aed82d1883
Model: fpadovani/jpn-jpan-10mb-after-ppt-shuff-dyck-100mb-ckpt500_seed455 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": 0.3462204270051933,
|
|
"eval_steps": 3000,
|
|
"global_step": 3000,
|
|
"is_hyper_param_search": false,
|
|
"is_local_process_zero": true,
|
|
"is_world_process_zero": true,
|
|
"log_history": [
|
|
{
|
|
"entropy": 2.512531781196594,
|
|
"epoch": 0.0005770340450086555,
|
|
"grad_norm": 18.125,
|
|
"learning_rate": 2e-06,
|
|
"loss": 14.35,
|
|
"mean_token_accuracy": 0.04723494742065668,
|
|
"num_tokens": 13337.0,
|
|
"step": 5
|
|
},
|
|
{
|
|
"entropy": 2.5895443677902223,
|
|
"epoch": 0.001154068090017311,
|
|
"grad_norm": 17.5,
|
|
"learning_rate": 4.5e-06,
|
|
"loss": 14.2242,
|
|
"mean_token_accuracy": 0.045978688448667523,
|
|
"num_tokens": 26339.0,
|
|
"step": 10
|
|
},
|
|
{
|
|
"entropy": 2.6310792684555055,
|
|
"epoch": 0.0017311021350259665,
|
|
"grad_norm": 19.5,
|
|
"learning_rate": 7e-06,
|
|
"loss": 14.3304,
|
|
"mean_token_accuracy": 0.03695605173707008,
|
|
"num_tokens": 39118.0,
|
|
"step": 15
|
|
},
|
|
{
|
|
"entropy": 2.683561897277832,
|
|
"epoch": 0.002308136180034622,
|
|
"grad_norm": 20.625,
|
|
"learning_rate": 9.5e-06,
|
|
"loss": 14.3454,
|
|
"mean_token_accuracy": 0.029470206797122957,
|
|
"num_tokens": 51367.0,
|
|
"step": 20
|
|
},
|
|
{
|
|
"entropy": 3.0045490741729735,
|
|
"epoch": 0.0028851702250432777,
|
|
"grad_norm": 25.0,
|
|
"learning_rate": 1.2e-05,
|
|
"loss": 13.9558,
|
|
"mean_token_accuracy": 0.037074245233088735,
|
|
"num_tokens": 64639.0,
|
|
"step": 25
|
|
},
|
|
{
|
|
"entropy": 3.8651180982589723,
|
|
"epoch": 0.003462204270051933,
|
|
"grad_norm": 24.5,
|
|
"learning_rate": 1.4500000000000002e-05,
|
|
"loss": 13.2224,
|
|
"mean_token_accuracy": 0.03461765330284834,
|
|
"num_tokens": 76244.0,
|
|
"step": 30
|
|
},
|
|
{
|
|
"entropy": 5.199391555786133,
|
|
"epoch": 0.004039238315060588,
|
|
"grad_norm": 41.25,
|
|
"learning_rate": 1.7000000000000003e-05,
|
|
"loss": 12.2743,
|
|
"mean_token_accuracy": 0.028778869472444058,
|
|
"num_tokens": 88490.0,
|
|
"step": 35
|
|
},
|
|
{
|
|
"entropy": 8.932403516769408,
|
|
"epoch": 0.004616272360069244,
|
|
"grad_norm": 8.0625,
|
|
"learning_rate": 1.95e-05,
|
|
"loss": 10.7862,
|
|
"mean_token_accuracy": 0.016108644660562277,
|
|
"num_tokens": 102022.0,
|
|
"step": 40
|
|
},
|
|
{
|
|
"entropy": 10.609907341003417,
|
|
"epoch": 0.0051933064050779,
|
|
"grad_norm": 5.03125,
|
|
"learning_rate": 2.2e-05,
|
|
"loss": 10.5807,
|
|
"mean_token_accuracy": 0.008532280148938299,
|
|
"num_tokens": 114442.0,
|
|
"step": 45
|
|
},
|
|
{
|
|
"entropy": 10.433589267730714,
|
|
"epoch": 0.005770340450086555,
|
|
"grad_norm": 2.59375,
|
|
"learning_rate": 2.4500000000000003e-05,
|
|
"loss": 10.4268,
|
|
"mean_token_accuracy": 0.01151183140464127,
|
|
"num_tokens": 128044.0,
|
|
"step": 50
|
|
},
|
|
{
|
|
"entropy": 10.309624099731446,
|
|
"epoch": 0.006347374495095211,
|
|
"grad_norm": 2.5,
|
|
"learning_rate": 2.7e-05,
|
|
"loss": 10.344,
|
|
"mean_token_accuracy": 0.027350079361349346,
|
|
"num_tokens": 141818.0,
|
|
"step": 55
|
|
},
|
|
{
|
|
"entropy": 10.577155780792236,
|
|
"epoch": 0.006924408540103866,
|
|
"grad_norm": 2.265625,
|
|
"learning_rate": 2.95e-05,
|
|
"loss": 10.1314,
|
|
"mean_token_accuracy": 0.03637834042310715,
|
|
"num_tokens": 155109.0,
|
|
"step": 60
|
|
},
|
|
{
|
|
"entropy": 10.506378841400146,
|
|
"epoch": 0.0075014425851125215,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 3.2e-05,
|
|
"loss": 9.9578,
|
|
"mean_token_accuracy": 0.04525792058557272,
|
|
"num_tokens": 167036.0,
|
|
"step": 65
|
|
},
|
|
{
|
|
"entropy": 10.556257247924805,
|
|
"epoch": 0.008078476630121177,
|
|
"grad_norm": 2.34375,
|
|
"learning_rate": 3.4500000000000005e-05,
|
|
"loss": 9.9262,
|
|
"mean_token_accuracy": 0.050815035589039326,
|
|
"num_tokens": 181398.0,
|
|
"step": 70
|
|
},
|
|
{
|
|
"entropy": 10.460558032989502,
|
|
"epoch": 0.008655510675129832,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 3.7e-05,
|
|
"loss": 9.7428,
|
|
"mean_token_accuracy": 0.06986093260347843,
|
|
"num_tokens": 193242.0,
|
|
"step": 75
|
|
},
|
|
{
|
|
"entropy": 10.52681770324707,
|
|
"epoch": 0.009232544720138488,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 3.95e-05,
|
|
"loss": 9.7351,
|
|
"mean_token_accuracy": 0.06739085242152214,
|
|
"num_tokens": 206744.0,
|
|
"step": 80
|
|
},
|
|
{
|
|
"entropy": 10.430398750305176,
|
|
"epoch": 0.009809578765147143,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 4.2000000000000004e-05,
|
|
"loss": 9.6365,
|
|
"mean_token_accuracy": 0.06604859046638012,
|
|
"num_tokens": 219120.0,
|
|
"step": 85
|
|
},
|
|
{
|
|
"entropy": 10.513145351409912,
|
|
"epoch": 0.0103866128101558,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 4.45e-05,
|
|
"loss": 9.5987,
|
|
"mean_token_accuracy": 0.06549847275018691,
|
|
"num_tokens": 231942.0,
|
|
"step": 90
|
|
},
|
|
{
|
|
"entropy": 10.511101913452148,
|
|
"epoch": 0.010963646855164455,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 4.7000000000000004e-05,
|
|
"loss": 9.5376,
|
|
"mean_token_accuracy": 0.07021979242563248,
|
|
"num_tokens": 244786.0,
|
|
"step": 95
|
|
},
|
|
{
|
|
"entropy": 10.338568496704102,
|
|
"epoch": 0.01154068090017311,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 4.9500000000000004e-05,
|
|
"loss": 9.3663,
|
|
"mean_token_accuracy": 0.07713823206722736,
|
|
"num_tokens": 257503.0,
|
|
"step": 100
|
|
},
|
|
{
|
|
"entropy": 10.395394325256348,
|
|
"epoch": 0.012117714945181766,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 5.2e-05,
|
|
"loss": 9.3013,
|
|
"mean_token_accuracy": 0.07871861308813095,
|
|
"num_tokens": 270330.0,
|
|
"step": 105
|
|
},
|
|
{
|
|
"entropy": 10.267610359191895,
|
|
"epoch": 0.012694748990190421,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 5.45e-05,
|
|
"loss": 9.289,
|
|
"mean_token_accuracy": 0.08360295034945012,
|
|
"num_tokens": 283866.0,
|
|
"step": 110
|
|
},
|
|
{
|
|
"entropy": 10.299630165100098,
|
|
"epoch": 0.013271783035199077,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 5.7e-05,
|
|
"loss": 9.219,
|
|
"mean_token_accuracy": 0.07119438238441944,
|
|
"num_tokens": 296715.0,
|
|
"step": 115
|
|
},
|
|
{
|
|
"entropy": 10.345106220245361,
|
|
"epoch": 0.013848817080207732,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 5.9499999999999996e-05,
|
|
"loss": 9.1287,
|
|
"mean_token_accuracy": 0.06990180611610412,
|
|
"num_tokens": 309268.0,
|
|
"step": 120
|
|
},
|
|
{
|
|
"entropy": 10.140081024169922,
|
|
"epoch": 0.014425851125216388,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 6.2e-05,
|
|
"loss": 9.0404,
|
|
"mean_token_accuracy": 0.0861529141664505,
|
|
"num_tokens": 322471.0,
|
|
"step": 125
|
|
},
|
|
{
|
|
"entropy": 10.096904373168945,
|
|
"epoch": 0.015002885170225043,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 6.450000000000001e-05,
|
|
"loss": 9.0344,
|
|
"mean_token_accuracy": 0.07451867423951626,
|
|
"num_tokens": 335728.0,
|
|
"step": 130
|
|
},
|
|
{
|
|
"entropy": 10.11425609588623,
|
|
"epoch": 0.015579919215233698,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 6.7e-05,
|
|
"loss": 8.8978,
|
|
"mean_token_accuracy": 0.07459303736686707,
|
|
"num_tokens": 347861.0,
|
|
"step": 135
|
|
},
|
|
{
|
|
"entropy": 9.995181465148926,
|
|
"epoch": 0.016156953260242354,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 6.950000000000001e-05,
|
|
"loss": 8.868,
|
|
"mean_token_accuracy": 0.08410398475825787,
|
|
"num_tokens": 360275.0,
|
|
"step": 140
|
|
},
|
|
{
|
|
"entropy": 9.862716579437256,
|
|
"epoch": 0.01673398730525101,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 7.2e-05,
|
|
"loss": 8.8007,
|
|
"mean_token_accuracy": 0.07614478804171085,
|
|
"num_tokens": 373948.0,
|
|
"step": 145
|
|
},
|
|
{
|
|
"entropy": 9.893266773223877,
|
|
"epoch": 0.017311021350259664,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 7.45e-05,
|
|
"loss": 8.7368,
|
|
"mean_token_accuracy": 0.07509239986538888,
|
|
"num_tokens": 386267.0,
|
|
"step": 150
|
|
},
|
|
{
|
|
"entropy": 9.75681676864624,
|
|
"epoch": 0.01788805539526832,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 7.7e-05,
|
|
"loss": 8.6465,
|
|
"mean_token_accuracy": 0.07349924966692925,
|
|
"num_tokens": 398595.0,
|
|
"step": 155
|
|
},
|
|
{
|
|
"entropy": 9.599973392486572,
|
|
"epoch": 0.018465089440276975,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 7.950000000000001e-05,
|
|
"loss": 8.5952,
|
|
"mean_token_accuracy": 0.0733072243630886,
|
|
"num_tokens": 410626.0,
|
|
"step": 160
|
|
},
|
|
{
|
|
"entropy": 9.452995586395264,
|
|
"epoch": 0.019042123485285632,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 8.2e-05,
|
|
"loss": 8.5567,
|
|
"mean_token_accuracy": 0.07969285026192666,
|
|
"num_tokens": 423176.0,
|
|
"step": 165
|
|
},
|
|
{
|
|
"entropy": 9.233365058898926,
|
|
"epoch": 0.019619157530294286,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 8.450000000000001e-05,
|
|
"loss": 8.4908,
|
|
"mean_token_accuracy": 0.08393557146191596,
|
|
"num_tokens": 435997.0,
|
|
"step": 170
|
|
},
|
|
{
|
|
"entropy": 9.169007682800293,
|
|
"epoch": 0.020196191575302943,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 8.7e-05,
|
|
"loss": 8.459,
|
|
"mean_token_accuracy": 0.08070328459143639,
|
|
"num_tokens": 449295.0,
|
|
"step": 175
|
|
},
|
|
{
|
|
"entropy": 9.00176544189453,
|
|
"epoch": 0.0207732256203116,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 8.95e-05,
|
|
"loss": 8.4618,
|
|
"mean_token_accuracy": 0.08123850636184216,
|
|
"num_tokens": 463983.0,
|
|
"step": 180
|
|
},
|
|
{
|
|
"entropy": 8.961482334136964,
|
|
"epoch": 0.021350259665320254,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 9.2e-05,
|
|
"loss": 8.4659,
|
|
"mean_token_accuracy": 0.07538431286811828,
|
|
"num_tokens": 476849.0,
|
|
"step": 185
|
|
},
|
|
{
|
|
"entropy": 8.856469058990479,
|
|
"epoch": 0.02192729371032891,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 9.45e-05,
|
|
"loss": 8.4194,
|
|
"mean_token_accuracy": 0.0841868095099926,
|
|
"num_tokens": 489120.0,
|
|
"step": 190
|
|
},
|
|
{
|
|
"entropy": 8.735506343841553,
|
|
"epoch": 0.022504327755337564,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 9.7e-05,
|
|
"loss": 8.338,
|
|
"mean_token_accuracy": 0.08333569169044494,
|
|
"num_tokens": 501085.0,
|
|
"step": 195
|
|
},
|
|
{
|
|
"entropy": 8.774681186676025,
|
|
"epoch": 0.02308136180034622,
|
|
"grad_norm": 0.78515625,
|
|
"learning_rate": 9.95e-05,
|
|
"loss": 8.4191,
|
|
"mean_token_accuracy": 0.07852545715868472,
|
|
"num_tokens": 513207.0,
|
|
"step": 200
|
|
},
|
|
{
|
|
"entropy": 8.802916240692138,
|
|
"epoch": 0.023658395845354875,
|
|
"grad_norm": 0.7890625,
|
|
"learning_rate": 0.000102,
|
|
"loss": 8.3567,
|
|
"mean_token_accuracy": 0.07992818728089332,
|
|
"num_tokens": 524809.0,
|
|
"step": 205
|
|
},
|
|
{
|
|
"entropy": 8.692363357543945,
|
|
"epoch": 0.024235429890363532,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00010449999999999999,
|
|
"loss": 8.3929,
|
|
"mean_token_accuracy": 0.0764585092663765,
|
|
"num_tokens": 538950.0,
|
|
"step": 210
|
|
},
|
|
{
|
|
"entropy": 8.760814189910889,
|
|
"epoch": 0.024812463935372186,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.000107,
|
|
"loss": 8.367,
|
|
"mean_token_accuracy": 0.08504860773682595,
|
|
"num_tokens": 551199.0,
|
|
"step": 215
|
|
},
|
|
{
|
|
"entropy": 8.599481773376464,
|
|
"epoch": 0.025389497980380843,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0001095,
|
|
"loss": 8.3044,
|
|
"mean_token_accuracy": 0.08574924021959304,
|
|
"num_tokens": 563202.0,
|
|
"step": 220
|
|
},
|
|
{
|
|
"entropy": 8.647394752502441,
|
|
"epoch": 0.025966532025389497,
|
|
"grad_norm": 0.6484375,
|
|
"learning_rate": 0.000112,
|
|
"loss": 8.2907,
|
|
"mean_token_accuracy": 0.0885565310716629,
|
|
"num_tokens": 576716.0,
|
|
"step": 225
|
|
},
|
|
{
|
|
"entropy": 8.612112045288086,
|
|
"epoch": 0.026543566070398154,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0001145,
|
|
"loss": 8.3039,
|
|
"mean_token_accuracy": 0.08598211780190468,
|
|
"num_tokens": 588413.0,
|
|
"step": 230
|
|
},
|
|
{
|
|
"entropy": 8.698466682434082,
|
|
"epoch": 0.027120600115406807,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00011700000000000001,
|
|
"loss": 8.3579,
|
|
"mean_token_accuracy": 0.08150896914303303,
|
|
"num_tokens": 602052.0,
|
|
"step": 235
|
|
},
|
|
{
|
|
"entropy": 8.66174020767212,
|
|
"epoch": 0.027697634160415464,
|
|
"grad_norm": 0.72265625,
|
|
"learning_rate": 0.00011949999999999999,
|
|
"loss": 8.3016,
|
|
"mean_token_accuracy": 0.08273345604538918,
|
|
"num_tokens": 614508.0,
|
|
"step": 240
|
|
},
|
|
{
|
|
"entropy": 8.5486985206604,
|
|
"epoch": 0.02827466820542412,
|
|
"grad_norm": 0.79296875,
|
|
"learning_rate": 0.000122,
|
|
"loss": 8.3261,
|
|
"mean_token_accuracy": 0.08385896608233452,
|
|
"num_tokens": 628758.0,
|
|
"step": 245
|
|
},
|
|
{
|
|
"entropy": 8.613620281219482,
|
|
"epoch": 0.028851702250432775,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0001245,
|
|
"loss": 8.2462,
|
|
"mean_token_accuracy": 0.08523005284368992,
|
|
"num_tokens": 641046.0,
|
|
"step": 250
|
|
},
|
|
{
|
|
"entropy": 8.58726749420166,
|
|
"epoch": 0.029428736295441432,
|
|
"grad_norm": 0.76171875,
|
|
"learning_rate": 0.000127,
|
|
"loss": 8.2527,
|
|
"mean_token_accuracy": 0.08660949915647506,
|
|
"num_tokens": 653910.0,
|
|
"step": 255
|
|
},
|
|
{
|
|
"entropy": 8.568908309936523,
|
|
"epoch": 0.030005770340450086,
|
|
"grad_norm": 0.796875,
|
|
"learning_rate": 0.0001295,
|
|
"loss": 8.2246,
|
|
"mean_token_accuracy": 0.08737964332103729,
|
|
"num_tokens": 665862.0,
|
|
"step": 260
|
|
},
|
|
{
|
|
"entropy": 8.553102970123291,
|
|
"epoch": 0.030582804385458743,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.000132,
|
|
"loss": 8.2409,
|
|
"mean_token_accuracy": 0.08849976807832718,
|
|
"num_tokens": 678854.0,
|
|
"step": 265
|
|
},
|
|
{
|
|
"entropy": 8.565754413604736,
|
|
"epoch": 0.031159838430467397,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.00013450000000000002,
|
|
"loss": 8.2342,
|
|
"mean_token_accuracy": 0.08802064135670662,
|
|
"num_tokens": 690188.0,
|
|
"step": 270
|
|
},
|
|
{
|
|
"entropy": 8.613789081573486,
|
|
"epoch": 0.031736872475476054,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00013700000000000002,
|
|
"loss": 8.2052,
|
|
"mean_token_accuracy": 0.09102782309055328,
|
|
"num_tokens": 702041.0,
|
|
"step": 275
|
|
},
|
|
{
|
|
"entropy": 8.503752613067627,
|
|
"epoch": 0.03231390652048471,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0001395,
|
|
"loss": 8.2211,
|
|
"mean_token_accuracy": 0.09037618786096573,
|
|
"num_tokens": 714109.0,
|
|
"step": 280
|
|
},
|
|
{
|
|
"entropy": 8.470402336120605,
|
|
"epoch": 0.03289094056549336,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00014199999999999998,
|
|
"loss": 8.231,
|
|
"mean_token_accuracy": 0.08331561237573623,
|
|
"num_tokens": 726120.0,
|
|
"step": 285
|
|
},
|
|
{
|
|
"entropy": 8.582913875579834,
|
|
"epoch": 0.03346797461050202,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0001445,
|
|
"loss": 8.1805,
|
|
"mean_token_accuracy": 0.09305408522486687,
|
|
"num_tokens": 737868.0,
|
|
"step": 290
|
|
},
|
|
{
|
|
"entropy": 8.502965545654297,
|
|
"epoch": 0.034045008655510675,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000147,
|
|
"loss": 8.2844,
|
|
"mean_token_accuracy": 0.0913321390748024,
|
|
"num_tokens": 751829.0,
|
|
"step": 295
|
|
},
|
|
{
|
|
"entropy": 8.543883037567138,
|
|
"epoch": 0.03462204270051933,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0001495,
|
|
"loss": 8.2192,
|
|
"mean_token_accuracy": 0.09328029677271843,
|
|
"num_tokens": 764457.0,
|
|
"step": 300
|
|
},
|
|
{
|
|
"entropy": 8.415755367279052,
|
|
"epoch": 0.03519907674552799,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.000152,
|
|
"loss": 8.2432,
|
|
"mean_token_accuracy": 0.09327497407793998,
|
|
"num_tokens": 776887.0,
|
|
"step": 305
|
|
},
|
|
{
|
|
"entropy": 8.506604480743409,
|
|
"epoch": 0.03577611079053664,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.00015450000000000001,
|
|
"loss": 8.2075,
|
|
"mean_token_accuracy": 0.09153351783752442,
|
|
"num_tokens": 789001.0,
|
|
"step": 310
|
|
},
|
|
{
|
|
"entropy": 8.496920394897462,
|
|
"epoch": 0.0363531448355453,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.000157,
|
|
"loss": 8.2141,
|
|
"mean_token_accuracy": 0.09203747734427452,
|
|
"num_tokens": 802719.0,
|
|
"step": 315
|
|
},
|
|
{
|
|
"entropy": 8.46874942779541,
|
|
"epoch": 0.03693017888055395,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0001595,
|
|
"loss": 8.1205,
|
|
"mean_token_accuracy": 0.0977991059422493,
|
|
"num_tokens": 815064.0,
|
|
"step": 320
|
|
},
|
|
{
|
|
"entropy": 8.398346996307373,
|
|
"epoch": 0.03750721292556261,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.000162,
|
|
"loss": 8.164,
|
|
"mean_token_accuracy": 0.10131372883915901,
|
|
"num_tokens": 827778.0,
|
|
"step": 325
|
|
},
|
|
{
|
|
"entropy": 8.450510501861572,
|
|
"epoch": 0.038084246970571264,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00016450000000000001,
|
|
"loss": 8.1331,
|
|
"mean_token_accuracy": 0.09271264746785164,
|
|
"num_tokens": 840691.0,
|
|
"step": 330
|
|
},
|
|
{
|
|
"entropy": 8.408138275146484,
|
|
"epoch": 0.03866128101557992,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00016700000000000002,
|
|
"loss": 8.182,
|
|
"mean_token_accuracy": 0.08595972582697868,
|
|
"num_tokens": 852818.0,
|
|
"step": 335
|
|
},
|
|
{
|
|
"entropy": 8.384876346588134,
|
|
"epoch": 0.03923831506058857,
|
|
"grad_norm": 1.84375,
|
|
"learning_rate": 0.00016950000000000003,
|
|
"loss": 8.177,
|
|
"mean_token_accuracy": 0.10347938761115075,
|
|
"num_tokens": 866854.0,
|
|
"step": 340
|
|
},
|
|
{
|
|
"entropy": 8.501971244812012,
|
|
"epoch": 0.03981534910559723,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00017199999999999998,
|
|
"loss": 8.1456,
|
|
"mean_token_accuracy": 0.09828434884548187,
|
|
"num_tokens": 879234.0,
|
|
"step": 345
|
|
},
|
|
{
|
|
"entropy": 8.459957504272461,
|
|
"epoch": 0.040392383150605886,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00017449999999999999,
|
|
"loss": 8.0968,
|
|
"mean_token_accuracy": 0.09369696900248528,
|
|
"num_tokens": 890927.0,
|
|
"step": 350
|
|
},
|
|
{
|
|
"entropy": 8.416207027435302,
|
|
"epoch": 0.04096941719561454,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.000177,
|
|
"loss": 8.1284,
|
|
"mean_token_accuracy": 0.10050402954220772,
|
|
"num_tokens": 902965.0,
|
|
"step": 355
|
|
},
|
|
{
|
|
"entropy": 8.422626209259032,
|
|
"epoch": 0.0415464512406232,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.0001795,
|
|
"loss": 8.0804,
|
|
"mean_token_accuracy": 0.10290733128786086,
|
|
"num_tokens": 916384.0,
|
|
"step": 360
|
|
},
|
|
{
|
|
"entropy": 8.409742259979248,
|
|
"epoch": 0.042123485285631854,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.000182,
|
|
"loss": 8.0126,
|
|
"mean_token_accuracy": 0.10525307431817055,
|
|
"num_tokens": 928618.0,
|
|
"step": 365
|
|
},
|
|
{
|
|
"entropy": 8.309245777130126,
|
|
"epoch": 0.04270051933064051,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0001845,
|
|
"loss": 8.0938,
|
|
"mean_token_accuracy": 0.0991098240017891,
|
|
"num_tokens": 940087.0,
|
|
"step": 370
|
|
},
|
|
{
|
|
"entropy": 8.369062232971192,
|
|
"epoch": 0.04327755337564916,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.000187,
|
|
"loss": 8.0771,
|
|
"mean_token_accuracy": 0.10679042860865592,
|
|
"num_tokens": 953322.0,
|
|
"step": 375
|
|
},
|
|
{
|
|
"entropy": 8.470877838134765,
|
|
"epoch": 0.04385458742065782,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0001895,
|
|
"loss": 8.1176,
|
|
