0.17970041632652284,
|
|
"num_tokens": 24823953.0,
|
|
"step": 14310
|
|
},
|
|
{
|
|
"entropy": 5.422196865081787,
|
|
"epoch": 1.113752188290216,
|
|
"grad_norm": 3.328125,
|
|
"learning_rate": 0.0004880045771823802,
|
|
"loss": 5.1656,
|
|
"mean_token_accuracy": 0.18355161249637603,
|
|
"num_tokens": 24832414.0,
|
|
"step": 14315
|
|
},
|
|
{
|
|
"entropy": 5.459926748275757,
|
|
"epoch": 1.1141412176619334,
|
|
"grad_norm": 2.328125,
|
|
"learning_rate": 0.00048799564685721695,
|
|
"loss": 5.296,
|
|
"mean_token_accuracy": 0.17886112183332442,
|
|
"num_tokens": 24840503.0,
|
|
"step": 14320
|
|
},
|
|
{
|
|
"entropy": 5.5691217422485355,
|
|
"epoch": 1.1145302470336511,
|
|
"grad_norm": 1.890625,
|
|
"learning_rate": 0.0004879867133001837,
|
|
"loss": 5.4229,
|
|
"mean_token_accuracy": 0.15954364389181136,
|
|
"num_tokens": 24849272.0,
|
|
"step": 14325
|
|
},
|
|
{
|
|
"entropy": 5.577770709991455,
|
|
"epoch": 1.1149192764053686,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 0.0004879777765114162,
|
|
"loss": 5.3797,
|
|
"mean_token_accuracy": 0.16698006838560103,
|
|
"num_tokens": 24858565.0,
|
|
"step": 14330
|
|
},
|
|
{
|
|
"entropy": 5.638581800460815,
|
|
"epoch": 1.115308305777086,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.00048796883649104996,
|
|
"loss": 5.3186,
|
|
"mean_token_accuracy": 0.1710255578160286,
|
|
"num_tokens": 24867811.0,
|
|
"step": 14335
|
|
},
|
|
{
|
|
"entropy": 5.521627950668335,
|
|
"epoch": 1.1156973351488038,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.0004879598932392206,
|
|
"loss": 5.3498,
|
|
"mean_token_accuracy": 0.15957373678684234,
|
|
"num_tokens": 24876776.0,
|
|
"step": 14340
|
|
},
|
|
{
|
|
"entropy": 5.455714321136474,
|
|
"epoch": 1.1160863645205212,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.00048795094675606364,
|
|
"loss": 5.2856,
|
|
"mean_token_accuracy": 0.16614772975444794,
|
|
"num_tokens": 24885030.0,
|
|
"step": 14345
|
|
},
|
|
{
|
|
"entropy": 5.6199556350708,
|
|
"epoch": 1.116475393892239,
|
|
"grad_norm": 1.890625,
|
|
"learning_rate": 0.0004879419970417152,
|
|
"loss": 5.4281,
|
|
"mean_token_accuracy": 0.1604268178343773,
|
|
"num_tokens": 24894336.0,
|
|
"step": 14350
|
|
},
|
|
{
|
|
"entropy": 5.626073360443115,
|
|
"epoch": 1.1168644232639564,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.00048793304409631077,
|
|
"loss": 5.3907,
|
|
"mean_token_accuracy": 0.16631727069616317,
|
|
"num_tokens": 24903107.0,
|
|
"step": 14355
|
|
},
|
|
{
|
|
"entropy": 5.663770961761474,
|
|
"epoch": 1.117253452635674,
|
|
"grad_norm": 1.9140625,
|
|
"learning_rate": 0.0004879240879199863,
|
|
"loss": 5.4806,
|
|
"mean_token_accuracy": 0.16219090670347214,
|
|
"num_tokens": 24912727.0,
|
|
"step": 14360
|
|
},
|
|
{
|
|
"entropy": 5.5100079536437985,
|
|
"epoch": 1.1176424820073916,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.00048791512851287786,
|
|
"loss": 5.2233,
|
|
"mean_token_accuracy": 0.16763668060302733,
|
|
"num_tokens": 24921534.0,
|
|
"step": 14365
|
|
},
|
|
{
|
|
"entropy": 5.5396849632263185,
|
|
"epoch": 1.118031511379109,
|
|
"grad_norm": 1.9765625,
|
|
"learning_rate": 0.00048790616587512107,
|
|
"loss": 5.3085,
|
|
"mean_token_accuracy": 0.17270931750535964,
|
|
"num_tokens": 24930093.0,
|
|
"step": 14370
|
|
},
|
|
{
|
|
"entropy": 5.582523584365845,
|
|
"epoch": 1.1184205407508268,
|
|
"grad_norm": 2.96875,
|
|
"learning_rate": 0.0004878972000068521,
|
|
"loss": 5.4002,
|
|
"mean_token_accuracy": 0.16867225617170334,
|
|
"num_tokens": 24939230.0,
|
|
"step": 14375
|
|
},
|
|
{
|
|
"entropy": 5.577020215988159,
|
|
"epoch": 1.1188095701225442,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.00048788823090820707,
|
|
"loss": 5.4192,
|
|
"mean_token_accuracy": 0.1723649948835373,
|
|
"num_tokens": 24947595.0,
|
|
"step": 14380
|
|
},
|
|
{
|
|
"entropy": 5.589379405975341,
|
|
"epoch": 1.1191985994942617,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.00048787925857932194,
|
|
"loss": 5.4044,
|
|
"mean_token_accuracy": 0.16684343963861464,
|
|
"num_tokens": 24957099.0,
|
|
"step": 14385
|
|
},
|
|
{
|
|
"entropy": 5.482144927978515,
|
|
"epoch": 1.1195876288659794,
|
|
"grad_norm": 1.84375,
|
|
"learning_rate": 0.00048787028302033287,
|
|
"loss": 5.2689,
|
|
"mean_token_accuracy": 0.17104468792676925,
|
|
"num_tokens": 24965701.0,
|
|
"step": 14390
|
|
},
|
|
{
|
|
"entropy": 5.579807996749878,
|
|
"epoch": 1.1199766582376969,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.00048786130423137606,
|
|
"loss": 5.3965,
|
|
"mean_token_accuracy": 0.16277793794870377,
|
|
"num_tokens": 24974025.0,
|
|
"step": 14395
|
|
},
|
|
{
|
|
"entropy": 5.6031183242797855,
|
|
