043a6d536a
Model: fpadovani/ind-latn-100mb-after-ppt-Dp-100mb-ckpt500_seed3407 Source: Original Platform
6046 lines
164 KiB
JSON
6046 lines
164 KiB
JSON
{
|
|
"best_global_step": null,
|
|
"best_metric": null,
|
|
"best_model_checkpoint": null,
|
|
"epoch": 0.2334176230305388,
|
|
"eval_steps": 3000,
|
|
"global_step": 3000,
|
|
"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
|
|
}
|
|
],
|
|
"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": 7097826576384000.0,
|
|
"train_batch_size": 16,
|
|
"trial_name": null,
|
|
"trial_params": null
|
|
}
|