"mean_token_accuracy": 0.1005910687148571,
|
|
"num_tokens": 965815.0,
|
|
"step": 380
|
|
},
|
|
{
|
|
"entropy": 8.311385822296142,
|
|
"epoch": 0.044431621465666475,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000192,
|
|
"loss": 8.0945,
|
|
"mean_token_accuracy": 0.09785286337137222,
|
|
"num_tokens": 978731.0,
|
|
"step": 385
|
|
},
|
|
{
|
|
"entropy": 8.387943077087403,
|
|
"epoch": 0.04500865551067513,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0001945,
|
|
"loss": 7.9726,
|
|
"mean_token_accuracy": 0.11110492274165154,
|
|
"num_tokens": 989505.0,
|
|
"step": 390
|
|
},
|
|
{
|
|
"entropy": 8.284615898132325,
|
|
"epoch": 0.04558568955568378,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00019700000000000002,
|
|
"loss": 8.0892,
|
|
"mean_token_accuracy": 0.10689176395535469,
|
|
"num_tokens": 1001888.0,
|
|
"step": 395
|
|
},
|
|
{
|
|
"entropy": 8.30747365951538,
|
|
"epoch": 0.04616272360069244,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.00019950000000000002,
|
|
"loss": 8.0217,
|
|
"mean_token_accuracy": 0.11540292128920555,
|
|
"num_tokens": 1015362.0,
|
|
"step": 400
|
|
},
|
|
{
|
|
"entropy": 8.404990005493165,
|
|
"epoch": 0.0467397576457011,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.000202,
|
|
"loss": 8.1001,
|
|
"mean_token_accuracy": 0.09940713718533516,
|
|
"num_tokens": 1028700.0,
|
|
"step": 405
|
|
},
|
|
{
|
|
"entropy": 8.34985990524292,
|
|
"epoch": 0.04731679169070975,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00020449999999999998,
|
|
"loss": 8.1157,
|
|
"mean_token_accuracy": 0.10158640816807747,
|
|
"num_tokens": 1040766.0,
|
|
"step": 410
|
|
},
|
|
{
|
|
"entropy": 8.311649894714355,
|
|
"epoch": 0.04789382573571841,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.000207,
|
|
"loss": 7.9689,
|
|
"mean_token_accuracy": 0.10854383111000061,
|
|
"num_tokens": 1054321.0,
|
|
"step": 415
|
|
},
|
|
{
|
|
"entropy": 8.336063480377197,
|
|
"epoch": 0.048470859780727064,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0002095,
|
|
"loss": 8.0275,
|
|
"mean_token_accuracy": 0.11042613610625267,
|
|
"num_tokens": 1065410.0,
|
|
"step": 420
|
|
},
|
|
{
|
|
"entropy": 8.372344303131104,
|
|
"epoch": 0.04904789382573572,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.000212,
|
|
"loss": 8.0589,
|
|
"mean_token_accuracy": 0.09765132367610932,
|
|
"num_tokens": 1077369.0,
|
|
"step": 425
|
|
},
|
|
{
|
|
"entropy": 8.32605962753296,
|
|
"epoch": 0.04962492787074437,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0002145,
|
|
"loss": 8.0076,
|
|
"mean_token_accuracy": 0.10854156166315079,
|
|
"num_tokens": 1089065.0,
|
|
"step": 430
|
|
},
|
|
{
|
|
"entropy": 8.241904735565186,
|
|
"epoch": 0.05020196191575303,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00021700000000000002,
|
|
"loss": 7.9173,
|
|
"mean_token_accuracy": 0.11676707863807678,
|
|
"num_tokens": 1101285.0,
|
|
"step": 435
|
|
},
|
|
{
|
|
"entropy": 8.32933588027954,
|
|
"epoch": 0.050778995960761686,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0002195,
|
|
"loss": 7.9379,
|
|
"mean_token_accuracy": 0.10726014450192452,
|
|
"num_tokens": 1114001.0,
|
|
"step": 440
|
|
},
|
|
{
|
|
"entropy": 8.260017490386963,
|
|
"epoch": 0.05135603000577034,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.000222,
|
|
"loss": 8.0005,
|
|
"mean_token_accuracy": 0.1092146560549736,
|
|
"num_tokens": 1126751.0,
|
|
"step": 445
|
|
},
|
|
{
|
|
"entropy": 8.230885124206543,
|
|
"epoch": 0.05193306405077899,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0002245,
|
|
"loss": 7.991,
|
|
"mean_token_accuracy": 0.10859929993748665,
|
|
"num_tokens": 1140737.0,
|
|
"step": 450
|
|
},
|
|
{
|
|
"entropy": 8.258237075805663,
|
|
"epoch": 0.052510098095787654,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00022700000000000002,
|
|
"loss": 7.9376,
|
|
"mean_token_accuracy": 0.11085548251867294,
|
|
"num_tokens": 1152569.0,
|
|
"step": 455
|
|
},
|
|
{
|
|
"entropy": 8.315269184112548,
|
|
"epoch": 0.05308713214079631,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.00022950000000000002,
|
|
"loss": 7.9535,
|
|
"mean_token_accuracy": 0.11076531112194062,
|
|
"num_tokens": 1166163.0,
|
|
"step": 460
|
|
},
|
|
{
|
|
"entropy": 8.270787239074707,
|
|
"epoch": 0.05366416618580496,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00023200000000000003,
|
|
"loss": 7.9184,
|
|
"mean_token_accuracy": 0.11104324012994767,
|
|
"num_tokens": 1177647.0,
|
|
"step": 465
|
|
},
|
|
{
|
|
"entropy": 8.256643295288086,
|
|
"epoch": 0.054241200230813615,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00023449999999999998,
|
|
"loss": 7.9545,
|
|
"mean_token_accuracy": 0.11232023686170578,
|
|
"num_tokens": 1190884.0,
|
|
"step": 470
|
|
},
|
|
{
|
|
"entropy": 8.198192024230957,
|
|
"epoch": 0.054818234275822275,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.000237,
|
|
"loss": 7.9617,
|
|
"mean_token_accuracy": 0.11213421821594238,
|
|
"num_tokens": 1203276.0,
|
|
"step": 475
|
|
},
|
|
{
|
|
"entropy": 8.210485458374023,
|
|
"epoch": 0.05539526832083093,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0002395,
|
|
"loss": 7.8697,
|
|
"mean_token_accuracy": 0.12074657827615738,
|
|
"num_tokens": 1216001.0,
|
|
"step": 480
|
|
},
|
|
{
|
|
"entropy": 8.263874912261963,
|
|
"epoch": 0.05597230236583958,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000242,
|
|
"loss": 7.971,
|
|
"mean_token_accuracy": 0.11633578017354011,
|
|
"num_tokens": 1228724.0,
|
|
"step": 485
|
|
},
|
|
{
|
|
"entropy": 8.196341419219971,
|
|
"epoch": 0.05654933641084824,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0002445,
|
|
"loss": 7.9923,
|
|
"mean_token_accuracy": 0.11399635374546051,
|
|
"num_tokens": 1242731.0,
|
|
"step": 490
|
|
},
|
|
{
|
|
"entropy": 8.200312662124634,
|
|
"epoch": 0.0571263704558569,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000247,
|
|
"loss": 7.9326,
|
|
"mean_token_accuracy": 0.11518245413899422,
|
|
"num_tokens": 1255275.0,
|
|
"step": 495
|
|
},
|
|
{
|
|
"entropy": 8.26755723953247,
|
|
"epoch": 0.05770340450086555,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0002495,
|
|
"loss": 7.9145,
|
|
"mean_token_accuracy": 0.12056171074509621,
|
|
"num_tokens": 1267719.0,
|
|
"step": 500
|
|
},
|
|
{
|
|
"entropy": 8.105032253265382,
|
|
"epoch": 0.058280438545874204,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.000252,
|
|
"loss": 7.9041,
|
|
"mean_token_accuracy": 0.11403353810310364,
|
|
"num_tokens": 1279960.0,
|
|
"step": 505
|
|
},
|
|
{
|
|
"entropy": 8.281104183197021,
|
|
"epoch": 0.058857472590882864,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0002545,
|
|
"loss": 7.8882,
|
|
"mean_token_accuracy": 0.11356199756264687,
|
|
"num_tokens": 1292570.0,
|
|
"step": 510
|
|
},
|
|
{
|
|
"entropy": 8.16637954711914,
|
|
"epoch": 0.05943450663589152,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000257,
|
|
"loss": 7.8851,
|
|
"mean_token_accuracy": 0.11174787804484368,
|
|
"num_tokens": 1305548.0,
|
|
"step": 515
|
|
},
|
|
{
|
|
"entropy": 8.07060809135437,
|
|
"epoch": 0.06001154068090017,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0002595,
|
|
"loss": 7.828,
|
|
"mean_token_accuracy": 0.12017364054918289,
|
|
"num_tokens": 1318904.0,
|
|
"step": 520
|
|
},
|
|
{
|
|
"entropy": 8.264026546478272,
|
|
"epoch": 0.060588574725908825,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.000262,
|
|
"loss": 7.8875,
|
|
"mean_token_accuracy": 0.11706614196300506,
|
|
"num_tokens": 1332841.0,
|
|
"step": 525
|
|
},
|
|
{
|
|
"entropy": 8.177509117126466,
|
|
"epoch": 0.061165608770917486,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00026450000000000003,
|
|
"loss": 7.8888,
|
|
"mean_token_accuracy": 0.11371787264943123,
|
|
"num_tokens": 1345708.0,
|
|
"step": 530
|
|
},
|
|
{
|
|
"entropy": 8.115266609191895,
|
|
"epoch": 0.06174264281592614,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00026700000000000004,
|
|
"loss": 7.8416,
|
|
"mean_token_accuracy": 0.12110820636153222,
|
|
"num_tokens": 1358611.0,
|
|
"step": 535
|
|
},
|
|
{
|
|
"entropy": 8.071786689758301,
|
|
"epoch": 0.06231967686093479,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00026950000000000005,
|
|
"loss": 7.8965,
|
|
"mean_token_accuracy": 0.11819371730089187,
|
|
"num_tokens": 1372753.0,
|
|
"step": 540
|
|
},
|
|
{
|
|
"entropy": 8.169945526123048,
|
|
"epoch": 0.06289671090594345,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00027200000000000005,
|
|
"loss": 7.8013,
|
|
"mean_token_accuracy": 0.12582628801465034,
|
|
"num_tokens": 1383811.0,
|
|
"step": 545
|
|
},
|
|
{
|
|
"entropy": 8.11972336769104,
|
|
"epoch": 0.06347374495095211,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0002745,
|
|
"loss": 7.8802,
|
|
"mean_token_accuracy": 0.11965988725423812,
|
|
"num_tokens": 1395228.0,
|
|
"step": 550
|
|
},
|
|
{
|
|
"entropy": 8.023060703277588,
|
|
"epoch": 0.06405077899596076,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.000277,
|
|
"loss": 7.8824,
|
|
"mean_token_accuracy": 0.11617207005620003,
|
|
"num_tokens": 1408869.0,
|
|
"step": 555
|
|
},
|
|
{
|
|
"entropy": 8.129542350769043,
|
|
"epoch": 0.06462781304096941,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0002795,
|
|
"loss": 7.7987,
|
|
"mean_token_accuracy": 0.12237567305564881,
|
|
"num_tokens": 1420926.0,
|
|
"step": 560
|
|
},
|
|
{
|
|
"entropy": 8.091229438781738,
|
|
"epoch": 0.06520484708597807,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00028199999999999997,
|
|
"loss": 7.7791,
|
|
"mean_token_accuracy": 0.12508851885795594,
|
|
"num_tokens": 1432435.0,
|
|
"step": 565
|
|
},
|
|
{
|
|
"entropy": 8.181858110427857,
|
|
"epoch": 0.06578188113098672,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0002845,
|
|
"loss": 7.9104,
|
|
"mean_token_accuracy": 0.11593875512480736,
|
|
"num_tokens": 1444716.0,
|
|
"step": 570
|
|
},
|
|
{
|
|
"entropy": 8.023220300674438,
|
|
"epoch": 0.06635891517599539,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000287,
|
|
"loss": 7.8024,
|
|
"mean_token_accuracy": 0.12172861248254777,
|
|
"num_tokens": 1458129.0,
|
|
"step": 575
|
|
},
|
|
{
|
|
"entropy": 8.007987642288208,
|
|
"epoch": 0.06693594922100404,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0002895,
|
|
"loss": 7.7706,
|
|
"mean_token_accuracy": 0.1253301203250885,
|
|
"num_tokens": 1472076.0,
|
|
"step": 580
|
|
},
|
|
{
|
|
"entropy": 8.011878776550294,
|
|
"epoch": 0.0675129832660127,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.000292,
|
|
"loss": 7.7542,
|
|
"mean_token_accuracy": 0.13274379968643188,
|
|
"num_tokens": 1486026.0,
|
|
"step": 585
|
|
},
|
|
{
|
|
"entropy": 8.01979365348816,
|
|
"epoch": 0.06809001731102135,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0002945,
|
|
"loss": 7.772,
|
|
"mean_token_accuracy": 0.13351956158876419,
|
|
"num_tokens": 1498735.0,
|
|
"step": 590
|
|
},
|
|
{
|
|
"entropy": 8.010276079177856,
|
|
"epoch": 0.06866705135603,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.000297,
|
|
"loss": 7.7535,
|
|
"mean_token_accuracy": 0.1248227261006832,
|
|
"num_tokens": 1510755.0,
|
|
"step": 595
|
|
},
|
|
{
|
|
"entropy": 8.088212156295777,
|
|
"epoch": 0.06924408540103866,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0002995,
|
|
"loss": 7.7748,
|
|
"mean_token_accuracy": 0.12387159541249275,
|
|
"num_tokens": 1522386.0,
|
|
"step": 600
|
|
},
|
|
{
|
|
"entropy": 8.043047952651978,
|
|
"epoch": 0.06982111944604731,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000302,
|
|
"loss": 7.8151,
|
|
"mean_token_accuracy": 0.12131175622344018,
|
|
"num_tokens": 1534757.0,
|
|
"step": 605
|
|
},
|
|
{
|
|
"entropy": 8.028788948059082,
|
|
"epoch": 0.07039815349105598,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0003045,
|
|
"loss": 7.7821,
|
|
"mean_token_accuracy": 0.12405301108956338,
|
|
"num_tokens": 1547684.0,
|
|
"step": 610
|
|
},
|
|
{
|
|
"entropy": 8.01380696296692,
|
|
"epoch": 0.07097518753606463,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.000307,
|
|
"loss": 7.7925,
|
|
"mean_token_accuracy": 0.11749588996171952,
|
|
"num_tokens": 1560583.0,
|
|
"step": 615
|
|
},
|
|
{
|
|
"entropy": 8.04894208908081,
|
|
"epoch": 0.07155222158107329,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0003095,
|
|
"loss": 7.787,
|
|
"mean_token_accuracy": 0.11909917891025543,
|
|
"num_tokens": 1573174.0,
|
|
"step": 620
|
|
},
|
|
{
|
|
"entropy": 8.029009103775024,
|
|
"epoch": 0.07212925562608194,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.000312,
|
|
"loss": 7.7789,
|
|
"mean_token_accuracy": 0.12413554638624191,
|
|
"num_tokens": 1585746.0,
|
|
"step": 625
|
|
},
|
|
{
|
|
"entropy": 8.037794351577759,
|
|
"epoch": 0.0727062896710906,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0003145,
|
|
"loss": 7.7608,
|
|
"mean_token_accuracy": 0.12169933542609215,
|
|
"num_tokens": 1598538.0,
|
|
"step": 630
|
|
},
|
|
{
|
|
"entropy": 7.993807029724121,
|
|
"epoch": 0.07328332371609925,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.000317,
|
|
"loss": 7.7304,
|
|
"mean_token_accuracy": 0.12405971959233283,
|
|
"num_tokens": 1612598.0,
|
|
"step": 635
|
|
},
|
|
{
|
|
"entropy": 7.991437578201294,
|
|
"epoch": 0.0738603577611079,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0003195,
|
|
"loss": 7.6674,
|
|
"mean_token_accuracy": 0.12977527305483819,
|
|
"num_tokens": 1624418.0,
|
|
"step": 640
|
|
},
|
|
{
|
|
"entropy": 7.903521156311035,
|
|
"epoch": 0.07443739180611655,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.000322,
|
|
"loss": 7.7507,
|
|
"mean_token_accuracy": 0.13144003003835678,
|
|
"num_tokens": 1637512.0,
|
|
"step": 645
|
|
},
|
|
{
|
|
"entropy": 7.92955265045166,
|
|
"epoch": 0.07501442585112522,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00032450000000000003,
|
|
"loss": 7.6976,
|
|
"mean_token_accuracy": 0.12809038534760475,
|
|
"num_tokens": 1650413.0,
|
|
"step": 650
|
|
},
|
|
{
|
|
"entropy": 7.944208335876465,
|
|
"epoch": 0.07559145989613388,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.00032700000000000003,
|
|
"loss": 7.6683,
|
|
"mean_token_accuracy": 0.12944014593958855,
|
|
"num_tokens": 1662225.0,
|
|
"step": 655
|
|
},
|
|
{
|
|
"entropy": 7.995383930206299,
|
|
"epoch": 0.07616849394114253,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00032950000000000004,
|
|
"loss": 7.7236,
|
|
"mean_token_accuracy": 0.12496703863143921,
|
|
"num_tokens": 1674458.0,
|
|
"step": 660
|
|
},
|
|
{
|
|
"entropy": 7.944713544845581,
|
|
"epoch": 0.07674552798615118,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00033200000000000005,
|
|
"loss": 7.7476,
|
|
"mean_token_accuracy": 0.12143125832080841,
|
|
"num_tokens": 1686366.0,
|
|
"step": 665
|
|
},
|
|
{
|
|
"entropy": 8.000255727767945,
|
|
"epoch": 0.07732256203115984,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.00033450000000000005,
|
|
"loss": 7.7442,
|
|
"mean_token_accuracy": 0.12491990998387337,
|
|
"num_tokens": 1699654.0,
|
|
"step": 670
|
|
},
|
|
{
|
|
"entropy": 7.9440826892852785,
|
|
"epoch": 0.07789959607616849,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000337,
|
|
"loss": 7.6926,
|
|
"mean_token_accuracy": 0.12900558561086656,
|
|
"num_tokens": 1711923.0,
|
|
"step": 675
|
|
},
|
|
{
|
|
"entropy": 7.972041606903076,
|
|
"epoch": 0.07847663012117714,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0003395,
|
|
"loss": 7.6978,
|
|
"mean_token_accuracy": 0.12197642624378205,
|
|
"num_tokens": 1723413.0,
|
|
"step": 680
|
|
},
|
|
{
|
|
"entropy": 7.880360507965088,
|
|
"epoch": 0.07905366416618581,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.000342,
|
|
"loss": 7.6585,
|
|
"mean_token_accuracy": 0.12834955081343652,
|
|
"num_tokens": 1735975.0,
|
|
"step": 685
|
|
},
|
|
{
|
|
"entropy": 7.841808462142945,
|
|
"epoch": 0.07963069821119446,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00034449999999999997,
|
|
"loss": 7.6589,
|
|
"mean_token_accuracy": 0.12771303430199624,
|
|
"num_tokens": 1748563.0,
|
|
"step": 690
|
|
},
|
|
{
|
|
"entropy": 7.920938873291016,
|
|
"epoch": 0.08020773225620312,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000347,
|
|
"loss": 7.685,
|
|
"mean_token_accuracy": 0.1225068636238575,
|
|
"num_tokens": 1762914.0,
|
|
"step": 695
|
|
},
|
|
{
|
|
"entropy": 7.946118593215942,
|
|
"epoch": 0.08078476630121177,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0003495,
|
|
"loss": 7.6416,
|
|
"mean_token_accuracy": 0.13206669613718985,
|
|
"num_tokens": 1776084.0,
|
|
"step": 700
|
|
},
|
|
{
|
|
"entropy": 7.8522233963012695,
|
|
"epoch": 0.08136180034622043,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000352,
|
|
"loss": 7.6597,
|
|
"mean_token_accuracy": 0.12902271673083304,
|
|
"num_tokens": 1789316.0,
|
|
"step": 705
|
|
},
|
|
{
|
|
"entropy": 7.830107116699219,
|
|
"epoch": 0.08193883439122908,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0003545,
|
|
"loss": 7.6724,
|
|
"mean_token_accuracy": 0.1287533812224865,
|
|
"num_tokens": 1801576.0,
|
|
"step": 710
|
|
},
|
|
{
|
|
"entropy": 7.857487392425537,
|
|
"epoch": 0.08251586843623773,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.000357,
|
|
"loss": 7.6286,
|
|
"mean_token_accuracy": 0.12918446362018585,
|
|
"num_tokens": 1814039.0,
|
|
"step": 715
|
|
},
|
|
{
|
|
"entropy": 7.842514276504517,
|
|
"epoch": 0.0830929024812464,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0003595,
|
|
"loss": 7.5683,
|
|
"mean_token_accuracy": 0.13093318343162536,
|
|
"num_tokens": 1825193.0,
|
|
"step": 720
|
|
},
|
|
{
|
|
"entropy": 7.7918308734893795,
|
|
"epoch": 0.08366993652625505,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000362,
|
|
"loss": 7.653,
|
|
"mean_token_accuracy": 0.1273672729730606,
|
|
"num_tokens": 1837983.0,
|
|
"step": 725
|
|
},
|
|
{
|
|
"entropy": 7.921112680435181,
|
|
"epoch": 0.08424697057126371,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0003645,
|
|
"loss": 7.5584,
|
|
"mean_token_accuracy": 0.13639293611049652,
|
|
"num_tokens": 1849830.0,
|
|
"step": 730
|
|
},
|
|
{
|
|
"entropy": 7.83430438041687,
|
|
"epoch": 0.08482400461627236,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.000367,
|
|
"loss": 7.6309,
|
|
"mean_token_accuracy": 0.1251987598836422,
|
|
"num_tokens": 1862577.0,
|
|
"step": 735
|
|
},
|
|
{
|
|
"entropy": 7.849653959274292,
|
|
"epoch": 0.08540103866128101,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0003695,
|
|
"loss": 7.6367,
|
|
"mean_token_accuracy": 0.13423554003238677,
|
|
"num_tokens": 1874888.0,
|
|
"step": 740
|
|
},
|
|
{
|
|
"entropy": 7.746623182296753,
|
|
"epoch": 0.08597807270628967,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.000372,
|
|
"loss": 7.5754,
|
|
"mean_token_accuracy": 0.13472723960876465,
|
|
"num_tokens": 1888400.0,
|
|
"step": 745
|
|
},
|
|
{
|
|
"entropy": 7.872568368911743,
|
|
"epoch": 0.08655510675129832,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0003745,
|
|
"loss": 7.6565,
|
|
"mean_token_accuracy": 0.12168999016284943,
|
|
"num_tokens": 1900961.0,
|
|
"step": 750
|
|
},
|
|
{
|
|
"entropy": 7.816582107543946,
|
|
"epoch": 0.08713214079630698,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.000377,
|
|
"loss": 7.5822,
|
|
"mean_token_accuracy": 0.1359177239239216,
|
|
"num_tokens": 1913410.0,
|
|
"step": 755
|
|
},
|
|
{
|
|
"entropy": 7.774113464355469,
|
|
"epoch": 0.08770917484131564,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0003795,
|
|
"loss": 7.632,
|
|
"mean_token_accuracy": 0.12596142962574958,
|
|
"num_tokens": 1926602.0,
|
|
"step": 760
|
|
},
|
|
{
|
|
"entropy": 7.874756813049316,
|
|
"epoch": 0.0882862088863243,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000382,
|
|
"loss": 7.6001,
|
|
"mean_token_accuracy": 0.1248251162469387,