"epoch": 1.1203656876094146,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004878523222125879,
|
|
"loss": 5.4484,
|
|
"mean_token_accuracy": 0.16234600692987441,
|
|
"num_tokens": 24982930.0,
|
|
"step": 14400
|
|
},
|
|
{
|
|
"entropy": 5.568015909194946,
|
|
"epoch": 1.120754716981132,
|
|
"grad_norm": 2.234375,
|
|
"learning_rate": 0.0004878433369641044,
|
|
"loss": 5.3134,
|
|
"mean_token_accuracy": 0.1732340633869171,
|
|
"num_tokens": 24991332.0,
|
|
"step": 14405
|
|
},
|
|
{
|
|
"entropy": 5.5209790706634525,
|
|
"epoch": 1.1211437463528497,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.0004878343484860621,
|
|
"loss": 5.3097,
|
|
"mean_token_accuracy": 0.1751156657934189,
|
|
"num_tokens": 25000130.0,
|
|
"step": 14410
|
|
},
|
|
{
|
|
"entropy": 5.525942850112915,
|
|
"epoch": 1.1215327757245672,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0004878253567785972,
|
|
"loss": 5.3041,
|
|
"mean_token_accuracy": 0.17408304214477538,
|
|
"num_tokens": 25008423.0,
|
|
"step": 14415
|
|
},
|
|
{
|
|
"entropy": 5.585805654525757,
|
|
"epoch": 1.1219218050962847,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.00048781636184184644,
|
|
"loss": 5.3924,
|
|
"mean_token_accuracy": 0.17055297642946243,
|
|
"num_tokens": 25017399.0,
|
|
"step": 14420
|
|
},
|
|
{
|
|
"entropy": 5.623371362686157,
|
|
"epoch": 1.1223108344680024,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.000487807363675946,
|
|
"loss": 5.375,
|
|
"mean_token_accuracy": 0.17363773584365844,
|
|
"num_tokens": 25025957.0,
|
|
"step": 14425
|
|
},
|
|
{
|
|
"entropy": 5.570174980163574,
|
|
"epoch": 1.1226998638397199,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004877983622810326,
|
|
"loss": 5.264,
|
|
"mean_token_accuracy": 0.17775200456380844,
|
|
"num_tokens": 25034246.0,
|
|
"step": 14430
|
|
},
|
|
{
|
|
"entropy": 5.452083778381348,
|
|
"epoch": 1.1230888932114376,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.0004877893576572427,
|
|
"loss": 5.2729,
|
|
"mean_token_accuracy": 0.17524188607931138,
|
|
"num_tokens": 25042461.0,
|
|
"step": 14435
|
|
},
|
|
{
|
|
"entropy": 5.499751281738281,
|
|
"epoch": 1.123477922583155,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.000487780349804713,
|
|
"loss": 5.2527,
|
|
"mean_token_accuracy": 0.1751112535595894,
|
|
"num_tokens": 25051291.0,
|
|
"step": 14440
|
|
},
|
|
{
|
|
"entropy": 5.555979871749878,
|
|
"epoch": 1.1238669519548725,
|
|
"grad_norm": 2.65625,
|
|
"learning_rate": 0.0004877713387235802,
|
|
"loss": 5.3901,
|
|
"mean_token_accuracy": 0.16702209562063217,
|
|
"num_tokens": 25060538.0,
|
|
"step": 14445
|
|
},
|
|
{
|
|
"entropy": 5.5903130054473875,
|
|
"epoch": 1.1242559813265902,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.000487762324413981,
|
|
"loss": 5.3614,
|
|
"mean_token_accuracy": 0.16249305307865142,
|
|
"num_tokens": 25068965.0,
|
|
"step": 14450
|
|
},
|
|
{
|
|
"entropy": 5.531769514083862,
|
|
"epoch": 1.1246450106983077,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.00048775330687605213,
|
|
"loss": 5.3471,
|
|
"mean_token_accuracy": 0.16777345687150955,
|
|
"num_tokens": 25077021.0,
|
|
"step": 14455
|
|
},
|
|
{
|
|
"entropy": 5.584255599975586,
|
|
"epoch": 1.1250340400700254,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.0004877442861099305,
|
|
"loss": 5.3543,
|
|
"mean_token_accuracy": 0.17016467899084092,
|
|
"num_tokens": 25086009.0,
|
|
"step": 14460
|
|
},
|
|
{
|
|
"entropy": 5.514311599731445,
|
|
"epoch": 1.1254230694417429,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004877352621157529,
|
|
"loss": 5.2403,
|
|
"mean_token_accuracy": 0.17592113912105561,
|
|
"num_tokens": 25094745.0,
|
|
"step": 14465
|
|
},
|
|
{
|
|
"entropy": 5.563268756866455,
|
|
"epoch": 1.1258120988134603,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.00048772623489365635,
|
|
"loss": 5.2941,
|
|
"mean_token_accuracy": 0.17110613882541656,
|
|
"num_tokens": 25103087.0,
|
|
"step": 14470
|
|
},
|
|
{
|
|
"entropy": 5.569503116607666,
|
|
"epoch": 1.126201128185178,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.0004877172044437777,
|
|
"loss": 5.3325,
|
|
"mean_token_accuracy": 0.16647037714719773,
|
|
"num_tokens": 25111822.0,
|
|
"step": 14475
|
|
},
|
|
{
|
|
"entropy": 5.5227227210998535,
|
|
"epoch": 1.1265901575568955,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.00048770817076625416,
|
|
"loss": 5.2971,
|
|
"mean_token_accuracy": 0.16923800706863404,
|
|
"num_tokens": 25119975.0,
|
|
"step": 14480
|
|
},
|
|
{
|
|
"entropy": 5.538654518127442,
|
|
"epoch": 1.126979186928613,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.00048769913386122253,
|
|
"loss": 5.3741,
|
|
"mean_token_accuracy": 0.16533004641532897,