|
|
"num_tokens": 1938904.0,
|
|
"step": 765
|
|
},
|
|
{
|
|
"entropy": 7.8404929637908936,
|
|
"epoch": 0.08886324293133295,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0003845,
|
|
"loss": 7.6437,
|
|
"mean_token_accuracy": 0.12104213982820511,
|
|
"num_tokens": 1952827.0,
|
|
"step": 770
|
|
},
|
|
{
|
|
"entropy": 7.740968370437622,
|
|
"epoch": 0.0894402769763416,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00038700000000000003,
|
|
"loss": 7.6081,
|
|
"mean_token_accuracy": 0.13230291232466698,
|
|
"num_tokens": 1965182.0,
|
|
"step": 775
|
|
},
|
|
{
|
|
"entropy": 7.757106733322144,
|
|
"epoch": 0.09001731102135026,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00038950000000000003,
|
|
"loss": 7.5679,
|
|
"mean_token_accuracy": 0.12761696726083754,
|
|
"num_tokens": 1976953.0,
|
|
"step": 780
|
|
},
|
|
{
|
|
"entropy": 7.908223438262939,
|
|
"epoch": 0.09059434506635891,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.00039200000000000004,
|
|
"loss": 7.6523,
|
|
"mean_token_accuracy": 0.12661396712064743,
|
|
"num_tokens": 1990019.0,
|
|
"step": 785
|
|
},
|
|
{
|
|
"entropy": 7.842516183853149,
|
|
"epoch": 0.09117137911136756,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00039450000000000005,
|
|
"loss": 7.5967,
|
|
"mean_token_accuracy": 0.1285574607551098,
|
|
"num_tokens": 2002976.0,
|
|
"step": 790
|
|
},
|
|
{
|
|
"entropy": 7.783304500579834,
|
|
"epoch": 0.09174841315637623,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00039700000000000005,
|
|
"loss": 7.606,
|
|
"mean_token_accuracy": 0.12812672331929206,
|
|
"num_tokens": 2017368.0,
|
|
"step": 795
|
|
},
|
|
{
|
|
"entropy": 7.74679274559021,
|
|
"epoch": 0.09232544720138489,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0003995,
|
|
"loss": 7.4697,
|
|
"mean_token_accuracy": 0.13386220484972,
|
|
"num_tokens": 2029838.0,
|
|
"step": 800
|
|
},
|
|
{
|
|
"entropy": 7.811276197433472,
|
|
"epoch": 0.09290248124639354,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000402,
|
|
"loss": 7.5942,
|
|
"mean_token_accuracy": 0.12542516514658927,
|
|
"num_tokens": 2042085.0,
|
|
"step": 805
|
|
},
|
|
{
|
|
"entropy": 7.784253311157227,
|
|
"epoch": 0.0934795152914022,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004045,
|
|
"loss": 7.6123,
|
|
"mean_token_accuracy": 0.12910280898213386,
|
|
"num_tokens": 2053268.0,
|
|
"step": 810
|
|
},
|
|
{
|
|
"entropy": 7.732159948348999,
|
|
"epoch": 0.09405654933641085,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00040699999999999997,
|
|
"loss": 7.5886,
|
|
"mean_token_accuracy": 0.12081153169274331,
|
|
"num_tokens": 2066621.0,
|
|
"step": 815
|
|
},
|
|
{
|
|
"entropy": 7.798933219909668,
|
|
"epoch": 0.0946335833814195,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004095,
|
|
"loss": 7.4894,
|
|
"mean_token_accuracy": 0.12757847532629968,
|
|
"num_tokens": 2079590.0,
|
|
"step": 820
|
|
},
|
|
{
|
|
"entropy": 7.734460258483887,
|
|
"epoch": 0.09521061742642815,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000412,
|
|
"loss": 7.5833,
|
|
"mean_token_accuracy": 0.12265915721654892,
|
|
"num_tokens": 2091729.0,
|
|
"step": 825
|
|
},
|
|
{
|
|
"entropy": 7.6462846279144285,
|
|
"epoch": 0.09578765147143682,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004145,
|
|
"loss": 7.547,
|
|
"mean_token_accuracy": 0.1345345124602318,
|
|
"num_tokens": 2104254.0,
|
|
"step": 830
|
|
},
|
|
{
|
|
"entropy": 7.8504674434661865,
|
|
"epoch": 0.09636468551644548,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.000417,
|
|
"loss": 7.6223,
|
|
"mean_token_accuracy": 0.12215886563062668,
|
|
"num_tokens": 2116327.0,
|
|
"step": 835
|
|
},
|
|
{
|
|
"entropy": 7.772087621688843,
|
|
"epoch": 0.09694171956145413,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004195,
|
|
"loss": 7.5887,
|
|
"mean_token_accuracy": 0.12261896207928658,
|
|
"num_tokens": 2129153.0,
|
|
"step": 840
|
|
},
|
|
{
|
|
"entropy": 7.678793621063233,
|
|
"epoch": 0.09751875360646278,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.000422,
|
|
"loss": 7.5453,
|
|
"mean_token_accuracy": 0.13327833712100984,
|
|
"num_tokens": 2141705.0,
|
|
"step": 845
|
|
},
|
|
{
|
|
"entropy": 7.719631814956665,
|
|
"epoch": 0.09809578765147144,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004245,
|
|
"loss": 7.4725,
|
|
"mean_token_accuracy": 0.13811284452676773,
|
|
"num_tokens": 2153760.0,
|
|
"step": 850
|
|
},
|
|
{
|
|
"entropy": 7.7237812042236325,
|
|
"epoch": 0.09867282169648009,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.000427,
|
|
"loss": 7.5732,
|
|
"mean_token_accuracy": 0.13227060809731483,
|
|
"num_tokens": 2168206.0,
|
|
"step": 855
|
|
},
|
|
{
|
|
"entropy": 7.767458248138428,
|
|
"epoch": 0.09924985574148874,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004295,
|
|
"loss": 7.5144,
|
|
"mean_token_accuracy": 0.13358384743332863,
|
|
"num_tokens": 2180779.0,
|
|
"step": 860
|
|
},
|
|
{
|
|
"entropy": 7.586296081542969,
|
|
"epoch": 0.0998268897864974,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000432,
|
|
"loss": 7.4646,
|
|
"mean_token_accuracy": 0.1356838047504425,
|
|
"num_tokens": 2194075.0,
|
|
"step": 865
|
|
},
|
|
{
|
|
"entropy": 7.7125969409942625,
|
|
"epoch": 0.10040392383150606,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004345,
|
|
"loss": 7.4718,
|
|
"mean_token_accuracy": 0.13414136543869973,
|
|
"num_tokens": 2206424.0,
|
|
"step": 870
|
|
},
|
|
{
|
|
"entropy": 7.709120893478394,
|
|
"epoch": 0.10098095787651472,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.000437,
|
|
"loss": 7.516,
|
|
"mean_token_accuracy": 0.12676840350031854,
|
|
"num_tokens": 2218550.0,
|
|
"step": 875
|
|
},
|
|
{
|
|
"entropy": 7.638567209243774,
|
|
"epoch": 0.10155799192152337,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004395,
|
|
"loss": 7.5389,
|
|
"mean_token_accuracy": 0.13040511906147004,
|
|
"num_tokens": 2231857.0,
|
|
"step": 880
|
|
},
|
|
{
|
|
"entropy": 7.743336486816406,
|
|
"epoch": 0.10213502596653203,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000442,
|
|
"loss": 7.5447,
|
|
"mean_token_accuracy": 0.13032453507184982,
|
|
"num_tokens": 2244057.0,
|
|
"step": 885
|
|
},
|
|
{
|
|
"entropy": 7.807929277420044,
|
|
"epoch": 0.10271206001154068,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004445,
|
|
"loss": 7.5759,
|
|
"mean_token_accuracy": 0.1243269257247448,
|
|
"num_tokens": 2257361.0,
|
|
"step": 890
|
|
},
|
|
{
|
|
"entropy": 7.6737877368927006,
|
|
"epoch": 0.10328909405654933,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.000447,
|
|
"loss": 7.5513,
|
|
"mean_token_accuracy": 0.1263903483748436,
|
|
"num_tokens": 2269599.0,
|
|
"step": 895
|
|
},
|
|
{
|
|
"entropy": 7.745085287094116,
|
|
"epoch": 0.10386612810155799,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00044950000000000003,
|
|
"loss": 7.576,
|
|
"mean_token_accuracy": 0.1303069844841957,
|
|
"num_tokens": 2282791.0,
|
|
"step": 900
|
|
},
|
|
{
|
|
"entropy": 7.7095636367797855,
|
|
"epoch": 0.10444316214656665,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00045200000000000004,
|
|
"loss": 7.5207,
|
|
"mean_token_accuracy": 0.13242215067148208,
|
|
"num_tokens": 2295336.0,
|
|
"step": 905
|
|
},
|
|
{
|
|
"entropy": 7.752670526504517,
|
|
"epoch": 0.10502019619157531,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00045450000000000004,
|
|
"loss": 7.5386,
|
|
"mean_token_accuracy": 0.12832471057772638,
|
|
"num_tokens": 2308813.0,
|
|
"step": 910
|
|
},
|
|
{
|
|
"entropy": 7.666492176055908,
|
|
"epoch": 0.10559723023658396,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00045700000000000005,
|
|
"loss": 7.5173,
|
|
"mean_token_accuracy": 0.12629655599594117,
|
|
"num_tokens": 2321374.0,
|
|
"step": 915
|
|
},
|
|
{
|
|
"entropy": 7.706280326843261,
|
|
"epoch": 0.10617426428159261,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00045950000000000006,
|
|
"loss": 7.5314,
|
|
"mean_token_accuracy": 0.12404570654034615,
|
|
"num_tokens": 2333698.0,
|
|
"step": 920
|
|
},
|
|
{
|
|
"entropy": 7.732450342178344,
|
|
"epoch": 0.10675129832660127,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000462,
|
|
"loss": 7.5129,
|
|
"mean_token_accuracy": 0.13543608784675598,
|
|
"num_tokens": 2346557.0,
|
|
"step": 925
|
|
},
|
|
{
|
|
"entropy": 7.497116231918335,
|
|
"epoch": 0.10732833237160992,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004645,
|
|
"loss": 7.3586,
|
|
"mean_token_accuracy": 0.13911109417676926,
|
|
"num_tokens": 2360003.0,
|
|
"step": 930
|
|
},
|
|
{
|
|
"entropy": 7.704750299453735,
|
|
"epoch": 0.10790536641661858,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000467,
|
|
"loss": 7.4169,
|
|
"mean_token_accuracy": 0.13651928678154945,
|
|
"num_tokens": 2372765.0,
|
|
"step": 935
|
|
},
|
|
{
|
|
"entropy": 7.554190254211425,
|
|
"epoch": 0.10848240046162723,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004695,
|
|
"loss": 7.4229,
|
|
"mean_token_accuracy": 0.13624904453754424,
|
|
"num_tokens": 2385154.0,
|
|
"step": 940
|
|
},
|
|
{
|
|
"entropy": 7.579919815063477,
|
|
"epoch": 0.1090594345066359,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000472,
|
|
"loss": 7.4283,
|
|
"mean_token_accuracy": 0.13729820549488067,
|
|
"num_tokens": 2397264.0,
|
|
"step": 945
|
|
},
|
|
{
|
|
"entropy": 7.707980585098267,
|
|
"epoch": 0.10963646855164455,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004745,
|
|
"loss": 7.5236,
|
|
"mean_token_accuracy": 0.1310661919414997,
|
|
"num_tokens": 2408652.0,
|
|
"step": 950
|
|
},
|
|
{
|
|
"entropy": 7.583171081542969,
|
|
"epoch": 0.1102135025966532,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.000477,
|
|
"loss": 7.4921,
|
|
"mean_token_accuracy": 0.12758150473237037,
|
|
"num_tokens": 2421683.0,
|
|
"step": 955
|
|
},
|
|
{
|
|
"entropy": 7.651930141448974,
|
|
"epoch": 0.11079053664166186,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004795,
|
|
"loss": 7.4028,
|
|
"mean_token_accuracy": 0.13190027326345444,
|
|
"num_tokens": 2434622.0,
|
|
"step": 960
|
|
},
|
|
{
|
|
"entropy": 7.659194564819336,
|
|
"epoch": 0.11136757068667051,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000482,
|
|
"loss": 7.4263,
|
|
"mean_token_accuracy": 0.14118838533759118,
|
|
"num_tokens": 2448157.0,
|
|
"step": 965
|
|
},
|
|
{
|
|
"entropy": 7.696449565887451,
|
|
"epoch": 0.11194460473167916,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004845,
|
|
"loss": 7.4789,
|
|
"mean_token_accuracy": 0.12850709185004233,
|
|
"num_tokens": 2460284.0,
|
|
"step": 970
|
|
},
|
|
{
|
|
"entropy": 7.52245602607727,
|
|
"epoch": 0.11252163877668782,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.000487,
|
|
"loss": 7.476,
|
|
"mean_token_accuracy": 0.1310298591852188,
|
|
"num_tokens": 2473031.0,
|
|
"step": 975
|
|
},
|
|
{
|
|
"entropy": 7.670017910003662,
|
|
"epoch": 0.11309867282169649,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004895,
|
|
"loss": 7.4819,
|
|
"mean_token_accuracy": 0.13639922589063644,
|
|
"num_tokens": 2486870.0,
|
|
"step": 980
|
|
},
|
|
{
|
|
"entropy": 7.584562635421753,
|
|
"epoch": 0.11367570686670514,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000492,
|
|
"loss": 7.3807,
|
|
"mean_token_accuracy": 0.13501427620649337,
|
|
"num_tokens": 2498921.0,
|
|
"step": 985
|
|
},
|
|
{
|
|
"entropy": 7.616317844390869,
|
|
"epoch": 0.1142527409117138,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004945,
|
|
"loss": 7.4674,
|
|
"mean_token_accuracy": 0.12648973166942595,
|
|
"num_tokens": 2511122.0,
|
|
"step": 990
|
|
},
|
|
{
|
|
"entropy": 7.670611572265625,
|
|
"epoch": 0.11482977495672245,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000497,
|
|
"loss": 7.4794,
|
|
"mean_token_accuracy": 0.1284182198345661,
|
|
"num_tokens": 2523726.0,
|
|
"step": 995
|
|
},
|
|
{
|
|
"entropy": 7.538252162933349,
|
|
"epoch": 0.1154068090017311,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004995,
|
|
"loss": 7.3524,
|
|
"mean_token_accuracy": 0.13616370856761933,
|
|
"num_tokens": 2536192.0,
|
|
"step": 1000
|
|
},
|
|
{
|
|
"entropy": 7.569291305541992,
|
|
"epoch": 0.11598384304673975,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004999999975783157,
|
|
"loss": 7.4319,
|
|
"mean_token_accuracy": 0.12918952256441116,
|
|
"num_tokens": 2550200.0,
|
|
"step": 1005
|
|
},
|
|
{
|
|
"entropy": 7.612759971618653,
|
|
"epoch": 0.11656087709174841,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999999877402236,
|
|
"loss": 7.3793,
|
|
"mean_token_accuracy": 0.133512731641531,
|
|
"num_tokens": 2564045.0,
|
|
"step": 1010
|
|
},
|
|
{
|
|
"entropy": 7.557199764251709,
|
|
"epoch": 0.11713791113675708,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999999703343686,
|
|
"loss": 7.3972,
|
|
"mean_token_accuracy": 0.12909132093191147,
|
|
"num_tokens": 2576210.0,
|
|
"step": 1015
|
|
},
|
|
{
|
|
"entropy": 7.435172700881958,
|
|
"epoch": 0.11771494518176573,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004999999453607515,
|
|
"loss": 7.378,
|
|
"mean_token_accuracy": 0.1307467371225357,
|
|
"num_tokens": 2589325.0,
|
|
"step": 1020
|
|
},
|
|
{
|
|
"entropy": 7.680232429504395,
|
|
"epoch": 0.11829197922677438,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999999128193729,
|
|
"loss": 7.4734,
|
|
"mean_token_accuracy": 0.13209090158343315,
|
|
"num_tokens": 2601522.0,
|
|
"step": 1025
|
|
},
|
|
{
|
|
"entropy": 7.629494333267212,
|
|
"epoch": 0.11886901327178304,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000499999872710234,
|
|
"loss": 7.4398,
|
|
"mean_token_accuracy": 0.1303465448319912,
|
|
"num_tokens": 2615364.0,
|
|
"step": 1030
|
|
},
|
|
{
|
|
"entropy": 7.538928461074829,
|
|
"epoch": 0.11944604731679169,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004999998250333361,
|
|
"loss": 7.3623,
|
|
"mean_token_accuracy": 0.13469313830137253,
|
|
"num_tokens": 2628528.0,
|
|
"step": 1035
|
|
},
|
|
{
|
|
"entropy": 7.55066442489624,
|
|
"epoch": 0.12002308136180034,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.000499999769788681,
|
|
"loss": 7.3676,
|
|
"mean_token_accuracy": 0.13092967718839646,
|
|
"num_tokens": 2641877.0,
|
|
"step": 1040
|
|
},
|
|
{
|
|
"entropy": 7.518403100967407,
|
|
"epoch": 0.120600115406809,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999997069762703,
|
|
"loss": 7.3645,
|
|
"mean_token_accuracy": 0.1341833934187889,
|
|
"num_tokens": 2655419.0,
|
|
"step": 1045
|
|
},
|
|
{
|
|
"entropy": 7.514628076553345,
|
|
"epoch": 0.12117714945181765,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999996365961062,
|
|
"loss": 7.3271,
|
|
"mean_token_accuracy": 0.1362943857908249,
|
|
"num_tokens": 2667551.0,
|
|
"step": 1050
|
|
},
|
|
{
|
|
"entropy": 7.557382869720459,
|
|
"epoch": 0.12175418349682632,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999995586481912,
|
|
"loss": 7.3534,
|
|
"mean_token_accuracy": 0.13944169133901596,
|
|
"num_tokens": 2679948.0,
|
|
"step": 1055
|
|
},
|
|
{
|
|
"entropy": 7.471993780136108,
|
|
"epoch": 0.12233121754183497,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004999994731325276,
|
|
"loss": 7.3972,
|
|
"mean_token_accuracy": 0.1320507399737835,
|
|
"num_tokens": 2691501.0,
|
|
"step": 1060
|
|
},
|
|
{
|
|
"entropy": 7.50092716217041,
|
|
"epoch": 0.12290825158684363,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999993800491187,
|
|
"loss": 7.3195,
|
|
"mean_token_accuracy": 0.1353978231549263,
|
|
"num_tokens": 2702689.0,
|
|
"step": 1065
|
|
},
|
|
{
|
|
"entropy": 7.551953458786011,
|
|
"epoch": 0.12348528563185228,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004999992793979672,
|
|
"loss": 7.3338,
|
|
"mean_token_accuracy": 0.1352718137204647,
|
|
"num_tokens": 2715023.0,
|
|
"step": 1070
|
|
},
|
|
{
|
|
"entropy": 7.482572031021118,
|
|
"epoch": 0.12406231967686093,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004999991711790769,
|
|
"loss": 7.25,
|
|
"mean_token_accuracy": 0.13727134317159653,
|
|
"num_tokens": 2729517.0,
|
|
"step": 1075
|
|
},
|
|
{
|
|
"entropy": 7.496352291107177,
|
|
"epoch": 0.12463935372186959,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004999990553924511,
|
|
"loss": 7.3561,
|
|
"mean_token_accuracy": 0.13238862976431848,
|
|
"num_tokens": 2740984.0,
|
|
"step": 1080
|
|
},
|
|
{
|
|
"entropy": 7.511165189743042,
|
|
"epoch": 0.12521638776687824,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004999989320380939,
|
|
"loss": 7.3101,
|
|
"mean_token_accuracy": 0.1363685481250286,
|
|
"num_tokens": 2752943.0,
|
|
"step": 1085
|
|
},
|
|
{
|
|
"entropy": 7.534621715545654,
|
|
"epoch": 0.1257934218118869,
|
|
"grad_norm": 0.79296875,
|
|
"learning_rate": 0.0004999988011160094,
|
|
"loss": 7.3589,
|
|
"mean_token_accuracy": 0.13417960107326507,
|
|
"num_tokens": 2765613.0,
|
|
"step": 1090
|
|
},
|
|
{
|
|
"entropy": 7.450796127319336,
|
|
"epoch": 0.12637045585689555,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.000499998662626202,
|
|
"loss": 7.2979,
|
|
"mean_token_accuracy": 0.1321871429681778,
|
|
"num_tokens": 2776820.0,
|
|
"step": 1095
|
|
},
|
|
{
|
|
"entropy": 7.463679599761963,
|
|
"epoch": 0.12694748990190421,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004999985165686764,
|
|
"loss": 7.3429,
|
|
"mean_token_accuracy": 0.13456639721989633,
|
|
"num_tokens": 2788981.0,
|
|
"step": 1100
|
|
},
|
|
{
|
|
"entropy": 7.459660530090332,
|
|
"epoch": 0.12752452394691285,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004999983629434373,
|
|
"loss": 7.1963,
|
|
"mean_token_accuracy": 0.1402936853468418,
|
|
"num_tokens": 2801975.0,
|
|
"step": 1105
|
|
},
|
|
{
|
|
"entropy": 7.450168704986572,
|
|
"epoch": 0.12810155799192152,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004999982017504901,
|
|
"loss": 7.2817,
|
|
"mean_token_accuracy": 0.1321284957230091,
|
|
"num_tokens": 2814708.0,
|
|
"step": 1110
|
|
},
|
|
{
|
|
"entropy": 7.456075811386109,
|
|
"epoch": 0.1286785920369302,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004999980329898401,
|
|
"loss": 7.302,
|
|
"mean_token_accuracy": 0.13727107644081116,
|
|
"num_tokens": 2827903.0,
|
|
"step": 1115
|
|
},
|
|
{
|
|
"entropy": 7.500937414169312,
|
|
"epoch": 0.12925562608193883,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000499997856661493,
|
|
"loss": 7.3277,
|
|
"mean_token_accuracy": 0.13589581474661827,
|
|
"num_tokens": 2841077.0,
|
|
"step": 1120
|
|
},
|
|
{
|
|
"entropy": 7.48737940788269,
|
|
"epoch": 0.1298326601269475,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.000499997672765455,
|
|
"loss": 7.3185,
|
|
"mean_token_accuracy": 0.13034305721521378,
|
|
"num_tokens": 2853235.0,
|
|
"step": 1125
|
|
},
|
|
{
|
|
"entropy": 7.418439817428589,
|
|
"epoch": 0.13040969417195614,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004999974813017318,
|
|
"loss": 7.288,
|
|
"mean_token_accuracy": 0.1318283796310425,
|
|
"num_tokens": 2864937.0,
|
|
"step": 1130
|
|
},
|
|
{
|
|
"entropy": 7.438732004165649,
|
|
"epoch": 0.1309867282169648,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004999972822703301,
|
|
"loss": 7.2431,
|
|
"mean_token_accuracy": 0.14729652926325798,
|
|
"num_tokens": 2877791.0,
|
|
"step": 1135
|
|
},
|
|
{
|
|
"entropy": 7.374364995956421,
|
|
"epoch": 0.13156376226197344,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999970756712567,
|
|
"loss": 7.2388,
|
|
"mean_token_accuracy": 0.13121830448508262,
|
|
"num_tokens": 2889897.0,
|
|
"step": 1140
|
|
},
|
|
{
|
|
"entropy": 7.502627754211426,
|
|
"epoch": 0.1321407963069821,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004999968615045183,
|
|
"loss": 7.2464,
|
|
"mean_token_accuracy": 0.13865444660186768,
|
|
"num_tokens": 2902806.0,
|
|
"step": 1145
|
|
},
|
|
{
|
|
"entropy": 7.364279270172119,
|
|
"epoch": 0.13271783035199078,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004999966397701222,
|
|
"loss": 7.1478,
|
|
"mean_token_accuracy": 0.14386670887470246,
|
|
"num_tokens": 2915703.0,
|
|
"step": 1150
|
|
},
|
|
{
|
|
"entropy": 7.446257495880127,
|
|
"epoch": 0.13329486439699942,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004999964104680759,
|
|
"loss": 7.3489,
|
|
"mean_token_accuracy": 0.12771031260490417,
|
|
"num_tokens": 2928171.0,
|
|
"step": 1155
|
|
},
|
|
{
|
|
"entropy": 7.4577220439910885,
|
|
"epoch": 0.13387189844200809,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004999961735983871,
|
|
"loss": 7.1758,
|
|
"mean_token_accuracy": 0.14841930717229843,
|
|
"num_tokens": 2939909.0,
|
|
"step": 1160
|
|
},
|
|
{
|
|
"entropy": 7.482584476470947,
|
|
"epoch": 0.13444893248701673,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004999959291610639,
|
|
"loss": 7.3014,
|
|
"mean_token_accuracy": 0.13288074284791945,
|
|
"num_tokens": 2951510.0,
|
|
"step": 1165
|
|
},
|
|
{
|
|
"entropy": 7.388064241409301,
|
|
"epoch": 0.1350259665320254,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004999956771561143,
|
|
"loss": 7.2356,
|
|
"mean_token_accuracy": 0.1302425242960453,
|
|
"num_tokens": 2963326.0,
|
|
"step": 1170
|
|
},
|
|
{
|
|
"entropy": 7.376373052597046,
|
|
"epoch": 0.13560300057703403,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004999954175835469,
|
|
"loss": 7.2405,
|
|
"mean_token_accuracy": 0.14472833275794983,
|
|
"num_tokens": 2976226.0,
|
|
"step": 1175
|
|
},
|
|
{
|
|
"entropy": 7.442576217651367,
|
|
"epoch": 0.1361800346220427,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004999951504433703,
|
|
"loss": 7.255,
|
|
"mean_token_accuracy": 0.13099167943000795,
|
|
"num_tokens": 2988180.0,
|
|
"step": 1180
|
|
},
|
|
{
|
|
"entropy": 7.3849358558654785,
|
|
"epoch": 0.13675706866705137,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004999948757355935,
|
|
"loss": 7.2402,
|
|
"mean_token_accuracy": 0.13745544701814652,
|
|
"num_tokens": 3000215.0,
|
|
"step": 1185
|
|
},
|
|
{
|
|
"entropy": 7.460414743423462,
|
|
"epoch": 0.13733410271206,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.000499994593460226,
|
|
"loss": 7.2419,
|
|
"mean_token_accuracy": 0.13573380932211876,
|
|
"num_tokens": 3012516.0,
|
|
"step": 1190
|
|
},
|
|
{
|
|
"entropy": 7.335642337799072,
|
|
"epoch": 0.13791113675706868,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004999943036172771,
|
|
"loss": 7.2407,
|
|
"mean_token_accuracy": 0.13760888651013375,
|
|
"num_tokens": 3024786.0,
|
|
"step": 1195
|
|
},
|
|
{
|
|
"entropy": 7.41163215637207,
|
|
"epoch": 0.13848817080207732,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004999940062067565,
|
|
"loss": 7.1789,
|
|
"mean_token_accuracy": 0.1398928850889206,
|
|
"num_tokens": 3037179.0,
|
|
"step": 1200
|
|
},
|
|
{
|
|
"entropy": 7.380322027206421,
|
|
"epoch": 0.13906520484708598,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004999937012286742,
|
|
"loss": 7.2651,
|
|
"mean_token_accuracy": 0.1392878621816635,
|
|
"num_tokens": 3049443.0,
|
|
"step": 1205
|
|
},
|
|
{
|
|
"entropy": 7.35688591003418,
|
|
"epoch": 0.13964223889209462,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999933886830405,
|
|
"loss": 7.1713,
|
|
"mean_token_accuracy": 0.133247160166502,
|
|
"num_tokens": 3061857.0,
|
|
"step": 1210
|
|
},
|
|
{
|
|
"entropy": 7.40545539855957,
|
|
"epoch": 0.1402192729371033,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.000499993068569866,
|
|
"loss": 7.2008,
|
|
"mean_token_accuracy": 0.14127044454216958,
|
|
"num_tokens": 3075185.0,
|
|
"step": 1215
|
|
},
|
|
{
|
|
"entropy": 7.398829460144043,
|
|
"epoch": 0.14079630698211196,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004999927408891614,
|
|
"loss": 7.2143,
|
|
"mean_token_accuracy": 0.14073001742362976,
|
|
"num_tokens": 3087645.0,
|
|
"step": 1220
|
|
},
|
|
{
|
|
"entropy": 7.389093589782715,
|
|
"epoch": 0.1413733410271206,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004999924056409378,
|
|
"loss": 7.2218,
|
|
"mean_token_accuracy": 0.13467969745397568,
|
|
"num_tokens": 3101185.0,
|
|
"step": 1225
|
|
},
|
|
{
|
|
"entropy": 7.341273593902588,
|
|
"epoch": 0.14195037507212926,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004999920628252063,
|
|
"loss": 7.1938,
|
|
"mean_token_accuracy": 0.13926867693662642,
|
|
"num_tokens": 3113694.0,
|
|
"step": 1230
|
|
},
|
|
{
|
|
"entropy": 7.389741516113281,
|
|
"epoch": 0.1425274091171379,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004999917124419785,
|
|
"loss": 7.2361,
|
|
"mean_token_accuracy": 0.1366308718919754,
|
|
"num_tokens": 3128225.0,
|
|
"step": 1235
|
|
},
|
|
{
|
|
"entropy": 7.346083259582519,
|
|
"epoch": 0.14310444316214657,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004999913544912664,
|
|
"loss": 7.1621,
|
|
"mean_token_accuracy": 0.14138347059488296,
|
|
"num_tokens": 3140118.0,
|
|
"step": 1240
|
|
},
|
|
{
|
|
"entropy": 7.316737031936645,
|
|
"epoch": 0.1436814772071552,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004999909889730817,
|
|
"loss": 7.2285,
|
|
"mean_token_accuracy": 0.13803385123610495,
|
|
"num_tokens": 3153479.0,
|
|
"step": 1245
|
|
},
|
|
{
|
|
"entropy": 7.433447456359863,
|
|
"epoch": 0.14425851125216388,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999906158874368,
|
|
"loss": 7.2226,
|
|
"mean_token_accuracy": 0.14075266495347022,
|
|
"num_tokens": 3167062.0,
|
|
"step": 1250
|
|
},
|
|
{
|
|
"entropy": 7.32918004989624,
|
|
"epoch": 0.14483554529717255,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004999902352343444,
|
|
"loss": 7.181,
|
|
"mean_token_accuracy": 0.13708969652652742,
|
|
"num_tokens": 3179061.0,
|
|
"step": 1255
|
|
},
|
|
{
|
|
"entropy": 7.340552043914795,
|
|
"epoch": 0.1454125793421812,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004999898470138171,
|
|
"loss": 7.1299,
|
|
"mean_token_accuracy": 0.137362752109766,
|
|
"num_tokens": 3191333.0,
|
|
"step": 1260
|
|
},
|
|
{
|
|
"entropy": 7.366755676269531,
|
|
"epoch": 0.14598961338718985,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004999894512258681,
|
|
"loss": 7.2347,
|
|
"mean_token_accuracy": 0.1339644305408001,
|
|
"num_tokens": 3204487.0,
|
|
"step": 1265
|
|
},
|
|
{
|
|
"entropy": 7.3037999153137205,
|
|
"epoch": 0.1465666474321985,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004999890478705107,
|
|
"loss": 7.2018,
|
|
"mean_token_accuracy": 0.1373523458838463,
|
|
"num_tokens": 3216733.0,
|
|
"step": 1270
|
|
},
|
|
{
|
|
"entropy": 7.35508165359497,
|
|
"epoch": 0.14714368147720716,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004999886369477585,
|
|
"loss": 7.1258,
|
|
"mean_token_accuracy": 0.14343418851494788,
|
|
"num_tokens": 3229605.0,
|
|
"step": 1275
|
|
},
|
|
{
|
|
"entropy": 7.294068384170532,
|
|
"epoch": 0.1477207155222158,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004999882184576251,
|
|
"loss": 7.1764,
|
|
"mean_token_accuracy": 0.13913899287581444,
|
|
"num_tokens": 3241023.0,
|
|
"step": 1280
|
|
},
|
|
{
|
|
"entropy": 7.356681680679321,
|
|
"epoch": 0.14829774956722447,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004999877924001248,
|
|
"loss": 7.1466,
|
|
"mean_token_accuracy": 0.1401684083044529,
|
|
"num_tokens": 3252435.0,
|
|
"step": 1285
|
|
},
|
|
{
|
|
"entropy": 7.2978212356567385,
|
|
"epoch": 0.1488747836122331,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004999873587752718,
|
|
"loss": 7.1465,
|
|
"mean_token_accuracy": 0.14340650513768197,
|
|
"num_tokens": 3265663.0,
|
|
"step": 1290
|
|
},
|
|
{
|
|
"entropy": 7.384179496765137,
|
|
"epoch": 0.14945181765724178,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004999869175830808,
|
|
"loss": 7.2055,
|
|
"mean_token_accuracy": 0.13356677517294885,
|
|
"num_tokens": 3278309.0,
|
|
"step": 1295
|
|
},
|
|
{
|
|
"entropy": 7.367056083679199,
|
|
"epoch": 0.15002885170225044,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004999864688235666,
|
|
"loss": 7.2115,
|
|
"mean_token_accuracy": 0.1325480066239834,
|
|
"num_tokens": 3290899.0,
|
|
"step": 1300
|
|
},
|
|
{
|
|
"entropy": 7.298659467697144,
|
|
"epoch": 0.15060588574725908,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004999860124967442,
|
|
"loss": 7.1556,
|
|
"mean_token_accuracy": 0.13973417952656747,
|
|
"num_tokens": 3304383.0,
|
|
"step": 1305
|
|
},
|
|
{
|
|
"entropy": 7.280820751190186,
|
|
"epoch": 0.15118291979226775,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004999855486026291,
|
|
"loss": 7.1489,
|
|
"mean_token_accuracy": 0.13906904980540274,
|
|
"num_tokens": 3316310.0,
|
|
"step": 1310
|
|
},
|
|
{
|
|
"entropy": 7.3616657733917235,
|
|
"epoch": 0.1517599538372764,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004999850771412369,
|
|
"loss": 7.2426,
|
|
"mean_token_accuracy": 0.13819348588585853,
|
|
"num_tokens": 3330018.0,
|
|
"step": 1315
|
|
},
|
|
{
|
|
"entropy": 7.392954874038696,
|
|
"epoch": 0.15233698788228506,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999845981125832,
|
|
"loss": 7.3005,
|
|
"mean_token_accuracy": 0.1357297696173191,
|
|
"num_tokens": 3343134.0,
|
|
"step": 1320
|
|
},
|
|
{
|
|
"entropy": 7.2494100570678714,
|
|
"epoch": 0.1529140219272937,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004999841115166844,
|
|
"loss": 7.0969,
|
|
"mean_token_accuracy": 0.14118720814585686,
|
|
"num_tokens": 3356262.0,
|
|
"step": 1325
|
|
},
|
|
{
|
|
"entropy": 7.343341732025147,
|
|
"epoch": 0.15349105597230236,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004999836173535568,
|
|
"loss": 7.2429,
|
|
"mean_token_accuracy": 0.12794803753495215,
|
|
"num_tokens": 3369672.0,
|
|
"step": 1330
|
|
},
|
|
{
|
|
"entropy": 7.342515563964843,
|
|
"epoch": 0.15406809001731103,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004999831156232169,
|
|
"loss": 7.1474,
|
|
"mean_token_accuracy": 0.14077327102422715,
|
|
"num_tokens": 3381677.0,
|
|
"step": 1335
|
|
},
|
|
{
|
|
"entropy": 7.262819242477417,
|
|
"epoch": 0.15464512406231967,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004999826063256818,
|
|
"loss": 7.0818,
|
|
"mean_token_accuracy": 0.14118852764368056,
|
|
"num_tokens": 3394662.0,
|
|
"step": 1340
|
|
},
|
|
{
|
|
"entropy": 7.284024095535278,
|
|
"epoch": 0.15522215810732834,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004999820894609683,
|
|
"loss": 7.0937,
|
|
"mean_token_accuracy": 0.14023175537586213,
|
|
"num_tokens": 3407286.0,
|
|
"step": 1345
|
|
},
|
|
{
|
|
"entropy": 7.391539764404297,
|
|
"epoch": 0.15579919215233698,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004999815650290941,
|
|
"loss": 7.2068,
|
|
"mean_token_accuracy": 0.13057266250252725,
|
|
"num_tokens": 3419478.0,
|
|
"step": 1350
|
|
},
|
|
{
|
|
"entropy": 7.242104721069336,
|
|
"epoch": 0.15637622619734565,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004999810330300766,
|
|
"loss": 7.1625,
|
|
"mean_token_accuracy": 0.13775511607527732,
|
|
"num_tokens": 3433188.0,
|
|
"step": 1355
|
|
},
|
|
{
|
|
"entropy": 7.366675519943238,
|
|
"epoch": 0.1569532602423543,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.000499980493463934,
|
|
"loss": 7.0901,
|
|
"mean_token_accuracy": 0.13610174432396888,
|
|
"num_tokens": 3445806.0,
|
|
"step": 1360
|
|
},
|
|
{
|
|
"entropy": 7.216462755203247,
|
|
"epoch": 0.15753029428736295,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.0004999799463306841,
|
|
"loss": 7.1471,
|
|
"mean_token_accuracy": 0.13988320752978325,
|
|
"num_tokens": 3458931.0,
|
|
"step": 1365
|
|
},
|
|
{
|
|
"entropy": 7.320661640167236,
|
|
"epoch": 0.15810732833237162,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004999793916303455,
|
|
"loss": 7.1803,
|
|
"mean_token_accuracy": 0.13539275228977204,
|
|
"num_tokens": 3471338.0,
|
|
"step": 1370
|
|
},
|
|
{
|
|
"entropy": 7.3501372814178465,
|
|
"epoch": 0.15868436237738026,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004999788293629368,
|
|
"loss": 7.2315,
|
|
"mean_token_accuracy": 0.13646726906299592,
|
|
"num_tokens": 3484865.0,
|
|
"step": 1375
|
|
},
|
|
{
|
|
"entropy": 7.3266260623931885,
|
|
"epoch": 0.15926139642238893,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.000499978259528477,
|
|
"loss": 7.0678,
|
|
"mean_token_accuracy": 0.14280698746442794,
|
|
"num_tokens": 3496676.0,
|
|
"step": 1380
|
|
},
|
|
{
|
|
"entropy": 7.195064067840576,
|
|
"epoch": 0.15983843046739757,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004999776821269852,
|
|
"loss": 7.0447,
|
|
"mean_token_accuracy": 0.1451018936932087,
|
|
"num_tokens": 3508748.0,
|
|
"step": 1385
|
|
},
|
|
{
|
|
"entropy": 7.267773008346557,
|
|
"epoch": 0.16041546451240624,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004999770971584807,
|
|
"loss": 7.1826,
|
|
"mean_token_accuracy": 0.13283163756132127,
|
|
"num_tokens": 3521490.0,
|
|
"step": 1390
|
|
},
|
|
{
|
|
"entropy": 7.2999695301055905,
|
|
"epoch": 0.16099249855741488,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004999765046229834,
|
|
"loss": 7.1451,
|
|
"mean_token_accuracy": 0.13972139805555345,
|
|
"num_tokens": 3534092.0,
|
|
"step": 1395
|
|
},
|
|
{
|
|
"entropy": 7.30112590789795,
|
|
"epoch": 0.16156953260242354,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.000499975904520513,
|
|
"loss": 7.1229,
|
|
"mean_token_accuracy": 0.13600729033350945,
|
|
"num_tokens": 3546583.0,
|
|
"step": 1400
|
|
},
|
|
{
|
|
"entropy": 7.261274099349976,
|
|
"epoch": 0.1621465666474322,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.00049997529685109,
|
|
"loss": 7.0986,
|
|
"mean_token_accuracy": 0.13902345672249794,
|
|
"num_tokens": 3559409.0,
|
|
"step": 1405
|
|
},
|
|
{
|
|
"entropy": 7.244414520263672,
|
|
"epoch": 0.16272360069244085,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004999746816147344,
|
|
"loss": 7.1063,
|
|
"mean_token_accuracy": 0.13943156972527504,
|
|
"num_tokens": 3572362.0,
|
|
"step": 1410
|
|
},
|
|
{
|
|
"entropy": 7.205703496932983,
|
|
"epoch": 0.16330063473744952,
|
|
"grad_norm": 0.7890625,
|
|
"learning_rate": 0.0004999740588114673,
|
|
"loss": 7.0916,
|
|
"mean_token_accuracy": 0.14903789088129998,
|
|
"num_tokens": 3585505.0,
|
|
"step": 1415
|
|
},
|
|
{
|
|
"entropy": 7.34771957397461,
|
|
"epoch": 0.16387766878245816,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004999734284413095,
|
|
"loss": 7.1202,
|
|
"mean_token_accuracy": 0.14055844619870186,
|
|
"num_tokens": 3597322.0,
|
|
"step": 1420
|
|
},
|
|
{
|
|
"entropy": 7.172052621841431,
|
|
"epoch": 0.16445470282746683,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.000499972790504282,
|
|
"loss": 7.1121,
|
|
"mean_token_accuracy": 0.13925491869449616,
|
|
"num_tokens": 3609941.0,
|
|
"step": 1425
|
|
},
|
|
{
|
|
"entropy": 7.33465166091919,
|
|
"epoch": 0.16503173687247547,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004999721450004067,
|
|
"loss": 7.1586,
|
|
"mean_token_accuracy": 0.13594435006380082,
|
|
"num_tokens": 3621751.0,
|
|
"step": 1430
|
|
},
|
|
{
|
|
"entropy": 7.223167848587036,
|
|
"epoch": 0.16560877091748413,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004999714919297049,
|
|
"loss": 7.1104,
|
|
"mean_token_accuracy": 0.13295586705207824,
|
|
"num_tokens": 3633070.0,
|
|
"step": 1435
|
|
},
|
|
{
|
|
"entropy": 7.267610120773315,
|
|
"epoch": 0.1661858049624928,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004999708312921987,
|
|
"loss": 7.0962,
|
|
"mean_token_accuracy": 0.13987760469317437,
|
|
"num_tokens": 3646730.0,
|
|
"step": 1440
|
|
},
|
|
{
|
|
"entropy": 7.284721183776855,
|
|
"epoch": 0.16676283900750144,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004999701630879103,
|
|
"loss": 7.1188,
|
|
"mean_token_accuracy": 0.1329401448369026,
|
|
"num_tokens": 3659976.0,
|
|
"step": 1445
|
|
},
|
|
{
|
|
"entropy": 7.247362232208252,
|
|
"epoch": 0.1673398730525101,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004999694873168623,
|
|
"loss": 7.0619,
|
|
"mean_token_accuracy": 0.13823318034410476,
|
|
"num_tokens": 3672607.0,
|
|
"step": 1450
|
|
},
|
|
{
|
|
"entropy": 7.093194961547852,
|
|
"epoch": 0.16791690709751875,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004999688039790773,
|
|
"loss": 6.9973,
|
|
"mean_token_accuracy": 0.1486719325184822,
|
|
"num_tokens": 3686338.0,
|
|
"step": 1455
|
|
},
|
|
{
|
|
"entropy": 7.252864933013916,
|
|
"epoch": 0.16849394114252741,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999681130745784,
|
|
"loss": 7.001,
|
|
"mean_token_accuracy": 0.1449768289923668,
|
|
"num_tokens": 3698986.0,
|
|
"step": 1460
|
|
},
|
|
{
|
|
"entropy": 7.1841700077056885,
|
|
"epoch": 0.16907097518753605,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004999674146033888,
|
|
"loss": 7.0495,
|
|
"mean_token_accuracy": 0.14095961302518845,
|
|
"num_tokens": 3712453.0,
|
|
"step": 1465
|
|
},
|
|
{
|
|
"entropy": 7.133856296539307,
|
|
"epoch": 0.16964800923254472,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004999667085655318,
|
|
"loss": 7.0579,
|
|
"mean_token_accuracy": 0.13971312269568442,
|
|
"num_tokens": 3724769.0,
|
|
"step": 1470
|
|
},
|
|
{
|
|
"entropy": 7.322906827926635,
|
|
"epoch": 0.1702250432775534,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004999659949610313,
|
|
"loss": 7.105,
|
|
"mean_token_accuracy": 0.13217086791992189,
|
|
"num_tokens": 3738052.0,
|
|
"step": 1475
|
|
},
|
|
{
|
|
"entropy": 7.270902395248413,
|
|
"epoch": 0.17080207732256203,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004999652737899114,
|
|
"loss": 7.0903,
|
|
"mean_token_accuracy": 0.13719962015748025,
|
|
"num_tokens": 3751279.0,
|
|
"step": 1480
|
|
},
|
|
{
|
|
"entropy": 7.262608242034912,
|
|
"epoch": 0.1713791113675707,
|
|
"grad_norm": 0.75,
|
|
"learning_rate": 0.0004999645450521963,
|
|
"loss": 7.1323,
|
|
"mean_token_accuracy": 0.13691732063889503,
|
|
"num_tokens": 3764688.0,
|
|
"step": 1485
|
|
},
|
|
{
|
|
"entropy": 7.236039876937866,
|
|
"epoch": 0.17195614541257934,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004999638087479104,
|
|
"loss": 7.0961,
|
|
"mean_token_accuracy": 0.13691733703017234,
|
|
"num_tokens": 3776892.0,
|
|
"step": 1490
|
|
},
|
|
{
|
|
"entropy": 7.258961296081543,
|
|
"epoch": 0.172533179457588,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004999630648770786,
|
|
"loss": 7.0148,
|
|
"mean_token_accuracy": 0.14263081848621367,
|
|
"num_tokens": 3789287.0,
|
|
"step": 1495
|
|
},
|
|
{
|
|
"entropy": 7.17362151145935,
|
|
"epoch": 0.17311021350259664,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004999623134397257,
|
|
"loss": 7.0039,
|
|
"mean_token_accuracy": 0.14118167236447335,
|
|
"num_tokens": 3801467.0,
|
|
"step": 1500
|
|
},
|
|
{
|
|
"entropy": 7.180401945114136,
|
|
"epoch": 0.1736872475476053,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004999615544358774,
|
|
"loss": 7.0941,
|
|
"mean_token_accuracy": 0.1388135813176632,
|
|
"num_tokens": 3814641.0,
|
|
"step": 1505
|
|
},
|
|
{
|
|
"entropy": 7.323696327209473,
|
|
"epoch": 0.17426428159261395,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004999607878655587,
|
|
"loss": 7.1379,
|
|
"mean_token_accuracy": 0.13087100833654403,
|
|
"num_tokens": 3827187.0,
|
|
"step": 1510
|
|
},
|
|
{
|
|
"entropy": 7.094374799728394,
|
|
"epoch": 0.17484131563762262,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004999600137287958,
|
|
"loss": 6.972,
|
|
"mean_token_accuracy": 0.14806395322084426,
|
|
"num_tokens": 3839832.0,
|
|
"step": 1515
|
|
},
|
|
{
|
|
"entropy": 7.095919132232666,
|
|
"epoch": 0.17541834968263129,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004999592320256146,
|
|
"loss": 6.9735,
|
|