|
|
"num_tokens": 25129031.0,
|
|
"step": 14485
|
|
},
|
|
{
|
|
"entropy": 5.603739881515503,
|
|
"epoch": 1.1273682163003307,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004876900937288202,
|
|
"loss": 5.3084,
|
|
"mean_token_accuracy": 0.1722537100315094,
|
|
"num_tokens": 25138230.0,
|
|
"step": 14490
|
|
},
|
|
{
|
|
"entropy": 5.598256683349609,
|
|
"epoch": 1.1277572456720482,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.00048768105036918426,
|
|
"loss": 5.3047,
|
|
"mean_token_accuracy": 0.17206084132194518,
|
|
"num_tokens": 25147120.0,
|
|
"step": 14495
|
|
},
|
|
{
|
|
"entropy": 5.539633464813233,
|
|
"epoch": 1.1281462750437659,
|
|
"grad_norm": 1.984375,
|
|
"learning_rate": 0.00048767200378245187,
|
|
"loss": 5.3123,
|
|
"mean_token_accuracy": 0.16815738528966903,
|
|
"num_tokens": 25155623.0,
|
|
"step": 14500
|
|
},
|
|
{
|
|
"entropy": 5.4743105411529545,
|
|
"epoch": 1.1285353044154833,
|
|
"grad_norm": 3.0625,
|
|
"learning_rate": 0.00048766295396876025,
|
|
"loss": 5.2129,
|
|
"mean_token_accuracy": 0.1806921422481537,
|
|
"num_tokens": 25163867.0,
|
|
"step": 14505
|
|
},
|
|
{
|
|
"entropy": 5.53100619316101,
|
|
"epoch": 1.128924333787201,
|
|
"grad_norm": 1.8984375,
|
|
"learning_rate": 0.00048765390092824683,
|
|
"loss": 5.3267,
|
|
"mean_token_accuracy": 0.16829499900341033,
|
|
"num_tokens": 25172838.0,
|
|
"step": 14510
|
|
},
|
|
{
|
|
"entropy": 5.490903615951538,
|
|
"epoch": 1.1293133631589185,
|
|
"grad_norm": 1.8515625,
|
|
"learning_rate": 0.000487644844661049,
|
|
"loss": 5.2787,
|
|
"mean_token_accuracy": 0.1737896293401718,
|
|
"num_tokens": 25181168.0,
|
|
"step": 14515
|
|
},
|
|
{
|
|
"entropy": 5.529686689376831,
|
|
"epoch": 1.129702392530636,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.000487635785167304,
|
|
"loss": 5.3545,
|
|
"mean_token_accuracy": 0.17582946866750718,
|
|
"num_tokens": 25190115.0,
|
|
"step": 14520
|
|
},
|
|
{
|
|
"entropy": 5.536796569824219,
|
|
"epoch": 1.1300914219023537,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.00048762672244714953,
|
|
"loss": 5.3707,
|
|
"mean_token_accuracy": 0.1692177951335907,
|
|
"num_tokens": 25199594.0,
|
|
"step": 14525
|
|
},
|
|
{
|
|
"entropy": 5.571754026412964,
|
|
"epoch": 1.1304804512740712,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.0004876176565007229,
|
|
"loss": 5.3041,
|
|
"mean_token_accuracy": 0.16696984320878983,
|
|
"num_tokens": 25208060.0,
|
|
"step": 14530
|
|
},
|
|
{
|
|
"entropy": 5.54861888885498,
|
|
"epoch": 1.1308694806457888,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.00048760858732816174,
|
|
"loss": 5.2631,
|
|
"mean_token_accuracy": 0.16919180899858474,
|
|
"num_tokens": 25216257.0,
|
|
"step": 14535
|
|
},
|
|
{
|
|
"entropy": 5.509464979171753,
|
|
"epoch": 1.1312585100175063,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004875995149296037,
|
|
"loss": 5.2854,
|
|
"mean_token_accuracy": 0.17048473209142684,
|
|
"num_tokens": 25225032.0,
|
|
"step": 14540
|
|
},
|
|
{
|
|
"entropy": 5.543582487106323,
|
|
"epoch": 1.1316475393892238,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.0004875904393051864,
|
|
"loss": 5.3193,
|
|
"mean_token_accuracy": 0.17101970165967942,
|
|
"num_tokens": 25233624.0,
|
|
"step": 14545
|
|
},
|
|
{
|
|
"entropy": 5.49220461845398,
|
|
"epoch": 1.1320365687609415,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004875813604550476,
|
|
"loss": 5.2737,
|
|
"mean_token_accuracy": 0.17455722838640214,
|
|
"num_tokens": 25242132.0,
|
|
"step": 14550
|
|
},
|
|
{
|
|
"entropy": 5.517650556564331,
|
|
"epoch": 1.132425598132659,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.00048757227837932494,
|
|
"loss": 5.2988,
|
|
"mean_token_accuracy": 0.17298836559057235,
|
|
"num_tokens": 25250923.0,
|
|
"step": 14555
|
|
},
|
|
{
|
|
"entropy": 5.49726824760437,
|
|
"epoch": 1.1328146275043767,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.0004875631930781563,
|
|
"loss": 5.3022,
|
|
"mean_token_accuracy": 0.16802928298711778,
|
|
"num_tokens": 25259783.0,
|
|
"step": 14560
|
|
},
|
|
{
|
|
"entropy": 5.600533151626587,
|
|
"epoch": 1.1332036568760941,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 0.00048755410455167967,
|
|
"loss": 5.4761,
|
|
"mean_token_accuracy": 0.16585941314697267,
|
|
"num_tokens": 25268801.0,
|
|
"step": 14565
|
|
},
|
|
{
|
|
"entropy": 5.52184944152832,
|
|
"epoch": 1.1335926862478116,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.0004875450128000326,
|
|
"loss": 5.2866,
|
|
"mean_token_accuracy": 0.1824623465538025,
|
|
"num_tokens": 25277226.0,
|
|
"step": 14570
|
|
},
|
|
{
|
|
"entropy": 5.575818490982056,
|
|