"mean_token_accuracy": 0.1458645448088646,
|
|
"num_tokens": 3852026.0,
|
|
"step": 1520
|
|
},
|
|
{
|
|
"entropy": 7.2352509021759035,
|
|
"epoch": 0.17599538372763993,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004999584427560412,
|
|
"loss": 7.017,
|
|
"mean_token_accuracy": 0.14108823537826537,
|
|
"num_tokens": 3864481.0,
|
|
"step": 1525
|
|
},
|
|
{
|
|
"entropy": 7.192263603210449,
|
|
"epoch": 0.1765724177726486,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004999576459201024,
|
|
"loss": 7.0276,
|
|
"mean_token_accuracy": 0.1382262274622917,
|
|
"num_tokens": 3876896.0,
|
|
"step": 1530
|
|
},
|
|
{
|
|
"entropy": 7.149485349655151,
|
|
"epoch": 0.17714945181765723,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000499956841517825,
|
|
"loss": 6.9683,
|
|
"mean_token_accuracy": 0.14003728628158568,
|
|
"num_tokens": 3890230.0,
|
|
"step": 1535
|
|
},
|
|
{
|
|
"entropy": 7.214767408370972,
|
|
"epoch": 0.1777264858626659,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.000499956029549236,
|
|
"loss": 7.0839,
|
|
"mean_token_accuracy": 0.13458969220519065,
|
|
"num_tokens": 3903138.0,
|
|
"step": 1540
|
|
},
|
|
{
|
|
"entropy": 7.140475034713745,
|
|
"epoch": 0.17830351990767454,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004999552100143625,
|
|
"loss": 6.9988,
|
|
"mean_token_accuracy": 0.1441511981189251,
|
|
"num_tokens": 3915709.0,
|
|
"step": 1545
|
|
},
|
|
{
|
|
"entropy": 7.149213743209839,
|
|
"epoch": 0.1788805539526832,
|
|
"grad_norm": 0.7734375,
|
|
"learning_rate": 0.0004999543829132324,
|
|
"loss": 7.0617,
|
|
"mean_token_accuracy": 0.14265220016241073,
|
|
"num_tokens": 3929265.0,
|
|
"step": 1550
|
|
},
|
|
{
|
|
"entropy": 7.208163404464722,
|
|
"epoch": 0.17945758799769188,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004999535482458734,
|
|
"loss": 7.0482,
|
|
"mean_token_accuracy": 0.14286358505487443,
|
|
"num_tokens": 3940416.0,
|
|
"step": 1555
|
|
},
|
|
{
|
|
"entropy": 7.217859220504761,
|
|
"epoch": 0.18003462204270052,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004999527060123135,
|
|
"loss": 7.0464,
|
|
"mean_token_accuracy": 0.13893593847751617,
|
|
"num_tokens": 3952999.0,
|
|
"step": 1560
|
|
},
|
|
{
|
|
"entropy": 7.1100293636322025,
|
|
"epoch": 0.18061165608770918,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004999518562125811,
|
|
"loss": 7.0657,
|
|
"mean_token_accuracy": 0.1427687995135784,
|
|
"num_tokens": 3966852.0,
|
|
"step": 1565
|
|
},
|
|
{
|
|
"entropy": 7.210110139846802,
|
|
"epoch": 0.18118869013271782,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004999509988467047,
|
|
"loss": 6.9639,
|
|
"mean_token_accuracy": 0.14725383818149568,
|
|
"num_tokens": 3978242.0,
|
|
"step": 1570
|
|
},
|
|
{
|
|
"entropy": 7.188309288024902,
|
|
"epoch": 0.1817657241777265,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.0004999501339147132,
|
|
"loss": 7.0899,
|
|
"mean_token_accuracy": 0.131745096296072,
|
|
"num_tokens": 3993122.0,
|
|
"step": 1575
|
|
},
|
|
{
|
|
"entropy": 7.261885738372802,
|
|
"epoch": 0.18234275822273513,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004999492614166357,
|
|
"loss": 7.0259,
|
|
"mean_token_accuracy": 0.13976342976093292,
|
|
"num_tokens": 4005230.0,
|
|
"step": 1580
|
|
},
|
|
{
|
|
"entropy": 7.037604188919067,
|
|
"epoch": 0.1829197922677438,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004999483813525014,
|
|
"loss": 6.978,
|
|
"mean_token_accuracy": 0.14762265235185623,
|
|
"num_tokens": 4017413.0,
|
|
"step": 1585
|
|
},
|
|
{
|
|
"entropy": 7.191242218017578,
|
|
"epoch": 0.18349682631275246,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004999474937223403,
|
|
"loss": 6.991,
|
|
"mean_token_accuracy": 0.13611105009913443,
|
|
"num_tokens": 4029679.0,
|
|
"step": 1590
|
|
},
|
|
{
|
|
"entropy": 7.1627381324768065,
|
|
"epoch": 0.1840738603577611,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004999465985261818,
|
|
"loss": 6.9535,
|
|
"mean_token_accuracy": 0.14157049655914306,
|
|
"num_tokens": 4041857.0,
|
|
"step": 1595
|
|
},
|
|
{
|
|
"entropy": 7.140171051025391,
|
|
"epoch": 0.18465089440276977,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004999456957640562,
|
|
"loss": 7.0374,
|
|
"mean_token_accuracy": 0.13944343626499175,
|
|
"num_tokens": 4054743.0,
|
|
"step": 1600
|
|
},
|
|
{
|
|
"entropy": 7.072859477996826,
|
|
"epoch": 0.1852279284477784,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004999447854359939,
|
|
"loss": 6.9562,
|
|
"mean_token_accuracy": 0.14270277544856072,
|
|
"num_tokens": 4067554.0,
|
|
"step": 1605
|
|
},
|
|
{
|
|
"entropy": 7.180684185028076,
|
|
"epoch": 0.18580496249278708,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004999438675420255,
|
|
"loss": 6.9519,
|
|
"mean_token_accuracy": 0.1420460894703865,
|
|
"num_tokens": 4079912.0,
|
|
"step": 1610
|
|
},
|
|
{
|
|
"entropy": 7.153562593460083,
|
|
"epoch": 0.18638199653779572,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004999429420821818,
|
|
"loss": 7.0764,
|
|
"mean_token_accuracy": 0.13569277077913283,
|
|
"num_tokens": 4093217.0,
|
|
"step": 1615
|
|
},
|
|
{
|
|
"entropy": 7.13769006729126,
|
|
"epoch": 0.1869590305828044,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.000499942009056494,
|
|
"loss": 7.0162,
|
|
"mean_token_accuracy": 0.1355166032910347,
|
|
"num_tokens": 4104328.0,
|
|
"step": 1620
|
|
},
|
|
{
|
|
"entropy": 7.216564655303955,
|
|
"epoch": 0.18753606462781305,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004999410684649935,
|
|
"loss": 6.9849,
|
|
"mean_token_accuracy": 0.13703312277793883,
|
|
"num_tokens": 4116711.0,
|
|
"step": 1625
|
|
},
|
|
{
|
|
"entropy": 7.153830718994141,
|
|
"epoch": 0.1881130986728217,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004999401203077119,
|
|
"loss": 7.0056,
|
|
"mean_token_accuracy": 0.14228765815496444,
|
|
"num_tokens": 4129066.0,
|
|
"step": 1630
|
|
},
|
|
{
|
|
"entropy": 7.08653039932251,
|
|
"epoch": 0.18869013271783036,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000499939164584681,
|
|
"loss": 6.9143,
|
|
"mean_token_accuracy": 0.14499093145132064,
|
|
"num_tokens": 4141312.0,
|
|
"step": 1635
|
|
},
|
|
{
|
|
"entropy": 7.0617640018463135,
|
|
"epoch": 0.189267166762839,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999382012959331,
|
|
"loss": 6.961,
|
|
"mean_token_accuracy": 0.1401074267923832,
|
|
"num_tokens": 4154687.0,
|
|
"step": 1640
|
|
},
|
|
{
|
|
"entropy": 7.193846559524536,
|
|
"epoch": 0.18984420080784767,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004999372304415005,
|
|
"loss": 7.0702,
|
|
"mean_token_accuracy": 0.1319998621940613,
|
|
"num_tokens": 4168401.0,
|
|
"step": 1645
|
|
},
|
|
{
|
|
"entropy": 7.144888019561767,
|
|
"epoch": 0.1904212348528563,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004999362520214159,
|
|
"loss": 6.9787,
|
|
"mean_token_accuracy": 0.143699299544096,
|
|
"num_tokens": 4180707.0,
|
|
"step": 1650
|
|
},
|
|
{
|
|
"entropy": 7.093651580810547,
|
|
"epoch": 0.19099826889786498,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004999352660357122,
|
|
"loss": 6.9224,
|
|
"mean_token_accuracy": 0.1452721819281578,
|
|
"num_tokens": 4192939.0,
|
|
"step": 1655
|
|
},
|
|
{
|
|
"entropy": 7.1100091457366945,
|
|
"epoch": 0.19157530294287364,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004999342724844226,
|
|
"loss": 6.9571,
|
|
"mean_token_accuracy": 0.14119631350040435,
|
|
"num_tokens": 4206277.0,
|
|
"step": 1660
|
|
},
|
|
{
|
|
"entropy": 7.124865531921387,
|
|
"epoch": 0.19215233698788228,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004999332713675804,
|
|
"loss": 6.9803,
|
|
"mean_token_accuracy": 0.14399617463350295,
|
|
"num_tokens": 4218672.0,
|
|
"step": 1665
|
|
},
|
|
{
|
|
"entropy": 7.107157850265503,
|
|
"epoch": 0.19272937103289095,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004999322626852193,
|
|
"loss": 6.9265,
|
|
"mean_token_accuracy": 0.15203145295381545,
|
|
"num_tokens": 4229002.0,
|
|
"step": 1670
|
|
},
|
|
{
|
|
"entropy": 7.030970716476441,
|
|
"epoch": 0.1933064050778996,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999312464373734,
|
|
"loss": 6.8427,
|
|
"mean_token_accuracy": 0.15255002826452255,
|
|
"num_tokens": 4241986.0,
|
|
"step": 1675
|
|
},
|
|
{
|
|
"entropy": 7.03170862197876,
|
|
"epoch": 0.19388343912290826,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004999302226240767,
|
|
"loss": 6.9614,
|
|
"mean_token_accuracy": 0.1456663116812706,
|
|
"num_tokens": 4254670.0,
|
|
"step": 1680
|
|
},
|
|
{
|
|
"entropy": 7.147547388076783,
|
|
"epoch": 0.1944604731679169,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004999291912453637,
|
|
"loss": 6.9988,
|
|
"mean_token_accuracy": 0.1436385042965412,
|
|
"num_tokens": 4267561.0,
|
|
"step": 1685
|
|
},
|
|
{
|
|
"entropy": 7.182132863998413,
|
|
"epoch": 0.19503750721292556,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004999281523012691,
|
|
"loss": 6.9331,
|
|
"mean_token_accuracy": 0.14853112250566483,
|
|
"num_tokens": 4280145.0,
|
|
"step": 1690
|
|
},
|
|
{
|
|
"entropy": 7.027525091171265,
|
|
"epoch": 0.1956145412579342,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004999271057918278,
|
|
"loss": 6.9788,
|
|
"mean_token_accuracy": 0.14283846467733383,
|
|
"num_tokens": 4294089.0,
|
|
"step": 1695
|
|
},
|
|
{
|
|
"entropy": 7.107568359375,
|
|
"epoch": 0.19619157530294287,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004999260517170751,
|
|
"loss": 6.9167,
|
|
"mean_token_accuracy": 0.14075717329978943,
|
|
"num_tokens": 4305926.0,
|
|
"step": 1700
|
|
},
|
|
{
|
|
"entropy": 7.086518144607544,
|
|
"epoch": 0.19676860934795154,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004999249900770463,
|
|
"loss": 6.9481,
|
|
"mean_token_accuracy": 0.14459511563181876,
|
|
"num_tokens": 4319319.0,
|
|
"step": 1705
|
|
},
|
|
{
|
|
"entropy": 7.104380512237549,
|
|
"epoch": 0.19734564339296018,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004999239208717772,
|
|
"loss": 6.9396,
|
|
"mean_token_accuracy": 0.1490633636713028,
|
|
"num_tokens": 4331650.0,
|
|
"step": 1710
|
|
},
|
|
{
|
|
"entropy": 6.978099775314331,
|
|
"epoch": 0.19792267743796885,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004999228441013037,
|
|
"loss": 6.9182,
|
|
"mean_token_accuracy": 0.14964553862810134,
|
|
"num_tokens": 4344289.0,
|
|
"step": 1715
|
|
},
|
|
{
|
|
"entropy": 7.099493741989136,
|
|
"epoch": 0.1984997114829775,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.000499921759765662,
|
|
"loss": 6.9221,
|
|
"mean_token_accuracy": 0.14225320667028427,
|
|
"num_tokens": 4357316.0,
|
|
"step": 1720
|
|
},
|
|
{
|
|
"entropy": 7.004121541976929,
|
|
"epoch": 0.19907674552798615,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004999206678648888,
|
|
"loss": 6.9264,
|
|
"mean_token_accuracy": 0.1489520326256752,
|
|
"num_tokens": 4369383.0,
|
|
"step": 1725
|
|
},
|
|
{
|
|
"entropy": 7.094613456726075,
|
|
"epoch": 0.1996537795729948,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004999195683990206,
|
|
"loss": 6.9235,
|
|
"mean_token_accuracy": 0.14189272969961167,
|
|
"num_tokens": 4383509.0,
|
|
"step": 1730
|
|
},
|
|
{
|
|
"entropy": 7.103254556655884,
|
|
"epoch": 0.20023081361800346,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004999184613680945,
|
|
"loss": 6.9059,
|
|
"mean_token_accuracy": 0.14382569789886473,
|
|
"num_tokens": 4395105.0,
|
|
"step": 1735
|
|
},
|
|
{
|
|
"entropy": 7.039672946929931,
|
|
"epoch": 0.20080784766301213,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004999173467721476,
|
|
"loss": 6.9091,
|
|
"mean_token_accuracy": 0.15155962854623795,
|
|
"num_tokens": 4407473.0,
|
|
"step": 1740
|
|
},
|
|
{
|
|
"entropy": 7.116544246673584,
|
|
"epoch": 0.20138488170802077,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004999162246112175,
|
|
"loss": 6.991,
|
|
"mean_token_accuracy": 0.13716431334614754,
|
|
"num_tokens": 4420186.0,
|
|
"step": 1745
|
|
},
|
|
{
|
|
"entropy": 7.053312683105469,
|
|
"epoch": 0.20196191575302944,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004999150948853419,
|
|
"loss": 6.8901,
|
|
"mean_token_accuracy": 0.14453017637133597,
|
|
"num_tokens": 4432944.0,
|
|
"step": 1750
|
|
},
|
|
{
|
|
"entropy": 7.120892095565796,
|
|
"epoch": 0.20253894979803808,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004999139575945587,
|
|
"loss": 6.9558,
|
|
"mean_token_accuracy": 0.14354105591773986,
|
|
"num_tokens": 4445784.0,
|
|
"step": 1755
|
|
},
|
|
{
|
|
"entropy": 6.965320730209351,
|
|
"epoch": 0.20311598384304674,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004999128127389065,
|
|
"loss": 6.8445,
|
|
"mean_token_accuracy": 0.15029353350400926,
|
|
"num_tokens": 4458338.0,
|
|
"step": 1760
|
|
},
|
|
{
|
|
"entropy": 7.06877818107605,
|
|
"epoch": 0.20369301788805538,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004999116603184233,
|
|
"loss": 6.8774,
|
|
"mean_token_accuracy": 0.13867350146174431,
|
|
"num_tokens": 4471058.0,
|
|
"step": 1765
|
|
},
|
|
{
|
|
"entropy": 6.997467470169068,
|
|
"epoch": 0.20427005193306405,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004999105003331482,
|
|
"loss": 6.8973,
|
|
"mean_token_accuracy": 0.14823642373085022,
|
|
"num_tokens": 4485561.0,
|
|
"step": 1770
|
|
},
|
|
{
|
|
"entropy": 7.019530820846557,
|
|
"epoch": 0.20484708597807272,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004999093327831202,
|
|
"loss": 6.9028,
|
|
"mean_token_accuracy": 0.14461316913366318,
|
|
"num_tokens": 4497865.0,
|
|
"step": 1775
|
|
},
|
|
{
|
|
"entropy": 6.937532806396485,
|
|
"epoch": 0.20542412002308136,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004999081576683784,
|
|
"loss": 6.8082,
|
|
"mean_token_accuracy": 0.15614131838083267,
|
|
"num_tokens": 4510291.0,
|
|
"step": 1780
|
|
},
|
|
{
|
|
"entropy": 7.044717454910279,
|
|
"epoch": 0.20600115406809003,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004999069749889626,
|
|
"loss": 6.9073,
|
|
"mean_token_accuracy": 0.1450217232108116,
|
|
"num_tokens": 4521855.0,
|
|
"step": 1785
|
|
},
|
|
{
|
|
"entropy": 7.052458572387695,
|
|
"epoch": 0.20657818811309867,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.0004999057847449123,
|
|
"loss": 6.99,
|
|
"mean_token_accuracy": 0.1421843633055687,
|
|
"num_tokens": 4534123.0,
|
|
"step": 1790
|
|
},
|
|
{
|
|
"entropy": 7.197088527679443,
|
|
"epoch": 0.20715522215810733,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004999045869362678,
|
|
"loss": 6.9418,
|
|
"mean_token_accuracy": 0.13784723579883576,
|
|
"num_tokens": 4547298.0,
|
|
"step": 1795
|
|
},
|
|
{
|
|
"entropy": 6.992271852493286,
|
|
"epoch": 0.20773225620311597,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.000499903381563069,
|
|
"loss": 6.8698,
|
|
"mean_token_accuracy": 0.1466771975159645,
|
|
"num_tokens": 4560945.0,
|
|
"step": 1800
|
|
},
|
|
{
|
|
"entropy": 7.020458364486695,
|
|
"epoch": 0.20830929024812464,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004999021686253568,
|
|
"loss": 6.9329,
|
|
"mean_token_accuracy": 0.14652197062969208,
|
|
"num_tokens": 4572696.0,
|
|
"step": 1805
|
|
},
|
|
{
|
|
"entropy": 6.95990252494812,
|
|
"epoch": 0.2088863242931333,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004999009481231719,
|
|
"loss": 6.8845,
|
|
"mean_token_accuracy": 0.14989398419857025,
|
|
"num_tokens": 4585670.0,
|
|
"step": 1810
|
|
},
|
|
{
|
|
"entropy": 7.115705442428589,
|
|
"epoch": 0.20946335833814195,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.0004998997200565553,
|
|
"loss": 6.8657,
|
|
"mean_token_accuracy": 0.15091128051280975,
|
|
"num_tokens": 4597694.0,
|
|
"step": 1815
|
|
},
|
|
{
|
|
"entropy": 7.001132869720459,
|
|
"epoch": 0.21004039238315061,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004998984844255483,
|
|
"loss": 6.8746,
|
|
"mean_token_accuracy": 0.14744569212198258,
|
|
"num_tokens": 4609924.0,
|
|
"step": 1820
|
|
},
|
|
{
|
|
"entropy": 7.056229448318481,
|
|
"epoch": 0.21061742642815925,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004998972412301925,
|
|
"loss": 6.885,
|
|
"mean_token_accuracy": 0.1468400090932846,
|
|
"num_tokens": 4621668.0,
|
|
"step": 1825
|
|
},
|
|
{
|
|
"entropy": 7.011569261550903,
|
|
"epoch": 0.21119446047316792,
|
|
"grad_norm": 0.765625,
|
|
"learning_rate": 0.0004998959904705297,
|
|
"loss": 6.9449,
|
|
"mean_token_accuracy": 0.14132919982075692,
|
|
"num_tokens": 4635970.0,
|
|
"step": 1830
|
|
},
|
|
{
|
|
"entropy": 7.080425167083741,
|
|
"epoch": 0.21177149451817656,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004998947321466021,
|
|
"loss": 6.9183,
|
|
"mean_token_accuracy": 0.14053108170628548,
|
|
"num_tokens": 4649557.0,
|
|
"step": 1835
|
|
},
|
|
{
|
|
"entropy": 7.013520288467407,
|
|
"epoch": 0.21234852856318523,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004998934662584518,
|
|
"loss": 6.9063,
|
|
"mean_token_accuracy": 0.14713118821382523,
|
|
"num_tokens": 4662572.0,
|
|
"step": 1840
|
|
},
|
|
{
|
|
"entropy": 7.0543595314025875,
|
|
"epoch": 0.2129255626081939,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004998921928061214,
|
|
"loss": 6.8599,
|
|
"mean_token_accuracy": 0.14088837131857873,
|
|
"num_tokens": 4674783.0,
|
|
"step": 1845
|
|
},
|
|
{
|
|
"entropy": 6.977069759368897,
|
|
"epoch": 0.21350259665320254,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004998909117896539,
|
|
"loss": 6.8811,
|
|
"mean_token_accuracy": 0.1488935634493828,
|
|
"num_tokens": 4687543.0,
|
|
"step": 1850
|
|
},
|
|
{
|
|
"entropy": 7.099917268753051,
|
|
"epoch": 0.2140796306982112,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004998896232090922,
|
|
"loss": 6.8471,
|
|
"mean_token_accuracy": 0.14590785950422286,
|
|
"num_tokens": 4700225.0,
|
|
"step": 1855
|
|
},
|
|
{
|
|
"entropy": 6.8859778881073,
|
|
"epoch": 0.21465666474321984,
|
|
"grad_norm": 0.80078125,
|
|
"learning_rate": 0.0004998883270644798,
|
|
"loss": 6.8981,
|
|
"mean_token_accuracy": 0.1461702950298786,
|
|
"num_tokens": 4712950.0,
|
|
"step": 1860
|
|
},
|
|
{
|
|
"entropy": 7.103154993057251,
|
|
"epoch": 0.2152336987882285,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004998870233558602,
|
|
"loss": 6.9823,
|
|
"mean_token_accuracy": 0.14054031670093536,
|
|
"num_tokens": 4725563.0,
|
|
"step": 1865
|
|
},
|
|
{
|
|
"entropy": 7.021540546417237,
|
|
"epoch": 0.21581073283323715,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004998857120832774,
|
|
"loss": 6.8994,
|
|
"mean_token_accuracy": 0.14567926824092864,
|
|
"num_tokens": 4739057.0,
|
|
"step": 1870
|
|
},
|
|
{
|
|
"entropy": 7.013464498519897,
|
|
"epoch": 0.21638776687824582,
|
|
"grad_norm": 0.796875,
|
|
"learning_rate": 0.0004998843932467751,
|
|
"loss": 6.8557,
|
|
"mean_token_accuracy": 0.14868776947259904,
|
|
"num_tokens": 4752782.0,
|
|
"step": 1875
|
|
},
|
|
{
|
|
"entropy": 7.032290697097778,
|
|
"epoch": 0.21696480092325446,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004998830668463982,
|
|
"loss": 6.8122,
|
|
"mean_token_accuracy": 0.14852888584136964,
|
|
"num_tokens": 4765740.0,
|
|
"step": 1880
|
|
},
|
|
{
|
|
"entropy": 6.985332727432251,
|
|
"epoch": 0.21754183496826313,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004998817328821909,
|
|
"loss": 6.8821,
|
|
"mean_token_accuracy": 0.14597213715314866,
|
|
"num_tokens": 4778711.0,
|
|
"step": 1885
|
|
},
|
|
{
|
|
"entropy": 7.0917829990386965,
|
|
"epoch": 0.2181188690132718,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004998803913541983,
|
|
"loss": 6.8686,
|
|
"mean_token_accuracy": 0.14363647997379303,
|
|
"num_tokens": 4791402.0,
|
|
"step": 1890
|
|
},
|
|
{
|
|
"entropy": 7.007903146743774,
|
|