"epoch": 1.1339817156195293,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0004875359178233534,
|
|
"loss": 5.3595,
|
|
"mean_token_accuracy": 0.16765044033527374,
|
|
"num_tokens": 25285887.0,
|
|
"step": 14575
|
|
},
|
|
{
|
|
"entropy": 5.519542980194092,
|
|
"epoch": 1.1343707449912468,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.00048752681962177985,
|
|
"loss": 5.1973,
|
|
"mean_token_accuracy": 0.17466872185468674,
|
|
"num_tokens": 25294025.0,
|
|
"step": 14580
|
|
},
|
|
{
|
|
"entropy": 5.565718936920166,
|
|
"epoch": 1.1347597743629645,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.00048751771819545013,
|
|
"loss": 5.4337,
|
|
"mean_token_accuracy": 0.16750813871622086,
|
|
"num_tokens": 25303016.0,
|
|
"step": 14585
|
|
},
|
|
{
|
|
"entropy": 5.507101583480835,
|
|
"epoch": 1.135148803734682,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.00048750861354450236,
|
|
"loss": 5.2075,
|
|
"mean_token_accuracy": 0.17866807132959367,
|
|
"num_tokens": 25311193.0,
|
|
"step": 14590
|
|
},
|
|
{
|
|
"entropy": 5.473371791839599,
|
|
"epoch": 1.1355378331063994,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004874995056690746,
|
|
"loss": 5.2434,
|
|
"mean_token_accuracy": 0.1704245001077652,
|
|
"num_tokens": 25319380.0,
|
|
"step": 14595
|
|
},
|
|
{
|
|
"entropy": 5.498834466934204,
|
|
"epoch": 1.1359268624781171,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.000487490394569305,
|
|
"loss": 5.3013,
|
|
"mean_token_accuracy": 0.17470889240503312,
|
|
"num_tokens": 25327854.0,
|
|
"step": 14600
|
|
},
|
|
{
|
|
"entropy": 5.581671094894409,
|
|
"epoch": 1.1363158918498346,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004874812802453319,
|
|
"loss": 5.3435,
|
|
"mean_token_accuracy": 0.17040662765502929,
|
|
"num_tokens": 25335912.0,
|
|
"step": 14605
|
|
},
|
|
{
|
|
"entropy": 5.544326734542847,
|
|
"epoch": 1.1367049212215523,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.0004874721626972936,
|
|
"loss": 5.3414,
|
|
"mean_token_accuracy": 0.17743494361639023,
|
|
"num_tokens": 25344104.0,
|
|
"step": 14610
|
|
},
|
|
{
|
|
"entropy": 5.414308357238769,
|
|
"epoch": 1.1370939505932698,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.0004874630419253284,
|
|
"loss": 5.1279,
|
|
"mean_token_accuracy": 0.18145185112953185,
|
|
"num_tokens": 25352583.0,
|
|
"step": 14615
|
|
},
|
|
{
|
|
"entropy": 5.465250444412232,
|
|
"epoch": 1.1374829799649873,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.00048745391792957474,
|
|
"loss": 5.221,
|
|
"mean_token_accuracy": 0.17378100603818894,
|
|
"num_tokens": 25361035.0,
|
|
"step": 14620
|
|
},
|
|
{
|
|
"entropy": 5.455963516235352,
|
|
"epoch": 1.137872009336705,
|
|
"grad_norm": 1.9453125,
|
|
"learning_rate": 0.00048744479071017097,
|
|
"loss": 5.2872,
|
|
"mean_token_accuracy": 0.1703445315361023,
|
|
"num_tokens": 25369511.0,
|
|
"step": 14625
|
|
},
|
|
{
|
|
"entropy": 5.566524267196655,
|
|
"epoch": 1.1382610387084224,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.0004874356602672556,
|
|
"loss": 5.291,
|
|
"mean_token_accuracy": 0.17134100198745728,
|
|
"num_tokens": 25378023.0,
|
|
"step": 14630
|
|
},
|
|
{
|
|
"entropy": 5.529734802246094,
|
|
"epoch": 1.1386500680801401,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 0.0004874265266009673,
|
|
"loss": 5.3083,
|
|
"mean_token_accuracy": 0.16630384474992752,
|
|
"num_tokens": 25386791.0,
|
|
"step": 14635
|
|
},
|
|
{
|
|
"entropy": 5.516237497329712,
|
|
"epoch": 1.1390390974518576,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004874173897114445,
|
|
"loss": 5.3484,
|
|
"mean_token_accuracy": 0.16917914450168609,
|
|
"num_tokens": 25395401.0,
|
|
"step": 14640
|
|
},
|
|
{
|
|
"entropy": 5.471943664550781,
|
|
"epoch": 1.1394281268235753,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.00048740824959882603,
|
|
"loss": 5.3024,
|
|
"mean_token_accuracy": 0.1702470913529396,
|
|
"num_tokens": 25404193.0,
|
|
"step": 14645
|
|
},
|
|
{
|
|
"entropy": 5.6503493309021,
|
|
"epoch": 1.1398171561952928,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004873991062632504,
|
|
"loss": 5.3881,
|
|
"mean_token_accuracy": 0.15999443233013153,
|
|
"num_tokens": 25413073.0,
|
|
"step": 14650
|
|
},
|
|
{
|
|
"entropy": 5.536189699172974,
|
|
"epoch": 1.1402061855670103,
|
|
"grad_norm": 2.46875,
|
|
"learning_rate": 0.00048738995970485635,
|
|
"loss": 5.2772,
|
|
"mean_token_accuracy": 0.17062387019395828,
|
|
"num_tokens": 25422064.0,
|
|
"step": 14655
|
|
},
|
|
{
|
|
"entropy": 5.4656829833984375,
|
|
"epoch": 1.140595214938728,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.0004873808099237827,
|
|
"loss": 5.2504,
|
|
"mean_token_accuracy": 0.17227883785963058,
|
|
"num_tokens": 25430711.0,