"epoch": 0.21869590305828043,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004998790422624654,
|
|
"loss": 6.8535,
|
|
"mean_token_accuracy": 0.13729466870427132,
|
|
"num_tokens": 4804256.0,
|
|
"step": 1895
|
|
},
|
|
{
|
|
"entropy": 6.964800500869751,
|
|
"epoch": 0.2192729371032891,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004998776856070376,
|
|
"loss": 6.8066,
|
|
"mean_token_accuracy": 0.1438037261366844,
|
|
"num_tokens": 4817424.0,
|
|
"step": 1900
|
|
},
|
|
{
|
|
"entropy": 7.044483804702759,
|
|
"epoch": 0.21984997114829774,
|
|
"grad_norm": 0.80078125,
|
|
"learning_rate": 0.0004998763213879606,
|
|
"loss": 6.8492,
|
|
"mean_token_accuracy": 0.1408962205052376,
|
|
"num_tokens": 4829222.0,
|
|
"step": 1905
|
|
},
|
|
{
|
|
"entropy": 6.946775960922241,
|
|
"epoch": 0.2204270051933064,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004998749496052803,
|
|
"loss": 6.8166,
|
|
"mean_token_accuracy": 0.1510320410132408,
|
|
"num_tokens": 4844011.0,
|
|
"step": 1910
|
|
},
|
|
{
|
|
"entropy": 7.0013550281524655,
|
|
"epoch": 0.22100403923831505,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.0004998735702590426,
|
|
"loss": 6.8753,
|
|
"mean_token_accuracy": 0.14439389556646348,
|
|
"num_tokens": 4857116.0,
|
|
"step": 1915
|
|
},
|
|
{
|
|
"entropy": 6.983421802520752,
|
|
"epoch": 0.22158107328332372,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004998721833492942,
|
|
"loss": 6.7985,
|
|
"mean_token_accuracy": 0.15554276704788209,
|
|
"num_tokens": 4867680.0,
|
|
"step": 1920
|
|
},
|
|
{
|
|
"entropy": 6.959651088714599,
|
|
"epoch": 0.22215810732833238,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004998707888760816,
|
|
"loss": 6.87,
|
|
"mean_token_accuracy": 0.14348941370844842,
|
|
"num_tokens": 4880553.0,
|
|
"step": 1925
|
|
},
|
|
{
|
|
"entropy": 7.035657167434692,
|
|
"epoch": 0.22273514137334102,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004998693868394516,
|
|
"loss": 6.8344,
|
|
"mean_token_accuracy": 0.14735666215419768,
|
|
"num_tokens": 4893706.0,
|
|
"step": 1930
|
|
},
|
|
{
|
|
"entropy": 6.914802122116089,
|
|
"epoch": 0.2233121754183497,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004998679772394516,
|
|
"loss": 6.9102,
|
|
"mean_token_accuracy": 0.1454026609659195,
|
|
"num_tokens": 4906016.0,
|
|
"step": 1935
|
|
},
|
|
{
|
|
"entropy": 6.97300386428833,
|
|
"epoch": 0.22388920946335833,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004998665600761289,
|
|
"loss": 6.7939,
|
|
"mean_token_accuracy": 0.14941516369581223,
|
|
"num_tokens": 4918628.0,
|
|
"step": 1940
|
|
},
|
|
{
|
|
"entropy": 7.029558706283569,
|
|
"epoch": 0.224466243508367,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.000499865135349531,
|
|
"loss": 6.8703,
|
|
"mean_token_accuracy": 0.13900768756866455,
|
|
"num_tokens": 4930525.0,
|
|
"step": 1945
|
|
},
|
|
{
|
|
"entropy": 7.005332565307617,
|
|
"epoch": 0.22504327755337564,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004998637030597061,
|
|
"loss": 6.8806,
|
|
"mean_token_accuracy": 0.14249326959252356,
|
|
"num_tokens": 4942510.0,
|
|
"step": 1950
|
|
},
|
|
{
|
|
"entropy": 7.0068284034729,
|
|
"epoch": 0.2256203115983843,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004998622632067022,
|
|
"loss": 6.8463,
|
|
"mean_token_accuracy": 0.1456683486700058,
|
|
"num_tokens": 4954865.0,
|
|
"step": 1955
|
|
},
|
|
{
|
|
"entropy": 6.9775794506072994,
|
|
"epoch": 0.22619734564339297,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004998608157905678,
|
|
"loss": 6.95,
|
|
"mean_token_accuracy": 0.1380724899470806,
|
|
"num_tokens": 4968078.0,
|
|
"step": 1960
|
|
},
|
|
{
|
|
"entropy": 7.020229148864746,
|
|
"epoch": 0.2267743796884016,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.0004998593608113515,
|
|
"loss": 6.7892,
|
|
"mean_token_accuracy": 0.14944704324007035,
|
|
"num_tokens": 4980273.0,
|
|
"step": 1965
|
|
},
|
|
{
|
|
"entropy": 6.9938514709472654,
|
|
"epoch": 0.22735141373341028,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004998578982691024,
|
|
"loss": 6.8542,
|
|
"mean_token_accuracy": 0.14151277467608453,
|
|
"num_tokens": 4992372.0,
|
|
"step": 1970
|
|
},
|
|
{
|
|
"entropy": 6.939938163757324,
|
|
"epoch": 0.22792844777841892,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004998564281638694,
|
|
"loss": 6.8316,
|
|
"mean_token_accuracy": 0.14077244997024535,
|
|
"num_tokens": 5004766.0,
|
|
"step": 1975
|
|
},
|
|
{
|
|
"entropy": 7.018451166152954,
|
|
"epoch": 0.2285054818234276,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004998549504957023,
|
|
"loss": 6.7877,
|
|
"mean_token_accuracy": 0.14108608216047286,
|
|
"num_tokens": 5017007.0,
|
|
"step": 1980
|
|
},
|
|
{
|
|
"entropy": 6.921030187606812,
|
|
"epoch": 0.22908251586843623,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004998534652646506,
|
|
"loss": 6.8458,
|
|
"mean_token_accuracy": 0.14241134524345397,
|
|
"num_tokens": 5029506.0,
|
|
"step": 1985
|
|
},
|
|
{
|
|
"entropy": 6.955693626403809,
|
|
"epoch": 0.2296595499134449,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004998519724707642,
|
|
"loss": 6.8155,
|
|
"mean_token_accuracy": 0.14788847863674165,
|
|
"num_tokens": 5042209.0,
|
|
"step": 1990
|
|
},
|
|
{
|
|
"entropy": 6.97462306022644,
|
|
"epoch": 0.23023658395845356,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004998504721140934,
|
|
"loss": 6.8718,
|
|
"mean_token_accuracy": 0.13877833858132363,
|
|
"num_tokens": 5056026.0,
|
|
"step": 1995
|
|
},
|
|
{
|
|
"entropy": 6.990704870223999,
|
|
"epoch": 0.2308136180034622,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004998489641946887,
|
|
"loss": 6.8118,
|
|
"mean_token_accuracy": 0.14473072141408921,
|
|
"num_tokens": 5068194.0,
|
|
"step": 2000
|
|
},
|
|
{
|
|
"entropy": 6.874226713180542,
|
|
"epoch": 0.23139065204847087,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004998474487126009,
|
|
"loss": 6.7544,
|
|
"mean_token_accuracy": 0.14470188170671464,
|
|
"num_tokens": 5080468.0,
|
|
"step": 2005
|
|
},
|
|
{
|
|
"entropy": 7.0825056552886965,
|
|
"epoch": 0.2319676860934795,
|
|
"grad_norm": 0.76953125,
|
|
"learning_rate": 0.0004998459256678806,
|
|
"loss": 6.9486,
|
|
"mean_token_accuracy": 0.13459489569067956,
|
|
"num_tokens": 5093104.0,
|
|
"step": 2010
|
|
},
|
|
{
|
|
"entropy": 7.020360994338989,
|
|
"epoch": 0.23254472013848818,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0004998443950605796,
|
|
"loss": 6.8025,
|
|
"mean_token_accuracy": 0.14722402542829513,
|
|
"num_tokens": 5105710.0,
|
|
"step": 2015
|
|
},
|
|
{
|
|
"entropy": 6.992463827133179,
|
|
"epoch": 0.23312175418349682,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004998428568907488,
|
|
"loss": 6.8825,
|
|
"mean_token_accuracy": 0.14219225868582724,
|
|
"num_tokens": 5118946.0,
|
|
"step": 2020
|
|
},
|
|
{
|
|
"entropy": 6.929893112182617,
|
|
"epoch": 0.23369878822850548,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004998413111584403,
|
|
"loss": 6.7236,
|
|
"mean_token_accuracy": 0.15229955613613128,
|
|
"num_tokens": 5132567.0,
|
|
"step": 2025
|
|
},
|
|
{
|
|
"entropy": 6.87170090675354,
|
|
"epoch": 0.23427582227351415,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004998397578637059,
|
|
"loss": 6.7848,
|
|
"mean_token_accuracy": 0.1508283868432045,
|
|
"num_tokens": 5145669.0,
|
|
"step": 2030
|
|
},
|
|
{
|
|
"entropy": 6.9173017024993895,
|
|
"epoch": 0.2348528563185228,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.000499838197006598,
|
|
"loss": 6.7264,
|
|
"mean_token_accuracy": 0.1511531800031662,
|
|
"num_tokens": 5157753.0,
|
|
"step": 2035
|
|
},
|
|
{
|
|
"entropy": 6.895808982849121,
|
|
"epoch": 0.23542989036353146,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.000499836628587169,
|
|
"loss": 6.7534,
|
|
"mean_token_accuracy": 0.1487403929233551,
|
|
"num_tokens": 5170167.0,
|
|
"step": 2040
|
|
},
|
|
{
|
|
"entropy": 6.922911071777344,
|
|
"epoch": 0.2360069244085401,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004998350526054716,
|
|
"loss": 6.7484,
|
|
"mean_token_accuracy": 0.14699087888002396,
|
|
"num_tokens": 5182143.0,
|
|
"step": 2045
|
|
},
|
|
{
|
|
"entropy": 6.920343017578125,
|
|
"epoch": 0.23658395845354876,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004998334690615591,
|
|
"loss": 6.7837,
|
|
"mean_token_accuracy": 0.14400450214743615,
|
|
"num_tokens": 5195586.0,
|
|
"step": 2050
|
|
},
|
|
{
|
|
"entropy": 6.898791360855102,
|
|
"epoch": 0.2371609924985574,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004998318779554844,
|
|
"loss": 6.7823,
|
|
"mean_token_accuracy": 0.14565831422805786,
|
|
"num_tokens": 5207774.0,
|
|
"step": 2055
|
|
},
|
|
{
|
|
"entropy": 6.857323026657104,
|
|
"epoch": 0.23773802654356607,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004998302792873012,
|
|
"loss": 6.7961,
|
|
"mean_token_accuracy": 0.14450274109840394,
|
|
"num_tokens": 5219330.0,
|
|
"step": 2060
|
|
},
|
|
{
|
|
"entropy": 7.0199343204498295,
|
|
"epoch": 0.23831506058857474,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004998286730570631,
|
|
"loss": 6.8601,
|
|
"mean_token_accuracy": 0.13632812798023225,
|
|
"num_tokens": 5233817.0,
|
|
"step": 2065
|
|
},
|
|
{
|
|
"entropy": 6.916458797454834,
|
|
"epoch": 0.23889209463358338,
|
|
"grad_norm": 0.796875,
|
|
"learning_rate": 0.0004998270592648245,
|
|
"loss": 6.8575,
|
|
"mean_token_accuracy": 0.14362055882811547,
|
|
"num_tokens": 5246483.0,
|
|
"step": 2070
|
|
},
|
|
{
|
|
"entropy": 6.994282245635986,
|
|
"epoch": 0.23946912867859205,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004998254379106394,
|
|
"loss": 6.839,
|
|
"mean_token_accuracy": 0.14538607597351075,
|
|
"num_tokens": 5258695.0,
|
|
"step": 2075
|
|
},
|
|
{
|
|
"entropy": 6.908141565322876,
|
|
"epoch": 0.2400461627236007,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004998238089945622,
|
|
"loss": 6.8047,
|
|
"mean_token_accuracy": 0.14092738628387452,
|
|
"num_tokens": 5271355.0,
|
|
"step": 2080
|
|
},
|
|
{
|
|
"entropy": 7.025559520721435,
|
|
"epoch": 0.24062319676860935,
|
|
"grad_norm": 0.7890625,
|
|
"learning_rate": 0.0004998221725166479,
|
|
"loss": 6.9123,
|
|
"mean_token_accuracy": 0.13938132375478746,
|
|
"num_tokens": 5284905.0,
|
|
"step": 2085
|
|
},
|
|
{
|
|
"entropy": 6.899095153808593,
|
|
"epoch": 0.241200230813618,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.0004998205284769516,
|
|
"loss": 6.8295,
|
|
"mean_token_accuracy": 0.1434583306312561,
|
|
"num_tokens": 5298266.0,
|
|
"step": 2090
|
|
},
|
|
{
|
|
"entropy": 6.973186731338501,
|
|
"epoch": 0.24177726485862666,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004998188768755285,
|
|
"loss": 6.8747,
|
|
"mean_token_accuracy": 0.13531978204846382,
|
|
"num_tokens": 5311148.0,
|
|
"step": 2095
|
|
},
|
|
{
|
|
"entropy": 6.945560312271118,
|
|
"epoch": 0.2423542989036353,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004998172177124341,
|
|
"loss": 6.7786,
|
|
"mean_token_accuracy": 0.1462605893611908,
|
|
"num_tokens": 5322638.0,
|
|
"step": 2100
|
|
},
|
|
{
|
|
"entropy": 6.831422948837281,
|
|
"epoch": 0.24293133294864397,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004998155509877242,
|
|
"loss": 6.6679,
|
|
"mean_token_accuracy": 0.15973918437957763,
|
|
"num_tokens": 5336116.0,
|
|
"step": 2105
|
|
},
|
|
{
|
|
"entropy": 6.87315354347229,
|
|
"epoch": 0.24350836699365264,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.000499813876701455,
|
|
"loss": 6.7941,
|
|
"mean_token_accuracy": 0.14872830137610435,
|
|
"num_tokens": 5347561.0,
|
|
"step": 2110
|
|
},
|
|
{
|
|
"entropy": 7.002074909210205,
|
|
"epoch": 0.24408540103866128,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.0004998121948536828,
|
|
"loss": 6.8244,
|
|
"mean_token_accuracy": 0.1419316753745079,
|
|
"num_tokens": 5360055.0,
|
|
"step": 2115
|
|
},
|
|
{
|
|
"entropy": 6.937633228302002,
|
|
"epoch": 0.24466243508366994,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004998105054444639,
|
|
"loss": 6.7812,
|
|
"mean_token_accuracy": 0.15047216340899466,
|
|
"num_tokens": 5372722.0,
|
|
"step": 2120
|
|
},
|
|
{
|
|
"entropy": 6.960194253921509,
|
|
"epoch": 0.24523946912867858,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004998088084738555,
|
|
"loss": 6.7418,
|
|
"mean_token_accuracy": 0.14477523565292358,
|
|
"num_tokens": 5385586.0,
|
|
"step": 2125
|
|
},
|
|
{
|
|
"entropy": 6.831562471389771,
|
|
"epoch": 0.24581650317368725,
|
|
"grad_norm": 0.76953125,
|
|
"learning_rate": 0.0004998071039419144,
|
|
"loss": 6.7828,
|
|
"mean_token_accuracy": 0.1484777107834816,
|
|
"num_tokens": 5399266.0,
|
|
"step": 2130
|
|
},
|
|
{
|
|
"entropy": 6.943821907043457,
|
|
"epoch": 0.2463935372186959,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.000499805391848698,
|
|
"loss": 6.7836,
|
|
"mean_token_accuracy": 0.1484945073723793,
|
|
"num_tokens": 5412093.0,
|
|
"step": 2135
|
|
},
|
|
{
|
|
"entropy": 6.854267024993897,
|
|
"epoch": 0.24697057126370456,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.000499803672194264,
|
|
"loss": 6.7768,
|
|
"mean_token_accuracy": 0.14299426227808,
|
|
"num_tokens": 5425181.0,
|
|
"step": 2140
|
|
},
|
|
{
|
|
"entropy": 6.8708819389343265,
|
|
"epoch": 0.24754760530871323,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004998019449786701,
|
|
"loss": 6.6947,
|
|
"mean_token_accuracy": 0.15227821469306946,
|
|
"num_tokens": 5437392.0,
|
|
"step": 2145
|
|
},
|
|
{
|
|
"entropy": 6.947283506393433,
|
|
"epoch": 0.24812463935372187,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004998002102019744,
|
|
"loss": 6.7657,
|
|
"mean_token_accuracy": 0.15049567073583603,
|
|
"num_tokens": 5449455.0,
|
|
"step": 2150
|
|
},
|
|
{
|
|
"entropy": 6.891529560089111,
|
|
"epoch": 0.24870167339873053,
|
|
"grad_norm": 0.80078125,
|
|
"learning_rate": 0.0004997984678642354,
|
|
"loss": 6.7946,
|
|
"mean_token_accuracy": 0.14755706638097763,
|
|
"num_tokens": 5463095.0,
|
|
"step": 2155
|
|
},
|
|
{
|
|
"entropy": 6.925650119781494,
|
|
"epoch": 0.24927870744373917,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004997967179655115,
|
|
"loss": 6.7416,
|
|
"mean_token_accuracy": 0.15180930644273757,
|
|
"num_tokens": 5474440.0,
|
|
"step": 2160
|
|
},
|
|
{
|
|
"entropy": 6.880334043502808,
|
|
"epoch": 0.24985574148874784,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004997949605058617,
|
|
"loss": 6.7436,
|
|
"mean_token_accuracy": 0.15553607046604156,
|
|
"num_tokens": 5487365.0,
|
|
"step": 2165
|
|
},
|
|
{
|
|
"entropy": 6.943732452392578,
|
|
"epoch": 0.2504327755337565,
|
|
"grad_norm": 0.80078125,
|
|
"learning_rate": 0.0004997931954853451,
|
|
"loss": 6.8102,
|
|
"mean_token_accuracy": 0.1437340646982193,
|
|
"num_tokens": 5502356.0,
|
|
"step": 2170
|
|
},
|
|
{
|
|
"entropy": 6.863589477539063,
|
|
"epoch": 0.2510098095787651,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.000499791422904021,
|
|
"loss": 6.814,
|
|
"mean_token_accuracy": 0.14547016769647597,
|
|
"num_tokens": 5514504.0,
|
|
"step": 2175
|
|
},
|
|
{
|
|
"entropy": 7.013930749893189,
|
|
"epoch": 0.2515868436237738,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004997896427619491,
|
|
"loss": 6.8368,
|
|
"mean_token_accuracy": 0.14100218415260315,
|
|
"num_tokens": 5526415.0,
|
|
"step": 2180
|
|
},
|
|
{
|
|
"entropy": 6.841579246520996,
|
|
"epoch": 0.25216387766878245,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004997878550591892,
|
|
"loss": 6.6874,
|
|
"mean_token_accuracy": 0.15348772406578065,
|
|
"num_tokens": 5538484.0,
|
|
"step": 2185
|
|
},
|
|
{
|
|
"entropy": 6.90242280960083,
|
|
"epoch": 0.2527409117137911,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004997860597958013,
|
|
"loss": 6.764,
|
|
"mean_token_accuracy": 0.15220421701669692,
|
|
"num_tokens": 5551315.0,
|
|
"step": 2190
|
|
},
|
|
{
|
|
"entropy": 6.826332235336304,
|
|
"epoch": 0.2533179457587998,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004997842569718461,
|
|
"loss": 6.6467,
|
|
"mean_token_accuracy": 0.15433922857046128,
|
|
"num_tokens": 5564179.0,
|
|
"step": 2195
|
|
},
|
|
{
|
|
"entropy": 6.796852874755859,
|
|
"epoch": 0.25389497980380843,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.000499782446587384,
|
|
"loss": 6.7843,
|
|
"mean_token_accuracy": 0.14296953305602073,
|
|
"num_tokens": 5577060.0,
|
|
"step": 2200
|
|
},
|
|
{
|
|
"entropy": 6.819638252258301,
|
|
"epoch": 0.25447201384881707,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.000499780628642476,
|
|
"loss": 6.6023,
|
|
"mean_token_accuracy": 0.16436567083001136,
|
|
"num_tokens": 5589170.0,
|
|
"step": 2205
|
|
},
|
|
{
|
|
"entropy": 6.853410863876343,
|
|
"epoch": 0.2550490478938257,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004997788031371834,
|
|
"loss": 6.7762,
|
|
"mean_token_accuracy": 0.1478083088994026,
|
|
"num_tokens": 5601747.0,
|
|
"step": 2210
|
|
},
|
|
{
|
|
"entropy": 6.910475969314575,
|
|
"epoch": 0.2556260819388344,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004997769700715672,
|
|
"loss": 6.8117,
|
|
"mean_token_accuracy": 0.14246365278959275,
|
|
"num_tokens": 5614308.0,
|
|
"step": 2215
|
|
},
|
|
{
|
|
"entropy": 6.882238912582397,
|
|
"epoch": 0.25620311598384304,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.0004997751294456892,
|
|
"loss": 6.7753,
|
|
"mean_token_accuracy": 0.13991254717111587,
|
|
"num_tokens": 5626351.0,
|
|
"step": 2220
|
|
},
|
|
{
|
|
"entropy": 6.902230548858642,
|
|
"epoch": 0.2567801500288517,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004997732812596114,
|
|
"loss": 6.7473,
|
|
"mean_token_accuracy": 0.1505092367529869,
|
|
"num_tokens": 5638339.0,
|
|
"step": 2225
|
|
},
|
|
{
|
|
"entropy": 6.901751756668091,
|
|
"epoch": 0.2573571840738604,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004997714255133961,
|
|
"loss": 6.8054,
|
|
"mean_token_accuracy": 0.14526830166578292,
|
|
"num_tokens": 5651210.0,
|
|
"step": 2230
|
|
},
|
|
{
|
|
"entropy": 6.877227878570556,
|
|
"epoch": 0.257934218118869,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004997695622071054,
|
|
"loss": 6.7704,
|
|
"mean_token_accuracy": 0.14814679324626923,
|
|
"num_tokens": 5664150.0,
|
|
"step": 2235
|
|
},
|
|
{
|
|
"entropy": 6.898557186126709,
|
|
"epoch": 0.25851125216387766,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004997676913408021,
|
|
"loss": 6.7121,
|
|
"mean_token_accuracy": 0.15328368097543715,
|
|
"num_tokens": 5676009.0,
|
|
"step": 2240
|
|
},
|
|
{
|
|
"entropy": 6.965892267227173,
|
|
"epoch": 0.2590882862088863,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004997658129145493,
|
|
"loss": 6.8838,
|
|
"mean_token_accuracy": 0.14226163998246194,
|
|
"num_tokens": 5688557.0,
|
|
"step": 2245
|
|
},
|
|
{
|
|
"entropy": 6.861143636703491,
|
|
"epoch": 0.259665320253895,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.0004997639269284099,
|
|
"loss": 6.8308,
|
|
"mean_token_accuracy": 0.1465721994638443,
|
|
"num_tokens": 5702032.0,
|
|
"step": 2250
|
|
},
|
|
{
|
|
"entropy": 6.920127868652344,
|
|
"epoch": 0.26024235429890363,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004997620333824476,
|
|
"loss": 6.6695,
|
|
"mean_token_accuracy": 0.15270446389913558,
|
|
"num_tokens": 5714623.0,
|
|
"step": 2255
|
|
},
|
|
{
|
|
"entropy": 6.813676214218139,
|
|
"epoch": 0.2608193883439123,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004997601322767258,
|
|
"loss": 6.6871,
|
|
"mean_token_accuracy": 0.1490221619606018,
|
|
"num_tokens": 5727415.0,
|
|
"step": 2260
|
|
},
|
|
{
|
|
"entropy": 6.875842475891114,
|
|
"epoch": 0.26139642238892097,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004997582236113087,
|
|
"loss": 6.7316,
|
|
"mean_token_accuracy": 0.14756003841757775,
|
|
"num_tokens": 5740129.0,
|
|
"step": 2265
|
|
},
|
|
{
|
|
"entropy": 6.854972076416016,
|
|
"epoch": 0.2619734564339296,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004997563073862603,
|
|
"loss": 6.6885,
|
|
"mean_token_accuracy": 0.15406904220581055,
|
|
"num_tokens": 5752469.0,
|
|
"step": 2270
|
|
},
|
|
{
|
|
"entropy": 6.81607403755188,
|
|
"epoch": 0.26255049047893825,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004997543836016453,
|
|
"loss": 6.7811,
|
|
"mean_token_accuracy": 0.15202534720301628,
|
|
"num_tokens": 5765408.0,
|
|
"step": 2275
|
|
},
|
|
{
|
|
"entropy": 6.929606485366821,
|
|
"epoch": 0.2631275245239469,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004997524522575281,
|
|
"loss": 6.705,
|
|
"mean_token_accuracy": 0.1446349136531353,
|
|
"num_tokens": 5777450.0,
|
|
"step": 2280
|
|
},
|
|
{
|
|
"entropy": 6.859155130386353,
|
|
"epoch": 0.2637045585689556,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004997505133539738,
|
|
"loss": 6.76,
|
|
"mean_token_accuracy": 0.14340940490365028,
|
|
"num_tokens": 5790435.0,
|
|
"step": 2285
|
|
},
|
|
{
|
|
"entropy": 6.930182981491089,
|
|
"epoch": 0.2642815926139642,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004997485668910476,
|
|
"loss": 6.7483,
|
|
"mean_token_accuracy": 0.14692381769418716,
|
|
"num_tokens": 5803517.0,
|
|
"step": 2290
|
|
},
|
|
{
|
|
"entropy": 6.785097646713257,
|
|
"epoch": 0.26485862665897286,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004997466128688151,
|
|
"loss": 6.7016,
|
|
"mean_token_accuracy": 0.15636104047298433,
|
|
"num_tokens": 5815802.0,
|
|
"step": 2295
|
|
},
|
|
{
|
|
"entropy": 6.829444026947021,
|
|
"epoch": 0.26543566070398156,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.000499744651287342,
|
|
"loss": 6.7371,
|
|
"mean_token_accuracy": 0.1466741144657135,
|
|
"num_tokens": 5827807.0,
|
|
"step": 2300
|
|
},
|
|
{
|
|
"entropy": 6.863865900039673,
|
|
"epoch": 0.2660126947489902,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.000499742682146694,
|
|
"loss": 6.7391,
|
|
"mean_token_accuracy": 0.14884627610445023,
|
|
"num_tokens": 5840759.0,
|
|
"step": 2305
|
|
},
|
|
{
|
|
"entropy": 6.915482997894287,
|
|
"epoch": 0.26658972879399884,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004997407054469377,
|
|
"loss": 6.7772,
|
|
"mean_token_accuracy": 0.14534752815961838,
|
|
"num_tokens": 5853117.0,
|
|
"step": 2310
|
|
},
|
|
{
|
|
"entropy": 6.74487190246582,
|
|
"epoch": 0.2671667628390075,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004997387211881392,
|
|
"loss": 6.6864,
|
|
"mean_token_accuracy": 0.15353853702545167,
|
|
"num_tokens": 5866717.0,
|
|
"step": 2315
|
|
},
|
|
{
|
|
"entropy": 6.883811712265015,
|
|
"epoch": 0.26774379688401617,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004997367293703656,
|
|
"loss": 6.7412,
|
|
"mean_token_accuracy": 0.14999326467514038,
|
|
"num_tokens": 5879017.0,
|
|
"step": 2320
|
|
},
|
|
{
|
|
"entropy": 6.83184404373169,
|
|
"epoch": 0.2683208309290248,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004997347299936837,
|
|
"loss": 6.7185,
|
|
"mean_token_accuracy": 0.14858803004026414,
|
|
"num_tokens": 5891481.0,
|
|
"step": 2325
|
|
},
|
|
{
|
|
"entropy": 6.848265933990478,
|
|
"epoch": 0.26889786497403345,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004997327230581608,
|
|
"loss": 6.7359,
|
|
"mean_token_accuracy": 0.1505471758544445,
|
|
"num_tokens": 5903389.0,
|
|
"step": 2330
|
|
},
|
|
{
|
|
"entropy": 6.828605127334595,
|
|
"epoch": 0.26947489901904215,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004997307085638644,
|
|
"loss": 6.6471,
|
|
"mean_token_accuracy": 0.14687670022249222,
|
|
"num_tokens": 5916084.0,
|
|
"step": 2335
|
|
},
|
|
{
|
|
"entropy": 6.8207825183868405,
|
|
"epoch": 0.2700519330640508,
|
|
"grad_norm": 0.74609375,
|
|
"learning_rate": 0.0004997286865108621,
|
|
"loss": 6.6947,
|
|
"mean_token_accuracy": 0.14965061396360396,
|
|
"num_tokens": 5927797.0,
|
|
"step": 2340
|
|
},
|
|
{
|
|
"entropy": 6.725537252426148,
|
|
"epoch": 0.2706289671090594,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004997266568992222,
|
|
"loss": 6.602,
|
|
"mean_token_accuracy": 0.15474189966917037,
|
|
"num_tokens": 5941886.0,
|
|
"step": 2345
|
|
},
|
|
{
|
|
"entropy": 6.837874221801758,
|
|
"epoch": 0.27120600115406807,
|
|
"grad_norm": 0.7890625,
|
|
"learning_rate": 0.0004997246197290128,
|
|
"loss": 6.7189,
|
|
"mean_token_accuracy": 0.1519598752260208,
|
|
"num_tokens": 5953655.0,
|
|
"step": 2350
|
|
},
|
|
{
|
|
"entropy": 6.989822483062744,
|
|
"epoch": 0.27178303519907676,
|
|
"grad_norm": 0.80078125,
|
|
"learning_rate": 0.0004997225750003024,
|
|
"loss": 6.7316,
|
|
"mean_token_accuracy": 0.14648340493440629,
|
|
"num_tokens": 5967818.0,
|
|
"step": 2355
|
|
},
|
|
{
|
|
"entropy": 6.777784395217895,
|
|
"epoch": 0.2723600692440854,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004997205227131599,
|
|
"loss": 6.6877,
|
|
"mean_token_accuracy": 0.15397463142871856,
|
|
"num_tokens": 5980742.0,
|
|
"step": 2360
|
|
},
|
|
{
|
|
"entropy": 6.8580399513244625,
|
|
"epoch": 0.27293710328909404,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004997184628676542,
|
|
"loss": 6.7001,
|
|
"mean_token_accuracy": 0.1460026979446411,
|
|
"num_tokens": 5993263.0,
|
|
"step": 2365
|
|
},
|
|
{
|
|
"entropy": 6.879456043243408,
|
|
"epoch": 0.27351413733410274,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004997163954638546,
|
|
"loss": 6.794,
|
|
"mean_token_accuracy": 0.13860531225800515,
|
|
"num_tokens": 6007820.0,
|
|
"step": 2370
|
|
},
|
|
{
|
|
"entropy": 6.88253002166748,
|
|
"epoch": 0.2740911713791114,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004997143205018306,
|
|
"loss": 6.736,
|
|
"mean_token_accuracy": 0.14723660051822662,
|
|
"num_tokens": 6020665.0,
|
|
"step": 2375
|
|
},
|
|
{
|
|
"entropy": 6.853304862976074,
|
|
"epoch": 0.27466820542412,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004997122379816523,
|
|
"loss": 6.6706,
|
|
"mean_token_accuracy": 0.15280609726905822,
|
|
"num_tokens": 6032847.0,
|
|
"step": 2380
|
|
},
|
|
{
|
|
"entropy": 6.813856410980224,
|
|
"epoch": 0.27524523946912866,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004997101479033893,
|
|
"loss": 6.7285,
|
|
"mean_token_accuracy": 0.14313747137784957,
|
|
"num_tokens": 6045291.0,
|
|
"step": 2385
|
|
},
|
|
{
|
|
"entropy": 6.841581058502197,
|
|
"epoch": 0.27582227351413735,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004997080502671122,
|
|
"loss": 6.7033,
|
|
"mean_token_accuracy": 0.14931570738554,
|
|
"num_tokens": 6057872.0,
|
|
"step": 2390
|
|
},
|
|
{
|
|
"entropy": 6.79990816116333,
|
|
"epoch": 0.276399307559146,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004997059450728913,
|
|
"loss": 6.6866,
|
|
"mean_token_accuracy": 0.15096329003572465,
|
|
"num_tokens": 6070252.0,
|
|
"step": 2395
|
|
},
|
|
{
|
|
"entropy": 6.918078327178955,
|
|
"epoch": 0.27697634160415463,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004997038323207977,
|
|
"loss": 6.7697,
|
|
"mean_token_accuracy": 0.14049090892076493,
|
|
"num_tokens": 6083728.0,
|
|
"step": 2400
|
|
},
|
|
{
|
|
"entropy": 6.816164302825928,
|
|
"epoch": 0.2775533756491633,
|
|
"grad_norm": 0.80078125,
|
|
"learning_rate": 0.0004997017120109022,
|
|
"loss": 6.7161,
|
|
"mean_token_accuracy": 0.14372968971729277,
|
|
"num_tokens": 6097140.0,
|
|
"step": 2405
|
|
},
|
|
{
|
|
"entropy": 6.773523044586182,
|
|
"epoch": 0.27813040969417197,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004996995841432762,
|
|
"loss": 6.6932,
|
|
"mean_token_accuracy": 0.14606269001960753,
|
|
"num_tokens": 6109518.0,
|
|
"step": 2410
|
|
},
|
|
{
|
|
"entropy": 6.870539903640747,
|
|
"epoch": 0.2787074437391806,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004996974487179915,
|
|
"loss": 6.6722,
|
|
"mean_token_accuracy": 0.1518884226679802,
|
|
"num_tokens": 6122160.0,
|
|
"step": 2415
|
|
},
|
|
{
|
|
"entropy": 6.702911806106568,
|
|
"epoch": 0.27928447778418924,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004996953057351195,
|
|
"loss": 6.7244,
|
|
"mean_token_accuracy": 0.14826845824718476,
|
|
"num_tokens": 6134638.0,
|
|
"step": 2420
|
|
},
|
|
{
|
|
"entropy": 6.88034405708313,
|
|
"epoch": 0.27986151182919794,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004996931551947327,
|
|
"loss": 6.7612,
|
|
"mean_token_accuracy": 0.14381736442446708,
|
|
"num_tokens": 6147142.0,
|
|
"step": 2425
|
|
},
|
|
{
|
|
"entropy": 6.940686750411987,
|
|
"epoch": 0.2804385458742066,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004996909970969031,
|
|
"loss": 6.7526,
|
|
"mean_token_accuracy": 0.1503518268465996,
|
|
"num_tokens": 6159137.0,
|
|
"step": 2430
|
|
},
|
|
{
|
|
"entropy": 6.719251680374145,
|
|
"epoch": 0.2810155799192152,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004996888314417034,
|
|
"loss": 6.7423,
|
|
"mean_token_accuracy": 0.1468128316104412,
|
|
"num_tokens": 6171663.0,
|
|
"step": 2435
|
|
},
|
|
{
|
|
"entropy": 6.958425569534302,
|
|
"epoch": 0.2815926139642239,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004996866582292067,
|
|
"loss": 6.7465,
|
|
"mean_token_accuracy": 0.15097531378269197,
|
|
"num_tokens": 6184282.0,
|
|
"step": 2440
|
|
},
|
|
{
|
|
"entropy": 6.830920457839966,
|
|
"epoch": 0.28216964800923255,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004996844774594856,
|
|
"loss": 6.7386,
|
|
"mean_token_accuracy": 0.14542510211467743,
|
|
"num_tokens": 6197243.0,
|
|
"step": 2445
|
|
},
|
|
{
|
|
"entropy": 6.791044044494629,
|
|
"epoch": 0.2827466820542412,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004996822891326138,
|
|
"loss": 6.6572,
|
|
"mean_token_accuracy": 0.14865050166845323,
|
|
"num_tokens": 6209061.0,
|
|
"step": 2450
|
|
},
|
|
{
|
|
"entropy": 6.817491722106934,
|
|
"epoch": 0.28332371609924983,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004996800932486648,
|
|
"loss": 6.641,
|
|
"mean_token_accuracy": 0.1513649955391884,
|
|
"num_tokens": 6223497.0,
|
|
"step": 2455
|
|
},
|
|
{
|
|
"entropy": 6.7723153591156,
|
|
"epoch": 0.28390075014425853,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004996778898077126,
|
|
"loss": 6.6669,
|
|
"mean_token_accuracy": 0.15665484070777894,
|
|
"num_tokens": 6236395.0,
|
|
"step": 2460
|
|
},
|
|
{
|
|
"entropy": 6.745643424987793,
|
|
"epoch": 0.28447778418926717,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004996756788098309,
|
|
"loss": 6.6425,
|
|
"mean_token_accuracy": 0.1522977739572525,
|
|
"num_tokens": 6248700.0,
|
|
"step": 2465
|
|
},
|
|
{
|
|
"entropy": 6.87175989151001,
|
|
"epoch": 0.2850548182342758,
|
|
"grad_norm": 0.76953125,
|
|
"learning_rate": 0.0004996734602550945,
|
|
"loss": 6.6899,
|
|
"mean_token_accuracy": 0.14756119549274443,
|
|
"num_tokens": 6262728.0,
|
|
"step": 2470
|
|
},
|
|
{
|
|
"entropy": 6.705410718917847,
|
|
"epoch": 0.2856318522792845,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004996712341435779,
|
|
"loss": 6.6553,
|
|
"mean_token_accuracy": 0.14883957505226136,
|
|
"num_tokens": 6276007.0,
|
|
"step": 2475
|
|
},
|
|
{
|
|
"entropy": 6.898572158813477,
|
|
"epoch": 0.28620888632429314,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004996690004753559,
|
|
"loss": 6.7871,
|
|
"mean_token_accuracy": 0.14304396212100984,
|
|
"num_tokens": 6289033.0,
|
|
"step": 2480
|
|
},
|
|
{
|
|
"entropy": 6.798679208755493,
|
|
"epoch": 0.2867859203693018,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004996667592505037,
|
|
"loss": 6.7183,
|
|
"mean_token_accuracy": 0.14170958548784257,
|
|
"num_tokens": 6300994.0,
|
|
"step": 2485
|
|
},
|
|
{
|
|
"entropy": 6.767846488952637,
|
|
"epoch": 0.2873629544143104,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004996645104690967,
|
|
"loss": 6.6763,
|
|
"mean_token_accuracy": 0.15046601742506027,
|
|
"num_tokens": 6313447.0,
|
|
"step": 2490
|
|
},
|
|
{
|
|
"entropy": 6.8288219451904295,
|
|
"epoch": 0.2879399884593191,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004996622541312103,
|
|
"loss": 6.6737,
|
|
"mean_token_accuracy": 0.15016402155160904,
|
|
"num_tokens": 6326622.0,
|
|
"step": 2495
|
|
},
|
|
{
|
|
"entropy": 6.799957323074341,
|
|
"epoch": 0.28851702250432776,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004996599902369207,
|
|
"loss": 6.6845,
|
|
"mean_token_accuracy": 0.14732487350702286,
|
|
"num_tokens": 6339286.0,
|
|
"step": 2500
|
|
},
|
|
{
|
|
"entropy": 6.783337116241455,
|
|
"epoch": 0.2890940565493364,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004996577187863039,
|
|
"loss": 6.6882,
|
|
"mean_token_accuracy": 0.14488342702388762,
|
|
"num_tokens": 6351869.0,
|
|
"step": 2505
|
|
},
|
|
{
|
|
"entropy": 6.761418199539184,
|
|
"epoch": 0.2896710905943451,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004996554397794364,
|
|
"loss": 6.623,
|
|
"mean_token_accuracy": 0.1587457537651062,
|
|
"num_tokens": 6363974.0,
|
|
"step": 2510
|
|
},
|
|
{
|
|
"entropy": 6.773473787307739,
|
|
"epoch": 0.29024812463935373,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.0004996531532163947,
|
|
"loss": 6.6119,
|
|
"mean_token_accuracy": 0.1547771155834198,
|
|
"num_tokens": 6376569.0,
|
|
"step": 2515
|
|
},
|
|
{
|
|
"entropy": 6.77434344291687,
|
|
"epoch": 0.2908251586843624,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004996508590972558,
|
|
"loss": 6.6397,
|
|
"mean_token_accuracy": 0.15693849921226502,
|
|
"num_tokens": 6388830.0,
|
|
"step": 2520
|
|
},
|
|
{
|
|
"entropy": 6.750413084030152,
|
|
"epoch": 0.291402192729371,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004996485574220969,
|
|
"loss": 6.6441,
|
|
"mean_token_accuracy": 0.14794425517320633,
|
|
"num_tokens": 6401542.0,
|
|
"step": 2525
|
|
},
|
|
{
|
|
"entropy": 6.694020843505859,
|
|
"epoch": 0.2919792267743797,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004996462481909953,
|
|
"loss": 6.6248,
|
|
"mean_token_accuracy": 0.1506824940443039,
|
|
"num_tokens": 6414123.0,
|
|
"step": 2530
|
|
},
|
|
{
|
|
"entropy": 6.8416389465332035,
|
|
"epoch": 0.29255626081938835,
|
|
"grad_norm": 0.7890625,
|
|
"learning_rate": 0.0004996439314040287,
|
|
"loss": 6.6858,
|
|
"mean_token_accuracy": 0.14844510704278946,
|
|
"num_tokens": 6427269.0,
|
|
"step": 2535
|
|
},
|
|
{
|
|
"entropy": 6.79074239730835,
|
|
"epoch": 0.293133294864397,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.000499641607061275,
|
|
"loss": 6.758,
|
|
"mean_token_accuracy": 0.1483464166522026,
|
|
"num_tokens": 6442296.0,
|
|
"step": 2540
|
|
},
|
|
{
|
|
"entropy": 6.821115922927857,
|
|
"epoch": 0.2937103289094057,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004996392751628126,
|
|
"loss": 6.7614,
|
|
"mean_token_accuracy": 0.14189203828573227,
|
|
"num_tokens": 6456954.0,
|
|
"step": 2545
|
|
},
|
|
{
|
|
"entropy": 6.866867971420288,
|
|
"epoch": 0.2942873629544143,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004996369357087196,
|
|
"loss": 6.7358,
|
|
"mean_token_accuracy": 0.14389990866184235,
|
|
"num_tokens": 6470139.0,
|
|
"step": 2550
|
|
},
|
|
{
|
|
"entropy": 6.869349193572998,
|
|
"epoch": 0.29486439699942296,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.000499634588699075,
|
|
"loss": 6.6721,
|
|
"mean_token_accuracy": 0.15112345814704894,
|
|
"num_tokens": 6483106.0,
|
|
"step": 2555
|
|
},
|
|
{
|
|
"entropy": 6.740794134140015,
|
|
"epoch": 0.2954414310444316,
|
|
"grad_norm": 0.77734375,
|
|
"learning_rate": 0.0004996322341339575,
|
|
"loss": 6.7031,
|
|
"mean_token_accuracy": 0.1481093369424343,
|
|
"num_tokens": 6495921.0,
|
|
"step": 2560
|
|
},
|
|
{
|
|
"entropy": 6.757239103317261,
|
|
"epoch": 0.2960184650894403,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004996298720134465,
|
|
"loss": 6.5961,
|
|
"mean_token_accuracy": 0.1495403155684471,
|
|
"num_tokens": 6508408.0,
|
|
"step": 2565
|
|
},
|
|
{
|
|
"entropy": 6.712530660629272,
|
|
"epoch": 0.29659549913444894,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004996275023376213,
|
|
"loss": 6.6843,
|
|
"mean_token_accuracy": 0.14357175007462503,
|
|
"num_tokens": 6522081.0,
|
|
"step": 2570
|
|
},
|
|
{
|
|
"entropy": 6.83108491897583,
|
|
"epoch": 0.2971725331794576,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004996251251065615,
|
|
"loss": 6.667,
|
|
"mean_token_accuracy": 0.14881591349840165,
|
|
"num_tokens": 6535065.0,
|
|
"step": 2575
|
|
},
|
|
{
|
|
"entropy": 6.745174551010132,
|
|
"epoch": 0.2977495672244662,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004996227403203473,
|
|
"loss": 6.6262,
|
|
"mean_token_accuracy": 0.15182467997074128,
|
|
"num_tokens": 6547972.0,
|
|
"step": 2580
|
|
},
|
|
{
|
|
"entropy": 6.76308388710022,
|
|
"epoch": 0.2983266012694749,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004996203479790589,
|
|
"loss": 6.6084,
|
|
"mean_token_accuracy": 0.15488889515399934,
|
|
"num_tokens": 6559935.0,
|
|
"step": 2585
|
|
},
|
|
{
|
|
"entropy": 6.758035564422608,
|
|
"epoch": 0.29890363531448355,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0004996179480827764,
|
|
"loss": 6.6027,
|
|
"mean_token_accuracy": 0.15274570137262344,
|
|
"num_tokens": 6572373.0,
|
|
"step": 2590
|
|
},
|
|
{
|
|
"entropy": 6.786394119262695,
|
|
"epoch": 0.2994806693594922,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.000499615540631581,
|
|
"loss": 6.6898,
|
|
"mean_token_accuracy": 0.15085428357124328,
|
|
"num_tokens": 6585846.0,
|
|
"step": 2595
|
|
},
|
|
{
|
|
"entropy": 6.833403587341309,
|
|
"epoch": 0.3000577034045009,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004996131256255534,
|
|
"loss": 6.7514,
|
|
"mean_token_accuracy": 0.14574786573648452,
|
|
"num_tokens": 6600387.0,
|
|
"step": 2600
|
|
},
|
|
{
|
|
"entropy": 6.733997964859009,
|
|
"epoch": 0.3006347374495095,
|
|
"grad_norm": 0.796875,
|
|
"learning_rate": 0.0004996107030647749,
|
|
"loss": 6.6546,
|
|
"mean_token_accuracy": 0.1498239278793335,
|
|
"num_tokens": 6613142.0,
|
|
"step": 2605
|
|
},
|
|
{
|
|
"entropy": 6.719230985641479,
|
|
"epoch": 0.30121177149451817,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004996082729493269,
|
|
"loss": 6.576,
|
|
"mean_token_accuracy": 0.15462903380393983,
|
|
"num_tokens": 6626273.0,
|
|
"step": 2610
|
|
},
|
|
{
|
|
"entropy": 6.811122417449951,
|
|
"epoch": 0.3017888055395268,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004996058352792913,
|
|
"loss": 6.6689,
|
|
"mean_token_accuracy": 0.14554012417793274,
|
|
"num_tokens": 6639831.0,
|
|
"step": 2615
|
|
},
|
|
{
|
|
"entropy": 6.734864568710327,
|
|
"epoch": 0.3023658395845355,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.00049960339005475,
|
|
"loss": 6.7325,
|
|
"mean_token_accuracy": 0.14520045071840287,
|
|
"num_tokens": 6652776.0,
|
|
"step": 2620
|
|
},
|
|
{
|
|
"entropy": 6.930051994323731,
|
|
"epoch": 0.30294287362954414,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004996009372757852,
|
|
"loss": 6.6974,
|
|
"mean_token_accuracy": 0.14814985245466233,
|
|
"num_tokens": 6665465.0,
|
|
"step": 2625
|
|
},
|
|
{
|
|
"entropy": 6.608390140533447,
|
|
"epoch": 0.3035199076745528,
|
|
"grad_norm": 0.79296875,
|
|
"learning_rate": 0.0004995984769424795,
|
|
"loss": 6.5622,
|
|
"mean_token_accuracy": 0.16428658366203308,
|
|
"num_tokens": 6677472.0,
|
|
"step": 2630
|
|
},
|
|
{
|
|
"entropy": 6.680166530609131,
|
|
"epoch": 0.3040969417195615,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004995960090549155,
|
|
"loss": 6.5869,
|
|
"mean_token_accuracy": 0.15190582871437072,
|
|
"num_tokens": 6689145.0,
|
|
"step": 2635
|
|
},
|
|
{
|
|
"entropy": 6.766489934921265,
|
|
"epoch": 0.3046739757645701,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004995935336131764,