|
|
"step": 14660
|
|
},
|
|
{
|
|
"entropy": 5.600215339660645,
|
|
"epoch": 1.1409842443104454,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004873716569201684,
|
|
"loss": 5.3842,
|
|
"mean_token_accuracy": 0.16563586443662642,
|
|
"num_tokens": 25439527.0,
|
|
"step": 14665
|
|
},
|
|
{
|
|
"entropy": 5.5954320430755615,
|
|
"epoch": 1.141373273682163,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.00048736250069415213,
|
|
"loss": 5.3431,
|
|
"mean_token_accuracy": 0.16915304958820343,
|
|
"num_tokens": 25448633.0,
|
|
"step": 14670
|
|
},
|
|
{
|
|
"entropy": 5.511667633056641,
|
|
"epoch": 1.1417623030538806,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004873533412458729,
|
|
"loss": 5.3272,
|
|
"mean_token_accuracy": 0.16899686455726623,
|
|
"num_tokens": 25457657.0,
|
|
"step": 14675
|
|
},
|
|
{
|
|
"entropy": 5.531187295913696,
|
|
"epoch": 1.142151332425598,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.00048734417857546986,
|
|
"loss": 5.3755,
|
|
"mean_token_accuracy": 0.16160681396722792,
|
|
"num_tokens": 25466698.0,
|
|
"step": 14680
|
|
},
|
|
{
|
|
"entropy": 5.5505894184112545,
|
|
"epoch": 1.1425403617973158,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.0004873350126830818,
|
|
"loss": 5.3245,
|
|
"mean_token_accuracy": 0.16614405065774918,
|
|
"num_tokens": 25474921.0,
|
|
"step": 14685
|
|
},
|
|
{
|
|
"entropy": 5.506896305084228,
|
|
"epoch": 1.1429293911690332,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.0004873258435688479,
|
|
"loss": 5.2313,
|
|
"mean_token_accuracy": 0.17805486917495728,
|
|
"num_tokens": 25483553.0,
|
|
"step": 14690
|
|
},
|
|
{
|
|
"entropy": 5.5363534450531,
|
|
"epoch": 1.143318420540751,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0004873166712329073,
|
|
"loss": 5.3066,
|
|
"mean_token_accuracy": 0.17466685324907302,
|
|
"num_tokens": 25492408.0,
|
|
"step": 14695
|
|
},
|
|
{
|
|
"entropy": 5.503551387786866,
|
|
"epoch": 1.1437074499124684,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.00048730749567539914,
|
|
"loss": 5.3265,
|
|
"mean_token_accuracy": 0.1674924299120903,
|
|
"num_tokens": 25501404.0,
|
|
"step": 14700
|
|
},
|
|
{
|
|
"entropy": 5.5991332054138185,
|
|
"epoch": 1.144096479284186,
|
|
"grad_norm": 1.9375,
|
|
"learning_rate": 0.00048729831689646257,
|
|
"loss": 5.3276,
|
|
"mean_token_accuracy": 0.16516642272472382,
|
|
"num_tokens": 25510176.0,
|
|
"step": 14705
|
|
},
|
|
{
|
|
"entropy": 5.516887187957764,
|
|
"epoch": 1.1444855086559036,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.00048728913489623705,
|
|
"loss": 5.2538,
|
|
"mean_token_accuracy": 0.17168099731206893,
|
|
"num_tokens": 25518809.0,
|
|
"step": 14710
|
|
},
|
|
{
|
|
"entropy": 5.506005954742432,
|
|
"epoch": 1.144874538027621,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004872799496748618,
|
|
"loss": 5.3523,
|
|
"mean_token_accuracy": 0.16978123188018798,
|
|
"num_tokens": 25527415.0,
|
|
"step": 14715
|
|
},
|
|
{
|
|
"entropy": 5.483895921707154,
|
|
"epoch": 1.1452635673993385,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004872707612324761,
|
|
"loss": 5.2894,
|
|
"mean_token_accuracy": 0.1682486578822136,
|
|
"num_tokens": 25535618.0,
|
|
"step": 14720
|
|
},
|
|
{
|
|
"entropy": 5.604482364654541,
|
|
"epoch": 1.1456525967710562,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.0004872615695692196,
|
|
"loss": 5.3085,
|
|
"mean_token_accuracy": 0.17212099432945252,
|
|
"num_tokens": 25544228.0,
|
|
"step": 14725
|
|
},
|
|
{
|
|
"entropy": 5.601893615722656,
|
|
"epoch": 1.1460416261427737,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004872523746852315,
|
|
"loss": 5.3419,
|
|
"mean_token_accuracy": 0.1676053911447525,
|
|
"num_tokens": 25553557.0,
|
|
"step": 14730
|
|
},
|
|
{
|
|
"entropy": 5.532661056518554,
|
|
"epoch": 1.1464306555144914,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.00048724317658065146,
|
|
"loss": 5.2992,
|
|
"mean_token_accuracy": 0.1749195411801338,
|
|
"num_tokens": 25562018.0,
|
|
"step": 14735
|
|
},
|
|
{
|
|
"entropy": 5.560487556457519,
|
|
"epoch": 1.146819684886209,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.00048723397525561916,
|
|
"loss": 5.306,
|
|
"mean_token_accuracy": 0.17520872503519058,
|
|
"num_tokens": 25569382.0,
|
|
"step": 14740
|
|
},
|
|
{
|
|
"entropy": 5.441896295547485,
|
|
"epoch": 1.1472087142579266,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.00048722477071027394,
|
|
"loss": 5.2831,
|
|
"mean_token_accuracy": 0.16793857514858246,
|
|
"num_tokens": 25578172.0,
|
|
"step": 14745
|
|
},
|
|
{
|
|
"entropy": 5.493895244598389,
|
|
"epoch": 1.147597743629644,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.00048721556294475574,