|
|
"loss": 6.5804,
|
|
"mean_token_accuracy": 0.15143152326345444,
|
|
"num_tokens": 6701520.0,
|
|
"step": 2640
|
|
},
|
|
{
|
|
"entropy": 6.769906234741211,
|
|
"epoch": 0.30525100980957875,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.0004995910506173452,
|
|
"loss": 6.6662,
|
|
"mean_token_accuracy": 0.1508184403181076,
|
|
"num_tokens": 6715615.0,
|
|
"step": 2645
|
|
},
|
|
{
|
|
"entropy": 6.837305879592895,
|
|
"epoch": 0.3058280438545874,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.0004995885600675059,
|
|
"loss": 6.6889,
|
|
"mean_token_accuracy": 0.14585935696959496,
|
|
"num_tokens": 6728772.0,
|
|
"step": 2650
|
|
},
|
|
{
|
|
"entropy": 6.781810855865478,
|
|
"epoch": 0.3064050778995961,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004995860619637415,
|
|
"loss": 6.6319,
|
|
"mean_token_accuracy": 0.14923317804932595,
|
|
"num_tokens": 6741454.0,
|
|
"step": 2655
|
|
},
|
|
{
|
|
"entropy": 6.709044456481934,
|
|
"epoch": 0.30698211194460473,
|
|
"grad_norm": 0.78125,
|
|
"learning_rate": 0.0004995835563061367,
|
|
"loss": 6.6654,
|
|
"mean_token_accuracy": 0.14947767108678817,
|
|
"num_tokens": 6753983.0,
|
|
"step": 2660
|
|
},
|
|
{
|
|
"entropy": 6.855918884277344,
|
|
"epoch": 0.30755914598961337,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004995810430947756,
|
|
"loss": 6.7013,
|
|
"mean_token_accuracy": 0.14999711960554124,
|
|
"num_tokens": 6767377.0,
|
|
"step": 2665
|
|
},
|
|
{
|
|
"entropy": 6.7711738586425785,
|
|
"epoch": 0.30813618003462206,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004995785223297426,
|
|
"loss": 6.6499,
|
|
"mean_token_accuracy": 0.15468411445617675,
|
|
"num_tokens": 6779220.0,
|
|
"step": 2670
|
|
},
|
|
{
|
|
"entropy": 6.8247597217559814,
|
|
"epoch": 0.3087132140796307,
|
|
"grad_norm": 0.796875,
|
|
"learning_rate": 0.0004995759940111225,
|
|
"loss": 6.6286,
|
|
"mean_token_accuracy": 0.15276417881250381,
|
|
"num_tokens": 6792202.0,
|
|
"step": 2675
|
|
},
|
|
{
|
|
"entropy": 6.6788218975067135,
|
|
"epoch": 0.30929024812463934,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004995734581390005,
|
|
"loss": 6.6376,
|
|
"mean_token_accuracy": 0.15422565937042237,
|
|
"num_tokens": 6804988.0,
|
|
"step": 2680
|
|
},
|
|
{
|
|
"entropy": 6.736396455764771,
|
|
"epoch": 0.309867282169648,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004995709147134617,
|
|
"loss": 6.6538,
|
|
"mean_token_accuracy": 0.14916067719459533,
|
|
"num_tokens": 6817311.0,
|
|
"step": 2685
|
|
},
|
|
{
|
|
"entropy": 6.789905023574829,
|
|
"epoch": 0.3104443162146567,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.0004995683637345919,
|
|
"loss": 6.6367,
|
|
"mean_token_accuracy": 0.1507313832640648,
|
|
"num_tokens": 6829875.0,
|
|
"step": 2690
|
|
},
|
|
{
|
|
"entropy": 6.814420080184936,
|
|
"epoch": 0.3110213502596653,
|
|
"grad_norm": 0.79296875,
|
|
"learning_rate": 0.0004995658052024765,
|
|
"loss": 6.6156,
|
|
"mean_token_accuracy": 0.15454477518796922,
|
|
"num_tokens": 6843080.0,
|
|
"step": 2695
|
|
},
|
|
{
|
|
"entropy": 6.697454023361206,
|
|
"epoch": 0.31159838430467396,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004995632391172019,
|
|
"loss": 6.6061,
|
|
"mean_token_accuracy": 0.1518676370382309,
|
|
"num_tokens": 6857202.0,
|
|
"step": 2700
|
|
},
|
|
{
|
|
"entropy": 6.774089813232422,
|
|
"epoch": 0.31217541834968265,
|
|
"grad_norm": 0.77734375,
|
|
"learning_rate": 0.0004995606654788543,
|
|
"loss": 6.6958,
|
|
"mean_token_accuracy": 0.14331221878528594,
|
|
"num_tokens": 6870801.0,
|
|
"step": 2705
|
|
},
|
|
{
|
|
"entropy": 6.790430974960327,
|
|
"epoch": 0.3127524523946913,
|
|
"grad_norm": 0.77734375,
|
|
"learning_rate": 0.0004995580842875202,
|
|
"loss": 6.642,
|
|
"mean_token_accuracy": 0.1496342271566391,
|
|
"num_tokens": 6883084.0,
|
|
"step": 2710
|
|
},
|
|
{
|
|
"entropy": 6.821096277236938,
|
|
"epoch": 0.31332948643969993,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004995554955432866,
|
|
"loss": 6.6693,
|
|
"mean_token_accuracy": 0.14794540405273438,
|
|
"num_tokens": 6895309.0,
|
|
"step": 2715
|
|
},
|
|
{
|
|
"entropy": 6.7353767395019535,
|
|
"epoch": 0.3139065204847086,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004995528992462404,
|
|
"loss": 6.6427,
|
|
"mean_token_accuracy": 0.15779228061437606,
|
|
"num_tokens": 6907646.0,
|
|
"step": 2720
|
|
},
|
|
{
|
|
"entropy": 6.766403102874756,
|
|
"epoch": 0.31448355452971727,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.000499550295396469,
|
|
"loss": 6.6185,
|
|
"mean_token_accuracy": 0.1583697885274887,
|
|
"num_tokens": 6919769.0,
|
|
"step": 2725
|
|
},
|
|
{
|
|
"entropy": 6.680029249191284,
|
|
"epoch": 0.3150605885747259,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004995476839940598,
|
|
"loss": 6.581,
|
|
"mean_token_accuracy": 0.15339329093694687,
|
|
"num_tokens": 6933348.0,
|
|
"step": 2730
|
|
},
|
|
{
|
|
"entropy": 6.785920238494873,
|
|
"epoch": 0.31563762261973455,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.000499545065039101,
|
|
"loss": 6.6585,
|
|
"mean_token_accuracy": 0.14711489379405976,
|
|
"num_tokens": 6945105.0,
|
|
"step": 2735
|
|
},
|
|
{
|
|
"entropy": 6.736616373062134,
|
|
"epoch": 0.31621465666474324,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004995424385316803,
|
|
"loss": 6.6561,
|
|
"mean_token_accuracy": 0.14591162502765656,
|
|
"num_tokens": 6958009.0,
|
|
"step": 2740
|
|
},
|
|
{
|
|
"entropy": 6.748479509353638,
|
|
"epoch": 0.3167916907097519,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004995398044718863,
|
|
"loss": 6.5594,
|
|
"mean_token_accuracy": 0.15630290359258653,
|
|
"num_tokens": 6970156.0,
|
|
"step": 2745
|
|
},
|
|
{
|
|
"entropy": 6.710201978683472,
|
|
"epoch": 0.3173687247547605,
|
|
"grad_norm": 0.80078125,
|
|
"learning_rate": 0.0004995371628598074,
|
|
"loss": 6.6478,
|
|
"mean_token_accuracy": 0.15026513785123824,
|
|
"num_tokens": 6983431.0,
|
|
"step": 2750
|
|
},
|
|
{
|
|
"entropy": 6.806408214569092,
|
|
"epoch": 0.31794575879976916,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004995345136955328,
|
|
"loss": 6.6938,
|
|
"mean_token_accuracy": 0.14544053599238396,
|
|
"num_tokens": 6997470.0,
|
|
"step": 2755
|
|
},
|
|
{
|
|
"entropy": 6.746524286270142,
|
|
"epoch": 0.31852279284477786,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004995318569791512,
|
|
"loss": 6.6371,
|
|
"mean_token_accuracy": 0.15571504682302476,
|
|
"num_tokens": 7010337.0,
|
|
"step": 2760
|
|
},
|
|
{
|
|
"entropy": 6.8036500930786135,
|
|
"epoch": 0.3190998268897865,
|
|
"grad_norm": 0.76171875,
|
|
"learning_rate": 0.0004995291927107522,
|
|
"loss": 6.6618,
|
|
"mean_token_accuracy": 0.1454496204853058,
|
|
"num_tokens": 7023950.0,
|
|
"step": 2765
|
|
},
|
|
{
|
|
"entropy": 6.689703798294067,
|
|
"epoch": 0.31967686093479514,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004995265208904252,
|
|
"loss": 6.6302,
|
|
"mean_token_accuracy": 0.15477116107940675,
|
|
"num_tokens": 7036409.0,
|
|
"step": 2770
|
|
},
|
|
{
|
|
"entropy": 6.779079484939575,
|
|
"epoch": 0.32025389497980383,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004995238415182603,
|
|
"loss": 6.6425,
|
|
"mean_token_accuracy": 0.1460179179906845,
|
|
"num_tokens": 7049409.0,
|
|
"step": 2775
|
|
},
|
|
{
|
|
"entropy": 6.785402870178222,
|
|
"epoch": 0.3208309290248125,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004995211545943476,
|
|
"loss": 6.6862,
|
|
"mean_token_accuracy": 0.15174451917409898,
|
|
"num_tokens": 7062120.0,
|
|
"step": 2780
|
|
},
|
|
{
|
|
"entropy": 6.77389817237854,
|
|
"epoch": 0.3214079630698211,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004995184601187772,
|
|
"loss": 6.6715,
|
|
"mean_token_accuracy": 0.1446915090084076,
|
|
"num_tokens": 7073150.0,
|
|
"step": 2785
|
|
},
|
|
{
|
|
"entropy": 6.756207847595215,
|
|
"epoch": 0.32198499711482975,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.00049951575809164,
|
|
"loss": 6.6123,
|
|
"mean_token_accuracy": 0.14350593835115433,
|
|
"num_tokens": 7085927.0,
|
|
"step": 2790
|
|
},
|
|
{
|
|
"entropy": 6.743623447418213,
|
|
"epoch": 0.32256203115983845,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004995130485130269,
|
|
"loss": 6.6799,
|
|
"mean_token_accuracy": 0.1505696654319763,
|
|
"num_tokens": 7097607.0,
|
|
"step": 2795
|
|
},
|
|
{
|
|
"entropy": 6.801728105545044,
|
|
"epoch": 0.3231390652048471,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004995103313830289,
|
|
"loss": 6.591,
|
|
"mean_token_accuracy": 0.1520095705986023,
|
|
"num_tokens": 7109771.0,
|
|
"step": 2800
|
|
},
|
|
{
|
|
"entropy": 6.725235414505005,
|
|
"epoch": 0.3237160992498557,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004995076067017373,
|
|
"loss": 6.6574,
|
|
"mean_token_accuracy": 0.14673417136073114,
|
|
"num_tokens": 7122757.0,
|
|
"step": 2805
|
|
},
|
|
{
|
|
"entropy": 6.721699571609497,
|
|
"epoch": 0.3242931332948644,
|
|
"grad_norm": 0.79296875,
|
|
"learning_rate": 0.0004995048744692439,
|
|
"loss": 6.6415,
|
|
"mean_token_accuracy": 0.14944978207349777,
|
|
"num_tokens": 7135516.0,
|
|
"step": 2810
|
|
},
|
|
{
|
|
"entropy": 6.755308294296265,
|
|
"epoch": 0.32487016733987306,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004995021346856405,
|
|
"loss": 6.7226,
|
|
"mean_token_accuracy": 0.1461216315627098,
|
|
"num_tokens": 7149125.0,
|
|
"step": 2815
|
|
},
|
|
{
|
|
"entropy": 6.745944166183472,
|
|
"epoch": 0.3254472013848817,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004994993873510196,
|
|
"loss": 6.6727,
|
|
"mean_token_accuracy": 0.14473605155944824,
|
|
"num_tokens": 7160723.0,
|
|
"step": 2820
|
|
},
|
|
{
|
|
"entropy": 6.771013927459717,
|
|
"epoch": 0.32602423542989034,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004994966324654731,
|
|
"loss": 6.6407,
|
|
"mean_token_accuracy": 0.14543287828564644,
|
|
"num_tokens": 7174551.0,
|
|
"step": 2825
|
|
},
|
|
{
|
|
"entropy": 6.802860164642334,
|
|
"epoch": 0.32660126947489904,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.000499493870029094,
|
|
"loss": 6.6193,
|
|
"mean_token_accuracy": 0.14886424392461778,
|
|
"num_tokens": 7186764.0,
|
|
"step": 2830
|
|
},
|
|
{
|
|
"entropy": 6.7293703079223635,
|
|
"epoch": 0.3271783035199077,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004994911000419749,
|
|
"loss": 6.6135,
|
|
"mean_token_accuracy": 0.1525777131319046,
|
|
"num_tokens": 7199645.0,
|
|
"step": 2835
|
|
},
|
|
{
|
|
"entropy": 6.685914325714111,
|
|
"epoch": 0.3277553375649163,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004994883225042093,
|
|
"loss": 6.5341,
|
|
"mean_token_accuracy": 0.16299870759248733,
|
|
"num_tokens": 7212579.0,
|
|
"step": 2840
|
|
},
|
|
{
|
|
"entropy": 6.696114015579224,
|
|
"epoch": 0.328332371609925,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004994855374158905,
|
|
"loss": 6.5716,
|
|
"mean_token_accuracy": 0.15522724390029907,
|
|
"num_tokens": 7225139.0,
|
|
"step": 2845
|
|
},
|
|
{
|
|
"entropy": 6.791204595565796,
|
|
"epoch": 0.32890940565493365,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.000499482744777112,
|
|
"loss": 6.7228,
|
|
"mean_token_accuracy": 0.142743781208992,
|
|
"num_tokens": 7239220.0,
|
|
"step": 2850
|
|
},
|
|
{
|
|
"entropy": 6.822061014175415,
|
|
"epoch": 0.3294864396999423,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.000499479944587968,
|
|
"loss": 6.7418,
|
|
"mean_token_accuracy": 0.1484747812151909,
|
|
"num_tokens": 7252613.0,
|
|
"step": 2855
|
|
},
|
|
{
|
|
"entropy": 6.678646373748779,
|
|
"epoch": 0.33006347374495093,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004994771368485526,
|
|
"loss": 6.5736,
|
|
"mean_token_accuracy": 0.15565900206565858,
|
|
"num_tokens": 7263658.0,
|
|
"step": 2860
|
|
},
|
|
{
|
|
"entropy": 6.7811792373657225,
|
|
"epoch": 0.3306405077899596,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004994743215589602,
|
|
"loss": 6.5885,
|
|
"mean_token_accuracy": 0.1597794234752655,
|
|
"num_tokens": 7275782.0,
|
|
"step": 2865
|
|
},
|
|
{
|
|
"entropy": 6.614157962799072,
|
|
"epoch": 0.33121754183496827,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004994714987192854,
|
|
"loss": 6.6449,
|
|
"mean_token_accuracy": 0.15721748024225235,
|
|
"num_tokens": 7288536.0,
|
|
"step": 2870
|
|
},
|
|
{
|
|
"entropy": 6.73630838394165,
|
|
"epoch": 0.3317945758799769,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004994686683296234,
|
|
"loss": 6.6077,
|
|
"mean_token_accuracy": 0.15456028878688813,
|
|
"num_tokens": 7300480.0,
|
|
"step": 2875
|
|
},
|
|
{
|
|
"entropy": 6.709596300125122,
|
|
"epoch": 0.3323716099249856,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.0004994658303900691,
|
|
"loss": 6.6456,
|
|
"mean_token_accuracy": 0.15098604261875154,
|
|
"num_tokens": 7313168.0,
|
|
"step": 2880
|
|
},
|
|
{
|
|
"entropy": 6.666839075088501,
|
|
"epoch": 0.33294864396999424,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004994629849007182,
|
|
"loss": 6.6031,
|
|
"mean_token_accuracy": 0.15539678037166596,
|
|
"num_tokens": 7327347.0,
|
|
"step": 2885
|
|
},
|
|
{
|
|
"entropy": 6.813637113571167,
|
|
"epoch": 0.3335256780150029,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004994601318616663,
|
|
"loss": 6.6433,
|
|
"mean_token_accuracy": 0.1485406205058098,
|
|
"num_tokens": 7339955.0,
|
|
"step": 2890
|
|
},
|
|
{
|
|
"entropy": 6.741922521591187,
|
|
"epoch": 0.3341027120600115,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004994572712730092,
|
|
"loss": 6.6214,
|
|
"mean_token_accuracy": 0.15295621007680893,
|
|
"num_tokens": 7353586.0,
|
|
"step": 2895
|
|
},
|
|
{
|
|
"entropy": 6.6835249900817875,
|
|
"epoch": 0.3346797461050202,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004994544031348434,
|
|
"loss": 6.6024,
|
|
"mean_token_accuracy": 0.152432219684124,
|
|
"num_tokens": 7365802.0,
|
|
"step": 2900
|
|
},
|
|
{
|
|
"entropy": 6.729006338119507,
|
|
"epoch": 0.33525678015002885,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004994515274472653,
|
|
"loss": 6.5619,
|
|
"mean_token_accuracy": 0.14667018949985505,
|
|
"num_tokens": 7377864.0,
|
|
"step": 2905
|
|
},
|
|
{
|
|
"entropy": 6.67462158203125,
|
|
"epoch": 0.3358338141950375,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.0004994486442103715,
|
|
"loss": 6.5129,
|
|
"mean_token_accuracy": 0.15633828938007355,
|
|
"num_tokens": 7389921.0,
|
|
"step": 2910
|
|
},
|
|
{
|
|
"entropy": 6.713885641098022,
|
|
"epoch": 0.3364108482400462,
|
|
"grad_norm": 0.78125,
|
|
"learning_rate": 0.000499445753424259,
|
|
"loss": 6.5734,
|
|
"mean_token_accuracy": 0.15145887583494186,
|
|
"num_tokens": 7402765.0,
|
|
"step": 2915
|
|
},
|
|
{
|
|
"entropy": 6.767501354217529,
|
|
"epoch": 0.33698788228505483,
|
|
"grad_norm": 0.7578125,
|
|
"learning_rate": 0.0004994428550890251,
|
|
"loss": 6.5914,
|
|
"mean_token_accuracy": 0.14778004884719848,
|
|
"num_tokens": 7416330.0,
|
|
"step": 2920
|
|
},
|
|
{
|
|
"entropy": 6.617673254013061,
|
|
"epoch": 0.33756491633006347,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.0004994399492047672,
|
|
"loss": 6.5484,
|
|
"mean_token_accuracy": 0.16363891512155532,
|
|
"num_tokens": 7428701.0,
|
|
"step": 2925
|
|
},
|
|
{
|
|
"entropy": 6.790898227691651,
|
|
"epoch": 0.3381419503750721,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004994370357715832,
|
|
"loss": 6.5492,
|
|
"mean_token_accuracy": 0.1558838188648224,
|
|
"num_tokens": 7440687.0,
|
|
"step": 2930
|
|
},
|
|
{
|
|
"entropy": 6.691900014877319,
|
|
"epoch": 0.3387189844200808,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.000499434114789571,
|
|
"loss": 6.6532,
|
|
"mean_token_accuracy": 0.14500061124563218,
|
|
"num_tokens": 7454448.0,
|
|
"step": 2935
|
|
},
|
|
{
|
|
"entropy": 6.795220136642456,
|
|
"epoch": 0.33929601846508944,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004994311862588286,
|
|
"loss": 6.5717,
|
|
"mean_token_accuracy": 0.15572112798690796,
|
|
"num_tokens": 7466722.0,
|
|
"step": 2940
|
|
},
|
|
{
|
|
"entropy": 6.66687707901001,
|
|
"epoch": 0.3398730525100981,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004994282501794551,
|
|
"loss": 6.5761,
|
|
"mean_token_accuracy": 0.1562015950679779,
|
|
"num_tokens": 7478574.0,
|
|
"step": 2945
|
|
},
|
|
{
|
|
"entropy": 6.6353167533874515,
|
|
"epoch": 0.3404500865551068,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004994253065515486,
|
|
"loss": 6.4752,
|
|
"mean_token_accuracy": 0.15674795657396318,
|
|
"num_tokens": 7490424.0,
|
|
"step": 2950
|
|
},
|
|
{
|
|
"entropy": 6.738166666030883,
|
|
"epoch": 0.3410271206001154,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004994223553752084,
|
|
"loss": 6.6116,
|
|
"mean_token_accuracy": 0.1547369971871376,
|
|
"num_tokens": 7502832.0,
|
|
"step": 2955
|
|
},
|
|
{
|
|
"entropy": 6.6372476577758786,
|
|
"epoch": 0.34160415464512406,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004994193966505339,
|
|
"loss": 6.5617,
|
|
"mean_token_accuracy": 0.15487824976444245,
|
|
"num_tokens": 7514151.0,
|
|
"step": 2960
|
|
},
|
|
{
|
|
"entropy": 6.712488985061645,
|
|
"epoch": 0.3421811886901327,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004994164303776244,
|
|
"loss": 6.5853,
|
|
"mean_token_accuracy": 0.15818527191877366,
|
|
"num_tokens": 7526877.0,
|
|
"step": 2965
|
|
},
|
|
{
|
|
"entropy": 6.701138973236084,
|
|
"epoch": 0.3427582227351414,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004994134565565797,
|
|
"loss": 6.551,
|
|
"mean_token_accuracy": 0.15412139296531677,
|
|
"num_tokens": 7538858.0,
|
|
"step": 2970
|
|
},
|
|
{
|
|
"entropy": 6.767053508758545,
|
|
"epoch": 0.34333525678015003,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004994104751875,
|
|
"loss": 6.5921,
|
|
"mean_token_accuracy": 0.154334969073534,
|
|
"num_tokens": 7550804.0,
|
|
"step": 2975
|
|
},
|
|
{
|
|
"entropy": 6.637975883483887,
|
|
"epoch": 0.3439122908251587,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004994074862704854,
|
|
"loss": 6.5323,
|
|
"mean_token_accuracy": 0.1576222226023674,
|
|
"num_tokens": 7562269.0,
|
|
"step": 2980
|
|
},
|
|
{
|
|
"entropy": 6.650318717956543,
|
|
"epoch": 0.3444893248701673,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004994044898056363,
|
|
"loss": 6.6225,
|
|
"mean_token_accuracy": 0.14792083203792572,
|
|
"num_tokens": 7573695.0,
|
|
"step": 2985
|
|
},
|
|
{
|
|
"entropy": 6.7255530834198,
|
|
"epoch": 0.345066358915176,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004994014857930538,
|
|
"loss": 6.6233,
|
|
"mean_token_accuracy": 0.14724487364292144,
|
|
"num_tokens": 7585943.0,
|
|
"step": 2990
|
|
},
|
|
{
|
|
"entropy": 6.695814752578736,
|
|
"epoch": 0.34564339296018465,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004993984742328387,
|
|
"loss": 6.6071,
|
|
"mean_token_accuracy": 0.15086225420236588,
|
|
"num_tokens": 7598326.0,
|
|
"step": 2995
|
|
},
|
|
{
|
|
"entropy": 6.731552076339722,
|
|
"epoch": 0.3462204270051933,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004993954551250925,
|
|
"loss": 6.6033,
|
|
"mean_token_accuracy": 0.148460191488266,
|
|
"num_tokens": 7609950.0,
|
|
"step": 3000
|
|
},
|
|
{
|
|
"epoch": 0.3462204270051933,
|
|
"eval_entropy": 6.558329563233064,
|
|
"eval_loss": 6.633069038391113,
|
|
"eval_mean_token_accuracy": 0.15427329348342508,
|
|
"eval_num_tokens": 7609950.0,
|
|
"eval_runtime": 17.9419,
|
|
"eval_samples_per_second": 1568.171,
|
|
"eval_steps_per_second": 196.021,
|
|
"step": 3000
|
|
}
|
|
],
|
|
"logging_steps": 5,
|
|
"max_steps": 86650,
|
|
"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": 1670144584089600.0,
|
|
"train_batch_size": 16,
|
|
"trial_name": null,
|
|
"trial_params": null
|
|
}
|