|
|
"loss": 5.3264,
|
|
"mean_token_accuracy": 0.16599381864070892,
|
|
"num_tokens": 25587572.0,
|
|
"step": 14750
|
|
},
|
|
{
|
|
"entropy": 5.530125331878662,
|
|
"epoch": 1.1479867730013615,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.00048720635195920403,
|
|
"loss": 5.3676,
|
|
"mean_token_accuracy": 0.16962938457727433,
|
|
"num_tokens": 25596609.0,
|
|
"step": 14755
|
|
},
|
|
{
|
|
"entropy": 5.562018489837646,
|
|
"epoch": 1.1483758023730792,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004871971377537588,
|
|
"loss": 5.3712,
|
|
"mean_token_accuracy": 0.16780511289834976,
|
|
"num_tokens": 25605707.0,
|
|
"step": 14760
|
|
},
|
|
{
|
|
"entropy": 5.525937843322754,
|
|
"epoch": 1.1487648317447967,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004871879203285597,
|
|
"loss": 5.3163,
|
|
"mean_token_accuracy": 0.16738255321979523,
|
|
"num_tokens": 25614218.0,
|
|
"step": 14765
|
|
},
|
|
{
|
|
"entropy": 5.499395322799683,
|
|
"epoch": 1.1491538611165142,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.00048717869968374655,
|
|
"loss": 5.2345,
|
|
"mean_token_accuracy": 0.17317628860473633,
|
|
"num_tokens": 25622613.0,
|
|
"step": 14770
|
|
},
|
|
{
|
|
"entropy": 5.634173345565796,
|
|
"epoch": 1.1495428904882319,
|
|
"grad_norm": 2.4375,
|
|
"learning_rate": 0.00048716947581945954,
|
|
"loss": 5.3896,
|
|
"mean_token_accuracy": 0.16756265312433244,
|
|
"num_tokens": 25631396.0,
|
|
"step": 14775
|
|
},
|
|
{
|
|
"entropy": 5.560069274902344,
|
|
"epoch": 1.1499319198599494,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.0004871602487358383,
|
|
"loss": 5.3002,
|
|
"mean_token_accuracy": 0.17219740897417068,
|
|
"num_tokens": 25640870.0,
|
|
"step": 14780
|
|
},
|
|
{
|
|
"entropy": 5.548902797698974,
|
|
"epoch": 1.150320949231667,
|
|
"grad_norm": 2.234375,
|
|
"learning_rate": 0.000487151018433023,
|
|
"loss": 5.3387,
|
|
"mean_token_accuracy": 0.1698947697877884,
|
|
"num_tokens": 25649395.0,
|
|
"step": 14785
|
|
},
|
|
{
|
|
"entropy": 5.534258604049683,
|
|
"epoch": 1.1507099786033845,
|
|
"grad_norm": 2.359375,
|
|
"learning_rate": 0.00048714178491115367,
|
|
"loss": 5.474,
|
|
"mean_token_accuracy": 0.1614096313714981,
|
|
"num_tokens": 25659087.0,
|
|
"step": 14790
|
|
},
|
|
{
|
|
"entropy": 5.557971811294555,
|
|
"epoch": 1.1510990079751022,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.00048713254817037046,
|
|
"loss": 5.3703,
|
|
"mean_token_accuracy": 0.17371327728033065,
|
|
"num_tokens": 25667847.0,
|
|
"step": 14795
|
|
},
|
|
{
|
|
"entropy": 5.528278160095215,
|
|
"epoch": 1.1514880373468197,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004871233082108135,
|
|
"loss": 5.3284,
|
|
"mean_token_accuracy": 0.1763760879635811,
|
|
"num_tokens": 25676786.0,
|
|
"step": 14800
|
|
},
|
|
{
|
|
"entropy": 5.571025609970093,
|
|
"epoch": 1.1518770667185372,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004871140650326228,
|
|
"loss": 5.3708,
|
|
"mean_token_accuracy": 0.16312464475631713,
|
|
"num_tokens": 25685223.0,
|
|
"step": 14805
|
|
},
|
|
{
|
|
"entropy": 5.581476497650146,
|
|
"epoch": 1.1522660960902549,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004871048186359389,
|
|
"loss": 5.3192,
|
|
"mean_token_accuracy": 0.1679316446185112,
|
|
"num_tokens": 25694243.0,
|
|
"step": 14810
|
|
},
|
|
{
|
|
"entropy": 5.519680452346802,
|
|
"epoch": 1.1526551254619724,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.000487095569020902,
|
|
"loss": 5.1898,
|
|
"mean_token_accuracy": 0.17910245805978775,
|
|
"num_tokens": 25702735.0,
|
|
"step": 14815
|
|
},
|
|
{
|
|
"entropy": 5.468982696533203,
|
|
"epoch": 1.1530441548336898,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.0004870863161876524,
|
|
"loss": 5.2978,
|
|
"mean_token_accuracy": 0.17906799912452698,
|
|
"num_tokens": 25711577.0,
|
|
"step": 14820
|
|
},
|
|
{
|
|
"entropy": 5.501131439208985,
|
|
"epoch": 1.1534331842054075,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.0004870770601363305,
|
|
"loss": 5.1985,
|
|
"mean_token_accuracy": 0.179717318713665,
|
|
"num_tokens": 25719927.0,
|
|
"step": 14825
|
|
},
|
|
{
|
|
"entropy": 5.528051471710205,
|
|
"epoch": 1.153822213577125,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.00048706780086707675,
|
|
"loss": 5.2517,
|
|
"mean_token_accuracy": 0.17344313561916352,
|
|
"num_tokens": 25728144.0,
|
|
"step": 14830
|
|
},
|
|
{
|
|
"entropy": 5.476591014862061,
|
|
"epoch": 1.1542112429488427,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0004870585383800317,
|
|
"loss": 5.2512,
|
|
"mean_token_accuracy": 0.17349060028791427,
|
|
"num_tokens": 25736736.0,
|
|
"step": 14835
|
|
},
|
|
{
|
|
"entropy": 5.597461891174317,
|
|
"epoch": 1.1546002723205602,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.00048704927267533585,
|
|
"loss": 5.4041,
|
|
"mean_token_accuracy": 0.17167434245347976,
|
|
"num_tokens": 25745031.0,
|
|
"step": 14840
|
|
},
|
|
{
|
|
"entropy": 5.656373119354248,
|
|
"epoch": 1.1549893016922779,
|
|
"grad_norm": 1.9609375,
|
|
"learning_rate": 0.00048704000375312975,
|
|
"loss": 5.3921,
|
|
"mean_token_accuracy": 0.1711965247988701,
|
|
"num_tokens": 25754265.0,
|
|
"step": 14845
|
|
},
|
|
{
|
|
"entropy": 5.6430717468261715,
|
|
"epoch": 1.1553783310639953,
|
|
"grad_norm": 1.90625,
|
|
"learning_rate": 0.00048703073161355414,
|
|
"loss": 5.3988,
|
|
"mean_token_accuracy": 0.1649368241429329,
|
|
"num_tokens": 25763084.0,
|
|
"step": 14850
|
|
},
|
|
{
|
|
"entropy": 5.5506752014160154,
|
|
"epoch": 1.1557673604357128,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004870214562567497,
|
|
"loss": 5.3776,
|
|
"mean_token_accuracy": 0.16386552304029464,
|
|
"num_tokens": 25771626.0,
|
|
"step": 14855
|
|
},
|
|
{
|
|
"entropy": 5.527558851242065,
|
|
"epoch": 1.1561563898074305,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.000487012177682857,
|
|
"loss": 5.3302,
|
|
"mean_token_accuracy": 0.17056528925895692,
|
|
"num_tokens": 25780326.0,
|
|
"step": 14860
|
|
},
|
|
{
|
|
"entropy": 5.63654351234436,
|
|
"epoch": 1.156545419179148,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.0004870028958920171,
|
|
"loss": 5.454,
|
|
"mean_token_accuracy": 0.16422211974859238,
|
|
"num_tokens": 25789318.0,
|
|
"step": 14865
|
|
},
|
|
{
|
|
"entropy": 5.589743423461914,
|
|
"epoch": 1.1569344485508655,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004869936108843706,
|
|
"loss": 5.3899,
|
|
"mean_token_accuracy": 0.16977383345365524,
|
|
"num_tokens": 25798025.0,
|
|
"step": 14870
|
|
},
|
|
{
|
|
"entropy": 5.546756410598755,
|
|
"epoch": 1.1573234779225832,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.00048698432266005854,
|
|
"loss": 5.2925,
|
|
"mean_token_accuracy": 0.17116822749376298,
|
|
"num_tokens": 25806669.0,
|
|
"step": 14875
|
|
},
|
|
{
|
|
"entropy": 5.5741355419158936,
|
|
"epoch": 1.1577125072943006,
|
|
"grad_norm": 2.234375,
|
|
"learning_rate": 0.0004869750312192217,
|
|
"loss": 5.3318,
|
|
"mean_token_accuracy": 0.17086806446313857,
|
|
"num_tokens": 25815938.0,
|
|
"step": 14880
|
|
},
|
|
{
|
|
"entropy": 5.550272417068482,
|
|
"epoch": 1.1581015366660183,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.00048696573656200123,
|
|
"loss": 5.2384,
|
|
"mean_token_accuracy": 0.17205784022808074,
|
|
"num_tokens": 25824293.0,
|
|
"step": 14885
|
|
},
|
|
{
|
|
"entropy": 5.584497117996216,
|
|
"epoch": 1.1584905660377358,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.00048695643868853806,
|
|
"loss": 5.3593,
|
|
"mean_token_accuracy": 0.1697976768016815,
|
|
"num_tokens": 25833081.0,
|
|
"step": 14890
|
|
},
|
|
{
|
|
"entropy": 5.594502925872803,
|
|
"epoch": 1.1588795954094535,
|
|
"grad_norm": 1.875,
|
|
"learning_rate": 0.0004869471375989733,
|
|
"loss": 5.38,
|
|
"mean_token_accuracy": 0.16600252091884612,
|
|
"num_tokens": 25841344.0,
|
|
"step": 14895
|
|
},
|
|
{
|
|
"entropy": 5.518092823028565,
|
|
"epoch": 1.159268624781171,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.0004869378332934481,
|
|
"loss": 5.3775,
|
|
"mean_token_accuracy": 0.1708097890019417,
|
|
"num_tokens": 25850617.0,
|
|
"step": 14900
|
|
},
|
|
{
|
|
"entropy": 5.5187623500823975,
|
|
"epoch": 1.1596576541528885,
|
|
"grad_norm": 1.9140625,
|
|
"learning_rate": 0.00048692852577210356,
|
|
"loss": 5.3101,
|
|
"mean_token_accuracy": 0.17654780447483062,
|
|
"num_tokens": 25858569.0,
|
|
"step": 14905
|
|
},
|
|
{
|
|
"entropy": 5.51036114692688,
|
|
"epoch": 1.1600466835246062,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.000486919215035081,
|
|
"loss": 5.3144,
|
|
"mean_token_accuracy": 0.17520852982997895,
|
|
"num_tokens": 25866892.0,
|
|
"step": 14910
|
|
},
|
|
{
|
|
"entropy": 5.557921838760376,
|
|
"epoch": 1.1604357128963236,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.0004869099010825217,
|
|
"loss": 5.3857,
|
|
"mean_token_accuracy": 0.1661457136273384,
|
|
"num_tokens": 25875661.0,
|
|
"step": 14915
|
|
},
|
|
{
|
|
"entropy": 5.471675395965576,
|
|
"epoch": 1.1608247422680413,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.00048690058391456684,
|
|
"loss": 5.2002,
|
|
"mean_token_accuracy": 0.18471098989248275,
|
|
"num_tokens": 25884951.0,
|
|
"step": 14920
|
|
},
|
|
{
|
|
"entropy": 5.623416090011597,
|
|
"epoch": 1.1612137716397588,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0004868912635313579,
|
|
"loss": 5.4444,
|
|
"mean_token_accuracy": 0.16651476174592972,
|
|
"num_tokens": 25893652.0,
|
|
"step": 14925
|
|
},
|
|
{
|
|
"entropy": 5.5562656879425045,
|
|
"epoch": 1.1616028010114763,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004868819399330364,
|
|
"loss": 5.2707,
|
|
"mean_token_accuracy": 0.16911213248968124,
|
|
"num_tokens": 25902375.0,
|
|
"step": 14930
|
|
},
|
|
{
|
|
"entropy": 5.516563606262207,
|
|
"epoch": 1.161991830383194,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004868726131197436,
|
|
"loss": 5.2579,
|
|
"mean_token_accuracy": 0.1764596402645111,
|
|
"num_tokens": 25911322.0,
|
|
"step": 14935
|
|
},
|
|
{
|
|
"entropy": 5.556664037704468,
|
|
"epoch": 1.1623808597549115,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.0004868632830916212,
|
|
"loss": 5.3542,
|
|
"mean_token_accuracy": 0.17195518016815187,
|
|
"num_tokens": 25920444.0,
|
|
"step": 14940
|
|
},
|
|
{
|
|
"entropy": 5.524413537979126,
|
|
"epoch": 1.1627698891266292,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.0004868539498488106,
|
|
"loss": 5.3632,
|
|
"mean_token_accuracy": 0.1721347987651825,
|
|
"num_tokens": 25928986.0,
|
|
"step": 14945
|
|
},
|
|
{
|
|
"entropy": 5.531350946426391,
|
|
"epoch": 1.1631589184983466,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004868446133914536,
|
|
"loss": 5.3615,
|
|
"mean_token_accuracy": 0.166203336417675,
|
|
"num_tokens": 25938209.0,
|
|
"step": 14950
|
|
},
|
|
{
|
|
"entropy": 5.604267740249634,
|
|
"epoch": 1.163547947870064,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.00048683527371969185,
|
|
"loss": 5.3652,
|
|
"mean_token_accuracy": 0.16511280983686447,
|
|
"num_tokens": 25946909.0,
|
|
"step": 14955
|
|
},
|
|
{
|
|
"entropy": 5.599248695373535,
|
|
"epoch": 1.1639369772417818,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.00048682593083366685,
|
|
"loss": 5.4171,
|
|
"mean_token_accuracy": 0.16767913103103638,
|
|
"num_tokens": 25956154.0,
|
|
"step": 14960
|
|
},
|
|
{
|
|
"entropy": 5.576940107345581,
|
|
"epoch": 1.1643260066134993,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.00048681658473352055,
|
|
"loss": 5.2935,
|
|
"mean_token_accuracy": 0.17817407995462417,
|
|
"num_tokens": 25964478.0,
|
|
"step": 14965
|
|
},
|
|
{
|
|
"entropy": 5.524170589447022,
|
|
"epoch": 1.164715035985217,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.0004868072354193947,
|
|
"loss": 5.2969,
|
|
"mean_token_accuracy": 0.1717832386493683,
|
|
"num_tokens": 25973162.0,
|
|
"step": 14970
|
|
},
|
|
{
|
|
"entropy": 5.522262191772461,
|
|
"epoch": 1.1651040653569344,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.0004867978828914312,
|
|
"loss": 5.2601,
|
|
"mean_token_accuracy": 0.17269359156489372,
|
|
"num_tokens": 25982790.0,
|
|
"step": 14975
|
|
},
|
|
{
|
|
"entropy": 5.542874526977539,
|
|
"epoch": 1.165493094728652,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004867885271497719,
|
|
"loss": 5.2151,
|
|
"mean_token_accuracy": 0.17674386948347093,
|
|
"num_tokens": 25992111.0,
|
|
"step": 14980
|
|
},
|
|
{
|
|
"entropy": 5.596861791610718,
|
|
"epoch": 1.1658821241003696,
|
|
"grad_norm": 1.9296875,
|
|
"learning_rate": 0.0004867791681945588,
|
|
"loss": 5.3512,
|
|
"mean_token_accuracy": 0.16662645041942598,
|
|
"num_tokens": 26000803.0,
|
|
"step": 14985
|
|
},
|
|
{
|
|
"entropy": 5.609333229064942,
|
|
"epoch": 1.166271153472087,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.00048676980602593395,
|
|
"loss": 5.464,
|
|
"mean_token_accuracy": 0.16393478512763976,
|
|
"num_tokens": 26010152.0,
|
|
"step": 14990
|
|
},
|
|
{
|
|
"entropy": 5.588193464279175,
|
|
"epoch": 1.1666601828438048,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.00048676044064403936,
|
|
"loss": 5.3623,
|
|
"mean_token_accuracy": 0.16017225235700608,
|
|
"num_tokens": 26019183.0,
|
|
"step": 14995
|
|
},
|
|
{
|
|
"entropy": 5.591608190536499,
|
|
"epoch": 1.1670492122155223,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004867510720490171,
|
|
"loss": 5.2983,
|
|
"mean_token_accuracy": 0.17426167875528337,
|
|
"num_tokens": 26027459.0,
|
|
"step": 15000
|
|
},
|
|
{
|
|
"epoch": 1.1670492122155223,
|
|
"eval_entropy": 5.3949590197426405,
|
|
"eval_loss": 5.428474426269531,
|
|
"eval_mean_token_accuracy": 0.17521766310304948,
|
|
"eval_num_tokens": 26027459.0,
|
|
"eval_runtime": 28.4227,
|
|
"eval_samples_per_second": 1462.141,
|
|
"eval_steps_per_second": 182.776,
|
|
"step": 15000
|
|
}
|
|
],
|
|
"logging_steps": 5,
|
|
"max_steps": 128520,
|
|
"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": 3.53271292704e+16,
|
|
"train_batch_size": 16,
|
|
"trial_name": null,
|
|
"trial_params": null
|
|
}
|